Token | while |
Token ID | 981 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
axter | +0.337 |
�� | +0.335 |
ioch | +0.331 |
theless | +0.330 |
arnaev | +0.326 |
Neg logit contributions | |
FAQ | -0.363 |
Bowman | -0.278 |
DG | -0.262 |
roots | -0.253 |
Dems | -0.251 |
Token | CBS |
Token ID | 11133 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
FAQ | +0.036 |
Bowman | +0.028 |
DG | +0.026 |
roots | +0.026 |
vae | +0.025 |
Neg logit contributions | |
axter | -0.031 |
�� | -0.031 |
ioch | -0.031 |
theless | -0.031 |
arnaev | -0.030 |
Token | ' |
Token ID | 6 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
axter | +0.301 |
�� | +0.300 |
ioch | +0.296 |
theless | +0.294 |
arnaev | +0.290 |
Neg logit contributions | |
FAQ | -0.356 |
Bowman | -0.276 |
DG | -0.260 |
roots | -0.252 |
Dems | -0.250 |
Token | anchor |
Token ID | 18021 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
axter | +0.097 |
�� | +0.096 |
ioch | +0.095 |
theless | +0.095 |
arnaev | +0.093 |
Neg logit contributions | |
FAQ | -0.114 |
Bowman | -0.088 |
DG | -0.083 |
roots | -0.080 |
ollow | -0.080 |
Token | Scott |
Token ID | 4746 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
axter | +0.291 |
�� | +0.290 |
ioch | +0.286 |
theless | +0.285 |
arnaev | +0.281 |
Neg logit contributions | |
FAQ | -0.343 |
Bowman | -0.266 |
DG | -0.251 |
roots | -0.243 |
Dems | -0.241 |
Token | Pel |
Token ID | 12903 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
axter | +0.429 |
�� | +0.429 |
ioch | +0.423 |
theless | +0.422 |
arnaev | +0.417 |
Neg logit contributions | |
FAQ | -0.395 |
Bowman | -0.297 |
DG | -0.275 |
roots | -0.265 |
ollow | -0.263 |
Token | ley |
Token ID | 1636 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
FAQ | +2.020 |
Bowman | +1.502 |
DG | +1.406 |
Bounty | +1.402 |
Dems | +1.402 |
Neg logit contributions | |
ioch | -2.136 |
axter | -2.110 |
�� | -2.106 |
theless | -2.096 |
arnaev | -2.078 |
Token | is |
Token ID | 318 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
axter | +0.073 |
�� | +0.073 |
ioch | +0.072 |
theless | +0.072 |
arnaev | +0.071 |
Neg logit contributions | |
FAQ | -0.084 |
Bowman | -0.065 |
DG | -0.061 |
roots | -0.060 |
ollow | -0.059 |
Token | leading |
Token ID | 3756 |
Feature activation | -4.38e-03 |
Pos logit contributions | |
axter | +0.139 |
�� | +0.138 |
ioch | +0.137 |
theless | +0.136 |
arnaev | +0.134 |
Neg logit contributions | |
FAQ | -0.156 |
Bowman | -0.120 |
DG | -0.113 |
roots | -0.109 |
ollow | -0.108 |
Token | his |
Token ID | 465 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
axter | +0.003 |
�� | +0.003 |
ioch | +0.003 |
theless | +0.003 |
arnaev | +0.003 |
Neg logit contributions | |
FAQ | -0.003 |
Bowman | -0.003 |
DG | -0.002 |
roots | -0.002 |
ollow | -0.002 |
Token | network |
Token ID | 3127 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
axter | +0.210 |
�� | +0.209 |
ioch | +0.206 |
theless | +0.205 |
arnaev | +0.203 |
Neg logit contributions | |
FAQ | -0.248 |
Bowman | -0.193 |
DG | -0.182 |
roots | -0.176 |
Dems | -0.175 |
Token |
|
Token ID | 198 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
FAQ | +0.156 |
Bowman | +0.120 |
DG | +0.113 |
roots | +0.109 |
vae | +0.109 |
Neg logit contributions | |
axter | -0.141 |
�� | -0.139 |
ioch | -0.138 |
theless | -0.138 |
arnaev | -0.136 |
Token |
|
Token ID | 198 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
axter | +0.018 |
�� | +0.018 |
ioch | +0.018 |
theless | +0.018 |
arnaev | +0.017 |
Neg logit contributions | |
FAQ | -0.021 |
Bowman | -0.016 |
DG | -0.015 |
roots | -0.015 |
vae | -0.015 |
Token | Book |
Token ID | 10482 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
FAQ | +0.042 |
Bowman | +0.033 |
DG | +0.031 |
roots | +0.030 |
vae | +0.029 |
Neg logit contributions | |
axter | -0.039 |
�� | -0.039 |
ioch | -0.038 |
theless | -0.038 |
arnaev | -0.038 |
Token | mark |
Token ID | 4102 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
FAQ | +0.374 |
Bowman | +0.312 |
DG | +0.300 |
roots | +0.293 |
vae | +0.292 |
Neg logit contributions | |
axter | -0.139 |
�� | -0.136 |
ioch | -0.134 |
theless | -0.134 |
arnaev | -0.130 |
Token | with |
Token ID | 351 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
FAQ | +0.701 |
Bowman | +0.533 |
DG | +0.500 |
roots | +0.493 |
vae | +0.492 |
Neg logit contributions | |
axter | -0.618 |
�� | -0.609 |
ioch | -0.606 |
theless | -0.605 |
arnaev | -0.596 |
Token | : |
Token ID | 25 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
FAQ | +0.339 |
Bowman | +0.261 |
DG | +0.245 |
roots | +0.239 |
vae | +0.237 |
Neg logit contributions | |
axter | -0.302 |
�� | -0.298 |
ioch | -0.297 |
theless | -0.294 |
arnaev | -0.292 |
Token | Delicious |
Token ID | 39528 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
FAQ | +2.017 |
Bowman | +1.482 |
DG | +1.409 |
vae | +1.409 |
roots | +1.393 |
Neg logit contributions | |
axter | -2.098 |
ioch | -2.044 |
theless | -1.996 |
paren | -1.987 |
arnaev | -1.983 |
Token |
|
Token ID | 198 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
FAQ | +0.056 |
Bowman | +0.043 |
DG | +0.041 |
roots | +0.039 |
vae | +0.039 |
Neg logit contributions | |
axter | -0.047 |
�� | -0.047 |
ioch | -0.047 |
theless | -0.046 |
arnaev | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
axter | +0.341 |
�� | +0.340 |
ioch | +0.334 |
theless | +0.334 |
arnaev | +0.329 |
Neg logit contributions | |
FAQ | -0.386 |
Bowman | -0.297 |
DG | -0.280 |
roots | -0.271 |
ollow | -0.269 |
Token | D |
Token ID | 35 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
�� | +0.303 |
axter | +0.303 |
ioch | +0.297 |
theless | +0.297 |
arnaev | +0.292 |
Neg logit contributions | |
FAQ | -0.345 |
Bowman | -0.265 |
DG | -0.250 |
roots | -0.242 |
Dems | -0.240 |
Token | igg |
Token ID | 6950 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
�� | +0.326 |
axter | +0.325 |
theless | +0.317 |
ioch | +0.315 |
arnaev | +0.310 |
Neg logit contributions | |
FAQ | -0.686 |
Bowman | -0.560 |
DG | -0.539 |
ollow | -0.526 |
roots | -0.525 |
Token | sporting |
Token ID | 17702 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
FAQ | +0.666 |
Bowman | +0.513 |
DG | +0.484 |
ollow | +0.468 |
roots | +0.468 |
Neg logit contributions | |
�� | -0.569 |
axter | -0.565 |
ioch | -0.557 |
theless | -0.553 |
arnaev | -0.547 |
Token | black |
Token ID | 2042 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
FAQ | +0.030 |
Bowman | +0.023 |
DG | +0.021 |
roots | +0.021 |
ollow | +0.021 |
Neg logit contributions | |
axter | -0.026 |
�� | -0.026 |
ioch | -0.026 |
theless | -0.026 |
arnaev | -0.025 |
Token | bomber |
Token ID | 24065 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
axter | +0.086 |
�� | +0.085 |
ioch | +0.084 |
theless | +0.084 |
arnaev | +0.083 |
Neg logit contributions | |
FAQ | -0.070 |
Bowman | -0.051 |
DG | -0.047 |
roots | -0.045 |
ollow | -0.045 |
Token | jacket |
Token ID | 15224 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
FAQ | +0.025 |
Bowman | +0.019 |
DG | +0.018 |
roots | +0.017 |
ollow | +0.017 |
Neg logit contributions | |
axter | -0.026 |
�� | -0.026 |
ioch | -0.026 |
theless | -0.026 |
arnaev | -0.026 |
Token | with |
Token ID | 351 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
axter | +0.189 |
�� | +0.188 |
ioch | +0.186 |
theless | +0.185 |
arnaev | +0.183 |
Neg logit contributions | |
FAQ | -0.220 |
Bowman | -0.170 |
DG | -0.161 |
roots | -0.156 |
Dems | -0.155 |
Token | ' |
Token ID | 705 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
axter | +0.340 |
�� | +0.337 |
theless | +0.333 |
ioch | +0.332 |
arnaev | +0.325 |
Neg logit contributions | |
FAQ | -0.526 |
Bowman | -0.422 |
DG | -0.402 |
roots | -0.391 |
Dems | -0.388 |
Token | 44 |
Token ID | 2598 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
FAQ | +2.341 |
Bowman | +1.845 |
DG | +1.717 |
vae | +1.712 |
Bounty | +1.677 |
Neg logit contributions | |
axter | -1.811 |
ioch | -1.738 |
paren | -1.698 |
theless | -1.686 |
arnaev | -1.686 |
Token | ' |
Token ID | 6 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
FAQ | +1.478 |
Bowman | +1.125 |
DG | +1.045 |
vae | +1.033 |
roots | +1.025 |
Neg logit contributions | |
axter | -1.330 |
ioch | -1.298 |
arnaev | -1.290 |
�� | -1.288 |
theless | -1.275 |
Token | on |
Token ID | 319 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
FAQ | +1.202 |
Bowman | +0.919 |
DG | +0.855 |
roots | +0.854 |
vae | +0.847 |
Neg logit contributions | |
axter | -0.980 |
�� | -0.975 |
ioch | -0.967 |
arnaev | -0.950 |
theless | -0.936 |
Token | sleeve |
Token ID | 23179 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
FAQ | +0.503 |
Bowman | +0.386 |
DG | +0.364 |
vae | +0.356 |
roots | +0.355 |
Neg logit contributions | |
axter | -0.419 |
�� | -0.414 |
ioch | -0.410 |
theless | -0.403 |
arnaev | -0.402 |
Token | at |
Token ID | 379 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
FAQ | +0.565 |
Bowman | +0.432 |
DG | +0.407 |
roots | +0.399 |
vae | +0.399 |
Neg logit contributions | |
axter | -0.481 |
�� | -0.476 |
theless | -0.473 |
ioch | -0.471 |
arnaev | -0.467 |
Token | looms |
Token ID | 46234 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
FAQ | +0.862 |
Bowman | +0.684 |
DG | +0.649 |
iris | +0.629 |
ollow | +0.627 |
Neg logit contributions | |
axter | -0.603 |
ioch | -0.590 |
theless | -0.587 |
�� | -0.584 |
arnaev | -0.578 |
Token | over |
Token ID | 625 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
FAQ | +0.477 |
Bowman | +0.365 |
DG | +0.343 |
roots | +0.332 |
ollow | +0.332 |
Neg logit contributions | |
axter | -0.445 |
�� | -0.440 |
ioch | -0.436 |
theless | -0.432 |
arnaev | -0.430 |
Token | the |
Token ID | 262 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
FAQ | +0.138 |
Bowman | +0.106 |
DG | +0.100 |
roots | +0.097 |
vae | +0.097 |
Neg logit contributions | |
axter | -0.122 |
�� | -0.122 |
ioch | -0.120 |
theless | -0.120 |
arnaev | -0.118 |
Token | 2020 |
Token ID | 12131 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
FAQ | +1.006 |
Bowman | +0.774 |
DG | +0.727 |
atsu | +0.703 |
vae | +0.699 |
Neg logit contributions | |
axter | -0.933 |
ioch | -0.922 |
theless | -0.917 |
�� | -0.915 |
arnaev | -0.910 |
Token | race |
Token ID | 3234 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
FAQ | +1.429 |
Bowman | +1.089 |
DG | +1.056 |
vae | +1.022 |
iris | +1.012 |
Neg logit contributions | |
axter | -1.218 |
ioch | -1.192 |
�� | -1.186 |
arnaev | -1.181 |
theless | -1.170 |
Token | Obama |
Token ID | 2486 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
FAQ | +0.634 |
Bowman | +0.483 |
DG | +0.455 |
iris | +0.446 |
roots | +0.443 |
Neg logit contributions | |
axter | -0.573 |
theless | -0.564 |
ioch | -0.564 |
�� | -0.563 |
arnaev | -0.560 |
Token | goes |
Token ID | 2925 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
FAQ | +2.151 |
Bowman | +1.702 |
atsu | +1.553 |
vae | +1.537 |
ierre | +1.535 |
Neg logit contributions | |
axter | -1.817 |
paren | -1.810 |
ioch | -1.778 |
theless | -1.774 |
�� | -1.734 |
Token | viral |
Token ID | 14416 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
FAQ | +0.639 |
Bowman | +0.484 |
DG | +0.454 |
roots | +0.433 |
ollow | +0.433 |
Neg logit contributions | |
axter | -0.647 |
ioch | -0.637 |
�� | -0.635 |
theless | -0.628 |
arnaev | -0.627 |
Token | after |
Token ID | 706 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
FAQ | +0.460 |
Bowman | +0.350 |
DG | +0.331 |
vae | +0.321 |
roots | +0.321 |
Neg logit contributions | |
axter | -0.415 |
�� | -0.409 |
ioch | -0.404 |
theless | -0.402 |
arnaev | -0.398 |
Token | sporting |
Token ID | 17702 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
FAQ | +0.666 |
Bowman | +0.513 |
DG | +0.484 |
ollow | +0.468 |
roots | +0.468 |
Neg logit contributions | |
�� | -0.569 |
axter | -0.565 |
ioch | -0.557 |
theless | -0.553 |
arnaev | -0.547 |
Token | black |
Token ID | 2042 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
FAQ | +0.030 |
Bowman | +0.023 |
DG | +0.021 |
roots | +0.021 |
ollow | +0.021 |
Neg logit contributions | |
axter | -0.026 |
�� | -0.026 |
ioch | -0.026 |
theless | -0.026 |
arnaev | -0.025 |
Token | Diane |
Token ID | 26542 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
axter | +0.041 |
�� | +0.041 |
ioch | +0.040 |
theless | +0.040 |
arnaev | +0.040 |
Neg logit contributions | |
FAQ | -0.034 |
Bowman | -0.024 |
DG | -0.023 |
roots | -0.022 |
ollow | -0.022 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
FAQ | +0.527 |
Bowman | +0.411 |
DG | +0.391 |
roots | +0.381 |
ollow | +0.379 |
Neg logit contributions | |
axter | -0.380 |
�� | -0.374 |
theless | -0.368 |
ioch | -0.367 |
arnaev | -0.365 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
FAQ | +0.474 |
Bowman | +0.373 |
DG | +0.356 |
roots | +0.345 |
ollow | +0.343 |
Neg logit contributions | |
axter | -0.340 |
�� | -0.335 |
theless | -0.332 |
ioch | -0.330 |
arnaev | -0.326 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
FAQ | +0.285 |
Bowman | +0.219 |
DG | +0.206 |
roots | +0.198 |
ollow | +0.197 |
Neg logit contributions | |
axter | -0.271 |
�� | -0.267 |
ioch | -0.265 |
theless | -0.264 |
arnaev | -0.261 |
Token | : |
Token ID | 25 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
FAQ | +0.346 |
Bowman | +0.275 |
DG | +0.261 |
roots | +0.254 |
ollow | +0.253 |
Neg logit contributions | |
axter | -0.237 |
�� | -0.232 |
ioch | -0.231 |
theless | -0.231 |
arnaev | -0.227 |
Token | ' |
Token ID | 705 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
FAQ | +0.343 |
Bowman | +0.261 |
DG | +0.247 |
roots | +0.239 |
vae | +0.239 |
Neg logit contributions | |
axter | -0.301 |
�� | -0.295 |
ioch | -0.295 |
theless | -0.295 |
arnaev | -0.291 |
Token | I |
Token ID | 40 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
FAQ | +2.081 |
Bowman | +1.610 |
DG | +1.558 |
vae | +1.511 |
ollow | +1.486 |
Neg logit contributions | |
axter | -1.798 |
theless | -1.722 |
ioch | -1.721 |
�� | -1.668 |
paren | -1.666 |
Token | fully |
Token ID | 3938 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
FAQ | +1.371 |
Bowman | +1.069 |
DG | +1.023 |
roots | +1.002 |
atsu | +0.985 |
Neg logit contributions | |
axter | -1.071 |
theless | -1.042 |
ioch | -1.041 |
�� | -1.030 |
arnaev | -1.029 |
Token | expect |
Token ID | 1607 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
FAQ | +0.767 |
Bowman | +0.596 |
DG | +0.567 |
roots | +0.554 |
ollow | +0.548 |
Neg logit contributions | |
axter | -0.585 |
�� | -0.570 |
ioch | -0.568 |
theless | -0.563 |
arnaev | -0.557 |
Token | ' |
Token ID | 6 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
axter | +0.006 |
�� | +0.006 |
ioch | +0.006 |
theless | +0.006 |
arnaev | +0.006 |
Neg logit contributions | |
FAQ | -0.012 |
Bowman | -0.010 |
DG | -0.009 |
roots | -0.009 |
vae | -0.009 |
Token | fair |
Token ID | 3148 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
FAQ | +0.459 |
Bowman | +0.355 |
DG | +0.336 |
roots | +0.328 |
ollow | +0.327 |
Neg logit contributions | |
axter | -0.372 |
�� | -0.370 |
ioch | -0.366 |
theless | -0.366 |
arnaev | -0.360 |
Token | Diane |
Token ID | 26542 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
axter | +0.056 |
�� | +0.055 |
ioch | +0.055 |
theless | +0.055 |
arnaev | +0.054 |
Neg logit contributions | |
FAQ | -0.046 |
Bowman | -0.033 |
DG | -0.031 |
roots | -0.030 |
ollow | -0.029 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
FAQ | +0.296 |
Bowman | +0.232 |
DG | +0.220 |
roots | +0.214 |
ollow | +0.212 |
Neg logit contributions | |
axter | -0.218 |
�� | -0.215 |
theless | -0.213 |
ioch | -0.212 |
arnaev | -0.210 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
FAQ | +0.550 |
Bowman | +0.433 |
DG | +0.413 |
roots | +0.401 |
ollow | +0.399 |
Neg logit contributions | |
axter | -0.392 |
�� | -0.386 |
theless | -0.383 |
ioch | -0.380 |
arnaev | -0.376 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
FAQ | +0.400 |
Bowman | +0.312 |
DG | +0.294 |
roots | +0.284 |
ollow | +0.283 |
Neg logit contributions | |
axter | -0.345 |
�� | -0.339 |
ioch | -0.337 |
theless | -0.336 |
arnaev | -0.332 |
Token | : |
Token ID | 25 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
FAQ | +0.789 |
Bowman | +0.632 |
DG | +0.596 |
ollow | +0.582 |
vae | +0.582 |
Neg logit contributions | |
axter | -0.522 |
theless | -0.510 |
ioch | -0.509 |
�� | -0.506 |
arnaev | -0.500 |
Token | ' |
Token ID | 705 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
FAQ | +0.403 |
Bowman | +0.306 |
DG | +0.289 |
vae | +0.281 |
iris | +0.280 |
Neg logit contributions | |
axter | -0.353 |
ioch | -0.346 |
�� | -0.346 |
theless | -0.345 |
arnaev | -0.342 |
Token | I |
Token ID | 40 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
FAQ | +1.939 |
Bowman | +1.498 |
DG | +1.437 |
vae | +1.406 |
ollow | +1.377 |
Neg logit contributions | |
axter | -1.681 |
theless | -1.633 |
ioch | -1.623 |
paren | -1.583 |
�� | -1.582 |
Token | fully |
Token ID | 3938 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
FAQ | +1.155 |
Bowman | +0.898 |
DG | +0.857 |
roots | +0.834 |
vae | +0.826 |
Neg logit contributions | |
axter | -0.913 |
theless | -0.894 |
ioch | -0.890 |
�� | -0.879 |
arnaev | -0.875 |
Token | expect |
Token ID | 1607 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
FAQ | +0.702 |
Bowman | +0.546 |
DG | +0.520 |
roots | +0.507 |
ollow | +0.502 |
Neg logit contributions | |
axter | -0.533 |
�� | -0.519 |
ioch | -0.518 |
theless | -0.514 |
arnaev | -0.508 |
Token | ' |
Token ID | 6 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
axter | +0.061 |
�� | +0.060 |
ioch | +0.059 |
theless | +0.059 |
arnaev | +0.058 |
Neg logit contributions | |
FAQ | -0.108 |
Bowman | -0.088 |
DG | -0.084 |
roots | -0.082 |
vae | -0.081 |
Token | fair |
Token ID | 3148 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
FAQ | +0.223 |
Bowman | +0.173 |
DG | +0.163 |
roots | +0.159 |
vae | +0.158 |
Neg logit contributions | |
axter | -0.186 |
�� | -0.184 |
ioch | -0.183 |
theless | -0.182 |
arnaev | -0.180 |
Token | Murray |
Token ID | 12164 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
FAQ | +1.421 |
Bowman | +1.196 |
DG | +1.165 |
vae | +1.151 |
ollow | +1.149 |
Neg logit contributions | |
axter | -0.350 |
theless | -0.321 |
ioch | -0.321 |
�� | -0.314 |
arnaev | -0.298 |
Token | N |
Token ID | 399 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
FAQ | +1.391 |
Bowman | +1.037 |
DG | +0.986 |
vae | +0.974 |
orthy | +0.958 |
Neg logit contributions | |
axter | -1.346 |
ioch | -1.318 |
theless | -1.314 |
paren | -1.305 |
�� | -1.299 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
axter | +0.510 |
�� | +0.509 |
ioch | +0.502 |
theless | +0.500 |
arnaev | +0.493 |
Neg logit contributions | |
FAQ | -0.533 |
Bowman | -0.408 |
DG | -0.382 |
roots | -0.373 |
vae | -0.368 |
Token | Roth |
Token ID | 16131 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
FAQ | +1.285 |
Bowman | +1.047 |
DG | +1.004 |
vae | +0.990 |
iris | +0.987 |
Neg logit contributions | |
axter | -0.621 |
theless | -0.609 |
ioch | -0.600 |
�� | -0.597 |
arnaev | -0.591 |
Token | bard |
Token ID | 23024 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
FAQ | +0.670 |
Bowman | +0.535 |
DG | +0.509 |
Dems | +0.496 |
vae | +0.494 |
Neg logit contributions | |
axter | -0.428 |
ioch | -0.421 |
�� | -0.418 |
theless | -0.417 |
arnaev | -0.405 |
Token | ( |
Token ID | 357 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
FAQ | +1.245 |
Bowman | +0.958 |
DG | +0.902 |
iris | +0.890 |
roots | +0.887 |
Neg logit contributions | |
axter | -1.047 |
ioch | -1.028 |
�� | -1.020 |
theless | -1.009 |
paren | -0.995 |
Token | Prom |
Token ID | 24129 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
FAQ | +1.426 |
Bowman | +1.001 |
DG | +0.920 |
Dems | +0.913 |
vae | +0.898 |
Neg logit contributions | |
axter | -2.132 |
ioch | -2.118 |
theless | -2.088 |
arnaev | -2.076 |
paren | -2.058 |
Token | etheus |
Token ID | 36916 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
FAQ | +0.758 |
Bowman | +0.614 |
DG | +0.591 |
vae | +0.580 |
ollow | +0.575 |
Neg logit contributions | |
axter | -0.383 |
ioch | -0.380 |
�� | -0.375 |
theless | -0.371 |
arnaev | -0.363 |
Token | Books |
Token ID | 13661 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
FAQ | +0.793 |
Bowman | +0.587 |
DG | +0.542 |
vae | +0.531 |
roots | +0.522 |
Neg logit contributions | |
axter | -0.897 |
ioch | -0.883 |
�� | -0.873 |
theless | -0.869 |
paren | -0.862 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
FAQ | +0.502 |
Bowman | +0.389 |
DG | +0.365 |
vae | +0.356 |
roots | +0.356 |
Neg logit contributions | |
axter | -0.424 |
ioch | -0.420 |
�� | -0.418 |
theless | -0.414 |
arnaev | -0.408 |
Token | 2000 |
Token ID | 4751 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
FAQ | +0.727 |
Bowman | +0.531 |
DG | +0.493 |
roots | +0.481 |
vae | +0.479 |
Neg logit contributions | |
axter | -0.853 |
ioch | -0.845 |
�� | -0.837 |
theless | -0.832 |
arnaev | -0.828 |
Token | President |
Token ID | 1992 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
FAQ | +0.118 |
Bowman | +0.091 |
DG | +0.086 |
roots | +0.083 |
ollow | +0.083 |
Neg logit contributions | |
axter | -0.102 |
�� | -0.101 |
ioch | -0.100 |
theless | -0.100 |
arnaev | -0.099 |
Token | Trump |
Token ID | 1301 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
FAQ | +0.070 |
Bowman | +0.055 |
DG | +0.053 |
roots | +0.051 |
ollow | +0.051 |
Neg logit contributions | |
axter | -0.046 |
�� | -0.045 |
ioch | -0.045 |
theless | -0.045 |
arnaev | -0.044 |
Token | Donald |
Token ID | 3759 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
axter | +0.143 |
�� | +0.142 |
ioch | +0.141 |
theless | +0.140 |
arnaev | +0.139 |
Neg logit contributions | |
FAQ | -0.148 |
Bowman | -0.112 |
DG | -0.106 |
roots | -0.102 |
ollow | -0.101 |
Token | John |
Token ID | 1757 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
axter | +0.059 |
�� | +0.058 |
ioch | +0.057 |
theless | +0.057 |
arnaev | +0.056 |
Neg logit contributions | |
FAQ | -0.070 |
Bowman | -0.054 |
DG | -0.051 |
roots | -0.049 |
vae | -0.049 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
FAQ | +0.250 |
Bowman | +0.203 |
DG | +0.194 |
roots | +0.190 |
vae | +0.189 |
Neg logit contributions | |
axter | -0.129 |
�� | -0.127 |
ioch | -0.126 |
theless | -0.125 |
arnaev | -0.123 |
Token | House |
Token ID | 18102 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
FAQ | +0.218 |
Bowman | +0.168 |
DG | +0.158 |
roots | +0.153 |
vae | +0.152 |
Neg logit contributions | |
axter | -0.201 |
�� | -0.199 |
ioch | -0.198 |
theless | -0.196 |
arnaev | -0.194 |
Token | committee |
Token ID | 5583 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
FAQ | +1.810 |
Bowman | +1.365 |
DG | +1.268 |
roots | +1.258 |
vae | +1.235 |
Neg logit contributions | |
axter | -1.815 |
ioch | -1.748 |
arnaev | -1.720 |
theless | -1.718 |
paren | -1.698 |
Token | believes |
Token ID | 5804 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
axter | +0.139 |
�� | +0.139 |
ioch | +0.138 |
theless | +0.137 |
arnaev | +0.136 |
Neg logit contributions | |
FAQ | -0.074 |
Bowman | -0.048 |
DG | -0.043 |
roots | -0.040 |
ollow | -0.040 |
Token | it |
Token ID | 340 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
axter | +0.419 |
�� | +0.416 |
theless | +0.411 |
ioch | +0.406 |
arnaev | +0.398 |
Neg logit contributions | |
FAQ | -0.775 |
Bowman | -0.632 |
DG | -0.606 |
Dems | -0.591 |
roots | -0.588 |
Token | has |
Token ID | 468 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
FAQ | +0.217 |
Bowman | +0.171 |
DG | +0.162 |
roots | +0.158 |
vae | +0.157 |
Neg logit contributions | |
axter | -0.158 |
�� | -0.157 |
ioch | -0.156 |
theless | -0.155 |
arnaev | -0.153 |
Token | evidence |
Token ID | 2370 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
FAQ | +0.700 |
Bowman | +0.568 |
DG | +0.543 |
vae | +0.531 |
atsu | +0.531 |
Neg logit contributions | |
axter | -0.354 |
ioch | -0.347 |
�� | -0.347 |
theless | -0.344 |
arnaev | -0.338 |
Token | com |
Token ID | 785 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
FAQ | +0.244 |
Bowman | +0.181 |
DG | +0.168 |
roots | +0.162 |
vae | +0.160 |
Neg logit contributions | |
axter | -0.278 |
�� | -0.276 |
ioch | -0.274 |
theless | -0.273 |
arnaev | -0.269 |
Token | or |
Token ID | 393 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
axter | +0.034 |
�� | +0.034 |
ioch | +0.034 |
theless | +0.033 |
arnaev | +0.033 |
Neg logit contributions | |
FAQ | -0.038 |
Bowman | -0.030 |
DG | -0.028 |
roots | -0.027 |
vae | -0.027 |
Token | call |
Token ID | 869 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
FAQ | +0.131 |
Bowman | +0.098 |
DG | +0.092 |
roots | +0.089 |
vae | +0.088 |
Neg logit contributions | |
axter | -0.141 |
�� | -0.139 |
ioch | -0.138 |
theless | -0.137 |
arnaev | -0.136 |
Token | 03 |
Token ID | 7643 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
axter | +0.034 |
�� | +0.034 |
ioch | +0.033 |
theless | +0.033 |
arnaev | +0.033 |
Neg logit contributions | |
FAQ | -0.032 |
Bowman | -0.024 |
DG | -0.023 |
roots | -0.022 |
vae | -0.022 |
Token | 30 |
Token ID | 1270 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
axter | +0.122 |
�� | +0.122 |
ioch | +0.120 |
theless | +0.120 |
arnaev | +0.118 |
Neg logit contributions | |
FAQ | -0.145 |
Bowman | -0.112 |
DG | -0.106 |
roots | -0.102 |
ollow | -0.102 |
Token | 333 |
Token ID | 23460 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
FAQ | +0.323 |
Bowman | +0.245 |
DG | +0.229 |
roots | +0.222 |
vae | +0.222 |
Neg logit contributions | |
axter | -0.318 |
�� | -0.314 |
ioch | -0.314 |
theless | -0.313 |
arnaev | -0.307 |
Token | 68 |
Token ID | 8257 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
FAQ | +2.155 |
Bowman | +1.755 |
DG | +1.631 |
vae | +1.617 |
ollow | +1.609 |
Neg logit contributions | |
ioch | -1.348 |
�� | -1.348 |
theless | -1.341 |
axter | -1.321 |
arnaev | -1.270 |
Token | 46 |
Token ID | 3510 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
FAQ | +0.901 |
Bowman | +0.712 |
DG | +0.660 |
vae | +0.649 |
atsu | +0.644 |
Neg logit contributions | |
ioch | -0.748 |
axter | -0.747 |
�� | -0.737 |
theless | -0.731 |
arnaev | -0.715 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
FAQ | +0.021 |
Bowman | +0.016 |
DG | +0.015 |
roots | +0.014 |
vae | +0.014 |
Neg logit contributions | |
axter | -0.019 |
�� | -0.019 |
ioch | -0.018 |
theless | -0.018 |
arnaev | -0.018 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
FAQ | +0.121 |
Bowman | +0.095 |
DG | +0.090 |
roots | +0.087 |
vae | +0.086 |
Neg logit contributions | |
axter | -0.093 |
�� | -0.092 |
ioch | -0.092 |
theless | -0.091 |
arnaev | -0.090 |
Token | ( |
Token ID | 7 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
FAQ | +0.034 |
Bowman | +0.026 |
DG | +0.024 |
roots | +0.024 |
ollow | +0.023 |
Neg logit contributions | |
axter | -0.032 |
�� | -0.032 |
ioch | -0.032 |
theless | -0.032 |
arnaev | -0.031 |
Token | Diane |
Token ID | 26542 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
FAQ | +0.214 |
Bowman | +0.156 |
DG | +0.145 |
roots | +0.140 |
ollow | +0.139 |
Neg logit contributions | |
axter | -0.253 |
�� | -0.250 |
theless | -0.249 |
ioch | -0.249 |
arnaev | -0.246 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
FAQ | +0.347 |
Bowman | +0.271 |
DG | +0.257 |
roots | +0.250 |
ollow | +0.249 |
Neg logit contributions | |
axter | -0.253 |
�� | -0.250 |
theless | -0.247 |
ioch | -0.247 |
arnaev | -0.244 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
FAQ | +0.696 |
Bowman | +0.548 |
DG | +0.524 |
roots | +0.508 |
ollow | +0.505 |
Neg logit contributions | |
axter | -0.491 |
�� | -0.483 |
theless | -0.480 |
ioch | -0.475 |
arnaev | -0.471 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
FAQ | +0.530 |
Bowman | +0.415 |
DG | +0.392 |
roots | +0.378 |
ollow | +0.377 |
Neg logit contributions | |
axter | -0.448 |
�� | -0.439 |
ioch | -0.436 |
theless | -0.435 |
arnaev | -0.430 |
Token | : |
Token ID | 25 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
FAQ | +0.781 |
Bowman | +0.628 |
DG | +0.594 |
ollow | +0.580 |
vae | +0.579 |
Neg logit contributions | |
axter | -0.499 |
theless | -0.486 |
ioch | -0.485 |
�� | -0.483 |
arnaev | -0.477 |
Token | ' |
Token ID | 705 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
FAQ | +0.643 |
Bowman | +0.488 |
DG | +0.462 |
iris | +0.451 |
vae | +0.451 |
Neg logit contributions | |
axter | -0.550 |
ioch | -0.540 |
theless | -0.540 |
�� | -0.537 |
arnaev | -0.533 |
Token | I |
Token ID | 40 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
FAQ | +1.873 |
Bowman | +1.447 |
DG | +1.385 |
vae | +1.357 |
ollow | +1.333 |
Neg logit contributions | |
axter | -1.638 |
theless | -1.600 |
ioch | -1.580 |
�� | -1.558 |
paren | -1.548 |
Token | fully |
Token ID | 3938 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
FAQ | +1.244 |
Bowman | +0.969 |
DG | +0.925 |
roots | +0.899 |
vae | +0.889 |
Neg logit contributions | |
axter | -0.983 |
theless | -0.962 |
ioch | -0.955 |
�� | -0.946 |
arnaev | -0.946 |
Token | expect |
Token ID | 1607 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
FAQ | +0.812 |
Bowman | +0.631 |
DG | +0.600 |
roots | +0.586 |
ollow | +0.581 |
Neg logit contributions | |
axter | -0.618 |
�� | -0.600 |
ioch | -0.600 |
theless | -0.596 |
arnaev | -0.589 |
Token | ' |
Token ID | 6 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
axter | +0.017 |
�� | +0.017 |
ioch | +0.017 |
theless | +0.017 |
arnaev | +0.016 |
Neg logit contributions | |
FAQ | -0.033 |
Bowman | -0.027 |
DG | -0.026 |
roots | -0.025 |
vae | -0.025 |
Token | fair |
Token ID | 3148 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
FAQ | +0.165 |
Bowman | +0.128 |
DG | +0.121 |
roots | +0.117 |
ollow | +0.117 |
Neg logit contributions | |
axter | -0.138 |
�� | -0.137 |
ioch | -0.135 |
theless | -0.135 |
arnaev | -0.133 |
Token | by |
Token ID | 416 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
axter | +0.193 |
�� | +0.191 |
ioch | +0.189 |
theless | +0.189 |
arnaev | +0.186 |
Neg logit contributions | |
FAQ | -0.219 |
Bowman | -0.169 |
DG | -0.159 |
roots | -0.154 |
ollow | -0.153 |
Token | Patrick |
Token ID | 9925 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
FAQ | +1.354 |
Bowman | +1.025 |
DG | +0.988 |
ollow | +0.955 |
vae | +0.954 |
Neg logit contributions | |
axter | -1.132 |
ioch | -1.111 |
�� | -1.097 |
theless | -1.080 |
paren | -1.067 |
Token | J |
Token ID | 449 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
FAQ | +0.828 |
Bowman | +0.639 |
DG | +0.611 |
Dems | +0.593 |
vae | +0.591 |
Neg logit contributions | |
axter | -0.629 |
ioch | -0.615 |
�� | -0.613 |
theless | -0.608 |
arnaev | -0.602 |
Token | . |
Token ID | 13 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
FAQ | +0.599 |
Bowman | +0.455 |
DG | +0.437 |
roots | +0.421 |
vae | +0.420 |
Neg logit contributions | |
axter | -0.522 |
ioch | -0.509 |
�� | -0.508 |
arnaev | -0.503 |
theless | -0.499 |
Token | Buchanan |
Token ID | 36358 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
FAQ | +0.637 |
Bowman | +0.511 |
DG | +0.489 |
vae | +0.480 |
roots | +0.478 |
Neg logit contributions | |
axter | -0.366 |
�� | -0.360 |
ioch | -0.358 |
theless | -0.355 |
arnaev | -0.351 |
Token | , |
Token ID | 11 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
FAQ | +1.109 |
Bowman | +0.863 |
DG | +0.811 |
roots | +0.805 |
vae | +0.796 |
Neg logit contributions | |
axter | -0.916 |
ioch | -0.897 |
�� | -0.873 |
theless | -0.872 |
arnaev | -0.867 |
Token | and |
Token ID | 290 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
FAQ | +1.857 |
Bowman | +1.460 |
DG | +1.361 |
roots | +1.360 |
vae | +1.344 |
Neg logit contributions | |
axter | -1.483 |
ioch | -1.460 |
�� | -1.430 |
arnaev | -1.421 |
paren | -1.393 |
Token | critical |
Token ID | 4688 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
FAQ | +0.193 |
Bowman | +0.159 |
DG | +0.152 |
roots | +0.149 |
vae | +0.148 |
Neg logit contributions | |
axter | -0.088 |
�� | -0.086 |
ioch | -0.086 |
theless | -0.084 |
arnaev | -0.084 |
Token | essays |
Token ID | 27126 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
FAQ | +1.089 |
Bowman | +0.793 |
DG | +0.745 |
vae | +0.738 |
roots | +0.728 |
Neg logit contributions | |
axter | -1.260 |
ioch | -1.238 |
theless | -1.226 |
arnaev | -1.215 |
�� | -1.211 |
Token | by |
Token ID | 416 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
FAQ | +0.191 |
Bowman | +0.148 |
DG | +0.140 |
roots | +0.136 |
vae | +0.135 |
Neg logit contributions | |
axter | -0.162 |
�� | -0.159 |
ioch | -0.159 |
theless | -0.158 |
arnaev | -0.156 |
Token | Scott |
Token ID | 4746 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
FAQ | +1.984 |
Bowman | +1.551 |
DG | +1.499 |
atsu | +1.472 |
ollow | +1.452 |
Neg logit contributions | |
axter | -1.242 |
ioch | -1.226 |
�� | -1.173 |
paren | -1.152 |
theless | -1.148 |
Token | Daily |
Token ID | 6714 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
axter | +0.188 |
�� | +0.187 |
ioch | +0.185 |
theless | +0.184 |
arnaev | +0.181 |
Neg logit contributions | |
FAQ | -0.234 |
Bowman | -0.183 |
DG | -0.173 |
roots | -0.168 |
Dems | -0.166 |
Token | Edition |
Token ID | 5061 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
FAQ | +0.458 |
Bowman | +0.365 |
DG | +0.346 |
roots | +0.338 |
vae | +0.338 |
Neg logit contributions | |
axter | -0.301 |
�� | -0.297 |
ioch | -0.295 |
theless | -0.294 |
arnaev | -0.288 |
Token | by |
Token ID | 416 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
axter | +0.482 |
�� | +0.481 |
ioch | +0.474 |
theless | +0.473 |
arnaev | +0.467 |
Neg logit contributions | |
FAQ | -0.534 |
Bowman | -0.412 |
DG | -0.387 |
roots | -0.374 |
Dems | -0.371 |
Token | email |
Token ID | 3053 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
FAQ | +0.517 |
Bowman | +0.411 |
DG | +0.391 |
vae | +0.383 |
roots | +0.381 |
Neg logit contributions | |
axter | -0.324 |
�� | -0.318 |
ioch | -0.315 |
theless | -0.314 |
arnaev | -0.308 |
Token | and |
Token ID | 290 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
FAQ | +0.073 |
Bowman | +0.056 |
DG | +0.052 |
roots | +0.051 |
vae | +0.050 |
Neg logit contributions | |
axter | -0.065 |
�� | -0.065 |
ioch | -0.064 |
theless | -0.064 |
arnaev | -0.063 |
Token | never |
Token ID | 1239 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
FAQ | +0.844 |
Bowman | +0.669 |
DG | +0.638 |
roots | +0.623 |
vae | +0.622 |
Neg logit contributions | |
axter | -0.561 |
�� | -0.557 |
ioch | -0.547 |
theless | -0.547 |
arnaev | -0.534 |
Token | miss |
Token ID | 2051 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
FAQ | +1.761 |
Bowman | +1.303 |
DG | +1.255 |
Bounty | +1.234 |
vae | +1.221 |
Neg logit contributions | |
axter | -1.605 |
theless | -1.596 |
ioch | -1.557 |
�� | -1.530 |
paren | -1.529 |
Token | our |
Token ID | 674 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
FAQ | +0.730 |
Bowman | +0.551 |
DG | +0.520 |
roots | +0.509 |
vae | +0.507 |
Neg logit contributions | |
axter | -0.659 |
ioch | -0.651 |
�� | -0.650 |
theless | -0.646 |
arnaev | -0.637 |
Token | top |
Token ID | 1353 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
FAQ | +0.719 |
Bowman | +0.567 |
DG | +0.532 |
vae | +0.524 |
roots | +0.522 |
Neg logit contributions | |
axter | -0.538 |
�� | -0.532 |
ioch | -0.527 |
theless | -0.524 |
arnaev | -0.516 |
Token | stories |
Token ID | 3923 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
FAQ | +0.095 |
Bowman | +0.071 |
DG | +0.066 |
roots | +0.064 |
vae | +0.063 |
Neg logit contributions | |
axter | -0.103 |
�� | -0.102 |
ioch | -0.101 |
theless | -0.100 |
arnaev | -0.099 |
Token | Free |
Token ID | 3232 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
FAQ | +0.486 |
Bowman | +0.381 |
DG | +0.361 |
roots | +0.352 |
vae | +0.351 |
Neg logit contributions | |
axter | -0.362 |
�� | -0.357 |
ioch | -0.354 |
theless | -0.352 |
arnaev | -0.351 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
FAQ | +0.934 |
Bowman | +0.724 |
DG | +0.682 |
ollow | +0.667 |
roots | +0.666 |
Neg logit contributions | |
axter | -0.754 |
�� | -0.742 |
ioch | -0.733 |
theless | -0.727 |
arnaev | -0.721 |
Token | Sum |
Token ID | 5060 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
FAQ | +0.993 |
Bowman | +0.788 |
DG | +0.740 |
roots | +0.724 |
iris | +0.720 |
Neg logit contributions | |
axter | -0.746 |
�� | -0.738 |
ioch | -0.736 |
theless | -0.722 |
arnaev | -0.721 |
Token | ma |
Token ID | 2611 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
FAQ | +0.037 |
Bowman | +0.032 |
DG | +0.031 |
roots | +0.030 |
ollow | +0.030 |
Neg logit contributions | |
axter | -0.010 |
�� | -0.010 |
ioch | -0.010 |
theless | -0.010 |
arnaev | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
FAQ | +0.315 |
Bowman | +0.243 |
DG | +0.229 |
roots | +0.224 |
vae | +0.222 |
Neg logit contributions | |
axter | -0.273 |
�� | -0.270 |
theless | -0.269 |
ioch | -0.269 |
arnaev | -0.263 |
Token | Bible |
Token ID | 9111 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
FAQ | +0.413 |
Bowman | +0.311 |
DG | +0.293 |
roots | +0.284 |
vae | +0.281 |
Neg logit contributions | |
axter | -0.422 |
�� | -0.422 |
ioch | -0.419 |
theless | -0.414 |
arnaev | -0.411 |
Token | and |
Token ID | 290 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
FAQ | +1.211 |
Bowman | +0.945 |
DG | +0.898 |
ollow | +0.869 |
vae | +0.869 |
Neg logit contributions | |
axter | -0.988 |
�� | -0.967 |
ioch | -0.963 |
theless | -0.958 |
paren | -0.932 |
Token | more |
Token ID | 517 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
FAQ | +1.762 |
Bowman | +1.364 |
DG | +1.308 |
vae | +1.283 |
roots | +1.281 |
Neg logit contributions | |
axter | -1.486 |
�� | -1.474 |
ioch | -1.469 |
theless | -1.449 |
arnaev | -1.434 |
Token | � |
Token ID | 1587 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
FAQ | +0.566 |
Bowman | +0.444 |
DG | +0.422 |
roots | +0.416 |
vae | +0.413 |
Neg logit contributions | |
axter | -0.401 |
ioch | -0.394 |
�� | -0.393 |
theless | -0.392 |
arnaev | -0.384 |
Token | � |
Token ID | 245 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
FAQ | +0.166 |
Bowman | +0.124 |
DG | +0.116 |
roots | +0.112 |
Dems | +0.111 |
Neg logit contributions | |
axter | -0.178 |
�� | -0.177 |
ioch | -0.175 |
theless | -0.174 |
arnaev | -0.172 |
Token | all |
Token ID | 477 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
�� | +0.559 |
axter | +0.558 |
ioch | +0.548 |
theless | +0.544 |
arnaev | +0.538 |
Neg logit contributions | |
FAQ | -0.613 |
Bowman | -0.471 |
DG | -0.443 |
roots | -0.429 |
vae | -0.425 |
Token | for |
Token ID | 329 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
FAQ | +0.676 |
Bowman | +0.522 |
DG | +0.486 |
vae | +0.478 |
iris | +0.478 |
Neg logit contributions | |
axter | -0.593 |
ioch | -0.583 |
theless | -0.582 |
�� | -0.577 |
arnaev | -0.570 |
Token | 59 |
Token ID | 3270 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
FAQ | +0.130 |
Bowman | +0.102 |
DG | +0.096 |
roots | +0.093 |
vae | +0.093 |
Neg logit contributions | |
axter | -0.103 |
�� | -0.102 |
ioch | -0.101 |
theless | -0.101 |
arnaev | -0.099 |
Token | , |
Token ID | 11 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
axter | +0.107 |
�� | +0.106 |
ioch | +0.105 |
theless | +0.105 |
arnaev | +0.103 |
Neg logit contributions | |
FAQ | -0.119 |
Bowman | -0.091 |
DG | -0.086 |
roots | -0.083 |
ollow | -0.083 |
Token | go |
Token ID | 467 |
Feature activation | -3.23e-04 |
Pos logit contributions | |
FAQ | +0.019 |
Bowman | +0.015 |
DG | +0.014 |
roots | +0.014 |
ollow | +0.014 |
Neg logit contributions | |
axter | -0.016 |
�� | -0.016 |
ioch | -0.016 |
theless | -0.016 |
arnaev | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
axter | +0.000 |
�� | +0.000 |
ioch | +0.000 |
theless | +0.000 |
arnaev | +0.000 |
Neg logit contributions | |
FAQ | -0.000 |
Bowman | -0.000 |
DG | -0.000 |
roots | -0.000 |
ollow | -0.000 |
Token | book |
Token ID | 1492 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
FAQ | +0.197 |
Bowman | +0.148 |
DG | +0.138 |
roots | +0.134 |
vae | +0.133 |
Neg logit contributions | |
axter | -0.201 |
�� | -0.199 |
ioch | -0.198 |
theless | -0.197 |
arnaev | -0.194 |
Token | shop |
Token ID | 24643 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
FAQ | +0.474 |
Bowman | +0.364 |
DG | +0.341 |
roots | +0.330 |
vae | +0.329 |
Neg logit contributions | |
axter | -0.447 |
�� | -0.442 |
ioch | -0.439 |
theless | -0.439 |
arnaev | -0.430 |
Token | . |
Token ID | 13 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
FAQ | +1.814 |
Bowman | +1.407 |
roots | +1.317 |
vae | +1.315 |
DG | +1.304 |
Neg logit contributions | |
axter | -1.468 |
�� | -1.412 |
ioch | -1.411 |
theless | -1.398 |
arnaev | -1.382 |
Token | the |
Token ID | 1169 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
FAQ | +0.301 |
Bowman | +0.230 |
DG | +0.215 |
vae | +0.208 |
roots | +0.207 |
Neg logit contributions | |
axter | -0.285 |
�� | -0.282 |
ioch | -0.282 |
theless | -0.281 |
arnaev | -0.275 |
Token | guard |
Token ID | 14864 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
axter | +0.151 |
�� | +0.150 |
ioch | +0.148 |
theless | +0.147 |
arnaev | +0.145 |
Neg logit contributions | |
FAQ | -0.239 |
Bowman | -0.191 |
DG | -0.182 |
roots | -0.178 |
ollow | -0.176 |
Token | ian |
Token ID | 666 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
FAQ | +0.260 |
Bowman | +0.202 |
DG | +0.189 |
roots | +0.184 |
vae | +0.183 |
Neg logit contributions | |
axter | -0.220 |
�� | -0.217 |
ioch | -0.217 |
theless | -0.215 |
arnaev | -0.213 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
FAQ | +0.274 |
Bowman | +0.211 |
DG | +0.198 |
roots | +0.192 |
vae | +0.191 |
Neg logit contributions | |
axter | -0.246 |
�� | -0.243 |
ioch | -0.243 |
theless | -0.241 |
arnaev | -0.238 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
FAQ | +0.193 |
Bowman | +0.148 |
DG | +0.140 |
roots | +0.135 |
ollow | +0.135 |
Neg logit contributions | |
axter | -0.172 |
�� | -0.169 |
ioch | -0.168 |
theless | -0.168 |
arnaev | -0.166 |
Token | great |
Token ID | 1049 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
�� | +1.292 |
ioch | +1.259 |
axter | +1.242 |
theless | +1.237 |
arnaev | +1.217 |
Neg logit contributions | |
FAQ | -1.184 |
Bowman | -0.893 |
DG | -0.840 |
roots | -0.806 |
Dems | -0.799 |
Token | libertarian |
Token ID | 19466 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
axter | +0.221 |
�� | +0.221 |
ioch | +0.217 |
theless | +0.217 |
arnaev | +0.214 |
Neg logit contributions | |
FAQ | -0.261 |
Bowman | -0.203 |
DG | -0.191 |
roots | -0.185 |
Dems | -0.183 |
Token | thinker |
Token ID | 45206 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
FAQ | +0.237 |
Bowman | +0.185 |
DG | +0.176 |
roots | +0.171 |
ollow | +0.170 |
Neg logit contributions | |
axter | -0.180 |
�� | -0.177 |
ioch | -0.176 |
theless | -0.176 |
arnaev | -0.173 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
FAQ | +0.061 |
Bowman | +0.047 |
DG | +0.044 |
roots | +0.043 |
vae | +0.042 |
Neg logit contributions | |
axter | -0.053 |
�� | -0.053 |
ioch | -0.052 |
theless | -0.052 |
arnaev | -0.051 |
Token | here |
Token ID | 994 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
FAQ | +1.448 |
Bowman | +1.142 |
DG | +1.091 |
roots | +1.072 |
atsu | +1.069 |
Neg logit contributions | |
axter | -0.991 |
ioch | -0.963 |
arnaev | -0.954 |
theless | -0.948 |
�� | -0.943 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
FAQ | +1.801 |
Bowman | +1.399 |
DG | +1.355 |
roots | +1.313 |
Bounty | +1.311 |
Neg logit contributions | |
axter | -1.432 |
ioch | -1.404 |
theless | -1.379 |
arnaev | -1.364 |
�� | -1.356 |
Token |
|
Token ID | 198 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
FAQ | +0.876 |
Bowman | +0.679 |
DG | +0.649 |
roots | +0.632 |
atsu | +0.630 |
Neg logit contributions | |
axter | -0.703 |
ioch | -0.688 |
�� | -0.685 |
arnaev | -0.682 |
theless | -0.681 |
Token |
|
Token ID | 198 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
axter | +0.049 |
�� | +0.048 |
ioch | +0.048 |
theless | +0.048 |
arnaev | +0.047 |
Neg logit contributions | |
FAQ | -0.057 |
Bowman | -0.044 |
DG | -0.041 |
roots | -0.040 |
ollow | -0.040 |
Token | Read |
Token ID | 5569 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
�� | +0.275 |
axter | +0.274 |
ioch | +0.270 |
theless | +0.269 |
arnaev | +0.265 |
Neg logit contributions | |
FAQ | -0.345 |
Bowman | -0.268 |
DG | -0.253 |
roots | -0.246 |
ollow | -0.245 |
Token | more |
Token ID | 517 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
FAQ | +0.077 |
Bowman | +0.059 |
DG | +0.055 |
roots | +0.053 |
vae | +0.053 |
Neg logit contributions | |
axter | -0.074 |
�� | -0.073 |
ioch | -0.073 |
theless | -0.073 |
arnaev | -0.072 |
Token | y |
Token ID | 88 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
axter | +0.135 |
�� | +0.134 |
ioch | +0.132 |
theless | +0.132 |
arnaev | +0.130 |
Neg logit contributions | |
FAQ | -0.157 |
Bowman | -0.121 |
DG | -0.114 |
roots | -0.111 |
ollow | -0.110 |
Token | K |
Token ID | 509 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
FAQ | +1.733 |
Bowman | +1.342 |
iris | +1.302 |
DG | +1.298 |
ollow | +1.285 |
Neg logit contributions | |
axter | -1.107 |
�� | -1.081 |
ioch | -1.055 |
theless | -1.047 |
arnaev | -1.025 |
Token | aling |
Token ID | 4272 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
axter | +0.041 |
�� | +0.041 |
ioch | +0.040 |
theless | +0.040 |
arnaev | +0.039 |
Neg logit contributions | |
FAQ | -0.087 |
Bowman | -0.071 |
DG | -0.068 |
roots | -0.067 |
ollow | -0.067 |
Token | The |
Token ID | 383 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
FAQ | +0.108 |
Bowman | +0.083 |
DG | +0.078 |
roots | +0.076 |
ollow | +0.075 |
Neg logit contributions | |
axter | -0.093 |
�� | -0.092 |
ioch | -0.091 |
theless | -0.091 |
arnaev | -0.090 |
Token | Mind |
Token ID | 10175 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
axter | +0.255 |
�� | +0.254 |
ioch | +0.250 |
theless | +0.250 |
arnaev | +0.246 |
Neg logit contributions | |
FAQ | -0.293 |
Bowman | -0.227 |
DG | -0.213 |
roots | -0.206 |
Dems | -0.205 |
Token | y |
Token ID | 88 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
axter | +0.120 |
�� | +0.119 |
ioch | +0.118 |
theless | +0.118 |
arnaev | +0.116 |
Neg logit contributions | |
FAQ | -0.133 |
Bowman | -0.102 |
DG | -0.096 |
roots | -0.093 |
ollow | -0.092 |
Token | Project |
Token ID | 4935 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
FAQ | +1.195 |
Bowman | +0.753 |
DG | +0.717 |
iris | +0.714 |
ollow | +0.686 |
Neg logit contributions | |
axter | -2.044 |
�� | -1.998 |
ioch | -1.986 |
theless | -1.969 |
arnaev | -1.963 |
Token | Fox |
Token ID | 5426 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
axter | +0.086 |
�� | +0.086 |
ioch | +0.085 |
theless | +0.085 |
arnaev | +0.083 |
Neg logit contributions | |
FAQ | -0.103 |
Bowman | -0.080 |
DG | -0.076 |
roots | -0.073 |
ollow | -0.073 |
Token | Julia |
Token ID | 22300 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
axter | +0.188 |
�� | +0.187 |
ioch | +0.185 |
theless | +0.184 |
arnaev | +0.182 |
Neg logit contributions | |
FAQ | -0.217 |
Bowman | -0.168 |
DG | -0.158 |
roots | -0.153 |
ollow | -0.152 |
Token | Louis |
Token ID | 5593 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
axter | +0.811 |
�� | +0.811 |
ioch | +0.802 |
theless | +0.796 |
arnaev | +0.790 |
Neg logit contributions | |
FAQ | -0.861 |
Bowman | -0.667 |
DG | -0.624 |
Dems | -0.599 |
Bounty | -0.598 |
Token | - |
Token ID | 12 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
FAQ | +0.017 |
Bowman | +0.013 |
DG | +0.012 |
roots | +0.012 |
vae | +0.011 |
Neg logit contributions | |
axter | -0.017 |
�� | -0.017 |
ioch | -0.017 |
theless | -0.017 |
arnaev | -0.017 |
Token | Obama |
Token ID | 2486 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
FAQ | +0.487 |
Bowman | +0.366 |
DG | +0.342 |
roots | +0.333 |
ollow | +0.329 |
Neg logit contributions | |
axter | -0.488 |
�� | -0.480 |
ioch | -0.479 |
theless | -0.477 |
arnaev | -0.472 |
Token | Barack |
Token ID | 8732 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
axter | +0.008 |
�� | +0.008 |
ioch | +0.008 |
theless | +0.008 |
arnaev | +0.008 |
Neg logit contributions | |
FAQ | -0.009 |
Bowman | -0.007 |
DG | -0.007 |
roots | -0.007 |
ollow | -0.007 |
Token | Hussein |
Token ID | 22983 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
FAQ | +0.458 |
Bowman | +0.345 |
DG | +0.323 |
roots | +0.315 |
vae | +0.314 |
Neg logit contributions | |
axter | -0.447 |
�� | -0.438 |
theless | -0.437 |
ioch | -0.437 |
arnaev | -0.430 |
Token | Obama |
Token ID | 2486 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
FAQ | +0.441 |
Bowman | +0.332 |
DG | +0.311 |
roots | +0.300 |
ollow | +0.298 |
Neg logit contributions | |
axter | -0.441 |
�� | -0.431 |
ioch | -0.431 |
theless | -0.430 |
arnaev | -0.426 |
Token | With |
Token ID | 3152 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
FAQ | +0.560 |
Bowman | +0.437 |
DG | +0.411 |
roots | +0.397 |
vae | +0.396 |
Neg logit contributions | |
axter | -0.483 |
ioch | -0.472 |
�� | -0.471 |
theless | -0.467 |
arnaev | -0.462 |
Token | low |
Token ID | 1877 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
axter | +0.043 |
�� | +0.042 |
ioch | +0.042 |
theless | +0.042 |
arnaev | +0.041 |
Neg logit contributions | |
FAQ | -0.055 |
Bowman | -0.043 |
DG | -0.041 |
roots | -0.040 |
vae | -0.039 |
Token | birth |
Token ID | 4082 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
FAQ | +1.687 |
Bowman | +1.280 |
DG | +1.189 |
ollow | +1.158 |
orthy | +1.149 |
Neg logit contributions | |
axter | -1.565 |
ioch | -1.521 |
�� | -1.511 |
paren | -1.498 |
arnaev | -1.498 |
Token | rate |
Token ID | 2494 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
FAQ | +0.174 |
Bowman | +0.140 |
DG | +0.133 |
roots | +0.130 |
ollow | +0.130 |
Neg logit contributions | |
axter | -0.106 |
�� | -0.105 |
ioch | -0.103 |
theless | -0.103 |
arnaev | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
FAQ | +1.001 |
Bowman | +0.775 |
DG | +0.735 |
roots | +0.718 |
vae | +0.708 |
Neg logit contributions | |
axter | -0.822 |
�� | -0.804 |
theless | -0.800 |
ioch | -0.797 |
arnaev | -0.786 |
Token | America |
Token ID | 2253 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
FAQ | +1.141 |
Bowman | +0.895 |
DG | +0.847 |
roots | +0.828 |
orthy | +0.825 |
Neg logit contributions | |
axter | -0.839 |
�� | -0.828 |
theless | -0.820 |
ioch | -0.818 |
arnaev | -0.805 |
Token | needs |
Token ID | 2476 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
FAQ | +0.665 |
Bowman | +0.507 |
DG | +0.474 |
vae | +0.458 |
atsu | +0.456 |
Neg logit contributions | |
axter | -0.652 |
theless | -0.641 |
ioch | -0.637 |
�� | -0.636 |
arnaev | -0.631 |
Token | Donald |
Token ID | 3759 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
axter | +0.165 |
�� | +0.164 |
ioch | +0.161 |
theless | +0.160 |
arnaev | +0.156 |
Neg logit contributions | |
FAQ | -0.375 |
Bowman | -0.309 |
DG | -0.297 |
roots | -0.290 |
Dems | -0.288 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
axter | +0.120 |
�� | +0.119 |
ioch | +0.118 |
theless | +0.117 |
arnaev | +0.115 |
Neg logit contributions | |
FAQ | -0.223 |
Bowman | -0.182 |
DG | -0.173 |
roots | -0.169 |
ollow | -0.168 |
Token | Donald |
Token ID | 3759 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
axter | +0.257 |
�� | +0.254 |
ioch | +0.250 |
theless | +0.249 |
arnaev | +0.243 |
Neg logit contributions | |
FAQ | -0.576 |
Bowman | -0.475 |
DG | -0.455 |
roots | -0.444 |
Dems | -0.443 |
Token | John |
Token ID | 1757 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
axter | +0.413 |
�� | +0.412 |
ioch | +0.405 |
theless | +0.404 |
arnaev | +0.398 |
Neg logit contributions | |
FAQ | -0.475 |
Bowman | -0.368 |
DG | -0.347 |
roots | -0.335 |
Dems | -0.334 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
FAQ | +0.272 |
Bowman | +0.222 |
DG | +0.212 |
roots | +0.207 |
vae | +0.206 |
Neg logit contributions | |
axter | -0.141 |
�� | -0.139 |
ioch | -0.137 |
theless | -0.137 |
arnaev | -0.134 |
Token | House |
Token ID | 18102 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
FAQ | +0.086 |
Bowman | +0.066 |
DG | +0.062 |
roots | +0.060 |
vae | +0.060 |
Neg logit contributions | |
axter | -0.079 |
�� | -0.078 |
ioch | -0.078 |
theless | -0.077 |
arnaev | -0.076 |
Token | committee |
Token ID | 5583 |
Feature activation | +9.09e-03 |
Pos logit contributions | |
FAQ | +1.602 |
Bowman | +1.203 |
DG | +1.121 |
roots | +1.105 |
vae | +1.092 |
Neg logit contributions | |
axter | -1.643 |
ioch | -1.596 |
theless | -1.572 |
arnaev | -1.565 |
�� | -1.564 |
Token | believes |
Token ID | 5804 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
FAQ | +0.005 |
Bowman | +0.003 |
DG | +0.003 |
roots | +0.003 |
vae | +0.003 |
Neg logit contributions | |
axter | -0.009 |
�� | -0.009 |
ioch | -0.008 |
theless | -0.008 |
arnaev | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
FAQ | +0.445 |
Bowman | +0.352 |
DG | +0.334 |
vae | +0.327 |
roots | +0.326 |
Neg logit contributions | |
axter | -0.297 |
�� | -0.294 |
ioch | -0.293 |
theless | -0.288 |
arnaev | -0.286 |
Token | has |
Token ID | 468 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
FAQ | +0.355 |
Bowman | +0.279 |
DG | +0.265 |
roots | +0.258 |
vae | +0.258 |
Neg logit contributions | |
axter | -0.252 |
�� | -0.250 |
ioch | -0.249 |
theless | -0.247 |
arnaev | -0.244 |
Token | evidence |
Token ID | 2370 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
FAQ | +0.529 |
Bowman | +0.429 |
DG | +0.410 |
vae | +0.401 |
roots | +0.400 |
Neg logit contributions | |
axter | -0.276 |
�� | -0.272 |
ioch | -0.272 |
theless | -0.269 |
arnaev | -0.265 |
Token | Buchanan |
Token ID | 36358 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
FAQ | +0.637 |
Bowman | +0.511 |
DG | +0.489 |
vae | +0.480 |
roots | +0.478 |
Neg logit contributions | |
axter | -0.366 |
�� | -0.360 |
ioch | -0.358 |
theless | -0.355 |
arnaev | -0.351 |
Token | , |
Token ID | 11 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
FAQ | +1.109 |
Bowman | +0.863 |
DG | +0.811 |
roots | +0.805 |
vae | +0.796 |
Neg logit contributions | |
axter | -0.916 |
ioch | -0.897 |
�� | -0.873 |
theless | -0.872 |
arnaev | -0.867 |
Token | and |
Token ID | 290 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
FAQ | +1.857 |
Bowman | +1.460 |
DG | +1.361 |
roots | +1.360 |
vae | +1.344 |
Neg logit contributions | |
axter | -1.483 |
ioch | -1.460 |
�� | -1.430 |
arnaev | -1.421 |
paren | -1.393 |
Token | critical |
Token ID | 4688 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
FAQ | +0.193 |
Bowman | +0.159 |
DG | +0.152 |
roots | +0.149 |
vae | +0.148 |
Neg logit contributions | |
axter | -0.088 |
�� | -0.086 |
ioch | -0.086 |
theless | -0.084 |
arnaev | -0.084 |
Token | essays |
Token ID | 27126 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
FAQ | +1.089 |
Bowman | +0.793 |
DG | +0.745 |
vae | +0.738 |
roots | +0.728 |
Neg logit contributions | |
axter | -1.260 |
ioch | -1.238 |
theless | -1.226 |
arnaev | -1.215 |
�� | -1.211 |
Token | by |
Token ID | 416 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
FAQ | +0.191 |
Bowman | +0.148 |
DG | +0.140 |
roots | +0.136 |
vae | +0.135 |
Neg logit contributions | |
axter | -0.162 |
�� | -0.159 |
ioch | -0.159 |
theless | -0.158 |
arnaev | -0.156 |
Token | Scott |
Token ID | 4746 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
FAQ | +1.984 |
Bowman | +1.551 |
DG | +1.499 |
atsu | +1.472 |
ollow | +1.452 |
Neg logit contributions | |
axter | -1.242 |
ioch | -1.226 |
�� | -1.173 |
paren | -1.152 |
theless | -1.148 |
Token | Ric |
Token ID | 15868 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
FAQ | +0.383 |
Bowman | +0.276 |
DG | +0.258 |
roots | +0.250 |
vae | +0.249 |
Neg logit contributions | |
axter | -0.459 |
�� | -0.452 |
ioch | -0.452 |
theless | -0.445 |
arnaev | -0.442 |
Token | her |
Token ID | 372 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
FAQ | +1.139 |
Bowman | +0.893 |
DG | +0.856 |
Bounty | +0.827 |
Dems | +0.825 |
Neg logit contributions | |
axter | -0.796 |
ioch | -0.783 |
arnaev | -0.765 |
�� | -0.764 |
theless | -0.753 |
Token | t |
Token ID | 83 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
axter | +0.047 |
�� | +0.046 |
ioch | +0.046 |
theless | +0.046 |
arnaev | +0.045 |
Neg logit contributions | |
FAQ | -0.034 |
Bowman | -0.024 |
DG | -0.022 |
roots | -0.021 |
vae | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
FAQ | +0.106 |
Bowman | +0.081 |
DG | +0.076 |
roots | +0.074 |
Dems | +0.073 |
Neg logit contributions | |
axter | -0.095 |
�� | -0.094 |
ioch | -0.093 |
theless | -0.093 |
arnaev | -0.092 |
Token | gest |
Token ID | 3495 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
FAQ | +0.201 |
Bowman | +0.152 |
DG | +0.142 |
roots | +0.138 |
ollow | +0.137 |
Neg logit contributions | |
axter | -0.198 |
�� | -0.195 |
ioch | -0.195 |
theless | -0.194 |
arnaev | -0.192 |
Token | a |
Token ID | 257 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
axter | +0.235 |
�� | +0.233 |
ioch | +0.231 |
theless | +0.230 |
arnaev | +0.227 |
Neg logit contributions | |
FAQ | -0.232 |
Bowman | -0.175 |
DG | -0.164 |
roots | -0.158 |
Dems | -0.157 |
Token | -- |
Token ID | 438 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
FAQ | +0.221 |
Bowman | +0.166 |
DG | +0.156 |
roots | +0.150 |
ollow | +0.149 |
Neg logit contributions | |
axter | -0.228 |
�� | -0.225 |
ioch | -0.225 |
theless | -0.223 |
arnaev | -0.221 |
Token | holes |
Token ID | 28439 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
axter | +0.379 |
�� | +0.379 |
ioch | +0.371 |
theless | +0.369 |
arnaev | +0.365 |
Neg logit contributions | |
FAQ | -0.599 |
Bowman | -0.480 |
DG | -0.455 |
roots | -0.445 |
Dems | -0.444 |
Token | in |
Token ID | 287 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
axter | +0.376 |
�� | +0.375 |
theless | +0.368 |
ioch | +0.366 |
arnaev | +0.359 |
Neg logit contributions | |
FAQ | -0.693 |
Bowman | -0.567 |
DG | -0.539 |
Dems | -0.527 |
roots | -0.527 |
Token | American |
Token ID | 1605 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
FAQ | +0.597 |
Bowman | +0.453 |
DG | +0.427 |
roots | +0.412 |
ollow | +0.410 |
Neg logit contributions | |
axter | -0.539 |
ioch | -0.534 |
�� | -0.533 |
theless | -0.526 |
arnaev | -0.522 |
Token | politics |
Token ID | 4819 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
FAQ | +1.675 |
Bowman | +1.281 |
DG | +1.215 |
ollow | +1.168 |
iris | +1.162 |
Neg logit contributions | |
axter | -1.527 |
ioch | -1.520 |
theless | -1.464 |
�� | -1.454 |
arnaev | -1.446 |
Token | ' |
Token ID | 6 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
axter | +0.326 |
�� | +0.325 |
theless | +0.319 |
ioch | +0.317 |
arnaev | +0.309 |
Neg logit contributions | |
FAQ | -0.601 |
Bowman | -0.489 |
DG | -0.466 |
Dems | -0.456 |
roots | -0.455 |
Token | MORE |
Token ID | 12011 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
axter | +1.095 |
�� | +1.089 |
theless | +1.074 |
ioch | +1.074 |
arnaev | +1.049 |
Neg logit contributions | |
FAQ | -1.008 |
Bowman | -0.748 |
DG | -0.690 |
Dems | -0.685 |
roots | -0.677 |
Token | completed |
Token ID | 5668 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
axter | +0.099 |
�� | +0.098 |
ioch | +0.097 |
theless | +0.097 |
arnaev | +0.096 |
Neg logit contributions | |
FAQ | -0.113 |
Bowman | -0.087 |
DG | -0.082 |
roots | -0.079 |
ollow | -0.079 |
Token | a |
Token ID | 257 |
Feature activation | -1.24e-03 |
Pos logit contributions | |
axter | +0.059 |
�� | +0.059 |
ioch | +0.058 |
theless | +0.058 |
arnaev | +0.057 |
Neg logit contributions | |
FAQ | -0.074 |
Bowman | -0.058 |
DG | -0.055 |
roots | -0.053 |
ollow | -0.053 |
Token | Policy |
Token ID | 7820 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
FAQ | +0.121 |
Bowman | +0.095 |
DG | +0.089 |
roots | +0.087 |
vae | +0.086 |
Neg logit contributions | |
axter | -0.096 |
�� | -0.095 |
ioch | -0.094 |
theless | -0.093 |
arnaev | -0.092 |
Token | or |
Token ID | 393 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
FAQ | +0.292 |
Bowman | +0.226 |
DG | +0.212 |
roots | +0.207 |
vae | +0.206 |
Neg logit contributions | |
axter | -0.252 |
�� | -0.248 |
ioch | -0.248 |
theless | -0.245 |
arnaev | -0.243 |
Token | the |
Token ID | 262 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
FAQ | +0.181 |
Bowman | +0.138 |
DG | +0.130 |
roots | +0.127 |
ollow | +0.126 |
Neg logit contributions | |
axter | -0.159 |
�� | -0.157 |
ioch | -0.157 |
theless | -0.155 |
arnaev | -0.153 |
Token | London |
Token ID | 3576 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
axter | +0.016 |
�� | +0.016 |
ioch | +0.015 |
theless | +0.015 |
arnaev | +0.015 |
Neg logit contributions | |
FAQ | -0.016 |
Bowman | -0.012 |
DG | -0.012 |
roots | -0.011 |
ollow | -0.011 |
Token | School |
Token ID | 3961 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
axter | +0.201 |
�� | +0.200 |
ioch | +0.197 |
theless | +0.197 |
arnaev | +0.193 |
Neg logit contributions | |
FAQ | -0.251 |
Bowman | -0.196 |
DG | -0.186 |
roots | -0.180 |
Dems | -0.178 |
Token | of |
Token ID | 286 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
axter | +0.682 |
�� | +0.681 |
theless | +0.673 |
ioch | +0.669 |
arnaev | +0.659 |
Neg logit contributions | |
FAQ | -0.721 |
Bowman | -0.548 |
DG | -0.520 |
roots | -0.499 |
Dems | -0.498 |
Token | Economics |
Token ID | 18963 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
theless | +1.822 |
�� | +1.794 |
axter | +1.782 |
arnaev | +1.753 |
ioch | +1.745 |
Neg logit contributions | |
FAQ | -1.701 |
Bowman | -1.296 |
DG | -1.245 |
Dems | -1.189 |
roots | -1.179 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
axter | +0.664 |
�� | +0.660 |
theless | +0.655 |
ioch | +0.648 |
arnaev | +0.639 |
Neg logit contributions | |
FAQ | -0.689 |
Bowman | -0.520 |
DG | -0.495 |
roots | -0.474 |
Bounty | -0.470 |
Token |
|
Token ID | 198 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
axter | +0.178 |
�� | +0.177 |
ioch | +0.175 |
theless | +0.174 |
arnaev | +0.172 |
Neg logit contributions | |
FAQ | -0.202 |
Bowman | -0.156 |
DG | -0.147 |
roots | -0.142 |
ollow | -0.141 |
Token |
|
Token ID | 198 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
axter | +0.063 |
�� | +0.062 |
ioch | +0.062 |
theless | +0.061 |
arnaev | +0.061 |
Neg logit contributions | |
FAQ | -0.073 |
Bowman | -0.056 |
DG | -0.053 |
roots | -0.052 |
ollow | -0.051 |
Token | ________________________________ |
Token ID | 10221 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
FAQ | +0.430 |
Bowman | +0.336 |
DG | +0.317 |
roots | +0.307 |
Dems | +0.306 |
Neg logit contributions | |
axter | -0.361 |
�� | -0.354 |
ioch | -0.353 |
theless | -0.349 |
arnaev | -0.347 |
Token | File |
Token ID | 9220 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
FAQ | +0.079 |
Bowman | +0.061 |
DG | +0.057 |
roots | +0.055 |
ollow | +0.055 |
Neg logit contributions | |
axter | -0.068 |
�� | -0.068 |
ioch | -0.067 |
theless | -0.067 |
arnaev | -0.066 |
Token | ) |
Token ID | 8 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
FAQ | +0.350 |
Bowman | +0.269 |
DG | +0.252 |
roots | +0.246 |
ollow | +0.244 |
Neg logit contributions | |
axter | -0.309 |
�� | -0.306 |
ioch | -0.303 |
theless | -0.301 |
arnaev | -0.298 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
axter | +0.158 |
�� | +0.157 |
ioch | +0.155 |
theless | +0.155 |
arnaev | +0.152 |
Neg logit contributions | |
FAQ | -0.170 |
Bowman | -0.130 |
DG | -0.122 |
roots | -0.118 |
ollow | -0.117 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
axter | +0.011 |
�� | +0.011 |
ioch | +0.011 |
theless | +0.011 |
arnaev | +0.011 |
Neg logit contributions | |
FAQ | -0.013 |
Bowman | -0.010 |
DG | -0.009 |
roots | -0.009 |
vae | -0.009 |
Token | L |
Token ID | 43 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
axter | +0.105 |
�� | +0.104 |
ioch | +0.103 |
theless | +0.103 |
arnaev | +0.101 |
Neg logit contributions | |
FAQ | -0.105 |
Bowman | -0.079 |
DG | -0.074 |
roots | -0.072 |
ollow | -0.071 |
Token | ANS |
Token ID | 15037 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
axter | +0.154 |
�� | +0.154 |
ioch | +0.152 |
theless | +0.151 |
arnaev | +0.149 |
Neg logit contributions | |
FAQ | -0.164 |
Bowman | -0.125 |
DG | -0.118 |
roots | -0.114 |
ollow | -0.113 |
Token | ING |
Token ID | 2751 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
�� | +1.576 |
axter | +1.542 |
theless | +1.529 |
ioch | +1.492 |
arnaev | +1.482 |
Neg logit contributions | |
FAQ | -1.763 |
Bowman | -1.377 |
DG | -1.291 |
Dems | -1.224 |
ollow | -1.223 |
Token | , |
Token ID | 11 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
axter | +0.065 |
�� | +0.065 |
ioch | +0.064 |
theless | +0.064 |
arnaev | +0.063 |
Neg logit contributions | |
FAQ | -0.075 |
Bowman | -0.058 |
DG | -0.055 |
roots | -0.053 |
ollow | -0.053 |
Token | MI |
Token ID | 15789 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
FAQ | +0.020 |
Bowman | +0.016 |
DG | +0.015 |
roots | +0.015 |
ollow | +0.014 |
Neg logit contributions | |
axter | -0.015 |
�� | -0.015 |
ioch | -0.015 |
theless | -0.015 |
arnaev | -0.014 |
Token | -- |
Token ID | 1377 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
axter | +0.144 |
�� | +0.143 |
ioch | +0.142 |
theless | +0.141 |
arnaev | +0.139 |
Neg logit contributions | |
FAQ | -0.171 |
Bowman | -0.132 |
DG | -0.125 |
roots | -0.121 |
ollow | -0.120 |
Token | The |
Token ID | 383 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
FAQ | +0.102 |
Bowman | +0.077 |
DG | +0.072 |
roots | +0.070 |
ollow | +0.069 |
Neg logit contributions | |
axter | -0.101 |
�� | -0.100 |
ioch | -0.099 |
theless | -0.099 |
arnaev | -0.098 |
Token | Close |
Token ID | 13872 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
�� | +0.622 |
axter | +0.610 |
ioch | +0.602 |
theless | +0.601 |
arnaev | +0.592 |
Neg logit contributions | |
FAQ | -0.956 |
Bowman | -0.764 |
DG | -0.726 |
Dems | -0.708 |
roots | -0.702 |
Token |
|
Token ID | 198 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
FAQ | +0.178 |
Bowman | +0.138 |
DG | +0.130 |
roots | +0.126 |
vae | +0.125 |
Neg logit contributions | |
axter | -0.150 |
�� | -0.148 |
ioch | -0.147 |
theless | -0.147 |
arnaev | -0.145 |
Token |
|
Token ID | 198 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
axter | +0.142 |
�� | +0.141 |
ioch | +0.140 |
theless | +0.139 |
arnaev | +0.137 |
Neg logit contributions | |
FAQ | -0.164 |
Bowman | -0.127 |
DG | -0.119 |
roots | -0.116 |
ollow | -0.115 |
Token | Email |
Token ID | 15333 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
axter | +0.124 |
�� | +0.123 |
ioch | +0.121 |
theless | +0.120 |
arnaev | +0.118 |
Neg logit contributions | |
FAQ | -0.211 |
Bowman | -0.170 |
DG | -0.162 |
roots | -0.158 |
ollow | -0.157 |
Token | This |
Token ID | 770 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
FAQ | +0.412 |
Bowman | +0.320 |
DG | +0.301 |
roots | +0.292 |
ollow | +0.291 |
Neg logit contributions | |
axter | -0.340 |
�� | -0.334 |
ioch | -0.333 |
theless | -0.331 |
arnaev | -0.327 |
Token | Story |
Token ID | 8362 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
axter | +0.879 |
�� | +0.876 |
theless | +0.864 |
ioch | +0.862 |
arnaev | +0.850 |
Neg logit contributions | |
FAQ | -0.957 |
Bowman | -0.740 |
DG | -0.698 |
ollow | -0.674 |
Bounty | -0.671 |
Token | Send |
Token ID | 16290 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
�� | +1.114 |
axter | +1.096 |
ioch | +1.055 |
theless | +1.044 |
arnaev | +1.041 |
Neg logit contributions | |
FAQ | -2.095 |
Bowman | -1.733 |
DG | -1.663 |
Bounty | -1.610 |
Dems | -1.609 |
Token | email |
Token ID | 3053 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
FAQ | +0.939 |
Bowman | +0.753 |
DG | +0.716 |
roots | +0.705 |
vae | +0.702 |
Neg logit contributions | |
axter | -0.578 |
�� | -0.564 |
ioch | -0.558 |
theless | -0.556 |
arnaev | -0.550 |
Token | to |
Token ID | 284 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
FAQ | +0.134 |
Bowman | +0.102 |
DG | +0.096 |
roots | +0.093 |
vae | +0.092 |
Neg logit contributions | |
axter | -0.127 |
�� | -0.126 |
ioch | -0.125 |
theless | -0.124 |
arnaev | -0.123 |
Token | this |
Token ID | 428 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
axter | +0.262 |
�� | +0.260 |
ioch | +0.257 |
theless | +0.257 |
arnaev | +0.254 |
Neg logit contributions | |
FAQ | -0.240 |
Bowman | -0.179 |
DG | -0.167 |
roots | -0.161 |
ollow | -0.159 |
Token | address |
Token ID | 2209 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
�� | +0.461 |
axter | +0.460 |
theless | +0.453 |
ioch | +0.452 |
arnaev | +0.447 |
Neg logit contributions | |
FAQ | -0.426 |
Bowman | -0.318 |
DG | -0.298 |
roots | -0.287 |
ollow | -0.284 |
Token |
|
Token ID | 198 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
axter | +0.191 |
�� | +0.190 |
ioch | +0.187 |
theless | +0.187 |
arnaev | +0.184 |
Neg logit contributions | |
FAQ | -0.219 |
Bowman | -0.169 |
DG | -0.159 |
roots | -0.154 |
ollow | -0.153 |
Token |
|
Token ID | 198 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
axter | +0.026 |
�� | +0.025 |
ioch | +0.025 |
theless | +0.025 |
arnaev | +0.025 |
Neg logit contributions | |
FAQ | -0.030 |
Bowman | -0.023 |
DG | -0.022 |
roots | -0.021 |
vae | -0.021 |
Token | 10 |
Token ID | 940 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
axter | +0.201 |
�� | +0.199 |
ioch | +0.197 |
theless | +0.196 |
arnaev | +0.193 |
Neg logit contributions | |
FAQ | -0.259 |
Bowman | -0.203 |
DG | -0.192 |
roots | -0.186 |
ollow | -0.185 |
Token | Cab |
Token ID | 15976 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
FAQ | +0.199 |
Bowman | +0.153 |
DG | +0.144 |
roots | +0.141 |
vae | +0.139 |
Neg logit contributions | |
axter | -0.172 |
�� | -0.170 |
ioch | -0.169 |
theless | -0.169 |
arnaev | -0.166 |
Token | o |
Token ID | 78 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
axter | +0.148 |
�� | +0.147 |
ioch | +0.146 |
theless | +0.145 |
arnaev | +0.143 |
Neg logit contributions | |
FAQ | -0.160 |
Bowman | -0.123 |
DG | -0.115 |
roots | -0.112 |
ollow | -0.111 |
Token | Ver |
Token ID | 4643 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
FAQ | +0.208 |
Bowman | +0.154 |
DG | +0.144 |
roots | +0.139 |
ollow | +0.138 |
Neg logit contributions | |
axter | -0.226 |
�� | -0.223 |
ioch | -0.222 |
theless | -0.221 |
arnaev | -0.218 |
Token | de |
Token ID | 2934 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
�� | +1.631 |
axter | +1.593 |
theless | +1.571 |
ioch | +1.564 |
arnaev | +1.557 |
Neg logit contributions | |
FAQ | -1.575 |
Bowman | -1.178 |
DG | -1.132 |
Dems | -1.092 |
roots | -1.086 |
Token | 124 |
Token ID | 19755 |
Feature activation | -5.25e-03 |
Pos logit contributions | |
axter | +0.008 |
�� | +0.008 |
ioch | +0.007 |
theless | +0.007 |
arnaev | +0.007 |
Neg logit contributions | |
FAQ | -0.009 |
Bowman | -0.007 |
DG | -0.006 |
roots | -0.006 |
ollow | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
axter | +0.004 |
�� | +0.004 |
ioch | +0.004 |
theless | +0.004 |
arnaev | +0.004 |
Neg logit contributions | |
FAQ | -0.004 |
Bowman | -0.003 |
DG | -0.003 |
roots | -0.003 |
ollow | -0.003 |
Token | 8 |
Token ID | 23 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
FAQ | +0.060 |
Bowman | +0.045 |
DG | +0.042 |
roots | +0.040 |
ollow | +0.040 |
Neg logit contributions | |
axter | -0.063 |
�� | -0.062 |
ioch | -0.062 |
theless | -0.061 |
arnaev | -0.061 |
Token |
|
Token ID | 198 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
axter | +0.032 |
�� | +0.032 |
ioch | +0.032 |
theless | +0.031 |
arnaev | +0.031 |
Neg logit contributions | |
FAQ | -0.037 |
Bowman | -0.029 |
DG | -0.027 |
roots | -0.026 |
ollow | -0.026 |
Token | qu |
Token ID | 627 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
FAQ | +0.019 |
Bowman | +0.015 |
DG | +0.014 |
roots | +0.014 |
ollow | +0.014 |
Neg logit contributions | |
axter | -0.015 |
�� | -0.015 |
ioch | -0.015 |
theless | -0.015 |
arnaev | -0.014 |
Token | ash |
Token ID | 1077 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
FAQ | +0.073 |
Bowman | +0.052 |
DG | +0.048 |
roots | +0.046 |
Dems | +0.046 |
Neg logit contributions | |
axter | -0.095 |
�� | -0.094 |
ioch | -0.094 |
theless | -0.093 |
arnaev | -0.092 |
Token | changes |
Token ID | 2458 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
FAQ | +0.172 |
Bowman | +0.132 |
DG | +0.125 |
roots | +0.121 |
ollow | +0.120 |
Neg logit contributions | |
axter | -0.150 |
�� | -0.149 |
ioch | -0.148 |
theless | -0.147 |
arnaev | -0.145 |
Token | to |
Token ID | 284 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
FAQ | +0.146 |
Bowman | +0.111 |
DG | +0.105 |
roots | +0.101 |
vae | +0.101 |
Neg logit contributions | |
axter | -0.137 |
�� | -0.136 |
ioch | -0.134 |
theless | -0.134 |
arnaev | -0.132 |
Token | an |
Token ID | 281 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
axter | +0.026 |
�� | +0.026 |
ioch | +0.026 |
theless | +0.026 |
arnaev | +0.025 |
Neg logit contributions | |
FAQ | -0.029 |
Bowman | -0.022 |
DG | -0.021 |
roots | -0.020 |
ollow | -0.020 |
Token | En |
Token ID | 2039 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
FAQ | +0.236 |
Bowman | +0.183 |
DG | +0.173 |
roots | +0.168 |
ollow | +0.167 |
Neg logit contributions | |
axter | -0.198 |
�� | -0.195 |
ioch | -0.194 |
theless | -0.193 |
arnaev | -0.189 |
Token | bridge |
Token ID | 9458 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
�� | +1.210 |
axter | +1.201 |
theless | +1.183 |
arnaev | +1.157 |
ioch | +1.153 |
Neg logit contributions | |
FAQ | -1.891 |
Bowman | -1.519 |
DG | -1.424 |
roots | -1.406 |
iris | -1.400 |
Token | Inc |
Token ID | 3457 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
axter | +0.116 |
�� | +0.116 |
ioch | +0.114 |
theless | +0.114 |
arnaev | +0.112 |
Neg logit contributions | |
FAQ | -0.124 |
Bowman | -0.095 |
DG | -0.089 |
roots | -0.086 |
ollow | -0.085 |
Token | pipeline |
Token ID | 11523 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
axter | +0.325 |
�� | +0.323 |
ioch | +0.319 |
theless | +0.319 |
arnaev | +0.315 |
Neg logit contributions | |
FAQ | -0.341 |
Bowman | -0.260 |
DG | -0.244 |
roots | -0.236 |
ollow | -0.234 |
Token | . |
Token ID | 13 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
axter | +0.283 |
�� | +0.282 |
ioch | +0.278 |
theless | +0.278 |
arnaev | +0.274 |
Neg logit contributions | |
FAQ | -0.312 |
Bowman | -0.240 |
DG | -0.226 |
roots | -0.218 |
ollow | -0.217 |
Token |
|
Token ID | 198 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
FAQ | +0.049 |
Bowman | +0.038 |
DG | +0.036 |
roots | +0.034 |
ollow | +0.034 |
Neg logit contributions | |
axter | -0.042 |
�� | -0.041 |
ioch | -0.041 |
theless | -0.041 |
arnaev | -0.040 |
Token | died |
Token ID | 3724 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
axter | +0.118 |
�� | +0.117 |
ioch | +0.116 |
theless | +0.115 |
arnaev | +0.114 |
Neg logit contributions | |
FAQ | -0.140 |
Bowman | -0.108 |
DG | -0.102 |
roots | -0.099 |
ollow | -0.098 |
Token | of |
Token ID | 286 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
axter | +0.120 |
�� | +0.120 |
ioch | +0.118 |
theless | +0.118 |
arnaev | +0.116 |
Neg logit contributions | |
FAQ | -0.133 |
Bowman | -0.102 |
DG | -0.096 |
roots | -0.093 |
ollow | -0.092 |
Token | his |
Token ID | 465 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
FAQ | +0.088 |
Bowman | +0.068 |
DG | +0.064 |
roots | +0.062 |
ollow | +0.062 |
Neg logit contributions | |
axter | -0.075 |
�� | -0.074 |
ioch | -0.073 |
theless | -0.073 |
arnaev | -0.072 |
Token | infection |
Token ID | 10280 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
axter | +0.110 |
�� | +0.109 |
ioch | +0.108 |
theless | +0.107 |
arnaev | +0.106 |
Neg logit contributions | |
FAQ | -0.130 |
Bowman | -0.101 |
DG | -0.095 |
roots | -0.092 |
ollow | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
axter | +0.071 |
�� | +0.070 |
ioch | +0.070 |
theless | +0.070 |
arnaev | +0.069 |
Neg logit contributions | |
FAQ | -0.079 |
Bowman | -0.061 |
DG | -0.057 |
roots | -0.055 |
ollow | -0.055 |
Token | Thomas |
Token ID | 5658 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
FAQ | +0.014 |
Bowman | +0.011 |
DG | +0.010 |
roots | +0.010 |
ollow | +0.010 |
Neg logit contributions | |
axter | -0.013 |
�� | -0.012 |
ioch | -0.012 |
theless | -0.012 |
arnaev | -0.012 |
Token | Eric |
Token ID | 7651 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
�� | +1.214 |
axter | +1.177 |
theless | +1.163 |
ioch | +1.146 |
paren | +1.114 |
Neg logit contributions | |
FAQ | -1.857 |
Bowman | -1.527 |
DG | -1.428 |
roots | -1.380 |
Bounty | -1.376 |
Token | Duncan |
Token ID | 18625 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
�� | +0.842 |
axter | +0.835 |
theless | +0.829 |
ioch | +0.821 |
arnaev | +0.807 |
Neg logit contributions | |
FAQ | -0.799 |
Bowman | -0.609 |
DG | -0.563 |
roots | -0.543 |
Dems | -0.540 |
Token | succumbed |
Token ID | 47290 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
axter | +0.318 |
�� | +0.316 |
ioch | +0.312 |
theless | +0.311 |
arnaev | +0.306 |
Neg logit contributions | |
FAQ | -0.368 |
Bowman | -0.286 |
DG | -0.269 |
roots | -0.260 |
Dems | -0.258 |
Token | to |
Token ID | 284 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
axter | +0.066 |
�� | +0.065 |
ioch | +0.065 |
theless | +0.064 |
arnaev | +0.064 |
Neg logit contributions | |
FAQ | -0.069 |
Bowman | -0.053 |
DG | -0.049 |
roots | -0.048 |
ollow | -0.047 |
Token | his |
Token ID | 465 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
axter | +0.028 |
�� | +0.028 |
ioch | +0.027 |
theless | +0.027 |
arnaev | +0.027 |
Neg logit contributions | |
FAQ | -0.034 |
Bowman | -0.027 |
DG | -0.025 |
roots | -0.024 |
ollow | -0.024 |
Token | ," |
Token ID | 553 |
Feature activation | -7.88e-02 |
Pos logit contributions | |
axter | +0.084 |
�� | +0.083 |
ioch | +0.082 |
theless | +0.082 |
arnaev | +0.080 |
Neg logit contributions | |
FAQ | -0.106 |
Bowman | -0.082 |
DG | -0.078 |
roots | -0.076 |
ollow | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
axter | +0.055 |
�� | +0.055 |
ioch | +0.054 |
theless | +0.054 |
arnaev | +0.053 |
Neg logit contributions | |
FAQ | -0.059 |
Bowman | -0.045 |
DG | -0.043 |
roots | -0.041 |
ollow | -0.041 |
Token | 1976 |
Token ID | 15408 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
axter | +0.152 |
�� | +0.150 |
ioch | +0.149 |
theless | +0.148 |
arnaev | +0.146 |
Neg logit contributions | |
FAQ | -0.171 |
Bowman | -0.132 |
DG | -0.124 |
roots | -0.120 |
ollow | -0.119 |
Token | Martin |
Token ID | 5780 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
axter | +0.035 |
�� | +0.034 |
ioch | +0.034 |
theless | +0.034 |
arnaev | +0.033 |
Neg logit contributions | |
FAQ | -0.042 |
Bowman | -0.033 |
DG | -0.031 |
roots | -0.030 |
ollow | -0.030 |
Token | Sc |
Token ID | 1446 |
Feature activation | -7.01e-04 |
Pos logit contributions | |
FAQ | +0.095 |
Bowman | +0.077 |
DG | +0.073 |
roots | +0.072 |
ollow | +0.071 |
Neg logit contributions | |
axter | -0.052 |
�� | -0.051 |
ioch | -0.051 |
theless | -0.050 |
arnaev | -0.050 |
Token | ors |
Token ID | 669 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
axter | +0.000 |
�� | +0.000 |
ioch | +0.000 |
theless | +0.000 |
arnaev | +0.000 |
Neg logit contributions | |
FAQ | -0.001 |
Bowman | -0.000 |
DG | -0.000 |
roots | -0.000 |
ollow | -0.000 |
Token | ese |
Token ID | 2771 |
Feature activation | -5.62e-03 |
Pos logit contributions | |
�� | +0.945 |
axter | +0.924 |
theless | +0.911 |
ioch | +0.889 |
arnaev | +0.885 |
Neg logit contributions | |
FAQ | -2.056 |
Bowman | -1.697 |
DG | -1.636 |
iris | -1.616 |
roots | -1.603 |
Token | film |
Token ID | 2646 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
axter | +0.003 |
�� | +0.003 |
ioch | +0.003 |
theless | +0.003 |
arnaev | +0.003 |
Neg logit contributions | |
FAQ | -0.005 |
Bowman | -0.004 |
DG | -0.003 |
roots | -0.003 |
ollow | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
FAQ | +0.370 |
Bowman | +0.285 |
DG | +0.269 |
roots | +0.262 |
vae | +0.260 |
Neg logit contributions | |
axter | -0.312 |
�� | -0.309 |
ioch | -0.306 |
theless | -0.305 |
arnaev | -0.301 |
Token | 's |
Token ID | 338 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
axter | +0.152 |
�� | +0.151 |
ioch | +0.149 |
theless | +0.148 |
arnaev | +0.146 |
Neg logit contributions | |
FAQ | -0.182 |
Bowman | -0.141 |
DG | -0.133 |
roots | -0.129 |
ollow | -0.128 |
Token | celebrating |
Token ID | 17499 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
FAQ | +0.029 |
Bowman | +0.022 |
DG | +0.021 |
roots | +0.021 |
ollow | +0.020 |
Neg logit contributions | |
axter | -0.025 |
�� | -0.024 |
ioch | -0.024 |
theless | -0.024 |
arnaev | -0.024 |
Token | intersection |
Token ID | 16246 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
FAQ | +0.002 |
Bowman | +0.001 |
DG | +0.001 |
roots | +0.001 |
ollow | +0.001 |
Neg logit contributions | |
axter | -0.001 |
�� | -0.001 |
ioch | -0.001 |
theless | -0.001 |
arnaev | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
FAQ | +0.124 |
Bowman | +0.096 |
DG | +0.090 |
roots | +0.088 |
vae | +0.087 |
Neg logit contributions | |
axter | -0.107 |
�� | -0.106 |
ioch | -0.105 |
theless | -0.105 |
arnaev | -0.103 |
Token | Y |
Token ID | 575 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
axter | +0.017 |
�� | +0.016 |
ioch | +0.016 |
theless | +0.016 |
arnaev | +0.016 |
Neg logit contributions | |
FAQ | -0.019 |
Bowman | -0.015 |
DG | -0.014 |
roots | -0.014 |
ollow | -0.014 |
Token | onge |
Token ID | 14220 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
axter | +0.185 |
�� | +0.184 |
ioch | +0.182 |
theless | +0.182 |
arnaev | +0.180 |
Neg logit contributions | |
FAQ | -0.135 |
Bowman | -0.096 |
DG | -0.088 |
roots | -0.085 |
ollow | -0.084 |
Token | and |
Token ID | 290 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
axter | +0.119 |
�� | +0.118 |
ioch | +0.117 |
theless | +0.117 |
arnaev | +0.115 |
Neg logit contributions | |
FAQ | -0.133 |
Bowman | -0.102 |
DG | -0.096 |
roots | -0.093 |
ollow | -0.092 |
Token | E |
Token ID | 412 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
axter | +0.398 |
�� | +0.396 |
ioch | +0.391 |
theless | +0.390 |
arnaev | +0.386 |
Neg logit contributions | |
FAQ | -0.438 |
Bowman | -0.338 |
DG | -0.318 |
roots | -0.306 |
ollow | -0.304 |
Token | gl |
Token ID | 4743 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
�� | +1.052 |
axter | +1.026 |
ioch | +1.010 |
arnaev | +1.008 |
theless | +1.007 |
Neg logit contributions | |
FAQ | -1.944 |
Bowman | -1.594 |
DG | -1.509 |
ollow | -1.474 |
roots | -1.472 |
Token | inton |
Token ID | 2371 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
axter | +0.035 |
�� | +0.034 |
ioch | +0.034 |
theless | +0.034 |
arnaev | +0.033 |
Neg logit contributions | |
FAQ | -0.055 |
Bowman | -0.044 |
DG | -0.042 |
roots | -0.041 |
vae | -0.040 |
Token | will |
Token ID | 481 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
axter | +0.122 |
�� | +0.121 |
ioch | +0.119 |
theless | +0.119 |
arnaev | +0.117 |
Neg logit contributions | |
FAQ | -0.143 |
Bowman | -0.110 |
DG | -0.104 |
roots | -0.101 |
ollow | -0.100 |
Token | feature |
Token ID | 3895 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
axter | +0.349 |
�� | +0.347 |
ioch | +0.343 |
theless | +0.342 |
arnaev | +0.337 |
Neg logit contributions | |
FAQ | -0.431 |
Bowman | -0.337 |
DG | -0.319 |
roots | -0.308 |
ollow | -0.307 |
Token | large |
Token ID | 1588 |
Feature activation | +8.01e-02 |
Pos logit contributions | |
axter | +0.048 |
�� | +0.048 |
ioch | +0.047 |
theless | +0.047 |
arnaev | +0.046 |
Neg logit contributions | |
FAQ | -0.054 |
Bowman | -0.042 |
DG | -0.039 |
roots | -0.038 |
ollow | -0.038 |
Token | requested |
Token ID | 9167 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
FAQ | +0.368 |
Bowman | +0.282 |
DG | +0.263 |
roots | +0.258 |
vae | +0.256 |
Neg logit contributions | |
axter | -0.328 |
�� | -0.326 |
ioch | -0.324 |
theless | -0.324 |
arnaev | -0.318 |
Token | putting |
Token ID | 5137 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
axter | +0.481 |
�� | +0.477 |
theless | +0.473 |
ioch | +0.471 |
arnaev | +0.465 |
Neg logit contributions | |
FAQ | -0.446 |
Bowman | -0.332 |
DG | -0.311 |
Dems | -0.298 |
roots | -0.298 |
Token | ally |
Token ID | 12525 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
axter | +0.112 |
�� | +0.111 |
ioch | +0.110 |
theless | +0.110 |
arnaev | +0.109 |
Neg logit contributions | |
FAQ | -0.086 |
Bowman | -0.062 |
DG | -0.057 |
roots | -0.055 |
ollow | -0.054 |
Token | in |
Token ID | 287 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
FAQ | +0.646 |
Bowman | +0.496 |
DG | +0.470 |
roots | +0.459 |
vae | +0.455 |
Neg logit contributions | |
axter | -0.531 |
ioch | -0.523 |
�� | -0.521 |
theless | -0.512 |
arnaev | -0.512 |
Token | charge |
Token ID | 3877 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
FAQ | +0.250 |
Bowman | +0.194 |
DG | +0.183 |
roots | +0.179 |
ollow | +0.177 |
Neg logit contributions | |
axter | -0.200 |
ioch | -0.196 |
�� | -0.196 |
theless | -0.194 |
arnaev | -0.192 |
Token | of |
Token ID | 286 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
axter | +0.429 |
�� | +0.429 |
ioch | +0.423 |
theless | +0.422 |
arnaev | +0.415 |
Neg logit contributions | |
FAQ | -0.463 |
Bowman | -0.354 |
DG | -0.335 |
roots | -0.322 |
Dems | -0.322 |
Token | Cohen |
Token ID | 17154 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
�� | +1.386 |
axter | +1.370 |
ioch | +1.341 |
theless | +1.340 |
arnaev | +1.309 |
Neg logit contributions | |
FAQ | -1.626 |
Bowman | -1.259 |
DG | -1.202 |
Dems | -1.175 |
roots | -1.151 |
Token | probe |
Token ID | 12774 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
axter | +0.043 |
�� | +0.042 |
ioch | +0.042 |
theless | +0.042 |
arnaev | +0.041 |
Neg logit contributions | |
FAQ | -0.044 |
Bowman | -0.033 |
DG | -0.031 |
roots | -0.030 |
ollow | -0.030 |
Token | : |
Token ID | 25 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
axter | +0.791 |
�� | +0.790 |
ioch | +0.778 |
theless | +0.773 |
arnaev | +0.762 |
Neg logit contributions | |
FAQ | -0.829 |
Bowman | -0.636 |
DG | -0.596 |
Dems | -0.587 |
ollow | -0.576 |
Token | report |
Token ID | 989 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
�� | +0.672 |
axter | +0.671 |
ioch | +0.658 |
theless | +0.656 |
arnaev | +0.651 |
Neg logit contributions | |
FAQ | -0.671 |
Bowman | -0.511 |
DG | -0.476 |
Dems | -0.464 |
roots | -0.460 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
FAQ | +0.432 |
Bowman | +0.302 |
DG | +0.278 |
roots | +0.268 |
iris | +0.267 |
Neg logit contributions | |
axter | -0.603 |
�� | -0.598 |
ioch | -0.591 |
theless | -0.591 |
arnaev | -0.587 |
Token | , |
Token ID | 11 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
FAQ | +0.148 |
Bowman | +0.115 |
DG | +0.108 |
roots | +0.104 |
vae | +0.104 |
Neg logit contributions | |
axter | -0.129 |
�� | -0.128 |
ioch | -0.127 |
theless | -0.127 |
arnaev | -0.125 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
FAQ | +0.492 |
Bowman | +0.368 |
DG | +0.343 |
roots | +0.335 |
ollow | +0.330 |
Neg logit contributions | |
axter | -0.527 |
�� | -0.521 |
ioch | -0.520 |
theless | -0.514 |
arnaev | -0.510 |
Token | ). |
Token ID | 737 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
FAQ | +0.342 |
Bowman | +0.262 |
DG | +0.246 |
roots | +0.239 |
ollow | +0.238 |
Neg logit contributions | |
axter | -0.310 |
�� | -0.305 |
ioch | -0.304 |
theless | -0.302 |
arnaev | -0.299 |
Token |
|
Token ID | 198 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
FAQ | +0.653 |
Bowman | +0.507 |
DG | +0.482 |
roots | +0.470 |
iris | +0.465 |
Neg logit contributions | |
axter | -0.534 |
ioch | -0.523 |
theless | -0.520 |
�� | -0.517 |
arnaev | -0.517 |
Token |
|
Token ID | 198 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
axter | +0.040 |
�� | +0.039 |
ioch | +0.039 |
theless | +0.039 |
arnaev | +0.038 |
Neg logit contributions | |
FAQ | -0.046 |
Bowman | -0.036 |
DG | -0.034 |
roots | -0.033 |
vae | -0.032 |
Token | You |
Token ID | 1639 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
axter | +0.213 |
�� | +0.213 |
ioch | +0.210 |
theless | +0.209 |
arnaev | +0.206 |
Neg logit contributions | |
FAQ | -0.249 |
Bowman | -0.192 |
DG | -0.181 |
roots | -0.176 |
ollow | -0.174 |
Token | can |
Token ID | 460 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
�� | +1.128 |
axter | +1.090 |
theless | +1.083 |
arnaev | +1.072 |
ioch | +1.068 |
Neg logit contributions | |
FAQ | -1.859 |
Bowman | -1.493 |
DG | -1.416 |
iris | -1.401 |
Bounty | -1.394 |
Token | buy |
Token ID | 2822 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
FAQ | +0.602 |
Bowman | +0.493 |
DG | +0.476 |
roots | +0.466 |
ollow | +0.463 |
Neg logit contributions | |
axter | -0.270 |
�� | -0.265 |
ioch | -0.263 |
theless | -0.262 |
arnaev | -0.257 |
Token | An |
Token ID | 1052 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
FAQ | +1.365 |
Bowman | +1.004 |
DG | +0.959 |
roots | +0.952 |
atsu | +0.950 |
Neg logit contributions | |
axter | -1.221 |
theless | -1.200 |
�� | -1.187 |
ioch | -1.172 |
arnaev | -1.169 |
Token | Enemy |
Token ID | 21785 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
�� | +0.349 |
axter | +0.347 |
theless | +0.340 |
ioch | +0.339 |
arnaev | +0.331 |
Neg logit contributions | |
FAQ | -0.679 |
Bowman | -0.554 |
DG | -0.529 |
roots | -0.517 |
Bounty | -0.513 |
Token | of |
Token ID | 286 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
FAQ | +0.342 |
Bowman | +0.264 |
DG | +0.248 |
roots | +0.241 |
vae | +0.239 |
Neg logit contributions | |
axter | -0.295 |
�� | -0.291 |
ioch | -0.289 |
theless | -0.286 |
arnaev | -0.284 |
Token | Ellis |
Token ID | 21299 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
axter | +0.186 |
�� | +0.185 |
ioch | +0.183 |
theless | +0.182 |
arnaev | +0.180 |
Neg logit contributions | |
FAQ | -0.195 |
Bowman | -0.148 |
DG | -0.139 |
roots | -0.135 |
ollow | -0.133 |
Token | , |
Token ID | 11 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
axter | +0.048 |
�� | +0.048 |
ioch | +0.048 |
theless | +0.047 |
arnaev | +0.047 |
Neg logit contributions | |
FAQ | -0.054 |
Bowman | -0.042 |
DG | -0.039 |
roots | -0.038 |
ollow | -0.038 |
Token | Devin |
Token ID | 37081 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
FAQ | +0.110 |
Bowman | +0.085 |
DG | +0.080 |
roots | +0.077 |
ollow | +0.077 |
Neg logit contributions | |
axter | -0.098 |
�� | -0.097 |
ioch | -0.096 |
theless | -0.096 |
arnaev | -0.095 |
Token | Harris |
Token ID | 10026 |
Feature activation | -4.53e-03 |
Pos logit contributions | |
FAQ | +0.129 |
Bowman | +0.098 |
DG | +0.092 |
roots | +0.090 |
vae | +0.089 |
Neg logit contributions | |
axter | -0.121 |
�� | -0.120 |
ioch | -0.119 |
theless | -0.118 |
arnaev | -0.117 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
axter | +0.003 |
�� | +0.003 |
ioch | +0.003 |
theless | +0.003 |
arnaev | +0.003 |
Neg logit contributions | |
FAQ | -0.003 |
Bowman | -0.003 |
DG | -0.003 |
roots | -0.002 |
ollow | -0.002 |
Token | Raymond |
Token ID | 24238 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
FAQ | +0.105 |
Bowman | +0.081 |
DG | +0.076 |
roots | +0.074 |
ollow | +0.073 |
Neg logit contributions | |
axter | -0.094 |
�� | -0.093 |
ioch | -0.092 |
theless | -0.092 |
arnaev | -0.090 |
Token | Fel |
Token ID | 13937 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
�� | +1.262 |
axter | +1.258 |
theless | +1.250 |
ioch | +1.232 |
arnaev | +1.218 |
Neg logit contributions | |
FAQ | -1.608 |
Bowman | -1.277 |
DG | -1.213 |
iris | -1.166 |
Bounty | -1.162 |
Token | ton |
Token ID | 1122 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
FAQ | +0.277 |
Bowman | +0.200 |
DG | +0.185 |
roots | +0.178 |
vae | +0.177 |
Neg logit contributions | |
axter | -0.346 |
�� | -0.341 |
ioch | -0.341 |
theless | -0.340 |
arnaev | -0.335 |
Token | ( |
Token ID | 357 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
FAQ | +0.077 |
Bowman | +0.059 |
DG | +0.056 |
roots | +0.054 |
vae | +0.054 |
Neg logit contributions | |
axter | -0.068 |
�� | -0.068 |
ioch | -0.067 |
theless | -0.067 |
arnaev | -0.066 |
Token | who |
Token ID | 8727 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
FAQ | +0.054 |
Bowman | +0.041 |
DG | +0.039 |
roots | +0.038 |
ollow | +0.037 |
Neg logit contributions | |
axter | -0.048 |
�� | -0.048 |
ioch | -0.047 |
theless | -0.047 |
arnaev | -0.046 |
Token | has |
Token ID | 468 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
FAQ | +0.019 |
Bowman | +0.015 |
DG | +0.014 |
roots | +0.014 |
ollow | +0.014 |
Neg logit contributions | |
axter | -0.016 |
�� | -0.016 |
ioch | -0.016 |
theless | -0.016 |
arnaev | -0.016 |
Token | i |
Token ID | 72 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
axter | +0.173 |
�� | +0.172 |
ioch | +0.170 |
theless | +0.170 |
arnaev | +0.168 |
Neg logit contributions | |
FAQ | -0.120 |
Bowman | -0.084 |
DG | -0.077 |
roots | -0.074 |
ollow | -0.073 |
Token | ( |
Token ID | 357 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
axter | +0.203 |
�� | +0.202 |
ioch | +0.200 |
theless | +0.199 |
arnaev | +0.196 |
Neg logit contributions | |
FAQ | -0.210 |
Bowman | -0.160 |
DG | -0.150 |
roots | -0.145 |
ollow | -0.144 |
Token | Ag |
Token ID | 10262 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
�� | +0.546 |
axter | +0.545 |
theless | +0.536 |
ioch | +0.535 |
arnaev | +0.528 |
Neg logit contributions | |
FAQ | -0.590 |
Bowman | -0.449 |
DG | -0.423 |
roots | -0.409 |
ollow | -0.406 |
Token | 2 |
Token ID | 17 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
axter | +0.204 |
�� | +0.203 |
ioch | +0.201 |
theless | +0.201 |
arnaev | +0.198 |
Neg logit contributions | |
FAQ | -0.182 |
Bowman | -0.135 |
DG | -0.126 |
roots | -0.122 |
ollow | -0.120 |
Token | r |
Token ID | 81 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
FAQ | +0.414 |
Bowman | +0.271 |
DG | +0.243 |
Dems | +0.228 |
Bounty | +0.226 |
Neg logit contributions | |
axter | -0.759 |
ioch | -0.748 |
�� | -0.742 |
theless | -0.739 |
arnaev | -0.733 |
Token | - |
Token ID | 12 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
axter | +0.240 |
�� | +0.239 |
ioch | +0.236 |
theless | +0.235 |
arnaev | +0.232 |
Neg logit contributions | |
FAQ | -0.240 |
Bowman | -0.182 |
DG | -0.171 |
roots | -0.165 |
vae | -0.163 |
Token | La |
Token ID | 14772 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
�� | +1.547 |
arnaev | +1.521 |
axter | +1.514 |
theless | +1.509 |
ioch | +1.487 |
Neg logit contributions | |
FAQ | -1.347 |
Bowman | -1.000 |
DG | -0.925 |
ollow | -0.892 |
Bounty | -0.892 |
Token | Mond |
Token ID | 27328 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
FAQ | +0.525 |
Bowman | +0.426 |
DG | +0.406 |
roots | +0.399 |
vae | +0.397 |
Neg logit contributions | |
axter | -0.274 |
�� | -0.270 |
ioch | -0.269 |
theless | -0.269 |
arnaev | -0.262 |
Token | ial |
Token ID | 498 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
FAQ | +0.672 |
Bowman | +0.549 |
DG | +0.524 |
roots | +0.511 |
vae | +0.511 |
Neg logit contributions | |
ioch | -0.352 |
axter | -0.352 |
�� | -0.351 |
theless | -0.338 |
arnaev | -0.337 |
Token | e |
Token ID | 68 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
�� | +0.537 |
axter | +0.535 |
theless | +0.525 |
ioch | +0.521 |
arnaev | +0.513 |
Neg logit contributions | |
FAQ | -0.786 |
Bowman | -0.628 |
DG | -0.594 |
roots | -0.576 |
Bounty | -0.576 |
Token | ) |
Token ID | 8 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
axter | +0.146 |
�� | +0.145 |
ioch | +0.143 |
theless | +0.143 |
arnaev | +0.141 |
Neg logit contributions | |
FAQ | -0.139 |
Bowman | -0.105 |
DG | -0.098 |
roots | -0.094 |
ollow | -0.093 |
Token | both |
Token ID | 1111 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
axter | +0.308 |
�� | +0.306 |
ioch | +0.303 |
theless | +0.302 |
arnaev | +0.298 |
Neg logit contributions | |
FAQ | -0.345 |
Bowman | -0.266 |
DG | -0.251 |
roots | -0.242 |
Dems | -0.240 |
Token | fl |
Token ID | 781 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
axter | +0.097 |
�� | +0.096 |
ioch | +0.095 |
theless | +0.095 |
arnaev | +0.093 |
Neg logit contributions | |
FAQ | -0.102 |
Bowman | -0.078 |
DG | -0.073 |
roots | -0.071 |
ollow | -0.070 |
Token | anks |
Token ID | 2283 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
axter | +0.207 |
�� | +0.206 |
ioch | +0.203 |
theless | +0.203 |
arnaev | +0.199 |
Neg logit contributions | |
FAQ | -0.362 |
Bowman | -0.293 |
DG | -0.280 |
roots | -0.273 |
ollow | -0.271 |
Token | and |
Token ID | 290 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
axter | +0.112 |
�� | +0.111 |
ioch | +0.110 |
theless | +0.110 |
arnaev | +0.108 |
Neg logit contributions | |
FAQ | -0.125 |
Bowman | -0.096 |
DG | -0.091 |
roots | -0.088 |
ollow | -0.087 |
Token | Ar |
Token ID | 943 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
axter | +0.219 |
�� | +0.218 |
ioch | +0.215 |
theless | +0.214 |
arnaev | +0.212 |
Neg logit contributions | |
FAQ | -0.261 |
Bowman | -0.203 |
DG | -0.192 |
roots | -0.186 |
Dems | -0.184 |
Token | jen |
Token ID | 48796 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
axter | +0.069 |
�� | +0.069 |
ioch | +0.068 |
theless | +0.067 |
arnaev | +0.066 |
Neg logit contributions | |
FAQ | -0.102 |
Bowman | -0.081 |
DG | -0.077 |
roots | -0.075 |
ollow | -0.075 |
Token | Rob |
Token ID | 3851 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
axter | +0.902 |
�� | +0.901 |
theless | +0.890 |
ioch | +0.887 |
arnaev | +0.881 |
Neg logit contributions | |
FAQ | -1.943 |
Bowman | -1.615 |
DG | -1.534 |
Dems | -1.502 |
Bounty | -1.500 |
Token | ben |
Token ID | 11722 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
�� | +0.464 |
axter | +0.464 |
theless | +0.459 |
ioch | +0.457 |
arnaev | +0.452 |
Neg logit contributions | |
FAQ | -0.374 |
Bowman | -0.273 |
DG | -0.252 |
roots | -0.241 |
ollow | -0.240 |
Token | pushed |
Token ID | 7121 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
axter | +0.103 |
�� | +0.102 |
ioch | +0.101 |
theless | +0.101 |
arnaev | +0.100 |
Neg logit contributions | |
FAQ | -0.118 |
Bowman | -0.091 |
DG | -0.086 |
roots | -0.083 |
ollow | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
axter | +0.271 |
�� | +0.269 |
ioch | +0.266 |
theless | +0.265 |
arnaev | +0.262 |
Neg logit contributions | |
FAQ | -0.329 |
Bowman | -0.256 |
DG | -0.242 |
roots | -0.235 |
Dems | -0.233 |
Token | the |
Token ID | 262 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
axter | +0.162 |
�� | +0.161 |
ioch | +0.159 |
theless | +0.159 |
arnaev | +0.157 |
Neg logit contributions | |
FAQ | -0.192 |
Bowman | -0.149 |
DG | -0.140 |
roots | -0.136 |
ollow | -0.135 |
Token | requested |
Token ID | 9167 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
FAQ | +0.312 |
Bowman | +0.235 |
DG | +0.219 |
roots | +0.214 |
vae | +0.212 |
Neg logit contributions | |
axter | -0.314 |
�� | -0.312 |
ioch | -0.310 |
theless | -0.310 |
arnaev | -0.305 |
Token | putting |
Token ID | 5137 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
axter | +0.525 |
�� | +0.520 |
theless | +0.517 |
ioch | +0.513 |
arnaev | +0.506 |
Neg logit contributions | |
FAQ | -0.513 |
Bowman | -0.387 |
DG | -0.364 |
Dems | -0.349 |
roots | -0.349 |
Token | ally |
Token ID | 12525 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
axter | +0.061 |
�� | +0.060 |
ioch | +0.060 |
theless | +0.059 |
arnaev | +0.059 |
Neg logit contributions | |
FAQ | -0.062 |
Bowman | -0.047 |
DG | -0.044 |
roots | -0.042 |
ollow | -0.042 |
Token | in |
Token ID | 287 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
FAQ | +0.699 |
Bowman | +0.531 |
DG | +0.501 |
roots | +0.491 |
vae | +0.486 |
Neg logit contributions | |
axter | -0.610 |
ioch | -0.600 |
�� | -0.598 |
theless | -0.590 |
arnaev | -0.589 |
Token | charge |
Token ID | 3877 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
FAQ | +0.141 |
Bowman | +0.110 |
DG | +0.104 |
roots | +0.101 |
ollow | +0.100 |
Neg logit contributions | |
axter | -0.112 |
�� | -0.110 |
ioch | -0.110 |
theless | -0.109 |
arnaev | -0.108 |
Token | of |
Token ID | 286 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
axter | +0.402 |
�� | +0.401 |
ioch | +0.395 |
theless | +0.395 |
arnaev | +0.388 |
Neg logit contributions | |
FAQ | -0.436 |
Bowman | -0.334 |
DG | -0.316 |
roots | -0.305 |
Dems | -0.304 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
�� | +1.274 |
axter | +1.263 |
ioch | +1.235 |
theless | +1.233 |
arnaev | +1.207 |
Neg logit contributions | |
FAQ | -1.515 |
Bowman | -1.180 |
DG | -1.120 |
Dems | -1.092 |
roots | -1.076 |
Token | probe |
Token ID | 12774 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
FAQ | +0.080 |
Bowman | +0.061 |
DG | +0.057 |
roots | +0.055 |
ollow | +0.054 |
Neg logit contributions | |
axter | -0.080 |
�� | -0.080 |
ioch | -0.079 |
theless | -0.079 |
arnaev | -0.078 |
Token | : |
Token ID | 25 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
axter | +0.714 |
�� | +0.713 |
ioch | +0.702 |
theless | +0.698 |
arnaev | +0.685 |
Neg logit contributions | |
FAQ | -0.903 |
Bowman | -0.713 |
DG | -0.672 |
Dems | -0.663 |
ollow | -0.651 |
Token | report |
Token ID | 989 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
�� | +0.966 |
axter | +0.961 |
ioch | +0.946 |
theless | +0.942 |
arnaev | +0.937 |
Neg logit contributions | |
FAQ | -0.950 |
Bowman | -0.724 |
DG | -0.671 |
Dems | -0.659 |
roots | -0.650 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
FAQ | +0.111 |
Bowman | +0.081 |
DG | +0.075 |
roots | +0.072 |
ollow | +0.071 |
Neg logit contributions | |
axter | -0.135 |
�� | -0.134 |
ioch | -0.133 |
theless | -0.132 |
arnaev | -0.131 |
Token | on |
Token ID | 319 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
axter | +0.429 |
�� | +0.429 |
theless | +0.423 |
ioch | +0.422 |
arnaev | +0.415 |
Neg logit contributions | |
FAQ | -0.441 |
Bowman | -0.335 |
DG | -0.316 |
roots | -0.304 |
ollow | -0.302 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
FAQ | +0.204 |
Bowman | +0.163 |
DG | +0.155 |
roots | +0.152 |
vae | +0.151 |
Neg logit contributions | |
axter | -0.130 |
�� | -0.128 |
ioch | -0.128 |
theless | -0.127 |
arnaev | -0.125 |
Token |
|
Token ID | 198 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
axter | +0.157 |
�� | +0.156 |
ioch | +0.155 |
theless | +0.154 |
arnaev | +0.152 |
Neg logit contributions | |
FAQ | -0.181 |
Bowman | -0.140 |
DG | -0.132 |
roots | -0.128 |
ollow | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
axter | +0.204 |
�� | +0.203 |
ioch | +0.200 |
theless | +0.200 |
arnaev | +0.197 |
Neg logit contributions | |
FAQ | -0.233 |
Bowman | -0.180 |
DG | -0.170 |
roots | -0.165 |
ollow | -0.163 |
Token | NY |
Token ID | 12805 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
axter | +0.167 |
�� | +0.166 |
ioch | +0.164 |
theless | +0.164 |
arnaev | +0.162 |
Neg logit contributions | |
FAQ | -0.177 |
Bowman | -0.135 |
DG | -0.127 |
roots | -0.122 |
ollow | -0.121 |
Token | T |
Token ID | 51 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
axter | +0.086 |
�� | +0.086 |
ioch | +0.085 |
theless | +0.085 |
arnaev | +0.083 |
Neg logit contributions | |
FAQ | -0.094 |
Bowman | -0.072 |
DG | -0.067 |
roots | -0.065 |
ollow | -0.065 |
Token | Pick |
Token ID | 12346 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
�� | +1.130 |
axter | +1.121 |
theless | +1.104 |
ioch | +1.089 |
arnaev | +1.065 |
Neg logit contributions | |
FAQ | -1.630 |
Bowman | -1.312 |
DG | -1.254 |
roots | -1.208 |
Dems | -1.206 |
Token | J |
Token ID | 449 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
FAQ | +0.029 |
Bowman | +0.022 |
DG | +0.021 |
roots | +0.020 |
ollow | +0.020 |
Neg logit contributions | |
axter | -0.025 |
�� | -0.024 |
ioch | -0.024 |
theless | -0.024 |
arnaev | -0.024 |
Token | AB |
Token ID | 6242 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
axter | +0.010 |
�� | +0.010 |
ioch | +0.010 |
theless | +0.010 |
arnaev | +0.010 |
Neg logit contributions | |
FAQ | -0.011 |
Bowman | -0.008 |
DG | -0.008 |
roots | -0.007 |
ollow | -0.007 |
Token | arry |
Token ID | 6532 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
FAQ | +0.009 |
Bowman | +0.007 |
DG | +0.007 |
roots | +0.007 |
ollow | +0.006 |
Neg logit contributions | |
axter | -0.009 |
�� | -0.009 |
ioch | -0.009 |
theless | -0.009 |
arnaev | -0.009 |
Token | Maryland |
Token ID | 10769 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
FAQ | +0.130 |
Bowman | +0.100 |
DG | +0.094 |
roots | +0.091 |
vae | +0.091 |
Neg logit contributions | |
axter | -0.116 |
�� | -0.115 |
ioch | -0.114 |
theless | -0.114 |
arnaev | -0.112 |
Token | 16 |
Token ID | 1433 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
axter | +0.107 |
�� | +0.106 |
ioch | +0.105 |
theless | +0.104 |
arnaev | +0.103 |
Neg logit contributions | |
FAQ | -0.119 |
Bowman | -0.091 |
DG | -0.086 |
roots | -0.083 |
ollow | -0.083 |
Token | million |
Token ID | 1510 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
axter | +0.308 |
�� | +0.306 |
ioch | +0.302 |
theless | +0.302 |
arnaev | +0.297 |
Neg logit contributions | |
FAQ | -0.396 |
Bowman | -0.311 |
DG | -0.294 |
roots | -0.285 |
ollow | -0.283 |
Token | owed |
Token ID | 21057 |
Feature activation | -5.35e-03 |
Pos logit contributions | |
axter | +0.329 |
�� | +0.328 |
ioch | +0.323 |
theless | +0.323 |
arnaev | +0.318 |
Neg logit contributions | |
FAQ | -0.364 |
Bowman | -0.281 |
DG | -0.264 |
roots | -0.255 |
Dems | -0.254 |
Token | to |
Token ID | 284 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
axter | +0.004 |
�� | +0.004 |
ioch | +0.004 |
theless | +0.004 |
arnaev | +0.004 |
Neg logit contributions | |
FAQ | -0.004 |
Bowman | -0.003 |
DG | -0.003 |
roots | -0.003 |
ollow | -0.003 |
Token | Cameron |
Token ID | 10821 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
FAQ | +0.034 |
Bowman | +0.026 |
DG | +0.024 |
roots | +0.023 |
ollow | +0.023 |
Neg logit contributions | |
axter | -0.031 |
�� | -0.030 |
ioch | -0.030 |
theless | -0.030 |
arnaev | -0.030 |
Token | May |
Token ID | 1737 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
FAQ | +0.021 |
Bowman | +0.016 |
DG | +0.015 |
roots | +0.015 |
vae | +0.015 |
Neg logit contributions | |
axter | -0.014 |
�� | -0.014 |
ioch | -0.014 |
theless | -0.014 |
arnaev | -0.014 |
Token | bin |
Token ID | 8800 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
axter | +0.865 |
�� | +0.864 |
theless | +0.827 |
ioch | +0.822 |
arnaev | +0.812 |
Neg logit contributions | |
FAQ | -1.843 |
Bowman | -1.522 |
DG | -1.441 |
roots | -1.425 |
ollow | -1.419 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
FAQ | +0.127 |
Bowman | +0.097 |
DG | +0.092 |
roots | +0.089 |
vae | +0.088 |
Neg logit contributions | |
axter | -0.115 |
�� | -0.114 |
ioch | -0.113 |
theless | -0.112 |
arnaev | -0.111 |
Token | $ |
Token ID | 720 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
axter | +0.094 |
�� | +0.093 |
ioch | +0.092 |
theless | +0.092 |
arnaev | +0.091 |
Neg logit contributions | |
FAQ | -0.109 |
Bowman | -0.084 |
DG | -0.080 |
roots | -0.077 |
ollow | -0.077 |
Token | 8 |
Token ID | 23 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
axter | +0.097 |
�� | +0.096 |
ioch | +0.095 |
theless | +0.095 |
arnaev | +0.093 |
Neg logit contributions | |
FAQ | -0.114 |
Bowman | -0.089 |
DG | -0.084 |
roots | -0.081 |
ollow | -0.080 |
Token | million |
Token ID | 1510 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
axter | +0.066 |
�� | +0.065 |
ioch | +0.065 |
theless | +0.064 |
arnaev | +0.063 |
Neg logit contributions | |
FAQ | -0.090 |
Bowman | -0.071 |
DG | -0.068 |
roots | -0.066 |
ollow | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
FAQ | +0.045 |
Bowman | +0.035 |
DG | +0.033 |
roots | +0.032 |
ollow | +0.032 |
Neg logit contributions | |
axter | -0.040 |
�� | -0.040 |
ioch | -0.040 |
theless | -0.039 |
arnaev | -0.039 |
Token | oceans |
Token ID | 23744 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
FAQ | +0.292 |
Bowman | +0.226 |
DG | +0.213 |
roots | +0.207 |
ollow | +0.205 |
Neg logit contributions | |
axter | -0.248 |
�� | -0.244 |
ioch | -0.243 |
theless | -0.242 |
arnaev | -0.238 |
Token | - |
Token ID | 12 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
FAQ | +0.369 |
Bowman | +0.281 |
DG | +0.262 |
roots | +0.254 |
Dems | +0.252 |
Neg logit contributions | |
axter | -0.361 |
�� | -0.358 |
ioch | -0.355 |
theless | -0.353 |
arnaev | -0.349 |
Token | and |
Token ID | 392 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
axter | +0.068 |
�� | +0.067 |
ioch | +0.066 |
theless | +0.066 |
arnaev | +0.065 |
Neg logit contributions | |
FAQ | -0.113 |
Bowman | -0.091 |
DG | -0.087 |
roots | -0.085 |
ollow | -0.084 |
Token | - |
Token ID | 12 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
FAQ | +0.244 |
Bowman | +0.184 |
DG | +0.172 |
roots | +0.165 |
Dems | +0.164 |
Neg logit contributions | |
axter | -0.247 |
�� | -0.244 |
ioch | -0.244 |
theless | -0.242 |
arnaev | -0.239 |
Token | ree |
Token ID | 631 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
axter | +0.035 |
�� | +0.035 |
ioch | +0.034 |
theless | +0.034 |
arnaev | +0.033 |
Neg logit contributions | |
FAQ | -0.108 |
Bowman | -0.090 |
DG | -0.087 |
roots | -0.085 |
ollow | -0.085 |
Token | fs |
Token ID | 9501 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
�� | +1.251 |
axter | +1.219 |
theless | +1.211 |
arnaev | +1.191 |
ioch | +1.190 |
Neg logit contributions | |
FAQ | -1.458 |
Bowman | -1.120 |
roots | -1.069 |
DG | -1.058 |
vae | -1.053 |
Token | , |
Token ID | 11 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
FAQ | +0.162 |
Bowman | +0.125 |
DG | +0.117 |
roots | +0.113 |
ollow | +0.113 |
Neg logit contributions | |
axter | -0.143 |
�� | -0.142 |
ioch | -0.141 |
theless | -0.140 |
arnaev | -0.138 |
Token | water |
Token ID | 1660 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
FAQ | +0.208 |
Bowman | +0.161 |
DG | +0.152 |
roots | +0.147 |
ollow | +0.146 |
Neg logit contributions | |
axter | -0.176 |
�� | -0.173 |
ioch | -0.172 |
theless | -0.171 |
arnaev | -0.169 |
Token | - |
Token ID | 12 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
axter | +0.178 |
�� | +0.177 |
ioch | +0.175 |
theless | +0.175 |
arnaev | +0.172 |
Neg logit contributions | |
FAQ | -0.187 |
Bowman | -0.142 |
DG | -0.134 |
roots | -0.129 |
ollow | -0.128 |
Token | poll |
Token ID | 30393 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
axter | +0.333 |
�� | +0.332 |
ioch | +0.327 |
theless | +0.326 |
arnaev | +0.323 |
Neg logit contributions | |
FAQ | -0.339 |
Bowman | -0.256 |
DG | -0.241 |
roots | -0.234 |
vae | -0.231 |
Token | Center |
Token ID | 3337 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
axter | +0.143 |
�� | +0.142 |
ioch | +0.140 |
theless | +0.140 |
arnaev | +0.138 |
Neg logit contributions | |
FAQ | -0.153 |
Bowman | -0.117 |
DG | -0.110 |
roots | -0.106 |
ollow | -0.105 |
Token | for |
Token ID | 329 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
FAQ | +0.240 |
Bowman | +0.184 |
DG | +0.173 |
roots | +0.167 |
vae | +0.167 |
Neg logit contributions | |
axter | -0.217 |
�� | -0.215 |
ioch | -0.214 |
theless | -0.213 |
arnaev | -0.210 |
Token | Budget |
Token ID | 15401 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
FAQ | +0.093 |
Bowman | +0.072 |
DG | +0.068 |
roots | +0.066 |
vae | +0.066 |
Neg logit contributions | |
axter | -0.077 |
�� | -0.076 |
ioch | -0.075 |
theless | -0.075 |
arnaev | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
FAQ | +0.325 |
Bowman | +0.250 |
DG | +0.236 |
roots | +0.228 |
vae | +0.227 |
Neg logit contributions | |
axter | -0.288 |
�� | -0.285 |
ioch | -0.283 |
theless | -0.281 |
arnaev | -0.277 |
Token | Policy |
Token ID | 7820 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
FAQ | +0.209 |
Bowman | +0.164 |
DG | +0.154 |
roots | +0.150 |
vae | +0.149 |
Neg logit contributions | |
axter | -0.163 |
�� | -0.161 |
ioch | -0.160 |
theless | -0.159 |
arnaev | -0.156 |
Token | Prior |
Token ID | 14481 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
axter | +0.244 |
�� | +0.244 |
ioch | +0.239 |
theless | +0.238 |
arnaev | +0.234 |
Neg logit contributions | |
FAQ | -0.437 |
Bowman | -0.354 |
DG | -0.338 |
roots | -0.330 |
ollow | -0.328 |
Token | ities |
Token ID | 871 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
�� | +1.255 |
axter | +1.234 |
theless | +1.225 |
ioch | +1.211 |
arnaev | +1.201 |
Neg logit contributions | |
FAQ | -1.439 |
Bowman | -1.110 |
DG | -1.041 |
Dems | -1.016 |
roots | -1.015 |
Token | ( |
Token ID | 357 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
axter | +0.279 |
�� | +0.278 |
ioch | +0.274 |
theless | +0.273 |
arnaev | +0.269 |
Neg logit contributions | |
FAQ | -0.320 |
Bowman | -0.247 |
DG | -0.233 |
roots | -0.225 |
ollow | -0.224 |
Token | CB |
Token ID | 23199 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
axter | +0.217 |
�� | +0.216 |
ioch | +0.213 |
theless | +0.213 |
arnaev | +0.210 |
Neg logit contributions | |
FAQ | -0.197 |
Bowman | -0.147 |
DG | -0.137 |
roots | -0.132 |
ollow | -0.131 |
Token | PP |
Token ID | 10246 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
FAQ | +0.579 |
Bowman | +0.432 |
DG | +0.405 |
vae | +0.391 |
roots | +0.387 |
Neg logit contributions | |
axter | -0.654 |
ioch | -0.645 |
�� | -0.639 |
theless | -0.639 |
paren | -0.631 |
Token | ) |
Token ID | 8 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
axter | +0.067 |
�� | +0.066 |
ioch | +0.066 |
theless | +0.065 |
arnaev | +0.064 |
Neg logit contributions | |
FAQ | -0.076 |
Bowman | -0.058 |
DG | -0.055 |
roots | -0.053 |
ollow | -0.053 |
Token | Santos |
Token ID | 28458 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
axter | +0.369 |
�� | +0.368 |
ioch | +0.361 |
theless | +0.359 |
arnaev | +0.351 |
Neg logit contributions | |
FAQ | -0.626 |
Bowman | -0.507 |
DG | -0.482 |
roots | -0.470 |
Dems | -0.467 |
Token | and |
Token ID | 290 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
axter | +0.111 |
�� | +0.111 |
ioch | +0.109 |
theless | +0.109 |
arnaev | +0.107 |
Neg logit contributions | |
FAQ | -0.134 |
Bowman | -0.104 |
DG | -0.098 |
roots | -0.095 |
ollow | -0.095 |
Token | O |
Token ID | 440 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
axter | +0.288 |
�� | +0.286 |
ioch | +0.283 |
theless | +0.282 |
arnaev | +0.278 |
Neg logit contributions | |
FAQ | -0.353 |
Bowman | -0.275 |
DG | -0.260 |
roots | -0.252 |
Dems | -0.250 |
Token | ribe |
Token ID | 4892 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
FAQ | +0.166 |
Bowman | +0.124 |
DG | +0.116 |
roots | +0.112 |
Dems | +0.111 |
Neg logit contributions | |
axter | -0.179 |
�� | -0.178 |
ioch | -0.176 |
theless | -0.176 |
arnaev | -0.173 |
Token | P |
Token ID | 350 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
axter | +0.402 |
�� | +0.400 |
ioch | +0.394 |
theless | +0.393 |
arnaev | +0.388 |
Neg logit contributions | |
FAQ | -0.439 |
Bowman | -0.338 |
DG | -0.317 |
roots | -0.306 |
ollow | -0.304 |
Token | eral |
Token ID | 1691 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
FAQ | +0.037 |
Bowman | +0.027 |
DG | +0.025 |
roots | +0.024 |
Dems | +0.024 |
Neg logit contributions | |
axter | -0.045 |
�� | -0.044 |
ioch | -0.044 |
theless | -0.044 |
arnaev | -0.043 |
Token | ta |
Token ID | 8326 |
Feature activation | -6.34e-02 |
Pos logit contributions | |
�� | +0.508 |
axter | +0.504 |
theless | +0.484 |
ioch | +0.483 |
arnaev | +0.470 |
Neg logit contributions | |
FAQ | -2.148 |
Bowman | -1.825 |
DG | -1.764 |
roots | -1.731 |
vae | -1.730 |
Token | made |
Token ID | 925 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
axter | +0.041 |
�� | +0.040 |
ioch | +0.040 |
theless | +0.040 |
arnaev | +0.039 |
Neg logit contributions | |
FAQ | -0.051 |
Bowman | -0.040 |
DG | -0.038 |
roots | -0.037 |
ollow | -0.037 |
Token | dec |
Token ID | 875 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
axter | +0.091 |
�� | +0.090 |
ioch | +0.089 |
theless | +0.089 |
arnaev | +0.088 |
Neg logit contributions | |
FAQ | -0.107 |
Bowman | -0.083 |
DG | -0.078 |
roots | -0.076 |
ollow | -0.075 |
Token | oy |
Token ID | 726 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
�� | +0.586 |
axter | +0.586 |
theless | +0.575 |
ioch | +0.575 |
arnaev | +0.566 |
Neg logit contributions | |
FAQ | -0.729 |
Bowman | -0.568 |
DG | -0.535 |
roots | -0.521 |
ollow | -0.517 |
Token | runs |
Token ID | 4539 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
axter | +0.205 |
�� | +0.203 |
ioch | +0.200 |
theless | +0.200 |
arnaev | +0.197 |
Neg logit contributions | |
FAQ | -0.298 |
Bowman | -0.237 |
DG | -0.225 |
roots | -0.219 |
Dems | -0.217 |
Token | pan |
Token ID | 6839 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
axter | +0.001 |
�� | +0.001 |
ioch | +0.001 |
theless | +0.001 |
arnaev | +0.001 |
Neg logit contributions | |
FAQ | -0.004 |
Bowman | -0.004 |
DG | -0.004 |
roots | -0.003 |
ollow | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
FAQ | +0.171 |
Bowman | +0.130 |
DG | +0.122 |
roots | +0.118 |
vae | +0.118 |
Neg logit contributions | |
axter | -0.165 |
�� | -0.164 |
ioch | -0.162 |
theless | -0.162 |
arnaev | -0.159 |
Token | bring |
Token ID | 2222 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
axter | +0.050 |
�� | +0.049 |
ioch | +0.049 |
theless | +0.049 |
arnaev | +0.048 |
Neg logit contributions | |
FAQ | -0.067 |
Bowman | -0.053 |
DG | -0.050 |
roots | -0.049 |
ollow | -0.048 |
Token | it |
Token ID | 340 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
axter | +0.322 |
�� | +0.319 |
ioch | +0.316 |
theless | +0.315 |
arnaev | +0.311 |
Neg logit contributions | |
FAQ | -0.334 |
Bowman | -0.255 |
DG | -0.240 |
roots | -0.231 |
Dems | -0.229 |
Token | to |
Token ID | 284 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
axter | +0.468 |
�� | +0.465 |
ioch | +0.459 |
theless | +0.458 |
arnaev | +0.452 |
Neg logit contributions | |
FAQ | -0.476 |
Bowman | -0.363 |
DG | -0.340 |
roots | -0.328 |
ollow | -0.325 |
Token | a |
Token ID | 257 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
axter | +0.830 |
�� | +0.822 |
theless | +0.813 |
ioch | +0.810 |
arnaev | +0.803 |
Neg logit contributions | |
FAQ | -0.883 |
Bowman | -0.679 |
DG | -0.638 |
roots | -0.613 |
ollow | -0.610 |
Token | boil |
Token ID | 20667 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
axter | +1.062 |
�� | +1.043 |
theless | +1.029 |
ioch | +1.027 |
arnaev | +1.016 |
Neg logit contributions | |
FAQ | -1.582 |
Bowman | -1.275 |
DG | -1.200 |
roots | -1.162 |
atsu | -1.162 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
axter | +0.252 |
�� | +0.250 |
ioch | +0.248 |
theless | +0.247 |
arnaev | +0.244 |
Neg logit contributions | |
FAQ | -0.260 |
Bowman | -0.197 |
DG | -0.185 |
roots | -0.179 |
ollow | -0.177 |
Token | Once |
Token ID | 4874 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
axter | +0.096 |
�� | +0.095 |
ioch | +0.094 |
theless | +0.094 |
arnaev | +0.093 |
Neg logit contributions | |
FAQ | -0.109 |
Bowman | -0.084 |
DG | -0.079 |
roots | -0.076 |
ollow | -0.076 |
Token | its |
Token ID | 663 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
axter | +0.149 |
�� | +0.148 |
ioch | +0.146 |
theless | +0.146 |
arnaev | +0.144 |
Neg logit contributions | |
FAQ | -0.176 |
Bowman | -0.137 |
DG | -0.129 |
roots | -0.125 |
ollow | -0.124 |
Token | boiling |
Token ID | 24372 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
axter | +0.121 |
�� | +0.120 |
ioch | +0.119 |
theless | +0.118 |
arnaev | +0.117 |
Neg logit contributions | |
FAQ | -0.171 |
Bowman | -0.135 |
DG | -0.128 |
roots | -0.125 |
ollow | -0.124 |
Token | , |
Token ID | 11 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
axter | +0.115 |
�� | +0.114 |
ioch | +0.113 |
theless | +0.113 |
arnaev | +0.111 |
Neg logit contributions | |
FAQ | -0.129 |
Bowman | -0.099 |
DG | -0.093 |
roots | -0.090 |
ollow | -0.090 |
Token | d |
Token ID | 288 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
axter | +0.174 |
�� | +0.173 |
ioch | +0.171 |
theless | +0.170 |
arnaev | +0.168 |
Neg logit contributions | |
FAQ | -0.202 |
Bowman | -0.156 |
DG | -0.147 |
roots | -0.142 |
ollow | -0.141 |
Token | sle |
Token ID | 26738 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
�� | +0.457 |
axter | +0.456 |
ioch | +0.449 |
theless | +0.448 |
arnaev | +0.443 |
Neg logit contributions | |
FAQ | -0.489 |
Bowman | -0.373 |
DG | -0.351 |
roots | -0.340 |
ollow | -0.337 |
Token | et |
Token ID | 316 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
FAQ | +0.200 |
Bowman | +0.157 |
DG | +0.148 |
roots | +0.144 |
Dems | +0.143 |
Neg logit contributions | |
axter | -0.158 |
�� | -0.156 |
ioch | -0.155 |
theless | -0.154 |
arnaev | -0.152 |
Token | @ |
Token ID | 31 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
axter | +0.245 |
�� | +0.244 |
ioch | +0.242 |
theless | +0.242 |
arnaev | +0.239 |
Neg logit contributions | |
FAQ | -0.132 |
Bowman | -0.086 |
DG | -0.077 |
roots | -0.073 |
ollow | -0.071 |
Token | cd |
Token ID | 10210 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
axter | +0.151 |
�� | +0.150 |
ioch | +0.149 |
theless | +0.148 |
arnaev | +0.146 |
Neg logit contributions | |
FAQ | -0.155 |
Bowman | -0.118 |
DG | -0.111 |
roots | -0.107 |
ollow | -0.106 |
Token | c |
Token ID | 66 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
FAQ | +0.931 |
Bowman | +0.659 |
DG | +0.606 |
Bounty | +0.584 |
Dems | +0.573 |
Neg logit contributions | |
axter | -1.339 |
ioch | -1.325 |
theless | -1.294 |
�� | -1.287 |
paren | -1.285 |
Token | . |
Token ID | 13 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
axter | +0.357 |
�� | +0.357 |
theless | +0.351 |
ioch | +0.350 |
arnaev | +0.345 |
Neg logit contributions | |
FAQ | -0.381 |
Bowman | -0.291 |
DG | -0.274 |
roots | -0.266 |
ollow | -0.263 |
Token | gov |
Token ID | 9567 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
axter | +0.205 |
�� | +0.204 |
ioch | +0.200 |
theless | +0.199 |
arnaev | +0.195 |
Neg logit contributions | |
FAQ | -0.416 |
Bowman | -0.341 |
DG | -0.326 |
roots | -0.319 |
ollow | -0.317 |
Token | , |
Token ID | 11 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
axter | +0.237 |
�� | +0.235 |
ioch | +0.232 |
theless | +0.232 |
arnaev | +0.229 |
Neg logit contributions | |
FAQ | -0.269 |
Bowman | -0.207 |
DG | -0.196 |
roots | -0.189 |
ollow | -0.188 |
Token | 7 |
Token ID | 767 |
Feature activation | -7.06e-03 |
Pos logit contributions | |
axter | +0.141 |
�� | +0.140 |
ioch | +0.139 |
theless | +0.138 |
arnaev | +0.136 |
Neg logit contributions | |
FAQ | -0.156 |
Bowman | -0.120 |
DG | -0.113 |
roots | -0.109 |
ollow | -0.108 |
Token | to |
Token ID | 284 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
axter | +0.302 |
�� | +0.300 |
ioch | +0.297 |
theless | +0.296 |
arnaev | +0.292 |
Neg logit contributions | |
FAQ | -0.307 |
Bowman | -0.233 |
DG | -0.219 |
roots | -0.211 |
ollow | -0.210 |
Token | become |
Token ID | 1716 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
FAQ | +0.260 |
Bowman | +0.205 |
DG | +0.195 |
roots | +0.190 |
vae | +0.189 |
Neg logit contributions | |
axter | -0.188 |
�� | -0.186 |
ioch | -0.185 |
theless | -0.183 |
arnaev | -0.180 |
Token | an |
Token ID | 281 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
axter | +0.110 |
�� | +0.109 |
ioch | +0.108 |
theless | +0.107 |
arnaev | +0.106 |
Neg logit contributions | |
FAQ | -0.137 |
Bowman | -0.107 |
DG | -0.101 |
roots | -0.098 |
ollow | -0.098 |
Token | In |
Token ID | 554 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
FAQ | +0.026 |
Bowman | +0.020 |
DG | +0.019 |
roots | +0.018 |
ollow | +0.018 |
Neg logit contributions | |
axter | -0.023 |
�� | -0.022 |
ioch | -0.022 |
theless | -0.022 |
arnaev | -0.022 |
Token | Daily |
Token ID | 28545 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
axter | +0.339 |
�� | +0.338 |
ioch | +0.333 |
theless | +0.333 |
arnaev | +0.329 |
Neg logit contributions | |
FAQ | -0.303 |
Bowman | -0.224 |
DG | -0.209 |
roots | -0.202 |
ollow | -0.200 |
Token | supporter |
Token ID | 15525 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
axter | +0.034 |
�� | +0.034 |
ioch | +0.033 |
theless | +0.033 |
arnaev | +0.033 |
Neg logit contributions | |
FAQ | -0.040 |
Bowman | -0.031 |
DG | -0.029 |
roots | -0.028 |
vae | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
FAQ | +1.402 |
Bowman | +1.078 |
DG | +1.023 |
roots | +1.019 |
vae | +1.018 |
Neg logit contributions | |
axter | -1.106 |
ioch | -1.099 |
theless | -1.086 |
�� | -1.079 |
arnaev | -1.061 |
Token | Powered |
Token ID | 45090 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
FAQ | +1.404 |
Bowman | +1.070 |
DG | +1.018 |
roots | +1.015 |
vae | +1.008 |
Neg logit contributions | |
axter | -1.291 |
ioch | -1.268 |
�� | -1.248 |
theless | -1.246 |
arnaev | -1.239 |
Token | by |
Token ID | 416 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
FAQ | +0.035 |
Bowman | +0.027 |
DG | +0.025 |
roots | +0.024 |
vae | +0.024 |
Neg logit contributions | |
axter | -0.030 |
�� | -0.030 |
ioch | -0.029 |
theless | -0.029 |
arnaev | -0.029 |
Token | Press |
Token ID | 4332 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
FAQ | +0.197 |
Bowman | +0.130 |
DG | +0.116 |
roots | +0.111 |
vae | +0.110 |
Neg logit contributions | |
axter | -0.349 |
�� | -0.346 |
ioch | -0.345 |
theless | -0.344 |
arnaev | -0.340 |
Token | Pat |
Token ID | 12130 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
axter | +0.382 |
�� | +0.382 |
ioch | +0.377 |
theless | +0.376 |
arnaev | +0.371 |
Neg logit contributions | |
FAQ | -0.401 |
Bowman | -0.304 |
DG | -0.286 |
roots | -0.277 |
Dems | -0.275 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
FAQ | +0.527 |
Bowman | +0.411 |
DG | +0.391 |
roots | +0.381 |
ollow | +0.379 |
Neg logit contributions | |
axter | -0.380 |
�� | -0.374 |
theless | -0.368 |
ioch | -0.367 |
arnaev | -0.365 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
FAQ | +0.474 |
Bowman | +0.373 |
DG | +0.356 |
roots | +0.345 |
ollow | +0.343 |
Neg logit contributions | |
axter | -0.340 |
�� | -0.335 |
theless | -0.332 |
ioch | -0.330 |
arnaev | -0.326 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
FAQ | +0.285 |
Bowman | +0.219 |
DG | +0.206 |
roots | +0.198 |
ollow | +0.197 |
Neg logit contributions | |
axter | -0.271 |
�� | -0.267 |
ioch | -0.265 |
theless | -0.264 |
arnaev | -0.261 |
Token | : |
Token ID | 25 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
FAQ | +0.346 |
Bowman | +0.275 |
DG | +0.261 |
roots | +0.254 |
ollow | +0.253 |
Neg logit contributions | |
axter | -0.237 |
�� | -0.232 |
ioch | -0.231 |
theless | -0.231 |
arnaev | -0.227 |
Token | ' |
Token ID | 705 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
FAQ | +0.343 |
Bowman | +0.261 |
DG | +0.247 |
roots | +0.239 |
vae | +0.239 |
Neg logit contributions | |
axter | -0.301 |
�� | -0.295 |
ioch | -0.295 |
theless | -0.295 |
arnaev | -0.291 |
Token | I |
Token ID | 40 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
FAQ | +2.081 |
Bowman | +1.610 |
DG | +1.558 |
vae | +1.511 |
ollow | +1.486 |
Neg logit contributions | |
axter | -1.798 |
theless | -1.722 |
ioch | -1.721 |
�� | -1.668 |
paren | -1.666 |
Token | fully |
Token ID | 3938 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
FAQ | +1.371 |
Bowman | +1.069 |
DG | +1.023 |
roots | +1.002 |
atsu | +0.985 |
Neg logit contributions | |
axter | -1.071 |
theless | -1.042 |
ioch | -1.041 |
�� | -1.030 |
arnaev | -1.029 |
Token | expect |
Token ID | 1607 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
FAQ | +0.767 |
Bowman | +0.596 |
DG | +0.567 |
roots | +0.554 |
ollow | +0.548 |
Neg logit contributions | |
axter | -0.585 |
�� | -0.570 |
ioch | -0.568 |
theless | -0.563 |
arnaev | -0.557 |
Token | ' |
Token ID | 6 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
axter | +0.006 |
�� | +0.006 |
ioch | +0.006 |
theless | +0.006 |
arnaev | +0.006 |
Neg logit contributions | |
FAQ | -0.012 |
Bowman | -0.010 |
DG | -0.009 |
roots | -0.009 |
vae | -0.009 |
Token | fair |
Token ID | 3148 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
FAQ | +0.459 |
Bowman | +0.355 |
DG | +0.336 |
roots | +0.328 |
ollow | +0.327 |
Neg logit contributions | |
axter | -0.372 |
�� | -0.370 |
ioch | -0.366 |
theless | -0.366 |
arnaev | -0.360 |
Token | treatment |
Token ID | 3513 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
FAQ | +0.534 |
Bowman | +0.383 |
DG | +0.360 |
vae | +0.346 |
roots | +0.345 |
Neg logit contributions | |
axter | -0.622 |
ioch | -0.617 |
�� | -0.615 |
theless | -0.607 |
arnaev | -0.603 |
Token | Diane |
Token ID | 26542 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
axter | +0.041 |
�� | +0.041 |
ioch | +0.040 |
theless | +0.040 |
arnaev | +0.040 |
Neg logit contributions | |
FAQ | -0.034 |
Bowman | -0.024 |
DG | -0.023 |
roots | -0.022 |
ollow | -0.022 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
FAQ | +0.527 |
Bowman | +0.411 |
DG | +0.391 |
roots | +0.381 |
ollow | +0.379 |
Neg logit contributions | |
axter | -0.380 |
�� | -0.374 |
theless | -0.368 |
ioch | -0.367 |
arnaev | -0.365 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
FAQ | +0.474 |
Bowman | +0.373 |
DG | +0.356 |
roots | +0.345 |
ollow | +0.343 |
Neg logit contributions | |
axter | -0.340 |
�� | -0.335 |
theless | -0.332 |
ioch | -0.330 |
arnaev | -0.326 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
FAQ | +0.285 |
Bowman | +0.219 |
DG | +0.206 |
roots | +0.198 |
ollow | +0.197 |
Neg logit contributions | |
axter | -0.271 |
�� | -0.267 |
ioch | -0.265 |
theless | -0.264 |
arnaev | -0.261 |
Token | : |
Token ID | 25 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
FAQ | +0.346 |
Bowman | +0.275 |
DG | +0.261 |
roots | +0.254 |
ollow | +0.253 |
Neg logit contributions | |
axter | -0.237 |
�� | -0.232 |
ioch | -0.231 |
theless | -0.231 |
arnaev | -0.227 |
Token | ' |
Token ID | 705 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
FAQ | +0.343 |
Bowman | +0.261 |
DG | +0.247 |
roots | +0.239 |
vae | +0.239 |
Neg logit contributions | |
axter | -0.301 |
�� | -0.295 |
ioch | -0.295 |
theless | -0.295 |
arnaev | -0.291 |
Token | I |
Token ID | 40 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
FAQ | +2.081 |
Bowman | +1.610 |
DG | +1.558 |
vae | +1.511 |
ollow | +1.486 |
Neg logit contributions | |
axter | -1.798 |
theless | -1.722 |
ioch | -1.721 |
�� | -1.668 |
paren | -1.666 |
Token | fully |
Token ID | 3938 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
FAQ | +1.371 |
Bowman | +1.069 |
DG | +1.023 |
roots | +1.002 |
atsu | +0.985 |
Neg logit contributions | |
axter | -1.071 |
theless | -1.042 |
ioch | -1.041 |
�� | -1.030 |
arnaev | -1.029 |
Token | expect |
Token ID | 1607 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
FAQ | +0.767 |
Bowman | +0.596 |
DG | +0.567 |
roots | +0.554 |
ollow | +0.548 |
Neg logit contributions | |
axter | -0.585 |
�� | -0.570 |
ioch | -0.568 |
theless | -0.563 |
arnaev | -0.557 |
Token | ' |
Token ID | 6 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
axter | +0.006 |
�� | +0.006 |
ioch | +0.006 |
theless | +0.006 |
arnaev | +0.006 |
Neg logit contributions | |
FAQ | -0.012 |
Bowman | -0.010 |
DG | -0.009 |
roots | -0.009 |
vae | -0.009 |
Token | fair |
Token ID | 3148 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
FAQ | +0.459 |
Bowman | +0.355 |
DG | +0.336 |
roots | +0.328 |
ollow | +0.327 |
Neg logit contributions | |
axter | -0.372 |
�� | -0.370 |
ioch | -0.366 |
theless | -0.366 |
arnaev | -0.360 |
Token | - |
Token ID | 12 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
FAQ | +0.594 |
Bowman | +0.451 |
DG | +0.421 |
roots | +0.406 |
vae | +0.404 |
Neg logit contributions | |
axter | -0.592 |
ioch | -0.584 |
�� | -0.583 |
theless | -0.580 |
arnaev | -0.572 |
Token | the |
Token ID | 1169 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
FAQ | +0.288 |
Bowman | +0.224 |
DG | +0.212 |
roots | +0.204 |
ollow | +0.203 |
Neg logit contributions | |
axter | -0.244 |
�� | -0.241 |
ioch | -0.240 |
theless | -0.239 |
arnaev | -0.235 |
Token | - |
Token ID | 12 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
FAQ | +0.376 |
Bowman | +0.284 |
DG | +0.266 |
roots | +0.256 |
vae | +0.255 |
Neg logit contributions | |
axter | -0.380 |
�� | -0.375 |
ioch | -0.374 |
theless | -0.372 |
arnaev | -0.368 |
Token | trans |
Token ID | 7645 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
FAQ | +0.246 |
Bowman | +0.191 |
DG | +0.181 |
roots | +0.174 |
ollow | +0.173 |
Neg logit contributions | |
axter | -0.210 |
�� | -0.208 |
ioch | -0.206 |
theless | -0.205 |
arnaev | -0.202 |
Token | - |
Token ID | 12 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
FAQ | +0.012 |
Bowman | +0.009 |
DG | +0.008 |
roots | +0.008 |
vae | +0.008 |
Neg logit contributions | |
axter | -0.010 |
�� | -0.010 |
ioch | -0.010 |
theless | -0.010 |
arnaev | -0.010 |
Token | pac |
Token ID | 33587 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
axter | +0.162 |
�� | +0.161 |
ioch | +0.159 |
theless | +0.158 |
arnaev | +0.156 |
Neg logit contributions | |
FAQ | -0.235 |
Bowman | -0.187 |
DG | -0.177 |
roots | -0.173 |
ollow | -0.171 |
Token | ific |
Token ID | 811 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
FAQ | +1.144 |
Bowman | +0.817 |
DG | +0.765 |
vae | +0.728 |
Bounty | +0.716 |
Neg logit contributions | |
axter | -1.576 |
ioch | -1.557 |
theless | -1.528 |
arnaev | -1.518 |
�� | -1.508 |
Token | ... |
Token ID | 986 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
FAQ | +0.240 |
Bowman | +0.181 |
DG | +0.169 |
roots | +0.163 |
vae | +0.162 |
Neg logit contributions | |
axter | -0.243 |
�� | -0.240 |
ioch | -0.239 |
theless | -0.238 |
arnaev | -0.235 |
Token | Flag |
Token ID | 19762 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
FAQ | +0.166 |
Bowman | +0.127 |
DG | +0.120 |
roots | +0.116 |
vae | +0.115 |
Neg logit contributions | |
axter | -0.152 |
�� | -0.151 |
ioch | -0.149 |
theless | -0.149 |
arnaev | -0.147 |
Token |
|
Token ID | 198 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
axter | +0.120 |
�� | +0.119 |
ioch | +0.117 |
theless | +0.117 |
arnaev | +0.115 |
Neg logit contributions | |
FAQ | -0.137 |
Bowman | -0.106 |
DG | -0.100 |
roots | -0.097 |
ollow | -0.096 |
Token |
|
Token ID | 198 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
axter | +0.184 |
�� | +0.183 |
ioch | +0.180 |
theless | +0.180 |
arnaev | +0.177 |
Neg logit contributions | |
FAQ | -0.211 |
Bowman | -0.163 |
DG | -0.154 |
roots | -0.149 |
ollow | -0.148 |
Token | much |
Token ID | 881 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
axter | +0.059 |
�� | +0.059 |
ioch | +0.058 |
theless | +0.058 |
arnaev | +0.057 |
Neg logit contributions | |
FAQ | -0.067 |
Bowman | -0.052 |
DG | -0.049 |
roots | -0.047 |
ollow | -0.047 |
Token | larger |
Token ID | 4025 |
Feature activation | -3.07e-03 |
Pos logit contributions | |
axter | +0.413 |
�� | +0.411 |
ioch | +0.406 |
theless | +0.404 |
arnaev | +0.400 |
Neg logit contributions | |
FAQ | -0.445 |
Bowman | -0.341 |
DG | -0.320 |
roots | -0.310 |
Dems | -0.307 |
Token | than |
Token ID | 621 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
axter | +0.002 |
�� | +0.002 |
ioch | +0.002 |
theless | +0.002 |
arnaev | +0.002 |
Neg logit contributions | |
FAQ | -0.002 |
Bowman | -0.002 |
DG | -0.002 |
roots | -0.002 |
ollow | -0.002 |
Token | merely |
Token ID | 6974 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
axter | +0.199 |
�� | +0.198 |
ioch | +0.196 |
theless | +0.195 |
arnaev | +0.193 |
Neg logit contributions | |
FAQ | -0.229 |
Bowman | -0.177 |
DG | -0.167 |
roots | -0.162 |
Dems | -0.161 |
Token | a |
Token ID | 257 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
axter | +0.075 |
�� | +0.074 |
ioch | +0.073 |
theless | +0.073 |
arnaev | +0.072 |
Neg logit contributions | |
FAQ | -0.083 |
Bowman | -0.064 |
DG | -0.060 |
roots | -0.058 |
ollow | -0.058 |
Token | fight |
Token ID | 1907 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
axter | +0.053 |
�� | +0.052 |
ioch | +0.052 |
theless | +0.052 |
arnaev | +0.051 |
Neg logit contributions | |
FAQ | -0.068 |
Bowman | -0.053 |
DG | -0.051 |
roots | -0.049 |
ollow | -0.049 |
Token | over |
Token ID | 625 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
FAQ | +0.199 |
Bowman | +0.152 |
DG | +0.143 |
roots | +0.139 |
vae | +0.138 |
Neg logit contributions | |
axter | -0.181 |
�� | -0.179 |
ioch | -0.178 |
theless | -0.177 |
arnaev | -0.174 |
Token | a |
Token ID | 257 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
FAQ | +0.168 |
Bowman | +0.128 |
DG | +0.120 |
roots | +0.117 |
ollow | +0.116 |
Neg logit contributions | |
axter | -0.154 |
�� | -0.152 |
ioch | -0.151 |
theless | -0.151 |
arnaev | -0.148 |
Token | city |
Token ID | 1748 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
FAQ | +0.160 |
Bowman | +0.123 |
DG | +0.115 |
roots | +0.112 |
vae | +0.111 |
Neg logit contributions | |
axter | -0.144 |
�� | -0.143 |
ioch | -0.141 |
theless | -0.141 |
arnaev | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
FAQ | +0.145 |
Bowman | +0.111 |
DG | +0.105 |
roots | +0.102 |
vae | +0.101 |
Neg logit contributions | |
axter | -0.129 |
�� | -0.128 |
ioch | -0.127 |
theless | -0.127 |
arnaev | -0.125 |
Token | This |
Token ID | 770 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
FAQ | +0.127 |
Bowman | +0.098 |
DG | +0.092 |
roots | +0.089 |
vae | +0.089 |
Neg logit contributions | |
axter | -0.112 |
�� | -0.111 |
ioch | -0.110 |
theless | -0.110 |
arnaev | -0.108 |
Token | rain |
Token ID | 6290 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
axter | +0.016 |
�� | +0.016 |
ioch | +0.016 |
theless | +0.016 |
arnaev | +0.015 |
Neg logit contributions | |
FAQ | -0.018 |
Bowman | -0.014 |
DG | -0.013 |
roots | -0.013 |
ollow | -0.013 |
Token | bows |
Token ID | 25435 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
FAQ | +0.147 |
Bowman | +0.068 |
DG | +0.052 |
roots | +0.044 |
vae | +0.043 |
Neg logit contributions | |
axter | -0.500 |
�� | -0.496 |
ioch | -0.495 |
theless | -0.494 |
arnaev | -0.489 |
Token | , |
Token ID | 11 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
FAQ | +0.141 |
Bowman | +0.108 |
DG | +0.102 |
roots | +0.099 |
ollow | +0.098 |
Neg logit contributions | |
axter | -0.123 |
�� | -0.122 |
ioch | -0.120 |
theless | -0.120 |
arnaev | -0.118 |
Token | � |
Token ID | 447 |
Feature activation | +9.32e-02 |
Pos logit contributions | |
FAQ | +0.254 |
Bowman | +0.195 |
DG | +0.183 |
roots | +0.177 |
ollow | +0.176 |
Neg logit contributions | |
axter | -0.232 |
�� | -0.230 |
ioch | -0.228 |
theless | -0.227 |
arnaev | -0.224 |
Token | � |
Token ID | 251 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
FAQ | +0.061 |
Bowman | +0.045 |
DG | +0.042 |
roots | +0.040 |
ollow | +0.040 |
Neg logit contributions | |
axter | -0.074 |
�� | -0.074 |
ioch | -0.073 |
theless | -0.073 |
arnaev | -0.072 |
Token | their |
Token ID | 511 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
FAQ | +0.192 |
Bowman | +0.148 |
DG | +0.139 |
roots | +0.135 |
ollow | +0.134 |
Neg logit contributions | |
axter | -0.170 |
�� | -0.168 |
ioch | -0.166 |
theless | -0.166 |
arnaev | -0.163 |
Token | children |
Token ID | 1751 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
FAQ | +0.266 |
Bowman | +0.205 |
DG | +0.194 |
roots | +0.188 |
ollow | +0.187 |
Neg logit contributions | |
axter | -0.227 |
�� | -0.225 |
ioch | -0.223 |
theless | -0.222 |
arnaev | -0.219 |
Token | � |
Token ID | 447 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
FAQ | +0.064 |
Bowman | +0.049 |
DG | +0.046 |
roots | +0.045 |
ollow | +0.044 |
Neg logit contributions | |
axter | -0.058 |
�� | -0.058 |
ioch | -0.057 |
theless | -0.057 |
arnaev | -0.056 |
Token | � |
Token ID | 247 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
axter | +0.012 |
�� | +0.012 |
ioch | +0.012 |
theless | +0.012 |
arnaev | +0.012 |
Neg logit contributions | |
FAQ | -0.011 |
Bowman | -0.008 |
DG | -0.008 |
roots | -0.007 |
ollow | -0.007 |
Token | s |
Token ID | 82 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
FAQ | +0.061 |
Bowman | +0.047 |
DG | +0.044 |
roots | +0.043 |
ollow | +0.043 |
Neg logit contributions | |
axter | -0.054 |
�� | -0.054 |
ioch | -0.053 |
theless | -0.053 |
arnaev | -0.052 |
Token | birth |
Token ID | 4082 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
FAQ | +0.029 |
Bowman | +0.023 |
DG | +0.021 |
roots | +0.021 |
ollow | +0.021 |
Neg logit contributions | |
axter | -0.025 |
�� | -0.025 |
ioch | -0.025 |
theless | -0.025 |
arnaev | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
FAQ | +0.192 |
Bowman | +0.148 |
DG | +0.140 |
roots | +0.136 |
vae | +0.135 |
Neg logit contributions | |
axter | -0.163 |
�� | -0.162 |
ioch | -0.160 |
theless | -0.160 |
arnaev | -0.157 |
Token | elect |
Token ID | 1742 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
FAQ | +0.283 |
Bowman | +0.221 |
DG | +0.209 |
roots | +0.204 |
vae | +0.203 |
Neg logit contributions | |
axter | -0.220 |
�� | -0.218 |
ioch | -0.216 |
theless | -0.215 |
arnaev | -0.211 |
Token | roph |
Token ID | 10051 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
axter | +0.136 |
�� | +0.135 |
ioch | +0.134 |
theless | +0.133 |
arnaev | +0.132 |
Neg logit contributions | |
FAQ | -0.106 |
Bowman | -0.076 |
DG | -0.070 |
roots | -0.067 |
ollow | -0.067 |
Token | ys |
Token ID | 893 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
axter | +0.283 |
�� | +0.281 |
ioch | +0.276 |
theless | +0.276 |
arnaev | +0.271 |
Neg logit contributions | |
FAQ | -0.422 |
Bowman | -0.335 |
DG | -0.319 |
roots | -0.310 |
ollow | -0.308 |
Token | iological |
Token ID | 15071 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
axter | +0.082 |
�� | +0.081 |
ioch | +0.080 |
theless | +0.080 |
arnaev | +0.078 |
Neg logit contributions | |
FAQ | -0.150 |
Bowman | -0.122 |
DG | -0.116 |
roots | -0.113 |
ollow | -0.113 |
Token | procedures |
Token ID | 9021 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
FAQ | +0.201 |
Bowman | +0.155 |
DG | +0.146 |
roots | +0.143 |
vae | +0.142 |
Neg logit contributions | |
axter | -0.169 |
�� | -0.167 |
ioch | -0.166 |
theless | -0.165 |
arnaev | -0.162 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
FAQ | +0.208 |
Bowman | +0.159 |
DG | +0.149 |
roots | +0.145 |
vae | +0.144 |
Neg logit contributions | |
axter | -0.193 |
�� | -0.192 |
ioch | -0.190 |
theless | -0.189 |
arnaev | -0.187 |
Token | This |
Token ID | 770 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
FAQ | +0.095 |
Bowman | +0.073 |
DG | +0.069 |
roots | +0.067 |
vae | +0.066 |
Neg logit contributions | |
axter | -0.084 |
�� | -0.083 |
ioch | -0.082 |
theless | -0.082 |
arnaev | -0.081 |
Token | paper |
Token ID | 3348 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
FAQ | +0.219 |
Bowman | +0.169 |
DG | +0.159 |
roots | +0.155 |
vae | +0.154 |
Neg logit contributions | |
axter | -0.186 |
�� | -0.184 |
ioch | -0.183 |
theless | -0.182 |
arnaev | -0.179 |
Token | presents |
Token ID | 10969 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
axter | +0.170 |
�� | +0.169 |
ioch | +0.167 |
theless | +0.166 |
arnaev | +0.164 |
Neg logit contributions | |
FAQ | -0.198 |
Bowman | -0.153 |
DG | -0.144 |
roots | -0.140 |
ollow | -0.139 |
Token | behavioral |
Token ID | 17211 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
FAQ | +0.026 |
Bowman | +0.020 |
DG | +0.019 |
roots | +0.019 |
vae | +0.018 |
Neg logit contributions | |
axter | -0.023 |
�� | -0.023 |
ioch | -0.023 |
theless | -0.023 |
arnaev | -0.023 |
Token | effects |
Token ID | 3048 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
axter | +0.198 |
�� | +0.196 |
ioch | +0.194 |
theless | +0.194 |
arnaev | +0.191 |
Neg logit contributions | |
FAQ | -0.207 |
Bowman | -0.158 |
DG | -0.148 |
roots | -0.143 |
ollow | -0.142 |
Token | some |
Token ID | 617 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
axter | +0.127 |
�� | +0.126 |
ioch | +0.125 |
theless | +0.124 |
arnaev | +0.123 |
Neg logit contributions | |
FAQ | -0.140 |
Bowman | -0.108 |
DG | -0.101 |
roots | -0.098 |
ollow | -0.097 |
Token | what |
Token ID | 644 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
FAQ | +0.152 |
Bowman | +0.117 |
DG | +0.110 |
roots | +0.107 |
vae | +0.106 |
Neg logit contributions | |
axter | -0.135 |
�� | -0.134 |
ioch | -0.132 |
theless | -0.132 |
arnaev | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
axter | +0.101 |
�� | +0.100 |
ioch | +0.099 |
theless | +0.099 |
arnaev | +0.098 |
Neg logit contributions | |
FAQ | -0.112 |
Bowman | -0.086 |
DG | -0.081 |
roots | -0.079 |
ollow | -0.078 |
Token | Some |
Token ID | 2773 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
FAQ | +0.024 |
Bowman | +0.019 |
DG | +0.017 |
roots | +0.017 |
vae | +0.017 |
Neg logit contributions | |
axter | -0.021 |
�� | -0.021 |
ioch | -0.021 |
theless | -0.021 |
arnaev | -0.020 |
Token | people |
Token ID | 661 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
FAQ | +0.034 |
Bowman | +0.026 |
DG | +0.025 |
roots | +0.024 |
vae | +0.024 |
Neg logit contributions | |
axter | -0.031 |
�� | -0.031 |
ioch | -0.031 |
theless | -0.031 |
arnaev | -0.030 |
Token | just |
Token ID | 655 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
FAQ | +0.187 |
Bowman | +0.146 |
DG | +0.138 |
roots | +0.134 |
vae | +0.133 |
Neg logit contributions | |
axter | -0.152 |
�� | -0.150 |
theless | -0.149 |
ioch | -0.149 |
arnaev | -0.146 |
Token | chew |
Token ID | 34722 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
axter | +0.088 |
�� | +0.087 |
ioch | +0.086 |
theless | +0.086 |
arnaev | +0.085 |
Neg logit contributions | |
FAQ | -0.114 |
Bowman | -0.089 |
DG | -0.085 |
roots | -0.082 |
ollow | -0.081 |
Token | them |
Token ID | 606 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
axter | +0.367 |
�� | +0.366 |
ioch | +0.361 |
theless | +0.360 |
arnaev | +0.355 |
Neg logit contributions | |
FAQ | -0.415 |
Bowman | -0.319 |
DG | -0.301 |
roots | -0.292 |
ollow | -0.289 |
Token | up |
Token ID | 510 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
axter | +0.287 |
�� | +0.286 |
ioch | +0.282 |
theless | +0.281 |
arnaev | +0.277 |
Neg logit contributions | |
FAQ | -0.320 |
Bowman | -0.246 |
DG | -0.232 |
roots | -0.225 |
ollow | -0.223 |
Token | and |
Token ID | 290 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
axter | +0.112 |
�� | +0.112 |
ioch | +0.110 |
theless | +0.110 |
arnaev | +0.108 |
Neg logit contributions | |
FAQ | -0.126 |
Bowman | -0.097 |
DG | -0.091 |
roots | -0.088 |
ollow | -0.088 |
Token | 's |
Token ID | 338 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
axter | +0.267 |
�� | +0.265 |
ioch | +0.262 |
theless | +0.262 |
arnaev | +0.258 |
Neg logit contributions | |
FAQ | -0.251 |
Bowman | -0.188 |
DG | -0.176 |
roots | -0.170 |
vae | -0.168 |
Token | lawsuit |
Token ID | 8087 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
axter | +0.062 |
�� | +0.061 |
ioch | +0.060 |
theless | +0.060 |
arnaev | +0.059 |
Neg logit contributions | |
FAQ | -0.087 |
Bowman | -0.069 |
DG | -0.065 |
roots | -0.064 |
ollow | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
axter | +0.017 |
�� | +0.016 |
ioch | +0.016 |
theless | +0.016 |
arnaev | +0.016 |
Neg logit contributions | |
FAQ | -0.019 |
Bowman | -0.014 |
DG | -0.014 |
roots | -0.013 |
ollow | -0.013 |
Token | said |
Token ID | 531 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
FAQ | +0.118 |
Bowman | +0.089 |
DG | +0.083 |
roots | +0.081 |
ollow | +0.080 |
Neg logit contributions | |
axter | -0.118 |
�� | -0.117 |
ioch | -0.116 |
theless | -0.116 |
arnaev | -0.114 |
Token | he |
Token ID | 339 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
FAQ | +0.184 |
Bowman | +0.142 |
DG | +0.133 |
roots | +0.130 |
ollow | +0.128 |
Neg logit contributions | |
axter | -0.162 |
�� | -0.160 |
ioch | -0.159 |
theless | -0.158 |
arnaev | -0.156 |
Token | could |
Token ID | 714 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
FAQ | +0.044 |
Bowman | +0.034 |
DG | +0.032 |
roots | +0.031 |
ollow | +0.031 |
Neg logit contributions | |
axter | -0.037 |
�� | -0.036 |
ioch | -0.036 |
theless | -0.036 |
arnaev | -0.035 |
Token | not |
Token ID | 407 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
FAQ | +0.400 |
Bowman | +0.312 |
DG | +0.295 |
roots | +0.287 |
ollow | +0.284 |
Neg logit contributions | |
axter | -0.318 |
�� | -0.314 |
ioch | -0.311 |
theless | -0.309 |
arnaev | -0.305 |
Token | comment |
Token ID | 2912 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
FAQ | +0.277 |
Bowman | +0.215 |
DG | +0.203 |
roots | +0.197 |
ollow | +0.196 |
Neg logit contributions | |
axter | -0.226 |
�� | -0.223 |
ioch | -0.221 |
theless | -0.221 |
arnaev | -0.217 |
Token | because |
Token ID | 780 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
FAQ | +0.097 |
Bowman | +0.075 |
DG | +0.070 |
roots | +0.068 |
ollow | +0.068 |
Neg logit contributions | |
axter | -0.084 |
�� | -0.083 |
ioch | -0.083 |
theless | -0.082 |
arnaev | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
FAQ | +0.154 |
Bowman | +0.118 |
DG | +0.111 |
roots | +0.108 |
vae | +0.107 |
Neg logit contributions | |
axter | -0.136 |
�� | -0.135 |
ioch | -0.134 |
theless | -0.133 |
arnaev | -0.131 |
Token | settlement |
Token ID | 9443 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
FAQ | +0.090 |
Bowman | +0.071 |
DG | +0.067 |
roots | +0.065 |
ollow | +0.065 |
Neg logit contributions | |
axter | -0.067 |
�� | -0.067 |
ioch | -0.066 |
theless | -0.066 |
arnaev | -0.065 |
Token | ][ |
Token ID | 7131 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
axter | +0.086 |
�� | +0.086 |
ioch | +0.085 |
theless | +0.085 |
arnaev | +0.084 |
Neg logit contributions | |
FAQ | -0.080 |
Bowman | -0.060 |
DG | -0.056 |
roots | -0.054 |
ollow | -0.053 |
Token | 8 |
Token ID | 23 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
FAQ | +0.169 |
Bowman | +0.127 |
DG | +0.119 |
roots | +0.115 |
Dems | +0.114 |
Neg logit contributions | |
axter | -0.175 |
�� | -0.173 |
ioch | -0.172 |
theless | -0.171 |
arnaev | -0.169 |
Token | ] |
Token ID | 60 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
axter | +0.093 |
�� | +0.093 |
ioch | +0.092 |
theless | +0.092 |
arnaev | +0.090 |
Neg logit contributions | |
FAQ | -0.088 |
Bowman | -0.066 |
DG | -0.062 |
roots | -0.060 |
ollow | -0.059 |
Token | W |
Token ID | 370 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
axter | +0.033 |
�� | +0.033 |
ioch | +0.032 |
theless | +0.032 |
arnaev | +0.032 |
Neg logit contributions | |
FAQ | -0.038 |
Bowman | -0.029 |
DG | -0.027 |
roots | -0.027 |
ollow | -0.026 |
Token | EP |
Token ID | 8905 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
FAQ | +0.166 |
Bowman | +0.126 |
DG | +0.119 |
roots | +0.115 |
Bounty | +0.114 |
Neg logit contributions | |
axter | -0.160 |
�� | -0.159 |
ioch | -0.158 |
theless | -0.157 |
arnaev | -0.155 |
Token | uses |
Token ID | 3544 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
axter | +0.108 |
�� | +0.108 |
ioch | +0.107 |
theless | +0.106 |
arnaev | +0.105 |
Neg logit contributions | |
FAQ | -0.121 |
Bowman | -0.093 |
DG | -0.087 |
roots | -0.085 |
ollow | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
axter | +0.020 |
�� | +0.019 |
ioch | +0.019 |
theless | +0.019 |
arnaev | +0.019 |
Neg logit contributions | |
FAQ | -0.023 |
Bowman | -0.018 |
DG | -0.017 |
roots | -0.016 |
ollow | -0.016 |
Token | stream |
Token ID | 4269 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
axter | +0.263 |
�� | +0.261 |
ioch | +0.258 |
theless | +0.257 |
arnaev | +0.253 |
Neg logit contributions | |
FAQ | -0.365 |
Bowman | -0.288 |
DG | -0.274 |
roots | -0.266 |
Dems | -0.264 |
Token | cipher |
Token ID | 38012 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
axter | +0.065 |
�� | +0.065 |
ioch | +0.064 |
theless | +0.063 |
arnaev | +0.062 |
Neg logit contributions | |
FAQ | -0.131 |
Bowman | -0.107 |
DG | -0.103 |
roots | -0.100 |
ollow | -0.100 |
Token | RC |
Token ID | 13987 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
axter | +0.151 |
�� | +0.150 |
ioch | +0.149 |
theless | +0.148 |
arnaev | +0.146 |
Neg logit contributions | |
FAQ | -0.169 |
Bowman | -0.130 |
DG | -0.123 |
roots | -0.119 |
ollow | -0.118 |
Token | 4 |
Token ID | 19 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
FAQ | +0.103 |
Bowman | +0.077 |
DG | +0.072 |
roots | +0.069 |
ollow | +0.068 |
Neg logit contributions | |
axter | -0.114 |
�� | -0.113 |
ioch | -0.112 |
theless | -0.111 |
arnaev | -0.110 |
Token | " |
Token ID | 366 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
FAQ | +0.074 |
Bowman | +0.057 |
DG | +0.054 |
roots | +0.052 |
ollow | +0.052 |
Neg logit contributions | |
axter | -0.066 |
�� | -0.065 |
ioch | -0.064 |
theless | -0.064 |
arnaev | -0.063 |
Token | b |
Token ID | 65 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
axter | +0.054 |
�� | +0.053 |
ioch | +0.053 |
theless | +0.053 |
arnaev | +0.052 |
Neg logit contributions | |
FAQ | -0.060 |
Bowman | -0.046 |
DG | -0.044 |
roots | -0.042 |
ollow | -0.042 |
Token | io |
Token ID | 952 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
axter | +0.117 |
�� | +0.117 |
ioch | +0.115 |
theless | +0.115 |
arnaev | +0.113 |
Neg logit contributions | |
FAQ | -0.139 |
Bowman | -0.108 |
DG | -0.102 |
roots | -0.099 |
ollow | -0.098 |
Token | indicator |
Token ID | 16916 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
FAQ | +0.143 |
Bowman | +0.109 |
DG | +0.103 |
roots | +0.099 |
vae | +0.099 |
Neg logit contributions | |
axter | -0.131 |
�� | -0.130 |
ioch | -0.129 |
theless | -0.128 |
arnaev | -0.127 |
Token | " |
Token ID | 1 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
axter | +0.108 |
�� | +0.107 |
ioch | +0.106 |
theless | +0.105 |
arnaev | +0.104 |
Neg logit contributions | |
FAQ | -0.120 |
Bowman | -0.092 |
DG | -0.087 |
roots | -0.084 |
ollow | -0.083 |
Token | and |
Token ID | 290 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
axter | +0.070 |
�� | +0.069 |
ioch | +0.068 |
theless | +0.068 |
arnaev | +0.067 |
Neg logit contributions | |
FAQ | -0.078 |
Bowman | -0.060 |
DG | -0.056 |
roots | -0.054 |
ollow | -0.054 |
Token | looking |
Token ID | 2045 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
axter | +0.058 |
�� | +0.058 |
ioch | +0.057 |
theless | +0.057 |
arnaev | +0.056 |
Neg logit contributions | |
FAQ | -0.066 |
Bowman | -0.051 |
DG | -0.048 |
roots | -0.047 |
ollow | -0.046 |
Token | at |
Token ID | 379 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
axter | +0.012 |
�� | +0.012 |
ioch | +0.012 |
theless | +0.011 |
arnaev | +0.011 |
Neg logit contributions | |
FAQ | -0.013 |
Bowman | -0.010 |
DG | -0.009 |
roots | -0.009 |
ollow | -0.009 |
Token | those |
Token ID | 883 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
FAQ | +0.026 |
Bowman | +0.020 |
DG | +0.019 |
roots | +0.018 |
ollow | +0.018 |
Neg logit contributions | |
axter | -0.022 |
�� | -0.022 |
ioch | -0.021 |
theless | -0.021 |
arnaev | -0.021 |
Token | being |
Token ID | 852 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
axter | +0.111 |
�� | +0.111 |
ioch | +0.109 |
theless | +0.109 |
arnaev | +0.108 |
Neg logit contributions | |
FAQ | -0.126 |
Bowman | -0.097 |
DG | -0.092 |
roots | -0.089 |
ollow | -0.088 |
Token | affected |
Token ID | 5676 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
axter | +0.077 |
�� | +0.076 |
ioch | +0.075 |
theless | +0.075 |
arnaev | +0.074 |
Neg logit contributions | |
FAQ | -0.095 |
Bowman | -0.074 |
DG | -0.070 |
roots | -0.068 |
ollow | -0.068 |
Token | of |
Token ID | 286 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
FAQ | +0.037 |
Bowman | +0.028 |
DG | +0.026 |
roots | +0.026 |
vae | +0.025 |
Neg logit contributions | |
axter | -0.032 |
�� | -0.032 |
ioch | -0.032 |
theless | -0.031 |
arnaev | -0.031 |
Token | slavery |
Token ID | 13503 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
axter | +0.028 |
�� | +0.028 |
ioch | +0.027 |
theless | +0.027 |
arnaev | +0.027 |
Neg logit contributions | |
FAQ | -0.033 |
Bowman | -0.026 |
DG | -0.024 |
roots | -0.023 |
ollow | -0.023 |
Token | …" |
Token ID | 9962 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
FAQ | +0.029 |
Bowman | +0.022 |
DG | +0.021 |
roots | +0.020 |
ollow | +0.020 |
Neg logit contributions | |
axter | -0.026 |
�� | -0.026 |
ioch | -0.025 |
theless | -0.025 |
arnaev | -0.025 |
Token | There |
Token ID | 1858 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
axter | +0.014 |
�� | +0.014 |
ioch | +0.013 |
theless | +0.013 |
arnaev | +0.013 |
Neg logit contributions | |
FAQ | -0.017 |
Bowman | -0.013 |
DG | -0.013 |
roots | -0.012 |
vae | -0.012 |
Token | are |
Token ID | 389 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
FAQ | +0.032 |
Bowman | +0.025 |
DG | +0.023 |
roots | +0.023 |
ollow | +0.022 |
Neg logit contributions | |
axter | -0.029 |
�� | -0.029 |
ioch | -0.029 |
theless | -0.028 |
arnaev | -0.028 |
Token | currently |
Token ID | 3058 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
FAQ | +0.068 |
Bowman | +0.053 |
DG | +0.050 |
roots | +0.048 |
ollow | +0.048 |
Neg logit contributions | |
axter | -0.057 |
�� | -0.057 |
ioch | -0.056 |
theless | -0.056 |
arnaev | -0.055 |
Token | more |
Token ID | 517 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
FAQ | +0.098 |
Bowman | +0.075 |
DG | +0.071 |
roots | +0.069 |
ollow | +0.068 |
Neg logit contributions | |
axter | -0.085 |
�� | -0.084 |
ioch | -0.084 |
theless | -0.084 |
arnaev | -0.082 |
Token | monuments |
Token ID | 28814 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
FAQ | +0.127 |
Bowman | +0.093 |
DG | +0.086 |
roots | +0.083 |
ollow | +0.082 |
Neg logit contributions | |
axter | -0.150 |
�� | -0.149 |
ioch | -0.148 |
theless | -0.147 |
arnaev | -0.145 |
Token | to |
Token ID | 284 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
FAQ | +0.144 |
Bowman | +0.110 |
DG | +0.104 |
roots | +0.101 |
vae | +0.100 |
Neg logit contributions | |
axter | -0.128 |
�� | -0.127 |
ioch | -0.126 |
theless | -0.126 |
arnaev | -0.124 |
Token | David |
Token ID | 3271 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
FAQ | +0.392 |
Bowman | +0.296 |
DG | +0.278 |
roots | +0.270 |
ollow | +0.268 |
Neg logit contributions | |
axter | -0.381 |
�� | -0.376 |
ioch | -0.374 |
theless | -0.373 |
arnaev | -0.368 |
Token | O |
Token ID | 440 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
FAQ | +0.203 |
Bowman | +0.155 |
DG | +0.146 |
roots | +0.142 |
vae | +0.141 |
Neg logit contributions | |
axter | -0.179 |
�� | -0.178 |
ioch | -0.176 |
theless | -0.176 |
arnaev | -0.174 |
Token | . |
Token ID | 13 |
Feature activation | -8.64e-02 |
Pos logit contributions | |
axter | +0.027 |
�� | +0.027 |
ioch | +0.027 |
theless | +0.027 |
arnaev | +0.026 |
Neg logit contributions | |
FAQ | -0.031 |
Bowman | -0.024 |
DG | -0.022 |
roots | -0.022 |
vae | -0.022 |
Token | Then |
Token ID | 3244 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
axter | +0.058 |
�� | +0.058 |
ioch | +0.057 |
theless | +0.057 |
arnaev | +0.056 |
Neg logit contributions | |
FAQ | -0.067 |
Bowman | -0.052 |
DG | -0.049 |
roots | -0.047 |
ollow | -0.047 |
Token | he |
Token ID | 339 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
axter | +0.186 |
�� | +0.185 |
ioch | +0.183 |
theless | +0.182 |
arnaev | +0.180 |
Neg logit contributions | |
FAQ | -0.206 |
Bowman | -0.159 |
DG | -0.149 |
roots | -0.144 |
ollow | -0.143 |
Token | opened |
Token ID | 4721 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
axter | +0.113 |
�� | +0.112 |
ioch | +0.111 |
theless | +0.111 |
arnaev | +0.109 |
Neg logit contributions | |
FAQ | -0.146 |
Bowman | -0.115 |
DG | -0.108 |
roots | -0.105 |
ollow | -0.104 |
Token | his |
Token ID | 465 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
axter | +0.250 |
�� | +0.248 |
ioch | +0.245 |
theless | +0.245 |
arnaev | +0.241 |
Neg logit contributions | |
FAQ | -0.323 |
Bowman | -0.253 |
DG | -0.240 |
roots | -0.233 |
ollow | -0.231 |
Token | eyes |
Token ID | 2951 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
axter | +0.083 |
�� | +0.083 |
ioch | +0.081 |
theless | +0.081 |
arnaev | +0.080 |
Neg logit contributions | |
FAQ | -0.155 |
Bowman | -0.126 |
DG | -0.120 |
roots | -0.117 |
ollow | -0.117 |
Token | and |
Token ID | 290 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
FAQ | +0.012 |
Bowman | +0.009 |
DG | +0.008 |
roots | +0.008 |
vae | +0.008 |
Neg logit contributions | |
axter | -0.011 |
�� | -0.010 |
ioch | -0.010 |
theless | -0.010 |
arnaev | -0.010 |
Token | said |
Token ID | 531 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
axter | +0.203 |
�� | +0.202 |
ioch | +0.199 |
theless | +0.199 |
arnaev | +0.196 |
Neg logit contributions | |
FAQ | -0.272 |
Bowman | -0.215 |
DG | -0.203 |
roots | -0.197 |
ollow | -0.196 |
Token | , |
Token ID | 11 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
FAQ | +0.186 |
Bowman | +0.143 |
DG | +0.134 |
roots | +0.130 |
vae | +0.129 |
Neg logit contributions | |
axter | -0.166 |
�� | -0.164 |
ioch | -0.163 |
theless | -0.162 |
arnaev | -0.160 |
Token | � |
Token ID | 564 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
FAQ | +0.012 |
Bowman | +0.009 |
DG | +0.009 |
roots | +0.009 |
vae | +0.008 |
Neg logit contributions | |
axter | -0.011 |
�� | -0.011 |
ioch | -0.011 |
theless | -0.011 |
arnaev | -0.011 |
Token | � |
Token ID | 250 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
axter | +0.223 |
�� | +0.221 |
ioch | +0.220 |
theless | +0.219 |
arnaev | +0.217 |
Neg logit contributions | |
FAQ | -0.164 |
Bowman | -0.117 |
DG | -0.108 |
roots | -0.103 |
ollow | -0.102 |
Token | that |
Token ID | 326 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
axter | +0.186 |
�� | +0.185 |
ioch | +0.183 |
theless | +0.182 |
arnaev | +0.180 |
Neg logit contributions | |
FAQ | -0.200 |
Bowman | -0.153 |
DG | -0.144 |
roots | -0.139 |
ollow | -0.138 |
Token | complicate |
Token ID | 45058 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
axter | +0.184 |
�� | +0.183 |
ioch | +0.181 |
theless | +0.180 |
arnaev | +0.177 |
Neg logit contributions | |
FAQ | -0.233 |
Bowman | -0.183 |
DG | -0.173 |
roots | -0.167 |
ollow | -0.166 |
Token | the |
Token ID | 262 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
FAQ | +0.032 |
Bowman | +0.025 |
DG | +0.023 |
roots | +0.023 |
ollow | +0.022 |
Neg logit contributions | |
axter | -0.028 |
�� | -0.028 |
ioch | -0.028 |
theless | -0.027 |
arnaev | -0.027 |
Token | determination |
Token ID | 12123 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
axter | +0.108 |
�� | +0.107 |
ioch | +0.106 |
theless | +0.106 |
arnaev | +0.104 |
Neg logit contributions | |
FAQ | -0.124 |
Bowman | -0.096 |
DG | -0.090 |
roots | -0.087 |
ollow | -0.087 |
Token | of |
Token ID | 286 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
axter | +0.008 |
�� | +0.008 |
ioch | +0.008 |
theless | +0.008 |
arnaev | +0.008 |
Neg logit contributions | |
FAQ | -0.010 |
Bowman | -0.007 |
DG | -0.007 |
roots | -0.007 |
ollow | -0.007 |
Token | climate |
Token ID | 4258 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
axter | +0.129 |
�� | +0.128 |
ioch | +0.127 |
theless | +0.127 |
arnaev | +0.125 |
Neg logit contributions | |
FAQ | -0.163 |
Bowman | -0.128 |
DG | -0.121 |
roots | -0.117 |
ollow | -0.116 |
Token | sensitivity |
Token ID | 14233 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
axter | +0.043 |
�� | +0.043 |
ioch | +0.042 |
theless | +0.042 |
arnaev | +0.041 |
Neg logit contributions | |
FAQ | -0.064 |
Bowman | -0.051 |
DG | -0.048 |
roots | -0.047 |
ollow | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
axter | +0.075 |
�� | +0.074 |
ioch | +0.073 |
theless | +0.073 |
arnaev | +0.072 |
Neg logit contributions | |
FAQ | -0.082 |
Bowman | -0.063 |
DG | -0.059 |
roots | -0.057 |
ollow | -0.057 |
Token | The |
Token ID | 383 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
axter | +0.155 |
�� | +0.154 |
ioch | +0.152 |
theless | +0.152 |
arnaev | +0.150 |
Neg logit contributions | |
FAQ | -0.178 |
Bowman | -0.137 |
DG | -0.129 |
roots | -0.125 |
ollow | -0.124 |
Token | methodology |
Token ID | 20411 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
axter | +0.084 |
�� | +0.083 |
ioch | +0.082 |
theless | +0.082 |
arnaev | +0.081 |
Neg logit contributions | |
FAQ | -0.100 |
Bowman | -0.078 |
DG | -0.074 |
roots | -0.071 |
ollow | -0.071 |
Token | that |
Token ID | 326 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
axter | +0.162 |
�� | +0.161 |
ioch | +0.159 |
theless | +0.159 |
arnaev | +0.157 |
Neg logit contributions | |
FAQ | -0.180 |
Bowman | -0.139 |
DG | -0.131 |
roots | -0.126 |
ollow | -0.125 |
Token | ade |
Token ID | 671 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
FAQ | +0.415 |
Bowman | +0.329 |
DG | +0.313 |
roots | +0.305 |
ollow | +0.302 |
Neg logit contributions | |
axter | -0.297 |
�� | -0.293 |
ioch | -0.292 |
theless | -0.289 |
arnaev | -0.286 |
Token | h |
Token ID | 71 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
FAQ | +0.128 |
Bowman | +0.096 |
DG | +0.090 |
roots | +0.087 |
ollow | +0.086 |
Neg logit contributions | |
axter | -0.136 |
�� | -0.135 |
ioch | -0.134 |
theless | -0.133 |
arnaev | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
FAQ | +0.256 |
Bowman | +0.195 |
DG | +0.183 |
roots | +0.178 |
vae | +0.176 |
Neg logit contributions | |
axter | -0.240 |
�� | -0.238 |
ioch | -0.236 |
theless | -0.235 |
arnaev | -0.232 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
axter | +0.054 |
�� | +0.054 |
ioch | +0.053 |
theless | +0.053 |
arnaev | +0.052 |
Neg logit contributions | |
FAQ | -0.062 |
Bowman | -0.048 |
DG | -0.045 |
roots | -0.043 |
ollow | -0.043 |
Token | NEW |
Token ID | 13965 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
FAQ | +0.026 |
Bowman | +0.020 |
DG | +0.019 |
roots | +0.018 |
ollow | +0.018 |
Neg logit contributions | |
axter | -0.025 |
�� | -0.025 |
ioch | -0.025 |
theless | -0.024 |
arnaev | -0.024 |
Token | DEL |
Token ID | 28163 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
FAQ | +0.184 |
Bowman | +0.150 |
DG | +0.143 |
roots | +0.140 |
ollow | +0.139 |
Neg logit contributions | |
axter | -0.095 |
�� | -0.094 |
ioch | -0.092 |
theless | -0.092 |
arnaev | -0.090 |
Token | HI |
Token ID | 25374 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
axter | +0.994 |
�� | +0.993 |
ioch | +0.972 |
theless | +0.965 |
arnaev | +0.960 |
Neg logit contributions | |
FAQ | -1.123 |
Bowman | -0.854 |
DG | -0.817 |
roots | -0.778 |
Dems | -0.777 |
Token | : |
Token ID | 25 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
axter | +0.164 |
�� | +0.163 |
ioch | +0.161 |
theless | +0.161 |
arnaev | +0.158 |
Neg logit contributions | |
FAQ | -0.177 |
Bowman | -0.136 |
DG | -0.128 |
roots | -0.123 |
ollow | -0.122 |
Token | In |
Token ID | 554 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
FAQ | +0.032 |
Bowman | +0.024 |
DG | +0.023 |
roots | +0.022 |
vae | +0.022 |
Neg logit contributions | |
axter | -0.029 |
�� | -0.029 |
ioch | -0.029 |
theless | -0.028 |
arnaev | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
axter | +0.232 |
�� | +0.230 |
ioch | +0.228 |
theless | +0.227 |
arnaev | +0.224 |
Neg logit contributions | |
FAQ | -0.267 |
Bowman | -0.206 |
DG | -0.194 |
roots | -0.188 |
ollow | -0.187 |
Token | setback |
Token ID | 34116 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
FAQ | +0.128 |
Bowman | +0.100 |
DG | +0.094 |
roots | +0.092 |
ollow | +0.091 |
Neg logit contributions | |
axter | -0.102 |
�� | -0.101 |
ioch | -0.100 |
theless | -0.100 |
arnaev | -0.098 |
Token | babe |
Token ID | 42666 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
axter | +0.062 |
�� | +0.061 |
ioch | +0.061 |
theless | +0.060 |
arnaev | +0.060 |
Neg logit contributions | |
FAQ | -0.073 |
Bowman | -0.056 |
DG | -0.053 |
roots | -0.051 |
ollow | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
axter | +0.209 |
�� | +0.208 |
ioch | +0.205 |
theless | +0.205 |
arnaev | +0.202 |
Neg logit contributions | |
FAQ | -0.241 |
Bowman | -0.186 |
DG | -0.176 |
roots | -0.170 |
ollow | -0.169 |
Token | now |
Token ID | 783 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
axter | +0.181 |
�� | +0.180 |
ioch | +0.178 |
theless | +0.178 |
arnaev | +0.175 |
Neg logit contributions | |
FAQ | -0.206 |
Bowman | -0.159 |
DG | -0.150 |
roots | -0.145 |
ollow | -0.144 |
Token | be |
Token ID | 307 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
axter | +0.217 |
�� | +0.216 |
ioch | +0.213 |
theless | +0.212 |
arnaev | +0.210 |
Neg logit contributions | |
FAQ | -0.263 |
Bowman | -0.204 |
DG | -0.193 |
roots | -0.187 |
ollow | -0.186 |
Token | a |
Token ID | 257 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
axter | +0.318 |
�� | +0.316 |
ioch | +0.312 |
theless | +0.311 |
arnaev | +0.307 |
Neg logit contributions | |
FAQ | -0.395 |
Bowman | -0.309 |
DG | -0.292 |
roots | -0.283 |
vae | -0.281 |
Token | good |
Token ID | 922 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
axter | +0.529 |
�� | +0.525 |
ioch | +0.519 |
theless | +0.516 |
arnaev | +0.511 |
Neg logit contributions | |
FAQ | -0.587 |
Bowman | -0.452 |
DG | -0.425 |
roots | -0.410 |
ollow | -0.408 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
axter | +0.920 |
�� | +0.916 |
ioch | +0.900 |
theless | +0.896 |
arnaev | +0.891 |
Neg logit contributions | |
FAQ | -1.075 |
Bowman | -0.842 |
DG | -0.789 |
roots | -0.763 |
ollow | -0.762 |
Token | and |
Token ID | 290 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
axter | +0.224 |
�� | +0.223 |
ioch | +0.221 |
theless | +0.220 |
arnaev | +0.217 |
Neg logit contributions | |
FAQ | -0.253 |
Bowman | -0.195 |
DG | -0.184 |
roots | -0.178 |
ollow | -0.176 |
Token | stay |
Token ID | 2652 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
axter | +0.167 |
�� | +0.166 |
ioch | +0.164 |
theless | +0.163 |
arnaev | +0.161 |
Neg logit contributions | |
FAQ | -0.210 |
Bowman | -0.164 |
DG | -0.155 |
roots | -0.151 |
ollow | -0.150 |
Token | in |
Token ID | 287 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
FAQ | +0.286 |
Bowman | +0.221 |
DG | +0.209 |
roots | +0.202 |
vae | +0.201 |
Neg logit contributions | |
axter | -0.238 |
�� | -0.235 |
theless | -0.234 |
ioch | -0.233 |
arnaev | -0.229 |
Token | bed |
Token ID | 3996 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
axter | +0.044 |
�� | +0.043 |
ioch | +0.043 |
theless | +0.042 |
arnaev | +0.042 |
Neg logit contributions | |
FAQ | -0.072 |
Bowman | -0.058 |
DG | -0.056 |
roots | -0.054 |
ollow | -0.054 |
Token | s |
Token ID | 82 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
FAQ | +0.008 |
Bowman | +0.006 |
DG | +0.006 |
roots | +0.005 |
ollow | +0.005 |
Neg logit contributions | |
axter | -0.007 |
�� | -0.007 |
ioch | -0.007 |
theless | -0.007 |
arnaev | -0.007 |
Token | largest |
Token ID | 4387 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
FAQ | +0.042 |
Bowman | +0.032 |
DG | +0.031 |
roots | +0.030 |
ollow | +0.029 |
Neg logit contributions | |
axter | -0.036 |
�� | -0.036 |
ioch | -0.035 |
theless | -0.035 |
arnaev | -0.035 |
Token | party |
Token ID | 2151 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
axter | +0.054 |
�� | +0.054 |
ioch | +0.053 |
theless | +0.053 |
arnaev | +0.052 |
Neg logit contributions | |
FAQ | -0.063 |
Bowman | -0.049 |
DG | -0.046 |
roots | -0.044 |
ollow | -0.044 |
Token | abandoned |
Token ID | 9958 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
axter | +0.128 |
�� | +0.128 |
ioch | +0.126 |
theless | +0.126 |
arnaev | +0.124 |
Neg logit contributions | |
FAQ | -0.150 |
Bowman | -0.116 |
DG | -0.109 |
roots | -0.106 |
ollow | -0.105 |
Token | President |
Token ID | 1992 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
FAQ | +0.109 |
Bowman | +0.084 |
DG | +0.079 |
roots | +0.077 |
ollow | +0.076 |
Neg logit contributions | |
axter | -0.095 |
�� | -0.094 |
ioch | -0.093 |
theless | -0.093 |
arnaev | -0.091 |
Token | Dil |
Token ID | 29328 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
axter | +0.088 |
�� | +0.087 |
ioch | +0.086 |
theless | +0.085 |
arnaev | +0.084 |
Neg logit contributions | |
FAQ | -0.155 |
Bowman | -0.126 |
DG | -0.120 |
roots | -0.117 |
ollow | -0.116 |
Token | ma |
Token ID | 2611 |
Feature activation | +4.49e-03 |
Pos logit contributions | |
�� | +0.562 |
axter | +0.539 |
ioch | +0.535 |
theless | +0.529 |
arnaev | +0.508 |
Neg logit contributions | |
FAQ | -1.724 |
Bowman | -1.453 |
DG | -1.389 |
vae | -1.370 |
roots | -1.370 |
Token | Rousse |
Token ID | 42849 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
FAQ | +0.005 |
Bowman | +0.004 |
DG | +0.004 |
roots | +0.004 |
vae | +0.004 |
Neg logit contributions | |
axter | -0.002 |
�� | -0.002 |
ioch | -0.002 |
theless | -0.002 |
arnaev | -0.002 |
Token | ff |
Token ID | 487 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
axter | +0.735 |
�� | +0.734 |
ioch | +0.726 |
theless | +0.722 |
arnaev | +0.714 |
Neg logit contributions | |
FAQ | -0.552 |
Bowman | -0.396 |
DG | -0.362 |
roots | -0.349 |
vae | -0.346 |
Token | � |
Token ID | 447 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
axter | +0.056 |
�� | +0.055 |
ioch | +0.055 |
theless | +0.055 |
arnaev | +0.054 |
Neg logit contributions | |
FAQ | -0.056 |
Bowman | -0.042 |
DG | -0.040 |
roots | -0.038 |
ollow | -0.038 |
Token | � |
Token ID | 247 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
FAQ | +0.046 |
Bowman | +0.035 |
DG | +0.033 |
roots | +0.031 |
ollow | +0.031 |
Neg logit contributions | |
axter | -0.048 |
�� | -0.048 |
ioch | -0.047 |
theless | -0.047 |
arnaev | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
axter | +0.029 |
�� | +0.029 |
ioch | +0.028 |
theless | +0.028 |
arnaev | +0.028 |
Neg logit contributions | |
FAQ | -0.032 |
Bowman | -0.025 |
DG | -0.023 |
roots | -0.023 |
ollow | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
axter | +0.029 |
�� | +0.029 |
ioch | +0.029 |
theless | +0.029 |
arnaev | +0.028 |
Neg logit contributions | |
FAQ | -0.033 |
Bowman | -0.026 |
DG | -0.024 |
roots | -0.023 |
ollow | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
FAQ | +0.025 |
Bowman | +0.019 |
DG | +0.018 |
roots | +0.018 |
vae | +0.017 |
Neg logit contributions | |
axter | -0.021 |
�� | -0.021 |
ioch | -0.021 |
theless | -0.021 |
arnaev | -0.020 |
Token | BL |
Token ID | 9148 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
axter | +0.020 |
�� | +0.020 |
ioch | +0.020 |
theless | +0.020 |
arnaev | +0.019 |
Neg logit contributions | |
FAQ | -0.021 |
Bowman | -0.016 |
DG | -0.015 |
roots | -0.015 |
ollow | -0.015 |
Token | IT |
Token ID | 2043 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
axter | +0.075 |
�� | +0.074 |
ioch | +0.073 |
theless | +0.073 |
arnaev | +0.071 |
Neg logit contributions | |
FAQ | -0.113 |
Bowman | -0.090 |
DG | -0.086 |
roots | -0.084 |
ollow | -0.083 |
Token | Z |
Token ID | 57 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
FAQ | +0.080 |
Bowman | +0.058 |
DG | +0.054 |
roots | +0.052 |
vae | +0.051 |
Neg logit contributions | |
axter | -0.099 |
�� | -0.099 |
ioch | -0.098 |
theless | -0.098 |
arnaev | -0.096 |
Token | ER |
Token ID | 1137 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
�� | +1.163 |
axter | +1.153 |
theless | +1.136 |
ioch | +1.127 |
arnaev | +1.108 |
Neg logit contributions | |
FAQ | -1.202 |
Bowman | -0.916 |
DG | -0.870 |
Dems | -0.823 |
roots | -0.816 |
Token | : |
Token ID | 25 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
FAQ | +0.374 |
Bowman | +0.286 |
DG | +0.269 |
roots | +0.265 |
vae | +0.263 |
Neg logit contributions | |
axter | -0.333 |
ioch | -0.329 |
�� | -0.328 |
theless | -0.328 |
arnaev | -0.322 |
Token | I |
Token ID | 314 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
axter | +0.132 |
�� | +0.131 |
ioch | +0.130 |
theless | +0.129 |
arnaev | +0.127 |
Neg logit contributions | |
FAQ | -0.148 |
Bowman | -0.114 |
DG | -0.107 |
roots | -0.104 |
ollow | -0.103 |
Token | am |
Token ID | 716 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
axter | +0.257 |
�� | +0.256 |
ioch | +0.252 |
theless | +0.251 |
arnaev | +0.248 |
Neg logit contributions | |
FAQ | -0.329 |
Bowman | -0.258 |
DG | -0.244 |
roots | -0.237 |
ollow | -0.235 |
Token | not |
Token ID | 407 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
axter | +0.294 |
�� | +0.293 |
ioch | +0.289 |
theless | +0.289 |
arnaev | +0.285 |
Neg logit contributions | |
FAQ | -0.325 |
Bowman | -0.251 |
DG | -0.236 |
roots | -0.228 |
Dems | -0.226 |
Token | Fox |
Token ID | 5426 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
axter | +0.086 |
�� | +0.086 |
ioch | +0.085 |
theless | +0.085 |
arnaev | +0.083 |
Neg logit contributions | |
FAQ | -0.103 |
Bowman | -0.080 |
DG | -0.076 |
roots | -0.073 |
ollow | -0.073 |
Token | Julia |
Token ID | 22300 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
axter | +0.188 |
�� | +0.187 |
ioch | +0.185 |
theless | +0.184 |
arnaev | +0.182 |
Neg logit contributions | |
FAQ | -0.217 |
Bowman | -0.168 |
DG | -0.158 |
roots | -0.153 |
ollow | -0.152 |
Token | Louis |
Token ID | 5593 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
axter | +0.811 |
�� | +0.811 |
ioch | +0.802 |
theless | +0.796 |
arnaev | +0.790 |
Neg logit contributions | |
FAQ | -0.861 |
Bowman | -0.667 |
DG | -0.624 |
Dems | -0.599 |
Bounty | -0.598 |
Token | - |
Token ID | 12 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
FAQ | +0.017 |
Bowman | +0.013 |
DG | +0.012 |
roots | +0.012 |
vae | +0.011 |
Neg logit contributions | |
axter | -0.017 |
�� | -0.017 |
ioch | -0.017 |
theless | -0.017 |
arnaev | -0.017 |
Token | D |
Token ID | 35 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
FAQ | +0.849 |
Bowman | +0.667 |
DG | +0.625 |
vae | +0.615 |
ollow | +0.609 |
Neg logit contributions | |
axter | -0.670 |
�� | -0.662 |
ioch | -0.660 |
theless | -0.649 |
arnaev | -0.646 |
Token | rey |
Token ID | 4364 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
FAQ | +0.483 |
Bowman | +0.364 |
DG | +0.340 |
roots | +0.330 |
Bounty | +0.327 |
Neg logit contributions | |
axter | -0.491 |
ioch | -0.484 |
�� | -0.476 |
theless | -0.476 |
arnaev | -0.470 |
Token | f |
Token ID | 69 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
�� | +1.172 |
axter | +1.165 |
ioch | +1.152 |
theless | +1.140 |
arnaev | +1.122 |
Neg logit contributions | |
FAQ | -1.176 |
Bowman | -0.901 |
DG | -0.834 |
roots | -0.816 |
vae | -0.815 |
Token | us |
Token ID | 385 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
FAQ | +1.082 |
Bowman | +0.785 |
DG | +0.753 |
roots | +0.723 |
Bounty | +0.714 |
Neg logit contributions | |
axter | -1.199 |
ioch | -1.185 |
�� | -1.169 |
theless | -1.148 |
arnaev | -1.146 |
Token | Ve |
Token ID | 8016 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
axter | +0.124 |
�� | +0.123 |
ioch | +0.122 |
theless | +0.122 |
arnaev | +0.120 |
Neg logit contributions | |
FAQ | -0.142 |
Bowman | -0.110 |
DG | -0.104 |
roots | -0.100 |
ollow | -0.099 |
Token | ep |
Token ID | 538 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
FAQ | +0.151 |
Bowman | +0.106 |
DG | +0.097 |
roots | +0.092 |
ollow | +0.091 |
Neg logit contributions | |
axter | -0.218 |
�� | -0.216 |
ioch | -0.215 |
theless | -0.214 |
arnaev | -0.211 |
Token | HBO |
Token ID | 18804 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
FAQ | +0.202 |
Bowman | +0.156 |
DG | +0.147 |
roots | +0.143 |
vae | +0.142 |
Neg logit contributions | |
axter | -0.173 |
�� | -0.171 |
ioch | -0.170 |
theless | -0.169 |
arnaev | -0.166 |