Token | air |
Token ID | 1633 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
rons | +3.808 |
liam | +3.676 |
enegger | +3.271 |
oons | +2.964 |
ries | +2.844 |
Neg logit contributions | |
ciplinary | -3.103 |
CLASSIFIED | -2.966 |
vantage | -2.849 |
ffect | -2.747 |
unexplained | -2.700 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
rons | +1.251 |
liam | +1.222 |
enegger | +1.106 |
oons | +1.015 |
ries | +0.982 |
Neg logit contributions | |
ciplinary | -0.691 |
CLASSIFIED | -0.647 |
vantage | -0.625 |
ffect | -0.596 |
unexplained | -0.585 |
Token | or |
Token ID | 393 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
rons | +1.863 |
liam | +1.814 |
enegger | +1.652 |
oons | +1.520 |
ries | +1.470 |
Neg logit contributions | |
ciplinary | -0.955 |
CLASSIFIED | -0.899 |
vantage | -0.848 |
ffect | -0.815 |
unexplained | -0.804 |
Token | you |
Token ID | 345 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
rons | +3.038 |
liam | +2.953 |
enegger | +2.689 |
oons | +2.473 |
rises | +2.388 |
Neg logit contributions | |
ciplinary | -1.612 |
CLASSIFIED | -1.517 |
vantage | -1.437 |
ffect | -1.376 |
unexplained | -1.356 |
Token | may |
Token ID | 743 |
Feature activation | +8.50e+00 |
Pos logit contributions | |
rons | +5.782 |
liam | +5.621 |
enegger | +5.141 |
oons | +4.792 |
ries | +4.664 |
Neg logit contributions | |
ciplinary | -2.184 |
CLASSIFIED | -2.069 |
vantage | -1.899 |
ffect | -1.780 |
unexplained | -1.715 |
Token | even |
Token ID | 772 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
rons | +8.963 |
liam | +8.682 |
enegger | +7.709 |
oons | +7.093 |
ries | +6.904 |
Neg logit contributions | |
ciplinary | -5.908 |
CLASSIFIED | -5.890 |
vantage | -5.465 |
ffect | -5.083 |
unexplained | -4.975 |
Token | want |
Token ID | 765 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
rons | +14.315 |
liam | +13.808 |
enegger | +11.836 |
oons | +10.953 |
ries | +10.755 |
Neg logit contributions | |
CLASSIFIED | -11.683 |
ciplinary | -10.977 |
vantage | -10.416 |
ffect | -9.521 |
terday | -9.330 |
Token | to |
Token ID | 284 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
rons | +3.961 |
liam | +3.847 |
enegger | +3.497 |
oons | +3.245 |
ries | +3.150 |
Neg logit contributions | |
ciplinary | -1.898 |
CLASSIFIED | -1.782 |
vantage | -1.682 |
ffect | -1.598 |
unexplained | -1.551 |
Token | fly |
Token ID | 6129 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
rons | +4.714 |
liam | +4.563 |
enegger | +4.092 |
oons | +3.754 |
ries | +3.624 |
Neg logit contributions | |
ciplinary | -3.141 |
CLASSIFIED | -3.010 |
vantage | -2.861 |
ffect | -2.733 |
unexplained | -2.673 |
Token | yourself |
Token ID | 3511 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
rons | +2.549 |
liam | +2.479 |
enegger | +2.266 |
oons | +2.089 |
rises | +2.025 |
Neg logit contributions | |
ciplinary | -1.196 |
CLASSIFIED | -1.124 |
vantage | -1.063 |
ffect | -1.009 |
unexplained | -0.992 |
Token | . |
Token ID | 13 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
ciplinary | +0.406 |
CLASSIFIED | +0.376 |
vantage | +0.361 |
unexplained | +0.351 |
respectively | +0.349 |
Neg logit contributions | |
rons | -0.806 |
liam | -0.786 |
enegger | -0.720 |
oons | -0.659 |
rises | -0.640 |
Token | Rud |
Token ID | 17421 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
rons | +0.292 |
liam | +0.283 |
enegger | +0.255 |
oons | +0.233 |
rises | +0.225 |
Neg logit contributions | |
ciplinary | -0.189 |
CLASSIFIED | -0.175 |
vantage | -0.169 |
ffect | -0.163 |
respectively | -0.161 |
Token | erman |
Token ID | 2224 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
rons | +5.776 |
liam | +5.561 |
enegger | +4.937 |
oons | +4.467 |
ries | +4.290 |
Neg logit contributions | |
ciplinary | -4.891 |
CLASSIFIED | -4.714 |
vantage | -4.492 |
ffect | -4.348 |
unexplained | -4.288 |
Token | and |
Token ID | 290 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
rons | +3.171 |
liam | +3.083 |
enegger | +2.808 |
oons | +2.604 |
rises | +2.520 |
Neg logit contributions | |
ciplinary | -1.503 |
CLASSIFIED | -1.396 |
vantage | -1.321 |
ffect | -1.258 |
unexplained | -1.227 |
Token | Mike |
Token ID | 4995 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
rons | +0.129 |
liam | +0.124 |
enegger | +0.112 |
oons | +0.103 |
rises | +0.100 |
Neg logit contributions | |
ciplinary | -0.081 |
CLASSIFIED | -0.077 |
vantage | -0.073 |
respectively | -0.071 |
ffect | -0.071 |
Token | G |
Token ID | 402 |
Feature activation | +8.06e+00 |
Pos logit contributions | |
rons | +0.603 |
liam | +0.584 |
enegger | +0.531 |
oons | +0.484 |
rises | +0.469 |
Neg logit contributions | |
ciplinary | -0.376 |
CLASSIFIED | -0.352 |
vantage | -0.339 |
ffect | -0.329 |
respectively | -0.324 |
Token | abb |
Token ID | 6485 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
rons | +7.731 |
liam | +7.420 |
enegger | +6.530 |
oons | +5.970 |
ries | +5.846 |
Neg logit contributions | |
ciplinary | -6.536 |
CLASSIFIED | -6.449 |
vantage | -5.995 |
ffect | -5.823 |
terday | -5.811 |
Token | ard |
Token ID | 446 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
rons | +7.912 |
liam | +7.234 |
enegger | +5.688 |
ries | +4.972 |
oons | +4.870 |
Neg logit contributions | |
CLASSIFIED | -17.767 |
ciplinary | -16.680 |
unexplained | -16.153 |
terday | -16.115 |
vantage | -16.022 |
Token | will |
Token ID | 481 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
rons | +3.357 |
liam | +3.260 |
enegger | +2.962 |
oons | +2.722 |
rises | +2.628 |
Neg logit contributions | |
ciplinary | -1.905 |
CLASSIFIED | -1.788 |
vantage | -1.707 |
ffect | -1.634 |
respectively | -1.611 |
Token | also |
Token ID | 635 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
rons | +5.296 |
liam | +5.122 |
enegger | +4.596 |
oons | +4.203 |
ries | +4.053 |
Neg logit contributions | |
ciplinary | -3.618 |
CLASSIFIED | -3.468 |
vantage | -3.304 |
ffect | -3.163 |
unexplained | -3.101 |
Token | address |
Token ID | 2209 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
rons | +10.931 |
liam | +10.511 |
enegger | +9.199 |
oons | +8.423 |
ries | +8.202 |
Neg logit contributions | |
CLASSIFIED | -8.679 |
ciplinary | -8.354 |
vantage | -7.997 |
ffect | -7.436 |
terday | -7.353 |
Token | the |
Token ID | 262 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
rons | +1.662 |
liam | +1.613 |
enegger | +1.472 |
oons | +1.349 |
rises | +1.307 |
Neg logit contributions | |
ciplinary | -0.912 |
CLASSIFIED | -0.856 |
vantage | -0.813 |
ffect | -0.778 |
respectively | -0.772 |
Token | is |
Token ID | 318 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
rons | +1.170 |
liam | +1.147 |
enegger | +1.050 |
oons | +0.966 |
rises | +0.939 |
Neg logit contributions | |
ciplinary | -0.514 |
CLASSIFIED | -0.472 |
vantage | -0.448 |
ffect | -0.429 |
respectively | -0.420 |
Token | dens |
Token ID | 29509 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
rons | +2.829 |
liam | +2.754 |
enegger | +2.506 |
oons | +2.308 |
rises | +2.235 |
Neg logit contributions | |
ciplinary | -1.509 |
CLASSIFIED | -1.409 |
vantage | -1.336 |
ffect | -1.285 |
unexplained | -1.267 |
Token | er |
Token ID | 263 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
rons | +3.660 |
liam | +3.534 |
enegger | +3.139 |
oons | +2.835 |
rises | +2.718 |
Neg logit contributions | |
ciplinary | -3.115 |
CLASSIFIED | -2.967 |
vantage | -2.864 |
ffect | -2.763 |
unexplained | -2.717 |
Token | than |
Token ID | 621 |
Feature activation | +7.95e+00 |
Pos logit contributions | |
rons | +5.634 |
liam | +5.417 |
enegger | +4.807 |
oons | +4.370 |
ries | +4.222 |
Neg logit contributions | |
ciplinary | -4.499 |
CLASSIFIED | -4.350 |
vantage | -4.142 |
ffect | -3.968 |
unexplained | -3.887 |
Token | zinc |
Token ID | 31861 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
rons | +7.985 |
liam | +7.641 |
enegger | +6.781 |
oons | +6.147 |
ries | +6.019 |
Neg logit contributions | |
ciplinary | -6.139 |
CLASSIFIED | -5.929 |
vantage | -5.553 |
ffect | -5.347 |
terday | -5.230 |
Token | sulf |
Token ID | 22443 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
rons | +11.108 |
liam | +10.488 |
enegger | +9.524 |
oons | +8.791 |
ries | +8.633 |
Neg logit contributions | |
ciplinary | -7.007 |
CLASSIFIED | -6.850 |
vantage | -6.348 |
ffect | -6.107 |
terday | -5.804 |
Token | ate |
Token ID | 378 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
rons | +11.237 |
liam | +10.652 |
enegger | +8.592 |
oons | +8.564 |
ries | +7.925 |
Neg logit contributions | |
CLASSIFIED | -14.636 |
ciplinary | -13.940 |
vantage | -12.739 |
unexplained | -12.733 |
ffect | -12.615 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
rons | +9.505 |
liam | +9.047 |
enegger | +8.174 |
oons | +7.600 |
ries | +7.455 |
Neg logit contributions | |
ciplinary | -5.651 |
CLASSIFIED | -5.549 |
vantage | -5.114 |
ffect | -4.858 |
unexplained | -4.687 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ciplinary | +0.858 |
CLASSIFIED | +0.777 |
vantage | +0.757 |
respectively | +0.743 |
ffect | +0.743 |
Neg logit contributions | |
rons | -1.898 |
liam | -1.883 |
enegger | -1.728 |
oons | -1.594 |
rises | -1.551 |
Token | zinc |
Token ID | 31861 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
ciplinary | +1.104 |
CLASSIFIED | +1.024 |
ffect | +1.010 |
vantage | +1.007 |
respectively | +0.998 |
Neg logit contributions | |
rons | -1.527 |
liam | -1.522 |
enegger | -1.370 |
oons | -1.240 |
rises | -1.204 |
Token | solution |
Token ID | 4610 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
rons | +5.382 |
liam | +5.160 |
enegger | +4.591 |
oons | +4.167 |
ries | +4.005 |
Neg logit contributions | |
ciplinary | -4.466 |
CLASSIFIED | -4.302 |
vantage | -4.109 |
ffect | -3.961 |
unexplained | -3.888 |
Token | the |
Token ID | 262 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
rons | +6.631 |
liam | +6.435 |
enegger | +5.780 |
oons | +5.287 |
ries | +5.131 |
Neg logit contributions | |
ciplinary | -4.269 |
CLASSIFIED | -4.115 |
vantage | -3.870 |
ffect | -3.722 |
terday | -3.593 |
Token | final |
Token ID | 2457 |
Feature activation | +8.11e+00 |
Pos logit contributions | |
rons | +2.632 |
liam | +2.547 |
enegger | +2.295 |
oons | +2.103 |
rises | +2.027 |
Neg logit contributions | |
ciplinary | -1.698 |
CLASSIFIED | -1.606 |
vantage | -1.535 |
ffect | -1.474 |
unexplained | -1.451 |
Token | pro |
Token ID | 386 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
rons | +8.243 |
liam | +7.984 |
enegger | +7.065 |
oons | +6.481 |
ries | +6.317 |
Neg logit contributions | |
ciplinary | -6.005 |
CLASSIFIED | -5.826 |
vantage | -5.540 |
ffect | -5.256 |
terday | -5.077 |
Token | - |
Token ID | 12 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
ciplinary | +1.755 |
CLASSIFIED | +1.569 |
vantage | +1.502 |
ffect | +1.418 |
respectively | +1.344 |
Neg logit contributions | |
rons | -4.825 |
liam | -4.690 |
enegger | -4.365 |
oons | -4.054 |
rises | -3.934 |
Token | independence |
Token ID | 39894 |
Feature activation | +8.05e+00 |
Pos logit contributions | |
ciplinary | +2.867 |
CLASSIFIED | +2.630 |
vantage | +2.590 |
ffect | +2.419 |
respectively | +2.325 |
Neg logit contributions | |
rons | -6.184 |
liam | -5.957 |
enegger | -5.658 |
oons | -5.155 |
aires | -4.827 |
Token | rally |
Token ID | 7903 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
rons | +7.744 |
liam | +7.488 |
enegger | +6.500 |
oons | +6.022 |
ries | +5.830 |
Neg logit contributions | |
ciplinary | -6.377 |
CLASSIFIED | -6.261 |
vantage | -5.923 |
ffect | -5.623 |
terday | -5.480 |
Token | at |
Token ID | 379 |
Feature activation | +8.34e+00 |
Pos logit contributions | |
rons | +14.663 |
liam | +13.791 |
enegger | +11.753 |
ries | +11.335 |
oons | +11.279 |
Neg logit contributions | |
CLASSIFIED | -10.753 |
ciplinary | -10.232 |
vantage | -9.846 |
ffect | -8.967 |
userc | -8.702 |
Token | Plaza |
Token ID | 23280 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
rons | +8.703 |
liam | +8.420 |
enegger | +7.533 |
oons | +6.883 |
ries | +6.694 |
Neg logit contributions | |
ciplinary | -5.821 |
CLASSIFIED | -5.678 |
vantage | -5.292 |
ffect | -5.105 |
unexplained | -4.893 |
Token | Esp |
Token ID | 20386 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
rons | +0.714 |
liam | +0.693 |
enegger | +0.629 |
oons | +0.576 |
rises | +0.552 |
Neg logit contributions | |
ciplinary | -0.454 |
CLASSIFIED | -0.429 |
vantage | -0.409 |
ffect | -0.393 |
respectively | -0.389 |
Token | ana |
Token ID | 2271 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
rons | +1.183 |
liam | +1.140 |
enegger | +1.029 |
oons | +0.905 |
rises | +0.882 |
Neg logit contributions | |
ciplinary | -0.967 |
CLASSIFIED | -0.892 |
vantage | -0.886 |
ffect | -0.847 |
respectively | -0.832 |
Token | tonight |
Token ID | 9975 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
rons | +2.262 |
liam | +2.194 |
enegger | +1.994 |
oons | +1.825 |
rises | +1.761 |
Neg logit contributions | |
ciplinary | -1.346 |
CLASSIFIED | -1.262 |
vantage | -1.210 |
ffect | -1.162 |
respectively | -1.138 |
Token | All |
Token ID | 3237 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
ciplinary | +2.021 |
CLASSIFIED | +1.929 |
vantage | +1.850 |
ffect | +1.816 |
terday | +1.749 |
Neg logit contributions | |
rons | -3.387 |
liam | -3.254 |
enegger | -2.984 |
oons | -2.702 |
rises | -2.589 |
Token | the |
Token ID | 262 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
rons | +4.238 |
liam | +4.111 |
enegger | +3.715 |
oons | +3.416 |
ries | +3.302 |
Neg logit contributions | |
ciplinary | -2.503 |
CLASSIFIED | -2.371 |
vantage | -2.257 |
ffect | -2.153 |
unexplained | -2.107 |
Token | fish |
Token ID | 5916 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
rons | +4.486 |
liam | +4.343 |
enegger | +3.906 |
oons | +3.574 |
ries | +3.449 |
Neg logit contributions | |
ciplinary | -2.967 |
CLASSIFIED | -2.822 |
vantage | -2.696 |
ffect | -2.581 |
unexplained | -2.523 |
Token | died |
Token ID | 3724 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
rons | +7.671 |
liam | +7.431 |
enegger | +6.677 |
oons | +6.214 |
ries | +6.064 |
Neg logit contributions | |
ciplinary | -4.185 |
CLASSIFIED | -3.980 |
vantage | -3.753 |
ffect | -3.562 |
terday | -3.454 |
Token | , |
Token ID | 11 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
rons | +4.562 |
liam | +4.414 |
enegger | +3.972 |
oons | +3.664 |
ries | +3.568 |
Neg logit contributions | |
ciplinary | -2.728 |
CLASSIFIED | -2.608 |
vantage | -2.458 |
ffect | -2.341 |
terday | -2.272 |
Token | even |
Token ID | 772 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
rons | +4.625 |
liam | +4.493 |
enegger | +4.080 |
oons | +3.773 |
rises | +3.655 |
Neg logit contributions | |
ciplinary | -2.356 |
CLASSIFIED | -2.224 |
vantage | -2.105 |
ffect | -1.989 |
terday | -1.938 |
Token | chickens |
Token ID | 25972 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
rons | +14.790 |
liam | +14.404 |
enegger | +12.717 |
oons | +11.813 |
ries | +11.565 |
Neg logit contributions | |
ciplinary | -9.847 |
CLASSIFIED | -9.529 |
vantage | -8.788 |
ffect | -8.292 |
terday | -7.986 |
Token | and |
Token ID | 290 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
rons | +4.304 |
liam | +4.171 |
enegger | +3.782 |
oons | +3.497 |
ries | +3.386 |
Neg logit contributions | |
ciplinary | -2.300 |
CLASSIFIED | -2.180 |
vantage | -2.053 |
ffect | -1.953 |
terday | -1.900 |
Token | ducks |
Token ID | 39694 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
rons | +4.345 |
liam | +4.206 |
enegger | +3.752 |
oons | +3.431 |
ries | +3.307 |
Neg logit contributions | |
ciplinary | -3.181 |
CLASSIFIED | -3.040 |
vantage | -2.903 |
ffect | -2.787 |
terday | -2.725 |
Token | that |
Token ID | 326 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
rons | +6.895 |
liam | +6.663 |
enegger | +6.002 |
oons | +5.546 |
ries | +5.393 |
Neg logit contributions | |
ciplinary | -4.061 |
CLASSIFIED | -3.913 |
vantage | -3.640 |
ffect | -3.461 |
terday | -3.379 |
Token | drank |
Token ID | 24070 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
rons | +8.292 |
liam | +8.043 |
enegger | +7.237 |
oons | +6.758 |
ries | +6.540 |
Neg logit contributions | |
ciplinary | -4.288 |
CLASSIFIED | -4.101 |
vantage | -3.848 |
ffect | -3.632 |
unexplained | -3.456 |
Token | spending |
Token ID | 4581 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
rons | +4.691 |
liam | +4.521 |
enegger | +3.995 |
oons | +3.596 |
ries | +3.457 |
Neg logit contributions | |
ciplinary | -4.222 |
CLASSIFIED | -4.054 |
vantage | -3.913 |
ffect | -3.767 |
terday | -3.691 |
Token | increases |
Token ID | 5732 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
rons | +7.398 |
liam | +7.120 |
enegger | +6.188 |
oons | +5.658 |
ries | +5.523 |
Neg logit contributions | |
ciplinary | -6.686 |
CLASSIFIED | -6.481 |
vantage | -6.253 |
ffect | -5.959 |
terday | -5.868 |
Token | combined |
Token ID | 5929 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
rons | +7.062 |
liam | +6.839 |
enegger | +6.162 |
oons | +5.693 |
ries | +5.548 |
Neg logit contributions | |
ciplinary | -3.894 |
CLASSIFIED | -3.702 |
vantage | -3.516 |
ffect | -3.337 |
terday | -3.191 |
Token | with |
Token ID | 351 |
Feature activation | +9.33e+00 |
Pos logit contributions | |
rons | +2.633 |
liam | +2.543 |
enegger | +2.251 |
oons | +2.044 |
ries | +1.984 |
Neg logit contributions | |
ciplinary | -2.077 |
CLASSIFIED | -2.016 |
vantage | -1.922 |
ffect | -1.837 |
terday | -1.808 |
Token | big |
Token ID | 1263 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
rons | +10.058 |
liam | +9.787 |
enegger | +8.753 |
oons | +8.025 |
ries | +7.868 |
Neg logit contributions | |
ciplinary | -6.088 |
CLASSIFIED | -5.891 |
vantage | -5.742 |
ffect | -5.346 |
terday | -5.241 |
Token | new |
Token ID | 649 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
rons | +10.166 |
liam | +9.954 |
enegger | +8.655 |
oons | +7.943 |
ries | +7.723 |
Neg logit contributions | |
ciplinary | -8.634 |
CLASSIFIED | -8.394 |
vantage | -8.210 |
ffect | -7.753 |
terday | -7.495 |
Token | tax |
Token ID | 1687 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
rons | +12.626 |
liam | +12.377 |
enegger | +10.526 |
oons | +9.749 |
ries | +9.748 |
Neg logit contributions | |
ciplinary | -11.390 |
vantage | -11.132 |
CLASSIFIED | -11.053 |
ffect | -10.258 |
terday | -9.996 |
Token | cuts |
Token ID | 6630 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
rons | +10.072 |
liam | +9.593 |
enegger | +7.850 |
ries | +7.536 |
rises | +7.363 |
Neg logit contributions | |
ciplinary | -11.194 |
CLASSIFIED | -10.901 |
vantage | -10.757 |
ffect | -10.077 |
terday | -9.990 |
Token | — |
Token ID | 960 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
rons | +5.762 |
liam | +5.571 |
enegger | +5.043 |
oons | +4.659 |
ries | +4.535 |
Neg logit contributions | |
ciplinary | -3.145 |
CLASSIFIED | -2.998 |
vantage | -2.815 |
ffect | -2.677 |
unexplained | -2.590 |
Token | without |
Token ID | 19419 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
rons | +2.165 |
liam | +2.091 |
enegger | +1.891 |
oons | +1.722 |
ries | +1.656 |
Neg logit contributions | |
ciplinary | -1.451 |
CLASSIFIED | -1.371 |
vantage | -1.317 |
ffect | -1.265 |
respectively | -1.239 |
Token | vastly |
Token ID | 22056 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ciplinary | +0.406 |
CLASSIFIED | +0.378 |
vantage | +0.356 |
unexplained | +0.355 |
probation | +0.354 |
Neg logit contributions | |
rons | -0.737 |
liam | -0.715 |
enegger | -0.657 |
oons | -0.597 |
rises | -0.579 |
Token | baking |
Token ID | 16871 |
Feature activation | +7.55e+00 |
Pos logit contributions | |
rons | +6.037 |
liam | +5.813 |
enegger | +5.152 |
oons | +4.715 |
ries | +4.623 |
Neg logit contributions | |
ciplinary | -4.493 |
CLASSIFIED | -4.354 |
vantage | -4.168 |
ffect | -3.951 |
terday | -3.894 |
Token | recipes |
Token ID | 14296 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
rons | +7.554 |
liam | +7.277 |
enegger | +6.467 |
oons | +5.951 |
ries | +5.824 |
Neg logit contributions | |
ciplinary | -5.709 |
CLASSIFIED | -5.549 |
vantage | -5.218 |
ffect | -4.987 |
terday | -4.976 |
Token | like |
Token ID | 588 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
ciplinary | +0.987 |
CLASSIFIED | +0.901 |
vantage | +0.887 |
respectively | +0.859 |
ffect | +0.846 |
Neg logit contributions | |
rons | -1.930 |
liam | -1.891 |
enegger | -1.707 |
oons | -1.574 |
rises | -1.519 |
Token | cookies |
Token ID | 14746 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
rons | +4.354 |
liam | +4.221 |
enegger | +3.814 |
oons | +3.501 |
ries | +3.378 |
Neg logit contributions | |
ciplinary | -2.628 |
CLASSIFIED | -2.488 |
vantage | -2.369 |
ffect | -2.269 |
unexplained | -2.225 |
Token | and |
Token ID | 290 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
ciplinary | +0.225 |
CLASSIFIED | +0.207 |
vantage | +0.200 |
respectively | +0.191 |
ffect | +0.190 |
Neg logit contributions | |
rons | -0.472 |
liam | -0.461 |
enegger | -0.417 |
oons | -0.384 |
rises | -0.375 |
Token | muff |
Token ID | 27563 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
rons | +3.278 |
liam | +3.169 |
enegger | +2.840 |
oons | +2.580 |
rises | +2.479 |
Neg logit contributions | |
ciplinary | -2.431 |
CLASSIFIED | -2.312 |
vantage | -2.217 |
ffect | -2.137 |
unexplained | -2.107 |
Token | ins |
Token ID | 1040 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
rons | +10.837 |
liam | +9.689 |
enegger | +8.106 |
oons | +7.956 |
ries | +7.907 |
Neg logit contributions | |
CLASSIFIED | -14.092 |
ciplinary | -13.796 |
vantage | -12.866 |
unexplained | -12.705 |
probation | -12.695 |
Token | . |
Token ID | 13 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
rons | +3.200 |
liam | +3.110 |
enegger | +2.809 |
oons | +2.581 |
rises | +2.495 |
Neg logit contributions | |
ciplinary | -1.855 |
CLASSIFIED | -1.748 |
vantage | -1.670 |
ffect | -1.598 |
respectively | -1.570 |
Token | Ground |
Token ID | 13706 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
ciplinary | +1.757 |
CLASSIFIED | +1.666 |
vantage | +1.635 |
respectively | +1.591 |
ffect | +1.549 |
Neg logit contributions | |
rons | -3.690 |
liam | -3.561 |
enegger | -3.317 |
oons | -2.977 |
rises | -2.946 |
Token | fl |
Token ID | 781 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
ciplinary | +3.543 |
CLASSIFIED | +3.249 |
vantage | +3.228 |
respectively | +3.181 |
unexplained | +3.175 |
Neg logit contributions | |
rons | -6.265 |
liam | -6.181 |
enegger | -5.639 |
oons | -5.150 |
rises | -4.972 |
Token | ax |
Token ID | 897 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
rons | +4.322 |
liam | +4.131 |
enegger | +3.562 |
oons | +3.283 |
ries | +3.155 |
Neg logit contributions | |
ciplinary | -4.268 |
CLASSIFIED | -4.223 |
vantage | -3.935 |
ffect | -3.827 |
unexplained | -3.805 |
Token | they |
Token ID | 484 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
ciplinary | +1.779 |
CLASSIFIED | +1.693 |
vantage | +1.593 |
unexplained | +1.582 |
respectively | +1.564 |
Neg logit contributions | |
rons | -2.860 |
liam | -2.795 |
enegger | -2.555 |
oons | -2.311 |
ries | -2.200 |
Token | will |
Token ID | 481 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ciplinary | +1.361 |
CLASSIFIED | +1.178 |
vantage | +1.166 |
respectively | +1.117 |
probation | +1.110 |
Neg logit contributions | |
rons | -3.520 |
liam | -3.448 |
enegger | -3.196 |
oons | -2.972 |
ries | -2.863 |
Token | arrange |
Token ID | 21674 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
rons | +1.161 |
liam | +1.126 |
enegger | +1.023 |
oons | +0.937 |
ries | +0.901 |
Neg logit contributions | |
ciplinary | -0.691 |
CLASSIFIED | -0.647 |
vantage | -0.619 |
ffect | -0.597 |
respectively | -0.587 |
Token | the |
Token ID | 262 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
ciplinary | +1.578 |
CLASSIFIED | +1.475 |
vantage | +1.385 |
probation | +1.351 |
unexplained | +1.345 |
Neg logit contributions | |
rons | -3.487 |
liam | -3.388 |
enegger | -3.126 |
oons | -2.868 |
ries | -2.748 |
Token | perfect |
Token ID | 2818 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
ciplinary | +0.189 |
CLASSIFIED | +0.177 |
vantage | +0.168 |
probation | +0.164 |
unexplained | +0.163 |
Neg logit contributions | |
rons | -0.315 |
liam | -0.307 |
enegger | -0.279 |
oons | -0.254 |
ries | -0.243 |
Token | deton |
Token ID | 20413 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
rons | +5.473 |
liam | +5.287 |
enegger | +4.760 |
oons | +4.382 |
ries | +4.253 |
Neg logit contributions | |
ciplinary | -3.432 |
CLASSIFIED | -3.253 |
vantage | -3.115 |
ffect | -2.975 |
unexplained | -2.888 |
Token | ation |
Token ID | 341 |
Feature activation | +7.23e+00 |
Pos logit contributions | |
rons | +9.395 |
liam | +8.762 |
enegger | +7.092 |
oons | +6.496 |
ries | +6.317 |
Neg logit contributions | |
ciplinary | -14.710 |
CLASSIFIED | -14.338 |
vantage | -13.478 |
ffect | -13.338 |
terday | -13.319 |
Token | of |
Token ID | 286 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
rons | +8.007 |
liam | +7.682 |
enegger | +6.911 |
oons | +6.441 |
ries | +6.265 |
Neg logit contributions | |
ciplinary | -4.745 |
CLASSIFIED | -4.490 |
vantage | -4.233 |
ffect | -4.047 |
unexplained | -3.902 |
Token | the |
Token ID | 262 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
rons | +2.386 |
liam | +2.324 |
enegger | +2.118 |
oons | +1.948 |
ries | +1.885 |
Neg logit contributions | |
ciplinary | -1.213 |
CLASSIFIED | -1.148 |
vantage | -1.079 |
ffect | -1.030 |
unexplained | -1.018 |
Token | PAT |
Token ID | 28748 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
rons | +2.204 |
liam | +2.152 |
enegger | +1.945 |
oons | +1.767 |
rises | +1.697 |
Neg logit contributions | |
ciplinary | -1.397 |
CLASSIFIED | -1.326 |
vantage | -1.252 |
ffect | -1.216 |
unexplained | -1.213 |
Token | super |
Token ID | 2208 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
rons | +6.758 |
liam | +6.506 |
enegger | +5.827 |
oons | +5.405 |
ries | +5.261 |
Neg logit contributions | |
ciplinary | -3.956 |
CLASSIFIED | -3.735 |
vantage | -3.528 |
ffect | -3.419 |
terday | -3.333 |
Token | to |
Token ID | 284 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ciplinary | +0.481 |
CLASSIFIED | +0.447 |
vantage | +0.422 |
unexplained | +0.406 |
ffect | +0.399 |
Neg logit contributions | |
rons | -1.033 |
liam | -1.001 |
enegger | -0.931 |
oons | -0.846 |
rises | -0.821 |
Token | top |
Token ID | 1353 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
rons | +1.823 |
liam | +1.768 |
enegger | +1.600 |
oons | +1.456 |
rises | +1.402 |
Neg logit contributions | |
ciplinary | -1.198 |
CLASSIFIED | -1.127 |
vantage | -1.083 |
ffect | -1.045 |
unexplained | -1.030 |
Token | mine |
Token ID | 6164 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ciplinary | +1.487 |
CLASSIFIED | +1.367 |
vantage | +1.288 |
unexplained | +1.218 |
ffect | +1.218 |
Neg logit contributions | |
rons | -3.620 |
liam | -3.511 |
enegger | -3.265 |
oons | -2.983 |
rises | -2.865 |
Token | with |
Token ID | 351 |
Feature activation | +7.33e+00 |
Pos logit contributions | |
rons | +3.470 |
liam | +3.369 |
enegger | +3.060 |
oons | +2.816 |
ries | +2.720 |
Neg logit contributions | |
ciplinary | -1.896 |
CLASSIFIED | -1.789 |
vantage | -1.701 |
ffect | -1.623 |
unexplained | -1.589 |
Token | frozen |
Token ID | 12912 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
rons | +7.874 |
liam | +7.607 |
enegger | +6.732 |
oons | +6.256 |
ries | +6.148 |
Neg logit contributions | |
ciplinary | -5.007 |
CLASSIFIED | -4.829 |
vantage | -4.558 |
ffect | -4.367 |
terday | -4.251 |
Token | cher |
Token ID | 21382 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
ciplinary | +3.519 |
CLASSIFIED | +3.360 |
unexplained | +3.242 |
respectively | +3.223 |
probation | +3.199 |
Neg logit contributions | |
rons | -4.424 |
liam | -4.265 |
enegger | -3.981 |
oons | -3.494 |
rises | -3.341 |
Token | ries |
Token ID | 1678 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
rons | +5.815 |
liam | +4.937 |
ries | +3.911 |
oons | +2.679 |
enegger | +2.435 |
Neg logit contributions | |
CLASSIFIED | -19.343 |
ciplinary | -18.836 |
vantage | -17.695 |
unexplained | -17.604 |
probation | -17.496 |
Token | , |
Token ID | 11 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
rons | +1.401 |
liam | +1.366 |
enegger | +1.245 |
oons | +1.143 |
rises | +1.109 |
Neg logit contributions | |
ciplinary | -0.710 |
CLASSIFIED | -0.666 |
vantage | -0.635 |
ffect | -0.607 |
respectively | -0.595 |
Token | which |
Token ID | 543 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
rons | +0.563 |
liam | +0.547 |
enegger | +0.502 |
oons | +0.458 |
rises | +0.443 |
Neg logit contributions | |
ciplinary | -0.308 |
CLASSIFIED | -0.288 |
vantage | -0.275 |
unexplained | -0.264 |
respectively | -0.264 |
Token | are |
Token ID | 389 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ciplinary | +1.091 |
CLASSIFIED | +1.008 |
vantage | +0.979 |
respectively | +0.938 |
ffect | +0.937 |
Neg logit contributions | |
rons | -2.293 |
liam | -2.233 |
enegger | -2.061 |
oons | -1.874 |
rises | -1.831 |
Token | so |
Token ID | 523 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
ciplinary | +1.129 |
CLASSIFIED | +1.034 |
vantage | +0.985 |
respectively | +0.974 |
unexplained | +0.966 |
Neg logit contributions | |
rons | -2.227 |
liam | -2.180 |
enegger | -1.999 |
oons | -1.817 |
rises | -1.778 |
Token | We |
Token ID | 775 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ciplinary | +0.286 |
CLASSIFIED | +0.274 |
vantage | +0.263 |
ffect | +0.255 |
respectively | +0.249 |
Neg logit contributions | |
rons | -0.505 |
liam | -0.490 |
enegger | -0.448 |
oons | -0.405 |
rises | -0.396 |
Token | 'd |
Token ID | 1549 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
rons | +3.236 |
liam | +3.149 |
enegger | +2.878 |
oons | +2.670 |
ries | +2.589 |
Neg logit contributions | |
ciplinary | -1.427 |
CLASSIFIED | -1.324 |
vantage | -1.254 |
ffect | -1.188 |
unexplained | -1.158 |
Token | lose |
Token ID | 4425 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
rons | +7.264 |
liam | +7.002 |
enegger | +6.309 |
oons | +5.816 |
rises | +5.634 |
Neg logit contributions | |
ciplinary | -4.289 |
CLASSIFIED | -4.263 |
vantage | -3.893 |
ffect | -3.648 |
terday | -3.571 |
Token | our |
Token ID | 674 |
Feature activation | +7.61e+00 |
Pos logit contributions | |
rons | +6.214 |
liam | +6.019 |
enegger | +5.422 |
oons | +5.029 |
ries | +4.876 |
Neg logit contributions | |
ciplinary | -3.442 |
CLASSIFIED | -3.261 |
vantage | -3.089 |
ffect | -2.914 |
terday | -2.843 |
Token | colorful |
Token ID | 20239 |
Feature activation | +8.70e+00 |
Pos logit contributions | |
rons | +8.084 |
liam | +7.823 |
enegger | +7.000 |
oons | +6.434 |
ries | +6.259 |
Neg logit contributions | |
ciplinary | -5.269 |
CLASSIFIED | -5.084 |
vantage | -4.878 |
ffect | -4.562 |
respectively | -4.451 |
Token | aur |
Token ID | 45714 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
rons | +8.819 |
liam | +8.554 |
enegger | +7.593 |
oons | +6.974 |
ries | +6.846 |
Neg logit contributions | |
ciplinary | -6.490 |
CLASSIFIED | -6.186 |
vantage | -6.023 |
ffect | -5.570 |
terday | -5.411 |
Token | oras |
Token ID | 41043 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
rons | +8.106 |
liam | +7.143 |
oons | +5.086 |
enegger | +4.716 |
ries | +4.596 |
Neg logit contributions | |
CLASSIFIED | -17.225 |
ciplinary | -16.699 |
vantage | -15.789 |
probation | -15.552 |
unexplained | -15.516 |
Token | , |
Token ID | 11 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
rons | +7.583 |
liam | +7.307 |
enegger | +6.613 |
oons | +6.154 |
ries | +5.980 |
Neg logit contributions | |
ciplinary | -4.026 |
CLASSIFIED | -3.841 |
vantage | -3.589 |
ffect | -3.361 |
terday | -3.295 |
Token | and |
Token ID | 290 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
rons | +6.205 |
liam | +6.022 |
enegger | +5.454 |
oons | +5.040 |
rises | +4.875 |
Neg logit contributions | |
ciplinary | -3.354 |
CLASSIFIED | -3.167 |
vantage | -3.007 |
ffect | -2.848 |
terday | -2.786 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
rons | +1.105 |
liam | +1.076 |
enegger | +0.982 |
oons | +0.896 |
ries | +0.862 |
Neg logit contributions | |
ciplinary | -0.636 |
CLASSIFIED | -0.600 |
vantage | -0.566 |
unexplained | -0.562 |
ffect | -0.552 |
Token | Van |
Token ID | 6656 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
rons | +2.087 |
liam | +2.037 |
enegger | +1.847 |
oons | +1.686 |
rises | +1.616 |
Neg logit contributions | |
ciplinary | -1.296 |
CLASSIFIED | -1.218 |
vantage | -1.160 |
unexplained | -1.154 |
ffect | -1.149 |
Token | lasting |
Token ID | 15727 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
rons | +1.658 |
liam | +1.607 |
enegger | +1.470 |
oons | +1.353 |
rises | +1.308 |
Neg logit contributions | |
ciplinary | -0.847 |
CLASSIFIED | -0.789 |
vantage | -0.744 |
ffect | -0.717 |
unexplained | -0.709 |
Token | that |
Token ID | 326 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ciplinary | +1.851 |
CLASSIFIED | +1.689 |
ffect | +1.644 |
vantage | +1.630 |
unexplained | +1.606 |
Neg logit contributions | |
rons | -3.461 |
liam | -3.373 |
enegger | -3.109 |
oons | -2.838 |
rises | -2.733 |
Token | will |
Token ID | 481 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
rons | +2.459 |
liam | +2.387 |
enegger | +2.173 |
oons | +2.000 |
ries | +1.931 |
Neg logit contributions | |
ciplinary | -1.319 |
CLASSIFIED | -1.240 |
vantage | -1.174 |
ffect | -1.129 |
unexplained | -1.106 |
Token | be |
Token ID | 307 |
Feature activation | +6.37e+00 |
Pos logit contributions | |
rons | +4.943 |
liam | +4.793 |
enegger | +4.278 |
oons | +3.953 |
ries | +3.827 |
Neg logit contributions | |
ciplinary | -3.060 |
CLASSIFIED | -2.980 |
vantage | -2.821 |
ffect | -2.614 |
unexplained | -2.553 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
rons | +7.411 |
liam | +7.228 |
enegger | +6.496 |
oons | +6.010 |
ries | +5.875 |
Neg logit contributions | |
ciplinary | -3.779 |
CLASSIFIED | -3.649 |
vantage | -3.487 |
ffect | -3.217 |
terday | -3.139 |
Token | even |
Token ID | 772 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
rons | +1.670 |
liam | +1.628 |
enegger | +1.483 |
oons | +1.371 |
rises | +1.324 |
Neg logit contributions | |
ciplinary | -0.801 |
CLASSIFIED | -0.745 |
vantage | -0.706 |
ffect | -0.678 |
respectively | -0.663 |
Token | if |
Token ID | 611 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
rons | +13.920 |
liam | +13.332 |
enegger | +12.097 |
oons | +10.763 |
ries | +10.696 |
Neg logit contributions | |
ciplinary | -9.951 |
CLASSIFIED | -9.867 |
vantage | -9.257 |
ffect | -8.480 |
userc | -8.296 |
Token | played |
Token ID | 2826 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
rons | +11.512 |
liam | +11.133 |
enegger | +9.881 |
oons | +9.240 |
ries | +9.132 |
Neg logit contributions | |
ciplinary | -6.361 |
CLASSIFIED | -6.133 |
vantage | -5.979 |
ffect | -5.368 |
respectively | -5.176 |
Token | much |
Token ID | 881 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
rons | +4.278 |
liam | +4.150 |
enegger | +3.746 |
oons | +3.455 |
ries | +3.344 |
Neg logit contributions | |
ciplinary | -2.438 |
CLASSIFIED | -2.311 |
vantage | -2.198 |
ffect | -2.092 |
unexplained | -2.037 |
Token | later |
Token ID | 1568 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
rons | +3.410 |
liam | +3.323 |
enegger | +3.047 |
oons | +2.834 |
rises | +2.747 |
Neg logit contributions | |
ciplinary | -1.344 |
CLASSIFIED | -1.246 |
vantage | -1.166 |
ffect | -1.102 |
unexplained | -1.073 |
Token | .' |
Token ID | 2637 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
rons | +8.335 |
liam | +8.027 |
enegger | +7.128 |
oons | +6.587 |
ries | +6.435 |
Neg logit contributions | |
ciplinary | -5.684 |
CLASSIFIED | -5.546 |
vantage | -5.209 |
ffect | -4.917 |
unexplained | -4.785 |
Token | about |
Token ID | 546 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
rons | +4.725 |
liam | +4.579 |
enegger | +4.121 |
oons | +3.809 |
ries | +3.697 |
Neg logit contributions | |
ciplinary | -2.711 |
CLASSIFIED | -2.565 |
vantage | -2.436 |
ffect | -2.323 |
terday | -2.259 |
Token | a |
Token ID | 257 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
rons | +4.105 |
liam | +3.977 |
enegger | +3.582 |
oons | +3.302 |
ries | +3.192 |
Neg logit contributions | |
ciplinary | -2.475 |
CLASSIFIED | -2.350 |
vantage | -2.237 |
ffect | -2.138 |
unexplained | -2.085 |
Token | cup |
Token ID | 6508 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
rons | +3.137 |
liam | +3.014 |
enegger | +2.636 |
oons | +2.345 |
ries | +2.232 |
Neg logit contributions | |
ciplinary | -3.348 |
CLASSIFIED | -3.219 |
vantage | -3.109 |
ffect | -3.015 |
unexplained | -2.972 |
Token | of |
Token ID | 286 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
rons | +7.194 |
liam | +6.919 |
enegger | +6.180 |
oons | +5.798 |
ries | +5.640 |
Neg logit contributions | |
ciplinary | -4.172 |
CLASSIFIED | -3.988 |
vantage | -3.744 |
ffect | -3.579 |
terday | -3.476 |
Token | frozen |
Token ID | 12912 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
rons | +0.526 |
liam | +0.508 |
enegger | +0.463 |
oons | +0.420 |
rises | +0.406 |
Neg logit contributions | |
ciplinary | -0.343 |
CLASSIFIED | -0.324 |
vantage | -0.311 |
ffect | -0.300 |
unexplained | -0.299 |
Token | cher |
Token ID | 21382 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
ciplinary | +4.465 |
CLASSIFIED | +4.218 |
respectively | +4.186 |
unexplained | +4.150 |
probation | +4.093 |
Neg logit contributions | |
rons | -5.918 |
liam | -5.696 |
enegger | -5.377 |
oons | -4.696 |
rises | -4.499 |
Token | ries |
Token ID | 1678 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
rons | +5.027 |
liam | +4.139 |
ries | +3.180 |
oons | +1.842 |
enegger | +1.584 |
Neg logit contributions | |
CLASSIFIED | -20.252 |
ciplinary | -19.492 |
unexplained | -18.365 |
vantage | -18.361 |
probation | -18.241 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
rons | +1.957 |
liam | +1.906 |
enegger | +1.737 |
oons | +1.594 |
rises | +1.543 |
Neg logit contributions | |
ciplinary | -1.007 |
CLASSIFIED | -0.946 |
vantage | -0.899 |
ffect | -0.859 |
respectively | -0.844 |
Token | and |
Token ID | 290 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
rons | +1.776 |
liam | +1.727 |
enegger | +1.574 |
oons | +1.440 |
rises | +1.391 |
Neg logit contributions | |
ciplinary | -0.987 |
CLASSIFIED | -0.932 |
vantage | -0.886 |
ffect | -0.848 |
unexplained | -0.837 |
Token | keep |
Token ID | 1394 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
ciplinary | +0.987 |
CLASSIFIED | +0.935 |
vantage | +0.900 |
respectively | +0.876 |
unexplained | +0.871 |
Neg logit contributions | |
rons | -1.532 |
liam | -1.503 |
enegger | -1.385 |
oons | -1.230 |
rises | -1.198 |
Token | going |
Token ID | 1016 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ciplinary | +2.467 |
CLASSIFIED | +2.346 |
unexplained | +2.169 |
respectively | +2.161 |
vantage | +2.154 |
Neg logit contributions | |
rons | -5.522 |
liam | -5.400 |
enegger | -5.087 |
oons | -4.557 |
rises | -4.417 |
Token | military |
Token ID | 2422 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
rons | +10.972 |
liam | +10.774 |
enegger | +9.615 |
oons | +8.910 |
ries | +8.723 |
Neg logit contributions | |
ciplinary | -6.774 |
CLASSIFIED | -6.536 |
vantage | -6.411 |
ffect | -5.843 |
terday | -5.766 |
Token | missions |
Token ID | 10566 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
rons | +5.452 |
liam | +5.264 |
enegger | +4.742 |
oons | +4.359 |
ries | +4.214 |
Neg logit contributions | |
ciplinary | -3.503 |
CLASSIFIED | -3.332 |
vantage | -3.184 |
ffect | -3.044 |
terday | -2.963 |
Token | and |
Token ID | 290 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
rons | +0.382 |
liam | +0.372 |
enegger | +0.340 |
oons | +0.312 |
rises | +0.303 |
Neg logit contributions | |
ciplinary | -0.193 |
CLASSIFIED | -0.179 |
vantage | -0.170 |
ffect | -0.163 |
respectively | -0.163 |
Token | agreed |
Token ID | 4987 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
ciplinary | +0.226 |
CLASSIFIED | +0.209 |
vantage | +0.196 |
probation | +0.196 |
respectively | +0.195 |
Neg logit contributions | |
rons | -0.376 |
liam | -0.364 |
enegger | -0.333 |
oons | -0.306 |
rises | -0.294 |
Token | a |
Token ID | 257 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
rons | +11.696 |
liam | +11.454 |
enegger | +10.132 |
oons | +9.440 |
ries | +9.381 |
Neg logit contributions | |
ciplinary | -6.812 |
CLASSIFIED | -6.531 |
vantage | -6.437 |
ffect | -5.988 |
terday | -5.682 |
Token | common |
Token ID | 2219 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
rons | +6.772 |
liam | +6.574 |
enegger | +5.852 |
oons | +5.418 |
ries | +5.316 |
Neg logit contributions | |
ciplinary | -4.226 |
CLASSIFIED | -4.031 |
vantage | -3.922 |
ffect | -3.646 |
terday | -3.638 |
Token | arrest |
Token ID | 3251 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
rons | +13.648 |
liam | +13.441 |
enegger | +11.631 |
ries | +11.111 |
oons | +10.772 |
Neg logit contributions | |
ciplinary | -9.343 |
vantage | -9.313 |
CLASSIFIED | -9.169 |
ffect | -8.297 |
terday | -8.056 |
Token | warrant |
Token ID | 8084 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
rons | +7.053 |
liam | +6.871 |
enegger | +6.244 |
oons | +5.864 |
ries | +5.722 |
Neg logit contributions | |
ciplinary | -2.629 |
CLASSIFIED | -2.435 |
vantage | -2.269 |
ffect | -2.141 |
terday | -2.054 |
Token | to |
Token ID | 284 |
Feature activation | +7.63e-03 |
Pos logit contributions | |
rons | +7.851 |
liam | +7.607 |
enegger | +6.809 |
oons | +6.293 |
ries | +6.153 |
Neg logit contributions | |
ciplinary | -4.722 |
CLASSIFIED | -4.518 |
vantage | -4.291 |
ffect | -4.071 |
unexplained | -3.984 |
Token | tackle |
Token ID | 9761 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
rons | +0.009 |
liam | +0.008 |
enegger | +0.008 |
oons | +0.007 |
rises | +0.007 |
Neg logit contributions | |
ciplinary | -0.005 |
CLASSIFIED | -0.005 |
vantage | -0.004 |
probation | -0.004 |
ffect | -0.004 |
Token | cross |
Token ID | 3272 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
ciplinary | +2.857 |
CLASSIFIED | +2.661 |
unexplained | +2.660 |
probation | +2.573 |
intentional | +2.503 |
Neg logit contributions | |
rons | -5.536 |
liam | -5.364 |
enegger | -5.004 |
oons | -4.492 |
rises | -4.344 |
Token | your |
Token ID | 534 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
rons | +0.079 |
liam | +0.077 |
enegger | +0.071 |
oons | +0.065 |
rises | +0.064 |
Neg logit contributions | |
ciplinary | -0.034 |
CLASSIFIED | -0.032 |
vantage | -0.030 |
ffect | -0.028 |
unexplained | -0.028 |
Token | friends |
Token ID | 2460 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
rons | +5.134 |
liam | +4.930 |
enegger | +4.424 |
oons | +4.043 |
ries | +3.909 |
Neg logit contributions | |
ciplinary | -3.641 |
CLASSIFIED | -3.452 |
vantage | -3.324 |
ffect | -3.162 |
terday | -3.128 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ciplinary | +0.512 |
CLASSIFIED | +0.487 |
vantage | +0.461 |
respectively | +0.443 |
ffect | +0.442 |
Neg logit contributions | |
rons | -0.996 |
liam | -0.978 |
enegger | -0.887 |
oons | -0.817 |
rises | -0.793 |
Token | You |
Token ID | 921 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
ciplinary | +0.617 |
CLASSIFIED | +0.607 |
vantage | +0.572 |
ffect | +0.546 |
respectively | +0.543 |
Neg logit contributions | |
rons | -1.226 |
liam | -1.186 |
enegger | -1.081 |
oons | -0.991 |
rises | -0.966 |
Token | can |
Token ID | 460 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ciplinary | +0.480 |
CLASSIFIED | +0.450 |
vantage | +0.436 |
ffect | +0.410 |
respectively | +0.402 |
Neg logit contributions | |
rons | -0.977 |
liam | -0.955 |
enegger | -0.872 |
oons | -0.809 |
ries | -0.778 |
Token | even |
Token ID | 772 |
Feature activation | +1.40e+01 |
Pos logit contributions | |
ciplinary | +0.103 |
CLASSIFIED | +0.095 |
vantage | +0.090 |
ffect | +0.087 |
respectively | +0.087 |
Neg logit contributions | |
rons | -0.229 |
liam | -0.223 |
enegger | -0.205 |
oons | -0.189 |
rises | -0.183 |
Token | set |
Token ID | 900 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
rons | +13.581 |
liam | +12.976 |
enegger | +11.218 |
oons | +10.654 |
ries | +10.360 |
Neg logit contributions | |
ciplinary | -9.801 |
CLASSIFIED | -9.682 |
vantage | -9.236 |
ffect | -8.462 |
terday | -8.365 |
Token | an |
Token ID | 281 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ciplinary | +0.310 |
CLASSIFIED | +0.297 |
vantage | +0.273 |
ffect | +0.256 |
unexplained | +0.253 |
Neg logit contributions | |
rons | -0.798 |
liam | -0.780 |
enegger | -0.722 |
oons | -0.663 |
rises | -0.643 |
Token | alarm |
Token ID | 10436 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
rons | +2.217 |
liam | +2.151 |
enegger | +1.952 |
oons | +1.801 |
ries | +1.742 |
Neg logit contributions | |
ciplinary | -1.187 |
CLASSIFIED | -1.119 |
vantage | -1.061 |
ffect | -1.012 |
unexplained | -0.988 |
Token | and |
Token ID | 290 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
rons | +5.538 |
liam | +5.344 |
enegger | +4.822 |
oons | +4.467 |
ries | +4.325 |
Neg logit contributions | |
ciplinary | -3.235 |
CLASSIFIED | -3.052 |
vantage | -2.888 |
ffect | -2.753 |
terday | -2.693 |
Token | watch |
Token ID | 2342 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
ciplinary | +0.293 |
CLASSIFIED | +0.282 |
vantage | +0.265 |
ffect | +0.258 |
probation | +0.258 |
Neg logit contributions | |
rons | -0.471 |
liam | -0.460 |
enegger | -0.420 |
oons | -0.378 |
rises | -0.369 |
Token | the |
Token ID | 262 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
ciplinary | +2.012 |
CLASSIFIED | +1.829 |
probation | +1.752 |
vantage | +1.703 |
ffect | +1.679 |
Neg logit contributions | |
rons | -4.414 |
liam | -4.305 |
enegger | -3.968 |
oons | -3.658 |
rises | -3.548 |
Token | profession |
Token ID | 7573 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
ciplinary | +1.546 |
CLASSIFIED | +1.395 |
ffect | +1.303 |
probation | +1.301 |
vantage | +1.284 |
Neg logit contributions | |
rons | -3.837 |
liam | -3.758 |
enegger | -3.441 |
oons | -3.181 |
rises | -3.097 |
Token | . |
Token ID | 13 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
rons | +2.534 |
liam | +2.467 |
enegger | +2.237 |
oons | +2.064 |
rises | +1.992 |
Neg logit contributions | |
ciplinary | -1.379 |
CLASSIFIED | -1.295 |
vantage | -1.238 |
ffect | -1.184 |
respectively | -1.162 |
Token | We |
Token ID | 775 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ciplinary | +0.227 |
CLASSIFIED | +0.218 |
vantage | +0.206 |
ffect | +0.198 |
respectively | +0.196 |
Neg logit contributions | |
rons | -0.419 |
liam | -0.402 |
enegger | -0.367 |
oons | -0.338 |
rises | -0.327 |
Token | may |
Token ID | 743 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
rons | +0.363 |
liam | +0.353 |
enegger | +0.322 |
oons | +0.300 |
ries | +0.289 |
Neg logit contributions | |
ciplinary | -0.183 |
CLASSIFIED | -0.165 |
vantage | -0.161 |
ffect | -0.155 |
respectively | -0.153 |
Token | even |
Token ID | 772 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
rons | +4.587 |
liam | +4.455 |
enegger | +4.031 |
oons | +3.711 |
ries | +3.594 |
Neg logit contributions | |
ciplinary | -2.537 |
CLASSIFIED | -2.425 |
vantage | -2.286 |
ffect | -2.166 |
unexplained | -2.112 |
Token | start |
Token ID | 923 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
rons | +12.432 |
liam | +12.199 |
enegger | +10.365 |
oons | +9.302 |
ries | +9.249 |
Neg logit contributions | |
CLASSIFIED | -11.277 |
ciplinary | -10.562 |
vantage | -10.049 |
terday | -9.200 |
ffect | -9.199 |
Token | to |
Token ID | 284 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ciplinary | +0.374 |
CLASSIFIED | +0.342 |
vantage | +0.321 |
probation | +0.314 |
unexplained | +0.314 |
Neg logit contributions | |
rons | -0.865 |
liam | -0.841 |
enegger | -0.780 |
oons | -0.718 |
rises | -0.692 |
Token | see |
Token ID | 766 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
rons | +2.509 |
liam | +2.423 |
enegger | +2.170 |
oons | +1.963 |
ries | +1.882 |
Neg logit contributions | |
ciplinary | -2.005 |
CLASSIFIED | -1.897 |
vantage | -1.834 |
ffect | -1.776 |
unexplained | -1.752 |
Token | a |
Token ID | 257 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
rons | +3.678 |
liam | +3.561 |
enegger | +3.235 |
oons | +2.978 |
rises | +2.864 |
Neg logit contributions | |
ciplinary | -2.080 |
CLASSIFIED | -1.949 |
vantage | -1.837 |
ffect | -1.775 |
unexplained | -1.763 |
Token | different |
Token ID | 1180 |
Feature activation | +9.72e+00 |
Pos logit contributions | |
rons | +3.213 |
liam | +3.116 |
enegger | +2.822 |
oons | +2.599 |
ries | +2.502 |
Neg logit contributions | |
ciplinary | -1.820 |
CLASSIFIED | -1.715 |
vantage | -1.624 |
ffect | -1.563 |
unexplained | -1.536 |
Token | � |
Token ID | 564 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
rons | +2.033 |
liam | +1.975 |
enegger | +1.791 |
oons | +1.649 |
rises | +1.600 |
Neg logit contributions | |
ciplinary | -1.081 |
CLASSIFIED | -1.025 |
vantage | -0.971 |
ffect | -0.925 |
unexplained | -0.912 |
Token | � |
Token ID | 250 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
ciplinary | +0.266 |
CLASSIFIED | +0.256 |
vantage | +0.241 |
ffect | +0.234 |
unexplained | +0.230 |
Neg logit contributions | |
rons | -0.398 |
liam | -0.383 |
enegger | -0.348 |
oons | -0.316 |
rises | -0.306 |
Token | Outside |
Token ID | 30815 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
rons | +0.590 |
liam | +0.569 |
enegger | +0.519 |
oons | +0.473 |
ries | +0.458 |
Neg logit contributions | |
ciplinary | -0.354 |
CLASSIFIED | -0.340 |
vantage | -0.324 |
ffect | -0.309 |
terday | -0.303 |
Token | First |
Token ID | 3274 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
ciplinary | +1.968 |
CLASSIFIED | +1.893 |
vantage | +1.825 |
probation | +1.733 |
respectively | +1.724 |
Neg logit contributions | |
rons | -4.130 |
liam | -4.030 |
enegger | -3.715 |
oons | -3.389 |
rises | -3.328 |
Token | Presidential |
Token ID | 17471 |
Feature activation | +7.61e+00 |
Pos logit contributions | |
ciplinary | +1.732 |
CLASSIFIED | +1.649 |
vantage | +1.617 |
respectively | +1.549 |
probation | +1.511 |
Neg logit contributions | |
rons | -2.564 |
liam | -2.471 |
enegger | -2.298 |
oons | -2.003 |
rises | -1.995 |
Token | Debate |
Token ID | 41029 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
rons | +6.049 |
liam | +5.761 |
enegger | +4.934 |
oons | +4.435 |
ries | +4.238 |
Neg logit contributions | |
ciplinary | -7.370 |
CLASSIFIED | -7.133 |
vantage | -6.785 |
ffect | -6.654 |
terday | -6.579 |
Token | , |
Token ID | 11 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
rons | +14.121 |
liam | +13.684 |
enegger | +12.158 |
oons | +11.367 |
ries | +10.974 |
Neg logit contributions | |
ciplinary | -9.040 |
CLASSIFIED | -8.516 |
vantage | -7.988 |
ffect | -7.749 |
terday | -7.436 |
Token | 24 |
Token ID | 1987 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
rons | +5.463 |
liam | +5.313 |
enegger | +4.797 |
oons | +4.425 |
ries | +4.266 |
Neg logit contributions | |
ciplinary | -3.120 |
CLASSIFIED | -2.935 |
vantage | -2.792 |
ffect | -2.675 |
terday | -2.597 |
Token | Arrest |
Token ID | 35080 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
ciplinary | +0.905 |
CLASSIFIED | +0.862 |
vantage | +0.822 |
ffect | +0.787 |
unexplained | +0.784 |
Neg logit contributions | |
rons | -1.536 |
liam | -1.480 |
enegger | -1.367 |
oons | -1.228 |
ries | -1.195 |
Token | ed |
Token ID | 276 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
rons | +3.510 |
liam | +3.364 |
enegger | +2.920 |
oons | +2.592 |
ries | +2.463 |
Neg logit contributions | |
ciplinary | -4.011 |
CLASSIFIED | -3.860 |
vantage | -3.735 |
ffect | -3.623 |
unexplained | -3.570 |
Token | at |
Token ID | 379 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
ciplinary | +1.126 |
CLASSIFIED | +1.056 |
vantage | +1.007 |
respectively | +0.979 |
ffect | +0.976 |
Neg logit contributions | |
rons | -2.149 |
liam | -2.089 |
enegger | -1.919 |
oons | -1.751 |
rises | -1.709 |
Token | before |
Token ID | 878 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
rons | +4.690 |
liam | +4.543 |
enegger | +4.081 |
oons | +3.780 |
ries | +3.670 |
Neg logit contributions | |
ciplinary | -2.723 |
CLASSIFIED | -2.575 |
vantage | -2.425 |
ffect | -2.308 |
unexplained | -2.255 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
rons | +1.489 |
liam | +1.447 |
enegger | +1.320 |
oons | +1.203 |
rises | +1.165 |
Neg logit contributions | |
ciplinary | -0.895 |
CLASSIFIED | -0.850 |
vantage | -0.806 |
ffect | -0.777 |
probation | -0.773 |
Token | Nov |
Token ID | 5267 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
rons | +1.371 |
liam | +1.333 |
enegger | +1.203 |
oons | +1.093 |
rises | +1.056 |
Neg logit contributions | |
ciplinary | -0.919 |
CLASSIFIED | -0.870 |
vantage | -0.833 |
ffect | -0.806 |
unexplained | -0.797 |
Token | . |
Token ID | 13 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
rons | +7.277 |
liam | +7.014 |
enegger | +6.160 |
ries | +5.650 |
oons | +5.650 |
Neg logit contributions | |
ciplinary | -5.753 |
CLASSIFIED | -5.670 |
terday | -5.157 |
vantage | -5.123 |
unexplained | -5.027 |
Token | 8 |
Token ID | 807 |
Feature activation | +6.68e+00 |
Pos logit contributions | |
rons | +8.144 |
liam | +7.917 |
enegger | +6.665 |
ries | +6.610 |
oons | +6.342 |
Neg logit contributions | |
ciplinary | -7.017 |
CLASSIFIED | -6.778 |
vantage | -6.255 |
terday | -6.158 |
userc | -5.987 |
Token | election |
Token ID | 3071 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
rons | +6.184 |
liam | +5.934 |
enegger | +5.171 |
oons | +4.742 |
ries | +4.658 |
Neg logit contributions | |
ciplinary | -5.563 |
CLASSIFIED | -5.371 |
vantage | -5.068 |
ffect | -4.877 |
terday | -4.860 |
Token | . |
Token ID | 13 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
rons | +13.081 |
liam | +12.055 |
enegger | +10.722 |
ries | +10.075 |
oons | +9.834 |
Neg logit contributions | |
ciplinary | -10.297 |
CLASSIFIED | -9.718 |
vantage | -8.802 |
terday | -8.610 |
ffect | -8.438 |
Token |
|
Token ID | 198 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
ciplinary | +0.333 |
CLASSIFIED | +0.323 |
vantage | +0.304 |
ffect | +0.288 |
respectively | +0.286 |
Neg logit contributions | |
rons | -0.685 |
liam | -0.664 |
enegger | -0.609 |
oons | -0.557 |
rises | -0.545 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ciplinary | +0.503 |
CLASSIFIED | +0.474 |
vantage | +0.450 |
ffect | +0.430 |
unexplained | +0.419 |
Neg logit contributions | |
rons | -0.930 |
liam | -0.903 |
enegger | -0.820 |
oons | -0.755 |
rises | -0.730 |
Token | ADVERTISEMENT |
Token ID | 19053 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
rons | +2.277 |
liam | +2.207 |
enegger | +2.031 |
oons | +1.868 |
rises | +1.807 |
Neg logit contributions | |
ciplinary | -1.050 |
CLASSIFIED | -1.004 |
vantage | -0.930 |
ffect | -0.885 |
respectively | -0.855 |
Token |
|
Token ID | 198 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
rons | +3.974 |
liam | +3.875 |
enegger | +3.459 |
oons | +3.226 |
ries | +3.113 |
Neg logit contributions | |
ciplinary | -2.496 |
CLASSIFIED | -2.329 |
vantage | -2.207 |
ffect | -2.128 |
unexplained | -2.093 |
Token | GDP |
Token ID | 12396 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ciplinary | +2.080 |
CLASSIFIED | +1.931 |
respectively | +1.875 |
probation | +1.871 |
unexplained | +1.870 |
Neg logit contributions | |
rons | -3.070 |
liam | -2.964 |
enegger | -2.693 |
oons | -2.471 |
rises | -2.367 |
Token | have |
Token ID | 423 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ciplinary | +1.167 |
CLASSIFIED | +1.040 |
vantage | +1.013 |
respectively | +0.996 |
unexplained | +0.971 |
Neg logit contributions | |
rons | -2.465 |
liam | -2.403 |
enegger | -2.219 |
oons | -2.037 |
rises | -1.985 |
Token | already |
Token ID | 1541 |
Feature activation | +8.03e+00 |
Pos logit contributions | |
rons | +3.234 |
liam | +3.141 |
enegger | +2.847 |
oons | +2.623 |
rises | +2.533 |
Neg logit contributions | |
ciplinary | -1.822 |
CLASSIFIED | -1.714 |
vantage | -1.628 |
ffect | -1.560 |
unexplained | -1.533 |
Token | changed |
Token ID | 3421 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
rons | +8.677 |
liam | +8.329 |
enegger | +7.458 |
oons | +6.793 |
ries | +6.687 |
Neg logit contributions | |
ciplinary | -5.395 |
CLASSIFIED | -5.370 |
vantage | -5.059 |
ffect | -4.719 |
terday | -4.632 |
Token | not |
Token ID | 407 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
rons | +1.914 |
liam | +1.857 |
enegger | +1.712 |
oons | +1.580 |
rises | +1.534 |
Neg logit contributions | |
ciplinary | -0.830 |
CLASSIFIED | -0.777 |
vantage | -0.731 |
ffect | -0.696 |
probation | -0.680 |
Token | only |
Token ID | 691 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
rons | +6.269 |
liam | +6.095 |
enegger | +5.577 |
oons | +5.207 |
ries | +5.088 |
Neg logit contributions | |
ciplinary | -2.339 |
CLASSIFIED | -2.189 |
vantage | -2.027 |
ffect | -1.901 |
unexplained | -1.825 |
Token | their |
Token ID | 511 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
rons | +15.401 |
liam | +15.109 |
enegger | +13.300 |
ries | +12.591 |
oons | +12.559 |
Neg logit contributions | |
ciplinary | -7.473 |
CLASSIFIED | -7.330 |
vantage | -6.577 |
ffect | -6.155 |
terday | -6.058 |
Token | legal |
Token ID | 2742 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
rons | +8.215 |
liam | +7.996 |
enegger | +7.072 |
oons | +6.512 |
ries | +6.418 |
Neg logit contributions | |
ciplinary | -5.534 |
CLASSIFIED | -5.356 |
vantage | -5.129 |
ffect | -4.823 |
terday | -4.666 |
Token | headquarters |
Token ID | 10043 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
rons | +6.784 |
liam | +6.589 |
enegger | +5.837 |
oons | +5.368 |
ries | +5.265 |
Neg logit contributions | |
ciplinary | -4.589 |
CLASSIFIED | -4.387 |
vantage | -4.259 |
ffect | -4.003 |
terday | -3.912 |
Token | but |
Token ID | 475 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
rons | +3.272 |
liam | +3.182 |
enegger | +2.888 |
oons | +2.659 |
rises | +2.571 |
Neg logit contributions | |
ciplinary | -1.784 |
CLASSIFIED | -1.675 |
vantage | -1.593 |
ffect | -1.524 |
respectively | -1.492 |
Token | , |
Token ID | 11 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
rons | +2.482 |
liam | +2.420 |
enegger | +2.232 |
oons | +2.082 |
rises | +2.022 |
Neg logit contributions | |
ciplinary | -0.821 |
CLASSIFIED | -0.754 |
vantage | -0.698 |
ffect | -0.650 |
unexplained | -0.633 |
Token | we |
Token ID | 356 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
ciplinary | +0.536 |
CLASSIFIED | +0.500 |
vantage | +0.476 |
respectively | +0.469 |
ffect | +0.465 |
Neg logit contributions | |
rons | -0.933 |
liam | -0.908 |
enegger | -0.827 |
oons | -0.758 |
rises | -0.730 |
Token | want |
Token ID | 765 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
rons | +1.148 |
liam | +1.119 |
enegger | +1.021 |
oons | +0.941 |
ries | +0.910 |
Neg logit contributions | |
ciplinary | -0.585 |
CLASSIFIED | -0.535 |
vantage | -0.518 |
ffect | -0.495 |
respectively | -0.490 |
Token | to |
Token ID | 284 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ciplinary | +0.026 |
CLASSIFIED | +0.024 |
vantage | +0.023 |
ffect | +0.022 |
respectively | +0.021 |
Neg logit contributions | |
rons | -0.060 |
liam | -0.058 |
enegger | -0.054 |
oons | -0.049 |
rises | -0.048 |
Token | duplicate |
Token ID | 23418 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
rons | +1.263 |
liam | +1.226 |
enegger | +1.114 |
oons | +1.018 |
rises | +0.983 |
Neg logit contributions | |
ciplinary | -0.765 |
CLASSIFIED | -0.707 |
vantage | -0.681 |
ffect | -0.663 |
respectively | -0.655 |
Token | what |
Token ID | 644 |
Feature activation | +9.57e+00 |
Pos logit contributions | |
rons | +1.273 |
liam | +1.235 |
enegger | +1.132 |
oons | +1.043 |
rises | +1.004 |
Neg logit contributions | |
ciplinary | -0.635 |
CLASSIFIED | -0.592 |
vantage | -0.560 |
ffect | -0.540 |
respectively | -0.534 |
Token | we |
Token ID | 356 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
rons | +9.954 |
liam | +9.635 |
enegger | +8.460 |
oons | +7.829 |
ries | +7.821 |
Neg logit contributions | |
ciplinary | -6.587 |
CLASSIFIED | -6.424 |
vantage | -6.094 |
ffect | -5.750 |
terday | -5.671 |
Token | have |
Token ID | 423 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
rons | +13.528 |
liam | +12.730 |
enegger | +11.089 |
oons | +10.192 |
ries | +10.184 |
Neg logit contributions | |
CLASSIFIED | -10.270 |
ciplinary | -9.365 |
vantage | -8.872 |
ffect | -8.402 |
unexplained | -8.234 |
Token | in |
Token ID | 287 |
Feature activation | +7.30e+00 |
Pos logit contributions | |
rons | +12.103 |
liam | +11.274 |
enegger | +10.136 |
ries | +9.275 |
oons | +9.106 |
Neg logit contributions | |
CLASSIFIED | -8.834 |
ciplinary | -8.656 |
vantage | -8.239 |
ffect | -7.730 |
terday | -7.615 |
Token | the |
Token ID | 262 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
rons | +7.855 |
liam | +7.564 |
enegger | +6.814 |
oons | +6.257 |
ries | +6.149 |
Neg logit contributions | |
ciplinary | -4.978 |
CLASSIFIED | -4.801 |
vantage | -4.519 |
ffect | -4.290 |
terday | -4.255 |
Token | US |
Token ID | 1294 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
rons | +5.211 |
liam | +5.030 |
enegger | +4.521 |
oons | +4.140 |
ries | +4.011 |
Neg logit contributions | |
ciplinary | -3.467 |
CLASSIFIED | -3.328 |
vantage | -3.158 |
ffect | -3.013 |
terday | -2.964 |
Token | and |
Token ID | 290 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
rons | +1.561 |
liam | +1.528 |
enegger | +1.388 |
oons | +1.280 |
rises | +1.240 |
Neg logit contributions | |
ciplinary | -0.789 |
CLASSIFIED | -0.732 |
vantage | -0.701 |
ffect | -0.672 |
respectively | -0.665 |
Token | including |
Token ID | 1390 |
Feature activation | +8.64e+00 |
Pos logit contributions | |
rons | +4.476 |
liam | +4.345 |
enegger | +3.940 |
oons | +3.650 |
rises | +3.536 |
Neg logit contributions | |
ciplinary | -2.303 |
CLASSIFIED | -2.169 |
vantage | -2.055 |
ffect | -1.942 |
terday | -1.894 |
Token | people |
Token ID | 661 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
rons | +9.639 |
liam | +9.337 |
enegger | +8.384 |
oons | +7.771 |
rises | +7.569 |
Neg logit contributions | |
ciplinary | -5.584 |
CLASSIFIED | -5.232 |
vantage | -5.001 |
ffect | -4.709 |
terday | -4.549 |
Token | , |
Token ID | 11 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
rons | +4.446 |
liam | +4.300 |
enegger | +3.906 |
oons | +3.615 |
ries | +3.523 |
Neg logit contributions | |
ciplinary | -2.241 |
CLASSIFIED | -2.122 |
vantage | -1.998 |
ffect | -1.879 |
terday | -1.835 |
Token | buildings |
Token ID | 6832 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
rons | +3.095 |
liam | +3.000 |
enegger | +2.708 |
oons | +2.479 |
ries | +2.391 |
Neg logit contributions | |
ciplinary | -1.951 |
CLASSIFIED | -1.854 |
vantage | -1.769 |
ffect | -1.696 |
unexplained | -1.669 |
Token | and |
Token ID | 290 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
rons | +2.975 |
liam | +2.893 |
enegger | +2.639 |
oons | +2.444 |
ries | +2.368 |
Neg logit contributions | |
ciplinary | -1.373 |
CLASSIFIED | -1.288 |
vantage | -1.214 |
ffect | -1.151 |
unexplained | -1.122 |
Token | even |
Token ID | 772 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
rons | +4.416 |
liam | +4.276 |
enegger | +3.832 |
oons | +3.512 |
ries | +3.395 |
Neg logit contributions | |
ciplinary | -2.969 |
CLASSIFIED | -2.814 |
vantage | -2.693 |
ffect | -2.580 |
terday | -2.516 |
Token | trees |
Token ID | 7150 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
rons | +13.580 |
liam | +13.219 |
enegger | +11.443 |
oons | +10.765 |
rises | +10.571 |
Neg logit contributions | |
ciplinary | -9.665 |
CLASSIFIED | -8.936 |
vantage | -8.643 |
ffect | -8.228 |
terday | -7.878 |
Token | , |
Token ID | 11 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
rons | +4.159 |
liam | +4.023 |
enegger | +3.630 |
oons | +3.341 |
ries | +3.234 |
Neg logit contributions | |
ciplinary | -2.504 |
CLASSIFIED | -2.373 |
vantage | -2.256 |
ffect | -2.154 |
terday | -2.099 |
Token | top |
Token ID | 1353 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
rons | +2.722 |
liam | +2.648 |
enegger | +2.415 |
oons | +2.234 |
ries | +2.159 |
Neg logit contributions | |
ciplinary | -1.314 |
CLASSIFIED | -1.235 |
vantage | -1.168 |
ffect | -1.112 |
unexplained | -1.095 |
Token | so |
Token ID | 568 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
ciplinary | +2.309 |
CLASSIFIED | +2.209 |
vantage | +2.179 |
respectively | +2.081 |
unexplained | +2.074 |
Neg logit contributions | |
rons | -2.425 |
liam | -2.349 |
enegger | -2.122 |
oons | -1.855 |
ries | -1.792 |
Token | il |
Token ID | 346 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ciplinary | +0.461 |
CLASSIFIED | +0.433 |
vantage | +0.416 |
ffect | +0.407 |
unexplained | +0.397 |
Neg logit contributions | |
rons | -0.644 |
liam | -0.625 |
enegger | -0.563 |
oons | -0.508 |
rises | -0.491 |
Token | I |
Token ID | 314 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
ciplinary | +0.824 |
CLASSIFIED | +0.777 |
vantage | +0.742 |
ffect | +0.724 |
probation | +0.715 |
Neg logit contributions | |
rons | -1.311 |
liam | -1.264 |
enegger | -1.146 |
oons | -1.050 |
rises | -1.012 |
Token | turn |
Token ID | 1210 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
rons | +2.122 |
liam | +2.060 |
enegger | +1.735 |
oons | +1.590 |
ries | +1.522 |
Neg logit contributions | |
ciplinary | -2.303 |
CLASSIFIED | -2.272 |
vantage | -2.132 |
terday | -2.056 |
ffect | -2.045 |
Token | AA |
Token ID | 15923 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
ciplinary | +3.146 |
CLASSIFIED | +2.958 |
respectively | +2.790 |
vantage | +2.690 |
ffect | +2.651 |
Neg logit contributions | |
rons | -15.798 |
liam | -15.307 |
enegger | -14.664 |
rises | -13.432 |
oons | -13.324 |
Token | on |
Token ID | 319 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
ciplinary | +3.566 |
CLASSIFIED | +3.123 |
vantage | +3.109 |
ffect | +3.087 |
respectively | +3.066 |
Neg logit contributions | |
rons | -8.189 |
liam | -8.072 |
enegger | -7.585 |
oons | -6.801 |
覚醒 | -6.591 |
Token | things |
Token ID | 1243 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
ciplinary | +1.989 |
CLASSIFIED | +1.829 |
vantage | +1.681 |
respectively | +1.673 |
ffect | +1.669 |
Neg logit contributions | |
rons | -6.346 |
liam | -6.222 |
enegger | -5.850 |
oons | -5.330 |
rises | -5.118 |
Token | slow |
Token ID | 3105 |
Feature activation | -1.65e+01 |
Pos logit contributions | |
ciplinary | +3.969 |
respectively | +3.587 |
probation | +3.474 |
unexplained | +3.423 |
unclear | +3.362 |
Neg logit contributions | |
rons | -14.420 |
liam | -13.948 |
enegger | -13.618 |
oons | -12.084 |
覚醒 | -11.992 |
Token | down |
Token ID | 866 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
respectively | +2.111 |
versa | +2.036 |
ciplinary | +1.867 |
away | +1.559 |
unexplained | +1.558 |
Neg logit contributions | |
rons | -23.187 |
liam | -22.642 |
enegger | -22.465 |
覚醒 | -21.211 |
rises | -19.964 |
Token | quite |
Token ID | 2407 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
ciplinary | +2.923 |
CLASSIFIED | +2.500 |
unexplained | +2.457 |
respectively | +2.449 |
vantage | +2.448 |
Neg logit contributions | |
rons | -9.514 |
liam | -9.145 |
enegger | -8.630 |
oons | -7.918 |
rises | -7.667 |
Token | a |
Token ID | 257 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
ciplinary | +0.607 |
CLASSIFIED | +0.572 |
vantage | +0.545 |
ffect | +0.523 |
unexplained | +0.513 |
Neg logit contributions | |
rons | -1.057 |
liam | -1.025 |
enegger | -0.930 |
oons | -0.852 |
rises | -0.825 |
Token | bit |
Token ID | 1643 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
rons | +0.869 |
liam | +0.838 |
enegger | +0.748 |
oons | +0.679 |
ries | +0.657 |
Neg logit contributions | |
ciplinary | -0.693 |
CLASSIFIED | -0.668 |
vantage | -0.638 |
ffect | -0.609 |
terday | -0.601 |
Token | but |
Token ID | 475 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
ciplinary | +3.105 |
CLASSIFIED | +2.757 |
vantage | +2.734 |
ffect | +2.697 |
respectively | +2.655 |
Neg logit contributions | |
rons | -7.341 |
liam | -7.206 |
enegger | -6.592 |
oons | -6.093 |
rises | -5.921 |
Token | famous |
Token ID | 45143 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
ciplinary | +7.176 |
CLASSIFIED | +6.459 |
vantage | +6.276 |
camp | +6.110 |
probation | +5.965 |
Neg logit contributions | |
rons | -11.045 |
liam | -10.453 |
enegger | -9.926 |
oons | -8.584 |
ries | -8.232 |
Token | , |
Token ID | 11 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ciplinary | +0.629 |
CLASSIFIED | +0.587 |
vantage | +0.559 |
probation | +0.550 |
ffect | +0.548 |
Neg logit contributions | |
rons | -1.091 |
liam | -1.052 |
enegger | -0.954 |
oons | -0.875 |
rises | -0.849 |
Token | best |
Token ID | 1266 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
ciplinary | +1.692 |
CLASSIFIED | +1.569 |
vantage | +1.492 |
unexplained | +1.478 |
probation | +1.464 |
Neg logit contributions | |
rons | -2.934 |
liam | -2.827 |
enegger | -2.569 |
oons | -2.347 |
rises | -2.292 |
Token | - |
Token ID | 12 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
ciplinary | +2.170 |
CLASSIFIED | +2.005 |
vantage | +1.836 |
unexplained | +1.818 |
probation | +1.817 |
Neg logit contributions | |
rons | -5.164 |
liam | -4.985 |
enegger | -4.598 |
oons | -4.244 |
rises | -4.152 |
Token | selling |
Token ID | 16473 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
ciplinary | +2.170 |
CLASSIFIED | +1.970 |
vantage | +1.904 |
ffect | +1.837 |
respectively | +1.830 |
Neg logit contributions | |
rons | -3.538 |
liam | -3.372 |
enegger | -3.158 |
oons | -2.835 |
ries | -2.749 |
Token | self |
Token ID | 2116 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
rons | +4.309 |
liam | +4.187 |
enegger | +3.767 |
oons | +3.457 |
ries | +3.344 |
Neg logit contributions | |
ciplinary | -2.784 |
CLASSIFIED | -2.647 |
vantage | -2.532 |
ffect | -2.414 |
unexplained | -2.350 |
Token | - |
Token ID | 12 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
ciplinary | +6.404 |
CLASSIFIED | +5.375 |
probation | +5.149 |
intentional | +5.132 |
versa | +4.975 |
Neg logit contributions | |
rons | -19.144 |
liam | -18.066 |
enegger | -16.630 |
oons | -15.774 |
ries | -15.171 |
Token | help |
Token ID | 16794 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ciplinary | +5.097 |
CLASSIFIED | +4.132 |
vantage | +4.044 |
ffect | +3.992 |
closure | +3.947 |
Neg logit contributions | |
rons | -13.053 |
liam | -12.378 |
enegger | -11.591 |
oons | -10.682 |
ries | -10.271 |
Token | Kindle |
Token ID | 27114 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
ciplinary | +1.036 |
CLASSIFIED | +0.946 |
vantage | +0.902 |
probation | +0.888 |
ffect | +0.876 |
Neg logit contributions | |
rons | -1.906 |
liam | -1.829 |
enegger | -1.664 |
oons | -1.522 |
rises | -1.492 |
Token | author |
Token ID | 1772 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
ciplinary | +2.289 |
CLASSIFIED | +2.110 |
vantage | +2.017 |
probation | +1.973 |
respectively | +1.955 |
Neg logit contributions | |
rons | -4.123 |
liam | -3.937 |
enegger | -3.616 |
oons | -3.292 |
rises | -3.219 |
Token | , |
Token ID | 11 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
ciplinary | +0.415 |
CLASSIFIED | +0.389 |
vantage | +0.367 |
unexplained | +0.350 |
ffect | +0.349 |
Neg logit contributions | |
rons | -0.899 |
liam | -0.870 |
enegger | -0.795 |
oons | -0.736 |
rises | -0.709 |
Token | that |
Token ID | 326 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
ciplinary | +2.728 |
CLASSIFIED | +2.453 |
probation | +2.347 |
unexplained | +2.319 |
respectively | +2.304 |
Neg logit contributions | |
rons | -4.696 |
liam | -4.635 |
enegger | -4.213 |
oons | -3.845 |
rises | -3.833 |
Token | sentenced |
Token ID | 11897 |
Feature activation | -8.31e+00 |
Pos logit contributions | |
ciplinary | +2.586 |
CLASSIFIED | +2.276 |
probation | +2.236 |
respectively | +2.219 |
unexplained | +2.197 |
Neg logit contributions | |
rons | -4.325 |
liam | -4.210 |
enegger | -3.867 |
oons | -3.572 |
rises | -3.478 |
Token | him |
Token ID | 683 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
ciplinary | +4.254 |
CLASSIFIED | +3.940 |
probation | +3.831 |
unexplained | +3.629 |
respectively | +3.614 |
Neg logit contributions | |
rons | -9.805 |
liam | -9.593 |
enegger | -8.810 |
oons | -8.138 |
rises | -7.900 |
Token | to |
Token ID | 284 |
Feature activation | -7.44e+00 |
Pos logit contributions | |
ciplinary | +2.103 |
CLASSIFIED | +1.879 |
probation | +1.838 |
respectively | +1.817 |
unexplained | +1.794 |
Neg logit contributions | |
rons | -3.832 |
liam | -3.733 |
enegger | -3.387 |
oons | -3.155 |
rises | -3.066 |
Token | eight |
Token ID | 3624 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
ciplinary | +4.336 |
CLASSIFIED | +4.051 |
probation | +3.940 |
vantage | +3.753 |
unexplained | +3.725 |
Neg logit contributions | |
rons | -8.389 |
liam | -8.222 |
enegger | -7.613 |
oons | -6.945 |
rises | -6.741 |
Token | years |
Token ID | 812 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
ciplinary | +3.494 |
CLASSIFIED | +3.281 |
probation | +3.135 |
unexplained | +3.098 |
respectively | +3.065 |
Neg logit contributions | |
rons | -4.672 |
liam | -4.526 |
enegger | -4.168 |
oons | -3.696 |
rises | -3.555 |
Token | made |
Token ID | 925 |
Feature activation | -8.10e+00 |
Pos logit contributions | |
ciplinary | +7.706 |
probation | +7.668 |
respectively | +6.893 |
unexplained | +6.528 |
CLASSIFIED | +6.513 |
Neg logit contributions | |
rons | -16.816 |
liam | -16.449 |
enegger | -15.456 |
oons | -14.270 |
覚醒 | -14.026 |
Token | no |
Token ID | 645 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
ciplinary | +4.573 |
probation | +4.267 |
CLASSIFIED | +4.183 |
unexplained | +4.156 |
intentional | +4.031 |
Neg logit contributions | |
rons | -9.264 |
liam | -9.007 |
enegger | -8.350 |
oons | -7.602 |
rises | -7.388 |
Token | distinction |
Token ID | 12941 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ciplinary | +2.881 |
CLASSIFIED | +2.632 |
probation | +2.608 |
unexplained | +2.575 |
intentional | +2.519 |
Neg logit contributions | |
rons | -5.162 |
liam | -5.101 |
enegger | -4.679 |
oons | -4.214 |
rises | -4.101 |
Token | between |
Token ID | 1022 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
rons | +1.230 |
liam | +1.195 |
enegger | +1.093 |
oons | +1.010 |
rises | +0.980 |
Neg logit contributions | |
ciplinary | -0.571 |
CLASSIFIED | -0.533 |
vantage | -0.505 |
ffect | -0.482 |
unexplained | -0.476 |
Token | youth |
Token ID | 6205 |
Feature activation | -7.29e+00 |
Pos logit contributions | |
ciplinary | +2.076 |
CLASSIFIED | +1.941 |
probation | +1.843 |
unexplained | +1.793 |
intentional | +1.769 |
Neg logit contributions | |
rons | -3.946 |
liam | -3.889 |
enegger | -3.565 |
oons | -3.243 |
rises | -3.134 |
Token | s |
Token ID | 82 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
ciplinary | +1.342 |
CLASSIFIED | +1.243 |
vantage | +1.233 |
ffect | +1.202 |
probation | +1.179 |
Neg logit contributions | |
rons | -1.464 |
liam | -1.408 |
enegger | -1.241 |
oons | -1.129 |
rises | -1.069 |
Token | lawyers |
Token ID | 9326 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
ciplinary | +2.335 |
CLASSIFIED | +2.165 |
probation | +2.105 |
vantage | +2.005 |
unexplained | +2.004 |
Neg logit contributions | |
rons | -4.029 |
liam | -3.903 |
enegger | -3.516 |
oons | -3.248 |
rises | -3.134 |
Token | argued |
Token ID | 7189 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
rons | +0.416 |
liam | +0.404 |
enegger | +0.363 |
oons | +0.333 |
rises | +0.322 |
Neg logit contributions | |
ciplinary | -0.281 |
CLASSIFIED | -0.261 |
vantage | -0.252 |
ffect | -0.244 |
respectively | -0.242 |
Token | that |
Token ID | 326 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
rons | +2.522 |
liam | +2.455 |
enegger | +2.219 |
oons | +2.048 |
rises | +1.976 |
Neg logit contributions | |
ciplinary | -1.421 |
CLASSIFIED | -1.341 |
vantage | -1.265 |
ffect | -1.216 |
probation | -1.203 |
Token | eight |
Token ID | 3624 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
ciplinary | +1.178 |
CLASSIFIED | +1.109 |
probation | +1.035 |
vantage | +1.015 |
unexplained | +1.002 |
Neg logit contributions | |
rons | -2.187 |
liam | -2.144 |
enegger | -1.944 |
oons | -1.798 |
rises | -1.726 |
Token | years |
Token ID | 812 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
ciplinary | +2.944 |
CLASSIFIED | +2.784 |
probation | +2.629 |
unexplained | +2.585 |
respectively | +2.575 |
Neg logit contributions | |
rons | -3.940 |
liam | -3.803 |
enegger | -3.451 |
oons | -3.086 |
rises | -2.977 |
Token | for |
Token ID | 329 |
Feature activation | -9.95e+00 |
Pos logit contributions | |
ciplinary | +7.649 |
probation | +7.609 |
respectively | +7.089 |
unexplained | +6.709 |
unclear | +6.623 |
Neg logit contributions | |
rons | -16.763 |
liam | -16.505 |
enegger | -15.332 |
oons | -14.055 |
覚醒 | -13.952 |
Token | crimes |
Token ID | 6741 |
Feature activation | -8.24e+00 |
Pos logit contributions | |
ciplinary | +5.483 |
probation | +5.225 |
unexplained | +4.990 |
CLASSIFIED | +4.968 |
intentional | +4.873 |
Neg logit contributions | |
rons | -11.171 |
liam | -11.111 |
enegger | -10.223 |
oons | -9.203 |
rises | -8.966 |
Token | including |
Token ID | 1390 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
ciplinary | +4.808 |
CLASSIFIED | +4.271 |
unexplained | +4.156 |
probation | +4.147 |
respectively | +4.095 |
Neg logit contributions | |
rons | -9.370 |
liam | -9.309 |
enegger | -8.679 |
oons | -7.859 |
rises | -7.561 |
Token | murder |
Token ID | 5123 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
ciplinary | +1.552 |
CLASSIFIED | +1.457 |
probation | +1.357 |
unexplained | +1.357 |
intentional | +1.346 |
Neg logit contributions | |
rons | -3.053 |
liam | -3.005 |
enegger | -2.746 |
oons | -2.508 |
rises | -2.432 |
Token | only |
Token ID | 691 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ciplinary | +2.538 |
CLASSIFIED | +2.350 |
probation | +2.173 |
vantage | +2.149 |
respectively | +2.140 |
Neg logit contributions | |
rons | -6.478 |
liam | -6.397 |
enegger | -5.855 |
oons | -5.429 |
rises | -5.259 |
Token | notes |
Token ID | 4710 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
ciplinary | +2.864 |
CLASSIFIED | +2.562 |
vantage | +2.480 |
unexplained | +2.445 |
respectively | +2.443 |
Neg logit contributions | |
rons | -4.655 |
liam | -4.474 |
enegger | -4.038 |
oons | -3.714 |
rises | -3.656 |
Token | , |
Token ID | 11 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
ciplinary | +0.592 |
CLASSIFIED | +0.552 |
vantage | +0.517 |
unexplained | +0.501 |
probation | +0.499 |
Neg logit contributions | |
rons | -1.126 |
liam | -1.096 |
enegger | -0.998 |
oons | -0.913 |
rises | -0.891 |
Token | correctly |
Token ID | 9380 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
rons | +2.499 |
liam | +2.421 |
enegger | +2.194 |
oons | +2.016 |
rises | +1.947 |
Neg logit contributions | |
ciplinary | -1.435 |
CLASSIFIED | -1.356 |
vantage | -1.287 |
ffect | -1.231 |
unexplained | -1.214 |
Token | , |
Token ID | 11 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
rons | +1.279 |
liam | +1.240 |
enegger | +1.130 |
oons | +1.046 |
rises | +1.012 |
Neg logit contributions | |
ciplinary | -0.657 |
CLASSIFIED | -0.612 |
vantage | -0.583 |
ffect | -0.555 |
unexplained | -0.552 |
Token | that |
Token ID | 326 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
rons | +3.090 |
liam | +2.997 |
enegger | +2.719 |
oons | +2.501 |
rises | +2.418 |
Neg logit contributions | |
ciplinary | -1.726 |
CLASSIFIED | -1.628 |
vantage | -1.543 |
ffect | -1.475 |
unexplained | -1.450 |
Token | Sa |
Token ID | 10318 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
rons | +0.769 |
liam | +0.746 |
enegger | +0.679 |
oons | +0.622 |
rises | +0.604 |
Neg logit contributions | |
ciplinary | -0.420 |
CLASSIFIED | -0.398 |
vantage | -0.373 |
ffect | -0.359 |
probation | -0.358 |
Token | 'd |
Token ID | 1549 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
ciplinary | +6.784 |
CLASSIFIED | +6.201 |
probation | +5.927 |
respectively | +5.812 |
ffect | +5.788 |
Neg logit contributions | |
rons | -16.774 |
liam | -16.086 |
enegger | -15.299 |
oons | -14.042 |
ries | -13.838 |
Token | judgment |
Token ID | 8492 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ciplinary | +0.602 |
CLASSIFIED | +0.571 |
vantage | +0.541 |
ffect | +0.522 |
probation | +0.521 |
Neg logit contributions | |
rons | -0.950 |
liam | -0.919 |
enegger | -0.839 |
oons | -0.760 |
rises | -0.743 |
Token | acc |
Token ID | 697 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
rons | +0.218 |
liam | +0.212 |
enegger | +0.194 |
oons | +0.179 |
rises | +0.174 |
Neg logit contributions | |
ciplinary | -0.094 |
CLASSIFIED | -0.086 |
vantage | -0.082 |
ffect | -0.078 |
respectively | -0.077 |
Token | ords |
Token ID | 3669 |
Feature activation | -5.18e-03 |
Pos logit contributions | |
rons | +0.227 |
liam | +0.219 |
enegger | +0.198 |
oons | +0.175 |
rises | +0.167 |
Neg logit contributions | |
ciplinary | -0.188 |
CLASSIFIED | -0.175 |
vantage | -0.175 |
ffect | -0.169 |
respectively | -0.164 |
Token | with |
Token ID | 351 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
ciplinary | +0.004 |
CLASSIFIED | +0.003 |
vantage | +0.003 |
ffect | +0.003 |
respectively | +0.003 |
Neg logit contributions | |
rons | -0.006 |
liam | -0.005 |
enegger | -0.005 |
oons | -0.005 |
rises | -0.004 |
Token | infants |
Token ID | 18775 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
rons | +3.827 |
liam | +3.710 |
enegger | +3.348 |
oons | +3.065 |
rises | +2.955 |
Neg logit contributions | |
ciplinary | -2.406 |
CLASSIFIED | -2.281 |
vantage | -2.174 |
ffect | -2.088 |
unexplained | -2.050 |
Token | . |
Token ID | 13 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
ciplinary | +0.243 |
CLASSIFIED | +0.228 |
vantage | +0.217 |
ffect | +0.207 |
respectively | +0.205 |
Neg logit contributions | |
rons | -0.481 |
liam | -0.469 |
enegger | -0.425 |
oons | -0.393 |
rises | -0.379 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ciplinary | +0.347 |
CLASSIFIED | +0.337 |
vantage | +0.318 |
ffect | +0.306 |
respectively | +0.302 |
Neg logit contributions | |
rons | -0.644 |
liam | -0.621 |
enegger | -0.564 |
oons | -0.519 |
rises | -0.503 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ciplinary | +0.966 |
CLASSIFIED | +0.901 |
vantage | +0.858 |
ffect | +0.824 |
respectively | +0.804 |
Neg logit contributions | |
rons | -1.887 |
liam | -1.830 |
enegger | -1.675 |
oons | -1.536 |
rises | -1.486 |
Token | Under |
Token ID | 9203 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
rons | +1.871 |
liam | +1.803 |
enegger | +1.646 |
oons | +1.499 |
rises | +1.440 |
Neg logit contributions | |
ciplinary | -1.150 |
CLASSIFIED | -1.113 |
vantage | -1.043 |
ffect | -1.004 |
terday | -0.973 |
Token | chain |
Token ID | 6333 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
rons | +2.208 |
liam | +2.145 |
enegger | +1.936 |
oons | +1.784 |
rises | +1.718 |
Neg logit contributions | |
ciplinary | -1.257 |
CLASSIFIED | -1.193 |
vantage | -1.132 |
ffect | -1.087 |
unexplained | -1.065 |
Token | - |
Token ID | 12 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
ciplinary | +7.272 |
probation | +6.901 |
CLASSIFIED | +6.612 |
versa | +6.159 |
respectively | +6.062 |
Neg logit contributions | |
rons | -16.845 |
liam | -16.241 |
enegger | -15.559 |
oons | -14.004 |
heny | -13.297 |
Token | m |
Token ID | 76 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ciplinary | +7.941 |
vantage | +7.315 |
CLASSIFIED | +7.025 |
ffect | +7.002 |
camp | +6.992 |
Neg logit contributions | |
rons | -11.387 |
liam | -11.034 |
enegger | -10.594 |
oons | -9.151 |
heny | -9.062 |
Token | igration |
Token ID | 4254 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
ciplinary | +1.375 |
CLASSIFIED | +1.299 |
vantage | +1.265 |
ffect | +1.220 |
respectively | +1.194 |
Neg logit contributions | |
rons | -1.614 |
liam | -1.559 |
enegger | -1.387 |
oons | -1.246 |
rises | -1.197 |
Token | policies |
Token ID | 4788 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
ciplinary | +3.101 |
CLASSIFIED | +2.923 |
probation | +2.871 |
vantage | +2.822 |
respectively | +2.788 |
Neg logit contributions | |
rons | -3.805 |
liam | -3.664 |
enegger | -3.315 |
oons | -2.924 |
rises | -2.830 |
Token | , |
Token ID | 11 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
ciplinary | +1.440 |
CLASSIFIED | +1.353 |
vantage | +1.288 |
ffect | +1.238 |
probation | +1.233 |
Neg logit contributions | |
rons | -2.979 |
liam | -2.903 |
enegger | -2.652 |
oons | -2.454 |
rises | -2.379 |
Token | . |
Token ID | 13 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
ciplinary | +3.718 |
vantage | +3.340 |
respectively | +3.299 |
CLASSIFIED | +3.291 |
unexplained | +3.244 |
Neg logit contributions | |
rons | -8.449 |
liam | -8.348 |
enegger | -7.699 |
oons | -6.936 |
rises | -6.722 |
Token | Find |
Token ID | 9938 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
rons | +0.534 |
liam | +0.514 |
enegger | +0.466 |
oons | +0.422 |
rises | +0.411 |
Neg logit contributions | |
ciplinary | -0.338 |
CLASSIFIED | -0.328 |
vantage | -0.314 |
ffect | -0.299 |
respectively | -0.295 |
Token | out |
Token ID | 503 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ciplinary | +0.449 |
CLASSIFIED | +0.414 |
vantage | +0.397 |
unexplained | +0.379 |
ffect | +0.379 |
Neg logit contributions | |
rons | -0.980 |
liam | -0.951 |
enegger | -0.871 |
oons | -0.799 |
rises | -0.781 |
Token | if |
Token ID | 611 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
rons | +1.385 |
liam | +1.346 |
enegger | +1.222 |
oons | +1.124 |
rises | +1.088 |
Neg logit contributions | |
ciplinary | -0.749 |
CLASSIFIED | -0.705 |
vantage | -0.671 |
ffect | -0.643 |
unexplained | -0.633 |
Token | one |
Token ID | 530 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
rons | +2.192 |
liam | +2.130 |
enegger | +1.942 |
oons | +1.777 |
rises | +1.723 |
Neg logit contributions | |
ciplinary | -1.186 |
CLASSIFIED | -1.115 |
vantage | -1.061 |
ffect | -1.021 |
unexplained | -1.009 |
Token | way |
Token ID | 835 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
ciplinary | +1.729 |
vantage | +1.545 |
CLASSIFIED | +1.539 |
ffect | +1.499 |
probation | +1.479 |
Neg logit contributions | |
rons | -3.566 |
liam | -3.470 |
enegger | -3.191 |
oons | -2.921 |
rises | -2.827 |
Token | or |
Token ID | 393 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
ciplinary | +7.902 |
vantage | +7.209 |
respectively | +7.032 |
probation | +7.011 |
intentional | +6.973 |
Neg logit contributions | |
rons | -15.646 |
liam | -15.547 |
enegger | -14.645 |
覚醒 | -12.659 |
oons | -12.617 |
Token | the |
Token ID | 262 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
ciplinary | +3.203 |
vantage | +2.933 |
CLASSIFIED | +2.857 |
ffect | +2.718 |
probation | +2.701 |
Neg logit contributions | |
rons | -7.113 |
liam | -7.104 |
enegger | -6.542 |
oons | -5.932 |
rises | -5.903 |
Token | other |
Token ID | 584 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
ciplinary | +2.293 |
vantage | +2.011 |
CLASSIFIED | +2.006 |
ffect | +1.931 |
probation | +1.873 |
Neg logit contributions | |
rons | -6.361 |
liam | -6.332 |
enegger | -5.885 |
rises | -5.286 |
oons | -5.259 |
Token | is |
Token ID | 318 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
ciplinary | +1.145 |
CLASSIFIED | +1.003 |
vantage | +0.993 |
ffect | +0.953 |
respectively | +0.937 |
Neg logit contributions | |
rons | -3.139 |
liam | -3.075 |
enegger | -2.834 |
oons | -2.611 |
rises | -2.531 |
Token | better |
Token ID | 1365 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
ciplinary | +3.317 |
CLASSIFIED | +2.979 |
vantage | +2.950 |
intentional | +2.905 |
respectively | +2.889 |
Neg logit contributions | |
rons | -8.025 |
liam | -7.792 |
enegger | -7.216 |
oons | -6.697 |
rises | -6.441 |
Token | having |
Token ID | 1719 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
rons | +1.080 |
liam | +1.045 |
enegger | +0.953 |
oons | +0.877 |
rises | +0.848 |
Neg logit contributions | |
ciplinary | -0.589 |
CLASSIFIED | -0.557 |
vantage | -0.529 |
ffect | -0.508 |
unexplained | -0.501 |
Token | to |
Token ID | 284 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
rons | +4.348 |
liam | +4.225 |
enegger | +3.845 |
oons | +3.557 |
ries | +3.446 |
Neg logit contributions | |
ciplinary | -2.131 |
CLASSIFIED | -2.003 |
vantage | -1.893 |
ffect | -1.798 |
unexplained | -1.754 |
Token | do |
Token ID | 466 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
ciplinary | +0.161 |
CLASSIFIED | +0.151 |
vantage | +0.141 |
probation | +0.139 |
ffect | +0.139 |
Neg logit contributions | |
rons | -0.314 |
liam | -0.302 |
enegger | -0.278 |
oons | -0.259 |
rises | -0.247 |
Token | with |
Token ID | 351 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
ciplinary | +1.906 |
CLASSIFIED | +1.779 |
vantage | +1.684 |
ffect | +1.660 |
probation | +1.646 |
Neg logit contributions | |
rons | -3.006 |
liam | -2.891 |
enegger | -2.629 |
oons | -2.426 |
rises | -2.322 |
Token | leaving |
Token ID | 4305 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
rons | +0.090 |
liam | +0.087 |
enegger | +0.080 |
oons | +0.074 |
rises | +0.071 |
Neg logit contributions | |
ciplinary | -0.046 |
CLASSIFIED | -0.044 |
vantage | -0.042 |
ffect | -0.040 |
probation | -0.039 |
Token | chain |
Token ID | 6333 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
ciplinary | +3.421 |
CLASSIFIED | +3.212 |
vantage | +3.174 |
ffect | +3.138 |
probation | +3.079 |
Neg logit contributions | |
rons | -6.869 |
liam | -6.550 |
enegger | -6.136 |
oons | -5.556 |
rises | -5.362 |
Token | migration |
Token ID | 13472 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
ciplinary | +7.639 |
probation | +7.370 |
versa | +7.056 |
CLASSIFIED | +7.044 |
vantage | +6.912 |
Neg logit contributions | |
rons | -15.809 |
liam | -15.441 |
enegger | -14.687 |
oons | -13.249 |
iator | -12.572 |
Token | . |
Token ID | 13 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
ciplinary | +1.900 |
CLASSIFIED | +1.782 |
vantage | +1.738 |
unexplained | +1.722 |
probation | +1.694 |
Neg logit contributions | |
rons | -3.908 |
liam | -3.789 |
enegger | -3.550 |
oons | -3.191 |
rises | -3.093 |
Token | Chain |
Token ID | 21853 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
rons | +0.389 |
liam | +0.374 |
enegger | +0.340 |
oons | +0.311 |
rises | +0.301 |
Neg logit contributions | |
ciplinary | -0.234 |
CLASSIFIED | -0.228 |
vantage | -0.218 |
ffect | -0.208 |
respectively | -0.203 |
Token | migration |
Token ID | 13472 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
ciplinary | +5.923 |
probation | +5.371 |
CLASSIFIED | +5.328 |
vantage | +5.219 |
versa | +4.976 |
Neg logit contributions | |
rons | -15.883 |
liam | -15.466 |
enegger | -14.728 |
oons | -13.556 |
heny | -12.877 |
Token | is |
Token ID | 318 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
ciplinary | +1.761 |
CLASSIFIED | +1.593 |
vantage | +1.547 |
ffect | +1.489 |
probation | +1.479 |
Neg logit contributions | |
rons | -4.644 |
liam | -4.516 |
enegger | -4.203 |
oons | -3.853 |
rises | -3.732 |
Token | games |
Token ID | 1830 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
rons | +0.149 |
liam | +0.144 |
enegger | +0.130 |
oons | +0.120 |
ries | +0.115 |
Neg logit contributions | |
ciplinary | -0.090 |
CLASSIFIED | -0.085 |
vantage | -0.081 |
ffect | -0.078 |
unexplained | -0.076 |
Token | with |
Token ID | 351 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
ciplinary | +0.011 |
CLASSIFIED | +0.010 |
vantage | +0.010 |
ffect | +0.009 |
unexplained | +0.009 |
Neg logit contributions | |
rons | -0.015 |
liam | -0.014 |
enegger | -0.013 |
oons | -0.012 |
ries | -0.011 |
Token | AA |
Token ID | 15923 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
ciplinary | +0.464 |
CLASSIFIED | +0.433 |
vantage | +0.404 |
ffect | +0.381 |
unexplained | +0.369 |
Neg logit contributions | |
rons | -1.155 |
liam | -1.125 |
enegger | -1.029 |
oons | -0.958 |
ries | -0.930 |
Token | on |
Token ID | 319 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
ciplinary | +3.235 |
vantage | +2.871 |
CLASSIFIED | +2.853 |
ffect | +2.804 |
respectively | +2.779 |
Neg logit contributions | |
rons | -7.147 |
liam | -7.047 |
enegger | -6.541 |
oons | -5.906 |
rises | -5.734 |
Token | ( |
Token ID | 357 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
ciplinary | +2.598 |
CLASSIFIED | +2.423 |
vantage | +2.315 |
ffect | +2.236 |
probation | +2.163 |
Neg logit contributions | |
rons | -5.872 |
liam | -5.685 |
enegger | -5.227 |
oons | -4.814 |
rises | -4.686 |
Token | Anti |
Token ID | 28795 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
ciplinary | +1.745 |
CLASSIFIED | +1.651 |
vantage | +1.560 |
ffect | +1.484 |
probation | +1.426 |
Neg logit contributions | |
rons | -3.511 |
liam | -3.403 |
enegger | -3.134 |
oons | -2.872 |
rises | -2.765 |
Token | Ali |
Token ID | 37893 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
ciplinary | +6.610 |
vantage | +6.080 |
CLASSIFIED | +5.889 |
SPONSORED | +5.545 |
ffect | +5.444 |
Neg logit contributions | |
rons | -17.625 |
liam | -17.088 |
enegger | -16.296 |
oons | -14.553 |
rises | -14.291 |
Token | asing |
Token ID | 2313 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
ciplinary | +5.203 |
vantage | +4.848 |
CLASSIFIED | +4.719 |
ffect | +4.664 |
pped | +4.491 |
Neg logit contributions | |
rons | -6.251 |
liam | -6.017 |
enegger | -5.489 |
oons | -4.730 |
rises | -4.626 |
Token | is |
Token ID | 318 |
Feature activation | -7.46e+00 |
Pos logit contributions | |
ciplinary | +2.611 |
vantage | +2.141 |
CLASSIFIED | +2.110 |
ffect | +2.036 |
respectively | +2.031 |
Neg logit contributions | |
rons | -9.205 |
liam | -8.927 |
enegger | -8.342 |
oons | -7.750 |
rises | -7.555 |
Token | a |
Token ID | 257 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
ciplinary | +3.787 |
CLASSIFIED | +3.233 |
respectively | +3.183 |
unexplained | +3.176 |
probation | +3.174 |
Neg logit contributions | |
rons | -9.177 |
liam | -8.802 |
enegger | -8.274 |
oons | -7.520 |
rises | -7.346 |
Token | technique |
Token ID | 8173 |
Feature activation | -8.26e+00 |
Pos logit contributions | |
ciplinary | +3.190 |
CLASSIFIED | +2.774 |
vantage | +2.741 |
ffect | +2.635 |
unexplained | +2.552 |
Neg logit contributions | |
rons | -8.475 |
liam | -8.213 |
enegger | -7.603 |
oons | -7.046 |
rises | -6.808 |
Token | place |
Token ID | 1295 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
ciplinary | +4.529 |
ffect | +4.343 |
CLASSIFIED | +4.285 |
respectively | +4.276 |
vantage | +4.268 |
Neg logit contributions | |
rons | -8.699 |
liam | -8.639 |
enegger | -8.053 |
oons | -7.196 |
rises | -6.859 |
Token | . |
Token ID | 13 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
rons | +0.877 |
liam | +0.855 |
enegger | +0.773 |
oons | +0.713 |
rises | +0.688 |
Neg logit contributions | |
ciplinary | -0.476 |
CLASSIFIED | -0.447 |
vantage | -0.430 |
ffect | -0.411 |
respectively | -0.404 |
Token |
|
Token ID | 198 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ciplinary | +1.937 |
CLASSIFIED | +1.853 |
vantage | +1.747 |
ffect | +1.715 |
respectively | +1.702 |
Neg logit contributions | |
rons | -4.146 |
liam | -4.021 |
enegger | -3.683 |
oons | -3.363 |
ries | -3.268 |
Token |
|
Token ID | 198 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
ciplinary | +1.004 |
CLASSIFIED | +0.933 |
vantage | +0.891 |
ffect | +0.857 |
respectively | +0.835 |
Neg logit contributions | |
rons | -1.962 |
liam | -1.902 |
enegger | -1.741 |
oons | -1.596 |
rises | -1.545 |
Token | Dec |
Token ID | 10707 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
rons | +0.440 |
liam | +0.425 |
enegger | +0.388 |
oons | +0.350 |
ries | +0.338 |
Neg logit contributions | |
ciplinary | -0.286 |
CLASSIFIED | -0.273 |
vantage | -0.258 |
ffect | -0.250 |
probation | -0.242 |
Token | ades |
Token ID | 2367 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
rons | +4.864 |
liam | +4.670 |
enegger | +4.153 |
oons | +3.799 |
ries | +3.673 |
Neg logit contributions | |
ciplinary | -3.760 |
CLASSIFIED | -3.631 |
vantage | -3.442 |
ffect | -3.311 |
unexplained | -3.275 |
Token | ago |
Token ID | 2084 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ciplinary | +7.312 |
probation | +6.526 |
respectively | +6.368 |
vantage | +6.294 |
CLASSIFIED | +6.288 |
Neg logit contributions | |
rons | -16.674 |
liam | -16.273 |
enegger | -15.089 |
oons | -13.813 |
rises | -13.294 |
Token | , |
Token ID | 11 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
ciplinary | +0.839 |
CLASSIFIED | +0.778 |
vantage | +0.734 |
ffect | +0.713 |
probation | +0.711 |
Neg logit contributions | |
rons | -1.801 |
liam | -1.747 |
enegger | -1.595 |
oons | -1.475 |
ries | -1.431 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
rons | +2.636 |
liam | +2.555 |
enegger | +2.313 |
oons | +2.124 |
ries | +2.052 |
Neg logit contributions | |
ciplinary | -1.549 |
CLASSIFIED | -1.461 |
vantage | -1.391 |
ffect | -1.336 |
unexplained | -1.313 |
Token | city |
Token ID | 1748 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
ciplinary | +0.752 |
CLASSIFIED | +0.702 |
vantage | +0.675 |
ffect | +0.662 |
probation | +0.657 |
Neg logit contributions | |
rons | -1.207 |
liam | -1.176 |
enegger | -1.059 |
oons | -0.965 |
ries | -0.932 |
Token | planted |
Token ID | 18969 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
rons | +0.376 |
liam | +0.366 |
enegger | +0.333 |
oons | +0.307 |
rises | +0.297 |
Neg logit contributions | |
ciplinary | -0.211 |
CLASSIFIED | -0.198 |
vantage | -0.188 |
ffect | -0.182 |
probation | -0.180 |
Token | . |
Token ID | 13 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
ciplinary | +3.653 |
CLASSIFIED | +3.443 |
vantage | +3.394 |
respectively | +3.294 |
ffect | +3.289 |
Neg logit contributions | |
rons | -3.968 |
liam | -3.809 |
enegger | -3.446 |
oons | -2.976 |
覚醒 | -2.855 |
Token | I |
Token ID | 40 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
ciplinary | +2.031 |
CLASSIFIED | +1.911 |
vantage | +1.898 |
respectively | +1.812 |
probation | +1.767 |
Neg logit contributions | |
rons | -3.208 |
liam | -3.099 |
enegger | -2.809 |
oons | -2.549 |
ries | -2.472 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ciplinary | +3.795 |
CLASSIFIED | +3.563 |
vantage | +3.459 |
respectively | +3.407 |
ffect | +3.376 |
Neg logit contributions | |
rons | -9.061 |
liam | -8.711 |
enegger | -8.123 |
oons | -7.414 |
rises | -7.254 |
Token | P |
Token ID | 47 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
ciplinary | +0.898 |
CLASSIFIED | +0.835 |
vantage | +0.790 |
respectively | +0.755 |
ffect | +0.751 |
Neg logit contributions | |
rons | -2.289 |
liam | -2.224 |
enegger | -2.048 |
oons | -1.887 |
rises | -1.829 |
Token | ., |
Token ID | 1539 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
ciplinary | +1.554 |
CLASSIFIED | +1.499 |
vantage | +1.437 |
respectively | +1.370 |
ffect | +1.346 |
Neg logit contributions | |
rons | -3.082 |
liam | -3.001 |
enegger | -2.730 |
oons | -2.479 |
rises | -2.429 |
Token | Self |
Token ID | 12189 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
rons | +2.657 |
liam | +2.578 |
enegger | +2.340 |
oons | +2.148 |
rises | +2.077 |
Neg logit contributions | |
ciplinary | -1.505 |
CLASSIFIED | -1.426 |
vantage | -1.351 |
ffect | -1.292 |
unexplained | -1.271 |
Token | ie |
Token ID | 494 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
ciplinary | +10.728 |
respectively | +10.160 |
vantage | +10.146 |
CLASSIFIED | +9.897 |
ffect | +9.788 |
Neg logit contributions | |
rons | -12.399 |
liam | -11.975 |
enegger | -11.496 |
oons | -9.637 |
覚醒 | -9.479 |
Token | ), |
Token ID | 828 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ciplinary | +2.999 |
CLASSIFIED | +2.927 |
vantage | +2.793 |
respectively | +2.681 |
probation | +2.628 |
Neg logit contributions | |
rons | -6.052 |
liam | -5.923 |
enegger | -5.481 |
oons | -4.949 |
rises | -4.796 |
Token | but |
Token ID | 475 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
ciplinary | +0.889 |
CLASSIFIED | +0.831 |
vantage | +0.772 |
unexplained | +0.752 |
respectively | +0.749 |
Neg logit contributions | |
rons | -1.900 |
liam | -1.837 |
enegger | -1.687 |
oons | -1.546 |
rises | -1.507 |
Token | , |
Token ID | 11 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
ciplinary | +2.771 |
CLASSIFIED | +2.632 |
unexplained | +2.480 |
respectively | +2.469 |
probation | +2.442 |
Neg logit contributions | |
rons | -5.299 |
liam | -5.162 |
enegger | -4.818 |
oons | -4.335 |
rises | -4.181 |
Token | as |
Token ID | 355 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
rons | +0.670 |
liam | +0.650 |
enegger | +0.591 |
oons | +0.544 |
ries | +0.524 |
Neg logit contributions | |
ciplinary | -0.374 |
CLASSIFIED | -0.352 |
vantage | -0.333 |
ffect | -0.320 |
respectively | -0.319 |
Token | . |
Token ID | 13 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
ciplinary | +3.003 |
probation | +2.862 |
CLASSIFIED | +2.860 |
vantage | +2.759 |
respectively | +2.637 |
Neg logit contributions | |
rons | -6.374 |
liam | -6.246 |
enegger | -5.847 |
oons | -5.421 |
rises | -5.080 |
Token | The |
Token ID | 383 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
rons | +2.353 |
liam | +2.272 |
enegger | +2.032 |
oons | +1.845 |
ries | +1.773 |
Neg logit contributions | |
ciplinary | -1.793 |
CLASSIFIED | -1.715 |
vantage | -1.643 |
ffect | -1.585 |
probation | -1.555 |
Token | sentence |
Token ID | 6827 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ciplinary | +0.756 |
CLASSIFIED | +0.711 |
probation | +0.685 |
vantage | +0.679 |
ffect | +0.664 |
Neg logit contributions | |
rons | -1.171 |
liam | -1.140 |
enegger | -1.038 |
oons | -0.940 |
rises | -0.907 |
Token | of |
Token ID | 286 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ciplinary | +0.701 |
CLASSIFIED | +0.630 |
probation | +0.613 |
vantage | +0.598 |
ffect | +0.593 |
Neg logit contributions | |
rons | -1.615 |
liam | -1.578 |
enegger | -1.466 |
oons | -1.341 |
rises | -1.290 |
Token | 20 |
Token ID | 1160 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
ciplinary | +1.683 |
CLASSIFIED | +1.560 |
probation | +1.558 |
unexplained | +1.459 |
vantage | +1.445 |
Neg logit contributions | |
rons | -3.345 |
liam | -3.273 |
enegger | -3.011 |
oons | -2.773 |
rises | -2.656 |
Token | years |
Token ID | 812 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
ciplinary | +1.588 |
CLASSIFIED | +1.518 |
vantage | +1.447 |
probation | +1.430 |
ffect | +1.402 |
Neg logit contributions | |
rons | -2.010 |
liam | -1.943 |
enegger | -1.754 |
oons | -1.563 |
rises | -1.511 |
Token | , |
Token ID | 11 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
probation | +7.471 |
ciplinary | +7.194 |
respectively | +6.420 |
unexplained | +6.229 |
unclear | +6.071 |
Neg logit contributions | |
rons | -16.469 |
liam | -16.274 |
enegger | -15.302 |
oons | -13.986 |
覚醒 | -13.797 |
Token | or |
Token ID | 393 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
ciplinary | +2.192 |
CLASSIFIED | +2.077 |
probation | +2.066 |
respectively | +1.976 |
unexplained | +1.939 |
Neg logit contributions | |
rons | -4.439 |
liam | -4.360 |
enegger | -3.972 |
oons | -3.675 |
ries | -3.548 |
Token | whatever |
Token ID | 4232 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ciplinary | +2.359 |
probation | +2.244 |
CLASSIFIED | +2.240 |
respectively | +2.122 |
unexplained | +2.086 |
Neg logit contributions | |
rons | -4.662 |
liam | -4.604 |
enegger | -4.182 |
oons | -3.899 |
rises | -3.704 |
Token | it |
Token ID | 340 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
rons | +1.556 |
liam | +1.512 |
enegger | +1.381 |
oons | +1.276 |
rises | +1.235 |
Neg logit contributions | |
ciplinary | -0.740 |
CLASSIFIED | -0.694 |
vantage | -0.654 |
ffect | -0.623 |
probation | -0.612 |
Token | happens |
Token ID | 4325 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
rons | +3.549 |
liam | +3.453 |
enegger | +3.158 |
oons | +2.933 |
rises | +2.845 |
Neg logit contributions | |
ciplinary | -1.482 |
CLASSIFIED | -1.376 |
vantage | -1.292 |
ffect | -1.222 |
probation | -1.189 |
Token | charged |
Token ID | 5047 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ciplinary | +3.886 |
probation | +3.544 |
respectively | +3.464 |
CLASSIFIED | +3.410 |
vantage | +3.318 |
Neg logit contributions | |
liam | -7.262 |
rons | -7.181 |
enegger | -6.619 |
oons | -5.987 |
rises | -5.883 |
Token | him |
Token ID | 683 |
Feature activation | -9.74e-02 |
Pos logit contributions | |
ciplinary | +1.071 |
CLASSIFIED | +0.976 |
probation | +0.930 |
vantage | +0.925 |
unexplained | +0.897 |
Neg logit contributions | |
rons | -2.351 |
liam | -2.318 |
enegger | -2.131 |
oons | -1.945 |
rises | -1.884 |
Token | with |
Token ID | 351 |
Feature activation | -8.05e+00 |
Pos logit contributions | |
ciplinary | +0.067 |
CLASSIFIED | +0.063 |
vantage | +0.060 |
probation | +0.059 |
respectively | +0.059 |
Neg logit contributions | |
rons | -0.105 |
liam | -0.103 |
enegger | -0.093 |
oons | -0.085 |
rises | -0.081 |
Token | first |
Token ID | 717 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
ciplinary | +4.221 |
probation | +3.986 |
intentional | +3.865 |
CLASSIFIED | +3.802 |
unexplained | +3.796 |
Neg logit contributions | |
liam | -9.536 |
rons | -9.462 |
enegger | -8.725 |
oons | -7.927 |
rises | -7.650 |
Token | - |
Token ID | 12 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
ciplinary | +3.491 |
CLASSIFIED | +3.077 |
probation | +3.072 |
intentional | +3.070 |
unexplained | +3.060 |
Neg logit contributions | |
rons | -11.233 |
liam | -11.051 |
enegger | -10.627 |
oons | -9.538 |
rises | -9.315 |
Token | degree |
Token ID | 16863 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
ciplinary | +5.041 |
intentional | +4.269 |
respectively | +4.267 |
ffect | +4.249 |
probation | +4.174 |
Neg logit contributions | |
rons | -15.020 |
liam | -14.975 |
enegger | -14.685 |
oons | -12.795 |
iator | -12.435 |
Token | murder |
Token ID | 5123 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
intentional | +7.068 |
ciplinary | +6.437 |
probation | +6.403 |
unexplained | +6.086 |
ffect | +5.790 |
Neg logit contributions | |
liam | -17.194 |
rons | -16.872 |
enegger | -16.158 |
oons | -14.486 |
rises | -14.034 |
Token | and |
Token ID | 290 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
ciplinary | +2.348 |
CLASSIFIED | +2.221 |
respectively | +2.110 |
probation | +2.103 |
vantage | +2.096 |
Neg logit contributions | |
rons | -5.206 |
liam | -5.140 |
enegger | -4.695 |
oons | -4.343 |
rises | -4.174 |
Token | first |
Token ID | 717 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
ciplinary | +3.737 |
probation | +3.521 |
intentional | +3.412 |
unexplained | +3.365 |
CLASSIFIED | +3.307 |
Neg logit contributions | |
liam | -8.135 |
rons | -8.078 |
enegger | -7.412 |
oons | -6.769 |
rises | -6.550 |
Token | - |
Token ID | 12 |
Feature activation | -8.03e+00 |
Pos logit contributions | |
ciplinary | +1.694 |
CLASSIFIED | +1.524 |
probation | +1.414 |
vantage | +1.386 |
unexplained | +1.377 |
Neg logit contributions | |
rons | -5.418 |
liam | -5.317 |
enegger | -5.012 |
oons | -4.571 |
rises | -4.453 |
Token | degree |
Token ID | 16863 |
Feature activation | -8.93e+00 |
Pos logit contributions | |
ciplinary | +3.908 |
vantage | +3.321 |
ffect | +3.219 |
respectively | +3.191 |
CLASSIFIED | +3.180 |
Neg logit contributions | |
rons | -9.970 |
liam | -9.753 |
enegger | -9.411 |
oons | -8.377 |
rises | -8.006 |
Token | K |
Token ID | 42 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
rons | +2.691 |
liam | +2.599 |
enegger | +2.361 |
oons | +2.147 |
ries | +2.070 |
Neg logit contributions | |
ciplinary | -1.720 |
CLASSIFIED | -1.640 |
vantage | -1.558 |
ffect | -1.495 |
unexplained | -1.456 |
Token | TR |
Token ID | 5446 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
rons | +5.420 |
liam | +5.229 |
enegger | +4.643 |
oons | +4.220 |
ries | +4.050 |
Neg logit contributions | |
ciplinary | -4.444 |
CLASSIFIED | -4.250 |
vantage | -4.079 |
ffect | -3.934 |
unexplained | -3.873 |
Token | 024 |
Token ID | 40839 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
rons | +0.129 |
liam | +0.125 |
enegger | +0.114 |
oons | +0.103 |
rises | +0.100 |
Neg logit contributions | |
ciplinary | -0.077 |
CLASSIFIED | -0.074 |
vantage | -0.070 |
ffect | -0.067 |
unexplained | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
ciplinary | +2.301 |
CLASSIFIED | +2.208 |
vantage | +2.101 |
ffect | +2.045 |
respectively | +2.005 |
Neg logit contributions | |
rons | -3.831 |
liam | -3.704 |
enegger | -3.422 |
oons | -3.039 |
rises | -2.955 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
rons | +0.531 |
liam | +0.515 |
enegger | +0.464 |
oons | +0.429 |
ries | +0.416 |
Neg logit contributions | |
ciplinary | -0.303 |
CLASSIFIED | -0.288 |
vantage | -0.273 |
ffect | -0.260 |
unexplained | -0.255 |
Token | Self |
Token ID | 24704 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
rons | +1.657 |
liam | +1.598 |
enegger | +1.463 |
oons | +1.324 |
ries | +1.276 |
Neg logit contributions | |
ciplinary | -1.030 |
CLASSIFIED | -0.986 |
vantage | -0.931 |
ffect | -0.894 |
unexplained | -0.866 |
Token | described |
Token ID | 3417 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
ciplinary | +9.624 |
CLASSIFIED | +8.977 |
probation | +8.535 |
intentional | +8.447 |
unexplained | +8.284 |
Neg logit contributions | |
rons | -13.733 |
liam | -13.451 |
enegger | -12.679 |
oons | -11.193 |
heny | -10.581 |
Token | as |
Token ID | 355 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
ciplinary | +2.125 |
CLASSIFIED | +1.992 |
vantage | +1.924 |
respectively | +1.883 |
unexplained | +1.848 |
Neg logit contributions | |
rons | -3.974 |
liam | -3.845 |
enegger | -3.540 |
oons | -3.202 |
rises | -3.104 |
Token | " |
Token ID | 366 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
rons | +0.074 |
liam | +0.072 |
enegger | +0.065 |
oons | +0.059 |
ries | +0.058 |
Neg logit contributions | |
ciplinary | -0.040 |
CLASSIFIED | -0.038 |
vantage | -0.036 |
unexplained | -0.035 |
ffect | -0.034 |
Token | f |
Token ID | 69 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
ciplinary | +0.894 |
CLASSIFIED | +0.846 |
vantage | +0.811 |
ffect | +0.769 |
unexplained | +0.749 |
Neg logit contributions | |
rons | -1.413 |
liam | -1.363 |
enegger | -1.256 |
oons | -1.124 |
ries | -1.085 |
Token | ucked |
Token ID | 17758 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
ciplinary | +4.089 |
vantage | +3.826 |
CLASSIFIED | +3.672 |
ffect | +3.625 |
terday | +3.560 |
Neg logit contributions | |
rons | -3.926 |
liam | -3.802 |
enegger | -3.511 |
oons | -2.890 |
rises | -2.852 |
Token | , |
Token ID | 11 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
rons | +3.232 |
liam | +3.139 |
enegger | +2.853 |
oons | +2.636 |
rises | +2.550 |
Neg logit contributions | |
ciplinary | -1.660 |
CLASSIFIED | -1.561 |
vantage | -1.473 |
ffect | -1.408 |
unexplained | -1.377 |
Token | and |
Token ID | 290 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
ciplinary | +0.272 |
CLASSIFIED | +0.258 |
vantage | +0.241 |
respectively | +0.232 |
ffect | +0.231 |
Neg logit contributions | |
rons | -0.506 |
liam | -0.492 |
enegger | -0.449 |
oons | -0.412 |
rises | -0.398 |
Token | Schiff |
Token ID | 41665 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
ciplinary | +2.524 |
CLASSIFIED | +2.412 |
vantage | +2.237 |
respectively | +2.224 |
probation | +2.195 |
Neg logit contributions | |
rons | -3.976 |
liam | -3.931 |
enegger | -3.555 |
oons | -3.202 |
rises | -3.115 |
Token | man |
Token ID | 805 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
rons | +2.882 |
liam | +2.761 |
enegger | +2.454 |
oons | +2.209 |
ries | +2.127 |
Neg logit contributions | |
ciplinary | -2.508 |
CLASSIFIED | -2.474 |
vantage | -2.322 |
ffect | -2.237 |
terday | -2.220 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
rons | +2.152 |
liam | +2.090 |
enegger | +1.900 |
oons | +1.756 |
rises | +1.699 |
Neg logit contributions | |
ciplinary | -1.095 |
CLASSIFIED | -1.030 |
vantage | -0.974 |
ffect | -0.928 |
respectively | -0.911 |
Token | Outside |
Token ID | 22151 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
ciplinary | +1.561 |
CLASSIFIED | +1.477 |
respectively | +1.406 |
vantage | +1.396 |
ffect | +1.363 |
Neg logit contributions | |
rons | -2.062 |
liam | -1.985 |
enegger | -1.786 |
oons | -1.617 |
rises | -1.561 |
Token | the |
Token ID | 262 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
ciplinary | +6.573 |
CLASSIFIED | +6.298 |
respectively | +6.154 |
vantage | +5.799 |
probation | +5.365 |
Neg logit contributions | |
rons | -16.581 |
liam | -16.452 |
enegger | -15.350 |
oons | -13.927 |
rises | -13.521 |
Token | Bible |
Token ID | 9111 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
ciplinary | +3.743 |
CLASSIFIED | +3.499 |
vantage | +3.440 |
respectively | +3.340 |
ffect | +3.335 |
Neg logit contributions | |
rons | -4.930 |
liam | -4.760 |
enegger | -4.287 |
oons | -3.824 |
rises | -3.717 |
Token | , |
Token ID | 11 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ciplinary | +0.385 |
CLASSIFIED | +0.359 |
vantage | +0.342 |
respectively | +0.331 |
ffect | +0.330 |
Neg logit contributions | |
rons | -0.731 |
liam | -0.709 |
enegger | -0.653 |
oons | -0.593 |
rises | -0.576 |
Token | 3 |
Token ID | 513 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
ciplinary | +0.971 |
CLASSIFIED | +0.916 |
vantage | +0.869 |
respectively | +0.857 |
ffect | +0.847 |
Neg logit contributions | |
rons | -1.435 |
liam | -1.390 |
enegger | -1.279 |
oons | -1.141 |
rises | -1.103 |
Token | - |
Token ID | 12 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
rons | +0.574 |
liam | +0.559 |
enegger | +0.512 |
oons | +0.463 |
rises | +0.449 |
Neg logit contributions | |
ciplinary | -0.345 |
CLASSIFIED | -0.326 |
vantage | -0.307 |
ffect | -0.299 |
respectively | -0.296 |
Token | - |
Token ID | 12 |
Feature activation | -9.07e+00 |
Pos logit contributions | |
ciplinary | +4.785 |
CLASSIFIED | +4.335 |
vantage | +4.166 |
pped | +4.021 |
ffect | +4.005 |
Neg logit contributions | |
rons | -11.016 |
liam | -10.860 |
enegger | -9.829 |
oons | -9.126 |
rises | -8.993 |
Token | working |
Token ID | 16090 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ciplinary | +4.155 |
vantage | +3.431 |
ffect | +3.355 |
CLASSIFIED | +3.336 |
pped | +3.199 |
Neg logit contributions | |
rons | -11.160 |
liam | -11.024 |
enegger | -10.187 |
oons | -9.320 |
heny | -9.182 |
Token | , |
Token ID | 11 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ciplinary | +0.844 |
CLASSIFIED | +0.785 |
vantage | +0.734 |
ffect | +0.716 |
probation | +0.698 |
Neg logit contributions | |
rons | -2.033 |
liam | -2.009 |
enegger | -1.826 |
oons | -1.688 |
rises | -1.656 |
Token | organized |
Token ID | 8389 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
ciplinary | +1.113 |
CLASSIFIED | +1.000 |
vantage | +0.936 |
ffect | +0.918 |
unexplained | +0.910 |
Neg logit contributions | |
rons | -2.389 |
liam | -2.330 |
enegger | -2.139 |
oons | -1.966 |
rises | -1.911 |
Token | , |
Token ID | 11 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
ciplinary | +1.581 |
CLASSIFIED | +1.469 |
vantage | +1.387 |
ffect | +1.361 |
probation | +1.335 |
Neg logit contributions | |
rons | -3.982 |
liam | -3.911 |
enegger | -3.630 |
oons | -3.327 |
rises | -3.262 |
Token | self |
Token ID | 2116 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
ciplinary | +1.160 |
CLASSIFIED | +1.030 |
vantage | +0.953 |
ffect | +0.933 |
unexplained | +0.927 |
Neg logit contributions | |
rons | -3.001 |
liam | -2.918 |
enegger | -2.699 |
oons | -2.500 |
rises | -2.429 |
Token | - |
Token ID | 12 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
ciplinary | +7.751 |
intentional | +6.667 |
probation | +6.512 |
ffect | +6.463 |
CLASSIFIED | +6.349 |
Neg logit contributions | |
rons | -16.193 |
liam | -15.746 |
enegger | -14.516 |
oons | -13.610 |
rams | -12.995 |
Token | mot |
Token ID | 27926 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
ciplinary | +7.588 |
vantage | +6.169 |
ffect | +6.060 |
CLASSIFIED | +5.927 |
pped | +5.790 |
Neg logit contributions | |
rons | -13.970 |
liam | -13.679 |
enegger | -12.754 |
oons | -11.673 |
rams | -11.208 |
Token | ivated |
Token ID | 30829 |
Feature activation | -7.87e+00 |
Pos logit contributions | |
ciplinary | +3.062 |
CLASSIFIED | +2.795 |
vantage | +2.735 |
ffect | +2.671 |
terday | +2.601 |
Neg logit contributions | |
rons | -4.742 |
liam | -4.697 |
enegger | -4.268 |
oons | -3.835 |
rises | -3.765 |
Token | , |
Token ID | 11 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
ciplinary | +3.493 |
CLASSIFIED | +3.206 |
ffect | +3.093 |
respectively | +2.993 |
vantage | +2.976 |
Neg logit contributions | |
rons | -9.660 |
liam | -9.640 |
enegger | -8.973 |
oons | -8.078 |
rises | -7.992 |
Token | and |
Token ID | 290 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
ciplinary | +1.618 |
CLASSIFIED | +1.430 |
vantage | +1.327 |
ffect | +1.310 |
intentional | +1.307 |
Neg logit contributions | |
rons | -4.075 |
liam | -3.972 |
enegger | -3.669 |
oons | -3.381 |
rises | -3.289 |
Token | could |
Token ID | 714 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
rons | +4.530 |
liam | +4.401 |
enegger | +4.003 |
oons | +3.713 |
ries | +3.595 |
Neg logit contributions | |
ciplinary | -2.122 |
CLASSIFIED | -2.006 |
vantage | -1.875 |
ffect | -1.768 |
unexplained | -1.727 |
Token | shoot |
Token ID | 2686 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
rons | +1.701 |
liam | +1.649 |
enegger | +1.495 |
oons | +1.361 |
rises | +1.307 |
Neg logit contributions | |
ciplinary | -1.106 |
CLASSIFIED | -1.036 |
vantage | -1.004 |
ffect | -0.974 |
respectively | -0.954 |
Token | with |
Token ID | 351 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
ciplinary | +0.367 |
CLASSIFIED | +0.346 |
vantage | +0.325 |
unexplained | +0.315 |
ffect | +0.312 |
Neg logit contributions | |
rons | -0.777 |
liam | -0.758 |
enegger | -0.692 |
oons | -0.633 |
ries | -0.618 |
Token | that |
Token ID | 326 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
rons | +0.872 |
liam | +0.852 |
enegger | +0.781 |
oons | +0.719 |
rises | +0.697 |
Neg logit contributions | |
ciplinary | -0.391 |
CLASSIFIED | -0.361 |
vantage | -0.343 |
ffect | -0.329 |
unexplained | -0.325 |
Token | ," |
Token ID | 553 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
ciplinary | +0.461 |
CLASSIFIED | +0.435 |
vantage | +0.421 |
ffect | +0.408 |
unexplained | +0.403 |
Neg logit contributions | |
rons | -0.747 |
liam | -0.729 |
enegger | -0.658 |
oons | -0.599 |
rises | -0.579 |
Token | Retro |
Token ID | 29884 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
rons | +0.992 |
liam | +0.966 |
enegger | +0.872 |
oons | +0.806 |
rises | +0.777 |
Neg logit contributions | |
ciplinary | -0.534 |
CLASSIFIED | -0.502 |
vantage | -0.479 |
ffect | -0.458 |
unexplained | -0.452 |
Token | Camera |
Token ID | 20432 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ciplinary | +6.100 |
vantage | +5.736 |
CLASSIFIED | +5.720 |
Scouting | +5.091 |
respectively | +5.012 |
Neg logit contributions | |
liam | -17.289 |
rons | -16.945 |
enegger | -15.490 |
oons | -14.131 |
ries | -13.728 |
Token | should |
Token ID | 815 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
ciplinary | +0.936 |
CLASSIFIED | +0.869 |
vantage | +0.830 |
unexplained | +0.796 |
respectively | +0.792 |
Neg logit contributions | |
rons | -2.003 |
liam | -1.968 |
enegger | -1.800 |
oons | -1.639 |
rises | -1.591 |
Token | be |
Token ID | 307 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ciplinary | +2.013 |
vantage | +1.813 |
CLASSIFIED | +1.796 |
ffect | +1.787 |
respectively | +1.779 |
Neg logit contributions | |
rons | -3.723 |
liam | -3.643 |
enegger | -3.310 |
oons | -3.029 |
rises | -2.890 |
Token | your |
Token ID | 534 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
rons | +0.428 |
liam | +0.416 |
enegger | +0.380 |
oons | +0.351 |
rises | +0.336 |
Neg logit contributions | |
ciplinary | -0.217 |
CLASSIFIED | -0.201 |
vantage | -0.192 |
ffect | -0.184 |
probation | -0.183 |
Token | next |
Token ID | 1306 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
rons | +0.508 |
liam | +0.494 |
enegger | +0.447 |
oons | +0.411 |
rises | +0.395 |
Neg logit contributions | |
ciplinary | -0.294 |
CLASSIFIED | -0.275 |
vantage | -0.262 |
ffect | -0.253 |
probation | -0.250 |
Token | O |
Token ID | 440 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
ciplinary | +1.669 |
CLASSIFIED | +1.594 |
vantage | +1.539 |
respectively | +1.461 |
ffect | +1.446 |
Neg logit contributions | |
rons | -3.159 |
liam | -3.053 |
enegger | -2.788 |
oons | -2.537 |
rises | -2.507 |
Token | ka |
Token ID | 4914 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
ciplinary | +3.570 |
vantage | +3.151 |
ffect | +3.055 |
CLASSIFIED | +3.054 |
pped | +2.955 |
Neg logit contributions | |
rons | -5.813 |
liam | -5.610 |
enegger | -5.155 |
oons | -4.631 |
rises | -4.505 |
Token | for |
Token ID | 1640 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
ciplinary | +1.712 |
CLASSIFIED | +1.482 |
vantage | +1.469 |
ffect | +1.404 |
respectively | +1.353 |
Neg logit contributions | |
rons | -3.957 |
liam | -3.821 |
enegger | -3.546 |
oons | -3.259 |
rises | -3.160 |
Token | finished |
Token ID | 5201 |
Feature activation | -6.27e+00 |
Pos logit contributions | |
ciplinary | +1.568 |
CLASSIFIED | +1.386 |
vantage | +1.332 |
respectively | +1.285 |
probation | +1.280 |
Neg logit contributions | |
rons | -3.695 |
liam | -3.573 |
enegger | -3.296 |
oons | -3.044 |
rises | -2.986 |
Token | as |
Token ID | 355 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ciplinary | +3.262 |
CLASSIFIED | +2.980 |
probation | +2.957 |
respectively | +2.854 |
vantage | +2.846 |
Neg logit contributions | |
rons | -7.497 |
liam | -7.213 |
enegger | -6.872 |
oons | -6.267 |
rises | -5.950 |
Token | runner |
Token ID | 17490 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
ciplinary | +0.957 |
CLASSIFIED | +0.910 |
vantage | +0.861 |
probation | +0.819 |
ffect | +0.816 |
Neg logit contributions | |
rons | -1.930 |
liam | -1.880 |
enegger | -1.720 |
oons | -1.578 |
rises | -1.542 |
Token | - |
Token ID | 12 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
ciplinary | +4.020 |
versa | +3.356 |
CLASSIFIED | +3.295 |
respectively | +3.284 |
probation | +3.281 |
Neg logit contributions | |
rons | -19.767 |
liam | -19.187 |
enegger | -18.502 |
oons | -17.010 |
rises | -16.737 |
Token | up |
Token ID | 929 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
ciplinary | +3.212 |
vantage | +2.649 |
CLASSIFIED | +2.267 |
pped | +2.108 |
ffect | +2.090 |
Neg logit contributions | |
rons | -15.827 |
liam | -15.465 |
enegger | -14.606 |
oons | -13.796 |
heny | -13.385 |
Token | to |
Token ID | 284 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
ciplinary | +1.497 |
CLASSIFIED | +1.407 |
vantage | +1.345 |
probation | +1.282 |
respectively | +1.281 |
Neg logit contributions | |
rons | -2.933 |
liam | -2.870 |
enegger | -2.640 |
oons | -2.401 |
rises | -2.340 |
Token | Kam |
Token ID | 12670 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ciplinary | +0.375 |
CLASSIFIED | +0.354 |
vantage | +0.339 |
probation | +0.321 |
ffect | +0.321 |
Neg logit contributions | |
rons | -0.658 |
liam | -0.639 |
enegger | -0.579 |
oons | -0.531 |
rises | -0.516 |
Token | insky |
Token ID | 19870 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
rons | +0.154 |
liam | +0.145 |
enegger | +0.120 |
oons | +0.100 |
ries | +0.093 |
Neg logit contributions | |
ciplinary | -0.286 |
CLASSIFIED | -0.278 |
vantage | -0.270 |
ffect | -0.263 |
unexplained | -0.261 |
Token | oche |
Token ID | 30848 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
ciplinary | +1.609 |
CLASSIFIED | +1.477 |
vantage | +1.461 |
ffect | +1.386 |
respectively | +1.355 |
Neg logit contributions | |
rons | -2.432 |
liam | -2.342 |
enegger | -2.115 |
oons | -1.918 |
rises | -1.855 |
Token | said |
Token ID | 531 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
rons | +0.714 |
liam | +0.691 |
enegger | +0.613 |
oons | +0.567 |
rises | +0.542 |
Neg logit contributions | |
ciplinary | -0.501 |
CLASSIFIED | -0.473 |
vantage | -0.457 |
ffect | -0.437 |
respectively | -0.436 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
rons | +6.833 |
liam | +6.593 |
enegger | +5.960 |
oons | +5.454 |
ries | +5.302 |
Neg logit contributions | |
ciplinary | -4.334 |
CLASSIFIED | -4.123 |
vantage | -3.912 |
ffect | -3.745 |
unexplained | -3.614 |
Token | � |
Token ID | 564 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ciplinary | +0.975 |
CLASSIFIED | +0.953 |
vantage | +0.906 |
ffect | +0.861 |
respectively | +0.853 |
Neg logit contributions | |
rons | -1.820 |
liam | -1.750 |
enegger | -1.594 |
oons | -1.459 |
rises | -1.420 |
Token | � |
Token ID | 250 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
rons | +1.607 |
liam | +1.550 |
enegger | +1.398 |
oons | +1.279 |
rises | +1.230 |
Neg logit contributions | |
ciplinary | -1.075 |
CLASSIFIED | -1.023 |
vantage | -0.976 |
ffect | -0.939 |
probation | -0.922 |
Token | Self |
Token ID | 24704 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
rons | +0.388 |
liam | +0.372 |
enegger | +0.339 |
oons | +0.308 |
rises | +0.296 |
Neg logit contributions | |
ciplinary | -0.246 |
CLASSIFIED | -0.238 |
vantage | -0.226 |
ffect | -0.218 |
terday | -0.212 |
Token | ishly |
Token ID | 29735 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
ciplinary | +9.885 |
vantage | +9.284 |
probation | +8.821 |
ffect | +8.802 |
intentional | +8.785 |
Neg logit contributions | |
rons | -13.304 |
liam | -12.592 |
enegger | -12.100 |
oons | -10.748 |
heny | -10.201 |
Token | I |
Token ID | 314 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ciplinary | +3.459 |
CLASSIFIED | +3.246 |
vantage | +3.191 |
unexplained | +3.058 |
probation | +3.018 |
Neg logit contributions | |
rons | -8.788 |
liam | -8.530 |
enegger | -7.788 |
oons | -7.339 |
rises | -7.098 |
Token | want |
Token ID | 765 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
ciplinary | +0.705 |
CLASSIFIED | +0.647 |
vantage | +0.647 |
probation | +0.610 |
ffect | +0.610 |
Neg logit contributions | |
rons | -1.227 |
liam | -1.192 |
enegger | -1.085 |
oons | -1.010 |
ries | -0.957 |
Token | him |
Token ID | 683 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
ciplinary | +0.224 |
CLASSIFIED | +0.209 |
vantage | +0.196 |
ffect | +0.183 |
unexplained | +0.181 |
Neg logit contributions | |
rons | -0.568 |
liam | -0.553 |
enegger | -0.510 |
oons | -0.470 |
rises | -0.457 |
Token | here |
Token ID | 994 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
rons | +5.565 |
liam | +5.417 |
enegger | +4.928 |
oons | +4.542 |
ries | +4.428 |
Neg logit contributions | |
ciplinary | -2.847 |
CLASSIFIED | -2.688 |
vantage | -2.537 |
ffect | -2.415 |
terday | -2.344 |
Token | sentenced |
Token ID | 11897 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
ciplinary | +1.982 |
CLASSIFIED | +1.734 |
probation | +1.711 |
unexplained | +1.668 |
respectively | +1.661 |
Neg logit contributions | |
rons | -4.161 |
liam | -4.082 |
enegger | -3.718 |
oons | -3.442 |
rises | -3.319 |
Token | last |
Token ID | 938 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ciplinary | +2.119 |
CLASSIFIED | +1.936 |
probation | +1.886 |
respectively | +1.813 |
vantage | +1.720 |
Neg logit contributions | |
rons | -5.478 |
liam | -5.372 |
enegger | -5.000 |
oons | -4.592 |
rises | -4.533 |
Token | Thursday |
Token ID | 3635 |
Feature activation | -9.93e-02 |
Pos logit contributions | |
rons | +3.758 |
liam | +3.643 |
enegger | +3.274 |
oons | +3.004 |
ries | +2.904 |
Neg logit contributions | |
ciplinary | -2.387 |
CLASSIFIED | -2.275 |
vantage | -2.169 |
ffect | -2.072 |
unexplained | -2.023 |
Token | to |
Token ID | 284 |
Feature activation | -5.67e+00 |
Pos logit contributions | |
ciplinary | +0.055 |
CLASSIFIED | +0.050 |
vantage | +0.047 |
ffect | +0.045 |
probation | +0.045 |
Neg logit contributions | |
rons | -0.122 |
liam | -0.119 |
enegger | -0.109 |
oons | -0.101 |
rises | -0.098 |
Token | 35 |
Token ID | 3439 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
ciplinary | +3.482 |
probation | +3.354 |
CLASSIFIED | +3.198 |
unexplained | +3.064 |
respectively | +3.030 |
Neg logit contributions | |
rons | -6.392 |
liam | -6.295 |
enegger | -5.820 |
oons | -5.226 |
rises | -5.072 |
Token | years |
Token ID | 812 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
ciplinary | +5.267 |
probation | +5.021 |
CLASSIFIED | +4.898 |
ffect | +4.734 |
unexplained | +4.713 |
Neg logit contributions | |
rons | -7.474 |
liam | -7.261 |
enegger | -6.693 |
oons | -5.829 |
rises | -5.773 |
Token | in |
Token ID | 287 |
Feature activation | -6.77e+00 |
Pos logit contributions | |
probation | +7.301 |
ciplinary | +6.883 |
respectively | +6.356 |
unexplained | +5.973 |
intentional | +5.941 |
Neg logit contributions | |
rons | -16.443 |
liam | -16.306 |
enegger | -15.042 |
oons | -14.001 |
rises | -13.700 |
Token | prison |
Token ID | 3770 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
ciplinary | +3.509 |
probation | +3.300 |
unexplained | +2.940 |
respectively | +2.922 |
intentional | +2.882 |
Neg logit contributions | |
rons | -8.284 |
liam | -8.074 |
enegger | -7.558 |
oons | -6.820 |
rises | -6.816 |
Token | for |
Token ID | 329 |
Feature activation | -8.10e+00 |
Pos logit contributions | |
ciplinary | +3.000 |
probation | +2.788 |
respectively | +2.724 |
CLASSIFIED | +2.709 |
vantage | +2.569 |
Neg logit contributions | |
rons | -7.128 |
liam | -7.019 |
enegger | -6.365 |
oons | -5.973 |
rises | -5.809 |
Token | his |
Token ID | 465 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
ciplinary | +4.161 |
probation | +3.997 |
intentional | +3.894 |
unexplained | +3.842 |
CLASSIFIED | +3.760 |
Neg logit contributions | |
liam | -9.516 |
rons | -9.418 |
enegger | -8.688 |
oons | -7.856 |
rises | -7.730 |
Token | role |
Token ID | 2597 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
ciplinary | +2.764 |
CLASSIFIED | +2.601 |
probation | +2.591 |
unexplained | +2.575 |
intentional | +2.528 |
Neg logit contributions | |
rons | -3.999 |
liam | -3.959 |
enegger | -3.539 |
oons | -3.184 |
rises | -3.083 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
rons | +3.337 |
liam | +3.229 |
enegger | +2.918 |
oons | +2.695 |
ries | +2.612 |
Neg logit contributions | |
ciplinary | -1.900 |
CLASSIFIED | -1.814 |
vantage | -1.719 |
ffect | -1.645 |
unexplained | -1.603 |
Token |
|
Token ID | 198 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
rons | +2.171 |
liam | +2.115 |
enegger | +1.868 |
oons | +1.746 |
ries | +1.706 |
Neg logit contributions | |
ciplinary | -1.381 |
CLASSIFIED | -1.347 |
vantage | -1.262 |
ffect | -1.189 |
unexplained | -1.186 |
Token | Address |
Token ID | 20231 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
rons | +3.558 |
liam | +3.495 |
enegger | +2.998 |
oons | +2.793 |
ries | +2.695 |
Neg logit contributions | |
ciplinary | -2.959 |
CLASSIFIED | -2.811 |
vantage | -2.723 |
unexplained | -2.636 |
ffect | -2.625 |
Token | : |
Token ID | 25 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
rons | +0.814 |
liam | +0.790 |
enegger | +0.705 |
oons | +0.648 |
ries | +0.628 |
Neg logit contributions | |
ciplinary | -0.547 |
CLASSIFIED | -0.525 |
vantage | -0.498 |
ffect | -0.476 |
unexplained | -0.469 |
Token | Kal |
Token ID | 12612 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
rons | +5.055 |
liam | +4.894 |
enegger | +4.399 |
oons | +4.034 |
ries | +3.896 |
Neg logit contributions | |
ciplinary | -3.290 |
CLASSIFIED | -3.119 |
vantage | -2.977 |
ffect | -2.855 |
unexplained | -2.800 |
Token | up |
Token ID | 929 |
Feature activation | +8.82e+00 |
Pos logit contributions | |
rons | +4.473 |
liam | +4.333 |
enegger | +3.869 |
oons | +3.539 |
ries | +3.410 |
Neg logit contributions | |
ciplinary | -3.203 |
CLASSIFIED | -3.080 |
vantage | -2.923 |
ffect | -2.808 |
unexplained | -2.769 |
Token | ur |
Token ID | 333 |
Feature activation | +7.16e+00 |
Pos logit contributions | |
rons | +8.757 |
liam | +8.380 |
enegger | +7.402 |
oons | +6.851 |
ries | +6.594 |
Neg logit contributions | |
ciplinary | -6.682 |
CLASSIFIED | -6.588 |
vantage | -6.084 |
unexplained | -5.859 |
ffect | -5.839 |
Token | , |
Token ID | 11 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
rons | +7.783 |
liam | +7.593 |
enegger | +6.748 |
oons | +6.251 |
ries | +6.068 |
Neg logit contributions | |
ciplinary | -4.767 |
CLASSIFIED | -4.616 |
vantage | -4.307 |
ffect | -4.088 |
unexplained | -4.035 |
Token | Ahmed |
Token ID | 21157 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
rons | +5.351 |
liam | +5.181 |
enegger | +4.626 |
oons | +4.214 |
ries | +4.068 |
Neg logit contributions | |
ciplinary | -3.918 |
CLASSIFIED | -3.730 |
vantage | -3.567 |
ffect | -3.432 |
terday | -3.366 |
Token | abad |
Token ID | 17325 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
rons | +2.367 |
liam | +2.263 |
enegger | +1.943 |
oons | +1.698 |
ries | +1.603 |
Neg logit contributions | |
ciplinary | -3.109 |
CLASSIFIED | -3.000 |
vantage | -2.907 |
ffect | -2.828 |
unexplained | -2.790 |
Token | , |
Token ID | 11 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
rons | +2.141 |
liam | +2.078 |
enegger | +1.889 |
oons | +1.742 |
rises | +1.685 |
Neg logit contributions | |
ciplinary | -1.124 |
CLASSIFIED | -1.062 |
vantage | -1.004 |
ffect | -0.958 |
unexplained | -0.936 |
Token | � |
Token ID | 447 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
rons | +1.171 |
liam | +1.126 |
enegger | +1.033 |
oons | +0.935 |
rises | +0.901 |
Neg logit contributions | |
ciplinary | -0.730 |
CLASSIFIED | -0.704 |
vantage | -0.658 |
ffect | -0.635 |
respectively | -0.614 |
Token | � |
Token ID | 250 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
rons | +0.767 |
liam | +0.734 |
enegger | +0.662 |
oons | +0.598 |
rises | +0.574 |
Neg logit contributions | |
ciplinary | -0.593 |
CLASSIFIED | -0.575 |
vantage | -0.543 |
ffect | -0.529 |
unexplained | -0.521 |
Token | We |
Token ID | 1135 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
ciplinary | +3.045 |
CLASSIFIED | +2.942 |
vantage | +2.798 |
ffect | +2.758 |
probation | +2.617 |
Neg logit contributions | |
rons | -5.164 |
liam | -5.002 |
enegger | -4.586 |
oons | -4.101 |
rises | -3.999 |
Token | do |
Token ID | 466 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
rons | +1.163 |
liam | +1.135 |
enegger | +1.030 |
oons | +0.955 |
rises | +0.922 |
Neg logit contributions | |
ciplinary | -0.610 |
CLASSIFIED | -0.561 |
vantage | -0.538 |
ffect | -0.519 |
respectively | -0.509 |
Token | know |
Token ID | 760 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
ciplinary | +1.313 |
CLASSIFIED | +1.188 |
probation | +1.075 |
respectively | +1.074 |
ffect | +1.073 |
Neg logit contributions | |
rons | -3.212 |
liam | -3.136 |
enegger | -2.880 |
oons | -2.687 |
rises | -2.613 |
Token | in |
Token ID | 287 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
rons | +5.871 |
liam | +5.692 |
enegger | +5.099 |
oons | +4.723 |
ries | +4.600 |
Neg logit contributions | |
ciplinary | -3.476 |
CLASSIFIED | -3.308 |
vantage | -3.195 |
ffect | -2.989 |
terday | -2.912 |
Token | the |
Token ID | 262 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
rons | +8.063 |
liam | +7.837 |
enegger | +7.036 |
oons | +6.548 |
ries | +6.280 |
Neg logit contributions | |
ciplinary | -5.114 |
CLASSIFIED | -4.949 |
vantage | -4.754 |
ffect | -4.410 |
terday | -4.386 |
Token | U |
Token ID | 471 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
rons | +2.813 |
liam | +2.733 |
enegger | +2.482 |
oons | +2.294 |
ries | +2.223 |
Neg logit contributions | |
ciplinary | -1.440 |
CLASSIFIED | -1.358 |
vantage | -1.286 |
ffect | -1.221 |
unexplained | -1.189 |
Token | . |
Token ID | 13 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
rons | +4.911 |
liam | +4.750 |
enegger | +4.171 |
oons | +3.875 |
ries | +3.797 |
Neg logit contributions | |
ciplinary | -3.459 |
CLASSIFIED | -3.329 |
vantage | -3.175 |
terday | -3.008 |
unexplained | -2.987 |
Token | N |
Token ID | 45 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
rons | +4.721 |
liam | +4.550 |
enegger | +4.077 |
oons | +3.743 |
ries | +3.617 |
Neg logit contributions | |
ciplinary | -3.400 |
CLASSIFIED | -3.187 |
vantage | -3.116 |
ffect | -2.978 |
terday | -2.929 |
Token | . |
Token ID | 13 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
rons | +3.723 |
liam | +3.611 |
enegger | +3.238 |
oons | +2.983 |
ries | +2.881 |
Neg logit contributions | |
ciplinary | -2.417 |
CLASSIFIED | -2.297 |
vantage | -2.208 |
ffect | -2.101 |
terday | -2.070 |
Token | ar |
Token ID | 283 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
rons | +1.723 |
liam | +1.661 |
enegger | +1.503 |
oons | +1.339 |
rises | +1.289 |
Neg logit contributions | |
ciplinary | -1.385 |
CLASSIFIED | -1.300 |
vantage | -1.263 |
ffect | -1.229 |
respectively | -1.196 |
Token | landscape |
Token ID | 10747 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
ciplinary | +2.448 |
CLASSIFIED | +2.296 |
unexplained | +2.251 |
ffect | +2.230 |
probation | +2.227 |
Neg logit contributions | |
rons | -3.615 |
liam | -3.481 |
enegger | -3.183 |
oons | -2.870 |
rises | -2.738 |
Token | " |
Token ID | 1 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ciplinary | +0.153 |
CLASSIFIED | +0.144 |
vantage | +0.137 |
ffect | +0.135 |
unexplained | +0.134 |
Neg logit contributions | |
rons | -0.294 |
liam | -0.288 |
enegger | -0.262 |
oons | -0.240 |
ries | -0.230 |
Token | after |
Token ID | 706 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
rons | +2.661 |
liam | +2.589 |
enegger | +2.352 |
oons | +2.161 |
ries | +2.085 |
Neg logit contributions | |
ciplinary | -1.456 |
CLASSIFIED | -1.367 |
vantage | -1.299 |
ffect | -1.255 |
unexplained | -1.236 |
Token | a |
Token ID | 257 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
rons | +4.335 |
liam | +4.204 |
enegger | +3.817 |
oons | +3.500 |
ries | +3.378 |
Neg logit contributions | |
ciplinary | -2.481 |
CLASSIFIED | -2.339 |
vantage | -2.219 |
ffect | -2.138 |
unexplained | -2.109 |
Token | fire |
Token ID | 2046 |
Feature activation | +9.81e+00 |
Pos logit contributions | |
rons | +0.490 |
liam | +0.474 |
enegger | +0.431 |
oons | +0.391 |
rises | +0.374 |
Neg logit contributions | |
ciplinary | -0.316 |
CLASSIFIED | -0.294 |
ffect | -0.281 |
vantage | -0.280 |
unexplained | -0.279 |
Token | . |
Token ID | 13 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
rons | +10.584 |
liam | +10.086 |
enegger | +9.016 |
oons | +8.447 |
ries | +8.376 |
Neg logit contributions | |
ciplinary | -6.427 |
CLASSIFIED | -6.301 |
vantage | -5.788 |
ffect | -5.392 |
terday | -5.341 |
Token |
|
Token ID | 198 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ciplinary | +0.540 |
CLASSIFIED | +0.506 |
vantage | +0.490 |
ffect | +0.469 |
respectively | +0.460 |
Neg logit contributions | |
rons | -1.118 |
liam | -1.081 |
enegger | -0.991 |
oons | -0.904 |
rises | -0.881 |
Token |
|
Token ID | 198 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
ciplinary | +0.617 |
CLASSIFIED | +0.578 |
vantage | +0.549 |
ffect | +0.526 |
unexplained | +0.512 |
Neg logit contributions | |
rons | -1.167 |
liam | -1.132 |
enegger | -1.032 |
oons | -0.949 |
rises | -0.918 |
Token | More |
Token ID | 5167 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
rons | +2.964 |
liam | +2.864 |
enegger | +2.604 |
oons | +2.378 |
ries | +2.293 |
Neg logit contributions | |
ciplinary | -1.803 |
CLASSIFIED | -1.714 |
vantage | -1.627 |
ffect | -1.562 |
unexplained | -1.521 |
Token | than |
Token ID | 621 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
rons | +3.281 |
liam | +3.159 |
enegger | +2.789 |
oons | +2.503 |
ries | +2.392 |
Neg logit contributions | |
ciplinary | -3.083 |
CLASSIFIED | -2.956 |
vantage | -2.848 |
ffect | -2.758 |
unexplained | -2.716 |
Token | presidency |
Token ID | 12112 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
rons | +1.093 |
liam | +1.060 |
enegger | +0.958 |
oons | +0.877 |
rises | +0.846 |
Neg logit contributions | |
ciplinary | -0.692 |
CLASSIFIED | -0.645 |
vantage | -0.616 |
ffect | -0.600 |
probation | -0.600 |
Token | , |
Token ID | 11 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
rons | +3.386 |
liam | +3.289 |
enegger | +2.975 |
oons | +2.737 |
ries | +2.642 |
Neg logit contributions | |
ciplinary | -1.943 |
CLASSIFIED | -1.836 |
vantage | -1.751 |
ffect | -1.673 |
unexplained | -1.638 |
Token | given |
Token ID | 1813 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
rons | +0.876 |
liam | +0.851 |
enegger | +0.775 |
oons | +0.719 |
ries | +0.695 |
Neg logit contributions | |
ciplinary | -0.426 |
CLASSIFIED | -0.405 |
vantage | -0.376 |
ffect | -0.362 |
unexplained | -0.359 |
Token | his |
Token ID | 465 |
Feature activation | +9.60e+00 |
Pos logit contributions | |
rons | +7.373 |
liam | +7.163 |
enegger | +6.490 |
oons | +5.994 |
ries | +5.854 |
Neg logit contributions | |
ciplinary | -3.777 |
CLASSIFIED | -3.538 |
vantage | -3.399 |
ffect | -3.196 |
terday | -3.079 |
Token | precarious |
Token ID | 38761 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
rons | +10.901 |
liam | +10.502 |
enegger | +9.593 |
oons | +8.873 |
ries | +8.634 |
Neg logit contributions | |
ciplinary | -5.639 |
CLASSIFIED | -5.416 |
vantage | -5.240 |
ffect | -4.840 |
terday | -4.721 |
Token | public |
Token ID | 1171 |
Feature activation | +8.29e+00 |
Pos logit contributions | |
rons | +4.422 |
liam | +4.282 |
enegger | +3.867 |
oons | +3.551 |
rises | +3.421 |
Neg logit contributions | |
ciplinary | -2.763 |
CLASSIFIED | -2.613 |
vantage | -2.483 |
ffect | -2.389 |
probation | -2.363 |
Token | standing |
Token ID | 5055 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
rons | +8.531 |
liam | +8.252 |
enegger | +7.332 |
oons | +6.731 |
ries | +6.575 |
Neg logit contributions | |
ciplinary | -6.021 |
CLASSIFIED | -5.767 |
vantage | -5.567 |
ffect | -5.329 |
terday | -5.202 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
rons | +7.382 |
liam | +7.146 |
enegger | +6.466 |
oons | +5.940 |
ries | +5.786 |
Neg logit contributions | |
ciplinary | -4.201 |
CLASSIFIED | -3.994 |
vantage | -3.780 |
ffect | -3.617 |
terday | -3.509 |
Token | his |
Token ID | 465 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
ciplinary | +0.701 |
CLASSIFIED | +0.656 |
unexplained | +0.609 |
vantage | +0.602 |
probation | +0.598 |
Neg logit contributions | |
rons | -1.436 |
liam | -1.396 |
enegger | -1.267 |
oons | -1.188 |
rises | -1.139 |
Token | party |
Token ID | 2151 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
rons | +8.414 |
liam | +8.158 |
enegger | +7.435 |
oons | +6.845 |
ries | +6.640 |
Neg logit contributions | |
ciplinary | -4.382 |
CLASSIFIED | -4.169 |
vantage | -4.018 |
ffect | -3.754 |
terday | -3.666 |
Token | � |
Token ID | 447 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
rons | +6.072 |
liam | +5.848 |
enegger | +5.251 |
oons | +4.803 |
ries | +4.656 |
Neg logit contributions | |
ciplinary | -4.054 |
CLASSIFIED | -3.865 |
vantage | -3.678 |
ffect | -3.543 |
terday | -3.487 |
Token | � |
Token ID | 251 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
rons | +1.914 |
liam | +1.841 |
enegger | +1.653 |
oons | +1.506 |
rises | +1.449 |
Neg logit contributions | |
ciplinary | -1.420 |
CLASSIFIED | -1.355 |
vantage | -1.294 |
ffect | -1.251 |
probation | -1.229 |
Token |
|
Token ID | 198 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
rons | +7.016 |
liam | +6.828 |
enegger | +6.161 |
oons | +5.661 |
ries | +5.488 |
Neg logit contributions | |
ciplinary | -4.093 |
CLASSIFIED | -3.860 |
vantage | -3.674 |
ffect | -3.508 |
unexplained | -3.433 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
rons | +0.602 |
liam | +0.585 |
enegger | +0.527 |
oons | +0.487 |
ries | +0.473 |
Neg logit contributions | |
ciplinary | -0.345 |
CLASSIFIED | -0.328 |
vantage | -0.311 |
ffect | -0.295 |
unexplained | -0.290 |
Token | At |
Token ID | 2953 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
rons | +1.359 |
liam | +1.307 |
enegger | +1.200 |
oons | +1.093 |
rises | +1.046 |
Neg logit contributions | |
ciplinary | -0.845 |
CLASSIFIED | -0.815 |
vantage | -0.765 |
ffect | -0.735 |
terday | -0.711 |
Token | the |
Token ID | 262 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
rons | +3.249 |
liam | +3.162 |
enegger | +2.879 |
oons | +2.648 |
rises | +2.559 |
Neg logit contributions | |
ciplinary | -1.731 |
CLASSIFIED | -1.628 |
vantage | -1.549 |
ffect | -1.477 |
unexplained | -1.446 |
Token | same |
Token ID | 976 |
Feature activation | +8.46e+00 |
Pos logit contributions | |
rons | +1.026 |
liam | +0.999 |
enegger | +0.910 |
oons | +0.837 |
rises | +0.812 |
Neg logit contributions | |
ciplinary | -0.542 |
CLASSIFIED | -0.507 |
vantage | -0.479 |
ffect | -0.460 |
unexplained | -0.455 |
Token | time |
Token ID | 640 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
rons | +8.627 |
liam | +8.364 |
enegger | +7.362 |
oons | +6.833 |
ries | +6.693 |
Neg logit contributions | |
ciplinary | -6.052 |
CLASSIFIED | -5.750 |
vantage | -5.607 |
ffect | -5.319 |
respectively | -5.068 |
Token | , |
Token ID | 11 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
rons | +6.149 |
liam | +5.979 |
enegger | +5.382 |
oons | +4.947 |
ries | +4.857 |
Neg logit contributions | |
ciplinary | -3.520 |
CLASSIFIED | -3.305 |
vantage | -3.168 |
ffect | -3.017 |
unexplained | -2.900 |
Token | another |
Token ID | 1194 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
rons | +6.193 |
liam | +6.014 |
enegger | +5.404 |
oons | +4.973 |
ries | +4.835 |
Neg logit contributions | |
ciplinary | -3.694 |
CLASSIFIED | -3.497 |
vantage | -3.345 |
ffect | -3.194 |
terday | -3.098 |
Token | official |
Token ID | 1743 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
rons | +3.649 |
liam | +3.540 |
enegger | +3.191 |
oons | +2.932 |
ries | +2.837 |
Neg logit contributions | |
ciplinary | -2.210 |
CLASSIFIED | -2.099 |
vantage | -2.001 |
ffect | -1.908 |
unexplained | -1.863 |
Token | added |
Token ID | 2087 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
rons | +2.001 |
liam | +1.938 |
enegger | +1.744 |
oons | +1.597 |
rises | +1.532 |
Neg logit contributions | |
ciplinary | -1.396 |
CLASSIFIED | -1.315 |
vantage | -1.259 |
ffect | -1.215 |
unexplained | -1.204 |
Token | or |
Token ID | 393 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
rons | +0.074 |
liam | +0.073 |
enegger | +0.067 |
oons | +0.061 |
rises | +0.059 |
Neg logit contributions | |
ciplinary | -0.037 |
CLASSIFIED | -0.034 |
vantage | -0.033 |
ffect | -0.032 |
respectively | -0.032 |
Token | directly |
Token ID | 3264 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
rons | +1.030 |
liam | +1.003 |
enegger | +0.916 |
oons | +0.833 |
rises | +0.805 |
Neg logit contributions | |
ciplinary | -0.632 |
CLASSIFIED | -0.589 |
vantage | -0.568 |
ffect | -0.550 |
probation | -0.548 |
Token | to |
Token ID | 284 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
rons | +3.586 |
liam | +3.483 |
enegger | +3.165 |
oons | +2.901 |
rises | +2.800 |
Neg logit contributions | |
ciplinary | -2.073 |
CLASSIFIED | -1.949 |
vantage | -1.861 |
ffect | -1.786 |
probation | -1.751 |
Token | individuals |
Token ID | 3925 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
rons | +3.423 |
liam | +3.320 |
enegger | +3.001 |
oons | +2.759 |
ries | +2.665 |
Neg logit contributions | |
ciplinary | -2.018 |
CLASSIFIED | -1.911 |
vantage | -1.818 |
ffect | -1.739 |
unexplained | -1.702 |
Token | ," |
Token ID | 553 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
rons | +2.173 |
liam | +2.112 |
enegger | +1.923 |
oons | +1.773 |
rises | +1.713 |
Neg logit contributions | |
ciplinary | -1.129 |
CLASSIFIED | -1.060 |
vantage | -1.008 |
ffect | -0.963 |
unexplained | -0.941 |
Token | as |
Token ID | 355 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
rons | +0.545 |
liam | +0.529 |
enegger | +0.479 |
oons | +0.438 |
rises | +0.423 |
Neg logit contributions | |
ciplinary | -0.343 |
CLASSIFIED | -0.328 |
vantage | -0.310 |
respectively | -0.304 |
ffect | -0.302 |
Token | the |
Token ID | 262 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
rons | +1.494 |
liam | +1.452 |
enegger | +1.319 |
oons | +1.207 |
rises | +1.166 |
Neg logit contributions | |
ciplinary | -0.884 |
CLASSIFIED | -0.839 |
vantage | -0.796 |
ffect | -0.776 |
unexplained | -0.765 |
Token | Huffington |
Token ID | 23807 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ciplinary | +1.135 |
CLASSIFIED | +1.070 |
vantage | +1.016 |
ffect | +1.010 |
probation | +1.001 |
Neg logit contributions | |
rons | -1.833 |
liam | -1.791 |
enegger | -1.636 |
oons | -1.473 |
rises | -1.431 |
Token | Post |
Token ID | 2947 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
rons | +0.133 |
liam | +0.128 |
enegger | +0.114 |
oons | +0.103 |
ries | +0.099 |
Neg logit contributions | |
ciplinary | -0.113 |
CLASSIFIED | -0.109 |
vantage | -0.104 |
ffect | -0.101 |
unexplained | -0.099 |
Token | explained |
Token ID | 4893 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
ciplinary | +0.294 |
CLASSIFIED | +0.279 |
vantage | +0.267 |
ffect | +0.257 |
unexplained | +0.255 |
Neg logit contributions | |
rons | -0.436 |
liam | -0.422 |
enegger | -0.379 |
oons | -0.347 |
rises | -0.333 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
rons | +0.913 |
liam | +0.890 |
enegger | +0.807 |
oons | +0.741 |
rises | +0.718 |
Neg logit contributions | |
ciplinary | -0.505 |
CLASSIFIED | -0.477 |
vantage | -0.454 |
ffect | -0.434 |
terday | -0.433 |
Token | them |
Token ID | 606 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
rons | +1.515 |
liam | +1.474 |
enegger | +1.348 |
oons | +1.240 |
rises | +1.200 |
Neg logit contributions | |
ciplinary | -0.737 |
CLASSIFIED | -0.692 |
vantage | -0.656 |
ffect | -0.624 |
unexplained | -0.613 |
Token | to |
Token ID | 284 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
rons | +3.367 |
liam | +3.259 |
enegger | +2.968 |
oons | +2.749 |
ries | +2.674 |
Neg logit contributions | |
ciplinary | -1.639 |
CLASSIFIED | -1.542 |
vantage | -1.454 |
ffect | -1.389 |
unexplained | -1.340 |
Token | ren |
Token ID | 8851 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
rons | +3.937 |
liam | +3.813 |
enegger | +3.427 |
oons | +3.148 |
ries | +3.041 |
Neg logit contributions | |
ciplinary | -2.521 |
CLASSIFIED | -2.414 |
vantage | -2.291 |
ffect | -2.186 |
unexplained | -2.138 |
Token | ounce |
Token ID | 8652 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
ciplinary | +0.107 |
CLASSIFIED | +0.102 |
vantage | +0.100 |
ffect | +0.097 |
respectively | +0.095 |
Neg logit contributions | |
rons | -0.107 |
liam | -0.102 |
enegger | -0.091 |
oons | -0.080 |
ries | -0.077 |
Token | them |
Token ID | 606 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ciplinary | +0.348 |
CLASSIFIED | +0.331 |
vantage | +0.315 |
ffect | +0.301 |
probation | +0.300 |
Neg logit contributions | |
rons | -0.619 |
liam | -0.602 |
enegger | -0.549 |
oons | -0.501 |
rises | -0.486 |
Token | immediately |
Token ID | 3393 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
rons | +1.821 |
liam | +1.771 |
enegger | +1.610 |
oons | +1.483 |
rises | +1.432 |
Neg logit contributions | |
ciplinary | -0.974 |
CLASSIFIED | -0.917 |
vantage | -0.874 |
ffect | -0.833 |
unexplained | -0.820 |
Token | as |
Token ID | 355 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
rons | +1.515 |
liam | +1.476 |
enegger | +1.341 |
oons | +1.236 |
ries | +1.194 |
Neg logit contributions | |
ciplinary | -0.789 |
CLASSIFIED | -0.742 |
vantage | -0.709 |
ffect | -0.676 |
respectively | -0.669 |
Token | well |
Token ID | 880 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
rons | +2.521 |
liam | +2.448 |
enegger | +2.231 |
oons | +2.056 |
rises | +1.991 |
Neg logit contributions | |
ciplinary | -1.264 |
CLASSIFIED | -1.188 |
vantage | -1.123 |
ffect | -1.071 |
unexplained | -1.053 |
Token | , |
Token ID | 11 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
rons | +4.479 |
liam | +4.335 |
enegger | +3.933 |
oons | +3.618 |
ries | +3.506 |
Neg logit contributions | |
ciplinary | -2.538 |
CLASSIFIED | -2.404 |
vantage | -2.273 |
ffect | -2.171 |
unexplained | -2.113 |
Token | given |
Token ID | 1813 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
ciplinary | +0.055 |
CLASSIFIED | +0.052 |
vantage | +0.049 |
respectively | +0.047 |
ffect | +0.047 |
Neg logit contributions | |
rons | -0.107 |
liam | -0.105 |
enegger | -0.095 |
oons | -0.088 |
rises | -0.085 |
Token | that |
Token ID | 326 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
rons | +5.920 |
liam | +5.738 |
enegger | +5.176 |
oons | +4.794 |
ries | +4.673 |
Neg logit contributions | |
ciplinary | -3.271 |
CLASSIFIED | -3.086 |
vantage | -2.938 |
ffect | -2.782 |
terday | -2.680 |
Token | with |
Token ID | 351 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
ciplinary | +0.858 |
CLASSIFIED | +0.813 |
respectively | +0.753 |
vantage | +0.749 |
probation | +0.746 |
Neg logit contributions | |
rons | -1.722 |
liam | -1.686 |
enegger | -1.544 |
oons | -1.420 |
rises | -1.359 |
Token | JPMorgan |
Token ID | 43318 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
ciplinary | +2.242 |
CLASSIFIED | +2.103 |
vantage | +2.070 |
probation | +1.995 |
unexplained | +1.979 |
Neg logit contributions | |
rons | -3.813 |
liam | -3.751 |
enegger | -3.404 |
oons | -3.102 |
rises | -3.000 |
Token | who |
Token ID | 508 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ciplinary | +1.353 |
CLASSIFIED | +1.279 |
vantage | +1.212 |
respectively | +1.179 |
unexplained | +1.167 |
Neg logit contributions | |
rons | -2.464 |
liam | -2.405 |
enegger | -2.185 |
oons | -2.001 |
rises | -1.948 |
Token | specializes |
Token ID | 29786 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
ciplinary | +0.888 |
CLASSIFIED | +0.793 |
vantage | +0.766 |
respectively | +0.765 |
unexplained | +0.753 |
Neg logit contributions | |
rons | -1.735 |
liam | -1.700 |
enegger | -1.550 |
oons | -1.434 |
rises | -1.376 |
Token | in |
Token ID | 287 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
ciplinary | +2.786 |
CLASSIFIED | +2.447 |
vantage | +2.406 |
probation | +2.405 |
respectively | +2.400 |
Neg logit contributions | |
rons | -4.998 |
liam | -4.850 |
enegger | -4.469 |
oons | -4.080 |
rises | -3.986 |
Token | big |
Token ID | 1263 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ciplinary | +2.101 |
CLASSIFIED | +1.955 |
unexplained | +1.926 |
probation | +1.897 |
vantage | +1.896 |
Neg logit contributions | |
rons | -2.858 |
liam | -2.761 |
enegger | -2.514 |
oons | -2.248 |
rises | -2.149 |
Token | energy |
Token ID | 2568 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
rons | +1.430 |
liam | +1.378 |
enegger | +1.242 |
oons | +1.120 |
ries | +1.075 |
Neg logit contributions | |
ciplinary | -1.076 |
CLASSIFIED | -1.021 |
vantage | -0.983 |
unexplained | -0.953 |
ffect | -0.947 |
Token | deals |
Token ID | 7529 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
rons | +1.645 |
liam | +1.593 |
enegger | +1.431 |
oons | +1.295 |
ries | +1.239 |
Neg logit contributions | |
ciplinary | -1.233 |
CLASSIFIED | -1.175 |
vantage | -1.123 |
ffect | -1.084 |
unexplained | -1.074 |
Token | . |
Token ID | 13 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
rons | +0.925 |
liam | +0.900 |
enegger | +0.814 |
oons | +0.750 |
rises | +0.723 |
Neg logit contributions | |
ciplinary | -0.504 |
CLASSIFIED | -0.471 |
vantage | -0.450 |
ffect | -0.432 |
respectively | -0.428 |
Token | " |
Token ID | 366 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
ciplinary | +0.132 |
CLASSIFIED | +0.129 |
vantage | +0.123 |
ffect | +0.116 |
respectively | +0.115 |
Neg logit contributions | |
rons | -0.254 |
liam | -0.246 |
enegger | -0.224 |
oons | -0.206 |
rises | -0.199 |
Token | The |
Token ID | 464 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
rons | +4.725 |
liam | +4.588 |
enegger | +4.085 |
oons | +3.744 |
ries | +3.611 |
Neg logit contributions | |
ciplinary | -3.356 |
CLASSIFIED | -3.168 |
vantage | -3.039 |
ffect | -2.919 |
unexplained | -2.883 |
Token | they |
Token ID | 484 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
rons | +1.587 |
liam | +1.539 |
enegger | +1.400 |
oons | +1.281 |
ries | +1.232 |
Neg logit contributions | |
ciplinary | -0.934 |
CLASSIFIED | -0.883 |
vantage | -0.837 |
ffect | -0.808 |
unexplained | -0.799 |
Token | 're |
Token ID | 821 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
rons | +1.741 |
liam | +1.688 |
enegger | +1.520 |
oons | +1.392 |
ries | +1.337 |
Neg logit contributions | |
ciplinary | -1.157 |
CLASSIFIED | -1.087 |
vantage | -1.047 |
ffect | -1.009 |
probation | -0.993 |
Token | working |
Token ID | 1762 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
rons | +0.763 |
liam | +0.742 |
enegger | +0.673 |
oons | +0.625 |
rises | +0.599 |
Neg logit contributions | |
ciplinary | -0.401 |
CLASSIFIED | -0.374 |
vantage | -0.350 |
respectively | -0.342 |
unexplained | -0.342 |
Token | in |
Token ID | 287 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
rons | +2.641 |
liam | +2.563 |
enegger | +2.314 |
oons | +2.130 |
rises | +2.041 |
Neg logit contributions | |
ciplinary | -1.597 |
CLASSIFIED | -1.507 |
vantage | -1.440 |
ffect | -1.386 |
probation | -1.366 |
Token | ." |
Token ID | 526 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
rons | +2.268 |
liam | +2.205 |
enegger | +1.982 |
oons | +1.812 |
ries | +1.741 |
Neg logit contributions | |
ciplinary | -1.478 |
CLASSIFIED | -1.399 |
vantage | -1.340 |
ffect | -1.291 |
unexplained | -1.275 |
Token | Vel |
Token ID | 17378 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
rons | +1.480 |
liam | +1.437 |
enegger | +1.303 |
oons | +1.200 |
ries | +1.161 |
Neg logit contributions | |
ciplinary | -0.813 |
CLASSIFIED | -0.768 |
vantage | -0.729 |
ffect | -0.695 |
unexplained | -0.680 |
Token | ie |
Token ID | 494 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
rons | +0.879 |
liam | +0.841 |
enegger | +0.708 |
oons | +0.613 |
ries | +0.578 |
Neg logit contributions | |
ciplinary | -1.319 |
CLASSIFIED | -1.288 |
vantage | -1.238 |
ffect | -1.206 |
unexplained | -1.196 |
Token | said |
Token ID | 531 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
rons | +0.444 |
liam | +0.432 |
enegger | +0.388 |
oons | +0.357 |
rises | +0.342 |
Neg logit contributions | |
ciplinary | -0.280 |
CLASSIFIED | -0.256 |
vantage | -0.250 |
ffect | -0.244 |
respectively | -0.241 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
rons | +5.396 |
liam | +5.218 |
enegger | +4.701 |
oons | +4.336 |
ries | +4.210 |
Neg logit contributions | |
ciplinary | -3.240 |
CLASSIFIED | -3.078 |
vantage | -2.944 |
ffect | -2.781 |
terday | -2.704 |
Token |
|
Token ID | 198 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
ciplinary | +1.297 |
CLASSIFIED | +1.223 |
vantage | +1.166 |
ffect | +1.118 |
unexplained | +1.092 |
Neg logit contributions | |
rons | -2.611 |
liam | -2.525 |
enegger | -2.304 |
oons | -2.127 |
rises | -2.058 |
Token |
|
Token ID | 198 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ciplinary | +0.210 |
CLASSIFIED | +0.198 |
vantage | +0.188 |
ffect | +0.180 |
unexplained | +0.176 |
Neg logit contributions | |
rons | -0.388 |
liam | -0.376 |
enegger | -0.342 |
oons | -0.315 |
ries | -0.304 |
Token | Summit |
Token ID | 20014 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
rons | +2.150 |
liam | +2.084 |
enegger | +1.877 |
oons | +1.709 |
ries | +1.647 |
Neg logit contributions | |
ciplinary | -1.477 |
CLASSIFIED | -1.397 |
vantage | -1.341 |
ffect | -1.289 |
probation | -1.266 |
Token | April |
Token ID | 3035 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
rons | +6.511 |
liam | +6.282 |
enegger | +5.656 |
oons | +5.199 |
ries | +5.042 |
Neg logit contributions | |
ciplinary | -4.067 |
CLASSIFIED | -3.887 |
vantage | -3.695 |
ffect | -3.542 |
unexplained | -3.449 |
Token | 18 |
Token ID | 1248 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
rons | +3.857 |
liam | +3.745 |
enegger | +3.300 |
oons | +3.070 |
ries | +2.999 |
Neg logit contributions | |
ciplinary | -2.730 |
CLASSIFIED | -2.666 |
vantage | -2.515 |
ffect | -2.388 |
terday | -2.338 |
Token | , |
Token ID | 11 |
Feature activation | +8.74e+00 |
Pos logit contributions | |
rons | +5.226 |
liam | +5.072 |
enegger | +4.584 |
oons | +4.215 |
ries | +4.104 |
Neg logit contributions | |
ciplinary | -2.927 |
CLASSIFIED | -2.833 |
vantage | -2.642 |
ffect | -2.541 |
terday | -2.462 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
rons | +7.234 |
liam | +6.910 |
enegger | +6.043 |
oons | +5.308 |
ries | +5.145 |
Neg logit contributions | |
ciplinary | -7.980 |
CLASSIFIED | -7.849 |
vantage | -7.376 |
ffect | -7.319 |
terday | -7.076 |
Token | , |
Token ID | 11 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
rons | +6.220 |
liam | +6.021 |
enegger | +5.461 |
oons | +5.012 |
ries | +4.873 |
Neg logit contributions | |
ciplinary | -3.493 |
CLASSIFIED | -3.337 |
vantage | -3.139 |
ffect | -3.010 |
unexplained | -2.930 |
Token | in |
Token ID | 287 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
rons | +6.359 |
liam | +6.121 |
enegger | +5.497 |
oons | +5.021 |
ries | +4.856 |
Neg logit contributions | |
ciplinary | -4.327 |
CLASSIFIED | -4.146 |
vantage | -3.928 |
ffect | -3.782 |
unexplained | -3.683 |
Token | Nash |
Token ID | 13950 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
rons | +7.949 |
liam | +7.681 |
enegger | +6.878 |
oons | +6.340 |
ries | +6.140 |
Neg logit contributions | |
ciplinary | -5.154 |
CLASSIFIED | -4.977 |
vantage | -4.642 |
ffect | -4.454 |
terday | -4.331 |
Token | ua |
Token ID | 6413 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
rons | +2.486 |
liam | +2.369 |
enegger | +1.973 |
oons | +1.743 |
ries | +1.616 |
Neg logit contributions | |
ciplinary | -4.010 |
CLASSIFIED | -3.942 |
vantage | -3.749 |
ffect | -3.680 |
terday | -3.666 |
Token | , |
Token ID | 11 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
ciplinary | +1.334 |
CLASSIFIED | +1.218 |
vantage | +1.177 |
respectively | +1.135 |
ffect | +1.110 |
Neg logit contributions | |
rons | -3.312 |
liam | -3.201 |
enegger | -2.927 |
oons | -2.695 |
rises | -2.662 |
Token | New |
Token ID | 968 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
rons | +3.656 |
liam | +3.554 |
enegger | +3.225 |
oons | +2.975 |
ries | +2.885 |
Neg logit contributions | |
ciplinary | -1.936 |
CLASSIFIED | -1.823 |
vantage | -1.730 |
ffect | -1.645 |
terday | -1.603 |
Token | al |
Token ID | 282 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
rons | +2.996 |
liam | +2.893 |
enegger | +2.594 |
oons | +2.353 |
ries | +2.261 |
Neg logit contributions | |
ciplinary | -2.272 |
CLASSIFIED | -2.162 |
vantage | -2.079 |
ffect | -2.001 |
unexplained | -1.965 |
Token | ise |
Token ID | 786 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
rons | +1.371 |
liam | +1.307 |
enegger | +1.075 |
oons | +0.924 |
ries | +0.869 |
Neg logit contributions | |
ciplinary | -2.330 |
CLASSIFIED | -2.285 |
vantage | -2.188 |
ffect | -2.135 |
unexplained | -2.121 |
Token | — |
Token ID | 851 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
rons | +2.517 |
liam | +2.442 |
enegger | +2.213 |
oons | +2.037 |
rises | +1.966 |
Neg logit contributions | |
ciplinary | -1.431 |
CLASSIFIED | -1.353 |
vantage | -1.282 |
ffect | -1.227 |
unexplained | -1.212 |
Token | crimes |
Token ID | 6741 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
rons | +1.991 |
liam | +1.934 |
enegger | +1.760 |
oons | +1.626 |
ries | +1.575 |
Neg logit contributions | |
ciplinary | -0.989 |
CLASSIFIED | -0.931 |
vantage | -0.879 |
ffect | -0.836 |
unexplained | -0.818 |
Token | she |
Token ID | 673 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
ciplinary | +3.998 |
CLASSIFIED | +3.874 |
unexplained | +3.713 |
probation | +3.639 |
intentional | +3.604 |
Neg logit contributions | |
rons | -7.551 |
liam | -7.428 |
enegger | -6.969 |
oons | -6.200 |
rises | -6.093 |
Token | did |
Token ID | 750 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
rons | +3.169 |
liam | +3.078 |
enegger | +2.797 |
oons | +2.584 |
ries | +2.499 |
Neg logit contributions | |
ciplinary | -1.628 |
CLASSIFIED | -1.531 |
vantage | -1.451 |
ffect | -1.381 |
unexplained | -1.350 |
Token | not |
Token ID | 407 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ciplinary | +0.832 |
CLASSIFIED | +0.786 |
vantage | +0.725 |
probation | +0.721 |
unexplained | +0.705 |
Neg logit contributions | |
rons | -1.824 |
liam | -1.781 |
enegger | -1.621 |
oons | -1.509 |
rises | -1.464 |
Token | commit |
Token ID | 4589 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
rons | +2.096 |
liam | +2.045 |
enegger | +1.871 |
oons | +1.734 |
ries | +1.681 |
Neg logit contributions | |
ciplinary | -0.899 |
CLASSIFIED | -0.829 |
vantage | -0.782 |
ffect | -0.747 |
probation | -0.733 |
Token | ? |
Token ID | 30 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
ciplinary | +2.372 |
CLASSIFIED | +2.220 |
probation | +2.122 |
respectively | +2.099 |
vantage | +2.077 |
Neg logit contributions | |
rons | -4.734 |
liam | -4.672 |
enegger | -4.188 |
oons | -3.872 |
rises | -3.772 |
Token | Are |
Token ID | 4231 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
ciplinary | +0.429 |
CLASSIFIED | +0.416 |
vantage | +0.392 |
ffect | +0.375 |
respectively | +0.373 |
Neg logit contributions | |
rons | -0.921 |
liam | -0.888 |
enegger | -0.814 |
oons | -0.745 |
rises | -0.727 |
Token | they |
Token ID | 484 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
rons | +1.027 |
liam | +0.994 |
enegger | +0.907 |
oons | +0.822 |
rises | +0.793 |
Neg logit contributions | |
ciplinary | -0.650 |
CLASSIFIED | -0.621 |
vantage | -0.582 |
probation | -0.570 |
unexplained | -0.567 |
Token | to |
Token ID | 284 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
ciplinary | +3.159 |
probation | +2.781 |
CLASSIFIED | +2.675 |
unexplained | +2.618 |
respectively | +2.586 |
Neg logit contributions | |
rons | -8.074 |
liam | -7.859 |
enegger | -7.314 |
oons | -6.817 |
rises | -6.558 |
Token | the |
Token ID | 262 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
ciplinary | +2.641 |
probation | +2.376 |
CLASSIFIED | +2.368 |
vantage | +2.293 |
ffect | +2.203 |
Neg logit contributions | |
rons | -5.696 |
liam | -5.545 |
enegger | -5.146 |
oons | -4.662 |
rises | -4.575 |
Token | jail |
Token ID | 7356 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
ciplinary | +3.087 |
probation | +2.811 |
CLASSIFIED | +2.692 |
unexplained | +2.626 |
ffect | +2.622 |
Neg logit contributions | |
rons | -6.381 |
liam | -6.250 |
enegger | -5.814 |
oons | -5.191 |
rises | -5.156 |
Token | drunk |
Token ID | 10785 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
rons | +1.853 |
liam | +1.802 |
enegger | +1.637 |
oons | +1.503 |
rises | +1.450 |
Neg logit contributions | |
ciplinary | -1.034 |
CLASSIFIED | -0.971 |
vantage | -0.922 |
ffect | -0.887 |
probation | -0.873 |
Token | after |
Token ID | 706 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ciplinary | +0.496 |
CLASSIFIED | +0.461 |
vantage | +0.442 |
ffect | +0.422 |
probation | +0.415 |
Neg logit contributions | |
rons | -1.101 |
liam | -1.074 |
enegger | -0.981 |
oons | -0.906 |
rises | -0.883 |
Token | resisting |
Token ID | 28943 |
Feature activation | -7.35e+00 |
Pos logit contributions | |
rons | +2.410 |
liam | +2.339 |
enegger | +2.120 |
oons | +1.946 |
rises | +1.877 |
Neg logit contributions | |
ciplinary | -1.444 |
CLASSIFIED | -1.355 |
vantage | -1.284 |
ffect | -1.241 |
probation | -1.239 |
Token | arrest |
Token ID | 3251 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
ciplinary | +3.080 |
probation | +2.833 |
CLASSIFIED | +2.684 |
unexplained | +2.636 |
respectively | +2.463 |
Neg logit contributions | |
rons | -9.520 |
liam | -9.511 |
enegger | -8.711 |
oons | -8.035 |
rises | -7.812 |
Token | following |
Token ID | 1708 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
rons | +2.370 |
liam | +2.302 |
enegger | +2.090 |
oons | +1.927 |
ries | +1.863 |
Neg logit contributions | |
ciplinary | -1.260 |
CLASSIFIED | -1.188 |
vantage | -1.126 |
ffect | -1.074 |
unexplained | -1.051 |
Token | an |
Token ID | 281 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ciplinary | +1.850 |
CLASSIFIED | +1.656 |
probation | +1.640 |
unexplained | +1.608 |
vantage | +1.555 |
Neg logit contributions | |
rons | -3.795 |
liam | -3.716 |
enegger | -3.383 |
oons | -3.128 |
rises | -3.008 |
Token | incident |
Token ID | 4519 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ciplinary | +0.846 |
CLASSIFIED | +0.771 |
vantage | +0.724 |
unexplained | +0.704 |
probation | +0.694 |
Neg logit contributions | |
rons | -2.057 |
liam | -2.016 |
enegger | -1.847 |
oons | -1.705 |
rises | -1.662 |
Token | at |
Token ID | 379 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
rons | +1.777 |
liam | +1.729 |
enegger | +1.563 |
oons | +1.433 |
rises | +1.383 |
Neg logit contributions | |
ciplinary | -1.063 |
CLASSIFIED | -1.005 |
vantage | -0.955 |
ffect | -0.918 |
unexplained | -0.905 |
Token | one |
Token ID | 530 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ciplinary | +2.847 |
CLASSIFIED | +2.602 |
unexplained | +2.527 |
vantage | +2.526 |
probation | +2.524 |
Neg logit contributions | |
rons | -4.726 |
liam | -4.652 |
enegger | -4.241 |
oons | -3.796 |
rises | -3.658 |
Token | used |
Token ID | 973 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
ciplinary | +0.650 |
CLASSIFIED | +0.601 |
vantage | +0.569 |
ffect | +0.558 |
unexplained | +0.552 |
Neg logit contributions | |
rons | -1.209 |
liam | -1.178 |
enegger | -1.080 |
oons | -0.992 |
rises | -0.954 |
Token | for |
Token ID | 329 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
rons | +0.497 |
liam | +0.484 |
enegger | +0.440 |
oons | +0.405 |
rises | +0.391 |
Neg logit contributions | |
ciplinary | -0.269 |
CLASSIFIED | -0.251 |
vantage | -0.239 |
ffect | -0.229 |
probation | -0.226 |
Token | Arizona |
Token ID | 7943 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
ciplinary | +3.745 |
CLASSIFIED | +3.413 |
probation | +3.291 |
unexplained | +3.247 |
intentional | +3.244 |
Neg logit contributions | |
rons | -6.519 |
liam | -6.372 |
enegger | -5.865 |
oons | -5.326 |
rises | -5.074 |
Token | League |
Token ID | 4041 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
ciplinary | +2.836 |
CLASSIFIED | +2.635 |
vantage | +2.495 |
probation | +2.450 |
respectively | +2.423 |
Neg logit contributions | |
rons | -5.101 |
liam | -5.037 |
enegger | -4.646 |
oons | -4.169 |
rises | -4.011 |
Token | games |
Token ID | 1830 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ciplinary | +4.669 |
CLASSIFIED | +4.308 |
vantage | +4.161 |
probation | +4.086 |
intentional | +3.933 |
Neg logit contributions | |
rons | -7.864 |
liam | -7.698 |
enegger | -7.143 |
oons | -6.297 |
rises | -6.182 |
Token | is |
Token ID | 318 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
ciplinary | +1.059 |
CLASSIFIED | +0.976 |
vantage | +0.934 |
respectively | +0.884 |
unexplained | +0.881 |
Neg logit contributions | |
rons | -2.171 |
liam | -2.118 |
enegger | -1.936 |
oons | -1.785 |
rises | -1.721 |
Token | lit |
Token ID | 6578 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
ciplinary | +0.303 |
CLASSIFIED | +0.282 |
vantage | +0.267 |
unexplained | +0.257 |
ffect | +0.256 |
Neg logit contributions | |
rons | -0.549 |
liam | -0.536 |
enegger | -0.488 |
oons | -0.449 |
rises | -0.434 |
Token | , |
Token ID | 11 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
rons | +4.111 |
liam | +4.002 |
enegger | +3.655 |
oons | +3.375 |
rises | +3.263 |
Neg logit contributions | |
ciplinary | -1.977 |
CLASSIFIED | -1.848 |
vantage | -1.755 |
ffect | -1.662 |
unexplained | -1.623 |
Token | but |
Token ID | 475 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
rons | +4.625 |
liam | +4.488 |
enegger | +4.065 |
oons | +3.747 |
ries | +3.623 |
Neg logit contributions | |
ciplinary | -2.552 |
CLASSIFIED | -2.411 |
vantage | -2.290 |
ffect | -2.184 |
unexplained | -2.132 |
Token | not |
Token ID | 407 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
rons | +0.014 |
liam | +0.014 |
enegger | +0.012 |
oons | +0.011 |
rises | +0.011 |
Neg logit contributions | |
ciplinary | -0.007 |
CLASSIFIED | -0.007 |
vantage | -0.006 |
unexplained | -0.006 |
ffect | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
ciplinary | +0.191 |
CLASSIFIED | +0.181 |
vantage | +0.172 |
respectively | +0.167 |
ffect | +0.167 |
Neg logit contributions | |
rons | -0.340 |
liam | -0.333 |
enegger | -0.303 |
oons | -0.277 |
rises | -0.267 |
Token | which |
Token ID | 543 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
ciplinary | +1.353 |
CLASSIFIED | +1.282 |
respectively | +1.244 |
vantage | +1.211 |
ffect | +1.178 |
Neg logit contributions | |
rons | -2.818 |
liam | -2.762 |
enegger | -2.526 |
oons | -2.319 |
rises | -2.267 |
Token | are |
Token ID | 389 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
ciplinary | +1.527 |
CLASSIFIED | +1.394 |
respectively | +1.365 |
vantage | +1.337 |
ffect | +1.304 |
Neg logit contributions | |
rons | -3.488 |
liam | -3.413 |
enegger | -3.132 |
oons | -2.893 |
rises | -2.820 |
Token | par |
Token ID | 1582 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
ciplinary | +2.320 |
CLASSIFIED | +2.158 |
respectively | +2.107 |
ffect | +2.044 |
intentional | +2.036 |
Neg logit contributions | |
rons | -4.116 |
liam | -4.067 |
enegger | -3.674 |
oons | -3.383 |
rises | -3.302 |
Token | av |
Token ID | 615 |
Feature activation | +8.74e+00 |
Pos logit contributions | |
ciplinary | +0.659 |
CLASSIFIED | +0.619 |
vantage | +0.616 |
ffect | +0.594 |
respectively | +0.581 |
Neg logit contributions | |
rons | -0.851 |
liam | -0.818 |
enegger | -0.743 |
oons | -0.666 |
rises | -0.635 |
Token | irt |
Token ID | 2265 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
rons | +7.227 |
liam | +6.965 |
enegger | +5.920 |
oons | +5.448 |
ries | +5.164 |
Neg logit contributions | |
ciplinary | -8.071 |
CLASSIFIED | -7.966 |
vantage | -7.367 |
unexplained | -7.245 |
ffect | -7.211 |
Token | drivers |
Token ID | 6643 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
ciplinary | +0.806 |
CLASSIFIED | +0.766 |
vantage | +0.728 |
respectively | +0.721 |
ffect | +0.718 |
Neg logit contributions | |
rons | -1.166 |
liam | -1.150 |
enegger | -1.028 |
oons | -0.934 |
rises | -0.911 |
Token | that |
Token ID | 326 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ciplinary | +2.895 |
respectively | +2.698 |
CLASSIFIED | +2.578 |
ffect | +2.537 |
vantage | +2.536 |
Neg logit contributions | |
rons | -6.498 |
liam | -6.410 |
enegger | -5.827 |
oons | -5.407 |
rises | -5.277 |
Token | use |
Token ID | 779 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ciplinary | +1.007 |
CLASSIFIED | +0.929 |
respectively | +0.892 |
vantage | +0.886 |
ffect | +0.871 |
Neg logit contributions | |
rons | -2.056 |
liam | -2.015 |
enegger | -1.848 |
oons | -1.697 |
rises | -1.643 |
Token | H |
Token ID | 367 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
ciplinary | +0.842 |
CLASSIFIED | +0.800 |
vantage | +0.763 |
respectively | +0.754 |
probation | +0.747 |
Neg logit contributions | |
rons | -1.387 |
liam | -1.354 |
enegger | -1.222 |
oons | -1.125 |
rises | -1.085 |
Token | VM |
Token ID | 15996 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
rons | +0.614 |
liam | +0.598 |
enegger | +0.548 |
oons | +0.504 |
rises | +0.488 |
Neg logit contributions | |
ciplinary | -0.291 |
CLASSIFIED | -0.274 |
vantage | -0.261 |
ffect | -0.250 |
respectively | -0.245 |
Token | your |
Token ID | 534 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
rons | +5.919 |
liam | +5.725 |
enegger | +5.166 |
oons | +4.753 |
ries | +4.599 |
Neg logit contributions | |
ciplinary | -3.563 |
CLASSIFIED | -3.358 |
vantage | -3.202 |
ffect | -3.054 |
unexplained | -2.990 |
Token | parents |
Token ID | 3397 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
rons | +2.945 |
liam | +2.854 |
enegger | +2.575 |
oons | +2.362 |
ries | +2.280 |
Neg logit contributions | |
ciplinary | -1.827 |
CLASSIFIED | -1.733 |
vantage | -1.651 |
ffect | -1.582 |
unexplained | -1.550 |
Token | get |
Token ID | 651 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
ciplinary | +3.655 |
respectively | +3.330 |
probation | +3.294 |
CLASSIFIED | +3.252 |
ffect | +3.242 |
Neg logit contributions | |
rons | -5.969 |
liam | -5.823 |
enegger | -5.363 |
oons | -4.823 |
rises | -4.667 |
Token | your |
Token ID | 534 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ciplinary | +2.542 |
CLASSIFIED | +2.328 |
probation | +2.266 |
respectively | +2.257 |
unexplained | +2.206 |
Neg logit contributions | |
rons | -6.706 |
liam | -6.612 |
enegger | -6.210 |
oons | -5.677 |
rises | -5.460 |
Token | love |
Token ID | 1842 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
ciplinary | +1.059 |
CLASSIFIED | +1.017 |
vantage | +0.953 |
probation | +0.948 |
unexplained | +0.941 |
Neg logit contributions | |
rons | -1.725 |
liam | -1.693 |
enegger | -1.520 |
oons | -1.391 |
rises | -1.346 |
Token | for |
Token ID | 329 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
rons | +2.380 |
liam | +2.305 |
enegger | +2.068 |
oons | +1.884 |
ries | +1.811 |
Neg logit contributions | |
ciplinary | -1.693 |
CLASSIFIED | -1.616 |
vantage | -1.544 |
ffect | -1.487 |
unexplained | -1.462 |
Token | Star |
Token ID | 2907 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ciplinary | +2.952 |
CLASSIFIED | +2.777 |
unexplained | +2.627 |
vantage | +2.618 |
ffect | +2.565 |
Neg logit contributions | |
rons | -5.911 |
liam | -5.798 |
enegger | -5.331 |
oons | -4.791 |
rises | -4.687 |
Token | Wars |
Token ID | 6176 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
ciplinary | +1.878 |
CLASSIFIED | +1.768 |
vantage | +1.707 |
ffect | +1.645 |
unexplained | +1.609 |
Neg logit contributions | |
rons | -2.754 |
liam | -2.699 |
enegger | -2.454 |
oons | -2.206 |
ries | -2.111 |
Token | ? |
Token ID | 30 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
rons | +0.800 |
liam | +0.776 |
enegger | +0.702 |
oons | +0.646 |
ries | +0.624 |
Neg logit contributions | |
ciplinary | -0.463 |
CLASSIFIED | -0.438 |
vantage | -0.416 |
ffect | -0.398 |
unexplained | -0.392 |
Token |
|
Token ID | 198 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
rons | +2.101 |
liam | +2.036 |
enegger | +1.847 |
oons | +1.697 |
rises | +1.642 |
Neg logit contributions | |
ciplinary | -1.162 |
CLASSIFIED | -1.106 |
vantage | -1.054 |
ffect | -1.010 |
respectively | -0.991 |
Token |
|
Token ID | 198 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
rons | +1.880 |
liam | +1.831 |
enegger | +1.626 |
oons | +1.511 |
ries | +1.475 |
Neg logit contributions | |
ciplinary | -1.184 |
CLASSIFIED | -1.141 |
vantage | -1.077 |
ffect | -1.012 |
unexplained | -1.009 |
Token | get |
Token ID | 651 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
ciplinary | +0.033 |
CLASSIFIED | +0.031 |
vantage | +0.030 |
ffect | +0.029 |
respectively | +0.028 |
Neg logit contributions | |
rons | -0.058 |
liam | -0.056 |
enegger | -0.051 |
oons | -0.047 |
ries | -0.045 |
Token | loud |
Token ID | 7812 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ciplinary | +3.016 |
CLASSIFIED | +2.775 |
probation | +2.618 |
vantage | +2.611 |
intentional | +2.602 |
Neg logit contributions | |
rons | -6.399 |
liam | -6.240 |
enegger | -5.839 |
oons | -5.315 |
rises | -5.073 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ciplinary | +0.241 |
CLASSIFIED | +0.225 |
vantage | +0.218 |
ffect | +0.206 |
respectively | +0.201 |
Neg logit contributions | |
rons | -0.504 |
liam | -0.494 |
enegger | -0.451 |
oons | -0.415 |
rises | -0.401 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
rons | +1.300 |
liam | +1.258 |
enegger | +1.146 |
oons | +1.052 |
rises | +1.019 |
Neg logit contributions | |
ciplinary | -0.693 |
CLASSIFIED | -0.661 |
vantage | -0.631 |
ffect | -0.602 |
respectively | -0.590 |
Token |
|
Token ID | 198 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
ciplinary | +0.891 |
CLASSIFIED | +0.831 |
vantage | +0.792 |
ffect | +0.759 |
respectively | +0.740 |
Neg logit contributions | |
rons | -1.734 |
liam | -1.681 |
enegger | -1.537 |
oons | -1.410 |
rises | -1.365 |
Token | It |
Token ID | 1026 |
Feature activation | -9.05e+00 |
Pos logit contributions | |
ciplinary | +0.063 |
CLASSIFIED | +0.061 |
vantage | +0.057 |
ffect | +0.055 |
respectively | +0.053 |
Neg logit contributions | |
rons | -0.107 |
liam | -0.103 |
enegger | -0.095 |
oons | -0.086 |
ries | -0.083 |
Token | � |
Token ID | 447 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
ciplinary | +4.914 |
vantage | +4.497 |
CLASSIFIED | +4.389 |
ffect | +4.220 |
unclear | +4.047 |
Neg logit contributions | |
rons | -10.283 |
liam | -9.921 |
enegger | -9.045 |
oons | -8.374 |
aires | -8.058 |
Token | � |
Token ID | 247 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ciplinary | +3.052 |
CLASSIFIED | +2.888 |
vantage | +2.783 |
ffect | +2.712 |
probation | +2.694 |
Neg logit contributions | |
rons | -3.253 |
liam | -3.086 |
enegger | -2.826 |
oons | -2.478 |
rises | -2.399 |
Token | s |
Token ID | 82 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
ciplinary | +1.460 |
CLASSIFIED | +1.364 |
vantage | +1.361 |
ffect | +1.314 |
respectively | +1.289 |
Neg logit contributions | |
rons | -1.589 |
liam | -1.534 |
enegger | -1.377 |
oons | -1.213 |
rises | -1.148 |
Token | not |
Token ID | 407 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
ciplinary | +2.945 |
CLASSIFIED | +2.685 |
unclear | +2.568 |
unexplained | +2.546 |
vantage | +2.524 |
Neg logit contributions | |
rons | -6.815 |
liam | -6.638 |
enegger | -6.120 |
oons | -5.672 |
rises | -5.508 |
Token | a |
Token ID | 257 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ciplinary | +2.162 |
CLASSIFIED | +2.015 |
unexplained | +1.910 |
vantage | +1.883 |
intentional | +1.874 |
Neg logit contributions | |
rons | -4.876 |
liam | -4.766 |
enegger | -4.410 |
oons | -4.006 |
rises | -3.923 |
Token | 375 |
Token ID | 29414 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
rons | +5.329 |
liam | +5.152 |
enegger | +4.652 |
oons | +4.282 |
ries | +4.162 |
Neg logit contributions | |
ciplinary | -3.118 |
CLASSIFIED | -2.942 |
vantage | -2.789 |
ffect | -2.660 |
terday | -2.603 |
Token | , |
Token ID | 11 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ciplinary | +0.614 |
CLASSIFIED | +0.587 |
vantage | +0.566 |
ffect | +0.545 |
respectively | +0.540 |
Neg logit contributions | |
rons | -0.870 |
liam | -0.845 |
enegger | -0.775 |
oons | -0.684 |
rises | -0.676 |
Token | so |
Token ID | 523 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
rons | +0.326 |
liam | +0.318 |
enegger | +0.289 |
oons | +0.263 |
rises | +0.255 |
Neg logit contributions | |
ciplinary | -0.189 |
CLASSIFIED | -0.179 |
vantage | -0.172 |
ffect | -0.164 |
respectively | -0.163 |
Token | after |
Token ID | 706 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
ciplinary | +3.510 |
CLASSIFIED | +3.298 |
vantage | +3.138 |
respectively | +3.133 |
unexplained | +3.086 |
Neg logit contributions | |
rons | -6.280 |
liam | -6.215 |
enegger | -5.642 |
oons | -5.124 |
rises | -5.038 |
Token | 12 |
Token ID | 1105 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
rons | +2.434 |
liam | +2.372 |
enegger | +2.159 |
oons | +1.969 |
rises | +1.909 |
Neg logit contributions | |
ciplinary | -1.389 |
CLASSIFIED | -1.312 |
vantage | -1.247 |
ffect | -1.196 |
unexplained | -1.181 |
Token | minutes |
Token ID | 2431 |
Feature activation | -9.02e+00 |
Pos logit contributions | |
ciplinary | +3.232 |
CLASSIFIED | +3.074 |
vantage | +2.974 |
unexplained | +2.895 |
ffect | +2.888 |
Neg logit contributions | |
rons | -3.934 |
liam | -3.766 |
enegger | -3.482 |
oons | -2.976 |
rises | -2.917 |
Token | we |
Token ID | 356 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
ciplinary | +4.801 |
CLASSIFIED | +4.524 |
respectively | +4.523 |
probation | +4.437 |
unexplained | +4.361 |
Neg logit contributions | |
rons | -10.076 |
liam | -10.049 |
enegger | -9.491 |
oons | -8.321 |
rises | -8.034 |
Token | lowered |
Token ID | 17788 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
ciplinary | +0.528 |
vantage | +0.474 |
CLASSIFIED | +0.468 |
respectively | +0.457 |
ffect | +0.452 |
Neg logit contributions | |
rons | -0.939 |
liam | -0.926 |
enegger | -0.846 |
oons | -0.771 |
ries | -0.745 |
Token | the |
Token ID | 262 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
ciplinary | +1.251 |
CLASSIFIED | +1.174 |
vantage | +1.120 |
respectively | +1.068 |
probation | +1.052 |
Neg logit contributions | |
rons | -2.981 |
liam | -2.939 |
enegger | -2.714 |
oons | -2.474 |
rises | -2.402 |
Token | temperature |
Token ID | 5951 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
rons | +1.618 |
liam | +1.583 |
enegger | +1.417 |
oons | +1.276 |
rises | +1.224 |
Neg logit contributions | |
ciplinary | -1.246 |
CLASSIFIED | -1.183 |
vantage | -1.147 |
ffect | -1.110 |
unexplained | -1.096 |
Token | to |
Token ID | 284 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
rons | +0.826 |
liam | +0.810 |
enegger | +0.744 |
oons | +0.681 |
rises | +0.659 |
Neg logit contributions | |
ciplinary | -0.378 |
CLASSIFIED | -0.355 |
vantage | -0.337 |
ffect | -0.320 |
respectively | -0.317 |
Token | ir |
Token ID | 343 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
rons | +2.288 |
liam | +2.204 |
enegger | +1.959 |
oons | +1.765 |
rises | +1.702 |
Neg logit contributions | |
ciplinary | -1.940 |
CLASSIFIED | -1.838 |
vantage | -1.788 |
ffect | -1.731 |
respectively | -1.700 |
Token | an |
Token ID | 272 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
rons | +1.424 |
liam | +1.366 |
enegger | +1.181 |
oons | +1.027 |
rises | +0.973 |
Neg logit contributions | |
ciplinary | -1.827 |
CLASSIFIED | -1.742 |
vantage | -1.716 |
ffect | -1.661 |
respectively | -1.638 |
Token | E |
Token ID | 412 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
ciplinary | +2.495 |
CLASSIFIED | +2.330 |
vantage | +2.241 |
ffect | +2.209 |
respectively | +2.180 |
Neg logit contributions | |
rons | -3.890 |
liam | -3.765 |
enegger | -3.451 |
oons | -3.137 |
rises | -3.040 |
Token | inav |
Token ID | 26802 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
ciplinary | +0.078 |
CLASSIFIED | +0.072 |
vantage | +0.072 |
ffect | +0.069 |
respectively | +0.068 |
Neg logit contributions | |
rons | -0.086 |
liam | -0.083 |
enegger | -0.074 |
oons | -0.066 |
rises | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
rons | +0.037 |
liam | +0.036 |
enegger | +0.032 |
oons | +0.030 |
rises | +0.029 |
Neg logit contributions | |
ciplinary | -0.019 |
CLASSIFIED | -0.018 |
vantage | -0.018 |
ffect | -0.017 |
unexplained | -0.016 |
Token | turned |
Token ID | 2900 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
ciplinary | +1.077 |
CLASSIFIED | +1.012 |
vantage | +0.964 |
respectively | +0.951 |
unexplained | +0.951 |
Neg logit contributions | |
rons | -1.841 |
liam | -1.786 |
enegger | -1.608 |
oons | -1.478 |
rises | -1.437 |
Token | out |
Token ID | 503 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
ciplinary | +4.096 |
CLASSIFIED | +3.973 |
vantage | +3.972 |
intentional | +3.966 |
probation | +3.961 |
Neg logit contributions | |
rons | -12.403 |
liam | -12.016 |
enegger | -11.619 |
覚醒 | -10.314 |
oons | -10.301 |
Token | to |
Token ID | 284 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
rons | +3.132 |
liam | +3.044 |
enegger | +2.776 |
oons | +2.570 |
ries | +2.491 |
Neg logit contributions | |
ciplinary | -1.476 |
CLASSIFIED | -1.382 |
vantage | -1.304 |
ffect | -1.237 |
unexplained | -1.202 |
Token | have |
Token ID | 423 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
ciplinary | +1.430 |
CLASSIFIED | +1.316 |
vantage | +1.282 |
respectively | +1.260 |
unexplained | +1.237 |
Neg logit contributions | |
rons | -2.226 |
liam | -2.147 |
enegger | -1.935 |
oons | -1.780 |
ries | -1.721 |
Token | mis |
Token ID | 2984 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
ciplinary | +0.241 |
CLASSIFIED | +0.227 |
vantage | +0.212 |
unexplained | +0.211 |
probation | +0.208 |
Neg logit contributions | |
rons | -0.452 |
liam | -0.444 |
enegger | -0.403 |
oons | -0.373 |
rises | -0.359 |
Token | read |
Token ID | 961 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
ciplinary | +2.229 |
vantage | +1.995 |
CLASSIFIED | +1.989 |
ffect | +1.938 |
pped | +1.914 |
Neg logit contributions | |
rons | -2.945 |
liam | -2.861 |
enegger | -2.568 |
oons | -2.350 |
rises | -2.247 |
Token | be |
Token ID | 307 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
rons | +7.282 |
liam | +7.016 |
enegger | +6.311 |
oons | +5.765 |
rises | +5.586 |
Neg logit contributions | |
ciplinary | -5.088 |
CLASSIFIED | -4.996 |
vantage | -4.635 |
ffect | -4.476 |
unexplained | -4.357 |
Token | reversed |
Token ID | 17687 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
rons | +4.880 |
liam | +4.734 |
enegger | +4.278 |
oons | +3.942 |
ries | +3.819 |
Neg logit contributions | |
ciplinary | -2.815 |
CLASSIFIED | -2.667 |
vantage | -2.531 |
ffect | -2.429 |
terday | -2.362 |
Token | . |
Token ID | 13 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
rons | +1.585 |
liam | +1.543 |
enegger | +1.398 |
oons | +1.288 |
rises | +1.244 |
Neg logit contributions | |
ciplinary | -0.867 |
CLASSIFIED | -0.815 |
vantage | -0.782 |
ffect | -0.743 |
respectively | -0.737 |
Token | It |
Token ID | 632 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
rons | +5.392 |
liam | +5.251 |
enegger | +4.686 |
oons | +4.303 |
ries | +4.149 |
Neg logit contributions | |
ciplinary | -3.664 |
CLASSIFIED | -3.431 |
vantage | -3.281 |
ffect | -3.139 |
unexplained | -3.109 |
Token | is |
Token ID | 318 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
ciplinary | +0.768 |
CLASSIFIED | +0.692 |
vantage | +0.661 |
ffect | +0.615 |
unexplained | +0.608 |
Neg logit contributions | |
rons | -2.141 |
liam | -2.083 |
enegger | -1.914 |
oons | -1.789 |
rises | -1.727 |
Token | far |
Token ID | 1290 |
Feature activation | -8.76e+00 |
Pos logit contributions | |
ciplinary | +1.619 |
CLASSIFIED | +1.477 |
unexplained | +1.415 |
vantage | +1.380 |
unclear | +1.373 |
Neg logit contributions | |
rons | -3.944 |
liam | -3.797 |
enegger | -3.523 |
oons | -3.299 |
rises | -3.183 |
Token | from |
Token ID | 422 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
ciplinary | +4.078 |
CLASSIFIED | +3.564 |
unclear | +3.550 |
vantage | +3.523 |
unexplained | +3.510 |
Neg logit contributions | |
rons | -10.724 |
liam | -10.355 |
enegger | -9.657 |
oons | -9.034 |
rises | -8.858 |
Token | clear |
Token ID | 1598 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ciplinary | +2.070 |
CLASSIFIED | +1.937 |
unexplained | +1.893 |
vantage | +1.803 |
unclear | +1.800 |
Neg logit contributions | |
rons | -5.568 |
liam | -5.365 |
enegger | -5.017 |
oons | -4.630 |
rises | -4.454 |
Token | that |
Token ID | 326 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
rons | +2.284 |
liam | +2.215 |
enegger | +2.015 |
oons | +1.857 |
rises | +1.795 |
Neg logit contributions | |
ciplinary | -1.214 |
CLASSIFIED | -1.143 |
vantage | -1.082 |
ffect | -1.037 |
unexplained | -1.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
rons | +2.047 |
liam | +1.984 |
enegger | +1.813 |
oons | +1.669 |
rises | +1.609 |
Neg logit contributions | |
ciplinary | -1.078 |
CLASSIFIED | -1.020 |
vantage | -0.964 |
ffect | -0.928 |
unexplained | -0.911 |
Token | Governor |
Token ID | 10807 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
ciplinary | +0.120 |
CLASSIFIED | +0.113 |
vantage | +0.109 |
ffect | +0.106 |
unexplained | +0.106 |
Neg logit contributions | |
rons | -0.182 |
liam | -0.175 |
enegger | -0.159 |
oons | -0.145 |
rises | -0.138 |
Token |
|
Token ID | 198 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
ciplinary | +0.672 |
CLASSIFIED | +0.630 |
vantage | +0.599 |
ffect | +0.574 |
unexplained | +0.559 |
Neg logit contributions | |
rons | -1.269 |
liam | -1.230 |
enegger | -1.121 |
oons | -1.031 |
rises | -0.997 |
Token | The |
Token ID | 464 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
rons | +0.663 |
liam | +0.637 |
enegger | +0.585 |
oons | +0.530 |
rises | +0.510 |
Neg logit contributions | |
ciplinary | -0.407 |
CLASSIFIED | -0.397 |
vantage | -0.371 |
ffect | -0.356 |
probation | -0.347 |
Token | firm |
Token ID | 4081 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ciplinary | +1.423 |
CLASSIFIED | +1.358 |
vantage | +1.281 |
probation | +1.279 |
ffect | +1.274 |
Neg logit contributions | |
rons | -2.387 |
liam | -2.352 |
enegger | -2.114 |
oons | -1.916 |
rises | -1.868 |
Token | hired |
Token ID | 9657 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
rons | +1.508 |
liam | +1.470 |
enegger | +1.334 |
oons | +1.234 |
rises | +1.193 |
Neg logit contributions | |
ciplinary | -0.773 |
CLASSIFIED | -0.726 |
vantage | -0.686 |
ffect | -0.658 |
unexplained | -0.644 |
Token | to |
Token ID | 284 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
rons | +1.664 |
liam | +1.617 |
enegger | +1.467 |
oons | +1.349 |
rises | +1.306 |
Neg logit contributions | |
ciplinary | -0.911 |
CLASSIFIED | -0.861 |
vantage | -0.819 |
ffect | -0.781 |
unexplained | -0.766 |
Token | do |
Token ID | 466 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
ciplinary | +2.893 |
CLASSIFIED | +2.573 |
probation | +2.521 |
ffect | +2.516 |
respectively | +2.516 |
Neg logit contributions | |
rons | -5.590 |
liam | -5.500 |
enegger | -5.097 |
oons | -4.630 |
rises | -4.472 |
Token | testing |
Token ID | 4856 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ciplinary | +6.000 |
CLASSIFIED | +5.907 |
probation | +5.788 |
ffect | +5.489 |
unexplained | +5.468 |
Neg logit contributions | |
rons | -12.965 |
liam | -12.794 |
enegger | -11.539 |
oons | -10.649 |
rises | -10.370 |
Token | , |
Token ID | 11 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
rons | +1.461 |
liam | +1.422 |
enegger | +1.289 |
oons | +1.186 |
rises | +1.144 |
Neg logit contributions | |
ciplinary | -0.816 |
CLASSIFIED | -0.764 |
vantage | -0.728 |
ffect | -0.701 |
probation | -0.690 |
Token | AIR |
Token ID | 31600 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
ciplinary | +1.276 |
CLASSIFIED | +1.227 |
vantage | +1.167 |
respectively | +1.125 |
ffect | +1.121 |
Neg logit contributions | |
rons | -2.183 |
liam | -2.140 |
enegger | -1.941 |
oons | -1.763 |
rises | -1.733 |
Token | , |
Token ID | 11 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ciplinary | +2.985 |
CLASSIFIED | +2.867 |
vantage | +2.766 |
respectively | +2.595 |
ffect | +2.591 |
Neg logit contributions | |
rons | -6.228 |
liam | -6.060 |
enegger | -5.461 |
oons | -5.096 |
rises | -4.936 |
Token | separately |
Token ID | 13869 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
ciplinary | +0.799 |
CLASSIFIED | +0.741 |
vantage | +0.708 |
respectively | +0.686 |
ffect | +0.684 |
Neg logit contributions | |
rons | -1.502 |
liam | -1.472 |
enegger | -1.334 |
oons | -1.225 |
rises | -1.187 |