Token | TODAY |
Token ID | 20092 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
�� | +0.698 |
�� | +0.646 |
�� | +0.614 |
�� | +0.569 |
�� | +0.567 |
Neg logit contributions | |
acebook | -0.139 |
phabet | -0.138 |
utherland | -0.130 |
Civil | -0.102 |
FontSize | -0.094 |
Token | 's |
Token ID | 338 |
Feature activation | +9.37e+00 |
Pos logit contributions | |
�� | +5.366 |
�� | +4.811 |
�� | +4.515 |
�� | +4.063 |
�� | +4.058 |
Neg logit contributions | |
acebook | -2.592 |
utherland | -2.588 |
phabet | -2.567 |
FontSize | -2.250 |
Civil | -2.228 |
Token | news |
Token ID | 1705 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
�� | +11.535 |
�� | +9.702 |
�� | +8.842 |
�� | +7.902 |
�� | +7.733 |
Neg logit contributions | |
phabet | -8.480 |
acebook | -8.436 |
utherland | -8.358 |
sung | -7.964 |
FontSize | -7.912 |
Token | staff |
Token ID | 3085 |
Feature activation | +8.28e+00 |
Pos logit contributions | |
�� | +3.902 |
�� | +3.478 |
�� | +3.263 |
�� | +2.939 |
�� | +2.852 |
Neg logit contributions | |
acebook | -2.131 |
phabet | -2.119 |
utherland | -2.078 |
Civil | -1.861 |
FontSize | -1.848 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
�� | +11.237 |
�� | +9.945 |
�� | +9.473 |
�� | +8.340 |
�� | +8.307 |
Neg logit contributions | |
acebook | -6.676 |
phabet | -6.249 |
utherland | -6.229 |
Civil | -5.577 |
FontSize | -5.554 |
Token | Most |
Token ID | 4042 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
�� | +17.598 |
�� | +15.072 |
�� | +14.724 |
�� | +13.167 |
�� | +12.485 |
Neg logit contributions | |
phabet | -10.115 |
acebook | -10.018 |
FontSize | -9.459 |
utherland | -9.172 |
rift | -8.889 |
Token | editor |
Token ID | 5464 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
�� | +19.083 |
�� | +16.869 |
�� | +15.900 |
�� | +14.744 |
�� | +14.084 |
Neg logit contributions | |
acebook | -10.589 |
phabet | -10.119 |
utherland | -9.718 |
FontSize | -9.436 |
uay | -8.880 |
Token | ials |
Token ID | 8231 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
�� | +2.804 |
�� | +2.556 |
�� | +2.425 |
�� | +2.260 |
�� | +2.235 |
Neg logit contributions | |
acebook | -0.597 |
phabet | -0.575 |
utherland | -0.569 |
Civil | -0.459 |
FontSize | -0.425 |
Token | are |
Token ID | 389 |
Feature activation | +8.68e+00 |
Pos logit contributions | |
�� | +8.707 |
�� | +7.864 |
�� | +7.425 |
�� | +6.753 |
�� | +6.555 |
Neg logit contributions | |
phabet | -4.066 |
acebook | -3.927 |
utherland | -3.911 |
FontSize | -3.637 |
Civil | -3.444 |
Token | accompanied |
Token ID | 11791 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
�� | +10.698 |
�� | +9.609 |
�� | +8.836 |
�� | +7.652 |
�� | +7.557 |
Neg logit contributions | |
phabet | -8.138 |
acebook | -7.946 |
utherland | -7.871 |
FontSize | -7.310 |
rift | -7.081 |
Token | by |
Token ID | 416 |
Feature activation | +7.75e+00 |
Pos logit contributions | |
acebook | +0.580 |
phabet | +0.575 |
utherland | +0.568 |
Civil | +0.514 |
FontSize | +0.485 |
Neg logit contributions | |
�� | -1.272 |
�� | -1.142 |
�� | -1.070 |
�� | -0.973 |
�� | -0.962 |
Token | Board |
Token ID | 5926 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
�� | +1.875 |
�� | +1.717 |
�� | +1.625 |
�� | +1.508 |
�� | +1.489 |
Neg logit contributions | |
acebook | -0.420 |
phabet | -0.419 |
utherland | -0.412 |
Civil | -0.349 |
FontSize | -0.310 |
Token | 's |
Token ID | 338 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
�� | +8.160 |
�� | +7.352 |
�� | +6.826 |
�� | +6.249 |
�� | +6.111 |
Neg logit contributions | |
acebook | -4.036 |
phabet | -3.945 |
utherland | -3.912 |
Civil | -3.450 |
sung | -3.406 |
Token | point |
Token ID | 966 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
�� | +9.197 |
�� | +8.189 |
�� | +7.603 |
�� | +6.978 |
�� | +6.827 |
Neg logit contributions | |
phabet | -4.627 |
acebook | -4.592 |
utherland | -4.489 |
Civil | -3.993 |
FontSize | -3.948 |
Token | of |
Token ID | 286 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
�� | +3.275 |
�� | +2.940 |
�� | +2.750 |
�� | +2.512 |
�� | +2.448 |
Neg logit contributions | |
acebook | -1.503 |
phabet | -1.495 |
utherland | -1.476 |
Civil | -1.337 |
sung | -1.285 |
Token | view |
Token ID | 1570 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
�� | +4.716 |
�� | +4.232 |
�� | +3.991 |
�� | +3.697 |
�� | +3.602 |
Neg logit contributions | |
phabet | -1.627 |
acebook | -1.621 |
utherland | -1.595 |
Civil | -1.395 |
sung | -1.351 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
�� | +1.261 |
�� | +1.137 |
�� | +1.068 |
�� | +0.978 |
�� | +0.957 |
Neg logit contributions | |
acebook | -0.530 |
phabet | -0.526 |
utherland | -0.522 |
Civil | -0.471 |
FontSize | -0.443 |
Token |
|
Token ID | 198 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
�� | +18.389 |
�� | +15.687 |
�� | +15.207 |
�� | +13.242 |
�� | +12.893 |
Neg logit contributions | |
phabet | -10.894 |
acebook | -10.777 |
utherland | -10.224 |
FontSize | -9.898 |
sung | -9.285 |
Token |
|
Token ID | 198 |
Feature activation | +7.48e+00 |
Pos logit contributions | |
�� | +6.217 |
�� | +5.456 |
�� | +5.062 |
�� | +4.573 |
�� | +4.543 |
Neg logit contributions | |
acebook | -3.593 |
phabet | -3.458 |
utherland | -3.328 |
Civil | -2.838 |
FontSize | -2.785 |
Token | Case |
Token ID | 20448 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
�� | +10.822 |
�� | +9.486 |
�� | +9.041 |
�� | +8.107 |
�� | +7.970 |
Neg logit contributions | |
acebook | -5.284 |
phabet | -5.087 |
utherland | -4.986 |
Civil | -4.644 |
romeda | -4.216 |
Token | in |
Token ID | 287 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
�� | +6.772 |
�� | +6.103 |
�� | +5.639 |
�� | +5.191 |
�� | +5.059 |
Neg logit contributions | |
acebook | -3.374 |
phabet | -3.347 |
utherland | -3.272 |
Civil | -2.984 |
FontSize | -2.860 |
Token | point |
Token ID | 966 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
�� | +5.823 |
�� | +5.228 |
�� | +4.846 |
�� | +4.457 |
�� | +4.356 |
Neg logit contributions | |
acebook | -2.672 |
phabet | -2.652 |
utherland | -2.599 |
Civil | -2.245 |
FontSize | -2.229 |
Token | , |
Token ID | 11 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
�� | +4.054 |
�� | +3.640 |
�� | +3.375 |
�� | +3.052 |
�� | +3.028 |
Neg logit contributions | |
acebook | -1.959 |
phabet | -1.942 |
utherland | -1.896 |
Civil | -1.729 |
FontSize | -1.672 |
Token | which |
Token ID | 543 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
�� | +1.347 |
�� | +1.212 |
�� | +1.133 |
�� | +1.031 |
�� | +1.018 |
Neg logit contributions | |
acebook | -0.588 |
phabet | -0.584 |
utherland | -0.578 |
Civil | -0.522 |
FontSize | -0.495 |
Token | is |
Token ID | 318 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
�� | +8.638 |
�� | +7.707 |
�� | +7.309 |
�� | +6.526 |
�� | +6.500 |
Neg logit contributions | |
phabet | -4.020 |
acebook | -4.000 |
utherland | -3.950 |
Civil | -3.455 |
sung | -3.438 |
Token | the |
Token ID | 262 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
�� | +4.189 |
�� | +3.764 |
�� | +3.510 |
�� | +3.179 |
�� | +3.158 |
Neg logit contributions | |
phabet | -1.978 |
acebook | -1.974 |
utherland | -1.942 |
Civil | -1.733 |
FontSize | -1.675 |
Token | bread |
Token ID | 8509 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
�� | +5.877 |
�� | +5.284 |
�� | +4.927 |
�� | +4.462 |
�� | +4.402 |
Neg logit contributions | |
acebook | -2.924 |
phabet | -2.903 |
utherland | -2.865 |
Civil | -2.530 |
FontSize | -2.511 |
Token | and |
Token ID | 290 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
�� | +4.765 |
�� | +4.283 |
�� | +4.008 |
�� | +3.665 |
�� | +3.544 |
Neg logit contributions | |
acebook | -2.320 |
phabet | -2.283 |
utherland | -2.282 |
Civil | -2.068 |
FontSize | -1.975 |
Token | butter |
Token ID | 9215 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
�� | +14.300 |
�� | +12.105 |
�� | +10.730 |
�� | +9.719 |
�� | +9.171 |
Neg logit contributions | |
utherland | -14.201 |
acebook | -14.128 |
phabet | -14.055 |
FontSize | -13.370 |
uay | -12.945 |
Token | for |
Token ID | 329 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
�� | +2.652 |
�� | +2.393 |
�� | +2.238 |
�� | +2.024 |
�� | +1.997 |
Neg logit contributions | |
acebook | -1.221 |
phabet | -1.206 |
utherland | -1.193 |
Civil | -1.073 |
FontSize | -1.037 |
Token | these |
Token ID | 777 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
�� | +1.966 |
�� | +1.765 |
�� | +1.648 |
�� | +1.494 |
�� | +1.473 |
Neg logit contributions | |
acebook | -0.982 |
phabet | -0.979 |
utherland | -0.968 |
Civil | -0.875 |
FontSize | -0.837 |
Token | guys |
Token ID | 3730 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
�� | +5.149 |
�� | +4.586 |
�� | +4.282 |
�� | +3.857 |
�� | +3.820 |
Neg logit contributions | |
acebook | -3.012 |
phabet | -2.996 |
utherland | -2.927 |
Civil | -2.661 |
FontSize | -2.629 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
�� | +1.053 |
�� | +0.946 |
�� | +0.883 |
�� | +0.805 |
�� | +0.795 |
Neg logit contributions | |
acebook | -0.485 |
phabet | -0.481 |
utherland | -0.476 |
Civil | -0.434 |
FontSize | -0.410 |
Token | a |
Token ID | 257 |
Feature activation | +7.80e+00 |
Pos logit contributions | |
�� | +4.845 |
�� | +4.326 |
�� | +3.970 |
�� | +3.568 |
�� | +3.550 |
Neg logit contributions | |
phabet | -2.823 |
acebook | -2.778 |
utherland | -2.696 |
FontSize | -2.421 |
rift | -2.379 |
Token | couple |
Token ID | 3155 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
�� | +9.538 |
�� | +8.523 |
�� | +7.788 |
�� | +6.918 |
�� | +6.856 |
Neg logit contributions | |
acebook | -7.101 |
phabet | -6.732 |
utherland | -6.464 |
FontSize | -6.246 |
sung | -5.851 |
Token | of |
Token ID | 286 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
�� | +10.168 |
�� | +9.143 |
�� | +8.119 |
�� | +7.557 |
�� | +7.419 |
Neg logit contributions | |
acebook | -5.948 |
phabet | -5.915 |
utherland | -5.556 |
rift | -5.139 |
sung | -5.070 |
Token | books |
Token ID | 3835 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
�� | +12.596 |
�� | +11.364 |
�� | +10.029 |
�� | +9.495 |
�� | +8.978 |
Neg logit contributions | |
phabet | -8.461 |
acebook | -8.160 |
utherland | -8.089 |
FontSize | -7.598 |
romeda | -7.232 |
Token | , |
Token ID | 11 |
Feature activation | +9.73e+00 |
Pos logit contributions | |
�� | +12.402 |
�� | +10.484 |
�� | +9.331 |
�� | +8.872 |
�� | +8.792 |
Neg logit contributions | |
acebook | -10.335 |
utherland | -10.062 |
phabet | -9.592 |
FontSize | -9.074 |
sung | -8.747 |
Token | which |
Token ID | 543 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
�� | +13.085 |
�� | +10.801 |
�� | +9.886 |
�� | +9.127 |
�� | +9.111 |
Neg logit contributions | |
acebook | -7.866 |
phabet | -7.693 |
utherland | -7.625 |
rift | -6.924 |
ieth | -6.711 |
Token | you |
Token ID | 345 |
Feature activation | +9.81e+00 |
Pos logit contributions | |
�� | +15.943 |
�� | +13.996 |
�� | +13.197 |
�� | +11.544 |
�� | +11.208 |
Neg logit contributions | |
acebook | -11.732 |
sung | -11.075 |
rift | -10.968 |
phabet | -10.913 |
FontSize | -10.667 |
Token | might |
Token ID | 1244 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
�� | +11.989 |
�� | +9.484 |
�� | +8.731 |
�� | +8.324 |
�� | +8.305 |
Neg logit contributions | |
acebook | -9.272 |
phabet | -9.119 |
utherland | -8.380 |
FontSize | -7.862 |
uay | -7.849 |
Token | want |
Token ID | 765 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
�� | +15.484 |
�� | +13.199 |
�� | +11.524 |
�� | +10.891 |
�� | +10.765 |
Neg logit contributions | |
acebook | -11.767 |
phabet | -10.740 |
utherland | -10.510 |
rift | -9.578 |
FontSize | -9.571 |
Token | to |
Token ID | 284 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
�� | +6.912 |
�� | +6.126 |
�� | +5.615 |
�� | +5.077 |
�� | +5.002 |
Neg logit contributions | |
acebook | -3.678 |
phabet | -3.492 |
utherland | -3.412 |
Civil | -3.075 |
FontSize | -3.038 |
Token | per |
Token ID | 583 |
Feature activation | +9.76e+00 |
Pos logit contributions | |
�� | +8.792 |
�� | +7.822 |
�� | +7.251 |
�� | +6.620 |
�� | +6.405 |
Neg logit contributions | |
acebook | -4.751 |
phabet | -4.672 |
utherland | -4.417 |
FontSize | -4.142 |
heres | -3.982 |
Token | , |
Token ID | 11 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
phabet | +3.016 |
acebook | +2.995 |
utherland | +2.980 |
Civil | +2.782 |
sung | +2.525 |
Neg logit contributions | |
�� | -7.004 |
�� | -6.327 |
�� | -5.928 |
�� | -5.446 |
�� | -5.346 |
Token | but |
Token ID | 475 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
phabet | +2.034 |
acebook | +2.031 |
utherland | +2.022 |
Civil | +1.872 |
FontSize | +1.730 |
Neg logit contributions | |
�� | -4.308 |
�� | -3.881 |
�� | -3.625 |
�� | -3.313 |
�� | -3.258 |
Token | occasionally |
Token ID | 10491 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
�� | +0.348 |
�� | +0.313 |
�� | +0.293 |
�� | +0.267 |
�� | +0.263 |
Neg logit contributions | |
acebook | -0.159 |
phabet | -0.159 |
utherland | -0.157 |
Civil | -0.143 |
FontSize | -0.135 |
Token | , |
Token ID | 11 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
�� | +1.252 |
�� | +1.122 |
�� | +1.047 |
�� | +0.951 |
�� | +0.936 |
Neg logit contributions | |
phabet | -0.610 |
acebook | -0.610 |
utherland | -0.602 |
Civil | -0.548 |
FontSize | -0.521 |
Token | Dungeons |
Token ID | 25461 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
acebook | +0.559 |
phabet | +0.557 |
utherland | +0.552 |
Civil | +0.505 |
FontSize | +0.474 |
Neg logit contributions | |
�� | -1.212 |
�� | -1.089 |
�� | -1.018 |
�� | -0.929 |
�� | -0.914 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
acebook | +0.553 |
phabet | +0.550 |
utherland | +0.544 |
Civil | +0.490 |
FontSize | +0.451 |
Neg logit contributions | |
�� | -1.527 |
�� | -1.383 |
�� | -1.300 |
�� | -1.196 |
�� | -1.178 |
Token | Dragons |
Token ID | 19075 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
�� | +15.778 |
�� | +13.418 |
�� | +12.030 |
�� | +11.280 |
�� | +11.156 |
Neg logit contributions | |
phabet | -11.811 |
utherland | -11.781 |
acebook | -11.599 |
FontSize | -10.940 |
ieth | -10.588 |
Token | players |
Token ID | 1938 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
acebook | +1.426 |
phabet | +1.416 |
utherland | +1.407 |
Civil | +1.304 |
FontSize | +1.202 |
Neg logit contributions | |
�� | -3.182 |
�� | -2.863 |
�� | -2.683 |
�� | -2.458 |
�� | -2.406 |
Token | do |
Token ID | 466 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
acebook | +0.778 |
phabet | +0.776 |
utherland | +0.768 |
Civil | +0.700 |
FontSize | +0.644 |
Neg logit contributions | |
�� | -1.994 |
�� | -1.802 |
�� | -1.693 |
�� | -1.553 |
�� | -1.527 |
Token | not |
Token ID | 407 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
acebook | +0.061 |
phabet | +0.061 |
utherland | +0.060 |
Civil | +0.054 |
FontSize | +0.050 |
Neg logit contributions | |
�� | -0.152 |
�� | -0.137 |
�� | -0.129 |
�� | -0.118 |
�� | -0.116 |
Token | take |
Token ID | 1011 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
acebook | +1.308 |
phabet | +1.308 |
utherland | +1.292 |
Civil | +1.188 |
sung | +1.073 |
Neg logit contributions | |
�� | -3.705 |
�� | -3.344 |
�� | -3.172 |
�� | -2.908 |
�� | -2.856 |
Token | USA |
Token ID | 4916 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
�� | +10.356 |
�� | +9.100 |
�� | +8.509 |
�� | +7.582 |
�� | +7.525 |
Neg logit contributions | |
acebook | -6.222 |
utherland | -6.196 |
phabet | -6.040 |
FontSize | -5.627 |
sung | -5.520 |
Token | TODAY |
Token ID | 20092 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
�� | +0.698 |
�� | +0.646 |
�� | +0.614 |
�� | +0.569 |
�� | +0.567 |
Neg logit contributions | |
acebook | -0.139 |
phabet | -0.138 |
utherland | -0.130 |
Civil | -0.102 |
FontSize | -0.094 |
Token | 's |
Token ID | 338 |
Feature activation | +9.37e+00 |
Pos logit contributions | |
�� | +5.366 |
�� | +4.811 |
�� | +4.515 |
�� | +4.063 |
�� | +4.058 |
Neg logit contributions | |
acebook | -2.592 |
utherland | -2.588 |
phabet | -2.567 |
FontSize | -2.250 |
Civil | -2.228 |
Token | news |
Token ID | 1705 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
�� | +11.535 |
�� | +9.702 |
�� | +8.842 |
�� | +7.902 |
�� | +7.733 |
Neg logit contributions | |
phabet | -8.480 |
acebook | -8.436 |
utherland | -8.358 |
sung | -7.964 |
FontSize | -7.912 |
Token | staff |
Token ID | 3085 |
Feature activation | +8.28e+00 |
Pos logit contributions | |
�� | +3.902 |
�� | +3.478 |
�� | +3.263 |
�� | +2.939 |
�� | +2.852 |
Neg logit contributions | |
acebook | -2.131 |
phabet | -2.119 |
utherland | -2.078 |
Civil | -1.861 |
FontSize | -1.848 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
�� | +11.237 |
�� | +9.945 |
�� | +9.473 |
�� | +8.340 |
�� | +8.307 |
Neg logit contributions | |
acebook | -6.676 |
phabet | -6.249 |
utherland | -6.229 |
Civil | -5.577 |
FontSize | -5.554 |
Token | Most |
Token ID | 4042 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
�� | +17.598 |
�� | +15.072 |
�� | +14.724 |
�� | +13.167 |
�� | +12.485 |
Neg logit contributions | |
phabet | -10.115 |
acebook | -10.018 |
FontSize | -9.459 |
utherland | -9.172 |
rift | -8.889 |
Token | editor |
Token ID | 5464 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
�� | +19.083 |
�� | +16.869 |
�� | +15.900 |
�� | +14.744 |
�� | +14.084 |
Neg logit contributions | |
acebook | -10.589 |
phabet | -10.119 |
utherland | -9.718 |
FontSize | -9.436 |
uay | -8.880 |
Token | ials |
Token ID | 8231 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
�� | +2.804 |
�� | +2.556 |
�� | +2.425 |
�� | +2.260 |
�� | +2.235 |
Neg logit contributions | |
acebook | -0.597 |
phabet | -0.575 |
utherland | -0.569 |
Civil | -0.459 |
FontSize | -0.425 |
Token | are |
Token ID | 389 |
Feature activation | +8.68e+00 |
Pos logit contributions | |
�� | +8.707 |
�� | +7.864 |
�� | +7.425 |
�� | +6.753 |
�� | +6.555 |
Neg logit contributions | |
phabet | -4.066 |
acebook | -3.927 |
utherland | -3.911 |
FontSize | -3.637 |
Civil | -3.444 |
Token | accompanied |
Token ID | 11791 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
�� | +10.698 |
�� | +9.609 |
�� | +8.836 |
�� | +7.652 |
�� | +7.557 |
Neg logit contributions | |
phabet | -8.138 |
acebook | -7.946 |
utherland | -7.871 |
FontSize | -7.310 |
rift | -7.081 |
Token | tune |
Token ID | 14009 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
acebook | +1.872 |
phabet | +1.861 |
utherland | +1.853 |
Civil | +1.739 |
FontSize | +1.589 |
Neg logit contributions | |
�� | -4.079 |
�� | -3.665 |
�� | -3.426 |
�� | -3.122 |
�� | -3.073 |
Token | of |
Token ID | 286 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
�� | +0.644 |
�� | +0.580 |
�� | +0.544 |
�� | +0.497 |
�� | +0.489 |
Neg logit contributions | |
acebook | -0.277 |
phabet | -0.276 |
utherland | -0.274 |
Civil | -0.247 |
FontSize | -0.232 |
Token | George |
Token ID | 4502 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
acebook | +1.027 |
phabet | +1.023 |
utherland | +1.014 |
Civil | +0.935 |
FontSize | +0.866 |
Neg logit contributions | |
�� | -2.322 |
�� | -2.092 |
�� | -1.957 |
�� | -1.789 |
�� | -1.758 |
Token | G |
Token ID | 402 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
phabet | +3.785 |
acebook | +3.739 |
utherland | +3.732 |
Civil | +3.547 |
sung | +3.207 |
Neg logit contributions | |
�� | -9.697 |
�� | -8.853 |
�� | -8.260 |
�� | -7.671 |
�� | -7.444 |
Token | ers |
Token ID | 364 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
utherland | +2.606 |
acebook | +2.589 |
phabet | +2.556 |
Civil | +2.368 |
sung | +2.150 |
Neg logit contributions | |
�� | -7.073 |
�� | -6.473 |
�� | -6.051 |
�� | -5.655 |
�� | -5.500 |
Token | h |
Token ID | 71 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
�� | +3.755 |
�� | +3.413 |
�� | +3.212 |
�� | +2.960 |
�� | +2.950 |
Neg logit contributions | |
phabet | -0.992 |
acebook | -0.987 |
utherland | -0.965 |
Civil | -0.840 |
FontSize | -0.803 |
Token | win |
Token ID | 5404 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
�� | +17.628 |
�� | +15.261 |
�� | +14.694 |
�� | +13.253 |
�� | +13.077 |
Neg logit contributions | |
acebook | -10.261 |
phabet | -10.000 |
utherland | -9.691 |
FontSize | -8.802 |
romeda | -8.538 |
Token | � |
Token ID | 447 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
phabet | +0.881 |
acebook | +0.878 |
utherland | +0.872 |
Civil | +0.792 |
sung | +0.725 |
Neg logit contributions | |
�� | -2.427 |
�� | -2.203 |
�� | -2.068 |
�� | -1.904 |
�� | -1.871 |
Token | � |
Token ID | 247 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
�� | +0.708 |
�� | +0.574 |
�� | +0.498 |
�� | +0.398 |
�� | +0.381 |
Neg logit contributions | |
phabet | -1.241 |
acebook | -1.236 |
utherland | -1.232 |
Civil | -1.183 |
FontSize | -1.149 |
Token | s |
Token ID | 82 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
�� | +2.182 |
�� | +1.951 |
�� | +1.818 |
�� | +1.656 |
�� | +1.632 |
Neg logit contributions | |
acebook | -1.090 |
phabet | -1.082 |
utherland | -1.075 |
Civil | -0.981 |
FontSize | -0.932 |
Token | � |
Token ID | 564 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
�� | +2.623 |
�� | +2.359 |
�� | +2.206 |
�� | +2.015 |
�� | +1.988 |
Neg logit contributions | |
acebook | -1.171 |
phabet | -1.168 |
utherland | -1.153 |
Civil | -1.031 |
FontSize | -0.987 |
Token | N |
Token ID | 45 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
�� | +3.101 |
�� | +2.795 |
�� | +2.614 |
�� | +2.382 |
�� | +2.355 |
Neg logit contributions | |
phabet | -1.326 |
acebook | -1.321 |
utherland | -1.308 |
Civil | -1.154 |
FontSize | -1.096 |
Token | os |
Token ID | 418 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
acebook | +1.106 |
phabet | +1.097 |
utherland | +1.077 |
Civil | +0.941 |
FontSize | +0.834 |
Neg logit contributions | |
�� | -4.439 |
�� | -4.060 |
�� | -3.839 |
�� | -3.552 |
�� | -3.513 |
Token | relations |
Token ID | 2316 |
Feature activation | +8.23e+00 |
Pos logit contributions | |
�� | +8.448 |
�� | +7.622 |
�� | +7.081 |
�� | +6.464 |
�� | +6.334 |
Neg logit contributions | |
phabet | -3.775 |
acebook | -3.772 |
utherland | -3.726 |
Civil | -3.307 |
FontSize | -3.239 |
Token | diplomat |
Token ID | 28278 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
�� | +11.916 |
�� | +10.735 |
�� | +9.998 |
�� | +9.122 |
�� | +8.968 |
Neg logit contributions | |
phabet | -5.505 |
utherland | -5.452 |
acebook | -5.444 |
FontSize | -4.576 |
sung | -4.550 |
Token | iques |
Token ID | 6368 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
�� | +7.037 |
�� | +6.357 |
�� | +5.941 |
�� | +5.406 |
�� | +5.359 |
Neg logit contributions | |
acebook | -2.814 |
phabet | -2.812 |
utherland | -2.775 |
Civil | -2.433 |
FontSize | -2.316 |
Token | a |
Token ID | 257 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
�� | +3.153 |
�� | +2.845 |
�� | +2.655 |
�� | +2.421 |
�� | +2.382 |
Neg logit contributions | |
acebook | -1.396 |
phabet | -1.394 |
utherland | -1.381 |
Civil | -1.225 |
FontSize | -1.171 |
Token | vec |
Token ID | 35138 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
�� | +18.007 |
�� | +16.173 |
�� | +14.863 |
�� | +13.528 |
�� | +13.391 |
Neg logit contributions | |
acebook | -9.195 |
phabet | -8.966 |
utherland | -8.863 |
FontSize | -7.707 |
Civil | -7.619 |
Token | e |
Token ID | 304 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
�� | +6.039 |
�� | +5.433 |
�� | +5.058 |
�� | +4.595 |
�� | +4.529 |
Neg logit contributions | |
acebook | -2.810 |
phabet | -2.805 |
utherland | -2.779 |
Civil | -2.431 |
FontSize | -2.377 |
Token | ux |
Token ID | 2821 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
�� | +10.484 |
�� | +9.452 |
�� | +8.716 |
�� | +8.017 |
�� | +7.877 |
Neg logit contributions | |
acebook | -4.583 |
phabet | -4.490 |
utherland | -4.430 |
Civil | -4.041 |
FontSize | -3.798 |
Token | s |
Token ID | 264 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
acebook | +0.330 |
phabet | +0.329 |
utherland | +0.326 |
Civil | +0.299 |
FontSize | +0.279 |
Neg logit contributions | |
�� | -0.733 |
�� | -0.659 |
�� | -0.617 |
�� | -0.563 |
�� | -0.554 |
Token | ont |
Token ID | 756 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
�� | +3.164 |
�� | +2.832 |
�� | +2.628 |
�� | +2.387 |
�� | +2.351 |
Neg logit contributions | |
acebook | -1.650 |
phabet | -1.647 |
utherland | -1.618 |
Civil | -1.494 |
FontSize | -1.425 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
�� | +0.897 |
�� | +0.805 |
�� | +0.754 |
�� | +0.685 |
�� | +0.681 |
Neg logit contributions | |
acebook | -0.384 |
phabet | -0.379 |
utherland | -0.372 |
Civil | -0.330 |
FontSize | -0.309 |
Token | That |
Token ID | 2504 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
�� | +2.041 |
�� | +1.829 |
�� | +1.709 |
�� | +1.555 |
�� | +1.532 |
Neg logit contributions | |
acebook | -0.950 |
phabet | -0.939 |
utherland | -0.930 |
Civil | -0.843 |
FontSize | -0.780 |
Token | seems |
Token ID | 2331 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
�� | +4.283 |
�� | +3.837 |
�� | +3.579 |
�� | +3.272 |
�� | +3.225 |
Neg logit contributions | |
phabet | -1.958 |
acebook | -1.939 |
utherland | -1.932 |
Civil | -1.706 |
FontSize | -1.642 |
Token | to |
Token ID | 284 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
�� | +4.334 |
�� | +3.905 |
�� | +3.623 |
�� | +3.333 |
�� | +3.262 |
Neg logit contributions | |
acebook | -1.945 |
phabet | -1.937 |
utherland | -1.920 |
Civil | -1.686 |
FontSize | -1.611 |
Token | be |
Token ID | 307 |
Feature activation | +8.10e+00 |
Pos logit contributions | |
�� | +5.234 |
�� | +4.735 |
�� | +4.415 |
�� | +4.041 |
�� | +3.995 |
Neg logit contributions | |
acebook | -2.263 |
phabet | -2.256 |
utherland | -2.237 |
Civil | -1.971 |
FontSize | -1.889 |
Token | the |
Token ID | 262 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
�� | +11.404 |
�� | +10.263 |
�� | +9.398 |
�� | +8.493 |
�� | +8.447 |
Neg logit contributions | |
acebook | -6.018 |
phabet | -5.969 |
utherland | -5.916 |
Civil | -5.030 |
FontSize | -5.027 |
Token | case |
Token ID | 1339 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
�� | +17.456 |
�� | +15.575 |
�� | +14.235 |
�� | +12.837 |
�� | +12.730 |
Neg logit contributions | |
phabet | -9.930 |
acebook | -9.876 |
utherland | -9.606 |
FontSize | -8.387 |
sung | -8.090 |
Token | with |
Token ID | 351 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
�� | +4.612 |
�� | +4.137 |
�� | +3.866 |
�� | +3.508 |
�� | +3.495 |
Neg logit contributions | |
acebook | -1.999 |
phabet | -1.984 |
utherland | -1.969 |
Civil | -1.733 |
FontSize | -1.665 |
Token | University |
Token ID | 2059 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
�� | +4.654 |
�� | +4.179 |
�� | +3.885 |
�� | +3.541 |
�� | +3.488 |
Neg logit contributions | |
phabet | -2.181 |
acebook | -2.181 |
utherland | -2.142 |
Civil | -1.908 |
FontSize | -1.857 |
Token | of |
Token ID | 286 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
�� | +4.865 |
�� | +4.345 |
�� | +4.052 |
�� | +3.664 |
�� | +3.630 |
Neg logit contributions | |
phabet | -2.203 |
acebook | -2.181 |
utherland | -2.167 |
Civil | -1.917 |
FontSize | -1.877 |
Token | Ottawa |
Token ID | 14074 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
�� | +2.648 |
�� | +2.367 |
�� | +2.198 |
�� | +1.996 |
�� | +1.973 |
Neg logit contributions | |
phabet | -1.334 |
acebook | -1.332 |
utherland | -1.315 |
Civil | -1.175 |
FontSize | -1.136 |
Token | , |
Token ID | 11 |
Feature activation | +8.90e+00 |
Pos logit contributions | |
�� | +5.176 |
�� | +4.620 |
�� | +4.308 |
�� | +3.816 |
�� | +3.809 |
Neg logit contributions | |
acebook | -3.105 |
phabet | -3.080 |
utherland | -3.052 |
FontSize | -2.744 |
Civil | -2.709 |
Token | The |
Token ID | 383 |
Feature activation | +9.75e+00 |
Pos logit contributions | |
�� | +11.718 |
�� | +10.257 |
�� | +9.706 |
�� | +8.546 |
�� | +8.453 |
Neg logit contributions | |
phabet | -7.103 |
acebook | -7.066 |
utherland | -6.952 |
FontSize | -6.324 |
sung | -5.901 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
�� | +13.856 |
�� | +12.466 |
�� | +11.746 |
�� | +10.607 |
�� | +10.325 |
Neg logit contributions | |
phabet | -6.823 |
acebook | -6.592 |
utherland | -6.429 |
FontSize | -5.885 |
sung | -5.438 |
Token | 2 |
Token ID | 362 |
Feature activation | +8.97e+00 |
Pos logit contributions | |
�� | +9.807 |
�� | +8.853 |
�� | +8.290 |
�� | +7.390 |
�� | +7.358 |
Neg logit contributions | |
acebook | -5.404 |
utherland | -5.308 |
phabet | -5.201 |
FontSize | -4.785 |
Civil | -4.521 |
Token | of |
Token ID | 286 |
Feature activation | +9.79e+00 |
Pos logit contributions | |
�� | +11.679 |
�� | +10.298 |
�� | +9.654 |
�� | +8.507 |
�� | +8.482 |
Neg logit contributions | |
acebook | -7.363 |
utherland | -6.935 |
phabet | -6.776 |
FontSize | -6.444 |
sung | -6.168 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
�� | +11.363 |
�� | +9.998 |
�� | +9.092 |
�� | +8.258 |
�� | +7.918 |
Neg logit contributions | |
acebook | -9.066 |
phabet | -8.750 |
utherland | -8.633 |
FontSize | -7.683 |
rift | -7.589 |
Token | Photo |
Token ID | 5555 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
�� | +16.190 |
�� | +14.385 |
�� | +13.353 |
�� | +12.112 |
�� | +11.844 |
Neg logit contributions | |
acebook | -10.155 |
utherland | -9.787 |
phabet | -9.703 |
FontSize | -9.240 |
sung | -8.587 |
Token | : |
Token ID | 25 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
�� | +1.682 |
�� | +1.507 |
�� | +1.411 |
�� | +1.270 |
�� | +1.269 |
Neg logit contributions | |
acebook | -0.795 |
phabet | -0.778 |
utherland | -0.767 |
Civil | -0.689 |
FontSize | -0.655 |
Token | Le |
Token ID | 1004 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
�� | +6.373 |
�� | +5.719 |
�� | +5.350 |
�� | +4.803 |
�� | +4.798 |
Neg logit contributions | |
phabet | -2.896 |
acebook | -2.894 |
utherland | -2.872 |
Civil | -2.452 |
FontSize | -2.434 |
Token | a |
Token ID | 64 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
�� | +6.241 |
�� | +5.530 |
�� | +5.202 |
�� | +4.663 |
�� | +4.648 |
Neg logit contributions | |
acebook | -3.133 |
utherland | -3.040 |
phabet | -3.038 |
Civil | -2.677 |
FontSize | -2.607 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
acebook | +0.323 |
phabet | +0.320 |
utherland | +0.315 |
Civil | +0.263 |
FontSize | +0.230 |
Neg logit contributions | |
�� | -1.581 |
�� | -1.448 |
�� | -1.372 |
�� | -1.275 |
�� | -1.261 |
Token | s |
Token ID | 82 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
phabet | +2.013 |
acebook | +1.992 |
utherland | +1.971 |
Civil | +1.809 |
sung | +1.693 |
Neg logit contributions | |
�� | -4.397 |
�� | -3.946 |
�� | -3.709 |
�� | -3.378 |
�� | -3.329 |
Token | functions |
Token ID | 5499 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
acebook | +2.573 |
phabet | +2.572 |
utherland | +2.568 |
Civil | +2.397 |
FontSize | +2.198 |
Neg logit contributions | |
�� | -5.399 |
�� | -4.856 |
�� | -4.540 |
�� | -4.137 |
�� | -4.078 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
phabet | +1.222 |
acebook | +1.221 |
utherland | +1.210 |
Civil | +1.104 |
sung | +1.018 |
Neg logit contributions | |
�� | -3.040 |
�� | -2.750 |
�� | -2.576 |
�� | -2.367 |
�� | -2.325 |
Token | as |
Token ID | 355 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
�� | +1.654 |
�� | +1.492 |
�� | +1.395 |
�� | +1.272 |
�� | +1.251 |
Neg logit contributions | |
acebook | -0.719 |
phabet | -0.712 |
utherland | -0.707 |
Civil | -0.640 |
FontSize | -0.602 |
Token | was |
Token ID | 373 |
Feature activation | +9.26e+00 |
Pos logit contributions | |
�� | +2.285 |
�� | +2.050 |
�� | +1.902 |
�� | +1.736 |
�� | +1.697 |
Neg logit contributions | |
acebook | -1.140 |
phabet | -1.128 |
utherland | -1.119 |
Civil | -1.018 |
FontSize | -0.973 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
�� | +12.653 |
�� | +11.231 |
�� | +10.216 |
�� | +9.331 |
�� | +9.238 |
Neg logit contributions | |
acebook | -7.080 |
utherland | -6.991 |
phabet | -6.966 |
Civil | -6.080 |
FontSize | -5.974 |
Token | case |
Token ID | 1339 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
�� | +15.437 |
�� | +13.520 |
�� | +12.176 |
�� | +10.694 |
�� | +10.573 |
Neg logit contributions | |
acebook | -11.394 |
phabet | -11.289 |
utherland | -11.216 |
FontSize | -9.822 |
sung | -9.494 |
Token | with |
Token ID | 351 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
�� | +3.933 |
�� | +3.529 |
�� | +3.314 |
�� | +3.017 |
�� | +2.983 |
Neg logit contributions | |
acebook | -1.615 |
phabet | -1.601 |
utherland | -1.588 |
Civil | -1.416 |
FontSize | -1.342 |
Token | this |
Token ID | 428 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
�� | +2.401 |
�� | +2.157 |
�� | +2.013 |
�� | +1.834 |
�� | +1.801 |
Neg logit contributions | |
acebook | -1.136 |
phabet | -1.129 |
utherland | -1.121 |
Civil | -1.015 |
FontSize | -0.963 |
Token | study |
Token ID | 2050 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
acebook | +0.453 |
phabet | +0.452 |
utherland | +0.448 |
Civil | +0.415 |
FontSize | +0.391 |
Neg logit contributions | |
�� | -0.832 |
�� | -0.743 |
�� | -0.691 |
�� | -0.626 |
�� | -0.615 |
Token | of |
Token ID | 286 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
�� | +1.141 |
�� | +1.028 |
�� | +0.965 |
�� | +0.878 |
�� | +0.866 |
Neg logit contributions | |
acebook | -0.489 |
phabet | -0.484 |
utherland | -0.480 |
Civil | -0.432 |
FontSize | -0.408 |
Token | short |
Token ID | 1790 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
�� | +0.355 |
�� | +0.320 |
�� | +0.300 |
�� | +0.274 |
�� | +0.270 |
Neg logit contributions | |
acebook | -0.152 |
phabet | -0.152 |
utherland | -0.150 |
Civil | -0.137 |
FontSize | -0.128 |
Token | limit |
Token ID | 4179 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
�� | +5.577 |
�� | +4.890 |
�� | +4.504 |
�� | +3.937 |
�� | +3.925 |
Neg logit contributions | |
acebook | -3.939 |
phabet | -3.847 |
utherland | -3.800 |
Civil | -3.440 |
FontSize | -3.375 |
Token | : |
Token ID | 25 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
�� | +0.352 |
�� | +0.315 |
�� | +0.295 |
�� | +0.266 |
�� | +0.266 |
Neg logit contributions | |
acebook | -0.163 |
phabet | -0.161 |
utherland | -0.159 |
Civil | -0.143 |
FontSize | -0.134 |
Token | 7 |
Token ID | 22 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
acebook | +2.393 |
utherland | +2.366 |
phabet | +2.348 |
Civil | +2.169 |
FontSize | +1.993 |
Neg logit contributions | |
�� | -6.653 |
�� | -6.071 |
�� | -5.665 |
�� | -5.291 |
�� | -5.132 |
Token | R |
Token ID | 371 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
�� | +2.191 |
�� | +1.978 |
�� | +1.856 |
�� | +1.690 |
�� | +1.670 |
Neg logit contributions | |
acebook | -0.936 |
phabet | -0.930 |
utherland | -0.927 |
Civil | -0.823 |
FontSize | -0.783 |
Token | TS |
Token ID | 4694 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
�� | +5.370 |
�� | +4.775 |
�� | +4.471 |
�� | +4.050 |
�� | +4.045 |
Neg logit contributions | |
acebook | -2.437 |
phabet | -2.397 |
utherland | -2.338 |
Civil | -2.126 |
FontSize | -1.984 |
Token | thr |
Token ID | 5636 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
�� | +10.966 |
�� | +8.983 |
�� | +8.191 |
�� | +6.616 |
�� | +6.564 |
Neg logit contributions | |
acebook | -15.165 |
phabet | -14.822 |
utherland | -14.606 |
FontSize | -13.806 |
Civil | -13.211 |
Token | : |
Token ID | 25 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
�� | +10.391 |
�� | +9.010 |
�� | +8.403 |
�� | +7.601 |
�� | +7.382 |
Neg logit contributions | |
acebook | -6.810 |
phabet | -6.476 |
utherland | -6.290 |
Civil | -5.477 |
FontSize | -5.272 |
Token | off |
Token ID | 2364 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
�� | +1.120 |
�� | +1.005 |
�� | +0.938 |
�� | +0.853 |
�� | +0.842 |
Neg logit contributions | |
acebook | -0.535 |
phabet | -0.528 |
utherland | -0.522 |
Civil | -0.476 |
FontSize | -0.448 |
Token | Frag |
Token ID | 24229 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
phabet | +1.477 |
acebook | +1.474 |
utherland | +1.456 |
Civil | +1.348 |
FontSize | +1.245 |
Neg logit contributions | |
�� | -3.347 |
�� | -3.007 |
�� | -2.816 |
�� | -2.577 |
�� | -2.528 |
Token | ment |
Token ID | 434 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
�� | +1.629 |
�� | +1.477 |
�� | +1.389 |
�� | +1.276 |
�� | +1.268 |
Neg logit contributions | |
acebook | -0.528 |
phabet | -0.513 |
utherland | -0.509 |
Civil | -0.447 |
FontSize | -0.414 |
Token | ans |
Token ID | 504 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
�� | +7.071 |
�� | +6.364 |
�� | +6.029 |
�� | +5.545 |
�� | +5.437 |
Neg logit contributions | |
utherland | -2.431 |
phabet | -2.390 |
acebook | -2.373 |
Civil | -2.101 |
FontSize | -2.076 |
Token | ole |
Token ID | 2305 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
�� | +5.787 |
�� | +5.034 |
�� | +4.577 |
�� | +4.096 |
�� | +4.095 |
Neg logit contributions | |
acebook | -5.210 |
phabet | -5.124 |
utherland | -4.963 |
FontSize | -4.577 |
sung | -4.557 |
Token | il |
Token ID | 346 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
�� | +6.238 |
�� | +5.677 |
�� | +5.328 |
�� | +4.940 |
�� | +4.883 |
Neg logit contributions | |
acebook | -1.885 |
phabet | -1.849 |
utherland | -1.848 |
Civil | -1.602 |
FontSize | -1.473 |
Token | - |
Token ID | 12 |
Feature activation | +7.81e+00 |
Pos logit contributions | |
�� | +1.837 |
�� | +1.645 |
�� | +1.536 |
�� | +1.398 |
�� | +1.376 |
Neg logit contributions | |
acebook | -0.903 |
phabet | -0.899 |
utherland | -0.892 |
Civil | -0.811 |
FontSize | -0.773 |
Token | DC |
Token ID | 9697 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
�� | +9.007 |
�� | +7.820 |
�� | +7.251 |
�� | +6.288 |
�� | +6.286 |
Neg logit contributions | |
acebook | -7.913 |
phabet | -7.791 |
utherland | -7.708 |
FontSize | -6.959 |
Civil | -6.939 |
Token | M |
Token ID | 44 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
acebook | +0.170 |
phabet | +0.170 |
utherland | +0.168 |
Civil | +0.158 |
FontSize | +0.148 |
Neg logit contributions | |
�� | -0.304 |
�� | -0.273 |
�� | -0.253 |
�� | -0.229 |
�� | -0.224 |
Token | ) |
Token ID | 8 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
�� | +14.313 |
�� | +11.641 |
�� | +11.327 |
�� | +9.896 |
�� | +9.894 |
Neg logit contributions | |
acebook | -12.202 |
phabet | -12.134 |
utherland | -12.111 |
FontSize | -10.933 |
Civil | -10.628 |
Token | s |
Token ID | 264 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
�� | +4.626 |
�� | +4.184 |
�� | +3.935 |
�� | +3.646 |
�� | +3.571 |
Neg logit contributions | |
acebook | -1.609 |
phabet | -1.609 |
utherland | -1.604 |
Civil | -1.396 |
FontSize | -1.335 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
�� | +0.785 |
�� | +0.703 |
�� | +0.657 |
�� | +0.595 |
�� | +0.595 |
Neg logit contributions | |
acebook | -0.355 |
phabet | -0.348 |
utherland | -0.341 |
Civil | -0.306 |
FontSize | -0.287 |
Token | t |
Token ID | 83 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
�� | +3.008 |
�� | +2.693 |
�� | +2.510 |
�� | +2.271 |
�� | +2.271 |
Neg logit contributions | |
acebook | -1.380 |
phabet | -1.344 |
utherland | -1.321 |
Civil | -1.192 |
FontSize | -1.122 |
Token | . |
Token ID | 13 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
�� | +7.421 |
�� | +6.489 |
�� | +5.988 |
�� | +5.499 |
�� | +5.407 |
Neg logit contributions | |
acebook | -4.371 |
phabet | -4.213 |
utherland | -4.048 |
Civil | -3.493 |
FontSize | -3.458 |
Token | _ |
Token ID | 62 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
�� | +11.742 |
�� | +10.484 |
�� | +9.827 |
�� | +8.852 |
�� | +8.769 |
Neg logit contributions | |
acebook | -5.419 |
phabet | -5.362 |
utherland | -5.154 |
Civil | -4.991 |
FontSize | -4.722 |
Token | k |
Token ID | 74 |
Feature activation | +8.07e+00 |
Pos logit contributions | |
�� | +8.068 |
�� | +7.232 |
�� | +6.802 |
�� | +6.203 |
�� | +6.132 |
Neg logit contributions | |
acebook | -3.308 |
phabet | -3.246 |
utherland | -3.194 |
Civil | -3.005 |
FontSize | -2.792 |
Token | 10 |
Token ID | 940 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
�� | +11.973 |
�� | +10.671 |
�� | +9.991 |
�� | +9.124 |
�� | +8.977 |
Neg logit contributions | |
acebook | -5.029 |
phabet | -4.997 |
utherland | -4.743 |
Civil | -4.587 |
FontSize | -4.408 |
Token | > |
Token ID | 29 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
acebook | +0.241 |
phabet | +0.240 |
utherland | +0.237 |
Civil | +0.212 |
FontSize | +0.194 |
Neg logit contributions | |
�� | -0.738 |
�� | -0.670 |
�� | -0.631 |
�� | -0.581 |
�� | -0.573 |
Token | ke |
Token ID | 885 |
Feature activation | +7.89e+00 |
Pos logit contributions | |
�� | +5.245 |
�� | +4.717 |
�� | +4.385 |
�� | +4.008 |
�� | +3.951 |
Neg logit contributions | |
acebook | -2.406 |
phabet | -2.391 |
utherland | -2.376 |
Civil | -2.112 |
FontSize | -2.055 |
Token | k |
Token ID | 74 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
�� | +11.241 |
�� | +10.001 |
�� | +9.336 |
�� | +8.512 |
�� | +8.429 |
Neg logit contributions | |
phabet | -5.529 |
acebook | -5.454 |
utherland | -5.373 |
Civil | -4.935 |
FontSize | -4.819 |
Token | m |
Token ID | 285 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
�� | +16.591 |
�� | +14.686 |
�� | +13.686 |
�� | +12.416 |
�� | +12.268 |
Neg logit contributions | |
acebook | -9.266 |
phabet | -9.068 |
utherland | -9.064 |
FontSize | -8.132 |
Civil | -7.952 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
�� | +9.019 |
�� | +8.119 |
�� | +7.461 |
�� | +6.705 |
�� | +6.655 |
Neg logit contributions | |
utherland | -5.128 |
acebook | -5.112 |
phabet | -5.073 |
Civil | -4.622 |
FontSize | -4.579 |
Token | k |
Token ID | 74 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
�� | +7.283 |
�� | +6.378 |
�� | +5.861 |
�� | +5.275 |
�� | +5.199 |
Neg logit contributions | |
acebook | -4.963 |
phabet | -4.873 |
utherland | -4.817 |
Civil | -4.400 |
FontSize | -4.362 |
Token | [ |
Token ID | 685 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
�� | +8.383 |
�� | +7.494 |
�� | +6.903 |
�� | +6.244 |
�� | +6.118 |
Neg logit contributions | |
phabet | -5.148 |
acebook | -5.136 |
utherland | -5.112 |
Civil | -4.657 |
FontSize | -4.570 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
phabet | +1.314 |
acebook | +1.312 |
utherland | +1.302 |
Civil | +1.188 |
FontSize | +1.105 |
Neg logit contributions | |
�� | -3.276 |
�� | -2.961 |
�� | -2.779 |
�� | -2.550 |
�� | -2.505 |
Token | 25 |
Token ID | 1495 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
acebook | +0.553 |
phabet | +0.552 |
utherland | +0.544 |
Civil | +0.492 |
FontSize | +0.459 |
Neg logit contributions | |
�� | -1.304 |
�� | -1.174 |
�� | -1.100 |
�� | -1.003 |
�� | -0.992 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
�� | +5.884 |
�� | +5.212 |
�� | +4.861 |
�� | +4.345 |
�� | +4.340 |
Neg logit contributions | |
phabet | -3.586 |
acebook | -3.560 |
utherland | -3.508 |
Civil | -3.149 |
FontSize | -3.098 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
�� | +0.274 |
�� | +0.246 |
�� | +0.231 |
�� | +0.210 |
�� | +0.208 |
Neg logit contributions | |
acebook | -0.120 |
phabet | -0.120 |
utherland | -0.118 |
Civil | -0.107 |
FontSize | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
�� | +2.704 |
�� | +2.431 |
�� | +2.281 |
�� | +2.076 |
�� | +2.054 |
Neg logit contributions | |
acebook | -1.188 |
phabet | -1.182 |
utherland | -1.168 |
Civil | -1.052 |
FontSize | -1.003 |
Token | Mos |
Token ID | 5826 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
acebook | +0.291 |
phabet | +0.290 |
utherland | +0.288 |
Civil | +0.264 |
FontSize | +0.246 |
Neg logit contributions | |
�� | -0.639 |
�� | -0.575 |
�� | -0.537 |
�� | -0.491 |
�� | -0.482 |
Token | k |
Token ID | 74 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
�� | +5.107 |
�� | +4.574 |
�� | +4.246 |
�� | +3.853 |
�� | +3.829 |
Neg logit contributions | |
acebook | -2.401 |
phabet | -2.379 |
utherland | -2.369 |
Civil | -2.151 |
FontSize | -2.072 |
Token | owitz |
Token ID | 20951 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
�� | +16.863 |
�� | +14.922 |
�� | +14.204 |
�� | +12.853 |
�� | +12.618 |
Neg logit contributions | |
acebook | -9.393 |
utherland | -8.636 |
phabet | -8.582 |
FontSize | -8.086 |
Civil | -7.613 |
Token | H |
Token ID | 367 |
Feature activation | +6.70e+00 |
Pos logit contributions | |
�� | +3.295 |
�� | +2.955 |
�� | +2.776 |
�� | +2.530 |
�� | +2.496 |
Neg logit contributions | |
acebook | -1.437 |
phabet | -1.422 |
utherland | -1.399 |
Civil | -1.250 |
FontSize | -1.206 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
�� | +9.304 |
�� | +8.260 |
�� | +7.788 |
�� | +7.012 |
�� | +6.940 |
Neg logit contributions | |
acebook | -5.109 |
phabet | -5.085 |
utherland | -5.019 |
Civil | -4.494 |
FontSize | -4.445 |
Token | Fi |
Token ID | 23238 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
�� | +1.617 |
�� | +1.454 |
�� | +1.364 |
�� | +1.245 |
�� | +1.228 |
Neg logit contributions | |
acebook | -0.692 |
phabet | -0.692 |
utherland | -0.681 |
Civil | -0.614 |
FontSize | -0.583 |
Token | ore |
Token ID | 382 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
phabet | +1.606 |
acebook | +1.595 |
utherland | +1.581 |
Civil | +1.454 |
FontSize | +1.351 |
Neg logit contributions | |
�� | -3.364 |
�� | -3.020 |
�� | -2.835 |
�� | -2.580 |
�� | -2.540 |
Token | of |
Token ID | 286 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
�� | +10.168 |
�� | +9.143 |
�� | +8.119 |
�� | +7.557 |
�� | +7.419 |
Neg logit contributions | |
acebook | -5.948 |
phabet | -5.915 |
utherland | -5.556 |
rift | -5.139 |
sung | -5.070 |
Token | books |
Token ID | 3835 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
�� | +12.596 |
�� | +11.364 |
�� | +10.029 |
�� | +9.495 |
�� | +8.978 |
Neg logit contributions | |
phabet | -8.461 |
acebook | -8.160 |
utherland | -8.089 |
FontSize | -7.598 |
romeda | -7.232 |
Token | , |
Token ID | 11 |
Feature activation | +9.73e+00 |
Pos logit contributions | |
�� | +12.402 |
�� | +10.484 |
�� | +9.331 |
�� | +8.872 |
�� | +8.792 |
Neg logit contributions | |
acebook | -10.335 |
utherland | -10.062 |
phabet | -9.592 |
FontSize | -9.074 |
sung | -8.747 |
Token | which |
Token ID | 543 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
�� | +13.085 |
�� | +10.801 |
�� | +9.886 |
�� | +9.127 |
�� | +9.111 |
Neg logit contributions | |
acebook | -7.866 |
phabet | -7.693 |
utherland | -7.625 |
rift | -6.924 |
ieth | -6.711 |
Token | you |
Token ID | 345 |
Feature activation | +9.81e+00 |
Pos logit contributions | |
�� | +15.943 |
�� | +13.996 |
�� | +13.197 |
�� | +11.544 |
�� | +11.208 |
Neg logit contributions | |
acebook | -11.732 |
sung | -11.075 |
rift | -10.968 |
phabet | -10.913 |
FontSize | -10.667 |
Token | might |
Token ID | 1244 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
�� | +11.989 |
�� | +9.484 |
�� | +8.731 |
�� | +8.324 |
�� | +8.305 |
Neg logit contributions | |
acebook | -9.272 |
phabet | -9.119 |
utherland | -8.380 |
FontSize | -7.862 |
uay | -7.849 |
Token | want |
Token ID | 765 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
�� | +15.484 |
�� | +13.199 |
�� | +11.524 |
�� | +10.891 |
�� | +10.765 |
Neg logit contributions | |
acebook | -11.767 |
phabet | -10.740 |
utherland | -10.510 |
rift | -9.578 |
FontSize | -9.571 |
Token | to |
Token ID | 284 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
�� | +6.912 |
�� | +6.126 |
�� | +5.615 |
�� | +5.077 |
�� | +5.002 |
Neg logit contributions | |
acebook | -3.678 |
phabet | -3.492 |
utherland | -3.412 |
Civil | -3.075 |
FontSize | -3.038 |
Token | per |
Token ID | 583 |
Feature activation | +9.76e+00 |
Pos logit contributions | |
�� | +8.792 |
�� | +7.822 |
�� | +7.251 |
�� | +6.620 |
�� | +6.405 |
Neg logit contributions | |
acebook | -4.751 |
phabet | -4.672 |
utherland | -4.417 |
FontSize | -4.142 |
heres | -3.982 |
Token | use |
Token ID | 1904 |
Feature activation | +7.97e+00 |
Pos logit contributions | |
�� | +12.109 |
�� | +10.443 |
�� | +9.242 |
�� | +8.587 |
�� | +8.192 |
Neg logit contributions | |
acebook | -9.148 |
phabet | -9.103 |
utherland | -8.900 |
Civil | -8.108 |
FontSize | -7.982 |
Token | . |
Token ID | 13 |
Feature activation | +6.40e+00 |
Pos logit contributions | |
�� | +10.961 |
�� | +9.703 |
�� | +8.788 |
�� | +8.073 |
�� | +8.046 |
Neg logit contributions | |
acebook | -6.143 |
utherland | -5.808 |
phabet | -5.671 |
sung | -5.212 |
FontSize | -5.198 |
Token | the |
Token ID | 262 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
�� | +2.309 |
�� | +2.075 |
�� | +1.941 |
�� | +1.768 |
�� | +1.741 |
Neg logit contributions | |
acebook | -1.035 |
phabet | -1.032 |
utherland | -1.029 |
Civil | -0.922 |
FontSize | -0.873 |
Token | Virtual |
Token ID | 15595 |
Feature activation | +6.68e-03 |
Pos logit contributions | |
�� | +3.677 |
�� | +3.313 |
�� | +3.105 |
�� | +2.833 |
�� | +2.795 |
Neg logit contributions | |
acebook | -1.503 |
phabet | -1.501 |
utherland | -1.492 |
Civil | -1.320 |
FontSize | -1.259 |
Token | Console |
Token ID | 24371 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
�� | +0.009 |
�� | +0.008 |
�� | +0.008 |
�� | +0.007 |
�� | +0.007 |
Neg logit contributions | |
acebook | -0.005 |
phabet | -0.005 |
utherland | -0.005 |
Civil | -0.005 |
FontSize | -0.005 |
Token | service |
Token ID | 2139 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
�� | +4.635 |
�� | +4.029 |
�� | +3.676 |
�� | +3.216 |
�� | +3.133 |
Neg logit contributions | |
acebook | -3.997 |
utherland | -3.934 |
phabet | -3.933 |
Civil | -3.621 |
FontSize | -3.553 |
Token | , |
Token ID | 11 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
�� | +7.312 |
�� | +6.471 |
�� | +6.003 |
�� | +5.348 |
�� | +5.241 |
Neg logit contributions | |
acebook | -4.523 |
utherland | -4.489 |
phabet | -4.302 |
sung | -3.950 |
Civil | -3.930 |
Token | which |
Token ID | 543 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
�� | +5.954 |
�� | +5.247 |
�� | +4.924 |
�� | +4.349 |
�� | +4.276 |
Neg logit contributions | |
acebook | -3.017 |
utherland | -2.912 |
phabet | -2.876 |
FontSize | -2.563 |
Civil | -2.560 |
Token | brings |
Token ID | 6774 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
�� | +16.142 |
�� | +14.238 |
�� | +13.406 |
�� | +11.687 |
�� | +11.533 |
Neg logit contributions | |
acebook | -9.751 |
utherland | -8.877 |
phabet | -8.867 |
sung | -8.856 |
FontSize | -8.357 |
Token | you |
Token ID | 345 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
�� | +2.029 |
�� | +1.822 |
�� | +1.699 |
�� | +1.543 |
�� | +1.519 |
Neg logit contributions | |
acebook | -0.955 |
phabet | -0.937 |
utherland | -0.936 |
Civil | -0.842 |
FontSize | -0.805 |
Token | great |
Token ID | 1049 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
�� | +7.830 |
�� | +6.792 |
�� | +6.289 |
�� | +5.666 |
�� | +5.548 |
Neg logit contributions | |
acebook | -4.666 |
phabet | -4.623 |
utherland | -4.617 |
FontSize | -4.162 |
Civil | -4.119 |
Token | games |
Token ID | 1830 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
�� | +5.556 |
�� | +4.852 |
�� | +4.569 |
�� | +4.046 |
�� | +3.948 |
Neg logit contributions | |
acebook | -3.239 |
phabet | -3.137 |
utherland | -3.074 |
FontSize | -2.880 |
Civil | -2.763 |
Token | created |
Token ID | 2727 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
�� | +3.812 |
�� | +3.430 |
�� | +3.294 |
�� | +2.961 |
�� | +2.960 |
Neg logit contributions | |
acebook | -1.299 |
phabet | -1.246 |
utherland | -1.220 |
Civil | -0.987 |
rift | -0.971 |
Token | of |
Token ID | 286 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
acebook | +1.003 |
phabet | +1.001 |
utherland | +0.992 |
Civil | +0.914 |
FontSize | +0.855 |
Neg logit contributions | |
�� | -2.079 |
�� | -1.867 |
�� | -1.743 |
�� | -1.588 |
�� | -1.561 |
Token | z |
Token ID | 1976 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
acebook | +0.536 |
phabet | +0.535 |
utherland | +0.531 |
Civil | +0.491 |
FontSize | +0.461 |
Neg logit contributions | |
�� | -1.017 |
�� | -0.909 |
�� | -0.847 |
�� | -0.769 |
�� | -0.756 |
Token | uc |
Token ID | 1229 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
�� | +2.700 |
�� | +2.431 |
�� | +2.276 |
�� | +2.089 |
�� | +2.066 |
Neg logit contributions | |
acebook | -1.033 |
phabet | -1.030 |
utherland | -1.013 |
Civil | -0.918 |
FontSize | -0.866 |
Token | chini |
Token ID | 45045 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
�� | +1.716 |
�� | +1.550 |
�� | +1.454 |
�� | +1.333 |
�� | +1.323 |
Neg logit contributions | |
acebook | -0.598 |
phabet | -0.592 |
utherland | -0.584 |
Civil | -0.523 |
FontSize | -0.489 |
Token | in |
Token ID | 287 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
�� | +2.027 |
�� | +1.819 |
�� | +1.700 |
�� | +1.543 |
�� | +1.525 |
Neg logit contributions | |
acebook | -0.959 |
phabet | -0.947 |
utherland | -0.940 |
Civil | -0.850 |
FontSize | -0.813 |
Token | my |
Token ID | 616 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
�� | +7.498 |
�� | +6.692 |
�� | +6.171 |
�� | +5.657 |
�� | +5.602 |
Neg logit contributions | |
acebook | -3.915 |
phabet | -3.860 |
utherland | -3.856 |
Civil | -3.421 |
FontSize | -3.318 |
Token | kitchen |
Token ID | 9592 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
�� | +16.153 |
�� | +14.375 |
�� | +13.217 |
�� | +12.041 |
�� | +11.882 |
Neg logit contributions | |
acebook | -9.165 |
utherland | -8.842 |
phabet | -8.811 |
FontSize | -7.525 |
sung | -7.356 |
Token | ! |
Token ID | 0 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
�� | +3.434 |
�� | +3.093 |
�� | +2.888 |
�� | +2.635 |
�� | +2.604 |
Neg logit contributions | |
acebook | -1.490 |
phabet | -1.469 |
utherland | -1.459 |
Civil | -1.310 |
FontSize | -1.242 |
Token | — |
Token ID | 851 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
�� | +6.424 |
�� | +5.736 |
�� | +5.356 |
�� | +4.857 |
�� | +4.804 |
Neg logit contributions | |
acebook | -2.975 |
phabet | -2.943 |
utherland | -2.940 |
Civil | -2.574 |
FontSize | -2.488 |
Token | K |
Token ID | 42 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
�� | +5.854 |
�� | +5.286 |
�� | +4.955 |
�� | +4.500 |
�� | +4.443 |
Neg logit contributions | |
acebook | -2.528 |
utherland | -2.501 |
phabet | -2.492 |
Civil | -2.223 |
FontSize | -2.108 |
Token | el |
Token ID | 417 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
�� | +0.954 |
�� | +0.854 |
�� | +0.795 |
�� | +0.722 |
�� | +0.708 |
Neg logit contributions | |
acebook | -0.498 |
phabet | -0.496 |
utherland | -0.492 |
Civil | -0.453 |
FontSize | -0.429 |
Token | + |
Token ID | 10 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
phabet | +3.120 |
acebook | +3.120 |
utherland | +3.058 |
Civil | +2.822 |
FontSize | +2.618 |
Neg logit contributions | |
�� | -9.275 |
�� | -8.421 |
�� | -7.919 |
�� | -7.300 |
�� | -7.238 |
Token | Soul |
Token ID | 8653 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
�� | +1.922 |
�� | +1.722 |
�� | +1.611 |
�� | +1.469 |
�� | +1.444 |
Neg logit contributions | |
phabet | -0.896 |
acebook | -0.894 |
utherland | -0.888 |
Civil | -0.792 |
FontSize | -0.758 |
Token | ful |
Token ID | 913 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
�� | +4.519 |
�� | +4.043 |
�� | +3.745 |
�� | +3.402 |
�� | +3.305 |
Neg logit contributions | |
acebook | -2.524 |
phabet | -2.504 |
utherland | -2.489 |
Civil | -2.244 |
FontSize | -2.173 |
Token | , |
Token ID | 11 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
�� | +1.976 |
�� | +1.766 |
�� | +1.642 |
�� | +1.488 |
�� | +1.456 |
Neg logit contributions | |
acebook | -1.073 |
phabet | -1.072 |
utherland | -1.067 |
Civil | -0.974 |
FontSize | -0.931 |
Token | Trans |
Token ID | 3602 |
Feature activation | +9.73e+00 |
Pos logit contributions | |
�� | +4.987 |
�� | +4.454 |
�� | +4.168 |
�� | +3.800 |
�� | +3.734 |
Neg logit contributions | |
phabet | -2.354 |
acebook | -2.337 |
utherland | -2.331 |
Civil | -2.014 |
FontSize | -1.977 |
Token | cend |
Token ID | 15695 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
�� | +13.231 |
�� | +11.619 |
�� | +10.868 |
�� | +9.720 |
�� | +9.537 |
Neg logit contributions | |
utherland | -7.390 |
phabet | -7.262 |
acebook | -7.217 |
FontSize | -6.542 |
Civil | -6.461 |
Token | ental |
Token ID | 2470 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
�� | +13.370 |
�� | +11.814 |
�� | +10.568 |
�� | +9.473 |
�� | +9.311 |
Neg logit contributions | |
phabet | -11.364 |
utherland | -11.215 |
acebook | -10.731 |
FontSize | -10.519 |
Civil | -9.976 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
�� | +4.287 |
�� | +3.836 |
�� | +3.566 |
�� | +3.235 |
�� | +3.176 |
Neg logit contributions | |
phabet | -2.255 |
acebook | -2.253 |
utherland | -2.248 |
Civil | -2.003 |
FontSize | -1.945 |
Token | Kn |
Token ID | 6102 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
�� | +2.539 |
�� | +2.274 |
�� | +2.128 |
�� | +1.943 |
�� | +1.910 |
Neg logit contributions | |
phabet | -1.170 |
acebook | -1.167 |
utherland | -1.159 |
Civil | -1.029 |
FontSize | -0.988 |
Token | ows |
Token ID | 1666 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
acebook | +3.559 |
phabet | +3.496 |
utherland | +3.474 |
Civil | +3.213 |
sung | +3.022 |
Neg logit contributions | |
�� | -6.560 |
�� | -5.873 |
�� | -5.478 |
�� | -4.964 |
�� | -4.862 |
Token | value |
Token ID | 1988 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
acebook | +0.806 |
phabet | +0.803 |
utherland | +0.794 |
Civil | +0.732 |
FontSize | +0.681 |
Neg logit contributions | |
�� | -1.729 |
�� | -1.554 |
�� | -1.452 |
�� | -1.326 |
�� | -1.304 |
Token | " |
Token ID | 366 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
acebook | +2.776 |
phabet | +2.767 |
utherland | +2.740 |
Civil | +2.560 |
sung | +2.319 |
Neg logit contributions | |
�� | -6.885 |
�� | -6.259 |
�� | -5.825 |
�� | -5.338 |
�� | -5.245 |
Token | ra |
Token ID | 430 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
�� | +5.323 |
�� | +4.765 |
�� | +4.498 |
�� | +4.119 |
�� | +4.012 |
Neg logit contributions | |
acebook | -2.320 |
utherland | -2.272 |
phabet | -2.267 |
Civil | -2.078 |
FontSize | -1.930 |
Token | i |
Token ID | 72 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
acebook | +0.059 |
phabet | +0.059 |
utherland | +0.059 |
Civil | +0.053 |
FontSize | +0.050 |
Neg logit contributions | |
�� | -0.145 |
�� | -0.131 |
�� | -0.123 |
�� | -0.113 |
�� | -0.111 |
Token | N |
Token ID | 45 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
�� | +2.066 |
�� | +1.852 |
�� | +1.734 |
�� | +1.581 |
�� | +1.555 |
Neg logit contributions | |
acebook | -0.968 |
phabet | -0.962 |
utherland | -0.954 |
Civil | -0.874 |
FontSize | -0.823 |
Token | " |
Token ID | 1 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
�� | +2.429 |
�� | +2.164 |
�� | +2.024 |
�� | +1.839 |
�� | +1.800 |
Neg logit contributions | |
acebook | -1.280 |
phabet | -1.265 |
utherland | -1.265 |
Civil | -1.164 |
FontSize | -1.111 |
Token | D |
Token ID | 360 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
�� | +7.039 |
�� | +6.292 |
�� | +5.927 |
�� | +5.432 |
�� | +5.357 |
Neg logit contributions | |
acebook | -3.027 |
phabet | -3.006 |
utherland | -2.959 |
Civil | -2.608 |
FontSize | -2.574 |
Token | ettel |
Token ID | 47417 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
�� | +16.940 |
�� | +15.046 |
�� | +14.297 |
�� | +12.921 |
�� | +12.854 |
Neg logit contributions | |
phabet | -7.551 |
acebook | -7.436 |
utherland | -7.349 |
Civil | -7.031 |
FontSize | -6.916 |
Token | b |
Token ID | 65 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
phabet | +2.062 |
acebook | +2.056 |
utherland | +2.046 |
Civil | +1.890 |
sung | +1.769 |
Neg logit contributions | |
�� | -4.044 |
�� | -3.632 |
�� | -3.380 |
�� | -3.082 |
�� | -3.019 |
Token | acher |
Token ID | 3493 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
�� | +3.397 |
�� | +3.028 |
�� | +2.823 |
�� | +2.553 |
�� | +2.516 |
Neg logit contributions | |
acebook | -1.818 |
phabet | -1.811 |
utherland | -1.792 |
Civil | -1.658 |
FontSize | -1.581 |
Token | is |
Token ID | 318 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
�� | +1.500 |
�� | +1.352 |
�� | +1.270 |
�� | +1.164 |
�� | +1.146 |
Neg logit contributions | |
acebook | -0.604 |
phabet | -0.602 |
utherland | -0.595 |
Civil | -0.538 |
FontSize | -0.503 |
Token | still |
Token ID | 991 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
�� | +2.413 |
�� | +2.158 |
�� | +2.012 |
�� | +1.839 |
�� | +1.802 |
Neg logit contributions | |
acebook | -1.191 |
phabet | -1.183 |
utherland | -1.175 |
Civil | -1.062 |
FontSize | -1.006 |
Token | content |
Token ID | 2695 |
Feature activation | -8.09e+00 |
Pos logit contributions | |
phabet | +5.121 |
utherland | +5.073 |
acebook | +5.053 |
Civil | +4.728 |
FontSize | +4.327 |
Neg logit contributions | |
�� | -12.004 |
�� | -10.811 |
�� | -10.250 |
�� | -9.424 |
�� | -9.214 |
Token | , |
Token ID | 837 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
utherland | +4.396 |
phabet | +4.357 |
acebook | +4.308 |
Civil | +3.874 |
FontSize | +3.648 |
Neg logit contributions | |
�� | -12.896 |
�� | -11.682 |
�� | -11.017 |
�� | -10.162 |
�� | -10.104 |
Token | ' |
Token ID | 705 |
Feature activation | -9.39e+00 |
Pos logit contributions | |
phabet | +3.578 |
acebook | +3.573 |
utherland | +3.571 |
Civil | +3.325 |
FontSize | +3.026 |
Neg logit contributions | |
�� | -8.741 |
�� | -7.898 |
�� | -7.440 |
�� | -6.829 |
�� | -6.689 |
Token |
|
Token ID | 198 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
phabet | +5.948 |
utherland | +5.872 |
acebook | +5.832 |
Civil | +5.349 |
ro | +5.171 |
Neg logit contributions | |
�� | -13.911 |
�� | -12.382 |
�� | -11.797 |
�� | -10.848 |
�� | -10.774 |
Token |
|
Token ID | 198 |
Feature activation | -8.64e+00 |
Pos logit contributions | |
utherland | +2.865 |
phabet | +2.832 |
acebook | +2.747 |
Civil | +2.681 |
sung | +2.437 |
Neg logit contributions | |
�� | -9.782 |
�� | -8.950 |
�� | -8.516 |
�� | -7.959 |
�� | -7.694 |
Token | ' |
Token ID | 6 |
Feature activation | -1.66e+01 |
Pos logit contributions | |
phabet | +5.282 |
utherland | +5.232 |
acebook | +5.206 |
Civil | +4.713 |
sung | +4.536 |
Neg logit contributions | |
�� | -13.220 |
�� | -11.864 |
�� | -11.241 |
�� | -10.408 |
�� | -10.269 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
utherland | +7.478 |
phabet | +7.345 |
acebook | +7.182 |
Civil | +6.859 |
LINK | +6.419 |
Neg logit contributions | |
�� | -24.973 |
�� | -22.678 |
�� | -21.578 |
�� | -20.168 |
�� | -19.928 |
Token | AS |
Token ID | 7054 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
phabet | +1.932 |
acebook | +1.923 |
utherland | +1.915 |
Civil | +1.763 |
FontSize | +1.607 |
Neg logit contributions | |
�� | -5.029 |
�� | -4.546 |
�� | -4.270 |
�� | -3.938 |
�� | -3.863 |
Token | line |
Token ID | 1627 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
phabet | +2.590 |
acebook | +2.589 |
utherland | +2.582 |
Civil | +2.384 |
FontSize | +2.179 |
Neg logit contributions | |
�� | -6.192 |
�� | -5.557 |
�� | -5.242 |
�� | -4.804 |
�� | -4.717 |
Token | FROM |
Token ID | 16034 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
utherland | +6.392 |
phabet | +6.252 |
acebook | +5.984 |
Civil | +5.701 |
FontSize | +5.118 |
Neg logit contributions | |
�� | -19.196 |
�� | -17.253 |
�� | -16.361 |
�� | -15.293 |
�� | -15.066 |
Token | [ |
Token ID | 685 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
acebook | +0.012 |
phabet | +0.012 |
utherland | +0.012 |
Civil | +0.011 |
FontSize | +0.010 |
Neg logit contributions | |
�� | -0.028 |
�� | -0.025 |
�� | -0.023 |
�� | -0.021 |
�� | -0.021 |
Token | at |
Token ID | 379 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
acebook | +0.417 |
phabet | +0.416 |
utherland | +0.412 |
Civil | +0.376 |
FontSize | +0.350 |
Neg logit contributions | |
�� | -0.993 |
�� | -0.895 |
�� | -0.839 |
�� | -0.768 |
�� | -0.755 |
Token | Five |
Token ID | 10579 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
acebook | +0.422 |
phabet | +0.421 |
utherland | +0.417 |
Civil | +0.382 |
FontSize | +0.354 |
Neg logit contributions | |
�� | -0.992 |
�� | -0.895 |
�� | -0.839 |
�� | -0.767 |
�� | -0.754 |
Token | Corn |
Token ID | 11424 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
acebook | +0.504 |
phabet | +0.502 |
utherland | +0.497 |
Civil | +0.453 |
FontSize | +0.421 |
Neg logit contributions | |
�� | -1.202 |
�� | -1.084 |
�� | -1.016 |
�� | -0.930 |
�� | -0.915 |
Token | ers |
Token ID | 364 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
acebook | +0.596 |
phabet | +0.594 |
utherland | +0.586 |
Civil | +0.526 |
FontSize | +0.490 |
Neg logit contributions | |
�� | -1.638 |
�� | -1.483 |
�� | -1.392 |
�� | -1.281 |
�� | -1.261 |
Token | in |
Token ID | 287 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
�� | +0.079 |
�� | +0.071 |
�� | +0.066 |
�� | +0.061 |
�� | +0.060 |
Neg logit contributions | |
acebook | -0.034 |
phabet | -0.034 |
utherland | -0.033 |
Civil | -0.030 |
FontSize | -0.028 |
Token | Bur |
Token ID | 5481 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
acebook | +0.977 |
phabet | +0.973 |
utherland | +0.967 |
Civil | +0.895 |
FontSize | +0.820 |
Neg logit contributions | |
�� | -2.344 |
�� | -2.117 |
�� | -1.988 |
�� | -1.815 |
�� | -1.785 |
Token | ien |
Token ID | 2013 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
phabet | +8.642 |
acebook | +8.291 |
utherland | +8.288 |
Civil | +8.116 |
ro | +7.961 |
Neg logit contributions | |
�� | -21.789 |
�� | -19.539 |
�� | -18.620 |
�� | -17.497 |
�� | -16.561 |
Token |
|
Token ID | 198 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
phabet | +2.569 |
utherland | +2.520 |
acebook | +2.519 |
Civil | +2.374 |
FontSize | +2.116 |
Neg logit contributions | |
�� | -6.615 |
�� | -5.956 |
�� | -5.602 |
�� | -5.175 |
�� | -5.056 |
Token |
|
Token ID | 198 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
phabet | +1.465 |
acebook | +1.463 |
utherland | +1.455 |
Civil | +1.329 |
FontSize | +1.222 |
Neg logit contributions | |
�� | -4.058 |
�� | -3.682 |
�� | -3.460 |
�� | -3.192 |
�� | -3.127 |
Token | P |
Token ID | 47 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
phabet | +1.913 |
acebook | +1.904 |
utherland | +1.893 |
Civil | +1.741 |
FontSize | +1.620 |
Neg logit contributions | |
�� | -4.798 |
�� | -4.344 |
�� | -4.073 |
�� | -3.744 |
�� | -3.670 |
Token | CC |
Token ID | 4093 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
acebook | +3.212 |
phabet | +3.174 |
utherland | +3.160 |
Civil | +2.913 |
sung | +2.692 |
Neg logit contributions | |
�� | -6.202 |
�� | -5.578 |
�� | -5.211 |
�� | -4.719 |
�� | -4.637 |
Token | ministry |
Token ID | 11957 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
�� | +1.889 |
�� | +1.701 |
�� | +1.594 |
�� | +1.457 |
�� | +1.435 |
Neg logit contributions | |
phabet | -0.797 |
acebook | -0.797 |
utherland | -0.785 |
Civil | -0.708 |
FontSize | -0.668 |
Token | under |
Token ID | 739 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
�� | +3.161 |
�� | +2.844 |
�� | +2.661 |
�� | +2.416 |
�� | +2.388 |
Neg logit contributions | |
acebook | -1.375 |
phabet | -1.362 |
utherland | -1.353 |
Civil | -1.207 |
FontSize | -1.148 |
Token | secretary |
Token ID | 7705 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
�� | +1.943 |
�� | +1.744 |
�� | +1.630 |
�� | +1.482 |
�� | +1.457 |
Neg logit contributions | |
acebook | -0.932 |
phabet | -0.926 |
utherland | -0.919 |
Civil | -0.839 |
FontSize | -0.791 |
Token | Fer |
Token ID | 12880 |
Feature activation | -6.46e+00 |
Pos logit contributions | |
acebook | +0.514 |
phabet | +0.514 |
utherland | +0.508 |
Civil | +0.467 |
FontSize | +0.432 |
Neg logit contributions | |
�� | -1.216 |
�� | -1.097 |
�� | -1.027 |
�� | -0.941 |
�� | -0.926 |
Token | id |
Token ID | 312 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
phabet | +3.154 |
acebook | +3.038 |
utherland | +2.998 |
Civil | +2.738 |
sung | +2.453 |
Neg logit contributions | |
�� | -11.009 |
�� | -10.033 |
�� | -9.441 |
�� | -8.825 |
�� | -8.549 |
Token | un |
Token ID | 403 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
phabet | +1.646 |
acebook | +1.622 |
utherland | +1.585 |
Civil | +1.393 |
sung | +1.129 |
Neg logit contributions | |
�� | -9.700 |
�� | -8.964 |
�� | -8.467 |
�� | -7.877 |
�� | -7.794 |
Token | Sin |
Token ID | 10884 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
phabet | +9.060 |
Civil | +8.625 |
acebook | +8.305 |
utherland | +8.211 |
ro | +7.543 |
Neg logit contributions | |
�� | -21.130 |
�� | -19.353 |
�� | -18.377 |
�� | -16.510 |
�� | -16.504 |
Token | irl |
Token ID | 1901 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
�� | +5.199 |
�� | +4.615 |
�� | +4.309 |
�� | +3.927 |
�� | +3.848 |
Neg logit contributions | |
acebook | -2.785 |
utherland | -2.704 |
phabet | -2.685 |
Civil | -2.440 |
FontSize | -2.430 |
Token | i |
Token ID | 72 |
Feature activation | -8.20e+00 |
Pos logit contributions | |
acebook | +0.122 |
phabet | +0.121 |
utherland | +0.120 |
Civil | +0.109 |
FontSize | +0.102 |
Neg logit contributions | |
�� | -0.296 |
�� | -0.267 |
�� | -0.250 |
�� | -0.229 |
�� | -0.226 |
Token | oglu |
Token ID | 49006 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
phabet | +4.411 |
utherland | +4.225 |
acebook | +4.150 |
Civil | +3.987 |
ro | +3.581 |
Neg logit contributions | |
�� | -13.356 |
�� | -12.145 |
�� | -11.434 |
�� | -10.573 |
�� | -10.373 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
�� | +4.335 |
�� | +3.895 |
�� | +3.654 |
�� | +3.315 |
�� | +3.270 |
Neg logit contributions | |
acebook | -1.965 |
phabet | -1.926 |
utherland | -1.923 |
Civil | -1.719 |
FontSize | -1.644 |
Token | poses |
Token ID | 17313 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
acebook | +0.030 |
phabet | +0.030 |
utherland | +0.029 |
Civil | +0.027 |
FontSize | +0.025 |
Neg logit contributions | |
�� | -0.072 |
�� | -0.065 |
�� | -0.061 |
�� | -0.056 |
�� | -0.055 |
Token | for |
Token ID | 329 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
acebook | +2.111 |
phabet | +2.091 |
utherland | +2.089 |
Civil | +1.913 |
sung | +1.728 |
Neg logit contributions | |
�� | -6.149 |
�� | -5.600 |
�� | -5.261 |
�� | -4.852 |
�� | -4.767 |
Token | a |
Token ID | 257 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
�� | +1.083 |
�� | +0.971 |
�� | +0.908 |
�� | +0.825 |
�� | +0.811 |
Neg logit contributions | |
acebook | -0.515 |
phabet | -0.513 |
utherland | -0.509 |
Civil | -0.463 |
FontSize | -0.440 |
Token | selfie |
Token ID | 38704 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
�� | +0.547 |
�� | +0.492 |
�� | +0.461 |
�� | +0.420 |
�� | +0.415 |
Neg logit contributions | |
acebook | -0.239 |
phabet | -0.238 |
utherland | -0.236 |
Civil | -0.210 |
FontSize | -0.202 |
Token | with |
Token ID | 351 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
acebook | +2.459 |
utherland | +2.431 |
phabet | +2.417 |
Civil | +2.249 |
sung | +2.040 |
Neg logit contributions | |
�� | -7.185 |
�� | -6.543 |
�� | -6.126 |
�� | -5.679 |
�� | -5.547 |
Token | Joe |
Token ID | 5689 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
�� | +1.240 |
�� | +1.116 |
�� | +1.042 |
�� | +0.950 |
�� | +0.937 |
Neg logit contributions | |
acebook | -0.555 |
phabet | -0.554 |
utherland | -0.549 |
Civil | -0.494 |
FontSize | -0.470 |
Token | K |
Token ID | 509 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
acebook | +9.415 |
Civil | +8.925 |
utherland | +8.911 |
phabet | +8.831 |
Canary | +7.508 |
Neg logit contributions | |
�� | -21.145 |
�� | -18.904 |
�� | -17.864 |
�� | -16.246 |
�� | -15.737 |
Token | ober |
Token ID | 2023 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
�� | +6.174 |
�� | +5.492 |
�� | +5.139 |
�� | +4.673 |
�� | +4.634 |
Neg logit contributions | |
acebook | -2.732 |
phabet | -2.724 |
utherland | -2.643 |
FontSize | -2.398 |
Civil | -2.396 |
Token | na |
Token ID | 2616 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
phabet | +3.192 |
utherland | +3.153 |
acebook | +3.129 |
Civil | +2.935 |
sung | +2.728 |
Neg logit contributions | |
�� | -7.019 |
�� | -6.382 |
�� | -5.934 |
�� | -5.410 |
�� | -5.315 |
Token | at |
Token ID | 379 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
�� | +1.683 |
�� | +1.503 |
�� | +1.406 |
�� | +1.276 |
�� | +1.258 |
Neg logit contributions | |
acebook | -0.872 |
phabet | -0.867 |
utherland | -0.859 |
Civil | -0.790 |
FontSize | -0.747 |
Token | the |
Token ID | 262 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
acebook | +0.141 |
phabet | +0.140 |
utherland | +0.139 |
Civil | +0.127 |
FontSize | +0.119 |
Neg logit contributions | |
�� | -0.312 |
�� | -0.281 |
�� | -0.262 |
�� | -0.239 |
�� | -0.236 |
Token | disdain |
Token ID | 31564 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
acebook | +3.536 |
phabet | +3.514 |
utherland | +3.450 |
Civil | +3.287 |
FontSize | +2.998 |
Neg logit contributions | |
�� | -8.132 |
�� | -7.347 |
�� | -6.879 |
�� | -6.285 |
�� | -6.203 |
Token | for |
Token ID | 329 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
�� | +4.693 |
�� | +4.219 |
�� | +3.966 |
�� | +3.610 |
�� | +3.547 |
Neg logit contributions | |
acebook | -1.994 |
phabet | -1.983 |
utherland | -1.967 |
Civil | -1.764 |
FontSize | -1.684 |
Token | public |
Token ID | 1171 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
�� | +2.269 |
�� | +2.031 |
�� | +1.896 |
�� | +1.728 |
�� | +1.695 |
Neg logit contributions | |
acebook | -1.093 |
phabet | -1.090 |
utherland | -1.078 |
Civil | -0.962 |
FontSize | -0.928 |
Token | br |
Token ID | 865 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
acebook | +1.743 |
phabet | +1.740 |
utherland | +1.723 |
Civil | +1.603 |
FontSize | +1.489 |
Neg logit contributions | |
�� | -3.503 |
�� | -3.150 |
�� | -2.926 |
�� | -2.670 |
�� | -2.627 |
Token | agg |
Token ID | 9460 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
acebook | +4.375 |
utherland | +4.255 |
phabet | +4.236 |
Civil | +3.887 |
sung | +3.689 |
Neg logit contributions | |
�� | -7.933 |
�� | -7.131 |
�� | -6.634 |
�� | -6.032 |
�� | -5.892 |
Token | ad |
Token ID | 324 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
acebook | +1.609 |
phabet | +1.591 |
utherland | +1.575 |
Civil | +1.412 |
sung | +1.290 |
Neg logit contributions | |
�� | -4.763 |
�� | -4.326 |
�� | -4.084 |
�� | -3.772 |
�� | -3.691 |
Token | oc |
Token ID | 420 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
acebook | +6.244 |
phabet | +6.050 |
utherland | +5.931 |
Civil | +5.677 |
rift | +5.644 |
Neg logit contributions | |
�� | -24.008 |
�� | -21.490 |
�� | -20.935 |
�� | -19.596 |
�� | -19.191 |
Token | io |
Token ID | 952 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
acebook | +2.564 |
phabet | +2.495 |
utherland | +2.470 |
Civil | +2.265 |
sung | +2.051 |
Neg logit contributions | |
�� | -8.688 |
�� | -7.922 |
�� | -7.587 |
�� | -6.988 |
�� | -6.805 |
Token | � |
Token ID | 447 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
phabet | +1.986 |
acebook | +1.978 |
utherland | +1.958 |
Civil | +1.822 |
FontSize | +1.674 |
Neg logit contributions | |
�� | -4.373 |
�� | -3.930 |
�� | -3.681 |
�� | -3.372 |
�� | -3.313 |
Token | � |
Token ID | 251 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
phabet | +0.475 |
acebook | +0.473 |
utherland | +0.471 |
Civil | +0.454 |
FontSize | +0.440 |
Neg logit contributions | |
�� | -0.254 |
�� | -0.202 |
�� | -0.175 |
�� | -0.136 |
�� | -0.131 |
Token | as |
Token ID | 355 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
�� | +1.620 |
�� | +1.456 |
�� | +1.361 |
�� | +1.241 |
�� | +1.219 |
Neg logit contributions | |
acebook | -0.745 |
phabet | -0.740 |
utherland | -0.736 |
Civil | -0.668 |
FontSize | -0.632 |
Token | the |
Token ID | 262 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
acebook | +1.107 |
phabet | +1.105 |
utherland | +1.095 |
Civil | +1.009 |
FontSize | +0.938 |
Neg logit contributions | |
�� | -2.439 |
�� | -2.196 |
�� | -2.055 |
�� | -1.875 |
�� | -1.845 |
Token | field |
Token ID | 2214 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
acebook | +0.355 |
phabet | +0.354 |
utherland | +0.350 |
Civil | +0.317 |
FontSize | +0.298 |
Neg logit contributions | |
�� | -0.823 |
�� | -0.741 |
�� | -0.693 |
�� | -0.634 |
�� | -0.624 |
Token | on |
Token ID | 319 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
phabet | +2.300 |
utherland | +2.296 |
acebook | +2.290 |
Civil | +2.112 |
sung | +1.923 |
Neg logit contributions | |
�� | -5.531 |
�� | -5.006 |
�� | -4.709 |
�� | -4.320 |
�� | -4.232 |
Token | military |
Token ID | 2422 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
acebook | +0.852 |
phabet | +0.847 |
utherland | +0.839 |
Civil | +0.774 |
FontSize | +0.719 |
Neg logit contributions | |
�� | -1.884 |
�� | -1.693 |
�� | -1.585 |
�� | -1.447 |
�� | -1.424 |
Token | operations |
Token ID | 4560 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
acebook | +0.300 |
phabet | +0.299 |
utherland | +0.296 |
Civil | +0.272 |
FontSize | +0.257 |
Neg logit contributions | |
�� | -0.598 |
�� | -0.536 |
�� | -0.500 |
�� | -0.455 |
�� | -0.447 |
Token | ad |
Token ID | 512 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
phabet | +3.467 |
utherland | +3.436 |
acebook | +3.425 |
Civil | +3.227 |
FontSize | +2.926 |
Neg logit contributions | |
�� | -8.686 |
�� | -7.813 |
�� | -7.397 |
�� | -6.839 |
�� | -6.605 |
Token | inf |
Token ID | 1167 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
rift | +9.675 |
acebook | +9.606 |
phabet | +9.566 |
Civil | +9.495 |
utherland | +9.330 |
Neg logit contributions | |
�� | -19.449 |
�� | -17.609 |
�� | -16.469 |
�� | -15.187 |
�� | -14.456 |
Token | init |
Token ID | 15003 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
acebook | +0.761 |
phabet | +0.759 |
utherland | +0.750 |
Civil | +0.683 |
sung | +0.629 |
Neg logit contributions | |
�� | -1.904 |
�� | -1.719 |
�� | -1.617 |
�� | -1.482 |
�� | -1.457 |
Token | um |
Token ID | 388 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
phabet | +4.521 |
acebook | +4.478 |
utherland | +4.411 |
Civil | +4.245 |
ieth | +3.928 |
Neg logit contributions | |
�� | -7.454 |
�� | -6.691 |
�� | -6.257 |
�� | -5.631 |
�� | -5.491 |
Token | . |
Token ID | 13 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
phabet | +1.732 |
acebook | +1.720 |
utherland | +1.708 |
Civil | +1.573 |
FontSize | +1.436 |
Neg logit contributions | |
�� | -4.291 |
�� | -3.868 |
�� | -3.636 |
�� | -3.342 |
�� | -3.282 |
Token | � |
Token ID | 447 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
acebook | +0.255 |
phabet | +0.254 |
utherland | +0.251 |
Civil | +0.227 |
FontSize | +0.212 |
Neg logit contributions | |
�� | -0.640 |
�� | -0.578 |
�� | -0.542 |
�� | -0.497 |
�� | -0.489 |
Token | leader |
Token ID | 3554 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
�� | +5.887 |
�� | +5.209 |
�� | +4.879 |
�� | +4.379 |
�� | +4.372 |
Neg logit contributions | |
acebook | -3.146 |
phabet | -3.125 |
utherland | -3.045 |
FontSize | -2.702 |
Civil | -2.666 |
Token | David |
Token ID | 3271 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
�� | +0.951 |
�� | +0.859 |
�� | +0.810 |
�� | +0.741 |
�� | +0.734 |
Neg logit contributions | |
phabet | -0.342 |
acebook | -0.341 |
utherland | -0.335 |
Civil | -0.293 |
FontSize | -0.279 |
Token | Duke |
Token ID | 11083 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
acebook | +0.583 |
utherland | +0.575 |
phabet | +0.519 |
Civil | +0.484 |
sung | +0.296 |
Neg logit contributions | |
�� | -5.509 |
�� | -5.122 |
�� | -4.794 |
�� | -4.577 |
�� | -4.457 |
Token | . |
Token ID | 13 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
�� | +1.416 |
�� | +1.273 |
�� | +1.195 |
�� | +1.091 |
�� | +1.076 |
Neg logit contributions | |
acebook | -0.604 |
phabet | -0.601 |
utherland | -0.594 |
Civil | -0.537 |
FontSize | -0.506 |
Token | ( |
Token ID | 357 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
�� | +9.122 |
�� | +8.044 |
�� | +7.476 |
�� | +6.793 |
�� | +6.674 |
Neg logit contributions | |
acebook | -4.691 |
phabet | -4.689 |
utherland | -4.598 |
FontSize | -3.990 |
sung | -3.968 |
Token | Joe |
Token ID | 19585 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
�� | +1.371 |
�� | +1.231 |
�� | +1.156 |
�� | +1.050 |
�� | +1.037 |
Neg logit contributions | |
acebook | -0.602 |
phabet | -0.598 |
utherland | -0.591 |
Civil | -0.535 |
FontSize | -0.503 |
Token | Bur |
Token ID | 5481 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
acebook | +6.999 |
utherland | +6.975 |
Civil | +6.701 |
phabet | +6.435 |
ro | +5.311 |
Neg logit contributions | |
�� | -23.311 |
�� | -21.045 |
�� | -20.067 |
�� | -18.486 |
�� | -17.816 |
Token | bank |
Token ID | 17796 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
acebook | +0.841 |
phabet | +0.840 |
utherland | +0.829 |
Civil | +0.730 |
sung | +0.653 |
Neg logit contributions | |
�� | -3.312 |
�� | -3.015 |
�� | -2.865 |
�� | -2.663 |
�� | -2.613 |
Token | / |
Token ID | 14 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
acebook | +0.523 |
phabet | +0.522 |
utherland | +0.518 |
Civil | +0.476 |
FontSize | +0.444 |
Neg logit contributions | |
�� | -1.121 |
�� | -1.008 |
�� | -0.942 |
�� | -0.859 |
�� | -0.844 |
Token | Or |
Token ID | 5574 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
�� | +0.705 |
�� | +0.633 |
�� | +0.591 |
�� | +0.538 |
�� | +0.531 |
Neg logit contributions | |
phabet | -0.332 |
acebook | -0.331 |
utherland | -0.327 |
Civil | -0.297 |
FontSize | -0.280 |
Token | lando |
Token ID | 11993 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
acebook | +0.628 |
phabet | +0.627 |
utherland | +0.622 |
Civil | +0.585 |
sung | +0.551 |
Neg logit contributions | |
�� | -0.915 |
�� | -0.809 |
�� | -0.749 |
�� | -0.673 |
�� | -0.656 |
Token | : |
Token ID | 25 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
�� | +0.017 |
�� | +0.015 |
�� | +0.014 |
�� | +0.013 |
�� | +0.013 |
Neg logit contributions | |
acebook | -0.007 |
phabet | -0.007 |
utherland | -0.007 |
Civil | -0.007 |
FontSize | -0.006 |
Token | develop |
Token ID | 1205 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
acebook | +0.938 |
phabet | +0.937 |
utherland | +0.926 |
Civil | +0.848 |
FontSize | +0.779 |
Neg logit contributions | |
�� | -2.335 |
�� | -2.106 |
�� | -1.976 |
�� | -1.813 |
�� | -1.786 |
Token | a |
Token ID | 257 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
acebook | +2.613 |
phabet | +2.603 |
utherland | +2.584 |
Civil | +2.442 |
FontSize | +2.201 |
Neg logit contributions | |
�� | -5.741 |
�� | -5.163 |
�� | -4.833 |
�� | -4.395 |
�� | -4.386 |
Token | � |
Token ID | 564 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
phabet | +3.745 |
acebook | +3.693 |
utherland | +3.653 |
Civil | +3.539 |
FontSize | +3.157 |
Neg logit contributions | |
�� | -7.726 |
�� | -6.925 |
�� | -6.483 |
�� | -5.880 |
�� | -5.828 |
Token | � |
Token ID | 250 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
phabet | +4.519 |
utherland | +4.458 |
acebook | +4.456 |
Civil | +4.302 |
FontSize | +4.208 |
Neg logit contributions | |
�� | -2.297 |
�� | -1.833 |
�� | -1.574 |
�� | -1.225 |
�� | -1.162 |
Token | pro |
Token ID | 1676 |
Feature activation | -1.44e+01 |
Pos logit contributions | |
phabet | +4.454 |
acebook | +4.398 |
utherland | +4.374 |
Civil | +4.136 |
sung | +3.857 |
Neg logit contributions | |
�� | -8.961 |
�� | -8.026 |
�� | -7.507 |
�� | -6.820 |
�� | -6.800 |
Token | active |
Token ID | 5275 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
phabet | +9.200 |
acebook | +8.624 |
utherland | +8.573 |
Civil | +8.424 |
ro | +7.709 |
Neg logit contributions | |
�� | -19.996 |
�� | -17.767 |
�� | -16.689 |
�� | -15.535 |
�� | -15.457 |
Token | compliance |
Token ID | 11846 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
Civil | +6.833 |
acebook | +6.785 |
phabet | +6.715 |
utherland | +6.496 |
inspector | +5.815 |
Neg logit contributions | |
�� | -16.366 |
�� | -14.748 |
�� | -13.742 |
�� | -12.650 |
�� | -12.596 |
Token | program |
Token ID | 1430 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
phabet | +3.209 |
acebook | +3.205 |
utherland | +3.148 |
Civil | +2.986 |
FontSize | +2.649 |
Neg logit contributions | |
�� | -7.650 |
�� | -6.892 |
�� | -6.447 |
�� | -5.915 |
�� | -5.845 |
Token | , |
Token ID | 11 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
acebook | +0.646 |
phabet | +0.645 |
utherland | +0.638 |
Civil | +0.585 |
FontSize | +0.546 |
Neg logit contributions | |
�� | -1.414 |
�� | -1.272 |
�� | -1.189 |
�� | -1.086 |
�� | -1.068 |
Token | � |
Token ID | 447 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
acebook | +0.758 |
phabet | +0.757 |
utherland | +0.749 |
Civil | +0.683 |
FontSize | +0.630 |
Neg logit contributions | |
�� | -1.900 |
�� | -1.715 |
�� | -1.609 |
�� | -1.476 |
�� | -1.454 |
Token | AV |
Token ID | 10116 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
�� | +1.096 |
�� | +0.984 |
�� | +0.920 |
�� | +0.839 |
�� | +0.825 |
Neg logit contributions | |
acebook | -0.515 |
phabet | -0.515 |
utherland | -0.510 |
Civil | -0.466 |
FontSize | -0.438 |
Token | ING |
Token ID | 2751 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
acebook | +0.371 |
phabet | +0.369 |
utherland | +0.366 |
Civil | +0.339 |
FontSize | +0.319 |
Neg logit contributions | |
�� | -0.694 |
�� | -0.619 |
�� | -0.578 |
�� | -0.525 |
�� | -0.515 |
Token | line |
Token ID | 1627 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
acebook | +2.454 |
phabet | +2.424 |
utherland | +2.419 |
Civil | +2.236 |
FontSize | +2.037 |
Neg logit contributions | |
�� | -5.823 |
�� | -5.235 |
�� | -4.942 |
�� | -4.516 |
�� | -4.460 |
Token | contains |
Token ID | 4909 |
Feature activation | -6.50e+00 |
Pos logit contributions | |
phabet | +1.727 |
acebook | +1.726 |
utherland | +1.720 |
Civil | +1.563 |
FontSize | +1.438 |
Neg logit contributions | |
�� | -4.479 |
�� | -4.048 |
�� | -3.802 |
�� | -3.496 |
�� | -3.443 |
Token | ' |
Token ID | 705 |
Feature activation | -9.68e+00 |
Pos logit contributions | |
utherland | +4.081 |
acebook | +4.050 |
phabet | +4.047 |
Civil | +3.829 |
sung | +3.461 |
Neg logit contributions | |
�� | -9.868 |
�� | -8.864 |
�� | -8.379 |
�� | -7.727 |
�� | -7.639 |
Token | [' |
Token ID | 17816 |
Feature activation | -1.40e+01 |
Pos logit contributions | |
phabet | +5.989 |
utherland | +5.951 |
acebook | +5.946 |
Civil | +5.502 |
ro | +5.275 |
Neg logit contributions | |
�� | -14.274 |
�� | -12.742 |
�� | -12.180 |
�� | -11.185 |
�� | -11.075 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
acebook | +7.387 |
utherland | +7.331 |
phabet | +7.217 |
Civil | +6.947 |
LINK | +6.368 |
Neg logit contributions | |
�� | -20.911 |
�� | -18.880 |
�� | -18.044 |
�� | -16.711 |
�� | -16.617 |
Token | GROUP |
Token ID | 44441 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
acebook | +1.975 |
phabet | +1.963 |
utherland | +1.954 |
Civil | +1.803 |
FontSize | +1.641 |
Neg logit contributions | |
�� | -5.168 |
�� | -4.675 |
�� | -4.398 |
�� | -4.050 |
�� | -3.992 |
Token | BY |
Token ID | 11050 |
Feature activation | -8.82e+00 |
Pos logit contributions | |
utherland | +1.340 |
phabet | +1.330 |
acebook | +1.317 |
Civil | +1.185 |
sung | +1.035 |
Neg logit contributions | |
�� | -5.105 |
�� | -4.671 |
�� | -4.409 |
�� | -4.110 |
�� | -4.025 |
Token | library |
Token ID | 5888 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
utherland | +5.213 |
phabet | +5.197 |
acebook | +5.190 |
Civil | +4.909 |
LINK | +4.470 |
Neg logit contributions | |
�� | -13.430 |
�� | -12.086 |
�� | -11.599 |
�� | -10.573 |
�� | -10.399 |
Token | , |
Token ID | 837 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
phabet | +6.454 |
utherland | +6.331 |
acebook | +6.322 |
Civil | +6.020 |
LINK | +5.479 |
Neg logit contributions | |
�� | -17.347 |
�� | -15.585 |
�� | -14.844 |
�� | -13.858 |
�� | -13.624 |
Token | " |
Token ID | 1 |
Feature activation | -7.87e+00 |
Pos logit contributions | |
acebook | +2.025 |
phabet | +2.019 |
utherland | +2.001 |
Civil | +1.839 |
FontSize | +1.732 |
Neg logit contributions | |
�� | -4.469 |
�� | -3.992 |
�� | -3.765 |
�� | -3.441 |
�� | -3.377 |
Token | \ |
Token ID | 59 |
Feature activation | -8.26e+00 |
Pos logit contributions | |
acebook | +4.949 |
phabet | +4.901 |
utherland | +4.877 |
Civil | +4.510 |
FontSize | +4.225 |
Neg logit contributions | |
�� | -11.930 |
�� | -10.534 |
�� | -10.144 |
�� | -9.283 |
�� | -9.174 |
Token | S |
Token ID | 50 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
acebook | +4.756 |
utherland | +4.750 |
phabet | +4.714 |
Civil | +4.361 |
sung | +4.192 |
Neg logit contributions | |
�� | -12.764 |
�� | -11.375 |
�� | -10.827 |
�� | -9.933 |
�� | -9.754 |
Token | + |
Token ID | 10 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
�� | +4.434 |
�� | +4.017 |
�� | +3.727 |
�� | +3.393 |
�� | +3.354 |
Neg logit contributions | |
acebook | -1.955 |
phabet | -1.955 |
utherland | -1.921 |
Civil | -1.745 |
sung | -1.635 |
Token | "] |
Token ID | 8973 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
acebook | +1.609 |
phabet | +1.604 |
utherland | +1.587 |
Civil | +1.463 |
FontSize | +1.374 |
Neg logit contributions | |
�� | -3.440 |
�� | -3.079 |
�� | -2.892 |
�� | -2.641 |
�� | -2.595 |
Token | ' |
Token ID | 6 |
Feature activation | -1.40e+01 |
Pos logit contributions | |
acebook | +3.172 |
phabet | +3.156 |
utherland | +3.144 |
Civil | +2.895 |
FontSize | +2.682 |
Neg logit contributions | |
�� | -7.726 |
�� | -6.882 |
�� | -6.564 |
�� | -6.021 |
�� | -5.928 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
acebook | +5.992 |
utherland | +5.959 |
phabet | +5.860 |
Civil | +5.342 |
sung | +4.782 |
Neg logit contributions | |
�� | -22.251 |
�� | -20.119 |
�� | -19.264 |
�� | -18.077 |
�� | -17.846 |
Token | AS |
Token ID | 7054 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
acebook | +0.826 |
phabet | +0.824 |
utherland | +0.817 |
Civil | +0.746 |
FontSize | +0.690 |
Neg logit contributions | |
�� | -2.022 |
�� | -1.825 |
�� | -1.712 |
�� | -1.571 |
�� | -1.545 |
Token | library |
Token ID | 5888 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
phabet | +1.859 |
acebook | +1.858 |
utherland | +1.844 |
Civil | +1.700 |
FontSize | +1.569 |
Neg logit contributions | |
�� | -4.353 |
�� | -3.919 |
�� | -3.687 |
�� | -3.377 |
�� | -3.322 |
Token | , |
Token ID | 837 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
phabet | +6.252 |
utherland | +6.233 |
acebook | +6.127 |
Civil | +5.789 |
LINK | +5.292 |
Neg logit contributions | |
�� | -16.330 |
�� | -14.689 |
�� | -13.815 |
�� | -12.995 |
�� | -12.748 |
Token | REG |
Token ID | 23337 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
utherland | +5.364 |
phabet | +5.349 |
acebook | +5.322 |
Civil | +5.067 |
LINK | +4.639 |
Neg logit contributions | |
�� | -12.866 |
�� | -11.639 |
�� | -10.975 |
�� | -10.177 |
�� | -9.941 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
�� | +6.972 |
�� | +6.248 |
�� | +5.815 |
�� | +5.256 |
�� | +5.215 |
Neg logit contributions | |
acebook | -3.351 |
phabet | -3.299 |
utherland | -3.255 |
Civil | -2.937 |
FontSize | -2.785 |
Token | A |
Token ID | 317 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
acebook | +1.119 |
phabet | +1.113 |
utherland | +1.108 |
Civil | +1.017 |
FontSize | +0.940 |
Neg logit contributions | |
�� | -2.650 |
�� | -2.390 |
�� | -2.240 |
�� | -2.053 |
�� | -2.015 |
Token | visual |
Token ID | 5874 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
�� | +2.836 |
�� | +2.547 |
�� | +2.382 |
�� | +2.165 |
�� | +2.138 |
Neg logit contributions | |
acebook | -1.373 |
phabet | -1.354 |
utherland | -1.349 |
Civil | -1.218 |
FontSize | -1.159 |
Token | , |
Token ID | 11 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
�� | +4.292 |
�� | +3.867 |
�� | +3.616 |
�� | +3.261 |
�� | +3.224 |
Neg logit contributions | |
acebook | -2.088 |
phabet | -2.046 |
utherland | -2.038 |
Civil | -1.829 |
FontSize | -1.766 |
Token | and |
Token ID | 290 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
acebook | +0.541 |
phabet | +0.540 |
utherland | +0.535 |
Civil | +0.491 |
FontSize | +0.461 |
Neg logit contributions | |
�� | -1.124 |
�� | -1.009 |
�� | -0.943 |
�� | -0.858 |
�� | -0.844 |
Token | perhaps |
Token ID | 3737 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
acebook | +3.683 |
phabet | +3.664 |
utherland | +3.638 |
Civil | +3.472 |
FontSize | +3.176 |
Neg logit contributions | |
�� | -8.099 |
�� | -7.274 |
�� | -6.787 |
�� | -6.231 |
�� | -6.081 |
Token | visceral |
Token ID | 38259 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
Civil | +8.155 |
acebook | +7.995 |
utherland | +7.920 |
phabet | +7.902 |
ro | +7.395 |
Neg logit contributions | |
�� | -19.975 |
�� | -18.087 |
�� | -16.696 |
�� | -15.466 |
�� | -14.848 |
Token | , |
Token ID | 11 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
�� | +4.494 |
�� | +4.025 |
�� | +3.774 |
�� | +3.367 |
�� | +3.339 |
Neg logit contributions | |
acebook | -2.500 |
phabet | -2.465 |
utherland | -2.460 |
Civil | -2.234 |
FontSize | -2.166 |
Token | reminder |
Token ID | 15438 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
�� | +6.157 |
�� | +5.538 |
�� | +5.215 |
�� | +4.683 |
�� | +4.644 |
Neg logit contributions | |
acebook | -3.044 |
phabet | -2.998 |
utherland | -2.941 |
Civil | -2.614 |
FontSize | -2.578 |
Token | to |
Token ID | 284 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
acebook | +0.916 |
phabet | +0.915 |
utherland | +0.906 |
Civil | +0.828 |
FontSize | +0.768 |
Neg logit contributions | |
�� | -2.212 |
�� | -1.995 |
�� | -1.868 |
�� | -1.714 |
�� | -1.685 |
Token | all |
Token ID | 477 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
utherland | +3.604 |
phabet | +3.563 |
acebook | +3.536 |
Civil | +3.406 |
sung | +3.063 |
Neg logit contributions | |
�� | -8.496 |
�� | -7.645 |
�� | -7.158 |
�� | -6.572 |
�� | -6.406 |
Token | your |
Token ID | 534 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
acebook | +1.690 |
phabet | +1.686 |
utherland | +1.669 |
Civil | +1.546 |
FontSize | +1.417 |
Neg logit contributions | |
�� | -3.888 |
�� | -3.496 |
�� | -3.284 |
�� | -2.995 |
�� | -2.942 |
Token | sh |
Token ID | 427 |
Feature activation | -2.24e-03 |
Pos logit contributions | |
acebook | +1.129 |
phabet | +1.126 |
utherland | +1.117 |
Civil | +1.034 |
FontSize | +0.968 |
Neg logit contributions | |
�� | -2.215 |
�� | -1.984 |
�� | -1.849 |
�� | -1.681 |
�� | -1.650 |
Token | rooms |
Token ID | 9649 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
acebook | +0.002 |
phabet | +0.002 |
utherland | +0.002 |
Civil | +0.001 |
FontSize | +0.001 |
Neg logit contributions | |
�� | -0.003 |
�� | -0.003 |
�� | -0.003 |
�� | -0.003 |
�� | -0.003 |
Token | ( |
Token ID | 357 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
acebook | +1.808 |
phabet | +1.805 |
utherland | +1.780 |
Civil | +1.630 |
FontSize | +1.490 |
Neg logit contributions | |
�� | -4.767 |
�� | -4.306 |
�� | -4.053 |
�� | -3.713 |
�� | -3.638 |
Token | fresh |
Token ID | 48797 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
phabet | +1.252 |
acebook | +1.245 |
utherland | +1.238 |
Civil | +1.136 |
FontSize | +1.068 |
Neg logit contributions | |
�� | -2.598 |
�� | -2.333 |
�� | -2.181 |
�� | -1.988 |
�� | -1.955 |
Token | or |
Token ID | 393 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
�� | +3.060 |
�� | +2.741 |
�� | +2.557 |
�� | +2.337 |
�� | +2.298 |
Neg logit contributions | |
acebook | -1.462 |
phabet | -1.446 |
utherland | -1.433 |
Civil | -1.311 |
FontSize | -1.244 |
Token | dry |
Token ID | 5894 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
phabet | +8.480 |
utherland | +8.198 |
Civil | +8.150 |
acebook | +8.144 |
ro | +7.687 |
Neg logit contributions | |
�� | -18.886 |
�� | -17.177 |
�� | -16.387 |
�� | -15.005 |
�� | -14.258 |
Token | ) |
Token ID | 8 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
phabet | +0.983 |
acebook | +0.980 |
utherland | +0.971 |
Civil | +0.899 |
FontSize | +0.840 |
Neg logit contributions | |
�� | -1.906 |
�� | -1.707 |
�� | -1.592 |
�� | -1.445 |
�� | -1.419 |
Token | and |
Token ID | 290 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
acebook | +1.486 |
phabet | +1.484 |
utherland | +1.466 |
Civil | +1.335 |
FontSize | +1.228 |
Neg logit contributions | |
�� | -3.788 |
�� | -3.424 |
�� | -3.215 |
�� | -2.946 |
�� | -2.896 |
Token | wh |
Token ID | 348 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
phabet | +2.092 |
acebook | +2.090 |
utherland | +2.058 |
Civil | +1.910 |
FontSize | +1.746 |
Neg logit contributions | |
�� | -4.860 |
�� | -4.373 |
�� | -4.112 |
�� | -3.744 |
�� | -3.679 |
Token | iz |
Token ID | 528 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
�� | +2.767 |
�� | +2.447 |
�� | +2.275 |
�� | +2.045 |
�� | +2.032 |
Neg logit contributions | |
phabet | -1.600 |
acebook | -1.599 |
utherland | -1.574 |
Civil | -1.474 |
FontSize | -1.410 |
Token | New |
Token ID | 968 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
�� | +0.104 |
�� | +0.094 |
�� | +0.088 |
�� | +0.081 |
�� | +0.079 |
Neg logit contributions | |
acebook | -0.042 |
phabet | -0.042 |
utherland | -0.041 |
Civil | -0.037 |
FontSize | -0.035 |
Token | York |
Token ID | 1971 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
�� | +4.227 |
�� | +3.775 |
�� | +3.543 |
�� | +3.210 |
�� | +3.194 |
Neg logit contributions | |
acebook | -1.923 |
phabet | -1.878 |
utherland | -1.861 |
Civil | -1.628 |
FontSize | -1.575 |
Token | cho |
Token ID | 1727 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
phabet | +2.407 |
acebook | +2.406 |
utherland | +2.371 |
Civil | +2.238 |
sung | +2.040 |
Neg logit contributions | |
�� | -5.064 |
�� | -4.553 |
�� | -4.242 |
�� | -3.870 |
�� | -3.805 |
Token | pper |
Token ID | 2848 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
acebook | +1.822 |
phabet | +1.806 |
utherland | +1.794 |
Civil | +1.627 |
sung | +1.481 |
Neg logit contributions | |
�� | -5.272 |
�� | -4.822 |
�� | -4.531 |
�� | -4.168 |
�� | -4.101 |
Token | reporter |
Token ID | 9095 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
acebook | +0.123 |
phabet | +0.123 |
utherland | +0.121 |
Civil | +0.110 |
FontSize | +0.104 |
Neg logit contributions | |
�� | -0.277 |
�� | -0.249 |
�� | -0.233 |
�� | -0.213 |
�� | -0.209 |
Token | Joe |
Token ID | 5689 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
�� | +2.621 |
�� | +2.351 |
�� | +2.202 |
�� | +2.000 |
�� | +1.974 |
Neg logit contributions | |
acebook | -1.213 |
phabet | -1.212 |
utherland | -1.196 |
Civil | -1.069 |
FontSize | -1.034 |
Token | B |
Token ID | 347 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
acebook | +8.474 |
utherland | +8.367 |
Civil | +8.326 |
phabet | +8.227 |
ro | +7.293 |
Neg logit contributions | |
�� | -18.482 |
�� | -16.772 |
�� | -15.540 |
�� | -14.310 |
�� | -13.801 |
Token | ier |
Token ID | 959 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
�� | +4.350 |
�� | +3.895 |
�� | +3.622 |
�� | +3.313 |
�� | +3.245 |
Neg logit contributions | |
acebook | -2.074 |
phabet | -2.070 |
utherland | -2.048 |
Civil | -1.882 |
FontSize | -1.822 |
Token | mann |
Token ID | 9038 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
acebook | +0.402 |
phabet | +0.401 |
utherland | +0.397 |
Civil | +0.365 |
FontSize | +0.343 |
Neg logit contributions | |
�� | -0.821 |
�� | -0.736 |
�� | -0.688 |
�� | -0.626 |
�� | -0.616 |
Token | , |
Token ID | 11 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
phabet | +2.969 |
acebook | +2.961 |
utherland | +2.945 |
Civil | +2.760 |
sung | +2.499 |
Neg logit contributions | |
�� | -6.248 |
�� | -5.655 |
�� | -5.216 |
�� | -4.796 |
�� | -4.696 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
acebook | +1.463 |
phabet | +1.459 |
utherland | +1.448 |
Civil | +1.338 |
FontSize | +1.233 |
Neg logit contributions | |
�� | -3.197 |
�� | -2.877 |
�� | -2.686 |
�� | -2.458 |
�� | -2.414 |
Token | hold |
Token ID | 1745 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
acebook | +2.762 |
phabet | +2.735 |
utherland | +2.712 |
Civil | +2.549 |
sung | +2.264 |
Neg logit contributions | |
�� | -6.996 |
�� | -6.299 |
�� | -5.898 |
�� | -5.422 |
�� | -5.332 |
Token | $ |
Token ID | 720 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
acebook | +1.344 |
phabet | +1.336 |
utherland | +1.325 |
Civil | +1.233 |
sung | +1.130 |
Neg logit contributions | |
�� | -2.885 |
�� | -2.586 |
�� | -2.418 |
�� | -2.213 |
�� | -2.173 |
Token | 185 |
Token ID | 21652 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
acebook | +1.777 |
utherland | +1.771 |
phabet | +1.768 |
Civil | +1.624 |
FontSize | +1.511 |
Neg logit contributions | |
�� | -4.112 |
�� | -3.714 |
�� | -3.470 |
�� | -3.197 |
�� | -3.116 |
Token | million |
Token ID | 1510 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
acebook | +0.043 |
phabet | +0.042 |
utherland | +0.042 |
Civil | +0.038 |
FontSize | +0.036 |
Neg logit contributions | |
�� | -0.099 |
�� | -0.089 |
�� | -0.084 |
�� | -0.077 |
�� | -0.075 |
Token | in |
Token ID | 287 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
phabet | +3.349 |
acebook | +3.341 |
utherland | +3.299 |
Civil | +3.067 |
sung | +2.761 |
Neg logit contributions | |
�� | -8.714 |
�� | -7.881 |
�� | -7.398 |
�� | -6.855 |
�� | -6.699 |
Token | un |
Token ID | 555 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
acebook | +3.567 |
phabet | +3.535 |
utherland | +3.523 |
Civil | +3.402 |
sung | +3.037 |
Neg logit contributions | |
�� | -7.559 |
�� | -6.753 |
�� | -6.326 |
�� | -5.794 |
�� | -5.708 |
Token | sec |
Token ID | 2363 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
phabet | +6.776 |
utherland | +6.681 |
acebook | +6.410 |
ro | +6.248 |
sung | +6.039 |
Neg logit contributions | |
�� | -20.499 |
�� | -18.527 |
�� | -17.743 |
�� | -16.310 |
�� | -15.946 |
Token | ured |
Token ID | 1522 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
acebook | +1.572 |
phabet | +1.552 |
utherland | +1.544 |
Civil | +1.293 |
sung | +1.120 |
Neg logit contributions | |
�� | -8.571 |
�� | -7.834 |
�� | -7.466 |
�� | -7.026 |
�� | -6.876 |
Token | loans |
Token ID | 10021 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
acebook | +4.162 |
phabet | +4.132 |
utherland | +4.080 |
Civil | +3.985 |
sung | +3.559 |
Neg logit contributions | |
�� | -8.311 |
�� | -7.397 |
�� | -6.884 |
�� | -6.335 |
�� | -6.188 |
Token | . |
Token ID | 13 |
Feature activation | -5.58e+00 |
Pos logit contributions | |
phabet | +3.117 |
acebook | +3.107 |
utherland | +3.067 |
Civil | +2.898 |
FontSize | +2.594 |
Neg logit contributions | |
�� | -8.057 |
�� | -7.287 |
�� | -6.794 |
�� | -6.319 |
�� | -6.164 |
Token | The |
Token ID | 383 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
acebook | +3.536 |
utherland | +3.457 |
phabet | +3.449 |
Civil | +3.365 |
sung | +2.897 |
Neg logit contributions | |
�� | -8.647 |
�� | -7.826 |
�� | -7.371 |
�� | -6.808 |
�� | -6.603 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
acebook | +7.387 |
utherland | +7.331 |
phabet | +7.217 |
Civil | +6.947 |
LINK | +6.368 |
Neg logit contributions | |
�� | -20.911 |
�� | -18.880 |
�� | -18.044 |
�� | -16.711 |
�� | -16.617 |
Token | GROUP |
Token ID | 44441 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
acebook | +1.975 |
phabet | +1.963 |
utherland | +1.954 |
Civil | +1.803 |
FontSize | +1.641 |
Neg logit contributions | |
�� | -5.168 |
�� | -4.675 |
�� | -4.398 |
�� | -4.050 |
�� | -3.992 |
Token | BY |
Token ID | 11050 |
Feature activation | -8.82e+00 |
Pos logit contributions | |
utherland | +1.340 |
phabet | +1.330 |
acebook | +1.317 |
Civil | +1.185 |
sung | +1.035 |
Neg logit contributions | |
�� | -5.105 |
�� | -4.671 |
�� | -4.409 |
�� | -4.110 |
�� | -4.025 |
Token | library |
Token ID | 5888 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
utherland | +5.213 |
phabet | +5.197 |
acebook | +5.190 |
Civil | +4.909 |
LINK | +4.470 |
Neg logit contributions | |
�� | -13.430 |
�� | -12.086 |
�� | -11.599 |
�� | -10.573 |
�� | -10.399 |
Token | , |
Token ID | 837 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
phabet | +6.454 |
utherland | +6.331 |
acebook | +6.322 |
Civil | +6.020 |
LINK | +5.479 |
Neg logit contributions | |
�� | -17.347 |
�� | -15.585 |
�� | -14.844 |
�� | -13.858 |
�� | -13.624 |
Token | version |
Token ID | 2196 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
phabet | +3.288 |
utherland | +3.280 |
acebook | +3.255 |
Civil | +3.056 |
FontSize | +2.724 |
Neg logit contributions | |
�� | -8.373 |
�� | -7.586 |
�� | -7.166 |
�� | -6.585 |
�� | -6.477 |
Token | H |
Token ID | 367 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
phabet | +7.076 |
utherland | +7.002 |
acebook | +6.969 |
Civil | +6.654 |
LINK | +6.054 |
Neg logit contributions | |
�� | -19.439 |
�� | -17.535 |
�� | -16.728 |
�� | -15.514 |
�� | -15.327 |
Token | AV |
Token ID | 10116 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
acebook | +0.455 |
phabet | +0.453 |
utherland | +0.448 |
Civil | +0.395 |
FontSize | +0.356 |
Neg logit contributions | |
�� | -1.643 |
�� | -1.499 |
�� | -1.414 |
�� | -1.309 |
�� | -1.290 |
Token | ING |
Token ID | 2751 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
acebook | +0.446 |
phabet | +0.444 |
utherland | +0.442 |
Civil | +0.410 |
FontSize | +0.388 |
Neg logit contributions | |
�� | -0.806 |
�� | -0.719 |
�� | -0.669 |
�� | -0.607 |
�� | -0.595 |
Token | library |
Token ID | 5888 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
utherland | +7.429 |
phabet | +7.225 |
acebook | +7.213 |
Civil | +6.974 |
LINK | +6.557 |
Neg logit contributions | |
�� | -18.160 |
�� | -16.201 |
�� | -15.664 |
�� | -14.213 |
�� | -14.035 |
Token | is |
Token ID | 318 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
utherland | +5.224 |
phabet | +5.201 |
acebook | +5.109 |
Civil | +4.783 |
LINK | +4.382 |
Neg logit contributions | |
�� | -15.786 |
�� | -14.320 |
�� | -13.450 |
�� | -12.596 |
�� | -12.483 |
Token | 49 |
Token ID | 5125 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
acebook | +0.589 |
phabet | +0.586 |
utherland | +0.582 |
Civil | +0.535 |
FontSize | +0.499 |
Neg logit contributions | |
�� | -1.269 |
�� | -1.141 |
�� | -1.066 |
�� | -0.972 |
�� | -0.956 |
Token | ers |
Token ID | 364 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
acebook | +0.303 |
phabet | +0.302 |
utherland | +0.297 |
Civil | +0.266 |
FontSize | +0.250 |
Neg logit contributions | |
�� | -0.813 |
�� | -0.734 |
�� | -0.689 |
�� | -0.634 |
�� | -0.625 |
Token | quarterback |
Token ID | 7880 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
acebook | +0.877 |
phabet | +0.876 |
utherland | +0.868 |
Civil | +0.797 |
FontSize | +0.740 |
Neg logit contributions | |
�� | -1.961 |
�� | -1.765 |
�� | -1.652 |
�� | -1.509 |
�� | -1.483 |
Token | for |
Token ID | 329 |
Feature activation | -7.85e+00 |
Pos logit contributions | |
phabet | +2.736 |
acebook | +2.722 |
utherland | +2.706 |
Civil | +2.526 |
sung | +2.300 |
Neg logit contributions | |
�� | -6.481 |
�� | -5.865 |
�� | -5.480 |
�� | -5.017 |
�� | -4.916 |
Token | almost |
Token ID | 2048 |
Feature activation | -9.28e+00 |
Pos logit contributions | |
phabet | +4.726 |
acebook | +4.690 |
utherland | +4.680 |
Civil | +4.594 |
sung | +4.021 |
Neg logit contributions | |
�� | -11.984 |
�� | -10.897 |
�� | -10.201 |
�� | -9.430 |
�� | -9.096 |
Token | the |
Token ID | 262 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
Civil | +5.128 |
acebook | +5.119 |
utherland | +5.018 |
phabet | +4.912 |
ro | +4.376 |
Neg logit contributions | |
�� | -14.521 |
�� | -13.214 |
�� | -12.317 |
�� | -11.556 |
�� | -11.187 |
Token | entire |
Token ID | 2104 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
Civil | +4.813 |
acebook | +4.279 |
utherland | +4.181 |
phabet | +4.043 |
namesake | +3.570 |
Neg logit contributions | |
�� | -22.288 |
�� | -20.435 |
�� | -19.335 |
�� | -18.067 |
�� | -17.820 |
Token | four |
Token ID | 1440 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
acebook | +3.355 |
utherland | +3.316 |
phabet | +3.296 |
Civil | +3.220 |
sung | +2.800 |
Neg logit contributions | |
�� | -8.694 |
�� | -7.876 |
�� | -7.365 |
�� | -6.799 |
�� | -6.646 |
Token | hours |
Token ID | 2250 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
�� | +0.089 |
�� | +0.079 |
�� | +0.074 |
�� | +0.067 |
�� | +0.066 |
Neg logit contributions | |
acebook | -0.046 |
phabet | -0.045 |
utherland | -0.045 |
Civil | -0.041 |
FontSize | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
phabet | +1.399 |
acebook | +1.398 |
utherland | +1.384 |
Civil | +1.283 |
FontSize | +1.188 |
Neg logit contributions | |
�� | -3.080 |
�� | -2.768 |
�� | -2.590 |
�� | -2.366 |
�� | -2.328 |
Token | The |
Token ID | 383 |
Feature activation | +1.09e-03 |
Pos logit contributions | |
�� | +0.211 |
�� | +0.190 |
�� | +0.177 |
�� | +0.162 |
�� | +0.160 |
Neg logit contributions | |
acebook | -0.095 |
phabet | -0.095 |
utherland | -0.093 |
Civil | -0.084 |
FontSize | -0.080 |
Token | evidence |
Token ID | 2370 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
�� | +2.549 |
�� | +2.294 |
�� | +2.139 |
�� | +1.954 |
�� | +1.919 |
Neg logit contributions | |
acebook | -1.172 |
phabet | -1.170 |
utherland | -1.148 |
Civil | -1.027 |
FontSize | -1.003 |
Token | and |
Token ID | 290 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
�� | +3.217 |
�� | +2.889 |
�� | +2.701 |
�� | +2.456 |
�� | +2.417 |
Neg logit contributions | |
acebook | -1.526 |
phabet | -1.509 |
utherland | -1.502 |
Civil | -1.357 |
FontSize | -1.299 |
Token | interviewing |
Token ID | 31481 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
�� | +3.311 |
�� | +2.967 |
�� | +2.758 |
�� | +2.523 |
�� | +2.473 |
Neg logit contributions | |
phabet | -1.675 |
acebook | -1.670 |
utherland | -1.652 |
Civil | -1.465 |
FontSize | -1.425 |
Token | numerous |
Token ID | 6409 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
�� | +3.252 |
�� | +2.931 |
�� | +2.736 |
�� | +2.513 |
�� | +2.463 |
Neg logit contributions | |
phabet | -1.349 |
acebook | -1.340 |
utherland | -1.313 |
Civil | -1.160 |
FontSize | -1.133 |
Token | current |
Token ID | 1459 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
acebook | +0.552 |
phabet | +0.549 |
utherland | +0.544 |
Civil | +0.493 |
FontSize | +0.453 |
Neg logit contributions | |
�� | -1.484 |
�� | -1.344 |
�� | -1.263 |
�� | -1.159 |
�� | -1.143 |
Token | and |
Token ID | 290 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
�� | +0.620 |
�� | +0.557 |
�� | +0.521 |
�� | +0.476 |
�� | +0.468 |
Neg logit contributions | |
acebook | -0.281 |
phabet | -0.281 |
utherland | -0.277 |
Civil | -0.252 |
FontSize | -0.238 |
Token | former |
Token ID | 1966 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
acebook | +4.058 |
Civil | +3.890 |
phabet | +3.774 |
utherland | +3.759 |
ro | +3.126 |
Neg logit contributions | |
�� | -22.220 |
�� | -20.602 |
�� | -19.870 |
�� | -18.585 |
�� | -18.156 |
Token | Shotgun |
Token ID | 34198 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
acebook | +0.442 |
phabet | +0.440 |
utherland | +0.437 |
Civil | +0.400 |
FontSize | +0.371 |
Neg logit contributions | |
�� | -1.023 |
�� | -0.922 |
�� | -0.864 |
�� | -0.789 |
�� | -0.777 |
Token | Willie |
Token ID | 28623 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
acebook | +0.839 |
phabet | +0.836 |
utherland | +0.832 |
Civil | +0.772 |
FontSize | +0.721 |
Neg logit contributions | |
�� | -1.574 |
�� | -1.410 |
�� | -1.315 |
�� | -1.192 |
�� | -1.171 |
Token | � |
Token ID | 447 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
�� | +5.262 |
�� | +4.675 |
�� | +4.356 |
�� | +3.971 |
�� | +3.933 |
Neg logit contributions | |
phabet | -2.611 |
acebook | -2.589 |
utherland | -2.535 |
Civil | -2.289 |
FontSize | -2.244 |
Token | � |
Token ID | 247 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
phabet | +3.560 |
acebook | +3.527 |
utherland | +3.518 |
Civil | +3.396 |
FontSize | +3.288 |
Neg logit contributions | |
�� | -1.961 |
�� | -1.573 |
�� | -1.380 |
�� | -1.077 |
�� | -1.030 |
Token | "( |
Token ID | 18109 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
acebook | +1.862 |
phabet | +1.859 |
utherland | +1.843 |
Civil | +1.695 |
FontSize | +1.591 |
Neg logit contributions | |
�� | -3.990 |
�� | -3.569 |
�� | -3.357 |
�� | -3.062 |
�� | -3.013 |
Token | \ |
Token ID | 59 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
phabet | +3.089 |
acebook | +3.077 |
utherland | +3.048 |
Civil | +2.786 |
FontSize | +2.646 |
Neg logit contributions | |
�� | -7.251 |
�� | -6.475 |
�� | -6.149 |
�� | -5.605 |
�� | -5.544 |
Token | S |
Token ID | 50 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
utherland | +4.374 |
acebook | +4.353 |
phabet | +4.293 |
Civil | +3.935 |
FontSize | +3.905 |
Neg logit contributions | |
�� | -16.574 |
�� | -14.881 |
�� | -14.212 |
�� | -13.174 |
�� | -12.868 |
Token | +) |
Token ID | 28988 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
�� | +5.539 |
�� | +5.027 |
�� | +4.643 |
�� | +4.253 |
�� | +4.187 |
Neg logit contributions | |
phabet | -2.443 |
acebook | -2.431 |
utherland | -2.402 |
Civil | -2.175 |
sung | -2.044 |
Token | "] |
Token ID | 8973 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
acebook | +1.231 |
phabet | +1.227 |
utherland | +1.217 |
Civil | +1.116 |
FontSize | +1.045 |
Neg logit contributions | |
�� | -2.758 |
�� | -2.476 |
�� | -2.325 |
�� | -2.125 |
�� | -2.088 |
Token | ' |
Token ID | 6 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
acebook | +1.878 |
phabet | +1.870 |
utherland | +1.851 |
Civil | +1.706 |
FontSize | +1.587 |
Neg logit contributions | |
�� | -4.403 |
�� | -3.950 |
�� | -3.727 |
�� | -3.403 |
�� | -3.354 |
Token | ) |
Token ID | 1267 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
phabet | +4.420 |
utherland | +4.418 |
acebook | +4.414 |
Civil | +3.660 |
sung | +3.221 |
Neg logit contributions | |
�� | -21.597 |
�� | -19.662 |
�� | -18.900 |
�� | -17.650 |
�� | -17.446 |
Token | AS |
Token ID | 7054 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
acebook | +1.490 |
phabet | +1.484 |
utherland | +1.474 |
Civil | +1.351 |
FontSize | +1.243 |
Neg logit contributions | |
�� | -3.706 |
�� | -3.346 |
�� | -3.141 |
�� | -2.891 |
�� | -2.840 |
Token | version |
Token ID | 2196 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
acebook | +3.594 |
utherland | +3.589 |
phabet | +3.576 |
Civil | +3.345 |
FontSize | +3.001 |
Neg logit contributions | |
�� | -8.829 |
�� | -7.937 |
�� | -7.514 |
�� | -6.920 |
�� | -6.801 |
Token | , |
Token ID | 837 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
utherland | +6.057 |
phabet | +5.923 |
acebook | +5.872 |
Civil | +5.413 |
sung | +4.890 |
Neg logit contributions | |
�� | -18.484 |
�� | -16.833 |
�� | -15.909 |
�� | -14.825 |
�� | -14.816 |
Token | C |
Token ID | 327 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
acebook | +4.363 |
utherland | +4.356 |
phabet | +4.330 |
Civil | +4.112 |
FontSize | +3.734 |
Neg logit contributions | |
�� | -9.673 |
�� | -8.740 |
�� | -8.224 |
�� | -7.527 |
�� | -7.400 |
Token | and |
Token ID | 290 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
acebook | +2.632 |
phabet | +2.621 |
utherland | +2.605 |
Civil | +2.424 |
sung | +2.204 |
Neg logit contributions | |
�� | -6.622 |
�� | -6.017 |
�� | -5.646 |
�� | -5.166 |
�� | -5.060 |
Token | Mill |
Token ID | 9212 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
acebook | +2.099 |
phabet | +2.084 |
utherland | +2.066 |
Civil | +1.957 |
sung | +1.744 |
Neg logit contributions | |
�� | -5.280 |
�� | -4.772 |
�� | -4.505 |
�� | -4.124 |
�� | -4.025 |
Token | Rd |
Token ID | 20769 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
�� | +1.395 |
�� | +1.256 |
�� | +1.175 |
�� | +1.072 |
�� | +1.056 |
Neg logit contributions | |
acebook | -0.614 |
phabet | -0.611 |
utherland | -0.604 |
Civil | -0.550 |
FontSize | -0.518 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
�� | +6.872 |
�� | +6.176 |
�� | +5.729 |
�� | +5.302 |
�� | +5.225 |
Neg logit contributions | |
acebook | -3.363 |
phabet | -3.326 |
utherland | -3.320 |
Civil | -2.981 |
FontSize | -2.896 |
Token | in |
Token ID | 287 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
acebook | +1.158 |
phabet | +1.152 |
utherland | +1.142 |
Civil | +1.043 |
sung | +0.959 |
Neg logit contributions | |
�� | -2.891 |
�� | -2.612 |
�� | -2.450 |
�� | -2.244 |
�� | -2.206 |
Token | Et |
Token ID | 17906 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
acebook | +1.081 |
phabet | +1.078 |
utherland | +1.068 |
Civil | +0.989 |
FontSize | +0.906 |
Neg logit contributions | |
�� | -2.622 |
�� | -2.367 |
�� | -2.224 |
�� | -2.033 |
�� | -1.998 |
Token | obic |
Token ID | 20803 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
utherland | +5.844 |
phabet | +5.509 |
acebook | +5.381 |
ro | +5.246 |
Civil | +4.911 |
Neg logit contributions | |
�� | -20.616 |
�� | -19.215 |
�� | -18.271 |
�� | -17.080 |
�� | -16.591 |
Token | oke |
Token ID | 2088 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
acebook | +2.219 |
phabet | +2.219 |
utherland | +2.202 |
Civil | +2.072 |
FontSize | +1.979 |
Neg logit contributions | |
�� | -2.867 |
�� | -2.515 |
�� | -2.309 |
�� | -2.056 |
�� | -2.012 |
Token | � |
Token ID | 447 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
acebook | +2.912 |
phabet | +2.911 |
utherland | +2.873 |
Civil | +2.753 |
sung | +2.471 |
Neg logit contributions | |
�� | -7.646 |
�� | -6.935 |
�� | -6.451 |
�� | -5.979 |
�� | -5.815 |
Token | � |
Token ID | 247 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
phabet | +2.683 |
utherland | +2.660 |
acebook | +2.623 |
Civil | +2.568 |
FontSize | +2.492 |
Neg logit contributions | |
�� | -1.543 |
�� | -1.248 |
�� | -1.098 |
�� | -0.877 |
�� | -0.829 |
Token | s |
Token ID | 82 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
�� | +1.491 |
�� | +1.344 |
�� | +1.258 |
�� | +1.150 |
�� | +1.134 |
Neg logit contributions | |
acebook | -0.643 |
phabet | -0.642 |
utherland | -0.634 |
Civil | -0.575 |
FontSize | -0.543 |
Token | , |
Token ID | 11 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
acebook | +0.282 |
phabet | +0.281 |
utherland | +0.278 |
Civil | +0.253 |
FontSize | +0.235 |
Neg logit contributions | |
�� | -0.684 |
�� | -0.617 |
�� | -0.578 |
�� | -0.530 |
�� | -0.521 |
Token | HI |
Token ID | 36210 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
acebook | +1.144 |
phabet | +1.141 |
utherland | +1.130 |
Civil | +1.036 |
FontSize | +0.962 |
Neg logit contributions | |
�� | -2.692 |
�� | -2.429 |
�� | -2.275 |
�� | -2.084 |
�� | -2.049 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
phabet | +4.217 |
utherland | +4.171 |
acebook | +4.164 |
Civil | +3.926 |
ro | +3.550 |
Neg logit contributions | |
�� | -9.752 |
�� | -8.829 |
�� | -8.309 |
�� | -7.655 |
�� | -7.388 |
Token | born |
Token ID | 4642 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
acebook | +1.073 |
phabet | +1.070 |
utherland | +1.059 |
Civil | +0.967 |
FontSize | +0.897 |
Neg logit contributions | |
�� | -2.585 |
�� | -2.335 |
�� | -2.187 |
�� | -2.005 |
�� | -1.971 |
Token | at |
Token ID | 379 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
acebook | +1.156 |
phabet | +1.153 |
utherland | +1.142 |
Civil | +1.045 |
FontSize | +0.965 |
Neg logit contributions | |
�� | -2.815 |
�� | -2.543 |
�� | -2.383 |
�� | -2.188 |
�� | -2.150 |
Token | Gu |
Token ID | 1962 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
acebook | +1.488 |
utherland | +1.477 |
phabet | +1.477 |
Civil | +1.373 |
FontSize | +1.257 |
Neg logit contributions | |
�� | -3.512 |
�� | -3.173 |
�� | -2.976 |
�� | -2.731 |
�� | -2.671 |
Token | adal |
Token ID | 31682 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
acebook | +7.979 |
utherland | +7.948 |
phabet | +7.916 |
Civil | +7.152 |
ro | +6.831 |
Neg logit contributions | |
�� | -18.184 |
�� | -16.392 |
�� | -15.811 |
�� | -14.450 |
�� | -13.964 |
Token | upe |
Token ID | 48722 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
phabet | +2.966 |
acebook | +2.939 |
utherland | +2.929 |
Civil | +2.747 |
sung | +2.577 |
Neg logit contributions | |
�� | -5.157 |
�� | -4.618 |
�� | -4.297 |
�� | -3.904 |
�� | -3.807 |
Token | Valley |
Token ID | 6916 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
�� | +3.101 |
�� | +2.782 |
�� | +2.599 |
�� | +2.370 |
�� | +2.341 |
Neg logit contributions | |
acebook | -1.391 |
phabet | -1.384 |
utherland | -1.363 |
Civil | -1.224 |
FontSize | -1.173 |
Token | Hospital |
Token ID | 9256 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
�� | +2.639 |
�� | +2.356 |
�� | +2.195 |
�� | +1.993 |
�� | +1.966 |
Neg logit contributions | |
acebook | -1.330 |
phabet | -1.330 |
utherland | -1.307 |
Civil | -1.183 |
FontSize | -1.135 |
Token | on |
Token ID | 319 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
�� | +3.958 |
�� | +3.538 |
�� | +3.311 |
�� | +3.008 |
�� | +2.977 |
Neg logit contributions | |
acebook | -1.757 |
phabet | -1.748 |
utherland | -1.725 |
Civil | -1.533 |
FontSize | -1.481 |
Token | could |
Token ID | 714 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
acebook | +1.507 |
phabet | +1.506 |
utherland | +1.491 |
Civil | +1.382 |
FontSize | +1.245 |
Neg logit contributions | |
�� | -4.030 |
�� | -3.655 |
�� | -3.441 |
�� | -3.153 |
�� | -3.106 |
Token | receive |
Token ID | 3328 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
acebook | +1.007 |
phabet | +1.005 |
utherland | +0.997 |
Civil | +0.913 |
FontSize | +0.827 |
Neg logit contributions | |
�� | -2.752 |
�� | -2.492 |
�� | -2.349 |
�� | -2.153 |
�� | -2.116 |
Token | the |
Token ID | 262 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
�� | +1.673 |
�� | +1.498 |
�� | +1.394 |
�� | +1.265 |
�� | +1.245 |
Neg logit contributions | |
phabet | -0.843 |
acebook | -0.842 |
utherland | -0.832 |
Civil | -0.747 |
sung | -0.718 |
Token | same |
Token ID | 976 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
�� | +4.814 |
�� | +4.298 |
�� | +4.010 |
�� | +3.643 |
�� | +3.591 |
Neg logit contributions | |
phabet | -2.354 |
acebook | -2.341 |
utherland | -2.306 |
Civil | -1.995 |
FontSize | -1.991 |
Token | treatment |
Token ID | 3513 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
�� | +5.704 |
�� | +5.041 |
�� | +4.698 |
�� | +4.213 |
�� | +4.159 |
Neg logit contributions | |
phabet | -3.305 |
acebook | -3.295 |
utherland | -3.244 |
sung | -2.857 |
FontSize | -2.834 |
Token | all |
Token ID | 477 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
�� | +4.349 |
�� | +3.876 |
�� | +3.603 |
�� | +3.267 |
�� | +3.238 |
Neg logit contributions | |
acebook | -2.188 |
phabet | -2.166 |
utherland | -2.149 |
Civil | -1.893 |
FontSize | -1.860 |
Token | of |
Token ID | 286 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
�� | +10.274 |
�� | +9.038 |
�� | +8.224 |
�� | +7.529 |
�� | +7.440 |
Neg logit contributions | |
acebook | -6.120 |
phabet | -6.066 |
utherland | -6.015 |
sung | -5.288 |
FontSize | -5.263 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
�� | +7.823 |
�� | +6.986 |
�� | +6.337 |
�� | +5.804 |
�� | +5.796 |
Neg logit contributions | |
utherland | -4.354 |
acebook | -4.343 |
phabet | -4.288 |
sung | -3.762 |
Civil | -3.757 |
Token | other |
Token ID | 584 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
�� | +1.954 |
�� | +1.761 |
�� | +1.650 |
�� | +1.512 |
�� | +1.488 |
Neg logit contributions | |
phabet | -0.798 |
acebook | -0.797 |
utherland | -0.786 |
Civil | -0.699 |
FontSize | -0.666 |
Token | married |
Token ID | 6405 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
�� | +2.330 |
�� | +2.085 |
�� | +1.951 |
�� | +1.774 |
�� | +1.751 |
Neg logit contributions | |
phabet | -1.109 |
acebook | -1.107 |
utherland | -1.091 |
Civil | -0.969 |
FontSize | -0.938 |
Token | employees |
Token ID | 4409 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
�� | +2.605 |
�� | +2.327 |
�� | +2.169 |
�� | +1.967 |
�� | +1.940 |
Neg logit contributions | |
acebook | -1.330 |
phabet | -1.329 |
utherland | -1.313 |
Civil | -1.166 |
FontSize | -1.135 |
Token | omb |
Token ID | 2381 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
�� | +9.122 |
�� | +8.209 |
�� | +7.739 |
�� | +6.994 |
�� | +6.953 |
Neg logit contributions | |
acebook | -3.787 |
phabet | -3.772 |
utherland | -3.662 |
Civil | -3.475 |
FontSize | -3.261 |
Token | ied |
Token ID | 798 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
�� | +5.445 |
�� | +4.892 |
�� | +4.571 |
�� | +4.157 |
�� | +4.106 |
Neg logit contributions | |
acebook | -2.394 |
phabet | -2.380 |
utherland | -2.350 |
Civil | -2.188 |
FontSize | -2.055 |
Token | unk |
Token ID | 2954 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
phabet | +1.195 |
acebook | +1.194 |
utherland | +1.183 |
Civil | +1.068 |
sung | +0.997 |
Neg logit contributions | |
�� | -2.872 |
�� | -2.594 |
�� | -2.431 |
�� | -2.227 |
�� | -2.189 |
Token | > |
Token ID | 29 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
�� | +6.409 |
�� | +5.792 |
�� | +5.423 |
�� | +4.981 |
�� | +4.902 |
Neg logit contributions | |
acebook | -2.295 |
phabet | -2.276 |
utherland | -2.225 |
Civil | -2.044 |
FontSize | -1.889 |
Token | lol |
Token ID | 19462 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
�� | +4.498 |
�� | +4.044 |
�� | +3.765 |
�� | +3.438 |
�� | +3.389 |
Neg logit contributions | |
acebook | -2.067 |
phabet | -2.055 |
utherland | -2.044 |
Civil | -1.817 |
FontSize | -1.762 |
Token | m |
Token ID | 285 |
Feature activation | +7.30e+00 |
Pos logit contributions | |
�� | +8.797 |
�� | +7.885 |
�� | +7.282 |
�� | +6.575 |
�� | +6.524 |
Neg logit contributions | |
acebook | -4.799 |
phabet | -4.767 |
utherland | -4.757 |
Civil | -4.276 |
FontSize | -4.184 |
Token | 2 |
Token ID | 17 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
�� | +9.852 |
�� | +8.894 |
�� | +8.145 |
�� | +7.255 |
�� | +7.205 |
Neg logit contributions | |
acebook | -5.755 |
utherland | -5.751 |
phabet | -5.682 |
Civil | -5.205 |
FontSize | -5.170 |
Token | k |
Token ID | 74 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
�� | +6.251 |
�� | +5.465 |
�� | +5.015 |
�� | +4.498 |
�� | +4.434 |
Neg logit contributions | |
acebook | -4.365 |
phabet | -4.252 |
utherland | -4.203 |
Civil | -3.842 |
FontSize | -3.783 |
Token | [ |
Token ID | 685 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
�� | +6.933 |
�� | +6.167 |
�� | +5.695 |
�� | +5.088 |
�� | +5.040 |
Neg logit contributions | |
acebook | -4.375 |
phabet | -4.332 |
utherland | -4.260 |
Civil | -3.851 |
FontSize | -3.804 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
phabet | +1.394 |
acebook | +1.390 |
utherland | +1.382 |
Civil | +1.262 |
FontSize | +1.173 |
Neg logit contributions | |
�� | -3.507 |
�� | -3.172 |
�� | -2.978 |
�� | -2.735 |
�� | -2.684 |
Token | : |
Token ID | 25 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
acebook | +1.080 |
phabet | +1.078 |
utherland | +1.068 |
Civil | +0.975 |
FontSize | +0.907 |
Neg logit contributions | |
�� | -2.591 |
�� | -2.339 |
�� | -2.191 |
�� | -2.008 |
�� | -1.973 |
Token | 17 |
Token ID | 1596 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
acebook | +1.717 |
phabet | +1.711 |
utherland | +1.700 |
Civil | +1.567 |
FontSize | +1.446 |
Neg logit contributions | |
�� | -3.782 |
�� | -3.403 |
�� | -3.190 |
�� | -2.912 |
�� | -2.864 |
Token | known |
Token ID | 1900 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
phabet | +4.501 |
utherland | +4.471 |
acebook | +4.427 |
Civil | +4.179 |
ro | +3.805 |
Neg logit contributions | |
�� | -9.624 |
�� | -8.645 |
�� | -8.080 |
�� | -7.406 |
�� | -7.210 |
Token | species |
Token ID | 4693 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
phabet | +4.006 |
utherland | +3.991 |
acebook | +3.981 |
Civil | +3.812 |
sung | +3.478 |
Neg logit contributions | |
�� | -8.515 |
�� | -7.652 |
�� | -7.147 |
�� | -6.556 |
�� | -6.378 |
Token | of |
Token ID | 286 |
Feature activation | -6.61e+00 |
Pos logit contributions | |
�� | +7.515 |
�� | +6.736 |
�� | +6.234 |
�� | +5.620 |
�� | +5.596 |
Neg logit contributions | |
acebook | -3.755 |
utherland | -3.677 |
phabet | -3.673 |
Civil | -3.280 |
FontSize | -3.176 |
Token | rock |
Token ID | 3881 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
acebook | +4.192 |
phabet | +4.183 |
utherland | +4.151 |
Civil | +3.980 |
ro | +3.620 |
Neg logit contributions | |
�� | -10.035 |
�� | -9.010 |
�� | -8.530 |
�� | -7.800 |
�� | -7.577 |
Token | - |
Token ID | 12 |
Feature activation | +7.47e+00 |
Pos logit contributions | |
�� | +3.315 |
�� | +2.972 |
�� | +2.766 |
�� | +2.529 |
�� | +2.479 |
Neg logit contributions | |
phabet | -1.653 |
acebook | -1.650 |
utherland | -1.636 |
Civil | -1.502 |
FontSize | -1.428 |
Token | wall |
Token ID | 11930 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
�� | +9.505 |
�� | +8.409 |
�� | +7.622 |
�� | +6.936 |
�� | +6.815 |
Neg logit contributions | |
acebook | -6.385 |
phabet | -6.219 |
utherland | -6.176 |
Civil | -5.898 |
FontSize | -5.672 |
Token | abies |
Token ID | 43256 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
acebook | +0.705 |
phabet | +0.704 |
utherland | +0.699 |
Civil | +0.660 |
FontSize | +0.633 |
Neg logit contributions | |
�� | -0.795 |
�� | -0.691 |
�� | -0.631 |
�� | -0.555 |
�� | -0.542 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
phabet | +0.947 |
acebook | +0.947 |
utherland | +0.937 |
Civil | +0.862 |
FontSize | +0.803 |
Neg logit contributions | |
�� | -2.068 |
�� | -1.859 |
�� | -1.739 |
�� | -1.590 |
�� | -1.561 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
acebook | +1.435 |
phabet | +1.433 |
utherland | +1.422 |
Civil | +1.310 |
FontSize | +1.196 |
Neg logit contributions | |
�� | -3.542 |
�� | -3.199 |
�� | -3.003 |
�� | -2.760 |
�� | -2.703 |
Token |
|
Token ID | 198 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
�� | +2.125 |
�� | +1.897 |
�� | +1.767 |
�� | +1.600 |
�� | +1.591 |
Neg logit contributions | |
acebook | -1.005 |
phabet | -0.983 |
utherland | -0.959 |
Civil | -0.837 |
FontSize | -0.804 |
Token | that |
Token ID | 326 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
acebook | +0.441 |
phabet | +0.440 |
utherland | +0.436 |
Civil | +0.401 |
FontSize | +0.376 |
Neg logit contributions | |
�� | -0.914 |
�� | -0.820 |
�� | -0.766 |
�� | -0.698 |
�� | -0.686 |
Token | can |
Token ID | 460 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
acebook | +0.461 |
phabet | +0.460 |
utherland | +0.455 |
Civil | +0.415 |
FontSize | +0.385 |
Neg logit contributions | |
�� | -1.124 |
�� | -1.014 |
�� | -0.951 |
�� | -0.871 |
�� | -0.857 |
Token | � |
Token ID | 447 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
�� | +2.815 |
�� | +2.544 |
�� | +2.380 |
�� | +2.180 |
�� | +2.150 |
Neg logit contributions | |
acebook | -1.176 |
phabet | -1.167 |
utherland | -1.156 |
Civil | -1.042 |
FontSize | -0.984 |
Token | � |
Token ID | 247 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
phabet | +1.509 |
acebook | +1.496 |
utherland | +1.492 |
Civil | +1.438 |
FontSize | +1.398 |
Neg logit contributions | |
�� | -0.870 |
�� | -0.707 |
�� | -0.617 |
�� | -0.493 |
�� | -0.469 |
Token | t |
Token ID | 83 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
�� | +2.583 |
�� | +2.329 |
�� | +2.184 |
�� | +2.003 |
�� | +1.969 |
Neg logit contributions | |
acebook | -1.056 |
phabet | -1.046 |
utherland | -1.037 |
Civil | -0.935 |
FontSize | -0.876 |
Token | be |
Token ID | 307 |
Feature activation | +7.74e+00 |
Pos logit contributions | |
�� | +2.575 |
�� | +2.326 |
�� | +2.178 |
�� | +1.991 |
�� | +1.969 |
Neg logit contributions | |
acebook | -1.088 |
phabet | -1.080 |
utherland | -1.067 |
Civil | -0.963 |
FontSize | -0.907 |
Token | resolved |
Token ID | 12939 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
�� | +11.295 |
�� | +10.259 |
�� | +9.413 |
�� | +8.735 |
�� | +8.602 |
Neg logit contributions | |
phabet | -5.330 |
acebook | -5.204 |
utherland | -5.188 |
Civil | -4.444 |
FontSize | -4.327 |
Token | by |
Token ID | 416 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
�� | +4.924 |
�� | +4.437 |
�� | +4.110 |
�� | +3.728 |
�� | +3.708 |
Neg logit contributions | |
acebook | -2.449 |
phabet | -2.431 |
utherland | -2.418 |
Civil | -2.153 |
FontSize | -2.090 |
Token | a |
Token ID | 257 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
�� | +0.680 |
�� | +0.611 |
�� | +0.569 |
�� | +0.518 |
�� | +0.510 |
Neg logit contributions | |
acebook | -0.331 |
phabet | -0.329 |
utherland | -0.326 |
Civil | -0.295 |
FontSize | -0.281 |
Token | qu |
Token ID | 627 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
�� | +2.473 |
�� | +2.221 |
�� | +2.073 |
�� | +1.886 |
�� | +1.860 |
Neg logit contributions | |
acebook | -1.202 |
phabet | -1.186 |
utherland | -1.183 |
Civil | -1.050 |
FontSize | -1.014 |
Token | ip |
Token ID | 541 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
acebook | +1.953 |
phabet | +1.952 |
utherland | +1.922 |
Civil | +1.732 |
sung | +1.586 |
Neg logit contributions | |
�� | -5.812 |
�� | -5.297 |
�� | -4.979 |
�� | -4.600 |
�� | -4.527 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
�� | +0.168 |
�� | +0.151 |
�� | +0.142 |
�� | +0.130 |
�� | +0.128 |
Neg logit contributions | |
acebook | -0.070 |
phabet | -0.069 |
utherland | -0.069 |
Civil | -0.062 |
FontSize | -0.058 |
Token | While |
Token ID | 2893 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
�� | +2.406 |
�� | +2.169 |
�� | +2.032 |
�� | +1.855 |
�� | +1.830 |
Neg logit contributions | |
acebook | -0.972 |
phabet | -0.963 |
utherland | -0.954 |
Civil | -0.846 |
FontSize | -0.808 |
Token | they |
Token ID | 484 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
acebook | +0.823 |
phabet | +0.821 |
utherland | +0.814 |
Civil | +0.749 |
FontSize | +0.699 |
Neg logit contributions | |
�� | -1.745 |
�� | -1.567 |
�� | -1.465 |
�� | -1.336 |
�� | -1.314 |
Token | are |
Token ID | 389 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
phabet | +1.901 |
acebook | +1.894 |
utherland | +1.877 |
Civil | +1.717 |
sung | +1.556 |
Neg logit contributions | |
�� | -5.132 |
�� | -4.650 |
�� | -4.378 |
�� | -4.032 |
�� | -3.946 |
Token | both |
Token ID | 1111 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
acebook | +1.878 |
phabet | +1.870 |
utherland | +1.857 |
Civil | +1.727 |
FontSize | +1.584 |
Neg logit contributions | |
�� | -4.170 |
�� | -3.746 |
�� | -3.524 |
�� | -3.220 |
�� | -3.159 |
Token | Stanford |
Token ID | 13863 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
acebook | +1.169 |
phabet | +1.162 |
utherland | +1.155 |
Civil | +1.066 |
FontSize | +0.980 |
Neg logit contributions | |
�� | -2.748 |
�� | -2.479 |
�� | -2.327 |
�� | -2.130 |
�� | -2.094 |
Token | economists |
Token ID | 16816 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
�� | +11.049 |
�� | +9.870 |
�� | +9.176 |
�� | +8.322 |
�� | +8.198 |
Neg logit contributions | |
phabet | -5.544 |
acebook | -5.481 |
utherland | -5.294 |
FontSize | -4.722 |
Civil | -4.581 |
Token | , |
Token ID | 11 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
�� | +2.061 |
�� | +1.841 |
�� | +1.715 |
�� | +1.550 |
�� | +1.527 |
Neg logit contributions | |
acebook | -1.101 |
phabet | -1.095 |
utherland | -1.086 |
Civil | -0.996 |
FontSize | -0.950 |
Token | they |
Token ID | 484 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
�� | +4.563 |
�� | +4.057 |
�� | +3.780 |
�� | +3.419 |
�� | +3.374 |
Neg logit contributions | |
acebook | -2.289 |
phabet | -2.271 |
utherland | -2.244 |
Civil | -2.019 |
FontSize | -1.964 |
Token | are |
Token ID | 389 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
�� | +5.537 |
�� | +4.989 |
�� | +4.662 |
�� | +4.258 |
�� | +4.231 |
Neg logit contributions | |
acebook | -2.276 |
phabet | -2.254 |
utherland | -2.247 |
Civil | -1.990 |
FontSize | -1.928 |
Token | not |
Token ID | 407 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
acebook | +1.806 |
phabet | +1.797 |
utherland | +1.791 |
Civil | +1.658 |
FontSize | +1.509 |
Neg logit contributions | |
�� | -4.443 |
�� | -4.007 |
�� | -3.764 |
�� | -3.461 |
�� | -3.397 |
Token | me |
Token ID | 502 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
�� | +1.043 |
�� | +0.944 |
�� | +0.883 |
�� | +0.808 |
�� | +0.798 |
Neg logit contributions | |
phabet | -0.409 |
acebook | -0.408 |
utherland | -0.403 |
Civil | -0.360 |
FontSize | -0.339 |
Token | the |
Token ID | 262 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
�� | +1.491 |
�� | +1.338 |
�� | +1.244 |
�� | +1.128 |
�� | +1.117 |
Neg logit contributions | |
acebook | -0.742 |
phabet | -0.742 |
utherland | -0.733 |
Civil | -0.664 |
FontSize | -0.635 |
Token | sort |
Token ID | 3297 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
acebook | +0.610 |
phabet | +0.607 |
utherland | +0.602 |
Civil | +0.552 |
FontSize | +0.513 |
Neg logit contributions | |
�� | -1.396 |
�� | -1.257 |
�� | -1.177 |
�� | -1.076 |
�� | -1.059 |
Token | of |
Token ID | 286 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
�� | +0.972 |
�� | +0.873 |
�� | +0.817 |
�� | +0.746 |
�� | +0.734 |
Neg logit contributions | |
acebook | -0.424 |
phabet | -0.417 |
utherland | -0.413 |
Civil | -0.375 |
FontSize | -0.352 |
Token | world |
Token ID | 995 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
acebook | +0.887 |
phabet | +0.884 |
utherland | +0.877 |
Civil | +0.809 |
FontSize | +0.755 |
Neg logit contributions | |
�� | -1.876 |
�� | -1.684 |
�� | -1.575 |
�� | -1.436 |
�� | -1.412 |
Token | of |
Token ID | 286 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
�� | +1.868 |
�� | +1.679 |
�� | +1.559 |
�� | +1.420 |
�� | +1.401 |
Neg logit contributions | |
phabet | -0.894 |
acebook | -0.893 |
utherland | -0.885 |
Civil | -0.798 |
FontSize | -0.766 |
Token | it |
Token ID | 340 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
acebook | +0.599 |
phabet | +0.597 |
utherland | +0.591 |
Civil | +0.543 |
FontSize | +0.509 |
Neg logit contributions | |
�� | -1.270 |
�� | -1.141 |
�� | -1.066 |
�� | -0.972 |
�� | -0.956 |
Token | and |
Token ID | 290 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
acebook | +1.245 |
phabet | +1.242 |
utherland | +1.232 |
Civil | +1.131 |
sung | +1.042 |
Neg logit contributions | |
�� | -2.956 |
�� | -2.669 |
�� | -2.503 |
�� | -2.300 |
�� | -2.251 |
Token | who |
Token ID | 508 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
�� | +1.198 |
�� | +1.075 |
�� | +1.002 |
�� | +0.911 |
�� | +0.899 |
Neg logit contributions | |
acebook | -0.574 |
phabet | -0.574 |
utherland | -0.568 |
Civil | -0.515 |
FontSize | -0.488 |
Token | I |
Token ID | 314 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
�� | +1.513 |
�� | +1.358 |
�� | +1.268 |
�� | +1.157 |
�� | +1.139 |
Neg logit contributions | |
acebook | -0.695 |
phabet | -0.692 |
utherland | -0.687 |
Civil | -0.624 |
FontSize | -0.590 |
Token | was |
Token ID | 373 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
�� | +2.703 |
�� | +2.439 |
�� | +2.277 |
�� | +2.082 |
�� | +2.065 |
Neg logit contributions | |
acebook | -1.132 |
phabet | -1.115 |
utherland | -1.111 |
Civil | -1.003 |
FontSize | -0.945 |
Token | to |
Token ID | 284 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
acebook | +0.867 |
phabet | +0.865 |
utherland | +0.856 |
Civil | +0.787 |
FontSize | +0.735 |
Neg logit contributions | |
�� | -1.874 |
�� | -1.684 |
�� | -1.575 |
�� | -1.437 |
�� | -1.413 |
Token | be |
Token ID | 307 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
phabet | +2.864 |
utherland | +2.843 |
acebook | +2.828 |
Civil | +2.656 |
FontSize | +2.354 |
Neg logit contributions | |
�� | -7.921 |
�� | -7.175 |
�� | -6.729 |
�� | -6.188 |
�� | -6.087 |
Token | perfectly |
Token ID | 7138 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
acebook | +0.578 |
phabet | +0.576 |
utherland | +0.572 |
Civil | +0.528 |
FontSize | +0.501 |
Neg logit contributions | |
�� | -1.008 |
�� | -0.898 |
�� | -0.835 |
�� | -0.755 |
�� | -0.741 |
Token | honest |
Token ID | 5508 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
acebook | +0.768 |
phabet | +0.765 |
utherland | +0.759 |
Civil | +0.706 |
FontSize | +0.665 |
Neg logit contributions | |
�� | -1.362 |
�� | -1.216 |
�� | -1.130 |
�� | -1.022 |
�� | -1.004 |
Token | with |
Token ID | 351 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
acebook | +1.503 |
phabet | +1.501 |
utherland | +1.479 |
Civil | +1.360 |
FontSize | +1.246 |
Neg logit contributions | |
�� | -3.757 |
�� | -3.402 |
�� | -3.193 |
�� | -2.923 |
�� | -2.880 |
Token | you |
Token ID | 345 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
phabet | +2.149 |
acebook | +2.147 |
utherland | +2.131 |
Civil | +1.973 |
FontSize | +1.793 |
Neg logit contributions | |
�� | -5.333 |
�� | -4.818 |
�� | -4.517 |
�� | -4.133 |
�� | -4.071 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
�� | +0.547 |
�� | +0.490 |
�� | +0.457 |
�� | +0.416 |
�� | +0.410 |
Neg logit contributions | |
acebook | -0.265 |
phabet | -0.264 |
utherland | -0.262 |
Civil | -0.239 |
FontSize | -0.226 |
Token | what |
Token ID | 644 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
acebook | +0.741 |
phabet | +0.739 |
utherland | +0.732 |
Civil | +0.670 |
FontSize | +0.626 |
Neg logit contributions | |
�� | -1.645 |
�� | -1.480 |
�� | -1.385 |
�� | -1.264 |
�� | -1.244 |
Token | their |
Token ID | 511 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
acebook | +3.071 |
phabet | +3.028 |
utherland | +3.025 |
Civil | +2.885 |
FontSize | +2.539 |
Neg logit contributions | |
�� | -7.702 |
�� | -6.969 |
�� | -6.567 |
�� | -6.023 |
�� | -5.961 |
Token | motive |
Token ID | 20289 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
acebook | +2.464 |
phabet | +2.436 |
utherland | +2.425 |
Civil | +2.272 |
FontSize | +2.050 |
Neg logit contributions | |
�� | -5.995 |
�� | -5.422 |
�� | -5.084 |
�� | -4.675 |
�� | -4.600 |
Token | was |
Token ID | 373 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
acebook | +0.967 |
phabet | +0.963 |
utherland | +0.953 |
Civil | +0.868 |
FontSize | +0.800 |
Neg logit contributions | |
�� | -2.512 |
�� | -2.272 |
�� | -2.133 |
�� | -1.960 |
�� | -1.929 |
Token | ley |
Token ID | 1636 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
phabet | +1.274 |
acebook | +1.267 |
utherland | +1.258 |
Civil | +1.151 |
sung | +1.072 |
Neg logit contributions | |
�� | -2.896 |
�� | -2.614 |
�� | -2.446 |
�� | -2.237 |
�� | -2.195 |
Token | . |
Token ID | 13 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
�� | +4.975 |
�� | +4.470 |
�� | +4.200 |
�� | +3.811 |
�� | +3.785 |
Neg logit contributions | |
acebook | -2.258 |
phabet | -2.247 |
utherland | -2.200 |
Civil | -1.991 |
FontSize | -1.908 |
Token | ( |
Token ID | 357 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
acebook | +0.468 |
phabet | +0.468 |
utherland | +0.462 |
Civil | +0.418 |
FontSize | +0.392 |
Neg logit contributions | |
�� | -1.106 |
�� | -0.997 |
�� | -0.933 |
�� | -0.853 |
�� | -0.842 |
Token | The |
Token ID | 464 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
�� | +1.153 |
�� | +1.034 |
�� | +0.968 |
�� | +0.881 |
�� | +0.869 |
Neg logit contributions | |
acebook | -0.517 |
phabet | -0.516 |
utherland | -0.506 |
Civil | -0.458 |
FontSize | -0.429 |
Token | nut |
Token ID | 6701 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
�� | +0.256 |
�� | +0.230 |
�� | +0.216 |
�� | +0.197 |
�� | +0.194 |
Neg logit contributions | |
acebook | -0.110 |
phabet | -0.109 |
utherland | -0.108 |
Civil | -0.099 |
FontSize | -0.092 |
Token | cr |
Token ID | 6098 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
�� | +1.811 |
�� | +1.629 |
�� | +1.525 |
�� | +1.394 |
�� | +1.371 |
Neg logit contributions | |
acebook | -0.791 |
phabet | -0.786 |
utherland | -0.777 |
Civil | -0.710 |
FontSize | -0.671 |
Token | acker |
Token ID | 10735 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
acebook | +0.493 |
phabet | +0.492 |
utherland | +0.489 |
Civil | +0.456 |
FontSize | +0.433 |
Neg logit contributions | |
�� | -0.778 |
�� | -0.690 |
�� | -0.639 |
�� | -0.575 |
�� | -0.564 |
Token | then |
Token ID | 788 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
acebook | +0.300 |
phabet | +0.299 |
utherland | +0.296 |
Civil | +0.266 |
FontSize | +0.247 |
Neg logit contributions | |
�� | -0.812 |
�� | -0.735 |
�� | -0.691 |
�� | -0.635 |
�� | -0.625 |
Token | goes |
Token ID | 2925 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
�� | +2.343 |
�� | +2.105 |
�� | +1.971 |
�� | +1.801 |
�� | +1.778 |
Neg logit contributions | |
phabet | -1.034 |
acebook | -1.031 |
utherland | -1.019 |
Civil | -0.916 |
FontSize | -0.867 |
Token | on |
Token ID | 319 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
�� | +3.657 |
�� | +3.285 |
�� | +3.068 |
�� | +2.786 |
�� | +2.785 |
Neg logit contributions | |
acebook | -1.687 |
phabet | -1.675 |
utherland | -1.660 |
Civil | -1.488 |
FontSize | -1.415 |
Token | to |
Token ID | 284 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
�� | +6.054 |
�� | +5.459 |
�� | +5.083 |
�� | +4.619 |
�� | +4.615 |
Neg logit contributions | |
acebook | -2.787 |
utherland | -2.770 |
phabet | -2.763 |
Civil | -2.444 |
FontSize | -2.338 |
Token | Francisco |
Token ID | 6033 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
phabet | +2.530 |
acebook | +2.508 |
utherland | +2.482 |
Civil | +2.293 |
sung | +2.096 |
Neg logit contributions | |
�� | -6.859 |
�� | -6.216 |
�� | -5.856 |
�� | -5.396 |
�� | -5.314 |
Token | , |
Token ID | 11 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
�� | +5.034 |
�� | +4.464 |
�� | +4.168 |
�� | +3.782 |
�� | +3.759 |
Neg logit contributions | |
acebook | -2.526 |
phabet | -2.489 |
utherland | -2.483 |
Civil | -2.200 |
FontSize | -2.132 |
Token | grew |
Token ID | 6348 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
acebook | +0.299 |
phabet | +0.298 |
utherland | +0.295 |
Civil | +0.268 |
FontSize | +0.253 |
Neg logit contributions | |
�� | -0.652 |
�� | -0.585 |
�� | -0.547 |
�� | -0.498 |
�� | -0.491 |
Token | up |
Token ID | 510 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
acebook | +2.136 |
phabet | +2.126 |
utherland | +2.117 |
Civil | +1.944 |
FontSize | +1.757 |
Neg logit contributions | |
�� | -5.945 |
�� | -5.388 |
�� | -5.075 |
�� | -4.673 |
�� | -4.586 |
Token | there |
Token ID | 612 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
acebook | +0.329 |
phabet | +0.328 |
utherland | +0.324 |
Civil | +0.295 |
FontSize | +0.277 |
Neg logit contributions | |
�� | -0.741 |
�� | -0.667 |
�� | -0.624 |
�� | -0.570 |
�� | -0.562 |
Token | , |
Token ID | 11 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
�� | +0.250 |
�� | +0.224 |
�� | +0.209 |
�� | +0.190 |
�� | +0.187 |
Neg logit contributions | |
acebook | -0.123 |
phabet | -0.122 |
utherland | -0.121 |
Civil | -0.111 |
FontSize | -0.105 |
Token | and |
Token ID | 290 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
acebook | +0.141 |
phabet | +0.141 |
utherland | +0.140 |
Civil | +0.126 |
FontSize | +0.119 |
Neg logit contributions | |
�� | -0.326 |
�� | -0.294 |
�� | -0.275 |
�� | -0.251 |
�� | -0.248 |
Token | had |
Token ID | 550 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
acebook | +0.896 |
phabet | +0.893 |
utherland | +0.884 |
Civil | +0.806 |
FontSize | +0.747 |
Neg logit contributions | |
�� | -2.216 |
�� | -2.000 |
�� | -1.876 |
�� | -1.720 |
�� | -1.691 |
Token | followed |
Token ID | 3940 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
phabet | +0.004 |
acebook | +0.004 |
utherland | +0.004 |
Civil | +0.003 |
FontSize | +0.003 |
Neg logit contributions | |
�� | -0.009 |
�� | -0.008 |
�� | -0.007 |
�� | -0.007 |
�� | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
acebook | +2.284 |
phabet | +2.270 |
utherland | +2.243 |
Civil | +2.105 |
sung | +1.891 |
Neg logit contributions | |
�� | -5.365 |
�� | -4.837 |
�� | -4.556 |
�� | -4.174 |
�� | -4.088 |
Token | US |
Token ID | 1294 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
acebook | +1.386 |
phabet | +1.380 |
utherland | +1.369 |
Civil | +1.285 |
sung | +1.164 |
Neg logit contributions | |
�� | -3.076 |
�� | -2.766 |
�� | -2.589 |
�� | -2.367 |
�� | -2.325 |
Token | with |
Token ID | 351 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
�� | +2.515 |
�� | +2.247 |
�� | +2.094 |
�� | +1.900 |
�� | +1.870 |
Neg logit contributions | |
acebook | -1.295 |
phabet | -1.286 |
utherland | -1.275 |
Civil | -1.163 |
FontSize | -1.112 |
Token | creativity |
Token ID | 16389 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
acebook | +0.182 |
phabet | +0.181 |
utherland | +0.179 |
Civil | +0.164 |
FontSize | +0.154 |
Neg logit contributions | |
�� | -0.392 |
�� | -0.352 |
�� | -0.329 |
�� | -0.300 |
�� | -0.295 |
Token | and |
Token ID | 290 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
phabet | +2.389 |
acebook | +2.374 |
utherland | +2.373 |
Civil | +2.192 |
FontSize | +2.021 |
Neg logit contributions | |
�� | -5.313 |
�� | -4.785 |
�� | -4.469 |
�� | -4.098 |
�� | -4.018 |
Token | sales |
Token ID | 4200 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
�� | +2.950 |
�� | +2.656 |
�� | +2.477 |
�� | +2.245 |
�� | +2.210 |
Neg logit contributions | |
acebook | -1.388 |
phabet | -1.382 |
utherland | -1.367 |
Civil | -1.222 |
FontSize | -1.171 |
Token | and |
Token ID | 290 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
�� | +5.539 |
�� | +4.940 |
�� | +4.596 |
�� | +4.093 |
�� | +4.036 |
Neg logit contributions | |
acebook | -3.230 |
phabet | -3.177 |
utherland | -3.171 |
Civil | -2.901 |
FontSize | -2.789 |
Token | marketing |
Token ID | 7124 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
�� | +5.129 |
�� | +4.621 |
�� | +4.302 |
�� | +3.872 |
�� | +3.830 |
Neg logit contributions | |
phabet | -2.503 |
acebook | -2.495 |
utherland | -2.479 |
Civil | -2.200 |
FontSize | -2.127 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
�� | +1.329 |
�� | +1.190 |
�� | +1.110 |
�� | +1.008 |
�� | +0.992 |
Neg logit contributions | |
acebook | -0.665 |
phabet | -0.661 |
utherland | -0.653 |
Civil | -0.597 |
FontSize | -0.566 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
�� | +0.322 |
�� | +0.289 |
�� | +0.271 |
�� | +0.246 |
�� | +0.242 |
Neg logit contributions | |
acebook | -0.150 |
phabet | -0.150 |
utherland | -0.149 |
Civil | -0.136 |
FontSize | -0.128 |
Token | more |
Token ID | 517 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
�� | +1.642 |
�� | +1.473 |
�� | +1.381 |
�� | +1.259 |
�� | +1.236 |
Neg logit contributions | |
acebook | -0.746 |
phabet | -0.742 |
utherland | -0.735 |
Civil | -0.666 |
FontSize | -0.632 |
Token | confident |
Token ID | 6563 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
acebook | +0.894 |
phabet | +0.891 |
utherland | +0.885 |
Civil | +0.811 |
FontSize | +0.756 |
Neg logit contributions | |
�� | -1.973 |
�� | -1.776 |
�� | -1.661 |
�� | -1.516 |
�� | -1.494 |
Token | we |
Token ID | 356 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
acebook | +0.204 |
phabet | +0.204 |
utherland | +0.202 |
Civil | +0.185 |
FontSize | +0.174 |
Neg logit contributions | |
�� | -0.440 |
�� | -0.395 |
�� | -0.369 |
�� | -0.337 |
�� | -0.331 |
Token | Friday |
Token ID | 20610 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
phabet | +1.534 |
acebook | +1.532 |
utherland | +1.523 |
Civil | +1.392 |
FontSize | +1.302 |
Neg logit contributions | |
�� | -3.793 |
�� | -3.434 |
�� | -3.217 |
�� | -2.957 |
�� | -2.903 |
Token | , |
Token ID | 11 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
�� | +2.136 |
�� | +1.911 |
�� | +1.777 |
�� | +1.612 |
�� | +1.589 |
Neg logit contributions | |
acebook | -1.126 |
phabet | -1.120 |
utherland | -1.113 |
Civil | -1.016 |
FontSize | -0.971 |
Token | June |
Token ID | 2795 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
acebook | +0.258 |
phabet | +0.257 |
utherland | +0.254 |
Civil | +0.229 |
FontSize | +0.212 |
Neg logit contributions | |
�� | -0.685 |
�� | -0.620 |
�� | -0.582 |
�� | -0.534 |
�� | -0.526 |
Token | 16 |
Token ID | 1467 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
acebook | +0.284 |
phabet | +0.283 |
utherland | +0.280 |
Civil | +0.256 |
FontSize | +0.238 |
Neg logit contributions | |
�� | -0.669 |
�� | -0.603 |
�� | -0.564 |
�� | -0.516 |
�� | -0.508 |
Token | Last |
Token ID | 4586 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
acebook | +0.521 |
phabet | +0.520 |
utherland | +0.515 |
Civil | +0.472 |
FontSize | +0.439 |
Neg logit contributions | |
�� | -1.177 |
�� | -1.060 |
�� | -0.992 |
�� | -0.906 |
�� | -0.891 |
Token | day |
Token ID | 1110 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
�� | +3.280 |
�� | +2.941 |
�� | +2.757 |
�� | +2.506 |
�� | +2.478 |
Neg logit contributions | |
phabet | -1.459 |
acebook | -1.456 |
utherland | -1.440 |
Civil | -1.283 |
FontSize | -1.234 |
Token | to |
Token ID | 284 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
acebook | +0.858 |
phabet | +0.855 |
utherland | +0.849 |
Civil | +0.778 |
FontSize | +0.709 |
Neg logit contributions | |
�� | -2.217 |
�� | -2.008 |
�� | -1.886 |
�� | -1.732 |
�� | -1.704 |
Token | place |
Token ID | 1295 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
phabet | +3.221 |
utherland | +3.220 |
acebook | +3.214 |
Civil | +3.113 |
sung | +2.663 |
Neg logit contributions | |
�� | -9.592 |
�� | -8.810 |
�� | -8.269 |
�� | -7.629 |
�� | -7.431 |
Token | Player |
Token ID | 7853 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
acebook | +1.326 |
phabet | +1.325 |
utherland | +1.315 |
Civil | +1.218 |
FontSize | +1.129 |
Neg logit contributions | |
�� | -2.751 |
�� | -2.476 |
�� | -2.310 |
�� | -2.107 |
�� | -2.072 |
Token | on |
Token ID | 319 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
acebook | +0.193 |
phabet | +0.193 |
utherland | +0.191 |
Civil | +0.173 |
FontSize | +0.161 |
Neg logit contributions | |
�� | -0.480 |
�� | -0.434 |
�� | -0.407 |
�� | -0.373 |
�� | -0.367 |
Token | Wa |
Token ID | 15329 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
�� | +0.286 |
�� | +0.259 |
�� | +0.243 |
�� | +0.224 |
�� | +0.220 |
Neg logit contributions | |
acebook | -0.102 |
phabet | -0.101 |
utherland | -0.100 |
Civil | -0.090 |
FontSize | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
acebook | +0.712 |
phabet | +0.710 |
utherland | +0.703 |
Civil | +0.643 |
FontSize | +0.598 |
Neg logit contributions | |
�� | -1.653 |
�� | -1.490 |
�� | -1.396 |
�� | -1.277 |
�� | -1.256 |
Token | It |
Token ID | 632 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
acebook | +0.916 |
phabet | +0.912 |
utherland | +0.905 |
Civil | +0.831 |
FontSize | +0.771 |
Neg logit contributions | |
�� | -2.089 |
�� | -1.883 |
�� | -1.762 |
�� | -1.612 |
�� | -1.585 |
Token | 's |
Token ID | 338 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
acebook | +0.436 |
phabet | +0.434 |
utherland | +0.430 |
Civil | +0.392 |
FontSize | +0.365 |
Neg logit contributions | |
�� | -1.039 |
�� | -0.937 |
�� | -0.878 |
�� | -0.804 |
�� | -0.791 |
Token | a |
Token ID | 257 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
acebook | +1.645 |
phabet | +1.639 |
utherland | +1.632 |
Civil | +1.503 |
FontSize | +1.386 |
Neg logit contributions | |
�� | -3.914 |
�� | -3.533 |
�� | -3.310 |
�� | -3.031 |
�� | -2.986 |
Token | lot |
Token ID | 1256 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
phabet | +2.977 |
acebook | +2.968 |
utherland | +2.946 |
Civil | +2.779 |
sung | +2.557 |
Neg logit contributions | |
�� | -5.691 |
�� | -5.099 |
�� | -4.741 |
�� | -4.330 |
�� | -4.237 |
Token | of |
Token ID | 286 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
phabet | +1.587 |
acebook | +1.585 |
utherland | +1.570 |
Civil | +1.436 |
FontSize | +1.332 |
Neg logit contributions | |
�� | -3.744 |
�� | -3.381 |
�� | -3.164 |
�� | -2.896 |
�� | -2.854 |
Token | hard |
Token ID | 1327 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
acebook | +0.720 |
phabet | +0.718 |
utherland | +0.712 |
Civil | +0.654 |
FontSize | +0.613 |
Neg logit contributions | |
�� | -1.501 |
�� | -1.347 |
�� | -1.258 |
�� | -1.146 |
�� | -1.127 |
Token | work |
Token ID | 670 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
�� | +3.628 |
�� | +3.244 |
�� | +3.042 |
�� | +2.745 |
�� | +2.713 |
Neg logit contributions | |
acebook | -1.826 |
phabet | -1.794 |
utherland | -1.793 |
Civil | -1.621 |
FontSize | -1.575 |
Token | . |
Token ID | 13 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
�� | +3.990 |
�� | +3.571 |
�� | +3.337 |
�� | +3.007 |
�� | +2.971 |
Neg logit contributions | |
acebook | -2.019 |
phabet | -1.983 |
utherland | -1.962 |
Civil | -1.780 |
FontSize | -1.721 |
Token | I |
Token ID | 314 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
acebook | +0.634 |
phabet | +0.632 |
utherland | +0.626 |
Civil | +0.571 |
FontSize | +0.534 |
Neg logit contributions | |
�� | -1.446 |
�� | -1.302 |
�� | -1.219 |
�� | -1.114 |
�� | -1.096 |
Token | think |
Token ID | 892 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
acebook | +0.737 |
phabet | +0.737 |
utherland | +0.729 |
Civil | +0.663 |
FontSize | +0.613 |
Neg logit contributions | |
�� | -1.859 |
�� | -1.680 |
�� | -1.578 |
�� | -1.445 |
�� | -1.422 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
�� | +3.632 |
�� | +3.231 |
�� | +3.029 |
�� | +2.732 |
�� | +2.728 |
Neg logit contributions | |
acebook | -1.693 |
phabet | -1.663 |
utherland | -1.614 |
Civil | -1.415 |
sung | -1.348 |
Token | The |
Token ID | 464 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
�� | +1.583 |
�� | +1.420 |
�� | +1.328 |
�� | +1.210 |
�� | +1.189 |
Neg logit contributions | |
acebook | -0.738 |
phabet | -0.731 |
utherland | -0.725 |
Civil | -0.659 |
FontSize | -0.614 |
Token | situation |
Token ID | 3074 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
acebook | +0.939 |
phabet | +0.934 |
utherland | +0.927 |
Civil | +0.860 |
FontSize | +0.783 |
Neg logit contributions | |
�� | -2.309 |
�� | -2.085 |
�� | -1.958 |
�� | -1.788 |
�� | -1.767 |
Token | remained |
Token ID | 6150 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
acebook | +1.357 |
phabet | +1.353 |
utherland | +1.344 |
Civil | +1.233 |
FontSize | +1.129 |
Neg logit contributions | |
�� | -3.389 |
�� | -3.067 |
�� | -2.875 |
�� | -2.633 |
�� | -2.594 |
Token | calm |
Token ID | 9480 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
acebook | +1.579 |
phabet | +1.575 |
utherland | +1.566 |
Civil | +1.453 |
FontSize | +1.346 |
Neg logit contributions | |
�� | -3.456 |
�� | -3.108 |
�� | -2.909 |
�� | -2.652 |
�� | -2.605 |
Token | in |
Token ID | 287 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
�� | +0.118 |
�� | +0.106 |
�� | +0.099 |
�� | +0.090 |
�� | +0.089 |
Neg logit contributions | |
acebook | -0.054 |
phabet | -0.053 |
utherland | -0.053 |
Civil | -0.048 |
FontSize | -0.045 |
Token | Chern |
Token ID | 37243 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
acebook | +1.440 |
phabet | +1.434 |
utherland | +1.427 |
Civil | +1.328 |
FontSize | +1.205 |
Neg logit contributions | |
�� | -3.438 |
�� | -3.102 |
�� | -2.911 |
�� | -2.660 |
�� | -2.621 |
Token | iv |
Token ID | 452 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
�� | +4.353 |
�� | +3.870 |
�� | +3.575 |
�� | +3.241 |
�� | +3.152 |
Neg logit contributions | |
acebook | -2.565 |
phabet | -2.562 |
utherland | -2.524 |
Civil | -2.298 |
FontSize | -2.268 |
Token | ts |
Token ID | 912 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
acebook | +0.808 |
phabet | +0.807 |
utherland | +0.801 |
Civil | +0.738 |
FontSize | +0.689 |
Neg logit contributions | |
�� | -1.654 |
�� | -1.485 |
�� | -1.387 |
�� | -1.262 |
�� | -1.240 |
Token | i |
Token ID | 72 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
acebook | +1.719 |
utherland | +1.716 |
phabet | +1.714 |
Civil | +1.582 |
sung | +1.459 |
Neg logit contributions | |
�� | -3.916 |
�� | -3.529 |
�� | -3.298 |
�� | -3.018 |
�� | -2.965 |
Token | , |
Token ID | 11 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
phabet | +2.644 |
acebook | +2.622 |
utherland | +2.621 |
Civil | +2.477 |
sung | +2.230 |
Neg logit contributions | |
�� | -6.069 |
�� | -5.456 |
�� | -5.112 |
�� | -4.680 |
�� | -4.594 |
Token | 51 |
Token ID | 6885 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
�� | +3.740 |
�� | +3.362 |
�� | +3.144 |
�� | +2.833 |
�� | +2.810 |
Neg logit contributions | |
acebook | -1.848 |
phabet | -1.829 |
utherland | -1.821 |
Civil | -1.630 |
FontSize | -1.583 |
Token | % |
Token ID | 4 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
acebook | +0.090 |
phabet | +0.090 |
utherland | +0.089 |
Civil | +0.081 |
FontSize | +0.076 |
Neg logit contributions | |
�� | -0.202 |
�� | -0.182 |
�� | -0.170 |
�� | -0.155 |
�� | -0.153 |
Token | stated |
Token ID | 5081 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
�� | +2.038 |
�� | +1.830 |
�� | +1.713 |
�� | +1.566 |
�� | +1.545 |
Neg logit contributions | |
acebook | -0.886 |
phabet | -0.881 |
utherland | -0.875 |
Civil | -0.788 |
FontSize | -0.749 |
Token | that |
Token ID | 326 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
acebook | +0.770 |
phabet | +0.767 |
utherland | +0.760 |
Civil | +0.701 |
FontSize | +0.655 |
Neg logit contributions | |
�� | -1.614 |
�� | -1.450 |
�� | -1.354 |
�� | -1.234 |
�� | -1.213 |
Token | they |
Token ID | 484 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
�� | +0.565 |
�� | +0.505 |
�� | +0.469 |
�� | +0.425 |
�� | +0.418 |
Neg logit contributions | |
acebook | -0.304 |
phabet | -0.302 |
utherland | -0.301 |
Civil | -0.273 |
FontSize | -0.262 |
Token | believed |
Token ID | 4762 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
�� | +0.769 |
�� | +0.694 |
�� | +0.651 |
�� | +0.597 |
�� | +0.589 |
Neg logit contributions | |
acebook | -0.305 |
phabet | -0.303 |
utherland | -0.301 |
Civil | -0.270 |
FontSize | -0.254 |
Token | marijuana |
Token ID | 5727 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
phabet | +1.491 |
acebook | +1.490 |
utherland | +1.470 |
Civil | +1.374 |
FontSize | +1.254 |
Neg logit contributions | |
�� | -3.404 |
�� | -3.066 |
�� | -2.878 |
�� | -2.631 |
�� | -2.583 |
Token | should |
Token ID | 815 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
�� | +6.667 |
�� | +5.972 |
�� | +5.594 |
�� | +5.089 |
�� | +5.033 |
Neg logit contributions | |
acebook | -3.009 |
phabet | -2.958 |
utherland | -2.927 |
Civil | -2.543 |
FontSize | -2.524 |
Token | be |
Token ID | 307 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
phabet | +1.396 |
acebook | +1.394 |
utherland | +1.372 |
Civil | +1.265 |
sung | +1.133 |
Neg logit contributions | |
�� | -3.927 |
�� | -3.555 |
�� | -3.351 |
�� | -3.061 |
�� | -3.014 |
Token | made |
Token ID | 925 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
acebook | +1.037 |
phabet | +1.031 |
utherland | +1.017 |
Civil | +0.923 |
FontSize | +0.828 |
Neg logit contributions | |
�� | -3.170 |
�� | -2.878 |
�� | -2.717 |
�� | -2.498 |
�� | -2.462 |
Token | legal |
Token ID | 2742 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
phabet | +2.272 |
acebook | +2.269 |
utherland | +2.189 |
Civil | +2.076 |
ro | +1.727 |
Neg logit contributions | |
�� | -8.415 |
�� | -7.712 |
�� | -7.324 |
�� | -6.760 |
�� | -6.636 |
Token | pollution |
Token ID | 12231 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
acebook | +0.639 |
phabet | +0.639 |
utherland | +0.634 |
Civil | +0.576 |
FontSize | +0.527 |
Neg logit contributions | |
�� | -1.691 |
�� | -1.528 |
�� | -1.434 |
�� | -1.320 |
�� | -1.300 |
Token | , |
Token ID | 11 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
�� | +0.790 |
�� | +0.710 |
�� | +0.665 |
�� | +0.602 |
�� | +0.594 |
Neg logit contributions | |
acebook | -0.377 |
phabet | -0.375 |
utherland | -0.369 |
Civil | -0.336 |
FontSize | -0.318 |
Token | � |
Token ID | 447 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
acebook | +0.154 |
phabet | +0.154 |
utherland | +0.152 |
Civil | +0.139 |
FontSize | +0.130 |
Neg logit contributions | |
�� | -0.359 |
�� | -0.323 |
�� | -0.303 |
�� | -0.277 |
�� | -0.273 |
Token | � |
Token ID | 251 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
phabet | +1.737 |
acebook | +1.730 |
utherland | +1.719 |
Civil | +1.653 |
FontSize | +1.602 |
Neg logit contributions | |
�� | -0.994 |
�� | -0.799 |
�� | -0.697 |
�� | -0.560 |
�� | -0.537 |
Token | said |
Token ID | 531 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
�� | +0.707 |
�� | +0.637 |
�� | +0.596 |
�� | +0.544 |
�� | +0.535 |
Neg logit contributions | |
acebook | -0.308 |
phabet | -0.307 |
utherland | -0.304 |
Civil | -0.276 |
FontSize | -0.260 |
Token | Edward |
Token ID | 10443 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
acebook | +1.804 |
phabet | +1.790 |
utherland | +1.771 |
Civil | +1.659 |
sung | +1.513 |
Neg logit contributions | |
�� | -4.073 |
�� | -3.673 |
�� | -3.435 |
�� | -3.153 |
�� | -3.108 |
Token | Chan |
Token ID | 18704 |
Feature activation | -5.75e+00 |
Pos logit contributions | |
acebook | +2.226 |
phabet | +2.213 |
utherland | +2.210 |
Civil | +2.057 |
sung | +1.878 |
Neg logit contributions | |
�� | -5.209 |
�� | -4.719 |
�� | -4.400 |
�� | -4.039 |
�� | -3.954 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
phabet | +3.958 |
utherland | +3.934 |
acebook | +3.904 |
Civil | +3.667 |
sung | +3.421 |
Neg logit contributions | |
�� | -8.487 |
�� | -7.694 |
�� | -7.165 |
�� | -6.577 |
�� | -6.499 |
Token | an |
Token ID | 281 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
�� | +0.423 |
�� | +0.381 |
�� | +0.357 |
�� | +0.326 |
�� | +0.320 |
Neg logit contributions | |
acebook | -0.184 |
phabet | -0.183 |
utherland | -0.182 |
Civil | -0.163 |
FontSize | -0.155 |
Token | official |
Token ID | 1743 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
acebook | +1.017 |
phabet | +1.009 |
utherland | +1.007 |
Civil | +0.934 |
sung | +0.860 |
Neg logit contributions | |
�� | -2.228 |
�� | -2.007 |
�� | -1.875 |
�� | -1.715 |
�� | -1.692 |
Token | with |
Token ID | 351 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
utherland | +3.839 |
acebook | +3.817 |
phabet | +3.792 |
Civil | +3.625 |
ro | +3.199 |
Neg logit contributions | |
�� | -10.300 |
�� | -9.390 |
�� | -8.740 |
�� | -8.097 |
�� | -7.989 |
Token | number |
Token ID | 1271 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
acebook | +1.731 |
phabet | +1.731 |
utherland | +1.712 |
Civil | +1.599 |
FontSize | +1.474 |
Neg logit contributions | |
�� | -3.760 |
�� | -3.384 |
�� | -3.160 |
�� | -2.891 |
�� | -2.835 |
Token | of |
Token ID | 286 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
acebook | +0.905 |
phabet | +0.903 |
utherland | +0.896 |
Civil | +0.815 |
FontSize | +0.756 |
Neg logit contributions | |
�� | -2.234 |
�� | -2.019 |
�� | -1.893 |
�� | -1.734 |
�� | -1.707 |
Token | people |
Token ID | 661 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
acebook | +2.867 |
utherland | +2.859 |
phabet | +2.842 |
Civil | +2.684 |
sung | +2.458 |
Neg logit contributions | |
�� | -5.830 |
�� | -5.246 |
�� | -4.893 |
�� | -4.469 |
�� | -4.379 |
Token | nearby |
Token ID | 6716 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
acebook | +1.340 |
phabet | +1.328 |
utherland | +1.326 |
Civil | +1.225 |
sung | +1.113 |
Neg logit contributions | |
�� | -3.452 |
�� | -3.132 |
�� | -2.940 |
�� | -2.691 |
�� | -2.650 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
�� | +0.657 |
�� | +0.592 |
�� | +0.555 |
�� | +0.509 |
�� | +0.500 |
Neg logit contributions | |
acebook | -0.270 |
phabet | -0.270 |
utherland | -0.266 |
Civil | -0.239 |
FontSize | -0.226 |
Token | un |
Token ID | 555 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
acebook | +0.766 |
phabet | +0.763 |
utherland | +0.757 |
Civil | +0.693 |
FontSize | +0.643 |
Neg logit contributions | |
�� | -1.771 |
�� | -1.597 |
�� | -1.495 |
�� | -1.367 |
�� | -1.345 |
Token | connected |
Token ID | 15236 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
utherland | +6.815 |
phabet | +6.792 |
acebook | +6.769 |
Civil | +6.489 |
ro | +6.430 |
Neg logit contributions | |
�� | -15.603 |
�� | -14.135 |
�� | -13.506 |
�� | -12.309 |
�� | -12.029 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
acebook | +2.607 |
phabet | +2.568 |
utherland | +2.556 |
Civil | +2.377 |
sung | +2.094 |
Neg logit contributions | |
�� | -7.561 |
�� | -6.879 |
�� | -6.476 |
�� | -5.946 |
�� | -5.846 |
Token | the |
Token ID | 262 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
acebook | +0.703 |
phabet | +0.701 |
utherland | +0.695 |
Civil | +0.637 |
FontSize | +0.594 |
Neg logit contributions | |
�� | -1.554 |
�� | -1.397 |
�� | -1.308 |
�� | -1.194 |
�� | -1.174 |
Token | pair |
Token ID | 5166 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
acebook | +0.216 |
phabet | +0.215 |
utherland | +0.213 |
Civil | +0.193 |
FontSize | +0.179 |
Neg logit contributions | |
�� | -0.550 |
�� | -0.497 |
�� | -0.466 |
�� | -0.427 |
�� | -0.421 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
acebook | +0.370 |
phabet | +0.369 |
utherland | +0.365 |
Civil | +0.337 |
FontSize | +0.317 |
Neg logit contributions | |
�� | -0.723 |
�� | -0.648 |
�� | -0.604 |
�� | -0.549 |
�� | -0.539 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
acebook | +7.387 |
utherland | +7.331 |
phabet | +7.217 |
Civil | +6.947 |
LINK | +6.368 |
Neg logit contributions | |
�� | -20.911 |
�� | -18.880 |
�� | -18.044 |
�� | -16.711 |
�� | -16.617 |
Token | GROUP |
Token ID | 44441 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
acebook | +1.975 |
phabet | +1.963 |
utherland | +1.954 |
Civil | +1.803 |
FontSize | +1.641 |
Neg logit contributions | |
�� | -5.168 |
�� | -4.675 |
�� | -4.398 |
�� | -4.050 |
�� | -3.992 |
Token | BY |
Token ID | 11050 |
Feature activation | -8.82e+00 |
Pos logit contributions | |
utherland | +1.340 |
phabet | +1.330 |
acebook | +1.317 |
Civil | +1.185 |
sung | +1.035 |
Neg logit contributions | |
�� | -5.105 |
�� | -4.671 |
�� | -4.409 |
�� | -4.110 |
�� | -4.025 |
Token | library |
Token ID | 5888 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
utherland | +5.213 |
phabet | +5.197 |
acebook | +5.190 |
Civil | +4.909 |
LINK | +4.470 |
Neg logit contributions | |
�� | -13.430 |
�� | -12.086 |
�� | -11.599 |
�� | -10.573 |
�� | -10.399 |
Token | , |
Token ID | 837 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
phabet | +6.454 |
utherland | +6.331 |
acebook | +6.322 |
Civil | +6.020 |
LINK | +5.479 |
Neg logit contributions | |
�� | -17.347 |
�� | -15.585 |
�� | -14.844 |
�� | -13.858 |
�� | -13.624 |
Token | version |
Token ID | 2196 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
phabet | +3.288 |
utherland | +3.280 |
acebook | +3.255 |
Civil | +3.056 |
FontSize | +2.724 |
Neg logit contributions | |
�� | -8.373 |
�� | -7.586 |
�� | -7.166 |
�� | -6.585 |
�� | -6.477 |
Token | H |
Token ID | 367 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
phabet | +7.076 |
utherland | +7.002 |
acebook | +6.969 |
Civil | +6.654 |
LINK | +6.054 |
Neg logit contributions | |
�� | -19.439 |
�� | -17.535 |
�� | -16.728 |
�� | -15.514 |
�� | -15.327 |
Token | AV |
Token ID | 10116 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
acebook | +0.455 |
phabet | +0.453 |
utherland | +0.448 |
Civil | +0.395 |
FontSize | +0.356 |
Neg logit contributions | |
�� | -1.643 |
�� | -1.499 |
�� | -1.414 |
�� | -1.309 |
�� | -1.290 |
Token | ING |
Token ID | 2751 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
acebook | +0.446 |
phabet | +0.444 |
utherland | +0.442 |
Civil | +0.410 |
FontSize | +0.388 |
Neg logit contributions | |
�� | -0.806 |
�� | -0.719 |
�� | -0.669 |
�� | -0.607 |
�� | -0.595 |
Token | library |
Token ID | 5888 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
utherland | +7.429 |
phabet | +7.225 |
acebook | +7.213 |
Civil | +6.974 |
LINK | +6.557 |
Neg logit contributions | |
�� | -18.160 |
�� | -16.201 |
�� | -15.664 |
�� | -14.213 |
�� | -14.035 |
Token | is |
Token ID | 318 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
utherland | +5.224 |
phabet | +5.201 |
acebook | +5.109 |
Civil | +4.783 |
LINK | +4.382 |
Neg logit contributions | |
�� | -15.786 |
�� | -14.320 |
�� | -13.450 |
�� | -12.596 |
�� | -12.483 |
Token | House |
Token ID | 2097 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
�� | +2.500 |
�� | +2.250 |
�� | +2.105 |
�� | +1.929 |
�� | +1.893 |
Neg logit contributions | |
phabet | -1.018 |
acebook | -1.018 |
utherland | -1.002 |
Civil | -0.887 |
FontSize | -0.854 |
Token | press |
Token ID | 1803 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
�� | +2.651 |
�� | +2.372 |
�� | +2.213 |
�� | +2.017 |
�� | +1.985 |
Neg logit contributions | |
acebook | -1.242 |
phabet | -1.235 |
utherland | -1.215 |
Civil | -1.090 |
FontSize | -1.041 |
Token | secretary |
Token ID | 7705 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
acebook | +1.687 |
phabet | +1.687 |
utherland | +1.675 |
Civil | +1.540 |
FontSize | +1.442 |
Neg logit contributions | |
�� | -3.581 |
�� | -3.221 |
�� | -3.008 |
�� | -2.743 |
�� | -2.696 |
Token | . |
Token ID | 13 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
acebook | +0.576 |
phabet | +0.575 |
utherland | +0.570 |
Civil | +0.526 |
FontSize | +0.492 |
Neg logit contributions | |
�� | -1.190 |
�� | -1.068 |
�� | -0.997 |
�� | -0.909 |
�� | -0.893 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
�� | +0.910 |
�� | +0.819 |
�� | +0.767 |
�� | +0.698 |
�� | +0.690 |
Neg logit contributions | |
acebook | -0.387 |
phabet | -0.387 |
utherland | -0.380 |
Civil | -0.342 |
FontSize | -0.322 |
Token | AL |
Token ID | 1847 |
Feature activation | -9.16e+00 |
Pos logit contributions | |
�� | +2.359 |
�� | +2.120 |
�� | +1.986 |
�� | +1.814 |
�� | +1.783 |
Neg logit contributions | |
acebook | -1.026 |
phabet | -1.014 |
utherland | -1.007 |
Civil | -0.913 |
FontSize | -0.842 |
Token | B |
Token ID | 33 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
phabet | +5.552 |
acebook | +5.231 |
utherland | +5.193 |
Civil | +4.962 |
FontSize | +4.491 |
Neg logit contributions | |
�� | -13.940 |
�� | -12.469 |
�� | -11.891 |
�� | -11.029 |
�� | -10.760 |
Token | ION |
Token ID | 2849 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
�� | +9.410 |
�� | +8.293 |
�� | +7.683 |
�� | +6.996 |
�� | +6.947 |
Neg logit contributions | |
acebook | -4.631 |
phabet | -4.617 |
utherland | -4.482 |
Civil | -3.918 |
FontSize | -3.848 |
Token | are |
Token ID | 389 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
acebook | +4.688 |
phabet | +4.605 |
utherland | +4.572 |
Civil | +4.437 |
sung | +3.983 |
Neg logit contributions | |
�� | -10.164 |
�� | -9.173 |
�� | -8.599 |
�� | -7.848 |
�� | -7.698 |
Token | delighted |
Token ID | 20707 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
�� | +1.734 |
�� | +1.556 |
�� | +1.447 |
�� | +1.325 |
�� | +1.301 |
Neg logit contributions | |
acebook | -0.820 |
phabet | -0.819 |
utherland | -0.807 |
Civil | -0.727 |
FontSize | -0.694 |
Token | to |
Token ID | 284 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
acebook | +0.150 |
phabet | +0.150 |
utherland | +0.148 |
Civil | +0.133 |
FontSize | +0.125 |
Neg logit contributions | |
�� | -0.377 |
�� | -0.340 |
�� | -0.319 |
�� | -0.292 |
�� | -0.288 |
Token | flex |
Token ID | 32880 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
phabet | +1.258 |
acebook | +1.254 |
utherland | +1.240 |
Civil | +1.142 |
sung | +1.069 |
Neg logit contributions | |
�� | -2.671 |
�� | -2.399 |
�� | -2.243 |
�� | -2.046 |
�� | -2.017 |
Token | ible |
Token ID | 856 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
�� | +1.545 |
�� | +1.386 |
�� | +1.292 |
�� | +1.175 |
�� | +1.154 |
Neg logit contributions | |
acebook | -0.767 |
phabet | -0.765 |
utherland | -0.760 |
Civil | -0.697 |
FontSize | -0.658 |
Token | - |
Token ID | 12 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
phabet | +2.625 |
acebook | +2.617 |
utherland | +2.584 |
Civil | +2.380 |
sung | +2.204 |
Neg logit contributions | |
�� | -6.108 |
�� | -5.479 |
�� | -5.136 |
�� | -4.719 |
�� | -4.674 |
Token | limit |
Token ID | 32374 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
phabet | +1.878 |
acebook | +1.873 |
utherland | +1.849 |
Civil | +1.681 |
sung | +1.586 |
Neg logit contributions | |
�� | -4.600 |
�� | -4.150 |
�� | -3.893 |
�� | -3.580 |
�� | -3.531 |
Token | - |
Token ID | 12 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
�� | +2.133 |
�� | +1.916 |
�� | +1.788 |
�� | +1.623 |
�� | +1.595 |
Neg logit contributions | |
acebook | -1.044 |
phabet | -1.038 |
utherland | -1.029 |
Civil | -0.944 |
FontSize | -0.893 |
Token | tr |
Token ID | 2213 |
Feature activation | -9.64e+00 |
Pos logit contributions | |
�� | +1.539 |
�� | +1.382 |
�� | +1.288 |
�� | +1.168 |
�� | +1.145 |
Neg logit contributions | |
acebook | -0.761 |
phabet | -0.756 |
utherland | -0.752 |
Civil | -0.690 |
FontSize | -0.650 |
Token | ading |
Token ID | 4980 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
acebook | +7.117 |
utherland | +6.899 |
phabet | +6.761 |
Civil | +6.225 |
sung | +5.939 |
Neg logit contributions | |
�� | -13.975 |
�� | -12.588 |
�� | -11.718 |
�� | -10.869 |
�� | -10.535 |
Token | - |
Token ID | 12 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
acebook | +0.184 |
phabet | +0.183 |
utherland | +0.182 |
Civil | +0.167 |
FontSize | +0.156 |
Neg logit contributions | |
�� | -0.394 |
�� | -0.354 |
�� | -0.331 |
�� | -0.302 |
�� | -0.297 |
Token | sub |
Token ID | 7266 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
�� | +0.620 |
�� | +0.556 |
�� | +0.518 |
�� | +0.471 |
�� | +0.462 |
Neg logit contributions | |
acebook | -0.307 |
phabet | -0.305 |
utherland | -0.303 |
Civil | -0.278 |
FontSize | -0.262 |
Token | s |
Token ID | 82 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
�� | +4.109 |
�� | +3.702 |
�� | +3.429 |
�� | +3.130 |
�� | +3.072 |
Neg logit contributions | |
acebook | -2.004 |
phabet | -1.984 |
utherland | -1.982 |
Civil | -1.807 |
FontSize | -1.736 |
Token | idy |
Token ID | 19325 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
�� | +7.445 |
�� | +6.640 |
�� | +6.128 |
�� | +5.506 |
�� | +5.447 |
Neg logit contributions | |
phabet | -4.470 |
acebook | -4.405 |
utherland | -4.262 |
Civil | -4.074 |
FontSize | -3.953 |
Token | � |
Token ID | 251 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
�� | +2.383 |
�� | +1.917 |
�� | +1.631 |
�� | +1.288 |
�� | +1.219 |
Neg logit contributions | |
acebook | -4.522 |
utherland | -4.503 |
phabet | -4.502 |
Civil | -4.315 |
FontSize | -4.177 |
Token | and |
Token ID | 290 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
acebook | +1.449 |
phabet | +1.445 |
utherland | +1.431 |
Civil | +1.313 |
sung | +1.206 |
Neg logit contributions | |
�� | -3.644 |
�� | -3.292 |
�� | -3.085 |
�� | -2.840 |
�� | -2.795 |
Token | � |
Token ID | 564 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
�� | +1.472 |
�� | +1.330 |
�� | +1.246 |
�� | +1.141 |
�� | +1.125 |
Neg logit contributions | |
acebook | -0.586 |
phabet | -0.582 |
utherland | -0.578 |
Civil | -0.520 |
FontSize | -0.487 |
Token | � |
Token ID | 250 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
�� | +1.153 |
�� | +0.903 |
�� | +0.758 |
�� | +0.577 |
�� | +0.545 |
Neg logit contributions | |
acebook | -2.455 |
phabet | -2.448 |
utherland | -2.440 |
Civil | -2.345 |
FontSize | -2.277 |
Token | Love |
Token ID | 18565 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
�� | +2.129 |
�� | +1.917 |
�� | +1.797 |
�� | +1.641 |
�� | +1.612 |
Neg logit contributions | |
acebook | -0.909 |
phabet | -0.898 |
utherland | -0.894 |
Civil | -0.809 |
FontSize | -0.753 |
Token | tr |
Token ID | 491 |
Feature activation | -9.16e+00 |
Pos logit contributions | |
�� | +4.951 |
�� | +4.453 |
�� | +4.156 |
�� | +3.760 |
�� | +3.709 |
Neg logit contributions | |
acebook | -2.358 |
phabet | -2.326 |
utherland | -2.315 |
Civil | -2.059 |
FontSize | -1.995 |
Token | umps |
Token ID | 8142 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
acebook | +5.981 |
utherland | +5.880 |
phabet | +5.830 |
Civil | +5.408 |
ieth | +4.992 |
Neg logit contributions | |
�� | -13.663 |
�� | -12.360 |
�� | -11.571 |
�� | -10.680 |
�� | -10.285 |
Token | hate |
Token ID | 5465 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
�� | +3.445 |
�� | +3.107 |
�� | +2.892 |
�� | +2.654 |
�� | +2.611 |
Neg logit contributions | |
acebook | -1.500 |
phabet | -1.499 |
utherland | -1.481 |
Civil | -1.309 |
FontSize | -1.266 |
Token | , |
Token ID | 11 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
�� | +3.783 |
�� | +3.417 |
�� | +3.195 |
�� | +2.915 |
�� | +2.875 |
Neg logit contributions | |
acebook | -1.562 |
phabet | -1.539 |
utherland | -1.522 |
Civil | -1.370 |
FontSize | -1.312 |
Token | � |
Token ID | 447 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
�� | +0.802 |
�� | +0.729 |
�� | +0.686 |
�� | +0.631 |
�� | +0.622 |
Neg logit contributions | |
acebook | -0.264 |
phabet | -0.262 |
utherland | -0.259 |
Civil | -0.230 |
FontSize | -0.212 |
Token | � |
Token ID | 251 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
�� | +0.628 |
�� | +0.508 |
�� | +0.440 |
�� | +0.352 |
�� | +0.338 |
Neg logit contributions | |
acebook | -1.097 |
phabet | -1.097 |
utherland | -1.090 |
Civil | -1.046 |
FontSize | -1.015 |