Token | Del |
Token ID | 13856 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
bid | +3.879 |
drawn | +3.743 |
Stro | +3.659 |
hene | +3.487 |
ringe | +3.353 |
Neg logit contributions | |
olars | -3.605 |
pont | -3.434 |
litter | -3.404 |
lations | -3.381 |
tons | -3.356 |
Token | hi |
Token ID | 5303 |
Feature activation | +9.72e+00 |
Pos logit contributions | |
bid | +5.078 |
drawn | +4.838 |
Stro | +4.708 |
hene | +4.544 |
inder | +4.491 |
Neg logit contributions | |
olars | -11.087 |
�� | -11.002 |
tons | -10.935 |
litter | -10.784 |
Soph | -10.767 |
Token | Law |
Token ID | 3854 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
Stro | +6.292 |
bid | +6.197 |
hene | +5.801 |
drawn | +5.795 |
inder | +5.644 |
Neg logit contributions | |
olars | -6.536 |
tons | -6.296 |
lations | -6.199 |
lear | -6.001 |
esta | -5.997 |
Token | Minister |
Token ID | 4139 |
Feature activation | +8.91e+00 |
Pos logit contributions | |
olars | +2.170 |
tons | +2.149 |
Soph | +2.032 |
litter | +1.996 |
lations | +1.993 |
Neg logit contributions | |
bid | -7.948 |
Stro | -7.806 |
drawn | -7.755 |
hene | -7.585 |
ringe | -7.394 |
Token | J |
Token ID | 449 |
Feature activation | +9.84e+00 |
Pos logit contributions | |
bid | +5.161 |
Stro | +5.109 |
drawn | +4.696 |
hene | +4.615 |
inder | +4.444 |
Neg logit contributions | |
olars | -6.846 |
tons | -6.615 |
lear | -6.548 |
lations | -6.456 |
esm | -6.330 |
Token | it |
Token ID | 270 |
Feature activation | +2.18e+01 |
Pos logit contributions | |
bid | +4.902 |
hene | +4.712 |
Stro | +4.678 |
inder | +4.607 |
drawn | +4.404 |
Neg logit contributions | |
olars | -7.965 |
tons | -7.920 |
litter | -7.806 |
resil | -7.665 |
�� | -7.635 |
Token | ender |
Token ID | 2194 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
inder | +7.691 |
bid | +7.563 |
drawn | +7.502 |
Stro | +7.204 |
hene | +6.964 |
Neg logit contributions | |
�� | -19.015 |
olars | -18.476 |
pont | -18.438 |
litter | -18.387 |
resil | -17.967 |
Token | Singh |
Token ID | 14403 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
Stro | +4.433 |
bid | +4.073 |
drawn | +3.295 |
hene | +3.191 |
inder | +3.056 |
Neg logit contributions | |
olars | -14.921 |
resil | -14.713 |
lear | -14.306 |
tons | -14.209 |
�� | -14.146 |
Token | Tom |
Token ID | 4186 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
bid | +2.059 |
Stro | +2.029 |
drawn | +1.952 |
hene | +1.888 |
ringe | +1.831 |
Neg logit contributions | |
olars | -1.567 |
tons | -1.482 |
lations | -1.469 |
lear | -1.453 |
litter | -1.439 |
Token | ar |
Token ID | 283 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
olars | +1.401 |
tons | +1.361 |
esta | +1.325 |
lations | +1.323 |
lear | +1.322 |
Neg logit contributions | |
bid | -1.367 |
Stro | -1.358 |
drawn | -1.317 |
hene | -1.267 |
ringe | -1.225 |
Token | of |
Token ID | 286 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
bid | +1.850 |
Stro | +1.813 |
drawn | +1.757 |
hene | +1.708 |
ringe | +1.639 |
Neg logit contributions | |
olars | -1.770 |
tons | -1.730 |
lations | -1.678 |
lear | -1.651 |
litter | -1.641 |
Token | SEM |
Token ID | 48603 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
bid | +1.148 |
Stro | +1.130 |
drawn | +1.089 |
hene | +1.044 |
ringe | +1.006 |
Neg logit contributions | |
olars | -1.045 |
tons | -0.990 |
lations | -0.970 |
lear | -0.963 |
litter | -0.958 |
Token | INAL |
Token ID | 17961 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
bid | +2.252 |
Stro | +2.229 |
drawn | +2.104 |
hene | +2.003 |
ringe | +1.944 |
Neg logit contributions | |
olars | -2.779 |
tons | -2.695 |
lations | -2.621 |
lear | -2.602 |
esta | -2.600 |
Token | MA |
Token ID | 8779 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
olars | +0.765 |
tons | +0.734 |
lations | +0.718 |
litter | +0.717 |
pont | +0.711 |
Neg logit contributions | |
bid | -0.863 |
Stro | -0.844 |
drawn | -0.826 |
hene | -0.793 |
ringe | -0.771 |
Token | IN |
Token ID | 1268 |
Feature activation | +6.63e+00 |
Pos logit contributions | |
bid | +3.309 |
Stro | +3.268 |
drawn | +2.991 |
inder | +2.853 |
hene | +2.837 |
Neg logit contributions | |
olars | -6.194 |
tons | -5.995 |
lations | -5.878 |
litter | -5.755 |
esta | -5.753 |
Token | AK |
Token ID | 15837 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
bid | +4.724 |
Stro | +4.718 |
drawn | +4.546 |
hene | +4.283 |
ringe | +4.042 |
Neg logit contributions | |
olars | -4.459 |
tons | -4.104 |
esta | -4.030 |
lations | -4.020 |
litter | -3.991 |
Token | NOW |
Token ID | 45669 |
Feature activation | +2.03e+01 |
Pos logit contributions | |
bid | +3.310 |
Stro | +3.285 |
drawn | +3.219 |
hene | +3.010 |
ringe | +2.841 |
Neg logit contributions | |
olars | -4.472 |
tons | -4.281 |
lations | -4.196 |
Soph | -4.166 |
litter | -4.150 |
Token | LED |
Token ID | 30465 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
drawn | +4.489 |
bid | +4.480 |
Stro | +3.819 |
inder | +3.565 |
hene | +3.280 |
Neg logit contributions | |
olars | -20.500 |
esta | -19.760 |
emort | -19.680 |
litter | -19.520 |
resil | -19.491 |
Token | G |
Token ID | 38 |
Feature activation | +1.60e+01 |
Pos logit contributions | |
bid | +2.404 |
Stro | +2.361 |
drawn | +2.329 |
hene | +2.222 |
ringe | +2.154 |
Neg logit contributions | |
olars | -2.023 |
tons | -1.890 |
litter | -1.875 |
pont | -1.863 |
lations | -1.862 |
Token | ED |
Token ID | 1961 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
drawn | +2.978 |
bid | +2.915 |
Stro | +2.710 |
inder | +1.984 |
ID | +1.970 |
Neg logit contributions | |
olars | -17.870 |
litter | -17.032 |
pont | -16.725 |
emort | -16.655 |
resil | -16.551 |
Token | NET |
Token ID | 30502 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
bid | +1.779 |
Stro | +1.754 |
drawn | +1.701 |
hene | +1.627 |
ringe | +1.563 |
Neg logit contributions | |
olars | -1.619 |
tons | -1.517 |
lations | -1.494 |
esta | -1.481 |
litter | -1.477 |
Token | CALL |
Token ID | 42815 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
bid | +1.605 |
Stro | +1.579 |
drawn | +1.520 |
hene | +1.422 |
ringe | +1.367 |
Neg logit contributions | |
olars | -2.015 |
tons | -1.918 |
esta | -1.866 |
lations | -1.860 |
litter | -1.858 |
Token | Media |
Token ID | 6343 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
olars | +1.189 |
tons | +1.148 |
lations | +1.123 |
litter | +1.121 |
pont | +1.112 |
Neg logit contributions | |
bid | -1.308 |
Stro | -1.274 |
drawn | -1.250 |
hene | -1.201 |
ringe | -1.172 |
Token | . |
Token ID | 13 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
bid | +3.224 |
Stro | +3.146 |
drawn | +2.975 |
hene | +2.893 |
ringe | +2.775 |
Neg logit contributions | |
olars | -3.470 |
tons | -3.314 |
litter | -3.260 |
lear | -3.239 |
lations | -3.205 |
Token | Executive |
Token ID | 10390 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Stro | +3.022 |
bid | +2.992 |
drawn | +2.866 |
hene | +2.763 |
ringe | +2.658 |
Neg logit contributions | |
olars | -2.415 |
tons | -2.265 |
litter | -2.262 |
lear | -2.221 |
pont | -2.203 |
Token | producers |
Token ID | 11408 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
bid | +1.069 |
Stro | +1.055 |
drawn | +1.027 |
hene | +0.941 |
ringe | +0.917 |
Neg logit contributions | |
olars | -1.707 |
tons | -1.662 |
litter | -1.630 |
lations | -1.629 |
esta | -1.623 |
Token | are |
Token ID | 389 |
Feature activation | +7.45e+00 |
Pos logit contributions | |
Stro | +7.231 |
bid | +7.070 |
drawn | +6.673 |
hene | +6.515 |
ringe | +6.271 |
Neg logit contributions | |
olars | -7.287 |
lations | -6.843 |
tons | -6.825 |
lear | -6.773 |
esm | -6.737 |
Token | Robert |
Token ID | 5199 |
Feature activation | +2.00e+01 |
Pos logit contributions | |
Stro | +5.246 |
bid | +5.139 |
drawn | +4.970 |
hene | +4.756 |
ringe | +4.579 |
Neg logit contributions | |
olars | -4.869 |
lations | -4.668 |
tons | -4.613 |
esm | -4.585 |
lear | -4.559 |
Token | Hal |
Token ID | 11023 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
Stro | +11.001 |
bid | +10.069 |
hene | +9.091 |
drawn | +8.791 |
inder | +8.614 |
Neg logit contributions | |
�� | -13.198 |
olars | -13.089 |
litter | -12.761 |
resil | -12.748 |
pont | -12.490 |
Token | mi |
Token ID | 11632 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
bid | +0.474 |
Stro | +0.455 |
drawn | +0.449 |
hene | +0.430 |
ringe | +0.418 |
Neg logit contributions | |
olars | -0.542 |
tons | -0.523 |
litter | -0.519 |
pont | -0.515 |
lations | -0.514 |
Token | Sr |
Token ID | 21714 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
olars | +0.397 |
tons | +0.374 |
lations | +0.362 |
litter | +0.361 |
lear | +0.355 |
Neg logit contributions | |
bid | -0.864 |
Stro | -0.850 |
drawn | -0.834 |
hene | -0.811 |
ringe | -0.795 |
Token | . |
Token ID | 13 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
olars | +1.310 |
tons | +1.262 |
lations | +1.238 |
litter | +1.234 |
pont | +1.227 |
Neg logit contributions | |
bid | -1.258 |
Stro | -1.224 |
drawn | -1.201 |
hene | -1.144 |
ringe | -1.116 |
Token | for |
Token ID | 329 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
bid | +1.856 |
Stro | +1.847 |
drawn | +1.780 |
hene | +1.712 |
ringe | +1.665 |
Neg logit contributions | |
olars | -1.948 |
tons | -1.904 |
litter | -1.859 |
lations | -1.830 |
lear | -1.824 |
Token | , |
Token ID | 11 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
bid | +3.687 |
Stro | +3.577 |
drawn | +3.520 |
hene | +3.270 |
ringe | +3.247 |
Neg logit contributions | |
olars | -3.948 |
tons | -3.740 |
lear | -3.714 |
lations | -3.681 |
esta | -3.679 |
Token | but |
Token ID | 475 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
bid | +3.190 |
Stro | +3.158 |
drawn | +3.054 |
hene | +2.921 |
ringe | +2.870 |
Neg logit contributions | |
olars | -3.136 |
lations | -2.975 |
tons | -2.972 |
lear | -2.965 |
esta | -2.888 |
Token | keep |
Token ID | 1394 |
Feature activation | +7.26e+00 |
Pos logit contributions | |
bid | +4.958 |
Stro | +4.793 |
drawn | +4.721 |
hene | +4.487 |
ringe | +4.476 |
Neg logit contributions | |
olars | -3.801 |
lations | -3.493 |
lear | -3.478 |
esta | -3.470 |
Soph | -3.458 |
Token | the |
Token ID | 262 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
Stro | +5.001 |
bid | +4.921 |
drawn | +4.829 |
ringe | +4.467 |
hene | +4.387 |
Neg logit contributions | |
olars | -4.877 |
lations | -4.554 |
tons | -4.542 |
lear | -4.512 |
esta | -4.470 |
Token | resulting |
Token ID | 7186 |
Feature activation | +6.88e+00 |
Pos logit contributions | |
Stro | +3.665 |
bid | +3.583 |
drawn | +3.476 |
hene | +3.312 |
ringe | +3.271 |
Neg logit contributions | |
olars | -4.031 |
tons | -3.800 |
lations | -3.798 |
lear | -3.762 |
esm | -3.723 |
Token | juice |
Token ID | 13135 |
Feature activation | +1.96e+01 |
Pos logit contributions | |
Stro | +4.155 |
bid | +4.015 |
drawn | +3.899 |
hene | +3.707 |
ringe | +3.623 |
Neg logit contributions | |
olars | -5.287 |
lear | -4.931 |
tons | -4.930 |
lations | -4.925 |
esm | -4.898 |
Token | on |
Token ID | 319 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
Stro | +10.546 |
drawn | +10.164 |
bid | +9.954 |
concentration | +9.761 |
traces | +9.403 |
Neg logit contributions | |
olars | -12.487 |
tons | -12.257 |
esm | -12.234 |
lear | -12.022 |
folios | -11.788 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
Stro | +6.810 |
bid | +6.445 |
drawn | +6.229 |
ringe | +5.932 |
hene | +5.758 |
Neg logit contributions | |
olars | -7.992 |
tons | -7.719 |
lations | -7.644 |
esm | -7.640 |
lear | -7.496 |
Token | strong |
Token ID | 1913 |
Feature activation | +7.95e+00 |
Pos logit contributions | |
Stro | +7.259 |
bid | +6.796 |
drawn | +6.699 |
ringe | +6.464 |
inder | +6.398 |
Neg logit contributions | |
olars | -8.069 |
lations | -7.708 |
lear | -7.699 |
tons | -7.697 |
esm | -7.634 |
Token | side |
Token ID | 1735 |
Feature activation | +9.61e+00 |
Pos logit contributions | |
Stro | +3.174 |
bid | +3.155 |
drawn | +2.908 |
hene | +2.781 |
ringe | +2.618 |
Neg logit contributions | |
olars | -7.432 |
tons | -7.278 |
esta | -7.237 |
lations | -7.236 |
lear | -7.204 |
Token | . |
Token ID | 13 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
bid | +5.759 |
Stro | +5.675 |
drawn | +5.469 |
ringe | +5.192 |
hene | +5.149 |
Neg logit contributions | |
olars | -6.950 |
lear | -6.765 |
esta | -6.550 |
tons | -6.547 |
lations | -6.415 |
Token | ors |
Token ID | 669 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
olars | +0.089 |
tons | +0.086 |
lations | +0.085 |
litter | +0.084 |
pont | +0.084 |
Neg logit contributions | |
bid | -0.086 |
Stro | -0.084 |
drawn | -0.082 |
hene | -0.079 |
ringe | -0.077 |
Token | carried |
Token ID | 5281 |
Feature activation | -7.87e+00 |
Pos logit contributions | |
bid | +7.033 |
Stro | +7.004 |
drawn | +6.779 |
hene | +6.156 |
ringe | +5.823 |
Neg logit contributions | |
olars | -11.715 |
tons | -11.183 |
emort | -11.141 |
esm | -11.090 |
lations | -10.931 |
Token | the |
Token ID | 262 |
Feature activation | +6.80e+00 |
Pos logit contributions | |
olars | +3.856 |
tons | +3.784 |
pont | +3.735 |
lations | +3.713 |
litter | +3.706 |
Neg logit contributions | |
bid | -6.784 |
Stro | -6.520 |
drawn | -6.410 |
hene | -6.352 |
ringe | -6.279 |
Token | Catalan |
Token ID | 31066 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
Stro | +2.480 |
bid | +2.451 |
drawn | +2.310 |
hene | +2.063 |
ringe | +1.852 |
Neg logit contributions | |
olars | -6.788 |
tons | -6.519 |
lear | -6.396 |
esta | -6.364 |
lations | -6.353 |
Token | pro |
Token ID | 386 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
bid | +2.717 |
Stro | +2.675 |
drawn | +2.587 |
hene | +2.485 |
ringe | +2.407 |
Neg logit contributions | |
olars | -1.980 |
tons | -1.864 |
lations | -1.813 |
lear | -1.810 |
esta | -1.782 |
Token | - |
Token ID | 12 |
Feature activation | +1.96e+01 |
Pos logit contributions | |
bid | +3.730 |
Stro | +3.578 |
drawn | +3.537 |
hene | +3.348 |
ringe | +3.226 |
Neg logit contributions | |
olars | -4.067 |
tons | -3.839 |
lear | -3.786 |
litter | -3.774 |
esta | -3.758 |
Token | independence |
Token ID | 39894 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
bid | +8.521 |
drawn | +8.516 |
364 | +7.177 |
hene | +7.144 |
ringe | +6.943 |
Neg logit contributions | |
olars | -15.735 |
litter | -15.354 |
resil | -15.305 |
pont | -15.218 |
Soph | -15.163 |
Token | flag |
Token ID | 6056 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
bid | +3.171 |
Stro | +3.109 |
drawn | +3.031 |
hene | +2.849 |
ringe | +2.752 |
Neg logit contributions | |
olars | -3.349 |
lations | -3.119 |
lear | -3.117 |
tons | -3.094 |
esta | -3.050 |
Token | - |
Token ID | 532 |
Feature activation | +7.86e+00 |
Pos logit contributions | |
bid | +0.996 |
Stro | +0.981 |
drawn | +0.962 |
hene | +0.909 |
ringe | +0.878 |
Neg logit contributions | |
olars | -1.003 |
tons | -0.967 |
lations | -0.945 |
lear | -0.940 |
esta | -0.934 |
Token | the |
Token ID | 1169 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Stro | +3.721 |
bid | +3.691 |
drawn | +3.633 |
hene | +3.024 |
inder | +3.022 |
Neg logit contributions | |
olars | -6.898 |
tons | -6.620 |
lations | -6.513 |
lear | -6.448 |
esta | -6.439 |
Token | est |
Token ID | 1556 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
olars | +1.000 |
tons | +0.958 |
lations | +0.935 |
litter | +0.933 |
pont | +0.924 |
Neg logit contributions | |
bid | -1.394 |
Stro | -1.363 |
drawn | -1.339 |
hene | -1.291 |
ringe | -1.262 |
Token | dan |
Token ID | 25604 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
olars | +2.129 |
tons | +2.094 |
lear | +2.034 |
lations | +2.033 |
esta | +2.020 |
Neg logit contributions | |
Stro | -2.449 |
bid | -2.435 |
drawn | -2.286 |
hene | -2.239 |
ringe | -2.170 |
Token | meric |
Token ID | 946 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
olars | +4.115 |
lations | +3.994 |
lear | +3.965 |
tons | +3.965 |
esta | +3.940 |
Neg logit contributions | |
Stro | -1.164 |
bid | -1.151 |
drawn | -1.023 |
hene | -0.876 |
ringe | -0.833 |
Token | a |
Token ID | 64 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
bid | +3.346 |
drawn | +3.088 |
Stro | +3.054 |
hene | +2.900 |
ringe | +2.779 |
Neg logit contributions | |
olars | -4.887 |
litter | -4.686 |
pont | -4.650 |
Soph | -4.626 |
lations | -4.597 |
Token | CNN |
Token ID | 18474 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
bid | +3.023 |
Stro | +2.874 |
drawn | +2.867 |
hene | +2.712 |
ringe | +2.619 |
Neg logit contributions | |
olars | -3.283 |
tons | -3.116 |
litter | -3.088 |
pont | -3.086 |
lations | -3.065 |
Token | ) |
Token ID | 8 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
olars | +1.442 |
tons | +1.426 |
lations | +1.365 |
Soph | +1.341 |
litter | +1.329 |
Neg logit contributions | |
bid | -2.864 |
Stro | -2.816 |
drawn | -2.769 |
hene | -2.709 |
ringe | -2.659 |
Token | October |
Token ID | 3267 |
Feature activation | +1.96e+01 |
Pos logit contributions | |
bid | +2.867 |
Stro | +2.807 |
drawn | +2.732 |
hene | +2.677 |
ringe | +2.563 |
Neg logit contributions | |
olars | -2.153 |
tons | -2.053 |
lear | -1.971 |
litter | -1.971 |
lations | -1.954 |
Token | 23 |
Token ID | 2242 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
bid | +6.734 |
Stro | +6.682 |
drawn | +5.695 |
hene | +5.045 |
advertisement | +4.765 |
Neg logit contributions | |
olars | -18.005 |
�� | -16.852 |
emort | -16.454 |
lations | -16.162 |
lear | -16.010 |
Token | , |
Token ID | 11 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
bid | +0.579 |
Stro | +0.564 |
drawn | +0.552 |
hene | +0.527 |
ringe | +0.513 |
Neg logit contributions | |
olars | -0.554 |
tons | -0.527 |
lations | -0.520 |
litter | -0.520 |
pont | -0.516 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
bid | +1.528 |
Stro | +1.498 |
drawn | +1.464 |
hene | +1.400 |
ringe | +1.364 |
Neg logit contributions | |
olars | -1.135 |
tons | -1.067 |
lations | -1.052 |
litter | -1.049 |
pont | -1.045 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
olars | +1.365 |
tons | +1.305 |
lations | +1.274 |
litter | +1.268 |
pont | +1.257 |
Neg logit contributions | |
bid | -2.187 |
Stro | -2.139 |
drawn | -2.105 |
hene | -2.033 |
ringe | -1.990 |
Token |
|
Token ID | 198 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
olars | +0.824 |
tons | +0.802 |
lations | +0.772 |
litter | +0.767 |
Soph | +0.763 |
Neg logit contributions | |
bid | -1.410 |
Stro | -1.381 |
drawn | -1.360 |
hene | -1.323 |
ringe | -1.298 |
Token | . |
Token ID | 13 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
bid | +3.006 |
Stro | +2.973 |
drawn | +2.759 |
hene | +2.710 |
ringe | +2.624 |
Neg logit contributions | |
olars | -2.882 |
tons | -2.784 |
lations | -2.710 |
litter | -2.683 |
lear | -2.681 |
Token | Correspond |
Token ID | 34428 |
Feature activation | +9.12e+00 |
Pos logit contributions | |
Stro | +3.639 |
bid | +3.588 |
drawn | +3.431 |
hene | +3.252 |
ringe | +3.119 |
Neg logit contributions | |
olars | -3.192 |
tons | -3.021 |
litter | -2.940 |
pont | -2.921 |
lations | -2.910 |
Token | ing |
Token ID | 278 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
bid | +3.101 |
drawn | +2.888 |
Stro | +2.852 |
ringe | +2.489 |
inder | +2.428 |
Neg logit contributions | |
olars | -9.130 |
tons | -8.890 |
lear | -8.762 |
Soph | -8.748 |
litter | -8.690 |
Token | contributor |
Token ID | 18920 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
Stro | +3.462 |
bid | +3.419 |
drawn | +3.287 |
hene | +3.012 |
ringe | +2.999 |
Neg logit contributions | |
olars | -3.805 |
tons | -3.757 |
lear | -3.739 |
lations | -3.635 |
esm | -3.632 |
Token | : |
Token ID | 25 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
Stro | +6.293 |
bid | +6.224 |
drawn | +5.844 |
hene | +5.557 |
ringe | +5.322 |
Neg logit contributions | |
olars | -7.448 |
esm | -7.254 |
tons | -7.214 |
esta | -7.153 |
lations | -7.027 |
Token | David |
Token ID | 3271 |
Feature activation | +1.94e+01 |
Pos logit contributions | |
Stro | +2.629 |
bid | +2.623 |
drawn | +2.475 |
hene | +2.383 |
ringe | +2.305 |
Neg logit contributions | |
olars | -2.428 |
tons | -2.338 |
lations | -2.283 |
esta | -2.258 |
pont | -2.253 |
Token | A |
Token ID | 317 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
Stro | +12.717 |
bid | +11.124 |
hene | +10.020 |
drawn | +9.965 |
inder | +9.606 |
Neg logit contributions | |
olars | -11.664 |
resil | -11.260 |
litter | -11.131 |
lations | -10.928 |
assetsadobe | -10.770 |
Token | . |
Token ID | 13 |
Feature activation | +8.14e+00 |
Pos logit contributions | |
Stro | +4.726 |
bid | +4.552 |
hene | +4.233 |
drawn | +4.090 |
ringe | +3.970 |
Neg logit contributions | |
olars | -5.325 |
tons | -5.170 |
pont | -5.145 |
litter | -5.117 |
lations | -5.082 |
Token | Sle |
Token ID | 19498 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
Stro | +4.360 |
bid | +3.953 |
drawn | +3.535 |
hene | +3.488 |
ringe | +3.248 |
Neg logit contributions | |
olars | -7.021 |
tons | -6.746 |
litter | -6.667 |
pont | -6.639 |
lations | -6.627 |
Token | et |
Token ID | 316 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
bid | +3.188 |
Stro | +3.043 |
drawn | +3.006 |
hene | +2.932 |
ringe | +2.877 |
Neg logit contributions | |
olars | -2.243 |
tons | -2.133 |
litter | -2.125 |
pont | -2.121 |
lations | -2.116 |
Token | , |
Token ID | 11 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
bid | +0.161 |
Stro | +0.157 |
drawn | +0.153 |
hene | +0.148 |
ringe | +0.143 |
Neg logit contributions | |
olars | -0.149 |
tons | -0.143 |
litter | -0.139 |
lations | -0.139 |
pont | -0.138 |
Token | punk |
Token ID | 30354 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
bid | +1.425 |
Stro | +1.358 |
drawn | +1.343 |
hene | +1.290 |
ringe | +1.258 |
Neg logit contributions | |
olars | -1.252 |
tons | -1.200 |
lations | -1.180 |
litter | -1.166 |
pont | -1.163 |
Token | " |
Token ID | 1 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
bid | +3.416 |
Stro | +3.350 |
drawn | +3.156 |
hene | +3.097 |
ringe | +3.016 |
Neg logit contributions | |
olars | -4.073 |
tons | -3.906 |
lations | -3.877 |
Soph | -3.788 |
esta | -3.763 |
Token | their |
Token ID | 511 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
bid | +2.296 |
Stro | +2.279 |
drawn | +2.170 |
hene | +2.098 |
ringe | +2.038 |
Neg logit contributions | |
olars | -2.255 |
tons | -2.149 |
lations | -2.119 |
lear | -2.090 |
esta | -2.086 |
Token | kids |
Token ID | 3988 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
olars | +1.405 |
tons | +1.346 |
litter | +1.327 |
lations | +1.312 |
pont | +1.310 |
Neg logit contributions | |
bid | -1.912 |
Stro | -1.864 |
drawn | -1.837 |
hene | -1.770 |
ringe | -1.728 |
Token | any |
Token ID | 597 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
olars | +1.174 |
tons | +1.130 |
lations | +1.106 |
litter | +1.103 |
pont | +1.095 |
Neg logit contributions | |
bid | -1.302 |
Stro | -1.269 |
drawn | -1.245 |
hene | -1.196 |
ringe | -1.165 |
Token | way |
Token ID | 835 |
Feature activation | +1.93e+01 |
Pos logit contributions | |
bid | +0.615 |
Stro | +0.598 |
drawn | +0.583 |
hene | +0.560 |
ringe | +0.544 |
Neg logit contributions | |
olars | -0.641 |
tons | -0.616 |
lations | -0.602 |
esta | -0.594 |
lear | -0.593 |
Token | they |
Token ID | 484 |
Feature activation | +9.80e+00 |
Pos logit contributions | |
bid | +8.991 |
Stro | +8.550 |
drawn | +7.953 |
traces | +7.409 |
hene | +7.288 |
Neg logit contributions | |
olars | -13.896 |
esta | -13.313 |
tons | -13.274 |
esm | -13.251 |
assetsadobe | -13.220 |
Token | could |
Token ID | 714 |
Feature activation | +7.81e+00 |
Pos logit contributions | |
bid | +4.826 |
drawn | +4.636 |
Stro | +4.529 |
hene | +4.411 |
ringe | +4.172 |
Neg logit contributions | |
olars | -8.232 |
tons | -7.933 |
lations | -7.816 |
esta | -7.783 |
emort | -7.548 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
bid | +4.934 |
Stro | +4.739 |
drawn | +4.576 |
hene | +4.420 |
ringe | +4.372 |
Neg logit contributions | |
olars | -5.620 |
tons | -5.467 |
lations | -5.323 |
esta | -5.263 |
lear | -5.258 |
Token | Parents |
Token ID | 28231 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
bid | +0.843 |
Stro | +0.840 |
drawn | +0.806 |
hene | +0.777 |
ringe | +0.755 |
Neg logit contributions | |
olars | -0.617 |
tons | -0.582 |
lations | -0.575 |
lear | -0.571 |
litter | -0.566 |
Token | took |
Token ID | 1718 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
olars | +0.456 |
tons | +0.437 |
lations | +0.429 |
lear | +0.423 |
litter | +0.423 |
Neg logit contributions | |
bid | -0.509 |
Stro | -0.495 |
drawn | -0.485 |
hene | -0.465 |
ringe | -0.453 |
Token | In |
Token ID | 818 |
Feature activation | -8.22e+00 |
Pos logit contributions | |
bid | +3.844 |
Stro | +3.790 |
drawn | +3.743 |
hene | +3.468 |
ringe | +3.375 |
Neg logit contributions | |
olars | -4.338 |
litter | -4.195 |
pont | -4.172 |
tons | -4.153 |
lations | -4.070 |
Token | Memory |
Token ID | 30871 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
tons | +3.389 |
olars | +3.352 |
lations | +3.222 |
Mis | +3.121 |
lear | +3.113 |
Neg logit contributions | |
bid | -7.457 |
Stro | -7.433 |
drawn | -7.145 |
ignt | -7.084 |
hene | -7.051 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
bid | +3.461 |
Stro | +3.430 |
drawn | +3.285 |
hene | +3.154 |
ringe | +3.014 |
Neg logit contributions | |
olars | -3.303 |
tons | -3.235 |
lear | -3.162 |
lations | -3.154 |
esta | -3.128 |
Token | 66 |
Token ID | 2791 |
Feature activation | +8.71e+00 |
Pos logit contributions | |
olars | +1.126 |
tons | +1.081 |
lations | +1.050 |
litter | +1.048 |
Soph | +1.035 |
Neg logit contributions | |
bid | -1.643 |
Stro | -1.592 |
drawn | -1.574 |
hene | -1.523 |
ringe | -1.492 |
Token | 284 |
Token ID | 30336 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
bid | +2.642 |
Stro | +2.415 |
drawn | +2.183 |
hene | +2.006 |
364 | +1.842 |
Neg logit contributions | |
olars | -9.227 |
pont | -9.107 |
litter | -9.030 |
lations | -8.936 |
lear | -8.863 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.93e+01 |
Pos logit contributions | |
olars | +1.758 |
tons | +1.709 |
litter | +1.665 |
Soph | +1.648 |
lations | +1.644 |
Neg logit contributions | |
bid | -2.715 |
Stro | -2.633 |
drawn | -2.614 |
hene | -2.548 |
ringe | -2.516 |
Token | 64 |
Token ID | 2414 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
364 | +4.482 |
Stro | +4.423 |
drawn | +4.399 |
bid | +4.317 |
inder | +3.323 |
Neg logit contributions | |
resil | -19.850 |
Palestin | -19.648 |
�� | -19.325 |
aution | -19.029 |
emort | -18.959 |
Token | 406 |
Token ID | 29703 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
drawn | +5.445 |
bid | +5.352 |
Stro | +5.094 |
364 | +5.023 |
inder | +4.748 |
Neg logit contributions | |
olars | -12.229 |
Soph | -11.973 |
litter | -11.921 |
pont | -11.758 |
resil | -11.725 |
Token | Mem |
Token ID | 4942 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
Soph | +2.912 |
tons | +2.902 |
olars | +2.812 |
mk | +2.777 |
litter | +2.776 |
Neg logit contributions | |
bid | -6.583 |
drawn | -6.307 |
ringe | -6.145 |
hene | -6.110 |
Stro | -6.050 |
Token | c |
Token ID | 66 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
bid | +5.759 |
drawn | +5.506 |
Stro | +5.159 |
hene | +4.735 |
ringe | +4.538 |
Neg logit contributions | |
olars | -9.613 |
�� | -9.577 |
resil | -9.534 |
pont | -9.491 |
BuyableInstoreAndOnline | -9.365 |
Token | py |
Token ID | 9078 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
bid | +2.521 |
drawn | +2.365 |
Stro | +2.315 |
hene | +2.132 |
ringe | +2.006 |
Neg logit contributions | |
olars | -5.027 |
litter | -4.890 |
pont | -4.854 |
Soph | -4.820 |
lations | -4.798 |
Token | : |
Token ID | 25 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
bid | +2.676 |
Stro | +2.628 |
drawn | +2.533 |
hene | +2.401 |
ringe | +2.311 |
Neg logit contributions | |
olars | -2.732 |
tons | -2.587 |
lations | -2.564 |
lear | -2.559 |
pont | -2.552 |
Token | Photograph |
Token ID | 18903 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
bid | +1.555 |
Stro | +1.532 |
drawn | +1.469 |
hene | +1.418 |
ringe | +1.356 |
Neg logit contributions | |
olars | -1.625 |
tons | -1.560 |
lear | -1.520 |
lations | -1.516 |
pont | -1.515 |
Token | s |
Token ID | 82 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
bid | +0.210 |
Stro | +0.206 |
drawn | +0.204 |
hene | +0.197 |
ringe | +0.194 |
Neg logit contributions | |
olars | -0.076 |
tons | -0.071 |
litter | -0.068 |
lations | -0.068 |
pont | -0.067 |
Token | of |
Token ID | 286 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
bid | +0.934 |
Stro | +0.910 |
drawn | +0.891 |
hene | +0.850 |
ringe | +0.824 |
Neg logit contributions | |
olars | -0.843 |
tons | -0.801 |
lations | -0.790 |
litter | -0.785 |
lear | -0.784 |
Token | Los |
Token ID | 5401 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
olars | +2.662 |
tons | +2.609 |
litter | +2.572 |
lations | +2.529 |
Soph | +2.500 |
Neg logit contributions | |
bid | -3.674 |
drawn | -3.533 |
Stro | -3.520 |
hene | -3.412 |
ringe | -3.369 |
Token | Angeles |
Token ID | 5652 |
Feature activation | +1.90e+01 |
Pos logit contributions | |
bid | +1.579 |
Stro | +1.553 |
drawn | +1.520 |
hene | +1.471 |
ringe | +1.431 |
Neg logit contributions | |
olars | -0.922 |
tons | -0.862 |
lations | -0.846 |
litter | -0.842 |
pont | -0.838 |
Token | 1980 |
Token ID | 7169 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
Stro | +5.868 |
bid | +5.525 |
inder | +4.264 |
drawn | +4.134 |
traces | +3.877 |
Neg logit contributions | |
olars | -18.107 |
lear | -17.844 |
pont | -17.677 |
�� | -17.524 |
lations | -17.300 |
Token | – |
Token ID | 1906 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
olars | +2.487 |
tons | +2.470 |
Soph | +2.391 |
litter | +2.369 |
lations | +2.364 |
Neg logit contributions | |
bid | -3.420 |
Stro | -3.333 |
drawn | -3.323 |
hene | -3.221 |
ringe | -3.202 |
Token | 84 |
Token ID | 5705 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
bid | +6.209 |
Stro | +5.588 |
drawn | +5.375 |
364 | +5.317 |
advertisement | +4.993 |
Neg logit contributions | |
olars | -9.002 |
pont | -8.628 |
emort | -8.590 |
litter | -8.560 |
lations | -8.491 |
Token | . |
Token ID | 13 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
bid | +1.686 |
Stro | +1.647 |
drawn | +1.599 |
hene | +1.528 |
ringe | +1.483 |
Neg logit contributions | |
olars | -1.654 |
tons | -1.582 |
lations | -1.556 |
lear | -1.551 |
litter | -1.547 |
Token | Copyright |
Token ID | 15069 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
bid | +1.579 |
Stro | +1.543 |
drawn | +1.464 |
hene | +1.363 |
ringe | +1.288 |
Neg logit contributions | |
olars | -2.863 |
tons | -2.753 |
lear | -2.720 |
lations | -2.717 |
esta | -2.712 |
Token | aged |
Token ID | 1886 |
Feature activation | +7.45e+00 |
Pos logit contributions | |
bid | +2.531 |
drawn | +2.438 |
Stro | +2.407 |
hene | +2.263 |
ringe | +2.223 |
Neg logit contributions | |
olars | -2.277 |
litter | -2.189 |
pont | -2.162 |
tons | -2.155 |
lations | -2.142 |
Token | Access |
Token ID | 8798 |
Feature activation | +9.11e+00 |
Pos logit contributions | |
Stro | +5.442 |
bid | +5.350 |
drawn | +5.032 |
hene | +4.706 |
inder | +4.574 |
Neg logit contributions | |
olars | -5.024 |
lations | -4.585 |
pont | -4.556 |
litter | -4.500 |
emort | -4.498 |
Token | Point |
Token ID | 6252 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
Stro | +6.643 |
bid | +6.424 |
drawn | +6.142 |
hene | +5.848 |
inder | +5.776 |
Neg logit contributions | |
olars | -6.076 |
lations | -5.566 |
esta | -5.516 |
resil | -5.447 |
litter | -5.385 |
Token | : |
Token ID | 25 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
bid | +2.590 |
Stro | +2.547 |
drawn | +2.466 |
hene | +2.320 |
ringe | +2.242 |
Neg logit contributions | |
olars | -2.702 |
pont | -2.535 |
lations | -2.530 |
tons | -2.527 |
litter | -2.521 |
Token | Not |
Token ID | 1892 |
Feature activation | +8.98e+00 |
Pos logit contributions | |
bid | +1.760 |
Stro | +1.759 |
drawn | +1.690 |
hene | +1.586 |
ringe | +1.547 |
Neg logit contributions | |
olars | -1.908 |
lations | -1.794 |
litter | -1.786 |
tons | -1.785 |
pont | -1.766 |
Token | - |
Token ID | 12 |
Feature activation | +1.90e+01 |
Pos logit contributions | |
Stro | +5.350 |
bid | +5.334 |
drawn | +5.124 |
hene | +4.627 |
inder | +4.424 |
Neg logit contributions | |
olars | -7.104 |
pont | -6.644 |
lations | -6.537 |
litter | -6.503 |
tons | -6.467 |
Token | Associated |
Token ID | 29014 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
drawn | +6.447 |
bid | +6.323 |
advertisement | +5.716 |
Stro | +5.144 |
364 | +4.938 |
Neg logit contributions | |
olars | -18.186 |
pont | -17.685 |
litter | -17.374 |
emort | -16.698 |
princ | -16.422 |
Token | T |
Token ID | 309 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
Stro | +5.930 |
bid | +5.559 |
drawn | +5.263 |
hene | +4.780 |
inder | +4.700 |
Neg logit contributions | |
olars | -7.989 |
esta | -7.366 |
lear | -7.361 |
lations | -7.286 |
pont | -7.260 |
Token | x |
Token ID | 87 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
olars | +0.417 |
tons | +0.405 |
lations | +0.390 |
lear | +0.385 |
litter | +0.384 |
Neg logit contributions | |
bid | -0.654 |
Stro | -0.642 |
drawn | -0.631 |
hene | -0.611 |
ringe | -0.598 |
Token | - |
Token ID | 12 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
bid | +3.235 |
Stro | +3.197 |
drawn | +3.070 |
hene | +2.893 |
ringe | +2.777 |
Neg logit contributions | |
olars | -3.633 |
esta | -3.380 |
litter | -3.374 |
pont | -3.368 |
lations | -3.359 |
Token | Power |
Token ID | 13434 |
Feature activation | +9.38e+00 |
Pos logit contributions | |
bid | +1.309 |
Stro | +1.281 |
drawn | +1.264 |
hene | +1.220 |
ringe | +1.197 |
Neg logit contributions | |
olars | -0.642 |
tons | -0.600 |
litter | -0.588 |
lations | -0.586 |
pont | -0.582 |
Token | : |
Token ID | 25 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
bid | +2.459 |
Stro | +2.403 |
drawn | +2.316 |
hene | +2.231 |
ringe | +2.140 |
Neg logit contributions | |
olars | -2.487 |
tons | -2.422 |
lear | -2.357 |
lations | -2.350 |
litter | -2.343 |
Token | Photograph |
Token ID | 18903 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
bid | +1.439 |
Stro | +1.418 |
drawn | +1.351 |
hene | +1.309 |
ringe | +1.239 |
Neg logit contributions | |
olars | -1.599 |
tons | -1.562 |
lear | -1.501 |
lations | -1.484 |
pont | -1.483 |
Token | s |
Token ID | 82 |
Feature activation | -7.41e-03 |
Pos logit contributions | |
bid | +2.046 |
Stro | +2.009 |
drawn | +1.976 |
hene | +1.907 |
ringe | +1.863 |
Neg logit contributions | |
olars | -0.811 |
tons | -0.743 |
pont | -0.725 |
lear | -0.724 |
litter | -0.720 |
Token | of |
Token ID | 286 |
Feature activation | -5.75e+00 |
Pos logit contributions | |
olars | +0.005 |
tons | +0.004 |
lations | +0.004 |
litter | +0.004 |
pont | +0.004 |
Neg logit contributions | |
bid | -0.006 |
Stro | -0.005 |
drawn | -0.005 |
hene | -0.005 |
ringe | -0.005 |
Token | Los |
Token ID | 5401 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
olars | +3.172 |
tons | +3.106 |
litter | +3.078 |
lations | +3.019 |
Soph | +2.992 |
Neg logit contributions | |
bid | -4.645 |
drawn | -4.486 |
Stro | -4.431 |
hene | -4.314 |
ringe | -4.283 |
Token | Angeles |
Token ID | 5652 |
Feature activation | +1.89e+01 |
Pos logit contributions | |
bid | +0.178 |
Stro | +0.174 |
drawn | +0.171 |
hene | +0.166 |
ringe | +0.162 |
Neg logit contributions | |
olars | -0.096 |
tons | -0.091 |
lations | -0.088 |
litter | -0.088 |
pont | -0.087 |
Token | 1980 |
Token ID | 7169 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
Stro | +7.286 |
bid | +7.157 |
traces | +6.012 |
hene | +5.995 |
inder | +5.915 |
Neg logit contributions | |
olars | -15.432 |
lear | -15.207 |
tons | -14.827 |
lations | -14.783 |
pont | -14.774 |
Token | – |
Token ID | 1906 |
Feature activation | +9.67e+00 |
Pos logit contributions | |
olars | +2.002 |
tons | +1.938 |
litter | +1.894 |
lations | +1.887 |
Soph | +1.879 |
Neg logit contributions | |
bid | -2.468 |
Stro | -2.409 |
drawn | -2.379 |
hene | -2.290 |
ringe | -2.247 |
Token | 84 |
Token ID | 5705 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
bid | +5.724 |
Stro | +5.209 |
drawn | +5.055 |
364 | +4.875 |
inder | +4.585 |
Neg logit contributions | |
olars | -7.597 |
pont | -7.270 |
litter | -7.223 |
lations | -7.212 |
emort | -7.195 |
Token | . |
Token ID | 13 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
bid | +1.212 |
Stro | +1.190 |
drawn | +1.152 |
hene | +1.108 |
ringe | +1.070 |
Neg logit contributions | |
olars | -1.178 |
tons | -1.151 |
esta | -1.112 |
lear | -1.110 |
lations | -1.107 |
Token | Copyright |
Token ID | 15069 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
bid | +1.837 |
Stro | +1.795 |
drawn | +1.702 |
hene | +1.557 |
ringe | +1.459 |
Neg logit contributions | |
olars | -3.546 |
tons | -3.473 |
esta | -3.381 |
lear | -3.379 |
lations | -3.357 |
Token | much |
Token ID | 881 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
olars | +0.950 |
tons | +0.915 |
lations | +0.898 |
litter | +0.894 |
lear | +0.890 |
Neg logit contributions | |
bid | -0.973 |
Stro | -0.949 |
drawn | -0.928 |
hene | -0.890 |
ringe | -0.867 |
Token | everybody |
Token ID | 7288 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Stro | +3.203 |
bid | +3.161 |
drawn | +3.025 |
hene | +2.897 |
ringe | +2.831 |
Neg logit contributions | |
olars | -3.124 |
lations | -2.987 |
lear | -2.977 |
esta | -2.969 |
tons | -2.955 |
Token | ? |
Token ID | 30 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
olars | +1.619 |
tons | +1.559 |
litter | +1.525 |
lations | +1.523 |
pont | +1.511 |
Neg logit contributions | |
bid | -1.957 |
Stro | -1.909 |
drawn | -1.880 |
hene | -1.805 |
ringe | -1.762 |
Token |
|
Token ID | 198 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
Stro | +1.507 |
bid | +1.503 |
drawn | +1.427 |
hene | +1.385 |
ringe | +1.342 |
Neg logit contributions | |
olars | -1.199 |
tons | -1.103 |
pont | -1.102 |
lear | -1.099 |
litter | -1.098 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
bid | +3.015 |
Stro | +2.951 |
drawn | +2.881 |
hene | +2.726 |
ringe | +2.636 |
Neg logit contributions | |
olars | -2.496 |
pont | -2.305 |
litter | -2.303 |
lations | -2.302 |
tons | -2.290 |
Token | Jay |
Token ID | 30568 |
Feature activation | +1.89e+01 |
Pos logit contributions | |
bid | +0.827 |
Stro | +0.797 |
drawn | +0.792 |
hene | +0.751 |
ringe | +0.737 |
Neg logit contributions | |
olars | -0.870 |
tons | -0.839 |
litter | -0.833 |
pont | -0.830 |
lations | -0.821 |
Token | C |
Token ID | 327 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
Stro | +6.826 |
bid | +5.314 |
drawn | +4.869 |
LCD | +4.279 |
hene | +4.061 |
Neg logit contributions | |
olars | -18.185 |
�� | -17.693 |
emort | -17.454 |
resil | -17.424 |
lear | -17.212 |
Token | z |
Token ID | 89 |
Feature activation | +8.33e+00 |
Pos logit contributions | |
olars | +1.595 |
tons | +1.546 |
lations | +1.463 |
esta | +1.431 |
lear | +1.393 |
Neg logit contributions | |
bid | -4.042 |
Stro | -4.008 |
drawn | -3.887 |
hene | -3.809 |
ringe | -3.732 |
Token | ark |
Token ID | 668 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
bid | +4.445 |
drawn | +4.108 |
Stro | +4.063 |
hene | +3.898 |
ringe | +3.894 |
Neg logit contributions | |
olars | -6.767 |
Soph | -6.734 |
pont | -6.730 |
litter | -6.696 |
tons | -6.671 |
Token | owski |
Token ID | 12079 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
bid | +0.532 |
Stro | +0.521 |
drawn | +0.514 |
hene | +0.498 |
ringe | +0.489 |
Neg logit contributions | |
olars | -0.231 |
tons | -0.218 |
litter | -0.211 |
lations | -0.211 |
pont | -0.208 |
Token | : |
Token ID | 25 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
bid | +2.171 |
Stro | +2.130 |
drawn | +2.059 |
hene | +1.964 |
ringe | +1.899 |
Neg logit contributions | |
olars | -2.203 |
tons | -2.077 |
lations | -2.065 |
litter | -2.061 |
pont | -2.059 |
Token | WITH |
Token ID | 13315 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
olars | +2.000 |
tons | +1.928 |
litter | +1.886 |
lations | +1.886 |
pont | +1.870 |
Neg logit contributions | |
bid | -2.537 |
Stro | -2.473 |
drawn | -2.429 |
hene | -2.337 |
ringe | -2.293 |
Token | THE |
Token ID | 3336 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
drawn | +4.641 |
bid | +4.636 |
Stro | +4.578 |
hene | +4.267 |
ringe | +4.041 |
Neg logit contributions | |
olars | -4.131 |
tons | -3.883 |
lations | -3.881 |
litter | -3.854 |
pont | -3.823 |
Token | BAT |
Token ID | 37421 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
bid | +2.250 |
Stro | +2.227 |
drawn | +2.179 |
hene | +2.047 |
ringe | +1.980 |
Neg logit contributions | |
olars | -2.202 |
tons | -2.098 |
lations | -2.073 |
esta | -2.045 |
litter | -2.034 |
Token | TER |
Token ID | 5781 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
Stro | +2.856 |
bid | +2.736 |
drawn | +2.681 |
hene | +2.438 |
ringe | +2.375 |
Neg logit contributions | |
olars | -5.318 |
tons | -4.991 |
esta | -4.933 |
lations | -4.931 |
pont | -4.897 |
Token | Y |
Token ID | 56 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
olars | +0.295 |
tons | +0.282 |
lations | +0.274 |
litter | +0.274 |
pont | +0.271 |
Neg logit contributions | |
bid | -0.467 |
Stro | -0.457 |
drawn | -0.450 |
hene | -0.435 |
ringe | -0.425 |
Token | BACK |
Token ID | 28767 |
Feature activation | +1.87e+01 |
Pos logit contributions | |
Stro | +4.082 |
bid | +4.009 |
drawn | +3.880 |
hene | +3.636 |
ringe | +3.432 |
Neg logit contributions | |
olars | -5.117 |
esta | -4.772 |
lations | -4.753 |
pont | -4.731 |
lear | -4.713 |
Token | ED |
Token ID | 1961 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
Stro | +6.629 |
drawn | +6.449 |
bid | +6.255 |
ID | +5.697 |
LCD | +5.541 |
Neg logit contributions | |
olars | -16.777 |
emort | -15.097 |
lear | -15.006 |
esta | -14.966 |
pont | -14.947 |
Token | D |
Token ID | 360 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
bid | +3.423 |
Stro | +3.402 |
drawn | +3.295 |
hene | +3.072 |
ringe | +2.898 |
Neg logit contributions | |
olars | -5.141 |
lations | -4.847 |
esta | -4.815 |
tons | -4.742 |
esm | -4.724 |
Token | OCK |
Token ID | 11290 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
bid | +2.179 |
Stro | +2.118 |
drawn | +2.086 |
hene | +2.011 |
ringe | +1.972 |
Neg logit contributions | |
olars | -1.587 |
tons | -1.518 |
lations | -1.483 |
litter | -1.480 |
pont | -1.473 |
Token | , |
Token ID | 11 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
olars | +0.202 |
tons | +0.192 |
lations | +0.189 |
litter | +0.188 |
pont | +0.187 |
Neg logit contributions | |
bid | -0.214 |
Stro | -0.211 |
drawn | -0.206 |
hene | -0.197 |
ringe | -0.191 |
Token | IT |
Token ID | 7283 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
olars | +0.093 |
tons | +0.088 |
lations | +0.087 |
litter | +0.086 |
lear | +0.086 |
Neg logit contributions | |
bid | -0.107 |
Stro | -0.106 |
drawn | -0.103 |
hene | -0.099 |
ringe | -0.095 |
Token | E |
Token ID | 36 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
bid | +2.429 |
Stro | +2.386 |
drawn | +2.307 |
hene | +2.219 |
ringe | +2.127 |
Neg logit contributions | |
olars | -2.373 |
tons | -2.265 |
pont | -2.219 |
lations | -2.214 |
lear | -2.212 |
Token | ER |
Token ID | 1137 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
bid | +3.121 |
Stro | +3.082 |
drawn | +2.969 |
hene | +2.875 |
ringe | +2.700 |
Neg logit contributions | |
olars | -2.828 |
tons | -2.661 |
litter | -2.583 |
pont | -2.576 |
lations | -2.568 |
Token | T |
Token ID | 309 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
bid | +2.155 |
Stro | +2.118 |
drawn | +2.060 |
hene | +1.971 |
ringe | +1.883 |
Neg logit contributions | |
olars | -1.953 |
tons | -1.827 |
lations | -1.796 |
litter | -1.791 |
lear | -1.774 |
Token | OC |
Token ID | 4503 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
bid | +3.442 |
Stro | +3.371 |
drawn | +3.271 |
hene | +3.103 |
ringe | +3.003 |
Neg logit contributions | |
olars | -3.006 |
tons | -2.945 |
lations | -2.828 |
lear | -2.813 |
Soph | -2.800 |
Token | AK |
Token ID | 15837 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
bid | +4.008 |
Stro | +3.999 |
drawn | +3.866 |
hene | +3.651 |
inder | +3.446 |
Neg logit contributions | |
olars | -3.838 |
tons | -3.544 |
lations | -3.444 |
esta | -3.426 |
litter | -3.410 |
Token | NOW |
Token ID | 45669 |
Feature activation | +1.83e+01 |
Pos logit contributions | |
bid | +2.107 |
Stro | +2.057 |
drawn | +2.021 |
hene | +1.878 |
ringe | +1.786 |
Neg logit contributions | |
olars | -2.938 |
tons | -2.800 |
lations | -2.749 |
litter | -2.748 |
pont | -2.740 |
Token | LED |
Token ID | 30465 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
bid | +4.398 |
drawn | +4.396 |
Stro | +3.972 |
inder | +3.516 |
ID | +3.479 |
Neg logit contributions | |
olars | -18.690 |
esta | -18.091 |
pont | -17.912 |
emort | -17.838 |
resil | -17.827 |
Token | G |
Token ID | 38 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
bid | +1.087 |
Stro | +1.064 |
drawn | +1.047 |
hene | +1.005 |
ringe | +0.980 |
Neg logit contributions | |
olars | -0.825 |
tons | -0.783 |
litter | -0.768 |
lations | -0.768 |
pont | -0.763 |
Token | ED |
Token ID | 1961 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
bid | +2.770 |
drawn | +2.728 |
Stro | +2.624 |
hene | +2.008 |
inder | +1.832 |
Neg logit contributions | |
olars | -14.220 |
litter | -13.575 |
pont | -13.417 |
emort | -13.239 |
tons | -13.219 |
Token | NET |
Token ID | 30502 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
bid | +2.833 |
Stro | +2.789 |
drawn | +2.693 |
hene | +2.564 |
ringe | +2.439 |
Neg logit contributions | |
olars | -2.898 |
tons | -2.715 |
lations | -2.663 |
esta | -2.663 |
litter | -2.640 |
Token | CALL |
Token ID | 42815 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
bid | +2.184 |
Stro | +2.160 |
drawn | +2.060 |
hene | +1.933 |
ringe | +1.851 |
Neg logit contributions | |
olars | -2.718 |
tons | -2.553 |
esta | -2.515 |
lations | -2.508 |
pont | -2.492 |
Token | 1980 |
Token ID | 7169 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
Stro | +4.879 |
bid | +4.763 |
drawn | +4.524 |
hene | +4.471 |
idding | +4.177 |
Neg logit contributions | |
olars | -4.634 |
tons | -4.402 |
lations | -4.375 |
lear | -4.353 |
esta | -4.181 |
Token | – |
Token ID | 1906 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
olars | +3.096 |
tons | +2.974 |
litter | +2.921 |
lations | +2.900 |
Soph | +2.885 |
Neg logit contributions | |
bid | -4.049 |
Stro | -3.940 |
drawn | -3.885 |
hene | -3.751 |
ringe | -3.668 |
Token | 84 |
Token ID | 5705 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
olars | +0.035 |
tons | +0.034 |
lations | +0.033 |
litter | +0.033 |
pont | +0.033 |
Neg logit contributions | |
bid | -0.028 |
Stro | -0.027 |
drawn | -0.027 |
hene | -0.025 |
ringe | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
bid | +0.813 |
Stro | +0.802 |
drawn | +0.777 |
hene | +0.748 |
ringe | +0.727 |
Neg logit contributions | |
olars | -0.710 |
tons | -0.686 |
lations | -0.669 |
lear | -0.667 |
esta | -0.662 |
Token | Copyright |
Token ID | 15069 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
Stro | +4.859 |
bid | +4.806 |
drawn | +4.571 |
hene | +4.318 |
inder | +4.135 |
Neg logit contributions | |
olars | -4.096 |
tons | -3.946 |
lear | -3.806 |
lations | -3.783 |
litter | -3.769 |
Token | John |
Token ID | 1757 |
Feature activation | +1.81e+01 |
Pos logit contributions | |
bid | +3.866 |
Stro | +3.821 |
drawn | +3.647 |
hene | +3.413 |
ringe | +3.330 |
Neg logit contributions | |
olars | -4.474 |
tons | -4.381 |
lear | -4.225 |
lations | -4.164 |
esta | -4.144 |
Token | Brian |
Token ID | 8403 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
bid | +10.684 |
Stro | +10.155 |
drawn | +9.242 |
hene | +8.820 |
inder | +8.530 |
Neg logit contributions | |
olars | -11.566 |
esta | -11.239 |
resil | -11.131 |
tons | -10.917 |
esm | -10.762 |
Token | King |
Token ID | 2677 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
olars | +0.770 |
tons | +0.725 |
lations | +0.699 |
litter | +0.699 |
lear | +0.691 |
Neg logit contributions | |
bid | -1.631 |
Stro | -1.603 |
drawn | -1.575 |
hene | -1.526 |
ringe | -1.497 |
Token |
|
Token ID | 198 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
olars | +3.624 |
tons | +3.473 |
litter | +3.413 |
lations | +3.406 |
Soph | +3.387 |
Neg logit contributions | |
bid | -4.411 |
Stro | -4.303 |
drawn | -4.238 |
hene | -4.074 |
ringe | -3.996 |
Token |
|
Token ID | 198 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
bid | +3.245 |
Stro | +3.154 |
drawn | +3.110 |
hene | +2.915 |
ringe | +2.836 |
Neg logit contributions | |
olars | -2.639 |
litter | -2.470 |
pont | -2.466 |
tons | -2.450 |
lations | -2.416 |
Token | John |
Token ID | 7554 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
bid | +2.681 |
drawn | +2.561 |
Stro | +2.526 |
hene | +2.373 |
ringe | +2.315 |
Neg logit contributions | |
olars | -2.424 |
litter | -2.328 |
pont | -2.321 |
tons | -2.299 |
Soph | -2.287 |
Token | AP |
Token ID | 3486 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
olars | +2.302 |
tons | +2.219 |
litter | +2.174 |
lations | +2.162 |
pont | +2.156 |
Neg logit contributions | |
bid | -2.685 |
Stro | -2.616 |
drawn | -2.578 |
hene | -2.488 |
ringe | -2.413 |
Token | CO |
Token ID | 8220 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
bid | +0.809 |
Stro | +0.796 |
drawn | +0.772 |
hene | +0.744 |
ringe | +0.728 |
Neg logit contributions | |
olars | -0.661 |
tons | -0.636 |
lations | -0.624 |
litter | -0.622 |
pont | -0.612 |
Token | Worldwide |
Token ID | 33140 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
bid | +1.565 |
Stro | +1.516 |
drawn | +1.465 |
hene | +1.418 |
ringe | +1.375 |
Neg logit contributions | |
olars | -1.470 |
tons | -1.419 |
lations | -1.393 |
pont | -1.378 |
litter | -1.376 |
Token | , |
Token ID | 11 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
bid | +0.097 |
Stro | +0.094 |
drawn | +0.092 |
hene | +0.089 |
ringe | +0.086 |
Neg logit contributions | |
olars | -0.089 |
tons | -0.086 |
lations | -0.084 |
litter | -0.084 |
lear | -0.083 |
Token | a |
Token ID | 257 |
Feature activation | +6.04e+00 |
Pos logit contributions | |
bid | +1.724 |
Stro | +1.688 |
drawn | +1.637 |
hene | +1.562 |
ringe | +1.518 |
Neg logit contributions | |
olars | -1.553 |
tons | -1.491 |
lations | -1.460 |
lear | -1.442 |
litter | -1.429 |
Token | Washington |
Token ID | 2669 |
Feature activation | +1.81e+01 |
Pos logit contributions | |
bid | +4.190 |
Stro | +4.139 |
drawn | +3.851 |
hene | +3.734 |
ringe | +3.610 |
Neg logit contributions | |
olars | -4.220 |
tons | -4.020 |
lations | -4.002 |
lear | -3.913 |
esta | -3.800 |
Token | influence |
Token ID | 4588 |
Feature activation | +7.73e+00 |
Pos logit contributions | |
bid | +9.950 |
Stro | +9.707 |
hene | +9.261 |
drawn | +8.727 |
ignt | +8.524 |
Neg logit contributions | |
olars | -12.500 |
lations | -11.711 |
tons | -11.502 |
emort | -11.482 |
lear | -11.310 |
Token | firm |
Token ID | 4081 |
Feature activation | +7.73e+00 |
Pos logit contributions | |
bid | +4.725 |
Stro | +4.448 |
drawn | +4.265 |
hene | +3.990 |
ringe | +3.871 |
Neg logit contributions | |
olars | -6.074 |
tons | -5.673 |
lations | -5.647 |
lear | -5.514 |
esm | -5.440 |
Token | with |
Token ID | 351 |
Feature activation | +7.11e+00 |
Pos logit contributions | |
bid | +4.951 |
Stro | +4.755 |
drawn | +4.561 |
hene | +4.342 |
inder | +4.187 |
Neg logit contributions | |
olars | -5.610 |
tons | -5.307 |
lations | -5.207 |
lear | -5.194 |
esm | -5.163 |
Token | a |
Token ID | 257 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
bid | +4.615 |
Stro | +4.512 |
drawn | +4.473 |
hene | +3.945 |
traces | +3.875 |
Neg logit contributions | |
olars | -5.141 |
lear | -4.902 |
lations | -4.894 |
tons | -4.813 |
esm | -4.773 |
Token | long |
Token ID | 890 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
bid | +2.438 |
Stro | +2.395 |
drawn | +2.323 |
hene | +2.209 |
ringe | +2.119 |
Neg logit contributions | |
olars | -2.216 |
lations | -2.151 |
tons | -2.146 |
lear | -2.100 |
esta | -2.033 |
Token | an |
Token ID | 281 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
bid | +0.328 |
Stro | +0.319 |
drawn | +0.314 |
hene | +0.299 |
ringe | +0.291 |
Neg logit contributions | |
olars | -0.297 |
tons | -0.283 |
lations | -0.281 |
litter | -0.275 |
lear | -0.275 |
Token | interest |
Token ID | 1393 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
olars | +3.932 |
tons | +3.787 |
esta | +3.762 |
litter | +3.748 |
Soph | +3.709 |
Neg logit contributions | |
bid | -4.657 |
Stro | -4.575 |
drawn | -4.472 |
hene | -4.304 |
ringe | -4.196 |
Token | in |
Token ID | 287 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
olars | +0.315 |
tons | +0.305 |
lations | +0.299 |
litter | +0.298 |
pont | +0.296 |
Neg logit contributions | |
bid | -0.275 |
Stro | -0.268 |
drawn | -0.262 |
hene | -0.250 |
ringe | -0.243 |
Token | keeping |
Token ID | 5291 |
Feature activation | +9.21e+00 |
Pos logit contributions | |
olars | +1.045 |
tons | +1.003 |
lations | +0.981 |
litter | +0.977 |
pont | +0.969 |
Neg logit contributions | |
bid | -1.322 |
Stro | -1.291 |
drawn | -1.267 |
hene | -1.219 |
ringe | -1.191 |
Token | whistleblower |
Token ID | 34875 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
bid | +5.980 |
Stro | +5.905 |
drawn | +5.525 |
hene | +5.227 |
ringe | +5.215 |
Neg logit contributions | |
olars | -6.438 |
lations | -6.031 |
lear | -5.943 |
tons | -5.923 |
esm | -5.888 |
Token | information |
Token ID | 1321 |
Feature activation | +1.81e+01 |
Pos logit contributions | |
bid | +6.347 |
Stro | +6.237 |
drawn | +5.855 |
hene | +5.549 |
traces | +5.544 |
Neg logit contributions | |
olars | -8.891 |
lear | -8.396 |
tons | -8.389 |
esm | -8.353 |
�� | -8.290 |
Token | secret |
Token ID | 3200 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
bid | +9.697 |
Stro | +9.354 |
drawn | +8.755 |
hene | +8.642 |
traces | +8.447 |
Neg logit contributions | |
olars | -12.387 |
lear | -11.652 |
esm | -11.555 |
lations | -11.458 |
tons | -11.357 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
bid | +7.159 |
Stro | +6.768 |
drawn | +6.735 |
hene | +6.527 |
ringe | +6.180 |
Neg logit contributions | |
olars | -8.667 |
tons | -8.418 |
lear | -8.155 |
lations | -8.108 |
esm | -7.961 |
Token | However |
Token ID | 2102 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
bid | +0.082 |
Stro | +0.081 |
drawn | +0.078 |
hene | +0.076 |
ringe | +0.074 |
Neg logit contributions | |
olars | -0.058 |
tons | -0.054 |
lations | -0.054 |
litter | -0.053 |
lear | -0.053 |
Token | that |
Token ID | 326 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
olars | +0.625 |
tons | +0.600 |
lations | +0.590 |
litter | +0.587 |
lear | +0.584 |
Neg logit contributions | |
bid | -0.670 |
Stro | -0.652 |
drawn | -0.639 |
hene | -0.613 |
ringe | -0.598 |
Token | interest |
Token ID | 1393 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
olars | +3.487 |
tons | +3.437 |
litter | +3.353 |
pont | +3.345 |
Soph | +3.308 |
Neg logit contributions | |
bid | -5.054 |
Stro | -4.958 |
drawn | -4.945 |
hene | -4.757 |
ringe | -4.616 |
Token | AC |
Token ID | 2246 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
olars | +1.150 |
tons | +1.110 |
lations | +1.087 |
litter | +1.086 |
pont | +1.078 |
Neg logit contributions | |
bid | -1.171 |
Stro | -1.140 |
drawn | -1.117 |
hene | -1.071 |
ringe | -1.042 |
Token | HE |
Token ID | 13909 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
olars | +0.268 |
tons | +0.257 |
lations | +0.249 |
litter | +0.249 |
pont | +0.246 |
Neg logit contributions | |
bid | -0.352 |
Stro | -0.346 |
drawn | -0.338 |
hene | -0.327 |
ringe | -0.317 |
Token | T |
Token ID | 309 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
bid | +2.052 |
Stro | +2.019 |
drawn | +1.954 |
hene | +1.892 |
ringe | +1.798 |
Neg logit contributions | |
olars | -1.845 |
tons | -1.720 |
lations | -1.683 |
litter | -1.680 |
pont | -1.678 |
Token | OC |
Token ID | 4503 |
Feature activation | +5.86e+00 |
Pos logit contributions | |
bid | +2.741 |
Stro | +2.685 |
drawn | +2.603 |
hene | +2.470 |
ringe | +2.389 |
Neg logit contributions | |
olars | -2.362 |
tons | -2.306 |
lear | -2.217 |
lations | -2.213 |
litter | -2.210 |
Token | AK |
Token ID | 15837 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
bid | +4.051 |
Stro | +4.041 |
drawn | +3.898 |
hene | +3.693 |
ringe | +3.467 |
Neg logit contributions | |
olars | -4.099 |
tons | -3.794 |
lations | -3.674 |
esta | -3.667 |
litter | -3.632 |
Token | NOW |
Token ID | 45669 |
Feature activation | +1.80e+01 |
Pos logit contributions | |
bid | +1.920 |
Stro | +1.868 |
drawn | +1.834 |
hene | +1.717 |
ringe | +1.633 |
Neg logit contributions | |
olars | -2.589 |
tons | -2.471 |
litter | -2.434 |
lations | -2.428 |
pont | -2.427 |
Token | LED |
Token ID | 30465 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
bid | +4.593 |
drawn | +4.505 |
Stro | +4.054 |
inder | +3.682 |
hene | +3.678 |
Neg logit contributions | |
olars | -18.239 |
esta | -17.668 |
pont | -17.567 |
resil | -17.406 |
emort | -17.384 |
Token | G |
Token ID | 38 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
bid | +0.457 |
Stro | +0.447 |
drawn | +0.439 |
hene | +0.423 |
ringe | +0.414 |
Neg logit contributions | |
olars | -0.329 |
tons | -0.315 |
lations | -0.307 |
litter | -0.307 |
pont | -0.304 |
Token | ED |
Token ID | 1961 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
bid | +2.733 |
drawn | +2.651 |
Stro | +2.598 |
hene | +2.000 |
inder | +1.788 |
Neg logit contributions | |
olars | -13.459 |
litter | -12.871 |
pont | -12.735 |
emort | -12.555 |
tons | -12.553 |
Token | NET |
Token ID | 30502 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
bid | +2.015 |
Stro | +1.982 |
drawn | +1.923 |
hene | +1.829 |
ringe | +1.747 |
Neg logit contributions | |
olars | -2.123 |
tons | -2.002 |
lations | -1.958 |
esta | -1.955 |
litter | -1.946 |
Token | CALL |
Token ID | 42815 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
bid | +1.980 |
Stro | +1.954 |
drawn | +1.870 |
hene | +1.758 |
ringe | +1.687 |
Neg logit contributions | |
olars | -2.420 |
tons | -2.278 |
esta | -2.243 |
lations | -2.237 |
litter | -2.226 |
Token | introduced |
Token ID | 5495 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
olars | +0.632 |
tons | +0.608 |
lations | +0.596 |
litter | +0.595 |
pont | +0.590 |
Neg logit contributions | |
bid | -0.701 |
Stro | -0.683 |
drawn | -0.670 |
hene | -0.643 |
ringe | -0.627 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
bid | +0.034 |
Stro | +0.034 |
drawn | +0.033 |
hene | +0.031 |
ringe | +0.030 |
Neg logit contributions | |
olars | -0.029 |
tons | -0.028 |
lations | -0.027 |
lear | -0.027 |
litter | -0.027 |
Token | Motor |
Token ID | 12533 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
olars | +0.895 |
tons | +0.860 |
lations | +0.841 |
litter | +0.838 |
pont | +0.832 |
Neg logit contributions | |
bid | -1.060 |
Stro | -1.036 |
drawn | -1.015 |
hene | -0.974 |
ringe | -0.952 |
Token | Vehicle |
Token ID | 21501 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
bid | +1.020 |
Stro | +1.001 |
drawn | +0.982 |
hene | +0.939 |
ringe | +0.926 |
Neg logit contributions | |
olars | -0.590 |
tons | -0.561 |
lations | -0.543 |
pont | -0.539 |
litter | -0.537 |
Token | ( |
Token ID | 357 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Stro | +4.303 |
bid | +4.288 |
drawn | +4.092 |
hene | +3.843 |
ringe | +3.805 |
Neg logit contributions | |
olars | -4.089 |
tons | -3.878 |
lations | -3.832 |
lear | -3.807 |
pont | -3.798 |
Token | Am |
Token ID | 5840 |
Feature activation | +1.79e+01 |
Pos logit contributions | |
bid | +0.933 |
Stro | +0.906 |
drawn | +0.904 |
hene | +0.855 |
ringe | +0.846 |
Neg logit contributions | |
olars | -0.496 |
tons | -0.458 |
lations | -0.451 |
litter | -0.450 |
pont | -0.450 |
Token | endment |
Token ID | 5904 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
bid | +6.300 |
Stro | +5.767 |
inder | +5.533 |
drawn | +5.084 |
ringe | +4.917 |
Neg logit contributions | |
olars | -16.300 |
tons | -16.061 |
�� | -15.843 |
resil | -15.755 |
lear | -15.404 |
Token | ) |
Token ID | 8 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
bid | +2.202 |
Stro | +2.166 |
drawn | +2.120 |
hene | +2.039 |
ringe | +1.993 |
Neg logit contributions | |
olars | -1.619 |
tons | -1.528 |
lear | -1.502 |
lations | -1.492 |
pont | -1.490 |
Token | Bill |
Token ID | 3941 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
bid | +0.914 |
Stro | +0.899 |
drawn | +0.860 |
hene | +0.813 |
ringe | +0.792 |
Neg logit contributions | |
olars | -1.298 |
tons | -1.248 |
lear | -1.226 |
lations | -1.222 |
pont | -1.219 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
bid | +3.883 |
Stro | +3.756 |
drawn | +3.686 |
hene | +3.494 |
ringe | +3.403 |
Neg logit contributions | |
olars | -3.534 |
tons | -3.364 |
lear | -3.261 |
pont | -3.253 |
lations | -3.243 |
Token | for |
Token ID | 329 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
bid | +1.662 |
Stro | +1.617 |
drawn | +1.597 |
hene | +1.523 |
ringe | +1.469 |
Neg logit contributions | |
olars | -1.645 |
tons | -1.598 |
lear | -1.541 |
lations | -1.539 |
pont | -1.531 |
Token | � |
Token ID | 447 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
bid | +2.267 |
Stro | +2.266 |
drawn | +2.152 |
hene | +2.084 |
ringe | +2.004 |
Neg logit contributions | |
olars | -1.777 |
tons | -1.667 |
lear | -1.629 |
esta | -1.616 |
litter | -1.611 |
Token | � |
Token ID | 251 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
bid | +1.488 |
Stro | +1.455 |
drawn | +1.426 |
hene | +1.375 |
ringe | +1.352 |
Neg logit contributions | |
olars | -0.851 |
tons | -0.809 |
litter | -0.787 |
lear | -0.778 |
lations | -0.777 |
Token | Currently |
Token ID | 16888 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
bid | +0.881 |
Stro | +0.876 |
drawn | +0.840 |
hene | +0.813 |
ringe | +0.786 |
Neg logit contributions | |
olars | -0.677 |
tons | -0.632 |
lear | -0.617 |
esta | -0.615 |
lations | -0.615 |
Token | So |
Token ID | 1406 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
bid | +0.625 |
Stro | +0.621 |
drawn | +0.602 |
hene | +0.576 |
ringe | +0.553 |
Neg logit contributions | |
olars | -0.589 |
tons | -0.561 |
lations | -0.549 |
esta | -0.545 |
lear | -0.543 |
Token | i |
Token ID | 72 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
olars | +1.370 |
tons | +1.328 |
lations | +1.306 |
litter | +1.304 |
pont | +1.296 |
Neg logit contributions | |
bid | -0.977 |
Stro | -0.946 |
drawn | -0.923 |
hene | -0.876 |
ringe | -0.847 |
Token | F |
Token ID | 376 |
Feature activation | -2.20e+01 |
Pos logit contributions | |
olars | +1.738 |
tons | +1.668 |
litter | +1.633 |
lations | +1.633 |
pont | +1.617 |
Neg logit contributions | |
bid | -2.178 |
Stro | -2.121 |
drawn | -2.089 |
hene | -2.006 |
ringe | -1.964 |
Token | on |
Token ID | 261 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
esta | +8.559 |
olars | +7.978 |
lear | +7.694 |
esm | +7.657 |
olia | +7.653 |
Neg logit contributions | |
Stro | -16.987 |
drawn | -16.612 |
bid | -16.542 |
aditional | -16.023 |
ÍÍ | -15.973 |
Token | held |
Token ID | 2714 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
olars | +3.261 |
tons | +3.125 |
litter | +3.099 |
lations | +3.076 |
pont | +3.052 |
Neg logit contributions | |
bid | -3.708 |
Stro | -3.576 |
drawn | -3.553 |
hene | -3.394 |
ringe | -3.343 |
Token | both |
Token ID | 1111 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
olars | +4.197 |
tons | +4.111 |
litter | +4.095 |
pont | +4.078 |
Soph | +4.025 |
Neg logit contributions | |
bid | -5.993 |
Stro | -5.674 |
drawn | -5.625 |
hene | -5.488 |
ringe | -5.392 |
Token | positions |
Token ID | 6116 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
bid | +0.019 |
Stro | +0.019 |
drawn | +0.018 |
hene | +0.018 |
ringe | +0.017 |
Neg logit contributions | |
olars | -0.014 |
tons | -0.014 |
lations | -0.013 |
lear | -0.013 |
litter | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
olars | +1.345 |
tons | +1.295 |
lations | +1.265 |
litter | +1.263 |
lear | +1.254 |
Neg logit contributions | |
bid | -1.493 |
Stro | -1.456 |
drawn | -1.428 |
hene | -1.370 |
ringe | -1.334 |
Token | one |
Token ID | 530 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
olars | +1.611 |
tons | +1.551 |
lations | +1.518 |
litter | +1.514 |
pont | +1.502 |
Neg logit contributions | |
bid | -1.820 |
Stro | -1.775 |
drawn | -1.741 |
hene | -1.672 |
ringe | -1.630 |
Token | of |
Token ID | 286 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
bid | +3.624 |
Stro | +3.517 |
drawn | +3.393 |
hene | +3.254 |
ringe | +3.185 |
Neg logit contributions | |
olars | -3.753 |
lations | -3.571 |
tons | -3.532 |
esta | -3.514 |
lear | -3.451 |
Token | the |
Token ID | 262 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
bid | +2.258 |
Stro | +2.216 |
drawn | +2.157 |
hene | +2.047 |
ringe | +2.002 |
Neg logit contributions | |
olars | -2.047 |
tons | -1.957 |
lear | -1.943 |
lations | -1.922 |
esta | -1.902 |
Token | more |
Token ID | 517 |
Feature activation | -8.51e+00 |
Pos logit contributions | |
olars | +0.603 |
tons | +0.581 |
lations | +0.571 |
litter | +0.568 |
lear | +0.565 |
Neg logit contributions | |
bid | -0.596 |
Stro | -0.581 |
drawn | -0.569 |
hene | -0.544 |
ringe | -0.530 |
Token | popular |
Token ID | 2968 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
olars | +5.246 |
tons | +5.220 |
litter | +5.197 |
pont | +5.196 |
Soph | +5.047 |
Neg logit contributions | |
bid | -6.218 |
Stro | -5.994 |
drawn | -5.916 |
hene | -5.619 |
ringe | -5.489 |
Token | prime |
Token ID | 6994 |
Feature activation | -2.15e+01 |
Pos logit contributions | |
olars | +1.856 |
tons | +1.796 |
litter | +1.759 |
lations | +1.751 |
pont | +1.749 |
Neg logit contributions | |
bid | -2.000 |
Stro | -1.947 |
drawn | -1.917 |
hene | -1.839 |
ringe | -1.794 |
Token | ministers |
Token ID | 14138 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
pont | +5.887 |
tons | +5.768 |
litter | +5.286 |
olars | +4.961 |
mk | +4.925 |
Neg logit contributions | |
bid | -20.044 |
drawn | -19.988 |
Stro | -19.675 |
ringe | -18.942 |
hene | -18.879 |
Token | we |
Token ID | 356 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
bid | +0.064 |
Stro | +0.062 |
drawn | +0.060 |
hene | +0.057 |
ringe | +0.056 |
Neg logit contributions | |
olars | -0.067 |
tons | -0.064 |
lations | -0.063 |
lear | -0.063 |
esta | -0.062 |
Token | have |
Token ID | 423 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
bid | +2.593 |
Stro | +2.455 |
drawn | +2.401 |
hene | +2.346 |
ringe | +2.288 |
Neg logit contributions | |
olars | -2.345 |
tons | -2.260 |
lations | -2.225 |
esm | -2.182 |
Soph | -2.174 |
Token | ever |
Token ID | 1683 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
bid | +0.980 |
Stro | +0.944 |
drawn | +0.924 |
hene | +0.887 |
ringe | +0.852 |
Neg logit contributions | |
olars | -0.993 |
tons | -0.957 |
lations | -0.940 |
esta | -0.924 |
lear | -0.924 |
Token | had |
Token ID | 550 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
olars | +1.604 |
tons | +1.550 |
litter | +1.519 |
lations | +1.518 |
pont | +1.509 |
Neg logit contributions | |
bid | -1.581 |
Stro | -1.541 |
drawn | -1.508 |
hene | -1.443 |
ringe | -1.406 |
Token | fades |
Token ID | 41381 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
bid | +2.292 |
Stro | +2.277 |
drawn | +2.172 |
hene | +2.092 |
ringe | +2.031 |
Neg logit contributions | |
olars | -2.193 |
lations | -2.066 |
lear | -2.063 |
tons | -2.053 |
esta | -2.006 |
Token | . |
Token ID | 13 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
olars | +2.428 |
tons | +2.351 |
litter | +2.329 |
lations | +2.297 |
pont | +2.292 |
Neg logit contributions | |
bid | -2.868 |
Stro | -2.790 |
drawn | -2.731 |
hene | -2.642 |
ringe | -2.594 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
olars | +1.854 |
tons | +1.793 |
Soph | +1.753 |
lations | +1.742 |
litter | +1.742 |
Neg logit contributions | |
bid | -2.564 |
Stro | -2.484 |
drawn | -2.462 |
hene | -2.374 |
ringe | -2.329 |
Token |
|
Token ID | 198 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
olars | +0.524 |
tons | +0.507 |
lations | +0.489 |
litter | +0.488 |
Soph | +0.483 |
Neg logit contributions | |
bid | -0.869 |
Stro | -0.851 |
drawn | -0.836 |
hene | -0.813 |
ringe | -0.796 |
Token | R |
Token ID | 49 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
olars | +0.610 |
tons | +0.588 |
litter | +0.575 |
lations | +0.575 |
pont | +0.572 |
Neg logit contributions | |
bid | -0.675 |
Stro | -0.655 |
drawn | -0.646 |
hene | -0.617 |
ringe | -0.603 |
Token | ANK |
Token ID | 15154 |
Feature activation | -2.12e+01 |
Pos logit contributions | |
bid | +4.325 |
Stro | +3.928 |
drawn | +3.845 |
hene | +3.719 |
ringe | +3.653 |
Neg logit contributions | |
tons | -5.222 |
olars | -5.193 |
litter | -5.119 |
lations | -5.071 |
pont | -5.068 |
Token | 5 |
Token ID | 642 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
mk | +4.195 |
Soph | +4.173 |
Mk | +3.879 |
Ys | +3.644 |
tons | +3.606 |
Neg logit contributions | |
ignt | -20.675 |
quartered | -20.397 |
ringe | -20.129 |
bid | -20.023 |
aditional | -19.814 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
olars | +2.369 |
tons | +2.286 |
litter | +2.255 |
Soph | +2.252 |
lations | +2.234 |
Neg logit contributions | |
bid | -2.608 |
Stro | -2.522 |
drawn | -2.489 |
hene | -2.398 |
ringe | -2.345 |
Token | Smith |
Token ID | 4176 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
bid | +0.255 |
Stro | +0.250 |
drawn | +0.242 |
hene | +0.236 |
ringe | +0.231 |
Neg logit contributions | |
olars | -0.172 |
tons | -0.164 |
lations | -0.163 |
pont | -0.162 |
litter | -0.159 |
Token | , |
Token ID | 11 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
olars | +2.792 |
tons | +2.741 |
Soph | +2.696 |
litter | +2.665 |
pont | +2.626 |
Neg logit contributions | |
bid | -3.777 |
Stro | -3.658 |
drawn | -3.625 |
hene | -3.472 |
ringe | -3.415 |
Token | Ravens |
Token ID | 20091 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
olars | +2.215 |
tons | +2.119 |
litter | +2.079 |
Soph | +2.071 |
pont | +2.061 |
Neg logit contributions | |
bid | -3.105 |
Stro | -3.003 |
drawn | -2.978 |
hene | -2.881 |
ringe | -2.826 |
Token | ! |
Token ID | 0 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
bid | +1.444 |
Stro | +1.422 |
drawn | +1.381 |
hene | +1.317 |
ringe | +1.283 |
Neg logit contributions | |
olars | -1.302 |
tons | -1.244 |
lations | -1.216 |
lear | -1.212 |
pont | -1.204 |
Token | � |
Token ID | 447 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
Stro | +2.737 |
bid | +2.722 |
drawn | +2.592 |
hene | +2.478 |
ringe | +2.404 |
Neg logit contributions | |
olars | -2.187 |
tons | -2.059 |
lear | -2.007 |
lations | -2.001 |
litter | -1.999 |
Token | � |
Token ID | 251 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
bid | +0.742 |
Stro | +0.723 |
drawn | +0.710 |
hene | +0.683 |
ringe | +0.674 |
Neg logit contributions | |
olars | -0.469 |
tons | -0.446 |
litter | -0.432 |
lations | -0.432 |
lear | -0.427 |
Token | So |
Token ID | 1406 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Stro | +2.569 |
bid | +2.541 |
drawn | +2.436 |
hene | +2.318 |
ringe | +2.252 |
Neg logit contributions | |
olars | -2.064 |
tons | -1.904 |
litter | -1.880 |
lear | -1.880 |
lations | -1.880 |
Token | i |
Token ID | 72 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
bid | +0.796 |
Stro | +0.769 |
drawn | +0.750 |
hene | +0.716 |
ringe | +0.689 |
Neg logit contributions | |
olars | -0.983 |
tons | -0.943 |
lations | -0.929 |
litter | -0.925 |
pont | -0.920 |
Token | F |
Token ID | 376 |
Feature activation | -2.10e+01 |
Pos logit contributions | |
bid | +0.463 |
Stro | +0.459 |
drawn | +0.441 |
hene | +0.427 |
ringe | +0.410 |
Neg logit contributions | |
olars | -0.406 |
tons | -0.391 |
lations | -0.380 |
lear | -0.376 |
litter | -0.375 |
Token | on |
Token ID | 261 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
esta | +4.925 |
tons | +4.744 |
olars | +4.714 |
lear | +4.526 |
esm | +4.408 |
Neg logit contributions | |
aditional | -19.590 |
Stro | -19.352 |
ÍÍ | -19.048 |
龍契士 | -18.718 |
bid | -18.677 |
Token | followed |
Token ID | 3940 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
olars | +1.916 |
tons | +1.841 |
litter | +1.800 |
lations | +1.800 |
pont | +1.781 |
Neg logit contributions | |
bid | -2.416 |
Stro | -2.354 |
drawn | -2.317 |
hene | -2.230 |
ringe | -2.182 |
Token | her |
Token ID | 607 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Stro | +3.405 |
bid | +3.367 |
drawn | +3.233 |
hene | +3.053 |
ringe | +2.931 |
Neg logit contributions | |
olars | -3.456 |
tons | -3.254 |
lear | -3.179 |
lations | -3.178 |
pont | -3.159 |
Token | out |
Token ID | 503 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
bid | +1.484 |
Stro | +1.460 |
drawn | +1.424 |
hene | +1.344 |
ringe | +1.307 |
Neg logit contributions | |
olars | -1.436 |
tons | -1.383 |
lations | -1.353 |
lear | -1.332 |
esta | -1.332 |
Token | the |
Token ID | 262 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
bid | +2.409 |
Stro | +2.348 |
drawn | +2.307 |
hene | +2.163 |
ringe | +2.096 |
Neg logit contributions | |
olars | -2.379 |
tons | -2.267 |
lear | -2.202 |
lations | -2.196 |
litter | -2.171 |
Token | marked |
Token ID | 7498 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
olars | +0.132 |
tons | +0.128 |
lations | +0.126 |
lear | +0.124 |
litter | +0.123 |
Neg logit contributions | |
bid | -0.140 |
Stro | -0.137 |
drawn | -0.134 |
hene | -0.129 |
ringe | -0.124 |
Token | her |
Token ID | 607 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
olars | +2.695 |
tons | +2.598 |
litter | +2.530 |
pont | +2.520 |
lations | +2.517 |
Neg logit contributions | |
bid | -3.703 |
Stro | -3.588 |
drawn | -3.538 |
hene | -3.414 |
ringe | -3.358 |
Token | final |
Token ID | 2457 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
olars | +2.812 |
tons | +2.700 |
pont | +2.669 |
litter | +2.668 |
Soph | +2.632 |
Neg logit contributions | |
bid | -3.484 |
Stro | -3.368 |
drawn | -3.324 |
hene | -3.203 |
ringe | -3.166 |
Token | event |
Token ID | 1785 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
olars | +1.966 |
tons | +1.892 |
litter | +1.868 |
pont | +1.858 |
lations | +1.846 |
Neg logit contributions | |
bid | -2.247 |
Stro | -2.175 |
drawn | -2.150 |
hene | -2.068 |
ringe | -2.022 |
Token | as |
Token ID | 355 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
bid | +1.862 |
Stro | +1.817 |
drawn | +1.789 |
hene | +1.709 |
ringe | +1.653 |
Neg logit contributions | |
olars | -1.849 |
tons | -1.778 |
lations | -1.754 |
lear | -1.723 |
litter | -1.722 |
Token | first |
Token ID | 717 |
Feature activation | -2.08e+01 |
Pos logit contributions | |
olars | +0.894 |
tons | +0.854 |
lations | +0.836 |
litter | +0.828 |
lear | +0.825 |
Neg logit contributions | |
bid | -1.180 |
Stro | -1.158 |
drawn | -1.131 |
hene | -1.093 |
ringe | -1.062 |
Token | lady |
Token ID | 10846 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
litter | +6.662 |
pont | +6.509 |
Soph | +5.573 |
tons | +5.449 |
esta | +5.359 |
Neg logit contributions | |
bid | -18.201 |
drawn | -17.800 |
ringe | -17.659 |
Stro | -17.633 |
hene | -17.446 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
olars | +3.488 |
tons | +3.370 |
litter | +3.346 |
pont | +3.328 |
lations | +3.287 |
Neg logit contributions | |
bid | -4.375 |
Stro | -4.269 |
drawn | -4.208 |
hene | -4.022 |
ringe | -3.990 |
Token |
|
Token ID | 198 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
olars | +0.131 |
tons | +0.124 |
litter | +0.122 |
lations | +0.121 |
pont | +0.120 |
Neg logit contributions | |
bid | -0.179 |
Stro | -0.178 |
drawn | -0.172 |
hene | -0.167 |
ringe | -0.161 |
Token |
|
Token ID | 198 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
tons | +2.706 |
olars | +2.589 |
Soph | +2.571 |
lations | +2.474 |
litter | +2.446 |
Neg logit contributions | |
bid | -6.024 |
Stro | -5.859 |
drawn | -5.816 |
hene | -5.815 |
ringe | -5.735 |
Token | Before |
Token ID | 8421 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
olars | +3.542 |
tons | +3.493 |
lear | +3.360 |
lations | +3.350 |
esta | +3.325 |
Neg logit contributions | |
bid | -4.764 |
Stro | -4.715 |
drawn | -4.559 |
hene | -4.456 |
ringe | -4.354 |
Token | and |
Token ID | 290 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
olars | +0.668 |
tons | +0.643 |
lations | +0.628 |
litter | +0.626 |
lear | +0.621 |
Neg logit contributions | |
bid | -0.773 |
Stro | -0.753 |
drawn | -0.739 |
hene | -0.711 |
ringe | -0.692 |
Token | was |
Token ID | 373 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
olars | +0.075 |
tons | +0.072 |
lations | +0.071 |
litter | +0.070 |
lear | +0.070 |
Neg logit contributions | |
bid | -0.084 |
Stro | -0.082 |
drawn | -0.080 |
hene | -0.077 |
ringe | -0.075 |
Token | sworn |
Token ID | 20990 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
olars | +0.002 |
tons | +0.002 |
lations | +0.002 |
litter | +0.002 |
lear | +0.002 |
Neg logit contributions | |
bid | -0.003 |
Stro | -0.003 |
drawn | -0.003 |
hene | -0.003 |
ringe | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
olars | +3.044 |
tons | +3.008 |
pont | +2.972 |
litter | +2.967 |
lations | +2.922 |
Neg logit contributions | |
bid | -3.208 |
Stro | -3.086 |
drawn | -3.028 |
hene | -2.892 |
ringe | -2.829 |
Token | as |
Token ID | 355 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
olars | +0.606 |
tons | +0.582 |
lations | +0.570 |
litter | +0.566 |
lear | +0.562 |
Neg logit contributions | |
bid | -0.702 |
Stro | -0.685 |
drawn | -0.672 |
hene | -0.646 |
ringe | -0.629 |
Token | prime |
Token ID | 6994 |
Feature activation | -2.06e+01 |
Pos logit contributions | |
olars | +0.244 |
tons | +0.234 |
lations | +0.229 |
litter | +0.226 |
lear | +0.225 |
Neg logit contributions | |
bid | -0.286 |
Stro | -0.281 |
drawn | -0.274 |
hene | -0.263 |
ringe | -0.257 |
Token | minister |
Token ID | 5342 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
pont | +4.607 |
litter | +3.444 |
mk | +3.169 |
Soph | +2.967 |
tons | +2.869 |
Neg logit contributions | |
bid | -21.347 |
drawn | -20.779 |
ÍÍ | -20.084 |
idding | -19.995 |
hene | -19.733 |
Token | later |
Token ID | 1568 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
olars | +1.240 |
tons | +1.190 |
litter | +1.164 |
lations | +1.163 |
pont | +1.155 |
Neg logit contributions | |
bid | -1.681 |
Stro | -1.644 |
drawn | -1.615 |
hene | -1.555 |
ringe | -1.522 |
Token | that |
Token ID | 326 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
olars | +1.326 |
tons | +1.278 |
litter | +1.258 |
lations | +1.255 |
pont | +1.245 |
Neg logit contributions | |
bid | -1.592 |
Stro | -1.554 |
drawn | -1.524 |
hene | -1.465 |
ringe | -1.436 |
Token | day |
Token ID | 1110 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
bid | +0.461 |
Stro | +0.451 |
drawn | +0.442 |
hene | +0.423 |
ringe | +0.413 |
Neg logit contributions | |
olars | -0.381 |
tons | -0.365 |
lations | -0.356 |
lear | -0.349 |
esta | -0.349 |
Token | .[ |
Token ID | 3693 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
bid | +1.779 |
Stro | +1.731 |
drawn | +1.695 |
hene | +1.628 |
ringe | +1.573 |
Neg logit contributions | |
olars | -1.745 |
tons | -1.693 |
lations | -1.635 |
lear | -1.630 |
litter | -1.618 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
olars | +0.101 |
tons | +0.097 |
lations | +0.095 |
litter | +0.095 |
Soph | +0.094 |
Neg logit contributions | |
bid | -0.088 |
Stro | -0.085 |
drawn | -0.083 |
hene | -0.079 |
ringe | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
bid | +0.010 |
Stro | +0.009 |
drawn | +0.009 |
hene | +0.009 |
ringe | +0.009 |
Neg logit contributions | |
olars | -0.009 |
tons | -0.009 |
lations | -0.008 |
litter | -0.008 |
lear | -0.008 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
bid | +2.009 |
Stro | +1.883 |
drawn | +1.862 |
hene | +1.745 |
ringe | +1.671 |
Neg logit contributions | |
olars | -3.201 |
tons | -3.063 |
lations | -3.014 |
Soph | -3.006 |
litter | -2.999 |
Token | , |
Token ID | 11 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
olars | +0.885 |
tons | +0.852 |
lations | +0.834 |
litter | +0.833 |
pont | +0.826 |
Neg logit contributions | |
bid | -1.008 |
Stro | -0.983 |
drawn | -0.964 |
hene | -0.926 |
ringe | -0.903 |
Token | 4 |
Token ID | 19 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
olars | +2.432 |
tons | +2.399 |
litter | +2.329 |
lations | +2.328 |
lear | +2.308 |
Neg logit contributions | |
bid | -2.047 |
Stro | -2.028 |
drawn | -1.967 |
hene | -1.895 |
ringe | -1.849 |
Token | , |
Token ID | 11 |
Feature activation | -2.05e+01 |
Pos logit contributions | |
olars | +2.956 |
tons | +2.868 |
litter | +2.804 |
lations | +2.788 |
pont | +2.776 |
Neg logit contributions | |
bid | -3.709 |
Stro | -3.638 |
drawn | -3.609 |
hene | -3.439 |
ringe | -3.375 |
Token | 5 |
Token ID | 20 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
tons | +5.034 |
pod | +4.000 |
litter | +3.847 |
lations | +3.826 |
fund | +3.794 |
Neg logit contributions | |
aditional | -19.441 |
Stro | -19.145 |
ringe | -18.669 |
quartered | -18.638 |
hene | -18.427 |
Token | ]. |
Token ID | 4083 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
olars | +3.587 |
tons | +3.473 |
litter | +3.409 |
lations | +3.352 |
pont | +3.324 |
Neg logit contributions | |
bid | -6.089 |
Stro | -5.957 |
drawn | -5.942 |
hene | -5.680 |
ringe | -5.594 |
Token | each |
Token ID | 27379 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
olars | +0.599 |
tons | +0.566 |
lations | +0.551 |
litter | +0.550 |
pont | +0.544 |
Neg logit contributions | |
bid | -1.131 |
Stro | -1.102 |
drawn | -1.089 |
hene | -1.053 |
ringe | -1.031 |
Token | { |
Token ID | 1391 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
olars | +2.815 |
tons | +2.711 |
litter | +2.652 |
lations | +2.629 |
pont | +2.627 |
Neg logit contributions | |
bid | -4.950 |
Stro | -4.875 |
drawn | -4.839 |
hene | -4.669 |
ringe | -4.557 |
Token | | |
Token ID | 91 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
olars | +1.103 |
tons | +1.071 |
lations | +1.054 |
litter | +1.053 |
pont | +1.046 |
Neg logit contributions | |
bid | -0.645 |
Stro | -0.620 |
drawn | -0.604 |
hene | -0.567 |
ringe | -0.547 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
olars | +5.405 |
pont | +5.308 |
litter | +5.236 |
Soph | +5.224 |
tons | +5.222 |
Neg logit contributions | |
bid | -6.814 |
drawn | -6.594 |
Stro | -6.480 |
ringe | -6.240 |
hene | -6.203 |
Token | her |
Token ID | 607 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
bid | +1.200 |
Stro | +1.193 |
drawn | +1.167 |
hene | +1.102 |
ringe | +1.071 |
Neg logit contributions | |
olars | -1.151 |
tons | -1.105 |
lations | -1.083 |
lear | -1.073 |
litter | -1.057 |
Token | final |
Token ID | 2457 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
olars | +1.644 |
tons | +1.587 |
lations | +1.555 |
litter | +1.553 |
pont | +1.542 |
Neg logit contributions | |
bid | -1.649 |
Stro | -1.605 |
drawn | -1.573 |
hene | -1.507 |
ringe | -1.467 |
Token | speech |
Token ID | 4046 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
olars | +2.640 |
tons | +2.545 |
litter | +2.526 |
pont | +2.503 |
esta | +2.495 |
Neg logit contributions | |
bid | -2.875 |
Stro | -2.761 |
drawn | -2.748 |
hene | -2.637 |
ringe | -2.579 |
Token | as |
Token ID | 355 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
bid | +1.803 |
Stro | +1.787 |
drawn | +1.741 |
hene | +1.663 |
ringe | +1.595 |
Neg logit contributions | |
olars | -1.717 |
tons | -1.665 |
lations | -1.631 |
lear | -1.603 |
litter | -1.583 |
Token | first |
Token ID | 717 |
Feature activation | -2.03e+01 |
Pos logit contributions | |
Stro | +3.929 |
bid | +3.887 |
drawn | +3.704 |
hene | +3.616 |
ringe | +3.406 |
Neg logit contributions | |
olars | -3.705 |
tons | -3.517 |
lations | -3.461 |
lear | -3.368 |
esm | -3.329 |
Token | lady |
Token ID | 10846 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
pont | +5.325 |
litter | +5.307 |
Soph | +4.417 |
tons | +4.286 |
esta | +4.184 |
Neg logit contributions | |
bid | -19.181 |
drawn | -18.865 |
Stro | -18.596 |
ringe | -18.309 |
hene | -18.229 |
Token | on |
Token ID | 319 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
olars | +2.144 |
tons | +2.059 |
litter | +2.021 |
lations | +2.011 |
pont | +2.006 |
Neg logit contributions | |
bid | -2.683 |
Stro | -2.616 |
drawn | -2.571 |
hene | -2.471 |
ringe | -2.424 |
Token | Friday |
Token ID | 3217 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
olars | +0.165 |
tons | +0.159 |
lations | +0.157 |
litter | +0.154 |
lear | +0.154 |
Neg logit contributions | |
bid | -0.172 |
Stro | -0.170 |
drawn | -0.165 |
hene | -0.158 |
ringe | -0.153 |
Token | , |
Token ID | 11 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
olars | +0.409 |
tons | +0.396 |
lations | +0.387 |
lear | +0.383 |
litter | +0.382 |
Neg logit contributions | |
bid | -0.463 |
Stro | -0.454 |
drawn | -0.443 |
hene | -0.428 |
ringe | -0.413 |
Token | during |
Token ID | 1141 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
olars | +3.767 |
litter | +3.663 |
pont | +3.624 |
tons | +3.592 |
Soph | +3.563 |
Neg logit contributions | |
bid | -5.214 |
Stro | -5.021 |
drawn | -5.010 |
hene | -4.834 |
ringe | -4.786 |
Token | 2 |
Token ID | 17 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
bid | +0.021 |
Stro | +0.020 |
drawn | +0.019 |
hene | +0.019 |
ringe | +0.018 |
Neg logit contributions | |
olars | -0.025 |
tons | -0.024 |
lations | -0.024 |
litter | -0.024 |
Soph | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
bid | +0.434 |
Stro | +0.420 |
drawn | +0.411 |
hene | +0.395 |
ringe | +0.384 |
Neg logit contributions | |
olars | -0.410 |
tons | -0.395 |
lations | -0.387 |
litter | -0.386 |
lear | -0.383 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
bid | +2.499 |
Stro | +2.325 |
drawn | +2.309 |
hene | +2.147 |
ringe | +2.054 |
Neg logit contributions | |
olars | -4.159 |
tons | -4.006 |
Soph | -3.913 |
lations | -3.911 |
litter | -3.909 |
Token | , |
Token ID | 11 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
olars | +0.761 |
tons | +0.732 |
lations | +0.717 |
litter | +0.716 |
pont | +0.710 |
Neg logit contributions | |
bid | -0.847 |
Stro | -0.826 |
drawn | -0.810 |
hene | -0.778 |
ringe | -0.758 |
Token | 4 |
Token ID | 19 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
olars | +1.497 |
tons | +1.465 |
lations | +1.429 |
litter | +1.428 |
lear | +1.418 |
Neg logit contributions | |
bid | -1.207 |
Stro | -1.187 |
drawn | -1.154 |
hene | -1.107 |
ringe | -1.078 |
Token | , |
Token ID | 11 |
Feature activation | -2.02e+01 |
Pos logit contributions | |
olars | +2.922 |
tons | +2.822 |
litter | +2.756 |
lations | +2.750 |
pont | +2.737 |
Neg logit contributions | |
bid | -3.635 |
Stro | -3.573 |
drawn | -3.542 |
hene | -3.379 |
ringe | -3.306 |
Token | 5 |
Token ID | 20 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
tons | +4.129 |
pod | +3.208 |
lations | +2.993 |
fund | +2.972 |
wordpress | +2.932 |
Neg logit contributions | |
aditional | -20.818 |
Stro | -19.891 |
exha | -19.576 |
quartered | -19.491 |
ringe | -19.440 |
Token | ]. |
Token ID | 4083 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
olars | +3.511 |
tons | +3.373 |
litter | +3.322 |
lations | +3.285 |
pont | +3.246 |
Neg logit contributions | |
bid | -6.248 |
Stro | -6.139 |
drawn | -6.102 |
hene | -5.847 |
ringe | -5.739 |
Token | each |
Token ID | 27379 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
olars | +1.818 |
tons | +1.738 |
lations | +1.678 |
lear | +1.660 |
litter | +1.660 |
Neg logit contributions | |
bid | -3.694 |
Stro | -3.660 |
drawn | -3.571 |
hene | -3.478 |
ringe | -3.416 |
Token | do |
Token ID | 466 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
olars | +2.337 |
tons | +2.244 |
lations | +2.191 |
litter | +2.189 |
lear | +2.163 |
Neg logit contributions | |
bid | -3.635 |
Stro | -3.569 |
drawn | -3.518 |
hene | -3.397 |
ringe | -3.316 |
Token | | |
Token ID | 930 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
olars | +0.219 |
tons | +0.210 |
lations | +0.205 |
litter | +0.204 |
Soph | +0.203 |
Neg logit contributions | |
bid | -0.260 |
Stro | -0.253 |
drawn | -0.247 |
hene | -0.239 |
ringe | -0.232 |
Token |
|
Token ID | 198 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
olars | +1.519 |
tons | +1.453 |
lations | +1.414 |
litter | +1.412 |
pont | +1.398 |
Neg logit contributions | |
bid | -2.384 |
Stro | -2.331 |
drawn | -2.296 |
hene | -2.218 |
ringe | -2.170 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
bid | +1.883 |
Stro | +1.837 |
drawn | +1.805 |
hene | +1.717 |
ringe | +1.673 |
Neg logit contributions | |
olars | -1.418 |
tons | -1.318 |
litter | -1.312 |
lations | -1.311 |
pont | -1.306 |
Token | 1 |
Token ID | 16 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
bid | +1.035 |
Stro | +0.981 |
drawn | +0.976 |
hene | +0.912 |
ringe | +0.889 |
Neg logit contributions | |
olars | -1.446 |
tons | -1.394 |
litter | -1.383 |
pont | -1.379 |
lations | -1.372 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
olars | +2.031 |
tons | +1.938 |
litter | +1.916 |
lations | +1.904 |
pont | +1.889 |
Neg logit contributions | |
bid | -2.854 |
Stro | -2.778 |
drawn | -2.743 |
hene | -2.647 |
ringe | -2.576 |
Token | 3 |
Token ID | 513 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
bid | +0.887 |
Stro | +0.866 |
drawn | +0.844 |
hene | +0.809 |
ringe | +0.785 |
Neg logit contributions | |
olars | -0.951 |
tons | -0.920 |
lations | -0.896 |
lear | -0.892 |
litter | -0.888 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
olars | +1.787 |
tons | +1.705 |
litter | +1.684 |
pont | +1.671 |
lations | +1.670 |
Neg logit contributions | |
bid | -2.548 |
Stro | -2.481 |
drawn | -2.453 |
hene | -2.360 |
ringe | -2.305 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
mk | +6.963 |
litter | +6.877 |
pont | +6.656 |
olars | +6.328 |
esta | +6.279 |
Neg logit contributions | |
bid | -17.113 |
Stro | -16.556 |
drawn | -16.493 |
hene | -15.728 |
ringe | -15.629 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
mk | +5.202 |
olars | +5.101 |
litter | +5.069 |
tons | +4.782 |
pont | +4.769 |
Neg logit contributions | |
bid | -14.390 |
drawn | -13.755 |
Stro | -13.684 |
hene | -13.233 |
ignt | -13.181 |
Token | 7 |
Token ID | 767 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
litter | +3.523 |
olars | +3.434 |
mk | +3.371 |
tons | +3.287 |
pont | +3.269 |
Neg logit contributions | |
bid | -9.551 |
drawn | -9.455 |
Stro | -9.333 |
hene | -9.180 |
ringe | -9.097 |
Token | | |
Token ID | 930 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
olars | +2.635 |
litter | +2.515 |
tons | +2.503 |
lations | +2.460 |
lear | +2.453 |
Neg logit contributions | |
bid | -3.978 |
Stro | -3.868 |
drawn | -3.858 |
hene | -3.710 |
ringe | -3.639 |
Token | library |
Token ID | 5888 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
olars | +0.615 |
tons | +0.592 |
lations | +0.579 |
litter | +0.577 |
pont | +0.573 |
Neg logit contributions | |
bid | -0.697 |
Stro | -0.680 |
drawn | -0.667 |
hene | -0.640 |
ringe | -0.624 |
Token | than |
Token ID | 621 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
bid | +3.719 |
Stro | +3.514 |
drawn | +3.458 |
hene | +3.265 |
ringe | +3.199 |
Neg logit contributions | |
olars | -3.781 |
tons | -3.656 |
lear | -3.598 |
esta | -3.588 |
lations | -3.546 |
Token | other |
Token ID | 584 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
olars | +2.372 |
tons | +2.285 |
litter | +2.253 |
pont | +2.226 |
lations | +2.224 |
Neg logit contributions | |
bid | -2.999 |
Stro | -2.920 |
drawn | -2.890 |
hene | -2.784 |
ringe | -2.714 |
Token | college |
Token ID | 4152 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
olars | +2.403 |
tons | +2.304 |
litter | +2.273 |
lations | +2.245 |
pont | +2.243 |
Neg logit contributions | |
bid | -3.183 |
Stro | -3.101 |
drawn | -3.066 |
hene | -2.966 |
ringe | -2.895 |
Token | - |
Token ID | 12 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
olars | +2.026 |
tons | +1.935 |
litter | +1.900 |
lear | +1.886 |
pont | +1.877 |
Neg logit contributions | |
bid | -2.683 |
Stro | -2.619 |
drawn | -2.576 |
hene | -2.483 |
ringe | -2.437 |
Token | educated |
Token ID | 27317 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
olars | +0.835 |
tons | +0.801 |
lations | +0.784 |
litter | +0.782 |
pont | +0.775 |
Neg logit contributions | |
bid | -1.152 |
Stro | -1.123 |
drawn | -1.107 |
hene | -1.064 |
ringe | -1.040 |
Token | prime |
Token ID | 6994 |
Feature activation | -1.91e+01 |
Pos logit contributions | |
olars | +1.232 |
tons | +1.184 |
lations | +1.157 |
litter | +1.156 |
pont | +1.146 |
Neg logit contributions | |
bid | -1.512 |
Stro | -1.476 |
drawn | -1.449 |
hene | -1.394 |
ringe | -1.361 |
Token | - |
Token ID | 12 |
Feature activation | -1.38e+01 |
Pos logit contributions | |
olars | +9.337 |
tons | +9.232 |
pont | +9.023 |
Soph | +8.911 |
litter | +8.909 |
Neg logit contributions | |
bid | -13.749 |
drawn | -13.466 |
Stro | -13.267 |
ringe | -12.921 |
hene | -12.822 |
Token | age |
Token ID | 496 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
olars | +7.185 |
tons | +7.070 |
lear | +7.023 |
esta | +6.963 |
Soph | +6.835 |
Neg logit contributions | |
Stro | -10.609 |
bid | -10.239 |
drawn | -9.940 |
hene | -9.875 |
ringe | -9.704 |
Token | workers |
Token ID | 3259 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
olars | +1.868 |
tons | +1.795 |
litter | +1.754 |
pont | +1.741 |
lations | +1.740 |
Neg logit contributions | |
bid | -2.361 |
Stro | -2.303 |
drawn | -2.267 |
hene | -2.187 |
ringe | -2.139 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
bid | +1.046 |
Stro | +1.005 |
drawn | +0.987 |
hene | +0.939 |
ringe | +0.918 |
Neg logit contributions | |
olars | -1.026 |
tons | -0.991 |
lations | -0.962 |
lear | -0.959 |
Soph | -0.954 |
Token | When |
Token ID | 1649 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
bid | +1.156 |
Stro | +1.147 |
drawn | +1.097 |
hene | +1.051 |
ringe | +1.019 |
Neg logit contributions | |
olars | -0.902 |
tons | -0.855 |
litter | -0.840 |
lations | -0.839 |
lear | -0.835 |
Token | president |
Token ID | 1893 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
olars | +4.515 |
pont | +4.368 |
litter | +4.364 |
tons | +4.345 |
Soph | +4.287 |
Neg logit contributions | |
bid | -6.001 |
drawn | -5.783 |
Stro | -5.687 |
hene | -5.556 |
ringe | -5.408 |
Token | have |
Token ID | 423 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
pont | +5.857 |
olars | +5.823 |
tons | +5.805 |
litter | +5.768 |
esta | +5.616 |
Neg logit contributions | |
bid | -8.037 |
drawn | -7.938 |
Stro | -7.884 |
ringe | -7.487 |
hene | -7.343 |
Token | raised |
Token ID | 4376 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
olars | +3.416 |
tons | +3.343 |
litter | +3.308 |
pont | +3.304 |
Soph | +3.229 |
Neg logit contributions | |
bid | -3.843 |
Stro | -3.698 |
drawn | -3.651 |
ringe | -3.508 |
hene | -3.507 |
Token | two |
Token ID | 734 |
Feature activation | -8.76e+00 |
Pos logit contributions | |
olars | +1.185 |
tons | +1.140 |
lations | +1.114 |
litter | +1.114 |
pont | +1.104 |
Neg logit contributions | |
bid | -1.411 |
Stro | -1.377 |
drawn | -1.352 |
hene | -1.300 |
ringe | -1.269 |
Token | daughters |
Token ID | 14850 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
olars | +4.632 |
litter | +4.547 |
tons | +4.546 |
pont | +4.464 |
Soph | +4.292 |
Neg logit contributions | |
bid | -7.163 |
drawn | -7.089 |
Stro | -6.927 |
hene | -6.785 |
ringe | -6.747 |
Token | , |
Token ID | 11 |
Feature activation | -1.91e+01 |
Pos logit contributions | |
olars | +5.830 |
litter | +5.755 |
tons | +5.716 |
pont | +5.677 |
Soph | +5.666 |
Neg logit contributions | |
bid | -7.724 |
drawn | -7.505 |
Stro | -7.457 |
ringe | -7.339 |
hene | -7.065 |
Token | Mal |
Token ID | 4434 |
Feature activation | -7.86e+00 |
Pos logit contributions | |
Soph | +10.390 |
litter | +9.837 |
pont | +9.722 |
olars | +9.562 |
Ys | +9.441 |
Neg logit contributions | |
bid | -12.787 |
drawn | -12.650 |
ringe | -12.492 |
Stro | -12.036 |
inatory | -11.629 |
Token | ia |
Token ID | 544 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
olars | +5.338 |
esta | +5.170 |
lear | +5.093 |
tons | +5.059 |
litter | +5.015 |
Neg logit contributions | |
bid | -5.174 |
Stro | -5.151 |
drawn | -4.991 |
hene | -4.792 |
ringe | -4.697 |
Token | and |
Token ID | 290 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
olars | +1.090 |
tons | +1.055 |
lations | +1.030 |
litter | +1.026 |
lear | +1.019 |
Neg logit contributions | |
bid | -1.170 |
Stro | -1.142 |
drawn | -1.111 |
hene | -1.074 |
ringe | -1.038 |
Token | Sasha |
Token ID | 32151 |
Feature activation | -7.34e+00 |
Pos logit contributions | |
Soph | +5.292 |
olars | +5.126 |
litter | +5.112 |
pont | +4.977 |
tons | +4.965 |
Neg logit contributions | |
bid | -8.615 |
drawn | -8.413 |
ringe | -8.188 |
Stro | -8.171 |
hene | -7.864 |
Token | , |
Token ID | 11 |
Feature activation | -8.12e+00 |
Pos logit contributions | |
olars | +4.338 |
tons | +4.120 |
litter | +4.077 |
lations | +4.066 |
Soph | +4.066 |
Neg logit contributions | |
bid | -5.637 |
drawn | -5.516 |
Stro | -5.434 |
ringe | -5.226 |
hene | -5.129 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
olars | +0.185 |
tons | +0.176 |
lations | +0.172 |
lear | +0.171 |
litter | +0.171 |
Neg logit contributions | |
bid | -0.256 |
Stro | -0.251 |
drawn | -0.244 |
hene | -0.236 |
ringe | -0.230 |
Token |
|
Token ID | 198 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
bid | +1.169 |
Stro | +1.141 |
drawn | +1.120 |
hene | +1.073 |
ringe | +1.046 |
Neg logit contributions | |
olars | -0.824 |
tons | -0.773 |
lations | -0.764 |
litter | -0.764 |
pont | -0.759 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
olars | +0.053 |
tons | +0.051 |
litter | +0.050 |
lations | +0.050 |
pont | +0.050 |
Neg logit contributions | |
bid | -0.058 |
Stro | -0.056 |
drawn | -0.055 |
hene | -0.053 |
ringe | -0.051 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
olars | +1.154 |
tons | +1.108 |
lations | +1.081 |
litter | +1.079 |
pont | +1.070 |
Neg logit contributions | |
bid | -1.499 |
Stro | -1.465 |
drawn | -1.437 |
hene | -1.384 |
ringe | -1.353 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
bid | +1.105 |
Stro | +1.075 |
drawn | +1.046 |
hene | +1.007 |
ringe | +0.974 |
Neg logit contributions | |
olars | -1.185 |
tons | -1.147 |
lations | -1.116 |
lear | -1.115 |
litter | -1.108 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.90e+01 |
Pos logit contributions | |
olars | +1.333 |
tons | +1.275 |
litter | +1.250 |
lations | +1.247 |
pont | +1.241 |
Neg logit contributions | |
bid | -1.822 |
Stro | -1.777 |
drawn | -1.755 |
hene | -1.685 |
ringe | -1.649 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
litter | +7.252 |
mk | +7.195 |
pont | +7.170 |
olars | +7.089 |
esta | +6.857 |
Neg logit contributions | |
bid | -15.501 |
drawn | -15.221 |
Stro | -15.099 |
ringe | -14.339 |
hene | -14.209 |
Token | 6 |
Token ID | 718 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
olars | +5.292 |
litter | +5.119 |
tons | +5.010 |
mk | +5.006 |
pont | +4.866 |
Neg logit contributions | |
bid | -12.171 |
drawn | -11.752 |
Stro | -11.623 |
hene | -11.152 |
ringe | -11.045 |
Token | 7 |
Token ID | 767 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
olars | +3.057 |
litter | +2.974 |
tons | +2.939 |
Soph | +2.872 |
pont | +2.866 |
Neg logit contributions | |
bid | -6.579 |
drawn | -6.463 |
Stro | -6.420 |
hene | -6.229 |
ringe | -6.189 |
Token | 8 |
Token ID | 807 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
olars | +1.745 |
tons | +1.670 |
litter | +1.648 |
lations | +1.637 |
pont | +1.629 |
Neg logit contributions | |
bid | -2.253 |
Stro | -2.187 |
drawn | -2.170 |
hene | -2.079 |
ringe | -2.038 |
Token | 9 |
Token ID | 860 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
olars | +1.758 |
tons | +1.666 |
litter | +1.643 |
lations | +1.636 |
pont | +1.620 |
Neg logit contributions | |
bid | -2.976 |
Stro | -2.904 |
drawn | -2.867 |
hene | -2.762 |
ringe | -2.716 |
Token |
|
Token ID | 198 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
olars | +1.423 |
tons | +1.360 |
lations | +1.325 |
litter | +1.323 |
pont | +1.310 |
Neg logit contributions | |
bid | -2.177 |
Stro | -2.129 |
drawn | -2.095 |
hene | -2.022 |
ringe | -1.979 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
bid | +1.914 |
Stro | +1.867 |
drawn | +1.833 |
hene | +1.743 |
ringe | +1.697 |
Neg logit contributions | |
olars | -1.445 |
tons | -1.341 |
litter | -1.336 |
lations | -1.335 |
pont | -1.329 |
Token | 1 |
Token ID | 16 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
bid | +0.085 |
Stro | +0.082 |
drawn | +0.081 |
hene | +0.076 |
ringe | +0.074 |
Neg logit contributions | |
olars | -0.107 |
tons | -0.103 |
litter | -0.102 |
pont | -0.101 |
lations | -0.101 |
Token | 2 |
Token ID | 362 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
olars | +1.563 |
tons | +1.499 |
lations | +1.464 |
litter | +1.463 |
pont | +1.449 |
Neg logit contributions | |
bid | -2.086 |
Stro | -2.037 |
drawn | -2.002 |
hene | -1.929 |
ringe | -1.884 |
Token | 3 |
Token ID | 513 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
bid | +0.235 |
Stro | +0.229 |
drawn | +0.223 |
hene | +0.214 |
ringe | +0.208 |
Neg logit contributions | |
olars | -0.242 |
tons | -0.233 |
lations | -0.228 |
litter | -0.227 |
lear | -0.226 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.90e+01 |
Pos logit contributions | |
olars | +1.887 |
tons | +1.801 |
litter | +1.775 |
lations | +1.766 |
pont | +1.764 |
Neg logit contributions | |
bid | -2.681 |
Stro | -2.611 |
drawn | -2.585 |
hene | -2.489 |
ringe | -2.424 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
mk | +7.180 |
litter | +6.848 |
pont | +6.763 |
olars | +6.482 |
lations | +6.331 |
Neg logit contributions | |
bid | -16.230 |
drawn | -15.796 |
Stro | -15.745 |
hene | -15.170 |
ringe | -14.824 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
mk | +5.180 |
olars | +5.095 |
litter | +4.887 |
tons | +4.734 |
pont | +4.728 |
Neg logit contributions | |
bid | -13.479 |
drawn | -13.027 |
Stro | -12.811 |
hene | -12.603 |
ignt | -12.313 |
Token | 7 |
Token ID | 767 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
litter | +3.811 |
olars | +3.756 |
mk | +3.727 |
pont | +3.608 |
tons | +3.545 |
Neg logit contributions | |
bid | -9.985 |
drawn | -9.949 |
Stro | -9.776 |
hene | -9.696 |
ringe | -9.477 |
Token | 8 |
Token ID | 807 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
olars | +2.311 |
tons | +2.200 |
litter | +2.195 |
lations | +2.160 |
pont | +2.159 |
Neg logit contributions | |
bid | -3.413 |
Stro | -3.325 |
drawn | -3.318 |
hene | -3.193 |
ringe | -3.107 |
Token | 9 |
Token ID | 860 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
olars | +2.902 |
litter | +2.746 |
lations | +2.709 |
tons | +2.695 |
pont | +2.690 |
Neg logit contributions | |
bid | -5.553 |
Stro | -5.427 |
drawn | -5.372 |
hene | -5.173 |
ringe | -5.084 |
Token | he |
Token ID | 339 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
Stro | +0.686 |
bid | +0.685 |
drawn | +0.657 |
hene | +0.616 |
ringe | +0.604 |
Neg logit contributions | |
olars | -0.766 |
tons | -0.732 |
lations | -0.718 |
lear | -0.716 |
litter | -0.701 |
Token | steps |
Token ID | 4831 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
olars | +3.299 |
tons | +3.168 |
litter | +3.143 |
pont | +3.126 |
esta | +3.093 |
Neg logit contributions | |
bid | -4.845 |
Stro | -4.706 |
drawn | -4.661 |
hene | -4.482 |
ringe | -4.422 |
Token | out |
Token ID | 503 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
tons | +4.614 |
olars | +4.610 |
litter | +4.610 |
esta | +4.560 |
pont | +4.533 |
Neg logit contributions | |
bid | -7.573 |
Stro | -7.374 |
drawn | -7.308 |
hene | -7.044 |
ringe | -6.977 |
Token | from |
Token ID | 422 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
olars | +2.876 |
tons | +2.763 |
litter | +2.740 |
pont | +2.723 |
lations | +2.710 |
Neg logit contributions | |
bid | -3.454 |
Stro | -3.375 |
drawn | -3.312 |
hene | -3.204 |
ringe | -3.136 |
Token | Air |
Token ID | 3701 |
Feature activation | -1.68e+01 |
Pos logit contributions | |
olars | +4.550 |
litter | +4.394 |
pont | +4.322 |
tons | +4.272 |
lations | +4.258 |
Neg logit contributions | |
bid | -6.020 |
drawn | -5.783 |
Stro | -5.692 |
hene | -5.576 |
ringe | -5.439 |
Token | Force |
Token ID | 5221 |
Feature activation | -1.89e+01 |
Pos logit contributions | |
pont | +3.714 |
lear | +3.647 |
Soph | +3.530 |
tons | +3.493 |
iesel | +3.484 |
Neg logit contributions | |
advertisement | -16.722 |
drawn | -16.622 |
bid | -16.521 |
hene | -16.416 |
ringe | -16.332 |
Token | One |
Token ID | 1881 |
Feature activation | -9.72e+00 |
Pos logit contributions | |
litter | +3.139 |
Soph | +3.074 |
tons | +2.854 |
pont | +2.532 |
mk | +2.488 |
Neg logit contributions | |
bid | -20.626 |
drawn | -20.553 |
ignt | -19.596 |
ringe | -19.495 |
Stro | -19.283 |
Token | in |
Token ID | 287 |
Feature activation | -7.98e+00 |
Pos logit contributions | |
olars | +5.200 |
litter | +5.180 |
pont | +5.036 |
tons | +5.025 |
esta | +5.011 |
Neg logit contributions | |
bid | -7.666 |
Stro | -7.505 |
drawn | -7.275 |
hene | -7.172 |
ringe | -7.097 |
Token | Reno |
Token ID | 33817 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
olars | +4.618 |
tons | +4.529 |
litter | +4.491 |
pont | +4.472 |
Soph | +4.466 |
Neg logit contributions | |
bid | -5.955 |
drawn | -5.807 |
Stro | -5.711 |
hene | -5.702 |
ringe | -5.542 |
Token | , |
Token ID | 11 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
bid | +1.081 |
Stro | +1.054 |
drawn | +1.024 |
hene | +0.994 |
ringe | +0.940 |
Neg logit contributions | |
olars | -1.113 |
tons | -1.080 |
lear | -1.063 |
lations | -1.048 |
pont | -1.040 |
Token | Nevada |
Token ID | 12087 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
olars | +1.981 |
tons | +1.888 |
litter | +1.844 |
lations | +1.837 |
pont | +1.820 |
Neg logit contributions | |
bid | -3.166 |
Stro | -3.091 |
drawn | -3.043 |
hene | -2.940 |
ringe | -2.890 |
Token | cant |
Token ID | 18548 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
bid | +0.951 |
Stro | +0.941 |
drawn | +0.913 |
hene | +0.866 |
ringe | +0.849 |
Neg logit contributions | |
olars | -0.937 |
tons | -0.896 |
lations | -0.884 |
lear | -0.871 |
litter | -0.861 |
Token | een |
Token ID | 6429 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
bid | +3.133 |
Stro | +2.977 |
drawn | +2.921 |
hene | +2.882 |
ringe | +2.760 |
Neg logit contributions | |
olars | -4.166 |
Soph | -3.959 |
tons | -3.956 |
pont | -3.943 |
litter | -3.940 |
Token | but |
Token ID | 475 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
bid | +1.031 |
Stro | +0.999 |
drawn | +0.981 |
hene | +0.931 |
ringe | +0.910 |
Neg logit contributions | |
olars | -0.962 |
tons | -0.909 |
lations | -0.904 |
lear | -0.897 |
Soph | -0.882 |
Token | not |
Token ID | 407 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
bid | +4.510 |
Stro | +4.386 |
drawn | +4.252 |
hene | +4.023 |
ringe | +3.851 |
Neg logit contributions | |
olars | -4.310 |
lations | -3.998 |
esta | -3.932 |
tons | -3.901 |
esm | -3.901 |
Token | as |
Token ID | 355 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
bid | +3.205 |
Stro | +3.079 |
drawn | +2.988 |
hene | +2.820 |
ringe | +2.719 |
Neg logit contributions | |
olars | -3.111 |
lations | -2.890 |
tons | -2.886 |
esm | -2.820 |
lear | -2.818 |
Token | Prime |
Token ID | 5537 |
Feature activation | -1.89e+01 |
Pos logit contributions | |
bid | +4.171 |
Stro | +4.168 |
drawn | +3.932 |
hene | +3.704 |
ringe | +3.645 |
Neg logit contributions | |
olars | -4.795 |
lations | -4.471 |
tons | -4.454 |
esm | -4.378 |
lear | -4.365 |
Token | Minister |
Token ID | 4139 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
Soph | +2.720 |
tons | +2.475 |
Mk | +2.282 |
mk | +2.220 |
pont | +1.972 |
Neg logit contributions | |
bid | -20.253 |
drawn | -20.129 |
hene | -19.538 |
ringe | -19.487 |
ignt | -19.417 |
Token | , |
Token ID | 11 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
olars | +2.844 |
tons | +2.740 |
litter | +2.706 |
pont | +2.705 |
lations | +2.685 |
Neg logit contributions | |
bid | -3.453 |
Stro | -3.392 |
drawn | -3.345 |
hene | -3.216 |
ringe | -3.153 |
Token | reports |
Token ID | 3136 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
olars | +0.427 |
tons | +0.411 |
lations | +0.402 |
lear | +0.396 |
litter | +0.396 |
Neg logit contributions | |
bid | -0.488 |
Stro | -0.478 |
drawn | -0.468 |
hene | -0.449 |
ringe | -0.436 |
Token | said |
Token ID | 531 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
bid | +2.342 |
Stro | +2.329 |
drawn | +2.235 |
hene | +2.159 |
ringe | +2.116 |
Neg logit contributions | |
olars | -1.809 |
tons | -1.770 |
lations | -1.708 |
pont | -1.657 |
lear | -1.656 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
olars | +1.630 |
tons | +1.567 |
lations | +1.533 |
litter | +1.533 |
pont | +1.521 |
Neg logit contributions | |
bid | -1.883 |
Stro | -1.837 |
drawn | -1.803 |
hene | -1.733 |
ringe | -1.690 |
Token | In |
Token ID | 554 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
bid | +2.415 |
Stro | +2.404 |
drawn | +2.296 |
hene | +2.198 |
ringe | +2.154 |
Neg logit contributions | |
olars | -2.137 |
tons | -2.030 |
litter | -2.002 |
lations | -1.993 |
lear | -1.990 |
Token | this |
Token ID | 428 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
olars | +0.919 |
tons | +0.895 |
litter | +0.870 |
lations | +0.865 |
Soph | +0.865 |
Neg logit contributions | |
bid | -1.442 |
Stro | -1.404 |
drawn | -1.381 |
hene | -1.348 |
ringe | -1.321 |
Token | post |
Token ID | 1281 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
olars | +1.092 |
tons | +1.058 |
litter | +1.048 |
pont | +1.044 |
lations | +1.039 |
Neg logit contributions | |
bid | -0.946 |
Stro | -0.914 |
drawn | -0.900 |
hene | -0.862 |
ringe | -0.834 |
Token | I |
Token ID | 314 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
olars | +0.901 |
tons | +0.865 |
litter | +0.843 |
lations | +0.841 |
pont | +0.836 |
Neg logit contributions | |
bid | -1.394 |
Stro | -1.362 |
drawn | -1.345 |
hene | -1.300 |
ringe | -1.269 |
Token | 'll |
Token ID | 1183 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
olars | +5.768 |
pont | +5.740 |
litter | +5.653 |
tons | +5.385 |
lations | +5.122 |
Neg logit contributions | |
bid | -11.203 |
drawn | -11.067 |
Stro | -10.893 |
hene | -10.872 |
ignt | -10.441 |
Token | round |
Token ID | 2835 |
Feature activation | -1.89e+01 |
Pos logit contributions | |
olars | +1.953 |
litter | +1.857 |
pont | +1.851 |
tons | +1.834 |
lations | +1.778 |
Neg logit contributions | |
bid | -3.438 |
drawn | -3.340 |
Stro | -3.315 |
hene | -3.264 |
ringe | -3.148 |
Token | up |
Token ID | 510 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
tons | +3.651 |
litter | +3.635 |
olars | +2.991 |
Soph | +2.949 |
pont | +2.939 |
Neg logit contributions | |
bid | -18.805 |
hene | -18.691 |
drawn | -18.248 |
ringe | -17.890 |
ignt | -17.859 |
Token | some |
Token ID | 617 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
olars | +3.041 |
tons | +2.963 |
litter | +2.877 |
pont | +2.863 |
lations | +2.862 |
Neg logit contributions | |
bid | -4.311 |
Stro | -4.125 |
drawn | -4.095 |
hene | -4.028 |
ringe | -3.918 |
Token | got |
Token ID | 1392 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
olars | +2.015 |
tons | +1.974 |
litter | +1.920 |
pont | +1.917 |
lear | +1.912 |
Neg logit contributions | |
bid | -2.199 |
Stro | -2.149 |
drawn | -2.105 |
hene | -2.012 |
ringe | -1.988 |
Token | cha |
Token ID | 11693 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
tons | +4.546 |
olars | +4.193 |
lations | +3.992 |
lear | +3.977 |
esta | +3.806 |
Neg logit contributions | |
Stro | -9.895 |
bid | -9.853 |
drawn | -9.720 |
hene | -9.425 |
ringe | -9.186 |
Token | 's |
Token ID | 338 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
bid | +2.229 |
Stro | +2.174 |
drawn | +2.082 |
hene | +1.985 |
ringe | +1.918 |
Neg logit contributions | |
olars | -1.991 |
esta | -1.866 |
lear | -1.861 |
tons | -1.859 |
litter | -1.849 |
Token | out |
Token ID | 503 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
olars | +0.666 |
tons | +0.634 |
lations | +0.621 |
litter | +0.614 |
lear | +0.612 |
Neg logit contributions | |
bid | -0.969 |
Stro | -0.950 |
drawn | -0.933 |
hene | -0.898 |
ringe | -0.878 |
Token | of |
Token ID | 286 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
olars | +0.516 |
tons | +0.495 |
lations | +0.484 |
litter | +0.482 |
lear | +0.480 |
Neg logit contributions | |
bid | -0.608 |
Stro | -0.592 |
drawn | -0.581 |
hene | -0.557 |
ringe | -0.544 |
Token | the |
Token ID | 262 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
bid | +1.425 |
Stro | +1.402 |
drawn | +1.355 |
hene | +1.288 |
ringe | +1.237 |
Neg logit contributions | |
olars | -1.663 |
tons | -1.591 |
lations | -1.587 |
esta | -1.554 |
lear | -1.551 |
Token | ocean |
Token ID | 9151 |
Feature activation | -9.74e+00 |
Pos logit contributions | |
Stro | +3.178 |
bid | +3.164 |
drawn | +3.043 |
hene | +2.880 |
ringe | +2.811 |
Neg logit contributions | |
olars | -3.125 |
lations | -2.945 |
tons | -2.927 |
lear | -2.842 |
esta | -2.830 |
Token | . |
Token ID | 13 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
olars | +5.418 |
litter | +5.354 |
tons | +5.242 |
lations | +5.141 |
pont | +5.131 |
Neg logit contributions | |
bid | -7.554 |
drawn | -7.399 |
Stro | -7.372 |
hene | -7.100 |
ringe | -6.925 |
Token | Life |
Token ID | 5155 |
Feature activation | -1.88e+01 |
Pos logit contributions | |
olars | +3.739 |
tons | +3.691 |
Soph | +3.680 |
litter | +3.572 |
lations | +3.534 |
Neg logit contributions | |
bid | -5.392 |
drawn | -5.230 |
Stro | -5.139 |
hene | -5.064 |
ringe | -5.014 |
Token | in |
Token ID | 287 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
litter | +9.654 |
olars | +9.408 |
Soph | +9.102 |
pont | +9.101 |
esm | +9.089 |
Neg logit contributions | |
bid | -13.137 |
hene | -12.939 |
drawn | -12.889 |
Stro | -12.694 |
ringe | -12.352 |
Token | the |
Token ID | 262 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
olars | +5.793 |
litter | +5.697 |
pont | +5.524 |
Soph | +5.513 |
tons | +5.509 |
Neg logit contributions | |
bid | -8.280 |
Stro | -8.034 |
drawn | -7.944 |
hene | -7.846 |
ringe | -7.667 |
Token | Gulf |
Token ID | 12108 |
Feature activation | -7.23e+00 |
Pos logit contributions | |
olars | +5.443 |
litter | +5.406 |
tons | +5.336 |
Soph | +5.306 |
pont | +5.281 |
Neg logit contributions | |
bid | -7.668 |
drawn | -7.345 |
hene | -7.246 |
Stro | -7.245 |
ringe | -7.033 |
Token | of |
Token ID | 286 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
olars | +4.305 |
tons | +4.165 |
litter | +4.116 |
pont | +4.037 |
Soph | +4.035 |
Neg logit contributions | |
bid | -5.504 |
drawn | -5.382 |
Stro | -5.378 |
hene | -5.110 |
ringe | -5.056 |
Token | Mexico |
Token ID | 5828 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
olars | +0.881 |
tons | +0.845 |
litter | +0.828 |
lations | +0.823 |
pont | +0.822 |
Neg logit contributions | |
bid | -1.299 |
Stro | -1.265 |
drawn | -1.249 |
hene | -1.207 |
ringe | -1.190 |
Token | right |
Token ID | 826 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
Stro | +3.612 |
bid | +3.610 |
drawn | +3.505 |
hene | +3.280 |
ringe | +3.247 |
Neg logit contributions | |
olars | -4.138 |
tons | -4.051 |
lear | -4.026 |
lations | -4.019 |
esta | -3.956 |
Token | : |
Token ID | 25 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
Stro | +3.775 |
bid | +3.752 |
drawn | +3.601 |
hene | +3.452 |
ringe | +3.398 |
Neg logit contributions | |
olars | -4.183 |
tons | -4.116 |
lations | -4.061 |
esta | -4.024 |
lear | -3.958 |
Token | Me |
Token ID | 2185 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
olars | +2.773 |
tons | +2.685 |
litter | +2.641 |
Soph | +2.630 |
pont | +2.614 |
Neg logit contributions | |
bid | -3.171 |
Stro | -3.060 |
drawn | -3.028 |
hene | -2.920 |
ringe | -2.856 |
Token | in |
Token ID | 287 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
bid | +2.312 |
Stro | +2.278 |
drawn | +2.165 |
hene | +2.141 |
ringe | +2.064 |
Neg logit contributions | |
olars | -1.982 |
tons | -1.916 |
lations | -1.875 |
litter | -1.842 |
pont | -1.832 |
Token | 11 |
Token ID | 1367 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
olars | +4.260 |
litter | +4.103 |
tons | +4.097 |
Soph | +4.075 |
pont | +4.031 |
Neg logit contributions | |
bid | -5.605 |
Stro | -5.408 |
drawn | -5.359 |
hene | -5.225 |
ringe | -5.112 |
Token | th |
Token ID | 400 |
Feature activation | -1.87e+01 |
Pos logit contributions | |
olars | +6.236 |
tons | +5.943 |
Soph | +5.876 |
lear | +5.806 |
litter | +5.786 |
Neg logit contributions | |
bid | -9.881 |
Stro | -9.548 |
drawn | -9.342 |
hene | -9.110 |
ringe | -8.856 |
Token | grade |
Token ID | 9559 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
olars | +7.508 |
Soph | +7.374 |
litter | +7.253 |
pont | +6.915 |
mk | +6.872 |
Neg logit contributions | |
bid | -15.388 |
Stro | -14.795 |
drawn | -14.765 |
hene | -14.517 |
ringe | -14.191 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
litter | +7.219 |
olars | +7.189 |
Soph | +7.046 |
pont | +7.002 |
tons | +6.989 |
Neg logit contributions | |
bid | -11.572 |
drawn | -11.115 |
Stro | -11.100 |
hene | -10.916 |
ringe | -10.771 |
Token | Now |
Token ID | 2735 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
olars | +1.342 |
tons | +1.279 |
lations | +1.250 |
litter | +1.247 |
pont | +1.236 |
Neg logit contributions | |
bid | -1.936 |
Stro | -1.899 |
drawn | -1.860 |
hene | -1.792 |
ringe | -1.752 |
Token | I |
Token ID | 314 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
bid | +2.217 |
Stro | +2.185 |
drawn | +2.096 |
hene | +2.004 |
ringe | +1.947 |
Neg logit contributions | |
olars | -2.020 |
lations | -1.906 |
tons | -1.888 |
esta | -1.873 |
lear | -1.861 |
Token | know |
Token ID | 760 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
olars | +0.746 |
tons | +0.712 |
lations | +0.696 |
litter | +0.691 |
lear | +0.684 |
Neg logit contributions | |
bid | -1.138 |
Stro | -1.111 |
drawn | -1.092 |
hene | -1.055 |
ringe | -1.033 |
Token | a |
Token ID | 257 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
bid | +2.202 |
Stro | +2.184 |
drawn | +2.105 |
hene | +1.994 |
ringe | +1.965 |
Neg logit contributions | |
olars | -1.993 |
lations | -1.891 |
esta | -1.879 |
lear | -1.878 |
tons | -1.863 |
Token | complete |
Token ID | 1844 |
Feature activation | -7.95e+00 |
Pos logit contributions | |
olars | +0.905 |
tons | +0.869 |
lations | +0.855 |
litter | +0.847 |
lear | +0.843 |
Neg logit contributions | |
bid | -1.001 |
Stro | -0.977 |
drawn | -0.958 |
hene | -0.918 |
ringe | -0.894 |
Token | distortion |
Token ID | 25100 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
olars | +4.614 |
litter | +4.548 |
tons | +4.546 |
pont | +4.492 |
Soph | +4.406 |
Neg logit contributions | |
bid | -6.155 |
Stro | -5.868 |
drawn | -5.798 |
hene | -5.681 |
ringe | -5.510 |
Token | of |
Token ID | 286 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
bid | +1.746 |
Stro | +1.709 |
drawn | +1.654 |
hene | +1.569 |
ringe | +1.529 |
Neg logit contributions | |
olars | -1.744 |
tons | -1.686 |
lear | -1.635 |
lations | -1.620 |
esta | -1.620 |
Token | what |
Token ID | 644 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
olars | +2.932 |
tons | +2.804 |
litter | +2.761 |
pont | +2.757 |
Soph | +2.753 |
Neg logit contributions | |
bid | -4.219 |
Stro | -4.061 |
drawn | -4.046 |
hene | -3.965 |
ringe | -3.832 |
Token | I |
Token ID | 314 |
Feature activation | -1.86e+01 |
Pos logit contributions | |
olars | +2.072 |
tons | +1.992 |
litter | +1.953 |
lations | +1.944 |
pont | +1.934 |
Neg logit contributions | |
bid | -2.740 |
Stro | -2.661 |
drawn | -2.632 |
hene | -2.542 |
ringe | -2.466 |
Token | wrote |
Token ID | 2630 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
pont | +9.536 |
litter | +9.210 |
lear | +8.638 |
esta | +8.469 |
olars | +8.370 |
Neg logit contributions | |
drawn | -13.589 |
Stro | -13.515 |
bid | -12.895 |
hene | -12.782 |
ィ | -12.694 |
Token | and |
Token ID | 290 |
Feature activation | -7.43e+00 |
Pos logit contributions | |
olars | +3.682 |
pont | +3.531 |
litter | +3.530 |
tons | +3.523 |
Soph | +3.460 |
Neg logit contributions | |
bid | -4.823 |
Stro | -4.694 |
drawn | -4.651 |
hene | -4.516 |
ringe | -4.399 |
Token | intended |
Token ID | 5292 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
olars | +4.587 |
litter | +4.551 |
pont | +4.548 |
tons | +4.547 |
lations | +4.424 |
Neg logit contributions | |
bid | -5.336 |
Stro | -5.189 |
drawn | -5.124 |
hene | -5.040 |
ringe | -4.910 |
Token | to |
Token ID | 284 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
olars | +5.538 |
litter | +5.445 |
pont | +5.397 |
Soph | +5.321 |
tons | +5.294 |
Neg logit contributions | |
bid | -7.985 |
Stro | -7.782 |
drawn | -7.755 |
hene | -7.530 |
ringe | -7.443 |
Token | write |
Token ID | 3551 |
Feature activation | -7.54e+00 |
Pos logit contributions | |
pont | +7.342 |
litter | +7.196 |
olars | +6.789 |
Soph | +6.723 |
tons | +6.603 |
Neg logit contributions | |
drawn | -9.316 |
bid | -9.290 |
hene | -9.232 |
Stro | -9.149 |
ィ | -8.825 |
Token | global |
Token ID | 3298 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
bid | +0.703 |
Stro | +0.690 |
drawn | +0.668 |
hene | +0.637 |
ringe | +0.621 |
Neg logit contributions | |
olars | -0.715 |
tons | -0.687 |
lations | -0.675 |
lear | -0.668 |
esta | -0.662 |
Token | outsourcing |
Token ID | 44333 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
bid | +0.434 |
Stro | +0.426 |
drawn | +0.414 |
hene | +0.395 |
ringe | +0.384 |
Neg logit contributions | |
olars | -0.423 |
tons | -0.404 |
lations | -0.398 |
lear | -0.393 |
esta | -0.391 |
Token | firm |
Token ID | 4081 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
bid | +2.284 |
Stro | +2.245 |
drawn | +2.113 |
hene | +1.987 |
ringe | +1.905 |
Neg logit contributions | |
olars | -3.505 |
lations | -3.329 |
tons | -3.310 |
lear | -3.259 |
esta | -3.234 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
bid | +4.949 |
Stro | +4.811 |
drawn | +4.559 |
hene | +4.369 |
inder | +4.259 |
Neg logit contributions | |
olars | -4.708 |
lations | -4.404 |
esm | -4.309 |
tons | -4.276 |
litter | -4.225 |
Token | who |
Token ID | 508 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
bid | +0.089 |
Stro | +0.088 |
drawn | +0.085 |
hene | +0.082 |
ringe | +0.079 |
Neg logit contributions | |
olars | -0.076 |
tons | -0.073 |
lations | -0.071 |
litter | -0.071 |
lear | -0.070 |
Token | did |
Token ID | 750 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
bid | +2.468 |
Stro | +2.373 |
drawn | +2.277 |
hene | +2.206 |
ringe | +2.135 |
Neg logit contributions | |
olars | -2.785 |
tons | -2.616 |
litter | -2.593 |
esm | -2.592 |
lations | -2.586 |
Token | not |
Token ID | 407 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
bid | +5.905 |
Stro | +5.671 |
drawn | +5.435 |
ringe | +4.877 |
hene | +4.855 |
Neg logit contributions | |
olars | -10.707 |
tons | -10.208 |
lations | -10.051 |
�� | -9.965 |
esm | -9.894 |
Token | want |
Token ID | 765 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
bid | +2.643 |
Stro | +2.467 |
drawn | +2.428 |
ringe | +2.319 |
hene | +2.318 |
Neg logit contributions | |
olars | -2.823 |
tons | -2.678 |
lations | -2.635 |
esta | -2.575 |
litter | -2.556 |
Token | to |
Token ID | 284 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
bid | +1.812 |
Stro | +1.757 |
drawn | +1.725 |
hene | +1.645 |
ringe | +1.597 |
Neg logit contributions | |
olars | -1.795 |
tons | -1.718 |
lations | -1.679 |
litter | -1.670 |
esta | -1.664 |
Token | be |
Token ID | 307 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
bid | +2.131 |
Stro | +2.002 |
drawn | +1.958 |
hene | +1.870 |
ringe | +1.841 |
Neg logit contributions | |
olars | -2.700 |
tons | -2.585 |
lations | -2.530 |
esta | -2.486 |
lear | -2.463 |
Token | named |
Token ID | 3706 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
bid | +2.448 |
Stro | +2.303 |
drawn | +2.285 |
hene | +2.141 |
ringe | +2.075 |
Neg logit contributions | |
olars | -3.108 |
tons | -2.947 |
lations | -2.864 |
litter | -2.810 |
esta | -2.807 |
Token | doing |
Token ID | 1804 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
bid | +0.627 |
Stro | +0.613 |
drawn | +0.596 |
hene | +0.571 |
ringe | +0.556 |
Neg logit contributions | |
olars | -0.494 |
tons | -0.472 |
lations | -0.464 |
lear | -0.452 |
Soph | -0.452 |
Token | more |
Token ID | 517 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
bid | +7.284 |
Stro | +7.079 |
drawn | +6.965 |
hene | +6.374 |
ringe | +6.261 |
Neg logit contributions | |
olars | -8.480 |
tons | -7.992 |
lations | -7.885 |
assetsadobe | -7.714 |
esta | -7.667 |
Token | to |
Token ID | 284 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
bid | +6.776 |
Stro | +6.577 |
drawn | +6.203 |
hene | +5.798 |
ringe | +5.791 |
Neg logit contributions | |
olars | -9.223 |
�� | -8.827 |
tons | -8.790 |
esm | -8.634 |
lations | -8.625 |
Token | distance |
Token ID | 5253 |
Feature activation | +7.66e+00 |
Pos logit contributions | |
bid | +4.601 |
Stro | +4.543 |
drawn | +4.232 |
hene | +4.050 |
idding | +3.987 |
Neg logit contributions | |
olars | -4.925 |
tons | -4.782 |
lations | -4.725 |
lear | -4.620 |
Soph | -4.604 |
Token | the |
Token ID | 262 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
bid | +4.205 |
Stro | +4.116 |
drawn | +3.840 |
hene | +3.547 |
ringe | +3.492 |
Neg logit contributions | |
olars | -6.240 |
tons | -6.022 |
lations | -5.929 |
lear | -5.845 |
esm | -5.809 |
Token | UK |
Token ID | 3482 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
bid | +1.343 |
Stro | +1.323 |
drawn | +1.255 |
hene | +1.189 |
ringe | +1.161 |
Neg logit contributions | |
olars | -1.943 |
tons | -1.885 |
lations | -1.851 |
lear | -1.848 |
esta | -1.831 |
Token | from |
Token ID | 422 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
bid | +5.166 |
Stro | +4.929 |
drawn | +4.421 |
hene | +4.327 |
ringe | +4.224 |
Neg logit contributions | |
olars | -9.903 |
tons | -9.839 |
lations | -9.474 |
lear | -9.430 |
esm | -9.359 |
Token | the |
Token ID | 262 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
olars | +0.913 |
tons | +0.879 |
lations | +0.859 |
litter | +0.854 |
lear | +0.853 |
Neg logit contributions | |
bid | -0.992 |
Stro | -0.968 |
drawn | -0.948 |
hene | -0.907 |
ringe | -0.885 |
Token | EU |
Token ID | 4576 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
olars | +2.263 |
tons | +2.196 |
litter | +2.158 |
lations | +2.155 |
pont | +2.150 |
Neg logit contributions | |
bid | -1.888 |
Stro | -1.820 |
drawn | -1.791 |
hene | -1.709 |
ringe | -1.658 |
Token | . |
Token ID | 13 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
bid | +3.208 |
Stro | +3.061 |
drawn | +2.915 |
hene | +2.855 |
ringe | +2.789 |
Neg logit contributions | |
olars | -3.227 |
tons | -3.148 |
lations | -3.114 |
lear | -3.081 |
esta | -3.056 |
Token |
|
Token ID | 198 |
Feature activation | -8.29e+00 |
Pos logit contributions | |
Stro | +1.747 |
bid | +1.742 |
drawn | +1.669 |
hene | +1.591 |
ringe | +1.528 |
Neg logit contributions | |
olars | -1.420 |
tons | -1.337 |
litter | -1.310 |
lations | -1.302 |
lear | -1.301 |
Token | chief |
Token ID | 4039 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
bid | +1.259 |
Stro | +1.240 |
drawn | +1.201 |
hene | +1.154 |
ringe | +1.127 |
Neg logit contributions | |
olars | -1.105 |
tons | -1.048 |
lations | -1.033 |
lear | -1.014 |
esta | -1.008 |
Token | vows |
Token ID | 36605 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
bid | +0.065 |
Stro | +0.064 |
drawn | +0.062 |
hene | +0.059 |
ringe | +0.058 |
Neg logit contributions | |
olars | -0.056 |
tons | -0.054 |
lations | -0.053 |
litter | -0.052 |
lear | -0.052 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
bid | +0.192 |
Stro | +0.189 |
drawn | +0.184 |
hene | +0.176 |
ringe | +0.171 |
Neg logit contributions | |
olars | -0.187 |
tons | -0.178 |
lations | -0.176 |
lear | -0.173 |
litter | -0.173 |
Token | suspect |
Token ID | 4099 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
bid | +1.546 |
Stro | +1.503 |
drawn | +1.466 |
hene | +1.406 |
ringe | +1.372 |
Neg logit contributions | |
olars | -1.515 |
tons | -1.442 |
lations | -1.414 |
esta | -1.411 |
lear | -1.406 |
Token | " |
Token ID | 366 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
Stro | +7.108 |
bid | +6.943 |
drawn | +6.656 |
hene | +6.315 |
ringe | +6.235 |
Neg logit contributions | |
olars | -7.668 |
esta | -7.163 |
esm | -7.101 |
tons | -7.001 |
lations | -6.992 |
Token | will |
Token ID | 10594 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
bid | +4.542 |
drawn | +4.448 |
Stro | +4.252 |
hene | +4.106 |
ringe | +4.053 |
Neg logit contributions | |
olars | -3.184 |
litter | -3.014 |
pont | -2.998 |
Soph | -2.970 |
lations | -2.929 |
Token | be |
Token ID | 307 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
bid | +6.666 |
Stro | +6.515 |
drawn | +6.027 |
hene | +5.935 |
ringe | +5.847 |
Neg logit contributions | |
olars | -8.239 |
tons | -7.843 |
lations | -7.825 |
lear | -7.718 |
Soph | -7.551 |
Token | in |
Token ID | 287 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
Stro | +7.385 |
bid | +7.341 |
drawn | +7.018 |
hene | +6.539 |
inder | +6.286 |
Neg logit contributions | |
olars | -8.928 |
lations | -8.514 |
tons | -8.484 |
esm | -8.236 |
esta | -8.182 |
Token | custody |
Token ID | 10804 |
Feature activation | +7.93e+00 |
Pos logit contributions | |
Stro | +6.828 |
bid | +6.762 |
drawn | +6.504 |
hene | +6.069 |
ringe | +5.854 |
Neg logit contributions | |
olars | -8.321 |
tons | -8.077 |
lations | -7.991 |
lear | -7.873 |
esm | -7.853 |
Token | pretty |
Token ID | 2495 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
bid | +5.166 |
Stro | +5.006 |
drawn | +4.953 |
hene | +4.600 |
ringe | +4.465 |
Neg logit contributions | |
olars | -5.772 |
tons | -5.400 |
lear | -5.238 |
lations | -5.224 |
esta | -5.198 |
Token | quickly |
Token ID | 2952 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
bid | +1.927 |
Stro | +1.870 |
drawn | +1.813 |
hene | +1.731 |
ringe | +1.704 |
Neg logit contributions | |
olars | -2.283 |
tons | -2.179 |
lear | -2.145 |
esta | -2.111 |
Soph | -2.109 |
Token | brother |
Token ID | 3956 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
bid | +1.922 |
Stro | +1.908 |
drawn | +1.819 |
hene | +1.762 |
ringe | +1.719 |
Neg logit contributions | |
olars | -1.968 |
tons | -1.896 |
lations | -1.866 |
lear | -1.838 |
esta | -1.822 |
Token | � |
Token ID | 447 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
olars | +0.208 |
tons | +0.200 |
lations | +0.195 |
litter | +0.194 |
lear | +0.193 |
Neg logit contributions | |
bid | -0.260 |
Stro | -0.254 |
drawn | -0.247 |
hene | -0.237 |
ringe | -0.233 |
Token | � |
Token ID | 247 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
bid | +0.088 |
Stro | +0.087 |
drawn | +0.086 |
hene | +0.083 |
ringe | +0.082 |
Neg logit contributions | |
olars | -0.034 |
tons | -0.032 |
litter | -0.030 |
lations | -0.030 |
pont | -0.030 |
Token | s |
Token ID | 82 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
olars | +0.954 |
tons | +0.898 |
lations | +0.868 |
litter | +0.865 |
pont | +0.854 |
Neg logit contributions | |
bid | -2.235 |
Stro | -2.193 |
drawn | -2.163 |
hene | -2.098 |
ringe | -2.059 |
Token | … |
Token ID | 1399 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
bid | +1.437 |
Stro | +1.422 |
drawn | +1.350 |
hene | +1.306 |
ringe | +1.272 |
Neg logit contributions | |
olars | -1.678 |
tons | -1.613 |
lations | -1.598 |
lear | -1.569 |
esta | -1.558 |
Token | he |
Token ID | 258 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
bid | +3.211 |
Stro | +3.144 |
drawn | +3.057 |
hene | +2.932 |
ringe | +2.888 |
Neg logit contributions | |
olars | -2.689 |
tons | -2.550 |
lations | -2.505 |
litter | -2.492 |
pont | -2.458 |
Token | used |
Token ID | 973 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
bid | +7.617 |
Stro | +7.151 |
drawn | +6.903 |
hene | +6.649 |
ringe | +6.433 |
Neg logit contributions | |
olars | -7.241 |
tons | -7.061 |
esm | -6.914 |
litter | -6.838 |
lus | -6.837 |
Token | to |
Token ID | 284 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
olars | +1.707 |
tons | +1.642 |
lations | +1.607 |
litter | +1.604 |
pont | +1.592 |
Neg logit contributions | |
bid | -1.933 |
Stro | -1.885 |
drawn | -1.849 |
hene | -1.776 |
ringe | -1.732 |
Token | smoke |
Token ID | 7523 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
bid | +3.429 |
Stro | +3.299 |
drawn | +3.125 |
hene | +2.991 |
ringe | +2.972 |
Neg logit contributions | |
olars | -3.424 |
lations | -3.202 |
tons | -3.173 |
lear | -3.088 |
emort | -3.057 |
Token | and |
Token ID | 290 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
bid | +1.432 |
Stro | +1.412 |
drawn | +1.349 |
hene | +1.299 |
ringe | +1.263 |
Neg logit contributions | |
olars | -1.409 |
tons | -1.330 |
lations | -1.317 |
lear | -1.296 |
esta | -1.283 |
Token | I |
Token ID | 314 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
bid | +3.130 |
Stro | +3.089 |
drawn | +2.897 |
hene | +2.830 |
ringe | +2.737 |
Neg logit contributions | |
olars | -3.037 |
tons | -2.814 |
lations | -2.797 |
lear | -2.749 |
esta | -2.739 |
Token | themed |
Token ID | 26966 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
bid | +0.075 |
Stro | +0.072 |
drawn | +0.072 |
hene | +0.068 |
ringe | +0.066 |
Neg logit contributions | |
olars | -0.076 |
tons | -0.073 |
litter | -0.072 |
pont | -0.072 |
lations | -0.071 |
Token | drinks |
Token ID | 11758 |
Feature activation | +9.96e+00 |
Pos logit contributions | |
bid | +4.239 |
Stro | +4.232 |
drawn | +3.976 |
hene | +3.752 |
ringe | +3.689 |
Neg logit contributions | |
olars | -3.790 |
tons | -3.574 |
lear | -3.567 |
lations | -3.511 |
esm | -3.476 |
Token | he |
Token ID | 339 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
Stro | +6.173 |
bid | +5.935 |
drawn | +5.498 |
hene | +5.335 |
ringe | +5.298 |
Neg logit contributions | |
olars | -7.091 |
esm | -6.769 |
lear | -6.757 |
tons | -6.669 |
lations | -6.591 |
Token | � |
Token ID | 447 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
bid | +6.814 |
Stro | +6.552 |
drawn | +6.287 |
hene | +5.893 |
inder | +5.743 |
Neg logit contributions | |
olars | -8.910 |
tons | -8.566 |
esm | -8.562 |
esta | -8.446 |
lations | -8.404 |
Token | � |
Token ID | 247 |
Feature activation | +7.69e+00 |
Pos logit contributions | |
bid | +3.268 |
Stro | +3.185 |
drawn | +3.159 |
ringe | +3.040 |
hene | +3.037 |
Neg logit contributions | |
olars | -1.461 |
tons | -1.418 |
Soph | -1.385 |
pont | -1.354 |
lear | -1.348 |
Token | d |
Token ID | 67 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
bid | +6.385 |
drawn | +6.199 |
Stro | +6.072 |
hene | +5.762 |
ringe | +5.747 |
Neg logit contributions | |
olars | -3.980 |
tons | -3.758 |
Soph | -3.755 |
lations | -3.706 |
litter | -3.691 |
Token | had |
Token ID | 550 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
bid | +7.146 |
Stro | +6.887 |
drawn | +6.773 |
inder | +6.239 |
hene | +6.077 |
Neg logit contributions | |
olars | -8.474 |
lations | -8.205 |
tons | -7.979 |
esta | -7.929 |
esm | -7.926 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
bid | +4.908 |
Stro | +4.755 |
drawn | +4.670 |
hene | +4.255 |
ringe | +4.160 |
Neg logit contributions | |
olars | -5.104 |
esm | -4.851 |
lations | -4.849 |
tons | -4.795 |
lear | -4.758 |
Token | He |
Token ID | 679 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
bid | +1.726 |
Stro | +1.723 |
drawn | +1.639 |
hene | +1.581 |
ringe | +1.537 |
Neg logit contributions | |
olars | -1.485 |
tons | -1.389 |
litter | -1.365 |
lear | -1.362 |
esta | -1.359 |
Token | looks |
Token ID | 3073 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
bid | +2.834 |
Stro | +2.735 |
drawn | +2.664 |
hene | +2.567 |
ringe | +2.481 |
Neg logit contributions | |
olars | -2.553 |
tons | -2.445 |
esta | -2.384 |
lations | -2.383 |
lear | -2.374 |
Token | at |
Token ID | 379 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
bid | +1.259 |
Stro | +1.229 |
drawn | +1.209 |
hene | +1.144 |
ringe | +1.112 |
Neg logit contributions | |
olars | -1.211 |
tons | -1.155 |
lear | -1.131 |
lations | -1.126 |
esta | -1.114 |
Token | adds |
Token ID | 6673 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
bid | +1.730 |
Stro | +1.698 |
drawn | +1.639 |
hene | +1.593 |
ringe | +1.522 |
Neg logit contributions | |
olars | -1.694 |
tons | -1.637 |
lear | -1.628 |
lations | -1.624 |
Soph | -1.598 |
Token | a |
Token ID | 257 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
olars | +1.105 |
tons | +1.061 |
lations | +1.043 |
litter | +1.035 |
lear | +1.032 |
Neg logit contributions | |
bid | -1.251 |
Stro | -1.220 |
drawn | -1.196 |
hene | -1.148 |
ringe | -1.120 |
Token | small |
Token ID | 1402 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
olars | +2.661 |
tons | +2.583 |
litter | +2.563 |
pont | +2.532 |
Soph | +2.510 |
Neg logit contributions | |
bid | -2.809 |
Stro | -2.724 |
drawn | -2.697 |
hene | -2.578 |
ringe | -2.526 |
Token | uncertainty |
Token ID | 13479 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
olars | +0.396 |
tons | +0.380 |
lations | +0.377 |
lear | +0.370 |
esta | +0.369 |
Neg logit contributions | |
bid | -0.416 |
Stro | -0.406 |
drawn | -0.396 |
hene | -0.380 |
ringe | -0.368 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
bid | +1.549 |
Stro | +1.508 |
drawn | +1.442 |
hene | +1.387 |
ringe | +1.370 |
Neg logit contributions | |
olars | -1.593 |
tons | -1.537 |
lations | -1.515 |
lear | -1.507 |
esta | -1.494 |
Token | but |
Token ID | 475 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
olars | +0.720 |
tons | +0.693 |
lations | +0.681 |
lear | +0.674 |
litter | +0.673 |
Neg logit contributions | |
bid | -0.781 |
Stro | -0.764 |
drawn | -0.748 |
hene | -0.716 |
ringe | -0.697 |
Token | contamination |
Token ID | 22733 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
bid | +0.569 |
Stro | +0.560 |
drawn | +0.544 |
hene | +0.523 |
ringe | +0.510 |
Neg logit contributions | |
olars | -0.450 |
lations | -0.427 |
tons | -0.426 |
lear | -0.422 |
esta | -0.418 |
Token | by |
Token ID | 416 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
olars | +2.868 |
tons | +2.800 |
litter | +2.744 |
lations | +2.712 |
pont | +2.710 |
Neg logit contributions | |
bid | -3.403 |
Stro | -3.324 |
drawn | -3.284 |
hene | -3.152 |
ringe | -3.095 |
Token | " |
Token ID | 366 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
olars | +4.079 |
litter | +3.988 |
tons | +3.959 |
pont | +3.884 |
Soph | +3.875 |
Neg logit contributions | |
bid | -4.350 |
Stro | -4.209 |
drawn | -4.157 |
hene | -4.019 |
ringe | -3.912 |
Token | modern |
Token ID | 23922 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
olars | +0.069 |
tons | +0.066 |
pont | +0.065 |
litter | +0.065 |
lations | +0.065 |
Neg logit contributions | |
bid | -0.072 |
Stro | -0.069 |
drawn | -0.069 |
hene | -0.065 |
ringe | -0.064 |
Token | carbon |
Token ID | 6588 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
olars | +1.686 |
tons | +1.628 |
litter | +1.595 |
lations | +1.593 |
pont | +1.581 |
Neg logit contributions | |
bid | -1.697 |
Stro | -1.650 |
drawn | -1.617 |
hene | -1.550 |
ringe | -1.510 |
Token | is |
Token ID | 318 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
olars | +0.855 |
tons | +0.823 |
lations | +0.802 |
litter | +0.799 |
lear | +0.796 |
Neg logit contributions | |
bid | -0.970 |
Stro | -0.945 |
drawn | -0.926 |
hene | -0.890 |
ringe | -0.868 |
Token | every |
Token ID | 790 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
bid | +1.953 |
Stro | +1.940 |
drawn | +1.863 |
hene | +1.794 |
ringe | +1.732 |
Neg logit contributions | |
olars | -1.901 |
lear | -1.786 |
tons | -1.784 |
lations | -1.769 |
esta | -1.743 |
Token | year |
Token ID | 614 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
olars | +0.024 |
tons | +0.023 |
lations | +0.023 |
litter | +0.022 |
lear | +0.022 |
Neg logit contributions | |
bid | -0.028 |
Stro | -0.028 |
drawn | -0.027 |
hene | -0.026 |
ringe | -0.025 |
Token | he |
Token ID | 339 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
bid | +0.373 |
Stro | +0.366 |
drawn | +0.353 |
hene | +0.342 |
ringe | +0.334 |
Neg logit contributions | |
olars | -0.331 |
tons | -0.316 |
lations | -0.312 |
esta | -0.309 |
lear | -0.309 |
Token | has |
Token ID | 468 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
bid | +3.041 |
Stro | +2.936 |
drawn | +2.883 |
hene | +2.759 |
ィ | +2.651 |
Neg logit contributions | |
olars | -2.824 |
tons | -2.714 |
esm | -2.665 |
Soph | -2.649 |
lations | -2.645 |
Token | all |
Token ID | 477 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
Stro | +3.760 |
bid | +3.742 |
drawn | +3.660 |
hene | +3.443 |
ringe | +3.309 |
Neg logit contributions | |
olars | -3.905 |
lations | -3.629 |
tons | -3.616 |
esm | -3.580 |
lear | -3.538 |
Token | these |
Token ID | 777 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
bid | +3.796 |
Stro | +3.755 |
drawn | +3.680 |
hene | +3.425 |
ringe | +3.339 |
Neg logit contributions | |
olars | -3.789 |
tons | -3.640 |
lations | -3.534 |
litter | -3.452 |
Soph | -3.447 |
Token | really |
Token ID | 1107 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
Stro | +3.553 |
bid | +3.553 |
drawn | +3.439 |
hene | +3.199 |
ringe | +3.155 |
Neg logit contributions | |
olars | -3.190 |
lations | -3.048 |
tons | -3.004 |
lear | -2.989 |
esta | -2.931 |
Token | new |
Token ID | 649 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
bid | +0.548 |
Stro | +0.535 |
drawn | +0.521 |
hene | +0.494 |
ringe | +0.478 |
Neg logit contributions | |
olars | -0.674 |
tons | -0.646 |
lations | -0.642 |
lear | -0.634 |
esta | -0.630 |
Token | iconic |
Token ID | 14133 |
Feature activation | +6.82e+00 |
Pos logit contributions | |
bid | +2.680 |
Stro | +2.676 |
drawn | +2.593 |
hene | +2.420 |
ringe | +2.373 |
Neg logit contributions | |
olars | -2.421 |
lations | -2.269 |
lear | -2.240 |
tons | -2.237 |
esta | -2.196 |
Token | walk |
Token ID | 2513 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Stro | +4.790 |
bid | +4.717 |
drawn | +4.580 |
hene | +4.156 |
ringe | +4.098 |
Neg logit contributions | |
olars | -4.570 |
lations | -4.352 |
lear | -4.306 |
tons | -4.241 |
esta | -4.194 |
Token | party |
Token ID | 2151 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Stro | +2.487 |
bid | +2.431 |
drawn | +2.159 |
hene | +2.086 |
inder | +1.935 |
Neg logit contributions | |
olars | -8.339 |
lear | -8.112 |
tons | -8.040 |
lations | -8.020 |
esm | -7.952 |
Token | movement |
Token ID | 3356 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
bid | +1.289 |
Stro | +1.268 |
drawn | +1.217 |
hene | +1.167 |
ringe | +1.138 |
Neg logit contributions | |
olars | -1.439 |
tons | -1.366 |
lations | -1.363 |
lear | -1.351 |
litter | -1.335 |
Token | , |
Token ID | 11 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
olars | +0.411 |
tons | +0.395 |
lations | +0.389 |
litter | +0.386 |
lear | +0.384 |
Neg logit contributions | |
bid | -0.451 |
Stro | -0.441 |
drawn | -0.431 |
hene | -0.414 |
ringe | -0.403 |
Token | which |
Token ID | 543 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
bid | +1.811 |
Stro | +1.807 |
drawn | +1.743 |
hene | +1.636 |
ringe | +1.610 |
Neg logit contributions | |
olars | -1.764 |
tons | -1.672 |
lations | -1.666 |
lear | -1.657 |
esta | -1.629 |
Token | was |
Token ID | 373 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
bid | +2.011 |
Stro | +1.986 |
drawn | +1.910 |
hene | +1.818 |
ringe | +1.772 |
Neg logit contributions | |
olars | -2.024 |
tons | -1.934 |
lations | -1.928 |
lear | -1.917 |
esta | -1.893 |
Token | roughly |
Token ID | 7323 |
Feature activation | +7.80e+00 |
Pos logit contributions | |
bid | +1.214 |
Stro | +1.199 |
drawn | +1.167 |
hene | +1.103 |
ringe | +1.077 |
Neg logit contributions | |
olars | -1.244 |
tons | -1.183 |
lations | -1.173 |
lear | -1.154 |
esta | -1.151 |
Token | a |
Token ID | 257 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Stro | +5.292 |
bid | +5.156 |
drawn | +5.041 |
hene | +4.588 |
ringe | +4.491 |
Neg logit contributions | |
olars | -5.232 |
esm | -5.113 |
esta | -5.011 |
lations | -4.987 |
lear | -4.975 |
Token | year |
Token ID | 614 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
bid | +1.442 |
Stro | +1.429 |
drawn | +1.379 |
hene | +1.302 |
ringe | +1.277 |
Neg logit contributions | |
olars | -1.541 |
lations | -1.491 |
tons | -1.488 |
esta | -1.469 |
lear | -1.459 |
Token | old |
Token ID | 1468 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
bid | +2.666 |
Stro | +2.600 |
drawn | +2.507 |
hene | +2.377 |
ringe | +2.332 |
Neg logit contributions | |
olars | -2.808 |
tons | -2.760 |
lations | -2.680 |
lear | -2.652 |
esta | -2.642 |
Token | by |
Token ID | 416 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
olars | +2.172 |
tons | +2.099 |
litter | +2.053 |
pont | +2.038 |
lations | +2.038 |
Neg logit contributions | |
bid | -2.762 |
Stro | -2.697 |
drawn | -2.655 |
hene | -2.563 |
ringe | -2.494 |
Token | then |
Token ID | 788 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
olars | +1.695 |
tons | +1.627 |
lations | +1.593 |
litter | +1.588 |
lear | +1.576 |
Neg logit contributions | |
bid | -2.060 |
Stro | -2.012 |
drawn | -1.973 |
hene | -1.895 |
ringe | -1.851 |
Token | or |
Token ID | 393 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
olars | +0.742 |
tons | +0.710 |
lations | +0.697 |
lear | +0.692 |
litter | +0.691 |
Neg logit contributions | |
bid | -0.810 |
Stro | -0.792 |
drawn | -0.775 |
hene | -0.742 |
ringe | -0.725 |
Token | crazy |
Token ID | 7165 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
olars | +3.028 |
tons | +2.939 |
litter | +2.900 |
pont | +2.874 |
lations | +2.844 |
Neg logit contributions | |
bid | -3.698 |
Stro | -3.581 |
drawn | -3.519 |
hene | -3.406 |
ringe | -3.310 |
Token | to |
Token ID | 284 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
olars | +0.783 |
tons | +0.750 |
lations | +0.735 |
lear | +0.730 |
litter | +0.729 |
Neg logit contributions | |
bid | -0.858 |
Stro | -0.838 |
drawn | -0.822 |
hene | -0.785 |
ringe | -0.768 |
Token | everyone |
Token ID | 2506 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
bid | +2.489 |
Stro | +2.451 |
drawn | +2.345 |
hene | +2.217 |
ringe | +2.190 |
Neg logit contributions | |
olars | -2.257 |
lations | -2.153 |
tons | -2.148 |
lear | -2.141 |
esta | -2.073 |
Token | else |
Token ID | 2073 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
olars | +1.333 |
tons | +1.280 |
lations | +1.251 |
litter | +1.244 |
lear | +1.236 |
Neg logit contributions | |
bid | -1.594 |
Stro | -1.558 |
drawn | -1.525 |
hene | -1.466 |
ringe | -1.431 |
Token | . |
Token ID | 13 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
bid | +0.929 |
Stro | +0.914 |
drawn | +0.880 |
hene | +0.844 |
ringe | +0.823 |
Neg logit contributions | |
olars | -0.910 |
tons | -0.869 |
lations | -0.851 |
lear | -0.842 |
esta | -0.839 |
Token |
|
Token ID | 198 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
bid | +0.044 |
Stro | +0.044 |
drawn | +0.042 |
hene | +0.041 |
ringe | +0.040 |
Neg logit contributions | |
olars | -0.032 |
tons | -0.030 |
lear | -0.029 |
lations | -0.029 |
litter | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
bid | +3.110 |
Stro | +3.029 |
drawn | +2.967 |
hene | +2.796 |
ringe | +2.705 |
Neg logit contributions | |
olars | -2.594 |
pont | -2.391 |
litter | -2.390 |
lations | -2.379 |
esta | -2.361 |
Token | For |
Token ID | 1890 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
olars | +0.452 |
tons | +0.432 |
litter | +0.425 |
lations | +0.424 |
pont | +0.423 |
Neg logit contributions | |
bid | -0.516 |
Stro | -0.500 |
drawn | -0.492 |
hene | -0.472 |
ringe | -0.460 |
Token | instance |
Token ID | 4554 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
bid | +7.126 |
Stro | +6.677 |
drawn | +6.431 |
hene | +5.941 |
inder | +5.886 |
Neg logit contributions | |
olars | -7.367 |
lear | -7.092 |
lations | -6.784 |
pont | -6.686 |
tons | -6.676 |
Token | , |
Token ID | 11 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
olars | +0.495 |
tons | +0.477 |
lations | +0.467 |
litter | +0.465 |
lear | +0.463 |
Neg logit contributions | |
bid | -0.528 |
Stro | -0.516 |
drawn | -0.503 |
hene | -0.484 |
ringe | -0.472 |
Token |
|
Token ID | 198 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
olars | +2.391 |
tons | +2.290 |
litter | +2.250 |
Soph | +2.227 |
lations | +2.226 |
Neg logit contributions | |
bid | -3.857 |
Stro | -3.740 |
drawn | -3.709 |
hene | -3.592 |
ringe | -3.515 |
Token |
|
Token ID | 198 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
olars | +0.188 |
tons | +0.180 |
lations | +0.175 |
litter | +0.175 |
pont | +0.173 |
Neg logit contributions | |
bid | -0.297 |
Stro | -0.291 |
drawn | -0.286 |
hene | -0.276 |
ringe | -0.270 |
Token | Prim |
Token ID | 23828 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
bid | +4.008 |
drawn | +3.787 |
Stro | +3.786 |
hene | +3.528 |
ringe | +3.414 |
Neg logit contributions | |
olars | -3.711 |
litter | -3.552 |
pont | -3.540 |
lations | -3.470 |
tons | -3.460 |
Token | al |
Token ID | 282 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
olars | +4.611 |
tons | +4.419 |
esta | +4.331 |
lear | +4.307 |
Soph | +4.306 |
Neg logit contributions | |
bid | -4.199 |
Stro | -4.103 |
drawn | -4.021 |
hene | -3.834 |
ringe | -3.724 |
Token | Surge |
Token ID | 46774 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
olars | +1.302 |
tons | +1.249 |
lations | +1.223 |
litter | +1.219 |
pont | +1.211 |
Neg logit contributions | |
bid | -1.517 |
Stro | -1.485 |
drawn | -1.450 |
hene | -1.395 |
ringe | -1.361 |
Token | vs |
Token ID | 3691 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
olars | +2.210 |
tons | +2.123 |
lations | +2.082 |
litter | +2.079 |
pont | +2.066 |
Neg logit contributions | |
bid | -2.583 |
Stro | -2.510 |
drawn | -2.475 |
hene | -2.383 |
ringe | -2.324 |
Token | Safe |
Token ID | 19978 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
bid | +2.679 |
Stro | +2.678 |
drawn | +2.532 |
hene | +2.423 |
ringe | +2.333 |
Neg logit contributions | |
olars | -2.317 |
tons | -2.188 |
lations | -2.170 |
lear | -2.154 |
esta | -2.153 |
Token | Passage |
Token ID | 46169 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
bid | +0.630 |
Stro | +0.618 |
drawn | +0.602 |
hene | +0.576 |
ringe | +0.564 |
Neg logit contributions | |
olars | -0.555 |
tons | -0.529 |
litter | -0.518 |
lations | -0.517 |
pont | -0.516 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
olars | +0.101 |
tons | +0.096 |
lations | +0.094 |
litter | +0.093 |
lear | +0.093 |
Neg logit contributions | |
bid | -0.128 |
Stro | -0.125 |
drawn | -0.122 |
hene | -0.117 |
ringe | -0.115 |
Token |
|
Token ID | 198 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
olars | +0.581 |
tons | +0.562 |
lations | +0.542 |
litter | +0.541 |
Soph | +0.536 |
Neg logit contributions | |
bid | -0.964 |
Stro | -0.943 |
drawn | -0.928 |
hene | -0.901 |
ringe | -0.884 |
Token | M |
Token ID | 44 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
bid | +3.479 |
Stro | +3.291 |
drawn | +3.288 |
hene | +3.064 |
ringe | +2.981 |
Neg logit contributions | |
olars | -3.203 |
litter | -3.066 |
pont | -3.055 |
tons | -3.007 |
lations | -3.000 |
Token | that |
Token ID | 326 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
bid | +0.757 |
Stro | +0.737 |
drawn | +0.722 |
hene | +0.692 |
ringe | +0.669 |
Neg logit contributions | |
olars | -0.697 |
tons | -0.666 |
lations | -0.654 |
lear | -0.650 |
litter | -0.647 |
Token | the |
Token ID | 262 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
olars | +1.395 |
tons | +1.342 |
litter | +1.309 |
lations | +1.308 |
pont | +1.297 |
Neg logit contributions | |
bid | -1.771 |
Stro | -1.729 |
drawn | -1.699 |
hene | -1.634 |
ringe | -1.598 |
Token | unique |
Token ID | 3748 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
olars | +0.021 |
tons | +0.020 |
lations | +0.020 |
lear | +0.020 |
litter | +0.020 |
Neg logit contributions | |
bid | -0.023 |
Stro | -0.023 |
drawn | -0.022 |
hene | -0.021 |
ringe | -0.021 |
Token | look |
Token ID | 804 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
bid | +0.121 |
Stro | +0.118 |
drawn | +0.115 |
hene | +0.110 |
ringe | +0.107 |
Neg logit contributions | |
olars | -0.117 |
tons | -0.112 |
lations | -0.111 |
lear | -0.110 |
esta | -0.109 |
Token | stemmed |
Token ID | 44997 |
Feature activation | +8.40e+00 |
Pos logit contributions | |
bid | +1.518 |
Stro | +1.483 |
drawn | +1.448 |
hene | +1.394 |
ringe | +1.333 |
Neg logit contributions | |
olars | -1.456 |
tons | -1.409 |
lations | -1.385 |
lear | -1.378 |
esta | -1.362 |
Token | from |
Token ID | 422 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
bid | +3.806 |
Stro | +3.777 |
drawn | +3.710 |
hene | +3.298 |
ringe | +3.233 |
Neg logit contributions | |
olars | -7.285 |
lear | -7.011 |
tons | -6.958 |
lations | -6.944 |
esm | -6.907 |
Token | the |
Token ID | 262 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
olars | +1.427 |
tons | +1.372 |
litter | +1.340 |
lations | +1.339 |
pont | +1.327 |
Neg logit contributions | |
bid | -1.800 |
Stro | -1.756 |
drawn | -1.725 |
hene | -1.661 |
ringe | -1.624 |
Token | need |
Token ID | 761 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
olars | +3.096 |
tons | +3.003 |
litter | +2.954 |
pont | +2.934 |
Soph | +2.905 |
Neg logit contributions | |
bid | -3.633 |
Stro | -3.513 |
drawn | -3.479 |
hene | -3.342 |
ringe | -3.295 |
Token | to |
Token ID | 284 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
olars | +1.152 |
tons | +1.112 |
lations | +1.087 |
litter | +1.087 |
pont | +1.078 |
Neg logit contributions | |
bid | -1.335 |
Stro | -1.304 |
drawn | -1.278 |
hene | -1.227 |
ringe | -1.200 |
Token | seamlessly |
Token ID | 33681 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
bid | +2.990 |
Stro | +2.877 |
drawn | +2.748 |
hene | +2.669 |
ringe | +2.616 |
Neg logit contributions | |
olars | -3.072 |
tons | -2.946 |
lations | -2.932 |
lear | -2.912 |
Soph | -2.832 |
Token | transition |
Token ID | 6801 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
bid | +0.183 |
Stro | +0.177 |
drawn | +0.172 |
hene | +0.165 |
ringe | +0.160 |
Neg logit contributions | |
olars | -0.234 |
tons | -0.226 |
lations | -0.223 |
lear | -0.221 |
litter | -0.220 |
Token | of |
Token ID | 286 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
bid | +0.620 |
Stro | +0.602 |
drawn | +0.588 |
hene | +0.563 |
ringe | +0.547 |
Neg logit contributions | |
olars | -0.580 |
tons | -0.558 |
lations | -0.547 |
lear | -0.542 |
esta | -0.538 |
Token | a |
Token ID | 257 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
olars | +0.829 |
tons | +0.794 |
lations | +0.779 |
lear | +0.769 |
litter | +0.765 |
Neg logit contributions | |
bid | -0.982 |
Stro | -0.959 |
drawn | -0.937 |
hene | -0.900 |
ringe | -0.877 |
Token | Deep |
Token ID | 10766 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
olars | +2.315 |
tons | +2.235 |
litter | +2.204 |
pont | +2.183 |
lations | +2.183 |
Neg logit contributions | |
bid | -2.459 |
Stro | -2.392 |
drawn | -2.352 |
hene | -2.259 |
ringe | -2.205 |
Token | water |
Token ID | 7050 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
olars | +1.148 |
tons | +1.091 |
lations | +1.059 |
litter | +1.056 |
pont | +1.046 |
Neg logit contributions | |
bid | -2.027 |
Stro | -1.986 |
drawn | -1.950 |
hene | -1.889 |
ringe | -1.846 |
Token | Horizon |
Token ID | 22776 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
bid | +1.648 |
Stro | +1.621 |
drawn | +1.493 |
hene | +1.419 |
ringe | +1.334 |
Neg logit contributions | |
olars | -3.074 |
tons | -2.905 |
lations | -2.880 |
litter | -2.820 |
pont | -2.820 |
Token | - |
Token ID | 12 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
olars | +0.355 |
tons | +0.339 |
lations | +0.333 |
lear | +0.326 |
esta | +0.325 |
Neg logit contributions | |
bid | -0.404 |
Stro | -0.393 |
drawn | -0.385 |
hene | -0.369 |
ringe | -0.358 |
Token | style |
Token ID | 7635 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
olars | +1.024 |
tons | +0.983 |
lations | +0.966 |
litter | +0.962 |
pont | +0.957 |
Neg logit contributions | |
bid | -0.953 |
Stro | -0.923 |
drawn | -0.909 |
hene | -0.863 |
ringe | -0.839 |
Token | blow |
Token ID | 6611 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
bid | +1.052 |
Stro | +1.036 |
drawn | +1.001 |
hene | +0.956 |
ringe | +0.926 |
Neg logit contributions | |
olars | -0.908 |
lations | -0.859 |
tons | -0.854 |
lear | -0.830 |
esta | -0.829 |
Token | out |
Token ID | 448 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
olars | +1.773 |
tons | +1.714 |
lations | +1.681 |
litter | +1.678 |
pont | +1.666 |
Neg logit contributions | |
bid | -1.617 |
Stro | -1.572 |
drawn | -1.539 |
hene | -1.471 |
ringe | -1.429 |
Token | late |
Token ID | 2739 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
olars | +0.369 |
tons | +0.352 |
lations | +0.347 |
lear | +0.342 |
esta | +0.340 |
Neg logit contributions | |
bid | -0.400 |
Stro | -0.389 |
drawn | -0.380 |
hene | -0.363 |
ringe | -0.354 |
Token | in |
Token ID | 287 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
olars | +0.510 |
tons | +0.489 |
lations | +0.479 |
litter | +0.476 |
lear | +0.476 |
Neg logit contributions | |
bid | -0.496 |
Stro | -0.479 |
drawn | -0.472 |
hene | -0.449 |
ringe | -0.436 |
Token | natural |
Token ID | 3288 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
olars | +1.600 |
tons | +1.549 |
litter | +1.521 |
lations | +1.511 |
pont | +1.510 |
Neg logit contributions | |
bid | -1.621 |
Stro | -1.575 |
drawn | -1.548 |
hene | -1.482 |
ringe | -1.444 |
Token | gas |
Token ID | 3623 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
olars | +2.552 |
litter | +2.475 |
tons | +2.473 |
pont | +2.458 |
lations | +2.403 |
Neg logit contributions | |
bid | -3.275 |
Stro | -3.188 |
drawn | -3.149 |
hene | -3.027 |
ringe | -2.974 |
Token | well |
Token ID | 880 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
bid | +1.919 |
Stro | +1.884 |
drawn | +1.805 |
hene | +1.733 |
ringe | +1.686 |
Neg logit contributions | |
olars | -2.129 |
tons | -2.036 |
lations | -2.029 |
lear | -1.960 |
esta | -1.951 |
Token | in |
Token ID | 287 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
olars | +3.335 |
tons | +3.272 |
litter | +3.220 |
pont | +3.191 |
lations | +3.171 |
Neg logit contributions | |
bid | -3.630 |
Stro | -3.560 |
drawn | -3.463 |
hene | -3.357 |
ringe | -3.277 |
Token | northeastern |
Token ID | 38131 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
olars | +1.239 |
tons | +1.196 |
lations | +1.172 |
litter | +1.170 |
pont | +1.162 |
Neg logit contributions | |
bid | -1.259 |
Stro | -1.225 |
drawn | -1.201 |
hene | -1.151 |
ringe | -1.121 |
Token | British |
Token ID | 3517 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
bid | +2.113 |
Stro | +2.105 |
drawn | +1.980 |
hene | +1.886 |
ringe | +1.817 |
Neg logit contributions | |
olars | -2.425 |
tons | -2.327 |
lear | -2.309 |
lations | -2.297 |
esta | -2.282 |
Token | Columbia |
Token ID | 9309 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
olars | +1.353 |
tons | +1.309 |
lations | +1.286 |
litter | +1.282 |
pont | +1.273 |
Neg logit contributions | |
bid | -1.132 |
Stro | -1.100 |
drawn | -1.075 |
hene | -1.025 |
ringe | -0.995 |
Token | , |
Token ID | 11 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
olars | +0.271 |
tons | +0.260 |
lations | +0.255 |
lear | +0.252 |
esta | +0.251 |
Neg logit contributions | |
bid | -0.289 |
Stro | -0.281 |
drawn | -0.276 |
hene | -0.266 |
ringe | -0.256 |
Token | says |
Token ID | 1139 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
olars | +2.500 |
tons | +2.404 |
litter | +2.380 |
lations | +2.349 |
pont | +2.346 |
Neg logit contributions | |
bid | -2.940 |
Stro | -2.860 |
drawn | -2.823 |
hene | -2.709 |
ringe | -2.651 |
Token | a |
Token ID | 257 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
olars | +0.838 |
tons | +0.806 |
lations | +0.788 |
litter | +0.782 |
lear | +0.779 |
Neg logit contributions | |
bid | -0.978 |
Stro | -0.956 |
drawn | -0.936 |
hene | -0.899 |
ringe | -0.877 |
Token | report |
Token ID | 989 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
bid | +0.452 |
Stro | +0.443 |
drawn | +0.429 |
hene | +0.410 |
ringe | +0.399 |
Neg logit contributions | |
olars | -0.467 |
tons | -0.452 |
lations | -0.443 |
esta | -0.436 |
lear | -0.436 |
Token | in |
Token ID | 287 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
bid | +1.901 |
Stro | +1.842 |
drawn | +1.808 |
hene | +1.723 |
ringe | +1.663 |
Neg logit contributions | |
olars | -1.851 |
tons | -1.786 |
lations | -1.757 |
lear | -1.756 |
esta | -1.731 |
Token | the |
Token ID | 262 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
olars | +0.601 |
tons | +0.574 |
lations | +0.560 |
litter | +0.558 |
lear | +0.554 |
Neg logit contributions | |
bid | -0.890 |
Stro | -0.871 |
drawn | -0.856 |
hene | -0.825 |
ringe | -0.805 |
Token | past |
Token ID | 1613 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
bid | +1.197 |
Stro | +1.171 |
drawn | +1.139 |
hene | +1.091 |
ringe | +1.058 |
Neg logit contributions | |
olars | -1.003 |
tons | -0.971 |
lations | -0.948 |
lear | -0.942 |
esta | -0.931 |
Token | seven |
Token ID | 3598 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
bid | +1.803 |
Stro | +1.765 |
drawn | +1.713 |
hene | +1.661 |
ringe | +1.605 |
Neg logit contributions | |
olars | -1.157 |
tons | -1.091 |
lations | -1.082 |
lear | -1.071 |
esta | -1.060 |
Token | days |
Token ID | 1528 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
bid | +1.179 |
Stro | +1.154 |
drawn | +1.122 |
hene | +1.065 |
ringe | +1.024 |
Neg logit contributions | |
olars | -1.324 |
tons | -1.279 |
lations | -1.256 |
lear | -1.252 |
litter | -1.251 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
bid | +2.359 |
Stro | +2.283 |
drawn | +2.244 |
hene | +2.163 |
ringe | +2.057 |
Neg logit contributions | |
olars | -2.449 |
tons | -2.379 |
lear | -2.340 |
lations | -2.319 |
esta | -2.299 |
Token | When |
Token ID | 1649 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
olars | +1.350 |
tons | +1.297 |
litter | +1.258 |
lations | +1.258 |
pont | +1.246 |
Neg logit contributions | |
bid | -2.107 |
Stro | -2.058 |
drawn | -2.030 |
hene | -1.960 |
ringe | -1.921 |
Token | a |
Token ID | 257 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
bid | +1.321 |
Stro | +1.299 |
drawn | +1.265 |
hene | +1.207 |
ringe | +1.163 |
Neg logit contributions | |
olars | -1.109 |
lations | -1.045 |
tons | -1.042 |
lear | -1.033 |
litter | -1.025 |
Token | user |
Token ID | 2836 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
bid | +0.842 |
Stro | +0.821 |
drawn | +0.799 |
hene | +0.767 |
ringe | +0.742 |
Neg logit contributions | |
olars | -0.856 |
tons | -0.826 |
lations | -0.820 |
esta | -0.803 |
litter | -0.802 |
Token | earned |
Token ID | 7366 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
olars | +0.593 |
tons | +0.568 |
lations | +0.560 |
litter | +0.556 |
pont | +0.551 |
Neg logit contributions | |
bid | -0.638 |
Stro | -0.622 |
drawn | -0.609 |
hene | -0.583 |
ringe | -0.566 |
Token | points |
Token ID | 2173 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
olars | +2.415 |
tons | +2.340 |
litter | +2.279 |
lations | +2.277 |
pont | +2.260 |
Neg logit contributions | |
bid | -2.840 |
Stro | -2.764 |
drawn | -2.712 |
hene | -2.616 |
ringe | -2.569 |
Token | to |
Token ID | 284 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
bid | +0.878 |
Stro | +0.870 |
drawn | +0.835 |
hene | +0.796 |
ringe | +0.777 |
Neg logit contributions | |
olars | -0.908 |
tons | -0.876 |
lations | -0.860 |
lear | -0.848 |
esta | -0.843 |
Token | the |
Token ID | 262 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
olars | +0.276 |
tons | +0.267 |
lations | +0.261 |
lear | +0.257 |
litter | +0.253 |
Neg logit contributions | |
bid | -0.311 |
Stro | -0.308 |
drawn | -0.296 |
hene | -0.286 |
ringe | -0.279 |
Token | pen |
Token ID | 3112 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
olars | +1.527 |
tons | +1.479 |
lations | +1.453 |
litter | +1.449 |
lear | +1.440 |
Neg logit contributions | |
bid | -1.220 |
Stro | -1.186 |
drawn | -1.156 |
hene | -1.102 |
ringe | -1.069 |
Token | last |
Token ID | 938 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
bid | +0.988 |
Stro | +0.962 |
drawn | +0.944 |
hene | +0.901 |
ringe | +0.879 |
Neg logit contributions | |
olars | -0.959 |
tons | -0.926 |
lations | -0.902 |
lear | -0.897 |
esta | -0.895 |
Token | year |
Token ID | 614 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
olars | +3.210 |
litter | +3.114 |
Soph | +3.038 |
pont | +3.000 |
tons | +2.983 |
Neg logit contributions | |
bid | -6.549 |
Stro | -6.409 |
drawn | -6.393 |
hene | -6.154 |
ringe | -6.079 |
Token | , |
Token ID | 11 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
bid | +0.945 |
Stro | +0.915 |
drawn | +0.895 |
hene | +0.859 |
ringe | +0.833 |
Neg logit contributions | |
olars | -0.937 |
tons | -0.909 |
lear | -0.879 |
lations | -0.878 |
esta | -0.876 |
Token | am |
Token ID | 716 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
olars | +1.067 |
tons | +1.029 |
lations | +1.006 |
litter | +1.000 |
lear | +0.996 |
Neg logit contributions | |
bid | -1.201 |
Stro | -1.173 |
drawn | -1.147 |
hene | -1.102 |
ringe | -1.075 |
Token | assing |
Token ID | 19696 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
bid | +0.279 |
Stro | +0.266 |
drawn | +0.251 |
hene | +0.237 |
ringe | +0.225 |
Neg logit contributions | |
olars | -0.633 |
tons | -0.621 |
lations | -0.613 |
litter | -0.609 |
lear | -0.606 |
Token | a |
Token ID | 257 |
Feature activation | -7.02e+00 |
Pos logit contributions | |
olars | +3.223 |
tons | +3.115 |
litter | +3.087 |
pont | +3.041 |
Soph | +3.040 |
Neg logit contributions | |
bid | -4.192 |
Stro | -4.037 |
drawn | -4.008 |
hene | -3.908 |
ringe | -3.810 |
Token | 2 |
Token ID | 362 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
olars | +4.292 |
litter | +4.160 |
tons | +4.086 |
Soph | +4.078 |
pont | +4.062 |
Neg logit contributions | |
bid | -5.231 |
drawn | -5.086 |
Stro | -5.073 |
hene | -4.918 |
ringe | -4.780 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
olars | +2.288 |
tons | +2.194 |
litter | +2.149 |
lations | +2.145 |
pont | +2.129 |
Neg logit contributions | |
bid | -2.653 |
Stro | -2.589 |
drawn | -2.554 |
hene | -2.449 |
ringe | -2.387 |
Token | than |
Token ID | 621 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
olars | +0.044 |
tons | +0.043 |
lations | +0.042 |
lear | +0.042 |
litter | +0.042 |
Neg logit contributions | |
bid | -0.030 |
Stro | -0.029 |
drawn | -0.028 |
hene | -0.026 |
ringe | -0.026 |
Token | 10 |
Token ID | 838 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
olars | +1.229 |
tons | +1.179 |
lations | +1.152 |
litter | +1.148 |
pont | +1.138 |
Neg logit contributions | |
bid | -1.660 |
Stro | -1.623 |
drawn | -1.594 |
hene | -1.536 |
ringe | -1.500 |
Token | years |
Token ID | 812 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
olars | +0.516 |
tons | +0.497 |
lations | +0.490 |
litter | +0.486 |
lear | +0.485 |
Neg logit contributions | |
bid | -0.498 |
Stro | -0.484 |
drawn | -0.472 |
hene | -0.454 |
ringe | -0.440 |
Token | built |
Token ID | 3170 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
olars | +0.880 |
tons | +0.843 |
lations | +0.828 |
lear | +0.821 |
litter | +0.820 |
Neg logit contributions | |
bid | -1.034 |
Stro | -1.005 |
drawn | -0.984 |
hene | -0.948 |
ringe | -0.925 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
litter | +6.492 |
olars | +6.432 |
tons | +6.353 |
pont | +6.220 |
Soph | +6.191 |
Neg logit contributions | |
bid | -9.148 |
Stro | -8.868 |
drawn | -8.808 |
hene | -8.343 |
ringe | -8.335 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
litter | +7.954 |
tons | +7.761 |
olars | +7.699 |
pont | +7.627 |
Soph | +7.623 |
Neg logit contributions | |
bid | -10.301 |
drawn | -9.688 |
hene | -9.671 |
Stro | -9.654 |
ringe | -9.436 |
Token | ratio |
Token ID | 8064 |
Feature activation | -6.61e+00 |
Pos logit contributions | |
litter | +8.208 |
olars | +8.073 |
pont | +7.967 |
Soph | +7.954 |
tons | +7.891 |
Neg logit contributions | |
bid | -9.703 |
drawn | -9.026 |
hene | -8.979 |
Stro | -8.925 |
ringe | -8.824 |
Token | stock |
Token ID | 4283 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
olars | +3.939 |
tons | +3.817 |
litter | +3.779 |
pont | +3.728 |
lations | +3.699 |
Neg logit contributions | |
bid | -5.081 |
Stro | -4.927 |
drawn | -4.896 |
hene | -4.727 |
ringe | -4.633 |
Token | / |
Token ID | 14 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
tons | +7.295 |
olars | +7.221 |
lations | +7.045 |
pont | +7.005 |
litter | +6.970 |
Neg logit contributions | |
bid | -7.443 |
Stro | -7.234 |
drawn | -7.048 |
ringe | -6.832 |
hene | -6.734 |
Token | ( |
Token ID | 357 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
olars | +2.754 |
tons | +2.685 |
litter | +2.607 |
lations | +2.603 |
lear | +2.589 |
Neg logit contributions | |
bid | -2.741 |
Stro | -2.691 |
drawn | -2.624 |
hene | -2.513 |
ringe | -2.450 |
Token | year |
Token ID | 1941 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
olars | +0.800 |
tons | +0.768 |
lations | +0.759 |
litter | +0.756 |
pont | +0.752 |
Neg logit contributions | |
bid | -0.757 |
Stro | -0.732 |
drawn | -0.720 |
hene | -0.686 |
ringe | -0.668 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
bid | +0.363 |
Stro | +0.353 |
drawn | +0.344 |
hene | +0.330 |
ringe | +0.321 |
Neg logit contributions | |
olars | -0.350 |
tons | -0.338 |
lations | -0.332 |
lear | -0.331 |
litter | -0.328 |
Token | boosting |
Token ID | 27611 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
olars | +1.012 |
tons | +0.971 |
lations | +0.950 |
litter | +0.947 |
pont | +0.939 |
Neg logit contributions | |
bid | -1.276 |
Stro | -1.245 |
drawn | -1.222 |
hene | -1.175 |
ringe | -1.148 |
Token | the |
Token ID | 262 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
olars | +0.607 |
tons | +0.585 |
lations | +0.571 |
litter | +0.569 |
pont | +0.565 |
Neg logit contributions | |
bid | -0.701 |
Stro | -0.683 |
drawn | -0.670 |
hene | -0.642 |
ringe | -0.626 |
Token | value |
Token ID | 1988 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
bid | +0.278 |
Stro | +0.271 |
drawn | +0.264 |
hene | +0.254 |
ringe | +0.248 |
Neg logit contributions | |
olars | -0.232 |
tons | -0.223 |
lations | -0.219 |
litter | -0.216 |
lear | -0.216 |
Token | of |
Token ID | 286 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
olars | +1.391 |
tons | +1.336 |
litter | +1.307 |
lations | +1.307 |
pont | +1.296 |
Neg logit contributions | |
bid | -1.697 |
Stro | -1.658 |
drawn | -1.629 |
hene | -1.568 |
ringe | -1.531 |
Token | real |
Token ID | 1103 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
olars | +2.372 |
tons | +2.285 |
litter | +2.249 |
pont | +2.233 |
lations | +2.230 |
Neg logit contributions | |
bid | -2.756 |
Stro | -2.687 |
drawn | -2.646 |
hene | -2.558 |
ringe | -2.497 |
Token | estate |
Token ID | 7964 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
olars | +4.141 |
tons | +3.899 |
lear | +3.634 |
pont | +3.619 |
litter | +3.553 |
Neg logit contributions | |
Stro | -12.227 |
bid | -12.060 |
drawn | -11.852 |
hene | -11.615 |
ringe | -11.594 |
Token | holdings |
Token ID | 27572 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
bid | +0.239 |
Stro | +0.232 |
drawn | +0.226 |
hene | +0.216 |
ringe | +0.211 |
Neg logit contributions | |
olars | -0.216 |
tons | -0.207 |
lations | -0.205 |
lear | -0.202 |
litter | -0.201 |
Token | , |
Token ID | 11 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
bid | +1.306 |
Stro | +1.264 |
drawn | +1.224 |
hene | +1.181 |
ringe | +1.136 |
Neg logit contributions | |
olars | -1.274 |
tons | -1.217 |
lations | -1.208 |
lear | -1.204 |
esta | -1.189 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
bid | +2.315 |
Stro | +2.223 |
drawn | +2.163 |
hene | +2.044 |
ringe | +1.986 |
Neg logit contributions | |
olars | -2.268 |
tons | -2.166 |
lations | -2.155 |
lear | -2.125 |
esta | -2.119 |
Token | high |
Token ID | 1029 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
olars | +0.858 |
tons | +0.824 |
lations | +0.806 |
litter | +0.804 |
lear | +0.797 |
Neg logit contributions | |
bid | -1.057 |
Stro | -1.032 |
drawn | -1.011 |
hene | -0.972 |
ringe | -0.949 |
Token | t |
Token ID | 83 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
olars | +0.654 |
tons | +0.626 |
lations | +0.612 |
litter | +0.612 |
pont | +0.606 |
Neg logit contributions | |
bid | -0.851 |
Stro | -0.829 |
drawn | -0.814 |
hene | -0.782 |
ringe | -0.768 |
Token | want |
Token ID | 765 |
Feature activation | -6.55e+00 |
Pos logit contributions | |
bid | +2.083 |
Stro | +2.013 |
drawn | +1.899 |
ringe | +1.836 |
hene | +1.821 |
Neg logit contributions | |
olars | -2.248 |
tons | -2.207 |
lations | -2.144 |
lear | -2.141 |
esm | -2.090 |
Token | to |
Token ID | 284 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
olars | +3.825 |
tons | +3.700 |
litter | +3.645 |
pont | +3.637 |
lations | +3.608 |
Neg logit contributions | |
bid | -5.095 |
Stro | -4.993 |
drawn | -4.926 |
hene | -4.788 |
ringe | -4.647 |
Token | hear |
Token ID | 3285 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
olars | +2.407 |
litter | +2.307 |
pont | +2.302 |
tons | +2.294 |
lations | +2.258 |
Neg logit contributions | |
bid | -2.743 |
Stro | -2.696 |
drawn | -2.670 |
hene | -2.563 |
ringe | -2.473 |
Token | anything |
Token ID | 1997 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
olars | +0.848 |
tons | +0.813 |
lations | +0.793 |
litter | +0.791 |
lear | +0.785 |
Neg logit contributions | |
bid | -1.138 |
Stro | -1.113 |
drawn | -1.092 |
hene | -1.051 |
ringe | -1.028 |
Token | from |
Token ID | 422 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
olars | +2.104 |
tons | +2.036 |
litter | +2.006 |
lations | +1.997 |
pont | +1.988 |
Neg logit contributions | |
bid | -2.479 |
Stro | -2.404 |
drawn | -2.372 |
hene | -2.290 |
ringe | -2.223 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -7.03e+00 |
Pos logit contributions | |
olars | +6.355 |
litter | +6.220 |
Soph | +6.187 |
tons | +6.184 |
pont | +6.152 |
Neg logit contributions | |
bid | -9.361 |
drawn | -9.031 |
hene | -8.959 |
Stro | -8.881 |
ringe | -8.441 |
Token | supporters |
Token ID | 5941 |
Feature activation | -8.99e+00 |
Pos logit contributions | |
olars | +4.142 |
tons | +4.049 |
litter | +3.949 |
lations | +3.934 |
pont | +3.912 |
Neg logit contributions | |
bid | -5.438 |
Stro | -5.310 |
drawn | -5.285 |
hene | -5.085 |
ringe | -4.894 |
Token | about |
Token ID | 546 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
olars | +4.811 |
litter | +4.745 |
pont | +4.689 |
tons | +4.665 |
lations | +4.586 |
Neg logit contributions | |
bid | -7.264 |
Stro | -7.060 |
drawn | -6.949 |
hene | -6.850 |
ringe | -6.571 |
Token | sexism |
Token ID | 24953 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
bid | +0.390 |
Stro | +0.379 |
drawn | +0.368 |
hene | +0.349 |
ringe | +0.344 |
Neg logit contributions | |
olars | -0.377 |
tons | -0.358 |
lear | -0.354 |
lations | -0.353 |
esta | -0.349 |
Token | and |
Token ID | 290 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
bid | +0.113 |
Stro | +0.109 |
drawn | +0.107 |
hene | +0.102 |
ringe | +0.100 |
Neg logit contributions | |
olars | -0.109 |
tons | -0.105 |
lear | -0.104 |
lations | -0.102 |
litter | -0.102 |
Token | also |
Token ID | 635 |
Feature activation | -7.05e+00 |
Pos logit contributions | |
olars | +4.800 |
pont | +4.633 |
tons | +4.616 |
litter | +4.612 |
lations | +4.430 |
Neg logit contributions | |
bid | -6.069 |
Stro | -5.947 |
drawn | -5.888 |
hene | -5.738 |
ringe | -5.616 |
Token | thinks |
Token ID | 6834 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
olars | +4.461 |
litter | +4.315 |
pont | +4.277 |
tons | +4.269 |
lations | +4.137 |
Neg logit contributions | |
bid | -5.162 |
Stro | -5.055 |
drawn | -4.995 |
hene | -4.846 |
ringe | -4.736 |
Token | that |
Token ID | 326 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
olars | +1.303 |
tons | +1.255 |
litter | +1.227 |
lations | +1.225 |
pont | +1.217 |
Neg logit contributions | |
bid | -1.591 |
Stro | -1.548 |
drawn | -1.523 |
hene | -1.467 |
ringe | -1.433 |
Token | there |
Token ID | 612 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
olars | +0.818 |
tons | +0.787 |
lations | +0.770 |
litter | +0.768 |
pont | +0.762 |
Neg logit contributions | |
bid | -0.967 |
Stro | -0.944 |
drawn | -0.926 |
hene | -0.890 |
ringe | -0.868 |
Token | is |
Token ID | 318 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
olars | +2.781 |
tons | +2.670 |
litter | +2.624 |
lations | +2.617 |
pont | +2.597 |
Neg logit contributions | |
bid | -3.237 |
Stro | -3.162 |
drawn | -3.113 |
hene | -2.983 |
ringe | -2.908 |
Token | something |
Token ID | 1223 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
olars | +4.003 |
tons | +3.925 |
litter | +3.893 |
pont | +3.827 |
Soph | +3.812 |
Neg logit contributions | |
bid | -4.902 |
Stro | -4.779 |
drawn | -4.653 |
hene | -4.505 |
ringe | -4.408 |
Token | worth |
Token ID | 2861 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
Soph | +6.531 |
litter | +6.511 |
tons | +6.448 |
pont | +6.400 |
olars | +6.361 |
Neg logit contributions | |
bid | -8.378 |
Stro | -8.091 |
drawn | -8.034 |
hene | -7.795 |
ringe | -7.661 |
Token | saving |
Token ID | 8914 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
olars | +3.766 |
pont | +3.625 |
litter | +3.621 |
tons | +3.592 |
lear | +3.539 |
Neg logit contributions | |
bid | -4.572 |
Stro | -4.487 |
drawn | -4.372 |
hene | -4.239 |
ringe | -4.162 |
Token | in |
Token ID | 287 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
olars | +1.250 |
tons | +1.206 |
lations | +1.182 |
litter | +1.180 |
pont | +1.171 |
Neg logit contributions | |
bid | -1.256 |
Stro | -1.223 |
drawn | -1.198 |
hene | -1.148 |
ringe | -1.117 |
Token | all |
Token ID | 477 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
olars | +3.256 |
tons | +3.131 |
litter | +3.096 |
Soph | +3.083 |
pont | +3.060 |
Neg logit contributions | |
bid | -3.985 |
Stro | -3.824 |
drawn | -3.797 |
hene | -3.672 |
ringe | -3.607 |
Token | of |
Token ID | 286 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
bid | +1.604 |
Stro | +1.573 |
drawn | +1.540 |
hene | +1.466 |
ringe | +1.418 |
Neg logit contributions | |
olars | -1.440 |
tons | -1.389 |
lations | -1.353 |
lear | -1.345 |
litter | -1.339 |
Token | via |
Token ID | 2884 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
bid | +3.197 |
Stro | +3.193 |
drawn | +3.022 |
hene | +2.967 |
ringe | +2.829 |
Neg logit contributions | |
olars | -3.256 |
tons | -3.074 |
lations | -3.051 |
lear | -3.043 |
esta | -2.953 |
Token | AP |
Token ID | 3486 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
bid | +0.417 |
Stro | +0.412 |
drawn | +0.404 |
hene | +0.387 |
ringe | +0.376 |
Neg logit contributions | |
olars | -0.323 |
tons | -0.309 |
lations | -0.300 |
lear | -0.298 |
litter | -0.298 |
Token | A |
Token ID | 317 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
olars | +0.750 |
tons | +0.715 |
lations | +0.702 |
lear | +0.695 |
litter | +0.694 |
Neg logit contributions | |
bid | -0.954 |
Stro | -0.940 |
drawn | -0.918 |
hene | -0.883 |
ringe | -0.860 |
Token | woman |
Token ID | 2415 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
olars | +0.798 |
tons | +0.767 |
lations | +0.754 |
lear | +0.743 |
litter | +0.742 |
Neg logit contributions | |
bid | -0.886 |
Stro | -0.866 |
drawn | -0.851 |
hene | -0.815 |
ringe | -0.794 |
Token | and |
Token ID | 290 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
olars | +0.270 |
tons | +0.259 |
lations | +0.255 |
lear | +0.253 |
esta | +0.250 |
Neg logit contributions | |
bid | -0.301 |
Stro | -0.294 |
drawn | -0.288 |
hene | -0.276 |
ringe | -0.267 |
Token | children |
Token ID | 1751 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
olars | +0.703 |
tons | +0.674 |
lations | +0.663 |
lear | +0.657 |
esta | +0.651 |
Neg logit contributions | |
bid | -0.779 |
Stro | -0.762 |
drawn | -0.749 |
hene | -0.713 |
ringe | -0.699 |
Token | are |
Token ID | 389 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
litter | +7.069 |
pont | +6.758 |
tons | +6.733 |
olars | +6.705 |
esta | +6.655 |
Neg logit contributions | |
bid | -8.471 |
Stro | -8.374 |
drawn | -8.234 |
hene | -7.915 |
ringe | -7.753 |
Token | rescued |
Token ID | 19868 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
olars | +3.783 |
litter | +3.677 |
tons | +3.660 |
pont | +3.599 |
lations | +3.565 |
Neg logit contributions | |
bid | -5.171 |
Stro | -5.047 |
drawn | -4.944 |
hene | -4.796 |
ringe | -4.717 |
Token | by |
Token ID | 416 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
olars | +3.556 |
tons | +3.448 |
litter | +3.438 |
pont | +3.396 |
lations | +3.379 |
Neg logit contributions | |
bid | -3.466 |
Stro | -3.382 |
drawn | -3.274 |
hene | -3.168 |
ringe | -3.107 |
Token | boat |
Token ID | 8848 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
olars | +0.731 |
tons | +0.702 |
lations | +0.694 |
lear | +0.683 |
esta | +0.677 |
Neg logit contributions | |
bid | -0.854 |
Stro | -0.842 |
drawn | -0.824 |
hene | -0.784 |
ringe | -0.766 |
Token | in |
Token ID | 287 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
olars | +1.729 |
tons | +1.670 |
lations | +1.637 |
litter | +1.635 |
pont | +1.623 |
Neg logit contributions | |
bid | -1.622 |
Stro | -1.578 |
drawn | -1.545 |
hene | -1.478 |
ringe | -1.437 |