Token | has |
Token ID | 468 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
entric | +0.280 |
orical | +0.266 |
cester | +0.266 |
metic | +0.261 |
ignment | +0.259 |
Neg logit contributions | |
PLA | -0.253 |
Occupations | -0.233 |
ORTS | -0.232 |
Mp | -0.231 |
tremend | -0.228 |
Token | left |
Token ID | 1364 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
entric | +3.257 |
orical | +3.102 |
cester | +3.066 |
ignment | +3.033 |
metic | +3.023 |
Neg logit contributions | |
PLA | -3.312 |
ORTS | -3.045 |
Mp | -3.038 |
Occupations | -3.036 |
tremend | -2.976 |
Token | us |
Token ID | 514 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
entric | +2.711 |
orical | +2.601 |
cester | +2.569 |
metic | +2.533 |
ignment | +2.525 |
Neg logit contributions | |
PLA | -2.457 |
ORTS | -2.277 |
Mp | -2.256 |
Occupations | -2.237 |
tremend | -2.231 |
Token | with |
Token ID | 351 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
entric | +0.054 |
orical | +0.051 |
cester | +0.051 |
metic | +0.050 |
ignment | +0.049 |
Neg logit contributions | |
PLA | -0.053 |
Occupations | -0.049 |
ORTS | -0.048 |
Mp | -0.048 |
tremend | -0.048 |
Token | an |
Token ID | 281 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
entric | +0.833 |
orical | +0.787 |
cester | +0.785 |
metic | +0.769 |
ignment | +0.764 |
Neg logit contributions | |
PLA | -0.906 |
Occupations | -0.840 |
ORTS | -0.838 |
Mp | -0.834 |
tremend | -0.825 |
Token | olig |
Token ID | 24869 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
entric | +0.253 |
orical | +0.239 |
cester | +0.238 |
metic | +0.233 |
ignment | +0.231 |
Neg logit contributions | |
PLA | -0.303 |
Occupations | -0.283 |
ORTS | -0.282 |
Mp | -0.280 |
tremend | -0.278 |
Token | archy |
Token ID | 9282 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
entric | +6.256 |
orical | +5.766 |
cester | +5.658 |
ignment | +5.488 |
metic | +5.484 |
Neg logit contributions | |
PLA | -9.079 |
Occupations | -8.822 |
ORTS | -8.713 |
Mp | -8.573 |
tremend | -8.556 |
Token | of |
Token ID | 286 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
entric | +3.928 |
orical | +3.700 |
cester | +3.640 |
metic | +3.614 |
ignment | +3.587 |
Neg logit contributions | |
PLA | -3.988 |
ORTS | -3.684 |
Mp | -3.674 |
Occupations | -3.664 |
tremend | -3.562 |
Token | platform |
Token ID | 3859 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
entric | +0.160 |
cester | +0.151 |
orical | +0.150 |
metic | +0.148 |
ignment | +0.146 |
Neg logit contributions | |
PLA | -0.182 |
Occupations | -0.170 |
ORTS | -0.169 |
Mp | -0.168 |
tremend | -0.166 |
Token | monopol |
Token ID | 30797 |
Feature activation | +7.46e+00 |
Pos logit contributions | |
entric | +1.738 |
orical | +1.637 |
cester | +1.614 |
metic | +1.596 |
ignment | +1.580 |
Neg logit contributions | |
PLA | -1.968 |
ORTS | -1.825 |
Occupations | -1.824 |
Mp | -1.819 |
tremend | -1.803 |
Token | ies |
Token ID | 444 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
entric | +4.710 |
orical | +4.430 |
cester | +4.318 |
ignment | +4.290 |
metic | +4.275 |
Neg logit contributions | |
PLA | -6.177 |
Occupations | -5.725 |
tremend | -5.692 |
ORTS | -5.656 |
Mp | -5.623 |
Token | fork |
Token ID | 32523 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
PLA | +1.239 |
Mp | +1.160 |
ORTS | +1.159 |
Occupations | +1.151 |
tremend | +1.138 |
Neg logit contributions | |
entric | -0.601 |
orical | -0.551 |
cester | -0.546 |
metic | -0.525 |
ignment | -0.516 |
Token | which |
Token ID | 543 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
entric | +1.500 |
orical | +1.411 |
cester | +1.397 |
metic | +1.388 |
ignment | +1.383 |
Neg logit contributions | |
PLA | -1.762 |
Occupations | -1.652 |
ORTS | -1.641 |
Mp | -1.639 |
tremend | -1.630 |
Token | increases |
Token ID | 5732 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
entric | +0.697 |
cester | +0.664 |
orical | +0.662 |
metic | +0.648 |
ignment | +0.646 |
Neg logit contributions | |
PLA | -0.684 |
Occupations | -0.635 |
ORTS | -0.630 |
Mp | -0.626 |
tremend | -0.625 |
Token | capacity |
Token ID | 5339 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
PLA | +0.843 |
ORTS | +0.786 |
Mp | +0.783 |
Occupations | +0.783 |
tremend | +0.774 |
Neg logit contributions | |
entric | -0.657 |
cester | -0.616 |
orical | -0.616 |
metic | -0.603 |
ignment | -0.596 |
Token | and |
Token ID | 290 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
entric | +1.992 |
orical | +1.886 |
cester | +1.876 |
metic | +1.854 |
ignment | +1.836 |
Neg logit contributions | |
PLA | -2.388 |
Occupations | -2.217 |
ORTS | -2.211 |
Mp | -2.196 |
tremend | -2.186 |
Token | scal |
Token ID | 16578 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
PLA | +0.051 |
Occupations | +0.047 |
ORTS | +0.047 |
Mp | +0.047 |
tremend | +0.046 |
Neg logit contributions | |
entric | -0.047 |
orical | -0.045 |
cester | -0.045 |
metic | -0.044 |
ignment | -0.043 |
Token | ability |
Token ID | 1799 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
entric | +5.211 |
metic | +4.813 |
orical | +4.780 |
ignment | +4.771 |
cester | +4.703 |
Neg logit contributions | |
PLA | -9.228 |
Occupations | -9.127 |
tremend | -8.902 |
ORTS | -8.879 |
CHAT | -8.611 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
entric | +1.172 |
orical | +1.111 |
cester | +1.106 |
metic | +1.088 |
ignment | +1.078 |
Neg logit contributions | |
PLA | -1.359 |
ORTS | -1.257 |
Occupations | -1.257 |
Mp | -1.254 |
tremend | -1.241 |
Token | and |
Token ID | 290 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
entric | +0.078 |
orical | +0.074 |
cester | +0.074 |
metic | +0.072 |
ignment | +0.072 |
Neg logit contributions | |
PLA | -0.091 |
Occupations | -0.084 |
ORTS | -0.084 |
Mp | -0.084 |
tremend | -0.083 |
Token | recent |
Token ID | 2274 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
PLA | +0.209 |
Occupations | +0.193 |
ORTS | +0.192 |
Mp | +0.191 |
tremend | +0.189 |
Neg logit contributions | |
entric | -0.216 |
orical | -0.205 |
cester | -0.204 |
metic | -0.201 |
ignment | -0.199 |
Token | speed |
Token ID | 2866 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
entric | +0.506 |
orical | +0.479 |
cester | +0.478 |
metic | +0.467 |
ignment | +0.464 |
Neg logit contributions | |
PLA | -0.574 |
Occupations | -0.532 |
ORTS | -0.532 |
Mp | -0.528 |
tremend | -0.524 |
Token | Star |
Token ID | 2907 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
entric | +0.832 |
orical | +0.787 |
cester | +0.784 |
metic | +0.768 |
ignment | +0.763 |
Neg logit contributions | |
PLA | -0.922 |
Occupations | -0.854 |
ORTS | -0.854 |
Mp | -0.849 |
tremend | -0.841 |
Token | Trek |
Token ID | 12338 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
PLA | +1.748 |
Occupations | +1.581 |
Mp | +1.556 |
ORTS | +1.551 |
tremend | +1.503 |
Neg logit contributions | |
entric | -3.322 |
orical | -3.188 |
cester | -3.164 |
metic | -3.134 |
ignment | -3.111 |
Token | universe |
Token ID | 6881 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
PLA | +0.312 |
Occupations | +0.287 |
ORTS | +0.286 |
Mp | +0.284 |
tremend | +0.280 |
Neg logit contributions | |
entric | -0.359 |
orical | -0.342 |
cester | -0.341 |
metic | -0.335 |
ignment | -0.333 |
Token | neglect |
Token ID | 17985 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
PLA | +0.497 |
Occupations | +0.458 |
ORTS | +0.456 |
Mp | +0.453 |
tremend | +0.447 |
Neg logit contributions | |
entric | -0.565 |
orical | -0.539 |
cester | -0.539 |
metic | -0.530 |
ignment | -0.524 |
Token | s |
Token ID | 82 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
PLA | +0.798 |
ORTS | +0.749 |
Occupations | +0.749 |
Mp | +0.747 |
tremend | +0.739 |
Neg logit contributions | |
entric | -0.466 |
cester | -0.433 |
orical | -0.432 |
metic | -0.420 |
ignment | -0.417 |
Token | relat |
Token ID | 48993 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
entric | +0.231 |
orical | +0.218 |
cester | +0.218 |
metic | +0.213 |
ignment | +0.212 |
Neg logit contributions | |
PLA | -0.241 |
Occupations | -0.223 |
ORTS | -0.223 |
Mp | -0.222 |
tremend | -0.219 |
Token | iv |
Token ID | 452 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
entric | +6.804 |
orical | +6.512 |
ignment | +6.194 |
metic | +6.100 |
cester | +6.065 |
Neg logit contributions | |
PLA | -8.079 |
Occupations | -7.460 |
tremend | -7.337 |
ORTS | -7.211 |
Mp | -7.155 |
Token | istic |
Token ID | 2569 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
entric | +0.671 |
orical | +0.599 |
cester | +0.596 |
metic | +0.571 |
ignment | +0.559 |
Neg logit contributions | |
PLA | -2.226 |
Occupations | -2.115 |
ORTS | -2.112 |
Mp | -2.107 |
tremend | -2.092 |
Token | effects |
Token ID | 3048 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
entric | +1.751 |
orical | +1.635 |
cester | +1.620 |
metic | +1.586 |
ignment | +1.582 |
Neg logit contributions | |
PLA | -2.441 |
ORTS | -2.271 |
Occupations | -2.263 |
Mp | -2.255 |
tremend | -2.238 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
entric | +1.003 |
orical | +0.947 |
cester | +0.944 |
metic | +0.926 |
ignment | +0.919 |
Neg logit contributions | |
PLA | -1.117 |
Occupations | -1.035 |
ORTS | -1.033 |
Mp | -1.029 |
tremend | -1.018 |
Token | ( |
Token ID | 357 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
entric | +0.196 |
orical | +0.186 |
cester | +0.186 |
metic | +0.183 |
ignment | +0.181 |
Neg logit contributions | |
PLA | -0.176 |
Occupations | -0.162 |
ORTS | -0.161 |
Mp | -0.160 |
tremend | -0.158 |
Token | think |
Token ID | 892 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
PLA | +0.466 |
Occupations | +0.430 |
ORTS | +0.429 |
Mp | +0.427 |
tremend | +0.420 |
Neg logit contributions | |
entric | -0.490 |
orical | -0.465 |
cester | -0.463 |
metic | -0.454 |
ignment | -0.451 |
Token | the |
Token ID | 262 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
entric | +0.507 |
orical | +0.472 |
cester | +0.470 |
metic | +0.458 |
ignment | +0.454 |
Neg logit contributions | |
PLA | -0.854 |
Occupations | -0.802 |
ORTS | -0.801 |
Mp | -0.798 |
tremend | -0.792 |
Token | average |
Token ID | 2811 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
entric | +0.413 |
orical | +0.388 |
cester | +0.387 |
metic | +0.378 |
ignment | +0.375 |
Neg logit contributions | |
PLA | -0.530 |
Occupations | -0.494 |
ORTS | -0.493 |
Mp | -0.491 |
tremend | -0.486 |
Token | rent |
Token ID | 5602 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
entric | +0.729 |
cester | +0.687 |
orical | +0.686 |
metic | +0.673 |
ignment | +0.668 |
Neg logit contributions | |
PLA | -0.850 |
ORTS | -0.788 |
Occupations | -0.786 |
Mp | -0.781 |
tremend | -0.779 |
Token | is |
Token ID | 318 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
entric | +3.098 |
orical | +2.921 |
cester | +2.917 |
ignment | +2.899 |
metic | +2.875 |
Neg logit contributions | |
PLA | -3.630 |
ORTS | -3.407 |
tremend | -3.397 |
Occupations | -3.386 |
Mp | -3.317 |
Token | € |
Token ID | 10432 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
entric | +2.228 |
cester | +2.114 |
orical | +2.110 |
metic | +2.067 |
ignment | +2.049 |
Neg logit contributions | |
PLA | -2.846 |
ORTS | -2.650 |
Occupations | -2.643 |
Mp | -2.620 |
tremend | -2.616 |
Token | 1 |
Token ID | 16 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
entric | +7.062 |
orical | +6.787 |
cester | +6.659 |
es | +6.646 |
metic | +6.583 |
Neg logit contributions | |
tremend | -7.191 |
PLA | -6.591 |
Occupations | -6.288 |
ORTS | -6.245 |
Mp | -6.094 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
entric | +0.325 |
orical | +0.306 |
cester | +0.306 |
metic | +0.299 |
ignment | +0.297 |
Neg logit contributions | |
PLA | -0.362 |
Occupations | -0.335 |
ORTS | -0.335 |
Mp | -0.334 |
tremend | -0.330 |
Token | 707 |
Token ID | 24038 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
entric | +0.867 |
orical | +0.822 |
cester | +0.820 |
metic | +0.805 |
ignment | +0.799 |
Neg logit contributions | |
PLA | -0.827 |
Occupations | -0.762 |
ORTS | -0.761 |
Mp | -0.757 |
tremend | -0.748 |
Token | and |
Token ID | 290 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
entric | +0.459 |
orical | +0.433 |
cester | +0.431 |
metic | +0.422 |
ignment | +0.419 |
Neg logit contributions | |
PLA | -0.535 |
Occupations | -0.497 |
ORTS | -0.496 |
Mp | -0.494 |
tremend | -0.489 |
Token | add |
Token ID | 751 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
entric | +0.639 |
orical | +0.604 |
cester | +0.602 |
metic | +0.590 |
ignment | +0.585 |
Neg logit contributions | |
PLA | -0.724 |
Occupations | -0.671 |
ORTS | -0.670 |
Mp | -0.667 |
tremend | -0.660 |
Token | is |
Token ID | 318 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
entric | +1.138 |
orical | +1.081 |
cester | +1.078 |
metic | +1.058 |
ignment | +1.052 |
Neg logit contributions | |
PLA | -1.074 |
ORTS | -0.992 |
Occupations | -0.992 |
Mp | -0.986 |
tremend | -0.976 |
Token | in |
Token ID | 287 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
entric | +2.123 |
orical | +2.017 |
cester | +1.994 |
metic | +1.964 |
ignment | +1.953 |
Neg logit contributions | |
PLA | -2.329 |
Occupations | -2.171 |
ORTS | -2.163 |
Mp | -2.150 |
tremend | -2.125 |
Token | with |
Token ID | 351 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
PLA | +1.080 |
Occupations | +1.001 |
ORTS | +0.995 |
Mp | +0.989 |
tremend | +0.983 |
Neg logit contributions | |
entric | -1.057 |
cester | -0.999 |
orical | -0.997 |
metic | -0.976 |
ignment | -0.968 |
Token | all |
Token ID | 477 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
entric | +1.037 |
orical | +0.983 |
cester | +0.981 |
metic | +0.962 |
ignment | +0.955 |
Neg logit contributions | |
PLA | -0.996 |
Occupations | -0.918 |
ORTS | -0.916 |
Mp | -0.912 |
tremend | -0.901 |
Token | the |
Token ID | 262 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
entric | +1.681 |
orical | +1.599 |
cester | +1.596 |
metic | +1.566 |
ignment | +1.560 |
Neg logit contributions | |
PLA | -1.548 |
Occupations | -1.420 |
ORTS | -1.418 |
Mp | -1.412 |
tremend | -1.396 |
Token | olig |
Token ID | 24869 |
Feature activation | +9.81e+00 |
Pos logit contributions | |
entric | +0.245 |
orical | +0.228 |
cester | +0.228 |
metic | +0.222 |
ignment | +0.219 |
Neg logit contributions | |
PLA | -0.359 |
Occupations | -0.336 |
ORTS | -0.335 |
Mp | -0.334 |
tremend | -0.331 |
Token | archs |
Token ID | 34592 |
Feature activation | +7.22e+00 |
Pos logit contributions | |
entric | +5.787 |
cester | +5.479 |
orical | +5.419 |
es | +5.268 |
ignment | +5.219 |
Neg logit contributions | |
PLA | -8.282 |
Occupations | -7.817 |
tremend | -7.744 |
Mp | -7.700 |
ORTS | -7.679 |
Token | , |
Token ID | 11 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
entric | +4.726 |
orical | +4.452 |
cester | +4.446 |
metic | +4.397 |
ignment | +4.380 |
Neg logit contributions | |
PLA | -5.614 |
Mp | -5.246 |
Occupations | -5.225 |
ORTS | -5.213 |
tremend | -5.185 |
Token | � |
Token ID | 447 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
entric | +0.432 |
orical | +0.408 |
cester | +0.408 |
metic | +0.400 |
ignment | +0.396 |
Neg logit contributions | |
PLA | -0.449 |
Occupations | -0.415 |
ORTS | -0.413 |
Mp | -0.412 |
tremend | -0.407 |
Token | � |
Token ID | 251 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
PLA | +0.799 |
Occupations | +0.751 |
ORTS | +0.747 |
Mp | +0.744 |
tremend | +0.725 |
Neg logit contributions | |
entric | -0.588 |
cester | -0.545 |
orical | -0.539 |
metic | -0.534 |
ignment | -0.527 |
Token | Letter |
Token ID | 18121 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
PLA | +0.237 |
Occupations | +0.219 |
ORTS | +0.218 |
Mp | +0.217 |
tremend | +0.214 |
Neg logit contributions | |
entric | -0.250 |
orical | -0.237 |
cester | -0.237 |
metic | -0.232 |
ignment | -0.230 |
Token | one |
Token ID | 530 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
entric | +1.836 |
orical | +1.737 |
cester | +1.732 |
metic | +1.699 |
ignment | +1.687 |
Neg logit contributions | |
PLA | -1.959 |
Occupations | -1.812 |
ORTS | -1.810 |
Mp | -1.801 |
tremend | -1.780 |
Token | party |
Token ID | 2151 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
entric | +1.046 |
orical | +0.993 |
cester | +0.990 |
metic | +0.972 |
ignment | +0.965 |
Neg logit contributions | |
PLA | -0.982 |
Occupations | -0.904 |
ORTS | -0.902 |
Mp | -0.898 |
tremend | -0.887 |
Token | that |
Token ID | 326 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
entric | +0.715 |
orical | +0.675 |
cester | +0.675 |
metic | +0.660 |
ignment | +0.654 |
Neg logit contributions | |
PLA | -0.807 |
Occupations | -0.747 |
ORTS | -0.747 |
Mp | -0.743 |
tremend | -0.737 |
Token | serves |
Token ID | 9179 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
entric | +0.666 |
orical | +0.632 |
cester | +0.631 |
metic | +0.619 |
ignment | +0.615 |
Neg logit contributions | |
PLA | -0.631 |
Occupations | -0.581 |
ORTS | -0.580 |
Mp | -0.577 |
tremend | -0.570 |
Token | powerful |
Token ID | 3665 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
entric | +0.425 |
orical | +0.402 |
cester | +0.400 |
metic | +0.393 |
ignment | +0.390 |
Neg logit contributions | |
PLA | -0.454 |
Occupations | -0.421 |
ORTS | -0.420 |
Mp | -0.418 |
tremend | -0.413 |
Token | corporate |
Token ID | 6355 |
Feature activation | +9.70e+00 |
Pos logit contributions | |
entric | +0.833 |
orical | +0.782 |
cester | +0.780 |
metic | +0.763 |
ignment | +0.756 |
Neg logit contributions | |
PLA | -1.089 |
Occupations | -1.015 |
ORTS | -1.013 |
Mp | -1.009 |
tremend | -0.999 |
Token | interests |
Token ID | 5353 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
entric | +4.879 |
cester | +4.517 |
orical | +4.493 |
es | +4.483 |
ignment | +4.439 |
Neg logit contributions | |
PLA | -8.848 |
ORTS | -8.339 |
Mp | -8.339 |
tremend | -8.257 |
Occupations | -8.238 |
Token | unab |
Token ID | 40986 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
entric | +2.759 |
orical | +2.587 |
cester | +2.577 |
metic | +2.527 |
ignment | +2.515 |
Neg logit contributions | |
PLA | -3.296 |
Mp | -3.055 |
Occupations | -3.051 |
ORTS | -3.047 |
tremend | -2.985 |
Token | ashed |
Token ID | 5263 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
entric | +0.983 |
orical | +0.922 |
cester | +0.915 |
metic | +0.894 |
ignment | +0.885 |
Neg logit contributions | |
PLA | -1.310 |
Occupations | -1.232 |
ORTS | -1.229 |
Mp | -1.223 |
tremend | -1.216 |
Token | ly |
Token ID | 306 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
entric | +2.158 |
orical | +2.062 |
cester | +2.056 |
metic | +2.024 |
ignment | +2.012 |
Neg logit contributions | |
PLA | -1.538 |
Occupations | -1.397 |
ORTS | -1.395 |
Mp | -1.386 |
tremend | -1.366 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
entric | +1.970 |
orical | +1.855 |
cester | +1.848 |
metic | +1.810 |
ignment | +1.796 |
Neg logit contributions | |
PLA | -2.393 |
Occupations | -2.227 |
ORTS | -2.223 |
Mp | -2.215 |
tremend | -2.188 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
PLA | +1.172 |
ORTS | +1.088 |
Occupations | +1.088 |
Mp | +1.082 |
tremend | +1.066 |
Neg logit contributions | |
entric | -1.132 |
cester | -1.075 |
orical | -1.074 |
metic | -1.046 |
ignment | -1.038 |
Token | I |
Token ID | 314 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
entric | +0.228 |
orical | +0.216 |
cester | +0.216 |
metic | +0.212 |
ignment | +0.211 |
Neg logit contributions | |
PLA | -0.209 |
ORTS | -0.192 |
Occupations | -0.192 |
Mp | -0.191 |
tremend | -0.189 |
Token | will |
Token ID | 481 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
entric | +1.125 |
orical | +1.069 |
cester | +1.066 |
metic | +1.047 |
ignment | +1.038 |
Neg logit contributions | |
PLA | -1.085 |
Occupations | -1.006 |
ORTS | -1.004 |
Mp | -0.996 |
tremend | -0.989 |
Token | donate |
Token ID | 16565 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
entric | +0.055 |
orical | +0.052 |
cester | +0.052 |
metic | +0.051 |
ignment | +0.050 |
Neg logit contributions | |
PLA | -0.053 |
ORTS | -0.048 |
Occupations | -0.048 |
Mp | -0.048 |
tremend | -0.047 |
Token | them |
Token ID | 606 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
entric | +1.996 |
orical | +1.889 |
cester | +1.870 |
metic | +1.855 |
ignment | +1.822 |
Neg logit contributions | |
PLA | -2.393 |
ORTS | -2.229 |
Occupations | -2.216 |
Mp | -2.212 |
tremend | -2.188 |
Token | € |
Token ID | 10432 |
Feature activation | +9.57e+00 |
Pos logit contributions | |
PLA | +1.818 |
ORTS | +1.686 |
Occupations | +1.684 |
Mp | +1.684 |
tremend | +1.658 |
Neg logit contributions | |
entric | -1.632 |
cester | -1.541 |
orical | -1.537 |
metic | -1.501 |
ignment | -1.495 |
Token | 50 |
Token ID | 1120 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
entric | +6.551 |
orical | +6.241 |
es | +6.100 |
cester | +6.072 |
metic | +6.038 |
Neg logit contributions | |
tremend | -6.758 |
PLA | -6.516 |
Occupations | -6.258 |
ORTS | -6.196 |
Mp | -6.074 |
Token | every |
Token ID | 790 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
entric | +1.440 |
orical | +1.359 |
cester | +1.349 |
metic | +1.327 |
ignment | +1.310 |
Neg logit contributions | |
PLA | -1.703 |
Occupations | -1.596 |
ORTS | -1.586 |
Mp | -1.570 |
tremend | -1.565 |
Token | month |
Token ID | 1227 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
entric | +1.534 |
orical | +1.432 |
cester | +1.430 |
metic | +1.395 |
ignment | +1.392 |
Neg logit contributions | |
PLA | -2.223 |
Occupations | -2.086 |
ORTS | -2.085 |
Mp | -2.072 |
tremend | -2.052 |
Token | starting |
Token ID | 3599 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
entric | +1.929 |
orical | +1.825 |
cester | +1.818 |
metic | +1.779 |
ignment | +1.764 |
Neg logit contributions | |
PLA | -2.266 |
Occupations | -2.114 |
ORTS | -2.100 |
Mp | -2.093 |
tremend | -2.082 |
Token | this |
Token ID | 428 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
PLA | +1.476 |
Occupations | +1.364 |
ORTS | +1.360 |
Mp | +1.353 |
tremend | +1.330 |
Neg logit contributions | |
entric | -1.499 |
orical | -1.414 |
cester | -1.414 |
metic | -1.388 |
ignment | -1.371 |
Token | a |
Token ID | 257 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
PLA | +0.488 |
Occupations | +0.452 |
ORTS | +0.451 |
Mp | +0.448 |
tremend | +0.443 |
Neg logit contributions | |
entric | -0.484 |
orical | -0.459 |
cester | -0.458 |
metic | -0.449 |
ignment | -0.445 |
Token | few |
Token ID | 1178 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
entric | +0.063 |
orical | +0.059 |
cester | +0.059 |
metic | +0.058 |
ignment | +0.058 |
Neg logit contributions | |
PLA | -0.069 |
Occupations | -0.064 |
ORTS | -0.064 |
Mp | -0.063 |
tremend | -0.063 |
Token | dozen |
Token ID | 8667 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
PLA | +2.390 |
Occupations | +2.209 |
Mp | +2.206 |
ORTS | +2.204 |
tremend | +2.160 |
Neg logit contributions | |
entric | -2.191 |
orical | -2.074 |
cester | -2.070 |
metic | -2.024 |
ignment | -2.000 |
Token | functions |
Token ID | 5499 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
PLA | +1.414 |
Occupations | +1.311 |
ORTS | +1.308 |
Mp | +1.304 |
tremend | +1.283 |
Neg logit contributions | |
entric | -1.301 |
orical | -1.232 |
cester | -1.230 |
metic | -1.203 |
ignment | -1.193 |
Token | like |
Token ID | 588 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
entric | +1.768 |
orical | +1.673 |
cester | +1.669 |
metic | +1.642 |
ignment | +1.634 |
Neg logit contributions | |
PLA | -2.046 |
Occupations | -1.899 |
ORTS | -1.884 |
Mp | -1.877 |
tremend | -1.876 |
Token | digital |
Token ID | 4875 |
Feature activation | +9.51e+00 |
Pos logit contributions | |
PLA | +0.931 |
Occupations | +0.861 |
ORTS | +0.856 |
Mp | +0.855 |
tremend | +0.844 |
Neg logit contributions | |
entric | -0.920 |
orical | -0.872 |
cester | -0.869 |
metic | -0.852 |
ignment | -0.844 |
Token | Write |
Token ID | 16594 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
entric | +6.341 |
cester | +6.118 |
orical | +6.028 |
ignment | +5.994 |
metic | +5.862 |
Neg logit contributions | |
PLA | -6.943 |
ORTS | -6.611 |
Occupations | -6.608 |
tremend | -6.436 |
Mp | -6.435 |
Token | () |
Token ID | 3419 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
entric | +2.070 |
orical | +1.955 |
cester | +1.943 |
metic | +1.912 |
ignment | +1.910 |
Neg logit contributions | |
PLA | -2.262 |
Occupations | -2.121 |
ORTS | -2.093 |
tremend | -2.086 |
Mp | -2.073 |
Token | is |
Token ID | 318 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
entric | +0.749 |
orical | +0.708 |
cester | +0.706 |
metic | +0.691 |
ignment | +0.686 |
Neg logit contributions | |
PLA | -0.851 |
Occupations | -0.789 |
ORTS | -0.788 |
Mp | -0.785 |
tremend | -0.776 |
Token | only |
Token ID | 691 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
entric | +1.761 |
orical | +1.672 |
cester | +1.660 |
metic | +1.643 |
ignment | +1.614 |
Neg logit contributions | |
PLA | -2.030 |
Occupations | -1.879 |
ORTS | -1.876 |
Mp | -1.862 |
tremend | -1.839 |
Token | the |
Token ID | 262 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
entric | +1.622 |
orical | +1.540 |
cester | +1.535 |
metic | +1.512 |
ignment | +1.489 |
Neg logit contributions | |
PLA | -1.917 |
ORTS | -1.779 |
Occupations | -1.769 |
Mp | -1.761 |
tremend | -1.747 |
Token | . |
Token ID | 13 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
PLA | +0.095 |
Occupations | +0.088 |
ORTS | +0.087 |
Mp | +0.087 |
tremend | +0.086 |
Neg logit contributions | |
entric | -0.093 |
orical | -0.088 |
cester | -0.088 |
metic | -0.086 |
ignment | -0.086 |
Token | The |
Token ID | 383 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
entric | +0.029 |
orical | +0.028 |
cester | +0.027 |
metic | +0.027 |
ignment | +0.027 |
Neg logit contributions | |
PLA | -0.026 |
Occupations | -0.024 |
ORTS | -0.024 |
Mp | -0.024 |
tremend | -0.023 |
Token | orbit |
Token ID | 13066 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
entric | +0.462 |
cester | +0.435 |
orical | +0.433 |
metic | +0.426 |
ignment | +0.419 |
Neg logit contributions | |
PLA | -0.619 |
Occupations | -0.580 |
ORTS | -0.577 |
Mp | -0.577 |
tremend | -0.567 |
Token | is |
Token ID | 318 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
entric | +1.573 |
orical | +1.486 |
cester | +1.478 |
ignment | +1.455 |
metic | +1.448 |
Neg logit contributions | |
PLA | -1.409 |
ORTS | -1.292 |
Occupations | -1.291 |
Mp | -1.280 |
tremend | -1.272 |
Token | an |
Token ID | 281 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
entric | +1.528 |
orical | +1.443 |
cester | +1.439 |
metic | +1.410 |
ignment | +1.402 |
Neg logit contributions | |
PLA | -1.685 |
Occupations | -1.559 |
ORTS | -1.557 |
Mp | -1.548 |
tremend | -1.534 |
Token | ell |
Token ID | 30004 |
Feature activation | +9.38e+00 |
Pos logit contributions | |
entric | +0.465 |
orical | +0.441 |
cester | +0.440 |
metic | +0.430 |
ignment | +0.422 |
Neg logit contributions | |
PLA | -0.578 |
Occupations | -0.542 |
ORTS | -0.541 |
Mp | -0.539 |
tremend | -0.532 |
Token | ip |
Token ID | 541 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
entric | +2.807 |
orical | +2.320 |
ignment | +2.317 |
cester | +2.090 |
es | +2.079 |
Neg logit contributions | |
PLA | -10.925 |
Occupations | -10.619 |
ORTS | -10.591 |
tremend | -10.552 |
Mp | -10.403 |
Token | se |
Token ID | 325 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
entric | +1.182 |
orical | +1.108 |
cester | +1.102 |
metic | +1.077 |
ignment | +1.066 |
Neg logit contributions | |
PLA | -1.807 |
Occupations | -1.691 |
ORTS | -1.690 |
Mp | -1.682 |
tremend | -1.665 |
Token | , |
Token ID | 11 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
entric | +2.853 |
orical | +2.674 |
cester | +2.663 |
metic | +2.622 |
ignment | +2.618 |
Neg logit contributions | |
PLA | -3.106 |
Occupations | -2.881 |
ORTS | -2.878 |
Mp | -2.866 |
tremend | -2.843 |
Token | but |
Token ID | 475 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
entric | +0.641 |
orical | +0.606 |
cester | +0.606 |
metic | +0.592 |
ignment | +0.586 |
Neg logit contributions | |
PLA | -0.760 |
Occupations | -0.707 |
ORTS | -0.705 |
Mp | -0.704 |
tremend | -0.693 |
Token | to |
Token ID | 284 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
entric | +1.082 |
orical | +1.021 |
cester | +1.018 |
metic | +0.998 |
ignment | +0.991 |
Neg logit contributions | |
PLA | -1.203 |
Occupations | -1.114 |
ORTS | -1.114 |
Mp | -1.108 |
tremend | -1.098 |
Token | a |
Token ID | 257 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
entric | +0.505 |
orical | +0.477 |
cester | +0.476 |
metic | +0.467 |
ignment | +0.463 |
Neg logit contributions | |
PLA | -0.561 |
Occupations | -0.520 |
ORTS | -0.519 |
Mp | -0.517 |
tremend | -0.511 |
Token | contempt |
Token ID | 18035 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
PLA | +0.146 |
ORTS | +0.136 |
Occupations | +0.136 |
Mp | +0.135 |
tremend | +0.134 |
Neg logit contributions | |
entric | -0.126 |
orical | -0.119 |
cester | -0.118 |
metic | -0.116 |
ignment | -0.115 |
Token | ible |
Token ID | 856 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
PLA | +1.065 |
ORTS | +0.991 |
Mp | +0.990 |
Occupations | +0.985 |
tremend | +0.982 |
Neg logit contributions | |
entric | -0.858 |
cester | -0.825 |
orical | -0.807 |
metic | -0.795 |
ignment | -0.794 |
Token | class |
Token ID | 1398 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
entric | +0.243 |
orical | +0.229 |
cester | +0.228 |
metic | +0.223 |
ignment | +0.220 |
Neg logit contributions | |
PLA | -0.292 |
Occupations | -0.272 |
ORTS | -0.271 |
Mp | -0.270 |
tremend | -0.267 |
Token | of |
Token ID | 286 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
entric | +0.188 |
cester | +0.180 |
orical | +0.180 |
metic | +0.176 |
ignment | +0.174 |
Neg logit contributions | |
PLA | -0.155 |
Occupations | -0.142 |
ORTS | -0.141 |
Mp | -0.140 |
tremend | -0.140 |
Token | corporate |
Token ID | 6355 |
Feature activation | +9.32e+00 |
Pos logit contributions | |
PLA | +0.461 |
Occupations | +0.429 |
ORTS | +0.427 |
Mp | +0.425 |
tremend | +0.421 |
Neg logit contributions | |
entric | -0.410 |
cester | -0.387 |
orical | -0.386 |
metic | -0.378 |
ignment | -0.374 |
Token | fascists |
Token ID | 48594 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
entric | +6.145 |
orical | +5.697 |
es | +5.660 |
cester | +5.615 |
ignment | +5.578 |
Neg logit contributions | |
PLA | -7.262 |
Mp | -6.639 |
ORTS | -6.600 |
tremend | -6.518 |
Occupations | -6.511 |
Token | , |
Token ID | 11 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
entric | +0.051 |
orical | +0.048 |
cester | +0.048 |
metic | +0.047 |
ignment | +0.047 |
Neg logit contributions | |
PLA | -0.047 |
ORTS | -0.043 |
Occupations | -0.043 |
Mp | -0.043 |
tremend | -0.042 |
Token | ego |
Token ID | 19225 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
entric | +0.152 |
orical | +0.144 |
cester | +0.144 |
metic | +0.141 |
ignment | +0.140 |
Neg logit contributions | |
PLA | -0.153 |
Occupations | -0.142 |
ORTS | -0.141 |
Mp | -0.141 |
tremend | -0.139 |
Token | maniac |
Token ID | 45575 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
entric | +0.931 |
orical | +0.867 |
cester | +0.861 |
metic | +0.842 |
ignment | +0.834 |
Neg logit contributions | |
PLA | -1.340 |
Occupations | -1.254 |
ORTS | -1.251 |
Mp | -1.245 |
tremend | -1.234 |
Token | al |
Token ID | 282 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
entric | +1.496 |
orical | +1.385 |
cester | +1.367 |
metic | +1.336 |
ignment | +1.318 |
Neg logit contributions | |
PLA | -2.704 |
Occupations | -2.542 |
ORTS | -2.537 |
Mp | -2.528 |
tremend | -2.499 |
Token | where |
Token ID | 810 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
entric | +1.734 |
orical | +1.654 |
cester | +1.643 |
metic | +1.605 |
ignment | +1.599 |
Neg logit contributions | |
PLA | -1.947 |
ORTS | -1.802 |
Mp | -1.790 |
Occupations | -1.787 |
tremend | -1.783 |
Token | tourists |
Token ID | 15930 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
entric | +2.258 |
orical | +2.151 |
cester | +2.143 |
metic | +2.102 |
ignment | +2.086 |
Neg logit contributions | |
PLA | -2.283 |
ORTS | -2.105 |
tremend | -2.093 |
Mp | -2.091 |
Occupations | -2.087 |
Token | versus |
Token ID | 9051 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
PLA | +0.587 |
Occupations | +0.542 |
ORTS | +0.541 |
Mp | +0.539 |
tremend | +0.531 |
Neg logit contributions | |
entric | -0.610 |
orical | -0.578 |
cester | -0.576 |
metic | -0.566 |
ignment | -0.562 |
Token | locals |
Token ID | 17205 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
PLA | +0.604 |
Occupations | +0.557 |
ORTS | +0.555 |
Mp | +0.553 |
tremend | +0.545 |
Neg logit contributions | |
entric | -0.645 |
orical | -0.612 |
cester | -0.611 |
metic | -0.600 |
ignment | -0.595 |
Token | take |
Token ID | 1011 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
entric | +0.258 |
orical | +0.245 |
cester | +0.245 |
metic | +0.240 |
ignment | +0.238 |
Neg logit contributions | |
PLA | -0.238 |
Occupations | -0.219 |
ORTS | -0.219 |
Mp | -0.217 |
tremend | -0.215 |
Token | geo |
Token ID | 40087 |
Feature activation | +9.22e+00 |
Pos logit contributions | |
entric | +0.234 |
orical | +0.222 |
cester | +0.221 |
metic | +0.217 |
ignment | +0.216 |
Neg logit contributions | |
PLA | -0.222 |
Occupations | -0.204 |
ORTS | -0.204 |
Mp | -0.203 |
tremend | -0.200 |
Token | - |
Token ID | 12 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
entric | +5.652 |
orical | +5.459 |
cester | +5.331 |
ignment | +5.278 |
metic | +5.194 |
Neg logit contributions | |
PLA | -7.348 |
tremend | -7.036 |
Occupations | -6.865 |
ORTS | -6.834 |
Mp | -6.829 |
Token | tag |
Token ID | 12985 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
PLA | +0.300 |
Occupations | +0.281 |
Mp | +0.280 |
ORTS | +0.280 |
tremend | +0.272 |
Neg logit contributions | |
entric | -0.178 |
cester | -0.167 |
orical | -0.165 |
ignment | -0.162 |
metic | -0.159 |
Token | ged |
Token ID | 2004 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
PLA | +0.038 |
ORTS | +0.036 |
Occupations | +0.036 |
Mp | +0.036 |
tremend | +0.035 |
Neg logit contributions | |
entric | -0.031 |
cester | -0.029 |
orical | -0.029 |
metic | -0.028 |
ignment | -0.028 |
Token | pictures |
Token ID | 5986 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
entric | +1.363 |
orical | +1.292 |
cester | +1.288 |
metic | +1.262 |
ignment | +1.254 |
Neg logit contributions | |
PLA | -1.488 |
ORTS | -1.374 |
Occupations | -1.374 |
Mp | -1.367 |
tremend | -1.359 |
Token | , |
Token ID | 11 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
entric | +0.949 |
orical | +0.904 |
cester | +0.901 |
metic | +0.882 |
ignment | +0.878 |
Neg logit contributions | |
PLA | -0.944 |
Occupations | -0.871 |
ORTS | -0.870 |
Mp | -0.865 |
tremend | -0.860 |
Token | : |
Token ID | 25 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
entric | +2.160 |
cester | +2.041 |
orical | +2.028 |
metic | +1.991 |
ignment | +1.980 |
Neg logit contributions | |
PLA | -2.349 |
Occupations | -2.190 |
ORTS | -2.187 |
Mp | -2.170 |
tremend | -2.156 |
Token | Canada |
Token ID | 3340 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
entric | +1.553 |
orical | +1.470 |
cester | +1.469 |
metic | +1.444 |
ignment | +1.433 |
Neg logit contributions | |
PLA | -1.760 |
ORTS | -1.635 |
Mp | -1.627 |
Occupations | -1.627 |
tremend | -1.620 |
Token | will |
Token ID | 481 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
entric | +1.441 |
orical | +1.363 |
cester | +1.360 |
metic | +1.333 |
ignment | +1.330 |
Neg logit contributions | |
PLA | -1.417 |
ORTS | -1.312 |
Occupations | -1.311 |
Mp | -1.304 |
tremend | -1.295 |
Token | take |
Token ID | 1011 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
entric | +0.736 |
orical | +0.694 |
cester | +0.692 |
metic | +0.680 |
ignment | +0.675 |
Neg logit contributions | |
PLA | -0.800 |
Occupations | -0.742 |
ORTS | -0.740 |
Mp | -0.736 |
tremend | -0.729 |
Token | its |
Token ID | 663 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
entric | +0.952 |
orical | +0.902 |
cester | +0.900 |
metic | +0.885 |
ignment | +0.880 |
Neg logit contributions | |
PLA | -0.994 |
Occupations | -0.917 |
ORTS | -0.916 |
Mp | -0.914 |
tremend | -0.904 |
Token | global |
Token ID | 3298 |
Feature activation | +9.11e+00 |
Pos logit contributions | |
entric | +0.028 |
cester | +0.026 |
orical | +0.026 |
metic | +0.026 |
ignment | +0.025 |
Neg logit contributions | |
PLA | -0.035 |
Occupations | -0.033 |
ORTS | -0.033 |
Mp | -0.033 |
tremend | -0.032 |
Token | responsibilities |
Token ID | 15171 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
entric | +5.558 |
ignment | +5.150 |
orical | +5.077 |
cester | +5.064 |
metic | +4.932 |
Neg logit contributions | |
PLA | -7.613 |
ORTS | -7.107 |
Mp | -7.006 |
tremend | -7.004 |
Occupations | -6.980 |
Token | seriously |
Token ID | 6411 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
entric | +3.194 |
orical | +2.974 |
cester | +2.948 |
metic | +2.903 |
ignment | +2.877 |
Neg logit contributions | |
PLA | -3.763 |
ORTS | -3.498 |
Occupations | -3.492 |
Mp | -3.451 |
tremend | -3.414 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
entric | +0.234 |
orical | +0.222 |
cester | +0.222 |
metic | +0.217 |
ignment | +0.215 |
Neg logit contributions | |
PLA | -0.241 |
ORTS | -0.222 |
Occupations | -0.221 |
Mp | -0.221 |
tremend | -0.218 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
entric | +0.741 |
orical | +0.705 |
cester | +0.703 |
metic | +0.689 |
ignment | +0.686 |
Neg logit contributions | |
PLA | -0.743 |
tremend | -0.688 |
ORTS | -0.686 |
Occupations | -0.682 |
Mp | -0.682 |
Token |
|
Token ID | 198 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
entric | +0.874 |
orical | +0.829 |
cester | +0.827 |
metic | +0.811 |
ignment | +0.806 |
Neg logit contributions | |
PLA | -0.884 |
Occupations | -0.817 |
ORTS | -0.816 |
Mp | -0.811 |
tremend | -0.810 |
Token | this |
Token ID | 428 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
PLA | +0.275 |
Occupations | +0.256 |
ORTS | +0.255 |
Mp | +0.253 |
tremend | +0.250 |
Neg logit contributions | |
entric | -0.261 |
orical | -0.246 |
cester | -0.246 |
metic | -0.241 |
ignment | -0.238 |
Token | shameless |
Token ID | 41564 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
entric | +0.618 |
orical | +0.583 |
cester | +0.581 |
metic | +0.569 |
ignment | +0.564 |
Neg logit contributions | |
PLA | -0.707 |
Occupations | -0.655 |
ORTS | -0.655 |
Mp | -0.652 |
tremend | -0.645 |
Token | r |
Token ID | 374 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
PLA | +0.177 |
ORTS | +0.163 |
Occupations | +0.163 |
Mp | +0.163 |
tremend | +0.160 |
Neg logit contributions | |
entric | -0.163 |
cester | -0.154 |
orical | -0.154 |
metic | -0.150 |
ignment | -0.147 |
Token | use |
Token ID | 1904 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
PLA | +1.778 |
ORTS | +1.619 |
Mp | +1.605 |
Occupations | +1.588 |
tremend | +1.554 |
Neg logit contributions | |
entric | -2.151 |
cester | -2.052 |
orical | -2.049 |
metic | -1.999 |
ignment | -1.977 |
Token | by |
Token ID | 416 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
PLA | +0.194 |
Occupations | +0.178 |
ORTS | +0.178 |
Mp | +0.177 |
tremend | +0.174 |
Neg logit contributions | |
entric | -0.203 |
orical | -0.193 |
cester | -0.192 |
metic | -0.189 |
ignment | -0.187 |
Token | corporate |
Token ID | 6355 |
Feature activation | +9.06e+00 |
Pos logit contributions | |
entric | +0.667 |
orical | +0.631 |
cester | +0.630 |
metic | +0.618 |
ignment | +0.612 |
Neg logit contributions | |
PLA | -0.702 |
Occupations | -0.649 |
ORTS | -0.649 |
Mp | -0.645 |
tremend | -0.638 |
Token | America |
Token ID | 2253 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
entric | +5.688 |
orical | +5.360 |
cester | +5.326 |
ignment | +5.271 |
es | +5.258 |
Neg logit contributions | |
PLA | -7.296 |
Mp | -6.722 |
ORTS | -6.719 |
tremend | -6.655 |
Occupations | -6.643 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
entric | +1.846 |
orical | +1.745 |
cester | +1.744 |
metic | +1.706 |
ignment | +1.699 |
Neg logit contributions | |
PLA | -1.872 |
Occupations | -1.725 |
ORTS | -1.725 |
Mp | -1.718 |
tremend | -1.700 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
PLA | +0.669 |
Occupations | +0.616 |
ORTS | +0.616 |
Mp | +0.611 |
tremend | +0.600 |
Neg logit contributions | |
entric | -0.805 |
cester | -0.765 |
orical | -0.765 |
metic | -0.753 |
ignment | -0.745 |
Token | Wall |
Token ID | 5007 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
PLA | +0.913 |
Occupations | +0.851 |
ORTS | +0.849 |
Mp | +0.845 |
tremend | +0.833 |
Neg logit contributions | |
entric | -0.820 |
cester | -0.770 |
orical | -0.769 |
metic | -0.756 |
ignment | -0.746 |
Token | Street |
Token ID | 3530 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
PLA | +0.089 |
tremend | +0.083 |
ORTS | +0.083 |
Occupations | +0.082 |
Mp | +0.082 |
Neg logit contributions | |
entric | -0.084 |
cester | -0.079 |
orical | -0.079 |
metic | -0.077 |
ignment | -0.077 |
Token | about |
Token ID | 546 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
entric | +0.550 |
cester | +0.515 |
orical | +0.514 |
metic | +0.498 |
ignment | +0.492 |
Neg logit contributions | |
PLA | -0.762 |
Occupations | -0.711 |
ORTS | -0.708 |
Mp | -0.705 |
tremend | -0.695 |
Token | creating |
Token ID | 4441 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
entric | +1.748 |
orical | +1.668 |
cester | +1.659 |
ignment | +1.638 |
metic | +1.637 |
Neg logit contributions | |
PLA | -1.665 |
ORTS | -1.528 |
Occupations | -1.524 |
Mp | -1.524 |
tremend | -1.507 |
Token | 21 |
Token ID | 2310 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
PLA | +0.736 |
Occupations | +0.693 |
ORTS | +0.684 |
Mp | +0.680 |
tremend | +0.672 |
Neg logit contributions | |
entric | -0.732 |
orical | -0.695 |
cester | -0.693 |
metic | -0.675 |
ignment | -0.665 |
Token | st |
Token ID | 301 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
entric | +1.630 |
orical | +1.531 |
cester | +1.525 |
metic | +1.495 |
ignment | +1.484 |
Neg logit contributions | |
PLA | -2.309 |
ORTS | -2.155 |
Occupations | -2.154 |
Mp | -2.142 |
tremend | -2.128 |
Token | century |
Token ID | 4289 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
PLA | +0.093 |
Occupations | +0.087 |
ORTS | +0.087 |
Mp | +0.087 |
tremend | +0.086 |
Neg logit contributions | |
entric | -0.045 |
orical | -0.041 |
cester | -0.041 |
metic | -0.040 |
ignment | -0.040 |
Token | global |
Token ID | 3298 |
Feature activation | +9.02e+00 |
Pos logit contributions | |
entric | +1.687 |
orical | +1.586 |
cester | +1.580 |
metic | +1.551 |
ignment | +1.541 |
Neg logit contributions | |
PLA | -2.174 |
ORTS | -2.019 |
Occupations | -2.013 |
Mp | -2.012 |
tremend | -1.997 |
Token | citizens |
Token ID | 4290 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
entric | +5.678 |
ignment | +5.344 |
orical | +5.316 |
cester | +5.242 |
metic | +5.129 |
Neg logit contributions | |
PLA | -7.342 |
tremend | -6.788 |
ORTS | -6.774 |
Mp | -6.770 |
Occupations | -6.623 |
Token | , |
Token ID | 11 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
entric | +0.611 |
orical | +0.578 |
cester | +0.577 |
metic | +0.565 |
ignment | +0.561 |
Neg logit contributions | |
PLA | -0.655 |
Occupations | -0.606 |
ORTS | -0.605 |
Mp | -0.602 |
tremend | -0.596 |
Token | and |
Token ID | 290 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
entric | +0.233 |
orical | +0.221 |
cester | +0.220 |
metic | +0.216 |
ignment | +0.215 |
Neg logit contributions | |
PLA | -0.242 |
Occupations | -0.224 |
ORTS | -0.223 |
Mp | -0.222 |
tremend | -0.220 |
Token | it |
Token ID | 340 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
PLA | +0.213 |
Occupations | +0.197 |
ORTS | +0.197 |
Mp | +0.196 |
tremend | +0.193 |
Neg logit contributions | |
entric | -0.215 |
orical | -0.204 |
cester | -0.204 |
metic | -0.200 |
ignment | -0.198 |
Token | begins |
Token ID | 6140 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
PLA | +2.226 |
Occupations | +2.021 |
ORTS | +2.014 |
Mp | +2.012 |
tremend | +1.981 |
Neg logit contributions | |
entric | -3.007 |
orical | -2.872 |
cester | -2.841 |
metic | -2.812 |
ignment | -2.772 |
Token | New |
Token ID | 968 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
PLA | +1.661 |
Occupations | +1.544 |
ORTS | +1.526 |
Mp | +1.521 |
tremend | +1.493 |
Neg logit contributions | |
entric | -1.955 |
orical | -1.840 |
cester | -1.837 |
metic | -1.805 |
ignment | -1.787 |
Token | York |
Token ID | 1971 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
PLA | +0.658 |
Occupations | +0.608 |
ORTS | +0.600 |
Mp | +0.596 |
tremend | +0.578 |
Neg logit contributions | |
entric | -1.004 |
orical | -0.960 |
cester | -0.948 |
metic | -0.944 |
ignment | -0.933 |
Token | trading |
Token ID | 7313 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
entric | +0.315 |
orical | +0.297 |
cester | +0.296 |
metic | +0.291 |
ignment | +0.288 |
Neg logit contributions | |
PLA | -0.338 |
Occupations | -0.314 |
ORTS | -0.313 |
Mp | -0.311 |
tremend | -0.308 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
entric | +1.610 |
cester | +1.524 |
orical | +1.521 |
metic | +1.486 |
ignment | +1.484 |
Neg logit contributions | |
PLA | -1.907 |
ORTS | -1.765 |
Mp | -1.758 |
Occupations | -1.752 |
tremend | -1.747 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
PLA | +0.111 |
Occupations | +0.103 |
ORTS | +0.103 |
Mp | +0.102 |
tremend | +0.099 |
Neg logit contributions | |
entric | -0.117 |
orical | -0.110 |
cester | -0.110 |
metic | -0.108 |
ignment | -0.107 |
Token | Greg |
Token ID | 25025 |
Feature activation | +9.01e+00 |
Pos logit contributions | |
PLA | +0.890 |
Mp | +0.813 |
ORTS | +0.809 |
Occupations | +0.803 |
AGES | +0.774 |
Neg logit contributions | |
entric | -0.977 |
orical | -0.923 |
cester | -0.922 |
metic | -0.901 |
ignment | -0.899 |
Token | or |
Token ID | 273 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
entric | +6.662 |
orical | +6.430 |
cester | +6.252 |
metic | +6.092 |
oret | +6.076 |
Neg logit contributions | |
PLA | -6.388 |
Occupations | -5.813 |
tremend | -5.802 |
Mp | -5.775 |
ORTS | -5.720 |
Token | Townsend |
Token ID | 46811 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
entric | +1.566 |
cester | +1.486 |
orical | +1.481 |
ignment | +1.446 |
metic | +1.445 |
Neg logit contributions | |
PLA | -1.382 |
Occupations | -1.262 |
ORTS | -1.261 |
Mp | -1.257 |
tremend | -1.244 |
Token | has |
Token ID | 468 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
entric | +1.258 |
cester | +1.193 |
orical | +1.192 |
metic | +1.168 |
ignment | +1.162 |
Neg logit contributions | |
PLA | -1.180 |
Occupations | -1.084 |
ORTS | -1.083 |
Mp | -1.077 |
tremend | -1.067 |
Token | named |
Token ID | 3706 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
entric | +3.761 |
cester | +3.552 |
orical | +3.527 |
metic | +3.502 |
ignment | +3.483 |
Neg logit contributions | |
PLA | -4.199 |
Occupations | -3.842 |
ORTS | -3.825 |
Mp | -3.817 |
tremend | -3.758 |
Token | an |
Token ID | 281 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
PLA | +0.049 |
Occupations | +0.045 |
ORTS | +0.045 |
Mp | +0.045 |
tremend | +0.044 |
Neg logit contributions | |
entric | -0.055 |
orical | -0.052 |
cester | -0.052 |
metic | -0.051 |
ignment | -0.051 |
Token | that |
Token ID | 326 |
Feature activation | -2.46e-03 |
Pos logit contributions | |
entric | +1.668 |
cester | +1.580 |
orical | +1.579 |
metic | +1.550 |
ignment | +1.542 |
Neg logit contributions | |
PLA | -1.606 |
Occupations | -1.480 |
ORTS | -1.475 |
Mp | -1.466 |
tremend | -1.452 |
Token | protected |
Token ID | 6861 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
PLA | +0.002 |
Occupations | +0.002 |
ORTS | +0.002 |
Mp | +0.002 |
tremend | +0.002 |
Neg logit contributions | |
entric | -0.002 |
orical | -0.002 |
cester | -0.002 |
metic | -0.002 |
ignment | -0.002 |
Token | consumers |
Token ID | 7008 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
PLA | +1.132 |
Mp | +1.049 |
Occupations | +1.047 |
ORTS | +1.046 |
tremend | +1.024 |
Neg logit contributions | |
entric | -1.156 |
cester | -1.088 |
orical | -1.086 |
metic | -1.066 |
ignment | -1.050 |
Token | from |
Token ID | 422 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
entric | +0.412 |
orical | +0.390 |
cester | +0.390 |
metic | +0.382 |
ignment | +0.379 |
Neg logit contributions | |
PLA | -0.382 |
Occupations | -0.352 |
ORTS | -0.351 |
Mp | -0.350 |
tremend | -0.345 |
Token | the |
Token ID | 262 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
PLA | +0.116 |
ORTS | +0.108 |
Occupations | +0.108 |
Mp | +0.107 |
tremend | +0.105 |
Neg logit contributions | |
entric | -0.106 |
cester | -0.099 |
orical | -0.099 |
metic | -0.097 |
ignment | -0.096 |
Token | corporate |
Token ID | 6355 |
Feature activation | +9.01e+00 |
Pos logit contributions | |
entric | +0.060 |
cester | +0.056 |
orical | +0.056 |
metic | +0.055 |
ignment | +0.054 |
Neg logit contributions | |
PLA | -0.063 |
ORTS | -0.059 |
Occupations | -0.059 |
Mp | -0.059 |
tremend | -0.058 |
Token | wrath |
Token ID | 26485 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
entric | +5.890 |
orical | +5.574 |
cester | +5.373 |
ignment | +5.368 |
es | +5.292 |
Neg logit contributions | |
PLA | -7.134 |
Occupations | -6.633 |
ORTS | -6.607 |
tremend | -6.519 |
Mp | -6.510 |
Token | of |
Token ID | 286 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
entric | +2.780 |
orical | +2.645 |
cester | +2.629 |
metic | +2.582 |
ignment | +2.578 |
Neg logit contributions | |
PLA | -2.294 |
Occupations | -2.118 |
ORTS | -2.095 |
Mp | -2.080 |
tremend | -2.045 |
Token | broadband |
Token ID | 18729 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
entric | +0.608 |
orical | +0.574 |
cester | +0.573 |
metic | +0.563 |
ignment | +0.556 |
Neg logit contributions | |
PLA | -0.658 |
Occupations | -0.610 |
ORTS | -0.610 |
Mp | -0.607 |
tremend | -0.599 |
Token | internet |
Token ID | 5230 |
Feature activation | +6.23e+00 |
Pos logit contributions | |
entric | +3.279 |
cester | +3.110 |
orical | +3.094 |
ignment | +3.040 |
metic | +3.006 |
Neg logit contributions | |
PLA | -3.812 |
Occupations | -3.552 |
ORTS | -3.535 |
tremend | -3.534 |
Mp | -3.477 |
Token | service |
Token ID | 2139 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
entric | +3.962 |
cester | +3.778 |
orical | +3.747 |
ignment | +3.689 |
metic | +3.643 |
Neg logit contributions | |
PLA | -5.028 |
Occupations | -4.662 |
tremend | -4.637 |
ORTS | -4.625 |
Mp | -4.568 |
Token | companies |
Token ID | 2706 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
entric | +1.307 |
orical | +1.239 |
cester | +1.234 |
metic | +1.215 |
ignment | +1.206 |
Neg logit contributions | |
PLA | -1.312 |
ORTS | -1.213 |
Occupations | -1.205 |
Mp | -1.205 |
tremend | -1.194 |
Token | such |
Token ID | 884 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
entric | +2.039 |
orical | +1.936 |
cester | +1.932 |
metic | +1.917 |
ignment | +1.896 |
Neg logit contributions | |
PLA | -1.979 |
Mp | -1.809 |
ORTS | -1.807 |
Occupations | -1.802 |
tremend | -1.786 |
Token | as |
Token ID | 355 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
PLA | +0.127 |
Occupations | +0.118 |
ORTS | +0.117 |
Mp | +0.117 |
tremend | +0.116 |
Neg logit contributions | |
entric | -0.107 |
orical | -0.101 |
cester | -0.101 |
metic | -0.098 |
ignment | -0.098 |
Token | Con |
Token ID | 1482 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
PLA | +0.300 |
ORTS | +0.276 |
Occupations | +0.276 |
Mp | +0.274 |
tremend | +0.268 |
Neg logit contributions | |
entric | -0.283 |
orical | -0.268 |
cester | -0.268 |
metic | -0.263 |
ignment | -0.262 |
Token | oco |
Token ID | 25634 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
entric | +1.551 |
orical | +1.434 |
cester | +1.429 |
metic | +1.385 |
ignment | +1.381 |
Neg logit contributions | |
PLA | -2.393 |
Occupations | -2.259 |
ORTS | -2.254 |
Mp | -2.248 |
tremend | -2.229 |
Token | Phill |
Token ID | 41970 |
Feature activation | +8.99e+00 |
Pos logit contributions | |
entric | +0.304 |
orical | +0.287 |
cester | +0.286 |
metic | +0.281 |
ignment | +0.279 |
Neg logit contributions | |
PLA | -0.315 |
Occupations | -0.291 |
ORTS | -0.291 |
Mp | -0.288 |
tremend | -0.286 |
Token | ips |
Token ID | 2419 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
entric | +1.759 |
metic | +1.599 |
orical | +1.532 |
cester | +1.468 |
es | +1.372 |
Neg logit contributions | |
tremend | -11.339 |
PLA | -11.297 |
Occupations | -10.835 |
AGES | -10.659 |
ORTS | -10.654 |
Token | and |
Token ID | 290 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
entric | +0.570 |
orical | +0.540 |
cester | +0.538 |
metic | +0.529 |
ignment | +0.524 |
Neg logit contributions | |
PLA | -0.626 |
Occupations | -0.579 |
ORTS | -0.578 |
Mp | -0.576 |
tremend | -0.570 |
Token | Marathon |
Token ID | 24828 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
PLA | +0.416 |
Occupations | +0.384 |
ORTS | +0.384 |
Mp | +0.381 |
tremend | +0.373 |
Neg logit contributions | |
entric | -0.406 |
orical | -0.384 |
cester | -0.383 |
metic | -0.377 |
ignment | -0.375 |
Token | have |
Token ID | 423 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
PLA | +2.419 |
Occupations | +2.241 |
ORTS | +2.227 |
Mp | +2.208 |
tremend | +2.159 |
Neg logit contributions | |
entric | -3.017 |
cester | -2.869 |
orical | -2.854 |
metic | -2.795 |
ignment | -2.778 |
Token | each |
Token ID | 1123 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
entric | +1.364 |
orical | +1.287 |
cester | +1.283 |
metic | +1.258 |
ignment | +1.247 |
Neg logit contributions | |
PLA | -1.609 |
Occupations | -1.493 |
ORTS | -1.490 |
Mp | -1.484 |
tremend | -1.468 |
Token | Australia |
Token ID | 4505 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
PLA | +1.426 |
ORTS | +1.324 |
Occupations | +1.323 |
Mp | +1.310 |
tremend | +1.290 |
Neg logit contributions | |
entric | -1.509 |
orical | -1.425 |
cester | -1.415 |
metic | -1.386 |
ignment | -1.369 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
entric | +1.262 |
orical | +1.205 |
cester | +1.204 |
metic | +1.184 |
ignment | +1.177 |
Neg logit contributions | |
PLA | -0.877 |
Occupations | -0.794 |
ORTS | -0.793 |
Mp | -0.790 |
tremend | -0.779 |
Token | � |
Token ID | 247 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
PLA | +0.992 |
Occupations | +0.919 |
Mp | +0.919 |
ORTS | +0.915 |
gallery | +0.878 |
Neg logit contributions | |
entric | -0.966 |
cester | -0.908 |
orical | -0.892 |
metic | -0.886 |
ignment | -0.875 |
Token | s |
Token ID | 82 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
PLA | +0.031 |
Occupations | +0.029 |
ORTS | +0.029 |
Mp | +0.028 |
tremend | +0.028 |
Neg logit contributions | |
entric | -0.028 |
orical | -0.026 |
cester | -0.026 |
metic | -0.026 |
ignment | -0.026 |
Token | worst |
Token ID | 5290 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
entric | +0.737 |
orical | +0.693 |
cester | +0.692 |
metic | +0.676 |
ignment | +0.670 |
Neg logit contributions | |
PLA | -0.924 |
Occupations | -0.861 |
ORTS | -0.860 |
Mp | -0.856 |
tremend | -0.847 |
Token | corporate |
Token ID | 6355 |
Feature activation | +8.93e+00 |
Pos logit contributions | |
PLA | +1.357 |
ORTS | +1.273 |
Occupations | +1.272 |
Mp | +1.265 |
tremend | +1.241 |
Neg logit contributions | |
entric | -0.996 |
cester | -0.931 |
orical | -0.927 |
metic | -0.899 |
ignment | -0.886 |
Token | corruption |
Token ID | 9253 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
entric | +4.996 |
orical | +4.702 |
ignment | +4.673 |
cester | +4.663 |
metic | +4.603 |
Neg logit contributions | |
PLA | -7.790 |
ORTS | -7.296 |
tremend | -7.231 |
Occupations | -7.191 |
Mp | -7.188 |
Token | scandal |
Token ID | 10731 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
entric | +2.846 |
orical | +2.653 |
cester | +2.625 |
metic | +2.604 |
ignment | +2.594 |
Neg logit contributions | |
PLA | -4.159 |
Occupations | -3.865 |
ORTS | -3.851 |
tremend | -3.850 |
Mp | -3.840 |
Token | - |
Token ID | 532 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
entric | +1.006 |
orical | +0.953 |
cester | +0.950 |
metic | +0.932 |
ignment | +0.926 |
Neg logit contributions | |
PLA | -1.033 |
Occupations | -0.955 |
ORTS | -0.953 |
Mp | -0.948 |
tremend | -0.940 |
Token | up |
Token ID | 510 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
entric | +1.243 |
orical | +1.176 |
cester | +1.174 |
metic | +1.152 |
ignment | +1.142 |
Neg logit contributions | |
PLA | -1.338 |
Occupations | -1.238 |
ORTS | -1.236 |
Mp | -1.231 |
tremend | -1.219 |
Token | to |
Token ID | 284 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
entric | +0.457 |
orical | +0.432 |
cester | +0.432 |
metic | +0.423 |
ignment | +0.421 |
Neg logit contributions | |
PLA | -0.449 |
Occupations | -0.414 |
ORTS | -0.413 |
Mp | -0.412 |
tremend | -0.406 |
Token | the |
Token ID | 262 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
entric | +0.799 |
orical | +0.760 |
cester | +0.757 |
metic | +0.744 |
ignment | +0.739 |
Neg logit contributions | |
PLA | -0.748 |
Occupations | -0.688 |
ORTS | -0.688 |
Mp | -0.685 |
tremend | -0.677 |
Token | book |
Token ID | 1492 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
PLA | +0.409 |
Occupations | +0.378 |
ORTS | +0.376 |
Mp | +0.374 |
tremend | +0.370 |
Neg logit contributions | |
entric | -0.428 |
orical | -0.405 |
cester | -0.405 |
metic | -0.397 |
ignment | -0.392 |
Token | he |
Token ID | 339 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
entric | +1.160 |
orical | +1.099 |
cester | +1.091 |
metic | +1.073 |
ignment | +1.065 |
Neg logit contributions | |
PLA | -1.322 |
Occupations | -1.228 |
ORTS | -1.227 |
Mp | -1.223 |
tremend | -1.216 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
entric | +0.849 |
orical | +0.806 |
cester | +0.804 |
metic | +0.789 |
ignment | +0.783 |
Neg logit contributions | |
PLA | -0.774 |
Occupations | -0.713 |
ORTS | -0.712 |
Mp | -0.709 |
tremend | -0.698 |
Token | that |
Token ID | 326 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
PLA | +0.865 |
Occupations | +0.802 |
ORTS | +0.800 |
Mp | +0.796 |
tremend | +0.787 |
Neg logit contributions | |
entric | -0.792 |
orical | -0.746 |
cester | -0.746 |
metic | -0.729 |
ignment | -0.725 |
Token | Georg |
Token ID | 6850 |
Feature activation | +8.88e+00 |
Pos logit contributions | |
entric | +0.382 |
orical | +0.361 |
cester | +0.360 |
metic | +0.353 |
ignment | +0.351 |
Neg logit contributions | |
PLA | -0.396 |
Occupations | -0.366 |
ORTS | -0.365 |
Mp | -0.363 |
tremend | -0.359 |
Token | es |
Token ID | 274 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
entric | +6.270 |
orical | +5.944 |
es | +5.909 |
cester | +5.784 |
ignment | +5.733 |
Neg logit contributions | |
PLA | -6.604 |
ORTS | -6.233 |
tremend | -6.108 |
Occupations | -6.021 |
Mp | -5.996 |
Token | Mé |
Token ID | 43579 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
entric | +3.426 |
orical | +3.247 |
cester | +3.236 |
metic | +3.183 |
ignment | +3.182 |
Neg logit contributions | |
PLA | -2.855 |
ORTS | -2.606 |
Occupations | -2.605 |
Mp | -2.589 |
tremend | -2.574 |
Token | li |
Token ID | 4528 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
PLA | +1.553 |
Occupations | +1.443 |
ORTS | +1.443 |
Mp | +1.440 |
tremend | +1.411 |
Neg logit contributions | |
entric | -1.029 |
cester | -0.965 |
orical | -0.963 |
metic | -0.946 |
ignment | -0.941 |
Token | è |
Token ID | 14064 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
entric | +3.238 |
orical | +3.039 |
metic | +2.986 |
ignment | +2.974 |
oret | +2.962 |
Neg logit contributions | |
PLA | -2.836 |
tremend | -2.671 |
Mp | -2.640 |
Occupations | -2.631 |
ORTS | -2.623 |
Token | s |
Token ID | 82 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
entric | +0.933 |
cester | +0.862 |
orical | +0.848 |
metic | +0.824 |
ignment | +0.811 |
Neg logit contributions | |
PLA | -1.849 |
ORTS | -1.766 |
tremend | -1.761 |
Occupations | -1.753 |
Mp | -1.745 |
Token | for |
Token ID | 329 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
entric | +0.716 |
orical | +0.675 |
cester | +0.674 |
metic | +0.659 |
ignment | +0.654 |
Neg logit contributions | |
PLA | -0.840 |
Occupations | -0.780 |
ORTS | -0.779 |
Mp | -0.776 |
tremend | -0.767 |
Token | gambling |
Token ID | 19029 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
entric | +0.547 |
orical | +0.520 |
cester | +0.519 |
metic | +0.509 |
ignment | +0.506 |
Neg logit contributions | |
PLA | -0.488 |
Occupations | -0.448 |
ORTS | -0.447 |
Mp | -0.445 |
tremend | -0.440 |
Token | on |
Token ID | 319 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
entric | +2.797 |
cester | +2.647 |
orical | +2.630 |
metic | +2.585 |
ignment | +2.577 |
Neg logit contributions | |
PLA | -3.531 |
ORTS | -3.253 |
Occupations | -3.252 |
Mp | -3.251 |
tremend | -3.245 |
Token | football |
Token ID | 4346 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
entric | +1.625 |
orical | +1.541 |
cester | +1.539 |
metic | +1.508 |
ignment | +1.503 |
Neg logit contributions | |
PLA | -1.710 |
Occupations | -1.580 |
ORTS | -1.572 |
Mp | -1.570 |
tremend | -1.556 |
Token | and |
Token ID | 290 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
entric | +2.055 |
orical | +1.934 |
cester | +1.931 |
metic | +1.894 |
ignment | +1.883 |
Neg logit contributions | |
PLA | -2.576 |
Occupations | -2.397 |
ORTS | -2.389 |
Mp | -2.381 |
tremend | -2.358 |
Token | Lex |
Token ID | 17210 |
Feature activation | +8.85e+00 |
Pos logit contributions | |
PLA | +0.203 |
Occupations | +0.187 |
ORTS | +0.187 |
Mp | +0.186 |
tremend | +0.184 |
Neg logit contributions | |
entric | -0.201 |
orical | -0.191 |
cester | -0.190 |
metic | -0.186 |
ignment | -0.184 |
Token | Smith |
Token ID | 4176 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
entric | +6.358 |
cester | +6.125 |
orical | +6.066 |
ignment | +5.978 |
es | +5.886 |
Neg logit contributions | |
PLA | -6.457 |
ORTS | -5.937 |
tremend | -5.838 |
Occupations | -5.756 |
Mp | -5.722 |
Token | taken |
Token ID | 2077 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
entric | +0.095 |
orical | +0.090 |
cester | +0.090 |
metic | +0.089 |
ignment | +0.088 |
Neg logit contributions | |
PLA | -0.093 |
Occupations | -0.086 |
ORTS | -0.086 |
Mp | -0.086 |
tremend | -0.085 |
Token | out |
Token ID | 503 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
entric | +0.340 |
cester | +0.322 |
orical | +0.322 |
metic | +0.314 |
ignment | +0.313 |
Neg logit contributions | |
PLA | -0.391 |
Occupations | -0.363 |
ORTS | -0.361 |
Mp | -0.359 |
tremend | -0.356 |
Token | of |
Token ID | 286 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
entric | +0.771 |
orical | +0.735 |
cester | +0.733 |
metic | +0.721 |
ignment | +0.717 |
Neg logit contributions | |
PLA | -0.617 |
Occupations | -0.563 |
ORTS | -0.562 |
Mp | -0.559 |
tremend | -0.551 |
Token | the |
Token ID | 262 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
PLA | +0.234 |
ORTS | +0.217 |
Occupations | +0.216 |
Mp | +0.215 |
tremend | +0.212 |
Neg logit contributions | |
entric | -0.233 |
orical | -0.220 |
cester | -0.219 |
metic | -0.215 |
ignment | -0.212 |
Token | / |
Token ID | 14 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
PLA | +0.423 |
Occupations | +0.389 |
ORTS | +0.388 |
Mp | +0.387 |
tremend | +0.383 |
Neg logit contributions | |
entric | -0.471 |
orical | -0.448 |
cester | -0.446 |
metic | -0.438 |
ignment | -0.436 |
Token | File |
Token ID | 8979 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
PLA | +1.569 |
ORTS | +1.412 |
Mp | +1.407 |
Occupations | +1.358 |
AGES | +1.321 |
Neg logit contributions | |
entric | -2.468 |
cester | -2.347 |
orical | -2.340 |
metic | -2.323 |
ignment | -2.319 |
Token | photo |
Token ID | 4590 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
PLA | +2.878 |
ORTS | +2.616 |
Occupations | +2.615 |
Mp | +2.594 |
AGES | +2.498 |
Neg logit contributions | |
entric | -3.158 |
orical | -3.021 |
cester | -2.996 |
metic | -2.929 |
ignment | -2.927 |
Token | TP |
Token ID | 24525 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
PLA | +1.116 |
Occupations | +1.026 |
ORTS | +1.025 |
Mp | +1.019 |
tremend | +1.005 |
Neg logit contributions | |
entric | -1.211 |
orical | -1.150 |
cester | -1.147 |
metic | -1.126 |
ignment | -1.117 |
Token | X |
Token ID | 55 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
PLA | +1.276 |
ORTS | +1.162 |
Mp | +1.142 |
Occupations | +1.131 |
tremend | +1.109 |
Neg logit contributions | |
entric | -1.667 |
orical | -1.588 |
cester | -1.587 |
metic | -1.558 |
ignment | -1.553 |
Token | IMAGES |
Token ID | 45325 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
entric | +0.279 |
cester | +0.270 |
orical | +0.269 |
metic | +0.267 |
ignment | +0.265 |
Neg logit contributions | |
PLA | -0.045 |
Occupations | -0.033 |
tremend | -0.032 |
Mp | -0.032 |
ORTS | -0.031 |
Token | OF |
Token ID | 3963 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
PLA | +3.830 |
ORTS | +3.334 |
Occupations | +3.010 |
Mp | +2.991 |
AGES | +2.950 |
Neg logit contributions | |
entric | -12.508 |
cester | -12.216 |
metic | -12.015 |
orical | -11.910 |
ulty | -11.885 |
Token | THE |
Token ID | 3336 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
PLA | +1.152 |
ORTS | +1.072 |
Occupations | +1.058 |
Mp | +1.045 |
AGES | +1.024 |
Neg logit contributions | |
entric | -1.141 |
orical | -1.079 |
cester | -1.076 |
metic | -1.057 |
ignment | -1.037 |
Token | DAY |
Token ID | 24644 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
PLA | +0.551 |
Occupations | +0.515 |
ORTS | +0.514 |
Mp | +0.513 |
tremend | +0.510 |
Neg logit contributions | |
entric | -0.383 |
orical | -0.359 |
cester | -0.358 |
metic | -0.350 |
ignment | -0.347 |
Token | ) |
Token ID | 8 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
PLA | +1.163 |
Occupations | +1.068 |
ORTS | +1.067 |
Mp | +1.060 |
tremend | +1.045 |
Neg logit contributions | |
entric | -1.272 |
orical | -1.209 |
cester | -1.206 |
metic | -1.184 |
ignment | -1.176 |
Token | Chris |
Token ID | 5180 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
PLA | +0.196 |
Occupations | +0.180 |
ORTS | +0.180 |
Mp | +0.179 |
tremend | +0.177 |
Neg logit contributions | |
entric | -0.218 |
orical | -0.207 |
cester | -0.206 |
metic | -0.203 |
ignment | -0.201 |
Token |
|
Token ID | 198 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
PLA | +3.035 |
ORTS | +2.780 |
Occupations | +2.768 |
Mp | +2.729 |
gallery | +2.648 |
Neg logit contributions | |
entric | -3.722 |
orical | -3.517 |
metic | -3.460 |
cester | -3.452 |
ignment | -3.389 |
Token |
|
Token ID | 198 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
PLA | +0.612 |
Mp | +0.561 |
ORTS | +0.558 |
Occupations | +0.557 |
00200000 | +0.537 |
Neg logit contributions | |
entric | -0.681 |
orical | -0.642 |
cester | -0.641 |
metic | -0.628 |
ignment | -0.621 |
Token | Power |
Token ID | 13434 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
PLA | +0.596 |
Mp | +0.537 |
Occupations | +0.536 |
ORTS | +0.536 |
tremend | +0.514 |
Neg logit contributions | |
entric | -0.682 |
orical | -0.639 |
cester | -0.636 |
ignment | -0.629 |
metic | -0.625 |
Token | Point |
Token ID | 12727 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
PLA | +0.033 |
ORTS | +0.031 |
Occupations | +0.031 |
Mp | +0.031 |
tremend | +0.030 |
Neg logit contributions | |
entric | -0.023 |
orical | -0.021 |
cester | -0.021 |
metic | -0.021 |
ignment | -0.020 |
Token | slide |
Token ID | 10649 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
PLA | +1.108 |
Occupations | +1.035 |
Mp | +1.027 |
ORTS | +1.022 |
AGES | +0.983 |
Neg logit contributions | |
entric | -1.356 |
orical | -1.259 |
cester | -1.258 |
metic | -1.233 |
ignment | -1.212 |
Token | PNG |
Token ID | 36182 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
PLA | +1.947 |
Occupations | +1.749 |
ORTS | +1.734 |
Mp | +1.721 |
tremend | +1.640 |
Neg logit contributions | |
entric | -3.741 |
orical | -3.590 |
cester | -3.555 |
metic | -3.535 |
ignment | -3.496 |
Token | larger |
Token ID | 4025 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
PLA | +5.892 |
ORTS | +5.381 |
gallery | +5.376 |
AGES | +5.330 |
Mp | +5.286 |
Neg logit contributions | |
entric | -8.955 |
orical | -8.727 |
ulty | -8.557 |
ité | -8.528 |
cester | -8.416 |
Token | image |
Token ID | 2939 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
PLA | +0.976 |
Occupations | +0.878 |
ORTS | +0.878 |
Mp | +0.873 |
AGES | +0.844 |
Neg logit contributions | |
entric | -1.553 |
orical | -1.480 |
cester | -1.469 |
metic | -1.453 |
ulty | -1.422 |
Token |
|
Token ID | 198 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
PLA | +2.522 |
Occupations | +2.333 |
ORTS | +2.333 |
Mp | +2.316 |
gallery | +2.228 |
Neg logit contributions | |
entric | -2.796 |
orical | -2.631 |
cester | -2.626 |
metic | -2.591 |
ignment | -2.549 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
PLA | +0.680 |
Mp | +0.623 |
ORTS | +0.621 |
Occupations | +0.620 |
00200000 | +0.596 |
Neg logit contributions | |
entric | -0.743 |
orical | -0.700 |
cester | -0.698 |
metic | -0.686 |
ignment | -0.677 |
Token | larg |
Token ID | 15521 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
PLA | +0.841 |
Occupations | +0.789 |
ORTS | +0.788 |
tremend | +0.787 |
Mp | +0.776 |
Neg logit contributions | |
entric | -0.749 |
cester | -0.714 |
orical | -0.712 |
metic | -0.699 |
ignment | -0.693 |
Token | reject |
Token ID | 4968 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
entric | +0.029 |
orical | +0.027 |
cester | +0.027 |
metic | +0.027 |
ignment | +0.027 |
Neg logit contributions | |
PLA | -0.027 |
Occupations | -0.025 |
ORTS | -0.025 |
Mp | -0.025 |
tremend | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
PLA | +1.764 |
Occupations | +1.645 |
ORTS | +1.635 |
Mp | +1.619 |
tremend | +1.606 |
Neg logit contributions | |
entric | -1.652 |
cester | -1.568 |
orical | -1.543 |
metic | -1.528 |
ignment | -1.501 |
Token | fantasy |
Token ID | 8842 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
entric | +0.100 |
cester | +0.093 |
orical | +0.093 |
metic | +0.091 |
ignment | +0.090 |
Neg logit contributions | |
PLA | -0.134 |
Occupations | -0.125 |
ORTS | -0.125 |
Mp | -0.124 |
tremend | -0.123 |
Token | that |
Token ID | 326 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
PLA | +0.722 |
ORTS | +0.660 |
Occupations | +0.658 |
Mp | +0.654 |
tremend | +0.650 |
Neg logit contributions | |
entric | -0.820 |
cester | -0.782 |
orical | -0.776 |
metic | -0.765 |
ignment | -0.757 |
Token | some |
Token ID | 617 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
PLA | +0.272 |
Occupations | +0.254 |
ORTS | +0.253 |
Mp | +0.251 |
tremend | +0.248 |
Neg logit contributions | |
entric | -0.244 |
orical | -0.230 |
cester | -0.230 |
metic | -0.225 |
ignment | -0.222 |
Token | spark |
Token ID | 9009 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
PLA | +1.802 |
Occupations | +1.663 |
Mp | +1.653 |
ORTS | +1.644 |
tremend | +1.626 |
Neg logit contributions | |
entric | -1.827 |
cester | -1.728 |
orical | -1.721 |
metic | -1.684 |
ignment | -1.655 |
Token | will |
Token ID | 481 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
PLA | +6.986 |
ORTS | +6.430 |
tremend | +6.413 |
Occupations | +6.315 |
Mp | +6.301 |
Neg logit contributions | |
entric | -7.605 |
cester | -7.263 |
orical | -7.103 |
ulty | -7.032 |
metic | -6.916 |
Token | ignite |
Token ID | 44794 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
entric | +0.408 |
orical | +0.389 |
cester | +0.388 |
metic | +0.381 |
ignment | +0.378 |
Neg logit contributions | |
PLA | -0.333 |
Occupations | -0.305 |
ORTS | -0.304 |
Mp | -0.303 |
tremend | -0.299 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
PLA | +2.107 |
Occupations | +1.947 |
ORTS | +1.941 |
Mp | +1.918 |
tremend | +1.911 |
Neg logit contributions | |
entric | -2.104 |
cester | -1.991 |
orical | -1.970 |
metic | -1.944 |
ignment | -1.907 |
Token | People |
Token ID | 4380 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
entric | +0.077 |
orical | +0.073 |
cester | +0.073 |
metic | +0.072 |
ignment | +0.071 |
Neg logit contributions | |
PLA | -0.082 |
Occupations | -0.076 |
ORTS | -0.076 |
Mp | -0.076 |
tremend | -0.075 |
Token | to |
Token ID | 284 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
PLA | +2.044 |
Occupations | +1.860 |
ORTS | +1.847 |
Mp | +1.838 |
tremend | +1.812 |
Neg logit contributions | |
entric | -2.608 |
cester | -2.480 |
orical | -2.479 |
metic | -2.442 |
ignment | -2.415 |
Token | way |
Token ID | 835 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
entric | +0.400 |
orical | +0.378 |
cester | +0.378 |
metic | +0.371 |
ignment | +0.368 |
Neg logit contributions | |
PLA | -0.406 |
Occupations | -0.375 |
ORTS | -0.374 |
Mp | -0.373 |
tremend | -0.368 |
Token | that |
Token ID | 326 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
entric | +0.124 |
orical | +0.117 |
cester | +0.117 |
metic | +0.115 |
ignment | +0.114 |
Neg logit contributions | |
PLA | -0.126 |
Occupations | -0.116 |
ORTS | -0.116 |
Mp | -0.116 |
tremend | -0.114 |
Token | Cape |
Token ID | 15725 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
PLA | +0.044 |
Occupations | +0.040 |
ORTS | +0.040 |
Mp | +0.040 |
tremend | +0.040 |
Neg logit contributions | |
entric | -0.044 |
orical | -0.041 |
cester | -0.041 |
metic | -0.040 |
ignment | -0.040 |
Token | lla |
Token ID | 8466 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
PLA | +3.477 |
Mp | +3.244 |
Occupations | +3.228 |
ORTS | +3.226 |
gallery | +3.134 |
Neg logit contributions | |
entric | -2.217 |
orical | -2.057 |
ignment | -1.971 |
metic | -1.967 |
cester | -1.962 |
Token | might |
Token ID | 1244 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
entric | +0.687 |
orical | +0.653 |
cester | +0.652 |
metic | +0.640 |
ignment | +0.636 |
Neg logit contributions | |
PLA | -0.617 |
Occupations | -0.567 |
ORTS | -0.567 |
Mp | -0.563 |
tremend | -0.557 |
Token | spark |
Token ID | 9009 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
PLA | +2.856 |
Occupations | +2.592 |
Mp | +2.588 |
ORTS | +2.580 |
tremend | +2.527 |
Neg logit contributions | |
entric | -3.186 |
cester | -3.072 |
orical | -3.055 |
metic | -2.979 |
ignment | -2.965 |
Token | some |
Token ID | 617 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
PLA | +6.964 |
Occupations | +6.275 |
Mp | +6.240 |
ORTS | +6.214 |
tremend | +6.068 |
Neg logit contributions | |
entric | -7.149 |
cester | -6.895 |
orical | -6.703 |
metic | -6.623 |
ignment | -6.572 |
Token | ear |
Token ID | 1027 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
PLA | +1.487 |
Occupations | +1.374 |
ORTS | +1.368 |
Mp | +1.365 |
tremend | +1.346 |
Neg logit contributions | |
entric | -1.469 |
cester | -1.391 |
orical | -1.391 |
metic | -1.362 |
ignment | -1.348 |
Token | recognition |
Token ID | 9465 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
PLA | +1.402 |
Mp | +1.298 |
Occupations | +1.291 |
ORTS | +1.290 |
tremend | +1.275 |
Neg logit contributions | |
entric | -1.196 |
cester | -1.132 |
orical | -1.125 |
metic | -1.096 |
ignment | -1.093 |
Token | , |
Token ID | 11 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
PLA | +0.841 |
Occupations | +0.778 |
ORTS | +0.775 |
Mp | +0.771 |
tremend | +0.761 |
Neg logit contributions | |
entric | -0.813 |
orical | -0.771 |
cester | -0.770 |
metic | -0.752 |
ignment | -0.741 |
Token | someone |
Token ID | 2130 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
entric | +0.224 |
orical | +0.212 |
cester | +0.211 |
metic | +0.207 |
ignment | +0.205 |
Neg logit contributions | |
PLA | -0.242 |
Occupations | -0.224 |
ORTS | -0.223 |
Mp | -0.222 |
tremend | -0.220 |
Token | early |
Token ID | 1903 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
PLA | +0.164 |
Occupations | +0.153 |
ORTS | +0.152 |
Mp | +0.151 |
tremend | +0.150 |
Neg logit contributions | |
entric | -0.149 |
orical | -0.140 |
cester | -0.140 |
metic | -0.137 |
ignment | -0.136 |
Token | - |
Token ID | 12 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
PLA | +1.943 |
Occupations | +1.808 |
ORTS | +1.800 |
Mp | +1.789 |
tremend | +1.779 |
Neg logit contributions | |
entric | -1.777 |
orical | -1.678 |
cester | -1.649 |
metic | -1.638 |
ignment | -1.609 |
Token | season |
Token ID | 6230 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
PLA | +2.017 |
Mp | +1.875 |
ORTS | +1.862 |
Occupations | +1.861 |
tremend | +1.828 |
Neg logit contributions | |
entric | -1.365 |
orical | -1.264 |
cester | -1.247 |
metic | -1.211 |
ignment | -1.202 |
Token | spike |
Token ID | 20240 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
PLA | +0.437 |
Occupations | +0.405 |
ORTS | +0.403 |
Mp | +0.403 |
tremend | +0.398 |
Neg logit contributions | |
entric | -0.423 |
orical | -0.401 |
cester | -0.399 |
metic | -0.392 |
ignment | -0.388 |
Token | and |
Token ID | 290 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
PLA | +3.123 |
Occupations | +2.883 |
ORTS | +2.881 |
tremend | +2.853 |
Mp | +2.848 |
Neg logit contributions | |
entric | -3.249 |
orical | -3.102 |
cester | -3.060 |
metic | -3.025 |
ignment | -2.982 |
Token | spark |
Token ID | 9009 |
Feature activation | -9.95e+00 |
Pos logit contributions | |
entric | +0.014 |
orical | +0.013 |
cester | +0.013 |
metic | +0.013 |
ignment | +0.013 |
Neg logit contributions | |
PLA | -0.014 |
Occupations | -0.013 |
ORTS | -0.013 |
Mp | -0.013 |
tremend | -0.013 |
Token | le |
Token ID | 293 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
PLA | +7.073 |
ORTS | +6.527 |
Occupations | +6.439 |
AGES | +6.335 |
tremend | +6.299 |
Neg logit contributions | |
entric | -7.008 |
orical | -6.676 |
cester | -6.559 |
metic | -6.460 |
ignment | -6.336 |
Token | . |
Token ID | 13 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
entric | +0.947 |
cester | +0.894 |
orical | +0.893 |
metic | +0.875 |
ignment | +0.869 |
Neg logit contributions | |
PLA | -1.052 |
Occupations | -0.976 |
ORTS | -0.974 |
Mp | -0.972 |
tremend | -0.959 |
Token |
|
Token ID | 198 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
entric | +0.063 |
orical | +0.060 |
cester | +0.059 |
metic | +0.058 |
ignment | +0.058 |
Neg logit contributions | |
PLA | -0.059 |
ORTS | -0.054 |
Occupations | -0.054 |
Mp | -0.054 |
tremend | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
entric | +0.246 |
orical | +0.233 |
cester | +0.232 |
metic | +0.228 |
ignment | +0.226 |
Neg logit contributions | |
PLA | -0.244 |
Occupations | -0.225 |
ORTS | -0.225 |
Mp | -0.224 |
tremend | -0.220 |
Token | " |
Token ID | 1 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
entric | +0.015 |
orical | +0.014 |
cester | +0.014 |
metic | +0.014 |
ignment | +0.014 |
Neg logit contributions | |
PLA | -0.015 |
Occupations | -0.013 |
ORTS | -0.013 |
Mp | -0.013 |
tremend | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
entric | +1.160 |
orical | +1.094 |
cester | +1.091 |
metic | +1.068 |
ignment | +1.060 |
Neg logit contributions | |
PLA | -1.351 |
Occupations | -1.255 |
ORTS | -1.253 |
Mp | -1.248 |
tremend | -1.234 |
Token | we |
Token ID | 356 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
entric | +0.141 |
cester | +0.133 |
orical | +0.133 |
metic | +0.130 |
ignment | +0.129 |
Neg logit contributions | |
PLA | -0.166 |
Occupations | -0.155 |
ORTS | -0.154 |
Mp | -0.154 |
tremend | -0.152 |
Token | know |
Token ID | 760 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
PLA | +0.169 |
ORTS | +0.154 |
Occupations | +0.154 |
Mp | +0.153 |
tremend | +0.151 |
Neg logit contributions | |
entric | -0.213 |
orical | -0.203 |
cester | -0.203 |
metic | -0.199 |
ignment | -0.198 |
Token | how |
Token ID | 703 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
entric | +0.188 |
orical | +0.176 |
cester | +0.176 |
metic | +0.172 |
ignment | +0.171 |
Neg logit contributions | |
PLA | -0.245 |
Occupations | -0.229 |
ORTS | -0.228 |
Mp | -0.227 |
tremend | -0.225 |
Token | to |
Token ID | 284 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
entric | +1.074 |
orical | +1.016 |
cester | +1.013 |
metic | +0.998 |
ignment | +0.987 |
Neg logit contributions | |
PLA | -1.113 |
Occupations | -1.027 |
ORTS | -1.026 |
Mp | -1.022 |
tremend | -1.009 |
Token | spark |
Token ID | 9009 |
Feature activation | -9.74e+00 |
Pos logit contributions | |
PLA | +0.240 |
ORTS | +0.221 |
Occupations | +0.221 |
Mp | +0.220 |
tremend | +0.217 |
Neg logit contributions | |
entric | -0.253 |
orical | -0.240 |
cester | -0.240 |
metic | -0.234 |
ignment | -0.233 |
Token | an |
Token ID | 281 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
PLA | +7.171 |
ORTS | +6.696 |
Occupations | +6.639 |
Mp | +6.531 |
tremend | +6.457 |
Neg logit contributions | |
entric | -6.416 |
cester | -6.137 |
metic | -5.942 |
ulty | -5.940 |
orical | -5.916 |
Token | energy |
Token ID | 2568 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
entric | +0.272 |
orical | +0.257 |
cester | +0.256 |
metic | +0.251 |
ignment | +0.248 |
Neg logit contributions | |
PLA | -0.304 |
Occupations | -0.283 |
ORTS | -0.282 |
Mp | -0.281 |
tremend | -0.277 |
Token | revolution |
Token ID | 5854 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
entric | +1.419 |
orical | +1.341 |
cester | +1.329 |
metic | +1.307 |
ignment | +1.303 |
Neg logit contributions | |
PLA | -1.706 |
Occupations | -1.588 |
ORTS | -1.581 |
Mp | -1.576 |
tremend | -1.561 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
entric | +0.313 |
orical | +0.295 |
cester | +0.295 |
metic | +0.289 |
ignment | +0.286 |
Neg logit contributions | |
PLA | -0.347 |
Occupations | -0.321 |
ORTS | -0.321 |
Mp | -0.319 |
tremend | -0.316 |
Token | but |
Token ID | 475 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
entric | +0.108 |
cester | +0.102 |
orical | +0.102 |
metic | +0.099 |
ignment | +0.098 |
Neg logit contributions | |
PLA | -0.135 |
Occupations | -0.126 |
ORTS | -0.125 |
Mp | -0.125 |
tremend | -0.124 |
Token | — |
Token ID | 851 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
entric | +1.207 |
orical | +1.134 |
cester | +1.130 |
metic | +1.100 |
ignment | +1.095 |
Neg logit contributions | |
PLA | -1.893 |
tremend | -1.769 |
Occupations | -1.763 |
ORTS | -1.757 |
Mp | -1.747 |
Token | B |
Token ID | 347 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
entric | +1.298 |
orical | +1.239 |
cester | +1.236 |
metic | +1.211 |
ignment | +1.208 |
Neg logit contributions | |
PLA | -1.053 |
Occupations | -0.958 |
Mp | -0.955 |
ORTS | -0.953 |
tremend | -0.945 |
Token | orm |
Token ID | 579 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
PLA | +2.789 |
ORTS | +2.571 |
Mp | +2.509 |
Occupations | +2.500 |
tremend | +2.467 |
Neg logit contributions | |
entric | -2.654 |
cester | -2.517 |
orical | -2.487 |
metic | -2.470 |
ignment | -2.432 |
Token | es |
Token ID | 274 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
PLA | +0.454 |
Occupations | +0.435 |
ORTS | +0.435 |
Mp | +0.433 |
tremend | +0.431 |
Neg logit contributions | |
entric | -0.047 |
orical | -0.034 |
cester | -0.033 |
metic | -0.029 |
ignment | -0.027 |
Token | les |
Token ID | 10287 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
entric | +2.008 |
orical | +1.910 |
cester | +1.900 |
metic | +1.876 |
ignment | +1.856 |
Neg logit contributions | |
PLA | -1.931 |
Occupations | -1.790 |
ORTS | -1.790 |
Mp | -1.781 |
tremend | -1.776 |
Token | Mim |
Token ID | 39312 |
Feature activation | -9.70e+00 |
Pos logit contributions | |
entric | +5.795 |
cester | +5.584 |
orical | +5.566 |
metic | +5.475 |
es | +5.468 |
Neg logit contributions | |
PLA | -4.529 |
ORTS | -4.131 |
Mp | -4.094 |
tremend | -4.094 |
Occupations | -4.072 |
Token | os |
Token ID | 418 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
PLA | +8.099 |
ORTS | +7.638 |
Occupations | +7.603 |
Mp | +7.570 |
ascal | +7.410 |
Neg logit contributions | |
entric | -5.298 |
cester | -5.060 |
orical | -4.833 |
metic | -4.817 |
ulty | -4.752 |
Token | as |
Token ID | 292 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
entric | +1.369 |
orical | +1.250 |
cester | +1.244 |
metic | +1.219 |
ignment | +1.211 |
Neg logit contributions | |
PLA | -2.661 |
Mp | -2.498 |
Occupations | -2.496 |
ORTS | -2.496 |
tremend | -2.474 |
Token | (@ |
Token ID | 4275 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
entric | +1.089 |
cester | +1.025 |
orical | +1.024 |
metic | +1.000 |
ignment | +0.999 |
Neg logit contributions | |
PLA | -1.282 |
Occupations | -1.191 |
Mp | -1.188 |
ORTS | -1.187 |
tremend | -1.178 |
Token | b |
Token ID | 65 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
entric | +2.965 |
orical | +2.862 |
cester | +2.844 |
metic | +2.806 |
ignment | +2.768 |
Neg logit contributions | |
PLA | -2.312 |
Occupations | -2.170 |
ORTS | -2.130 |
tremend | -2.124 |
Mp | -2.085 |
Token | orm |
Token ID | 579 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
PLA | +1.128 |
ORTS | +1.044 |
Occupations | +1.035 |
Mp | +1.035 |
tremend | +1.019 |
Neg logit contributions | |
entric | -1.004 |
cester | -0.945 |
orical | -0.936 |
metic | -0.924 |
ignment | -0.912 |
Token | display |
Token ID | 3359 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
entric | +2.093 |
cester | +1.948 |
orical | +1.947 |
metic | +1.904 |
ignment | +1.893 |
Neg logit contributions | |
PLA | -3.165 |
ORTS | -2.963 |
Occupations | -2.956 |
Mp | -2.937 |
tremend | -2.930 |
Token | at |
Token ID | 379 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
PLA | +0.720 |
Occupations | +0.666 |
ORTS | +0.662 |
Mp | +0.661 |
tremend | +0.653 |
Neg logit contributions | |
entric | -0.667 |
cester | -0.635 |
orical | -0.633 |
metic | -0.616 |
ignment | -0.611 |
Token | the |
Token ID | 262 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
entric | +1.819 |
orical | +1.730 |
cester | +1.716 |
metic | +1.690 |
ignment | +1.683 |
Neg logit contributions | |
PLA | -1.761 |
Occupations | -1.614 |
Mp | -1.613 |
ORTS | -1.609 |
tremend | -1.597 |
Token | Center |
Token ID | 3337 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
PLA | +0.310 |
Occupations | +0.284 |
ORTS | +0.283 |
Mp | +0.282 |
tremend | +0.278 |
Neg logit contributions | |
entric | -0.372 |
orical | -0.354 |
cester | -0.353 |
metic | -0.347 |
ignment | -0.344 |
Token | for |
Token ID | 329 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
PLA | +0.276 |
Occupations | +0.254 |
ORTS | +0.254 |
Mp | +0.253 |
tremend | +0.250 |
Neg logit contributions | |
entric | -0.269 |
orical | -0.255 |
cester | -0.254 |
metic | -0.249 |
ignment | -0.247 |
Token | Pupp |
Token ID | 20926 |
Feature activation | -9.52e+00 |
Pos logit contributions | |
PLA | +0.270 |
Occupations | +0.247 |
ORTS | +0.246 |
Mp | +0.244 |
tremend | +0.241 |
Neg logit contributions | |
entric | -0.342 |
orical | -0.326 |
cester | -0.326 |
metic | -0.320 |
ignment | -0.318 |
Token | etry |
Token ID | 11973 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
PLA | +5.134 |
ORTS | +4.806 |
Mp | +4.729 |
icip | +4.544 |
Occupations | +4.535 |
Neg logit contributions | |
entric | -7.884 |
cester | -7.769 |
orical | -7.492 |
metic | -7.433 |
ignment | -7.425 |
Token | Arts |
Token ID | 11536 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
PLA | +2.682 |
Occupations | +2.498 |
ORTS | +2.497 |
Mp | +2.448 |
tremend | +2.419 |
Neg logit contributions | |
entric | -2.608 |
cester | -2.486 |
orical | -2.483 |
metic | -2.418 |
ignment | -2.399 |
Token | in |
Token ID | 287 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
PLA | +1.673 |
ORTS | +1.551 |
Occupations | +1.549 |
Mp | +1.531 |
tremend | +1.512 |
Neg logit contributions | |
entric | -1.565 |
orical | -1.476 |
cester | -1.476 |
metic | -1.436 |
ignment | -1.425 |
Token | Atlanta |
Token ID | 9371 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
PLA | +1.939 |
Occupations | +1.792 |
ORTS | +1.779 |
Mp | +1.746 |
tremend | +1.714 |
Neg logit contributions | |
entric | -2.554 |
orical | -2.422 |
cester | -2.407 |
metic | -2.374 |
ignment | -2.339 |
Token | , |
Token ID | 11 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
entric | +0.885 |
orical | +0.836 |
cester | +0.835 |
metic | +0.818 |
ignment | +0.813 |
Neg logit contributions | |
PLA | -0.952 |
Occupations | -0.879 |
ORTS | -0.879 |
Mp | -0.876 |
tremend | -0.867 |
Token | echoes |
Token ID | 30346 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
entric | +2.632 |
orical | +2.514 |
cester | +2.492 |
metic | +2.459 |
ignment | +2.439 |
Neg logit contributions | |
PLA | -2.677 |
ORTS | -2.491 |
Occupations | -2.464 |
tremend | -2.441 |
Mp | -2.440 |
Token | of |
Token ID | 286 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
PLA | +1.349 |
Occupations | +1.238 |
Mp | +1.235 |
ORTS | +1.232 |
tremend | +1.220 |
Neg logit contributions | |
entric | -1.499 |
cester | -1.414 |
orical | -1.408 |
ignment | -1.376 |
metic | -1.376 |
Token | M |
Token ID | 337 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
PLA | +0.285 |
Occupations | +0.264 |
ORTS | +0.262 |
Mp | +0.262 |
tremend | +0.259 |
Neg logit contributions | |
entric | -0.288 |
cester | -0.272 |
orical | -0.272 |
metic | -0.266 |
ignment | -0.265 |
Token | . |
Token ID | 13 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
PLA | +3.045 |
Mp | +2.804 |
ORTS | +2.803 |
Occupations | +2.777 |
tremend | +2.724 |
Neg logit contributions | |
entric | -2.841 |
cester | -2.705 |
orical | -2.661 |
metic | -2.638 |
ignment | -2.599 |
Token | Night |
Token ID | 5265 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
PLA | +0.576 |
Occupations | +0.530 |
ORTS | +0.528 |
Mp | +0.526 |
tremend | +0.518 |
Neg logit contributions | |
entric | -0.674 |
cester | -0.640 |
orical | -0.639 |
metic | -0.627 |
ignment | -0.623 |
Token | Shy |
Token ID | 36838 |
Feature activation | -9.47e+00 |
Pos logit contributions | |
PLA | +1.270 |
Occupations | +1.154 |
ORTS | +1.148 |
Mp | +1.145 |
tremend | +1.125 |
Neg logit contributions | |
entric | -1.813 |
orical | -1.730 |
cester | -1.726 |
metic | -1.702 |
ignment | -1.689 |
Token | am |
Token ID | 321 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
PLA | +5.984 |
Occupations | +5.573 |
ORTS | +5.490 |
Runner | +5.407 |
Mp | +5.405 |
Neg logit contributions | |
entric | -7.365 |
metic | -7.148 |
ignment | -6.850 |
cester | -6.759 |
orical | -6.748 |
Token | alan |
Token ID | 25786 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
entric | +0.694 |
orical | +0.667 |
cester | +0.661 |
metic | +0.649 |
ignment | +0.642 |
Neg logit contributions | |
PLA | -0.602 |
Occupations | -0.553 |
ORTS | -0.552 |
tremend | -0.551 |
Mp | -0.547 |
Token | � |
Token ID | 447 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
entric | +2.122 |
orical | +2.037 |
cester | +2.013 |
metic | +1.988 |
ignment | +1.970 |
Neg logit contributions | |
PLA | -1.860 |
ORTS | -1.718 |
Occupations | -1.701 |
Mp | -1.701 |
tremend | -1.676 |
Token | � |
Token ID | 247 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
PLA | +0.504 |
Occupations | +0.443 |
ORTS | +0.441 |
Mp | +0.436 |
00200000 | +0.407 |
Neg logit contributions | |
entric | -1.164 |
cester | -1.112 |
orical | -1.106 |
metic | -1.098 |
ignment | -1.089 |
Token | s |
Token ID | 82 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
entric | +0.117 |
cester | +0.108 |
orical | +0.108 |
metic | +0.105 |
ignment | +0.105 |
Neg logit contributions | |
PLA | -0.194 |
Occupations | -0.182 |
ORTS | -0.182 |
Mp | -0.182 |
tremend | -0.179 |
Token | riz |
Token ID | 47847 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
PLA | +2.695 |
Occupations | +2.513 |
Mp | +2.507 |
ORTS | +2.473 |
ascal | +2.453 |
Neg logit contributions | |
entric | -2.653 |
orical | -2.521 |
cester | -2.511 |
metic | -2.470 |
ignment | -2.423 |
Token | , |
Token ID | 11 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
entric | +0.368 |
orical | +0.346 |
cester | +0.345 |
metic | +0.338 |
ignment | +0.335 |
Neg logit contributions | |
PLA | -0.461 |
Occupations | -0.430 |
ORTS | -0.429 |
Mp | -0.427 |
tremend | -0.422 |
Token | Yaz |
Token ID | 35856 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
PLA | +0.723 |
Occupations | +0.675 |
Mp | +0.665 |
ORTS | +0.665 |
tremend | +0.646 |
Neg logit contributions | |
entric | -0.843 |
orical | -0.804 |
cester | -0.802 |
metic | -0.788 |
ignment | -0.778 |
Token | d |
Token ID | 67 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
PLA | +0.472 |
Occupations | +0.439 |
Mp | +0.438 |
ORTS | +0.436 |
tremend | +0.426 |
Neg logit contributions | |
entric | -0.380 |
cester | -0.356 |
orical | -0.355 |
metic | -0.347 |
ignment | -0.345 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
entric | +0.351 |
cester | +0.331 |
orical | +0.331 |
metic | +0.324 |
ignment | +0.320 |
Neg logit contributions | |
PLA | -0.417 |
Occupations | -0.388 |
ORTS | -0.387 |
Mp | -0.385 |
tremend | -0.381 |
Token | Shir |
Token ID | 21972 |
Feature activation | -9.44e+00 |
Pos logit contributions | |
PLA | +0.878 |
Occupations | +0.811 |
ORTS | +0.801 |
Mp | +0.800 |
tremend | +0.779 |
Neg logit contributions | |
entric | -1.172 |
orical | -1.119 |
cester | -1.115 |
metic | -1.099 |
ignment | -1.085 |
Token | az |
Token ID | 1031 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
PLA | +3.148 |
Occupations | +3.005 |
Mp | +2.887 |
ascal | +2.837 |
abee | +2.834 |
Neg logit contributions | |
entric | -9.604 |
orical | -9.446 |
ulty | -9.327 |
metic | -9.078 |
cester | -8.965 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
entric | +0.263 |
orical | +0.249 |
cester | +0.248 |
metic | +0.243 |
ignment | +0.241 |
Neg logit contributions | |
PLA | -0.281 |
Occupations | -0.260 |
ORTS | -0.260 |
Mp | -0.258 |
tremend | -0.256 |
Token | where |
Token ID | 810 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
PLA | +1.028 |
Occupations | +0.969 |
Mp | +0.953 |
ORTS | +0.950 |
tremend | +0.930 |
Neg logit contributions | |
entric | -1.004 |
orical | -0.950 |
cester | -0.944 |
metic | -0.926 |
ignment | -0.916 |
Token | protesters |
Token ID | 9584 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
entric | +0.926 |
orical | +0.882 |
cester | +0.880 |
metic | +0.865 |
ignment | +0.860 |
Neg logit contributions | |
PLA | -0.789 |
ORTS | -0.722 |
Occupations | -0.722 |
Mp | -0.719 |
tremend | -0.711 |
Token | skirm |
Token ID | 37238 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
PLA | +3.679 |
Occupations | +3.509 |
Mp | +3.428 |
ORTS | +3.376 |
tremend | +3.264 |
Neg logit contributions | |
entric | -4.655 |
cester | -4.462 |
orical | -4.451 |
metic | -4.303 |
ignment | -4.286 |
Token | Ken |
Token ID | 7148 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
PLA | +0.780 |
Occupations | +0.716 |
ORTS | +0.714 |
Mp | +0.713 |
tremend | +0.699 |
Neg logit contributions | |
entric | -0.870 |
orical | -0.829 |
cester | -0.824 |
metic | -0.810 |
ignment | -0.804 |
Token | y |
Token ID | 88 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
entric | +1.774 |
orical | +1.702 |
cester | +1.696 |
metic | +1.666 |
ignment | +1.655 |
Neg logit contributions | |
PLA | -1.414 |
tremend | -1.338 |
Occupations | -1.307 |
ORTS | -1.303 |
Mp | -1.280 |
Token | atta |
Token ID | 25014 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
entric | +0.468 |
orical | +0.406 |
cester | +0.402 |
metic | +0.375 |
ignment | +0.368 |
Neg logit contributions | |
PLA | -2.163 |
tremend | -2.075 |
Occupations | -2.071 |
ORTS | -2.063 |
Mp | -2.049 |
Token | travelled |
Token ID | 21650 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
PLA | +0.330 |
Occupations | +0.305 |
ORTS | +0.305 |
Mp | +0.303 |
tremend | +0.299 |
Neg logit contributions | |
entric | -0.338 |
orical | -0.321 |
cester | -0.320 |
metic | -0.314 |
ignment | -0.312 |
Token | to |
Token ID | 284 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
entric | +0.673 |
orical | +0.639 |
cester | +0.638 |
metic | +0.626 |
ignment | +0.621 |
Neg logit contributions | |
PLA | -0.704 |
Occupations | -0.652 |
ORTS | -0.648 |
Mp | -0.644 |
tremend | -0.639 |
Token | Mog |
Token ID | 30926 |
Feature activation | -9.31e+00 |
Pos logit contributions | |
PLA | +0.189 |
Occupations | +0.172 |
ORTS | +0.172 |
Mp | +0.171 |
tremend | +0.169 |
Neg logit contributions | |
entric | -0.243 |
orical | -0.232 |
cester | -0.232 |
metic | -0.227 |
ignment | -0.226 |
Token | adish |
Token ID | 48563 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
PLA | +1.587 |
ascal | +1.175 |
Mp | +1.173 |
arest | +1.101 |
gallery | +1.060 |
Neg logit contributions | |
entric | -11.032 |
orical | -10.903 |
cester | -10.763 |
metic | -10.763 |
ignment | -10.643 |
Token | u |
Token ID | 84 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
PLA | +3.017 |
Mp | +2.837 |
ORTS | +2.834 |
Occupations | +2.790 |
gallery | +2.693 |
Neg logit contributions | |
entric | -2.684 |
orical | -2.547 |
cester | -2.467 |
metic | -2.457 |
ignment | -2.441 |
Token | to |
Token ID | 284 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
PLA | +1.648 |
Occupations | +1.529 |
ORTS | +1.524 |
Mp | +1.523 |
tremend | +1.496 |
Neg logit contributions | |
entric | -1.546 |
orical | -1.464 |
cester | -1.455 |
metic | -1.429 |
ignment | -1.420 |
Token | discuss |
Token ID | 2112 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
PLA | +0.350 |
Occupations | +0.323 |
ORTS | +0.321 |
Mp | +0.319 |
tremend | +0.316 |
Neg logit contributions | |
entric | -0.391 |
orical | -0.372 |
cester | -0.372 |
metic | -0.364 |
ignment | -0.362 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
PLA | +0.019 |
Occupations | +0.017 |
ORTS | +0.017 |
Mp | +0.017 |
tremend | +0.017 |
Neg logit contributions | |
entric | -0.018 |
orical | -0.017 |
cester | -0.017 |
metic | -0.017 |
ignment | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
PLA | +0.381 |
ORTS | +0.353 |
Occupations | +0.352 |
Mp | +0.351 |
tremend | +0.345 |
Neg logit contributions | |
entric | -0.360 |
orical | -0.340 |
cester | -0.339 |
metic | -0.333 |
ignment | -0.330 |
Token | M |
Token ID | 44 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
PLA | +0.553 |
ORTS | +0.508 |
Occupations | +0.507 |
Mp | +0.504 |
tremend | +0.487 |
Neg logit contributions | |
entric | -0.656 |
cester | -0.622 |
orical | -0.622 |
metic | -0.611 |
ignment | -0.609 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
PLA | +3.167 |
ORTS | +2.967 |
Occupations | +2.934 |
Mp | +2.918 |
tremend | +2.856 |
Neg logit contributions | |
entric | -3.094 |
cester | -2.917 |
orical | -2.907 |
metic | -2.901 |
ignment | -2.864 |
Token | S |
Token ID | 50 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
PLA | +0.996 |
Occupations | +0.912 |
ORTS | +0.912 |
Mp | +0.905 |
tremend | +0.887 |
Neg logit contributions | |
entric | -1.258 |
orical | -1.194 |
cester | -1.192 |
metic | -1.175 |
ignment | -1.168 |
Token | . |
Token ID | 13 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
PLA | +1.918 |
ORTS | +1.797 |
Occupations | +1.790 |
Mp | +1.772 |
tremend | +1.737 |
Neg logit contributions | |
entric | -1.716 |
orical | -1.616 |
cester | -1.610 |
metic | -1.585 |
ignment | -1.577 |
Token | Surprise |
Token ID | 47893 |
Feature activation | -9.30e+00 |
Pos logit contributions | |
PLA | +1.134 |
Occupations | +1.041 |
ORTS | +1.039 |
Mp | +1.031 |
tremend | +1.007 |
Neg logit contributions | |
entric | -1.366 |
orical | -1.296 |
cester | -1.292 |
metic | -1.277 |
ignment | -1.266 |
Token | " |
Token ID | 1 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
PLA | +6.863 |
Occupations | +6.564 |
Runner | +6.370 |
Mp | +6.353 |
ORTS | +6.346 |
Neg logit contributions | |
entric | -6.393 |
orical | -5.912 |
metic | -5.772 |
cester | -5.761 |
ulty | -5.575 |
Token | ( |
Token ID | 357 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
PLA | +0.904 |
ORTS | +0.839 |
Occupations | +0.836 |
Mp | +0.835 |
tremend | +0.826 |
Neg logit contributions | |
entric | -0.866 |
orical | -0.818 |
cester | -0.815 |
metic | -0.801 |
ignment | -0.795 |
Token | 1973 |
Token ID | 40220 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
entric | +0.125 |
orical | +0.119 |
cester | +0.119 |
metic | +0.117 |
ignment | +0.117 |
Neg logit contributions | |
PLA | -0.068 |
ORTS | -0.061 |
Occupations | -0.060 |
Mp | -0.060 |
tremend | -0.058 |
Token | ). |
Token ID | 737 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
PLA | +0.413 |
ORTS | +0.380 |
Occupations | +0.379 |
Mp | +0.378 |
tremend | +0.372 |
Neg logit contributions | |
entric | -0.425 |
orical | -0.402 |
cester | -0.401 |
metic | -0.394 |
ignment | -0.391 |
Token | The |
Token ID | 383 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
PLA | +0.080 |
tremend | +0.074 |
ORTS | +0.074 |
Occupations | +0.074 |
Mp | +0.073 |
Neg logit contributions | |
entric | -0.086 |
orical | -0.081 |
cester | -0.081 |
metic | -0.080 |
ignment | -0.079 |
Token | planner |
Token ID | 42351 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
PLA | +2.938 |
Occupations | +2.692 |
ORTS | +2.679 |
Mp | +2.656 |
Runner | +2.564 |
Neg logit contributions | |
entric | -3.760 |
orical | -3.606 |
cester | -3.606 |
metic | -3.470 |
ignment | -3.438 |
Token | at |
Token ID | 379 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
PLA | +2.290 |
ORTS | +2.129 |
Occupations | +2.126 |
Mp | +2.110 |
tremend | +2.048 |
Neg logit contributions | |
entric | -2.255 |
orical | -2.153 |
cester | -2.128 |
metic | -2.086 |
ignment | -2.063 |
Token | NASA |
Token ID | 8884 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
entric | +1.134 |
orical | +1.071 |
cester | +1.069 |
ignment | +1.046 |
metic | +1.046 |
Neg logit contributions | |
PLA | -1.148 |
ORTS | -1.057 |
Mp | -1.056 |
Occupations | -1.054 |
tremend | -1.052 |
Token | 's |
Token ID | 338 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
PLA | +2.590 |
Occupations | +2.350 |
ORTS | +2.306 |
Mp | +2.253 |
gallery | +2.143 |
Neg logit contributions | |
entric | -4.787 |
orical | -4.652 |
cester | -4.623 |
metic | -4.599 |
ignment | -4.511 |
Token | Jet |
Token ID | 19013 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
PLA | +0.327 |
Occupations | +0.294 |
ORTS | +0.293 |
Mp | +0.291 |
tremend | +0.286 |
Neg logit contributions | |
entric | -0.538 |
orical | -0.515 |
cester | -0.514 |
metic | -0.507 |
ignment | -0.503 |
Token | Prop |
Token ID | 8772 |
Feature activation | -9.28e+00 |
Pos logit contributions | |
PLA | +1.553 |
Occupations | +1.348 |
ORTS | +1.312 |
Mp | +1.289 |
tremend | +1.242 |
Neg logit contributions | |
entric | -4.236 |
orical | -4.089 |
cester | -4.086 |
metic | -4.035 |
ignment | -3.997 |
Token | ulsion |
Token ID | 15204 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
PLA | +3.650 |
ORTS | +3.500 |
Occupations | +3.265 |
Runner | +3.175 |
gallery | +3.069 |
Neg logit contributions | |
entric | -9.126 |
cester | -8.970 |
metic | -8.895 |
orical | -8.826 |
ulty | -8.689 |
Token | Laboratory |
Token ID | 18643 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
PLA | +0.583 |
ORTS | +0.421 |
Occupations | +0.416 |
Mp | +0.400 |
tremend | +0.372 |
Neg logit contributions | |
entric | -3.675 |
orical | -3.568 |
cester | -3.563 |
metic | -3.524 |
ignment | -3.509 |
Token | in |
Token ID | 287 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
PLA | +1.459 |
ORTS | +1.354 |
Occupations | +1.353 |
Mp | +1.338 |
tremend | +1.318 |
Neg logit contributions | |
entric | -1.351 |
orical | -1.280 |
cester | -1.272 |
metic | -1.250 |
ignment | -1.236 |
Token | Pasadena |
Token ID | 41010 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
PLA | +1.722 |
ORTS | +1.550 |
Occupations | +1.541 |
Mp | +1.519 |
tremend | +1.475 |
Neg logit contributions | |
entric | -3.105 |
orical | -2.977 |
cester | -2.968 |
metic | -2.935 |
ignment | -2.899 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
PLA | +3.411 |
ORTS | +3.145 |
Occupations | +3.135 |
Mp | +3.097 |
tremend | +3.030 |
Neg logit contributions | |
entric | -3.544 |
orical | -3.387 |
cester | -3.383 |
metic | -3.300 |
ignment | -3.237 |
Token | loves |
Token ID | 10408 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
PLA | +1.152 |
Occupations | +1.060 |
ORTS | +1.058 |
Mp | +1.051 |
tremend | +1.037 |
Neg logit contributions | |
entric | -1.271 |
orical | -1.209 |
cester | -1.205 |
metic | -1.181 |
ignment | -1.172 |
Token | to |
Token ID | 284 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
PLA | +0.499 |
Occupations | +0.462 |
ORTS | +0.461 |
Mp | +0.458 |
tremend | +0.453 |
Neg logit contributions | |
entric | -0.498 |
orical | -0.471 |
cester | -0.471 |
metic | -0.461 |
ignment | -0.457 |
Token | see |
Token ID | 766 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
entric | +0.288 |
orical | +0.273 |
cester | +0.273 |
metic | +0.268 |
ignment | +0.266 |
Neg logit contributions | |
PLA | -0.275 |
Occupations | -0.254 |
ORTS | -0.253 |
Mp | -0.252 |
tremend | -0.249 |
Token | their |
Token ID | 511 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
PLA | +0.238 |
Occupations | +0.220 |
ORTS | +0.219 |
Mp | +0.218 |
tremend | +0.216 |
Neg logit contributions | |
entric | -0.245 |
orical | -0.232 |
cester | -0.232 |
metic | -0.227 |
ignment | -0.225 |
Token | kids |
Token ID | 3988 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
PLA | +0.080 |
Occupations | +0.074 |
ORTS | +0.074 |
Mp | +0.074 |
tremend | +0.073 |
Neg logit contributions | |
entric | -0.075 |
orical | -0.071 |
cester | -0.071 |
metic | -0.069 |
ignment | -0.069 |
Token | spark |
Token ID | 9009 |
Feature activation | -9.26e+00 |
Pos logit contributions | |
PLA | +0.830 |
Occupations | +0.771 |
ORTS | +0.768 |
Mp | +0.763 |
tremend | +0.757 |
Neg logit contributions | |
entric | -0.755 |
orical | -0.715 |
cester | -0.713 |
metic | -0.695 |
ignment | -0.690 |
Token | le |
Token ID | 293 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
PLA | +6.049 |
ORTS | +5.633 |
Occupations | +5.535 |
tremend | +5.437 |
Mp | +5.333 |
Neg logit contributions | |
entric | -6.973 |
cester | -6.768 |
orical | -6.748 |
metic | -6.640 |
ulty | -6.633 |
Token | with |
Token ID | 351 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
entric | +1.208 |
orical | +1.137 |
cester | +1.132 |
metic | +1.110 |
ignment | +1.100 |
Neg logit contributions | |
PLA | -1.472 |
Occupations | -1.366 |
ORTS | -1.364 |
Mp | -1.361 |
tremend | -1.341 |
Token | delight |
Token ID | 10974 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
entric | +0.930 |
orical | +0.880 |
cester | +0.875 |
metic | +0.860 |
ignment | +0.856 |
Neg logit contributions | |
PLA | -0.973 |
Occupations | -0.897 |
ORTS | -0.897 |
Mp | -0.895 |
tremend | -0.882 |
Token | at |
Token ID | 379 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
PLA | +0.145 |
Occupations | +0.134 |
ORTS | +0.134 |
Mp | +0.133 |
tremend | +0.132 |
Neg logit contributions | |
entric | -0.127 |
orical | -0.120 |
cester | -0.120 |
metic | -0.117 |
ignment | -0.116 |
Token | the |
Token ID | 262 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
entric | +1.968 |
orical | +1.875 |
cester | +1.851 |
metic | +1.829 |
ignment | +1.827 |
Neg logit contributions | |
PLA | -2.049 |
Mp | -1.892 |
ORTS | -1.880 |
Occupations | -1.880 |
tremend | -1.866 |
Token | out |
Token ID | 503 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
PLA | +2.849 |
Mp | +2.679 |
Occupations | +2.619 |
ORTS | +2.607 |
tremend | +2.537 |
Neg logit contributions | |
entric | -3.400 |
orical | -3.215 |
cester | -3.209 |
metic | -3.112 |
ignment | -3.109 |
Token | of |
Token ID | 286 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
PLA | +0.266 |
Occupations | +0.244 |
ORTS | +0.244 |
Mp | +0.242 |
tremend | +0.240 |
Neg logit contributions | |
entric | -0.301 |
orical | -0.287 |
cester | -0.286 |
metic | -0.281 |
ignment | -0.279 |
Token | the |
Token ID | 262 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
PLA | +0.642 |
Occupations | +0.591 |
ORTS | +0.590 |
Mp | +0.588 |
tremend | +0.581 |
Neg logit contributions | |
entric | -0.669 |
orical | -0.635 |
cester | -0.633 |
metic | -0.622 |
ignment | -0.617 |
Token | capital |
Token ID | 3139 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
PLA | +0.681 |
Occupations | +0.636 |
Mp | +0.633 |
ORTS | +0.633 |
tremend | +0.622 |
Neg logit contributions | |
entric | -0.602 |
orical | -0.569 |
cester | -0.567 |
metic | -0.555 |
ignment | -0.548 |
Token | , |
Token ID | 11 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
entric | +0.836 |
orical | +0.801 |
cester | +0.800 |
metic | +0.787 |
ignment | +0.785 |
Neg logit contributions | |
PLA | -0.489 |
ORTS | -0.433 |
Occupations | -0.432 |
tremend | -0.426 |
Mp | -0.426 |
Token | Mog |
Token ID | 30926 |
Feature activation | -9.24e+00 |
Pos logit contributions | |
PLA | +0.189 |
Occupations | +0.167 |
ORTS | +0.167 |
Mp | +0.166 |
tremend | +0.162 |
Neg logit contributions | |
entric | -0.395 |
orical | -0.379 |
cester | -0.378 |
metic | -0.374 |
ignment | -0.371 |
Token | adish |
Token ID | 48563 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
PLA | +0.886 |
ascal | +0.687 |
arest | +0.610 |
gallery | +0.599 |
Mp | +0.454 |
Neg logit contributions | |
entric | -11.503 |
metic | -11.356 |
cester | -11.267 |
orical | -11.254 |
•••• | -11.171 |
Token | u |
Token ID | 84 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
PLA | +3.103 |
ORTS | +2.917 |
Mp | +2.914 |
Occupations | +2.852 |
gallery | +2.771 |
Neg logit contributions | |
entric | -2.841 |
orical | -2.714 |
cester | -2.619 |
metic | -2.606 |
ignment | -2.583 |
Token | . |
Token ID | 13 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
PLA | +1.932 |
Occupations | +1.783 |
ORTS | +1.782 |
Mp | +1.780 |
tremend | +1.752 |
Neg logit contributions | |
entric | -1.925 |
orical | -1.836 |
cester | -1.830 |
metic | -1.800 |
ignment | -1.784 |
Token |
|
Token ID | 198 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
PLA | +0.590 |
Occupations | +0.546 |
ORTS | +0.544 |
Mp | +0.541 |
tremend | +0.530 |
Neg logit contributions | |
entric | -0.609 |
orical | -0.578 |
cester | -0.576 |
metic | -0.566 |
ignment | -0.561 |
Token |
|
Token ID | 198 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
PLA | +0.246 |
Occupations | +0.226 |
ORTS | +0.226 |
Mp | +0.225 |
tremend | +0.219 |
Neg logit contributions | |
entric | -0.251 |
orical | -0.238 |
cester | -0.237 |
metic | -0.233 |
ignment | -0.231 |
Token | the |
Token ID | 262 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
PLA | +1.301 |
Occupations | +1.201 |
ORTS | +1.197 |
Mp | +1.195 |
tremend | +1.171 |
Neg logit contributions | |
entric | -1.380 |
cester | -1.306 |
orical | -1.304 |
metic | -1.280 |
ignment | -1.265 |
Token | Western |
Token ID | 4885 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
PLA | +0.729 |
Occupations | +0.663 |
ORTS | +0.662 |
Mp | +0.658 |
tremend | +0.649 |
Neg logit contributions | |
entric | -0.975 |
orical | -0.931 |
cester | -0.929 |
metic | -0.913 |
ignment | -0.907 |
Token | - |
Token ID | 12 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
entric | +1.503 |
orical | +1.420 |
cester | +1.413 |
metic | +1.399 |
ignment | +1.398 |
Neg logit contributions | |
PLA | -1.368 |
ORTS | -1.275 |
tremend | -1.259 |
Occupations | -1.251 |
Mp | -1.244 |
Token | backed |
Token ID | 17078 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
PLA | +1.930 |
Mp | +1.751 |
Occupations | +1.706 |
ORTS | +1.685 |
tremend | +1.631 |
Neg logit contributions | |
entric | -2.917 |
cester | -2.820 |
orical | -2.805 |
ignment | -2.726 |
ulty | -2.723 |
Token | Syrian |
Token ID | 6318 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
PLA | +3.142 |
Occupations | +2.907 |
Mp | +2.831 |
ORTS | +2.830 |
tremend | +2.694 |
Neg logit contributions | |
entric | -4.513 |
cester | -4.286 |
orical | -4.274 |
metic | -4.188 |
ulty | -4.130 |
Token | rebel |
Token ID | 14034 |
Feature activation | -9.18e+00 |
Pos logit contributions | |
PLA | +4.100 |
Occupations | +3.806 |
ORTS | +3.732 |
Mp | +3.732 |
Brigade | +3.562 |
Neg logit contributions | |
entric | -4.730 |
cester | -4.523 |
metic | -4.405 |
orical | -4.404 |
ulty | -4.274 |
Token | alliance |
Token ID | 12801 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
PLA | +5.420 |
Occupations | +4.997 |
ORTS | +4.871 |
Mp | +4.840 |
Brigade | +4.749 |
Neg logit contributions | |
entric | -7.878 |
cester | -7.441 |
orical | -7.280 |
metic | -7.235 |
ulty | -7.092 |
Token | , |
Token ID | 11 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
PLA | +0.226 |
Occupations | +0.209 |
ORTS | +0.209 |
Mp | +0.208 |
tremend | +0.206 |
Neg logit contributions | |
entric | -0.230 |
orical | -0.218 |
cester | -0.217 |
metic | -0.213 |
ignment | -0.212 |
Token | the |
Token ID | 262 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
PLA | +0.264 |
Occupations | +0.243 |
ORTS | +0.242 |
Mp | +0.241 |
tremend | +0.237 |
Neg logit contributions | |
entric | -0.287 |
orical | -0.273 |
cester | -0.273 |
metic | -0.268 |
ignment | -0.265 |
Token | Free |
Token ID | 3232 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
PLA | +0.624 |
Occupations | +0.570 |
ORTS | +0.569 |
Mp | +0.566 |
tremend | +0.557 |
Neg logit contributions | |
entric | -0.780 |
orical | -0.743 |
cester | -0.741 |
metic | -0.729 |
ignment | -0.723 |
Token | Syrian |
Token ID | 6318 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
PLA | +0.577 |
Occupations | +0.508 |
ORTS | +0.505 |
Mp | +0.498 |
tremend | +0.471 |
Neg logit contributions | |
entric | -1.214 |
cester | -1.163 |
orical | -1.160 |
metic | -1.146 |
ignment | -1.130 |
Token | his |
Token ID | 465 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
entric | +0.936 |
orical | +0.889 |
cester | +0.886 |
metic | +0.871 |
ignment | +0.864 |
Neg logit contributions | |
PLA | -0.879 |
Occupations | -0.809 |
ORTS | -0.807 |
Mp | -0.804 |
tremend | -0.794 |
Token | appearance |
Token ID | 5585 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
entric | +1.917 |
orical | +1.820 |
cester | +1.810 |
metic | +1.786 |
ignment | +1.768 |
Neg logit contributions | |
PLA | -1.877 |
Occupations | -1.728 |
ORTS | -1.723 |
Mp | -1.714 |
tremend | -1.692 |
Token | in |
Token ID | 287 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
PLA | +1.526 |
Occupations | +1.420 |
ORTS | +1.415 |
Mp | +1.410 |
tremend | +1.393 |
Neg logit contributions | |
entric | -1.402 |
cester | -1.327 |
orical | -1.327 |
metic | -1.300 |
ignment | -1.283 |
Token | The |
Token ID | 383 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
PLA | +1.775 |
Occupations | +1.644 |
ORTS | +1.640 |
Mp | +1.624 |
tremend | +1.602 |
Neg logit contributions | |
entric | -1.832 |
cester | -1.729 |
orical | -1.725 |
metic | -1.687 |
ignment | -1.679 |
Token | M |
Token ID | 337 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
PLA | +0.377 |
Occupations | +0.350 |
Mp | +0.345 |
ORTS | +0.345 |
tremend | +0.332 |
Neg logit contributions | |
entric | -0.460 |
orical | -0.436 |
cester | -0.436 |
metic | -0.429 |
ignment | -0.426 |
Token | uppet |
Token ID | 44933 |
Feature activation | -9.13e+00 |
Pos logit contributions | |
PLA | +3.891 |
Mp | +3.548 |
ORTS | +3.539 |
Occupations | +3.509 |
AGES | +3.379 |
Neg logit contributions | |
entric | -4.545 |
cester | -4.332 |
orical | -4.306 |
metic | -4.262 |
ignment | -4.144 |
Token | Movie |
Token ID | 15875 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
PLA | +4.596 |
Occupations | +4.212 |
ORTS | +4.201 |
Mp | +4.091 |
Brigade | +3.882 |
Neg logit contributions | |
entric | -8.377 |
cester | -8.102 |
metic | -8.036 |
orical | -8.000 |
ignment | -7.901 |
Token | ( |
Token ID | 357 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
PLA | +3.706 |
Occupations | +3.451 |
ORTS | +3.445 |
Mp | +3.440 |
tremend | +3.305 |
Neg logit contributions | |
entric | -4.157 |
orical | -3.951 |
cester | -3.938 |
metic | -3.901 |
ignment | -3.849 |
Token | 1979 |
Token ID | 33581 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
PLA | +0.247 |
Occupations | +0.224 |
ORTS | +0.224 |
Mp | +0.223 |
tremend | +0.218 |
Neg logit contributions | |
entric | -0.339 |
orical | -0.323 |
cester | -0.322 |
metic | -0.316 |
ignment | -0.315 |
Token | ). |
Token ID | 737 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
PLA | +0.717 |
ORTS | +0.658 |
Occupations | +0.658 |
Mp | +0.653 |
tremend | +0.644 |
Neg logit contributions | |
entric | -0.794 |
orical | -0.751 |
cester | -0.750 |
metic | -0.737 |
ignment | -0.733 |
Token | The |
Token ID | 383 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
PLA | +0.482 |
Occupations | +0.442 |
ORTS | +0.440 |
Mp | +0.438 |
tremend | +0.430 |
Neg logit contributions | |
entric | -0.576 |
orical | -0.548 |
cester | -0.547 |
metic | -0.537 |
ignment | -0.533 |
Token | Dayton |
Token ID | 24450 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
PLA | +1.922 |
Occupations | +1.763 |
ORTS | +1.758 |
Mp | +1.738 |
tremend | +1.717 |
Neg logit contributions | |
entric | -2.114 |
orical | -2.000 |
cester | -1.991 |
metic | -1.960 |
ignment | -1.936 |
Token | , |
Token ID | 11 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
PLA | +0.716 |
Occupations | +0.661 |
ORTS | +0.660 |
Mp | +0.656 |
tremend | +0.648 |
Neg logit contributions | |
entric | -0.680 |
cester | -0.642 |
orical | -0.642 |
metic | -0.630 |
ignment | -0.624 |
Token | Ohio |
Token ID | 6835 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
PLA | +0.603 |
Occupations | +0.564 |
ORTS | +0.560 |
Mp | +0.557 |
tremend | +0.551 |
Neg logit contributions | |
entric | -0.501 |
orical | -0.471 |
cester | -0.469 |
metic | -0.460 |
ignment | -0.453 |
Token | at |
Token ID | 379 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
entric | +0.534 |
orical | +0.506 |
cester | +0.502 |
metic | +0.493 |
ignment | +0.490 |
Neg logit contributions | |
PLA | -0.572 |
ORTS | -0.530 |
Occupations | -0.530 |
Mp | -0.529 |
tremend | -0.523 |
Token | a |
Token ID | 257 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
entric | +0.943 |
orical | +0.897 |
cester | +0.892 |
metic | +0.873 |
ignment | +0.872 |
Neg logit contributions | |
PLA | -0.941 |
Occupations | -0.869 |
Mp | -0.867 |
ORTS | -0.866 |
tremend | -0.857 |
Token | mock |
Token ID | 15290 |
Feature activation | -9.12e+00 |
Pos logit contributions | |
PLA | +0.491 |
Occupations | +0.451 |
ORTS | +0.450 |
Mp | +0.448 |
tremend | +0.443 |
Neg logit contributions | |
entric | -0.535 |
orical | -0.508 |
cester | -0.507 |
metic | -0.498 |
ignment | -0.494 |
Token | large |
Token ID | 1588 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
PLA | +6.619 |
ORTS | +5.946 |
Mp | +5.847 |
Occupations | +5.843 |
gallery | +5.802 |
Neg logit contributions | |
entric | -6.461 |
cester | -6.118 |
metic | -6.056 |
orical | -6.033 |
ulty | -5.832 |
Token | tail |
Token ID | 7894 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
PLA | +0.247 |
Occupations | +0.230 |
ORTS | +0.229 |
Mp | +0.228 |
tremend | +0.225 |
Neg logit contributions | |
entric | -0.200 |
orical | -0.189 |
cester | -0.189 |
metic | -0.185 |
ignment | -0.182 |
Token | gate |
Token ID | 10494 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
PLA | +0.929 |
ORTS | +0.864 |
Mp | +0.856 |
Occupations | +0.856 |
tremend | +0.847 |
Neg logit contributions | |
entric | -0.776 |
cester | -0.733 |
orical | -0.727 |
metic | -0.712 |
ignment | -0.702 |
Token | event |
Token ID | 1785 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
entric | +2.282 |
orical | +2.155 |
cester | +2.133 |
ignment | +2.116 |
metic | +2.110 |
Neg logit contributions | |
PLA | -2.421 |
Occupations | -2.256 |
Mp | -2.251 |
ORTS | -2.234 |
tremend | -2.223 |
Token | where |
Token ID | 810 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
entric | +0.245 |
orical | +0.232 |
cester | +0.231 |
metic | +0.227 |
ignment | +0.225 |
Neg logit contributions | |
PLA | -0.243 |
Occupations | -0.225 |
ORTS | -0.224 |
Mp | -0.223 |
tremend | -0.221 |
Token | set |
Token ID | 900 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
entric | +2.339 |
orical | +2.213 |
cester | +2.206 |
metic | +2.180 |
ignment | +2.164 |
Neg logit contributions | |
PLA | -2.302 |
ORTS | -2.112 |
Occupations | -2.111 |
Mp | -2.094 |
tremend | -2.083 |
Token | up |
Token ID | 510 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
entric | +0.813 |
orical | +0.777 |
cester | +0.774 |
metic | +0.761 |
ignment | +0.756 |
Neg logit contributions | |
PLA | -0.695 |
ORTS | -0.638 |
Occupations | -0.638 |
Mp | -0.633 |
tremend | -0.627 |
Token | a |
Token ID | 257 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
PLA | +0.292 |
Occupations | +0.269 |
ORTS | +0.269 |
Mp | +0.267 |
tremend | +0.264 |
Neg logit contributions | |
entric | -0.313 |
orical | -0.297 |
cester | -0.296 |
metic | -0.291 |
ignment | -0.289 |
Token | large |
Token ID | 1588 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
PLA | +0.128 |
Occupations | +0.119 |
ORTS | +0.118 |
Mp | +0.118 |
tremend | +0.116 |
Neg logit contributions | |
entric | -0.130 |
orical | -0.123 |
cester | -0.123 |
metic | -0.120 |
ignment | -0.119 |
Token | , |
Token ID | 11 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
entric | +0.332 |
orical | +0.315 |
cester | +0.315 |
metic | +0.308 |
ignment | +0.306 |
Neg logit contributions | |
PLA | -0.308 |
Occupations | -0.284 |
ORTS | -0.283 |
Mp | -0.281 |
tremend | -0.278 |
Token | mock |
Token ID | 15290 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
entric | +0.018 |
orical | +0.017 |
cester | +0.017 |
metic | +0.016 |
ignment | +0.016 |
Neg logit contributions | |
PLA | -0.019 |
Occupations | -0.018 |
ORTS | -0.018 |
Mp | -0.018 |
tremend | -0.018 |
Token | ballot |
Token ID | 11100 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
PLA | +6.612 |
Occupations | +6.017 |
ORTS | +5.962 |
Mp | +5.873 |
gallery | +5.727 |
Neg logit contributions | |
entric | -6.392 |
cester | -6.133 |
metic | -5.916 |
ulty | -5.911 |
orical | -5.835 |
Token | box |
Token ID | 3091 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
PLA | +1.508 |
ORTS | +1.370 |
Mp | +1.370 |
Occupations | +1.366 |
tremend | +1.323 |
Neg logit contributions | |
entric | -1.895 |
cester | -1.794 |
orical | -1.788 |
metic | -1.761 |
ignment | -1.734 |
Token | in |
Token ID | 287 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
PLA | +1.729 |
Occupations | +1.585 |
ORTS | +1.579 |
Mp | +1.572 |
tremend | +1.543 |
Neg logit contributions | |
entric | -1.729 |
cester | -1.634 |
orical | -1.630 |
metic | -1.598 |
ignment | -1.580 |
Token | the |
Token ID | 262 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
PLA | +1.568 |
Occupations | +1.447 |
ORTS | +1.432 |
Mp | +1.431 |
tremend | +1.401 |
Neg logit contributions | |
entric | -1.841 |
cester | -1.751 |
orical | -1.746 |
metic | -1.712 |
ignment | -1.695 |
Token | centre |
Token ID | 7372 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
PLA | +0.849 |
Occupations | +0.785 |
ORTS | +0.782 |
Mp | +0.778 |
tremend | +0.766 |
Neg logit contributions | |
entric | -0.912 |
orical | -0.864 |
cester | -0.863 |
metic | -0.846 |
ignment | -0.838 |
Token | series |
Token ID | 2168 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
PLA | +1.027 |
Occupations | +0.941 |
ORTS | +0.937 |
Mp | +0.934 |
tremend | +0.917 |
Neg logit contributions | |
entric | -1.230 |
cester | -1.168 |
orical | -1.168 |
metic | -1.141 |
ignment | -1.131 |
Token | . |
Token ID | 13 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
PLA | +0.297 |
Occupations | +0.275 |
ORTS | +0.274 |
Mp | +0.273 |
tremend | +0.270 |
Neg logit contributions | |
entric | -0.278 |
orical | -0.263 |
cester | -0.262 |
metic | -0.257 |
ignment | -0.255 |
Token |
|
Token ID | 198 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
PLA | +0.682 |
Occupations | +0.628 |
ORTS | +0.627 |
Mp | +0.624 |
tremend | +0.618 |
Neg logit contributions | |
entric | -0.717 |
orical | -0.680 |
cester | -0.679 |
metic | -0.666 |
ignment | -0.661 |
Token |
|
Token ID | 198 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
PLA | +0.564 |
Mp | +0.517 |
ORTS | +0.517 |
Occupations | +0.516 |
00200000 | +0.495 |
Neg logit contributions | |
entric | -0.611 |
orical | -0.576 |
cester | -0.576 |
metic | -0.564 |
ignment | -0.558 |
Token | The |
Token ID | 464 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
PLA | +0.636 |
Mp | +0.578 |
Occupations | +0.578 |
ORTS | +0.578 |
tremend | +0.561 |
Neg logit contributions | |
entric | -0.778 |
orical | -0.739 |
cester | -0.739 |
metic | -0.724 |
ignment | -0.720 |
Token | PBS |
Token ID | 30051 |
Feature activation | -9.01e+00 |
Pos logit contributions | |
PLA | +0.141 |
Occupations | +0.129 |
ORTS | +0.129 |
Mp | +0.128 |
tremend | +0.127 |
Neg logit contributions | |
entric | -0.162 |
orical | -0.154 |
cester | -0.153 |
metic | -0.151 |
ignment | -0.150 |
Token | / |
Token ID | 14 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
PLA | +5.499 |
ORTS | +5.108 |
Occupations | +5.058 |
Mp | +5.028 |
Runner | +4.832 |
Neg logit contributions | |
entric | -7.269 |
cester | -6.925 |
orical | -6.875 |
metic | -6.828 |
ignment | -6.691 |
Token | W |
Token ID | 54 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
PLA | +2.461 |
ORTS | +2.224 |
Mp | +2.223 |
Occupations | +2.176 |
AGES | +2.108 |
Neg logit contributions | |
entric | -3.163 |
cester | -3.011 |
orical | -3.006 |
metic | -2.950 |
ignment | -2.936 |
Token | NET |
Token ID | 12884 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
PLA | +1.694 |
ORTS | +1.510 |
Mp | +1.504 |
Occupations | +1.451 |
AGES | +1.433 |
Neg logit contributions | |
entric | -2.428 |
cester | -2.330 |
orical | -2.324 |
metic | -2.306 |
ignment | -2.293 |
Token | series |
Token ID | 2168 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
PLA | +2.640 |
ORTS | +2.416 |
Occupations | +2.414 |
Mp | +2.392 |
tremend | +2.336 |
Neg logit contributions | |
entric | -3.291 |
orical | -3.136 |
cester | -3.124 |
metic | -3.074 |
ignment | -3.046 |
Token | Nature |
Token ID | 10362 |
Feature activation | -6.50e+00 |
Pos logit contributions | |
PLA | +0.808 |
Occupations | +0.745 |
ORTS | +0.743 |
Mp | +0.739 |
tremend | +0.729 |
Neg logit contributions | |
entric | -0.871 |
orical | -0.826 |
cester | -0.825 |
metic | -0.810 |
ignment | -0.803 |
Token | it |
Token ID | 340 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
entric | +0.037 |
orical | +0.035 |
cester | +0.035 |
metic | +0.034 |
ignment | +0.034 |
Neg logit contributions | |
PLA | -0.040 |
Occupations | -0.037 |
ORTS | -0.037 |
Mp | -0.037 |
tremend | -0.036 |
Token | wasn |
Token ID | 2492 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
PLA | +2.175 |
Occupations | +1.979 |
Mp | +1.971 |
ORTS | +1.967 |
tremend | +1.954 |
Neg logit contributions | |
entric | -2.810 |
cester | -2.679 |
orical | -2.656 |
metic | -2.635 |
ignment | -2.593 |
Token | � |
Token ID | 447 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
PLA | +1.201 |
ORTS | +1.095 |
Mp | +1.094 |
Occupations | +1.091 |
00200000 | +1.045 |
Neg logit contributions | |
entric | -1.346 |
cester | -1.268 |
orical | -1.262 |
metic | -1.244 |
ignment | -1.227 |
Token | � |
Token ID | 247 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
PLA | +0.274 |
ORTS | +0.238 |
Mp | +0.237 |
Occupations | +0.237 |
gallery | +0.217 |
Neg logit contributions | |
entric | -0.670 |
cester | -0.640 |
orical | -0.637 |
metic | -0.633 |
ignment | -0.628 |
Token | t |
Token ID | 83 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
entric | +0.619 |
orical | +0.583 |
cester | +0.583 |
metic | +0.570 |
ignment | +0.567 |
Neg logit contributions | |
PLA | -0.677 |
Occupations | -0.627 |
ORTS | -0.627 |
Mp | -0.624 |
tremend | -0.617 |
Token | just |
Token ID | 655 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
entric | +1.499 |
orical | +1.433 |
cester | +1.422 |
metic | +1.406 |
ignment | +1.385 |
Neg logit contributions | |
PLA | -1.709 |
ORTS | -1.583 |
Occupations | -1.578 |
Mp | -1.575 |
tremend | -1.556 |
Token | in |
Token ID | 287 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
entric | +3.725 |
orical | +3.600 |
cester | +3.577 |
ignment | +3.522 |
metic | +3.519 |
Neg logit contributions | |
PLA | -4.428 |
ORTS | -4.101 |
Mp | -4.057 |
Occupations | -4.043 |
tremend | -4.022 |
Token | the |
Token ID | 262 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
PLA | +1.045 |
Occupations | +0.969 |
ORTS | +0.963 |
Mp | +0.962 |
tremend | +0.949 |
Neg logit contributions | |
entric | -1.018 |
orical | -0.960 |
cester | -0.959 |
metic | -0.939 |
ignment | -0.931 |
Token | mind |
Token ID | 2000 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
entric | +0.115 |
orical | +0.108 |
cester | +0.108 |
metic | +0.106 |
ignment | +0.105 |
Neg logit contributions | |
PLA | -0.122 |
Occupations | -0.114 |
ORTS | -0.113 |
Mp | -0.113 |
tremend | -0.111 |
Token | of |
Token ID | 286 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
PLA | +0.193 |
Occupations | +0.177 |
ORTS | +0.177 |
Mp | +0.176 |
tremend | +0.174 |
Neg logit contributions | |
entric | -0.222 |
orical | -0.211 |
cester | -0.211 |
metic | -0.207 |
ignment | -0.206 |
Token | one |
Token ID | 530 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
PLA | +0.460 |
Occupations | +0.426 |
ORTS | +0.425 |
Mp | +0.423 |
tremend | +0.418 |
Neg logit contributions | |
entric | -0.455 |
orical | -0.431 |
cester | -0.430 |
metic | -0.421 |
ignment | -0.418 |
Token | . |
Token ID | 13 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
entric | +0.894 |
orical | +0.844 |
cester | +0.839 |
metic | +0.825 |
ignment | +0.818 |
Neg logit contributions | |
PLA | -1.021 |
Occupations | -0.951 |
ORTS | -0.948 |
Mp | -0.942 |
tremend | -0.933 |
Token | � |
Token ID | 447 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
entric | +0.173 |
orical | +0.164 |
cester | +0.164 |
metic | +0.161 |
ignment | +0.160 |
Neg logit contributions | |
PLA | -0.167 |
Occupations | -0.154 |
ORTS | -0.154 |
Mp | -0.153 |
tremend | -0.152 |
Token | � |
Token ID | 251 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
PLA | +0.428 |
Occupations | +0.400 |
ORTS | +0.399 |
Mp | +0.397 |
tremend | +0.392 |
Neg logit contributions | |
entric | -0.313 |
cester | -0.292 |
orical | -0.291 |
metic | -0.286 |
ignment | -0.283 |
Token |
|
Token ID | 198 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
PLA | +0.302 |
Occupations | +0.278 |
ORTS | +0.277 |
Mp | +0.277 |
tremend | +0.272 |
Neg logit contributions | |
entric | -0.323 |
orical | -0.307 |
cester | -0.306 |
metic | -0.300 |
ignment | -0.298 |
Token |
|
Token ID | 198 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
entric | +0.711 |
orical | +0.675 |
cester | +0.673 |
metic | +0.660 |
ignment | +0.656 |
Neg logit contributions | |
PLA | -0.719 |
Occupations | -0.665 |
ORTS | -0.663 |
Mp | -0.660 |
tremend | -0.658 |
Token | Just |
Token ID | 5703 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
entric | +0.493 |
orical | +0.468 |
cester | +0.467 |
metic | +0.458 |
ignment | +0.455 |
Neg logit contributions | |
PLA | -0.476 |
Occupations | -0.440 |
ORTS | -0.439 |
Mp | -0.436 |
tremend | -0.433 |
Token | as |
Token ID | 355 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
entric | +3.802 |
cester | +3.685 |
orical | +3.625 |
ignment | +3.591 |
metic | +3.577 |
Neg logit contributions | |
PLA | -4.697 |
ORTS | -4.433 |
Occupations | -4.382 |
tremend | -4.347 |
Mp | -4.336 |
Token | his |
Token ID | 465 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
PLA | +0.591 |
Occupations | +0.547 |
ORTS | +0.545 |
Mp | +0.544 |
tremend | +0.536 |
Neg logit contributions | |
entric | -0.569 |
orical | -0.539 |
cester | -0.538 |
metic | -0.526 |
ignment | -0.522 |
Token | grandmother |
Token ID | 18410 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
entric | +2.006 |
orical | +1.876 |
cester | +1.870 |
metic | +1.853 |
ignment | +1.827 |
Neg logit contributions | |
PLA | -2.585 |
ORTS | -2.411 |
Occupations | -2.400 |
Mp | -2.382 |
tremend | -2.366 |
Token | motivated |
Token ID | 13338 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
PLA | +0.681 |
Occupations | +0.629 |
ORTS | +0.627 |
Mp | +0.627 |
tremend | +0.617 |
Neg logit contributions | |
entric | -0.725 |
orical | -0.690 |
cester | -0.688 |
metic | -0.673 |
ignment | -0.667 |
Token | him |
Token ID | 683 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
PLA | +1.771 |
Occupations | +1.618 |
ORTS | +1.609 |
Mp | +1.606 |
tremend | +1.557 |
Neg logit contributions | |
entric | -2.396 |
cester | -2.290 |
orical | -2.286 |
metic | -2.242 |
ignment | -2.218 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
PLA | +0.015 |
Occupations | +0.014 |
ORTS | +0.014 |
Mp | +0.014 |
tremend | +0.014 |
Neg logit contributions | |
entric | -0.013 |
cester | -0.013 |
orical | -0.013 |
metic | -0.012 |
ignment | -0.012 |
Token | It |
Token ID | 632 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
entric | +0.791 |
orical | +0.750 |
cester | +0.748 |
metic | +0.734 |
ignment | +0.729 |
Neg logit contributions | |
PLA | -0.770 |
Occupations | -0.709 |
ORTS | -0.709 |
Mp | -0.705 |
tremend | -0.699 |
Token | � |
Token ID | 447 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
PLA | +1.524 |
Occupations | +1.390 |
ORTS | +1.378 |
Mp | +1.378 |
tremend | +1.369 |
Neg logit contributions | |
entric | -1.800 |
cester | -1.707 |
orical | -1.700 |
metic | -1.680 |
ignment | -1.659 |
Token | � |
Token ID | 247 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
PLA | +0.281 |
Occupations | +0.245 |
ORTS | +0.245 |
Mp | +0.245 |
tremend | +0.226 |
Neg logit contributions | |
entric | -0.656 |
cester | -0.626 |
orical | -0.625 |
metic | -0.618 |
ignment | -0.616 |
Token | s |
Token ID | 82 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
entric | +0.329 |
orical | +0.306 |
cester | +0.305 |
metic | +0.297 |
ignment | +0.294 |
Neg logit contributions | |
PLA | -0.556 |
Occupations | -0.522 |
ORTS | -0.522 |
Mp | -0.520 |
tremend | -0.515 |
Token | delusional |
Token ID | 45935 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
entric | +0.991 |
orical | +0.935 |
cester | +0.934 |
metic | +0.913 |
ignment | +0.906 |
Neg logit contributions | |
PLA | -1.127 |
Occupations | -1.046 |
ORTS | -1.044 |
Mp | -1.039 |
tremend | -1.029 |
Token | darkness |
Token ID | 11854 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
entric | +4.329 |
orical | +4.077 |
ignment | +4.023 |
metic | +4.002 |
cester | +3.991 |
Neg logit contributions | |
PLA | -5.167 |
ORTS | -4.821 |
Occupations | -4.814 |
Mp | -4.763 |
tremend | -4.657 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
entric | +0.529 |
orical | +0.502 |
cester | +0.502 |
metic | +0.491 |
ignment | +0.487 |
Neg logit contributions | |
PLA | -0.520 |
Occupations | -0.479 |
ORTS | -0.478 |
Mp | -0.475 |
tremend | -0.472 |
Token | right |
Token ID | 826 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
entric | +0.760 |
cester | +0.715 |
orical | +0.713 |
metic | +0.695 |
ignment | +0.689 |
Neg logit contributions | |
PLA | -0.976 |
Occupations | -0.909 |
ORTS | -0.905 |
Mp | -0.904 |
tremend | -0.896 |
Token | ? |
Token ID | 30 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
entric | +3.786 |
orical | +3.622 |
cester | +3.570 |
ignment | +3.520 |
metic | +3.506 |
Neg logit contributions | |
PLA | -4.340 |
Occupations | -4.073 |
ORTS | -4.052 |
Mp | -4.013 |
tremend | -3.997 |
Token | He |
Token ID | 679 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
entric | +1.228 |
orical | +1.167 |
cester | +1.162 |
metic | +1.140 |
ignment | +1.134 |
Neg logit contributions | |
PLA | -1.235 |
ORTS | -1.140 |
Occupations | -1.137 |
tremend | -1.135 |
Mp | -1.133 |
Token | than |
Token ID | 621 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
PLA | +0.974 |
Occupations | +0.898 |
ORTS | +0.898 |
Mp | +0.893 |
tremend | +0.874 |
Neg logit contributions | |
entric | -0.883 |
orical | -0.831 |
cester | -0.831 |
metic | -0.810 |
ignment | -0.808 |
Token | a |
Token ID | 257 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
entric | +0.521 |
orical | +0.494 |
cester | +0.492 |
metic | +0.485 |
ignment | +0.480 |
Neg logit contributions | |
PLA | -0.528 |
Occupations | -0.488 |
ORTS | -0.486 |
Mp | -0.484 |
tremend | -0.483 |
Token | hood |
Token ID | 14263 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
entric | +0.510 |
orical | +0.484 |
cester | +0.482 |
metic | +0.472 |
ignment | +0.469 |
Neg logit contributions | |
PLA | -0.598 |
Occupations | -0.557 |
ORTS | -0.552 |
Mp | -0.550 |
tremend | -0.548 |
Token | ie |
Token ID | 494 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
PLA | +1.513 |
ORTS | +1.414 |
Occupations | +1.413 |
Mp | +1.409 |
tremend | +1.392 |
Neg logit contributions | |
entric | -1.011 |
orical | -0.945 |
cester | -0.944 |
metic | -0.919 |
ignment | -0.912 |
Token | , |
Token ID | 11 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
entric | +0.982 |
orical | +0.927 |
cester | +0.925 |
metic | +0.906 |
ignment | +0.899 |
Neg logit contributions | |
PLA | -1.144 |
Occupations | -1.065 |
ORTS | -1.061 |
Mp | -1.058 |
tremend | -1.053 |
Token | has |
Token ID | 468 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
entric | +0.553 |
orical | +0.522 |
cester | +0.521 |
metic | +0.510 |
ignment | +0.506 |
Neg logit contributions | |
PLA | -0.614 |
Occupations | -0.569 |
ORTS | -0.569 |
Mp | -0.566 |
tremend | -0.559 |
Token | no |
Token ID | 645 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
entric | +3.689 |
cester | +3.501 |
metic | +3.483 |
orical | +3.477 |
ignment | +3.417 |
Neg logit contributions | |
PLA | -4.144 |
Occupations | -3.835 |
ORTS | -3.801 |
Mp | -3.796 |
tremend | -3.741 |
Token | affinity |
Token ID | 28430 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
entric | +0.563 |
orical | +0.531 |
cester | +0.529 |
metic | +0.518 |
ignment | +0.514 |
Neg logit contributions | |
PLA | -0.653 |
Occupations | -0.607 |
ORTS | -0.606 |
Mp | -0.604 |
tremend | -0.596 |
Token | for |
Token ID | 329 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
PLA | +1.158 |
ORTS | +1.073 |
Occupations | +1.070 |
Mp | +1.069 |
tremend | +1.055 |
Neg logit contributions | |
entric | -1.131 |
cester | -1.076 |
orical | -1.067 |
metic | -1.047 |
ignment | -1.042 |
Token | ge |
Token ID | 4903 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
entric | +0.824 |
orical | +0.784 |
cester | +0.779 |
metic | +0.765 |
ignment | +0.761 |
Neg logit contributions | |
PLA | -0.924 |
Occupations | -0.851 |
Mp | -0.850 |
ORTS | -0.849 |
tremend | -0.844 |
Token | eking |
Token ID | 18754 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
entric | +3.126 |
orical | +2.994 |
cester | +2.939 |
metic | +2.908 |
ignment | +2.886 |
Neg logit contributions | |
PLA | -3.906 |
Occupations | -3.670 |
tremend | -3.668 |
ORTS | -3.641 |
Mp | -3.627 |
Token | criticised |
Token ID | 23894 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
entric | +3.686 |
cester | +3.477 |
orical | +3.469 |
metic | +3.437 |
ignment | +3.421 |
Neg logit contributions | |
PLA | -3.097 |
Occupations | -2.821 |
ORTS | -2.796 |
Mp | -2.754 |
tremend | -2.731 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
PLA | +0.129 |
Occupations | +0.119 |
ORTS | +0.119 |
Mp | +0.118 |
tremend | +0.117 |
Neg logit contributions | |
entric | -0.135 |
orical | -0.128 |
cester | -0.127 |
metic | -0.125 |
ignment | -0.124 |
Token | prime |
Token ID | 6994 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
PLA | +0.103 |
Occupations | +0.095 |
ORTS | +0.095 |
Mp | +0.095 |
tremend | +0.094 |
Neg logit contributions | |
entric | -0.101 |
orical | -0.096 |
cester | -0.096 |
metic | -0.094 |
ignment | -0.093 |
Token | minister |
Token ID | 5342 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
PLA | +0.877 |
Occupations | +0.782 |
ORTS | +0.780 |
Mp | +0.779 |
tremend | +0.756 |
Neg logit contributions | |
entric | -1.588 |
orical | -1.523 |
cester | -1.518 |
metic | -1.496 |
ignment | -1.485 |
Token | 's |
Token ID | 338 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
PLA | +0.972 |
ORTS | +0.900 |
Mp | +0.895 |
Occupations | +0.893 |
tremend | +0.881 |
Neg logit contributions | |
entric | -0.977 |
orical | -0.929 |
cester | -0.923 |
metic | -0.906 |
ignment | -0.900 |
Token | European |
Token ID | 3427 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
PLA | +0.126 |
ORTS | +0.118 |
Occupations | +0.117 |
Mp | +0.117 |
tremend | +0.116 |
Neg logit contributions | |
entric | -0.109 |
cester | -0.103 |
orical | -0.103 |
metic | -0.100 |
ignment | -0.100 |
Token | strategy |
Token ID | 4811 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
entric | +5.027 |
orical | +4.627 |
cester | +4.601 |
ignment | +4.586 |
metic | +4.448 |
Neg logit contributions | |
PLA | -4.992 |
ORTS | -4.519 |
Occupations | -4.506 |
tremend | -4.469 |
Mp | -4.443 |
Token | , |
Token ID | 11 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
PLA | +0.258 |
ORTS | +0.239 |
Occupations | +0.238 |
Mp | +0.238 |
tremend | +0.233 |
Neg logit contributions | |
entric | -0.236 |
orical | -0.224 |
cester | -0.223 |
metic | -0.217 |
ignment | -0.215 |
Token | saying |
Token ID | 2282 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
PLA | +0.166 |
ORTS | +0.151 |
Occupations | +0.150 |
Mp | +0.150 |
tremend | +0.147 |
Neg logit contributions | |
entric | -0.224 |
orical | -0.214 |
cester | -0.213 |
metic | -0.210 |
ignment | -0.208 |
Token | an |
Token ID | 281 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
entric | +0.707 |
orical | +0.667 |
cester | +0.667 |
metic | +0.653 |
ignment | +0.650 |
Neg logit contributions | |
PLA | -0.779 |
Occupations | -0.722 |
ORTS | -0.719 |
Mp | -0.716 |
tremend | -0.711 |
Token | " |
Token ID | 366 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
entric | +0.057 |
orical | +0.054 |
cester | +0.054 |
metic | +0.053 |
ignment | +0.052 |
Neg logit contributions | |
PLA | -0.062 |
ORTS | -0.058 |
Occupations | -0.058 |
Mp | -0.057 |
tremend | -0.057 |
Token | Brexit |
Token ID | 11435 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
entric | +0.130 |
orical | +0.123 |
cester | +0.123 |
metic | +0.120 |
ignment | +0.119 |
Neg logit contributions | |
PLA | -0.134 |
Occupations | -0.124 |
ORTS | -0.124 |
Mp | -0.123 |
tremend | -0.122 |
Token | betrayal |
Token ID | 29355 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
entric | +3.920 |
orical | +3.644 |
ignment | +3.644 |
cester | +3.621 |
metic | +3.602 |
Neg logit contributions | |
PLA | -3.675 |
ORTS | -3.402 |
tremend | -3.395 |
Occupations | -3.381 |
Mp | -3.315 |
Token | is |
Token ID | 318 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
entric | +1.311 |
orical | +1.244 |
cester | +1.242 |
metic | +1.220 |
ignment | +1.218 |
Neg logit contributions | |
PLA | -1.225 |
Occupations | -1.127 |
ORTS | -1.125 |
Mp | -1.117 |
tremend | -1.107 |
Token | coming |
Token ID | 2406 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
entric | +2.023 |
orical | +1.915 |
cester | +1.915 |
metic | +1.884 |
ignment | +1.869 |
Neg logit contributions | |
PLA | -2.367 |
ORTS | -2.190 |
Occupations | -2.186 |
Mp | -2.172 |
tremend | -2.151 |
Token | – |
Token ID | 784 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
PLA | +0.143 |
Occupations | +0.132 |
ORTS | +0.132 |
Mp | +0.131 |
tremend | +0.130 |
Neg logit contributions | |
entric | -0.138 |
orical | -0.130 |
cester | -0.130 |
metic | -0.127 |
ignment | -0.126 |
Token | but |
Token ID | 475 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
entric | +2.312 |
orical | +2.182 |
cester | +2.178 |
ignment | +2.144 |
metic | +2.142 |
Neg logit contributions | |
PLA | -2.470 |
ORTS | -2.291 |
Occupations | -2.277 |
Mp | -2.262 |
tremend | -2.251 |
Token | who |
Token ID | 508 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
entric | +1.220 |
orical | +1.152 |
cester | +1.150 |
metic | +1.133 |
ignment | +1.126 |
Neg logit contributions | |
PLA | -1.361 |
ORTS | -1.257 |
Occupations | -1.257 |
Mp | -1.249 |
tremend | -1.240 |
Token | will |
Token ID | 481 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
entric | +0.649 |
orical | +0.617 |
cester | +0.616 |
metic | +0.604 |
ignment | +0.601 |
Neg logit contributions | |
PLA | -0.617 |
ORTS | -0.567 |
Occupations | -0.567 |
Mp | -0.563 |
tremend | -0.559 |
Token | get |
Token ID | 651 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
PLA | +0.241 |
Occupations | +0.223 |
ORTS | +0.223 |
Mp | +0.222 |
tremend | +0.219 |
Neg logit contributions | |
entric | -0.229 |
orical | -0.217 |
cester | -0.216 |
metic | -0.212 |
ignment | -0.210 |
Token | the |
Token ID | 262 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
PLA | +0.758 |
Occupations | +0.702 |
ORTS | +0.702 |
Mp | +0.699 |
tremend | +0.690 |
Neg logit contributions | |
entric | -0.705 |
orical | -0.666 |
cester | -0.664 |
metic | -0.651 |
ignment | -0.645 |
Token | blame |
Token ID | 8138 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
entric | +0.089 |
orical | +0.084 |
cester | +0.084 |
metic | +0.081 |
ignment | +0.081 |
Neg logit contributions | |
PLA | -0.114 |
Occupations | -0.107 |
ORTS | -0.106 |
Mp | -0.106 |
tremend | -0.105 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
entric | +1.503 |
orical | +1.418 |
cester | +1.416 |
metic | +1.387 |
ignment | +1.377 |
Neg logit contributions | |
PLA | -1.677 |
Occupations | -1.553 |
ORTS | -1.552 |
Mp | -1.548 |
tremend | -1.533 |
Token | � |
Token ID | 447 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
entric | +0.786 |
orical | +0.740 |
cester | +0.738 |
metic | +0.722 |
ignment | +0.716 |
Neg logit contributions | |
PLA | -0.985 |
Occupations | -0.917 |
ORTS | -0.916 |
Mp | -0.912 |
tremend | -0.902 |
Token | � |
Token ID | 251 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
PLA | +0.265 |
Occupations | +0.245 |
ORTS | +0.243 |
Mp | +0.242 |
tremend | +0.236 |
Neg logit contributions | |
entric | -0.302 |
cester | -0.286 |
orical | -0.283 |
metic | -0.280 |
ignment | -0.279 |
Token | Bengals |
Token ID | 24037 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
PLA | +0.473 |
Occupations | +0.439 |
ORTS | +0.438 |
Mp | +0.435 |
tremend | +0.429 |
Neg logit contributions | |
entric | -0.394 |
orical | -0.369 |
cester | -0.369 |
metic | -0.361 |
ignment | -0.356 |
Token | special |
Token ID | 2041 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
PLA | +1.429 |
ORTS | +1.323 |
Occupations | +1.322 |
Mp | +1.313 |
tremend | +1.295 |
Neg logit contributions | |
entric | -1.331 |
orical | -1.261 |
cester | -1.260 |
metic | -1.234 |
ignment | -1.216 |
Token | teams |
Token ID | 3466 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
entric | +1.532 |
orical | +1.445 |
cester | +1.438 |
metic | +1.409 |
ignment | +1.393 |
Neg logit contributions | |
PLA | -1.813 |
ORTS | -1.686 |
Occupations | -1.686 |
Mp | -1.676 |
tremend | -1.658 |
Token | coordinator |
Token ID | 16052 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
PLA | +0.043 |
Occupations | +0.039 |
ORTS | +0.039 |
Mp | +0.039 |
tremend | +0.038 |
Neg logit contributions | |
entric | -0.052 |
orical | -0.050 |
cester | -0.050 |
metic | -0.049 |
ignment | -0.048 |
Token | D |
Token ID | 360 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
entric | +0.342 |
orical | +0.325 |
cester | +0.324 |
metic | +0.318 |
ignment | +0.316 |
Neg logit contributions | |
PLA | -0.327 |
Occupations | -0.301 |
ORTS | -0.301 |
Mp | -0.299 |
tremend | -0.296 |
Token | arr |
Token ID | 3258 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
PLA | +0.109 |
Occupations | +0.101 |
ORTS | +0.101 |
Mp | +0.100 |
tremend | +0.099 |
Neg logit contributions | |
entric | -0.096 |
orical | -0.090 |
cester | -0.090 |
metic | -0.089 |
ignment | -0.088 |
Token | in |
Token ID | 259 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
entric | +0.471 |
orical | +0.439 |
cester | +0.437 |
metic | +0.424 |
ignment | +0.422 |
Neg logit contributions | |
PLA | -0.744 |
ORTS | -0.695 |
Occupations | -0.693 |
Mp | -0.692 |
tremend | -0.688 |
Token | Simmons |
Token ID | 22553 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
entric | +0.448 |
orical | +0.426 |
cester | +0.425 |
metic | +0.417 |
ignment | +0.415 |
Neg logit contributions | |
PLA | -0.390 |
ORTS | -0.356 |
Occupations | -0.356 |
Mp | -0.355 |
tremend | -0.352 |
Token | joined |
Token ID | 5399 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
entric | +1.542 |
orical | +1.455 |
cester | +1.454 |
metic | +1.426 |
ignment | +1.419 |
Neg logit contributions | |
PLA | -1.585 |
ORTS | -1.469 |
Occupations | -1.463 |
Mp | -1.454 |
tremend | -1.450 |
Token | the |
Token ID | 262 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
PLA | +1.312 |
ORTS | +1.204 |
Occupations | +1.199 |
Mp | +1.187 |
tremend | +1.169 |
Neg logit contributions | |
entric | -1.355 |
cester | -1.285 |
orical | -1.282 |
metic | -1.246 |
ulty | -1.232 |
Token | EU |
Token ID | 4576 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
PLA | +0.669 |
Occupations | +0.621 |
ORTS | +0.615 |
Mp | +0.610 |
tremend | +0.600 |
Neg logit contributions | |
entric | -0.739 |
cester | -0.706 |
orical | -0.704 |
metic | -0.687 |
ignment | -0.678 |
Token | ( |
Token ID | 357 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
entric | +2.669 |
orical | +2.508 |
cester | +2.501 |
metic | +2.474 |
ignment | +2.439 |
Neg logit contributions | |
PLA | -3.037 |
Mp | -2.825 |
ORTS | -2.819 |
Occupations | -2.814 |
tremend | -2.786 |
Token | the |
Token ID | 1169 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
entric | +0.282 |
orical | +0.265 |
cester | +0.264 |
metic | +0.257 |
ignment | +0.257 |
Neg logit contributions | |
PLA | -0.360 |
Occupations | -0.334 |
ORTS | -0.334 |
Mp | -0.333 |
tremend | -0.328 |
Token | E |
Token ID | 412 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
entric | +0.749 |
orical | +0.710 |
cester | +0.707 |
metic | +0.694 |
ignment | +0.688 |
Neg logit contributions | |
PLA | -0.799 |
Occupations | -0.739 |
ORTS | -0.738 |
Mp | -0.735 |
tremend | -0.728 |
Token | EC |
Token ID | 2943 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
entric | +1.542 |
orical | +1.455 |
cester | +1.448 |
metic | +1.418 |
ignment | +1.406 |
Neg logit contributions | |
PLA | -1.862 |
ORTS | -1.725 |
Occupations | -1.722 |
Mp | -1.718 |
tremend | -1.694 |
Token | as |
Token ID | 355 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
entric | +1.063 |
orical | +1.002 |
cester | +0.998 |
metic | +0.980 |
ignment | +0.971 |
Neg logit contributions | |
PLA | -1.185 |
Occupations | -1.099 |
ORTS | -1.097 |
Mp | -1.092 |
tremend | -1.083 |
Token | it |
Token ID | 340 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
PLA | +1.564 |
Occupations | +1.459 |
Mp | +1.442 |
ORTS | +1.440 |
tremend | +1.404 |
Neg logit contributions | |
entric | -1.664 |
orical | -1.584 |
cester | -1.582 |
metic | -1.549 |
ignment | -1.532 |
Token | was |
Token ID | 373 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
PLA | +2.788 |
Mp | +2.586 |
Occupations | +2.570 |
ORTS | +2.558 |
tremend | +2.508 |
Neg logit contributions | |
entric | -3.266 |
cester | -3.089 |
orical | -3.073 |
metic | -3.037 |
ulty | -3.007 |
Token | then |
Token ID | 788 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
PLA | +0.263 |
Occupations | +0.241 |
ORTS | +0.240 |
Mp | +0.240 |
tremend | +0.235 |
Neg logit contributions | |
entric | -0.326 |
orical | -0.309 |
cester | -0.309 |
metic | -0.303 |
ignment | -0.300 |
Token | in |
Token ID | 287 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
PLA | +0.970 |
Occupations | +0.897 |
Mp | +0.897 |
ORTS | +0.895 |
tremend | +0.882 |
Neg logit contributions | |
entric | -0.917 |
cester | -0.872 |
orical | -0.864 |
metic | -0.846 |
ignment | -0.842 |
Token | any |
Token ID | 597 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
PLA | +1.049 |
Occupations | +0.975 |
ORTS | +0.970 |
Mp | +0.960 |
tremend | +0.946 |
Neg logit contributions | |
entric | -1.011 |
cester | -0.958 |
orical | -0.951 |
metic | -0.935 |
ignment | -0.922 |
Token | kind |
Token ID | 1611 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
entric | +0.368 |
orical | +0.349 |
cester | +0.348 |
metic | +0.342 |
ignment | +0.339 |
Neg logit contributions | |
PLA | -0.372 |
Occupations | -0.343 |
ORTS | -0.343 |
Mp | -0.341 |
tremend | -0.338 |
Token | of |
Token ID | 286 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
PLA | +0.612 |
Occupations | +0.555 |
ORTS | +0.553 |
Mp | +0.552 |
tremend | +0.529 |
Neg logit contributions | |
entric | -0.862 |
cester | -0.822 |
orical | -0.821 |
metic | -0.806 |
ignment | -0.799 |
Token | structural |
Token ID | 13204 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
entric | +0.096 |
orical | +0.091 |
cester | +0.091 |
metic | +0.089 |
ignment | +0.088 |
Neg logit contributions | |
PLA | -0.110 |
Occupations | -0.102 |
ORTS | -0.102 |
Mp | -0.101 |
tremend | -0.100 |
Token | or |
Token ID | 393 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
entric | +1.901 |
orical | +1.787 |
cester | +1.768 |
metic | +1.740 |
ignment | +1.735 |
Neg logit contributions | |
PLA | -2.584 |
ORTS | -2.413 |
Occupations | -2.412 |
Mp | -2.402 |
tremend | -2.386 |
Token | meaningful |
Token ID | 11570 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
PLA | +0.026 |
Occupations | +0.024 |
ORTS | +0.024 |
Mp | +0.024 |
tremend | +0.024 |
Neg logit contributions | |
entric | -0.023 |
orical | -0.022 |
cester | -0.022 |
metic | -0.021 |
ignment | -0.021 |
Token | rationale |
Token ID | 25738 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
entric | +0.759 |
orical | +0.717 |
cester | +0.714 |
metic | +0.700 |
ignment | +0.695 |
Neg logit contributions | |
PLA | -0.888 |
Occupations | -0.824 |
ORTS | -0.823 |
Mp | -0.820 |
tremend | -0.812 |
Token | . |
Token ID | 13 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
PLA | +1.063 |
ORTS | +0.972 |
Occupations | +0.971 |
Mp | +0.967 |
tremend | +0.953 |
Neg logit contributions | |
entric | -1.128 |
cester | -1.074 |
orical | -1.070 |
metic | -1.046 |
ignment | -1.040 |
Token | While |
Token ID | 2893 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
entric | +0.029 |
orical | +0.027 |
cester | +0.027 |
metic | +0.027 |
ignment | +0.026 |
Neg logit contributions | |
PLA | -0.026 |
ORTS | -0.024 |
Occupations | -0.024 |
Mp | -0.024 |
tremend | -0.024 |
Token | panel |
Token ID | 6103 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
PLA | +1.600 |
Occupations | +1.477 |
ORTS | +1.471 |
Mp | +1.462 |
tremend | +1.441 |
Neg logit contributions | |
entric | -1.612 |
cester | -1.531 |
orical | -1.525 |
metic | -1.483 |
ignment | -1.474 |
Token | cut |
Token ID | 2005 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
PLA | +0.326 |
ORTS | +0.300 |
Occupations | +0.299 |
Mp | +0.299 |
tremend | +0.295 |
Neg logit contributions | |
entric | -0.349 |
orical | -0.332 |
cester | -0.332 |
metic | -0.325 |
ignment | -0.322 |
Token | down |
Token ID | 866 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
entric | +0.283 |
orical | +0.266 |
cester | +0.265 |
metic | +0.259 |
ignment | +0.257 |
Neg logit contributions | |
PLA | -0.360 |
Occupations | -0.336 |
ORTS | -0.335 |
Mp | -0.334 |
tremend | -0.330 |
Token | development |
Token ID | 2478 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
entric | +1.634 |
orical | +1.533 |
cester | +1.515 |
metic | +1.493 |
ignment | +1.480 |
Neg logit contributions | |
PLA | -2.180 |
Occupations | -2.046 |
ORTS | -2.036 |
Mp | -2.022 |
tremend | -2.003 |
Token | time |
Token ID | 640 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
PLA | +0.570 |
Occupations | +0.535 |
ORTS | +0.534 |
Mp | +0.532 |
tremend | +0.526 |
Neg logit contributions | |
entric | -0.366 |
cester | -0.342 |
orical | -0.342 |
metic | -0.331 |
ignment | -0.328 |
Token | drastically |
Token ID | 22188 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
entric | +0.019 |
orical | +0.018 |
cester | +0.018 |
metic | +0.017 |
ignment | +0.017 |
Neg logit contributions | |
PLA | -0.021 |
ORTS | -0.020 |
Occupations | -0.020 |
Mp | -0.020 |
tremend | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
entric | +1.644 |
orical | +1.551 |
cester | +1.547 |
metic | +1.516 |
ignment | +1.505 |
Neg logit contributions | |
PLA | -1.894 |
Occupations | -1.757 |
ORTS | -1.755 |
Mp | -1.745 |
tremend | -1.728 |
Token | make |
Token ID | 787 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
PLA | +0.009 |
Occupations | +0.009 |
ORTS | +0.009 |
Mp | +0.009 |
tremend | +0.008 |
Neg logit contributions | |
entric | -0.010 |
orical | -0.009 |
cester | -0.009 |
metic | -0.009 |
ignment | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
PLA | +1.503 |
Occupations | +1.385 |
Mp | +1.381 |
ORTS | +1.379 |
tremend | +1.358 |
Neg logit contributions | |
entric | -1.425 |
cester | -1.346 |
orical | -1.343 |
metic | -1.310 |
ignment | -1.302 |
Token | much |
Token ID | 881 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
PLA | +2.093 |
Mp | +1.967 |
Occupations | +1.966 |
ORTS | +1.949 |
tremend | +1.933 |
Neg logit contributions | |
entric | -2.070 |
cester | -1.955 |
orical | -1.950 |
ignment | -1.891 |
metic | -1.887 |
Token | more |
Token ID | 517 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
entric | +0.575 |
orical | +0.540 |
cester | +0.539 |
metic | +0.528 |
ignment | +0.523 |
Neg logit contributions | |
PLA | -0.768 |
Occupations | -0.716 |
ORTS | -0.715 |
Mp | -0.711 |
tremend | -0.705 |
Token | straightforward |
Token ID | 15836 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
PLA | +1.167 |
Occupations | +1.086 |
Mp | +1.081 |
ORTS | +1.081 |
tremend | +1.065 |
Neg logit contributions | |
entric | -1.083 |
orical | -1.022 |
cester | -1.019 |
metic | -0.992 |
ignment | -0.991 |
Token | - |
Token ID | 12 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
PLA | +2.120 |
ORTS | +1.979 |
Occupations | +1.967 |
Mp | +1.964 |
tremend | +1.936 |
Neg logit contributions | |
entric | -1.273 |
cester | -1.184 |
orical | -1.183 |
metic | -1.140 |
ignment | -1.130 |
Token | back |
Token ID | 1891 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
PLA | +1.458 |
Mp | +1.338 |
ORTS | +1.338 |
Occupations | +1.332 |
gallery | +1.302 |
Neg logit contributions | |
entric | -0.922 |
cester | -0.860 |
orical | -0.856 |
metic | -0.813 |
ignment | -0.811 |
Token | from |
Token ID | 422 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
PLA | +0.523 |
Occupations | +0.481 |
ORTS | +0.480 |
Mp | +0.477 |
tremend | +0.471 |
Neg logit contributions | |
entric | -0.545 |
orical | -0.516 |
cester | -0.516 |
metic | -0.505 |
ignment | -0.502 |
Token | current |
Token ID | 1459 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
PLA | +0.252 |
Occupations | +0.233 |
ORTS | +0.233 |
Mp | +0.231 |
tremend | +0.229 |
Neg logit contributions | |
entric | -0.257 |
orical | -0.244 |
cester | -0.243 |
metic | -0.238 |
ignment | -0.237 |
Token | and |
Token ID | 290 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
PLA | +0.075 |
Occupations | +0.070 |
ORTS | +0.070 |
Mp | +0.069 |
tremend | +0.068 |
Neg logit contributions | |
entric | -0.059 |
orical | -0.056 |
cester | -0.056 |
metic | -0.054 |
ignment | -0.054 |
Token | former |
Token ID | 1966 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
PLA | +0.240 |
Occupations | +0.222 |
ORTS | +0.221 |
Mp | +0.220 |
tremend | +0.218 |
Neg logit contributions | |
entric | -0.254 |
orical | -0.241 |
cester | -0.241 |
metic | -0.236 |
ignment | -0.235 |
Token | military |
Token ID | 2422 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
PLA | +2.248 |
Occupations | +2.060 |
ORTS | +2.045 |
Mp | +2.042 |
tremend | +1.957 |
Neg logit contributions | |
entric | -2.529 |
orical | -2.387 |
cester | -2.382 |
metic | -2.339 |
ignment | -2.324 |
Token | and |
Token ID | 290 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
PLA | +0.997 |
Occupations | +0.919 |
ORTS | +0.911 |
Mp | +0.907 |
tremend | +0.891 |
Neg logit contributions | |
entric | -1.043 |
orical | -0.987 |
cester | -0.984 |
metic | -0.964 |
ignment | -0.958 |
Token | intelligence |
Token ID | 4430 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
PLA | +0.576 |
ORTS | +0.535 |
Occupations | +0.535 |
Mp | +0.532 |
tremend | +0.523 |
Neg logit contributions | |
entric | -0.494 |
orical | -0.465 |
cester | -0.464 |
metic | -0.455 |
ignment | -0.451 |
Token | professionals |
Token ID | 11153 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
PLA | +1.544 |
Occupations | +1.427 |
ORTS | +1.413 |
Mp | +1.406 |
tremend | +1.371 |
Neg logit contributions | |
entric | -1.625 |
orical | -1.536 |
cester | -1.525 |
metic | -1.486 |
ignment | -1.483 |
Token | . |
Token ID | 13 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
PLA | +2.377 |
ORTS | +2.179 |
Occupations | +2.172 |
Mp | +2.163 |
tremend | +2.120 |
Neg logit contributions | |
entric | -2.639 |
orical | -2.504 |
cester | -2.495 |
metic | -2.444 |
ignment | -2.429 |
Token | the |
Token ID | 262 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
entric | +0.336 |
orical | +0.318 |
cester | +0.317 |
metic | +0.311 |
ignment | +0.308 |
Neg logit contributions | |
PLA | -0.350 |
Occupations | -0.324 |
ORTS | -0.324 |
Mp | -0.322 |
tremend | -0.318 |
Token | current |
Token ID | 1459 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
PLA | +0.212 |
Occupations | +0.199 |
ORTS | +0.198 |
Mp | +0.196 |
tremend | +0.195 |
Neg logit contributions | |
entric | -0.180 |
orical | -0.169 |
cester | -0.169 |
metic | -0.166 |
ignment | -0.162 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
entric | +0.081 |
orical | +0.077 |
cester | +0.076 |
metic | +0.075 |
ignment | +0.074 |
Neg logit contributions | |
PLA | -0.084 |
Occupations | -0.078 |
ORTS | -0.077 |
Mp | -0.077 |
tremend | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
entric | +1.710 |
cester | +1.611 |
orical | +1.607 |
ignment | +1.569 |
metic | +1.561 |
Neg logit contributions | |
PLA | -1.975 |
Occupations | -1.833 |
ORTS | -1.827 |
tremend | -1.819 |
Mp | -1.812 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
PLA | +0.273 |
Occupations | +0.247 |
ORTS | +0.247 |
Mp | +0.246 |
tremend | +0.237 |
Neg logit contributions | |
entric | -0.395 |
orical | -0.377 |
cester | -0.376 |
metic | -0.370 |
ignment | -0.367 |
Token | - |
Token ID | 12 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
PLA | +0.436 |
ORTS | +0.405 |
Mp | +0.405 |
Occupations | +0.404 |
tremend | +0.398 |
Neg logit contributions | |
entric | -0.367 |
orical | -0.347 |
cester | -0.346 |
metic | -0.341 |
ignment | -0.335 |
Token | liter |
Token ID | 17201 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
PLA | +1.496 |
Mp | +1.390 |
ORTS | +1.365 |
Occupations | +1.352 |
tremend | +1.318 |
Neg logit contributions | |
entric | -1.767 |
orical | -1.677 |
cester | -1.668 |
metic | -1.661 |
ignment | -1.630 |
Token | V |
Token ID | 569 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
entric | +1.913 |
orical | +1.805 |
cester | +1.793 |
metic | +1.756 |
ignment | +1.747 |
Neg logit contributions | |
PLA | -2.268 |
Occupations | -2.105 |
ORTS | -2.099 |
Mp | -2.094 |
tremend | -2.072 |
Token | 8 |
Token ID | 23 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
entric | +0.525 |
orical | +0.501 |
cester | +0.501 |
metic | +0.493 |
ignment | +0.489 |
Neg logit contributions | |
PLA | -0.361 |
ORTS | -0.326 |
Occupations | -0.326 |
Mp | -0.324 |
tremend | -0.319 |
Token | , |
Token ID | 11 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
PLA | +0.233 |
ORTS | +0.215 |
Occupations | +0.214 |
Mp | +0.213 |
tremend | +0.210 |
Neg logit contributions | |
entric | -0.241 |
orical | -0.230 |
cester | -0.229 |
metic | -0.225 |
ignment | -0.223 |
Token | which |
Token ID | 543 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
PLA | +0.147 |
Occupations | +0.136 |
ORTS | +0.136 |
Mp | +0.135 |
tremend | +0.133 |
Neg logit contributions | |
entric | -0.152 |
orical | -0.144 |
cester | -0.143 |
metic | -0.141 |
ignment | -0.139 |
Token | osh |
Token ID | 3768 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
PLA | +3.265 |
Occupations | +2.991 |
ORTS | +2.963 |
Mp | +2.961 |
tremend | +2.863 |
Neg logit contributions | |
entric | -2.873 |
cester | -2.839 |
orical | -2.736 |
metic | -2.730 |
ignment | -2.631 |
Token | an |
Token ID | 272 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
entric | +1.447 |
orical | +1.338 |
cester | +1.322 |
metic | +1.300 |
ignment | +1.283 |
Neg logit contributions | |
PLA | -2.495 |
Occupations | -2.352 |
ORTS | -2.351 |
Mp | -2.344 |
tremend | -2.327 |
Token | Mining |
Token ID | 29269 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
entric | +1.266 |
orical | +1.202 |
cester | +1.198 |
metic | +1.177 |
ignment | +1.169 |
Neg logit contributions | |
PLA | -1.156 |
Occupations | -1.064 |
ORTS | -1.063 |
Mp | -1.057 |
tremend | -1.046 |
Token | Co |
Token ID | 1766 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
PLA | +2.306 |
Occupations | +2.145 |
Mp | +2.104 |
ORTS | +2.091 |
Runner | +2.002 |
Neg logit contributions | |
entric | -2.583 |
cester | -2.455 |
orical | -2.451 |
metic | -2.419 |
ignment | -2.380 |
Token | Ltd |
Token ID | 12052 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
entric | +1.834 |
orical | +1.727 |
cester | +1.720 |
metic | +1.697 |
ignment | +1.678 |
Neg logit contributions | |
PLA | -2.127 |
ORTS | -1.985 |
Occupations | -1.980 |
Mp | -1.978 |
tremend | -1.971 |
Token | , |
Token ID | 11 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
entric | +1.507 |
orical | +1.423 |
cester | +1.417 |
metic | +1.395 |
ignment | +1.381 |
Neg logit contributions | |
PLA | -1.739 |
Occupations | -1.618 |
ORTS | -1.615 |
Mp | -1.613 |
tremend | -1.601 |
Token | past |
Token ID | 1613 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
PLA | +0.379 |
Occupations | +0.352 |
ORTS | +0.349 |
Mp | +0.349 |
tremend | +0.343 |
Neg logit contributions | |
entric | -0.379 |
orical | -0.358 |
cester | -0.358 |
metic | -0.350 |
ignment | -0.348 |
Token | the |
Token ID | 262 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
entric | +0.167 |
orical | +0.159 |
cester | +0.158 |
metic | +0.155 |
ignment | +0.154 |
Neg logit contributions | |
PLA | -0.158 |
Occupations | -0.146 |
ORTS | -0.145 |
Mp | -0.145 |
tremend | -0.143 |
Token | ram |
Token ID | 15770 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
PLA | +0.678 |
Occupations | +0.624 |
ORTS | +0.622 |
Mp | +0.621 |
tremend | +0.611 |
Neg logit contributions | |
entric | -0.755 |
orical | -0.718 |
cester | -0.716 |
metic | -0.704 |
ignment | -0.696 |
Token | sh |
Token ID | 1477 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
PLA | +2.468 |
Mp | +2.308 |
ORTS | +2.307 |
Occupations | +2.300 |
tremend | +2.274 |
Neg logit contributions | |
entric | -1.581 |
cester | -1.465 |
orical | -1.464 |
metic | -1.440 |
ignment | -1.408 |
Token | ackle |
Token ID | 20523 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
PLA | +0.298 |
ORTS | +0.264 |
Occupations | +0.263 |
Mp | +0.261 |
tremend | +0.256 |
Neg logit contributions | |
entric | -0.582 |
orical | -0.559 |
cester | -0.558 |
metic | -0.550 |
ignment | -0.547 |
Token | my |
Token ID | 616 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
PLA | +0.940 |
Occupations | +0.867 |
ORTS | +0.863 |
Mp | +0.858 |
tremend | +0.849 |
Neg logit contributions | |
entric | -1.077 |
orical | -1.022 |
cester | -1.021 |
metic | -1.005 |
ignment | -0.994 |
Token | HS |
Token ID | 18070 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
entric | +1.008 |
orical | +0.954 |
cester | +0.950 |
metic | +0.936 |
ignment | +0.926 |
Neg logit contributions | |
PLA | -1.095 |
Occupations | -1.011 |
ORTS | -1.010 |
Mp | -1.005 |
tremend | -0.995 |
Token | feels |
Token ID | 5300 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
PLA | +2.313 |
ORTS | +2.131 |
Occupations | +2.129 |
Mp | +2.111 |
tremend | +2.083 |
Neg logit contributions | |
entric | -2.599 |
cester | -2.466 |
orical | -2.454 |
metic | -2.416 |
ignment | -2.384 |
Token | like |
Token ID | 588 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
PLA | +1.594 |
ORTS | +1.481 |
Mp | +1.480 |
tremend | +1.470 |
Occupations | +1.467 |
Neg logit contributions | |
entric | -1.477 |
cester | -1.388 |
orical | -1.381 |
metic | -1.350 |
ignment | -1.345 |
Token | we |
Token ID | 356 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
PLA | +0.845 |
Occupations | +0.783 |
ORTS | +0.780 |
Mp | +0.775 |
tremend | +0.771 |
Neg logit contributions | |
entric | -0.799 |
cester | -0.756 |
orical | -0.753 |
metic | -0.737 |
ignment | -0.731 |
Token | must |
Token ID | 1276 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
PLA | +0.057 |
Occupations | +0.052 |
ORTS | +0.052 |
Mp | +0.052 |
tremend | +0.051 |
Neg logit contributions | |
entric | -0.075 |
orical | -0.071 |
cester | -0.071 |
metic | -0.070 |
ignment | -0.069 |
Token | all |
Token ID | 477 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
PLA | +0.548 |
ORTS | +0.504 |
Occupations | +0.503 |
Mp | +0.501 |
tremend | +0.495 |
Neg logit contributions | |
entric | -0.575 |
orical | -0.547 |
cester | -0.546 |
metic | -0.535 |
ignment | -0.531 |
Token | go |
Token ID | 467 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
entric | +0.750 |
orical | +0.712 |
cester | +0.711 |
metic | +0.697 |
ignment | +0.693 |
Neg logit contributions | |
PLA | -0.708 |
Occupations | -0.652 |
ORTS | -0.650 |
Mp | -0.647 |
tremend | -0.640 |
Token | at |
Token ID | 379 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
entric | +0.271 |
orical | +0.256 |
cester | +0.255 |
metic | +0.250 |
ignment | +0.248 |
Neg logit contributions | |
PLA | -0.301 |
Occupations | -0.279 |
ORTS | -0.278 |
Mp | -0.277 |
tremend | -0.274 |
Token | the |
Token ID | 262 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
entric | +1.658 |
orical | +1.557 |
cester | +1.550 |
metic | +1.521 |
ignment | +1.510 |
Neg logit contributions | |
PLA | -2.212 |
Occupations | -2.061 |
ORTS | -2.057 |
Mp | -2.045 |
tremend | -2.026 |
Token | same |
Token ID | 976 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
entric | +0.048 |
orical | +0.044 |
cester | +0.044 |
metic | +0.043 |
ignment | +0.042 |
Neg logit contributions | |
PLA | -0.083 |
Occupations | -0.078 |
ORTS | -0.078 |
Mp | -0.077 |
tremend | -0.077 |
Token | ea |
Token ID | 18213 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
entric | +0.988 |
orical | +0.939 |
cester | +0.937 |
metic | +0.920 |
ignment | +0.914 |
Neg logit contributions | |
PLA | -0.870 |
Occupations | -0.799 |
ORTS | -0.798 |
Mp | -0.793 |
tremend | -0.784 |
Token | Community |
Token ID | 8108 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
entric | +0.701 |
cester | +0.665 |
orical | +0.665 |
metic | +0.652 |
ignment | +0.651 |
Neg logit contributions | |
PLA | -0.632 |
ORTS | -0.576 |
Occupations | -0.575 |
tremend | -0.574 |
Mp | -0.573 |
Token | Connect |
Token ID | 8113 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
PLA | +1.451 |
Occupations | +1.334 |
ORTS | +1.323 |
Mp | +1.320 |
tremend | +1.270 |
Neg logit contributions | |
entric | -2.011 |
orical | -1.933 |
cester | -1.918 |
metic | -1.893 |
ignment | -1.867 |
Token | ions |
Token ID | 507 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
entric | +0.996 |
orical | +0.938 |
cester | +0.934 |
metic | +0.914 |
ignment | +0.910 |
Neg logit contributions | |
PLA | -1.210 |
Occupations | -1.123 |
ORTS | -1.118 |
tremend | -1.113 |
Mp | -1.112 |
Token | provides |
Token ID | 3769 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
entric | +0.584 |
cester | +0.553 |
orical | +0.553 |
metic | +0.543 |
ignment | +0.542 |
Neg logit contributions | |
PLA | -0.540 |
ORTS | -0.493 |
Occupations | -0.493 |
tremend | -0.491 |
Mp | -0.490 |
Token | emergency |
Token ID | 6334 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
PLA | +1.816 |
Occupations | +1.708 |
ORTS | +1.697 |
Mp | +1.696 |
tremend | +1.657 |
Neg logit contributions | |
entric | -1.777 |
orical | -1.686 |
cester | -1.666 |
metic | -1.620 |
ignment | -1.608 |
Token | relief |
Token ID | 8259 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
PLA | +2.856 |
Mp | +2.698 |
ORTS | +2.683 |
Occupations | +2.678 |
AGES | +2.567 |
Neg logit contributions | |
entric | -3.071 |
orical | -2.932 |
cester | -2.898 |
metic | -2.816 |
ulty | -2.770 |
Token | to |
Token ID | 284 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
PLA | +2.033 |
ORTS | +1.896 |
Occupations | +1.891 |
Mp | +1.883 |
tremend | +1.827 |
Neg logit contributions | |
entric | -2.020 |
orical | -1.923 |
cester | -1.910 |
metic | -1.845 |
ignment | -1.824 |
Token | those |
Token ID | 883 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
entric | +0.058 |
orical | +0.055 |
cester | +0.055 |
metic | +0.054 |
ignment | +0.054 |
Neg logit contributions | |
PLA | -0.052 |
Occupations | -0.047 |
ORTS | -0.047 |
Mp | -0.047 |
tremend | -0.047 |
Token | struggling |
Token ID | 9648 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
PLA | +1.568 |
Occupations | +1.446 |
Mp | +1.445 |
ORTS | +1.438 |
tremend | +1.416 |
Neg logit contributions | |
entric | -1.921 |
orical | -1.831 |
cester | -1.820 |
ignment | -1.781 |
metic | -1.776 |
Token | , |
Token ID | 11 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
PLA | +3.128 |
Occupations | +2.897 |
Mp | +2.896 |
tremend | +2.876 |
ORTS | +2.863 |
Neg logit contributions | |
entric | -3.741 |
orical | -3.574 |
cester | -3.535 |
ignment | -3.461 |
metic | -3.458 |
Token | Services |
Token ID | 6168 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
PLA | +1.168 |
Occupations | +1.072 |
Mp | +1.049 |
ORTS | +1.023 |
AGES | +0.991 |
Neg logit contributions | |
entric | -2.161 |
cester | -2.081 |
orical | -2.061 |
metic | -2.049 |
ignment | -2.032 |
Token | . |
Token ID | 764 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
PLA | +0.461 |
Occupations | +0.426 |
ORTS | +0.426 |
Mp | +0.424 |
tremend | +0.420 |
Neg logit contributions | |
entric | -0.427 |
orical | -0.403 |
cester | -0.402 |
metic | -0.394 |
ignment | -0.391 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
PLA | +0.923 |
Occupations | +0.851 |
ORTS | +0.845 |
Mp | +0.843 |
AGES | +0.807 |
Neg logit contributions | |
entric | -1.012 |
orical | -0.953 |
cester | -0.949 |
metic | -0.937 |
ignment | -0.926 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
PLA | +0.730 |
Mp | +0.670 |
ORTS | +0.669 |
Occupations | +0.668 |
00200000 | +0.639 |
Neg logit contributions | |
entric | -0.812 |
orical | -0.765 |
cester | -0.765 |
metic | -0.749 |
ignment | -0.740 |
Token | Google |
Token ID | 11708 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
PLA | +1.000 |
Mp | +0.923 |
ORTS | +0.915 |
Occupations | +0.906 |
AGES | +0.884 |
Neg logit contributions | |
entric | -0.845 |
cester | -0.789 |
orical | -0.787 |
metic | -0.771 |
ignment | -0.766 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
PLA | +1.479 |
Occupations | +1.366 |
ORTS | +1.344 |
Mp | +1.323 |
AGES | +1.277 |
Neg logit contributions | |
entric | -2.067 |
cester | -1.957 |
orical | -1.957 |
metic | -1.933 |
ulty | -1.889 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
PLA | +3.903 |
ORTS | +3.626 |
Occupations | +3.587 |
Mp | +3.516 |
tremend | +3.465 |
Neg logit contributions | |
entric | -4.678 |
cester | -4.492 |
orical | -4.447 |
metic | -4.378 |
ignment | -4.359 |
Token |
|
Token ID | 198 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
PLA | +1.032 |
Mp | +0.946 |
ORTS | +0.944 |
Occupations | +0.942 |
00200000 | +0.902 |
Neg logit contributions | |
entric | -1.171 |
orical | -1.103 |
cester | -1.102 |
metic | -1.079 |
ignment | -1.064 |
Token | Re |
Token ID | 3041 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
PLA | +1.141 |
Mp | +1.035 |
ORTS | +1.025 |
Occupations | +1.018 |
AGES | +0.969 |
Neg logit contributions | |
entric | -1.334 |
cester | -1.259 |
orical | -1.253 |
metic | -1.233 |
ignment | -1.232 |
Token | yn |
Token ID | 2047 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
PLA | +0.215 |
ORTS | +0.200 |
Occupations | +0.200 |
Mp | +0.200 |
tremend | +0.195 |
Neg logit contributions | |
entric | -0.168 |
orical | -0.158 |
cester | -0.157 |
metic | -0.153 |
ignment | -0.152 |
Token | olds |
Token ID | 10119 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
PLA | +0.470 |
Occupations | +0.428 |
ORTS | +0.428 |
Mp | +0.426 |
tremend | +0.417 |
Neg logit contributions | |
entric | -0.600 |
orical | -0.571 |
cester | -0.570 |
metic | -0.561 |
ignment | -0.556 |
Token | had |
Token ID | 550 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
entric | +0.892 |
orical | +0.847 |
cester | +0.844 |
metic | +0.830 |
ignment | +0.827 |
Neg logit contributions | |
PLA | -0.833 |
ORTS | -0.766 |
Occupations | -0.764 |
Mp | -0.760 |
tremend | -0.754 |
Token | earlier |
Token ID | 2961 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
entric | +1.073 |
orical | +1.018 |
cester | +1.016 |
metic | +0.996 |
ignment | +0.987 |
Neg logit contributions | |
PLA | -1.014 |
Occupations | -0.936 |
ORTS | -0.934 |
Mp | -0.930 |
tremend | -0.917 |
Token | issued |
Token ID | 4884 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
PLA | +1.940 |
Occupations | +1.820 |
ORTS | +1.800 |
Mp | +1.789 |
tremend | +1.747 |
Neg logit contributions | |
entric | -2.144 |
cester | -2.032 |
orical | -2.031 |
metic | -1.967 |
ignment | -1.927 |
Token | notices |
Token ID | 19748 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
entric | +0.060 |
orical | +0.057 |
cester | +0.057 |
metic | +0.056 |
ignment | +0.055 |
Neg logit contributions | |
PLA | -0.060 |
Occupations | -0.055 |
ORTS | -0.055 |
Mp | -0.055 |
tremend | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
entric | +0.882 |
orical | +0.836 |
cester | +0.836 |
metic | +0.821 |
ignment | +0.818 |
Neg logit contributions | |
PLA | -0.870 |
ORTS | -0.803 |
Occupations | -0.802 |
Mp | -0.795 |
tremend | -0.792 |
Token | sought |
Token ID | 7194 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
PLA | +0.510 |
Occupations | +0.472 |
ORTS | +0.471 |
Mp | +0.470 |
tremend | +0.461 |
Neg logit contributions | |
entric | -0.499 |
orical | -0.473 |
cester | -0.473 |
metic | -0.463 |
ignment | -0.457 |
Token | response |
Token ID | 2882 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
PLA | +4.650 |
Occupations | +4.322 |
Mp | +4.320 |
ORTS | +4.299 |
00200000 | +4.152 |
Neg logit contributions | |
entric | -4.812 |
cester | -4.558 |
orical | -4.551 |
metic | -4.373 |
ulty | -4.356 |
Token | within |
Token ID | 1626 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
PLA | +1.725 |
ORTS | +1.577 |
Occupations | +1.571 |
Mp | +1.570 |
tremend | +1.517 |
Neg logit contributions | |
entric | -2.050 |
cester | -1.948 |
orical | -1.943 |
metic | -1.884 |
ignment | -1.872 |
Token | four |
Token ID | 1440 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
PLA | +1.796 |
Occupations | +1.654 |
ORTS | +1.644 |
Mp | +1.634 |
tremend | +1.607 |
Neg logit contributions | |
entric | -1.863 |
orical | -1.768 |
cester | -1.754 |
metic | -1.705 |
ignment | -1.684 |
Token | weeks |
Token ID | 2745 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
entric | +1.089 |
orical | +1.025 |
cester | +1.024 |
metic | +1.004 |
ignment | +0.996 |
Neg logit contributions | |
PLA | -1.358 |
Occupations | -1.267 |
ORTS | -1.265 |
Mp | -1.257 |
tremend | -1.247 |
Token | from |
Token ID | 422 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
entric | +1.438 |
orical | +1.360 |
cester | +1.354 |
metic | +1.334 |
ignment | +1.328 |
Neg logit contributions | |
PLA | -1.492 |
Occupations | -1.380 |
ORTS | -1.378 |
Mp | -1.368 |
tremend | -1.364 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
PLA | +0.279 |
Occupations | +0.258 |
ORTS | +0.257 |
Mp | +0.256 |
tremend | +0.251 |
Neg logit contributions | |
entric | -0.292 |
orical | -0.277 |
cester | -0.276 |
metic | -0.271 |
ignment | -0.269 |
Token | Ill |
Token ID | 21478 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
PLA | +0.268 |
Mp | +0.244 |
ORTS | +0.244 |
Occupations | +0.243 |
tremend | +0.236 |
Neg logit contributions | |
entric | -0.295 |
orical | -0.279 |
cester | -0.279 |
metic | -0.273 |
ignment | -0.272 |
Token | ustration |
Token ID | 44027 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
entric | +0.590 |
orical | +0.559 |
cester | +0.558 |
metic | +0.547 |
ignment | +0.544 |
Neg logit contributions | |
PLA | -0.573 |
Occupations | -0.528 |
ORTS | -0.528 |
Mp | -0.525 |
tremend | -0.519 |
Token | by |
Token ID | 416 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
PLA | +2.163 |
Occupations | +2.014 |
ORTS | +2.006 |
Mp | +1.990 |
tremend | +1.959 |
Neg logit contributions | |
entric | -2.159 |
orical | -2.043 |
cester | -2.040 |
metic | -1.998 |
ignment | -1.981 |
Token | Allison |
Token ID | 33461 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
entric | +0.389 |
orical | +0.370 |
cester | +0.369 |
metic | +0.363 |
ignment | +0.361 |
Neg logit contributions | |
PLA | -0.336 |
Occupations | -0.307 |
ORTS | -0.307 |
Mp | -0.306 |
tremend | -0.302 |
Token | Br |
Token ID | 1709 |
Feature activation | -7.61e+00 |
Pos logit contributions | |
PLA | +0.759 |
Occupations | +0.702 |
ORTS | +0.697 |
Mp | +0.696 |
tremend | +0.678 |
Neg logit contributions | |
entric | -0.878 |
orical | -0.834 |
cester | -0.833 |
metic | -0.820 |
ignment | -0.810 |
Token | uns |
Token ID | 13271 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
PLA | +5.628 |
Mp | +5.178 |
ascal | +5.172 |
Occupations | +5.152 |
ORTS | +5.108 |
Neg logit contributions | |
entric | -5.061 |
cester | -4.844 |
orical | -4.811 |
metic | -4.710 |
ignment | -4.517 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
PLA | +1.043 |
Occupations | +0.963 |
ORTS | +0.959 |
Mp | +0.956 |
tremend | +0.935 |
Neg logit contributions | |
entric | -0.993 |
orical | -0.942 |
cester | -0.937 |
metic | -0.916 |
ignment | -0.910 |
Token |
|
Token ID | 198 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
entric | +0.142 |
orical | +0.134 |
cester | +0.134 |
metic | +0.131 |
ignment | +0.130 |
Neg logit contributions | |
PLA | -0.136 |
ORTS | -0.125 |
Occupations | -0.125 |
Mp | -0.125 |
00200000 | -0.119 |
Token | In |
Token ID | 818 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
PLA | +0.035 |
Mp | +0.032 |
ORTS | +0.032 |
Occupations | +0.032 |
tremend | +0.030 |
Neg logit contributions | |
entric | -0.035 |
orical | -0.033 |
cester | -0.033 |
metic | -0.033 |
ignment | -0.032 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
PLA | +1.334 |
Occupations | +1.232 |
ORTS | +1.224 |
Mp | +1.217 |
tremend | +1.198 |
Neg logit contributions | |
entric | -1.497 |
orical | -1.416 |
cester | -1.411 |
metic | -1.383 |
ignment | -1.371 |
Token | about |
Token ID | 546 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
entric | +1.185 |
orical | +1.127 |
cester | +1.122 |
metic | +1.104 |
ignment | +1.098 |
Neg logit contributions | |
PLA | -1.046 |
Occupations | -0.954 |
ORTS | -0.953 |
Mp | -0.950 |
tremend | -0.940 |
Token | health |
Token ID | 1535 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
entric | +1.586 |
orical | +1.502 |
cester | +1.495 |
metic | +1.475 |
ignment | +1.465 |
Neg logit contributions | |
PLA | -1.663 |
ORTS | -1.526 |
Occupations | -1.525 |
Mp | -1.523 |
tremend | -1.505 |
Token | care |
Token ID | 1337 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
PLA | +2.158 |
Occupations | +2.033 |
ORTS | +2.016 |
tremend | +1.985 |
Mp | +1.974 |
Neg logit contributions | |
entric | -2.267 |
orical | -2.183 |
cester | -2.167 |
metic | -2.094 |
ignment | -2.076 |
Token | from |
Token ID | 422 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
PLA | +0.119 |
Occupations | +0.111 |
ORTS | +0.110 |
Mp | +0.110 |
tremend | +0.109 |
Neg logit contributions | |
entric | -0.105 |
orical | -0.100 |
cester | -0.100 |
metic | -0.097 |
ignment | -0.096 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
PLA | +0.188 |
Occupations | +0.174 |
ORTS | +0.173 |
Mp | +0.172 |
tremend | +0.170 |
Neg logit contributions | |
entric | -0.207 |
orical | -0.196 |
cester | -0.196 |
metic | -0.192 |
ignment | -0.191 |
Token | nurse |
Token ID | 15849 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
PLA | +0.121 |
Occupations | +0.111 |
ORTS | +0.111 |
Mp | +0.111 |
tremend | +0.109 |
Neg logit contributions | |
entric | -0.121 |
orical | -0.114 |
cester | -0.114 |
metic | -0.112 |
ignment | -0.111 |
Token | � |
Token ID | 447 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
PLA | +3.894 |
Occupations | +3.657 |
Mp | +3.637 |
ORTS | +3.624 |
tremend | +3.539 |
Neg logit contributions | |
entric | -4.905 |
orical | -4.758 |
cester | -4.697 |
metic | -4.515 |
ignment | -4.512 |
Token | � |
Token ID | 247 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
PLA | +0.809 |
Occupations | +0.754 |
ORTS | +0.750 |
Mp | +0.749 |
tremend | +0.727 |
Neg logit contributions | |
entric | -0.812 |
cester | -0.773 |
orical | -0.758 |
metic | -0.749 |
ignment | -0.742 |
Token | s |
Token ID | 82 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
PLA | +0.112 |
Occupations | +0.104 |
ORTS | +0.104 |
Mp | +0.104 |
tremend | +0.102 |
Neg logit contributions | |
entric | -0.099 |
orical | -0.093 |
cester | -0.093 |
metic | -0.091 |
ignment | -0.090 |
Token | - |
Token ID | 12 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
entric | +0.839 |
orical | +0.785 |
cester | +0.782 |
metic | +0.766 |
ignment | +0.758 |
Neg logit contributions | |
PLA | -1.225 |
Occupations | -1.144 |
ORTS | -1.144 |
Mp | -1.138 |
tremend | -1.128 |
Token | eye |
Token ID | 25379 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
PLA | +1.541 |
Occupations | +1.423 |
Mp | +1.420 |
ORTS | +1.413 |
tremend | +1.384 |
Neg logit contributions | |
entric | -1.463 |
orical | -1.394 |
cester | -1.390 |
ignment | -1.351 |
metic | -1.348 |
Token | NASA |
Token ID | 8884 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
entric | +1.834 |
orical | +1.750 |
cester | +1.736 |
metic | +1.706 |
ignment | +1.705 |
Neg logit contributions | |
PLA | -1.586 |
ORTS | -1.449 |
Occupations | -1.444 |
Mp | -1.438 |
tremend | -1.429 |
Token | Goddard |
Token ID | 47386 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
PLA | +2.929 |
Occupations | +2.681 |
ORTS | +2.657 |
Mp | +2.638 |
tremend | +2.573 |
Neg logit contributions | |
entric | -3.700 |
cester | -3.563 |
orical | -3.544 |
metic | -3.505 |
ignment | -3.454 |
Token | glac |
Token ID | 25169 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
PLA | +0.769 |
Occupations | +0.704 |
ORTS | +0.702 |
Mp | +0.697 |
tremend | +0.686 |
Neg logit contributions | |
entric | -0.953 |
orical | -0.911 |
cester | -0.907 |
metic | -0.893 |
ignment | -0.884 |
Token | iologist |
Token ID | 31599 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
entric | +3.376 |
orical | +3.245 |
cester | +3.219 |
metic | +3.171 |
ignment | +3.169 |
Neg logit contributions | |
PLA | -2.131 |
ORTS | -1.913 |
Occupations | -1.904 |
tremend | -1.891 |
Mp | -1.890 |
Token | Kelly |
Token ID | 9077 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
PLA | +2.096 |
Occupations | +1.956 |
ORTS | +1.936 |
Mp | +1.933 |
tremend | +1.844 |
Neg logit contributions | |
entric | -2.473 |
cester | -2.351 |
orical | -2.347 |
metic | -2.304 |
ignment | -2.272 |
Token | Br |
Token ID | 1709 |
Feature activation | -8.22e+00 |
Pos logit contributions | |
entric | +2.211 |
orical | +2.108 |
cester | +2.102 |
metic | +2.057 |
ignment | +2.055 |
Neg logit contributions | |
PLA | -1.956 |
tremend | -1.789 |
ORTS | -1.776 |
Occupations | -1.764 |
Mp | -1.762 |
Token | unt |
Token ID | 2797 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
PLA | +6.036 |
ascal | +5.607 |
Mp | +5.595 |
Occupations | +5.563 |
ORTS | +5.523 |
Neg logit contributions | |
entric | -5.379 |
cester | -5.123 |
orical | -5.109 |
metic | -5.008 |
ignment | -4.792 |
Token | . |
Token ID | 13 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
PLA | +1.766 |
Occupations | +1.633 |
ORTS | +1.633 |
Mp | +1.632 |
tremend | +1.601 |
Neg logit contributions | |
entric | -1.657 |
orical | -1.561 |
cester | -1.558 |
metic | -1.529 |
ignment | -1.512 |
Token | This |
Token ID | 770 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
PLA | +0.228 |
Occupations | +0.210 |
ORTS | +0.209 |
Mp | +0.209 |
tremend | +0.204 |
Neg logit contributions | |
entric | -0.247 |
orical | -0.234 |
cester | -0.233 |
metic | -0.229 |
ignment | -0.227 |
Token | year |
Token ID | 614 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
entric | +0.613 |
orical | +0.580 |
cester | +0.579 |
metic | +0.568 |
ignment | +0.563 |
Neg logit contributions | |
PLA | -0.615 |
Occupations | -0.568 |
ORTS | -0.567 |
Mp | -0.565 |
tremend | -0.558 |
Token | � |
Token ID | 447 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
entric | +0.857 |
orical | +0.815 |
cester | +0.812 |
metic | +0.797 |
ignment | +0.793 |
Neg logit contributions | |
PLA | -0.771 |
Occupations | -0.709 |
ORTS | -0.708 |
Mp | -0.704 |
tremend | -0.697 |