Token | three |
Token ID | 1115 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Lie | +1.899 |
parach | +1.768 |
Simulation | +1.607 |
Chaff | +1.601 |
itzer | +1.520 |
Neg logit contributions | |
uni | -3.462 |
zik | -3.413 |
Toronto | -3.401 |
opian | -3.394 |
aunder | -3.258 |
Token | meaningful |
Token ID | 11570 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
Lie | +2.170 |
parach | +2.138 |
actionGroup | +1.880 |
Simulation | +1.872 |
Chaff | +1.858 |
Neg logit contributions | |
Toronto | -4.528 |
zik | -4.519 |
uni | -4.509 |
aunder | -4.215 |
opian | -4.173 |
Token | actions |
Token ID | 4028 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Lie | +2.195 |
parach | +2.174 |
actionGroup | +1.968 |
Simulation | +1.917 |
Chaff | +1.886 |
Neg logit contributions | |
Toronto | -3.781 |
zik | -3.767 |
uni | -3.749 |
opian | -3.575 |
aunder | -3.540 |
Token | you |
Token ID | 345 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
Lie | +2.460 |
parach | +2.312 |
Simulation | +2.210 |
Chaff | +2.153 |
itta | +2.116 |
Neg logit contributions | |
Toronto | -2.503 |
uni | -2.472 |
zik | -2.453 |
opian | -2.376 |
rall | -2.367 |
Token | can |
Token ID | 460 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Lie | +3.597 |
parach | +3.511 |
Simulation | +3.237 |
Chaff | +3.183 |
actionGroup | +3.177 |
Neg logit contributions | |
Toronto | -4.420 |
uni | -4.301 |
zik | -4.219 |
rall | -4.201 |
opian | -4.147 |
Token | take |
Token ID | 1011 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Lie | +2.274 |
parach | +2.151 |
Simulation | +1.978 |
itta | +1.970 |
Chaff | +1.916 |
Neg logit contributions | |
Toronto | -2.602 |
zik | -2.499 |
uni | -2.469 |
opian | -2.418 |
gyn | -2.300 |
Token | each |
Token ID | 1123 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
parach | +3.604 |
Lie | +3.588 |
Chaff | +2.955 |
@@ | +2.637 |
Simulation | +2.485 |
Neg logit contributions | |
zik | -20.418 |
Toronto | -19.818 |
rall | -19.597 |
uni | -19.473 |
opian | -19.120 |
Token | week |
Token ID | 1285 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Lie | +2.130 |
parach | +2.004 |
itta | +1.816 |
Simulation | +1.730 |
Chaff | +1.717 |
Neg logit contributions | |
Toronto | -4.135 |
uni | -4.048 |
zik | -4.021 |
opian | -4.003 |
aunder | -3.877 |
Token | . |
Token ID | 13 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
Lie | +2.728 |
Simulation | +2.373 |
parach | +2.273 |
itta | +2.268 |
Chaff | +2.253 |
Neg logit contributions | |
rall | -3.917 |
zik | -3.823 |
opian | -3.739 |
Toronto | -3.733 |
uni | -3.662 |
Token |
|
Token ID | 198 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
Lie | +4.619 |
Simulation | +3.965 |
Chaff | +3.721 |
parach | +3.600 |
@@ | +3.600 |
Neg logit contributions | |
rall | -7.436 |
zik | -7.070 |
opian | -7.016 |
uckland | -6.900 |
uni | -6.891 |
Token |
|
Token ID | 198 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
Lie | +4.033 |
Simulation | +3.389 |
@@ | +3.205 |
parach | +3.177 |
Chaff | +3.162 |
Neg logit contributions | |
rall | -7.164 |
zik | -6.712 |
uckland | -6.642 |
ngth | -6.600 |
opian | -6.541 |
Token | Psychology |
Token ID | 18430 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Lie | +1.601 |
Simulation | +1.406 |
parach | +1.309 |
Curse | +1.267 |
Princ | +1.253 |
Neg logit contributions | |
zik | -2.528 |
Toronto | -2.502 |
opian | -2.488 |
uni | -2.482 |
aunder | -2.433 |
Token | , |
Token ID | 11 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Toronto | +1.540 |
uni | +1.428 |
zik | +1.405 |
opian | +1.371 |
gyn | +1.291 |
Neg logit contributions | |
Lie | -2.453 |
parach | -2.422 |
Simulation | -2.329 |
actionGroup | -2.303 |
itta | -2.292 |
Token | 49 |
Token ID | 5125 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Lie | +1.596 |
Simulation | +1.471 |
parach | +1.417 |
Chaff | +1.386 |
Princ | +1.384 |
Neg logit contributions | |
zik | -1.289 |
opian | -1.252 |
Toronto | -1.248 |
uni | -1.237 |
aunder | -1.149 |
Token | , |
Token ID | 11 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
Lie | +1.078 |
parach | +1.040 |
Simulation | +1.017 |
itta | +0.985 |
Chaff | +0.969 |
Neg logit contributions | |
Toronto | -0.755 |
zik | -0.718 |
uni | -0.703 |
opian | -0.677 |
aunder | -0.637 |
Token | 306 |
Token ID | 37255 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Lie | +5.963 |
Simulation | +5.337 |
parach | +5.189 |
Princ | +5.130 |
Chaff | +5.015 |
Neg logit contributions | |
zik | -5.689 |
Toronto | -5.628 |
opian | -5.527 |
uni | -5.486 |
aunder | -5.135 |
Token | - |
Token ID | 532 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Lie | +5.492 |
Simulation | +4.822 |
Chaff | +4.447 |
Curse | +4.128 |
Lie | +4.054 |
Neg logit contributions | |
rall | -10.264 |
zik | -10.242 |
opian | -9.990 |
uni | -9.945 |
uckland | -9.714 |
Token | 307 |
Token ID | 38369 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
Lie | +8.439 |
Simulation | +6.806 |
Curse | +6.680 |
Chaff | +6.528 |
Princ | +6.376 |
Neg logit contributions | |
opian | -14.080 |
zik | -13.925 |
uni | -13.813 |
Toronto | -13.339 |
uckland | -13.116 |
Token | . |
Token ID | 764 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
Lie | +3.070 |
Simulation | +2.404 |
Chaff | +2.120 |
itta | +2.003 |
parach | +1.794 |
Neg logit contributions | |
rall | -10.519 |
zik | -10.039 |
opian | -9.925 |
uckland | -9.768 |
uni | -9.764 |
Token |
|
Token ID | 198 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Lie | +3.455 |
Simulation | +2.981 |
Chaff | +2.754 |
parach | +2.752 |
itta | +2.734 |
Neg logit contributions | |
rall | -5.136 |
zik | -4.992 |
opian | -4.929 |
uni | -4.819 |
uckland | -4.814 |
Token |
|
Token ID | 198 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
Lie | +1.360 |
Simulation | +1.191 |
parach | +1.165 |
itta | +1.117 |
Chaff | +1.112 |
Neg logit contributions | |
zik | -1.718 |
Toronto | -1.680 |
rall | -1.670 |
opian | -1.664 |
uni | -1.658 |
Token | Google |
Token ID | 11708 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Lie | +3.008 |
Lie | +2.761 |
Simulation | +2.668 |
@@ | +2.644 |
JUST | +2.626 |
Neg logit contributions | |
zik | -2.875 |
rall | -2.745 |
opian | -2.687 |
fitt | -2.586 |
conserve | -2.578 |
Token | 97 |
Token ID | 5607 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Lie | +6.370 |
@@ | +5.367 |
Simulation | +5.230 |
Lie | +5.111 |
Chaff | +4.945 |
Neg logit contributions | |
zik | -12.542 |
opian | -12.333 |
aunder | -12.106 |
Toronto | -11.884 |
uni | -11.871 |
Token | ] |
Token ID | 60 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
Lie | +2.408 |
parach | +2.325 |
Simulation | +2.292 |
itta | +2.237 |
Chaff | +2.215 |
Neg logit contributions | |
Toronto | -0.805 |
zik | -0.752 |
uni | -0.717 |
opian | -0.682 |
aunder | -0.605 |
Token | Ble |
Token ID | 17175 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
Toronto | +0.247 |
zik | +0.240 |
uni | +0.235 |
opian | +0.231 |
aunder | +0.218 |
Neg logit contributions | |
Lie | -0.237 |
parach | -0.222 |
Simulation | -0.219 |
itta | -0.209 |
Princ | -0.207 |
Token | acher |
Token ID | 3493 |
Feature activation | -7.46e-03 |
Pos logit contributions | |
Toronto | +0.582 |
zik | +0.566 |
uni | +0.553 |
opian | +0.542 |
aunder | +0.514 |
Neg logit contributions | |
Lie | -0.569 |
parach | -0.535 |
Simulation | -0.526 |
itta | -0.507 |
Chaff | -0.497 |
Token | Report |
Token ID | 6358 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Toronto | +0.057 |
zik | +0.056 |
uni | +0.054 |
opian | +0.053 |
aunder | +0.050 |
Neg logit contributions | |
Lie | -0.063 |
parach | -0.059 |
Simulation | -0.058 |
itta | -0.056 |
Princ | -0.055 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Lie | +2.546 |
parach | +2.411 |
Simulation | +2.390 |
itta | +2.292 |
Princ | +2.281 |
Neg logit contributions | |
Toronto | -1.646 |
zik | -1.609 |
uni | -1.585 |
opian | -1.545 |
aunder | -1.441 |
Token | 98 |
Token ID | 4089 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Lie | +6.871 |
Simulation | +5.467 |
Curse | +5.373 |
itta | +5.268 |
Lie | +5.266 |
Neg logit contributions | |
zik | -14.658 |
brut | -13.688 |
opian | -13.671 |
aunder | -13.499 |
uni | -13.474 |
Token | ] |
Token ID | 60 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
Lie | +4.224 |
parach | +4.067 |
Simulation | +4.015 |
itta | +3.916 |
Chaff | +3.870 |
Neg logit contributions | |
Toronto | -1.510 |
zik | -1.419 |
uni | -1.359 |
opian | -1.302 |
aunder | -1.157 |
Token | Sporting |
Token ID | 31790 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
Toronto | +0.337 |
zik | +0.329 |
uni | +0.322 |
opian | +0.316 |
aunder | +0.300 |
Neg logit contributions | |
Lie | -0.306 |
parach | -0.286 |
Simulation | -0.282 |
itta | -0.268 |
Princ | -0.266 |
Token | News |
Token ID | 3000 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Lie | +0.361 |
Simulation | +0.330 |
parach | +0.330 |
itta | +0.310 |
Princ | +0.308 |
Neg logit contributions | |
Toronto | -0.457 |
zik | -0.453 |
uni | -0.444 |
opian | -0.438 |
aunder | -0.418 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Lie | +2.180 |
parach | +2.066 |
Simulation | +2.054 |
itta | +1.971 |
Princ | +1.953 |
Neg logit contributions | |
Toronto | -1.432 |
zik | -1.410 |
uni | -1.365 |
opian | -1.334 |
aunder | -1.248 |
Token | _ |
Token ID | 62 |
Feature activation | +2.92e-04 |
Pos logit contributions | |
Lie | +1.896 |
Simulation | +1.739 |
parach | +1.665 |
Chaff | +1.652 |
itta | +1.611 |
Neg logit contributions | |
zik | -2.089 |
opian | -2.026 |
Toronto | -2.012 |
uni | -2.011 |
rall | -1.931 |
Token | B |
Token ID | 33 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
Lie | +0.002 |
Simulation | +0.002 |
parach | +0.002 |
Chaff | +0.002 |
itta | +0.002 |
Neg logit contributions | |
zik | -0.002 |
Toronto | -0.002 |
opian | -0.002 |
uni | -0.002 |
aunder | -0.002 |
Token | GR |
Token ID | 10761 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Lie | +2.799 |
Simulation | +2.510 |
@@ | +2.498 |
Chaff | +2.494 |
itta | +2.463 |
Neg logit contributions | |
zik | -2.585 |
opian | -2.578 |
Toronto | -2.438 |
uni | -2.387 |
rall | -2.361 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Lie | +1.979 |
Simulation | +1.815 |
Chaff | +1.681 |
parach | +1.679 |
itta | +1.632 |
Neg logit contributions | |
opian | -2.513 |
zik | -2.512 |
Toronto | -2.391 |
uni | -2.379 |
rall | -2.349 |
Token | G |
Token ID | 38 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Lie | +2.606 |
Simulation | +2.184 |
Chaff | +2.164 |
JUST | +2.023 |
parach | +1.942 |
Neg logit contributions | |
opian | -5.935 |
zik | -5.919 |
uni | -5.733 |
rall | -5.658 |
Toronto | -5.595 |
Token | RAY |
Token ID | 30631 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
zik | +0.593 |
Toronto | +0.592 |
opian | +0.571 |
uni | +0.558 |
aunder | +0.499 |
Neg logit contributions | |
Lie | -1.375 |
Simulation | -1.299 |
parach | -1.297 |
itta | -1.266 |
Chaff | -1.260 |
Token | ) |
Token ID | 1267 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
Lie | +5.131 |
Simulation | +4.297 |
Chaff | +3.768 |
parach | +3.536 |
Winchester | +3.506 |
Neg logit contributions | |
rall | -15.169 |
opian | -14.309 |
uckland | -14.279 |
zik | -13.995 |
�� | -13.904 |
Token | # |
Token ID | 1303 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Lie | +3.124 |
parach | +2.932 |
Simulation | +2.883 |
itta | +2.748 |
Chaff | +2.711 |
Neg logit contributions | |
Toronto | -3.428 |
zik | -3.327 |
uni | -3.249 |
opian | -3.187 |
aunder | -3.022 |
Token | smooth |
Token ID | 7209 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
Lie | +1.364 |
parach | +1.287 |
Simulation | +1.285 |
itta | +1.206 |
Chaff | +1.199 |
Neg logit contributions | |
Toronto | -1.446 |
zik | -1.399 |
uni | -1.365 |
opian | -1.340 |
gyn | -1.256 |
Token | the |
Token ID | 262 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Lie | +0.597 |
parach | +0.543 |
Simulation | +0.536 |
Chaff | +0.509 |
itta | +0.498 |
Neg logit contributions | |
Toronto | -0.829 |
zik | -0.815 |
uni | -0.806 |
opian | -0.800 |
aunder | -0.759 |
Token | image |
Token ID | 2939 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
Toronto | +1.305 |
zik | +1.241 |
uni | +1.206 |
opian | +1.187 |
aunder | +1.122 |
Neg logit contributions | |
Lie | -1.844 |
parach | -1.748 |
Simulation | -1.724 |
itta | -1.646 |
Chaff | -1.643 |
Token | releasing |
Token ID | 13011 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
Toronto | +0.502 |
zik | +0.498 |
uni | +0.485 |
opian | +0.480 |
aunder | +0.459 |
Neg logit contributions | |
Lie | -0.452 |
parach | -0.436 |
Simulation | -0.412 |
itta | -0.397 |
Chaff | -0.389 |
Token | an |
Token ID | 281 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Lie | +0.227 |
parach | +0.216 |
Simulation | +0.205 |
itta | +0.195 |
Princ | +0.194 |
Neg logit contributions | |
Toronto | -0.268 |
zik | -0.265 |
uni | -0.259 |
opian | -0.256 |
aunder | -0.248 |
Token | official |
Token ID | 1743 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Toronto | +1.626 |
zik | +1.590 |
uni | +1.545 |
opian | +1.531 |
aunder | +1.453 |
Neg logit contributions | |
Lie | -1.422 |
parach | -1.334 |
Simulation | -1.302 |
itta | -1.247 |
Princ | -1.226 |
Token | statement |
Token ID | 2643 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Lie | +1.850 |
parach | +1.673 |
Simulation | +1.603 |
itta | +1.544 |
Princ | +1.534 |
Neg logit contributions | |
zik | -2.068 |
Toronto | -2.062 |
uni | -2.040 |
opian | -1.983 |
aunder | -1.896 |
Token | soon |
Token ID | 2582 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
parach | +3.379 |
Lie | +3.322 |
Simulation | +2.897 |
itta | +2.893 |
Princ | +2.877 |
Neg logit contributions | |
zik | -3.573 |
aunder | -3.569 |
Toronto | -3.495 |
uni | -3.492 |
opian | -3.412 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Lie | +1.057 |
Simulation | +0.946 |
parach | +0.929 |
itta | +0.891 |
Chaff | +0.882 |
Neg logit contributions | |
zik | -1.289 |
Toronto | -1.261 |
opian | -1.244 |
uni | -1.237 |
rall | -1.212 |
Token | As |
Token ID | 1081 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
Lie | +7.262 |
Simulation | +6.520 |
Princ | +5.671 |
Chaff | +5.592 |
Aux | +5.554 |
Neg logit contributions | |
rall | -13.013 |
opian | -12.918 |
uckland | -12.830 |
�� | -12.587 |
zik | -12.579 |
Token | well |
Token ID | 880 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Lie | +2.282 |
parach | +2.125 |
Simulation | +1.967 |
Chaff | +1.891 |
itzer | +1.862 |
Neg logit contributions | |
Toronto | -3.336 |
zik | -3.271 |
opian | -3.261 |
uni | -3.239 |
aunder | -3.087 |
Token | as |
Token ID | 355 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Lie | +1.210 |
parach | +1.128 |
Simulation | +1.078 |
Chaff | +1.029 |
itta | +1.000 |
Neg logit contributions | |
Toronto | -1.610 |
uni | -1.555 |
zik | -1.538 |
opian | -1.520 |
aunder | -1.460 |
Token | updates |
Token ID | 5992 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
Lie | +1.299 |
parach | +1.264 |
Simulation | +1.210 |
Chaff | +1.161 |
Princ | +1.140 |
Neg logit contributions | |
Toronto | -1.096 |
zik | -1.088 |
uni | -1.052 |
opian | -1.012 |
gyn | -0.961 |
Token | regarding |
Token ID | 5115 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
Lie | +4.176 |
parach | +3.765 |
Simulation | +3.577 |
Princ | +3.317 |
Chaff | +3.271 |
Neg logit contributions | |
zik | -9.459 |
Toronto | -9.104 |
uni | -8.783 |
opian | -8.597 |
ridges | -8.576 |
Token | 92 |
Token ID | 5892 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Lie | +6.252 |
@@ | +5.165 |
Simulation | +5.151 |
Lie | +4.951 |
itta | +4.889 |
Neg logit contributions | |
zik | -12.359 |
opian | -12.186 |
Toronto | -11.985 |
aunder | -11.933 |
uni | -11.719 |
Token | ] |
Token ID | 60 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Lie | +2.250 |
parach | +2.180 |
Simulation | +2.147 |
itta | +2.093 |
Chaff | +2.067 |
Neg logit contributions | |
Toronto | -0.770 |
zik | -0.721 |
uni | -0.687 |
opian | -0.653 |
aunder | -0.582 |
Token | Ath |
Token ID | 13548 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
Toronto | +1.860 |
zik | +1.796 |
uni | +1.754 |
opian | +1.713 |
aunder | +1.623 |
Neg logit contributions | |
Lie | -1.891 |
parach | -1.789 |
Simulation | -1.756 |
itta | -1.698 |
Chaff | -1.660 |
Token | lon |
Token ID | 14995 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Toronto | +0.952 |
zik | +0.872 |
uni | +0.818 |
opian | +0.768 |
aunder | +0.636 |
Neg logit contributions | |
Lie | -4.165 |
parach | -4.018 |
Simulation | -3.976 |
itta | -3.884 |
Chaff | -3.846 |
Token | Sports |
Token ID | 7092 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Toronto | +1.937 |
zik | +1.887 |
uni | +1.860 |
opian | +1.825 |
aunder | +1.742 |
Neg logit contributions | |
Lie | -1.327 |
parach | -1.234 |
Simulation | -1.207 |
itta | -1.142 |
Princ | -1.121 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Lie | +1.448 |
parach | +1.372 |
Simulation | +1.366 |
itta | +1.305 |
Princ | +1.294 |
Neg logit contributions | |
Toronto | -1.031 |
zik | -1.006 |
uni | -0.986 |
opian | -0.958 |
aunder | -0.903 |
Token | 97 |
Token ID | 5607 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Lie | +6.370 |
@@ | +5.367 |
Simulation | +5.230 |
Lie | +5.111 |
Chaff | +4.945 |
Neg logit contributions | |
zik | -12.542 |
opian | -12.333 |
aunder | -12.106 |
Toronto | -11.884 |
uni | -11.871 |
Token | ] |
Token ID | 60 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
Lie | +2.408 |
parach | +2.325 |
Simulation | +2.292 |
itta | +2.237 |
Chaff | +2.215 |
Neg logit contributions | |
Toronto | -0.805 |
zik | -0.752 |
uni | -0.717 |
opian | -0.682 |
aunder | -0.605 |
Token | Ble |
Token ID | 17175 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
Toronto | +0.247 |
zik | +0.240 |
uni | +0.235 |
opian | +0.231 |
aunder | +0.218 |
Neg logit contributions | |
Lie | -0.237 |
parach | -0.222 |
Simulation | -0.219 |
itta | -0.209 |
Princ | -0.207 |
Token | acher |
Token ID | 3493 |
Feature activation | -7.46e-03 |
Pos logit contributions | |
Toronto | +0.582 |
zik | +0.566 |
uni | +0.553 |
opian | +0.542 |
aunder | +0.514 |
Neg logit contributions | |
Lie | -0.569 |
parach | -0.535 |
Simulation | -0.526 |
itta | -0.507 |
Chaff | -0.497 |
Token | Report |
Token ID | 6358 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Toronto | +0.057 |
zik | +0.056 |
uni | +0.054 |
opian | +0.053 |
aunder | +0.050 |
Neg logit contributions | |
Lie | -0.063 |
parach | -0.059 |
Simulation | -0.058 |
itta | -0.056 |
Princ | -0.055 |
Token | ] |
Token ID | 60 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
Toronto | +0.018 |
zik | +0.017 |
uni | +0.016 |
opian | +0.015 |
aunder | +0.013 |
Neg logit contributions | |
Lie | -0.063 |
parach | -0.061 |
Simulation | -0.060 |
itta | -0.058 |
Chaff | -0.058 |
Token | NBC |
Token ID | 9716 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Lie | +0.491 |
parach | +0.460 |
Simulation | +0.452 |
itta | +0.430 |
Princ | +0.429 |
Neg logit contributions | |
Toronto | -0.507 |
zik | -0.495 |
uni | -0.485 |
opian | -0.479 |
aunder | -0.451 |
Token | Sports |
Token ID | 18153 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
Lie | +1.511 |
parach | +1.363 |
Simulation | +1.346 |
itta | +1.241 |
Princ | +1.237 |
Neg logit contributions | |
Toronto | -2.953 |
zik | -2.939 |
opian | -2.880 |
uni | -2.870 |
aunder | -2.770 |
Token | . |
Token ID | 13 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Lie | +2.569 |
parach | +2.437 |
Simulation | +2.395 |
itta | +2.315 |
Chaff | +2.275 |
Neg logit contributions | |
Toronto | -2.130 |
zik | -2.048 |
uni | -2.002 |
opian | -1.951 |
aunder | -1.833 |
Token | com |
Token ID | 785 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Lie | +2.367 |
Simulation | +2.054 |
parach | +2.010 |
Chaff | +1.973 |
itta | +1.972 |
Neg logit contributions | |
opian | -3.112 |
zik | -3.098 |
rall | -3.041 |
Toronto | -3.030 |
uni | -2.945 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Lie | +2.272 |
parach | +2.161 |
Simulation | +2.126 |
itta | +2.051 |
Princ | +2.034 |
Neg logit contributions | |
Toronto | -1.518 |
zik | -1.490 |
uni | -1.446 |
opian | -1.426 |
aunder | -1.316 |
Token | 92 |
Token ID | 5892 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Lie | +6.252 |
@@ | +5.165 |
Simulation | +5.151 |
Lie | +4.951 |
itta | +4.889 |
Neg logit contributions | |
zik | -12.359 |
opian | -12.186 |
Toronto | -11.985 |
aunder | -11.933 |
uni | -11.719 |
Token | ] |
Token ID | 60 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Lie | +2.250 |
parach | +2.180 |
Simulation | +2.147 |
itta | +2.093 |
Chaff | +2.067 |
Neg logit contributions | |
Toronto | -0.770 |
zik | -0.721 |
uni | -0.687 |
opian | -0.653 |
aunder | -0.582 |
Token | Ath |
Token ID | 13548 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
Toronto | +1.860 |
zik | +1.796 |
uni | +1.754 |
opian | +1.713 |
aunder | +1.623 |
Neg logit contributions | |
Lie | -1.891 |
parach | -1.789 |
Simulation | -1.756 |
itta | -1.698 |
Chaff | -1.660 |
Token | lon |
Token ID | 14995 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Toronto | +0.952 |
zik | +0.872 |
uni | +0.818 |
opian | +0.768 |
aunder | +0.636 |
Neg logit contributions | |
Lie | -4.165 |
parach | -4.018 |
Simulation | -3.976 |
itta | -3.884 |
Chaff | -3.846 |
Token | Sports |
Token ID | 7092 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Toronto | +1.937 |
zik | +1.887 |
uni | +1.860 |
opian | +1.825 |
aunder | +1.742 |
Neg logit contributions | |
Lie | -1.327 |
parach | -1.234 |
Simulation | -1.207 |
itta | -1.142 |
Princ | -1.121 |
Token | June |
Token ID | 2795 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
Lie | +4.533 |
Simulation | +3.977 |
parach | +3.795 |
Princ | +3.778 |
Chaff | +3.748 |
Neg logit contributions | |
opian | -5.033 |
zik | -4.982 |
Toronto | -4.877 |
uni | -4.875 |
aunder | -4.625 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
Lie | +4.027 |
Simulation | +3.560 |
Princ | +3.368 |
Curse | +3.360 |
Chaff | +3.340 |
Neg logit contributions | |
zik | -4.245 |
opian | -4.220 |
uni | -4.144 |
Toronto | -4.120 |
aunder | -3.905 |
Token | Canada |
Token ID | 3340 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Lie | +5.238 |
Simulation | +4.583 |
Princ | +4.521 |
parach | +4.471 |
Chaff | +4.418 |
Neg logit contributions | |
zik | -4.713 |
opian | -4.583 |
uni | -4.517 |
Toronto | -4.476 |
aunder | -4.249 |
Token | 16 |
Token ID | 1467 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
Lie | +2.216 |
Simulation | +2.002 |
parach | +1.929 |
Princ | +1.894 |
Chaff | +1.884 |
Neg logit contributions | |
zik | -2.012 |
opian | -1.977 |
Toronto | -1.942 |
uni | -1.940 |
aunder | -1.807 |
Token | 10 |
Token ID | 940 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
Lie | +4.196 |
Simulation | +3.724 |
Princ | +3.469 |
parach | +3.450 |
Curse | +3.449 |
Neg logit contributions | |
zik | -5.190 |
opian | -5.128 |
uni | -5.126 |
Toronto | -5.048 |
aunder | -4.779 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Lie | +4.096 |
Simulation | +3.525 |
Princ | +3.063 |
Curse | +3.047 |
Chaff | +2.798 |
Neg logit contributions | |
opian | -7.936 |
zik | -7.905 |
uni | -7.702 |
unal | -7.519 |
Toronto | -7.394 |
Token | # |
Token ID | 1303 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Lie | +7.798 |
Simulation | +6.962 |
parach | +6.625 |
itta | +6.395 |
Curse | +6.393 |
Neg logit contributions | |
Toronto | -11.543 |
opian | -11.213 |
zik | -11.203 |
uni | -10.954 |
aunder | -10.465 |
Token | 14 |
Token ID | 1415 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Lie | +1.218 |
parach | +1.007 |
Simulation | +0.983 |
@@ | +0.930 |
itta | +0.900 |
Neg logit contributions | |
zik | -3.063 |
rall | -3.015 |
opian | -2.941 |
conserve | -2.930 |
uni | -2.921 |
Token | On |
Token ID | 1550 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Lie | +1.533 |
parach | +1.424 |
Simulation | +1.402 |
Chaff | +1.344 |
itta | +1.330 |
Neg logit contributions | |
Toronto | -1.530 |
zik | -1.484 |
uni | -1.460 |
opian | -1.454 |
aunder | -1.358 |
Token | September |
Token ID | 2693 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
Toronto | +1.059 |
zik | +1.039 |
uni | +1.012 |
opian | +0.999 |
aunder | +0.960 |
Neg logit contributions | |
Lie | -0.843 |
parach | -0.774 |
Simulation | -0.764 |
itta | -0.724 |
Princ | -0.712 |
Token | 20 |
Token ID | 1160 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Toronto | +2.035 |
uni | +1.961 |
zik | +1.927 |
opian | +1.752 |
gyn | +1.526 |
Neg logit contributions | |
Lie | -6.767 |
parach | -6.578 |
actionGroup | -6.398 |
itta | -6.353 |
Simulation | -6.318 |
Token | the |
Token ID | 262 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Lie | +0.888 |
parach | +0.805 |
Simulation | +0.798 |
Chaff | +0.754 |
itta | +0.740 |
Neg logit contributions | |
zik | -1.238 |
Toronto | -1.234 |
uni | -1.204 |
opian | -1.200 |
aunder | -1.147 |
Token | future |
Token ID | 2003 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
Lie | +1.142 |
parach | +1.067 |
Simulation | +1.010 |
itta | +0.939 |
Chaff | +0.931 |
Neg logit contributions | |
zik | -2.005 |
Toronto | -1.992 |
uni | -1.934 |
opian | -1.898 |
aunder | -1.862 |
Token | of |
Token ID | 286 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Lie | +0.575 |
parach | +0.524 |
Simulation | +0.520 |
Chaff | +0.496 |
Curse | +0.482 |
Neg logit contributions | |
zik | -0.670 |
Toronto | -0.659 |
uni | -0.645 |
opian | -0.635 |
aunder | -0.609 |
Token | Cl |
Token ID | 1012 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
Lie | +1.036 |
parach | +0.924 |
Simulation | +0.917 |
Chaff | +0.886 |
Curse | +0.869 |
Neg logit contributions | |
Toronto | -1.440 |
zik | -1.433 |
opian | -1.415 |
uni | -1.406 |
aunder | -1.316 |
Token | arity |
Token ID | 6806 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
Toronto | +0.142 |
zik | +0.138 |
uni | +0.130 |
opian | +0.128 |
Azerbai | +0.118 |
Neg logit contributions | |
Lie | -0.227 |
parach | -0.216 |
itta | -0.213 |
Simulation | -0.212 |
itzer | -0.204 |
Token | Gaming |
Token ID | 14426 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Lie | +2.811 |
Simulation | +2.664 |
Curse | +2.374 |
parach | +2.308 |
Chaff | +2.297 |
Neg logit contributions | |
Toronto | -4.918 |
zik | -4.912 |
uni | -4.851 |
opian | -4.838 |
rall | -4.659 |
Token | Cl |
Token ID | 1012 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
Lie | +8.196 |
Curse | +7.421 |
parach | +7.345 |
Simulation | +7.302 |
Chaff | +7.089 |
Neg logit contributions | |
Toronto | -10.704 |
opian | -10.600 |
uni | -10.588 |
zik | -10.579 |
aunder | -9.701 |
Token | arity |
Token ID | 6806 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
Toronto | +0.137 |
zik | +0.134 |
uni | +0.126 |
opian | +0.124 |
rall | +0.116 |
Neg logit contributions | |
Lie | -0.219 |
parach | -0.208 |
itta | -0.207 |
Simulation | -0.206 |
Chaff | -0.197 |
Token | Gaming |
Token ID | 14426 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
Lie | +2.681 |
Simulation | +2.514 |
parach | +2.268 |
Curse | +2.267 |
Chaff | +2.162 |
Neg logit contributions | |
Toronto | -4.590 |
uni | -4.545 |
zik | -4.530 |
opian | -4.470 |
rall | -4.355 |
Token | will |
Token ID | 481 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Lie | +4.628 |
parach | +4.366 |
Simulation | +3.599 |
Chaff | +3.466 |
itta | +3.464 |
Neg logit contributions | |
uni | -9.628 |
opian | -9.582 |
rall | -9.576 |
zik | -9.537 |
Toronto | -9.528 |
Token | also |
Token ID | 635 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Toronto | +1.477 |
zik | +1.435 |
uni | +1.414 |
opian | +1.392 |
aunder | +1.327 |
Neg logit contributions | |
Lie | -1.277 |
parach | -1.194 |
Simulation | -1.149 |
itta | -1.112 |
Chaff | -1.083 |
Token | ology |
Token ID | 1435 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
Lie | +1.622 |
Simulation | +1.521 |
itta | +1.476 |
parach | +1.451 |
itzer | +1.407 |
Neg logit contributions | |
Toronto | -1.818 |
zik | -1.732 |
uni | -1.708 |
rall | -1.638 |
aunder | -1.616 |
Token | 62 |
Token ID | 8190 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Toronto | +0.146 |
zik | +0.143 |
uni | +0.138 |
opian | +0.136 |
gyn | +0.127 |
Neg logit contributions | |
Lie | -0.171 |
parach | -0.161 |
Simulation | -0.161 |
itta | -0.153 |
Princ | -0.151 |
Token | ( |
Token ID | 357 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
Lie | +2.212 |
parach | +2.038 |
Simulation | +2.031 |
itta | +1.936 |
Princ | +1.904 |
Neg logit contributions | |
Toronto | -2.651 |
zik | -2.627 |
uni | -2.585 |
opian | -2.507 |
aunder | -2.368 |
Token | 5 |
Token ID | 20 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
Lie | +4.741 |
Simulation | +4.400 |
parach | +4.226 |
itta | +4.174 |
Princ | +3.981 |
Neg logit contributions | |
zik | -5.891 |
Toronto | -5.702 |
opian | -5.632 |
uni | -5.616 |
conserve | -5.272 |
Token | ) |
Token ID | 8 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Lie | +5.118 |
parach | +4.821 |
Simulation | +4.814 |
itta | +4.701 |
Princ | +4.665 |
Neg logit contributions | |
zik | -2.432 |
Toronto | -2.335 |
uni | -2.278 |
opian | -2.204 |
gyn | -1.916 |
Token | 401 |
Token ID | 22219 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Lie | +5.112 |
Simulation | +4.693 |
parach | +4.644 |
Princ | +4.477 |
itta | +4.438 |
Neg logit contributions | |
Toronto | -4.309 |
zik | -4.291 |
uni | -4.159 |
opian | -4.088 |
gyn | -3.864 |
Token | - |
Token ID | 12 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
Lie | +7.931 |
Simulation | +7.403 |
itta | +6.702 |
Princ | +6.697 |
parach | +6.657 |
Neg logit contributions | |
Toronto | -10.369 |
zik | -10.313 |
uni | -10.151 |
opian | -9.919 |
gyn | -9.578 |
Token | 414 |
Token ID | 37309 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
Lie | +5.101 |
Simulation | +4.683 |
itta | +4.521 |
Princ | +4.397 |
parach | +4.342 |
Neg logit contributions | |
opian | -6.060 |
zik | -5.950 |
uni | -5.912 |
Toronto | -5.705 |
rall | -5.669 |
Token | ; |
Token ID | 26 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Lie | +5.932 |
Simulation | +5.632 |
parach | +5.148 |
itta | +5.101 |
Princ | +5.017 |
Neg logit contributions | |
Toronto | -7.844 |
zik | -7.658 |
opian | -7.599 |
uni | -7.535 |
gyn | -7.080 |
Token | doi |
Token ID | 23899 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Lie | +2.572 |
Simulation | +2.343 |
parach | +2.287 |
Princ | +2.186 |
itta | +2.176 |
Neg logit contributions | |
Toronto | -4.121 |
zik | -4.085 |
uni | -3.970 |
opian | -3.924 |
gyn | -3.766 |
Token | : |
Token ID | 25 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Lie | +5.026 |
Simulation | +4.389 |
@@ | +4.300 |
itta | +4.024 |
parach | +3.781 |
Neg logit contributions | |
zik | -11.225 |
opian | -11.085 |
rall | -10.900 |
uni | -10.494 |
Toronto | -10.494 |
Token | ibe |
Token ID | 32438 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Toronto | +2.659 |
zik | +2.558 |
uni | +2.496 |
opian | +2.450 |
aunder | +2.338 |
Neg logit contributions | |
Lie | -2.368 |
parach | -2.217 |
Simulation | -2.177 |
itta | -2.117 |
Chaff | -2.034 |
Token | products |
Token ID | 3186 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Toronto | +1.678 |
zik | +1.620 |
uni | +1.581 |
opian | +1.547 |
aunder | +1.457 |
Neg logit contributions | |
Lie | -1.983 |
parach | -1.876 |
Simulation | -1.845 |
itta | -1.780 |
Princ | -1.752 |
Token | . |
Token ID | 13 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
Toronto | +1.985 |
zik | +1.921 |
uni | +1.875 |
opian | +1.834 |
aunder | +1.729 |
Neg logit contributions | |
Lie | -2.198 |
parach | -2.076 |
Simulation | -2.035 |
itta | -1.967 |
Chaff | -1.932 |
Token | � |
Token ID | 447 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
Lie | +0.312 |
Simulation | +0.288 |
parach | +0.287 |
itta | +0.275 |
Princ | +0.274 |
Neg logit contributions | |
Toronto | -0.305 |
zik | -0.300 |
uni | -0.292 |
opian | -0.288 |
aunder | -0.271 |
Token | � |
Token ID | 251 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
Lie | +4.443 |
parach | +4.264 |
Simulation | +4.239 |
itta | +4.138 |
Chaff | +4.099 |
Neg logit contributions | |
Toronto | -1.277 |
zik | -1.184 |
uni | -1.126 |
opian | -1.072 |
aunder | -0.938 |
Token | [ |
Token ID | 58 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Lie | +2.145 |
Simulation | +1.963 |
parach | +1.955 |
Chaff | +1.893 |
itta | +1.883 |
Neg logit contributions | |
Toronto | -1.991 |
zik | -1.975 |
uni | -1.924 |
opian | -1.909 |
aunder | -1.788 |
Token | 7 |
Token ID | 22 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Lie | +6.634 |
Simulation | +5.745 |
@@ | +5.604 |
parach | +5.533 |
itta | +5.366 |
Neg logit contributions | |
Toronto | -11.463 |
zik | -11.229 |
opian | -11.226 |
aunder | -11.179 |
uni | -10.873 |
Token | ] |
Token ID | 60 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Lie | +1.907 |
Simulation | +1.758 |
parach | +1.739 |
Chaff | +1.699 |
itta | +1.693 |
Neg logit contributions | |
zik | -1.034 |
Toronto | -1.008 |
opian | -0.999 |
uni | -0.960 |
aunder | -0.875 |
Token | Because |
Token ID | 4362 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
Toronto | +1.648 |
zik | +1.593 |
uni | +1.558 |
opian | +1.524 |
aunder | +1.440 |
Neg logit contributions | |
Lie | -1.694 |
parach | -1.601 |
Simulation | -1.572 |
itta | -1.514 |
Chaff | -1.484 |
Token | Chevron |
Token ID | 50083 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Lie | +0.466 |
parach | +0.437 |
Simulation | +0.428 |
itta | +0.413 |
Chaff | +0.406 |
Neg logit contributions | |
Toronto | -0.467 |
zik | -0.454 |
uni | -0.444 |
opian | -0.435 |
aunder | -0.412 |
Token | and |
Token ID | 290 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
Lie | +2.017 |
parach | +1.903 |
Simulation | +1.843 |
itta | +1.789 |
Princ | +1.772 |
Neg logit contributions | |
Toronto | -1.629 |
zik | -1.591 |
uni | -1.532 |
opian | -1.527 |
aunder | -1.430 |
Token | gray |
Token ID | 12768 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
Toronto | +0.678 |
zik | +0.657 |
uni | +0.640 |
opian | +0.630 |
aunder | +0.593 |
Neg logit contributions | |
Lie | -0.663 |
parach | -0.626 |
Simulation | -0.597 |
Chaff | -0.580 |
itta | -0.580 |
Token | , |
Token ID | 837 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
Lie | +1.615 |
parach | +1.217 |
Simulation | +1.158 |
Chaff | +1.154 |
itta | +1.035 |
Neg logit contributions | |
rall | -5.935 |
zik | -5.806 |
Toronto | -5.802 |
uni | -5.769 |
opian | -5.761 |
Token | ( |
Token ID | 357 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Lie | +1.963 |
parach | +1.822 |
Simulation | +1.714 |
Chaff | +1.646 |
actionGroup | +1.637 |
Neg logit contributions | |
Toronto | -3.069 |
zik | -2.981 |
uni | -2.966 |
opian | -2.963 |
ridges | -2.780 |
Token | 3 |
Token ID | 513 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Lie | +1.163 |
parach | +1.087 |
Simulation | +1.052 |
Chaff | +1.026 |
actionGroup | +1.013 |
Neg logit contributions | |
Toronto | -1.088 |
zik | -1.055 |
uni | -1.046 |
opian | -1.037 |
gyn | -0.960 |
Token | , |
Token ID | 837 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Lie | +1.254 |
Simulation | +0.967 |
parach | +0.945 |
Chaff | +0.902 |
itta | +0.862 |
Neg logit contributions | |
zik | -3.783 |
rall | -3.761 |
Toronto | -3.735 |
uni | -3.706 |
opian | -3.690 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Toronto | +0.946 |
zik | +0.917 |
uni | +0.903 |
opian | +0.891 |
aunder | +0.830 |
Neg logit contributions | |
Lie | -1.129 |
parach | -1.052 |
Simulation | -1.032 |
Chaff | -0.993 |
itta | -0.983 |
Token | ) |
Token ID | 1267 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
Lie | +4.616 |
Simulation | +3.625 |
parach | +3.605 |
Princ | +3.220 |
Chaff | +3.150 |
Neg logit contributions | |
rall | -13.821 |
zik | -13.177 |
�� | -12.719 |
uckland | -12.673 |
opian | -12.611 |
Token | , |
Token ID | 837 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Lie | +3.107 |
parach | +2.573 |
Simulation | +2.554 |
Chaff | +2.215 |
Princ | +2.112 |
Neg logit contributions | |
rall | -9.064 |
zik | -8.884 |
Toronto | -8.769 |
uni | -8.692 |
opian | -8.666 |
Token | 0 |
Token ID | 657 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
Lie | +3.912 |
parach | +3.756 |
Simulation | +3.686 |
Chaff | +3.546 |
actionGroup | +3.515 |
Neg logit contributions | |
Toronto | -2.455 |
zik | -2.330 |
opian | -2.259 |
uni | -2.244 |
gyn | -2.129 |
Token | ) |
Token ID | 1267 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Lie | +4.311 |
Simulation | +3.478 |
Chaff | +3.307 |
parach | +3.212 |
itta | +3.096 |
Neg logit contributions | |
rall | -10.334 |
uckland | -9.674 |
opian | -9.658 |
zik | -9.644 |
Toronto | -9.400 |
Token | black |
Token ID | 2042 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
Lie | +2.628 |
parach | +2.451 |
Simulation | +2.288 |
actionGroup | +2.267 |
Chaff | +2.206 |
Neg logit contributions | |
Toronto | -4.383 |
zik | -4.272 |
uni | -4.186 |
opian | -4.094 |
gyn | -3.947 |
Token | 51 |
Token ID | 6885 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
Toronto | +1.538 |
zik | +1.499 |
uni | +1.453 |
opian | +1.426 |
aunder | +1.339 |
Neg logit contributions | |
Lie | -1.876 |
parach | -1.760 |
Simulation | -1.743 |
itta | -1.667 |
Chaff | -1.659 |
Token | ( |
Token ID | 7 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Lie | +0.111 |
parach | +0.107 |
Simulation | +0.105 |
itta | +0.102 |
Princ | +0.100 |
Neg logit contributions | |
Toronto | -0.076 |
zik | -0.073 |
uni | -0.071 |
opian | -0.068 |
aunder | -0.065 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Lie | +1.198 |
Simulation | +1.103 |
parach | +1.101 |
itta | +1.051 |
Princ | +1.037 |
Neg logit contributions | |
Toronto | -1.193 |
zik | -1.184 |
uni | -1.154 |
opian | -1.143 |
aunder | -1.069 |
Token | ), |
Token ID | 828 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
Lie | +1.514 |
parach | +1.438 |
Simulation | +1.418 |
itta | +1.369 |
Chaff | +1.347 |
Neg logit contributions | |
Toronto | -1.176 |
zik | -1.127 |
uni | -1.103 |
opian | -1.072 |
aunder | -1.009 |
Token | 306 |
Token ID | 37255 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Lie | +0.694 |
parach | +0.640 |
Simulation | +0.639 |
Chaff | +0.607 |
Princ | +0.606 |
Neg logit contributions | |
zik | -0.546 |
Toronto | -0.545 |
uni | -0.525 |
opian | -0.522 |
aunder | -0.482 |
Token | - |
Token ID | 532 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Lie | +8.037 |
Simulation | +7.456 |
parach | +7.193 |
Chaff | +6.909 |
itta | +6.889 |
Neg logit contributions | |
Toronto | -9.759 |
zik | -9.702 |
uni | -9.536 |
opian | -9.335 |
aunder | -8.949 |
Token | 327 |
Token ID | 36203 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
Lie | +7.213 |
Simulation | +5.937 |
Curse | +5.742 |
Chaff | +5.713 |
Princ | +5.605 |
Neg logit contributions | |
zik | -11.589 |
opian | -11.468 |
uni | -11.383 |
Toronto | -11.064 |
uckland | -10.676 |
Token | . |
Token ID | 764 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Lie | +3.251 |
Simulation | +2.625 |
Chaff | +2.487 |
Winchester | +2.168 |
Princ | +2.040 |
Neg logit contributions | |
zik | -10.417 |
rall | -10.367 |
opian | -10.344 |
uni | -10.253 |
enei | -10.020 |
Token |
|
Token ID | 198 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Lie | +1.494 |
parach | +1.445 |
Simulation | +1.404 |
itta | +1.366 |
Princ | +1.335 |
Neg logit contributions | |
Toronto | -1.281 |
zik | -1.221 |
uni | -1.205 |
opian | -1.169 |
aunder | -1.103 |
Token |
|
Token ID | 198 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
Lie | +1.727 |
Simulation | +1.489 |
parach | +1.433 |
Chaff | +1.404 |
itta | +1.385 |
Neg logit contributions | |
zik | -2.267 |
rall | -2.218 |
opian | -2.195 |
Toronto | -2.189 |
uni | -2.175 |
Token | Google |
Token ID | 11708 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
Toronto | +0.360 |
zik | +0.344 |
uni | +0.337 |
opian | +0.328 |
aunder | +0.308 |
Neg logit contributions | |
Lie | -0.439 |
parach | -0.419 |
Simulation | -0.411 |
itta | -0.397 |
Princ | -0.391 |
Token | Haitian |
Token ID | 48723 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Lie | +0.787 |
parach | +0.732 |
Simulation | +0.712 |
itta | +0.684 |
Princ | +0.681 |
Neg logit contributions | |
Toronto | -0.820 |
zik | -0.793 |
uni | -0.777 |
opian | -0.757 |
aunder | -0.727 |
Token | population |
Token ID | 3265 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Lie | +2.138 |
parach | +1.991 |
Simulation | +1.915 |
Princ | +1.863 |
itta | +1.859 |
Neg logit contributions | |
Toronto | -2.294 |
zik | -2.191 |
uni | -2.149 |
opian | -2.088 |
aunder | -2.040 |
Token | . |
Token ID | 13 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
Toronto | +1.729 |
zik | +1.667 |
uni | +1.628 |
opian | +1.589 |
aunder | +1.488 |
Neg logit contributions | |
Lie | -2.193 |
parach | -2.080 |
Simulation | -2.051 |
itta | -1.981 |
Princ | -1.948 |
Token | � |
Token ID | 447 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Toronto | +0.411 |
zik | +0.401 |
uni | +0.391 |
opian | +0.384 |
aunder | +0.362 |
Neg logit contributions | |
Lie | -0.435 |
parach | -0.405 |
Simulation | -0.402 |
itta | -0.386 |
Princ | -0.382 |
Token | � |
Token ID | 251 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Lie | +5.507 |
parach | +5.284 |
Simulation | +5.266 |
itta | +5.141 |
Chaff | +5.097 |
Neg logit contributions | |
Toronto | -1.584 |
zik | -1.458 |
uni | -1.390 |
opian | -1.320 |
aunder | -1.176 |
Token | [ |
Token ID | 58 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Lie | +1.765 |
parach | +1.624 |
Simulation | +1.622 |
itta | +1.560 |
Chaff | +1.557 |
Neg logit contributions | |
Toronto | -1.603 |
zik | -1.578 |
uni | -1.536 |
opian | -1.517 |
aunder | -1.428 |
Token | 8 |
Token ID | 23 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Lie | +5.377 |
@@ | +4.944 |
Lie | +4.563 |
Simulation | +4.108 |
Curse | +3.924 |
Neg logit contributions | |
zik | -12.376 |
rall | -12.267 |
conserve | -11.845 |
�� | -11.760 |
�� | -11.755 |
Token | ] |
Token ID | 60 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Lie | +2.852 |
Simulation | +2.609 |
parach | +2.566 |
Chaff | +2.524 |
Princ | +2.510 |
Neg logit contributions | |
zik | -1.630 |
Toronto | -1.594 |
opian | -1.570 |
uni | -1.537 |
uckland | -1.421 |
Token | Chevron |
Token ID | 50083 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Toronto | +1.245 |
zik | +1.206 |
uni | +1.179 |
opian | +1.154 |
aunder | +1.090 |
Neg logit contributions | |
Lie | -1.306 |
parach | -1.230 |
Simulation | -1.211 |
itta | -1.166 |
Princ | -1.146 |
Token | eventually |
Token ID | 4191 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Lie | +0.960 |
parach | +0.904 |
Simulation | +0.878 |
itta | +0.850 |
Princ | +0.841 |
Neg logit contributions | |
Toronto | -0.833 |
zik | -0.809 |
uni | -0.790 |
opian | -0.779 |
aunder | -0.732 |
Token | signed |
Token ID | 4488 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
Toronto | +1.368 |
zik | +1.320 |
uni | +1.289 |
opian | +1.265 |
aunder | +1.180 |
Neg logit contributions | |
Lie | -1.735 |
parach | -1.655 |
Simulation | -1.607 |
itta | -1.559 |
Chaff | -1.532 |
Token | for |
Token ID | 329 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
Lie | +1.354 |
parach | +1.243 |
Simulation | +1.193 |
Chaff | +1.128 |
Princ | +1.117 |
Neg logit contributions | |
zik | -1.722 |
Toronto | -1.716 |
uni | -1.657 |
opian | -1.620 |
aunder | -1.558 |
Token | modern |
Token ID | 3660 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
Lie | +3.926 |
parach | +3.734 |
Simulation | +3.559 |
Princ | +3.285 |
@@ | +3.154 |
Neg logit contributions | |
zik | -5.250 |
Toronto | -5.173 |
uni | -5.060 |
ridges | -4.808 |
�� | -4.750 |
Token | web |
Token ID | 3992 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Lie | +3.792 |
parach | +3.212 |
Simulation | +2.688 |
Chaff | +2.438 |
Curse | +2.428 |
Neg logit contributions | |
zik | -12.006 |
Toronto | -11.608 |
uni | -11.429 |
ridges | -11.179 |
rall | -11.150 |
Token | applications |
Token ID | 5479 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
Lie | +2.100 |
parach | +1.986 |
Simulation | +1.951 |
Princ | +1.846 |
Chaff | +1.783 |
Neg logit contributions | |
Toronto | -2.451 |
zik | -2.440 |
uni | -2.342 |
opian | -2.255 |
aunder | -2.214 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Lie | +0.153 |
Simulation | +0.141 |
parach | +0.139 |
itta | +0.133 |
Chaff | +0.131 |
Neg logit contributions | |
Toronto | -0.167 |
zik | -0.164 |
uni | -0.160 |
opian | -0.158 |
aunder | -0.148 |
Token | But |
Token ID | 887 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Toronto | +1.476 |
zik | +1.410 |
uni | +1.355 |
opian | +1.295 |
gyn | +1.223 |
Neg logit contributions | |
Lie | -2.090 |
parach | -2.071 |
itta | -1.944 |
Simulation | -1.925 |
actionGroup | -1.903 |
Token | as |
Token ID | 355 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Lie | +5.773 |
parach | +5.168 |
Simulation | +4.983 |
Chaff | +4.469 |
itta | +4.099 |
Neg logit contributions | |
rall | -11.945 |
Toronto | -11.872 |
uni | -11.561 |
ngth | -11.526 |
uckland | -11.365 |
Token | with |
Token ID | 351 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
Lie | +2.986 |
parach | +2.616 |
Simulation | +2.585 |
Chaff | +2.363 |
Princ | +2.335 |
Neg logit contributions | |
Toronto | -3.988 |
zik | -3.941 |
uni | -3.900 |
opian | -3.894 |
rall | -3.743 |
Token | every |
Token ID | 790 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
Lie | +2.813 |
parach | +2.641 |
Simulation | +2.453 |
Princ | +2.174 |
Curse | +2.169 |
Neg logit contributions | |
Toronto | -5.199 |
zik | -5.073 |
uni | -4.925 |
opian | -4.791 |
aunder | -4.699 |
Token | new |
Token ID | 649 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
Lie | +0.516 |
parach | +0.482 |
Simulation | +0.457 |
Chaff | +0.434 |
itta | +0.433 |
Neg logit contributions | |
Toronto | -0.611 |
zik | -0.602 |
opian | -0.582 |
uni | -0.580 |
aunder | -0.559 |
Token | toy |
Token ID | 13373 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Toronto | +4.939 |
zik | +4.781 |
uni | +4.673 |
opian | +4.541 |
aunder | +4.195 |
Neg logit contributions | |
Lie | -6.201 |
parach | -5.867 |
Simulation | -5.794 |
itta | -5.616 |
Princ | -5.559 |
Token | 2006 |
Token ID | 4793 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Toronto | +0.161 |
zik | +0.157 |
uni | +0.153 |
opian | +0.150 |
aunder | +0.140 |
Neg logit contributions | |
Lie | -0.192 |
parach | -0.179 |
Simulation | -0.178 |
itta | -0.171 |
Princ | -0.168 |
Token | 18 |
Token ID | 1248 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
Toronto | +2.997 |
zik | +2.864 |
uni | +2.796 |
opian | +2.717 |
aunder | +2.548 |
Neg logit contributions | |
Lie | -3.794 |
parach | -3.631 |
Simulation | -3.553 |
itta | -3.458 |
Chaff | -3.382 |
Token | 9 |
Token ID | 860 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
Toronto | +2.540 |
zik | +2.441 |
uni | +2.378 |
opian | +2.317 |
aunder | +2.167 |
Neg logit contributions | |
Lie | -3.446 |
parach | -3.280 |
Simulation | -3.226 |
itta | -3.126 |
Chaff | -3.074 |
Token | 2007 |
Token ID | 4343 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
Lie | +4.909 |
Simulation | +4.433 |
parach | +4.376 |
itta | +4.202 |
Chaff | +4.078 |
Neg logit contributions | |
Toronto | -6.371 |
zik | -6.096 |
opian | -6.047 |
uni | -6.036 |
aunder | -5.782 |
Token | 6 |
Token ID | 718 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Toronto | +3.675 |
zik | +3.461 |
uni | +3.381 |
opian | +3.257 |
aunder | +3.036 |
Neg logit contributions | |
Lie | -5.480 |
parach | -5.290 |
Simulation | -5.174 |
itta | -5.057 |
actionGroup | -4.979 |
Token | 0 |
Token ID | 657 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Toronto | +1.680 |
zik | +1.633 |
uni | +1.592 |
opian | +1.563 |
aunder | +1.459 |
Neg logit contributions | |
Lie | -2.108 |
parach | -1.980 |
Simulation | -1.965 |
itta | -1.887 |
Princ | -1.864 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
Lie | +6.953 |
Simulation | +6.132 |
parach | +5.833 |
Curse | +5.577 |
itta | +5.459 |
Neg logit contributions | |
Toronto | -11.510 |
zik | -11.370 |
opian | -11.012 |
uni | -10.924 |
aunder | -10.496 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Toronto | +3.244 |
zik | +3.104 |
uni | +3.029 |
opian | +2.945 |
aunder | +2.764 |
Neg logit contributions | |
Lie | -4.090 |
parach | -3.916 |
Simulation | -3.833 |
itta | -3.725 |
Chaff | -3.645 |
Token | 4 |
Token ID | 604 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
Toronto | +1.635 |
zik | +1.587 |
uni | +1.546 |
opian | +1.517 |
aunder | +1.418 |
Neg logit contributions | |
Lie | -2.099 |
parach | -1.974 |
Simulation | -1.959 |
itta | -1.881 |
Princ | -1.860 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Lie | +3.238 |
parach | +2.996 |
Simulation | +2.965 |
itta | +2.829 |
Princ | +2.779 |
Neg logit contributions | |
Toronto | -3.524 |
zik | -3.429 |
uni | -3.351 |
opian | -3.291 |
aunder | -3.125 |
Token | 10 |
Token ID | 838 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
Toronto | +3.731 |
zik | +3.546 |
uni | +3.466 |
opian | +3.356 |
aunder | +3.141 |
Neg logit contributions | |
Lie | -4.921 |
parach | -4.731 |
Simulation | -4.628 |
itta | -4.512 |
actionGroup | -4.425 |
Token | ( |
Token ID | 7 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
Lie | +2.410 |
parach | +2.296 |
Simulation | +2.254 |
itta | +2.180 |
Chaff | +2.138 |
Neg logit contributions | |
Toronto | -1.993 |
zik | -1.914 |
uni | -1.870 |
opian | -1.821 |
aunder | -1.717 |
Token | 10 |
Token ID | 940 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
Lie | +4.212 |
Simulation | +3.871 |
parach | +3.765 |
itta | +3.667 |
Princ | +3.582 |
Neg logit contributions | |
zik | -4.702 |
Toronto | -4.663 |
opian | -4.583 |
uni | -4.567 |
aunder | -4.266 |
Token | ), |
Token ID | 828 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
Lie | +6.701 |
Simulation | +6.111 |
parach | +6.093 |
Princ | +5.885 |
itta | +5.873 |
Neg logit contributions | |
zik | -6.764 |
Toronto | -6.687 |
opian | -6.506 |
uni | -6.419 |
aunder | -5.972 |
Token | 1 |
Token ID | 352 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
Lie | +4.727 |
Simulation | +4.344 |
Princ | +4.114 |
parach | +4.067 |
Chaff | +3.993 |
Neg logit contributions | |
zik | -4.450 |
Toronto | -4.349 |
opian | -4.321 |
uni | -4.303 |
gyn | -4.013 |
Token | - |
Token ID | 532 |
Feature activation | +6.73e-03 |
Pos logit contributions | |
Lie | +4.261 |
Simulation | +3.834 |
parach | +3.736 |
itta | +3.595 |
Chaff | +3.578 |
Neg logit contributions | |
zik | -5.161 |
Toronto | -5.005 |
uni | -4.997 |
opian | -4.988 |
aunder | -4.678 |
Token | 13 |
Token ID | 1511 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Lie | +0.060 |
Simulation | +0.056 |
parach | +0.055 |
Princ | +0.053 |
Chaff | +0.053 |
Neg logit contributions | |
Toronto | -0.049 |
zik | -0.049 |
uni | -0.047 |
opian | -0.047 |
aunder | -0.044 |
Token | . |
Token ID | 764 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
Lie | +3.856 |
Simulation | +3.159 |
Chaff | +2.829 |
Princ | +2.307 |
Winchester | +2.161 |
Neg logit contributions | |
rall | -14.378 |
opian | -13.992 |
zik | -13.908 |
enei | -13.619 |
uckland | -13.515 |
Token |
|
Token ID | 198 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
Lie | +3.122 |
Simulation | +2.820 |
parach | +2.676 |
Chaff | +2.640 |
itta | +2.598 |
Neg logit contributions | |
zik | -3.631 |
Toronto | -3.601 |
uni | -3.529 |
opian | -3.527 |
conserve | -3.334 |
Token |
|
Token ID | 198 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
Lie | +2.542 |
Simulation | +2.178 |
parach | +2.091 |
Chaff | +2.028 |
itta | +2.019 |
Neg logit contributions | |
rall | -3.614 |
zik | -3.564 |
opian | -3.468 |
Toronto | -3.444 |
uni | -3.435 |
Token | Google |
Token ID | 11708 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Lie | +4.433 |
Lie | +4.015 |
Simulation | +4.010 |
@@ | +3.881 |
JUST | +3.827 |
Neg logit contributions | |
zik | -4.004 |
opian | -3.739 |
uni | -3.655 |
fitt | -3.566 |
rall | -3.547 |
Token | Scholar |
Token ID | 11713 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
Lie | +1.639 |
Simulation | +0.937 |
Chaff | +0.448 |
Scholar | +0.160 |
Curse | -0.027 |
Neg logit contributions | |
rall | -15.726 |
zik | -15.333 |
opian | -15.233 |
uckland | -15.194 |
Toronto | -15.139 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
Lie | +1.938 |
Simulation | +1.728 |
parach | +1.670 |
Princ | +1.651 |
Curse | +1.639 |
Neg logit contributions | |
zik | -1.754 |
Toronto | -1.754 |
opian | -1.715 |
uni | -1.713 |
aunder | -1.598 |
Token | United |
Token ID | 1578 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
Lie | +4.536 |
Simulation | +3.964 |
parach | +3.927 |
Princ | +3.916 |
Chaff | +3.804 |
Neg logit contributions | |
zik | -3.986 |
opian | -3.880 |
Toronto | -3.840 |
uni | -3.838 |
aunder | -3.605 |
Token | States |
Token ID | 1829 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Lie | +3.114 |
parach | +2.778 |
Simulation | +2.737 |
itta | +2.543 |
Princ | +2.492 |
Neg logit contributions | |
Toronto | -6.341 |
zik | -6.197 |
uni | -6.080 |
opian | -6.018 |
aunder | -5.784 |
Token | 10 |
Token ID | 838 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
Lie | +4.332 |
Simulation | +3.933 |
parach | +3.812 |
Princ | +3.767 |
Chaff | +3.683 |
Neg logit contributions | |
zik | -3.976 |
opian | -3.859 |
Toronto | -3.829 |
uni | -3.812 |
aunder | -3.560 |
Token | 53 |
Token ID | 4310 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Lie | +3.630 |
Simulation | +3.211 |
parach | +3.057 |
Princ | +3.046 |
Curse | +2.999 |
Neg logit contributions | |
zik | -4.348 |
uni | -4.265 |
Toronto | -4.223 |
opian | -4.218 |
aunder | -3.939 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Lie | +1.131 |
Simulation | +1.019 |
parach | +0.927 |
Princ | +0.909 |
Curse | +0.898 |
Neg logit contributions | |
zik | -1.864 |
opian | -1.856 |
Toronto | -1.851 |
uni | -1.835 |
aunder | -1.713 |
Token | # |
Token ID | 1303 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
Lie | +7.533 |
Simulation | +6.726 |
parach | +6.464 |
itta | +6.236 |
Curse | +6.220 |
Neg logit contributions | |
Toronto | -10.736 |
opian | -10.422 |
zik | -10.394 |
uni | -10.201 |
aunder | -9.731 |
Token | 15 |
Token ID | 1314 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
zik | +0.059 |
Toronto | +0.058 |
opian | +0.058 |
uni | +0.057 |
rall | +0.056 |
Neg logit contributions | |
Lie | -0.042 |
parach | -0.039 |
Simulation | -0.038 |
itta | -0.036 |
@@ | -0.035 |
Token | honestly |
Token ID | 12698 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
Lie | +1.716 |
parach | +1.590 |
Simulation | +1.569 |
Chaff | +1.499 |
itta | +1.492 |
Neg logit contributions | |
Toronto | -1.718 |
zik | -1.667 |
uni | -1.641 |
opian | -1.630 |
aunder | -1.523 |
Token | if |
Token ID | 611 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Toronto | +0.341 |
zik | +0.328 |
uni | +0.321 |
opian | +0.314 |
aunder | +0.297 |
Neg logit contributions | |
Lie | -0.393 |
parach | -0.370 |
Simulation | -0.364 |
itta | -0.349 |
Chaff | -0.347 |
Token | we |
Token ID | 356 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
Toronto | +1.712 |
zik | +1.657 |
uni | +1.617 |
opian | +1.579 |
aunder | +1.489 |
Neg logit contributions | |
Lie | -1.930 |
parach | -1.825 |
Simulation | -1.797 |
itta | -1.735 |
Princ | -1.702 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Lie | +1.502 |
Simulation | +1.347 |
Princ | +1.211 |
Curse | +1.205 |
parach | +1.196 |
Neg logit contributions | |
zik | -2.483 |
opian | -2.476 |
uni | -2.445 |
Toronto | -2.427 |
conserve | -2.269 |
Token | Last |
Token ID | 4586 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
Lie | +7.505 |
Simulation | +6.731 |
parach | +6.512 |
itta | +6.237 |
Curse | +6.187 |
Neg logit contributions | |
Toronto | -10.356 |
zik | -10.068 |
opian | -9.957 |
uni | -9.841 |
aunder | -9.350 |
Token | Edited |
Token ID | 34212 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
Lie | +3.183 |
Simulation | +2.891 |
itta | +2.675 |
Curse | +2.637 |
parach | +2.636 |
Neg logit contributions | |
opian | -4.554 |
Toronto | -4.549 |
uni | -4.480 |
zik | -4.456 |
aunder | -4.379 |
Token | : |
Token ID | 25 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
Lie | +2.541 |
Simulation | +2.177 |
parach | +2.070 |
Curse | +2.026 |
@@ | +1.995 |
Neg logit contributions | |
zik | -3.778 |
opian | -3.777 |
Toronto | -3.756 |
uni | -3.746 |
rall | -3.673 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
Lie | +0.106 |
Simulation | +0.097 |
parach | +0.097 |
Chaff | +0.093 |
Princ | +0.093 |
Neg logit contributions | |
zik | -0.076 |
Toronto | -0.074 |
uni | -0.073 |
opian | -0.071 |
aunder | -0.067 |
Token | - |
Token ID | 12 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Lie | +2.988 |
Simulation | +2.663 |
parach | +2.548 |
Chaff | +2.476 |
Princ | +2.386 |
Neg logit contributions | |
zik | -4.661 |
opian | -4.542 |
Toronto | -4.460 |
uni | -4.442 |
rall | -4.334 |
Token | 09 |
Token ID | 2931 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
Lie | +3.099 |
@@ | +2.213 |
Lie | +2.134 |
JUST | +2.104 |
itta | +1.465 |
Neg logit contributions | |
rall | -15.001 |
ngth | -14.717 |
zik | -14.520 |
opian | -14.455 |
brut | -14.142 |
Token | - |
Token ID | 12 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Lie | +4.086 |
Simulation | +3.316 |
@@ | +3.254 |
parach | +3.136 |
Lie | +3.038 |
Neg logit contributions | |
rall | -8.416 |
ngth | -7.926 |
zik | -7.900 |
uckland | -7.771 |
�� | -7.729 |
Token | 20 |
Token ID | 1238 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Lie | +1.758 |
Simulation | +1.545 |
@@ | +1.488 |
parach | +1.487 |
Lie | +1.481 |
Neg logit contributions | |
zik | -2.553 |
opian | -2.489 |
rall | -2.449 |
uni | -2.412 |
aunder | -2.382 |
Token | 01 |
Token ID | 5534 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
Lie | +4.624 |
Simulation | +4.206 |
Princ | +3.932 |
Curse | +3.925 |
Chaff | +3.884 |
Neg logit contributions | |
opian | -4.841 |
zik | -4.778 |
ngth | -4.619 |
uni | -4.592 |
aunder | -4.574 |
Token | : |
Token ID | 25 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Lie | +3.226 |
Simulation | +2.712 |
@@ | +2.572 |
parach | +2.521 |
Chaff | +2.439 |
Neg logit contributions | |
rall | -5.873 |
opian | -5.630 |
ngth | -5.574 |
zik | -5.566 |
aunder | -5.513 |
Token | , |
Token ID | 11 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Toronto | +0.432 |
uni | +0.405 |
zik | +0.402 |
opian | +0.389 |
gyn | +0.363 |
Neg logit contributions | |
Lie | -0.638 |
parach | -0.623 |
Simulation | -0.595 |
itta | -0.586 |
actionGroup | -0.583 |
Token | 35 |
Token ID | 3439 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
Lie | +2.884 |
Simulation | +2.664 |
parach | +2.524 |
Chaff | +2.497 |
Princ | +2.494 |
Neg logit contributions | |
zik | -2.405 |
opian | -2.344 |
Toronto | -2.318 |
uni | -2.313 |
aunder | -2.163 |
Token | , |
Token ID | 11 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
Lie | +0.667 |
Simulation | +0.599 |
parach | +0.593 |
itta | +0.572 |
Chaff | +0.571 |
Neg logit contributions | |
zik | -0.644 |
Toronto | -0.635 |
opian | -0.631 |
uni | -0.625 |
conserve | -0.582 |
Token | 100 |
Token ID | 1802 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
Lie | +5.828 |
Simulation | +5.238 |
parach | +5.040 |
Princ | +5.023 |
Chaff | +4.926 |
Neg logit contributions | |
zik | -5.562 |
Toronto | -5.501 |
opian | -5.411 |
uni | -5.376 |
aunder | -5.014 |
Token | 9 |
Token ID | 24 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Lie | +5.975 |
Simulation | +5.522 |
parach | +5.345 |
itta | +5.093 |
Princ | +5.057 |
Neg logit contributions | |
Toronto | -6.818 |
zik | -6.801 |
uni | -6.616 |
opian | -6.557 |
aunder | -6.212 |
Token | - |
Token ID | 532 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Lie | +5.540 |
Simulation | +4.818 |
Chaff | +4.315 |
Curse | +4.120 |
Princ | +3.887 |
Neg logit contributions | |
rall | -11.647 |
zik | -11.323 |
ngth | -11.049 |
uckland | -10.869 |
opian | -10.854 |
Token | 101 |
Token ID | 8949 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
Lie | +6.475 |
Princ | +5.807 |
Simulation | +5.412 |
Chaff | +5.191 |
Winchester | +5.149 |
Neg logit contributions | |
zik | -11.173 |
opian | -11.104 |
Toronto | -10.696 |
etooth | -10.618 |
aunder | -10.575 |
Token | 9 |
Token ID | 24 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
Toronto | +0.529 |
zik | +0.518 |
uni | +0.505 |
opian | +0.505 |
aunder | +0.476 |
Neg logit contributions | |
Lie | -0.528 |
Simulation | -0.492 |
parach | -0.482 |
itta | -0.464 |
Chaff | -0.457 |
Token | . |
Token ID | 764 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
Lie | +3.206 |
Simulation | +2.526 |
Chaff | +2.245 |
itta | +1.916 |
@@ | +1.822 |
Neg logit contributions | |
rall | -12.514 |
zik | -11.878 |
opian | -11.640 |
uckland | -11.579 |
ngth | -11.482 |
Token |
|
Token ID | 198 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Lie | +3.590 |
Simulation | +3.087 |
parach | +2.859 |
Chaff | +2.837 |
itta | +2.819 |
Neg logit contributions | |
rall | -5.573 |
zik | -5.344 |
opian | -5.273 |
uckland | -5.202 |
uni | -5.183 |
Token |
|
Token ID | 198 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
Lie | +1.781 |
Simulation | +1.551 |
parach | +1.515 |
itta | +1.453 |
Chaff | +1.446 |
Neg logit contributions | |
zik | -2.336 |
rall | -2.308 |
Toronto | -2.282 |
opian | -2.266 |
uni | -2.255 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Toronto | +0.098 |
zik | +0.095 |
uni | +0.093 |
opian | +0.092 |
aunder | +0.088 |
Neg logit contributions | |
Lie | -0.084 |
parach | -0.077 |
Simulation | -0.076 |
itta | -0.073 |
Chaff | -0.072 |
Token | { |
Token ID | 1391 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
Toronto | +1.839 |
zik | +1.797 |
uni | +1.761 |
opian | +1.755 |
aunder | +1.655 |
Neg logit contributions | |
Lie | -1.395 |
Simulation | -1.276 |
parach | -1.265 |
itta | -1.183 |
Princ | -1.171 |
Token | ( |
Token ID | 7 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Lie | +0.117 |
Simulation | +0.106 |
parach | +0.103 |
itta | +0.099 |
@@ | +0.099 |
Neg logit contributions | |
zik | -0.156 |
Toronto | -0.152 |
opian | -0.152 |
uni | -0.150 |
rall | -0.145 |
Token | 4 |
Token ID | 19 |
Feature activation | +9.70e-03 |
Pos logit contributions | |
Toronto | +2.321 |
zik | +2.262 |
uni | +2.210 |
opian | +2.175 |
aunder | +2.053 |
Neg logit contributions | |
Lie | -2.158 |
parach | -2.011 |
Simulation | -1.990 |
itta | -1.907 |
Chaff | -1.872 |
Token | s |
Token ID | 82 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Lie | +0.078 |
parach | +0.074 |
Simulation | +0.072 |
itta | +0.071 |
Chaff | +0.069 |
Neg logit contributions | |
Toronto | -0.077 |
zik | -0.074 |
uni | -0.073 |
opian | -0.070 |
aunder | -0.067 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Lie | +0.855 |
Simulation | +0.764 |
parach | +0.762 |
itta | +0.742 |
Princ | +0.719 |
Neg logit contributions | |
Toronto | -0.969 |
zik | -0.963 |
opian | -0.926 |
uni | -0.920 |
gyn | -0.875 |
Token | 60 |
Token ID | 3126 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
zik | +4.568 |
Toronto | +4.179 |
uni | +4.123 |
ities | +3.692 |
opian | +3.636 |
Neg logit contributions | |
aukee | -16.135 |
Lie | -16.035 |
parach | -15.808 |
itta | -15.713 |
actionGroup | -15.634 |
Token | . |
Token ID | 13 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Lie | +0.742 |
Simulation | +0.662 |
parach | +0.644 |
itta | +0.614 |
Chaff | +0.614 |
Neg logit contributions | |
zik | -0.848 |
Toronto | -0.840 |
opian | -0.828 |
uni | -0.822 |
rall | -0.796 |
Token | e |
Token ID | 304 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Toronto | +2.044 |
zik | +1.976 |
uni | +1.935 |
opian | +1.894 |
aunder | +1.783 |
Neg logit contributions | |
Lie | -2.236 |
parach | -2.104 |
Simulation | -2.072 |
itta | -1.990 |
Princ | -1.962 |
Token | 7 |
Token ID | 22 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Toronto | +1.517 |
zik | +1.464 |
uni | +1.438 |
opian | +1.407 |
aunder | +1.337 |
Neg logit contributions | |
Lie | -1.516 |
parach | -1.418 |
Simulation | -1.396 |
itta | -1.349 |
Chaff | -1.319 |
Token | { |
Token ID | 1391 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
Toronto | +2.265 |
zik | +2.197 |
uni | +2.145 |
opian | +2.099 |
aunder | +1.995 |
Neg logit contributions | |
Lie | -2.102 |
parach | -1.988 |
Simulation | -1.947 |
itta | -1.879 |
Chaff | -1.841 |
Token | 5 |
Token ID | 20 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Toronto | +3.614 |
zik | +3.500 |
uni | +3.423 |
opian | +3.351 |
aunder | +3.166 |
Neg logit contributions | |
Lie | -3.678 |
parach | -3.467 |
Simulation | -3.409 |
itta | -3.279 |
Princ | -3.220 |
Token | { |
Token ID | 1391 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
Toronto | +1.596 |
zik | +1.563 |
uni | +1.528 |
opian | +1.519 |
aunder | +1.439 |
Neg logit contributions | |
Lie | -1.227 |
Simulation | -1.123 |
parach | -1.108 |
itta | -1.034 |
Chaff | -1.029 |
Token | ( |
Token ID | 7 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
Lie | +0.183 |
Simulation | +0.166 |
parach | +0.161 |
itta | +0.155 |
@@ | +0.154 |
Neg logit contributions | |
zik | -0.245 |
Toronto | -0.240 |
opian | -0.239 |
uni | -0.236 |
rall | -0.228 |
Token | 4 |
Token ID | 19 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Toronto | +2.817 |
zik | +2.731 |
uni | +2.674 |
opian | +2.620 |
aunder | +2.481 |
Neg logit contributions | |
Lie | -2.654 |
parach | -2.496 |
Simulation | -2.453 |
itta | -2.355 |
Princ | -2.311 |
Token | s |
Token ID | 82 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
Lie | +1.380 |
parach | +1.293 |
Simulation | +1.273 |
itta | +1.213 |
Chaff | +1.196 |
Neg logit contributions | |
Toronto | -1.536 |
zik | -1.492 |
uni | -1.459 |
opian | -1.435 |
aunder | -1.357 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Lie | +0.139 |
Simulation | +0.126 |
parach | +0.125 |
itta | +0.122 |
Princ | +0.118 |
Neg logit contributions | |
Toronto | -0.153 |
zik | -0.151 |
opian | -0.145 |
uni | -0.145 |
gyn | -0.137 |
Token | 30 |
Token ID | 1542 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
zik | +4.985 |
Toronto | +4.514 |
uni | +4.257 |
Sergey | +4.017 |
ities | +3.958 |
Neg logit contributions | |
Lie | -14.940 |
itta | -14.899 |
parach | -14.681 |
actionGroup | -14.668 |
itzer | -14.619 |
Token | . |
Token ID | 13 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Lie | +1.311 |
Simulation | +1.169 |
parach | +1.125 |
Chaff | +1.084 |
itta | +1.080 |
Neg logit contributions | |
zik | -1.548 |
Toronto | -1.526 |
opian | -1.518 |
uni | -1.497 |
rall | -1.460 |
Token | K |
Token ID | 509 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
Toronto | +2.138 |
zik | +2.068 |
uni | +2.022 |
opian | +1.979 |
aunder | +1.866 |
Neg logit contributions | |
Lie | -2.290 |
parach | -2.160 |
Simulation | -2.126 |
itta | -2.045 |
Princ | -2.011 |
Token | f |
Token ID | 69 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
Toronto | +2.803 |
zik | +2.708 |
uni | +2.644 |
opian | +2.585 |
aunder | +2.432 |
Neg logit contributions | |
Lie | -3.204 |
parach | -3.033 |
Simulation | -2.985 |
itta | -2.876 |
Princ | -2.831 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
Toronto | +3.097 |
zik | +2.993 |
uni | +2.924 |
opian | +2.862 |
aunder | +2.694 |
Neg logit contributions | |
Lie | -3.515 |
parach | -3.320 |
Simulation | -3.267 |
itta | -3.151 |
Chaff | -3.097 |
Token | s |
Token ID | 264 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Toronto | +1.587 |
zik | +1.529 |
uni | +1.505 |
opian | +1.404 |
aunder | +1.379 |
Neg logit contributions | |
Lie | -1.733 |
parach | -1.654 |
Simulation | -1.618 |
itta | -1.610 |
Chaff | -1.578 |
Token | . |
Token ID | 13 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
Toronto | +1.217 |
zik | +1.199 |
uni | +1.164 |
opian | +1.156 |
aunder | +1.083 |
Neg logit contributions | |
Lie | -1.249 |
parach | -1.155 |
Simulation | -1.147 |
itta | -1.104 |
Chaff | -1.078 |
Token | t |
Token ID | 83 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
Toronto | +3.547 |
zik | +3.428 |
uni | +3.355 |
opian | +3.277 |
aunder | +3.094 |
Neg logit contributions | |
Lie | -3.734 |
parach | -3.528 |
Simulation | -3.468 |
itta | -3.336 |
Princ | -3.282 |
Token | . |
Token ID | 13 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
Toronto | +0.158 |
zik | +0.158 |
opian | +0.153 |
uni | +0.152 |
aunder | +0.143 |
Neg logit contributions | |
Lie | -0.153 |
Simulation | -0.140 |
parach | -0.138 |
itta | -0.133 |
Chaff | -0.131 |
Token | A |
Token ID | 317 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Lie | +3.987 |
Simulation | +3.646 |
parach | +3.600 |
Princ | +3.512 |
Chaff | +3.399 |
Neg logit contributions | |
Toronto | -3.955 |
zik | -3.929 |
opian | -3.804 |
uni | -3.736 |
gyn | -3.550 |
Token | US |
Token ID | 2937 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Lie | +3.793 |
Simulation | +3.361 |
parach | +3.275 |
@@ | +3.262 |
Lie | +3.259 |
Neg logit contributions | |
opian | -3.999 |
zik | -3.947 |
rall | -3.902 |
Toronto | -3.723 |
aunder | -3.680 |
Token | 20 |
Token ID | 1160 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Toronto | +4.501 |
uni | +4.455 |
zik | +4.375 |
opian | +3.830 |
ART | +3.619 |
Neg logit contributions | |
actionGroup | -14.678 |
Lie | -14.556 |
Chaff | -14.387 |
itta | -14.279 |
itzer | -14.266 |
Token | Simon |
Token ID | 11288 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Lie | +2.245 |
Simulation | +2.042 |
parach | +2.040 |
Princ | +1.951 |
Chaff | +1.930 |
Neg logit contributions | |
Toronto | -1.858 |
zik | -1.821 |
uni | -1.770 |
opian | -1.750 |
aunder | -1.652 |
Token | Gerr |
Token ID | 45140 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
Toronto | +3.039 |
zik | +2.956 |
uni | +2.897 |
opian | +2.832 |
aunder | +2.686 |
Neg logit contributions | |
Lie | -2.344 |
parach | -2.217 |
Simulation | -2.172 |
itta | -2.086 |
actionGroup | -2.031 |
Token | ans |
Token ID | 504 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
Lie | +0.701 |
Simulation | +0.627 |
parach | +0.622 |
itta | +0.613 |
Aux | +0.581 |
Neg logit contributions | |
Toronto | -0.673 |
zik | -0.633 |
uni | -0.633 |
opian | -0.632 |
aunder | -0.608 |
Token | ( |
Token ID | 357 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Lie | +1.209 |
Simulation | +1.067 |
parach | +1.057 |
Chaff | +1.001 |
Princ | +0.983 |
Neg logit contributions | |
Toronto | -1.632 |
zik | -1.589 |
opian | -1.580 |
uni | -1.577 |
conserve | -1.485 |
Token | x |
Token ID | 2124 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Toronto | +0.814 |
zik | +0.789 |
uni | +0.780 |
opian | +0.770 |
aunder | +0.728 |
Neg logit contributions | |
Lie | -0.767 |
parach | -0.717 |
Simulation | -0.706 |
Chaff | -0.666 |
itta | -0.661 |
Token | . |
Token ID | 13 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Toronto | +1.590 |
zik | +1.566 |
uni | +1.518 |
opian | +1.508 |
aunder | +1.414 |
Neg logit contributions | |
Lie | -1.630 |
parach | -1.507 |
Simulation | -1.497 |
itta | -1.435 |
Chaff | -1.412 |
Token | x |
Token ID | 87 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
Toronto | +2.404 |
zik | +2.336 |
uni | +2.266 |
opian | +2.229 |
aunder | +2.091 |
Neg logit contributions | |
Lie | -3.000 |
parach | -2.822 |
Simulation | -2.790 |
itta | -2.701 |
Chaff | -2.645 |
Token | . |
Token ID | 13 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
Toronto | +0.618 |
zik | +0.615 |
opian | +0.593 |
uni | +0.591 |
rall | +0.559 |
Neg logit contributions | |
Lie | -0.596 |
Simulation | -0.542 |
parach | -0.541 |
itta | -0.520 |
Chaff | -0.509 |
Token | x |
Token ID | 87 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
Toronto | +3.572 |
zik | +3.427 |
uni | +3.351 |
opian | +3.255 |
aunder | +3.038 |
Neg logit contributions | |
Lie | -4.909 |
parach | -4.677 |
Simulation | -4.605 |
itta | -4.442 |
Princ | -4.404 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Toronto | +5.233 |
uni | +4.919 |
zik | +4.902 |
opian | +4.665 |
aunder | +4.433 |
Neg logit contributions | |
Lie | -6.961 |
parach | -6.703 |
Simulation | -6.558 |
Princ | -6.311 |
actionGroup | -6.308 |
Token | 120 |
Token ID | 10232 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Toronto | +5.175 |
uni | +4.843 |
zik | +4.312 |
opian | +3.898 |
gyn | +3.635 |
Neg logit contributions | |
Lie | -16.412 |
Simulation | -15.503 |
parach | -15.422 |
actionGroup | -15.066 |
Chaff | -15.006 |
Token | 10 |
Token ID | 838 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
Lie | +2.620 |
Simulation | +2.424 |
parach | +2.344 |
Princ | +2.299 |
itta | +2.283 |
Neg logit contributions | |
Toronto | -2.739 |
zik | -2.734 |
opian | -2.629 |
uni | -2.597 |
gyn | -2.450 |
Token | 25 |
Token ID | 1495 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
Lie | +4.754 |
Simulation | +4.307 |
@@ | +3.957 |
parach | +3.905 |
itta | +3.827 |
Neg logit contributions | |
zik | -6.232 |
uni | -6.026 |
opian | -6.010 |
Toronto | -5.959 |
rall | -5.919 |
Token | 290 |
Token ID | 24369 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
Lie | +0.250 |
parach | +0.231 |
Simulation | +0.230 |
itta | +0.220 |
Chaff | +0.216 |
Neg logit contributions | |
Toronto | -0.271 |
zik | -0.265 |
uni | -0.259 |
opian | -0.257 |
aunder | -0.241 |
Token | x |
Token ID | 2124 |
Feature activation | -9.72e-02 |
Pos logit contributions | |
Toronto | +0.475 |
zik | +0.460 |
uni | +0.454 |
opian | +0.447 |
aunder | +0.422 |
Neg logit contributions | |
Lie | -0.443 |
parach | -0.414 |
Simulation | -0.406 |
Chaff | -0.383 |
itta | -0.382 |
Token | x |
Token ID | 2124 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Toronto | +1.857 |
zik | +1.795 |
uni | +1.770 |
opian | +1.737 |
aunder | +1.638 |
Neg logit contributions | |
Lie | -1.865 |
parach | -1.752 |
Simulation | -1.725 |
itta | -1.636 |
Chaff | -1.631 |
Token | . |
Token ID | 13 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
Toronto | +1.660 |
zik | +1.634 |
uni | +1.586 |
opian | +1.574 |
aunder | +1.477 |
Neg logit contributions | |
Lie | -1.709 |
parach | -1.581 |
Simulation | -1.571 |
itta | -1.506 |
Chaff | -1.482 |
Token | x |
Token ID | 87 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Toronto | +2.870 |
zik | +2.771 |
uni | +2.698 |
opian | +2.637 |
aunder | +2.470 |
Neg logit contributions | |
Lie | -3.754 |
parach | -3.557 |
Simulation | -3.508 |
itta | -3.391 |
Chaff | -3.334 |
Token | . |
Token ID | 13 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Toronto | +1.349 |
zik | +1.332 |
uni | +1.288 |
opian | +1.283 |
aunder | +1.205 |
Neg logit contributions | |
Lie | -1.366 |
parach | -1.256 |
Simulation | -1.253 |
itta | -1.202 |
Chaff | -1.178 |
Token | x |
Token ID | 87 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
Toronto | +3.080 |
zik | +2.970 |
uni | +2.893 |
opian | +2.825 |
aunder | +2.645 |
Neg logit contributions | |
Lie | -4.063 |
parach | -3.854 |
Simulation | -3.798 |
itta | -3.673 |
Chaff | -3.612 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Toronto | +5.276 |
zik | +4.972 |
uni | +4.922 |
opian | +4.605 |
gyn | +4.408 |
Neg logit contributions | |
Lie | -7.119 |
parach | -6.924 |
Simulation | -6.744 |
Princ | -6.558 |
actionGroup | -6.472 |
Token | 135 |
Token ID | 17059 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Toronto | +7.024 |
zik | +6.677 |
uni | +6.538 |
opian | +5.300 |
gyn | +5.265 |
Neg logit contributions | |
Lie | -13.873 |
Simulation | -13.230 |
Princ | -13.144 |
parach | -13.105 |
Curse | -12.843 |
Token | 106 |
Token ID | 15696 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
Lie | +2.456 |
Simulation | +2.299 |
parach | +2.212 |
Princ | +2.173 |
itta | +2.153 |
Neg logit contributions | |
Toronto | -2.427 |
zik | -2.398 |
opian | -2.340 |
uni | -2.318 |
gyn | -2.175 |
Token | 19 |
Token ID | 1129 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Lie | +3.263 |
Simulation | +2.948 |
@@ | +2.680 |
parach | +2.640 |
itta | +2.627 |
Neg logit contributions | |
opian | -4.859 |
zik | -4.829 |
uni | -4.792 |
rall | -4.704 |
Toronto | -4.652 |
Token | 41 |
Token ID | 3901 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
Toronto | +2.078 |
zik | +2.046 |
uni | +2.002 |
opian | +1.979 |
aunder | +1.876 |
Neg logit contributions | |
Lie | -1.682 |
parach | -1.540 |
Simulation | -1.530 |
itta | -1.453 |
Chaff | -1.431 |
Token | x |
Token ID | 2124 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Toronto | +3.420 |
zik | +3.301 |
uni | +3.219 |
opian | +3.145 |
aunder | +2.961 |
Neg logit contributions | |
Lie | -3.912 |
parach | -3.703 |
Simulation | -3.647 |
itta | -3.533 |
Princ | -3.463 |
Token | 7 |
Token ID | 22 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
Toronto | +4.400 |
zik | +4.258 |
uni | +4.156 |
opian | +4.061 |
gyn | +3.821 |
Neg logit contributions | |
Lie | -4.657 |
parach | -4.407 |
Simulation | -4.344 |
itta | -4.161 |
Princ | -4.113 |
Token | { |
Token ID | 1391 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
Toronto | +4.621 |
zik | +4.484 |
uni | +4.394 |
opian | +4.301 |
aunder | +4.086 |
Neg logit contributions | |
Lie | -4.115 |
parach | -3.874 |
Simulation | -3.789 |
itta | -3.656 |
Chaff | -3.579 |
Token | ( |
Token ID | 7 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Lie | +0.308 |
Simulation | +0.278 |
parach | +0.269 |
@@ | +0.261 |
itta | +0.260 |
Neg logit contributions | |
zik | -0.420 |
opian | -0.409 |
Toronto | -0.409 |
uni | -0.404 |
rall | -0.394 |
Token | 507 |
Token ID | 35378 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
Toronto | +2.250 |
zik | +2.187 |
uni | +2.138 |
opian | +2.100 |
aunder | +1.985 |
Neg logit contributions | |
Lie | -2.119 |
parach | -1.982 |
Simulation | -1.956 |
itta | -1.876 |
Princ | -1.841 |
Token | s |
Token ID | 82 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Lie | +0.621 |
parach | +0.562 |
Simulation | +0.560 |
itta | +0.510 |
actionGroup | +0.504 |
Neg logit contributions | |
Toronto | -0.926 |
zik | -0.919 |
uni | -0.894 |
opian | -0.887 |
aunder | -0.852 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Lie | +1.942 |
Simulation | +1.702 |
parach | +1.686 |
itta | +1.678 |
@@ | +1.631 |
Neg logit contributions | |
zik | -2.418 |
Toronto | -2.417 |
opian | -2.331 |
uni | -2.313 |
rall | -2.243 |
Token | 20 |
Token ID | 1160 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
zik | +4.980 |
Toronto | +4.638 |
uni | +4.614 |
opian | +4.121 |
Azerbai | +3.978 |
Neg logit contributions | |
Lie | -13.364 |
itta | -13.351 |
actionGroup | -13.136 |
aukee | -13.113 |
parach | -12.982 |
Token | . |
Token ID | 13 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
Lie | +1.518 |
Simulation | +1.338 |
parach | +1.290 |
Chaff | +1.239 |
@@ | +1.236 |
Neg logit contributions | |
zik | -1.842 |
opian | -1.818 |
Toronto | -1.816 |
uni | -1.786 |
rall | -1.752 |
Token | N |
Token ID | 399 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
Toronto | +2.465 |
zik | +2.386 |
uni | +2.336 |
opian | +2.287 |
aunder | +2.159 |
Neg logit contributions | |
Lie | -2.546 |
parach | -2.397 |
Simulation | -2.358 |
itta | -2.266 |
Princ | -2.228 |
Token | c |
Token ID | 66 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
Toronto | +3.987 |
zik | +3.855 |
uni | +3.728 |
opian | +3.663 |
gyn | +3.426 |
Neg logit contributions | |
Lie | -4.927 |
parach | -4.714 |
Simulation | -4.664 |
itta | -4.451 |
Princ | -4.451 |
Token | 7 |
Token ID | 22 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Toronto | +3.689 |
zik | +3.556 |
uni | +3.473 |
opian | +3.386 |
gyn | +3.171 |
Neg logit contributions | |
Lie | -4.395 |
parach | -4.184 |
Simulation | -4.125 |
itta | -3.957 |
Princ | -3.907 |
Token | x |
Token ID | 2124 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Toronto | +0.653 |
zik | +0.635 |
uni | +0.627 |
opian | +0.618 |
aunder | +0.584 |
Neg logit contributions | |
Lie | -0.619 |
parach | -0.578 |
Simulation | -0.569 |
Chaff | -0.538 |
itta | -0.535 |
Token | . |
Token ID | 13 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Toronto | +1.323 |
zik | +1.309 |
uni | +1.267 |
opian | +1.264 |
aunder | +1.184 |
Neg logit contributions | |
Lie | -1.327 |
parach | -1.217 |
Simulation | -1.214 |
itta | -1.162 |
Chaff | -1.144 |
Token | x |
Token ID | 87 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
Toronto | +2.454 |
zik | +2.385 |
uni | +2.315 |
opian | +2.276 |
aunder | +2.136 |
Neg logit contributions | |
Lie | -3.076 |
parach | -2.894 |
Simulation | -2.863 |
itta | -2.769 |
Chaff | -2.714 |
Token | . |
Token ID | 13 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
zik | +0.387 |
Toronto | +0.387 |
opian | +0.374 |
uni | +0.372 |
rall | +0.356 |
Neg logit contributions | |
Lie | -0.370 |
Simulation | -0.337 |
parach | -0.334 |
itta | -0.322 |
Chaff | -0.315 |
Token | x |
Token ID | 87 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
Toronto | +3.218 |
zik | +3.096 |
uni | +3.019 |
opian | +2.942 |
aunder | +2.749 |
Neg logit contributions | |
Lie | -4.318 |
parach | -4.104 |
Simulation | -4.041 |
itta | -3.905 |
Princ | -3.853 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Toronto | +5.586 |
zik | +5.224 |
uni | +5.186 |
opian | +4.827 |
gyn | +4.632 |
Neg logit contributions | |
Lie | -7.748 |
parach | -7.523 |
Simulation | -7.301 |
Princ | -7.115 |
actionGroup | -7.067 |
Token | 140 |
Token ID | 15187 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Toronto | +8.304 |
zik | +7.731 |
uni | +7.624 |
opian | +6.851 |
gyn | +6.656 |
Neg logit contributions | |
Lie | -12.382 |
parach | -11.589 |
Simulation | -11.394 |
Chaff | -11.387 |
Princ | -11.349 |
Token | 10 |
Token ID | 838 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
Lie | +3.094 |
Simulation | +2.844 |
parach | +2.734 |
Princ | +2.713 |
itta | +2.665 |
Neg logit contributions | |
Toronto | -3.292 |
zik | -3.278 |
opian | -3.188 |
uni | -3.142 |
gyn | -2.968 |
Token | 59 |
Token ID | 3270 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Lie | +4.427 |
Simulation | +3.906 |
parach | +3.614 |
@@ | +3.575 |
Lie | +3.485 |
Neg logit contributions | |
zik | -6.130 |
opian | -5.966 |
uni | -5.959 |
Toronto | -5.946 |
rall | -5.867 |
Token | 272 |
Token ID | 29807 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
Lie | +1.505 |
parach | +1.381 |
Simulation | +1.376 |
itta | +1.315 |
Chaff | +1.293 |
Neg logit contributions | |
Toronto | -1.640 |
zik | -1.603 |
uni | -1.568 |
opian | -1.549 |
aunder | -1.455 |
Token | x |
Token ID | 2124 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
Toronto | +0.639 |
zik | +0.621 |
uni | +0.612 |
opian | +0.601 |
aunder | +0.569 |
Neg logit contributions | |
Lie | -0.601 |
parach | -0.561 |
Simulation | -0.549 |
Chaff | -0.521 |
itta | -0.517 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Toronto | +3.200 |
zik | +3.043 |
uni | +3.036 |
opian | +2.924 |
aunder | +2.691 |
Neg logit contributions | |
Lie | -5.425 |
Simulation | -5.215 |
parach | -5.146 |
itta | -5.077 |
Princ | -4.978 |
Token | initially |
Token ID | 7317 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
Toronto | +1.038 |
zik | +1.007 |
uni | +0.985 |
opian | +0.966 |
aunder | +0.916 |
Neg logit contributions | |
Lie | -0.951 |
parach | -0.894 |
Simulation | -0.878 |
itta | -0.842 |
Princ | -0.827 |
Token | failing |
Token ID | 9894 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
Toronto | +2.061 |
zik | +1.982 |
uni | +1.935 |
opian | +1.905 |
gyn | +1.798 |
Neg logit contributions | |
Lie | -1.801 |
Simulation | -1.688 |
parach | -1.687 |
itta | -1.609 |
actionGroup | -1.581 |
Token | , |
Token ID | 11 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Toronto | +3.766 |
zik | +3.661 |
uni | +3.547 |
opian | +3.434 |
aunder | +3.200 |
Neg logit contributions | |
Lie | -6.816 |
parach | -6.557 |
Simulation | -6.542 |
itta | -6.510 |
actionGroup | -6.196 |
Token | sec |
Token ID | 792 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Toronto | +3.758 |
zik | +3.652 |
uni | +3.588 |
opian | +3.501 |
aunder | +3.361 |
Neg logit contributions | |
Lie | -2.977 |
Simulation | -2.738 |
parach | -2.723 |
itta | -2.621 |
Chaff | -2.571 |
Token | ures |
Token ID | 942 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Toronto | +1.636 |
zik | +1.563 |
uni | +1.498 |
opian | +1.448 |
aunder | +1.317 |
Neg logit contributions | |
Lie | -3.537 |
parach | -3.398 |
Simulation | -3.341 |
itta | -3.256 |
Princ | -3.213 |
Token | mark |
Token ID | 1317 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
Toronto | +5.263 |
zik | +5.162 |
uni | +4.680 |
♦ | +4.562 |
conserve | +4.309 |
Neg logit contributions | |
Simulation | -12.339 |
Lie | -12.264 |
parach | -12.055 |
itta | -11.845 |
Chaff | -11.501 |
Token | ( |
Token ID | 357 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Toronto | +1.722 |
zik | +1.659 |
uni | +1.645 |
opian | +1.582 |
aunder | +1.506 |
Neg logit contributions | |
Lie | -1.998 |
parach | -1.941 |
Simulation | -1.899 |
itta | -1.837 |
Chaff | -1.796 |
Token | 1 |
Token ID | 16 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
Toronto | +1.187 |
zik | +1.133 |
uni | +1.121 |
opian | +1.070 |
gyn | +0.999 |
Neg logit contributions | |
Lie | -1.614 |
parach | -1.552 |
Simulation | -1.510 |
Chaff | -1.462 |
Princ | -1.450 |
Token | – |
Token ID | 1906 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Toronto | +0.305 |
zik | +0.292 |
uni | +0.289 |
opian | +0.278 |
aunder | +0.263 |
Neg logit contributions | |
Lie | -0.347 |
parach | -0.329 |
Simulation | -0.327 |
itta | -0.313 |
Princ | -0.307 |
Token | 4 |
Token ID | 19 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Toronto | +2.604 |
zik | +2.420 |
uni | +2.418 |
opian | +2.303 |
aunder | +2.203 |
Neg logit contributions | |
Lie | -3.095 |
parach | -2.984 |
Simulation | -2.915 |
itta | -2.787 |
Princ | -2.761 |
Token | be |
Token ID | 307 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Toronto | +0.968 |
zik | +0.931 |
uni | +0.910 |
opian | +0.893 |
aunder | +0.839 |
Neg logit contributions | |
Lie | -1.148 |
parach | -1.093 |
Simulation | -1.063 |
itta | -1.028 |
Chaff | -1.013 |
Token | headed |
Token ID | 15353 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Lie | +1.726 |
parach | +1.630 |
Simulation | +1.560 |
itta | +1.505 |
Princ | +1.463 |
Neg logit contributions | |
Toronto | -2.560 |
zik | -2.435 |
uni | -2.420 |
opian | -2.412 |
aunder | -2.285 |
Token | therein |
Token ID | 27258 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Toronto | +2.062 |
zik | +1.995 |
uni | +1.952 |
opian | +1.906 |
aunder | +1.793 |
Neg logit contributions | |
Lie | -2.345 |
parach | -2.217 |
Simulation | -2.188 |
itta | -2.108 |
Chaff | -2.072 |
Token | .[ |
Token ID | 3693 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
Toronto | +1.231 |
zik | +1.189 |
uni | +1.161 |
opian | +1.136 |
aunder | +1.068 |
Neg logit contributions | |
Lie | -1.425 |
parach | -1.347 |
Simulation | -1.326 |
itta | -1.279 |
Princ | -1.258 |
Token | 1 |
Token ID | 16 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Toronto | +4.789 |
zik | +4.574 |
uni | +4.443 |
opian | +4.171 |
gyn | +4.021 |
Neg logit contributions | |
Lie | -6.437 |
parach | -6.161 |
Simulation | -6.053 |
itta | -5.797 |
Princ | -5.791 |
Token | ][ |
Token ID | 7131 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Toronto | +0.835 |
zik | +0.791 |
uni | +0.751 |
opian | +0.671 |
aunder | +0.625 |
Neg logit contributions | |
Lie | -2.585 |
parach | -2.515 |
Simulation | -2.484 |
itta | -2.418 |
actionGroup | -2.415 |
Token | 27 |
Token ID | 1983 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Toronto | +8.076 |
zik | +7.548 |
uni | +7.393 |
opian | +6.718 |
gyn | +6.691 |
Neg logit contributions | |
Lie | -10.876 |
parach | -10.508 |
Simulation | -10.245 |
actionGroup | -9.919 |
Princ | -9.822 |
Token | ][ |
Token ID | 7131 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
Lie | +1.656 |
parach | +1.602 |
Simulation | +1.581 |
itta | +1.543 |
Princ | +1.523 |
Neg logit contributions | |
Toronto | -0.532 |
zik | -0.499 |
uni | -0.479 |
opian | -0.445 |
aunder | -0.397 |
Token | 45 |
Token ID | 2231 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Toronto | +4.596 |
zik | +4.402 |
uni | +4.328 |
opian | +4.178 |
gyn | +3.978 |
Neg logit contributions | |
Lie | -4.587 |
parach | -4.365 |
Simulation | -4.259 |
itta | -4.092 |
Princ | -4.041 |
Token | ] |
Token ID | 60 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Toronto | +0.585 |
zik | +0.537 |
uni | +0.521 |
opian | +0.463 |
aunder | +0.415 |
Neg logit contributions | |
Lie | -2.210 |
parach | -2.156 |
Simulation | -2.121 |
itta | -2.074 |
actionGroup | -2.055 |
Token |
|
Token ID | 198 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Toronto | +1.485 |
zik | +1.439 |
uni | +1.405 |
opian | +1.380 |
aunder | +1.301 |
Neg logit contributions | |
Lie | -1.567 |
parach | -1.472 |
Simulation | -1.454 |
itta | -1.398 |
Princ | -1.376 |
Token | F |
Token ID | 37 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Toronto | +0.994 |
zik | +0.962 |
uni | +0.934 |
opian | +0.913 |
aunder | +0.850 |
Neg logit contributions | |
Lie | -1.383 |
parach | -1.309 |
Simulation | -1.294 |
itta | -1.247 |
Chaff | -1.236 |
Token | . |
Token ID | 13 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
Toronto | +2.025 |
uni | +1.960 |
zik | +1.952 |
opian | +1.818 |
aunder | +1.739 |
Neg logit contributions | |
Lie | -2.797 |
parach | -2.733 |
Simulation | -2.644 |
itta | -2.586 |
actionGroup | -2.580 |
Token | spends |
Token ID | 16887 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
Toronto | +2.886 |
zik | +2.774 |
uni | +2.733 |
opian | +2.635 |
aunder | +2.495 |
Neg logit contributions | |
Lie | -3.339 |
parach | -3.191 |
Simulation | -3.133 |
itta | -3.049 |
actionGroup | -2.955 |
Token | record |
Token ID | 1700 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
Toronto | +2.799 |
zik | +2.695 |
uni | +2.634 |
opian | +2.554 |
aunder | +2.391 |
Neg logit contributions | |
Lie | -3.597 |
parach | -3.435 |
Simulation | -3.382 |
itta | -3.294 |
Princ | -3.207 |
Token | $ |
Token ID | 720 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
Toronto | +4.679 |
zik | +4.493 |
uni | +4.425 |
opian | +4.213 |
aunder | +3.996 |
Neg logit contributions | |
Lie | -6.021 |
parach | -5.823 |
Simulation | -5.757 |
itta | -5.589 |
actionGroup | -5.479 |
Token | 241 |
Token ID | 28872 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Toronto | +3.723 |
zik | +3.582 |
uni | +3.514 |
opian | +3.429 |
aunder | +3.259 |
Neg logit contributions | |
Lie | -3.643 |
parach | -3.457 |
Simulation | -3.379 |
itta | -3.252 |
Princ | -3.198 |
Token | million |
Token ID | 1510 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Toronto | +6.849 |
zik | +6.774 |
uni | +6.375 |
opian | +5.917 |
aunder | +5.874 |
Neg logit contributions | |
Lie | -11.297 |
Simulation | -10.770 |
parach | -10.751 |
actionGroup | -10.683 |
itta | -10.665 |
Token | on |
Token ID | 319 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Toronto | +3.777 |
zik | +3.668 |
uni | +3.532 |
opian | +3.438 |
aunder | +3.277 |
Neg logit contributions | |
Lie | -4.730 |
parach | -4.500 |
Simulation | -4.435 |
itta | -4.350 |
actionGroup | -4.199 |
Token | homeless |
Token ID | 10463 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Toronto | +1.667 |
zik | +1.601 |
uni | +1.560 |
opian | +1.513 |
aunder | +1.412 |
Neg logit contributions | |
Lie | -2.487 |
parach | -2.368 |
Simulation | -2.337 |
itta | -2.269 |
Chaff | -2.227 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Toronto | +2.810 |
zik | +2.708 |
uni | +2.647 |
opian | +2.569 |
aunder | +2.427 |
Neg logit contributions | |
Lie | -3.292 |
parach | -3.119 |
Simulation | -3.071 |
itta | -2.977 |
Chaff | -2.914 |
Token | can |
Token ID | 460 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Toronto | +1.148 |
zik | +1.111 |
uni | +1.080 |
opian | +1.067 |
aunder | +0.988 |
Neg logit contributions | |
Lie | -1.425 |
parach | -1.344 |
Simulation | -1.322 |
itta | -1.270 |
Chaff | -1.259 |
Token | p |
Token ID | 79 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Toronto | +0.922 |
zik | +0.893 |
uni | +0.874 |
opian | +0.862 |
aunder | +0.811 |
Neg logit contributions | |
Lie | -0.980 |
parach | -0.927 |
Simulation | -0.909 |
itta | -0.874 |
Princ | -0.860 |
Token | aul |
Token ID | 2518 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Toronto | +3.123 |
zik | +3.006 |
uni | +2.972 |
opian | +2.855 |
aunder | +2.703 |
Neg logit contributions | |
Lie | -3.545 |
parach | -3.360 |
Simulation | -3.309 |
itta | -3.162 |
Chaff | -3.147 |
Token | i |
Token ID | 72 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
Toronto | +2.738 |
zik | +2.660 |
uni | +2.620 |
opian | +2.504 |
aunder | +2.339 |
Neg logit contributions | |
Lie | -4.268 |
parach | -4.090 |
Simulation | -4.039 |
Chaff | -3.876 |
itta | -3.853 |
Token | . |
Token ID | 13 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
Toronto | +6.234 |
zik | +6.130 |
uni | +6.071 |
opian | +5.721 |
aunder | +5.561 |
Neg logit contributions | |
Lie | -7.319 |
parach | -6.969 |
Simulation | -6.829 |
Chaff | -6.739 |
Princ | -6.620 |
Token | re |
Token ID | 260 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
Toronto | +4.621 |
zik | +4.501 |
uni | +4.483 |
opian | +4.229 |
aunder | +4.029 |
Neg logit contributions | |
Lie | -5.585 |
parach | -5.357 |
Simulation | -5.230 |
Chaff | -5.084 |
Princ | -5.043 |
Token | in |
Token ID | 259 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
zik | +5.453 |
uni | +5.361 |
Toronto | +5.250 |
opian | +5.126 |
aunder | +4.684 |
Neg logit contributions | |
Lie | -9.058 |
parach | -8.853 |
Chaff | -8.642 |
Simulation | -8.628 |
Princ | -8.603 |
Token | ik |
Token ID | 1134 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
zik | +7.624 |
uni | +6.886 |
Toronto | +6.682 |
opian | +6.403 |
iker | +6.281 |
Neg logit contributions | |
Lie | -11.310 |
Chaff | -10.887 |
parach | -10.799 |
Princ | -10.641 |
Simulation | -10.532 |
Token | ain |
Token ID | 391 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
uni | +3.790 |
Toronto | +3.733 |
zik | +3.640 |
opian | +3.387 |
aunder | +3.315 |
Neg logit contributions | |
Lie | -8.865 |
parach | -8.607 |
Simulation | -8.394 |
Chaff | -8.317 |
Princ | -8.128 |
Token | en |
Token ID | 268 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Toronto | +1.558 |
zik | +1.509 |
uni | +1.460 |
opian | +1.342 |
aunder | +1.148 |
Neg logit contributions | |
Lie | -5.247 |
parach | -5.085 |
Simulation | -5.032 |
Chaff | -4.907 |
itta | -4.900 |
Token | @ |
Token ID | 2488 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Toronto | +3.385 |
zik | +3.278 |
uni | +3.225 |
opian | +3.100 |
aunder | +2.942 |
Neg logit contributions | |
Lie | -3.499 |
parach | -3.283 |
Simulation | -3.248 |
itta | -3.120 |
Chaff | -3.108 |
Token | il |
Token ID | 4229 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
Toronto | +3.319 |
zik | +3.189 |
uni | +3.140 |
opian | +3.037 |
aunder | +2.849 |
Neg logit contributions | |
Lie | -3.615 |
parach | -3.416 |
Simulation | -3.358 |
itta | -3.225 |
Chaff | -3.218 |
Token | : |
Token ID | 25 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Lie | +0.832 |
parach | +0.782 |
Simulation | +0.769 |
itta | +0.737 |
Chaff | +0.726 |
Neg logit contributions | |
Toronto | -0.864 |
zik | -0.838 |
uni | -0.819 |
opian | -0.803 |
aunder | -0.760 |
Token | US |
Token ID | 1294 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Lie | +1.997 |
Simulation | +1.837 |
parach | +1.796 |
Princ | +1.735 |
Chaff | +1.729 |
Neg logit contributions | |
Toronto | -2.234 |
zik | -2.211 |
uni | -2.131 |
opian | -2.116 |
aunder | -2.023 |
Token | Department |
Token ID | 2732 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Toronto | +2.339 |
zik | +2.251 |
uni | +2.226 |
opian | +2.162 |
aunder | +2.026 |
Neg logit contributions | |
Lie | -2.562 |
parach | -2.433 |
Simulation | -2.380 |
itta | -2.318 |
Princ | -2.255 |
Token | of |
Token ID | 286 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
Toronto | +2.305 |
zik | +2.249 |
uni | +2.190 |
opian | +2.155 |
aunder | +2.039 |
Neg logit contributions | |
Lie | -2.422 |
parach | -2.266 |
Simulation | -2.245 |
itta | -2.151 |
Chaff | -2.122 |
Token | Health |
Token ID | 3893 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
Toronto | +3.992 |
zik | +3.871 |
uni | +3.667 |
opian | +3.631 |
ities | +3.466 |
Neg logit contributions | |
parach | -8.646 |
Lie | -8.622 |
itta | -8.546 |
actionGroup | -8.404 |
Simulation | -8.252 |
Token | and |
Token ID | 290 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Toronto | +3.510 |
zik | +3.464 |
uni | +3.320 |
gyn | +3.168 |
opian | +3.131 |
Neg logit contributions | |
Lie | -5.700 |
parach | -5.648 |
actionGroup | -5.440 |
itta | -5.425 |
Simulation | -5.298 |
Token | Human |
Token ID | 5524 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
Toronto | +4.751 |
uni | +4.507 |
zik | +4.442 |
gyn | +4.424 |
opian | +4.275 |
Neg logit contributions | |
Lie | -12.637 |
itta | -12.544 |
parach | -12.374 |
Simulation | -12.217 |
actionGroup | -12.157 |
Token | Services |
Token ID | 6168 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
zik | +5.465 |
Toronto | +5.373 |
opian | +5.008 |
uni | +5.001 |
ities | +4.965 |
Neg logit contributions | |
Lie | -6.444 |
parach | -6.089 |
actionGroup | -5.838 |
itta | -5.811 |
Simulation | -5.788 |
Token | , |
Token ID | 11 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
Toronto | +1.356 |
zik | +1.307 |
uni | +1.276 |
opian | +1.243 |
aunder | +1.169 |
Neg logit contributions | |
Lie | -1.688 |
parach | -1.611 |
Simulation | -1.568 |
itta | -1.529 |
actionGroup | -1.508 |
Token | CDC |
Token ID | 20434 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
Toronto | +0.324 |
zik | +0.314 |
uni | +0.307 |
opian | +0.301 |
aunder | +0.285 |
Neg logit contributions | |
Lie | -0.325 |
parach | -0.304 |
Simulation | -0.302 |
itta | -0.285 |
Princ | -0.285 |
Token | ; |
Token ID | 26 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Lie | +0.366 |
parach | +0.344 |
Simulation | +0.341 |
itta | +0.327 |
Princ | +0.323 |
Neg logit contributions | |
Toronto | -0.335 |
zik | -0.325 |
uni | -0.316 |
opian | -0.311 |
aunder | -0.293 |
Token | , |
Token ID | 11 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Toronto | +2.914 |
zik | +2.785 |
opian | +2.756 |
uni | +2.747 |
aunder | +2.538 |
Neg logit contributions | |
Lie | -3.307 |
parach | -3.143 |
Simulation | -3.121 |
itta | -2.987 |
Chaff | -2.951 |
Token | years |
Token ID | 812 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Toronto | +1.713 |
zik | +1.665 |
uni | +1.625 |
opian | +1.579 |
aunder | +1.497 |
Neg logit contributions | |
Lie | -1.759 |
parach | -1.649 |
Simulation | -1.618 |
itta | -1.555 |
Chaff | -1.536 |
Token | and |
Token ID | 290 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Toronto | +1.820 |
zik | +1.729 |
opian | +1.705 |
uni | +1.695 |
aunder | +1.557 |
Neg logit contributions | |
Lie | -2.638 |
parach | -2.516 |
Simulation | -2.511 |
itta | -2.408 |
actionGroup | -2.376 |
Token | in |
Token ID | 287 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
Toronto | +2.785 |
zik | +2.689 |
uni | +2.645 |
opian | +2.600 |
aunder | +2.453 |
Neg logit contributions | |
Lie | -2.642 |
parach | -2.485 |
Simulation | -2.450 |
itta | -2.355 |
Princ | -2.306 |
Token | some |
Token ID | 617 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Toronto | +2.595 |
zik | +2.506 |
uni | +2.466 |
opian | +2.411 |
aunder | +2.261 |
Neg logit contributions | |
Lie | -2.680 |
parach | -2.536 |
Simulation | -2.499 |
itta | -2.415 |
Chaff | -2.363 |
Token | cases |
Token ID | 2663 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Toronto | +1.318 |
zik | +1.275 |
uni | +1.238 |
opian | +1.210 |
aunder | +1.129 |
Neg logit contributions | |
Lie | -1.835 |
parach | -1.746 |
Simulation | -1.717 |
itta | -1.654 |
Chaff | -1.636 |
Token | , |
Token ID | 11 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
Toronto | +6.886 |
generations | +6.672 |
uni | +6.621 |
opian | +6.447 |
zik | +6.281 |
Neg logit contributions | |
Lie | -10.515 |
Simulation | -10.265 |
parach | -10.235 |
itta | -9.926 |
actionGroup | -9.829 |
Token | a |
Token ID | 257 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
Toronto | +4.284 |
uni | +4.063 |
zik | +4.029 |
opian | +3.991 |
aunder | +3.731 |
Neg logit contributions | |
Lie | -5.440 |
parach | -5.189 |
Simulation | -5.183 |
itta | -4.978 |
Chaff | -4.884 |
Token | lifetime |
Token ID | 10869 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
Toronto | +2.118 |
zik | +2.056 |
uni | +2.007 |
opian | +1.966 |
aunder | +1.860 |
Neg logit contributions | |
Lie | -2.141 |
parach | -2.017 |
Simulation | -1.979 |
itta | -1.902 |
Princ | -1.871 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Toronto | +2.594 |
zik | +2.497 |
uni | +2.433 |
opian | +2.421 |
aunder | +2.250 |
Neg logit contributions | |
Lie | -3.042 |
parach | -2.893 |
Simulation | -2.851 |
itta | -2.766 |
Chaff | -2.704 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Lie | +1.294 |
Simulation | +1.186 |
Princ | +1.122 |
parach | +1.110 |
Chaff | +1.102 |
Neg logit contributions | |
zik | -1.296 |
Toronto | -1.289 |
uni | -1.244 |
opian | -1.241 |
aunder | -1.157 |
Token | x |
Token ID | 2124 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
Toronto | +0.639 |
zik | +0.621 |
uni | +0.612 |
opian | +0.601 |
aunder | +0.569 |
Neg logit contributions | |
Lie | -0.601 |
parach | -0.561 |
Simulation | -0.549 |
Chaff | -0.521 |
itta | -0.517 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Toronto | +0.544 |
zik | +0.542 |
opian | +0.525 |
uni | +0.524 |
aunder | +0.492 |
Neg logit contributions | |
Lie | -0.521 |
parach | -0.474 |
Simulation | -0.473 |
itta | -0.452 |
Chaff | -0.446 |
Token | x |
Token ID | 87 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
Toronto | +1.873 |
zik | +1.832 |
uni | +1.773 |
opian | +1.751 |
aunder | +1.647 |
Neg logit contributions | |
Lie | -2.255 |
parach | -2.108 |
Simulation | -2.090 |
itta | -2.023 |
Chaff | -1.976 |
Token | . |
Token ID | 13 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Lie | +0.157 |
Simulation | +0.142 |
parach | +0.141 |
itta | +0.136 |
Chaff | +0.133 |
Neg logit contributions | |
zik | -0.170 |
Toronto | -0.170 |
opian | -0.165 |
uni | -0.163 |
rall | -0.160 |
Token | x |
Token ID | 87 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
Toronto | +2.658 |
zik | +2.572 |
uni | +2.500 |
opian | +2.451 |
aunder | +2.302 |
Neg logit contributions | |
Lie | -3.413 |
parach | -3.230 |
Simulation | -3.187 |
itta | -3.088 |
Chaff | -3.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Toronto | +5.153 |
zik | +4.882 |
uni | +4.842 |
opian | +4.525 |
gyn | +4.286 |
Neg logit contributions | |
Lie | -6.987 |
parach | -6.749 |
Simulation | -6.562 |
Princ | -6.312 |
actionGroup | -6.309 |
Token | 141 |
Token ID | 23756 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
Toronto | +7.201 |
zik | +6.906 |
uni | +6.891 |
opian | +5.996 |
gyn | +5.652 |
Neg logit contributions | |
Lie | -11.975 |
parach | -11.241 |
Simulation | -11.017 |
Chaff | -10.909 |
disg | -10.694 |
Token | 112 |
Token ID | 13539 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
Toronto | +0.084 |
zik | +0.082 |
uni | +0.080 |
opian | +0.079 |
aunder | +0.074 |
Neg logit contributions | |
Lie | -0.090 |
Simulation | -0.084 |
parach | -0.084 |
itta | -0.080 |
Princ | -0.080 |
Token | 08 |
Token ID | 2919 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Lie | +2.831 |
Simulation | +2.574 |
parach | +2.377 |
itta | +2.345 |
Princ | +2.304 |
Neg logit contributions | |
zik | -3.613 |
Toronto | -3.529 |
opian | -3.494 |
uni | -3.483 |
rall | -3.323 |
Token | 80 |
Token ID | 1795 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
Toronto | +2.287 |
zik | +2.240 |
uni | +2.190 |
opian | +2.158 |
aunder | +2.042 |
Neg logit contributions | |
Lie | -2.032 |
parach | -1.879 |
Simulation | -1.863 |
itta | -1.778 |
Chaff | -1.747 |
Token | x |
Token ID | 2124 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Toronto | +0.823 |
zik | +0.803 |
uni | +0.791 |
opian | +0.777 |
aunder | +0.736 |
Neg logit contributions | |
Lie | -0.789 |
parach | -0.735 |
Simulation | -0.725 |
Chaff | -0.685 |
itta | -0.681 |
Token | � |
Token ID | 250 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
Lie | +0.304 |
parach | +0.288 |
Simulation | +0.285 |
itta | +0.282 |
Chaff | +0.275 |
Neg logit contributions | |
Toronto | -0.143 |
zik | -0.138 |
uni | -0.131 |
opian | -0.128 |
aunder | -0.115 |
Token | dr |
Token ID | 7109 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
Lie | +0.521 |
parach | +0.492 |
Simulation | +0.484 |
itta | +0.469 |
Chaff | +0.458 |
Neg logit contributions | |
zik | -0.423 |
Toronto | -0.420 |
opian | -0.410 |
uni | -0.408 |
aunder | -0.380 |
Token | unk |
Token ID | 2954 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
Lie | +1.692 |
Simulation | +1.574 |
parach | +1.567 |
itta | +1.541 |
Princ | +1.490 |
Neg logit contributions | |
Toronto | -1.267 |
zik | -1.219 |
opian | -1.194 |
uni | -1.181 |
aunder | -1.088 |
Token | en |
Token ID | 268 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
Lie | +1.766 |
parach | +1.678 |
Simulation | +1.652 |
itta | +1.604 |
Chaff | +1.582 |
Neg logit contributions | |
Toronto | -0.836 |
zik | -0.821 |
uni | -0.766 |
opian | -0.753 |
aunder | -0.701 |
Token | st |
Token ID | 336 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Toronto | +0.681 |
zik | +0.667 |
uni | +0.646 |
opian | +0.635 |
aunder | +0.595 |
Neg logit contributions | |
Lie | -0.765 |
parach | -0.720 |
Simulation | -0.705 |
itta | -0.679 |
Chaff | -0.667 |
Token | up |
Token ID | 929 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Toronto | +0.989 |
zik | +0.961 |
uni | +0.936 |
opian | +0.922 |
gyn | +0.862 |
Neg logit contributions | |
Lie | -1.002 |
parach | -0.934 |
Simulation | -0.926 |
itta | -0.894 |
Chaff | -0.870 |
Token | or |
Token ID | 273 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Toronto | +5.224 |
zik | +5.109 |
uni | +5.071 |
opian | +5.034 |
aunder | +4.573 |
Neg logit contributions | |
Lie | -12.477 |
parach | -12.442 |
actionGroup | -12.309 |
Simulation | -11.818 |
Aux | -11.782 |
Token | � |
Token ID | 447 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Lie | +1.034 |
parach | +0.970 |
Simulation | +0.961 |
itta | +0.923 |
Chaff | +0.904 |
Neg logit contributions | |
Toronto | -0.957 |
zik | -0.932 |
uni | -0.913 |
opian | -0.884 |
aunder | -0.841 |
Token | � |
Token ID | 251 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Lie | +1.520 |
parach | +1.435 |
Simulation | +1.435 |
itta | +1.405 |
Chaff | +1.388 |
Neg logit contributions | |
Toronto | -0.837 |
zik | -0.784 |
uni | -0.768 |
opian | -0.741 |
aunder | -0.690 |
Token | — |
Token ID | 960 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
Lie | +3.199 |
parach | +2.944 |
Simulation | +2.888 |
Chaff | +2.795 |
itta | +2.787 |
Neg logit contributions | |
Toronto | -3.148 |
zik | -3.108 |
uni | -3.090 |
opian | -3.024 |
aunder | -2.844 |
Token | and |
Token ID | 392 |
Feature activation | +6.47e-03 |
Pos logit contributions | |
Lie | +2.981 |
parach | +2.788 |
Simulation | +2.727 |
itta | +2.671 |
Princ | +2.628 |
Neg logit contributions | |
zik | -2.358 |
Toronto | -2.348 |
opian | -2.280 |
uni | -2.274 |
aunder | -2.132 |
Token | Republican |
Token ID | 3415 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Lie | +2.728 |
parach | +2.514 |
Chaff | +2.450 |
Simulation | +2.449 |
Princ | +2.413 |
Neg logit contributions | |
Toronto | -2.289 |
zik | -2.281 |
uni | -2.255 |
opian | -2.187 |
aunder | -2.068 |
Token | nominee |
Token ID | 10429 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Toronto | +0.851 |
zik | +0.824 |
uni | +0.807 |
opian | +0.794 |
aunder | +0.746 |
Neg logit contributions | |
Lie | -1.018 |
parach | -0.960 |
Simulation | -0.943 |
itta | -0.908 |
Chaff | -0.900 |
Token | Donald |
Token ID | 3759 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Toronto | +1.209 |
zik | +1.161 |
uni | +1.129 |
opian | +1.099 |
aunder | +1.021 |
Neg logit contributions | |
Lie | -1.890 |
parach | -1.800 |
Simulation | -1.775 |
itta | -1.719 |
Chaff | -1.696 |
Token | Trump |
Token ID | 1301 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
Lie | +1.436 |
Simulation | +1.314 |
Chaff | +1.282 |
parach | +1.279 |
itta | +1.247 |
Neg logit contributions | |
Toronto | -1.116 |
zik | -1.102 |
opian | -1.090 |
uni | -1.088 |
aunder | -1.012 |
Token | Donald |
Token ID | 3759 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
Lie | +0.462 |
parach | +0.435 |
Simulation | +0.429 |
itta | +0.414 |
Chaff | +0.413 |
Neg logit contributions | |
Toronto | -0.328 |
zik | -0.319 |
uni | -0.315 |
opian | -0.307 |
aunder | -0.288 |
Token | John |
Token ID | 1757 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Toronto | +4.001 |
zik | +3.646 |
uni | +3.483 |
opian | +3.341 |
gyn | +3.083 |
Neg logit contributions | |
Lie | -6.765 |
parach | -6.646 |
Simulation | -6.497 |
itta | -6.370 |
Princ | -6.219 |
Token | Trump |
Token ID | 1301 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
Toronto | +4.815 |
zik | +4.418 |
opian | +3.984 |
ities | +3.847 |
aunder | +3.833 |
Neg logit contributions | |
Lie | -12.769 |
parach | -12.726 |
Simulation | -12.543 |
actionGroup | -12.472 |
itta | -12.349 |
Token | House |
Token ID | 18102 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
Toronto | +4.393 |
zik | +4.020 |
uni | +3.873 |
opian | +3.800 |
gyn | +3.568 |
Neg logit contributions | |
Lie | -6.553 |
parach | -6.262 |
Simulation | -6.245 |
itta | -6.016 |
actionGroup | -6.008 |
Token | committee |
Token ID | 5583 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Toronto | +3.053 |
zik | +2.824 |
uni | +2.724 |
opian | +2.638 |
aunder | +2.301 |
Neg logit contributions | |
Lie | -8.521 |
parach | -8.225 |
Simulation | -8.206 |
itta | -8.113 |
actionGroup | -7.918 |
Token | believes |
Token ID | 5804 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
Toronto | +2.551 |
zik | +2.472 |
uni | +2.388 |
opian | +2.366 |
gyn | +2.272 |
Neg logit contributions | |
Lie | -2.640 |
parach | -2.534 |
Simulation | -2.507 |
actionGroup | -2.458 |
itta | -2.449 |
Token | it |
Token ID | 340 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
Toronto | +0.542 |
zik | +0.514 |
uni | +0.496 |
opian | +0.481 |
aunder | +0.456 |
Neg logit contributions | |
Lie | -0.784 |
Simulation | -0.745 |
parach | -0.743 |
itta | -0.718 |
Princ | -0.704 |
Token | be |
Token ID | 307 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
Lie | +5.608 |
parach | +5.419 |
Simulation | +5.056 |
itta | +5.009 |
Chaff | +4.880 |
Neg logit contributions | |
Toronto | -4.764 |
zik | -4.752 |
uni | -4.489 |
opian | -4.294 |
ridges | -4.228 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
Lie | +3.383 |
parach | +3.205 |
Simulation | +3.069 |
itta | +3.002 |
Princ | +2.936 |
Neg logit contributions | |
Toronto | -3.705 |
zik | -3.663 |
uni | -3.478 |
opian | -3.430 |
aunder | -3.252 |
Token |
|
Token ID | 198 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Lie | +0.161 |
Simulation | +0.149 |
parach | +0.143 |
Princ | +0.141 |
itta | +0.140 |
Neg logit contributions | |
zik | -0.160 |
Toronto | -0.160 |
opian | -0.155 |
uni | -0.155 |
aunder | -0.146 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
zik | +1.729 |
Toronto | +1.720 |
uni | +1.672 |
opian | +1.670 |
aunder | +1.587 |
Neg logit contributions | |
Lie | -1.703 |
Simulation | -1.563 |
parach | -1.547 |
itta | -1.498 |
Princ | -1.468 |
Token | What |
Token ID | 2061 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
Toronto | +1.789 |
zik | +1.762 |
uni | +1.707 |
opian | +1.688 |
aunder | +1.598 |
Neg logit contributions | |
Lie | -1.991 |
parach | -1.853 |
Simulation | -1.845 |
itta | -1.788 |
Princ | -1.742 |
Token | makes |
Token ID | 1838 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Toronto | +0.729 |
zik | +0.708 |
uni | +0.688 |
opian | +0.680 |
aunder | +0.642 |
Neg logit contributions | |
Lie | -0.882 |
parach | -0.819 |
Simulation | -0.813 |
itta | -0.787 |
Princ | -0.780 |
Token | the |
Token ID | 262 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
Toronto | +7.782 |
uni | +7.334 |
zik | +7.321 |
opian | +6.894 |
itor | +6.662 |
Neg logit contributions | |
Lie | -9.459 |
parach | -9.458 |
Simulation | -8.848 |
actionGroup | -8.830 |
Chaff | -8.652 |
Token | manga |
Token ID | 15911 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Toronto | +3.378 |
zik | +3.250 |
uni | +3.177 |
opian | +3.103 |
aunder | +2.882 |
Neg logit contributions | |
Lie | -4.248 |
parach | -4.065 |
Simulation | -3.973 |
itta | -3.850 |
Chaff | -3.795 |
Token | truly |
Token ID | 4988 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Toronto | +1.411 |
zik | +1.366 |
uni | +1.332 |
opian | +1.298 |
aunder | +1.228 |
Neg logit contributions | |
Lie | -1.672 |
parach | -1.575 |
Simulation | -1.553 |
itta | -1.498 |
Princ | -1.475 |
Token | unique |
Token ID | 3748 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
Toronto | +1.666 |
zik | +1.620 |
uni | +1.584 |
opian | +1.546 |
aunder | +1.466 |
Neg logit contributions | |
Lie | -1.684 |
parach | -1.581 |
Simulation | -1.553 |
itta | -1.491 |
Chaff | -1.464 |
Token | compared |
Token ID | 3688 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
Lie | +0.254 |
parach | +0.239 |
Simulation | +0.236 |
itta | +0.229 |
Princ | +0.225 |
Neg logit contributions | |
Toronto | -0.199 |
zik | -0.193 |
uni | -0.186 |
opian | -0.182 |
aunder | -0.173 |
Token | ring |
Token ID | 1806 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Toronto | +2.368 |
zik | +2.253 |
uni | +2.162 |
opian | +2.097 |
aunder | +1.896 |
Neg logit contributions | |
Lie | -5.205 |
parach | -4.988 |
Simulation | -4.920 |
itta | -4.796 |
Princ | -4.738 |
Token | if |
Token ID | 611 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Lie | +0.736 |
parach | +0.689 |
Simulation | +0.672 |
itta | +0.644 |
Princ | +0.631 |
Neg logit contributions | |
Toronto | -0.889 |
zik | -0.867 |
uni | -0.848 |
opian | -0.829 |
aunder | -0.797 |
Token | she |
Token ID | 673 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Toronto | +2.291 |
zik | +2.212 |
uni | +2.163 |
opian | +2.116 |
aunder | +1.991 |
Neg logit contributions | |
Lie | -2.874 |
parach | -2.727 |
Simulation | -2.656 |
itta | -2.579 |
Chaff | -2.551 |
Token | didn |
Token ID | 1422 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
Toronto | +2.139 |
zik | +2.031 |
uni | +1.994 |
opian | +1.941 |
aunder | +1.833 |
Neg logit contributions | |
Lie | -3.291 |
parach | -3.139 |
Simulation | -3.075 |
itta | -2.987 |
Chaff | -2.936 |
Token | 't |
Token ID | 470 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
Toronto | +2.943 |
zik | +2.839 |
uni | +2.767 |
opian | +2.703 |
aunder | +2.531 |
Neg logit contributions | |
Lie | -3.828 |
parach | -3.628 |
Simulation | -3.577 |
itta | -3.457 |
Chaff | -3.401 |
Token | act |
Token ID | 719 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Toronto | +3.801 |
zik | +3.694 |
uni | +3.621 |
opian | +3.558 |
aunder | +3.383 |
Neg logit contributions | |
Lie | -2.985 |
parach | -2.788 |
Simulation | -2.741 |
itta | -2.617 |
Chaff | -2.563 |
Token | right |
Token ID | 826 |
Feature activation | +3.29e-03 |
Pos logit contributions | |
Toronto | +5.427 |
zik | +5.033 |
opian | +4.831 |
uni | +4.748 |
ities | +4.416 |
Neg logit contributions | |
Lie | -11.992 |
Simulation | -11.949 |
parach | -11.622 |
itta | -11.542 |
Princ | -11.437 |
Token | away |
Token ID | 1497 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Lie | +0.024 |
parach | +0.023 |
Simulation | +0.022 |
itta | +0.021 |
Chaff | +0.021 |
Neg logit contributions | |
Toronto | -0.028 |
zik | -0.028 |
opian | -0.026 |
uni | -0.026 |
aunder | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
Toronto | +0.796 |
zik | +0.764 |
uni | +0.747 |
opian | +0.730 |
gyn | +0.680 |
Neg logit contributions | |
Lie | -1.036 |
parach | -0.983 |
Simulation | -0.973 |
itta | -0.937 |
Chaff | -0.921 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Toronto | +2.056 |
zik | +1.964 |
uni | +1.933 |
opian | +1.881 |
gyn | +1.774 |
Neg logit contributions | |
Lie | -2.182 |
parach | -2.093 |
Simulation | -2.042 |
itta | -1.969 |
Chaff | -1.925 |
Token |
|
Token ID | 198 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
Lie | +1.337 |
Simulation | +1.177 |
parach | +1.149 |
itta | +1.105 |
Chaff | +1.099 |
Neg logit contributions | |
zik | -1.681 |
Toronto | -1.648 |
opian | -1.631 |
rall | -1.630 |
uni | -1.625 |
Token | That |
Token ID | 2504 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Lie | +2.814 |
Simulation | +2.568 |
itta | +2.527 |
parach | +2.518 |
Lie | +2.456 |
Neg logit contributions | |
zik | -2.676 |
Toronto | -2.627 |
uni | -2.579 |
opian | -2.574 |
aunder | -2.444 |
Token | � |
Token ID | 447 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
Toronto | +2.277 |
zik | +2.206 |
uni | +2.147 |
opian | +2.099 |
gyn | +1.950 |
Neg logit contributions | |
Lie | -2.877 |
parach | -2.751 |
Simulation | -2.707 |
itta | -2.608 |
actionGroup | -2.571 |
Token | � |
Token ID | 247 |
Feature activation | -9.86e-03 |
Pos logit contributions | |
Toronto | +0.130 |
zik | +0.125 |
opian | +0.121 |
uni | +0.121 |
aunder | +0.113 |
Neg logit contributions | |
Lie | -0.138 |
parach | -0.127 |
Simulation | -0.126 |
itta | -0.124 |
Chaff | -0.121 |
Token | s |
Token ID | 82 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
Toronto | +0.085 |
zik | +0.083 |
uni | +0.081 |
opian | +0.080 |
aunder | +0.076 |
Neg logit contributions | |
Lie | -0.073 |
parach | -0.068 |
Simulation | -0.067 |
itta | -0.064 |
Chaff | -0.063 |
Token | what |
Token ID | 644 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Toronto | +0.275 |
zik | +0.268 |
uni | +0.262 |
opian | +0.256 |
aunder | +0.243 |
Neg logit contributions | |
Lie | -0.285 |
parach | -0.266 |
Simulation | -0.261 |
itta | -0.252 |
Princ | -0.249 |
Token | makes |
Token ID | 1838 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Toronto | +2.605 |
zik | +2.511 |
uni | +2.455 |
opian | +2.398 |
aunder | +2.247 |
Neg logit contributions | |
Lie | -3.159 |
parach | -3.000 |
Simulation | -2.954 |
itta | -2.852 |
Chaff | -2.805 |
Token | it |
Token ID | 340 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
Toronto | +7.200 |
zik | +6.796 |
uni | +6.702 |
opian | +6.561 |
gyn | +6.318 |
Neg logit contributions | |
Lie | -9.587 |
parach | -9.346 |
actionGroup | -9.254 |
Simulation | -9.145 |
Chaff | -8.880 |
Token | so |
Token ID | 523 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
Toronto | +3.656 |
zik | +3.510 |
uni | +3.439 |
opian | +3.373 |
aunder | +3.116 |
Neg logit contributions | |
Lie | -4.774 |
parach | -4.578 |
Simulation | -4.510 |
itta | -4.350 |
Chaff | -4.303 |
Token | sad |
Token ID | 6507 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
Toronto | +2.502 |
zik | +2.423 |
uni | +2.371 |
opian | +2.324 |
aunder | +2.196 |
Neg logit contributions | |
Lie | -2.465 |
parach | -2.324 |
Simulation | -2.286 |
itta | -2.197 |
Princ | -2.158 |
Token | . |
Token ID | 13 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
Lie | +0.512 |
parach | +0.477 |
Simulation | +0.470 |
itta | +0.458 |
Princ | +0.446 |
Neg logit contributions | |
Toronto | -0.491 |
zik | -0.482 |
uni | -0.465 |
opian | -0.454 |
aunder | -0.432 |
Token | I |
Token ID | 314 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
Lie | +0.375 |
Simulation | +0.345 |
parach | +0.332 |
Princ | +0.328 |
Chaff | +0.326 |
Neg logit contributions | |
Toronto | -0.376 |
zik | -0.373 |
uni | -0.361 |
opian | -0.359 |
aunder | -0.341 |
Token | and |
Token ID | 290 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
Toronto | +1.649 |
zik | +1.593 |
uni | +1.558 |
opian | +1.524 |
aunder | +1.434 |
Neg logit contributions | |
Lie | -1.848 |
parach | -1.745 |
Simulation | -1.721 |
itta | -1.657 |
Chaff | -1.629 |
Token | the |
Token ID | 262 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
Toronto | +3.119 |
zik | +3.002 |
uni | +2.939 |
opian | +2.856 |
aunder | +2.699 |
Neg logit contributions | |
Lie | -3.642 |
parach | -3.452 |
Simulation | -3.420 |
itta | -3.288 |
Princ | -3.223 |
Token | man |
Token ID | 582 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
Toronto | +3.756 |
zik | +3.598 |
uni | +3.503 |
opian | +3.406 |
aunder | +3.182 |
Neg logit contributions | |
Lie | -5.271 |
parach | -5.012 |
Simulation | -4.967 |
itta | -4.801 |
Princ | -4.716 |
Token | escaped |
Token ID | 13537 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Toronto | +2.444 |
zik | +2.352 |
uni | +2.290 |
opian | +2.236 |
aunder | +2.083 |
Neg logit contributions | |
Lie | -3.469 |
parach | -3.305 |
Simulation | -3.238 |
itta | -3.142 |
Chaff | -3.096 |
Token | the |
Token ID | 262 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Toronto | +4.382 |
zik | +4.166 |
uni | +4.079 |
opian | +3.945 |
gyn | +3.696 |
Neg logit contributions | |
Lie | -5.623 |
Simulation | -5.429 |
parach | -5.274 |
itta | -5.170 |
actionGroup | -5.122 |
Token | Fred |
Token ID | 8559 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Toronto | +2.675 |
zik | +2.589 |
uni | +2.532 |
opian | +2.479 |
aunder | +2.341 |
Neg logit contributions | |
Lie | -2.767 |
parach | -2.609 |
Simulation | -2.566 |
itta | -2.470 |
Princ | -2.425 |
Token | Meyer |
Token ID | 23975 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
zik | +5.659 |
Toronto | +5.621 |
uni | +5.169 |
opian | +4.986 |
ities | +4.710 |
Neg logit contributions | |
parach | -11.103 |
Simulation | -11.016 |
Lie | -10.887 |
actionGroup | -10.653 |
itta | -10.378 |
Token | at |
Token ID | 379 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Toronto | +3.488 |
zik | +3.322 |
uni | +3.260 |
opian | +3.182 |
aunder | +2.974 |
Neg logit contributions | |
Lie | -4.178 |
parach | -3.994 |
Simulation | -3.931 |
itta | -3.813 |
actionGroup | -3.748 |
Token | 3 |
Token ID | 513 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
Lie | +0.953 |
parach | +0.887 |
Simulation | +0.871 |
Chaff | +0.841 |
itta | +0.841 |
Neg logit contributions | |
Toronto | -0.874 |
zik | -0.849 |
uni | -0.820 |
opian | -0.805 |
gyn | -0.759 |
Token | 184 |
Token ID | 22883 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Toronto | +0.716 |
zik | +0.694 |
uni | +0.679 |
opian | +0.665 |
aunder | +0.629 |
Neg logit contributions | |
Lie | -0.712 |
parach | -0.671 |
Simulation | -0.659 |
itta | -0.634 |
Princ | -0.623 |
Token | Ocean |
Token ID | 10692 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
Toronto | +2.664 |
zik | +2.559 |
uni | +2.519 |
opian | +2.458 |
aunder | +2.338 |
Neg logit contributions | |
Lie | -2.597 |
parach | -2.488 |
Simulation | -2.422 |
itta | -2.341 |
actionGroup | -2.285 |
Token | International |
Token ID | 4037 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Toronto | +0.961 |
zik | +0.928 |
uni | +0.911 |
opian | +0.890 |
aunder | +0.841 |
Neg logit contributions | |
Lie | -0.936 |
parach | -0.885 |
Simulation | -0.865 |
itta | -0.835 |
Chaff | -0.818 |
Token | , |
Token ID | 11 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Toronto | +1.689 |
zik | +1.609 |
uni | +1.580 |
opian | +1.539 |
aunder | +1.439 |
Neg logit contributions | |
Lie | -2.042 |
parach | -1.946 |
Simulation | -1.902 |
itta | -1.848 |
actionGroup | -1.814 |
Token | 25 |
Token ID | 1679 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Toronto | +1.684 |
zik | +1.647 |
uni | +1.599 |
opian | +1.574 |
aunder | +1.464 |
Neg logit contributions | |
Lie | -2.238 |
parach | -2.107 |
Simulation | -2.095 |
itta | -2.002 |
Princ | -1.992 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
Toronto | +1.085 |
zik | +1.003 |
uni | +0.987 |
opian | +0.943 |
gyn | +0.897 |
Neg logit contributions | |
Lie | -1.544 |
parach | -1.507 |
Simulation | -1.473 |
itta | -1.429 |
actionGroup | -1.398 |
Token | 287 |
Token ID | 38721 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Lie | +1.780 |
Simulation | +1.635 |
parach | +1.621 |
Princ | +1.561 |
Chaff | +1.540 |
Neg logit contributions | |
Toronto | -1.516 |
zik | -1.508 |
uni | -1.459 |
opian | -1.448 |
aunder | -1.341 |
Token | - |
Token ID | 532 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Lie | +5.733 |
Simulation | +5.071 |
Chaff | +4.705 |
Princ | +4.414 |
Curse | +4.394 |
Neg logit contributions | |
zik | -10.929 |
opian | -10.625 |
uni | -10.455 |
rall | -10.421 |
ridges | -10.316 |
Token | 300 |
Token ID | 5867 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
Lie | +6.937 |
Simulation | +5.551 |
Chaff | +5.535 |
Curse | +5.506 |
Princ | +5.499 |
Neg logit contributions | |
opian | -10.949 |
uni | -10.818 |
zik | -10.732 |
Toronto | -10.731 |
uckland | -10.213 |
Token | . |
Token ID | 764 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Lie | +2.875 |
Simulation | +2.294 |
Chaff | +2.116 |
itta | +1.835 |
Princ | +1.709 |
Neg logit contributions | |
rall | -9.966 |
zik | -9.655 |
opian | -9.501 |
uni | -9.328 |
uckland | -9.312 |
Token |
|
Token ID | 198 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Lie | +2.761 |
Simulation | +2.421 |
parach | +2.279 |
Chaff | +2.247 |
itta | +2.231 |
Neg logit contributions | |
zik | -3.672 |
rall | -3.643 |
opian | -3.600 |
Toronto | -3.558 |
uni | -3.547 |
Token |
|
Token ID | 198 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Lie | +1.430 |
Simulation | +1.252 |
parach | +1.223 |
itta | +1.174 |
Chaff | +1.170 |
Neg logit contributions | |
zik | -1.811 |
Toronto | -1.774 |
rall | -1.763 |
opian | -1.756 |
uni | -1.749 |
Token | Google |
Token ID | 11708 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
Lie | +2.322 |
Lie | +2.116 |
Simulation | +2.077 |
@@ | +2.029 |
JUST | +2.003 |
Neg logit contributions | |
zik | -2.102 |
opian | -1.960 |
rall | -1.948 |
uni | -1.900 |
conserve | -1.874 |
Token | soon |
Token ID | 2582 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
Lie | +3.154 |
parach | +3.139 |
itta | +2.809 |
Simulation | +2.775 |
Princ | +2.702 |
Neg logit contributions | |
aunder | -3.281 |
Toronto | -3.218 |
zik | -3.202 |
uni | -3.146 |
opian | -3.142 |
Token | . |
Token ID | 13 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
Lie | +0.536 |
Simulation | +0.490 |
parach | +0.483 |
itta | +0.461 |
Chaff | +0.454 |
Neg logit contributions | |
zik | -0.614 |
Toronto | -0.609 |
opian | -0.592 |
uni | -0.590 |
aunder | -0.558 |
Token | As |
Token ID | 1081 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
Lie | +7.636 |
Simulation | +7.155 |
parach | +6.957 |
itta | +6.622 |
Chaff | +6.611 |
Neg logit contributions | |
Toronto | -7.376 |
zik | -7.155 |
uni | -7.116 |
opian | -7.079 |
aunder | -6.594 |
Token | well |
Token ID | 880 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Lie | +3.736 |
parach | +3.389 |
Simulation | +3.162 |
Chaff | +3.056 |
itzer | +2.934 |
Neg logit contributions | |
Toronto | -6.034 |
opian | -5.919 |
zik | -5.852 |
uni | -5.773 |
rall | -5.659 |
Token | as |
Token ID | 355 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Lie | +1.247 |
parach | +1.144 |
Simulation | +1.117 |
Chaff | +1.055 |
itta | +1.027 |
Neg logit contributions | |
Toronto | -1.651 |
zik | -1.588 |
uni | -1.587 |
opian | -1.560 |
aunder | -1.494 |
Token | updates |
Token ID | 5992 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
Lie | +2.490 |
parach | +2.425 |
Simulation | +2.319 |
Chaff | +2.200 |
Aux | +2.175 |
Neg logit contributions | |
zik | -2.333 |
Toronto | -2.315 |
uni | -2.194 |
opian | -2.134 |
aunder | -2.047 |
Token | regarding |
Token ID | 5115 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
Lie | +4.394 |
parach | +3.939 |
Simulation | +3.715 |
@@ | +3.496 |
Princ | +3.304 |
Neg logit contributions | |
zik | -10.479 |
Toronto | -10.180 |
rall | -9.722 |
uni | -9.626 |
uckland | -9.592 |
Token | the |
Token ID | 262 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
Lie | +2.385 |
Simulation | +2.099 |
parach | +2.092 |
Chaff | +1.993 |
itta | +1.895 |
Neg logit contributions | |
zik | -3.827 |
Toronto | -3.768 |
opian | -3.716 |
uni | -3.698 |
rall | -3.645 |
Token | future |
Token ID | 2003 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
Lie | +2.031 |
parach | +1.899 |
Simulation | +1.803 |
itta | +1.663 |
Chaff | +1.635 |
Neg logit contributions | |
zik | -3.767 |
Toronto | -3.734 |
uni | -3.601 |
opian | -3.533 |
aunder | -3.466 |
Token | of |
Token ID | 286 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Lie | +3.032 |
Simulation | +2.670 |
parach | +2.643 |
Chaff | +2.563 |
Curse | +2.471 |
Neg logit contributions | |
zik | -4.419 |
Toronto | -4.250 |
uni | -4.229 |
rall | -4.175 |
opian | -4.167 |
Token | Cl |
Token ID | 1012 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Lie | +0.969 |
parach | +0.910 |
Simulation | +0.896 |
itta | +0.845 |
Princ | +0.843 |
Neg logit contributions | |
Toronto | -1.034 |
zik | -1.005 |
uni | -0.987 |
opian | -0.973 |
aunder | -0.918 |
Token | Profile |
Token ID | 13118 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
Toronto | +2.566 |
zik | +2.475 |
uni | +2.417 |
opian | +2.353 |
aunder | +2.202 |
Neg logit contributions | |
Lie | -2.869 |
parach | -2.728 |
Simulation | -2.672 |
itta | -2.578 |
Princ | -2.546 |
Token | Blog |
Token ID | 14001 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
Lie | +0.545 |
parach | +0.513 |
Simulation | +0.504 |
itta | +0.484 |
Princ | +0.475 |
Neg logit contributions | |
Toronto | -0.561 |
zik | -0.543 |
uni | -0.532 |
opian | -0.521 |
aunder | -0.493 |
Token | Joined |
Token ID | 16709 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Lie | +4.405 |
Simulation | +3.608 |
parach | +3.461 |
Princ | +3.375 |
Curse | +3.223 |
Neg logit contributions | |
opian | -7.665 |
Toronto | -7.608 |
zik | -7.583 |
aunder | -7.290 |
uni | -7.274 |
Token | December |
Token ID | 3426 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Lie | +4.591 |
Simulation | +4.025 |
parach | +3.852 |
Princ | +3.813 |
Chaff | +3.784 |
Neg logit contributions | |
opian | -5.205 |
zik | -5.150 |
uni | -5.050 |
Toronto | -5.020 |
aunder | -4.828 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
Lie | +2.658 |
Simulation | +2.342 |
Princ | +2.236 |
Chaff | +2.222 |
parach | +2.218 |
Neg logit contributions | |
zik | -2.676 |
opian | -2.627 |
Toronto | -2.621 |
uni | -2.598 |
aunder | -2.438 |
Token | TL |
Token ID | 24811 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
Lie | +5.938 |
Simulation | +5.214 |
parach | +5.178 |
Princ | +5.156 |
Chaff | +4.990 |
Neg logit contributions | |
zik | -5.175 |
opian | -5.047 |
Toronto | -5.015 |
uni | -4.977 |
aunder | -4.661 |
Token | AD |
Token ID | 2885 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
Lie | +7.259 |
Simulation | +6.605 |
parach | +6.575 |
Curse | +6.571 |
Princ | +6.349 |
Neg logit contributions | |
zik | -7.964 |
uni | -7.053 |
opian | -6.976 |
Toronto | -6.897 |
etooth | -6.701 |
Token | T |
Token ID | 51 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Lie | +0.351 |
Simulation | +0.328 |
parach | +0.325 |
itta | +0.310 |
Curse | +0.306 |
Neg logit contributions | |
Toronto | -0.339 |
zik | -0.333 |
uni | -0.320 |
opian | -0.318 |
aunder | -0.311 |
Token | 235 |
Token ID | 28878 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Lie | +3.206 |
Simulation | +2.940 |
parach | +2.931 |
Princ | +2.814 |
Curse | +2.804 |
Neg logit contributions | |
zik | -2.772 |
Toronto | -2.762 |
uni | -2.676 |
opian | -2.641 |
gyn | -2.490 |
Token | 21 |
Token ID | 2481 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
Lie | +2.290 |
Simulation | +2.114 |
parach | +2.007 |
Princ | +1.983 |
Curse | +1.922 |
Neg logit contributions | |
Toronto | -2.758 |
zik | -2.755 |
uni | -2.732 |
opian | -2.713 |
aunder | -2.540 |
Token | Posts |
Token ID | 12043 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Lie | +2.909 |
Simulation | +2.618 |
Princ | +2.321 |
Curse | +2.311 |
parach | +2.297 |
Neg logit contributions | |
opian | -5.047 |
zik | -5.003 |
uni | -4.905 |
Toronto | -4.861 |
aunder | -4.663 |
Token | 's |
Token ID | 338 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Toronto | +3.409 |
zik | +3.293 |
uni | +3.218 |
opian | +3.137 |
aunder | +2.952 |
Neg logit contributions | |
Lie | -3.899 |
parach | -3.701 |
Simulation | -3.634 |
itta | -3.515 |
Princ | -3.455 |
Token | a |
Token ID | 257 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
Lie | +1.164 |
parach | +1.086 |
Simulation | +1.052 |
itta | +0.979 |
Chaff | +0.976 |
Neg logit contributions | |
Toronto | -1.417 |
zik | -1.386 |
uni | -1.359 |
opian | -1.311 |
rall | -1.264 |
Token | marvelous |
Token ID | 43937 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Toronto | +0.289 |
zik | +0.278 |
uni | +0.276 |
opian | +0.267 |
aunder | +0.259 |
Neg logit contributions | |
Lie | -0.224 |
parach | -0.204 |
Simulation | -0.200 |
Princ | -0.187 |
itta | -0.187 |
Token | framework |
Token ID | 9355 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Toronto | +0.999 |
zik | +0.959 |
uni | +0.933 |
opian | +0.918 |
aunder | +0.869 |
Neg logit contributions | |
Lie | -1.018 |
parach | -0.959 |
Simulation | -0.945 |
itta | -0.896 |
Princ | -0.887 |
Token | for |
Token ID | 329 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
Lie | +1.354 |
parach | +1.243 |
Simulation | +1.193 |
Chaff | +1.128 |
Princ | +1.117 |
Neg logit contributions | |
zik | -1.722 |
Toronto | -1.716 |
uni | -1.657 |
opian | -1.620 |
aunder | -1.558 |
Token | modern |
Token ID | 3660 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
Lie | +3.926 |
parach | +3.734 |
Simulation | +3.559 |
Princ | +3.285 |
@@ | +3.154 |
Neg logit contributions | |
zik | -5.250 |
Toronto | -5.173 |
uni | -5.060 |
ridges | -4.808 |
�� | -4.750 |
Token | web |
Token ID | 3992 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Lie | +3.792 |
parach | +3.212 |
Simulation | +2.688 |
Chaff | +2.438 |
Curse | +2.428 |
Neg logit contributions | |
zik | -12.006 |
Toronto | -11.608 |
uni | -11.429 |
ridges | -11.179 |
rall | -11.150 |
Token | applications |
Token ID | 5479 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
Lie | +2.100 |
parach | +1.986 |
Simulation | +1.951 |
Princ | +1.846 |
Chaff | +1.783 |
Neg logit contributions | |
Toronto | -2.451 |
zik | -2.440 |
uni | -2.342 |
opian | -2.255 |
aunder | -2.214 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Lie | +0.153 |
Simulation | +0.141 |
parach | +0.139 |
itta | +0.133 |
Chaff | +0.131 |
Neg logit contributions | |
Toronto | -0.167 |
zik | -0.164 |
uni | -0.160 |
opian | -0.158 |
aunder | -0.148 |
Token | But |
Token ID | 887 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Toronto | +1.476 |
zik | +1.410 |
uni | +1.355 |
opian | +1.295 |
gyn | +1.223 |
Neg logit contributions | |
Lie | -2.090 |
parach | -2.071 |
itta | -1.944 |
Simulation | -1.925 |
actionGroup | -1.903 |
Token | as |
Token ID | 355 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Lie | +5.773 |
parach | +5.168 |
Simulation | +4.983 |
Chaff | +4.469 |
itta | +4.099 |
Neg logit contributions | |
rall | -11.945 |
Toronto | -11.872 |
uni | -11.561 |
ngth | -11.526 |
uckland | -11.365 |
Token | _. |
Token ID | 44807 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Toronto | +0.222 |
zik | +0.215 |
uni | +0.212 |
opian | +0.205 |
aunder | +0.198 |
Neg logit contributions | |
Lie | -0.178 |
parach | -0.167 |
Simulation | -0.163 |
itta | -0.155 |
Chaff | -0.154 |
Token | Exception |
Token ID | 16922 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Toronto | +1.801 |
zik | +1.666 |
uni | +1.635 |
opian | +1.532 |
aunder | +1.455 |
Neg logit contributions | |
Lie | -3.267 |
parach | -3.163 |
Simulation | -3.060 |
itta | -2.984 |
Princ | -2.969 |
Token | . |
Token ID | 13 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
Toronto | +1.062 |
zik | +1.054 |
uni | +1.019 |
opian | +1.013 |
aunder | +0.942 |
Neg logit contributions | |
Lie | -1.049 |
Simulation | -0.967 |
parach | -0.959 |
itta | -0.925 |
Chaff | -0.913 |
Token | Message |
Token ID | 12837 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
Toronto | +0.637 |
zik | +0.612 |
uni | +0.597 |
opian | +0.583 |
aunder | +0.551 |
Neg logit contributions | |
Lie | -0.575 |
parach | -0.548 |
Simulation | -0.528 |
itta | -0.510 |
Princ | -0.502 |
Token | )" |
Token ID | 16725 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Lie | +3.121 |
parach | +2.973 |
Simulation | +2.931 |
itta | +2.840 |
Chaff | +2.801 |
Neg logit contributions | |
Toronto | -2.005 |
zik | -1.925 |
uni | -1.872 |
opian | -1.821 |
aunder | -1.694 |
Token | break |
Token ID | 2270 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
Toronto | +1.436 |
zik | +1.378 |
uni | +1.332 |
opian | +1.294 |
aunder | +1.185 |
Neg logit contributions | |
Lie | -2.505 |
parach | -2.380 |
Simulation | -2.350 |
itta | -2.269 |
Chaff | -2.247 |
Token | } |
Token ID | 1782 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Lie | +5.885 |
Simulation | +5.176 |
parach | +4.736 |
Curse | +4.600 |
Chaff | +4.575 |
Neg logit contributions | |
Toronto | -9.291 |
zik | -9.059 |
uni | -8.908 |
opian | -8.906 |
gyn | -8.670 |
Token | } |
Token ID | 1782 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Lie | +3.092 |
parach | +2.881 |
Simulation | +2.866 |
itta | +2.724 |
Chaff | +2.689 |
Neg logit contributions | |
Toronto | -2.788 |
zik | -2.692 |
uni | -2.634 |
opian | -2.578 |
gyn | -2.423 |
Token | End |
Token ID | 5268 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
Lie | +1.903 |
Simulation | +1.765 |
parach | +1.750 |
itta | +1.637 |
Princ | +1.629 |
Neg logit contributions | |
Toronto | -2.107 |
zik | -2.036 |
uni | -2.008 |
opian | -1.974 |
gyn | -1.862 |
Token | { |
Token ID | 1391 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Lie | +4.629 |
Simulation | +4.306 |
parach | +4.046 |
itta | +3.791 |
Princ | +3.786 |
Neg logit contributions | |
Toronto | -5.774 |
zik | -5.724 |
uni | -5.659 |
opian | -5.523 |
gyn | -5.250 |
Token | Try |
Token ID | 9993 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
Lie | +2.705 |
Simulation | +2.534 |
parach | +2.483 |
Princ | +2.336 |
actionGroup | +2.326 |
Neg logit contributions | |
Toronto | -2.771 |
zik | -2.686 |
uni | -2.654 |
opian | -2.586 |
gyn | -2.471 |
Token | needs |
Token ID | 2476 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Lie | +0.118 |
parach | +0.111 |
Simulation | +0.108 |
itta | +0.105 |
Princ | +0.103 |
Neg logit contributions | |
Toronto | -0.115 |
zik | -0.112 |
uni | -0.110 |
opian | -0.109 |
aunder | -0.102 |
Token | to |
Token ID | 284 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Lie | +3.185 |
parach | +2.980 |
Simulation | +2.877 |
Chaff | +2.765 |
Princ | +2.763 |
Neg logit contributions | |
Toronto | -3.650 |
zik | -3.636 |
uni | -3.535 |
opian | -3.427 |
aunder | -3.274 |
Token | find |
Token ID | 1064 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Lie | +1.331 |
parach | +1.273 |
Simulation | +1.226 |
itta | +1.202 |
Princ | +1.167 |
Neg logit contributions | |
Toronto | -0.992 |
zik | -0.963 |
uni | -0.929 |
opian | -0.916 |
aunder | -0.859 |
Token | its |
Token ID | 663 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
Lie | +1.641 |
parach | +1.537 |
Simulation | +1.491 |
Chaff | +1.435 |
itta | +1.434 |
Neg logit contributions | |
Toronto | -1.623 |
zik | -1.583 |
uni | -1.559 |
opian | -1.513 |
aunder | -1.425 |
Token | two |
Token ID | 734 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Lie | +3.601 |
parach | +3.464 |
Simulation | +3.246 |
Princ | +3.179 |
Chaff | +3.162 |
Neg logit contributions | |
Toronto | -3.336 |
zik | -3.305 |
uni | -3.195 |
opian | -3.101 |
aunder | -2.993 |
Token | leads |
Token ID | 5983 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
Lie | +3.161 |
parach | +3.028 |
Princ | +2.789 |
Simulation | +2.783 |
itta | +2.773 |
Neg logit contributions | |
Toronto | -3.113 |
zik | -3.103 |
uni | -2.976 |
opian | -2.967 |
aunder | -2.814 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
Lie | +5.392 |
parach | +4.987 |
Simulation | +4.683 |
Chaff | +4.585 |
Princ | +4.567 |
Neg logit contributions | |
Toronto | -5.730 |
zik | -5.722 |
uni | -5.596 |
opian | -5.469 |
aunder | -5.083 |
Token | Hun |
Token ID | 5900 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
Lie | +2.677 |
Simulation | +2.414 |
Princ | +2.323 |
parach | +2.315 |
Chaff | +2.271 |
Neg logit contributions | |
zik | -2.758 |
Toronto | -2.726 |
opian | -2.725 |
uni | -2.682 |
aunder | -2.517 |
Token | nam |
Token ID | 7402 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
Lie | +2.296 |
parach | +2.069 |
itta | +2.068 |
Simulation | +1.950 |
itzer | +1.930 |
Neg logit contributions | |
Toronto | -2.721 |
rall | -2.598 |
opian | -2.582 |
zik | -2.547 |
uni | -2.541 |
Token | joins |
Token ID | 15449 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
Lie | +0.672 |
parach | +0.641 |
Simulation | +0.617 |
itta | +0.604 |
Princ | +0.593 |
Neg logit contributions | |
Toronto | -0.537 |
zik | -0.516 |
uni | -0.509 |
opian | -0.498 |
aunder | -0.472 |
Token | a |
Token ID | 257 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
Toronto | +0.210 |
zik | +0.204 |
uni | +0.199 |
opian | +0.196 |
aunder | +0.185 |
Neg logit contributions | |
Lie | -0.215 |
parach | -0.202 |
Simulation | -0.198 |
itta | -0.190 |
Princ | -0.188 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
Toronto | +0.631 |
zik | +0.614 |
uni | +0.594 |
opian | +0.583 |
aunder | +0.551 |
Neg logit contributions | |
Lie | -0.724 |
parach | -0.682 |
Simulation | -0.669 |
itta | -0.646 |
Chaff | -0.635 |
Token | � |
Token ID | 447 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
Lie | +1.499 |
Simulation | +1.361 |
Princ | +1.305 |
parach | +1.299 |
Chaff | +1.294 |
Neg logit contributions | |
Toronto | -1.455 |
zik | -1.449 |
opian | -1.425 |
uni | -1.412 |
aunder | -1.324 |
Token | � |
Token ID | 247 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Lie | +0.627 |
parach | +0.596 |
Simulation | +0.590 |
itta | +0.573 |
Chaff | +0.565 |
Neg logit contributions | |
Toronto | -0.359 |
zik | -0.343 |
uni | -0.333 |
opian | -0.324 |
aunder | -0.300 |
Token | But |
Token ID | 887 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
Lie | +0.900 |
Simulation | +0.817 |
parach | +0.808 |
itta | +0.784 |
Princ | +0.780 |
Neg logit contributions | |
Toronto | -0.858 |
zik | -0.837 |
uni | -0.828 |
opian | -0.823 |
aunder | -0.771 |
Token | I |
Token ID | 314 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Lie | +3.955 |
parach | +3.645 |
Simulation | +3.530 |
itta | +3.459 |
Princ | +3.437 |
Neg logit contributions | |
Toronto | -4.008 |
zik | -3.938 |
uni | -3.917 |
opian | -3.835 |
aunder | -3.748 |
Token | � |
Token ID | 447 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Lie | +0.919 |
parach | +0.857 |
Simulation | +0.850 |
itta | +0.819 |
Princ | +0.804 |
Neg logit contributions | |
Toronto | -0.738 |
zik | -0.703 |
uni | -0.699 |
opian | -0.681 |
aunder | -0.644 |
Token | � |
Token ID | 247 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Lie | +2.308 |
parach | +2.075 |
Simulation | +2.059 |
itta | +2.036 |
Chaff | +2.029 |
Neg logit contributions | |
Toronto | -2.171 |
zik | -2.062 |
opian | -2.035 |
uni | -1.999 |
aunder | -1.903 |
Token | ve |
Token ID | 303 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
Lie | +1.038 |
parach | +0.930 |
Simulation | +0.929 |
itta | +0.903 |
Chaff | +0.887 |
Neg logit contributions | |
Toronto | -1.101 |
zik | -1.044 |
opian | -1.034 |
uni | -1.028 |
aunder | -0.970 |
Token | had |
Token ID | 550 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Toronto | +0.366 |
zik | +0.357 |
uni | +0.351 |
opian | +0.344 |
aunder | +0.324 |
Neg logit contributions | |
Lie | -0.411 |
parach | -0.386 |
Simulation | -0.379 |
itta | -0.366 |
Princ | -0.359 |
Token | the |
Token ID | 262 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
Lie | +1.813 |
parach | +1.683 |
Simulation | +1.639 |
itta | +1.582 |
Princ | +1.567 |
Neg logit contributions | |
Toronto | -1.821 |
zik | -1.778 |
uni | -1.755 |
opian | -1.709 |
aunder | -1.656 |
Token | experience |
Token ID | 1998 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
Lie | +0.408 |
parach | +0.381 |
Simulation | +0.373 |
itta | +0.358 |
Princ | +0.356 |
Neg logit contributions | |
Toronto | -0.404 |
zik | -0.394 |
uni | -0.385 |
opian | -0.379 |
aunder | -0.362 |
Token | be |
Token ID | 307 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
Toronto | +0.569 |
zik | +0.545 |
uni | +0.533 |
opian | +0.518 |
aunder | +0.485 |
Neg logit contributions | |
Lie | -0.784 |
parach | -0.747 |
Simulation | -0.729 |
itta | -0.707 |
Chaff | -0.690 |
Token | involved |
Token ID | 2950 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
Toronto | +0.349 |
zik | +0.341 |
uni | +0.332 |
opian | +0.326 |
aunder | +0.310 |
Neg logit contributions | |
Lie | -0.360 |
parach | -0.345 |
Simulation | -0.332 |
itta | -0.318 |
Princ | -0.315 |
Token | in |
Token ID | 287 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Lie | +2.255 |
parach | +2.144 |
Simulation | +2.085 |
itta | +2.006 |
Princ | +1.973 |
Neg logit contributions | |
Toronto | -2.261 |
zik | -2.198 |
uni | -2.147 |
opian | -2.087 |
aunder | -1.986 |
Token | this |
Token ID | 428 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Lie | +2.064 |
parach | +1.961 |
Simulation | +1.908 |
Princ | +1.804 |
itta | +1.794 |
Neg logit contributions | |
Toronto | -2.140 |
zik | -2.121 |
uni | -2.057 |
opian | -2.007 |
aunder | -1.904 |
Token | story |
Token ID | 1621 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
Lie | +1.011 |
parach | +0.938 |
Simulation | +0.929 |
itta | +0.883 |
Princ | +0.878 |
Neg logit contributions | |
Toronto | -1.033 |
zik | -1.020 |
uni | -0.991 |
opian | -0.974 |
aunder | -0.916 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Lie | +0.172 |
parach | +0.163 |
Simulation | +0.159 |
itta | +0.153 |
Princ | +0.151 |
Neg logit contributions | |
Toronto | -0.163 |
zik | -0.159 |
uni | -0.156 |
opian | -0.150 |
aunder | -0.143 |
Token | The |
Token ID | 383 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Lie | +1.773 |
Simulation | +1.625 |
Princ | +1.547 |
parach | +1.534 |
Chaff | +1.525 |
Neg logit contributions | |
zik | -1.756 |
Toronto | -1.750 |
opian | -1.706 |
uni | -1.703 |
aunder | -1.605 |
Token | fact |
Token ID | 1109 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Lie | +1.464 |
parach | +1.365 |
Simulation | +1.341 |
Princ | +1.284 |
itta | +1.272 |
Neg logit contributions | |
Toronto | -1.394 |
zik | -1.360 |
uni | -1.317 |
opian | -1.287 |
aunder | -1.225 |
Token | that |
Token ID | 326 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Toronto | +2.202 |
zik | +2.085 |
uni | +2.045 |
opian | +2.002 |
aunder | +1.853 |
Neg logit contributions | |
Lie | -3.055 |
parach | -2.929 |
Simulation | -2.913 |
itta | -2.792 |
actionGroup | -2.774 |
Token | he |
Token ID | 339 |
Feature activation | -2.02e-03 |
Pos logit contributions | |
Toronto | +2.296 |
zik | +2.208 |
uni | +2.154 |
opian | +2.102 |
aunder | +1.962 |
Neg logit contributions | |
Lie | -2.993 |
parach | -2.849 |
Simulation | -2.810 |
itta | -2.719 |
Chaff | -2.670 |
Token | 's |
Token ID | 338 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Toronto | +0.016 |
zik | +0.015 |
uni | +0.015 |
opian | +0.014 |
aunder | +0.014 |
Neg logit contributions | |
Lie | -0.017 |
parach | -0.016 |
Simulation | -0.016 |
itta | -0.015 |
Chaff | -0.015 |
Token | # |
Token ID | 1303 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
Lie | +7.533 |
Simulation | +6.726 |
parach | +6.464 |
itta | +6.236 |
Curse | +6.220 |
Neg logit contributions | |
Toronto | -10.736 |
opian | -10.422 |
zik | -10.394 |
uni | -10.201 |
aunder | -9.731 |
Token | 15 |
Token ID | 1314 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
zik | +0.059 |
Toronto | +0.058 |
opian | +0.058 |
uni | +0.057 |
rall | +0.056 |
Neg logit contributions | |
Lie | -0.042 |
parach | -0.039 |
Simulation | -0.038 |
itta | -0.036 |
@@ | -0.035 |
Token | honestly |
Token ID | 12698 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
Lie | +1.716 |
parach | +1.590 |
Simulation | +1.569 |
Chaff | +1.499 |
itta | +1.492 |
Neg logit contributions | |
Toronto | -1.718 |
zik | -1.667 |
uni | -1.641 |
opian | -1.630 |
aunder | -1.523 |
Token | if |
Token ID | 611 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Toronto | +0.341 |
zik | +0.328 |
uni | +0.321 |
opian | +0.314 |
aunder | +0.297 |
Neg logit contributions | |
Lie | -0.393 |
parach | -0.370 |
Simulation | -0.364 |
itta | -0.349 |
Chaff | -0.347 |
Token | we |
Token ID | 356 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
Toronto | +1.712 |
zik | +1.657 |
uni | +1.617 |
opian | +1.579 |
aunder | +1.489 |
Neg logit contributions | |
Lie | -1.930 |
parach | -1.825 |
Simulation | -1.797 |
itta | -1.735 |
Princ | -1.702 |
Token | just |
Token ID | 655 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Lie | +0.269 |
parach | +0.256 |
Simulation | +0.249 |
itta | +0.240 |
Chaff | +0.238 |
Neg logit contributions | |
Toronto | -0.219 |
zik | -0.209 |
uni | -0.204 |
opian | -0.203 |
aunder | -0.188 |
Token | had |
Token ID | 550 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
Lie | +0.965 |
parach | +0.918 |
Simulation | +0.882 |
itta | +0.853 |
Chaff | +0.847 |
Neg logit contributions | |
Toronto | -0.815 |
zik | -0.782 |
opian | -0.769 |
uni | -0.764 |
aunder | -0.704 |
Token | a |
Token ID | 257 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Lie | +0.576 |
parach | +0.544 |
Simulation | +0.531 |
itta | +0.506 |
Chaff | +0.504 |
Neg logit contributions | |
Toronto | -0.559 |
zik | -0.538 |
uni | -0.528 |
opian | -0.522 |
aunder | -0.487 |
Token | sc |
Token ID | 629 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
Lie | +1.053 |
parach | +0.993 |
Simulation | +0.968 |
itta | +0.919 |
Chaff | +0.915 |
Neg logit contributions | |
Toronto | -1.025 |
zik | -0.985 |
uni | -0.962 |
opian | -0.954 |
aunder | -0.905 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
Lie | +2.536 |
parach | +2.386 |
Simulation | +2.372 |
itta | +2.340 |
Princ | +2.193 |
Neg logit contributions | |
Toronto | -2.622 |
zik | -2.559 |
opian | -2.467 |
uni | -2.444 |
aunder | -2.324 |
Token | drama |
Token ID | 10512 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Toronto | +0.409 |
zik | +0.395 |
uni | +0.385 |
opian | +0.378 |
aunder | +0.359 |
Neg logit contributions | |
Lie | -0.446 |
parach | -0.421 |
Simulation | -0.414 |
itta | -0.399 |
Princ | -0.391 |
Token | campaign |
Token ID | 1923 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
Lie | +1.638 |
parach | +1.509 |
Simulation | +1.474 |
Princ | +1.420 |
itta | +1.398 |
Neg logit contributions | |
Toronto | -1.968 |
zik | -1.911 |
uni | -1.903 |
opian | -1.863 |
aunder | -1.789 |
Token | earlier |
Token ID | 2961 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Lie | +2.681 |
parach | +2.535 |
Simulation | +2.451 |
Princ | +2.383 |
itta | +2.379 |
Neg logit contributions | |
Toronto | -2.168 |
zik | -2.086 |
uni | -2.055 |
opian | -2.012 |
aunder | -1.904 |
Token | this |
Token ID | 428 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Lie | +2.034 |
parach | +1.902 |
Simulation | +1.822 |
itta | +1.801 |
Princ | +1.743 |
Neg logit contributions | |
Toronto | -2.409 |
zik | -2.349 |
uni | -2.285 |
opian | -2.237 |
aunder | -2.131 |
Token | week |
Token ID | 1285 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Lie | +1.640 |
parach | +1.523 |
Simulation | +1.481 |
itta | +1.449 |
Princ | +1.417 |
Neg logit contributions | |
Toronto | -1.920 |
zik | -1.875 |
uni | -1.820 |
opian | -1.779 |
aunder | -1.706 |
Token | about |
Token ID | 546 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Lie | +1.698 |
parach | +1.583 |
Simulation | +1.543 |
Princ | +1.498 |
Chaff | +1.498 |
Neg logit contributions | |
Toronto | -1.526 |
zik | -1.483 |
uni | -1.439 |
opian | -1.418 |
aunder | -1.340 |
Token | how |
Token ID | 703 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Lie | +2.729 |
parach | +2.554 |
Simulation | +2.509 |
Princ | +2.393 |
Chaff | +2.388 |
Neg logit contributions | |
Toronto | -2.875 |
zik | -2.813 |
uni | -2.756 |
opian | -2.696 |
aunder | -2.574 |
Token | they |
Token ID | 484 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Lie | +3.350 |
parach | +3.103 |
Simulation | +3.057 |
Chaff | +2.943 |
Princ | +2.938 |
Neg logit contributions | |
Toronto | -3.258 |
zik | -3.192 |
uni | -3.152 |
opian | -3.094 |
aunder | -2.912 |
Token | expected |
Token ID | 2938 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
Lie | +3.683 |
parach | +3.496 |
Simulation | +3.356 |
itta | +3.235 |
Chaff | +3.201 |
Neg logit contributions | |
Toronto | -3.189 |
zik | -3.045 |
uni | -2.956 |
opian | -2.935 |
ridges | -2.729 |
Token | to |
Token ID | 284 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
Lie | +2.408 |
parach | +2.224 |
Simulation | +2.201 |
Princ | +2.125 |
Chaff | +2.107 |
Neg logit contributions | |
Toronto | -2.358 |
zik | -2.312 |
uni | -2.275 |
opian | -2.227 |
aunder | -2.094 |
Token | finish |
Token ID | 5461 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Lie | +2.712 |
parach | +2.524 |
Simulation | +2.421 |
itta | +2.386 |
Curse | +2.325 |
Neg logit contributions | |
Toronto | -2.539 |
zik | -2.484 |
uni | -2.405 |
opian | -2.402 |
aunder | -2.248 |
Token | in |
Token ID | 287 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
Toronto | +1.238 |
zik | +1.200 |
uni | +1.175 |
opian | +1.152 |
aunder | +1.091 |
Neg logit contributions | |
Lie | -1.218 |
parach | -1.143 |
Simulation | -1.124 |
itta | -1.079 |
Chaff | -1.062 |
Token | molecules |
Token ID | 17745 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Lie | +2.473 |
parach | +2.340 |
Simulation | +2.263 |
Princ | +2.140 |
itta | +2.136 |
Neg logit contributions | |
Toronto | -2.709 |
zik | -2.654 |
uni | -2.609 |
opian | -2.546 |
aunder | -2.397 |
Token | absorbed |
Token ID | 19233 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
Lie | +1.513 |
parach | +1.446 |
Simulation | +1.390 |
itta | +1.321 |
Princ | +1.316 |
Neg logit contributions | |
Toronto | -1.571 |
zik | -1.525 |
uni | -1.491 |
opian | -1.473 |
aunder | -1.376 |
Token | by |
Token ID | 416 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
Lie | +0.332 |
parach | +0.315 |
Simulation | +0.306 |
itta | +0.293 |
Chaff | +0.289 |
Neg logit contributions | |
Toronto | -0.325 |
zik | -0.314 |
uni | -0.307 |
opian | -0.299 |
aunder | -0.286 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Lie | +0.478 |
parach | +0.453 |
Simulation | +0.439 |
itta | +0.418 |
Princ | +0.415 |
Neg logit contributions | |
Toronto | -0.508 |
zik | -0.494 |
uni | -0.483 |
opian | -0.474 |
aunder | -0.450 |
Token | vegetation |
Token ID | 28459 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Lie | +0.922 |
parach | +0.872 |
Simulation | +0.843 |
itta | +0.793 |
Princ | +0.790 |
Neg logit contributions | |
Toronto | -1.083 |
zik | -1.049 |
uni | -1.030 |
opian | -1.012 |
aunder | -0.967 |
Token | by |
Token ID | 416 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Toronto | +1.667 |
zik | +1.615 |
uni | +1.579 |
opian | +1.543 |
aunder | +1.456 |
Neg logit contributions | |
Lie | -1.790 |
parach | -1.691 |
Simulation | -1.662 |
itta | -1.600 |
Princ | -1.572 |
Token | molecules |
Token ID | 17745 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Lie | +0.807 |
parach | +0.765 |
Simulation | +0.741 |
itta | +0.704 |
Princ | +0.701 |
Neg logit contributions | |
Toronto | -0.842 |
zik | -0.818 |
uni | -0.794 |
opian | -0.784 |
aunder | -0.741 |
Token | out |
Token ID | 503 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
Lie | +2.361 |
parach | +2.264 |
Simulation | +2.124 |
itta | +2.055 |
Chaff | +2.040 |
Neg logit contributions | |
Toronto | -2.473 |
zik | -2.402 |
uni | -2.350 |
opian | -2.338 |
aunder | -2.187 |
Token | - |
Token ID | 12 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Lie | +2.331 |
parach | +2.200 |
Simulation | +2.155 |
itta | +2.076 |
actionGroup | +2.014 |
Neg logit contributions | |
Toronto | -2.301 |
zik | -2.285 |
uni | -2.152 |
opian | -2.124 |
aunder | -2.054 |
Token | g |
Token ID | 70 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
Toronto | +1.002 |
zik | +0.969 |
uni | +0.947 |
opian | +0.926 |
aunder | +0.872 |
Neg logit contributions | |
Lie | -1.119 |
parach | -1.057 |
Simulation | -1.041 |
itta | -1.003 |
Princ | -0.986 |
Token | assed |
Token ID | 21390 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Toronto | +2.807 |
zik | +2.709 |
uni | +2.617 |
opian | +2.563 |
aunder | +2.392 |
Neg logit contributions | |
Lie | -4.212 |
parach | -4.006 |
Simulation | -3.996 |
Chaff | -3.815 |
itta | -3.815 |
Token | was |
Token ID | 373 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
Toronto | +0.332 |
zik | +0.317 |
uni | +0.311 |
opian | +0.305 |
aunder | +0.286 |
Neg logit contributions | |
Lie | -0.440 |
parach | -0.421 |
Simulation | -0.410 |
itta | -0.399 |
Chaff | -0.391 |
Token | not |
Token ID | 407 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
Lie | +0.683 |
parach | +0.650 |
Simulation | +0.628 |
Chaff | +0.606 |
itta | +0.600 |
Neg logit contributions | |
Toronto | -0.575 |
zik | -0.561 |
uni | -0.544 |
opian | -0.535 |
aunder | -0.506 |
Token | known |
Token ID | 1900 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
Lie | +0.440 |
parach | +0.417 |
Simulation | +0.401 |
Chaff | +0.387 |
itta | +0.385 |
Neg logit contributions | |
Toronto | -0.388 |
zik | -0.376 |
uni | -0.367 |
opian | -0.364 |
aunder | -0.345 |
Token | at |
Token ID | 379 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
Lie | +0.374 |
parach | +0.352 |
Simulation | +0.343 |
itta | +0.333 |
Chaff | +0.328 |
Neg logit contributions | |
Toronto | -0.333 |
zik | -0.325 |
uni | -0.311 |
opian | -0.307 |
aunder | -0.291 |
Token | the |
Token ID | 262 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
Toronto | +0.137 |
zik | +0.133 |
uni | +0.130 |
opian | +0.127 |
aunder | +0.121 |
Neg logit contributions | |
Lie | -0.131 |
parach | -0.123 |
Simulation | -0.121 |
itta | -0.116 |
Chaff | -0.114 |
Token | time |
Token ID | 640 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
Lie | +0.625 |
parach | +0.590 |
Simulation | +0.580 |
Chaff | +0.557 |
Princ | +0.545 |
Neg logit contributions | |
Toronto | -0.592 |
zik | -0.578 |
uni | -0.563 |
opian | -0.545 |
aunder | -0.517 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Lie | +0.455 |
parach | +0.432 |
Simulation | +0.426 |
itta | +0.411 |
Princ | +0.404 |
Neg logit contributions | |
Toronto | -0.361 |
zik | -0.347 |
uni | -0.340 |
opian | -0.331 |
aunder | -0.311 |
Token | several |
Token ID | 1811 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
Lie | +1.363 |
parach | +1.293 |
Simulation | +1.258 |
Chaff | +1.198 |
itta | +1.197 |
Neg logit contributions | |
Toronto | -1.418 |
zik | -1.369 |
uni | -1.336 |
opian | -1.327 |
aunder | -1.243 |
Token | changes |
Token ID | 2458 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Lie | +0.453 |
parach | +0.437 |
Simulation | +0.421 |
Chaff | +0.404 |
itta | +0.401 |
Neg logit contributions | |
Toronto | -0.398 |
zik | -0.384 |
uni | -0.376 |
opian | -0.370 |
aunder | -0.347 |
Token | in |
Token ID | 287 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
Lie | +1.042 |
parach | +0.985 |
Simulation | +0.957 |
itta | +0.932 |
Chaff | +0.919 |
Neg logit contributions | |
Toronto | -0.845 |
zik | -0.817 |
uni | -0.788 |
opian | -0.768 |
aunder | -0.728 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Lie | +0.442 |
parach | +0.420 |
Simulation | +0.409 |
itta | +0.393 |
Chaff | +0.387 |
Neg logit contributions | |
Toronto | -0.457 |
zik | -0.442 |
uni | -0.433 |
opian | -0.423 |
aunder | -0.403 |
Token | fire |
Token ID | 2046 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
Lie | +1.992 |
parach | +1.924 |
Simulation | +1.806 |
Chaff | +1.771 |
itta | +1.732 |
Neg logit contributions | |
Toronto | -1.915 |
zik | -1.852 |
uni | -1.809 |
opian | -1.793 |
aunder | -1.685 |
Token | doors |
Token ID | 8215 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Lie | +4.360 |
parach | +4.262 |
Simulation | +4.009 |
itta | +3.946 |
Chaff | +3.879 |
Neg logit contributions | |
Toronto | -3.510 |
zik | -3.377 |
uni | -3.292 |
opian | -3.257 |
aunder | -3.154 |
Token | or |
Token ID | 393 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
Lie | +1.509 |
parach | +1.438 |
Simulation | +1.372 |
itta | +1.346 |
Chaff | +1.338 |
Neg logit contributions | |
Toronto | -1.406 |
zik | -1.363 |
uni | -1.326 |
opian | -1.299 |
aunder | -1.232 |
Token | other |
Token ID | 584 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
Lie | +0.134 |
parach | +0.129 |
Simulation | +0.123 |
itta | +0.119 |
Chaff | +0.119 |
Neg logit contributions | |
Toronto | -0.120 |
zik | -0.116 |
uni | -0.114 |
opian | -0.111 |
aunder | -0.105 |
Token | containment |
Token ID | 37149 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Toronto | +0.187 |
zik | +0.182 |
uni | +0.177 |
opian | +0.173 |
aunder | +0.166 |
Neg logit contributions | |
Lie | -0.202 |
parach | -0.195 |
Simulation | -0.184 |
itta | -0.179 |
Chaff | -0.178 |
Token | structures |
Token ID | 8573 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
Toronto | +1.496 |
zik | +1.447 |
uni | +1.422 |
opian | +1.382 |
aunder | +1.310 |
Neg logit contributions | |
Lie | -1.728 |
parach | -1.643 |
Simulation | -1.601 |
itta | -1.547 |
Chaff | -1.525 |
Token | , |
Token ID | 11 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Toronto | +0.339 |
zik | +0.327 |
uni | +0.319 |
opian | +0.312 |
aunder | +0.293 |
Neg logit contributions | |
Lie | -0.433 |
parach | -0.411 |
Simulation | -0.398 |
itta | -0.388 |
Chaff | -0.384 |
Token | when |
Token ID | 618 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Lie | +1.624 |
parach | +1.562 |
Simulation | +1.480 |
Chaff | +1.438 |
itta | +1.423 |
Neg logit contributions | |
Toronto | -1.588 |
zik | -1.545 |
uni | -1.518 |
opian | -1.490 |
aunder | -1.402 |
Token | properly |
Token ID | 6105 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Lie | +1.666 |
parach | +1.609 |
Simulation | +1.506 |
Chaff | +1.479 |
itta | +1.461 |
Neg logit contributions | |
Toronto | -1.605 |
zik | -1.592 |
uni | -1.543 |
opian | -1.517 |
gyn | -1.439 |
Token | installed |
Token ID | 6589 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Toronto | +0.996 |
zik | +0.965 |
uni | +0.945 |
opian | +0.927 |
aunder | +0.873 |
Neg logit contributions | |
Lie | -1.074 |
parach | -1.020 |
Simulation | -0.996 |
itta | -0.960 |
Chaff | -0.948 |
Token | , |
Token ID | 11 |
Feature activation | +9.15e-02 |
Pos logit contributions | |
Toronto | +0.757 |
zik | +0.727 |
uni | +0.714 |
opian | +0.694 |
aunder | +0.651 |
Neg logit contributions | |
Lie | -1.007 |
parach | -0.956 |
Simulation | -0.947 |
itta | -0.912 |
Princ | -0.898 |
Token | dirty |
Token ID | 11841 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Lie | +0.139 |
parach | +0.131 |
Simulation | +0.128 |
itta | +0.123 |
Chaff | +0.121 |
Neg logit contributions | |
Toronto | -0.136 |
zik | -0.132 |
uni | -0.128 |
opian | -0.124 |
aunder | -0.119 |
Token | energy |
Token ID | 2568 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Toronto | +2.488 |
zik | +2.398 |
uni | +2.338 |
opian | +2.282 |
aunder | +2.137 |
Neg logit contributions | |
Lie | -3.218 |
parach | -3.054 |
Simulation | -3.009 |
itta | -2.908 |
Chaff | -2.862 |
Token | . |
Token ID | 13 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
Toronto | +0.983 |
zik | +0.954 |
uni | +0.930 |
opian | +0.908 |
aunder | +0.855 |
Neg logit contributions | |
Lie | -1.096 |
parach | -1.032 |
Simulation | -1.015 |
itta | -0.977 |
Princ | -0.961 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Lie | +0.551 |
Simulation | +0.508 |
parach | +0.490 |
Princ | +0.478 |
Chaff | +0.476 |
Neg logit contributions | |
Toronto | -0.542 |
zik | -0.538 |
uni | -0.521 |
opian | -0.520 |
aunder | -0.488 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Toronto | +0.935 |
zik | +0.931 |
uni | +0.902 |
opian | +0.897 |
aunder | +0.855 |
Neg logit contributions | |
Lie | -0.887 |
parach | -0.809 |
Simulation | -0.806 |
itta | -0.771 |
Chaff | -0.760 |
Token | >> |
Token ID | 4211 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
Toronto | +1.213 |
zik | +1.167 |
uni | +1.142 |
opian | +1.113 |
aunder | +1.048 |
Neg logit contributions | |
Lie | -1.409 |
parach | -1.337 |
Simulation | -1.315 |
itta | -1.265 |
Chaff | -1.248 |
Token | Take |
Token ID | 7214 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Lie | +0.334 |
Simulation | +0.307 |
parach | +0.305 |
itta | +0.293 |
Princ | +0.290 |
Neg logit contributions | |
Toronto | -0.323 |
zik | -0.318 |
uni | -0.309 |
opian | -0.307 |
aunder | -0.287 |
Token | action |
Token ID | 2223 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Lie | +1.456 |
Simulation | +1.340 |
parach | +1.337 |
itta | +1.244 |
Princ | +1.227 |
Neg logit contributions | |
Toronto | -1.924 |
zik | -1.870 |
uni | -1.829 |
opian | -1.819 |
aunder | -1.742 |
Token | : |
Token ID | 25 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Lie | +0.970 |
parach | +0.891 |
Simulation | +0.883 |
itta | +0.850 |
Princ | +0.844 |
Neg logit contributions | |
Toronto | -0.839 |
zik | -0.827 |
uni | -0.799 |
opian | -0.775 |
aunder | -0.738 |
Token | tell |
Token ID | 1560 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
Toronto | +1.002 |
zik | +0.973 |
uni | +0.947 |
opian | +0.929 |
aunder | +0.871 |
Neg logit contributions | |
Lie | -1.155 |
parach | -1.080 |
Simulation | -1.069 |
itta | -1.026 |
Chaff | -1.013 |
Token | Shell |
Token ID | 17537 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
Lie | +3.767 |
parach | +3.326 |
Simulation | +3.288 |
Chaff | +3.212 |
itta | +3.150 |
Neg logit contributions | |
Toronto | -4.265 |
zik | -4.254 |
opian | -4.105 |
uni | -3.992 |
aunder | -3.852 |
Token | skip |
Token ID | 14267 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Lie | +2.396 |
parach | +2.274 |
Simulation | +2.224 |
itta | +2.109 |
Chaff | +2.098 |
Neg logit contributions | |
Toronto | -2.285 |
zik | -2.197 |
uni | -2.125 |
opian | -2.099 |
aunder | -1.994 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Lie | +1.258 |
parach | +1.190 |
Simulation | +1.163 |
itta | +1.113 |
Chaff | +1.098 |
Neg logit contributions | |
Toronto | -1.202 |
zik | -1.154 |
uni | -1.130 |
opian | -1.104 |
aunder | -1.052 |
Token | Hop |
Token ID | 9996 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Lie | +1.378 |
Simulation | +1.271 |
parach | +1.238 |
Princ | +1.195 |
Chaff | +1.193 |
Neg logit contributions | |
Toronto | -1.310 |
zik | -1.276 |
opian | -1.254 |
uni | -1.242 |
aunder | -1.174 |
Token | ing |
Token ID | 278 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
Lie | +1.235 |
parach | +1.168 |
Simulation | +1.150 |
itta | +1.103 |
Chaff | +1.083 |
Neg logit contributions | |
Toronto | -1.230 |
zik | -1.195 |
uni | -1.152 |
opian | -1.128 |
aunder | -1.099 |
Token | to |
Token ID | 284 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
Toronto | +0.366 |
zik | +0.355 |
uni | +0.347 |
opian | +0.340 |
aunder | +0.322 |
Neg logit contributions | |
Lie | -0.369 |
parach | -0.347 |
Simulation | -0.342 |
itta | -0.328 |
Princ | -0.322 |
Token | have |
Token ID | 423 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Lie | +0.573 |
parach | +0.542 |
Simulation | +0.529 |
itta | +0.510 |
Princ | +0.497 |
Neg logit contributions | |
Toronto | -0.472 |
zik | -0.453 |
uni | -0.441 |
opian | -0.437 |
aunder | -0.414 |
Token | a |
Token ID | 257 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
Toronto | +1.756 |
zik | +1.700 |
uni | +1.661 |
opian | +1.627 |
aunder | +1.535 |
Neg logit contributions | |
Lie | -1.854 |
parach | -1.750 |
Simulation | -1.721 |
itta | -1.655 |
Chaff | -1.627 |
Token | run |
Token ID | 1057 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Lie | +0.433 |
parach | +0.407 |
Simulation | +0.401 |
itta | +0.377 |
Princ | +0.376 |
Neg logit contributions | |
Toronto | -0.410 |
zik | -0.396 |
uni | -0.384 |
opian | -0.382 |
aunder | -0.363 |
Token | of |
Token ID | 286 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
Lie | +1.309 |
parach | +1.235 |
Simulation | +1.223 |
itta | +1.182 |
Princ | +1.141 |
Neg logit contributions | |
Toronto | -1.143 |
zik | -1.107 |
uni | -1.070 |
opian | -1.056 |
aunder | -1.009 |
Token | this |
Token ID | 428 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Toronto | +1.929 |
zik | +1.868 |
uni | +1.824 |
opian | +1.789 |
aunder | +1.693 |
Neg logit contributions | |
Lie | -1.985 |
parach | -1.871 |
Simulation | -1.840 |
itta | -1.763 |
Chaff | -1.736 |
Token | submitted |
Token ID | 8948 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Toronto | +1.943 |
zik | +1.884 |
uni | +1.845 |
opian | +1.809 |
aunder | +1.713 |
Neg logit contributions | |
Lie | -2.010 |
parach | -1.894 |
Simulation | -1.864 |
itta | -1.785 |
Princ | -1.758 |
Token | above |
Token ID | 2029 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Lie | +0.310 |
parach | +0.293 |
Simulation | +0.288 |
itta | +0.278 |
Princ | +0.271 |
Neg logit contributions | |
Toronto | -0.334 |
zik | -0.322 |
uni | -0.312 |
opian | -0.308 |
aunder | -0.294 |
Token | the |
Token ID | 262 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Lie | +1.552 |
parach | +1.449 |
Simulation | +1.393 |
Princ | +1.335 |
Chaff | +1.327 |
Neg logit contributions | |
Toronto | -1.824 |
zik | -1.793 |
uni | -1.743 |
opian | -1.723 |
gyn | -1.636 |
Token | Earth |
Token ID | 3668 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
Lie | +1.070 |
parach | +1.012 |
Simulation | +0.969 |
Princ | +0.941 |
Chaff | +0.922 |
Neg logit contributions | |
Toronto | -1.162 |
zik | -1.138 |
uni | -1.111 |
opian | -1.094 |
gyn | -1.044 |
Token | 's |
Token ID | 338 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Toronto | +0.386 |
zik | +0.375 |
uni | +0.366 |
opian | +0.358 |
aunder | +0.334 |
Neg logit contributions | |
Lie | -0.446 |
parach | -0.424 |
Simulation | -0.416 |
itta | -0.404 |
Chaff | -0.396 |
Token | surface |
Token ID | 4417 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Toronto | +1.171 |
zik | +1.143 |
uni | +1.116 |
opian | +1.095 |
aunder | +1.039 |
Neg logit contributions | |
Lie | -1.087 |
parach | -1.025 |
Simulation | -1.000 |
itta | -0.957 |
Chaff | -0.945 |
Token |
|
Token ID | 198 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
Toronto | +0.865 |
zik | +0.835 |
uni | +0.818 |
opian | +0.798 |
aunder | +0.751 |
Neg logit contributions | |
Lie | -0.977 |
parach | -0.924 |
Simulation | -0.909 |
itta | -0.879 |
Chaff | -0.864 |
Token |
|
Token ID | 198 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
Toronto | +5.670 |
zik | +5.088 |
uni | +5.083 |
opian | +4.718 |
gyn | +4.519 |
Neg logit contributions | |
Lie | -7.745 |
parach | -7.703 |
Simulation | -7.380 |
itta | -7.369 |
disg | -7.330 |
Token | The |
Token ID | 464 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Toronto | +5.174 |
uni | +4.696 |
zik | +4.648 |
opian | +4.344 |
gyn | +4.173 |
Neg logit contributions | |
Lie | -6.009 |
parach | -5.747 |
Simulation | -5.697 |
actionGroup | -5.608 |
itta | -5.496 |
Token | European |
Token ID | 3427 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Toronto | +1.293 |
zik | +1.251 |
uni | +1.224 |
opian | +1.197 |
aunder | +1.128 |
Neg logit contributions | |
Lie | -1.407 |
parach | -1.327 |
Simulation | -1.308 |
itta | -1.261 |
Chaff | -1.238 |
Token | Space |
Token ID | 4687 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Toronto | +0.883 |
zik | +0.850 |
uni | +0.829 |
opian | +0.808 |
aunder | +0.755 |
Neg logit contributions | |
Lie | -1.207 |
parach | -1.146 |
Simulation | -1.130 |
itta | -1.094 |
Chaff | -1.076 |
Token | Agency |
Token ID | 7732 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Lie | +1.146 |
parach | +1.061 |
Simulation | +1.059 |
Princ | +1.010 |
itta | +0.983 |
Neg logit contributions | |
Toronto | -1.270 |
zik | -1.210 |
opian | -1.183 |
uni | -1.178 |
aunder | -1.111 |
Token | hou |
Token ID | 15710 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Lie | +0.929 |
parach | +0.868 |
Simulation | +0.846 |
itta | +0.821 |
Chaff | +0.805 |
Neg logit contributions | |
Toronto | -1.088 |
zik | -1.046 |
uni | -1.025 |
opian | -1.023 |
aunder | -0.973 |
Token | B |
Token ID | 347 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Toronto | +2.533 |
zik | +2.453 |
uni | +2.401 |
opian | +2.349 |
aunder | +2.215 |
Neg logit contributions | |
Lie | -2.472 |
parach | -2.332 |
Simulation | -2.282 |
itta | -2.208 |
Chaff | -2.161 |
Token | unk |
Token ID | 2954 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
Toronto | +1.725 |
zik | +1.661 |
uni | +1.617 |
opian | +1.580 |
aunder | +1.484 |
Neg logit contributions | |
Lie | -2.189 |
parach | -2.072 |
Simulation | -2.044 |
itta | -1.981 |
Princ | -1.944 |
Token | a |
Token ID | 64 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Lie | +0.270 |
parach | +0.257 |
Simulation | +0.254 |
itta | +0.246 |
Chaff | +0.241 |
Neg logit contributions | |
Toronto | -0.174 |
zik | -0.168 |
uni | -0.159 |
opian | -0.157 |
aunder | -0.148 |
Token | Shin |
Token ID | 11466 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
Toronto | +2.488 |
zik | +2.411 |
uni | +2.369 |
opian | +2.307 |
aunder | +2.169 |
Neg logit contributions | |
Lie | -2.604 |
parach | -2.469 |
Simulation | -2.414 |
itta | -2.333 |
Chaff | -2.298 |
Token | p |
Token ID | 79 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
Toronto | +0.637 |
zik | +0.613 |
uni | +0.599 |
opian | +0.587 |
aunder | +0.556 |
Neg logit contributions | |
Lie | -0.692 |
parach | -0.653 |
Simulation | -0.644 |
itta | -0.619 |
Princ | -0.608 |
Token | ou |
Token ID | 280 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
uni | +4.276 |
Toronto | +4.219 |
zik | +4.072 |
opian | +3.921 |
itor | +3.481 |
Neg logit contributions | |
Lie | -8.697 |
parach | -8.464 |
Simulation | -8.207 |
actionGroup | -8.151 |
Chaff | -7.982 |
Token | ( |
Token ID | 357 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Toronto | +1.611 |
zik | +1.562 |
uni | +1.527 |
opian | +1.490 |
aunder | +1.405 |
Neg logit contributions | |
Lie | -1.710 |
parach | -1.616 |
Simulation | -1.587 |
itta | -1.531 |
Chaff | -1.504 |
Token | Word |
Token ID | 9678 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
Toronto | +1.841 |
zik | +1.776 |
uni | +1.740 |
opian | +1.700 |
aunder | +1.604 |
Neg logit contributions | |
Lie | -1.927 |
parach | -1.821 |
Simulation | -1.788 |
itta | -1.721 |
Chaff | -1.692 |
Token | 's |
Token ID | 338 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
Lie | +0.096 |
parach | +0.089 |
Simulation | +0.089 |
itta | +0.085 |
Princ | +0.084 |
Neg logit contributions | |
Toronto | -0.093 |
zik | -0.090 |
uni | -0.088 |
opian | -0.086 |
aunder | -0.082 |
Token | End |
Token ID | 5268 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
Lie | +0.141 |
Simulation | +0.130 |
parach | +0.129 |
itta | +0.124 |
Chaff | +0.122 |
Neg logit contributions | |
Toronto | -0.139 |
zik | -0.135 |
uni | -0.132 |
opian | -0.130 |
gyn | -0.122 |
Token | [ |
Token ID | 58 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Toronto | +2.959 |
zik | +2.797 |
uni | +2.777 |
opian | +2.660 |
aunder | +2.553 |
Neg logit contributions | |
Lie | -3.937 |
parach | -3.772 |
Simulation | -3.719 |
itta | -3.596 |
Princ | -3.524 |
Token | step |
Token ID | 9662 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Toronto | +2.942 |
uni | +2.793 |
zik | +2.783 |
opian | +2.657 |
aunder | +2.479 |
Neg logit contributions | |
Lie | -3.915 |
parach | -3.759 |
Simulation | -3.710 |
itta | -3.594 |
Chaff | -3.546 |
Token | New |
Token ID | 3791 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
Lie | +1.314 |
parach | +1.220 |
Simulation | +1.211 |
itta | +1.164 |
Chaff | +1.145 |
Neg logit contributions | |
Toronto | -1.212 |
zik | -1.205 |
uni | -1.161 |
opian | -1.155 |
aunder | -1.077 |
Token | ][ |
Token ID | 7131 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Toronto | +2.812 |
uni | +2.663 |
zik | +2.586 |
opian | +2.386 |
aunder | +2.273 |
Neg logit contributions | |
Lie | -5.682 |
parach | -5.618 |
Simulation | -5.496 |
itta | -5.413 |
Chaff | -5.256 |
Token | [ |
Token ID | 58 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Toronto | +2.216 |
zik | +2.123 |
uni | +2.093 |
opian | +2.027 |
aunder | +1.897 |
Neg logit contributions | |
Lie | -2.752 |
parach | -2.619 |
Simulation | -2.585 |
itta | -2.497 |
Chaff | -2.457 |
Token | i |
Token ID | 72 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
Toronto | +2.080 |
zik | +1.994 |
uni | +1.965 |
opian | +1.902 |
aunder | +1.784 |
Neg logit contributions | |
Lie | -2.646 |
parach | -2.522 |
Simulation | -2.482 |
itta | -2.404 |
Chaff | -2.359 |
Token | ]] |
Token ID | 11907 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Toronto | +4.412 |
uni | +4.149 |
zik | +4.055 |
opian | +3.888 |
aunder | +3.717 |
Neg logit contributions | |
Lie | -6.977 |
parach | -6.852 |
Simulation | -6.729 |
itta | -6.517 |
Princ | -6.387 |
Token | ] |
Token ID | 60 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Toronto | +0.890 |
zik | +0.853 |
uni | +0.830 |
opian | +0.806 |
aunder | +0.747 |
Neg logit contributions | |
Lie | -1.436 |
parach | -1.369 |
Simulation | -1.351 |
itta | -1.310 |
Princ | -1.291 |
Token | = |
Token ID | 796 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
Toronto | +1.283 |
zik | +1.233 |
uni | +1.203 |
opian | +1.170 |
aunder | +1.096 |
Neg logit contributions | |
Lie | -1.742 |
parach | -1.657 |
Simulation | -1.633 |
itta | -1.581 |
Princ | -1.555 |
Token | " |
Token ID | 366 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Toronto | +0.138 |
zik | +0.134 |
uni | +0.130 |
opian | +0.128 |
gyn | +0.121 |
Neg logit contributions | |
Lie | -0.144 |
parach | -0.134 |
Simulation | -0.133 |
Princ | -0.126 |
itta | -0.125 |
Token | S |
Token ID | 50 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Toronto | +1.947 |
zik | +1.884 |
uni | +1.842 |
opian | +1.802 |
aunder | +1.700 |
Neg logit contributions | |
Lie | -2.086 |
parach | -1.969 |
Simulation | -1.937 |
itta | -1.865 |
Princ | -1.833 |
Token | matchup |
Token ID | 18406 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
Toronto | +1.997 |
zik | +1.933 |
uni | +1.884 |
opian | +1.850 |
aunder | +1.744 |
Neg logit contributions | |
Lie | -2.109 |
parach | -1.992 |
Simulation | -1.962 |
itta | -1.890 |
Princ | -1.856 |
Token | between |
Token ID | 1022 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
Toronto | +0.229 |
zik | +0.222 |
uni | +0.220 |
opian | +0.214 |
aunder | +0.205 |
Neg logit contributions | |
Lie | -0.172 |
parach | -0.160 |
Simulation | -0.156 |
itta | -0.149 |
Chaff | -0.148 |
Token | Donald |
Token ID | 3759 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
Toronto | +0.409 |
zik | +0.397 |
uni | +0.389 |
opian | +0.379 |
aunder | +0.357 |
Neg logit contributions | |
Lie | -0.454 |
parach | -0.426 |
Simulation | -0.420 |
itta | -0.401 |
Chaff | -0.401 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
Lie | +0.603 |
parach | +0.583 |
Simulation | +0.575 |
itta | +0.556 |
actionGroup | +0.550 |
Neg logit contributions | |
Toronto | -0.338 |
zik | -0.325 |
uni | -0.313 |
opian | -0.304 |
gyn | -0.282 |
Token | Donald |
Token ID | 3759 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
Toronto | +0.101 |
zik | +0.097 |
uni | +0.094 |
opian | +0.092 |
gyn | +0.088 |
Neg logit contributions | |
Lie | -0.122 |
parach | -0.115 |
Simulation | -0.115 |
itta | -0.110 |
actionGroup | -0.110 |
Token | John |
Token ID | 1757 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Toronto | +3.976 |
zik | +3.617 |
uni | +3.445 |
opian | +3.361 |
gyn | +3.068 |
Neg logit contributions | |
Lie | -6.786 |
parach | -6.676 |
Simulation | -6.497 |
itta | -6.405 |
Princ | -6.212 |
Token | Trump |
Token ID | 1301 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
Toronto | +4.597 |
zik | +4.304 |
opian | +3.835 |
aunder | +3.739 |
uni | +3.694 |
Neg logit contributions | |
parach | -11.730 |
Lie | -11.699 |
Simulation | -11.554 |
itta | -11.407 |
actionGroup | -11.371 |
Token | House |
Token ID | 18102 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
Toronto | +4.146 |
zik | +3.833 |
uni | +3.674 |
opian | +3.607 |
gyn | +3.366 |
Neg logit contributions | |
Lie | -6.295 |
parach | -5.985 |
Simulation | -5.984 |
itta | -5.770 |
actionGroup | -5.739 |
Token | committee |
Token ID | 5583 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Toronto | +2.860 |
zik | +2.658 |
uni | +2.545 |
opian | +2.481 |
aunder | +2.155 |
Neg logit contributions | |
Lie | -7.899 |
parach | -7.621 |
Simulation | -7.605 |
itta | -7.526 |
actionGroup | -7.372 |
Token | believes |
Token ID | 5804 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
Toronto | +2.163 |
zik | +2.104 |
uni | +2.024 |
opian | +2.004 |
gyn | +1.908 |
Neg logit contributions | |
Lie | -2.094 |
parach | -1.991 |
Simulation | -1.972 |
itta | -1.911 |
actionGroup | -1.908 |
Token | it |
Token ID | 340 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Toronto | +0.237 |
zik | +0.224 |
uni | +0.215 |
opian | +0.208 |
aunder | +0.195 |
Neg logit contributions | |
Lie | -0.431 |
parach | -0.409 |
Simulation | -0.409 |
itta | -0.397 |
Princ | -0.390 |
Token | ial |
Token ID | 498 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
Toronto | +3.186 |
zik | +3.092 |
uni | +3.017 |
opian | +2.963 |
aunder | +2.871 |
Neg logit contributions | |
Lie | -2.171 |
parach | -1.979 |
Simulation | -1.954 |
itta | -1.860 |
Princ | -1.798 |
Token | ets |
Token ID | 1039 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
Toronto | +0.516 |
zik | +0.499 |
uni | +0.485 |
opian | +0.481 |
aunder | +0.460 |
Neg logit contributions | |
Lie | -0.427 |
parach | -0.397 |
Simulation | -0.393 |
itta | -0.387 |
Chaff | -0.367 |
Token | � |
Token ID | 447 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Toronto | +0.419 |
zik | +0.406 |
uni | +0.395 |
opian | +0.389 |
aunder | +0.365 |
Neg logit contributions | |
Lie | -0.512 |
parach | -0.480 |
Simulation | -0.474 |
itta | -0.456 |
Princ | -0.451 |
Token | � |
Token ID | 247 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
Lie | +1.079 |
parach | +0.988 |
Simulation | +0.986 |
itta | +0.960 |
Chaff | +0.933 |
Neg logit contributions | |
Toronto | -1.093 |
zik | -1.035 |
uni | -1.010 |
opian | -1.006 |
aunder | -0.955 |
Token | st |
Token ID | 336 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Lie | +0.457 |
parach | +0.426 |
Simulation | +0.420 |
itta | +0.402 |
Princ | +0.395 |
Neg logit contributions | |
Toronto | -0.516 |
zik | -0.500 |
uni | -0.491 |
opian | -0.483 |
aunder | -0.458 |
Token | up |
Token ID | 929 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
Toronto | +0.950 |
zik | +0.917 |
uni | +0.892 |
opian | +0.877 |
aunder | +0.821 |
Neg logit contributions | |
Lie | -1.061 |
parach | -0.997 |
Simulation | -0.981 |
itta | -0.953 |
Princ | -0.929 |
Token | end |
Token ID | 437 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
Toronto | +2.848 |
uni | +2.798 |
zik | +2.592 |
opian | +2.441 |
gyn | +2.079 |
Neg logit contributions | |
Lie | -11.271 |
parach | -10.953 |
Simulation | -10.716 |
actionGroup | -10.508 |
Chaff | -10.499 |
Token | ous |
Token ID | 516 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
Toronto | +2.577 |
zik | +2.491 |
uni | +2.411 |
opian | +2.364 |
aunder | +2.199 |
Neg logit contributions | |
Lie | -3.676 |
parach | -3.511 |
Simulation | -3.453 |
itta | -3.348 |
Princ | -3.288 |
Token | imaging |
Token ID | 19560 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Toronto | +3.436 |
zik | +3.318 |
uni | +3.243 |
opian | +3.138 |
gyn | +2.952 |
Neg logit contributions | |
Lie | -3.900 |
parach | -3.717 |
Simulation | -3.636 |
itta | -3.527 |
Chaff | -3.467 |
Token | , |
Token ID | 11 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
Lie | +1.046 |
parach | +0.984 |
Simulation | +0.969 |
itta | +0.923 |
Princ | +0.915 |
Neg logit contributions | |
Toronto | -0.945 |
zik | -0.923 |
uni | -0.899 |
opian | -0.894 |
aunder | -0.860 |
Token | gorgeous |
Token ID | 18857 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Lie | +0.252 |
parach | +0.236 |
Simulation | +0.233 |
itta | +0.222 |
Princ | +0.220 |
Neg logit contributions | |
Toronto | -0.245 |
zik | -0.237 |
uni | -0.232 |
opian | -0.229 |
aunder | -0.217 |