Token | ! |
Token ID | 0 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
edIn | +6.568 |
ification | +5.982 |
ifiers | +5.889 |
ified | +5.856 |
itect | +5.821 |
Neg logit contributions | |
senal | -4.916 |
berman | -4.916 |
Klux | -4.819 |
mma | -4.814 |
tails | -4.797 |
Token | Sign |
Token ID | 5865 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
edIn | +0.696 |
itect | +0.610 |
ification | +0.599 |
ified | +0.594 |
icians | +0.593 |
Neg logit contributions | |
berman | -0.637 |
tti | -0.607 |
HAEL | -0.597 |
mma | -0.592 |
tails | -0.592 |
Token | up |
Token ID | 510 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
edIn | +4.447 |
ified | +3.993 |
ification | +3.969 |
icians | +3.916 |
itect | +3.889 |
Neg logit contributions | |
berman | -2.484 |
HAEL | -2.429 |
tti | -2.371 |
senal | -2.364 |
tails | -2.336 |
Token | for |
Token ID | 329 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
edIn | +2.573 |
ification | +2.326 |
ified | +2.312 |
icians | +2.312 |
itect | +2.274 |
Neg logit contributions | |
berman | -1.645 |
HAEL | -1.640 |
tails | -1.559 |
tti | -1.550 |
Gamble | -1.495 |
Token | our |
Token ID | 674 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
edIn | +0.590 |
ification | +0.521 |
icians | +0.521 |
ified | +0.520 |
itect | +0.513 |
Neg logit contributions | |
berman | -0.469 |
HAEL | -0.448 |
tti | -0.448 |
tails | -0.437 |
mma | -0.430 |
Token | Email |
Token ID | 9570 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
berman | +2.009 |
HAEL | +1.935 |
tti | +1.926 |
tails | +1.870 |
Heck | +1.865 |
Neg logit contributions | |
edIn | -2.904 |
itect | -2.573 |
ification | -2.550 |
ified | -2.531 |
icians | -2.524 |
Token | News |
Token ID | 3000 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
berman | +5.409 |
Heck | +5.091 |
tti | +4.735 |
mma | +4.714 |
HO | +4.619 |
Neg logit contributions | |
edIn | -17.007 |
itect | -16.967 |
icter | -16.800 |
icians | -16.573 |
ifiers | -16.443 |
Token | letters |
Token ID | 15653 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
edIn | +2.873 |
ification | +2.333 |
icians | +2.295 |
ified | +2.265 |
itect | +2.240 |
Neg logit contributions | |
berman | -5.100 |
HAEL | -4.982 |
tti | -4.945 |
tails | -4.849 |
mma | -4.785 |
Token | here |
Token ID | 994 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
edIn | +0.258 |
icians | +0.224 |
itect | +0.224 |
ification | +0.222 |
ified | +0.221 |
Neg logit contributions | |
berman | -0.256 |
tti | -0.245 |
HAEL | -0.243 |
tails | -0.239 |
Heck | -0.238 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
edIn | +0.489 |
ification | +0.440 |
icians | +0.437 |
ified | +0.437 |
itect | +0.435 |
Neg logit contributions | |
berman | -0.274 |
HAEL | -0.257 |
tti | -0.256 |
tails | -0.249 |
Heck | -0.241 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
edIn | +0.327 |
icians | +0.282 |
itect | +0.279 |
ified | +0.278 |
ification | +0.278 |
Neg logit contributions | |
berman | -0.328 |
tti | -0.322 |
HAEL | -0.317 |
Heck | -0.311 |
tails | -0.309 |
Token | ex |
Token ID | 409 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
edIn | +0.272 |
icians | +0.238 |
itect | +0.237 |
ification | +0.236 |
ified | +0.235 |
Neg logit contributions | |
berman | -0.197 |
tti | -0.189 |
HAEL | -0.188 |
tails | -0.184 |
Heck | -0.181 |
Token | pelling |
Token ID | 35025 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
berman | +2.581 |
tti | +2.504 |
tails | +2.470 |
HAEL | +2.467 |
Heck | +2.433 |
Neg logit contributions | |
edIn | -1.361 |
icians | -1.065 |
ified | -1.044 |
itect | -1.033 |
ification | -1.032 |
Token | Cuba |
Token ID | 14159 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
berman | +2.083 |
tti | +2.002 |
HAEL | +1.973 |
Heck | +1.955 |
tails | +1.943 |
Neg logit contributions | |
edIn | -2.849 |
icians | -2.493 |
itect | -2.483 |
ification | -2.451 |
ified | -2.444 |
Token | from |
Token ID | 422 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
edIn | +1.956 |
icians | +1.726 |
ification | +1.721 |
itect | +1.715 |
ified | +1.712 |
Neg logit contributions | |
berman | -1.307 |
tti | -1.253 |
HAEL | -1.252 |
tails | -1.214 |
Heck | -1.191 |
Token | the |
Token ID | 262 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
edIn | +2.336 |
icians | +2.045 |
ification | +2.043 |
itect | +2.030 |
ified | +2.029 |
Neg logit contributions | |
berman | -1.850 |
HAEL | -1.779 |
tti | -1.778 |
tails | -1.727 |
Heck | -1.696 |
Token | O |
Token ID | 440 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
edIn | +1.197 |
icians | +1.058 |
ification | +1.056 |
itect | +1.051 |
ified | +1.049 |
Neg logit contributions | |
berman | -0.769 |
tti | -0.736 |
HAEL | -0.735 |
tails | -0.713 |
Heck | -0.700 |
Token | AS |
Token ID | 1921 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
DI | +5.143 |
HO | +4.839 |
berman | +4.767 |
tti | +4.384 |
HAEL | +4.322 |
Neg logit contributions | |
edIn | -17.806 |
icter | -15.905 |
icians | -15.506 |
itect | -15.461 |
ification | -15.018 |
Token | in |
Token ID | 287 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
berman | +1.410 |
tti | +1.366 |
HAEL | +1.351 |
tails | +1.314 |
Gamble | +1.309 |
Neg logit contributions | |
edIn | -1.956 |
icians | -1.710 |
itect | -1.683 |
ification | -1.676 |
ified | -1.673 |
Token | 1962 |
Token ID | 20033 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
edIn | +1.142 |
icians | +0.982 |
ification | +0.981 |
itect | +0.974 |
ified | +0.974 |
Neg logit contributions | |
berman | -1.148 |
HAEL | -1.110 |
tti | -1.109 |
tails | -1.082 |
Heck | -1.066 |
Token | reversed |
Token ID | 17687 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
berman | +3.099 |
tti | +3.031 |
HAEL | +2.924 |
Heck | +2.855 |
tails | +2.850 |
Neg logit contributions | |
edIn | -4.537 |
icians | -3.835 |
itect | -3.783 |
ified | -3.719 |
ification | -3.712 |
Token | course |
Token ID | 1781 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
berman | +0.232 |
tti | +0.221 |
HAEL | +0.220 |
tails | +0.214 |
Heck | +0.211 |
Neg logit contributions | |
edIn | -0.364 |
icians | -0.322 |
itect | -0.321 |
ification | -0.321 |
ified | -0.319 |
Token | of |
Token ID | 286 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
berman | +0.924 |
tti | +0.879 |
HAEL | +0.871 |
Heck | +0.828 |
tails | +0.823 |
Neg logit contributions | |
edIn | -1.979 |
icians | -1.770 |
itect | -1.759 |
ification | -1.759 |
ified | -1.747 |
Token | Mana |
Token ID | 17493 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
berman | +0.819 |
HAEL | +0.780 |
tti | +0.779 |
tails | +0.753 |
Heck | +0.735 |
Neg logit contributions | |
edIn | -1.526 |
icians | -1.362 |
ification | -1.360 |
itect | -1.354 |
ified | -1.353 |
Token | � |
Token ID | 447 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
berman | +2.947 |
tti | +2.851 |
HAEL | +2.756 |
Heck | +2.728 |
tails | +2.696 |
Neg logit contributions | |
edIn | -4.607 |
icians | -4.033 |
ification | -4.009 |
itect | -3.989 |
ified | -3.966 |
Token | � |
Token ID | 247 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
edIn | +0.258 |
icians | +0.223 |
ification | +0.223 |
itect | +0.221 |
ified | +0.221 |
Neg logit contributions | |
berman | -0.247 |
tti | -0.239 |
HAEL | -0.239 |
tails | -0.233 |
Heck | -0.229 |
Token | s |
Token ID | 82 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
berman | +1.597 |
tti | +1.550 |
HAEL | +1.503 |
tails | +1.497 |
mma | +1.453 |
Neg logit contributions | |
edIn | -2.373 |
ification | -2.069 |
icians | -2.061 |
itect | -2.047 |
ified | -2.043 |
Token | O |
Token ID | 440 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
berman | +0.507 |
tti | +0.488 |
HAEL | +0.486 |
tails | +0.474 |
Heck | +0.469 |
Neg logit contributions | |
edIn | -0.581 |
icians | -0.505 |
ification | -0.503 |
itect | -0.501 |
ified | -0.499 |
Token | ST |
Token ID | 2257 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
berman | +9.091 |
tti | +8.577 |
DI | +8.569 |
HO | +8.120 |
train | +8.032 |
Neg logit contributions | |
edIn | -12.923 |
icter | -11.696 |
icians | -11.370 |
itect | -11.229 |
ified | -11.181 |
Token | set |
Token ID | 900 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
berman | +1.826 |
tti | +1.767 |
HAEL | +1.742 |
tails | +1.696 |
Heck | +1.675 |
Neg logit contributions | |
edIn | -2.788 |
icians | -2.441 |
ification | -2.412 |
itect | -2.409 |
ified | -2.394 |
Token | the |
Token ID | 262 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
edIn | +3.253 |
ification | +2.887 |
icians | +2.884 |
ified | +2.870 |
itect | +2.851 |
Neg logit contributions | |
berman | -2.239 |
HAEL | -2.161 |
tti | -2.137 |
tails | -2.084 |
mma | -2.050 |
Token | bar |
Token ID | 2318 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
edIn | +1.267 |
icians | +1.104 |
ification | +1.100 |
itect | +1.096 |
ified | +1.092 |
Neg logit contributions | |
berman | -1.056 |
tti | -1.015 |
HAEL | -1.013 |
tails | -0.988 |
Heck | -0.974 |
Token | for |
Token ID | 329 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
berman | +1.919 |
tti | +1.805 |
HAEL | +1.805 |
Heck | +1.769 |
tails | +1.743 |
Neg logit contributions | |
edIn | -3.292 |
icians | -2.892 |
itect | -2.883 |
ification | -2.875 |
ified | -2.848 |
Token | Margaret |
Token ID | 19579 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
berman | +1.022 |
tti | +0.994 |
HAEL | +0.987 |
Heck | +0.957 |
tails | +0.951 |
Neg logit contributions | |
edIn | -1.245 |
icians | -1.073 |
itect | -1.060 |
ification | -1.055 |
ified | -1.051 |
Token | At |
Token ID | 1629 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
edIn | +0.718 |
icians | +0.639 |
ification | +0.638 |
itect | +0.635 |
ified | +0.634 |
Neg logit contributions | |
berman | -0.416 |
HAEL | -0.397 |
tti | -0.396 |
tails | -0.383 |
Heck | -0.374 |
Token | wood |
Token ID | 3822 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
berman | +3.051 |
tti | +2.947 |
HAEL | +2.776 |
tails | +2.742 |
Heck | +2.723 |
Neg logit contributions | |
edIn | -4.683 |
itect | -4.022 |
icians | -4.009 |
ified | -3.972 |
ification | -3.969 |
Token | and |
Token ID | 290 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
edIn | +1.270 |
icians | +1.127 |
ification | +1.125 |
itect | +1.119 |
ified | +1.118 |
Neg logit contributions | |
berman | -0.789 |
HAEL | -0.754 |
tti | -0.753 |
tails | -0.730 |
Heck | -0.715 |
Token | Michael |
Token ID | 3899 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
berman | +1.993 |
tti | +1.935 |
HAEL | +1.930 |
Heck | +1.876 |
Gamble | +1.865 |
Neg logit contributions | |
edIn | -3.015 |
icians | -2.621 |
ification | -2.616 |
itect | -2.615 |
ified | -2.597 |
Token | O |
Token ID | 440 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
Gamble | +5.770 |
berman | +5.697 |
Heck | +5.672 |
tti | +5.662 |
HAEL | +5.386 |
Neg logit contributions | |
edIn | -9.905 |
icians | -8.525 |
itect | -8.498 |
icter | -8.365 |
ification | -8.344 |
Token | nda |
Token ID | 45658 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
berman | +10.356 |
tti | +10.006 |
train | +9.342 |
Gamble | +9.259 |
mouth | +9.047 |
Neg logit contributions | |
edIn | -11.473 |
icter | -10.029 |
itect | -9.847 |
icians | -9.745 |
acters | -9.552 |
Token | at |
Token ID | 265 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
edIn | +3.034 |
itect | +2.634 |
ification | +2.629 |
icians | +2.608 |
ified | +2.606 |
Neg logit contributions | |
berman | -2.762 |
tti | -2.696 |
HAEL | -2.643 |
tails | -2.565 |
mma | -2.544 |
Token | je |
Token ID | 18015 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
edIn | +2.067 |
ification | +1.764 |
ified | +1.735 |
icians | +1.734 |
ifiers | +1.707 |
Neg logit contributions | |
berman | -3.198 |
tti | -3.082 |
tails | -3.063 |
HAEL | -3.054 |
train | -2.977 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
edIn | +4.546 |
ification | +4.074 |
icians | +4.069 |
itect | +4.061 |
ified | +4.036 |
Neg logit contributions | |
berman | -2.643 |
HAEL | -2.565 |
tails | -2.482 |
tti | -2.473 |
mma | -2.394 |
Token | It |
Token ID | 632 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
edIn | +0.431 |
icians | +0.379 |
ification | +0.377 |
ified | +0.375 |
itect | +0.375 |
Neg logit contributions | |
berman | -0.312 |
tti | -0.301 |
HAEL | -0.301 |
tails | -0.292 |
Heck | -0.288 |
Token | 1999 |
Token ID | 18946 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
berman | +0.551 |
tti | +0.530 |
HAEL | +0.529 |
tails | +0.514 |
mma | +0.504 |
Neg logit contributions | |
edIn | -0.735 |
icians | -0.644 |
ification | -0.640 |
itect | -0.640 |
ified | -0.636 |
Token | The |
Token ID | 383 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
edIn | +3.970 |
icians | +3.568 |
ification | +3.547 |
ified | +3.531 |
itect | +3.493 |
Neg logit contributions | |
berman | -2.680 |
HAEL | -2.586 |
tti | -2.534 |
tails | -2.494 |
mma | -2.434 |
Token | NIH |
Token ID | 37483 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
berman | +0.826 |
tti | +0.795 |
HAEL | +0.786 |
Heck | +0.763 |
tails | +0.760 |
Neg logit contributions | |
edIn | -1.328 |
icians | -1.168 |
itect | -1.166 |
ification | -1.164 |
ified | -1.156 |
Token | and |
Token ID | 290 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
edIn | +3.492 |
ification | +3.094 |
icians | +3.091 |
ified | +3.074 |
itect | +3.069 |
Neg logit contributions | |
berman | -2.865 |
HAEL | -2.743 |
tti | -2.727 |
tails | -2.667 |
mma | -2.611 |
Token | the |
Token ID | 262 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
berman | +2.101 |
tti | +2.040 |
HAEL | +2.004 |
Heck | +1.972 |
tails | +1.946 |
Neg logit contributions | |
edIn | -3.193 |
itect | -2.785 |
ification | -2.778 |
icians | -2.771 |
ified | -2.751 |
Token | O |
Token ID | 440 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
berman | +2.306 |
tti | +2.242 |
HAEL | +2.181 |
Heck | +2.174 |
Gamble | +2.127 |
Neg logit contributions | |
edIn | -3.961 |
itect | -3.468 |
ification | -3.459 |
icians | -3.436 |
ifiers | -3.422 |
Token | HR |
Token ID | 17184 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
tti | +8.931 |
berman | +8.595 |
DI | +8.577 |
HO | +8.315 |
Heck | +7.817 |
Neg logit contributions | |
edIn | -12.626 |
icter | -11.168 |
itect | -10.990 |
acters | -10.746 |
icians | -10.709 |
Token | P |
Token ID | 47 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
berman | +1.953 |
tti | +1.883 |
HAEL | +1.883 |
tails | +1.829 |
Heck | +1.796 |
Neg logit contributions | |
edIn | -2.321 |
icians | -1.999 |
itect | -1.983 |
ification | -1.981 |
ified | -1.975 |
Token | require |
Token ID | 2421 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
berman | +3.747 |
tti | +3.638 |
HAEL | +3.602 |
tails | +3.514 |
Heck | +3.456 |
Neg logit contributions | |
edIn | -4.493 |
icians | -3.834 |
itect | -3.795 |
ification | -3.779 |
ified | -3.776 |
Token | all |
Token ID | 477 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
berman | +3.642 |
tti | +3.582 |
HAEL | +3.452 |
Heck | +3.449 |
Gamble | +3.411 |
Neg logit contributions | |
edIn | -5.379 |
itect | -4.727 |
icians | -4.622 |
ification | -4.576 |
ifiers | -4.560 |
Token | people |
Token ID | 661 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
berman | +4.020 |
tti | +3.939 |
Heck | +3.806 |
HAEL | +3.744 |
Gamble | +3.700 |
Neg logit contributions | |
edIn | -5.971 |
itect | -5.230 |
icians | -5.132 |
ification | -5.117 |
ifiers | -5.054 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
edIn | +1.217 |
icians | +1.059 |
ification | +1.057 |
itect | +1.051 |
ified | +1.050 |
Neg logit contributions | |
berman | -1.043 |
HAEL | -1.005 |
tti | -1.005 |
tails | -0.979 |
Heck | -0.963 |
Token | The |
Token ID | 464 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
edIn | +3.508 |
ification | +3.096 |
ified | +3.079 |
icians | +3.078 |
itect | +3.060 |
Neg logit contributions | |
berman | -2.375 |
tti | -2.273 |
HAEL | -2.273 |
Heck | -2.188 |
tails | -2.186 |
Token | People |
Token ID | 4380 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
edIn | +2.662 |
ification | +2.356 |
icians | +2.352 |
ified | +2.343 |
itect | +2.339 |
Neg logit contributions | |
berman | -1.798 |
HAEL | -1.729 |
tti | -1.719 |
tails | -1.673 |
mma | -1.632 |
Token | v |
Token ID | 410 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
edIn | +0.979 |
icians | +0.852 |
ification | +0.848 |
itect | +0.846 |
ified | +0.843 |
Neg logit contributions | |
berman | -0.826 |
tti | -0.796 |
HAEL | -0.791 |
tails | -0.770 |
Heck | -0.762 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
berman | +0.633 |
tti | +0.600 |
HAEL | +0.596 |
tails | +0.575 |
Heck | +0.570 |
Neg logit contributions | |
edIn | -1.265 |
icians | -1.127 |
itect | -1.125 |
ification | -1.125 |
ified | -1.119 |
Token | O |
Token ID | 440 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
berman | +3.733 |
Heck | +3.535 |
Gamble | +3.456 |
HAEL | +3.389 |
tti | +3.383 |
Neg logit contributions | |
edIn | -7.265 |
itect | -6.391 |
icians | -6.360 |
ified | -6.219 |
acters | -6.200 |
Token | . |
Token ID | 13 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
berman | +10.419 |
tti | +9.751 |
DI | +9.470 |
HO | +9.398 |
Heck | +9.357 |
Neg logit contributions | |
edIn | -11.395 |
icter | -10.068 |
icians | -10.063 |
itect | -9.848 |
acters | -9.322 |
Token | J |
Token ID | 41 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
berman | +3.467 |
HAEL | +3.176 |
Gamble | +3.170 |
Heck | +3.129 |
tti | +3.126 |
Neg logit contributions | |
edIn | -9.618 |
itect | -8.582 |
ifiers | -8.498 |
icians | -8.449 |
ification | -8.367 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
edIn | +1.205 |
icians | +1.079 |
ification | +1.075 |
itect | +1.072 |
ified | +1.070 |
Neg logit contributions | |
berman | -0.663 |
HAEL | -0.632 |
tti | -0.632 |
tails | -0.607 |
mma | -0.590 |
Token | Simpson |
Token ID | 20531 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
berman | +4.691 |
Gamble | +4.464 |
Heck | +4.452 |
tti | +4.404 |
HAEL | +4.399 |
Neg logit contributions | |
edIn | -5.317 |
icians | -4.557 |
ifiers | -4.501 |
itect | -4.472 |
ification | -4.454 |
Token | : |
Token ID | 25 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
edIn | +3.466 |
ification | +3.073 |
ified | +3.059 |
icians | +3.037 |
itect | +3.014 |
Neg logit contributions | |
berman | -2.516 |
HAEL | -2.414 |
tti | -2.396 |
tails | -2.332 |
mma | -2.257 |
Token | ard |
Token ID | 446 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
edIn | +1.168 |
ification | +1.017 |
icians | +1.014 |
itect | +1.012 |
ified | +1.011 |
Neg logit contributions | |
berman | -1.147 |
HAEL | -1.111 |
tti | -1.101 |
tails | -1.081 |
mma | -1.060 |
Token | took |
Token ID | 1718 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
edIn | +1.214 |
icians | +1.084 |
ification | +1.082 |
itect | +1.078 |
ified | +1.076 |
Neg logit contributions | |
berman | -0.623 |
tti | -0.593 |
HAEL | -0.592 |
tails | -0.571 |
Heck | -0.558 |
Token | the |
Token ID | 262 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
berman | +1.138 |
tti | +1.104 |
HAEL | +1.079 |
Heck | +1.061 |
Gamble | +1.050 |
Neg logit contributions | |
edIn | -2.114 |
icians | -1.890 |
itect | -1.880 |
ification | -1.855 |
ified | -1.847 |
Token | reins |
Token ID | 35627 |
Feature activation | +4.19e-03 |
Pos logit contributions | |
berman | +1.006 |
tti | +0.972 |
HAEL | +0.954 |
Heck | +0.935 |
Gamble | +0.928 |
Neg logit contributions | |
edIn | -1.681 |
icians | -1.490 |
itect | -1.478 |
ification | -1.469 |
ified | -1.465 |
Token | of |
Token ID | 286 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
berman | +0.009 |
tti | +0.009 |
HAEL | +0.009 |
tails | +0.008 |
Heck | +0.008 |
Neg logit contributions | |
edIn | -0.017 |
icians | -0.015 |
ification | -0.015 |
itect | -0.015 |
ified | -0.015 |
Token | O |
Token ID | 440 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
berman | +0.999 |
tti | +0.967 |
HAEL | +0.954 |
Heck | +0.933 |
Gamble | +0.928 |
Neg logit contributions | |
edIn | -1.500 |
icians | -1.327 |
itect | -1.305 |
ification | -1.304 |
ified | -1.299 |
Token | CL |
Token ID | 5097 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
tti | +10.132 |
berman | +10.114 |
DI | +9.794 |
train | +9.576 |
HO | +9.387 |
Neg logit contributions | |
edIn | -10.814 |
icter | -9.534 |
icians | -9.305 |
itect | -9.062 |
ification | -8.858 |
Token | C |
Token ID | 34 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
berman | +0.878 |
HAEL | +0.844 |
tti | +0.843 |
tails | +0.813 |
Heck | +0.799 |
Neg logit contributions | |
edIn | -1.626 |
icians | -1.447 |
ification | -1.433 |
itect | -1.428 |
ified | -1.425 |
Token | as |
Token ID | 355 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
berman | +0.626 |
HAEL | +0.605 |
tti | +0.602 |
tails | +0.579 |
Heck | +0.571 |
Neg logit contributions | |
edIn | -1.136 |
icians | -1.014 |
ification | -1.002 |
ified | -0.998 |
itect | -0.996 |
Token | its |
Token ID | 663 |
Feature activation | +9.46e-03 |
Pos logit contributions | |
edIn | +1.097 |
icians | +0.960 |
ification | +0.957 |
itect | +0.953 |
ified | +0.951 |
Neg logit contributions | |
berman | -0.850 |
tti | -0.817 |
HAEL | -0.817 |
tails | -0.794 |
Heck | -0.781 |
Token | new |
Token ID | 649 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
berman | +0.025 |
tti | +0.024 |
HAEL | +0.024 |
tails | +0.024 |
Heck | +0.023 |
Neg logit contributions | |
edIn | -0.034 |
icians | -0.030 |
ification | -0.030 |
itect | -0.030 |
ified | -0.030 |
Token | Gu |
Token ID | 1962 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
berman | +0.899 |
tti | +0.887 |
HAEL | +0.857 |
Heck | +0.851 |
Gamble | +0.838 |
Neg logit contributions | |
edIn | -1.590 |
icians | -1.415 |
ification | -1.397 |
itect | -1.396 |
ified | -1.389 |
Token | ib |
Token ID | 571 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
berman | +0.966 |
tti | +0.930 |
HAEL | +0.902 |
tails | +0.895 |
mma | +0.883 |
Neg logit contributions | |
edIn | -0.991 |
icians | -0.838 |
itect | -0.832 |
ification | -0.831 |
ified | -0.826 |
Token | bert |
Token ID | 4835 |
Feature activation | -1.45e-03 |
Pos logit contributions | |
edIn | +0.801 |
icians | +0.691 |
ification | +0.690 |
itect | +0.686 |
ified | +0.685 |
Neg logit contributions | |
berman | -0.768 |
HAEL | -0.742 |
tti | -0.742 |
tails | -0.724 |
Heck | -0.713 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
edIn | +0.006 |
icians | +0.005 |
ification | +0.005 |
itect | +0.005 |
ified | +0.005 |
Neg logit contributions | |
berman | -0.004 |
tti | -0.003 |
HAEL | -0.003 |
tails | -0.003 |
Heck | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
edIn | +0.037 |
icians | +0.032 |
itect | +0.032 |
ification | +0.032 |
ified | +0.032 |
Neg logit contributions | |
berman | -0.029 |
tti | -0.028 |
HAEL | -0.028 |
tails | -0.027 |
Heck | -0.027 |
Token | O |
Token ID | 440 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
edIn | +3.785 |
ification | +3.367 |
icians | +3.348 |
ified | +3.337 |
itect | +3.300 |
Neg logit contributions | |
berman | -2.540 |
HAEL | -2.408 |
tti | -2.390 |
tails | -2.339 |
mma | -2.276 |
Token | rec |
Token ID | 8344 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
tti | +9.672 |
berman | +9.470 |
DI | +9.359 |
HAEL | +8.943 |
tails | +8.900 |
Neg logit contributions | |
edIn | -11.625 |
icter | -10.046 |
itect | -9.844 |
icians | -9.738 |
ificant | -9.700 |
Token | as |
Token ID | 292 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
edIn | +0.612 |
icians | +0.541 |
ification | +0.536 |
itect | +0.535 |
ified | +0.534 |
Neg logit contributions | |
berman | -0.393 |
tti | -0.377 |
HAEL | -0.375 |
tails | -0.364 |
Heck | -0.358 |
Token | filling |
Token ID | 12591 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
edIn | +3.018 |
icians | +2.678 |
ification | +2.675 |
itect | +2.658 |
ified | +2.656 |
Neg logit contributions | |
berman | -2.064 |
HAEL | -1.976 |
tti | -1.949 |
tails | -1.912 |
mma | -1.863 |
Token | the |
Token ID | 262 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
berman | +2.290 |
tti | +2.193 |
Heck | +2.155 |
HAEL | +2.148 |
tails | +2.126 |
Neg logit contributions | |
edIn | -4.058 |
itect | -3.688 |
icians | -3.665 |
ification | -3.616 |
ified | -3.594 |
Token | top |
Token ID | 1353 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
berman | +0.092 |
HAEL | +0.089 |
tti | +0.089 |
tails | +0.086 |
Heck | +0.085 |
Neg logit contributions | |
edIn | -0.119 |
icians | -0.105 |
ification | -0.104 |
itect | -0.104 |
ified | -0.104 |
Token | lens |
Token ID | 10317 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
berman | +2.075 |
tti | +1.995 |
HAEL | +1.970 |
Heck | +1.912 |
mma | +1.895 |
Neg logit contributions | |
edIn | -3.203 |
icians | -2.830 |
ification | -2.809 |
itect | -2.807 |
ified | -2.804 |
Token | , |
Token ID | 11 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
berman | +0.924 |
tti | +0.885 |
HAEL | +0.879 |
tails | +0.851 |
Heck | +0.841 |
Neg logit contributions | |
edIn | -1.627 |
icians | -1.447 |
ification | -1.437 |
itect | -1.431 |
ified | -1.430 |
Token | put |
Token ID | 1234 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
edIn | +2.894 |
ification | +2.551 |
ified | +2.537 |
icians | +2.534 |
itect | +2.512 |
Neg logit contributions | |
berman | -2.364 |
HAEL | -2.281 |
tti | -2.252 |
tails | -2.215 |
mma | -2.151 |
Token | it |
Token ID | 340 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
edIn | +0.769 |
icians | +0.676 |
ification | +0.675 |
ified | +0.671 |
itect | +0.671 |
Neg logit contributions | |
berman | -0.562 |
HAEL | -0.540 |
tti | -0.539 |
tails | -0.524 |
Heck | -0.514 |
Token | on |
Token ID | 319 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
berman | +0.961 |
tti | +0.918 |
HAEL | +0.903 |
tails | +0.885 |
Heck | +0.862 |
Neg logit contributions | |
edIn | -1.907 |
icians | -1.702 |
itect | -1.689 |
ification | -1.688 |
ified | -1.676 |
Token | OL |
Token ID | 22258 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
berman | +1.697 |
tti | +1.648 |
HAEL | +1.618 |
Heck | +1.580 |
tails | +1.575 |
Neg logit contributions | |
edIn | -2.506 |
icians | -2.204 |
itect | -2.191 |
ification | -2.184 |
ified | -2.176 |
Token | AF |
Token ID | 8579 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
tti | +8.720 |
berman | +8.628 |
DI | +8.531 |
HO | +8.166 |
HAEL | +8.126 |
Neg logit contributions | |
edIn | -12.350 |
icians | -10.877 |
itect | -10.788 |
icipated | -10.656 |
acters | -10.397 |
Token | , |
Token ID | 11 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
berman | +0.170 |
tti | +0.163 |
HAEL | +0.162 |
tails | +0.158 |
Heck | +0.155 |
Neg logit contributions | |
edIn | -0.260 |
icians | -0.230 |
ification | -0.229 |
itect | -0.228 |
ified | -0.228 |
Token | and |
Token ID | 290 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
berman | +1.242 |
tti | +1.215 |
HAEL | +1.194 |
Heck | +1.166 |
tails | +1.161 |
Neg logit contributions | |
edIn | -1.537 |
icians | -1.343 |
itect | -1.329 |
ification | -1.318 |
ified | -1.304 |
Token | took |
Token ID | 1718 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
berman | +2.583 |
tti | +2.530 |
HAEL | +2.473 |
Heck | +2.436 |
tails | +2.405 |
Neg logit contributions | |
edIn | -3.159 |
icians | -2.763 |
itect | -2.742 |
ification | -2.707 |
ified | -2.679 |
Token | images |
Token ID | 4263 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
berman | +1.496 |
tti | +1.441 |
HAEL | +1.435 |
tails | +1.394 |
Heck | +1.388 |
Neg logit contributions | |
edIn | -2.018 |
icians | -1.767 |
itect | -1.757 |
ification | -1.752 |
ified | -1.743 |
Token | in |
Token ID | 259 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
edIn | +3.951 |
ification | +3.424 |
ified | +3.390 |
itect | +3.372 |
icians | +3.367 |
Neg logit contributions | |
berman | -4.379 |
HAEL | -4.328 |
tti | -4.211 |
tails | -4.185 |
Heck | -4.160 |
Token | ik |
Token ID | 1134 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
edIn | +3.272 |
icians | +2.857 |
ification | +2.849 |
itect | +2.845 |
ified | +2.831 |
Neg logit contributions | |
berman | -3.199 |
HAEL | -3.117 |
tti | -3.085 |
tails | -3.029 |
Gamble | -2.987 |
Token | ain |
Token ID | 391 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
edIn | +3.339 |
ification | +2.944 |
icians | +2.941 |
itect | +2.931 |
ified | +2.927 |
Neg logit contributions | |
berman | -2.524 |
tti | -2.434 |
HAEL | -2.429 |
tails | -2.366 |
Heck | -2.334 |
Token | en |
Token ID | 268 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
edIn | +3.367 |
ification | +2.911 |
icians | +2.908 |
itect | +2.895 |
ified | +2.895 |
Neg logit contributions | |
berman | -3.268 |
HAEL | -3.179 |
tti | -3.147 |
tails | -3.090 |
Heck | -3.054 |
Token | @ |
Token ID | 2488 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
edIn | +2.262 |
icians | +1.959 |
ification | +1.959 |
itect | +1.948 |
ified | +1.946 |
Neg logit contributions | |
berman | -2.067 |
HAEL | -1.993 |
tti | -1.990 |
tails | -1.942 |
Heck | -1.912 |
Token | il |
Token ID | 4229 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
berman | +3.753 |
tti | +3.688 |
HAEL | +3.613 |
tails | +3.571 |
HO | +3.520 |
Neg logit contributions | |
edIn | -5.222 |
icians | -4.580 |
itect | -4.514 |
ification | -4.498 |
ifiers | -4.492 |
Token | media |
Token ID | 11431 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
tti | +10.606 |
berman | +10.584 |
mma | +9.969 |
tails | +9.901 |
mouth | +9.668 |
Neg logit contributions | |
edIn | -10.609 |
icians | -8.319 |
acters | -8.283 |
ified | -8.190 |
ifiers | -8.162 |
Token | . |
Token ID | 13 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
berman | +3.768 |
tti | +3.692 |
HAEL | +3.625 |
tails | +3.513 |
train | +3.436 |
Neg logit contributions | |
edIn | -4.825 |
icians | -4.187 |
itect | -4.133 |
ification | -4.113 |
ified | -4.093 |
Token | fi |
Token ID | 12463 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
berman | +2.322 |
tti | +2.269 |
HAEL | +2.209 |
tails | +2.182 |
mma | +2.148 |
Neg logit contributions | |
edIn | -2.601 |
icians | -2.240 |
ification | -2.219 |
itect | -2.213 |
ified | -2.198 |
Token | Translation |
Token ID | 48313 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
berman | +1.946 |
HAEL | +1.887 |
tti | +1.886 |
tails | +1.810 |
Heck | +1.795 |
Neg logit contributions | |
edIn | -2.721 |
icians | -2.400 |
itect | -2.371 |
ification | -2.360 |
ified | -2.356 |
Token | to |
Token ID | 284 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
edIn | +3.783 |
ification | +3.381 |
icians | +3.365 |
ified | +3.361 |
itect | +3.338 |
Neg logit contributions | |
berman | -2.374 |
tti | -2.262 |
HAEL | -2.261 |
tails | -2.210 |
mma | -2.148 |
Token | a |
Token ID | 257 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
edIn | +2.684 |
ification | +2.357 |
icians | +2.355 |
ified | +2.338 |
itect | +2.331 |
Neg logit contributions | |
berman | -2.092 |
HAEL | -2.010 |
tti | -2.001 |
tails | -1.952 |
mma | -1.907 |
Token | diplomatic |
Token ID | 13093 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
edIn | +0.596 |
icians | +0.515 |
itect | +0.513 |
ification | +0.509 |
ified | +0.506 |
Neg logit contributions | |
berman | -0.479 |
tti | -0.462 |
HAEL | -0.457 |
tails | -0.448 |
Heck | -0.446 |
Token | courtesy |
Token ID | 12537 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
edIn | +0.883 |
icians | +0.777 |
ification | +0.772 |
itect | +0.771 |
ified | +0.767 |
Neg logit contributions | |
berman | -0.616 |
tti | -0.591 |
HAEL | -0.588 |
tails | -0.572 |
Heck | -0.565 |
Token | Cuba |
Token ID | 14159 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
berman | +0.743 |
tti | +0.715 |
HAEL | +0.713 |
tails | +0.683 |
Heck | +0.681 |
Neg logit contributions | |
edIn | -1.283 |
icians | -1.132 |
itect | -1.131 |
ification | -1.125 |
ified | -1.121 |
Token | invited |
Token ID | 9392 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
edIn | +2.043 |
icians | +1.779 |
ification | +1.775 |
itect | +1.764 |
ified | +1.762 |
Neg logit contributions | |
berman | -1.758 |
HAEL | -1.694 |
tti | -1.692 |
tails | -1.649 |
Heck | -1.622 |
Token | O |
Token ID | 440 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
berman | +0.630 |
tti | +0.607 |
HAEL | +0.604 |
tails | +0.588 |
Heck | +0.582 |
Neg logit contributions | |
edIn | -0.875 |
icians | -0.767 |
itect | -0.765 |
ification | -0.764 |
ified | -0.759 |
Token | AS |
Token ID | 1921 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
berman | +4.781 |
DI | +4.557 |
HO | +4.390 |
tti | +4.301 |
HAEL | +4.251 |
Neg logit contributions | |
edIn | -16.733 |
icter | -15.240 |
icians | -14.598 |
itect | -14.593 |
ification | -14.385 |
Token | Secretary |
Token ID | 4986 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
berman | +1.097 |
tti | +1.062 |
HAEL | +1.054 |
tails | +1.023 |
Heck | +1.019 |
Neg logit contributions | |
edIn | -1.398 |
icians | -1.198 |
itect | -1.197 |
ification | -1.196 |
ified | -1.196 |
Token | General |
Token ID | 3611 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
berman | +0.444 |
tti | +0.424 |
HAEL | +0.422 |
tails | +0.406 |
Heck | +0.401 |
Neg logit contributions | |
edIn | -0.905 |
icians | -0.808 |
ification | -0.805 |
itect | -0.803 |
ified | -0.800 |
Token | Jose |
Token ID | 5264 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
berman | +2.237 |
tti | +2.177 |
HAEL | +2.156 |
Heck | +2.113 |
tails | +2.084 |
Neg logit contributions | |
edIn | -3.929 |
icians | -3.426 |
itect | -3.423 |
ification | -3.388 |
ified | -3.362 |
Token | Miguel |
Token ID | 29825 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
berman | +1.613 |
tti | +1.561 |
HAEL | +1.498 |
Heck | +1.479 |
Gamble | +1.474 |
Neg logit contributions | |
edIn | -2.877 |
icians | -2.532 |
itect | -2.517 |
ification | -2.512 |
ified | -2.494 |
Token | ( |
Token ID | 357 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
berman | +0.833 |
tti | +0.805 |
HAEL | +0.796 |
tails | +0.774 |
Heck | +0.760 |
Neg logit contributions | |
edIn | -1.495 |
icians | -1.330 |
ification | -1.324 |
itect | -1.318 |
ified | -1.315 |
Token | June |
Token ID | 15749 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
berman | +0.582 |
tti | +0.563 |
HAEL | +0.561 |
tails | +0.551 |
mma | +0.538 |
Neg logit contributions | |
edIn | -0.636 |
icians | -0.550 |
itect | -0.545 |
ification | -0.544 |
ified | -0.540 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
edIn | +1.857 |
icians | +1.566 |
ification | +1.565 |
itect | +1.553 |
ified | +1.552 |
Neg logit contributions | |
berman | -2.312 |
HAEL | -2.244 |
tti | -2.241 |
tails | -2.193 |
Heck | -2.162 |
Token | ), |
Token ID | 828 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
berman | +1.646 |
tti | +1.586 |
HAEL | +1.573 |
tails | +1.535 |
mma | +1.521 |
Neg logit contributions | |
edIn | -2.124 |
icians | -1.840 |
ification | -1.824 |
itect | -1.814 |
ified | -1.811 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
berman | +0.082 |
tti | +0.079 |
HAEL | +0.078 |
tails | +0.076 |
Heck | +0.075 |
Neg logit contributions | |
edIn | -0.132 |
icians | -0.116 |
ification | -0.116 |
itect | -0.115 |
ified | -0.115 |
Token | O |
Token ID | 440 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
berman | +3.032 |
tti | +2.961 |
Heck | +2.907 |
HAEL | +2.874 |
Gamble | +2.869 |
Neg logit contributions | |
edIn | -4.955 |
icians | -4.383 |
ification | -4.331 |
itect | -4.328 |
ified | -4.288 |
Token | CL |
Token ID | 5097 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
berman | +9.626 |
tti | +9.571 |
DI | +9.475 |
train | +9.161 |
HO | +9.098 |
Neg logit contributions | |
edIn | -10.630 |
icter | -9.382 |
icians | -9.260 |
itect | -9.134 |
ified | -8.965 |
Token | C |
Token ID | 34 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
edIn | +1.822 |
icians | +1.645 |
ification | +1.643 |
itect | +1.636 |
ified | +1.635 |
Neg logit contributions | |
berman | -0.724 |
tti | -0.681 |
HAEL | -0.680 |
tails | -0.651 |
Heck | -0.632 |
Token | ( |
Token ID | 357 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
edIn | +1.405 |
icians | +1.249 |
ification | +1.247 |
itect | +1.242 |
ified | +1.240 |
Neg logit contributions | |
berman | -0.810 |
tti | -0.772 |
HAEL | -0.772 |
tails | -0.747 |
Heck | -0.731 |
Token | June |
Token ID | 15749 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
berman | +1.530 |
tti | +1.479 |
HAEL | +1.465 |
tails | +1.451 |
train | +1.420 |
Neg logit contributions | |
edIn | -1.767 |
icians | -1.537 |
itect | -1.519 |
ification | -1.509 |
ified | -1.497 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
edIn | +1.679 |
icians | +1.417 |
ification | +1.412 |
itect | +1.403 |
ified | +1.400 |
Neg logit contributions | |
berman | -2.039 |
tti | -1.977 |
HAEL | -1.975 |
tails | -1.933 |
Heck | -1.907 |
Token | apologized |
Token ID | 22893 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
edIn | +0.758 |
icians | +0.659 |
ification | +0.657 |
itect | +0.654 |
ified | +0.653 |
Neg logit contributions | |
berman | -0.640 |
tti | -0.617 |
HAEL | -0.616 |
tails | -0.600 |
Heck | -0.590 |
Token | to |
Token ID | 284 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
edIn | +0.562 |
ification | +0.506 |
ified | +0.504 |
icians | +0.503 |
itect | +0.500 |
Neg logit contributions | |
berman | -0.334 |
HAEL | -0.318 |
tti | -0.316 |
tails | -0.310 |
mma | -0.298 |
Token | [ |
Token ID | 685 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
berman | +0.751 |
HAEL | +0.723 |
tti | +0.720 |
tails | +0.695 |
Heck | +0.692 |
Neg logit contributions | |
edIn | -1.111 |
icians | -0.978 |
ification | -0.972 |
itect | -0.972 |
ified | -0.966 |
Token | Love |
Token ID | 18565 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
berman | +4.415 |
train | +4.259 |
HO | +4.223 |
mouth | +4.209 |
HAEL | +4.198 |
Neg logit contributions | |
edIn | -8.666 |
icter | -7.755 |
itect | -7.729 |
icians | -7.670 |
osate | -7.541 |
Token | ]," |
Token ID | 17241 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
berman | +2.931 |
tti | +2.865 |
HAEL | +2.836 |
Heck | +2.734 |
tails | +2.727 |
Neg logit contributions | |
edIn | -3.092 |
icians | -2.616 |
itect | -2.607 |
ification | -2.574 |
ified | -2.541 |
Token | O |
Token ID | 440 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
edIn | +0.300 |
icians | +0.268 |
ification | +0.265 |
itect | +0.265 |
ified | +0.263 |
Neg logit contributions | |
berman | -0.157 |
HAEL | -0.150 |
tti | -0.149 |
Heck | -0.144 |
tails | -0.143 |
Token | ly |
Token ID | 306 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
berman | +10.555 |
tti | +10.285 |
train | +9.992 |
tails | +9.663 |
HO | +9.562 |
Neg logit contributions | |
edIn | -10.476 |
icter | -9.622 |
osate | -8.910 |
itect | -8.682 |
icians | -8.671 |
Token | ny |
Token ID | 3281 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
berman | +4.648 |
tti | +4.528 |
HAEL | +4.347 |
mma | +4.346 |
tails | +4.345 |
Neg logit contributions | |
edIn | -4.455 |
icians | -3.693 |
itect | -3.675 |
icter | -3.637 |
ification | -3.591 |
Token | k |
Token ID | 74 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
edIn | +1.023 |
ification | +0.919 |
icians | +0.914 |
ified | +0.914 |
itect | +0.905 |
Neg logit contributions | |
berman | -0.777 |
HAEL | -0.773 |
tti | -0.739 |
tails | -0.736 |
Gamble | -0.728 |
Token | said |
Token ID | 531 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
edIn | +1.676 |
icians | +1.460 |
ification | +1.460 |
ified | +1.453 |
itect | +1.449 |
Neg logit contributions | |
berman | -1.423 |
HAEL | -1.374 |
tti | -1.372 |
tails | -1.339 |
Heck | -1.311 |
Token | . |
Token ID | 13 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
berman | +1.000 |
tti | +0.949 |
HAEL | +0.937 |
Heck | +0.897 |
tails | +0.894 |
Neg logit contributions | |
edIn | -2.114 |
icians | -1.890 |
itect | -1.884 |
ification | -1.873 |
ified | -1.859 |
Token | . |
Token ID | 13 |
Feature activation | +8.64e-02 |
Pos logit contributions | |
edIn | +1.148 |
ification | +1.027 |
icians | +1.026 |
ified | +1.021 |
itect | +1.019 |
Neg logit contributions | |
berman | -0.681 |
HAEL | -0.646 |
tti | -0.640 |
tails | -0.624 |
mma | -0.609 |
Token | Earlier |
Token ID | 20635 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
berman | +0.219 |
tti | +0.212 |
HAEL | +0.211 |
tails | +0.205 |
Heck | +0.203 |
Neg logit contributions | |
edIn | -0.324 |
icians | -0.285 |
ification | -0.284 |
itect | -0.283 |
ified | -0.283 |
Token | this |
Token ID | 428 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
berman | +0.131 |
tti | +0.125 |
HAEL | +0.125 |
tails | +0.121 |
Heck | +0.119 |
Neg logit contributions | |
edIn | -0.211 |
icians | -0.187 |
ification | -0.186 |
itect | -0.186 |
ified | -0.185 |
Token | month |
Token ID | 1227 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
berman | +0.414 |
tti | +0.399 |
HAEL | +0.398 |
tails | +0.385 |
Heck | +0.380 |
Neg logit contributions | |
edIn | -0.646 |
icians | -0.571 |
ification | -0.568 |
itect | -0.567 |
ified | -0.565 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
berman | +0.726 |
tti | +0.696 |
HAEL | +0.689 |
tails | +0.661 |
Heck | +0.650 |
Neg logit contributions | |
edIn | -1.665 |
icians | -1.490 |
ification | -1.488 |
itect | -1.484 |
ified | -1.480 |
Token | O |
Token ID | 440 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
edIn | +0.424 |
icians | +0.374 |
ification | +0.373 |
itect | +0.371 |
ified | +0.371 |
Neg logit contributions | |
berman | -0.297 |
HAEL | -0.285 |
tti | -0.284 |
tails | -0.276 |
Heck | -0.271 |
Token | la |
Token ID | 5031 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
DI | +9.739 |
berman | +9.726 |
tti | +9.638 |
HO | +9.240 |
train | +9.165 |
Neg logit contributions | |
edIn | -10.785 |
icter | -9.270 |
icians | -9.195 |
acters | -9.050 |
itect | -9.038 |
Token | , |
Token ID | 11 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
berman | +4.204 |
tti | +4.151 |
HAEL | +4.046 |
Gamble | +3.982 |
Heck | +3.940 |
Neg logit contributions | |
edIn | -6.460 |
icians | -5.628 |
ification | -5.616 |
itect | -5.561 |
ified | -5.540 |
Token | a |
Token ID | 257 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
berman | +2.137 |
tti | +2.088 |
HAEL | +2.072 |
Heck | +2.017 |
tails | +2.004 |
Neg logit contributions | |
edIn | -3.045 |
icians | -2.656 |
ification | -2.637 |
itect | -2.635 |
ified | -2.615 |
Token | local |
Token ID | 1957 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
berman | +1.390 |
tti | +1.351 |
HAEL | +1.328 |
Heck | +1.295 |
tails | +1.291 |
Neg logit contributions | |
edIn | -2.197 |
icians | -1.922 |
itect | -1.915 |
ification | -1.912 |
ified | -1.896 |
Token | taxi |
Token ID | 17536 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
berman | +0.124 |
tti | +0.119 |
HAEL | +0.119 |
tails | +0.115 |
Heck | +0.113 |
Neg logit contributions | |
edIn | -0.198 |
icians | -0.175 |
ification | -0.175 |
itect | -0.174 |
ified | -0.174 |
Token | they |
Token ID | 484 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
berman | +2.876 |
tti | +2.777 |
HAEL | +2.775 |
Heck | +2.721 |
Gamble | +2.654 |
Neg logit contributions | |
edIn | -4.039 |
itect | -3.561 |
ification | -3.505 |
icians | -3.504 |
ified | -3.463 |
Token | first |
Token ID | 717 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
berman | +0.570 |
tti | +0.552 |
HAEL | +0.542 |
tails | +0.532 |
Heck | +0.528 |
Neg logit contributions | |
edIn | -0.642 |
icians | -0.545 |
itect | -0.543 |
ification | -0.542 |
ified | -0.537 |
Token | met |
Token ID | 1138 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
edIn | +1.448 |
icians | +1.259 |
ification | +1.257 |
itect | +1.249 |
ified | +1.249 |
Neg logit contributions | |
berman | -1.276 |
HAEL | -1.231 |
tti | -1.229 |
tails | -1.199 |
Heck | -1.179 |
Token | , |
Token ID | 11 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
berman | +1.764 |
tti | +1.681 |
HAEL | +1.672 |
Heck | +1.607 |
tails | +1.606 |
Neg logit contributions | |
edIn | -3.638 |
itect | -3.269 |
icians | -3.249 |
ification | -3.237 |
ified | -3.205 |
Token | and |
Token ID | 290 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
edIn | +1.242 |
icians | +1.097 |
ification | +1.095 |
ified | +1.089 |
itect | +1.084 |
Neg logit contributions | |
berman | -0.874 |
HAEL | -0.838 |
tti | -0.838 |
tails | -0.817 |
mma | -0.796 |
Token | O |
Token ID | 440 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
edIn | +1.731 |
icians | +1.531 |
ification | +1.528 |
ified | +1.521 |
itect | +1.511 |
Neg logit contributions | |
berman | -1.204 |
HAEL | -1.156 |
tti | -1.153 |
tails | -1.127 |
mma | -1.101 |
Token | ' |
Token ID | 6 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
berman | +9.205 |
tti | +8.899 |
HAEL | +8.431 |
HO | +8.419 |
DI | +8.228 |
Neg logit contributions | |
edIn | -12.008 |
icter | -10.614 |
icians | -10.087 |
itect | -10.023 |
acters | -9.927 |
Token | Neill |
Token ID | 26538 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
berman | +2.944 |
HAEL | +2.831 |
tti | +2.642 |
HO | +2.565 |
Gamble | +2.442 |
Neg logit contributions | |
edIn | -9.097 |
icter | -8.285 |
itect | -8.099 |
icians | -8.082 |
icipated | -8.020 |
Token | attempted |
Token ID | 7482 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
edIn | +1.724 |
ification | +1.518 |
icians | +1.514 |
ified | +1.507 |
itect | +1.498 |
Neg logit contributions | |
berman | -1.422 |
HAEL | -1.373 |
tti | -1.364 |
tails | -1.333 |
mma | -1.305 |
Token | to |
Token ID | 284 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
berman | +3.197 |
tti | +3.028 |
HAEL | +2.986 |
Heck | +2.888 |
tails | +2.842 |
Neg logit contributions | |
edIn | -7.025 |
itect | -6.434 |
icians | -6.369 |
ification | -6.216 |
ifiers | -6.209 |
Token | advise |
Token ID | 18595 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
berman | +1.561 |
tti | +1.497 |
HAEL | +1.473 |
tails | +1.446 |
Heck | +1.437 |
Neg logit contributions | |
edIn | -2.078 |
icians | -1.812 |
itect | -1.798 |
ification | -1.792 |
ified | -1.779 |
Token | half |
Token ID | 2063 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
berman | +1.344 |
tti | +1.290 |
HAEL | +1.285 |
tails | +1.243 |
Heck | +1.242 |
Neg logit contributions | |
edIn | -1.883 |
itect | -1.635 |
icians | -1.629 |
ification | -1.609 |
ified | -1.597 |
Token | right |
Token ID | 826 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
berman | +0.990 |
tti | +0.952 |
HAEL | +0.942 |
Heck | +0.915 |
tails | +0.913 |
Neg logit contributions | |
edIn | -1.407 |
itect | -1.223 |
icians | -1.215 |
ification | -1.200 |
ified | -1.187 |
Token | ; |
Token ID | 26 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
berman | +2.065 |
tti | +1.937 |
HAEL | +1.912 |
tails | +1.836 |
Gamble | +1.826 |
Neg logit contributions | |
edIn | -4.544 |
itect | -4.036 |
icians | -4.026 |
ification | -3.941 |
ified | -3.919 |
Token | none |
Token ID | 4844 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
berman | +0.858 |
tti | +0.826 |
HAEL | +0.820 |
tails | +0.795 |
Heck | +0.793 |
Neg logit contributions | |
edIn | -1.165 |
icians | -1.013 |
itect | -1.011 |
ification | -1.005 |
ified | -1.000 |
Token | of |
Token ID | 286 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
edIn | +0.557 |
icians | +0.496 |
ification | +0.494 |
itect | +0.493 |
ified | +0.492 |
Neg logit contributions | |
berman | -0.294 |
tti | -0.279 |
HAEL | -0.278 |
tails | -0.268 |
Heck | -0.263 |
Token | O |
Token ID | 440 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
berman | +2.342 |
HAEL | +2.214 |
tti | +2.201 |
Heck | +2.186 |
Gamble | +2.166 |
Neg logit contributions | |
edIn | -3.708 |
itect | -3.277 |
icians | -3.237 |
ification | -3.208 |
ified | -3.187 |
Token | ' |
Token ID | 6 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
berman | +9.197 |
tti | +8.762 |
train | +8.303 |
DI | +8.236 |
HAEL | +8.229 |
Neg logit contributions | |
edIn | -11.818 |
icter | -10.464 |
icians | -10.134 |
itect | -10.052 |
acters | -9.706 |
Token | Brian |
Token ID | 24761 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
berman | +4.013 |
HAEL | +3.785 |
tti | +3.699 |
tails | +3.660 |
HO | +3.584 |
Neg logit contributions | |
edIn | -6.484 |
icians | -5.648 |
itect | -5.634 |
icter | -5.596 |
icipated | -5.514 |
Token | 's |
Token ID | 338 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
edIn | +1.606 |
icians | +1.388 |
ification | +1.384 |
itect | +1.378 |
ified | +1.374 |
Neg logit contributions | |
berman | -1.471 |
tti | -1.419 |
HAEL | -1.418 |
tails | -1.383 |
Heck | -1.362 |
Token | work |
Token ID | 670 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
berman | +0.625 |
tti | +0.603 |
HAEL | +0.599 |
tails | +0.585 |
Heck | +0.580 |
Neg logit contributions | |
edIn | -0.846 |
icians | -0.739 |
itect | -0.738 |
ification | -0.737 |
ified | -0.731 |
Token | was |
Token ID | 373 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
berman | +2.553 |
tti | +2.473 |
HAEL | +2.445 |
tails | +2.418 |
Heck | +2.387 |
Neg logit contributions | |
edIn | -3.448 |
itect | -2.952 |
icians | -2.947 |
ification | -2.887 |
ified | -2.862 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
edIn | +2.394 |
ification | +2.119 |
icians | +2.103 |
ified | +2.099 |
itect | +2.092 |
Neg logit contributions | |
berman | -1.571 |
HAEL | -1.515 |
tti | -1.494 |
tails | -1.450 |
mma | -1.429 |
Token | on |
Token ID | 319 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
berman | +0.385 |
tti | +0.373 |
HAEL | +0.371 |
tails | +0.363 |
Heck | +0.359 |
Neg logit contributions | |
edIn | -0.443 |
icians | -0.385 |
itect | -0.382 |
ification | -0.381 |
ified | -0.379 |
Token | a |
Token ID | 257 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
berman | +0.458 |
tti | +0.444 |
HAEL | +0.438 |
tails | +0.430 |
Heck | +0.424 |
Neg logit contributions | |
edIn | -0.598 |
icians | -0.526 |
itect | -0.523 |
ification | -0.521 |
ified | -0.518 |
Token | mission |
Token ID | 4365 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
berman | +0.230 |
tti | +0.220 |
HAEL | +0.220 |
tails | +0.213 |
Heck | +0.209 |
Neg logit contributions | |
edIn | -0.386 |
icians | -0.343 |
ification | -0.342 |
itect | -0.341 |
ified | -0.340 |
Token | designated |
Token ID | 11032 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
berman | +1.096 |
tti | +1.055 |
HAEL | +1.030 |
tails | +1.006 |
Heck | +0.988 |
Neg logit contributions | |
edIn | -2.105 |
icians | -1.887 |
itect | -1.878 |
ification | -1.853 |
ified | -1.850 |
Token | O |
Token ID | 440 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
edIn | +5.181 |
ification | +4.676 |
ified | +4.646 |
itect | +4.527 |
ifiers | +4.508 |
Neg logit contributions | |
berman | -3.158 |
HAEL | -3.078 |
tails | -2.941 |
tti | -2.933 |
mma | -2.804 |
Token | A |
Token ID | 32 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
berman | +8.060 |
DI | +7.669 |
tti | +7.622 |
HAEL | +7.556 |
HO | +7.491 |
Neg logit contributions | |
edIn | -12.300 |
icians | -11.212 |
icter | -11.086 |
itect | -11.004 |
ified | -10.610 |
Token | - |
Token ID | 12 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
berman | +2.060 |
HAEL | +1.995 |
tti | +1.971 |
tails | +1.911 |
HO | +1.900 |
Neg logit contributions | |
edIn | -3.255 |
icians | -2.914 |
ification | -2.885 |
ified | -2.854 |
itect | -2.852 |
Token | 7 |
Token ID | 22 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
berman | +1.126 |
HAEL | +1.085 |
tti | +1.085 |
tails | +1.047 |
HO | +1.020 |
Neg logit contributions | |
edIn | -2.157 |
icians | -1.943 |
itect | -1.923 |
ification | -1.921 |
ified | -1.908 |
Token | , |
Token ID | 11 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
berman | +0.542 |
tti | +0.517 |
HAEL | +0.516 |
tails | +0.496 |
Heck | +0.485 |
Neg logit contributions | |
edIn | -1.090 |
icians | -0.978 |
ification | -0.972 |
itect | -0.969 |
ified | -0.967 |
Token | was |
Token ID | 373 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
berman | +1.980 |
tti | +1.930 |
HAEL | +1.885 |
tails | +1.878 |
Heck | +1.839 |
Neg logit contributions | |
edIn | -2.385 |
itect | -2.080 |
icians | -2.073 |
ification | -2.055 |
ified | -2.043 |
Token | to |
Token ID | 284 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
edIn | +1.986 |
ification | +1.821 |
ified | +1.805 |
icians | +1.793 |
itect | +1.768 |
Neg logit contributions | |
berman | -1.282 |
HAEL | -1.230 |
tti | -1.206 |
tails | -1.196 |
senal | -1.166 |
Token | certain |
Token ID | 1728 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
edIn | +1.474 |
icians | +1.295 |
ification | +1.293 |
ified | +1.285 |
itect | +1.281 |
Neg logit contributions | |
berman | -1.094 |
HAEL | -1.053 |
tti | -1.052 |
tails | -1.023 |
Heck | -0.999 |
Token | issues |
Token ID | 2428 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
berman | +0.122 |
tti | +0.117 |
HAEL | +0.117 |
tails | +0.113 |
Heck | +0.112 |
Neg logit contributions | |
edIn | -0.163 |
icians | -0.143 |
ification | -0.142 |
itect | -0.142 |
ified | -0.142 |
Token | , |
Token ID | 11 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
edIn | +1.802 |
icians | +1.621 |
ification | +1.620 |
ified | +1.611 |
itect | +1.603 |
Neg logit contributions | |
berman | -0.903 |
tti | -0.856 |
HAEL | -0.855 |
tails | -0.826 |
mma | -0.800 |
Token | to |
Token ID | 284 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
berman | +0.229 |
HAEL | +0.220 |
tti | +0.220 |
tails | +0.212 |
Heck | +0.211 |
Neg logit contributions | |
edIn | -0.327 |
icians | -0.287 |
itect | -0.287 |
ification | -0.286 |
ified | -0.285 |
Token | O |
Token ID | 440 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
edIn | +1.375 |
icians | +1.189 |
ification | +1.186 |
itect | +1.181 |
ified | +1.178 |
Neg logit contributions | |
berman | -1.262 |
tti | -1.217 |
HAEL | -1.217 |
tails | -1.187 |
Heck | -1.169 |
Token | ' |
Token ID | 6 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
berman | +8.957 |
tti | +8.562 |
HO | +8.218 |
HAEL | +8.160 |
mouth | +8.033 |
Neg logit contributions | |
edIn | -11.893 |
icter | -10.618 |
itect | -9.977 |
icians | -9.902 |
acters | -9.892 |
Token | Neill |
Token ID | 26538 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
berman | +2.712 |
HAEL | +2.612 |
tti | +2.425 |
HO | +2.351 |
Heck | +2.273 |
Neg logit contributions | |
edIn | -8.272 |
icter | -7.460 |
icians | -7.370 |
itect | -7.345 |
ification | -7.276 |
Token | 's |
Token ID | 338 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
berman | +0.850 |
tti | +0.819 |
HAEL | +0.818 |
Heck | +0.792 |
tails | +0.792 |
Neg logit contributions | |
edIn | -1.059 |
itect | -0.920 |
icians | -0.915 |
ification | -0.907 |
ified | -0.903 |
Token | open |
Token ID | 1280 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
berman | +2.053 |
tti | +2.004 |
HAEL | +1.975 |
Heck | +1.948 |
tails | +1.909 |
Neg logit contributions | |
edIn | -3.266 |
itect | -2.900 |
icians | -2.855 |
ification | -2.825 |
icter | -2.801 |
Token | - |
Token ID | 12 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
berman | +1.923 |
tti | +1.863 |
HAEL | +1.838 |
tails | +1.813 |
Heck | +1.801 |
Neg logit contributions | |
edIn | -2.783 |
itect | -2.430 |
icians | -2.406 |
ification | -2.376 |
ified | -2.366 |
Token | s |
Token ID | 82 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
berman | +0.142 |
tti | +0.137 |
HAEL | +0.136 |
tails | +0.133 |
Heck | +0.130 |
Neg logit contributions | |
edIn | -0.188 |
icians | -0.165 |
ification | -0.164 |
itect | -0.164 |
ified | -0.163 |
Token | largest |
Token ID | 4387 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
berman | +0.477 |
tti | +0.457 |
HAEL | +0.456 |
tails | +0.442 |
Heck | +0.435 |
Neg logit contributions | |
edIn | -0.717 |
icians | -0.633 |
ification | -0.631 |
itect | -0.628 |
ified | -0.627 |
Token | capacity |
Token ID | 5339 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
berman | +1.040 |
tti | +0.997 |
HAEL | +0.983 |
Heck | +0.961 |
tails | +0.954 |
Neg logit contributions | |
edIn | -1.511 |
icians | -1.328 |
ification | -1.315 |
itect | -1.307 |
ified | -1.302 |
Token | cartridge |
Token ID | 26904 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
berman | +0.172 |
tti | +0.164 |
HAEL | +0.164 |
tails | +0.159 |
Heck | +0.156 |
Neg logit contributions | |
edIn | -0.269 |
icians | -0.238 |
ification | -0.237 |
itect | -0.236 |
ified | -0.236 |
Token | , |
Token ID | 11 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
berman | +1.505 |
tti | +1.444 |
HAEL | +1.416 |
Heck | +1.380 |
tails | +1.378 |
Neg logit contributions | |
edIn | -2.572 |
icians | -2.269 |
itect | -2.246 |
ification | -2.239 |
ified | -2.223 |
Token | O |
Token ID | 440 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
edIn | +0.211 |
icians | +0.185 |
ification | +0.184 |
itect | +0.184 |
ified | +0.183 |
Neg logit contributions | |
berman | -0.151 |
tti | -0.146 |
HAEL | -0.145 |
tails | -0.140 |
Heck | -0.140 |
Token | car |
Token ID | 7718 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
berman | +6.799 |
tti | +6.625 |
train | +6.165 |
cycl | +6.122 |
DI | +6.033 |
Neg logit contributions | |
edIn | -13.502 |
icter | -12.132 |
itect | -12.035 |
ifiers | -12.033 |
icians | -12.023 |
Token | ina |
Token ID | 1437 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
berman | +0.622 |
HAEL | +0.599 |
tti | +0.597 |
tails | +0.582 |
Heck | +0.574 |
Neg logit contributions | |
edIn | -0.758 |
ification | -0.664 |
icians | -0.663 |
ified | -0.660 |
itect | -0.659 |
Token | of |
Token ID | 286 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
edIn | +3.234 |
ification | +2.884 |
icians | +2.883 |
itect | +2.878 |
ified | +2.864 |
Neg logit contributions | |
berman | -1.808 |
HAEL | -1.735 |
tti | -1.708 |
tails | -1.684 |
mma | -1.611 |
Token | Time |
Token ID | 3862 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
edIn | +0.582 |
ification | +0.520 |
ified | +0.516 |
icians | +0.515 |
itect | +0.514 |
Neg logit contributions | |
berman | -0.345 |
HAEL | -0.331 |
tti | -0.322 |
tails | -0.310 |
mma | -0.306 |
Token | was |
Token ID | 373 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
berman | +3.752 |
tti | +3.730 |
HAEL | +3.536 |
Heck | +3.528 |
Gamble | +3.496 |
Neg logit contributions | |
edIn | -5.738 |
icians | -5.038 |
itect | -4.940 |
ification | -4.932 |
ifiers | -4.889 |
Token | cos |
Token ID | 6966 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
berman | +1.243 |
tti | +1.159 |
HAEL | +1.118 |
tails | +1.113 |
Heck | +1.068 |
Neg logit contributions | |
edIn | -3.035 |
itect | -2.695 |
ification | -2.679 |
icians | -2.673 |
ified | -2.661 |
Token | such |
Token ID | 884 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
edIn | +3.829 |
ification | +3.427 |
ified | +3.388 |
icians | +3.380 |
itect | +3.353 |
Neg logit contributions | |
berman | -3.281 |
HAEL | -3.166 |
tti | -3.146 |
tails | -3.093 |
mma | -3.019 |
Token | as |
Token ID | 355 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
berman | +2.524 |
tti | +2.417 |
HAEL | +2.379 |
tails | +2.290 |
Heck | +2.252 |
Neg logit contributions | |
edIn | -5.355 |
icians | -4.760 |
itect | -4.728 |
ification | -4.695 |
ified | -4.675 |
Token | BT |
Token ID | 22205 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
berman | +1.763 |
tti | +1.697 |
HAEL | +1.667 |
Heck | +1.652 |
Gamble | +1.644 |
Neg logit contributions | |
edIn | -3.338 |
icians | -2.980 |
itect | -2.966 |
ification | -2.942 |
ified | -2.923 |
Token | , |
Token ID | 11 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
berman | +0.350 |
tti | +0.337 |
HAEL | +0.336 |
tails | +0.324 |
Heck | +0.321 |
Neg logit contributions | |
edIn | -0.540 |
icians | -0.476 |
itect | -0.474 |
ification | -0.473 |
ified | -0.470 |
Token | O |
Token ID | 440 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
berman | +1.707 |
tti | +1.651 |
HAEL | +1.630 |
Heck | +1.594 |
Gamble | +1.593 |
Neg logit contributions | |
edIn | -3.079 |
icians | -2.735 |
itect | -2.723 |
ification | -2.708 |
ified | -2.689 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
DI | +7.510 |
tti | +7.427 |
berman | +7.425 |
train | +7.017 |
mma | +6.976 |
Neg logit contributions | |
edIn | -12.695 |
icter | -11.912 |
icians | -11.358 |
itect | -11.118 |
icipated | -11.002 |
Token | and |
Token ID | 290 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
berman | +2.911 |
tti | +2.820 |
HAEL | +2.779 |
Gamble | +2.711 |
Heck | +2.694 |
Neg logit contributions | |
edIn | -4.717 |
icians | -4.107 |
itect | -4.093 |
ification | -4.054 |
ified | -4.036 |
Token | Virgin |
Token ID | 5283 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
berman | +3.374 |
Gamble | +3.334 |
tti | +3.315 |
Heck | +3.294 |
HAEL | +3.155 |
Neg logit contributions | |
edIn | -6.786 |
itect | -6.012 |
icians | -5.997 |
icter | -5.923 |
ification | -5.912 |
Token | having |
Token ID | 1719 |
Feature activation | -6.98e-03 |
Pos logit contributions | |
tti | +2.448 |
berman | +2.445 |
Gamble | +2.419 |
HAEL | +2.358 |
Heck | +2.345 |
Neg logit contributions | |
edIn | -4.404 |
icians | -3.922 |
itect | -3.877 |
icter | -3.816 |
acters | -3.790 |
Token | blocked |
Token ID | 10226 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
edIn | +0.023 |
icians | +0.020 |
itect | +0.020 |
ification | +0.020 |
ified | +0.020 |
Neg logit contributions | |
berman | -0.021 |
tti | -0.020 |
HAEL | -0.020 |
tails | -0.020 |
Heck | -0.020 |
Token | before |
Token ID | 878 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
berman | +2.234 |
tti | +2.156 |
HAEL | +2.087 |
tails | +2.051 |
Heck | +2.039 |
Neg logit contributions | |
edIn | -4.275 |
icians | -3.746 |
itect | -3.736 |
ified | -3.672 |
ification | -3.670 |
Token | the |
Token ID | 262 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
edIn | +1.188 |
icians | +1.045 |
ification | +1.042 |
itect | +1.038 |
ified | +1.036 |
Neg logit contributions | |
berman | -0.841 |
tti | -0.808 |
HAEL | -0.807 |
tails | -0.783 |
Heck | -0.772 |
Token | program |
Token ID | 1430 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
edIn | +1.866 |
ification | +1.670 |
icians | +1.669 |
ified | +1.658 |
itect | +1.652 |
Neg logit contributions | |
berman | -1.113 |
HAEL | -1.072 |
tti | -1.065 |
tails | -1.034 |
mma | -1.012 |
Token | was |
Token ID | 373 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
edIn | +0.093 |
icians | +0.082 |
itect | +0.081 |
ification | +0.081 |
ified | +0.081 |
Neg logit contributions | |
berman | -0.063 |
tti | -0.060 |
HAEL | -0.060 |
tails | -0.058 |
Heck | -0.057 |
Token | finally |
Token ID | 3443 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
edIn | +0.866 |
ification | +0.750 |
icians | +0.749 |
ified | +0.745 |
itect | +0.742 |
Neg logit contributions | |
berman | -0.848 |
HAEL | -0.821 |
tti | -0.816 |
tails | -0.799 |
Heck | -0.783 |
Token | declass |
Token ID | 42794 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
edIn | +0.890 |
ification | +0.771 |
icians | +0.769 |
ified | +0.766 |
itect | +0.762 |
Neg logit contributions | |
berman | -0.880 |
HAEL | -0.853 |
tti | -0.848 |
tails | -0.828 |
Heck | -0.813 |
Token | ified |
Token ID | 1431 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ified | +6.520 |
ification | +5.720 |
ifying | +3.959 |
edIn | +3.873 |
ifiers | +3.812 |
Neg logit contributions | |
senal | -23.292 |
berman | -21.651 |
HAEL | -21.337 |
tails | -21.080 |
Heck | -20.961 |
Token | in |
Token ID | 287 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
edIn | +6.388 |
ification | +5.856 |
ified | +5.811 |
icians | +5.695 |
itect | +5.660 |
Neg logit contributions | |
berman | -4.131 |
HAEL | -3.957 |
tti | -3.879 |
tails | -3.862 |
mma | -3.691 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
edIn | +2.747 |
ification | +2.419 |
ified | +2.405 |
icians | +2.396 |
itect | +2.359 |
Neg logit contributions | |
berman | -2.733 |
HAEL | -2.661 |
tti | -2.641 |
tails | -2.586 |
mma | -2.539 |
Token | . |
Token ID | 13 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
berman | +0.865 |
tti | +0.828 |
HAEL | +0.819 |
tails | +0.785 |
Heck | +0.780 |
Neg logit contributions | |
edIn | -1.791 |
icians | -1.597 |
itect | -1.585 |
ification | -1.579 |
ified | -1.574 |
Token | That |
Token ID | 1320 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
edIn | +0.972 |
icians | +0.853 |
ification | +0.851 |
itect | +0.847 |
ified | +0.846 |
Neg logit contributions | |
berman | -0.717 |
tti | -0.690 |
HAEL | -0.689 |
tails | -0.669 |
Heck | -0.661 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
edIn | +0.133 |
icians | +0.113 |
ification | +0.113 |
ified | +0.112 |
itect | +0.112 |
Neg logit contributions | |
berman | -0.150 |
HAEL | -0.145 |
tti | -0.145 |
tails | -0.141 |
Heck | -0.139 |
Token | election |
Token ID | 3071 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
edIn | +0.410 |
icians | +0.362 |
ification | +0.360 |
itect | +0.360 |
ified | +0.358 |
Neg logit contributions | |
berman | -0.271 |
tti | -0.259 |
HAEL | -0.258 |
tails | -0.252 |
Heck | -0.248 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
edIn | +1.662 |
icians | +1.486 |
ification | +1.484 |
ified | +1.476 |
itect | +1.475 |
Neg logit contributions | |
berman | -0.871 |
tti | -0.829 |
HAEL | -0.829 |
tails | -0.801 |
Heck | -0.779 |
Token |
|
Token ID | 198 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
berman | +0.312 |
tti | +0.302 |
HAEL | +0.300 |
Heck | +0.296 |
Gamble | +0.290 |
Neg logit contributions | |
edIn | -0.426 |
icians | -0.375 |
itect | -0.370 |
ification | -0.370 |
ified | -0.368 |
Token |
|
Token ID | 198 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
edIn | +1.549 |
ification | +1.391 |
ified | +1.385 |
itect | +1.364 |
icians | +1.358 |
Neg logit contributions | |
berman | -1.571 |
senal | -1.524 |
HAEL | -1.516 |
tti | -1.494 |
tails | -1.468 |
Token | Christ |
Token ID | 10684 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
edIn | +1.920 |
icians | +1.675 |
ification | +1.673 |
itect | +1.663 |
ified | +1.662 |
Neg logit contributions | |
berman | -1.545 |
tti | -1.486 |
HAEL | -1.486 |
tails | -1.445 |
Heck | -1.421 |
Token | ie |
Token ID | 494 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ification | +7.589 |
ified | +7.576 |
edIn | +7.150 |
ifiers | +6.777 |
itect | +6.748 |
Neg logit contributions | |
senal | -17.641 |
HAEL | -16.681 |
tails | -16.619 |
unnecess | -16.254 |
berman | -16.194 |
Token | is |
Token ID | 318 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
edIn | +3.968 |
ification | +3.471 |
icians | +3.455 |
ified | +3.435 |
itect | +3.429 |
Neg logit contributions | |
berman | -3.477 |
HAEL | -3.373 |
tti | -3.333 |
tails | -3.280 |
mma | -3.225 |
Token | widely |
Token ID | 6768 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
edIn | +0.459 |
icians | +0.399 |
ification | +0.398 |
itect | +0.396 |
ified | +0.395 |
Neg logit contributions | |
berman | -0.381 |
tti | -0.367 |
HAEL | -0.366 |
tails | -0.357 |
Heck | -0.352 |
Token | considered |
Token ID | 3177 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
edIn | +1.026 |
icians | +0.876 |
ification | +0.874 |
itect | +0.868 |
ified | +0.867 |
Neg logit contributions | |
berman | -1.120 |
HAEL | -1.083 |
tti | -1.083 |
tails | -1.058 |
Heck | -1.043 |
Token | to |
Token ID | 284 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
edIn | +0.973 |
icians | +0.858 |
ification | +0.856 |
itect | +0.853 |
ified | +0.851 |
Neg logit contributions | |
berman | -0.650 |
tti | -0.622 |
HAEL | -0.622 |
tails | -0.603 |
Heck | -0.592 |
Token | exit |
Token ID | 8420 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
edIn | +3.466 |
ified | +3.030 |
ification | +3.028 |
icians | +3.012 |
itect | +2.977 |
Neg logit contributions | |
berman | -2.764 |
HAEL | -2.665 |
tti | -2.645 |
tails | -2.613 |
mma | -2.569 |
Token | polls |
Token ID | 9231 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
edIn | +0.662 |
icians | +0.560 |
ification | +0.558 |
itect | +0.557 |
ified | +0.553 |
Neg logit contributions | |
berman | -0.695 |
HAEL | -0.673 |
tti | -0.673 |
tails | -0.658 |
Heck | -0.651 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
edIn | +5.386 |
ified | +4.881 |
ification | +4.862 |
icians | +4.821 |
itect | +4.725 |
Neg logit contributions | |
berman | -3.598 |
tti | -3.489 |
HAEL | -3.470 |
tails | -3.428 |
mma | -3.367 |
Token |
|
Token ID | 198 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
edIn | +0.479 |
icians | +0.421 |
ification | +0.418 |
itect | +0.417 |
ified | +0.416 |
Neg logit contributions | |
berman | -0.342 |
tti | -0.330 |
HAEL | -0.330 |
tails | -0.319 |
Heck | -0.319 |
Token |
|
Token ID | 198 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
edIn | +1.373 |
ification | +1.224 |
ified | +1.219 |
itect | +1.203 |
icians | +1.198 |
Neg logit contributions | |
berman | -1.360 |
HAEL | -1.303 |
tti | -1.294 |
senal | -1.291 |
tails | -1.271 |
Token | Christ |
Token ID | 10684 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
edIn | +1.512 |
icians | +1.322 |
ification | +1.318 |
itect | +1.312 |
ified | +1.309 |
Neg logit contributions | |
berman | -1.208 |
tti | -1.163 |
HAEL | -1.163 |
tails | -1.131 |
Heck | -1.111 |
Token | ie |
Token ID | 494 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ification | +5.393 |
ified | +5.235 |
ifiers | +4.642 |
edIn | +4.600 |
icians | +4.565 |
Neg logit contributions | |
senal | -18.898 |
HAEL | -18.090 |
tails | -18.030 |
tti | -17.598 |
mma | -17.445 |
Token | � |
Token ID | 447 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
edIn | +3.773 |
ification | +3.320 |
icians | +3.309 |
ified | +3.304 |
itect | +3.255 |
Neg logit contributions | |
berman | -3.294 |
HAEL | -3.213 |
tti | -3.150 |
tails | -3.109 |
mma | -3.051 |
Token | � |
Token ID | 247 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
berman | +0.092 |
tti | +0.089 |
HAEL | +0.089 |
tails | +0.086 |
Heck | +0.085 |
Neg logit contributions | |
edIn | -0.115 |
icians | -0.100 |
ification | -0.100 |
itect | -0.099 |
ified | -0.099 |
Token | s |
Token ID | 82 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
berman | +1.768 |
tti | +1.716 |
HAEL | +1.696 |
tails | +1.648 |
Heck | +1.640 |
Neg logit contributions | |
edIn | -2.076 |
icians | -1.805 |
itect | -1.791 |
ification | -1.790 |
ified | -1.773 |
Token | showing |
Token ID | 4478 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
berman | +1.089 |
tti | +1.050 |
HAEL | +1.041 |
Heck | +1.017 |
tails | +1.014 |
Neg logit contributions | |
edIn | -1.320 |
itect | -1.156 |
icians | -1.156 |
ification | -1.143 |
ified | -1.133 |
Token | humiliating |
Token ID | 37743 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
edIn | +4.698 |
ification | +4.129 |
ified | +4.122 |
icians | +4.092 |
itect | +4.089 |
Neg logit contributions | |
berman | -3.543 |
tti | -3.394 |
HAEL | -3.368 |
tails | -3.233 |
Heck | -3.188 |
Token | defeat |
Token ID | 7433 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
edIn | +3.232 |
ified | +2.711 |
ification | +2.700 |
itect | +2.634 |
icians | +2.520 |
Neg logit contributions | |
berman | -5.003 |
tti | -4.860 |
HAEL | -4.831 |
tails | -4.759 |
HO | -4.704 |
Token | to |
Token ID | 284 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
edIn | +4.287 |
ification | +3.869 |
ified | +3.828 |
icians | +3.806 |
itect | +3.789 |
Neg logit contributions | |
berman | -2.906 |
HAEL | -2.770 |
tti | -2.708 |
tails | -2.687 |
mma | -2.639 |
Token | the |
Token ID | 262 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
edIn | +4.730 |
ification | +4.133 |
icians | +4.119 |
ified | +4.071 |
itect | +4.019 |
Neg logit contributions | |
berman | -4.103 |
HAEL | -4.015 |
tti | -4.004 |
tails | -3.885 |
mma | -3.883 |
Token | euros |
Token ID | 21138 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
edIn | +1.984 |
icians | +1.730 |
ification | +1.722 |
ified | +1.708 |
itect | +1.705 |
Neg logit contributions | |
berman | -1.725 |
HAEL | -1.675 |
tti | -1.669 |
tails | -1.622 |
Heck | -1.599 |
Token | cept |
Token ID | 984 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
edIn | +1.272 |
ification | +0.954 |
icians | +0.950 |
ified | +0.927 |
itect | +0.902 |
Neg logit contributions | |
berman | -4.674 |
HAEL | -4.653 |
tti | -4.583 |
Gamble | -4.533 |
tails | -4.527 |
Token | ic |
Token ID | 291 |
Feature activation | -3.20e-05 |
Pos logit contributions | |
ification | +3.319 |
icians | +3.203 |
ified | +3.180 |
ics | +3.055 |
edIn | +2.544 |
Neg logit contributions | |
senal | -22.296 |
HAEL | -20.573 |
unnecess | -20.063 |
Gamble | -19.899 |
Heck | -19.612 |
Token | UK |
Token ID | 3482 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
edIn | +0.000 |
icians | +0.000 |
ification | +0.000 |
ified | +0.000 |
itect | +0.000 |
Neg logit contributions | |
berman | -0.000 |
tti | -0.000 |
HAEL | -0.000 |
tails | -0.000 |
Heck | -0.000 |
Token | IP |
Token ID | 6101 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
berman | +1.837 |
tti | +1.721 |
HAEL | +1.709 |
tails | +1.641 |
Heck | +1.630 |
Neg logit contributions | |
edIn | -4.978 |
itect | -4.504 |
icians | -4.488 |
ification | -4.449 |
ified | -4.428 |
Token | party |
Token ID | 2151 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
berman | +4.653 |
HAEL | +4.584 |
tti | +4.333 |
HO | +4.282 |
Heck | +4.274 |
Neg logit contributions | |
edIn | -8.039 |
ifiers | -7.294 |
ification | -7.168 |
ified | -7.159 |
itect | -7.158 |
Token | in |
Token ID | 287 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
berman | +0.431 |
tti | +0.413 |
HAEL | +0.412 |
tails | +0.396 |
Heck | +0.391 |
Neg logit contributions | |
edIn | -0.805 |
icians | -0.718 |
itect | -0.713 |
ification | -0.713 |
ified | -0.711 |
Token | � |
Token ID | 447 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
edIn | +1.124 |
icians | +0.994 |
ification | +0.992 |
itect | +0.987 |
ified | +0.987 |
Neg logit contributions | |
berman | -0.761 |
HAEL | -0.728 |
tti | -0.728 |
tails | -0.705 |
Heck | -0.692 |
Token | � |
Token ID | 251 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
edIn | +1.294 |
icians | +1.130 |
ification | +1.126 |
itect | +1.122 |
ified | +1.119 |
Neg logit contributions | |
berman | -1.028 |
tti | -0.988 |
HAEL | -0.988 |
tails | -0.961 |
Heck | -0.944 |
Token | system |
Token ID | 1080 |
Feature activation | -8.98e-03 |
Pos logit contributions | |
edIn | +5.192 |
ification | +4.636 |
icians | +4.614 |
ified | +4.611 |
itect | +4.591 |
Neg logit contributions | |
berman | -3.653 |
HAEL | -3.484 |
tti | -3.470 |
tails | -3.362 |
Heck | -3.274 |
Token | has |
Token ID | 468 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
edIn | +0.034 |
icians | +0.030 |
ification | +0.030 |
itect | +0.030 |
ified | +0.029 |
Neg logit contributions | |
berman | -0.023 |
HAEL | -0.022 |
tti | -0.022 |
tails | -0.021 |
Heck | -0.021 |
Token | been |
Token ID | 587 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
edIn | +5.180 |
ification | +4.545 |
ified | +4.531 |
icians | +4.522 |
itect | +4.498 |
Neg logit contributions | |
berman | -4.798 |
HAEL | -4.607 |
tti | -4.534 |
tails | -4.506 |
mma | -4.382 |
Token | declass |
Token ID | 42794 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
edIn | +0.877 |
icians | +0.760 |
ification | +0.759 |
itect | +0.755 |
ified | +0.754 |
Neg logit contributions | |
berman | -0.786 |
tti | -0.758 |
HAEL | -0.758 |
tails | -0.739 |
Heck | -0.727 |
Token | ified |
Token ID | 1431 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ified | +5.640 |
ification | +4.889 |
edIn | +4.545 |
ifiers | +3.669 |
ifying | +3.585 |
Neg logit contributions | |
berman | -19.772 |
HAEL | -19.462 |
senal | -19.288 |
tails | -19.267 |
tti | -19.128 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
edIn | +6.146 |
ification | +5.612 |
ified | +5.573 |
icians | +5.479 |
itect | +5.478 |
Neg logit contributions | |
berman | -4.048 |
HAEL | -3.861 |
tti | -3.834 |
tails | -3.746 |
mma | -3.638 |
Token | although |
Token ID | 3584 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
edIn | +3.760 |
ification | +3.327 |
icians | +3.315 |
ified | +3.300 |
itect | +3.283 |
Neg logit contributions | |
berman | -3.015 |
HAEL | -2.899 |
tti | -2.887 |
tails | -2.810 |
mma | -2.768 |
Token | it |
Token ID | 340 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
edIn | +4.265 |
ification | +3.802 |
ified | +3.768 |
icians | +3.768 |
itect | +3.702 |
Neg logit contributions | |
berman | -3.596 |
HAEL | -3.457 |
tti | -3.417 |
tails | -3.363 |
mma | -3.291 |
Token | is |
Token ID | 318 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
berman | +0.842 |
tti | +0.812 |
HAEL | +0.795 |
tails | +0.786 |
Heck | +0.770 |
Neg logit contributions | |
edIn | -1.259 |
icians | -1.095 |
itect | -1.090 |
ification | -1.084 |
ified | -1.080 |
Token | US |
Token ID | 1294 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
berman | +0.538 |
tti | +0.518 |
HAEL | +0.515 |
tails | +0.504 |
Heck | +0.499 |
Neg logit contributions | |
edIn | -0.699 |
icians | -0.609 |
itect | -0.606 |
ification | -0.605 |
ified | -0.601 |
Token | , |
Token ID | 11 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
berman | +0.900 |
tti | +0.856 |
HAEL | +0.851 |
Heck | +0.819 |
tails | +0.817 |
Neg logit contributions | |
edIn | -1.817 |
icians | -1.621 |
itect | -1.605 |
ified | -1.598 |
ification | -1.594 |
Token | where |
Token ID | 810 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
edIn | +1.932 |
icians | +1.694 |
ification | +1.689 |
itect | +1.682 |
ified | +1.679 |
Neg logit contributions | |
berman | -1.457 |
tti | -1.401 |
HAEL | -1.399 |
tails | -1.360 |
Heck | -1.338 |
Token | 11 |
Token ID | 1367 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
edIn | +1.917 |
icians | +1.681 |
ification | +1.678 |
itect | +1.669 |
ified | +1.667 |
Neg logit contributions | |
berman | -1.452 |
HAEL | -1.395 |
tti | -1.395 |
tails | -1.355 |
Heck | -1.329 |
Token | b |
Token ID | 275 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
berman | +1.128 |
tti | +1.108 |
HAEL | +1.080 |
tails | +1.064 |
Heck | +1.045 |
Neg logit contributions | |
edIn | -1.840 |
ification | -1.617 |
icians | -1.614 |
ified | -1.608 |
itect | -1.608 |
Token | idd |
Token ID | 1638 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
edIn | +1.445 |
icians | +1.290 |
ification | +1.289 |
itect | +1.284 |
ified | +1.282 |
Neg logit contributions | |
berman | -0.720 |
tti | -0.685 |
HAEL | -0.685 |
tails | -0.660 |
Heck | -0.644 |
Token | ers |
Token ID | 364 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
edIn | +10.774 |
ification | +9.872 |
ifiers | +9.702 |
ified | +9.673 |
icians | +9.619 |
Neg logit contributions | |
senal | -14.029 |
HAEL | -13.723 |
berman | -13.529 |
mma | -12.766 |
HO | -12.713 |
Token | have |
Token ID | 423 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
edIn | +6.679 |
ification | +6.175 |
ified | +6.090 |
icians | +6.004 |
ifiers | +5.956 |
Neg logit contributions | |
berman | -6.679 |
HAEL | -6.466 |
tti | -6.409 |
tails | -6.327 |
mma | -6.236 |
Token | sent |
Token ID | 1908 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
edIn | +5.708 |
ified | +5.029 |
ification | +5.027 |
icians | +4.882 |
ifiers | +4.836 |
Neg logit contributions | |
berman | -6.815 |
HAEL | -6.685 |
tti | -6.502 |
tails | -6.497 |
mma | -6.362 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
berman | +1.680 |
tti | +1.599 |
Heck | +1.587 |
tails | +1.578 |
HAEL | +1.571 |
Neg logit contributions | |
edIn | -2.561 |
itect | -2.271 |
icians | -2.249 |
ification | -2.216 |
ified | -2.208 |
Token | price |
Token ID | 2756 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
edIn | +0.474 |
icians | +0.412 |
itect | +0.410 |
ification | +0.409 |
ified | +0.406 |
Neg logit contributions | |
berman | -0.387 |
tti | -0.375 |
HAEL | -0.372 |
tails | -0.364 |
Heck | -0.361 |
Token | leak |
Token ID | 13044 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
edIn | +3.785 |
ification | +3.323 |
icians | +3.314 |
ified | +3.309 |
itect | +3.257 |
Neg logit contributions | |
berman | -3.350 |
HAEL | -3.235 |
tti | -3.203 |
tails | -3.135 |
mma | -3.051 |
Token | isn |
Token ID | 2125 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
berman | +2.443 |
tti | +2.398 |
HAEL | +2.324 |
tails | +2.286 |
Heck | +2.280 |
Neg logit contributions | |
edIn | -3.897 |
itect | -3.433 |
icians | -3.410 |
ification | -3.342 |
ifiers | -3.317 |
Token | 't |
Token ID | 470 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
edIn | +1.978 |
ification | +1.762 |
ified | +1.758 |
itect | +1.687 |
icians | +1.687 |
Neg logit contributions | |
berman | -3.210 |
senal | -3.158 |
HAEL | -3.142 |
tti | -3.076 |
tails | -3.029 |
Token | a |
Token ID | 257 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
edIn | +1.832 |
ification | +1.605 |
ified | +1.599 |
icians | +1.595 |
itect | +1.576 |
Neg logit contributions | |
berman | -1.615 |
HAEL | -1.563 |
tti | -1.552 |
tails | -1.513 |
mma | -1.486 |
Token | ' |
Token ID | 705 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
edIn | +2.955 |
ification | +2.591 |
icians | +2.581 |
ified | +2.576 |
itect | +2.562 |
Neg logit contributions | |
berman | -2.434 |
HAEL | -2.353 |
tti | -2.342 |
tails | -2.275 |
mma | -2.234 |
Token | cons |
Token ID | 5936 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
edIn | +0.967 |
icians | +0.841 |
ification | +0.838 |
itect | +0.834 |
ified | +0.833 |
Neg logit contributions | |
berman | -0.825 |
tti | -0.795 |
HAEL | -0.794 |
tails | -0.774 |
Heck | -0.761 |
Token | piracy |
Token ID | 8703 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
ification | +5.583 |
ified | +5.263 |
edIn | +5.250 |
ularity | +5.126 |
itect | +4.930 |
Neg logit contributions | |
senal | -18.251 |
HAEL | -17.478 |
berman | -16.653 |
tti | -16.559 |
tails | -16.371 |
Token | theory |
Token ID | 4583 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
edIn | +5.183 |
ification | +4.452 |
ified | +4.379 |
icians | +4.295 |
itect | +4.269 |
Neg logit contributions | |
berman | -8.369 |
HAEL | -8.176 |
tti | -8.050 |
tails | -7.974 |
mma | -7.802 |
Token | ' |
Token ID | 6 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
edIn | +4.696 |
ification | +4.100 |
ified | +4.054 |
icians | +4.020 |
itect | +3.956 |
Neg logit contributions | |
berman | -5.881 |
HAEL | -5.756 |
tti | -5.722 |
tails | -5.606 |
mma | -5.499 |
Token | like |
Token ID | 588 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
berman | +0.042 |
tti | +0.041 |
HAEL | +0.041 |
tails | +0.039 |
Heck | +0.039 |
Neg logit contributions | |
edIn | -0.057 |
icians | -0.050 |
itect | -0.049 |
ification | -0.049 |
ified | -0.049 |
Token | Donald |
Token ID | 3759 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
berman | +0.406 |
tti | +0.390 |
HAEL | +0.387 |
tails | +0.378 |
Heck | +0.377 |
Neg logit contributions | |
edIn | -0.549 |
itect | -0.483 |
icians | -0.480 |
ification | -0.477 |
ified | -0.473 |
Token | , |
Token ID | 11 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
edIn | +4.750 |
ification | +4.344 |
itect | +4.299 |
ified | +4.298 |
icians | +4.264 |
Neg logit contributions | |
berman | -2.510 |
HAEL | -2.401 |
tti | -2.357 |
tails | -2.347 |
mma | -2.242 |
Token | drew |
Token ID | 9859 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
berman | +0.621 |
tti | +0.602 |
HAEL | +0.586 |
tails | +0.580 |
Heck | +0.576 |
Neg logit contributions | |
edIn | -0.887 |
icians | -0.773 |
itect | -0.767 |
ification | -0.766 |
ified | -0.764 |
Token | just |
Token ID | 655 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
edIn | +0.432 |
icians | +0.380 |
ification | +0.378 |
itect | +0.378 |
ified | +0.376 |
Neg logit contributions | |
berman | -0.293 |
tti | -0.283 |
HAEL | -0.281 |
tails | -0.274 |
Heck | -0.271 |
Token | eight |
Token ID | 3624 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
edIn | +5.426 |
ified | +4.917 |
ification | +4.914 |
icians | +4.855 |
ifiers | +4.791 |
Neg logit contributions | |
berman | -4.468 |
HAEL | -4.300 |
tti | -4.239 |
tails | -4.233 |
mma | -4.057 |
Token | b |
Token ID | 275 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
edIn | +0.441 |
icians | +0.387 |
ification | +0.386 |
itect | +0.384 |
ified | +0.384 |
Neg logit contributions | |
berman | -0.327 |
tti | -0.314 |
HAEL | -0.313 |
tails | -0.305 |
Heck | -0.299 |
Token | idd |
Token ID | 1638 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
edIn | +0.827 |
icians | +0.739 |
ification | +0.738 |
itect | +0.735 |
ified | +0.734 |
Neg logit contributions | |
berman | -0.400 |
tti | -0.379 |
HAEL | -0.378 |
tails | -0.365 |
Heck | -0.355 |
Token | ers |
Token ID | 364 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
edIn | +10.191 |
ification | +9.340 |
ified | +9.093 |
ifiers | +9.077 |
icians | +8.960 |
Neg logit contributions | |
senal | -14.216 |
HAEL | -13.499 |
berman | -13.278 |
tti | -12.540 |
HO | -12.512 |
Token | when |
Token ID | 618 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
edIn | +7.230 |
ification | +6.742 |
ified | +6.683 |
icians | +6.520 |
itect | +6.514 |
Neg logit contributions | |
berman | -4.820 |
HAEL | -4.731 |
tails | -4.586 |
tti | -4.583 |
mma | -4.469 |
Token | auction |
Token ID | 14389 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
edIn | +1.184 |
icians | +1.040 |
ification | +1.036 |
itect | +1.031 |
ified | +1.029 |
Neg logit contributions | |
berman | -0.890 |
HAEL | -0.857 |
tti | -0.855 |
tails | -0.832 |
Heck | -0.823 |
Token | ed |
Token ID | 276 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
edIn | +3.678 |
icians | +3.172 |
ification | +3.165 |
ified | +3.158 |
itect | +3.155 |
Neg logit contributions | |
berman | -3.332 |
tti | -3.206 |
HAEL | -3.202 |
tails | -3.115 |
mma | -3.069 |
Token | by |
Token ID | 416 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
berman | +0.704 |
tti | +0.669 |
HAEL | +0.667 |
tails | +0.642 |
Heck | +0.637 |
Neg logit contributions | |
edIn | -1.438 |
icians | -1.289 |
itect | -1.284 |
ification | -1.281 |
ified | -1.273 |
Token | ), |
Token ID | 828 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
berman | +0.393 |
tti | +0.378 |
HAEL | +0.378 |
tails | +0.366 |
Heck | +0.362 |
Neg logit contributions | |
edIn | -0.546 |
icians | -0.481 |
itect | -0.475 |
ification | -0.474 |
ified | -0.471 |
Token | Gu |
Token ID | 1962 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
berman | +2.609 |
tti | +2.498 |
HAEL | +2.480 |
Heck | +2.466 |
Gamble | +2.439 |
Neg logit contributions | |
edIn | -3.673 |
itect | -3.199 |
icians | -3.186 |
ification | -3.129 |
ified | -3.121 |
Token | illa |
Token ID | 5049 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
berman | +2.274 |
tti | +2.183 |
HAEL | +2.177 |
tails | +2.116 |
mma | +2.097 |
Neg logit contributions | |
edIn | -2.513 |
icians | -2.151 |
itect | -2.140 |
ification | -2.136 |
ified | -2.121 |
Token | ume |
Token ID | 2454 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
berman | +2.700 |
tti | +2.601 |
HAEL | +2.578 |
mma | +2.535 |
tails | +2.513 |
Neg logit contributions | |
edIn | -2.626 |
icians | -2.193 |
itect | -2.184 |
ification | -2.165 |
ified | -2.146 |
Token | ( |
Token ID | 357 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
berman | +0.169 |
tti | +0.161 |
HAEL | +0.160 |
tails | +0.154 |
Heck | +0.152 |
Neg logit contributions | |
edIn | -0.326 |
icians | -0.291 |
ification | -0.289 |
itect | -0.289 |
ified | -0.287 |
Token | nom |
Token ID | 26601 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
berman | +2.258 |
tti | +2.184 |
HAEL | +2.159 |
tails | +2.129 |
train | +2.086 |
Neg logit contributions | |
edIn | -2.929 |
icians | -2.589 |
itect | -2.557 |
ification | -2.518 |
ified | -2.496 |
Token | inated |
Token ID | 3898 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
edIn | +6.595 |
ified | +6.131 |
ification | +5.928 |
icipated | +5.545 |
icians | +5.504 |
Neg logit contributions | |
HAEL | -15.879 |
senal | -15.826 |
tails | -15.747 |
berman | -15.529 |
tti | -15.453 |
Token | five |
Token ID | 1936 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
edIn | +5.023 |
ification | +4.462 |
ified | +4.446 |
icians | +4.381 |
itect | +4.342 |
Neg logit contributions | |
berman | -3.915 |
HAEL | -3.754 |
tti | -3.710 |
tails | -3.682 |
mma | -3.541 |
Token | times |
Token ID | 1661 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
edIn | +0.898 |
icians | +0.804 |
ification | +0.802 |
itect | +0.799 |
ified | +0.799 |
Neg logit contributions | |
berman | -0.454 |
HAEL | -0.431 |
tti | -0.429 |
tails | -0.414 |
Heck | -0.403 |
Token | for |
Token ID | 329 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
berman | +1.639 |
HAEL | +1.556 |
tti | +1.542 |
tails | +1.480 |
Heck | +1.473 |
Neg logit contributions | |
edIn | -3.205 |
icians | -2.857 |
itect | -2.833 |
ification | -2.829 |
ified | -2.802 |
Token | Benson |
Token ID | 33940 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
edIn | +0.768 |
icians | +0.683 |
ification | +0.680 |
itect | +0.678 |
ified | +0.677 |
Neg logit contributions | |
berman | -0.454 |
tti | -0.433 |
HAEL | -0.433 |
tails | -0.418 |
Heck | -0.412 |
Token | mentioned |
Token ID | 4750 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
berman | +1.581 |
tti | +1.518 |
HAEL | +1.505 |
tails | +1.460 |
Heck | +1.458 |
Neg logit contributions | |
edIn | -2.199 |
icians | -1.914 |
itect | -1.914 |
ification | -1.890 |
ified | -1.884 |
Token | in |
Token ID | 287 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
edIn | +2.814 |
ification | +2.513 |
ified | +2.499 |
icians | +2.498 |
itect | +2.477 |
Neg logit contributions | |
berman | -1.808 |
HAEL | -1.733 |
tti | -1.727 |
tails | -1.684 |
mma | -1.629 |
Token | at |
Token ID | 379 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
edIn | +2.255 |
icians | +1.982 |
ification | +1.980 |
itect | +1.969 |
ified | +1.968 |
Neg logit contributions | |
berman | -1.668 |
HAEL | -1.603 |
tti | -1.601 |
tails | -1.556 |
Heck | -1.523 |
Token | least |
Token ID | 1551 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
berman | +0.672 |
tti | +0.651 |
HAEL | +0.645 |
tails | +0.633 |
Heck | +0.628 |
Neg logit contributions | |
edIn | -0.900 |
icians | -0.777 |
itect | -0.770 |
ification | -0.769 |
ified | -0.766 |
Token | one |
Token ID | 530 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
edIn | +0.690 |
icians | +0.607 |
ification | +0.605 |
itect | +0.603 |
ified | +0.601 |
Neg logit contributions | |
berman | -0.491 |
tti | -0.472 |
HAEL | -0.471 |
tails | -0.457 |
Heck | -0.450 |
Token | declass |
Token ID | 42794 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
berman | +1.742 |
tti | +1.683 |
HAEL | +1.651 |
Heck | +1.640 |
tails | +1.616 |
Neg logit contributions | |
edIn | -2.512 |
icians | -2.207 |
itect | -2.181 |
ification | -2.165 |
ified | -2.155 |
Token | ified |
Token ID | 1431 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ified | +5.520 |
ification | +5.341 |
edIn | +4.604 |
ifying | +3.921 |
ifiers | +3.871 |
Neg logit contributions | |
berman | -18.268 |
HAEL | -17.857 |
tails | -17.692 |
senal | -17.676 |
tti | -17.674 |
Token | document |
Token ID | 3188 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
edIn | +4.355 |
ification | +3.940 |
ified | +3.916 |
icians | +3.838 |
itect | +3.833 |
Neg logit contributions | |
berman | -3.584 |
HAEL | -3.479 |
tti | -3.443 |
tails | -3.381 |
mma | -3.267 |
Token | dating |
Token ID | 10691 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
edIn | +1.817 |
icians | +1.616 |
ification | +1.615 |
ified | +1.605 |
itect | +1.605 |
Neg logit contributions | |
berman | -1.091 |
HAEL | -1.043 |
tti | -1.041 |
tails | -1.008 |
Heck | -0.985 |
Token | from |
Token ID | 422 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
edIn | +5.101 |
ification | +4.651 |
ified | +4.599 |
icians | +4.587 |
ifiers | +4.487 |
Neg logit contributions | |
berman | -3.455 |
HAEL | -3.355 |
tti | -3.284 |
tails | -3.245 |
mma | -3.147 |
Token | late |
Token ID | 2739 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
edIn | +2.266 |
ification | +1.977 |
icians | +1.963 |
ified | +1.957 |
itect | +1.942 |
Neg logit contributions | |
berman | -2.187 |
HAEL | -2.123 |
tti | -2.107 |
tails | -2.073 |
mma | -2.027 |
Token | - |
Token ID | 12 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
edIn | +0.187 |
icians | +0.163 |
itect | +0.162 |
ification | +0.161 |
ified | +0.160 |
Neg logit contributions | |
berman | -0.149 |
tti | -0.144 |
HAEL | -0.144 |
tails | -0.140 |
Heck | -0.137 |
Token | o |
Token ID | 78 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
edIn | +1.921 |
ification | +1.669 |
icians | +1.669 |
ified | +1.660 |
itect | +1.657 |
Neg logit contributions | |
berman | -1.690 |
tti | -1.632 |
HAEL | -1.631 |
tails | -1.583 |
Heck | -1.569 |
Token | vert |
Token ID | 1851 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
berman | +1.503 |
tti | +1.416 |
tails | +1.373 |
HAEL | +1.370 |
Gamble | +1.356 |
Neg logit contributions | |
edIn | -1.810 |
icians | -1.594 |
itect | -1.577 |
ifiers | -1.558 |
ification | -1.556 |
Token | ime |
Token ID | 524 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
edIn | +1.934 |
ification | +1.701 |
icians | +1.694 |
itect | +1.691 |
ified | +1.688 |
Neg logit contributions | |
berman | -1.680 |
tti | -1.622 |
HAEL | -1.618 |
tails | -1.582 |
Heck | -1.548 |
Token | goal |
Token ID | 3061 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
edIn | +0.081 |
icians | +0.071 |
itect | +0.071 |
ification | +0.071 |
ified | +0.070 |
Neg logit contributions | |
berman | -0.060 |
tti | -0.058 |
HAEL | -0.058 |
tails | -0.056 |
Heck | -0.055 |
Token | clin |
Token ID | 5327 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
edIn | +1.212 |
icians | +1.073 |
ification | +1.069 |
itect | +1.066 |
ified | +1.063 |
Neg logit contributions | |
berman | -0.779 |
tti | -0.747 |
HAEL | -0.745 |
tails | -0.722 |
Heck | -0.709 |
Token | ched |
Token ID | 1740 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ified | +6.393 |
ification | +5.909 |
edIn | +5.710 |
icians | +5.085 |
ifiers | +5.051 |
Neg logit contributions | |
senal | -17.592 |
HAEL | -17.123 |
Gamble | -15.926 |
berman | -15.863 |
Heck | -15.777 |
Token | New |
Token ID | 968 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
edIn | +5.021 |
ified | +4.429 |
ification | +4.403 |
icians | +4.343 |
itect | +4.229 |
Neg logit contributions | |
berman | -4.370 |
HAEL | -4.271 |
tti | -4.214 |
tails | -4.092 |
mma | -4.023 |
Token | Jersey |
Token ID | 8221 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
edIn | +2.579 |
ification | +2.243 |
icians | +2.243 |
ified | +2.229 |
itect | +2.220 |
Neg logit contributions | |
berman | -2.061 |
HAEL | -2.010 |
tti | -1.996 |
tails | -1.935 |
mma | -1.911 |
Token | � |
Token ID | 447 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
edIn | +6.157 |
ification | +5.447 |
ified | +5.422 |
icians | +5.285 |
itect | +5.205 |
Neg logit contributions | |
berman | -5.995 |
HAEL | -5.971 |
tti | -5.753 |
tails | -5.690 |
mma | -5.656 |
Token | � |
Token ID | 247 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
edIn | +1.180 |
icians | +0.997 |
ification | +0.993 |
ified | +0.992 |
itect | +0.988 |
Neg logit contributions | |
berman | -1.342 |
tti | -1.304 |
HAEL | -1.295 |
tails | -1.289 |
Heck | -1.253 |
Token | and |
Token ID | 290 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
berman | +0.397 |
tti | +0.383 |
HAEL | +0.378 |
tails | +0.368 |
Heck | +0.367 |
Neg logit contributions | |
edIn | -0.676 |
icians | -0.597 |
ification | -0.594 |
itect | -0.594 |
ified | -0.591 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
berman | +2.128 |
tti | +2.065 |
HAEL | +2.047 |
Heck | +1.993 |
Gamble | +1.985 |
Neg logit contributions | |
edIn | -3.395 |
icians | -2.975 |
itect | -2.975 |
ification | -2.948 |
ified | -2.920 |
Token | Giant |
Token ID | 17384 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
berman | +0.475 |
tti | +0.459 |
HAEL | +0.456 |
tails | +0.443 |
Heck | +0.439 |
Neg logit contributions | |
edIn | -0.801 |
icians | -0.708 |
ification | -0.706 |
itect | -0.705 |
ified | -0.702 |
Token | Peach |
Token ID | 33230 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
berman | +0.603 |
tti | +0.578 |
HAEL | +0.569 |
tails | +0.561 |
Heck | +0.554 |
Neg logit contributions | |
edIn | -1.039 |
icians | -0.921 |
ification | -0.918 |
itect | -0.916 |
ified | -0.910 |
Token | ( |
Token ID | 357 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
edIn | +0.589 |
icians | +0.526 |
ification | +0.525 |
itect | +0.523 |
ified | +0.522 |
Neg logit contributions | |
berman | -0.307 |
HAEL | -0.291 |
tti | -0.291 |
tails | -0.281 |
Heck | -0.274 |
Token | init |
Token ID | 15003 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
berman | +0.823 |
tti | +0.791 |
HAEL | +0.790 |
tails | +0.769 |
mma | +0.750 |
Neg logit contributions | |
edIn | -1.212 |
icians | -1.072 |
itect | -1.063 |
ification | -1.058 |
ified | -1.049 |
Token | ially |
Token ID | 1927 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
edIn | +8.375 |
ified | +7.954 |
ification | +7.857 |
itect | +7.111 |
icipated | +7.094 |
Neg logit contributions | |
berman | -14.205 |
HAEL | -14.021 |
tti | -13.445 |
HO | -13.337 |
mma | -13.259 |
Token | titled |
Token ID | 11946 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
edIn | +4.027 |
ification | +3.593 |
ified | +3.580 |
itect | +3.503 |
icians | +3.499 |
Neg logit contributions | |
berman | -3.701 |
HAEL | -3.561 |
tti | -3.509 |
tails | -3.451 |
mma | -3.373 |
Token | James |
Token ID | 3700 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
edIn | +3.628 |
ification | +3.239 |
ified | +3.231 |
icians | +3.218 |
itect | +3.209 |
Neg logit contributions | |
berman | -2.364 |
HAEL | -2.256 |
tti | -2.231 |
tails | -2.176 |
mma | -2.112 |
Token | and |
Token ID | 290 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
edIn | +2.968 |
ification | +2.619 |
icians | +2.615 |
ified | +2.607 |
itect | +2.599 |
Neg logit contributions | |
berman | -2.115 |
HAEL | -2.033 |
tti | -2.019 |
tails | -1.959 |
Heck | -1.917 |
Token | the |
Token ID | 262 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
edIn | +2.114 |
ification | +1.861 |
icians | +1.860 |
ified | +1.851 |
itect | +1.844 |
Neg logit contributions | |
berman | -1.595 |
HAEL | -1.536 |
tti | -1.524 |
tails | -1.480 |
mma | -1.451 |
Token | dinosaurs |
Token ID | 27199 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
berman | +3.517 |
tti | +3.453 |
HAEL | +3.353 |
tails | +3.318 |
Heck | +3.316 |
Neg logit contributions | |
edIn | -4.601 |
icians | -3.960 |
itect | -3.930 |
ification | -3.847 |
icter | -3.810 |
Token | do |
Token ID | 466 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
edIn | +4.593 |
ification | +4.229 |
ified | +4.207 |
icians | +4.123 |
itect | +4.085 |
Neg logit contributions | |
berman | -4.813 |
HAEL | -4.775 |
tti | -4.673 |
tails | -4.601 |
mma | -4.511 |
Token | while |
Token ID | 981 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
berman | +3.507 |
tti | +3.286 |
HAEL | +3.244 |
Heck | +3.134 |
tails | +3.126 |
Neg logit contributions | |
edIn | -7.295 |
icians | -6.410 |
itect | -6.327 |
ification | -6.240 |
icter | -6.239 |
Token | nesting |
Token ID | 46282 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
edIn | +0.255 |
icians | +0.223 |
ification | +0.221 |
itect | +0.221 |
ified | +0.220 |
Neg logit contributions | |
berman | -0.201 |
tti | -0.193 |
HAEL | -0.192 |
tails | -0.189 |
Heck | -0.186 |
Token | ( |
Token ID | 357 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
berman | +0.932 |
tti | +0.884 |
HAEL | +0.875 |
tails | +0.857 |
Heck | +0.837 |
Neg logit contributions | |
edIn | -1.889 |
icians | -1.700 |
ification | -1.684 |
itect | -1.680 |
ified | -1.670 |
Token | scient |
Token ID | 25346 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
edIn | +0.087 |
icians | +0.076 |
ification | +0.075 |
itect | +0.075 |
ified | +0.075 |
Neg logit contributions | |
berman | -0.070 |
tti | -0.067 |
HAEL | -0.067 |
tails | -0.065 |
Heck | -0.064 |
Token | ists |
Token ID | 1023 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
edIn | +8.319 |
icians | +7.973 |
ified | +7.836 |
ification | +7.812 |
ifiers | +7.342 |
Neg logit contributions | |
HAEL | -13.794 |
mma | -13.760 |
berman | -13.716 |
tti | -13.592 |
Heck | -13.209 |
Token | think |
Token ID | 892 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
edIn | +5.363 |
ification | +4.900 |
ified | +4.886 |
icians | +4.834 |
itect | +4.751 |
Neg logit contributions | |
berman | -4.909 |
HAEL | -4.849 |
tti | -4.765 |
tails | -4.707 |
mma | -4.607 |
Token | some |
Token ID | 617 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
edIn | +2.732 |
ification | +2.415 |
icians | +2.400 |
ified | +2.395 |
itect | +2.371 |
Neg logit contributions | |
berman | -2.206 |
HAEL | -2.146 |
tti | -2.110 |
tails | -2.057 |
mma | -2.006 |
Token | species |
Token ID | 4693 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
berman | +0.263 |
tti | +0.253 |
HAEL | +0.251 |
tails | +0.245 |
Heck | +0.240 |
Neg logit contributions | |
edIn | -0.401 |
icians | -0.354 |
ification | -0.352 |
itect | -0.352 |
ified | -0.350 |
Token | sat |
Token ID | 3332 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
edIn | +3.060 |
ification | +2.711 |
icians | +2.697 |
ified | +2.692 |
itect | +2.684 |
Neg logit contributions | |
berman | -2.537 |
HAEL | -2.463 |
tti | -2.443 |
tails | -2.387 |
Heck | -2.338 |
Token | arts |
Token ID | 10848 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
berman | +2.182 |
HAEL | +2.115 |
tti | +2.110 |
tails | +2.092 |
Gamble | +2.038 |
Neg logit contributions | |
edIn | -3.043 |
itect | -2.625 |
icians | -2.621 |
ified | -2.587 |
ification | -2.584 |
Token | in |
Token ID | 287 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
edIn | +1.093 |
icians | +0.969 |
ification | +0.965 |
itect | +0.963 |
ified | +0.961 |
Neg logit contributions | |
berman | -0.647 |
tti | -0.620 |
HAEL | -0.619 |
tails | -0.600 |
Heck | -0.587 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
edIn | +2.916 |
ification | +2.536 |
icians | +2.533 |
itect | +2.517 |
ified | +2.515 |
Neg logit contributions | |
berman | -2.635 |
HAEL | -2.551 |
tti | -2.539 |
tails | -2.473 |
mma | -2.425 |
Token | post |
Token ID | 1281 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
edIn | +0.854 |
icians | +0.761 |
ification | +0.761 |
ified | +0.757 |
itect | +0.755 |
Neg logit contributions | |
berman | -0.499 |
HAEL | -0.478 |
tti | -0.475 |
tails | -0.459 |
mma | -0.447 |
Token | - |
Token ID | 12 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
berman | +2.842 |
tti | +2.730 |
HAEL | +2.666 |
Heck | +2.633 |
Gamble | +2.620 |
Neg logit contributions | |
edIn | -4.194 |
icians | -3.606 |
itect | -3.582 |
ification | -3.540 |
ified | -3.497 |
Token | conf |
Token ID | 10414 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
berman | +0.993 |
tti | +0.946 |
HAEL | +0.936 |
tails | +0.928 |
Heck | +0.898 |
Neg logit contributions | |
edIn | -1.541 |
icians | -1.358 |
itect | -1.346 |
ification | -1.344 |
ified | -1.339 |
Token | lict |
Token ID | 13758 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
edIn | +6.166 |
ification | +5.846 |
ified | +5.795 |
essed | +5.138 |
icians | +4.834 |
Neg logit contributions | |
HAEL | -15.875 |
senal | -15.849 |
tti | -15.262 |
berman | -15.250 |
Heck | -14.884 |
Token | capital |
Token ID | 3139 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
berman | +0.427 |
tti | +0.409 |
HAEL | +0.408 |
tails | +0.396 |
Heck | +0.389 |
Neg logit contributions | |
edIn | -0.681 |
icians | -0.603 |
ification | -0.601 |
itect | -0.599 |
ified | -0.598 |
Token | and |
Token ID | 290 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
edIn | +1.115 |
icians | +0.994 |
ification | +0.992 |
itect | +0.988 |
ified | +0.987 |
Neg logit contributions | |
berman | -0.606 |
tti | -0.577 |
HAEL | -0.577 |
tails | -0.557 |
Heck | -0.545 |
Token | her |
Token ID | 607 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
edIn | +2.099 |
icians | +1.851 |
ification | +1.848 |
ified | +1.837 |
itect | +1.836 |
Neg logit contributions | |
berman | -1.568 |
HAEL | -1.512 |
tti | -1.505 |
tails | -1.465 |
Heck | -1.435 |
Token | drive |
Token ID | 3708 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
edIn | +1.792 |
ification | +1.578 |
icians | +1.574 |
ified | +1.567 |
itect | +1.558 |
Neg logit contributions | |
berman | -1.325 |
HAEL | -1.273 |
tti | -1.266 |
tails | -1.229 |
Heck | -1.206 |
Token | called |
Token ID | 1444 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
edIn | +5.995 |
ified | +5.513 |
ification | +5.475 |
icians | +5.311 |
ifiers | +5.286 |
Neg logit contributions | |
berman | -6.187 |
HAEL | -6.050 |
tails | -5.846 |
tti | -5.775 |
mma | -5.724 |
Token | these |
Token ID | 777 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
berman | +1.465 |
tti | +1.402 |
HAEL | +1.374 |
Heck | +1.349 |
tails | +1.346 |
Neg logit contributions | |
edIn | -2.468 |
itect | -2.207 |
icians | -2.185 |
ification | -2.173 |
ified | -2.153 |
Token | accusations |
Token ID | 14227 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
berman | +3.339 |
tti | +3.237 |
tails | +3.160 |
Heck | +3.150 |
HAEL | +3.101 |
Neg logit contributions | |
edIn | -4.834 |
itect | -4.289 |
icians | -4.188 |
ification | -4.122 |
icter | -4.108 |
Token | a |
Token ID | 257 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
berman | +0.458 |
tti | +0.439 |
HAEL | +0.438 |
tails | +0.426 |
Heck | +0.420 |
Neg logit contributions | |
edIn | -0.645 |
icians | -0.567 |
itect | -0.563 |
ification | -0.563 |
ified | -0.560 |
Token | ' |
Token ID | 705 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
edIn | +3.070 |
ification | +2.708 |
icians | +2.694 |
ified | +2.693 |
itect | +2.679 |
Neg logit contributions | |
berman | -2.350 |
HAEL | -2.270 |
tti | -2.261 |
tails | -2.188 |
mma | -2.153 |
Token | cons |
Token ID | 5936 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
edIn | +1.018 |
icians | +0.886 |
ification | +0.881 |
itect | +0.879 |
ified | +0.876 |
Neg logit contributions | |
berman | -0.853 |
tti | -0.822 |
HAEL | -0.819 |
tails | -0.802 |
Heck | -0.786 |
Token | piracy |
Token ID | 8703 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
edIn | +5.803 |
ification | +5.676 |
ified | +5.531 |
ervatives | +5.206 |
ularity | +5.044 |
Neg logit contributions | |
HAEL | -16.031 |
berman | -15.573 |
tails | -15.310 |
tti | -15.301 |
senal | -15.061 |
Token | theory |
Token ID | 4583 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
edIn | +3.898 |
ification | +3.396 |
ified | +3.349 |
icians | +3.314 |
itect | +3.291 |
Neg logit contributions | |
berman | -5.640 |
HAEL | -5.533 |
tti | -5.453 |
tails | -5.404 |
mma | -5.285 |
Token | .' |
Token ID | 2637 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
edIn | +4.553 |
ification | +4.075 |
ified | +4.037 |
icians | +3.999 |
itect | +3.947 |
Neg logit contributions | |
berman | -4.552 |
HAEL | -4.460 |
tti | -4.404 |
tails | -4.291 |
Heck | -4.210 |
Token |
|
Token ID | 198 |
Feature activation | +9.70e-03 |
Pos logit contributions | |
edIn | +0.482 |
icians | +0.420 |
itect | +0.419 |
ification | +0.419 |
ified | +0.415 |
Neg logit contributions | |
berman | -0.378 |
tti | -0.365 |
HAEL | -0.363 |
tails | -0.354 |
Heck | -0.351 |
Token |
|
Token ID | 198 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
berman | +0.028 |
HAEL | +0.027 |
tti | +0.027 |
tails | +0.027 |
Heck | +0.026 |
Neg logit contributions | |
edIn | -0.033 |
ification | -0.029 |
icians | -0.028 |
ified | -0.028 |
itect | -0.028 |
Token | one |
Token ID | 530 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
berman | +0.452 |
tti | +0.435 |
HAEL | +0.434 |
tails | +0.420 |
Heck | +0.416 |
Neg logit contributions | |
edIn | -0.605 |
icians | -0.528 |
ification | -0.527 |
itect | -0.525 |
ified | -0.523 |
Token | of |
Token ID | 286 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
edIn | +1.132 |
icians | +1.012 |
ification | +1.011 |
ified | +1.005 |
itect | +1.005 |
Neg logit contributions | |
berman | -0.596 |
HAEL | -0.567 |
tti | -0.567 |
tails | -0.548 |
mma | -0.532 |
Token | the |
Token ID | 262 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
edIn | +0.384 |
icians | +0.338 |
ification | +0.337 |
itect | +0.336 |
ified | +0.335 |
Neg logit contributions | |
berman | -0.260 |
HAEL | -0.249 |
tti | -0.249 |
tails | -0.241 |
Heck | -0.238 |
Token | more |
Token ID | 517 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
edIn | +1.677 |
ification | +1.476 |
icians | +1.475 |
ified | +1.467 |
itect | +1.466 |
Neg logit contributions | |
berman | -1.285 |
HAEL | -1.234 |
tti | -1.230 |
tails | -1.198 |
Heck | -1.175 |
Token | devastating |
Token ID | 14101 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
edIn | +1.695 |
ification | +1.504 |
icians | +1.503 |
ified | +1.496 |
itect | +1.491 |
Neg logit contributions | |
berman | -1.057 |
HAEL | -1.012 |
tti | -1.010 |
tails | -0.978 |
Heck | -0.955 |
Token | sequ |
Token ID | 3107 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
berman | +0.733 |
tti | +0.704 |
HAEL | +0.701 |
tails | +0.682 |
Heck | +0.672 |
Neg logit contributions | |
edIn | -1.054 |
icians | -0.926 |
ification | -0.924 |
itect | -0.921 |
ified | -0.917 |
Token | ences |
Token ID | 3007 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
edIn | +8.943 |
icians | +8.447 |
ified | +8.326 |
ification | +8.258 |
ifiers | +7.989 |
Neg logit contributions | |
HAEL | -12.908 |
senal | -12.656 |
Heck | -12.225 |
Gamble | -12.084 |
mma | -11.911 |
Token | in |
Token ID | 287 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
edIn | +2.810 |
icians | +2.521 |
ification | +2.513 |
ified | +2.504 |
itect | +2.484 |
Neg logit contributions | |
berman | -1.602 |
HAEL | -1.524 |
tti | -1.517 |
tails | -1.484 |
mma | -1.434 |
Token | movie |
Token ID | 3807 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
edIn | +1.262 |
icians | +1.114 |
ification | +1.112 |
itect | +1.107 |
ified | +1.105 |
Neg logit contributions | |
berman | -0.840 |
tti | -0.805 |
HAEL | -0.804 |
tails | -0.780 |
Heck | -0.765 |
Token | history |
Token ID | 2106 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
berman | +0.263 |
tti | +0.254 |
HAEL | +0.252 |
tails | +0.246 |
Heck | +0.243 |
Neg logit contributions | |
edIn | -0.282 |
icians | -0.241 |
ification | -0.238 |
itect | -0.238 |
ified | -0.237 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
edIn | +1.248 |
icians | +1.122 |
ification | +1.120 |
ified | +1.115 |
itect | +1.112 |
Neg logit contributions | |
berman | -0.665 |
HAEL | -0.636 |
tti | -0.631 |
tails | -0.614 |
Heck | -0.596 |
Token | such |
Token ID | 884 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
edIn | +3.914 |
ification | +3.493 |
icians | +3.482 |
ified | +3.465 |
ifiers | +3.381 |
Neg logit contributions | |
berman | -2.832 |
HAEL | -2.741 |
tti | -2.698 |
tails | -2.644 |
mma | -2.584 |
Token | services |
Token ID | 2594 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
berman | +3.867 |
Heck | +3.766 |
tti | +3.694 |
Gamble | +3.637 |
HAEL | +3.619 |
Neg logit contributions | |
edIn | -7.606 |
itect | -6.885 |
icter | -6.698 |
icians | -6.689 |
osate | -6.618 |
Token | remains |
Token ID | 3793 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
berman | +3.299 |
tti | +3.141 |
HAEL | +3.099 |
Heck | +3.076 |
tails | +3.043 |
Neg logit contributions | |
edIn | -4.924 |
itect | -4.276 |
icians | -4.218 |
icter | -4.215 |
ification | -4.122 |
Token | a |
Token ID | 257 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
edIn | +1.001 |
ification | +0.881 |
icians | +0.877 |
ified | +0.877 |
itect | +0.866 |
Neg logit contributions | |
berman | -0.741 |
HAEL | -0.714 |
tti | -0.713 |
tails | -0.690 |
Gamble | -0.673 |
Token | min |
Token ID | 949 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
edIn | +2.286 |
ification | +2.003 |
icians | +2.002 |
ified | +1.995 |
itect | +1.984 |
Neg logit contributions | |
berman | -1.781 |
tti | -1.716 |
HAEL | -1.715 |
tails | -1.666 |
Heck | -1.624 |
Token | usc |
Token ID | 16241 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
ified | +5.770 |
ification | +5.702 |
edIn | +5.694 |
ificant | +5.242 |
icians | +5.220 |
Neg logit contributions | |
HAEL | -9.536 |
berman | -9.434 |
tti | -9.378 |
tails | -9.262 |
HO | -9.044 |
Token | ule |
Token ID | 2261 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
ification | +4.486 |
ified | +4.303 |
ularity | +3.803 |
edIn | +3.479 |
itect | +3.412 |
Neg logit contributions | |
senal | -18.470 |
berman | -17.497 |
tails | -17.237 |
tti | -16.812 |
Gamble | -16.600 |
Token | fraction |
Token ID | 13390 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
edIn | +3.245 |
ification | +2.882 |
ified | +2.878 |
icians | +2.827 |
itect | +2.792 |
Neg logit contributions | |
berman | -2.710 |
HAEL | -2.639 |
tti | -2.631 |
tails | -2.578 |
mma | -2.463 |
Token | of |
Token ID | 286 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
edIn | +2.029 |
icians | +1.820 |
ification | +1.819 |
ified | +1.811 |
itect | +1.804 |
Neg logit contributions | |
berman | -1.096 |
HAEL | -1.048 |
tti | -1.047 |
tails | -1.014 |
Heck | -0.978 |
Token | the |
Token ID | 262 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
edIn | +0.831 |
icians | +0.732 |
ification | +0.730 |
itect | +0.726 |
ified | +0.725 |
Neg logit contributions | |
berman | -0.586 |
tti | -0.563 |
HAEL | -0.562 |
tails | -0.546 |
Heck | -0.535 |
Token | school |
Token ID | 1524 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
edIn | +1.559 |
icians | +1.364 |
ification | +1.362 |
ified | +1.353 |
itect | +1.343 |
Neg logit contributions | |
berman | -1.281 |
tti | -1.236 |
HAEL | -1.234 |
tails | -1.201 |
mma | -1.176 |
Token | awareness |
Token ID | 47812 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
berman | +0.496 |
tti | +0.479 |
HAEL | +0.473 |
tails | +0.469 |
train | +0.455 |
Neg logit contributions | |
edIn | -0.634 |
icians | -0.553 |
itect | -0.547 |
ification | -0.540 |
ified | -0.539 |
Token | regarding |
Token ID | 5115 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
edIn | +5.207 |
ification | +4.840 |
ified | +4.757 |
icians | +4.724 |
itect | +4.669 |
Neg logit contributions | |
berman | -3.736 |
HAEL | -3.605 |
tti | -3.514 |
tails | -3.473 |
Heck | -3.392 |
Token | incorporation |
Token ID | 43619 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
edIn | +4.278 |
ification | +3.852 |
ified | +3.819 |
icians | +3.793 |
itect | +3.736 |
Neg logit contributions | |
berman | -3.311 |
HAEL | -3.244 |
tti | -3.191 |
tails | -3.104 |
mma | -3.031 |
Token | " |
Token ID | 1 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
berman | +0.442 |
tti | +0.421 |
HAEL | +0.418 |
tails | +0.406 |
Heck | +0.400 |
Neg logit contributions | |
edIn | -0.752 |
icians | -0.665 |
itect | -0.662 |
ification | -0.659 |
ified | -0.657 |
Token | ( |
Token ID | 357 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
berman | +0.541 |
tti | +0.517 |
HAEL | +0.514 |
tails | +0.497 |
Heck | +0.490 |
Neg logit contributions | |
edIn | -0.967 |
icians | -0.858 |
itect | -0.851 |
ification | -0.850 |
ified | -0.845 |
Token | Ne |
Token ID | 8199 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
edIn | +2.508 |
icians | +2.255 |
ification | +2.254 |
ified | +2.244 |
itect | +2.243 |
Neg logit contributions | |
berman | -1.091 |
HAEL | -1.035 |
tti | -1.031 |
tails | -0.990 |
Heck | -0.968 |
Token | h |
Token ID | 71 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ification | +5.249 |
ified | +5.139 |
icians | +4.758 |
itect | +4.744 |
edIn | +4.734 |
Neg logit contributions | |
senal | -16.804 |
HAEL | -15.350 |
unnecess | -15.145 |
Gamble | -14.746 |
tails | -14.453 |
Token | ring |
Token ID | 1806 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
edIn | +4.489 |
ification | +4.398 |
ified | +4.318 |
icians | +4.233 |
ifiers | +4.207 |
Neg logit contributions | |
senal | -5.019 |
HAEL | -4.524 |
Gamble | -4.513 |
berman | -4.465 |
tti | -4.418 |
Token | 86 |
Token ID | 9849 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
edIn | +5.386 |
ification | +4.829 |
ified | +4.821 |
icians | +4.746 |
itect | +4.737 |
Neg logit contributions | |
berman | -4.113 |
HAEL | -4.009 |
tti | -3.895 |
tails | -3.852 |
mma | -3.723 |
Token | ). |
Token ID | 737 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
berman | +2.334 |
tti | +2.273 |
HAEL | +2.259 |
mma | +2.220 |
tails | +2.201 |
Neg logit contributions | |
edIn | -2.125 |
icians | -1.791 |
ification | -1.759 |
itect | -1.755 |
ified | -1.739 |
Token | B |
Token ID | 347 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
edIn | +0.316 |
icians | +0.278 |
ification | +0.278 |
itect | +0.277 |
ified | +0.276 |
Neg logit contributions | |
berman | -0.221 |
tti | -0.212 |
HAEL | -0.212 |
tails | -0.206 |
Heck | -0.202 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
edIn | +7.955 |
ification | +7.312 |
icians | +7.302 |
ified | +7.252 |
itect | +7.155 |
Neg logit contributions | |
berman | -5.493 |
HAEL | -5.442 |
tti | -5.250 |
senal | -5.162 |
Gamble | -5.138 |
Token | Rand |
Token ID | 8790 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
edIn | +0.536 |
icians | +0.473 |
ification | +0.471 |
itect | +0.470 |
ified | +0.469 |
Neg logit contributions | |
berman | -0.347 |
tti | -0.333 |
HAEL | -0.332 |
tails | -0.322 |
Heck | -0.318 |
Token | Paul |
Token ID | 3362 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
edIn | +3.782 |
icians | +3.374 |
ification | +3.368 |
ified | +3.364 |
itect | +3.298 |
Neg logit contributions | |
berman | -4.362 |
HAEL | -4.269 |
tti | -4.206 |
tails | -4.201 |
mma | -4.147 |
Token | is |
Token ID | 318 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
edIn | +2.286 |
ification | +2.022 |
icians | +2.022 |
ified | +2.012 |
itect | +2.004 |
Neg logit contributions | |
berman | -1.564 |
HAEL | -1.501 |
tti | -1.499 |
tails | -1.454 |
Heck | -1.422 |
Token | " |
Token ID | 366 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
edIn | +1.990 |
ification | +1.757 |
icians | +1.750 |
ified | +1.745 |
itect | +1.733 |
Neg logit contributions | |
berman | -1.613 |
HAEL | -1.558 |
tti | -1.550 |
tails | -1.514 |
Heck | -1.472 |
Token | bas |
Token ID | 12093 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
berman | +0.646 |
tti | +0.620 |
HAEL | +0.612 |
tails | +0.608 |
train | +0.593 |
Neg logit contributions | |
edIn | -0.906 |
icians | -0.797 |
itect | -0.790 |
ification | -0.783 |
ified | -0.778 |
Token | ically |
Token ID | 1146 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
edIn | +5.899 |
ified | +5.323 |
icians | +5.314 |
ification | +5.308 |
itect | +4.749 |
Neg logit contributions | |
tails | -15.688 |
HAEL | -15.611 |
tti | -15.508 |
berman | -15.482 |
senal | -15.402 |
Token | an |
Token ID | 281 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
edIn | +1.024 |
icians | +0.892 |
itect | +0.888 |
ification | +0.885 |
ified | +0.878 |
Neg logit contributions | |
berman | -0.783 |
tti | -0.749 |
HAEL | -0.747 |
tails | -0.731 |
Heck | -0.722 |
Token | isolation |
Token ID | 15133 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
edIn | +0.590 |
ification | +0.524 |
icians | +0.523 |
ified | +0.521 |
itect | +0.521 |
Neg logit contributions | |
berman | -0.367 |
HAEL | -0.352 |
tti | -0.351 |
tails | -0.340 |
mma | -0.332 |
Token | ist |
Token ID | 396 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
edIn | +0.160 |
icians | +0.138 |
ification | +0.137 |
itect | +0.136 |
ified | +0.136 |
Neg logit contributions | |
berman | -0.160 |
HAEL | -0.154 |
tti | -0.154 |
tails | -0.150 |
Heck | -0.148 |
Token | ," |
Token ID | 553 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
berman | +0.295 |
tti | +0.280 |
HAEL | +0.279 |
tails | +0.271 |
Heck | +0.270 |
Neg logit contributions | |
edIn | -0.443 |
icians | -0.390 |
ification | -0.386 |
itect | -0.386 |
ified | -0.385 |
Token | You |
Token ID | 921 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
berman | +0.005 |
tti | +0.005 |
HAEL | +0.005 |
tails | +0.005 |
Heck | +0.005 |
Neg logit contributions | |
edIn | -0.008 |
ification | -0.007 |
icians | -0.007 |
ified | -0.007 |
itect | -0.007 |
Token | will |
Token ID | 481 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
edIn | +2.833 |
ification | +2.494 |
ified | +2.463 |
itect | +2.429 |
icians | +2.403 |
Neg logit contributions | |
berman | -3.823 |
HAEL | -3.761 |
tti | -3.746 |
senal | -3.654 |
tails | -3.651 |
Token | receive |
Token ID | 3328 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
edIn | +3.163 |
ification | +2.840 |
ified | +2.805 |
icians | +2.698 |
itect | +2.694 |
Neg logit contributions | |
berman | -4.934 |
tti | -4.852 |
HAEL | -4.828 |
senal | -4.739 |
tails | -4.704 |
Token | emails |
Token ID | 7237 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
edIn | +3.083 |
ification | +2.792 |
ified | +2.776 |
icians | +2.769 |
ifiers | +2.704 |
Neg logit contributions | |
berman | -2.916 |
tti | -2.845 |
HAEL | -2.809 |
mma | -2.704 |
tails | -2.699 |
Token | containing |
Token ID | 7268 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
edIn | +1.083 |
ification | +0.943 |
ified | +0.929 |
icians | +0.922 |
itect | +0.898 |
Neg logit contributions | |
berman | -1.576 |
tti | -1.544 |
HAEL | -1.542 |
tails | -1.505 |
mma | -1.483 |
Token | news |
Token ID | 1705 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
edIn | +3.824 |
ification | +3.518 |
ified | +3.489 |
icians | +3.361 |
ifiers | +3.292 |
Neg logit contributions | |
berman | -4.078 |
HAEL | -4.074 |
senal | -3.997 |
tti | -3.989 |
tails | -3.881 |
Token | content |
Token ID | 2695 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
ification | +6.569 |
ified | +6.225 |
edIn | +6.139 |
icians | +5.739 |
ifiers | +5.663 |
Neg logit contributions | |
senal | -15.298 |
HAEL | -13.598 |
berman | -13.399 |
tti | -13.388 |
mma | -12.947 |
Token | , |
Token ID | 837 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
edIn | +5.762 |
ification | +5.356 |
ified | +5.298 |
icians | +5.288 |
itect | +5.095 |
Neg logit contributions | |
berman | -4.514 |
senal | -4.336 |
HAEL | -4.232 |
tti | -4.204 |
tails | -4.080 |
Token | updates |
Token ID | 5992 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
edIn | +4.244 |
icians | +3.746 |
ification | +3.689 |
itect | +3.498 |
ified | +3.486 |
Neg logit contributions | |
berman | -8.493 |
senal | -8.479 |
HAEL | -8.440 |
tti | -8.227 |
tails | -8.108 |
Token | and |
Token ID | 290 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
edIn | +6.043 |
ification | +6.024 |
ified | +5.930 |
icians | +5.706 |
itect | +5.464 |
Neg logit contributions | |
senal | -11.333 |
berman | -10.599 |
HAEL | -10.463 |
tti | -10.222 |
tails | -10.144 |
Token | promotions |
Token ID | 20699 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
edIn | +4.050 |
ification | +3.579 |
ified | +3.565 |
icians | +3.467 |
itect | +3.377 |
Neg logit contributions | |
berman | -4.399 |
HAEL | -4.382 |
tti | -4.338 |
senal | -4.247 |
mma | -4.247 |
Token | , |
Token ID | 11 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
berman | +2.870 |
tti | +2.787 |
HAEL | +2.718 |
Heck | +2.635 |
Gamble | +2.623 |
Neg logit contributions | |
edIn | -5.705 |
icians | -4.974 |
itect | -4.971 |
ification | -4.921 |
ified | -4.901 |
Token | it |
Token ID | 340 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
berman | +0.636 |
tti | +0.613 |
HAEL | +0.609 |
tails | +0.591 |
Heck | +0.586 |
Neg logit contributions | |
edIn | -0.851 |
icians | -0.742 |
itect | -0.738 |
ification | -0.737 |
ified | -0.734 |
Token | � |
Token ID | 447 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
tti | +4.554 |
berman | +4.543 |
HAEL | +4.358 |
tails | +4.288 |
train | +4.229 |
Neg logit contributions | |
edIn | -5.934 |
itect | -4.914 |
icians | -4.914 |
ification | -4.868 |
ifiers | -4.866 |
Token | � |
Token ID | 247 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
berman | +3.004 |
tti | +2.917 |
HAEL | +2.902 |
tails | +2.822 |
Heck | +2.803 |
Neg logit contributions | |
edIn | -3.413 |
icians | -2.973 |
ification | -2.963 |
itect | -2.936 |
ified | -2.926 |
Token | s |
Token ID | 82 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
berman | +1.842 |
tti | +1.830 |
tails | +1.766 |
HAEL | +1.765 |
mma | +1.717 |
Neg logit contributions | |
edIn | -2.740 |
itect | -2.358 |
icians | -2.358 |
ification | -2.354 |
ified | -2.342 |
Token | always |
Token ID | 1464 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
berman | +2.951 |
tti | +2.878 |
HAEL | +2.829 |
Gamble | +2.754 |
Heck | +2.746 |
Neg logit contributions | |
edIn | -4.402 |
itect | -3.793 |
icians | -3.774 |
ification | -3.747 |
ified | -3.719 |
Token | men |
Token ID | 1450 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
tti | +5.625 |
berman | +5.601 |
Gamble | +5.475 |
HAEL | +5.425 |
Heck | +5.361 |
Neg logit contributions | |
edIn | -8.795 |
icter | -7.342 |
itect | -7.342 |
icians | -7.313 |
ification | -7.238 |
Token | . |
Token ID | 13 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
berman | +1.428 |
tti | +1.372 |
HAEL | +1.336 |
tails | +1.285 |
Heck | +1.276 |
Neg logit contributions | |
edIn | -2.699 |
icians | -2.340 |
itect | -2.336 |
ification | -2.317 |
ified | -2.307 |
Token | Then |
Token ID | 3244 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
berman | +1.538 |
tti | +1.498 |
HAEL | +1.483 |
Heck | +1.457 |
tails | +1.435 |
Neg logit contributions | |
edIn | -2.402 |
icians | -2.111 |
ification | -2.082 |
itect | -2.080 |
ified | -2.075 |
Token | I |
Token ID | 314 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
berman | +2.649 |
tti | +2.549 |
HAEL | +2.507 |
tails | +2.434 |
Heck | +2.415 |
Neg logit contributions | |
edIn | -4.104 |
icians | -3.531 |
itect | -3.524 |
ification | -3.499 |
ified | -3.495 |
Token | � |
Token ID | 447 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
berman | +1.833 |
tti | +1.798 |
HAEL | +1.748 |
tails | +1.700 |
Heck | +1.687 |
Neg logit contributions | |
edIn | -2.258 |
icians | -1.896 |
itect | -1.892 |
ification | -1.881 |
ified | -1.872 |
Token | About |
Token ID | 8585 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
edIn | +0.725 |
icians | +0.640 |
ification | +0.639 |
itect | +0.636 |
ified | +0.635 |
Neg logit contributions | |
berman | -0.489 |
tti | -0.469 |
HAEL | -0.469 |
tails | -0.455 |
Heck | -0.446 |
Token | that |
Token ID | 326 |
Feature activation | +8.32e-03 |
Pos logit contributions | |
berman | +0.287 |
tti | +0.276 |
HAEL | +0.275 |
tails | +0.267 |
Heck | +0.263 |
Neg logit contributions | |
edIn | -0.404 |
icians | -0.355 |
ification | -0.354 |
itect | -0.353 |
ified | -0.352 |
Token | time |
Token ID | 640 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
berman | +0.020 |
tti | +0.020 |
HAEL | +0.020 |
tails | +0.019 |
Heck | +0.019 |
Neg logit contributions | |
edIn | -0.032 |
icians | -0.028 |
ification | -0.028 |
itect | -0.028 |
ified | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
berman | +0.732 |
tti | +0.701 |
HAEL | +0.698 |
tails | +0.674 |
Heck | +0.664 |
Neg logit contributions | |
edIn | -1.245 |
icians | -1.105 |
ification | -1.101 |
itect | -1.099 |
ified | -1.095 |
Token | the |
Token ID | 262 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
edIn | +0.080 |
icians | +0.071 |
ification | +0.071 |
itect | +0.070 |
ified | +0.070 |
Neg logit contributions | |
berman | -0.053 |
HAEL | -0.050 |
tti | -0.050 |
tails | -0.049 |
Heck | -0.048 |
Token | L |
Token ID | 406 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
edIn | +0.877 |
icians | +0.776 |
ification | +0.776 |
ified | +0.771 |
itect | +0.771 |
Neg logit contributions | |
berman | -0.583 |
HAEL | -0.558 |
tti | -0.556 |
tails | -0.540 |
Heck | -0.528 |
Token | SO |
Token ID | 15821 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
berman | +6.262 |
HAEL | +6.109 |
tti | +6.066 |
HO | +6.014 |
DI | +5.876 |
Neg logit contributions | |
edIn | -9.086 |
itect | -7.803 |
ification | -7.679 |
icians | -7.593 |
ifiers | -7.571 |
Token | came |
Token ID | 1625 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
berman | +1.613 |
tti | +1.567 |
HAEL | +1.561 |
tails | +1.508 |
Heck | +1.489 |
Neg logit contributions | |
edIn | -2.223 |
icians | -1.937 |
ification | -1.924 |
itect | -1.921 |
ified | -1.911 |
Token | up |
Token ID | 510 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
berman | +1.925 |
tti | +1.844 |
HAEL | +1.784 |
tails | +1.768 |
Heck | +1.748 |
Neg logit contributions | |
edIn | -3.582 |
itect | -3.154 |
icians | -3.151 |
ification | -3.074 |
ified | -3.066 |
Token | on |
Token ID | 319 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
edIn | +0.626 |
icians | +0.557 |
ification | +0.556 |
itect | +0.553 |
ified | +0.553 |
Neg logit contributions | |
berman | -0.356 |
tti | -0.340 |
HAEL | -0.339 |
tails | -0.328 |
Heck | -0.321 |
Token | tower |
Token ID | 10580 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
berman | +1.568 |
tti | +1.522 |
HAEL | +1.498 |
tails | +1.458 |
Heck | +1.446 |
Neg logit contributions | |
edIn | -2.313 |
icians | -2.031 |
itect | -2.028 |
ification | -2.019 |
ified | -2.007 |
Token | as |
Token ID | 355 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
berman | +0.297 |
tti | +0.282 |
HAEL | +0.281 |
tails | +0.273 |
Heck | +0.267 |
Neg logit contributions | |
edIn | -0.558 |
icians | -0.496 |
itect | -0.494 |
ification | -0.494 |
ified | -0.491 |
Token | much |
Token ID | 881 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
edIn | +0.824 |
icians | +0.692 |
ification | +0.689 |
itect | +0.686 |
ified | +0.684 |
Neg logit contributions | |
berman | -1.051 |
tti | -1.019 |
HAEL | -1.018 |
tails | -0.997 |
Heck | -0.984 |
Token | as |
Token ID | 355 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
berman | +3.329 |
tti | +3.160 |
Heck | +3.070 |
HAEL | +3.054 |
Gamble | +3.026 |
Neg logit contributions | |
edIn | -6.524 |
icians | -5.820 |
itect | -5.784 |
ification | -5.696 |
ified | -5.635 |
Token | the |
Token ID | 262 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
berman | +0.222 |
tti | +0.213 |
HAEL | +0.213 |
tails | +0.207 |
Heck | +0.205 |
Neg logit contributions | |
edIn | -0.305 |
icians | -0.268 |
ification | -0.267 |
itect | -0.267 |
ified | -0.266 |
Token | U |
Token ID | 471 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
berman | +0.074 |
tti | +0.071 |
HAEL | +0.070 |
tails | +0.068 |
Heck | +0.067 |
Neg logit contributions | |
edIn | -0.112 |
icians | -0.099 |
ification | -0.099 |
itect | -0.099 |
ified | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
berman | +2.512 |
tti | +2.395 |
HAEL | +2.348 |
tails | +2.267 |
mma | +2.232 |
Neg logit contributions | |
edIn | -5.751 |
icians | -5.113 |
itect | -5.082 |
ification | -5.047 |
icter | -5.043 |
Token | S |
Token ID | 50 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
berman | +3.212 |
tti | +3.023 |
HAEL | +2.958 |
HO | +2.937 |
Heck | +2.824 |
Neg logit contributions | |
edIn | -10.103 |
icter | -9.232 |
itect | -9.054 |
icians | -8.996 |
icipated | -8.906 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
berman | +1.310 |
tti | +1.228 |
HAEL | +1.226 |
tails | +1.173 |
Heck | +1.158 |
Neg logit contributions | |
edIn | -2.855 |
icians | -2.541 |
ification | -2.535 |
itect | -2.530 |
ified | -2.514 |
Token | did |
Token ID | 750 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
berman | +3.301 |
tti | +3.107 |
Heck | +3.075 |
HAEL | +3.047 |
Gamble | +3.012 |
Neg logit contributions | |
edIn | -5.671 |
icians | -5.057 |
ification | -5.030 |
itect | -5.010 |
ifiers | -4.979 |
Token | on |
Token ID | 319 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
berman | +1.877 |
tti | +1.787 |
HAEL | +1.746 |
Heck | +1.703 |
tails | +1.689 |
Neg logit contributions | |
edIn | -3.838 |
icians | -3.410 |
itect | -3.391 |
ification | -3.356 |
ified | -3.336 |
Token | passenger |
Token ID | 11849 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
berman | +1.591 |
tti | +1.511 |
HAEL | +1.497 |
Heck | +1.477 |
tails | +1.477 |
Neg logit contributions | |
edIn | -2.394 |
icians | -2.120 |
itect | -2.119 |
ification | -2.095 |
ified | -2.079 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
edIn | +3.298 |
ification | +2.958 |
ified | +2.938 |
itect | +2.936 |
icians | +2.930 |
Neg logit contributions | |
berman | -1.991 |
HAEL | -1.909 |
tti | -1.882 |
tails | -1.853 |
mma | -1.799 |
Token | Because |
Token ID | 4362 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
edIn | +0.551 |
icians | +0.486 |
ification | +0.484 |
itect | +0.482 |
ified | +0.481 |
Neg logit contributions | |
berman | -0.378 |
tti | -0.363 |
HAEL | -0.363 |
tails | -0.352 |
Heck | -0.347 |
Token | despite |
Token ID | 3805 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
berman | +0.147 |
tti | +0.141 |
HAEL | +0.141 |
tails | +0.136 |
Heck | +0.134 |
Neg logit contributions | |
edIn | -0.222 |
icians | -0.196 |
ification | -0.195 |
itect | -0.195 |
ified | -0.194 |
Token | his |
Token ID | 465 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
edIn | +4.928 |
ification | +4.350 |
ified | +4.312 |
icians | +4.287 |
itect | +4.277 |
Neg logit contributions | |
berman | -4.093 |
HAEL | -3.945 |
tti | -3.925 |
tails | -3.848 |
mma | -3.791 |
Token | best |
Token ID | 1266 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
edIn | +1.052 |
icians | +0.926 |
ification | +0.924 |
itect | +0.919 |
ified | +0.918 |
Neg logit contributions | |
berman | -0.743 |
tti | -0.713 |
HAEL | -0.713 |
tails | -0.692 |
Heck | -0.679 |
Token | efforts |
Token ID | 4040 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
edIn | +0.689 |
icians | +0.622 |
ification | +0.621 |
itect | +0.619 |
ified | +0.618 |
Neg logit contributions | |
berman | -0.254 |
tti | -0.238 |
HAEL | -0.237 |
tails | -0.227 |
Heck | -0.220 |
Token | , |
Token ID | 11 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
berman | +3.672 |
tti | +3.578 |
HAEL | +3.480 |
Heck | +3.405 |
HO | +3.349 |
Neg logit contributions | |
edIn | -8.284 |
icians | -7.317 |
itect | -7.278 |
ified | -7.171 |
ifiers | -7.168 |
Token | the |
Token ID | 262 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
berman | +0.480 |
HAEL | +0.463 |
tti | +0.463 |
Heck | +0.446 |
tails | +0.446 |
Neg logit contributions | |
edIn | -0.670 |
icians | -0.587 |
itect | -0.582 |
ification | -0.580 |
ified | -0.579 |
Token | life |
Token ID | 1204 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
berman | +0.519 |
tti | +0.499 |
HAEL | +0.496 |
tails | +0.485 |
Heck | +0.481 |
Neg logit contributions | |
edIn | -0.731 |
icians | -0.640 |
ification | -0.635 |
itect | -0.634 |
ified | -0.631 |
Token | could |
Token ID | 714 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
berman | +0.110 |
tti | +0.106 |
HAEL | +0.105 |
tails | +0.102 |
Heck | +0.101 |
Neg logit contributions | |
edIn | -0.183 |
icians | -0.161 |
itect | -0.161 |
ification | -0.160 |
ified | -0.160 |
Token | never |
Token ID | 1239 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
berman | +0.918 |
tti | +0.888 |
HAEL | +0.880 |
tails | +0.861 |
Heck | +0.846 |
Neg logit contributions | |
edIn | -1.129 |
icians | -0.966 |
ification | -0.964 |
itect | -0.964 |
ified | -0.959 |
Token | medical |
Token ID | 3315 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
edIn | +0.950 |
icians | +0.835 |
ification | +0.833 |
itect | +0.830 |
ified | +0.829 |
Neg logit contributions | |
berman | -0.684 |
tti | -0.656 |
HAEL | -0.656 |
tails | -0.637 |
Heck | -0.625 |
Token | school |
Token ID | 1524 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
edIn | +0.219 |
icians | +0.193 |
itect | +0.193 |
ification | +0.192 |
ified | +0.191 |
Neg logit contributions | |
berman | -0.129 |
tti | -0.123 |
HAEL | -0.123 |
tails | -0.120 |
Heck | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
edIn | +3.886 |
ification | +3.517 |
icians | +3.488 |
ified | +3.482 |
itect | +3.472 |
Neg logit contributions | |
berman | -2.264 |
HAEL | -2.150 |
tti | -2.146 |
tails | -2.053 |
mma | -2.024 |
Token | Harvard |
Token ID | 11131 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
edIn | +0.781 |
icians | +0.685 |
ification | +0.684 |
itect | +0.681 |
ified | +0.680 |
Neg logit contributions | |
berman | -0.583 |
HAEL | -0.559 |
tti | -0.559 |
tails | -0.543 |
Heck | -0.532 |
Token | professor |
Token ID | 6240 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
edIn | +1.245 |
icians | +1.095 |
ification | +1.092 |
itect | +1.087 |
ified | +1.085 |
Neg logit contributions | |
berman | -0.871 |
tti | -0.836 |
HAEL | -0.835 |
tails | -0.811 |
Heck | -0.797 |
Token | E |
Token ID | 412 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
edIn | +2.766 |
icians | +2.473 |
ification | +2.472 |
ified | +2.458 |
itect | +2.443 |
Neg logit contributions | |
berman | -1.803 |
tti | -1.729 |
HAEL | -1.721 |
tails | -1.677 |
mma | -1.637 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
tti | +8.731 |
berman | +8.694 |
tails | +8.317 |
HAEL | +8.314 |
Gamble | +8.195 |
Neg logit contributions | |
edIn | -6.413 |
itect | -5.261 |
ification | -5.138 |
ifiers | -5.134 |
icians | -5.081 |
Token | H |
Token ID | 367 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
HAEL | +4.727 |
berman | +4.700 |
Heck | +4.615 |
Gamble | +4.560 |
tti | +4.502 |
Neg logit contributions | |
edIn | -10.176 |
icter | -8.914 |
itect | -8.847 |
ifiers | -8.802 |
icians | -8.762 |
Token | . |
Token ID | 13 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
berman | +2.949 |
tti | +2.790 |
Gamble | +2.707 |
HAEL | +2.670 |
Heck | +2.654 |
Neg logit contributions | |
edIn | -6.215 |
itect | -5.445 |
icians | -5.430 |
ification | -5.426 |
ified | -5.383 |
Token | Clarke |
Token ID | 19635 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Heck | +5.418 |
Gamble | +5.411 |
berman | +5.183 |
HAEL | +4.959 |
tti | +4.892 |
Neg logit contributions | |
edIn | -9.348 |
icter | -8.101 |
icians | -8.093 |
itect | -7.963 |
ification | -7.950 |
Token | used |
Token ID | 973 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
edIn | +4.058 |
ification | +3.623 |
ified | +3.600 |
icians | +3.574 |
itect | +3.565 |
Neg logit contributions | |
berman | -2.988 |
HAEL | -2.903 |
tti | -2.832 |
tails | -2.807 |
mma | -2.750 |
Token | with |
Token ID | 351 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
edIn | +3.119 |
ification | +2.797 |
icians | +2.785 |
ified | +2.784 |
itect | +2.764 |
Neg logit contributions | |
berman | -1.826 |
HAEL | -1.748 |
tti | -1.735 |
tails | -1.704 |
Heck | -1.646 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
berman | +1.109 |
tti | +1.069 |
HAEL | +1.054 |
tails | +1.033 |
Heck | +1.028 |
Neg logit contributions | |
edIn | -1.620 |
icians | -1.427 |
itect | -1.418 |
ification | -1.410 |
ified | -1.402 |
Token | glacier |
Token ID | 44539 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
edIn | +0.369 |
icians | +0.325 |
ification | +0.324 |
itect | +0.322 |
ified | +0.322 |
Neg logit contributions | |
berman | -0.268 |
tti | -0.257 |
HAEL | -0.257 |
tails | -0.249 |
Heck | -0.245 |
Token | , |
Token ID | 11 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
edIn | +1.419 |
icians | +1.245 |
ification | +1.243 |
itect | +1.236 |
ified | +1.235 |
Neg logit contributions | |
berman | -1.071 |
HAEL | -1.029 |
tti | -1.029 |
tails | -0.999 |
Heck | -0.982 |
Token | anyway |
Token ID | 6949 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
edIn | +0.678 |
icians | +0.574 |
ification | +0.571 |
itect | +0.568 |
ified | +0.566 |
Neg logit contributions | |
berman | -0.800 |
tti | -0.776 |
HAEL | -0.774 |
tails | -0.758 |
Heck | -0.748 |
Token | ) |
Token ID | 8 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
edIn | +0.115 |
icians | +0.098 |
ification | +0.097 |
itect | +0.097 |
ified | +0.096 |
Neg logit contributions | |
berman | -0.121 |
tti | -0.118 |
HAEL | -0.117 |
tails | -0.115 |
Heck | -0.113 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
berman | +1.896 |
tti | +1.855 |
HAEL | +1.809 |
tails | +1.775 |
Heck | +1.772 |
Neg logit contributions | |
edIn | -2.821 |
icians | -2.455 |
itect | -2.398 |
ification | -2.384 |
ified | -2.381 |
Token | in |
Token ID | 287 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
edIn | +0.590 |
icians | +0.518 |
ification | +0.517 |
itect | +0.514 |
ified | +0.514 |
Neg logit contributions | |
berman | -0.442 |
HAEL | -0.425 |
tti | -0.424 |
tails | -0.412 |
Heck | -0.405 |
Token | effect |
Token ID | 1245 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
berman | +0.135 |
tti | +0.130 |
HAEL | +0.128 |
tails | +0.127 |
Heck | +0.125 |
Neg logit contributions | |
edIn | -0.173 |
icians | -0.151 |
itect | -0.149 |
ification | -0.149 |
ified | -0.148 |
Token | � |
Token ID | 564 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
berman | +3.261 |
tti | +3.195 |
tails | +3.135 |
HAEL | +3.054 |
Heck | +3.029 |
Neg logit contributions | |
edIn | -5.104 |
itect | -4.449 |
icians | -4.441 |
ification | -4.372 |
icipated | -4.359 |
Token | � |
Token ID | 250 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
edIn | +0.377 |
icians | +0.330 |
ification | +0.330 |
itect | +0.328 |
ified | +0.327 |
Neg logit contributions | |
berman | -0.297 |
tti | -0.286 |
HAEL | -0.285 |
tails | -0.278 |
Heck | -0.274 |
Token | � |
Token ID | 247 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
edIn | +0.221 |
icians | +0.189 |
ification | +0.188 |
ified | +0.188 |
itect | +0.188 |
Neg logit contributions | |
berman | -0.241 |
HAEL | -0.233 |
tti | -0.233 |
tails | -0.229 |
Heck | -0.224 |
Token | s |
Token ID | 82 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
berman | +0.446 |
tti | +0.432 |
HAEL | +0.422 |
tails | +0.419 |
mma | +0.410 |
Neg logit contributions | |
edIn | -0.638 |
ification | -0.554 |
icians | -0.552 |
itect | -0.552 |
ified | -0.551 |
Token | legal |
Token ID | 2742 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
berman | +0.439 |
tti | +0.422 |
HAEL | +0.417 |
tails | +0.411 |
Heck | +0.408 |
Neg logit contributions | |
edIn | -0.511 |
itect | -0.445 |
icians | -0.441 |
ification | -0.441 |
ified | -0.438 |
Token | cases |
Token ID | 2663 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
berman | +2.619 |
tti | +2.519 |
tails | +2.449 |
Heck | +2.442 |
train | +2.433 |
Neg logit contributions | |
edIn | -3.939 |
itect | -3.496 |
ification | -3.406 |
icians | -3.383 |
ified | -3.362 |
Token | are |
Token ID | 389 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
edIn | +2.561 |
icians | +2.247 |
ification | +2.241 |
itect | +2.230 |
ified | +2.227 |
Neg logit contributions | |
berman | -1.938 |
HAEL | -1.863 |
tti | -1.863 |
tails | -1.810 |
Heck | -1.778 |
Token | filed |
Token ID | 5717 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
berman | +0.003 |
tti | +0.003 |
HAEL | +0.003 |
tails | +0.003 |
Heck | +0.003 |
Neg logit contributions | |
edIn | -0.003 |
itect | -0.003 |
icians | -0.003 |
ification | -0.003 |
ified | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
berman | +1.407 |
tti | +1.326 |
HAEL | +1.303 |
tails | +1.265 |
Heck | +1.250 |
Neg logit contributions | |
edIn | -2.865 |
icians | -2.560 |
itect | -2.553 |
ification | -2.535 |
ified | -2.517 |
Token | Whatever |
Token ID | 15935 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
berman | +0.248 |
tti | +0.240 |
HAEL | +0.239 |
Heck | +0.233 |
tails | +0.232 |
Neg logit contributions | |
edIn | -0.340 |
icians | -0.298 |
ification | -0.296 |
itect | -0.295 |
ified | -0.294 |
Token | recon |
Token ID | 8195 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
berman | +1.284 |
tti | +1.242 |
HAEL | +1.216 |
tails | +1.212 |
Heck | +1.195 |
Neg logit contributions | |
edIn | -1.809 |
itect | -1.606 |
icians | -1.584 |
ification | -1.580 |
ified | -1.573 |
Token | figured |
Token ID | 46296 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
edIn | +5.451 |
ification | +4.927 |
ified | +4.872 |
itect | +4.864 |
icians | +4.847 |
Neg logit contributions | |
berman | -4.182 |
HAEL | -4.029 |
tti | -3.902 |
mma | -3.821 |
tails | -3.779 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
edIn | +3.031 |
ification | +2.688 |
icians | +2.681 |
ified | +2.670 |
itect | +2.641 |
Neg logit contributions | |
berman | -2.217 |
HAEL | -2.159 |
tti | -2.132 |
tails | -2.080 |
mma | -2.030 |
Token | song |
Token ID | 3496 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
edIn | +1.390 |
icians | +1.209 |
ification | +1.206 |
itect | +1.202 |
ified | +1.198 |
Neg logit contributions | |
berman | -1.138 |
tti | -1.095 |
HAEL | -1.094 |
tails | -1.067 |
Heck | -1.052 |
Token | ] |
Token ID | 60 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
edIn | +4.428 |
ification | +4.019 |
ified | +3.990 |
icians | +3.979 |
itect | +3.917 |
Neg logit contributions | |
berman | -3.682 |
HAEL | -3.545 |
tti | -3.531 |
tails | -3.428 |
Heck | -3.361 |
Token | One |
Token ID | 1881 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
berman | +1.665 |
tti | +1.603 |
HAEL | +1.595 |
Heck | +1.551 |
tails | +1.538 |
Neg logit contributions | |
edIn | -2.718 |
icians | -2.400 |
itect | -2.394 |
ification | -2.385 |
ified | -2.374 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
berman | +1.330 |
tti | +1.283 |
HAEL | +1.261 |
tails | +1.222 |
Heck | +1.217 |
Neg logit contributions | |
edIn | -2.365 |
icians | -2.097 |
itect | -2.091 |
ification | -2.073 |
ified | -2.067 |
Token | two |
Token ID | 734 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
berman | +2.811 |
tti | +2.700 |
HAEL | +2.669 |
Heck | +2.610 |
tails | +2.570 |
Neg logit contributions | |
edIn | -4.132 |
itect | -3.610 |
icians | -3.574 |
ification | -3.538 |
ified | -3.526 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
berman | +2.145 |
tti | +2.051 |
HAEL | +1.992 |
tails | +1.973 |
Heck | +1.943 |
Neg logit contributions | |
edIn | -5.092 |
itect | -4.534 |
icians | -4.472 |
ification | -4.444 |
ified | -4.417 |
Token | three |
Token ID | 1115 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
berman | +2.193 |
tti | +2.089 |
HAEL | +2.049 |
Heck | +2.016 |
tails | +1.969 |
Neg logit contributions | |
edIn | -4.514 |
itect | -4.024 |
icians | -3.975 |
ified | -3.946 |
ification | -3.939 |
Token | , |
Token ID | 11 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
berman | +2.146 |
tti | +2.073 |
HAEL | +2.011 |
tails | +1.983 |
Heck | +1.966 |
Neg logit contributions | |
edIn | -4.553 |
itect | -4.052 |
icians | -4.007 |
ification | -3.987 |
ified | -3.964 |
Token | four |
Token ID | 1440 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
berman | +1.329 |
tti | +1.274 |
HAEL | +1.270 |
tails | +1.224 |
Heck | +1.214 |
Neg logit contributions | |
edIn | -2.318 |
icians | -2.040 |
itect | -2.033 |
ification | -2.029 |
ified | -2.018 |
Token | . |
Token ID | 13 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
berman | +1.364 |
tti | +1.307 |
HAEL | +1.287 |
tails | +1.255 |
Heck | +1.235 |
Neg logit contributions | |
edIn | -2.688 |
itect | -2.386 |
icians | -2.379 |
ification | -2.372 |
ified | -2.358 |
Token |
|
Token ID | 198 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
berman | +1.599 |
tti | +1.547 |
HAEL | +1.542 |
Heck | +1.517 |
tails | +1.491 |
Neg logit contributions | |
edIn | -2.514 |
icians | -2.211 |
itect | -2.198 |
ification | -2.196 |
ified | -2.185 |
Token | it |
Token ID | 340 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
edIn | +1.335 |
ification | +1.176 |
icians | +1.176 |
ified | +1.169 |
itect | +1.166 |
Neg logit contributions | |
berman | -0.961 |
HAEL | -0.922 |
tti | -0.920 |
tails | -0.895 |
Heck | -0.875 |
Token | will |
Token ID | 481 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
berman | +0.878 |
tti | +0.854 |
HAEL | +0.834 |
tails | +0.828 |
Heck | +0.811 |
Neg logit contributions | |
edIn | -1.070 |
icians | -0.915 |
itect | -0.907 |
ification | -0.903 |
ified | -0.900 |
Token | consider |
Token ID | 2074 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
berman | +1.286 |
tti | +1.237 |
HAEL | +1.216 |
tails | +1.198 |
Heck | +1.183 |
Neg logit contributions | |
edIn | -1.563 |
icians | -1.345 |
ification | -1.332 |
itect | -1.330 |
ified | -1.323 |
Token | the |
Token ID | 262 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
berman | +0.205 |
tti | +0.197 |
HAEL | +0.197 |
tails | +0.191 |
Heck | +0.189 |
Neg logit contributions | |
edIn | -0.299 |
icians | -0.264 |
ification | -0.263 |
itect | -0.262 |
ified | -0.261 |
Token | role |
Token ID | 2597 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
berman | +0.667 |
tti | +0.642 |
HAEL | +0.636 |
tails | +0.622 |
Heck | +0.621 |
Neg logit contributions | |
edIn | -0.922 |
icians | -0.807 |
itect | -0.805 |
ification | -0.797 |
ified | -0.794 |
Token | of |
Token ID | 286 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
berman | +2.031 |
tti | +1.910 |
HAEL | +1.892 |
Heck | +1.837 |
Gamble | +1.825 |
Neg logit contributions | |
edIn | -4.625 |
itect | -4.124 |
icians | -4.101 |
ification | -4.056 |
ified | -4.046 |
Token | ment |
Token ID | 6229 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
berman | +1.428 |
tti | +1.367 |
HAEL | +1.349 |
Heck | +1.322 |
tails | +1.316 |
Neg logit contributions | |
edIn | -2.437 |
itect | -2.161 |
icians | -2.152 |
ification | -2.135 |
ified | -2.122 |
Token | hol |
Token ID | 3937 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
berman | +1.916 |
tails | +1.811 |
tti | +1.810 |
HAEL | +1.753 |
mma | +1.680 |
Neg logit contributions | |
edIn | -6.414 |
icians | -5.564 |
acters | -5.506 |
icter | -5.495 |
itect | -5.494 |
Token | and |
Token ID | 290 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
berman | +1.483 |
tti | +1.429 |
HAEL | +1.394 |
tails | +1.369 |
Heck | +1.342 |
Neg logit contributions | |
edIn | -2.909 |
icians | -2.572 |
itect | -2.568 |
ification | -2.530 |
ified | -2.525 |
Token | other |
Token ID | 584 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
berman | +2.432 |
tti | +2.327 |
HAEL | +2.277 |
Heck | +2.249 |
Gamble | +2.248 |
Neg logit contributions | |
edIn | -4.688 |
itect | -4.172 |
icians | -4.165 |
ification | -4.097 |
ified | -4.077 |
Token | flavors |
Token ID | 17361 |
Feature activation | +9.54e-02 |
Pos logit contributions | |
berman | +3.179 |
tti | +3.125 |
Gamble | +3.078 |
Heck | +3.042 |
HAEL | +3.039 |
Neg logit contributions | |
edIn | -6.388 |
itect | -5.748 |
icians | -5.645 |
icter | -5.525 |
ification | -5.506 |
Token | is |
Token ID | 318 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
edIn | +3.853 |
ification | +3.438 |
icians | +3.423 |
ified | +3.408 |
itect | +3.385 |
Neg logit contributions | |
berman | -2.961 |
HAEL | -2.870 |
tti | -2.802 |
tails | -2.731 |
mma | -2.698 |
Token | on |
Token ID | 319 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
edIn | +0.182 |
icians | +0.160 |
ification | +0.159 |
itect | +0.158 |
ified | +0.158 |
Neg logit contributions | |
berman | -0.136 |
tti | -0.131 |
HAEL | -0.131 |
tails | -0.127 |
Heck | -0.126 |
Token | the |
Token ID | 262 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
edIn | +2.050 |
ification | +1.797 |
icians | +1.797 |
ified | +1.785 |
itect | +1.784 |
Neg logit contributions | |
berman | -1.552 |
HAEL | -1.492 |
tti | -1.489 |
tails | -1.448 |
Heck | -1.418 |
Token | way |
Token ID | 835 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
edIn | +2.645 |
ification | +2.347 |
ified | +2.337 |
icians | +2.327 |
itect | +2.321 |
Neg logit contributions | |
berman | -1.851 |
HAEL | -1.792 |
tti | -1.768 |
tails | -1.712 |
mma | -1.690 |
Token | to |
Token ID | 284 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
berman | +0.677 |
tti | +0.647 |
HAEL | +0.643 |
tails | +0.624 |
Heck | +0.612 |
Neg logit contributions | |
edIn | -1.177 |
icians | -1.042 |
itect | -1.036 |
ification | -1.034 |
ified | -1.029 |
Token | failing |
Token ID | 9894 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
edIn | +2.101 |
ification | +1.851 |
icians | +1.847 |
ified | +1.835 |
itect | +1.832 |
Neg logit contributions | |
berman | -1.615 |
HAEL | -1.559 |
tti | -1.557 |
tails | -1.507 |
mma | -1.478 |
Token | . |
Token ID | 13 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
berman | +2.308 |
tti | +2.209 |
HAEL | +2.186 |
tails | +2.172 |
Heck | +2.145 |
Neg logit contributions | |
edIn | -3.736 |
icians | -3.323 |
ification | -3.279 |
itect | -3.272 |
ified | -3.264 |
Token | If |
Token ID | 1002 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
berman | +0.155 |
tti | +0.149 |
HAEL | +0.149 |
tails | +0.144 |
Heck | +0.143 |
Neg logit contributions | |
edIn | -0.219 |
icians | -0.192 |
ification | -0.191 |
itect | -0.191 |
ified | -0.190 |
Token | you |
Token ID | 345 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
berman | +1.675 |
tti | +1.611 |
HAEL | +1.595 |
Heck | +1.565 |
tails | +1.552 |
Neg logit contributions | |
edIn | -2.454 |
icians | -2.145 |
itect | -2.136 |
ification | -2.116 |
ified | -2.105 |
Token | want |
Token ID | 765 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
berman | +2.723 |
tti | +2.634 |
HAEL | +2.564 |
Heck | +2.543 |
Gamble | +2.525 |
Neg logit contributions | |
edIn | -3.313 |
icians | -2.819 |
itect | -2.807 |
ification | -2.783 |
ified | -2.770 |
Token | to |
Token ID | 284 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
berman | +3.580 |
tti | +3.536 |
HAEL | +3.394 |
Heck | +3.357 |
tails | +3.343 |
Neg logit contributions | |
edIn | -6.786 |
itect | -5.968 |
icians | -5.953 |
ified | -5.850 |
ification | -5.841 |
Token | the |
Token ID | 262 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
edIn | +0.627 |
icians | +0.552 |
ification | +0.550 |
itect | +0.548 |
ified | +0.547 |
Neg logit contributions | |
berman | -0.439 |
tti | -0.421 |
HAEL | -0.421 |
tails | -0.409 |
Heck | -0.402 |
Token | party |
Token ID | 2151 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
edIn | +2.684 |
ification | +2.373 |
icians | +2.368 |
ified | +2.355 |
itect | +2.346 |
Neg logit contributions | |
berman | -2.052 |
HAEL | -1.984 |
tti | -1.969 |
tails | -1.904 |
mma | -1.882 |
Token | explores |
Token ID | 25409 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
edIn | +3.106 |
ification | +2.772 |
icians | +2.755 |
ified | +2.751 |
itect | +2.726 |
Neg logit contributions | |
berman | -2.463 |
HAEL | -2.398 |
tti | -2.372 |
tails | -2.291 |
mma | -2.256 |
Token | and |
Token ID | 290 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
edIn | +2.857 |
ification | +2.517 |
ified | +2.501 |
icians | +2.493 |
itect | +2.490 |
Neg logit contributions | |
berman | -2.201 |
HAEL | -2.110 |
tti | -2.093 |
tails | -2.029 |
mma | -1.999 |
Token | discovers |
Token ID | 27472 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
edIn | +0.918 |
icians | +0.806 |
ification | +0.805 |
itect | +0.800 |
ified | +0.800 |
Neg logit contributions | |
berman | -0.689 |
HAEL | -0.663 |
tti | -0.662 |
tails | -0.642 |
Heck | -0.631 |
Token | the |
Token ID | 262 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
edIn | +2.919 |
ification | +2.580 |
ified | +2.561 |
icians | +2.553 |
itect | +2.544 |
Neg logit contributions | |
berman | -2.238 |
HAEL | -2.152 |
tti | -2.121 |
tails | -2.062 |
mma | -2.027 |
Token | discrepancy |
Token ID | 34466 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
edIn | +2.722 |
ification | +2.406 |
icians | +2.396 |
ified | +2.392 |
itect | +2.379 |
Neg logit contributions | |
berman | -1.968 |
HAEL | -1.888 |
tti | -1.874 |
tails | -1.817 |
mma | -1.790 |
Token | . |
Token ID | 13 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
edIn | +2.099 |
ification | +1.882 |
icians | +1.876 |
ified | +1.869 |
itect | +1.863 |
Neg logit contributions | |
berman | -1.228 |
HAEL | -1.172 |
tti | -1.167 |
tails | -1.130 |
Heck | -1.098 |
Token |
|
Token ID | 198 |
Feature activation | -4.21e-03 |
Pos logit contributions | |
berman | +0.645 |
tti | +0.626 |
HAEL | +0.623 |
Heck | +0.607 |
tails | +0.606 |
Neg logit contributions | |
edIn | -0.892 |
icians | -0.783 |
ification | -0.776 |
itect | -0.773 |
ified | -0.772 |
Token |
|
Token ID | 198 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
edIn | +0.014 |
ification | +0.012 |
ified | +0.012 |
icians | +0.012 |
itect | +0.012 |
Neg logit contributions | |
berman | -0.012 |
HAEL | -0.012 |
tti | -0.012 |
tails | -0.012 |
Heck | -0.011 |
Token | How |
Token ID | 2437 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
edIn | +0.284 |
icians | +0.249 |
ification | +0.248 |
itect | +0.247 |
ified | +0.247 |
Neg logit contributions | |
berman | -0.213 |
tti | -0.205 |
HAEL | -0.205 |
tails | -0.199 |
Heck | -0.196 |
Token | takes |
Token ID | 2753 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
edIn | +0.453 |
ification | +0.401 |
icians | +0.401 |
ified | +0.398 |
itect | +0.397 |
Neg logit contributions | |
berman | -0.321 |
tti | -0.308 |
HAEL | -0.306 |
tails | -0.297 |
Heck | -0.292 |
Token | steps |
Token ID | 4831 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
edIn | +2.824 |
ification | +2.441 |
ified | +2.431 |
ifiers | +2.348 |
icians | +2.344 |
Neg logit contributions | |
tti | -3.277 |
HAEL | -3.238 |
berman | -3.210 |
tails | -3.100 |
mma | -3.098 |
Token | to |
Token ID | 284 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
edIn | +2.270 |
ification | +2.157 |
ified | +2.129 |
itect | +2.093 |
icians | +2.063 |
Neg logit contributions | |
HAEL | -1.705 |
tails | -1.697 |
berman | -1.688 |
tti | -1.653 |
senal | -1.637 |
Token | open |
Token ID | 1280 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
edIn | +3.634 |
ified | +3.609 |
ification | +3.591 |
itect | +3.486 |
icians | +3.476 |
Neg logit contributions | |
tti | -4.024 |
HAEL | -3.933 |
berman | -3.820 |
Klux | -3.792 |
mma | -3.772 |
Token | flights |
Token ID | 13956 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
edIn | +0.664 |
ification | +0.591 |
ified | +0.590 |
icians | +0.587 |
itect | +0.579 |
Neg logit contributions | |
berman | -0.461 |
HAEL | -0.446 |
tti | -0.441 |
tails | -0.431 |
Heck | -0.417 |
Token | to |
Token ID | 284 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
berman | +0.500 |
HAEL | +0.484 |
tti | +0.481 |
tails | +0.467 |
Heck | +0.452 |
Neg logit contributions | |
edIn | -0.824 |
ification | -0.734 |
ified | -0.731 |
icians | -0.731 |
itect | -0.720 |
Token | US |
Token ID | 1294 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
edIn | +2.603 |
ification | +2.388 |
ified | +2.383 |
icians | +2.339 |
itect | +2.290 |
Neg logit contributions | |
berman | -2.560 |
HAEL | -2.540 |
tti | -2.533 |
tails | -2.473 |
mma | -2.412 |
Token | on |
Token ID | 319 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
edIn | +0.986 |
ification | +0.924 |
ified | +0.924 |
ifiers | +0.911 |
icians | +0.890 |
Neg logit contributions | |
berman | -0.628 |
tti | -0.608 |
HAEL | -0.603 |
mma | -0.584 |
tails | -0.580 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
edIn | +1.559 |
ification | +1.391 |
ified | +1.382 |
icians | +1.377 |
ifiers | +1.355 |
Neg logit contributions | |
berman | -0.945 |
HAEL | -0.937 |
tti | -0.912 |
tails | -0.896 |
mma | -0.854 |
Token | of |
Token ID | 286 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
edIn | +5.055 |
ification | +4.725 |
ified | +4.641 |
itect | +4.570 |
icians | +4.546 |
Neg logit contributions | |
senal | -3.510 |
berman | -3.478 |
tti | -3.358 |
tails | -3.340 |
HAEL | -3.279 |
Token | Trump |
Token ID | 1301 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
edIn | +2.108 |
icians | +1.925 |
ification | +1.909 |
ified | +1.902 |
itect | +1.865 |
Neg logit contributions | |
berman | -1.483 |
tti | -1.447 |
HAEL | -1.442 |
tails | -1.396 |
train | -1.360 |
Token | � |
Token ID | 251 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
berman | +0.573 |
HAEL | +0.553 |
tti | +0.553 |
tails | +0.538 |
Heck | +0.532 |
Neg logit contributions | |
edIn | -0.607 |
icians | -0.527 |
ification | -0.524 |
itect | -0.522 |
ified | -0.520 |
Token | Zone |
Token ID | 13035 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
edIn | +1.499 |
icians | +1.321 |
ification | +1.319 |
itect | +1.312 |
ified | +1.311 |
Neg logit contributions | |
berman | -1.036 |
HAEL | -0.993 |
tti | -0.993 |
tails | -0.963 |
Heck | -0.945 |
Token | Threat |
Token ID | 25238 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
berman | +1.535 |
tti | +1.492 |
HAEL | +1.458 |
tails | +1.436 |
Heck | +1.433 |
Neg logit contributions | |
edIn | -1.699 |
icians | -1.479 |
itect | -1.451 |
ified | -1.451 |
ification | -1.450 |
Token |
|
Token ID | 198 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
berman | +0.762 |
tti | +0.735 |
HAEL | +0.727 |
tails | +0.711 |
Heck | +0.705 |
Neg logit contributions | |
edIn | -0.984 |
icians | -0.867 |
itect | -0.852 |
ified | -0.850 |
ification | -0.850 |
Token |
|
Token ID | 198 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
berman | +1.520 |
tti | +1.470 |
HAEL | +1.460 |
tails | +1.426 |
Heck | +1.406 |
Neg logit contributions | |
edIn | -1.962 |
icians | -1.709 |
itect | -1.690 |
ification | -1.690 |
ified | -1.680 |
Token | Sur |
Token ID | 14214 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
berman | +0.153 |
HAEL | +0.147 |
tti | +0.147 |
tails | +0.142 |
Heck | +0.139 |
Neg logit contributions | |
edIn | -0.226 |
icians | -0.201 |
ification | -0.199 |
itect | -0.199 |
ified | -0.198 |
Token | prisingly |
Token ID | 20859 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
edIn | +3.543 |
ification | +3.102 |
icians | +3.087 |
ified | +3.084 |
itect | +3.068 |
Neg logit contributions | |
berman | -2.913 |
HAEL | -2.834 |
tti | -2.816 |
tails | -2.716 |
mma | -2.696 |
Token | , |
Token ID | 11 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
edIn | +1.898 |
icians | +1.707 |
ification | +1.707 |
ified | +1.701 |
itect | +1.695 |
Neg logit contributions | |
berman | -0.969 |
HAEL | -0.938 |
tti | -0.917 |
tails | -0.896 |
mma | -0.863 |
Token | Wallace |
Token ID | 17161 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
edIn | +1.081 |
ification | +0.954 |
icians | +0.953 |
ified | +0.949 |
itect | +0.948 |
Neg logit contributions | |
berman | -0.713 |
HAEL | -0.686 |
tti | -0.684 |
tails | -0.664 |
mma | -0.649 |
Token | caught |
Token ID | 4978 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
edIn | +0.710 |
icians | +0.622 |
ification | +0.618 |
itect | +0.616 |
ified | +0.615 |
Neg logit contributions | |
berman | -0.547 |
tti | -0.528 |
HAEL | -0.524 |
tails | -0.511 |
Heck | -0.504 |
Token | nine |
Token ID | 5193 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
berman | +1.450 |
tti | +1.396 |
HAEL | +1.384 |
tails | +1.370 |
Heck | +1.360 |
Neg logit contributions | |
edIn | -1.871 |
icians | -1.632 |
itect | -1.620 |
ification | -1.615 |
ified | -1.604 |
Token | he |
Token ID | 339 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
berman | +0.336 |
tti | +0.324 |
HAEL | +0.322 |
tails | +0.314 |
Heck | +0.312 |
Neg logit contributions | |
edIn | -0.400 |
icians | -0.347 |
itect | -0.345 |
ification | -0.344 |
ified | -0.343 |
Token | will |
Token ID | 481 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
edIn | +0.589 |
icians | +0.510 |
ification | +0.506 |
itect | +0.506 |
ified | +0.504 |
Neg logit contributions | |
berman | -0.473 |
tti | -0.457 |
HAEL | -0.453 |
tails | -0.442 |
Heck | -0.435 |
Token | be |
Token ID | 307 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
berman | +0.856 |
tti | +0.827 |
HAEL | +0.810 |
tails | +0.795 |
Heck | +0.795 |
Neg logit contributions | |
edIn | -1.122 |
icians | -0.966 |
itect | -0.955 |
ification | -0.954 |
ified | -0.951 |
Token | impe |
Token ID | 18516 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
berman | +1.612 |
tti | +1.550 |
HAEL | +1.522 |
Heck | +1.510 |
tails | +1.502 |
Neg logit contributions | |
edIn | -2.290 |
itect | -1.989 |
icians | -1.977 |
ification | -1.955 |
ified | -1.939 |
Token | ached |
Token ID | 2317 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
edIn | +0.317 |
icians | +0.265 |
ification | +0.265 |
itect | +0.263 |
ified | +0.263 |
Neg logit contributions | |
berman | -0.410 |
HAEL | -0.398 |
tti | -0.398 |
tails | -0.390 |
Heck | -0.385 |
Token | , |
Token ID | 11 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
edIn | +0.818 |
icians | +0.725 |
ification | +0.725 |
itect | +0.721 |
ified | +0.720 |
Neg logit contributions | |
berman | -0.526 |
HAEL | -0.504 |
tti | -0.503 |
tails | -0.488 |
Heck | -0.478 |
Token | � |
Token ID | 447 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
edIn | +1.618 |
icians | +1.383 |
ification | +1.383 |
itect | +1.372 |
ified | +1.371 |
Neg logit contributions | |
berman | -1.763 |
HAEL | -1.707 |
tti | -1.706 |
tails | -1.668 |
Heck | -1.641 |
Token | � |
Token ID | 251 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
edIn | +1.180 |
ification | +0.955 |
icians | +0.951 |
itect | +0.946 |
ified | +0.945 |
Neg logit contributions | |
berman | -1.950 |
HAEL | -1.901 |
tti | -1.898 |
tails | -1.864 |
Heck | -1.834 |
Token | she |
Token ID | 673 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
edIn | +5.545 |
ification | +4.951 |
ified | +4.931 |
icians | +4.857 |
itect | +4.835 |
Neg logit contributions | |
berman | -4.216 |
HAEL | -4.038 |
tti | -4.005 |
tails | -3.948 |
Heck | -3.781 |
Token | said |
Token ID | 531 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
edIn | +2.844 |
ification | +2.484 |
ified | +2.468 |
icians | +2.465 |
itect | +2.452 |
Neg logit contributions | |
berman | -2.717 |
HAEL | -2.631 |
tti | -2.613 |
tails | -2.570 |
Heck | -2.510 |
Token | . |
Token ID | 13 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
berman | +0.819 |
tti | +0.780 |
HAEL | +0.778 |
tails | +0.743 |
Heck | +0.740 |
Neg logit contributions | |
edIn | -1.654 |
icians | -1.481 |
itect | -1.472 |
ification | -1.469 |
ified | -1.461 |
Token | I |
Token ID | 314 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
berman | +0.862 |
tti | +0.834 |
HAEL | +0.824 |
Heck | +0.818 |
tails | +0.805 |
Neg logit contributions | |
edIn | -1.305 |
icians | -1.149 |
ification | -1.139 |
itect | -1.133 |
ified | -1.131 |
Token | know |
Token ID | 760 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
edIn | +0.663 |
icians | +0.574 |
ification | +0.572 |
itect | +0.570 |
ified | +0.568 |
Neg logit contributions | |
berman | -0.589 |
tti | -0.568 |
HAEL | -0.566 |
tails | -0.552 |
Heck | -0.544 |
Token | I |
Token ID | 314 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
edIn | +0.668 |
ification | +0.595 |
icians | +0.594 |
ified | +0.591 |
itect | +0.589 |
Neg logit contributions | |
berman | -0.466 |
HAEL | -0.450 |
tti | -0.445 |
tails | -0.436 |
mma | -0.421 |
Token | � |
Token ID | 447 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
edIn | +2.591 |
ification | +2.271 |
icians | +2.263 |
ified | +2.247 |
itect | +2.241 |
Neg logit contributions | |
berman | -2.398 |
HAEL | -2.327 |
tti | -2.304 |
tails | -2.269 |
Heck | -2.222 |
Token | � |
Token ID | 247 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
berman | +2.613 |
tti | +2.541 |
HAEL | +2.525 |
tails | +2.442 |
Heck | +2.436 |
Neg logit contributions | |
edIn | -2.999 |
icians | -2.636 |
ification | -2.614 |
itect | -2.601 |
ified | -2.573 |
Token | m |
Token ID | 76 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
berman | +0.951 |
tti | +0.921 |
HAEL | +0.903 |
tails | +0.882 |
mma | +0.878 |
Neg logit contributions | |
edIn | -1.420 |
icians | -1.252 |
ification | -1.244 |
itect | -1.237 |
ified | -1.236 |
Token | not |
Token ID | 407 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
edIn | +1.664 |
ification | +1.472 |
icians | +1.468 |
ified | +1.461 |
itect | +1.456 |
Neg logit contributions | |
berman | -1.290 |
HAEL | -1.242 |
tti | -1.240 |
tails | -1.209 |
Heck | -1.178 |
Token | the |
Token ID | 262 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
edIn | +4.032 |
ification | +3.678 |
ified | +3.637 |
icians | +3.631 |
itect | +3.604 |
Neg logit contributions | |
berman | -2.289 |
HAEL | -2.226 |
tti | -2.186 |
tails | -2.133 |
mma | -2.037 |
Token | only |
Token ID | 691 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
edIn | +3.890 |
ification | +3.365 |
ified | +3.347 |
itect | +3.334 |
icians | +3.289 |
Neg logit contributions | |
berman | -4.413 |
HAEL | -4.315 |
tti | -4.236 |
tails | -4.156 |
mma | -4.089 |
Token | one |
Token ID | 530 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
edIn | +0.966 |
ification | +0.838 |
icians | +0.838 |
ified | +0.834 |
itect | +0.833 |
Neg logit contributions | |
berman | -0.847 |
HAEL | -0.818 |
tti | -0.815 |
tails | -0.797 |
Heck | -0.780 |
Token | . |
Token ID | 13 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
berman | +1.365 |
tti | +1.316 |
HAEL | +1.301 |
tails | +1.274 |
Heck | +1.266 |
Neg logit contributions | |
edIn | -1.828 |
icians | -1.592 |
itect | -1.583 |
ification | -1.565 |
ified | -1.558 |
Token | that |
Token ID | 326 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
berman | +2.220 |
tti | +2.142 |
HAEL | +2.058 |
Heck | +2.029 |
tails | +2.021 |
Neg logit contributions | |
edIn | -4.610 |
icians | -4.017 |
itect | -3.988 |
ification | -3.950 |
ified | -3.946 |
Token | will |
Token ID | 481 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
edIn | +4.493 |
icians | +3.957 |
ification | +3.946 |
itect | +3.908 |
ified | +3.898 |
Neg logit contributions | |
berman | -3.956 |
HAEL | -3.833 |
tti | -3.744 |
tails | -3.693 |
mma | -3.638 |
Token | be |
Token ID | 307 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
edIn | +3.602 |
ification | +3.204 |
icians | +3.190 |
ified | +3.177 |
itect | +3.162 |
Neg logit contributions | |
berman | -3.358 |
HAEL | -3.288 |
tti | -3.203 |
tails | -3.146 |
mma | -3.105 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
edIn | +2.185 |
ification | +1.941 |
ified | +1.930 |
icians | +1.924 |
itect | +1.915 |
Neg logit contributions | |
berman | -1.835 |
HAEL | -1.769 |
tti | -1.747 |
tails | -1.706 |
mma | -1.670 |
Token |
|
Token ID | 198 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
berman | +0.458 |
HAEL | +0.441 |
tti | +0.440 |
tails | +0.428 |
Heck | +0.421 |
Neg logit contributions | |
edIn | -0.535 |
ification | -0.468 |
icians | -0.467 |
ified | -0.465 |
itect | -0.464 |
Token | app |
Token ID | 1324 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
berman | +1.139 |
tti | +1.097 |
HAEL | +1.081 |
tails | +1.078 |
train | +1.049 |
Neg logit contributions | |
edIn | -1.386 |
icians | -1.201 |
itect | -1.190 |
ification | -1.187 |
ified | -1.173 |
Token | reci |
Token ID | 29102 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
edIn | +7.550 |
itect | +6.607 |
ified | +6.431 |
icians | +6.367 |
ification | +6.349 |
Neg logit contributions | |
berman | -9.786 |
HAEL | -9.431 |
tti | -9.374 |
Gamble | -9.102 |
mma | -9.094 |
Token | ated |
Token ID | 515 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
edIn | +4.981 |
ified | +4.537 |
itect | +4.423 |
ification | +4.416 |
icians | +4.333 |
Neg logit contributions | |
berman | -3.446 |
HAEL | -3.327 |
tti | -3.228 |
Heck | -3.181 |
Gamble | -3.175 |
Token | by |
Token ID | 416 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
edIn | +0.990 |
ification | +0.886 |
icians | +0.886 |
ified | +0.882 |
itect | +0.880 |
Neg logit contributions | |
berman | -0.585 |
HAEL | -0.559 |
tti | -0.558 |
tails | -0.540 |
mma | -0.525 |
Token | all |
Token ID | 477 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
edIn | +1.500 |
icians | +1.328 |
ification | +1.322 |
itect | +1.317 |
ified | +1.313 |
Neg logit contributions | |
berman | -1.065 |
HAEL | -1.027 |
tti | -1.022 |
tails | -0.988 |
mma | -0.969 |
Token | lovers |
Token ID | 20175 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
berman | +2.168 |
tti | +2.105 |
HAEL | +2.034 |
Heck | +2.029 |
tails | +2.020 |
Neg logit contributions | |
edIn | -3.540 |
ification | -3.102 |
ified | -3.091 |
icians | -3.091 |
itect | -3.079 |
Token | dinosaurs |
Token ID | 27199 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
berman | +3.517 |
tti | +3.453 |
HAEL | +3.353 |
tails | +3.318 |
Heck | +3.316 |
Neg logit contributions | |
edIn | -4.601 |
icians | -3.960 |
itect | -3.930 |
ification | -3.847 |
icter | -3.810 |
Token | do |
Token ID | 466 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
edIn | +4.593 |
ification | +4.229 |
ified | +4.207 |
icians | +4.123 |
itect | +4.085 |
Neg logit contributions | |
berman | -4.813 |
HAEL | -4.775 |
tti | -4.673 |
tails | -4.601 |
mma | -4.511 |
Token | while |
Token ID | 981 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
berman | +3.507 |
tti | +3.286 |
HAEL | +3.244 |
Heck | +3.134 |
tails | +3.126 |
Neg logit contributions | |
edIn | -7.295 |
icians | -6.410 |
itect | -6.327 |
ification | -6.240 |
icter | -6.239 |
Token | nesting |
Token ID | 46282 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
edIn | +0.255 |
icians | +0.223 |
ification | +0.221 |
itect | +0.221 |
ified | +0.220 |
Neg logit contributions | |
berman | -0.201 |
tti | -0.193 |
HAEL | -0.192 |
tails | -0.189 |
Heck | -0.186 |
Token | ( |
Token ID | 357 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
berman | +0.932 |
tti | +0.884 |
HAEL | +0.875 |
tails | +0.857 |
Heck | +0.837 |
Neg logit contributions | |
edIn | -1.889 |
icians | -1.700 |
ification | -1.684 |
itect | -1.680 |
ified | -1.670 |
Token | scient |
Token ID | 25346 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
edIn | +0.087 |
icians | +0.076 |
ification | +0.075 |
itect | +0.075 |
ified | +0.075 |
Neg logit contributions | |
berman | -0.070 |
tti | -0.067 |
HAEL | -0.067 |
tails | -0.065 |
Heck | -0.064 |
Token | ists |
Token ID | 1023 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
edIn | +8.319 |
icians | +7.973 |
ified | +7.836 |
ification | +7.812 |
ifiers | +7.342 |
Neg logit contributions | |
HAEL | -13.794 |
mma | -13.760 |
berman | -13.716 |
tti | -13.592 |
Heck | -13.209 |
Token | think |
Token ID | 892 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
edIn | +5.363 |
ification | +4.900 |
ified | +4.886 |
icians | +4.834 |
itect | +4.751 |
Neg logit contributions | |
berman | -4.909 |
HAEL | -4.849 |
tti | -4.765 |
tails | -4.707 |
mma | -4.607 |
Token | some |
Token ID | 617 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
edIn | +2.732 |
ification | +2.415 |
icians | +2.400 |
ified | +2.395 |
itect | +2.371 |
Neg logit contributions | |
berman | -2.206 |
HAEL | -2.146 |
tti | -2.110 |
tails | -2.057 |
mma | -2.006 |
Token | species |
Token ID | 4693 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
berman | +0.263 |
tti | +0.253 |
HAEL | +0.251 |
tails | +0.245 |
Heck | +0.240 |
Neg logit contributions | |
edIn | -0.401 |
icians | -0.354 |
ification | -0.352 |
itect | -0.352 |
ified | -0.350 |
Token | sat |
Token ID | 3332 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
edIn | +3.060 |
ification | +2.711 |
icians | +2.697 |
ified | +2.692 |
itect | +2.684 |
Neg logit contributions | |
berman | -2.537 |
HAEL | -2.463 |
tti | -2.443 |
tails | -2.387 |
Heck | -2.338 |
Token | - |
Token ID | 12 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
edIn | +3.245 |
ification | +2.889 |
ified | +2.874 |
icians | +2.869 |
itect | +2.831 |
Neg logit contributions | |
berman | -3.059 |
HAEL | -2.896 |
tti | -2.883 |
Heck | -2.766 |
tails | -2.755 |
Token | f |
Token ID | 69 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
edIn | +2.862 |
ification | +2.647 |
icians | +2.623 |
ified | +2.618 |
itect | +2.572 |
Neg logit contributions | |
berman | -2.184 |
HAEL | -2.119 |
tti | -2.065 |
Heck | -2.004 |
Gamble | -1.963 |
Token | inance |
Token ID | 14149 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
edIn | +4.102 |
icians | +3.924 |
ification | +3.895 |
ified | +3.828 |
itect | +3.806 |
Neg logit contributions | |
HAEL | -2.964 |
berman | -2.892 |
senal | -2.780 |
Heck | -2.741 |
tti | -2.730 |
Token | , |
Token ID | 11 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
edIn | +0.260 |
icians | +0.234 |
ification | +0.234 |
itect | +0.233 |
ified | +0.233 |
Neg logit contributions | |
berman | -0.117 |
HAEL | -0.110 |
tti | -0.110 |
tails | -0.106 |
Heck | -0.103 |
Token | wh |
Token ID | 348 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
edIn | +2.913 |
ification | +2.607 |
icians | +2.602 |
ified | +2.591 |
itect | +2.587 |
Neg logit contributions | |
berman | -1.953 |
HAEL | -1.873 |
tti | -1.851 |
tails | -1.826 |
Heck | -1.762 |
Token | itt |
Token ID | 715 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
edIn | +8.208 |
icians | +7.941 |
ification | +7.887 |
ified | +7.823 |
itect | +7.746 |
Neg logit contributions | |
HAEL | -8.611 |
senal | -8.223 |
berman | -8.154 |
HO | -7.861 |
Gamble | -7.822 |
Token | les |
Token ID | 829 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
icians | +9.211 |
ification | +9.010 |
edIn | +8.937 |
ified | +8.932 |
itect | +8.586 |
Neg logit contributions | |
senal | -10.594 |
HAEL | -9.118 |
Gamble | -8.797 |
Heck | -8.547 |
berman | -8.534 |
Token | ea |
Token ID | 18213 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
edIn | +5.725 |
ification | +5.304 |
ified | +5.281 |
itect | +5.126 |
icians | +5.121 |
Neg logit contributions | |
senal | -5.652 |
HAEL | -5.589 |
berman | -5.508 |
Heck | -5.447 |
tti | -5.442 |
Token | - |
Token ID | 12 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
edIn | +6.107 |
itect | +5.417 |
ification | +5.397 |
icians | +5.385 |
ified | +5.376 |
Neg logit contributions | |
berman | -6.740 |
HAEL | -6.546 |
tails | -6.522 |
tti | -6.473 |
Gamble | -6.257 |
Token | 375 |
Token ID | 22318 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
edIn | +4.972 |
ification | +4.506 |
ified | +4.487 |
icians | +4.486 |
itect | +4.476 |
Neg logit contributions | |
berman | -2.470 |
HAEL | -2.448 |
tti | -2.339 |
tails | -2.309 |
Heck | -2.296 |
Token | 7 |
Token ID | 22 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
edIn | +2.099 |
ification | +1.891 |
itect | +1.884 |
icians | +1.880 |
ified | +1.880 |
Neg logit contributions | |
berman | -1.159 |
HAEL | -1.100 |
tti | -1.087 |
tails | -1.063 |
Gamble | -1.036 |
Token | mentioned |
Token ID | 4750 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
berman | +1.581 |
tti | +1.518 |
HAEL | +1.505 |
tails | +1.460 |
Heck | +1.458 |
Neg logit contributions | |
edIn | -2.199 |
icians | -1.914 |
itect | -1.914 |
ification | -1.890 |
ified | -1.884 |
Token | in |
Token ID | 287 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
edIn | +2.814 |
ification | +2.513 |
ified | +2.499 |
icians | +2.498 |
itect | +2.477 |
Neg logit contributions | |
berman | -1.808 |
HAEL | -1.733 |
tti | -1.727 |
tails | -1.684 |
mma | -1.629 |
Token | at |
Token ID | 379 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
edIn | +2.255 |
icians | +1.982 |
ification | +1.980 |
itect | +1.969 |
ified | +1.968 |
Neg logit contributions | |
berman | -1.668 |
HAEL | -1.603 |
tti | -1.601 |
tails | -1.556 |
Heck | -1.523 |
Token | least |
Token ID | 1551 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
berman | +0.672 |
tti | +0.651 |
HAEL | +0.645 |
tails | +0.633 |
Heck | +0.628 |
Neg logit contributions | |
edIn | -0.900 |
icians | -0.777 |
itect | -0.770 |
ification | -0.769 |
ified | -0.766 |
Token | one |
Token ID | 530 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
edIn | +0.690 |
icians | +0.607 |
ification | +0.605 |
itect | +0.603 |
ified | +0.601 |
Neg logit contributions | |
berman | -0.491 |
tti | -0.472 |
HAEL | -0.471 |
tails | -0.457 |
Heck | -0.450 |
Token | declass |
Token ID | 42794 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
berman | +1.742 |
tti | +1.683 |
HAEL | +1.651 |
Heck | +1.640 |
tails | +1.616 |
Neg logit contributions | |
edIn | -2.512 |
icians | -2.207 |
itect | -2.181 |
ification | -2.165 |
ified | -2.155 |
Token | ified |
Token ID | 1431 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ified | +5.520 |
ification | +5.341 |
edIn | +4.604 |
ifying | +3.921 |
ifiers | +3.871 |
Neg logit contributions | |
berman | -18.268 |
HAEL | -17.857 |
tails | -17.692 |
senal | -17.676 |
tti | -17.674 |
Token | document |
Token ID | 3188 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
edIn | +4.355 |
ification | +3.940 |
ified | +3.916 |
icians | +3.838 |
itect | +3.833 |
Neg logit contributions | |
berman | -3.584 |
HAEL | -3.479 |
tti | -3.443 |
tails | -3.381 |
mma | -3.267 |
Token | dating |
Token ID | 10691 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
edIn | +1.817 |
icians | +1.616 |
ification | +1.615 |
ified | +1.605 |
itect | +1.605 |
Neg logit contributions | |
berman | -1.091 |
HAEL | -1.043 |
tti | -1.041 |
tails | -1.008 |
Heck | -0.985 |
Token | from |
Token ID | 422 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
edIn | +5.101 |
ification | +4.651 |
ified | +4.599 |
icians | +4.587 |
ifiers | +4.487 |
Neg logit contributions | |
berman | -3.455 |
HAEL | -3.355 |
tti | -3.284 |
tails | -3.245 |
mma | -3.147 |
Token | late |
Token ID | 2739 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
edIn | +2.266 |
ification | +1.977 |
icians | +1.963 |
ified | +1.957 |
itect | +1.942 |
Neg logit contributions | |
berman | -2.187 |
HAEL | -2.123 |
tti | -2.107 |
tails | -2.073 |
mma | -2.027 |
Token | all |
Token ID | 477 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
berman | +1.159 |
tti | +1.114 |
HAEL | +1.083 |
Heck | +1.074 |
tails | +1.071 |
Neg logit contributions | |
edIn | -1.455 |
icians | -1.261 |
itect | -1.258 |
ification | -1.245 |
ified | -1.234 |
Token | non |
Token ID | 1729 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
berman | +3.148 |
tti | +3.033 |
Heck | +2.838 |
HAEL | +2.832 |
train | +2.815 |
Neg logit contributions | |
edIn | -6.937 |
itect | -6.169 |
icians | -6.158 |
osate | -6.131 |
ification | -6.113 |
Token | farm |
Token ID | 43323 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
berman | +1.814 |
tti | +1.765 |
HAEL | +1.703 |
tails | +1.698 |
train | +1.693 |
Neg logit contributions | |
edIn | -2.574 |
icians | -2.213 |
ification | -2.208 |
itect | -2.198 |
ified | -2.174 |
Token | sectors |
Token ID | 16020 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
edIn | +0.024 |
icians | +0.021 |
ification | +0.021 |
itect | +0.021 |
ified | +0.021 |
Neg logit contributions | |
berman | -0.015 |
tti | -0.015 |
HAEL | -0.015 |
tails | -0.014 |
Heck | -0.014 |
Token | ( |
Token ID | 357 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
berman | +2.061 |
tti | +1.996 |
HAEL | +1.943 |
Heck | +1.870 |
tails | +1.866 |
Neg logit contributions | |
edIn | -4.290 |
icians | -3.813 |
itect | -3.783 |
ification | -3.762 |
ified | -3.733 |
Token | author |
Token ID | 9800 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
edIn | +1.982 |
ification | +1.755 |
icians | +1.754 |
ified | +1.748 |
itect | +1.745 |
Neg logit contributions | |
berman | -1.260 |
HAEL | -1.209 |
tti | -1.205 |
tails | -1.168 |
Heck | -1.145 |
Token | � |
Token ID | 447 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
edIn | +11.660 |
ification | +11.085 |
ified | +11.010 |
icians | +10.615 |
itect | +10.427 |
Neg logit contributions | |
berman | -8.570 |
HAEL | -8.157 |
tti | -7.946 |
tails | -7.926 |
Klux | -7.718 |
Token | � |
Token ID | 247 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
edIn | +3.504 |
icians | +3.013 |
itect | +3.009 |
ification | +2.995 |
ified | +2.976 |
Neg logit contributions | |
berman | -2.898 |
tti | -2.771 |
HAEL | -2.769 |
tails | -2.705 |
mma | -2.647 |
Token | s |
Token ID | 82 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
edIn | +1.351 |
icians | +1.200 |
ification | +1.198 |
itect | +1.192 |
ified | +1.192 |
Neg logit contributions | |
berman | -0.804 |
HAEL | -0.767 |
tti | -0.767 |
tails | -0.743 |
Heck | -0.725 |
Token | analysis |
Token ID | 3781 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
edIn | +3.774 |
ification | +3.336 |
icians | +3.322 |
ified | +3.316 |
itect | +3.283 |
Neg logit contributions | |
berman | -3.103 |
HAEL | -3.003 |
tti | -2.971 |
tails | -2.923 |
Heck | -2.819 |
Token | of |
Token ID | 286 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
edIn | +0.132 |
icians | +0.115 |
ification | +0.115 |
itect | +0.115 |
ified | +0.114 |
Neg logit contributions | |
berman | -0.104 |
tti | -0.101 |
HAEL | -0.100 |
tails | -0.097 |
Heck | -0.096 |