Token | , |
Token ID | 11 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
terness | +1.207 |
thur | +1.143 |
phia | +1.088 |
י� | +1.073 |
chio | +1.067 |
Neg logit contributions | |
�� | -1.058 |
Belg | -1.011 |
uss | -0.983 |
rol | -0.962 |
roid | -0.947 |
Token | � |
Token ID | 447 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
terness | +1.091 |
thur | +1.042 |
phia | +0.998 |
י� | +0.987 |
chio | +0.980 |
Neg logit contributions | |
�� | -0.695 |
Belg | -0.659 |
uss | -0.639 |
rol | -0.621 |
roid | -0.609 |
Token | � |
Token ID | 251 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
terness | +1.022 |
thur | +0.962 |
phia | +0.910 |
י� | +0.895 |
chio | +0.886 |
Neg logit contributions | |
�� | -1.138 |
Belg | -1.100 |
uss | -1.075 |
rol | -1.054 |
roid | -1.037 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
terness | +0.347 |
thur | +0.330 |
phia | +0.314 |
י� | +0.310 |
chio | +0.308 |
Neg logit contributions | |
�� | -0.286 |
Belg | -0.273 |
uss | -0.266 |
rol | -0.260 |
roid | -0.255 |
Token | C |
Token ID | 327 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
terness | +1.039 |
thur | +0.988 |
phia | +0.943 |
י� | +0.929 |
chio | +0.923 |
Neg logit contributions | |
�� | -0.845 |
Belg | -0.808 |
uss | -0.786 |
rol | -0.769 |
roid | -0.755 |
Token | OO |
Token ID | 6684 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
terness | +1.472 |
thur | +1.374 |
phia | +1.285 |
י� | +1.258 |
chio | +1.248 |
Neg logit contributions | |
�� | -2.217 |
Belg | -2.142 |
uss | -2.090 |
rol | -2.058 |
roid | -2.034 |
Token | Sher |
Token ID | 6528 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
terness | +8.610 |
thur | +8.085 |
phia | +8.069 |
TER | +8.053 |
י� | +7.956 |
Neg logit contributions | |
�� | -7.949 |
Belg | -7.369 |
uss | -7.097 |
roid | -6.966 |
rol | -6.867 |
Token | yl |
Token ID | 2645 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
terness | +0.396 |
thur | +0.369 |
phia | +0.348 |
י� | +0.343 |
chio | +0.338 |
Neg logit contributions | |
�� | -0.518 |
Belg | -0.506 |
uss | -0.496 |
rol | -0.490 |
roid | -0.481 |
Token | Sand |
Token ID | 3837 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
terness | +1.948 |
thur | +1.839 |
phia | +1.751 |
י� | +1.720 |
chio | +1.705 |
Neg logit contributions | |
�� | -1.939 |
Belg | -1.864 |
uss | -1.823 |
rol | -1.787 |
roid | -1.756 |
Token | berg |
Token ID | 3900 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
uss | +3.124 |
�� | +3.012 |
rol | +3.005 |
Belg | +3.001 |
roid | +2.884 |
Neg logit contributions | |
terness | -3.076 |
thur | -2.798 |
renheit | -2.729 |
BLIC | -2.663 |
phia | -2.651 |
Token | said |
Token ID | 531 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
terness | +3.411 |
thur | +3.262 |
phia | +3.104 |
chio | +3.094 |
י� | +3.087 |
Neg logit contributions | |
�� | -2.879 |
Belg | -2.695 |
uss | -2.596 |
rol | -2.550 |
roid | -2.518 |
Token | seen |
Token ID | 1775 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
terness | +2.873 |
thur | +2.759 |
phia | +2.636 |
י� | +2.619 |
chio | +2.606 |
Neg logit contributions | |
�� | -2.204 |
Belg | -2.047 |
uss | -1.990 |
rol | -1.943 |
roid | -1.892 |
Token | any |
Token ID | 597 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
�� | +0.552 |
Belg | +0.537 |
uss | +0.521 |
rol | +0.510 |
roid | +0.499 |
Neg logit contributions | |
terness | -0.749 |
thur | -0.710 |
phia | -0.680 |
י� | -0.669 |
renheit | -0.666 |
Token | claims |
Token ID | 3667 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
�� | +0.015 |
Belg | +0.014 |
uss | +0.014 |
rol | +0.013 |
roid | +0.013 |
Neg logit contributions | |
terness | -0.020 |
thur | -0.019 |
phia | -0.018 |
י� | -0.018 |
chio | -0.018 |
Token | yet |
Token ID | 1865 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
terness | +1.131 |
thur | +1.077 |
phia | +1.029 |
י� | +1.015 |
chio | +1.009 |
Neg logit contributions | |
�� | -0.839 |
Belg | -0.800 |
uss | -0.777 |
rol | -0.759 |
roid | -0.743 |
Token | ," |
Token ID | 553 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
�� | +0.844 |
Belg | +0.831 |
uss | +0.808 |
rol | +0.794 |
roid | +0.776 |
Neg logit contributions | |
terness | -1.202 |
thur | -1.149 |
phia | -1.098 |
י� | -1.078 |
renheit | -1.076 |
Token | Las |
Token ID | 10123 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
�� | +0.953 |
Belg | +0.938 |
uss | +0.898 |
rol | +0.885 |
roid | +0.856 |
Neg logit contributions | |
terness | -1.538 |
thur | -1.473 |
phia | -1.409 |
renheit | -1.394 |
י� | -1.385 |
Token | z |
Token ID | 89 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
terness | +6.255 |
thur | +6.230 |
chio | +5.949 |
TER | +5.878 |
phia | +5.799 |
Neg logit contributions | |
�� | -9.767 |
Belg | -8.961 |
newsp | -8.318 |
millenn | -8.165 |
heartbeat | -8.045 |
Token | ewski |
Token ID | 46151 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
terness | +2.713 |
thur | +2.596 |
chio | +2.445 |
phia | +2.435 |
י� | +2.367 |
Neg logit contributions | |
�� | -4.014 |
Belg | -3.817 |
uss | -3.589 |
rol | -3.582 |
roid | -3.563 |
Token | says |
Token ID | 1139 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
terness | +1.539 |
thur | +1.463 |
phia | +1.395 |
י� | +1.384 |
chio | +1.377 |
Neg logit contributions | |
�� | -1.208 |
Belg | -1.146 |
uss | -1.111 |
rol | -1.084 |
roid | -1.066 |
Token | . |
Token ID | 13 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
terness | +0.578 |
thur | +0.546 |
phia | +0.519 |
י� | +0.514 |
chio | +0.510 |
Neg logit contributions | |
�� | -0.511 |
Belg | -0.489 |
uss | -0.477 |
rol | -0.466 |
roid | -0.459 |
Token | " |
Token ID | 366 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
terness | +1.821 |
thur | +1.716 |
phia | +1.629 |
י� | +1.607 |
chio | +1.593 |
Neg logit contributions | |
�� | -1.894 |
Belg | -1.809 |
uss | -1.770 |
rol | -1.731 |
roid | -1.709 |
Token | carbon |
Token ID | 6588 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
terness | +0.139 |
thur | +0.131 |
phia | +0.125 |
י� | +0.124 |
chio | +0.123 |
Neg logit contributions | |
�� | -0.111 |
Belg | -0.105 |
uss | -0.103 |
rol | -0.101 |
roid | -0.099 |
Token | ation |
Token ID | 341 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
terness | +0.226 |
thur | +0.213 |
phia | +0.201 |
י� | +0.198 |
chio | +0.196 |
Neg logit contributions | |
�� | -0.255 |
Belg | -0.246 |
uss | -0.240 |
rol | -0.236 |
roid | -0.232 |
Token | . |
Token ID | 13 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
�� | +0.652 |
Belg | +0.632 |
uss | +0.616 |
rol | +0.605 |
roid | +0.593 |
Neg logit contributions | |
terness | -0.806 |
thur | -0.774 |
phia | -0.737 |
י� | -0.722 |
renheit | -0.719 |
Token | In |
Token ID | 554 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
terness | +1.544 |
thur | +1.462 |
phia | +1.390 |
י� | +1.372 |
chio | +1.361 |
Neg logit contributions | |
�� | -1.386 |
Belg | -1.322 |
uss | -1.293 |
rol | -1.266 |
roid | -1.245 |
Token | the |
Token ID | 262 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
terness | +1.405 |
thur | +1.325 |
phia | +1.263 |
י� | +1.245 |
chio | +1.245 |
Neg logit contributions | |
�� | -1.065 |
Belg | -1.003 |
uss | -0.977 |
rol | -0.960 |
roid | -0.949 |
Token | mouth |
Token ID | 5422 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
terness | +1.265 |
thur | +1.200 |
phia | +1.145 |
י� | +1.131 |
chio | +1.126 |
Neg logit contributions | |
�� | -0.952 |
Belg | -0.903 |
uss | -0.882 |
rol | -0.864 |
roid | -0.848 |
Token | it |
Token ID | 340 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
terness | +7.926 |
thur | +7.085 |
י� | +6.771 |
renheit | +6.705 |
TER | +6.590 |
Neg logit contributions | |
�� | -7.960 |
Belg | -7.274 |
roid | -7.039 |
rol | -6.994 |
uss | -6.939 |
Token | has |
Token ID | 468 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
�� | +0.221 |
Belg | +0.215 |
uss | +0.210 |
rol | +0.204 |
roid | +0.200 |
Neg logit contributions | |
terness | -0.297 |
thur | -0.283 |
phia | -0.271 |
י� | -0.267 |
renheit | -0.265 |
Token | an |
Token ID | 281 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
terness | +2.263 |
thur | +2.135 |
phia | +2.014 |
י� | +2.002 |
chio | +1.983 |
Neg logit contributions | |
�� | -1.952 |
Belg | -1.829 |
uss | -1.796 |
rol | -1.756 |
roid | -1.727 |
Token | incredibly |
Token ID | 8131 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
terness | +1.179 |
thur | +1.116 |
phia | +1.054 |
י� | +1.046 |
chio | +1.037 |
Neg logit contributions | |
�� | -0.941 |
Belg | -0.890 |
uss | -0.869 |
rol | -0.849 |
roid | -0.836 |
Token | soft |
Token ID | 2705 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
�� | +1.454 |
Belg | +1.430 |
uss | +1.375 |
rol | +1.340 |
roid | +1.298 |
Neg logit contributions | |
terness | -2.193 |
thur | -2.116 |
phia | -2.045 |
י� | -1.988 |
renheit | -1.984 |
Token | put |
Token ID | 1234 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
�� | +1.059 |
Belg | +1.048 |
uss | +1.029 |
rol | +1.003 |
roid | +0.976 |
Neg logit contributions | |
terness | -1.315 |
thur | -1.248 |
phia | -1.189 |
renheit | -1.172 |
י� | -1.164 |
Token | them |
Token ID | 606 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
�� | +1.562 |
Belg | +1.504 |
uss | +1.482 |
rol | +1.447 |
roid | +1.401 |
Neg logit contributions | |
terness | -2.542 |
thur | -2.445 |
phia | -2.339 |
י� | -2.314 |
renheit | -2.286 |
Token | in |
Token ID | 287 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
terness | +0.997 |
thur | +0.950 |
phia | +0.908 |
י� | +0.895 |
chio | +0.890 |
Neg logit contributions | |
�� | -0.744 |
Belg | -0.710 |
uss | -0.687 |
rol | -0.671 |
roid | -0.658 |
Token | with |
Token ID | 351 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
�� | +0.529 |
Belg | +0.510 |
uss | +0.499 |
rol | +0.487 |
roid | +0.478 |
Neg logit contributions | |
terness | -0.615 |
thur | -0.587 |
phia | -0.556 |
י� | -0.548 |
renheit | -0.542 |
Token | the |
Token ID | 262 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
�� | +1.439 |
Belg | +1.421 |
uss | +1.376 |
rol | +1.353 |
roid | +1.314 |
Neg logit contributions | |
terness | -1.762 |
thur | -1.688 |
phia | -1.602 |
י� | -1.569 |
renheit | -1.564 |
Token | bell |
Token ID | 8966 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
�� | +0.195 |
Belg | +0.191 |
uss | +0.185 |
rol | +0.182 |
roid | +0.178 |
Neg logit contributions | |
terness | -0.186 |
thur | -0.176 |
phia | -0.167 |
י� | -0.164 |
renheit | -0.163 |
Token | peppers |
Token ID | 31804 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
terness | +3.953 |
thur | +3.493 |
phia | +3.281 |
chio | +3.097 |
י� | +3.093 |
Neg logit contributions | |
�� | -11.628 |
Belg | -11.108 |
uss | -10.682 |
roid | -10.517 |
rol | -10.470 |
Token | . |
Token ID | 13 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
terness | +2.355 |
thur | +2.220 |
phia | +2.113 |
י� | +2.090 |
chio | +2.071 |
Neg logit contributions | |
�� | -2.200 |
Belg | -2.096 |
uss | -2.025 |
rol | -1.981 |
roid | -1.950 |
Token | Fry |
Token ID | 25305 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
terness | +0.425 |
thur | +0.404 |
phia | +0.385 |
י� | +0.378 |
chio | +0.376 |
Neg logit contributions | |
�� | -0.369 |
Belg | -0.357 |
uss | -0.347 |
rol | -0.340 |
roid | -0.333 |
Token | until |
Token ID | 1566 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
terness | +0.733 |
thur | +0.698 |
phia | +0.666 |
י� | +0.657 |
chio | +0.653 |
Neg logit contributions | |
�� | -0.562 |
Belg | -0.539 |
uss | -0.524 |
rol | -0.513 |
roid | -0.502 |
Token | the |
Token ID | 262 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
terness | +0.246 |
thur | +0.237 |
phia | +0.225 |
י� | +0.221 |
renheit | +0.221 |
Neg logit contributions | |
�� | -0.195 |
Belg | -0.187 |
uss | -0.183 |
rol | -0.179 |
roid | -0.174 |
Token | its |
Token ID | 663 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
terness | +1.716 |
thur | +1.631 |
phia | +1.556 |
י� | +1.534 |
chio | +1.523 |
Neg logit contributions | |
�� | -1.372 |
Belg | -1.316 |
uss | -1.280 |
rol | -1.252 |
roid | -1.227 |
Token | top |
Token ID | 1353 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
terness | +0.514 |
thur | +0.484 |
phia | +0.463 |
י� | +0.457 |
renheit | +0.455 |
Neg logit contributions | |
�� | -0.384 |
Belg | -0.377 |
uss | -0.366 |
rol | -0.359 |
roid | -0.347 |
Token | - |
Token ID | 12 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
terness | +2.673 |
thur | +2.566 |
phia | +2.442 |
י� | +2.416 |
renheit | +2.387 |
Neg logit contributions | |
�� | -2.094 |
Belg | -1.955 |
uss | -1.910 |
rol | -1.855 |
roid | -1.829 |
Token | not |
Token ID | 1662 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
�� | +0.701 |
Belg | +0.686 |
uss | +0.675 |
rol | +0.665 |
roid | +0.652 |
Neg logit contributions | |
terness | -0.756 |
thur | -0.711 |
phia | -0.678 |
י� | -0.666 |
renheit | -0.664 |
Token | ch |
Token ID | 354 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
�� | +0.207 |
Belg | +0.202 |
uss | +0.200 |
rol | +0.196 |
roid | +0.192 |
Neg logit contributions | |
terness | -0.197 |
thur | -0.186 |
phia | -0.178 |
י� | -0.175 |
renheit | -0.173 |
Token | rating |
Token ID | 7955 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
�� | +0.531 |
Belg | +0.516 |
uss | +0.500 |
rol | +0.488 |
roid | +0.476 |
Neg logit contributions | |
terness | -0.782 |
thur | -0.743 |
phia | -0.710 |
י� | -0.701 |
renheit | -0.697 |
Token | in |
Token ID | 287 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
terness | +7.209 |
thur | +6.914 |
chio | +6.483 |
י� | +6.477 |
phia | +6.419 |
Neg logit contributions | |
�� | -8.106 |
Belg | -7.116 |
uss | -6.984 |
rol | -6.810 |
roid | -6.758 |
Token | the |
Token ID | 262 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
terness | +1.712 |
thur | +1.633 |
phia | +1.552 |
י� | +1.518 |
chio | +1.516 |
Neg logit contributions | |
�� | -1.683 |
Belg | -1.580 |
uss | -1.540 |
rol | -1.513 |
roid | -1.505 |
Token | event |
Token ID | 1785 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
terness | +1.828 |
thur | +1.748 |
phia | +1.673 |
י� | +1.648 |
chio | +1.640 |
Neg logit contributions | |
�� | -1.426 |
Belg | -1.335 |
uss | -1.297 |
rol | -1.274 |
roid | -1.256 |
Token | of |
Token ID | 286 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
terness | +2.470 |
thur | +2.330 |
phia | +2.188 |
י� | +2.165 |
chio | +2.156 |
Neg logit contributions | |
�� | -2.559 |
Belg | -2.413 |
uss | -2.340 |
rol | -2.308 |
roid | -2.305 |
Token | a |
Token ID | 257 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
terness | +0.257 |
thur | +0.244 |
phia | +0.233 |
י� | +0.230 |
chio | +0.228 |
Neg logit contributions | |
�� | -0.205 |
Belg | -0.197 |
uss | -0.192 |
rol | -0.188 |
roid | -0.184 |
Token | able |
Token ID | 540 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
terness | +1.304 |
thur | +1.256 |
phia | +1.192 |
chio | +1.191 |
י� | +1.175 |
Neg logit contributions | |
�� | -0.793 |
Belg | -0.725 |
rol | -0.702 |
uss | -0.699 |
roid | -0.660 |
Token | version |
Token ID | 2196 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
terness | +1.591 |
thur | +1.535 |
phia | +1.441 |
chio | +1.428 |
י� | +1.422 |
Neg logit contributions | |
�� | -1.496 |
Belg | -1.411 |
uss | -1.369 |
rol | -1.353 |
roid | -1.315 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
terness | +1.070 |
thur | +1.015 |
phia | +0.949 |
chio | +0.935 |
י� | +0.935 |
Neg logit contributions | |
�� | -1.400 |
Belg | -1.321 |
uss | -1.300 |
rol | -1.295 |
roid | -1.240 |
Token | Rob |
Token ID | 14350 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
terness | +0.854 |
thur | +0.804 |
phia | +0.760 |
י� | +0.747 |
chio | +0.741 |
Neg logit contributions | |
�� | -0.956 |
Belg | -0.923 |
uss | -0.902 |
rol | -0.886 |
roid | -0.871 |
Token | C |
Token ID | 327 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
�� | +1.436 |
Belg | +1.398 |
uss | +1.362 |
rol | +1.336 |
roid | +1.312 |
Neg logit contributions | |
terness | -1.573 |
thur | -1.497 |
phia | -1.407 |
י� | -1.392 |
renheit | -1.389 |
Token | estern |
Token ID | 3330 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
�� | +1.663 |
uss | +1.646 |
Belg | +1.642 |
rol | +1.617 |
roid | +1.582 |
Neg logit contributions | |
terness | -1.013 |
thur | -0.925 |
phia | -0.869 |
י� | -0.857 |
renheit | -0.829 |
Token | ino |
Token ID | 2879 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
terness | +4.498 |
thur | +4.369 |
chio | +4.311 |
י� | +3.886 |
phia | +3.831 |
Neg logit contributions | |
�� | -11.095 |
Belg | -10.200 |
roid | -9.559 |
rol | -9.400 |
heartbeat | -9.376 |
Token | hosts |
Token ID | 11453 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
terness | +3.337 |
thur | +3.178 |
phia | +3.013 |
chio | +2.996 |
י� | +2.987 |
Neg logit contributions | |
�� | -2.976 |
Belg | -2.781 |
uss | -2.676 |
rol | -2.648 |
roid | -2.597 |
Token | a |
Token ID | 257 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
terness | +1.203 |
thur | +1.144 |
phia | +1.090 |
י� | +1.073 |
chio | +1.067 |
Neg logit contributions | |
�� | -1.033 |
Belg | -0.988 |
uss | -0.961 |
rol | -0.941 |
roid | -0.924 |
Token | jam |
Token ID | 16853 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
terness | +0.246 |
thur | +0.234 |
phia | +0.224 |
י� | +0.222 |
renheit | +0.220 |
Neg logit contributions | |
�� | -0.161 |
Belg | -0.154 |
uss | -0.150 |
rol | -0.146 |
roid | -0.143 |
Token | packed |
Token ID | 11856 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
terness | +0.615 |
thur | +0.584 |
phia | +0.557 |
י� | +0.549 |
renheit | +0.545 |
Neg logit contributions | |
�� | -0.486 |
Belg | -0.466 |
uss | -0.455 |
rol | -0.444 |
roid | -0.436 |
Token | it |
Token ID | 340 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
terness | +7.926 |
thur | +7.085 |
י� | +6.771 |
renheit | +6.705 |
TER | +6.590 |
Neg logit contributions | |
�� | -7.960 |
Belg | -7.274 |
roid | -7.039 |
rol | -6.994 |
uss | -6.939 |
Token | has |
Token ID | 468 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
�� | +0.221 |
Belg | +0.215 |
uss | +0.210 |
rol | +0.204 |
roid | +0.200 |
Neg logit contributions | |
terness | -0.297 |
thur | -0.283 |
phia | -0.271 |
י� | -0.267 |
renheit | -0.265 |
Token | an |
Token ID | 281 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
terness | +2.263 |
thur | +2.135 |
phia | +2.014 |
י� | +2.002 |
chio | +1.983 |
Neg logit contributions | |
�� | -1.952 |
Belg | -1.829 |
uss | -1.796 |
rol | -1.756 |
roid | -1.727 |
Token | incredibly |
Token ID | 8131 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
terness | +1.179 |
thur | +1.116 |
phia | +1.054 |
י� | +1.046 |
chio | +1.037 |
Neg logit contributions | |
�� | -0.941 |
Belg | -0.890 |
uss | -0.869 |
rol | -0.849 |
roid | -0.836 |
Token | soft |
Token ID | 2705 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
�� | +1.454 |
Belg | +1.430 |
uss | +1.375 |
rol | +1.340 |
roid | +1.298 |
Neg logit contributions | |
terness | -2.193 |
thur | -2.116 |
phia | -2.045 |
י� | -1.988 |
renheit | -1.984 |
Token | mouth |
Token ID | 5422 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
terness | +1.020 |
thur | +0.962 |
phia | +0.917 |
י� | +0.904 |
chio | +0.897 |
Neg logit contributions | |
�� | -0.861 |
Belg | -0.819 |
uss | -0.799 |
rol | -0.781 |
roid | -0.768 |
Token | feel |
Token ID | 36410 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
terness | +6.359 |
thur | +5.863 |
י� | +5.395 |
phia | +5.394 |
TER | +5.265 |
Neg logit contributions | |
�� | -8.580 |
Belg | -8.368 |
roid | -7.839 |
uss | -7.742 |
rol | -7.602 |
Token | , |
Token ID | 11 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
terness | +1.720 |
thur | +1.621 |
phia | +1.540 |
י� | +1.526 |
chio | +1.508 |
Neg logit contributions | |
�� | -1.533 |
Belg | -1.472 |
uss | -1.431 |
rol | -1.400 |
roid | -1.376 |
Token | very |
Token ID | 845 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
terness | +0.404 |
thur | +0.384 |
phia | +0.367 |
י� | +0.362 |
chio | +0.359 |
Neg logit contributions | |
�� | -0.320 |
Belg | -0.306 |
uss | -0.298 |
rol | -0.291 |
roid | -0.286 |
Token | smooth |
Token ID | 7209 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
�� | +0.459 |
Belg | +0.439 |
uss | +0.425 |
rol | +0.414 |
roid | +0.404 |
Neg logit contributions | |
terness | -0.706 |
thur | -0.675 |
phia | -0.647 |
י� | -0.638 |
chio | -0.634 |
Token | , |
Token ID | 11 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
terness | +0.755 |
thur | +0.712 |
phia | +0.677 |
י� | +0.669 |
chio | +0.661 |
Neg logit contributions | |
�� | -0.685 |
Belg | -0.656 |
uss | -0.638 |
rol | -0.626 |
roid | -0.615 |
Token | the |
Token ID | 262 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
�� | +0.303 |
Belg | +0.297 |
uss | +0.289 |
rol | +0.282 |
roid | +0.275 |
Neg logit contributions | |
terness | -0.371 |
thur | -0.352 |
phia | -0.336 |
י� | -0.331 |
renheit | -0.330 |
Token | baking |
Token ID | 16871 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
terness | +1.044 |
thur | +0.993 |
phia | +0.948 |
י� | +0.933 |
chio | +0.927 |
Neg logit contributions | |
�� | -0.838 |
Belg | -0.798 |
uss | -0.777 |
rol | -0.760 |
roid | -0.746 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
terness | +0.164 |
thur | +0.157 |
phia | +0.150 |
י� | +0.148 |
chio | +0.146 |
Neg logit contributions | |
�� | -0.122 |
Belg | -0.118 |
uss | -0.114 |
rol | -0.112 |
roid | -0.109 |
Token |
|
Token ID | 198 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
terness | +1.045 |
thur | +0.991 |
phia | +0.942 |
י� | +0.926 |
chio | +0.921 |
Neg logit contributions | |
�� | -0.941 |
Belg | -0.910 |
uss | -0.884 |
rol | -0.866 |
roid | -0.850 |
Token |
|
Token ID | 198 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
terness | +0.714 |
thur | +0.670 |
phia | +0.634 |
י� | +0.622 |
chio | +0.617 |
Neg logit contributions | |
�� | -0.786 |
Belg | -0.763 |
uss | -0.746 |
rol | -0.733 |
roid | -0.720 |
Token | Chest |
Token ID | 45170 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
�� | +0.182 |
Belg | +0.178 |
uss | +0.176 |
rol | +0.173 |
roid | +0.170 |
Neg logit contributions | |
terness | -0.166 |
thur | -0.154 |
phia | -0.146 |
renheit | -0.143 |
י� | -0.142 |
Token | nut |
Token ID | 14930 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
terness | +4.668 |
thur | +4.586 |
phia | +4.057 |
chio | +4.010 |
י� | +3.835 |
Neg logit contributions | |
�� | -10.051 |
Belg | -9.568 |
uss | -9.330 |
rol | -9.103 |
roid | -9.045 |
Token | Fl |
Token ID | 1610 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
terness | +4.815 |
thur | +4.620 |
phia | +4.406 |
chio | +4.376 |
י� | +4.322 |
Neg logit contributions | |
�� | -3.363 |
Belg | -3.118 |
uss | -3.071 |
rol | -2.944 |
roid | -2.897 |
Token | our |
Token ID | 454 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
�� | +0.762 |
Belg | +0.726 |
uss | +0.717 |
rol | +0.678 |
roid | +0.655 |
Neg logit contributions | |
terness | -2.376 |
thur | -2.278 |
phia | -2.201 |
י� | -2.190 |
renheit | -2.169 |
Token | — |
Token ID | 960 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
terness | +0.114 |
thur | +0.108 |
phia | +0.103 |
י� | +0.101 |
chio | +0.100 |
Neg logit contributions | |
�� | -0.102 |
Belg | -0.098 |
uss | -0.096 |
rol | -0.094 |
roid | -0.092 |
Token | This |
Token ID | 1212 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
�� | +0.193 |
Belg | +0.190 |
uss | +0.186 |
rol | +0.182 |
roid | +0.179 |
Neg logit contributions | |
terness | -0.183 |
thur | -0.171 |
phia | -0.162 |
renheit | -0.159 |
י� | -0.159 |
Token | . |
Token ID | 13 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
�� | +0.230 |
Belg | +0.227 |
uss | +0.222 |
rol | +0.218 |
roid | +0.212 |
Neg logit contributions | |
terness | -0.309 |
thur | -0.291 |
phia | -0.278 |
י� | -0.271 |
renheit | -0.271 |
Token | Now |
Token ID | 2735 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
terness | +2.125 |
thur | +2.012 |
phia | +1.922 |
י� | +1.911 |
chio | +1.897 |
Neg logit contributions | |
�� | -1.558 |
Belg | -1.462 |
uss | -1.426 |
rol | -1.390 |
roid | -1.371 |
Token | we |
Token ID | 356 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
terness | +2.466 |
thur | +2.339 |
phia | +2.228 |
י� | +2.213 |
chio | +2.200 |
Neg logit contributions | |
�� | -1.888 |
Belg | -1.766 |
uss | -1.704 |
rol | -1.664 |
roid | -1.641 |
Token | cut |
Token ID | 2005 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
terness | +1.436 |
thur | +1.365 |
phia | +1.299 |
י� | +1.285 |
chio | +1.277 |
Neg logit contributions | |
�� | -1.192 |
Belg | -1.140 |
uss | -1.103 |
rol | -1.080 |
roid | -1.063 |
Token | the |
Token ID | 262 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
terness | +3.248 |
thur | +3.063 |
phia | +2.915 |
י� | +2.882 |
chio | +2.856 |
Neg logit contributions | |
�� | -3.118 |
Belg | -2.968 |
uss | -2.864 |
rol | -2.814 |
roid | -2.773 |
Token | bell |
Token ID | 8966 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
terness | +0.490 |
thur | +0.463 |
phia | +0.441 |
י� | +0.434 |
renheit | +0.430 |
Neg logit contributions | |
�� | -0.450 |
Belg | -0.436 |
uss | -0.425 |
rol | -0.416 |
roid | -0.407 |
Token | peppers |
Token ID | 31804 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
terness | +4.606 |
thur | +4.263 |
phia | +4.098 |
chio | +3.851 |
י� | +3.808 |
Neg logit contributions | |
�� | -10.702 |
Belg | -9.908 |
uss | -9.581 |
rol | -9.453 |
roid | -9.443 |
Token | into |
Token ID | 656 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
terness | +3.037 |
thur | +2.877 |
phia | +2.732 |
י� | +2.708 |
chio | +2.702 |
Neg logit contributions | |
�� | -2.770 |
Belg | -2.608 |
uss | -2.524 |
rol | -2.470 |
roid | -2.424 |
Token | small |
Token ID | 1402 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
terness | +2.367 |
thur | +2.260 |
phia | +2.165 |
י� | +2.135 |
chio | +2.124 |
Neg logit contributions | |
�� | -1.846 |
Belg | -1.724 |
uss | -1.682 |
rol | -1.643 |
roid | -1.616 |
Token | - |
Token ID | 12 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
terness | +1.144 |
thur | +1.089 |
phia | +1.041 |
י� | +1.025 |
chio | +1.019 |
Neg logit contributions | |
�� | -0.903 |
Belg | -0.860 |
uss | -0.838 |
rol | -0.819 |
roid | -0.803 |
Token | medium |
Token ID | 24132 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
terness | +0.604 |
thur | +0.571 |
phia | +0.541 |
י� | +0.533 |
chio | +0.529 |
Neg logit contributions | |
�� | -0.603 |
Belg | -0.580 |
uss | -0.567 |
rol | -0.555 |
roid | -0.546 |
Token | critical |
Token ID | 4688 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
terness | +1.128 |
thur | +1.077 |
phia | +1.027 |
י� | +1.015 |
chio | +1.009 |
Neg logit contributions | |
�� | -0.854 |
Belg | -0.808 |
uss | -0.787 |
rol | -0.768 |
roid | -0.752 |
Token | illness |
Token ID | 8526 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
�� | +0.253 |
Belg | +0.244 |
uss | +0.237 |
rol | +0.232 |
roid | +0.227 |
Neg logit contributions | |
terness | -0.367 |
thur | -0.350 |
phia | -0.335 |
י� | -0.330 |
renheit | -0.328 |
Token | - |
Token ID | 12 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
�� | +0.388 |
Belg | +0.375 |
uss | +0.365 |
rol | +0.357 |
roid | +0.351 |
Neg logit contributions | |
terness | -0.466 |
thur | -0.444 |
phia | -0.422 |
י� | -0.417 |
renheit | -0.414 |
Token | related |
Token ID | 5363 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
terness | +1.019 |
thur | +0.970 |
phia | +0.926 |
י� | +0.914 |
renheit | +0.908 |
Neg logit contributions | |
�� | -0.773 |
Belg | -0.743 |
uss | -0.725 |
rol | -0.707 |
roid | -0.693 |
Token | cort |
Token ID | 12794 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
�� | +0.713 |
Belg | +0.700 |
uss | +0.677 |
rol | +0.662 |
roid | +0.650 |
Neg logit contributions | |
terness | -0.943 |
thur | -0.897 |
phia | -0.858 |
י� | -0.841 |
renheit | -0.841 |
Token | ic |
Token ID | 291 |
Feature activation | +9.99e+00 |
Pos logit contributions | |
terness | +1.366 |
thur | +1.270 |
phia | +1.183 |
י� | +1.155 |
chio | +1.148 |
Neg logit contributions | |
�� | -2.245 |
Belg | -2.170 |
uss | -2.116 |
rol | -2.087 |
roid | -2.061 |
Token | oster |
Token ID | 6197 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
terness | +6.072 |
thur | +5.647 |
chio | +5.479 |
phia | +5.244 |
י� | +5.229 |
Neg logit contributions | |
�� | -9.261 |
Belg | -8.583 |
uss | -8.006 |
rol | -7.982 |
roid | -7.755 |
Token | oid |
Token ID | 1868 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
terness | +1.462 |
thur | +1.303 |
phia | +1.153 |
י� | +1.098 |
chio | +1.097 |
Neg logit contributions | |
�� | -4.713 |
Belg | -4.556 |
uss | -4.449 |
rol | -4.389 |
roid | -4.343 |
Token | ins |
Token ID | 1035 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
terness | +4.644 |
thur | +4.354 |
phia | +4.220 |
chio | +4.186 |
י� | +4.179 |
Neg logit contributions | |
�� | -3.927 |
Belg | -3.535 |
uss | -3.376 |
rol | -3.326 |
roid | -3.229 |
Token | uff |
Token ID | 1648 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
terness | +3.127 |
thur | +2.931 |
phia | +2.831 |
chio | +2.770 |
י� | +2.764 |
Neg logit contributions | |
�� | -2.621 |
Belg | -2.495 |
uss | -2.355 |
rol | -2.316 |
roid | -2.277 |
Token | iciency |
Token ID | 19777 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
�� | +0.379 |
Belg | +0.370 |
uss | +0.367 |
rol | +0.362 |
roid | +0.354 |
Neg logit contributions | |
terness | -0.387 |
thur | -0.365 |
phia | -0.343 |
י� | -0.340 |
renheit | -0.337 |
Token | California |
Token ID | 3442 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
�� | +0.358 |
Belg | +0.346 |
uss | +0.336 |
rol | +0.330 |
roid | +0.323 |
Neg logit contributions | |
terness | -0.393 |
thur | -0.371 |
phia | -0.353 |
י� | -0.348 |
renheit | -0.346 |
Token | 's |
Token ID | 338 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
terness | +0.654 |
thur | +0.624 |
phia | +0.595 |
י� | +0.586 |
chio | +0.582 |
Neg logit contributions | |
�� | -0.507 |
Belg | -0.484 |
uss | -0.470 |
rol | -0.459 |
roid | -0.451 |
Token | Great |
Token ID | 3878 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
�� | +1.452 |
Belg | +1.417 |
uss | +1.365 |
rol | +1.343 |
roid | +1.312 |
Neg logit contributions | |
terness | -1.760 |
thur | -1.661 |
phia | -1.589 |
י� | -1.562 |
renheit | -1.557 |
Token | America |
Token ID | 2253 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
�� | +0.132 |
Belg | +0.127 |
uss | +0.124 |
rol | +0.122 |
roid | +0.119 |
Neg logit contributions | |
terness | -0.139 |
thur | -0.132 |
phia | -0.125 |
י� | -0.123 |
chio | -0.122 |
Token | in |
Token ID | 287 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
terness | +0.810 |
thur | +0.776 |
phia | +0.738 |
י� | +0.723 |
chio | +0.721 |
Neg logit contributions | |
�� | -0.717 |
Belg | -0.680 |
uss | -0.662 |
rol | -0.649 |
roid | -0.637 |
Token | Santa |
Token ID | 8909 |
Feature activation | +9.96e+00 |
Pos logit contributions | |
�� | +0.765 |
Belg | +0.741 |
uss | +0.718 |
rol | +0.703 |
roid | +0.688 |
Neg logit contributions | |
terness | -0.949 |
thur | -0.900 |
phia | -0.858 |
י� | -0.846 |
chio | -0.840 |
Token | Clara |
Token ID | 27443 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
terness | +6.160 |
thur | +6.033 |
phia | +5.628 |
renheit | +5.499 |
chio | +5.478 |
Neg logit contributions | |
�� | -8.634 |
Belg | -7.854 |
uss | -7.791 |
roid | -7.707 |
rol | -7.533 |
Token | , |
Token ID | 11 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
terness | +2.375 |
thur | +2.284 |
phia | +2.188 |
י� | +2.122 |
chio | +2.120 |
Neg logit contributions | |
�� | -2.259 |
Belg | -2.135 |
uss | -2.080 |
rol | -2.036 |
roid | -2.002 |
Token | California |
Token ID | 3442 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
terness | +1.081 |
thur | +1.018 |
phia | +0.948 |
י� | +0.930 |
chio | +0.921 |
Neg logit contributions | |
�� | -1.544 |
Belg | -1.475 |
uss | -1.446 |
rol | -1.427 |
roid | -1.408 |
Token | was |
Token ID | 373 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
terness | +2.792 |
thur | +2.701 |
phia | +2.561 |
chio | +2.520 |
י� | +2.512 |
Neg logit contributions | |
�� | -2.652 |
Belg | -2.508 |
uss | -2.424 |
rol | -2.377 |
roid | -2.350 |
Token | originally |
Token ID | 6198 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
�� | +0.363 |
Belg | +0.350 |
uss | +0.340 |
rol | +0.332 |
roid | +0.325 |
Neg logit contributions | |
terness | -0.513 |
thur | -0.488 |
phia | -0.466 |
י� | -0.460 |
renheit | -0.457 |
Token | straight |
Token ID | 3892 |
Feature activation | +7.65e+00 |
Pos logit contributions | |
terness | +2.472 |
thur | +2.358 |
phia | +2.236 |
י� | +2.214 |
chio | +2.199 |
Neg logit contributions | |
�� | -2.061 |
Belg | -1.905 |
uss | -1.873 |
rol | -1.830 |
roid | -1.813 |
Token | from |
Token ID | 422 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
terness | +6.069 |
thur | +5.847 |
י� | +5.553 |
phia | +5.493 |
DEN | +5.443 |
Neg logit contributions | |
�� | -5.525 |
Belg | -4.873 |
uss | -4.752 |
rol | -4.703 |
roid | -4.613 |
Token | the |
Token ID | 262 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
terness | +2.312 |
thur | +2.203 |
phia | +2.097 |
י� | +2.074 |
chio | +2.053 |
Neg logit contributions | |
�� | -1.915 |
Belg | -1.793 |
uss | -1.752 |
rol | -1.715 |
roid | -1.690 |
Token | horse |
Token ID | 8223 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
terness | +1.372 |
thur | +1.313 |
phia | +1.252 |
י� | +1.237 |
chio | +1.230 |
Neg logit contributions | |
�� | -1.019 |
Belg | -0.961 |
uss | -0.936 |
rol | -0.914 |
roid | -0.896 |
Token | 's |
Token ID | 338 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
terness | +3.409 |
thur | +3.309 |
phia | +3.096 |
י� | +3.048 |
chio | +3.021 |
Neg logit contributions | |
�� | -3.010 |
Belg | -2.821 |
uss | -2.730 |
rol | -2.666 |
roid | -2.651 |
Token | mouth |
Token ID | 5422 |
Feature activation | +9.89e+00 |
Pos logit contributions | |
terness | +0.275 |
thur | +0.262 |
phia | +0.251 |
י� | +0.248 |
chio | +0.246 |
Neg logit contributions | |
�� | -0.193 |
Belg | -0.184 |
uss | -0.179 |
rol | -0.174 |
roid | -0.171 |
Token | ! |
Token ID | 0 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
terness | +7.117 |
thur | +6.707 |
י� | +6.368 |
phia | +6.336 |
TER | +6.269 |
Neg logit contributions | |
�� | -7.696 |
Belg | -6.906 |
uss | -6.654 |
rol | -6.640 |
roid | -6.503 |
Token | Now |
Token ID | 2735 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
terness | +3.407 |
thur | +3.243 |
י� | +3.072 |
phia | +3.054 |
chio | +3.031 |
Neg logit contributions | |
�� | -3.169 |
Belg | -2.891 |
uss | -2.874 |
rol | -2.805 |
roid | -2.786 |
Token | , |
Token ID | 11 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
terness | +2.813 |
thur | +2.691 |
phia | +2.532 |
י� | +2.525 |
chio | +2.506 |
Neg logit contributions | |
�� | -2.491 |
Belg | -2.305 |
uss | -2.240 |
rol | -2.187 |
roid | -2.162 |
Token | as |
Token ID | 355 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
terness | +0.355 |
thur | +0.338 |
phia | +0.322 |
י� | +0.317 |
chio | +0.315 |
Neg logit contributions | |
�� | -0.284 |
Belg | -0.272 |
uss | -0.265 |
rol | -0.259 |
roid | -0.254 |
Token | cool |
Token ID | 3608 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
terness | +2.575 |
thur | +2.453 |
phia | +2.312 |
י� | +2.286 |
chio | +2.267 |
Neg logit contributions | |
�� | -2.435 |
Belg | -2.273 |
uss | -2.218 |
rol | -2.177 |
roid | -2.162 |
Token | reviewed |
Token ID | 11765 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
terness | +3.117 |
thur | +2.992 |
phia | +2.847 |
י� | +2.811 |
chio | +2.797 |
Neg logit contributions | |
�� | -2.621 |
Belg | -2.404 |
uss | -2.360 |
rol | -2.308 |
roid | -2.272 |
Token | by |
Token ID | 416 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
terness | +2.850 |
thur | +2.721 |
phia | +2.572 |
י� | +2.549 |
chio | +2.534 |
Neg logit contributions | |
�� | -2.755 |
Belg | -2.586 |
uss | -2.537 |
rol | -2.466 |
roid | -2.441 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
�� | +0.499 |
Belg | +0.482 |
uss | +0.467 |
rol | +0.458 |
roid | +0.448 |
Neg logit contributions | |
terness | -0.613 |
thur | -0.581 |
phia | -0.553 |
י� | -0.545 |
chio | -0.542 |
Token | employees |
Token ID | 4409 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
�� | +0.143 |
Belg | +0.138 |
uss | +0.134 |
rol | +0.131 |
roid | +0.129 |
Neg logit contributions | |
terness | -0.172 |
thur | -0.163 |
phia | -0.155 |
י� | -0.153 |
chio | -0.152 |
Token | in |
Token ID | 287 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
terness | +1.413 |
thur | +1.343 |
phia | +1.278 |
י� | +1.262 |
chio | +1.250 |
Neg logit contributions | |
�� | -1.298 |
Belg | -1.236 |
uss | -1.204 |
rol | -1.176 |
roid | -1.157 |
Token | Palo |
Token ID | 44878 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
terness | +1.051 |
thur | +1.002 |
phia | +0.958 |
י� | +0.944 |
chio | +0.939 |
Neg logit contributions | |
�� | -0.812 |
Belg | -0.769 |
uss | -0.748 |
rol | -0.733 |
roid | -0.719 |
Token | Alto |
Token ID | 34317 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
terness | +3.763 |
thur | +3.528 |
phia | +3.231 |
chio | +3.007 |
renheit | +2.861 |
Neg logit contributions | |
�� | -11.268 |
Belg | -10.342 |
uss | -10.318 |
rol | -10.199 |
roid | -10.069 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
terness | +4.586 |
thur | +4.418 |
phia | +4.265 |
י� | +4.056 |
chio | +4.042 |
Neg logit contributions | |
�� | -5.173 |
Belg | -4.812 |
uss | -4.723 |
rol | -4.579 |
roid | -4.566 |
Token | Calif |
Token ID | 3192 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
terness | +0.927 |
thur | +0.873 |
phia | +0.824 |
י� | +0.809 |
chio | +0.801 |
Neg logit contributions | |
�� | -1.097 |
Belg | -1.055 |
uss | -1.032 |
rol | -1.014 |
roid | -0.998 |
Token | ., |
Token ID | 1539 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
terness | +3.248 |
thur | +3.098 |
phia | +2.928 |
י� | +2.855 |
chio | +2.834 |
Neg logit contributions | |
�� | -4.381 |
Belg | -4.179 |
uss | -4.000 |
roid | -3.907 |
rol | -3.899 |
Token | and |
Token ID | 290 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
�� | +0.192 |
Belg | +0.186 |
uss | +0.180 |
rol | +0.176 |
roid | +0.173 |
Neg logit contributions | |
terness | -0.238 |
thur | -0.226 |
phia | -0.215 |
י� | -0.212 |
renheit | -0.211 |
Token | s |
Token ID | 82 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
terness | +0.437 |
thur | +0.416 |
phia | +0.397 |
י� | +0.392 |
chio | +0.389 |
Neg logit contributions | |
�� | -0.330 |
Belg | -0.316 |
uss | -0.307 |
rol | -0.300 |
roid | -0.294 |
Token | tongue |
Token ID | 11880 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
terness | +0.206 |
thur | +0.196 |
phia | +0.187 |
י� | +0.184 |
renheit | +0.183 |
Neg logit contributions | |
�� | -0.168 |
Belg | -0.161 |
uss | -0.157 |
rol | -0.154 |
roid | -0.151 |
Token | , |
Token ID | 11 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
terness | +3.544 |
thur | +3.345 |
י� | +3.201 |
phia | +3.182 |
chio | +3.149 |
Neg logit contributions | |
�� | -2.671 |
Belg | -2.543 |
uss | -2.428 |
rol | -2.373 |
roid | -2.333 |
Token | lips |
Token ID | 11914 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
terness | +1.247 |
thur | +1.185 |
phia | +1.129 |
י� | +1.118 |
chio | +1.108 |
Neg logit contributions | |
�� | -1.002 |
Belg | -0.956 |
uss | -0.930 |
rol | -0.909 |
roid | -0.894 |
Token | , |
Token ID | 11 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
terness | +3.481 |
thur | +3.283 |
phia | +3.094 |
י� | +3.087 |
chio | +3.036 |
Neg logit contributions | |
�� | -3.501 |
Belg | -3.373 |
uss | -3.245 |
rol | -3.188 |
roid | -3.140 |
Token | jaw |
Token ID | 19218 |
Feature activation | +9.79e+00 |
Pos logit contributions | |
terness | +1.883 |
thur | +1.781 |
phia | +1.693 |
י� | +1.671 |
chio | +1.653 |
Neg logit contributions | |
�� | -1.889 |
Belg | -1.809 |
uss | -1.761 |
rol | -1.727 |
roid | -1.696 |
Token | and |
Token ID | 290 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
terness | +6.998 |
thur | +6.640 |
phia | +6.270 |
י� | +6.216 |
chio | +6.146 |
Neg logit contributions | |
�� | -7.536 |
Belg | -7.173 |
uss | -6.728 |
rol | -6.594 |
roid | -6.527 |
Token | l |
Token ID | 300 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
terness | +1.150 |
thur | +1.092 |
phia | +1.040 |
י� | +1.024 |
chio | +1.015 |
Neg logit contributions | |
�� | -1.082 |
Belg | -1.034 |
uss | -1.005 |
rol | -0.985 |
roid | -0.966 |
Token | aryn |
Token ID | 38621 |
Feature activation | +8.57e+00 |
Pos logit contributions | |
�� | +0.842 |
Belg | +0.819 |
uss | +0.813 |
rol | +0.798 |
roid | +0.786 |
Neg logit contributions | |
terness | -0.550 |
thur | -0.509 |
phia | -0.474 |
י� | -0.464 |
renheit | -0.463 |
Token | x |
Token ID | 87 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
terness | +4.227 |
thur | +4.073 |
chio | +3.760 |
phia | +3.701 |
י� | +3.513 |
Neg logit contributions | |
�� | -8.696 |
Belg | -8.395 |
uss | -8.067 |
rol | -7.939 |
roid | -7.913 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
terness | +1.573 |
thur | +1.498 |
phia | +1.431 |
י� | +1.420 |
chio | +1.408 |
Neg logit contributions | |
�� | -1.109 |
Belg | -1.058 |
uss | -1.023 |
rol | -0.998 |
roid | -0.977 |
Token | 1080 |
Token ID | 24045 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
terness | +2.447 |
thur | +2.314 |
phia | +2.174 |
י� | +2.150 |
chio | +2.125 |
Neg logit contributions | |
�� | -3.210 |
Belg | -3.071 |
uss | -3.008 |
rol | -2.962 |
roid | -2.904 |
Token | ships |
Token ID | 7937 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
�� | +2.225 |
Belg | +2.168 |
uss | +2.111 |
rol | +2.060 |
roid | +2.046 |
Neg logit contributions | |
terness | -2.991 |
thur | -2.832 |
phia | -2.676 |
י� | -2.651 |
renheit | -2.638 |
Token | with |
Token ID | 351 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
�� | +1.339 |
Belg | +1.317 |
uss | +1.276 |
rol | +1.246 |
roid | +1.222 |
Neg logit contributions | |
terness | -1.781 |
thur | -1.696 |
phia | -1.609 |
י� | -1.589 |
renheit | -1.580 |
Token | 25 |
Token ID | 1679 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
�� | +0.715 |
Belg | +0.700 |
uss | +0.676 |
rol | +0.662 |
roid | +0.646 |
Neg logit contributions | |
terness | -0.914 |
thur | -0.869 |
phia | -0.821 |
י� | -0.812 |
renheit | -0.805 |
Token | 60 |
Token ID | 1899 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
�� | +1.330 |
Belg | +1.285 |
uss | +1.246 |
rol | +1.214 |
roid | +1.187 |
Neg logit contributions | |
terness | -1.709 |
thur | -1.637 |
phia | -1.559 |
י� | -1.519 |
chio | -1.516 |
Token | CU |
Token ID | 29369 |
Feature activation | +9.78e+00 |
Pos logit contributions | |
terness | +2.313 |
thur | +2.167 |
phia | +2.064 |
י� | +2.027 |
renheit | +2.008 |
Neg logit contributions | |
�� | -2.717 |
Belg | -2.605 |
uss | -2.564 |
rol | -2.510 |
roid | -2.470 |
Token | DA |
Token ID | 5631 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
terness | +2.615 |
thur | +2.277 |
TER | +1.985 |
phia | +1.904 |
chio | +1.890 |
Neg logit contributions | |
�� | -12.170 |
Belg | -11.655 |
uss | -11.221 |
roid | -11.128 |
rol | -11.095 |
Token | cores |
Token ID | 21758 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
�� | +1.211 |
Belg | +1.153 |
uss | +1.118 |
rol | +1.086 |
roid | +1.055 |
Neg logit contributions | |
terness | -2.300 |
thur | -2.205 |
phia | -2.117 |
י� | -2.083 |
chio | -2.077 |
Token | and |
Token ID | 290 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
�� | +0.605 |
Belg | +0.584 |
uss | +0.569 |
rol | +0.556 |
roid | +0.546 |
Neg logit contributions | |
terness | -0.715 |
thur | -0.679 |
phia | -0.645 |
י� | -0.634 |
chio | -0.631 |
Token | 20 |
Token ID | 1160 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
�� | +0.324 |
Belg | +0.314 |
uss | +0.306 |
rol | +0.298 |
roid | +0.293 |
Neg logit contributions | |
terness | -0.371 |
thur | -0.352 |
phia | -0.334 |
י� | -0.329 |
chio | -0.326 |
Token | SM |
Token ID | 9447 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
terness | +0.367 |
thur | +0.347 |
phia | +0.330 |
י� | +0.325 |
chio | +0.322 |
Neg logit contributions | |
�� | -0.355 |
Belg | -0.341 |
uss | -0.333 |
rol | -0.326 |
roid | -0.321 |
Token | se |
Token ID | 325 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
�� | +1.165 |
uss | +1.128 |
Belg | +1.118 |
rol | +1.105 |
roid | +1.086 |
Neg logit contributions | |
terness | -1.138 |
thur | -1.079 |
phia | -1.023 |
י� | -1.016 |
renheit | -0.995 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
�� | +0.800 |
Belg | +0.772 |
uss | +0.754 |
rol | +0.739 |
roid | +0.725 |
Neg logit contributions | |
terness | -0.840 |
thur | -0.795 |
phia | -0.755 |
י� | -0.745 |
chio | -0.737 |
Token | M |
Token ID | 337 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
terness | +1.279 |
thur | +1.223 |
phia | +1.172 |
י� | +1.160 |
chio | +1.153 |
Neg logit contributions | |
�� | -0.851 |
Belg | -0.795 |
uss | -0.777 |
rol | -0.756 |
roid | -0.741 |
Token | ., |
Token ID | 1539 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
�� | +0.513 |
Belg | +0.493 |
uss | +0.481 |
rol | +0.472 |
roid | +0.463 |
Neg logit contributions | |
terness | -0.541 |
thur | -0.513 |
phia | -0.487 |
י� | -0.479 |
chio | -0.476 |
Token | Sch |
Token ID | 3059 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
�� | +1.046 |
Belg | +1.025 |
uss | +0.984 |
rol | +0.965 |
roid | +0.940 |
Neg logit contributions | |
terness | -1.331 |
thur | -1.265 |
phia | -1.201 |
י� | -1.180 |
renheit | -1.177 |
Token | ol |
Token ID | 349 |
Feature activation | +9.74e+00 |
Pos logit contributions | |
terness | +2.525 |
thur | +2.429 |
phia | +2.288 |
chio | +2.260 |
renheit | +2.241 |
Neg logit contributions | |
�� | -2.202 |
Belg | -2.089 |
uss | -1.976 |
rol | -1.947 |
roid | -1.917 |
Token | te |
Token ID | 660 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
terness | +4.724 |
thur | +4.328 |
phia | +4.044 |
chio | +3.979 |
mie | +3.867 |
Neg logit contributions | |
�� | -9.976 |
Belg | -9.415 |
uss | -8.874 |
rol | -8.792 |
heartbeat | -8.748 |
Token | , |
Token ID | 11 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
terness | +3.607 |
thur | +3.478 |
phia | +3.285 |
chio | +3.259 |
י� | +3.236 |
Neg logit contributions | |
�� | -4.394 |
Belg | -4.072 |
uss | -3.942 |
rol | -3.831 |
roid | -3.802 |
Token | R |
Token ID | 371 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
terness | +3.299 |
thur | +3.135 |
phia | +2.999 |
י� | +2.987 |
chio | +2.967 |
Neg logit contributions | |
�� | -2.653 |
Belg | -2.500 |
uss | -2.429 |
rol | -2.329 |
roid | -2.298 |
Token | ., |
Token ID | 1539 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
terness | +1.208 |
thur | +1.146 |
phia | +1.089 |
י� | +1.073 |
chio | +1.063 |
Neg logit contributions | |
�� | -1.168 |
Belg | -1.125 |
uss | -1.083 |
rol | -1.066 |
roid | -1.055 |
Token | Sal |
Token ID | 4849 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
�� | +1.529 |
Belg | +1.512 |
uss | +1.446 |
rol | +1.419 |
roid | +1.375 |
Neg logit contributions | |
terness | -1.987 |
thur | -1.886 |
phia | -1.792 |
י� | -1.759 |
renheit | -1.759 |
Token | the |
Token ID | 262 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
�� | +0.226 |
Belg | +0.223 |
uss | +0.215 |
rol | +0.211 |
roid | +0.205 |
Neg logit contributions | |
terness | -0.244 |
thur | -0.231 |
phia | -0.217 |
renheit | -0.214 |
י� | -0.214 |
Token | University |
Token ID | 2059 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
terness | +0.340 |
thur | +0.321 |
phia | +0.303 |
י� | +0.298 |
chio | +0.296 |
Neg logit contributions | |
�� | -0.341 |
Belg | -0.332 |
uss | -0.323 |
rol | -0.316 |
roid | -0.310 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Belg | +1.318 |
�� | +1.291 |
uss | +1.268 |
rol | +1.252 |
roid | +1.211 |
Neg logit contributions | |
terness | -1.640 |
thur | -1.525 |
phia | -1.469 |
renheit | -1.445 |
י� | -1.433 |
Token | California |
Token ID | 3442 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
terness | +0.077 |
thur | +0.073 |
phia | +0.068 |
י� | +0.067 |
renheit | +0.067 |
Neg logit contributions | |
�� | -0.085 |
Belg | -0.083 |
uss | -0.080 |
rol | -0.079 |
roid | -0.078 |
Token | , |
Token ID | 11 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
�� | +0.527 |
Belg | +0.517 |
uss | +0.506 |
rol | +0.497 |
roid | +0.483 |
Neg logit contributions | |
terness | -0.592 |
thur | -0.558 |
phia | -0.530 |
י� | -0.521 |
renheit | -0.518 |
Token | Santa |
Token ID | 8909 |
Feature activation | +9.73e+00 |
Pos logit contributions | |
�� | +0.315 |
Belg | +0.303 |
uss | +0.297 |
rol | +0.291 |
roid | +0.288 |
Neg logit contributions | |
terness | -0.253 |
thur | -0.238 |
phia | -0.224 |
י� | -0.220 |
chio | -0.218 |
Token | Barbara |
Token ID | 16685 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
terness | +4.695 |
thur | +4.661 |
phia | +4.243 |
chio | +4.073 |
TER | +4.067 |
Neg logit contributions | |
�� | -9.895 |
roid | -8.917 |
uss | -8.914 |
Belg | -8.887 |
rol | -8.677 |
Token | , |
Token ID | 11 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
terness | +1.423 |
thur | +1.357 |
phia | +1.289 |
י� | +1.271 |
chio | +1.261 |
Neg logit contributions | |
�� | -1.348 |
Belg | -1.287 |
uss | -1.247 |
rol | -1.221 |
roid | -1.205 |
Token | and |
Token ID | 290 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
terness | +0.448 |
thur | +0.425 |
phia | +0.404 |
י� | +0.398 |
chio | +0.395 |
Neg logit contributions | |
�� | -0.416 |
Belg | -0.399 |
uss | -0.388 |
rol | -0.381 |
roid | -0.374 |
Token | an |
Token ID | 281 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
�� | +0.090 |
Belg | +0.087 |
uss | +0.084 |
rol | +0.083 |
roid | +0.081 |
Neg logit contributions | |
terness | -0.113 |
thur | -0.107 |
phia | -0.102 |
י� | -0.101 |
renheit | -0.100 |
Token | organizer |
Token ID | 26311 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
terness | +1.271 |
thur | +1.215 |
phia | +1.165 |
י� | +1.151 |
chio | +1.143 |
Neg logit contributions | |
�� | -0.797 |
Belg | -0.756 |
uss | -0.731 |
rol | -0.712 |
roid | -0.697 |
Token | ol |
Token ID | 349 |
Feature activation | +6.67e+00 |
Pos logit contributions | |
terness | +1.609 |
thur | +1.526 |
phia | +1.451 |
י� | +1.429 |
chio | +1.419 |
Neg logit contributions | |
�� | -1.465 |
Belg | -1.405 |
uss | -1.368 |
rol | -1.339 |
roid | -1.316 |
Token | can |
Token ID | 460 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
terness | +5.254 |
thur | +4.970 |
phia | +4.800 |
י� | +4.677 |
chio | +4.664 |
Neg logit contributions | |
�� | -4.971 |
Belg | -4.581 |
uss | -4.386 |
rol | -4.276 |
roid | -4.258 |
Token | be |
Token ID | 307 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
terness | +2.717 |
thur | +2.589 |
phia | +2.458 |
י� | +2.436 |
chio | +2.416 |
Neg logit contributions | |
�� | -2.323 |
Belg | -2.219 |
uss | -2.141 |
rol | -2.095 |
roid | -2.060 |
Token | a |
Token ID | 257 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
terness | +1.124 |
thur | +1.069 |
phia | +1.021 |
י� | +1.005 |
chio | +0.999 |
Neg logit contributions | |
�� | -0.890 |
Belg | -0.856 |
uss | -0.833 |
rol | -0.815 |
roid | -0.798 |
Token | daunting |
Token ID | 30496 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
terness | +2.017 |
thur | +1.924 |
phia | +1.834 |
י� | +1.814 |
chio | +1.801 |
Neg logit contributions | |
�� | -1.572 |
Belg | -1.494 |
uss | -1.450 |
rol | -1.413 |
roid | -1.388 |
Token | mouth |
Token ID | 5422 |
Feature activation | +9.65e+00 |
Pos logit contributions | |
terness | +2.070 |
thur | +1.981 |
phia | +1.895 |
י� | +1.875 |
chio | +1.863 |
Neg logit contributions | |
�� | -1.356 |
Belg | -1.276 |
uss | -1.237 |
rol | -1.206 |
roid | -1.180 |
Token | ful |
Token ID | 913 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
terness | +6.653 |
thur | +6.383 |
י� | +5.939 |
mie | +5.790 |
TER | +5.741 |
Neg logit contributions | |
�� | -7.753 |
Belg | -7.314 |
roid | -6.748 |
uss | -6.724 |
rol | -6.640 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
terness | +5.114 |
thur | +4.811 |
י� | +4.587 |
phia | +4.533 |
chio | +4.509 |
Neg logit contributions | |
�� | -4.883 |
Belg | -4.569 |
uss | -4.371 |
rol | -4.265 |
roid | -4.258 |
Token | in |
Token ID | 287 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
terness | +1.191 |
thur | +1.133 |
phia | +1.082 |
י� | +1.067 |
chio | +1.060 |
Neg logit contributions | |
�� | -0.913 |
Belg | -0.874 |
uss | -0.850 |
rol | -0.830 |
roid | -0.814 |
Token | more |
Token ID | 517 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
terness | +1.368 |
thur | +1.304 |
phia | +1.245 |
י� | +1.228 |
chio | +1.220 |
Neg logit contributions | |
�� | -1.017 |
Belg | -0.970 |
uss | -0.942 |
rol | -0.921 |
roid | -0.903 |
Token | ways |
Token ID | 2842 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
terness | +1.380 |
thur | +1.323 |
phia | +1.273 |
י� | +1.257 |
chio | +1.250 |
Neg logit contributions | |
�� | -0.713 |
Belg | -0.676 |
uss | -0.651 |
rol | -0.633 |
roid | -0.615 |
Token | . |
Token ID | 13 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
�� | +1.474 |
Belg | +1.441 |
uss | +1.414 |
rol | +1.374 |
roid | +1.346 |
Neg logit contributions | |
terness | -1.941 |
thur | -1.824 |
phia | -1.742 |
י� | -1.720 |
chio | -1.712 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
terness | +0.811 |
thur | +0.769 |
phia | +0.733 |
י� | +0.720 |
chio | +0.717 |
Neg logit contributions | |
�� | -0.684 |
Belg | -0.662 |
uss | -0.643 |
rol | -0.629 |
roid | -0.617 |
Token | B |
Token ID | 33 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
terness | +1.068 |
thur | +1.007 |
phia | +0.952 |
י� | +0.936 |
chio | +0.928 |
Neg logit contributions | |
�� | -1.196 |
Belg | -1.153 |
uss | -1.126 |
rol | -1.105 |
roid | -1.087 |
Token | rock |
Token ID | 10823 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
terness | +0.146 |
thur | +0.138 |
phia | +0.132 |
י� | +0.130 |
chio | +0.129 |
Neg logit contributions | |
�� | -0.129 |
Belg | -0.123 |
uss | -0.120 |
rol | -0.117 |
roid | -0.115 |
Token | Les |
Token ID | 11732 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
terness | +0.854 |
thur | +0.810 |
phia | +0.770 |
י� | +0.759 |
chio | +0.754 |
Neg logit contributions | |
�� | -0.760 |
Belg | -0.731 |
uss | -0.712 |
rol | -0.698 |
roid | -0.685 |
Token | nar |
Token ID | 23955 |
Feature activation | +9.54e+00 |
Pos logit contributions | |
terness | +1.355 |
thur | +1.260 |
phia | +1.181 |
י� | +1.161 |
renheit | +1.155 |
Neg logit contributions | |
�� | -2.093 |
Belg | -2.043 |
uss | -2.012 |
rol | -1.982 |
roid | -1.945 |
Token | has |
Token ID | 468 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
terness | +7.239 |
thur | +6.977 |
chio | +6.618 |
phia | +6.397 |
TER | +6.363 |
Neg logit contributions | |
�� | -6.894 |
Belg | -6.268 |
rol | -6.025 |
roid | -5.936 |
uss | -5.878 |
Token | been |
Token ID | 587 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
terness | +1.303 |
thur | +1.243 |
phia | +1.179 |
י� | +1.164 |
chio | +1.160 |
Neg logit contributions | |
�� | -1.097 |
Belg | -1.040 |
uss | -1.012 |
rol | -0.992 |
roid | -0.973 |
Token | flagged |
Token ID | 34060 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
�� | +0.753 |
Belg | +0.727 |
uss | +0.707 |
rol | +0.689 |
roid | +0.673 |
Neg logit contributions | |
terness | -1.125 |
thur | -1.072 |
phia | -1.028 |
י� | -1.013 |
renheit | -1.010 |
Token | by |
Token ID | 416 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
�� | +1.282 |
Belg | +1.241 |
uss | +1.212 |
rol | +1.189 |
roid | +1.158 |
Neg logit contributions | |
terness | -1.738 |
thur | -1.642 |
phia | -1.582 |
י� | -1.555 |
renheit | -1.543 |
Token | the |
Token ID | 262 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
�� | +1.735 |
Belg | +1.710 |
uss | +1.669 |
rol | +1.621 |
roid | +1.569 |
Neg logit contributions | |
terness | -2.118 |
thur | -2.017 |
phia | -1.905 |
renheit | -1.892 |
י� | -1.871 |
Token | surgery |
Token ID | 8185 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
�� | +0.827 |
Belg | +0.798 |
uss | +0.777 |
rol | +0.760 |
roid | +0.744 |
Neg logit contributions | |
terness | -1.021 |
thur | -0.968 |
phia | -0.924 |
י� | -0.909 |
renheit | -0.904 |
Token | after |
Token ID | 706 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
terness | +2.184 |
thur | +2.092 |
phia | +1.988 |
י� | +1.967 |
chio | +1.949 |
Neg logit contributions | |
�� | -1.815 |
Belg | -1.707 |
uss | -1.658 |
rol | -1.621 |
roid | -1.593 |
Token | suffering |
Token ID | 7195 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
�� | +1.635 |
Belg | +1.629 |
uss | +1.575 |
rol | +1.533 |
roid | +1.496 |
Neg logit contributions | |
terness | -2.828 |
thur | -2.691 |
phia | -2.590 |
renheit | -2.561 |
י� | -2.554 |
Token | a |
Token ID | 257 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
terness | +3.445 |
thur | +3.335 |
phia | +3.157 |
י� | +3.133 |
chio | +3.080 |
Neg logit contributions | |
�� | -3.477 |
Belg | -3.236 |
uss | -3.139 |
rol | -3.063 |
roid | -2.994 |
Token | fractured |
Token ID | 34051 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
terness | +1.126 |
thur | +1.073 |
phia | +1.023 |
י� | +1.011 |
chio | +1.004 |
Neg logit contributions | |
�� | -0.868 |
Belg | -0.828 |
uss | -0.804 |
rol | -0.785 |
roid | -0.770 |
Token | collar |
Token ID | 19908 |
Feature activation | +9.50e+00 |
Pos logit contributions | |
terness | +2.019 |
thur | +1.922 |
phia | +1.828 |
י� | +1.812 |
chio | +1.800 |
Neg logit contributions | |
�� | -1.830 |
Belg | -1.738 |
uss | -1.690 |
rol | -1.660 |
roid | -1.624 |
Token | bone |
Token ID | 9970 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
terness | +1.552 |
thur | +1.430 |
phia | +1.299 |
chio | +1.275 |
י� | +1.172 |
Neg logit contributions | |
�� | -12.404 |
Belg | -11.767 |
uss | -11.343 |
rol | -11.327 |
roid | -11.069 |
Token | in |
Token ID | 287 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
terness | +0.232 |
thur | +0.220 |
phia | +0.211 |
י� | +0.208 |
renheit | +0.207 |
Neg logit contributions | |
�� | -0.176 |
Belg | -0.169 |
uss | -0.165 |
rol | -0.161 |
roid | -0.158 |
Token | Foot |
Token ID | 7870 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
terness | +0.338 |
thur | +0.323 |
phia | +0.309 |
י� | +0.304 |
chio | +0.303 |
Neg logit contributions | |
�� | -0.252 |
Belg | -0.240 |
uss | -0.232 |
rol | -0.228 |
roid | -0.223 |
Token | sc |
Token ID | 1416 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
terness | +0.204 |
thur | +0.193 |
phia | +0.184 |
י� | +0.182 |
chio | +0.180 |
Neg logit contributions | |
�� | -0.181 |
Belg | -0.174 |
uss | -0.170 |
rol | -0.166 |
roid | -0.163 |
Token | ray |
Token ID | 2433 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
�� | +1.087 |
Belg | +1.062 |
uss | +1.046 |
rol | +1.021 |
roid | +0.992 |
Neg logit contributions | |
terness | -1.645 |
thur | -1.563 |
phia | -1.495 |
י� | -1.491 |
renheit | -1.468 |
Token | : |
Token ID | 25 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Belg | +2.051 |
uss | +1.987 |
rol | +1.938 |
�� | +1.917 |
roid | +1.856 |
Neg logit contributions | |
terness | -3.503 |
thur | -3.285 |
phia | -3.202 |
renheit | -3.124 |
chio | -3.061 |
Token | New |
Token ID | 968 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
�� | +0.166 |
Belg | +0.161 |
uss | +0.156 |
rol | +0.153 |
roid | +0.150 |
Neg logit contributions | |
terness | -0.192 |
thur | -0.182 |
phia | -0.173 |
י� | -0.170 |
renheit | -0.170 |
Token | Insight |
Token ID | 39917 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
�� | +2.102 |
Belg | +2.065 |
uss | +1.974 |
rol | +1.929 |
roid | +1.901 |
Neg logit contributions | |
terness | -3.240 |
thur | -3.054 |
renheit | -2.929 |
phia | -2.921 |
י� | -2.885 |
Token | Into |
Token ID | 20008 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
�� | +0.829 |
Belg | +0.804 |
uss | +0.780 |
rol | +0.762 |
roid | +0.747 |
Neg logit contributions | |
terness | -1.027 |
thur | -0.982 |
phia | -0.935 |
י� | -0.921 |
chio | -0.917 |
Token | How |
Token ID | 1374 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
�� | +0.366 |
Belg | +0.354 |
uss | +0.343 |
rol | +0.336 |
roid | +0.330 |
Neg logit contributions | |
terness | -0.446 |
thur | -0.424 |
phia | -0.403 |
י� | -0.398 |
renheit | -0.396 |
Token | Bees |
Token ID | 46698 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
�� | +1.070 |
Belg | +1.039 |
uss | +1.006 |
rol | +0.983 |
roid | +0.965 |
Neg logit contributions | |
terness | -1.347 |
thur | -1.280 |
phia | -1.218 |
renheit | -1.201 |
י� | -1.201 |
Token | See |
Token ID | 4091 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
Belg | +6.888 |
uss | +6.709 |
�� | +6.566 |
rol | +6.426 |
roid | +6.201 |
Neg logit contributions | |
terness | -10.510 |
thur | -10.006 |
renheit | -9.860 |
phia | -9.496 |
DEN | -9.252 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Belg | +3.195 |
�� | +3.186 |
uss | +3.087 |
rol | +3.017 |
roid | +2.921 |
Neg logit contributions | |
terness | -3.972 |
thur | -3.696 |
phia | -3.572 |
renheit | -3.523 |
י� | -3.513 |
Token | The |
Token ID | 464 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
terness | +1.002 |
thur | +0.944 |
phia | +0.893 |
י� | +0.877 |
chio | +0.870 |
Neg logit contributions | |
�� | -1.119 |
Belg | -1.080 |
uss | -1.055 |
rol | -1.036 |
roid | -1.019 |
Token | fuss |
Token ID | 34297 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
�� | +0.344 |
Belg | +0.334 |
uss | +0.323 |
rol | +0.316 |
roid | +0.310 |
Neg logit contributions | |
terness | -0.434 |
thur | -0.412 |
phia | -0.393 |
י� | -0.387 |
renheit | -0.385 |
Token | is |
Token ID | 318 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
�� | +2.041 |
Belg | +1.979 |
uss | +1.929 |
rol | +1.897 |
roid | +1.867 |
Neg logit contributions | |
terness | -3.102 |
thur | -2.987 |
phia | -2.835 |
י� | -2.827 |
renheit | -2.802 |
Token | last |
Token ID | 938 |
Feature activation | -4.30e-03 |
Pos logit contributions | |
�� | +0.925 |
Belg | +0.902 |
uss | +0.887 |
rol | +0.871 |
roid | +0.848 |
Neg logit contributions | |
terness | -1.087 |
thur | -1.030 |
phia | -0.982 |
י� | -0.965 |
renheit | -0.961 |
Token | one |
Token ID | 530 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
�� | +0.003 |
Belg | +0.003 |
uss | +0.003 |
rol | +0.002 |
roid | +0.002 |
Neg logit contributions | |
terness | -0.004 |
thur | -0.004 |
phia | -0.004 |
י� | -0.004 |
renheit | -0.003 |
Token | is |
Token ID | 318 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
terness | +1.716 |
thur | +1.632 |
phia | +1.553 |
י� | +1.538 |
chio | +1.522 |
Neg logit contributions | |
�� | -1.410 |
Belg | -1.335 |
uss | -1.299 |
rol | -1.270 |
roid | -1.247 |
Token | standing |
Token ID | 5055 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
terness | +0.686 |
thur | +0.651 |
phia | +0.622 |
י� | +0.612 |
chio | +0.608 |
Neg logit contributions | |
�� | -0.530 |
Belg | -0.513 |
uss | -0.498 |
rol | -0.486 |
roid | -0.476 |
Token | against |
Token ID | 1028 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
�� | +1.052 |
Belg | +1.049 |
uss | +1.008 |
rol | +0.990 |
roid | +0.953 |
Neg logit contributions | |
terness | -1.611 |
thur | -1.521 |
phia | -1.467 |
renheit | -1.442 |
י� | -1.442 |
Token | Boris |
Token ID | 25026 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
�� | +0.888 |
Belg | +0.871 |
uss | +0.842 |
rol | +0.824 |
roid | +0.805 |
Neg logit contributions | |
terness | -1.040 |
thur | -0.979 |
phia | -0.939 |
י� | -0.919 |
chio | -0.917 |
Token | ). |
Token ID | 737 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Belg | +5.956 |
uss | +5.804 |
rol | +5.717 |
�� | +5.382 |
fitt | +5.029 |
Neg logit contributions | |
terness | -11.391 |
thur | -10.874 |
renheit | -10.584 |
phia | -10.496 |
י� | -10.281 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
�� | +1.037 |
Belg | +1.026 |
uss | +0.994 |
rol | +0.976 |
roid | +0.948 |
Neg logit contributions | |
terness | -1.083 |
thur | -1.018 |
phia | -0.966 |
renheit | -0.944 |
chio | -0.944 |
Token |
|
Token ID | 198 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
terness | +0.900 |
thur | +0.848 |
phia | +0.801 |
י� | +0.787 |
chio | +0.780 |
Neg logit contributions | |
�� | -1.013 |
Belg | -0.979 |
uss | -0.957 |
rol | -0.940 |
roid | -0.924 |
Token | But |
Token ID | 1537 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
terness | +0.029 |
thur | +0.027 |
phia | +0.025 |
renheit | +0.024 |
י� | +0.024 |
Neg logit contributions | |
�� | -0.033 |
Belg | -0.032 |
uss | -0.032 |
rol | -0.031 |
roid | -0.030 |
Token | that |
Token ID | 326 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
terness | +2.621 |
thur | +2.497 |
phia | +2.376 |
י� | +2.332 |
chio | +2.318 |
Neg logit contributions | |
�� | -2.327 |
Belg | -2.175 |
uss | -2.123 |
rol | -2.073 |
roid | -2.056 |
Token | post |
Token ID | 1281 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
�� | +0.294 |
Belg | +0.284 |
uss | +0.274 |
rol | +0.268 |
roid | +0.262 |
Neg logit contributions | |
terness | -0.403 |
thur | -0.381 |
phia | -0.363 |
י� | -0.360 |
renheit | -0.359 |
Token | G |
Token ID | 402 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
�� | +1.756 |
Belg | +1.709 |
uss | +1.661 |
rol | +1.616 |
roid | +1.590 |
Neg logit contributions | |
terness | -2.262 |
thur | -2.137 |
phia | -2.042 |
י� | -2.011 |
renheit | -2.011 |
Token | WAR |
Token ID | 16279 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
�� | +2.143 |
uss | +2.124 |
Belg | +2.107 |
rol | +2.090 |
roid | +2.067 |
Neg logit contributions | |
terness | -1.522 |
thur | -1.380 |
phia | -1.336 |
chio | -1.282 |
renheit | -1.279 |
Token | Eternal |
Token ID | 21475 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
�� | +1.130 |
Belg | +1.088 |
uss | +1.052 |
rol | +1.025 |
roid | +1.007 |
Neg logit contributions | |
terness | -1.652 |
thur | -1.573 |
phia | -1.505 |
י� | -1.482 |
renheit | -1.481 |
Token | Tour |
Token ID | 9852 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
�� | +1.032 |
Belg | +0.985 |
uss | +0.942 |
rol | +0.898 |
roid | +0.871 |
Neg logit contributions | |
terness | -2.794 |
thur | -2.674 |
phia | -2.589 |
renheit | -2.569 |
י� | -2.562 |
Token | Beaut |
Token ID | 13711 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
�� | +2.244 |
Belg | +2.192 |
uss | +2.134 |
rol | +2.063 |
roid | +2.020 |
Neg logit contributions | |
terness | -2.972 |
thur | -2.797 |
phia | -2.679 |
renheit | -2.658 |
י� | -2.642 |
Token | ifully |
Token ID | 17049 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
uss | +6.399 |
�� | +6.271 |
rol | +6.089 |
Belg | +6.007 |
roid | +5.910 |
Neg logit contributions | |
terness | -10.338 |
thur | -9.976 |
phia | -9.617 |
renheit | -9.485 |
י� | -9.476 |
Token | Paid |
Token ID | 47355 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
�� | +1.689 |
Belg | +1.648 |
uss | +1.598 |
rol | +1.559 |
roid | +1.521 |
Neg logit contributions | |
terness | -2.198 |
thur | -2.091 |
phia | -1.993 |
renheit | -1.960 |
י� | -1.950 |
Token | Hom |
Token ID | 8074 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
�� | +1.999 |
Belg | +1.954 |
uss | +1.898 |
rol | +1.848 |
roid | +1.807 |
Neg logit contributions | |
terness | -3.052 |
thur | -2.884 |
phia | -2.779 |
renheit | -2.751 |
chio | -2.731 |
Token | age |
Token ID | 496 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
terness | +1.118 |
thur | +1.042 |
phia | +0.971 |
י� | +0.950 |
chio | +0.941 |
Neg logit contributions | |
�� | -1.731 |
Belg | -1.677 |
uss | -1.642 |
rol | -1.617 |
roid | -1.594 |
Token | To |
Token ID | 1675 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
�� | +0.216 |
Belg | +0.207 |
uss | +0.201 |
rol | +0.197 |
roid | +0.193 |
Neg logit contributions | |
terness | -0.278 |
thur | -0.264 |
phia | -0.252 |
י� | -0.249 |
chio | -0.247 |
Token | former |
Token ID | 1966 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
Belg | +2.123 |
�� | +2.101 |
uss | +2.049 |
rol | +2.039 |
roid | +1.949 |
Neg logit contributions | |
terness | -2.784 |
thur | -2.618 |
renheit | -2.506 |
phia | -2.502 |
chio | -2.478 |
Token | India |
Token ID | 3794 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
terness | +0.556 |
thur | +0.528 |
phia | +0.504 |
י� | +0.497 |
chio | +0.493 |
Neg logit contributions | |
�� | -0.447 |
Belg | -0.431 |
uss | -0.419 |
rol | -0.410 |
roid | -0.401 |
Token | captain |
Token ID | 10654 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
�� | +0.267 |
Belg | +0.257 |
uss | +0.250 |
rol | +0.244 |
roid | +0.238 |
Neg logit contributions | |
terness | -0.394 |
thur | -0.375 |
phia | -0.359 |
י� | -0.355 |
renheit | -0.353 |
Token | , |
Token ID | 11 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
terness | +0.835 |
thur | +0.795 |
phia | +0.758 |
י� | +0.748 |
chio | +0.743 |
Neg logit contributions | |
�� | -0.652 |
Belg | -0.626 |
uss | -0.608 |
rol | -0.595 |
roid | -0.583 |
Token | Rahul |
Token ID | 48543 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
terness | +0.076 |
thur | +0.072 |
phia | +0.069 |
י� | +0.068 |
chio | +0.068 |
Neg logit contributions | |
�� | -0.061 |
Belg | -0.058 |
uss | -0.057 |
rol | -0.056 |
roid | -0.054 |
Token | D |
Token ID | 360 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
�� | +0.937 |
Belg | +0.895 |
uss | +0.868 |
rol | +0.846 |
roid | +0.826 |
Neg logit contributions | |
terness | -1.482 |
thur | -1.414 |
phia | -1.357 |
י� | -1.342 |
chio | -1.331 |
Token | rav |
Token ID | 4108 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
uss | +6.473 |
rol | +6.016 |
Belg | +5.671 |
roid | +5.467 |
inson | +5.401 |
Neg logit contributions | |
terness | -10.975 |
thur | -9.938 |
י� | -9.877 |
phia | -9.877 |
renheit | -9.858 |
Token | id |
Token ID | 312 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
�� | +2.821 |
uss | +2.799 |
Belg | +2.687 |
rol | +2.639 |
roid | +2.587 |
Neg logit contributions | |
terness | -5.453 |
thur | -5.090 |
phia | -5.008 |
י� | -4.976 |
renheit | -4.961 |
Token | who |
Token ID | 508 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
�� | +0.928 |
Belg | +0.895 |
uss | +0.882 |
rol | +0.868 |
roid | +0.848 |
Neg logit contributions | |
terness | -1.141 |
thur | -1.081 |
phia | -1.036 |
י� | -1.016 |
renheit | -1.013 |
Token | said |
Token ID | 531 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
�� | +1.485 |
Belg | +1.464 |
uss | +1.421 |
rol | +1.394 |
roid | +1.361 |
Neg logit contributions | |
terness | -2.117 |
thur | -1.999 |
phia | -1.919 |
י� | -1.893 |
renheit | -1.892 |
Token | there |
Token ID | 612 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
�� | +0.288 |
Belg | +0.278 |
uss | +0.269 |
rol | +0.263 |
roid | +0.257 |
Neg logit contributions | |
terness | -0.397 |
thur | -0.378 |
phia | -0.362 |
י� | -0.357 |
renheit | -0.355 |
Token | she |
Token ID | 673 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
terness | +1.674 |
thur | +1.591 |
phia | +1.518 |
י� | +1.496 |
chio | +1.489 |
Neg logit contributions | |
�� | -1.454 |
Belg | -1.360 |
uss | -1.330 |
rol | -1.306 |
roid | -1.283 |
Token | calls |
Token ID | 3848 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Belg | +2.137 |
uss | +2.085 |
�� | +2.080 |
rol | +2.002 |
roid | +1.973 |
Neg logit contributions | |
terness | -3.202 |
thur | -3.018 |
phia | -2.891 |
renheit | -2.873 |
י� | -2.871 |
Token | the |
Token ID | 262 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
�� | +1.040 |
Belg | +1.007 |
uss | +0.981 |
rol | +0.959 |
roid | +0.944 |
Neg logit contributions | |
terness | -1.173 |
thur | -1.112 |
phia | -1.058 |
י� | -1.041 |
renheit | -1.034 |
Token | War |
Token ID | 1810 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
�� | +0.604 |
Belg | +0.588 |
uss | +0.572 |
rol | +0.558 |
roid | +0.549 |
Neg logit contributions | |
terness | -0.691 |
thur | -0.654 |
phia | -0.622 |
י� | -0.612 |
renheit | -0.609 |
Token | on |
Token ID | 319 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
terness | +0.995 |
thur | +0.946 |
phia | +0.900 |
י� | +0.886 |
chio | +0.882 |
Neg logit contributions | |
�� | -0.833 |
Belg | -0.795 |
uss | -0.773 |
rol | -0.757 |
roid | -0.742 |
Token | Women |
Token ID | 6926 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
Belg | +1.472 |
�� | +1.455 |
uss | +1.411 |
rol | +1.373 |
roid | +1.320 |
Neg logit contributions | |
terness | -2.341 |
thur | -2.237 |
phia | -2.153 |
renheit | -2.107 |
י� | -2.101 |
Token | in |
Token ID | 287 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
Belg | +6.146 |
uss | +6.023 |
rol | +5.957 |
�� | +5.817 |
roid | +5.571 |
Neg logit contributions | |
terness | -9.638 |
thur | -9.316 |
renheit | -8.854 |
phia | -8.847 |
י� | -8.753 |
Token | politics |
Token ID | 4819 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
�� | +1.585 |
Belg | +1.573 |
uss | +1.521 |
rol | +1.474 |
roid | +1.428 |
Neg logit contributions | |
terness | -1.812 |
thur | -1.711 |
phia | -1.629 |
י� | -1.603 |
renheit | -1.597 |
Token | . |
Token ID | 13 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Belg | +2.745 |
�� | +2.732 |
uss | +2.675 |
rol | +2.583 |
roid | +2.504 |
Neg logit contributions | |
terness | -3.898 |
thur | -3.668 |
phia | -3.504 |
renheit | -3.478 |
י� | -3.453 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
�� | +0.285 |
Belg | +0.280 |
uss | +0.273 |
rol | +0.268 |
roid | +0.264 |
Neg logit contributions | |
terness | -0.194 |
thur | -0.181 |
phia | -0.169 |
י� | -0.165 |
renheit | -0.163 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
terness | +0.901 |
thur | +0.844 |
phia | +0.793 |
י� | +0.779 |
chio | +0.773 |
Neg logit contributions | |
�� | -1.227 |
Belg | -1.179 |
uss | -1.155 |
rol | -1.136 |
roid | -1.122 |
Token | We |
Token ID | 1135 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
terness | +0.589 |
thur | +0.545 |
phia | +0.508 |
chio | +0.494 |
י� | +0.493 |
Neg logit contributions | |
�� | -0.892 |
Belg | -0.878 |
uss | -0.861 |
rol | -0.847 |
roid | -0.834 |
Token | don |
Token ID | 836 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
terness | +0.673 |
thur | +0.638 |
phia | +0.607 |
י� | +0.599 |
renheit | +0.597 |
Neg logit contributions | |
�� | -0.545 |
Belg | -0.529 |
uss | -0.515 |
rol | -0.503 |
roid | -0.493 |
Token | 't |
Token ID | 470 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
terness | +0.302 |
thur | +0.285 |
phia | +0.273 |
י� | +0.268 |
renheit | +0.267 |
Neg logit contributions | |
�� | -0.230 |
Belg | -0.224 |
uss | -0.218 |
rol | -0.213 |
roid | -0.209 |
Token | have |
Token ID | 423 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
terness | +1.460 |
thur | +1.391 |
phia | +1.328 |
י� | +1.307 |
chio | +1.300 |
Neg logit contributions | |
�� | -1.337 |
Belg | -1.264 |
uss | -1.229 |
rol | -1.209 |
roid | -1.185 |
Token | Q |
Token ID | 1195 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
�� | +0.859 |
Belg | +0.838 |
uss | +0.810 |
rol | +0.791 |
roid | +0.772 |
Neg logit contributions | |
terness | -1.149 |
thur | -1.088 |
phia | -1.040 |
י� | -1.023 |
renheit | -1.020 |
Token | d |
Token ID | 67 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
terness | +1.234 |
thur | +1.171 |
phia | +1.108 |
י� | +1.090 |
chio | +1.082 |
Neg logit contributions | |
�� | -1.278 |
Belg | -1.225 |
uss | -1.190 |
rol | -1.170 |
roid | -1.151 |
Token | oba |
Token ID | 19981 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
uss | +8.018 |
rol | +7.937 |
Belg | +7.890 |
roid | +7.820 |
�� | +7.442 |
Neg logit contributions | |
terness | -7.628 |
thur | -6.606 |
י� | -6.550 |
renheit | -6.540 |
chio | -6.425 |
Token | there |
Token ID | 612 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
�� | +1.508 |
Belg | +1.495 |
uss | +1.455 |
rol | +1.422 |
roid | +1.384 |
Neg logit contributions | |
terness | -1.986 |
thur | -1.874 |
phia | -1.775 |
י� | -1.764 |
renheit | -1.757 |
Token | ." |
Token ID | 526 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Belg | +1.691 |
�� | +1.687 |
uss | +1.641 |
rol | +1.603 |
roid | +1.550 |
Neg logit contributions | |
terness | -2.437 |
thur | -2.305 |
phia | -2.190 |
י� | -2.164 |
renheit | -2.163 |
Token |
|
Token ID | 198 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
�� | +0.089 |
Belg | +0.086 |
uss | +0.084 |
rol | +0.083 |
roid | +0.081 |
Neg logit contributions | |
terness | -0.082 |
thur | -0.078 |
phia | -0.074 |
י� | -0.072 |
chio | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | +6.00e-03 |
Pos logit contributions | |
terness | +0.626 |
thur | +0.586 |
phia | +0.555 |
י� | +0.543 |
renheit | +0.540 |
Neg logit contributions | |
�� | -0.667 |
Belg | -0.652 |
uss | -0.638 |
rol | -0.627 |
roid | -0.615 |
Token | industry |
Token ID | 2831 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
terness | +0.906 |
thur | +0.863 |
phia | +0.824 |
י� | +0.812 |
chio | +0.807 |
Neg logit contributions | |
�� | -0.747 |
Belg | -0.710 |
uss | -0.691 |
rol | -0.675 |
roid | -0.664 |
Token | ." |
Token ID | 526 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
�� | +1.077 |
Belg | +1.061 |
uss | +1.028 |
rol | +1.008 |
roid | +0.983 |
Neg logit contributions | |
terness | -1.622 |
thur | -1.546 |
phia | -1.474 |
י� | -1.453 |
renheit | -1.448 |
Token |
|
Token ID | 198 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
terness | +0.338 |
thur | +0.319 |
phia | +0.301 |
י� | +0.296 |
chio | +0.294 |
Neg logit contributions | |
�� | -0.385 |
Belg | -0.371 |
uss | -0.362 |
rol | -0.356 |
roid | -0.350 |
Token |
|
Token ID | 198 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
terness | +1.120 |
thur | +1.058 |
phia | +0.999 |
י� | +0.984 |
chio | +0.976 |
Neg logit contributions | |
�� | -1.311 |
Belg | -1.257 |
uss | -1.228 |
rol | -1.204 |
roid | -1.186 |
Token | Jerry |
Token ID | 43462 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
terness | +0.222 |
thur | +0.208 |
phia | +0.196 |
renheit | +0.192 |
י� | +0.191 |
Neg logit contributions | |
�� | -0.230 |
Belg | -0.225 |
uss | -0.221 |
rol | -0.217 |
roid | -0.213 |
Token | Dw |
Token ID | 19113 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
terness | +4.686 |
thur | +4.479 |
phia | +4.328 |
chio | +4.246 |
י� | +4.232 |
Neg logit contributions | |
�� | -3.778 |
Belg | -3.496 |
uss | -3.455 |
rol | -3.369 |
roid | -3.314 |
Token | or |
Token ID | 273 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
uss | +5.980 |
rol | +5.697 |
roid | +5.578 |
inson | +5.546 |
Belg | +5.423 |
Neg logit contributions | |
terness | -9.582 |
thur | -8.889 |
י� | -8.851 |
renheit | -8.604 |
phia | -8.589 |
Token | ak |
Token ID | 461 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
�� | +1.457 |
uss | +1.434 |
Belg | +1.421 |
rol | +1.411 |
roid | +1.353 |
Neg logit contributions | |
terness | -1.572 |
thur | -1.460 |
phia | -1.413 |
י� | -1.403 |
renheit | -1.374 |
Token | , |
Token ID | 11 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
�� | +0.982 |
Belg | +0.958 |
uss | +0.952 |
rol | +0.931 |
roid | +0.909 |
Neg logit contributions | |
terness | -1.130 |
thur | -1.062 |
phia | -1.018 |
י� | -1.006 |
renheit | -0.997 |
Token | head |
Token ID | 1182 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
terness | +1.466 |
thur | +1.389 |
phia | +1.321 |
י� | +1.303 |
chio | +1.294 |
Neg logit contributions | |
�� | -1.355 |
Belg | -1.290 |
uss | -1.260 |
rol | -1.232 |
roid | -1.215 |
Token | of |
Token ID | 286 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
terness | +3.319 |
thur | +3.126 |
phia | +2.971 |
י� | +2.959 |
chio | +2.894 |
Neg logit contributions | |
�� | -3.657 |
Belg | -3.450 |
uss | -3.351 |
rol | -3.235 |
roid | -3.229 |
Token | Stephen |
Token ID | 7970 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
terness | +0.859 |
thur | +0.814 |
phia | +0.775 |
י� | +0.763 |
chio | +0.757 |
Neg logit contributions | |
�� | -0.807 |
Belg | -0.771 |
uss | -0.753 |
rol | -0.738 |
roid | -0.726 |
Token | Am |
Token ID | 1703 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
terness | +2.154 |
thur | +2.040 |
phia | +1.952 |
chio | +1.916 |
י� | +1.906 |
Neg logit contributions | |
�� | -1.930 |
Belg | -1.826 |
uss | -1.764 |
rol | -1.742 |
roid | -1.727 |
Token | ell |
Token ID | 695 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
uss | +4.317 |
rol | +4.129 |
�� | +4.121 |
Belg | +4.066 |
roid | +4.049 |
Neg logit contributions | |
terness | -4.258 |
thur | -3.931 |
phia | -3.732 |
renheit | -3.731 |
DEN | -3.613 |
Token | and |
Token ID | 290 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
terness | +0.588 |
thur | +0.556 |
phia | +0.527 |
י� | +0.519 |
chio | +0.516 |
Neg logit contributions | |
�� | -0.584 |
Belg | -0.562 |
uss | -0.548 |
rol | -0.537 |
roid | -0.528 |
Token | Robert |
Token ID | 5199 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
terness | +0.388 |
thur | +0.368 |
phia | +0.351 |
י� | +0.345 |
chio | +0.343 |
Neg logit contributions | |
�� | -0.354 |
Belg | -0.339 |
uss | -0.331 |
rol | -0.324 |
roid | -0.318 |
Token | Patt |
Token ID | 24682 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
�� | +0.072 |
Belg | +0.069 |
uss | +0.067 |
rol | +0.065 |
roid | +0.064 |
Neg logit contributions | |
terness | -0.093 |
thur | -0.089 |
phia | -0.085 |
י� | -0.084 |
chio | -0.083 |
Token | inson |
Token ID | 7899 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
inson | +0.871 |
uss | +0.552 |
rol | +0.375 |
roid | -0.022 |
Belg | -0.161 |
Neg logit contributions | |
terness | -15.152 |
thur | -14.331 |
י� | -14.285 |
chio | -14.187 |
phia | -14.143 |
Token | . |
Token ID | 13 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
terness | +0.324 |
thur | +0.307 |
phia | +0.293 |
י� | +0.288 |
chio | +0.286 |
Neg logit contributions | |
�� | -0.274 |
Belg | -0.263 |
uss | -0.256 |
rol | -0.250 |
roid | -0.246 |
Token |
|
Token ID | 198 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
terness | +0.267 |
thur | +0.253 |
phia | +0.240 |
י� | +0.235 |
renheit | +0.234 |
Neg logit contributions | |
�� | -0.255 |
Belg | -0.249 |
uss | -0.242 |
rol | -0.238 |
roid | -0.233 |
Token |
|
Token ID | 198 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
terness | +1.342 |
thur | +1.276 |
phia | +1.202 |
י� | +1.193 |
chio | +1.178 |
Neg logit contributions | |
�� | -1.676 |
Belg | -1.584 |
uss | -1.549 |
rol | -1.518 |
roid | -1.497 |
Token | While |
Token ID | 3633 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
terness | +0.679 |
thur | +0.641 |
phia | +0.607 |
י� | +0.597 |
chio | +0.592 |
Neg logit contributions | |
�� | -0.722 |
Belg | -0.695 |
uss | -0.679 |
rol | -0.666 |
roid | -0.655 |
Token | bound |
Token ID | 7784 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
terness | +1.756 |
thur | +1.666 |
phia | +1.576 |
י� | +1.554 |
chio | +1.539 |
Neg logit contributions | |
�� | -1.777 |
Belg | -1.700 |
uss | -1.657 |
rol | -1.619 |
roid | -1.601 |
Token | on |
Token ID | 319 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
Belg | +1.264 |
�� | +1.264 |
uss | +1.234 |
rol | +1.208 |
roid | +1.152 |
Neg logit contributions | |
terness | -1.737 |
thur | -1.634 |
phia | -1.567 |
י� | -1.544 |
renheit | -1.533 |
Token | East |
Token ID | 3687 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
�� | +2.506 |
Belg | +2.479 |
uss | +2.419 |
rol | +2.396 |
roid | +2.313 |
Neg logit contributions | |
terness | -1.761 |
thur | -1.620 |
phia | -1.513 |
י� | -1.501 |
chio | -1.487 |
Token | 16 |
Token ID | 1467 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
�� | +1.571 |
Belg | +1.566 |
uss | +1.521 |
rol | +1.505 |
roid | +1.448 |
Neg logit contributions | |
terness | -1.566 |
thur | -1.459 |
phia | -1.385 |
י� | -1.377 |
chio | -1.370 |
Token | th |
Token ID | 400 |
Feature activation | -7.43e+00 |
Pos logit contributions | |
Belg | +3.827 |
uss | +3.782 |
�� | +3.748 |
rol | +3.714 |
roid | +3.472 |
Neg logit contributions | |
terness | -4.677 |
thur | -4.330 |
phia | -4.285 |
chio | -4.192 |
י� | -4.171 |
Token | Avenue |
Token ID | 8878 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
Belg | +4.441 |
�� | +4.311 |
uss | +4.274 |
rol | +4.227 |
roid | +3.981 |
Neg logit contributions | |
terness | -6.670 |
thur | -6.216 |
phia | -5.991 |
י� | -5.939 |
chio | -5.890 |
Token | . |
Token ID | 13 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
Belg | +5.974 |
uss | +5.896 |
rol | +5.738 |
�� | +5.357 |
roid | +5.354 |
Neg logit contributions | |
terness | -9.065 |
thur | -8.301 |
phia | -8.175 |
renheit | -7.968 |
י� | -7.893 |
Token |
|
Token ID | 198 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
�� | +0.370 |
Belg | +0.368 |
uss | +0.356 |
rol | +0.350 |
roid | +0.339 |
Neg logit contributions | |
terness | -0.414 |
thur | -0.392 |
phia | -0.373 |
י� | -0.365 |
chio | -0.364 |
Token |
|
Token ID | 198 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
terness | +0.450 |
thur | +0.422 |
phia | +0.399 |
י� | +0.391 |
renheit | +0.388 |
Neg logit contributions | |
�� | -0.486 |
Belg | -0.474 |
uss | -0.464 |
rol | -0.456 |
roid | -0.447 |
Token | The |
Token ID | 464 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
�� | +0.405 |
Belg | +0.396 |
uss | +0.391 |
rol | +0.384 |
roid | +0.375 |
Neg logit contributions | |
terness | -0.414 |
thur | -0.388 |
phia | -0.369 |
renheit | -0.360 |
chio | -0.359 |
Token | woman |
Token ID | 2415 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
�� | +0.930 |
Belg | +0.905 |
uss | +0.878 |
rol | +0.859 |
roid | +0.832 |
Neg logit contributions | |
terness | -1.416 |
thur | -1.346 |
phia | -1.291 |
י� | -1.269 |
renheit | -1.267 |
Token | Trophy |
Token ID | 25640 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
terness | +2.039 |
thur | +1.957 |
phia | +1.860 |
י� | +1.823 |
chio | +1.818 |
Neg logit contributions | |
�� | -1.997 |
Belg | -1.896 |
uss | -1.844 |
rol | -1.809 |
roid | -1.784 |
Token | and |
Token ID | 290 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
terness | +0.503 |
thur | +0.480 |
phia | +0.457 |
י� | +0.451 |
chio | +0.449 |
Neg logit contributions | |
�� | -0.425 |
Belg | -0.405 |
uss | -0.392 |
rol | -0.383 |
roid | -0.379 |
Token | Way |
Token ID | 6378 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
�� | +0.298 |
Belg | +0.288 |
uss | +0.280 |
rol | +0.274 |
roid | +0.268 |
Neg logit contributions | |
terness | -0.372 |
thur | -0.353 |
phia | -0.336 |
י� | -0.331 |
renheit | -0.330 |
Token | man |
Token ID | 805 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
�� | +1.313 |
Belg | +1.289 |
uss | +1.276 |
rol | +1.251 |
roid | +1.217 |
Neg logit contributions | |
terness | -1.401 |
thur | -1.301 |
י� | -1.237 |
phia | -1.235 |
renheit | -1.223 |
Token | T |
Token ID | 309 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
�� | +0.400 |
Belg | +0.384 |
uss | +0.373 |
rol | +0.365 |
roid | +0.356 |
Neg logit contributions | |
terness | -0.561 |
thur | -0.532 |
phia | -0.508 |
י� | -0.502 |
renheit | -0.501 |
Token | isd |
Token ID | 9409 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
�� | +0.051 |
Belg | +0.050 |
uss | +0.049 |
rol | +0.048 |
roid | +0.047 |
Neg logit contributions | |
terness | -0.062 |
thur | -0.059 |
phia | -0.056 |
י� | -0.055 |
renheit | -0.055 |
Token | ale |
Token ID | 1000 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
rol | +4.738 |
uss | +4.629 |
roid | +4.356 |
�� | +4.304 |
Belg | +4.135 |
Neg logit contributions | |
terness | -10.347 |
thur | -9.994 |
phia | -9.607 |
renheit | -9.551 |
י� | -9.490 |
Token | Award |
Token ID | 11289 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
terness | +0.731 |
thur | +0.695 |
phia | +0.662 |
י� | +0.651 |
chio | +0.647 |
Neg logit contributions | |
�� | -0.632 |
Belg | -0.606 |
uss | -0.590 |
rol | -0.577 |
roid | -0.567 |
Token | Watch |
Token ID | 6305 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
terness | +0.783 |
thur | +0.746 |
phia | +0.712 |
י� | +0.702 |
chio | +0.699 |
Neg logit contributions | |
�� | -0.624 |
Belg | -0.595 |
uss | -0.576 |
rol | -0.562 |
roid | -0.555 |
Token | Lists |
Token ID | 44968 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
�� | +0.621 |
Belg | +0.592 |
uss | +0.579 |
rol | +0.567 |
roid | +0.543 |
Neg logit contributions | |
terness | -1.343 |
thur | -1.280 |
phia | -1.238 |
י� | -1.220 |
renheit | -1.215 |
Token | .[ |
Token ID | 3693 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
�� | +1.423 |
Belg | +1.367 |
uss | +1.344 |
rol | +1.318 |
roid | +1.268 |
Neg logit contributions | |
terness | -2.261 |
thur | -2.153 |
phia | -2.063 |
י� | -2.041 |
renheit | -2.031 |
Token | officer |
Token ID | 3818 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
�� | +0.244 |
Belg | +0.238 |
uss | +0.232 |
rol | +0.228 |
roid | +0.224 |
Neg logit contributions | |
terness | -0.214 |
thur | -0.201 |
phia | -0.189 |
י� | -0.186 |
renheit | -0.185 |
Token | , |
Token ID | 11 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
terness | +0.616 |
thur | +0.584 |
phia | +0.556 |
י� | +0.548 |
chio | +0.544 |
Neg logit contributions | |
�� | -0.515 |
Belg | -0.496 |
uss | -0.483 |
rol | -0.473 |
roid | -0.463 |
Token | Ak |
Token ID | 9084 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
terness | +1.042 |
thur | +0.990 |
phia | +0.944 |
י� | +0.927 |
chio | +0.920 |
Neg logit contributions | |
�� | -0.965 |
Belg | -0.919 |
uss | -0.897 |
rol | -0.877 |
roid | -0.866 |
Token | iny |
Token ID | 3541 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
�� | +1.013 |
Belg | +0.994 |
uss | +0.989 |
rol | +0.970 |
roid | +0.940 |
Neg logit contributions | |
terness | -1.079 |
thur | -1.012 |
phia | -0.977 |
י� | -0.970 |
chio | -0.952 |
Token | emi |
Token ID | 43967 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
�� | +1.131 |
Belg | +1.114 |
uss | +1.095 |
rol | +1.069 |
roid | +1.059 |
Neg logit contributions | |
terness | -1.003 |
thur | -0.937 |
phia | -0.887 |
י� | -0.885 |
renheit | -0.875 |
Token | Boris |
Token ID | 25026 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
terness | +1.584 |
thur | +1.510 |
phia | +1.444 |
י� | +1.424 |
chio | +1.418 |
Neg logit contributions | |
�� | -1.203 |
Belg | -1.137 |
uss | -1.111 |
rol | -1.082 |
roid | -1.063 |
Token | ade |
Token ID | 671 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
uss | +7.216 |
rol | +7.057 |
Belg | +7.024 |
�� | +6.954 |
roid | +6.691 |
Neg logit contributions | |
terness | -7.475 |
thur | -6.995 |
י� | -6.779 |
phia | -6.751 |
renheit | -6.688 |
Token | , |
Token ID | 11 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
�� | +3.069 |
Belg | +3.035 |
uss | +2.996 |
rol | +2.959 |
roid | +2.858 |
Neg logit contributions | |
terness | -4.044 |
thur | -3.802 |
phia | -3.657 |
י� | -3.637 |
renheit | -3.587 |
Token | had |
Token ID | 550 |
Feature activation | -2.19e-03 |
Pos logit contributions | |
terness | +0.051 |
thur | +0.049 |
phia | +0.046 |
י� | +0.046 |
chio | +0.045 |
Neg logit contributions | |
�� | -0.040 |
Belg | -0.039 |
uss | -0.038 |
rol | -0.037 |
roid | -0.036 |
Token | only |
Token ID | 691 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
�� | +0.002 |
Belg | +0.002 |
uss | +0.001 |
rol | +0.001 |
roid | +0.001 |
Neg logit contributions | |
terness | -0.002 |
thur | -0.002 |
phia | -0.002 |
י� | -0.002 |
chio | -0.002 |
Token | been |
Token ID | 587 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
�� | +1.370 |
Belg | +1.353 |
uss | +1.304 |
rol | +1.285 |
roid | +1.254 |
Neg logit contributions | |
terness | -1.705 |
thur | -1.608 |
phia | -1.532 |
י� | -1.507 |
renheit | -1.506 |
Token | , |
Token ID | 11 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
terness | +3.451 |
thur | +3.242 |
phia | +3.095 |
י� | +3.079 |
chio | +3.014 |
Neg logit contributions | |
�� | -3.213 |
Belg | -3.019 |
uss | -2.924 |
rol | -2.870 |
roid | -2.833 |
Token | that |
Token ID | 326 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
terness | +0.885 |
thur | +0.842 |
phia | +0.805 |
י� | +0.795 |
chio | +0.789 |
Neg logit contributions | |
�� | -0.642 |
Belg | -0.609 |
uss | -0.591 |
rol | -0.578 |
roid | -0.568 |
Token | will |
Token ID | 481 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
�� | +0.050 |
Belg | +0.048 |
uss | +0.046 |
rol | +0.045 |
roid | +0.044 |
Neg logit contributions | |
terness | -0.065 |
thur | -0.062 |
phia | -0.059 |
י� | -0.058 |
chio | -0.058 |
Token | no |
Token ID | 645 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
terness | +2.137 |
thur | +2.036 |
phia | +1.940 |
י� | +1.917 |
chio | +1.902 |
Neg logit contributions | |
�� | -1.698 |
Belg | -1.611 |
uss | -1.564 |
rol | -1.524 |
roid | -1.499 |
Token | - |
Token ID | 12 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
terness | +0.691 |
thur | +0.661 |
phia | +0.631 |
י� | +0.626 |
chio | +0.621 |
Neg logit contributions | |
�� | -0.442 |
Belg | -0.417 |
uss | -0.403 |
rol | -0.394 |
roid | -0.387 |
Token | d |
Token ID | 67 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
�� | +3.601 |
uss | +3.568 |
Belg | +3.563 |
rol | +3.411 |
roid | +3.326 |
Neg logit contributions | |
terness | -4.155 |
thur | -3.855 |
phia | -3.744 |
renheit | -3.718 |
י� | -3.677 |
Token | oubt |
Token ID | 47675 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
uss | +5.069 |
Belg | +4.719 |
roid | +4.645 |
rol | +4.637 |
�� | +4.386 |
Neg logit contributions | |
terness | -10.141 |
thur | -9.358 |
י� | -9.323 |
phia | -9.317 |
renheit | -9.222 |
Token | reach |
Token ID | 3151 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
�� | +0.128 |
Belg | +0.125 |
uss | +0.121 |
rol | +0.118 |
roid | +0.116 |
Neg logit contributions | |
terness | -0.160 |
thur | -0.152 |
phia | -0.145 |
י� | -0.143 |
renheit | -0.142 |
Token | fever |
Token ID | 17372 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
terness | +2.636 |
thur | +2.517 |
phia | +2.397 |
י� | +2.353 |
renheit | +2.328 |
Neg logit contributions | |
�� | -2.069 |
Belg | -1.937 |
uss | -1.892 |
rol | -1.857 |
roid | -1.825 |
Token | pitch |
Token ID | 7078 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
terness | +1.442 |
thur | +1.355 |
phia | +1.273 |
י� | +1.250 |
chio | +1.240 |
Neg logit contributions | |
�� | -1.807 |
Belg | -1.741 |
uss | -1.704 |
rol | -1.676 |
roid | -1.649 |
Token | around |
Token ID | 1088 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
terness | +1.064 |
thur | +1.013 |
phia | +0.967 |
י� | +0.954 |
chio | +0.947 |
Neg logit contributions | |
�� | -0.812 |
Belg | -0.775 |
uss | -0.753 |
rol | -0.736 |
roid | -0.722 |
Token | in |
Token ID | 287 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
terness | +0.297 |
thur | +0.281 |
phia | +0.267 |
י� | +0.263 |
chio | +0.261 |
Neg logit contributions | |
�� | -0.276 |
Belg | -0.266 |
uss | -0.259 |
rol | -0.254 |
roid | -0.250 |
Token | Boston |
Token ID | 6182 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
�� | +0.303 |
Belg | +0.293 |
uss | +0.284 |
rol | +0.278 |
roid | +0.272 |
Neg logit contributions | |
terness | -0.341 |
thur | -0.324 |
phia | -0.307 |
י� | -0.302 |
chio | -0.301 |
Token | by |
Token ID | 416 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
�� | +1.325 |
Belg | +1.293 |
uss | +1.245 |
rol | +1.232 |
roid | +1.187 |
Neg logit contributions | |
terness | -1.896 |
thur | -1.815 |
phia | -1.727 |
renheit | -1.705 |
י� | -1.699 |
Token | anti |
Token ID | 3098 |
Feature activation | -8.52e+00 |
Pos logit contributions | |
�� | +2.156 |
Belg | +2.121 |
uss | +2.022 |
rol | +1.997 |
roid | +1.934 |
Neg logit contributions | |
terness | -2.510 |
thur | -2.410 |
phia | -2.255 |
chio | -2.240 |
renheit | -2.237 |
Token | - |
Token ID | 12 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
Belg | +4.628 |
uss | +4.601 |
rol | +4.530 |
�� | +4.477 |
roid | +4.318 |
Neg logit contributions | |
terness | -7.985 |
thur | -7.324 |
phia | -7.210 |
chio | -7.170 |
renheit | -7.140 |
Token | street |
Token ID | 25662 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
uss | +2.961 |
�� | +2.944 |
Belg | +2.933 |
rol | +2.902 |
roid | +2.873 |
Neg logit contributions | |
terness | -4.502 |
thur | -4.208 |
renheit | -4.036 |
phia | -4.020 |
chio | -4.015 |
Token | harassment |
Token ID | 10556 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
�� | +4.946 |
Belg | +4.839 |
uss | +4.838 |
rol | +4.820 |
roid | +4.586 |
Neg logit contributions | |
terness | -9.432 |
thur | -9.034 |
phia | -8.594 |
renheit | -8.593 |
chio | -8.520 |
Token | organization |
Token ID | 4009 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Belg | +2.838 |
�� | +2.770 |
uss | +2.720 |
rol | +2.686 |
roid | +2.613 |
Neg logit contributions | |
terness | -3.986 |
thur | -3.799 |
phia | -3.577 |
chio | -3.548 |
renheit | -3.541 |
Token | Holl |
Token ID | 11806 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
�� | +0.215 |
Belg | +0.209 |
uss | +0.202 |
rol | +0.198 |
roid | +0.193 |
Neg logit contributions | |
terness | -0.270 |
thur | -0.258 |
phia | -0.245 |
י� | -0.241 |
chio | -0.240 |
Token | ab |
Token ID | 397 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
�� | +0.519 |
Belg | +0.501 |
uss | +0.492 |
rol | +0.479 |
roid | +0.468 |
Neg logit contributions | |
terness | -0.699 |
thur | -0.663 |
phia | -0.632 |
י� | -0.626 |
chio | -0.625 |
Token | ack |
Token ID | 441 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
terness | +1.889 |
thur | +1.792 |
phia | +1.694 |
י� | +1.672 |
chio | +1.643 |
Neg logit contributions | |
�� | -2.191 |
Belg | -2.077 |
uss | -2.002 |
rol | -1.982 |
roid | -1.952 |
Token | the |
Token ID | 262 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
terness | +0.255 |
thur | +0.242 |
phia | +0.230 |
י� | +0.226 |
renheit | +0.225 |
Neg logit contributions | |
�� | -0.218 |
Belg | -0.211 |
uss | -0.205 |
rol | -0.200 |
roid | -0.196 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
�� | +0.272 |
Belg | +0.264 |
uss | +0.255 |
rol | +0.249 |
roid | +0.244 |
Neg logit contributions | |
terness | -0.337 |
thur | -0.320 |
phia | -0.306 |
י� | -0.300 |
renheit | -0.299 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
�� | +0.219 |
Belg | +0.215 |
uss | +0.208 |
rol | +0.204 |
roid | +0.199 |
Neg logit contributions | |
terness | -0.262 |
thur | -0.248 |
phia | -0.239 |
י� | -0.234 |
renheit | -0.233 |
Token | Orders |
Token ID | 30689 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
�� | +1.283 |
Belg | +1.234 |
uss | +1.207 |
rol | +1.171 |
roid | +1.146 |
Neg logit contributions | |
terness | -1.712 |
thur | -1.633 |
phia | -1.566 |
renheit | -1.540 |
י� | -1.537 |
Token | on |
Token ID | 319 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
�� | +1.714 |
Belg | +1.694 |
uss | +1.631 |
rol | +1.595 |
roid | +1.555 |
Neg logit contributions | |
terness | -2.007 |
thur | -1.920 |
phia | -1.832 |
renheit | -1.812 |
י� | -1.792 |
Token | Aadhaar |
Token ID | 47727 |
Feature activation | -9.99e+00 |
Pos logit contributions | |
�� | +1.599 |
Belg | +1.591 |
uss | +1.528 |
rol | +1.502 |
roid | +1.463 |
Neg logit contributions | |
terness | -1.919 |
thur | -1.797 |
phia | -1.728 |
renheit | -1.698 |
י� | -1.687 |
Token |
|
Token ID | 198 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
Belg | +6.192 |
�� | +5.949 |
uss | +5.905 |
rol | +5.886 |
roid | +5.765 |
Neg logit contributions | |
terness | -8.451 |
thur | -7.922 |
renheit | -7.737 |
phia | -7.595 |
י� | -7.565 |
Token |
|
Token ID | 198 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
�� | +2.006 |
Belg | +1.987 |
uss | +1.938 |
rol | +1.909 |
roid | +1.867 |
Neg logit contributions | |
terness | -2.087 |
thur | -1.950 |
phia | -1.855 |
renheit | -1.813 |
chio | -1.813 |
Token | The |
Token ID | 464 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
�� | +1.805 |
Belg | +1.795 |
uss | +1.783 |
rol | +1.744 |
roid | +1.713 |
Neg logit contributions | |
terness | -1.751 |
thur | -1.627 |
phia | -1.551 |
renheit | -1.522 |
chio | -1.517 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
�� | +0.975 |
Belg | +0.949 |
uss | +0.923 |
rol | +0.901 |
roid | +0.880 |
Neg logit contributions | |
terness | -1.256 |
thur | -1.192 |
phia | -1.146 |
י� | -1.123 |
renheit | -1.121 |
Token | Court |
Token ID | 3078 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
�� | +0.721 |
Belg | +0.710 |
uss | +0.691 |
rol | +0.677 |
roid | +0.658 |
Neg logit contributions | |
terness | -0.891 |
thur | -0.839 |
phia | -0.814 |
י� | -0.791 |
renheit | -0.790 |
Token | we |
Token ID | 356 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
�� | +1.088 |
Belg | +1.058 |
uss | +1.032 |
rol | +1.010 |
roid | +0.985 |
Neg logit contributions | |
terness | -1.431 |
thur | -1.360 |
phia | -1.296 |
י� | -1.281 |
renheit | -1.275 |
Token | will |
Token ID | 481 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
terness | +1.502 |
thur | +1.435 |
phia | +1.363 |
י� | +1.346 |
chio | +1.337 |
Neg logit contributions | |
�� | -1.246 |
Belg | -1.179 |
uss | -1.131 |
rol | -1.107 |
roid | -1.091 |
Token | perform |
Token ID | 1620 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
terness | +0.434 |
thur | +0.414 |
phia | +0.396 |
י� | +0.391 |
chio | +0.389 |
Neg logit contributions | |
�� | -0.298 |
Belg | -0.284 |
uss | -0.274 |
rol | -0.268 |
roid | -0.262 |
Token | meta |
Token ID | 13634 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
�� | +0.453 |
Belg | +0.440 |
uss | +0.428 |
rol | +0.418 |
roid | +0.408 |
Neg logit contributions | |
terness | -0.641 |
thur | -0.608 |
phia | -0.582 |
י� | -0.575 |
renheit | -0.573 |
Token | - |
Token ID | 12 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
�� | +2.412 |
uss | +2.388 |
Belg | +2.376 |
rol | +2.325 |
roid | +2.256 |
Neg logit contributions | |
terness | -3.532 |
thur | -3.317 |
phia | -3.230 |
renheit | -3.181 |
chio | -3.149 |
Token | reg |
Token ID | 2301 |
Feature activation | -9.97e+00 |
Pos logit contributions | |
uss | +5.676 |
rol | +5.573 |
Belg | +5.451 |
roid | +5.444 |
rolling | +5.331 |
Neg logit contributions | |
terness | -4.970 |
thur | -4.446 |
renheit | -4.408 |
chio | -4.317 |
phia | -4.262 |
Token | ression |
Token ID | 2234 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
uss | +2.727 |
rol | +2.675 |
rolling | +2.317 |
istry | +2.290 |
roid | +2.166 |
Neg logit contributions | |
terness | -12.066 |
renheit | -11.366 |
phia | -11.338 |
thur | -11.326 |
chio | -10.983 |
Token | if |
Token ID | 611 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
terness | +1.104 |
thur | +1.050 |
phia | +1.001 |
י� | +0.988 |
chio | +0.980 |
Neg logit contributions | |
�� | -0.893 |
Belg | -0.851 |
uss | -0.824 |
rol | -0.806 |
roid | -0.793 |
Token | a |
Token ID | 257 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
�� | +0.485 |
Belg | +0.470 |
uss | +0.458 |
rol | +0.448 |
roid | +0.437 |
Neg logit contributions | |
terness | -0.635 |
thur | -0.604 |
phia | -0.575 |
י� | -0.569 |
renheit | -0.567 |
Token | sufficient |
Token ID | 6751 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
terness | +0.677 |
thur | +0.647 |
phia | +0.621 |
י� | +0.612 |
chio | +0.610 |
Neg logit contributions | |
�� | -0.450 |
Belg | -0.427 |
uss | -0.412 |
rol | -0.402 |
roid | -0.394 |
Token | number |
Token ID | 1271 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
�� | +1.343 |
Belg | +1.313 |
uss | +1.275 |
rol | +1.245 |
roid | +1.219 |
Neg logit contributions | |
terness | -1.819 |
thur | -1.723 |
phia | -1.647 |
renheit | -1.625 |
י� | -1.621 |
Token | .' |
Token ID | 2637 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
�� | +2.166 |
Belg | +2.103 |
uss | +2.071 |
rol | +2.020 |
roid | +1.975 |
Neg logit contributions | |
terness | -2.479 |
thur | -2.326 |
phia | -2.216 |
י� | -2.198 |
renheit | -2.180 |
Token | s |
Token ID | 82 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
�� | +0.339 |
Belg | +0.337 |
uss | +0.333 |
rol | +0.326 |
roid | +0.321 |
Neg logit contributions | |
terness | -0.238 |
thur | -0.220 |
phia | -0.207 |
renheit | -0.202 |
י� | -0.201 |
Token | lead |
Token ID | 1085 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
�� | +0.282 |
Belg | +0.272 |
uss | +0.264 |
rol | +0.259 |
roid | +0.254 |
Neg logit contributions | |
terness | -0.324 |
thur | -0.307 |
phia | -0.292 |
י� | -0.288 |
chio | -0.286 |
Token | singer |
Token ID | 14015 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
�� | +0.050 |
Belg | +0.047 |
uss | +0.046 |
rol | +0.045 |
roid | +0.044 |
Neg logit contributions | |
terness | -0.064 |
thur | -0.061 |
phia | -0.059 |
י� | -0.058 |
chio | -0.057 |
Token | Michael |
Token ID | 3899 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
terness | +3.504 |
thur | +3.339 |
phia | +3.155 |
י� | +3.112 |
TER | +3.075 |
Neg logit contributions | |
�� | -3.622 |
Belg | -3.399 |
uss | -3.300 |
rol | -3.245 |
roid | -3.222 |
Token | St |
Token ID | 520 |
Feature activation | -9.79e+00 |
Pos logit contributions | |
�� | +1.684 |
Belg | +1.660 |
uss | +1.599 |
rol | +1.561 |
roid | +1.518 |
Neg logit contributions | |
terness | -2.123 |
thur | -2.005 |
phia | -1.896 |
renheit | -1.888 |
י� | -1.882 |
Token | ipe |
Token ID | 3757 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
uss | +6.569 |
Belg | +6.285 |
rol | +6.207 |
�� | +6.061 |
roid | +6.006 |
Neg logit contributions | |
terness | -8.274 |
thur | -7.690 |
י� | -7.571 |
phia | -7.226 |
DEN | -7.156 |
Token | , |
Token ID | 11 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
�� | +1.758 |
Belg | +1.710 |
uss | +1.673 |
rol | +1.648 |
roid | +1.609 |
Neg logit contributions | |
terness | -2.011 |
thur | -1.901 |
phia | -1.814 |
י� | -1.787 |
renheit | -1.778 |
Token | told |
Token ID | 1297 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
�� | +0.387 |
Belg | +0.372 |
uss | +0.362 |
rol | +0.354 |
roid | +0.346 |
Neg logit contributions | |
terness | -0.492 |
thur | -0.468 |
phia | -0.447 |
י� | -0.440 |
chio | -0.437 |
Token | Newsweek |
Token ID | 39594 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
�� | +0.955 |
Belg | +0.937 |
uss | +0.903 |
rol | +0.882 |
roid | +0.862 |
Neg logit contributions | |
terness | -1.225 |
thur | -1.160 |
phia | -1.105 |
י� | -1.088 |
renheit | -1.085 |
Token | in |
Token ID | 287 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
�� | +0.875 |
Belg | +0.844 |
uss | +0.820 |
rol | +0.802 |
roid | +0.786 |
Neg logit contributions | |
terness | -1.077 |
thur | -1.023 |
phia | -0.974 |
י� | -0.962 |
chio | -0.954 |
Token | a |
Token ID | 64 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
terness | +2.112 |
thur | +1.991 |
phia | +1.896 |
י� | +1.848 |
chio | +1.845 |
Neg logit contributions | |
�� | -2.563 |
Belg | -2.442 |
uss | -2.370 |
rol | -2.325 |
roid | -2.310 |
Token | mission |
Token ID | 4365 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
Belg | +2.385 |
�� | +2.344 |
uss | +2.344 |
rol | +2.295 |
roid | +2.191 |
Neg logit contributions | |
terness | -3.010 |
thur | -2.845 |
phia | -2.715 |
renheit | -2.713 |
י� | -2.693 |
Token | manager |
Token ID | 4706 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Belg | +2.376 |
�� | +2.344 |
uss | +2.306 |
rol | +2.271 |
roid | +2.171 |
Neg logit contributions | |
terness | -3.663 |
thur | -3.470 |
phia | -3.334 |
י� | -3.300 |
renheit | -3.292 |
Token | Dr |
Token ID | 1583 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
terness | +0.822 |
thur | +0.780 |
phia | +0.742 |
י� | +0.730 |
chio | +0.725 |
Neg logit contributions | |
�� | -0.741 |
Belg | -0.709 |
uss | -0.692 |
rol | -0.678 |
roid | -0.666 |
Token | Rune |
Token ID | 28228 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
�� | +1.981 |
Belg | +1.972 |
uss | +1.904 |
rol | +1.872 |
roid | +1.799 |
Neg logit contributions | |
terness | -2.254 |
thur | -2.141 |
phia | -2.036 |
י� | -1.998 |
renheit | -1.995 |
Token | Fl |
Token ID | 1610 |
Feature activation | -9.75e+00 |
Pos logit contributions | |
�� | +0.719 |
Belg | +0.699 |
uss | +0.680 |
rol | +0.663 |
roid | +0.648 |
Neg logit contributions | |
terness | -0.919 |
thur | -0.870 |
phia | -0.833 |
י� | -0.823 |
renheit | -0.816 |
Token | ober |
Token ID | 2023 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
uss | +7.331 |
rol | +6.860 |
Belg | +6.676 |
roid | +6.599 |
inson | +6.497 |
Neg logit contributions | |
terness | -7.124 |
thur | -6.613 |
י� | -6.528 |
renheit | -6.297 |
DEN | -6.286 |
Token | gh |
Token ID | 456 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
terness | +1.135 |
thur | +1.075 |
phia | +1.007 |
chio | +0.985 |
י� | +0.983 |
Neg logit contributions | |
�� | -1.375 |
Belg | -1.315 |
uss | -1.281 |
rol | -1.254 |
roid | -1.238 |
Token | agen |
Token ID | 11286 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
terness | +3.636 |
thur | +3.506 |
chio | +3.260 |
phia | +3.249 |
י� | +3.217 |
Neg logit contributions | |
�� | -3.560 |
Belg | -3.319 |
uss | -3.120 |
rol | -3.099 |
roid | -3.085 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
terness | +0.518 |
thur | +0.491 |
phia | +0.469 |
י� | +0.461 |
chio | +0.458 |
Neg logit contributions | |
�� | -0.443 |
Belg | -0.428 |
uss | -0.417 |
rol | -0.408 |
roid | -0.399 |
Token |
|
Token ID | 198 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
terness | +1.612 |
thur | +1.522 |
phia | +1.432 |
י� | +1.414 |
chio | +1.404 |
Neg logit contributions | |
�� | -1.915 |
Belg | -1.829 |
uss | -1.790 |
rol | -1.753 |
roid | -1.730 |
Token | . |
Token ID | 13 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
�� | +1.863 |
Belg | +1.844 |
uss | +1.812 |
rol | +1.787 |
roid | +1.705 |
Neg logit contributions | |
terness | -2.583 |
thur | -2.471 |
phia | -2.371 |
chio | -2.317 |
renheit | -2.302 |
Token | At |
Token ID | 1629 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
�� | +0.539 |
Belg | +0.528 |
uss | +0.513 |
rol | +0.505 |
roid | +0.491 |
Neg logit contributions | |
terness | -0.554 |
thur | -0.527 |
phia | -0.499 |
י� | -0.488 |
chio | -0.488 |
Token | least |
Token ID | 1551 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
�� | +1.335 |
Belg | +1.288 |
uss | +1.245 |
rol | +1.219 |
roid | +1.184 |
Neg logit contributions | |
terness | -1.995 |
thur | -1.903 |
phia | -1.823 |
י� | -1.799 |
chio | -1.785 |
Token | 250 |
Token ID | 8646 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
Belg | +2.952 |
�� | +2.832 |
uss | +2.804 |
rol | +2.737 |
roid | +2.640 |
Neg logit contributions | |
terness | -4.659 |
thur | -4.395 |
phia | -4.228 |
renheit | -4.173 |
י� | -4.166 |
Token | people |
Token ID | 661 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
Belg | +2.575 |
�� | +2.543 |
uss | +2.491 |
rol | +2.463 |
roid | +2.363 |
Neg logit contributions | |
terness | -3.140 |
thur | -3.020 |
phia | -2.848 |
chio | -2.824 |
renheit | -2.809 |
Token | cycle |
Token ID | 6772 |
Feature activation | -9.74e+00 |
Pos logit contributions | |
Belg | +2.096 |
�� | +2.065 |
uss | +2.034 |
rol | +2.001 |
roid | +1.918 |
Neg logit contributions | |
terness | -2.947 |
thur | -2.805 |
phia | -2.649 |
renheit | -2.611 |
chio | -2.599 |
Token | in |
Token ID | 287 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
Belg | +5.711 |
uss | +5.507 |
rol | +5.504 |
�� | +5.167 |
roid | +5.069 |
Neg logit contributions | |
terness | -8.760 |
thur | -8.198 |
chio | -7.825 |
phia | -7.803 |
renheit | -7.779 |
Token | and |
Token ID | 290 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
�� | +2.428 |
Belg | +2.389 |
uss | +2.339 |
rol | +2.303 |
roid | +2.226 |
Neg logit contributions | |
terness | -3.036 |
thur | -2.869 |
phia | -2.728 |
chio | -2.696 |
י� | -2.683 |
Token | out |
Token ID | 503 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
�� | +0.418 |
Belg | +0.401 |
uss | +0.388 |
rol | +0.378 |
roid | +0.366 |
Neg logit contributions | |
terness | -0.732 |
thur | -0.700 |
phia | -0.672 |
י� | -0.662 |
chio | -0.660 |
Token | of |
Token ID | 286 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
terness | +0.415 |
thur | +0.393 |
phia | +0.373 |
י� | +0.368 |
chio | +0.365 |
Neg logit contributions | |
�� | -0.386 |
Belg | -0.370 |
uss | -0.361 |
rol | -0.353 |
roid | -0.348 |
Token | the |
Token ID | 262 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
�� | +1.843 |
Belg | +1.806 |
uss | +1.755 |
rol | +1.728 |
roid | +1.682 |
Neg logit contributions | |
terness | -2.071 |
thur | -1.977 |
phia | -1.861 |
chio | -1.834 |
י� | -1.832 |
Token | companies |
Token ID | 2706 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
terness | +2.000 |
thur | +1.900 |
phia | +1.805 |
י� | +1.779 |
chio | +1.768 |
Neg logit contributions | |
�� | -1.799 |
Belg | -1.721 |
uss | -1.676 |
rol | -1.640 |
roid | -1.611 |
Token | letter |
Token ID | 3850 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
terness | +0.647 |
thur | +0.614 |
phia | +0.586 |
י� | +0.577 |
chio | +0.574 |
Neg logit contributions | |
�� | -0.562 |
Belg | -0.534 |
uss | -0.520 |
rol | -0.509 |
roid | -0.500 |
Token | to |
Token ID | 284 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
�� | +1.463 |
Belg | +1.422 |
uss | +1.384 |
rol | +1.351 |
roid | +1.322 |
Neg logit contributions | |
terness | -2.003 |
thur | -1.910 |
phia | -1.830 |
י� | -1.793 |
renheit | -1.788 |
Token | Sen |
Token ID | 2311 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
�� | +0.324 |
Belg | +0.318 |
uss | +0.309 |
rol | +0.303 |
roid | +0.296 |
Neg logit contributions | |
terness | -0.353 |
thur | -0.333 |
phia | -0.317 |
renheit | -0.310 |
י� | -0.310 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
terness | +0.922 |
thur | +0.881 |
phia | +0.834 |
י� | +0.825 |
chio | +0.821 |
Neg logit contributions | |
�� | -0.817 |
Belg | -0.782 |
uss | -0.757 |
rol | -0.741 |
roid | -0.731 |
Token | Patty |
Token ID | 42417 |
Feature activation | -9.73e+00 |
Pos logit contributions | |
Belg | +1.768 |
�� | +1.765 |
uss | +1.706 |
rol | +1.681 |
roid | +1.636 |
Neg logit contributions | |
terness | -1.943 |
thur | -1.814 |
phia | -1.739 |
renheit | -1.695 |
י� | -1.673 |
Token | Murray |
Token ID | 12164 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
Belg | +4.381 |
rol | +4.217 |
roid | +4.183 |
uss | +4.181 |
�� | +4.021 |
Neg logit contributions | |
terness | -9.947 |
thur | -9.842 |
renheit | -9.145 |
phia | -9.127 |
י� | -9.010 |
Token | , |
Token ID | 11 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
�� | +0.550 |
Belg | +0.533 |
uss | +0.519 |
rol | +0.509 |
roid | +0.498 |
Neg logit contributions | |
terness | -0.660 |
thur | -0.628 |
phia | -0.602 |
י� | -0.591 |
renheit | -0.587 |
Token | Chair |
Token ID | 9369 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
�� | +0.873 |
Belg | +0.849 |
uss | +0.820 |
rol | +0.801 |
roid | +0.780 |
Neg logit contributions | |
terness | -1.229 |
thur | -1.170 |
phia | -1.120 |
י� | -1.105 |
renheit | -1.098 |
Token | , |
Token ID | 11 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
terness | +2.847 |
thur | +2.698 |
phia | +2.547 |
י� | +2.521 |
chio | +2.501 |
Neg logit contributions | |
�� | -2.590 |
Belg | -2.479 |
uss | -2.402 |
rol | -2.339 |
roid | -2.310 |
Token | Democratic |
Token ID | 4390 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
terness | +0.274 |
thur | +0.260 |
phia | +0.248 |
י� | +0.244 |
renheit | +0.243 |
Neg logit contributions | |
�� | -0.229 |
Belg | -0.221 |
uss | -0.215 |
rol | -0.210 |
roid | -0.206 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
terness | +0.069 |
thur | +0.066 |
phia | +0.063 |
י� | +0.062 |
chio | +0.062 |
Neg logit contributions | |
�� | -0.050 |
Belg | -0.048 |
uss | -0.047 |
rol | -0.046 |
roid | -0.045 |
Token | say |
Token ID | 910 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
�� | +0.661 |
Belg | +0.645 |
uss | +0.633 |
rol | +0.615 |
roid | +0.605 |
Neg logit contributions | |
terness | -0.907 |
thur | -0.860 |
phia | -0.823 |
renheit | -0.814 |
י� | -0.805 |
Token | today |
Token ID | 1909 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
�� | +0.066 |
Belg | +0.064 |
uss | +0.063 |
rol | +0.061 |
roid | +0.060 |
Neg logit contributions | |
terness | -0.078 |
thur | -0.074 |
phia | -0.070 |
י� | -0.069 |
chio | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
terness | +2.158 |
thur | +2.045 |
phia | +1.942 |
י� | +1.924 |
chio | +1.907 |
Neg logit contributions | |
�� | -1.923 |
Belg | -1.837 |
uss | -1.785 |
rol | -1.744 |
roid | -1.717 |
Token | about |
Token ID | 546 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
terness | +0.197 |
thur | +0.187 |
phia | +0.179 |
י� | +0.177 |
chio | +0.176 |
Neg logit contributions | |
�� | -0.134 |
Belg | -0.128 |
uss | -0.124 |
rol | -0.121 |
roid | -0.118 |
Token | Dw |
Token ID | 19113 |
Feature activation | -9.71e+00 |
Pos logit contributions | |
terness | +1.143 |
thur | +1.092 |
phia | +1.038 |
י� | +1.028 |
chio | +1.018 |
Neg logit contributions | |
�� | -0.945 |
Belg | -0.894 |
uss | -0.865 |
rol | -0.849 |
roid | -0.838 |
Token | y |
Token ID | 88 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
uss | +3.204 |
rol | +3.136 |
Belg | +3.045 |
�� | +2.975 |
roid | +2.941 |
Neg logit contributions | |
terness | -11.336 |
phia | -10.389 |
thur | -10.233 |
י� | -9.955 |
DEN | -9.871 |
Token | ane |
Token ID | 1531 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
uss | +3.435 |
Belg | +3.412 |
rol | +3.351 |
roid | +3.276 |
�� | +3.223 |
Neg logit contributions | |
terness | -2.920 |
thur | -2.632 |
renheit | -2.483 |
phia | -2.463 |
י� | -2.412 |
Token | Wade |
Token ID | 19136 |
Feature activation | -7.91e+00 |
Pos logit contributions | |
�� | +2.621 |
Belg | +2.483 |
uss | +2.332 |
rol | +2.270 |
roid | +2.172 |
Neg logit contributions | |
terness | -6.397 |
thur | -6.055 |
phia | -5.922 |
renheit | -5.817 |
chio | -5.777 |
Token | , |
Token ID | 11 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
�� | +4.666 |
uss | +4.588 |
rol | +4.571 |
Belg | +4.473 |
roid | +4.249 |
Neg logit contributions | |
terness | -6.832 |
thur | -6.506 |
phia | -6.404 |
chio | -6.178 |
י� | -6.143 |
Token | Chris |
Token ID | 5180 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
�� | +0.337 |
Belg | +0.323 |
uss | +0.315 |
rol | +0.308 |
roid | +0.303 |
Neg logit contributions | |
terness | -0.380 |
thur | -0.361 |
phia | -0.343 |
י� | -0.338 |
chio | -0.336 |
Token | rock |
Token ID | 3881 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
terness | +0.320 |
thur | +0.304 |
phia | +0.290 |
י� | +0.286 |
chio | +0.284 |
Neg logit contributions | |
�� | -0.255 |
Belg | -0.245 |
uss | -0.238 |
rol | -0.233 |
roid | -0.229 |
Token | out |
Token ID | 503 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
�� | +1.125 |
Belg | +1.102 |
uss | +1.078 |
rol | +1.044 |
roid | +1.034 |
Neg logit contributions | |
terness | -1.446 |
thur | -1.359 |
phia | -1.298 |
renheit | -1.287 |
י� | -1.287 |
Token | cro |
Token ID | 19915 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
terness | +0.733 |
thur | +0.681 |
phia | +0.635 |
י� | +0.620 |
chio | +0.614 |
Neg logit contributions | |
�� | -1.176 |
Belg | -1.138 |
uss | -1.115 |
rol | -1.097 |
roid | -1.083 |
Token | ps |
Token ID | 862 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
�� | +0.116 |
Belg | +0.114 |
uss | +0.112 |
rol | +0.110 |
roid | +0.109 |
Neg logit contributions | |
terness | -0.068 |
thur | -0.063 |
phia | -0.058 |
י� | -0.058 |
chio | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
�� | +0.878 |
Belg | +0.855 |
uss | +0.835 |
rol | +0.813 |
roid | +0.794 |
Neg logit contributions | |
terness | -1.140 |
thur | -1.078 |
phia | -1.034 |
י� | -1.020 |
renheit | -1.015 |
Token | upper |
Token ID | 6727 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
�� | +0.602 |
Belg | +0.588 |
uss | +0.571 |
rol | +0.558 |
roid | +0.546 |
Neg logit contributions | |
terness | -0.769 |
thur | -0.725 |
phia | -0.694 |
י� | -0.686 |
renheit | -0.682 |
Token | flat |
Token ID | 6228 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
terness | +4.723 |
thur | +4.562 |
phia | +4.385 |
י� | +4.254 |
chio | +4.240 |
Neg logit contributions | |
�� | -4.062 |
Belg | -3.682 |
uss | -3.613 |
rol | -3.531 |
roid | -3.449 |
Token | areas |
Token ID | 3006 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
terness | +1.400 |
thur | +1.333 |
phia | +1.273 |
י� | +1.255 |
chio | +1.247 |
Neg logit contributions | |
�� | -1.060 |
Belg | -1.013 |
uss | -0.984 |
rol | -0.962 |
roid | -0.942 |
Token | . |
Token ID | 13 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
�� | +1.250 |
Belg | +1.227 |
uss | +1.200 |
rol | +1.168 |
roid | +1.142 |
Neg logit contributions | |
terness | -1.629 |
thur | -1.534 |
phia | -1.475 |
י� | -1.452 |
renheit | -1.450 |
Token | If |
Token ID | 1002 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
�� | +0.561 |
Belg | +0.559 |
uss | +0.539 |
rol | +0.526 |
roid | +0.512 |
Neg logit contributions | |
terness | -0.727 |
thur | -0.685 |
phia | -0.657 |
renheit | -0.645 |
י� | -0.644 |
Token | you |
Token ID | 345 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
terness | +0.678 |
thur | +0.642 |
phia | +0.609 |
י� | +0.600 |
chio | +0.595 |
Neg logit contributions | |
�� | -0.654 |
Belg | -0.630 |
uss | -0.614 |
rol | -0.602 |
roid | -0.592 |
Token | Sullivan |
Token ID | 18501 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
terness | +0.142 |
thur | +0.135 |
phia | +0.129 |
י� | +0.127 |
chio | +0.126 |
Neg logit contributions | |
�� | -0.106 |
Belg | -0.102 |
uss | -0.099 |
rol | -0.097 |
roid | -0.095 |
Token | is |
Token ID | 318 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
terness | +3.605 |
thur | +3.448 |
phia | +3.289 |
chio | +3.227 |
י� | +3.223 |
Neg logit contributions | |
�� | -3.082 |
Belg | -2.877 |
uss | -2.784 |
rol | -2.728 |
roid | -2.680 |
Token | finally |
Token ID | 3443 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
terness | +1.780 |
thur | +1.702 |
phia | +1.634 |
י� | +1.609 |
chio | +1.599 |
Neg logit contributions | |
�� | -1.228 |
Belg | -1.142 |
uss | -1.110 |
rol | -1.085 |
roid | -1.062 |
Token | able |
Token ID | 1498 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
terness | +2.841 |
thur | +2.736 |
phia | +2.624 |
י� | +2.592 |
chio | +2.579 |
Neg logit contributions | |
�� | -1.828 |
Belg | -1.672 |
uss | -1.624 |
rol | -1.578 |
roid | -1.534 |
Token | to |
Token ID | 284 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
terness | +1.249 |
thur | +1.191 |
phia | +1.137 |
י� | +1.124 |
chio | +1.116 |
Neg logit contributions | |
�� | -0.940 |
Belg | -0.896 |
uss | -0.870 |
rol | -0.850 |
roid | -0.832 |
Token | enter |
Token ID | 3802 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
terness | +0.852 |
thur | +0.813 |
phia | +0.777 |
י� | +0.766 |
chio | +0.763 |
Neg logit contributions | |
�� | -0.653 |
Belg | -0.620 |
uss | -0.602 |
rol | -0.590 |
roid | -0.577 |
Token | the |
Token ID | 262 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
terness | +4.949 |
thur | +4.710 |
phia | +4.535 |
י� | +4.475 |
chio | +4.399 |
Neg logit contributions | |
�� | -4.498 |
Belg | -4.132 |
uss | -4.069 |
rol | -4.033 |
roid | -3.955 |
Token | cabin |
Token ID | 9351 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
terness | +0.923 |
thur | +0.877 |
phia | +0.837 |
י� | +0.825 |
chio | +0.819 |
Neg logit contributions | |
�� | -0.731 |
Belg | -0.702 |
uss | -0.682 |
rol | -0.666 |
roid | -0.654 |
Token | more |
Token ID | 517 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
terness | +2.881 |
thur | +2.747 |
phia | +2.600 |
י� | +2.573 |
chio | +2.551 |
Neg logit contributions | |
�� | -2.585 |
Belg | -2.451 |
uss | -2.370 |
rol | -2.315 |
roid | -2.272 |
Token | than |
Token ID | 621 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
terness | +1.170 |
thur | +1.121 |
phia | +1.071 |
י� | +1.062 |
chio | +1.055 |
Neg logit contributions | |
�� | -0.727 |
Belg | -0.685 |
uss | -0.665 |
rol | -0.647 |
roid | -0.631 |
Token | an |
Token ID | 281 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
terness | +1.664 |
thur | +1.593 |
phia | +1.516 |
י� | +1.500 |
chio | +1.492 |
Neg logit contributions | |
�� | -1.218 |
Belg | -1.150 |
uss | -1.122 |
rol | -1.097 |
roid | -1.075 |
Token | for |
Token ID | 329 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
�� | +0.916 |
Belg | +0.885 |
uss | +0.864 |
rol | +0.845 |
roid | +0.824 |
Neg logit contributions | |
terness | -1.362 |
thur | -1.292 |
phia | -1.236 |
chio | -1.218 |
י� | -1.217 |
Token | repairing |
Token ID | 39005 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
terness | +1.331 |
thur | +1.275 |
phia | +1.218 |
י� | +1.205 |
chio | +1.194 |
Neg logit contributions | |
�� | -0.960 |
Belg | -0.894 |
uss | -0.869 |
rol | -0.848 |
roid | -0.835 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
terness | +0.405 |
thur | +0.385 |
phia | +0.366 |
י� | +0.361 |
chio | +0.358 |
Neg logit contributions | |
�� | -0.342 |
Belg | -0.329 |
uss | -0.321 |
rol | -0.314 |
roid | -0.308 |
Token | sidewalks |
Token ID | 38282 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
terness | +1.043 |
thur | +0.990 |
phia | +0.947 |
י� | +0.932 |
chio | +0.924 |
Neg logit contributions | |
�� | -0.863 |
Belg | -0.815 |
uss | -0.794 |
rol | -0.776 |
roid | -0.766 |
Token | . |
Token ID | 13 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
Belg | +2.570 |
�� | +2.553 |
uss | +2.523 |
rol | +2.455 |
roid | +2.386 |
Neg logit contributions | |
terness | -3.602 |
thur | -3.422 |
phia | -3.273 |
renheit | -3.218 |
chio | -3.213 |
Token | AB |
Token ID | 9564 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
terness | +0.317 |
thur | +0.302 |
phia | +0.288 |
י� | +0.283 |
renheit | +0.282 |
Neg logit contributions | |
�� | -0.237 |
Belg | -0.232 |
uss | -0.224 |
rol | -0.219 |
roid | -0.214 |
Token | 12 |
Token ID | 1105 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
terness | +4.101 |
thur | +3.820 |
chio | +3.537 |
phia | +3.529 |
TER | +3.518 |
Neg logit contributions | |
�� | -4.914 |
Belg | -4.670 |
uss | -4.509 |
rol | -4.427 |
roid | -4.380 |
Token | 90 |
Token ID | 3829 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
�� | +0.072 |
Belg | +0.070 |
uss | +0.068 |
rol | +0.067 |
roid | +0.065 |
Neg logit contributions | |
terness | -0.092 |
thur | -0.087 |
phia | -0.083 |
י� | -0.082 |
chio | -0.082 |
Token | money |
Token ID | 1637 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
terness | +0.453 |
thur | +0.431 |
phia | +0.411 |
י� | +0.405 |
chio | +0.402 |
Neg logit contributions | |
�� | -0.356 |
Belg | -0.341 |
uss | -0.332 |
rol | -0.325 |
roid | -0.318 |
Token | is |
Token ID | 318 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
�� | +0.562 |
Belg | +0.545 |
uss | +0.531 |
rol | +0.520 |
roid | +0.510 |
Neg logit contributions | |
terness | -0.734 |
thur | -0.697 |
phia | -0.663 |
י� | -0.654 |
renheit | -0.651 |
Token | to |
Token ID | 284 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
terness | +1.386 |
thur | +1.321 |
phia | +1.262 |
י� | +1.244 |
chio | +1.234 |
Neg logit contributions | |
�� | -1.138 |
Belg | -1.072 |
uss | -1.042 |
rol | -1.023 |
roid | -1.005 |
Token | court |
Token ID | 2184 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
terness | +1.957 |
thur | +1.873 |
phia | +1.787 |
י� | +1.764 |
chio | +1.754 |
Neg logit contributions | |
�� | -1.415 |
Belg | -1.343 |
uss | -1.299 |
rol | -1.276 |
roid | -1.249 |
Token | has |
Token ID | 468 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
terness | +0.512 |
thur | +0.488 |
phia | +0.467 |
י� | +0.460 |
chio | +0.457 |
Neg logit contributions | |
�� | -0.365 |
Belg | -0.350 |
uss | -0.340 |
rol | -0.332 |
roid | -0.325 |
Token | ruled |
Token ID | 8879 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
terness | +1.069 |
thur | +1.020 |
phia | +0.971 |
י� | +0.958 |
chio | +0.951 |
Neg logit contributions | |
�� | -0.886 |
Belg | -0.843 |
uss | -0.822 |
rol | -0.803 |
roid | -0.788 |
Token | if |
Token ID | 611 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
terness | +0.992 |
thur | +0.946 |
phia | +0.900 |
י� | +0.889 |
chio | +0.881 |
Neg logit contributions | |
�� | -0.835 |
Belg | -0.790 |
uss | -0.770 |
rol | -0.755 |
roid | -0.742 |
Token | the |
Token ID | 262 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
�� | +0.183 |
Belg | +0.177 |
uss | +0.173 |
rol | +0.168 |
roid | +0.165 |
Neg logit contributions | |
terness | -0.218 |
thur | -0.206 |
phia | -0.196 |
י� | -0.194 |
renheit | -0.193 |
Token | seizure |
Token ID | 22338 |
Feature activation | +6.87e+00 |
Pos logit contributions | |
terness | +0.397 |
thur | +0.378 |
phia | +0.361 |
י� | +0.356 |
chio | +0.354 |
Neg logit contributions | |
�� | -0.291 |
Belg | -0.279 |
uss | -0.271 |
rol | -0.264 |
roid | -0.259 |
Token | can |
Token ID | 460 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
terness | +5.324 |
thur | +5.158 |
phia | +4.850 |
י� | +4.823 |
chio | +4.808 |
Neg logit contributions | |
�� | -5.135 |
Belg | -4.712 |
uss | -4.573 |
rol | -4.484 |
roid | -4.401 |
Token | go |
Token ID | 467 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
terness | +1.496 |
thur | +1.414 |
phia | +1.343 |
י� | +1.321 |
chio | +1.311 |
Neg logit contributions | |
�� | -1.458 |
Belg | -1.403 |
uss | -1.369 |
rol | -1.342 |
roid | -1.319 |
Token | ahead |
Token ID | 4058 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
�� | +0.145 |
Belg | +0.137 |
uss | +0.131 |
rol | +0.127 |
roid | +0.123 |
Neg logit contributions | |
terness | -0.344 |
thur | -0.330 |
phia | -0.318 |
י� | -0.315 |
chio | -0.313 |
Token | . |
Token ID | 13 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
�� | +0.147 |
Belg | +0.144 |
uss | +0.141 |
rol | +0.138 |
roid | +0.134 |
Neg logit contributions | |
terness | -0.191 |
thur | -0.180 |
phia | -0.174 |
chio | -0.170 |
י� | -0.170 |
Token | Some |
Token ID | 2773 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
�� | +0.024 |
Belg | +0.024 |
uss | +0.023 |
rol | +0.022 |
roid | +0.022 |
Neg logit contributions | |
terness | -0.030 |
thur | -0.029 |
phia | -0.027 |
chio | -0.027 |
renheit | -0.027 |
Token | stars |
Token ID | 5788 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
terness | +0.202 |
thur | +0.191 |
phia | +0.183 |
י� | +0.180 |
renheit | +0.179 |
Neg logit contributions | |
�� | -0.149 |
Belg | -0.146 |
uss | -0.140 |
rol | -0.137 |
roid | -0.134 |
Token | a |
Token ID | 257 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
terness | +0.124 |
thur | +0.118 |
phia | +0.112 |
י� | +0.110 |
renheit | +0.110 |
Neg logit contributions | |
�� | -0.099 |
Belg | -0.096 |
uss | -0.093 |
rol | -0.091 |
roid | -0.089 |
Token | great |
Token ID | 1049 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
�� | +0.214 |
Belg | +0.209 |
uss | +0.202 |
rol | +0.198 |
roid | +0.194 |
Neg logit contributions | |
terness | -0.284 |
thur | -0.269 |
phia | -0.256 |
י� | -0.252 |
renheit | -0.252 |
Token | future |
Token ID | 2003 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
�� | +0.323 |
Belg | +0.315 |
uss | +0.306 |
rol | +0.298 |
roid | +0.292 |
Neg logit contributions | |
terness | -0.443 |
thur | -0.419 |
phia | -0.402 |
renheit | -0.394 |
י� | -0.394 |
Token | for |
Token ID | 329 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
terness | +1.320 |
thur | +1.256 |
phia | +1.195 |
י� | +1.181 |
chio | +1.173 |
Neg logit contributions | |
�� | -1.074 |
Belg | -1.024 |
uss | -0.996 |
rol | -0.974 |
roid | -0.955 |
Token | Tol |
Token ID | 20054 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
�� | +0.541 |
Belg | +0.534 |
uss | +0.512 |
rol | +0.501 |
roid | +0.485 |
Neg logit contributions | |
terness | -0.864 |
thur | -0.824 |
phia | -0.789 |
renheit | -0.777 |
י� | -0.776 |
Token | ui |
Token ID | 9019 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
terness | +4.495 |
thur | +4.253 |
phia | +4.037 |
chio | +3.990 |
י� | +3.969 |
Neg logit contributions | |
�� | -4.825 |
Belg | -4.454 |
uss | -4.365 |
rol | -4.268 |
roid | -4.183 |
Token | 's |
Token ID | 338 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
�� | +1.457 |
Belg | +1.449 |
uss | +1.414 |
rol | +1.395 |
roid | +1.343 |
Neg logit contributions | |
terness | -1.796 |
thur | -1.696 |
phia | -1.615 |
renheit | -1.596 |
י� | -1.588 |
Token | eldest |
Token ID | 34331 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Belg | +1.568 |
�� | +1.553 |
uss | +1.512 |
rol | +1.487 |
roid | +1.461 |
Neg logit contributions | |
terness | -1.539 |
thur | -1.425 |
phia | -1.357 |
renheit | -1.335 |
י� | -1.327 |
Token | son |
Token ID | 3367 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
terness | +1.482 |
thur | +1.402 |
phia | +1.327 |
י� | +1.305 |
chio | +1.296 |
Neg logit contributions | |
�� | -1.561 |
Belg | -1.497 |
uss | -1.463 |
rol | -1.437 |
roid | -1.412 |
Token | and |
Token ID | 290 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
terness | +1.527 |
thur | +1.448 |
phia | +1.379 |
י� | +1.359 |
chio | +1.349 |
Neg logit contributions | |
�� | -1.332 |
Belg | -1.276 |
uss | -1.244 |
rol | -1.218 |
roid | -1.196 |
Token | � |
Token ID | 564 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
terness | +0.807 |
thur | +0.766 |
phia | +0.728 |
י� | +0.728 |
chio | +0.717 |
Neg logit contributions | |
�� | -0.618 |
Belg | -0.591 |
uss | -0.574 |
rol | -0.562 |
roid | -0.554 |
Token | � |
Token ID | 250 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
terness | +1.375 |
thur | +1.297 |
phia | +1.226 |
י� | +1.208 |
chio | +1.196 |
Neg logit contributions | |
�� | -1.502 |
Belg | -1.456 |
uss | -1.418 |
rol | -1.388 |
roid | -1.366 |
Token | He |
Token ID | 1544 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
terness | +0.670 |
thur | +0.631 |
phia | +0.595 |
י� | +0.586 |
chio | +0.580 |
Neg logit contributions | |
�� | -0.776 |
Belg | -0.747 |
uss | -0.730 |
rol | -0.716 |
roid | -0.705 |
Token | 's |
Token ID | 338 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
�� | +1.497 |
uss | +1.478 |
Belg | +1.476 |
rol | +1.436 |
roid | +1.396 |
Neg logit contributions | |
terness | -2.203 |
thur | -2.065 |
phia | -2.004 |
י� | -1.963 |
renheit | -1.950 |
Token | an |
Token ID | 281 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
terness | +0.113 |
thur | +0.108 |
phia | +0.103 |
י� | +0.102 |
chio | +0.101 |
Neg logit contributions | |
�� | -0.081 |
Belg | -0.077 |
uss | -0.075 |
rol | -0.073 |
roid | -0.071 |
Token | animated |
Token ID | 15108 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
terness | +0.858 |
thur | +0.819 |
phia | +0.781 |
י� | +0.771 |
chio | +0.766 |
Neg logit contributions | |
�� | -0.642 |
Belg | -0.611 |
uss | -0.594 |
rol | -0.580 |
roid | -0.568 |
Token | figure |
Token ID | 3785 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
terness | +1.166 |
thur | +1.111 |
phia | +1.060 |
י� | +1.045 |
chio | +1.038 |
Neg logit contributions | |
�� | -0.866 |
Belg | -0.831 |
uss | -0.807 |
rol | -0.788 |
roid | -0.773 |
Token | , |
Token ID | 11 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
terness | +3.035 |
thur | +2.879 |
phia | +2.741 |
י� | +2.718 |
chio | +2.699 |
Neg logit contributions | |
�� | -2.626 |
Belg | -2.484 |
uss | -2.400 |
rol | -2.357 |
roid | -2.308 |
Token | so |
Token ID | 523 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
�� | +0.094 |
Belg | +0.091 |
uss | +0.088 |
rol | +0.086 |
roid | +0.085 |
Neg logit contributions | |
terness | -0.115 |
thur | -0.109 |
phia | -0.104 |
י� | -0.103 |
chio | -0.102 |
Token | he |
Token ID | 339 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
terness | +0.924 |
thur | +0.878 |
phia | +0.836 |
י� | +0.825 |
chio | +0.819 |
Neg logit contributions | |
�� | -0.754 |
Belg | -0.717 |
uss | -0.698 |
rol | -0.682 |
roid | -0.670 |
Token | 's |
Token ID | 338 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
�� | +0.609 |
Belg | +0.589 |
uss | +0.580 |
rol | +0.567 |
roid | +0.551 |
Neg logit contributions | |
terness | -0.898 |
thur | -0.852 |
phia | -0.819 |
י� | -0.803 |
renheit | -0.801 |
Token | start |
Token ID | 923 |
Feature activation | +2.16e-03 |
Pos logit contributions | |
terness | +0.693 |
thur | +0.657 |
phia | +0.621 |
י� | +0.610 |
chio | +0.606 |
Neg logit contributions | |
�� | -0.739 |
Belg | -0.708 |
uss | -0.693 |
rol | -0.679 |
roid | -0.669 |
Token | schedules |
Token ID | 24025 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
terness | +0.002 |
thur | +0.002 |
phia | +0.002 |
י� | +0.002 |
chio | +0.002 |
Neg logit contributions | |
�� | -0.001 |
Belg | -0.001 |
uss | -0.001 |
rol | -0.001 |
roid | -0.001 |
Token | up |
Token ID | 510 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
�� | +1.106 |
Belg | +1.098 |
uss | +1.057 |
rol | +1.038 |
roid | +1.011 |
Neg logit contributions | |
terness | -1.603 |
thur | -1.514 |
phia | -1.453 |
י� | -1.429 |
renheit | -1.426 |
Token | and |
Token ID | 290 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
terness | +0.318 |
thur | +0.301 |
phia | +0.288 |
י� | +0.284 |
chio | +0.282 |
Neg logit contributions | |
�� | -0.247 |
Belg | -0.239 |
uss | -0.232 |
rol | -0.228 |
roid | -0.221 |
Token | back |
Token ID | 736 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
�� | +0.354 |
Belg | +0.342 |
uss | +0.332 |
rol | +0.325 |
roid | +0.318 |
Neg logit contributions | |
terness | -0.467 |
thur | -0.444 |
phia | -0.424 |
י� | -0.418 |
chio | -0.415 |
Token | ." |
Token ID | 526 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
terness | +1.133 |
thur | +1.079 |
phia | +1.030 |
י� | +1.015 |
chio | +1.009 |
Neg logit contributions | |
�� | -0.870 |
Belg | -0.832 |
uss | -0.809 |
rol | -0.790 |
roid | -0.774 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
terness | +0.536 |
thur | +0.504 |
phia | +0.478 |
י� | +0.470 |
chio | +0.465 |
Neg logit contributions | |
�� | -0.606 |
Belg | -0.584 |
uss | -0.571 |
rol | -0.560 |
roid | -0.552 |
Token |
|
Token ID | 198 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
terness | +1.274 |
thur | +1.204 |
phia | +1.137 |
י� | +1.121 |
chio | +1.110 |
Neg logit contributions | |
�� | -1.500 |
Belg | -1.436 |
uss | -1.403 |
rol | -1.376 |
roid | -1.356 |
Token | Let |
Token ID | 5756 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
terness | +0.532 |
thur | +0.500 |
phia | +0.472 |
י� | +0.462 |
chio | +0.460 |
Neg logit contributions | |
�� | -0.580 |
Belg | -0.563 |
uss | -0.551 |
rol | -0.542 |
roid | -0.532 |
Token | ting |
Token ID | 889 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
terness | +1.744 |
thur | +1.639 |
phia | +1.561 |
י� | +1.532 |
chio | +1.530 |
Neg logit contributions | |
�� | -1.687 |
Belg | -1.613 |
uss | -1.570 |
rol | -1.531 |
roid | -1.515 |
Token | teenagers |
Token ID | 17366 |
Feature activation | -6.79e+00 |
Pos logit contributions | |
terness | +2.627 |
thur | +2.469 |
phia | +2.349 |
chio | +2.296 |
י� | +2.287 |
Neg logit contributions | |
�� | -3.072 |
Belg | -2.854 |
uss | -2.811 |
rol | -2.746 |
roid | -2.738 |
Token | by |
Token ID | 416 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
terness | +1.524 |
thur | +1.443 |
phia | +1.364 |
י� | +1.347 |
chio | +1.336 |
Neg logit contributions | |
�� | -1.525 |
Belg | -1.460 |
uss | -1.428 |
rol | -1.399 |
roid | -1.375 |
Token | WikiLeaks |
Token ID | 19766 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
terness | +0.172 |
thur | +0.164 |
phia | +0.157 |
י� | +0.154 |
chio | +0.154 |
Neg logit contributions | |
�� | -0.123 |
Belg | -0.119 |
uss | -0.115 |
rol | -0.112 |
roid | -0.110 |
Token | sent |
Token ID | 1908 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
Belg | +2.421 |
�� | +2.417 |
uss | +2.307 |
rol | +2.247 |
roid | +2.178 |
Neg logit contributions | |
terness | -3.788 |
thur | -3.619 |
phia | -3.499 |
י� | -3.400 |
renheit | -3.398 |
Token | from |
Token ID | 422 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
�� | +0.372 |
Belg | +0.359 |
uss | +0.348 |
rol | +0.341 |
roid | +0.334 |
Neg logit contributions | |
terness | -0.483 |
thur | -0.459 |
phia | -0.439 |
י� | -0.430 |
chio | -0.428 |
Token | the |
Token ID | 262 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
terness | +1.793 |
thur | +1.703 |
phia | +1.619 |
י� | +1.594 |
chio | +1.581 |
Neg logit contributions | |
�� | -1.668 |
Belg | -1.595 |
uss | -1.558 |
rol | -1.528 |
roid | -1.501 |
Token | US |
Token ID | 1294 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
terness | +0.331 |
thur | +0.312 |
phia | +0.298 |
י� | +0.293 |
chio | +0.291 |
Neg logit contributions | |
�� | -0.286 |
Belg | -0.279 |
uss | -0.270 |
rol | -0.264 |
roid | -0.259 |
Token | embassy |
Token ID | 18613 |
Feature activation | -5.92e+00 |
Pos logit contributions | |
terness | +2.693 |
thur | +2.583 |
phia | +2.446 |
י� | +2.418 |
chio | +2.388 |
Neg logit contributions | |
�� | -2.164 |
Belg | -2.035 |
uss | -1.981 |
rol | -1.940 |
roid | -1.903 |
Token | in |
Token ID | 287 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
�� | +3.206 |
Belg | +3.206 |
uss | +3.093 |
rol | +2.957 |
roid | +2.830 |
Neg logit contributions | |
terness | -5.680 |
thur | -5.363 |
phia | -5.168 |
י� | -5.086 |
renheit | -5.066 |
Token | Tripoli |
Token ID | 47318 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
terness | +0.383 |
thur | +0.361 |
phia | +0.341 |
י� | +0.335 |
chio | +0.332 |
Neg logit contributions | |
�� | -0.454 |
Belg | -0.436 |
uss | -0.427 |
rol | -0.420 |
roid | -0.414 |
Token | in |
Token ID | 287 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
�� | +0.482 |
Belg | +0.466 |
uss | +0.452 |
rol | +0.441 |
roid | +0.431 |
Neg logit contributions | |
terness | -0.635 |
thur | -0.604 |
phia | -0.578 |
י� | -0.568 |
renheit | -0.564 |
Token | November |
Token ID | 3389 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
terness | +0.340 |
thur | +0.323 |
phia | +0.308 |
י� | +0.303 |
chio | +0.301 |
Neg logit contributions | |
�� | -0.291 |
Belg | -0.279 |
uss | -0.272 |
rol | -0.266 |
roid | -0.261 |
Token | battle |
Token ID | 3344 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
�� | +2.088 |
Belg | +2.061 |
uss | +2.008 |
rol | +1.954 |
roid | +1.902 |
Neg logit contributions | |
terness | -3.346 |
thur | -3.143 |
phia | -3.059 |
renheit | -3.022 |
י� | -2.993 |
Token | engines |
Token ID | 11874 |
Feature activation | -7.36e-02 |
Pos logit contributions | |
�� | +0.109 |
Belg | +0.105 |
uss | +0.103 |
rol | +0.101 |
roid | +0.099 |
Neg logit contributions | |
terness | -0.124 |
thur | -0.117 |
phia | -0.112 |
י� | -0.110 |
chio | -0.109 |
Token | as |
Token ID | 355 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
�� | +0.050 |
Belg | +0.048 |
uss | +0.047 |
rol | +0.046 |
roid | +0.045 |
Neg logit contributions | |
terness | -0.063 |
thur | -0.060 |
phia | -0.057 |
י� | -0.056 |
chio | -0.056 |
Token | well |
Token ID | 880 |
Feature activation | -6.22e+00 |
Pos logit contributions | |
terness | +1.229 |
thur | +1.169 |
phia | +1.107 |
י� | +1.090 |
chio | +1.082 |
Neg logit contributions | |
�� | -1.179 |
Belg | -1.128 |
uss | -1.099 |
rol | -1.080 |
roid | -1.062 |
Token | . |
Token ID | 13 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
�� | +3.892 |
Belg | +3.814 |
uss | +3.712 |
rol | +3.649 |
roid | +3.511 |
Neg logit contributions | |
terness | -5.476 |
thur | -5.181 |
phia | -5.022 |
chio | -4.892 |
renheit | -4.848 |
Token | Talk |
Token ID | 12167 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
�� | +0.559 |
Belg | +0.554 |
uss | +0.533 |
rol | +0.523 |
roid | +0.510 |
Neg logit contributions | |
terness | -0.648 |
thur | -0.609 |
phia | -0.582 |
renheit | -0.571 |
י� | -0.568 |
Token | about |
Token ID | 546 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
terness | +0.884 |
thur | +0.837 |
phia | +0.795 |
י� | +0.781 |
chio | +0.776 |
Neg logit contributions | |
�� | -0.847 |
Belg | -0.812 |
uss | -0.791 |
rol | -0.776 |
roid | -0.764 |
Token | a |
Token ID | 257 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
�� | +0.233 |
Belg | +0.224 |
uss | +0.217 |
rol | +0.212 |
roid | +0.208 |
Neg logit contributions | |
terness | -0.326 |
thur | -0.310 |
phia | -0.297 |
י� | -0.293 |
renheit | -0.291 |
Token | theme |
Token ID | 7505 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
�� | +0.250 |
Belg | +0.240 |
uss | +0.233 |
rol | +0.228 |
roid | +0.223 |
Neg logit contributions | |
terness | -0.354 |
thur | -0.337 |
phia | -0.322 |
י� | -0.318 |
chio | -0.316 |
Token | force |
Token ID | 2700 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
�� | +2.416 |
Belg | +2.325 |
uss | +2.292 |
rol | +2.189 |
roid | +2.185 |
Neg logit contributions | |
terness | -3.996 |
thur | -3.798 |
phia | -3.623 |
renheit | -3.617 |
י� | -3.611 |
Token | with |
Token ID | 351 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
�� | +3.234 |
Belg | +3.197 |
uss | +3.167 |
rol | +3.053 |
roid | +3.026 |
Neg logit contributions | |
terness | -4.768 |
thur | -4.549 |
renheit | -4.347 |
phia | -4.343 |
י� | -4.305 |
Token | Arts |
Token ID | 11536 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
�� | +0.202 |
Belg | +0.196 |
uss | +0.191 |
rol | +0.187 |
roid | +0.183 |
Neg logit contributions | |
terness | -0.237 |
thur | -0.225 |
phia | -0.215 |
י� | -0.212 |
renheit | -0.211 |
Token | , |
Token ID | 11 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
�� | +1.332 |
Belg | +1.303 |
uss | +1.272 |
rol | +1.255 |
roid | +1.224 |
Neg logit contributions | |
terness | -1.535 |
thur | -1.444 |
phia | -1.386 |
renheit | -1.367 |
י� | -1.361 |
Token | which |
Token ID | 543 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
terness | +0.225 |
thur | +0.215 |
phia | +0.205 |
י� | +0.202 |
chio | +0.201 |
Neg logit contributions | |
�� | -0.171 |
Belg | -0.163 |
uss | -0.159 |
rol | -0.155 |
roid | -0.152 |
Token | were |
Token ID | 547 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
�� | +0.754 |
Belg | +0.726 |
uss | +0.706 |
rol | +0.690 |
roid | +0.676 |
Neg logit contributions | |
terness | -0.945 |
thur | -0.897 |
phia | -0.856 |
י� | -0.844 |
renheit | -0.839 |
Token | parties |
Token ID | 4671 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
�� | +0.887 |
Belg | +0.857 |
uss | +0.832 |
rol | +0.813 |
roid | +0.794 |
Neg logit contributions | |
terness | -1.209 |
thur | -1.150 |
phia | -1.101 |
י� | -1.083 |
renheit | -1.080 |
Token | to |
Token ID | 284 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
�� | +0.336 |
Belg | +0.321 |
uss | +0.312 |
rol | +0.305 |
roid | +0.298 |
Neg logit contributions | |
terness | -0.466 |
thur | -0.444 |
phia | -0.425 |
י� | -0.419 |
chio | -0.417 |
Token | the |
Token ID | 262 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
terness | +0.344 |
thur | +0.325 |
phia | +0.308 |
י� | +0.304 |
chio | +0.301 |
Neg logit contributions | |
�� | -0.336 |
Belg | -0.325 |
uss | -0.315 |
rol | -0.309 |
roid | -0.305 |
Token | public |
Token ID | 1171 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
�� | +0.055 |
Belg | +0.053 |
uss | +0.051 |
rol | +0.050 |
roid | +0.049 |
Neg logit contributions | |
terness | -0.084 |
thur | -0.080 |
phia | -0.076 |
י� | -0.075 |
chio | -0.075 |
Token | interest |
Token ID | 1393 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
�� | +0.469 |
Belg | +0.449 |
uss | +0.437 |
rol | +0.427 |
roid | +0.418 |
Neg logit contributions | |
terness | -0.647 |
thur | -0.616 |
phia | -0.589 |
י� | -0.580 |
chio | -0.577 |
Token | litigation |
Token ID | 19284 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
�� | +0.807 |
Belg | +0.772 |
uss | +0.750 |
rol | +0.731 |
roid | +0.714 |
Neg logit contributions | |
terness | -1.248 |
thur | -1.191 |
phia | -1.143 |
י� | -1.127 |
renheit | -1.122 |
Token | ( |
Token ID | 357 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
terness | +0.144 |
thur | +0.137 |
phia | +0.131 |
י� | +0.129 |
chio | +0.128 |
Neg logit contributions | |
�� | -0.111 |
Belg | -0.106 |
uss | -0.103 |
rol | -0.100 |
roid | -0.099 |
Token | situation |
Token ID | 3074 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
�� | +0.062 |
Belg | +0.060 |
uss | +0.058 |
rol | +0.057 |
roid | +0.056 |
Neg logit contributions | |
terness | -0.088 |
thur | -0.084 |
phia | -0.080 |
renheit | -0.079 |
י� | -0.079 |
Token | was |
Token ID | 373 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
terness | +1.469 |
thur | +1.399 |
phia | +1.338 |
י� | +1.320 |
chio | +1.309 |
Neg logit contributions | |
�� | -1.094 |
Belg | -1.045 |
uss | -1.013 |
rol | -0.991 |
roid | -0.971 |
Token | . |
Token ID | 13 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
�� | +0.348 |
Belg | +0.336 |
uss | +0.329 |
rol | +0.323 |
roid | +0.316 |
Neg logit contributions | |
terness | -0.447 |
thur | -0.426 |
phia | -0.406 |
י� | -0.398 |
chio | -0.397 |
Token | Areas |
Token ID | 38662 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
terness | +0.177 |
thur | +0.168 |
phia | +0.160 |
chio | +0.157 |
renheit | +0.157 |
Neg logit contributions | |
�� | -0.136 |
Belg | -0.136 |
uss | -0.130 |
rol | -0.128 |
roid | -0.124 |
Token | of |
Token ID | 286 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
�� | +1.621 |
Belg | +1.606 |
uss | +1.559 |
rol | +1.520 |
roid | +1.490 |
Neg logit contributions | |
terness | -2.222 |
thur | -2.111 |
phia | -2.038 |
renheit | -2.006 |
chio | -1.986 |
Token | skin |
Token ID | 4168 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
�� | +0.470 |
Belg | +0.462 |
uss | +0.447 |
rol | +0.438 |
roid | +0.428 |
Neg logit contributions | |
terness | -0.600 |
thur | -0.572 |
phia | -0.543 |
renheit | -0.535 |
י� | -0.535 |
Token | on |
Token ID | 319 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
�� | +1.389 |
Belg | +1.365 |
uss | +1.326 |
rol | +1.302 |
roid | +1.276 |
Neg logit contributions | |
terness | -1.983 |
thur | -1.899 |
phia | -1.821 |
renheit | -1.805 |
chio | -1.786 |
Token | his |
Token ID | 465 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Belg | +1.622 |
�� | +1.621 |
uss | +1.582 |
rol | +1.542 |
roid | +1.483 |
Neg logit contributions | |
terness | -2.349 |
thur | -2.223 |
phia | -2.119 |
renheit | -2.080 |
chio | -2.078 |
Token | face |
Token ID | 1986 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
�� | +1.134 |
Belg | +1.119 |
uss | +1.097 |
rol | +1.071 |
roid | +1.051 |
Neg logit contributions | |
terness | -1.389 |
thur | -1.307 |
phia | -1.247 |
renheit | -1.230 |
chio | -1.222 |
Token | and |
Token ID | 290 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
terness | +1.050 |
thur | +0.997 |
phia | +0.951 |
י� | +0.936 |
chio | +0.931 |
Neg logit contributions | |
�� | -0.872 |
Belg | -0.839 |
uss | -0.817 |
rol | -0.800 |
roid | -0.785 |
Token | legs |
Token ID | 7405 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
terness | +0.245 |
thur | +0.233 |
phia | +0.221 |
י� | +0.218 |
chio | +0.217 |
Neg logit contributions | |
�� | -0.220 |
Belg | -0.211 |
uss | -0.205 |
rol | -0.201 |
roid | -0.197 |
Token | ast |
Token ID | 459 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
�� | +1.032 |
Belg | +0.994 |
uss | +0.988 |
rol | +0.966 |
roid | +0.952 |
Neg logit contributions | |
terness | -1.083 |
thur | -1.016 |
phia | -0.971 |
י� | -0.959 |
renheit | -0.951 |
Token | > |
Token ID | 29 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
�� | +2.911 |
uss | +2.861 |
rol | +2.815 |
Belg | +2.813 |
roid | +2.771 |
Neg logit contributions | |
terness | -3.130 |
thur | -2.910 |
phia | -2.804 |
י� | -2.777 |
renheit | -2.747 |
Token | dude |
Token ID | 18396 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
terness | +0.022 |
thur | +0.021 |
phia | +0.020 |
י� | +0.019 |
chio | +0.019 |
Neg logit contributions | |
�� | -0.019 |
Belg | -0.018 |
uss | -0.018 |
rol | -0.017 |
roid | -0.017 |
Token | nice |
Token ID | 3621 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
�� | +1.061 |
Belg | +1.031 |
uss | +1.001 |
rol | +0.977 |
roid | +0.956 |
Neg logit contributions | |
terness | -1.424 |
thur | -1.348 |
phia | -1.300 |
י� | -1.276 |
renheit | -1.267 |
Token | [ |
Token ID | 685 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
�� | +2.279 |
Belg | +2.217 |
uss | +2.171 |
rol | +2.112 |
roid | +2.069 |
Neg logit contributions | |
terness | -3.005 |
thur | -2.842 |
phia | -2.731 |
י� | -2.683 |
renheit | -2.676 |
Token | 10 |
Token ID | 940 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
�� | +0.501 |
Belg | +0.493 |
uss | +0.485 |
rol | +0.477 |
roid | +0.467 |
Neg logit contributions | |
terness | -0.776 |
thur | -0.731 |
phia | -0.704 |
renheit | -0.688 |
י� | -0.685 |
Token | : |
Token ID | 25 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Belg | +1.731 |
uss | +1.670 |
rol | +1.649 |
�� | +1.636 |
roid | +1.603 |
Neg logit contributions | |
terness | -2.894 |
thur | -2.685 |
phia | -2.582 |
renheit | -2.527 |
chio | -2.499 |
Token | 47 |
Token ID | 2857 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
terness | +0.792 |
thur | +0.748 |
phia | +0.709 |
י� | +0.698 |
chio | +0.692 |
Neg logit contributions | |
�� | -0.832 |
Belg | -0.801 |
uss | -0.782 |
rol | -0.767 |
roid | -0.754 |
Token | ] |
Token ID | 60 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
�� | +0.674 |
Belg | +0.671 |
uss | +0.646 |
rol | +0.630 |
roid | +0.601 |
Neg logit contributions | |
terness | -1.959 |
thur | -1.861 |
phia | -1.803 |
renheit | -1.768 |
י� | -1.761 |
Token | < |
Token ID | 1279 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
terness | +0.436 |
thur | +0.412 |
phia | +0.387 |
י� | +0.383 |
chio | +0.379 |
Neg logit contributions | |
�� | -0.476 |
Belg | -0.460 |
uss | -0.449 |
rol | -0.440 |
roid | -0.433 |
Token | sp |
Token ID | 2777 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
terness | +2.670 |
thur | +2.566 |
phia | +2.424 |
י� | +2.371 |
chio | +2.371 |
Neg logit contributions | |
�� | -2.613 |
Belg | -2.507 |
uss | -2.402 |
rol | -2.347 |
roid | -2.305 |
Token | )); |
Token ID | 18125 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
�� | +1.329 |
Belg | +1.282 |
uss | +1.266 |
rol | +1.253 |
roid | +1.233 |
Neg logit contributions | |
terness | -1.465 |
thur | -1.397 |
phia | -1.320 |
י� | -1.306 |
renheit | -1.282 |
Token | RAW |
Token ID | 33782 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
�� | +1.824 |
Belg | +1.757 |
uss | +1.719 |
rol | +1.678 |
roid | +1.642 |
Neg logit contributions | |
terness | -2.141 |
thur | -2.046 |
phia | -1.956 |
י� | -1.913 |
renheit | -1.898 |
Token | _ |
Token ID | 62 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
terness | +0.433 |
thur | +0.410 |
phia | +0.390 |
י� | +0.383 |
chio | +0.380 |
Neg logit contributions | |
�� | -0.388 |
Belg | -0.374 |
uss | -0.365 |
rol | -0.358 |
roid | -0.351 |
Token | ASS |
Token ID | 10705 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
�� | +0.848 |
Belg | +0.812 |
uss | +0.790 |
rol | +0.772 |
roid | +0.757 |
Neg logit contributions | |
terness | -1.079 |
thur | -1.026 |
phia | -0.980 |
י� | -0.966 |
chio | -0.959 |
Token | ERT |
Token ID | 17395 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
uss | +5.194 |
Belg | +5.119 |
rol | +5.098 |
roid | +4.951 |
�� | +4.944 |
Neg logit contributions | |
terness | -4.737 |
thur | -4.396 |
phia | -4.171 |
renheit | -4.013 |
chio | -3.955 |
Token | ( |
Token ID | 7 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
�� | +1.906 |
Belg | +1.835 |
uss | +1.793 |
rol | +1.764 |
roid | +1.731 |
Neg logit contributions | |
terness | -1.915 |
thur | -1.812 |
phia | -1.721 |
י� | -1.681 |
chio | -1.674 |
Token | it |
Token ID | 270 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
�� | +0.717 |
Belg | +0.692 |
uss | +0.676 |
rol | +0.664 |
roid | +0.653 |
Neg logit contributions | |
terness | -0.629 |
thur | -0.592 |
phia | -0.559 |
י� | -0.550 |
chio | -0.546 |
Token | -> |
Token ID | 3784 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
terness | +0.151 |
thur | +0.145 |
phia | +0.140 |
י� | +0.138 |
chio | +0.137 |
Neg logit contributions | |
�� | -0.074 |
Belg | -0.070 |
uss | -0.068 |
rol | -0.066 |
roid | -0.064 |
Token | i |
Token ID | 72 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
�� | +0.680 |
Belg | +0.654 |
uss | +0.642 |
rol | +0.628 |
roid | +0.617 |
Neg logit contributions | |
terness | -0.743 |
thur | -0.704 |
phia | -0.669 |
י� | -0.660 |
chio | -0.652 |
Token | () |
Token ID | 3419 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
�� | +1.334 |
Belg | +1.286 |
uss | +1.257 |
rol | +1.233 |
roid | +1.213 |
Neg logit contributions | |
terness | -1.237 |
thur | -1.167 |
phia | -1.104 |
י� | -1.085 |
chio | -1.077 |
Token | == |
Token ID | 6624 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
�� | +0.960 |
Belg | +0.927 |
uss | +0.907 |
rol | +0.891 |
roid | +0.876 |
Neg logit contributions | |
terness | -0.807 |
thur | -0.759 |
phia | -0.715 |
י� | -0.702 |
chio | -0.696 |
Token | Dun |
Token ID | 5648 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
�� | +1.346 |
Belg | +1.328 |
uss | +1.279 |
rol | +1.252 |
roid | +1.216 |
Neg logit contributions | |
terness | -1.732 |
thur | -1.641 |
phia | -1.565 |
י� | -1.558 |
renheit | -1.550 |
Token | bar |
Token ID | 5657 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
uss | +5.779 |
Belg | +5.642 |
rol | +5.638 |
�� | +5.327 |
roid | +5.304 |
Neg logit contributions | |
terness | -5.504 |
thur | -5.055 |
י� | -4.999 |
BLIC | -4.801 |
phia | -4.783 |
Token | form |
Token ID | 1296 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
�� | +1.822 |
Belg | +1.796 |
uss | +1.779 |
rol | +1.737 |
roid | +1.694 |
Neg logit contributions | |
terness | -2.393 |
thur | -2.249 |
renheit | -2.158 |
phia | -2.155 |
י� | -2.124 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
�� | +0.747 |
Belg | +0.721 |
uss | +0.702 |
rol | +0.687 |
roid | +0.673 |
Neg logit contributions | |
terness | -0.814 |
thur | -0.769 |
phia | -0.730 |
י� | -0.719 |
renheit | -0.716 |
Token | centre |
Token ID | 7372 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
�� | +0.101 |
Belg | +0.096 |
uss | +0.093 |
rol | +0.090 |
roid | +0.089 |
Neg logit contributions | |
terness | -0.157 |
thur | -0.150 |
phia | -0.144 |
י� | -0.142 |
chio | -0.141 |
Token | partnership |
Token ID | 10413 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
terness | +0.015 |
thur | +0.015 |
phia | +0.014 |
י� | +0.014 |
chio | +0.014 |
Neg logit contributions | |
�� | -0.012 |
Belg | -0.012 |
uss | -0.011 |
rol | -0.011 |
roid | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
�� | +2.146 |
Belg | +2.146 |
uss | +2.090 |
rol | +2.044 |
roid | +1.965 |
Neg logit contributions | |
terness | -3.054 |
thur | -2.889 |
phia | -2.776 |
renheit | -2.744 |
י� | -2.727 |
Token | while |
Token ID | 981 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
�� | +1.610 |
Belg | +1.572 |
uss | +1.522 |
rol | +1.481 |
roid | +1.420 |
Neg logit contributions | |
terness | -2.426 |
thur | -2.305 |
phia | -2.213 |
renheit | -2.186 |
י� | -2.170 |
Token | Finn |
Token ID | 15368 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
�� | +3.188 |
Belg | +3.185 |
uss | +3.069 |
rol | +2.990 |
roid | +2.880 |
Neg logit contributions | |
terness | -3.732 |
thur | -3.519 |
renheit | -3.336 |
phia | -3.331 |
י� | -3.281 |
Token | Russell |
Token ID | 11563 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
terness | +3.444 |
thur | +3.278 |
phia | +3.129 |
chio | +3.076 |
י� | +3.065 |
Neg logit contributions | |
�� | -2.854 |
Belg | -2.676 |
uss | -2.593 |
rol | -2.559 |
roid | -2.513 |
Token | and |
Token ID | 290 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
�� | +0.596 |
Belg | +0.580 |
uss | +0.567 |
rol | +0.553 |
roid | +0.542 |
Neg logit contributions | |
terness | -0.731 |
thur | -0.692 |
phia | -0.662 |
י� | -0.652 |
renheit | -0.650 |
Token | or |
Token ID | 393 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
�� | +0.335 |
Belg | +0.324 |
uss | +0.315 |
rol | +0.309 |
roid | +0.303 |
Neg logit contributions | |
terness | -0.388 |
thur | -0.368 |
phia | -0.350 |
י� | -0.345 |
chio | -0.343 |
Token | 99 |
Token ID | 7388 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
terness | +1.148 |
thur | +1.091 |
phia | +1.037 |
י� | +1.020 |
chio | +1.015 |
Neg logit contributions | |
�� | -1.046 |
Belg | -0.999 |
uss | -0.972 |
rol | -0.955 |
roid | -0.938 |
Token | % |
Token ID | 4 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
�� | +0.055 |
Belg | +0.053 |
uss | +0.052 |
rol | +0.050 |
roid | +0.049 |
Neg logit contributions | |
terness | -0.065 |
thur | -0.062 |
phia | -0.059 |
י� | -0.058 |
chio | -0.058 |
Token | of |
Token ID | 286 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
�� | +1.000 |
Belg | +0.978 |
uss | +0.953 |
rol | +0.929 |
roid | +0.913 |
Neg logit contributions | |
terness | -1.187 |
thur | -1.125 |
phia | -1.073 |
י� | -1.059 |
chio | -1.046 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
terness | +0.028 |
thur | +0.027 |
phia | +0.026 |
י� | +0.025 |
chio | +0.025 |
Neg logit contributions | |
�� | -0.026 |
Belg | -0.025 |
uss | -0.024 |
rol | -0.024 |
roid | -0.023 |
Token | people |
Token ID | 661 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
terness | +0.151 |
thur | +0.143 |
phia | +0.136 |
י� | +0.134 |
chio | +0.134 |
Neg logit contributions | |
�� | -0.127 |
Belg | -0.121 |
uss | -0.118 |
rol | -0.116 |
roid | -0.114 |
Token | we |
Token ID | 356 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
�� | +1.135 |
Belg | +1.106 |
uss | +1.076 |
rol | +1.051 |
roid | +1.029 |
Neg logit contributions | |
terness | -1.493 |
thur | -1.418 |
phia | -1.349 |
י� | -1.336 |
renheit | -1.324 |
Token | so |
Token ID | 523 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
terness | +1.198 |
thur | +1.141 |
phia | +1.088 |
chio | +1.070 |
י� | +1.070 |
Neg logit contributions | |
�� | -1.035 |
Belg | -0.976 |
uss | -0.947 |
rol | -0.930 |
roid | -0.913 |
Token | far |
Token ID | 1290 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
�� | +0.457 |
Belg | +0.444 |
uss | +0.433 |
rol | +0.424 |
roid | +0.412 |
Neg logit contributions | |
terness | -0.641 |
thur | -0.610 |
phia | -0.584 |
י� | -0.577 |
renheit | -0.573 |
Token | know |
Token ID | 760 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
�� | +1.022 |
Belg | +1.006 |
uss | +0.978 |
rol | +0.958 |
roid | +0.940 |
Neg logit contributions | |
terness | -1.232 |
thur | -1.164 |
phia | -1.107 |
י� | -1.093 |
renheit | -1.088 |
Token | to |
Token ID | 284 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
terness | +1.763 |
thur | +1.674 |
phia | +1.606 |
י� | +1.568 |
chio | +1.563 |
Neg logit contributions | |
�� | -1.714 |
Belg | -1.596 |
uss | -1.555 |
rol | -1.523 |
roid | -1.493 |
Token | her |
Token ID | 607 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
terness | +0.210 |
thur | +0.200 |
phia | +0.191 |
י� | +0.189 |
chio | +0.187 |
Neg logit contributions | |
�� | -0.145 |
Belg | -0.139 |
uss | -0.135 |
rol | -0.131 |
roid | -0.128 |
Token | der |
Token ID | 1082 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
terness | +0.712 |
thur | +0.642 |
phia | +0.583 |
י� | +0.566 |
chio | +0.555 |
Neg logit contributions | |
�� | -1.763 |
Belg | -1.719 |
uss | -1.693 |
rol | -1.671 |
roid | -1.650 |
Token | , |
Token ID | 11 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
terness | +4.175 |
thur | +4.023 |
chio | +3.784 |
phia | +3.778 |
י� | +3.772 |
Neg logit contributions | |
�� | -3.904 |
Belg | -3.590 |
uss | -3.495 |
rol | -3.454 |
roid | -3.400 |
Token | Yuri |
Token ID | 38450 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
terness | +1.627 |
thur | +1.547 |
phia | +1.471 |
י� | +1.457 |
chio | +1.448 |
Neg logit contributions | |
�� | -1.369 |
Belg | -1.298 |
uss | -1.268 |
rol | -1.240 |
roid | -1.222 |
Token | Kh |
Token ID | 5311 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
terness | +0.156 |
thur | +0.148 |
phia | +0.142 |
י� | +0.140 |
chio | +0.138 |
Neg logit contributions | |
�� | -0.121 |
Belg | -0.116 |
uss | -0.113 |
rol | -0.110 |
roid | -0.108 |
Token | udi |
Token ID | 47928 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
uss | +4.506 |
rol | +4.322 |
�� | +4.298 |
roid | +4.177 |
Belg | +4.167 |
Neg logit contributions | |
terness | -5.016 |
thur | -4.587 |
י� | -4.525 |
phia | -4.483 |
DEN | -4.391 |
Token | , |
Token ID | 11 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
�� | +4.371 |
uss | +4.305 |
Belg | +4.269 |
rol | +4.233 |
roid | +4.061 |
Neg logit contributions | |
terness | -5.321 |
thur | -5.008 |
phia | -4.841 |
renheit | -4.735 |
י� | -4.708 |
Token | and |
Token ID | 290 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
terness | +1.375 |
thur | +1.312 |
phia | +1.246 |
י� | +1.233 |
chio | +1.226 |
Neg logit contributions | |
�� | -1.136 |
Belg | -1.078 |
uss | -1.050 |
rol | -1.028 |
roid | -1.012 |
Token | his |
Token ID | 465 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
terness | +0.036 |
thur | +0.035 |
phia | +0.033 |
י� | +0.033 |
chio | +0.033 |
Neg logit contributions | |
�� | -0.020 |
Belg | -0.019 |
uss | -0.018 |
rol | -0.018 |
roid | -0.017 |
Token | sons |
Token ID | 11989 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
terness | +0.405 |
thur | +0.376 |
phia | +0.351 |
י� | +0.343 |
chio | +0.339 |
Neg logit contributions | |
�� | -0.648 |
Belg | -0.629 |
uss | -0.617 |
rol | -0.607 |
roid | -0.598 |
Token | found |
Token ID | 1043 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
terness | +2.676 |
thur | +2.556 |
phia | +2.429 |
י� | +2.406 |
chio | +2.403 |
Neg logit contributions | |
�� | -2.329 |
Belg | -2.198 |
uss | -2.141 |
rol | -2.092 |
roid | -2.073 |
Token | of |
Token ID | 286 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
�� | +1.234 |
Belg | +1.200 |
uss | +1.166 |
rol | +1.138 |
roid | +1.118 |
Neg logit contributions | |
terness | -1.395 |
thur | -1.338 |
phia | -1.268 |
י� | -1.241 |
chio | -1.240 |
Token | calling |
Token ID | 4585 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Belg | +2.270 |
�� | +2.246 |
uss | +2.183 |
rol | +2.088 |
roid | +2.044 |
Neg logit contributions | |
terness | -4.467 |
thur | -4.261 |
phia | -4.103 |
renheit | -4.072 |
י� | -4.040 |
Token | out |
Token ID | 503 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
�� | +1.370 |
Belg | +1.362 |
uss | +1.333 |
rol | +1.286 |
roid | +1.258 |
Neg logit contributions | |
terness | -1.984 |
thur | -1.885 |
phia | -1.802 |
י� | -1.778 |
renheit | -1.768 |
Token | the |
Token ID | 262 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
Belg | +1.896 |
�� | +1.881 |
uss | +1.836 |
rol | +1.787 |
roid | +1.756 |
Neg logit contributions | |
terness | -2.271 |
thur | -2.142 |
phia | -2.048 |
י� | -2.008 |
renheit | -1.996 |
Token | hyper |
Token ID | 8718 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
�� | +1.709 |
Belg | +1.706 |
uss | +1.641 |
rol | +1.591 |
roid | +1.570 |
Neg logit contributions | |
terness | -2.314 |
thur | -2.195 |
phia | -2.099 |
י� | -2.064 |
renheit | -2.053 |
Token | b |
Token ID | 65 |
Feature activation | -7.87e+00 |
Pos logit contributions | |
terness | +0.203 |
thur | +0.192 |
phia | +0.182 |
י� | +0.180 |
chio | +0.178 |
Neg logit contributions | |
�� | -0.198 |
Belg | -0.189 |
uss | -0.184 |
rol | -0.180 |
roid | -0.177 |
Token | olic |
Token ID | 4160 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
uss | +5.962 |
rol | +5.827 |
Belg | +5.694 |
roid | +5.611 |
�� | +5.608 |
Neg logit contributions | |
terness | -5.686 |
thur | -5.267 |
י� | -5.197 |
phia | -5.043 |
chio | -5.032 |
Token | Republican |
Token ID | 3415 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
terness | +1.115 |
thur | +1.062 |
phia | +1.015 |
י� | +1.003 |
chio | +1.000 |
Neg logit contributions | |
�� | -0.856 |
Belg | -0.806 |
uss | -0.784 |
rol | -0.770 |
roid | -0.751 |
Token | allegations |
Token ID | 7636 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
terness | +2.725 |
thur | +2.598 |
phia | +2.490 |
י� | +2.449 |
chio | +2.449 |
Neg logit contributions | |
�� | -2.111 |
Belg | -1.949 |
uss | -1.889 |
rol | -1.871 |
roid | -1.815 |
Token | MM |
Token ID | 20806 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
�� | +0.766 |
Belg | +0.744 |
uss | +0.724 |
rol | +0.707 |
roid | +0.693 |
Neg logit contributions | |
terness | -0.898 |
thur | -0.858 |
phia | -0.821 |
י� | -0.803 |
chio | -0.797 |
Token | legitim |
Token ID | 18262 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
terness | +3.117 |
thur | +2.969 |
phia | +2.821 |
י� | +2.771 |
chio | +2.766 |
Neg logit contributions | |
�� | -2.847 |
Belg | -2.691 |
uss | -2.579 |
rol | -2.560 |
roid | -2.498 |
Token | " |
Token ID | 366 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
Belg | +2.488 |
�� | +2.449 |
uss | +2.420 |
rol | +2.417 |
roid | +2.365 |
Neg logit contributions | |
terness | -3.350 |
thur | -3.136 |
phia | -2.960 |
י� | -2.907 |
renheit | -2.889 |
Token | 94 |
Token ID | 5824 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
terness | +0.522 |
thur | +0.491 |
phia | +0.465 |
י� | +0.456 |
chio | +0.454 |
Neg logit contributions | |
�� | -0.537 |
Belg | -0.521 |
uss | -0.509 |
rol | -0.499 |
roid | -0.490 |
Token | "] |
Token ID | 8973 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
�� | +1.172 |
Belg | +1.113 |
uss | +1.076 |
rol | +1.049 |
roid | +1.012 |
Neg logit contributions | |
terness | -2.325 |
thur | -2.230 |
phia | -2.141 |
י� | -2.108 |
chio | -2.104 |
Token | [ |
Token ID | 685 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
terness | +0.751 |
thur | +0.713 |
phia | +0.679 |
י� | +0.669 |
chio | +0.664 |
Neg logit contributions | |
�� | -0.631 |
Belg | -0.606 |
uss | -0.590 |
rol | -0.577 |
roid | -0.566 |
Token | Event |
Token ID | 9237 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
�� | +0.541 |
Belg | +0.521 |
uss | +0.509 |
rol | +0.499 |
roid | +0.490 |
Neg logit contributions | |
terness | -0.559 |
thur | -0.528 |
phia | -0.502 |
י� | -0.493 |
chio | -0.490 |
Token | Date |
Token ID | 10430 |
Feature activation | -6.30e+00 |
Pos logit contributions | |
�� | +0.364 |
Belg | +0.353 |
uss | +0.346 |
rol | +0.340 |
roid | +0.335 |
Neg logit contributions | |
terness | -0.260 |
thur | -0.243 |
phia | -0.228 |
י� | -0.223 |
chio | -0.221 |
Token | " |
Token ID | 366 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
uss | +3.893 |
Belg | +3.855 |
rol | +3.828 |
roid | +3.756 |
�� | +3.680 |
Neg logit contributions | |
terness | -5.606 |
thur | -5.156 |
renheit | -4.903 |
phia | -4.892 |
chio | -4.737 |
Token | 2016 |
Token ID | 5304 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
terness | +0.489 |
thur | +0.461 |
phia | +0.436 |
י� | +0.430 |
chio | +0.423 |
Neg logit contributions | |
�� | -0.614 |
Belg | -0.591 |
uss | -0.576 |
rol | -0.567 |
roid | -0.558 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Belg | +1.650 |
uss | +1.625 |
�� | +1.622 |
rol | +1.590 |
roid | +1.526 |
Neg logit contributions | |
terness | -2.453 |
thur | -2.283 |
phia | -2.195 |
renheit | -2.148 |
chio | -2.117 |
Token | ?? |
Token ID | 3548 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
�� | +0.936 |
Belg | +0.915 |
uss | +0.894 |
rol | +0.868 |
roid | +0.855 |
Neg logit contributions | |
terness | -1.240 |
thur | -1.167 |
phia | -1.127 |
renheit | -1.100 |
chio | -1.094 |
Token | .? |
Token ID | 40791 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
�� | +1.232 |
Belg | +1.200 |
uss | +1.165 |
rol | +1.126 |
roid | +1.092 |
Neg logit contributions | |
terness | -2.121 |
thur | -2.011 |
phia | -1.921 |
chio | -1.905 |
י� | -1.888 |
Token | of |
Token ID | 286 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
terness | +1.147 |
thur | +1.080 |
י� | +1.019 |
phia | +1.016 |
renheit | +1.005 |
Neg logit contributions | |
�� | -1.197 |
Belg | -1.151 |
uss | -1.125 |
rol | -1.102 |
roid | -1.084 |
Token | modern |
Token ID | 3660 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
terness | +0.803 |
thur | +0.765 |
phia | +0.730 |
י� | +0.721 |
chio | +0.715 |
Neg logit contributions | |
�� | -0.640 |
Belg | -0.607 |
uss | -0.594 |
rol | -0.581 |
roid | -0.570 |
Token | architectural |
Token ID | 27070 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
Belg | +3.131 |
�� | +3.055 |
uss | +2.937 |
rol | +2.836 |
roid | +2.703 |
Neg logit contributions | |
terness | -5.462 |
thur | -5.122 |
phia | -4.964 |
chio | -4.868 |
renheit | -4.859 |
Token | firms |
Token ID | 9611 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Belg | +2.302 |
�� | +2.298 |
uss | +2.206 |
rol | +2.143 |
roid | +2.084 |
Neg logit contributions | |
terness | -3.258 |
thur | -3.063 |
phia | -2.945 |
renheit | -2.902 |
י� | -2.902 |
Token | and |
Token ID | 290 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
�� | +0.425 |
Belg | +0.408 |
uss | +0.397 |
rol | +0.388 |
roid | +0.380 |
Neg logit contributions | |
terness | -0.555 |
thur | -0.530 |
phia | -0.505 |
י� | -0.496 |
chio | -0.496 |
Token | urban |
Token ID | 7876 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
�� | +0.644 |
Belg | +0.619 |
uss | +0.601 |
rol | +0.588 |
roid | +0.576 |
Neg logit contributions | |
terness | -0.808 |
thur | -0.768 |
phia | -0.733 |
י� | -0.722 |
chio | -0.717 |
Token | planning |
Token ID | 5410 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
Belg | +3.693 |
�� | +3.612 |
uss | +3.505 |
rol | +3.355 |
roid | +3.320 |
Neg logit contributions | |
terness | -5.629 |
thur | -5.312 |
phia | -5.062 |
chio | -5.054 |
renheit | -5.025 |
Token | . |
Token ID | 13 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
�� | +2.066 |
Belg | +2.032 |
uss | +1.971 |
rol | +1.929 |
roid | +1.877 |
Neg logit contributions | |
terness | -2.763 |
thur | -2.612 |
phia | -2.488 |
chio | -2.466 |
י� | -2.450 |
Token |
|
Token ID | 198 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
�� | +0.459 |
Belg | +0.455 |
uss | +0.437 |
rol | +0.428 |
roid | +0.416 |
Neg logit contributions | |
terness | -0.573 |
thur | -0.543 |
phia | -0.515 |
renheit | -0.506 |
chio | -0.505 |
Token |
|
Token ID | 198 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
terness | +1.530 |
thur | +1.456 |
phia | +1.371 |
י� | +1.359 |
chio | +1.342 |
Neg logit contributions | |
�� | -1.900 |
Belg | -1.801 |
uss | -1.759 |
rol | -1.724 |
roid | -1.701 |
Token | Yet |
Token ID | 11486 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
terness | +0.464 |
thur | +0.438 |
phia | +0.414 |
י� | +0.407 |
chio | +0.404 |
Neg logit contributions | |
�� | -0.480 |
Belg | -0.464 |
uss | -0.453 |
rol | -0.445 |
roid | -0.437 |
Token | between |
Token ID | 1022 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
�� | +1.140 |
Belg | +1.110 |
uss | +1.067 |
rol | +1.043 |
roid | +1.017 |
Neg logit contributions | |
terness | -1.937 |
thur | -1.841 |
phia | -1.772 |
י� | -1.748 |
renheit | -1.738 |
Token | sub |
Token ID | 850 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
�� | +2.090 |
Belg | +2.065 |
uss | +1.970 |
rol | +1.941 |
roid | +1.896 |
Neg logit contributions | |
terness | -3.093 |
thur | -2.928 |
phia | -2.831 |
renheit | -2.777 |
י� | -2.776 |
Token | - |
Token ID | 12 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
�� | +1.114 |
Belg | +1.072 |
uss | +1.049 |
rol | +1.028 |
roid | +1.007 |
Neg logit contributions | |
terness | -1.390 |
thur | -1.315 |
phia | -1.260 |
י� | -1.237 |
chio | -1.228 |
Token | st |
Token ID | 301 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
�� | +2.871 |
Belg | +2.842 |
uss | +2.837 |
rol | +2.787 |
roid | +2.755 |
Neg logit contributions | |
terness | -3.307 |
thur | -3.047 |
phia | -2.953 |
י� | -2.885 |
renheit | -2.885 |
Token | ages |
Token ID | 1095 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
uss | +5.722 |
rol | +5.720 |
roid | +5.549 |
Belg | +5.511 |
�� | +5.289 |
Neg logit contributions | |
terness | -5.907 |
thur | -5.447 |
phia | -5.208 |
י� | -5.025 |
DEN | -4.965 |
Token | Super |
Token ID | 3115 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
�� | +1.640 |
Belg | +1.599 |
uss | +1.563 |
rol | +1.521 |
roid | +1.490 |
Neg logit contributions | |
terness | -2.041 |
thur | -1.940 |
phia | -1.865 |
renheit | -1.826 |
י� | -1.814 |
Token | Mario |
Token ID | 10682 |
Feature activation | -8.92e+00 |
Pos logit contributions | |
�� | +4.266 |
Belg | +4.263 |
uss | +4.118 |
rol | +4.100 |
roid | +4.022 |
Neg logit contributions | |
terness | -5.324 |
thur | -4.952 |
phia | -4.790 |
י� | -4.757 |
renheit | -4.603 |
Token | 64 |
Token ID | 5598 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
Belg | +5.127 |
�� | +5.093 |
uss | +5.004 |
roid | +4.852 |
rol | +4.825 |
Neg logit contributions | |
terness | -8.106 |
thur | -7.537 |
phia | -7.328 |
י� | -7.270 |
renheit | -7.128 |
Token | - |
Token ID | 12 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
�� | +1.868 |
Belg | +1.820 |
uss | +1.779 |
rol | +1.744 |
roid | +1.720 |
Neg logit contributions | |
terness | -2.213 |
thur | -2.093 |
phia | -2.002 |
י� | -1.971 |
renheit | -1.952 |
Token | style |
Token ID | 7635 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
terness | +0.330 |
thur | +0.312 |
phia | +0.297 |
י� | +0.292 |
chio | +0.290 |
Neg logit contributions | |
�� | -0.309 |
Belg | -0.297 |
uss | -0.289 |
rol | -0.283 |
roid | -0.278 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
�� | +1.609 |
Belg | +1.557 |
uss | +1.515 |
rol | +1.483 |
roid | +1.456 |
Neg logit contributions | |
terness | -1.961 |
thur | -1.862 |
phia | -1.779 |
י� | -1.747 |
renheit | -1.738 |