Token |
|
Token ID | 198 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
gaard | +0.475 |
ivist | +0.412 |
iors | +0.405 |
gets | +0.404 |
cific | +0.403 |
Neg logit contributions | |
tremend | -0.521 |
Idol | -0.491 |
Holo | -0.469 |
sych | -0.465 |
fw | -0.458 |
Token | is |
Token ID | 271 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
gaard | +2.831 |
ivist | +2.508 |
phies | +2.464 |
gets | +2.462 |
iors | +2.454 |
Neg logit contributions | |
Idol | -2.086 |
Holo | -1.964 |
sych | -1.907 |
tremend | -1.900 |
fw | -1.864 |
Token | created |
Token ID | 2727 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
gaard | +2.695 |
ivist | +2.255 |
phies | +2.155 |
cific | +2.148 |
iors | +2.147 |
Neg logit contributions | |
Idol | -4.050 |
Holo | -3.894 |
fw | -3.858 |
sych | -3.836 |
tremend | -3.820 |
Token | and |
Token ID | 290 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
gaard | +3.126 |
ivist | +2.697 |
cific | +2.623 |
iors | +2.621 |
gets | +2.595 |
Neg logit contributions | |
tremend | -4.084 |
Idol | -3.737 |
sych | -3.604 |
Holo | -3.577 |
therap | -3.575 |
Token | the |
Token ID | 262 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
gaard | +3.418 |
ivist | +2.992 |
gets | +2.920 |
cific | +2.915 |
iors | +2.875 |
Neg logit contributions | |
tremend | -3.740 |
Idol | -3.390 |
sych | -3.292 |
fw | -3.262 |
Holo | -3.210 |
Token | archived |
Token ID | 33962 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
gaard | +3.750 |
ivist | +3.292 |
phies | +3.218 |
cific | +3.198 |
iors | +3.168 |
Neg logit contributions | |
Idol | -3.714 |
Holo | -3.543 |
sych | -3.502 |
fw | -3.498 |
tremend | -3.415 |
Token | file |
Token ID | 2393 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
gaard | +7.467 |
ivist | +6.533 |
iors | +6.171 |
ong | +6.108 |
gets | +6.102 |
Neg logit contributions | |
tremend | -12.130 |
sych | -10.719 |
Idol | -10.610 |
therap | -10.497 |
etheless | -10.013 |
Token | is |
Token ID | 318 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
gaard | +3.462 |
gets | +3.042 |
ivist | +2.956 |
iors | +2.909 |
phies | +2.810 |
Neg logit contributions | |
tremend | -5.599 |
Idol | -4.968 |
therap | -4.891 |
sych | -4.848 |
ARA | -4.698 |
Token | uploaded |
Token ID | 19144 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
gaard | +2.839 |
ivist | +2.466 |
phies | +2.426 |
gets | +2.396 |
cific | +2.373 |
Neg logit contributions | |
tremend | -3.458 |
Idol | -3.397 |
sych | -3.244 |
Holo | -3.206 |
fw | -3.150 |
Token | to |
Token ID | 284 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
gaard | +5.095 |
gets | +4.626 |
ivist | +4.444 |
iors | +4.361 |
cific | +4.329 |
Neg logit contributions | |
tremend | -8.643 |
therap | -7.444 |
Idol | -7.013 |
eleph | -6.849 |
sych | -6.837 |
Token | it |
Token ID | 340 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
gaard | +3.538 |
ivist | +3.156 |
gets | +3.116 |
iors | +3.094 |
cific | +2.976 |
Neg logit contributions | |
tremend | -4.574 |
Idol | -4.091 |
sych | -4.009 |
Holo | -3.890 |
fw | -3.871 |
Token | AN |
Token ID | 1565 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
gaard | +2.862 |
ivist | +2.490 |
iors | +2.460 |
IVES | +2.400 |
cific | +2.354 |
Neg logit contributions | |
tremend | -3.195 |
Idol | -2.919 |
Holo | -2.844 |
fw | -2.794 |
therap | -2.786 |
Token | TS |
Token ID | 4694 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Idol | +1.508 |
Holo | +1.412 |
fw | +1.376 |
sych | +1.370 |
tremend | +1.350 |
Neg logit contributions | |
gaard | -2.693 |
ivist | -2.416 |
cific | -2.389 |
phies | -2.383 |
iors | -2.369 |
Token | � |
Token ID | 447 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
gaard | +0.680 |
ivist | +0.607 |
cific | +0.602 |
phies | +0.600 |
iferation | +0.595 |
Neg logit contributions | |
Idol | -0.410 |
Holo | -0.383 |
fw | -0.376 |
sych | -0.375 |
tremend | -0.362 |
Token | � |
Token ID | 247 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
gaard | +1.543 |
iors | +1.242 |
ivist | +1.234 |
cific | +1.215 |
phies | +1.213 |
Neg logit contributions | |
tremend | -2.129 |
Idol | -2.082 |
Holo | -2.007 |
sych | -2.003 |
fw | -1.987 |
Token | C |
Token ID | 327 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
gaard | +3.322 |
ivist | +2.898 |
cific | +2.836 |
phies | +2.822 |
iors | +2.817 |
Neg logit contributions | |
Idol | -3.235 |
Holo | -3.105 |
fw | -3.046 |
sych | -3.043 |
tremend | -3.029 |
Token | OU |
Token ID | 2606 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
gaard | +3.979 |
ivist | +3.432 |
cific | +3.385 |
phies | +3.375 |
iors | +3.372 |
Neg logit contributions | |
tremend | -4.209 |
Idol | -4.016 |
Holo | -3.828 |
sych | -3.677 |
therap | -3.612 |
Token | NS |
Token ID | 8035 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
gaard | +4.855 |
iors | +4.254 |
gets | +4.192 |
IVES | +4.172 |
cific | +3.683 |
Neg logit contributions | |
tremend | -15.364 |
therap | -13.463 |
eleph | -13.341 |
Idol | -12.680 |
Holo | -12.674 |
Token | EL |
Token ID | 3698 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
gaard | +2.121 |
ivist | +1.865 |
gets | +1.853 |
iors | +1.846 |
cific | +1.831 |
Neg logit contributions | |
tremend | -1.401 |
Idol | -1.269 |
Holo | -1.176 |
sych | -1.156 |
therap | -1.147 |
Token | : |
Token ID | 25 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
gaard | +2.833 |
ivist | +2.451 |
iors | +2.419 |
gets | +2.391 |
cific | +2.391 |
Neg logit contributions | |
tremend | -3.101 |
Idol | -2.730 |
therap | -2.655 |
sych | -2.644 |
Holo | -2.641 |
Token | We |
Token ID | 775 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
gaard | +2.763 |
ivist | +2.415 |
cific | +2.381 |
iors | +2.354 |
gets | +2.341 |
Neg logit contributions | |
tremend | -2.332 |
Idol | -2.263 |
sych | -2.207 |
Holo | -2.178 |
fw | -2.168 |
Token | can |
Token ID | 460 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
gaard | +1.578 |
ivist | +1.380 |
cific | +1.353 |
iors | +1.348 |
phies | +1.342 |
Neg logit contributions | |
Idol | -1.337 |
Holo | -1.278 |
tremend | -1.253 |
fw | -1.248 |
sych | -1.237 |
Token |
|
Token ID | 198 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
Idol | +0.812 |
Holo | +0.767 |
fw | +0.748 |
sych | +0.743 |
tremend | +0.722 |
Neg logit contributions | |
gaard | -0.999 |
ivist | -0.881 |
cific | -0.868 |
phies | -0.868 |
iferation | -0.861 |
Token |
|
Token ID | 198 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
gaard | +0.357 |
ivist | +0.309 |
iors | +0.305 |
gets | +0.303 |
cific | +0.303 |
Neg logit contributions | |
tremend | -0.396 |
Idol | -0.372 |
Holo | -0.356 |
sych | -0.354 |
fw | -0.350 |
Token | OB |
Token ID | 9864 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
gaard | +0.994 |
ivist | +0.881 |
phies | +0.871 |
cific | +0.867 |
iors | +0.862 |
Neg logit contributions | |
Idol | -0.741 |
Holo | -0.701 |
tremend | -0.691 |
sych | -0.681 |
fw | -0.679 |
Token | B |
Token ID | 33 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
gaard | +0.311 |
ivist | +0.282 |
cific | +0.279 |
phies | +0.276 |
iors | +0.275 |
Neg logit contributions | |
Idol | -0.156 |
Holo | -0.145 |
fw | -0.142 |
sych | -0.141 |
tremend | -0.136 |
Token | ( |
Token ID | 357 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Idol | +0.490 |
Holo | +0.453 |
fw | +0.438 |
sych | +0.436 |
tremend | +0.421 |
Neg logit contributions | |
gaard | -1.068 |
ivist | -0.966 |
cific | -0.957 |
phies | -0.953 |
iors | -0.946 |
Token | Object |
Token ID | 10267 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
gaard | +0.704 |
ivist | +0.623 |
cific | +0.613 |
phies | +0.612 |
iors | +0.606 |
Neg logit contributions | |
Idol | -0.549 |
Holo | -0.522 |
fw | -0.511 |
sych | -0.509 |
tremend | -0.498 |
Token | Al |
Token ID | 978 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
gaard | +9.745 |
ivist | +9.472 |
ivism | +8.811 |
IVES | +8.537 |
iferation | +8.527 |
Neg logit contributions | |
tremend | -7.351 |
Idol | -7.351 |
fw | -7.261 |
sych | -7.240 |
ARA | -7.052 |
Token | igned |
Token ID | 3916 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
gaard | +0.312 |
ivist | +0.274 |
cific | +0.270 |
phies | +0.269 |
iors | +0.266 |
Neg logit contributions | |
Idol | -0.264 |
Holo | -0.250 |
fw | -0.246 |
sych | -0.245 |
tremend | -0.239 |
Token | B |
Token ID | 347 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
gaard | +2.964 |
ivist | +2.625 |
cific | +2.576 |
iors | +2.559 |
phies | +2.558 |
Neg logit contributions | |
Idol | -2.167 |
Holo | -2.063 |
sych | -2.058 |
fw | -2.051 |
tremend | -2.049 |
Token | ounding |
Token ID | 9969 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
gaard | +3.503 |
ivist | +3.039 |
phies | +2.976 |
iors | +2.955 |
iferation | +2.954 |
Neg logit contributions | |
Idol | -3.779 |
Holo | -3.615 |
tremend | -3.568 |
sych | -3.516 |
fw | -3.504 |
Token | Box |
Token ID | 8315 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
Idol | +1.203 |
Holo | +1.131 |
fw | +1.093 |
sych | +1.084 |
Barcl | +1.047 |
Neg logit contributions | |
gaard | -1.640 |
ivist | -1.469 |
phies | -1.458 |
cific | -1.453 |
iors | -1.428 |
Token | nominee |
Token ID | 10429 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
gaard | +1.272 |
ivist | +1.143 |
iors | +1.121 |
cific | +1.121 |
phies | +1.117 |
Neg logit contributions | |
Idol | -0.755 |
Holo | -0.708 |
fw | -0.701 |
sych | -0.689 |
tremend | -0.679 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
gaard | +0.527 |
ivist | +0.432 |
cific | +0.419 |
phies | +0.417 |
iors | +0.415 |
Neg logit contributions | |
Idol | -0.955 |
Holo | -0.920 |
fw | -0.914 |
sych | -0.908 |
tremend | -0.899 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
gaard | +2.817 |
ivist | +2.254 |
iors | +2.131 |
gets | +2.114 |
cific | +2.053 |
Neg logit contributions | |
tremend | -7.707 |
Idol | -7.577 |
sych | -7.521 |
fw | -7.503 |
Holo | -7.449 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
gaard | +3.700 |
ivist | +3.208 |
iors | +3.131 |
cific | +3.099 |
phies | +3.098 |
Neg logit contributions | |
Idol | -3.790 |
fw | -3.641 |
Holo | -3.629 |
sych | -3.598 |
tremend | -3.570 |
Token | Diane |
Token ID | 26542 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
gaard | +3.121 |
ivist | +2.650 |
gets | +2.592 |
iors | +2.589 |
iferation | +2.585 |
Neg logit contributions | |
tremend | -4.861 |
Idol | -4.776 |
Holo | -4.666 |
fw | -4.660 |
sych | -4.568 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
gaard | +2.166 |
ivist | +1.534 |
iferation | +1.409 |
gets | +1.406 |
iors | +1.379 |
Neg logit contributions | |
Idol | -8.073 |
Holo | -7.871 |
tremend | -7.848 |
fw | -7.798 |
sych | -7.718 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
gaard | +3.880 |
iors | +2.858 |
ivist | +2.836 |
gets | +2.742 |
cific | +2.674 |
Neg logit contributions | |
tremend | -13.889 |
sych | -13.429 |
Idol | -13.110 |
fw | -12.905 |
Holo | -12.792 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
gaard | +6.191 |
iors | +5.519 |
gets | +5.484 |
ivist | +5.414 |
iferation | +5.303 |
Neg logit contributions | |
Idol | -6.304 |
tremend | -6.247 |
Holo | -5.994 |
sych | -5.948 |
fw | -5.887 |
Token | : |
Token ID | 25 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
gaard | +1.164 |
ivist | +0.986 |
cific | +0.977 |
phies | +0.975 |
iors | +0.950 |
Neg logit contributions | |
Idol | -1.483 |
Holo | -1.421 |
fw | -1.401 |
sych | -1.396 |
tremend | -1.368 |
Token | ' |
Token ID | 705 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
Idol | +1.356 |
Holo | +1.273 |
sych | +1.231 |
fw | +1.217 |
Barcl | +1.203 |
Neg logit contributions | |
gaard | -1.844 |
cific | -1.653 |
ivist | -1.627 |
phies | -1.619 |
iferation | -1.591 |
Token | I |
Token ID | 40 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
Idol | +2.924 |
Holo | +2.718 |
sych | +2.712 |
ARA | +2.611 |
fw | +2.538 |
Neg logit contributions | |
gaard | -5.773 |
ivist | -5.246 |
cific | -5.183 |
iferation | -5.147 |
phies | -5.108 |
Token |
|
Token ID | 198 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
Idol | +1.106 |
tremend | +1.075 |
Holo | +1.054 |
sych | +1.036 |
fw | +1.033 |
Neg logit contributions | |
gaard | -1.197 |
ivist | -1.046 |
cific | -1.028 |
iors | -1.022 |
phies | -1.020 |
Token | Like |
Token ID | 7594 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Idol | +0.126 |
Holo | +0.119 |
fw | +0.117 |
sych | +0.116 |
tremend | +0.115 |
Neg logit contributions | |
gaard | -0.157 |
ivist | -0.139 |
cific | -0.137 |
phies | -0.137 |
iors | -0.136 |
Token | almost |
Token ID | 2048 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Idol | +0.805 |
Holo | +0.765 |
fw | +0.745 |
sych | +0.744 |
tremend | +0.727 |
Neg logit contributions | |
gaard | -0.911 |
ivist | -0.799 |
cific | -0.790 |
phies | -0.787 |
iors | -0.777 |
Token | everything |
Token ID | 2279 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
Idol | +1.003 |
Holo | +0.956 |
fw | +0.925 |
sych | +0.924 |
tremend | +0.905 |
Neg logit contributions | |
gaard | -1.065 |
ivist | -0.934 |
cific | -0.925 |
phies | -0.920 |
iferation | -0.912 |
Token | Amy |
Token ID | 14235 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
Idol | +1.599 |
Holo | +1.514 |
sych | +1.465 |
fw | +1.461 |
tremend | +1.437 |
Neg logit contributions | |
gaard | -1.652 |
ivist | -1.442 |
cific | -1.437 |
phies | -1.429 |
iferation | -1.412 |
Token | Sed |
Token ID | 22710 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
gaard | +2.685 |
ivist | +2.361 |
phies | +2.311 |
cific | +2.308 |
iors | +2.293 |
Neg logit contributions | |
Idol | -2.050 |
Holo | -2.003 |
fw | -1.959 |
sych | -1.935 |
tremend | -1.911 |
Token | aris |
Token ID | 20066 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
gaard | +9.240 |
ivist | +8.141 |
iors | +7.846 |
phies | +7.782 |
gets | +7.724 |
Neg logit contributions | |
tremend | -8.788 |
fw | -8.369 |
Skydragon | -8.363 |
Holo | -8.240 |
sych | -7.995 |
Token | is |
Token ID | 318 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
gaard | +3.117 |
ivist | +2.701 |
phies | +2.612 |
iors | +2.605 |
cific | +2.592 |
Neg logit contributions | |
Idol | -3.057 |
Holo | -2.951 |
sych | -2.921 |
fw | -2.909 |
tremend | -2.894 |
Token | involved |
Token ID | 2950 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Idol | +0.342 |
Holo | +0.324 |
fw | +0.317 |
sych | +0.314 |
tremend | +0.307 |
Neg logit contributions | |
gaard | -0.434 |
ivist | -0.383 |
cific | -0.381 |
phies | -0.379 |
iferation | -0.376 |
Token | in |
Token ID | 287 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
gaard | +1.475 |
ivist | +1.305 |
cific | +1.303 |
phies | +1.295 |
iferation | +1.280 |
Neg logit contributions | |
Idol | -0.945 |
Holo | -0.889 |
fw | -0.862 |
sych | -0.858 |
tremend | -0.844 |
Token | , |
Token ID | 11 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
gaard | +2.430 |
ivist | +2.142 |
cific | +2.106 |
phies | +2.101 |
iors | +2.083 |
Neg logit contributions | |
Idol | -1.980 |
Holo | -1.881 |
fw | -1.849 |
sych | -1.841 |
tremend | -1.798 |
Token | and |
Token ID | 290 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
Idol | +2.873 |
Holo | +2.657 |
sych | +2.609 |
fw | +2.589 |
tremend | +2.507 |
Neg logit contributions | |
gaard | -4.260 |
phies | -3.793 |
cific | -3.769 |
ivist | -3.729 |
iferation | -3.720 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
Idol | +2.189 |
Holo | +2.103 |
sych | +2.038 |
fw | +2.037 |
tremend | +2.002 |
Neg logit contributions | |
gaard | -1.762 |
ivist | -1.492 |
cific | -1.477 |
phies | -1.476 |
iferation | -1.457 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
gaard | +2.314 |
ivist | +1.869 |
iors | +1.692 |
cific | +1.670 |
gets | +1.638 |
Neg logit contributions | |
tremend | -6.789 |
sych | -6.472 |
fw | -6.406 |
Idol | -6.364 |
Holo | -6.311 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
gaard | +1.864 |
ivist | +1.408 |
iors | +1.393 |
cific | +1.351 |
phies | +1.297 |
Neg logit contributions | |
Idol | -4.699 |
tremend | -4.652 |
fw | -4.641 |
sych | -4.583 |
Holo | -4.554 |
Token | Diane |
Token ID | 26542 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
gaard | +3.077 |
ivist | +2.566 |
iferation | +2.539 |
gets | +2.538 |
iors | +2.486 |
Neg logit contributions | |
tremend | -4.947 |
Idol | -4.825 |
Holo | -4.737 |
fw | -4.690 |
sych | -4.618 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
gaard | +2.314 |
ivist | +1.605 |
gets | +1.447 |
iors | +1.415 |
iferation | +1.413 |
Neg logit contributions | |
Idol | -10.233 |
Holo | -10.066 |
tremend | -10.028 |
fw | -9.957 |
sych | -9.782 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
gaard | +3.429 |
iors | +2.545 |
gets | +2.507 |
ivist | +2.429 |
cific | +2.248 |
Neg logit contributions | |
tremend | -14.258 |
sych | -13.605 |
Idol | -13.274 |
fw | -13.049 |
Holo | -13.019 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
gaard | +5.885 |
gets | +5.246 |
iors | +5.185 |
ivist | +5.077 |
cific | +5.030 |
Neg logit contributions | |
Idol | -7.039 |
tremend | -6.808 |
Holo | -6.714 |
sych | -6.575 |
fw | -6.503 |
Token | : |
Token ID | 25 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
gaard | +0.930 |
ivist | +0.783 |
cific | +0.776 |
phies | +0.773 |
iors | +0.755 |
Neg logit contributions | |
Idol | -1.250 |
Holo | -1.199 |
fw | -1.184 |
sych | -1.180 |
tremend | -1.156 |
Token | ' |
Token ID | 705 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
Idol | +0.750 |
Holo | +0.708 |
sych | +0.683 |
fw | +0.680 |
Barcl | +0.666 |
Neg logit contributions | |
gaard | -0.975 |
cific | -0.861 |
ivist | -0.860 |
phies | -0.849 |
iors | -0.839 |
Token | I |
Token ID | 40 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
Idol | +2.694 |
Holo | +2.507 |
sych | +2.488 |
fw | +2.374 |
ARA | +2.369 |
Neg logit contributions | |
gaard | -4.979 |
ivist | -4.504 |
cific | -4.435 |
phies | -4.395 |
iferation | -4.390 |
Token | and |
Token ID | 290 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
gaard | +0.134 |
ivist | +0.118 |
cific | +0.117 |
phies | +0.117 |
iors | +0.115 |
Neg logit contributions | |
Idol | -0.104 |
Holo | -0.098 |
fw | -0.096 |
sych | -0.095 |
tremend | -0.093 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
gaard | +0.302 |
ivist | +0.266 |
cific | +0.262 |
phies | +0.261 |
iors | +0.258 |
Neg logit contributions | |
Idol | -0.251 |
Holo | -0.239 |
fw | -0.237 |
sych | -0.235 |
tremend | -0.230 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
gaard | +3.832 |
ivist | +3.209 |
iors | +3.029 |
cific | +3.002 |
iferation | +2.955 |
Neg logit contributions | |
Idol | -6.813 |
Holo | -6.749 |
fw | -6.720 |
sych | -6.645 |
tremend | -6.558 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
gaard | +2.875 |
ivist | +2.224 |
cific | +2.141 |
iors | +2.124 |
iferation | +2.025 |
Neg logit contributions | |
Idol | -6.756 |
fw | -6.721 |
Holo | -6.634 |
tremend | -6.624 |
sych | -6.568 |
Token | Diane |
Token ID | 26542 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
gaard | +3.048 |
ivist | +2.571 |
iferation | +2.500 |
gets | +2.491 |
iors | +2.472 |
Neg logit contributions | |
Idol | -4.410 |
tremend | -4.391 |
Holo | -4.312 |
fw | -4.279 |
sych | -4.208 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
gaard | +2.417 |
ivist | +1.673 |
gets | +1.504 |
iors | +1.482 |
iferation | +1.446 |
Neg logit contributions | |
Idol | -10.359 |
Holo | -10.197 |
tremend | -10.165 |
fw | -10.090 |
sych | -9.906 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
gaard | +3.483 |
iors | +2.665 |
gets | +2.596 |
ivist | +2.553 |
cific | +2.381 |
Neg logit contributions | |
tremend | -13.745 |
sych | -13.220 |
Idol | -12.840 |
fw | -12.737 |
Holo | -12.670 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
gaard | +5.796 |
gets | +5.157 |
iors | +5.133 |
ivist | +4.995 |
iferation | +4.967 |
Neg logit contributions | |
Idol | -6.770 |
tremend | -6.583 |
Holo | -6.459 |
sych | -6.333 |
fw | -6.310 |
Token | : |
Token ID | 25 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
gaard | +0.914 |
ivist | +0.766 |
cific | +0.761 |
phies | +0.759 |
iferation | +0.737 |
Neg logit contributions | |
Idol | -1.255 |
Holo | -1.205 |
fw | -1.190 |
sych | -1.186 |
tremend | -1.162 |
Token | ' |
Token ID | 705 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
Idol | +0.941 |
Holo | +0.887 |
sych | +0.858 |
fw | +0.854 |
Barcl | +0.833 |
Neg logit contributions | |
gaard | -1.234 |
cific | -1.092 |
ivist | -1.087 |
phies | -1.077 |
iors | -1.062 |
Token | I |
Token ID | 40 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
Idol | +2.860 |
Holo | +2.668 |
sych | +2.656 |
ARA | +2.533 |
fw | +2.495 |
Neg logit contributions | |
gaard | -5.379 |
ivist | -4.857 |
cific | -4.785 |
iferation | -4.746 |
phies | -4.738 |
Token | sent |
Token ID | 1908 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
gaard | +2.549 |
ivist | +2.230 |
cific | +2.176 |
iors | +2.174 |
phies | +2.161 |
Neg logit contributions | |
Idol | -2.090 |
Holo | -1.979 |
sych | -1.974 |
tremend | -1.950 |
fw | -1.950 |
Token | by |
Token ID | 416 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
gaard | +0.704 |
ivist | +0.622 |
cific | +0.613 |
phies | +0.610 |
iors | +0.605 |
Neg logit contributions | |
Idol | -0.555 |
Holo | -0.526 |
fw | -0.517 |
sych | -0.515 |
tremend | -0.503 |
Token | Sar |
Token ID | 6866 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
Idol | +1.564 |
Holo | +1.483 |
fw | +1.440 |
sych | +1.426 |
tremend | +1.393 |
Neg logit contributions | |
gaard | -1.984 |
ivist | -1.752 |
cific | -1.736 |
phies | -1.734 |
iferation | -1.718 |
Token | uman |
Token ID | 3778 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
gaard | +1.748 |
ivist | +1.506 |
cific | +1.474 |
iors | +1.459 |
phies | +1.429 |
Neg logit contributions | |
tremend | -2.130 |
Idol | -2.122 |
sych | -2.046 |
Holo | -2.046 |
fw | -2.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Idol | +0.535 |
Holo | +0.508 |
fw | +0.498 |
sych | +0.497 |
tremend | +0.486 |
Neg logit contributions | |
gaard | -0.669 |
ivist | -0.590 |
cific | -0.581 |
phies | -0.579 |
iors | -0.574 |
Token | Saur |
Token ID | 46197 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
gaard | +0.686 |
ivist | +0.607 |
cific | +0.598 |
phies | +0.596 |
iors | +0.592 |
Neg logit contributions | |
Idol | -0.514 |
Holo | -0.487 |
fw | -0.480 |
sych | -0.480 |
tremend | -0.469 |
Token | on |
Token ID | 261 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
gaard | +6.067 |
iors | +5.275 |
ong | +5.009 |
ivist | +5.004 |
phies | +4.703 |
Neg logit contributions | |
tremend | -11.576 |
sych | -10.859 |
Idol | -10.753 |
Skydragon | -10.632 |
Holo | -10.502 |
Token | kill |
Token ID | 1494 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
gaard | +0.978 |
ivist | +0.860 |
cific | +0.843 |
iors | +0.838 |
phies | +0.837 |
Neg logit contributions | |
Idol | -0.789 |
Holo | -0.747 |
sych | -0.739 |
fw | -0.739 |
tremend | -0.726 |
Token | Bor |
Token ID | 12182 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
gaard | +0.909 |
ivist | +0.799 |
cific | +0.785 |
phies | +0.782 |
iors | +0.780 |
Neg logit contributions | |
Idol | -0.764 |
Holo | -0.726 |
fw | -0.718 |
sych | -0.716 |
tremend | -0.700 |
Token | om |
Token ID | 296 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
gaard | +0.286 |
ivist | +0.247 |
cific | +0.241 |
phies | +0.241 |
iors | +0.239 |
Neg logit contributions | |
Idol | -0.325 |
Holo | -0.311 |
sych | -0.306 |
fw | -0.305 |
tremend | -0.305 |
Token | ir |
Token ID | 343 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
Idol | +0.919 |
Holo | +0.866 |
fw | +0.845 |
sych | +0.842 |
tremend | +0.836 |
Neg logit contributions | |
gaard | -1.440 |
ivist | -1.289 |
cific | -1.270 |
phies | -1.266 |
iors | -1.259 |
Token | Aviation |
Token ID | 25186 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Idol | +1.749 |
Holo | +1.655 |
fw | +1.612 |
sych | +1.598 |
tremend | +1.546 |
Neg logit contributions | |
gaard | -2.322 |
ivist | -2.047 |
cific | -2.025 |
phies | -2.021 |
iors | -2.006 |
Token | Week |
Token ID | 6119 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
gaard | +0.631 |
ivist | +0.545 |
cific | +0.536 |
phies | +0.534 |
iors | +0.528 |
Neg logit contributions | |
Idol | -0.686 |
Holo | -0.656 |
fw | -0.645 |
sych | -0.643 |
tremend | -0.630 |
Token | � |
Token ID | 447 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
gaard | +0.301 |
ivist | +0.264 |
cific | +0.260 |
phies | +0.259 |
iors | +0.256 |
Neg logit contributions | |
Idol | -0.266 |
Holo | -0.253 |
fw | -0.249 |
sych | -0.248 |
tremend | -0.243 |
Token | � |
Token ID | 247 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Idol | +1.297 |
Holo | +1.235 |
tremend | +1.230 |
fw | +1.222 |
sych | +1.219 |
Neg logit contributions | |
gaard | -1.208 |
ivist | -1.026 |
phies | -1.015 |
cific | -1.015 |
iors | -1.011 |
Token | s |
Token ID | 82 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
Idol | +1.093 |
Holo | +1.043 |
fw | +1.028 |
sych | +1.023 |
tremend | +0.991 |
Neg logit contributions | |
gaard | -1.138 |
ivist | -0.991 |
cific | -0.977 |
phies | -0.976 |
iors | -0.962 |
Token | Lara |
Token ID | 29849 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
gaard | +0.089 |
ivist | +0.077 |
cific | +0.076 |
phies | +0.075 |
iors | +0.075 |
Neg logit contributions | |
Idol | -0.088 |
Holo | -0.084 |
fw | -0.082 |
sych | -0.082 |
tremend | -0.081 |
Token | Sel |
Token ID | 15300 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
gaard | +9.453 |
ivist | +8.248 |
iferation | +7.944 |
cific | +7.867 |
phies | +7.864 |
Neg logit contributions | |
tremend | -7.118 |
Idol | -7.110 |
sych | -7.004 |
fw | -6.926 |
Holo | -6.662 |
Token | ig |
Token ID | 328 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
gaard | +4.259 |
ivist | +3.669 |
phies | +3.631 |
cific | +3.565 |
iors | +3.542 |
Neg logit contributions | |
Idol | -3.628 |
tremend | -3.555 |
Holo | -3.511 |
sych | -3.411 |
fw | -3.375 |
Token | man |
Token ID | 805 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
gaard | +2.605 |
ivist | +2.236 |
cific | +2.191 |
phies | +2.188 |
iors | +2.159 |
Neg logit contributions | |
Idol | -2.655 |
Holo | -2.529 |
sych | -2.479 |
fw | -2.476 |
tremend | -2.447 |
Token | reminded |
Token ID | 14516 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
gaard | +1.315 |
ivist | +1.151 |
cific | +1.132 |
phies | +1.128 |
iors | +1.118 |
Neg logit contributions | |
Idol | -1.158 |
Holo | -1.102 |
fw | -1.085 |
sych | -1.080 |
tremend | -1.060 |
Token | folks |
Token ID | 7974 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
gaard | +0.203 |
ivist | +0.179 |
cific | +0.177 |
phies | +0.176 |
iors | +0.175 |
Neg logit contributions | |
Idol | -0.163 |
Holo | -0.155 |
fw | -0.151 |
sych | -0.151 |
tremend | -0.147 |
Token | � |
Token ID | 447 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
Idol | +1.126 |
Holo | +1.063 |
fw | +1.050 |
sych | +1.040 |
ARA | +0.999 |
Neg logit contributions | |
gaard | -1.613 |
ivist | -1.430 |
cific | -1.415 |
phies | -1.411 |
iferation | -1.399 |
Token | � |
Token ID | 250 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
Idol | +0.259 |
Holo | +0.245 |
fw | +0.240 |
sych | +0.238 |
tremend | +0.231 |
Neg logit contributions | |
gaard | -0.368 |
ivist | -0.329 |
cific | -0.325 |
phies | -0.321 |
iferation | -0.320 |
Token | Zero |
Token ID | 28667 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Idol | +0.289 |
Holo | +0.274 |
fw | +0.269 |
sych | +0.267 |
tremend | +0.260 |
Neg logit contributions | |
gaard | -0.384 |
ivist | -0.339 |
cific | -0.335 |
phies | -0.334 |
iors | -0.331 |
Token | poverty |
Token ID | 8098 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
gaard | +1.968 |
ivist | +1.769 |
phies | +1.730 |
cific | +1.721 |
iors | +1.716 |
Neg logit contributions | |
Idol | -1.290 |
Holo | -1.223 |
fw | -1.198 |
sych | -1.194 |
tremend | -1.166 |
Token | in |
Token ID | 287 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
gaard | +1.882 |
ivist | +1.658 |
cific | +1.620 |
phies | +1.617 |
iors | +1.609 |
Neg logit contributions | |
Idol | -1.635 |
Holo | -1.560 |
fw | -1.525 |
sych | -1.525 |
tremend | -1.491 |
Token | four |
Token ID | 1440 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
gaard | +3.689 |
ivist | +3.220 |
gets | +3.121 |
iors | +3.121 |
iferation | +3.104 |
Neg logit contributions | |
Idol | -4.273 |
Holo | -4.167 |
sych | -4.087 |
fw | -4.038 |
tremend | -3.984 |
Token | years |
Token ID | 812 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
gaard | +5.467 |
ivist | +4.461 |
iors | +4.419 |
phies | +4.319 |
cific | +4.255 |
Neg logit contributions | |
Idol | -11.160 |
Holo | -10.687 |
sych | -10.582 |
fw | -10.485 |
tremend | -10.410 |
Token | � |
Token ID | 447 |
Feature activation | -6.32e-03 |
Pos logit contributions | |
gaard | +3.082 |
ivist | +2.708 |
cific | +2.642 |
phies | +2.635 |
iors | +2.627 |
Neg logit contributions | |
Idol | -2.765 |
Holo | -2.655 |
sych | -2.600 |
fw | -2.595 |
tremend | -2.554 |
Token | � |
Token ID | 251 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
Idol | +0.029 |
tremend | +0.027 |
Holo | +0.027 |
sych | +0.027 |
fw | +0.027 |
Neg logit contributions | |
gaard | -0.031 |
ivist | -0.026 |
phies | -0.026 |
iors | -0.026 |
cific | -0.026 |
Token | served |
Token ID | 4983 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
gaard | +0.344 |
ivist | +0.301 |
cific | +0.297 |
phies | +0.296 |
iors | +0.293 |
Neg logit contributions | |
Idol | -0.309 |
Holo | -0.294 |
fw | -0.289 |
sych | -0.288 |
tremend | -0.282 |
Token | as |
Token ID | 355 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Idol | +1.319 |
Holo | +1.245 |
fw | +1.212 |
sych | +1.204 |
tremend | +1.186 |
Neg logit contributions | |
gaard | -1.865 |
ivist | -1.646 |
phies | -1.632 |
cific | -1.630 |
iferation | -1.614 |
Token | AN |
Token ID | 1565 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
gaard | +2.688 |
ivist | +2.439 |
iors | +2.365 |
cific | +2.350 |
phies | +2.345 |
Neg logit contributions | |
Idol | -1.994 |
fw | -1.904 |
Holo | -1.898 |
tremend | -1.870 |
sych | -1.838 |
Token | TS |
Token ID | 4694 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
Idol | +2.626 |
Holo | +2.465 |
ARA | +2.367 |
sych | +2.345 |
fw | +2.310 |
Neg logit contributions | |
gaard | -5.500 |
ivist | -4.991 |
cific | -4.899 |
phies | -4.885 |
iferation | -4.824 |
Token | � |
Token ID | 447 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
gaard | +0.174 |
ivist | +0.154 |
cific | +0.150 |
phies | +0.150 |
iors | +0.149 |
Neg logit contributions | |
Idol | -0.139 |
Holo | -0.132 |
fw | -0.130 |
sych | -0.130 |
tremend | -0.127 |
Token | � |
Token ID | 247 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
gaard | +1.943 |
ivist | +1.704 |
cific | +1.687 |
phies | +1.683 |
iors | +1.679 |
Neg logit contributions | |
Idol | -1.464 |
Holo | -1.390 |
fw | -1.373 |
tremend | -1.367 |
sych | -1.351 |
Token | C |
Token ID | 327 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
gaard | +1.061 |
ivist | +0.938 |
cific | +0.923 |
phies | +0.920 |
iors | +0.915 |
Neg logit contributions | |
Idol | -0.821 |
Holo | -0.778 |
fw | -0.762 |
sych | -0.760 |
tremend | -0.746 |
Token | OU |
Token ID | 2606 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
gaard | +1.373 |
ivist | +1.216 |
phies | +1.194 |
cific | +1.194 |
iors | +1.179 |
Neg logit contributions | |
Idol | -1.106 |
Holo | -1.050 |
sych | -1.020 |
fw | -1.019 |
tremend | -0.998 |
Token | NS |
Token ID | 8035 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
gaard | +8.948 |
gets | +7.653 |
ivist | +7.615 |
IVES | +7.593 |
cific | +7.562 |
Neg logit contributions | |
tremend | -7.927 |
Idol | -7.352 |
Holo | -7.333 |
srfAttach | -6.964 |
fw | -6.842 |
Token | EL |
Token ID | 3698 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
gaard | +0.870 |
ivist | +0.785 |
cific | +0.776 |
phies | +0.774 |
iors | +0.768 |
Neg logit contributions | |
Idol | -0.416 |
Holo | -0.387 |
fw | -0.377 |
sych | -0.375 |
tremend | -0.369 |
Token | : |
Token ID | 25 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
gaard | +0.924 |
ivist | +0.822 |
cific | +0.807 |
phies | +0.806 |
iors | +0.801 |
Neg logit contributions | |
Idol | -0.669 |
Holo | -0.635 |
fw | -0.620 |
sych | -0.620 |
tremend | -0.608 |
Token | When |
Token ID | 1649 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
gaard | +2.339 |
ivist | +2.072 |
cific | +2.048 |
iors | +2.026 |
gets | +2.012 |
Neg logit contributions | |
Idol | -1.605 |
tremend | -1.601 |
Holo | -1.533 |
sych | -1.531 |
fw | -1.521 |
Token | a |
Token ID | 257 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Idol | +0.796 |
Holo | +0.757 |
fw | +0.740 |
sych | +0.736 |
tremend | +0.717 |
Neg logit contributions | |
gaard | -0.939 |
ivist | -0.824 |
cific | -0.812 |
phies | -0.811 |
iferation | -0.802 |
Token | did |
Token ID | 750 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
Idol | +1.256 |
Holo | +1.192 |
fw | +1.169 |
sych | +1.164 |
tremend | +1.137 |
Neg logit contributions | |
gaard | -1.543 |
ivist | -1.360 |
cific | -1.341 |
phies | -1.337 |
iors | -1.324 |
Token | those |
Token ID | 883 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Idol | +1.624 |
Holo | +1.539 |
fw | +1.500 |
sych | +1.484 |
tremend | +1.452 |
Neg logit contributions | |
gaard | -2.168 |
ivist | -1.918 |
cific | -1.902 |
phies | -1.894 |
iferation | -1.875 |
Token | who |
Token ID | 508 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
Idol | +1.106 |
Holo | +1.048 |
fw | +1.026 |
sych | +1.017 |
tremend | +0.996 |
Neg logit contributions | |
gaard | -1.379 |
ivist | -1.217 |
cific | -1.203 |
phies | -1.200 |
iferation | -1.188 |
Token | held |
Token ID | 2714 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
Idol | +0.328 |
Holo | +0.313 |
fw | +0.307 |
sych | +0.306 |
tremend | +0.300 |
Neg logit contributions | |
gaard | -0.350 |
ivist | -0.305 |
cific | -0.301 |
phies | -0.299 |
iors | -0.297 |
Token | the |
Token ID | 262 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
gaard | +1.868 |
ivist | +1.671 |
cific | +1.631 |
phies | +1.623 |
iors | +1.614 |
Neg logit contributions | |
Idol | -1.352 |
Holo | -1.286 |
sych | -1.282 |
fw | -1.279 |
tremend | -1.228 |
Token | reins |
Token ID | 35627 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
gaard | +2.271 |
ivist | +2.015 |
phies | +1.965 |
cific | +1.960 |
iferation | +1.950 |
Neg logit contributions | |
Idol | -1.635 |
sych | -1.561 |
fw | -1.551 |
Holo | -1.548 |
tremend | -1.489 |
Token | of |
Token ID | 286 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
gaard | +7.846 |
ivist | +7.043 |
cific | +6.578 |
ivism | +6.492 |
phies | +6.433 |
Neg logit contributions | |
Idol | -8.227 |
sych | -8.114 |
Holo | -8.026 |
fw | -7.954 |
tremend | -7.780 |
Token | power |
Token ID | 1176 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
gaard | +7.004 |
ivist | +6.376 |
iferation | +6.198 |
cific | +6.164 |
phies | +6.151 |
Neg logit contributions | |
Idol | -2.665 |
sych | -2.626 |
fw | -2.540 |
Holo | -2.501 |
tremend | -2.326 |
Token | before |
Token ID | 878 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
gaard | +6.026 |
ivist | +5.415 |
cific | +5.123 |
ivism | +5.085 |
phies | +5.085 |
Neg logit contributions | |
Idol | -5.579 |
sych | -5.404 |
Holo | -5.385 |
fw | -5.362 |
tremend | -5.340 |
Token | them |
Token ID | 606 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
gaard | +3.562 |
ivist | +3.158 |
iors | +3.019 |
cific | +3.016 |
phies | +3.007 |
Neg logit contributions | |
Idol | -3.412 |
sych | -3.295 |
Holo | -3.281 |
fw | -3.255 |
tremend | -3.209 |
Token | : |
Token ID | 25 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Idol | +0.116 |
Holo | +0.109 |
fw | +0.107 |
sych | +0.106 |
tremend | +0.104 |
Neg logit contributions | |
gaard | -0.161 |
ivist | -0.142 |
cific | -0.141 |
phies | -0.141 |
iferation | -0.139 |
Token | uman |
Token ID | 3778 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
gaard | +1.415 |
ivist | +1.219 |
cific | +1.195 |
iors | +1.177 |
phies | +1.159 |
Neg logit contributions | |
tremend | -1.731 |
Idol | -1.707 |
Holo | -1.651 |
sych | -1.630 |
fw | -1.625 |
Token | used |
Token ID | 973 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Idol | +0.807 |
Holo | +0.770 |
fw | +0.754 |
sych | +0.753 |
tremend | +0.736 |
Neg logit contributions | |
gaard | -0.835 |
ivist | -0.728 |
cific | -0.717 |
phies | -0.715 |
iferation | -0.707 |
Token | to |
Token ID | 284 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
Idol | +1.228 |
Holo | +1.166 |
fw | +1.129 |
sych | +1.127 |
tremend | +1.097 |
Neg logit contributions | |
gaard | -1.693 |
ivist | -1.501 |
cific | -1.488 |
phies | -1.487 |
iferation | -1.473 |
Token | speak |
Token ID | 2740 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
gaard | +2.686 |
ivist | +2.341 |
cific | +2.320 |
iors | +2.315 |
phies | +2.310 |
Neg logit contributions | |
Idol | -2.000 |
Holo | -1.888 |
sych | -1.881 |
fw | -1.875 |
ARA | -1.843 |
Token | with |
Token ID | 351 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
gaard | +2.740 |
ivist | +2.441 |
cific | +2.371 |
phies | +2.355 |
iors | +2.350 |
Neg logit contributions | |
Idol | -2.135 |
Holo | -2.025 |
fw | -2.021 |
sych | -2.019 |
tremend | -1.959 |
Token | Saur |
Token ID | 46197 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
gaard | +0.156 |
ivist | +0.137 |
cific | +0.135 |
phies | +0.135 |
iors | +0.134 |
Neg logit contributions | |
Idol | -0.128 |
Holo | -0.122 |
fw | -0.119 |
sych | -0.119 |
tremend | -0.116 |
Token | on |
Token ID | 261 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
gaard | +5.182 |
iors | +4.090 |
ong | +4.065 |
ivist | +3.993 |
cific | +3.886 |
Neg logit contributions | |
tremend | -12.522 |
therap | -11.250 |
sych | -11.225 |
Skydragon | -11.084 |
Holo | -11.050 |
Token | and |
Token ID | 290 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
gaard | +1.245 |
ivist | +1.093 |
cific | +1.074 |
phies | +1.067 |
iors | +1.063 |
Neg logit contributions | |
Idol | -1.067 |
Holo | -1.013 |
fw | -1.004 |
sych | -1.000 |
tremend | -0.978 |
Token | through |
Token ID | 832 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
gaard | +1.041 |
ivist | +0.915 |
cific | +0.900 |
phies | +0.898 |
iors | +0.888 |
Neg logit contributions | |
Idol | -0.827 |
Holo | -0.785 |
fw | -0.780 |
sych | -0.779 |
tremend | -0.758 |
Token | which |
Token ID | 543 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
Idol | +1.060 |
Holo | +1.008 |
fw | +0.985 |
sych | +0.980 |
tremend | +0.958 |
Neg logit contributions | |
gaard | -1.252 |
ivist | -1.102 |
cific | -1.086 |
phies | -1.083 |
iors | -1.073 |
Token | Sar |
Token ID | 6866 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
gaard | +4.022 |
ivist | +3.515 |
cific | +3.430 |
phies | +3.421 |
gets | +3.397 |
Neg logit contributions | |
Idol | -3.599 |
sych | -3.464 |
fw | -3.450 |
Holo | -3.406 |
tremend | -3.387 |
Token | to |
Token ID | 284 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
gaard | +1.165 |
ivist | +1.020 |
cific | +1.010 |
phies | +1.002 |
iors | +0.995 |
Neg logit contributions | |
Idol | -0.990 |
Holo | -0.942 |
sych | -0.925 |
fw | -0.922 |
tremend | -0.903 |
Token | make |
Token ID | 787 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
Idol | +0.656 |
Holo | +0.625 |
fw | +0.613 |
sych | +0.611 |
tremend | +0.598 |
Neg logit contributions | |
gaard | -0.722 |
ivist | -0.632 |
cific | -0.622 |
phies | -0.620 |
iors | -0.614 |
Token | light |
Token ID | 1657 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Idol | +0.219 |
Holo | +0.208 |
fw | +0.204 |
sych | +0.203 |
tremend | +0.199 |
Neg logit contributions | |
gaard | -0.262 |
ivist | -0.231 |
cific | -0.227 |
phies | -0.227 |
iors | -0.224 |
Token | of |
Token ID | 286 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
gaard | +0.895 |
ivist | +0.797 |
cific | +0.790 |
iors | +0.780 |
phies | +0.779 |
Neg logit contributions | |
Idol | -0.730 |
Holo | -0.689 |
fw | -0.679 |
sych | -0.673 |
tremend | -0.660 |
Token | the |
Token ID | 262 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
gaard | +3.174 |
ivist | +2.789 |
phies | +2.724 |
iors | +2.700 |
cific | +2.697 |
Neg logit contributions | |
Idol | -2.586 |
Holo | -2.454 |
fw | -2.453 |
sych | -2.433 |
tremend | -2.403 |
Token | subject |
Token ID | 2426 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
gaard | +2.920 |
ivist | +2.566 |
cific | +2.532 |
phies | +2.529 |
iors | +2.508 |
Neg logit contributions | |
Idol | -1.978 |
Holo | -1.869 |
fw | -1.855 |
sych | -1.851 |
tremend | -1.795 |
Token | , |
Token ID | 11 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
gaard | +7.916 |
ivist | +7.375 |
ivism | +6.896 |
cific | +6.800 |
iors | +6.788 |
Neg logit contributions | |
Idol | -8.137 |
sych | -7.870 |
fw | -7.783 |
srfAttach | -7.763 |
Holo | -7.731 |
Token | but |
Token ID | 475 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
gaard | +1.331 |
ivist | +1.173 |
cific | +1.156 |
phies | +1.153 |
iors | +1.141 |
Neg logit contributions | |
Idol | -1.070 |
Holo | -1.016 |
fw | -0.997 |
sych | -0.995 |
tremend | -0.970 |
Token | I |
Token ID | 314 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
gaard | +1.809 |
ivist | +1.597 |
cific | +1.580 |
phies | +1.568 |
iors | +1.552 |
Neg logit contributions | |
Idol | -1.425 |
Holo | -1.351 |
fw | -1.331 |
sych | -1.328 |
tremend | -1.290 |
Token | felt |
Token ID | 2936 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
gaard | +1.347 |
ivist | +1.158 |
cific | +1.136 |
phies | +1.128 |
iors | +1.126 |
Neg logit contributions | |
Idol | -1.391 |
Holo | -1.334 |
fw | -1.314 |
sych | -1.305 |
tremend | -1.290 |
Token | like |
Token ID | 588 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
Idol | +0.155 |
Holo | +0.147 |
fw | +0.145 |
sych | +0.144 |
tremend | +0.140 |
Neg logit contributions | |
gaard | -0.192 |
ivist | -0.169 |
cific | -0.166 |
phies | -0.166 |
iors | -0.164 |
Token |
|
Token ID | 198 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
gaard | +0.325 |
ivist | +0.286 |
cific | +0.282 |
phies | +0.281 |
iors | +0.278 |
Neg logit contributions | |
Idol | -0.271 |
Holo | -0.258 |
fw | -0.253 |
sych | -0.252 |
tremend | -0.247 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
gaard | +0.655 |
ivist | +0.567 |
iors | +0.558 |
gets | +0.557 |
cific | +0.554 |
Neg logit contributions | |
tremend | -0.729 |
Idol | -0.681 |
Holo | -0.652 |
sych | -0.646 |
fw | -0.636 |
Token | Section |
Token ID | 16375 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
gaard | +0.894 |
ivist | +0.792 |
phies | +0.781 |
cific | +0.778 |
iors | +0.774 |
Neg logit contributions | |
Idol | -0.658 |
Holo | -0.622 |
fw | -0.604 |
sych | -0.600 |
tremend | -0.599 |
Token | III |
Token ID | 6711 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Idol | +0.226 |
Holo | +0.215 |
fw | +0.211 |
sych | +0.210 |
tremend | +0.205 |
Neg logit contributions | |
gaard | -0.274 |
ivist | -0.241 |
cific | -0.237 |
phies | -0.237 |
iors | -0.235 |
Token | : |
Token ID | 25 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
Idol | +1.613 |
Holo | +1.530 |
sych | +1.490 |
fw | +1.483 |
tremend | +1.421 |
Neg logit contributions | |
gaard | -2.189 |
ivist | -1.937 |
cific | -1.922 |
phies | -1.907 |
iferation | -1.898 |
Token | Lean |
Token ID | 45661 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
gaard | +0.244 |
ivist | +0.216 |
cific | +0.213 |
phies | +0.212 |
iors | +0.210 |
Neg logit contributions | |
Idol | -0.187 |
Holo | -0.177 |
fw | -0.174 |
sych | -0.173 |
tremend | -0.171 |
Token | Six |
Token ID | 9699 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
gaard | +9.244 |
ivist | +8.157 |
gets | +7.846 |
iors | +7.696 |
phies | +7.680 |
Neg logit contributions | |
Idol | -6.939 |
tremend | -6.703 |
fw | -6.684 |
Holo | -6.585 |
sych | -6.572 |
Token | Sigma |
Token ID | 31669 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Idol | +0.098 |
Holo | +0.092 |
sych | +0.089 |
fw | +0.089 |
tremend | +0.086 |
Neg logit contributions | |
gaard | -0.156 |
ivist | -0.141 |
cific | -0.139 |
phies | -0.138 |
iferation | -0.137 |
Token |
|
Token ID | 198 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Idol | +1.924 |
Holo | +1.817 |
fw | +1.766 |
sych | +1.764 |
Consortium | +1.691 |
Neg logit contributions | |
gaard | -2.523 |
ivist | -2.243 |
cific | -2.242 |
phies | -2.213 |
iferation | -2.205 |
Token |
|
Token ID | 198 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
gaard | +1.273 |
ivist | +1.101 |
iors | +1.085 |
gets | +1.080 |
cific | +1.072 |
Neg logit contributions | |
tremend | -1.500 |
Idol | -1.370 |
Holo | -1.313 |
sych | -1.299 |
therap | -1.297 |
Token | What |
Token ID | 2061 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
gaard | +1.481 |
ivist | +1.312 |
phies | +1.290 |
cific | +1.282 |
iors | +1.278 |
Neg logit contributions | |
Idol | -1.129 |
Holo | -1.071 |
tremend | -1.038 |
fw | -1.032 |
sych | -1.029 |
Token | 55 |
Token ID | 2816 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
gaard | +0.403 |
ivist | +0.359 |
cific | +0.354 |
iors | +0.353 |
phies | +0.351 |
Neg logit contributions | |
Idol | -0.250 |
tremend | -0.242 |
Holo | -0.236 |
sych | -0.230 |
fw | -0.226 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
gaard | +0.902 |
ivist | +0.782 |
iors | +0.764 |
cific | +0.762 |
phies | +0.741 |
Neg logit contributions | |
tremend | -1.050 |
Idol | -1.021 |
sych | -0.999 |
Holo | -0.996 |
fw | -0.989 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
gaard | +3.147 |
iors | +2.742 |
ivist | +2.735 |
cific | +2.660 |
gets | +2.657 |
Neg logit contributions | |
tremend | -4.436 |
therap | -3.857 |
Idol | -3.839 |
sych | -3.702 |
Holo | -3.681 |
Token |
|
Token ID | 198 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
gaard | +1.027 |
ivist | +0.888 |
iors | +0.885 |
gets | +0.878 |
cific | +0.868 |
Neg logit contributions | |
tremend | -1.222 |
Idol | -1.117 |
Holo | -1.069 |
sych | -1.061 |
therap | -1.057 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
gaard | +2.766 |
ivist | +2.487 |
iors | +2.480 |
cific | +2.471 |
gets | +2.445 |
Neg logit contributions | |
tremend | -2.203 |
Idol | -2.118 |
Holo | -2.014 |
therap | -1.963 |
sych | -1.944 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
gaard | +2.568 |
iors | +2.175 |
ivist | +2.066 |
cific | +1.827 |
IVES | +1.710 |
Neg logit contributions | |
tremend | -9.367 |
sych | -8.981 |
Idol | -8.943 |
fw | -8.750 |
ARA | -8.720 |
Token | this |
Token ID | 428 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
gaard | +5.740 |
iors | +5.213 |
cific | +5.186 |
gets | +5.182 |
ivist | +5.097 |
Neg logit contributions | |
tremend | -10.976 |
therap | -9.329 |
Idol | -8.992 |
etheless | -8.962 |
Skydragon | -8.858 |
Token | comment |
Token ID | 2912 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
gaard | +1.494 |
ivist | +1.202 |
cific | +1.186 |
iors | +1.166 |
gets | +1.136 |
Neg logit contributions | |
tremend | -2.680 |
Idol | -2.571 |
sych | -2.523 |
Holo | -2.509 |
fw | -2.498 |
Token | on |
Token ID | 319 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
gaard | +3.860 |
ivist | +3.415 |
iors | +3.324 |
gets | +3.246 |
cific | +3.224 |
Neg logit contributions | |
tremend | -5.578 |
therap | -4.839 |
Idol | -4.785 |
sych | -4.667 |
fw | -4.582 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
gaard | +1.205 |
ivist | +1.035 |
iors | +0.999 |
cific | +0.983 |
gets | +0.980 |
Neg logit contributions | |
tremend | -1.676 |
Idol | -1.609 |
sych | -1.562 |
Holo | -1.539 |
fw | -1.530 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
gaard | +2.200 |
ivist | +1.738 |
gets | +1.505 |
cific | +1.476 |
iors | +1.462 |
Neg logit contributions | |
tremend | -8.084 |
therap | -7.388 |
sych | -7.329 |
ARA | -7.105 |
Idol | -7.045 |
Token |
|
Token ID | 198 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
Idol | +1.310 |
Holo | +1.247 |
tremend | +1.242 |
sych | +1.224 |
fw | +1.223 |
Neg logit contributions | |
gaard | -1.457 |
ivist | -1.276 |
cific | -1.256 |
phies | -1.248 |
iors | -1.245 |
Token | . |
Token ID | 13 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
gaard | +0.242 |
ivist | +0.215 |
cific | +0.212 |
phies | +0.212 |
iors | +0.210 |
Neg logit contributions | |
Idol | -0.176 |
Holo | -0.166 |
sych | -0.162 |
fw | -0.162 |
tremend | -0.159 |
Token |
|
Token ID | 198 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Idol | +1.154 |
Holo | +1.100 |
fw | +1.074 |
sych | +1.059 |
tremend | +1.026 |
Neg logit contributions | |
gaard | -1.556 |
ivist | -1.380 |
cific | -1.360 |
phies | -1.353 |
iferation | -1.347 |
Token |
|
Token ID | 198 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
Idol | +1.858 |
Holo | +1.767 |
fw | +1.734 |
sych | +1.728 |
tremend | +1.700 |
Neg logit contributions | |
gaard | -2.149 |
ivist | -1.887 |
cific | -1.859 |
phies | -1.852 |
iors | -1.836 |
Token | ( |
Token ID | 7 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
Idol | +0.305 |
Holo | +0.289 |
fw | +0.284 |
sych | +0.281 |
tremend | +0.272 |
Neg logit contributions | |
gaard | -0.421 |
ivist | -0.374 |
cific | -0.369 |
phies | -0.367 |
iferation | -0.365 |
Token | Vis |
Token ID | 15854 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Idol | +1.773 |
Holo | +1.676 |
fw | +1.646 |
sych | +1.624 |
tremend | +1.579 |
Neg logit contributions | |
gaard | -2.507 |
ivist | -2.228 |
cific | -2.204 |
phies | -2.192 |
iferation | -2.182 |
Token | ited |
Token ID | 863 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
gaard | +5.455 |
ivist | +4.361 |
iors | +4.165 |
phies | +4.163 |
cific | +4.112 |
Neg logit contributions | |
Idol | -10.705 |
Holo | -10.232 |
fw | -10.223 |
sych | -10.191 |
tremend | -9.919 |
Token | 5 |
Token ID | 642 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
gaard | +5.678 |
ivist | +4.917 |
cific | +4.823 |
gets | +4.752 |
iors | +4.709 |
Neg logit contributions | |
tremend | -5.818 |
Idol | -5.663 |
sych | -5.564 |
fw | -5.534 |
Holo | -5.443 |
Token | , |
Token ID | 11 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
gaard | +3.464 |
ivist | +3.040 |
cific | +2.996 |
phies | +2.978 |
iors | +2.967 |
Neg logit contributions | |
Idol | -2.677 |
tremend | -2.565 |
Holo | -2.539 |
fw | -2.526 |
sych | -2.526 |
Token | 855 |
Token ID | 45432 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
gaard | +2.644 |
ivist | +2.345 |
cific | +2.310 |
phies | +2.299 |
iors | +2.285 |
Neg logit contributions | |
Idol | -1.915 |
Holo | -1.814 |
tremend | -1.785 |
fw | -1.775 |
sych | -1.772 |
Token | times |
Token ID | 1661 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
gaard | +4.080 |
ivist | +3.421 |
iors | +3.345 |
gets | +3.331 |
phies | +3.330 |
Neg logit contributions | |
Idol | -4.410 |
sych | -4.304 |
tremend | -4.262 |
fw | -4.251 |
Holo | -4.215 |
Token | it |
Token ID | 340 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
gaard | +0.476 |
ivist | +0.417 |
cific | +0.410 |
phies | +0.408 |
iors | +0.405 |
Neg logit contributions | |
Idol | -0.424 |
Holo | -0.405 |
sych | -0.397 |
fw | -0.397 |
tremend | -0.388 |
Token | will |
Token ID | 481 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
gaard | +0.414 |
ivist | +0.358 |
cific | +0.352 |
phies | +0.351 |
iors | +0.347 |
Neg logit contributions | |
Idol | -0.448 |
Holo | -0.428 |
fw | -0.421 |
sych | -0.420 |
tremend | -0.411 |
Token | become |
Token ID | 1716 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Idol | +0.334 |
Holo | +0.317 |
fw | +0.312 |
sych | +0.311 |
tremend | +0.304 |
Neg logit contributions | |
gaard | -0.385 |
ivist | -0.338 |
cific | -0.332 |
phies | -0.332 |
iors | -0.329 |
Token | for |
Token ID | 329 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
Idol | +1.216 |
Holo | +1.144 |
fw | +1.122 |
sych | +1.110 |
tremend | +1.086 |
Neg logit contributions | |
gaard | -1.651 |
ivist | -1.460 |
cific | -1.442 |
phies | -1.440 |
iferation | -1.429 |
Token | Mrs |
Token ID | 9074 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Idol | +0.365 |
Holo | +0.346 |
fw | +0.337 |
sych | +0.336 |
tremend | +0.328 |
Neg logit contributions | |
gaard | -0.478 |
ivist | -0.422 |
cific | -0.416 |
phies | -0.415 |
iferation | -0.412 |
Token | . |
Token ID | 13 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
gaard | +6.149 |
iors | +5.387 |
gets | +5.346 |
ivist | +5.175 |
cific | +5.121 |
Neg logit contributions | |
tremend | -11.121 |
therap | -9.543 |
eleph | -9.241 |
sych | -8.852 |
srfAttach | -8.541 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
gaard | +3.486 |
gets | +2.468 |
ivist | +2.463 |
iors | +2.336 |
cific | +2.323 |
Neg logit contributions | |
tremend | -13.357 |
sych | -12.138 |
therap | -12.046 |
fw | -11.681 |
Idol | -11.553 |
Token | . |
Token ID | 13 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
gaard | +4.089 |
ivist | +3.587 |
cific | +3.535 |
iors | +3.507 |
phies | +3.492 |
Neg logit contributions | |
Idol | -3.584 |
Holo | -3.485 |
sych | -3.459 |
fw | -3.387 |
tremend | -3.314 |
Token |
|
Token ID | 198 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
gaard | +1.416 |
ivist | +1.245 |
cific | +1.227 |
phies | +1.219 |
iors | +1.210 |
Neg logit contributions | |
Idol | -1.211 |
Holo | -1.155 |
fw | -1.140 |
sych | -1.140 |
tremend | -1.139 |
Token |
|
Token ID | 198 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
gaard | +0.456 |
ivist | +0.396 |
iors | +0.389 |
cific | +0.387 |
gets | +0.387 |
Neg logit contributions | |
tremend | -0.497 |
Idol | -0.471 |
Holo | -0.450 |
sych | -0.445 |
fw | -0.439 |
Token | But |
Token ID | 1537 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
gaard | +0.408 |
ivist | +0.363 |
cific | +0.358 |
phies | +0.357 |
iors | +0.354 |
Neg logit contributions | |
Idol | -0.297 |
Holo | -0.281 |
sych | -0.273 |
fw | -0.273 |
tremend | -0.271 |
Token | 5 |
Token ID | 20 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
gaard | +3.243 |
ivist | +2.873 |
iors | +2.821 |
cific | +2.820 |
gets | +2.816 |
Neg logit contributions | |
Idol | -2.211 |
Holo | -2.095 |
tremend | -2.070 |
sych | -2.039 |
fw | -2.019 |
Token | million |
Token ID | 1510 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
gaard | +2.274 |
ivist | +1.987 |
cific | +1.959 |
phies | +1.951 |
iors | +1.938 |
Neg logit contributions | |
Idol | -2.072 |
Holo | -1.968 |
fw | -1.950 |
sych | -1.940 |
tremend | -1.906 |
Token | Estimated |
Token ID | 47737 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
gaard | +1.223 |
ivist | +1.074 |
cific | +1.058 |
phies | +1.055 |
iors | +1.046 |
Neg logit contributions | |
Idol | -1.014 |
Holo | -0.964 |
fw | -0.950 |
sych | -0.946 |
tremend | -0.927 |
Token | number |
Token ID | 1271 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
gaard | +5.271 |
ivist | +4.590 |
phies | +4.540 |
cific | +4.523 |
iors | +4.488 |
Neg logit contributions | |
Idol | -4.276 |
fw | -4.118 |
sych | -4.105 |
Holo | -4.086 |
tremend | -4.028 |
Token | of |
Token ID | 286 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
gaard | +3.816 |
ivist | +3.323 |
phies | +3.224 |
cific | +3.221 |
iors | +3.165 |
Neg logit contributions | |
Idol | -4.036 |
tremend | -4.030 |
Holo | -3.903 |
sych | -3.899 |
fw | -3.862 |
Token | Buddh |
Token ID | 20921 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
gaard | +4.174 |
ivist | +3.705 |
phies | +3.644 |
cific | +3.631 |
iors | +3.628 |
Neg logit contributions | |
Idol | -2.881 |
fw | -2.734 |
Holo | -2.731 |
sych | -2.698 |
tremend | -2.667 |
Token | ists |
Token ID | 1023 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
gaard | +6.650 |
ivist | +6.024 |
iors | +5.835 |
phies | +5.657 |
gets | +5.606 |
Neg logit contributions | |
tremend | -10.258 |
Idol | -8.989 |
therap | -8.974 |
Holo | -8.846 |
srfAttach | -8.617 |
Token | in |
Token ID | 287 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
gaard | +4.109 |
ivist | +3.603 |
cific | +3.484 |
iors | +3.476 |
phies | +3.464 |
Neg logit contributions | |
Idol | -3.600 |
Holo | -3.457 |
fw | -3.421 |
sych | -3.412 |
tremend | -3.378 |
Token | the |
Token ID | 262 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
gaard | +3.984 |
ivist | +3.502 |
cific | +3.413 |
phies | +3.388 |
iferation | +3.366 |
Neg logit contributions | |
Idol | -3.439 |
fw | -3.314 |
Holo | -3.281 |
sych | -3.273 |
tremend | -3.242 |
Token | U |
Token ID | 471 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
gaard | +4.070 |
ivist | +3.522 |
cific | +3.404 |
phies | +3.364 |
iors | +3.351 |
Neg logit contributions | |
Idol | -4.204 |
fw | -4.117 |
sych | -4.027 |
Holo | -4.016 |
tremend | -3.989 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
gaard | +4.544 |
iors | +3.993 |
gets | +3.933 |
ivist | +3.864 |
cific | +3.814 |
Neg logit contributions | |
tremend | -6.866 |
therap | -5.849 |
Idol | -5.620 |
eleph | -5.590 |
Holo | -5.448 |
Token | / |
Token ID | 1220 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
gaard | +1.839 |
ivist | +1.615 |
cific | +1.591 |
phies | +1.585 |
iors | +1.577 |
Neg logit contributions | |
Idol | -1.542 |
Holo | -1.470 |
fw | -1.444 |
sych | -1.439 |
tremend | -1.408 |
Token | Courtesy |
Token ID | 22984 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
gaard | +0.980 |
ivist | +0.870 |
cific | +0.857 |
phies | +0.854 |
iors | +0.850 |
Neg logit contributions | |
Idol | -0.712 |
Holo | -0.672 |
fw | -0.664 |
sych | -0.661 |
tremend | -0.656 |
Token | Everett |
Token ID | 36815 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
gaard | +1.532 |
ivist | +1.347 |
cific | +1.328 |
phies | +1.324 |
iors | +1.311 |
Neg logit contributions | |
Idol | -1.289 |
Holo | -1.225 |
fw | -1.201 |
sych | -1.197 |
tremend | -1.170 |
Token | Collection |
Token ID | 12251 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
Idol | +3.247 |
Holo | +3.123 |
fw | +3.019 |
sych | +2.999 |
Barcl | +2.912 |
Neg logit contributions | |
gaard | -3.237 |
cific | -2.831 |
ivist | -2.799 |
phies | -2.789 |
iferation | -2.775 |
Token | Amy |
Token ID | 14235 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
gaard | +3.672 |
ivist | +3.221 |
cific | +3.150 |
iors | +3.139 |
phies | +3.110 |
Neg logit contributions | |
Idol | -3.362 |
fw | -3.248 |
tremend | -3.241 |
Holo | -3.229 |
sych | -3.185 |
Token | Sed |
Token ID | 22710 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
gaard | +1.740 |
ivist | +1.517 |
cific | +1.490 |
phies | +1.489 |
iors | +1.477 |
Neg logit contributions | |
Idol | -1.630 |
Holo | -1.558 |
fw | -1.536 |
sych | -1.525 |
tremend | -1.495 |
Token | aris |
Token ID | 20066 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
gaard | +8.410 |
iors | +7.378 |
ivist | +7.016 |
gets | +6.941 |
rees | +6.929 |
Neg logit contributions | |
tremend | -8.943 |
therap | -7.763 |
Idol | -7.595 |
Holo | -7.585 |
Skydragon | -7.173 |
Token | in |
Token ID | 287 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
gaard | +3.450 |
ivist | +2.999 |
iors | +2.941 |
phies | +2.910 |
gets | +2.903 |
Neg logit contributions | |
Idol | -3.034 |
Holo | -2.907 |
fw | -2.900 |
sych | -2.884 |
tremend | -2.831 |
Token | Str |
Token ID | 4285 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
gaard | +0.998 |
ivist | +0.878 |
cific | +0.863 |
phies | +0.857 |
iors | +0.856 |
Neg logit contributions | |
Idol | -0.823 |
Holo | -0.780 |
fw | -0.772 |
sych | -0.767 |
tremend | -0.753 |
Token | angers |
Token ID | 6606 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
gaard | +2.165 |
ivist | +1.916 |
cific | +1.873 |
phies | +1.862 |
iors | +1.842 |
Neg logit contributions | |
Idol | -1.980 |
Holo | -1.899 |
tremend | -1.879 |
fw | -1.857 |
sych | -1.841 |
Token | with |
Token ID | 351 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Idol | +0.351 |
Holo | +0.330 |
fw | +0.324 |
sych | +0.322 |
tremend | +0.313 |
Neg logit contributions | |
gaard | -0.482 |
ivist | -0.428 |
cific | -0.423 |
phies | -0.422 |
iferation | -0.418 |
Token | attorneys |
Token ID | 14449 |
Feature activation | +7.61e-03 |
Pos logit contributions | |
Idol | +1.722 |
Holo | +1.626 |
fw | +1.599 |
sych | +1.583 |
tremend | +1.533 |
Neg logit contributions | |
gaard | -1.899 |
ivist | -1.654 |
cific | -1.653 |
phies | -1.650 |
iors | -1.621 |
Token | general |
Token ID | 2276 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
gaard | +0.039 |
ivist | +0.034 |
iors | +0.033 |
phies | +0.033 |
cific | +0.033 |
Neg logit contributions | |
Idol | -0.033 |
Holo | -0.032 |
tremend | -0.031 |
fw | -0.030 |
sych | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
gaard | +0.152 |
ivist | +0.134 |
cific | +0.132 |
phies | +0.132 |
iors | +0.131 |
Neg logit contributions | |
Idol | -0.114 |
Holo | -0.108 |
fw | -0.106 |
sych | -0.105 |
tremend | -0.103 |
Token | oppose |
Token ID | 12856 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
gaard | +0.548 |
ivist | +0.483 |
cific | +0.480 |
phies | +0.475 |
iors | +0.474 |
Neg logit contributions | |
Idol | -0.412 |
Holo | -0.391 |
fw | -0.384 |
sych | -0.383 |
tremend | -0.374 |
Token | the |
Token ID | 262 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Idol | +2.095 |
Holo | +1.951 |
fw | +1.910 |
sych | +1.892 |
tremend | +1.830 |
Neg logit contributions | |
gaard | -2.881 |
ivist | -2.546 |
cific | -2.536 |
phies | -2.524 |
iors | -2.506 |
Token | confirmation |
Token ID | 12641 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Idol | +2.337 |
Holo | +2.211 |
fw | +2.156 |
sych | +2.144 |
tremend | +2.091 |
Neg logit contributions | |
gaard | -2.712 |
ivist | -2.374 |
cific | -2.363 |
phies | -2.347 |
iors | -2.321 |
Token | of |
Token ID | 286 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
Idol | +6.658 |
Holo | +6.031 |
sych | +5.801 |
fw | +5.782 |
ter | +5.755 |
Neg logit contributions | |
gaard | -11.998 |
cific | -10.784 |
iors | -10.677 |
gets | -10.656 |
phies | -10.470 |
Token | Mer |
Token ID | 4638 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
Idol | +2.931 |
Holo | +2.765 |
sych | +2.679 |
fw | +2.674 |
Barcl | +2.623 |
Neg logit contributions | |
gaard | -3.501 |
phies | -3.045 |
ivist | -3.033 |
cific | -3.029 |
iors | -2.992 |
Token | rick |
Token ID | 5557 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
gaard | +0.316 |
ivist | +0.278 |
cific | +0.273 |
phies | +0.271 |
iors | +0.269 |
Neg logit contributions | |
Idol | -0.287 |
Holo | -0.275 |
tremend | -0.269 |
fw | -0.267 |
sych | -0.266 |
Token | Garland |
Token ID | 35466 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Idol | +1.053 |
Holo | +0.995 |
fw | +0.975 |
sych | +0.969 |
tremend | +0.946 |
Neg logit contributions | |
gaard | -1.713 |
ivist | -1.530 |
cific | -1.507 |
phies | -1.503 |
iors | -1.493 |
Token | to |
Token ID | 284 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Idol | +1.320 |
Holo | +1.245 |
fw | +1.216 |
sych | +1.212 |
tremend | +1.176 |
Neg logit contributions | |
gaard | -1.857 |
ivist | -1.648 |
cific | -1.631 |
phies | -1.629 |
iors | -1.614 |
Token | member |
Token ID | 2888 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
Idol | +0.027 |
Holo | +0.026 |
fw | +0.025 |
sych | +0.025 |
tremend | +0.025 |
Neg logit contributions | |
gaard | -0.046 |
ivist | -0.041 |
cific | -0.041 |
phies | -0.041 |
iors | -0.040 |
Token | voted |
Token ID | 7052 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Idol | +1.442 |
Holo | +1.347 |
sych | +1.304 |
fw | +1.298 |
tremend | +1.265 |
Neg logit contributions | |
gaard | -1.838 |
ivist | -1.617 |
iferation | -1.609 |
cific | -1.605 |
phies | -1.600 |
Token | out |
Token ID | 503 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
Idol | +0.789 |
Holo | +0.748 |
fw | +0.735 |
sych | +0.731 |
tremend | +0.714 |
Neg logit contributions | |
gaard | -1.053 |
ivist | -0.932 |
cific | -0.919 |
phies | -0.916 |
iors | -0.908 |
Token | of |
Token ID | 286 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
Idol | +2.086 |
Holo | +1.961 |
sych | +1.901 |
fw | +1.896 |
tremend | +1.848 |
Neg logit contributions | |
gaard | -2.697 |
ivist | -2.377 |
phies | -2.351 |
cific | -2.346 |
iferation | -2.343 |
Token | San |
Token ID | 2986 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
Idol | +1.570 |
Holo | +1.475 |
sych | +1.420 |
fw | +1.418 |
tremend | +1.380 |
Neg logit contributions | |
gaard | -2.232 |
ivist | -1.993 |
cific | -1.960 |
phies | -1.955 |
iferation | -1.946 |
Token | Juan |
Token ID | 16852 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Idol | +2.243 |
Holo | +2.165 |
fw | +2.042 |
sych | +2.022 |
Barcl | +1.963 |
Neg logit contributions | |
gaard | -2.640 |
ivist | -2.360 |
cific | -2.323 |
iferation | -2.318 |
phies | -2.306 |
Token | Del |
Token ID | 4216 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
Idol | +6.837 |
Holo | +5.928 |
fw | +5.462 |
sych | +5.454 |
Consortium | +5.322 |
Neg logit contributions | |
gaard | -12.347 |
iferation | -11.260 |
ivist | -11.120 |
cific | -11.005 |
gets | -10.911 |
Token | Sur |
Token ID | 4198 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Idol | +2.485 |
Holo | +2.358 |
fw | +2.312 |
sych | +2.301 |
tremend | +2.246 |
Neg logit contributions | |
gaard | -3.013 |
ivist | -2.652 |
cific | -2.615 |
phies | -2.607 |
iors | -2.581 |
Token | . |
Token ID | 13 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Idol | +1.944 |
Holo | +1.826 |
fw | +1.770 |
sych | +1.765 |
tremend | +1.714 |
Neg logit contributions | |
gaard | -2.546 |
ivist | -2.258 |
cific | -2.222 |
phies | -2.217 |
iferation | -2.211 |
Token | As |
Token ID | 1081 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
gaard | +2.328 |
ivist | +2.032 |
cific | +1.997 |
phies | +1.989 |
iors | +1.985 |
Neg logit contributions | |
Idol | -2.093 |
tremend | -2.065 |
Holo | -2.002 |
fw | -2.002 |
sych | -1.988 |
Token | the |
Token ID | 262 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Idol | +1.044 |
Holo | +0.990 |
fw | +0.969 |
sych | +0.966 |
tremend | +0.941 |
Neg logit contributions | |
gaard | -1.321 |
ivist | -1.167 |
cific | -1.150 |
phies | -1.146 |
iferation | -1.136 |
Token | Coach |
Token ID | 16393 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
gaard | +0.000 |
ivist | +0.000 |
cific | +0.000 |
phies | +0.000 |
iors | +0.000 |
Neg logit contributions | |
Idol | -0.000 |
Holo | -0.000 |
fw | -0.000 |
sych | -0.000 |
tremend | -0.000 |
Token | returns |
Token ID | 5860 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
gaard | +1.257 |
ivist | +1.096 |
cific | +1.077 |
phies | +1.076 |
iors | +1.067 |
Neg logit contributions | |
Idol | -1.181 |
Holo | -1.127 |
fw | -1.117 |
sych | -1.108 |
tremend | -1.089 |
Token | to |
Token ID | 284 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Idol | +1.825 |
Holo | +1.726 |
fw | +1.689 |
sych | +1.682 |
tremend | +1.641 |
Neg logit contributions | |
gaard | -2.501 |
ivist | -2.218 |
cific | -2.189 |
phies | -2.183 |
iors | -2.162 |
Token | Recap |
Token ID | 46585 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Idol | +0.766 |
Holo | +0.727 |
fw | +0.722 |
sych | +0.719 |
tremend | +0.700 |
Neg logit contributions | |
gaard | -0.931 |
ivist | -0.818 |
cific | -0.807 |
phies | -0.805 |
iors | -0.797 |
Token | San |
Token ID | 2986 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
gaard | +1.394 |
ivist | +1.235 |
cific | +1.209 |
phies | +1.206 |
iors | +1.204 |
Neg logit contributions | |
Idol | -1.118 |
fw | -1.067 |
Holo | -1.065 |
sych | -1.059 |
tremend | -1.041 |
Token | Juan |
Token ID | 16852 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Idol | +0.548 |
Holo | +0.523 |
fw | +0.509 |
sych | +0.507 |
tremend | +0.492 |
Neg logit contributions | |
gaard | -0.579 |
ivist | -0.506 |
cific | -0.500 |
phies | -0.495 |
iferation | -0.493 |
Token | Del |
Token ID | 4216 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
Idol | +6.455 |
Holo | +5.692 |
fw | +5.279 |
sych | +5.178 |
ter | +5.102 |
Neg logit contributions | |
gaard | -12.361 |
iferation | -11.329 |
cific | -11.191 |
ivist | -11.058 |
phies | -10.919 |
Token | Sur |
Token ID | 4198 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Idol | +1.996 |
Holo | +1.896 |
fw | +1.860 |
sych | +1.853 |
tremend | +1.813 |
Neg logit contributions | |
gaard | -2.403 |
ivist | -2.115 |
cific | -2.085 |
phies | -2.079 |
iors | -2.058 |
Token | Episode |
Token ID | 7922 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Idol | +0.417 |
Holo | +0.396 |
sych | +0.391 |
fw | +0.391 |
tremend | +0.383 |
Neg logit contributions | |
gaard | -0.534 |
ivist | -0.472 |
cific | -0.463 |
phies | -0.463 |
iors | -0.461 |
Token | 5 |
Token ID | 642 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
gaard | +2.320 |
ivist | +2.045 |
phies | +1.993 |
cific | +1.988 |
iors | +1.973 |
Neg logit contributions | |
Idol | -2.099 |
Holo | -2.005 |
sych | -2.005 |
fw | -1.996 |
tremend | -1.986 |
Token |
|
Token ID | 198 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Idol | +1.963 |
Holo | +1.868 |
fw | +1.809 |
sych | +1.802 |
tremend | +1.735 |
Neg logit contributions | |
gaard | -2.469 |
ivist | -2.172 |
cific | -2.161 |
phies | -2.140 |
iferation | -2.139 |
Token | this |
Token ID | 428 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
gaard | +1.221 |
ivist | +1.078 |
cific | +1.071 |
phies | +1.064 |
iors | +1.057 |
Neg logit contributions | |
Idol | -0.840 |
Holo | -0.792 |
fw | -0.790 |
sych | -0.787 |
tremend | -0.761 |
Token | shootout |
Token ID | 34995 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
Idol | +0.605 |
Holo | +0.572 |
fw | +0.562 |
sych | +0.561 |
tremend | +0.546 |
Neg logit contributions | |
gaard | -0.850 |
ivist | -0.753 |
cific | -0.744 |
phies | -0.739 |
iors | -0.734 |
Token | , |
Token ID | 11 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
gaard | +0.262 |
ivist | +0.230 |
cific | +0.228 |
phies | +0.226 |
iors | +0.224 |
Neg logit contributions | |
Idol | -0.210 |
Holo | -0.199 |
fw | -0.197 |
sych | -0.196 |
tremend | -0.191 |
Token | I |
Token ID | 314 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Idol | +1.103 |
Holo | +1.043 |
fw | +1.018 |
sych | +1.013 |
tremend | +0.989 |
Neg logit contributions | |
gaard | -1.495 |
ivist | -1.326 |
cific | -1.308 |
phies | -1.305 |
iors | -1.292 |
Token | was |
Token ID | 373 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Idol | +1.056 |
Holo | +1.005 |
fw | +0.986 |
sych | +0.981 |
tremend | +0.962 |
Neg logit contributions | |
gaard | -1.277 |
ivist | -1.121 |
cific | -1.106 |
phies | -1.101 |
iors | -1.093 |
Token | torn |
Token ID | 12445 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Idol | +0.594 |
Holo | +0.566 |
fw | +0.557 |
sych | +0.556 |
tremend | +0.540 |
Neg logit contributions | |
gaard | -0.717 |
ivist | -0.629 |
cific | -0.619 |
phies | -0.616 |
iors | -0.613 |
Token | on |
Token ID | 319 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
Idol | +6.980 |
Holo | +6.550 |
ter | +6.273 |
Barcl | +6.266 |
fw | +6.224 |
Neg logit contributions | |
gaard | -11.283 |
iferation | -10.098 |
cific | -9.994 |
phies | -9.987 |
ivist | -9.796 |
Token | whether |
Token ID | 1771 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Idol | +2.970 |
Holo | +2.805 |
fw | +2.697 |
sych | +2.675 |
tremend | +2.631 |
Neg logit contributions | |
gaard | -4.274 |
ivist | -3.842 |
phies | -3.776 |
cific | -3.775 |
iferation | -3.762 |
Token | or |
Token ID | 393 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
Idol | +0.809 |
Holo | +0.769 |
fw | +0.752 |
sych | +0.748 |
tremend | +0.732 |
Neg logit contributions | |
gaard | -0.937 |
ivist | -0.824 |
cific | -0.812 |
phies | -0.810 |
iors | -0.802 |
Token | not |
Token ID | 407 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
gaard | +0.423 |
ivist | +0.371 |
cific | +0.368 |
iors | +0.364 |
gets | +0.359 |
Neg logit contributions | |
Idol | -0.389 |
tremend | -0.383 |
sych | -0.372 |
Holo | -0.369 |
fw | -0.361 |
Token | this |
Token ID | 428 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
gaard | +1.650 |
ivist | +1.447 |
cific | +1.436 |
phies | +1.429 |
iors | +1.411 |
Neg logit contributions | |
Idol | -1.289 |
Holo | -1.227 |
fw | -1.216 |
sych | -1.216 |
tremend | -1.182 |
Token | by |
Token ID | 416 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
Idol | +1.327 |
Holo | +1.255 |
fw | +1.228 |
sych | +1.215 |
tremend | +1.187 |
Neg logit contributions | |
gaard | -1.749 |
ivist | -1.536 |
cific | -1.532 |
phies | -1.530 |
iferation | -1.513 |
Token | him |
Token ID | 683 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
gaard | +0.173 |
ivist | +0.153 |
cific | +0.151 |
phies | +0.151 |
iors | +0.149 |
Neg logit contributions | |
Idol | -0.133 |
Holo | -0.126 |
fw | -0.123 |
sych | -0.123 |
tremend | -0.120 |
Token | smiling |
Token ID | 16755 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
Idol | +3.215 |
Holo | +3.057 |
fw | +2.998 |
sych | +2.980 |
tremend | +2.888 |
Neg logit contributions | |
gaard | -4.073 |
ivist | -3.582 |
phies | -3.576 |
cific | -3.569 |
iferation | -3.535 |
Token | , |
Token ID | 11 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
gaard | +2.621 |
ivist | +2.317 |
iors | +2.265 |
cific | +2.255 |
phies | +2.233 |
Neg logit contributions | |
Idol | -2.311 |
Holo | -2.199 |
sych | -2.168 |
fw | -2.168 |
tremend | -2.120 |
Token | being |
Token ID | 852 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
gaard | +2.695 |
ivist | +2.352 |
phies | +2.312 |
cific | +2.305 |
iors | +2.293 |
Neg logit contributions | |
Idol | -2.247 |
Holo | -2.135 |
sych | -2.132 |
fw | -2.114 |
tremend | -2.078 |
Token | torn |
Token ID | 12445 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Idol | +0.425 |
Holo | +0.403 |
fw | +0.396 |
sych | +0.393 |
tremend | +0.385 |
Neg logit contributions | |
gaard | -0.574 |
ivist | -0.509 |
cific | -0.502 |
phies | -0.499 |
iors | -0.496 |
Token | , |
Token ID | 11 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
Idol | +6.353 |
Holo | +5.846 |
fw | +5.536 |
sych | +5.489 |
ter | +5.405 |
Neg logit contributions | |
gaard | -11.668 |
cific | -10.535 |
phies | -10.463 |
iferation | -10.420 |
ivist | -10.218 |
Token | or |
Token ID | 393 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
Idol | +0.055 |
Holo | +0.052 |
fw | +0.051 |
sych | +0.051 |
tremend | +0.050 |
Neg logit contributions | |
gaard | -0.063 |
ivist | -0.056 |
cific | -0.055 |
phies | -0.055 |
iors | -0.054 |
Token | becoming |
Token ID | 5033 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
gaard | +2.242 |
ivist | +1.966 |
cific | +1.932 |
gets | +1.929 |
phies | +1.927 |
Neg logit contributions | |
Idol | -1.811 |
fw | -1.719 |
Holo | -1.719 |
sych | -1.700 |
tremend | -1.676 |
Token | enraged |
Token ID | 37530 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
Idol | +1.822 |
Holo | +1.719 |
fw | +1.671 |
sych | +1.668 |
tremend | +1.627 |
Neg logit contributions | |
gaard | -2.598 |
ivist | -2.301 |
phies | -2.277 |
cific | -2.272 |
iferation | -2.253 |
Token | , |
Token ID | 11 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
gaard | +0.326 |
ivist | +0.287 |
cific | +0.283 |
phies | +0.282 |
iors | +0.279 |
Neg logit contributions | |
Idol | -0.268 |
Holo | -0.254 |
fw | -0.249 |
sych | -0.248 |
tremend | -0.242 |
Token | episode |
Token ID | 4471 |
Feature activation | -3.15e-03 |
Pos logit contributions | |
Idol | +0.175 |
Holo | +0.166 |
fw | +0.163 |
sych | +0.163 |
tremend | +0.159 |
Neg logit contributions | |
gaard | -0.225 |
ivist | -0.199 |
cific | -0.196 |
phies | -0.196 |
iors | -0.194 |
Token | 5 |
Token ID | 642 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
Idol | +0.014 |
Holo | +0.013 |
sych | +0.013 |
fw | +0.013 |
tremend | +0.013 |
Neg logit contributions | |
gaard | -0.016 |
ivist | -0.014 |
cific | -0.013 |
phies | -0.013 |
iors | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
Idol | +1.804 |
Holo | +1.715 |
fw | +1.675 |
sych | +1.664 |
tremend | +1.612 |
Neg logit contributions | |
gaard | -2.271 |
ivist | -1.998 |
cific | -1.980 |
phies | -1.966 |
iferation | -1.958 |
Token | Survivor |
Token ID | 23740 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
Idol | +3.379 |
Holo | +3.160 |
sych | +3.001 |
fw | +3.000 |
Barcl | +2.914 |
Neg logit contributions | |
gaard | -4.365 |
ivist | -3.881 |
iferation | -3.838 |
cific | -3.833 |
phies | -3.782 |
Token | San |
Token ID | 2986 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
gaard | +0.139 |
ivist | +0.122 |
cific | +0.120 |
phies | +0.120 |
iors | +0.120 |
Neg logit contributions | |
Idol | -0.112 |
Holo | -0.107 |
fw | -0.106 |
sych | -0.105 |
tremend | -0.104 |
Token | Juan |
Token ID | 16852 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Idol | +0.987 |
Holo | +0.944 |
fw | +0.907 |
sych | +0.891 |
tremend | +0.856 |
Neg logit contributions | |
gaard | -1.707 |
ivist | -1.533 |
cific | -1.521 |
phies | -1.508 |
iferation | -1.503 |
Token | Del |
Token ID | 4216 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Idol | +7.905 |
Holo | +7.363 |
fw | +6.636 |
ter | +6.629 |
sych | +6.606 |
Neg logit contributions | |
gaard | -10.595 |
iferation | -9.620 |
ivist | -9.153 |
cific | -9.151 |
phies | -9.030 |
Token | Sur |
Token ID | 4198 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
Idol | +1.180 |
Holo | +1.119 |
sych | +1.084 |
fw | +1.084 |
tremend | +1.047 |
Neg logit contributions | |
gaard | -1.516 |
ivist | -1.336 |
cific | -1.326 |
phies | -1.315 |
iferation | -1.308 |
Token | featuring |
Token ID | 9593 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
Idol | +2.009 |
Holo | +1.901 |
fw | +1.855 |
sych | +1.847 |
tremend | +1.800 |
Neg logit contributions | |
gaard | -2.609 |
ivist | -2.307 |
cific | -2.278 |
phies | -2.270 |
iferation | -2.251 |
Token | Coach |
Token ID | 16393 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
gaard | +0.284 |
ivist | +0.249 |
cific | +0.246 |
phies | +0.245 |
iors | +0.243 |
Neg logit contributions | |
Idol | -0.238 |
Holo | -0.227 |
fw | -0.224 |
sych | -0.223 |
tremend | -0.218 |
Token | ( |
Token ID | 357 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
gaard | +1.170 |
ivist | +1.024 |
cific | +1.009 |
phies | +1.003 |
iors | +0.998 |
Neg logit contributions | |
Idol | -1.023 |
Holo | -0.977 |
fw | -0.972 |
sych | -0.960 |
tremend | -0.955 |
Token | oll |
Token ID | 692 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
gaard | +0.131 |
ivist | +0.116 |
cific | +0.114 |
phies | +0.113 |
iors | +0.113 |
Neg logit contributions | |
Idol | -0.105 |
Holo | -0.100 |
tremend | -0.098 |
sych | -0.096 |
fw | -0.096 |
Token | um |
Token ID | 388 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
Idol | +2.074 |
Holo | +1.984 |
fw | +1.952 |
sych | +1.945 |
tremend | +1.895 |
Neg logit contributions | |
gaard | -1.827 |
ivist | -1.571 |
cific | -1.544 |
phies | -1.540 |
iors | -1.521 |
Token | – |
Token ID | 784 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Idol | +3.206 |
Holo | +3.055 |
sych | +2.968 |
fw | +2.948 |
Barcl | +2.900 |
Neg logit contributions | |
gaard | -3.117 |
ivist | -2.718 |
cific | -2.699 |
iferation | -2.693 |
phies | -2.676 |
Token | who |
Token ID | 508 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
Idol | +0.422 |
Holo | +0.401 |
fw | +0.394 |
sych | +0.393 |
tremend | +0.384 |
Neg logit contributions | |
gaard | -0.540 |
ivist | -0.477 |
cific | -0.469 |
phies | -0.468 |
iors | -0.464 |
Token | is |
Token ID | 318 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
Idol | +2.746 |
Holo | +2.609 |
sych | +2.522 |
fw | +2.506 |
Barcl | +2.464 |
Neg logit contributions | |
gaard | -2.938 |
ivist | -2.561 |
cific | -2.558 |
iferation | -2.541 |
phies | -2.526 |
Token | torn |
Token ID | 12445 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Idol | +0.141 |
Holo | +0.133 |
fw | +0.132 |
sych | +0.131 |
tremend | +0.128 |
Neg logit contributions | |
gaard | -0.181 |
ivist | -0.160 |
cific | -0.157 |
phies | -0.156 |
iors | -0.156 |
Token | between |
Token ID | 1022 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
Idol | +6.295 |
Holo | +5.728 |
alleg | +5.367 |
fw | +5.355 |
sych | +5.312 |
Neg logit contributions | |
gaard | -11.847 |
cific | -10.800 |
phies | -10.661 |
iferation | -10.531 |
aceae | -10.377 |
Token | his |
Token ID | 465 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
Idol | +2.775 |
Holo | +2.598 |
fw | +2.502 |
sych | +2.464 |
tremend | +2.428 |
Neg logit contributions | |
gaard | -4.193 |
cific | -3.741 |
ivist | -3.727 |
phies | -3.722 |
iferation | -3.683 |
Token | loyalty |
Token ID | 15843 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
Idol | +2.531 |
Holo | +2.368 |
fw | +2.306 |
sych | +2.285 |
tremend | +2.231 |
Neg logit contributions | |
gaard | -3.694 |
ivist | -3.284 |
cific | -3.275 |
phies | -3.264 |
iferation | -3.224 |
Token | to |
Token ID | 284 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
Idol | +2.564 |
Holo | +2.351 |
fw | +2.256 |
sych | +2.243 |
Barcl | +2.226 |
Neg logit contributions | |
gaard | -4.148 |
cific | -3.721 |
phies | -3.670 |
ivist | -3.642 |
iferation | -3.633 |
Token | Fro |
Token ID | 9734 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
Idol | +2.317 |
Holo | +2.200 |
fw | +2.121 |
sych | +2.103 |
Barcl | +2.052 |
Neg logit contributions | |
gaard | -2.945 |
ivist | -2.604 |
cific | -2.601 |
phies | -2.583 |
iferation | -2.551 |
Token | en |
Token ID | 551 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
Idol | +1.966 |
Holo | +1.863 |
fw | +1.824 |
sych | +1.810 |
tremend | +1.766 |
Neg logit contributions | |
gaard | -2.717 |
ivist | -2.408 |
cific | -2.377 |
phies | -2.370 |
iferation | -2.352 |
Token | o |
Token ID | 78 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Idol | +3.005 |
Holo | +2.873 |
fw | +2.866 |
sych | +2.806 |
ARA | +2.709 |
Neg logit contributions | |
gaard | -3.655 |
ivist | -3.195 |
cific | -3.159 |
phies | -3.129 |
iferation | -3.124 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
Idol | +1.690 |
Holo | +1.602 |
fw | +1.577 |
sych | +1.557 |
tremend | +1.514 |
Neg logit contributions | |
gaard | -2.349 |
ivist | -2.082 |
cific | -2.061 |
phies | -2.056 |
iferation | -2.043 |
Token | or |
Token ID | 393 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
Idol | +1.746 |
Holo | +1.657 |
fw | +1.631 |
sych | +1.618 |
tremend | +1.579 |
Neg logit contributions | |
gaard | -2.203 |
ivist | -1.944 |
cific | -1.917 |
phies | -1.912 |
iferation | -1.895 |
Token | w |
Token ID | 266 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
Idol | +2.579 |
Holo | +2.451 |
fw | +2.398 |
sych | +2.360 |
tremend | +2.310 |
Neg logit contributions | |
gaard | -3.490 |
ivist | -3.093 |
cific | -3.055 |
phies | -3.051 |
iferation | -3.036 |
Token | lan |
Token ID | 9620 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Idol | +1.572 |
fw | +1.458 |
Holo | +1.454 |
sych | +1.418 |
tremend | +1.341 |
Neg logit contributions | |
gaard | -3.490 |
ivist | -3.144 |
phies | -3.113 |
cific | -3.108 |
iferation | -3.100 |
Token | 0 |
Token ID | 15 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
fw | +6.104 |
Idol | +5.841 |
Holo | +5.670 |
ter | +5.364 |
sych | +5.277 |
Neg logit contributions | |
gaard | -11.685 |
phies | -10.718 |
iferation | -10.700 |
ivist | -10.673 |
iors | -10.424 |
Token | . |
Token ID | 13 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
Idol | +3.912 |
fw | +3.745 |
Holo | +3.710 |
sych | +3.588 |
tremend | +3.472 |
Neg logit contributions | |
gaard | -5.330 |
ivist | -4.693 |
iferation | -4.664 |
cific | -4.661 |
phies | -4.651 |
Token | Mine |
Token ID | 11517 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Idol | +1.575 |
Holo | +1.493 |
fw | +1.464 |
sych | +1.459 |
tremend | +1.427 |
Neg logit contributions | |
gaard | -2.013 |
ivist | -1.778 |
cific | -1.753 |
phies | -1.748 |
iors | -1.732 |
Token | just |
Token ID | 655 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Idol | +1.273 |
Holo | +1.211 |
fw | +1.190 |
sych | +1.183 |
tremend | +1.156 |
Neg logit contributions | |
gaard | -1.420 |
ivist | -1.244 |
cific | -1.226 |
phies | -1.222 |
iors | -1.209 |
Token | happens |
Token ID | 4325 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Idol | +0.533 |
Holo | +0.509 |
fw | +0.500 |
sych | +0.499 |
tremend | +0.489 |
Neg logit contributions | |
gaard | -0.523 |
ivist | -0.455 |
cific | -0.447 |
phies | -0.446 |
iors | -0.441 |
Token | and |
Token ID | 290 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
Idol | +4.481 |
Holo | +4.296 |
sych | +4.211 |
fw | +4.127 |
Consortium | +4.034 |
Neg logit contributions | |
gaard | -6.002 |
ivist | -5.366 |
cific | -5.316 |
phies | -5.277 |
iors | -5.259 |
Token | other |
Token ID | 584 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Idol | +1.830 |
Holo | +1.724 |
fw | +1.690 |
sych | +1.680 |
tremend | +1.639 |
Neg logit contributions | |
gaard | -2.749 |
ivist | -2.448 |
cific | -2.417 |
phies | -2.410 |
iors | -2.388 |
Token | non |
Token ID | 1729 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Idol | +5.224 |
Holo | +5.029 |
sych | +4.784 |
fw | +4.629 |
Consortium | +4.488 |
Neg logit contributions | |
gaard | -8.948 |
ivist | -8.081 |
phies | -8.007 |
iors | -7.916 |
iferation | -7.908 |
Token | in |
Token ID | 259 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
Idol | +0.608 |
Holo | +0.573 |
fw | +0.560 |
sych | +0.558 |
tremend | +0.542 |
Neg logit contributions | |
gaard | -0.944 |
ivist | -0.842 |
cific | -0.832 |
phies | -0.830 |
iors | -0.822 |
Token | vasive |
Token ID | 23747 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
Idol | +1.594 |
Holo | +1.502 |
fw | +1.454 |
sych | +1.452 |
ARA | +1.384 |
Neg logit contributions | |
gaard | -3.011 |
phies | -2.699 |
ivist | -2.697 |
cific | -2.672 |
iferation | -2.660 |
Token | imaging |
Token ID | 19560 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Idol | +1.254 |
Holo | +1.170 |
fw | +1.148 |
sych | +1.137 |
tremend | +1.112 |
Neg logit contributions | |
gaard | -2.352 |
ivist | -2.114 |
cific | -2.089 |
phies | -2.081 |
iors | -2.065 |
Token | techniques |
Token ID | 7605 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Idol | +6.232 |
Holo | +5.946 |
sych | +5.794 |
Consortium | +5.591 |
fw | +5.503 |
Neg logit contributions | |
gaard | -11.592 |
iferation | -10.448 |
ivist | -10.383 |
phies | -10.306 |
iors | -10.302 |
Token | , |
Token ID | 11 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
Idol | +4.244 |
Holo | +4.035 |
sych | +3.880 |
fw | +3.877 |
Barcl | +3.732 |
Neg logit contributions | |
gaard | -6.149 |
ivist | -5.434 |
iors | -5.385 |
iferation | -5.382 |
phies | -5.378 |
Token | which |
Token ID | 543 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Idol | +3.262 |
Holo | +3.129 |
fw | +2.951 |
sych | +2.942 |
Barcl | +2.894 |
Neg logit contributions | |
gaard | -4.746 |
ivist | -4.203 |
iors | -4.177 |
phies | -4.150 |
iferation | -4.138 |
Token | have |
Token ID | 423 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
Idol | +1.470 |
Holo | +1.390 |
fw | +1.361 |
sych | +1.355 |
tremend | +1.322 |
Neg logit contributions | |
gaard | -2.054 |
ivist | -1.824 |
cific | -1.799 |
phies | -1.794 |
iors | -1.778 |
Token | revealed |
Token ID | 4602 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Idol | +0.394 |
Holo | +0.374 |
fw | +0.370 |
sych | +0.367 |
tremend | +0.360 |
Neg logit contributions | |
gaard | -0.453 |
ivist | -0.398 |
cific | -0.393 |
phies | -0.391 |
iors | -0.387 |
Token | Spirit |
Token ID | 7710 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
Idol | +1.784 |
Holo | +1.678 |
sych | +1.631 |
fw | +1.629 |
tremend | +1.563 |
Neg logit contributions | |
gaard | -2.320 |
ivist | -2.048 |
cific | -2.034 |
phies | -2.020 |
iferation | -1.999 |
Token | " |
Token ID | 1 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
gaard | +0.265 |
ivist | +0.235 |
cific | +0.232 |
phies | +0.231 |
iors | +0.230 |
Neg logit contributions | |
Idol | -0.183 |
Holo | -0.173 |
fw | -0.169 |
sych | -0.169 |
tremend | -0.165 |
Token | in |
Token ID | 287 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Idol | +0.029 |
Holo | +0.028 |
fw | +0.027 |
sych | +0.027 |
tremend | +0.026 |
Neg logit contributions | |
gaard | -0.035 |
ivist | -0.031 |
cific | -0.031 |
phies | -0.031 |
iors | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
gaard | +1.887 |
ivist | +1.668 |
cific | +1.646 |
phies | +1.638 |
iors | +1.633 |
Neg logit contributions | |
Idol | -1.405 |
fw | -1.327 |
sych | -1.326 |
Holo | -1.322 |
tremend | -1.296 |
Token | bar |
Token ID | 2318 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
gaard | +2.788 |
ivist | +2.471 |
cific | +2.429 |
phies | +2.402 |
iors | +2.394 |
Neg logit contributions | |
Idol | -2.034 |
fw | -1.915 |
sych | -1.895 |
Holo | -1.887 |
tremend | -1.847 |
Token | bers |
Token ID | 1213 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
gaard | +0.350 |
ivist | +0.308 |
cific | +0.304 |
phies | +0.303 |
iors | +0.300 |
Neg logit contributions | |
Idol | -0.289 |
Holo | -0.274 |
fw | -0.270 |
sych | -0.269 |
tremend | -0.263 |
Token | hop |
Token ID | 8548 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Idol | +6.378 |
ter | +5.796 |
Holo | +5.764 |
fw | +5.648 |
sych | +5.578 |
Neg logit contributions | |
gaard | -10.933 |
iferation | -10.018 |
phies | -9.980 |
ivist | -9.941 |
iors | -9.929 |
Token | quart |
Token ID | 28176 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Idol | +2.178 |
Holo | +2.070 |
fw | +1.996 |
sych | +1.987 |
tremend | +1.945 |
Neg logit contributions | |
gaard | -2.830 |
ivist | -2.498 |
phies | -2.478 |
cific | -2.477 |
iferation | -2.450 |
Token | et |
Token ID | 316 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Idol | +1.305 |
Holo | +1.246 |
fw | +1.223 |
sych | +1.219 |
tremend | +1.194 |
Neg logit contributions | |
gaard | -1.326 |
ivist | -1.154 |
cific | -1.136 |
phies | -1.132 |
iors | -1.120 |
Token | with |
Token ID | 351 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
gaard | +0.916 |
ivist | +0.806 |
cific | +0.792 |
phies | +0.786 |
iors | +0.784 |
Neg logit contributions | |
Idol | -0.756 |
Holo | -0.715 |
fw | -0.713 |
sych | -0.710 |
tremend | -0.693 |
Token | Sam |
Token ID | 3409 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
Idol | +0.047 |
Holo | +0.045 |
fw | +0.044 |
sych | +0.044 |
tremend | +0.043 |
Neg logit contributions | |
gaard | -0.060 |
ivist | -0.053 |
cific | -0.052 |
phies | -0.052 |
iors | -0.052 |
Token | campaign |
Token ID | 1923 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
Idol | +2.193 |
Holo | +2.087 |
sych | +2.014 |
fw | +2.011 |
tremend | +1.951 |
Neg logit contributions | |
gaard | -2.897 |
ivist | -2.594 |
cific | -2.565 |
iferation | -2.535 |
phies | -2.524 |
Token | was |
Token ID | 373 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Idol | +1.544 |
Holo | +1.460 |
fw | +1.427 |
sych | +1.425 |
tremend | +1.382 |
Neg logit contributions | |
gaard | -1.806 |
ivist | -1.590 |
cific | -1.579 |
iferation | -1.563 |
phies | -1.562 |
Token | more |
Token ID | 517 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
Idol | +0.445 |
Holo | +0.421 |
fw | +0.415 |
sych | +0.412 |
tremend | +0.401 |
Neg logit contributions | |
gaard | -0.590 |
ivist | -0.521 |
cific | -0.514 |
phies | -0.513 |
iors | -0.509 |
Token | of |
Token ID | 286 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Idol | +3.114 |
Holo | +2.952 |
sych | +2.831 |
fw | +2.791 |
tremend | +2.762 |
Neg logit contributions | |
gaard | -4.152 |
ivist | -3.701 |
iferation | -3.666 |
phies | -3.665 |
cific | -3.663 |
Token | the |
Token ID | 262 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
Idol | +1.425 |
Holo | +1.339 |
sych | +1.294 |
fw | +1.287 |
tremend | +1.262 |
Neg logit contributions | |
gaard | -1.979 |
ivist | -1.769 |
cific | -1.746 |
phies | -1.742 |
iferation | -1.731 |
Token | same |
Token ID | 976 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Idol | +1.611 |
Holo | +1.500 |
sych | +1.426 |
fw | +1.423 |
tremend | +1.354 |
Neg logit contributions | |
gaard | -3.712 |
ivist | -3.387 |
cific | -3.354 |
phies | -3.342 |
iferation | -3.314 |
Token | , |
Token ID | 11 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
Idol | +6.506 |
Holo | +5.908 |
sych | +5.720 |
ter | +5.683 |
Barcl | +5.682 |
Neg logit contributions | |
gaard | -10.933 |
iferation | -9.875 |
cific | -9.818 |
phies | -9.783 |
ivist | -9.742 |
Token | with |
Token ID | 351 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Idol | +1.143 |
Holo | +1.087 |
fw | +1.061 |
sych | +1.053 |
tremend | +1.030 |
Neg logit contributions | |
gaard | -1.467 |
ivist | -1.298 |
cific | -1.286 |
phies | -1.274 |
iferation | -1.267 |
Token | 1100 |
Token ID | 36566 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
gaard | +0.821 |
ivist | +0.717 |
cific | +0.706 |
phies | +0.704 |
iors | +0.699 |
Neg logit contributions | |
Idol | -0.705 |
Holo | -0.671 |
fw | -0.662 |
sych | -0.659 |
tremend | -0.647 |
Token | yards |
Token ID | 5695 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
Idol | +0.284 |
Holo | +0.273 |
fw | +0.268 |
sych | +0.266 |
tremend | +0.260 |
Neg logit contributions | |
gaard | -0.261 |
ivist | -0.227 |
cific | -0.224 |
phies | -0.222 |
iferation | -0.220 |
Token | at |
Token ID | 379 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
gaard | +2.721 |
ivist | +2.373 |
phies | +2.306 |
cific | +2.287 |
iors | +2.285 |
Neg logit contributions | |
Idol | -2.544 |
Holo | -2.406 |
sych | -2.400 |
fw | -2.367 |
tremend | -2.363 |
Token | richest |
Token ID | 24348 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
Idol | +2.067 |
Holo | +1.961 |
fw | +1.892 |
sych | +1.880 |
tremend | +1.842 |
Neg logit contributions | |
gaard | -2.852 |
ivist | -2.512 |
cific | -2.495 |
phies | -2.479 |
iferation | -2.472 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
gaard | +3.273 |
ivist | +2.888 |
iors | +2.842 |
phies | +2.783 |
cific | +2.766 |
Neg logit contributions | |
Idol | -3.343 |
sych | -3.206 |
Holo | -3.167 |
fw | -3.162 |
tremend | -3.147 |
Token | %, |
Token ID | 7441 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
gaard | +0.011 |
ivist | +0.010 |
cific | +0.010 |
phies | +0.009 |
iors | +0.009 |
Neg logit contributions | |
Idol | -0.012 |
Holo | -0.012 |
fw | -0.011 |
sych | -0.011 |
tremend | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
Idol | +0.768 |
Holo | +0.728 |
fw | +0.713 |
sych | +0.709 |
tremend | +0.692 |
Neg logit contributions | |
gaard | -1.008 |
ivist | -0.891 |
cific | -0.880 |
phies | -0.877 |
iferation | -0.869 |
Token | picture |
Token ID | 4286 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
Idol | +0.167 |
Holo | +0.157 |
fw | +0.156 |
sych | +0.156 |
tremend | +0.153 |
Neg logit contributions | |
gaard | -0.220 |
ivist | -0.195 |
phies | -0.191 |
cific | -0.190 |
iors | -0.190 |
Token | changes |
Token ID | 2458 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
gaard | +0.251 |
ivist | +0.217 |
cific | +0.213 |
phies | +0.212 |
iors | +0.210 |
Neg logit contributions | |
Idol | -0.280 |
Holo | -0.268 |
fw | -0.263 |
sych | -0.263 |
tremend | -0.259 |
Token | completely |
Token ID | 3190 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
Idol | +6.428 |
Holo | +6.131 |
tremend | +5.985 |
fw | +5.940 |
alleg | +5.835 |
Neg logit contributions | |
gaard | -10.619 |
phies | -9.757 |
iferation | -9.560 |
cific | -9.397 |
ivist | -9.221 |
Token | . |
Token ID | 13 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
Idol | +2.221 |
Holo | +2.092 |
fw | +2.054 |
sych | +2.046 |
tremend | +1.994 |
Neg logit contributions | |
gaard | -3.047 |
phies | -2.685 |
ivist | -2.679 |
cific | -2.665 |
iferation | -2.648 |
Token | Men |
Token ID | 6065 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Idol | +1.766 |
Holo | +1.673 |
fw | +1.621 |
sych | +1.609 |
Barcl | +1.549 |
Neg logit contributions | |
gaard | -2.370 |
ivist | -2.096 |
cific | -2.072 |
phies | -2.072 |
iferation | -2.057 |
Token | from |
Token ID | 422 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Idol | +0.661 |
Holo | +0.626 |
fw | +0.614 |
sych | +0.612 |
tremend | +0.599 |
Neg logit contributions | |
gaard | -0.855 |
ivist | -0.756 |
cific | -0.744 |
phies | -0.742 |
iors | -0.737 |
Token | such |
Token ID | 884 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
Idol | +0.697 |
Holo | +0.660 |
fw | +0.645 |
sych | +0.641 |
tremend | +0.627 |
Neg logit contributions | |
gaard | -0.944 |
ivist | -0.836 |
cific | -0.826 |
phies | -0.823 |
iferation | -0.815 |
Token | Harry |
Token ID | 5850 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
gaard | +3.353 |
ivist | +2.924 |
phies | +2.841 |
cific | +2.841 |
iors | +2.838 |
Neg logit contributions | |
Idol | -2.954 |
sych | -2.805 |
Holo | -2.801 |
fw | -2.769 |
tremend | -2.736 |
Token | Potter |
Token ID | 14179 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Idol | +0.086 |
Holo | +0.080 |
fw | +0.079 |
sych | +0.078 |
tremend | +0.076 |
Neg logit contributions | |
gaard | -0.153 |
ivist | -0.137 |
phies | -0.135 |
cific | -0.135 |
iors | -0.134 |
Token | sitting |
Token ID | 5586 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
gaard | +0.806 |
ivist | +0.705 |
cific | +0.693 |
phies | +0.692 |
iors | +0.687 |
Neg logit contributions | |
Idol | -0.689 |
Holo | -0.655 |
fw | -0.644 |
sych | -0.641 |
tremend | -0.628 |
Token | under |
Token ID | 739 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
gaard | +3.834 |
ivist | +3.372 |
iors | +3.268 |
gets | +3.257 |
cific | +3.234 |
Neg logit contributions | |
Idol | -3.548 |
fw | -3.443 |
Holo | -3.411 |
sych | -3.403 |
tremend | -3.359 |
Token | the |
Token ID | 262 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
gaard | +5.749 |
ivist | +5.057 |
phies | +4.942 |
gets | +4.877 |
iors | +4.789 |
Neg logit contributions | |
Idol | -5.165 |
fw | -4.944 |
Holo | -4.890 |
sych | -4.857 |
tremend | -4.842 |
Token | sorting |
Token ID | 29407 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
gaard | +2.221 |
ivist | +1.961 |
phies | +1.931 |
cific | +1.909 |
gets | +1.903 |
Neg logit contributions | |
Idol | -1.625 |
Holo | -1.535 |
fw | -1.533 |
sych | -1.513 |
tremend | -1.513 |
Token | hat |
Token ID | 6877 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
Idol | +6.788 |
Holo | +6.158 |
ter | +6.097 |
fw | +6.019 |
jack | +5.939 |
Neg logit contributions | |
gaard | -10.274 |
cific | -9.618 |
iors | -9.229 |
phies | -9.221 |
ivist | -9.055 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Idol | +1.386 |
Holo | +1.314 |
fw | +1.277 |
sych | +1.268 |
tremend | +1.226 |
Neg logit contributions | |
gaard | -1.856 |
ivist | -1.635 |
cific | -1.629 |
phies | -1.620 |
iferation | -1.615 |
Token | I |
Token ID | 314 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
gaard | +2.106 |
ivist | +1.837 |
cific | +1.808 |
phies | +1.798 |
iors | +1.791 |
Neg logit contributions | |
Idol | -1.820 |
tremend | -1.756 |
sych | -1.726 |
Holo | -1.721 |
fw | -1.713 |
Token | knew |
Token ID | 2993 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
gaard | +1.256 |
ivist | +1.078 |
cific | +1.057 |
phies | +1.050 |
iors | +1.046 |
Neg logit contributions | |
Idol | -1.294 |
Holo | -1.237 |
fw | -1.223 |
sych | -1.215 |
tremend | -1.203 |
Token | exactly |
Token ID | 3446 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
Idol | +1.015 |
Holo | +0.959 |
fw | +0.942 |
sych | +0.940 |
tremend | +0.917 |
Neg logit contributions | |
gaard | -1.370 |
ivist | -1.214 |
cific | -1.195 |
phies | -1.193 |
iors | -1.184 |
Token | distinctive |
Token ID | 18778 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Idol | +2.144 |
Holo | +2.040 |
fw | +1.977 |
sych | +1.955 |
tremend | +1.893 |
Neg logit contributions | |
gaard | -3.106 |
ivist | -2.751 |
cific | -2.719 |
phies | -2.717 |
iferation | -2.693 |
Token | characteristics |
Token ID | 9695 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Idol | +1.257 |
Holo | +1.190 |
fw | +1.163 |
sych | +1.157 |
tremend | +1.126 |
Neg logit contributions | |
gaard | -1.773 |
ivist | -1.573 |
cific | -1.554 |
phies | -1.549 |
iors | -1.535 |
Token | that |
Token ID | 326 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Idol | +2.677 |
Holo | +2.553 |
fw | +2.484 |
sych | +2.450 |
tremend | +2.360 |
Neg logit contributions | |
gaard | -3.895 |
ivist | -3.406 |
cific | -3.397 |
phies | -3.396 |
iferation | -3.385 |
Token | set |
Token ID | 900 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Idol | +0.489 |
Holo | +0.463 |
fw | +0.457 |
sych | +0.455 |
tremend | +0.444 |
Neg logit contributions | |
gaard | -0.661 |
ivist | -0.585 |
cific | -0.578 |
phies | -0.572 |
iors | -0.571 |
Token | them |
Token ID | 606 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
Idol | +2.326 |
Holo | +2.238 |
fw | +2.177 |
sych | +2.162 |
tremend | +2.120 |
Neg logit contributions | |
gaard | -2.130 |
ivist | -1.830 |
phies | -1.823 |
cific | -1.808 |
iferation | -1.783 |
Token | apart |
Token ID | 5475 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Idol | +1.359 |
Holo | +1.189 |
fw | +1.119 |
sych | +1.108 |
tremend | +1.041 |
Neg logit contributions | |
gaard | -5.414 |
phies | -4.936 |
ivist | -4.935 |
cific | -4.894 |
iferation | -4.889 |
Token | from |
Token ID | 422 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
Idol | +5.622 |
Holo | +5.336 |
fw | +5.254 |
ter | +4.894 |
sych | +4.887 |
Neg logit contributions | |
gaard | -11.118 |
phies | -10.162 |
iferation | -9.856 |
gets | -9.825 |
cific | -9.704 |
Token | the |
Token ID | 262 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Idol | +3.281 |
Holo | +3.170 |
fw | +2.962 |
sych | +2.917 |
Barcl | +2.871 |
Neg logit contributions | |
gaard | -4.858 |
phies | -4.338 |
cific | -4.338 |
ivist | -4.330 |
iferation | -4.276 |
Token | integrated |
Token ID | 11521 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Idol | +2.554 |
Holo | +2.436 |
fw | +2.320 |
sych | +2.294 |
tremend | +2.239 |
Neg logit contributions | |
gaard | -3.647 |
ivist | -3.257 |
phies | -3.235 |
cific | -3.226 |
iors | -3.200 |
Token | library |
Token ID | 5888 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
gaard | +1.865 |
ivist | +1.672 |
cific | +1.622 |
phies | +1.614 |
iors | +1.614 |
Neg logit contributions | |
Idol | -1.288 |
sych | -1.205 |
Holo | -1.205 |
fw | -1.198 |
tremend | -1.185 |
Token | systems |
Token ID | 3341 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
gaard | +1.539 |
ivist | +1.368 |
cific | +1.342 |
phies | +1.333 |
iors | +1.328 |
Neg logit contributions | |
Idol | -1.118 |
Holo | -1.052 |
sych | -1.035 |
fw | -1.034 |
tremend | -1.013 |
Token | only |
Token ID | 691 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
gaard | +0.201 |
ivist | +0.179 |
phies | +0.175 |
cific | +0.175 |
iors | +0.175 |
Neg logit contributions | |
Idol | -0.159 |
Holo | -0.151 |
fw | -0.150 |
sych | -0.149 |
tremend | -0.146 |
Token | a |
Token ID | 257 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
Idol | +1.526 |
Holo | +1.450 |
fw | +1.417 |
sych | +1.409 |
tremend | +1.373 |
Neg logit contributions | |
gaard | -1.876 |
ivist | -1.649 |
cific | -1.629 |
phies | -1.624 |
iferation | -1.610 |
Token | focus |
Token ID | 2962 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Idol | +2.523 |
Holo | +2.417 |
fw | +2.348 |
sych | +2.325 |
tremend | +2.247 |
Neg logit contributions | |
gaard | -3.126 |
ivist | -2.744 |
cific | -2.716 |
phies | -2.709 |
iferation | -2.681 |
Token | of |
Token ID | 286 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
gaard | +0.630 |
ivist | +0.558 |
cific | +0.546 |
phies | +0.543 |
iors | +0.540 |
Neg logit contributions | |
Idol | -0.518 |
Holo | -0.492 |
fw | -0.485 |
sych | -0.483 |
tremend | -0.473 |
Token | the |
Token ID | 262 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Idol | +0.596 |
Holo | +0.562 |
fw | +0.551 |
sych | +0.549 |
tremend | +0.534 |
Neg logit contributions | |
gaard | -0.870 |
ivist | -0.774 |
cific | -0.763 |
phies | -0.761 |
iors | -0.755 |
Token | magnet |
Token ID | 19972 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Idol | +1.140 |
Holo | +1.071 |
fw | +1.046 |
sych | +1.041 |
tremend | +1.012 |
Neg logit contributions | |
gaard | -1.915 |
ivist | -1.715 |
cific | -1.693 |
phies | -1.689 |
iors | -1.675 |
Token | school |
Token ID | 1524 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
Idol | +6.007 |
Holo | +5.553 |
sych | +5.379 |
fw | +5.269 |
ter | +5.252 |
Neg logit contributions | |
gaard | -10.945 |
phies | -10.047 |
cific | -9.744 |
iferation | -9.562 |
ivist | -9.533 |
Token | , |
Token ID | 11 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
Idol | +3.603 |
Holo | +3.380 |
fw | +3.235 |
sych | +3.228 |
tremend | +3.152 |
Neg logit contributions | |
gaard | -5.570 |
phies | -5.040 |
ivist | -4.973 |
cific | -4.963 |
iferation | -4.912 |
Token | the |
Token ID | 262 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Idol | +2.078 |
Holo | +1.980 |
fw | +1.913 |
sych | +1.890 |
tremend | +1.846 |
Neg logit contributions | |
gaard | -2.720 |
ivist | -2.395 |
phies | -2.376 |
cific | -2.372 |
iferation | -2.350 |
Token | founders |
Token ID | 22202 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Idol | +2.191 |
Holo | +2.078 |
fw | +2.009 |
sych | +1.998 |
tremend | +1.944 |
Neg logit contributions | |
gaard | -3.130 |
ivist | -2.781 |
phies | -2.760 |
cific | -2.751 |
iferation | -2.717 |
Token | explain |
Token ID | 4727 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
gaard | +0.767 |
ivist | +0.671 |
cific | +0.655 |
phies | +0.652 |
iors | +0.651 |
Neg logit contributions | |
Idol | -0.679 |
Holo | -0.646 |
fw | -0.639 |
sych | -0.633 |
tremend | -0.626 |
Token | benefits |
Token ID | 4034 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Idol | +0.915 |
Holo | +0.861 |
fw | +0.842 |
sych | +0.837 |
tremend | +0.815 |
Neg logit contributions | |
gaard | -1.478 |
ivist | -1.320 |
cific | -1.303 |
phies | -1.300 |
iors | -1.290 |
Token | , |
Token ID | 11 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
Idol | +3.832 |
Holo | +3.560 |
fw | +3.532 |
sych | +3.493 |
Barcl | +3.371 |
Neg logit contributions | |
gaard | -5.578 |
ivist | -4.928 |
cific | -4.922 |
phies | -4.910 |
iferation | -4.861 |
Token | killed |
Token ID | 2923 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
gaard | +0.351 |
ivist | +0.310 |
cific | +0.306 |
phies | +0.305 |
iors | +0.302 |
Neg logit contributions | |
Idol | -0.277 |
Holo | -0.263 |
fw | -0.258 |
sych | -0.257 |
tremend | -0.251 |
Token | voluntary |
Token ID | 16171 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Idol | +0.778 |
Holo | +0.735 |
fw | +0.719 |
sych | +0.716 |
tremend | +0.697 |
Neg logit contributions | |
gaard | -1.066 |
ivist | -0.944 |
cific | -0.932 |
phies | -0.929 |
iors | -0.921 |
Token | sever |
Token ID | 1750 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Idol | +0.425 |
Holo | +0.404 |
fw | +0.395 |
sych | +0.394 |
tremend | +0.387 |
Neg logit contributions | |
gaard | -0.633 |
ivist | -0.563 |
phies | -0.554 |
cific | -0.554 |
iors | -0.551 |
Token | ance |
Token ID | 590 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Idol | +6.186 |
Holo | +5.843 |
fw | +5.730 |
sych | +5.729 |
Barcl | +5.583 |
Neg logit contributions | |
gaard | -5.053 |
cific | -4.303 |
phies | -4.274 |
ivist | -4.244 |
iferation | -4.160 |
Token | benefits |
Token ID | 4034 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
Idol | +6.519 |
Holo | +5.736 |
sych | +5.679 |
fw | +5.650 |
jack | +5.584 |
Neg logit contributions | |
gaard | -10.678 |
iferation | -9.464 |
cific | -9.427 |
ivist | -9.414 |
phies | -9.403 |
Token | , |
Token ID | 11 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Idol | +1.745 |
Holo | +1.638 |
fw | +1.613 |
sych | +1.601 |
tremend | +1.547 |
Neg logit contributions | |
gaard | -2.360 |
ivist | -2.088 |
phies | -2.063 |
cific | -2.061 |
iferation | -2.035 |
Token | forced |
Token ID | 4137 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Idol | +0.804 |
Holo | +0.760 |
sych | +0.745 |
fw | +0.742 |
tremend | +0.722 |
Neg logit contributions | |
gaard | -0.957 |
ivist | -0.843 |
cific | -0.832 |
phies | -0.828 |
iferation | -0.821 |
Token | them |
Token ID | 606 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Idol | +1.175 |
Holo | +1.110 |
fw | +1.079 |
sych | +1.078 |
tremend | +1.044 |
Neg logit contributions | |
gaard | -1.562 |
ivist | -1.383 |
cific | -1.367 |
phies | -1.362 |
iferation | -1.353 |
Token | to |
Token ID | 284 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Idol | +1.265 |
Holo | +1.173 |
sych | +1.157 |
fw | +1.157 |
tremend | +1.119 |
Neg logit contributions | |
gaard | -1.926 |
ivist | -1.712 |
cific | -1.700 |
phies | -1.688 |
iors | -1.684 |
Token | name |
Token ID | 1438 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
gaard | +3.030 |
ivist | +2.714 |
iors | +2.577 |
cific | +2.546 |
gets | +2.543 |
Neg logit contributions | |
Idol | -2.709 |
Holo | -2.576 |
sych | -2.564 |
fw | -2.547 |
Barcl | -2.511 |
Token | is |
Token ID | 318 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
gaard | +4.536 |
ivist | +3.989 |
cific | +3.894 |
phies | +3.855 |
iors | +3.855 |
Neg logit contributions | |
Idol | -4.015 |
fw | -3.854 |
Holo | -3.848 |
sych | -3.835 |
tremend | -3.781 |
Token | in |
Token ID | 287 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
gaard | +0.374 |
ivist | +0.328 |
cific | +0.324 |
phies | +0.323 |
iors | +0.319 |
Neg logit contributions | |
Idol | -0.325 |
Holo | -0.309 |
fw | -0.303 |
sych | -0.302 |
tremend | -0.296 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Idol | +1.388 |
Holo | +1.295 |
fw | +1.248 |
sych | +1.247 |
tremend | +1.201 |
Neg logit contributions | |
gaard | -2.899 |
ivist | -2.607 |
phies | -2.589 |
cific | -2.586 |
iferation | -2.560 |
Token | returns |
Token ID | 5860 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
gaard | +0.540 |
ivist | +0.475 |
cific | +0.468 |
phies | +0.467 |
iors | +0.462 |
Neg logit contributions | |
Idol | -0.440 |
Holo | -0.418 |
fw | -0.412 |
sych | -0.411 |
tremend | -0.401 |
Token | � |
Token ID | 126 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Idol | +0.316 |
Holo | +0.300 |
fw | +0.293 |
sych | +0.291 |
tremend | +0.285 |
Neg logit contributions | |
gaard | -0.409 |
ivist | -0.361 |
cific | -0.358 |
phies | -0.356 |
iors | -0.353 |
Token | � |
Token ID | 245 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Idol | +5.664 |
Holo | +5.303 |
fw | +5.075 |
sych | +5.002 |
ter | +4.760 |
Neg logit contributions | |
gaard | -11.008 |
ivist | -10.367 |
iferation | -10.117 |
cific | -10.044 |
gets | -9.844 |
Token | and |
Token ID | 392 |
Feature activation | +4.31e-03 |
Pos logit contributions | |
gaard | +0.864 |
ivist | +0.766 |
cific | +0.754 |
phies | +0.752 |
iors | +0.747 |
Neg logit contributions | |
Idol | -0.644 |
Holo | -0.609 |
fw | -0.595 |
sych | -0.594 |
tremend | -0.582 |
Token | just |
Token ID | 655 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
gaard | +0.023 |
ivist | +0.020 |
cific | +0.020 |
phies | +0.020 |
iors | +0.020 |
Neg logit contributions | |
Idol | -0.017 |
Holo | -0.016 |
fw | -0.016 |
sych | -0.016 |
tremend | -0.016 |
Token | how |
Token ID | 703 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
gaard | +1.344 |
ivist | +1.185 |
cific | +1.172 |
phies | +1.161 |
iors | +1.152 |
Neg logit contributions | |
Idol | -1.123 |
Holo | -1.065 |
fw | -1.044 |
sych | -1.043 |
tremend | -1.022 |
Token | bad |
Token ID | 2089 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
gaard | +1.871 |
ivist | +1.637 |
cific | +1.609 |
iors | +1.599 |
phies | +1.598 |
Neg logit contributions | |
Idol | -1.642 |
Holo | -1.563 |
fw | -1.562 |
sych | -1.556 |
tremend | -1.505 |
Token | to |
Token ID | 284 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Idol | +2.855 |
Holo | +2.683 |
fw | +2.646 |
sych | +2.628 |
Barcl | +2.504 |
Neg logit contributions | |
gaard | -3.844 |
ivist | -3.455 |
phies | -3.428 |
cific | -3.380 |
iferation | -3.366 |
Token | a |
Token ID | 257 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Idol | +1.824 |
Holo | +1.713 |
fw | +1.670 |
sych | +1.664 |
tremend | +1.594 |
Neg logit contributions | |
gaard | -2.837 |
ivist | -2.536 |
phies | -2.506 |
cific | -2.493 |
iferation | -2.489 |
Token | member |
Token ID | 2888 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
Idol | +0.897 |
Holo | +0.841 |
fw | +0.820 |
sych | +0.816 |
tremend | +0.792 |
Neg logit contributions | |
gaard | -1.590 |
ivist | -1.427 |
cific | -1.410 |
phies | -1.407 |
iors | -1.395 |
Token | of |
Token ID | 286 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
Idol | +2.194 |
Holo | +2.027 |
sych | +1.993 |
fw | +1.972 |
Barcl | +1.882 |
Neg logit contributions | |
gaard | -3.134 |
phies | -2.805 |
gets | -2.765 |
iferation | -2.761 |
ivist | -2.734 |
Token | the |
Token ID | 262 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
Idol | +1.986 |
Holo | +1.850 |
sych | +1.776 |
fw | +1.774 |
Barcl | +1.698 |
Neg logit contributions | |
gaard | -3.194 |
ivist | -2.840 |
phies | -2.820 |
iferation | -2.807 |
cific | -2.802 |
Token | same |
Token ID | 976 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Idol | +2.263 |
Holo | +2.128 |
sych | +2.066 |
fw | +2.059 |
tremend | +1.986 |
Neg logit contributions | |
gaard | -3.561 |
ivist | -3.177 |
phies | -3.146 |
cific | -3.142 |
iferation | -3.124 |
Token | - |
Token ID | 12 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
Idol | +4.506 |
Holo | +4.042 |
sych | +3.990 |
ter | +3.627 |
fw | +3.555 |
Neg logit contributions | |
gaard | -12.198 |
phies | -11.045 |
cific | -11.002 |
iferation | -10.948 |
gets | -10.869 |
Token | sex |
Token ID | 8044 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
Idol | +2.245 |
Holo | +2.109 |
fw | +2.060 |
sych | +2.053 |
tremend | +1.947 |
Neg logit contributions | |
gaard | -4.041 |
ivist | -3.628 |
phies | -3.586 |
cific | -3.583 |
iferation | -3.555 |
Token | in |
Token ID | 287 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Idol | +3.706 |
Holo | +3.475 |
fw | +3.358 |
sych | +3.353 |
Consortium | +3.226 |
Neg logit contributions | |
gaard | -5.001 |
phies | -4.434 |
ivist | -4.392 |
cific | -4.379 |
iors | -4.368 |
Token | another |
Token ID | 1194 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
gaard | +0.811 |
ivist | +0.720 |
cific | +0.709 |
phies | +0.704 |
iors | +0.701 |
Neg logit contributions | |
Idol | -0.602 |
Holo | -0.569 |
fw | -0.558 |
sych | -0.555 |
tremend | -0.546 |
Token | state |
Token ID | 1181 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
Idol | +0.130 |
Holo | +0.123 |
fw | +0.121 |
sych | +0.120 |
tremend | +0.117 |
Neg logit contributions | |
gaard | -0.175 |
ivist | -0.155 |
cific | -0.153 |
phies | -0.153 |
iors | -0.152 |
Token |
|
Token ID | 198 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
gaard | +0.955 |
phies | +0.844 |
ivist | +0.842 |
cific | +0.838 |
iferation | +0.828 |
Neg logit contributions | |
Idol | -0.736 |
Holo | -0.697 |
sych | -0.673 |
fw | -0.662 |
Barcl | -0.653 |
Token |
|
Token ID | 198 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
gaard | +1.123 |
ivist | +0.967 |
iors | +0.955 |
gets | +0.951 |
cific | +0.944 |
Neg logit contributions | |
tremend | -1.329 |
Idol | -1.219 |
Holo | -1.163 |
sych | -1.156 |
therap | -1.152 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
gaard | +1.383 |
ivist | +1.223 |
cific | +1.200 |
iors | +1.197 |
phies | +1.188 |
Neg logit contributions | |
Idol | -1.118 |
Holo | -1.058 |
tremend | -1.056 |
fw | -1.032 |
sych | -1.028 |
Token | is |
Token ID | 318 |
Feature activation | +5.03e-04 |
Pos logit contributions | |
Idol | +1.422 |
Holo | +1.350 |
sych | +1.318 |
fw | +1.316 |
tremend | +1.277 |
Neg logit contributions | |
gaard | -1.624 |
ivist | -1.422 |
cific | -1.412 |
phies | -1.409 |
iferation | -1.392 |
Token | the |
Token ID | 262 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
gaard | +0.003 |
ivist | +0.002 |
cific | +0.002 |
phies | +0.002 |
iors | +0.002 |
Neg logit contributions | |
Idol | -0.002 |
Holo | -0.002 |
fw | -0.002 |
sych | -0.002 |
tremend | -0.002 |
Token | same |
Token ID | 976 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Idol | +1.569 |
Holo | +1.498 |
fw | +1.468 |
sych | +1.465 |
tremend | +1.433 |
Neg logit contributions | |
gaard | -1.578 |
ivist | -1.372 |
cific | -1.352 |
phies | -1.349 |
iors | -1.332 |
Token | . |
Token ID | 13 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
Idol | +6.982 |
Holo | +6.574 |
jack | +6.264 |
Barcl | +6.240 |
alleg | +6.081 |
Neg logit contributions | |
gaard | -9.849 |
iferation | -9.013 |
phies | -8.987 |
cific | -8.969 |
ivist | -8.648 |
Token | Recently |
Token ID | 23413 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
Idol | +0.120 |
Holo | +0.114 |
fw | +0.112 |
sych | +0.112 |
tremend | +0.109 |
Neg logit contributions | |
gaard | -0.141 |
ivist | -0.124 |
cific | -0.122 |
phies | -0.122 |
iors | -0.120 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
gaard | +1.242 |
ivist | +1.094 |
cific | +1.074 |
phies | +1.073 |
iors | +1.063 |
Neg logit contributions | |
Idol | -1.040 |
Holo | -0.988 |
fw | -0.976 |
sych | -0.968 |
tremend | -0.953 |
Token | he |
Token ID | 339 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
gaard | +0.077 |
ivist | +0.067 |
cific | +0.067 |
phies | +0.066 |
iors | +0.066 |
Neg logit contributions | |
Idol | -0.062 |
Holo | -0.059 |
fw | -0.058 |
sych | -0.058 |
tremend | -0.057 |
Token | overt |
Token ID | 9929 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Idol | +1.517 |
Holo | +1.447 |
sych | +1.416 |
fw | +1.404 |
tremend | +1.363 |
Neg logit contributions | |
gaard | -1.521 |
ivist | -1.323 |
cific | -1.311 |
phies | -1.305 |
iferation | -1.296 |
Token | to |
Token ID | 284 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
Idol | +0.219 |
Holo | +0.208 |
fw | +0.204 |
sych | +0.204 |
tremend | +0.199 |
Neg logit contributions | |
gaard | -0.267 |
ivist | -0.235 |
cific | -0.232 |
phies | -0.231 |
iors | -0.229 |
Token | make |
Token ID | 787 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
gaard | +0.180 |
ivist | +0.159 |
cific | +0.157 |
phies | +0.156 |
iors | +0.156 |
Neg logit contributions | |
Idol | -0.133 |
Holo | -0.126 |
fw | -0.124 |
sych | -0.124 |
tremend | -0.121 |
Token | a |
Token ID | 257 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Idol | +1.212 |
Holo | +1.153 |
fw | +1.128 |
sych | +1.123 |
tremend | +1.096 |
Neg logit contributions | |
gaard | -1.461 |
ivist | -1.285 |
cific | -1.268 |
phies | -1.265 |
iferation | -1.253 |
Token | decision |
Token ID | 2551 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
Idol | +0.999 |
Holo | +0.950 |
fw | +0.932 |
sych | +0.928 |
tremend | +0.906 |
Neg logit contributions | |
gaard | -1.185 |
ivist | -1.043 |
cific | -1.028 |
phies | -1.025 |
iors | -1.015 |
Token | , |
Token ID | 11 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
gaard | +2.526 |
ivist | +2.234 |
cific | +2.175 |
iors | +2.175 |
phies | +2.149 |
Neg logit contributions | |
Idol | -2.311 |
Holo | -2.180 |
sych | -2.154 |
fw | -2.145 |
tremend | -2.141 |
Token | � |
Token ID | 126 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Idol | +0.733 |
Holo | +0.695 |
fw | +0.681 |
sych | +0.678 |
tremend | +0.663 |
Neg logit contributions | |
gaard | -0.943 |
ivist | -0.834 |
cific | -0.822 |
phies | -0.820 |
iors | -0.812 |
Token | � |
Token ID | 242 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
Idol | +5.111 |
Holo | +4.696 |
fw | +4.525 |
sych | +4.349 |
ARA | +4.139 |
Neg logit contributions | |
gaard | -11.875 |
ivist | -10.847 |
iferation | -10.757 |
phies | -10.580 |
gets | -10.550 |
Token | he |
Token ID | 339 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
Idol | +1.634 |
Holo | +1.552 |
fw | +1.518 |
sych | +1.511 |
tremend | +1.471 |
Neg logit contributions | |
gaard | -2.094 |
ivist | -1.850 |
cific | -1.822 |
phies | -1.821 |
iferation | -1.805 |
Token | said |
Token ID | 531 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
Idol | +2.788 |
Holo | +2.669 |
sych | +2.637 |
fw | +2.600 |
tremend | +2.512 |
Neg logit contributions | |
gaard | -2.616 |
ivist | -2.262 |
iferation | -2.242 |
cific | -2.235 |
phies | -2.233 |
Token | . |
Token ID | 13 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
gaard | +0.115 |
ivist | +0.101 |
phies | +0.100 |
cific | +0.100 |
iferation | +0.099 |
Neg logit contributions | |
Idol | -0.084 |
Holo | -0.079 |
sych | -0.077 |
fw | -0.077 |
tremend | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Idol | +0.236 |
Holo | +0.224 |
fw | +0.216 |
sych | +0.215 |
ARA | +0.208 |
Neg logit contributions | |
gaard | -0.303 |
ivist | -0.269 |
phies | -0.264 |
iferation | -0.264 |
cific | -0.264 |
Token | the |
Token ID | 1169 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
Idol | +1.761 |
Holo | +1.683 |
fw | +1.669 |
sych | +1.656 |
ARA | +1.597 |
Neg logit contributions | |
gaard | -2.196 |
ivist | -1.933 |
phies | -1.912 |
cific | -1.909 |
iferation | -1.902 |
Token | killer |
Token ID | 11868 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
gaard | +1.753 |
ivist | +1.559 |
cific | +1.532 |
phies | +1.523 |
iors | +1.510 |
Neg logit contributions | |
Idol | -1.219 |
Holo | -1.150 |
fw | -1.131 |
sych | -1.126 |
tremend | -1.106 |
Token | ] |
Token ID | 60 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
gaard | +0.602 |
ivist | +0.537 |
cific | +0.531 |
phies | +0.530 |
iors | +0.526 |
Neg logit contributions | |
Idol | -0.383 |
Holo | -0.360 |
fw | -0.352 |
sych | -0.351 |
tremend | -0.341 |
Token | is |
Token ID | 318 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
gaard | +0.207 |
ivist | +0.180 |
cific | +0.177 |
phies | +0.176 |
iors | +0.174 |
Neg logit contributions | |
Idol | -0.207 |
Holo | -0.197 |
fw | -0.194 |
sych | -0.193 |
tremend | -0.189 |
Token | probably |
Token ID | 2192 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
gaard | +0.891 |
ivist | +0.773 |
phies | +0.758 |
cific | +0.757 |
iors | +0.751 |
Neg logit contributions | |
Idol | -0.885 |
Holo | -0.843 |
fw | -0.834 |
sych | -0.830 |
tremend | -0.814 |
Token | dead |
Token ID | 2636 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
gaard | +2.238 |
ivist | +1.930 |
phies | +1.888 |
cific | +1.887 |
iors | +1.879 |
Neg logit contributions | |
Idol | -2.276 |
fw | -2.176 |
Holo | -2.171 |
sych | -2.153 |
tremend | -2.124 |
Token | or |
Token ID | 393 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
gaard | +5.242 |
ivist | +4.591 |
iors | +4.522 |
phies | +4.504 |
gets | +4.434 |
Neg logit contributions | |
Idol | -5.059 |
Holo | -4.879 |
sych | -4.765 |
fw | -4.737 |
tremend | -4.698 |
Token | in |
Token ID | 287 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
gaard | +1.353 |
ivist | +1.173 |
cific | +1.153 |
phies | +1.152 |
iors | +1.143 |
Neg logit contributions | |
Idol | -1.348 |
Holo | -1.285 |
fw | -1.268 |
sych | -1.260 |
tremend | -1.240 |
Token | prison |
Token ID | 3770 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Idol | +0.508 |
Holo | +0.479 |
fw | +0.468 |
sych | +0.466 |
tremend | +0.453 |
Neg logit contributions | |
gaard | -0.801 |
ivist | -0.715 |
cific | -0.706 |
phies | -0.705 |
iors | -0.697 |
Token | . |
Token ID | 13 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
gaard | +0.717 |
ivist | +0.631 |
cific | +0.621 |
phies | +0.619 |
iors | +0.614 |
Neg logit contributions | |
Idol | -0.598 |
Holo | -0.568 |
fw | -0.557 |
sych | -0.555 |
tremend | -0.543 |
Token | But |
Token ID | 887 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
gaard | +1.982 |
ivist | +1.746 |
cific | +1.723 |
phies | +1.715 |
iors | +1.705 |
Neg logit contributions | |
Idol | -1.555 |
tremend | -1.481 |
Holo | -1.477 |
sych | -1.461 |
fw | -1.460 |
Token | sharing |
Token ID | 7373 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
gaard | +1.070 |
ivist | +0.946 |
cific | +0.924 |
phies | +0.916 |
iors | +0.914 |
Neg logit contributions | |
Idol | -0.954 |
Holo | -0.904 |
fw | -0.896 |
sych | -0.896 |
tremend | -0.877 |
Token | fake |
Token ID | 8390 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
gaard | +3.123 |
ivist | +2.808 |
cific | +2.690 |
iors | +2.670 |
gets | +2.636 |
Neg logit contributions | |
Idol | -2.948 |
sych | -2.793 |
fw | -2.786 |
tremend | -2.776 |
Holo | -2.768 |
Token | news |
Token ID | 1705 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
gaard | +4.937 |
ivist | +4.472 |
cific | +4.265 |
iors | +4.258 |
phies | +4.238 |
Neg logit contributions | |
Idol | -4.046 |
sych | -3.873 |
Holo | -3.850 |
tremend | -3.827 |
fw | -3.818 |
Token | on |
Token ID | 319 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
gaard | +3.453 |
ivist | +3.095 |
iors | +2.958 |
cific | +2.953 |
phies | +2.935 |
Neg logit contributions | |
Idol | -3.184 |
sych | -3.026 |
Holo | -2.986 |
fw | -2.979 |
tremend | -2.977 |
Token | his |
Token ID | 465 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
gaard | +1.628 |
ivist | +1.457 |
cific | +1.414 |
phies | +1.407 |
iors | +1.401 |
Neg logit contributions | |
Idol | -1.208 |
Holo | -1.142 |
sych | -1.134 |
fw | -1.128 |
tremend | -1.117 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
gaard | +1.730 |
ivist | +1.536 |
cific | +1.483 |
iors | +1.478 |
phies | +1.469 |
Neg logit contributions | |
Idol | -1.449 |
sych | -1.378 |
Holo | -1.373 |
tremend | -1.353 |
fw | -1.346 |
Token | page |
Token ID | 2443 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
gaard | +5.991 |
ivist | +5.472 |
iors | +5.316 |
iferation | +5.207 |
phies | +5.163 |
Neg logit contributions | |
Idol | -4.849 |
sych | -4.626 |
Holo | -4.613 |
tremend | -4.547 |
ARA | -4.422 |
Token | to |
Token ID | 284 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
gaard | +3.056 |
ivist | +2.715 |
cific | +2.623 |
iors | +2.623 |
phies | +2.619 |
Neg logit contributions | |
Idol | -2.740 |
Holo | -2.600 |
sych | -2.575 |
fw | -2.557 |
tremend | -2.531 |
Token | thousands |
Token ID | 4138 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
gaard | +1.985 |
ivist | +1.748 |
cific | +1.739 |
iors | +1.717 |
phies | +1.710 |
Neg logit contributions | |
Idol | -1.481 |
sych | -1.401 |
Holo | -1.391 |
fw | -1.382 |
tremend | -1.353 |
Token | upon |
Token ID | 2402 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
Idol | +0.202 |
Holo | +0.192 |
fw | +0.188 |
sych | +0.184 |
tremend | +0.182 |
Neg logit contributions | |
gaard | -0.253 |
ivist | -0.222 |
cific | -0.221 |
phies | -0.220 |
iors | -0.219 |
Token | thousands |
Token ID | 4138 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
gaard | +0.232 |
ivist | +0.198 |
cific | +0.194 |
phies | +0.194 |
iors | +0.193 |
Neg logit contributions | |
Idol | -0.304 |
tremend | -0.290 |
Holo | -0.289 |
fw | -0.286 |
sych | -0.285 |
Token |
|
Token ID | 198 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
gaard | +0.575 |
ivist | +0.498 |
iors | +0.492 |
gets | +0.488 |
cific | +0.486 |
Neg logit contributions | |
tremend | -0.640 |
Idol | -0.597 |
Holo | -0.573 |
sych | -0.566 |
fw | -0.557 |
Token | 14 |
Token ID | 1415 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
gaard | +2.427 |
ivist | +2.159 |
cific | +2.129 |
iors | +2.113 |
phies | +2.095 |
Neg logit contributions | |
Idol | -1.579 |
tremend | -1.521 |
Holo | -1.501 |
sych | -1.438 |
fw | -1.438 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
gaard | +1.780 |
ivist | +1.531 |
cific | +1.501 |
iors | +1.496 |
phies | +1.494 |
Neg logit contributions | |
Idol | -1.905 |
tremend | -1.857 |
Holo | -1.845 |
sych | -1.829 |
fw | -1.819 |
Token |
|
Token ID | 198 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
gaard | +4.028 |
iors | +3.541 |
ivist | +3.482 |
cific | +3.386 |
gets | +3.310 |
Neg logit contributions | |
tremend | -5.973 |
therap | -5.217 |
Idol | -5.116 |
sych | -4.954 |
Holo | -4.897 |
Token |
|
Token ID | 198 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
gaard | +1.419 |
iors | +1.219 |
ivist | +1.219 |
gets | +1.211 |
cific | +1.187 |
Neg logit contributions | |
tremend | -1.750 |
Idol | -1.566 |
therap | -1.516 |
Holo | -1.509 |
sych | -1.493 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
gaard | +2.515 |
iors | +2.248 |
ivist | +2.248 |
cific | +2.208 |
gets | +2.197 |
Neg logit contributions | |
Idol | -1.743 |
tremend | -1.716 |
Holo | -1.701 |
Barcl | -1.591 |
Consortium | -1.587 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
gaard | +2.624 |
iors | +2.349 |
ivist | +2.191 |
cific | +1.873 |
IVES | +1.845 |
Neg logit contributions | |
tremend | -10.114 |
Idol | -9.714 |
sych | -9.665 |
fw | -9.495 |
ARA | -9.415 |
Token | this |
Token ID | 428 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
gaard | +5.358 |
cific | +5.020 |
gets | +4.860 |
iors | +4.755 |
ivist | +4.543 |
Neg logit contributions | |
tremend | -9.989 |
Idol | -8.579 |
etheless | -8.485 |
fw | -8.472 |
CHECK | -8.355 |
Token | comment |
Token ID | 2912 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
gaard | +1.532 |
ivist | +1.235 |
cific | +1.227 |
iors | +1.223 |
phies | +1.184 |
Neg logit contributions | |
Idol | -2.348 |
tremend | -2.326 |
Holo | -2.288 |
sych | -2.287 |
ARA | -2.239 |
Token | on |
Token ID | 319 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
gaard | +4.441 |
ivist | +3.906 |
iors | +3.760 |
cific | +3.697 |
iferation | +3.584 |
Neg logit contributions | |
Idol | -4.851 |
tremend | -4.845 |
sych | -4.723 |
fw | -4.677 |
Holo | -4.643 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
gaard | +0.295 |
ivist | +0.255 |
cific | +0.251 |
phies | +0.250 |
iors | +0.247 |
Neg logit contributions | |
Idol | -0.320 |
Holo | -0.307 |
fw | -0.301 |
sych | -0.300 |
tremend | -0.294 |
Token | f |
Token ID | 69 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
Idol | +1.392 |
Holo | +1.304 |
tremend | +1.299 |
sych | +1.252 |
fw | +1.225 |
Neg logit contributions | |
gaard | -2.535 |
ivist | -2.271 |
cific | -2.248 |
iors | -2.237 |
phies | -2.233 |
Token | says |
Token ID | 1139 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Idol | +0.396 |
Holo | +0.379 |
fw | +0.373 |
sych | +0.372 |
tremend | +0.364 |
Neg logit contributions | |
gaard | -0.348 |
ivist | -0.299 |
cific | -0.294 |
phies | -0.293 |
iors | -0.290 |
Token | F |
Token ID | 376 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
gaard | +0.961 |
ivist | +0.848 |
cific | +0.835 |
phies | +0.830 |
iors | +0.828 |
Neg logit contributions | |
Idol | -0.765 |
fw | -0.725 |
Holo | -0.723 |
sych | -0.713 |
tremend | -0.706 |
Token | AS |
Token ID | 1921 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
gaard | +1.763 |
ivist | +1.538 |
cific | +1.511 |
phies | +1.506 |
iors | +1.495 |
Neg logit contributions | |
Idol | -1.667 |
Holo | -1.593 |
fw | -1.556 |
sych | -1.548 |
tremend | -1.526 |
Token | affects |
Token ID | 10975 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Idol | +1.323 |
Holo | +1.262 |
fw | +1.240 |
sych | +1.238 |
tremend | +1.201 |
Neg logit contributions | |
gaard | -1.481 |
ivist | -1.294 |
cific | -1.274 |
phies | -1.273 |
iors | -1.257 |
Token | only |
Token ID | 691 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
gaard | +1.239 |
ivist | +1.072 |
cific | +1.053 |
iors | +1.050 |
phies | +1.038 |
Neg logit contributions | |
Idol | -1.272 |
fw | -1.211 |
Holo | -1.207 |
sych | -1.198 |
tremend | -1.184 |
Token | a |
Token ID | 257 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
gaard | +5.363 |
ivist | +4.713 |
cific | +4.615 |
iors | +4.593 |
gets | +4.522 |
Neg logit contributions | |
Idol | -5.711 |
fw | -5.643 |
sych | -5.480 |
tremend | -5.470 |
Holo | -5.396 |
Token | small |
Token ID | 1402 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
gaard | +1.776 |
ivist | +1.584 |
cific | +1.550 |
iors | +1.533 |
phies | +1.519 |
Neg logit contributions | |
Idol | -1.384 |
Holo | -1.293 |
fw | -1.291 |
sych | -1.283 |
tremend | -1.255 |
Token | area |
Token ID | 1989 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
gaard | +2.317 |
ivist | +2.027 |
cific | +1.955 |
iors | +1.945 |
phies | +1.930 |
Neg logit contributions | |
Idol | -2.284 |
sych | -2.181 |
fw | -2.180 |
Holo | -2.162 |
tremend | -2.145 |
Token | of |
Token ID | 286 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
gaard | +0.251 |
ivist | +0.220 |
phies | +0.220 |
cific | +0.219 |
iferation | +0.216 |
Neg logit contributions | |
Idol | -0.201 |
Holo | -0.191 |
fw | -0.185 |
sych | -0.184 |
tremend | -0.181 |
Token | speech |
Token ID | 4046 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
gaard | +0.422 |
ivist | +0.375 |
cific | +0.370 |
phies | +0.369 |
iors | +0.365 |
Neg logit contributions | |
Idol | -0.291 |
Holo | -0.274 |
fw | -0.269 |
sych | -0.268 |
tremend | -0.261 |
Token | in |
Token ID | 287 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
gaard | +0.181 |
ivist | +0.159 |
cific | +0.157 |
phies | +0.156 |
iors | +0.156 |
Neg logit contributions | |
Idol | -0.141 |
Holo | -0.135 |
fw | -0.132 |
sych | -0.132 |
tremend | -0.129 |
Token | setting |
Token ID | 4634 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
Idol | +0.242 |
Holo | +0.230 |
fw | +0.226 |
sych | +0.225 |
tremend | +0.219 |
Neg logit contributions | |
gaard | -0.305 |
ivist | -0.269 |
cific | -0.265 |
phies | -0.264 |
iors | -0.262 |
Token | the |
Token ID | 262 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
gaard | +1.759 |
ivist | +1.550 |
cific | +1.516 |
phies | +1.515 |
iors | +1.507 |
Neg logit contributions | |
Idol | -1.356 |
Holo | -1.296 |
sych | -1.276 |
fw | -1.269 |
tremend | -1.239 |
Token | momentum |
Token ID | 12858 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
gaard | +0.880 |
ivist | +0.772 |
phies | +0.757 |
cific | +0.755 |
iferation | +0.750 |
Neg logit contributions | |
Idol | -0.710 |
Holo | -0.678 |
fw | -0.667 |
sych | -0.666 |
tremend | -0.651 |
Token | to |
Token ID | 284 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
gaard | +3.543 |
ivist | +3.150 |
cific | +3.052 |
phies | +3.049 |
iors | +3.043 |
Neg logit contributions | |
Idol | -2.906 |
Holo | -2.790 |
sych | -2.725 |
fw | -2.718 |
tremend | -2.649 |
Token | carry |
Token ID | 3283 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
gaard | +2.700 |
ivist | +2.358 |
cific | +2.342 |
iors | +2.307 |
gets | +2.305 |
Neg logit contributions | |
Idol | -2.275 |
sych | -2.166 |
Holo | -2.155 |
fw | -2.140 |
tremend | -2.051 |
Token | you |
Token ID | 345 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
gaard | +6.039 |
ivist | +5.348 |
cific | +5.241 |
gets | +5.109 |
iors | +5.092 |
Neg logit contributions | |
Idol | -5.577 |
sych | -5.411 |
fw | -5.338 |
Holo | -5.324 |
srfAttach | -5.175 |
Token | to |
Token ID | 284 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
gaard | +3.094 |
ivist | +2.707 |
cific | +2.642 |
iors | +2.600 |
phies | +2.599 |
Neg logit contributions | |
Idol | -2.877 |
Holo | -2.765 |
sych | -2.742 |
fw | -2.709 |
tremend | -2.647 |
Token | victory |
Token ID | 5373 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
gaard | +3.369 |
ivist | +2.933 |
cific | +2.901 |
iors | +2.865 |
phies | +2.863 |
Neg logit contributions | |
Idol | -3.011 |
sych | -2.907 |
Holo | -2.876 |
fw | -2.844 |
ARA | -2.747 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
gaard | +1.622 |
ivist | +1.432 |
cific | +1.408 |
phies | +1.398 |
iors | +1.393 |
Neg logit contributions | |
Idol | -1.368 |
Holo | -1.307 |
sych | -1.285 |
fw | -1.280 |
tremend | -1.248 |
Token | Will |
Token ID | 2561 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
Idol | +0.568 |
Holo | +0.539 |
fw | +0.529 |
sych | +0.527 |
tremend | +0.516 |
Neg logit contributions | |
gaard | -0.699 |
ivist | -0.616 |
cific | -0.607 |
phies | -0.605 |
iors | -0.599 |
Token | available |
Token ID | 1695 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Idol | +0.194 |
Holo | +0.183 |
fw | +0.179 |
sych | +0.178 |
tremend | +0.174 |
Neg logit contributions | |
gaard | -0.291 |
ivist | -0.259 |
cific | -0.256 |
phies | -0.255 |
iors | -0.253 |
Token | via |
Token ID | 2884 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Idol | +0.773 |
Holo | +0.732 |
fw | +0.717 |
sych | +0.714 |
tremend | +0.696 |
Neg logit contributions | |
gaard | -1.037 |
ivist | -0.918 |
cific | -0.906 |
phies | -0.904 |
iferation | -0.895 |
Token | Kindle |
Token ID | 27114 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Idol | +0.635 |
Holo | +0.601 |
fw | +0.591 |
sych | +0.589 |
tremend | +0.575 |
Neg logit contributions | |
gaard | -0.835 |
ivist | -0.738 |
cific | -0.728 |
phies | -0.725 |
iors | -0.718 |
Token | : |
Token ID | 25 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
gaard | +1.058 |
ivist | +0.936 |
cific | +0.913 |
iors | +0.912 |
phies | +0.910 |
Neg logit contributions | |
Idol | -0.882 |
Holo | -0.839 |
sych | -0.827 |
fw | -0.825 |
tremend | -0.818 |
Token | Of |
Token ID | 3226 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Idol | +0.448 |
Holo | +0.425 |
fw | +0.415 |
sych | +0.414 |
tremend | +0.403 |
Neg logit contributions | |
gaard | -0.576 |
ivist | -0.509 |
cific | -0.503 |
phies | -0.501 |
iferation | -0.496 |
Token | Two |
Token ID | 4930 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Idol | +1.070 |
Holo | +1.014 |
sych | +0.990 |
fw | +0.986 |
tremend | +0.953 |
Neg logit contributions | |
gaard | -1.350 |
ivist | -1.195 |
cific | -1.184 |
phies | -1.177 |
iferation | -1.167 |
Token | Mind |
Token ID | 10175 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
gaard | +0.581 |
ivist | +0.509 |
cific | +0.501 |
phies | +0.499 |
iors | +0.494 |
Neg logit contributions | |
Idol | -0.524 |
Holo | -0.499 |
fw | -0.490 |
sych | -0.488 |
tremend | -0.477 |
Token | s |
Token ID | 82 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
gaard | +0.680 |
ivist | +0.595 |
cific | +0.586 |
phies | +0.583 |
iferation | +0.579 |
Neg logit contributions | |
Idol | -0.643 |
Holo | -0.612 |
fw | -0.602 |
sych | -0.601 |
tremend | -0.581 |
Token | blog |
Token ID | 4130 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
Idol | +0.392 |
Holo | +0.372 |
fw | +0.364 |
sych | +0.363 |
tremend | +0.353 |
Neg logit contributions | |
gaard | -0.483 |
ivist | -0.426 |
cific | -0.422 |
phies | -0.420 |
iferation | -0.416 |
Token | - |
Token ID | 12 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
gaard | +4.357 |
ivist | +3.795 |
iors | +3.700 |
cific | +3.669 |
gets | +3.643 |
Neg logit contributions | |
Idol | -3.901 |
Holo | -3.718 |
tremend | -3.664 |
fw | -3.657 |
sych | -3.654 |
Token | Kind |
Token ID | 35854 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
gaard | +0.167 |
ivist | +0.147 |
cific | +0.145 |
phies | +0.145 |
iors | +0.144 |
Neg logit contributions | |
Idol | -0.132 |
Holo | -0.125 |
fw | -0.122 |
sych | -0.122 |
tremend | -0.119 |
Token | it |
Token ID | 340 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
gaard | +1.167 |
ivist | +1.027 |
cific | +1.014 |
phies | +1.004 |
iors | +0.994 |
Neg logit contributions | |
Idol | -0.960 |
Holo | -0.916 |
sych | -0.915 |
fw | -0.915 |
tremend | -0.892 |
Token | � |
Token ID | 447 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
gaard | +0.714 |
ivist | +0.623 |
cific | +0.615 |
phies | +0.609 |
iors | +0.605 |
Neg logit contributions | |
Idol | -0.684 |
Holo | -0.655 |
fw | -0.643 |
sych | -0.642 |
tremend | -0.629 |
Token | � |
Token ID | 247 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
Idol | +0.859 |
Holo | +0.821 |
sych | +0.809 |
fw | +0.808 |
tremend | +0.805 |
Neg logit contributions | |
gaard | -0.744 |
ivist | -0.633 |
phies | -0.623 |
cific | -0.622 |
iors | -0.621 |
Token | s |
Token ID | 82 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
gaard | +0.120 |
ivist | +0.104 |
cific | +0.102 |
phies | +0.102 |
iors | +0.101 |
Neg logit contributions | |
Idol | -0.120 |
Holo | -0.114 |
fw | -0.112 |
sych | -0.112 |
tremend | -0.110 |
Token | a |
Token ID | 257 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
gaard | +0.975 |
ivist | +0.861 |
cific | +0.850 |
phies | +0.844 |
iors | +0.838 |
Neg logit contributions | |
Idol | -0.797 |
Holo | -0.757 |
fw | -0.746 |
sych | -0.743 |
tremend | -0.721 |
Token | good |
Token ID | 922 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
gaard | +0.719 |
ivist | +0.635 |
cific | +0.626 |
phies | +0.622 |
iors | +0.616 |
Neg logit contributions | |
Idol | -0.560 |
Holo | -0.530 |
sych | -0.524 |
fw | -0.524 |
tremend | -0.505 |
Token | option |
Token ID | 3038 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
gaard | +0.426 |
ivist | +0.375 |
cific | +0.370 |
phies | +0.367 |
iferation | +0.365 |
Neg logit contributions | |
Idol | -0.340 |
Holo | -0.323 |
sych | -0.318 |
fw | -0.318 |
tremend | -0.310 |
Token | if |
Token ID | 611 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
gaard | +0.805 |
ivist | +0.716 |
cific | +0.706 |
iors | +0.698 |
phies | +0.698 |
Neg logit contributions | |
Idol | -0.598 |
Holo | -0.567 |
sych | -0.558 |
fw | -0.557 |
tremend | -0.544 |
Token | arrow |
Token ID | 15452 |
Feature activation | +7.39e-03 |
Pos logit contributions | |
Idol | +0.435 |
Holo | +0.414 |
fw | +0.406 |
sych | +0.403 |
tremend | +0.396 |
Neg logit contributions | |
gaard | -0.454 |
ivist | -0.395 |
cific | -0.390 |
phies | -0.387 |
iferation | -0.384 |
Token | root |
Token ID | 15763 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
gaard | +0.033 |
ivist | +0.028 |
cific | +0.028 |
phies | +0.028 |
iors | +0.027 |
Neg logit contributions | |
Idol | -0.036 |
Holo | -0.035 |
fw | -0.034 |
sych | -0.034 |
tremend | -0.033 |
Token | is |
Token ID | 318 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
Idol | +0.197 |
Holo | +0.187 |
fw | +0.183 |
sych | +0.182 |
tremend | +0.178 |
Neg logit contributions | |
gaard | -0.217 |
ivist | -0.189 |
cific | -0.186 |
phies | -0.186 |
iors | -0.184 |
Token | he |
Token ID | 339 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Idol | +2.047 |
Holo | +1.938 |
fw | +1.900 |
sych | +1.893 |
tremend | +1.843 |
Neg logit contributions | |
gaard | -2.563 |
ivist | -2.262 |
cific | -2.233 |
phies | -2.225 |
iferation | -2.214 |
Token | ended |
Token ID | 4444 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
Idol | +1.637 |
Holo | +1.554 |
sych | +1.530 |
fw | +1.526 |
tremend | +1.480 |
Neg logit contributions | |
gaard | -1.834 |
ivist | -1.608 |
cific | -1.594 |
phies | -1.585 |
iferation | -1.570 |
Token | up |
Token ID | 510 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
Idol | +1.928 |
Holo | +1.808 |
sych | +1.776 |
fw | +1.776 |
tremend | +1.714 |
Neg logit contributions | |
gaard | -2.896 |
ivist | -2.574 |
cific | -2.556 |
phies | -2.541 |
iferation | -2.517 |
Token | making |
Token ID | 1642 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
gaard | +1.610 |
ivist | +1.417 |
phies | +1.386 |
iors | +1.384 |
cific | +1.381 |
Neg logit contributions | |
Idol | -1.351 |
Holo | -1.293 |
fw | -1.264 |
sych | -1.260 |
tremend | -1.225 |
Token | millions |
Token ID | 5242 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Idol | +0.994 |
Holo | +0.943 |
fw | +0.924 |
sych | +0.921 |
tremend | +0.899 |
Neg logit contributions | |
gaard | -1.198 |
ivist | -1.054 |
cific | -1.039 |
phies | -1.036 |
iferation | -1.027 |
Token | of |
Token ID | 286 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
gaard | +0.613 |
ivist | +0.540 |
phies | +0.529 |
cific | +0.529 |
iors | +0.524 |
Neg logit contributions | |
Idol | -0.504 |
Holo | -0.481 |
sych | -0.469 |
fw | -0.469 |
tremend | -0.458 |
Token | dollars |
Token ID | 5054 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
gaard | +1.904 |
ivist | +1.659 |
phies | +1.643 |
cific | +1.617 |
iors | +1.609 |
Neg logit contributions | |
Idol | -1.778 |
Holo | -1.701 |
sych | -1.661 |
fw | -1.654 |
tremend | -1.636 |
Token | from |
Token ID | 422 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
gaard | +1.769 |
ivist | +1.556 |
phies | +1.522 |
cific | +1.515 |
gets | +1.510 |
Neg logit contributions | |
Idol | -1.471 |
Holo | -1.407 |
sych | -1.370 |
fw | -1.362 |
tremend | -1.336 |
Token | his |
Token ID | 465 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Idol | +0.918 |
Holo | +0.868 |
fw | +0.851 |
sych | +0.848 |
tremend | +0.826 |
Neg logit contributions | |
gaard | -1.257 |
ivist | -1.115 |
cific | -1.101 |
phies | -1.096 |
iferation | -1.086 |
Token | gamble |
Token ID | 32385 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Idol | +0.522 |
Holo | +0.494 |
fw | +0.484 |
sych | +0.482 |
tremend | +0.471 |
Neg logit contributions | |
gaard | -0.702 |
ivist | -0.621 |
cific | -0.612 |
phies | -0.611 |
iors | -0.605 |
Token | . |
Token ID | 13 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
Idol | +1.138 |
Holo | +1.077 |
fw | +1.058 |
sych | +1.056 |
tremend | +1.027 |
Neg logit contributions | |
gaard | -1.481 |
ivist | -1.308 |
cific | -1.296 |
phies | -1.291 |
iferation | -1.281 |
Token | different |
Token ID | 1180 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
gaard | +2.637 |
ivist | +2.293 |
cific | +2.259 |
phies | +2.245 |
iors | +2.218 |
Neg logit contributions | |
Idol | -2.903 |
sych | -2.781 |
fw | -2.772 |
Holo | -2.749 |
tremend | -2.711 |
Token | software |
Token ID | 3788 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
gaard | +0.315 |
ivist | +0.278 |
cific | +0.274 |
phies | +0.273 |
iors | +0.271 |
Neg logit contributions | |
Idol | -0.231 |
Holo | -0.217 |
sych | -0.217 |
fw | -0.215 |
tremend | -0.211 |
Token | . |
Token ID | 13 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
Idol | +0.062 |
Holo | +0.059 |
sych | +0.058 |
fw | +0.058 |
tremend | +0.056 |
Neg logit contributions | |
gaard | -0.078 |
ivist | -0.068 |
cific | -0.068 |
phies | -0.067 |
iors | -0.067 |
Token | Tape |
Token ID | 40849 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
gaard | +0.143 |
ivist | +0.126 |
cific | +0.124 |
phies | +0.123 |
iors | +0.122 |
Neg logit contributions | |
Idol | -0.117 |
Holo | -0.111 |
tremend | -0.111 |
sych | -0.111 |
fw | -0.111 |
Token | capacity |
Token ID | 5339 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
Idol | +1.867 |
Holo | +1.786 |
fw | +1.747 |
sych | +1.738 |
tremend | +1.700 |
Neg logit contributions | |
gaard | -1.929 |
ivist | -1.677 |
cific | -1.649 |
phies | -1.643 |
iferation | -1.640 |
Token | is |
Token ID | 318 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Idol | +4.219 |
Holo | +4.043 |
fw | +3.930 |
sych | +3.866 |
tremend | +3.810 |
Neg logit contributions | |
gaard | -4.717 |
ivist | -4.101 |
iferation | -4.086 |
phies | -4.073 |
cific | -4.058 |
Token | following |
Token ID | 1708 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
gaard | +1.938 |
ivist | +1.712 |
cific | +1.690 |
phies | +1.674 |
iors | +1.669 |
Neg logit contributions | |
Idol | -1.598 |
Holo | -1.517 |
fw | -1.514 |
sych | -1.513 |
tremend | -1.464 |
Token | Moore |
Token ID | 8877 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
Idol | +1.052 |
Holo | +0.995 |
fw | +0.975 |
sych | +0.971 |
tremend | +0.947 |
Neg logit contributions | |
gaard | -1.421 |
ivist | -1.259 |
cific | -1.242 |
phies | -1.239 |
iors | -1.227 |
Token | � |
Token ID | 447 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
Idol | +2.071 |
Holo | +1.933 |
fw | +1.875 |
sych | +1.836 |
tremend | +1.787 |
Neg logit contributions | |
gaard | -3.946 |
ivist | -3.607 |
cific | -3.556 |
phies | -3.538 |
iors | -3.533 |
Token | � |
Token ID | 247 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
gaard | +2.576 |
ivist | +2.229 |
phies | +2.214 |
cific | +2.200 |
iors | +2.185 |
Neg logit contributions | |
Idol | -2.276 |
Holo | -2.164 |
fw | -2.144 |
sych | -2.115 |
tremend | -2.102 |
Token | s |
Token ID | 82 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
gaard | +1.002 |
ivist | +0.863 |
cific | +0.855 |
phies | +0.851 |
iors | +0.840 |
Neg logit contributions | |
Idol | -1.030 |
Holo | -0.980 |
fw | -0.963 |
sych | -0.962 |
tremend | -0.947 |
Token | reconnect |
Token ID | 37671 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
Idol | +1.574 |
Holo | +1.495 |
fw | +1.465 |
sych | +1.454 |
tremend | +1.420 |
Neg logit contributions | |
gaard | -1.991 |
ivist | -1.762 |
cific | -1.737 |
phies | -1.731 |
iferation | -1.718 |
Token | – |
Token ID | 784 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Idol | +1.817 |
Holo | +1.726 |
fw | +1.694 |
sych | +1.678 |
tremend | +1.643 |
Neg logit contributions | |
gaard | -2.273 |
ivist | -2.004 |
cific | -1.976 |
phies | -1.972 |
iferation | -1.957 |
Token | no |
Token ID | 645 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
gaard | +0.969 |
ivist | +0.854 |
cific | +0.842 |
phies | +0.839 |
gets | +0.833 |
Neg logit contributions | |
Idol | -0.769 |
sych | -0.725 |
Holo | -0.724 |
fw | -0.709 |
tremend | -0.706 |
Token | big |
Token ID | 1263 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
gaard | +3.819 |
ivist | +3.416 |
phies | +3.387 |
cific | +3.382 |
gets | +3.355 |
Neg logit contributions | |
Idol | -2.347 |
sych | -2.176 |
Holo | -2.105 |
ARA | -2.093 |
tremend | -2.091 |
Token | gie |
Token ID | 22699 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
Idol | +0.846 |
Holo | +0.822 |
fw | +0.813 |
sych | +0.808 |
tremend | +0.798 |
Neg logit contributions | |
gaard | -0.269 |
ivist | -0.195 |
cific | -0.188 |
phies | -0.184 |
iferation | -0.184 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
gaard | +0.140 |
ivist | +0.124 |
cific | +0.122 |
phies | +0.122 |
iors | +0.121 |
Neg logit contributions | |
Idol | -0.112 |
Holo | -0.106 |
fw | -0.104 |
sych | -0.104 |
tremend | -0.102 |
Token | At |
Token ID | 1629 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
gaard | +0.543 |
ivist | +0.475 |
cific | +0.469 |
phies | +0.465 |
iors | +0.462 |
Neg logit contributions | |
Idol | -0.457 |
tremend | -0.438 |
sych | -0.434 |
Holo | -0.432 |
fw | -0.427 |
Token | this |
Token ID | 428 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
Idol | +0.654 |
Holo | +0.620 |
fw | +0.607 |
sych | +0.606 |
tremend | +0.592 |
Neg logit contributions | |
gaard | -0.818 |
ivist | -0.721 |
cific | -0.711 |
phies | -0.710 |
iors | -0.703 |
Token | moment |
Token ID | 2589 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Idol | +1.394 |
Holo | +1.296 |
fw | +1.251 |
sych | +1.240 |
tremend | +1.194 |
Neg logit contributions | |
gaard | -3.693 |
ivist | -3.368 |
cific | -3.324 |
phies | -3.311 |
iors | -3.308 |
Token | , |
Token ID | 11 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
Idol | +0.945 |
Holo | +0.900 |
fw | +0.880 |
sych | +0.869 |
tremend | +0.850 |
Neg logit contributions | |
gaard | -1.223 |
ivist | -1.079 |
cific | -1.066 |
phies | -1.062 |
iferation | -1.058 |
Token | I |
Token ID | 314 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
Idol | +0.087 |
Holo | +0.082 |
sych | +0.082 |
fw | +0.081 |
tremend | +0.080 |
Neg logit contributions | |
gaard | -0.109 |
ivist | -0.096 |
cific | -0.094 |
phies | -0.094 |
iors | -0.093 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +7.83e-03 |
Pos logit contributions | |
gaard | +1.060 |
ivist | +0.938 |
cific | +0.923 |
phies | +0.914 |
iors | +0.909 |
Neg logit contributions | |
Idol | -0.796 |
Holo | -0.754 |
sych | -0.745 |
fw | -0.744 |
tremend | -0.729 |
Token | ambassador |
Token ID | 14791 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
gaard | +0.044 |
ivist | +0.040 |
cific | +0.039 |
iors | +0.039 |
phies | +0.039 |
Neg logit contributions | |
Idol | -0.028 |
Holo | -0.027 |
fw | -0.026 |
sych | -0.026 |
tremend | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
gaard | +0.559 |
ivist | +0.493 |
cific | +0.486 |
phies | +0.485 |
iors | +0.480 |
Neg logit contributions | |
Idol | -0.442 |
Holo | -0.418 |
fw | -0.413 |
sych | -0.410 |
tremend | -0.402 |
Token | summoned |
Token ID | 20056 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Idol | +1.326 |
Holo | +1.266 |
fw | +1.239 |
sych | +1.235 |
tremend | +1.208 |
Neg logit contributions | |
gaard | -1.365 |
ivist | -1.189 |
cific | -1.172 |
phies | -1.169 |
iferation | -1.155 |
Token | ; |
Token ID | 26 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
Idol | +1.037 |
Holo | +0.979 |
fw | +0.956 |
sych | +0.950 |
tremend | +0.929 |
Neg logit contributions | |
gaard | -1.404 |
ivist | -1.239 |
phies | -1.229 |
cific | -1.228 |
iferation | -1.218 |
Token | he |
Token ID | 339 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
Idol | +0.379 |
Holo | +0.359 |
fw | +0.352 |
sych | +0.350 |
tremend | +0.342 |
Neg logit contributions | |
gaard | -0.493 |
ivist | -0.435 |
cific | -0.429 |
phies | -0.428 |
iors | -0.424 |
Token | denied |
Token ID | 6699 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Idol | +1.997 |
Holo | +1.895 |
sych | +1.851 |
fw | +1.846 |
Barcl | +1.777 |
Neg logit contributions | |
gaard | -2.319 |
ivist | -2.040 |
cific | -2.029 |
phies | -2.021 |
iferation | -2.013 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +1.87e-03 |
Pos logit contributions | |
Idol | +0.666 |
Holo | +0.631 |
fw | +0.618 |
sych | +0.615 |
tremend | +0.601 |
Neg logit contributions | |
gaard | -0.875 |
ivist | -0.774 |
cific | -0.764 |
phies | -0.762 |
iors | -0.754 |
Token | involvement |
Token ID | 9750 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
gaard | +0.010 |
ivist | +0.009 |
cific | +0.009 |
phies | +0.009 |
iors | +0.009 |
Neg logit contributions | |
Idol | -0.007 |
Holo | -0.007 |
fw | -0.007 |
sych | -0.007 |
tremend | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
gaard | +3.432 |
ivist | +3.029 |
cific | +2.957 |
phies | +2.929 |
iferation | +2.923 |
Neg logit contributions | |
Idol | -2.921 |
Holo | -2.774 |
sych | -2.740 |
fw | -2.732 |
tremend | -2.687 |
Token | and |
Token ID | 290 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
gaard | +1.121 |
ivist | +0.975 |
cific | +0.958 |
phies | +0.954 |
iors | +0.946 |
Neg logit contributions | |
Idol | -1.058 |
Holo | -1.009 |
fw | -0.998 |
sych | -0.998 |
tremend | -0.977 |
Token | won |
Token ID | 1839 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
gaard | +4.267 |
gets | +3.692 |
ivist | +3.664 |
iors | +3.655 |
phies | +3.571 |
Neg logit contributions | |
Idol | -5.014 |
fw | -4.852 |
Holo | -4.828 |
tremend | -4.819 |
sych | -4.763 |
Token | 't |
Token ID | 470 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
Idol | +0.978 |
Holo | +0.892 |
tremend | +0.881 |
sych | +0.856 |
fw | +0.854 |
Neg logit contributions | |
gaard | -2.823 |
ivist | -2.578 |
cific | -2.553 |
iors | -2.544 |
phies | -2.540 |
Token | want |
Token ID | 765 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
Idol | +2.046 |
Holo | +1.934 |
sych | +1.879 |
fw | +1.878 |
tremend | +1.823 |
Neg logit contributions | |
gaard | -2.891 |
ivist | -2.576 |
phies | -2.540 |
cific | -2.537 |
iferation | -2.520 |
Token | to |
Token ID | 284 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
Idol | +1.307 |
Holo | +1.232 |
fw | +1.183 |
sych | +1.180 |
Barcl | +1.166 |
Neg logit contributions | |
gaard | -1.872 |
ivist | -1.670 |
phies | -1.659 |
cific | -1.640 |
iferation | -1.639 |
Token | pay |
Token ID | 1414 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
gaard | +0.375 |
ivist | +0.329 |
cific | +0.325 |
iors | +0.323 |
phies | +0.323 |
Neg logit contributions | |
Idol | -0.297 |
Holo | -0.281 |
fw | -0.277 |
sych | -0.275 |
tremend | -0.269 |
Token | them |
Token ID | 606 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
gaard | +0.712 |
ivist | +0.626 |
cific | +0.616 |
phies | +0.612 |
iors | +0.609 |
Neg logit contributions | |
Idol | -0.616 |
Holo | -0.587 |
fw | -0.579 |
sych | -0.576 |
tremend | -0.563 |
Token | more |
Token ID | 517 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Idol | +2.248 |
Holo | +2.123 |
sych | +2.043 |
fw | +2.042 |
tremend | +2.011 |
Neg logit contributions | |
gaard | -2.917 |
ivist | -2.581 |
phies | -2.571 |
iferation | -2.556 |
cific | -2.551 |
Token | than |
Token ID | 621 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
Idol | +0.920 |
Holo | +0.866 |
fw | +0.842 |
sych | +0.837 |
tremend | +0.817 |
Neg logit contributions | |
gaard | -1.426 |
ivist | -1.271 |
phies | -1.259 |
cific | -1.257 |
iferation | -1.246 |
Token | the |
Token ID | 262 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Idol | +1.334 |
Holo | +1.266 |
fw | +1.223 |
sych | +1.220 |
Barcl | +1.191 |
Neg logit contributions | |
gaard | -1.706 |
ivist | -1.511 |
phies | -1.496 |
cific | -1.494 |
iferation | -1.486 |
Token | minimum |
Token ID | 5288 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
Idol | +0.927 |
Holo | +0.878 |
fw | +0.855 |
sych | +0.850 |
tremend | +0.828 |
Neg logit contributions | |
gaard | -1.202 |
ivist | -1.066 |
cific | -1.053 |
phies | -1.050 |
iferation | -1.041 |
Token | salary |
Token ID | 9588 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Idol | +2.415 |
Holo | +2.304 |
fw | +2.204 |
sych | +2.185 |
Barcl | +2.166 |
Neg logit contributions | |
gaard | -3.206 |
ivist | -2.851 |
cific | -2.833 |
phies | -2.830 |
iferation | -2.806 |
Token | � |
Token ID | 447 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
gaard | +0.618 |
iors | +0.551 |
ivist | +0.549 |
cific | +0.546 |
gets | +0.542 |
Neg logit contributions | |
tremend | -0.435 |
Idol | -0.413 |
Holo | -0.389 |
sych | -0.384 |
fw | -0.373 |
Token | � |
Token ID | 247 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
Idol | +0.834 |
tremend | +0.802 |
Holo | +0.799 |
fw | +0.788 |
sych | +0.787 |
Neg logit contributions | |
gaard | -0.697 |
ivist | -0.590 |
iors | -0.583 |
phies | -0.582 |
cific | -0.578 |
Token | t |
Token ID | 83 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
gaard | +0.532 |
ivist | +0.479 |
iors | +0.471 |
phies | +0.471 |
cific | +0.471 |
Neg logit contributions | |
Idol | -0.296 |
Holo | -0.278 |
tremend | -0.273 |
sych | -0.266 |
fw | -0.263 |
Token | want |
Token ID | 765 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
gaard | +0.831 |
ivist | +0.727 |
cific | +0.714 |
iors | +0.713 |
phies | +0.711 |
Neg logit contributions | |
Idol | -0.714 |
Holo | -0.679 |
fw | -0.669 |
sych | -0.668 |
tremend | -0.655 |
Token | to |
Token ID | 284 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
Idol | +1.197 |
Holo | +1.129 |
fw | +1.090 |
sych | +1.086 |
tremend | +1.060 |
Neg logit contributions | |
gaard | -1.676 |
ivist | -1.484 |
cific | -1.465 |
phies | -1.459 |
iferation | -1.453 |
Token | � |
Token ID | 564 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Idol | +0.403 |
Holo | +0.382 |
fw | +0.375 |
sych | +0.373 |
tremend | +0.365 |
Neg logit contributions | |
gaard | -0.517 |
ivist | -0.456 |
cific | -0.450 |
phies | -0.448 |
iors | -0.445 |
Token | � |
Token ID | 246 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
Idol | +0.662 |
Holo | +0.634 |
tremend | +0.629 |
fw | +0.628 |
sych | +0.625 |
Neg logit contributions | |
gaard | -0.566 |
ivist | -0.485 |
phies | -0.473 |
cific | -0.473 |
iors | -0.472 |
Token | net |
Token ID | 3262 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
gaard | +2.775 |
ivist | +2.456 |
cific | +2.417 |
phies | +2.412 |
iors | +2.401 |
Neg logit contributions | |
Idol | -2.084 |
Holo | -1.981 |
sych | -1.926 |
fw | -1.924 |
tremend | -1.899 |
Token | - |
Token ID | 12 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
Idol | +0.055 |
Holo | +0.053 |
fw | +0.051 |
sych | +0.051 |
tremend | +0.050 |
Neg logit contributions | |
gaard | -0.074 |
ivist | -0.065 |
cific | -0.064 |
phies | -0.064 |
iors | -0.064 |
Token | deck |
Token ID | 35875 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
gaard | +2.694 |
ivist | +2.410 |
cific | +2.338 |
phies | +2.324 |
gets | +2.314 |
Neg logit contributions | |
Idol | -2.054 |
Holo | -1.955 |
sych | -1.896 |
tremend | -1.871 |
fw | -1.869 |
Token | � |
Token ID | 447 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
gaard | +1.350 |
ivist | +1.193 |
cific | +1.170 |
phies | +1.161 |
iors | +1.156 |
Neg logit contributions | |
Idol | -1.063 |
Holo | -1.012 |
fw | -0.999 |
sych | -0.995 |
tremend | -0.974 |
Token | started |
Token ID | 2067 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
Idol | +1.453 |
Holo | +1.389 |
fw | +1.348 |
sych | +1.347 |
Barcl | +1.297 |
Neg logit contributions | |
gaard | -1.597 |
ivist | -1.393 |
cific | -1.386 |
iferation | -1.376 |
phies | -1.374 |
Token | his |
Token ID | 465 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
Idol | +1.126 |
Holo | +1.068 |
fw | +1.039 |
sych | +1.031 |
tremend | +1.005 |
Neg logit contributions | |
gaard | -1.533 |
ivist | -1.356 |
cific | -1.343 |
phies | -1.339 |
iferation | -1.329 |
Token | own |
Token ID | 898 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
Idol | +1.720 |
Holo | +1.638 |
fw | +1.598 |
sych | +1.579 |
tremend | +1.542 |
Neg logit contributions | |
gaard | -1.944 |
ivist | -1.689 |
cific | -1.681 |
phies | -1.678 |
iors | -1.657 |
Token | martial |
Token ID | 15618 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
Idol | +2.966 |
Holo | +2.815 |
fw | +2.691 |
sych | +2.622 |
Barcl | +2.597 |
Neg logit contributions | |
gaard | -4.097 |
phies | -3.625 |
cific | -3.619 |
ivist | -3.589 |
iferation | -3.582 |
Token | arts |
Token ID | 10848 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
gaard | +2.127 |
ivist | +1.920 |
cific | +1.886 |
iors | +1.879 |
phies | +1.872 |
Neg logit contributions | |
Idol | -1.252 |
fw | -1.184 |
Holo | -1.180 |
sych | -1.170 |
tremend | -1.143 |
Token | school |
Token ID | 1524 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
Idol | +2.100 |
Holo | +1.973 |
fw | +1.890 |
sych | +1.867 |
tremend | +1.807 |
Neg logit contributions | |
gaard | -3.518 |
cific | -3.128 |
ivist | -3.125 |
phies | -3.116 |
iferation | -3.076 |
Token | and |
Token ID | 290 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
Idol | +2.062 |
Holo | +1.959 |
fw | +1.887 |
sych | +1.876 |
tremend | +1.823 |
Neg logit contributions | |
gaard | -2.678 |
ivist | -2.354 |
cific | -2.351 |
phies | -2.342 |
iferation | -2.317 |
Token | all |
Token ID | 477 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
Idol | +0.301 |
Holo | +0.287 |
fw | +0.282 |
sych | +0.282 |
tremend | +0.276 |
Neg logit contributions | |
gaard | -0.296 |
ivist | -0.257 |
cific | -0.252 |
phies | -0.252 |
iors | -0.249 |
Token | went |
Token ID | 1816 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
gaard | +1.971 |
ivist | +1.740 |
cific | +1.713 |
phies | +1.708 |
iors | +1.697 |
Neg logit contributions | |
Idol | -1.614 |
Holo | -1.529 |
fw | -1.514 |
sych | -1.505 |
tremend | -1.480 |
Token | well |
Token ID | 880 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Idol | +0.264 |
Holo | +0.248 |
fw | +0.244 |
sych | +0.243 |
tremend | +0.236 |
Neg logit contributions | |
gaard | -0.428 |
ivist | -0.384 |
cific | -0.377 |
phies | -0.376 |
iors | -0.375 |
Token | for |
Token ID | 329 |
Feature activation | -9.19e-03 |
Pos logit contributions | |
gaard | +1.402 |
ivist | +1.242 |
iors | +1.210 |
phies | +1.204 |
cific | +1.197 |
Neg logit contributions | |
Idol | -1.217 |
Holo | -1.165 |
sych | -1.147 |
fw | -1.144 |
tremend | -1.123 |
Token | s |
Token ID | 82 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
gaard | +0.874 |
ivist | +0.764 |
cific | +0.750 |
phies | +0.747 |
iors | +0.745 |
Neg logit contributions | |
Idol | -0.805 |
Holo | -0.765 |
fw | -0.749 |
sych | -0.746 |
tremend | -0.735 |
Token | just |
Token ID | 655 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
gaard | +2.454 |
ivist | +2.156 |
iors | +2.119 |
phies | +2.106 |
cific | +2.100 |
Neg logit contributions | |
Idol | -2.027 |
Holo | -1.915 |
sych | -1.883 |
fw | -1.882 |
tremend | -1.843 |
Token | good |
Token ID | 922 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
gaard | +0.815 |
ivist | +0.725 |
cific | +0.712 |
phies | +0.710 |
iors | +0.705 |
Neg logit contributions | |
Idol | -0.620 |
Holo | -0.584 |
sych | -0.577 |
fw | -0.577 |
tremend | -0.562 |
Token | timing |
Token ID | 10576 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
gaard | +0.949 |
ivist | +0.845 |
cific | +0.828 |
phies | +0.823 |
iors | +0.822 |
Neg logit contributions | |
Idol | -0.647 |
Holo | -0.612 |
fw | -0.598 |
sych | -0.597 |
tremend | -0.583 |
Token | . |
Token ID | 13 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Idol | +2.053 |
Holo | +1.928 |
fw | +1.901 |
sych | +1.873 |
tremend | +1.819 |
Neg logit contributions | |
gaard | -2.952 |
ivist | -2.614 |
cific | -2.597 |
phies | -2.595 |
iferation | -2.581 |
Token | I |
Token ID | 314 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Idol | +1.017 |
Holo | +0.965 |
fw | +0.943 |
sych | +0.937 |
tremend | +0.903 |
Neg logit contributions | |
gaard | -1.273 |
ivist | -1.122 |
phies | -1.108 |
cific | -1.108 |
iferation | -1.098 |
Token | don |
Token ID | 836 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
Idol | +1.774 |
Holo | +1.670 |
fw | +1.645 |
sych | +1.635 |
tremend | +1.576 |
Neg logit contributions | |
gaard | -2.438 |
ivist | -2.171 |
cific | -2.146 |
phies | -2.142 |
iferation | -2.122 |
Token | � |
Token ID | 447 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Idol | +1.749 |
Holo | +1.639 |
fw | +1.596 |
sych | +1.592 |
tremend | +1.566 |
Neg logit contributions | |
gaard | -3.103 |
ivist | -2.786 |
cific | -2.753 |
phies | -2.745 |
iors | -2.727 |
Token | � |
Token ID | 247 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Idol | +1.181 |
tremend | +1.134 |
Holo | +1.132 |
sych | +1.120 |
fw | +1.118 |
Neg logit contributions | |
gaard | -0.994 |
ivist | -0.841 |
iors | -0.833 |
phies | -0.830 |
cific | -0.822 |
Token | t |
Token ID | 83 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
gaard | +0.627 |
ivist | +0.564 |
cific | +0.556 |
phies | +0.555 |
iors | +0.553 |
Neg logit contributions | |
Idol | -0.337 |
Holo | -0.316 |
sych | -0.303 |
fw | -0.302 |
tremend | -0.300 |
Token | know |
Token ID | 760 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
gaard | +0.689 |
ivist | +0.611 |
phies | +0.598 |
cific | +0.598 |
iors | +0.597 |
Neg logit contributions | |
Idol | -0.535 |
Holo | -0.511 |
fw | -0.498 |
sych | -0.495 |
tremend | -0.488 |
Token | be |
Token ID | 307 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
gaard | +0.631 |
ivist | +0.548 |
cific | +0.538 |
phies | +0.537 |
iors | +0.536 |
Neg logit contributions | |
Idol | -0.630 |
Holo | -0.602 |
fw | -0.602 |
sych | -0.598 |
tremend | -0.591 |
Token | headed |
Token ID | 15353 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
gaard | +0.467 |
ivist | +0.368 |
cific | +0.362 |
phies | +0.359 |
iors | +0.354 |
Neg logit contributions | |
Idol | -0.998 |
Holo | -0.965 |
fw | -0.950 |
sych | -0.949 |
tremend | -0.946 |
Token | therein |
Token ID | 27258 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
gaard | +0.076 |
ivist | +0.067 |
cific | +0.066 |
phies | +0.066 |
iors | +0.065 |
Neg logit contributions | |
Idol | -0.063 |
Holo | -0.060 |
fw | -0.059 |
sych | -0.059 |
tremend | -0.057 |
Token | .[ |
Token ID | 3693 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
Idol | +2.207 |
Holo | +2.085 |
fw | +2.029 |
sych | +2.017 |
tremend | +1.972 |
Neg logit contributions | |
gaard | -2.995 |
ivist | -2.648 |
cific | -2.624 |
phies | -2.623 |
iferation | -2.615 |
Token | 1 |
Token ID | 16 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
Idol | +2.687 |
Holo | +2.513 |
fw | +2.456 |
sych | +2.433 |
ARA | +2.312 |
Neg logit contributions | |
gaard | -5.875 |
cific | -5.294 |
ivist | -5.288 |
iferation | -5.285 |
phies | -5.217 |
Token | ][ |
Token ID | 7131 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Idol | +2.697 |
Holo | +2.519 |
fw | +2.484 |
sych | +2.392 |
ARA | +2.337 |
Neg logit contributions | |
gaard | -5.031 |
cific | -4.512 |
ivist | -4.499 |
phies | -4.463 |
iferation | -4.451 |
Token | 27 |
Token ID | 1983 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
Idol | +3.522 |
Holo | +3.312 |
fw | +3.253 |
sych | +3.200 |
ARA | +3.097 |
Neg logit contributions | |
gaard | -7.325 |
iferation | -6.598 |
cific | -6.566 |
ivist | -6.541 |
phies | -6.524 |
Token | ][ |
Token ID | 7131 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
Idol | +1.151 |
Holo | +1.098 |
fw | +1.073 |
sych | +1.047 |
ARA | +1.006 |
Neg logit contributions | |
gaard | -2.089 |
ivist | -1.876 |
cific | -1.858 |
phies | -1.853 |
iors | -1.824 |
Token | 45 |
Token ID | 2231 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
Idol | +2.912 |
Holo | +2.733 |
fw | +2.682 |
sych | +2.633 |
ARA | +2.537 |
Neg logit contributions | |
gaard | -5.864 |
ivist | -5.258 |
iferation | -5.237 |
cific | -5.237 |
phies | -5.218 |
Token | ] |
Token ID | 60 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Idol | +2.673 |
Holo | +2.554 |
fw | +2.495 |
sych | +2.430 |
Barcl | +2.321 |
Neg logit contributions | |
gaard | -5.380 |
cific | -4.839 |
ivist | -4.824 |
phies | -4.781 |
iferation | -4.743 |
Token |
|
Token ID | 198 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
Idol | +1.037 |
Holo | +0.984 |
fw | +0.963 |
sych | +0.957 |
tremend | +0.929 |
Neg logit contributions | |
gaard | -1.296 |
ivist | -1.144 |
cific | -1.128 |
phies | -1.127 |
iferation | -1.115 |
Token | Sea |
Token ID | 6896 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
gaard | +1.211 |
ivist | +1.083 |
cific | +1.069 |
phies | +1.066 |
iors | +1.057 |
Neg logit contributions | |
Idol | -0.743 |
Holo | -0.699 |
fw | -0.684 |
sych | -0.681 |
tremend | -0.663 |
Token | Islands |
Token ID | 12010 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
gaard | +0.475 |
ivist | +0.423 |
cific | +0.417 |
phies | +0.416 |
iors | +0.412 |
Neg logit contributions | |
Idol | -0.335 |
Holo | -0.317 |
fw | -0.311 |
sych | -0.310 |
tremend | -0.302 |
Token | ; |
Token ID | 26 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Idol | +1.298 |
Holo | +1.230 |
fw | +1.175 |
sych | +1.146 |
Consortium | +1.130 |
Neg logit contributions | |
gaard | -2.548 |
ivist | -2.290 |
cific | -2.282 |
phies | -2.267 |
gets | -2.244 |
Token | Heard |
Token ID | 49417 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Idol | +0.956 |
Holo | +0.910 |
fw | +0.884 |
sych | +0.879 |
tremend | +0.854 |
Neg logit contributions | |
gaard | -1.132 |
ivist | -0.996 |
phies | -0.984 |
cific | -0.983 |
iors | -0.972 |
Token | Island |
Token ID | 5451 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Idol | +3.879 |
Barcl | +3.442 |
Holo | +3.431 |
ter | +3.259 |
fw | +3.229 |
Neg logit contributions | |
gaard | -6.125 |
cific | -5.573 |
phies | -5.568 |
ivist | -5.425 |
iors | -5.323 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Idol | +5.131 |
Holo | +4.569 |
Barcl | +4.458 |
sych | +4.299 |
fw | +4.290 |
Neg logit contributions | |
gaard | -8.894 |
cific | -8.269 |
phies | -7.971 |
iferation | -7.780 |
ivist | -7.658 |
Token | McDonald |
Token ID | 14115 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
Idol | +3.761 |
Holo | +3.516 |
Barcl | +3.476 |
ter | +3.210 |
sych | +3.109 |
Neg logit contributions | |
gaard | -7.511 |
phies | -6.865 |
iferation | -6.850 |
cific | -6.766 |
iors | -6.705 |
Token | Islands |
Token ID | 12010 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
Idol | +3.115 |
Holo | +2.970 |
fw | +2.905 |
sych | +2.893 |
Barcl | +2.811 |
Neg logit contributions | |
gaard | -3.044 |
ivist | -2.628 |
phies | -2.606 |
cific | -2.604 |
iors | -2.569 |
Token | ; |
Token ID | 26 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
Idol | +2.840 |
Holo | +2.707 |
fw | +2.526 |
Consortium | +2.496 |
Barcl | +2.454 |
Neg logit contributions | |
gaard | -6.223 |
cific | -5.584 |
ivist | -5.577 |
phies | -5.548 |
gets | -5.478 |
Token | and |
Token ID | 290 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
Idol | +1.553 |
Holo | +1.479 |
fw | +1.421 |
sych | +1.415 |
Barcl | +1.384 |
Neg logit contributions | |
gaard | -1.846 |
ivist | -1.620 |
phies | -1.613 |
cific | -1.608 |
iors | -1.588 |
Token | J |
Token ID | 449 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
Idol | +3.061 |
Holo | +2.906 |
fw | +2.739 |
sych | +2.739 |
Barcl | +2.731 |
Neg logit contributions | |
gaard | -3.886 |
phies | -3.428 |
ivist | -3.416 |
cific | -3.393 |
iors | -3.374 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
gaard | +0.083 |
ivist | +0.073 |
cific | +0.072 |
phies | +0.071 |
iors | +0.071 |
Neg logit contributions | |
Idol | -0.071 |
Holo | -0.067 |
fw | -0.066 |
sych | -0.066 |
tremend | -0.064 |
Token | News |
Token ID | 3000 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
gaard | +0.593 |
ivist | +0.523 |
cific | +0.515 |
phies | +0.513 |
iors | +0.509 |
Neg logit contributions | |
Idol | -0.479 |
Holo | -0.454 |
fw | -0.446 |
sych | -0.445 |
tremend | -0.437 |
Token | footage |
Token ID | 9640 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
gaard | +0.474 |
ivist | +0.417 |
cific | +0.410 |
phies | +0.409 |
iors | +0.405 |
Neg logit contributions | |
Idol | -0.398 |
Holo | -0.378 |
fw | -0.371 |
sych | -0.370 |
tremend | -0.362 |
Token | shown |
Token ID | 3402 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Idol | +1.424 |
Holo | +1.357 |
fw | +1.321 |
sych | +1.319 |
tremend | +1.267 |
Neg logit contributions | |
gaard | -1.653 |
ivist | -1.439 |
cific | -1.434 |
phies | -1.430 |
iferation | -1.421 |
Token | on |
Token ID | 319 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
gaard | +1.191 |
ivist | +1.050 |
cific | +1.032 |
phies | +1.026 |
iors | +1.020 |
Neg logit contributions | |
Idol | -1.010 |
Holo | -0.960 |
fw | -0.946 |
sych | -0.943 |
tremend | -0.925 |
Token | local |
Token ID | 1957 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Idol | +1.142 |
Holo | +1.081 |
fw | +1.054 |
sych | +1.045 |
tremend | +1.020 |
Neg logit contributions | |
gaard | -1.499 |
ivist | -1.323 |
cific | -1.309 |
phies | -1.309 |
iors | -1.295 |
Token | television |
Token ID | 5581 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
Idol | +3.427 |
Holo | +3.213 |
fw | +3.005 |
sych | +2.887 |
Consortium | +2.803 |
Neg logit contributions | |
gaard | -7.257 |
phies | -6.610 |
cific | -6.576 |
ivist | -6.494 |
iferation | -6.494 |
Token | has |
Token ID | 468 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Idol | +1.685 |
Holo | +1.602 |
fw | +1.568 |
sych | +1.560 |
tremend | +1.514 |
Neg logit contributions | |
gaard | -2.008 |
ivist | -1.765 |
cific | -1.752 |
phies | -1.745 |
iferation | -1.726 |
Token | revealed |
Token ID | 4602 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
Idol | +1.576 |
Holo | +1.500 |
fw | +1.458 |
sych | +1.453 |
tremend | +1.408 |
Neg logit contributions | |
gaard | -1.945 |
ivist | -1.709 |
phies | -1.695 |
cific | -1.695 |
iferation | -1.681 |
Token | lines |
Token ID | 3951 |
Feature activation | -6.07e-03 |
Pos logit contributions | |
Idol | +0.260 |
Holo | +0.246 |
fw | +0.241 |
sych | +0.239 |
tremend | +0.234 |
Neg logit contributions | |
gaard | -0.340 |
ivist | -0.301 |
cific | -0.298 |
phies | -0.296 |
iferation | -0.294 |
Token | of |
Token ID | 286 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
Idol | +0.026 |
Holo | +0.024 |
fw | +0.024 |
sych | +0.024 |
tremend | +0.023 |
Neg logit contributions | |
gaard | -0.031 |
ivist | -0.027 |
cific | -0.027 |
phies | -0.027 |
iferation | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
gaard | +0.998 |
ivist | +0.875 |
cific | +0.864 |
phies | +0.859 |
iors | +0.852 |
Neg logit contributions | |
Idol | -0.833 |
Holo | -0.792 |
fw | -0.783 |
sych | -0.782 |
tremend | -0.782 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
gaard | +0.799 |
ivist | +0.691 |
iors | +0.681 |
gets | +0.678 |
cific | +0.676 |
Neg logit contributions | |
tremend | -0.907 |
Idol | -0.842 |
Holo | -0.804 |
sych | -0.801 |
fw | -0.788 |
Token | It |
Token ID | 1026 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
gaard | +0.672 |
ivist | +0.594 |
cific | +0.585 |
phies | +0.585 |
iors | +0.582 |
Neg logit contributions | |
Idol | -0.516 |
Holo | -0.488 |
tremend | -0.482 |
sych | -0.475 |
fw | -0.473 |
Token | was |
Token ID | 373 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
gaard | +0.227 |
ivist | +0.199 |
cific | +0.196 |
phies | +0.195 |
iors | +0.193 |
Neg logit contributions | |
Idol | -0.205 |
Holo | -0.196 |
fw | -0.192 |
sych | -0.191 |
tremend | -0.187 |
Token | the |
Token ID | 262 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
Idol | +0.307 |
Holo | +0.291 |
fw | +0.285 |
sych | +0.284 |
tremend | +0.277 |
Neg logit contributions | |
gaard | -0.410 |
ivist | -0.363 |
cific | -0.358 |
phies | -0.357 |
iors | -0.354 |
Token | kind |
Token ID | 1611 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Idol | +1.917 |
Holo | +1.810 |
fw | +1.758 |
sych | +1.755 |
tremend | +1.713 |
Neg logit contributions | |
gaard | -2.612 |
ivist | -2.328 |
cific | -2.293 |
phies | -2.288 |
iferation | -2.265 |
Token | of |
Token ID | 286 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
Idol | +4.619 |
Holo | +4.261 |
ter | +4.136 |
sych | +4.118 |
tremend | +4.111 |
Neg logit contributions | |
gaard | -7.047 |
iferation | -6.445 |
ivist | -6.392 |
cific | -6.340 |
iors | -6.254 |
Token | game |
Token ID | 983 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Idol | +2.859 |
Holo | +2.712 |
fw | +2.593 |
sych | +2.588 |
tremend | +2.539 |
Neg logit contributions | |
gaard | -3.906 |
ivist | -3.507 |
phies | -3.454 |
cific | -3.453 |
iferation | -3.433 |
Token | that |
Token ID | 326 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
gaard | +0.585 |
ivist | +0.518 |
cific | +0.510 |
phies | +0.508 |
iors | +0.504 |
Neg logit contributions | |
Idol | -0.459 |
Holo | -0.435 |
fw | -0.430 |
sych | -0.428 |
tremend | -0.418 |
Token | leaves |
Token ID | 5667 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
Idol | +1.272 |
Holo | +1.210 |
fw | +1.180 |
sych | +1.177 |
tremend | +1.155 |
Neg logit contributions | |
gaard | -1.375 |
ivist | -1.203 |
cific | -1.186 |
phies | -1.181 |
iferation | -1.174 |
Token | you |
Token ID | 345 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
Idol | +3.215 |
Holo | +3.050 |
fw | +2.938 |
sych | +2.917 |
tremend | +2.893 |
Neg logit contributions | |
gaard | -3.818 |
ivist | -3.403 |
cific | -3.374 |
iferation | -3.358 |
phies | -3.327 |
Token | single |
Token ID | 2060 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Idol | +1.024 |
Holo | +0.972 |
fw | +0.947 |
sych | +0.943 |
tremend | +0.918 |
Neg logit contributions | |
gaard | -1.395 |
ivist | -1.236 |
cific | -1.224 |
phies | -1.220 |
iferation | -1.209 |
Token | dumb |
Token ID | 13526 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
Idol | +1.745 |
Holo | +1.657 |
fw | +1.601 |
sych | +1.592 |
Barcl | +1.538 |
Neg logit contributions | |
gaard | -2.409 |
ivist | -2.129 |
cific | -2.124 |
phies | -2.117 |
iferation | -2.098 |
Token | bell |
Token ID | 7923 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
gaard | +3.602 |
ivist | +3.226 |
iors | +3.163 |
cific | +3.146 |
phies | +3.142 |
Neg logit contributions | |
Idol | -2.110 |
Holo | -2.009 |
sych | -1.965 |
fw | -1.939 |
tremend | -1.937 |
Token | and |
Token ID | 290 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Idol | +2.726 |
Holo | +2.592 |
fw | +2.505 |
sych | +2.473 |
tremend | +2.419 |
Neg logit contributions | |
gaard | -3.376 |
ivist | -2.958 |
cific | -2.953 |
phies | -2.953 |
iferation | -2.909 |
Token | weight |
Token ID | 3463 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Idol | +1.167 |
Holo | +1.109 |
fw | +1.077 |
sych | +1.070 |
tremend | +1.044 |
Neg logit contributions | |
gaard | -1.508 |
ivist | -1.334 |
cific | -1.321 |
phies | -1.316 |
iferation | -1.306 |
Token | lifting |
Token ID | 30510 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Idol | +1.826 |
Holo | +1.719 |
fw | +1.696 |
sych | +1.671 |
tremend | +1.622 |
Neg logit contributions | |
gaard | -2.422 |
cific | -2.131 |
ivist | -2.120 |
phies | -2.111 |
iferation | -2.084 |
Token | plates |
Token ID | 13375 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
Idol | +4.000 |
Holo | +3.747 |
Barcl | +3.492 |
fw | +3.478 |
jack | +3.454 |
Neg logit contributions | |
gaard | -6.066 |
cific | -5.404 |
ivist | -5.375 |
iferation | -5.351 |
phies | -5.337 |
Token | stre |
Token ID | 1937 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Idol | +3.172 |
Holo | +3.012 |
fw | +2.932 |
sych | +2.894 |
ARA | +2.799 |
Neg logit contributions | |
gaard | -3.942 |
cific | -3.487 |
ivist | -3.467 |
phies | -3.450 |
iferation | -3.408 |
Token | wn |
Token ID | 675 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
gaard | +3.236 |
ivist | +2.569 |
phies | +2.484 |
cific | +2.457 |
iors | +2.432 |
Neg logit contributions | |
Idol | -6.717 |
Holo | -6.517 |
tremend | -6.455 |
sych | -6.297 |
fw | -6.270 |
Token | on |
Token ID | 319 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
gaard | +4.368 |
ivist | +3.801 |
iors | +3.688 |
phies | +3.574 |
iferation | +3.553 |
Neg logit contributions | |
Idol | -5.143 |
sych | -4.995 |
Holo | -4.984 |
fw | -4.978 |
tremend | -4.911 |
Token | one |
Token ID | 530 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
gaard | +0.343 |
ivist | +0.304 |
phies | +0.299 |
cific | +0.299 |
iors | +0.297 |
Neg logit contributions | |
Idol | -0.252 |
Holo | -0.239 |
fw | -0.235 |
sych | -0.235 |
tremend | -0.229 |