Token | sale |
Token ID | 5466 |
Feature activation | -5.24e-03 |
Pos logit contributions | |
ocrine | +0.587 |
ary | +0.551 |
atory | +0.523 |
idia | +0.499 |
gery | +0.495 |
Neg logit contributions | |
én | -0.544 |
everal | -0.521 |
hate | -0.476 |
DEM | -0.468 |
friend | -0.461 |
Token | in |
Token ID | 287 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
én | +0.004 |
everal | +0.004 |
hate | +0.003 |
DEM | +0.003 |
friend | +0.003 |
Neg logit contributions | |
ocrine | -0.004 |
ary | -0.004 |
atory | -0.004 |
gery | -0.004 |
idia | -0.004 |
Token | nearby |
Token ID | 6716 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
én | +0.669 |
everal | +0.640 |
hate | +0.586 |
DEM | +0.573 |
friend | +0.568 |
Neg logit contributions | |
ocrine | -0.730 |
ary | -0.685 |
atory | -0.653 |
gery | -0.623 |
idia | -0.617 |
Token | gift |
Token ID | 6979 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
én | +1.593 |
everal | +1.487 |
hate | +1.352 |
DEM | +1.310 |
friend | +1.310 |
Neg logit contributions | |
ocrine | -2.453 |
ary | -2.323 |
atory | -2.225 |
gery | -2.138 |
idia | -2.100 |
Token | shops |
Token ID | 12437 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
én | +2.810 |
everal | +2.433 |
hate | +2.232 |
friend | +2.196 |
fw | +2.158 |
Neg logit contributions | |
ocrine | -6.844 |
ary | -6.456 |
atory | -6.150 |
idia | -6.064 |
gery | -6.016 |
Token | .[ |
Token ID | 3693 |
Feature activation | +2.07e+01 |
Pos logit contributions | |
ocrine | +0.375 |
ary | +0.352 |
atory | +0.336 |
gery | +0.321 |
idia | +0.321 |
Neg logit contributions | |
én | -0.336 |
everal | -0.321 |
hate | -0.295 |
DEM | -0.290 |
friend | -0.284 |
Token | 158 |
Token ID | 21273 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ocrine | +10.594 |
ary | +10.300 |
atory | +9.397 |
ph | +8.787 |
void | +8.762 |
Neg logit contributions | |
everal | -16.366 |
én | -15.628 |
orno | -14.749 |
haps | -14.307 |
hate | -14.273 |
Token | ] |
Token ID | 60 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
ocrine | +1.346 |
ary | +1.281 |
atory | +1.218 |
ph | +1.157 |
idia | +1.146 |
Neg logit contributions | |
én | -1.189 |
everal | -1.151 |
hate | -1.042 |
DEM | -1.040 |
friend | -1.009 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ocrine | +0.518 |
ary | +0.486 |
atory | +0.463 |
idia | +0.446 |
gery | +0.444 |
Neg logit contributions | |
én | -0.452 |
everal | -0.423 |
hate | -0.394 |
DEM | -0.388 |
friend | -0.384 |
Token |
|
Token ID | 198 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
én | +0.918 |
hate | +0.809 |
friend | +0.795 |
DEM | +0.791 |
fw | +0.760 |
Neg logit contributions | |
ocrine | -1.123 |
ary | -1.030 |
atory | -0.999 |
idia | -0.973 |
gery | -0.958 |
Token | See |
Token ID | 6214 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
én | +0.486 |
everal | +0.448 |
hate | +0.426 |
DEM | +0.421 |
friend | +0.410 |
Neg logit contributions | |
ocrine | -0.708 |
ary | -0.663 |
atory | -0.640 |
gery | -0.615 |
idia | -0.615 |
Token | shows |
Token ID | 2523 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ocrine | +0.519 |
ary | +0.482 |
atory | +0.464 |
gery | +0.443 |
idia | +0.439 |
Neg logit contributions | |
én | -0.470 |
everal | -0.448 |
hate | -0.416 |
DEM | -0.410 |
friend | -0.398 |
Token | in |
Token ID | 287 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
ocrine | +1.543 |
ary | +1.453 |
atory | +1.384 |
gery | +1.314 |
idia | +1.306 |
Neg logit contributions | |
én | -1.487 |
everal | -1.432 |
hate | -1.316 |
DEM | -1.297 |
friend | -1.271 |
Token | order |
Token ID | 1502 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
én | +0.412 |
everal | +0.391 |
hate | +0.364 |
DEM | +0.354 |
friend | +0.350 |
Neg logit contributions | |
ocrine | -0.461 |
ary | -0.432 |
atory | -0.410 |
gery | -0.389 |
ph | -0.386 |
Token | to |
Token ID | 284 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
én | +0.072 |
everal | +0.070 |
hate | +0.064 |
DEM | +0.064 |
friend | +0.062 |
Neg logit contributions | |
ocrine | -0.065 |
ary | -0.062 |
atory | -0.058 |
gery | -0.055 |
ph | -0.054 |
Token | win |
Token ID | 1592 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
én | +1.157 |
everal | +1.068 |
hate | +1.017 |
friend | +0.988 |
DEM | +0.978 |
Neg logit contributions | |
ocrine | -1.205 |
ary | -1.105 |
atory | -1.056 |
idia | -1.006 |
gery | -1.000 |
Token | .[ |
Token ID | 3693 |
Feature activation | +2.01e+01 |
Pos logit contributions | |
én | +3.626 |
everal | +3.350 |
hate | +3.032 |
friend | +3.011 |
DEM | +3.009 |
Neg logit contributions | |
ocrine | -4.513 |
ary | -4.209 |
atory | -4.012 |
idia | -3.903 |
gery | -3.844 |
Token | 156 |
Token ID | 21599 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ocrine | +10.552 |
ary | +10.544 |
atory | +9.435 |
ph | +9.243 |
idia | +8.691 |
Neg logit contributions | |
everal | -15.806 |
én | -15.275 |
orno | -14.006 |
DEM | -13.771 |
gobl | -13.719 |
Token | ] |
Token ID | 60 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
én | +1.817 |
everal | +1.755 |
hate | +1.585 |
DEM | +1.556 |
friend | +1.520 |
Neg logit contributions | |
ocrine | -2.378 |
ary | -2.261 |
atory | -2.160 |
gery | -2.067 |
idia | -2.059 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ocrine | +1.850 |
ary | +1.741 |
atory | +1.663 |
gery | +1.586 |
idia | +1.583 |
Neg logit contributions | |
én | -1.603 |
everal | -1.520 |
hate | -1.403 |
DEM | -1.388 |
friend | -1.361 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
én | +0.896 |
hate | +0.789 |
friend | +0.776 |
DEM | +0.774 |
fw | +0.742 |
Neg logit contributions | |
ocrine | -1.097 |
ary | -1.007 |
atory | -0.977 |
idia | -0.951 |
gery | -0.935 |
Token | Sound |
Token ID | 21369 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
ocrine | +0.019 |
ary | +0.018 |
atory | +0.018 |
gery | +0.017 |
idia | +0.017 |
Neg logit contributions | |
én | -0.013 |
everal | -0.012 |
hate | -0.011 |
DEM | -0.011 |
friend | -0.011 |
Token | time |
Token ID | 640 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
én | +2.075 |
everal | +1.876 |
hate | +1.690 |
DEM | +1.643 |
friend | +1.536 |
Neg logit contributions | |
ocrine | -4.417 |
ary | -4.148 |
gery | -3.990 |
atory | -3.976 |
idia | -3.871 |
Token | , |
Token ID | 11 |
Feature activation | -6.77e+00 |
Pos logit contributions | |
én | +2.758 |
everal | +2.568 |
hate | +2.455 |
DEM | +2.320 |
friend | +2.298 |
Neg logit contributions | |
ocrine | -3.354 |
ary | -3.082 |
atory | -2.987 |
idia | -2.908 |
gery | -2.872 |
Token | an |
Token ID | 281 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
én | +4.654 |
everal | +4.349 |
hate | +4.232 |
DEM | +4.100 |
friend | +4.059 |
Neg logit contributions | |
ocrine | -5.286 |
ary | -4.845 |
atory | -4.557 |
idia | -4.534 |
gery | -4.451 |
Token | F |
Token ID | 376 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
én | +0.265 |
everal | +0.249 |
hate | +0.234 |
DEM | +0.231 |
friend | +0.224 |
Neg logit contributions | |
ocrine | -0.266 |
ary | -0.249 |
atory | -0.235 |
ph | -0.225 |
gery | -0.225 |
Token | - |
Token ID | 12 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
én | +0.851 |
everal | +0.795 |
hate | +0.731 |
DEM | +0.721 |
friend | +0.709 |
Neg logit contributions | |
ocrine | -0.948 |
ary | -0.881 |
atory | -0.837 |
gery | -0.810 |
idia | -0.800 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.96e+01 |
Pos logit contributions | |
én | +2.186 |
everal | +1.988 |
hate | +1.899 |
DEM | +1.883 |
friend | +1.834 |
Neg logit contributions | |
ocrine | -2.836 |
ary | -2.602 |
atory | -2.527 |
gery | -2.519 |
idia | -2.466 |
Token | 155 |
Token ID | 18742 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
ocrine | +9.859 |
ary | +9.562 |
atory | +8.412 |
ph | +8.375 |
idia | +7.707 |
Neg logit contributions | |
everal | -16.091 |
én | -15.495 |
orno | -14.510 |
DEM | -14.490 |
hate | -14.139 |
Token | ] |
Token ID | 60 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
én | +0.678 |
everal | +0.656 |
hate | +0.593 |
DEM | +0.588 |
friend | +0.572 |
Neg logit contributions | |
ocrine | -0.825 |
ary | -0.786 |
atory | -0.749 |
gery | -0.709 |
idia | -0.709 |
Token | An |
Token ID | 1052 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ocrine | +1.574 |
ary | +1.482 |
atory | +1.416 |
gery | +1.350 |
idia | +1.346 |
Neg logit contributions | |
én | -1.405 |
everal | -1.340 |
hate | -1.238 |
DEM | -1.221 |
friend | -1.195 |
Token | ' |
Token ID | 705 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
ocrine | +1.023 |
ary | +0.960 |
atory | +0.917 |
gery | +0.874 |
idia | +0.866 |
Neg logit contributions | |
én | -0.908 |
everal | -0.861 |
hate | -0.795 |
DEM | -0.782 |
friend | -0.764 |
Token | inter |
Token ID | 3849 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
én | +2.167 |
everal | +1.923 |
hate | +1.913 |
DEM | +1.839 |
friend | +1.805 |
Neg logit contributions | |
ocrine | -3.185 |
ary | -2.973 |
atory | -2.855 |
gery | -2.794 |
idia | -2.722 |
Token | planet |
Token ID | 5440 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ocrine | +1.290 |
ary | +1.218 |
atory | +1.156 |
gery | +1.098 |
idia | +1.092 |
Neg logit contributions | |
én | -1.234 |
everal | -1.196 |
hate | -1.094 |
DEM | -1.079 |
friend | -1.056 |
Token | Venus |
Token ID | 21094 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
ocrine | +1.376 |
ary | +1.288 |
atory | +1.218 |
gery | +1.149 |
idia | +1.142 |
Neg logit contributions | |
én | -1.658 |
everal | -1.613 |
hate | -1.490 |
DEM | -1.473 |
friend | -1.444 |
Token | in |
Token ID | 287 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
ocrine | +2.300 |
ary | +2.176 |
atory | +2.058 |
gery | +1.944 |
idia | +1.942 |
Neg logit contributions | |
én | -2.411 |
everal | -2.344 |
hate | -2.148 |
DEM | -2.123 |
friend | -2.076 |
Token | her |
Token ID | 607 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
ocrine | +0.492 |
ary | +0.461 |
atory | +0.438 |
gery | +0.419 |
idia | +0.413 |
Neg logit contributions | |
én | -0.466 |
everal | -0.452 |
hate | -0.416 |
DEM | -0.409 |
friend | -0.403 |
Token | honor |
Token ID | 7522 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ocrine | +0.615 |
ary | +0.572 |
atory | +0.547 |
gery | +0.527 |
idia | +0.521 |
Neg logit contributions | |
én | -0.571 |
everal | -0.548 |
hate | -0.505 |
DEM | -0.496 |
friend | -0.492 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.92e+01 |
Pos logit contributions | |
én | +1.370 |
everal | +1.302 |
hate | +1.191 |
DEM | +1.181 |
friend | +1.156 |
Neg logit contributions | |
ocrine | -1.595 |
ary | -1.464 |
atory | -1.403 |
gery | -1.362 |
idia | -1.359 |
Token | 55 |
Token ID | 2816 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
ocrine | +9.134 |
ary | +8.609 |
ph | +8.176 |
atory | +7.791 |
idia | +7.189 |
Neg logit contributions | |
everal | -16.453 |
én | -16.011 |
orno | -14.918 |
resil | -14.467 |
hate | -14.448 |
Token | ] |
Token ID | 60 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
én | +2.254 |
everal | +2.173 |
hate | +1.963 |
DEM | +1.922 |
friend | +1.881 |
Neg logit contributions | |
ocrine | -3.019 |
ary | -2.866 |
atory | -2.736 |
gery | -2.631 |
idia | -2.618 |
Token |
|
Token ID | 198 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
ocrine | +3.328 |
ary | +3.153 |
atory | +2.990 |
gery | +2.829 |
idia | +2.820 |
Neg logit contributions | |
én | -3.289 |
everal | -3.209 |
hate | -2.921 |
DEM | -2.886 |
friend | -2.813 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ocrine | +0.590 |
ary | +0.549 |
atory | +0.527 |
idia | +0.505 |
gery | +0.502 |
Neg logit contributions | |
én | -0.539 |
everal | -0.484 |
hate | -0.477 |
DEM | -0.470 |
friend | -0.465 |
Token | In |
Token ID | 818 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ocrine | +1.906 |
ary | +1.806 |
atory | +1.734 |
gery | +1.664 |
idia | +1.658 |
Neg logit contributions | |
én | -1.320 |
everal | -1.252 |
hate | -1.144 |
DEM | -1.131 |
friend | -1.101 |
Token | playing |
Token ID | 2712 |
Feature activation | -8.31e+00 |
Pos logit contributions | |
ocrine | +1.628 |
ary | +1.525 |
atory | +1.453 |
gery | +1.378 |
idia | +1.378 |
Neg logit contributions | |
én | -1.560 |
everal | -1.505 |
hate | -1.382 |
DEM | -1.362 |
friend | -1.335 |
Token | it |
Token ID | 340 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
én | +5.237 |
everal | +4.815 |
hate | +4.469 |
DEM | +4.436 |
Thieves | +4.387 |
Neg logit contributions | |
ocrine | -7.101 |
ary | -6.496 |
atory | -6.256 |
gery | -6.107 |
idia | -5.982 |
Token | for |
Token ID | 329 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
én | +2.386 |
everal | +2.233 |
hate | +2.037 |
DEM | +1.996 |
friend | +1.988 |
Neg logit contributions | |
ocrine | -3.385 |
ary | -3.157 |
atory | -3.054 |
idia | -2.951 |
gery | -2.917 |
Token | 20 |
Token ID | 1160 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
én | +3.765 |
everal | +3.520 |
hate | +3.292 |
friend | +3.217 |
DEM | +3.213 |
Neg logit contributions | |
ocrine | -5.264 |
ary | -4.759 |
atory | -4.694 |
idia | -4.598 |
ドラ | -4.398 |
Token | minutes |
Token ID | 2431 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
én | +4.112 |
everal | +3.697 |
hate | +3.452 |
DEM | +3.262 |
friend | +3.227 |
Neg logit contributions | |
ocrine | -6.879 |
ary | -6.408 |
atory | -6.308 |
gery | -6.078 |
idia | -5.853 |
Token | ."[ |
Token ID | 18161 |
Feature activation | +1.87e+01 |
Pos logit contributions | |
én | +1.605 |
everal | +1.491 |
hate | +1.380 |
DEM | +1.325 |
friend | +1.323 |
Neg logit contributions | |
ocrine | -2.222 |
ary | -2.056 |
atory | -2.001 |
gery | -1.914 |
idia | -1.905 |
Token | 154 |
Token ID | 21526 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
ocrine | +8.787 |
ary | +8.666 |
atory | +7.524 |
idia | +7.013 |
ph | +6.898 |
Neg logit contributions | |
everal | -16.556 |
én | -16.028 |
orno | -14.913 |
hate | -14.609 |
gobl | -14.529 |
Token | ] |
Token ID | 60 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
ocrine | +0.036 |
ary | +0.035 |
atory | +0.033 |
ph | +0.031 |
gery | +0.031 |
Neg logit contributions | |
én | -0.031 |
everal | -0.030 |
hate | -0.027 |
DEM | -0.027 |
friend | -0.026 |
Token | The |
Token ID | 383 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ocrine | +0.715 |
ary | +0.671 |
atory | +0.644 |
gery | +0.615 |
idia | +0.614 |
Neg logit contributions | |
én | -0.608 |
everal | -0.573 |
hate | -0.535 |
DEM | -0.529 |
friend | -0.518 |
Token | game |
Token ID | 983 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
én | +1.196 |
everal | +1.124 |
hate | +1.047 |
DEM | +1.011 |
friend | +0.999 |
Neg logit contributions | |
ocrine | -1.521 |
ary | -1.425 |
atory | -1.375 |
gery | -1.308 |
idia | -1.301 |
Token | was |
Token ID | 373 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
én | +3.261 |
everal | +3.033 |
hate | +2.912 |
DEM | +2.859 |
friend | +2.833 |
Neg logit contributions | |
ocrine | -3.800 |
ary | -3.531 |
atory | -3.420 |
idia | -3.284 |
gery | -3.236 |
Token | the |
Token ID | 262 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
ocrine | +1.831 |
ary | +1.726 |
atory | +1.645 |
gery | +1.562 |
idia | +1.559 |
Neg logit contributions | |
én | -1.658 |
everal | -1.601 |
hate | -1.459 |
DEM | -1.436 |
friend | -1.409 |
Token | exception |
Token ID | 6631 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
ocrine | +3.011 |
ary | +2.847 |
atory | +2.703 |
gery | +2.563 |
idia | +2.555 |
Neg logit contributions | |
én | -2.930 |
everal | -2.841 |
hate | -2.597 |
DEM | -2.564 |
friend | -2.507 |
Token | of |
Token ID | 286 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ocrine | +0.423 |
ary | +0.403 |
atory | +0.379 |
idia | +0.352 |
gery | +0.352 |
Neg logit contributions | |
én | -0.498 |
everal | -0.483 |
hate | -0.447 |
DEM | -0.442 |
friend | -0.433 |
Token | season |
Token ID | 1622 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
én | +0.800 |
everal | +0.761 |
hate | +0.693 |
DEM | +0.672 |
friend | +0.666 |
Neg logit contributions | |
ocrine | -0.994 |
ary | -0.930 |
atory | -0.888 |
gery | -0.855 |
idia | -0.846 |
Token | 14 |
Token ID | 1478 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ocrine | +1.486 |
ary | +1.378 |
atory | +1.315 |
gery | +1.247 |
idia | +1.237 |
Neg logit contributions | |
én | -1.678 |
everal | -1.605 |
hate | -1.494 |
DEM | -1.478 |
friend | -1.456 |
Token | ).[ |
Token ID | 42669 |
Feature activation | +1.87e+01 |
Pos logit contributions | |
én | +0.649 |
everal | +0.604 |
hate | +0.559 |
DEM | +0.542 |
friend | +0.535 |
Neg logit contributions | |
ocrine | -0.892 |
ary | -0.832 |
atory | -0.803 |
gery | -0.775 |
idia | -0.761 |
Token | 157 |
Token ID | 18458 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
ocrine | +9.960 |
ary | +9.534 |
atory | +8.877 |
ph | +8.638 |
idia | +8.067 |
Neg logit contributions | |
everal | -15.042 |
én | -14.568 |
orno | -13.363 |
DEM | -13.201 |
gobl | -12.902 |
Token | ] |
Token ID | 60 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
én | +1.506 |
everal | +1.455 |
hate | +1.314 |
DEM | +1.293 |
friend | +1.261 |
Neg logit contributions | |
ocrine | -1.950 |
ary | -1.853 |
atory | -1.769 |
gery | -1.691 |
idia | -1.685 |
Token |
|
Token ID | 198 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
én | +0.827 |
everal | +0.767 |
hate | +0.720 |
DEM | +0.710 |
friend | +0.704 |
Neg logit contributions | |
ocrine | -1.008 |
ary | -0.932 |
atory | -0.899 |
gery | -0.868 |
idia | -0.867 |
Token |
|
Token ID | 198 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
én | +1.452 |
hate | +1.275 |
friend | +1.260 |
DEM | +1.245 |
fw | +1.198 |
Neg logit contributions | |
ocrine | -1.862 |
ary | -1.697 |
atory | -1.654 |
idia | -1.622 |
gery | -1.590 |
Token | Th |
Token ID | 817 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
én | +0.938 |
everal | +0.852 |
hate | +0.821 |
DEM | +0.820 |
friend | +0.791 |
Neg logit contributions | |
ocrine | -1.429 |
ary | -1.326 |
atory | -1.289 |
gery | -1.244 |
idia | -1.237 |
Token | on |
Token ID | 319 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ocrine | +0.381 |
ary | +0.353 |
atory | +0.338 |
gery | +0.326 |
idia | +0.324 |
Neg logit contributions | |
én | -0.341 |
everal | -0.322 |
hate | -0.298 |
DEM | -0.296 |
friend | -0.291 |
Token | the |
Token ID | 262 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
én | +0.700 |
everal | +0.678 |
DEM | +0.617 |
hate | +0.614 |
friend | +0.599 |
Neg logit contributions | |
ocrine | -0.833 |
ary | -0.775 |
atory | -0.741 |
idia | -0.715 |
gery | -0.714 |
Token | basis |
Token ID | 4308 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
én | +0.195 |
everal | +0.189 |
hate | +0.173 |
DEM | +0.173 |
friend | +0.169 |
Neg logit contributions | |
ocrine | -0.199 |
ary | -0.185 |
atory | -0.175 |
idia | -0.170 |
gery | -0.168 |
Token | of |
Token ID | 286 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
ocrine | +1.759 |
ary | +1.669 |
atory | +1.577 |
idia | +1.469 |
gery | +1.469 |
Neg logit contributions | |
én | -2.066 |
everal | -2.012 |
hate | -1.857 |
DEM | -1.827 |
friend | -1.797 |
Token | population |
Token ID | 3265 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
ocrine | +2.764 |
ary | +2.613 |
atory | +2.487 |
gery | +2.369 |
idia | +2.367 |
Neg logit contributions | |
én | -2.401 |
everal | -2.319 |
hate | -2.110 |
DEM | -2.087 |
friend | -2.037 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +1.82e+01 |
Pos logit contributions | |
én | +0.521 |
everal | +0.490 |
DEM | +0.462 |
hate | +0.462 |
friend | +0.446 |
Neg logit contributions | |
ocrine | -0.625 |
ary | -0.578 |
atory | -0.554 |
gery | -0.540 |
idia | -0.534 |
Token | 185 |
Token ID | 21652 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ocrine | +9.330 |
ary | +8.673 |
ph | +8.172 |
atory | +7.984 |
idia | +7.127 |
Neg logit contributions | |
everal | -15.157 |
én | -14.894 |
DEM | -14.154 |
orno | -13.436 |
resil | -13.304 |
Token | ] |
Token ID | 60 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
ocrine | +0.956 |
ary | +0.910 |
atory | +0.867 |
gery | +0.825 |
idia | +0.824 |
Neg logit contributions | |
én | -0.765 |
everal | -0.740 |
hate | -0.668 |
DEM | -0.659 |
friend | -0.642 |
Token | with |
Token ID | 351 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
ocrine | +0.059 |
ary | +0.055 |
atory | +0.052 |
idia | +0.051 |
gery | +0.050 |
Neg logit contributions | |
én | -0.051 |
everal | -0.049 |
DEM | -0.045 |
hate | -0.045 |
friend | -0.044 |
Token | each |
Token ID | 1123 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
ocrine | +3.177 |
ary | +2.992 |
atory | +2.838 |
gery | +2.691 |
idia | +2.689 |
Neg logit contributions | |
én | -3.184 |
everal | -3.088 |
hate | -2.827 |
DEM | -2.798 |
friend | -2.734 |
Token | original |
Token ID | 2656 |
Feature activation | +9.61e+00 |
Pos logit contributions | |
ocrine | +2.383 |
ary | +2.236 |
atory | +2.120 |
gery | +2.012 |
idia | +2.011 |
Neg logit contributions | |
én | -2.530 |
everal | -2.457 |
hate | -2.254 |
DEM | -2.233 |
friend | -2.185 |
Token | Beth |
Token ID | 19223 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
én | +2.329 |
everal | +2.266 |
hate | +2.062 |
DEM | +1.998 |
friend | +1.989 |
Neg logit contributions | |
ocrine | -2.811 |
ary | -2.607 |
atory | -2.465 |
idia | -2.400 |
gery | -2.391 |
Token | une |
Token ID | 1726 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
én | +0.316 |
everal | +0.283 |
hate | +0.268 |
DEM | +0.257 |
friend | +0.256 |
Neg logit contributions | |
ocrine | -0.514 |
ary | -0.488 |
atory | -0.470 |
gery | -0.456 |
idia | -0.449 |
Token | 's |
Token ID | 338 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
én | +0.500 |
everal | +0.476 |
hate | +0.440 |
DEM | +0.432 |
friend | +0.425 |
Neg logit contributions | |
ocrine | -0.530 |
ary | -0.492 |
atory | -0.469 |
gery | -0.449 |
idia | -0.446 |
Token | last |
Token ID | 938 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
én | +0.144 |
everal | +0.140 |
hate | +0.128 |
DEM | +0.126 |
friend | +0.125 |
Neg logit contributions | |
ocrine | -0.158 |
ary | -0.145 |
atory | -0.138 |
idia | -0.133 |
gery | -0.132 |
Token | residence |
Token ID | 11566 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
ocrine | +2.703 |
ary | +2.542 |
atory | +2.416 |
gery | +2.297 |
idia | +2.289 |
Neg logit contributions | |
én | -2.667 |
everal | -2.588 |
hate | -2.374 |
DEM | -2.344 |
friend | -2.301 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +1.76e+01 |
Pos logit contributions | |
ocrine | +0.469 |
ary | +0.435 |
atory | +0.413 |
gery | +0.397 |
idia | +0.396 |
Neg logit contributions | |
én | -0.410 |
everal | -0.392 |
hate | -0.365 |
DEM | -0.358 |
friend | -0.353 |
Token | 56 |
Token ID | 3980 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
ocrine | +8.275 |
ary | +8.060 |
ph | +7.329 |
atory | +7.157 |
void | +6.867 |
Neg logit contributions | |
everal | -15.221 |
én | -15.105 |
orno | -13.953 |
Thieves | -13.482 |
DEM | -13.402 |
Token | ] |
Token ID | 60 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
én | +3.733 |
everal | +3.597 |
hate | +3.226 |
DEM | +3.132 |
friend | +3.109 |
Neg logit contributions | |
ocrine | -5.427 |
ary | -5.149 |
atory | -4.912 |
gery | -4.788 |
idia | -4.743 |
Token | the |
Token ID | 262 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
ocrine | +1.554 |
ary | +1.465 |
atory | +1.391 |
gery | +1.326 |
idia | +1.322 |
Neg logit contributions | |
én | -1.427 |
everal | -1.376 |
hate | -1.257 |
DEM | -1.241 |
friend | -1.221 |
Token | N |
Token ID | 399 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
ocrine | +2.869 |
ary | +2.714 |
atory | +2.577 |
gery | +2.445 |
idia | +2.437 |
Neg logit contributions | |
én | -2.755 |
everal | -2.672 |
hate | -2.441 |
DEM | -2.410 |
friend | -2.355 |
Token | AC |
Token ID | 2246 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ocrine | +2.063 |
ary | +1.952 |
atory | +1.866 |
gery | +1.781 |
idia | +1.770 |
Neg logit contributions | |
én | -1.717 |
everal | -1.651 |
hate | -1.502 |
DEM | -1.481 |
friend | -1.444 |
Token | House |
Token ID | 2097 |
Feature activation | -6.71e+00 |
Pos logit contributions | |
én | +5.063 |
everal | +4.424 |
friend | +4.246 |
hate | +4.167 |
Thieves | +4.050 |
Neg logit contributions | |
ocrine | -6.691 |
ary | -6.138 |
gery | -5.855 |
idia | -5.852 |
atory | -5.840 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
én | +4.407 |
everal | +4.066 |
hate | +3.712 |
friend | +3.686 |
DEM | +3.652 |
Neg logit contributions | |
ocrine | -5.539 |
ary | -5.195 |
atory | -4.905 |
idia | -4.860 |
gery | -4.830 |
Token | 1971 |
Token ID | 16382 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
én | +1.363 |
everal | +1.250 |
hate | +1.210 |
DEM | +1.202 |
friend | +1.196 |
Neg logit contributions | |
ocrine | -1.167 |
ary | -1.075 |
atory | -1.026 |
idia | -0.987 |
gery | -0.971 |
Token | ), |
Token ID | 828 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
én | +3.934 |
everal | +3.420 |
hate | +3.002 |
friend | +2.926 |
DEM | +2.873 |
Neg logit contributions | |
ocrine | -10.513 |
ary | -9.906 |
atory | -9.700 |
gery | -9.479 |
idia | -9.456 |
Token | 413 |
Token ID | 46618 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
én | +1.248 |
everal | +1.176 |
hate | +1.103 |
DEM | +1.093 |
friend | +1.074 |
Neg logit contributions | |
ocrine | -1.121 |
ary | -1.041 |
atory | -0.981 |
gery | -0.950 |
idia | -0.934 |
Token | – |
Token ID | 1906 |
Feature activation | +1.72e+01 |
Pos logit contributions | |
én | +2.452 |
everal | +2.274 |
hate | +2.093 |
DEM | +2.073 |
friend | +2.019 |
Neg logit contributions | |
ocrine | -3.259 |
ary | -3.067 |
atory | -2.933 |
gery | -2.844 |
idia | -2.825 |
Token | 14 |
Token ID | 1415 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ocrine | +9.164 |
ary | +8.966 |
atory | +8.221 |
ph | +7.960 |
idia | +7.161 |
Neg logit contributions | |
everal | -15.178 |
én | -14.168 |
gobl | -13.219 |
hate | -13.012 |
hemor | -12.774 |
Token | . |
Token ID | 13 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
ocrine | +1.219 |
ary | +1.153 |
atory | +1.094 |
gery | +1.038 |
idia | +1.035 |
Neg logit contributions | |
én | -1.176 |
everal | -1.140 |
hate | -1.042 |
DEM | -1.029 |
friend | -1.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
én | +2.000 |
everal | +1.866 |
hate | +1.763 |
DEM | +1.717 |
friend | +1.691 |
Neg logit contributions | |
ocrine | -2.288 |
ary | -2.138 |
atory | -2.033 |
gery | -1.971 |
idia | -1.962 |
Token |
|
Token ID | 198 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
én | +0.951 |
hate | +0.835 |
friend | +0.822 |
DEM | +0.817 |
fw | +0.786 |
Neg logit contributions | |
ocrine | -1.150 |
ary | -1.059 |
atory | -1.023 |
idia | -0.997 |
gery | -0.985 |
Token | [ |
Token ID | 58 |
Feature activation | +8.25e+00 |
Pos logit contributions | |
én | +0.536 |
everal | +0.466 |
hate | +0.466 |
DEM | +0.463 |
friend | +0.453 |
Neg logit contributions | |
ocrine | -0.795 |
ary | -0.750 |
atory | -0.719 |
gery | -0.700 |
idia | -0.699 |
Token | ALL |
Token ID | 11096 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ocrine | +1.172 |
ary | +1.105 |
atory | +1.060 |
idia | +1.010 |
gery | +1.010 |
Neg logit contributions | |
én | -0.990 |
everal | -0.948 |
DEM | -0.875 |
hate | -0.858 |
friend | -0.839 |
Token | PERSON |
Token ID | 46740 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
ocrine | +1.177 |
ary | +1.117 |
atory | +1.073 |
idia | +1.028 |
gery | +1.028 |
Neg logit contributions | |
én | -0.831 |
everal | -0.787 |
DEM | -0.719 |
hate | -0.706 |
friend | -0.687 |
Token | EL |
Token ID | 3698 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
én | +1.065 |
DEM | +0.880 |
friend | +0.805 |
hate | +0.771 |
FG | +0.770 |
Neg logit contributions | |
ocrine | -3.405 |
ary | -3.231 |
atory | -3.197 |
gery | -3.087 |
idia | -3.082 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ocrine | +0.514 |
ary | +0.474 |
atory | +0.444 |
gery | +0.416 |
idia | +0.415 |
Neg logit contributions | |
én | -0.789 |
everal | -0.761 |
DEM | -0.711 |
hate | -0.710 |
friend | -0.694 |
Token | : |
Token ID | 25 |
Feature activation | +6.65e+00 |
Pos logit contributions | |
én | +1.243 |
DEM | +1.103 |
hate | +1.071 |
friend | +1.064 |
everal | +1.038 |
Neg logit contributions | |
ocrine | -1.538 |
ary | -1.414 |
atory | -1.380 |
gery | -1.327 |
idia | -1.324 |
Token | 0 |
Token ID | 657 |
Feature activation | +1.70e+01 |
Pos logit contributions | |
ocrine | +4.017 |
ary | +3.807 |
atory | +3.539 |
gery | +3.305 |
ph | +3.282 |
Neg logit contributions | |
én | -5.950 |
everal | -5.946 |
hate | -5.397 |
DEM | -5.286 |
friend | -5.231 |
Token | 605 |
Token ID | 32417 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ocrine | +7.550 |
ary | +6.857 |
ph | +6.150 |
atory | +5.866 |
gery | +5.672 |
Neg logit contributions | |
everal | -16.074 |
én | -15.655 |
gobl | -14.559 |
hate | -14.274 |
haps | -14.073 |
Token | z |
Token ID | 89 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
én | +0.779 |
hate | +0.660 |
everal | +0.657 |
DEM | +0.638 |
friend | +0.620 |
Neg logit contributions | |
ocrine | -1.391 |
ary | -1.309 |
atory | -1.270 |
idia | -1.232 |
gery | -1.221 |
Token | BLACK |
Token ID | 31963 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
ocrine | +2.623 |
ary | +2.479 |
atory | +2.361 |
gery | +2.243 |
idia | +2.236 |
Neg logit contributions | |
én | -2.432 |
everal | -2.350 |
hate | -2.147 |
DEM | -2.130 |
friend | -2.075 |
Token | FO |
Token ID | 6080 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
ocrine | +0.855 |
ary | +0.815 |
atory | +0.781 |
gery | +0.747 |
idia | +0.746 |
Neg logit contributions | |
én | -0.570 |
everal | -0.548 |
hate | -0.491 |
DEM | -0.486 |
friend | -0.471 |
Token | OT |
Token ID | 2394 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
ocrine | +1.848 |
ary | +1.760 |
atory | +1.688 |
idia | +1.618 |
gery | +1.617 |
Neg logit contributions | |
én | -1.208 |
everal | -1.139 |
hate | -1.037 |
DEM | -1.027 |
friend | -0.996 |
Token | air |
Token ID | 1633 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
ocrine | +3.094 |
ary | +2.935 |
atory | +2.792 |
gery | +2.654 |
idia | +2.645 |
Neg logit contributions | |
én | -2.766 |
everal | -2.681 |
hate | -2.437 |
DEM | -2.405 |
friend | -2.347 |
Token | / |
Token ID | 14 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
ocrine | +0.677 |
ary | +0.641 |
atory | +0.614 |
idia | +0.585 |
gery | +0.583 |
Neg logit contributions | |
én | -0.547 |
everal | -0.525 |
hate | -0.484 |
DEM | -0.476 |
friend | -0.464 |
Token | being |
Token ID | 11873 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
ocrine | +0.331 |
ary | +0.311 |
atory | +0.297 |
idia | +0.284 |
gery | +0.284 |
Neg logit contributions | |
én | -0.277 |
everal | -0.267 |
hate | -0.247 |
DEM | -0.241 |
friend | -0.238 |
Token | buried |
Token ID | 11694 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
én | +2.469 |
everal | +2.326 |
hate | +2.169 |
DEM | +2.139 |
friend | +2.087 |
Neg logit contributions | |
ocrine | -3.107 |
ary | -2.908 |
atory | -2.815 |
idia | -2.738 |
gery | -2.693 |
Token | alive |
Token ID | 6776 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ocrine | +0.759 |
ary | +0.712 |
atory | +0.678 |
gery | +0.648 |
idia | +0.647 |
Neg logit contributions | |
én | -0.725 |
everal | -0.697 |
hate | -0.640 |
DEM | -0.625 |
friend | -0.621 |
Token | ."[ |
Token ID | 18161 |
Feature activation | +1.70e+01 |
Pos logit contributions | |
ocrine | +2.210 |
ary | +2.089 |
atory | +2.000 |
gery | +1.911 |
idia | +1.902 |
Neg logit contributions | |
én | -1.770 |
everal | -1.706 |
hate | -1.551 |
DEM | -1.522 |
friend | -1.491 |
Token | 155 |
Token ID | 18742 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ocrine | +8.196 |
ary | +8.009 |
atory | +7.173 |
ph | +6.806 |
idia | +6.520 |
Neg logit contributions | |
everal | -14.818 |
én | -14.566 |
orno | -13.339 |
DEM | -13.180 |
hate | -13.159 |
Token | ] |
Token ID | 60 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ocrine | +1.090 |
ary | +1.044 |
atory | +0.989 |
ph | +0.937 |
idia | +0.930 |
Neg logit contributions | |
én | -0.946 |
everal | -0.915 |
hate | -0.827 |
DEM | -0.822 |
friend | -0.797 |
Token |
|
Token ID | 198 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ocrine | +1.480 |
ary | +1.392 |
atory | +1.330 |
gery | +1.270 |
idia | +1.267 |
Neg logit contributions | |
én | -1.308 |
everal | -1.245 |
hate | -1.152 |
DEM | -1.136 |
friend | -1.114 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
én | +1.037 |
hate | +0.914 |
friend | +0.899 |
DEM | +0.895 |
fw | +0.859 |
Neg logit contributions | |
ocrine | -1.278 |
ary | -1.171 |
atory | -1.136 |
idia | -1.109 |
gery | -1.090 |
Token | On |
Token ID | 2202 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
én | +0.789 |
everal | +0.718 |
hate | +0.691 |
DEM | +0.685 |
friend | +0.660 |
Neg logit contributions | |
ocrine | -1.192 |
ary | -1.113 |
atory | -1.076 |
gery | -1.038 |
idia | -1.032 |
Token | Beyond |
Token ID | 12197 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
én | +0.884 |
everal | +0.846 |
hate | +0.783 |
DEM | +0.775 |
friend | +0.760 |
Neg logit contributions | |
ocrine | -0.986 |
ary | -0.920 |
atory | -0.877 |
gery | -0.845 |
idia | -0.841 |
Token | the |
Token ID | 262 |
Feature activation | -6.91e+00 |
Pos logit contributions | |
én | +2.932 |
everal | +2.778 |
hate | +2.614 |
DEM | +2.552 |
friend | +2.539 |
Neg logit contributions | |
ocrine | -3.320 |
ary | -3.037 |
atory | -2.951 |
idia | -2.810 |
gery | -2.795 |
Token | Myth |
Token ID | 18900 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
én | +4.652 |
everal | +4.372 |
hate | +4.102 |
Thieves | +4.100 |
friend | +4.014 |
Neg logit contributions | |
ocrine | -5.473 |
ary | -5.013 |
atory | -4.922 |
idia | -4.715 |
gery | -4.632 |
Token | ".[ |
Token ID | 42924 |
Feature activation | +1.67e+01 |
Pos logit contributions | |
ocrine | +0.059 |
ary | +0.055 |
atory | +0.054 |
idia | +0.052 |
gery | +0.051 |
Neg logit contributions | |
én | -0.044 |
everal | -0.041 |
hate | -0.038 |
DEM | -0.037 |
friend | -0.036 |
Token | 51 |
Token ID | 4349 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ary | +6.869 |
ocrine | +6.862 |
atory | +5.915 |
ph | +5.663 |
idia | +5.203 |
Neg logit contributions | |
everal | -16.694 |
én | -15.896 |
gobl | -14.849 |
orno | -14.747 |
hate | -14.578 |
Token | ][ |
Token ID | 7131 |
Feature activation | +1.68e+01 |
Pos logit contributions | |
ocrine | +1.177 |
ary | +1.130 |
atory | +1.068 |
ph | +1.013 |
idia | +1.009 |
Neg logit contributions | |
én | -1.015 |
everal | -0.980 |
hate | -0.892 |
DEM | -0.883 |
friend | -0.853 |
Token | 54 |
Token ID | 4051 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ary | +7.851 |
ocrine | +7.802 |
atory | +6.946 |
ph | +6.712 |
idia | +6.231 |
Neg logit contributions | |
everal | -15.593 |
én | -14.976 |
orno | -13.751 |
gobl | -13.743 |
hate | -13.522 |
Token | ] |
Token ID | 60 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
én | +0.920 |
everal | +0.889 |
hate | +0.803 |
DEM | +0.792 |
friend | +0.771 |
Neg logit contributions | |
ocrine | -1.173 |
ary | -1.115 |
atory | -1.064 |
gery | -1.015 |
idia | -1.012 |
Token | The |
Token ID | 383 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
ocrine | +0.800 |
ary | +0.746 |
atory | +0.712 |
idia | +0.684 |
gery | +0.683 |
Neg logit contributions | |
én | -0.704 |
everal | -0.665 |
hate | -0.617 |
DEM | -0.610 |
friend | -0.600 |
Token | cat |
Token ID | 3797 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
én | +0.441 |
everal | +0.422 |
hate | +0.391 |
DEM | +0.384 |
friend | +0.376 |
Neg logit contributions | |
ocrine | -0.451 |
ary | -0.419 |
atory | -0.396 |
idia | -0.380 |
gery | -0.375 |
Token | has |
Token ID | 468 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
ocrine | +2.145 |
ary | +2.018 |
atory | +1.926 |
idia | +1.825 |
gery | +1.823 |
Neg logit contributions | |
én | -1.996 |
everal | -1.918 |
hate | -1.765 |
DEM | -1.736 |
friend | -1.705 |
Token | Leopard |
Token ID | 49072 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
én | +1.332 |
everal | +1.255 |
hate | +1.178 |
DEM | +1.163 |
friend | +1.134 |
Neg logit contributions | |
ocrine | -1.529 |
ary | -1.418 |
atory | -1.363 |
gery | -1.298 |
idia | -1.294 |
Token | – |
Token ID | 784 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
én | +2.302 |
everal | +2.097 |
hate | +2.020 |
friend | +1.955 |
DEM | +1.942 |
Neg logit contributions | |
ocrine | -3.008 |
ary | -2.754 |
atory | -2.685 |
idia | -2.595 |
gery | -2.556 |
Token | Beyond |
Token ID | 12197 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
én | +0.884 |
everal | +0.846 |
hate | +0.783 |
DEM | +0.775 |
friend | +0.760 |
Neg logit contributions | |
ocrine | -0.986 |
ary | -0.920 |
atory | -0.877 |
gery | -0.845 |
idia | -0.841 |
Token | the |
Token ID | 262 |
Feature activation | -6.91e+00 |
Pos logit contributions | |
én | +2.932 |
everal | +2.778 |
hate | +2.614 |
DEM | +2.552 |
friend | +2.539 |
Neg logit contributions | |
ocrine | -3.320 |
ary | -3.037 |
atory | -2.951 |
idia | -2.810 |
gery | -2.795 |
Token | Myth |
Token ID | 18900 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
én | +4.652 |
everal | +4.372 |
hate | +4.102 |
Thieves | +4.100 |
friend | +4.014 |
Neg logit contributions | |
ocrine | -5.473 |
ary | -5.013 |
atory | -4.922 |
idia | -4.715 |
gery | -4.632 |
Token | ".[ |
Token ID | 42924 |
Feature activation | +1.67e+01 |
Pos logit contributions | |
ocrine | +0.059 |
ary | +0.055 |
atory | +0.054 |
idia | +0.052 |
gery | +0.051 |
Neg logit contributions | |
én | -0.044 |
everal | -0.041 |
hate | -0.038 |
DEM | -0.037 |
friend | -0.036 |
Token | 51 |
Token ID | 4349 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ary | +6.869 |
ocrine | +6.862 |
atory | +5.915 |
ph | +5.663 |
idia | +5.203 |
Neg logit contributions | |
everal | -16.694 |
én | -15.896 |
gobl | -14.849 |
orno | -14.747 |
hate | -14.578 |
Token | ][ |
Token ID | 7131 |
Feature activation | +1.68e+01 |
Pos logit contributions | |
ocrine | +1.177 |
ary | +1.130 |
atory | +1.068 |
ph | +1.013 |
idia | +1.009 |
Neg logit contributions | |
én | -1.015 |
everal | -0.980 |
hate | -0.892 |
DEM | -0.883 |
friend | -0.853 |
Token | 54 |
Token ID | 4051 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ary | +7.851 |
ocrine | +7.802 |
atory | +6.946 |
ph | +6.712 |
idia | +6.231 |
Neg logit contributions | |
everal | -15.593 |
én | -14.976 |
orno | -13.751 |
gobl | -13.743 |
hate | -13.522 |
Token | ] |
Token ID | 60 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
én | +0.920 |
everal | +0.889 |
hate | +0.803 |
DEM | +0.792 |
friend | +0.771 |
Neg logit contributions | |
ocrine | -1.173 |
ary | -1.115 |
atory | -1.064 |
gery | -1.015 |
idia | -1.012 |
Token | The |
Token ID | 383 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
ocrine | +0.800 |
ary | +0.746 |
atory | +0.712 |
idia | +0.684 |
gery | +0.683 |
Neg logit contributions | |
én | -0.704 |
everal | -0.665 |
hate | -0.617 |
DEM | -0.610 |
friend | -0.600 |
Token | were |
Token ID | 547 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
én | +1.846 |
everal | +1.734 |
DEM | +1.592 |
hate | +1.581 |
friend | +1.534 |
Neg logit contributions | |
ocrine | -2.090 |
ary | -1.941 |
atory | -1.865 |
gery | -1.815 |
idia | -1.741 |
Token | also |
Token ID | 635 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
én | +1.136 |
everal | +1.075 |
hate | +0.980 |
DEM | +0.974 |
friend | +0.944 |
Neg logit contributions | |
ocrine | -1.552 |
ary | -1.430 |
atory | -1.384 |
gery | -1.325 |
idia | -1.325 |
Token | taken |
Token ID | 2077 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
én | +1.487 |
everal | +1.403 |
DEM | +1.273 |
hate | +1.271 |
friend | +1.229 |
Neg logit contributions | |
ocrine | -2.027 |
ary | -1.863 |
atory | -1.799 |
idia | -1.728 |
gery | -1.728 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
én | +2.664 |
everal | +2.477 |
hate | +2.285 |
friend | +2.250 |
DEM | +2.236 |
Neg logit contributions | |
ocrine | -3.422 |
ary | -3.067 |
atory | -2.965 |
idia | -2.881 |
ulatory | -2.854 |
Token | 12 |
Token ID | 1065 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
ocrine | +7.565 |
ary | +7.496 |
ph | +6.768 |
atory | +6.729 |
idia | +6.029 |
Neg logit contributions | |
everal | -13.734 |
én | -13.050 |
orno | -11.984 |
gobl | -11.916 |
hate | -11.817 |
Token | ][ |
Token ID | 7131 |
Feature activation | +1.59e+01 |
Pos logit contributions | |
én | +0.446 |
everal | +0.431 |
hate | +0.389 |
DEM | +0.383 |
friend | +0.373 |
Neg logit contributions | |
ocrine | -0.579 |
ary | -0.551 |
atory | -0.526 |
gery | -0.503 |
idia | -0.501 |
Token | 15 |
Token ID | 1314 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
ary | +7.786 |
ocrine | +7.714 |
ph | +7.013 |
atory | +7.009 |
idia | +6.224 |
Neg logit contributions | |
everal | -14.408 |
én | -13.728 |
orno | -12.634 |
gobl | -12.555 |
DEM | -12.541 |
Token | ] |
Token ID | 60 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
én | +3.222 |
everal | +3.120 |
hate | +2.800 |
DEM | +2.729 |
friend | +2.684 |
Neg logit contributions | |
ocrine | -4.913 |
ary | -4.646 |
atory | -4.441 |
gery | -4.341 |
idia | -4.302 |
Token |
|
Token ID | 198 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
ocrine | +0.269 |
ary | +0.251 |
atory | +0.240 |
gery | +0.231 |
idia | +0.230 |
Neg logit contributions | |
én | -0.233 |
everal | -0.219 |
DEM | -0.206 |
hate | -0.204 |
friend | -0.198 |
Token |
|
Token ID | 198 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
ocrine | +0.305 |
ary | +0.283 |
atory | +0.272 |
idia | +0.261 |
gery | +0.259 |
Neg logit contributions | |
én | -0.274 |
everal | -0.243 |
hate | -0.242 |
DEM | -0.238 |
friend | -0.236 |
Token | Results |
Token ID | 25468 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
ocrine | +0.873 |
ary | +0.821 |
atory | +0.791 |
gery | +0.761 |
idia | +0.760 |
Neg logit contributions | |
én | -0.591 |
everal | -0.553 |
DEM | -0.515 |
hate | -0.512 |
friend | -0.493 |
Token | prime |
Token ID | 6994 |
Feature activation | -9.62e+00 |
Pos logit contributions | |
ocrine | +2.822 |
ary | +2.678 |
atory | +2.538 |
gery | +2.407 |
idia | +2.394 |
Neg logit contributions | |
én | -2.719 |
everal | -2.640 |
hate | -2.408 |
DEM | -2.375 |
friend | -2.318 |
Token | minister |
Token ID | 5342 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
én | +3.384 |
hate | +2.684 |
friend | +2.672 |
DEM | +2.537 |
fw | +2.463 |
Neg logit contributions | |
ocrine | -10.398 |
idia | -9.482 |
aptic | -9.199 |
gery | -9.193 |
ary | -9.193 |
Token | later |
Token ID | 1568 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ocrine | +0.782 |
ary | +0.718 |
atory | +0.694 |
idia | +0.666 |
gery | +0.662 |
Neg logit contributions | |
én | -0.717 |
everal | -0.686 |
hate | -0.630 |
DEM | -0.626 |
friend | -0.613 |
Token | that |
Token ID | 326 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
ocrine | +1.796 |
ary | +1.685 |
atory | +1.602 |
gery | +1.527 |
idia | +1.521 |
Neg logit contributions | |
én | -1.733 |
everal | -1.667 |
hate | -1.531 |
DEM | -1.514 |
friend | -1.479 |
Token | day |
Token ID | 1110 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
én | +2.763 |
everal | +2.617 |
hate | +2.444 |
DEM | +2.436 |
friend | +2.373 |
Neg logit contributions | |
ocrine | -3.223 |
ary | -2.909 |
atory | -2.809 |
idia | -2.751 |
gery | -2.713 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
ocrine | +0.274 |
ary | +0.255 |
atory | +0.243 |
gery | +0.233 |
idia | +0.233 |
Neg logit contributions | |
én | -0.247 |
everal | -0.236 |
hate | -0.216 |
DEM | -0.214 |
friend | -0.209 |
Token | 195 |
Token ID | 22186 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
ocrine | +7.783 |
ary | +6.980 |
ph | +6.676 |
atory | +6.644 |
idia | +6.223 |
Neg logit contributions | |
én | -13.383 |
everal | -13.337 |
orno | -12.333 |
resil | -12.273 |
DEM | -12.184 |
Token | ] |
Token ID | 60 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
én | +2.777 |
everal | +2.667 |
hate | +2.404 |
DEM | +2.356 |
friend | +2.303 |
Neg logit contributions | |
ocrine | -3.850 |
ary | -3.648 |
atory | -3.487 |
gery | -3.369 |
idia | -3.353 |
Token |
|
Token ID | 198 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ocrine | +1.370 |
ary | +1.281 |
atory | +1.222 |
idia | +1.180 |
gery | +1.171 |
Neg logit contributions | |
én | -1.243 |
everal | -1.175 |
hate | -1.089 |
DEM | -1.088 |
friend | -1.063 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ocrine | +0.189 |
ary | +0.175 |
atory | +0.169 |
idia | +0.163 |
gery | +0.161 |
Neg logit contributions | |
én | -0.168 |
hate | -0.148 |
everal | -0.147 |
DEM | -0.146 |
friend | -0.145 |
Token | States |
Token ID | 42237 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ocrine | +1.309 |
ary | +1.232 |
atory | +1.185 |
idia | +1.144 |
gery | +1.143 |
Neg logit contributions | |
én | -0.900 |
everal | -0.844 |
hate | -0.784 |
DEM | -0.783 |
friend | -0.755 |
Token | was |
Token ID | 373 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
én | +1.060 |
everal | +0.985 |
hate | +0.915 |
DEM | +0.902 |
friend | +0.891 |
Neg logit contributions | |
ocrine | -1.258 |
ary | -1.163 |
atory | -1.108 |
idia | -1.088 |
gery | -1.071 |
Token | originally |
Token ID | 6198 |
Feature activation | +8.71e+00 |
Pos logit contributions | |
én | +0.669 |
everal | +0.633 |
hate | +0.584 |
DEM | +0.579 |
friend | +0.571 |
Neg logit contributions | |
ocrine | -0.653 |
ary | -0.600 |
atory | -0.567 |
idia | -0.555 |
gery | -0.553 |
Token | passed |
Token ID | 3804 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
ocrine | +5.874 |
ary | +5.625 |
atory | +5.357 |
ph | +4.932 |
gery | +4.894 |
Neg logit contributions | |
én | -7.081 |
everal | -7.071 |
hate | -6.460 |
DEM | -6.324 |
friend | -6.239 |
Token | in |
Token ID | 287 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
én | +0.331 |
everal | +0.313 |
hate | +0.286 |
DEM | +0.286 |
friend | +0.279 |
Neg logit contributions | |
ocrine | -0.366 |
ary | -0.339 |
atory | -0.322 |
idia | -0.315 |
gery | -0.311 |
Token | 1970 |
Token ID | 8069 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ocrine | +3.078 |
ary | +2.892 |
atory | +2.717 |
gery | +2.551 |
idia | +2.533 |
Neg logit contributions | |
én | -3.933 |
everal | -3.838 |
hate | -3.541 |
DEM | -3.500 |
friend | -3.428 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
én | +2.006 |
everal | +1.844 |
hate | +1.725 |
DEM | +1.681 |
friend | +1.659 |
Neg logit contributions | |
ocrine | -2.342 |
ary | -2.123 |
atory | -2.072 |
idia | -2.009 |
gery | -1.997 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
ocrine | +8.389 |
ary | +8.099 |
atory | +7.593 |
ph | +7.094 |
gery | +6.714 |
Neg logit contributions | |
én | -13.153 |
everal | -13.055 |
orno | -11.831 |
hate | -11.668 |
Thieves | -11.411 |
Token | ] |
Token ID | 60 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
én | +1.732 |
everal | +1.673 |
hate | +1.510 |
DEM | +1.486 |
friend | +1.451 |
Neg logit contributions | |
ocrine | -2.229 |
ary | -2.118 |
atory | -2.022 |
gery | -1.935 |
idia | -1.927 |
Token | and |
Token ID | 290 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
én | +0.482 |
everal | +0.450 |
hate | +0.414 |
DEM | +0.408 |
friend | +0.402 |
Neg logit contributions | |
ocrine | -0.541 |
ary | -0.500 |
atory | -0.477 |
idia | -0.470 |
gery | -0.458 |
Token | is |
Token ID | 318 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
én | +0.816 |
everal | +0.766 |
hate | +0.699 |
DEM | +0.696 |
friend | +0.679 |
Neg logit contributions | |
ocrine | -0.890 |
ary | -0.825 |
atory | -0.782 |
idia | -0.774 |
gery | -0.753 |
Token | enforced |
Token ID | 20326 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
én | +0.508 |
everal | +0.478 |
hate | +0.436 |
DEM | +0.433 |
friend | +0.426 |
Neg logit contributions | |
ocrine | -0.565 |
ary | -0.531 |
atory | -0.498 |
idia | -0.495 |
gery | -0.485 |
Token | , |
Token ID | 11 |
Feature activation | +6.40e+00 |
Pos logit contributions | |
ocrine | +1.146 |
ary | +1.068 |
atory | +1.022 |
idia | +0.978 |
gery | +0.973 |
Neg logit contributions | |
én | -1.080 |
everal | -1.035 |
hate | -0.956 |
DEM | -0.940 |
friend | -0.921 |
Token | including |
Token ID | 1390 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
ocrine | +4.450 |
ary | +4.202 |
atory | +3.986 |
gery | +3.716 |
ph | +3.698 |
Neg logit contributions | |
én | -5.222 |
everal | -5.129 |
hate | -4.686 |
DEM | -4.626 |
friend | -4.542 |
Token | consumer |
Token ID | 7172 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ocrine | +3.566 |
ary | +3.381 |
atory | +3.208 |
gery | +3.040 |
idia | +3.021 |
Neg logit contributions | |
én | -3.490 |
everal | -3.393 |
hate | -3.094 |
DEM | -3.060 |
friend | -2.988 |
Token | credit |
Token ID | 3884 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
én | +0.822 |
everal | +0.771 |
hate | +0.737 |
DEM | +0.716 |
friend | +0.713 |
Neg logit contributions | |
ocrine | -0.907 |
ary | -0.836 |
atory | -0.804 |
idia | -0.769 |
gery | -0.763 |
Token | information |
Token ID | 1321 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
én | +1.016 |
everal | +0.961 |
hate | +0.905 |
DEM | +0.866 |
friend | +0.860 |
Neg logit contributions | |
ocrine | -1.147 |
ary | -1.062 |
atory | -1.022 |
idia | -0.984 |
gery | -0.977 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
én | +0.650 |
everal | +0.613 |
hate | +0.573 |
DEM | +0.563 |
friend | +0.546 |
Neg logit contributions | |
ocrine | -0.746 |
ary | -0.689 |
atory | -0.665 |
idia | -0.638 |
gery | -0.636 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ocrine | +9.028 |
ary | +8.844 |
atory | +8.123 |
ph | +7.886 |
idia | +7.327 |
Neg logit contributions | |
everal | -12.788 |
én | -12.331 |
orno | -11.417 |
hate | -11.299 |
gobl | -11.148 |
Token | ] |
Token ID | 60 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
én | +1.153 |
everal | +1.107 |
hate | +0.999 |
DEM | +0.982 |
friend | +0.959 |
Neg logit contributions | |
ocrine | -1.564 |
ary | -1.481 |
atory | -1.420 |
gery | -1.371 |
idia | -1.362 |
Token | Together |
Token ID | 17083 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ocrine | +3.417 |
ary | +3.241 |
atory | +3.079 |
gery | +2.915 |
idia | +2.901 |
Neg logit contributions | |
én | -3.247 |
everal | -3.160 |
hate | -2.874 |
DEM | -2.834 |
friend | -2.772 |
Token | with |
Token ID | 351 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ocrine | +0.768 |
ary | +0.728 |
atory | +0.688 |
gery | +0.642 |
idia | +0.642 |
Neg logit contributions | |
én | -0.869 |
everal | -0.843 |
hate | -0.776 |
DEM | -0.768 |
friend | -0.754 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
én | +1.079 |
everal | +1.024 |
hate | +0.948 |
DEM | +0.922 |
friend | +0.907 |
Neg logit contributions | |
ocrine | -1.245 |
ary | -1.163 |
atory | -1.098 |
idia | -1.076 |
gery | -1.058 |
Token | be |
Token ID | 307 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
én | +0.852 |
everal | +0.803 |
hate | +0.747 |
DEM | +0.726 |
friend | +0.709 |
Neg logit contributions | |
ocrine | -1.159 |
ary | -1.074 |
atory | -1.039 |
idia | -1.001 |
gery | -0.994 |
Token | headed |
Token ID | 15353 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
én | +4.756 |
everal | +4.537 |
hate | +4.299 |
DEM | +4.219 |
friend | +4.204 |
Neg logit contributions | |
ocrine | -3.400 |
ary | -3.111 |
atory | -2.873 |
gery | -2.740 |
idia | -2.733 |
Token | therein |
Token ID | 27258 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
én | +1.614 |
everal | +1.505 |
hate | +1.408 |
DEM | +1.374 |
friend | +1.361 |
Neg logit contributions | |
ocrine | -1.946 |
ary | -1.793 |
atory | -1.718 |
idia | -1.680 |
gery | -1.652 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
én | +1.228 |
everal | +1.161 |
hate | +1.071 |
DEM | +1.045 |
friend | +1.026 |
Neg logit contributions | |
ocrine | -1.454 |
ary | -1.347 |
atory | -1.288 |
idia | -1.242 |
gery | -1.242 |
Token | 1 |
Token ID | 16 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
ocrine | +7.445 |
ary | +7.282 |
atory | +6.787 |
ph | +6.739 |
idia | +5.863 |
Neg logit contributions | |
everal | -13.682 |
én | -12.887 |
gobl | -11.911 |
orno | -11.766 |
hate | -11.689 |
Token | ][ |
Token ID | 7131 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
ocrine | +0.689 |
ary | +0.656 |
atory | +0.625 |
gery | +0.594 |
idia | +0.593 |
Neg logit contributions | |
én | -0.561 |
everal | -0.543 |
hate | -0.491 |
DEM | -0.485 |
friend | -0.471 |
Token | 27 |
Token ID | 1983 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
ary | +8.807 |
ocrine | +8.803 |
atory | +8.116 |
ph | +8.094 |
idia | +7.293 |
Neg logit contributions | |
everal | -12.964 |
én | -12.351 |
gobl | -11.223 |
orno | -11.167 |
hate | -10.968 |
Token | ][ |
Token ID | 7131 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
én | +1.311 |
everal | +1.267 |
hate | +1.144 |
DEM | +1.127 |
friend | +1.098 |
Neg logit contributions | |
ocrine | -1.696 |
ary | -1.612 |
atory | -1.539 |
gery | -1.469 |
idia | -1.465 |
Token | 45 |
Token ID | 2231 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
ocrine | +7.951 |
ary | +7.850 |
atory | +7.287 |
ph | +7.150 |
idia | +6.630 |
Neg logit contributions | |
everal | -11.189 |
én | -10.650 |
orno | -9.661 |
gobl | -9.623 |
hate | -9.430 |
Token | ] |
Token ID | 60 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
én | +3.168 |
everal | +3.056 |
hate | +2.756 |
DEM | +2.675 |
friend | +2.646 |
Neg logit contributions | |
ocrine | -4.648 |
ary | -4.407 |
atory | -4.210 |
gery | -4.098 |
idia | -4.059 |
Token |
|
Token ID | 198 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
ocrine | +0.629 |
ary | +0.590 |
atory | +0.562 |
idia | +0.540 |
gery | +0.538 |
Neg logit contributions | |
én | -0.567 |
everal | -0.536 |
hate | -0.500 |
DEM | -0.492 |
friend | -0.483 |
Token | birth |
Token ID | 4082 |
Feature activation | +6.83e+00 |
Pos logit contributions | |
ocrine | +0.559 |
ary | +0.526 |
atory | +0.502 |
idia | +0.478 |
gery | +0.476 |
Neg logit contributions | |
én | -0.493 |
everal | -0.473 |
hate | -0.433 |
DEM | -0.426 |
friend | -0.420 |
Token | of |
Token ID | 286 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ocrine | +4.739 |
ary | +4.534 |
atory | +4.245 |
ph | +3.962 |
idia | +3.952 |
Neg logit contributions | |
én | -5.513 |
everal | -5.423 |
hate | -4.977 |
DEM | -4.903 |
orno | -4.752 |
Token | their |
Token ID | 511 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
én | +0.163 |
everal | +0.154 |
hate | +0.141 |
DEM | +0.139 |
friend | +0.138 |
Neg logit contributions | |
ocrine | -0.206 |
ary | -0.194 |
atory | -0.186 |
idia | -0.178 |
gery | -0.178 |
Token | son |
Token ID | 3367 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
én | +1.354 |
everal | +1.280 |
hate | +1.188 |
friend | +1.181 |
DEM | +1.180 |
Neg logit contributions | |
ocrine | -1.301 |
ary | -1.213 |
atory | -1.164 |
gery | -1.101 |
idia | -1.096 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
én | +1.240 |
everal | +1.173 |
hate | +1.092 |
friend | +1.079 |
DEM | +1.073 |
Neg logit contributions | |
ocrine | -1.324 |
ary | -1.208 |
atory | -1.187 |
idia | -1.127 |
gery | -1.123 |
Token | Holl |
Token ID | 11806 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
én | +0.112 |
everal | +0.108 |
hate | +0.099 |
DEM | +0.099 |
friend | +0.097 |
Neg logit contributions | |
ocrine | -0.106 |
ary | -0.098 |
atory | -0.095 |
idia | -0.090 |
gery | -0.089 |
Token | is |
Token ID | 271 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ary | +7.995 |
ocrine | +7.743 |
atory | +6.543 |
ph | +6.362 |
idia | +6.329 |
Neg logit contributions | |
everal | -14.329 |
én | -13.177 |
DEM | -13.155 |
gobl | -12.881 |
hate | -12.590 |
Token | Alvin |
Token ID | 49939 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
ocrine | +1.115 |
ary | +1.037 |
atory | +0.984 |
gery | +0.922 |
idia | +0.917 |
Neg logit contributions | |
én | -1.415 |
everal | -1.372 |
hate | -1.268 |
DEM | -1.257 |
friend | -1.231 |
Token | James |
Token ID | 3700 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
én | +0.533 |
everal | +0.513 |
hate | +0.471 |
DEM | +0.468 |
friend | +0.455 |
Neg logit contributions | |
ocrine | -0.487 |
ary | -0.452 |
atory | -0.431 |
gery | -0.410 |
idia | -0.405 |
Token | Reid |
Token ID | 16095 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
én | +0.523 |
everal | +0.495 |
hate | +0.459 |
DEM | +0.455 |
friend | +0.446 |
Neg logit contributions | |
ocrine | -0.510 |
ary | -0.470 |
atory | -0.453 |
gery | -0.429 |
idia | -0.427 |
Token | Daniels |
Token ID | 28162 |
Feature activation | -6.89e+00 |
Pos logit contributions | |
én | +1.474 |
everal | +1.372 |
hate | +1.263 |
DEM | +1.250 |
friend | +1.233 |
Neg logit contributions | |
ocrine | -1.656 |
ary | -1.530 |
atory | -1.471 |
idia | -1.406 |
gery | -1.404 |
Token | still |
Token ID | 991 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
ocrine | +0.960 |
ary | +0.900 |
atory | +0.862 |
gery | +0.820 |
idia | +0.817 |
Neg logit contributions | |
én | -0.896 |
everal | -0.853 |
hate | -0.806 |
DEM | -0.772 |
friend | -0.767 |
Token | wonder |
Token ID | 4240 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ocrine | +2.579 |
ary | +2.430 |
atory | +2.317 |
gery | +2.202 |
idia | +2.198 |
Neg logit contributions | |
én | -2.432 |
everal | -2.343 |
hate | -2.169 |
DEM | -2.112 |
friend | -2.082 |
Token | why |
Token ID | 1521 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
ocrine | +1.674 |
ary | +1.568 |
atory | +1.489 |
idia | +1.422 |
gery | +1.412 |
Neg logit contributions | |
én | -1.592 |
everal | -1.525 |
hate | -1.415 |
DEM | -1.384 |
friend | -1.368 |
Token | in |
Token ID | 287 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
ocrine | +3.172 |
ary | +3.007 |
atory | +2.862 |
gery | +2.723 |
idia | +2.716 |
Neg logit contributions | |
én | -2.774 |
everal | -2.685 |
hate | -2.442 |
DEM | -2.408 |
friend | -2.351 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ocrine | +1.562 |
ary | +1.470 |
atory | +1.395 |
gery | +1.324 |
idia | +1.322 |
Neg logit contributions | |
én | -1.522 |
everal | -1.467 |
hate | -1.352 |
DEM | -1.332 |
friend | -1.307 |
Token | hell |
Token ID | 5968 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
ocrine | +0.835 |
ary | +0.785 |
atory | +0.742 |
idia | +0.704 |
gery | +0.703 |
Neg logit contributions | |
én | -0.894 |
everal | -0.870 |
hate | -0.804 |
DEM | -0.795 |
friend | -0.782 |
Token | he |
Token ID | 339 |
Feature activation | +7.93e+00 |
Pos logit contributions | |
ocrine | +10.011 |
ary | +9.742 |
atory | +9.321 |
ph | +8.560 |
gery | +8.241 |
Neg logit contributions | |
én | -11.377 |
everal | -11.296 |
hate | -9.998 |
DEM | -9.979 |
orno | -9.747 |
Token | would |
Token ID | 561 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
ocrine | +5.644 |
ary | +5.394 |
atory | +5.125 |
gery | +4.777 |
ph | +4.762 |
Neg logit contributions | |
én | -6.292 |
everal | -6.226 |
DEM | -5.634 |
hate | -5.562 |
friend | -5.380 |
Token | ever |
Token ID | 1683 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
ocrine | +3.224 |
ary | +3.046 |
atory | +2.892 |
gery | +2.748 |
idia | +2.742 |
Neg logit contributions | |
én | -3.074 |
everal | -2.972 |
hate | -2.724 |
DEM | -2.680 |
friend | -2.626 |
Token | paraph |
Token ID | 38624 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
ocrine | +2.864 |
ary | +2.706 |
atory | +2.569 |
gery | +2.438 |
idia | +2.432 |
Neg logit contributions | |
én | -2.767 |
everal | -2.679 |
hate | -2.453 |
DEM | -2.417 |
friend | -2.367 |
Token | rase |
Token ID | 22789 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
én | +2.527 |
robe | +1.726 |
orno | +1.696 |
hate | +1.367 |
friend | +1.314 |
Neg logit contributions | |
ocrine | -13.837 |
ary | -13.376 |
ドラ | -13.306 |
イト | -12.929 |
idia | -12.881 |
Token | private |
Token ID | 2839 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
én | +2.881 |
everal | +2.828 |
friend | +2.607 |
hate | +2.587 |
DEM | +2.513 |
Neg logit contributions | |
ocrine | -3.723 |
ary | -3.405 |
idia | -3.303 |
atory | -3.294 |
ulatory | -3.104 |
Token | hospital |
Token ID | 4436 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
én | +2.443 |
everal | +2.362 |
hate | +2.244 |
friend | +2.203 |
DEM | +2.151 |
Neg logit contributions | |
ocrine | -2.605 |
ary | -2.311 |
idia | -2.244 |
atory | -2.192 |
aptic | -2.139 |
Token | where |
Token ID | 810 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
ocrine | +3.462 |
ary | +3.295 |
atory | +3.130 |
gery | +2.976 |
idia | +2.958 |
Neg logit contributions | |
én | -3.059 |
everal | -2.968 |
hate | -2.690 |
DEM | -2.656 |
friend | -2.591 |
Token | both |
Token ID | 1111 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
én | +2.772 |
everal | +2.645 |
hate | +2.440 |
DEM | +2.367 |
friend | +2.354 |
Neg logit contributions | |
ocrine | -3.850 |
ary | -3.462 |
atory | -3.388 |
idia | -3.381 |
gery | -3.239 |
Token | died |
Token ID | 3724 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
én | +2.797 |
everal | +2.667 |
hate | +2.503 |
friend | +2.419 |
DEM | +2.410 |
Neg logit contributions | |
ocrine | -3.575 |
ary | -3.269 |
atory | -3.137 |
gery | -3.076 |
idia | -3.071 |
Token | of |
Token ID | 286 |
Feature activation | -1.62e+01 |
Pos logit contributions | |
én | +3.669 |
everal | +3.465 |
hate | +3.133 |
friend | +3.033 |
DEM | +2.967 |
Neg logit contributions | |
ocrine | -5.445 |
ary | -4.897 |
atory | -4.878 |
idia | -4.871 |
gery | -4.664 |
Token | cerebral |
Token ID | 31169 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
én | +7.333 |
everal | +6.920 |
inh | +6.764 |
hate | +6.477 |
friend | +6.319 |
Neg logit contributions | |
ocrine | -13.812 |
idia | -12.426 |
ary | -11.861 |
idential | -11.834 |
SpaceEngineers | -11.818 |
Token | ha |
Token ID | 387 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
én | +6.005 |
everal | +5.363 |
hate | +5.166 |
friend | +5.064 |
DEM | +5.020 |
Neg logit contributions | |
ocrine | -9.205 |
ary | -8.539 |
atory | -7.851 |
idia | -7.772 |
gery | -7.604 |
Token | em |
Token ID | 368 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ocrine | +4.167 |
ary | +3.979 |
atory | +3.801 |
ph | +3.667 |
gery | +3.663 |
Neg logit contributions | |
én | -3.028 |
everal | -2.948 |
hate | -2.623 |
DEM | -2.608 |
friend | -2.518 |
Token | or |
Token ID | 273 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
ocrine | +1.732 |
ary | +1.667 |
atory | +1.611 |
gery | +1.560 |
idia | +1.555 |
Neg logit contributions | |
én | -0.617 |
everal | -0.579 |
hate | -0.487 |
DEM | -0.468 |
friend | -0.446 |
Token | rh |
Token ID | 17179 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
ocrine | +2.362 |
ary | +2.209 |
atory | +2.040 |
ph | +1.891 |
gery | +1.890 |
Neg logit contributions | |
én | -3.910 |
everal | -3.899 |
hate | -3.589 |
DEM | -3.577 |
friend | -3.493 |
Token | started |
Token ID | 2067 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ocrine | +0.724 |
ary | +0.675 |
atory | +0.642 |
gery | +0.616 |
idia | +0.615 |
Neg logit contributions | |
én | -0.678 |
everal | -0.648 |
hate | -0.595 |
DEM | -0.584 |
friend | -0.584 |
Token | developing |
Token ID | 5922 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
ocrine | +1.590 |
ary | +1.500 |
atory | +1.424 |
gery | +1.360 |
idia | +1.358 |
Neg logit contributions | |
én | -1.451 |
everal | -1.394 |
hate | -1.272 |
DEM | -1.259 |
friend | -1.233 |
Token | a |
Token ID | 257 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
én | +3.935 |
everal | +3.742 |
DEM | +3.376 |
hate | +3.362 |
friend | +3.296 |
Neg logit contributions | |
ocrine | -5.065 |
ary | -4.759 |
atory | -4.547 |
idia | -4.489 |
gery | -4.422 |
Token | machine |
Token ID | 4572 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
én | +1.386 |
everal | +1.338 |
DEM | +1.215 |
hate | +1.212 |
friend | +1.185 |
Neg logit contributions | |
ocrine | -1.743 |
ary | -1.645 |
atory | -1.578 |
idia | -1.549 |
gery | -1.507 |
Token | that |
Token ID | 326 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
én | +4.409 |
everal | +4.082 |
hate | +3.927 |
friend | +3.890 |
DEM | +3.813 |
Neg logit contributions | |
ocrine | -5.773 |
ary | -5.278 |
atory | -5.068 |
idia | -5.014 |
gery | -4.863 |
Token | dist |
Token ID | 1233 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
én | +3.348 |
everal | +3.077 |
hate | +2.839 |
DEM | +2.817 |
Thieves | +2.772 |
Neg logit contributions | |
ocrine | -3.658 |
ary | -3.354 |
atory | -3.240 |
idia | -3.164 |
gery | -3.086 |
Token | ills |
Token ID | 2171 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
én | +8.530 |
imes | +7.026 |
hate | +6.757 |
robe | +6.656 |
orf | +6.464 |
Neg logit contributions | |
ocrine | -12.591 |
ary | -11.729 |
atory | -11.656 |
ドラ | -11.597 |
SpaceEngineers | -11.538 |
Token | plant |
Token ID | 4618 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ocrine | +2.336 |
ary | +2.198 |
atory | +2.098 |
gery | +1.996 |
idia | +1.995 |
Neg logit contributions | |
én | -2.156 |
everal | -2.090 |
hate | -1.909 |
DEM | -1.881 |
friend | -1.839 |
Token | oils |
Token ID | 20629 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ocrine | +1.185 |
ary | +1.104 |
atory | +1.051 |
gery | +1.016 |
idia | +1.002 |
Neg logit contributions | |
én | -1.146 |
everal | -1.091 |
hate | -1.018 |
DEM | -0.992 |
friend | -0.980 |
Token | . |
Token ID | 13 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
ocrine | +1.499 |
ary | +1.405 |
atory | +1.342 |
gery | +1.286 |
idia | +1.276 |
Neg logit contributions | |
én | -1.334 |
everal | -1.274 |
hate | -1.170 |
DEM | -1.148 |
friend | -1.130 |
Token | Paul |
Token ID | 3362 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
ocrine | +2.439 |
ary | +2.298 |
atory | +2.192 |
gery | +2.094 |
idia | +2.088 |
Neg logit contributions | |
én | -2.129 |
everal | -2.021 |
hate | -1.866 |
DEM | -1.852 |
friend | -1.811 |
Token | and |
Token ID | 290 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
én | +0.752 |
everal | +0.707 |
hate | +0.656 |
DEM | +0.651 |
friend | +0.627 |
Neg logit contributions | |
ocrine | -0.827 |
ary | -0.764 |
atory | -0.733 |
gery | -0.701 |
idia | -0.700 |
Token | Content |
Token ID | 14041 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
én | +0.558 |
everal | +0.537 |
hate | +0.492 |
DEM | +0.485 |
friend | +0.475 |
Neg logit contributions | |
ocrine | -0.627 |
ary | -0.584 |
atory | -0.559 |
idia | -0.534 |
gery | -0.530 |
Token | Distribution |
Token ID | 27484 |
Feature activation | -7.51e+00 |
Pos logit contributions | |
én | +2.702 |
everal | +2.577 |
hate | +2.414 |
DEM | +2.369 |
friend | +2.350 |
Neg logit contributions | |
ocrine | -2.494 |
ary | -2.277 |
atory | -2.193 |
gery | -2.068 |
idia | -2.061 |
Token | Networks |
Token ID | 27862 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
én | +5.082 |
everal | +4.599 |
hate | +4.416 |
DEM | +4.384 |
Thieves | +4.345 |
Neg logit contributions | |
ocrine | -6.215 |
ary | -5.398 |
atory | -5.386 |
gery | -5.215 |
idia | -5.207 |
Token | ( |
Token ID | 357 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
én | +2.513 |
everal | +2.325 |
DEM | +2.189 |
hate | +2.177 |
orno | +2.088 |
Neg logit contributions | |
ocrine | -2.770 |
ary | -2.527 |
atory | -2.441 |
gery | -2.350 |
idia | -2.308 |
Token | CD |
Token ID | 8610 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
én | +2.905 |
everal | +2.705 |
DEM | +2.641 |
hate | +2.557 |
friend | +2.450 |
Neg logit contributions | |
ocrine | -2.926 |
ary | -2.727 |
atory | -2.621 |
gery | -2.499 |
idia | -2.430 |
Token | N |
Token ID | 45 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
én | +6.369 |
DEM | +5.293 |
everal | +5.136 |
hate | +4.938 |
++) | +4.899 |
Neg logit contributions | |
ocrine | -14.858 |
atory | -13.423 |
gery | -13.107 |
ary | -13.019 |
idia | -13.000 |
Token | ) |
Token ID | 8 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
én | +3.160 |
everal | +2.851 |
hate | +2.670 |
DEM | +2.646 |
friend | +2.515 |
Neg logit contributions | |
ocrine | -5.580 |
ary | -5.181 |
atory | -5.057 |
gery | -4.969 |
idia | -4.791 |
Token | that |
Token ID | 326 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
én | +1.537 |
everal | +1.426 |
DEM | +1.337 |
hate | +1.334 |
friend | +1.292 |
Neg logit contributions | |
ocrine | -1.764 |
ary | -1.630 |
atory | -1.567 |
gery | -1.516 |
idia | -1.490 |
Token | are |
Token ID | 389 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
én | +1.190 |
everal | +1.119 |
hate | +1.040 |
DEM | +1.013 |
friend | +1.002 |
Neg logit contributions | |
ocrine | -1.295 |
ary | -1.192 |
atory | -1.146 |
idia | -1.097 |
gery | -1.085 |
Token | usually |
Token ID | 3221 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
én | +1.056 |
everal | +0.994 |
DEM | +0.909 |
hate | +0.908 |
friend | +0.877 |
Neg logit contributions | |
ocrine | -1.315 |
ary | -1.224 |
atory | -1.172 |
idia | -1.130 |
gery | -1.129 |
Token | � |
Token ID | 250 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
én | +2.076 |
everal | +2.025 |
hate | +1.811 |
DEM | +1.781 |
friend | +1.724 |
Neg logit contributions | |
ocrine | -2.573 |
ary | -2.413 |
atory | -2.305 |
idia | -2.217 |
gery | -2.207 |
Token | It |
Token ID | 1026 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
én | +1.860 |
DEM | +1.683 |
everal | +1.641 |
hate | +1.627 |
friend | +1.573 |
Neg logit contributions | |
ocrine | -3.006 |
ary | -2.763 |
atory | -2.666 |
gery | -2.642 |
idia | -2.622 |
Token | was |
Token ID | 373 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
én | +1.903 |
everal | +1.743 |
hate | +1.598 |
DEM | +1.561 |
friend | +1.525 |
Neg logit contributions | |
ocrine | -2.735 |
ary | -2.547 |
atory | -2.473 |
gery | -2.412 |
idia | -2.373 |
Token | Russia |
Token ID | 3284 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
én | +0.138 |
everal | +0.131 |
DEM | +0.118 |
hate | +0.118 |
friend | +0.115 |
Neg logit contributions | |
ocrine | -0.157 |
ary | -0.145 |
atory | -0.139 |
gery | -0.135 |
idia | -0.133 |
Token | that |
Token ID | 326 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
ocrine | +0.614 |
ary | +0.570 |
atory | +0.541 |
gery | +0.524 |
idia | +0.515 |
Neg logit contributions | |
én | -0.570 |
everal | -0.536 |
hate | -0.491 |
DEM | -0.491 |
friend | -0.478 |
Token | dist |
Token ID | 1233 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
ocrine | +2.753 |
ary | +2.584 |
atory | +2.455 |
gery | +2.344 |
idia | +2.334 |
Neg logit contributions | |
én | -2.691 |
everal | -2.595 |
hate | -2.372 |
DEM | -2.354 |
friend | -2.296 |
Token | anced |
Token ID | 2903 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
én | +6.820 |
friend | +4.856 |
everal | +4.778 |
hate | +4.765 |
DEM | +4.738 |
Neg logit contributions | |
ocrine | -14.518 |
atory | -13.672 |
ary | -13.604 |
gery | -13.290 |
ドラ | -13.157 |
Token | itself |
Token ID | 2346 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
én | +3.359 |
everal | +3.159 |
hate | +2.922 |
DEM | +2.873 |
friend | +2.858 |
Neg logit contributions | |
ocrine | -3.868 |
ary | -3.487 |
atory | -3.390 |
gery | -3.276 |
idia | -3.255 |
Token | from |
Token ID | 422 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
én | +2.039 |
everal | +1.893 |
hate | +1.744 |
DEM | +1.715 |
friend | +1.693 |
Neg logit contributions | |
ocrine | -2.491 |
ary | -2.305 |
atory | -2.222 |
gery | -2.153 |
idia | -2.132 |
Token | the |
Token ID | 262 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
ocrine | +0.085 |
ary | +0.078 |
atory | +0.074 |
gery | +0.071 |
idia | +0.071 |
Neg logit contributions | |
én | -0.082 |
everal | -0.079 |
hate | -0.073 |
DEM | -0.072 |
friend | -0.071 |
Token | G |
Token ID | 402 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
ocrine | +0.653 |
ary | +0.612 |
atory | +0.576 |
idia | +0.556 |
gery | +0.552 |
Neg logit contributions | |
én | -0.631 |
everal | -0.610 |
hate | -0.561 |
DEM | -0.552 |
friend | -0.541 |
Token | USA |
Token ID | 4916 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
én | +0.666 |
everal | +0.641 |
hate | +0.585 |
DEM | +0.577 |
friend | +0.565 |
Neg logit contributions | |
ocrine | -0.627 |
ary | -0.585 |
atory | -0.558 |
gery | -0.536 |
idia | -0.530 |
Token | unit |
Token ID | 4326 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ocrine | +0.611 |
ary | +0.570 |
atory | +0.538 |
gery | +0.510 |
idia | +0.509 |
Neg logit contributions | |
én | -0.711 |
everal | -0.690 |
hate | -0.635 |
DEM | -0.627 |
friend | -0.618 |
Token | , |
Token ID | 11 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
én | +0.982 |
everal | +0.939 |
hate | +0.859 |
DEM | +0.845 |
friend | +0.826 |
Neg logit contributions | |
ocrine | -1.131 |
ary | -1.046 |
atory | -1.011 |
gery | -0.977 |
idia | -0.967 |
Token | plunged |
Token ID | 31460 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
én | +1.396 |
everal | +1.321 |
hate | +1.201 |
DEM | +1.189 |
friend | +1.158 |
Neg logit contributions | |
ocrine | -2.004 |
ary | -1.871 |
atory | -1.785 |
gery | -1.756 |
idia | -1.731 |
Token | more |
Token ID | 517 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
én | +1.602 |
everal | +1.518 |
hate | +1.388 |
DEM | +1.386 |
friend | +1.348 |
Neg logit contributions | |
ocrine | -1.859 |
ary | -1.665 |
atory | -1.650 |
idia | -1.586 |
gery | -1.579 |
Token | than |
Token ID | 621 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
én | +2.356 |
everal | +2.213 |
DEM | +1.986 |
hate | +1.942 |
friend | +1.905 |
Neg logit contributions | |
ocrine | -4.848 |
ary | -4.395 |
atory | -4.359 |
gery | -4.305 |
idia | -4.273 |
Token | 10 |
Token ID | 838 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
én | +8.077 |
DEM | +7.046 |
Thieves | +6.912 |
friend | +6.823 |
everal | +6.779 |
Neg logit contributions | |
ocrine | -13.096 |
idia | -11.504 |
ドラ | -11.454 |
aptic | -11.228 |
イト | -11.213 |
Token | percent |
Token ID | 1411 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
én | +3.305 |
everal | +3.131 |
hate | +2.795 |
DEM | +2.787 |
friend | +2.711 |
Neg logit contributions | |
ocrine | -5.046 |
ary | -4.641 |
atory | -4.631 |
gery | -4.523 |
idia | -4.467 |
Token | after |
Token ID | 706 |
Feature activation | +7.26e+00 |
Pos logit contributions | |
én | +1.421 |
everal | +1.337 |
hate | +1.257 |
DEM | +1.229 |
friend | +1.204 |
Neg logit contributions | |
ocrine | -1.621 |
ary | -1.467 |
atory | -1.449 |
gery | -1.400 |
idia | -1.381 |
Token | the |
Token ID | 262 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ocrine | +4.998 |
ary | +4.737 |
atory | +4.455 |
ph | +4.178 |
gery | +4.151 |
Neg logit contributions | |
én | -5.910 |
everal | -5.759 |
hate | -5.288 |
DEM | -5.200 |
friend | -5.159 |
Token | FDA |
Token ID | 14672 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ocrine | +1.853 |
ary | +1.740 |
atory | +1.635 |
gery | +1.542 |
idia | +1.539 |
Neg logit contributions | |
én | -2.369 |
everal | -2.301 |
hate | -2.132 |
DEM | -2.110 |
friend | -2.066 |
Token | Aub |
Token ID | 19723 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
én | +0.787 |
everal | +0.745 |
hate | +0.678 |
DEM | +0.667 |
friend | +0.663 |
Neg logit contributions | |
ocrine | -0.928 |
ary | -0.864 |
atory | -0.828 |
idia | -0.805 |
ph | -0.777 |
Token | rey |
Token ID | 4364 |
Feature activation | -9.47e+00 |
Pos logit contributions | |
én | +2.736 |
everal | +2.545 |
hate | +2.383 |
friend | +2.330 |
DEM | +2.291 |
Neg logit contributions | |
ocrine | -2.535 |
ary | -2.291 |
atory | -2.217 |
idia | -2.154 |
gery | -2.079 |
Token | / |
Token ID | 14 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
én | +5.879 |
everal | +5.125 |
friend | +4.863 |
hate | +4.709 |
Thieves | +4.558 |
Neg logit contributions | |
ocrine | -8.261 |
ary | -7.301 |
idia | -7.157 |
atory | -7.147 |
aptic | -6.660 |
Token | M |
Token ID | 44 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
én | +3.087 |
everal | +2.677 |
hate | +2.605 |
DEM | +2.603 |
friend | +2.580 |
Neg logit contributions | |
ocrine | -6.635 |
ary | -6.135 |
atory | -6.023 |
idia | -5.882 |
gery | -5.816 |
Token | atur |
Token ID | 2541 |
Feature activation | -8.50e+00 |
Pos logit contributions | |
én | +3.839 |
hate | +3.211 |
orno | +3.023 |
friend | +3.010 |
everal | +2.974 |
Neg logit contributions | |
ocrine | -6.530 |
ary | -6.158 |
ドラ | -5.885 |
gery | -5.840 |
atory | -5.826 |
Token | in |
Token ID | 259 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
én | +4.226 |
hate | +3.442 |
friend | +3.267 |
fw | +2.829 |
orf | +2.815 |
Neg logit contributions | |
ocrine | -8.431 |
ary | -7.817 |
atory | -7.479 |
ドラ | -7.421 |
gery | -7.307 |
Token | Novel |
Token ID | 24467 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
én | +9.191 |
everal | +8.294 |
friend | +7.955 |
hate | +7.727 |
Thieves | +7.489 |
Neg logit contributions | |
ocrine | -12.039 |
idia | -10.410 |
ary | -10.316 |
atory | -10.218 |
aptic | -9.968 |
Token | s |
Token ID | 82 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
ocrine | +1.240 |
ary | +1.150 |
atory | +1.109 |
idia | +1.058 |
gery | +1.051 |
Neg logit contributions | |
én | -1.156 |
everal | -1.119 |
hate | -1.022 |
DEM | -1.005 |
friend | -0.993 |
Token | , |
Token ID | 11 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
én | +3.977 |
everal | +3.800 |
hate | +3.403 |
friend | +3.382 |
DEM | +3.335 |
Neg logit contributions | |
ocrine | -4.451 |
ary | -3.996 |
atory | -3.938 |
idia | -3.825 |
gery | -3.716 |
Token | as |
Token ID | 355 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
én | +1.717 |
everal | +1.620 |
hate | +1.480 |
friend | +1.458 |
DEM | +1.451 |
Neg logit contributions | |
ocrine | -1.928 |
ary | -1.778 |
atory | -1.699 |
idia | -1.663 |
gery | -1.631 |
Token | the |
Token ID | 262 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ocrine | +2.259 |
ary | +2.122 |
atory | +2.027 |
idia | +1.933 |
gery | +1.931 |
Neg logit contributions | |
én | -1.999 |
everal | -1.933 |
hate | -1.754 |
DEM | -1.735 |
friend | -1.696 |
Token | taste |
Token ID | 6938 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
én | +0.026 |
everal | +0.025 |
hate | +0.023 |
DEM | +0.022 |
friend | +0.022 |
Neg logit contributions | |
ocrine | -0.032 |
ary | -0.030 |
atory | -0.029 |
idia | -0.027 |
gery | -0.027 |
Token | of |
Token ID | 286 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
én | +1.878 |
everal | +1.770 |
hate | +1.674 |
friend | +1.608 |
DEM | +1.588 |
Neg logit contributions | |
ocrine | -2.113 |
ary | -1.979 |
atory | -1.905 |
gery | -1.862 |
idia | -1.835 |
Token | these |
Token ID | 777 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
én | +0.467 |
everal | +0.450 |
hate | +0.409 |
DEM | +0.404 |
friend | +0.393 |
Neg logit contributions | |
ocrine | -0.578 |
ary | -0.541 |
atory | -0.521 |
idia | -0.496 |
gery | -0.491 |
Token | mushrooms |
Token ID | 23452 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
én | +0.129 |
everal | +0.124 |
hate | +0.111 |
DEM | +0.110 |
friend | +0.106 |
Neg logit contributions | |
ocrine | -0.191 |
ary | -0.180 |
atory | -0.174 |
gery | -0.166 |
idia | -0.165 |
Token | particularly |
Token ID | 3573 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
én | +1.499 |
everal | +1.407 |
hate | +1.330 |
friend | +1.268 |
DEM | +1.257 |
Neg logit contributions | |
ocrine | -1.839 |
ary | -1.716 |
atory | -1.661 |
idia | -1.608 |
gery | -1.606 |
Token | dist |
Token ID | 1233 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
én | +5.018 |
hate | +4.576 |
everal | +4.531 |
friend | +4.173 |
Thieves | +4.018 |
Neg logit contributions | |
ocrine | -8.947 |
atory | -8.365 |
idia | -8.347 |
ary | -8.325 |
ドラ | -8.078 |
Token | ast |
Token ID | 459 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
én | +8.772 |
hate | +6.934 |
robe | +6.775 |
friend | +6.753 |
leg | +6.734 |
Neg logit contributions | |
ocrine | -11.783 |
ドラ | -11.723 |
atory | -11.493 |
イト | -11.269 |
SpaceEngineers | -11.102 |
Token | eful |
Token ID | 13839 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
én | +2.019 |
everal | +1.705 |
hate | +1.638 |
friend | +1.632 |
orno | +1.550 |
Neg logit contributions | |
ocrine | -3.593 |
ary | -3.346 |
gery | -3.258 |
idia | -3.198 |
atory | -3.179 |
Token | , |
Token ID | 11 |
Feature activation | -7.31e+00 |
Pos logit contributions | |
én | +0.164 |
everal | +0.157 |
hate | +0.145 |
DEM | +0.142 |
friend | +0.140 |
Neg logit contributions | |
ocrine | -0.177 |
ary | -0.166 |
atory | -0.159 |
idia | -0.152 |
gery | -0.152 |
Token | you |
Token ID | 345 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
én | +4.580 |
everal | +4.271 |
hate | +4.118 |
friend | +3.945 |
DEM | +3.923 |
Neg logit contributions | |
ocrine | -6.135 |
ary | -5.671 |
atory | -5.444 |
idia | -5.376 |
gery | -5.247 |
Token | can |
Token ID | 460 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
ocrine | +0.164 |
ary | +0.153 |
atory | +0.147 |
gery | +0.140 |
idia | +0.139 |
Neg logit contributions | |
én | -0.159 |
everal | -0.151 |
hate | -0.142 |
DEM | -0.137 |
friend | -0.137 |
Token | oil |
Token ID | 3056 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
én | +1.925 |
hate | +1.744 |
everal | +1.696 |
friend | +1.668 |
orno | +1.632 |
Neg logit contributions | |
ocrine | -2.415 |
ary | -2.261 |
atory | -2.199 |
idia | -2.167 |
ph | -2.103 |
Token | in |
Token ID | 287 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
én | +1.304 |
hate | +1.138 |
everal | +1.135 |
DEM | +1.115 |
friend | +1.101 |
Neg logit contributions | |
ocrine | -1.534 |
ary | -1.427 |
atory | -1.359 |
idia | -1.327 |
gery | -1.314 |
Token | a |
Token ID | 257 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
én | +1.525 |
hate | +1.315 |
everal | +1.277 |
friend | +1.266 |
DEM | +1.249 |
Neg logit contributions | |
ocrine | -2.332 |
ary | -2.168 |
atory | -2.086 |
idia | -2.054 |
gery | -2.016 |
Token | skillet |
Token ID | 41306 |
Feature activation | -9.13e+00 |
Pos logit contributions | |
én | +0.427 |
everal | +0.392 |
hate | +0.378 |
DEM | +0.369 |
friend | +0.366 |
Neg logit contributions | |
ocrine | -0.496 |
ary | -0.466 |
atory | -0.439 |
idia | -0.437 |
gery | -0.424 |
Token | over |
Token ID | 625 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
én | +4.815 |
hate | +4.239 |
friend | +4.015 |
orno | +3.839 |
robe | +3.736 |
Neg logit contributions | |
ocrine | -8.368 |
idia | -7.788 |
ary | -7.772 |
atory | -7.551 |
ドラ | -7.364 |
Token | medium |
Token ID | 7090 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
én | +3.054 |
hate | +2.763 |
everal | +2.643 |
friend | +2.639 |
DEM | +2.604 |
Neg logit contributions | |
ocrine | -3.124 |
ary | -2.819 |
atory | -2.740 |
idia | -2.663 |
gery | -2.637 |
Token | - |
Token ID | 12 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
én | +4.496 |
hate | +3.947 |
friend | +3.413 |
warmed | +3.257 |
vP | +3.052 |
Neg logit contributions | |
ocrine | -15.845 |
idia | -14.887 |
aptic | -14.471 |
ドラ | -14.413 |
ary | -14.239 |
Token | high |
Token ID | 8929 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
én | +1.424 |
hate | +1.168 |
friend | +1.028 |
everal | +0.979 |
DEM | +0.852 |
Neg logit contributions | |
ocrine | -5.511 |
ary | -5.266 |
atory | -5.132 |
idia | -5.098 |
gery | -5.022 |
Token | heat |
Token ID | 4894 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
én | +2.464 |
hate | +2.340 |
warmed | +1.592 |
friend | +1.458 |
warmer | +1.409 |
Neg logit contributions | |
ocrine | -14.425 |
idia | -14.218 |
ary | -13.835 |
atory | -13.478 |
ドラ | -13.447 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
én | +1.382 |
hate | +1.227 |
DEM | +1.210 |
everal | +1.202 |
friend | +1.185 |
Neg logit contributions | |
ocrine | -1.734 |
ary | -1.597 |
atory | -1.550 |
idia | -1.495 |
gery | -1.473 |
Token | Place |
Token ID | 8474 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
én | +1.027 |
everal | +0.876 |
hate | +0.833 |
DEM | +0.796 |
friend | +0.775 |
Neg logit contributions | |
ocrine | -2.705 |
ary | -2.548 |
atory | -2.499 |
idia | -2.430 |
gery | -2.411 |
Token | clarity |
Token ID | 16287 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
én | +0.605 |
everal | +0.576 |
hate | +0.536 |
DEM | +0.525 |
friend | +0.519 |
Neg logit contributions | |
ocrine | -0.628 |
ary | -0.589 |
atory | -0.555 |
gery | -0.536 |
idia | -0.532 |
Token | � |
Token ID | 447 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ocrine | +0.287 |
ary | +0.267 |
atory | +0.257 |
gery | +0.247 |
idia | +0.246 |
Neg logit contributions | |
én | -0.242 |
everal | -0.229 |
hate | -0.211 |
DEM | -0.207 |
friend | -0.203 |
Token | � |
Token ID | 247 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
én | +0.777 |
everal | +0.746 |
hate | +0.672 |
DEM | +0.655 |
friend | +0.642 |
Neg logit contributions | |
ocrine | -1.020 |
ary | -0.961 |
atory | -0.919 |
idia | -0.890 |
gery | -0.880 |
Token | happened |
Token ID | 3022 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
ocrine | +0.736 |
ary | +0.684 |
atory | +0.655 |
gery | +0.624 |
idia | +0.622 |
Neg logit contributions | |
én | -0.718 |
everal | -0.686 |
hate | -0.633 |
DEM | -0.621 |
friend | -0.613 |
Token | a |
Token ID | 257 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
ocrine | +3.386 |
ary | +3.220 |
atory | +3.045 |
gery | +2.882 |
idia | +2.875 |
Neg logit contributions | |
én | -3.324 |
everal | -3.233 |
hate | -2.958 |
DEM | -2.921 |
friend | -2.848 |
Token | long |
Token ID | 890 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
én | +2.474 |
everal | +2.457 |
hate | +2.164 |
DEM | +2.152 |
friend | +2.136 |
Neg logit contributions | |
ocrine | -3.190 |
ary | -2.942 |
atory | -2.878 |
gery | -2.749 |
idia | -2.739 |
Token | way |
Token ID | 835 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
én | +6.552 |
everal | +6.237 |
hate | +5.342 |
DEM | +5.194 |
orno | +4.949 |
Neg logit contributions | |
ocrine | -14.191 |
gery | -12.883 |
ary | -12.825 |
atory | -12.678 |
idia | -12.549 |
Token | back |
Token ID | 736 |
Feature activation | +6.96e+00 |
Pos logit contributions | |
én | +2.776 |
everal | +2.540 |
hate | +2.326 |
friend | +2.291 |
DEM | +2.257 |
Neg logit contributions | |
ocrine | -3.702 |
ary | -3.418 |
atory | -3.314 |
gery | -3.225 |
idia | -3.178 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ocrine | +4.923 |
ary | +4.703 |
atory | +4.403 |
gery | +4.155 |
ph | +4.139 |
Neg logit contributions | |
én | -5.469 |
everal | -5.408 |
hate | -4.955 |
DEM | -4.900 |
friend | -4.771 |
Token | and |
Token ID | 290 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
én | +0.776 |
everal | +0.741 |
hate | +0.675 |
DEM | +0.668 |
friend | +0.654 |
Neg logit contributions | |
ocrine | -0.955 |
ary | -0.896 |
atory | -0.856 |
gery | -0.830 |
idia | -0.825 |
Token | it |
Token ID | 340 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
én | +0.217 |
everal | +0.207 |
hate | +0.188 |
DEM | +0.186 |
friend | +0.183 |
Neg logit contributions | |
ocrine | -0.256 |
ary | -0.239 |
atory | -0.230 |
gery | -0.221 |
idia | -0.220 |
Token | water |
Token ID | 1660 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ocrine | +1.264 |
ary | +1.187 |
atory | +1.142 |
idia | +1.088 |
gery | +1.085 |
Neg logit contributions | |
én | -1.033 |
everal | -0.995 |
hate | -0.910 |
DEM | -0.896 |
friend | -0.875 |
Token | into |
Token ID | 656 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
én | +1.340 |
everal | +1.264 |
hate | +1.179 |
DEM | +1.152 |
friend | +1.140 |
Neg logit contributions | |
ocrine | -1.572 |
ary | -1.454 |
atory | -1.404 |
gery | -1.338 |
idia | -1.337 |
Token | a |
Token ID | 257 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
én | +0.843 |
everal | +0.815 |
hate | +0.737 |
DEM | +0.716 |
friend | +0.702 |
Neg logit contributions | |
ocrine | -1.173 |
ary | -1.103 |
atory | -1.046 |
idia | -1.021 |
gery | -1.009 |
Token | sauce |
Token ID | 10746 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
én | +2.039 |
everal | +1.991 |
hate | +1.840 |
DEM | +1.804 |
friend | +1.763 |
Neg logit contributions | |
ocrine | -2.801 |
ary | -2.621 |
idia | -2.513 |
atory | -2.500 |
gery | -2.403 |
Token | pan |
Token ID | 6839 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
én | +0.035 |
everal | +0.033 |
hate | +0.030 |
DEM | +0.030 |
friend | +0.029 |
Neg logit contributions | |
ocrine | -0.045 |
ary | -0.042 |
atory | -0.040 |
idia | -0.039 |
gery | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
én | +4.543 |
everal | +4.191 |
hate | +3.963 |
DEM | +3.870 |
friend | +3.788 |
Neg logit contributions | |
ocrine | -6.365 |
ary | -5.892 |
idia | -5.769 |
atory | -5.762 |
gery | -5.412 |
Token | bring |
Token ID | 2222 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
én | +7.148 |
warmed | +6.468 |
hate | +6.389 |
everal | +6.237 |
Thieves | +6.146 |
Neg logit contributions | |
ocrine | -13.562 |
idia | -12.169 |
atory | -12.070 |
ary | -11.716 |
ulatory | -11.526 |
Token | it |
Token ID | 340 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
ocrine | +1.190 |
ary | +1.120 |
atory | +1.070 |
gery | +1.014 |
idia | +1.011 |
Neg logit contributions | |
én | -1.106 |
everal | -1.071 |
hate | -0.981 |
DEM | -0.970 |
friend | -0.947 |
Token | to |
Token ID | 284 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
ocrine | +0.286 |
ary | +0.268 |
atory | +0.257 |
idia | +0.245 |
gery | +0.243 |
Neg logit contributions | |
én | -0.262 |
everal | -0.252 |
hate | -0.232 |
DEM | -0.226 |
friend | -0.225 |
Token | a |
Token ID | 257 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
én | +1.474 |
everal | +1.403 |
hate | +1.268 |
DEM | +1.253 |
friend | +1.219 |
Neg logit contributions | |
ocrine | -2.111 |
ary | -1.972 |
atory | -1.864 |
idia | -1.825 |
gery | -1.798 |
Token | boil |
Token ID | 20667 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
én | +1.968 |
everal | +1.909 |
hate | +1.723 |
DEM | +1.713 |
friend | +1.648 |
Neg logit contributions | |
ocrine | -2.916 |
ary | -2.695 |
atory | -2.605 |
idia | -2.590 |
gery | -2.497 |
Token | y |
Token ID | 88 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
én | +4.669 |
everal | +4.201 |
DEM | +4.174 |
hate | +4.160 |
fw | +4.032 |
Neg logit contributions | |
ocrine | -7.769 |
ary | -7.024 |
atory | -6.972 |
gery | -6.797 |
idia | -6.678 |
Token | / |
Token ID | 1220 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
én | +1.243 |
everal | +1.173 |
hate | +1.079 |
DEM | +1.068 |
friend | +1.041 |
Neg logit contributions | |
ocrine | -1.695 |
ary | -1.598 |
atory | -1.536 |
gery | -1.474 |
idia | -1.469 |
Token | _ |
Token ID | 4808 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
én | +1.743 |
everal | +1.685 |
DEM | +1.587 |
hate | +1.573 |
friend | +1.528 |
Neg logit contributions | |
ocrine | -2.014 |
ary | -1.858 |
atory | -1.751 |
idia | -1.710 |
gery | -1.698 |
Token | P |
Token ID | 47 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
én | +5.133 |
everal | +4.807 |
DEM | +4.685 |
hate | +4.575 |
friend | +4.280 |
Neg logit contributions | |
ocrine | -9.419 |
ary | -8.848 |
atory | -8.599 |
idia | -8.476 |
gery | -8.377 |
Token | ulse |
Token ID | 9615 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
én | +4.428 |
hate | +3.904 |
orno | +3.883 |
DEM | +3.872 |
vP | +3.820 |
Neg logit contributions | |
ocrine | -4.372 |
ary | -4.108 |
atory | -3.899 |
gery | -3.830 |
idia | -3.804 |
Token | Per |
Token ID | 5990 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
én | +2.443 |
DEM | +2.159 |
hate | +2.100 |
friend | +2.043 |
FG | +2.006 |
Neg logit contributions | |
ocrine | -4.755 |
ary | -4.371 |
atory | -4.274 |
idia | -4.227 |
gery | -4.200 |
Token | iod |
Token ID | 2101 |
Feature activation | -9.25e+00 |
Pos logit contributions | |
én | +4.458 |
hate | +3.597 |
norm | +3.461 |
fw | +3.255 |
friend | +3.095 |
Neg logit contributions | |
ocrine | -15.816 |
ドラ | -14.704 |
ary | -14.544 |
unsuccessfully | -14.316 |
idia | -14.269 |
Token | * |
Token ID | 1635 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
én | +5.008 |
everal | +4.707 |
DEM | +4.360 |
hate | +4.245 |
friend | +4.220 |
Neg logit contributions | |
ocrine | -8.383 |
ary | -7.710 |
atory | -7.509 |
idia | -7.358 |
gery | -7.291 |
Token | TA |
Token ID | 21664 |
Feature activation | -8.89e+00 |
Pos logit contributions | |
én | +2.943 |
everal | +2.818 |
DEM | +2.704 |
hate | +2.660 |
friend | +2.580 |
Neg logit contributions | |
ocrine | -3.525 |
ary | -3.241 |
atory | -3.072 |
idia | -3.006 |
gery | -2.982 |
Token | U |
Token ID | 52 |
Feature activation | -7.17e+00 |
Pos logit contributions | |
én | +4.683 |
DEM | +4.373 |
FG | +4.132 |
hate | +4.097 |
vP | +4.007 |
Neg logit contributions | |
ocrine | -8.038 |
ary | -7.621 |
atory | -7.401 |
idia | -7.187 |
gery | -7.135 |
Token | ) |
Token ID | 8 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
én | +3.738 |
everal | +3.287 |
DEM | +3.234 |
hate | +3.229 |
friend | +3.156 |
Neg logit contributions | |
ocrine | -6.800 |
ary | -6.330 |
atory | -6.186 |
idia | -5.978 |
gery | -5.950 |
Token | HQ |
Token ID | 41275 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
én | +2.149 |
everal | +1.952 |
DEM | +1.847 |
hate | +1.818 |
friend | +1.719 |
Neg logit contributions | |
ocrine | -3.653 |
ary | -3.391 |
atory | -3.317 |
gery | -3.166 |
idia | -3.153 |
Token | ) |
Token ID | 8 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
én | +3.356 |
everal | +3.117 |
hate | +2.786 |
DEM | +2.785 |
friend | +2.667 |
Neg logit contributions | |
ocrine | -6.957 |
ary | -6.469 |
atory | -6.314 |
idia | -6.062 |
gery | -6.034 |
Token | | |
Token ID | 930 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
én | +3.571 |
everal | +3.392 |
hate | +3.083 |
DEM | +3.063 |
friend | +3.007 |
Neg logit contributions | |
ocrine | -5.379 |
ary | -5.052 |
atory | -4.868 |
idia | -4.773 |
gery | -4.688 |
Token | iTunes |
Token ID | 4830 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
ocrine | +1.624 |
ary | +1.534 |
atory | +1.460 |
gery | +1.387 |
idia | +1.385 |
Neg logit contributions | |
én | -1.498 |
everal | -1.448 |
hate | -1.323 |
DEM | -1.307 |
friend | -1.278 |
Token | ( |
Token ID | 357 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
én | +3.883 |
everal | +3.655 |
hate | +3.430 |
DEM | +3.416 |
friend | +3.358 |
Neg logit contributions | |
ocrine | -4.634 |
ary | -4.254 |
atory | -4.133 |
idia | -3.936 |
gery | -3.899 |
Token | SD |
Token ID | 10305 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
én | +0.415 |
everal | +0.388 |
hate | +0.356 |
DEM | +0.355 |
friend | +0.340 |
Neg logit contributions | |
ocrine | -0.636 |
ary | -0.597 |
atory | -0.574 |
idia | -0.551 |
gery | -0.549 |
Token | ) |
Token ID | 8 |
Feature activation | -6.76e+00 |
Pos logit contributions | |
én | +6.615 |
everal | +6.264 |
DEM | +5.828 |
hate | +5.628 |
friend | +5.477 |
Neg logit contributions | |
ocrine | -14.587 |
ary | -13.326 |
atory | -13.094 |
idia | -12.593 |
gery | -12.584 |
Token |
|
Token ID | 198 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
én | +4.006 |
everal | +3.798 |
hate | +3.478 |
DEM | +3.473 |
friend | +3.379 |
Neg logit contributions | |
ocrine | -5.936 |
ary | -5.543 |
atory | -5.363 |
idia | -5.247 |
gery | -5.175 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
én | +1.238 |
hate | +1.095 |
friend | +1.075 |
DEM | +1.064 |
fw | +1.029 |
Neg logit contributions | |
ocrine | -1.551 |
ary | -1.421 |
atory | -1.379 |
idia | -1.351 |
gery | -1.327 |
Token | R |
Token ID | 49 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
én | +0.748 |
everal | +0.709 |
hate | +0.667 |
DEM | +0.663 |
friend | +0.642 |
Neg logit contributions | |
ocrine | -1.013 |
ary | -0.948 |
atory | -0.918 |
idia | -0.885 |
gery | -0.879 |
Token | SS |
Token ID | 5432 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
én | +0.191 |
everal | +0.181 |
hate | +0.166 |
DEM | +0.166 |
friend | +0.159 |
Neg logit contributions | |
ocrine | -0.214 |
ary | -0.200 |
atory | -0.191 |
gery | -0.185 |
idia | -0.182 |
Token | said |
Token ID | 531 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
ocrine | +0.327 |
ary | +0.302 |
atory | +0.286 |
gery | +0.277 |
idia | +0.275 |
Neg logit contributions | |
én | -0.343 |
everal | -0.329 |
hate | -0.306 |
DEM | -0.305 |
friend | -0.295 |
Token | industrial |
Token ID | 7593 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
én | +1.833 |
everal | +1.789 |
hate | +1.664 |
DEM | +1.638 |
friend | +1.600 |
Neg logit contributions | |
ocrine | -2.218 |
ary | -1.931 |
atory | -1.891 |
idia | -1.856 |
gery | -1.837 |
Token | output |
Token ID | 5072 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
én | +2.237 |
everal | +2.173 |
hate | +2.067 |
DEM | +2.014 |
friend | +1.988 |
Neg logit contributions | |
ocrine | -2.499 |
ary | -2.193 |
atory | -2.085 |
idia | -2.054 |
gery | -2.017 |
Token | rose |
Token ID | 8278 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
én | +1.145 |
everal | +1.077 |
hate | +1.017 |
DEM | +1.009 |
friend | +0.986 |
Neg logit contributions | |
ocrine | -1.371 |
ary | -1.210 |
atory | -1.188 |
idia | -1.158 |
gery | -1.154 |
Token | more |
Token ID | 517 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
én | +1.706 |
everal | +1.580 |
DEM | +1.508 |
hate | +1.493 |
friend | +1.448 |
Neg logit contributions | |
ocrine | -2.138 |
ary | -1.882 |
atory | -1.843 |
idia | -1.820 |
gery | -1.809 |
Token | than |
Token ID | 621 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
én | +2.018 |
everal | +1.817 |
DEM | +1.732 |
hate | +1.718 |
friend | +1.638 |
Neg logit contributions | |
ocrine | -3.668 |
ary | -3.235 |
gery | -3.169 |
atory | -3.161 |
idia | -3.160 |
Token | expected |
Token ID | 2938 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
én | +7.119 |
DEM | +6.668 |
Thieves | +6.434 |
accustomed | +6.232 |
warmed | +6.171 |
Neg logit contributions | |
ocrine | -13.189 |
idia | -11.380 |
aptic | -11.373 |
イト | -11.212 |
ドラ | -11.183 |
Token | in |
Token ID | 287 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
én | +2.675 |
everal | +2.472 |
hate | +2.357 |
DEM | +2.316 |
friend | +2.267 |
Neg logit contributions | |
ocrine | -3.622 |
atory | -3.204 |
ary | -3.203 |
idia | -3.115 |
gery | -3.088 |
Token | September |
Token ID | 2693 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
én | +2.321 |
everal | +2.270 |
hate | +2.129 |
DEM | +2.042 |
Thieves | +2.013 |
Neg logit contributions | |
ocrine | -3.135 |
ary | -2.755 |
atory | -2.705 |
gery | -2.648 |
idia | -2.642 |
Token | , |
Token ID | 11 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
én | +0.068 |
everal | +0.065 |
hate | +0.061 |
DEM | +0.059 |
friend | +0.058 |
Neg logit contributions | |
ocrine | -0.079 |
ary | -0.072 |
atory | -0.071 |
gery | -0.068 |
idia | -0.067 |
Token | boosted |
Token ID | 29657 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
én | +3.236 |
everal | +3.083 |
DEM | +2.894 |
hate | +2.886 |
friend | +2.799 |
Neg logit contributions | |
ocrine | -4.351 |
ary | -3.855 |
atory | -3.738 |
gery | -3.657 |
idia | -3.637 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ocrine | +0.373 |
ary | +0.352 |
atory | +0.333 |
idia | +0.325 |
gery | +0.321 |
Neg logit contributions | |
én | -0.307 |
everal | -0.293 |
hate | -0.269 |
DEM | -0.265 |
friend | -0.259 |
Token | handful |
Token ID | 10089 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
ocrine | +0.828 |
ary | +0.777 |
atory | +0.743 |
idia | +0.714 |
gery | +0.707 |
Neg logit contributions | |
én | -0.713 |
everal | -0.696 |
hate | -0.633 |
DEM | -0.627 |
friend | -0.611 |
Token | of |
Token ID | 286 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
ocrine | +2.719 |
ary | +2.566 |
atory | +2.422 |
gery | +2.283 |
idia | +2.273 |
Neg logit contributions | |
én | -3.062 |
everal | -2.983 |
hate | -2.735 |
DEM | -2.707 |
friend | -2.648 |
Token | symbols |
Token ID | 14354 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
ocrine | +2.542 |
ary | +2.406 |
atory | +2.291 |
gery | +2.184 |
idia | +2.182 |
Neg logit contributions | |
én | -2.209 |
everal | -2.135 |
hate | -1.949 |
DEM | -1.921 |
friend | -1.874 |
Token | to |
Token ID | 284 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
én | +0.666 |
everal | +0.638 |
hate | +0.594 |
DEM | +0.576 |
friend | +0.574 |
Neg logit contributions | |
ocrine | -0.760 |
ary | -0.699 |
atory | -0.678 |
idia | -0.649 |
gery | -0.639 |
Token | dist |
Token ID | 1233 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
én | +1.257 |
everal | +1.190 |
hate | +1.107 |
DEM | +1.099 |
friend | +1.074 |
Neg logit contributions | |
ocrine | -1.510 |
ary | -1.396 |
atory | -1.348 |
idia | -1.291 |
gery | -1.271 |
Token | ill |
Token ID | 359 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
én | +8.136 |
hate | +6.832 |
friend | +6.679 |
robe | +6.434 |
DEM | +6.373 |
Neg logit contributions | |
ocrine | -12.051 |
atory | -11.607 |
ドラ | -11.497 |
イト | -11.031 |
76561 | -11.021 |
Token | a |
Token ID | 257 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
én | +0.690 |
everal | +0.665 |
hate | +0.628 |
DEM | +0.600 |
friend | +0.597 |
Neg logit contributions | |
ocrine | -0.794 |
ary | -0.727 |
atory | -0.697 |
idia | -0.679 |
gery | -0.673 |
Token | weight |
Token ID | 3463 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
én | +0.907 |
everal | +0.892 |
hate | +0.831 |
DEM | +0.806 |
friend | +0.798 |
Neg logit contributions | |
ocrine | -1.077 |
ary | -1.001 |
atory | -0.963 |
idia | -0.940 |
gery | -0.915 |
Token | y |
Token ID | 88 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ocrine | +1.382 |
ary | +1.302 |
atory | +1.254 |
gery | +1.202 |
idia | +1.196 |
Neg logit contributions | |
én | -1.027 |
everal | -0.984 |
hate | -0.897 |
DEM | -0.875 |
friend | -0.859 |
Token | concept |
Token ID | 3721 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
én | +0.742 |
everal | +0.705 |
hate | +0.668 |
DEM | +0.644 |
friend | +0.635 |
Neg logit contributions | |
ocrine | -0.865 |
ary | -0.805 |
atory | -0.776 |
idia | -0.749 |
gery | -0.730 |
Token | hard |
Token ID | 1327 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
én | +1.391 |
everal | +1.325 |
hate | +1.203 |
DEM | +1.189 |
friend | +1.182 |
Neg logit contributions | |
ocrine | -1.728 |
ary | -1.612 |
atory | -1.541 |
gery | -1.508 |
idia | -1.494 |
Token | to |
Token ID | 284 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ocrine | +1.709 |
ary | +1.619 |
atory | +1.552 |
gery | +1.482 |
idia | +1.476 |
Neg logit contributions | |
én | -1.329 |
everal | -1.276 |
hate | -1.158 |
DEM | -1.136 |
friend | -1.114 |
Token | get |
Token ID | 651 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
ocrine | +1.796 |
ary | +1.703 |
atory | +1.624 |
gery | +1.551 |
idia | +1.546 |
Neg logit contributions | |
én | -1.452 |
everal | -1.399 |
hate | -1.266 |
DEM | -1.249 |
friend | -1.220 |
Token | to |
Token ID | 284 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
én | +3.592 |
everal | +3.338 |
hate | +3.039 |
friend | +2.988 |
DEM | +2.964 |
Neg logit contributions | |
ocrine | -4.157 |
ary | -3.787 |
atory | -3.595 |
idia | -3.563 |
gery | -3.538 |
Token | except |
Token ID | 2845 |
Feature activation | -6.62e+00 |
Pos logit contributions | |
ocrine | +0.181 |
ary | +0.170 |
atory | +0.161 |
gery | +0.156 |
idia | +0.154 |
Neg logit contributions | |
én | -0.167 |
everal | -0.159 |
hate | -0.146 |
DEM | -0.143 |
friend | -0.141 |
Token | by |
Token ID | 416 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
én | +4.321 |
everal | +3.996 |
hate | +3.625 |
friend | +3.578 |
DEM | +3.532 |
Neg logit contributions | |
ocrine | -5.450 |
ary | -5.013 |
atory | -4.812 |
gery | -4.751 |
idia | -4.695 |
Token | water |
Token ID | 1660 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
én | +7.067 |
everal | +6.657 |
Thieves | +6.565 |
friend | +6.421 |
accustomed | +6.158 |
Neg logit contributions | |
ocrine | -12.743 |
ary | -11.237 |
idia | -11.044 |
atory | -10.877 |
ドラ | -10.848 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
én | +0.783 |
everal | +0.742 |
hate | +0.690 |
DEM | +0.676 |
friend | +0.670 |
Neg logit contributions | |
ocrine | -0.894 |
ary | -0.831 |
atory | -0.800 |
gery | -0.769 |
idia | -0.755 |
Token | the |
Token ID | 262 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
én | +1.313 |
everal | +1.265 |
hate | +1.154 |
DEM | +1.129 |
friend | +1.106 |
Neg logit contributions | |
ocrine | -1.588 |
ary | -1.489 |
atory | -1.428 |
gery | -1.381 |
idia | -1.365 |
Token | Sund |
Token ID | 3309 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
én | +1.220 |
everal | +1.166 |
hate | +1.061 |
DEM | +1.033 |
friend | +1.015 |
Neg logit contributions | |
ocrine | -1.716 |
ary | -1.612 |
atory | -1.549 |
gery | -1.493 |
idia | -1.481 |
Token | arb |
Token ID | 38039 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
én | +0.876 |
everal | +0.635 |
hate | +0.625 |
friend | +0.551 |
orno | +0.536 |
Neg logit contributions | |
ocrine | -3.627 |
ary | -3.455 |
atory | -3.380 |
gery | -3.316 |
idia | -3.308 |
Token | system |
Token ID | 1080 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
én | +2.119 |
everal | +1.976 |
DEM | +1.875 |
hate | +1.832 |
fw | +1.765 |
Neg logit contributions | |
ocrine | -3.048 |
ary | -2.761 |
atory | -2.699 |
gery | -2.624 |
idia | -2.596 |
Token | could |
Token ID | 714 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ocrine | +1.975 |
ary | +1.850 |
atory | +1.766 |
gery | +1.671 |
idia | +1.669 |
Neg logit contributions | |
én | -2.010 |
everal | -1.934 |
hate | -1.795 |
DEM | -1.769 |
friend | -1.732 |
Token | definitely |
Token ID | 4753 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
én | +1.101 |
everal | +1.021 |
hate | +0.965 |
DEM | +0.937 |
friend | +0.921 |
Neg logit contributions | |
ocrine | -1.358 |
ary | -1.254 |
atory | -1.209 |
gery | -1.160 |
idia | -1.150 |
Token | benefit |
Token ID | 4414 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ocrine | +3.447 |
ary | +3.317 |
atory | +3.141 |
ph | +2.960 |
gery | +2.959 |
Neg logit contributions | |
én | -3.196 |
everal | -3.177 |
hate | -2.818 |
DEM | -2.815 |
friend | -2.733 |
Token | from |
Token ID | 422 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
én | +0.138 |
everal | +0.132 |
hate | +0.121 |
DEM | +0.120 |
friend | +0.117 |
Neg logit contributions | |
ocrine | -0.147 |
ary | -0.138 |
atory | -0.131 |
gery | -0.125 |
idia | -0.125 |
Token | spending |
Token ID | 4581 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
én | +3.867 |
everal | +3.594 |
DEM | +3.341 |
hate | +3.283 |
friend | +3.188 |
Neg logit contributions | |
ocrine | -4.848 |
ary | -4.385 |
atory | -4.196 |
gery | -4.105 |
idia | -4.064 |
Token | some |
Token ID | 617 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
én | +6.873 |
everal | +6.359 |
hate | +5.771 |
Thieves | +5.637 |
orno | +5.549 |
Neg logit contributions | |
ocrine | -13.513 |
ary | -12.293 |
idia | -12.230 |
gery | -11.861 |
ドラ | -11.773 |
Token | time |
Token ID | 640 |
Feature activation | -6.85e+00 |
Pos logit contributions | |
én | +4.059 |
everal | +3.820 |
hate | +3.443 |
Thieves | +3.193 |
HOW | +3.049 |
Neg logit contributions | |
ocrine | -12.351 |
ary | -11.557 |
idia | -11.227 |
gery | -11.202 |
atory | -11.078 |
Token | with |
Token ID | 351 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
én | +4.551 |
everal | +4.146 |
hate | +3.929 |
DEM | +3.886 |
fw | +3.818 |
Neg logit contributions | |
ocrine | -5.634 |
ary | -5.038 |
atory | -4.896 |
gery | -4.811 |
idia | -4.769 |
Token | Fedora |
Token ID | 32245 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
én | +3.101 |
everal | +2.972 |
DEM | +2.737 |
hate | +2.709 |
friend | +2.629 |
Neg logit contributions | |
ocrine | -4.030 |
ary | -3.757 |
atory | -3.595 |
gery | -3.445 |
idia | -3.417 |
Token | , |
Token ID | 11 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
én | +1.884 |
everal | +1.795 |
DEM | +1.690 |
hate | +1.660 |
friend | +1.628 |
Neg logit contributions | |
ocrine | -1.650 |
ary | -1.496 |
atory | -1.445 |
gery | -1.393 |
idia | -1.360 |
Token | , |
Token ID | 11 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
én | +3.605 |
everal | +3.431 |
hate | +3.205 |
DEM | +3.193 |
friend | +3.050 |
Neg logit contributions | |
ocrine | -4.761 |
ary | -4.345 |
atory | -4.162 |
gery | -4.113 |
idia | -4.092 |
Token | and |
Token ID | 290 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
én | +1.423 |
everal | +1.370 |
DEM | +1.274 |
hate | +1.238 |
friend | +1.198 |
Neg logit contributions | |
ocrine | -1.890 |
ary | -1.756 |
atory | -1.664 |
gery | -1.642 |
idia | -1.631 |
Token | those |
Token ID | 883 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
én | +1.919 |
everal | +1.850 |
DEM | +1.735 |
hate | +1.695 |
friend | +1.646 |
Neg logit contributions | |
ocrine | -2.064 |
ary | -1.886 |
atory | -1.788 |
gery | -1.767 |
idia | -1.744 |
Token | in |
Token ID | 287 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
én | +2.695 |
everal | +2.602 |
DEM | +2.446 |
hate | +2.368 |
friend | +2.284 |
Neg logit contributions | |
ocrine | -3.320 |
ary | -3.053 |
atory | -2.909 |
gery | -2.895 |
idia | -2.867 |
Token | Virginia |
Token ID | 6025 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
ocrine | +2.824 |
ary | +2.664 |
atory | +2.519 |
gery | +2.370 |
idia | +2.358 |
Neg logit contributions | |
én | -3.211 |
everal | -3.122 |
hate | -2.875 |
DEM | -2.835 |
friend | -2.782 |
Token | dist |
Token ID | 1233 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
én | +2.251 |
everal | +2.139 |
DEM | +2.034 |
hate | +1.993 |
friend | +1.926 |
Neg logit contributions | |
ocrine | -2.571 |
ary | -2.360 |
gery | -2.248 |
atory | -2.240 |
idia | -2.155 |
Token | r |
Token ID | 81 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
én | +5.391 |
hate | +4.528 |
friend | +4.524 |
fw | +4.102 |
DEM | +4.022 |
Neg logit contributions | |
ocrine | -14.775 |
ドラ | -13.726 |
ary | -13.554 |
gery | -13.389 |
atory | -13.304 |
Token | usted |
Token ID | 8459 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
én | +0.753 |
everal | +0.656 |
hate | +0.581 |
DEM | +0.560 |
friend | +0.542 |
Neg logit contributions | |
ocrine | -2.511 |
ary | -2.404 |
atory | -2.308 |
gery | -2.249 |
idia | -2.229 |
Token | her |
Token ID | 607 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
én | +1.162 |
everal | +1.125 |
DEM | +1.046 |
hate | +1.042 |
friend | +1.013 |
Neg logit contributions | |
ocrine | -1.220 |
ary | -1.123 |
atory | -1.062 |
gery | -1.029 |
idia | -1.028 |
Token | 55 |
Token ID | 5996 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
ocrine | +1.748 |
ary | +1.628 |
atory | +1.546 |
gery | +1.456 |
idia | +1.456 |
Neg logit contributions | |
én | -2.015 |
everal | -1.952 |
hate | -1.810 |
DEM | -1.795 |
friend | -1.764 |
Token | percent |
Token ID | 1411 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
én | +2.154 |
everal | +2.087 |
hate | +1.889 |
DEM | +1.862 |
friend | +1.811 |
Neg logit contributions | |
ocrine | -2.925 |
ary | -2.764 |
atory | -2.642 |
gery | -2.556 |
idia | -2.535 |
Token | , |
Token ID | 11 |
Feature activation | +7.95e+00 |
Pos logit contributions | |
én | +1.792 |
hate | +1.579 |
friend | +1.552 |
DEM | +1.541 |
fw | +1.487 |
Neg logit contributions | |
ocrine | -2.264 |
ary | -2.075 |
atory | -2.024 |
idia | -1.964 |
gery | -1.962 |
Token | 14 |
Token ID | 1478 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ocrine | +4.343 |
ary | +4.183 |
atory | +3.816 |
ph | +3.462 |
idia | +3.422 |
Neg logit contributions | |
everal | -7.554 |
én | -7.514 |
hate | -6.888 |
DEM | -6.745 |
orno | -6.664 |
Token | } |
Token ID | 92 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
én | +0.847 |
hate | +0.692 |
friend | +0.687 |
everal | +0.670 |
DEM | +0.670 |
Neg logit contributions | |
ocrine | -1.989 |
ary | -1.885 |
atory | -1.835 |
idia | -1.779 |
gery | -1.770 |
Token | -> |
Token ID | 4613 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
én | +0.821 |
everal | +0.733 |
hate | +0.725 |
DEM | +0.712 |
friend | +0.709 |
Neg logit contributions | |
ocrine | -0.855 |
ary | -0.791 |
atory | -0.762 |
idia | -0.730 |
gery | -0.729 |
Token | " |
Token ID | 366 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
ocrine | +1.001 |
ary | +0.929 |
atory | +0.873 |
idia | +0.822 |
gery | +0.820 |
Neg logit contributions | |
én | -1.366 |
everal | -1.302 |
hate | -1.235 |
DEM | -1.219 |
friend | -1.204 |
Token | D |
Token ID | 35 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
én | +3.499 |
everal | +3.190 |
DEM | +3.110 |
hate | +3.054 |
friend | +2.955 |
Neg logit contributions | |
ocrine | -5.544 |
ary | -5.128 |
atory | -5.043 |
gery | -4.977 |
idia | -4.876 |
Token | ", |
Token ID | 1600 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
én | +7.119 |
everal | +6.838 |
hate | +6.019 |
friend | +5.942 |
DEM | +5.702 |
Neg logit contributions | |
ocrine | -13.228 |
ary | -12.213 |
atory | -12.133 |
gery | -11.895 |
idia | -11.880 |
Token | { |
Token ID | 1391 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
ocrine | +1.653 |
ary | +1.573 |
atory | +1.479 |
gery | +1.376 |
ph | +1.365 |
Neg logit contributions | |
én | -2.099 |
everal | -2.038 |
hate | -1.867 |
DEM | -1.855 |
friend | -1.812 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ocrine | +3.009 |
ary | +2.879 |
atory | +2.672 |
ph | +2.542 |
gery | +2.488 |
Neg logit contributions | |
én | -3.759 |
everal | -3.689 |
hate | -3.329 |
DEM | -3.294 |
orno | -3.218 |
Token | , |
Token ID | 11 |
Feature activation | +6.40e+00 |
Pos logit contributions | |
ocrine | +1.501 |
ary | +1.420 |
atory | +1.345 |
gery | +1.273 |
idia | +1.269 |
Neg logit contributions | |
én | -1.521 |
everal | -1.486 |
hate | -1.351 |
DEM | -1.335 |
friend | -1.304 |
Token | 15 |
Token ID | 1315 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
ocrine | +3.696 |
ary | +3.508 |
atory | +3.239 |
ph | +2.964 |
gery | +2.956 |
Neg logit contributions | |
én | -5.962 |
everal | -5.915 |
hate | -5.436 |
DEM | -5.334 |
friend | -5.242 |
Token | part |
Token ID | 636 |
Feature activation | -5.67e+00 |
Pos logit contributions | |
én | +2.705 |
everal | +2.562 |
hate | +2.427 |
friend | +2.347 |
DEM | +2.326 |
Neg logit contributions | |
ocrine | -3.037 |
ary | -2.775 |
atory | -2.699 |
gery | -2.571 |
idia | -2.562 |
Token | happens |
Token ID | 4325 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
én | +4.248 |
everal | +3.769 |
hate | +3.659 |
friend | +3.569 |
DEM | +3.497 |
Neg logit contributions | |
ocrine | -4.301 |
ary | -3.932 |
atory | -3.784 |
gery | -3.692 |
idia | -3.692 |
Token | a |
Token ID | 257 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
ocrine | +3.291 |
ary | +3.123 |
atory | +2.955 |
gery | +2.795 |
idia | +2.786 |
Neg logit contributions | |
én | -3.373 |
everal | -3.288 |
hate | -3.011 |
DEM | -2.974 |
friend | -2.904 |
Token | little |
Token ID | 1310 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
én | +3.658 |
everal | +3.575 |
hate | +3.205 |
fw | +3.113 |
friend | +3.106 |
Neg logit contributions | |
ocrine | -4.455 |
ary | -4.087 |
atory | -4.050 |
idia | -3.801 |
gery | -3.795 |
Token | less |
Token ID | 1342 |
Feature activation | -9.54e+00 |
Pos logit contributions | |
én | +1.600 |
everal | +1.480 |
hate | +1.355 |
DEM | +1.307 |
fw | +1.288 |
Neg logit contributions | |
ocrine | -2.342 |
ary | -2.163 |
atory | -2.123 |
gery | -2.016 |
idia | -2.014 |
Token | than |
Token ID | 621 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
én | +5.599 |
everal | +5.028 |
hate | +4.706 |
friend | +4.609 |
DEM | +4.525 |
Neg logit contributions | |
ocrine | -8.196 |
ary | -7.202 |
atory | -7.128 |
idia | -6.917 |
gery | -6.882 |
Token | a |
Token ID | 257 |
Feature activation | -8.46e+00 |
Pos logit contributions | |
én | +7.103 |
Thieves | +6.244 |
everal | +6.219 |
warmed | +6.028 |
hate | +6.004 |
Neg logit contributions | |
ocrine | -13.150 |
ary | -11.429 |
idia | -11.428 |
ドラ | -11.237 |
atory | -11.231 |
Token | minute |
Token ID | 5664 |
Feature activation | -8.61e+00 |
Pos logit contributions | |
én | +4.773 |
everal | +4.515 |
hate | +4.200 |
friend | +4.140 |
DEM | +4.089 |
Neg logit contributions | |
ocrine | -7.357 |
ary | -6.726 |
atory | -6.689 |
idia | -6.482 |
gery | -6.227 |
Token | in |
Token ID | 287 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
én | +4.832 |
everal | +4.080 |
hate | +3.937 |
fw | +3.888 |
vP | +3.704 |
Neg logit contributions | |
ocrine | -7.719 |
atory | -6.843 |
ary | -6.755 |
gery | -6.701 |
ulatory | -6.671 |
Token | , |
Token ID | 11 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
én | +3.831 |
everal | +3.580 |
hate | +3.343 |
DEM | +3.265 |
friend | +3.223 |
Neg logit contributions | |
ocrine | -4.897 |
ary | -4.469 |
atory | -4.334 |
gery | -4.184 |
idia | -4.164 |
Token | when |
Token ID | 618 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
én | +0.734 |
everal | +0.687 |
hate | +0.643 |
DEM | +0.633 |
friend | +0.623 |
Neg logit contributions | |
ocrine | -0.814 |
ary | -0.752 |
atory | -0.726 |
idia | -0.697 |
gery | -0.690 |
Token | her |
Token ID | 607 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
ocrine | +1.428 |
ary | +1.342 |
atory | +1.272 |
gery | +1.206 |
idia | +1.206 |
Neg logit contributions | |
én | -1.436 |
everal | -1.385 |
hate | -1.275 |
DEM | -1.261 |
friend | -1.232 |
Token | . |
Token ID | 13 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ocrine | +0.552 |
ary | +0.515 |
atory | +0.495 |
gery | +0.468 |
idia | +0.467 |
Neg logit contributions | |
én | -0.490 |
everal | -0.467 |
hate | -0.431 |
DEM | -0.427 |
friend | -0.420 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
én | +0.196 |
everal | +0.179 |
DEM | +0.172 |
hate | +0.171 |
friend | +0.168 |
Neg logit contributions | |
ocrine | -0.226 |
ary | -0.210 |
atory | -0.202 |
idia | -0.194 |
gery | -0.194 |
Token |
|
Token ID | 198 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
ocrine | +0.121 |
ary | +0.112 |
atory | +0.108 |
idia | +0.103 |
gery | +0.103 |
Neg logit contributions | |
én | -0.109 |
everal | -0.098 |
hate | -0.097 |
DEM | -0.096 |
friend | -0.094 |
Token | More |
Token ID | 5167 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
én | +0.310 |
everal | +0.280 |
DEM | +0.274 |
hate | +0.269 |
friend | +0.263 |
Neg logit contributions | |
ocrine | -0.454 |
ary | -0.424 |
atory | -0.409 |
gery | -0.396 |
idia | -0.395 |
Token | than |
Token ID | 621 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
én | +0.935 |
everal | +0.880 |
hate | +0.797 |
DEM | +0.791 |
friend | +0.779 |
Neg logit contributions | |
ocrine | -1.388 |
ary | -1.304 |
atory | -1.257 |
gery | -1.215 |
idia | -1.196 |
Token | 12 |
Token ID | 1105 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
én | +7.779 |
friend | +6.717 |
Thieves | +6.647 |
everal | +6.586 |
hate | +6.479 |
Neg logit contributions | |
ocrine | -12.265 |
ドラ | -10.953 |
ary | -10.791 |
idia | -10.587 |
aptic | -10.567 |
Token | , |
Token ID | 11 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
én | +2.439 |
everal | +2.256 |
DEM | +2.076 |
hate | +2.061 |
friend | +2.042 |
Neg logit contributions | |
ocrine | -2.910 |
ary | -2.727 |
atory | -2.618 |
gery | -2.536 |
idia | -2.484 |
Token | 000 |
Token ID | 830 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
ocrine | +2.706 |
ary | +2.523 |
atory | +2.353 |
gery | +2.183 |
idia | +2.179 |
Neg logit contributions | |
én | -4.214 |
everal | -4.125 |
hate | -3.835 |
DEM | -3.795 |
friend | -3.721 |
Token | years |
Token ID | 812 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
ocrine | +3.253 |
ary | +3.079 |
atory | +2.922 |
gery | +2.769 |
idia | +2.767 |
Neg logit contributions | |
én | -3.113 |
everal | -3.029 |
hate | -2.762 |
DEM | -2.727 |
friend | -2.666 |
Token | later |
Token ID | 1568 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
én | +2.239 |
everal | +2.072 |
hate | +1.862 |
friend | +1.780 |
DEM | +1.746 |
Neg logit contributions | |
ocrine | -3.490 |
ary | -3.196 |
atory | -3.133 |
gery | -3.039 |
idia | -2.979 |
Token | � |
Token ID | 251 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
ocrine | +0.366 |
ary | +0.347 |
atory | +0.331 |
idia | +0.317 |
gery | +0.316 |
Neg logit contributions | |
én | -0.292 |
everal | -0.283 |
hate | -0.255 |
DEM | -0.251 |
friend | -0.244 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ocrine | +2.724 |
ary | +2.569 |
atory | +2.451 |
gery | +2.339 |
idia | +2.328 |
Neg logit contributions | |
én | -2.434 |
everal | -2.341 |
hate | -2.142 |
DEM | -2.122 |
friend | -2.066 |
Token |
|
Token ID | 198 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ocrine | +1.310 |
ary | +1.231 |
atory | +1.172 |
gery | +1.116 |
idia | +1.115 |
Neg logit contributions | |
én | -1.279 |
everal | -1.206 |
hate | -1.135 |
DEM | -1.124 |
friend | -1.100 |
Token | Fe |
Token ID | 14304 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
ocrine | +2.296 |
ary | +2.178 |
atory | +2.088 |
gery | +2.008 |
idia | +2.001 |
Neg logit contributions | |
én | -1.581 |
everal | -1.501 |
hate | -1.368 |
DEM | -1.365 |
friend | -1.315 |
Token | eling |
Token ID | 10809 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ocrine | +2.922 |
ary | +2.768 |
atory | +2.632 |
gery | +2.500 |
idia | +2.492 |
Neg logit contributions | |
én | -2.680 |
everal | -2.597 |
hate | -2.367 |
DEM | -2.336 |
friend | -2.281 |
Token | Hel |
Token ID | 5053 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
ocrine | +1.549 |
ary | +1.465 |
atory | +1.393 |
gery | +1.338 |
idia | +1.338 |
Neg logit contributions | |
én | -1.311 |
everal | -1.256 |
hate | -1.149 |
DEM | -1.134 |
friend | -1.105 |
Token | pless |
Token ID | 14570 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
ocrine | +4.630 |
ary | +4.239 |
atory | +3.937 |
ph | +3.732 |
gery | +3.296 |
Neg logit contributions | |
everal | -12.284 |
én | -11.945 |
DEM | -11.428 |
hate | -11.404 |
� | -10.952 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ocrine | +2.818 |
ary | +2.647 |
atory | +2.518 |
idia | +2.387 |
gery | +2.384 |
Neg logit contributions | |
én | -2.909 |
everal | -2.806 |
hate | -2.580 |
DEM | -2.549 |
friend | -2.504 |
Token |
|
Token ID | 198 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
én | +1.178 |
hate | +1.038 |
friend | +1.025 |
DEM | +1.018 |
fw | +0.976 |
Neg logit contributions | |
ocrine | -1.476 |
ary | -1.354 |
atory | -1.308 |
idia | -1.282 |
gery | -1.264 |
Token | But |
Token ID | 1537 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
ocrine | +0.364 |
ary | +0.342 |
atory | +0.329 |
gery | +0.318 |
idia | +0.318 |
Neg logit contributions | |
én | -0.241 |
everal | -0.224 |
DEM | -0.212 |
hate | -0.210 |
friend | -0.204 |
Token | are |
Token ID | 389 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
én | +2.599 |
everal | +2.489 |
hate | +2.269 |
DEM | +2.251 |
friend | +2.209 |
Neg logit contributions | |
ocrine | -2.909 |
ary | -2.650 |
atory | -2.516 |
gery | -2.460 |
idia | -2.444 |
Token | in |
Token ID | 287 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
én | +1.594 |
everal | +1.471 |
hate | +1.357 |
friend | +1.356 |
DEM | +1.338 |
Neg logit contributions | |
ocrine | -2.167 |
ary | -2.049 |
atory | -1.964 |
idia | -1.915 |
gery | -1.910 |
Token | the |
Token ID | 262 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
én | +0.178 |
everal | +0.170 |
hate | +0.157 |
DEM | +0.155 |
friend | +0.151 |
Neg logit contributions | |
ocrine | -0.191 |
ary | -0.178 |
atory | -0.171 |
idia | -0.163 |
gery | -0.162 |
Token | Mongol |
Token ID | 42188 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
én | +0.069 |
everal | +0.066 |
hate | +0.061 |
DEM | +0.060 |
friend | +0.059 |
Neg logit contributions | |
ocrine | -0.073 |
ary | -0.068 |
atory | -0.065 |
idia | -0.062 |
gery | -0.062 |
Token | ian |
Token ID | 666 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
én | +2.344 |
everal | +2.148 |
hate | +1.997 |
DEM | +1.939 |
friend | +1.906 |
Neg logit contributions | |
ocrine | -3.074 |
ary | -2.808 |
atory | -2.739 |
idia | -2.661 |
gery | -2.636 |
Token | language |
Token ID | 3303 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
én | +0.348 |
everal | +0.330 |
hate | +0.307 |
DEM | +0.300 |
friend | +0.295 |
Neg logit contributions | |
ocrine | -0.350 |
ary | -0.325 |
atory | -0.311 |
idia | -0.297 |
gery | -0.293 |
Token | ).[ |
Token ID | 42669 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
én | +1.445 |
everal | +1.312 |
hate | +1.192 |
DEM | +1.165 |
friend | +1.132 |
Neg logit contributions | |
ocrine | -2.962 |
ary | -2.787 |
atory | -2.718 |
gery | -2.626 |
idia | -2.618 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ocrine | +7.505 |
ary | +7.256 |
atory | +6.693 |
ph | +6.507 |
idia | +6.210 |
Neg logit contributions | |
everal | -9.996 |
én | -9.712 |
hate | -8.847 |
DEM | -8.618 |
orno | -8.618 |
Token | ] |
Token ID | 60 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
én | +1.226 |
everal | +1.172 |
hate | +1.055 |
DEM | +1.036 |
friend | +1.018 |
Neg logit contributions | |
ocrine | -1.688 |
ary | -1.596 |
atory | -1.535 |
gery | -1.479 |
idia | -1.469 |
Token |
|
Token ID | 198 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
ocrine | +0.996 |
ary | +0.935 |
atory | +0.897 |
idia | +0.863 |
gery | +0.858 |
Neg logit contributions | |
én | -0.851 |
everal | -0.790 |
DEM | -0.743 |
hate | -0.739 |
friend | -0.728 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ocrine | +0.069 |
ary | +0.064 |
atory | +0.061 |
idia | +0.060 |
gery | +0.059 |
Neg logit contributions | |
én | -0.060 |
DEM | -0.053 |
hate | -0.053 |
everal | -0.052 |
friend | -0.052 |
Token | Now |
Token ID | 3844 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ocrine | +0.959 |
ary | +0.907 |
atory | +0.874 |
idia | +0.842 |
gery | +0.842 |
Neg logit contributions | |
én | -0.632 |
everal | -0.589 |
DEM | -0.547 |
hate | -0.544 |
friend | -0.527 |
Token | them |
Token ID | 606 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
én | +1.182 |
everal | +1.120 |
hate | +1.054 |
DEM | +1.040 |
friend | +1.010 |
Neg logit contributions | |
ocrine | -1.251 |
ary | -1.156 |
atory | -1.104 |
idia | -1.068 |
gery | -1.051 |
Token | ", |
Token ID | 1600 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
ocrine | +1.241 |
ary | +1.160 |
atory | +1.107 |
idia | +1.055 |
gery | +1.054 |
Neg logit contributions | |
én | -1.196 |
everal | -1.143 |
hate | -1.060 |
DEM | -1.039 |
friend | -1.025 |
Token | rather |
Token ID | 2138 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
ocrine | +2.931 |
ary | +2.772 |
atory | +2.635 |
gery | +2.501 |
idia | +2.495 |
Neg logit contributions | |
én | -2.746 |
everal | -2.660 |
hate | -2.430 |
DEM | -2.397 |
friend | -2.344 |
Token | than |
Token ID | 621 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
ocrine | +3.583 |
ary | +3.434 |
atory | +3.265 |
gery | +3.125 |
ph | +3.107 |
Neg logit contributions | |
én | -2.768 |
everal | -2.673 |
hate | -2.393 |
DEM | -2.379 |
friend | -2.310 |
Token | lets |
Token ID | 8781 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
ocrine | +1.548 |
ary | +1.446 |
atory | +1.378 |
idia | +1.309 |
gery | +1.299 |
Neg logit contributions | |
én | -1.562 |
everal | -1.511 |
hate | -1.394 |
DEM | -1.365 |
friend | -1.344 |
Token | try |
Token ID | 1949 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
ocrine | +4.710 |
ary | +4.497 |
atory | +4.245 |
gery | +4.037 |
ph | +4.012 |
Neg logit contributions | |
én | -4.634 |
everal | -4.509 |
hate | -4.087 |
DEM | -4.075 |
friend | -3.955 |
Token | them |
Token ID | 606 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
ocrine | +7.571 |
ary | +7.545 |
atory | +6.895 |
gery | +6.567 |
ph | +6.547 |
Neg logit contributions | |
én | -9.018 |
everal | -8.953 |
DEM | -8.205 |
hate | -8.189 |
orno | -7.944 |
Token | on |
Token ID | 319 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
ocrine | +3.642 |
ary | +3.456 |
atory | +3.254 |
gery | +3.081 |
ph | +3.054 |
Neg logit contributions | |
én | -3.948 |
everal | -3.855 |
hate | -3.522 |
DEM | -3.496 |
friend | -3.406 |
Token | another |
Token ID | 1194 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
én | +0.157 |
everal | +0.150 |
hate | +0.137 |
DEM | +0.137 |
friend | +0.134 |
Neg logit contributions | |
ocrine | -0.177 |
ary | -0.164 |
atory | -0.159 |
idia | -0.152 |
gery | -0.151 |
Token | role |
Token ID | 2597 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
ocrine | +1.410 |
ary | +1.325 |
atory | +1.271 |
gery | +1.214 |
idia | +1.210 |
Neg logit contributions | |
én | -1.120 |
everal | -1.082 |
hate | -0.983 |
DEM | -0.970 |
friend | -0.949 |
Token | . |
Token ID | 13 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
ocrine | +0.640 |
ary | +0.592 |
atory | +0.573 |
gery | +0.544 |
idia | +0.542 |
Neg logit contributions | |
én | -0.561 |
everal | -0.535 |
hate | -0.495 |
DEM | -0.487 |
friend | -0.481 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ocrine | +4.534 |
ary | +4.328 |
atory | +4.101 |
gery | +3.881 |
idia | +3.835 |
Neg logit contributions | |
én | -4.533 |
everal | -4.419 |
hate | -4.015 |
DEM | -3.966 |
friend | -3.885 |
Token |
|
Token ID | 198 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
én | +0.159 |
everal | +0.151 |
DEM | +0.142 |
hate | +0.141 |
friend | +0.138 |
Neg logit contributions | |
ocrine | -0.177 |
ary | -0.164 |
atory | -0.158 |
idia | -0.152 |
gery | -0.151 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
én | +0.310 |
hate | +0.274 |
DEM | +0.270 |
friend | +0.269 |
everal | +0.269 |
Neg logit contributions | |
ocrine | -0.359 |
ary | -0.332 |
atory | -0.320 |
idia | -0.310 |
gery | -0.307 |
Token | About |
Token ID | 8585 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
ocrine | +0.908 |
ary | +0.849 |
atory | +0.820 |
idia | +0.793 |
gery | +0.790 |
Neg logit contributions | |
én | -0.629 |
everal | -0.594 |
DEM | -0.561 |
hate | -0.553 |
friend | -0.535 |
Token | 30 |
Token ID | 1542 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
én | +2.555 |
everal | +2.412 |
hate | +2.236 |
friend | +2.217 |
DEM | +2.203 |
Neg logit contributions | |
ocrine | -3.138 |
ary | -2.863 |
atory | -2.727 |
idia | -2.698 |
gery | -2.583 |
Token | or |
Token ID | 393 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
én | +2.566 |
everal | +2.518 |
hate | +2.342 |
DEM | +2.295 |
friend | +2.241 |
Neg logit contributions | |
ocrine | -2.858 |
ary | -2.632 |
atory | -2.554 |
idia | -2.431 |
gery | -2.416 |
Token | 40 |
Token ID | 2319 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
ocrine | +7.523 |
ary | +7.220 |
atory | +7.132 |
ph | +6.927 |
gery | +6.437 |
Neg logit contributions | |
everal | -9.928 |
én | -9.842 |
DEM | -8.877 |
hate | -8.844 |
orno | -8.649 |
Token | policemen |
Token ID | 33777 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
én | +0.584 |
everal | +0.573 |
hate | +0.530 |
DEM | +0.524 |
friend | +0.510 |
Neg logit contributions | |
ocrine | -0.578 |
ary | -0.537 |
atory | -0.514 |
idia | -0.489 |
gery | -0.485 |
Token | took |
Token ID | 1718 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
én | +0.168 |
everal | +0.161 |
hate | +0.149 |
DEM | +0.144 |
friend | +0.143 |
Neg logit contributions | |
ocrine | -0.183 |
ary | -0.169 |
atory | -0.163 |
idia | -0.158 |
ph | -0.155 |
Token | Mr |
Token ID | 1770 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
ocrine | +2.305 |
ary | +2.153 |
atory | +2.040 |
idia | +1.959 |
gery | +1.937 |
Neg logit contributions | |
én | -2.334 |
everal | -2.280 |
hate | -2.085 |
DEM | -2.057 |
friend | -2.002 |
Token | Tom |
Token ID | 4186 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
én | +0.267 |
everal | +0.261 |
hate | +0.242 |
DEM | +0.239 |
friend | +0.234 |
Neg logit contributions | |
ocrine | -0.206 |
ary | -0.192 |
atory | -0.181 |
gery | -0.170 |
idia | -0.170 |
Token | see |
Token ID | 766 |
Feature activation | +7.88e+00 |
Pos logit contributions | |
ocrine | +2.288 |
ary | +2.145 |
atory | +2.042 |
gery | +1.941 |
idia | +1.933 |
Neg logit contributions | |
én | -2.343 |
everal | -2.256 |
hate | -2.080 |
DEM | -2.048 |
friend | -2.008 |
Token | Hat |
Token ID | 10983 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
ocrine | +5.855 |
ary | +5.682 |
atory | +5.361 |
gery | +5.041 |
idia | +5.021 |
Neg logit contributions | |
én | -5.924 |
everal | -5.804 |
DEM | -5.215 |
hate | -5.181 |
friend | -5.023 |
Token | ay |
Token ID | 323 |
Feature activation | +7.32e+00 |
Pos logit contributions | |
ocrine | +3.953 |
ary | +3.826 |
atory | +3.592 |
ph | +3.369 |
gery | +3.363 |
Neg logit contributions | |
everal | -4.248 |
én | -4.160 |
hate | -3.741 |
DEM | -3.739 |
friend | -3.612 |
Token | as |
Token ID | 355 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
ocrine | +5.248 |
ary | +5.060 |
atory | +4.750 |
gery | +4.477 |
ph | +4.432 |
Neg logit contributions | |
én | -5.706 |
everal | -5.655 |
hate | -5.065 |
DEM | -5.058 |
friend | -4.908 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +8.87e+00 |
Pos logit contributions | |
ocrine | +4.199 |
ary | +4.004 |
atory | +3.801 |
gery | +3.598 |
idia | +3.584 |
Neg logit contributions | |
én | -3.931 |
everal | -3.827 |
hate | -3.458 |
DEM | -3.429 |
friend | -3.334 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
ocrine | +6.515 |
ary | +6.330 |
atory | +5.957 |
gery | +5.636 |
ph | +5.633 |
Neg logit contributions | |
én | -6.628 |
everal | -6.621 |
hate | -5.822 |
DEM | -5.697 |
fw | -5.567 |
Token | 46 |
Token ID | 3510 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
ary | +6.570 |
ocrine | +6.534 |
atory | +5.979 |
ph | +5.848 |
gery | +5.088 |
Neg logit contributions | |
everal | -14.109 |
én | -12.749 |
gobl | -12.487 |
proport | -12.151 |
resil | -11.858 |
Token | ] |
Token ID | 60 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
én | +2.299 |
hate | +1.950 |
friend | +1.898 |
fw | +1.866 |
DEM | +1.850 |
Neg logit contributions | |
ocrine | -3.946 |
ary | -3.677 |
atory | -3.579 |
gery | -3.512 |
idia | -3.508 |
Token |
|
Token ID | 198 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
ocrine | +2.695 |
ary | +2.535 |
atory | +2.419 |
idia | +2.308 |
gery | +2.307 |
Neg logit contributions | |
én | -2.492 |
everal | -2.377 |
hate | -2.208 |
DEM | -2.180 |
friend | -2.141 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ocrine | +0.591 |
ary | +0.551 |
atory | +0.528 |
idia | +0.507 |
gery | +0.504 |
Neg logit contributions | |
én | -0.538 |
everal | -0.485 |
hate | -0.476 |
DEM | -0.470 |
friend | -0.464 |
Token | Late |
Token ID | 26302 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ocrine | +2.167 |
ary | +2.047 |
atory | +1.971 |
gery | +1.896 |
idia | +1.893 |
Neg logit contributions | |
én | -1.467 |
everal | -1.382 |
hate | -1.278 |
DEM | -1.275 |
friend | -1.232 |
Token | would |
Token ID | 561 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
én | +3.633 |
everal | +3.303 |
hate | +3.115 |
DEM | +3.010 |
friend | +2.987 |
Neg logit contributions | |
ocrine | -4.215 |
ary | -3.797 |
atory | -3.702 |
gery | -3.597 |
idia | -3.574 |
Token | be |
Token ID | 307 |
Feature activation | -8.33e+00 |
Pos logit contributions | |
én | +4.268 |
everal | +3.863 |
hate | +3.701 |
DEM | +3.474 |
haps | +3.448 |
Neg logit contributions | |
ocrine | -5.895 |
ary | -5.229 |
atory | -5.198 |
gery | -5.032 |
ph | -4.979 |
Token | easy |
Token ID | 2562 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
én | +5.632 |
everal | +5.332 |
hate | +4.879 |
friend | +4.790 |
orno | +4.631 |
Neg logit contributions | |
ocrine | -6.432 |
ary | -5.810 |
atory | -5.619 |
idia | -5.403 |
gery | -5.318 |
Token | at |
Token ID | 379 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
ocrine | +0.348 |
ary | +0.329 |
atory | +0.312 |
gery | +0.296 |
idia | +0.295 |
Neg logit contributions | |
én | -0.342 |
everal | -0.332 |
hate | -0.303 |
DEM | -0.299 |
friend | -0.293 |
Token | a |
Token ID | 257 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
ocrine | +1.670 |
ary | +1.575 |
atory | +1.495 |
idia | +1.422 |
gery | +1.420 |
Neg logit contributions | |
én | -1.643 |
everal | -1.588 |
hate | -1.456 |
DEM | -1.440 |
friend | -1.407 |
Token | moment |
Token ID | 2589 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
én | +2.204 |
everal | +2.173 |
hate | +2.040 |
DEM | +1.983 |
friend | +1.971 |
Neg logit contributions | |
ocrine | -2.632 |
ary | -2.447 |
atory | -2.385 |
idia | -2.334 |
gery | -2.258 |
Token | like |
Token ID | 588 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ocrine | +3.005 |
ary | +2.844 |
atory | +2.666 |
gery | +2.503 |
idia | +2.499 |
Neg logit contributions | |
én | -3.527 |
everal | -3.451 |
hate | -3.161 |
DEM | -3.135 |
friend | -3.063 |
Token | this |
Token ID | 428 |
Feature activation | +6.25e+00 |
Pos logit contributions | |
ocrine | +0.120 |
ary | +0.113 |
atory | +0.108 |
idia | +0.103 |
gery | +0.102 |
Neg logit contributions | |
én | -0.112 |
everal | -0.108 |
hate | -0.100 |
DEM | -0.098 |
friend | -0.096 |
Token | to |
Token ID | 284 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ocrine | +4.662 |
ary | +4.452 |
atory | +4.204 |
gery | +3.969 |
ph | +3.947 |
Neg logit contributions | |
én | -4.754 |
everal | -4.674 |
DEM | -4.221 |
hate | -4.201 |
friend | -4.090 |
Token | focus |
Token ID | 2962 |
Feature activation | -9.43e+00 |
Pos logit contributions | |
ocrine | +1.056 |
ary | +0.986 |
atory | +0.944 |
idia | +0.898 |
gery | +0.898 |
Neg logit contributions | |
én | -0.928 |
everal | -0.877 |
hate | -0.821 |
DEM | -0.796 |
friend | -0.784 |
Token | on |
Token ID | 319 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
én | +5.546 |
everal | +5.339 |
hate | +5.218 |
orno | +5.006 |
friend | +4.887 |
Neg logit contributions | |
ocrine | -7.686 |
ary | -7.072 |
atory | -6.821 |
gery | -6.776 |
idia | -6.711 |
Token | – |
Token ID | 784 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
én | +2.269 |
everal | +2.082 |
hate | +1.967 |
DEM | +1.917 |
friend | +1.894 |
Neg logit contributions | |
ocrine | -2.771 |
ary | -2.542 |
atory | -2.419 |
idia | -2.406 |
gery | -2.374 |
Token | what |
Token ID | 644 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
én | +0.249 |
everal | +0.236 |
hate | +0.220 |
DEM | +0.215 |
friend | +0.212 |
Neg logit contributions | |
ocrine | -0.285 |
ary | -0.266 |
atory | -0.253 |
idia | -0.246 |
gery | -0.244 |
Token | 're |
Token ID | 821 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
ocrine | +0.951 |
ary | +0.885 |
atory | +0.848 |
idia | +0.806 |
gery | +0.803 |
Neg logit contributions | |
én | -0.933 |
everal | -0.892 |
hate | -0.829 |
DEM | -0.819 |
friend | -0.801 |
Token | your |
Token ID | 534 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
ocrine | +3.827 |
ary | +3.641 |
atory | +3.453 |
ph | +3.248 |
gery | +3.240 |
Neg logit contributions | |
én | -3.715 |
everal | -3.621 |
hate | -3.292 |
DEM | -3.256 |
friend | -3.180 |
Token | chances |
Token ID | 8395 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ocrine | +3.111 |
ary | +2.948 |
atory | +2.802 |
gery | +2.660 |
idia | +2.651 |
Neg logit contributions | |
én | -2.856 |
everal | -2.770 |
hate | -2.523 |
DEM | -2.490 |
friend | -2.431 |
Token | of |
Token ID | 286 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
ocrine | +2.483 |
ary | +2.329 |
atory | +2.201 |
gery | +2.086 |
idia | +2.076 |
Neg logit contributions | |
én | -2.802 |
everal | -2.711 |
hate | -2.502 |
DEM | -2.473 |
friend | -2.423 |
Token | making |
Token ID | 1642 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
ocrine | +4.136 |
ary | +3.922 |
atory | +3.714 |
gery | +3.519 |
idia | +3.483 |
Neg logit contributions | |
én | -4.445 |
everal | -4.340 |
hate | -3.964 |
DEM | -3.918 |
friend | -3.828 |
Token | the |
Token ID | 262 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
ocrine | +3.270 |
ary | +3.098 |
atory | +2.946 |
gery | +2.793 |
idia | +2.779 |
Neg logit contributions | |
én | -3.062 |
everal | -2.974 |
hate | -2.714 |
DEM | -2.678 |
friend | -2.613 |
Token | next |
Token ID | 1306 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
ocrine | +3.198 |
ary | +3.023 |
atory | +2.868 |
gery | +2.718 |
idia | +2.706 |
Neg logit contributions | |
én | -3.167 |
everal | -3.078 |
hate | -2.814 |
DEM | -2.778 |
friend | -2.716 |
Token | put |
Token ID | 1234 |
Feature activation | +7.50e+00 |
Pos logit contributions | |
ocrine | +4.464 |
ary | +4.232 |
atory | +4.015 |
gery | +3.794 |
ph | +3.781 |
Neg logit contributions | |
én | -4.313 |
everal | -4.222 |
hate | -3.867 |
DEM | -3.816 |
friend | -3.703 |
Token | t |
Token ID | 83 |
Feature activation | +8.23e+00 |
Pos logit contributions | |
ocrine | +6.362 |
ary | +6.115 |
atory | +5.861 |
gery | +5.572 |
ph | +5.529 |
Neg logit contributions | |
én | -4.879 |
everal | -4.786 |
hate | -4.276 |
DEM | -4.254 |
friend | -4.076 |
Token | 's |
Token ID | 338 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
én | +0.080 |
everal | +0.076 |
hate | +0.071 |
DEM | +0.069 |
friend | +0.068 |
Neg logit contributions | |
ocrine | -0.085 |
ary | -0.079 |
atory | -0.076 |
idia | -0.073 |
gery | -0.072 |
Token | Inn |
Token ID | 10849 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
én | +1.250 |
everal | +1.199 |
hate | +1.121 |
DEM | +1.091 |
friend | +1.067 |
Neg logit contributions | |
ocrine | -1.354 |
ary | -1.261 |
atory | -1.205 |
idia | -1.170 |
gery | -1.149 |
Token | oc |
Token ID | 420 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
ocrine | +2.482 |
ary | +2.328 |
atory | +2.197 |
idia | +2.064 |
gery | +2.056 |
Neg logit contributions | |
én | -2.991 |
everal | -2.932 |
hate | -2.697 |
DEM | -2.667 |
friend | -2.614 |
Token | ence |
Token ID | 594 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ocrine | +3.397 |
ary | +3.233 |
atory | +3.088 |
idia | +2.928 |
gery | +2.909 |
Neg logit contributions | |
én | -3.076 |
everal | -2.998 |
hate | -2.720 |
DEM | -2.696 |
friend | -2.619 |
Token | of |
Token ID | 286 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
ocrine | +0.079 |
ary | +0.072 |
atory | +0.070 |
gery | +0.068 |
idia | +0.066 |
Neg logit contributions | |
én | -0.075 |
everal | -0.072 |
hate | -0.066 |
DEM | -0.066 |
friend | -0.064 |
Token | Muslims |
Token ID | 7045 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
én | +2.338 |
everal | +2.120 |
hate | +2.061 |
Thieves | +2.046 |
DEM | +2.006 |
Neg logit contributions | |
ocrine | -3.070 |
ary | -2.836 |
atory | -2.756 |
idia | -2.664 |
gery | -2.637 |
Token | are |
Token ID | 389 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ocrine | +2.773 |
ary | +2.626 |
atory | +2.491 |
gery | +2.362 |
idia | +2.350 |
Neg logit contributions | |
én | -2.694 |
everal | -2.617 |
hate | -2.387 |
DEM | -2.359 |
friend | -2.306 |
Token | taken |
Token ID | 2077 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
én | +0.884 |
everal | +0.835 |
hate | +0.783 |
DEM | +0.761 |
friend | +0.743 |
Neg logit contributions | |
ocrine | -1.083 |
ary | -1.006 |
atory | -0.964 |
idia | -0.948 |
gery | -0.920 |
Token | as |
Token ID | 355 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
én | +2.490 |
everal | +2.258 |
hate | +2.248 |
friend | +2.104 |
DEM | +2.103 |
Neg logit contributions | |
ocrine | -3.074 |
ary | -2.756 |
atory | -2.701 |
idia | -2.665 |
gery | -2.575 |
Token | both |
Token ID | 1111 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
ocrine | +1.367 |
ary | +1.289 |
atory | +1.232 |
idia | +1.177 |
gery | +1.172 |
Neg logit contributions | |
én | -1.089 |
everal | -1.040 |
hate | -0.966 |
DEM | -0.937 |
friend | -0.916 |
Token | truth |
Token ID | 3872 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
én | +2.777 |
everal | +2.572 |
hate | +2.512 |
DEM | +2.367 |
friend | +2.348 |
Neg logit contributions | |
ocrine | -3.578 |
ary | -3.314 |
atory | -3.182 |
idia | -3.113 |
gery | -3.033 |
Token | of |
Token ID | 286 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
ocrine | +4.496 |
ary | +4.281 |
atory | +4.018 |
gery | +3.753 |
ph | +3.751 |
Neg logit contributions | |
én | -5.224 |
everal | -5.096 |
hate | -4.657 |
DEM | -4.641 |
friend | -4.510 |
Token | entities |
Token ID | 12066 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ocrine | +2.763 |
ary | +2.617 |
atory | +2.502 |
gery | +2.378 |
idia | +2.377 |
Neg logit contributions | |
én | -2.282 |
everal | -2.202 |
hate | -2.008 |
DEM | -1.972 |
friend | -1.927 |
Token | including |
Token ID | 1390 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
ocrine | +1.090 |
ary | +1.015 |
atory | +0.976 |
idia | +0.927 |
gery | +0.920 |
Neg logit contributions | |
én | -1.035 |
everal | -0.987 |
hate | -0.918 |
DEM | -0.898 |
friend | -0.881 |
Token | an |
Token ID | 281 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
ocrine | +2.327 |
ary | +2.194 |
atory | +2.094 |
idia | +1.990 |
gery | +1.990 |
Neg logit contributions | |
én | -2.070 |
everal | -1.995 |
hate | -1.826 |
DEM | -1.795 |
friend | -1.757 |
Token | animal |
Token ID | 5044 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ocrine | +2.910 |
ary | +2.744 |
atory | +2.595 |
gery | +2.450 |
idia | +2.441 |
Neg logit contributions | |
én | -3.210 |
everal | -3.129 |
hate | -2.871 |
DEM | -2.838 |
friend | -2.779 |
Token | in |
Token ID | 287 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
ocrine | +0.999 |
ary | +0.936 |
atory | +0.897 |
idia | +0.854 |
gery | +0.849 |
Neg logit contributions | |
én | -0.924 |
everal | -0.883 |
hate | -0.822 |
DEM | -0.808 |
friend | -0.795 |
Token | the |
Token ID | 262 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
ocrine | +2.218 |
ary | +2.092 |
atory | +1.988 |
gery | +1.884 |
idia | +1.881 |
Neg logit contributions | |
én | -2.165 |
everal | -2.098 |
hate | -1.924 |
DEM | -1.894 |
friend | -1.852 |
Token | house |
Token ID | 2156 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
ocrine | +3.334 |
ary | +3.150 |
atory | +2.991 |
gery | +2.836 |
idia | +2.831 |
Neg logit contributions | |
én | -3.222 |
everal | -3.121 |
hate | -2.857 |
DEM | -2.817 |
friend | -2.756 |
Token | I |
Token ID | 314 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
ocrine | +2.838 |
ary | +2.673 |
atory | +2.542 |
gery | +2.411 |
idia | +2.410 |
Neg logit contributions | |
én | -2.736 |
everal | -2.641 |
hate | -2.427 |
DEM | -2.386 |
friend | -2.340 |
Token | listened |
Token ID | 16399 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
ocrine | +0.605 |
ary | +0.560 |
atory | +0.543 |
gery | +0.514 |
idia | +0.506 |
Neg logit contributions | |
én | -0.618 |
everal | -0.584 |
hate | -0.555 |
friend | -0.534 |
DEM | -0.529 |
Token | to |
Token ID | 284 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
én | +0.113 |
everal | +0.108 |
hate | +0.099 |
DEM | +0.098 |
friend | +0.096 |
Neg logit contributions | |
ocrine | -0.119 |
ary | -0.112 |
atory | -0.107 |
gery | -0.102 |
idia | -0.101 |
Token | who |
Token ID | 508 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
én | +0.609 |
everal | +0.575 |
hate | +0.531 |
DEM | +0.515 |
friend | +0.514 |
Neg logit contributions | |
ocrine | -0.887 |
ary | -0.827 |
atory | -0.803 |
idia | -0.771 |
gery | -0.760 |
Token | wishes |
Token ID | 12802 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
én | +0.197 |
everal | +0.186 |
hate | +0.175 |
DEM | +0.169 |
friend | +0.168 |
Neg logit contributions | |
ocrine | -0.208 |
ary | -0.193 |
atory | -0.186 |
idia | -0.177 |
gery | -0.175 |
Token | to |
Token ID | 284 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
ocrine | +0.142 |
ary | +0.132 |
atory | +0.127 |
idia | +0.122 |
gery | +0.120 |
Neg logit contributions | |
én | -0.129 |
everal | -0.123 |
hate | -0.115 |
DEM | -0.112 |
friend | -0.110 |
Token | transition |
Token ID | 6801 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
én | +0.489 |
everal | +0.453 |
hate | +0.431 |
DEM | +0.411 |
friend | +0.410 |
Neg logit contributions | |
ocrine | -0.570 |
ary | -0.525 |
atory | -0.509 |
idia | -0.483 |
gery | -0.476 |
Token | their |
Token ID | 511 |
Feature activation | -2.92e-04 |
Pos logit contributions | |
ocrine | +1.393 |
ary | +1.307 |
atory | +1.254 |
idia | +1.191 |
gery | +1.187 |
Neg logit contributions | |
én | -1.267 |
everal | -1.209 |
hate | -1.114 |
DEM | -1.095 |
friend | -1.072 |
Token | gender |
Token ID | 5279 |
Feature activation | +7.47e+00 |
Pos logit contributions | |
én | +0.000 |
everal | +0.000 |
hate | +0.000 |
DEM | +0.000 |
friend | +0.000 |
Neg logit contributions | |
ocrine | -0.000 |
ary | -0.000 |
atory | -0.000 |
idia | -0.000 |
ph | -0.000 |
Token | socially |
Token ID | 18118 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
ocrine | +5.496 |
ary | +5.249 |
atory | +4.928 |
gery | +4.680 |
ph | +4.677 |
Neg logit contributions | |
én | -5.744 |
everal | -5.664 |
DEM | -5.124 |
hate | -5.118 |
friend | -4.915 |
Token | and |
Token ID | 290 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
ocrine | +2.439 |
ary | +2.299 |
atory | +2.193 |
gery | +2.089 |
idia | +2.083 |
Neg logit contributions | |
én | -2.249 |
everal | -2.157 |
hate | -1.978 |
DEM | -1.944 |
friend | -1.908 |
Token | / |
Token ID | 14 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
én | +3.812 |
everal | +3.414 |
hate | +3.269 |
DEM | +3.255 |
friend | +3.207 |
Neg logit contributions | |
ocrine | -4.080 |
ary | -3.782 |
atory | -3.629 |
idia | -3.597 |
gery | -3.485 |
Token | or |
Token ID | 273 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
én | +1.294 |
hate | +1.018 |
friend | +0.938 |
DEM | +0.854 |
fw | +0.841 |
Neg logit contributions | |
ocrine | -4.907 |
ary | -4.599 |
atory | -4.500 |
idia | -4.447 |
gery | -4.443 |
Token | physically |
Token ID | 10170 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
én | +2.435 |
everal | +2.247 |
hate | +2.130 |
DEM | +2.088 |
friend | +2.068 |
Neg logit contributions | |
ocrine | -2.466 |
ary | -2.294 |
atory | -2.179 |
idia | -2.151 |
gery | -2.086 |
Token | different |
Token ID | 1180 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
én | +2.417 |
everal | +2.394 |
hate | +2.118 |
DEM | +2.102 |
fw | +2.079 |
Neg logit contributions | |
ocrine | -3.040 |
ary | -2.806 |
atory | -2.712 |
idia | -2.639 |
gery | -2.613 |
Token | boot |
Token ID | 6297 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ocrine | +0.702 |
ary | +0.660 |
atory | +0.630 |
gery | +0.606 |
idia | +0.604 |
Neg logit contributions | |
én | -0.533 |
everal | -0.511 |
hate | -0.459 |
DEM | -0.455 |
friend | -0.446 |
Token | mode |
Token ID | 4235 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
ocrine | +2.708 |
ary | +2.547 |
atory | +2.421 |
gery | +2.313 |
idia | +2.299 |
Neg logit contributions | |
én | -2.565 |
everal | -2.471 |
hate | -2.263 |
DEM | -2.239 |
friend | -2.190 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ocrine | +2.773 |
ary | +2.607 |
atory | +2.481 |
gery | +2.357 |
idia | +2.347 |
Neg logit contributions | |
én | -2.674 |
everal | -2.584 |
hate | -2.368 |
DEM | -2.338 |
friend | -2.291 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
én | +1.021 |
everal | +0.947 |
hate | +0.900 |
DEM | +0.894 |
friend | +0.883 |
Neg logit contributions | |
ocrine | -1.278 |
ary | -1.187 |
atory | -1.147 |
idia | -1.100 |
gery | -1.093 |
Token |
|
Token ID | 198 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
én | +1.550 |
hate | +1.366 |
friend | +1.352 |
DEM | +1.346 |
fw | +1.293 |
Neg logit contributions | |
ocrine | -2.000 |
ary | -1.828 |
atory | -1.777 |
idia | -1.738 |
gery | -1.708 |
Token | * |
Token ID | 9 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
én | +1.626 |
everal | +1.548 |
DEM | +1.472 |
hate | +1.444 |
friend | +1.408 |
Neg logit contributions | |
ocrine | -2.356 |
ary | -2.204 |
atory | -2.130 |
gery | -2.039 |
idia | -2.034 |
Token | IF |
Token ID | 5064 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
én | +1.673 |
everal | +1.589 |
DEM | +1.495 |
hate | +1.472 |
friend | +1.426 |
Neg logit contributions | |
ocrine | -2.506 |
ary | -2.344 |
atory | -2.273 |
gery | -2.179 |
idia | -2.171 |
Token | , |
Token ID | 11 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
ocrine | +0.332 |
ary | +0.311 |
atory | +0.299 |
gery | +0.287 |
idia | +0.286 |
Neg logit contributions | |
én | -0.247 |
everal | -0.234 |
DEM | -0.216 |
hate | -0.210 |
friend | -0.207 |
Token | WITH |
Token ID | 13315 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
én | +1.828 |
everal | +1.660 |
DEM | +1.603 |
friend | +1.535 |
hate | +1.532 |
Neg logit contributions | |
ocrine | -2.442 |
ary | -2.286 |
atory | -2.216 |
idia | -2.147 |
gery | -2.125 |
Token | THE |
Token ID | 3336 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
én | +1.911 |
everal | +1.834 |
DEM | +1.728 |
hate | +1.654 |
friend | +1.653 |
Neg logit contributions | |
ocrine | -2.432 |
ary | -2.238 |
atory | -2.177 |
idia | -2.056 |
gery | -2.045 |
Token | � |
Token ID | 447 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ocrine | +3.314 |
ary | +3.132 |
atory | +2.973 |
gery | +2.819 |
idia | +2.808 |
Neg logit contributions | |
én | -3.275 |
everal | -3.175 |
hate | -2.908 |
DEM | -2.868 |
friend | -2.806 |
Token | � |
Token ID | 247 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
ocrine | +1.976 |
ary | +1.882 |
atory | +1.805 |
gery | +1.729 |
idia | +1.726 |
Neg logit contributions | |
én | -1.271 |
everal | -1.218 |
hate | -1.092 |
DEM | -1.070 |
friend | -1.040 |
Token | ve |
Token ID | 303 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
én | +2.189 |
everal | +2.050 |
hate | +1.993 |
friend | +1.888 |
fw | +1.866 |
Neg logit contributions | |
ocrine | -2.296 |
ary | -2.098 |
atory | -2.025 |
idia | -1.914 |
gery | -1.902 |
Token | trained |
Token ID | 8776 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
ocrine | +2.362 |
ary | +2.219 |
atory | +2.115 |
gery | +2.011 |
idia | +2.004 |
Neg logit contributions | |
én | -2.350 |
everal | -2.267 |
hate | -2.091 |
DEM | -2.049 |
friend | -2.018 |
Token | very |
Token ID | 845 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
én | +2.734 |
everal | +2.603 |
hate | +2.428 |
DEM | +2.371 |
friend | +2.337 |
Neg logit contributions | |
ocrine | -3.288 |
ary | -3.065 |
atory | -2.934 |
idia | -2.876 |
gery | -2.857 |
Token | rig |
Token ID | 7805 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
én | +1.969 |
everal | +1.877 |
hate | +1.737 |
DEM | +1.691 |
friend | +1.663 |
Neg logit contributions | |
ocrine | -2.446 |
ary | -2.282 |
atory | -2.184 |
idia | -2.150 |
gery | -2.130 |
Token | orously |
Token ID | 24882 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
én | +1.632 |
everal | +1.432 |
hate | +1.254 |
DEM | +1.237 |
friend | +1.195 |
Neg logit contributions | |
ocrine | -4.249 |
ary | -3.981 |
atory | -3.888 |
idia | -3.795 |
gery | -3.754 |
Token | here |
Token ID | 994 |
Feature activation | +7.40e+00 |
Pos logit contributions | |
ocrine | +0.260 |
ary | +0.244 |
atory | +0.233 |
idia | +0.224 |
gery | +0.223 |
Neg logit contributions | |
én | -0.234 |
everal | -0.221 |
hate | -0.205 |
DEM | -0.200 |
friend | -0.198 |
Token | in |
Token ID | 287 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ocrine | +5.252 |
ary | +4.987 |
atory | +4.704 |
ph | +4.437 |
gery | +4.412 |
Neg logit contributions | |
én | -5.806 |
everal | -5.748 |
hate | -5.217 |
DEM | -5.207 |
friend | -5.033 |
Token | Thailand |
Token ID | 16952 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ocrine | +0.896 |
ary | +0.838 |
atory | +0.799 |
gery | +0.756 |
idia | +0.755 |
Neg logit contributions | |
én | -0.949 |
everal | -0.920 |
hate | -0.853 |
DEM | -0.836 |
friend | -0.822 |
Token | for |
Token ID | 329 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ocrine | +0.194 |
ary | +0.181 |
atory | +0.173 |
gery | +0.166 |
idia | +0.165 |
Neg logit contributions | |
én | -0.173 |
everal | -0.164 |
hate | -0.152 |
DEM | -0.149 |
friend | -0.147 |
Token | Cloud |
Token ID | 10130 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ocrine | +1.178 |
ary | +1.100 |
atory | +1.053 |
idia | +1.001 |
gery | +0.999 |
Neg logit contributions | |
én | -1.085 |
everal | -1.041 |
hate | -0.952 |
DEM | -0.941 |
friend | -0.919 |
Token | based |
Token ID | 1912 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
én | +0.132 |
everal | +0.126 |
hate | +0.116 |
DEM | +0.115 |
friend | +0.112 |
Neg logit contributions | |
ocrine | -0.163 |
ary | -0.153 |
atory | -0.149 |
gery | -0.141 |
idia | -0.141 |
Token | Sc |
Token ID | 1446 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ocrine | +0.333 |
ary | +0.309 |
atory | +0.296 |
idia | +0.282 |
gery | +0.280 |
Neg logit contributions | |
én | -0.315 |
everal | -0.299 |
hate | -0.278 |
DEM | -0.274 |
friend | -0.267 |
Token | rub |
Token ID | 25089 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ocrine | +1.133 |
ary | +1.071 |
atory | +1.033 |
gery | +0.986 |
idia | +0.986 |
Neg logit contributions | |
én | -0.737 |
everal | -0.702 |
hate | -0.627 |
DEM | -0.615 |
friend | -0.597 |
Token | bing |
Token ID | 4623 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ocrine | +1.582 |
ary | +1.487 |
atory | +1.408 |
gery | +1.329 |
idia | +1.329 |
Neg logit contributions | |
én | -1.703 |
everal | -1.651 |
hate | -1.519 |
DEM | -1.501 |
friend | -1.470 |
Token | centers |
Token ID | 10399 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
én | +1.540 |
everal | +1.455 |
hate | +1.347 |
DEM | +1.336 |
friend | +1.309 |
Neg logit contributions | |
ocrine | -1.735 |
ary | -1.580 |
atory | -1.529 |
idia | -1.447 |
gery | -1.435 |
Token | and |
Token ID | 290 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
én | +0.752 |
everal | +0.707 |
hate | +0.656 |
DEM | +0.651 |
friend | +0.627 |
Neg logit contributions | |
ocrine | -0.827 |
ary | -0.764 |
atory | -0.733 |
gery | -0.701 |
idia | -0.700 |
Token | Content |
Token ID | 14041 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
én | +0.558 |
everal | +0.537 |
hate | +0.492 |
DEM | +0.485 |
friend | +0.475 |
Neg logit contributions | |
ocrine | -0.627 |
ary | -0.584 |
atory | -0.559 |
idia | -0.534 |
gery | -0.530 |
Token | Distribution |
Token ID | 27484 |
Feature activation | -7.51e+00 |
Pos logit contributions | |
én | +2.702 |
everal | +2.577 |
hate | +2.414 |
DEM | +2.369 |
friend | +2.350 |
Neg logit contributions | |
ocrine | -2.494 |
ary | -2.277 |
atory | -2.193 |
gery | -2.068 |
idia | -2.061 |
Token | Networks |
Token ID | 27862 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
én | +5.082 |
everal | +4.599 |
hate | +4.416 |
DEM | +4.384 |
Thieves | +4.345 |
Neg logit contributions | |
ocrine | -6.215 |
ary | -5.398 |
atory | -5.386 |
gery | -5.215 |
idia | -5.207 |
Token | ( |
Token ID | 357 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
én | +2.513 |
everal | +2.325 |
DEM | +2.189 |
hate | +2.177 |
orno | +2.088 |
Neg logit contributions | |
ocrine | -2.770 |
ary | -2.527 |
atory | -2.441 |
gery | -2.350 |
idia | -2.308 |
Token | Washington |
Token ID | 2669 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
én | +1.433 |
everal | +1.347 |
hate | +1.248 |
DEM | +1.241 |
friend | +1.194 |
Neg logit contributions | |
ocrine | -1.803 |
ary | -1.653 |
atory | -1.600 |
idia | -1.538 |
gery | -1.535 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ocrine | +0.026 |
ary | +0.024 |
atory | +0.023 |
idia | +0.022 |
gery | +0.021 |
Neg logit contributions | |
én | -0.024 |
everal | -0.023 |
DEM | -0.021 |
hate | -0.021 |
friend | -0.021 |
Token | its |
Token ID | 663 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
én | +0.740 |
everal | +0.706 |
hate | +0.658 |
DEM | +0.654 |
friend | +0.634 |
Neg logit contributions | |
ocrine | -0.818 |
ary | -0.754 |
atory | -0.715 |
idia | -0.699 |
gery | -0.690 |
Token | allies |
Token ID | 7681 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
én | +1.483 |
everal | +1.392 |
hate | +1.295 |
DEM | +1.285 |
friend | +1.269 |
Neg logit contributions | |
ocrine | -2.142 |
ary | -1.994 |
atory | -1.903 |
idia | -1.841 |
gery | -1.840 |
Token | have |
Token ID | 423 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
én | +2.300 |
everal | +2.118 |
hate | +2.042 |
DEM | +2.003 |
friend | +1.924 |
Neg logit contributions | |
ocrine | -2.798 |
ary | -2.586 |
atory | -2.463 |
idia | -2.399 |
gery | -2.369 |
Token | done |
Token ID | 1760 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
én | +1.059 |
everal | +1.001 |
hate | +0.932 |
DEM | +0.928 |
friend | +0.900 |
Neg logit contributions | |
ocrine | -1.266 |
ary | -1.170 |
atory | -1.126 |
idia | -1.075 |
gery | -1.065 |
Token | for |
Token ID | 329 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
én | +0.823 |
everal | +0.763 |
hate | +0.708 |
DEM | +0.702 |
friend | +0.689 |
Neg logit contributions | |
ocrine | -0.970 |
ary | -0.898 |
atory | -0.863 |
idia | -0.827 |
gery | -0.819 |
Token | decades |
Token ID | 4647 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ocrine | +2.479 |
ary | +2.319 |
atory | +2.208 |
idia | +2.090 |
gery | +2.081 |
Neg logit contributions | |
én | -2.441 |
everal | -2.355 |
hate | -2.167 |
DEM | -2.142 |
friend | -2.099 |
Token | since |
Token ID | 1201 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
ocrine | +1.497 |
ary | +1.403 |
atory | +1.340 |
gery | +1.273 |
idia | +1.267 |
Neg logit contributions | |
én | -1.431 |
everal | -1.372 |
hate | -1.264 |
DEM | -1.246 |
friend | -1.219 |
Token | the |
Token ID | 262 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ocrine | +3.345 |
ary | +3.152 |
atory | +2.984 |
gery | +2.820 |
idia | +2.810 |
Neg logit contributions | |
én | -3.612 |
everal | -3.509 |
hate | -3.223 |
DEM | -3.184 |
friend | -3.117 |
Token | dissolution |
Token ID | 37494 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
ocrine | +1.119 |
ary | +1.061 |
atory | +1.006 |
idia | +0.967 |
gery | +0.963 |
Neg logit contributions | |
én | -0.888 |
everal | -0.845 |
hate | -0.773 |
DEM | -0.765 |
friend | -0.746 |
Token | , |
Token ID | 11 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
ocrine | +1.620 |
ary | +1.519 |
atory | +1.457 |
gery | +1.392 |
idia | +1.381 |
Neg logit contributions | |
én | -1.464 |
everal | -1.403 |
hate | -1.288 |
DEM | -1.271 |
friend | -1.238 |
Token | but |
Token ID | 475 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
én | +0.234 |
everal | +0.224 |
hate | +0.207 |
DEM | +0.204 |
friend | +0.200 |
Neg logit contributions | |
ocrine | -0.261 |
ary | -0.244 |
atory | -0.234 |
idia | -0.223 |
gery | -0.222 |
Token | don |
Token ID | 836 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
ocrine | +0.138 |
ary | +0.129 |
atory | +0.123 |
idia | +0.118 |
gery | +0.117 |
Neg logit contributions | |
én | -0.123 |
everal | -0.118 |
hate | -0.109 |
DEM | -0.107 |
friend | -0.105 |
Token | � |
Token ID | 447 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
én | +2.572 |
hate | +2.054 |
DEM | +2.006 |
friend | +1.983 |
fw | +1.916 |
Neg logit contributions | |
ocrine | -5.569 |
ary | -5.176 |
idia | -5.034 |
gery | -4.987 |
atory | -4.979 |
Token | � |
Token ID | 247 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
ocrine | +0.364 |
ary | +0.347 |
atory | +0.333 |
idia | +0.320 |
gery | +0.320 |
Neg logit contributions | |
én | -0.221 |
everal | -0.208 |
hate | -0.188 |
DEM | -0.184 |
friend | -0.179 |
Token | t |
Token ID | 83 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
én | +1.438 |
everal | +1.283 |
hate | +1.211 |
friend | +1.162 |
DEM | +1.136 |
Neg logit contributions | |
ocrine | -2.497 |
ary | -2.353 |
atory | -2.243 |
idia | -2.182 |
gery | -2.175 |
Token | alert |
Token ID | 7995 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
ocrine | +1.466 |
ary | +1.379 |
atory | +1.319 |
idia | +1.254 |
gery | +1.250 |
Neg logit contributions | |
én | -1.299 |
everal | -1.244 |
hate | -1.148 |
DEM | -1.122 |
friend | -1.104 |
Token | on |
Token ID | 319 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
ocrine | +1.950 |
ary | +1.825 |
atory | +1.727 |
gery | +1.634 |
idia | +1.628 |
Neg logit contributions | |
én | -2.248 |
everal | -2.173 |
hate | -2.012 |
DEM | -1.994 |
friend | -1.951 |
Token | a |
Token ID | 257 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
én | +1.610 |
everal | +1.553 |
DEM | +1.421 |
hate | +1.421 |
friend | +1.370 |
Neg logit contributions | |
ocrine | -1.753 |
ary | -1.619 |
atory | -1.558 |
idia | -1.483 |
gery | -1.461 |
Token | file |
Token ID | 2393 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
ocrine | +0.202 |
ary | +0.189 |
atory | +0.182 |
idia | +0.175 |
gery | +0.172 |
Neg logit contributions | |
én | -0.172 |
everal | -0.169 |
hate | -0.153 |
DEM | -0.151 |
friend | -0.148 |
Token | that |
Token ID | 326 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
én | +3.783 |
everal | +3.519 |
hate | +3.325 |
DEM | +3.244 |
friend | +3.233 |
Neg logit contributions | |
ocrine | -4.433 |
ary | -4.048 |
atory | -3.897 |
idia | -3.790 |
gery | -3.666 |
Token | was |
Token ID | 373 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
én | +0.909 |
everal | +0.868 |
hate | +0.816 |
DEM | +0.800 |
friend | +0.777 |
Neg logit contributions | |
ocrine | -1.082 |
ary | -0.987 |
atory | -0.961 |
gery | -0.932 |
idia | -0.926 |
Token | not |
Token ID | 407 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
ocrine | +2.023 |
ary | +1.903 |
atory | +1.816 |
idia | +1.733 |
gery | +1.731 |
Neg logit contributions | |
én | -1.771 |
everal | -1.709 |
hate | -1.567 |
DEM | -1.546 |
friend | -1.504 |
Token | about |
Token ID | 546 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ocrine | +2.546 |
ary | +2.402 |
atory | +2.292 |
idia | +2.196 |
gery | +2.195 |
Neg logit contributions | |
én | -2.014 |
everal | -1.935 |
hate | -1.765 |
DEM | -1.745 |
friend | -1.693 |
Token | policy |
Token ID | 2450 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
én | +0.300 |
everal | +0.288 |
hate | +0.270 |
DEM | +0.266 |
friend | +0.259 |
Neg logit contributions | |
ocrine | -0.333 |
ary | -0.308 |
atory | -0.294 |
idia | -0.283 |
gery | -0.278 |
Token | differences |
Token ID | 5400 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
én | +1.622 |
everal | +1.519 |
hate | +1.445 |
DEM | +1.408 |
friend | +1.374 |
Neg logit contributions | |
ocrine | -2.085 |
ary | -1.905 |
atory | -1.877 |
idia | -1.816 |
gery | -1.771 |
Token | . |
Token ID | 13 |
Feature activation | -7.70e+00 |
Pos logit contributions | |
én | +3.523 |
everal | +3.311 |
hate | +3.159 |
DEM | +3.058 |
friend | +2.987 |
Neg logit contributions | |
ocrine | -4.763 |
ary | -4.324 |
atory | -4.263 |
idia | -4.113 |
gery | -4.089 |
Token | It |
Token ID | 632 |
Feature activation | -6.50e+00 |
Pos logit contributions | |
én | +4.389 |
DEM | +4.044 |
hate | +3.996 |
everal | +3.851 |
Thieves | +3.835 |
Neg logit contributions | |
ocrine | -6.743 |
ary | -6.135 |
atory | -5.980 |
idia | -5.894 |
gery | -5.843 |
Token | was |
Token ID | 373 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
én | +4.139 |
everal | +3.826 |
hate | +3.632 |
DEM | +3.550 |
friend | +3.428 |
Neg logit contributions | |
ocrine | -5.401 |
ary | -4.892 |
atory | -4.839 |
gery | -4.686 |
idia | -4.677 |
Token | about |
Token ID | 546 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
én | +1.545 |
everal | +1.476 |
hate | +1.357 |
DEM | +1.349 |
friend | +1.282 |
Neg logit contributions | |
ocrine | -2.406 |
ary | -2.244 |
atory | -2.175 |
idia | -2.106 |
gery | -2.088 |
Token | emotions |
Token ID | 10825 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
én | +0.633 |
everal | +0.610 |
hate | +0.569 |
DEM | +0.561 |
friend | +0.549 |
Neg logit contributions | |
ocrine | -0.722 |
ary | -0.668 |
atory | -0.640 |
idia | -0.616 |
gery | -0.604 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
ocrine | +0.911 |
ary | +0.857 |
atory | +0.819 |
gery | +0.779 |
idia | +0.777 |
Neg logit contributions | |
én | -0.859 |
everal | -0.832 |
hate | -0.764 |
DEM | -0.752 |
friend | -0.732 |
Token | Irvine |
Token ID | 37277 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ocrine | +1.101 |
ary | +1.035 |
atory | +0.993 |
gery | +0.945 |
idia | +0.940 |
Neg logit contributions | |
én | -1.019 |
everal | -0.981 |
hate | -0.901 |
DEM | -0.887 |
friend | -0.869 |
Token | , |
Token ID | 11 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
ocrine | +1.074 |
ary | +1.008 |
atory | +0.963 |
gery | +0.923 |
idia | +0.916 |
Neg logit contributions | |
én | -0.996 |
everal | -0.953 |
hate | -0.878 |
DEM | -0.869 |
friend | -0.847 |
Token | November |
Token ID | 3389 |
Feature activation | -6.38e+00 |
Pos logit contributions | |
én | +3.673 |
everal | +3.512 |
hate | +3.278 |
friend | +3.254 |
orno | +3.225 |
Neg logit contributions | |
ocrine | -3.336 |
ary | -3.067 |
atory | -2.932 |
gery | -2.776 |
idia | -2.729 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
én | +4.120 |
DEM | +3.683 |
friend | +3.625 |
Thieves | +3.548 |
hate | +3.544 |
Neg logit contributions | |
ocrine | -5.249 |
atory | -4.684 |
ary | -4.648 |
idia | -4.545 |
gery | -4.506 |
Token | , |
Token ID | 11 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
én | +1.409 |
everal | +1.368 |
hate | +1.252 |
DEM | +1.236 |
friend | +1.209 |
Neg logit contributions | |
ocrine | -1.408 |
ary | -1.330 |
atory | -1.262 |
gery | -1.195 |
idia | -1.192 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -7.75e+00 |
Pos logit contributions | |
én | +2.764 |
everal | +2.598 |
hate | +2.443 |
friend | +2.422 |
DEM | +2.417 |
Neg logit contributions | |
ocrine | -2.615 |
ary | -2.402 |
atory | -2.344 |
gery | -2.241 |
idia | -2.222 |
Token | , |
Token ID | 11 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
én | +5.260 |
everal | +5.060 |
hate | +4.590 |
DEM | +4.536 |
friend | +4.424 |
Neg logit contributions | |
ocrine | -6.299 |
ary | -5.845 |
atory | -5.678 |
idia | -5.441 |
gery | -5.412 |
Token | in |
Token ID | 287 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
én | +3.106 |
everal | +2.891 |
hate | +2.664 |
friend | +2.646 |
DEM | +2.600 |
Neg logit contributions | |
ocrine | -3.897 |
ary | -3.626 |
atory | -3.533 |
gery | -3.370 |
idia | -3.340 |
Token | Irvine |
Token ID | 37277 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
én | +0.254 |
everal | +0.248 |
hate | +0.234 |
DEM | +0.230 |
friend | +0.229 |
Neg logit contributions | |
ocrine | -0.142 |
ary | -0.129 |
atory | -0.121 |
gery | -0.112 |
idia | -0.110 |
Token | , |
Token ID | 11 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
ocrine | +1.194 |
ary | +1.119 |
atory | +1.068 |
gery | +1.017 |
idia | +1.009 |
Neg logit contributions | |
én | -1.126 |
everal | -1.074 |
hate | -0.997 |
DEM | -0.981 |
friend | -0.959 |
Token | California |
Token ID | 3442 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
én | +2.802 |
everal | +2.702 |
hate | +2.527 |
friend | +2.480 |
DEM | +2.468 |
Neg logit contributions | |
ocrine | -2.224 |
ary | -2.040 |
atory | -1.922 |
gery | -1.836 |
idia | -1.804 |
Token | W |
Token ID | 54 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
én | +1.685 |
everal | +1.598 |
hate | +1.485 |
DEM | +1.471 |
friend | +1.445 |
Neg logit contributions | |
ocrine | -2.361 |
ary | -2.193 |
atory | -2.110 |
gery | -2.042 |
idia | -2.041 |
Token | inger |
Token ID | 3889 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
én | +2.621 |
everal | +2.431 |
hate | +2.236 |
DEM | +2.171 |
friend | +2.132 |
Neg logit contributions | |
ocrine | -3.120 |
ary | -2.812 |
atory | -2.767 |
gery | -2.691 |
idia | -2.626 |
Token | � |
Token ID | 447 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
én | +0.485 |
everal | +0.461 |
hate | +0.423 |
DEM | +0.416 |
friend | +0.415 |
Neg logit contributions | |
ocrine | -0.548 |
ary | -0.505 |
atory | -0.491 |
idia | -0.469 |
gery | -0.468 |
Token | � |
Token ID | 247 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
én | +1.476 |
everal | +1.420 |
hate | +1.244 |
DEM | +1.215 |
friend | +1.180 |
Neg logit contributions | |
ocrine | -2.532 |
ary | -2.404 |
atory | -2.321 |
idia | -2.240 |
gery | -2.227 |
Token | = |
Token ID | 796 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
én | +1.575 |
everal | +1.482 |
hate | +1.377 |
friend | +1.348 |
DEM | +1.347 |
Neg logit contributions | |
ocrine | -1.749 |
ary | -1.593 |
atory | -1.550 |
idia | -1.493 |
gery | -1.482 |
Token | TIT |
Token ID | 37977 |
Feature activation | -7.48e+00 |
Pos logit contributions | |
ocrine | +2.023 |
ary | +1.911 |
atory | +1.817 |
gery | +1.730 |
idia | +1.727 |
Neg logit contributions | |
én | -1.855 |
everal | -1.795 |
hate | -1.636 |
DEM | -1.617 |
friend | -1.584 |
Token | , |
Token ID | 11 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
én | +4.789 |
everal | +4.345 |
DEM | +4.077 |
friend | +3.968 |
hate | +3.967 |
Neg logit contributions | |
ocrine | -6.300 |
ary | -5.871 |
atory | -5.612 |
idia | -5.508 |
gery | -5.499 |
Token | � |
Token ID | 564 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ocrine | +0.295 |
ary | +0.277 |
atory | +0.263 |
gery | +0.252 |
idia | +0.252 |
Neg logit contributions | |
én | -0.272 |
everal | -0.262 |
hate | -0.240 |
DEM | -0.238 |
friend | -0.235 |
Token | � |
Token ID | 246 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
én | +0.902 |
everal | +0.873 |
hate | +0.785 |
DEM | +0.772 |
friend | +0.752 |
Neg logit contributions | |
ocrine | -1.109 |
ary | -1.051 |
atory | -1.004 |
gery | -0.960 |
idia | -0.958 |
Token | def |
Token ID | 4299 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
én | +1.849 |
everal | +1.754 |
hate | +1.635 |
friend | +1.603 |
DEM | +1.590 |
Neg logit contributions | |
ocrine | -2.653 |
ary | -2.480 |
atory | -2.386 |
idia | -2.327 |
gery | -2.308 |
Token | ensive |
Token ID | 2021 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
ocrine | +0.813 |
ary | +0.765 |
atory | +0.729 |
gery | +0.707 |
idia | +0.703 |
Neg logit contributions | |
én | -0.634 |
everal | -0.602 |
hate | -0.536 |
DEM | -0.531 |
friend | -0.527 |
Token | thoughts |
Token ID | 6066 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
én | +0.692 |
everal | +0.656 |
hate | +0.617 |
DEM | +0.593 |
friend | +0.588 |
Neg logit contributions | |
ocrine | -0.788 |
ary | -0.736 |
atory | -0.703 |
idia | -0.681 |
gery | -0.676 |
Token | were |
Token ID | 547 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
én | +0.594 |
everal | +0.560 |
hate | +0.529 |
DEM | +0.516 |
friend | +0.504 |
Neg logit contributions | |
ocrine | -0.587 |
ary | -0.541 |
atory | -0.517 |
gery | -0.505 |
idia | -0.501 |
Token | coming |
Token ID | 2406 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
én | +2.162 |
everal | +1.989 |
hate | +1.899 |
DEM | +1.848 |
friend | +1.809 |
Neg logit contributions | |
ocrine | -2.209 |
ary | -1.971 |
atory | -1.936 |
gery | -1.864 |
idia | -1.845 |
Token | from |
Token ID | 422 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
ocrine | +1.439 |
ary | +1.351 |
atory | +1.284 |
gery | +1.230 |
idia | +1.223 |
Neg logit contributions | |
én | -1.335 |
everal | -1.265 |
hate | -1.168 |
DEM | -1.150 |
friend | -1.125 |
Token | and |
Token ID | 290 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
ocrine | +0.385 |
ary | +0.361 |
atory | +0.345 |
gery | +0.334 |
idia | +0.333 |
Neg logit contributions | |
én | -0.306 |
everal | -0.285 |
hate | -0.262 |
DEM | -0.262 |
friend | -0.254 |
Token | tools |
Token ID | 4899 |
Feature activation | -7.28e+00 |
Pos logit contributions | |
én | +0.360 |
everal | +0.336 |
hate | +0.313 |
DEM | +0.310 |
friend | +0.304 |
Neg logit contributions | |
ocrine | -0.411 |
ary | -0.381 |
atory | -0.360 |
idia | -0.354 |
gery | -0.350 |
Token | to |
Token ID | 284 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
én | +4.694 |
everal | +4.102 |
hate | +3.918 |
DEM | +3.854 |
friend | +3.703 |
Neg logit contributions | |
ocrine | -6.017 |
ary | -5.513 |
idia | -5.318 |
atory | -5.273 |
gery | -5.191 |
Token | deal |
Token ID | 1730 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
én | +2.252 |
everal | +2.011 |
hate | +1.937 |
DEM | +1.883 |
friend | +1.866 |
Neg logit contributions | |
ocrine | -2.656 |
ary | -2.460 |
atory | -2.354 |
idia | -2.272 |
gery | -2.213 |
Token | with |
Token ID | 351 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
én | +1.163 |
everal | +1.128 |
hate | +1.041 |
DEM | +1.028 |
friend | +1.003 |
Neg logit contributions | |
ocrine | -1.003 |
ary | -0.944 |
atory | -0.890 |
idia | -0.842 |
gery | -0.842 |
Token | these |
Token ID | 777 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ocrine | +2.301 |
ary | +2.156 |
atory | +2.044 |
idia | +1.927 |
gery | +1.927 |
Neg logit contributions | |
én | -2.632 |
everal | -2.546 |
hate | -2.359 |
DEM | -2.320 |
friend | -2.274 |
Token | thoughts |
Token ID | 6066 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ocrine | +2.081 |
ary | +1.954 |
atory | +1.861 |
gery | +1.770 |
idia | +1.765 |
Neg logit contributions | |
én | -2.159 |
everal | -2.080 |
hate | -1.934 |
DEM | -1.888 |
friend | -1.856 |
Token | The |
Token ID | 383 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
ocrine | +2.034 |
ary | +1.914 |
atory | +1.822 |
idia | +1.750 |
gery | +1.744 |
Neg logit contributions | |
én | -1.839 |
everal | -1.714 |
DEM | -1.619 |
hate | -1.611 |
friend | -1.563 |
Token | below |
Token ID | 2174 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
ocrine | +0.672 |
ary | +0.631 |
atory | +0.606 |
idia | +0.577 |
gery | +0.574 |
Neg logit contributions | |
én | -0.605 |
everal | -0.576 |
hate | -0.530 |
DEM | -0.530 |
friend | -0.514 |
Token | chart |
Token ID | 8262 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
ocrine | +0.289 |
ary | +0.270 |
atory | +0.254 |
idia | +0.247 |
gery | +0.245 |
Neg logit contributions | |
én | -0.287 |
everal | -0.270 |
hate | -0.250 |
DEM | -0.249 |
friend | -0.241 |
Token | shows |
Token ID | 2523 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
én | +2.399 |
everal | +2.175 |
DEM | +2.044 |
hate | +2.036 |
friend | +2.004 |
Neg logit contributions | |
ocrine | -2.895 |
ary | -2.617 |
atory | -2.554 |
idia | -2.513 |
gery | -2.438 |
Token | the |
Token ID | 262 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
én | +0.169 |
everal | +0.162 |
DEM | +0.151 |
hate | +0.148 |
friend | +0.143 |
Neg logit contributions | |
ocrine | -0.182 |
ary | -0.169 |
atory | -0.161 |
idia | -0.157 |
gery | -0.155 |
Token | distribution |
Token ID | 6082 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
ocrine | +0.264 |
ary | +0.246 |
atory | +0.235 |
idia | +0.226 |
gery | +0.224 |
Neg logit contributions | |
én | -0.253 |
everal | -0.242 |
DEM | -0.224 |
hate | -0.223 |
friend | -0.216 |
Token | in |
Token ID | 287 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
én | +4.961 |
everal | +4.704 |
DEM | +4.337 |
hate | +4.265 |
friend | +4.138 |
Neg logit contributions | |
ocrine | -5.644 |
ary | -5.063 |
atory | -5.002 |
gery | -4.961 |
idia | -4.919 |
Token | the |
Token ID | 262 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
én | +0.110 |
everal | +0.104 |
DEM | +0.097 |
hate | +0.096 |
friend | +0.094 |
Neg logit contributions | |
ocrine | -0.122 |
ary | -0.114 |
atory | -0.110 |
idia | -0.106 |
gery | -0.105 |
Token | national |
Token ID | 2260 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
én | +0.195 |
everal | +0.185 |
DEM | +0.172 |
hate | +0.171 |
friend | +0.168 |
Neg logit contributions | |
ocrine | -0.212 |
ary | -0.199 |
atory | -0.190 |
gery | -0.183 |
idia | -0.183 |
Token | legislature |
Token ID | 15928 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
ocrine | +0.903 |
ary | +0.839 |
atory | +0.798 |
gery | +0.774 |
idia | +0.770 |
Neg logit contributions | |
én | -0.850 |
everal | -0.810 |
hate | -0.751 |
DEM | -0.750 |
friend | -0.726 |
Token | of |
Token ID | 286 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
ocrine | +3.549 |
ary | +3.346 |
atory | +3.178 |
gery | +3.014 |
idia | +3.005 |
Neg logit contributions | |
én | -3.550 |
everal | -3.436 |
hate | -3.150 |
DEM | -3.114 |
friend | -3.042 |