Token | m |
Token ID | 76 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ades | +1.533 |
emi | +1.451 |
ade | +1.338 |
ghai | +1.291 |
anging | +1.265 |
Neg logit contributions | |
senal | -1.647 |
experien | -1.644 |
racuse | -1.599 |
hers | -1.591 |
lette | -1.549 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
hers | +0.987 |
lette | +0.964 |
experien | +0.964 |
racuse | +0.962 |
pict | +0.934 |
Neg logit contributions | |
ades | -1.480 |
emi | -1.403 |
ade | -1.302 |
ghai | -1.278 |
anging | -1.275 |
Token | ... |
Token ID | 2644 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
ades | +0.669 |
emi | +0.634 |
ade | +0.579 |
anging | +0.565 |
ghai | +0.563 |
Neg logit contributions | |
hers | -0.633 |
racuse | -0.625 |
lette | -0.624 |
experien | -0.619 |
Admin | -0.600 |
Token | after |
Token ID | 706 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
ades | +3.133 |
emi | +2.921 |
ade | +2.721 |
anging | +2.638 |
ghai | +2.587 |
Neg logit contributions | |
racuse | -3.054 |
lette | -3.020 |
experien | -3.005 |
hers | -2.990 |
senal | -2.965 |
Token | a |
Token ID | 257 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
ades | +1.501 |
emi | +1.371 |
ade | +1.282 |
anging | +1.224 |
ghai | +1.219 |
Neg logit contributions | |
racuse | -1.519 |
experien | -1.489 |
hers | -1.486 |
lette | -1.476 |
senal | -1.462 |
Token | prim |
Token ID | 2684 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
ades | +0.433 |
emi | +0.404 |
ade | +0.373 |
anging | +0.362 |
ghai | +0.355 |
Neg logit contributions | |
racuse | -0.419 |
hers | -0.413 |
experien | -0.407 |
pict | -0.405 |
lette | -0.404 |
Token | etime |
Token ID | 8079 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
hers | +11.069 |
lette | +11.008 |
tv | +10.636 |
pict | +10.519 |
ento | +10.502 |
Neg logit contributions | |
ades | -10.528 |
emi | -10.077 |
ghai | -9.436 |
reditary | -8.735 |
anging | -8.728 |
Token | playoff |
Token ID | 13119 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
hers | +3.555 |
lette | +3.486 |
experien | +3.461 |
racuse | +3.451 |
pict | +3.373 |
Neg logit contributions | |
ades | -3.971 |
emi | -3.743 |
ade | -3.427 |
ghai | -3.389 |
anging | -3.351 |
Token | game |
Token ID | 983 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
racuse | +0.544 |
hers | +0.541 |
senal | +0.523 |
experien | +0.523 |
pict | +0.521 |
Neg logit contributions | |
ades | -0.531 |
emi | -0.494 |
ade | -0.463 |
anging | -0.436 |
ghai | -0.426 |
Token | ... |
Token ID | 2644 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
hers | +3.583 |
lette | +3.506 |
experien | +3.471 |
racuse | +3.470 |
pict | +3.381 |
Neg logit contributions | |
ades | -4.785 |
emi | -4.524 |
ade | -4.184 |
ghai | -4.132 |
anging | -4.088 |
Token | that |
Token ID | 326 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
ades | +3.766 |
emi | +3.475 |
ade | +3.247 |
anging | +3.099 |
ghai | +3.073 |
Neg logit contributions | |
racuse | -3.655 |
senal | -3.601 |
lette | -3.572 |
hers | -3.563 |
experien | -3.563 |
Token | Power |
Token ID | 13434 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
ades | +0.980 |
emi | +0.900 |
ade | +0.865 |
ghai | +0.821 |
anging | +0.803 |
Neg logit contributions | |
experien | -0.879 |
racuse | -0.868 |
lette | -0.861 |
hers | -0.849 |
senal | -0.844 |
Token | , |
Token ID | 11 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
hers | +1.137 |
experien | +1.135 |
racuse | +1.119 |
lette | +1.109 |
pict | +1.078 |
Neg logit contributions | |
ades | -1.335 |
emi | -1.267 |
ade | -1.173 |
ghai | -1.142 |
anging | -1.114 |
Token | @ |
Token ID | 2488 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
hers | +1.113 |
lette | +1.087 |
experien | +1.082 |
racuse | +1.080 |
pict | +1.051 |
Neg logit contributions | |
ades | -1.546 |
emi | -1.460 |
ade | -1.357 |
ghai | -1.331 |
anging | -1.319 |
Token | P |
Token ID | 47 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ades | +1.219 |
emi | +1.136 |
ade | +1.076 |
ghai | +1.017 |
anging | +1.011 |
Neg logit contributions | |
experien | -0.980 |
hers | -0.956 |
racuse | -0.949 |
lette | -0.939 |
senal | -0.915 |
Token | OWER |
Token ID | 36048 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
experien | +1.902 |
hers | +1.898 |
racuse | +1.868 |
lette | +1.856 |
pict | +1.832 |
Neg logit contributions | |
ades | -1.772 |
emi | -1.660 |
ade | -1.521 |
ghai | -1.472 |
anging | -1.465 |
Token | mag |
Token ID | 19726 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
hers | +1.329 |
experien | +1.327 |
racuse | +1.304 |
lette | +1.300 |
ento | +1.247 |
Neg logit contributions | |
ades | -1.629 |
emi | -1.537 |
ade | -1.429 |
ghai | -1.393 |
anging | -1.371 |
Token | azine |
Token ID | 4994 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
hers | +9.965 |
lette | +9.751 |
racuse | +9.659 |
pict | +9.639 |
ento | +9.569 |
Neg logit contributions | |
ades | -11.146 |
emi | -10.465 |
ghai | -9.645 |
anging | -9.550 |
ade | -9.462 |
Token | ) |
Token ID | 8 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
hers | +4.057 |
lette | +3.973 |
racuse | +3.950 |
experien | +3.933 |
pict | +3.871 |
Neg logit contributions | |
ades | -4.834 |
emi | -4.556 |
ade | -4.183 |
ghai | -4.145 |
anging | -4.101 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
ades | +1.921 |
emi | +1.812 |
ade | +1.604 |
ghai | +1.563 |
anging | +1.551 |
Neg logit contributions | |
experien | -2.396 |
hers | -2.390 |
lette | -2.376 |
racuse | -2.376 |
ento | -2.301 |
Token | C |
Token ID | 34 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ades | +2.680 |
emi | +2.512 |
ade | +2.401 |
anging | +2.267 |
aye | +2.230 |
Neg logit contributions | |
racuse | -2.153 |
senal | -2.140 |
experien | -2.140 |
hers | -2.071 |
lette | -2.031 |
Token | it |
Token ID | 270 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
experien | +0.626 |
racuse | +0.625 |
hers | +0.625 |
lette | +0.619 |
pict | +0.613 |
Neg logit contributions | |
ades | -0.598 |
emi | -0.553 |
ade | -0.511 |
anging | -0.492 |
ghai | -0.489 |
Token | gl |
Token ID | 4743 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
hers | +2.004 |
experien | +1.971 |
racuse | +1.961 |
lette | +1.955 |
pict | +1.903 |
Neg logit contributions | |
ades | -2.372 |
emi | -2.232 |
ade | -2.068 |
ghai | -2.034 |
anging | -2.005 |
Token | ove |
Token ID | 659 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
ades | +4.581 |
ade | +3.820 |
emi | +3.484 |
end | +3.108 |
anging | +3.096 |
Neg logit contributions | |
senal | -6.598 |
experien | -6.597 |
hers | -6.350 |
lette | -6.181 |
racuse | -6.136 |
Token | Courier |
Token ID | 34268 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
ades | +2.311 |
emi | +2.119 |
ade | +2.036 |
ghai | +1.967 |
anging | +1.853 |
Neg logit contributions | |
experien | -2.474 |
racuse | -2.450 |
hers | -2.439 |
pict | -2.374 |
senal | -2.373 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
experien | +0.318 |
hers | +0.318 |
racuse | +0.316 |
lette | +0.309 |
pict | +0.307 |
Neg logit contributions | |
ades | -0.324 |
emi | -0.298 |
ade | -0.279 |
ghai | -0.270 |
anging | -0.262 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
hers | +0.327 |
lette | +0.319 |
racuse | +0.318 |
experien | +0.317 |
pict | +0.310 |
Neg logit contributions | |
ades | -0.377 |
emi | -0.355 |
ade | -0.326 |
ghai | -0.322 |
anging | -0.318 |
Token | Prim |
Token ID | 23828 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
ades | +0.587 |
emi | +0.552 |
ade | +0.521 |
ghai | +0.496 |
anging | +0.492 |
Neg logit contributions | |
experien | -0.525 |
racuse | -0.519 |
hers | -0.514 |
lette | -0.502 |
senal | -0.502 |
Token | al |
Token ID | 282 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
hers | +10.227 |
lette | +10.092 |
itives | +9.949 |
pict | +9.597 |
Admin | +9.573 |
Neg logit contributions | |
ades | -9.768 |
emi | -9.518 |
ghai | -8.554 |
anging | -8.503 |
�� | -8.311 |
Token | Surge |
Token ID | 46774 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
hers | +3.260 |
experien | +3.201 |
lette | +3.196 |
racuse | +3.193 |
pict | +3.127 |
Neg logit contributions | |
ades | -2.618 |
emi | -2.429 |
ade | -2.205 |
ghai | -2.157 |
anging | -2.118 |
Token | vs |
Token ID | 3691 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
hers | +1.435 |
experien | +1.412 |
racuse | +1.402 |
lette | +1.400 |
pict | +1.376 |
Neg logit contributions | |
ades | -1.698 |
emi | -1.579 |
ade | -1.477 |
ghai | -1.452 |
anging | -1.420 |
Token | Safe |
Token ID | 19978 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
hers | +2.281 |
lette | +2.240 |
racuse | +2.236 |
experien | +2.232 |
pict | +2.186 |
Neg logit contributions | |
ades | -1.992 |
emi | -1.851 |
ade | -1.692 |
ghai | -1.654 |
anging | -1.627 |
Token | Passage |
Token ID | 46169 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
ades | +2.555 |
emi | +2.324 |
ade | +2.246 |
ghai | +2.204 |
anging | +2.103 |
Neg logit contributions | |
experien | -2.629 |
racuse | -2.568 |
senal | -2.507 |
hers | -2.488 |
lette | -2.482 |
Token | � |
Token ID | 447 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
ades | +1.529 |
emi | +1.468 |
ade | +1.335 |
ghai | +1.276 |
ratification | +1.252 |
Neg logit contributions | |
racuse | -1.422 |
hers | -1.368 |
experien | -1.351 |
lette | -1.337 |
pict | -1.319 |
Token | � |
Token ID | 247 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ades | +0.693 |
emi | +0.624 |
ade | +0.563 |
ghai | +0.541 |
anging | +0.525 |
Neg logit contributions | |
racuse | -1.211 |
hers | -1.204 |
lette | -1.199 |
experien | -1.195 |
pict | -1.173 |
Token | s |
Token ID | 82 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ades | +0.901 |
emi | +0.847 |
ade | +0.791 |
ghai | +0.755 |
anging | +0.743 |
Neg logit contributions | |
racuse | -0.777 |
hers | -0.747 |
experien | -0.740 |
lette | -0.739 |
pict | -0.723 |
Token | anti |
Token ID | 3098 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ades | +0.687 |
emi | +0.647 |
ade | +0.597 |
ghai | +0.575 |
anging | +0.570 |
Neg logit contributions | |
racuse | -0.606 |
hers | -0.604 |
lette | -0.591 |
experien | -0.584 |
pict | -0.575 |
Token | - |
Token ID | 12 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
ades | +0.644 |
emi | +0.609 |
ade | +0.565 |
ghai | +0.546 |
anging | +0.544 |
Neg logit contributions | |
hers | -0.545 |
racuse | -0.543 |
experien | -0.539 |
lette | -0.528 |
pict | -0.515 |
Token | Pet |
Token ID | 25803 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
racuse | +0.998 |
experien | +0.980 |
hers | +0.973 |
lette | +0.950 |
pict | +0.918 |
Neg logit contributions | |
ades | -1.201 |
emi | -1.130 |
ade | -1.055 |
ghai | -1.005 |
anging | -1.003 |
Token | ro |
Token ID | 305 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
hers | +5.396 |
lette | +5.115 |
ras | +4.905 |
racuse | +4.746 |
Admin | +4.685 |
Neg logit contributions | |
ades | -14.841 |
emi | -14.220 |
ghai | -13.687 |
anging | -13.385 |
ade | -13.331 |
Token | car |
Token ID | 7718 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
hers | +3.408 |
lette | +3.376 |
experien | +3.220 |
pict | +3.213 |
racuse | +3.211 |
Neg logit contributions | |
ades | -5.081 |
emi | -4.831 |
ade | -4.447 |
ghai | -4.413 |
anging | -4.404 |
Token | ibe |
Token ID | 32438 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
hers | +0.244 |
lette | +0.240 |
racuse | +0.240 |
experien | +0.239 |
pict | +0.235 |
Neg logit contributions | |
ades | -0.185 |
emi | -0.172 |
ade | -0.155 |
ghai | -0.151 |
anging | -0.149 |
Token | position |
Token ID | 2292 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
hers | +1.520 |
racuse | +1.499 |
lette | +1.485 |
experien | +1.474 |
pict | +1.446 |
Neg logit contributions | |
ades | -1.749 |
emi | -1.645 |
ade | -1.522 |
ghai | -1.485 |
anging | -1.471 |
Token | and |
Token ID | 290 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ades | +0.220 |
emi | +0.206 |
ade | +0.191 |
ghai | +0.183 |
anging | +0.182 |
Neg logit contributions | |
racuse | -0.207 |
hers | -0.204 |
experien | -0.202 |
lette | -0.202 |
pict | -0.196 |
Token | meet |
Token ID | 1826 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
hers | +0.946 |
racuse | +0.932 |
lette | +0.928 |
experien | +0.922 |
pict | +0.909 |
Neg logit contributions | |
ades | -1.048 |
emi | -0.984 |
ade | -0.913 |
ghai | -0.891 |
anging | -0.882 |
Token | those |
Token ID | 883 |
Feature activation | +6.16e-03 |
Pos logit contributions | |
hers | +5.017 |
lette | +4.894 |
racuse | +4.853 |
experien | +4.847 |
pict | +4.721 |
Neg logit contributions | |
ades | -5.394 |
emi | -5.072 |
ghai | -4.637 |
ade | -4.613 |
anging | -4.532 |
Token | numbers |
Token ID | 3146 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
racuse | +0.019 |
lette | +0.019 |
hers | +0.019 |
experien | +0.019 |
Admin | +0.018 |
Neg logit contributions | |
ades | -0.021 |
emi | -0.020 |
ade | -0.019 |
ghai | -0.018 |
anging | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
ades | +0.246 |
emi | +0.230 |
ade | +0.214 |
anging | +0.206 |
ghai | +0.205 |
Neg logit contributions | |
racuse | -0.210 |
hers | -0.209 |
experien | -0.207 |
senal | -0.206 |
lette | -0.206 |
Token | then |
Token ID | 788 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
hers | +0.501 |
racuse | +0.494 |
lette | +0.493 |
experien | +0.490 |
pict | +0.483 |
Neg logit contributions | |
ades | -0.458 |
emi | -0.426 |
ade | -0.391 |
ghai | -0.377 |
anging | -0.375 |
Token | pit |
Token ID | 6028 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
ades | +1.771 |
emi | +1.635 |
ade | +1.567 |
ghai | +1.466 |
anging | +1.450 |
Neg logit contributions | |
racuse | -1.603 |
hers | -1.596 |
pict | -1.570 |
experien | -1.562 |
lette | -1.552 |
Token | Baylor |
Token ID | 28245 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
hers | +9.659 |
lette | +9.211 |
experien | +8.896 |
racuse | +8.764 |
pict | +8.708 |
Neg logit contributions | |
ades | -10.186 |
emi | -9.773 |
ghai | -9.283 |
anging | -8.734 |
azaki | -8.649 |
Token | 's |
Token ID | 338 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
hers | +1.914 |
racuse | +1.900 |
lette | +1.885 |
experien | +1.880 |
pict | +1.837 |
Neg logit contributions | |
ades | -2.649 |
emi | -2.498 |
ade | -2.330 |
ghai | -2.269 |
anging | -2.246 |
Token | small |
Token ID | 1402 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
racuse | +0.045 |
hers | +0.045 |
lette | +0.045 |
experien | +0.044 |
pict | +0.044 |
Neg logit contributions | |
ades | -0.050 |
emi | -0.046 |
ade | -0.043 |
ghai | -0.041 |
anging | -0.041 |
Token | backfield |
Token ID | 45747 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ades | +0.077 |
emi | +0.071 |
ade | +0.068 |
anging | +0.064 |
ghai | +0.064 |
Neg logit contributions | |
hers | -0.069 |
experien | -0.069 |
racuse | -0.068 |
lette | -0.068 |
Admin | -0.066 |
Token | against |
Token ID | 1028 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
racuse | +0.322 |
hers | +0.321 |
experien | +0.317 |
lette | +0.310 |
pict | +0.305 |
Neg logit contributions | |
ades | -0.517 |
emi | -0.479 |
ade | -0.459 |
ghai | -0.438 |
anging | -0.436 |
Token | / |
Token ID | 14 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
hers | +2.016 |
lette | +1.986 |
racuse | +1.983 |
experien | +1.963 |
pict | +1.937 |
Neg logit contributions | |
ades | -1.889 |
emi | -1.754 |
ade | -1.613 |
ghai | -1.573 |
anging | -1.551 |
Token | or |
Token ID | 273 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
hers | +4.351 |
lette | +4.116 |
Admin | +4.005 |
pict | +3.978 |
tv | +3.919 |
Neg logit contributions | |
ades | -7.059 |
emi | -6.724 |
ghai | -6.414 |
anging | -6.272 |
uberty | -6.237 |
Token | Survival |
Token ID | 20303 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
hers | +2.026 |
lette | +1.993 |
racuse | +1.990 |
experien | +1.980 |
pict | +1.941 |
Neg logit contributions | |
ades | -2.273 |
emi | -2.125 |
ade | -1.970 |
ghai | -1.930 |
anging | -1.906 |
Token | + |
Token ID | 10 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
hers | +4.338 |
lette | +4.245 |
racuse | +4.227 |
experien | +4.218 |
pict | +4.122 |
Neg logit contributions | |
ades | -4.907 |
emi | -4.616 |
ade | -4.245 |
ghai | -4.177 |
anging | -4.132 |
Token | The |
Token ID | 383 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
hers | +4.812 |
lette | +4.704 |
racuse | +4.671 |
experien | +4.668 |
pict | +4.567 |
Neg logit contributions | |
ades | -5.742 |
emi | -5.426 |
ade | -4.976 |
ghai | -4.937 |
anging | -4.875 |
Token | Prim |
Token ID | 11460 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
hers | +3.421 |
lette | +3.359 |
racuse | +3.350 |
experien | +3.342 |
pict | +3.275 |
Neg logit contributions | |
ades | -2.868 |
emi | -2.672 |
ade | -2.422 |
ghai | -2.364 |
anging | -2.335 |
Token | er |
Token ID | 263 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
hers | +9.876 |
itives | +9.711 |
lette | +9.709 |
pict | +9.352 |
entin | +9.240 |
Neg logit contributions | |
ades | -9.748 |
emi | -9.555 |
ghai | -8.674 |
anging | -8.521 |
aye | -8.348 |
Token | from |
Token ID | 422 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
hers | +3.634 |
lette | +3.545 |
racuse | +3.542 |
experien | +3.534 |
pict | +3.451 |
Neg logit contributions | |
ades | -4.234 |
emi | -3.981 |
ade | -3.675 |
ghai | -3.608 |
anging | -3.571 |
Token | your |
Token ID | 534 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
hers | +1.797 |
racuse | +1.762 |
lette | +1.762 |
experien | +1.749 |
pict | +1.714 |
Neg logit contributions | |
ades | -1.663 |
emi | -1.550 |
ade | -1.415 |
ghai | -1.372 |
anging | -1.369 |
Token | local |
Token ID | 1957 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
hers | +1.693 |
lette | +1.664 |
racuse | +1.659 |
experien | +1.636 |
pict | +1.617 |
Neg logit contributions | |
ades | -1.997 |
emi | -1.868 |
ade | -1.737 |
ghai | -1.688 |
anging | -1.685 |
Token | book |
Token ID | 1492 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
hers | +3.678 |
lette | +3.594 |
experien | +3.587 |
racuse | +3.556 |
pict | +3.470 |
Neg logit contributions | |
ades | -4.519 |
emi | -4.295 |
ade | -3.930 |
ghai | -3.913 |
anging | -3.866 |
Token | vs |
Token ID | 3691 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
ades | +1.377 |
emi | +1.283 |
ade | +1.191 |
ghai | +1.175 |
anging | +1.142 |
Neg logit contributions | |
experien | -1.228 |
hers | -1.225 |
racuse | -1.193 |
lette | -1.185 |
pict | -1.182 |
Token | Pyro |
Token ID | 44954 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
hers | +1.165 |
racuse | +1.146 |
lette | +1.145 |
experien | +1.143 |
pict | +1.118 |
Neg logit contributions | |
ades | -1.027 |
emi | -0.956 |
ade | -0.874 |
ghai | -0.851 |
anging | -0.838 |
Token | blast |
Token ID | 39806 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
hers | +4.248 |
lette | +4.157 |
experien | +4.149 |
racuse | +4.147 |
pict | +4.048 |
Neg logit contributions | |
ades | -4.378 |
emi | -4.104 |
ade | -3.759 |
ghai | -3.698 |
anging | -3.653 |
Token |
|
Token ID | 198 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
hers | +0.549 |
experien | +0.539 |
racuse | +0.536 |
lette | +0.536 |
pict | +0.524 |
Neg logit contributions | |
ades | -0.581 |
emi | -0.545 |
ade | -0.501 |
ghai | -0.492 |
anging | -0.483 |
Token |
|
Token ID | 198 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ades | +1.124 |
emi | +1.052 |
ade | +0.975 |
ghai | +0.943 |
anging | +0.936 |
Neg logit contributions | |
experien | -1.074 |
hers | -1.074 |
racuse | -1.069 |
senal | -1.068 |
lette | -1.057 |
Token | Prim |
Token ID | 23828 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
ades | +0.844 |
emi | +0.794 |
ade | +0.742 |
ghai | +0.710 |
anging | +0.708 |
Neg logit contributions | |
experien | -0.763 |
racuse | -0.755 |
hers | -0.749 |
lette | -0.737 |
senal | -0.729 |
Token | al |
Token ID | 282 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
hers | +8.047 |
lette | +7.905 |
itives | +7.780 |
pict | +7.511 |
Admin | +7.441 |
Neg logit contributions | |
ades | -11.342 |
emi | -10.957 |
ghai | -10.122 |
anging | -9.992 |
aye | -9.688 |
Token | Druid |
Token ID | 32685 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
hers | +2.442 |
experien | +2.403 |
lette | +2.394 |
racuse | +2.392 |
pict | +2.346 |
Neg logit contributions | |
ades | -1.931 |
emi | -1.786 |
ade | -1.629 |
ghai | -1.590 |
anging | -1.553 |
Token | vs |
Token ID | 3691 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
hers | +2.812 |
lette | +2.746 |
racuse | +2.742 |
experien | +2.741 |
pict | +2.672 |
Neg logit contributions | |
ades | -3.380 |
emi | -3.182 |
ade | -2.937 |
ghai | -2.892 |
anging | -2.854 |
Token | Er |
Token ID | 5256 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
hers | +1.649 |
lette | +1.624 |
racuse | +1.623 |
experien | +1.621 |
pict | +1.585 |
Neg logit contributions | |
ades | -1.458 |
emi | -1.355 |
ade | -1.240 |
ghai | -1.208 |
anging | -1.189 |
Token | t |
Token ID | 83 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
experien | +0.958 |
hers | +0.955 |
racuse | +0.935 |
lette | +0.934 |
pict | +0.916 |
Neg logit contributions | |
ades | -0.876 |
emi | -0.808 |
ade | -0.761 |
ghai | -0.726 |
anging | -0.721 |
Token | represent |
Token ID | 2380 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
hers | +0.502 |
racuse | +0.501 |
lette | +0.496 |
experien | +0.493 |
pict | +0.486 |
Neg logit contributions | |
ades | -0.551 |
emi | -0.518 |
ade | -0.479 |
ghai | -0.461 |
anging | -0.461 |
Token | different |
Token ID | 1180 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
hers | +1.516 |
racuse | +1.495 |
lette | +1.492 |
experien | +1.476 |
pict | +1.458 |
Neg logit contributions | |
ades | -1.631 |
emi | -1.524 |
ade | -1.403 |
ghai | -1.372 |
anging | -1.367 |
Token | segments |
Token ID | 17894 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
hers | +0.293 |
racuse | +0.289 |
lette | +0.287 |
experien | +0.282 |
pict | +0.282 |
Neg logit contributions | |
ades | -0.280 |
emi | -0.256 |
ade | -0.239 |
ghai | -0.233 |
anging | -0.230 |
Token | of |
Token ID | 286 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
ades | +2.643 |
emi | +2.422 |
ade | +2.230 |
ghai | +2.178 |
anging | +2.126 |
Neg logit contributions | |
racuse | -3.091 |
hers | -3.086 |
experien | -3.069 |
lette | -3.067 |
pict | -3.039 |
Token | the |
Token ID | 262 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
ades | +1.722 |
emi | +1.572 |
ade | +1.451 |
anging | +1.433 |
ghai | +1.398 |
Neg logit contributions | |
racuse | -1.876 |
pict | -1.870 |
lette | -1.866 |
hers | -1.861 |
senal | -1.820 |
Token | Mag |
Token ID | 2944 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
ades | +1.444 |
emi | +1.308 |
ade | +1.208 |
anging | +1.164 |
ghai | +1.163 |
Neg logit contributions | |
racuse | -1.886 |
lette | -1.881 |
hers | -1.878 |
pict | -1.850 |
experien | -1.833 |
Token | p |
Token ID | 79 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
hers | +8.190 |
lette | +7.752 |
ento | +7.546 |
pict | +7.338 |
experien | +7.317 |
Neg logit contributions | |
ades | -11.547 |
emi | -11.090 |
ghai | -10.285 |
ade | -10.117 |
anging | -10.032 |
Token | ies |
Token ID | 444 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
hers | +2.100 |
lette | +2.067 |
racuse | +2.067 |
experien | +2.061 |
pict | +2.023 |
Neg logit contributions | |
ades | -1.468 |
emi | -1.350 |
ade | -1.210 |
ghai | -1.179 |
anging | -1.163 |
Token | ' |
Token ID | 6 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
hers | +3.503 |
lette | +3.415 |
experien | +3.400 |
racuse | +3.388 |
pict | +3.313 |
Neg logit contributions | |
ades | -4.078 |
emi | -3.856 |
ade | -3.529 |
ghai | -3.491 |
anging | -3.453 |
Token | diverse |
Token ID | 10084 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
ades | +0.572 |
emi | +0.526 |
ade | +0.497 |
ghai | +0.483 |
anging | +0.477 |
Neg logit contributions | |
hers | -0.512 |
racuse | -0.511 |
lette | -0.510 |
experien | -0.494 |
pict | -0.494 |
Token | fan |
Token ID | 4336 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ades | +0.978 |
emi | +0.895 |
ade | +0.848 |
ghai | +0.817 |
anging | +0.805 |
Neg logit contributions | |
racuse | -0.925 |
hers | -0.924 |
lette | -0.913 |
pict | -0.893 |
experien | -0.889 |
Token | masturbation |
Token ID | 41054 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
racuse | +0.069 |
hers | +0.068 |
lette | +0.067 |
senal | +0.067 |
experien | +0.065 |
Neg logit contributions | |
ades | -0.079 |
emi | -0.074 |
ade | -0.068 |
anging | -0.066 |
ghai | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
hers | +2.242 |
racuse | +2.234 |
lette | +2.198 |
experien | +2.157 |
pict | +2.134 |
Neg logit contributions | |
ades | -2.567 |
emi | -2.388 |
ade | -2.223 |
ghai | -2.156 |
anging | -2.154 |
Token | Because |
Token ID | 4362 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
hers | +0.747 |
racuse | +0.740 |
lette | +0.735 |
experien | +0.735 |
pict | +0.715 |
Neg logit contributions | |
ades | -0.638 |
emi | -0.593 |
ade | -0.541 |
ghai | -0.524 |
anging | -0.519 |
Token | what |
Token ID | 644 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
hers | +0.915 |
racuse | +0.912 |
lette | +0.899 |
experien | +0.892 |
pict | +0.879 |
Neg logit contributions | |
ades | -0.856 |
emi | -0.791 |
ade | -0.730 |
ghai | -0.705 |
anging | -0.704 |
Token | crystal |
Token ID | 15121 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
hers | +2.730 |
lette | +2.676 |
experien | +2.660 |
racuse | +2.657 |
pict | +2.600 |
Neg logit contributions | |
ades | -2.814 |
emi | -2.644 |
ade | -2.417 |
ghai | -2.382 |
anging | -2.354 |
Token | meth |
Token ID | 11248 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ades | +1.794 |
emi | +1.554 |
ade | +1.553 |
anging | +1.413 |
ghai | +1.366 |
Neg logit contributions | |
racuse | -2.001 |
hers | -1.947 |
experien | -1.907 |
senal | -1.906 |
ento | -1.883 |
Token | does |
Token ID | 857 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
hers | +7.882 |
lette | +7.750 |
experien | +7.578 |
pict | +7.141 |
Admin | +7.125 |
Neg logit contributions | |
ades | -10.714 |
emi | -10.618 |
ghai | -9.958 |
anging | -9.679 |
aye | -9.435 |
Token | -- |
Token ID | 438 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
ades | +0.380 |
emi | +0.354 |
ade | +0.329 |
anging | +0.318 |
ghai | +0.311 |
Neg logit contributions | |
racuse | -0.371 |
hers | -0.360 |
senal | -0.359 |
experien | -0.353 |
pict | -0.350 |
Token | Mike |
Token ID | 16073 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
hers | +1.631 |
racuse | +1.630 |
lette | +1.608 |
experien | +1.602 |
pict | +1.554 |
Neg logit contributions | |
ades | -1.707 |
emi | -1.593 |
ade | -1.471 |
anging | -1.422 |
ghai | -1.421 |
Token | taught |
Token ID | 7817 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
hers | +4.095 |
lette | +4.013 |
experien | +3.970 |
racuse | +3.963 |
pict | +3.878 |
Neg logit contributions | |
ades | -4.496 |
emi | -4.247 |
ade | -3.883 |
ghai | -3.844 |
anging | -3.800 |
Token | me |
Token ID | 502 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ades | +0.544 |
emi | +0.505 |
ade | +0.469 |
anging | +0.448 |
ghai | +0.444 |
Neg logit contributions | |
racuse | -0.526 |
hers | -0.511 |
lette | -0.504 |
experien | -0.500 |
senal | -0.499 |
Token | to |
Token ID | 284 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
ades | +0.031 |
emi | +0.029 |
ade | +0.027 |
ghai | +0.026 |
anging | +0.026 |
Neg logit contributions | |
hers | -0.029 |
lette | -0.028 |
racuse | -0.028 |
experien | -0.028 |
pict | -0.027 |
Token | establish |
Token ID | 4474 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ades | +1.761 |
emi | +1.660 |
ade | +1.548 |
ghai | +1.501 |
anging | +1.479 |
Neg logit contributions | |
hers | -1.658 |
racuse | -1.655 |
lette | -1.621 |
pict | -1.611 |
experien | -1.594 |
Token | a |
Token ID | 257 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
hers | +0.504 |
lette | +0.499 |
racuse | +0.498 |
experien | +0.490 |
pict | +0.484 |
Neg logit contributions | |
ades | -0.541 |
emi | -0.510 |
ade | -0.468 |
ghai | -0.458 |
anging | -0.449 |
Token | new |
Token ID | 649 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
hers | +1.381 |
racuse | +1.360 |
lette | +1.360 |
experien | +1.342 |
pict | +1.328 |
Neg logit contributions | |
ades | -1.499 |
emi | -1.407 |
ade | -1.297 |
ghai | -1.272 |
anging | -1.254 |
Token | Asia |
Token ID | 7229 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
hers | +2.498 |
lette | +2.444 |
racuse | +2.441 |
experien | +2.423 |
pict | +2.379 |
Neg logit contributions | |
ades | -2.894 |
emi | -2.722 |
ade | -2.512 |
ghai | -2.469 |
anging | -2.440 |
Token | foc |
Token ID | 2133 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
hers | +2.238 |
racuse | +2.202 |
lette | +2.198 |
experien | +2.183 |
pict | +2.139 |
Neg logit contributions | |
ades | -2.549 |
emi | -2.398 |
ade | -2.221 |
ghai | -2.166 |
anging | -2.143 |
Token | ussed |
Token ID | 29569 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
hers | +8.669 |
lette | +8.215 |
experien | +8.147 |
racuse | +8.079 |
ento | +8.006 |
Neg logit contributions | |
ades | -10.274 |
emi | -9.803 |
ghai | -9.092 |
anging | -8.883 |
ade | -8.831 |
Token | joint |
Token ID | 6466 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
hers | +2.843 |
lette | +2.784 |
racuse | +2.776 |
experien | +2.761 |
pict | +2.708 |
Neg logit contributions | |
ades | -3.154 |
emi | -2.965 |
ade | -2.728 |
ghai | -2.682 |
anging | -2.650 |
Token | venture |
Token ID | 13189 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
hers | +3.652 |
lette | +3.580 |
racuse | +3.571 |
experien | +3.556 |
pict | +3.494 |
Neg logit contributions | |
ades | -3.262 |
emi | -3.043 |
ade | -2.769 |
ghai | -2.720 |
anging | -2.683 |
Token | , |
Token ID | 11 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
hers | +2.361 |
racuse | +2.314 |
lette | +2.311 |
experien | +2.292 |
pict | +2.251 |
Neg logit contributions | |
ades | -2.854 |
emi | -2.685 |
ade | -2.484 |
ghai | -2.439 |
anging | -2.412 |
Token | S |
Token ID | 311 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
hers | +1.181 |
lette | +1.173 |
racuse | +1.162 |
experien | +1.151 |
pict | +1.128 |
Neg logit contributions | |
ades | -1.242 |
emi | -1.169 |
ade | -1.072 |
ghai | -1.051 |
anging | -1.035 |
Token | a |
Token ID | 257 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
hers | +1.003 |
racuse | +0.986 |
lette | +0.986 |
experien | +0.972 |
pict | +0.956 |
Neg logit contributions | |
ades | -1.177 |
emi | -1.108 |
ade | -1.022 |
ghai | -1.003 |
anging | -0.992 |
Token | brick |
Token ID | 17214 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
hers | +2.302 |
lette | +2.247 |
racuse | +2.239 |
experien | +2.231 |
pict | +2.174 |
Neg logit contributions | |
ades | -3.302 |
emi | -3.125 |
ade | -2.900 |
ghai | -2.857 |
anging | -2.831 |
Token | - |
Token ID | 12 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
hers | +2.123 |
racuse | +2.089 |
lette | +2.083 |
experien | +2.081 |
pict | +2.041 |
Neg logit contributions | |
ades | -2.242 |
emi | -2.093 |
ade | -1.946 |
ghai | -1.867 |
anging | -1.866 |
Token | and |
Token ID | 392 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
racuse | +1.264 |
experien | +1.263 |
lette | +1.263 |
hers | +1.262 |
senal | +1.225 |
Neg logit contributions | |
ades | -1.226 |
emi | -1.124 |
ade | -1.065 |
anging | -1.005 |
ghai | -1.001 |
Token | - |
Token ID | 12 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
hers | +3.723 |
lette | +3.671 |
racuse | +3.516 |
Admin | +3.405 |
pict | +3.388 |
Neg logit contributions | |
ades | -6.280 |
emi | -6.111 |
ghai | -5.724 |
anging | -5.500 |
aye | -5.454 |
Token | mort |
Token ID | 30171 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
hers | +1.727 |
lette | +1.462 |
pict | +1.457 |
tv | +1.364 |
ento | +1.317 |
Neg logit contributions | |
ades | -9.798 |
emi | -9.749 |
ghai | -9.111 |
azaki | -8.865 |
atican | -8.856 |
Token | ar |
Token ID | 283 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
hers | +8.328 |
lette | +7.722 |
ento | +7.703 |
ogram | +7.410 |
tv | +7.350 |
Neg logit contributions | |
ades | -9.646 |
emi | -9.386 |
ghai | -9.379 |
�� | -9.150 |
ratification | -8.982 |
Token | retail |
Token ID | 6308 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
hers | +1.884 |
racuse | +1.843 |
lette | +1.832 |
experien | +1.810 |
pict | +1.781 |
Neg logit contributions | |
ades | -3.541 |
emi | -3.361 |
ade | -3.160 |
ghai | -3.094 |
anging | -3.073 |
Token | operation |
Token ID | 4905 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
hers | +2.418 |
racuse | +2.362 |
lette | +2.350 |
experien | +2.326 |
pict | +2.284 |
Neg logit contributions | |
ades | -4.380 |
emi | -4.164 |
ade | -3.899 |
ghai | -3.833 |
anging | -3.805 |
Token | , |
Token ID | 11 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
hers | +2.896 |
racuse | +2.850 |
lette | +2.848 |
experien | +2.827 |
pict | +2.774 |
Neg logit contributions | |
ades | -3.093 |
emi | -2.909 |
ade | -2.668 |
ghai | -2.609 |
anging | -2.593 |
Token | we |
Token ID | 356 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
hers | +1.188 |
lette | +1.173 |
racuse | +1.169 |
experien | +1.154 |
pict | +1.132 |
Neg logit contributions | |
ades | -1.371 |
emi | -1.292 |
ade | -1.189 |
ghai | -1.164 |
anging | -1.157 |
Token | more |
Token ID | 517 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
hers | +1.781 |
racuse | +1.772 |
lette | +1.767 |
experien | +1.725 |
pict | +1.704 |
Neg logit contributions | |
ades | -1.904 |
emi | -1.767 |
ade | -1.635 |
ghai | -1.576 |
anging | -1.569 |
Token | than |
Token ID | 621 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
hers | +0.846 |
lette | +0.839 |
racuse | +0.838 |
experien | +0.809 |
pict | +0.795 |
Neg logit contributions | |
ades | -1.412 |
emi | -1.328 |
ade | -1.248 |
ghai | -1.214 |
anging | -1.213 |
Token | 500 |
Token ID | 5323 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ades | +0.613 |
emi | +0.563 |
ade | +0.523 |
anging | +0.504 |
ghai | +0.495 |
Neg logit contributions | |
hers | -0.692 |
lette | -0.690 |
racuse | -0.690 |
experien | -0.672 |
pict | -0.665 |
Token | shops |
Token ID | 12437 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
lette | +0.413 |
racuse | +0.408 |
hers | +0.408 |
experien | +0.396 |
pict | +0.391 |
Neg logit contributions | |
ades | -0.541 |
emi | -0.504 |
ade | -0.473 |
anging | -0.455 |
ghai | -0.453 |
Token | , |
Token ID | 11 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ades | +1.315 |
emi | +1.188 |
ade | +1.122 |
anging | +1.041 |
ghai | +1.024 |
Neg logit contributions | |
racuse | -1.494 |
lette | -1.464 |
experien | -1.444 |
hers | -1.435 |
senal | -1.427 |
Token | petrol |
Token ID | 34139 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
racuse | +0.469 |
hers | +0.467 |
lette | +0.466 |
experien | +0.457 |
pict | +0.444 |
Neg logit contributions | |
ades | -0.634 |
emi | -0.592 |
ade | -0.553 |
anging | -0.534 |
ghai | -0.529 |
Token | pumps |
Token ID | 29019 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
hers | +7.465 |
lette | +7.111 |
experien | +7.038 |
racuse | +6.759 |
nas | +6.647 |
Neg logit contributions | |
ades | -11.021 |
emi | -10.999 |
ghai | -10.472 |
azaki | -9.839 |
anging | -9.780 |
Token | , |
Token ID | 11 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
hers | +2.298 |
lette | +2.261 |
racuse | +2.255 |
experien | +2.249 |
pict | +2.201 |
Neg logit contributions | |
ades | -2.281 |
emi | -2.129 |
ade | -1.951 |
ghai | -1.907 |
anging | -1.891 |
Token | schools |
Token ID | 4266 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
ades | +0.141 |
emi | +0.130 |
ade | +0.122 |
anging | +0.118 |
ghai | +0.116 |
Neg logit contributions | |
racuse | -0.112 |
hers | -0.112 |
lette | -0.110 |
experien | -0.109 |
pict | -0.107 |
Token | , |
Token ID | 11 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ades | +0.655 |
emi | +0.595 |
ade | +0.556 |
anging | +0.525 |
ghai | +0.517 |
Neg logit contributions | |
racuse | -0.721 |
lette | -0.712 |
experien | -0.708 |
hers | -0.704 |
pict | -0.688 |
Token | shopping |
Token ID | 9735 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ades | +0.963 |
emi | +0.889 |
ade | +0.836 |
anging | +0.802 |
ghai | +0.789 |
Neg logit contributions | |
racuse | -0.800 |
hers | -0.784 |
lette | -0.773 |
experien | -0.767 |
senal | -0.757 |
Token | . |
Token ID | 13 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
ades | +0.548 |
emi | +0.508 |
ade | +0.474 |
anging | +0.458 |
ghai | +0.458 |
Neg logit contributions | |
racuse | -0.473 |
hers | -0.469 |
lette | -0.461 |
experien | -0.457 |
senal | -0.446 |
Token |
|
Token ID | 198 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
ades | +1.616 |
emi | +1.497 |
ade | +1.387 |
ghai | +1.321 |
anging | +1.307 |
Neg logit contributions | |
racuse | -1.862 |
hers | -1.837 |
senal | -1.830 |
experien | -1.813 |
lette | -1.812 |
Token |
|
Token ID | 198 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
ades | +1.118 |
emi | +1.045 |
ade | +0.969 |
ghai | +0.937 |
anging | +0.931 |
Neg logit contributions | |
hers | -1.066 |
experien | -1.063 |
racuse | -1.060 |
senal | -1.054 |
lette | -1.046 |
Token | Things |
Token ID | 22248 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
racuse | +0.085 |
hers | +0.084 |
experien | +0.084 |
senal | +0.083 |
lette | +0.082 |
Neg logit contributions | |
ades | -0.115 |
emi | -0.108 |
ade | -0.102 |
anging | -0.098 |
ghai | -0.097 |
Token | are |
Token ID | 389 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
ades | +2.490 |
emi | +2.345 |
ade | +2.173 |
anging | +2.124 |
ghai | +2.072 |
Neg logit contributions | |
racuse | -2.724 |
hers | -2.630 |
lette | -2.609 |
senal | -2.586 |
experien | -2.547 |
Token | dire |
Token ID | 19958 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
racuse | +0.121 |
hers | +0.118 |
lette | +0.116 |
experien | +0.115 |
pict | +0.114 |
Neg logit contributions | |
ades | -0.122 |
emi | -0.113 |
ade | -0.106 |
ghai | -0.102 |
anging | -0.102 |
Token | enough |
Token ID | 1576 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
hers | +7.595 |
lette | +7.491 |
pict | +7.248 |
experien | +7.212 |
nas | +6.917 |
Neg logit contributions | |
ades | -10.997 |
emi | -10.417 |
ade | -9.659 |
ghai | -9.599 |
aye | -9.337 |
Token | that |
Token ID | 326 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
ades | +1.460 |
emi | +1.343 |
ade | +1.247 |
ghai | +1.209 |
anging | +1.201 |
Neg logit contributions | |
racuse | -1.526 |
senal | -1.474 |
hers | -1.472 |
experien | -1.453 |
lette | -1.440 |
Token | if |
Token ID | 611 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
hers | +1.509 |
racuse | +1.487 |
lette | +1.472 |
experien | +1.457 |
pict | +1.442 |
Neg logit contributions | |
ades | -1.508 |
emi | -1.401 |
ade | -1.293 |
ghai | -1.260 |
anging | -1.245 |
Token | you |
Token ID | 345 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
hers | +0.281 |
racuse | +0.281 |
lette | +0.275 |
pict | +0.270 |
experien | +0.270 |
Neg logit contributions | |
ades | -0.277 |
emi | -0.257 |
ade | -0.238 |
ghai | -0.232 |
anging | -0.228 |
Token | happen |
Token ID | 1645 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ades | +0.760 |
emi | +0.704 |
ade | +0.665 |
ghai | +0.632 |
anging | +0.626 |
Neg logit contributions | |
racuse | -0.677 |
hers | -0.676 |
senal | -0.671 |
lette | -0.655 |
pict | -0.652 |
Token | , |
Token ID | 11 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
hers | +0.905 |
racuse | +0.902 |
experien | +0.895 |
lette | +0.889 |
pict | +0.871 |
Neg logit contributions | |
ades | -0.961 |
emi | -0.894 |
ade | -0.829 |
ghai | -0.802 |
anging | -0.797 |
Token | appeared |
Token ID | 4120 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ades | +1.130 |
emi | +1.033 |
ade | +0.966 |
ghai | +0.922 |
anging | +0.910 |
Neg logit contributions | |
racuse | -1.185 |
hers | -1.166 |
experien | -1.157 |
lette | -1.150 |
pict | -1.127 |
Token | in |
Token ID | 287 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
racuse | +0.584 |
hers | +0.581 |
experien | +0.575 |
lette | +0.569 |
pict | +0.560 |
Neg logit contributions | |
ades | -0.695 |
emi | -0.643 |
ade | -0.612 |
ghai | -0.584 |
anging | -0.583 |
Token | the |
Token ID | 262 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
hers | +1.630 |
racuse | +1.619 |
experien | +1.613 |
lette | +1.612 |
pict | +1.559 |
Neg logit contributions | |
ades | -1.645 |
emi | -1.522 |
ade | -1.415 |
ghai | -1.362 |
anging | -1.352 |
Token | Melbourne |
Token ID | 14819 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
ades | +0.591 |
emi | +0.538 |
ade | +0.502 |
anging | +0.477 |
ghai | +0.477 |
Neg logit contributions | |
hers | -0.698 |
racuse | -0.693 |
lette | -0.689 |
experien | -0.687 |
pict | -0.671 |
Token | Mag |
Token ID | 2944 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
hers | +1.421 |
experien | +1.401 |
racuse | +1.397 |
lette | +1.396 |
pict | +1.345 |
Neg logit contributions | |
ades | -1.199 |
emi | -1.095 |
ade | -1.026 |
ghai | -0.979 |
anging | -0.961 |
Token | istrates |
Token ID | 37909 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
hers | +5.329 |
ento | +5.160 |
lette | +5.126 |
racuse | +4.909 |
pict | +4.847 |
Neg logit contributions | |
ades | -13.186 |
emi | -13.041 |
ghai | -11.934 |
atican | -11.879 |
ade | -11.736 |
Token | Court |
Token ID | 3078 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
hers | +0.721 |
racuse | +0.719 |
experien | +0.719 |
lette | +0.710 |
pict | +0.694 |
Neg logit contributions | |
ades | -0.647 |
emi | -0.586 |
ade | -0.554 |
anging | -0.530 |
ghai | -0.526 |
Token | this |
Token ID | 428 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ades | +0.155 |
emi | +0.142 |
ade | +0.137 |
ghai | +0.129 |
anging | +0.129 |
Neg logit contributions | |
racuse | -0.124 |
hers | -0.121 |
experien | -0.121 |
lette | -0.119 |
Admin | -0.117 |
Token | afternoon |
Token ID | 6672 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
ades | +0.491 |
emi | +0.460 |
ade | +0.430 |
anging | +0.403 |
ghai | +0.401 |
Neg logit contributions | |
racuse | -0.516 |
hers | -0.515 |
experien | -0.506 |
lette | -0.502 |
pict | -0.490 |
Token | , |
Token ID | 11 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
hers | +1.373 |
racuse | +1.366 |
experien | +1.351 |
lette | +1.344 |
pict | +1.313 |
Neg logit contributions | |
ades | -1.655 |
emi | -1.546 |
ade | -1.443 |
ghai | -1.397 |
anging | -1.389 |
Token | If |
Token ID | 1532 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
ades | +0.148 |
emi | +0.140 |
ade | +0.131 |
anging | +0.125 |
ghai | +0.124 |
Neg logit contributions | |
racuse | -0.114 |
experien | -0.111 |
hers | -0.111 |
senal | -0.109 |
lette | -0.109 |
Token | I |
Token ID | 314 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
hers | +1.133 |
racuse | +1.130 |
lette | +1.114 |
experien | +1.100 |
senal | +1.086 |
Neg logit contributions | |
ades | -1.144 |
emi | -1.059 |
ade | -0.988 |
ghai | -0.953 |
anging | -0.936 |
Token | were |
Token ID | 547 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
hers | +1.097 |
racuse | +1.080 |
lette | +1.073 |
experien | +1.067 |
pict | +1.051 |
Neg logit contributions | |
ades | -1.186 |
emi | -1.106 |
ade | -1.026 |
ghai | -0.993 |
anging | -0.984 |
Token | going |
Token ID | 1016 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
hers | +2.895 |
racuse | +2.846 |
lette | +2.838 |
experien | +2.818 |
pict | +2.767 |
Neg logit contributions | |
ades | -3.428 |
emi | -3.222 |
ade | -2.981 |
ghai | -2.917 |
anging | -2.889 |
Token | to |
Token ID | 284 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
ades | +1.722 |
emi | +1.564 |
ade | +1.482 |
ghai | +1.415 |
anging | +1.405 |
Neg logit contributions | |
hers | -1.665 |
experien | -1.648 |
lette | -1.647 |
racuse | -1.632 |
pict | -1.593 |
Token | pit |
Token ID | 6028 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
ades | +1.936 |
emi | +1.801 |
ade | +1.700 |
ghai | +1.602 |
anging | +1.600 |
Neg logit contributions | |
racuse | -1.833 |
hers | -1.822 |
senal | -1.799 |
lette | -1.789 |
pict | -1.784 |
Token | a |
Token ID | 257 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
hers | +8.500 |
lette | +8.375 |
experien | +8.107 |
pict | +8.002 |
ento | +7.897 |
Neg logit contributions | |
ades | -9.470 |
emi | -9.263 |
ghai | -8.468 |
anging | -8.229 |
ade | -8.120 |
Token | city |
Token ID | 1748 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
hers | +2.349 |
racuse | +2.298 |
lette | +2.284 |
experien | +2.275 |
pict | +2.232 |
Neg logit contributions | |
ades | -2.741 |
emi | -2.568 |
ade | -2.383 |
ghai | -2.326 |
anging | -2.310 |
Token | ordinance |
Token ID | 19784 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
racuse | +0.441 |
hers | +0.439 |
experien | +0.420 |
lette | +0.419 |
pict | +0.419 |
Neg logit contributions | |
ades | -0.774 |
emi | -0.727 |
ade | -0.694 |
ghai | -0.673 |
anging | -0.662 |
Token | against |
Token ID | 1028 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
ades | +3.518 |
emi | +3.296 |
ade | +3.182 |
ghai | +3.029 |
anging | +3.006 |
Neg logit contributions | |
racuse | -1.855 |
senal | -1.795 |
pict | -1.751 |
hers | -1.750 |
experien | -1.725 |
Token | human |
Token ID | 1692 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
hers | +0.778 |
racuse | +0.776 |
lette | +0.763 |
experien | +0.759 |
pict | +0.751 |
Neg logit contributions | |
ades | -0.833 |
emi | -0.772 |
ade | -0.722 |
ghai | -0.691 |
anging | -0.687 |
Token | i |
Token ID | 1312 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
hers | +0.912 |
racuse | +0.902 |
lette | +0.902 |
experien | +0.890 |
pict | +0.870 |
Neg logit contributions | |
ades | -0.943 |
emi | -0.884 |
ade | -0.814 |
ghai | -0.790 |
anging | -0.783 |
Token | . |
Token ID | 13 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
ades | +1.228 |
emi | +1.160 |
ade | +1.080 |
ghai | +1.045 |
anging | +1.040 |
Neg logit contributions | |
hers | -0.916 |
experien | -0.912 |
racuse | -0.911 |
lette | -0.902 |
senal | -0.889 |
Token | e |
Token ID | 68 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
ades | +3.787 |
emi | +3.631 |
ade | +3.467 |
ghai | +3.292 |
anging | +3.268 |
Neg logit contributions | |
senal | -2.289 |
experien | -2.141 |
racuse | -2.137 |
hers | -2.010 |
lette | -1.972 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
hers | +0.614 |
racuse | +0.599 |
lette | +0.599 |
experien | +0.597 |
pict | +0.576 |
Neg logit contributions | |
ades | -1.316 |
emi | -1.254 |
ade | -1.177 |
ghai | -1.157 |
anging | -1.152 |
Token | the |
Token ID | 262 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ades | +1.510 |
emi | +1.425 |
ade | +1.314 |
anging | +1.261 |
ghai | +1.259 |
Neg logit contributions | |
racuse | -1.478 |
hers | -1.460 |
lette | -1.442 |
ento | -1.424 |
experien | -1.417 |
Token | prim |
Token ID | 2684 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
hers | +0.467 |
racuse | +0.463 |
lette | +0.461 |
experien | +0.452 |
pict | +0.447 |
Neg logit contributions | |
ades | -0.504 |
emi | -0.474 |
ade | -0.434 |
ghai | -0.421 |
anging | -0.421 |
Token | etime |
Token ID | 8079 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
hers | +9.968 |
lette | +9.632 |
itives | +9.545 |
pict | +9.519 |
experien | +9.477 |
Neg logit contributions | |
ades | -8.288 |
emi | -7.969 |
ghai | -7.163 |
ade | -6.855 |
anging | -6.845 |
Token | soap |
Token ID | 19533 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
hers | +3.687 |
lette | +3.609 |
experien | +3.590 |
racuse | +3.585 |
pict | +3.508 |
Neg logit contributions | |
ades | -3.941 |
emi | -3.710 |
ade | -3.391 |
ghai | -3.346 |
anging | -3.311 |
Token | or |
Token ID | 393 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
hers | +3.051 |
racuse | +2.996 |
lette | +2.990 |
experien | +2.989 |
pict | +2.887 |
Neg logit contributions | |
ades | -4.294 |
emi | -4.039 |
ade | -3.774 |
ghai | -3.691 |
anging | -3.667 |
Token | the |
Token ID | 262 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
hers | +1.471 |
experien | +1.445 |
racuse | +1.441 |
lette | +1.439 |
pict | +1.405 |
Neg logit contributions | |
ades | -1.527 |
emi | -1.428 |
ade | -1.319 |
ghai | -1.277 |
anging | -1.270 |
Token | romantic |
Token ID | 14348 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
hers | +1.208 |
racuse | +1.191 |
lette | +1.185 |
experien | +1.180 |
pict | +1.154 |
Neg logit contributions | |
ades | -1.243 |
emi | -1.168 |
ade | -1.069 |
ghai | -1.044 |
anging | -1.039 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
hers | +1.489 |
racuse | +1.465 |
lette | +1.464 |
experien | +1.440 |
pict | +1.422 |
Neg logit contributions | |
ades | -1.702 |
emi | -1.591 |
ade | -1.469 |
ghai | -1.438 |
anging | -1.433 |
Token | three |
Token ID | 1115 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
hers | +0.409 |
lette | +0.407 |
racuse | +0.405 |
experien | +0.395 |
pict | +0.393 |
Neg logit contributions | |
ades | -0.429 |
emi | -0.399 |
ade | -0.368 |
ghai | -0.360 |
anging | -0.357 |
Token | different |
Token ID | 1180 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
ades | +1.550 |
emi | +1.400 |
ade | +1.321 |
ghai | +1.259 |
anging | +1.255 |
Neg logit contributions | |
hers | -1.577 |
racuse | -1.572 |
lette | -1.543 |
senal | -1.532 |
experien | -1.522 |
Token | urban |
Token ID | 7876 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
hers | +1.258 |
racuse | +1.234 |
lette | +1.230 |
experien | +1.218 |
pict | +1.195 |
Neg logit contributions | |
ades | -1.187 |
emi | -1.090 |
ade | -1.009 |
ghai | -0.982 |
anging | -0.972 |
Token | classes |
Token ID | 6097 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
hers | +0.524 |
racuse | +0.518 |
lette | +0.515 |
experien | +0.508 |
pict | +0.497 |
Neg logit contributions | |
ades | -0.571 |
emi | -0.524 |
ade | -0.493 |
ghai | -0.478 |
anging | -0.475 |
Token | prim |
Token ID | 2684 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
racuse | +0.156 |
hers | +0.154 |
lette | +0.152 |
experien | +0.151 |
senal | +0.150 |
Neg logit contributions | |
ades | -0.177 |
emi | -0.166 |
ade | -0.154 |
anging | -0.150 |
ghai | -0.149 |
Token | a |
Token ID | 64 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
hers | +8.592 |
lette | +8.324 |
itives | +8.220 |
pict | +8.138 |
racuse | +8.038 |
Neg logit contributions | |
ades | -9.628 |
emi | -9.298 |
ghai | -8.474 |
ade | -8.338 |
aye | -8.102 |
Token | fac |
Token ID | 1777 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
hers | +3.081 |
lette | +3.009 |
racuse | +2.988 |
experien | +2.988 |
pict | +2.922 |
Neg logit contributions | |
ades | -3.919 |
emi | -3.701 |
ade | -3.412 |
ghai | -3.370 |
anging | -3.328 |
Token | ie |
Token ID | 494 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
hers | +3.162 |
lette | +3.110 |
experien | +3.012 |
pict | +3.008 |
racuse | +2.997 |
Neg logit contributions | |
ades | -2.916 |
emi | -2.760 |
ghai | -2.490 |
ade | -2.475 |
anging | -2.466 |
Token | suggests |
Token ID | 5644 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
hers | +3.205 |
lette | +3.136 |
experien | +3.108 |
racuse | +3.094 |
pict | +3.034 |
Neg logit contributions | |
ades | -3.998 |
emi | -3.774 |
ade | -3.478 |
ghai | -3.446 |
anging | -3.401 |
Token | that |
Token ID | 326 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ades | +0.548 |
emi | +0.503 |
ade | +0.458 |
anging | +0.440 |
ghai | +0.435 |
Neg logit contributions | |
racuse | -0.699 |
hers | -0.695 |
lette | -0.692 |
experien | -0.684 |
senal | -0.677 |
Token | on |
Token ID | 319 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ades | +1.689 |
emi | +1.582 |
ade | +1.464 |
ghai | +1.407 |
anging | +1.400 |
Neg logit contributions | |
racuse | -1.677 |
experien | -1.646 |
lette | -1.633 |
hers | -1.629 |
pict | -1.611 |
Token | immigration |
Token ID | 6272 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
ades | +2.544 |
emi | +2.244 |
ade | +2.088 |
anging | +1.930 |
ratification | +1.915 |
Neg logit contributions | |
racuse | -4.236 |
lette | -4.109 |
experien | -4.096 |
pict | -4.094 |
senal | -4.092 |
Token | were |
Token ID | 547 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
ades | +1.414 |
emi | +1.313 |
ade | +1.206 |
anging | +1.146 |
ghai | +1.137 |
Neg logit contributions | |
racuse | -1.724 |
lette | -1.682 |
hers | -1.673 |
experien | -1.660 |
pict | -1.636 |
Token | far |
Token ID | 1290 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
hers | +2.054 |
lette | +2.038 |
racuse | +2.036 |
experien | +2.018 |
pict | +1.982 |
Neg logit contributions | |
ades | -2.322 |
emi | -2.190 |
ade | -2.016 |
ghai | -1.968 |
anging | -1.958 |
Token | too |
Token ID | 1165 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
hers | +4.333 |
racuse | +4.183 |
lette | +4.174 |
experien | +4.148 |
pict | +4.056 |
Neg logit contributions | |
ades | -6.053 |
emi | -5.732 |
ade | -5.293 |
ghai | -5.266 |
anging | -5.179 |
Token | per |
Token ID | 583 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
hers | +1.405 |
lette | +1.391 |
racuse | +1.390 |
experien | +1.374 |
pict | +1.346 |
Neg logit contributions | |
ades | -1.407 |
emi | -1.311 |
ade | -1.206 |
ghai | -1.176 |
anging | -1.168 |
Token | missive |
Token ID | 33532 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
hers | +5.994 |
lette | +5.755 |
racuse | +5.695 |
pict | +5.690 |
experien | +5.568 |
Neg logit contributions | |
ades | -12.394 |
emi | -11.702 |
ade | -10.968 |
ghai | -10.954 |
anging | -10.701 |
Token | for |
Token ID | 329 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
hers | +1.109 |
racuse | +1.100 |
experien | +1.095 |
lette | +1.086 |
pict | +1.057 |
Neg logit contributions | |
ades | -1.311 |
emi | -1.223 |
ade | -1.148 |
ghai | -1.116 |
anging | -1.102 |
Token | Bannon |
Token ID | 19688 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ades | +1.563 |
emi | +1.438 |
ade | +1.338 |
anging | +1.297 |
ghai | +1.257 |
Neg logit contributions | |
racuse | -1.736 |
lette | -1.724 |
experien | -1.712 |
pict | -1.707 |
senal | -1.695 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ades | +0.508 |
emi | +0.474 |
ade | +0.441 |
anging | +0.422 |
ghai | +0.421 |
Neg logit contributions | |
hers | -0.451 |
experien | -0.449 |
racuse | -0.449 |
lette | -0.446 |
pict | -0.439 |
Token | H |
Token ID | 367 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ades | +0.462 |
emi | +0.425 |
ade | +0.388 |
ghai | +0.374 |
anging | +0.369 |
Neg logit contributions | |
lette | -0.577 |
hers | -0.572 |
racuse | -0.571 |
experien | -0.570 |
pict | -0.559 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
hers | +2.983 |
lette | +2.912 |
racuse | +2.888 |
experien | +2.887 |
pict | +2.820 |
Neg logit contributions | |
ades | -3.832 |
emi | -3.628 |
ade | -3.342 |
ghai | -3.307 |
anging | -3.268 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ades | +0.443 |
emi | +0.418 |
ade | +0.382 |
ghai | +0.365 |
anging | +0.364 |
Neg logit contributions | |
experien | -0.461 |
racuse | -0.458 |
hers | -0.457 |
lette | -0.457 |
senal | -0.446 |
Token |
|
Token ID | 198 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
ades | +0.775 |
emi | +0.726 |
ade | +0.673 |
ghai | +0.650 |
anging | +0.646 |
Neg logit contributions | |
hers | -0.735 |
experien | -0.733 |
racuse | -0.731 |
lette | -0.723 |
senal | -0.722 |
Token | About |
Token ID | 8585 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
experien | +0.220 |
racuse | +0.219 |
senal | +0.216 |
hers | +0.216 |
lette | +0.212 |
Neg logit contributions | |
ades | -0.284 |
emi | -0.267 |
ade | -0.252 |
anging | -0.241 |
ghai | -0.238 |
Token | former |
Token ID | 1966 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
ades | +0.809 |
emi | +0.748 |
ade | +0.690 |
anging | +0.657 |
ghai | +0.649 |
Neg logit contributions | |
racuse | -0.851 |
hers | -0.849 |
lette | -0.843 |
experien | -0.834 |
pict | -0.833 |
Token | meth |
Token ID | 11248 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
hers | +1.117 |
racuse | +1.100 |
lette | +1.092 |
experien | +1.085 |
pict | +1.073 |
Neg logit contributions | |
ades | -1.132 |
emi | -1.056 |
ade | -0.972 |
ghai | -0.940 |
anging | -0.939 |
Token | dealer |
Token ID | 16456 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
hers | +8.834 |
lette | +8.642 |
experien | +8.531 |
Admin | +8.353 |
racuse | +8.293 |
Neg logit contributions | |
ades | -9.047 |
emi | -8.835 |
ghai | -8.152 |
anging | -7.790 |
azaki | -7.609 |
Token | and |
Token ID | 290 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
hers | +2.063 |
racuse | +2.030 |
lette | +2.023 |
experien | +2.016 |
pict | +1.978 |
Neg logit contributions | |
ades | -1.802 |
emi | -1.674 |
ade | -1.528 |
ghai | -1.485 |
anging | -1.474 |
Token | escort |
Token ID | 27675 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
ades | +1.296 |
emi | +1.196 |
ade | +1.117 |
anging | +1.066 |
ghai | +1.045 |
Neg logit contributions | |
racuse | -1.298 |
hers | -1.283 |
lette | -1.261 |
pict | -1.248 |
ento | -1.241 |
Token | Mike |
Token ID | 4995 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ades | +0.944 |
emi | +0.855 |
ade | +0.818 |
anging | +0.773 |
ghai | +0.761 |
Neg logit contributions | |
racuse | -0.962 |
hers | -0.957 |
ento | -0.915 |
lette | -0.915 |
experien | -0.910 |
Token | Jones |
Token ID | 5437 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
hers | +1.356 |
experien | +1.346 |
racuse | +1.338 |
lette | +1.316 |
pict | +1.305 |
Neg logit contributions | |
ades | -1.250 |
emi | -1.163 |
ade | -1.069 |
ghai | -1.035 |
anging | -1.019 |
Token | Dan |
Token ID | 6035 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
hers | +2.041 |
lette | +1.996 |
racuse | +1.995 |
experien | +1.991 |
pict | +1.937 |
Neg logit contributions | |
ades | -2.091 |
emi | -1.958 |
ade | -1.799 |
ghai | -1.756 |
anging | -1.738 |
Token | Mer |
Token ID | 4638 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
hers | +3.187 |
racuse | +3.131 |
experien | +3.130 |
lette | +3.112 |
pict | +3.049 |
Neg logit contributions | |
ades | -2.807 |
emi | -2.621 |
ade | -2.387 |
ghai | -2.339 |
anging | -2.300 |
Token | ica |
Token ID | 3970 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
hers | +2.285 |
lette | +2.230 |
racuse | +2.222 |
experien | +2.222 |
pict | +2.163 |
Neg logit contributions | |
ades | -2.941 |
emi | -2.775 |
ade | -2.567 |
ghai | -2.529 |
anging | -2.502 |
Token | (@ |
Token ID | 4275 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
hers | +0.727 |
racuse | +0.720 |
experien | +0.718 |
lette | +0.685 |
pict | +0.681 |
Neg logit contributions | |
ades | -1.204 |
emi | -1.146 |
ade | -1.076 |
ghai | -1.042 |
anging | -1.029 |
Token | dan |
Token ID | 25604 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ades | +2.441 |
emi | +2.264 |
ade | +2.190 |
aye | +1.985 |
end | +1.982 |
Neg logit contributions | |
experien | -2.185 |
senal | -2.184 |
racuse | -2.182 |
hers | -2.150 |
itives | -2.079 |
Token | meric |
Token ID | 946 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
hers | +3.409 |
lette | +3.325 |
racuse | +3.241 |
experien | +3.222 |
pict | +3.155 |
Neg logit contributions | |
ades | -7.223 |
emi | -6.877 |
ade | -6.443 |
ghai | -6.383 |
anging | -6.342 |
Token | a |
Token ID | 64 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
lette | +5.632 |
hers | +5.424 |
pict | +5.317 |
Admin | +5.190 |
ento | +5.169 |
Neg logit contributions | |
ades | -11.438 |
emi | -11.217 |
Reconstruction | -10.784 |
ratification | -10.756 |
ghai | -10.659 |
Token | CNN |
Token ID | 18474 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
hers | +1.236 |
experien | +1.233 |
racuse | +1.226 |
lette | +1.213 |
ento | +1.167 |
Neg logit contributions | |
ades | -1.841 |
emi | -1.714 |
ade | -1.643 |
ghai | -1.578 |
anging | -1.558 |
Token | ) |
Token ID | 8 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
hers | +2.569 |
lette | +2.508 |
racuse | +2.466 |
pict | +2.449 |
experien | +2.440 |
Neg logit contributions | |
ades | -3.787 |
emi | -3.599 |
ghai | -3.301 |
ade | -3.298 |
anging | -3.288 |
Token | October |
Token ID | 3267 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
ades | +0.782 |
emi | +0.712 |
ade | +0.626 |
anging | +0.588 |
ghai | +0.580 |
Neg logit contributions | |
racuse | -1.430 |
hers | -1.426 |
experien | -1.418 |
lette | -1.410 |
senal | -1.401 |
Token | 23 |
Token ID | 2242 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ades | +1.060 |
emi | +0.980 |
ade | +0.893 |
ghai | +0.855 |
anging | +0.853 |
Neg logit contributions | |
hers | -1.330 |
racuse | -1.321 |
experien | -1.318 |
lette | -1.305 |
senal | -1.286 |
Token | elman |
Token ID | 32370 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
ades | +2.704 |
emi | +2.528 |
ade | +2.349 |
anging | +2.215 |
ghai | +2.201 |
Neg logit contributions | |
experien | -2.655 |
senal | -2.631 |
racuse | -2.577 |
lette | -2.517 |
Admin | -2.514 |
Token | of |
Token ID | 286 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
ades | +1.630 |
emi | +1.532 |
ade | +1.410 |
ghai | +1.340 |
anging | +1.336 |
Neg logit contributions | |
racuse | -1.747 |
experien | -1.730 |
hers | -1.718 |
pict | -1.697 |
lette | -1.694 |
Token | Cong |
Token ID | 2908 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
ades | +1.615 |
emi | +1.490 |
ade | +1.366 |
ghai | +1.302 |
anging | +1.294 |
Neg logit contributions | |
racuse | -1.773 |
hers | -1.768 |
experien | -1.751 |
lette | -1.747 |
pict | -1.723 |
Token | regation |
Token ID | 43068 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ades | +1.406 |
emi | +1.277 |
ade | +1.101 |
aye | +1.035 |
anging | +0.961 |
Neg logit contributions | |
experien | -2.835 |
racuse | -2.794 |
senal | -2.791 |
pict | -2.739 |
Admin | -2.737 |
Token | Kol |
Token ID | 25910 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ades | +3.948 |
emi | +3.602 |
ade | +3.417 |
aye | +3.139 |
ghai | +3.136 |
Neg logit contributions | |
racuse | -4.538 |
hers | -4.425 |
experien | -4.371 |
senal | -4.370 |
lette | -4.295 |
Token | Han |
Token ID | 9530 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
ades | +1.025 |
emi | +0.944 |
ade | +0.889 |
anging | +0.838 |
aye | +0.835 |
Neg logit contributions | |
racuse | -1.086 |
experien | -1.082 |
hers | -1.080 |
lette | -1.050 |
pict | -1.040 |
Token | esh |
Token ID | 5069 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ades | +10.257 |
emi | +9.968 |
ade | +8.974 |
ghai | +8.727 |
anging | +8.551 |
Neg logit contributions | |
racuse | -10.678 |
experien | -10.118 |
senal | -10.091 |
pict | -9.836 |
hers | -9.825 |
Token | ama |
Token ID | 1689 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
ades | +4.457 |
emi | +4.135 |
ade | +3.894 |
aye | +3.688 |
anging | +3.639 |
Neg logit contributions | |
racuse | -4.700 |
hers | -4.511 |
experien | -4.501 |
pict | -4.492 |
Admin | -4.454 |
Token | and |
Token ID | 290 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ades | +2.292 |
emi | +2.196 |
ade | +2.003 |
ghai | +1.903 |
aye | +1.893 |
Neg logit contributions | |
racuse | -2.489 |
experien | -2.398 |
lette | -2.396 |
hers | -2.393 |
pict | -2.363 |
Token | Rabbi |
Token ID | 31807 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ades | +0.534 |
emi | +0.495 |
ade | +0.456 |
ghai | +0.434 |
anging | +0.432 |
Neg logit contributions | |
racuse | -0.568 |
hers | -0.565 |
lette | -0.562 |
experien | -0.552 |
ento | -0.550 |
Token | Leon |
Token ID | 10592 |
Feature activation | +4.47e-04 |
Pos logit contributions | |
ades | +4.392 |
emi | +4.068 |
ade | +3.818 |
aye | +3.530 |
ghai | +3.528 |
Neg logit contributions | |
racuse | -5.259 |
hers | -5.083 |
senal | -5.044 |
experien | -5.044 |
ento | -5.007 |
Token | rik |
Token ID | 12602 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
ades | +3.451 |
emi | +3.213 |
ade | +3.068 |
aye | +2.996 |
ghai | +2.973 |
Neg logit contributions | |
experien | -2.805 |
hers | -2.768 |
racuse | -2.745 |
Admin | -2.672 |
senal | -2.657 |
Token | Hed |
Token ID | 30920 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ades | +0.835 |
emi | +0.786 |
ade | +0.710 |
anging | +0.680 |
ghai | +0.677 |
Neg logit contributions | |
racuse | -0.943 |
experien | -0.942 |
hers | -0.932 |
pict | -0.918 |
lette | -0.915 |
Token | man |
Token ID | 805 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ades | +2.769 |
emi | +2.669 |
ade | +2.275 |
anging | +2.157 |
end | +2.152 |
Neg logit contributions | |
experien | -3.950 |
racuse | -3.880 |
senal | -3.868 |
Admin | -3.784 |
hers | -3.766 |
Token | and |
Token ID | 290 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
ades | +1.648 |
emi | +1.576 |
ade | +1.437 |
ghai | +1.368 |
anging | +1.352 |
Neg logit contributions | |
racuse | -1.596 |
experien | -1.595 |
hers | -1.581 |
Admin | -1.536 |
pict | -1.535 |
Token | Ben |
Token ID | 3932 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
ades | +0.158 |
emi | +0.148 |
ade | +0.136 |
ghai | +0.130 |
anging | +0.130 |
Neg logit contributions | |
racuse | -0.156 |
hers | -0.154 |
lette | -0.151 |
experien | -0.151 |
pict | -0.150 |
Token | Han |
Token ID | 9530 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
ades | +2.134 |
emi | +2.034 |
ade | +1.882 |
ghai | +1.829 |
anging | +1.800 |
Neg logit contributions | |
racuse | -1.807 |
experien | -1.787 |
hers | -1.762 |
Admin | -1.713 |
lette | -1.706 |
Token | ley |
Token ID | 1636 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
ades | +10.958 |
emi | +10.649 |
ade | +9.555 |
ghai | +9.366 |
aye | +9.077 |
Neg logit contributions | |
racuse | -10.281 |
senal | -9.498 |
experien | -9.447 |
Sov | -8.962 |
Admin | -8.925 |
Token | , |
Token ID | 11 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
ades | +3.172 |
emi | +3.083 |
ade | +2.764 |
aye | +2.635 |
anging | +2.600 |
Neg logit contributions | |
racuse | -3.026 |
experien | -2.997 |
hers | -2.944 |
pict | -2.876 |
Admin | -2.873 |
Token | while |
Token ID | 981 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
hers | +1.102 |
racuse | +1.090 |
lette | +1.089 |
experien | +1.080 |
pict | +1.064 |
Neg logit contributions | |
ades | -1.007 |
emi | -0.940 |
ade | -0.856 |
ghai | -0.833 |
anging | -0.823 |
Token | the |
Token ID | 262 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
hers | +1.808 |
racuse | +1.784 |
lette | +1.777 |
experien | +1.767 |
pict | +1.739 |
Neg logit contributions | |
ades | -1.823 |
emi | -1.709 |
ade | -1.564 |
ghai | -1.527 |
anging | -1.517 |
Token | sister |
Token ID | 6621 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
hers | +1.319 |
racuse | +1.308 |
lette | +1.295 |
experien | +1.282 |
pict | +1.271 |
Neg logit contributions | |
ades | -1.408 |
emi | -1.329 |
ade | -1.215 |
ghai | -1.186 |
anging | -1.178 |
Token | Lil |
Token ID | 16342 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
racuse | +1.189 |
experien | +1.182 |
hers | +1.175 |
lette | +1.157 |
pict | +1.141 |
Neg logit contributions | |
ades | -1.097 |
emi | -1.016 |
ade | -0.945 |
ghai | -0.902 |
anging | -0.898 |
Token | lee |
Token ID | 7197 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
ades | +1.458 |
emi | +1.340 |
ade | +1.299 |
ghai | +1.206 |
anging | +1.205 |
Neg logit contributions | |
racuse | -1.233 |
experien | -1.214 |
hers | -1.189 |
pict | -1.163 |
Admin | -1.155 |
Token | frozen |
Token ID | 12912 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
ades | +5.715 |
emi | +5.298 |
ade | +5.023 |
anging | +4.617 |
ghai | +4.601 |
Neg logit contributions | |
racuse | -6.152 |
experien | -6.065 |
Admin | -5.800 |
senal | -5.794 |
hers | -5.777 |
Token | forever |
Token ID | 8097 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ades | +2.703 |
emi | +2.478 |
ade | +2.379 |
anging | +2.271 |
ghai | +2.215 |
Neg logit contributions | |
racuse | -2.514 |
experien | -2.461 |
senal | -2.445 |
hers | -2.437 |
lette | -2.422 |
Token | like |
Token ID | 588 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ades | +0.408 |
emi | +0.380 |
ade | +0.356 |
anging | +0.345 |
ghai | +0.344 |
Neg logit contributions | |
racuse | -0.349 |
experien | -0.344 |
hers | -0.343 |
lette | -0.338 |
Admin | -0.335 |
Token | Han |
Token ID | 9530 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
ades | +0.488 |
emi | +0.451 |
ade | +0.422 |
anging | +0.406 |
ghai | +0.404 |
Neg logit contributions | |
racuse | -0.456 |
hers | -0.449 |
lette | -0.444 |
experien | -0.443 |
pict | -0.435 |
Token | Solo |
Token ID | 20284 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
ades | +9.311 |
emi | +8.673 |
ade | +8.044 |
ghai | +7.620 |
azaki | +7.128 |
Neg logit contributions | |
racuse | -12.072 |
experien | -11.136 |
ento | -10.733 |
senal | -10.518 |
itives | -10.402 |
Token | in |
Token ID | 287 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ades | +2.013 |
emi | +1.846 |
ade | +1.745 |
anging | +1.664 |
ghai | +1.663 |
Neg logit contributions | |
racuse | -1.819 |
hers | -1.793 |
experien | -1.779 |
lette | -1.772 |
Admin | -1.753 |
Token | his |
Token ID | 465 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
ades | +0.735 |
emi | +0.687 |
ade | +0.630 |
ghai | +0.602 |
anging | +0.599 |
Neg logit contributions | |
racuse | -0.774 |
hers | -0.769 |
lette | -0.765 |
experien | -0.761 |
Admin | -0.744 |
Token | classic |
Token ID | 6833 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
ades | +2.986 |
emi | +2.772 |
ade | +2.588 |
anging | +2.457 |
ghai | +2.446 |
Neg logit contributions | |
racuse | -2.972 |
hers | -2.909 |
lette | -2.829 |
pict | -2.802 |
experien | -2.790 |
Token | delivery |
Token ID | 7585 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ades | +1.371 |
emi | +1.282 |
ade | +1.191 |
ghai | +1.136 |
anging | +1.130 |
Neg logit contributions | |
racuse | -1.418 |
hers | -1.404 |
lette | -1.373 |
experien | -1.367 |
Admin | -1.349 |
Token | the |
Token ID | 262 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ades | +1.360 |
emi | +1.268 |
ade | +1.161 |
anging | +1.116 |
ghai | +1.113 |
Neg logit contributions | |
hers | -1.387 |
lette | -1.367 |
racuse | -1.365 |
experien | -1.357 |
pict | -1.354 |
Token | 1932 |
Token ID | 32471 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
ades | +1.398 |
emi | +1.284 |
ade | +1.193 |
ghai | +1.144 |
anging | +1.136 |
Neg logit contributions | |
hers | -1.564 |
racuse | -1.560 |
lette | -1.540 |
pict | -1.527 |
experien | -1.519 |
Token | convention |
Token ID | 9831 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
ades | +3.088 |
emi | +2.823 |
ade | +2.668 |
ghai | +2.586 |
ratification | +2.557 |
Neg logit contributions | |
hers | -3.369 |
racuse | -3.359 |
lette | -3.275 |
senal | -3.270 |
experien | -3.269 |
Token | by |
Token ID | 416 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
hers | +0.891 |
racuse | +0.882 |
lette | +0.881 |
experien | +0.873 |
pict | +0.859 |
Neg logit contributions | |
ades | -0.946 |
emi | -0.875 |
ade | -0.815 |
ghai | -0.786 |
anging | -0.780 |
Token | Daniel |
Token ID | 7806 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
racuse | +0.062 |
hers | +0.062 |
lette | +0.062 |
experien | +0.061 |
pict | +0.060 |
Neg logit contributions | |
ades | -0.062 |
emi | -0.057 |
ade | -0.053 |
anging | -0.051 |
ghai | -0.050 |
Token | Ho |
Token ID | 9544 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
hers | +0.939 |
experien | +0.929 |
racuse | +0.927 |
lette | +0.919 |
pict | +0.900 |
Neg logit contributions | |
ades | -0.864 |
emi | -0.802 |
ade | -0.739 |
ghai | -0.714 |
anging | -0.707 |
Token | an |
Token ID | 272 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
ades | +9.942 |
emi | +9.614 |
ade | +9.232 |
anging | +8.328 |
ghai | +8.297 |
Neg logit contributions | |
senal | -10.395 |
racuse | -10.135 |
experien | -9.921 |
pict | -9.522 |
Admin | -9.427 |
Token | of |
Token ID | 286 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
ades | +1.815 |
emi | +1.711 |
ade | +1.571 |
ghai | +1.534 |
anging | +1.478 |
Neg logit contributions | |
racuse | -1.815 |
experien | -1.809 |
hers | -1.742 |
senal | -1.738 |
Admin | -1.729 |
Token | Milwaukee |
Token ID | 16629 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ades | +1.675 |
emi | +1.539 |
ade | +1.405 |
anging | +1.353 |
ghai | +1.344 |
Neg logit contributions | |
hers | -1.829 |
racuse | -1.819 |
experien | -1.807 |
lette | -1.807 |
Admin | -1.781 |
Token | , |
Token ID | 11 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
racuse | +0.487 |
lette | +0.483 |
hers | +0.483 |
experien | +0.480 |
pict | +0.466 |
Neg logit contributions | |
ades | -0.461 |
emi | -0.428 |
ade | -0.392 |
ghai | -0.381 |
anging | -0.380 |
Token | with |
Token ID | 351 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
ades | +0.177 |
emi | +0.161 |
ade | +0.147 |
ghai | +0.140 |
anging | +0.139 |
Neg logit contributions | |
racuse | -0.237 |
lette | -0.236 |
hers | -0.235 |
experien | -0.233 |
pict | -0.229 |
Token | said |
Token ID | 531 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
ades | +3.929 |
emi | +3.774 |
ade | +3.485 |
ghai | +3.354 |
aye | +3.225 |
Neg logit contributions | |
racuse | -3.236 |
hers | -3.085 |
experien | -3.033 |
pict | -3.021 |
Admin | -3.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ades | +1.253 |
emi | +1.186 |
ade | +1.089 |
ghai | +1.070 |
anging | +1.035 |
Neg logit contributions | |
hers | -1.081 |
experien | -1.079 |
racuse | -1.077 |
lette | -1.063 |
pict | -1.050 |
Token |
|
Token ID | 198 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
ades | +0.635 |
emi | +0.594 |
ade | +0.546 |
ghai | +0.529 |
anging | +0.514 |
Neg logit contributions | |
racuse | -0.688 |
experien | -0.686 |
lette | -0.683 |
hers | -0.678 |
senal | -0.665 |
Token |
|
Token ID | 198 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
hers | +0.697 |
lette | +0.682 |
racuse | +0.675 |
experien | +0.672 |
pict | +0.661 |
Neg logit contributions | |
ades | -0.823 |
emi | -0.776 |
ade | -0.712 |
ghai | -0.704 |
anging | -0.696 |
Token | Albert |
Token ID | 42590 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
experien | +1.129 |
racuse | +1.127 |
hers | +1.123 |
lette | +1.101 |
senal | +1.091 |
Neg logit contributions | |
ades | -1.572 |
emi | -1.484 |
ade | -1.392 |
ghai | -1.354 |
anging | -1.345 |
Token | Ho |
Token ID | 9544 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
hers | +4.580 |
lette | +4.492 |
racuse | +4.455 |
experien | +4.447 |
pict | +4.371 |
Neg logit contributions | |
ades | -3.810 |
emi | -3.542 |
ade | -3.201 |
ghai | -3.148 |
anging | -3.116 |
Token | , |
Token ID | 11 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ades | +10.083 |
emi | +9.559 |
ade | +9.310 |
ghai | +8.753 |
anging | +8.403 |
Neg logit contributions | |
racuse | -10.369 |
senal | -9.823 |
experien | -9.257 |
Admin | -9.104 |
hers | -9.060 |
Token | another |
Token ID | 1194 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ades | +1.208 |
emi | +1.135 |
ade | +1.045 |
ghai | +1.029 |
anging | +0.999 |
Neg logit contributions | |
racuse | -1.118 |
hers | -1.101 |
lette | -1.095 |
experien | -1.074 |
pict | -1.063 |
Token | lawmaker |
Token ID | 31340 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ades | +0.847 |
emi | +0.787 |
ade | +0.737 |
ghai | +0.724 |
anging | +0.708 |
Neg logit contributions | |
racuse | -0.723 |
hers | -0.719 |
lette | -0.709 |
pict | -0.688 |
Admin | -0.688 |
Token | involved |
Token ID | 2950 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ades | +3.562 |
emi | +3.242 |
ade | +3.055 |
ghai | +2.979 |
anging | +2.845 |
Neg logit contributions | |
racuse | -4.638 |
senal | -4.602 |
experien | -4.543 |
hers | -4.511 |
pict | -4.510 |
Token | with |
Token ID | 351 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
ades | +1.065 |
emi | +1.002 |
ade | +0.932 |
ghai | +0.915 |
anging | +0.907 |
Neg logit contributions | |
hers | -0.816 |
experien | -0.799 |
lette | -0.794 |
racuse | -0.791 |
pict | -0.780 |
Token | � |
Token ID | 134 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ades | +2.294 |
emi | +2.091 |
ade | +1.822 |
ghai | +1.675 |
anging | +1.613 |
Neg logit contributions | |
racuse | -4.854 |
hers | -4.760 |
lette | -4.758 |
experien | -4.744 |
pict | -4.715 |
Token | � |
Token ID | 119 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
ades | +4.386 |
emi | +4.137 |
�� | +3.696 |
ade | +3.689 |
anging | +3.537 |
Neg logit contributions | |
racuse | -6.158 |
lette | -6.005 |
experien | -5.984 |
Admin | -5.912 |
entin | -5.862 |
Token | ō |
Token ID | 13090 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
ades | +1.951 |
emi | +1.859 |
ade | +1.700 |
ghai | +1.616 |
anging | +1.614 |
Neg logit contributions | |
experien | -1.955 |
racuse | -1.952 |
hers | -1.945 |
senal | -1.911 |
lette | -1.906 |
Token | le |
Token ID | 293 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
ades | +2.903 |
emi | +2.777 |
ade | +2.539 |
ghai | +2.448 |
anging | +2.386 |
Neg logit contributions | |
racuse | -2.777 |
hers | -2.737 |
experien | -2.697 |
senal | -2.666 |
pict | -2.662 |
Token | lo |
Token ID | 5439 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ades | +1.956 |
emi | +1.850 |
ade | +1.682 |
ghai | +1.606 |
anging | +1.577 |
Neg logit contributions | |
racuse | -2.220 |
hers | -2.179 |
experien | -2.131 |
pict | -2.107 |
senal | -2.098 |
Token | Hawai |
Token ID | 10847 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
ades | +5.572 |
emi | +5.324 |
ade | +4.941 |
anging | +4.514 |
ghai | +4.512 |
Neg logit contributions | |
racuse | -6.030 |
senal | -5.733 |
hers | -5.665 |
pict | -5.572 |
Admin | -5.524 |
Token | � |
Token ID | 134 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ades | +9.705 |
emi | +8.874 |
ade | +8.330 |
ghai | +7.932 |
anging | +7.775 |
Neg logit contributions | |
racuse | -10.369 |
pict | -9.616 |
senal | -9.613 |
entin | -9.431 |
Admin | -9.411 |
Token | � |
Token ID | 119 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
ades | +4.271 |
emi | +3.729 |
ade | +3.486 |
�� | +3.417 |
ghai | +3.282 |
Neg logit contributions | |
racuse | -5.937 |
experien | -5.612 |
lette | -5.611 |
pict | -5.561 |
hers | -5.474 |
Token | i |
Token ID | 72 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
ades | +2.266 |
emi | +2.132 |
ade | +1.980 |
ghai | +1.918 |
anging | +1.875 |
Neg logit contributions | |
racuse | -1.966 |
hers | -1.940 |
experien | -1.917 |
lette | -1.900 |
pict | -1.887 |
Token | a |
Token ID | 257 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
ades | +2.427 |
emi | +2.275 |
ade | +2.073 |
ghai | +2.003 |
anging | +1.958 |
Neg logit contributions | |
racuse | -2.686 |
hers | -2.646 |
lette | -2.598 |
experien | -2.566 |
pict | -2.561 |
Token | me |
Token ID | 502 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
hers | +1.215 |
racuse | +1.206 |
lette | +1.191 |
experien | +1.188 |
pict | +1.174 |
Neg logit contributions | |
ades | -1.090 |
emi | -1.017 |
ade | -0.929 |
ghai | -0.901 |
anging | -0.887 |
Token | according |
Token ID | 1864 |
Feature activation | +2.30e-03 |
Pos logit contributions | |
hers | +1.615 |
lette | +1.586 |
racuse | +1.576 |
experien | +1.573 |
pict | +1.542 |
Neg logit contributions | |
ades | -1.722 |
emi | -1.616 |
ade | -1.483 |
ghai | -1.456 |
anging | -1.441 |
Token | to |
Token ID | 284 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
hers | +0.007 |
lette | +0.007 |
racuse | +0.007 |
experien | +0.007 |
pict | +0.007 |
Neg logit contributions | |
ades | -0.008 |
emi | -0.008 |
ade | -0.007 |
ghai | -0.007 |
anging | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
hers | +0.387 |
lette | +0.381 |
experien | +0.376 |
racuse | +0.376 |
pict | +0.372 |
Neg logit contributions | |
ades | -0.364 |
emi | -0.341 |
ade | -0.310 |
ghai | -0.303 |
anging | -0.298 |
Token | University |
Token ID | 2059 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
ades | +0.896 |
emi | +0.837 |
ade | +0.765 |
ghai | +0.739 |
anging | +0.728 |
Neg logit contributions | |
hers | -0.981 |
lette | -0.967 |
racuse | -0.956 |
experien | -0.954 |
pict | -0.948 |
Token | of |
Token ID | 286 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
ades | +2.879 |
emi | +2.780 |
ade | +2.459 |
ghai | +2.440 |
anging | +2.348 |
Neg logit contributions | |
hers | -3.283 |
experien | -3.216 |
lette | -3.214 |
pict | -3.188 |
racuse | -3.166 |
Token | Hawai |
Token ID | 10847 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
ades | +1.139 |
emi | +1.032 |
ade | +0.900 |
ghai | +0.846 |
anging | +0.843 |
Neg logit contributions | |
hers | -2.308 |
racuse | -2.289 |
experien | -2.270 |
lette | -2.258 |
senal | -2.256 |
Token | � |
Token ID | 447 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
ades | +10.472 |
emi | +9.881 |
ghai | +9.048 |
ade | +9.040 |
anging | +8.942 |
Neg logit contributions | |
racuse | -9.430 |
senal | -9.290 |
entin | -8.994 |
experien | -8.383 |
Admin | -8.356 |
Token | � |
Token ID | 247 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
ades | +1.260 |
emi | +1.121 |
ade | +1.033 |
ghai | +0.983 |
anging | +0.922 |
Neg logit contributions | |
racuse | -2.224 |
lette | -2.217 |
experien | -2.206 |
pict | -2.166 |
hers | -2.158 |
Token | i |
Token ID | 72 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
ades | +1.751 |
emi | +1.615 |
ade | +1.528 |
ghai | +1.482 |
anging | +1.413 |
Neg logit contributions | |
racuse | -1.571 |
experien | -1.550 |
lette | -1.544 |
hers | -1.531 |
pict | -1.507 |
Token | , |
Token ID | 11 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ades | +2.401 |
emi | +2.306 |
ade | +2.085 |
ghai | +2.010 |
anging | +1.980 |
Neg logit contributions | |
hers | -2.464 |
racuse | -2.435 |
experien | -2.406 |
lette | -2.394 |
pict | -2.390 |
Token | there |
Token ID | 612 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
hers | +0.575 |
lette | +0.568 |
racuse | +0.563 |
experien | +0.562 |
pict | +0.554 |
Neg logit contributions | |
ades | -0.591 |
emi | -0.552 |
ade | -0.508 |
ghai | -0.495 |
anging | -0.491 |
Token | A |
Token ID | 317 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
ades | +1.058 |
emi | +0.997 |
ade | +0.905 |
anging | +0.852 |
ghai | +0.844 |
Neg logit contributions | |
racuse | -1.203 |
hers | -1.202 |
lette | -1.183 |
senal | -1.157 |
experien | -1.150 |
Token | US |
Token ID | 2937 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
hers | +0.827 |
lette | +0.811 |
racuse | +0.810 |
experien | +0.809 |
pict | +0.782 |
Neg logit contributions | |
ades | -1.255 |
emi | -1.192 |
ade | -1.109 |
ghai | -1.090 |
anging | -1.083 |
Token | 7 |
Token ID | 767 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
hers | +2.485 |
lette | +2.431 |
racuse | +2.410 |
experien | +2.406 |
pict | +2.362 |
Neg logit contributions | |
ades | -2.115 |
emi | -1.957 |
ade | -1.781 |
ghai | -1.761 |
anging | -1.723 |
Token | Hein |
Token ID | 26431 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ades | +0.935 |
emi | +0.881 |
ade | +0.809 |
ghai | +0.767 |
anging | +0.763 |
Neg logit contributions | |
racuse | -0.993 |
hers | -0.983 |
experien | -0.971 |
lette | -0.959 |
pict | -0.947 |
Token | rich |
Token ID | 7527 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
ades | +2.742 |
emi | +2.581 |
ade | +2.255 |
anging | +2.165 |
aye | +1.959 |
Neg logit contributions | |
racuse | -5.112 |
experien | -5.029 |
hers | -4.965 |
senal | -4.930 |
lette | -4.915 |
Token | Ha |
Token ID | 9398 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
ades | +1.072 |
emi | +0.956 |
ade | +0.759 |
anging | +0.700 |
ghai | +0.689 |
Neg logit contributions | |
hers | -3.460 |
experien | -3.455 |
racuse | -3.432 |
lette | -3.430 |
pict | -3.384 |
Token | uss |
Token ID | 1046 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
emi | +10.015 |
ades | +9.714 |
ade | +8.929 |
end | +7.991 |
aye | +7.949 |
Neg logit contributions | |
senal | -11.847 |
experien | -11.230 |
racuse | -10.422 |
Honest | -10.009 |
Admin | -9.974 |
Token | ler |
Token ID | 1754 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ades | +1.821 |
ade | +1.586 |
emi | +1.578 |
anging | +1.461 |
end | +1.383 |
Neg logit contributions | |
racuse | -2.575 |
experien | -2.553 |
hers | -2.498 |
senal | -2.486 |
pict | -2.445 |
Token | ( |
Token ID | 357 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
ades | +3.642 |
emi | +3.363 |
ade | +3.169 |
ghai | +2.970 |
anging | +2.949 |
Neg logit contributions | |
senal | -4.158 |
experien | -4.004 |
racuse | -3.918 |
hers | -3.887 |
lette | -3.754 |
Token | Gar |
Token ID | 27676 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
ades | +2.967 |
emi | +2.754 |
ade | +2.638 |
end | +2.469 |
anging | +2.451 |
Neg logit contributions | |
racuse | -3.532 |
senal | -3.514 |
experien | -3.504 |
lette | -3.364 |
hers | -3.333 |
Token | min |
Token ID | 1084 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ades | +1.262 |
emi | +1.206 |
ade | +1.134 |
ghai | +1.113 |
anging | +1.109 |
Neg logit contributions | |
hers | -0.529 |
experien | -0.514 |
racuse | -0.511 |
lette | -0.501 |
pict | -0.487 |
Token | that |
Token ID | 326 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
ades | +1.543 |
emi | +1.442 |
ade | +1.325 |
ghai | +1.278 |
anging | +1.275 |
Neg logit contributions | |
racuse | -1.621 |
hers | -1.585 |
experien | -1.566 |
lette | -1.558 |
Admin | -1.538 |
Token | sparked |
Token ID | 16752 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
hers | +0.310 |
racuse | +0.308 |
lette | +0.304 |
experien | +0.299 |
pict | +0.297 |
Neg logit contributions | |
ades | -0.345 |
emi | -0.320 |
ade | -0.298 |
ghai | -0.290 |
anging | -0.289 |
Token | all |
Token ID | 477 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ades | +2.613 |
emi | +2.469 |
ade | +2.219 |
ghai | +2.162 |
anging | +2.141 |
Neg logit contributions | |
racuse | -2.718 |
hers | -2.681 |
lette | -2.648 |
experien | -2.630 |
Admin | -2.612 |
Token | this |
Token ID | 428 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ades | +4.086 |
emi | +3.807 |
ade | +3.455 |
ghai | +3.430 |
anging | +3.371 |
Neg logit contributions | |
hers | -4.858 |
racuse | -4.829 |
experien | -4.739 |
lette | -4.738 |
senal | -4.691 |
Token | h |
Token ID | 289 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
ades | +3.616 |
emi | +3.439 |
ade | +3.150 |
ghai | +3.079 |
anging | +3.054 |
Neg logit contributions | |
racuse | -3.651 |
hers | -3.615 |
senal | -3.521 |
lette | -3.478 |
ento | -3.476 |
Token | oo |
Token ID | 2238 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
ades | +7.064 |
emi | +6.696 |
anging | +6.391 |
ade | +6.231 |
ghai | +5.859 |
Neg logit contributions | |
senal | -8.347 |
racuse | -8.081 |
experien | -8.015 |
hers | -7.733 |
Admin | -7.682 |
Token | - |
Token ID | 12 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ades | +8.984 |
emi | +8.710 |
anging | +8.510 |
ade | +8.327 |
ghai | +7.901 |
Neg logit contributions | |
senal | -10.142 |
racuse | -9.579 |
experien | -9.480 |
Admin | -9.181 |
ento | -8.906 |
Token | fer |
Token ID | 2232 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
ades | +4.312 |
emi | +3.906 |
ade | +3.669 |
anging | +3.622 |
ghai | +3.542 |
Neg logit contributions | |
experien | -4.897 |
senal | -4.757 |
racuse | -4.733 |
lette | -4.649 |
Admin | -4.616 |
Token | - |
Token ID | 12 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
hers | +0.977 |
racuse | +0.975 |
experien | +0.967 |
lette | +0.958 |
Admin | +0.938 |
Neg logit contributions | |
ades | -1.037 |
emi | -0.967 |
ade | -0.897 |
ghai | -0.876 |
anging | -0.874 |
Token | ah |
Token ID | 993 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
experien | +0.678 |
racuse | +0.677 |
lette | +0.677 |
hers | +0.675 |
Admin | +0.655 |
Neg logit contributions | |
ades | -0.750 |
emi | -0.697 |
ade | -0.646 |
ghai | -0.635 |
anging | -0.631 |
Token | h |
Token ID | 71 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
ades | +3.499 |
emi | +3.180 |
ade | +3.050 |
anging | +2.941 |
ghai | +2.908 |
Neg logit contributions | |
racuse | -3.300 |
experien | -3.236 |
Admin | -3.203 |
lette | -3.168 |
hers | -3.164 |
Token | Read |
Token ID | 5569 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
hers | +0.282 |
experien | +0.279 |
racuse | +0.277 |
lette | +0.277 |
senal | +0.266 |
Neg logit contributions | |
ades | -0.302 |
emi | -0.286 |
ade | -0.262 |
ghai | -0.255 |
anging | -0.255 |
Token | More |
Token ID | 3125 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ades | +1.034 |
emi | +0.973 |
ade | +0.885 |
ghai | +0.862 |
anging | +0.849 |
Neg logit contributions | |
hers | -1.107 |
racuse | -1.099 |
experien | -1.096 |
lette | -1.089 |
senal | -1.065 |
Token | About |
Token ID | 7994 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
hers | +0.580 |
lette | +0.574 |
racuse | +0.574 |
experien | +0.570 |
ento | +0.555 |
Neg logit contributions | |
ades | -0.451 |
emi | -0.416 |
ade | -0.379 |
ghai | -0.370 |
anging | -0.359 |
Token | B |
Token ID | 347 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
hers | +1.801 |
lette | +1.772 |
racuse | +1.766 |
experien | +1.764 |
pict | +1.726 |
Neg logit contributions | |
ades | -1.481 |
emi | -1.372 |
ade | -1.247 |
ghai | -1.224 |
anging | -1.199 |
Token | ala |
Token ID | 6081 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ades | +0.955 |
emi | +0.895 |
ade | +0.808 |
anging | +0.787 |
ghai | +0.785 |
Neg logit contributions | |
hers | -1.145 |
racuse | -1.136 |
experien | -1.136 |
lette | -1.124 |
pict | -1.107 |
Token | Han |
Token ID | 9530 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
ades | +0.779 |
emi | +0.702 |
ade | +0.619 |
ghai | +0.611 |
anging | +0.583 |
Neg logit contributions | |
racuse | -1.615 |
hers | -1.595 |
lette | -1.580 |
experien | -1.579 |
senal | -1.569 |
Token | uman |
Token ID | 3778 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
ades | +5.584 |
emi | +4.906 |
ade | +4.350 |
ghai | +4.031 |
anging | +3.609 |
Neg logit contributions | |
senal | -15.192 |
experien | -14.205 |
racuse | -13.902 |
pict | -13.637 |
lette | -13.631 |
Token | Temple |
Token ID | 10857 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
ades | +2.231 |
emi | +2.054 |
ade | +1.914 |
ghai | +1.839 |
anging | +1.728 |
Neg logit contributions | |
racuse | -2.985 |
hers | -2.971 |
experien | -2.937 |
senal | -2.931 |
lette | -2.926 |
Token | Here |
Token ID | 3423 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
ades | +1.586 |
emi | +1.504 |
ade | +1.378 |
ghai | +1.354 |
anging | +1.308 |
Neg logit contributions | |
racuse | -1.655 |
hers | -1.636 |
experien | -1.628 |
lette | -1.615 |
Admin | -1.566 |
Token |
|
Token ID | 198 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
hers | +1.620 |
lette | +1.584 |
racuse | +1.575 |
experien | +1.569 |
pict | +1.539 |
Neg logit contributions | |
ades | -1.880 |
emi | -1.770 |
ade | -1.627 |
ghai | -1.603 |
anging | -1.587 |
Token |
|
Token ID | 198 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ades | +0.629 |
emi | +0.590 |
ade | +0.546 |
ghai | +0.530 |
anging | +0.526 |
Neg logit contributions | |
hers | -0.588 |
experien | -0.584 |
racuse | -0.582 |
lette | -0.578 |
senal | -0.573 |
Token | with |
Token ID | 351 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
ades | +0.866 |
emi | +0.817 |
ade | +0.752 |
ghai | +0.718 |
anging | +0.717 |
Neg logit contributions | |
hers | -0.880 |
racuse | -0.856 |
lette | -0.840 |
experien | -0.834 |
senal | -0.819 |
Token | a |
Token ID | 257 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
ades | +0.763 |
emi | +0.723 |
ade | +0.662 |
anging | +0.637 |
ghai | +0.628 |
Neg logit contributions | |
hers | -0.713 |
racuse | -0.713 |
lette | -0.696 |
experien | -0.686 |
senal | -0.681 |
Token | football |
Token ID | 4346 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ades | +1.123 |
emi | +1.067 |
ade | +0.984 |
anging | +0.949 |
ghai | +0.936 |
Neg logit contributions | |
hers | -0.996 |
racuse | -0.992 |
lette | -0.968 |
experien | -0.966 |
pict | -0.954 |
Token | treatment |
Token ID | 3513 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
ades | +0.409 |
emi | +0.388 |
ade | +0.364 |
anging | +0.346 |
ghai | +0.345 |
Neg logit contributions | |
racuse | -0.323 |
hers | -0.321 |
lette | -0.315 |
pict | -0.313 |
experien | -0.312 |
Token | !) |
Token ID | 8133 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
hers | +1.583 |
racuse | +1.567 |
lette | +1.535 |
experien | +1.532 |
pict | +1.507 |
Neg logit contributions | |
ades | -1.741 |
emi | -1.641 |
ade | -1.515 |
ghai | -1.471 |
anging | -1.463 |
Token | HA |
Token ID | 14558 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
ades | +3.600 |
emi | +3.466 |
ade | +3.197 |
anging | +3.032 |
ghai | +2.968 |
Neg logit contributions | |
racuse | -3.693 |
lette | -3.542 |
hers | -3.531 |
senal | -3.511 |
experien | -3.437 |
Token | IRD |
Token ID | 46833 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
emi | +8.469 |
ades | +8.454 |
ade | +7.609 |
anging | +7.136 |
overed | +7.048 |
Neg logit contributions | |
racuse | -10.073 |
entin | -9.894 |
hers | -9.877 |
lette | -9.771 |
ento | -9.742 |
Token | RI |
Token ID | 7112 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
ades | +1.236 |
emi | +1.175 |
ade | +1.103 |
anging | +1.046 |
aye | +1.026 |
Neg logit contributions | |
racuse | -1.126 |
hers | -1.113 |
experien | -1.100 |
lette | -1.086 |
senal | -1.076 |
Token | ER |
Token ID | 1137 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
ades | +3.156 |
emi | +3.019 |
ade | +2.830 |
anging | +2.646 |
aye | +2.610 |
Neg logit contributions | |
racuse | -3.055 |
hers | -2.974 |
experien | -2.908 |
pict | -2.878 |
lette | -2.878 |
Token |
|
Token ID | 198 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
ades | +1.384 |
emi | +1.297 |
ade | +1.212 |
anging | +1.153 |
ghai | +1.141 |
Neg logit contributions | |
racuse | -1.413 |
hers | -1.405 |
lette | -1.379 |
experien | -1.370 |
senal | -1.362 |
Token |
|
Token ID | 198 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ades | +1.045 |
emi | +0.977 |
ade | +0.908 |
ghai | +0.875 |
anging | +0.870 |
Neg logit contributions | |
senal | -1.010 |
experien | -1.009 |
hers | -1.007 |
racuse | -1.005 |
lette | -0.993 |
Token |
|
Token ID | 198 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
ades | +0.717 |
emi | +0.672 |
ade | +0.622 |
ghai | +0.603 |
anging | +0.599 |
Neg logit contributions | |
hers | -0.675 |
experien | -0.672 |
racuse | -0.669 |
lette | -0.663 |
senal | -0.662 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ades | +0.889 |
emi | +0.824 |
ade | +0.754 |
ghai | +0.718 |
anging | +0.714 |
Neg logit contributions | |
hers | -1.262 |
experien | -1.260 |
racuse | -1.252 |
lette | -1.247 |
entin | -1.198 |
Token | . |
Token ID | 13 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
ades | +0.746 |
emi | +0.704 |
ade | +0.658 |
ghai | +0.642 |
anging | +0.635 |
Neg logit contributions | |
hers | -0.552 |
experien | -0.548 |
racuse | -0.545 |
lette | -0.539 |
senal | -0.530 |
Token | B |
Token ID | 347 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
ades | +1.756 |
emi | +1.647 |
ade | +1.501 |
ghai | +1.435 |
anging | +1.413 |
Neg logit contributions | |
racuse | -2.063 |
hers | -2.062 |
lette | -2.035 |
experien | -2.034 |
senal | -1.969 |
Token | ala |
Token ID | 6081 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
ades | +2.025 |
emi | +1.897 |
ade | +1.754 |
anging | +1.687 |
ghai | +1.644 |
Neg logit contributions | |
racuse | -2.053 |
experien | -2.019 |
lette | -1.989 |
hers | -1.973 |
pict | -1.962 |
Token | Han |
Token ID | 9530 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
ades | +0.524 |
emi | +0.489 |
ade | +0.449 |
ghai | +0.425 |
anging | +0.423 |
Neg logit contributions | |
racuse | -0.618 |
hers | -0.608 |
experien | -0.604 |
lette | -0.602 |
pict | -0.590 |
Token | uman |
Token ID | 3778 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
ades | +9.211 |
emi | +8.346 |
ade | +7.879 |
aye | +7.373 |
ghai | +7.305 |
Neg logit contributions | |
racuse | -10.734 |
senal | -10.426 |
experien | -10.314 |
hers | -9.538 |
lette | -9.494 |
Token | Mand |
Token ID | 13314 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ades | +2.403 |
emi | +2.222 |
ade | +2.090 |
ghai | +1.960 |
aye | +1.906 |
Neg logit contributions | |
racuse | -2.945 |
experien | -2.865 |
hers | -2.833 |
lette | -2.804 |
senal | -2.788 |
Token | ir |
Token ID | 343 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
hers | +3.307 |
lette | +3.237 |
racuse | +3.223 |
experien | +3.217 |
pict | +3.143 |
Neg logit contributions | |
ades | -3.776 |
emi | -3.554 |
ade | -3.268 |
ghai | -3.218 |
anging | -3.183 |
Token |
|
Token ID | 198 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
hers | +2.646 |
racuse | +2.602 |
lette | +2.593 |
experien | +2.592 |
pict | +2.523 |
Neg logit contributions | |
ades | -2.792 |
emi | -2.621 |
ade | -2.410 |
ghai | -2.357 |
anging | -2.333 |
Token |
|
Token ID | 198 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
ades | +0.235 |
emi | +0.221 |
ade | +0.204 |
ghai | +0.200 |
anging | +0.198 |
Neg logit contributions | |
hers | -0.209 |
lette | -0.205 |
racuse | -0.205 |
experien | -0.205 |
pict | -0.199 |
Token | ] |
Token ID | 60 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
racuse | +0.356 |
hers | +0.356 |
experien | +0.350 |
lette | +0.349 |
pict | +0.342 |
Neg logit contributions | |
ades | -0.485 |
emi | -0.453 |
ade | -0.426 |
anging | -0.415 |
ghai | -0.414 |
Token |
|
Token ID | 198 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
ades | +2.058 |
emi | +1.924 |
ade | +1.763 |
anging | +1.670 |
ghai | +1.666 |
Neg logit contributions | |
racuse | -2.633 |
hers | -2.563 |
experien | -2.551 |
lette | -2.535 |
senal | -2.518 |
Token |
|
Token ID | 198 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
ades | +0.184 |
emi | +0.173 |
ade | +0.159 |
ghai | +0.156 |
anging | +0.155 |
Neg logit contributions | |
hers | -0.163 |
lette | -0.160 |
racuse | -0.160 |
experien | -0.160 |
pict | -0.155 |
Token | RF |
Token ID | 32754 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
racuse | +1.472 |
hers | +1.469 |
experien | +1.459 |
lette | +1.444 |
senal | +1.409 |
Neg logit contributions | |
ades | -1.232 |
emi | -1.143 |
ade | -1.058 |
anging | -1.016 |
ghai | -1.013 |
Token | : |
Token ID | 25 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
hers | +1.249 |
lette | +1.218 |
racuse | +1.201 |
experien | +1.196 |
pict | +1.181 |
Neg logit contributions | |
ades | -1.630 |
emi | -1.543 |
ade | -1.417 |
ghai | -1.410 |
anging | -1.393 |
Token | Ho |
Token ID | 9544 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
ades | +1.133 |
emi | +1.054 |
ade | +0.966 |
anging | +0.919 |
ghai | +0.915 |
Neg logit contributions | |
racuse | -1.426 |
hers | -1.409 |
experien | -1.392 |
lette | -1.390 |
senal | -1.366 |
Token | ho |
Token ID | 8169 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
ades | +8.473 |
emi | +8.088 |
anging | +7.661 |
ade | +7.628 |
overed | +7.258 |
Neg logit contributions | |
racuse | -10.200 |
senal | -10.195 |
experien | -9.767 |
pict | -9.753 |
Admin | -9.344 |
Token | ! |
Token ID | 0 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
ades | +5.672 |
emi | +5.225 |
ade | +4.878 |
anging | +4.706 |
ghai | +4.568 |
Neg logit contributions | |
racuse | -6.830 |
senal | -6.526 |
pict | -6.524 |
experien | -6.509 |
Admin | -6.499 |
Token | [ |
Token ID | 685 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
ades | +5.627 |
emi | +5.220 |
ade | +4.921 |
Kappa | +4.804 |
Phi | +4.667 |
Neg logit contributions | |
racuse | -7.304 |
senal | -7.014 |
experien | -6.984 |
lette | -6.881 |
hers | -6.858 |
Token | Pause |
Token ID | 49991 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ades | +0.187 |
emi | +0.174 |
ade | +0.164 |
anging | +0.162 |
ghai | +0.158 |
Neg logit contributions | |
racuse | -0.158 |
experien | -0.154 |
lette | -0.151 |
hers | -0.151 |
pict | -0.146 |
Token | ] |
Token ID | 60 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
ades | +3.911 |
emi | +3.509 |
ade | +3.423 |
anging | +3.250 |
end | +3.135 |
Neg logit contributions | |
racuse | -3.642 |
experien | -3.476 |
hers | -3.454 |
senal | -3.450 |
Admin | -3.432 |
Token | but |
Token ID | 475 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
ades | +2.868 |
emi | +2.598 |
ade | +2.360 |
anging | +2.208 |
ghai | +2.156 |
Neg logit contributions | |
lette | -4.321 |
racuse | -4.314 |
hers | -4.264 |
Admin | -4.204 |
senal | -4.191 |
Token | the |
Token ID | 262 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
ades | +3.188 |
emi | +2.940 |
ade | +2.746 |
ghai | +2.619 |
anging | +2.599 |
Neg logit contributions | |
racuse | -3.197 |
hers | -3.183 |
lette | -3.178 |
pict | -3.172 |
senal | -3.131 |
Token | decisions |
Token ID | 5370 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
ades | +0.158 |
emi | +0.148 |
ade | +0.135 |
ghai | +0.131 |
anging | +0.131 |
Neg logit contributions | |
hers | -0.159 |
lette | -0.157 |
racuse | -0.156 |
experien | -0.154 |
pict | -0.153 |
Token | made |
Token ID | 925 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ades | +1.604 |
emi | +1.537 |
ade | +1.404 |
ghai | +1.362 |
anging | +1.354 |
Neg logit contributions | |
hers | -1.467 |
racuse | -1.461 |
lette | -1.458 |
experien | -1.435 |
pict | -1.433 |
Token | in |
Token ID | 287 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
hers | +0.700 |
lette | +0.688 |
racuse | +0.687 |
experien | +0.686 |
pict | +0.671 |
Neg logit contributions | |
ades | -0.759 |
emi | -0.715 |
ade | -0.658 |
ghai | -0.641 |
anging | -0.635 |
Token | Hawai |
Token ID | 10847 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
ades | +0.974 |
emi | +0.902 |
ade | +0.820 |
anging | +0.789 |
ghai | +0.783 |
Neg logit contributions | |
hers | -1.214 |
lette | -1.207 |
racuse | -1.201 |
pict | -1.182 |
experien | -1.182 |
Token | ` |
Token ID | 63 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
ades | +10.365 |
emi | +9.546 |
ade | +9.052 |
ghai | +8.911 |
anging | +8.625 |
Neg logit contributions | |
senal | -8.927 |
racuse | -8.919 |
experien | -8.279 |
entin | -8.096 |
pict | -7.891 |
Token | i |
Token ID | 72 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
ades | +2.774 |
emi | +2.617 |
ade | +2.426 |
ghai | +2.360 |
anging | +2.329 |
Neg logit contributions | |
racuse | -2.260 |
senal | -2.220 |
experien | -2.204 |
lette | -2.199 |
hers | -2.191 |
Token | in |
Token ID | 287 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
ades | +2.897 |
emi | +2.764 |
ade | +2.541 |
ghai | +2.435 |
anging | +2.378 |
Neg logit contributions | |
racuse | -2.755 |
lette | -2.730 |
experien | -2.725 |
hers | -2.724 |
senal | -2.627 |
Token | 2015 |
Token ID | 1853 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
ades | +0.827 |
emi | +0.771 |
ade | +0.704 |
anging | +0.677 |
ghai | +0.671 |
Neg logit contributions | |
lette | -0.910 |
racuse | -0.908 |
hers | -0.908 |
experien | -0.888 |
pict | -0.883 |
Token | and |
Token ID | 290 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ades | +1.888 |
emi | +1.806 |
ade | +1.660 |
anging | +1.569 |
ghai | +1.553 |
Neg logit contributions | |
hers | -1.847 |
experien | -1.833 |
racuse | -1.822 |
lette | -1.809 |
pict | -1.787 |
Token | chairman |
Token ID | 8900 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ades | +3.306 |
emi | +3.169 |
ade | +2.902 |
ghai | +2.790 |
anging | +2.752 |
Neg logit contributions | |
racuse | -3.489 |
pict | -3.280 |
hers | -3.261 |
lette | -3.238 |
experien | -3.185 |
Token | Kan |
Token ID | 14248 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ades | +3.276 |
emi | +3.092 |
ade | +2.815 |
ghai | +2.682 |
anging | +2.626 |
Neg logit contributions | |
racuse | -3.870 |
hers | -3.720 |
experien | -3.703 |
senal | -3.668 |
pict | -3.659 |
Token | ek |
Token ID | 988 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
ades | +3.901 |
emi | +3.690 |
ade | +3.491 |
ghai | +3.300 |
aye | +3.164 |
Neg logit contributions | |
racuse | -3.880 |
experien | -3.819 |
hers | -3.691 |
senal | -3.682 |
Admin | -3.630 |
Token | o |
Token ID | 78 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ades | +2.792 |
emi | +2.630 |
ade | +2.500 |
ghai | +2.373 |
aye | +2.343 |
Neg logit contributions | |
racuse | -2.131 |
experien | -2.103 |
hers | -2.068 |
lette | -2.065 |
senal | -2.034 |
Token | " |
Token ID | 366 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
ades | +3.276 |
emi | +3.191 |
ade | +2.810 |
ghai | +2.694 |
anging | +2.576 |
Neg logit contributions | |
racuse | -4.546 |
hers | -4.454 |
experien | -4.445 |
lette | -4.332 |
pict | -4.314 |
Token | H |
Token ID | 39 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
ades | +1.620 |
emi | +1.517 |
ade | +1.420 |
ghai | +1.363 |
anging | +1.350 |
Neg logit contributions | |
racuse | -1.445 |
experien | -1.415 |
hers | -1.397 |
lette | -1.385 |
senal | -1.329 |
Token | ame |
Token ID | 480 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
ades | +10.516 |
emi | +9.881 |
ade | +9.146 |
anging | +9.011 |
end | +8.714 |
Neg logit contributions | |
senal | -8.613 |
racuse | -8.599 |
experien | -8.423 |
hers | -8.283 |
pict | -8.032 |
Token | ko |
Token ID | 7204 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
ades | +2.492 |
emi | +2.434 |
ade | +2.225 |
ghai | +2.160 |
aye | +2.079 |
Neg logit contributions | |
racuse | -2.117 |
hers | -2.095 |
experien | -2.062 |
pict | -2.027 |
senal | -2.015 |
Token | " |
Token ID | 1 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ades | +5.538 |
emi | +5.424 |
ade | +4.975 |
ghai | +4.777 |
anging | +4.658 |
Neg logit contributions | |
hers | -4.300 |
racuse | -4.281 |
experien | -4.261 |
lette | -4.143 |
pict | -4.111 |
Token | Nor |
Token ID | 5414 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
ades | +3.322 |
emi | +3.184 |
ade | +2.853 |
ghai | +2.678 |
Kappa | +2.596 |
Neg logit contributions | |
racuse | -4.308 |
experien | -4.273 |
hers | -4.256 |
senal | -4.162 |
lette | -4.151 |
Token | iy |
Token ID | 7745 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
hers | +1.098 |
experien | +1.093 |
racuse | +1.088 |
lette | +1.074 |
pict | +1.053 |
Neg logit contributions | |
ades | -0.882 |
emi | -0.818 |
ade | -0.748 |
ghai | -0.714 |
anging | -0.704 |
Token | sc |
Token ID | 629 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ades | +0.054 |
emi | +0.050 |
ade | +0.046 |
anging | +0.045 |
ghai | +0.044 |
Neg logit contributions | |
racuse | -0.056 |
hers | -0.056 |
lette | -0.055 |
experien | -0.054 |
pict | -0.054 |
Token | ound |
Token ID | 633 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
ades | +0.800 |
emi | +0.699 |
ade | +0.647 |
anging | +0.607 |
ghai | +0.588 |
Neg logit contributions | |
experien | -1.608 |
senal | -1.598 |
racuse | -1.588 |
hers | -1.569 |
lette | -1.566 |
Token | rel |
Token ID | 2411 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
ades | +1.060 |
emi | +0.971 |
ade | +0.913 |
anging | +0.885 |
azaki | +0.828 |
Neg logit contributions | |
senal | -1.561 |
hers | -1.555 |
experien | -1.542 |
racuse | -1.517 |
itives | -1.509 |
Token | Vac |
Token ID | 25709 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ades | +0.202 |
emi | +0.187 |
ade | +0.174 |
anging | +0.166 |
ghai | +0.164 |
Neg logit contributions | |
racuse | -0.214 |
hers | -0.208 |
lette | -0.207 |
experien | -0.206 |
pict | -0.202 |
Token | lav |
Token ID | 18809 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
hers | +6.182 |
lette | +6.101 |
experien | +6.030 |
racuse | +6.023 |
pict | +5.979 |
Neg logit contributions | |
ades | -1.451 |
emi | -1.194 |
ghai | -0.892 |
ade | -0.889 |
anging | -0.827 |
Token | Ha |
Token ID | 9398 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
hers | +2.336 |
racuse | +2.304 |
experien | +2.302 |
lette | +2.299 |
pict | +2.267 |
Neg logit contributions | |
ades | -0.943 |
emi | -0.833 |
ade | -0.705 |
ghai | -0.678 |
anging | -0.660 |
Token | vel |
Token ID | 626 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ades | +4.276 |
emi | +4.251 |
ade | +3.455 |
end | +2.934 |
ghai | +2.427 |
Neg logit contributions | |
senal | -15.245 |
experien | -15.005 |
racuse | -14.922 |
Admin | -14.303 |
pict | -14.224 |
Token | coined |
Token ID | 33115 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
hers | +1.176 |
racuse | +1.169 |
experien | +1.158 |
lette | +1.135 |
pict | +1.127 |
Neg logit contributions | |
ades | -1.445 |
emi | -1.340 |
ade | -1.262 |
anging | -1.220 |
ghai | -1.214 |
Token | the |
Token ID | 262 |
Feature activation | -3.35e-03 |
Pos logit contributions | |
ades | +0.963 |
emi | +0.891 |
ade | +0.823 |
anging | +0.783 |
ghai | +0.783 |
Neg logit contributions | |
racuse | -1.016 |
hers | -1.013 |
lette | -1.009 |
experien | -1.006 |
Admin | -0.982 |
Token | Orwell |
Token ID | 32226 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
ades | +0.010 |
emi | +0.010 |
ade | +0.009 |
anging | +0.008 |
ghai | +0.008 |
Neg logit contributions | |
hers | -0.012 |
racuse | -0.012 |
lette | -0.012 |
experien | -0.012 |
pict | -0.011 |
Token | ian |
Token ID | 666 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
ades | +0.540 |
emi | +0.480 |
ade | +0.401 |
anging | +0.371 |
ghai | +0.356 |
Neg logit contributions | |
racuse | -1.496 |
hers | -1.495 |
experien | -1.491 |
lette | -1.479 |
Admin | -1.463 |
Token | articles |
Token ID | 6685 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
hers | +5.605 |
lette | +5.498 |
experien | +5.468 |
racuse | +5.383 |
pict | +5.340 |
Neg logit contributions | |
ades | -4.993 |
emi | -4.688 |
ade | -4.205 |
ghai | -4.200 |
anging | -4.112 |
Token | of |
Token ID | 286 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
hers | +1.785 |
racuse | +1.756 |
lette | +1.745 |
experien | +1.735 |
pict | +1.703 |
Neg logit contributions | |
ades | -2.107 |
emi | -1.989 |
ade | -1.834 |
ghai | -1.796 |
anging | -1.784 |
Token | the |
Token ID | 262 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
ades | +0.409 |
emi | +0.384 |
ade | +0.346 |
anging | +0.341 |
ghai | +0.335 |
Neg logit contributions | |
hers | -0.488 |
racuse | -0.486 |
lette | -0.481 |
experien | -0.478 |
pict | -0.472 |
Token | year |
Token ID | 614 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
ades | +0.938 |
emi | +0.868 |
ade | +0.791 |
anging | +0.760 |
ghai | +0.741 |
Neg logit contributions | |
racuse | -1.266 |
hers | -1.256 |
lette | -1.248 |
pict | -1.225 |
experien | -1.224 |
Token | . |
Token ID | 13 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
hers | +1.879 |
racuse | +1.852 |
experien | +1.831 |
lette | +1.829 |
pict | +1.795 |
Neg logit contributions | |
ades | -2.299 |
emi | -2.165 |
ade | -2.005 |
ghai | -1.949 |
anging | -1.946 |
Token | Happy |
Token ID | 14628 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
ades | +0.896 |
emi | +0.851 |
ade | +0.776 |
anging | +0.744 |
ghai | +0.742 |
Neg logit contributions | |
racuse | -0.989 |
hers | -0.985 |
experien | -0.979 |
lette | -0.969 |
senal | -0.956 |
Token | Hol |
Token ID | 6479 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ades | +8.099 |
emi | +7.001 |
ade | +6.779 |
holidays | +6.679 |
anging | +6.418 |
Neg logit contributions | |
racuse | -10.479 |
senal | -9.958 |
lette | -9.727 |
hers | -9.693 |
ento | -9.659 |
Token | idays |
Token ID | 13842 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
ades | +0.712 |
emi | +0.637 |
ade | +0.579 |
anging | +0.554 |
ghai | +0.528 |
Neg logit contributions | |
racuse | -1.018 |
experien | -0.997 |
hers | -0.981 |
senal | -0.963 |
lette | -0.962 |
Token | ! |
Token ID | 0 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ades | +2.720 |
emi | +2.518 |
ade | +2.324 |
anging | +2.190 |
ghai | +2.147 |
Neg logit contributions | |
racuse | -3.093 |
experien | -3.000 |
lette | -2.991 |
hers | -2.976 |
pict | -2.969 |
Token | -- |
Token ID | 1377 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
ades | +4.325 |
emi | +4.148 |
ade | +3.738 |
anging | +3.599 |
end | +3.583 |
Neg logit contributions | |
racuse | -5.281 |
experien | -5.207 |
hers | -5.182 |
senal | -5.082 |
lette | -5.059 |
Token | Remy |
Token ID | 32912 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ades | +0.836 |
emi | +0.791 |
ade | +0.729 |
anging | +0.703 |
ghai | +0.694 |
Neg logit contributions | |
racuse | -0.735 |
experien | -0.732 |
hers | -0.731 |
lette | -0.717 |
pict | -0.702 |
Token | stage |
Token ID | 3800 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
racuse | +0.543 |
hers | +0.541 |
lette | +0.534 |
experien | +0.529 |
pict | +0.518 |
Neg logit contributions | |
ades | -0.652 |
emi | -0.604 |
ade | -0.564 |
anging | -0.548 |
ghai | -0.546 |
Token | yelling |
Token ID | 22187 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
racuse | +0.409 |
hers | +0.406 |
lette | +0.399 |
experien | +0.398 |
Admin | +0.389 |
Neg logit contributions | |
ades | -0.449 |
emi | -0.416 |
ade | -0.388 |
anging | -0.376 |
ghai | -0.376 |
Token | at |
Token ID | 379 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
ades | +1.920 |
emi | +1.802 |
ade | +1.664 |
anging | +1.614 |
ghai | +1.576 |
Neg logit contributions | |
racuse | -2.090 |
lette | -2.020 |
hers | -2.000 |
experien | -1.973 |
Admin | -1.943 |
Token | everyone |
Token ID | 2506 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
racuse | +1.026 |
hers | +1.023 |
lette | +1.016 |
experien | +1.002 |
pict | +0.988 |
Neg logit contributions | |
ades | -1.108 |
emi | -1.035 |
ade | -0.959 |
anging | -0.937 |
ghai | -0.924 |
Token | ! |
Token ID | 0 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ades | +3.982 |
emi | +3.668 |
ade | +3.443 |
anging | +3.402 |
ghai | +3.283 |
Neg logit contributions | |
racuse | -4.277 |
senal | -4.159 |
experien | -4.061 |
Admin | -4.047 |
lette | -4.044 |
Token | H |
Token ID | 367 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
ades | +4.204 |
emi | +3.920 |
ade | +3.639 |
anging | +3.521 |
ghai | +3.482 |
Neg logit contributions | |
racuse | -5.354 |
senal | -5.238 |
lette | -5.212 |
experien | -5.200 |
hers | -5.161 |
Token | ah |
Token ID | 993 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
ades | +8.610 |
anging | +8.156 |
emi | +8.039 |
ade | +7.627 |
aye | +6.762 |
Neg logit contributions | |
senal | -10.247 |
experien | -9.913 |
lette | -9.787 |
hers | -9.787 |
racuse | -9.766 |
Token | aha |
Token ID | 12236 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ades | +5.650 |
emi | +5.270 |
ade | +4.871 |
anging | +4.623 |
aye | +4.382 |
Neg logit contributions | |
racuse | -9.282 |
senal | -9.157 |
experien | -9.072 |
lette | -8.991 |
pict | -8.897 |
Token | ! |
Token ID | 0 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
ades | +6.127 |
emi | +5.805 |
ade | +5.308 |
anging | +5.156 |
ghai | +4.966 |
Neg logit contributions | |
racuse | -7.460 |
senal | -7.267 |
lette | -7.177 |
experien | -7.102 |
Admin | -7.059 |
Token |
|
Token ID | 198 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
ades | +5.880 |
emi | +5.493 |
ade | +5.105 |
Kappa | +4.911 |
anging | +4.905 |
Neg logit contributions | |
racuse | -8.043 |
senal | -7.933 |
lette | -7.722 |
experien | -7.657 |
hers | -7.589 |
Token |
|
Token ID | 198 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
ades | +1.780 |
emi | +1.663 |
ade | +1.547 |
ghai | +1.476 |
anging | +1.471 |
Neg logit contributions | |
senal | -1.876 |
experien | -1.833 |
racuse | -1.820 |
hers | -1.806 |
lette | -1.782 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
experien | +0.519 |
racuse | +0.511 |
hers | +0.510 |
pict | +0.496 |
lette | +0.491 |
Neg logit contributions | |
ades | -0.543 |
emi | -0.509 |
ade | -0.477 |
anging | -0.462 |
ghai | -0.458 |
Token | � |
Token ID | 447 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ades | +0.562 |
emi | +0.533 |
ade | +0.502 |
ghai | +0.488 |
anging | +0.481 |
Neg logit contributions | |
experien | -0.328 |
hers | -0.326 |
racuse | -0.323 |
lette | -0.322 |
pict | -0.305 |
Token | � |
Token ID | 251 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
hers | +1.014 |
racuse | +1.005 |
lette | +1.002 |
experien | +1.002 |
pict | +0.984 |
Neg logit contributions | |
ades | -0.441 |
emi | -0.394 |
ade | -0.339 |
ghai | -0.327 |
anging | -0.319 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
hers | +0.898 |
lette | +0.879 |
experien | +0.875 |
racuse | +0.875 |
pict | +0.853 |
Neg logit contributions | |
ades | -1.019 |
emi | -0.959 |
ade | -0.882 |
ghai | -0.868 |
anging | -0.858 |
Token |
|
Token ID | 198 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
ades | +0.486 |
emi | +0.456 |
ade | +0.421 |
ghai | +0.411 |
anging | +0.407 |
Neg logit contributions | |
hers | -0.444 |
experien | -0.438 |
racuse | -0.438 |
lette | -0.435 |
senal | -0.424 |
Token | H |
Token ID | 39 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
experien | +0.068 |
racuse | +0.068 |
hers | +0.067 |
lette | +0.066 |
senal | +0.066 |
Neg logit contributions | |
ades | -0.089 |
emi | -0.083 |
ade | -0.078 |
anging | -0.075 |
ghai | -0.075 |
Token | ints |
Token ID | 29503 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
ades | +8.077 |
emi | +7.125 |
anging | +6.814 |
ade | +6.685 |
end | +5.924 |
Neg logit contributions | |
senal | -11.536 |
experien | -11.076 |
hers | -10.814 |
racuse | -10.786 |
lette | -10.553 |
Token | on |
Token ID | 319 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
ades | +1.934 |
emi | +1.831 |
ade | +1.691 |
ghai | +1.635 |
anging | +1.617 |
Neg logit contributions | |
experien | -1.787 |
hers | -1.786 |
racuse | -1.778 |
lette | -1.761 |
pict | -1.721 |
Token | Et |
Token ID | 17906 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
ades | +0.234 |
emi | +0.215 |
ade | +0.197 |
ghai | +0.188 |
anging | +0.188 |
Neg logit contributions | |
hers | -0.302 |
racuse | -0.297 |
lette | -0.297 |
experien | -0.295 |
pict | -0.287 |
Token | iquette |
Token ID | 40387 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
hers | +0.966 |
lette | +0.925 |
racuse | +0.900 |
experien | +0.883 |
pict | +0.867 |
Neg logit contributions | |
ades | -3.039 |
emi | -2.915 |
ade | -2.742 |
ghai | -2.728 |
anging | -2.709 |
Token | and |
Token ID | 290 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
ades | +0.365 |
emi | +0.337 |
ade | +0.313 |
ghai | +0.299 |
anging | +0.298 |
Neg logit contributions | |
hers | -0.425 |
experien | -0.420 |
racuse | -0.420 |
lette | -0.416 |
pict | -0.408 |
Token | still |
Token ID | 991 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
racuse | +0.764 |
hers | +0.751 |
lette | +0.746 |
experien | +0.736 |
pict | +0.731 |
Neg logit contributions | |
ades | -0.902 |
emi | -0.856 |
ade | -0.786 |
anging | -0.770 |
ghai | -0.766 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
racuse | +0.357 |
hers | +0.350 |
lette | +0.346 |
experien | +0.342 |
pict | +0.340 |
Neg logit contributions | |
ades | -0.429 |
emi | -0.405 |
ade | -0.374 |
anging | -0.365 |
ghai | -0.364 |
Token | . |
Token ID | 13 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
ades | +4.031 |
emi | +3.770 |
ade | +3.462 |
anging | +3.432 |
ghai | +3.290 |
Neg logit contributions | |
racuse | -4.368 |
senal | -4.265 |
hers | -4.116 |
lette | -4.048 |
pict | -4.025 |
Token |
|
Token ID | 198 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
ades | +1.587 |
emi | +1.500 |
ade | +1.367 |
anging | +1.295 |
ghai | +1.293 |
Neg logit contributions | |
racuse | -1.941 |
experien | -1.917 |
hers | -1.898 |
senal | -1.891 |
lette | -1.887 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
hers | +0.302 |
lette | +0.296 |
racuse | +0.295 |
experien | +0.295 |
pict | +0.287 |
Neg logit contributions | |
ades | -0.343 |
emi | -0.323 |
ade | -0.297 |
ghai | -0.292 |
anging | -0.289 |
Token | Happy |
Token ID | 25082 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
experien | +0.401 |
racuse | +0.398 |
hers | +0.396 |
lette | +0.390 |
senal | +0.387 |
Neg logit contributions | |
ades | -0.460 |
emi | -0.435 |
ade | -0.404 |
anging | -0.391 |
ghai | -0.387 |
Token | that |
Token ID | 326 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ades | +9.125 |
emi | +7.955 |
ade | +7.758 |
end | +7.271 |
anging | +7.179 |
Neg logit contributions | |
racuse | -9.583 |
senal | -9.216 |
ento | -9.060 |
entin | -8.753 |
itives | -8.603 |
Token | I |
Token ID | 314 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
ades | +3.190 |
emi | +2.991 |
ade | +2.714 |
ghai | +2.527 |
aye | +2.523 |
Neg logit contributions | |
racuse | -3.752 |
senal | -3.644 |
lette | -3.642 |
ento | -3.625 |
hers | -3.617 |
Token | made |
Token ID | 925 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ades | +3.283 |
emi | +3.106 |
ade | +2.887 |
anging | +2.742 |
ghai | +2.712 |
Neg logit contributions | |
racuse | -3.263 |
senal | -3.232 |
experien | -3.161 |
lette | -3.128 |
pict | -3.125 |
Token | it |
Token ID | 340 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
ades | +0.579 |
emi | +0.542 |
ade | +0.495 |
ghai | +0.472 |
anging | +0.469 |
Neg logit contributions | |
racuse | -0.579 |
hers | -0.576 |
lette | -0.574 |
experien | -0.568 |
senal | -0.562 |
Token | . |
Token ID | 13 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
ades | +1.057 |
emi | +0.991 |
ade | +0.915 |
anging | +0.880 |
ghai | +0.876 |
Neg logit contributions | |
racuse | -0.970 |
hers | -0.967 |
lette | -0.958 |
experien | -0.952 |
senal | -0.940 |
Token | What |
Token ID | 2061 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
experien | +1.220 |
racuse | +1.213 |
hers | +1.202 |
senal | +1.189 |
lette | +1.173 |
Neg logit contributions | |
ades | -1.653 |
emi | -1.565 |
ade | -1.467 |
anging | -1.410 |
ghai | -1.396 |
Token | 's |
Token ID | 338 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
racuse | +0.710 |
hers | +0.708 |
lette | +0.692 |
experien | +0.689 |
pict | +0.685 |
Neg logit contributions | |
ades | -0.790 |
emi | -0.744 |
ade | -0.685 |
ghai | -0.660 |
anging | -0.653 |
Token | my |
Token ID | 616 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
ades | +2.097 |
emi | +1.988 |
ade | +1.820 |
anging | +1.762 |
ghai | +1.734 |
Neg logit contributions | |
racuse | -1.835 |
lette | -1.803 |
senal | -1.781 |
pict | -1.762 |
hers | -1.758 |
Token | take |
Token ID | 1011 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
racuse | +0.956 |
hers | +0.956 |
lette | +0.940 |
experien | +0.918 |
pict | +0.918 |
Neg logit contributions | |
ades | -1.253 |
emi | -1.181 |
ade | -1.100 |
anging | -1.062 |
ghai | -1.058 |
Token | on |
Token ID | 319 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
hers | +2.165 |
racuse | +2.136 |
experien | +2.123 |
lette | +2.110 |
pict | +2.078 |
Neg logit contributions | |
ades | -2.687 |
emi | -2.547 |
ade | -2.339 |
ghai | -2.278 |
anging | -2.276 |
Token | Ramsey |
Token ID | 30552 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ades | +0.976 |
emi | +0.920 |
ade | +0.833 |
anging | +0.798 |
aye | +0.784 |
Neg logit contributions | |
racuse | -0.988 |
hers | -0.971 |
pict | -0.970 |
lette | -0.965 |
experien | -0.962 |
Token | 's |
Token ID | 338 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
hers | +5.730 |
lette | +5.581 |
experien | +5.506 |
racuse | +5.436 |
pict | +5.327 |
Neg logit contributions | |
ades | -7.031 |
emi | -6.618 |
ghai | -6.219 |
ade | -6.084 |
anging | -6.012 |
Token | tactics |
Token ID | 10815 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
ades | +2.208 |
emi | +2.054 |
ade | +1.888 |
anging | +1.797 |
ratification | +1.776 |
Neg logit contributions | |
racuse | -2.264 |
hers | -2.223 |
lette | -2.215 |
senal | -2.187 |
pict | -2.166 |
Token | ? |
Token ID | 30 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
hers | +1.751 |
experien | +1.725 |
racuse | +1.724 |
lette | +1.720 |
pict | +1.680 |
Neg logit contributions | |
ades | -2.075 |
emi | -1.958 |
ade | -1.802 |
anging | -1.753 |
ghai | -1.751 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
ades | +1.374 |
emi | +1.301 |
ade | +1.187 |
anging | +1.108 |
ghai | +1.097 |
Neg logit contributions | |
experien | -1.662 |
senal | -1.637 |
racuse | -1.632 |
hers | -1.613 |
lette | -1.599 |
Token |
|
Token ID | 198 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
hers | +0.634 |
lette | +0.619 |
racuse | +0.613 |
experien | +0.610 |
pict | +0.601 |
Neg logit contributions | |
ades | -0.751 |
emi | -0.709 |
ade | -0.650 |
ghai | -0.644 |
anging | -0.636 |
Token | if |
Token ID | 611 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
ades | +0.343 |
emi | +0.324 |
ade | +0.297 |
anging | +0.288 |
ghai | +0.288 |
Neg logit contributions | |
hers | -0.316 |
racuse | -0.314 |
lette | -0.311 |
experien | -0.306 |
pict | -0.301 |
Token | there |
Token ID | 612 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
hers | +1.692 |
lette | +1.658 |
racuse | +1.653 |
experien | +1.646 |
pict | +1.610 |
Neg logit contributions | |
ades | -1.828 |
emi | -1.716 |
ade | -1.577 |
ghai | -1.548 |
anging | -1.532 |
Token | will |
Token ID | 481 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
hers | +0.680 |
lette | +0.672 |
racuse | +0.671 |
experien | +0.666 |
pict | +0.648 |
Neg logit contributions | |
ades | -0.752 |
emi | -0.703 |
ade | -0.652 |
ghai | -0.635 |
anging | -0.632 |
Token | be |
Token ID | 307 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
ades | +1.102 |
emi | +1.028 |
ade | +0.930 |
ghai | +0.902 |
anging | +0.893 |
Neg logit contributions | |
hers | -1.502 |
lette | -1.484 |
racuse | -1.472 |
experien | -1.468 |
pict | -1.448 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
hers | +0.172 |
racuse | +0.169 |
lette | +0.168 |
experien | +0.166 |
pict | +0.163 |
Neg logit contributions | |
ades | -0.203 |
emi | -0.191 |
ade | -0.177 |
ghai | -0.172 |
anging | -0.172 |
Token | pre |
Token ID | 662 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
hers | +0.516 |
racuse | +0.507 |
lette | +0.504 |
experien | +0.500 |
pict | +0.491 |
Neg logit contributions | |
ades | -0.535 |
emi | -0.502 |
ade | -0.462 |
ghai | -0.448 |
anging | -0.447 |
Token | - |
Token ID | 12 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
hers | +5.649 |
lette | +5.518 |
racuse | +5.349 |
experien | +5.347 |
pict | +5.281 |
Neg logit contributions | |
ades | -6.529 |
emi | -6.142 |
ghai | -5.635 |
ade | -5.563 |
anging | -5.509 |
Token | order |
Token ID | 2875 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
hers | +2.444 |
racuse | +2.411 |
experien | +2.405 |
lette | +2.401 |
pict | +2.334 |
Neg logit contributions | |
ades | -2.167 |
emi | -2.019 |
ade | -1.847 |
ghai | -1.795 |
anging | -1.780 |
Token | through |
Token ID | 832 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
hers | +2.347 |
racuse | +2.294 |
lette | +2.293 |
experien | +2.279 |
pict | +2.234 |
Neg logit contributions | |
ades | -2.667 |
emi | -2.506 |
ade | -2.312 |
ghai | -2.269 |
anging | -2.246 |
Token |
|
Token ID | 198 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
ades | +1.328 |
emi | +1.209 |
ade | +1.120 |
anging | +1.064 |
ghai | +1.061 |
Neg logit contributions | |
hers | -1.516 |
racuse | -1.506 |
lette | -1.488 |
experien | -1.466 |
pict | -1.456 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ades | +0.970 |
emi | +0.909 |
ade | +0.841 |
ghai | +0.815 |
anging | +0.808 |
Neg logit contributions | |
hers | -0.924 |
experien | -0.922 |
racuse | -0.918 |
senal | -0.916 |
lette | -0.910 |
Token | 29 |
Token ID | 2808 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
ades | +1.491 |
emi | +1.348 |
ade | +1.250 |
ghai | +1.184 |
anging | +1.179 |
Neg logit contributions | |
hers | -1.877 |
racuse | -1.865 |
lette | -1.839 |
experien | -1.836 |
pict | -1.801 |
Token | questioned |
Token ID | 11434 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ades | +1.411 |
emi | +1.276 |
ade | +1.209 |
anging | +1.158 |
ghai | +1.140 |
Neg logit contributions | |
hers | -1.468 |
racuse | -1.446 |
lette | -1.441 |
experien | -1.430 |
pict | -1.420 |
Token | in |
Token ID | 287 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
hers | +0.759 |
racuse | +0.758 |
experien | +0.750 |
lette | +0.749 |
Admin | +0.739 |
Neg logit contributions | |
ades | -0.830 |
emi | -0.773 |
ade | -0.717 |
ghai | -0.688 |
anging | -0.683 |
Token | a |
Token ID | 257 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ades | +0.180 |
emi | +0.165 |
ade | +0.154 |
ghai | +0.148 |
anging | +0.147 |
Neg logit contributions | |
hers | -0.176 |
lette | -0.173 |
racuse | -0.173 |
experien | -0.172 |
pict | -0.168 |
Token | Reuters |
Token ID | 8428 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
ades | +1.823 |
emi | +1.690 |
ade | +1.568 |
ghai | +1.515 |
anging | +1.500 |
Neg logit contributions | |
hers | -1.828 |
experien | -1.820 |
racuse | -1.818 |
lette | -1.787 |
senal | -1.783 |
Token | / |
Token ID | 14 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
hers | +1.496 |
lette | +1.460 |
racuse | +1.457 |
experien | +1.450 |
pict | +1.413 |
Neg logit contributions | |
ades | -1.707 |
emi | -1.608 |
ade | -1.490 |
ghai | -1.456 |
anging | -1.435 |
Token | I |
Token ID | 40 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
hers | +5.728 |
experien | +5.624 |
Admin | +5.611 |
lette | +5.572 |
pict | +5.511 |
Neg logit contributions | |
ades | -8.981 |
emi | -8.464 |
anging | -8.002 |
ghai | -7.857 |
ade | -7.678 |
Token | ps |
Token ID | 862 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
hers | +1.766 |
lette | +1.708 |
racuse | +1.697 |
experien | +1.695 |
pict | +1.630 |
Neg logit contributions | |
ades | -4.012 |
emi | -3.830 |
ade | -3.599 |
ghai | -3.557 |
anging | -3.527 |
Token | os |
Token ID | 418 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
hers | +2.797 |
lette | +2.721 |
racuse | +2.669 |
experien | +2.651 |
pict | +2.577 |
Neg logit contributions | |
ades | -5.657 |
emi | -5.344 |
ade | -5.016 |
ghai | -4.978 |
anging | -4.934 |
Token | poll |
Token ID | 3278 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
hers | +2.354 |
lette | +2.303 |
racuse | +2.290 |
experien | +2.287 |
pict | +2.224 |
Neg logit contributions | |
ades | -2.976 |
emi | -2.817 |
ade | -2.606 |
ghai | -2.558 |
anging | -2.529 |
Token | , |
Token ID | 11 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
hers | +2.345 |
lette | +2.294 |
racuse | +2.292 |
experien | +2.284 |
pict | +2.232 |
Neg logit contributions | |
ades | -2.724 |
emi | -2.564 |
ade | -2.363 |
ghai | -2.319 |
anging | -2.293 |
Token | - |
Token ID | 12 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
ades | +0.269 |
emi | +0.250 |
ade | +0.236 |
ghai | +0.223 |
anging | +0.222 |
Neg logit contributions | |
racuse | -0.262 |
hers | -0.262 |
experien | -0.258 |
lette | -0.256 |
senal | -0.253 |
Token | wall |
Token ID | 11930 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
ades | +0.614 |
emi | +0.572 |
ade | +0.546 |
anging | +0.516 |
ghai | +0.510 |
Neg logit contributions | |
experien | -0.572 |
racuse | -0.570 |
hers | -0.559 |
lette | -0.555 |
senal | -0.551 |
Token | aby |
Token ID | 3930 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
racuse | +0.191 |
hers | +0.191 |
experien | +0.190 |
lette | +0.190 |
pict | +0.186 |
Neg logit contributions | |
ades | -0.207 |
emi | -0.190 |
ade | -0.181 |
ghai | -0.173 |
anging | -0.172 |
Token | ( |
Token ID | 357 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
hers | +3.320 |
lette | +3.254 |
racuse | +3.243 |
experien | +3.235 |
pict | +3.167 |
Neg logit contributions | |
ades | -3.268 |
emi | -3.062 |
ade | -2.797 |
ghai | -2.749 |
anging | -2.715 |
Token | Pet |
Token ID | 25803 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ades | +2.625 |
emi | +2.447 |
ade | +2.313 |
ghai | +2.227 |
anging | +2.174 |
Neg logit contributions | |
racuse | -2.289 |
experien | -2.265 |
lette | -2.239 |
hers | -2.225 |
senal | -2.156 |
Token | rog |
Token ID | 3828 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
hers | +8.713 |
lette | +8.379 |
racuse | +8.196 |
ras | +8.112 |
pict | +8.096 |
Neg logit contributions | |
ades | -8.864 |
emi | -8.270 |
ghai | -7.668 |
anging | -7.621 |
ade | -7.589 |
Token | ale |
Token ID | 1000 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
hers | +6.806 |
lette | +6.761 |
racuse | +6.588 |
pict | +6.497 |
ento | +6.448 |
Neg logit contributions | |
ades | -6.838 |
emi | -6.400 |
ghai | -5.843 |
ade | -5.825 |
anging | -5.686 |
Token | br |
Token ID | 865 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
hers | +2.840 |
lette | +2.782 |
racuse | +2.772 |
experien | +2.765 |
pict | +2.703 |
Neg logit contributions | |
ades | -3.033 |
emi | -2.849 |
ade | -2.612 |
ghai | -2.565 |
anging | -2.536 |
Token | achy |
Token ID | 35586 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
ades | +0.858 |
emi | +0.784 |
ade | +0.738 |
aye | +0.689 |
anging | +0.688 |
Neg logit contributions | |
experien | -0.933 |
hers | -0.928 |
senal | -0.917 |
racuse | -0.915 |
pict | -0.900 |
Token | ot |
Token ID | 313 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
hers | +3.799 |
experien | +3.784 |
racuse | +3.746 |
lette | +3.733 |
pict | +3.692 |
Neg logit contributions | |
ades | -1.597 |
emi | -1.440 |
ade | -1.215 |
ghai | -1.164 |
anging | -1.136 |
Token | is |
Token ID | 271 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
experien | +0.401 |
hers | +0.389 |
racuse | +0.387 |
senal | +0.382 |
pict | +0.380 |
Neg logit contributions | |
ades | -0.449 |
emi | -0.426 |
ade | -0.390 |
ghai | -0.382 |
anging | -0.378 |
Token | has |
Token ID | 468 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
hers | +1.213 |
lette | +1.184 |
experien | +1.159 |
racuse | +1.156 |
pict | +1.114 |
Neg logit contributions | |
ades | -1.948 |
emi | -1.875 |
ghai | -1.729 |
ade | -1.714 |
anging | -1.698 |
Token | occurred |
Token ID | 5091 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
hers | +2.333 |
lette | +2.255 |
experien | +2.176 |
racuse | +2.165 |
pict | +2.154 |
Neg logit contributions | |
ades | -3.296 |
emi | -3.191 |
ghai | -2.934 |
anging | -2.887 |
ade | -2.884 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
hers | +3.047 |
lette | +2.943 |
racuse | +2.805 |
pict | +2.800 |
Admin | +2.758 |
Neg logit contributions | |
ades | -5.750 |
emi | -5.542 |
ghai | -5.141 |
anging | -5.126 |
�� | -5.064 |
Token | Please |
Token ID | 4222 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
hers | +0.513 |
lette | +0.502 |
racuse | +0.498 |
experien | +0.497 |
pict | +0.486 |
Neg logit contributions | |
ades | -0.649 |
emi | -0.613 |
ade | -0.565 |
ghai | -0.559 |
anging | -0.553 |
Token | try |
Token ID | 1949 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
hers | +0.833 |
lette | +0.812 |
experien | +0.802 |
racuse | +0.802 |
pict | +0.777 |
Neg logit contributions | |
ades | -1.264 |
emi | -1.207 |
ade | -1.111 |
ghai | -1.106 |
anging | -1.096 |
Token | again |
Token ID | 757 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
hers | +3.313 |
lette | +3.197 |
racuse | +3.071 |
Admin | +3.043 |
pict | +3.041 |
Neg logit contributions | |
ades | -4.822 |
emi | -4.627 |
ghai | -4.308 |
ade | -4.210 |
anging | -4.198 |
Token | later |
Token ID | 1568 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
lette | +3.996 |
hers | +3.988 |
racuse | +3.823 |
experien | +3.725 |
pict | +3.711 |
Neg logit contributions | |
ades | -7.835 |
emi | -7.605 |
ghai | -6.987 |
anging | -6.978 |
ade | -6.932 |
Token | . |
Token ID | 13 |
Feature activation | +3.21e-03 |
Pos logit contributions | |
hers | +2.456 |
lette | +2.392 |
pict | +2.290 |
racuse | +2.282 |
Admin | +2.275 |
Neg logit contributions | |
ades | -4.322 |
emi | -4.134 |
ghai | -3.832 |
anging | -3.803 |
ade | -3.794 |
Token | View |
Token ID | 3582 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
hers | +0.010 |
lette | +0.010 |
racuse | +0.010 |
experien | +0.010 |
pict | +0.009 |
Neg logit contributions | |
ades | -0.011 |
emi | -0.011 |
ade | -0.010 |
ghai | -0.010 |
anging | -0.010 |
Token | all |
Token ID | 477 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
hers | +0.117 |
racuse | +0.116 |
experien | +0.115 |
lette | +0.115 |
senal | +0.113 |
Neg logit contributions | |
ades | -0.124 |
emi | -0.116 |
ade | -0.107 |
ghai | -0.105 |
anging | -0.103 |
Token | New |
Token ID | 968 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ades | +0.936 |
emi | +0.864 |
ade | +0.790 |
ghai | +0.769 |
anging | +0.756 |
Neg logit contributions | |
hers | -1.139 |
experien | -1.124 |
racuse | -1.117 |
lette | -1.117 |
senal | -1.092 |
Token | were |
Token ID | 547 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
hers | +1.041 |
racuse | +1.036 |
lette | +1.016 |
experien | +1.015 |
pict | +1.003 |
Neg logit contributions | |
ades | -1.144 |
emi | -1.083 |
ade | -0.997 |
ghai | -0.966 |
anging | -0.957 |
Token | negotiating |
Token ID | 19025 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
racuse | +1.593 |
hers | +1.562 |
lette | +1.545 |
experien | +1.534 |
pict | +1.515 |
Neg logit contributions | |
ades | -1.790 |
emi | -1.678 |
ade | -1.554 |
ghai | -1.513 |
anging | -1.502 |
Token | over |
Token ID | 625 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
ades | +2.465 |
emi | +2.256 |
ade | +2.132 |
ratification | +2.033 |
ghai | +2.013 |
Neg logit contributions | |
racuse | -2.559 |
hers | -2.431 |
lette | -2.385 |
senal | -2.382 |
experien | -2.380 |
Token | fees |
Token ID | 6642 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
ades | +2.620 |
emi | +2.428 |
ade | +2.257 |
anging | +2.165 |
ratification | +2.142 |
Neg logit contributions | |
racuse | -2.719 |
hers | -2.624 |
experien | -2.590 |
lette | -2.582 |
senal | -2.557 |
Token | for |
Token ID | 329 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ades | +0.899 |
emi | +0.845 |
ade | +0.780 |
anging | +0.755 |
ghai | +0.740 |
Neg logit contributions | |
racuse | -0.866 |
experien | -0.840 |
hers | -0.836 |
lette | -0.831 |
senal | -0.830 |
Token | collection |
Token ID | 4947 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ades | +0.833 |
emi | +0.773 |
ade | +0.722 |
anging | +0.687 |
ghai | +0.684 |
Neg logit contributions | |
racuse | -0.820 |
hers | -0.811 |
lette | -0.794 |
experien | -0.786 |
senal | -0.780 |
Token | , |
Token ID | 11 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
racuse | +0.469 |
hers | +0.462 |
lette | +0.455 |
experien | +0.448 |
senal | +0.446 |
Neg logit contributions | |
ades | -0.430 |
emi | -0.392 |
ade | -0.362 |
anging | -0.352 |
ghai | -0.348 |
Token | preservation |
Token ID | 22459 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
hers | +0.096 |
racuse | +0.095 |
lette | +0.094 |
experien | +0.093 |
pict | +0.091 |
Neg logit contributions | |
ades | -0.097 |
emi | -0.091 |
ade | -0.084 |
ghai | -0.081 |
anging | -0.080 |
Token | , |
Token ID | 11 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
hers | +2.192 |
racuse | +2.156 |
lette | +2.149 |
experien | +2.140 |
pict | +2.101 |
Neg logit contributions | |
ades | -1.989 |
emi | -1.844 |
ade | -1.686 |
ghai | -1.642 |
anging | -1.630 |
Token | and |
Token ID | 290 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
ades | +1.924 |
emi | +1.748 |
ade | +1.620 |
ghai | +1.532 |
anging | +1.519 |
Neg logit contributions | |
hers | -2.533 |
racuse | -2.526 |
lette | -2.499 |
experien | -2.467 |
senal | -2.446 |
Token | transport |
Token ID | 4839 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
ades | +1.883 |
emi | +1.723 |
ade | +1.610 |
ghai | +1.551 |
anging | +1.529 |
Neg logit contributions | |
racuse | -2.120 |
hers | -2.109 |
lette | -2.079 |
senal | -2.038 |
experien | -2.034 |
Token | should |
Token ID | 815 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
experien | +0.104 |
hers | +0.104 |
racuse | +0.104 |
senal | +0.102 |
lette | +0.101 |
Neg logit contributions | |
ades | -0.118 |
emi | -0.111 |
ade | -0.103 |
anging | -0.099 |
ghai | -0.099 |
Token | be |
Token ID | 307 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
ades | +2.376 |
emi | +2.265 |
ade | +2.103 |
anging | +2.043 |
ghai | +1.996 |
Neg logit contributions | |
racuse | -2.371 |
hers | -2.365 |
senal | -2.363 |
experien | -2.355 |
lette | -2.304 |
Token | called |
Token ID | 1444 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
ades | +0.173 |
emi | +0.164 |
ade | +0.153 |
anging | +0.147 |
ghai | +0.146 |
Neg logit contributions | |
racuse | -0.131 |
hers | -0.129 |
lette | -0.127 |
experien | -0.127 |
pict | -0.123 |
Token | plugin |
Token ID | 13877 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
ades | +1.252 |
emi | +1.160 |
ade | +1.083 |
anging | +1.033 |
ghai | +1.017 |
Neg logit contributions | |
hers | -1.279 |
lette | -1.263 |
racuse | -1.257 |
experien | -1.214 |
pict | -1.198 |
Token | . |
Token ID | 13 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
ades | +2.447 |
emi | +2.277 |
ade | +2.182 |
anging | +2.043 |
aye | +1.998 |
Neg logit contributions | |
hers | -2.100 |
racuse | -2.049 |
lette | -2.043 |
experien | -2.022 |
senal | -1.964 |
Token | video |
Token ID | 15588 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
ades | +0.217 |
emi | +0.205 |
ade | +0.188 |
anging | +0.179 |
ghai | +0.178 |
Neg logit contributions | |
hers | -0.233 |
experien | -0.231 |
racuse | -0.230 |
lette | -0.230 |
senal | -0.221 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
hers | +1.462 |
lette | +1.422 |
racuse | +1.417 |
experien | +1.412 |
pict | +1.365 |
Neg logit contributions | |
ades | -1.761 |
emi | -1.671 |
ade | -1.545 |
ghai | -1.494 |
anging | -1.488 |
Token | netflix |
Token ID | 36977 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ades | +0.602 |
emi | +0.574 |
ade | +0.533 |
anging | +0.510 |
ghai | +0.509 |
Neg logit contributions | |
hers | -0.484 |
experien | -0.478 |
racuse | -0.477 |
lette | -0.476 |
senal | -0.454 |
Token | - |
Token ID | 12 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ades | +0.663 |
emi | +0.629 |
ade | +0.585 |
ghai | +0.562 |
anging | +0.559 |
Neg logit contributions | |
hers | -0.539 |
racuse | -0.533 |
experien | -0.530 |
lette | -0.521 |
ento | -0.505 |
Token | master |
Token ID | 9866 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
hers | +0.905 |
racuse | +0.899 |
experien | +0.893 |
lette | +0.890 |
pict | +0.854 |
Neg logit contributions | |
ades | -0.966 |
emi | -0.913 |
ade | -0.841 |
ghai | -0.812 |
anging | -0.809 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
hers | +1.890 |
lette | +1.846 |
experien | +1.837 |
racuse | +1.831 |
pict | +1.773 |
Neg logit contributions | |
ades | -2.328 |
emi | -2.199 |
ade | -2.045 |
ghai | -1.997 |
anging | -1.984 |
Token | what |
Token ID | 644 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
hers | +0.808 |
lette | +0.794 |
racuse | +0.790 |
experien | +0.788 |
pict | +0.767 |
Neg logit contributions | |
ades | -1.215 |
emi | -1.153 |
ade | -1.072 |
ghai | -1.054 |
anging | -1.048 |
Token | you |
Token ID | 345 |
Feature activation | +8.91e-02 |
Pos logit contributions | |
hers | +1.201 |
lette | +1.177 |
racuse | +1.172 |
experien | +1.170 |
pict | +1.145 |
Neg logit contributions | |
ades | -1.197 |
emi | -1.121 |
ade | -1.025 |
ghai | -1.008 |
anging | -0.996 |
Token | think |
Token ID | 892 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
hers | +0.263 |
lette | +0.259 |
racuse | +0.258 |
experien | +0.257 |
pict | +0.250 |
Neg logit contributions | |
ades | -0.328 |
emi | -0.307 |
ade | -0.287 |
ghai | -0.279 |
anging | -0.277 |
Token | it |
Token ID | 340 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
ades | +1.962 |
emi | +1.788 |
ade | +1.698 |
ghai | +1.599 |
anging | +1.575 |
Neg logit contributions | |
senal | -2.415 |
racuse | -2.234 |
experien | -2.214 |
hers | -2.199 |
lette | -2.189 |
Token | is |
Token ID | 318 |
Feature activation | +9.00e-02 |
Pos logit contributions | |
hers | +1.095 |
lette | +1.070 |
racuse | +1.065 |
experien | +1.063 |
pict | +1.037 |
Neg logit contributions | |
ades | -1.393 |
emi | -1.315 |
ade | -1.215 |
ghai | -1.197 |
anging | -1.185 |
Token | , |
Token ID | 11 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
hers | +0.235 |
experien | +0.233 |
racuse | +0.233 |
lette | +0.231 |
pict | +0.226 |
Neg logit contributions | |
ades | -0.360 |
emi | -0.340 |
ade | -0.317 |
ghai | -0.307 |
anging | -0.306 |
Token | which |
Token ID | 543 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
hers | +2.400 |
lette | +2.369 |
racuse | +2.365 |
experien | +2.353 |
pict | +2.304 |
Neg logit contributions | |
ades | -2.245 |
emi | -2.095 |
ade | -1.911 |
ghai | -1.864 |
anging | -1.850 |
Token | I |
Token ID | 314 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
racuse | +0.140 |
hers | +0.140 |
lette | +0.138 |
experien | +0.138 |
pict | +0.135 |
Neg logit contributions | |
ades | -0.151 |
emi | -0.140 |
ade | -0.130 |
anging | -0.124 |
ghai | -0.124 |
Token | think |
Token ID | 892 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
hers | +0.280 |
racuse | +0.278 |
lette | +0.275 |
experien | +0.274 |
pict | +0.269 |
Neg logit contributions | |
ades | -0.339 |
emi | -0.317 |
ade | -0.297 |
ghai | -0.288 |
anging | -0.287 |
Token | is |
Token ID | 318 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
ades | +0.792 |
emi | +0.720 |
ade | +0.676 |
anging | +0.646 |
ghai | +0.646 |
Neg logit contributions | |
racuse | -0.749 |
lette | -0.741 |
experien | -0.734 |
hers | -0.734 |
senal | -0.728 |
Token | the |
Token ID | 262 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
racuse | +0.249 |
lette | +0.246 |
hers | +0.244 |
experien | +0.243 |
pict | +0.241 |
Neg logit contributions | |
ades | -0.283 |
emi | -0.266 |
ade | -0.245 |
ghai | -0.238 |
anging | -0.238 |
Token |
|
Token ID | 198 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
hers | +1.997 |
racuse | +1.954 |
experien | +1.953 |
lette | +1.953 |
pict | +1.898 |
Neg logit contributions | |
ades | -2.129 |
emi | -2.003 |
ade | -1.838 |
ghai | -1.801 |
anging | -1.782 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ades | +0.925 |
emi | +0.865 |
ade | +0.802 |
ghai | +0.775 |
anging | +0.771 |
Neg logit contributions | |
hers | -0.877 |
experien | -0.874 |
racuse | -0.870 |
senal | -0.864 |
lette | -0.861 |
Token | I |
Token ID | 40 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
hers | +0.556 |
racuse | +0.555 |
experien | +0.550 |
lette | +0.542 |
senal | +0.535 |
Neg logit contributions | |
ades | -0.767 |
emi | -0.725 |
ade | -0.679 |
anging | -0.656 |
ghai | -0.652 |
Token | was |
Token ID | 373 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
ades | +1.287 |
emi | +1.204 |
ade | +1.126 |
anging | +1.080 |
ghai | +1.079 |
Neg logit contributions | |
hers | -1.114 |
racuse | -1.106 |
senal | -1.090 |
experien | -1.088 |
lette | -1.084 |
Token | raised |
Token ID | 4376 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
racuse | +0.911 |
hers | +0.910 |
lette | +0.894 |
experien | +0.889 |
pict | +0.882 |
Neg logit contributions | |
ades | -1.066 |
emi | -0.999 |
ade | -0.926 |
ghai | -0.905 |
anging | -0.901 |
Token | in |
Token ID | 287 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
hers | +3.257 |
lette | +3.186 |
experien | +3.162 |
racuse | +3.158 |
pict | +3.086 |
Neg logit contributions | |
ades | -3.752 |
emi | -3.536 |
ade | -3.248 |
ghai | -3.203 |
anging | -3.166 |
Token | Utah |
Token ID | 10202 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
hers | +1.440 |
lette | +1.408 |
racuse | +1.407 |
experien | +1.397 |
pict | +1.373 |
Neg logit contributions | |
ades | -1.546 |
emi | -1.446 |
ade | -1.329 |
ghai | -1.296 |
anging | -1.294 |
Token | as |
Token ID | 355 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ades | +0.540 |
emi | +0.503 |
ade | +0.466 |
ghai | +0.446 |
anging | +0.446 |
Neg logit contributions | |
racuse | -0.532 |
experien | -0.522 |
hers | -0.521 |
lette | -0.513 |
pict | -0.508 |
Token | a |
Token ID | 257 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
ades | +0.975 |
emi | +0.912 |
ade | +0.848 |
ghai | +0.818 |
anging | +0.812 |
Neg logit contributions | |
racuse | -0.906 |
hers | -0.885 |
lette | -0.879 |
pict | -0.876 |
experien | -0.875 |
Token | Mormon |
Token ID | 13164 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
ades | +0.863 |
emi | +0.809 |
ade | +0.751 |
anging | +0.726 |
ghai | +0.722 |
Neg logit contributions | |
racuse | -0.831 |
hers | -0.826 |
lette | -0.814 |
experien | -0.805 |
pict | -0.803 |
Token | , |
Token ID | 11 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
racuse | +0.200 |
hers | +0.198 |
experien | +0.195 |
lette | +0.193 |
pict | +0.193 |
Neg logit contributions | |
ades | -0.195 |
emi | -0.185 |
ade | -0.171 |
anging | -0.162 |
ghai | -0.162 |
Token | about |
Token ID | 546 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
hers | +1.269 |
racuse | +1.268 |
lette | +1.238 |
experien | +1.224 |
pict | +1.206 |
Neg logit contributions | |
ades | -1.493 |
emi | -1.414 |
ade | -1.307 |
ghai | -1.274 |
anging | -1.264 |
Token | his |
Token ID | 465 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
ades | +0.333 |
emi | +0.310 |
ade | +0.287 |
anging | +0.277 |
ghai | +0.274 |
Neg logit contributions | |
racuse | -0.332 |
hers | -0.325 |
lette | -0.323 |
experien | -0.319 |
pict | -0.313 |
Token | city |
Token ID | 1748 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
racuse | +0.688 |
hers | +0.685 |
lette | +0.674 |
experien | +0.667 |
pict | +0.654 |
Neg logit contributions | |
ades | -0.846 |
emi | -0.790 |
ade | -0.737 |
anging | -0.714 |
ghai | -0.709 |
Token | , |
Token ID | 11 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
racuse | +1.177 |
hers | +1.169 |
experien | +1.157 |
lette | +1.155 |
pict | +1.123 |
Neg logit contributions | |
ades | -1.218 |
emi | -1.141 |
ade | -1.051 |
ghai | -1.022 |
anging | -1.015 |
Token | his |
Token ID | 465 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
hers | +1.760 |
racuse | +1.751 |
lette | +1.750 |
experien | +1.725 |
pict | +1.691 |
Neg logit contributions | |
ades | -1.717 |
emi | -1.594 |
ade | -1.463 |
ghai | -1.428 |
anging | -1.416 |
Token | community |
Token ID | 2055 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
hers | +2.601 |
racuse | +2.558 |
lette | +2.556 |
experien | +2.531 |
pict | +2.476 |
Neg logit contributions | |
ades | -3.132 |
emi | -2.942 |
ade | -2.720 |
ghai | -2.663 |
anging | -2.647 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
racuse | +0.584 |
hers | +0.582 |
lette | +0.574 |
experien | +0.574 |
pict | +0.561 |
Neg logit contributions | |
ades | -0.555 |
emi | -0.516 |
ade | -0.474 |
ghai | -0.455 |
anging | -0.453 |
Token | hip |
Token ID | 10359 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
ades | +0.416 |
emi | +0.381 |
ade | +0.347 |
anging | +0.333 |
ghai | +0.332 |
Neg logit contributions | |
lette | -0.509 |
racuse | -0.507 |
hers | -0.505 |
experien | -0.500 |
Admin | -0.490 |
Token | - |
Token ID | 12 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ades | +2.640 |
emi | +2.446 |
ade | +2.234 |
anging | +2.082 |
ghai | +2.071 |
Neg logit contributions | |
racuse | -3.112 |
experien | -3.044 |
lette | -3.005 |
hers | -2.972 |
Admin | -2.919 |
Token | hop |
Token ID | 8548 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
ades | +0.671 |
emi | +0.621 |
ade | +0.558 |
anging | +0.548 |
ghai | +0.533 |
Neg logit contributions | |
racuse | -0.983 |
experien | -0.973 |
lette | -0.971 |
hers | -0.955 |
Admin | -0.933 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
hers | +1.683 |
racuse | +1.681 |
lette | +1.663 |
experien | +1.650 |
pict | +1.614 |
Neg logit contributions | |
ades | -1.727 |
emi | -1.610 |
ade | -1.482 |
ghai | -1.443 |
anging | -1.430 |
Token | regular |
Token ID | 3218 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
ades | +0.114 |
emi | +0.106 |
ade | +0.099 |
anging | +0.095 |
ghai | +0.094 |
Neg logit contributions | |
racuse | -0.113 |
hers | -0.111 |
lette | -0.109 |
experien | -0.108 |
pict | -0.108 |
Token | playing |
Token ID | 2712 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
racuse | +0.191 |
hers | +0.189 |
lette | +0.184 |
experien | +0.183 |
pict | +0.182 |
Neg logit contributions | |
ades | -0.181 |
emi | -0.168 |
ade | -0.157 |
ghai | -0.149 |
anging | -0.149 |
Token | time |
Token ID | 640 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
hers | +3.057 |
racuse | +3.013 |
lette | +2.975 |
experien | +2.940 |
pict | +2.915 |
Neg logit contributions | |
ades | -3.181 |
emi | -2.980 |
ade | -2.751 |
ghai | -2.660 |
anging | -2.641 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
hers | +1.940 |
racuse | +1.919 |
lette | +1.903 |
experien | +1.882 |
pict | +1.852 |
Neg logit contributions | |
ades | -2.262 |
emi | -2.125 |
ade | -1.967 |
ghai | -1.916 |
anging | -1.901 |
Token | Bradley |
Token ID | 16182 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
racuse | +0.886 |
hers | +0.878 |
experien | +0.875 |
lette | +0.871 |
senal | +0.837 |
Neg logit contributions | |
ades | -1.284 |
emi | -1.215 |
ade | -1.140 |
ghai | -1.102 |
anging | -1.093 |
Token | took |
Token ID | 1718 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ades | +4.302 |
emi | +4.016 |
ade | +3.818 |
ghai | +3.601 |
anging | +3.565 |
Neg logit contributions | |
racuse | -3.613 |
senal | -3.439 |
hers | -3.426 |
pict | -3.388 |
experien | -3.377 |
Token | the |
Token ID | 262 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
ades | +0.884 |
emi | +0.835 |
ade | +0.761 |
ghai | +0.737 |
anging | +0.731 |
Neg logit contributions | |
racuse | -0.897 |
hers | -0.871 |
experien | -0.857 |
lette | -0.855 |
senal | -0.853 |
Token | then |
Token ID | 788 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
racuse | +0.259 |
hers | +0.254 |
lette | +0.249 |
experien | +0.247 |
pict | +0.246 |
Neg logit contributions | |
ades | -0.292 |
emi | -0.277 |
ade | -0.254 |
ghai | -0.249 |
anging | -0.246 |
Token | teenager |
Token ID | 15287 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
ades | +1.874 |
emi | +1.744 |
ade | +1.631 |
anging | +1.572 |
ghai | +1.540 |
Neg logit contributions | |
racuse | -1.914 |
hers | -1.864 |
pict | -1.857 |
experien | -1.853 |
ento | -1.834 |
Token | to |
Token ID | 284 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
ades | +1.866 |
emi | +1.730 |
ade | +1.613 |
ghai | +1.542 |
anging | +1.536 |
Neg logit contributions | |
racuse | -1.929 |
hers | -1.887 |
lette | -1.856 |
experien | -1.852 |
pict | -1.838 |
Token | the |
Token ID | 262 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
ades | +0.667 |
emi | +0.615 |
ade | +0.570 |
ghai | +0.549 |
anging | +0.544 |
Neg logit contributions | |
racuse | -0.681 |
hers | -0.676 |
lette | -0.669 |
experien | -0.666 |
pict | -0.659 |
Token | separation |
Token ID | 14139 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
ades | +1.481 |
emi | +1.387 |
ade | +1.270 |
ghai | +1.224 |
anging | +1.196 |
Neg logit contributions | |
racuse | -1.577 |
hers | -1.563 |
lette | -1.523 |
experien | -1.505 |
Admin | -1.503 |
Token | within |
Token ID | 1626 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
racuse | +1.285 |
hers | +1.284 |
lette | +1.257 |
experien | +1.246 |
pict | +1.225 |
Neg logit contributions | |
ades | -1.517 |
emi | -1.400 |
ade | -1.316 |
ghai | -1.275 |
anging | -1.254 |
Token | the |
Token ID | 262 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
hers | +1.072 |
racuse | +1.066 |
lette | +1.055 |
experien | +1.042 |
pict | +1.025 |
Neg logit contributions | |
ades | -1.023 |
emi | -0.945 |
ade | -0.871 |
ghai | -0.848 |
anging | -0.836 |
Token | West |
Token ID | 2688 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
ades | +1.293 |
emi | +1.201 |
ade | +1.108 |
ghai | +1.073 |
anging | +1.071 |
Neg logit contributions | |
racuse | -1.223 |
hers | -1.217 |
lette | -1.189 |
experien | -1.166 |
pict | -1.160 |
Token | Bank |
Token ID | 5018 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
ades | +1.641 |
emi | +1.435 |
ade | +1.316 |
ghai | +1.246 |
anging | +1.221 |
Neg logit contributions | |
hers | -3.132 |
racuse | -3.091 |
experien | -3.048 |
lette | -3.024 |
senal | -3.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ades | +2.513 |
emi | +2.278 |
ade | +2.176 |
ghai | +2.033 |
anging | +2.000 |
Neg logit contributions | |
racuse | -2.499 |
hers | -2.426 |
lette | -2.386 |
experien | -2.385 |
pict | -2.354 |
Token | Flying |
Token ID | 19903 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ades | +0.594 |
emi | +0.548 |
ade | +0.513 |
ghai | +0.487 |
anging | +0.477 |
Neg logit contributions | |
racuse | -0.635 |
hers | -0.628 |
experien | -0.624 |
lette | -0.619 |
senal | -0.607 |
Token | checkpoints |
Token ID | 36628 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
ades | +4.452 |
emi | +3.922 |
ade | +3.826 |
anging | +3.611 |
ghai | +3.556 |
Neg logit contributions | |
racuse | -4.600 |
hers | -4.463 |
senal | -4.365 |
ento | -4.279 |
lette | -4.275 |
Token | shift |
Token ID | 6482 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
hers | +1.654 |
racuse | +1.650 |
lette | +1.631 |
experien | +1.619 |
pict | +1.589 |
Neg logit contributions | |
ades | -1.824 |
emi | -1.695 |
ade | -1.582 |
ghai | -1.533 |
anging | -1.524 |
Token | around |
Token ID | 1088 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
racuse | +1.635 |
hers | +1.628 |
lette | +1.593 |
experien | +1.574 |
pict | +1.554 |
Neg logit contributions | |
ades | -1.781 |
emi | -1.661 |
ade | -1.542 |
ghai | -1.515 |
anging | -1.491 |
Token | arbitrarily |
Token ID | 40647 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
hers | +2.924 |
racuse | +2.883 |
lette | +2.861 |
experien | +2.845 |
pict | +2.792 |
Neg logit contributions | |
ades | -3.058 |
emi | -2.851 |
ade | -2.630 |
ghai | -2.572 |
anging | -2.552 |
Token | numerous |
Token ID | 6409 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ades | +0.810 |
emi | +0.754 |
ade | +0.687 |
ghai | +0.675 |
anging | +0.666 |
Neg logit contributions | |
hers | -0.826 |
racuse | -0.826 |
lette | -0.811 |
experien | -0.808 |
Admin | -0.792 |
Token | Yelp |
Token ID | 44628 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ades | +0.871 |
emi | +0.809 |
ade | +0.752 |
ghai | +0.745 |
anging | +0.725 |
Neg logit contributions | |
hers | -0.726 |
racuse | -0.718 |
lette | -0.705 |
senal | -0.683 |
experien | -0.682 |
Token | reviews |
Token ID | 8088 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
racuse | +0.793 |
hers | +0.793 |
lette | +0.778 |
experien | +0.768 |
pict | +0.753 |
Neg logit contributions | |
ades | -0.680 |
emi | -0.628 |
ade | -0.576 |
ghai | -0.562 |
anging | -0.553 |
Token | , |
Token ID | 11 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
hers | +0.702 |
racuse | +0.696 |
experien | +0.690 |
lette | +0.686 |
Admin | +0.673 |
Neg logit contributions | |
ades | -0.715 |
emi | -0.665 |
ade | -0.615 |
ghai | -0.607 |
anging | -0.595 |
Token | plenty |
Token ID | 6088 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
hers | +1.342 |
racuse | +1.335 |
lette | +1.319 |
experien | +1.311 |
pict | +1.283 |
Neg logit contributions | |
ades | -1.320 |
emi | -1.235 |
ade | -1.129 |
ghai | -1.107 |
anging | -1.096 |
Token | of |
Token ID | 286 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
ades | +0.963 |
emi | +0.895 |
ghai | +0.816 |
ade | +0.816 |
anging | +0.792 |
Neg logit contributions | |
hers | -1.078 |
experien | -1.069 |
lette | -1.066 |
racuse | -1.064 |
Admin | -1.036 |
Token | people |
Token ID | 661 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
racuse | +0.187 |
hers | +0.186 |
lette | +0.184 |
experien | +0.179 |
pict | +0.179 |
Neg logit contributions | |
ades | -0.196 |
emi | -0.182 |
ade | -0.167 |
ghai | -0.164 |
anging | -0.163 |
Token | equate |
Token ID | 45423 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ades | +2.115 |
emi | +1.954 |
ade | +1.864 |
ghai | +1.823 |
anging | +1.755 |
Neg logit contributions | |
racuse | -1.919 |
senal | -1.912 |
hers | -1.890 |
lette | -1.852 |
experien | -1.848 |
Token | great |
Token ID | 1049 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
hers | +4.413 |
lette | +4.330 |
experien | +4.298 |
racuse | +4.280 |
pict | +4.203 |
Neg logit contributions | |
ades | -4.277 |
emi | -4.023 |
ade | -3.650 |
ghai | -3.613 |
anging | -3.556 |
Token | taste |
Token ID | 6938 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
ades | +0.055 |
emi | +0.050 |
ade | +0.046 |
ghai | +0.044 |
anging | +0.044 |
Neg logit contributions | |
hers | -0.078 |
racuse | -0.078 |
experien | -0.076 |
lette | -0.076 |
Admin | -0.075 |
Token | with |
Token ID | 351 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
ades | +1.253 |
emi | +1.156 |
ade | +1.078 |
ghai | +1.048 |
anging | +1.029 |
Neg logit contributions | |
racuse | -1.277 |
hers | -1.276 |
experien | -1.234 |
lette | -1.224 |
pict | -1.213 |
Token | ," |
Token ID | 553 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
ades | +0.513 |
emi | +0.484 |
ade | +0.449 |
anging | +0.431 |
ghai | +0.430 |
Neg logit contributions | |
racuse | -0.438 |
senal | -0.431 |
hers | -0.430 |
experien | -0.426 |
lette | -0.424 |
Token | one |
Token ID | 530 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
hers | +1.716 |
lette | +1.685 |
racuse | +1.685 |
experien | +1.674 |
pict | +1.648 |
Neg logit contributions | |
ades | -1.805 |
emi | -1.688 |
ade | -1.556 |
ghai | -1.517 |
anging | -1.500 |
Token | NBA |
Token ID | 7403 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
hers | +4.251 |
lette | +4.174 |
experien | +4.157 |
racuse | +4.151 |
pict | +4.062 |
Neg logit contributions | |
ades | -3.349 |
emi | -3.115 |
ade | -2.801 |
ghai | -2.751 |
anging | -2.715 |
Token | general |
Token ID | 2276 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
hers | +2.040 |
racuse | +1.989 |
lette | +1.985 |
experien | +1.970 |
pict | +1.938 |
Neg logit contributions | |
ades | -2.727 |
emi | -2.578 |
ade | -2.393 |
ghai | -2.348 |
anging | -2.326 |
Token | manager |
Token ID | 4706 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
hers | +0.776 |
racuse | +0.757 |
experien | +0.734 |
lette | +0.733 |
pict | +0.727 |
Neg logit contributions | |
ades | -2.207 |
emi | -2.112 |
ade | -2.005 |
ghai | -1.968 |
anging | -1.960 |
Token | said |
Token ID | 531 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
hers | +1.706 |
racuse | +1.686 |
lette | +1.660 |
experien | +1.653 |
pict | +1.633 |
Neg logit contributions | |
ades | -2.493 |
emi | -2.354 |
ade | -2.201 |
ghai | -2.150 |
anging | -2.139 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ades | +0.088 |
emi | +0.082 |
ade | +0.076 |
ghai | +0.074 |
anging | +0.072 |
Neg logit contributions | |
hers | -0.079 |
racuse | -0.078 |
senal | -0.078 |
experien | -0.077 |
lette | -0.077 |
Token | "… |
Token ID | 29368 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
hers | +0.480 |
experien | +0.476 |
lette | +0.473 |
racuse | +0.471 |
pict | +0.460 |
Neg logit contributions | |
ades | -0.414 |
emi | -0.386 |
ade | -0.352 |
ghai | -0.344 |
anging | -0.336 |
Token | Maybe |
Token ID | 13300 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
hers | +1.720 |
racuse | +1.700 |
lette | +1.695 |
experien | +1.690 |
pict | +1.646 |
Neg logit contributions | |
ades | -1.638 |
emi | -1.529 |
ade | -1.405 |
ghai | -1.368 |
anging | -1.355 |
Token | just |
Token ID | 655 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
hers | +0.982 |
racuse | +0.970 |
lette | +0.964 |
experien | +0.958 |
pict | +0.948 |
Neg logit contributions | |
ades | -1.036 |
emi | -0.965 |
ade | -0.894 |
ghai | -0.870 |
anging | -0.862 |
Token | say |
Token ID | 910 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
hers | +1.412 |
racuse | +1.392 |
lette | +1.387 |
experien | +1.376 |
pict | +1.353 |
Neg logit contributions | |
ades | -1.713 |
emi | -1.605 |
ade | -1.492 |
ghai | -1.454 |
anging | -1.449 |
Token | and |
Token ID | 290 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
racuse | +0.216 |
hers | +0.214 |
lette | +0.211 |
experien | +0.210 |
Admin | +0.204 |
Neg logit contributions | |
ades | -0.215 |
emi | -0.198 |
ade | -0.184 |
ghai | -0.177 |
anging | -0.176 |
Token | a |
Token ID | 257 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
hers | +1.642 |
lette | +1.620 |
racuse | +1.616 |
experien | +1.597 |
pict | +1.563 |
Neg logit contributions | |
ades | -1.640 |
emi | -1.529 |
ade | -1.401 |
ghai | -1.376 |
anging | -1.361 |
Token | balance |
Token ID | 5236 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
hers | +1.118 |
lette | +1.100 |
racuse | +1.100 |
experien | +1.095 |
pict | +1.066 |
Neg logit contributions | |
ades | -1.140 |
emi | -1.068 |
ade | -0.979 |
ghai | -0.959 |
anging | -0.953 |
Token | sheet |
Token ID | 9629 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ades | +2.076 |
emi | +1.970 |
ade | +1.810 |
anging | +1.759 |
ghai | +1.730 |
Neg logit contributions | |
experien | -2.116 |
hers | -2.083 |
racuse | -2.060 |
lette | -2.050 |
pict | -2.033 |
Token | he |
Token ID | 339 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
hers | +0.667 |
racuse | +0.663 |
lette | +0.652 |
experien | +0.649 |
pict | +0.636 |
Neg logit contributions | |
ades | -0.714 |
emi | -0.670 |
ade | -0.617 |
ghai | -0.598 |
anging | -0.596 |
Token | released |
Token ID | 2716 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
hers | +2.110 |
racuse | +2.067 |
lette | +2.066 |
experien | +2.055 |
pict | +2.005 |
Neg logit contributions | |
ades | -2.822 |
emi | -2.671 |
ade | -2.468 |
ghai | -2.422 |
anging | -2.402 |
Token | last |
Token ID | 938 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
ades | +0.289 |
emi | +0.271 |
ade | +0.251 |
ghai | +0.242 |
anging | +0.241 |
Neg logit contributions | |
hers | -0.260 |
racuse | -0.258 |
experien | -0.254 |
lette | -0.254 |
Admin | -0.249 |
Token | July |
Token ID | 2901 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
racuse | +0.139 |
hers | +0.138 |
lette | +0.136 |
experien | +0.135 |
pict | +0.133 |
Neg logit contributions | |
ades | -0.111 |
emi | -0.104 |
ade | -0.094 |
anging | -0.090 |
ghai | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
ades | +1.209 |
emi | +1.129 |
ade | +1.045 |
anging | +0.999 |
ghai | +0.987 |
Neg logit contributions | |
hers | -1.188 |
racuse | -1.185 |
experien | -1.182 |
lette | -1.173 |
Admin | -1.152 |
Token | it |
Token ID | 340 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
hers | +1.435 |
lette | +1.420 |
racuse | +1.416 |
experien | +1.408 |
pict | +1.370 |
Neg logit contributions | |
ades | -1.431 |
emi | -1.338 |
ade | -1.224 |
ghai | -1.191 |
anging | -1.184 |
Token | appears |
Token ID | 3568 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
hers | +0.297 |
racuse | +0.296 |
experien | +0.295 |
lette | +0.294 |
senal | +0.287 |
Neg logit contributions | |
ades | -0.371 |
emi | -0.348 |
ade | -0.323 |
ghai | -0.313 |
anging | -0.310 |
Token | our |
Token ID | 674 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ades | +3.783 |
emi | +3.431 |
ade | +3.249 |
ghai | +3.111 |
anging | +3.107 |
Neg logit contributions | |
racuse | -3.896 |
senal | -3.845 |
raits | -3.717 |
experien | -3.716 |
hers | -3.713 |
Token | first |
Token ID | 717 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ades | +0.649 |
emi | +0.598 |
ade | +0.559 |
anging | +0.542 |
ghai | +0.535 |
Neg logit contributions | |
racuse | -0.630 |
hers | -0.620 |
lette | -0.607 |
senal | -0.603 |
ento | -0.601 |
Token | taste |
Token ID | 6938 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
hers | +3.345 |
lette | +3.280 |
experien | +3.262 |
racuse | +3.250 |
pict | +3.184 |
Neg logit contributions | |
ades | -3.565 |
emi | -3.357 |
ade | -3.066 |
ghai | -3.029 |
anging | -2.991 |
Token | , |
Token ID | 11 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
hers | +2.563 |
racuse | +2.528 |
lette | +2.497 |
experien | +2.485 |
pict | +2.449 |
Neg logit contributions | |
ades | -2.741 |
emi | -2.562 |
ade | -2.365 |
ghai | -2.308 |
anging | -2.292 |
Token | we |
Token ID | 356 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
hers | +0.923 |
racuse | +0.915 |
lette | +0.906 |
experien | +0.903 |
pict | +0.886 |
Neg logit contributions | |
ades | -0.888 |
emi | -0.830 |
ade | -0.758 |
ghai | -0.739 |
anging | -0.735 |
Token | agreed |
Token ID | 4987 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
hers | +0.290 |
racuse | +0.288 |
lette | +0.285 |
experien | +0.283 |
pict | +0.279 |
Neg logit contributions | |
ades | -0.355 |
emi | -0.333 |
ade | -0.310 |
ghai | -0.301 |
anging | -0.300 |
Token | that |
Token ID | 326 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
ades | +5.444 |
emi | +4.924 |
ade | +4.747 |
ghai | +4.359 |
anging | +4.301 |
Neg logit contributions | |
racuse | -6.712 |
senal | -6.691 |
experien | -6.642 |
lette | -6.453 |
hers | -6.449 |
Token | these |
Token ID | 777 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ades | +0.336 |
emi | +0.311 |
ade | +0.292 |
ghai | +0.281 |
anging | +0.279 |
Neg logit contributions | |
racuse | -0.320 |
hers | -0.319 |
experien | -0.315 |
lette | -0.314 |
pict | -0.309 |
Token | brought |
Token ID | 3181 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
ades | +0.634 |
emi | +0.586 |
ade | +0.549 |
ghai | +0.522 |
anging | +0.521 |
Neg logit contributions | |
racuse | -0.604 |
hers | -0.586 |
lette | -0.582 |
experien | -0.581 |
Admin | -0.570 |
Token | to |
Token ID | 284 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ades | +0.074 |
emi | +0.070 |
ade | +0.064 |
ghai | +0.062 |
anging | +0.062 |
Neg logit contributions | |
hers | -0.066 |
racuse | -0.066 |
lette | -0.066 |
experien | -0.065 |
pict | -0.064 |
Token | mind |
Token ID | 2000 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
hers | +0.739 |
racuse | +0.730 |
lette | +0.727 |
experien | +0.723 |
pict | +0.713 |
Neg logit contributions | |
ades | -0.621 |
emi | -0.579 |
ade | -0.527 |
ghai | -0.513 |
anging | -0.511 |
Token | exact |
Token ID | 2748 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
hers | +0.335 |
racuse | +0.330 |
lette | +0.326 |
experien | +0.318 |
pict | +0.318 |
Neg logit contributions | |
ades | -0.491 |
emi | -0.465 |
ade | -0.434 |
ghai | -0.425 |
anging | -0.423 |
Token | mechanism |
Token ID | 9030 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
hers | +0.181 |
racuse | +0.178 |
lette | +0.176 |
pict | +0.173 |
senal | +0.172 |
Neg logit contributions | |
ades | -0.267 |
emi | -0.253 |
ade | -0.237 |
ghai | -0.232 |
anging | -0.231 |
Token | that |
Token ID | 326 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
ades | +2.482 |
emi | +2.291 |
ade | +2.145 |
ghai | +2.075 |
anging | +2.042 |
Neg logit contributions | |
racuse | -2.660 |
hers | -2.586 |
lette | -2.585 |
pict | -2.565 |
experien | -2.559 |
Token | triggered |
Token ID | 13973 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
ades | +0.122 |
emi | +0.115 |
ade | +0.107 |
ghai | +0.105 |
anging | +0.103 |
Neg logit contributions | |
racuse | -0.091 |
hers | -0.091 |
lette | -0.089 |
pict | -0.088 |
experien | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
ades | +1.937 |
emi | +1.807 |
ade | +1.635 |
ghai | +1.588 |
anging | +1.568 |
Neg logit contributions | |
hers | -2.295 |
pict | -2.255 |
racuse | -2.254 |
lette | -2.230 |
experien | -2.211 |
Token | stream |
Token ID | 4269 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ades | +1.685 |
emi | +1.567 |
ade | +1.424 |
anging | +1.394 |
ghai | +1.374 |
Neg logit contributions | |
racuse | -1.960 |
hers | -1.958 |
lette | -1.920 |
pict | -1.910 |
senal | -1.899 |
Token | of |
Token ID | 286 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ades | +5.783 |
emi | +5.235 |
ade | +4.951 |
ghai | +4.645 |
anging | +4.458 |
Neg logit contributions | |
racuse | -7.238 |
experien | -7.162 |
hers | -7.126 |
Admin | -6.900 |
pict | -6.866 |
Token | incorrect |
Token ID | 11491 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
ades | +0.370 |
emi | +0.348 |
ade | +0.315 |
ghai | +0.310 |
anging | +0.309 |
Neg logit contributions | |
hers | -0.387 |
racuse | -0.380 |
lette | -0.378 |
experien | -0.370 |
senal | -0.366 |
Token | data |
Token ID | 1366 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ades | +1.659 |
emi | +1.533 |
ade | +1.430 |
ghai | +1.384 |
anging | +1.377 |
Neg logit contributions | |
hers | -1.875 |
racuse | -1.838 |
lette | -1.806 |
senal | -1.797 |
experien | -1.783 |
Token | . |
Token ID | 13 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
ades | +3.809 |
emi | +3.488 |
ade | +3.287 |
anging | +3.130 |
ghai | +3.108 |
Neg logit contributions | |
racuse | -3.677 |
experien | -3.633 |
senal | -3.625 |
hers | -3.604 |
lette | -3.546 |
Token | They |
Token ID | 1119 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
hers | +2.007 |
lette | +1.968 |
racuse | +1.965 |
experien | +1.963 |
pict | +1.916 |
Neg logit contributions | |
ades | -1.957 |
emi | -1.835 |
ade | -1.675 |
ghai | -1.644 |
anging | -1.622 |
Token | elman |
Token ID | 32370 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
ades | +2.704 |
emi | +2.528 |
ade | +2.349 |
anging | +2.215 |
ghai | +2.201 |
Neg logit contributions | |
experien | -2.655 |
senal | -2.631 |
racuse | -2.577 |
lette | -2.517 |
Admin | -2.514 |
Token | of |
Token ID | 286 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
ades | +1.630 |
emi | +1.532 |
ade | +1.410 |
ghai | +1.340 |
anging | +1.336 |
Neg logit contributions | |
racuse | -1.747 |
experien | -1.730 |
hers | -1.718 |
pict | -1.697 |
lette | -1.694 |
Token | Cong |
Token ID | 2908 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
ades | +1.615 |
emi | +1.490 |
ade | +1.366 |
ghai | +1.302 |
anging | +1.294 |
Neg logit contributions | |
racuse | -1.773 |
hers | -1.768 |
experien | -1.751 |
lette | -1.747 |
pict | -1.723 |
Token | regation |
Token ID | 43068 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ades | +1.406 |
emi | +1.277 |
ade | +1.101 |
aye | +1.035 |
anging | +0.961 |
Neg logit contributions | |
experien | -2.835 |
racuse | -2.794 |
senal | -2.791 |
pict | -2.739 |
Admin | -2.737 |
Token | Kol |
Token ID | 25910 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ades | +3.948 |
emi | +3.602 |
ade | +3.417 |
aye | +3.139 |
ghai | +3.136 |
Neg logit contributions | |
racuse | -4.538 |
hers | -4.425 |
experien | -4.371 |
senal | -4.370 |
lette | -4.295 |
Token | Han |
Token ID | 9530 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
ades | +1.025 |
emi | +0.944 |
ade | +0.889 |
anging | +0.838 |
aye | +0.835 |
Neg logit contributions | |
racuse | -1.086 |
experien | -1.082 |
hers | -1.080 |
lette | -1.050 |
pict | -1.040 |
Token | esh |
Token ID | 5069 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ades | +10.257 |
emi | +9.968 |
ade | +8.974 |
ghai | +8.727 |
anging | +8.551 |
Neg logit contributions | |
racuse | -10.678 |
experien | -10.118 |
senal | -10.091 |
pict | -9.836 |
hers | -9.825 |
Token | ama |
Token ID | 1689 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
ades | +4.457 |
emi | +4.135 |
ade | +3.894 |
aye | +3.688 |
anging | +3.639 |
Neg logit contributions | |
racuse | -4.700 |
hers | -4.511 |
experien | -4.501 |
pict | -4.492 |
Admin | -4.454 |
Token | and |
Token ID | 290 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ades | +2.292 |
emi | +2.196 |
ade | +2.003 |
ghai | +1.903 |
aye | +1.893 |
Neg logit contributions | |
racuse | -2.489 |
experien | -2.398 |
lette | -2.396 |
hers | -2.393 |
pict | -2.363 |
Token | Rabbi |
Token ID | 31807 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ades | +0.534 |
emi | +0.495 |
ade | +0.456 |
ghai | +0.434 |
anging | +0.432 |
Neg logit contributions | |
racuse | -0.568 |
hers | -0.565 |
lette | -0.562 |
experien | -0.552 |
ento | -0.550 |
Token | Leon |
Token ID | 10592 |
Feature activation | +4.47e-04 |
Pos logit contributions | |
ades | +4.392 |
emi | +4.068 |
ade | +3.818 |
aye | +3.530 |
ghai | +3.528 |
Neg logit contributions | |
racuse | -5.259 |
hers | -5.083 |
senal | -5.044 |
experien | -5.044 |
ento | -5.007 |
Token | é |
Token ID | 2634 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
ades | +2.936 |
emi | +2.761 |
ade | +2.564 |
anging | +2.398 |
aye | +2.370 |
Neg logit contributions | |
experien | -2.586 |
senal | -2.550 |
racuse | -2.537 |
hers | -2.525 |
Admin | -2.492 |
Token | pend |
Token ID | 37038 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
ades | +2.479 |
emi | +2.312 |
ade | +2.135 |
end | +1.918 |
aye | +1.876 |
Neg logit contributions | |
racuse | -3.166 |
hers | -3.095 |
Admin | -3.048 |
senal | -3.044 |
experien | -3.028 |
Token | ante |
Token ID | 12427 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
ades | +1.903 |
emi | +1.768 |
ade | +1.661 |
aye | +1.535 |
end | +1.509 |
Neg logit contributions | |
hers | -1.986 |
racuse | -1.972 |
experien | -1.959 |
senal | -1.948 |
lette | -1.906 |
Token | , |
Token ID | 11 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
ades | +3.253 |
emi | +3.085 |
ade | +2.856 |
end | +2.624 |
aye | +2.616 |
Neg logit contributions | |
racuse | -3.205 |
hers | -3.148 |
pict | -3.032 |
senal | -3.003 |
Admin | -2.988 |
Token | le |
Token ID | 443 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ades | +0.992 |
emi | +0.940 |
ade | +0.860 |
anging | +0.809 |
aye | +0.806 |
Neg logit contributions | |
hers | -0.983 |
racuse | -0.978 |
lette | -0.945 |
pict | -0.941 |
experien | -0.934 |
Token | Fl |
Token ID | 1610 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ades | +3.449 |
emi | +3.245 |
ade | +3.032 |
anging | +2.856 |
aye | +2.806 |
Neg logit contributions | |
racuse | -3.162 |
hers | -3.154 |
lette | -3.017 |
Admin | -3.008 |
pict | -2.988 |
Token | otte |
Token ID | 11404 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ades | +6.000 |
emi | +5.610 |
ade | +5.219 |
aye | +4.931 |
anging | +4.920 |
Neg logit contributions | |
senal | -7.108 |
hers | -7.032 |
experien | -6.993 |
racuse | -6.859 |
pict | -6.626 |
Token | de |
Token ID | 390 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ades | +3.430 |
emi | +3.275 |
ade | +2.988 |
ghai | +2.778 |
aye | +2.746 |
Neg logit contributions | |
hers | -3.466 |
racuse | -3.454 |
pict | -3.283 |
experien | -3.282 |
senal | -3.278 |
Token | l |
Token ID | 300 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ades | +4.193 |
emi | +3.862 |
ade | +3.629 |
ghai | +3.379 |
anging | +3.296 |
Neg logit contributions | |
hers | -4.441 |
racuse | -4.414 |
experien | -4.286 |
Admin | -4.278 |
pict | -4.241 |
Token | ' |
Token ID | 6 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
ades | +4.689 |
emi | +4.259 |
ade | +4.150 |
anging | +3.811 |
end | +3.704 |
Neg logit contributions | |
racuse | -4.560 |
hers | -4.478 |
experien | -4.463 |
senal | -4.443 |
pict | -4.388 |
Token | O |
Token ID | 46 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
ades | +2.785 |
emi | +2.640 |
ade | +2.475 |
anging | +2.362 |
aye | +2.330 |
Neg logit contributions | |
racuse | -2.442 |
hers | -2.370 |
lette | -2.355 |
experien | -2.343 |
senal | -2.294 |
Token | from |
Token ID | 422 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
ades | +2.666 |
emi | +2.486 |
ade | +2.311 |
ghai | +2.177 |
aye | +2.161 |
Neg logit contributions | |
racuse | -2.830 |
hers | -2.769 |
lette | -2.768 |
experien | -2.719 |
Admin | -2.685 |
Token | the |
Token ID | 262 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
ades | +1.575 |
emi | +1.436 |
ade | +1.337 |
anging | +1.266 |
ghai | +1.244 |
Neg logit contributions | |
racuse | -1.700 |
lette | -1.696 |
hers | -1.694 |
experien | -1.647 |
pict | -1.646 |
Token | horse |
Token ID | 8223 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
ades | +1.766 |
emi | +1.658 |
ade | +1.535 |
anging | +1.474 |
ghai | +1.465 |
Neg logit contributions | |
racuse | -1.610 |
lette | -1.580 |
hers | -1.565 |
pict | -1.522 |
ento | -1.504 |
Token | 's |
Token ID | 338 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
ades | +2.343 |
emi | +2.161 |
ade | +2.057 |
aye | +1.909 |
ghai | +1.896 |
Neg logit contributions | |
racuse | -2.277 |
experien | -2.190 |
hers | -2.185 |
ento | -2.161 |
lette | -2.150 |
Token | mouth |
Token ID | 5422 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ades | +1.096 |
emi | +1.009 |
ade | +0.925 |
anging | +0.871 |
ghai | +0.860 |
Neg logit contributions | |
racuse | -1.356 |
hers | -1.316 |
experien | -1.295 |
lette | -1.289 |
senal | -1.271 |
Token | ! |
Token ID | 0 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
hers | +1.201 |
racuse | +1.188 |
lette | +1.178 |
experien | +1.173 |
pict | +1.142 |
Neg logit contributions | |
ades | -1.432 |
emi | -1.350 |
ade | -1.248 |
ghai | -1.217 |
anging | -1.204 |
Token | Now |
Token ID | 2735 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ades | +5.884 |
emi | +5.468 |
ade | +5.139 |
Kappa | +4.812 |
Tart | +4.697 |
Neg logit contributions | |
senal | -8.098 |
racuse | -8.033 |
experien | -7.715 |
lette | -7.707 |
hers | -7.632 |
Token | , |
Token ID | 11 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ades | +1.303 |
emi | +1.216 |
ade | +1.136 |
anging | +1.083 |
ghai | +1.083 |
Neg logit contributions | |
racuse | -1.296 |
hers | -1.281 |
lette | -1.268 |
experien | -1.259 |
pict | -1.241 |
Token | as |
Token ID | 355 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
ades | +1.037 |
emi | +0.969 |
ade | +0.900 |
ghai | +0.871 |
anging | +0.866 |
Neg logit contributions | |
racuse | -0.956 |
hers | -0.955 |
lette | -0.951 |
experien | -0.932 |
Admin | -0.917 |
Token | cool |
Token ID | 3608 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
ades | +2.142 |
emi | +1.988 |
ade | +1.850 |
anging | +1.770 |
ghai | +1.759 |
Neg logit contributions | |
racuse | -2.078 |
lette | -2.042 |
hers | -2.024 |
pict | -1.972 |
senal | -1.971 |
Token | as |
Token ID | 355 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ades | +1.350 |
emi | +1.259 |
ade | +1.177 |
anging | +1.134 |
ghai | +1.129 |
Neg logit contributions | |
racuse | -1.091 |
hers | -1.089 |
lette | -1.056 |
experien | -1.042 |
Admin | -1.034 |