Token | � |
Token ID | 251 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
zona | +1.362 |
RESULTS | +1.246 |
haar | +1.180 |
bley | +1.152 |
atos | +1.124 |
Neg logit contributions | |
raq | -0.854 |
hai | -0.809 |
Wast | -0.714 |
Wars | -0.677 |
Synd | -0.668 |
Token | by |
Token ID | 416 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
zona | +1.666 |
RESULTS | +1.505 |
haar | +1.417 |
bley | +1.387 |
atos | +1.350 |
Neg logit contributions | |
raq | -1.374 |
hai | -1.288 |
Wast | -1.171 |
Wars | -1.112 |
fronts | -1.102 |
Token | R |
Token ID | 371 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
zona | +3.420 |
RESULTS | +3.085 |
haar | +2.893 |
bley | +2.839 |
atos | +2.776 |
Neg logit contributions | |
raq | -2.879 |
hai | -2.690 |
Wast | -2.404 |
Wars | -2.314 |
fronts | -2.279 |
Token | yo |
Token ID | 8226 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
zona | +8.281 |
RESULTS | +7.349 |
haar | +6.901 |
bley | +6.889 |
atos | +6.728 |
Neg logit contributions | |
raq | -6.147 |
hai | -5.832 |
Wast | -5.463 |
Wars | -5.142 |
fronts | -5.066 |
Token | ( |
Token ID | 357 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
zona | +2.740 |
RESULTS | +2.441 |
haar | +2.311 |
bley | +2.244 |
atos | +2.175 |
Neg logit contributions | |
raq | -2.468 |
hai | -2.336 |
Wast | -2.114 |
Wars | -2.030 |
fronts | -2.018 |
Token | Super |
Token ID | 12442 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
zona | +1.778 |
RESULTS | +1.613 |
haar | +1.505 |
bley | +1.473 |
atos | +1.437 |
Neg logit contributions | |
raq | -1.459 |
hai | -1.375 |
Wast | -1.252 |
fronts | -1.177 |
Wars | -1.174 |
Token | cell |
Token ID | 3846 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
zona | +13.712 |
RESULTS | +12.271 |
haar | +11.436 |
atos | +11.259 |
bley | +11.150 |
Neg logit contributions | |
raq | -10.382 |
hai | -9.920 |
Wast | -9.173 |
fronts | -8.708 |
obar | -8.550 |
Token | ). |
Token ID | 737 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
zona | +2.570 |
RESULTS | +2.300 |
haar | +2.159 |
bley | +2.095 |
atos | +2.077 |
Neg logit contributions | |
raq | -2.174 |
hai | -2.044 |
Wast | -1.828 |
Wars | -1.743 |
fronts | -1.738 |
Token | Here |
Token ID | 3423 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
zona | +1.657 |
RESULTS | +1.514 |
haar | +1.410 |
bley | +1.377 |
atos | +1.345 |
Neg logit contributions | |
raq | -1.297 |
hai | -1.219 |
Wast | -1.091 |
fronts | -1.037 |
Wars | -1.035 |
Token | � |
Token ID | 447 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
zona | +0.829 |
RESULTS | +0.755 |
haar | +0.710 |
bley | +0.697 |
atos | +0.679 |
Neg logit contributions | |
raq | -0.626 |
hai | -0.591 |
Wast | -0.529 |
Wars | -0.503 |
fronts | -0.495 |
Token | � |
Token ID | 247 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
raq | +1.162 |
hai | +1.076 |
Wast | +0.926 |
Wars | +0.847 |
fronts | +0.841 |
Neg logit contributions | |
zona | -2.442 |
RESULTS | -2.267 |
haar | -2.126 |
bley | -2.104 |
atos | -2.062 |
Token | store |
Token ID | 3650 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
raq | +1.984 |
hai | +1.864 |
Wast | +1.684 |
Synd | +1.560 |
fronts | +1.552 |
Neg logit contributions | |
zona | -3.082 |
RESULTS | -2.820 |
haar | -2.635 |
bley | -2.594 |
atos | -2.538 |
Token | and |
Token ID | 290 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
raq | +2.439 |
hai | +2.308 |
Wast | +2.083 |
Wars | +1.979 |
fronts | +1.969 |
Neg logit contributions | |
zona | -3.286 |
RESULTS | -3.020 |
haar | -2.806 |
bley | -2.764 |
atos | -2.693 |
Token | a |
Token ID | 257 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
zona | +2.467 |
RESULTS | +2.241 |
haar | +2.100 |
bley | +2.064 |
atos | +2.028 |
Neg logit contributions | |
raq | -1.902 |
hai | -1.797 |
Wast | -1.577 |
Wars | -1.537 |
fronts | -1.490 |
Token | brick |
Token ID | 17214 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
zona | +1.785 |
RESULTS | +1.626 |
haar | +1.533 |
bley | +1.503 |
atos | +1.457 |
Neg logit contributions | |
raq | -1.303 |
hai | -1.241 |
Wast | -1.092 |
Wars | -1.054 |
obar | -1.028 |
Token | - |
Token ID | 12 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
zona | +3.637 |
RESULTS | +3.221 |
haar | +3.086 |
bley | +2.989 |
atos | +2.916 |
Neg logit contributions | |
raq | -3.474 |
hai | -3.327 |
Wast | -3.031 |
Wars | -2.898 |
Synd | -2.883 |
Token | and |
Token ID | 392 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
zona | +6.062 |
RESULTS | +5.244 |
haar | +5.029 |
bley | +4.994 |
atos | +4.783 |
Neg logit contributions | |
raq | -7.725 |
hai | -7.362 |
Wast | -7.149 |
Synd | -6.696 |
Wars | -6.612 |
Token | - |
Token ID | 12 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
zona | +8.138 |
RESULTS | +7.345 |
haar | +7.245 |
bley | +6.900 |
atos | +6.442 |
Neg logit contributions | |
raq | -13.790 |
hai | -13.464 |
�� | -12.405 |
Wars | -12.180 |
�士 | -12.115 |
Token | mort |
Token ID | 30171 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
zona | +6.177 |
haar | +5.933 |
RESULTS | +5.898 |
bley | +5.689 |
cester | +4.916 |
Neg logit contributions | |
hai | -9.572 |
raq | -9.513 |
sugg | -9.338 |
Wast | -9.261 |
prominence | -8.839 |
Token | ar |
Token ID | 283 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
zona | +2.068 |
RESULTS | +1.748 |
haar | +1.708 |
bley | +1.635 |
atos | +1.558 |
Neg logit contributions | |
raq | -2.572 |
hai | -2.516 |
Wast | -2.402 |
Synd | -2.348 |
fronts | -2.330 |
Token | retail |
Token ID | 6308 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
zona | +1.377 |
RESULTS | +1.248 |
haar | +1.175 |
bley | +1.155 |
atos | +1.123 |
Neg logit contributions | |
raq | -1.033 |
hai | -0.979 |
Wast | -0.864 |
Wars | -0.836 |
obar | -0.814 |
Token | operation |
Token ID | 4905 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
zona | +0.698 |
RESULTS | +0.630 |
haar | +0.592 |
bley | +0.580 |
atos | +0.565 |
Neg logit contributions | |
raq | -0.540 |
hai | -0.514 |
Wast | -0.457 |
Wars | -0.440 |
Synd | -0.431 |
Token | arn |
Token ID | 1501 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
zona | +3.000 |
RESULTS | +2.632 |
haar | +2.575 |
bley | +2.525 |
atos | +2.476 |
Neg logit contributions | |
raq | -2.508 |
hai | -2.369 |
Wast | -2.198 |
fronts | -2.087 |
Synd | -2.080 |
Token | ieri |
Token ID | 29864 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
zona | +5.190 |
RESULTS | +4.497 |
atos | +4.434 |
haar | +4.385 |
bley | +4.288 |
Neg logit contributions | |
raq | -3.447 |
hai | -3.206 |
Wast | -3.078 |
Synd | -2.895 |
Wars | -2.883 |
Token | ( |
Token ID | 357 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
zona | +1.485 |
RESULTS | +1.340 |
haar | +1.252 |
bley | +1.218 |
atos | +1.192 |
Neg logit contributions | |
raq | -1.306 |
hai | -1.241 |
Wast | -1.116 |
Wars | -1.072 |
fronts | -1.055 |
Token | Ast |
Token ID | 33751 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
zona | +3.196 |
RESULTS | +3.023 |
haar | +2.637 |
atos | +2.615 |
bley | +2.574 |
Neg logit contributions | |
raq | -2.786 |
hai | -2.705 |
Wast | -2.392 |
fronts | -2.325 |
obar | -2.244 |
Token | ana |
Token ID | 2271 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
zona | +5.339 |
RESULTS | +4.886 |
haar | +4.467 |
atos | +4.354 |
bley | +4.329 |
Neg logit contributions | |
raq | -4.448 |
hai | -4.126 |
Wast | -3.852 |
Wars | -3.629 |
fronts | -3.535 |
Token | Pro |
Token ID | 1041 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
zona | +5.376 |
RESULTS | +4.895 |
haar | +4.393 |
bley | +4.225 |
atos | +4.205 |
Neg logit contributions | |
raq | -5.161 |
hai | -4.738 |
Wast | -4.141 |
Wars | -4.100 |
obar | -4.097 |
Token | Team |
Token ID | 4816 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
zona | +5.694 |
RESULTS | +5.078 |
haar | +4.105 |
bes | +3.606 |
Edge | +3.280 |
Neg logit contributions | |
raq | -18.089 |
hai | -16.409 |
obar | -15.465 |
sugg | -14.936 |
Wast | -14.843 |
Token | ) |
Token ID | 8 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
zona | +3.479 |
RESULTS | +3.169 |
haar | +2.895 |
bley | +2.782 |
atos | +2.724 |
Neg logit contributions | |
raq | -3.565 |
hai | -3.396 |
fronts | -3.004 |
Wast | -3.003 |
obar | -2.942 |
Token | s |
Token ID | 264 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
zona | +1.057 |
RESULTS | +0.972 |
haar | +0.914 |
bley | +0.894 |
atos | +0.876 |
Neg logit contributions | |
raq | -0.635 |
hai | -0.595 |
Wast | -0.519 |
Wars | -0.491 |
fronts | -0.481 |
Token | . |
Token ID | 13 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
raq | +0.793 |
hai | +0.753 |
Wast | +0.673 |
Wars | +0.641 |
iles | +0.632 |
Neg logit contributions | |
zona | -1.082 |
RESULTS | -0.980 |
haar | -0.925 |
bley | -0.910 |
iscons | -0.881 |
Token | t |
Token ID | 83 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
raq | +0.560 |
hai | +0.539 |
Wast | +0.496 |
Wars | +0.479 |
Synd | +0.474 |
Neg logit contributions | |
zona | -0.420 |
RESULTS | -0.369 |
haar | -0.337 |
bley | -0.328 |
atos | -0.316 |
Token | add |
Token ID | 751 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
zona | +1.034 |
RESULTS | +0.940 |
haar | +0.881 |
bley | +0.868 |
atos | +0.846 |
Neg logit contributions | |
raq | -0.749 |
hai | -0.709 |
Wast | -0.631 |
Wars | -0.603 |
Synd | -0.592 |
Token | salt |
Token ID | 8268 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
raq | +0.669 |
hai | +0.635 |
Wast | +0.567 |
Wars | +0.539 |
fronts | +0.533 |
Neg logit contributions | |
zona | -0.904 |
RESULTS | -0.823 |
haar | -0.770 |
bley | -0.756 |
atos | -0.736 |
Token | to |
Token ID | 284 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
raq | +1.284 |
hai | +1.217 |
Wast | +1.095 |
Wars | +1.035 |
fronts | +1.028 |
Neg logit contributions | |
zona | -1.712 |
RESULTS | -1.567 |
haar | -1.461 |
bley | -1.432 |
atos | -1.389 |
Token | injury |
Token ID | 5095 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
zona | +7.286 |
RESULTS | +6.374 |
haar | +6.065 |
bley | +5.919 |
atos | +5.829 |
Neg logit contributions | |
raq | -6.512 |
hai | -6.236 |
Wast | -5.560 |
Wars | -5.384 |
arthed | -5.343 |
Token | , |
Token ID | 11 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
zona | +6.825 |
RESULTS | +6.325 |
haar | +5.737 |
bley | +5.725 |
atos | +5.532 |
Neg logit contributions | |
raq | -6.199 |
hai | -6.015 |
Wast | -5.227 |
Wars | -5.219 |
arthed | -5.067 |
Token | Super |
Token ID | 3115 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
zona | +3.204 |
RESULTS | +2.908 |
haar | +2.716 |
bley | +2.668 |
atos | +2.594 |
Neg logit contributions | |
raq | -2.554 |
hai | -2.401 |
Wast | -2.108 |
Wars | -2.065 |
Synd | -2.001 |
Token | also |
Token ID | 635 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
zona | +12.961 |
RESULTS | +11.844 |
haar | +10.930 |
bley | +10.864 |
atos | +10.576 |
Neg logit contributions | |
raq | -9.870 |
hai | -9.491 |
Wast | -8.443 |
fronts | -8.220 |
obar | -8.050 |
Token | been |
Token ID | 587 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
zona | +0.597 |
RESULTS | +0.545 |
haar | +0.512 |
bley | +0.503 |
atos | +0.491 |
Neg logit contributions | |
raq | -0.404 |
hai | -0.380 |
Wast | -0.336 |
Wars | -0.320 |
Synd | -0.314 |
Token | actively |
Token ID | 10630 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
zona | +0.882 |
RESULTS | +0.803 |
haar | +0.750 |
bley | +0.737 |
atos | +0.716 |
Neg logit contributions | |
raq | -0.672 |
hai | -0.635 |
Wast | -0.564 |
Wars | -0.542 |
Synd | -0.530 |
Token | making |
Token ID | 1642 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
zona | +3.782 |
RESULTS | +3.449 |
haar | +3.195 |
bley | +3.139 |
atos | +3.085 |
Neg logit contributions | |
raq | -2.980 |
hai | -2.739 |
Wast | -2.440 |
Wars | -2.404 |
iles | -2.307 |
Token | a |
Token ID | 257 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
zona | +0.602 |
RESULTS | +0.549 |
haar | +0.513 |
bley | +0.504 |
atos | +0.491 |
Neg logit contributions | |
raq | -0.450 |
hai | -0.427 |
Wast | -0.379 |
Wars | -0.362 |
Synd | -0.355 |
Token | image |
Token ID | 2939 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
zona | +2.917 |
RESULTS | +2.520 |
haar | +2.367 |
bley | +2.229 |
atos | +2.165 |
Neg logit contributions | |
raq | -4.060 |
hai | -3.898 |
Wast | -3.548 |
Wars | -3.509 |
Synd | -3.403 |
Token | , |
Token ID | 837 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
zona | +6.711 |
RESULTS | +5.999 |
haar | +5.426 |
atos | +5.075 |
bley | +4.936 |
Neg logit contributions | |
raq | -10.487 |
hai | -10.118 |
facult | -9.454 |
sugg | -9.348 |
fronts | -9.141 |
Token | c |
Token ID | 269 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
zona | +5.300 |
RESULTS | +4.670 |
haar | +4.377 |
atos | +4.166 |
bley | +4.096 |
Neg logit contributions | |
raq | -7.073 |
hai | -6.670 |
Wars | -6.022 |
Wast | -5.975 |
obar | -5.750 |
Token | v |
Token ID | 85 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
zona | +6.424 |
RESULTS | +5.727 |
haar | +5.305 |
atos | +5.234 |
bley | +5.115 |
Neg logit contributions | |
raq | -7.493 |
hai | -6.996 |
Wast | -6.704 |
fronts | -6.670 |
sugg | -6.613 |
Token | 2 |
Token ID | 17 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
zona | +5.788 |
RESULTS | +5.413 |
haar | +4.665 |
atos | +4.579 |
bley | +4.244 |
Neg logit contributions | |
raq | -9.196 |
hai | -8.999 |
sugg | -8.674 |
fronts | -8.454 |
facult | -8.420 |
Token | . |
Token ID | 764 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
zona | +5.885 |
RESULTS | +5.466 |
haar | +4.601 |
atos | +4.470 |
Arbor | +4.285 |
Neg logit contributions | |
raq | -10.231 |
hai | -9.654 |
sugg | -9.236 |
facult | -9.157 |
fronts | -9.132 |
Token | COL |
Token ID | 20444 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
zona | +11.438 |
RESULTS | +9.958 |
haar | +9.531 |
bley | +9.055 |
iscons | +8.799 |
Neg logit contributions | |
raq | -11.539 |
hai | -10.764 |
Synd | -9.458 |
Wars | -9.420 |
Wast | -9.395 |
Token | OR |
Token ID | 1581 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
zona | +5.430 |
RESULTS | +4.885 |
haar | +4.144 |
atos | +3.873 |
bley | +3.849 |
Neg logit contributions | |
hai | -7.599 |
raq | -7.480 |
fronts | -6.979 |
Wast | -6.795 |
sugg | -6.661 |
Token | _ |
Token ID | 62 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
zona | +7.012 |
RESULTS | +6.339 |
haar | +5.533 |
atos | +5.155 |
bley | +5.017 |
Neg logit contributions | |
raq | -9.869 |
hai | -9.840 |
fronts | -9.190 |
facult | -9.149 |
sugg | -9.065 |
Token | B |
Token ID | 33 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
zona | +6.649 |
RESULTS | +6.590 |
haar | +5.349 |
ELF | +5.143 |
VS | +5.130 |
Neg logit contributions | |
raq | -9.525 |
hai | -9.344 |
sugg | -8.759 |
fronts | -8.716 |
Synd | -8.568 |
Token | GR |
Token ID | 10761 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
zona | +3.138 |
RESULTS | +2.864 |
haar | +2.545 |
bley | +2.434 |
atos | +2.323 |
Neg logit contributions | |
raq | -3.968 |
hai | -3.828 |
Wast | -3.551 |
fronts | -3.467 |
Synd | -3.460 |
Token | ( |
Token ID | 7 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
raq | +0.825 |
hai | +0.782 |
Wast | +0.694 |
Wars | +0.664 |
iles | +0.648 |
Neg logit contributions | |
zona | -1.206 |
RESULTS | -1.101 |
haar | -1.029 |
bley | -1.016 |
iscons | -0.987 |
Token | image |
Token ID | 9060 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
zona | +6.424 |
RESULTS | +5.608 |
haar | +5.323 |
bley | +5.083 |
atos | +5.046 |
Neg logit contributions | |
raq | -6.507 |
hai | -6.153 |
Wast | -5.914 |
Synd | -5.697 |
Wars | -5.539 |
Token | , |
Token ID | 11 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
zona | +6.715 |
RESULTS | +6.060 |
haar | +5.502 |
bley | +5.313 |
atos | +5.214 |
Neg logit contributions | |
raq | -8.500 |
hai | -8.220 |
Wast | -7.492 |
Synd | -7.092 |
sugg | -7.074 |
Token | c |
Token ID | 269 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
zona | +7.836 |
RESULTS | +6.788 |
haar | +6.610 |
bley | +6.308 |
atos | +6.276 |
Neg logit contributions | |
raq | -6.472 |
hai | -5.910 |
Wast | -5.262 |
Wars | -5.206 |
obar | -4.985 |
Token | v |
Token ID | 85 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
zona | +5.189 |
RESULTS | +4.615 |
bley | +4.321 |
haar | +4.302 |
atos | +4.184 |
Neg logit contributions | |
raq | -4.935 |
hai | -4.608 |
Wast | -4.342 |
Synd | -4.167 |
Wars | -4.160 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
zona | +6.998 |
RESULTS | +5.968 |
haar | +5.698 |
atos | +5.493 |
bley | +5.410 |
Neg logit contributions | |
raq | -9.259 |
hai | -9.126 |
Wast | -8.789 |
sugg | -8.284 |
fronts | -8.282 |
Token | . |
Token ID | 13 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
zona | +9.036 |
RESULTS | +8.279 |
haar | +7.119 |
VS | +6.805 |
atos | +6.728 |
Neg logit contributions | |
raq | -12.707 |
hai | -12.327 |
sugg | -11.926 |
fronts | -11.726 |
Wast | -11.564 |
Token | COLOR |
Token ID | 46786 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
zona | +8.599 |
RESULTS | +7.805 |
haar | +7.165 |
bley | +6.936 |
atos | +6.660 |
Neg logit contributions | |
raq | -7.831 |
hai | -7.217 |
Wast | -6.995 |
Synd | -6.786 |
fronts | -6.439 |
Token | _ |
Token ID | 62 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
zona | +5.079 |
RESULTS | +4.669 |
haar | +4.142 |
bley | +3.974 |
atos | +3.882 |
Neg logit contributions | |
raq | -5.468 |
hai | -5.399 |
Wast | -4.818 |
Wars | -4.660 |
Synd | -4.649 |
Token | B |
Token ID | 33 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
zona | +2.645 |
RESULTS | +2.455 |
haar | +2.199 |
bley | +2.153 |
atos | +2.094 |
Neg logit contributions | |
raq | -2.516 |
hai | -2.416 |
Wast | -2.183 |
fronts | -2.094 |
Synd | -2.090 |
Token | GR |
Token ID | 10761 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
zona | +0.488 |
RESULTS | +0.439 |
haar | +0.405 |
bley | +0.396 |
atos | +0.378 |
Neg logit contributions | |
raq | -0.527 |
hai | -0.504 |
Wast | -0.460 |
Wars | -0.443 |
Synd | -0.439 |
Token |
|
Token ID | 198 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
zona | +5.210 |
RESULTS | +4.972 |
haar | +4.309 |
atos | +4.197 |
bley | +4.107 |
Neg logit contributions | |
raq | -5.538 |
hai | -5.253 |
sugg | -4.901 |
fronts | -4.782 |
facult | -4.691 |
Token | Weight |
Token ID | 25844 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
zona | +4.830 |
RESULTS | +4.678 |
bley | +3.794 |
haar | +3.763 |
atos | +3.670 |
Neg logit contributions | |
raq | -7.523 |
hai | -6.907 |
Wast | -6.599 |
Synd | -6.461 |
fronts | -6.412 |
Token | : |
Token ID | 25 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
zona | +0.305 |
RESULTS | +0.276 |
haar | +0.257 |
bley | +0.252 |
atos | +0.245 |
Neg logit contributions | |
raq | -0.264 |
hai | -0.250 |
Wast | -0.225 |
Wars | -0.215 |
fronts | -0.214 |
Token | 190 |
Token ID | 19884 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
raq | +2.752 |
hai | +2.584 |
Wast | +2.343 |
Wars | +2.168 |
Synd | +2.154 |
Neg logit contributions | |
zona | -4.549 |
RESULTS | -4.182 |
haar | -3.949 |
bley | -3.871 |
atos | -3.773 |
Token |
|
Token ID | 198 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
zona | +2.239 |
RESULTS | +2.048 |
bley | +1.895 |
haar | +1.887 |
atos | +1.830 |
Neg logit contributions | |
raq | -1.629 |
hai | -1.568 |
Wast | -1.381 |
Wars | -1.310 |
Synd | -1.300 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
zona | +6.867 |
RESULTS | +6.785 |
haar | +5.538 |
atos | +5.492 |
Arbor | +5.390 |
Neg logit contributions | |
raq | -9.386 |
hai | -8.958 |
sugg | -8.920 |
mosqu | -8.737 |
facult | -8.551 |
Token | Birth |
Token ID | 38480 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
RESULTS | +11.981 |
zona | +11.293 |
AMS | +10.068 |
VS | +10.047 |
atos | +9.855 |
Neg logit contributions | |
raq | -9.390 |
sugg | -9.192 |
Wast | -8.655 |
fronts | -8.472 |
hai | -8.446 |
Token | Date |
Token ID | 7536 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
zona | +4.845 |
RESULTS | +4.226 |
haar | +3.985 |
bley | +3.847 |
iscons | +3.683 |
Neg logit contributions | |
raq | -5.298 |
hai | -4.945 |
Wast | -4.511 |
fronts | -4.407 |
Wars | -4.374 |
Token | : |
Token ID | 25 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
zona | +1.616 |
RESULTS | +1.460 |
haar | +1.353 |
bley | +1.318 |
atos | +1.292 |
Neg logit contributions | |
raq | -1.486 |
hai | -1.396 |
Wast | -1.261 |
fronts | -1.230 |
Wars | -1.199 |
Token | October |
Token ID | 3267 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
raq | +2.226 |
hai | +2.130 |
Wast | +1.941 |
Wars | +1.842 |
Synd | +1.831 |
Neg logit contributions | |
zona | -2.805 |
RESULTS | -2.571 |
haar | -2.408 |
bley | -2.360 |
atos | -2.293 |
Token | 16 |
Token ID | 1467 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
zona | +0.322 |
RESULTS | +0.292 |
haar | +0.272 |
bley | +0.266 |
atos | +0.261 |
Neg logit contributions | |
raq | -0.256 |
hai | -0.242 |
Wast | -0.217 |
Wars | -0.207 |
fronts | -0.205 |
Token | I |
Token ID | 314 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
raq | +0.508 |
hai | +0.482 |
Wast | +0.432 |
Wars | +0.411 |
fronts | +0.405 |
Neg logit contributions | |
zona | -0.651 |
RESULTS | -0.592 |
haar | -0.553 |
bley | -0.543 |
atos | -0.528 |
Token | would |
Token ID | 561 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
raq | +2.353 |
hai | +2.238 |
Wast | +1.961 |
fronts | +1.843 |
tered | +1.812 |
Neg logit contributions | |
zona | -4.557 |
RESULTS | -4.275 |
haar | -4.003 |
bley | -3.905 |
iscons | -3.833 |
Token | always |
Token ID | 1464 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
raq | +2.217 |
hai | +2.103 |
Wast | +1.886 |
fronts | +1.792 |
Synd | +1.764 |
Neg logit contributions | |
zona | -3.647 |
RESULTS | -3.400 |
haar | -3.150 |
bley | -3.078 |
iscons | -3.004 |
Token | take |
Token ID | 1011 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
zona | +2.216 |
RESULTS | +1.980 |
haar | +1.880 |
bley | +1.859 |
atos | +1.816 |
Neg logit contributions | |
raq | -1.624 |
hai | -1.530 |
Wast | -1.346 |
Wars | -1.282 |
Synd | -1.250 |
Token | human |
Token ID | 1692 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
zona | +2.408 |
RESULTS | +2.158 |
haar | +2.015 |
bley | +1.994 |
atos | +1.955 |
Neg logit contributions | |
raq | -1.972 |
hai | -1.894 |
Wast | -1.649 |
Wars | -1.611 |
obar | -1.553 |
Token | rights |
Token ID | 2489 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
zona | +7.073 |
RESULTS | +6.378 |
haar | +5.935 |
atos | +5.791 |
bley | +5.769 |
Neg logit contributions | |
raq | -8.337 |
hai | -8.009 |
Wast | -7.434 |
Wars | -7.245 |
arthed | -7.130 |
Token | ," |
Token ID | 553 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
zona | +10.077 |
RESULTS | +8.694 |
haar | +7.865 |
bley | +7.771 |
atos | +7.761 |
Neg logit contributions | |
raq | -11.943 |
hai | -11.064 |
arthed | -10.111 |
Wars | -9.951 |
Wast | -9.870 |
Token | he |
Token ID | 339 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
raq | +0.901 |
hai | +0.855 |
Wast | +0.771 |
Wars | +0.727 |
Synd | +0.725 |
Neg logit contributions | |
zona | -1.188 |
RESULTS | -1.083 |
haar | -1.012 |
bley | -0.990 |
atos | -0.966 |
Token | continued |
Token ID | 3767 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
zona | +2.406 |
RESULTS | +2.112 |
haar | +1.963 |
bley | +1.952 |
atos | +1.875 |
Neg logit contributions | |
raq | -2.625 |
hai | -2.503 |
Wast | -2.292 |
Wars | -2.212 |
Synd | -2.174 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
zona | +3.910 |
RESULTS | +3.514 |
haar | +3.281 |
bley | +3.196 |
atos | +3.118 |
Neg logit contributions | |
raq | -3.573 |
hai | -3.412 |
Wast | -3.098 |
Wars | -2.940 |
Synd | -2.899 |
Token |
|
Token ID | 198 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
raq | +1.637 |
hai | +1.552 |
Wast | +1.390 |
Wars | +1.312 |
Synd | +1.297 |
Neg logit contributions | |
zona | -2.480 |
RESULTS | -2.271 |
haar | -2.128 |
bley | -2.098 |
atos | -2.043 |
Token | ral |
Token ID | 1373 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
zona | +2.826 |
RESULTS | +2.537 |
haar | +2.341 |
atos | +2.283 |
bley | +2.266 |
Neg logit contributions | |
raq | -3.095 |
hai | -3.010 |
Wast | -2.791 |
Wars | -2.685 |
Synd | -2.659 |
Token | sensory |
Token ID | 23326 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
zona | +2.145 |
RESULTS | +1.956 |
haar | +1.821 |
bley | +1.782 |
atos | +1.760 |
Neg logit contributions | |
raq | -1.690 |
hai | -1.606 |
Wast | -1.443 |
Wars | -1.388 |
Synd | -1.352 |
Token | motor |
Token ID | 5584 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
zona | +4.032 |
RESULTS | +3.704 |
haar | +3.415 |
atos | +3.376 |
bley | +3.315 |
Neg logit contributions | |
raq | -2.857 |
hai | -2.653 |
Wast | -2.388 |
Wars | -2.285 |
Synd | -2.240 |
Token | cortex |
Token ID | 20223 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
zona | +3.784 |
RESULTS | +3.472 |
haar | +3.219 |
atos | +3.191 |
bley | +3.166 |
Neg logit contributions | |
raq | -2.470 |
hai | -2.328 |
Wast | -2.061 |
Wars | -1.936 |
obar | -1.903 |
Token | ( |
Token ID | 357 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
zona | +1.988 |
RESULTS | +1.799 |
haar | +1.670 |
bley | +1.638 |
atos | +1.609 |
Neg logit contributions | |
raq | -1.759 |
hai | -1.669 |
Wast | -1.508 |
Wars | -1.444 |
Synd | -1.418 |
Token | v |
Token ID | 85 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
zona | +8.141 |
RESULTS | +7.198 |
bley | +6.436 |
VS | +6.353 |
atos | +6.340 |
Neg logit contributions | |
hai | -8.843 |
raq | -8.730 |
Wast | -7.841 |
fronts | -7.486 |
Synd | -7.478 |
Token | S |
Token ID | 50 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
zona | +9.138 |
RESULTS | +8.496 |
atos | +8.089 |
VS | +7.928 |
bley | +7.805 |
Neg logit contributions | |
hai | -12.074 |
raq | -11.622 |
Wast | -10.521 |
Garrison | -10.393 |
fronts | -10.217 |
Token | MC |
Token ID | 9655 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
zona | +5.165 |
RESULTS | +4.767 |
bley | +4.175 |
haar | +4.160 |
atos | +4.015 |
Neg logit contributions | |
hai | -5.340 |
raq | -5.237 |
Wast | -4.594 |
sugg | -4.390 |
fronts | -4.355 |
Token | ) |
Token ID | 8 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
zona | +3.327 |
RESULTS | +3.024 |
haar | +2.806 |
bley | +2.762 |
atos | +2.673 |
Neg logit contributions | |
raq | -2.873 |
hai | -2.739 |
Wast | -2.462 |
Wars | -2.380 |
Synd | -2.328 |
Token | — |
Token ID | 851 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
zona | +4.419 |
RESULTS | +3.991 |
haar | +3.686 |
bley | +3.623 |
atos | +3.605 |
Neg logit contributions | |
raq | -3.991 |
hai | -3.799 |
Wast | -3.425 |
Wars | -3.291 |
Synd | -3.239 |
Token | how |
Token ID | 703 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
zona | +5.064 |
RESULTS | +4.474 |
haar | +4.177 |
bley | +4.132 |
atos | +4.061 |
Neg logit contributions | |
raq | -4.252 |
hai | -4.090 |
Wast | -3.659 |
Wars | -3.531 |
Synd | -3.436 |
Token |
|
Token ID | 198 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
raq | +0.452 |
hai | +0.427 |
Wast | +0.377 |
Wars | +0.356 |
fronts | +0.351 |
Neg logit contributions | |
zona | -0.701 |
RESULTS | -0.642 |
haar | -0.604 |
bley | -0.593 |
atos | -0.579 |
Token | San |
Token ID | 15017 |
Feature activation | +1.15e-03 |
Pos logit contributions | |
raq | +0.693 |
hai | +0.658 |
Wast | +0.591 |
Wars | +0.565 |
fronts | +0.556 |
Neg logit contributions | |
zona | -0.852 |
RESULTS | -0.773 |
haar | -0.723 |
bley | -0.708 |
atos | -0.689 |
Token | Francisco |
Token ID | 6033 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
zona | +0.014 |
RESULTS | +0.012 |
haar | +0.011 |
bley | +0.011 |
atos | +0.011 |
Neg logit contributions | |
raq | -0.014 |
hai | -0.014 |
Wast | -0.012 |
Wars | -0.012 |
fronts | -0.012 |
Token | Board |
Token ID | 5926 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
raq | +0.898 |
hai | +0.850 |
Wast | +0.755 |
Wars | +0.709 |
Synd | +0.701 |
Neg logit contributions | |
zona | -1.420 |
RESULTS | -1.303 |
haar | -1.226 |
bley | -1.208 |
atos | -1.173 |
Token | of |
Token ID | 286 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
raq | +0.395 |
hai | +0.375 |
Wast | +0.337 |
Wars | +0.321 |
Synd | +0.317 |
Neg logit contributions | |
zona | -0.503 |
RESULTS | -0.458 |
haar | -0.429 |
bley | -0.420 |
atos | -0.408 |
Token | Super |
Token ID | 3115 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
zona | +6.293 |
RESULTS | +5.613 |
haar | +5.258 |
atos | +5.092 |
iscons | +4.929 |
Neg logit contributions | |
raq | -7.084 |
hai | -6.712 |
Wars | -5.855 |
ilation | -5.846 |
sugg | -5.785 |
Token | visors |
Token ID | 27681 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
zona | +4.609 |
RESULTS | +2.949 |
atos | +2.629 |
haar | +2.348 |
bley | +2.303 |
Neg logit contributions | |
raq | -16.907 |
hai | -16.505 |
Wast | -15.375 |
obar | -15.282 |
Wars | -14.943 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
raq | +0.261 |
hai | +0.248 |
Wast | +0.220 |
Wars | +0.209 |
fronts | +0.206 |
Neg logit contributions | |
zona | -0.363 |
RESULTS | -0.331 |
haar | -0.310 |
bley | -0.304 |
atos | -0.297 |
Token |
|
Token ID | 198 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
zona | +2.278 |
RESULTS | +2.117 |
haar | +1.943 |
bley | +1.882 |
atos | +1.866 |
Neg logit contributions | |
raq | -1.777 |
hai | -1.684 |
Wast | -1.504 |
fronts | -1.458 |
sugg | -1.413 |
Token | San |
Token ID | 15017 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
raq | +0.372 |
hai | +0.354 |
Wast | +0.320 |
Wars | +0.302 |
fronts | +0.301 |
Neg logit contributions | |
zona | -0.450 |
RESULTS | -0.409 |
haar | -0.380 |
bley | -0.372 |
atos | -0.363 |
Token | Francisco |
Token ID | 6033 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
raq | +1.754 |
hai | +1.676 |
Wast | +1.488 |
Wars | +1.422 |
Synd | +1.406 |
Neg logit contributions | |
zona | -2.392 |
RESULTS | -2.214 |
haar | -2.063 |
bley | -2.037 |
atos | -1.954 |
Token | Although |
Token ID | 7003 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
zona | +2.797 |
RESULTS | +2.626 |
haar | +2.347 |
bley | +2.297 |
atos | +2.267 |
Neg logit contributions | |
raq | -2.373 |
hai | -2.244 |
Wast | -2.092 |
fronts | -2.001 |
Synd | -1.966 |
Token | it |
Token ID | 340 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
zona | +1.956 |
RESULTS | +1.778 |
haar | +1.657 |
bley | +1.629 |
atos | +1.589 |
Neg logit contributions | |
raq | -1.485 |
hai | -1.407 |
Wast | -1.241 |
Wars | -1.193 |
Synd | -1.162 |
Token | is |
Token ID | 318 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
zona | +0.273 |
RESULTS | +0.249 |
haar | +0.234 |
bley | +0.230 |
atos | +0.225 |
Neg logit contributions | |
raq | -0.183 |
hai | -0.172 |
Wast | -0.153 |
Wars | -0.145 |
Synd | -0.143 |
Token | impossible |
Token ID | 5340 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
zona | +3.547 |
RESULTS | +3.189 |
haar | +2.972 |
bley | +2.896 |
atos | +2.854 |
Neg logit contributions | |
raq | -2.950 |
hai | -2.818 |
Wast | -2.490 |
Wars | -2.420 |
iles | -2.371 |
Token | to |
Token ID | 284 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
zona | +4.470 |
RESULTS | +4.017 |
haar | +3.750 |
bley | +3.652 |
atos | +3.613 |
Neg logit contributions | |
raq | -3.753 |
hai | -3.665 |
Wast | -3.288 |
Wars | -3.114 |
fronts | -3.066 |
Token | dis |
Token ID | 595 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
zona | +4.822 |
RESULTS | +4.331 |
haar | +4.050 |
bley | +3.954 |
atos | +3.945 |
Neg logit contributions | |
raq | -3.790 |
hai | -3.631 |
Wast | -3.154 |
Wars | -3.070 |
arthed | -3.021 |
Token | amb |
Token ID | 4131 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
zona | +8.690 |
RESULTS | +6.857 |
atos | +6.707 |
bley | +6.414 |
haar | +6.171 |
Neg logit contributions | |
raq | -12.253 |
hai | -11.959 |
Wast | -11.577 |
fronts | -11.244 |
Wars | -11.183 |
Token | ig |
Token ID | 328 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
raq | +2.969 |
hai | +2.778 |
Wast | +2.521 |
iles | +2.475 |
obar | +2.445 |
Neg logit contributions | |
zona | -2.832 |
RESULTS | -2.510 |
haar | -2.238 |
bley | -2.190 |
iscons | -2.172 |
Token | uate |
Token ID | 4985 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
zona | +2.251 |
RESULTS | +2.034 |
haar | +1.908 |
bley | +1.843 |
atos | +1.832 |
Neg logit contributions | |
raq | -2.320 |
hai | -2.233 |
Wast | -2.032 |
Wars | -1.981 |
fronts | -1.934 |
Token | any |
Token ID | 597 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
zona | +1.805 |
RESULTS | +1.642 |
haar | +1.536 |
bley | +1.504 |
atos | +1.476 |
Neg logit contributions | |
raq | -1.370 |
hai | -1.289 |
Wast | -1.136 |
Wars | -1.096 |
Synd | -1.067 |
Token | single |
Token ID | 2060 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
zona | +2.327 |
RESULTS | +2.129 |
haar | +1.982 |
bley | +1.931 |
atos | +1.900 |
Neg logit contributions | |
raq | -1.823 |
hai | -1.725 |
Wast | -1.544 |
Wars | -1.472 |
Synd | -1.450 |
Token | groups |
Token ID | 2628 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
zona | +4.846 |
RESULTS | +4.382 |
haar | +4.123 |
bley | +4.064 |
iscons | +3.873 |
Neg logit contributions | |
raq | -4.308 |
hai | -4.112 |
Wast | -3.522 |
Wars | -3.517 |
obar | -3.422 |
Token | of |
Token ID | 286 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
zona | +0.838 |
RESULTS | +0.760 |
haar | +0.713 |
bley | +0.698 |
atos | +0.679 |
Neg logit contributions | |
raq | -0.681 |
hai | -0.643 |
Wast | -0.580 |
Wars | -0.551 |
Synd | -0.545 |
Token | people |
Token ID | 661 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
zona | +4.596 |
RESULTS | +4.154 |
haar | +3.912 |
bley | +3.879 |
atos | +3.775 |
Neg logit contributions | |
raq | -3.923 |
hai | -3.774 |
Wars | -3.305 |
Wast | -3.295 |
obar | -3.193 |
Token | who |
Token ID | 508 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
zona | +3.298 |
RESULTS | +2.999 |
haar | +2.820 |
bley | +2.770 |
atos | +2.659 |
Neg logit contributions | |
raq | -2.899 |
hai | -2.716 |
Wast | -2.425 |
Wars | -2.334 |
obar | -2.288 |
Token | " |
Token ID | 366 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
zona | +4.244 |
RESULTS | +3.795 |
haar | +3.620 |
bley | +3.568 |
atos | +3.455 |
Neg logit contributions | |
raq | -3.340 |
hai | -3.134 |
Wast | -2.766 |
Wars | -2.673 |
obar | -2.615 |
Token | inv |
Token ID | 16340 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
zona | +3.387 |
RESULTS | +3.099 |
haar | +2.883 |
bley | +2.834 |
atos | +2.744 |
Neg logit contributions | |
raq | -2.962 |
hai | -2.781 |
Wast | -2.603 |
Synd | -2.449 |
fronts | -2.425 |
Token | ade |
Token ID | 671 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
zona | +8.670 |
RESULTS | +7.211 |
iscons | +7.030 |
haar | +7.026 |
atos | +7.023 |
Neg logit contributions | |
hai | -11.631 |
raq | -11.451 |
Wast | -10.903 |
Wars | -10.400 |
fronts | -10.297 |
Token | our |
Token ID | 674 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
zona | +5.609 |
RESULTS | +4.902 |
haar | +4.607 |
bley | +4.579 |
atos | +4.458 |
Neg logit contributions | |
raq | -5.036 |
hai | -4.821 |
Wast | -4.194 |
Wars | -4.125 |
obar | -3.993 |
Token | communities |
Token ID | 5348 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
zona | +5.340 |
RESULTS | +4.753 |
haar | +4.519 |
bley | +4.495 |
atos | +4.310 |
Neg logit contributions | |
raq | -3.916 |
hai | -3.673 |
Wast | -3.105 |
Wars | -3.084 |
obar | -3.055 |
Token | pre |
Token ID | 662 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
zona | +2.433 |
RESULTS | +2.172 |
haar | +2.051 |
bley | +2.010 |
atos | +1.952 |
Neg logit contributions | |
raq | -2.131 |
hai | -2.014 |
Wast | -1.801 |
Wars | -1.727 |
obar | -1.693 |
Token | ying |
Token ID | 1112 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
zona | +0.823 |
RESULTS | +0.745 |
haar | +0.701 |
bley | +0.687 |
atos | +0.666 |
Neg logit contributions | |
raq | -0.641 |
hai | -0.605 |
Wast | -0.543 |
Wars | -0.517 |
Synd | -0.509 |
Token | or |
Token ID | 393 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
zona | +2.245 |
RESULTS | +2.021 |
haar | +1.942 |
bley | +1.855 |
atos | +1.823 |
Neg logit contributions | |
raq | -1.943 |
hai | -1.837 |
Wast | -1.647 |
obar | -1.564 |
Wars | -1.557 |
Token | visa |
Token ID | 14552 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
zona | +5.000 |
RESULTS | +4.447 |
haar | +4.359 |
bley | +4.226 |
atos | +4.051 |
Neg logit contributions | |
raq | -3.993 |
hai | -3.768 |
Wast | -3.302 |
obar | -3.238 |
Wars | -3.228 |
Token | to |
Token ID | 284 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
raq | +0.190 |
hai | +0.179 |
Wast | +0.160 |
Wars | +0.152 |
Synd | +0.150 |
Neg logit contributions | |
zona | -0.255 |
RESULTS | -0.232 |
haar | -0.219 |
bley | -0.214 |
atos | -0.208 |
Token | avoid |
Token ID | 3368 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
zona | +3.730 |
RESULTS | +3.371 |
haar | +3.201 |
bley | +3.150 |
atos | +3.038 |
Neg logit contributions | |
raq | -2.873 |
hai | -2.765 |
Wast | -2.439 |
Wars | -2.350 |
obar | -2.316 |
Token | facing |
Token ID | 6476 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
zona | +8.186 |
RESULTS | +7.374 |
haar | +7.211 |
bley | +6.841 |
atos | +6.742 |
Neg logit contributions | |
raq | -7.539 |
hai | -7.063 |
Wast | -6.113 |
Wars | -5.962 |
fighter | -5.837 |
Token | immediate |
Token ID | 7103 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
zona | +9.121 |
RESULTS | +8.091 |
haar | +8.087 |
bley | +7.685 |
atos | +7.369 |
Neg logit contributions | |
raq | -8.900 |
hai | -8.171 |
Wast | -7.069 |
Wars | -7.053 |
obar | -6.915 |
Token | suspension |
Token ID | 11461 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
zona | +10.696 |
haar | +9.559 |
RESULTS | +9.418 |
bley | +8.994 |
atos | +8.626 |
Neg logit contributions | |
raq | -9.804 |
hai | -9.055 |
Wast | -7.987 |
arthed | -7.909 |
Wars | -7.850 |
Token | of |
Token ID | 286 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
zona | +3.113 |
RESULTS | +2.820 |
haar | +2.649 |
bley | +2.584 |
atos | +2.531 |
Neg logit contributions | |
raq | -2.741 |
hai | -2.588 |
Wast | -2.330 |
Wars | -2.210 |
obar | -2.188 |
Token | service |
Token ID | 2139 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
zona | +2.132 |
RESULTS | +1.927 |
haar | +1.825 |
bley | +1.772 |
atos | +1.728 |
Neg logit contributions | |
raq | -1.850 |
hai | -1.759 |
Wast | -1.574 |
Wars | -1.515 |
obar | -1.478 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
raq | +0.400 |
hai | +0.380 |
Wast | +0.340 |
Wars | +0.323 |
fronts | +0.319 |
Neg logit contributions | |
zona | -0.530 |
RESULTS | -0.482 |
haar | -0.451 |
bley | -0.443 |
atos | -0.431 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
zona | +3.075 |
RESULTS | +2.832 |
haar | +2.625 |
bley | +2.549 |
atos | +2.490 |
Neg logit contributions | |
raq | -2.399 |
hai | -2.251 |
Wast | -1.975 |
fronts | -1.932 |
obar | -1.912 |
Token |
|
Token ID | 198 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
zona | +3.059 |
RESULTS | +2.871 |
haar | +2.574 |
bley | +2.485 |
atos | +2.483 |
Neg logit contributions | |
raq | -2.461 |
hai | -2.308 |
Wast | -2.093 |
fronts | -2.055 |
sugg | -2.014 |
Token | GPU |
Token ID | 33346 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
zona | +8.114 |
RESULTS | +7.719 |
haar | +6.609 |
atos | +6.502 |
bley | +6.338 |
Neg logit contributions | |
raq | -8.017 |
hai | -7.406 |
Wast | -7.298 |
sugg | -6.938 |
fronts | -6.844 |
Token | : |
Token ID | 25 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
zona | +0.770 |
RESULTS | +0.701 |
haar | +0.652 |
bley | +0.636 |
atos | +0.623 |
Neg logit contributions | |
raq | -0.650 |
hai | -0.615 |
Wast | -0.552 |
Wars | -0.530 |
fronts | -0.520 |
Token | AMD |
Token ID | 10324 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
zona | +1.417 |
RESULTS | +1.283 |
haar | +1.193 |
bley | +1.161 |
atos | +1.136 |
Neg logit contributions | |
raq | -1.287 |
hai | -1.227 |
Wast | -1.099 |
Wars | -1.062 |
fronts | -1.045 |
Token | Radeon |
Token ID | 13082 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
raq | +0.528 |
hai | +0.505 |
Wast | +0.461 |
Wars | +0.442 |
fronts | +0.437 |
Neg logit contributions | |
zona | -0.506 |
RESULTS | -0.453 |
haar | -0.419 |
bley | -0.409 |
atos | -0.397 |
Token | HD |
Token ID | 5572 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
zona | +1.155 |
RESULTS | +1.054 |
haar | +0.994 |
bley | +0.971 |
atos | +0.951 |
Neg logit contributions | |
raq | -0.791 |
hai | -0.746 |
Wast | -0.659 |
Wars | -0.628 |
fronts | -0.620 |
Token | 78 |
Token ID | 8699 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
zona | +9.493 |
RESULTS | +8.901 |
haar | +8.616 |
Arbor | +7.948 |
atos | +7.599 |
Neg logit contributions | |
hai | -10.719 |
raq | -10.514 |
fronts | -9.360 |
repre | -9.237 |
tein | -9.131 |
Token | 70 |
Token ID | 2154 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
raq | +2.019 |
hai | +1.909 |
Wast | +1.709 |
Wars | +1.593 |
Synd | +1.572 |
Neg logit contributions | |
zona | -3.145 |
RESULTS | -2.892 |
haar | -2.728 |
bley | -2.662 |
atos | -2.592 |
Token | - |
Token ID | 532 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
zona | +3.861 |
RESULTS | +3.492 |
haar | +3.365 |
bley | +3.205 |
atos | +3.162 |
Neg logit contributions | |
raq | -3.005 |
hai | -2.847 |
Wast | -2.501 |
Wars | -2.435 |
fronts | -2.410 |
Token | 1100 |
Token ID | 36566 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
zona | +1.023 |
RESULTS | +0.932 |
haar | +0.876 |
bley | +0.853 |
atos | +0.832 |
Neg logit contributions | |
raq | -0.815 |
hai | -0.773 |
Wast | -0.689 |
Wars | -0.661 |
fronts | -0.653 |
Token | MHz |
Token ID | 19805 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
raq | +1.170 |
hai | +1.119 |
Wast | +1.020 |
Wars | +0.978 |
fronts | +0.967 |
Neg logit contributions | |
zona | -1.135 |
RESULTS | -1.017 |
haar | -0.941 |
bley | -0.919 |
atos | -0.891 |
Token | the |
Token ID | 262 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
raq | +1.900 |
hai | +1.790 |
Wast | +1.607 |
Wars | +1.530 |
Synd | +1.519 |
Neg logit contributions | |
zona | -2.546 |
RESULTS | -2.315 |
haar | -2.165 |
bley | -2.128 |
atos | -2.078 |
Token | information |
Token ID | 1321 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
raq | +0.654 |
hai | +0.619 |
Wast | +0.552 |
Wars | +0.523 |
fronts | +0.516 |
Neg logit contributions | |
zona | -0.909 |
RESULTS | -0.829 |
haar | -0.778 |
bley | -0.763 |
atos | -0.744 |
Token | " |
Token ID | 366 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
raq | +1.389 |
hai | +1.309 |
Wast | +1.171 |
Wars | +1.113 |
Synd | +1.101 |
Neg logit contributions | |
zona | -1.940 |
RESULTS | -1.770 |
haar | -1.661 |
bley | -1.629 |
atos | -1.594 |
Token | off |
Token ID | 2364 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
zona | +1.334 |
RESULTS | +1.217 |
haar | +1.134 |
bley | +1.104 |
atos | +1.077 |
Neg logit contributions | |
raq | -1.120 |
hai | -1.067 |
Wast | -0.973 |
Wars | -0.917 |
Synd | -0.915 |
Token | - |
Token ID | 12 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
zona | +5.423 |
RESULTS | +5.004 |
haar | +4.552 |
bley | +4.422 |
atos | +4.347 |
Neg logit contributions | |
raq | -4.725 |
hai | -4.540 |
Wast | -4.063 |
obar | -3.875 |
Wars | -3.848 |
Token | the |
Token ID | 1169 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
zona | +3.073 |
RESULTS | +2.780 |
haar | +2.511 |
bley | +2.492 |
atos | +2.378 |
Neg logit contributions | |
raq | -3.216 |
hai | -3.039 |
Wast | -2.814 |
obar | -2.638 |
Wars | -2.638 |
Token | - |
Token ID | 12 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
zona | +9.051 |
bley | +7.392 |
haar | +7.381 |
RESULTS | +7.368 |
atos | +6.969 |
Neg logit contributions | |
raq | -11.407 |
hai | -10.969 |
Wast | -10.199 |
Wars | -10.072 |
ilation | -9.673 |
Token | record |
Token ID | 22105 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
zona | +5.044 |
RESULTS | +4.238 |
bley | +4.016 |
haar | +3.770 |
atos | +3.432 |
Neg logit contributions | |
raq | -8.398 |
hai | -8.031 |
Wast | -7.888 |
obar | -7.416 |
Synd | -7.344 |
Token | ", |
Token ID | 1600 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
raq | +0.474 |
hai | +0.451 |
Wast | +0.407 |
Wars | +0.388 |
fronts | +0.383 |
Neg logit contributions | |
zona | -0.554 |
RESULTS | -0.502 |
haar | -0.468 |
bley | -0.458 |
atos | -0.445 |
Token | had |
Token ID | 550 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
raq | +0.768 |
hai | +0.730 |
Wast | +0.654 |
Wars | +0.621 |
fronts | +0.616 |
Neg logit contributions | |
zona | -0.996 |
RESULTS | -0.907 |
haar | -0.849 |
bley | -0.831 |
atos | -0.809 |
Token | a |
Token ID | 257 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
raq | +3.094 |
hai | +2.870 |
Wast | +2.585 |
Synd | +2.451 |
fronts | +2.449 |
Neg logit contributions | |
zona | -4.559 |
RESULTS | -4.197 |
haar | -3.959 |
bley | -3.843 |
atos | -3.770 |
Token | Close |
Token ID | 13872 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
zona | +0.876 |
RESULTS | +0.796 |
haar | +0.742 |
bley | +0.729 |
atos | +0.710 |
Neg logit contributions | |
raq | -0.666 |
hai | -0.631 |
Wast | -0.561 |
Wars | -0.537 |
fronts | -0.528 |
Token | Graphics |
Token ID | 19840 |
Feature activation | -4.44e-03 |
Pos logit contributions | |
zona | +1.032 |
RESULTS | +0.936 |
haar | +0.878 |
bley | +0.863 |
atos | +0.841 |
Neg logit contributions | |
raq | -0.781 |
hai | -0.745 |
Wast | -0.661 |
Wars | -0.634 |
Synd | -0.616 |
Token | $ |
Token ID | 720 |
Feature activation | +7.83e-04 |
Pos logit contributions | |
raq | +0.045 |
hai | +0.042 |
Wast | +0.038 |
Wars | +0.036 |
Synd | +0.035 |
Neg logit contributions | |
zona | -0.062 |
RESULTS | -0.057 |
haar | -0.053 |
bley | -0.052 |
atos | -0.051 |
Token | image |
Token ID | 9060 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
zona | +0.010 |
RESULTS | +0.009 |
haar | +0.008 |
bley | +0.008 |
atos | +0.008 |
Neg logit contributions | |
raq | -0.009 |
hai | -0.009 |
Wast | -0.008 |
Wars | -0.008 |
Synd | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
zona | +0.306 |
RESULTS | +0.275 |
haar | +0.255 |
bley | +0.249 |
atos | +0.241 |
Neg logit contributions | |
raq | -0.306 |
hai | -0.293 |
Wast | -0.267 |
Wars | -0.255 |
Synd | -0.252 |
Token | Dis |
Token ID | 7279 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
zona | +5.062 |
RESULTS | +4.602 |
haar | +4.067 |
bley | +4.019 |
atos | +3.908 |
Neg logit contributions | |
raq | -5.147 |
hai | -4.879 |
Wast | -4.528 |
Synd | -4.403 |
fronts | -4.319 |
Token | pose |
Token ID | 3455 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
zona | +12.156 |
RESULTS | +10.948 |
bley | +10.249 |
atos | +10.016 |
iscons | +9.828 |
Neg logit contributions | |
raq | -8.670 |
hai | -8.073 |
Wast | -7.970 |
fronts | -7.449 |
Wars | -7.251 |
Token | (); |
Token ID | 9783 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
raq | +1.316 |
hai | +1.226 |
Wast | +1.085 |
Wars | +1.011 |
fronts | +0.994 |
Neg logit contributions | |
zona | -2.376 |
RESULTS | -2.179 |
haar | -2.064 |
bley | -2.029 |
atos | -1.982 |
Token | # |
Token ID | 1303 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
raq | +2.694 |
hai | +2.482 |
Wast | +2.236 |
fronts | +2.050 |
Synd | +2.042 |
Neg logit contributions | |
zona | -5.004 |
RESULTS | -4.603 |
haar | -4.437 |
bley | -4.311 |
atos | -4.212 |
Token | Save |
Token ID | 12793 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
zona | +2.272 |
RESULTS | +2.065 |
haar | +1.914 |
bley | +1.891 |
atos | +1.841 |
Neg logit contributions | |
raq | -1.711 |
hai | -1.617 |
Wast | -1.420 |
Wars | -1.379 |
fronts | -1.345 |
Token | and |
Token ID | 290 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
zona | +2.096 |
RESULTS | +1.903 |
haar | +1.767 |
bley | +1.732 |
atos | +1.702 |
Neg logit contributions | |
raq | -1.675 |
hai | -1.582 |
Wast | -1.407 |
Wars | -1.362 |
Synd | -1.317 |
Token | ); |
Token ID | 1776 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
zona | +1.689 |
RESULTS | +1.539 |
haar | +1.424 |
bley | +1.400 |
atos | +1.363 |
Neg logit contributions | |
raq | -1.418 |
hai | -1.348 |
Wast | -1.210 |
Wars | -1.151 |
fronts | -1.140 |
Token | $ |
Token ID | 720 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
raq | +3.571 |
hai | +3.304 |
Wast | +3.000 |
fronts | +2.779 |
Synd | +2.764 |
Neg logit contributions | |
zona | -6.079 |
RESULTS | -5.541 |
haar | -5.395 |
bley | -5.207 |
atos | -5.078 |
Token | b |
Token ID | 65 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
zona | +1.057 |
RESULTS | +0.965 |
haar | +0.894 |
bley | +0.877 |
atos | +0.854 |
Neg logit contributions | |
raq | -0.877 |
hai | -0.832 |
Wast | -0.760 |
Wars | -0.714 |
Synd | -0.713 |
Token | mp |
Token ID | 3149 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
raq | +1.161 |
hai | +1.058 |
Wast | +0.575 |
iles | +0.540 |
obar | +0.513 |
Neg logit contributions | |
zona | -6.529 |
RESULTS | -6.119 |
haar | -5.843 |
bley | -5.761 |
iscons | -5.707 |
Token | . |
Token ID | 13 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
raq | +0.985 |
hai | +0.932 |
Wast | +0.830 |
Wars | +0.795 |
iles | +0.784 |
Neg logit contributions | |
zona | -1.316 |
RESULTS | -1.190 |
haar | -1.125 |
bley | -1.098 |
atos | -1.072 |
Token | Dis |
Token ID | 7279 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
zona | +7.499 |
RESULTS | +7.190 |
bley | +5.882 |
haar | +5.845 |
atos | +5.749 |
Neg logit contributions | |
raq | -8.841 |
hai | -8.442 |
Wast | -8.069 |
sugg | -7.891 |
fronts | -7.862 |
Token | pose |
Token ID | 3455 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
zona | +10.207 |
RESULTS | +9.018 |
atos | +8.449 |
bley | +8.232 |
haar | +7.997 |
Neg logit contributions | |
raq | -9.997 |
hai | -9.675 |
Wast | -9.600 |
fronts | -9.581 |
sugg | -9.274 |
Token | (); |
Token ID | 9783 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
zona | +2.012 |
RESULTS | +1.842 |
haar | +1.710 |
bley | +1.670 |
atos | +1.634 |
Neg logit contributions | |
raq | -1.600 |
hai | -1.527 |
Wast | -1.363 |
Wars | -1.286 |
fronts | -1.279 |
Token | # |
Token ID | 1303 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
raq | +3.562 |
hai | +3.262 |
Wast | +2.957 |
fronts | +2.714 |
Synd | +2.697 |
Neg logit contributions | |
zona | -6.505 |
RESULTS | -5.950 |
haar | -5.800 |
bley | -5.594 |
atos | -5.472 |
Token | Output |
Token ID | 25235 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
zona | +3.797 |
RESULTS | +3.442 |
haar | +3.150 |
bley | +3.142 |
atos | +3.044 |
Neg logit contributions | |
raq | -3.047 |
hai | -2.885 |
Wast | -2.512 |
Wars | -2.474 |
fronts | -2.404 |
Token | our |
Token ID | 674 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
zona | +1.216 |
RESULTS | +1.105 |
haar | +1.031 |
bley | +1.012 |
atos | +0.986 |
Neg logit contributions | |
raq | -0.955 |
hai | -0.907 |
Wast | -0.808 |
Wars | -0.775 |
Synd | -0.759 |
Token | . |
Token ID | 764 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
zona | +6.239 |
RESULTS | +5.490 |
haar | +4.990 |
bley | +4.639 |
atos | +4.549 |
Neg logit contributions | |
raq | -12.160 |
hai | -11.257 |
facult | -10.704 |
fronts | -10.570 |
arthed | -10.420 |
Token | x |
Token ID | 2124 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
zona | +7.637 |
haar | +5.868 |
RESULTS | +5.849 |
bley | +5.814 |
atos | +5.250 |
Neg logit contributions | |
raq | -9.618 |
hai | -9.094 |
Wars | -8.287 |
Wast | -8.188 |
arthed | -8.014 |
Token | yz |
Token ID | 45579 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
zona | +5.919 |
RESULTS | +5.124 |
haar | +4.935 |
bley | +4.792 |
atos | +4.608 |
Neg logit contributions | |
raq | -5.731 |
hai | -5.336 |
Wast | -5.134 |
Synd | -4.844 |
fronts | -4.839 |
Token | += |
Token ID | 15853 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
zona | +1.390 |
RESULTS | +1.262 |
haar | +1.185 |
bley | +1.154 |
atos | +1.122 |
Neg logit contributions | |
raq | -1.133 |
hai | -1.074 |
Wast | -0.968 |
Wars | -0.921 |
fronts | -0.912 |
Token | v |
Token ID | 410 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
zona | +0.835 |
RESULTS | +0.759 |
haar | +0.711 |
bley | +0.696 |
atos | +0.679 |
Neg logit contributions | |
raq | -0.647 |
hai | -0.613 |
Wast | -0.547 |
Wars | -0.523 |
fronts | -0.514 |
Token | . |
Token ID | 764 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
zona | +3.764 |
RESULTS | +3.385 |
haar | +3.075 |
bley | +2.895 |
atos | +2.888 |
Neg logit contributions | |
raq | -5.068 |
hai | -4.764 |
Wast | -4.336 |
fronts | -4.293 |
Wars | -4.229 |
Token | normal |
Token ID | 3487 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
zona | +8.671 |
RESULTS | +6.980 |
haar | +6.664 |
atos | +6.634 |
bley | +6.515 |
Neg logit contributions | |
raq | -11.916 |
hai | -11.737 |
Wars | -10.732 |
Wast | -10.731 |
Synd | -10.334 |
Token | * |
Token ID | 1635 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
zona | +8.224 |
RESULTS | +7.675 |
haar | +7.032 |
atos | +6.770 |
bley | +6.707 |
Neg logit contributions | |
raq | -7.069 |
hai | -6.464 |
fronts | -5.920 |
Wars | -5.800 |
Wast | -5.769 |
Token | 1 |
Token ID | 352 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
zona | +2.725 |
RESULTS | +2.485 |
haar | +2.332 |
bley | +2.287 |
atos | +2.230 |
Neg logit contributions | |
raq | -2.029 |
hai | -1.898 |
Wast | -1.672 |
Wars | -1.625 |
fronts | -1.580 |
Token | ; |
Token ID | 2162 |
Feature activation | +1.30e-04 |
Pos logit contributions | |
zona | +1.120 |
RESULTS | +1.025 |
haar | +0.960 |
bley | +0.941 |
atos | +0.918 |
Neg logit contributions | |
raq | -0.789 |
hai | -0.743 |
Wast | -0.660 |
Wars | -0.628 |
fronts | -0.621 |
Token | } |
Token ID | 1782 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
zona | +0.002 |
RESULTS | +0.002 |
haar | +0.002 |
bley | +0.002 |
atos | +0.002 |
Neg logit contributions | |
raq | -0.001 |
hai | -0.001 |
Wast | -0.001 |
Wars | -0.001 |
fronts | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
raq | +1.129 |
hai | +1.070 |
Wast | +0.959 |
Wars | +0.906 |
fronts | +0.898 |
Neg logit contributions | |
zona | -1.567 |
RESULTS | -1.433 |
haar | -1.341 |
bley | -1.315 |
atos | -1.282 |
Token | gain |
Token ID | 4461 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
zona | +1.122 |
RESULTS | +1.022 |
haar | +0.964 |
bley | +0.946 |
atos | +0.923 |
Neg logit contributions | |
raq | -0.775 |
hai | -0.728 |
Wast | -0.644 |
Wars | -0.614 |
Synd | -0.602 |
Token | some |
Token ID | 617 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
zona | +0.713 |
RESULTS | +0.645 |
haar | +0.607 |
bley | +0.594 |
atos | +0.578 |
Neg logit contributions | |
raq | -0.568 |
hai | -0.541 |
Wast | -0.482 |
Wars | -0.461 |
fronts | -0.452 |
Token | real |
Token ID | 1103 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
zona | +3.230 |
RESULTS | +2.954 |
haar | +2.776 |
bley | +2.725 |
atos | +2.642 |
Neg logit contributions | |
raq | -2.522 |
hai | -2.382 |
Wast | -2.111 |
Wars | -2.039 |
Synd | -1.970 |
Token | field |
Token ID | 2214 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
zona | +5.755 |
RESULTS | +5.224 |
haar | +4.877 |
bley | +4.848 |
atos | +4.658 |
Neg logit contributions | |
raq | -4.732 |
hai | -4.446 |
Wast | -4.039 |
Wars | -3.841 |
Synd | -3.724 |
Token | of |
Token ID | 286 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
zona | +1.980 |
RESULTS | +1.792 |
haar | +1.679 |
bley | +1.628 |
atos | +1.596 |
Neg logit contributions | |
raq | -1.652 |
hai | -1.557 |
Wast | -1.419 |
Wars | -1.348 |
Synd | -1.328 |
Token | view |
Token ID | 1570 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
zona | +7.403 |
RESULTS | +5.948 |
haar | +5.311 |
atos | +4.865 |
bley | +4.528 |
Neg logit contributions | |
raq | -13.661 |
hai | -13.206 |
Wast | -12.009 |
Wars | -11.778 |
fur | -11.701 |
Token | advantages |
Token ID | 13391 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
zona | +2.898 |
RESULTS | +2.640 |
haar | +2.480 |
bley | +2.393 |
atos | +2.350 |
Neg logit contributions | |
raq | -2.561 |
hai | -2.417 |
Wast | -2.181 |
Wars | -2.083 |
Synd | -2.039 |
Token | , |
Token ID | 11 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
zona | +3.431 |
RESULTS | +3.106 |
haar | +2.954 |
bley | +2.871 |
atos | +2.805 |
Neg logit contributions | |
raq | -3.095 |
hai | -2.899 |
Wast | -2.641 |
Wars | -2.520 |
Synd | -2.457 |
Token | but |
Token ID | 475 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
zona | +1.588 |
RESULTS | +1.430 |
haar | +1.344 |
bley | +1.318 |
atos | +1.282 |
Neg logit contributions | |
raq | -1.339 |
hai | -1.258 |
Wast | -1.134 |
Wars | -1.084 |
Synd | -1.065 |
Token | you |
Token ID | 345 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
zona | +1.325 |
RESULTS | +1.204 |
haar | +1.124 |
bley | +1.108 |
atos | +1.078 |
Neg logit contributions | |
raq | -1.036 |
hai | -0.974 |
Wast | -0.865 |
Wars | -0.829 |
Synd | -0.812 |
Token | successful |
Token ID | 4388 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
raq | +0.870 |
hai | +0.825 |
Wast | +0.734 |
Wars | +0.694 |
fronts | +0.691 |
Neg logit contributions | |
zona | -1.217 |
RESULTS | -1.110 |
haar | -1.044 |
bley | -1.023 |
atos | -0.996 |
Token | that |
Token ID | 326 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
zona | +2.773 |
RESULTS | +2.555 |
haar | +2.343 |
bley | +2.337 |
atos | +2.261 |
Neg logit contributions | |
raq | -2.505 |
hai | -2.416 |
Wast | -2.193 |
Wars | -2.087 |
obar | -2.044 |
Token | several |
Token ID | 1811 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
zona | +2.524 |
RESULTS | +2.328 |
haar | +2.154 |
bley | +2.144 |
iscons | +2.072 |
Neg logit contributions | |
raq | -2.125 |
hai | -2.023 |
Wast | -1.785 |
Wars | -1.715 |
obar | -1.702 |
Token | prominent |
Token ID | 9208 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
zona | +1.531 |
RESULTS | +1.413 |
haar | +1.311 |
bley | +1.296 |
iscons | +1.266 |
Neg logit contributions | |
raq | -1.157 |
hai | -1.097 |
Wast | -0.969 |
Wars | -0.928 |
obar | -0.921 |
Token | white |
Token ID | 2330 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
zona | +1.201 |
RESULTS | +1.101 |
haar | +1.028 |
bley | +1.009 |
atos | +0.985 |
Neg logit contributions | |
raq | -0.917 |
hai | -0.865 |
Wast | -0.769 |
Wars | -0.738 |
obar | -0.726 |
Token | Ken |
Token ID | 7148 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
raq | +2.901 |
hai | +2.767 |
Wast | +2.439 |
fronts | +2.343 |
Synd | +2.321 |
Neg logit contributions | |
zona | -4.639 |
RESULTS | -4.167 |
haar | -3.941 |
bley | -3.903 |
atos | -3.750 |
Token | y |
Token ID | 88 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
zona | +8.670 |
RESULTS | +7.375 |
haar | +6.930 |
bley | +6.892 |
atos | +6.814 |
Neg logit contributions | |
raq | -11.588 |
hai | -11.014 |
Wast | -10.643 |
Wars | -10.096 |
arthed | -10.017 |
Token | ans |
Token ID | 504 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
zona | +1.950 |
RESULTS | +1.655 |
haar | +1.510 |
bley | +1.448 |
atos | +1.408 |
Neg logit contributions | |
raq | -3.737 |
hai | -3.585 |
Wast | -3.399 |
Wars | -3.282 |
fronts | -3.279 |
Token | backed |
Token ID | 9763 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
raq | +2.016 |
hai | +1.919 |
Wast | +1.698 |
Wars | +1.603 |
fronts | +1.600 |
Neg logit contributions | |
zona | -3.081 |
RESULTS | -2.810 |
haar | -2.660 |
bley | -2.590 |
atos | -2.526 |
Token | K |
Token ID | 509 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
zona | +3.975 |
RESULTS | +3.612 |
haar | +3.331 |
bley | +3.324 |
iscons | +3.234 |
Neg logit contributions | |
raq | -3.624 |
hai | -3.435 |
Wast | -3.069 |
Wars | -2.966 |
obar | -2.959 |
Token | AN |
Token ID | 1565 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
raq | +0.774 |
hai | +0.741 |
Wast | +0.668 |
Wars | +0.643 |
Synd | +0.635 |
Neg logit contributions | |
zona | -0.793 |
RESULTS | -0.714 |
haar | -0.660 |
bley | -0.647 |
atos | -0.627 |
Token | � |
Token ID | 447 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
raq | +2.514 |
hai | +2.438 |
Wast | +2.136 |
fronts | +1.998 |
Wars | +1.990 |
Neg logit contributions | |
zona | -4.141 |
RESULTS | -3.815 |
haar | -3.553 |
bley | -3.468 |
iscons | -3.412 |
Token | � |
Token ID | 247 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
zona | +0.504 |
RESULTS | +0.462 |
haar | +0.435 |
bley | +0.426 |
atos | +0.415 |
Neg logit contributions | |
raq | -0.336 |
hai | -0.318 |
Wast | -0.282 |
Wars | -0.267 |
Synd | -0.264 |
Token | re |
Token ID | 260 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
raq | +1.844 |
hai | +1.769 |
Wast | +1.593 |
Wars | +1.529 |
Synd | +1.506 |
Neg logit contributions | |
zona | -1.968 |
RESULTS | -1.779 |
haar | -1.642 |
bley | -1.606 |
iscons | -1.558 |
Token | fighting |
Token ID | 4330 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
raq | +1.556 |
hai | +1.491 |
Wast | +1.336 |
Wars | +1.263 |
fronts | +1.258 |
Neg logit contributions | |
zona | -2.133 |
RESULTS | -1.950 |
haar | -1.823 |
bley | -1.781 |
iscons | -1.734 |
Token | a |
Token ID | 257 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
raq | +2.212 |
hai | +2.115 |
Wast | +1.898 |
fronts | +1.818 |
Wars | +1.802 |
Neg logit contributions | |
zona | -3.094 |
RESULTS | -2.832 |
haar | -2.647 |
bley | -2.599 |
iscons | -2.499 |
Token | m |
Token ID | 285 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
raq | +1.802 |
hai | +1.714 |
Wast | +1.548 |
Wars | +1.461 |
fronts | +1.438 |
Neg logit contributions | |
zona | -2.573 |
RESULTS | -2.367 |
haar | -2.198 |
bley | -2.149 |
atos | -2.104 |
Token | ains |
Token ID | 1299 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
raq | +12.291 |
hai | +11.585 |
uer | +10.608 |
ista | +10.600 |
obar | +10.318 |
Neg logit contributions | |
zona | -13.042 |
RESULTS | -12.634 |
bley | -10.653 |
aukee | -10.268 |
haar | -10.146 |
Token | ail |
Token ID | 603 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
zona | +1.169 |
RESULTS | +1.059 |
haar | +0.992 |
bley | +0.956 |
atos | +0.919 |
Neg logit contributions | |
raq | -1.214 |
hai | -1.164 |
Wast | -1.059 |
Wars | -1.019 |
Synd | -1.008 |
Token | on |
Token ID | 319 |
Feature activation | -6.82e-03 |
Pos logit contributions | |
zona | +1.021 |
RESULTS | +0.920 |
haar | +0.866 |
bley | +0.848 |
atos | +0.828 |
Neg logit contributions | |
raq | -0.850 |
hai | -0.806 |
Wast | -0.724 |
Wars | -0.688 |
Synd | -0.684 |
Token | The |
Token ID | 383 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
raq | +0.072 |
hai | +0.068 |
Wast | +0.061 |
Wars | +0.058 |
fronts | +0.057 |
Neg logit contributions | |
zona | -0.092 |
RESULTS | -0.084 |
haar | -0.079 |
bley | -0.077 |
atos | -0.075 |
Token | Young |
Token ID | 6960 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
zona | +1.281 |
RESULTS | +1.161 |
haar | +1.086 |
bley | +1.066 |
atos | +1.040 |
Neg logit contributions | |
raq | -1.028 |
hai | -0.973 |
Wast | -0.870 |
Wars | -0.832 |
fronts | -0.821 |
Token | WOR |
Token ID | 21881 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
raq | +0.757 |
hai | +0.718 |
Wast | +0.650 |
Wars | +0.612 |
Synd | +0.606 |
Neg logit contributions | |
zona | -0.995 |
RESULTS | -0.904 |
haar | -0.852 |
bley | -0.834 |
atos | -0.810 |
Token | ST |
Token ID | 2257 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
raq | +3.396 |
hai | +3.268 |
Wast | +3.037 |
Wars | +2.918 |
Synd | +2.839 |
Neg logit contributions | |
zona | -3.049 |
RESULTS | -2.619 |
haar | -2.494 |
bley | -2.372 |
atos | -2.323 |
Token | S |
Token ID | 311 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
raq | +0.877 |
hai | +0.834 |
Wast | +0.754 |
Wars | +0.713 |
Synd | +0.705 |
Neg logit contributions | |
zona | -1.157 |
RESULTS | -1.046 |
haar | -0.990 |
bley | -0.969 |
atos | -0.938 |
Token | ONG |
Token ID | 18494 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
zona | +4.062 |
RESULTS | +3.778 |
haar | +3.382 |
atos | +3.293 |
bley | +3.284 |
Neg logit contributions | |
raq | -3.865 |
hai | -3.704 |
Wast | -3.372 |
fronts | -3.193 |
Synd | -3.160 |
Token | EVER |
Token ID | 20498 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
raq | +1.307 |
hai | +1.238 |
Wast | +1.115 |
Wars | +1.053 |
Synd | +1.040 |
Neg logit contributions | |
zona | -1.852 |
RESULTS | -1.685 |
haar | -1.595 |
bley | -1.558 |
atos | -1.512 |
Token | M |
Token ID | 337 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
raq | +0.183 |
hai | +0.174 |
Wast | +0.156 |
Wars | +0.149 |
fronts | +0.147 |
Neg logit contributions | |
zona | -0.231 |
RESULTS | -0.210 |
haar | -0.197 |
bley | -0.193 |
atos | -0.188 |
Token | ADE |
Token ID | 19266 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
raq | +8.365 |
hai | +8.196 |
IND | +7.632 |
Wars | +7.191 |
ENG | +7.148 |
Neg logit contributions | |
zona | -14.421 |
RESULTS | -13.315 |
haar | -13.099 |
bley | -12.414 |
atos | -12.384 |
Token | IN |
Token ID | 3268 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
zona | +3.120 |
RESULTS | +2.854 |
haar | +2.640 |
bley | +2.611 |
atos | +2.529 |
Neg logit contributions | |
raq | -2.720 |
hai | -2.605 |
Wast | -2.286 |
fronts | -2.205 |
obar | -2.202 |
Token | LIFE |
Token ID | 36821 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
zona | +3.456 |
RESULTS | +3.149 |
haar | +2.882 |
bley | +2.809 |
atos | +2.754 |
Neg logit contributions | |
raq | -2.987 |
hai | -2.904 |
Wast | -2.545 |
fronts | -2.458 |
obar | -2.445 |
Token | ! |
Token ID | 0 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
raq | +2.277 |
hai | +2.166 |
Wast | +1.957 |
Wars | +1.860 |
Synd | +1.830 |
Neg logit contributions | |
zona | -3.162 |
RESULTS | -2.857 |
haar | -2.700 |
bley | -2.634 |
atos | -2.561 |
Token | You |
Token ID | 921 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
zona | +0.363 |
RESULTS | +0.331 |
haar | +0.309 |
bley | +0.302 |
atos | +0.295 |
Neg logit contributions | |
raq | -0.276 |
hai | -0.261 |
Wast | -0.233 |
Wars | -0.222 |
fronts | -0.220 |
Token | ales |
Token ID | 2040 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
zona | +2.826 |
RESULTS | +2.549 |
haar | +2.380 |
bley | +2.339 |
atos | +2.312 |
Neg logit contributions | |
raq | -2.259 |
hai | -2.128 |
Wast | -1.958 |
fronts | -1.841 |
Synd | -1.841 |
Token | . |
Token ID | 13 |
Feature activation | +2.40e-03 |
Pos logit contributions | |
zona | +2.527 |
RESULTS | +2.288 |
haar | +2.132 |
bley | +2.108 |
atos | +2.067 |
Neg logit contributions | |
raq | -1.956 |
hai | -1.846 |
Wast | -1.628 |
Wars | -1.570 |
obar | -1.535 |
Token | He |
Token ID | 679 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
zona | +0.034 |
RESULTS | +0.031 |
haar | +0.029 |
bley | +0.029 |
atos | +0.028 |
Neg logit contributions | |
raq | -0.024 |
hai | -0.022 |
Wast | -0.020 |
Wars | -0.019 |
fronts | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
zona | +0.340 |
RESULTS | +0.309 |
haar | +0.290 |
bley | +0.285 |
atos | +0.278 |
Neg logit contributions | |
raq | -0.247 |
hai | -0.232 |
Wast | -0.208 |
Wars | -0.198 |
Synd | -0.194 |
Token | " |
Token ID | 366 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
zona | +0.229 |
RESULTS | +0.208 |
haar | +0.195 |
bley | +0.192 |
atos | +0.186 |
Neg logit contributions | |
raq | -0.171 |
hai | -0.162 |
Wast | -0.144 |
Wars | -0.137 |
fronts | -0.135 |
Token | m |
Token ID | 76 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
raq | +0.741 |
hai | +0.705 |
Wast | +0.636 |
Wars | +0.607 |
fronts | +0.599 |
Neg logit contributions | |
zona | -0.870 |
RESULTS | -0.788 |
haar | -0.735 |
bley | -0.719 |
atos | -0.700 |
Token | oved |
Token ID | 2668 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
raq | +10.754 |
hai | +10.682 |
iles | +10.322 |
iling | +9.326 |
tered | +9.209 |
Neg logit contributions | |
RESULTS | -12.419 |
zona | -12.140 |
haar | -10.522 |
bley | -10.371 |
aukee | -9.723 |
Token | to |
Token ID | 284 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
zona | +3.661 |
RESULTS | +3.224 |
haar | +3.058 |
bley | +3.025 |
atos | +2.920 |
Neg logit contributions | |
raq | -3.340 |
hai | -3.162 |
Wast | -2.891 |
Wars | -2.761 |
Synd | -2.729 |
Token | tears |
Token ID | 10953 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
raq | +0.357 |
hai | +0.339 |
Wast | +0.306 |
Wars | +0.292 |
fronts | +0.288 |
Neg logit contributions | |
zona | -0.413 |
RESULTS | -0.372 |
haar | -0.347 |
bley | -0.340 |
atos | -0.331 |
Token | ," |
Token ID | 553 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
zona | +3.178 |
RESULTS | +2.828 |
haar | +2.651 |
bley | +2.633 |
atos | +2.507 |
Neg logit contributions | |
raq | -3.067 |
hai | -2.929 |
Wast | -2.677 |
Wars | -2.567 |
Synd | -2.501 |
Token | according |
Token ID | 1864 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
raq | +0.881 |
hai | +0.837 |
Wast | +0.752 |
Wars | +0.713 |
Synd | +0.705 |
Neg logit contributions | |
zona | -1.151 |
RESULTS | -1.047 |
haar | -0.981 |
bley | -0.960 |
atos | -0.935 |
Token | - |
Token ID | 12 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
zona | +1.952 |
RESULTS | +1.763 |
haar | +1.646 |
bley | +1.619 |
atos | +1.574 |
Neg logit contributions | |
raq | -1.630 |
hai | -1.541 |
Wast | -1.392 |
Wars | -1.325 |
fronts | -1.308 |
Token | year |
Token ID | 1941 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
raq | +0.771 |
hai | +0.717 |
Wast | +0.587 |
Wars | +0.545 |
iles | +0.532 |
Neg logit contributions | |
zona | -2.016 |
RESULTS | -1.869 |
haar | -1.781 |
bley | -1.751 |
atos | -1.722 |
Token | - |
Token ID | 12 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
zona | +3.511 |
RESULTS | +3.153 |
haar | +2.961 |
bley | +2.875 |
iscons | +2.842 |
Neg logit contributions | |
raq | -3.084 |
hai | -2.911 |
Wast | -2.606 |
Wars | -2.503 |
Synd | -2.445 |
Token | old |
Token ID | 727 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
zona | +0.864 |
RESULTS | +0.788 |
haar | +0.740 |
bley | +0.724 |
atos | +0.709 |
Neg logit contributions | |
raq | -0.615 |
hai | -0.578 |
Wast | -0.524 |
fronts | -0.492 |
Wars | -0.491 |
Token | , |
Token ID | 11 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
raq | +1.684 |
hai | +1.602 |
Wast | +1.456 |
Synd | +1.353 |
fronts | +1.351 |
Neg logit contributions | |
zona | -2.472 |
RESULTS | -2.262 |
haar | -2.127 |
bley | -2.080 |
atos | -2.019 |
Token | m |
Token ID | 285 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
raq | +0.205 |
hai | +0.195 |
Wast | +0.174 |
Wars | +0.165 |
fronts | +0.162 |
Neg logit contributions | |
zona | -0.281 |
RESULTS | -0.256 |
haar | -0.240 |
bley | -0.235 |
atos | -0.229 |
Token | op |
Token ID | 404 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
raq | +11.745 |
hai | +11.041 |
iles | +10.225 |
uer | +10.030 |
obar | +9.882 |
Neg logit contributions | |
zona | -11.824 |
RESULTS | -11.624 |
bley | -10.227 |
haar | -9.446 |
aukee | -9.023 |
Token | - |
Token ID | 12 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
raq | +1.688 |
hai | +1.613 |
Wast | +1.450 |
Wars | +1.381 |
tered | +1.375 |
Neg logit contributions | |
zona | -2.003 |
RESULTS | -1.827 |
haar | -1.681 |
bley | -1.641 |
atos | -1.596 |
Token | headed |
Token ID | 15353 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
raq | +1.953 |
hai | +1.866 |
Wast | +1.644 |
Wars | +1.577 |
fronts | +1.550 |
Neg logit contributions | |
zona | -2.498 |
RESULTS | -2.273 |
haar | -2.112 |
bley | -2.055 |
atos | -2.015 |
Token | father |
Token ID | 2988 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
raq | +0.739 |
hai | +0.702 |
Wast | +0.630 |
Wars | +0.593 |
fronts | +0.588 |
Neg logit contributions | |
zona | -1.020 |
RESULTS | -0.932 |
haar | -0.874 |
bley | -0.856 |
atos | -0.833 |
Token | of |
Token ID | 286 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
raq | +1.629 |
hai | +1.548 |
Wast | +1.381 |
fronts | +1.310 |
Wars | +1.305 |
Neg logit contributions | |
zona | -2.329 |
RESULTS | -2.128 |
haar | -2.004 |
bley | -1.967 |
atos | -1.899 |
Token | y |
Token ID | 88 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
raq | +2.013 |
hai | +1.933 |
Wast | +1.706 |
Wars | +1.626 |
fronts | +1.622 |
Neg logit contributions | |
zona | -2.542 |
RESULTS | -2.338 |
haar | -2.166 |
bley | -2.098 |
iscons | -2.059 |
Token | , |
Token ID | 11 |
Feature activation | -2.95e-03 |
Pos logit contributions | |
zona | +0.521 |
RESULTS | +0.475 |
haar | +0.446 |
bley | +0.439 |
atos | +0.428 |
Neg logit contributions | |
raq | -0.367 |
hai | -0.346 |
Wast | -0.308 |
Wars | -0.294 |
Synd | -0.287 |
Token | with |
Token ID | 351 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
raq | +0.030 |
hai | +0.029 |
Wast | +0.026 |
Wars | +0.024 |
fronts | +0.024 |
Neg logit contributions | |
zona | -0.041 |
RESULTS | -0.037 |
haar | -0.035 |
bley | -0.034 |
atos | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
raq | +2.831 |
hai | +2.701 |
Wast | +2.436 |
fronts | +2.320 |
Synd | +2.282 |
Neg logit contributions | |
zona | -3.856 |
RESULTS | -3.533 |
haar | -3.280 |
bley | -3.205 |
atos | -3.148 |
Token | cool |
Token ID | 3608 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
raq | +0.675 |
hai | +0.640 |
Wast | +0.572 |
Wars | +0.540 |
Synd | +0.534 |
Neg logit contributions | |
zona | -0.940 |
RESULTS | -0.861 |
haar | -0.803 |
bley | -0.787 |
atos | -0.771 |
Token | m |
Token ID | 285 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
raq | +2.301 |
hai | +2.209 |
Wast | +1.973 |
Synd | +1.870 |
fronts | +1.867 |
Neg logit contributions | |
zona | -2.870 |
RESULTS | -2.638 |
haar | -2.430 |
bley | -2.382 |
atos | -2.315 |
Token | oust |
Token ID | 23968 |
Feature activation | +7.50e-04 |
Pos logit contributions | |
raq | +9.072 |
hai | +8.697 |
usal | +7.171 |
uer | +7.169 |
obar | +7.157 |
Neg logit contributions | |
zona | -13.541 |
RESULTS | -13.168 |
bley | -11.672 |
haar | -11.111 |
aukee | -10.939 |
Token | ache |
Token ID | 4891 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
zona | +0.010 |
RESULTS | +0.009 |
haar | +0.008 |
bley | +0.008 |
atos | +0.008 |
Neg logit contributions | |
raq | -0.008 |
hai | -0.008 |
Wast | -0.007 |
Wars | -0.007 |
fronts | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
zona | +2.337 |
RESULTS | +2.129 |
haar | +2.012 |
bley | +1.975 |
atos | +1.931 |
Neg logit contributions | |
raq | -1.616 |
hai | -1.503 |
Wast | -1.347 |
Wars | -1.286 |
Synd | -1.256 |
Token | a |
Token ID | 257 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
raq | +0.651 |
hai | +0.618 |
Wast | +0.555 |
Wars | +0.527 |
fronts | +0.521 |
Neg logit contributions | |
zona | -0.840 |
RESULTS | -0.765 |
haar | -0.714 |
bley | -0.700 |
atos | -0.682 |
Token | bit |
Token ID | 1643 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
raq | +1.313 |
hai | +1.247 |
Wast | +1.114 |
Wars | +1.050 |
fronts | +1.040 |
Neg logit contributions | |
zona | -1.834 |
RESULTS | -1.685 |
haar | -1.567 |
bley | -1.534 |
atos | -1.508 |
Token | a |
Token ID | 257 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
raq | +1.380 |
hai | +1.300 |
Wast | +1.177 |
Wars | +1.104 |
Synd | +1.102 |
Neg logit contributions | |
zona | -1.875 |
RESULTS | -1.718 |
haar | -1.601 |
bley | -1.571 |
atos | -1.534 |
Token | white |
Token ID | 2330 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
zona | +1.260 |
RESULTS | +1.144 |
haar | +1.078 |
bley | +1.056 |
atos | +1.025 |
Neg logit contributions | |
raq | -0.925 |
hai | -0.877 |
Wast | -0.776 |
Wars | -0.744 |
fronts | -0.730 |
Token | and |
Token ID | 290 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
raq | +1.731 |
hai | +1.659 |
Wast | +1.494 |
Synd | +1.394 |
fronts | +1.392 |
Neg logit contributions | |
zona | -2.498 |
RESULTS | -2.289 |
haar | -2.141 |
bley | -2.116 |
atos | -2.042 |
Token | black |
Token ID | 2042 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
zona | +1.623 |
RESULTS | +1.467 |
haar | +1.380 |
bley | +1.353 |
iscons | +1.309 |
Neg logit contributions | |
raq | -1.271 |
hai | -1.211 |
Wast | -1.085 |
Wars | -1.041 |
Synd | -1.018 |
Token | gay |
Token ID | 5650 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
zona | +0.482 |
RESULTS | +0.438 |
haar | +0.409 |
bley | +0.401 |
atos | +0.391 |
Neg logit contributions | |
raq | -0.380 |
hai | -0.360 |
Wast | -0.322 |
Wars | -0.308 |
Synd | -0.302 |
Token | m |
Token ID | 285 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
zona | +1.809 |
RESULTS | +1.637 |
haar | +1.537 |
bley | +1.504 |
atos | +1.482 |
Neg logit contributions | |
raq | -1.336 |
hai | -1.247 |
Wast | -1.113 |
Wars | -1.070 |
Synd | -1.040 |
Token | oles |
Token ID | 4316 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
raq | +10.026 |
hai | +9.683 |
uer | +8.742 |
ista | +8.497 |
iles | +8.374 |
Neg logit contributions | |
zona | -11.736 |
RESULTS | -11.611 |
bley | -10.764 |
aukee | -10.018 |
haar | -9.881 |
Token | ters |
Token ID | 1010 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
raq | +1.758 |
hai | +1.662 |
Wast | +1.466 |
Wars | +1.379 |
tered | +1.375 |
Neg logit contributions | |
zona | -2.622 |
RESULTS | -2.408 |
haar | -2.245 |
bley | -2.199 |
atos | -2.144 |
Token | as |
Token ID | 355 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
zona | +0.459 |
RESULTS | +0.416 |
haar | +0.391 |
bley | +0.383 |
atos | +0.373 |
Neg logit contributions | |
raq | -0.355 |
hai | -0.336 |
Wast | -0.302 |
Wars | -0.287 |
fronts | -0.282 |
Token | well |
Token ID | 880 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
raq | +0.768 |
hai | +0.729 |
Wast | +0.655 |
Wars | +0.621 |
fronts | +0.617 |
Neg logit contributions | |
zona | -1.015 |
RESULTS | -0.922 |
haar | -0.863 |
bley | -0.848 |
atos | -0.824 |
Token | as |
Token ID | 355 |
Feature activation | +4.93e-03 |
Pos logit contributions | |
raq | +2.302 |
hai | +2.232 |
Wast | +1.985 |
Wars | +1.882 |
fronts | +1.881 |
Neg logit contributions | |
zona | -3.165 |
RESULTS | -2.879 |
haar | -2.688 |
bley | -2.654 |
iscons | -2.568 |
Token | All |
Token ID | 1439 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
raq | +7.223 |
hai | +6.770 |
Wast | +6.647 |
fronts | +6.181 |
Synd | +6.065 |
Neg logit contributions | |
zona | -10.166 |
RESULTS | -9.356 |
haar | -8.788 |
bley | -8.544 |
atos | -8.425 |
Token | - |
Token ID | 12 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
raq | +1.034 |
hai | +0.983 |
Wast | +0.886 |
Wars | +0.841 |
fronts | +0.834 |
Neg logit contributions | |
zona | -1.332 |
RESULTS | -1.213 |
haar | -1.139 |
bley | -1.114 |
atos | -1.083 |
Token | Ter |
Token ID | 15156 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
raq | +0.404 |
hai | +0.385 |
Wast | +0.349 |
Wars | +0.332 |
Synd | +0.329 |
Neg logit contributions | |
zona | -0.447 |
RESULTS | -0.404 |
haar | -0.375 |
bley | -0.368 |
atos | -0.357 |
Token | rain |
Token ID | 3201 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
zona | +1.433 |
RESULTS | +1.272 |
haar | +1.165 |
bley | +1.129 |
atos | +1.108 |
Neg logit contributions | |
raq | -1.950 |
hai | -1.880 |
Wast | -1.725 |
Wars | -1.675 |
fronts | -1.662 |
Token | KO |
Token ID | 21054 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
raq | +5.941 |
hai | +5.586 |
Wast | +5.351 |
fronts | +5.037 |
Synd | +4.950 |
Neg logit contributions | |
zona | -8.461 |
RESULTS | -7.649 |
haar | -7.274 |
bley | -7.041 |
atos | -6.849 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
raq | +4.594 |
hai | +4.344 |
Wast | +4.042 |
fronts | +3.834 |
Synd | +3.749 |
Neg logit contributions | |
zona | -5.691 |
RESULTS | -5.142 |
haar | -4.862 |
bley | -4.683 |
atos | -4.536 |
Token | tires |
Token ID | 17920 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
raq | +9.119 |
hai | +8.439 |
Wast | +8.369 |
fronts | +7.915 |
Synd | +7.478 |
Neg logit contributions | |
zona | -13.118 |
RESULTS | -11.837 |
haar | -11.345 |
bley | -11.049 |
atos | -10.663 |
Token | specifically |
Token ID | 5734 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
raq | +5.566 |
hai | +5.311 |
Wast | +4.712 |
fronts | +4.654 |
iles | +4.533 |
Neg logit contributions | |
zona | -9.413 |
RESULTS | -8.747 |
haar | -8.089 |
bley | -8.087 |
iscons | -7.998 |
Token | designed |
Token ID | 3562 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
raq | +3.505 |
hai | +3.385 |
Wast | +2.961 |
fronts | +2.834 |
Synd | +2.749 |
Neg logit contributions | |
zona | -6.910 |
RESULTS | -6.446 |
bley | -5.988 |
haar | -5.986 |
iscons | -5.871 |
Token | for |
Token ID | 329 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
raq | +2.685 |
hai | +2.481 |
Wast | +2.228 |
fronts | +2.132 |
Wars | +2.080 |
Neg logit contributions | |
zona | -4.539 |
RESULTS | -4.269 |
haar | -3.938 |
bley | -3.901 |
atos | -3.797 |
Token | off |
Token ID | 572 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
raq | +2.140 |
hai | +2.013 |
Wast | +1.835 |
fronts | +1.725 |
Synd | +1.718 |
Neg logit contributions | |
zona | -2.773 |
RESULTS | -2.524 |
haar | -2.362 |
bley | -2.300 |
atos | -2.250 |
Token | focus |
Token ID | 2962 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
zona | +2.376 |
RESULTS | +2.147 |
haar | +2.014 |
bley | +1.978 |
atos | +1.932 |
Neg logit contributions | |
raq | -1.939 |
hai | -1.826 |
Wast | -1.635 |
Wars | -1.563 |
obar | -1.528 |
Token | and |
Token ID | 290 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
raq | +0.836 |
hai | +0.794 |
Wast | +0.712 |
Wars | +0.680 |
fronts | +0.672 |
Neg logit contributions | |
zona | -1.070 |
RESULTS | -0.974 |
haar | -0.907 |
bley | -0.890 |
atos | -0.865 |
Token | stability |
Token ID | 10159 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
raq | +0.638 |
hai | +0.605 |
Wast | +0.540 |
Wars | +0.512 |
fronts | +0.505 |
Neg logit contributions | |
zona | -0.872 |
RESULTS | -0.795 |
haar | -0.745 |
bley | -0.731 |
atos | -0.712 |
Token | ; |
Token ID | 26 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
zona | +1.139 |
RESULTS | +1.030 |
haar | +0.964 |
bley | +0.945 |
atos | +0.920 |
Neg logit contributions | |
raq | -0.985 |
hai | -0.936 |
Wast | -0.846 |
Wars | -0.802 |
Synd | -0.789 |
Token | its |
Token ID | 663 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
raq | +0.570 |
hai | +0.539 |
Wast | +0.482 |
Wars | +0.457 |
fronts | +0.450 |
Neg logit contributions | |
zona | -0.782 |
RESULTS | -0.713 |
haar | -0.668 |
bley | -0.655 |
atos | -0.639 |
Token | m |
Token ID | 285 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
raq | +1.553 |
hai | +1.481 |
Wast | +1.320 |
Wars | +1.251 |
fronts | +1.251 |
Neg logit contributions | |
zona | -2.151 |
RESULTS | -1.955 |
haar | -1.834 |
bley | -1.802 |
atos | -1.756 |
Token | é |
Token ID | 2634 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
raq | +9.723 |
hai | +9.048 |
iles | +8.156 |
uer | +7.910 |
ista | +7.624 |
Neg logit contributions | |
zona | -12.701 |
RESULTS | -11.847 |
bley | -10.819 |
haar | -10.220 |
aukee | -9.800 |
Token | tier |
Token ID | 24948 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
raq | +4.502 |
hai | +4.337 |
Wast | +3.778 |
Wars | +3.722 |
tered | +3.722 |
Neg logit contributions | |
zona | -4.282 |
RESULTS | -3.826 |
haar | -3.489 |
bley | -3.422 |
atos | -3.259 |
Token | is |
Token ID | 318 |
Feature activation | +9.75e-02 |
Pos logit contributions | |
zona | +0.693 |
RESULTS | +0.631 |
haar | +0.594 |
bley | +0.582 |
atos | +0.569 |
Neg logit contributions | |
raq | -0.495 |
hai | -0.467 |
Wast | -0.418 |
Wars | -0.395 |
Synd | -0.389 |
Token | bearing |
Token ID | 14121 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
zona | +1.338 |
RESULTS | +1.211 |
haar | +1.134 |
bley | +1.109 |
atos | +1.090 |
Neg logit contributions | |
raq | -1.007 |
hai | -0.955 |
Wast | -0.854 |
Wars | -0.809 |
fronts | -0.796 |
Token | witness |
Token ID | 4973 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
raq | +2.387 |
hai | +2.267 |
Wast | +2.014 |
fronts | +1.897 |
Wars | +1.886 |
Neg logit contributions | |
zona | -4.026 |
RESULTS | -3.711 |
haar | -3.501 |
bley | -3.415 |
iscons | -3.361 |
Token | of |
Token ID | 286 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
zona | +1.914 |
RESULTS | +1.741 |
haar | +1.631 |
bley | +1.608 |
atos | +1.562 |
Neg logit contributions | |
raq | -1.423 |
hai | -1.344 |
Wast | -1.209 |
Wars | -1.147 |
Synd | -1.130 |
Token | growth |
Token ID | 3349 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
zona | +1.628 |
RESULTS | +1.482 |
haar | +1.390 |
bley | +1.361 |
atos | +1.334 |
Neg logit contributions | |
raq | -1.195 |
hai | -1.135 |
Wast | -0.998 |
Wars | -0.954 |
Synd | -0.937 |
Token | have |
Token ID | 423 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
raq | +1.984 |
hai | +1.891 |
Wast | +1.653 |
Wars | +1.574 |
fronts | +1.573 |
Neg logit contributions | |
zona | -3.150 |
RESULTS | -2.916 |
haar | -2.728 |
bley | -2.666 |
iscons | -2.622 |
Token | led |
Token ID | 2957 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
raq | +0.096 |
hai | +0.091 |
Wast | +0.082 |
Wars | +0.077 |
fronts | +0.077 |
Neg logit contributions | |
zona | -0.129 |
RESULTS | -0.118 |
haar | -0.110 |
bley | -0.108 |
atos | -0.105 |
Token | a |
Token ID | 257 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
zona | +1.817 |
RESULTS | +1.646 |
haar | +1.540 |
bley | +1.514 |
atos | +1.478 |
Neg logit contributions | |
raq | -1.388 |
hai | -1.315 |
Wast | -1.172 |
Wars | -1.117 |
fronts | -1.104 |
Token | mell |
Token ID | 33748 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
raq | +1.659 |
hai | +1.575 |
Wast | +1.416 |
Wars | +1.318 |
Synd | +1.309 |
Neg logit contributions | |
zona | -2.380 |
RESULTS | -2.196 |
haar | -2.050 |
bley | -2.000 |
atos | -1.962 |
Token | ow |
Token ID | 322 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
raq | +7.380 |
hai | +7.038 |
obar | +6.080 |
tered | +5.953 |
iles | +5.923 |
Neg logit contributions | |
zona | -14.416 |
RESULTS | -13.865 |
haar | -12.681 |
bley | -12.375 |
aukee | -12.080 |
Token | rhythm |
Token ID | 18662 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
raq | +3.302 |
hai | +3.188 |
Wast | +2.857 |
Synd | +2.663 |
fronts | +2.648 |
Neg logit contributions | |
zona | -4.663 |
RESULTS | -4.351 |
haar | -4.035 |
bley | -3.972 |
iscons | -3.864 |
Token | to |
Token ID | 284 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
zona | +2.813 |
RESULTS | +2.528 |
haar | +2.369 |
bley | +2.336 |
atos | +2.285 |
Neg logit contributions | |
raq | -2.426 |
hai | -2.299 |
Wast | -2.085 |
Wars | -1.987 |
Synd | -1.941 |
Token | their |
Token ID | 511 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
raq | +1.302 |
hai | +1.234 |
Wast | +1.104 |
Wars | +1.046 |
Synd | +1.032 |
Neg logit contributions | |
zona | -1.800 |
RESULTS | -1.644 |
haar | -1.541 |
bley | -1.512 |
atos | -1.472 |
Token | days |
Token ID | 1528 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
raq | +4.420 |
hai | +4.247 |
Wast | +3.828 |
fronts | +3.710 |
prominence | +3.695 |
Neg logit contributions | |
zona | -6.363 |
RESULTS | -5.710 |
haar | -5.457 |
bley | -5.275 |
iscons | -5.184 |
Token | following |
Token ID | 1708 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
raq | +1.000 |
hai | +0.949 |
Wast | +0.826 |
Wars | +0.773 |
Synd | +0.763 |
Neg logit contributions | |
zona | -1.869 |
RESULTS | -1.724 |
haar | -1.621 |
bley | -1.594 |
atos | -1.559 |
Token | at |
Token ID | 379 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
raq | +2.862 |
hai | +2.729 |
Wast | +2.452 |
fronts | +2.314 |
Wars | +2.309 |
Neg logit contributions | |
zona | -4.179 |
RESULTS | -3.789 |
haar | -3.550 |
bley | -3.489 |
iscons | -3.404 |
Token | Ham |
Token ID | 4345 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
raq | +2.985 |
hai | +2.860 |
Wast | +2.584 |
Synd | +2.459 |
Wars | +2.441 |
Neg logit contributions | |
zona | -3.829 |
RESULTS | -3.488 |
haar | -3.220 |
bley | -3.161 |
atos | -3.079 |
Token | ill |
Token ID | 359 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
raq | +0.552 |
hai | +0.523 |
Wast | +0.453 |
Wars | +0.426 |
iles | +0.419 |
Neg logit contributions | |
zona | -0.953 |
RESULTS | -0.874 |
haar | -0.824 |
bley | -0.808 |
atos | -0.791 |
Token | ( |
Token ID | 357 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
raq | +0.841 |
hai | +0.802 |
Wast | +0.720 |
Wars | +0.683 |
fronts | +0.675 |
Neg logit contributions | |
zona | -1.087 |
RESULTS | -0.988 |
haar | -0.922 |
bley | -0.904 |
atos | -0.881 |
Token | m |
Token ID | 76 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
raq | +3.795 |
hai | +3.663 |
Wast | +3.215 |
Wars | +3.127 |
iles | +3.043 |
Neg logit contributions | |
zona | -4.733 |
RESULTS | -4.259 |
haar | -3.970 |
bley | -3.929 |
atos | -3.819 |
Token | essing |
Token ID | 27289 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
hai | +10.596 |
raq | +10.446 |
iles | +9.817 |
iling | +8.859 |
tered | +8.815 |
Neg logit contributions | |
zona | -10.882 |
RESULTS | -10.562 |
bley | -8.975 |
haar | -8.973 |
aukee | -8.463 |
Token | up |
Token ID | 510 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
zona | +0.697 |
RESULTS | +0.632 |
haar | +0.592 |
bley | +0.580 |
atos | +0.564 |
Neg logit contributions | |
raq | -0.557 |
hai | -0.528 |
Wast | -0.475 |
Wars | -0.453 |
fronts | -0.446 |
Token | his |
Token ID | 465 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
zona | +1.151 |
RESULTS | +1.043 |
haar | +0.980 |
bley | +0.963 |
atos | +0.934 |
Neg logit contributions | |
raq | -0.914 |
hai | -0.866 |
Wast | -0.775 |
Wars | -0.740 |
Synd | -0.724 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
zona | +1.537 |
RESULTS | +1.397 |
haar | +1.317 |
bley | +1.291 |
atos | +1.247 |
Neg logit contributions | |
raq | -1.195 |
hai | -1.122 |
Wast | -1.004 |
Wars | -0.954 |
obar | -0.939 |
Token | handle |
Token ID | 5412 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
zona | +0.688 |
RESULTS | +0.630 |
haar | +0.591 |
bley | +0.580 |
atos | +0.563 |
Neg logit contributions | |
raq | -0.487 |
hai | -0.459 |
Wast | -0.407 |
Wars | -0.387 |
Synd | -0.380 |
Token | that |
Token ID | 326 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
raq | +1.486 |
hai | +1.405 |
Wast | +1.269 |
fronts | +1.205 |
Wars | +1.202 |
Neg logit contributions | |
zona | -1.962 |
RESULTS | -1.781 |
haar | -1.683 |
bley | -1.643 |
iscons | -1.596 |
Token | includes |
Token ID | 3407 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
raq | +0.646 |
hai | +0.610 |
Wast | +0.539 |
Wars | +0.508 |
fronts | +0.502 |
Neg logit contributions | |
zona | -1.030 |
RESULTS | -0.943 |
haar | -0.889 |
bley | -0.872 |
atos | -0.852 |
Token | Best |
Token ID | 6705 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
raq | +2.386 |
hai | +2.243 |
Wast | +2.063 |
fronts | +1.951 |
Synd | +1.926 |
Neg logit contributions | |
zona | -3.204 |
RESULTS | -2.913 |
haar | -2.745 |
bley | -2.679 |
atos | -2.620 |
Token | in |
Token ID | 287 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
raq | +1.101 |
hai | +1.048 |
Wast | +0.946 |
Wars | +0.899 |
Synd | +0.888 |
Neg logit contributions | |
zona | -1.353 |
RESULTS | -1.229 |
haar | -1.151 |
bley | -1.124 |
atos | -1.095 |
Token | the |
Token ID | 262 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
raq | +0.408 |
hai | +0.384 |
Wast | +0.347 |
Wars | +0.328 |
Synd | +0.326 |
Neg logit contributions | |
zona | -0.540 |
RESULTS | -0.497 |
haar | -0.463 |
bley | -0.452 |
atos | -0.442 |
Token | Desert |
Token ID | 18692 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
zona | +2.495 |
RESULTS | +2.169 |
haar | +2.060 |
bley | +2.024 |
atos | +1.965 |
Neg logit contributions | |
raq | -2.356 |
hai | -2.261 |
Wast | -1.995 |
Wars | -1.957 |
fronts | -1.945 |
Token | , |
Token ID | 11 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
raq | +8.692 |
Wast | +7.909 |
hai | +7.894 |
fronts | +7.479 |
Synd | +7.365 |
Neg logit contributions | |
zona | -12.475 |
RESULTS | -11.691 |
haar | -11.322 |
iscons | -10.903 |
bley | -10.660 |
Token | Lucas |
Token ID | 15257 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
raq | +3.641 |
hai | +3.471 |
Wast | +3.270 |
Synd | +3.025 |
fronts | +3.010 |
Neg logit contributions | |
zona | -4.764 |
RESULTS | -4.369 |
haar | -4.140 |
bley | -4.009 |
atos | -3.915 |
Token | Oil |
Token ID | 11474 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
zona | +3.863 |
RESULTS | +3.454 |
haar | +3.062 |
atos | +3.026 |
bley | +3.024 |
Neg logit contributions | |
raq | -4.346 |
hai | -4.187 |
Wast | -3.665 |
iles | -3.651 |
Wars | -3.633 |
Token | Off |
Token ID | 3242 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
zona | +4.631 |
RESULTS | +4.112 |
bley | +3.782 |
haar | +3.774 |
aukee | +3.669 |
Neg logit contributions | |
raq | -3.932 |
hai | -3.832 |
Wast | -3.281 |
Wars | -3.241 |
iles | -3.217 |
Token | Road |
Token ID | 5567 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
zona | +3.564 |
RESULTS | +3.211 |
haar | +2.979 |
bley | +2.922 |
iscons | +2.852 |
Neg logit contributions | |
raq | -3.144 |
hai | -3.004 |
Wast | -2.648 |
Wars | -2.570 |
Synd | -2.525 |
Token | . |
Token ID | 13 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
raq | +1.487 |
hai | +1.408 |
Wast | +1.266 |
Wars | +1.198 |
fronts | +1.191 |
Neg logit contributions | |
zona | -2.054 |
RESULTS | -1.882 |
haar | -1.766 |
bley | -1.728 |
atos | -1.680 |
Token | He |
Token ID | 679 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
raq | +1.838 |
hai | +1.737 |
Wast | +1.580 |
Wars | +1.474 |
Synd | +1.468 |
Neg logit contributions | |
zona | -2.805 |
RESULTS | -2.548 |
haar | -2.420 |
bley | -2.384 |
atos | -2.315 |
Token | also |
Token ID | 635 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
raq | +1.627 |
hai | +1.541 |
Wast | +1.371 |
fronts | +1.313 |
Wars | +1.287 |
Neg logit contributions | |
zona | -2.433 |
RESULTS | -2.226 |
haar | -2.096 |
bley | -2.049 |
atos | -1.989 |
Token | performs |
Token ID | 17706 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
zona | +1.628 |
RESULTS | +1.481 |
haar | +1.390 |
bley | +1.368 |
atos | +1.343 |
Neg logit contributions | |
raq | -1.102 |
hai | -1.037 |
Wast | -0.914 |
Wars | -0.873 |
obar | -0.846 |
Token | " |
Token ID | 366 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
zona | +3.219 |
RESULTS | +2.918 |
haar | +2.700 |
bley | +2.678 |
atos | +2.618 |
Neg logit contributions | |
raq | -2.690 |
hai | -2.579 |
Wast | -2.252 |
Wars | -2.184 |
iles | -2.135 |
Token | Sm |
Token ID | 7556 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
zona | +0.458 |
RESULTS | +0.416 |
haar | +0.388 |
bley | +0.380 |
atos | +0.370 |
Neg logit contributions | |
raq | -0.370 |
hai | -0.351 |
Wast | -0.317 |
fronts | -0.298 |
Wars | -0.298 |
Token | ells |
Token ID | 19187 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
raq | +9.112 |
hai | +8.803 |
iles | +8.802 |
iling | +7.981 |
ilation | +7.565 |
Neg logit contributions | |
zona | -12.513 |
RESULTS | -12.058 |
haar | -10.496 |
bley | -10.062 |
atos | -9.812 |
Token | Like |
Token ID | 4525 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
raq | +3.716 |
hai | +3.338 |
Wast | +3.162 |
iles | +2.839 |
Synd | +2.797 |
Neg logit contributions | |
zona | -7.308 |
RESULTS | -6.890 |
haar | -6.379 |
bley | -6.139 |
iscons | -6.126 |
Token | Teen |
Token ID | 21432 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
raq | +4.444 |
Wast | +4.066 |
hai | +4.021 |
Synd | +3.789 |
Borders | +3.701 |
Neg logit contributions | |
zona | -6.512 |
RESULTS | -6.039 |
haar | -5.636 |
bley | -5.553 |
iscons | -5.322 |
Token | Spirit |
Token ID | 7710 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
raq | +0.435 |
hai | +0.416 |
Wast | +0.379 |
Wars | +0.363 |
Synd | +0.359 |
Neg logit contributions | |
zona | -0.431 |
RESULTS | -0.387 |
haar | -0.358 |
bley | -0.350 |
atos | -0.339 |
Token | " |
Token ID | 1 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
raq | +1.826 |
hai | +1.723 |
Wast | +1.561 |
Wars | +1.470 |
Synd | +1.461 |
Neg logit contributions | |
zona | -2.495 |
RESULTS | -2.313 |
haar | -2.145 |
bley | -2.097 |
iscons | -2.033 |
Token | D |
Token ID | 360 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
raq | +1.637 |
hai | +1.550 |
Wast | +1.412 |
Wars | +1.323 |
Synd | +1.310 |
Neg logit contributions | |
zona | -2.258 |
RESULTS | -2.040 |
haar | -1.934 |
bley | -1.896 |
atos | -1.843 |
Token | UST |
Token ID | 7759 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
raq | +2.052 |
hai | +1.949 |
Wast | +1.785 |
iles | +1.697 |
Wars | +1.694 |
Neg logit contributions | |
zona | -2.111 |
RESULTS | -1.881 |
haar | -1.766 |
bley | -1.716 |
atos | -1.683 |
Token | W |
Token ID | 54 |
Feature activation | +2.71e-03 |
Pos logit contributions | |
raq | +1.260 |
hai | +1.180 |
Wast | +1.031 |
Wars | +0.968 |
fronts | +0.934 |
Neg logit contributions | |
zona | -2.500 |
RESULTS | -2.294 |
haar | -2.184 |
bley | -2.154 |
atos | -2.106 |
Token | UN |
Token ID | 4944 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
zona | +0.044 |
RESULTS | +0.040 |
haar | +0.038 |
bley | +0.038 |
atos | +0.037 |
Neg logit contributions | |
raq | -0.022 |
hai | -0.020 |
Wast | -0.017 |
Wars | -0.016 |
fronts | -0.016 |
Token | FOR |
Token ID | 7473 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
raq | +2.133 |
hai | +2.022 |
Wast | +1.844 |
Wars | +1.734 |
fronts | +1.715 |
Neg logit contributions | |
zona | -2.887 |
RESULTS | -2.603 |
haar | -2.474 |
bley | -2.417 |
atos | -2.354 |
Token | M |
Token ID | 337 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
raq | +1.881 |
hai | +1.777 |
Wast | +1.615 |
Wars | +1.525 |
Synd | +1.511 |
Neg logit contributions | |
zona | -2.440 |
RESULTS | -2.181 |
haar | -2.073 |
bley | -2.042 |
atos | -1.977 |
Token | EST |
Token ID | 6465 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
raq | +10.253 |
hai | +9.837 |
iles | +9.149 |
IND | +9.120 |
Wast | +8.918 |
Neg logit contributions | |
zona | -10.982 |
haar | -9.373 |
RESULTS | -9.157 |
bley | -8.724 |
atos | -8.607 |
Token | OP |
Token ID | 13349 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
raq | +0.780 |
hai | +0.739 |
Wast | +0.666 |
Wars | +0.631 |
Synd | +0.622 |
Neg logit contributions | |
zona | -1.011 |
RESULTS | -0.915 |
haar | -0.861 |
bley | -0.844 |
atos | -0.822 |
Token | V |
Token ID | 569 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
zona | +0.695 |
RESULTS | +0.635 |
haar | +0.587 |
bley | +0.575 |
atos | +0.562 |
Neg logit contributions | |
raq | -0.579 |
hai | -0.552 |
Wast | -0.493 |
Wars | -0.472 |
fronts | -0.467 |
Token | B |
Token ID | 33 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
raq | +1.328 |
hai | +1.266 |
Wast | +1.143 |
Wars | +1.089 |
iles | +1.076 |
Neg logit contributions | |
zona | -1.559 |
RESULTS | -1.398 |
haar | -1.310 |
bley | -1.285 |
atos | -1.245 |
Token | 5 |
Token ID | 642 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
raq | +5.991 |
hai | +5.667 |
Wast | +5.190 |
iles | +4.878 |
Wars | +4.862 |
Neg logit contributions | |
zona | -7.985 |
RESULTS | -6.938 |
haar | -6.734 |
bley | -6.698 |
atos | -6.412 |
Token | medicine |
Token ID | 9007 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
zona | +4.732 |
RESULTS | +4.388 |
haar | +4.114 |
bley | +4.008 |
atos | +3.911 |
Neg logit contributions | |
raq | -3.449 |
hai | -3.194 |
Wast | -2.882 |
Wars | -2.810 |
obar | -2.720 |
Token | often |
Token ID | 1690 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
zona | +2.196 |
RESULTS | +2.007 |
haar | +1.880 |
bley | +1.840 |
atos | +1.797 |
Neg logit contributions | |
raq | -1.626 |
hai | -1.521 |
Wast | -1.361 |
Wars | -1.290 |
obar | -1.272 |
Token | did |
Token ID | 750 |
Feature activation | -6.80e-03 |
Pos logit contributions | |
zona | +2.787 |
RESULTS | +2.538 |
haar | +2.373 |
bley | +2.339 |
atos | +2.269 |
Neg logit contributions | |
raq | -2.128 |
hai | -1.972 |
Wast | -1.757 |
Wars | -1.693 |
iles | -1.654 |
Token | more |
Token ID | 517 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
raq | +0.070 |
hai | +0.066 |
Wast | +0.059 |
Wars | +0.056 |
Synd | +0.055 |
Neg logit contributions | |
zona | -0.094 |
RESULTS | -0.085 |
haar | -0.080 |
bley | -0.078 |
atos | -0.076 |
Token | harm |
Token ID | 4419 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
raq | +0.498 |
hai | +0.480 |
Wast | +0.444 |
Wars | +0.429 |
fronts | +0.425 |
Neg logit contributions | |
zona | -0.338 |
RESULTS | -0.295 |
haar | -0.267 |
bley | -0.260 |
atos | -0.249 |
Token | than |
Token ID | 621 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
zona | +2.101 |
RESULTS | +1.899 |
haar | +1.759 |
bley | +1.719 |
atos | +1.690 |
Neg logit contributions | |
raq | -2.015 |
hai | -1.943 |
Wast | -1.760 |
Wars | -1.665 |
Synd | -1.653 |
Token | it |
Token ID | 340 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
raq | +3.631 |
hai | +3.477 |
prominence | +3.258 |
Wast | +3.147 |
fronts | +2.964 |
Neg logit contributions | |
zona | -17.094 |
RESULTS | -16.131 |
haar | -15.255 |
bley | -14.831 |
iscons | -14.537 |
Token | did |
Token ID | 750 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
hai | +4.732 |
raq | +4.712 |
Wast | +4.238 |
fronts | +4.093 |
iles | +3.922 |
Neg logit contributions | |
zona | -9.849 |
RESULTS | -9.057 |
haar | -8.609 |
bley | -8.245 |
iscons | -8.175 |
Token | good |
Token ID | 922 |
Feature activation | -4.49e-03 |
Pos logit contributions | |
raq | +3.608 |
hai | +3.422 |
prominence | +3.157 |
Wast | +3.042 |
fronts | +3.032 |
Neg logit contributions | |
zona | -12.655 |
RESULTS | -11.840 |
haar | -11.245 |
bley | -10.882 |
iscons | -10.809 |
Token | . |
Token ID | 13 |
Feature activation | +5.73e-03 |
Pos logit contributions | |
raq | +0.047 |
hai | +0.045 |
Wast | +0.040 |
Wars | +0.038 |
fronts | +0.038 |
Neg logit contributions | |
zona | -0.061 |
RESULTS | -0.055 |
haar | -0.052 |
bley | -0.050 |
atos | -0.049 |
Token | Mol |
Token ID | 17958 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
zona | +0.080 |
RESULTS | +0.073 |
haar | +0.068 |
bley | +0.067 |
atos | +0.065 |
Neg logit contributions | |
raq | -0.058 |
hai | -0.055 |
Wast | -0.049 |
Wars | -0.046 |
fronts | -0.046 |
Token | by |
Token ID | 416 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
raq | +0.003 |
hai | +0.003 |
Wast | +0.003 |
Wars | +0.003 |
fronts | +0.003 |
Neg logit contributions | |
zona | -0.005 |
RESULTS | -0.004 |
haar | -0.004 |
bley | -0.004 |
atos | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
zona | +0.675 |
RESULTS | +0.612 |
haar | +0.572 |
bley | +0.561 |
atos | +0.545 |
Neg logit contributions | |
raq | -0.567 |
hai | -0.538 |
Wast | -0.483 |
Wars | -0.463 |
fronts | -0.456 |
Token | slim |
Token ID | 18862 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
zona | +0.378 |
RESULTS | +0.345 |
haar | +0.324 |
bley | +0.318 |
atos | +0.310 |
Neg logit contributions | |
raq | -0.261 |
hai | -0.247 |
Wast | -0.219 |
Wars | -0.208 |
fronts | -0.205 |
Token | y |
Token ID | 88 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
raq | +0.197 |
hai | +0.188 |
Wast | +0.169 |
Wars | +0.161 |
fronts | +0.159 |
Neg logit contributions | |
zona | -0.243 |
RESULTS | -0.221 |
haar | -0.206 |
bley | -0.202 |
atos | -0.196 |
Token | smooth |
Token ID | 7209 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
zona | +0.879 |
RESULTS | +0.799 |
haar | +0.752 |
bley | +0.737 |
atos | +0.720 |
Neg logit contributions | |
raq | -0.637 |
hai | -0.601 |
Wast | -0.535 |
Wars | -0.512 |
fronts | -0.502 |
Token | m |
Token ID | 285 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
raq | +3.614 |
hai | +3.567 |
Wast | +3.124 |
Synd | +2.908 |
iles | +2.893 |
Neg logit contributions | |
zona | -5.352 |
RESULTS | -5.066 |
haar | -4.586 |
bley | -4.495 |
atos | -4.339 |
Token | over |
Token ID | 2502 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
raq | +10.415 |
hai | +9.527 |
uer | +8.830 |
ista | +8.487 |
iles | +8.307 |
Neg logit contributions | |
zona | -11.223 |
RESULTS | -11.068 |
bley | -9.691 |
aukee | -9.081 |
haar | -9.037 |
Token | named |
Token ID | 3706 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
zona | +2.132 |
RESULTS | +1.928 |
haar | +1.819 |
bley | +1.783 |
atos | +1.736 |
Neg logit contributions | |
raq | -1.681 |
hai | -1.574 |
Wast | -1.420 |
Wars | -1.356 |
fronts | -1.332 |
Token | Dim |
Token ID | 14048 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
zona | +2.078 |
RESULTS | +1.874 |
haar | +1.750 |
bley | +1.719 |
atos | +1.676 |
Neg logit contributions | |
raq | -1.808 |
hai | -1.711 |
Wast | -1.519 |
Wars | -1.482 |
fronts | -1.460 |
Token | itri |
Token ID | 49510 |
Feature activation | -3.24e-03 |
Pos logit contributions | |
zona | +2.873 |
RESULTS | +2.555 |
haar | +2.457 |
bley | +2.445 |
atos | +2.367 |
Neg logit contributions | |
raq | -2.306 |
hai | -2.167 |
Wast | -1.943 |
Wars | -1.878 |
fronts | -1.861 |
Token | to |
Token ID | 284 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
raq | +0.035 |
hai | +0.033 |
Wast | +0.030 |
Wars | +0.028 |
fronts | +0.028 |
Neg logit contributions | |
zona | -0.043 |
RESULTS | -0.039 |
haar | -0.036 |
bley | -0.036 |
atos | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
zona | +1.888 |
RESULTS | +1.713 |
haar | +1.602 |
bley | +1.574 |
atos | +1.539 |
Neg logit contributions | |
raq | -1.428 |
hai | -1.343 |
Wast | -1.189 |
Wars | -1.150 |
Synd | -1.121 |
Token |
|
Token ID | 198 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
zona | +2.830 |
RESULTS | +2.629 |
haar | +2.400 |
bley | +2.319 |
atos | +2.314 |
Neg logit contributions | |
raq | -2.344 |
hai | -2.223 |
Wast | -1.976 |
fronts | -1.933 |
sugg | -1.894 |
Token | and |
Token ID | 392 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
zona | +0.250 |
RESULTS | +0.226 |
haar | +0.210 |
bley | +0.205 |
atos | +0.200 |
Neg logit contributions | |
raq | -0.221 |
hai | -0.210 |
Wast | -0.191 |
Wars | -0.181 |
fronts | -0.181 |
Token | for |
Token ID | 329 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
zona | +0.420 |
RESULTS | +0.383 |
haar | +0.359 |
bley | +0.352 |
atos | +0.345 |
Neg logit contributions | |
raq | -0.296 |
hai | -0.280 |
Wast | -0.247 |
Wars | -0.236 |
fronts | -0.231 |
Token | the |
Token ID | 262 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
zona | +0.412 |
RESULTS | +0.375 |
haar | +0.351 |
bley | +0.343 |
atos | +0.335 |
Neg logit contributions | |
raq | -0.330 |
hai | -0.314 |
Wast | -0.280 |
Wars | -0.269 |
fronts | -0.265 |
Token | most |
Token ID | 749 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
raq | +3.220 |
hai | +3.085 |
Wast | +2.835 |
fronts | +2.633 |
Synd | +2.626 |
Neg logit contributions | |
zona | -4.642 |
RESULTS | -4.208 |
haar | -3.938 |
bley | -3.893 |
atos | -3.751 |
Token | part |
Token ID | 636 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
hai | +6.642 |
raq | +6.570 |
Wast | +6.237 |
Synd | +5.507 |
iles | +5.449 |
Neg logit contributions | |
zona | -14.096 |
RESULTS | -12.984 |
bley | -12.347 |
haar | -12.030 |
iscons | -11.538 |
Token | , |
Token ID | 11 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
raq | +0.342 |
hai | +0.324 |
Wast | +0.290 |
Wars | +0.275 |
fronts | +0.271 |
Neg logit contributions | |
zona | -0.471 |
RESULTS | -0.429 |
haar | -0.402 |
bley | -0.394 |
atos | -0.384 |
Token |
|
Token ID | 198 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
raq | +1.167 |
hai | +1.104 |
Wast | +0.986 |
Wars | +0.927 |
fronts | +0.920 |
Neg logit contributions | |
zona | -1.740 |
RESULTS | -1.591 |
haar | -1.496 |
bley | -1.467 |
atos | -1.427 |
Token |
|
Token ID | 198 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
zona | +4.001 |
RESULTS | +3.760 |
haar | +3.387 |
atos | +3.266 |
bley | +3.239 |
Neg logit contributions | |
raq | -3.612 |
hai | -3.448 |
Wast | -3.078 |
sugg | -3.054 |
fronts | -3.054 |
Token | they |
Token ID | 9930 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
zona | +0.358 |
RESULTS | +0.325 |
haar | +0.302 |
bley | +0.296 |
atos | +0.288 |
Neg logit contributions | |
raq | -0.301 |
hai | -0.285 |
Wast | -0.259 |
fronts | -0.244 |
Wars | -0.244 |
Token | could |
Token ID | 714 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
zona | +0.812 |
RESULTS | +0.744 |
haar | +0.699 |
bley | +0.685 |
atos | +0.672 |
Neg logit contributions | |
raq | -0.562 |
hai | -0.528 |
Wast | -0.470 |
Wars | -0.445 |
Synd | -0.436 |
Token | be |
Token ID | 307 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
zona | +0.602 |
RESULTS | +0.545 |
haar | +0.510 |
bley | +0.499 |
atos | +0.485 |
Neg logit contributions | |
raq | -0.501 |
hai | -0.475 |
Wast | -0.429 |
Wars | -0.410 |
Synd | -0.403 |
Token | . |
Token ID | 13 |
Feature activation | -7.40e-03 |
Pos logit contributions | |
zona | +1.786 |
RESULTS | +1.626 |
haar | +1.528 |
bley | +1.486 |
atos | +1.451 |
Neg logit contributions | |
raq | -1.525 |
hai | -1.439 |
Wast | -1.303 |
Wars | -1.239 |
Synd | -1.218 |
Token |
|
Token ID | 198 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
raq | +0.071 |
hai | +0.067 |
Wast | +0.060 |
Wars | +0.057 |
Synd | +0.056 |
Neg logit contributions | |
zona | -0.107 |
RESULTS | -0.098 |
haar | -0.092 |
bley | -0.090 |
atos | -0.088 |
Token |
|
Token ID | 198 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
raq | +0.019 |
hai | +0.018 |
Wast | +0.016 |
Wars | +0.015 |
fronts | +0.015 |
Neg logit contributions | |
zona | -0.029 |
RESULTS | -0.026 |
haar | -0.025 |
bley | -0.024 |
atos | -0.024 |
Token | Mal |
Token ID | 15029 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
raq | +0.334 |
hai | +0.317 |
Wast | +0.284 |
Wars | +0.270 |
fronts | +0.266 |
Neg logit contributions | |
zona | -0.436 |
RESULTS | -0.396 |
haar | -0.371 |
bley | -0.364 |
atos | -0.354 |
Token | colm |
Token ID | 18414 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
hai | +5.773 |
raq | +5.450 |
tered | +4.501 |
Wast | +4.443 |
iles | +4.289 |
Neg logit contributions | |
zona | -15.273 |
RESULTS | -14.301 |
haar | -13.251 |
iscons | -12.789 |
aukee | -12.729 |
Token | Grim |
Token ID | 17525 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
raq | +1.875 |
hai | +1.797 |
Wast | +1.584 |
Synd | +1.442 |
Wars | +1.442 |
Neg logit contributions | |
zona | -3.736 |
RESULTS | -3.445 |
haar | -3.243 |
bley | -3.177 |
atos | -3.120 |
Token | ston |
Token ID | 3743 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
zona | +0.585 |
RESULTS | +0.526 |
haar | +0.491 |
bley | +0.480 |
atos | +0.466 |
Neg logit contributions | |
raq | -0.550 |
hai | -0.524 |
Wast | -0.476 |
Wars | -0.456 |
fronts | -0.450 |
Token | , |
Token ID | 11 |
Feature activation | +9.72e-02 |
Pos logit contributions | |
zona | +1.031 |
RESULTS | +0.930 |
haar | +0.873 |
bley | +0.852 |
atos | +0.833 |
Neg logit contributions | |
raq | -0.904 |
hai | -0.853 |
Wast | -0.771 |
Wars | -0.737 |
fronts | -0.725 |
Token | a |
Token ID | 257 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
zona | +1.314 |
RESULTS | +1.190 |
haar | +1.116 |
bley | +1.096 |
atos | +1.071 |
Neg logit contributions | |
raq | -1.031 |
hai | -0.966 |
Wast | -0.853 |
Wars | -0.821 |
fronts | -0.805 |
Token | so |
Token ID | 523 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
raq | +1.186 |
hai | +1.123 |
Wast | +1.010 |
Wars | +0.956 |
fronts | +0.951 |
Neg logit contributions | |
zona | -1.565 |
RESULTS | -1.431 |
haar | -1.337 |
bley | -1.306 |
atos | -1.273 |
Token | it |
Token ID | 340 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
raq | +0.788 |
hai | +0.746 |
Wast | +0.667 |
Wars | +0.634 |
Synd | +0.625 |
Neg logit contributions | |
zona | -1.055 |
RESULTS | -0.960 |
haar | -0.899 |
bley | -0.882 |
atos | -0.860 |
Token | did |
Token ID | 750 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
raq | +1.722 |
hai | +1.645 |
Wast | +1.448 |
fronts | +1.373 |
Wars | +1.355 |
Neg logit contributions | |
zona | -2.819 |
RESULTS | -2.603 |
haar | -2.451 |
bley | -2.392 |
iscons | -2.331 |
Token | tend |
Token ID | 4327 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
raq | +2.237 |
hai | +2.154 |
Wast | +1.931 |
fronts | +1.807 |
Wars | +1.803 |
Neg logit contributions | |
zona | -3.257 |
RESULTS | -2.991 |
haar | -2.811 |
bley | -2.741 |
atos | -2.692 |
Token | to |
Token ID | 284 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
raq | +2.074 |
hai | +1.941 |
Wast | +1.717 |
fronts | +1.630 |
Wars | +1.619 |
Neg logit contributions | |
zona | -3.211 |
RESULTS | -2.986 |
haar | -2.806 |
bley | -2.746 |
atos | -2.654 |
Token | m |
Token ID | 285 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
raq | +2.665 |
hai | +2.573 |
Wast | +2.329 |
fronts | +2.207 |
Wars | +2.155 |
Neg logit contributions | |
zona | -3.912 |
RESULTS | -3.645 |
haar | -3.394 |
bley | -3.312 |
atos | -3.232 |
Token | uffle |
Token ID | 18137 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
raq | +8.604 |
hai | +7.828 |
iles | +6.917 |
obar | +6.668 |
uer | +6.599 |
Neg logit contributions | |
zona | -12.267 |
RESULTS | -12.192 |
haar | -10.981 |
bley | -10.590 |
aukee | -10.252 |
Token | the |
Token ID | 262 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
zona | +1.345 |
RESULTS | +1.220 |
haar | +1.139 |
bley | +1.122 |
atos | +1.097 |
Neg logit contributions | |
raq | -1.075 |
hai | -1.018 |
Wast | -0.904 |
Wars | -0.873 |
Synd | -0.848 |
Token | down |
Token ID | 866 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
raq | +1.582 |
hai | +1.507 |
Wast | +1.359 |
fronts | +1.296 |
Wars | +1.279 |
Neg logit contributions | |
zona | -2.047 |
RESULTS | -1.865 |
haar | -1.748 |
bley | -1.705 |
atos | -1.655 |
Token | firing |
Token ID | 9645 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
raq | +0.836 |
hai | +0.797 |
Wast | +0.713 |
Wars | +0.678 |
fronts | +0.672 |
Neg logit contributions | |
zona | -1.071 |
RESULTS | -0.975 |
haar | -0.913 |
bley | -0.892 |
atos | -0.869 |
Token | design |
Token ID | 1486 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
raq | +4.100 |
hai | +3.964 |
Wast | +3.551 |
fronts | +3.528 |
iles | +3.391 |
Neg logit contributions | |
zona | -6.151 |
RESULTS | -5.710 |
haar | -5.425 |
bley | -5.160 |
iscons | -5.097 |
Token | positions |
Token ID | 6116 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
raq | +4.420 |
hai | +4.215 |
Wast | +3.824 |
fronts | +3.731 |
Synd | +3.573 |
Neg logit contributions | |
zona | -6.805 |
RESULTS | -6.217 |
haar | -5.805 |
bley | -5.685 |
atos | -5.477 |
Token | are |
Token ID | 389 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
zona | +0.940 |
RESULTS | +0.855 |
haar | +0.808 |
bley | +0.792 |
atos | +0.775 |
Neg logit contributions | |
raq | -0.638 |
hai | -0.600 |
Wast | -0.532 |
Wars | -0.507 |
Synd | -0.496 |
Token | currently |
Token ID | 3058 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
raq | +1.468 |
hai | +1.391 |
Wast | +1.247 |
Wars | +1.177 |
fronts | +1.176 |
Neg logit contributions | |
zona | -1.988 |
RESULTS | -1.817 |
haar | -1.706 |
bley | -1.669 |
atos | -1.621 |
Token | held |
Token ID | 2714 |
Feature activation | -9.62e-03 |
Pos logit contributions | |
raq | +0.720 |
hai | +0.681 |
Wast | +0.607 |
Wars | +0.576 |
Synd | +0.567 |
Neg logit contributions | |
zona | -1.004 |
RESULTS | -0.915 |
haar | -0.859 |
bley | -0.842 |
atos | -0.822 |
Token | by |
Token ID | 416 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
raq | +0.100 |
hai | +0.095 |
Wast | +0.085 |
Wars | +0.081 |
Synd | +0.080 |
Neg logit contributions | |
zona | -0.131 |
RESULTS | -0.119 |
haar | -0.112 |
bley | -0.110 |
atos | -0.107 |
Token | bilingual |
Token ID | 48116 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
raq | +4.327 |
hai | +4.043 |
Wast | +3.755 |
fronts | +3.616 |
Synd | +3.561 |
Neg logit contributions | |
zona | -6.148 |
RESULTS | -5.609 |
haar | -5.221 |
bley | -5.063 |
atos | -4.932 |
Token | public |
Token ID | 1171 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
raq | +7.105 |
hai | +6.991 |
fronts | +6.548 |
Wast | +6.468 |
iles | +6.383 |
Neg logit contributions | |
zona | -13.339 |
RESULTS | -12.090 |
haar | -11.205 |
bley | -11.011 |
atos | -10.541 |
Token | servants |
Token ID | 17523 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
zona | +1.063 |
RESULTS | +0.978 |
haar | +0.924 |
bley | +0.907 |
atos | +0.887 |
Neg logit contributions | |
raq | -0.634 |
hai | -0.594 |
Wast | -0.521 |
Wars | -0.492 |
Synd | -0.481 |
Token | . |
Token ID | 13 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
raq | +0.660 |
hai | +0.628 |
Wast | +0.563 |
Wars | +0.535 |
fronts | +0.532 |
Neg logit contributions | |
zona | -0.860 |
RESULTS | -0.782 |
haar | -0.730 |
bley | -0.715 |
atos | -0.697 |
Token |
|
Token ID | 198 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
raq | +0.718 |
hai | +0.677 |
Wast | +0.604 |
Wars | +0.567 |
Synd | +0.562 |
Neg logit contributions | |
zona | -1.098 |
RESULTS | -1.004 |
haar | -0.944 |
bley | -0.928 |
atos | -0.904 |
Token |
|
Token ID | 198 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
raq | +2.479 |
hai | +2.317 |
Wast | +2.022 |
Wars | +1.917 |
Synd | +1.878 |
Neg logit contributions | |
zona | -5.047 |
RESULTS | -4.565 |
haar | -4.402 |
bley | -4.376 |
iscons | -4.310 |
Token | ā |
Token ID | 10235 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
raq | +2.223 |
hai | +2.144 |
Wast | +1.908 |
iles | +1.822 |
Wars | +1.813 |
Neg logit contributions | |
zona | -2.337 |
RESULTS | -2.145 |
haar | -1.951 |
bley | -1.929 |
iscons | -1.842 |
Token | k |
Token ID | 74 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
raq | +1.263 |
hai | +1.210 |
Wast | +1.084 |
Wars | +1.028 |
Synd | +1.019 |
Neg logit contributions | |
zona | -1.472 |
RESULTS | -1.344 |
haar | -1.242 |
bley | -1.222 |
atos | -1.180 |
Token | ī |
Token ID | 18962 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
raq | +4.217 |
hai | +4.106 |
Wast | +3.590 |
iles | +3.504 |
Synd | +3.393 |
Neg logit contributions | |
zona | -4.741 |
RESULTS | -4.419 |
bley | -3.960 |
haar | -3.960 |
iscons | -3.793 |
Token | , |
Token ID | 11 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
raq | +1.193 |
hai | +1.142 |
Wast | +1.018 |
Wars | +0.964 |
Synd | +0.955 |
Neg logit contributions | |
zona | -1.506 |
RESULTS | -1.382 |
haar | -1.280 |
bley | -1.260 |
atos | -1.220 |
Token | ka |
Token ID | 38387 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
raq | +0.950 |
hai | +0.907 |
Wast | +0.808 |
Wars | +0.761 |
Synd | +0.754 |
Neg logit contributions | |
zona | -1.325 |
RESULTS | -1.214 |
haar | -1.134 |
bley | -1.115 |
atos | -1.085 |
Token | m |
Token ID | 285 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
raq | +1.251 |
hai | +1.195 |
Wast | +1.057 |
Wars | +0.985 |
Synd | +0.983 |
Neg logit contributions | |
zona | -1.905 |
RESULTS | -1.760 |
haar | -1.642 |
bley | -1.619 |
atos | -1.575 |
Token | aku |
Token ID | 8719 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
raq | +9.348 |
hai | +9.334 |
iles | +7.958 |
uer | +7.746 |
ista | +7.698 |
Neg logit contributions | |
RESULTS | -10.894 |
zona | -10.768 |
bley | -9.237 |
haar | -8.994 |
iscons | -8.721 |
Token | ah |
Token ID | 993 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
raq | +2.572 |
hai | +2.483 |
Wast | +2.172 |
iles | +2.042 |
fronts | +2.036 |
Neg logit contributions | |
zona | -3.402 |
RESULTS | -3.181 |
haar | -2.904 |
bley | -2.887 |
iscons | -2.798 |
Token | ine |
Token ID | 500 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
raq | +0.898 |
hai | +0.856 |
Wast | +0.765 |
Wars | +0.726 |
fronts | +0.721 |
Neg logit contributions | |
zona | -1.091 |
RESULTS | -0.996 |
haar | -0.924 |
bley | -0.907 |
atos | -0.879 |
Token | no |
Token ID | 645 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
zona | +1.203 |
RESULTS | +1.081 |
haar | +1.025 |
bley | +0.999 |
atos | +0.977 |
Neg logit contributions | |
raq | -0.923 |
hai | -0.867 |
Wast | -0.785 |
Wars | -0.753 |
Synd | -0.736 |
Token | Kau |
Token ID | 28148 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
zona | +2.492 |
RESULTS | +2.239 |
haar | +2.131 |
bley | +2.069 |
atos | +2.029 |
Neg logit contributions | |
raq | -1.910 |
hai | -1.772 |
Wast | -1.592 |
Wars | -1.543 |
obar | -1.502 |
Token | States |
Token ID | 1829 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
zona | +1.015 |
RESULTS | +0.905 |
haar | +0.835 |
bley | +0.814 |
atos | +0.788 |
Neg logit contributions | |
raq | -1.136 |
hai | -1.088 |
Wast | -0.996 |
Wars | -0.957 |
fronts | -0.946 |
Token | have |
Token ID | 423 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
raq | +0.626 |
hai | +0.585 |
Wast | +0.509 |
Wars | +0.478 |
fronts | +0.472 |
Neg logit contributions | |
zona | -1.154 |
RESULTS | -1.065 |
haar | -1.003 |
bley | -0.986 |
atos | -0.967 |
Token | imposed |
Token ID | 10893 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
zona | +2.255 |
RESULTS | +2.054 |
haar | +1.926 |
bley | +1.903 |
atos | +1.843 |
Neg logit contributions | |
raq | -1.624 |
hai | -1.523 |
Wast | -1.363 |
Wars | -1.299 |
Synd | -1.274 |
Token | travel |
Token ID | 3067 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
zona | +6.258 |
RESULTS | +5.535 |
haar | +5.294 |
bley | +5.226 |
atos | +5.058 |
Neg logit contributions | |
raq | -4.158 |
hai | -3.965 |
Wast | -3.463 |
obar | -3.218 |
Wars | -3.198 |
Token | bans |
Token ID | 20075 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
zona | +7.046 |
RESULTS | +5.774 |
haar | +5.576 |
bley | +5.468 |
iscons | +5.122 |
Neg logit contributions | |
raq | -7.297 |
hai | -6.892 |
Wast | -6.174 |
Synd | -6.115 |
obar | -5.976 |
Token | and |
Token ID | 290 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
zona | +5.645 |
RESULTS | +5.012 |
haar | +4.774 |
bley | +4.723 |
iscons | +4.490 |
Neg logit contributions | |
raq | -4.638 |
hai | -4.394 |
Wast | -3.924 |
Synd | -3.727 |
Wars | -3.699 |
Token | asset |
Token ID | 11171 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
zona | +10.819 |
RESULTS | +8.994 |
bley | +8.769 |
haar | +8.748 |
iscons | +8.447 |
Neg logit contributions | |
raq | -8.926 |
hai | -8.402 |
Wast | -7.403 |
obar | -7.392 |
fur | -7.340 |
Token | freezes |
Token ID | 44389 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
zona | +3.419 |
RESULTS | +2.825 |
haar | +2.496 |
bley | +2.332 |
iscons | +2.247 |
Neg logit contributions | |
raq | -7.000 |
hai | -6.713 |
Wast | -6.239 |
Wars | -6.133 |
Synd | -6.071 |
Token | on |
Token ID | 319 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
zona | +3.389 |
RESULTS | +3.072 |
haar | +2.915 |
bley | +2.869 |
atos | +2.768 |
Neg logit contributions | |
raq | -2.344 |
hai | -2.201 |
Wast | -1.955 |
Wars | -1.828 |
Synd | -1.814 |
Token | senior |
Token ID | 4664 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
zona | +4.900 |
RESULTS | +4.474 |
haar | +4.162 |
bley | +4.115 |
atos | +3.949 |
Neg logit contributions | |
raq | -4.849 |
hai | -4.659 |
Wast | -4.142 |
Wars | -3.956 |
obar | -3.950 |
Token | Russian |
Token ID | 3394 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
zona | +1.291 |
RESULTS | +1.178 |
haar | +1.104 |
bley | +1.080 |
atos | +1.057 |
Neg logit contributions | |
raq | -0.973 |
hai | -0.915 |
Wast | -0.818 |
Wars | -0.776 |
Synd | -0.763 |
Token | Congress |
Token ID | 3162 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
zona | +2.457 |
RESULTS | +2.242 |
haar | +2.096 |
bley | +2.057 |
atos | +2.015 |
Neg logit contributions | |
raq | -1.770 |
hai | -1.677 |
Wast | -1.463 |
Wars | -1.432 |
fronts | -1.401 |
Token | to |
Token ID | 284 |
Feature activation | +9.39e-02 |
Pos logit contributions | |
zona | +3.377 |
RESULTS | +3.027 |
haar | +2.840 |
bley | +2.768 |
iscons | +2.712 |
Neg logit contributions | |
raq | -2.723 |
hai | -2.637 |
Wast | -2.372 |
Wars | -2.256 |
obar | -2.231 |
Token | broaden |
Token ID | 44870 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
zona | +1.317 |
RESULTS | +1.199 |
haar | +1.125 |
bley | +1.109 |
atos | +1.081 |
Neg logit contributions | |
raq | -0.943 |
hai | -0.892 |
Wast | -0.783 |
Wars | -0.753 |
Synd | -0.735 |
Token | and |
Token ID | 290 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
zona | +3.577 |
RESULTS | +3.193 |
haar | +3.017 |
bley | +2.927 |
iscons | +2.865 |
Neg logit contributions | |
raq | -2.904 |
hai | -2.774 |
Wast | -2.426 |
Wars | -2.402 |
obar | -2.313 |
Token | leng |
Token ID | 40038 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
zona | +1.242 |
RESULTS | +1.128 |
haar | +1.058 |
bley | +1.038 |
atos | +1.011 |
Neg logit contributions | |
raq | -0.913 |
hai | -0.866 |
Wast | -0.763 |
Wars | -0.734 |
Synd | -0.718 |
Token | then |
Token ID | 8524 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
zona | +1.717 |
RESULTS | +1.534 |
haar | +1.462 |
bley | +1.428 |
atos | +1.404 |
Neg logit contributions | |
raq | -1.288 |
hai | -1.222 |
Wast | -1.102 |
fronts | -1.054 |
Wars | -1.047 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
zona | +7.733 |
RESULTS | +6.746 |
haar | +6.504 |
bley | +6.267 |
iscons | +6.155 |
Neg logit contributions | |
raq | -6.390 |
hai | -6.072 |
Wars | -5.256 |
Wast | -5.072 |
obar | -5.029 |
Token | tax |
Token ID | 1687 |
Feature activation | -3.76e-03 |
Pos logit contributions | |
zona | +1.596 |
RESULTS | +1.447 |
haar | +1.373 |
bley | +1.339 |
atos | +1.302 |
Neg logit contributions | |
raq | -1.139 |
hai | -1.068 |
Wast | -0.943 |
Wars | -0.908 |
obar | -0.886 |
Token | credits |
Token ID | 10824 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
raq | +0.043 |
hai | +0.040 |
Wast | +0.037 |
Wars | +0.035 |
Synd | +0.034 |
Neg logit contributions | |
zona | -0.048 |
RESULTS | -0.043 |
haar | -0.040 |
bley | -0.040 |
atos | -0.038 |
Token | for |
Token ID | 329 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
zona | +4.733 |
RESULTS | +4.259 |
haar | +3.978 |
bley | +3.826 |
atos | +3.722 |
Neg logit contributions | |
raq | -4.213 |
hai | -3.971 |
Wast | -3.509 |
Wars | -3.422 |
obar | -3.389 |
Token | renewable |
Token ID | 15713 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
zona | +3.152 |
RESULTS | +2.871 |
haar | +2.667 |
bley | +2.620 |
iscons | +2.550 |
Neg logit contributions | |
raq | -2.485 |
hai | -2.378 |
Wars | -2.043 |
Wast | -2.043 |
obar | -1.975 |
Token | Today |
Token ID | 6288 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
zona | +0.864 |
RESULTS | +0.720 |
haar | +0.641 |
bley | +0.629 |
iscons | +0.600 |
Neg logit contributions | |
raq | -1.592 |
hai | -1.533 |
Wast | -1.418 |
Wars | -1.382 |
fronts | -1.367 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
zona | +2.215 |
RESULTS | +2.000 |
haar | +1.873 |
bley | +1.851 |
iscons | +1.816 |
Neg logit contributions | |
raq | -1.538 |
hai | -1.455 |
Wast | -1.273 |
Wars | -1.231 |
fronts | -1.200 |
Token | 95 |
Token ID | 3865 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
raq | +4.694 |
hai | +4.372 |
Wast | +3.801 |
Wars | +3.690 |
tered | +3.638 |
Neg logit contributions | |
zona | -6.516 |
RESULTS | -5.825 |
haar | -5.696 |
bley | -5.522 |
aukee | -5.456 |
Token | ] |
Token ID | 60 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
zona | +1.724 |
RESULTS | +1.555 |
haar | +1.445 |
bley | +1.417 |
atos | +1.378 |
Neg logit contributions | |
raq | -1.554 |
hai | -1.482 |
Wast | -1.339 |
Wars | -1.283 |
fronts | -1.264 |
Token | CBS |
Token ID | 11133 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
zona | +5.912 |
RESULTS | +5.324 |
bley | +4.844 |
iscons | +4.819 |
haar | +4.765 |
Neg logit contributions | |
raq | -5.296 |
hai | -4.985 |
Wars | -4.319 |
Wast | -4.271 |
obar | -4.218 |
Token | Sports |
Token ID | 18153 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
zona | +2.376 |
RESULTS | +2.139 |
haar | +1.957 |
bley | +1.946 |
iscons | +1.895 |
Neg logit contributions | |
raq | -2.117 |
hai | -2.021 |
Wast | -1.801 |
Wars | -1.725 |
fronts | -1.716 |
Token | . |
Token ID | 13 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
zona | +7.179 |
RESULTS | +6.429 |
bley | +5.764 |
haar | +5.599 |
iscons | +5.549 |
Neg logit contributions | |
raq | -7.140 |
hai | -6.938 |
Wast | -6.075 |
obar | -5.863 |
fronts | -5.798 |
Token | com |
Token ID | 785 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
raq | +2.339 |
hai | +2.216 |
Wast | +1.984 |
Wars | +1.908 |
Synd | +1.883 |
Neg logit contributions | |
zona | -3.079 |
RESULTS | -2.794 |
haar | -2.650 |
bley | -2.588 |
iscons | -2.514 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
zona | +0.977 |
RESULTS | +0.895 |
haar | +0.839 |
bley | +0.829 |
atos | +0.805 |
Neg logit contributions | |
raq | -0.620 |
hai | -0.584 |
Wast | -0.511 |
Wars | -0.485 |
fronts | -0.476 |
Token | 96 |
Token ID | 4846 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
raq | +2.462 |
hai | +2.247 |
Wast | +1.760 |
Wars | +1.754 |
tered | +1.646 |
Neg logit contributions | |
zona | -6.281 |
RESULTS | -5.769 |
haar | -5.648 |
bley | -5.448 |
aukee | -5.379 |
Token | ] |
Token ID | 60 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
raq | +0.309 |
hai | +0.293 |
Wast | +0.265 |
Wars | +0.252 |
Synd | +0.250 |
Neg logit contributions | |
zona | -0.372 |
RESULTS | -0.338 |
haar | -0.316 |
bley | -0.308 |
atos | -0.300 |
Token | e |
Token ID | 68 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
zona | +3.368 |
RESULTS | +3.026 |
haar | +2.830 |
bley | +2.758 |
atos | +2.696 |
Neg logit contributions | |
raq | -2.831 |
hai | -2.669 |
Wast | -2.503 |
Synd | -2.383 |
fronts | -2.355 |
Token | el |
Token ID | 417 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
zona | +3.072 |
RESULTS | +2.768 |
haar | +2.594 |
bley | +2.542 |
atos | +2.479 |
Neg logit contributions | |
raq | -2.625 |
hai | -2.534 |
Wast | -2.291 |
Wars | -2.202 |
Synd | -2.183 |
Token | - |
Token ID | 12 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
zona | +1.750 |
RESULTS | +1.584 |
haar | +1.487 |
bley | +1.456 |
atos | +1.421 |
Neg logit contributions | |
raq | -1.433 |
hai | -1.353 |
Wast | -1.223 |
Wars | -1.167 |
fronts | -1.155 |
Token | ee |
Token ID | 1453 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
zona | +1.306 |
RESULTS | +1.178 |
haar | +1.101 |
bley | +1.077 |
atos | +1.048 |
Neg logit contributions | |
raq | -1.126 |
hai | -1.067 |
Wast | -0.983 |
Wars | -0.929 |
fronts | -0.927 |
Token | - |
Token ID | 12 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
zona | +1.031 |
RESULTS | +0.933 |
haar | +0.875 |
bley | +0.858 |
atos | +0.834 |
Neg logit contributions | |
raq | -0.841 |
hai | -0.797 |
Wast | -0.721 |
Wars | -0.687 |
Synd | -0.677 |
Token | OH |
Token ID | 12096 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
raq | +0.404 |
hai | +0.384 |
Wast | +0.347 |
Wars | +0.331 |
fronts | +0.327 |
Neg logit contributions | |
zona | -0.461 |
RESULTS | -0.417 |
haar | -0.388 |
bley | -0.380 |
atos | -0.370 |
Token | - |
Token ID | 12 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
zona | +8.301 |
RESULTS | +7.502 |
haar | +7.025 |
bley | +6.722 |
atos | +6.624 |
Neg logit contributions | |
raq | -8.652 |
hai | -8.060 |
Wast | -7.367 |
Wars | -7.321 |
Synd | -7.072 |
Token | t |
Token ID | 83 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
zona | +2.975 |
RESULTS | +2.670 |
haar | +2.515 |
bley | +2.459 |
atos | +2.383 |
Neg logit contributions | |
raq | -2.474 |
hai | -2.343 |
Wast | -2.168 |
Synd | -2.058 |
fronts | -2.053 |
Token | iss |
Token ID | 747 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
zona | +1.060 |
RESULTS | +0.959 |
haar | +0.902 |
bley | +0.881 |
atos | +0.862 |
Neg logit contributions | |
raq | -0.869 |
hai | -0.831 |
Wast | -0.755 |
Wars | -0.721 |
Synd | -0.709 |
Token | ), |
Token ID | 828 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
raq | +0.504 |
hai | +0.480 |
Wast | +0.428 |
Wars | +0.407 |
Synd | +0.402 |
Neg logit contributions | |
zona | -0.645 |
RESULTS | -0.588 |
haar | -0.548 |
bley | -0.538 |
atos | -0.523 |
Token | lead |
Token ID | 1085 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
zona | +3.231 |
RESULTS | +2.918 |
haar | +2.706 |
bley | +2.647 |
atos | +2.610 |
Neg logit contributions | |
raq | -2.765 |
hai | -2.589 |
Wast | -2.265 |
Wars | -2.244 |
fronts | -2.169 |
Token | worried |
Token ID | 7960 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
zona | +3.248 |
RESULTS | +2.934 |
haar | +2.729 |
bley | +2.691 |
atos | +2.623 |
Neg logit contributions | |
raq | -2.746 |
hai | -2.565 |
Wast | -2.297 |
Wars | -2.233 |
obar | -2.167 |
Token | about |
Token ID | 546 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
zona | +3.680 |
RESULTS | +3.307 |
haar | +3.054 |
bley | +3.034 |
atos | +2.994 |
Neg logit contributions | |
raq | -3.701 |
hai | -3.505 |
Wast | -3.131 |
obar | -3.023 |
Wars | -3.002 |
Token | being |
Token ID | 852 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
zona | +2.024 |
RESULTS | +1.852 |
haar | +1.721 |
bley | +1.693 |
atos | +1.653 |
Neg logit contributions | |
raq | -1.611 |
hai | -1.512 |
Wast | -1.327 |
Wars | -1.281 |
obar | -1.251 |
Token | in |
Token ID | 287 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
raq | +0.528 |
hai | +0.502 |
Wast | +0.451 |
Wars | +0.428 |
fronts | +0.424 |
Neg logit contributions | |
zona | -0.681 |
RESULTS | -0.620 |
haar | -0.580 |
bley | -0.569 |
atos | -0.553 |
Token | the |
Token ID | 262 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
zona | +4.788 |
RESULTS | +4.335 |
haar | +4.078 |
bley | +4.022 |
atos | +3.950 |
Neg logit contributions | |
raq | -3.976 |
hai | -3.774 |
Wast | -3.317 |
Wars | -3.136 |
arthed | -3.098 |
Token | public |
Token ID | 1171 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
zona | +6.634 |
RESULTS | +5.984 |
haar | +5.713 |
bley | +5.615 |
atos | +5.541 |
Neg logit contributions | |
raq | -5.559 |
hai | -5.186 |
Wast | -4.524 |
Wars | -4.402 |
arthed | -4.377 |
Token | eye |
Token ID | 4151 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
zona | +5.801 |
RESULTS | +5.100 |
haar | +4.996 |
bley | +4.725 |
iscons | +4.365 |
Neg logit contributions | |
raq | -10.959 |
hai | -9.927 |
Wars | -9.381 |
tein | -9.317 |
Wast | -9.302 |
Token | again |
Token ID | 757 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
zona | +4.590 |
RESULTS | +4.155 |
haar | +3.960 |
bley | +3.866 |
atos | +3.673 |
Neg logit contributions | |
raq | -4.734 |
hai | -4.402 |
Wast | -3.976 |
tein | -3.818 |
Wars | -3.817 |
Token | ? |
Token ID | 30 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
zona | +3.603 |
RESULTS | +3.243 |
haar | +3.059 |
bley | +2.974 |
atos | +2.884 |
Neg logit contributions | |
raq | -3.657 |
hai | -3.411 |
Wast | -3.104 |
Wars | -2.943 |
obar | -2.939 |
Token | She |
Token ID | 1375 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
zona | +0.586 |
RESULTS | +0.533 |
haar | +0.497 |
bley | +0.486 |
atos | +0.475 |
Neg logit contributions | |
raq | -0.466 |
hai | -0.441 |
Wast | -0.392 |
Wars | -0.375 |
fronts | -0.372 |
Token | thinks |
Token ID | 6834 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
zona | +2.545 |
RESULTS | +2.306 |
haar | +2.179 |
bley | +2.142 |
atos | +2.099 |
Neg logit contributions | |
raq | -1.811 |
hai | -1.688 |
Wast | -1.504 |
Wars | -1.441 |
Synd | -1.416 |
Token | map |
Token ID | 3975 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
raq | +2.797 |
hai | +2.644 |
Wast | +2.384 |
Wars | +2.271 |
Synd | +2.230 |
Neg logit contributions | |
zona | -3.873 |
RESULTS | -3.557 |
haar | -3.342 |
bley | -3.273 |
atos | -3.238 |
Token | is |
Token ID | 318 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
raq | +1.364 |
hai | +1.292 |
Wast | +1.145 |
Wars | +1.083 |
fronts | +1.076 |
Neg logit contributions | |
zona | -2.114 |
RESULTS | -1.933 |
haar | -1.817 |
bley | -1.786 |
atos | -1.741 |
Token | inaccurate |
Token ID | 21873 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
zona | +1.501 |
RESULTS | +1.358 |
haar | +1.281 |
bley | +1.250 |
atos | +1.219 |
Neg logit contributions | |
raq | -1.154 |
hai | -1.093 |
Wast | -0.969 |
Wars | -0.932 |
Synd | -0.910 |
Token | ?) |
Token ID | 10091 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
raq | +1.493 |
hai | +1.419 |
Wast | +1.276 |
Wars | +1.207 |
fronts | +1.194 |
Neg logit contributions | |
zona | -2.042 |
RESULTS | -1.862 |
haar | -1.736 |
bley | -1.706 |
atos | -1.662 |
Token | but |
Token ID | 475 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
zona | +0.388 |
RESULTS | +0.352 |
haar | +0.329 |
bley | +0.323 |
atos | +0.314 |
Neg logit contributions | |
raq | -0.311 |
hai | -0.293 |
Wast | -0.263 |
Wars | -0.251 |
fronts | -0.248 |
Token | the |
Token ID | 262 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
raq | +1.783 |
hai | +1.692 |
Wast | +1.520 |
Wars | +1.428 |
fronts | +1.423 |
Neg logit contributions | |
zona | -2.543 |
RESULTS | -2.320 |
haar | -2.182 |
bley | -2.136 |
atos | -2.085 |
Token | same |
Token ID | 976 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
zona | +0.632 |
RESULTS | +0.578 |
haar | +0.541 |
bley | +0.530 |
atos | +0.517 |
Neg logit contributions | |
raq | -0.471 |
hai | -0.447 |
Wast | -0.397 |
Wars | -0.379 |
Synd | -0.371 |
Token | thing |
Token ID | 1517 |
Feature activation | -1.53e-03 |
Pos logit contributions | |
raq | +1.679 |
hai | +1.592 |
Wast | +1.424 |
Wars | +1.337 |
fronts | +1.330 |
Neg logit contributions | |
zona | -2.519 |
RESULTS | -2.295 |
haar | -2.160 |
bley | -2.117 |
atos | -2.065 |
Token | can |
Token ID | 460 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
raq | +0.015 |
hai | +0.014 |
Wast | +0.012 |
Wars | +0.012 |
Synd | +0.012 |
Neg logit contributions | |
zona | -0.022 |
RESULTS | -0.020 |
haar | -0.019 |
bley | -0.018 |
atos | -0.018 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.10e-03 |
Pos logit contributions | |
zona | +3.655 |
RESULTS | +3.240 |
haar | +3.081 |
bley | +3.002 |
atos | +2.928 |
Neg logit contributions | |
raq | -3.047 |
hai | -2.850 |
Wast | -2.566 |
Wars | -2.493 |
Synd | -2.431 |
Token | with |
Token ID | 351 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
raq | +0.032 |
hai | +0.030 |
Wast | +0.027 |
Wars | +0.025 |
fronts | +0.025 |
Neg logit contributions | |
zona | -0.043 |
RESULTS | -0.039 |
haar | -0.037 |
bley | -0.036 |
atos | -0.035 |
Token | pian |
Token ID | 43923 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
zona | +1.184 |
RESULTS | +1.078 |
haar | +1.010 |
bley | +0.994 |
atos | +0.973 |
Neg logit contributions | |
raq | -0.887 |
hai | -0.836 |
Wast | -0.749 |
Wars | -0.715 |
Synd | -0.698 |
Token | ist |
Token ID | 396 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
zona | +2.584 |
RESULTS | +2.312 |
haar | +2.166 |
bley | +2.130 |
atos | +2.115 |
Neg logit contributions | |
raq | -2.566 |
hai | -2.396 |
Wast | -2.223 |
Wars | -2.146 |
fronts | -2.118 |
Token | 's |
Token ID | 338 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
zona | +4.377 |
RESULTS | +3.939 |
haar | +3.718 |
bley | +3.688 |
atos | +3.628 |
Neg logit contributions | |
raq | -3.601 |
hai | -3.364 |
Wast | -3.025 |
Wars | -2.961 |
Synd | -2.863 |
Token | substit |
Token ID | 21436 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
zona | +4.500 |
RESULTS | +4.133 |
haar | +3.868 |
bley | +3.801 |
atos | +3.779 |
Neg logit contributions | |
raq | -3.624 |
hai | -3.367 |
Wast | -3.032 |
Wars | -2.951 |
obar | -2.840 |
Token | utions |
Token ID | 3508 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
raq | +1.895 |
hai | +1.809 |
Wast | +1.607 |
Wars | +1.505 |
iles | +1.495 |
Neg logit contributions | |
zona | -3.066 |
RESULTS | -2.814 |
haar | -2.639 |
bley | -2.588 |
iscons | -2.506 |
Token | at |
Token ID | 379 |
Feature activation | +8.75e-03 |
Pos logit contributions | |
zona | +4.791 |
RESULTS | +4.312 |
haar | +4.075 |
bley | +4.021 |
atos | +3.889 |
Neg logit contributions | |
raq | -4.600 |
hai | -4.239 |
Wast | -3.876 |
Wars | -3.770 |
Synd | -3.677 |
Token | all |
Token ID | 477 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
zona | +0.120 |
RESULTS | +0.109 |
haar | +0.102 |
bley | +0.100 |
atos | +0.098 |
Neg logit contributions | |
raq | -0.091 |
hai | -0.086 |
Wast | -0.077 |
Wars | -0.073 |
fronts | -0.072 |
Token | during |
Token ID | 1141 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
zona | +4.417 |
RESULTS | +3.966 |
haar | +3.687 |
bley | +3.639 |
atos | +3.581 |
Neg logit contributions | |
raq | -4.269 |
hai | -3.993 |
Wast | -3.628 |
Wars | -3.472 |
Synd | -3.400 |
Token | these |
Token ID | 777 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
zona | +4.311 |
RESULTS | +3.891 |
haar | +3.593 |
bley | +3.576 |
atos | +3.554 |
Neg logit contributions | |
raq | -3.747 |
hai | -3.561 |
Wast | -3.174 |
Wars | -3.057 |
iles | -2.967 |
Token | two |
Token ID | 734 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
zona | +4.448 |
RESULTS | +4.060 |
bley | +3.714 |
haar | +3.673 |
atos | +3.671 |
Neg logit contributions | |
raq | -3.857 |
hai | -3.684 |
Wast | -3.266 |
Wars | -3.147 |
obar | -3.083 |
Token | ch |
Token ID | 442 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
zona | +0.513 |
RESULTS | +0.466 |
haar | +0.434 |
bley | +0.426 |
atos | +0.415 |
Neg logit contributions | |
raq | -0.424 |
hai | -0.403 |
Wast | -0.362 |
Wars | -0.346 |
Synd | -0.340 |
Token | Burning |
Token ID | 21460 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
raq | +2.081 |
hai | +1.981 |
Wast | +1.797 |
Wars | +1.694 |
Synd | +1.686 |
Neg logit contributions | |
zona | -2.740 |
RESULTS | -2.498 |
haar | -2.323 |
bley | -2.296 |
atos | -2.216 |
Token | Platform |
Token ID | 19193 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
raq | +4.173 |
hai | +3.987 |
Wast | +3.728 |
Wars | +3.486 |
Synd | +3.478 |
Neg logit contributions | |
zona | -5.167 |
RESULTS | -4.765 |
haar | -4.420 |
bley | -4.351 |
iscons | -4.179 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
raq | +2.396 |
hai | +2.294 |
Wast | +2.071 |
Wars | +1.968 |
Synd | +1.926 |
Neg logit contributions | |
zona | -3.454 |
RESULTS | -3.163 |
haar | -2.942 |
bley | -2.902 |
atos | -2.814 |
Token | OT |
Token ID | 2394 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
raq | +2.031 |
hai | +1.930 |
Wast | +1.701 |
Wars | +1.678 |
iles | +1.616 |
Neg logit contributions | |
zona | -2.534 |
RESULTS | -2.264 |
haar | -2.150 |
bley | -2.111 |
iscons | -2.042 |
Token | TA |
Token ID | 5603 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
zona | +1.757 |
RESULTS | +1.494 |
haar | +1.327 |
bley | +1.270 |
atos | +1.226 |
Neg logit contributions | |
raq | -3.245 |
hai | -3.116 |
Wast | -2.866 |
Wars | -2.811 |
fronts | -2.788 |
Token | WA |
Token ID | 15543 |
Feature activation | +2.11e-03 |
Pos logit contributions | |
zona | +2.041 |
RESULTS | +1.878 |
haar | +1.734 |
bley | +1.703 |
iscons | +1.646 |
Neg logit contributions | |
raq | -1.392 |
hai | -1.325 |
Wast | -1.167 |
obar | -1.089 |
fronts | -1.086 |
Token | ( |
Token ID | 357 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
zona | +0.028 |
RESULTS | +0.026 |
haar | +0.024 |
bley | +0.024 |
atos | +0.023 |
Neg logit contributions | |
raq | -0.022 |
hai | -0.021 |
Wast | -0.019 |
Wars | -0.018 |
fronts | -0.018 |
Token | Reuters |
Token ID | 12637 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
raq | +3.524 |
hai | +3.332 |
Wast | +3.018 |
Wars | +2.922 |
Synd | +2.837 |
Neg logit contributions | |
zona | -4.972 |
RESULTS | -4.396 |
haar | -4.212 |
bley | -4.161 |
atos | -4.028 |
Token | ) |
Token ID | 8 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
zona | +1.396 |
RESULTS | +1.266 |
haar | +1.168 |
bley | +1.141 |
atos | +1.114 |
Neg logit contributions | |
raq | -1.220 |
hai | -1.160 |
Wast | -1.044 |
Wars | -0.994 |
fronts | -0.992 |
Token | - |
Token ID | 532 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
zona | +1.852 |
RESULTS | +1.708 |
haar | +1.571 |
bley | +1.545 |
atos | +1.512 |
Neg logit contributions | |
raq | -1.479 |
hai | -1.410 |
Wast | -1.250 |
fronts | -1.205 |
Wars | -1.184 |
Token | Canada |
Token ID | 3340 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
zona | +0.927 |
RESULTS | +0.840 |
haar | +0.780 |
bley | +0.764 |
atos | +0.744 |
Neg logit contributions | |
raq | -0.826 |
hai | -0.785 |
Wast | -0.698 |
Wars | -0.674 |
fronts | -0.671 |
Token | and |
Token ID | 290 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
zona | +0.578 |
RESULTS | +0.524 |
haar | +0.491 |
bley | +0.481 |
atos | +0.469 |
Neg logit contributions | |
raq | -0.455 |
hai | -0.432 |
Wast | -0.385 |
Wars | -0.369 |
Synd | -0.362 |
Token | she |
Token ID | 673 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
zona | +0.524 |
RESULTS | +0.478 |
haar | +0.447 |
bley | +0.439 |
atos | +0.428 |
Neg logit contributions | |
raq | -0.383 |
hai | -0.363 |
Wast | -0.322 |
Wars | -0.309 |
fronts | -0.302 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
raq | +0.592 |
hai | +0.560 |
Wast | +0.495 |
Wars | +0.468 |
fronts | +0.462 |
Neg logit contributions | |
zona | -0.903 |
RESULTS | -0.826 |
haar | -0.777 |
bley | -0.763 |
atos | -0.744 |
Token | intimidated |
Token ID | 36601 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
zona | +1.851 |
RESULTS | +1.677 |
haar | +1.552 |
bley | +1.540 |
atos | +1.500 |
Neg logit contributions | |
raq | -1.514 |
hai | -1.443 |
Wast | -1.285 |
Wars | -1.241 |
Synd | -1.209 |
Token | into |
Token ID | 656 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
zona | +2.843 |
RESULTS | +2.584 |
haar | +2.382 |
bley | +2.380 |
atos | +2.324 |
Neg logit contributions | |
raq | -2.483 |
hai | -2.344 |
Wast | -2.112 |
Wars | -2.015 |
obar | -1.985 |
Token | filing |
Token ID | 12180 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
raq | +2.591 |
hai | +2.443 |
Wast | +2.183 |
fronts | +2.048 |
iles | +2.044 |
Neg logit contributions | |
zona | -5.076 |
RESULTS | -4.644 |
haar | -4.414 |
bley | -4.348 |
iscons | -4.228 |
Token | it |
Token ID | 340 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
zona | +1.833 |
RESULTS | +1.660 |
haar | +1.558 |
bley | +1.526 |
atos | +1.488 |
Neg logit contributions | |
raq | -1.474 |
hai | -1.406 |
Wast | -1.248 |
Wars | -1.197 |
Synd | -1.178 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
zona | +1.873 |
RESULTS | +1.700 |
haar | +1.586 |
bley | +1.560 |
atos | +1.515 |
Neg logit contributions | |
raq | -1.568 |
hai | -1.489 |
Wast | -1.331 |
Wars | -1.274 |
Synd | -1.249 |
Token | � |
Token ID | 447 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
raq | +1.445 |
hai | +1.366 |
Wast | +1.224 |
Synd | +1.146 |
Wars | +1.143 |
Neg logit contributions | |
zona | -2.298 |
RESULTS | -2.104 |
haar | -1.998 |
bley | -1.956 |
atos | -1.905 |
Token | � |
Token ID | 251 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
raq | +0.298 |
hai | +0.276 |
Wast | +0.235 |
Wars | +0.216 |
Synd | +0.212 |
Neg logit contributions | |
zona | -0.681 |
RESULTS | -0.631 |
haar | -0.598 |
bley | -0.589 |
atos | -0.577 |
Token |
|
Token ID | 198 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
raq | +2.112 |
hai | +1.988 |
Wast | +1.766 |
Synd | +1.672 |
Wars | +1.642 |
Neg logit contributions | |
zona | -3.665 |
RESULTS | -3.351 |
haar | -3.189 |
bley | -3.125 |
atos | -3.066 |
Token | will |
Token ID | 481 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
zona | +4.174 |
RESULTS | +3.720 |
haar | +3.561 |
bley | +3.448 |
atos | +3.380 |
Neg logit contributions | |
raq | -3.353 |
hai | -3.155 |
Wast | -2.845 |
Wars | -2.707 |
Synd | -2.659 |
Token | be |
Token ID | 307 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
zona | +4.049 |
RESULTS | +3.562 |
haar | +3.375 |
bley | +3.278 |
iscons | +3.179 |
Neg logit contributions | |
raq | -4.167 |
hai | -3.961 |
Wast | -3.639 |
Wars | -3.456 |
iles | -3.418 |
Token | a |
Token ID | 257 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
zona | +4.019 |
RESULTS | +3.603 |
haar | +3.371 |
bley | +3.328 |
atos | +3.224 |
Neg logit contributions | |
raq | -3.764 |
hai | -3.618 |
Wast | -3.194 |
Wars | -3.064 |
obar | -3.040 |
Token | full |
Token ID | 1336 |
Feature activation | +8.92e-02 |
Pos logit contributions | |
zona | +2.311 |
RESULTS | +2.094 |
haar | +1.977 |
bley | +1.962 |
atos | +1.895 |
Neg logit contributions | |
raq | -1.642 |
hai | -1.562 |
Wast | -1.376 |
Wars | -1.306 |
obar | -1.291 |
Token | rescue |
Token ID | 9992 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
zona | +1.277 |
RESULTS | +1.166 |
haar | +1.097 |
bley | +1.084 |
atos | +1.052 |
Neg logit contributions | |
raq | -0.859 |
hai | -0.815 |
Wast | -0.722 |
Wars | -0.683 |
obar | -0.668 |
Token | for |
Token ID | 329 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
zona | +4.644 |
RESULTS | +4.080 |
haar | +3.871 |
bley | +3.843 |
atos | +3.696 |
Neg logit contributions | |
raq | -4.304 |
hai | -4.085 |
Wast | -3.753 |
obar | -3.541 |
iles | -3.461 |
Token | Spain |
Token ID | 8602 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
zona | +2.947 |
RESULTS | +2.658 |
haar | +2.479 |
bley | +2.449 |
iscons | +2.395 |
Neg logit contributions | |
raq | -2.464 |
hai | -2.369 |
Wast | -2.096 |
Wars | -2.008 |
obar | -1.967 |
Token | , |
Token ID | 11 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
raq | +1.745 |
hai | +1.663 |
Wast | +1.480 |
Wars | +1.411 |
fronts | +1.399 |
Neg logit contributions | |
zona | -2.435 |
RESULTS | -2.226 |
haar | -2.076 |
bley | -2.032 |
atos | -1.991 |
Token | to |
Token ID | 284 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
raq | +0.399 |
hai | +0.378 |
Wast | +0.337 |
Wars | +0.320 |
fronts | +0.315 |
Neg logit contributions | |
zona | -0.543 |
RESULTS | -0.495 |
haar | -0.464 |
bley | -0.455 |
atos | -0.443 |
Token | � |
Token ID | 564 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
zona | +0.625 |
RESULTS | +0.568 |
haar | +0.535 |
bley | +0.524 |
atos | +0.512 |
Neg logit contributions | |
raq | -0.438 |
hai | -0.413 |
Wast | -0.366 |
Wars | -0.349 |
Synd | -0.341 |
Token | � |
Token ID | 250 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
zona | +2.644 |
RESULTS | +2.440 |
haar | +2.317 |
bley | +2.279 |
atos | +2.237 |
Neg logit contributions | |
raq | -1.286 |
hai | -1.222 |
Wast | -1.041 |
Wars | -0.983 |
Synd | -0.976 |
Token | him |
Token ID | 683 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
raq | +0.300 |
hai | +0.285 |
Wast | +0.256 |
Wars | +0.244 |
fronts | +0.240 |
Neg logit contributions | |
zona | -0.374 |
RESULTS | -0.340 |
haar | -0.318 |
bley | -0.311 |
atos | -0.303 |
Token | to |
Token ID | 284 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
zona | +1.849 |
RESULTS | +1.679 |
haar | +1.598 |
bley | +1.558 |
atos | +1.512 |
Neg logit contributions | |
raq | -1.477 |
hai | -1.393 |
Wast | -1.246 |
Wars | -1.199 |
fronts | -1.168 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
raq | +2.129 |
hai | +2.023 |
Wast | +1.827 |
Wars | +1.709 |
Synd | +1.700 |
Neg logit contributions | |
zona | -3.098 |
RESULTS | -2.834 |
haar | -2.624 |
bley | -2.590 |
atos | -2.516 |
Token | great |
Token ID | 1049 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
raq | +1.400 |
hai | +1.346 |
Wast | +1.215 |
Wars | +1.125 |
fronts | +1.125 |
Neg logit contributions | |
zona | -1.940 |
RESULTS | -1.781 |
haar | -1.635 |
bley | -1.618 |
atos | -1.581 |
Token | spider |
Token ID | 19230 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
zona | +0.210 |
RESULTS | +0.191 |
haar | +0.180 |
bley | +0.177 |
atos | +0.173 |
Neg logit contributions | |
raq | -0.143 |
hai | -0.134 |
Wast | -0.119 |
Wars | -0.113 |
fronts | -0.111 |
Token | Shel |
Token ID | 15325 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
zona | +4.599 |
RESULTS | +4.011 |
haar | +3.907 |
bley | +3.808 |
atos | +3.805 |
Neg logit contributions | |
raq | -3.796 |
hai | -3.535 |
Wast | -3.159 |
Wars | -3.073 |
Synd | -3.039 |
Token | ob |
Token ID | 672 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
raq | +0.807 |
hai | +0.765 |
Wast | +0.689 |
Wars | +0.657 |
Synd | +0.647 |
Neg logit contributions | |
zona | -1.008 |
RESULTS | -0.912 |
haar | -0.856 |
bley | -0.839 |
atos | -0.817 |
Token | in |
Token ID | 287 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
raq | +0.744 |
hai | +0.710 |
Wast | +0.638 |
Wars | +0.602 |
Synd | +0.596 |
Neg logit contributions | |
zona | -0.948 |
RESULTS | -0.867 |
haar | -0.803 |
bley | -0.788 |
iscons | -0.765 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
zona | +0.710 |
RESULTS | +0.642 |
haar | +0.609 |
bley | +0.593 |
atos | +0.581 |
Neg logit contributions | |
raq | -0.531 |
hai | -0.504 |
Wast | -0.446 |
Wars | -0.427 |
fronts | -0.420 |
Token | tunnels |
Token ID | 22642 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
zona | +1.505 |
RESULTS | +1.358 |
haar | +1.284 |
bley | +1.254 |
atos | +1.225 |
Neg logit contributions | |
raq | -1.130 |
hai | -1.064 |
Wast | -0.944 |
Wars | -0.907 |
obar | -0.892 |
Token | of |
Token ID | 286 |
Feature activation | +9.75e-02 |
Pos logit contributions | |
raq | +0.808 |
hai | +0.769 |
Wast | +0.691 |
Wars | +0.656 |
fronts | +0.650 |
Neg logit contributions | |
zona | -1.025 |
RESULTS | -0.930 |
haar | -0.867 |
bley | -0.850 |
atos | -0.826 |
Token | or |
Token ID | 393 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
raq | +1.655 |
hai | +1.561 |
Wast | +1.409 |
Wars | +1.336 |
fronts | +1.324 |
Neg logit contributions | |
zona | -2.308 |
RESULTS | -2.106 |
haar | -1.979 |
bley | -1.939 |
atos | -1.882 |
Token | respect |
Token ID | 2461 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
zona | +0.303 |
RESULTS | +0.275 |
haar | +0.258 |
bley | +0.255 |
atos | +0.249 |
Neg logit contributions | |
raq | -0.223 |
hai | -0.209 |
Wast | -0.188 |
Wars | -0.178 |
Synd | -0.174 |
Token | our |
Token ID | 674 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
raq | +0.155 |
hai | +0.147 |
Wast | +0.131 |
Wars | +0.124 |
fronts | +0.122 |
Neg logit contributions | |
zona | -0.208 |
RESULTS | -0.190 |
haar | -0.178 |
bley | -0.174 |
atos | -0.170 |
Token | right |
Token ID | 826 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
zona | +4.015 |
RESULTS | +3.615 |
haar | +3.434 |
bley | +3.421 |
iscons | +3.264 |
Neg logit contributions | |
raq | -3.383 |
hai | -3.152 |
Wast | -2.795 |
obar | -2.712 |
Wars | -2.679 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
zona | +3.455 |
RESULTS | +3.113 |
haar | +2.963 |
bley | +2.872 |
atos | +2.788 |
Neg logit contributions | |
raq | -2.852 |
hai | -2.696 |
Wast | -2.448 |
Wars | -2.304 |
Synd | -2.279 |
Token | My |
Token ID | 2011 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
raq | +2.015 |
hai | +1.924 |
Wast | +1.768 |
Wars | +1.677 |
Synd | +1.664 |
Neg logit contributions | |
zona | -2.868 |
RESULTS | -2.613 |
haar | -2.474 |
bley | -2.437 |
atos | -2.349 |
Token | condolences |
Token ID | 38671 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
raq | +1.405 |
hai | +1.334 |
Wast | +1.192 |
Wars | +1.132 |
fronts | +1.114 |
Neg logit contributions | |
zona | -1.968 |
RESULTS | -1.798 |
haar | -1.681 |
bley | -1.648 |
atos | -1.611 |
Token | and |
Token ID | 290 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
raq | +2.085 |
hai | +1.962 |
Wast | +1.706 |
Wars | +1.595 |
fronts | +1.584 |
Neg logit contributions | |
zona | -3.744 |
RESULTS | -3.451 |
haar | -3.234 |
bley | -3.174 |
atos | -3.116 |
Token | prayers |
Token ID | 15707 |
Feature activation | +9.39e-02 |
Pos logit contributions | |
raq | +0.221 |
hai | +0.208 |
Wast | +0.185 |
Wars | +0.177 |
obar | +0.173 |
Neg logit contributions | |
zona | -0.299 |
RESULTS | -0.272 |
haar | -0.256 |
bley | -0.251 |
atos | -0.245 |
Token | go |
Token ID | 467 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
zona | +1.399 |
RESULTS | +1.282 |
haar | +1.215 |
bley | +1.193 |
atos | +1.163 |
Neg logit contributions | |
raq | -0.854 |
hai | -0.803 |
Wast | -0.704 |
Wars | -0.667 |
fronts | -0.652 |
Token | out |
Token ID | 503 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
raq | +1.784 |
hai | +1.703 |
Wast | +1.533 |
Wars | +1.448 |
Synd | +1.428 |
Neg logit contributions | |
zona | -2.434 |
RESULTS | -2.214 |
haar | -2.068 |
bley | -2.031 |
atos | -1.986 |
Token | pursuing |
Token ID | 15461 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
zona | +1.232 |
RESULTS | +1.125 |
haar | +1.052 |
bley | +1.034 |
atos | +1.010 |
Neg logit contributions | |
raq | -0.902 |
hai | -0.852 |
Wast | -0.762 |
Wars | -0.730 |
Synd | -0.712 |
Token | appropriate |
Token ID | 5035 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
raq | +1.407 |
hai | +1.330 |
Wast | +1.193 |
fronts | +1.126 |
Wars | +1.120 |
Neg logit contributions | |
zona | -1.969 |
RESULTS | -1.789 |
haar | -1.679 |
bley | -1.646 |
atos | -1.604 |
Token | administrative |
Token ID | 11553 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
raq | +1.118 |
hai | +1.066 |
Wast | +0.959 |
fronts | +0.911 |
Wars | +0.909 |
Neg logit contributions | |
zona | -1.396 |
RESULTS | -1.264 |
haar | -1.182 |
bley | -1.156 |
atos | -1.127 |
Token | enforcement |
Token ID | 5394 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
raq | +1.851 |
hai | +1.753 |
Wast | +1.587 |
fronts | +1.525 |
Synd | +1.496 |
Neg logit contributions | |
zona | -2.361 |
RESULTS | -2.148 |
haar | -2.020 |
bley | -1.974 |
atos | -1.916 |
Token | action |
Token ID | 2223 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
zona | +2.015 |
RESULTS | +1.810 |
haar | +1.683 |
bley | +1.641 |
atos | +1.595 |
Neg logit contributions | |
raq | -1.977 |
hai | -1.889 |
Wast | -1.718 |
Wars | -1.640 |
obar | -1.613 |
Token | as |
Token ID | 355 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
zona | +0.048 |
RESULTS | +0.043 |
haar | +0.040 |
bley | +0.040 |
atos | +0.038 |
Neg logit contributions | |
raq | -0.039 |
hai | -0.037 |
Wast | -0.034 |
Wars | -0.032 |
Synd | -0.032 |
Token | allowed |
Token ID | 3142 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
raq | +1.486 |
hai | +1.404 |
Wast | +1.254 |
fronts | +1.190 |
Wars | +1.188 |
Neg logit contributions | |
zona | -2.047 |
RESULTS | -1.859 |
haar | -1.737 |
bley | -1.716 |
atos | -1.670 |
Token | to |
Token ID | 284 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
raq | +1.583 |
hai | +1.490 |
Wast | +1.324 |
Wars | +1.253 |
Synd | +1.250 |
Neg logit contributions | |
zona | -2.308 |
RESULTS | -2.116 |
haar | -1.979 |
bley | -1.940 |
atos | -1.888 |
Token | us |
Token ID | 514 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
raq | +0.440 |
hai | +0.417 |
Wast | +0.372 |
Wars | +0.353 |
Synd | +0.348 |
Neg logit contributions | |
zona | -0.606 |
RESULTS | -0.553 |
haar | -0.518 |
bley | -0.508 |
atos | -0.496 |
Token | by |
Token ID | 416 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
raq | +1.232 |
hai | +1.168 |
Wast | +1.047 |
Wars | +0.997 |
fronts | +0.990 |
Neg logit contributions | |
zona | -1.558 |
RESULTS | -1.417 |
haar | -1.319 |
bley | -1.289 |
atos | -1.259 |
Token | the |
Token ID | 262 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
raq | +0.651 |
hai | +0.614 |
Wast | +0.545 |
Wars | +0.515 |
Synd | +0.510 |
Neg logit contributions | |
zona | -0.973 |
RESULTS | -0.890 |
haar | -0.837 |
bley | -0.821 |
atos | -0.801 |
Token | America |
Token ID | 2253 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
raq | +0.855 |
hai | +0.808 |
Wast | +0.724 |
Wars | +0.687 |
fronts | +0.678 |
Neg logit contributions | |
zona | -1.184 |
RESULTS | -1.080 |
haar | -1.012 |
bley | -0.993 |
atos | -0.968 |
Token | as |
Token ID | 355 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
zona | +0.295 |
RESULTS | +0.267 |
haar | +0.250 |
bley | +0.245 |
atos | +0.238 |
Neg logit contributions | |
raq | -0.240 |
hai | -0.228 |
Wast | -0.205 |
Wars | -0.195 |
Synd | -0.193 |
Token | ' |
Token ID | 705 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
zona | +1.793 |
RESULTS | +1.623 |
haar | +1.503 |
bley | +1.466 |
iscons | +1.428 |
Neg logit contributions | |
raq | -1.599 |
hai | -1.526 |
Wast | -1.367 |
Wars | -1.311 |
Synd | -1.281 |
Token | not |
Token ID | 1662 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
zona | +0.904 |
RESULTS | +0.820 |
haar | +0.762 |
bley | +0.745 |
atos | +0.727 |
Neg logit contributions | |
raq | -0.766 |
hai | -0.725 |
Wast | -0.661 |
Wars | -0.624 |
Synd | -0.621 |
Token | a |
Token ID | 257 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
zona | +0.316 |
RESULTS | +0.285 |
haar | +0.267 |
bley | +0.262 |
atos | +0.255 |
Neg logit contributions | |
raq | -0.257 |
hai | -0.243 |
Wast | -0.219 |
Wars | -0.209 |
Synd | -0.206 |
Token | threat |
Token ID | 2372 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
raq | +0.144 |
hai | +0.136 |
Wast | +0.122 |
Wars | +0.115 |
fronts | +0.114 |
Neg logit contributions | |
zona | -0.197 |
RESULTS | -0.180 |
haar | -0.168 |
bley | -0.165 |
atos | -0.161 |
Token | to |
Token ID | 284 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
raq | +0.377 |
hai | +0.356 |
Wast | +0.317 |
Wars | +0.300 |
fronts | +0.296 |
Neg logit contributions | |
zona | -0.539 |
RESULTS | -0.493 |
haar | -0.462 |
bley | -0.454 |
atos | -0.442 |
Token | who |
Token ID | 508 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
raq | +2.121 |
hai | +2.015 |
Wast | +1.818 |
Wars | +1.722 |
fronts | +1.711 |
Neg logit contributions | |
zona | -2.910 |
RESULTS | -2.675 |
haar | -2.505 |
bley | -2.449 |
atos | -2.389 |
Token | we |
Token ID | 356 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
raq | +0.209 |
hai | +0.197 |
Wast | +0.175 |
Wars | +0.165 |
Synd | +0.163 |
Neg logit contributions | |
zona | -0.304 |
RESULTS | -0.277 |
haar | -0.260 |
bley | -0.255 |
atos | -0.249 |
Token | are |
Token ID | 389 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
zona | +0.803 |
RESULTS | +0.732 |
haar | +0.690 |
bley | +0.678 |
atos | +0.661 |
Neg logit contributions | |
raq | -0.549 |
hai | -0.518 |
Wast | -0.460 |
Wars | -0.436 |
Synd | -0.428 |
Token | ' |
Token ID | 6 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
raq | +2.677 |
hai | +2.575 |
Wast | +2.240 |
fronts | +2.142 |
Wars | +2.129 |
Neg logit contributions | |
zona | -4.165 |
RESULTS | -3.844 |
haar | -3.579 |
bley | -3.486 |
atos | -3.428 |
Token | iser |
Token ID | 5847 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
raq | +3.261 |
hai | +3.095 |
Wast | +2.729 |
Wars | +2.656 |
iles | +2.620 |
Neg logit contributions | |
zona | -3.888 |
RESULTS | -3.538 |
haar | -3.251 |
bley | -3.214 |
iscons | -3.094 |
Token | K |
Token ID | 42 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
raq | +1.089 |
hai | +1.036 |
Wast | +0.930 |
Wars | +0.889 |
Synd | +0.875 |
Neg logit contributions | |
zona | -1.336 |
RESULTS | -1.212 |
haar | -1.132 |
bley | -1.109 |
atos | -1.076 |
Token | ier |
Token ID | 959 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
raq | +2.177 |
hai | +2.072 |
Wast | +1.834 |
Wars | +1.766 |
iles | +1.751 |
Neg logit contributions | |
zona | -2.734 |
RESULTS | -2.485 |
haar | -2.304 |
bley | -2.275 |
iscons | -2.198 |
Token | an |
Token ID | 272 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
raq | +1.113 |
hai | +1.064 |
Wast | +0.953 |
Wars | +0.917 |
Synd | +0.904 |
Neg logit contributions | |
zona | -1.249 |
RESULTS | -1.130 |
haar | -1.049 |
bley | -1.028 |
iscons | -0.995 |
Token | Profile |
Token ID | 13118 |
Feature activation | -5.72e-03 |
Pos logit contributions | |
raq | +1.373 |
hai | +1.288 |
Wast | +1.115 |
Wars | +1.059 |
Synd | +1.030 |
Neg logit contributions | |
zona | -2.539 |
RESULTS | -2.352 |
haar | -2.217 |
bley | -2.187 |
iscons | -2.128 |
Token | Blog |
Token ID | 14001 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
raq | +0.056 |
hai | +0.053 |
Wast | +0.047 |
Wars | +0.045 |
Synd | +0.044 |
Neg logit contributions | |
zona | -0.082 |
RESULTS | -0.075 |
haar | -0.070 |
bley | -0.069 |
atos | -0.067 |
Token | Joined |
Token ID | 16709 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
raq | +1.621 |
hai | +1.509 |
Wast | +1.311 |
Wars | +1.201 |
Synd | +1.174 |
Neg logit contributions | |
zona | -3.981 |
RESULTS | -3.707 |
haar | -3.533 |
bley | -3.462 |
atos | -3.415 |
Token | August |
Token ID | 2932 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
raq | +0.826 |
hai | +0.786 |
Wast | +0.711 |
Wars | +0.675 |
Synd | +0.668 |
Neg logit contributions | |
zona | -1.041 |
RESULTS | -0.947 |
haar | -0.888 |
bley | -0.870 |
atos | -0.845 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
zona | +2.863 |
RESULTS | +2.589 |
haar | +2.382 |
bley | +2.314 |
atos | +2.304 |
Neg logit contributions | |
raq | -2.158 |
hai | -2.013 |
Wast | -1.738 |
obar | -1.720 |
fronts | -1.711 |
Token | United |
Token ID | 1578 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
zona | +3.876 |
RESULTS | +3.394 |
haar | +3.082 |
bley | +2.999 |
atos | +2.952 |
Neg logit contributions | |
raq | -4.018 |
hai | -3.787 |
obar | -3.372 |
fronts | -3.360 |
Wast | -3.344 |
Token | States |
Token ID | 1829 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
raq | +1.238 |
hai | +1.197 |
Wast | +1.101 |
Wars | +1.049 |
Synd | +1.043 |
Neg logit contributions | |
zona | -1.210 |
RESULTS | -1.103 |
haar | -1.013 |
bley | -1.005 |
atos | -0.960 |
Token | that |
Token ID | 326 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
zona | +0.904 |
RESULTS | +0.818 |
haar | +0.767 |
bley | +0.749 |
atos | +0.735 |
Neg logit contributions | |
raq | -0.722 |
hai | -0.686 |
Wast | -0.615 |
Wars | -0.587 |
Synd | -0.578 |
Token | denied |
Token ID | 6699 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
zona | +5.284 |
RESULTS | +4.720 |
haar | +4.365 |
bley | +4.322 |
atos | +4.222 |
Neg logit contributions | |
raq | -4.619 |
hai | -4.324 |
Wast | -3.824 |
Wars | -3.671 |
tein | -3.636 |
Token | rail |
Token ID | 6787 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
raq | +1.675 |
hai | +1.578 |
Wast | +1.422 |
fronts | +1.342 |
Wars | +1.340 |
Neg logit contributions | |
zona | -2.495 |
RESULTS | -2.288 |
haar | -2.158 |
bley | -2.103 |
atos | -2.051 |
Token | roads |
Token ID | 21372 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
zona | +3.415 |
RESULTS | +3.072 |
haar | +2.888 |
bley | +2.823 |
iscons | +2.708 |
Neg logit contributions | |
raq | -2.890 |
hai | -2.780 |
Wast | -2.495 |
Wars | -2.392 |
obar | -2.345 |
Token | " |
Token ID | 366 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
zona | +1.772 |
RESULTS | +1.595 |
haar | +1.502 |
bley | +1.474 |
atos | +1.425 |
Neg logit contributions | |
raq | -1.398 |
hai | -1.331 |
Wast | -1.182 |
Wars | -1.135 |
obar | -1.105 |
Token | the |
Token ID | 1169 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
raq | +2.476 |
hai | +2.364 |
Wast | +2.114 |
Wars | +2.035 |
iles | +1.991 |
Neg logit contributions | |
zona | -3.146 |
RESULTS | -2.877 |
haar | -2.682 |
bley | -2.620 |
iscons | -2.568 |
Token | right |
Token ID | 826 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
raq | +5.219 |
hai | +5.043 |
Wast | +4.668 |
prominence | +4.412 |
fronts | +4.271 |
Neg logit contributions | |
zona | -9.578 |
RESULTS | -9.028 |
haar | -8.368 |
bley | -8.186 |
atos | -8.089 |
Token | to |
Token ID | 284 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
zona | +0.795 |
RESULTS | +0.719 |
haar | +0.675 |
bley | +0.661 |
atos | +0.643 |
Neg logit contributions | |
raq | -0.627 |
hai | -0.594 |
Wast | -0.534 |
Wars | -0.507 |
Synd | -0.501 |
Token | deduct |
Token ID | 18777 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
zona | +1.263 |
RESULTS | +1.147 |
haar | +1.074 |
bley | +1.058 |
atos | +1.027 |
Neg logit contributions | |
raq | -0.927 |
hai | -0.880 |
Wast | -0.780 |
Wars | -0.740 |
Synd | -0.730 |
Token | the |
Token ID | 262 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
raq | +2.076 |
hai | +1.972 |
Wast | +1.768 |
Wars | +1.677 |
iles | +1.667 |
Neg logit contributions | |
zona | -2.793 |
RESULTS | -2.567 |
haar | -2.382 |
bley | -2.344 |
atos | -2.276 |
Token | amount |
Token ID | 2033 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
zona | +0.496 |
RESULTS | +0.452 |
haar | +0.424 |
bley | +0.416 |
atos | +0.405 |
Neg logit contributions | |
raq | -0.373 |
hai | -0.352 |
Wast | -0.313 |
Wars | -0.299 |
Synd | -0.293 |
Token | alliance |
Token ID | 12801 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
raq | +1.885 |
hai | +1.786 |
Wast | +1.586 |
Synd | +1.485 |
Wars | +1.481 |
Neg logit contributions | |
zona | -2.917 |
RESULTS | -2.670 |
haar | -2.518 |
bley | -2.482 |
atos | -2.414 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
raq | +1.848 |
hai | +1.750 |
Wast | +1.570 |
fronts | +1.511 |
Wars | +1.486 |
Neg logit contributions | |
zona | -2.646 |
RESULTS | -2.409 |
haar | -2.265 |
bley | -2.225 |
atos | -2.154 |
Token | wasted |
Token ID | 18359 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
raq | +1.454 |
hai | +1.371 |
Wast | +1.209 |
fronts | +1.146 |
Wars | +1.136 |
Neg logit contributions | |
zona | -2.413 |
RESULTS | -2.211 |
haar | -2.084 |
bley | -2.052 |
atos | -1.987 |
Token | no |
Token ID | 645 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
zona | +0.671 |
RESULTS | +0.611 |
haar | +0.572 |
bley | +0.561 |
atos | +0.546 |
Neg logit contributions | |
raq | -0.516 |
hai | -0.491 |
Wast | -0.437 |
Wars | -0.418 |
Synd | -0.410 |
Token | time |
Token ID | 640 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
zona | +4.165 |
RESULTS | +3.789 |
bley | +3.348 |
haar | +3.339 |
iscons | +3.220 |
Neg logit contributions | |
raq | -5.544 |
hai | -5.213 |
Wast | -4.747 |
Wars | -4.710 |
arthed | -4.660 |
Token | in |
Token ID | 287 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
raq | +2.750 |
hai | +2.580 |
Wast | +2.304 |
fronts | +2.213 |
Wars | +2.173 |
Neg logit contributions | |
zona | -4.310 |
RESULTS | -3.888 |
haar | -3.704 |
bley | -3.655 |
atos | -3.559 |
Token | expressing |
Token ID | 16621 |
Feature activation | -8.12e-03 |
Pos logit contributions | |
raq | +5.577 |
hai | +5.190 |
Wast | +4.898 |
fronts | +4.769 |
Synd | +4.655 |
Neg logit contributions | |
zona | -9.756 |
RESULTS | -8.774 |
haar | -8.404 |
bley | -8.262 |
atos | -7.983 |
Token | its |
Token ID | 663 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
raq | +0.087 |
hai | +0.082 |
Wast | +0.074 |
Wars | +0.070 |
Synd | +0.069 |
Neg logit contributions | |
zona | -0.109 |
RESULTS | -0.099 |
haar | -0.092 |
bley | -0.090 |
atos | -0.088 |
Token | delight |
Token ID | 10974 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
zona | +1.455 |
RESULTS | +1.319 |
haar | +1.241 |
bley | +1.213 |
atos | +1.183 |
Neg logit contributions | |
raq | -1.148 |
hai | -1.095 |
Wast | -0.970 |
Wars | -0.925 |
obar | -0.909 |
Token | after |
Token ID | 8499 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
zona | +1.237 |
RESULTS | +1.122 |
haar | +1.045 |
bley | +1.026 |
atos | +1.000 |
Neg logit contributions | |
raq | -1.048 |
hai | -0.996 |
Wast | -0.898 |
Wars | -0.855 |
Synd | -0.845 |
Token | that |
Token ID | 326 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
raq | +1.209 |
hai | +1.147 |
Wast | +1.033 |
Wars | +0.982 |
Synd | +0.972 |
Neg logit contributions | |
zona | -1.579 |
RESULTS | -1.430 |
haar | -1.342 |
bley | -1.315 |
atos | -1.281 |
Token | into |
Token ID | 656 |
Feature activation | +8.17e-04 |
Pos logit contributions | |
raq | +1.409 |
hai | +1.336 |
Wast | +1.201 |
fronts | +1.139 |
Wars | +1.136 |
Neg logit contributions | |
zona | -1.930 |
RESULTS | -1.761 |
haar | -1.643 |
bley | -1.613 |
iscons | -1.574 |
Token | space |
Token ID | 2272 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
zona | +0.011 |
RESULTS | +0.010 |
haar | +0.009 |
bley | +0.009 |
atos | +0.009 |
Neg logit contributions | |
raq | -0.009 |
hai | -0.008 |
Wast | -0.008 |
Wars | -0.007 |
fronts | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
raq | +1.637 |
hai | +1.548 |
Wast | +1.400 |
Wars | +1.332 |
fronts | +1.328 |
Neg logit contributions | |
zona | -2.174 |
RESULTS | -1.988 |
haar | -1.853 |
bley | -1.820 |
iscons | -1.775 |
Token | After |
Token ID | 2293 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
raq | +0.520 |
hai | +0.494 |
Wast | +0.444 |
Wars | +0.421 |
Synd | +0.416 |
Neg logit contributions | |
zona | -0.685 |
RESULTS | -0.622 |
haar | -0.583 |
bley | -0.572 |
atos | -0.557 |
Token | the |
Token ID | 262 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
raq | +1.823 |
hai | +1.721 |
Wast | +1.556 |
Wars | +1.459 |
fronts | +1.455 |
Neg logit contributions | |
zona | -2.545 |
RESULTS | -2.304 |
haar | -2.176 |
bley | -2.129 |
atos | -2.070 |
Token | second |
Token ID | 1218 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
raq | +3.936 |
hai | +3.729 |
Wast | +3.407 |
fronts | +3.206 |
Synd | +3.190 |
Neg logit contributions | |
zona | -5.865 |
RESULTS | -5.345 |
haar | -5.101 |
bley | -4.939 |
iscons | -4.867 |
Token | launch |
Token ID | 4219 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
raq | +5.268 |
hai | +4.996 |
Wast | +4.673 |
iles | +4.346 |
Synd | +4.295 |
Neg logit contributions | |
zona | -9.043 |
RESULTS | -8.320 |
haar | -8.148 |
bley | -7.752 |
iscons | -7.485 |
Token | , |
Token ID | 11 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
zona | +1.514 |
RESULTS | +1.364 |
haar | +1.259 |
bley | +1.239 |
atos | +1.214 |
Neg logit contributions | |
raq | -1.321 |
hai | -1.266 |
Wast | -1.130 |
Wars | -1.085 |
Synd | -1.065 |
Token | a |
Token ID | 257 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
raq | +1.961 |
hai | +1.854 |
Wast | +1.678 |
Wars | +1.576 |
fronts | +1.572 |
Neg logit contributions | |
zona | -2.711 |
RESULTS | -2.446 |
haar | -2.307 |
bley | -2.256 |
atos | -2.194 |
Token | veteran |
Token ID | 9298 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
raq | +1.232 |
hai | +1.156 |
Wast | +1.037 |
Synd | +0.966 |
Wars | +0.962 |
Neg logit contributions | |
zona | -1.869 |
RESULTS | -1.712 |
haar | -1.613 |
bley | -1.573 |
atos | -1.538 |
Token | safety |
Token ID | 3747 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
zona | +0.785 |
RESULTS | +0.711 |
haar | +0.661 |
bley | +0.650 |
atos | +0.639 |
Neg logit contributions | |
raq | -0.635 |
hai | -0.605 |
Wast | -0.536 |
Wars | -0.517 |
obar | -0.505 |
Token | give |
Token ID | 1577 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
raq | +2.751 |
hai | +2.643 |
Wast | +2.366 |
Synd | +2.232 |
iles | +2.223 |
Neg logit contributions | |
zona | -3.977 |
RESULTS | -3.649 |
haar | -3.411 |
bley | -3.341 |
atos | -3.238 |
Token | herself |
Token ID | 5223 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
raq | +1.208 |
hai | +1.153 |
Wast | +1.036 |
Wars | +0.979 |
Synd | +0.972 |
Neg logit contributions | |
zona | -1.609 |
RESULTS | -1.459 |
haar | -1.366 |
bley | -1.338 |
atos | -1.306 |
Token | some |
Token ID | 617 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
raq | +1.861 |
hai | +1.776 |
Wast | +1.602 |
fronts | +1.519 |
Wars | +1.513 |
Neg logit contributions | |
zona | -2.331 |
RESULTS | -2.112 |
haar | -1.979 |
bley | -1.939 |
atos | -1.880 |
Token | energy |
Token ID | 2568 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
raq | +1.318 |
hai | +1.258 |
Wast | +1.131 |
fronts | +1.071 |
Wars | +1.070 |
Neg logit contributions | |
zona | -1.693 |
RESULTS | -1.534 |
haar | -1.437 |
bley | -1.409 |
atos | -1.372 |
Token | , |
Token ID | 11 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
zona | +3.455 |
RESULTS | +3.113 |
haar | +2.900 |
bley | +2.848 |
atos | +2.772 |
Neg logit contributions | |
raq | -3.396 |
hai | -3.223 |
Wast | -2.911 |
Wars | -2.801 |
obar | -2.743 |
Token | Bl |
Token ID | 1086 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
raq | +2.494 |
hai | +2.375 |
Wast | +2.145 |
fronts | +2.005 |
Synd | +2.002 |
Neg logit contributions | |
zona | -3.749 |
RESULTS | -3.424 |
haar | -3.226 |
bley | -3.148 |
atos | -3.096 |
Token | ume |
Token ID | 2454 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
raq | +3.464 |
hai | +3.312 |
uer | +2.333 |
iles | +2.324 |
usal | +2.276 |
Neg logit contributions | |
zona | -11.972 |
RESULTS | -11.496 |
haar | -10.514 |
iscons | -10.297 |
atos | -10.212 |
Token | puts |
Token ID | 7584 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
raq | +0.150 |
hai | +0.142 |
Wast | +0.125 |
Wars | +0.118 |
fronts | +0.116 |
Neg logit contributions | |
zona | -0.235 |
RESULTS | -0.216 |
haar | -0.203 |
bley | -0.199 |
atos | -0.194 |
Token | on |
Token ID | 319 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
raq | +0.549 |
hai | +0.519 |
Wast | +0.461 |
Wars | +0.435 |
fronts | +0.430 |
Neg logit contributions | |
zona | -0.817 |
RESULTS | -0.747 |
haar | -0.702 |
bley | -0.689 |
atos | -0.672 |
Token | some |
Token ID | 617 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
zona | +0.322 |
RESULTS | +0.292 |
haar | +0.273 |
bley | +0.267 |
atos | +0.260 |
Neg logit contributions | |
raq | -0.263 |
hai | -0.251 |
Wast | -0.225 |
Wars | -0.214 |
Synd | -0.211 |
Token | songs |
Token ID | 7259 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
raq | +0.563 |
hai | +0.534 |
Wast | +0.477 |
Wars | +0.451 |
fronts | +0.448 |
Neg logit contributions | |
zona | -0.791 |
RESULTS | -0.721 |
haar | -0.677 |
bley | -0.662 |
atos | -0.646 |
Token | |
Token ID | 3907 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
zona | +2.280 |
RESULTS | +2.057 |
haar | +1.948 |
bley | +1.893 |
atos | +1.846 |
Neg logit contributions | |
raq | -1.824 |
hai | -1.712 |
Wast | -1.553 |
Wars | -1.483 |
Synd | -1.454 |
Token | ing |
Token ID | 278 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
raq | +2.619 |
hai | +2.547 |
Wast | +2.284 |
iles | +2.198 |
tered | +2.194 |
Neg logit contributions | |
zona | -2.138 |
RESULTS | -1.934 |
haar | -1.756 |
bley | -1.723 |
iscons | -1.646 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
raq | +2.497 |
hai | +2.400 |
Wast | +2.151 |
fronts | +2.042 |
Synd | +2.022 |
Neg logit contributions | |
zona | -3.302 |
RESULTS | -3.022 |
haar | -2.813 |
bley | -2.766 |
atos | -2.677 |
Token | Carter |
Token ID | 10831 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
raq | +1.429 |
hai | +1.364 |
Wast | +1.245 |
Wars | +1.183 |
Synd | +1.176 |
Neg logit contributions | |
zona | -1.529 |
RESULTS | -1.375 |
haar | -1.278 |
bley | -1.249 |
atos | -1.214 |
Token | . |
Token ID | 13 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
raq | +1.294 |
hai | +1.235 |
Wast | +1.103 |
Wars | +1.043 |
fronts | +1.035 |
Neg logit contributions | |
zona | -1.766 |
RESULTS | -1.619 |
haar | -1.512 |
bley | -1.478 |
atos | -1.443 |
Token | Al |
Token ID | 978 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
raq | +0.774 |
hai | +0.734 |
Wast | +0.658 |
Wars | +0.623 |
Synd | +0.615 |
Neg logit contributions | |
zona | -1.083 |
RESULTS | -0.987 |
haar | -0.926 |
bley | -0.911 |
atos | -0.886 |
Token | |
Token ID | 3907 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
raq | +7.559 |
hai | +7.288 |
tered | +6.564 |
Wast | +6.436 |
obar | +6.134 |
Neg logit contributions | |
zona | -7.862 |
RESULTS | -7.714 |
haar | -6.960 |
bley | -6.799 |
atos | -6.557 |
Token | though |
Token ID | 2016 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
raq | +2.445 |
hai | +2.308 |
Wast | +2.076 |
tered | +1.995 |
Wars | +1.981 |
Neg logit contributions | |
zona | -2.569 |
RESULTS | -2.389 |
haar | -2.179 |
bley | -2.152 |
atos | -2.058 |
Token | he |
Token ID | 339 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
zona | +0.207 |
RESULTS | +0.188 |
haar | +0.176 |
bley | +0.172 |
atos | +0.168 |
Neg logit contributions | |
raq | -0.158 |
hai | -0.150 |
Wast | -0.134 |
Wars | -0.128 |
fronts | -0.125 |
Token | left |
Token ID | 1364 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
raq | +0.472 |
hai | +0.445 |
Wast | +0.394 |
Wars | +0.372 |
fronts | +0.367 |
Neg logit contributions | |
zona | -0.727 |
RESULTS | -0.666 |
haar | -0.626 |
bley | -0.615 |
atos | -0.600 |
Token | the |
Token ID | 262 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
raq | +0.580 |
hai | +0.550 |
Wast | +0.495 |
Wars | +0.470 |
fronts | +0.464 |
Neg logit contributions | |
zona | -0.733 |
RESULTS | -0.666 |
haar | -0.622 |
bley | -0.610 |
atos | -0.594 |