Token | � |
Token ID | 251 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
clair | +0.199 |
hran | +0.197 |
Ul | +0.194 |
rily | +0.185 |
Tanz | +0.179 |
Neg logit contributions | |
`` | -0.191 |
HL | -0.183 |
ESV | -0.174 |
subs | -0.174 |
`` | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
clair | +3.950 |
hran | +3.893 |
Ul | +3.863 |
rily | +3.622 |
Tanz | +3.580 |
Neg logit contributions | |
`` | -4.323 |
HL | -4.182 |
subs | -4.131 |
ousse | -4.005 |
ESV | -4.004 |
Token |
|
Token ID | 198 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
Ul | +1.246 |
clair | +1.243 |
hran | +1.213 |
rily | +1.133 |
Ros | +1.120 |
Neg logit contributions | |
`` | -1.521 |
HL | -1.493 |
ESV | -1.455 |
Dise | -1.444 |
subs | -1.440 |
Token | ( |
Token ID | 7 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
clair | +3.143 |
Ul | +3.120 |
hran | +3.069 |
rily | +2.872 |
trump | +2.825 |
Neg logit contributions | |
HL | -2.807 |
`` | -2.796 |
subs | -2.700 |
ESV | -2.668 |
Dise | -2.599 |
Token | © |
Token ID | 16224 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
clair | +1.857 |
hran | +1.842 |
Ul | +1.834 |
rily | +1.705 |
Tanz | +1.661 |
Neg logit contributions | |
`` | -1.938 |
HL | -1.872 |
subs | -1.797 |
ESV | -1.782 |
ousse | -1.746 |
Token | Copyright |
Token ID | 15069 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
clair | +3.809 |
Ul | +3.747 |
hran | +3.668 |
rily | +3.365 |
Tanz | +3.335 |
Neg logit contributions | |
`` | -5.420 |
HL | -5.129 |
subs | -5.011 |
ESV | -5.005 |
ousse | -4.975 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
clair | +7.671 |
Ul | +7.593 |
Ros | +7.413 |
hran | +7.413 |
Tanz | +7.229 |
Neg logit contributions | |
`` | -10.313 |
ヘ | -9.471 |
ousse | -9.344 |
HL | -9.022 |
ESV | -8.988 |
Token | The |
Token ID | 383 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
clair | +4.213 |
hran | +4.092 |
Ul | +4.090 |
Ros | +3.852 |
rily | +3.834 |
Neg logit contributions | |
`` | -4.845 |
subs | -4.396 |
ousse | -4.395 |
HL | -4.392 |
ヘ | -4.328 |
Token | Associated |
Token ID | 10575 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
clair | +0.810 |
hran | +0.808 |
Ul | +0.790 |
rily | +0.743 |
Tanz | +0.724 |
Neg logit contributions | |
`` | -0.898 |
HL | -0.860 |
subs | -0.834 |
ESV | -0.821 |
ousse | -0.813 |
Token | Press |
Token ID | 4332 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
hran | +0.381 |
clair | +0.378 |
Ul | +0.375 |
rily | +0.327 |
Tanz | +0.321 |
Neg logit contributions | |
`` | -1.128 |
HL | -1.096 |
subs | -1.080 |
ESV | -1.063 |
ousse | -1.061 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
hran | +2.091 |
Ul | +2.051 |
clair | +2.048 |
Ros | +1.825 |
oute | +1.823 |
Neg logit contributions | |
`` | -3.268 |
HL | -3.110 |
subs | -3.009 |
ESV | -2.946 |
ousse | -2.936 |
Token | v |
Token ID | 410 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
clair | +2.025 |
hran | +2.023 |
Ul | +1.984 |
rily | +1.881 |
Tanz | +1.839 |
Neg logit contributions | |
`` | -1.843 |
HL | -1.750 |
subs | -1.668 |
ESV | -1.665 |
ousse | -1.623 |
Token | Blues |
Token ID | 15261 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
hran | +2.765 |
clair | +2.739 |
Ul | +2.710 |
rily | +2.552 |
Ros | +2.520 |
Neg logit contributions | |
`` | -2.725 |
HL | -2.570 |
subs | -2.480 |
ESV | -2.464 |
ousse | -2.435 |
Token | – |
Token ID | 784 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
hran | +3.102 |
clair | +3.100 |
Ul | +3.012 |
rily | +2.797 |
Ros | +2.760 |
Neg logit contributions | |
`` | -3.951 |
HL | -3.686 |
ESV | -3.587 |
subs | -3.560 |
ousse | -3.530 |
Token | Lost |
Token ID | 9164 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
hran | +2.856 |
clair | +2.848 |
Ul | +2.820 |
rily | +2.674 |
Ros | +2.638 |
Neg logit contributions | |
`` | -2.242 |
HL | -2.104 |
subs | -2.012 |
ESV | -1.983 |
ousse | -1.953 |
Token | 4 |
Token ID | 604 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
clair | +1.475 |
hran | +1.470 |
Ul | +1.441 |
rily | +1.376 |
Tanz | +1.334 |
Neg logit contributions | |
`` | -1.549 |
HL | -1.459 |
ESV | -1.404 |
subs | -1.397 |
ousse | -1.376 |
Token | - |
Token ID | 12 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Ul | +1.691 |
hran | +1.644 |
clair | +1.643 |
rily | +1.486 |
Ros | +1.484 |
Neg logit contributions | |
`` | -2.920 |
HL | -2.795 |
subs | -2.746 |
Dise | -2.726 |
ousse | -2.720 |
Token | 0 |
Token ID | 15 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
Ul | +6.419 |
clair | +6.320 |
hran | +6.122 |
rily | +5.579 |
trump | +5.560 |
Neg logit contributions | |
`` | -10.752 |
HL | -10.415 |
`` | -10.091 |
Dise | -10.078 |
ESV | -10.069 |
Token |
|
Token ID | 198 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
hran | +2.376 |
clair | +2.371 |
Ul | +2.330 |
rily | +2.207 |
Tanz | +2.145 |
Neg logit contributions | |
`` | -2.621 |
HL | -2.459 |
ESV | -2.377 |
subs | -2.369 |
ousse | -2.333 |
Token |
|
Token ID | 198 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Ul | +1.728 |
clair | +1.715 |
hran | +1.672 |
rily | +1.561 |
Ros | +1.558 |
Neg logit contributions | |
`` | -2.222 |
HL | -2.170 |
senal | -2.149 |
Dise | -2.139 |
ESV | -2.122 |
Token | Se |
Token ID | 4653 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Ul | +3.232 |
clair | +3.231 |
hran | +3.188 |
rily | +2.956 |
trump | +2.881 |
Neg logit contributions | |
`` | -3.483 |
HL | -3.425 |
ESV | -3.286 |
subs | -3.245 |
Dise | -3.231 |
Token | eking |
Token ID | 18754 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
hran | +1.925 |
clair | +1.924 |
Ul | +1.856 |
rily | +1.758 |
Tanz | +1.683 |
Neg logit contributions | |
`` | -2.314 |
HL | -2.242 |
ESV | -2.150 |
subs | -2.141 |
Dise | -2.090 |
Token | 47 |
Token ID | 2857 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
`` | +2.673 |
HL | +2.564 |
ESV | +2.431 |
subs | +2.429 |
Lange | +2.340 |
Neg logit contributions | |
clair | -2.778 |
hran | -2.768 |
Ul | -2.674 |
rily | -2.585 |
Tanz | -2.506 |
Token | s |
Token ID | 82 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
`` | +1.083 |
HL | +1.041 |
ESV | +0.988 |
subs | +0.987 |
ousse | +0.955 |
Neg logit contributions | |
clair | -1.172 |
hran | -1.171 |
Ul | -1.151 |
rily | -1.091 |
Tanz | -1.057 |
Token | )} |
Token ID | 38165 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
clair | +2.205 |
Ul | +2.150 |
hran | +2.111 |
rily | +1.921 |
Ros | +1.813 |
Neg logit contributions | |
HL | -6.463 |
`` | -6.383 |
ESV | -6.292 |
Dise | -6.282 |
subs | -6.277 |
Token | 58 |
Token ID | 7618 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
hran | +2.541 |
Ul | +2.513 |
clair | +2.468 |
rily | +2.298 |
Tanz | +2.244 |
Neg logit contributions | |
`` | -3.895 |
HL | -3.764 |
subs | -3.613 |
ESV | -3.588 |
ousse | -3.557 |
Token | . |
Token ID | 13 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
Ul | +3.312 |
clair | +3.109 |
hran | +2.970 |
Ros | +2.904 |
atar | +2.689 |
Neg logit contributions | |
senal | -6.897 |
`` | -6.426 |
Dise | -6.421 |
HL | -6.397 |
ーティ | -6.380 |
Token | Re |
Token ID | 797 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Ul | +4.670 |
hran | +4.612 |
clair | +4.451 |
Ros | +4.288 |
Tanz | +4.192 |
Neg logit contributions | |
`` | -5.666 |
HL | -5.369 |
ousse | -5.211 |
ヘ | -5.209 |
ESV | -5.130 |
Token | 1 |
Token ID | 16 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
hran | +7.042 |
Ul | +6.939 |
clair | +6.765 |
ception | +6.022 |
trump | +5.959 |
Neg logit contributions | |
HL | -9.632 |
Dise | -9.502 |
`` | -9.465 |
ーティ | -9.399 |
Lange | -9.325 |
Token | { |
Token ID | 1391 |
Feature activation | +2.28e-04 |
Pos logit contributions | |
Ul | +4.251 |
hran | +4.196 |
clair | +4.051 |
rily | +3.789 |
Ros | +3.721 |
Neg logit contributions | |
`` | -6.475 |
HL | -6.288 |
ESV | -6.007 |
ousse | -5.974 |
subs | -5.973 |
Token | ( |
Token ID | 7 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
clair | +0.002 |
hran | +0.002 |
Ul | +0.002 |
rily | +0.002 |
trump | +0.002 |
Neg logit contributions | |
`` | -0.002 |
HL | -0.002 |
ESV | -0.002 |
subs | -0.002 |
Lange | -0.002 |
Token | 25 |
Token ID | 1495 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
`` | +0.906 |
HL | +0.871 |
subs | +0.831 |
ESV | +0.829 |
`` | +0.800 |
Neg logit contributions | |
clair | -0.854 |
hran | -0.853 |
Ul | -0.830 |
rily | -0.790 |
Tanz | -0.768 |
Token | s |
Token ID | 82 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
`` | +0.727 |
HL | +0.700 |
ESV | +0.665 |
subs | +0.663 |
ousse | +0.643 |
Neg logit contributions | |
hran | -0.777 |
clair | -0.776 |
Ul | -0.764 |
rily | -0.723 |
Tanz | -0.700 |
Token | receiver |
Token ID | 9733 |
Feature activation | -8.62e-03 |
Pos logit contributions | |
`` | +2.081 |
HL | +2.043 |
subs | +1.938 |
ESV | +1.916 |
`` | +1.866 |
Neg logit contributions | |
clair | -2.297 |
hran | -2.297 |
Ul | -2.232 |
rily | -2.124 |
Tanz | -2.062 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
`` | +0.076 |
HL | +0.074 |
subs | +0.070 |
ESV | +0.070 |
ousse | +0.068 |
Neg logit contributions | |
clair | -0.069 |
hran | -0.069 |
Ul | -0.068 |
rily | -0.064 |
Tanz | -0.062 |
Token | The |
Token ID | 383 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
`` | +1.321 |
HL | +1.279 |
ESV | +1.204 |
subs | +1.201 |
`` | +1.166 |
Neg logit contributions | |
clair | -1.470 |
hran | -1.469 |
Ul | -1.431 |
rily | -1.366 |
Tanz | -1.328 |
Token | more |
Token ID | 517 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
`` | +0.719 |
HL | +0.697 |
subs | +0.664 |
ESV | +0.663 |
`` | +0.641 |
Neg logit contributions | |
clair | -0.665 |
hran | -0.664 |
Ul | -0.649 |
rily | -0.613 |
Tanz | -0.596 |
Token | familiar |
Token ID | 5385 |
Feature activation | -9.74e-03 |
Pos logit contributions | |
`` | +0.812 |
HL | +0.788 |
subs | +0.751 |
ESV | +0.746 |
`` | +0.723 |
Neg logit contributions | |
hran | -0.786 |
clair | -0.784 |
Ul | -0.764 |
rily | -0.724 |
Tanz | -0.706 |
Token | RT |
Token ID | 11923 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
`` | +0.094 |
HL | +0.092 |
subs | +0.088 |
ESV | +0.088 |
`` | +0.085 |
Neg logit contributions | |
clair | -0.070 |
hran | -0.070 |
Ul | -0.068 |
rily | -0.064 |
Tanz | -0.062 |
Token | T |
Token ID | 51 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
hran | +6.131 |
Ul | +6.092 |
clair | +5.984 |
Ros | +5.569 |
rily | +5.532 |
Neg logit contributions | |
`` | -9.678 |
HL | -9.409 |
ousse | -9.360 |
ESV | -9.342 |
Dise | -9.198 |
Token | ( |
Token ID | 357 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
hran | +5.098 |
Ul | +5.080 |
clair | +5.076 |
rily | +4.726 |
Ros | +4.681 |
Neg logit contributions | |
`` | -5.539 |
HL | -5.311 |
ESV | -5.212 |
ousse | -5.137 |
subs | -5.072 |
Token | round |
Token ID | 744 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
clair | +1.882 |
hran | +1.852 |
Ul | +1.851 |
rily | +1.727 |
oute | +1.671 |
Neg logit contributions | |
`` | -2.126 |
HL | -2.070 |
subs | -1.991 |
ESV | -1.987 |
ousse | -1.927 |
Token | - |
Token ID | 12 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
hran | +0.058 |
clair | +0.057 |
Ul | +0.056 |
rily | +0.053 |
Tanz | +0.052 |
Neg logit contributions | |
`` | -0.067 |
HL | -0.065 |
subs | -0.063 |
ESV | -0.062 |
`` | -0.060 |
Token | trip |
Token ID | 39813 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
hran | +0.181 |
clair | +0.179 |
Ul | +0.176 |
rily | +0.166 |
Tanz | +0.163 |
Neg logit contributions | |
`` | -0.199 |
HL | -0.190 |
subs | -0.182 |
ESV | -0.182 |
ousse | -0.177 |
Token | ( |
Token ID | 7 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Ul | +1.113 |
clair | +1.101 |
hran | +1.080 |
rily | +0.990 |
trump | +0.970 |
Neg logit contributions | |
`` | -1.481 |
HL | -1.478 |
ESV | -1.425 |
subs | -1.421 |
Dise | -1.410 |
Token | 8 |
Token ID | 23 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
`` | +1.330 |
HL | +1.276 |
subs | +1.211 |
ESV | +1.211 |
`` | +1.166 |
Neg logit contributions | |
hran | -1.407 |
clair | -1.407 |
Ul | -1.371 |
rily | -1.309 |
Tanz | -1.272 |
Token | 26 |
Token ID | 2075 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
hran | +1.448 |
clair | +1.432 |
Ul | +1.424 |
rily | +1.330 |
Tanz | +1.293 |
Neg logit contributions | |
`` | -1.706 |
HL | -1.647 |
ESV | -1.569 |
subs | -1.568 |
ousse | -1.542 |
Token | s |
Token ID | 82 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
`` | +0.467 |
HL | +0.452 |
ESV | +0.430 |
subs | +0.427 |
Dise | +0.418 |
Neg logit contributions | |
clair | -0.482 |
hran | -0.481 |
Ul | -0.476 |
rily | -0.448 |
trump | -0.432 |
Token | )} |
Token ID | 38165 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
clair | +2.457 |
Ul | +2.358 |
hran | +2.307 |
rily | +2.087 |
Ros | +2.002 |
Neg logit contributions | |
HL | -7.798 |
senal | -7.696 |
Dise | -7.643 |
`` | -7.577 |
subs | -7.561 |
Token | h |
Token ID | 289 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Ul | +5.352 |
hran | +5.277 |
clair | +5.105 |
Ros | +5.057 |
Tanz | +4.850 |
Neg logit contributions | |
`` | -6.531 |
ousse | -6.028 |
ーティ | -6.027 |
ヘ | -6.026 |
HL | -6.026 |
Token | 4 |
Token ID | 19 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
Ul | +6.977 |
hran | +6.707 |
clair | +6.618 |
trump | +6.055 |
oute | +6.020 |
Neg logit contributions | |
HL | -9.177 |
`` | -9.021 |
subs | -8.658 |
Dise | -8.637 |
Lange | -8.589 |
Token | { |
Token ID | 1391 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Ul | +2.894 |
hran | +2.890 |
clair | +2.845 |
rily | +2.580 |
Ros | +2.561 |
Neg logit contributions | |
`` | -4.708 |
HL | -4.553 |
subs | -4.367 |
Dise | -4.320 |
ヘ | -4.302 |
Token | ( |
Token ID | 7 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Ul | +1.060 |
clair | +1.052 |
hran | +1.030 |
rily | +0.944 |
trump | +0.925 |
Neg logit contributions | |
`` | -1.411 |
HL | -1.405 |
ESV | -1.358 |
subs | -1.353 |
Dise | -1.343 |
Token | 233 |
Token ID | 25429 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
`` | +2.566 |
HL | +2.464 |
ESV | +2.331 |
subs | +2.321 |
`` | +2.244 |
Neg logit contributions | |
hran | -2.820 |
clair | -2.811 |
Ul | -2.726 |
rily | -2.626 |
Tanz | -2.542 |
Token | s |
Token ID | 82 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
`` | +1.392 |
HL | +1.337 |
ESV | +1.268 |
subs | +1.268 |
ousse | +1.225 |
Neg logit contributions | |
clair | -1.512 |
hran | -1.510 |
Ul | -1.484 |
rily | -1.409 |
Tanz | -1.365 |
Token |
|
Token ID | 198 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
`` | +0.584 |
HL | +0.562 |
subs | +0.530 |
ESV | +0.530 |
`` | +0.512 |
Neg logit contributions | |
clair | -0.661 |
hran | -0.659 |
Ul | -0.644 |
rily | -0.615 |
Tanz | -0.596 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
Ul | +1.590 |
clair | +1.580 |
hran | +1.554 |
rily | +1.456 |
Ros | +1.431 |
Neg logit contributions | |
`` | -1.954 |
HL | -1.907 |
ESV | -1.853 |
Dise | -1.847 |
subs | -1.831 |
Token | To |
Token ID | 2514 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
`` | +1.728 |
HL | +1.602 |
subs | +1.504 |
ESV | +1.491 |
ousse | +1.450 |
Neg logit contributions | |
hran | -2.193 |
clair | -2.178 |
Ul | -2.073 |
rily | -2.053 |
Tanz | -2.003 |
Token | put |
Token ID | 1234 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
`` | +1.938 |
HL | +1.888 |
subs | +1.820 |
ESV | +1.766 |
Lange | +1.732 |
Neg logit contributions | |
clair | -2.017 |
hran | -2.005 |
Ul | -1.950 |
rily | -1.851 |
oute | -1.796 |
Token | it |
Token ID | 340 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
`` | +1.228 |
HL | +1.188 |
subs | +1.133 |
ESV | +1.116 |
`` | +1.083 |
Neg logit contributions | |
clair | -1.406 |
hran | -1.398 |
Ul | -1.367 |
rily | -1.299 |
Tanz | -1.261 |
Token | as |
Token ID | 355 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
hran | +1.992 |
clair | +1.988 |
Ul | +1.947 |
rily | +1.858 |
Tanz | +1.796 |
Neg logit contributions | |
`` | -1.920 |
HL | -1.842 |
ESV | -1.749 |
subs | -1.744 |
ousse | -1.697 |
Token | mildly |
Token ID | 33544 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
hran | +7.643 |
Ul | +7.504 |
clair | +7.370 |
Ros | +7.207 |
rily | +7.179 |
Neg logit contributions | |
`` | -8.321 |
HL | -7.909 |
Dise | -7.709 |
ousse | -7.682 |
ヘ | -7.628 |
Token | as |
Token ID | 355 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
clair | +6.401 |
hran | +6.397 |
Ul | +6.269 |
rily | +5.933 |
Ros | +5.877 |
Neg logit contributions | |
`` | -9.742 |
HL | -9.258 |
Dise | -9.226 |
ヘ | -9.033 |
ESV | -9.025 |
Token | I |
Token ID | 314 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
clair | +0.304 |
hran | +0.304 |
Ul | +0.296 |
rily | +0.278 |
Tanz | +0.269 |
Neg logit contributions | |
`` | -0.417 |
HL | -0.403 |
subs | -0.387 |
ESV | -0.387 |
ousse | -0.375 |
Token | can |
Token ID | 460 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
clair | +1.614 |
hran | +1.595 |
Ul | +1.562 |
rily | +1.494 |
Tanz | +1.416 |
Neg logit contributions | |
`` | -2.041 |
HL | -1.966 |
ESV | -1.891 |
subs | -1.878 |
ヘ | -1.858 |
Token | , |
Token ID | 11 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
clair | +2.450 |
hran | +2.426 |
Ul | +2.391 |
rily | +2.274 |
Tanz | +2.164 |
Neg logit contributions | |
`` | -2.918 |
HL | -2.808 |
ESV | -2.719 |
subs | -2.689 |
ヘ | -2.626 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
Ul | +1.590 |
clair | +1.580 |
hran | +1.554 |
rily | +1.456 |
Ros | +1.431 |
Neg logit contributions | |
`` | -1.954 |
HL | -1.907 |
ESV | -1.853 |
Dise | -1.847 |
subs | -1.831 |
Token | To |
Token ID | 2514 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
`` | +1.728 |
HL | +1.602 |
subs | +1.504 |
ESV | +1.491 |
ousse | +1.450 |
Neg logit contributions | |
hran | -2.193 |
clair | -2.178 |
Ul | -2.073 |
rily | -2.053 |
Tanz | -2.003 |
Token | put |
Token ID | 1234 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
`` | +1.938 |
HL | +1.888 |
subs | +1.820 |
ESV | +1.766 |
Lange | +1.732 |
Neg logit contributions | |
clair | -2.017 |
hran | -2.005 |
Ul | -1.950 |
rily | -1.851 |
oute | -1.796 |
Token | it |
Token ID | 340 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
`` | +1.228 |
HL | +1.188 |
subs | +1.133 |
ESV | +1.116 |
`` | +1.083 |
Neg logit contributions | |
clair | -1.406 |
hran | -1.398 |
Ul | -1.367 |
rily | -1.299 |
Tanz | -1.261 |
Token | as |
Token ID | 355 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
hran | +1.992 |
clair | +1.988 |
Ul | +1.947 |
rily | +1.858 |
Tanz | +1.796 |
Neg logit contributions | |
`` | -1.920 |
HL | -1.842 |
ESV | -1.749 |
subs | -1.744 |
ousse | -1.697 |
Token | mildly |
Token ID | 33544 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
hran | +7.643 |
Ul | +7.504 |
clair | +7.370 |
Ros | +7.207 |
rily | +7.179 |
Neg logit contributions | |
`` | -8.321 |
HL | -7.909 |
Dise | -7.709 |
ousse | -7.682 |
ヘ | -7.628 |
Token | as |
Token ID | 355 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
clair | +6.401 |
hran | +6.397 |
Ul | +6.269 |
rily | +5.933 |
Ros | +5.877 |
Neg logit contributions | |
`` | -9.742 |
HL | -9.258 |
Dise | -9.226 |
ヘ | -9.033 |
ESV | -9.025 |
Token | I |
Token ID | 314 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
clair | +0.304 |
hran | +0.304 |
Ul | +0.296 |
rily | +0.278 |
Tanz | +0.269 |
Neg logit contributions | |
`` | -0.417 |
HL | -0.403 |
subs | -0.387 |
ESV | -0.387 |
ousse | -0.375 |
Token | can |
Token ID | 460 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
clair | +1.614 |
hran | +1.595 |
Ul | +1.562 |
rily | +1.494 |
Tanz | +1.416 |
Neg logit contributions | |
`` | -2.041 |
HL | -1.966 |
ESV | -1.891 |
subs | -1.878 |
ヘ | -1.858 |
Token | , |
Token ID | 11 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
clair | +2.450 |
hran | +2.426 |
Ul | +2.391 |
rily | +2.274 |
Tanz | +2.164 |
Neg logit contributions | |
`` | -2.918 |
HL | -2.808 |
ESV | -2.719 |
subs | -2.689 |
ヘ | -2.626 |
Token | the |
Token ID | 262 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
`` | +1.933 |
HL | +1.878 |
subs | +1.784 |
ESV | +1.747 |
Lange | +1.720 |
Neg logit contributions | |
clair | -2.174 |
hran | -2.172 |
Ul | -2.115 |
rily | -2.027 |
oute | -1.959 |
Token | Blue |
Token ID | 4518 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
hran | +3.084 |
clair | +3.057 |
Ul | +3.006 |
rily | +2.831 |
Ros | +2.745 |
Neg logit contributions | |
`` | -3.314 |
HL | -3.133 |
ESV | -3.028 |
subs | -3.022 |
ousse | -2.940 |
Token | Jackets |
Token ID | 41324 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
clair | +0.516 |
hran | +0.513 |
Ul | +0.504 |
rily | +0.476 |
Tanz | +0.460 |
Neg logit contributions | |
`` | -0.494 |
HL | -0.471 |
ESV | -0.452 |
subs | -0.447 |
ousse | -0.436 |
Token | – |
Token ID | 784 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
clair | +2.535 |
hran | +2.518 |
Ul | +2.480 |
rily | +2.323 |
Ros | +2.287 |
Neg logit contributions | |
`` | -2.818 |
HL | -2.644 |
ESV | -2.551 |
subs | -2.537 |
ousse | -2.533 |
Token | Won |
Token ID | 23306 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
clair | +0.408 |
hran | +0.407 |
Ul | +0.399 |
rily | +0.378 |
Tanz | +0.368 |
Neg logit contributions | |
`` | -0.416 |
HL | -0.398 |
subs | -0.380 |
ESV | -0.380 |
ousse | -0.369 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
clair | +1.649 |
hran | +1.636 |
Ul | +1.614 |
rily | +1.528 |
Tanz | +1.477 |
Neg logit contributions | |
`` | -1.757 |
HL | -1.673 |
ESV | -1.624 |
subs | -1.606 |
Dise | -1.564 |
Token | - |
Token ID | 12 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
hran | +1.103 |
clair | +1.095 |
Ul | +1.084 |
rily | +1.008 |
Tanz | +0.970 |
Neg logit contributions | |
`` | -1.574 |
HL | -1.502 |
subs | -1.454 |
ESV | -1.446 |
ousse | -1.422 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Ul | +6.456 |
clair | +6.047 |
hran | +5.754 |
trump | +5.590 |
rily | +5.520 |
Neg logit contributions | |
`` | -9.630 |
HL | -9.607 |
Dise | -9.389 |
ESV | -9.291 |
`` | -9.287 |
Token |
|
Token ID | 198 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
hran | +1.879 |
clair | +1.876 |
Ul | +1.845 |
rily | +1.738 |
Tanz | +1.691 |
Neg logit contributions | |
`` | -2.158 |
HL | -2.028 |
ESV | -1.961 |
subs | -1.961 |
ousse | -1.926 |
Token |
|
Token ID | 198 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
clair | +0.275 |
Ul | +0.273 |
hran | +0.271 |
rily | +0.253 |
Ros | +0.246 |
Neg logit contributions | |
`` | -0.310 |
HL | -0.301 |
ESV | -0.291 |
subs | -0.289 |
Dise | -0.286 |
Token | Go |
Token ID | 5247 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
clair | +0.510 |
hran | +0.508 |
Ul | +0.501 |
rily | +0.472 |
Tanz | +0.457 |
Neg logit contributions | |
`` | -0.499 |
HL | -0.482 |
subs | -0.460 |
ESV | -0.459 |
ousse | -0.443 |
Token | als |
Token ID | 874 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
clair | +0.398 |
hran | +0.396 |
Ul | +0.389 |
rily | +0.364 |
Tanz | +0.351 |
Neg logit contributions | |
`` | -0.504 |
HL | -0.487 |
ESV | -0.467 |
subs | -0.467 |
ousse | -0.453 |
Token | 0 |
Token ID | 15 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
`` | +0.247 |
HL | +0.238 |
subs | +0.227 |
ESV | +0.226 |
ousse | +0.219 |
Neg logit contributions | |
clair | -0.226 |
hran | -0.226 |
Ul | -0.221 |
rily | -0.209 |
Tanz | -0.203 |
Token | s |
Token ID | 82 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
`` | +0.990 |
HL | +0.955 |
subs | +0.912 |
ESV | +0.904 |
Lange | +0.865 |
Neg logit contributions | |
clair | -1.199 |
hran | -1.170 |
Ul | -1.139 |
rily | -1.088 |
oute | -1.069 |
Token | )} |
Token ID | 38165 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
hran | +2.842 |
clair | +2.829 |
Ul | +2.750 |
rily | +2.569 |
Tanz | +2.431 |
Neg logit contributions | |
`` | -5.854 |
HL | -5.690 |
subs | -5.496 |
ESV | -5.484 |
ousse | -5.360 |
Token | N |
Token ID | 399 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
hran | +4.675 |
Ul | +4.606 |
clair | +4.596 |
Ros | +4.267 |
rily | +4.255 |
Neg logit contributions | |
`` | -5.114 |
HL | -4.776 |
ヘ | -4.607 |
Dise | -4.607 |
ousse | -4.587 |
Token | f |
Token ID | 69 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
hran | +2.149 |
clair | +2.141 |
Ul | +2.130 |
rily | +1.964 |
oute | +1.888 |
Neg logit contributions | |
`` | -2.706 |
HL | -2.649 |
ESV | -2.530 |
subs | -2.529 |
Lange | -2.469 |
Token | 6 |
Token ID | 21 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
hran | +3.563 |
clair | +3.558 |
Ul | +3.526 |
rily | +3.217 |
oute | +3.173 |
Neg logit contributions | |
`` | -4.401 |
HL | -4.343 |
ESV | -4.143 |
subs | -4.100 |
Dise | -4.099 |
Token | { |
Token ID | 1391 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
hran | +6.737 |
Ul | +6.681 |
clair | +6.499 |
Ros | +6.136 |
counters | +6.113 |
Neg logit contributions | |
`` | -8.636 |
HL | -8.492 |
Dise | -8.259 |
ヘ | -8.158 |
ーティ | -8.136 |
Token | ( |
Token ID | 7 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
clair | +0.659 |
hran | +0.656 |
Ul | +0.637 |
rily | +0.609 |
Tanz | +0.592 |
Neg logit contributions | |
`` | -0.702 |
HL | -0.676 |
subs | -0.647 |
ESV | -0.643 |
ousse | -0.624 |
Token | 0 |
Token ID | 15 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
clair | +0.279 |
hran | +0.279 |
Ul | +0.273 |
rily | +0.258 |
Tanz | +0.251 |
Neg logit contributions | |
`` | -0.299 |
HL | -0.289 |
subs | -0.276 |
ESV | -0.275 |
ousse | -0.266 |
Token | s |
Token ID | 82 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
`` | +0.435 |
HL | +0.413 |
subs | +0.397 |
ESV | +0.394 |
ousse | +0.378 |
Neg logit contributions | |
clair | -0.530 |
hran | -0.521 |
Ul | -0.508 |
rily | -0.486 |
Tanz | -0.478 |
Token | )} |
Token ID | 38165 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
clair | +2.822 |
hran | +2.726 |
Ul | +2.681 |
rily | +2.524 |
Ros | +2.301 |
Neg logit contributions | |
`` | -8.588 |
HL | -8.563 |
Dise | -8.456 |
ESV | -8.329 |
subs | -8.325 |
Token | { |
Token ID | 1391 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
hran | +4.230 |
Ul | +4.192 |
clair | +4.112 |
rily | +3.841 |
Ros | +3.714 |
Neg logit contributions | |
`` | -6.366 |
HL | -6.220 |
ESV | -5.877 |
ousse | -5.858 |
subs | -5.855 |
Token | ( |
Token ID | 7 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Ul | +0.840 |
clair | +0.836 |
hran | +0.822 |
rily | +0.754 |
trump | +0.735 |
Neg logit contributions | |
`` | -1.105 |
HL | -1.099 |
ESV | -1.062 |
subs | -1.056 |
Dise | -1.049 |
Token | 5 |
Token ID | 20 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
`` | +1.582 |
HL | +1.517 |
subs | +1.443 |
ESV | +1.441 |
`` | +1.392 |
Neg logit contributions | |
clair | -1.550 |
hran | -1.548 |
Ul | -1.504 |
rily | -1.436 |
Tanz | -1.396 |
Token | s |
Token ID | 82 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
`` | +1.073 |
HL | +1.030 |
subs | +0.993 |
ESV | +0.978 |
`` | +0.940 |
Neg logit contributions | |
clair | -1.403 |
hran | -1.359 |
Ul | -1.329 |
rily | -1.279 |
Tanz | -1.253 |
Token | )} |
Token ID | 38165 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
clair | +2.086 |
Ul | +2.016 |
hran | +2.008 |
rily | +1.843 |
Ros | +1.713 |
Neg logit contributions | |
HL | -5.883 |
`` | -5.834 |
Dise | -5.723 |
ESV | -5.710 |
subs | -5.694 |
Token | Kh |
Token ID | 5311 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
hran | +3.055 |
Ul | +3.033 |
clair | +2.982 |
rily | +2.791 |
Ros | +2.784 |
Neg logit contributions | |
`` | -3.795 |
HL | -3.586 |
ESV | -3.448 |
ousse | -3.447 |
ヘ | -3.423 |
Token | 7 |
Token ID | 22 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
Ul | +6.469 |
hran | +6.247 |
clair | +6.192 |
trump | +5.950 |
oute | +5.633 |
Neg logit contributions | |
HL | -9.458 |
`` | -9.163 |
Lange | -8.999 |
Dise | -8.995 |
ESV | -8.847 |
Token | { |
Token ID | 1391 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
Ul | +2.459 |
hran | +2.424 |
clair | +2.404 |
Ros | +2.222 |
rily | +2.172 |
Neg logit contributions | |
`` | -4.125 |
HL | -4.062 |
subs | -3.903 |
Dise | -3.889 |
ESV | -3.875 |
Token | ( |
Token ID | 7 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Ul | +0.643 |
clair | +0.641 |
hran | +0.630 |
rily | +0.579 |
trump | +0.564 |
Neg logit contributions | |
`` | -0.836 |
HL | -0.829 |
ESV | -0.801 |
subs | -0.798 |
Dise | -0.788 |
Token | 150 |
Token ID | 8628 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
`` | +1.634 |
HL | +1.567 |
subs | +1.487 |
ESV | +1.485 |
`` | +1.436 |
Neg logit contributions | |
clair | -1.658 |
hran | -1.657 |
Ul | -1.608 |
rily | -1.539 |
Tanz | -1.495 |
Token | s |
Token ID | 82 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
`` | +2.652 |
HL | +2.536 |
subs | +2.432 |
ESV | +2.396 |
`` | +2.316 |
Neg logit contributions | |
clair | -3.189 |
hran | -3.180 |
Ul | -3.090 |
rily | -2.970 |
Tanz | -2.917 |
Token | ( |
Token ID | 7 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Ul | +0.865 |
clair | +0.862 |
hran | +0.848 |
rily | +0.777 |
trump | +0.758 |
Neg logit contributions | |
`` | -1.134 |
HL | -1.125 |
ESV | -1.084 |
subs | -1.080 |
Dise | -1.066 |
Token | 9 |
Token ID | 24 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
`` | +2.141 |
HL | +2.047 |
subs | +1.950 |
ESV | +1.944 |
`` | +1.881 |
Neg logit contributions | |
clair | -2.117 |
hran | -2.115 |
Ul | -2.048 |
rily | -1.960 |
Tanz | -1.909 |
Token | 24 |
Token ID | 1731 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
clair | +0.247 |
hran | +0.246 |
Ul | +0.241 |
rily | +0.230 |
Tanz | +0.224 |
Neg logit contributions | |
`` | -0.216 |
HL | -0.207 |
subs | -0.198 |
ESV | -0.197 |
ousse | -0.189 |
Token | s |
Token ID | 82 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
`` | +3.248 |
HL | +3.096 |
subs | +2.981 |
ESV | +2.927 |
`` | +2.824 |
Neg logit contributions | |
clair | -4.080 |
hran | -4.076 |
Ul | -3.947 |
rily | -3.802 |
Tanz | -3.753 |
Token | )} |
Token ID | 38165 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
clair | +2.349 |
Ul | +2.299 |
hran | +2.257 |
rily | +2.055 |
Ros | +1.964 |
Neg logit contributions | |
HL | -7.688 |
senal | -7.589 |
`` | -7.551 |
Dise | -7.531 |
ESV | -7.481 |
Token | h |
Token ID | 289 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
hran | +3.794 |
Ul | +3.779 |
clair | +3.693 |
Ros | +3.515 |
rily | +3.471 |
Neg logit contributions | |
`` | -4.308 |
HL | -4.024 |
ousse | -3.914 |
ヘ | -3.886 |
ESV | -3.877 |
Token | 5 |
Token ID | 20 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Ul | +6.477 |
hran | +6.267 |
clair | +6.016 |
trump | +5.594 |
oute | +5.571 |
Neg logit contributions | |
HL | -9.090 |
`` | -9.003 |
subs | -8.629 |
Dise | -8.599 |
Lange | -8.543 |
Token | { |
Token ID | 1391 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
clair | +1.564 |
hran | +1.554 |
Ul | +1.515 |
rily | +1.433 |
Tanz | +1.388 |
Neg logit contributions | |
`` | -1.879 |
HL | -1.817 |
subs | -1.740 |
ESV | -1.737 |
`` | -1.681 |
Token | ( |
Token ID | 7 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
Ul | +0.880 |
clair | +0.879 |
hran | +0.864 |
rily | +0.792 |
trump | +0.773 |
Neg logit contributions | |
`` | -1.151 |
HL | -1.142 |
ESV | -1.101 |
subs | -1.097 |
Dise | -1.082 |
Token | 13 |
Token ID | 1511 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
`` | +2.517 |
HL | +2.402 |
subs | +2.280 |
ESV | +2.279 |
`` | +2.203 |
Neg logit contributions | |
hran | -2.600 |
clair | -2.599 |
Ul | -2.511 |
rily | -2.414 |
Tanz | -2.347 |
Token | 20 |
Token ID | 1238 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
hran | +1.766 |
clair | +1.755 |
Ul | +1.731 |
rily | +1.631 |
Tanz | +1.584 |
Neg logit contributions | |
`` | -1.882 |
HL | -1.805 |
ESV | -1.725 |
subs | -1.716 |
ousse | -1.676 |
Token | ap |
Token ID | 2471 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
hran | +2.798 |
clair | +2.787 |
Ul | +2.682 |
rily | +2.541 |
oute | +2.470 |
Neg logit contributions | |
`` | -4.661 |
HL | -4.434 |
ESV | -4.354 |
ousse | -4.282 |
ヘ | -4.260 |
Token | = |
Token ID | 796 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
clair | +1.125 |
Ul | +1.107 |
hran | +1.103 |
rily | +1.010 |
trump | +0.963 |
Neg logit contributions | |
`` | -1.902 |
HL | -1.852 |
ESV | -1.807 |
Dise | -1.799 |
subs | -1.796 |
Token | arg |
Token ID | 1822 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
clair | +1.108 |
hran | +1.083 |
Ul | +1.053 |
rily | +1.007 |
Ros | +0.975 |
Neg logit contributions | |
`` | -1.861 |
HL | -1.790 |
ousse | -1.754 |
ESV | -1.744 |
ヘ | -1.731 |
Token | parse |
Token ID | 29572 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
clair | +3.382 |
hran | +3.150 |
Ul | +3.081 |
oute | +2.946 |
trump | +2.936 |
Neg logit contributions | |
HL | -4.449 |
`` | -4.348 |
Dise | -4.301 |
Lange | -4.273 |
ESV | -4.207 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
clair | +0.120 |
hran | +0.119 |
Ul | +0.118 |
rily | +0.109 |
Ros | +0.105 |
Neg logit contributions | |
`` | -0.170 |
HL | -0.165 |
ESV | -0.160 |
subs | -0.159 |
Dise | -0.156 |
Token | Arg |
Token ID | 28100 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
Ul | +1.933 |
clair | +1.914 |
hran | +1.821 |
rily | +1.729 |
trump | +1.675 |
Neg logit contributions | |
HL | -1.970 |
`` | -1.939 |
ESV | -1.918 |
subs | -1.905 |
Dise | -1.889 |
Token | ument |
Token ID | 1713 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
clair | +4.710 |
Ul | +3.994 |
ception | +3.972 |
rily | +3.778 |
hran | +3.745 |
Neg logit contributions | |
Dise | -11.281 |
senal | -10.995 |
HL | -10.711 |
サーティワン | -10.489 |
ーティ | -10.402 |
Token | Parser |
Token ID | 46677 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
clair | +3.506 |
Ul | +3.492 |
hran | +3.378 |
rily | +3.258 |
Ros | +3.234 |
Neg logit contributions | |
HL | -2.021 |
`` | -1.889 |
subs | -1.848 |
ESV | -1.832 |
ousse | -1.816 |
Token | () |
Token ID | 3419 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
Ul | +2.622 |
clair | +2.563 |
hran | +2.463 |
rily | +2.308 |
Ros | +2.308 |
Neg logit contributions | |
HL | -4.722 |
senal | -4.709 |
Dise | -4.709 |
`` | -4.694 |
subs | -4.604 |
Token | ap |
Token ID | 2471 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
clair | +1.595 |
hran | +1.585 |
Ul | +1.533 |
rily | +1.477 |
Ros | +1.429 |
Neg logit contributions | |
`` | -2.816 |
HL | -2.712 |
ESV | -2.675 |
ousse | -2.639 |
ヘ | -2.636 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
`` | +1.449 |
HL | +1.403 |
subs | +1.348 |
ESV | +1.348 |
ousse | +1.306 |
Neg logit contributions | |
clair | -1.131 |
hran | -1.127 |
Ul | -1.105 |
rily | -1.036 |
Tanz | -0.998 |
Token | United |
Token ID | 1578 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
clair | +0.991 |
hran | +0.988 |
Ul | +0.968 |
rily | +0.918 |
Tanz | +0.893 |
Neg logit contributions | |
`` | -1.064 |
HL | -1.022 |
subs | -0.976 |
ESV | -0.975 |
ousse | -0.945 |
Token | Nations |
Token ID | 7973 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
hran | +3.328 |
clair | +3.316 |
Ul | +3.282 |
rily | +3.073 |
Tanz | +3.014 |
Neg logit contributions | |
`` | -4.639 |
HL | -4.464 |
subs | -4.279 |
ESV | -4.255 |
ousse | -4.178 |
Token | Educational |
Token ID | 30038 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
clair | +1.723 |
hran | +1.713 |
Ul | +1.678 |
rily | +1.599 |
Tanz | +1.570 |
Neg logit contributions | |
`` | -1.818 |
HL | -1.732 |
ESV | -1.667 |
subs | -1.644 |
ousse | -1.622 |
Token | , |
Token ID | 11 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
clair | +0.526 |
hran | +0.526 |
Ul | +0.514 |
rily | +0.486 |
Tanz | +0.472 |
Neg logit contributions | |
`` | -0.577 |
HL | -0.556 |
subs | -0.531 |
ESV | -0.531 |
ousse | -0.514 |
Token | Scientific |
Token ID | 22060 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
hran | +4.081 |
clair | +4.037 |
Ul | +4.028 |
Tanz | +3.838 |
Ros | +3.783 |
Neg logit contributions | |
`` | -5.074 |
HL | -4.887 |
ousse | -4.707 |
subs | -4.664 |
ESV | -4.589 |
Token | and |
Token ID | 290 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
hran | +3.206 |
clair | +3.132 |
Ul | +3.078 |
rily | +2.889 |
Tanz | +2.805 |
Neg logit contributions | |
`` | -4.027 |
HL | -3.753 |
subs | -3.656 |
ESV | -3.633 |
Lange | -3.633 |
Token | Cultural |
Token ID | 23897 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Ros | +5.784 |
hran | +5.715 |
Ul | +5.695 |
ception | +5.610 |
Tanz | +5.534 |
Neg logit contributions | |
`` | -9.461 |
光 | -9.000 |
ousse | -8.999 |
wolf | -8.794 |
HL | -8.779 |
Token | Organisation |
Token ID | 30801 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
clair | +1.582 |
hran | +1.576 |
Ul | +1.542 |
rily | +1.431 |
Ros | +1.411 |
Neg logit contributions | |
`` | -2.448 |
HL | -2.327 |
subs | -2.259 |
ESV | -2.247 |
ousse | -2.236 |
Token | ) |
Token ID | 8 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
clair | +0.130 |
hran | +0.129 |
Ul | +0.127 |
rily | +0.119 |
Tanz | +0.115 |
Neg logit contributions | |
`` | -0.158 |
HL | -0.153 |
subs | -0.146 |
ESV | -0.146 |
`` | -0.141 |
Token | designated |
Token ID | 11032 |
Feature activation | +9.19e-02 |
Pos logit contributions | |
hran | +1.440 |
clair | +1.427 |
Ul | +1.395 |
rily | +1.324 |
Tanz | +1.295 |
Neg logit contributions | |
`` | -1.449 |
HL | -1.392 |
ESV | -1.326 |
subs | -1.318 |
ousse | -1.291 |
Token | Lake |
Token ID | 6233 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
hran | +0.692 |
clair | +0.681 |
Ul | +0.671 |
rily | +0.633 |
Tanz | +0.615 |
Neg logit contributions | |
`` | -0.860 |
HL | -0.830 |
ESV | -0.798 |
subs | -0.791 |
ousse | -0.774 |
Token | www |
Token ID | 2503 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
`` | +0.203 |
HL | +0.195 |
subs | +0.187 |
ESV | +0.186 |
ousse | +0.180 |
Neg logit contributions | |
clair | -0.190 |
hran | -0.190 |
Ul | -0.186 |
rily | -0.176 |
Tanz | -0.170 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
clair | +0.547 |
hran | +0.541 |
Ul | +0.534 |
rily | +0.492 |
trump | +0.473 |
Neg logit contributions | |
`` | -0.791 |
HL | -0.772 |
ESV | -0.750 |
subs | -0.748 |
Dise | -0.740 |
Token | eng |
Token ID | 1516 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
clair | +1.906 |
hran | +1.902 |
Ul | +1.857 |
rily | +1.765 |
trump | +1.708 |
Neg logit contributions | |
`` | -1.671 |
HL | -1.619 |
ESV | -1.549 |
subs | -1.547 |
Lange | -1.490 |
Token | in |
Token ID | 259 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
clair | +3.556 |
hran | +3.543 |
Ul | +3.402 |
rily | +3.295 |
oute | +3.102 |
Neg logit contributions | |
`` | -3.857 |
HL | -3.712 |
ESV | -3.594 |
subs | -3.503 |
ヘ | -3.467 |
Token | . |
Token ID | 13 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
clair | +3.026 |
hran | +3.008 |
Ul | +2.898 |
rily | +2.770 |
oute | +2.671 |
Neg logit contributions | |
`` | -3.031 |
HL | -2.920 |
ESV | -2.810 |
subs | -2.788 |
Lange | -2.698 |
Token | um |
Token ID | 388 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
clair | +3.219 |
hran | +3.219 |
Ul | +3.125 |
rily | +3.004 |
trump | +2.915 |
Neg logit contributions | |
`` | -2.693 |
HL | -2.598 |
ESV | -2.505 |
subs | -2.469 |
ヘ | -2.380 |
Token | ich |
Token ID | 488 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
clair | +6.328 |
hran | +6.287 |
rily | +5.550 |
Ul | +5.388 |
ception | +5.208 |
Neg logit contributions | |
`` | -9.789 |
HL | -9.390 |
ESV | -9.283 |
ヘ | -9.116 |
ーティ | -9.033 |
Token | . |
Token ID | 13 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
clair | +4.075 |
hran | +3.945 |
Ul | +3.806 |
rily | +3.632 |
oute | +3.431 |
Neg logit contributions | |
`` | -5.641 |
HL | -5.424 |
subs | -5.243 |
ESV | -5.226 |
ヘ | -5.115 |
Token | edu |
Token ID | 15532 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
clair | +2.385 |
hran | +2.305 |
Ul | +2.272 |
rily | +2.062 |
trump | +1.973 |
Neg logit contributions | |
`` | -5.214 |
HL | -5.055 |
ESV | -4.947 |
subs | -4.905 |
Dise | -4.818 |
Token | /. |
Token ID | 11757 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
hran | +3.883 |
clair | +3.861 |
Ul | +3.755 |
rily | +3.517 |
Ros | +3.463 |
Neg logit contributions | |
`` | -4.293 |
HL | -4.110 |
subs | -3.999 |
ESV | -3.993 |
ousse | -3.922 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
hran | +1.418 |
clair | +1.418 |
Ul | +1.388 |
rily | +1.307 |
Tanz | +1.276 |
Neg logit contributions | |
`` | -1.450 |
HL | -1.388 |
subs | -1.334 |
ESV | -1.333 |
ousse | -1.293 |
Token | ing |
Token ID | 278 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
clair | +1.015 |
hran | +1.010 |
Ul | +1.007 |
rily | +0.938 |
trump | +0.901 |
Neg logit contributions | |
`` | -1.216 |
HL | -1.194 |
ESV | -1.152 |
subs | -1.146 |
Dise | -1.144 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
`` | +3.120 |
HL | +2.993 |
subs | +2.856 |
ESV | +2.845 |
`` | +2.772 |
Neg logit contributions | |
hran | -2.701 |
clair | -2.693 |
Ul | -2.597 |
rily | -2.490 |
Tanz | -2.433 |
Token | Graphics |
Token ID | 18172 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
clair | +1.349 |
hran | +1.345 |
Ul | +1.322 |
rily | +1.243 |
Tanz | +1.197 |
Neg logit contributions | |
`` | -1.645 |
HL | -1.590 |
subs | -1.526 |
ESV | -1.525 |
ousse | -1.479 |
Token | ] |
Token ID | 60 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
`` | +0.260 |
HL | +0.251 |
subs | +0.237 |
ESV | +0.233 |
Lange | +0.223 |
Neg logit contributions | |
clair | -0.379 |
hran | -0.378 |
Ul | -0.370 |
rily | -0.353 |
Tanz | -0.347 |
Token | :: |
Token ID | 3712 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
`` | +1.706 |
HL | +1.651 |
subs | +1.587 |
ESV | +1.583 |
ousse | +1.538 |
Neg logit contributions | |
clair | -1.216 |
hran | -1.214 |
Ul | -1.184 |
rily | -1.110 |
Tanz | -1.072 |
Token | From |
Token ID | 4863 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
hran | +0.082 |
clair | +0.082 |
Ul | +0.080 |
rily | +0.076 |
Tanz | +0.074 |
Neg logit contributions | |
`` | -0.092 |
HL | -0.089 |
subs | -0.085 |
ESV | -0.085 |
ousse | -0.082 |
Token | Image |
Token ID | 5159 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Ul | +5.884 |
clair | +5.411 |
hran | +5.095 |
rily | +4.827 |
atar | +4.577 |
Neg logit contributions | |
Dise | -9.488 |
permitting | -9.320 |
HL | -9.273 |
subs | -9.271 |
`` | -9.264 |
Token | ($ |
Token ID | 16763 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
clair | +2.237 |
hran | +2.222 |
Ul | +2.184 |
rily | +2.036 |
Tanz | +1.942 |
Neg logit contributions | |
`` | -3.887 |
HL | -3.779 |
ESV | -3.669 |
subs | -3.646 |
ousse | -3.565 |
Token | b |
Token ID | 65 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
clair | +1.260 |
hran | +1.214 |
Ul | +1.212 |
rily | +1.123 |
trump | +1.076 |
Neg logit contributions | |
`` | -2.062 |
HL | -2.026 |
ESV | -1.959 |
subs | -1.948 |
Dise | -1.941 |
Token | mp |
Token ID | 3149 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
clair | +2.087 |
hran | +1.839 |
Ul | +1.826 |
rily | +1.781 |
trump | +1.716 |
Neg logit contributions | |
ESV | -4.908 |
Dise | -4.873 |
`` | -4.823 |
HL | -4.797 |
ヘ | -4.742 |
Token | ) |
Token ID | 8 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
`` | +1.183 |
HL | +1.141 |
subs | +1.093 |
ESV | +1.083 |
ousse | +1.055 |
Neg logit contributions | |
hran | -1.063 |
clair | -1.062 |
Ul | -1.033 |
rily | -0.969 |
Tanz | -0.948 |
Token | 132 |
Token ID | 19924 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
`` | +0.981 |
HL | +0.941 |
subs | +0.895 |
ESV | +0.893 |
`` | +0.861 |
Neg logit contributions | |
clair | -1.046 |
hran | -1.045 |
Ul | -1.021 |
rily | -0.973 |
Tanz | -0.946 |
Token | s |
Token ID | 82 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
`` | +1.925 |
HL | +1.842 |
subs | +1.758 |
ESV | +1.745 |
`` | +1.682 |
Neg logit contributions | |
clair | -2.199 |
hran | -2.196 |
Ul | -2.146 |
rily | -2.048 |
Tanz | -2.002 |
Token | )} |
Token ID | 38165 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
clair | +2.017 |
Ul | +1.952 |
hran | +1.917 |
rily | +1.751 |
Ros | +1.651 |
Neg logit contributions | |
HL | -5.731 |
`` | -5.639 |
Dise | -5.547 |
subs | -5.545 |
ESV | -5.544 |
Token | B |
Token ID | 347 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
Ul | +4.117 |
hran | +4.108 |
clair | +3.984 |
Ros | +3.838 |
rily | +3.738 |
Neg logit contributions | |
`` | -5.125 |
HL | -4.775 |
ヘ | -4.675 |
ousse | -4.674 |
ーティ | -4.610 |
Token | d |
Token ID | 67 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
clair | +0.555 |
hran | +0.554 |
Ul | +0.544 |
rily | +0.512 |
Tanz | +0.494 |
Neg logit contributions | |
`` | -0.638 |
HL | -0.617 |
subs | -0.589 |
ESV | -0.588 |
ousse | -0.570 |
Token | 7 |
Token ID | 22 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
hran | +2.598 |
clair | +2.584 |
Ul | +2.558 |
rily | +2.329 |
oute | +2.293 |
Neg logit contributions | |
`` | -3.046 |
HL | -3.013 |
ESV | -2.839 |
subs | -2.820 |
Dise | -2.813 |
Token | { |
Token ID | 1391 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
Ul | +4.471 |
hran | +4.288 |
clair | +4.122 |
Ros | +3.987 |
Tanz | +3.778 |
Neg logit contributions | |
`` | -10.108 |
ーティ | -9.964 |
HL | -9.897 |
Dise | -9.817 |
ヘ | -9.709 |
Token | ( |
Token ID | 7 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Ul | +0.498 |
clair | +0.497 |
hran | +0.489 |
rily | +0.449 |
trump | +0.436 |
Neg logit contributions | |
`` | -0.643 |
HL | -0.637 |
ESV | -0.615 |
subs | -0.612 |
Dise | -0.603 |
Token | 507 |
Token ID | 35378 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
`` | +2.265 |
HL | +2.165 |
ESV | +2.049 |
subs | +2.048 |
`` | +1.978 |
Neg logit contributions | |
hran | -2.445 |
clair | -2.445 |
Ul | -2.365 |
rily | -2.276 |
Tanz | -2.213 |
Token | s |
Token ID | 82 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
`` | +1.025 |
HL | +0.985 |
ESV | +0.936 |
subs | +0.934 |
ousse | +0.903 |
Neg logit contributions | |
clair | -1.107 |
hran | -1.107 |
Ul | -1.088 |
rily | -1.031 |
Tanz | -0.999 |
Token | )} |
Token ID | 38165 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
clair | +2.062 |
Ul | +2.014 |
hran | +1.969 |
rily | +1.796 |
Ros | +1.703 |
Neg logit contributions | |
HL | -6.026 |
`` | -5.951 |
Dise | -5.859 |
ESV | -5.856 |
subs | -5.848 |
Token | < |
Token ID | 27 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
`` | +1.903 |
HL | +1.759 |
subs | +1.676 |
ousse | +1.640 |
ESV | +1.639 |
Neg logit contributions | |
hran | -1.961 |
clair | -1.942 |
Ul | -1.895 |
rily | -1.817 |
Tanz | -1.799 |
Token | body |
Token ID | 2618 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
clair | +2.826 |
hran | +2.810 |
Ul | +2.783 |
rily | +2.566 |
oute | +2.492 |
Neg logit contributions | |
`` | -3.834 |
HL | -3.720 |
ESV | -3.612 |
subs | -3.561 |
Dise | -3.507 |
Token | ng |
Token ID | 23370 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
clair | +0.388 |
hran | +0.385 |
Ul | +0.377 |
rily | +0.356 |
Tanz | +0.344 |
Neg logit contributions | |
`` | -0.453 |
HL | -0.438 |
subs | -0.419 |
ESV | -0.416 |
`` | -0.405 |
Token | - |
Token ID | 12 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
`` | +0.878 |
HL | +0.849 |
subs | +0.815 |
ESV | +0.815 |
ousse | +0.790 |
Neg logit contributions | |
clair | -0.660 |
hran | -0.657 |
Ul | -0.644 |
rily | -0.604 |
Tanz | -0.582 |
Token | controller |
Token ID | 36500 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
clair | +2.507 |
hran | +2.482 |
Ul | +2.436 |
rily | +2.326 |
oute | +2.266 |
Neg logit contributions | |
`` | -2.234 |
HL | -2.174 |
ESV | -2.093 |
subs | -2.058 |
Dise | -2.011 |
Token | =" |
Token ID | 2625 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
clair | +3.720 |
hran | +3.698 |
Ul | +3.641 |
rily | +3.474 |
oute | +3.340 |
Neg logit contributions | |
`` | -4.983 |
HL | -4.853 |
ESV | -4.642 |
subs | -4.609 |
ousse | -4.520 |
Token | Phone |
Token ID | 6132 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Ul | +7.472 |
clair | +7.419 |
hran | +7.165 |
rily | +6.549 |
trump | +6.535 |
Neg logit contributions | |
HL | -7.892 |
ESV | -7.728 |
`` | -7.503 |
Dise | -7.471 |
subs | -7.439 |
Token | List |
Token ID | 8053 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Ul | +2.494 |
clair | +2.480 |
hran | +2.473 |
rily | +2.211 |
oute | +2.156 |
Neg logit contributions | |
`` | -4.721 |
HL | -4.679 |
ESV | -4.534 |
subs | -4.476 |
Dise | -4.431 |
Token | Ctrl |
Token ID | 40069 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
clair | +2.387 |
hran | +2.387 |
Ul | +2.373 |
rily | +2.108 |
oute | +2.023 |
Neg logit contributions | |
`` | -5.006 |
HL | -4.955 |
ESV | -4.821 |
subs | -4.775 |
Dise | -4.711 |
Token | "> |
Token ID | 5320 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
clair | +1.289 |
hran | +1.285 |
Ul | +1.249 |
rily | +1.163 |
Tanz | +1.119 |
Neg logit contributions | |
`` | -2.147 |
HL | -2.090 |
subs | -2.012 |
ESV | -2.012 |
ousse | -1.958 |
Token | < |
Token ID | 1279 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
clair | +0.871 |
hran | +0.867 |
Ul | +0.851 |
rily | +0.816 |
Tanz | +0.796 |
Neg logit contributions | |
`` | -0.611 |
HL | -0.581 |
subs | -0.548 |
ESV | -0.544 |
`` | -0.528 |
Token | ale |
Token ID | 1000 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
`` | +1.900 |
HL | +1.804 |
subs | +1.700 |
ESV | +1.693 |
ousse | +1.632 |
Neg logit contributions | |
hran | -2.790 |
clair | -2.790 |
Ul | -2.744 |
rily | -2.632 |
Tanz | -2.582 |
Token | National |
Token ID | 2351 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
`` | +0.489 |
HL | +0.467 |
subs | +0.444 |
ESV | +0.442 |
ousse | +0.426 |
Neg logit contributions | |
clair | -0.606 |
hran | -0.604 |
Ul | -0.593 |
rily | -0.565 |
Tanz | -0.552 |
Token | Fresh |
Token ID | 20138 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
`` | +2.192 |
HL | +2.135 |
subs | +2.024 |
ESV | +2.022 |
`` | +1.951 |
Neg logit contributions | |
hran | -2.203 |
clair | -2.189 |
Ul | -2.141 |
rily | -2.036 |
Tanz | -1.949 |
Token | man |
Token ID | 805 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
clair | +0.434 |
hran | +0.434 |
Ul | +0.424 |
rily | +0.402 |
Tanz | +0.390 |
Neg logit contributions | |
`` | -0.459 |
HL | -0.443 |
subs | -0.422 |
ESV | -0.421 |
ousse | -0.407 |
Token | of |
Token ID | 286 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
`` | +1.483 |
HL | +1.426 |
subs | +1.354 |
ESV | +1.350 |
`` | +1.310 |
Neg logit contributions | |
hran | -1.522 |
clair | -1.505 |
Ul | -1.478 |
rily | -1.412 |
Tanz | -1.359 |
Token | the |
Token ID | 262 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
Ul | +3.622 |
clair | +3.606 |
Ros | +3.462 |
hran | +3.433 |
rily | +3.195 |
Neg logit contributions | |
`` | -7.492 |
HL | -7.360 |
ESV | -7.336 |
ousse | -7.333 |
ヘ | -7.331 |
Token | Week |
Token ID | 6119 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
Ul | +4.491 |
clair | +4.458 |
hran | +4.405 |
Ros | +4.056 |
rily | +3.854 |
Neg logit contributions | |
`` | -10.465 |
HL | -10.130 |
subs | -10.110 |
ヘ | -10.012 |
ESV | -9.977 |
Token | recogn |
Token ID | 3018 |
Feature activation | -8.21e-02 |
Pos logit contributions | |
`` | +0.514 |
HL | +0.491 |
subs | +0.466 |
ESV | +0.465 |
ousse | +0.447 |
Neg logit contributions | |
clair | -0.645 |
hran | -0.644 |
Ul | -0.632 |
rily | -0.602 |
Tanz | -0.588 |
Token | itions |
Token ID | 1756 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
`` | +0.762 |
HL | +0.735 |
subs | +0.704 |
ESV | +0.701 |
ousse | +0.683 |
Neg logit contributions | |
clair | -0.629 |
hran | -0.623 |
Ul | -0.612 |
rily | -0.577 |
Tanz | -0.560 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
`` | +0.536 |
HL | +0.515 |
subs | +0.490 |
ESV | +0.488 |
ousse | +0.471 |
Neg logit contributions | |
clair | -0.572 |
hran | -0.571 |
Ul | -0.560 |
rily | -0.532 |
Tanz | -0.517 |
Token | 111 |
Token ID | 16243 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
`` | +1.323 |
HL | +1.280 |
subs | +1.207 |
ESV | +1.187 |
Lange | +1.157 |
Neg logit contributions | |
clair | -1.417 |
hran | -1.402 |
Ul | -1.393 |
rily | -1.344 |
Tanz | -1.316 |
Token | Gould |
Token ID | 39292 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
hran | +3.243 |
clair | +3.222 |
Ul | +3.197 |
Tanz | +3.009 |
rily | +2.997 |
Neg logit contributions | |
`` | -3.116 |
HL | -2.932 |
subs | -2.849 |
ESV | -2.822 |
ousse | -2.747 |
Token | , |
Token ID | 11 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
hran | +0.112 |
clair | +0.111 |
Ul | +0.110 |
rily | +0.104 |
Tanz | +0.101 |
Neg logit contributions | |
`` | -0.112 |
HL | -0.109 |
subs | -0.103 |
ESV | -0.103 |
ousse | -0.100 |
Token | J |
Token ID | 449 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
`` | +0.336 |
HL | +0.319 |
subs | +0.309 |
ESV | +0.306 |
ousse | +0.301 |
Neg logit contributions | |
hran | -0.320 |
clair | -0.319 |
Ul | -0.314 |
rily | -0.297 |
Tanz | -0.291 |
Token | . |
Token ID | 13 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
clair | +0.595 |
hran | +0.593 |
Ul | +0.579 |
rily | +0.550 |
Tanz | +0.535 |
Neg logit contributions | |
`` | -0.666 |
HL | -0.643 |
subs | -0.614 |
ESV | -0.612 |
ousse | -0.596 |
Token | ( |
Token ID | 357 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
`` | +0.249 |
HL | +0.238 |
subs | +0.229 |
ESV | +0.227 |
ousse | +0.222 |
Neg logit contributions | |
clair | -0.246 |
hran | -0.246 |
Ul | -0.242 |
rily | -0.228 |
Tanz | -0.223 |
Token | 1981 |
Token ID | 14745 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
hran | +3.392 |
clair | +3.377 |
Ul | +3.356 |
Ros | +3.157 |
rily | +3.105 |
Neg logit contributions | |
`` | -3.391 |
HL | -3.212 |
subs | -3.157 |
ESV | -3.109 |
ousse | -3.072 |
Token | ). |
Token ID | 6739 |
Feature activation | +8.29e-02 |
Pos logit contributions | |
hran | +4.199 |
clair | +4.194 |
Ul | +3.995 |
rily | +3.588 |
Ros | +3.447 |
Neg logit contributions | |
`` | -11.372 |
HL | -10.711 |
ESV | -10.347 |
subs | -10.264 |
ousse | -10.248 |
Token | A |
Token ID | 317 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
clair | +0.689 |
hran | +0.687 |
Ul | +0.675 |
rily | +0.637 |
Tanz | +0.624 |
Neg logit contributions | |
`` | -0.709 |
HL | -0.681 |
subs | -0.652 |
ESV | -0.649 |
ousse | -0.631 |
Token | psych |
Token ID | 3795 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
`` | +1.686 |
HL | +1.621 |
subs | +1.569 |
ESV | +1.528 |
`` | +1.493 |
Neg logit contributions | |
hran | -1.807 |
clair | -1.792 |
Ul | -1.773 |
rily | -1.689 |
Tanz | -1.635 |
Token | ometric |
Token ID | 16996 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
clair | +0.407 |
hran | +0.406 |
Ul | +0.396 |
rily | +0.373 |
Tanz | +0.362 |
Neg logit contributions | |
`` | -0.480 |
HL | -0.463 |
ESV | -0.443 |
subs | -0.443 |
ousse | -0.428 |
Token | investigation |
Token ID | 3645 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
`` | +0.781 |
HL | +0.754 |
subs | +0.727 |
ESV | +0.713 |
`` | +0.695 |
Neg logit contributions | |
clair | -0.793 |
hran | -0.789 |
Ul | -0.772 |
rily | -0.733 |
Tanz | -0.711 |
Token | card |
Token ID | 2657 |
Feature activation | +3.27e-04 |
Pos logit contributions | |
`` | +1.085 |
HL | +1.059 |
subs | +1.028 |
ESV | +1.020 |
`` | +0.995 |
Neg logit contributions | |
clair | -0.554 |
hran | -0.547 |
Ul | -0.534 |
rily | -0.493 |
Tanz | -0.470 |
Token | companies |
Token ID | 2706 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
clair | +0.002 |
hran | +0.002 |
Ul | +0.002 |
rily | +0.002 |
Tanz | +0.002 |
Neg logit contributions | |
`` | -0.003 |
HL | -0.003 |
subs | -0.003 |
ESV | -0.003 |
ousse | -0.003 |
Token | ; |
Token ID | 26 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
clair | +2.419 |
hran | +2.403 |
Ul | +2.347 |
rily | +2.188 |
Tanz | +2.157 |
Neg logit contributions | |
`` | -3.162 |
HL | -3.059 |
ESV | -2.934 |
subs | -2.904 |
ousse | -2.869 |
Token | now |
Token ID | 783 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
clair | +0.374 |
hran | +0.373 |
Ul | +0.365 |
rily | +0.345 |
Tanz | +0.334 |
Neg logit contributions | |
`` | -0.438 |
HL | -0.422 |
subs | -0.403 |
ESV | -0.403 |
ousse | -0.391 |
Token | i |
Token ID | 1312 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
`` | +1.779 |
HL | +1.728 |
subs | +1.652 |
ESV | +1.629 |
`` | +1.571 |
Neg logit contributions | |
hran | -2.102 |
clair | -2.101 |
Ul | -2.067 |
rily | -1.958 |
Tanz | -1.904 |
Token | ... |
Token ID | 986 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
clair | +0.168 |
hran | +0.167 |
Ul | +0.164 |
rily | +0.155 |
Tanz | +0.150 |
Neg logit contributions | |
`` | -0.175 |
HL | -0.169 |
ESV | -0.161 |
subs | -0.160 |
ousse | -0.155 |
Token |
|
Token ID | 198 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
hran | +6.792 |
clair | +6.657 |
Ul | +6.605 |
Ros | +6.026 |
trump | +5.993 |
Neg logit contributions | |
`` | -8.415 |
HL | -7.873 |
subs | -7.669 |
ヘ | -7.571 |
ousse | -7.551 |
Token |
|
Token ID | 198 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
`` | +0.624 |
HL | +0.604 |
ESV | +0.579 |
subs | +0.578 |
ousse | +0.563 |
Neg logit contributions | |
clair | -0.591 |
hran | -0.587 |
Ul | -0.583 |
rily | -0.546 |
Tanz | -0.525 |
Token | Although |
Token ID | 7003 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
clair | +0.475 |
hran | +0.471 |
Ul | +0.466 |
rily | +0.439 |
Tanz | +0.425 |
Neg logit contributions | |
`` | -0.444 |
HL | -0.429 |
subs | -0.409 |
ESV | -0.408 |
ousse | -0.394 |
Token | this |
Token ID | 428 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
clair | +0.354 |
hran | +0.353 |
Ul | +0.345 |
rily | +0.327 |
Tanz | +0.318 |
Neg logit contributions | |
`` | -0.385 |
HL | -0.368 |
ESV | -0.353 |
subs | -0.352 |
ousse | -0.342 |
Token | one |
Token ID | 530 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
hran | +1.029 |
clair | +1.028 |
Ul | +1.006 |
rily | +0.948 |
Tanz | +0.925 |
Neg logit contributions | |
`` | -1.210 |
HL | -1.157 |
ESV | -1.112 |
subs | -1.107 |
ousse | -1.086 |
Token | liberal |
Token ID | 7270 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
hran | +0.958 |
clair | +0.958 |
Ul | +0.935 |
rily | +0.888 |
Tanz | +0.863 |
Neg logit contributions | |
`` | -1.010 |
HL | -0.972 |
ESV | -0.928 |
subs | -0.926 |
ousse | -0.899 |
Token | international |
Token ID | 3230 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
clair | +1.793 |
hran | +1.782 |
Ul | +1.751 |
rily | +1.662 |
Tanz | +1.625 |
Neg logit contributions | |
`` | -1.895 |
HL | -1.815 |
ESV | -1.736 |
subs | -1.733 |
ousse | -1.682 |
Token | ist |
Token ID | 396 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
clair | +0.857 |
hran | +0.854 |
Ul | +0.842 |
rily | +0.799 |
Tanz | +0.784 |
Neg logit contributions | |
`` | -0.688 |
HL | -0.658 |
ESV | -0.623 |
subs | -0.622 |
ousse | -0.601 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
clair | +0.625 |
hran | +0.623 |
Ul | +0.610 |
rily | +0.579 |
Tanz | +0.563 |
Neg logit contributions | |
`` | -0.659 |
HL | -0.634 |
subs | -0.605 |
ESV | -0.605 |
ousse | -0.585 |
Token | scratching |
Token ID | 34688 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
clair | +1.465 |
hran | +1.461 |
Ul | +1.432 |
rily | +1.363 |
Tanz | +1.325 |
Neg logit contributions | |
`` | -1.436 |
HL | -1.381 |
ESV | -1.312 |
subs | -1.305 |
ousse | -1.278 |
Token | his |
Token ID | 465 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
`` | +2.787 |
HL | +2.726 |
subs | +2.678 |
ESV | +2.585 |
`` | +2.562 |
Neg logit contributions | |
clair | -2.606 |
hran | -2.534 |
Ul | -2.512 |
rily | -2.314 |
ridor | -2.253 |
Token | head |
Token ID | 1182 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
`` | +7.172 |
subs | +7.046 |
HL | +6.791 |
`` | +6.530 |
mine | +6.172 |
Neg logit contributions | |
clair | -11.159 |
hran | -10.821 |
Ul | -10.748 |
ridor | -10.275 |
rily | -10.255 |
Token | as |
Token ID | 355 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
`` | +0.296 |
HL | +0.286 |
subs | +0.274 |
ESV | +0.272 |
`` | +0.265 |
Neg logit contributions | |
clair | -0.267 |
hran | -0.267 |
Ul | -0.262 |
rily | -0.244 |
Tanz | -0.239 |
Token | he |
Token ID | 339 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
`` | +2.721 |
HL | +2.674 |
subs | +2.564 |
ESV | +2.504 |
`` | +2.476 |
Neg logit contributions | |
clair | -2.741 |
hran | -2.707 |
Ul | -2.636 |
rily | -2.473 |
Tanz | -2.429 |
Token | conferences |
Token ID | 19993 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
clair | +1.355 |
hran | +1.355 |
Ul | +1.313 |
rily | +1.265 |
Tanz | +1.210 |
Neg logit contributions | |
`` | -1.468 |
HL | -1.408 |
ESV | -1.340 |
subs | -1.317 |
ousse | -1.301 |
Token | with |
Token ID | 351 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
`` | +1.504 |
HL | +1.471 |
subs | +1.409 |
ESV | +1.397 |
`` | +1.353 |
Neg logit contributions | |
clair | -1.501 |
hran | -1.474 |
Ul | -1.449 |
rily | -1.363 |
Tanz | -1.327 |
Token | Bi |
Token ID | 8436 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
hran | +0.717 |
clair | +0.717 |
Ul | +0.703 |
rily | +0.661 |
Tanz | +0.645 |
Neg logit contributions | |
`` | -0.798 |
HL | -0.766 |
ESV | -0.734 |
subs | -0.734 |
ousse | -0.714 |
Token | ographies |
Token ID | 41480 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
`` | +2.524 |
HL | +2.397 |
subs | +2.220 |
ESV | +2.218 |
ousse | +2.171 |
Neg logit contributions | |
clair | -3.946 |
hran | -3.937 |
Ul | -3.843 |
rily | -3.738 |
Tanz | -3.685 |
Token | – |
Token ID | 1906 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
clair | +0.507 |
hran | +0.507 |
Ul | +0.495 |
rily | +0.467 |
Tanz | +0.455 |
Neg logit contributions | |
`` | -0.562 |
HL | -0.541 |
subs | -0.518 |
ESV | -0.517 |
ousse | -0.502 |
Token | Charles |
Token ID | 28711 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
`` | +2.521 |
HL | +2.401 |
subs | +2.287 |
ESV | +2.277 |
`` | +2.212 |
Neg logit contributions | |
hran | -2.500 |
clair | -2.494 |
Ul | -2.401 |
rily | -2.338 |
Tanz | -2.255 |
Token | E |
Token ID | 412 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
`` | +6.125 |
HL | +6.118 |
ESV | +5.876 |
`` | +5.715 |
subs | +5.644 |
Neg logit contributions | |
clair | -7.126 |
hran | -7.123 |
Ul | -6.930 |
rily | -6.688 |
trump | -6.405 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
`` | +5.619 |
HL | +5.412 |
ESV | +5.143 |
subs | +5.117 |
`` | +5.099 |
Neg logit contributions | |
clair | -6.274 |
Ul | -6.217 |
hran | -6.167 |
rily | -5.885 |
Tanz | -5.853 |
Token | ( |
Token ID | 357 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
`` | +3.988 |
HL | +3.473 |
ESV | +3.429 |
`` | +3.413 |
subs | +3.105 |
Neg logit contributions | |
clair | -13.463 |
hran | -13.246 |
Ul | -12.971 |
rily | -12.589 |
oute | -12.388 |
Token | Chuck |
Token ID | 44324 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
`` | +0.723 |
HL | +0.698 |
subs | +0.665 |
ESV | +0.663 |
ousse | +0.641 |
Neg logit contributions | |
clair | -0.724 |
hran | -0.722 |
Ul | -0.709 |
rily | -0.671 |
Tanz | -0.652 |
Token | ) |
Token ID | 8 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
`` | +5.964 |
HL | +5.646 |
ESV | +5.435 |
subs | +5.397 |
`` | +5.352 |
Neg logit contributions | |
clair | -8.522 |
hran | -8.217 |
Ul | -8.216 |
rily | -7.713 |
trump | -7.530 |
Token | Ye |
Token ID | 11609 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
`` | +4.893 |
HL | +4.645 |
ESV | +4.431 |
`` | +4.352 |
subs | +4.225 |
Neg logit contributions | |
clair | -9.391 |
hran | -9.292 |
Ul | -9.060 |
rily | -8.802 |
oute | -8.560 |
Token | ager |
Token ID | 3536 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
clair | +0.443 |
hran | +0.437 |
Ul | +0.425 |
rily | +0.399 |
atar | +0.384 |
Neg logit contributions | |
`` | -0.692 |
HL | -0.679 |
subs | -0.651 |
ESV | -0.650 |
Dise | -0.638 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
`` | +0.360 |
HL | +0.347 |
subs | +0.328 |
ESV | +0.327 |
`` | +0.317 |
Neg logit contributions | |
clair | -0.391 |
hran | -0.389 |
Ul | -0.381 |
rily | -0.365 |
Tanz | -0.353 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
`` | +1.147 |
HL | +1.107 |
subs | +1.058 |
ESV | +1.057 |
ousse | +1.025 |
Neg logit contributions | |
clair | -1.135 |
hran | -1.130 |
Ul | -1.115 |
rily | -1.051 |
Tanz | -1.018 |
Token | � |
Token ID | 447 |
Feature activation | -3.62e-03 |
Pos logit contributions | |
`` | +0.860 |
HL | +0.818 |
subs | +0.777 |
ESV | +0.775 |
ousse | +0.748 |
Neg logit contributions | |
hran | -0.953 |
clair | -0.951 |
Ul | -0.924 |
rily | -0.889 |
Tanz | -0.866 |
Token | � |
Token ID | 250 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
`` | +0.023 |
HL | +0.022 |
subs | +0.020 |
ESV | +0.020 |
ousse | +0.019 |
Neg logit contributions | |
hran | -0.038 |
clair | -0.038 |
Ul | -0.038 |
rily | -0.036 |
Tanz | -0.035 |
Token | General |
Token ID | 12218 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
`` | +2.668 |
HL | +2.512 |
ESV | +2.373 |
subs | +2.372 |
`` | +2.302 |
Neg logit contributions | |
hran | -3.029 |
clair | -3.004 |
Ul | -2.899 |
rily | -2.844 |
Tanz | -2.766 |
Token | Chuck |
Token ID | 14663 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
`` | +4.172 |
HL | +4.106 |
ESV | +3.822 |
subs | +3.811 |
`` | +3.756 |
Neg logit contributions | |
hran | -5.543 |
clair | -5.533 |
Ul | -5.395 |
rily | -5.172 |
Tanz | -4.960 |
Token | Ye |
Token ID | 11609 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
`` | +3.120 |
HL | +2.839 |
ESV | +2.758 |
`` | +2.696 |
Lange | +2.503 |
Neg logit contributions | |
clair | -13.803 |
hran | -13.337 |
Ul | -13.326 |
rily | -12.951 |
trump | -12.526 |
Token | ager |
Token ID | 3536 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
clair | +0.637 |
hran | +0.628 |
Ul | +0.611 |
rily | +0.573 |
atar | +0.552 |
Neg logit contributions | |
`` | -1.010 |
HL | -0.991 |
subs | -0.951 |
ESV | -0.949 |
Dise | -0.933 |
Token | Interview |
Token ID | 19371 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
`` | +2.257 |
HL | +2.200 |
subs | +2.069 |
ESV | +2.059 |
`` | +2.021 |
Neg logit contributions | |
clair | -2.195 |
hran | -2.180 |
Ul | -2.143 |
rily | -2.044 |
Tanz | -1.963 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
`` | +1.089 |
HL | +1.055 |
subs | +1.002 |
ESV | +0.997 |
`` | +0.966 |
Neg logit contributions | |
clair | -1.071 |
hran | -1.067 |
Ul | -1.045 |
rily | -0.991 |
Tanz | -0.958 |
Token | � |
Token ID | 447 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
clair | +0.104 |
hran | +0.104 |
Ul | +0.102 |
rily | +0.096 |
Tanz | +0.094 |
Neg logit contributions | |
`` | -0.096 |
HL | -0.093 |
subs | -0.088 |
ESV | -0.088 |
ousse | -0.085 |
Token | functions |
Token ID | 5499 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
hran | +1.601 |
Ul | +1.585 |
clair | +1.559 |
rily | +1.481 |
Ros | +1.470 |
Neg logit contributions | |
`` | -1.813 |
HL | -1.750 |
ESV | -1.708 |
Dise | -1.676 |
ヘ | -1.664 |
Token | using |
Token ID | 1262 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
clair | +0.751 |
hran | +0.739 |
Ul | +0.731 |
rily | +0.686 |
Ros | +0.667 |
Neg logit contributions | |
`` | -1.115 |
HL | -1.089 |
ESV | -1.043 |
Dise | -1.043 |
ヘ | -1.029 |
Token | the |
Token ID | 262 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
clair | +0.105 |
hran | +0.104 |
Ul | +0.103 |
rily | +0.096 |
Tanz | +0.092 |
Neg logit contributions | |
`` | -0.151 |
HL | -0.146 |
ESV | -0.141 |
subs | -0.140 |
ousse | -0.138 |
Token | archived |
Token ID | 33962 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
`` | +4.389 |
HL | +4.363 |
subs | +4.210 |
ESV | +4.162 |
`` | +4.033 |
Neg logit contributions | |
hran | -2.994 |
clair | -2.965 |
Ul | -2.865 |
rily | -2.624 |
Tanz | -2.557 |
Token | file |
Token ID | 2393 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
`` | +2.162 |
HL | +2.095 |
subs | +2.018 |
ESV | +2.014 |
ousse | +1.961 |
Neg logit contributions | |
clair | -1.329 |
hran | -1.325 |
Ul | -1.289 |
rily | -1.202 |
Tanz | -1.156 |
Token | from |
Token ID | 422 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
`` | +0.902 |
HL | +0.867 |
ESV | +0.834 |
subs | +0.830 |
ousse | +0.813 |
Neg logit contributions | |
clair | -0.715 |
hran | -0.713 |
Ul | -0.700 |
rily | -0.659 |
Tanz | -0.635 |
Token | S |
Token ID | 311 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
HL | +6.660 |
`` | +6.448 |
subs | +6.340 |
ESV | +5.736 |
`` | +5.689 |
Neg logit contributions | |
hran | -11.107 |
clair | -10.740 |
Ul | -10.388 |
rily | -9.717 |
trump | -9.705 |
Token | 3 |
Token ID | 18 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
`` | +0.218 |
HL | +0.212 |
ESV | +0.204 |
subs | +0.203 |
Dise | +0.199 |
Neg logit contributions | |
clair | -0.189 |
hran | -0.185 |
Ul | -0.185 |
rily | -0.172 |
trump | -0.165 |
Token | bucket |
Token ID | 19236 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
HL | +1.454 |
`` | +1.429 |
subs | +1.137 |
`` | +0.847 |
ESV | +0.806 |
Neg logit contributions | |
hran | -11.986 |
clair | -11.858 |
Ul | -11.636 |
rily | -11.243 |
Tanz | -11.054 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
`` | +1.940 |
HL | +1.871 |
subs | +1.792 |
ESV | +1.786 |
`` | +1.732 |
Neg logit contributions | |
clair | -1.600 |
hran | -1.598 |
Ul | -1.557 |
rily | -1.472 |
Tanz | -1.428 |
Token | It |
Token ID | 632 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
`` | +0.125 |
HL | +0.119 |
subs | +0.116 |
ESV | +0.115 |
ousse | +0.112 |
Neg logit contributions | |
clair | -0.150 |
hran | -0.150 |
Ul | -0.149 |
rily | -0.140 |
Ros | -0.138 |
Token | � |
Token ID | 250 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
hran | +2.540 |
clair | +2.532 |
Ul | +2.497 |
rily | +2.315 |
Tanz | +2.270 |
Neg logit contributions | |
`` | -2.688 |
HL | -2.590 |
subs | -2.484 |
ESV | -2.465 |
ousse | -2.420 |
Token | B |
Token ID | 33 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
clair | +0.679 |
hran | +0.677 |
Ul | +0.668 |
rily | +0.625 |
Tanz | +0.611 |
Neg logit contributions | |
`` | -0.655 |
HL | -0.632 |
subs | -0.606 |
ESV | -0.602 |
ousse | -0.583 |
Token | rig |
Token ID | 4359 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
clair | +0.243 |
hran | +0.243 |
Ul | +0.237 |
rily | +0.224 |
Tanz | +0.217 |
Neg logit contributions | |
`` | -0.287 |
HL | -0.276 |
subs | -0.265 |
ESV | -0.264 |
ousse | -0.256 |
Token | adier |
Token ID | 38868 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
`` | +1.285 |
HL | +1.251 |
ESV | +1.198 |
subs | +1.192 |
ousse | +1.164 |
Neg logit contributions | |
clair | -0.942 |
hran | -0.939 |
Ul | -0.927 |
rily | -0.871 |
Tanz | -0.841 |
Token | General |
Token ID | 3611 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
`` | +4.014 |
HL | +3.938 |
subs | +3.636 |
ESV | +3.624 |
`` | +3.574 |
Neg logit contributions | |
clair | -4.669 |
hran | -4.643 |
Ul | -4.505 |
rily | -4.351 |
Tanz | -4.152 |
Token | Chuck |
Token ID | 14663 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
`` | +3.605 |
HL | +3.553 |
subs | +3.325 |
ESV | +3.313 |
`` | +3.273 |
Neg logit contributions | |
clair | -3.419 |
hran | -3.392 |
Ul | -3.302 |
rily | -3.174 |
oute | -3.009 |
Token | Ye |
Token ID | 11609 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
`` | +5.233 |
HL | +5.105 |
Lange | +4.776 |
ESV | +4.750 |
`` | +4.735 |
Neg logit contributions | |
clair | -11.047 |
hran | -10.742 |
Ul | -10.665 |
rily | -10.373 |
oute | -9.934 |
Token | ager |
Token ID | 3536 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
`` | +0.904 |
HL | +0.876 |
subs | +0.841 |
ESV | +0.840 |
Lange | +0.815 |
Neg logit contributions | |
clair | -0.642 |
hran | -0.640 |
Ul | -0.622 |
rily | -0.585 |
Tanz | -0.562 |
Token | : |
Token ID | 25 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
`` | +2.344 |
HL | +2.276 |
ESV | +2.146 |
subs | +2.144 |
`` | +2.093 |
Neg logit contributions | |
clair | -2.262 |
hran | -2.257 |
Ul | -2.217 |
rily | -2.121 |
Tanz | -2.028 |
Token | Official |
Token ID | 15934 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
`` | +1.610 |
HL | +1.555 |
ESV | +1.470 |
subs | +1.463 |
`` | +1.439 |
Neg logit contributions | |
clair | -1.619 |
hran | -1.618 |
Ul | -1.573 |
rily | -1.506 |
oute | -1.444 |
Token | Bi |
Token ID | 8436 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
`` | +0.744 |
HL | +0.718 |
subs | +0.682 |
ESV | +0.682 |
`` | +0.660 |
Neg logit contributions | |
clair | -0.725 |
hran | -0.724 |
Ul | -0.708 |
rily | -0.672 |
Tanz | -0.649 |
Token | was |
Token ID | 373 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
clair | +1.711 |
hran | +1.685 |
Ul | +1.661 |
rily | +1.543 |
Tanz | +1.505 |
Neg logit contributions | |
`` | -2.339 |
HL | -2.237 |
ESV | -2.161 |
subs | -2.131 |
ousse | -2.117 |
Token | announced |
Token ID | 3414 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
hran | +2.027 |
clair | +1.995 |
Ul | +1.958 |
rily | +1.845 |
Ros | +1.775 |
Neg logit contributions | |
`` | -2.302 |
HL | -2.214 |
ESV | -2.129 |
subs | -2.099 |
ousse | -2.082 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
`` | +2.012 |
HL | +1.944 |
subs | +1.860 |
ESV | +1.839 |
`` | +1.801 |
Neg logit contributions | |
clair | -1.872 |
hran | -1.868 |
Ul | -1.829 |
rily | -1.733 |
Tanz | -1.677 |
Token |
|
Token ID | 198 |
Feature activation | -2.46e-03 |
Pos logit contributions | |
clair | +1.047 |
hran | +1.047 |
Ul | +1.028 |
rily | +0.973 |
Tanz | +0.946 |
Neg logit contributions | |
`` | -1.030 |
HL | -0.989 |
subs | -0.946 |
ESV | -0.942 |
ousse | -0.912 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
`` | +0.021 |
HL | +0.021 |
ESV | +0.020 |
subs | +0.020 |
Dise | +0.020 |
Neg logit contributions | |
clair | -0.020 |
Ul | -0.019 |
hran | -0.019 |
rily | -0.018 |
Ros | -0.017 |
Token | G |
Token ID | 38 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Ul | +1.397 |
clair | +1.396 |
hran | +1.389 |
rily | +1.294 |
oute | +1.252 |
Neg logit contributions | |
`` | -1.307 |
HL | -1.275 |
subs | -1.222 |
ESV | -1.219 |
Dise | -1.179 |
Token | at |
Token ID | 265 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
`` | +5.946 |
ousse | +5.833 |
etus | +5.529 |
HL | +5.338 |
subs | +5.093 |
Neg logit contributions | |
clair | -9.629 |
Ul | -9.569 |
hran | -9.433 |
rily | -9.189 |
Ambro | -9.118 |
Token | ens |
Token ID | 641 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
`` | +2.959 |
HL | +2.851 |
subs | +2.736 |
ESV | +2.698 |
ousse | +2.641 |
Neg logit contributions | |
hran | -2.751 |
clair | -2.743 |
Ul | -2.703 |
rily | -2.544 |
Tanz | -2.525 |
Token | said |
Token ID | 531 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
`` | +1.224 |
HL | +1.178 |
subs | +1.125 |
ESV | +1.118 |
`` | +1.084 |
Neg logit contributions | |
hran | -1.189 |
clair | -1.188 |
Ul | -1.164 |
rily | -1.105 |
Tanz | -1.072 |
Token | NASA |
Token ID | 8884 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
hran | +0.467 |
clair | +0.466 |
Ul | +0.459 |
rily | +0.432 |
Tanz | +0.418 |
Neg logit contributions | |
`` | -0.549 |
HL | -0.526 |
ESV | -0.504 |
subs | -0.504 |
ousse | -0.491 |
Token | was |
Token ID | 373 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
clair | +1.635 |
hran | +1.634 |
Ul | +1.601 |
rily | +1.489 |
Tanz | +1.459 |
Neg logit contributions | |
`` | -1.967 |
HL | -1.888 |
ESV | -1.821 |
subs | -1.809 |
ousse | -1.786 |
Token | : |
Token ID | 25 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
`` | +1.904 |
HL | +1.818 |
subs | +1.748 |
ESV | +1.732 |
`` | +1.715 |
Neg logit contributions | |
hran | -1.768 |
clair | -1.746 |
Ul | -1.707 |
rily | -1.611 |
Tanz | -1.576 |
Token | " |
Token ID | 366 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
`` | +1.805 |
HL | +1.740 |
subs | +1.672 |
ESV | +1.652 |
`` | +1.625 |
Neg logit contributions | |
hran | -1.650 |
clair | -1.646 |
Ul | -1.604 |
rily | -1.514 |
Tanz | -1.468 |
Token | I |
Token ID | 40 |
Feature activation | -2.94e-03 |
Pos logit contributions | |
`` | +1.655 |
HL | +1.551 |
subs | +1.474 |
ESV | +1.462 |
`` | +1.413 |
Neg logit contributions | |
hran | -2.034 |
clair | -2.015 |
Ul | -1.945 |
rily | -1.894 |
Tanz | -1.863 |
Token | 'm |
Token ID | 1101 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
`` | +0.027 |
HL | +0.026 |
ESV | +0.025 |
subs | +0.024 |
ousse | +0.024 |
Neg logit contributions | |
clair | -0.023 |
hran | -0.023 |
Ul | -0.022 |
rily | -0.021 |
Tanz | -0.020 |
Token | licking |
Token ID | 43390 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
hran | +2.061 |
clair | +2.047 |
Ul | +2.007 |
rily | +1.914 |
Tanz | +1.844 |
Neg logit contributions | |
`` | -2.265 |
HL | -2.179 |
ESV | -2.096 |
ousse | -2.059 |
subs | -2.057 |
Token | my |
Token ID | 616 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
`` | +0.399 |
HL | +0.385 |
subs | +0.370 |
ESV | +0.366 |
`` | +0.356 |
Neg logit contributions | |
clair | -0.363 |
hran | -0.362 |
Ul | -0.355 |
rily | -0.334 |
Tanz | -0.324 |
Token | chops |
Token ID | 44512 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
`` | +6.671 |
HL | +6.453 |
subs | +6.343 |
`` | +6.001 |
ESV | +5.740 |
Neg logit contributions | |
hran | -9.951 |
clair | -9.892 |
Ul | -9.821 |
ridor | -9.155 |
rily | -9.118 |
Token | ." |
Token ID | 526 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
`` | +1.669 |
HL | +1.595 |
subs | +1.540 |
ESV | +1.514 |
`` | +1.487 |
Neg logit contributions | |
hran | -1.556 |
clair | -1.550 |
Ul | -1.525 |
rily | -1.428 |
Tanz | -1.391 |
Token |
|
Token ID | 198 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
clair | +1.325 |
hran | +1.320 |
Ul | +1.304 |
rily | +1.228 |
Tanz | +1.207 |
Neg logit contributions | |
`` | -1.352 |
HL | -1.300 |
subs | -1.255 |
ESV | -1.243 |
ousse | -1.218 |
Token |
|
Token ID | 198 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
`` | +3.091 |
HL | +2.933 |
subs | +2.776 |
ESV | +2.760 |
`` | +2.709 |
Neg logit contributions | |
hran | -3.517 |
clair | -3.499 |
Ul | -3.388 |
rily | -3.269 |
Tanz | -3.212 |
Token | Must |
Token ID | 34320 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
clair | +1.388 |
Ul | +1.376 |
hran | +1.375 |
rily | +1.283 |
Tanz | +1.239 |
Neg logit contributions | |
`` | -1.307 |
HL | -1.284 |
ESV | -1.222 |
subs | -1.221 |
Lange | -1.179 |
Token | with |
Token ID | 351 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
clair | +0.706 |
hran | +0.703 |
Ul | +0.686 |
rily | +0.648 |
Tanz | +0.633 |
Neg logit contributions | |
`` | -0.800 |
HL | -0.768 |
ESV | -0.736 |
subs | -0.733 |
ousse | -0.714 |
Token | Mike |
Token ID | 4995 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
hran | +0.047 |
clair | +0.047 |
Ul | +0.046 |
rily | +0.043 |
Tanz | +0.042 |
Neg logit contributions | |
`` | -0.051 |
HL | -0.050 |
subs | -0.048 |
ESV | -0.047 |
Lange | -0.046 |
Token | Bloom |
Token ID | 11891 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
clair | +0.374 |
hran | +0.374 |
Ul | +0.366 |
rily | +0.347 |
Tanz | +0.337 |
Neg logit contributions | |
`` | -0.383 |
HL | -0.369 |
subs | -0.352 |
ESV | -0.351 |
ousse | -0.339 |
Token | (@ |
Token ID | 4275 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
clair | +0.403 |
hran | +0.402 |
Ul | +0.393 |
rily | +0.372 |
Tanz | +0.362 |
Neg logit contributions | |
`` | -0.424 |
HL | -0.408 |
subs | -0.390 |
ESV | -0.389 |
ousse | -0.376 |
Token | AM |
Token ID | 2390 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
`` | +5.066 |
HL | +4.698 |
subs | +4.578 |
ESV | +4.476 |
mining | +4.438 |
Neg logit contributions | |
hran | -4.949 |
clair | -4.812 |
Tanz | -4.720 |
Ul | -4.696 |
rily | -4.549 |
Token | ike |
Token ID | 522 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
`` | +2.505 |
HL | +2.393 |
subs | +2.288 |
ESV | +2.273 |
ousse | +2.231 |
Neg logit contributions | |
hran | -2.680 |
clair | -2.660 |
Ul | -2.608 |
rily | -2.483 |
Tanz | -2.455 |
Token | Bloom |
Token ID | 38941 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
`` | +5.150 |
HL | +4.679 |
wolf | +4.361 |
subs | +4.329 |
ousse | +4.086 |
Neg logit contributions | |
Tanz | -10.501 |
hran | -10.493 |
Ul | -10.227 |
clair | -10.130 |
rily | -10.116 |
Token | Type |
Token ID | 6030 |
Feature activation | +4.60e-03 |
Pos logit contributions | |
clair | +0.266 |
hran | +0.265 |
Ul | +0.259 |
rily | +0.244 |
Tanz | +0.236 |
Neg logit contributions | |
`` | -0.323 |
HL | -0.312 |
subs | -0.299 |
ESV | -0.299 |
ousse | -0.290 |
Token | ) |
Token ID | 8 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
clair | +0.034 |
hran | +0.034 |
Ul | +0.033 |
rily | +0.031 |
Tanz | +0.030 |
Neg logit contributions | |
`` | -0.044 |
HL | -0.042 |
subs | -0.040 |
ESV | -0.040 |
ousse | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
`` | +0.697 |
HL | +0.673 |
subs | +0.642 |
ESV | +0.638 |
Lange | +0.618 |
Neg logit contributions | |
hran | -0.719 |
clair | -0.717 |
Ul | -0.701 |
rily | -0.668 |
Tanz | -0.647 |
Token | a |
Token ID | 257 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
clair | +0.214 |
hran | +0.214 |
Ul | +0.209 |
rily | +0.198 |
Tanz | +0.193 |
Neg logit contributions | |
`` | -0.232 |
HL | -0.223 |
subs | -0.213 |
ESV | -0.213 |
ousse | -0.206 |
Token | National |
Token ID | 2351 |
Feature activation | -8.72e-03 |
Pos logit contributions | |
`` | +2.154 |
HL | +2.110 |
subs | +2.008 |
ESV | +1.990 |
`` | +1.927 |
Neg logit contributions | |
hran | -2.250 |
clair | -2.249 |
Ul | -2.189 |
rily | -2.085 |
oute | -2.021 |
Token | Sample |
Token ID | 27565 |
Feature activation | -6.34e-02 |
Pos logit contributions | |
`` | +0.078 |
HL | +0.075 |
subs | +0.072 |
ESV | +0.071 |
ousse | +0.069 |
Neg logit contributions | |
clair | -0.070 |
hran | -0.070 |
Ul | -0.068 |
rily | -0.064 |
Tanz | -0.063 |
Token | Survey |
Token ID | 13084 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
`` | +0.488 |
HL | +0.469 |
subs | +0.446 |
ESV | +0.442 |
`` | +0.426 |
Neg logit contributions | |
clair | -0.585 |
hran | -0.585 |
Ul | -0.571 |
rily | -0.546 |
Tanz | -0.529 |
Token | Organisation |
Token ID | 30801 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
`` | +0.650 |
HL | +0.627 |
subs | +0.600 |
ESV | +0.595 |
`` | +0.576 |
Neg logit contributions | |
clair | -0.623 |
hran | -0.622 |
Ul | -0.608 |
rily | -0.577 |
Tanz | -0.557 |
Token | ( |
Token ID | 357 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
`` | +0.504 |
HL | +0.486 |
subs | +0.465 |
ESV | +0.461 |
`` | +0.447 |
Neg logit contributions | |
clair | -0.495 |
hran | -0.493 |
Ul | -0.484 |
rily | -0.460 |
Tanz | -0.444 |
Token | N |
Token ID | 45 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
`` | +4.993 |
HL | +4.609 |
subs | +4.476 |
ESV | +4.268 |
`` | +4.191 |
Neg logit contributions | |
hran | -5.801 |
clair | -5.683 |
Ul | -5.567 |
rily | -5.362 |
Tanz | -5.198 |
Token | SS |
Token ID | 5432 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
`` | +4.161 |
subs | +4.011 |
HL | +3.672 |
ousse | +3.501 |
sample | +3.337 |
Neg logit contributions | |
hran | -11.993 |
Ul | -11.605 |
clair | -11.550 |
Ambro | -11.313 |
oute | -11.008 |
Token | O |
Token ID | 46 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
`` | +1.570 |
HL | +1.520 |
subs | +1.470 |
ESV | +1.457 |
ousse | +1.419 |
Neg logit contributions | |
hran | -1.127 |
clair | -1.123 |
Ul | -1.081 |
rily | -1.028 |
Tanz | -0.993 |
Token | ) |
Token ID | 8 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
hran | +2.285 |
clair | +2.280 |
Ul | +2.195 |
rily | +2.054 |
Tanz | +1.990 |
Neg logit contributions | |
`` | -3.594 |
HL | -3.466 |
ESV | -3.334 |
subs | -3.329 |
Lange | -3.275 |
Token | for |
Token ID | 329 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
clair | +0.092 |
hran | +0.092 |
Ul | +0.090 |
rily | +0.085 |
Tanz | +0.083 |
Neg logit contributions | |
`` | -0.095 |
HL | -0.091 |
subs | -0.087 |
ESV | -0.087 |
ousse | -0.084 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
clair | +0.599 |
hran | +0.598 |
Ul | +0.587 |
rily | +0.558 |
Tanz | +0.545 |
Neg logit contributions | |
`` | -0.615 |
HL | -0.588 |
ESV | -0.563 |
subs | -0.559 |
ousse | -0.547 |
Token | we |
Token ID | 356 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
`` | +1.515 |
HL | +1.465 |
subs | +1.406 |
ESV | +1.394 |
Lange | +1.349 |
Neg logit contributions | |
hran | -1.456 |
clair | -1.450 |
Ul | -1.411 |
rily | -1.347 |
Tanz | -1.296 |
Token | must |
Token ID | 1276 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
`` | +0.322 |
HL | +0.309 |
subs | +0.295 |
ESV | +0.293 |
ousse | +0.284 |
Neg logit contributions | |
clair | -0.337 |
hran | -0.337 |
Ul | -0.330 |
rily | -0.314 |
Tanz | -0.305 |
Token | place |
Token ID | 1295 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
`` | +1.025 |
HL | +0.983 |
subs | +0.957 |
ESV | +0.935 |
`` | +0.917 |
Neg logit contributions | |
hran | -0.971 |
clair | -0.966 |
Ul | -0.952 |
rily | -0.890 |
Tanz | -0.873 |
Token | it |
Token ID | 340 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
`` | +2.685 |
HL | +2.593 |
subs | +2.528 |
ESV | +2.442 |
`` | +2.412 |
Neg logit contributions | |
clair | -2.982 |
hran | -2.973 |
Ul | -2.910 |
rily | -2.757 |
Tanz | -2.682 |
Token | front |
Token ID | 2166 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
`` | +0.128 |
HL | +0.123 |
subs | +0.118 |
ESV | +0.117 |
`` | +0.113 |
Neg logit contributions | |
clair | -0.137 |
hran | -0.137 |
Ul | -0.134 |
rily | -0.127 |
Tanz | -0.124 |
Token | and |
Token ID | 290 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
`` | +1.198 |
HL | +1.155 |
subs | +1.109 |
ESV | +1.090 |
`` | +1.064 |
Neg logit contributions | |
clair | -1.385 |
hran | -1.364 |
Ul | -1.325 |
rily | -1.266 |
oute | -1.235 |
Token | center |
Token ID | 3641 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
`` | +4.573 |
subs | +4.562 |
HL | +4.550 |
`` | +4.365 |
mine | +4.041 |
Neg logit contributions | |
hran | -11.176 |
clair | -11.174 |
Ul | -10.817 |
rily | -10.521 |
Tanz | -10.426 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
`` | +1.250 |
HL | +1.206 |
subs | +1.158 |
ESV | +1.144 |
`` | +1.115 |
Neg logit contributions | |
hran | -1.152 |
clair | -1.152 |
Ul | -1.125 |
rily | -1.060 |
Tanz | -1.034 |
Token | Dec |
Token ID | 4280 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
`` | +1.066 |
HL | +1.026 |
ESV | +0.973 |
subs | +0.967 |
`` | +0.944 |
Neg logit contributions | |
hran | -1.127 |
clair | -1.125 |
Ul | -1.092 |
rily | -1.046 |
oute | -1.010 |
Token | ades |
Token ID | 2367 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
clair | +3.062 |
hran | +3.046 |
Ul | +3.002 |
rily | +2.894 |
Tanz | +2.830 |
Neg logit contributions | |
`` | -1.807 |
HL | -1.711 |
subs | -1.600 |
ESV | -1.596 |
`` | -1.535 |
Token | ago |
Token ID | 2084 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
hran | +0.314 |
clair | +0.314 |
Ul | +0.307 |
rily | +0.291 |
Tanz | +0.282 |
Neg logit contributions | |
`` | -0.339 |
HL | -0.326 |
subs | -0.312 |
ESV | -0.311 |
ousse | -0.301 |
Token | , |
Token ID | 11 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
`` | +1.340 |
HL | +1.301 |
subs | +1.253 |
ESV | +1.231 |
Lange | +1.209 |
Neg logit contributions | |
clair | -1.097 |
hran | -1.088 |
Ul | -1.060 |
rily | -0.998 |
oute | -0.958 |
Token | Soviet |
Token ID | 7570 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
`` | +1.793 |
HL | +1.739 |
subs | +1.669 |
ESV | +1.640 |
`` | +1.610 |
Neg logit contributions | |
clair | -1.630 |
hran | -1.617 |
Ul | -1.580 |
rily | -1.483 |
oute | -1.433 |
Token | People |
Token ID | 4380 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
clair | +2.174 |
hran | +2.169 |
Ul | +2.132 |
rily | +2.045 |
Tanz | +2.019 |
Neg logit contributions | |
`` | -2.258 |
HL | -2.150 |
ESV | -2.057 |
ousse | -2.045 |
subs | -2.000 |
Token | 's |
Token ID | 338 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
clair | +1.327 |
hran | +1.326 |
Ul | +1.296 |
rily | +1.224 |
Tanz | +1.188 |
Neg logit contributions | |
`` | -1.525 |
HL | -1.474 |
ESV | -1.407 |
subs | -1.406 |
ousse | -1.365 |
Token | Comm |
Token ID | 1520 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
clair | +0.984 |
hran | +0.982 |
Ul | +0.967 |
rily | +0.923 |
Tanz | +0.905 |
Neg logit contributions | |
`` | -0.761 |
HL | -0.726 |
ESV | -0.687 |
subs | -0.685 |
ousse | -0.665 |
Token | iss |
Token ID | 747 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
clair | +0.506 |
hran | +0.504 |
Ul | +0.495 |
rily | +0.471 |
Tanz | +0.457 |
Neg logit contributions | |
`` | -0.464 |
HL | -0.445 |
subs | -0.424 |
ESV | -0.422 |
ousse | -0.407 |
Token | ar |
Token ID | 283 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
`` | +7.481 |
HL | +7.247 |
subs | +6.868 |
ousse | +6.739 |
`` | +6.732 |
Neg logit contributions | |
Ul | -7.693 |
hran | -7.673 |
clair | -7.669 |
rily | -7.569 |
trump | -7.296 |
Token | of |
Token ID | 286 |
Feature activation | +3.30e-03 |
Pos logit contributions | |
`` | +1.216 |
HL | +1.187 |
subs | +1.131 |
ESV | +1.117 |
Lange | +1.089 |
Neg logit contributions | |
clair | -1.152 |
hran | -1.145 |
Ul | -1.118 |
rily | -1.063 |
Tanz | -1.022 |
Token | Defense |
Token ID | 5947 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
clair | +0.027 |
hran | +0.027 |
Ul | +0.026 |
rily | +0.025 |
Tanz | +0.024 |
Neg logit contributions | |
`` | -0.029 |
HL | -0.028 |
subs | -0.027 |
ESV | -0.027 |
ousse | -0.026 |
Token | S |
Token ID | 311 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
`` | +0.413 |
HL | +0.399 |
subs | +0.381 |
ESV | +0.380 |
`` | +0.367 |
Neg logit contributions | |
clair | -0.378 |
hran | -0.377 |
Ul | -0.368 |
rily | -0.349 |
Tanz | -0.338 |
Token | emy |
Token ID | 3065 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
clair | +0.764 |
hran | +0.762 |
Ul | +0.744 |
rily | +0.702 |
Tanz | +0.677 |
Neg logit contributions | |
`` | -0.960 |
HL | -0.927 |
subs | -0.888 |
ESV | -0.887 |
ousse | -0.858 |
Token | business |
Token ID | 1597 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
`` | +2.032 |
HL | +1.976 |
subs | +1.895 |
ESV | +1.888 |
`` | +1.829 |
Neg logit contributions | |
clair | -1.837 |
hran | -1.826 |
Ul | -1.771 |
rily | -1.687 |
Tanz | -1.624 |
Token | of |
Token ID | 286 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
`` | +1.495 |
HL | +1.443 |
subs | +1.391 |
ESV | +1.366 |
`` | +1.333 |
Neg logit contributions | |
clair | -1.726 |
hran | -1.719 |
Ul | -1.685 |
rily | -1.605 |
Tanz | -1.565 |
Token | ignoring |
Token ID | 15482 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
`` | +1.386 |
HL | +1.334 |
subs | +1.279 |
ESV | +1.245 |
`` | +1.208 |
Neg logit contributions | |
hran | -2.015 |
clair | -2.014 |
Ul | -1.989 |
rily | -1.873 |
Tanz | -1.833 |
Token | what |
Token ID | 644 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
`` | +2.697 |
HL | +2.630 |
subs | +2.528 |
ESV | +2.518 |
`` | +2.423 |
Neg logit contributions | |
hran | -2.617 |
clair | -2.603 |
Ul | -2.554 |
rily | -2.439 |
Tanz | -2.348 |
Token | The |
Token ID | 383 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
`` | +2.809 |
HL | +2.716 |
ESV | +2.611 |
subs | +2.597 |
`` | +2.500 |
Neg logit contributions | |
clair | -2.982 |
hran | -2.973 |
Ul | -2.891 |
rily | -2.799 |
Tanz | -2.714 |
Token | Lord |
Token ID | 4453 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
`` | +1.901 |
HL | +1.835 |
ESV | +1.804 |
subs | +1.745 |
`` | +1.687 |
Neg logit contributions | |
clair | -2.067 |
hran | -2.036 |
Ul | -1.979 |
rily | -1.891 |
Tanz | -1.867 |
Token | commands |
Token ID | 9729 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
`` | +7.206 |
HL | +6.792 |
subs | +6.782 |
ESV | +6.542 |
`` | +6.380 |
Neg logit contributions | |
clair | -8.690 |
hran | -8.516 |
Ul | -8.209 |
rily | -8.064 |
ridor | -7.895 |
Token | of |
Token ID | 286 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
`` | +3.426 |
HL | +3.347 |
subs | +3.207 |
ESV | +3.201 |
`` | +3.049 |
Neg logit contributions | |
clair | -3.841 |
hran | -3.821 |
Ul | -3.737 |
rily | -3.550 |
Tanz | -3.478 |
Token | me |
Token ID | 502 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
`` | +2.843 |
HL | +2.775 |
ESV | +2.674 |
subs | +2.663 |
`` | +2.540 |
Neg logit contributions | |
clair | -2.907 |
hran | -2.874 |
Ul | -2.828 |
rily | -2.662 |
Tanz | -2.611 |
Token | , |
Token ID | 11 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
`` | +2.572 |
HL | +2.473 |
subs | +2.371 |
ESV | +2.357 |
`` | +2.271 |
Neg logit contributions | |
clair | -2.724 |
hran | -2.711 |
Ul | -2.672 |
rily | -2.532 |
Tanz | -2.461 |
Token | especially |
Token ID | 2592 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
`` | +2.110 |
HL | +2.022 |
subs | +1.922 |
ESV | +1.914 |
`` | +1.855 |
Neg logit contributions | |
hran | -2.416 |
clair | -2.398 |
Ul | -2.362 |
rily | -2.247 |
Tanz | -2.178 |
Token | with |
Token ID | 351 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
`` | +3.887 |
HL | +3.737 |
subs | +3.595 |
`` | +3.519 |
ESV | +3.465 |
Neg logit contributions | |
hran | -4.160 |
clair | -4.155 |
Ul | -4.060 |
rily | -3.805 |
Tanz | -3.754 |
Token | the |
Token ID | 262 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
`` | +2.755 |
HL | +2.652 |
subs | +2.557 |
`` | +2.513 |
ESV | +2.499 |
Neg logit contributions | |
hran | -2.907 |
clair | -2.885 |
Ul | -2.824 |
rily | -2.667 |
Tanz | -2.608 |
Token | ' |
Token ID | 705 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
`` | +3.751 |
HL | +3.630 |
subs | +3.496 |
`` | +3.439 |
ESV | +3.387 |
Neg logit contributions | |
hran | -4.147 |
clair | -4.147 |
Ul | -4.029 |
rily | -3.830 |
Tanz | -3.737 |
Token | model |
Token ID | 19849 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
clair | +0.195 |
hran | +0.195 |
Ul | +0.190 |
rily | +0.179 |
Tanz | +0.174 |
Neg logit contributions | |
`` | -0.235 |
HL | -0.227 |
subs | -0.218 |
ESV | -0.217 |
ousse | -0.210 |
Token | ines |
Token ID | 1127 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
`` | +2.444 |
HL | +2.298 |
subs | +2.188 |
ESV | +2.163 |
ousse | +2.101 |
Neg logit contributions | |
hran | -2.871 |
clair | -2.851 |
Ul | -2.783 |
rily | -2.667 |
Tanz | -2.628 |
Token | ' |
Token ID | 6 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
`` | +0.543 |
HL | +0.522 |
subs | +0.501 |
ESV | +0.499 |
ousse | +0.485 |
Neg logit contributions | |
clair | -0.441 |
hran | -0.441 |
Ul | -0.430 |
rily | -0.406 |
Tanz | -0.394 |
Token | option |
Token ID | 3038 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
`` | +7.158 |
HL | +6.573 |
subs | +6.524 |
`` | +6.309 |
ESV | +5.997 |
Neg logit contributions | |
hran | -8.895 |
clair | -8.689 |
Ul | -8.560 |
Tanz | -8.187 |
rily | -8.130 |
Token | . |
Token ID | 13 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
`` | +4.090 |
HL | +3.928 |
subs | +3.770 |
`` | +3.714 |
ESV | +3.669 |
Neg logit contributions | |
hran | -4.020 |
clair | -3.923 |
Ul | -3.911 |
rily | -3.648 |
Tanz | -3.588 |
Token | If |
Token ID | 1002 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
`` | +3.355 |
HL | +3.235 |
subs | +3.079 |
ESV | +3.044 |
`` | +3.011 |
Neg logit contributions | |
clair | -3.944 |
hran | -3.929 |
Ul | -3.850 |
rily | -3.655 |
ridor | -3.552 |
Token | ' |
Token ID | 705 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
`` | +2.682 |
HL | +2.595 |
subs | +2.499 |
ESV | +2.444 |
`` | +2.433 |
Neg logit contributions | |
hran | -2.735 |
clair | -2.724 |
Ul | -2.677 |
rily | -2.539 |
Tanz | -2.468 |
Token | mod |
Token ID | 4666 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
clair | +0.535 |
hran | +0.533 |
Ul | +0.521 |
rily | +0.491 |
Tanz | +0.475 |
Neg logit contributions | |
`` | -0.651 |
HL | -0.629 |
subs | -0.602 |
ESV | -0.601 |
ousse | -0.583 |
Token | — |
Token ID | 851 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
clair | +3.363 |
Ul | +3.287 |
hran | +3.252 |
rily | +3.001 |
Tanz | +2.968 |
Neg logit contributions | |
`` | -3.796 |
HL | -3.603 |
ESV | -3.522 |
subs | -3.444 |
ousse | -3.408 |
Token | Cody |
Token ID | 27035 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
clair | +0.460 |
hran | +0.459 |
Ul | +0.449 |
rily | +0.425 |
Tanz | +0.415 |
Neg logit contributions | |
`` | -0.495 |
HL | -0.474 |
subs | -0.455 |
ESV | -0.453 |
ousse | -0.440 |
Token | Wester |
Token ID | 32104 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
`` | +1.461 |
HL | +1.431 |
subs | +1.354 |
ESV | +1.350 |
Lange | +1.333 |
Neg logit contributions | |
clair | -1.363 |
hran | -1.351 |
Ul | -1.326 |
rily | -1.259 |
oute | -1.199 |
Token | lund |
Token ID | 37525 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
clair | +0.052 |
hran | +0.052 |
Ul | +0.050 |
rily | +0.048 |
Tanz | +0.046 |
Neg logit contributions | |
`` | -0.057 |
HL | -0.054 |
subs | -0.052 |
ESV | -0.052 |
ousse | -0.050 |
Token | (@ |
Token ID | 4275 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
`` | +1.607 |
HL | +1.573 |
ESV | +1.493 |
subs | +1.489 |
Lange | +1.446 |
Neg logit contributions | |
hran | -1.452 |
clair | -1.444 |
Ul | -1.416 |
rily | -1.344 |
Tanz | -1.294 |
Token | C |
Token ID | 34 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
`` | +4.433 |
HL | +4.052 |
subs | +3.810 |
wolf | +3.781 |
ESV | +3.767 |
Neg logit contributions | |
hran | -5.707 |
Ul | -5.518 |
clair | -5.481 |
Tanz | -5.385 |
rily | -5.277 |
Token | ody |
Token ID | 1118 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
`` | +8.504 |
HL | +7.720 |
ousse | +7.640 |
XX | +7.627 |
wolf | +7.608 |
Neg logit contributions | |
hran | -6.762 |
Ul | -6.511 |
clair | -6.490 |
Tanz | -6.414 |
Ambro | -6.098 |
Token | W |
Token ID | 54 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
`` | +6.043 |
wolf | +5.349 |
subs | +5.335 |
ESV | +5.334 |
HL | +5.282 |
Neg logit contributions | |
hran | -8.031 |
clair | -7.764 |
Tanz | -7.546 |
Ul | -7.495 |
rily | -7.325 |
Token | ester |
Token ID | 7834 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
`` | +2.675 |
HL | +2.465 |
ESV | +2.398 |
subs | +2.388 |
ousse | +2.348 |
Neg logit contributions | |
hran | -3.735 |
clair | -3.727 |
Ul | -3.672 |
Tanz | -3.536 |
rily | -3.495 |
Token | lund |
Token ID | 37525 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
`` | +0.464 |
HL | +0.444 |
subs | +0.422 |
ESV | +0.420 |
ousse | +0.405 |
Neg logit contributions | |
clair | -0.558 |
hran | -0.556 |
Ul | -0.546 |
rily | -0.519 |
Tanz | -0.505 |
Token | ) |
Token ID | 8 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
clair | +0.561 |
hran | +0.559 |
Ul | +0.546 |
rily | +0.515 |
Tanz | +0.499 |
Neg logit contributions | |
`` | -0.677 |
HL | -0.652 |
subs | -0.626 |
ESV | -0.624 |
ousse | -0.605 |
Token | is |
Token ID | 318 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
`` | +0.102 |
HL | +0.098 |
subs | +0.094 |
ESV | +0.094 |
ousse | +0.091 |
Neg logit contributions | |
clair | -0.099 |
hran | -0.099 |
Ul | -0.096 |
rily | -0.091 |
Tanz | -0.089 |
Token | being |
Token ID | 852 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
`` | +1.518 |
HL | +1.473 |
subs | +1.404 |
ESV | +1.386 |
`` | +1.354 |
Neg logit contributions | |
clair | -1.506 |
hran | -1.497 |
Ul | -1.464 |
rily | -1.394 |
Tanz | -1.356 |
Token | made |
Token ID | 925 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
hran | +2.303 |
clair | +2.269 |
Ul | +2.248 |
rily | +2.131 |
Tanz | +2.068 |
Neg logit contributions | |
`` | -2.302 |
HL | -2.173 |
ESV | -2.090 |
ousse | -2.061 |
subs | -2.059 |
Token | for |
Token ID | 329 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
clair | +0.948 |
hran | +0.947 |
Ul | +0.929 |
rily | +0.882 |
Tanz | +0.851 |
Neg logit contributions | |
`` | -1.082 |
HL | -1.042 |
ESV | -0.997 |
subs | -0.992 |
ousse | -0.973 |
Token | the |
Token ID | 262 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
clair | +0.133 |
hran | +0.133 |
Ul | +0.130 |
rily | +0.124 |
Tanz | +0.120 |
Neg logit contributions | |
`` | -0.145 |
HL | -0.140 |
subs | -0.134 |
ESV | -0.133 |
ousse | -0.129 |
Token | right |
Token ID | 826 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
`` | +1.821 |
HL | +1.767 |
subs | +1.686 |
ESV | +1.675 |
`` | +1.625 |
Neg logit contributions | |
hran | -1.849 |
clair | -1.845 |
Ul | -1.798 |
rily | -1.700 |
Tanz | -1.651 |
Token | reasons |
Token ID | 3840 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
HL | +5.506 |
`` | +5.486 |
subs | +5.315 |
`` | +4.969 |
ESV | +4.949 |
Neg logit contributions | |
clair | -10.148 |
hran | -9.981 |
Ul | -9.596 |
Tanz | -9.142 |
rily | -9.136 |
Token | ." |
Token ID | 526 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
clair | +0.591 |
hran | +0.589 |
Ul | +0.576 |
rily | +0.543 |
Tanz | +0.525 |
Neg logit contributions | |
`` | -0.742 |
HL | -0.717 |
ESV | -0.687 |
subs | -0.687 |
ousse | -0.668 |
Token | The |
Token ID | 464 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
clair | +0.223 |
hran | +0.223 |
Ul | +0.218 |
rily | +0.208 |
Tanz | +0.202 |
Neg logit contributions | |
`` | -0.203 |
HL | -0.195 |
subs | -0.186 |
ESV | -0.185 |
ousse | -0.179 |
Token | trade |
Token ID | 3292 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
clair | +0.584 |
hran | +0.582 |
Ul | +0.572 |
rily | +0.546 |
Tanz | +0.535 |
Neg logit contributions | |
`` | -0.424 |
HL | -0.404 |
subs | -0.382 |
ESV | -0.381 |
ousse | -0.367 |
Token | closes |
Token ID | 20612 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
hran | +2.910 |
clair | +2.907 |
Ul | +2.876 |
rily | +2.674 |
Tanz | +2.632 |
Neg logit contributions | |
`` | -3.329 |
HL | -3.174 |
ESV | -3.098 |
ousse | -3.026 |
subs | -2.998 |
Token | Kel |
Token ID | 15150 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
hran | +2.530 |
clair | +2.514 |
Ul | +2.512 |
rily | +2.357 |
Ros | +2.288 |
Neg logit contributions | |
`` | -3.132 |
HL | -2.993 |
subs | -2.889 |
ESV | -2.871 |
ousse | -2.850 |
Token | sey |
Token ID | 4397 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
`` | +1.485 |
HL | +1.432 |
subs | +1.364 |
ESV | +1.362 |
ousse | +1.315 |
Neg logit contributions | |
clair | -1.495 |
hran | -1.487 |
Ul | -1.456 |
rily | -1.384 |
Tanz | -1.339 |
Token | Gram |
Token ID | 20159 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
hran | +0.990 |
clair | +0.983 |
Ul | +0.973 |
rily | +0.905 |
Ros | +0.889 |
Neg logit contributions | |
`` | -1.317 |
HL | -1.272 |
subs | -1.233 |
ESV | -1.230 |
ousse | -1.215 |
Token | mer |
Token ID | 647 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
clair | +1.799 |
hran | +1.762 |
Ul | +1.743 |
rily | +1.677 |
trump | +1.644 |
Neg logit contributions | |
`` | -0.875 |
HL | -0.837 |
ESV | -0.794 |
subs | -0.779 |
Dise | -0.774 |
Token |
|
Token ID | 198 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
`` | +3.613 |
HL | +3.479 |
subs | +3.275 |
ESV | +3.264 |
`` | +3.188 |
Neg logit contributions | |
hran | -4.203 |
clair | -4.190 |
Ul | -4.073 |
rily | -3.931 |
Tanz | -3.815 |
Token |
|
Token ID | 198 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
`` | +2.752 |
HL | +2.618 |
subs | +2.483 |
ESV | +2.460 |
`` | +2.415 |
Neg logit contributions | |
hran | -3.158 |
clair | -3.143 |
Ul | -3.044 |
rily | -2.931 |
Tanz | -2.886 |
Token | 2002 |
Token ID | 16942 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
`` | +6.125 |
HL | +4.898 |
ESV | +4.778 |
`` | +4.759 |
subs | +4.685 |
Neg logit contributions | |
hran | -10.217 |
Tanz | -9.690 |
clair | -9.535 |
rily | -9.520 |
rall | -9.323 |
Token | Matt |
Token ID | 4705 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
clair | +0.520 |
hran | +0.519 |
Ul | +0.507 |
rily | +0.481 |
Tanz | +0.467 |
Neg logit contributions | |
`` | -0.552 |
HL | -0.532 |
subs | -0.508 |
ESV | -0.506 |
ousse | -0.489 |
Token | Le |
Token ID | 1004 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
`` | +0.464 |
HL | +0.448 |
subs | +0.429 |
ESV | +0.427 |
Lange | +0.416 |
Neg logit contributions | |
clair | -0.406 |
hran | -0.405 |
Ul | -0.396 |
rily | -0.375 |
Tanz | -0.362 |
Token | Bl |
Token ID | 3629 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
`` | +2.251 |
HL | +2.152 |
subs | +2.064 |
ESV | +2.024 |
ousse | +2.008 |
Neg logit contributions | |
hran | -2.340 |
clair | -2.320 |
Ul | -2.291 |
rily | -2.202 |
Tanz | -2.126 |
Token | anc |
Token ID | 1192 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
`` | +0.512 |
HL | +0.492 |
subs | +0.472 |
ESV | +0.470 |
ousse | +0.467 |
Neg logit contributions | |
clair | -0.399 |
hran | -0.398 |
Ul | -0.391 |
rily | -0.367 |
Tanz | -0.357 |
Token | to |
Token ID | 284 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
hran | +0.543 |
clair | +0.543 |
Ul | +0.531 |
rily | +0.504 |
Tanz | +0.488 |
Neg logit contributions | |
`` | -0.576 |
HL | -0.553 |
ESV | -0.528 |
subs | -0.527 |
ousse | -0.511 |
Token | be |
Token ID | 307 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
`` | +0.417 |
HL | +0.400 |
subs | +0.382 |
ESV | +0.379 |
`` | +0.366 |
Neg logit contributions | |
clair | -0.482 |
hran | -0.482 |
Ul | -0.473 |
rily | -0.449 |
Tanz | -0.438 |
Token | made |
Token ID | 925 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
hran | +0.690 |
clair | +0.688 |
Ul | +0.675 |
rily | +0.642 |
Tanz | +0.627 |
Neg logit contributions | |
`` | -0.662 |
HL | -0.632 |
ESV | -0.603 |
subs | -0.599 |
ousse | -0.586 |
Token | for |
Token ID | 329 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
clair | +0.443 |
hran | +0.442 |
Ul | +0.433 |
rily | +0.410 |
Tanz | +0.398 |
Neg logit contributions | |
`` | -0.487 |
HL | -0.470 |
ESV | -0.450 |
subs | -0.448 |
ousse | -0.436 |
Token | the |
Token ID | 262 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
`` | +1.092 |
HL | +1.060 |
subs | +1.009 |
ESV | +1.004 |
`` | +0.974 |
Neg logit contributions | |
clair | -1.061 |
hran | -1.059 |
Ul | -1.036 |
rily | -0.977 |
Tanz | -0.952 |
Token | right |
Token ID | 826 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
`` | +1.850 |
HL | +1.794 |
subs | +1.715 |
ESV | +1.705 |
`` | +1.649 |
Neg logit contributions | |
hran | -1.854 |
clair | -1.849 |
Ul | -1.805 |
rily | -1.709 |
Tanz | -1.655 |
Token | reasons |
Token ID | 3840 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
`` | +3.875 |
HL | +3.820 |
subs | +3.776 |
ESV | +3.412 |
`` | +3.375 |
Neg logit contributions | |
clair | -11.530 |
hran | -11.320 |
Ul | -11.072 |
rily | -10.527 |
oute | -10.496 |
Token | . |
Token ID | 13 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
clair | +0.620 |
hran | +0.618 |
Ul | +0.604 |
rily | +0.567 |
Tanz | +0.549 |
Neg logit contributions | |
`` | -0.818 |
HL | -0.792 |
ESV | -0.760 |
subs | -0.759 |
ousse | -0.739 |
Token | There |
Token ID | 1318 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
clair | +0.746 |
hran | +0.740 |
Ul | +0.735 |
rily | +0.690 |
Tanz | +0.678 |
Neg logit contributions | |
`` | -0.684 |
HL | -0.660 |
subs | -0.640 |
ESV | -0.630 |
ousse | -0.615 |
Token | could |
Token ID | 714 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
clair | +2.390 |
hran | +2.384 |
Ul | +2.307 |
rily | +2.136 |
Ros | +2.064 |
Neg logit contributions | |
`` | -3.136 |
HL | -3.059 |
ESV | -2.962 |
subs | -2.916 |
Dise | -2.894 |
Token | be |
Token ID | 307 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
`` | +1.411 |
HL | +1.351 |
subs | +1.299 |
ESV | +1.276 |
`` | +1.228 |
Neg logit contributions | |
hran | -1.843 |
clair | -1.834 |
Ul | -1.804 |
rily | -1.719 |
Tanz | -1.688 |
Token | / |
Token ID | 14 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
HL | +5.942 |
`` | +5.641 |
subs | +5.496 |
ESV | +5.337 |
ousse | +5.102 |
Neg logit contributions | |
clair | -9.006 |
hran | -8.922 |
Ul | -8.858 |
rily | -8.492 |
ridor | -8.256 |
Token | s |
Token ID | 82 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
`` | +1.591 |
HL | +1.533 |
subs | +1.451 |
ESV | +1.428 |
ousse | +1.389 |
Neg logit contributions | |
hran | -1.956 |
clair | -1.952 |
Ul | -1.914 |
rily | -1.826 |
Tanz | -1.799 |
Token | 109 |
Token ID | 16003 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
`` | +2.649 |
HL | +2.604 |
ESV | +2.446 |
subs | +2.441 |
`` | +2.345 |
Neg logit contributions | |
hran | -2.882 |
clair | -2.876 |
Ul | -2.798 |
rily | -2.666 |
Tanz | -2.574 |
Token | . |
Token ID | 13 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
`` | +1.555 |
HL | +1.515 |
ESV | +1.417 |
subs | +1.410 |
`` | +1.348 |
Neg logit contributions | |
clair | -2.059 |
hran | -2.050 |
Ul | -2.011 |
rily | -1.923 |
Tanz | -1.865 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
`` | +4.197 |
HL | +3.994 |
ESV | +3.755 |
subs | +3.693 |
`` | +3.620 |
Neg logit contributions | |
hran | -4.688 |
clair | -4.677 |
Ul | -4.420 |
rily | -4.350 |
oute | -4.226 |
Token | GT |
Token ID | 7963 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
HL | +3.706 |
`` | +3.634 |
ESV | +3.358 |
subs | +3.290 |
`` | +3.124 |
Neg logit contributions | |
clair | -5.763 |
hran | -5.706 |
Ul | -5.592 |
rily | -5.385 |
ridor | -5.224 |
Token | / |
Token ID | 14 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
HL | +6.121 |
`` | +6.043 |
subs | +5.523 |
ESV | +5.519 |
`` | +5.323 |
Neg logit contributions | |
clair | -9.066 |
hran | -8.999 |
Ul | -8.786 |
rily | -8.588 |
Tanz | -8.467 |
Token | s |
Token ID | 82 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
`` | +2.257 |
HL | +2.163 |
subs | +2.059 |
ESV | +2.045 |
ousse | +1.978 |
Neg logit contributions | |
hran | -2.574 |
clair | -2.572 |
Ul | -2.518 |
rily | -2.399 |
Tanz | -2.349 |
Token | 120 |
Token ID | 7982 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
`` | +3.086 |
HL | +3.059 |
ESV | +2.848 |
subs | +2.814 |
`` | +2.726 |
Neg logit contributions | |
clair | -3.946 |
hran | -3.936 |
Ul | -3.810 |
rily | -3.661 |
oute | -3.535 |
Token | . |
Token ID | 13 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
HL | +4.250 |
`` | +4.222 |
ESV | +3.997 |
subs | +3.948 |
Lange | +3.782 |
Neg logit contributions | |
clair | -4.646 |
hran | -4.620 |
Ul | -4.540 |
rily | -4.307 |
trump | -4.141 |
Token | 5 |
Token ID | 20 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
`` | +3.080 |
HL | +2.961 |
ESV | +2.799 |
subs | +2.773 |
`` | +2.690 |
Neg logit contributions | |
clair | -3.273 |
hran | -3.269 |
Ul | -3.120 |
rily | -3.035 |
oute | -2.929 |
Token | wing |
Token ID | 5469 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
`` | +3.337 |
HL | +3.142 |
subs | +2.979 |
ESV | +2.951 |
ousse | +2.909 |
Neg logit contributions | |
hran | -3.684 |
clair | -3.499 |
Ul | -3.418 |
rily | -3.353 |
Tanz | -3.317 |
Token | populist |
Token ID | 26815 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
clair | +1.403 |
hran | +1.395 |
Ul | +1.377 |
rily | +1.304 |
Tanz | +1.277 |
Neg logit contributions | |
`` | -1.436 |
HL | -1.373 |
ESV | -1.311 |
subs | -1.309 |
ousse | -1.277 |
Token | Alternative |
Token ID | 27182 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
clair | +0.647 |
hran | +0.645 |
Ul | +0.635 |
rily | +0.602 |
Tanz | +0.589 |
Neg logit contributions | |
`` | -0.619 |
HL | -0.594 |
subs | -0.566 |
ESV | -0.565 |
ousse | -0.547 |
Token | for |
Token ID | 329 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
`` | +2.403 |
HL | +2.289 |
subs | +2.245 |
ESV | +2.178 |
`` | +2.123 |
Neg logit contributions | |
clair | -2.557 |
hran | -2.503 |
Ul | -2.422 |
rily | -2.333 |
trump | -2.234 |
Token | Germany |
Token ID | 4486 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
`` | +0.628 |
HL | +0.600 |
subs | +0.562 |
ESV | +0.557 |
ousse | +0.520 |
Neg logit contributions | |
clair | -1.378 |
hran | -1.371 |
Ul | -1.328 |
rily | -1.283 |
Tanz | -1.248 |
Token | ( |
Token ID | 357 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
`` | +2.812 |
HL | +2.741 |
subs | +2.629 |
ESV | +2.555 |
Lange | +2.494 |
Neg logit contributions | |
hran | -3.299 |
clair | -3.262 |
Ul | -3.126 |
rily | -3.035 |
oute | -2.920 |
Token | Af |
Token ID | 17584 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
`` | +5.667 |
HL | +5.479 |
subs | +4.819 |
XX | +4.814 |
wolf | +4.782 |
Neg logit contributions | |
hran | -9.908 |
clair | -9.339 |
rily | -9.088 |
offic | -8.649 |
oute | -8.593 |
Token | D |
Token ID | 35 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
`` | +0.733 |
HL | +0.711 |
subs | +0.674 |
ESV | +0.635 |
ousse | +0.612 |
Neg logit contributions | |
hran | -1.671 |
clair | -1.634 |
rily | -1.562 |
Ul | -1.552 |
offic | -1.506 |
Token | ) |
Token ID | 8 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
`` | +3.290 |
HL | +3.214 |
subs | +3.039 |
ESV | +3.036 |
ousse | +2.935 |
Neg logit contributions | |
hran | -3.392 |
clair | -3.338 |
Ul | -3.181 |
rily | -3.071 |
Tanz | -2.927 |
Token | party |
Token ID | 2151 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
`` | +3.411 |
HL | +3.341 |
subs | +3.203 |
ESV | +3.118 |
Lange | +3.049 |
Neg logit contributions | |
hran | -3.667 |
clair | -3.636 |
Ul | -3.507 |
rily | -3.353 |
ridor | -3.240 |
Token | | |
Token ID | 930 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
`` | +1.608 |
HL | +1.565 |
subs | +1.495 |
ESV | +1.480 |
Lange | +1.440 |
Neg logit contributions | |
hran | -1.563 |
clair | -1.562 |
Ul | -1.516 |
rily | -1.442 |
Tanz | -1.389 |
Token | rate |
Token ID | 4873 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
`` | +1.515 |
HL | +1.453 |
subs | +1.377 |
ESV | +1.354 |
ousse | +1.309 |
Neg logit contributions | |
clair | -2.029 |
hran | -2.026 |
Ul | -1.988 |
rily | -1.898 |
Tanz | -1.860 |
Token | GT |
Token ID | 7963 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
`` | +2.464 |
HL | +2.396 |
subs | +2.280 |
ESV | +2.265 |
`` | +2.179 |
Neg logit contributions | |
clair | -2.686 |
hran | -2.683 |
Ul | -2.615 |
rily | -2.490 |
Tanz | -2.423 |
Token | / |
Token ID | 14 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
`` | +4.089 |
HL | +4.029 |
subs | +3.859 |
ESV | +3.756 |
`` | +3.623 |
Neg logit contributions | |
hran | -4.562 |
clair | -4.501 |
Ul | -4.332 |
rily | -4.153 |
trump | -4.081 |
Token | s |
Token ID | 82 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
`` | +2.607 |
HL | +2.504 |
subs | +2.355 |
ESV | +2.321 |
ousse | +2.250 |
Neg logit contributions | |
hran | -2.986 |
clair | -2.924 |
Ul | -2.854 |
rily | -2.753 |
Tanz | -2.702 |
Token | 72 |
Token ID | 7724 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
`` | +1.411 |
HL | +1.370 |
subs | +1.300 |
ESV | +1.297 |
ousse | +1.246 |
Neg logit contributions | |
hran | -1.523 |
clair | -1.519 |
Ul | -1.486 |
rily | -1.411 |
Tanz | -1.368 |
Token | GT |
Token ID | 7963 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
`` | +5.332 |
HL | +5.319 |
ESV | +4.957 |
subs | +4.905 |
`` | +4.727 |
Neg logit contributions | |
clair | -5.799 |
hran | -5.761 |
Ul | -5.533 |
rily | -5.330 |
trump | -5.163 |
Token | / |
Token ID | 14 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
HL | +5.942 |
`` | +5.641 |
subs | +5.496 |
ESV | +5.337 |
ousse | +5.102 |
Neg logit contributions | |
clair | -9.006 |
hran | -8.922 |
Ul | -8.858 |
rily | -8.492 |
ridor | -8.256 |
Token | s |
Token ID | 82 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
`` | +1.591 |
HL | +1.533 |
subs | +1.451 |
ESV | +1.428 |
ousse | +1.389 |
Neg logit contributions | |
hran | -1.956 |
clair | -1.952 |
Ul | -1.914 |
rily | -1.826 |
Tanz | -1.799 |
Token | 109 |
Token ID | 16003 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
`` | +2.649 |
HL | +2.604 |
ESV | +2.446 |
subs | +2.441 |
`` | +2.345 |
Neg logit contributions | |
hran | -2.882 |
clair | -2.876 |
Ul | -2.798 |
rily | -2.666 |
Tanz | -2.574 |
Token | . |
Token ID | 13 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
`` | +1.555 |
HL | +1.515 |
ESV | +1.417 |
subs | +1.410 |
`` | +1.348 |
Neg logit contributions | |
clair | -2.059 |
hran | -2.050 |
Ul | -2.011 |
rily | -1.923 |
Tanz | -1.865 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
`` | +4.197 |
HL | +3.994 |
ESV | +3.755 |
subs | +3.693 |
`` | +3.620 |
Neg logit contributions | |
hran | -4.688 |
clair | -4.677 |
Ul | -4.420 |
rily | -4.350 |
oute | -4.226 |
Token | $ |
Token ID | 720 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
clair | +1.525 |
Ul | +1.511 |
hran | +1.511 |
rily | +1.411 |
Ros | +1.384 |
Neg logit contributions | |
`` | -2.010 |
HL | -1.968 |
ESV | -1.906 |
subs | -1.898 |
Dise | -1.877 |
Token | rect |
Token ID | 2554 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
clair | +1.347 |
hran | +1.330 |
Ul | +1.297 |
rily | +1.235 |
oute | +1.180 |
Neg logit contributions | |
`` | -1.602 |
HL | -1.556 |
ESV | -1.480 |
subs | -1.480 |
Lange | -1.436 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
clair | +2.030 |
Ul | +1.982 |
hran | +1.977 |
trump | +1.840 |
rily | +1.832 |
Neg logit contributions | |
HL | -2.212 |
`` | -2.183 |
Dise | -2.118 |
ESV | -2.088 |
subs | -2.064 |
Token | , |
Token ID | 11 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
`` | +1.890 |
HL | +1.815 |
subs | +1.745 |
ESV | +1.733 |
`` | +1.671 |
Neg logit contributions | |
clair | -2.004 |
hran | -1.988 |
Ul | -1.938 |
rily | -1.833 |
Tanz | -1.812 |
Token | $ |
Token ID | 720 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
clair | +1.312 |
hran | +1.304 |
Ul | +1.304 |
rily | +1.213 |
Ros | +1.190 |
Neg logit contributions | |
`` | -1.694 |
HL | -1.650 |
ESV | -1.589 |
subs | -1.589 |
ousse | -1.567 |
Token | s |
Token ID | 82 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
`` | +0.807 |
HL | +0.766 |
subs | +0.737 |
ESV | +0.727 |
ousse | +0.709 |
Neg logit contributions | |
hran | -0.978 |
clair | -0.972 |
Ul | -0.954 |
rily | -0.908 |
Tanz | -0.895 |
Token | Format |
Token ID | 26227 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
Ul | +5.332 |
clair | +5.163 |
hran | +4.894 |
rily | +4.485 |
oute | +4.469 |
Neg logit contributions | |
HL | -6.344 |
Dise | -6.225 |
ESV | -6.211 |
ーティ | -6.129 |
サーティワン | -6.111 |
Token | ) |
Token ID | 8 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
clair | +0.241 |
hran | +0.240 |
Ul | +0.235 |
rily | +0.221 |
Tanz | +0.213 |
Neg logit contributions | |
`` | -0.319 |
HL | -0.308 |
subs | -0.296 |
ESV | -0.295 |
ousse | -0.287 |
Token | } |
Token ID | 1782 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
hran | +2.667 |
clair | +2.659 |
Ul | +2.585 |
rily | +2.464 |
Tanz | +2.373 |
Neg logit contributions | |
`` | -3.423 |
HL | -3.292 |
ESV | -3.140 |
subs | -3.137 |
ousse | -3.083 |
Token | } |
Token ID | 1782 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
clair | +1.666 |
hran | +1.660 |
Ul | +1.629 |
rily | +1.553 |
Tanz | +1.511 |
Neg logit contributions | |
`` | -1.548 |
HL | -1.486 |
ESV | -1.406 |
subs | -1.402 |
ousse | -1.374 |
Token | } |
Token ID | 1782 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
clair | +4.396 |
hran | +4.389 |
Ul | +4.305 |
rily | +4.157 |
Ros | +4.090 |
Neg logit contributions | |
`` | -4.639 |
HL | -4.409 |
ousse | -4.229 |
ESV | -4.216 |
subs | -4.154 |
Token | relations |
Token ID | 2316 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
hran | +2.421 |
clair | +2.390 |
Ul | +2.385 |
rily | +2.161 |
Tanz | +2.116 |
Neg logit contributions | |
`` | -4.562 |
HL | -4.446 |
ESV | -4.288 |
ousse | -4.249 |
subs | -4.192 |
Token | which |
Token ID | 543 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
hran | +3.334 |
clair | +3.314 |
Ul | +3.243 |
rily | +3.062 |
Tanz | +2.963 |
Neg logit contributions | |
`` | -3.654 |
HL | -3.575 |
ESV | -3.391 |
ousse | -3.331 |
subs | -3.310 |
Token | both |
Token ID | 1111 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
hran | +1.440 |
clair | +1.431 |
Ul | +1.404 |
rily | +1.322 |
Tanz | +1.287 |
Neg logit contributions | |
`` | -1.583 |
HL | -1.525 |
ESV | -1.457 |
subs | -1.434 |
ousse | -1.413 |
Token | countries |
Token ID | 2678 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
hran | +3.793 |
Ul | +3.689 |
clair | +3.687 |
rily | +3.450 |
Tanz | +3.408 |
Neg logit contributions | |
`` | -3.999 |
HL | -3.841 |
ESV | -3.688 |
ousse | -3.601 |
ヘ | -3.572 |
Token | wish |
Token ID | 4601 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
hran | +3.411 |
clair | +3.365 |
Ul | +3.258 |
rily | +3.146 |
Tanz | +3.053 |
Neg logit contributions | |
`` | -3.806 |
HL | -3.727 |
ESV | -3.552 |
ヘ | -3.535 |
ousse | -3.483 |
Token | to |
Token ID | 284 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
hran | +2.844 |
clair | +2.783 |
Ul | +2.747 |
rily | +2.599 |
Tanz | +2.488 |
Neg logit contributions | |
`` | -3.207 |
HL | -3.073 |
ESV | -2.954 |
subs | -2.905 |
ousse | -2.852 |
Token | develop |
Token ID | 1205 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
hran | +4.894 |
clair | +4.846 |
Ul | +4.739 |
rily | +4.554 |
offic | +4.519 |
Neg logit contributions | |
`` | -5.401 |
HL | -5.184 |
ヘ | -4.951 |
ESV | -4.908 |
Lange | -4.844 |
Token | ."[ |
Token ID | 18161 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
clair | +0.336 |
hran | +0.336 |
Ul | +0.329 |
rily | +0.312 |
Tanz | +0.303 |
Neg logit contributions | |
`` | -0.335 |
HL | -0.322 |
subs | -0.307 |
ESV | -0.307 |
ousse | -0.297 |
Token | 45 |
Token ID | 2231 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
clair | +4.403 |
Ul | +4.247 |
hran | +4.226 |
trump | +3.918 |
atar | +3.834 |
Neg logit contributions | |
HL | -5.994 |
`` | -5.929 |
senal | -5.743 |
Dise | -5.732 |
ESV | -5.729 |
Token | ] |
Token ID | 60 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Ul | +1.648 |
clair | +1.640 |
hran | +1.603 |
rily | +1.513 |
Ros | +1.497 |
Neg logit contributions | |
`` | -1.604 |
HL | -1.544 |
subs | -1.495 |
ESV | -1.484 |
Dise | -1.481 |
Token | Damascus |
Token ID | 21028 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
hran | +1.167 |
clair | +1.162 |
Ul | +1.149 |
rily | +1.081 |
Tanz | +1.070 |
Neg logit contributions | |
`` | -1.175 |
HL | -1.125 |
subs | -1.094 |
ESV | -1.074 |
ousse | -1.056 |
Token | Body |
Token ID | 12290 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
`` | +3.025 |
HL | +2.945 |
ESV | +2.775 |
subs | +2.752 |
`` | +2.715 |
Neg logit contributions | |
hran | -3.303 |
clair | -3.286 |
Ul | -3.193 |
rily | -3.098 |
oute | -2.972 |
Token | Mass |
Token ID | 5674 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
`` | +2.031 |
HL | +1.953 |
subs | +1.885 |
ESV | +1.847 |
`` | +1.807 |
Neg logit contributions | |
clair | -1.877 |
hran | -1.862 |
Ul | -1.814 |
rily | -1.749 |
Tanz | -1.682 |
Token | Index |
Token ID | 12901 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
clair | +1.507 |
hran | +1.504 |
Ul | +1.481 |
rily | +1.369 |
Tanz | +1.339 |
Neg logit contributions | |
`` | -2.154 |
HL | -2.076 |
subs | -2.003 |
ESV | -1.999 |
ousse | -1.941 |
Token | , |
Token ID | 11 |
Feature activation | -8.37e-03 |
Pos logit contributions | |
hran | +1.142 |
clair | +1.142 |
Ul | +1.124 |
rily | +1.057 |
Tanz | +1.033 |
Neg logit contributions | |
`` | -1.197 |
HL | -1.148 |
ESV | -1.099 |
subs | -1.094 |
ousse | -1.062 |
Token | or |
Token ID | 393 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
`` | +0.071 |
HL | +0.068 |
subs | +0.065 |
ESV | +0.065 |
ousse | +0.063 |
Neg logit contributions | |
clair | -0.071 |
hran | -0.071 |
Ul | -0.069 |
rily | -0.066 |
Tanz | -0.064 |
Token | BMI |
Token ID | 22456 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
`` | +1.298 |
HL | +1.277 |
subs | +1.199 |
ESV | +1.192 |
`` | +1.156 |
Neg logit contributions | |
clair | -1.599 |
hran | -1.595 |
Ul | -1.568 |
rily | -1.497 |
oute | -1.444 |
Token | , |
Token ID | 11 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Ul | +5.485 |
hran | +5.460 |
clair | +5.399 |
Ros | +4.987 |
atar | +4.898 |
Neg logit contributions | |
`` | -6.898 |
HL | -6.490 |
ESV | -6.429 |
ousse | -6.362 |
subs | -6.317 |
Token | is |
Token ID | 318 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
clair | +1.424 |
hran | +1.416 |
Ul | +1.396 |
rily | +1.300 |
Tanz | +1.266 |
Neg logit contributions | |
`` | -1.780 |
HL | -1.717 |
ESV | -1.651 |
subs | -1.644 |
ousse | -1.608 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
clair | +1.187 |
hran | +1.185 |
Ul | +1.165 |
rily | +1.095 |
Tanz | +1.061 |
Neg logit contributions | |
`` | -1.398 |
HL | -1.341 |
ESV | -1.290 |
subs | -1.288 |
ousse | -1.252 |
Token | official |
Token ID | 1743 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
clair | +1.068 |
hran | +1.066 |
Ul | +1.047 |
rily | +0.992 |
Tanz | +0.966 |
Neg logit contributions | |
`` | -1.101 |
HL | -1.045 |
ESV | -1.002 |
subs | -0.999 |
ousse | -0.973 |
Token | measure |
Token ID | 3953 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
hran | +1.138 |
clair | +1.137 |
Ul | +1.113 |
rily | +1.052 |
Tanz | +1.022 |
Neg logit contributions | |
`` | -1.269 |
HL | -1.219 |
ESV | -1.166 |
subs | -1.165 |
ousse | -1.130 |
Token | 7 |
Token ID | 767 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
`` | +0.602 |
HL | +0.577 |
subs | +0.549 |
ESV | +0.547 |
`` | +0.529 |
Neg logit contributions | |
clair | -0.696 |
hran | -0.696 |
Ul | -0.681 |
rily | -0.650 |
Tanz | -0.631 |
Token | }, |
Token ID | 5512 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
hran | +4.408 |
clair | +4.364 |
Ul | +4.325 |
rily | +4.099 |
Tanz | +4.003 |
Neg logit contributions | |
`` | -4.914 |
HL | -4.877 |
ESV | -4.614 |
subs | -4.601 |
Lange | -4.473 |
Token | { |
Token ID | 1391 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
`` | +0.679 |
HL | +0.653 |
subs | +0.628 |
ESV | +0.627 |
`` | +0.615 |
Neg logit contributions | |
clair | -0.621 |
hran | -0.620 |
Ul | -0.599 |
rily | -0.572 |
Tanz | -0.548 |
Token | 4 |
Token ID | 19 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
clair | +0.148 |
hran | +0.147 |
Ul | +0.144 |
rily | +0.137 |
Tanz | +0.134 |
Neg logit contributions | |
`` | -0.132 |
HL | -0.126 |
subs | -0.120 |
ESV | -0.120 |
`` | -0.116 |
Token | , |
Token ID | 11 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
`` | +3.334 |
HL | +3.187 |
subs | +3.037 |
ESV | +3.010 |
`` | +2.941 |
Neg logit contributions | |
clair | -3.349 |
hran | -3.347 |
Ul | -3.238 |
rily | -3.116 |
Tanz | -3.054 |
Token | 6 |
Token ID | 718 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
`` | +1.412 |
HL | +1.357 |
subs | +1.287 |
ESV | +1.284 |
`` | +1.237 |
Neg logit contributions | |
clair | -1.624 |
hran | -1.622 |
Ul | -1.588 |
rily | -1.517 |
Tanz | -1.469 |
Token | }, |
Token ID | 5512 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
clair | +4.836 |
Ul | +4.795 |
hran | +4.772 |
rily | +4.472 |
Tanz | +4.364 |
Neg logit contributions | |
HL | -6.575 |
`` | -6.388 |
ESV | -6.254 |
subs | -6.245 |
Lange | -6.170 |
Token | { |
Token ID | 1391 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
clair | +0.520 |
hran | +0.520 |
Ul | +0.505 |
rily | +0.479 |
Tanz | +0.461 |
Neg logit contributions | |
`` | -0.603 |
HL | -0.580 |
subs | -0.557 |
ESV | -0.556 |
`` | -0.542 |
Token | 4 |
Token ID | 19 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
clair | +0.473 |
hran | +0.472 |
Ul | +0.462 |
rily | +0.439 |
Tanz | +0.427 |
Neg logit contributions | |
`` | -0.455 |
HL | -0.437 |
subs | -0.416 |
ESV | -0.415 |
ousse | -0.401 |
Token | , |
Token ID | 11 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
`` | +3.266 |
HL | +3.125 |
subs | +2.974 |
ESV | +2.953 |
`` | +2.881 |
Neg logit contributions | |
hran | -3.250 |
clair | -3.249 |
Ul | -3.145 |
rily | -3.024 |
Tanz | -2.959 |
Token | 7 |
Token ID | 767 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
`` | +1.529 |
HL | +1.470 |
subs | +1.395 |
ESV | +1.390 |
`` | +1.340 |
Neg logit contributions | |
clair | -1.811 |
hran | -1.807 |
Ul | -1.770 |
rily | -1.695 |
Tanz | -1.638 |
Token | - |
Token ID | 12 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Ul | +4.051 |
hran | +4.043 |
clair | +3.908 |
rily | +3.651 |
Ros | +3.573 |
Neg logit contributions | |
`` | -5.551 |
HL | -5.292 |
subs | -5.234 |
ESV | -5.168 |
Dise | -5.095 |
Token | m |
Token ID | 76 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
clair | +3.925 |
hran | +3.899 |
Ul | +3.845 |
rily | +3.554 |
trump | +3.512 |
Neg logit contributions | |
`` | -4.090 |
HL | -3.983 |
ESV | -3.862 |
subs | -3.831 |
Dise | -3.755 |
Token | eth |
Token ID | 2788 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
clair | +1.750 |
hran | +1.749 |
Ul | +1.702 |
rily | +1.514 |
oute | +1.421 |
Neg logit contributions | |
`` | -4.118 |
HL | -4.039 |
ESV | -3.922 |
subs | -3.901 |
Lange | -3.799 |
Token | ox |
Token ID | 1140 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
clair | +2.854 |
hran | +2.852 |
Ul | +2.806 |
rily | +2.647 |
oute | +2.557 |
Neg logit contributions | |
`` | -2.795 |
HL | -2.692 |
subs | -2.586 |
ESV | -2.572 |
`` | -2.473 |
Token | ym |
Token ID | 4948 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
hran | +3.499 |
clair | +3.483 |
Ul | +3.285 |
rily | +2.935 |
atar | +2.867 |
Neg logit contributions | |
HL | -10.720 |
`` | -10.620 |
subs | -10.590 |
ESV | -10.538 |
Dise | -10.430 |
Token | ethyl |
Token ID | 21610 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
clair | +0.442 |
hran | +0.441 |
Ul | +0.427 |
rily | +0.395 |
Tanz | +0.381 |
Neg logit contributions | |
`` | -0.853 |
HL | -0.827 |
subs | -0.798 |
ESV | -0.797 |
ousse | -0.779 |
Token | phen |
Token ID | 31024 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
clair | +4.394 |
hran | +4.357 |
Ul | +4.316 |
rily | +3.938 |
trump | +3.898 |
Neg logit contributions | |
`` | -6.249 |
HL | -6.009 |
subs | -5.833 |
ESV | -5.796 |
Dise | -5.743 |
Token | yl |
Token ID | 2645 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
hran | +3.232 |
clair | +3.187 |
Ul | +3.166 |
rily | +2.926 |
Ros | +2.768 |
Neg logit contributions | |
`` | -4.897 |
HL | -4.823 |
subs | -4.702 |
ESV | -4.647 |
Dise | -4.549 |
Token | )- |
Token ID | 13219 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
hran | +2.782 |
clair | +2.764 |
Ul | +2.715 |
rily | +2.519 |
trump | +2.403 |
Neg logit contributions | |
`` | -4.278 |
HL | -4.153 |
subs | -4.011 |
ESV | -3.987 |
ousse | -3.907 |
Token | 2 |
Token ID | 17 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Ul | +4.471 |
clair | +4.463 |
hran | +4.463 |
rily | +4.067 |
trump | +3.987 |
Neg logit contributions | |
`` | -4.975 |
HL | -4.891 |
subs | -4.712 |
ESV | -4.706 |
Dise | -4.626 |
Token | - |
Token ID | 12 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
hran | +3.078 |
Ul | +3.058 |
clair | +2.989 |
rily | +2.801 |
Ros | +2.699 |
Neg logit contributions | |
`` | -3.884 |
HL | -3.724 |
subs | -3.627 |
ESV | -3.596 |
ousse | -3.553 |
Token | See |
Token ID | 4091 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
clair | +1.300 |
hran | +1.291 |
Ul | +1.272 |
rily | +1.196 |
Tanz | +1.171 |
Neg logit contributions | |
`` | -1.429 |
HL | -1.357 |
subs | -1.301 |
ESV | -1.297 |
ousse | -1.259 |
Token | Gallery |
Token ID | 12917 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
`` | +0.900 |
HL | +0.865 |
subs | +0.824 |
ESV | +0.823 |
ousse | +0.802 |
Neg logit contributions | |
clair | -0.832 |
hran | -0.831 |
Ul | -0.809 |
rily | -0.766 |
Tanz | -0.747 |
Token | Donald |
Token ID | 3759 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
clair | +1.775 |
hran | +1.763 |
Ul | +1.729 |
rily | +1.582 |
Tanz | +1.538 |
Neg logit contributions | |
`` | -3.332 |
HL | -3.196 |
subs | -3.125 |
ESV | -3.085 |
ヘ | -3.043 |
Token | Trump |
Token ID | 1301 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
clair | +0.905 |
hran | +0.875 |
Ul | +0.851 |
trump | +0.778 |
rily | +0.771 |
Neg logit contributions | |
`` | -2.858 |
HL | -2.773 |
ESV | -2.716 |
subs | -2.704 |
ヘ | -2.682 |
Token | passes |
Token ID | 8318 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
`` | +0.551 |
HL | +0.529 |
ESV | +0.507 |
subs | +0.506 |
ousse | +0.491 |
Neg logit contributions | |
clair | -0.469 |
hran | -0.466 |
Ul | -0.456 |
rily | -0.431 |
Tanz | -0.417 |
Token | on |
Token ID | 319 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
`` | +0.380 |
HL | +0.368 |
subs | +0.351 |
ESV | +0.349 |
`` | +0.337 |
Neg logit contributions | |
clair | -0.365 |
hran | -0.364 |
Ul | -0.356 |
rily | -0.337 |
Tanz | -0.327 |
Token | ' |
Token ID | 705 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
clair | +1.537 |
hran | +1.534 |
Ul | +1.498 |
rily | +1.414 |
Tanz | +1.370 |
Neg logit contributions | |
`` | -1.983 |
HL | -1.907 |
subs | -1.830 |
ESV | -1.828 |
ousse | -1.779 |
Token | in |
Token ID | 259 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
clair | +0.233 |
hran | +0.231 |
Ul | +0.228 |
rily | +0.215 |
Tanz | +0.209 |
Neg logit contributions | |
`` | -0.224 |
HL | -0.217 |
subs | -0.206 |
ESV | -0.206 |
ousse | -0.199 |
Token | appropriate |
Token ID | 13335 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
clair | +2.377 |
hran | +2.312 |
Ul | +2.279 |
rily | +2.174 |
oute | +2.087 |
Neg logit contributions | |
`` | -2.347 |
HL | -2.273 |
ESV | -2.172 |
subs | -2.154 |
ousse | -2.110 |
Token | ' |
Token ID | 6 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
`` | +1.060 |
HL | +1.029 |
subs | +0.988 |
ESV | +0.978 |
Lange | +0.948 |
Neg logit contributions | |
hran | -0.885 |
clair | -0.884 |
Ul | -0.861 |
rily | -0.809 |
Tanz | -0.785 |
Token | debate |
Token ID | 4384 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
`` | +0.125 |
HL | +0.120 |
subs | +0.115 |
ESV | +0.115 |
ousse | +0.112 |
Neg logit contributions | |
clair | -0.110 |
hran | -0.110 |
Ul | -0.108 |
rily | -0.102 |
Tanz | -0.099 |
Token | were |
Token ID | 547 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
clair | +0.479 |
hran | +0.477 |
Ul | +0.467 |
rily | +0.443 |
Tanz | +0.428 |
Neg logit contributions | |
`` | -0.524 |
HL | -0.505 |
ESV | -0.483 |
subs | -0.480 |
ousse | -0.468 |
Token | between |
Token ID | 1022 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
`` | +0.675 |
HL | +0.653 |
subs | +0.627 |
ESV | +0.617 |
`` | +0.600 |
Neg logit contributions | |
clair | -0.737 |
hran | -0.734 |
Ul | -0.719 |
rily | -0.681 |
Tanz | -0.663 |
Token | the |
Token ID | 262 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
hran | +0.960 |
clair | +0.958 |
Ul | +0.941 |
rily | +0.893 |
Tanz | +0.869 |
Neg logit contributions | |
`` | -0.974 |
HL | -0.932 |
subs | -0.888 |
ESV | -0.888 |
ousse | -0.862 |
Token | Captain |
Token ID | 8599 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
`` | +2.001 |
HL | +1.942 |
subs | +1.868 |
ESV | +1.845 |
`` | +1.787 |
Neg logit contributions | |
clair | -2.186 |
hran | -2.163 |
Ul | -2.118 |
rily | -2.010 |
oute | -1.940 |
Token | , |
Token ID | 11 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
`` | +2.096 |
HL | +2.017 |
subs | +1.936 |
ESV | +1.910 |
Lange | +1.867 |
Neg logit contributions | |
clair | -2.173 |
hran | -2.168 |
Ul | -2.119 |
rily | -2.013 |
Tanz | -1.947 |
Token | and |
Token ID | 290 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
clair | +0.374 |
hran | +0.374 |
Ul | +0.366 |
rily | +0.347 |
Tanz | +0.337 |
Neg logit contributions | |
`` | -0.394 |
HL | -0.380 |
subs | -0.363 |
ESV | -0.362 |
ousse | -0.350 |
Token | Seven |
Token ID | 13723 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
clair | +1.483 |
hran | +1.481 |
Ul | +1.456 |
rily | +1.377 |
Tanz | +1.344 |
Neg logit contributions | |
`` | -1.694 |
HL | -1.623 |
ESV | -1.553 |
subs | -1.551 |
ousse | -1.514 |
Token | and |
Token ID | 290 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
clair | +1.219 |
hran | +1.216 |
Ul | +1.194 |
rily | +1.129 |
Tanz | +1.095 |
Neg logit contributions | |
`` | -1.341 |
HL | -1.295 |
ESV | -1.235 |
subs | -1.231 |
ousse | -1.201 |
Token | the |
Token ID | 262 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
`` | +1.862 |
HL | +1.793 |
subs | +1.718 |
ESV | +1.705 |
`` | +1.668 |
Neg logit contributions | |
clair | -1.718 |
hran | -1.710 |
Ul | -1.661 |
rily | -1.570 |
Tanz | -1.522 |
Token | Doctor |
Token ID | 9356 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
`` | +0.711 |
HL | +0.685 |
subs | +0.654 |
ESV | +0.651 |
`` | +0.629 |
Neg logit contributions | |
clair | -0.709 |
hran | -0.708 |
Ul | -0.692 |
rily | -0.655 |
Tanz | -0.636 |
Token | . |
Token ID | 13 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
`` | +0.895 |
HL | +0.863 |
subs | +0.827 |
ESV | +0.821 |
Lange | +0.797 |
Neg logit contributions | |
clair | -0.813 |
hran | -0.811 |
Ul | -0.792 |
rily | -0.752 |
Tanz | -0.727 |
Token | I |
Token ID | 314 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
`` | +1.995 |
HL | +1.955 |
subs | +1.860 |
ESV | +1.845 |
Lange | +1.777 |
Neg logit contributions | |
clair | -2.116 |
hran | -2.105 |
Ul | -2.059 |
rily | -1.958 |
Tanz | -1.887 |
Token | � |
Token ID | 447 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
`` | +2.002 |
HL | +1.930 |
subs | +1.858 |
ESV | +1.847 |
`` | +1.789 |
Neg logit contributions | |
clair | -1.743 |
hran | -1.738 |
Ul | -1.702 |
rily | -1.602 |
Tanz | -1.553 |
Token | � |
Token ID | 247 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
`` | +0.544 |
HL | +0.522 |
subs | +0.497 |
ESV | +0.495 |
ousse | +0.478 |
Neg logit contributions | |
clair | -0.602 |
hran | -0.601 |
Ul | -0.589 |
rily | -0.560 |
Tanz | -0.545 |
Token | ve |
Token ID | 303 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
clair | +1.618 |
hran | +1.615 |
Ul | +1.587 |
rily | +1.504 |
oute | +1.448 |
Neg logit contributions | |
`` | -1.697 |
HL | -1.646 |
subs | -1.589 |
ESV | -1.572 |
ousse | -1.539 |
Token | seen |
Token ID | 1775 |
Feature activation | +8.98e-03 |
Pos logit contributions | |
`` | +1.123 |
HL | +1.079 |
subs | +1.028 |
ESV | +1.024 |
ousse | +0.988 |
Neg logit contributions | |
clair | -1.195 |
hran | -1.193 |
Ul | -1.169 |
rily | -1.111 |
Tanz | -1.080 |
Token | it |
Token ID | 340 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
hran | +0.073 |
clair | +0.073 |
Ul | +0.071 |
rily | +0.067 |
Tanz | +0.066 |
Neg logit contributions | |
`` | -0.079 |
HL | -0.075 |
subs | -0.072 |
ESV | -0.072 |
ousse | -0.070 |
Token | so |
Token ID | 523 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
clair | +0.666 |
hran | +0.665 |
Ul | +0.647 |
rily | +0.616 |
Tanz | +0.597 |
Neg logit contributions | |
`` | -0.730 |
HL | -0.703 |
ESV | -0.672 |
subs | -0.672 |
ousse | -0.654 |
Token | far |
Token ID | 1290 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
`` | +0.429 |
HL | +0.413 |
subs | +0.395 |
ESV | +0.393 |
ousse | +0.380 |
Neg logit contributions | |
clair | -0.417 |
hran | -0.416 |
Ul | -0.406 |
rily | -0.386 |
Tanz | -0.375 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
`` | +0.464 |
HL | +0.447 |
subs | +0.428 |
ESV | +0.427 |
ousse | +0.414 |
Neg logit contributions | |
clair | -0.396 |
hran | -0.395 |
Ul | -0.386 |
rily | -0.365 |
Tanz | -0.353 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
`` | +0.883 |
HL | +0.848 |
subs | +0.806 |
ESV | +0.805 |
ousse | +0.776 |
Neg logit contributions | |
clair | -0.951 |
hran | -0.950 |
Ul | -0.930 |
rily | -0.885 |
Tanz | -0.860 |
Token |
|
Token ID | 198 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
`` | +0.094 |
HL | +0.092 |
ESV | +0.088 |
subs | +0.088 |
Dise | +0.086 |
Neg logit contributions | |
clair | -0.087 |
hran | -0.086 |
Ul | -0.085 |
rily | -0.080 |
Ros | -0.077 |
Token | News |
Token ID | 3000 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
clair | +1.957 |
Ul | +1.924 |
hran | +1.920 |
rily | +1.779 |
Tanz | +1.756 |
Neg logit contributions | |
`` | -2.167 |
HL | -2.034 |
ESV | -2.004 |
subs | -1.983 |
ousse | -1.958 |
Token | 24 |
Token ID | 1987 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
`` | +1.818 |
HL | +1.766 |
subs | +1.675 |
ESV | +1.664 |
`` | +1.610 |
Neg logit contributions | |
hran | -1.815 |
clair | -1.804 |
Ul | -1.766 |
rily | -1.683 |
Tanz | -1.628 |
Token | . |
Token ID | 13 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
`` | +3.444 |
HL | +3.378 |
subs | +3.177 |
ESV | +3.154 |
`` | +3.050 |
Neg logit contributions | |
hran | -3.496 |
clair | -3.395 |
Ul | -3.384 |
rily | -3.224 |
Tanz | -3.118 |
Token |
|
Token ID | 198 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
`` | +2.545 |
HL | +2.460 |
subs | +2.328 |
ESV | +2.323 |
`` | +2.249 |
Neg logit contributions | |
hran | -2.683 |
clair | -2.649 |
Ul | -2.589 |
rily | -2.481 |
Tanz | -2.406 |
Token |
|
Token ID | 198 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
`` | +0.508 |
HL | +0.491 |
subs | +0.469 |
ESV | +0.469 |
ousse | +0.455 |
Neg logit contributions | |
clair | -0.497 |
hran | -0.494 |
Ul | -0.488 |
rily | -0.461 |
Tanz | -0.444 |
Token | Topics |
Token ID | 25902 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
clair | +0.766 |
hran | +0.763 |
Ul | +0.753 |
rily | +0.720 |
Tanz | +0.702 |
Neg logit contributions | |
`` | -0.492 |
HL | -0.469 |
subs | -0.442 |
ESV | -0.440 |
ousse | -0.421 |
Token | : |
Token ID | 25 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
clair | +0.324 |
hran | +0.321 |
Ul | +0.313 |
rily | +0.294 |
Tanz | +0.282 |
Neg logit contributions | |
`` | -0.452 |
HL | -0.435 |
ESV | -0.421 |
subs | -0.416 |
ousse | -0.410 |
Token | beef |
Token ID | 12023 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
hran | +2.066 |
clair | +2.046 |
Ul | +2.006 |
rily | +1.904 |
Tanz | +1.850 |
Neg logit contributions | |
`` | -2.221 |
HL | -2.079 |
ESV | -2.014 |
ousse | -1.983 |
ヘ | -1.972 |
Token | - |
Token ID | 12 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
`` | +0.887 |
HL | +0.852 |
subs | +0.822 |
ESV | +0.813 |
`` | +0.789 |
Neg logit contributions | |
clair | -0.852 |
hran | -0.847 |
Ul | -0.832 |
rily | -0.783 |
Tanz | -0.770 |
Token | c |
Token ID | 66 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
`` | +0.803 |
HL | +0.773 |
subs | +0.742 |
ESV | +0.737 |
ousse | +0.718 |
Neg logit contributions | |
hran | -0.663 |
clair | -0.663 |
Ul | -0.646 |
rily | -0.611 |
Tanz | -0.595 |
Token | attle |
Token ID | 1999 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
clair | +1.099 |
hran | +1.097 |
Ul | +1.073 |
rily | +1.020 |
Tanz | +0.989 |
Neg logit contributions | |
`` | -1.084 |
HL | -1.044 |
subs | -0.995 |
ESV | -0.993 |
ousse | -0.957 |
Token | time |
Token ID | 640 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
hran | +0.886 |
clair | +0.882 |
Ul | +0.863 |
rily | +0.816 |
Tanz | +0.791 |
Neg logit contributions | |
`` | -0.999 |
HL | -0.959 |
ESV | -0.920 |
subs | -0.914 |
ousse | -0.898 |
Token | to |
Token ID | 284 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
clair | +2.030 |
hran | +2.022 |
Ul | +1.983 |
rily | +1.870 |
Tanz | +1.816 |
Neg logit contributions | |
`` | -2.317 |
HL | -2.211 |
ESV | -2.125 |
subs | -2.110 |
ousse | -2.067 |
Token | make |
Token ID | 787 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
clair | +1.747 |
hran | +1.736 |
Ul | +1.697 |
rily | +1.630 |
Tanz | +1.567 |
Neg logit contributions | |
`` | -1.880 |
HL | -1.811 |
ESV | -1.725 |
subs | -1.705 |
Lange | -1.682 |
Token | like |
Token ID | 588 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
`` | +0.738 |
HL | +0.712 |
subs | +0.680 |
ESV | +0.677 |
`` | +0.654 |
Neg logit contributions | |
clair | -0.720 |
hran | -0.720 |
Ul | -0.705 |
rily | -0.668 |
Tanz | -0.649 |
Token | a |
Token ID | 257 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
clair | +0.261 |
hran | +0.260 |
Ul | +0.254 |
rily | +0.241 |
Tanz | +0.233 |
Neg logit contributions | |
`` | -0.306 |
HL | -0.294 |
subs | -0.282 |
ESV | -0.281 |
ousse | -0.273 |
Token | rat |
Token ID | 4227 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
`` | +1.101 |
HL | +1.062 |
subs | +1.014 |
ESV | +1.004 |
`` | +0.973 |
Neg logit contributions | |
hran | -1.133 |
clair | -1.132 |
Ul | -1.108 |
rily | -1.049 |
Tanz | -1.019 |
Token | and |
Token ID | 290 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
hran | +2.015 |
clair | +2.005 |
Ul | +1.949 |
rily | +1.845 |
oute | +1.797 |
Neg logit contributions | |
`` | -2.396 |
HL | -2.305 |
ESV | -2.218 |
subs | -2.194 |
Lange | -2.131 |
Token | get |
Token ID | 651 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
`` | +1.557 |
HL | +1.504 |
subs | +1.456 |
ESV | +1.420 |
`` | +1.392 |
Neg logit contributions | |
hran | -1.564 |
clair | -1.556 |
Ul | -1.531 |
rily | -1.436 |
Tanz | -1.407 |
Token | the |
Token ID | 262 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
clair | +0.140 |
hran | +0.140 |
Ul | +0.137 |
rily | +0.130 |
Tanz | +0.127 |
Neg logit contributions | |
`` | -0.140 |
HL | -0.135 |
subs | -0.129 |
ESV | -0.128 |
ousse | -0.124 |
Token | heck |
Token ID | 22574 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
clair | +1.688 |
hran | +1.685 |
Ul | +1.659 |
rily | +1.584 |
Tanz | +1.540 |
Neg logit contributions | |
`` | -1.557 |
HL | -1.472 |
ESV | -1.410 |
subs | -1.399 |
ousse | -1.382 |
Token | off |
Token ID | 572 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
`` | +1.613 |
HL | +1.547 |
subs | +1.483 |
ESV | +1.450 |
`` | +1.404 |
Neg logit contributions | |
hran | -2.135 |
clair | -2.133 |
Ul | -2.096 |
rily | -1.995 |
Tanz | -1.965 |
Token | lazy |
Token ID | 16931 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
clair | +0.743 |
hran | +0.741 |
Ul | +0.726 |
rily | +0.690 |
Tanz | +0.672 |
Neg logit contributions | |
`` | -0.749 |
HL | -0.719 |
ESV | -0.685 |
subs | -0.684 |
ousse | -0.667 |
Token | minorities |
Token ID | 15557 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
clair | +0.319 |
hran | +0.318 |
Ul | +0.312 |
rily | +0.297 |
Tanz | +0.288 |
Neg logit contributions | |
`` | -0.298 |
HL | -0.286 |
ESV | -0.271 |
subs | -0.271 |
ousse | -0.265 |
Token | , |
Token ID | 11 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
`` | +0.703 |
HL | +0.676 |
subs | +0.647 |
ESV | +0.642 |
`` | +0.622 |
Neg logit contributions | |
hran | -0.691 |
clair | -0.691 |
Ul | -0.676 |
rily | -0.640 |
Tanz | -0.622 |
Token | immigrants |
Token ID | 7971 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
clair | +1.597 |
hran | +1.594 |
Ul | +1.563 |
rily | +1.485 |
Tanz | +1.445 |
Neg logit contributions | |
`` | -1.657 |
HL | -1.586 |
ESV | -1.517 |
subs | -1.502 |
ousse | -1.494 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
`` | +0.659 |
HL | +0.634 |
subs | +0.607 |
ESV | +0.602 |
`` | +0.584 |
Neg logit contributions | |
hran | -0.653 |
clair | -0.653 |
Ul | -0.639 |
rily | -0.606 |
Tanz | -0.588 |
Token | rich |
Token ID | 5527 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
hran | +0.897 |
clair | +0.897 |
Ul | +0.878 |
rily | +0.835 |
Tanz | +0.810 |
Neg logit contributions | |
`` | -0.963 |
HL | -0.923 |
ESV | -0.881 |
subs | -0.876 |
ousse | -0.862 |
Token | liberals |
Token ID | 17194 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
`` | +0.493 |
HL | +0.476 |
subs | +0.457 |
ESV | +0.454 |
`` | +0.441 |
Neg logit contributions | |
clair | -0.403 |
hran | -0.403 |
Ul | -0.393 |
rily | -0.371 |
Tanz | -0.359 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
clair | +0.326 |
hran | +0.325 |
Ul | +0.317 |
rily | +0.300 |
Tanz | +0.291 |
Neg logit contributions | |
`` | -0.379 |
HL | -0.366 |
ESV | -0.350 |
subs | -0.349 |
ousse | -0.339 |
Token | This |
Token ID | 770 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
clair | +1.174 |
hran | +1.168 |
Ul | +1.154 |
rily | +1.092 |
Tanz | +1.065 |
Neg logit contributions | |
`` | -1.180 |
HL | -1.134 |
subs | -1.092 |
ESV | -1.084 |
ousse | -1.062 |
Token | diverted |
Token ID | 35673 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
`` | +1.175 |
HL | +1.138 |
subs | +1.094 |
ESV | +1.080 |
`` | +1.050 |
Neg logit contributions | |
clair | -1.068 |
hran | -1.065 |
Ul | -1.040 |
rily | -0.983 |
Tanz | -0.955 |
Token | attention |
Token ID | 3241 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
clair | +0.125 |
hran | +0.125 |
Ul | +0.122 |
rily | +0.116 |
Tanz | +0.113 |
Neg logit contributions | |
`` | -0.136 |
HL | -0.131 |
subs | -0.125 |
ESV | -0.125 |
ousse | -0.121 |
Token | , |
Token ID | 11 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
clair | +2.070 |
hran | +2.045 |
Ul | +2.011 |
rily | +1.889 |
Tanz | +1.842 |
Neg logit contributions | |
`` | -2.527 |
HL | -2.422 |
ESV | -2.343 |
subs | -2.304 |
ousse | -2.295 |
Token | plus |
Token ID | 5556 |
Feature activation | +5.88e-03 |
Pos logit contributions | |
clair | +2.013 |
hran | +1.985 |
Ul | +1.945 |
rily | +1.853 |
Tanz | +1.803 |
Neg logit contributions | |
`` | -2.219 |
HL | -2.136 |
ESV | -2.055 |
subs | -2.019 |
ousse | -2.017 |
Token | radical |
Token ID | 7702 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
clair | +0.046 |
hran | +0.046 |
Ul | +0.045 |
rily | +0.042 |
Tanz | +0.041 |
Neg logit contributions | |
`` | -0.053 |
HL | -0.051 |
subs | -0.049 |
ESV | -0.049 |
`` | -0.048 |
Token | ism |
Token ID | 1042 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
clair | +0.521 |
hran | +0.519 |
Ul | +0.509 |
rily | +0.483 |
Tanz | +0.471 |
Neg logit contributions | |
`` | -0.499 |
HL | -0.479 |
ESV | -0.456 |
subs | -0.455 |
ousse | -0.440 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
clair | +0.635 |
hran | +0.634 |
Ul | +0.620 |
rily | +0.586 |
Tanz | +0.569 |
Neg logit contributions | |
`` | -0.706 |
HL | -0.679 |
ESV | -0.649 |
subs | -0.649 |
ousse | -0.628 |
Token | that |
Token ID | 326 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
clair | +0.901 |
hran | +0.895 |
Ul | +0.877 |
rily | +0.831 |
Tanz | +0.807 |
Neg logit contributions | |
`` | -1.008 |
HL | -0.971 |
ESV | -0.930 |
subs | -0.925 |
ousse | -0.903 |
Token | was |
Token ID | 373 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
`` | +2.110 |
HL | +2.040 |
subs | +1.974 |
ESV | +1.930 |
`` | +1.888 |
Neg logit contributions | |
hran | -2.044 |
clair | -2.039 |
Ul | -1.992 |
rily | -1.896 |
Tanz | -1.832 |
Token | unprecedented |
Token ID | 13029 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
`` | +1.688 |
HL | +1.631 |
subs | +1.572 |
ESV | +1.541 |
`` | +1.506 |
Neg logit contributions | |
clair | -1.676 |
hran | -1.675 |
Ul | -1.641 |
rily | -1.556 |
Tanz | -1.519 |
Token | in |
Token ID | 287 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
`` | +1.373 |
HL | +1.329 |
subs | +1.277 |
ESV | +1.259 |
`` | +1.223 |
Neg logit contributions | |
hran | -1.291 |
clair | -1.289 |
Ul | -1.259 |
rily | -1.188 |
Tanz | -1.155 |
Token | a |
Token ID | 257 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
`` | +0.633 |
HL | +0.611 |
subs | +0.582 |
ESV | +0.578 |
`` | +0.560 |
Neg logit contributions | |
clair | -0.666 |
hran | -0.665 |
Ul | -0.653 |
rily | -0.619 |
Tanz | -0.601 |
Token | major |
Token ID | 1688 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
`` | +1.136 |
HL | +1.094 |
subs | +1.045 |
ESV | +1.034 |
`` | +1.012 |
Neg logit contributions | |
clair | -1.169 |
hran | -1.164 |
Ul | -1.142 |
rily | -1.078 |
Tanz | -1.050 |
Token | this |
Token ID | 428 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
`` | +1.235 |
HL | +1.195 |
subs | +1.139 |
ESV | +1.131 |
`` | +1.095 |
Neg logit contributions | |
clair | -1.308 |
hran | -1.307 |
Ul | -1.270 |
rily | -1.212 |
Tanz | -1.181 |
Token | point |
Token ID | 966 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
hran | +0.949 |
clair | +0.949 |
Ul | +0.928 |
rily | +0.877 |
Tanz | +0.851 |
Neg logit contributions | |
`` | -1.062 |
HL | -1.022 |
subs | -0.977 |
ESV | -0.976 |
ousse | -0.948 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
clair | +1.202 |
hran | +1.197 |
Ul | +1.173 |
rily | +1.102 |
Tanz | +1.065 |
Neg logit contributions | |
`` | -1.428 |
HL | -1.376 |
ESV | -1.318 |
subs | -1.309 |
ousse | -1.283 |
Token | and |
Token ID | 290 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
clair | +0.107 |
hran | +0.107 |
Ul | +0.105 |
rily | +0.100 |
Tanz | +0.097 |
Neg logit contributions | |
`` | -0.102 |
HL | -0.098 |
subs | -0.093 |
ESV | -0.093 |
ousse | -0.090 |
Token | I |
Token ID | 314 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
clair | +0.743 |
hran | +0.742 |
Ul | +0.726 |
rily | +0.688 |
Tanz | +0.669 |
Neg logit contributions | |
`` | -0.794 |
HL | -0.760 |
ESV | -0.727 |
subs | -0.727 |
ousse | -0.707 |
Token | � |
Token ID | 447 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
`` | +0.451 |
HL | +0.435 |
subs | +0.415 |
ESV | +0.415 |
ousse | +0.402 |
Neg logit contributions | |
clair | -0.411 |
hran | -0.411 |
Ul | -0.401 |
rily | -0.380 |
Tanz | -0.369 |
Token | � |
Token ID | 247 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
`` | +1.276 |
HL | +1.221 |
subs | +1.160 |
ESV | +1.157 |
`` | +1.112 |
Neg logit contributions | |
clair | -1.508 |
hran | -1.505 |
Ul | -1.476 |
rily | -1.409 |
Tanz | -1.373 |
Token | ve |
Token ID | 303 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
clair | +0.385 |
hran | +0.385 |
Ul | +0.376 |
rily | +0.357 |
Tanz | +0.345 |
Neg logit contributions | |
`` | -0.392 |
HL | -0.379 |
subs | -0.362 |
ESV | -0.360 |
ousse | -0.349 |
Token | always |
Token ID | 1464 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
`` | +1.611 |
HL | +1.548 |
subs | +1.480 |
ESV | +1.470 |
`` | +1.426 |
Neg logit contributions | |
clair | -1.631 |
hran | -1.622 |
Ul | -1.595 |
rily | -1.514 |
Tanz | -1.474 |
Token | known |
Token ID | 1900 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
`` | +0.888 |
HL | +0.853 |
subs | +0.817 |
ESV | +0.811 |
`` | +0.786 |
Neg logit contributions | |
clair | -0.878 |
hran | -0.877 |
Ul | -0.860 |
rily | -0.814 |
Tanz | -0.792 |
Token | that |
Token ID | 326 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
clair | +0.149 |
hran | +0.149 |
Ul | +0.146 |
rily | +0.138 |
Tanz | +0.134 |
Neg logit contributions | |
`` | -0.162 |
HL | -0.156 |
subs | -0.149 |
ESV | -0.149 |
ousse | -0.145 |
Token | like |
Token ID | 588 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
hran | +1.046 |
clair | +1.045 |
Ul | +1.026 |
rily | +0.973 |
Tanz | +0.941 |
Neg logit contributions | |
`` | -1.172 |
HL | -1.124 |
ESV | -1.078 |
subs | -1.073 |
ousse | -1.045 |
Token | - |
Token ID | 12 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
`` | +0.309 |
HL | +0.299 |
subs | +0.288 |
ESV | +0.286 |
`` | +0.277 |
Neg logit contributions | |
clair | -0.257 |
hran | -0.256 |
Ul | -0.250 |
rily | -0.234 |
Tanz | -0.229 |
Token | minded |
Token ID | 14543 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
`` | +0.509 |
HL | +0.493 |
ESV | +0.470 |
subs | +0.467 |
Lange | +0.450 |
Neg logit contributions | |
clair | -0.592 |
hran | -0.586 |
Ul | -0.577 |
rily | -0.553 |
trump | -0.533 |
Token | voters |
Token ID | 4446 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
clair | +0.148 |
hran | +0.148 |
Ul | +0.145 |
rily | +0.138 |
Tanz | +0.134 |
Neg logit contributions | |
`` | -0.159 |
HL | -0.153 |
subs | -0.146 |
ESV | -0.146 |
ousse | -0.141 |
Token | during |
Token ID | 1141 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
`` | +0.464 |
HL | +0.447 |
subs | +0.428 |
ESV | +0.425 |
`` | +0.413 |
Neg logit contributions | |
clair | -0.409 |
hran | -0.409 |
Ul | -0.400 |
rily | -0.378 |
Tanz | -0.366 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
`` | +0.833 |
HL | +0.804 |
subs | +0.769 |
ESV | +0.764 |
`` | +0.749 |
Neg logit contributions | |
hran | -0.696 |
clair | -0.693 |
Ul | -0.677 |
rily | -0.637 |
Tanz | -0.614 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
`` | +1.165 |
HL | +1.124 |
subs | +1.071 |
ESV | +1.061 |
`` | +1.037 |
Neg logit contributions | |
clair | -1.211 |
hran | -1.211 |
Ul | -1.180 |
rily | -1.123 |
Tanz | -1.086 |
Token | election |
Token ID | 3071 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
clair | +1.047 |
hran | +1.043 |
Ul | +1.025 |
rily | +0.965 |
Tanz | +0.944 |
Neg logit contributions | |
`` | -1.111 |
HL | -1.070 |
ESV | -1.021 |
subs | -1.021 |
ousse | -0.989 |
Token | that |
Token ID | 326 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
`` | +1.040 |
HL | +0.998 |
subs | +0.956 |
ESV | +0.943 |
`` | +0.929 |
Neg logit contributions | |
clair | -0.963 |
hran | -0.960 |
Ul | -0.935 |
rily | -0.890 |
Tanz | -0.860 |
Token | Obama |
Token ID | 2486 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
`` | +2.036 |
HL | +1.960 |
subs | +1.876 |
ESV | +1.855 |
`` | +1.845 |
Neg logit contributions | |
clair | -1.743 |
hran | -1.743 |
Ul | -1.692 |
rily | -1.604 |
Tanz | -1.535 |
Token | would |
Token ID | 561 |
Feature activation | +1.60e-03 |
Pos logit contributions | |
`` | +2.845 |
HL | +2.715 |
subs | +2.616 |
`` | +2.572 |
ESV | +2.572 |
Neg logit contributions | |
hran | -2.701 |
clair | -2.670 |
Ul | -2.625 |
rily | -2.516 |
Tanz | -2.430 |
Token | - |
Token ID | 12 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
clair | +0.365 |
hran | +0.363 |
Ul | +0.354 |
rily | +0.333 |
Tanz | +0.323 |
Neg logit contributions | |
`` | -0.478 |
HL | -0.461 |
subs | -0.442 |
ESV | -0.441 |
ousse | -0.429 |
Token | Jones |
Token ID | 25784 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
Ul | +1.190 |
clair | +1.172 |
hran | +1.112 |
rily | +0.993 |
trump | +0.984 |
Neg logit contributions | |
HL | -2.292 |
`` | -2.290 |
ESV | -2.227 |
subs | -2.203 |
Dise | -2.188 |
Token | sees |
Token ID | 7224 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
`` | +0.537 |
HL | +0.517 |
subs | +0.494 |
ESV | +0.494 |
ousse | +0.479 |
Neg logit contributions | |
clair | -0.471 |
hran | -0.470 |
Ul | -0.459 |
rily | -0.434 |
Tanz | -0.421 |
Token | it |
Token ID | 340 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
`` | +1.242 |
HL | +1.202 |
subs | +1.157 |
ESV | +1.143 |
`` | +1.116 |
Neg logit contributions | |
clair | -1.120 |
hran | -1.114 |
Ul | -1.089 |
rily | -1.026 |
Tanz | -0.996 |
Token | this |
Token ID | 428 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
clair | +0.146 |
hran | +0.146 |
Ul | +0.143 |
rily | +0.135 |
Tanz | +0.131 |
Neg logit contributions | |
`` | -0.164 |
HL | -0.158 |
subs | -0.151 |
ESV | -0.151 |
ousse | -0.146 |
Token | way |
Token ID | 835 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
`` | +2.092 |
HL | +1.965 |
ESV | +1.813 |
subs | +1.804 |
`` | +1.763 |
Neg logit contributions | |
clair | -4.360 |
hran | -4.328 |
Ul | -4.223 |
rily | -4.065 |
Tanz | -4.030 |
Token | : |
Token ID | 25 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
`` | +1.904 |
HL | +1.818 |
subs | +1.748 |
ESV | +1.732 |
`` | +1.715 |
Neg logit contributions | |
hran | -1.768 |
clair | -1.746 |
Ul | -1.707 |
rily | -1.611 |
Tanz | -1.576 |
Token | " |
Token ID | 366 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
`` | +1.805 |
HL | +1.740 |
subs | +1.672 |
ESV | +1.652 |
`` | +1.625 |
Neg logit contributions | |
hran | -1.650 |
clair | -1.646 |
Ul | -1.604 |
rily | -1.514 |
Tanz | -1.468 |
Token | I |
Token ID | 40 |
Feature activation | -2.94e-03 |
Pos logit contributions | |
`` | +1.655 |
HL | +1.551 |
subs | +1.474 |
ESV | +1.462 |
`` | +1.413 |
Neg logit contributions | |
hran | -2.034 |
clair | -2.015 |
Ul | -1.945 |
rily | -1.894 |
Tanz | -1.863 |
Token | 'm |
Token ID | 1101 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
`` | +0.027 |
HL | +0.026 |
ESV | +0.025 |
subs | +0.024 |
ousse | +0.024 |
Neg logit contributions | |
clair | -0.023 |
hran | -0.023 |
Ul | -0.022 |
rily | -0.021 |
Tanz | -0.020 |
Token | licking |
Token ID | 43390 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
hran | +2.061 |
clair | +2.047 |
Ul | +2.007 |
rily | +1.914 |
Tanz | +1.844 |
Neg logit contributions | |
`` | -2.265 |
HL | -2.179 |
ESV | -2.096 |
ousse | -2.059 |
subs | -2.057 |
Token | of |
Token ID | 286 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
clair | +1.036 |
hran | +1.025 |
Ul | +1.023 |
rily | +0.955 |
Ros | +0.928 |
Neg logit contributions | |
`` | -1.363 |
HL | -1.313 |
ESV | -1.270 |
ousse | -1.260 |
Dise | -1.250 |
Token | workers |
Token ID | 3259 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
hran | +0.801 |
clair | +0.799 |
Ul | +0.784 |
rily | +0.747 |
Tanz | +0.725 |
Neg logit contributions | |
`` | -0.799 |
HL | -0.764 |
ESV | -0.729 |
subs | -0.725 |
ousse | -0.709 |
Token | , |
Token ID | 11 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
clair | +1.075 |
hran | +1.072 |
Ul | +1.046 |
rily | +0.991 |
Tanz | +0.959 |
Neg logit contributions | |
`` | -1.196 |
HL | -1.156 |
ESV | -1.108 |
subs | -1.097 |
ousse | -1.072 |
Token | politicians |
Token ID | 7602 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
hran | +1.085 |
clair | +1.084 |
Ul | +1.061 |
rily | +1.011 |
Tanz | +0.979 |
Neg logit contributions | |
`` | -1.107 |
HL | -1.064 |
ESV | -1.013 |
subs | -1.006 |
ousse | -0.988 |
Token | who |
Token ID | 508 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
`` | +0.891 |
HL | +0.859 |
subs | +0.823 |
ESV | +0.812 |
`` | +0.791 |
Neg logit contributions | |
clair | -0.876 |
hran | -0.875 |
Ul | -0.858 |
rily | -0.813 |
Tanz | -0.788 |
Token | p |
Token ID | 279 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
`` | +1.051 |
HL | +1.012 |
subs | +0.971 |
ESV | +0.962 |
`` | +0.934 |
Neg logit contributions | |
clair | -1.000 |
hran | -1.000 |
Ul | -0.979 |
rily | -0.924 |
Tanz | -0.900 |
Token | ander |
Token ID | 4066 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
`` | +5.352 |
HL | +5.051 |
ousse | +4.877 |
subs | +4.831 |
ESV | +4.827 |
Neg logit contributions | |
hran | -4.806 |
clair | -4.604 |
Ul | -4.584 |
Tanz | -4.575 |
rily | -4.204 |
Token | to |
Token ID | 284 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
clair | +0.090 |
hran | +0.090 |
Ul | +0.088 |
rily | +0.083 |
Tanz | +0.082 |
Neg logit contributions | |
`` | -0.087 |
HL | -0.084 |
subs | -0.080 |
ESV | -0.079 |
`` | -0.077 |
Token | donors |
Token ID | 13334 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
`` | +2.039 |
HL | +1.989 |
subs | +1.927 |
ESV | +1.867 |
`` | +1.840 |
Neg logit contributions | |
clair | -1.918 |
hran | -1.917 |
Ul | -1.866 |
rily | -1.775 |
Tanz | -1.716 |
Token | not |
Token ID | 407 |
Feature activation | -4.20e-03 |
Pos logit contributions | |
`` | +2.029 |
HL | +1.955 |
subs | +1.882 |
ESV | +1.841 |
`` | +1.809 |
Neg logit contributions | |
hran | -2.061 |
clair | -2.053 |
Ul | -2.019 |
rily | -1.922 |
Tanz | -1.856 |
Token | voters |
Token ID | 4446 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
`` | +0.035 |
HL | +0.034 |
subs | +0.033 |
ESV | +0.032 |
ousse | +0.031 |
Neg logit contributions | |
clair | -0.036 |
hran | -0.036 |
Ul | -0.035 |
rily | -0.033 |
Tanz | -0.032 |
Token | that |
Token ID | 326 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
`` | +2.518 |
HL | +2.439 |
subs | +2.359 |
ESV | +2.291 |
`` | +2.272 |
Neg logit contributions | |
clair | -2.511 |
hran | -2.511 |
Ul | -2.448 |
rily | -2.314 |
Tanz | -2.251 |
Token | in |
Token ID | 287 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
`` | +2.422 |
HL | +2.311 |
subs | +2.199 |
`` | +2.108 |
ESV | +2.096 |
Neg logit contributions | |
clair | -4.013 |
hran | -3.968 |
Ul | -3.916 |
rily | -3.759 |
Tanz | -3.668 |
Token | oil |
Token ID | 3056 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
clair | +0.123 |
hran | +0.123 |
Ul | +0.120 |
rily | +0.114 |
Tanz | +0.111 |
Neg logit contributions | |
`` | -0.129 |
HL | -0.124 |
subs | -0.118 |
ESV | -0.118 |
ousse | -0.114 |
Token | - |
Token ID | 12 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
`` | +2.308 |
HL | +2.202 |
subs | +2.149 |
ESV | +2.087 |
`` | +2.047 |
Neg logit contributions | |
clair | -2.620 |
hran | -2.589 |
Ul | -2.573 |
rily | -2.412 |
Tanz | -2.392 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
`` | +1.479 |
HL | +1.394 |
subs | +1.361 |
ESV | +1.332 |
`` | +1.303 |
Neg logit contributions | |
hran | -1.290 |
clair | -1.280 |
Ul | -1.253 |
Tanz | -1.180 |
rily | -1.171 |
Token | gas |
Token ID | 3623 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
`` | +0.134 |
HL | +0.130 |
subs | +0.125 |
ESV | +0.124 |
`` | +0.120 |
Neg logit contributions | |
clair | -0.114 |
hran | -0.114 |
Ul | -0.111 |
rily | -0.104 |
Tanz | -0.102 |
Token | - |
Token ID | 12 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
`` | +4.612 |
HL | +4.431 |
subs | +4.389 |
`` | +4.187 |
permitting | +4.153 |
Neg logit contributions | |
clair | -5.218 |
hran | -5.106 |
Ul | -5.059 |
Tanz | -4.749 |
rily | -4.731 |
Token | related |
Token ID | 5363 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
`` | +0.511 |
HL | +0.490 |
subs | +0.475 |
ESV | +0.470 |
ousse | +0.459 |
Neg logit contributions | |
hran | -0.361 |
clair | -0.360 |
Ul | -0.350 |
rily | -0.326 |
Tanz | -0.322 |
Token | matters |
Token ID | 6067 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
`` | +1.842 |
HL | +1.772 |
subs | +1.698 |
ESV | +1.664 |
`` | +1.618 |
Neg logit contributions | |
clair | -2.325 |
hran | -2.316 |
Ul | -2.272 |
rily | -2.155 |
Tanz | -2.107 |
Token | . |
Token ID | 13 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
`` | +0.981 |
HL | +0.947 |
subs | +0.908 |
ESV | +0.898 |
`` | +0.880 |
Neg logit contributions | |
clair | -0.855 |
hran | -0.855 |
Ul | -0.834 |
rily | -0.790 |
Tanz | -0.764 |
Token |
|
Token ID | 198 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
`` | +2.400 |
HL | +2.295 |
subs | +2.155 |
`` | +2.121 |
ESV | +2.109 |
Neg logit contributions | |
clair | -2.921 |
hran | -2.907 |
Ul | -2.831 |
rily | -2.715 |
Tanz | -2.633 |
Token | - |
Token ID | 12 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
`` | +2.385 |
HL | +2.337 |
ESV | +2.229 |
subs | +2.215 |
Lange | +2.145 |
Neg logit contributions | |
clair | -2.329 |
hran | -2.309 |
Ul | -2.202 |
rily | -2.115 |
trump | -2.042 |
Token | Car |
Token ID | 9914 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
Ul | +3.638 |
clair | +3.574 |
hran | +3.499 |
rily | +3.254 |
trump | +3.249 |
Neg logit contributions | |
`` | -3.409 |
HL | -3.332 |
ESV | -3.219 |
subs | -3.217 |
`` | -3.096 |
Token | Crash |
Token ID | 23653 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
clair | +0.330 |
hran | +0.329 |
Ul | +0.322 |
rily | +0.305 |
Tanz | +0.296 |
Neg logit contributions | |
`` | -0.360 |
HL | -0.347 |
subs | -0.331 |
ESV | -0.331 |
ousse | -0.319 |
Token | Comedy |
Token ID | 22329 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
`` | +1.205 |
HL | +1.179 |
subs | +1.117 |
ESV | +1.112 |
Lange | +1.079 |
Neg logit contributions | |
clair | -1.191 |
hran | -1.181 |
Ul | -1.149 |
rily | -1.080 |
Tanz | -1.043 |
Token | 200 |
Token ID | 939 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
`` | +1.501 |
HL | +1.472 |
subs | +1.399 |
ESV | +1.396 |
Lange | +1.360 |
Neg logit contributions | |
clair | -1.435 |
hran | -1.431 |
Ul | -1.389 |
rily | -1.313 |
trump | -1.262 |
Token | 80 |
Token ID | 1795 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
`` | +0.584 |
HL | +0.564 |
subs | +0.540 |
ESV | +0.537 |
ousse | +0.521 |
Neg logit contributions | |
clair | -0.522 |
hran | -0.518 |
Ul | -0.515 |
rily | -0.479 |
Tanz | -0.467 |
Token | 206 |
Token ID | 22136 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
`` | +3.526 |
HL | +3.238 |
subs | +3.007 |
`` | +2.913 |
ESV | +2.913 |
Neg logit contributions | |
clair | -6.649 |
hran | -6.551 |
rily | -6.431 |
Tanz | -6.395 |
Ul | -6.382 |
Token | O |
Token ID | 440 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Ul | +2.200 |
Ros | +2.072 |
hran | +2.006 |
clair | +1.938 |
Tanz | +1.830 |
Neg logit contributions | |
`` | -4.823 |
senal | -4.582 |
subs | -4.559 |
HL | -4.538 |
ousse | -4.533 |
Token | & |
Token ID | 5 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Ul | +1.238 |
clair | +1.218 |
hran | +1.190 |
rily | +1.110 |
trump | +1.088 |
Neg logit contributions | |
`` | -1.325 |
HL | -1.302 |
subs | -1.262 |
ESV | -1.253 |
Dise | -1.241 |
Token | A |
Token ID | 32 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Ul | +1.854 |
hran | +1.749 |
clair | +1.737 |
rily | +1.601 |
Ros | +1.587 |
Neg logit contributions | |
`` | -2.076 |
HL | -2.039 |
subs | -1.980 |
ESV | -1.972 |
Dise | -1.966 |
Token | - |
Token ID | 12 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
Ul | +1.091 |
clair | +1.080 |
hran | +1.060 |
rily | +0.965 |
Ros | +0.958 |
Neg logit contributions | |
`` | -1.756 |
HL | -1.706 |
subs | -1.675 |
ESV | -1.649 |
ousse | -1.644 |
Token | a |
Token ID | 64 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
`` | +1.881 |
HL | +1.807 |
subs | +1.727 |
ESV | +1.720 |
ousse | +1.669 |
Neg logit contributions | |
clair | -1.794 |
hran | -1.791 |
Ul | -1.749 |
rily | -1.660 |
Tanz | -1.616 |
Token | . |
Token ID | 13 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
hran | +0.341 |
clair | +0.341 |
Ul | +0.334 |
rily | +0.314 |
Tanz | +0.304 |
Neg logit contributions | |
`` | -0.419 |
HL | -0.403 |
subs | -0.386 |
ESV | -0.386 |
ousse | -0.374 |
Token |
|
Token ID | 198 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
clair | +0.330 |
hran | +0.330 |
Ul | +0.325 |
rily | +0.307 |
Tanz | +0.300 |
Neg logit contributions | |
`` | -0.326 |
HL | -0.312 |
subs | -0.300 |
ESV | -0.298 |
ousse | -0.290 |
Token |
|
Token ID | 198 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
`` | +0.548 |
HL | +0.530 |
ESV | +0.508 |
subs | +0.507 |
ousse | +0.493 |
Neg logit contributions | |
clair | -0.525 |
hran | -0.521 |
Ul | -0.517 |
rily | -0.485 |
Tanz | -0.468 |
Token | For |
Token ID | 1890 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
`` | +0.420 |
HL | +0.403 |
subs | +0.383 |
ESV | +0.382 |
ousse | +0.369 |
Neg logit contributions | |
hran | -0.442 |
clair | -0.442 |
Ul | -0.430 |
rily | -0.411 |
Tanz | -0.400 |
Token | a |
Token ID | 257 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
`` | +1.652 |
HL | +1.616 |
subs | +1.536 |
ESV | +1.523 |
Lange | +1.478 |
Neg logit contributions | |
hran | -1.639 |
clair | -1.638 |
Ul | -1.579 |
rily | -1.503 |
Tanz | -1.458 |
Token | gallery |
Token ID | 15604 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
`` | +5.180 |
HL | +5.155 |
subs | +4.954 |
ESV | +4.770 |
Lange | +4.632 |
Neg logit contributions | |
hran | -5.423 |
clair | -5.374 |
Ul | -5.168 |
rily | -4.974 |
Tanz | -4.824 |
Token | of |
Token ID | 286 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
`` | +1.375 |
HL | +1.317 |
subs | +1.262 |
ESV | +1.248 |
`` | +1.210 |
Neg logit contributions | |
hran | -1.375 |
clair | -1.372 |
Ul | -1.346 |
rily | -1.282 |
Tanz | -1.244 |
Token | today |
Token ID | 1909 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
`` | +2.103 |
HL | +2.054 |
subs | +1.961 |
ESV | +1.939 |
Lange | +1.882 |
Neg logit contributions | |
clair | -2.066 |
hran | -2.058 |
Ul | -1.999 |
rily | -1.907 |
Tanz | -1.833 |
Token | 's |
Token ID | 338 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
clair | +0.789 |
hran | +0.788 |
Ul | +0.770 |
rily | +0.728 |
Tanz | +0.707 |
Neg logit contributions | |
`` | -0.882 |
HL | -0.851 |
subs | -0.813 |
ESV | -0.811 |
ousse | -0.785 |
Token | photos |
Token ID | 5205 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
hran | +0.406 |
clair | +0.406 |
Ul | +0.400 |
rily | +0.379 |
Tanz | +0.372 |
Neg logit contributions | |
`` | -0.388 |
HL | -0.367 |
ESV | -0.351 |
subs | -0.350 |
ousse | -0.342 |
Token | xual |
Token ID | 5541 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
`` | +2.704 |
HL | +2.581 |
subs | +2.500 |
ESV | +2.439 |
ousse | +2.431 |
Neg logit contributions | |
hran | -2.175 |
clair | -2.155 |
Ul | -2.133 |
rily | -2.012 |
Tanz | -1.976 |
Token | th |
Token ID | 400 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
hran | +0.190 |
clair | +0.190 |
Ul | +0.185 |
rily | +0.173 |
Tanz | +0.168 |
Neg logit contributions | |
`` | -0.288 |
HL | -0.278 |
subs | -0.269 |
ESV | -0.267 |
ousse | -0.260 |
Token | ug |
Token ID | 1018 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
clair | +3.549 |
hran | +3.521 |
Ul | +3.496 |
rily | +3.278 |
trump | +3.203 |
Neg logit contributions | |
`` | -3.579 |
HL | -3.554 |
ESV | -3.378 |
subs | -3.337 |
Lange | -3.270 |
Token | > |
Token ID | 29 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
clair | +0.261 |
hran | +0.261 |
Ul | +0.253 |
rily | +0.236 |
Tanz | +0.226 |
Neg logit contributions | |
`` | -0.431 |
HL | -0.418 |
subs | -0.403 |
ESV | -0.402 |
ousse | -0.391 |
Token | lol |
Token ID | 19462 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
`` | +1.429 |
HL | +1.387 |
subs | +1.326 |
ESV | +1.314 |
`` | +1.273 |
Neg logit contributions | |
clair | -1.388 |
hran | -1.386 |
Ul | -1.352 |
rily | -1.284 |
Tanz | -1.243 |
Token | m |
Token ID | 285 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
clair | +1.263 |
hran | +1.262 |
Ul | +1.237 |
rily | +1.176 |
Tanz | +1.147 |
Neg logit contributions | |
`` | -1.040 |
HL | -0.988 |
ESV | -0.939 |
subs | -0.936 |
ousse | -0.905 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
`` | +5.399 |
HL | +5.126 |
ousse | +4.958 |
subs | +4.927 |
ESV | +4.835 |
Neg logit contributions | |
hran | -5.178 |
clair | -5.127 |
Ul | -5.004 |
Tanz | -4.915 |
rily | -4.795 |
Token | k |
Token ID | 74 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
`` | +2.176 |
HL | +2.120 |
subs | +2.033 |
ESV | +2.002 |
ousse | +1.938 |
Neg logit contributions | |
clair | -2.027 |
hran | -2.016 |
Ul | -1.986 |
rily | -1.871 |
Tanz | -1.839 |
Token | [ |
Token ID | 685 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
`` | +0.492 |
HL | +0.475 |
subs | +0.454 |
ESV | +0.449 |
ousse | +0.434 |
Neg logit contributions | |
clair | -0.534 |
hran | -0.533 |
Ul | -0.523 |
rily | -0.497 |
Tanz | -0.485 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Ul | +2.186 |
clair | +2.179 |
hran | +2.058 |
trump | +1.908 |
rily | +1.853 |
Neg logit contributions | |
HL | -3.971 |
`` | -3.955 |
Dise | -3.888 |
ESV | -3.828 |
subs | -3.803 |
Token | : |
Token ID | 25 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
`` | +1.321 |
HL | +1.279 |
subs | +1.228 |
ESV | +1.226 |
ousse | +1.194 |
Neg logit contributions | |
clair | -1.013 |
hran | -1.009 |
Ul | -0.993 |
rily | -0.928 |
Tanz | -0.893 |