Token | |
Token ID | 3907 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
owitz | +1.095 |
chio | +0.939 |
illance | +0.937 |
edi | +0.908 |
ilon | +0.876 |
Neg logit contributions | |
anmar | -1.108 |
mil | -1.041 |
reluct | -1.036 |
fabrication | -1.007 |
interstitial | -0.999 |
Token | on |
Token ID | 261 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
anmar | +3.263 |
mil | +3.101 |
hub | +2.940 |
reluct | +2.915 |
fabrication | +2.899 |
Neg logit contributions | |
owitz | -4.502 |
illance | -3.985 |
chio | -3.939 |
edi | -3.768 |
oulos | -3.755 |
Token | to |
Token ID | 284 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
owitz | +3.644 |
chio | +3.226 |
illance | +3.105 |
edi | +3.069 |
ilon | +2.968 |
Neg logit contributions | |
anmar | -2.912 |
mil | -2.663 |
reluct | -2.613 |
interstitial | -2.578 |
fabrication | -2.527 |
Token | this |
Token ID | 428 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
owitz | +0.382 |
chio | +0.329 |
illance | +0.324 |
edi | +0.317 |
oulos | +0.309 |
Neg logit contributions | |
anmar | -0.335 |
mil | -0.313 |
reluct | -0.304 |
fabrication | -0.298 |
hub | -0.295 |
Token | pres |
Token ID | 906 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
owitz | +0.700 |
chio | +0.612 |
illance | +0.610 |
edi | +0.591 |
oulos | +0.577 |
Neg logit contributions | |
anmar | -0.520 |
mil | -0.485 |
reluct | -0.463 |
interstitial | -0.453 |
vg | -0.452 |
Token | |
Token ID | 3907 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
anmar | +0.038 |
reluct | +0.036 |
mil | +0.036 |
fabrication | +0.035 |
hub | +0.035 |
Neg logit contributions | |
owitz | -0.042 |
chio | -0.036 |
illance | -0.036 |
edi | -0.035 |
ilon | -0.033 |
Token | id |
Token ID | 312 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
mil | +7.413 |
anmar | +7.092 |
vg | +6.645 |
hub | +6.381 |
interstitial | +6.270 |
Neg logit contributions | |
owitz | -9.245 |
illance | -8.087 |
chio | -7.953 |
oulos | -7.699 |
™: | -7.460 |
Token | |
Token ID | 3907 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
anmar | +3.296 |
mil | +3.191 |
hub | +3.044 |
fabrication | +2.964 |
vg | +2.929 |
Neg logit contributions | |
owitz | -4.402 |
illance | -3.932 |
chio | -3.787 |
oulos | -3.664 |
ilon | -3.611 |
Token | ent |
Token ID | 298 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
anmar | +4.434 |
mil | +4.346 |
vg | +4.058 |
hub | +4.035 |
snap | +3.891 |
Neg logit contributions | |
owitz | -5.053 |
chio | -4.396 |
illance | -4.328 |
oulos | -4.175 |
™: | -4.072 |
Token | , |
Token ID | 11 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
anmar | +0.252 |
mil | +0.238 |
reluct | +0.230 |
fabrication | +0.227 |
hub | +0.227 |
Neg logit contributions | |
owitz | -0.254 |
chio | -0.217 |
illance | -0.216 |
edi | -0.206 |
oulos | -0.203 |
Token | � |
Token ID | 447 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
owitz | +1.752 |
chio | +1.497 |
illance | +1.460 |
edi | +1.455 |
oulos | +1.417 |
Neg logit contributions | |
anmar | -1.488 |
mil | -1.357 |
reluct | -1.319 |
fabrication | -1.301 |
interstitial | -1.300 |
Token | ce |
Token ID | 344 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
anmar | +4.097 |
mil | +4.053 |
hub | +3.760 |
vg | +3.736 |
fabrication | +3.707 |
Neg logit contributions | |
owitz | -4.418 |
illance | -3.827 |
chio | -3.723 |
oulos | -3.593 |
edi | -3.542 |
Token | ives |
Token ID | 1083 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
owitz | +0.812 |
illance | +0.678 |
chio | +0.665 |
edi | +0.620 |
oulos | +0.606 |
Neg logit contributions | |
anmar | -1.311 |
mil | -1.245 |
reluct | -1.237 |
hub | -1.220 |
fabrication | -1.218 |
Token | from |
Token ID | 422 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
owitz | +0.726 |
chio | +0.632 |
illance | +0.621 |
edi | +0.600 |
ilon | +0.589 |
Neg logit contributions | |
anmar | -0.636 |
mil | -0.588 |
reluct | -0.570 |
fabrication | -0.560 |
vg | -0.559 |
Token | his |
Token ID | 465 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
owitz | +1.065 |
chio | +0.921 |
illance | +0.906 |
edi | +0.879 |
oulos | +0.856 |
Neg logit contributions | |
anmar | -0.935 |
mil | -0.876 |
reluct | -0.844 |
fabrication | -0.837 |
vg | -0.829 |
Token | fel |
Token ID | 10756 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
owitz | +1.655 |
chio | +1.465 |
illance | +1.432 |
edi | +1.392 |
oulos | +1.370 |
Neg logit contributions | |
anmar | -1.126 |
mil | -1.057 |
reluct | -1.011 |
vg | -1.002 |
fabrication | -0.997 |
Token | |
Token ID | 3907 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
anmar | +1.594 |
mil | +1.508 |
reluct | +1.461 |
hub | +1.450 |
fabrication | +1.441 |
Neg logit contributions | |
owitz | -1.857 |
illance | -1.620 |
chio | -1.602 |
edi | -1.533 |
oulos | -1.514 |
Token | low |
Token ID | 9319 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
mil | +7.581 |
anmar | +7.038 |
vg | +6.600 |
hub | +6.392 |
aspx | +6.303 |
Neg logit contributions | |
owitz | -8.338 |
chio | -7.388 |
illance | -7.275 |
™: | -7.059 |
oulos | -6.997 |
Token | Demo |
Token ID | 34588 |
Feature activation | +9.40e-02 |
Pos logit contributions | |
owitz | +1.136 |
illance | +0.987 |
chio | +0.978 |
edi | +0.945 |
oulos | +0.919 |
Neg logit contributions | |
anmar | -0.942 |
mil | -0.889 |
reluct | -0.868 |
fabrication | -0.851 |
vg | -0.841 |
Token | |
Token ID | 3907 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
anmar | +0.345 |
mil | +0.323 |
reluct | +0.319 |
fabrication | +0.313 |
hub | +0.310 |
Neg logit contributions | |
owitz | -0.380 |
chio | -0.331 |
illance | -0.330 |
edi | -0.315 |
ilon | -0.309 |
Token | cr |
Token ID | 6098 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
mil | +3.460 |
anmar | +3.000 |
hub | +2.670 |
vg | +2.566 |
fabrication | +2.518 |
Neg logit contributions | |
owitz | -12.185 |
illance | -11.122 |
oulos | -10.814 |
chio | -10.688 |
™: | -10.501 |
Token | ats |
Token ID | 1381 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
anmar | +5.041 |
mil | +4.873 |
hub | +4.630 |
reluct | +4.566 |
fabrication | +4.507 |
Neg logit contributions | |
owitz | -5.367 |
illance | -4.778 |
chio | -4.649 |
edi | -4.471 |
oulos | -4.458 |
Token | cities |
Token ID | 4736 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
anmar | +1.083 |
mil | +1.025 |
reluct | +0.983 |
hub | +0.976 |
fabrication | +0.966 |
Neg logit contributions | |
owitz | -1.413 |
illance | -1.248 |
chio | -1.232 |
edi | -1.179 |
oulos | -1.171 |
Token | like |
Token ID | 588 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
owitz | +0.028 |
illance | +0.024 |
chio | +0.024 |
edi | +0.023 |
ilon | +0.023 |
Neg logit contributions | |
anmar | -0.022 |
mil | -0.021 |
reluct | -0.020 |
hub | -0.020 |
fabrication | -0.020 |
Token | Benghazi |
Token ID | 22497 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
anmar | +1.735 |
mil | +1.653 |
reluct | +1.592 |
hub | +1.586 |
fabrication | +1.572 |
Neg logit contributions | |
owitz | -1.851 |
illance | -1.613 |
chio | -1.591 |
edi | -1.513 |
oulos | -1.504 |
Token | and |
Token ID | 290 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
anmar | +1.304 |
mil | +1.237 |
reluct | +1.198 |
hub | +1.185 |
fabrication | +1.177 |
Neg logit contributions | |
owitz | -1.508 |
illance | -1.321 |
chio | -1.301 |
edi | -1.242 |
oulos | -1.234 |
Token | Mis |
Token ID | 14136 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
anmar | +1.201 |
mil | +1.139 |
reluct | +1.096 |
hub | +1.085 |
fabrication | +1.077 |
Neg logit contributions | |
owitz | -1.485 |
illance | -1.305 |
chio | -1.290 |
edi | -1.233 |
oulos | -1.225 |
Token | r |
Token ID | 81 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
anmar | +0.446 |
mil | +0.414 |
reluct | +0.397 |
hub | +0.390 |
fabrication | +0.387 |
Neg logit contributions | |
owitz | -0.982 |
illance | -0.885 |
chio | -0.878 |
edi | -0.848 |
oulos | -0.841 |
Token | ata |
Token ID | 1045 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
anmar | +9.292 |
mil | +8.876 |
hub | +8.515 |
fabrication | +8.321 |
vg | +8.319 |
Neg logit contributions | |
owitz | -6.847 |
illance | -6.008 |
chio | -5.800 |
ilon | -5.481 |
oulos | -5.461 |
Token | , |
Token ID | 11 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
anmar | +1.379 |
mil | +1.311 |
reluct | +1.268 |
hub | +1.257 |
fabrication | +1.248 |
Neg logit contributions | |
owitz | -1.551 |
illance | -1.353 |
chio | -1.336 |
edi | -1.274 |
oulos | -1.265 |
Token | where |
Token ID | 810 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
anmar | +0.280 |
mil | +0.264 |
reluct | +0.254 |
hub | +0.249 |
fabrication | +0.247 |
Neg logit contributions | |
owitz | -0.399 |
illance | -0.353 |
chio | -0.348 |
edi | -0.335 |
oulos | -0.333 |
Token | innocent |
Token ID | 10218 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
anmar | +1.997 |
mil | +1.892 |
hub | +1.834 |
fabrication | +1.802 |
reluct | +1.800 |
Neg logit contributions | |
owitz | -2.940 |
illance | -2.621 |
chio | -2.597 |
oulos | -2.462 |
edi | -2.459 |
Token | men |
Token ID | 1450 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
owitz | +0.821 |
illance | +0.728 |
chio | +0.720 |
edi | +0.705 |
oulos | +0.690 |
Neg logit contributions | |
anmar | -0.495 |
mil | -0.464 |
reluct | -0.452 |
interstitial | -0.434 |
vg | -0.431 |
Token | his |
Token ID | 465 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
owitz | +1.065 |
chio | +0.921 |
illance | +0.906 |
edi | +0.879 |
oulos | +0.856 |
Neg logit contributions | |
anmar | -0.935 |
mil | -0.876 |
reluct | -0.844 |
fabrication | -0.837 |
vg | -0.829 |
Token | fel |
Token ID | 10756 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
owitz | +1.655 |
chio | +1.465 |
illance | +1.432 |
edi | +1.392 |
oulos | +1.370 |
Neg logit contributions | |
anmar | -1.126 |
mil | -1.057 |
reluct | -1.011 |
vg | -1.002 |
fabrication | -0.997 |
Token | |
Token ID | 3907 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
anmar | +1.594 |
mil | +1.508 |
reluct | +1.461 |
hub | +1.450 |
fabrication | +1.441 |
Neg logit contributions | |
owitz | -1.857 |
illance | -1.620 |
chio | -1.602 |
edi | -1.533 |
oulos | -1.514 |
Token | low |
Token ID | 9319 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
mil | +7.581 |
anmar | +7.038 |
vg | +6.600 |
hub | +6.392 |
aspx | +6.303 |
Neg logit contributions | |
owitz | -8.338 |
chio | -7.388 |
illance | -7.275 |
™: | -7.059 |
oulos | -6.997 |
Token | Demo |
Token ID | 34588 |
Feature activation | +9.40e-02 |
Pos logit contributions | |
owitz | +1.136 |
illance | +0.987 |
chio | +0.978 |
edi | +0.945 |
oulos | +0.919 |
Neg logit contributions | |
anmar | -0.942 |
mil | -0.889 |
reluct | -0.868 |
fabrication | -0.851 |
vg | -0.841 |
Token | |
Token ID | 3907 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
anmar | +0.345 |
mil | +0.323 |
reluct | +0.319 |
fabrication | +0.313 |
hub | +0.310 |
Neg logit contributions | |
owitz | -0.380 |
chio | -0.331 |
illance | -0.330 |
edi | -0.315 |
ilon | -0.309 |
Token | cr |
Token ID | 6098 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
mil | +3.460 |
anmar | +3.000 |
hub | +2.670 |
vg | +2.566 |
fabrication | +2.518 |
Neg logit contributions | |
owitz | -12.185 |
illance | -11.122 |
oulos | -10.814 |
chio | -10.688 |
™: | -10.501 |
Token | ats |
Token ID | 1381 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
anmar | +5.041 |
mil | +4.873 |
hub | +4.630 |
reluct | +4.566 |
fabrication | +4.507 |
Neg logit contributions | |
owitz | -5.367 |
illance | -4.778 |
chio | -4.649 |
edi | -4.471 |
oulos | -4.458 |
Token | . |
Token ID | 13 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
anmar | +1.689 |
mil | +1.604 |
reluct | +1.551 |
hub | +1.541 |
fabrication | +1.535 |
Neg logit contributions | |
owitz | -1.782 |
illance | -1.543 |
chio | -1.530 |
edi | -1.451 |
oulos | -1.444 |
Token | At |
Token ID | 1629 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
owitz | +2.019 |
chio | +1.743 |
illance | +1.726 |
edi | +1.659 |
™: | +1.644 |
Neg logit contributions | |
anmar | -1.725 |
reluct | -1.609 |
mil | -1.563 |
fabrication | -1.550 |
confir | -1.512 |
Token | the |
Token ID | 262 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
anmar | +0.737 |
mil | +0.690 |
reluct | +0.672 |
fabrication | +0.661 |
hub | +0.656 |
Neg logit contributions | |
owitz | -0.847 |
chio | -0.737 |
illance | -0.727 |
edi | -0.695 |
ilon | -0.684 |
Token | are |
Token ID | 389 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
anmar | +0.590 |
mil | +0.562 |
hub | +0.535 |
fabrication | +0.526 |
reluct | +0.518 |
Neg logit contributions | |
owitz | -0.938 |
illance | -0.839 |
chio | -0.828 |
oulos | -0.794 |
edi | -0.792 |
Token | lightly |
Token ID | 15376 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
anmar | +0.206 |
mil | +0.190 |
hub | +0.176 |
reluct | +0.176 |
fabrication | +0.173 |
Neg logit contributions | |
owitz | -0.535 |
illance | -0.487 |
chio | -0.481 |
edi | -0.465 |
oulos | -0.463 |
Token | fried |
Token ID | 23018 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
anmar | +0.739 |
mil | +0.672 |
hub | +0.614 |
fabrication | +0.572 |
snap | +0.545 |
Neg logit contributions | |
owitz | -3.682 |
illance | -3.422 |
chio | -3.352 |
ilon | -3.264 |
oulos | -3.249 |
Token | and |
Token ID | 290 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
anmar | +0.885 |
mil | +0.851 |
hub | +0.807 |
fabrication | +0.786 |
vg | +0.772 |
Neg logit contributions | |
owitz | -1.662 |
illance | -1.507 |
chio | -1.480 |
oulos | -1.420 |
edi | -1.418 |
Token | not |
Token ID | 407 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
anmar | +0.106 |
mil | +0.102 |
hub | +0.096 |
fabrication | +0.095 |
reluct | +0.094 |
Neg logit contributions | |
owitz | -0.178 |
illance | -0.160 |
chio | -0.157 |
oulos | -0.151 |
edi | -0.150 |
Token | deep |
Token ID | 2769 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
anmar | +0.226 |
mil | +0.216 |
hub | +0.207 |
reluct | +0.205 |
fabrication | +0.204 |
Neg logit contributions | |
owitz | -0.287 |
illance | -0.253 |
chio | -0.249 |
oulos | -0.238 |
edi | -0.238 |
Token | fried |
Token ID | 23018 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
mil | +1.329 |
anmar | +1.290 |
hub | +1.263 |
snap | +1.139 |
fabrication | +1.051 |
Neg logit contributions | |
owitz | -13.105 |
illance | -12.592 |
chio | -12.049 |
ilon | -11.933 |
ioxide | -11.764 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
anmar | +1.457 |
mil | +1.450 |
hub | +1.379 |
vg | +1.344 |
snap | +1.335 |
Neg logit contributions | |
owitz | -1.798 |
illance | -1.611 |
chio | -1.563 |
oulos | -1.500 |
edi | -1.480 |
Token | 6 |
Token ID | 718 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
anmar | +4.351 |
mil | +4.232 |
hub | +4.090 |
reluct | +4.006 |
fabrication | +3.992 |
Neg logit contributions | |
owitz | -4.515 |
illance | -3.895 |
chio | -3.824 |
edi | -3.668 |
ilon | -3.598 |
Token | . |
Token ID | 13 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
anmar | +1.161 |
mil | +1.154 |
hub | +1.096 |
vg | +1.074 |
fabrication | +1.071 |
Neg logit contributions | |
owitz | -1.341 |
illance | -1.196 |
chio | -1.166 |
oulos | -1.115 |
edi | -1.106 |
Token | Drain |
Token ID | 36024 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
anmar | +0.833 |
mil | +0.794 |
hub | +0.748 |
fabrication | +0.733 |
reluct | +0.726 |
Neg logit contributions | |
owitz | -1.496 |
illance | -1.348 |
chio | -1.330 |
edi | -1.277 |
oulos | -1.276 |
Token | to |
Token ID | 284 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
owitz | +0.073 |
illance | +0.064 |
chio | +0.063 |
edi | +0.061 |
ilon | +0.060 |
Neg logit contributions | |
anmar | -0.052 |
mil | -0.049 |
reluct | -0.046 |
vg | -0.045 |
fabrication | -0.045 |
Token | see |
Token ID | 766 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
anmar | +0.381 |
mil | +0.358 |
reluct | +0.346 |
hub | +0.338 |
fabrication | +0.337 |
Neg logit contributions | |
owitz | -0.535 |
illance | -0.474 |
chio | -0.471 |
edi | -0.449 |
oulos | -0.445 |
Token | Ann |
Token ID | 5506 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
owitz | +2.065 |
illance | +1.804 |
chio | +1.778 |
edi | +1.732 |
ilon | +1.689 |
Neg logit contributions | |
anmar | -1.536 |
mil | -1.446 |
reluct | -1.376 |
vg | -1.355 |
interstitial | -1.348 |
Token | al |
Token ID | 282 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
anmar | +0.746 |
mil | +0.709 |
reluct | +0.683 |
hub | +0.680 |
fabrication | +0.674 |
Neg logit contributions | |
owitz | -0.880 |
illance | -0.771 |
chio | -0.762 |
edi | -0.727 |
oulos | -0.722 |
Token | ise |
Token ID | 786 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
anmar | +1.334 |
mil | +1.293 |
hub | +1.254 |
fabrication | +1.245 |
reluct | +1.238 |
Neg logit contributions | |
owitz | -0.550 |
illance | -0.430 |
chio | -0.411 |
edi | -0.372 |
oulos | -0.370 |
Token | admit |
Token ID | 9159 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
anmar | +0.363 |
mil | +0.341 |
reluct | +0.327 |
hub | +0.325 |
fabrication | +0.322 |
Neg logit contributions | |
owitz | -0.504 |
illance | -0.446 |
chio | -0.440 |
edi | -0.422 |
oulos | -0.418 |
Token | in |
Token ID | 287 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
anmar | +5.097 |
mil | +4.856 |
hub | +4.856 |
fabrication | +4.677 |
reluct | +4.628 |
Neg logit contributions | |
owitz | -9.715 |
illance | -8.782 |
chio | -8.672 |
oulos | -8.353 |
edi | -8.252 |
Token | a |
Token ID | 257 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
anmar | +1.767 |
mil | +1.670 |
reluct | +1.599 |
hub | +1.590 |
fabrication | +1.574 |
Neg logit contributions | |
owitz | -2.467 |
illance | -2.185 |
chio | -2.161 |
edi | -2.068 |
oulos | -2.053 |
Token | very |
Token ID | 845 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
anmar | +0.971 |
mil | +0.896 |
reluct | +0.855 |
hub | +0.837 |
fabrication | +0.829 |
Neg logit contributions | |
owitz | -1.773 |
illance | -1.589 |
chio | -1.577 |
edi | -1.511 |
oulos | -1.498 |
Token | vulnerable |
Token ID | 8826 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
owitz | +1.642 |
illance | +1.444 |
chio | +1.434 |
edi | +1.386 |
oulos | +1.351 |
Neg logit contributions | |
anmar | -1.133 |
mil | -1.040 |
reluct | -1.001 |
vg | -0.973 |
fabrication | -0.967 |
Token | way |
Token ID | 835 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
anmar | +0.987 |
mil | +0.910 |
reluct | +0.854 |
hub | +0.838 |
fabrication | +0.827 |
Neg logit contributions | |
owitz | -2.306 |
illance | -2.085 |
chio | -2.067 |
edi | -1.996 |
oulos | -1.981 |
Token | name |
Token ID | 1438 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
owitz | +1.476 |
chio | +1.292 |
illance | +1.275 |
edi | +1.232 |
oulos | +1.213 |
Neg logit contributions | |
anmar | -1.009 |
mil | -0.955 |
reluct | -0.907 |
vg | -0.907 |
interstitial | -0.899 |
Token | is |
Token ID | 318 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
anmar | +2.296 |
mil | +2.172 |
hub | +2.059 |
reluct | +2.054 |
fabrication | +2.030 |
Neg logit contributions | |
owitz | -3.792 |
illance | -3.396 |
chio | -3.356 |
edi | -3.213 |
oulos | -3.208 |
Token | still |
Token ID | 991 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
anmar | +1.047 |
mil | +0.982 |
reluct | +0.942 |
hub | +0.934 |
fabrication | +0.926 |
Neg logit contributions | |
owitz | -1.590 |
illance | -1.409 |
chio | -1.397 |
edi | -1.342 |
oulos | -1.330 |
Token | a |
Token ID | 257 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
owitz | +0.154 |
illance | +0.134 |
chio | +0.133 |
edi | +0.129 |
ilon | +0.126 |
Neg logit contributions | |
anmar | -0.116 |
mil | -0.108 |
reluct | -0.105 |
fabrication | -0.102 |
hub | -0.102 |
Token | polit |
Token ID | 1408 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
anmar | +0.247 |
mil | +0.225 |
reluct | +0.220 |
fabrication | +0.211 |
hub | +0.210 |
Neg logit contributions | |
owitz | -0.379 |
illance | -0.335 |
chio | -0.334 |
edi | -0.322 |
ilon | -0.317 |
Token | |
Token ID | 3907 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
anmar | +1.422 |
reluct | +1.327 |
mil | +1.318 |
fabrication | +1.288 |
hub | +1.283 |
Neg logit contributions | |
owitz | -1.461 |
chio | -1.259 |
illance | -1.253 |
edi | -1.211 |
ilon | -1.181 |
Token | ic |
Token ID | 291 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
anmar | +7.157 |
mil | +7.106 |
hub | +6.712 |
vg | +6.519 |
fabrication | +6.461 |
Neg logit contributions | |
owitz | -7.233 |
illance | -6.215 |
chio | -6.064 |
oulos | -5.833 |
™: | -5.724 |
Token | |
Token ID | 3907 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
anmar | +1.688 |
mil | +1.570 |
reluct | +1.552 |
hub | +1.496 |
fabrication | +1.496 |
Neg logit contributions | |
owitz | -1.869 |
chio | -1.639 |
illance | -1.634 |
edi | -1.553 |
ilon | -1.532 |
Token | al |
Token ID | 282 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
anmar | +4.709 |
mil | +4.565 |
hub | +4.249 |
fabrication | +4.173 |
vg | +4.144 |
Neg logit contributions | |
owitz | -6.265 |
illance | -5.593 |
chio | -5.386 |
oulos | -5.231 |
edi | -5.231 |
Token | in |
Token ID | 287 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
anmar | +0.425 |
mil | +0.390 |
reluct | +0.380 |
vg | +0.363 |
fabrication | +0.363 |
Neg logit contributions | |
owitz | -0.629 |
chio | -0.556 |
illance | -0.555 |
edi | -0.537 |
ilon | -0.526 |
Token | |
Token ID | 3907 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
owitz | +1.598 |
chio | +1.368 |
illance | +1.344 |
edi | +1.337 |
ilon | +1.279 |
Neg logit contributions | |
anmar | -1.497 |
mil | -1.389 |
reluct | -1.383 |
fabrication | -1.355 |
vg | -1.327 |
Token | . |
Token ID | 13 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
owitz | +0.983 |
chio | +0.833 |
illance | +0.828 |
edi | +0.787 |
oulos | +0.773 |
Neg logit contributions | |
anmar | -1.138 |
mil | -1.069 |
reluct | -1.055 |
interstitial | -1.035 |
vg | -1.032 |
Token | It |
Token ID | 632 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
anmar | +2.325 |
mil | +2.198 |
reluct | +2.112 |
hub | +2.100 |
fabrication | +2.080 |
Neg logit contributions | |
owitz | -3.084 |
illance | -2.723 |
chio | -2.694 |
edi | -2.575 |
oulos | -2.558 |
Token | has |
Token ID | 468 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
anmar | +0.642 |
mil | +0.593 |
reluct | +0.576 |
hub | +0.569 |
fabrication | +0.563 |
Neg logit contributions | |
owitz | -1.027 |
illance | -0.912 |
chio | -0.904 |
edi | -0.871 |
oulos | -0.862 |
Token | a |
Token ID | 257 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
owitz | +0.177 |
illance | +0.154 |
chio | +0.153 |
edi | +0.147 |
oulos | +0.144 |
Neg logit contributions | |
anmar | -0.156 |
mil | -0.147 |
reluct | -0.142 |
hub | -0.139 |
fabrication | -0.139 |
Token | more |
Token ID | 517 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
anmar | +0.219 |
mil | +0.202 |
reluct | +0.192 |
fabrication | +0.187 |
hub | +0.186 |
Neg logit contributions | |
owitz | -0.401 |
chio | -0.358 |
illance | -0.357 |
edi | -0.344 |
oulos | -0.341 |
Token | hold |
Token ID | 1745 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
anmar | +0.692 |
mil | +0.645 |
reluct | +0.620 |
hub | +0.607 |
fabrication | +0.604 |
Neg logit contributions | |
owitz | -1.106 |
illance | -0.980 |
chio | -0.976 |
edi | -0.940 |
oulos | -0.930 |
Token | than |
Token ID | 621 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
anmar | +5.713 |
mil | +5.518 |
hub | +5.183 |
fabrication | +5.094 |
vg | +5.039 |
Neg logit contributions | |
owitz | -8.887 |
illance | -7.977 |
chio | -7.828 |
oulos | -7.487 |
edi | -7.476 |
Token | almond |
Token ID | 26948 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
anmar | +0.310 |
mil | +0.285 |
reluct | +0.275 |
fabrication | +0.266 |
hub | +0.264 |
Neg logit contributions | |
owitz | -0.559 |
illance | -0.495 |
chio | -0.494 |
edi | -0.477 |
ilon | -0.473 |
Token | flour |
Token ID | 10601 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
anmar | +0.038 |
mil | +0.035 |
reluct | +0.034 |
interstitial | +0.034 |
hub | +0.033 |
Neg logit contributions | |
owitz | -0.049 |
chio | -0.043 |
illance | -0.043 |
edi | -0.041 |
oulos | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
owitz | +0.979 |
chio | +0.843 |
illance | +0.839 |
edi | +0.804 |
oulos | +0.801 |
Neg logit contributions | |
anmar | -0.867 |
mil | -0.804 |
reluct | -0.795 |
hub | -0.769 |
interstitial | -0.768 |
Token | which |
Token ID | 543 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
anmar | +0.331 |
mil | +0.306 |
reluct | +0.298 |
hub | +0.291 |
fabrication | +0.288 |
Neg logit contributions | |
owitz | -0.453 |
illance | -0.397 |
chio | -0.395 |
edi | -0.383 |
oulos | -0.375 |
Token | , |
Token ID | 11 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
anmar | +2.098 |
mil | +1.980 |
reluct | +1.903 |
hub | +1.885 |
fabrication | +1.870 |
Neg logit contributions | |
owitz | -2.694 |
illance | -2.376 |
chio | -2.343 |
edi | -2.244 |
oulos | -2.227 |
Token | and |
Token ID | 290 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
owitz | +0.045 |
illance | +0.039 |
chio | +0.039 |
edi | +0.038 |
oulos | +0.037 |
Neg logit contributions | |
anmar | -0.033 |
mil | -0.031 |
reluct | -0.030 |
hub | -0.029 |
fabrication | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
anmar | +0.781 |
mil | +0.738 |
reluct | +0.709 |
hub | +0.702 |
fabrication | +0.695 |
Neg logit contributions | |
owitz | -0.935 |
illance | -0.818 |
chio | -0.808 |
edi | -0.774 |
oulos | -0.767 |
Token | 31 |
Token ID | 3261 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
anmar | +0.145 |
mil | +0.137 |
reluct | +0.131 |
hub | +0.129 |
fabrication | +0.128 |
Neg logit contributions | |
owitz | -0.190 |
illance | -0.167 |
chio | -0.165 |
edi | -0.158 |
oulos | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
anmar | +1.455 |
mil | +1.361 |
reluct | +1.339 |
hub | +1.314 |
fabrication | +1.312 |
Neg logit contributions | |
owitz | -1.408 |
illance | -1.227 |
chio | -1.192 |
edi | -1.150 |
oulos | -1.127 |
Token | 5 |
Token ID | 20 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
anmar | +2.309 |
mil | +2.250 |
hub | +2.134 |
vg | +2.105 |
fabrication | +2.094 |
Neg logit contributions | |
owitz | -2.448 |
illance | -2.159 |
chio | -2.110 |
oulos | -2.011 |
edi | -1.999 |
Token | - |
Token ID | 12 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
anmar | +5.618 |
mil | +5.600 |
hub | +5.268 |
fabrication | +5.128 |
reluct | +5.101 |
Neg logit contributions | |
owitz | -8.386 |
chio | -7.442 |
illance | -7.369 |
oulos | -7.022 |
edi | -6.968 |
Token | met |
Token ID | 4164 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
anmar | +2.095 |
mil | +1.966 |
reluct | +1.931 |
hub | +1.915 |
fabrication | +1.903 |
Neg logit contributions | |
owitz | -2.003 |
illance | -1.742 |
chio | -1.703 |
edi | -1.626 |
oulos | -1.608 |
Token | re |
Token ID | 260 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
owitz | +1.257 |
illance | +1.076 |
chio | +1.059 |
edi | +0.997 |
oulos | +0.992 |
Neg logit contributions | |
anmar | -1.491 |
mil | -1.431 |
hub | -1.380 |
reluct | -1.377 |
fabrication | -1.368 |
Token | distance |
Token ID | 5253 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
anmar | +0.399 |
mil | +0.368 |
reluct | +0.353 |
hub | +0.344 |
vg | +0.341 |
Neg logit contributions | |
owitz | -0.639 |
illance | -0.572 |
chio | -0.561 |
edi | -0.544 |
oulos | -0.538 |
Token | from |
Token ID | 422 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
anmar | +2.320 |
mil | +2.206 |
reluct | +2.116 |
hub | +2.114 |
fabrication | +2.092 |
Neg logit contributions | |
owitz | -2.866 |
illance | -2.523 |
chio | -2.492 |
edi | -2.377 |
oulos | -2.364 |
Token | |
Token ID | 3907 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
owitz | +1.396 |
chio | +1.197 |
illance | +1.181 |
edi | +1.146 |
ilon | +1.130 |
Neg logit contributions | |
anmar | -1.402 |
mil | -1.301 |
reluct | -1.281 |
interstitial | -1.262 |
fabrication | -1.260 |
Token | ing |
Token ID | 278 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
anmar | +4.573 |
mil | +4.438 |
hub | +4.228 |
reluct | +4.157 |
fabrication | +4.154 |
Neg logit contributions | |
owitz | -4.223 |
illance | -3.673 |
chio | -3.619 |
oulos | -3.412 |
edi | -3.388 |
Token | is |
Token ID | 318 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
anmar | +0.852 |
mil | +0.791 |
reluct | +0.758 |
hub | +0.745 |
fabrication | +0.743 |
Neg logit contributions | |
owitz | -1.261 |
chio | -1.115 |
illance | -1.115 |
edi | -1.069 |
oulos | -1.061 |
Token | the |
Token ID | 262 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
owitz | +1.042 |
chio | +0.906 |
illance | +0.891 |
edi | +0.868 |
oulos | +0.852 |
Neg logit contributions | |
anmar | -0.887 |
mil | -0.825 |
reluct | -0.793 |
fabrication | -0.781 |
vg | -0.781 |
Token | treat |
Token ID | 2190 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
owitz | +1.305 |
chio | +1.159 |
illance | +1.149 |
edi | +1.110 |
oulos | +1.096 |
Neg logit contributions | |
anmar | -0.869 |
mil | -0.805 |
reluct | -0.755 |
vg | -0.753 |
interstitial | -0.742 |
Token | |
Token ID | 3907 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
owitz | +1.498 |
chio | +1.265 |
illance | +1.248 |
edi | +1.231 |
itar | +1.210 |
Neg logit contributions | |
anmar | -1.620 |
reluct | -1.509 |
fabrication | -1.481 |
mil | -1.454 |
interstitial | -1.445 |
Token | ment |
Token ID | 434 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
anmar | +7.017 |
mil | +6.911 |
hub | +6.457 |
vg | +6.408 |
fabrication | +6.347 |
Neg logit contributions | |
owitz | -6.771 |
illance | -5.769 |
chio | -5.766 |
oulos | -5.479 |
edi | -5.344 |
Token | Carter |
Token ID | 10831 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
owitz | +0.468 |
chio | +0.410 |
illance | +0.408 |
edi | +0.394 |
oulos | +0.387 |
Neg logit contributions | |
anmar | -0.344 |
mil | -0.317 |
reluct | -0.307 |
fabrication | -0.300 |
vg | -0.299 |
Token | re |
Token ID | 302 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
anmar | +0.522 |
mil | +0.487 |
reluct | +0.470 |
hub | +0.464 |
fabrication | +0.462 |
Neg logit contributions | |
owitz | -0.657 |
chio | -0.573 |
illance | -0.572 |
edi | -0.546 |
oulos | -0.542 |
Token | |
Token ID | 3907 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
anmar | +1.689 |
mil | +1.592 |
reluct | +1.553 |
hub | +1.535 |
fabrication | +1.525 |
Neg logit contributions | |
owitz | -1.936 |
illance | -1.686 |
chio | -1.681 |
edi | -1.607 |
oulos | -1.589 |
Token | ce |
Token ID | 344 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
anmar | +4.097 |
mil | +4.053 |
hub | +3.760 |
vg | +3.736 |
fabrication | +3.707 |
Neg logit contributions | |
owitz | -4.418 |
illance | -3.827 |
chio | -3.723 |
oulos | -3.593 |
edi | -3.542 |
Token | that |
Token ID | 326 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
anmar | +0.720 |
mil | +0.676 |
reluct | +0.644 |
hub | +0.631 |
fabrication | +0.630 |
Neg logit contributions | |
owitz | -1.085 |
illance | -0.959 |
chio | -0.954 |
edi | -0.920 |
oulos | -0.913 |
Token | means |
Token ID | 1724 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
owitz | +1.050 |
chio | +0.920 |
illance | +0.913 |
edi | +0.875 |
oulos | +0.860 |
Neg logit contributions | |
anmar | -0.798 |
mil | -0.741 |
reluct | -0.709 |
fabrication | -0.698 |
hub | -0.694 |
Token | that |
Token ID | 326 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
owitz | +1.440 |
illance | +1.272 |
chio | +1.270 |
edi | +1.228 |
oulos | +1.216 |
Neg logit contributions | |
anmar | -0.884 |
mil | -0.827 |
reluct | -0.791 |
fabrication | -0.764 |
hub | -0.761 |
Token | the |
Token ID | 262 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
owitz | +0.883 |
illance | +0.777 |
chio | +0.776 |
edi | +0.749 |
oulos | +0.743 |
Neg logit contributions | |
anmar | -0.571 |
mil | -0.537 |
reluct | -0.513 |
hub | -0.497 |
fabrication | -0.497 |
Token | mat |
Token ID | 2603 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
anmar | +0.056 |
mil | +0.053 |
reluct | +0.050 |
vg | +0.048 |
fabrication | +0.048 |
Neg logit contributions | |
owitz | -0.108 |
chio | -0.096 |
illance | -0.096 |
oulos | -0.093 |
edi | -0.092 |
Token | ri |
Token ID | 380 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
anmar | +3.349 |
mil | +3.196 |
hub | +3.070 |
reluct | +3.065 |
fabrication | +3.038 |
Neg logit contributions | |
owitz | -3.370 |
illance | -2.928 |
chio | -2.886 |
edi | -2.736 |
oulos | -2.724 |
Token | archs |
Token ID | 34592 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
anmar | +5.055 |
mil | +4.775 |
hub | +4.507 |
fabrication | +4.372 |
reluct | +4.347 |
Neg logit contributions | |
owitz | -8.647 |
illance | -7.859 |
chio | -7.606 |
oulos | -7.445 |
ilon | -7.384 |
Token | are |
Token ID | 389 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
anmar | +0.132 |
mil | +0.123 |
reluct | +0.119 |
hub | +0.117 |
fabrication | +0.116 |
Neg logit contributions | |
owitz | -0.199 |
chio | -0.175 |
illance | -0.175 |
edi | -0.167 |
oulos | -0.166 |
Token | great |
Token ID | 1049 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
owitz | +0.499 |
illance | +0.442 |
chio | +0.437 |
edi | +0.419 |
oulos | +0.415 |
Neg logit contributions | |
anmar | -0.346 |
mil | -0.326 |
reluct | -0.311 |
fabrication | -0.305 |
hub | -0.304 |
Token | cooks |
Token ID | 38383 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
owitz | +0.190 |
illance | +0.167 |
chio | +0.167 |
edi | +0.159 |
oulos | +0.158 |
Neg logit contributions | |
anmar | -0.138 |
mil | -0.129 |
reluct | -0.125 |
fabrication | -0.121 |
vg | -0.121 |
Token | , |
Token ID | 11 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
owitz | +0.486 |
illance | +0.422 |
chio | +0.416 |
edi | +0.398 |
oulos | +0.395 |
Neg logit contributions | |
anmar | -0.423 |
mil | -0.400 |
reluct | -0.390 |
hub | -0.382 |
fabrication | -0.380 |
Token | thrust |
Token ID | 14613 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
owitz | +0.718 |
chio | +0.634 |
illance | +0.626 |
edi | +0.607 |
oulos | +0.594 |
Neg logit contributions | |
anmar | -0.522 |
mil | -0.482 |
reluct | -0.466 |
vg | -0.449 |
hub | -0.448 |
Token | of |
Token ID | 286 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
owitz | +0.211 |
illance | +0.183 |
chio | +0.183 |
edi | +0.174 |
oulos | +0.172 |
Neg logit contributions | |
anmar | -0.174 |
mil | -0.162 |
reluct | -0.159 |
fabrication | -0.155 |
hub | -0.154 |
Token | his |
Token ID | 465 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
owitz | +1.984 |
chio | +1.730 |
illance | +1.715 |
edi | +1.660 |
oulos | +1.616 |
Neg logit contributions | |
anmar | -1.600 |
mil | -1.482 |
reluct | -1.440 |
vg | -1.405 |
fabrication | -1.387 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
owitz | +3.195 |
chio | +2.848 |
illance | +2.781 |
edi | +2.737 |
oulos | +2.646 |
Neg logit contributions | |
anmar | -2.178 |
mil | -2.005 |
reluct | -1.931 |
vg | -1.926 |
interstitial | -1.875 |
Token | pres |
Token ID | 906 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
owitz | +0.790 |
chio | +0.698 |
illance | +0.686 |
edi | +0.667 |
oulos | +0.655 |
Neg logit contributions | |
anmar | -0.526 |
mil | -0.489 |
reluct | -0.469 |
vg | -0.463 |
fabrication | -0.460 |
Token | |
Token ID | 3907 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
owitz | +1.589 |
chio | +1.373 |
illance | +1.365 |
edi | +1.326 |
oulos | +1.282 |
Neg logit contributions | |
anmar | -1.463 |
reluct | -1.389 |
mil | -1.361 |
fabrication | -1.340 |
hub | -1.332 |
Token | id |
Token ID | 312 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
mil | +5.052 |
anmar | +4.974 |
vg | +4.489 |
hub | +4.394 |
interstitial | +4.278 |
Neg logit contributions | |
owitz | -8.238 |
chio | -7.236 |
illance | -7.236 |
oulos | -6.995 |
™: | -6.776 |
Token | |
Token ID | 3907 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
anmar | +2.189 |
mil | +2.114 |
hub | +1.997 |
fabrication | +1.956 |
vg | +1.941 |
Neg logit contributions | |
owitz | -3.036 |
illance | -2.715 |
chio | -2.632 |
oulos | -2.555 |
ilon | -2.519 |
Token | en |
Token ID | 268 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
anmar | +4.176 |
mil | +4.101 |
vg | +3.821 |
hub | +3.796 |
snap | +3.693 |
Neg logit contributions | |
owitz | -4.591 |
chio | -3.929 |
illance | -3.882 |
oulos | -3.831 |
™: | -3.652 |
Token | |
Token ID | 3907 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
anmar | +0.594 |
mil | +0.552 |
reluct | +0.544 |
hub | +0.533 |
fabrication | +0.532 |
Neg logit contributions | |
owitz | -0.659 |
illance | -0.571 |
chio | -0.567 |
edi | -0.541 |
oulos | -0.533 |
Token | t |
Token ID | 83 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
mil | +4.508 |
anmar | +4.339 |
vg | +4.064 |
hub | +4.024 |
fabrication | +3.869 |
Neg logit contributions | |
owitz | -7.304 |
illance | -6.343 |
chio | -6.272 |
oulos | -6.139 |
edi | -6.054 |
Token | he |
Token ID | 339 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
anmar | +1.665 |
mil | +1.576 |
reluct | +1.507 |
hub | +1.505 |
fabrication | +1.488 |
Neg logit contributions | |
owitz | -2.351 |
illance | -2.088 |
chio | -2.061 |
edi | -1.972 |
oulos | -1.963 |
Token | 's |
Token ID | 338 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
anmar | +0.608 |
mil | +0.581 |
hub | +0.559 |
reluct | +0.558 |
fabrication | +0.553 |
Neg logit contributions | |
owitz | -0.646 |
illance | -0.564 |
chio | -0.555 |
edi | -0.527 |
oulos | -0.525 |
Token | averaging |
Token ID | 20430 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
owitz | +0.545 |
illance | +0.477 |
chio | +0.473 |
edi | +0.451 |
oulos | +0.446 |
Neg logit contributions | |
anmar | -0.466 |
mil | -0.443 |
reluct | -0.426 |
hub | -0.421 |
fabrication | -0.418 |
Token | 29 |
Token ID | 2808 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
anmar | +1.269 |
mil | +1.205 |
hub | +1.156 |
reluct | +1.155 |
fabrication | +1.143 |
Neg logit contributions | |
owitz | -1.620 |
illance | -1.430 |
chio | -1.410 |
edi | -1.347 |
oulos | -1.341 |
Token | . |
Token ID | 13 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
anmar | +4.021 |
mil | +3.848 |
hub | +3.694 |
reluct | +3.640 |
fabrication | +3.638 |
Neg logit contributions | |
owitz | -5.043 |
illance | -4.477 |
chio | -4.362 |
edi | -4.172 |
oulos | -4.166 |
Token | 9 |
Token ID | 24 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
anmar | +2.811 |
mil | +2.696 |
hub | +2.591 |
reluct | +2.581 |
fabrication | +2.563 |
Neg logit contributions | |
owitz | -2.672 |
illance | -2.316 |
chio | -2.276 |
edi | -2.157 |
oulos | -2.146 |
Token | Fantasy |
Token ID | 10982 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
anmar | +5.313 |
mil | +5.139 |
hub | +4.972 |
snap | +4.870 |
fabrication | +4.837 |
Neg logit contributions | |
owitz | -8.304 |
illance | -7.510 |
chio | -7.223 |
edi | -6.943 |
oulos | -6.937 |
Token | points |
Token ID | 2173 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
anmar | +0.388 |
mil | +0.357 |
reluct | +0.348 |
hub | +0.334 |
fabrication | +0.332 |
Neg logit contributions | |
owitz | -0.738 |
illance | -0.658 |
chio | -0.655 |
edi | -0.631 |
oulos | -0.628 |
Token | in |
Token ID | 287 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
anmar | +0.891 |
mil | +0.840 |
reluct | +0.805 |
hub | +0.797 |
fabrication | +0.790 |
Neg logit contributions | |
owitz | -1.259 |
illance | -1.114 |
chio | -1.104 |
edi | -1.057 |
oulos | -1.051 |
Token | his |
Token ID | 465 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
anmar | +1.052 |
mil | +0.993 |
reluct | +0.947 |
hub | +0.933 |
fabrication | +0.924 |
Neg logit contributions | |
owitz | -1.522 |
illance | -1.342 |
chio | -1.337 |
edi | -1.277 |
oulos | -1.266 |
Token | past |
Token ID | 1613 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
owitz | +0.089 |
illance | +0.077 |
chio | +0.077 |
edi | +0.073 |
oulos | +0.072 |
Neg logit contributions | |
anmar | -0.076 |
mil | -0.073 |
reluct | -0.069 |
hub | -0.068 |
fabrication | -0.068 |
Token | zones |
Token ID | 14123 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
owitz | +1.320 |
chio | +1.175 |
illance | +1.173 |
edi | +1.126 |
oulos | +1.108 |
Neg logit contributions | |
anmar | -0.733 |
mil | -0.669 |
reluct | -0.659 |
vg | -0.626 |
fabrication | -0.618 |
Token | : |
Token ID | 25 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
anmar | +0.553 |
mil | +0.524 |
reluct | +0.508 |
hub | +0.497 |
fabrication | +0.494 |
Neg logit contributions | |
owitz | -0.660 |
illance | -0.574 |
chio | -0.570 |
edi | -0.544 |
oulos | -0.538 |
Token | the |
Token ID | 262 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
owitz | +0.839 |
chio | +0.729 |
illance | +0.728 |
edi | +0.689 |
oulos | +0.682 |
Neg logit contributions | |
anmar | -0.677 |
mil | -0.638 |
reluct | -0.623 |
fabrication | -0.604 |
hub | -0.604 |
Token | free |
Token ID | 1479 |
Feature activation | -1.75e-03 |
Pos logit contributions | |
owitz | +0.296 |
chio | +0.261 |
illance | +0.261 |
edi | +0.248 |
oulos | +0.247 |
Neg logit contributions | |
anmar | -0.204 |
mil | -0.192 |
reluct | -0.187 |
fabrication | -0.180 |
vg | -0.180 |
Token | Mets |
Token ID | 26053 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
owitz | +0.008 |
illance | +0.007 |
chio | +0.007 |
edi | +0.007 |
oulos | +0.007 |
Neg logit contributions | |
anmar | -0.005 |
mil | -0.005 |
reluct | -0.005 |
fabrication | -0.005 |
hub | -0.005 |
Token | ä |
Token ID | 11033 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
anmar | +1.489 |
mil | +1.419 |
reluct | +1.386 |
hub | +1.369 |
fabrication | +1.366 |
Neg logit contributions | |
owitz | -1.481 |
illance | -1.274 |
chio | -1.265 |
edi | -1.195 |
oulos | -1.183 |
Token | Village |
Token ID | 14812 |
Feature activation | +8.29e-02 |
Pos logit contributions | |
anmar | +6.096 |
mil | +5.951 |
hub | +5.615 |
vg | +5.517 |
reluct | +5.454 |
Neg logit contributions | |
owitz | -7.311 |
illance | -6.409 |
chio | -6.249 |
oulos | -6.075 |
edi | -6.005 |
Token | area |
Token ID | 1989 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
anmar | +0.285 |
mil | +0.269 |
reluct | +0.263 |
fabrication | +0.254 |
vg | +0.254 |
Neg logit contributions | |
owitz | -0.354 |
illance | -0.308 |
chio | -0.308 |
edi | -0.293 |
oulos | -0.288 |
Token | , |
Token ID | 11 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
anmar | +1.790 |
mil | +1.698 |
reluct | +1.635 |
hub | +1.621 |
fabrication | +1.610 |
Neg logit contributions | |
owitz | -2.139 |
illance | -1.875 |
chio | -1.854 |
edi | -1.767 |
oulos | -1.754 |
Token | comprising |
Token ID | 27918 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
anmar | +2.508 |
mil | +2.383 |
hub | +2.283 |
reluct | +2.280 |
fabrication | +2.257 |
Neg logit contributions | |
owitz | -3.110 |
illance | -2.742 |
chio | -2.704 |
edi | -2.583 |
oulos | -2.569 |
Token | lake |
Token ID | 13546 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
anmar | +1.403 |
mil | +1.329 |
reluct | +1.279 |
hub | +1.261 |
fabrication | +1.250 |
Neg logit contributions | |
owitz | -1.841 |
illance | -1.612 |
chio | -1.601 |
edi | -1.525 |
oulos | -1.516 |
Token | and |
Token ID | 290 |
Feature activation | +9.72e-02 |
Pos logit contributions | |
anmar | +0.228 |
mil | +0.214 |
reluct | +0.208 |
hub | +0.204 |
fabrication | +0.203 |
Neg logit contributions | |
owitz | -0.268 |
illance | -0.233 |
chio | -0.233 |
edi | -0.222 |
oulos | -0.220 |
Token | allowed |
Token ID | 3142 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
anmar | +0.333 |
mil | +0.315 |
reluct | +0.302 |
hub | +0.299 |
fabrication | +0.296 |
Neg logit contributions | |
owitz | -0.417 |
illance | -0.366 |
chio | -0.363 |
edi | -0.347 |
oulos | -0.344 |
Token | a |
Token ID | 257 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
anmar | +0.150 |
mil | +0.142 |
reluct | +0.136 |
hub | +0.134 |
fabrication | +0.133 |
Neg logit contributions | |
owitz | -0.194 |
illance | -0.169 |
chio | -0.168 |
edi | -0.161 |
oulos | -0.160 |
Token | 39 |
Token ID | 5014 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
anmar | +0.876 |
mil | +0.820 |
hub | +0.777 |
reluct | +0.777 |
fabrication | +0.766 |
Neg logit contributions | |
owitz | -1.613 |
illance | -1.449 |
chio | -1.432 |
edi | -1.379 |
oulos | -1.373 |
Token | . |
Token ID | 13 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
anmar | +0.607 |
mil | +0.572 |
reluct | +0.559 |
fabrication | +0.546 |
hub | +0.545 |
Neg logit contributions | |
owitz | -0.705 |
illance | -0.615 |
chio | -0.608 |
edi | -0.581 |
oulos | -0.573 |
Token | 6 |
Token ID | 21 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
anmar | +2.654 |
mil | +2.548 |
hub | +2.447 |
reluct | +2.433 |
fabrication | +2.418 |
Neg logit contributions | |
owitz | -2.529 |
illance | -2.188 |
chio | -2.156 |
edi | -2.040 |
oulos | -2.032 |
Token | passer |
Token ID | 30286 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
anmar | +4.127 |
mil | +3.883 |
hub | +3.799 |
snap | +3.777 |
fabrication | +3.586 |
Neg logit contributions | |
owitz | -9.302 |
illance | -8.478 |
chio | -8.320 |
ilon | -8.042 |
edi | -8.034 |
Token | rating |
Token ID | 7955 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
anmar | +2.399 |
mil | +2.256 |
reluct | +2.168 |
hub | +2.143 |
fabrication | +2.121 |
Neg logit contributions | |
owitz | -3.425 |
illance | -3.037 |
chio | -3.010 |
edi | -2.873 |
oulos | -2.856 |
Token | against |
Token ID | 1028 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
anmar | +0.598 |
mil | +0.566 |
reluct | +0.545 |
hub | +0.537 |
fabrication | +0.535 |
Neg logit contributions | |
owitz | -0.705 |
illance | -0.615 |
chio | -0.612 |
edi | -0.582 |
oulos | -0.579 |
Token | when |
Token ID | 618 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
anmar | +0.115 |
mil | +0.108 |
reluct | +0.104 |
hub | +0.102 |
fabrication | +0.101 |
Neg logit contributions | |
owitz | -0.141 |
illance | -0.122 |
chio | -0.122 |
edi | -0.117 |
oulos | -0.115 |
Token | targeted |
Token ID | 7977 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
anmar | +1.061 |
mil | +1.004 |
reluct | +0.962 |
hub | +0.951 |
fabrication | +0.946 |
Neg logit contributions | |
owitz | -1.354 |
illance | -1.189 |
chio | -1.179 |
edi | -1.130 |
oulos | -1.118 |
Token | Obama |
Token ID | 2486 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
owitz | +0.855 |
illance | +0.699 |
chio | +0.695 |
edi | +0.660 |
oulos | +0.653 |
Neg logit contributions | |
anmar | -1.044 |
mil | -0.974 |
reluct | -0.951 |
vg | -0.947 |
fabrication | -0.945 |
Token | is |
Token ID | 318 |
Feature activation | -9.30e-03 |
Pos logit contributions | |
anmar | +1.640 |
mil | +1.549 |
reluct | +1.482 |
hub | +1.477 |
fabrication | +1.462 |
Neg logit contributions | |
owitz | -2.278 |
illance | -2.017 |
chio | -1.995 |
edi | -1.909 |
oulos | -1.898 |
Token | the |
Token ID | 262 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
owitz | +0.040 |
chio | +0.035 |
illance | +0.035 |
edi | +0.034 |
oulos | +0.033 |
Neg logit contributions | |
anmar | -0.032 |
mil | -0.030 |
reluct | -0.028 |
fabrication | -0.028 |
hub | -0.028 |
Token | worst |
Token ID | 5290 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
anmar | +0.112 |
mil | +0.104 |
reluct | +0.100 |
vg | +0.098 |
fabrication | +0.098 |
Neg logit contributions | |
owitz | -0.157 |
chio | -0.138 |
illance | -0.137 |
edi | -0.132 |
oulos | -0.130 |
Token | ne |
Token ID | 497 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
owitz | +2.017 |
chio | +1.738 |
illance | +1.706 |
edi | +1.685 |
ilon | +1.636 |
Neg logit contributions | |
anmar | -1.687 |
mil | -1.561 |
reluct | -1.506 |
vg | -1.490 |
interstitial | -1.466 |
Token | |
Token ID | 3907 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
owitz | +0.855 |
chio | +0.747 |
illance | +0.733 |
edi | +0.714 |
ilon | +0.690 |
Neg logit contributions | |
anmar | -0.797 |
reluct | -0.728 |
mil | -0.720 |
fabrication | -0.708 |
interstitial | -0.703 |
Token | go |
Token ID | 2188 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
mil | +5.796 |
anmar | +5.704 |
vg | +5.243 |
hub | +5.222 |
fabrication | +5.102 |
Neg logit contributions | |
owitz | -7.573 |
illance | -6.753 |
oulos | -6.417 |
chio | -6.374 |
™: | -6.247 |
Token | |
Token ID | 3907 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
owitz | +1.858 |
illance | +1.623 |
chio | +1.613 |
edi | +1.548 |
oulos | +1.509 |
Neg logit contributions | |
anmar | -1.692 |
mil | -1.594 |
reluct | -1.574 |
hub | -1.533 |
fabrication | -1.529 |
Token | ti |
Token ID | 20259 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
anmar | +5.135 |
mil | +5.111 |
hub | +4.769 |
vg | +4.692 |
fabrication | +4.684 |
Neg logit contributions | |
owitz | -5.116 |
illance | -4.456 |
chio | -4.289 |
oulos | -4.128 |
edi | -4.112 |
Token | |
Token ID | 3907 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
anmar | +0.355 |
mil | +0.336 |
reluct | +0.329 |
fabrication | +0.321 |
hub | +0.320 |
Neg logit contributions | |
owitz | -0.366 |
illance | -0.316 |
chio | -0.314 |
edi | -0.298 |
oulos | -0.297 |
Token | at |
Token ID | 265 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
anmar | +4.501 |
mil | +4.313 |
hub | +4.080 |
reluct | +4.035 |
fabrication | +4.033 |
Neg logit contributions | |
owitz | -5.430 |
illance | -4.796 |
chio | -4.707 |
edi | -4.504 |
oulos | -4.496 |
Token |
|
Token ID | 198 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
anmar | +1.648 |
mil | +1.556 |
reluct | +1.494 |
hub | +1.484 |
fabrication | +1.474 |
Neg logit contributions | |
owitz | -1.961 |
illance | -1.725 |
chio | -1.699 |
oulos | -1.616 |
edi | -1.615 |
Token |
|
Token ID | 198 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
mil | +1.400 |
anmar | +1.374 |
hub | +1.310 |
vg | +1.281 |
fabrication | +1.261 |
Neg logit contributions | |
owitz | -2.233 |
illance | -2.054 |
chio | -1.986 |
oulos | -1.923 |
edi | -1.897 |
Token | This |
Token ID | 1212 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
anmar | +1.750 |
mil | +1.677 |
hub | +1.580 |
reluct | +1.568 |
fabrication | +1.568 |
Neg logit contributions | |
owitz | -2.354 |
illance | -2.094 |
chio | -2.057 |
edi | -1.965 |
oulos | -1.963 |
Token | post |
Token ID | 1281 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
anmar | +0.728 |
mil | +0.683 |
reluct | +0.648 |
hub | +0.642 |
fabrication | +0.634 |
Neg logit contributions | |
owitz | -1.211 |
illance | -1.082 |
chio | -1.071 |
edi | -1.029 |
oulos | -1.024 |
Token | only |
Token ID | 691 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
owitz | +0.532 |
illance | +0.473 |
chio | +0.466 |
edi | +0.448 |
oulos | +0.445 |
Neg logit contributions | |
anmar | -0.375 |
mil | -0.351 |
reluct | -0.338 |
fabrication | -0.330 |
hub | -0.330 |
Token | repeats |
Token ID | 29819 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
anmar | +0.267 |
mil | +0.250 |
reluct | +0.238 |
hub | +0.237 |
fabrication | +0.234 |
Neg logit contributions | |
owitz | -0.461 |
illance | -0.413 |
chio | -0.408 |
edi | -0.392 |
oulos | -0.390 |
Token | some |
Token ID | 617 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
anmar | +5.316 |
hub | +5.102 |
fabrication | +5.052 |
mil | +4.952 |
reluct | +4.860 |
Neg logit contributions | |
owitz | -7.991 |
illance | -7.226 |
chio | -7.037 |
edi | -6.784 |
ilon | -6.658 |
Token | basic |
Token ID | 4096 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
anmar | +2.218 |
mil | +2.073 |
hub | +1.989 |
reluct | +1.970 |
fabrication | +1.960 |
Neg logit contributions | |
owitz | -4.292 |
illance | -3.874 |
chio | -3.823 |
edi | -3.684 |
oulos | -3.666 |
Token | information |
Token ID | 1321 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
anmar | +2.722 |
mil | +2.569 |
hub | +2.503 |
fabrication | +2.467 |
reluct | +2.458 |
Neg logit contributions | |
owitz | -4.309 |
illance | -3.851 |
chio | -3.793 |
edi | -3.653 |
oulos | -3.626 |
Token | about |
Token ID | 546 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
anmar | +2.107 |
mil | +2.001 |
hub | +1.932 |
reluct | +1.912 |
fabrication | +1.906 |
Neg logit contributions | |
owitz | -2.983 |
illance | -2.656 |
chio | -2.622 |
edi | -2.507 |
oulos | -2.492 |
Token | GHC |
Token ID | 46615 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
anmar | +1.390 |
mil | +1.323 |
reluct | +1.272 |
hub | +1.271 |
fabrication | +1.259 |
Neg logit contributions | |
owitz | -1.643 |
illance | -1.443 |
chio | -1.423 |
edi | -1.357 |
oulos | -1.349 |
Token | I |
Token ID | 314 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
owitz | +1.498 |
illance | +1.316 |
chio | +1.315 |
edi | +1.269 |
oulos | +1.251 |
Neg logit contributions | |
anmar | -0.951 |
mil | -0.864 |
reluct | -0.838 |
hub | -0.812 |
vg | -0.808 |
Token | don |
Token ID | 836 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
anmar | +0.030 |
mil | +0.028 |
reluct | +0.026 |
hub | +0.026 |
fabrication | +0.026 |
Neg logit contributions | |
owitz | -0.054 |
illance | -0.049 |
chio | -0.048 |
edi | -0.046 |
oulos | -0.046 |
Token | � |
Token ID | 447 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
anmar | +0.129 |
mil | +0.125 |
hub | +0.118 |
fabrication | +0.117 |
vg | +0.116 |
Neg logit contributions | |
owitz | -0.173 |
illance | -0.154 |
chio | -0.152 |
oulos | -0.145 |
edi | -0.145 |
Token | � |
Token ID | 247 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
anmar | +2.113 |
mil | +2.045 |
hub | +1.961 |
fabrication | +1.914 |
vg | +1.909 |
Neg logit contributions | |
owitz | -2.067 |
illance | -1.806 |
chio | -1.777 |
oulos | -1.681 |
edi | -1.658 |
Token | t |
Token ID | 83 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
anmar | +0.043 |
mil | +0.040 |
reluct | +0.040 |
hub | +0.039 |
fabrication | +0.038 |
Neg logit contributions | |
owitz | -0.054 |
illance | -0.047 |
chio | -0.047 |
edi | -0.045 |
oulos | -0.044 |
Token | try |
Token ID | 1949 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
anmar | +0.721 |
mil | +0.678 |
hub | +0.642 |
reluct | +0.641 |
fabrication | +0.633 |
Neg logit contributions | |
owitz | -1.285 |
illance | -1.152 |
chio | -1.139 |
edi | -1.095 |
oulos | -1.091 |
Token | to |
Token ID | 284 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
anmar | +4.650 |
mil | +4.533 |
hub | +4.265 |
fabrication | +4.203 |
reluct | +4.152 |
Neg logit contributions | |
owitz | -8.716 |
illance | -7.795 |
chio | -7.781 |
oulos | -7.427 |
edi | -7.426 |
Token | communicate |
Token ID | 10996 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
anmar | +1.996 |
mil | +1.908 |
hub | +1.825 |
fabrication | +1.796 |
reluct | +1.770 |
Neg logit contributions | |
owitz | -3.378 |
illance | -3.025 |
chio | -2.960 |
oulos | -2.857 |
edi | -2.851 |
Token | with |
Token ID | 351 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
owitz | +0.329 |
illance | +0.291 |
chio | +0.289 |
edi | +0.276 |
oulos | +0.273 |
Neg logit contributions | |
anmar | -0.233 |
mil | -0.218 |
reluct | -0.210 |
hub | -0.207 |
fabrication | -0.205 |
Token | kids |
Token ID | 3988 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
anmar | +1.059 |
mil | +0.995 |
reluct | +0.947 |
hub | +0.943 |
fabrication | +0.932 |
Neg logit contributions | |
owitz | -1.726 |
illance | -1.541 |
chio | -1.525 |
edi | -1.463 |
oulos | -1.456 |
Token | . |
Token ID | 13 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
anmar | +2.019 |
mil | +1.937 |
hub | +1.857 |
reluct | +1.846 |
fabrication | +1.835 |
Neg logit contributions | |
owitz | -2.320 |
illance | -2.036 |
chio | -2.008 |
edi | -1.913 |
oulos | -1.905 |
Token | teachers |
Token ID | 7799 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
owitz | +2.653 |
illance | +2.200 |
chio | +2.187 |
edi | +2.065 |
oulos | +2.030 |
Neg logit contributions | |
anmar | -3.647 |
mil | -3.475 |
reluct | -3.349 |
hub | -3.310 |
vg | -3.298 |
Token | , |
Token ID | 11 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
owitz | +0.906 |
illance | +0.791 |
chio | +0.790 |
oulos | +0.754 |
edi | +0.751 |
Neg logit contributions | |
anmar | -0.687 |
mil | -0.640 |
reluct | -0.619 |
hub | -0.613 |
fabrication | -0.606 |
Token | who |
Token ID | 508 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
anmar | +1.013 |
mil | +0.961 |
reluct | +0.922 |
hub | +0.921 |
fabrication | +0.911 |
Neg logit contributions | |
owitz | -1.278 |
illance | -1.128 |
chio | -1.114 |
edi | -1.063 |
oulos | -1.057 |
Token | are |
Token ID | 389 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
anmar | +0.646 |
mil | +0.610 |
reluct | +0.582 |
hub | +0.581 |
fabrication | +0.574 |
Neg logit contributions | |
owitz | -0.970 |
illance | -0.864 |
chio | -0.852 |
edi | -0.817 |
oulos | -0.813 |
Token | less |
Token ID | 1342 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
anmar | +1.825 |
mil | +1.732 |
hub | +1.671 |
reluct | +1.666 |
fabrication | +1.650 |
Neg logit contributions | |
owitz | -2.722 |
illance | -2.456 |
chio | -2.403 |
edi | -2.295 |
oulos | -2.282 |
Token | likely |
Token ID | 1884 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
anmar | +0.860 |
mil | +0.810 |
reluct | +0.774 |
hub | +0.770 |
fabrication | +0.762 |
Neg logit contributions | |
owitz | -1.240 |
illance | -1.100 |
chio | -1.087 |
edi | -1.043 |
oulos | -1.038 |
Token | to |
Token ID | 284 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
anmar | +4.234 |
mil | +4.095 |
hub | +3.922 |
reluct | +3.867 |
fabrication | +3.821 |
Neg logit contributions | |
owitz | -8.918 |
illance | -8.096 |
chio | -8.039 |
edi | -7.668 |
oulos | -7.576 |
Token | have |
Token ID | 423 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
anmar | +2.720 |
mil | +2.605 |
hub | +2.561 |
fabrication | +2.506 |
snap | +2.502 |
Neg logit contributions | |
owitz | -4.738 |
illance | -4.282 |
chio | -4.161 |
oulos | -3.984 |
edi | -3.984 |
Token | DB |
Token ID | 20137 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
anmar | +1.010 |
mil | +0.961 |
hub | +0.925 |
reluct | +0.924 |
fabrication | +0.915 |
Neg logit contributions | |
owitz | -1.179 |
illance | -1.036 |
chio | -1.021 |
edi | -0.972 |
oulos | -0.967 |
Token | pensions |
Token ID | 27581 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
anmar | +4.255 |
mil | +4.100 |
reluct | +3.915 |
hub | +3.909 |
fabrication | +3.888 |
Neg logit contributions | |
owitz | -5.214 |
illance | -4.605 |
chio | -4.522 |
oulos | -4.257 |
ilon | -4.254 |
Token | , |
Token ID | 11 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
owitz | +0.131 |
illance | +0.115 |
chio | +0.114 |
oulos | +0.110 |
edi | +0.110 |
Neg logit contributions | |
anmar | -0.093 |
mil | -0.087 |
reluct | -0.084 |
hub | -0.083 |
fabrication | -0.082 |
Token | or |
Token ID | 393 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
anmar | +1.617 |
mil | +1.540 |
hub | +1.473 |
reluct | +1.468 |
fabrication | +1.459 |
Neg logit contributions | |
owitz | -2.073 |
illance | -1.839 |
chio | -1.816 |
edi | -1.727 |
oulos | -1.718 |
Token | his |
Token ID | 465 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
owitz | +0.097 |
illance | +0.085 |
chio | +0.084 |
edi | +0.080 |
oulos | +0.080 |
Neg logit contributions | |
anmar | -0.080 |
mil | -0.076 |
reluct | -0.073 |
hub | -0.072 |
fabrication | -0.072 |
Token | actions |
Token ID | 4028 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
owitz | +1.080 |
illance | +0.956 |
chio | +0.946 |
oulos | +0.905 |
edi | +0.901 |
Neg logit contributions | |
anmar | -0.723 |
mil | -0.692 |
reluct | -0.649 |
vg | -0.637 |
hub | -0.633 |
Token | . |
Token ID | 13 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
owitz | +1.491 |
illance | +1.283 |
chio | +1.267 |
edi | +1.205 |
oulos | +1.204 |
Neg logit contributions | |
anmar | -1.517 |
mil | -1.442 |
reluct | -1.403 |
fabrication | -1.376 |
hub | -1.374 |
Token | Nor |
Token ID | 5414 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
anmar | +1.468 |
mil | +1.392 |
hub | +1.326 |
reluct | +1.317 |
fabrication | +1.309 |
Neg logit contributions | |
owitz | -2.088 |
illance | -1.860 |
chio | -1.834 |
edi | -1.756 |
oulos | -1.747 |
Token | do |
Token ID | 466 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
anmar | +0.432 |
mil | +0.403 |
reluct | +0.384 |
hub | +0.378 |
fabrication | +0.371 |
Neg logit contributions | |
owitz | -0.790 |
illance | -0.707 |
chio | -0.700 |
edi | -0.673 |
oulos | -0.670 |
Token | I |
Token ID | 314 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
anmar | +4.160 |
mil | +3.772 |
hub | +3.699 |
fabrication | +3.650 |
reluct | +3.584 |
Neg logit contributions | |
owitz | -9.189 |
illance | -8.399 |
chio | -8.335 |
oulos | -7.905 |
ilon | -7.902 |
Token | mean |
Token ID | 1612 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
anmar | +2.960 |
mil | +2.804 |
hub | +2.718 |
fabrication | +2.665 |
snap | +2.608 |
Neg logit contributions | |
owitz | -5.736 |
illance | -5.160 |
chio | -5.066 |
edi | -4.867 |
oulos | -4.860 |
Token | to |
Token ID | 284 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
anmar | +0.189 |
mil | +0.179 |
reluct | +0.171 |
hub | +0.169 |
fabrication | +0.166 |
Neg logit contributions | |
owitz | -0.285 |
illance | -0.252 |
chio | -0.250 |
oulos | -0.239 |
edi | -0.239 |
Token | imply |
Token ID | 20135 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
anmar | +0.629 |
mil | +0.590 |
reluct | +0.564 |
hub | +0.558 |
fabrication | +0.551 |
Neg logit contributions | |
owitz | -1.010 |
illance | -0.902 |
chio | -0.894 |
edi | -0.857 |
oulos | -0.853 |
Token | that |
Token ID | 326 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
anmar | +0.740 |
mil | +0.690 |
reluct | +0.650 |
hub | +0.642 |
fabrication | +0.631 |
Neg logit contributions | |
owitz | -1.485 |
illance | -1.336 |
chio | -1.325 |
edi | -1.276 |
oulos | -1.270 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
anmar | +0.156 |
mil | +0.146 |
reluct | +0.145 |
fabrication | +0.141 |
hub | +0.140 |
Neg logit contributions | |
owitz | -0.191 |
illance | -0.167 |
chio | -0.166 |
edi | -0.157 |
oulos | -0.157 |
Token |
|
Token ID | 198 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
owitz | +0.767 |
illance | +0.680 |
chio | +0.670 |
edi | +0.640 |
oulos | +0.638 |
Neg logit contributions | |
anmar | -0.584 |
mil | -0.558 |
hub | -0.532 |
fabrication | -0.525 |
reluct | -0.525 |
Token | Now |
Token ID | 3844 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
owitz | +0.331 |
illance | +0.289 |
chio | +0.287 |
edi | +0.274 |
oulos | +0.269 |
Neg logit contributions | |
anmar | -0.280 |
reluct | -0.262 |
mil | -0.262 |
hub | -0.256 |
fabrication | -0.255 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
owitz | +0.992 |
illance | +0.874 |
chio | +0.866 |
edi | +0.828 |
oulos | +0.825 |
Neg logit contributions | |
anmar | -0.727 |
mil | -0.692 |
reluct | -0.666 |
fabrication | -0.654 |
hub | -0.653 |
Token | : |
Token ID | 25 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
anmar | +0.618 |
mil | +0.592 |
reluct | +0.574 |
hub | +0.567 |
fabrication | +0.566 |
Neg logit contributions | |
owitz | -0.578 |
illance | -0.498 |
chio | -0.490 |
edi | -0.462 |
oulos | -0.459 |
Token | Watch |
Token ID | 6305 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
anmar | +0.309 |
mil | +0.298 |
hub | +0.289 |
fabrication | +0.283 |
reluct | +0.281 |
Neg logit contributions | |
owitz | -0.358 |
chio | -0.316 |
illance | -0.308 |
edi | -0.295 |
oulos | -0.295 |
Token | this |
Token ID | 428 |
Feature activation | -7.36e-02 |
Pos logit contributions | |
owitz | +7.831 |
chio | +6.647 |
illance | +6.631 |
edi | +6.374 |
oulos | +6.153 |
Neg logit contributions | |
anmar | -8.103 |
reluct | -7.615 |
carbohyd | -7.336 |
mil | -7.194 |
confir | -7.176 |
Token | : |
Token ID | 25 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
owitz | +0.274 |
illance | +0.236 |
chio | +0.233 |
edi | +0.220 |
oulos | +0.219 |
Neg logit contributions | |
anmar | -0.293 |
mil | -0.280 |
reluct | -0.272 |
hub | -0.268 |
fabrication | -0.267 |
Token | Top |
Token ID | 5849 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
anmar | +2.040 |
mil | +1.936 |
hub | +1.859 |
reluct | +1.817 |
fabrication | +1.813 |
Neg logit contributions | |
owitz | -2.848 |
illance | -2.534 |
chio | -2.501 |
edi | -2.397 |
oulos | -2.382 |
Token | 5 |
Token ID | 642 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
owitz | +1.357 |
illance | +1.203 |
chio | +1.187 |
edi | +1.138 |
oulos | +1.129 |
Neg logit contributions | |
anmar | -1.016 |
mil | -0.970 |
reluct | -0.939 |
fabrication | -0.920 |
vg | -0.905 |
Token | best |
Token ID | 1266 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
anmar | +0.024 |
mil | +0.023 |
reluct | +0.021 |
fabrication | +0.021 |
hub | +0.021 |
Neg logit contributions | |
owitz | -0.037 |
illance | -0.033 |
chio | -0.033 |
edi | -0.031 |
oulos | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
owitz | +0.979 |
illance | +0.860 |
chio | +0.843 |
edi | +0.810 |
oulos | +0.806 |
Neg logit contributions | |
anmar | -0.830 |
mil | -0.777 |
reluct | -0.755 |
hub | -0.738 |
interstitial | -0.736 |
Token | � |
Token ID | 447 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
anmar | +0.036 |
mil | +0.033 |
reluct | +0.033 |
fabrication | +0.032 |
hub | +0.032 |
Neg logit contributions | |
owitz | -0.055 |
illance | -0.048 |
chio | -0.048 |
edi | -0.046 |
oulos | -0.046 |
Token | � |
Token ID | 251 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
owitz | +0.666 |
illance | +0.575 |
chio | +0.568 |
edi | +0.541 |
oulos | +0.534 |
Neg logit contributions | |
anmar | -0.670 |
mil | -0.638 |
reluct | -0.620 |
hub | -0.613 |
fabrication | -0.610 |
Token |
|
Token ID | 198 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
anmar | +0.170 |
mil | +0.159 |
reluct | +0.155 |
hub | +0.153 |
fabrication | +0.152 |
Neg logit contributions | |
owitz | -0.190 |
illance | -0.165 |
chio | -0.164 |
edi | -0.156 |
oulos | -0.155 |
Token |
|
Token ID | 198 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
owitz | +1.390 |
illance | +1.223 |
chio | +1.209 |
edi | +1.155 |
oulos | +1.147 |
Neg logit contributions | |
anmar | -1.102 |
mil | -1.041 |
reluct | -1.008 |
hub | -0.997 |
fabrication | -0.988 |
Token | Watch |
Token ID | 10723 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
owitz | +0.700 |
illance | +0.607 |
chio | +0.607 |
edi | +0.576 |
oulos | +0.568 |
Neg logit contributions | |
anmar | -0.589 |
reluct | -0.549 |
mil | -0.546 |
hub | -0.537 |
fabrication | -0.532 |
Token | the |
Token ID | 262 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
owitz | +8.215 |
illance | +7.117 |
chio | +6.871 |
edi | +6.672 |
oulos | +6.588 |
Neg logit contributions | |
anmar | -7.064 |
reluct | -6.544 |
mil | -6.429 |
confir | -6.298 |
vg | -6.284 |
Token | moment |
Token ID | 2589 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
owitz | +3.800 |
illance | +3.359 |
chio | +3.352 |
oulos | +3.183 |
edi | +3.182 |
Neg logit contributions | |
anmar | -2.552 |
mil | -2.344 |
reluct | -2.273 |
vg | -2.193 |
interstitial | -2.138 |
Token | unfold |
Token ID | 16631 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
anmar | +0.038 |
mil | +0.035 |
reluct | +0.034 |
hub | +0.034 |
fabrication | +0.033 |
Neg logit contributions | |
owitz | -0.049 |
illance | -0.043 |
chio | -0.042 |
edi | -0.041 |
oulos | -0.040 |
Token | below |
Token ID | 2174 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
anmar | +2.409 |
mil | +2.295 |
hub | +2.218 |
reluct | +2.181 |
fabrication | +2.165 |
Neg logit contributions | |
owitz | -3.281 |
illance | -2.912 |
chio | -2.881 |
edi | -2.759 |
oulos | -2.726 |
Token | : |
Token ID | 25 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
owitz | +0.237 |
illance | +0.205 |
chio | +0.200 |
edi | +0.191 |
oulos | +0.190 |
Neg logit contributions | |
anmar | -0.252 |
mil | -0.239 |
reluct | -0.233 |
hub | -0.229 |
fabrication | -0.229 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
owitz | +1.414 |
illance | +1.229 |
chio | +1.221 |
edi | +1.163 |
oulos | +1.160 |
Neg logit contributions | |
anmar | -1.166 |
mil | -1.087 |
reluct | -1.078 |
fabrication | -1.044 |
hub | -1.043 |
Token | Please |
Token ID | 5492 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
owitz | +1.934 |
illance | +1.671 |
chio | +1.666 |
edi | +1.594 |
ilon | +1.545 |
Neg logit contributions | |
anmar | -1.734 |
reluct | -1.671 |
hub | -1.618 |
fabrication | -1.589 |
mil | -1.589 |
Token | enable |
Token ID | 7139 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
owitz | +1.644 |
illance | +1.439 |
chio | +1.419 |
edi | +1.363 |
ilon | +1.342 |
Neg logit contributions | |
anmar | -1.435 |
mil | -1.360 |
reluct | -1.316 |
fabrication | -1.282 |
vg | -1.281 |
Token | Javascript |
Token ID | 24711 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
anmar | +1.909 |
mil | +1.803 |
reluct | +1.720 |
hub | +1.711 |
fabrication | +1.693 |
Neg logit contributions | |
owitz | -2.895 |
illance | -2.577 |
chio | -2.543 |
edi | -2.439 |
oulos | -2.428 |
Token | to |
Token ID | 284 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
mil | +2.562 |
anmar | +2.531 |
hub | +2.412 |
snap | +2.270 |
vg | +2.263 |
Neg logit contributions | |
owitz | -5.778 |
illance | -5.225 |
chio | -5.200 |
oulos | -5.017 |
edi | -4.939 |
Token | watch |
Token ID | 2342 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
owitz | +1.197 |
illance | +1.053 |
chio | +1.040 |
edi | +0.990 |
oulos | +0.984 |
Neg logit contributions | |
anmar | -1.003 |
mil | -0.952 |
reluct | -0.919 |
hub | -0.910 |
fabrication | -0.903 |
Token | this |
Token ID | 428 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
owitz | +8.085 |
chio | +7.018 |
illance | +6.933 |
edi | +6.563 |
oded | +6.503 |
Neg logit contributions | |
anmar | -7.035 |
reluct | -7.020 |
confir | -6.670 |
carbohyd | -6.511 |
advoc | -6.255 |
Token | video |
Token ID | 2008 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
anmar | +0.048 |
mil | +0.045 |
hub | +0.043 |
fabrication | +0.043 |
reluct | +0.043 |
Neg logit contributions | |
owitz | -0.082 |
illance | -0.073 |
chio | -0.072 |
edi | -0.070 |
oulos | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
owitz | +0.265 |
illance | +0.237 |
chio | +0.232 |
edi | +0.223 |
oulos | +0.222 |
Neg logit contributions | |
anmar | -0.191 |
mil | -0.185 |
hub | -0.175 |
fabrication | -0.171 |
vg | -0.170 |
Token |
|
Token ID | 198 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
anmar | +0.350 |
mil | +0.342 |
hub | +0.322 |
fabrication | +0.316 |
vg | +0.314 |
Neg logit contributions | |
owitz | -0.490 |
illance | -0.441 |
chio | -0.431 |
edi | -0.413 |
oulos | -0.413 |
Token | V |
Token ID | 53 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
anmar | +0.229 |
reluct | +0.213 |
mil | +0.211 |
hub | +0.208 |
fabrication | +0.206 |
Neg logit contributions | |
owitz | -0.279 |
illance | -0.242 |
chio | -0.241 |
edi | -0.230 |
oulos | -0.227 |
Token | career |
Token ID | 3451 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
owitz | +0.544 |
illance | +0.480 |
chio | +0.471 |
edi | +0.449 |
oulos | +0.447 |
Neg logit contributions | |
anmar | -0.448 |
mil | -0.428 |
hub | -0.416 |
fabrication | -0.410 |
reluct | -0.406 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
anmar | +1.311 |
mil | +1.254 |
reluct | +1.228 |
hub | +1.212 |
fabrication | +1.209 |
Neg logit contributions | |
owitz | -0.953 |
illance | -0.797 |
chio | -0.790 |
edi | -0.736 |
oulos | -0.735 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
anmar | +1.208 |
mil | +1.145 |
reluct | +1.096 |
hub | +1.093 |
fabrication | +1.081 |
Neg logit contributions | |
owitz | -1.623 |
illance | -1.436 |
chio | -1.418 |
edi | -1.356 |
oulos | -1.349 |
Token | left |
Token ID | 1364 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
anmar | +0.412 |
mil | +0.385 |
reluct | +0.364 |
fabrication | +0.358 |
vg | +0.357 |
Neg logit contributions | |
owitz | -0.683 |
chio | -0.598 |
illance | -0.596 |
edi | -0.574 |
oulos | -0.567 |
Token | , |
Token ID | 11 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
owitz | +0.395 |
illance | +0.332 |
chio | +0.330 |
edi | +0.310 |
oulos | +0.304 |
Neg logit contributions | |
anmar | -0.494 |
mil | -0.470 |
reluct | -0.460 |
fabrication | -0.452 |
vg | -0.450 |
Token | watches |
Token ID | 16860 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
anmar | +0.890 |
mil | +0.836 |
reluct | +0.798 |
fabrication | +0.788 |
hub | +0.782 |
Neg logit contributions | |
owitz | -1.233 |
chio | -1.079 |
illance | -1.077 |
edi | -1.029 |
oulos | -1.022 |
Token | election |
Token ID | 3071 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
owitz | +7.673 |
chio | +6.711 |
illance | +6.406 |
edi | +6.216 |
oulos | +6.102 |
Neg logit contributions | |
anmar | -7.002 |
mil | -6.585 |
reluct | -6.500 |
vg | -6.237 |
carbohyd | -6.230 |
Token | results |
Token ID | 2482 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
anmar | +1.690 |
mil | +1.588 |
reluct | +1.517 |
hub | +1.505 |
fabrication | +1.489 |
Neg logit contributions | |
owitz | -2.644 |
illance | -2.354 |
chio | -2.331 |
edi | -2.235 |
oulos | -2.222 |
Token | with |
Token ID | 351 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
anmar | +1.243 |
mil | +1.175 |
reluct | +1.124 |
hub | +1.120 |
fabrication | +1.108 |
Neg logit contributions | |
owitz | -1.737 |
illance | -1.539 |
chio | -1.521 |
edi | -1.456 |
oulos | -1.448 |
Token | granddaughter |
Token ID | 46458 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
anmar | +0.039 |
mil | +0.037 |
reluct | +0.036 |
fabrication | +0.035 |
vg | +0.034 |
Neg logit contributions | |
owitz | -0.053 |
illance | -0.046 |
chio | -0.046 |
oulos | -0.044 |
edi | -0.044 |
Token | Kara |
Token ID | 34856 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
anmar | +2.454 |
mil | +2.331 |
hub | +2.230 |
reluct | +2.219 |
fabrication | +2.196 |
Neg logit contributions | |
owitz | -3.292 |
illance | -2.928 |
chio | -2.881 |
edi | -2.753 |
oulos | -2.743 |
Token | including |
Token ID | 1390 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
owitz | +2.004 |
illance | +1.742 |
chio | +1.705 |
edi | +1.649 |
oulos | +1.629 |
Neg logit contributions | |
anmar | -1.751 |
mil | -1.642 |
reluct | -1.591 |
hub | -1.571 |
fabrication | -1.557 |
Token | House |
Token ID | 2097 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
owitz | +1.512 |
illance | +1.318 |
chio | +1.300 |
edi | +1.242 |
oulos | +1.236 |
Neg logit contributions | |
anmar | -1.280 |
mil | -1.210 |
reluct | -1.170 |
hub | -1.146 |
fabrication | -1.141 |
Token | Majority |
Token ID | 22171 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
owitz | +2.799 |
illance | +2.322 |
chio | +2.302 |
edi | +2.131 |
oulos | +2.096 |
Neg logit contributions | |
anmar | -4.219 |
mil | -3.988 |
reluct | -3.944 |
hub | -3.856 |
fabrication | -3.850 |
Token | Whip |
Token ID | 40930 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
owitz | +1.807 |
illance | +1.608 |
chio | +1.584 |
edi | +1.518 |
oulos | +1.492 |
Neg logit contributions | |
anmar | -1.497 |
mil | -1.395 |
reluct | -1.366 |
fabrication | -1.339 |
hub | -1.330 |
Token | Steve |
Token ID | 6542 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
owitz | +3.118 |
chio | +2.660 |
illance | +2.649 |
edi | +2.575 |
oulos | +2.551 |
Neg logit contributions | |
anmar | -2.797 |
mil | -2.628 |
reluct | -2.614 |
hub | -2.515 |
confir | -2.512 |
Token | Scal |
Token ID | 34529 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
owitz | +1.458 |
illance | +0.867 |
chio | +0.820 |
edi | +0.634 |
oulos | +0.595 |
Neg logit contributions | |
anmar | -7.510 |
reluct | -7.387 |
mil | -7.234 |
confir | -7.195 |
fabrication | -7.100 |
Token | ise |
Token ID | 786 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
owitz | +2.350 |
chio | +2.018 |
edi | +1.622 |
itar | +1.318 |
illance | +1.228 |
Neg logit contributions | |
reluct | -12.498 |
anmar | -12.301 |
confir | -11.929 |
interstitial | -11.800 |
hub | -11.744 |
Token | ( |
Token ID | 357 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
owitz | +1.141 |
illance | +0.982 |
chio | +0.972 |
oulos | +0.921 |
edi | +0.921 |
Neg logit contributions | |
anmar | -1.259 |
mil | -1.186 |
reluct | -1.174 |
hub | -1.148 |
fabrication | -1.142 |
Token | R |
Token ID | 49 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
owitz | +0.805 |
illance | +0.698 |
chio | +0.697 |
edi | +0.662 |
oulos | +0.660 |
Neg logit contributions | |
anmar | -0.765 |
mil | -0.710 |
reluct | -0.709 |
hub | -0.700 |
fabrication | -0.691 |
Token | - |
Token ID | 12 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
anmar | +1.298 |
mil | +1.234 |
hub | +1.176 |
reluct | +1.173 |
fabrication | +1.162 |
Neg logit contributions | |
owitz | -1.629 |
illance | -1.433 |
chio | -1.417 |
edi | -1.354 |
oulos | -1.343 |
Token | La |
Token ID | 14772 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
owitz | +0.460 |
illance | +0.371 |
chio | +0.363 |
edi | +0.333 |
oulos | +0.330 |
Neg logit contributions | |
anmar | -0.902 |
mil | -0.868 |
reluct | -0.848 |
hub | -0.846 |
fabrication | -0.840 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
anmar | +0.205 |
mil | +0.192 |
reluct | +0.188 |
hub | +0.185 |
fabrication | +0.183 |
Neg logit contributions | |
owitz | -0.252 |
illance | -0.221 |
chio | -0.219 |
edi | -0.209 |
oulos | -0.207 |
Token |
|
Token ID | 198 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
owitz | +0.511 |
illance | +0.455 |
chio | +0.447 |
edi | +0.427 |
oulos | +0.426 |
Neg logit contributions | |
anmar | -0.382 |
mil | -0.367 |
hub | -0.349 |
fabrication | -0.344 |
reluct | -0.340 |
Token | Under |
Token ID | 9203 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
owitz | +0.155 |
illance | +0.134 |
chio | +0.133 |
edi | +0.126 |
oulos | +0.124 |
Neg logit contributions | |
anmar | -0.151 |
mil | -0.141 |
reluct | -0.140 |
hub | -0.138 |
fabrication | -0.137 |
Token | chain |
Token ID | 6333 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
owitz | +0.736 |
illance | +0.635 |
chio | +0.629 |
edi | +0.597 |
oulos | +0.594 |
Neg logit contributions | |
anmar | -0.643 |
mil | -0.606 |
reluct | -0.591 |
hub | -0.579 |
fabrication | -0.577 |
Token | - |
Token ID | 12 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
anmar | +1.925 |
mil | +1.794 |
reluct | +1.728 |
hub | +1.710 |
fabrication | +1.694 |
Neg logit contributions | |
owitz | -2.768 |
illance | -2.472 |
chio | -2.433 |
edi | -2.332 |
ilon | -2.304 |
Token | m |
Token ID | 76 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
owitz | +2.247 |
illance | +2.041 |
chio | +2.028 |
edi | +1.920 |
ilon | +1.903 |
Neg logit contributions | |
anmar | -1.887 |
reluct | -1.784 |
hub | -1.717 |
fabrication | -1.706 |
confir | -1.662 |
Token | igration |
Token ID | 4254 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
owitz | +3.085 |
illance | +2.282 |
chio | +2.100 |
edi | +1.883 |
oulos | +1.833 |
Neg logit contributions | |
anmar | -11.617 |
reluct | -11.301 |
mil | -10.947 |
fabrication | -10.845 |
hub | -10.820 |
Token | policies |
Token ID | 4788 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
owitz | +2.906 |
illance | +2.572 |
chio | +2.524 |
edi | +2.420 |
ilon | +2.386 |
Neg logit contributions | |
anmar | -2.136 |
mil | -1.970 |
reluct | -1.893 |
vg | -1.866 |
fabrication | -1.844 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
owitz | +0.538 |
illance | +0.464 |
chio | +0.458 |
edi | +0.434 |
oulos | +0.432 |
Neg logit contributions | |
anmar | -0.536 |
mil | -0.510 |
reluct | -0.494 |
hub | -0.489 |
fabrication | -0.486 |
Token | immigrants |
Token ID | 7971 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
owitz | +0.636 |
illance | +0.562 |
chio | +0.554 |
edi | +0.532 |
oulos | +0.527 |
Neg logit contributions | |
anmar | -0.470 |
mil | -0.440 |
reluct | -0.423 |
hub | -0.416 |
fabrication | -0.415 |
Token | granted |
Token ID | 7520 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
owitz | +0.204 |
illance | +0.180 |
chio | +0.179 |
edi | +0.171 |
oulos | +0.170 |
Neg logit contributions | |
anmar | -0.155 |
mil | -0.145 |
reluct | -0.139 |
hub | -0.137 |
fabrication | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
owitz | +1.500 |
illance | +1.297 |
chio | +1.282 |
edi | +1.222 |
oulos | +1.210 |
Neg logit contributions | |
anmar | -1.468 |
mil | -1.387 |
reluct | -1.342 |
hub | -1.311 |
interstitial | -1.307 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
anmar | +0.410 |
mil | +0.384 |
reluct | +0.379 |
hub | +0.369 |
fabrication | +0.368 |
Neg logit contributions | |
owitz | -0.493 |
illance | -0.430 |
chio | -0.425 |
edi | -0.406 |
oulos | -0.403 |
Token | Now |
Token ID | 3844 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
owitz | +1.605 |
illance | +1.386 |
chio | +1.383 |
edi | +1.322 |
ilon | +1.283 |
Neg logit contributions | |
anmar | -1.444 |
reluct | -1.389 |
hub | -1.347 |
mil | -1.327 |
fabrication | -1.323 |
Token | playing |
Token ID | 2712 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
owitz | +1.499 |
illance | +1.324 |
chio | +1.310 |
edi | +1.266 |
oulos | +1.257 |
Neg logit contributions | |
anmar | -0.946 |
mil | -0.892 |
reluct | -0.863 |
fabrication | -0.836 |
hub | -0.834 |
Token | : |
Token ID | 25 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
anmar | +0.160 |
mil | +0.153 |
reluct | +0.149 |
hub | +0.147 |
fabrication | +0.147 |
Neg logit contributions | |
owitz | -0.151 |
illance | -0.130 |
chio | -0.128 |
edi | -0.121 |
oulos | -0.120 |
Token | Watch |
Token ID | 6305 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
anmar | +1.488 |
mil | +1.435 |
hub | +1.388 |
fabrication | +1.355 |
snap | +1.348 |
Neg logit contributions | |
owitz | -1.740 |
chio | -1.545 |
illance | -1.506 |
edi | -1.445 |
oulos | -1.443 |
Token | this |
Token ID | 428 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
owitz | +7.563 |
illance | +6.407 |
chio | +6.241 |
edi | +5.958 |
oulos | +5.946 |
Neg logit contributions | |
anmar | -7.581 |
reluct | -7.246 |
confir | -6.852 |
carbohyd | -6.843 |
mil | -6.677 |
Token | : |
Token ID | 25 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
owitz | +0.138 |
illance | +0.118 |
chio | +0.117 |
edi | +0.110 |
oulos | +0.110 |
Neg logit contributions | |
anmar | -0.152 |
mil | -0.144 |
reluct | -0.142 |
fabrication | -0.138 |
hub | -0.138 |
Token | US |
Token ID | 1294 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
anmar | +1.996 |
mil | +1.897 |
hub | +1.818 |
reluct | +1.815 |
fabrication | +1.796 |
Neg logit contributions | |
owitz | -2.436 |
illance | -2.146 |
chio | -2.119 |
edi | -2.021 |
oulos | -2.010 |
Token | Army |
Token ID | 5407 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
owitz | +1.597 |
illance | +1.412 |
chio | +1.386 |
edi | +1.327 |
oulos | +1.308 |
Neg logit contributions | |
anmar | -1.242 |
mil | -1.163 |
reluct | -1.128 |
fabrication | -1.107 |
hub | -1.106 |
Token | tests |
Token ID | 5254 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
owitz | +2.467 |
illance | +2.176 |
chio | +2.141 |
edi | +2.053 |
™: | +2.014 |
Neg logit contributions | |
anmar | -1.868 |
mil | -1.708 |
reluct | -1.659 |
vg | -1.643 |
hub | -1.623 |
Token | of |
Token ID | 286 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
owitz | +0.026 |
illance | +0.022 |
chio | +0.022 |
edi | +0.022 |
oulos | +0.021 |
Neg logit contributions | |
anmar | -0.016 |
mil | -0.015 |
reluct | -0.014 |
fabrication | -0.014 |
hub | -0.014 |
Token | last |
Token ID | 938 |
Feature activation | -7.59e-03 |
Pos logit contributions | |
anmar | +0.094 |
mil | +0.089 |
reluct | +0.086 |
fabrication | +0.085 |
hub | +0.085 |
Neg logit contributions | |
owitz | -0.109 |
illance | -0.095 |
chio | -0.094 |
edi | -0.090 |
oulos | -0.089 |
Token | year |
Token ID | 614 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
owitz | +0.034 |
illance | +0.030 |
chio | +0.030 |
edi | +0.029 |
oulos | +0.028 |
Neg logit contributions | |
anmar | -0.024 |
mil | -0.023 |
reluct | -0.022 |
hub | -0.022 |
fabrication | -0.022 |
Token | 's |
Token ID | 338 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
anmar | +0.848 |
mil | +0.813 |
hub | +0.784 |
reluct | +0.781 |
fabrication | +0.776 |
Neg logit contributions | |
owitz | -0.735 |
illance | -0.632 |
chio | -0.623 |
edi | -0.586 |
oulos | -0.583 |
Token | Golden |
Token ID | 8407 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
owitz | +0.611 |
illance | +0.538 |
chio | +0.531 |
edi | +0.509 |
oulos | +0.502 |
Neg logit contributions | |
anmar | -0.479 |
mil | -0.451 |
reluct | -0.438 |
hub | -0.428 |
fabrication | -0.427 |
Token | Glob |
Token ID | 40713 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
owitz | +1.011 |
illance | +0.842 |
chio | +0.826 |
edi | +0.780 |
oulos | +0.763 |
Neg logit contributions | |
anmar | -1.433 |
mil | -1.373 |
reluct | -1.341 |
hub | -1.323 |
fabrication | -1.320 |
Token | es |
Token ID | 274 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
owitz | +6.036 |
chio | +4.915 |
illance | +4.863 |
edi | +4.838 |
oulos | +4.704 |
Neg logit contributions | |
anmar | -8.589 |
reluct | -8.259 |
mil | -8.156 |
confir | -8.008 |
fabrication | -7.867 |
Token | , |
Token ID | 11 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
owitz | +0.605 |
illance | +0.524 |
chio | +0.515 |
edi | +0.490 |
oulos | +0.486 |
Neg logit contributions | |
anmar | -0.619 |
mil | -0.588 |
reluct | -0.570 |
hub | -0.563 |
fabrication | -0.560 |
Token | has |
Token ID | 468 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
anmar | +0.080 |
mil | +0.074 |
reluct | +0.071 |
hub | +0.070 |
fabrication | +0.070 |
Neg logit contributions | |
owitz | -0.112 |
illance | -0.099 |
chio | -0.098 |
edi | -0.094 |
oulos | -0.094 |
Token | been |
Token ID | 587 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
owitz | +1.239 |
illance | +1.067 |
chio | +1.058 |
edi | +1.008 |
oulos | +1.005 |
Neg logit contributions | |
anmar | -1.209 |
mil | -1.142 |
reluct | -1.105 |
hub | -1.085 |
fabrication | -1.082 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
anmar | +0.896 |
mil | +0.849 |
reluct | +0.817 |
hub | +0.812 |
fabrication | +0.806 |
Neg logit contributions | |
owitz | -1.087 |
illance | -0.955 |
chio | -0.942 |
edi | -0.901 |
oulos | -0.895 |
Token | even |
Token ID | 772 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
owitz | +3.361 |
chio | +3.002 |
illance | +2.986 |
edi | +2.860 |
ilon | +2.802 |
Neg logit contributions | |
anmar | -2.427 |
reluct | -2.227 |
mil | -2.223 |
interstitial | -2.136 |
hub | -2.094 |
Token | set |
Token ID | 900 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
owitz | +0.575 |
illance | +0.516 |
chio | +0.514 |
edi | +0.493 |
oulos | +0.488 |
Neg logit contributions | |
anmar | -0.326 |
mil | -0.303 |
reluct | -0.291 |
hub | -0.284 |
fabrication | -0.281 |
Token | an |
Token ID | 281 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
owitz | +1.098 |
illance | +0.971 |
chio | +0.965 |
edi | +0.924 |
oulos | +0.911 |
Neg logit contributions | |
anmar | -0.780 |
mil | -0.723 |
reluct | -0.706 |
vg | -0.683 |
hub | -0.679 |
Token | alarm |
Token ID | 10436 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
owitz | +1.376 |
illance | +1.201 |
chio | +1.182 |
edi | +1.133 |
oulos | +1.128 |
Neg logit contributions | |
anmar | -1.267 |
mil | -1.208 |
reluct | -1.163 |
hub | -1.140 |
fabrication | -1.135 |
Token | and |
Token ID | 290 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
owitz | +1.902 |
chio | +1.689 |
illance | +1.681 |
edi | +1.578 |
ilon | +1.578 |
Neg logit contributions | |
anmar | -1.454 |
mil | -1.339 |
reluct | -1.309 |
fabrication | -1.266 |
interstitial | -1.262 |
Token | watch |
Token ID | 2342 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
owitz | +0.420 |
illance | +0.375 |
chio | +0.372 |
edi | +0.357 |
oulos | +0.353 |
Neg logit contributions | |
anmar | -0.271 |
mil | -0.252 |
reluct | -0.242 |
fabrication | -0.236 |
hub | -0.236 |
Token | as |
Token ID | 355 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
owitz | +7.542 |
illance | +6.705 |
chio | +6.585 |
edi | +6.325 |
itar | +6.095 |
Neg logit contributions | |
anmar | -6.378 |
reluct | -5.862 |
mil | -5.770 |
interstitial | -5.692 |
vg | -5.630 |
Token | your |
Token ID | 534 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
owitz | +0.390 |
illance | +0.349 |
chio | +0.341 |
edi | +0.331 |
oulos | +0.326 |
Neg logit contributions | |
anmar | -0.256 |
mil | -0.239 |
reluct | -0.231 |
hub | -0.224 |
vg | -0.224 |
Token | Android |
Token ID | 5565 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
owitz | +1.129 |
illance | +1.005 |
chio | +0.991 |
edi | +0.948 |
oulos | +0.939 |
Neg logit contributions | |
anmar | -0.792 |
mil | -0.748 |
reluct | -0.722 |
vg | -0.700 |
fabrication | -0.697 |
Token | phone |
Token ID | 3072 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
owitz | +1.903 |
illance | +1.692 |
chio | +1.670 |
edi | +1.608 |
™: | +1.586 |
Neg logit contributions | |
anmar | -1.369 |
mil | -1.286 |
reluct | -1.248 |
vg | -1.200 |
fabrication | -1.192 |
Token | closes |
Token ID | 20612 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
owitz | +4.832 |
chio | +4.335 |
illance | +4.334 |
edi | +4.086 |
oulos | +4.048 |
Neg logit contributions | |
anmar | -3.590 |
mil | -3.203 |
reluct | -3.139 |
vg | -3.086 |
interstitial | -3.037 |
Token | j |
Token ID | 73 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
owitz | +0.432 |
illance | +0.373 |
chio | +0.365 |
edi | +0.350 |
ilon | +0.347 |
Neg logit contributions | |
anmar | -0.442 |
mil | -0.417 |
reluct | -0.410 |
hub | -0.405 |
fabrication | -0.402 |
Token | agu |
Token ID | 11433 |
Feature activation | -8.09e-02 |
Pos logit contributions | |
anmar | +1.366 |
mil | +1.307 |
reluct | +1.277 |
hub | +1.268 |
fabrication | +1.259 |
Neg logit contributions | |
owitz | -0.961 |
illance | -0.805 |
chio | -0.790 |
edi | -0.746 |
oulos | -0.735 |
Token | war |
Token ID | 5767 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
owitz | +0.394 |
illance | +0.357 |
edi | +0.342 |
chio | +0.341 |
ilon | +0.332 |
Neg logit contributions | |
anmar | -0.229 |
reluct | -0.216 |
mil | -0.207 |
confir | -0.202 |
fabrication | -0.200 |
Token | Records |
Token ID | 13407 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
owitz | +0.167 |
illance | +0.141 |
chio | +0.139 |
edi | +0.132 |
oulos | +0.131 |
Neg logit contributions | |
anmar | -0.204 |
mil | -0.195 |
reluct | -0.190 |
hub | -0.189 |
fabrication | -0.188 |
Token | . |
Token ID | 13 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
owitz | +2.807 |
illance | +2.436 |
chio | +2.389 |
edi | +2.279 |
oulos | +2.269 |
Neg logit contributions | |
anmar | -2.904 |
mil | -2.747 |
reluct | -2.691 |
fabrication | -2.649 |
hub | -2.648 |
Token | Watch |
Token ID | 6305 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
owitz | +0.224 |
illance | +0.195 |
chio | +0.193 |
edi | +0.184 |
oulos | +0.183 |
Neg logit contributions | |
anmar | -0.195 |
mil | -0.183 |
reluct | -0.180 |
fabrication | -0.175 |
hub | -0.175 |
Token | fan |
Token ID | 4336 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
owitz | +7.277 |
illance | +6.437 |
chio | +6.157 |
edi | +6.146 |
oulos | +6.015 |
Neg logit contributions | |
anmar | -6.449 |
mil | -5.959 |
reluct | -5.818 |
interstitial | -5.800 |
vg | -5.593 |
Token | - |
Token ID | 12 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
anmar | +0.589 |
mil | +0.554 |
reluct | +0.533 |
hub | +0.522 |
fabrication | +0.518 |
Neg logit contributions | |
owitz | -0.865 |
illance | -0.772 |
chio | -0.763 |
edi | -0.727 |
oulos | -0.724 |
Token | shot |
Token ID | 9442 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
anmar | +2.025 |
mil | +1.935 |
reluct | +1.869 |
hub | +1.864 |
fabrication | +1.848 |
Neg logit contributions | |
owitz | -1.904 |
illance | -1.644 |
chio | -1.620 |
edi | -1.534 |
oulos | -1.524 |
Token | footage |
Token ID | 9640 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
owitz | +0.357 |
illance | +0.321 |
chio | +0.316 |
edi | +0.304 |
oulos | +0.303 |
Neg logit contributions | |
anmar | -0.216 |
mil | -0.200 |
reluct | -0.192 |
hub | -0.188 |
fabrication | -0.186 |
Token | of |
Token ID | 286 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
owitz | +0.615 |
illance | +0.548 |
chio | +0.538 |
edi | +0.519 |
oulos | +0.516 |
Neg logit contributions | |
anmar | -0.402 |
mil | -0.371 |
reluct | -0.356 |
fabrication | -0.347 |
hub | -0.346 |
Token | Martin |
Token ID | 5780 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
anmar | +0.223 |
mil | +0.209 |
reluct | +0.201 |
hub | +0.200 |
fabrication | +0.198 |
Neg logit contributions | |
owitz | -0.299 |
illance | -0.264 |
chio | -0.261 |
edi | -0.252 |
oulos | -0.249 |
Token | concluded |
Token ID | 8391 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
owitz | +0.182 |
illance | +0.158 |
chio | +0.157 |
edi | +0.150 |
oulos | +0.149 |
Neg logit contributions | |
anmar | -0.152 |
mil | -0.143 |
reluct | -0.138 |
hub | -0.136 |
fabrication | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
anmar | +3.104 |
mil | +2.966 |
reluct | +2.857 |
hub | +2.855 |
fabrication | +2.825 |
Neg logit contributions | |
owitz | -3.189 |
illance | -2.776 |
chio | -2.736 |
edi | -2.594 |
oulos | -2.577 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
anmar | +0.711 |
mil | +0.665 |
reluct | +0.649 |
hub | +0.640 |
fabrication | +0.639 |
Neg logit contributions | |
owitz | -0.853 |
illance | -0.749 |
chio | -0.736 |
edi | -0.704 |
oulos | -0.703 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
anmar | +0.033 |
mil | +0.032 |
hub | +0.031 |
fabrication | +0.030 |
vg | +0.030 |
Neg logit contributions | |
owitz | -0.046 |
illance | -0.041 |
chio | -0.041 |
oulos | -0.039 |
edi | -0.039 |
Token | Watch |
Token ID | 10723 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
anmar | +0.075 |
mil | +0.070 |
reluct | +0.069 |
hub | +0.068 |
fabrication | +0.067 |
Neg logit contributions | |
owitz | -0.088 |
illance | -0.077 |
chio | -0.076 |
edi | -0.073 |
oulos | -0.072 |
Token | � |
Token ID | 564 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
owitz | +7.345 |
illance | +6.544 |
chio | +6.101 |
edi | +6.034 |
oulos | +6.011 |
Neg logit contributions | |
anmar | -6.480 |
reluct | -5.977 |
mil | -5.912 |
vg | -5.737 |
interstitial | -5.645 |
Token | � |
Token ID | 250 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
owitz | +1.461 |
illance | +1.261 |
chio | +1.220 |
edi | +1.188 |
oulos | +1.157 |
Neg logit contributions | |
anmar | -1.555 |
mil | -1.462 |
reluct | -1.444 |
fabrication | -1.419 |
hub | -1.406 |
Token | Outside |
Token ID | 30815 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
owitz | +0.536 |
illance | +0.469 |
chio | +0.462 |
edi | +0.441 |
oulos | +0.438 |
Neg logit contributions | |
anmar | -0.480 |
mil | -0.449 |
reluct | -0.443 |
hub | -0.434 |
fabrication | -0.433 |
Token | First |
Token ID | 3274 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
anmar | +0.881 |
mil | +0.834 |
reluct | +0.806 |
hub | +0.793 |
fabrication | +0.789 |
Neg logit contributions | |
owitz | -0.985 |
illance | -0.862 |
chio | -0.850 |
edi | -0.810 |
oulos | -0.808 |
Token | Presidential |
Token ID | 17471 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
anmar | +1.151 |
mil | +1.097 |
reluct | +1.060 |
hub | +1.055 |
fabrication | +1.049 |
Neg logit contributions | |
owitz | -1.130 |
illance | -0.979 |
chio | -0.965 |
edi | -0.916 |
oulos | -0.910 |
Token | ( |
Token ID | 357 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
owitz | +0.665 |
illance | +0.580 |
chio | +0.573 |
edi | +0.552 |
oulos | +0.545 |
Neg logit contributions | |
anmar | -0.549 |
mil | -0.514 |
reluct | -0.498 |
hub | -0.488 |
fabrication | -0.484 |
Token | or |
Token ID | 273 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
owitz | +0.581 |
illance | +0.504 |
chio | +0.502 |
edi | +0.482 |
oulos | +0.475 |
Neg logit contributions | |
anmar | -0.490 |
mil | -0.456 |
reluct | -0.454 |
hub | -0.446 |
fabrication | -0.442 |
Token | infamous |
Token ID | 16526 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
owitz | +2.040 |
illance | +1.789 |
chio | +1.779 |
edi | +1.711 |
oulos | +1.692 |
Neg logit contributions | |
anmar | -1.492 |
mil | -1.368 |
reluct | -1.323 |
fabrication | -1.288 |
hub | -1.285 |
Token | , |
Token ID | 11 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
owitz | +0.684 |
illance | +0.584 |
chio | +0.577 |
edi | +0.548 |
oulos | +0.545 |
Neg logit contributions | |
anmar | -0.765 |
mil | -0.723 |
reluct | -0.705 |
hub | -0.692 |
fabrication | -0.689 |
Token | depending |
Token ID | 6906 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
owitz | +2.507 |
illance | +2.146 |
chio | +2.138 |
oulos | +2.055 |
edi | +2.052 |
Neg logit contributions | |
anmar | -2.202 |
mil | -2.019 |
reluct | -1.977 |
interstitial | -1.926 |
vg | -1.920 |
Token | on |
Token ID | 319 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
owitz | +3.692 |
illance | +3.198 |
chio | +3.165 |
edi | +3.014 |
ilon | +2.952 |
Neg logit contributions | |
anmar | -3.326 |
mil | -3.186 |
reluct | -3.072 |
interstitial | -3.063 |
vg | -2.986 |
Token | one |
Token ID | 530 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
owitz | +6.818 |
illance | +5.793 |
chio | +5.665 |
edi | +5.578 |
oulos | +5.396 |
Neg logit contributions | |
anmar | -6.846 |
mil | -6.385 |
reluct | -6.180 |
vg | -6.141 |
interstitial | -6.068 |
Token | � |
Token ID | 447 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
owitz | +3.634 |
illance | +2.945 |
chio | +2.809 |
edi | +2.674 |
oulos | +2.607 |
Neg logit contributions | |
anmar | -5.987 |
mil | -5.501 |
reluct | -5.449 |
interstitial | -5.364 |
vg | -5.289 |
Token | � |
Token ID | 247 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
owitz | +1.713 |
illance | +1.444 |
chio | +1.418 |
edi | +1.353 |
ilon | +1.302 |
Neg logit contributions | |
anmar | -2.275 |
mil | -2.159 |
reluct | -2.139 |
fabrication | -2.097 |
hub | -2.072 |
Token | s |
Token ID | 82 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
owitz | +1.353 |
illance | +1.153 |
chio | +1.146 |
edi | +1.097 |
oulos | +1.067 |
Neg logit contributions | |
anmar | -1.424 |
mil | -1.347 |
reluct | -1.333 |
hub | -1.293 |
fabrication | -1.287 |
Token | point |
Token ID | 966 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
owitz | +1.733 |
illance | +1.551 |
chio | +1.535 |
edi | +1.469 |
oulos | +1.466 |
Neg logit contributions | |
anmar | -0.997 |
mil | -0.933 |
reluct | -0.892 |
hub | -0.871 |
vg | -0.870 |
Token | 11 |
Token ID | 1157 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
anmar | +1.505 |
mil | +1.418 |
hub | +1.332 |
reluct | +1.332 |
fabrication | +1.315 |
Neg logit contributions | |
owitz | -2.645 |
illance | -2.376 |
chio | -2.339 |
edi | -2.257 |
oulos | -2.252 |
Token | . |
Token ID | 13 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
anmar | +0.474 |
mil | +0.466 |
hub | +0.442 |
vg | +0.433 |
fabrication | +0.432 |
Neg logit contributions | |
owitz | -0.528 |
illance | -0.471 |
chio | -0.458 |
oulos | -0.439 |
edi | -0.435 |
Token | The |
Token ID | 383 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
anmar | +2.850 |
mil | +2.730 |
hub | +2.612 |
reluct | +2.573 |
fabrication | +2.563 |
Neg logit contributions | |
owitz | -3.530 |
illance | -3.122 |
chio | -3.067 |
edi | -2.931 |
oulos | -2.919 |
Token | Legend |
Token ID | 9883 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
anmar | +0.722 |
mil | +0.686 |
reluct | +0.670 |
fabrication | +0.657 |
hub | +0.656 |
Neg logit contributions | |
owitz | -0.691 |
illance | -0.595 |
chio | -0.590 |
edi | -0.560 |
oulos | -0.553 |
Token | of |
Token ID | 286 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
owitz | +1.982 |
chio | +1.744 |
illance | +1.728 |
™: | +1.657 |
edi | +1.630 |
Neg logit contributions | |
anmar | -1.304 |
reluct | -1.177 |
mil | -1.174 |
fabrication | -1.121 |
vg | -1.107 |
Token | Zelda |
Token ID | 22166 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
owitz | +2.456 |
chio | +2.138 |
illance | +2.123 |
edi | +2.079 |
ilon | +1.997 |
Neg logit contributions | |
anmar | -1.978 |
mil | -1.845 |
reluct | -1.801 |
fabrication | -1.780 |
interstitial | -1.743 |
Token | : |
Token ID | 25 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
owitz | +5.747 |
™: | +5.130 |
chio | +4.779 |
illance | +4.563 |
oulos | +4.520 |
Neg logit contributions | |
anmar | -7.877 |
reluct | -7.369 |
mil | -7.321 |
carbohyd | -7.111 |
confir | -7.045 |
Token | O |
Token ID | 440 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
owitz | +2.051 |
chio | +1.771 |
illance | +1.746 |
edi | +1.692 |
™: | +1.684 |
Neg logit contributions | |
anmar | -1.628 |
mil | -1.510 |
reluct | -1.499 |
fabrication | -1.448 |
confir | -1.445 |
Token | car |
Token ID | 7718 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
owitz | +2.826 |
chio | +2.400 |
illance | +2.338 |
edi | +2.281 |
ilon | +2.183 |
Neg logit contributions | |
anmar | -3.500 |
reluct | -3.279 |
mil | -3.255 |
fabrication | -3.223 |
hub | -3.169 |
Token | ina |
Token ID | 1437 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
owitz | +4.026 |
chio | +3.601 |
illance | +3.435 |
itar | +3.281 |
edi | +3.279 |
Neg logit contributions | |
anmar | -3.573 |
reluct | -3.354 |
mil | -3.331 |
fabrication | -3.213 |
hub | -3.188 |
Token | of |
Token ID | 286 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
owitz | +4.666 |
chio | +4.125 |
illance | +4.086 |
™: | +3.923 |
edi | +3.902 |
Neg logit contributions | |
anmar | -3.052 |
reluct | -2.918 |
mil | -2.759 |
confir | -2.653 |
fabrication | -2.643 |
Token | 5 |
Token ID | 20 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
anmar | +1.238 |
mil | +1.163 |
reluct | +1.144 |
hub | +1.122 |
fabrication | +1.117 |
Neg logit contributions | |
owitz | -1.334 |
illance | -1.157 |
chio | -1.146 |
edi | -1.089 |
oulos | -1.082 |
Token | percent |
Token ID | 1411 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
anmar | +3.544 |
mil | +3.383 |
hub | +3.165 |
reluct | +3.123 |
fabrication | +3.122 |
Neg logit contributions | |
owitz | -6.712 |
illance | -6.035 |
chio | -5.963 |
edi | -5.741 |
oulos | -5.708 |
Token | from |
Token ID | 422 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
anmar | +1.516 |
mil | +1.423 |
reluct | +1.358 |
hub | +1.350 |
fabrication | +1.332 |
Neg logit contributions | |
owitz | -2.328 |
illance | -2.072 |
chio | -2.051 |
edi | -1.967 |
oulos | -1.958 |
Token | three |
Token ID | 1115 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
owitz | +2.385 |
chio | +2.077 |
illance | +2.070 |
oulos | +1.964 |
edi | +1.960 |
Neg logit contributions | |
anmar | -1.865 |
mil | -1.742 |
reluct | -1.661 |
vg | -1.617 |
hub | -1.604 |
Token | - |
Token ID | 12 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
owitz | +1.969 |
illance | +1.713 |
chio | +1.695 |
edi | +1.634 |
™: | +1.612 |
Neg logit contributions | |
anmar | -1.415 |
mil | -1.321 |
reluct | -1.283 |
interstitial | -1.231 |
hub | -1.225 |
Token | point |
Token ID | 4122 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
owitz | +4.734 |
chio | +4.080 |
illance | +4.055 |
edi | +3.974 |
™: | +3.765 |
Neg logit contributions | |
anmar | -3.661 |
reluct | -3.454 |
hub | -3.245 |
fabrication | -3.195 |
mil | -3.186 |
Token | range |
Token ID | 2837 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
owitz | +6.261 |
illance | +5.320 |
chio | +5.259 |
™: | +5.124 |
edi | +5.001 |
Neg logit contributions | |
anmar | -6.976 |
interstitial | -6.670 |
mil | -6.613 |
reluct | -6.337 |
vg | -6.204 |
Token | . |
Token ID | 13 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
owitz | +1.117 |
illance | +0.965 |
chio | +0.954 |
oulos | +0.907 |
edi | +0.906 |
Neg logit contributions | |
anmar | -1.130 |
mil | -1.073 |
reluct | -1.043 |
hub | -1.028 |
fabrication | -1.018 |
Token | He |
Token ID | 679 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
anmar | +0.225 |
mil | +0.208 |
reluct | +0.207 |
hub | +0.200 |
fabrication | +0.200 |
Neg logit contributions | |
owitz | -0.272 |
illance | -0.237 |
chio | -0.236 |
edi | -0.225 |
oulos | -0.224 |
Token | became |
Token ID | 2627 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
owitz | +0.576 |
illance | +0.505 |
chio | +0.501 |
edi | +0.479 |
oulos | +0.474 |
Neg logit contributions | |
anmar | -0.481 |
mil | -0.451 |
reluct | -0.438 |
hub | -0.433 |
fabrication | -0.431 |
Token | an |
Token ID | 281 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
anmar | +0.996 |
mil | +0.940 |
reluct | +0.904 |
hub | +0.898 |
fabrication | +0.892 |
Neg logit contributions | |
owitz | -1.166 |
illance | -1.015 |
chio | -1.007 |
edi | -0.959 |
oulos | -0.957 |
Token | soon |
Token ID | 2582 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
anmar | +2.290 |
mil | +2.207 |
hub | +2.129 |
fabrication | +2.089 |
reluct | +2.087 |
Neg logit contributions | |
owitz | -2.832 |
illance | -2.510 |
chio | -2.454 |
oulos | -2.349 |
edi | -2.343 |
Token | . |
Token ID | 13 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
owitz | +0.246 |
illance | +0.214 |
chio | +0.210 |
edi | +0.204 |
ilon | +0.200 |
Neg logit contributions | |
anmar | -0.204 |
mil | -0.191 |
reluct | -0.187 |
fabrication | -0.181 |
hub | -0.181 |
Token | So |
Token ID | 1406 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
anmar | +0.194 |
mil | +0.179 |
reluct | +0.177 |
hub | +0.171 |
fabrication | +0.171 |
Neg logit contributions | |
owitz | -0.275 |
illance | -0.242 |
chio | -0.241 |
edi | -0.230 |
oulos | -0.228 |
Token | you |
Token ID | 345 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
owitz | +2.322 |
illance | +2.038 |
chio | +2.034 |
edi | +1.968 |
oulos | +1.938 |
Neg logit contributions | |
anmar | -1.470 |
mil | -1.343 |
reluct | -1.310 |
vg | -1.260 |
interstitial | -1.252 |
Token | can |
Token ID | 460 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
owitz | +0.830 |
illance | +0.738 |
chio | +0.730 |
edi | +0.702 |
oulos | +0.692 |
Neg logit contributions | |
anmar | -0.569 |
mil | -0.531 |
reluct | -0.513 |
hub | -0.503 |
fabrication | -0.500 |
Token | watch |
Token ID | 2342 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
owitz | +2.146 |
chio | +1.868 |
illance | +1.858 |
edi | +1.784 |
ilon | +1.738 |
Neg logit contributions | |
anmar | -1.938 |
mil | -1.808 |
reluct | -1.792 |
interstitial | -1.728 |
hub | -1.719 |
Token | porn |
Token ID | 8483 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
owitz | +7.128 |
chio | +6.028 |
illance | +5.996 |
edi | +5.870 |
itar | +5.700 |
Neg logit contributions | |
anmar | -6.257 |
reluct | -5.626 |
mil | -5.560 |
interstitial | -5.524 |
vg | -5.429 |
Token | and |
Token ID | 290 |
Feature activation | -9.94e-02 |
Pos logit contributions | |
owitz | +0.047 |
illance | +0.041 |
chio | +0.041 |
edi | +0.039 |
oulos | +0.039 |
Neg logit contributions | |
anmar | -0.037 |
mil | -0.035 |
reluct | -0.033 |
hub | -0.033 |
fabrication | -0.033 |
Token | masturb |
Token ID | 22938 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
owitz | +0.467 |
illance | +0.415 |
chio | +0.411 |
edi | +0.397 |
oulos | +0.389 |
Neg logit contributions | |
anmar | -0.302 |
mil | -0.279 |
reluct | -0.271 |
vg | -0.259 |
hub | -0.259 |
Token | ate |
Token ID | 378 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
owitz | +0.582 |
chio | +0.350 |
illance | +0.334 |
edi | +0.240 |
ilon | +0.237 |
Neg logit contributions | |
anmar | -2.893 |
reluct | -2.824 |
mil | -2.817 |
fabrication | -2.762 |
hub | -2.754 |
Token | for |
Token ID | 329 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
anmar | +0.049 |
mil | +0.046 |
reluct | +0.045 |
hub | +0.044 |
fabrication | +0.044 |
Neg logit contributions | |
owitz | -0.062 |
illance | -0.054 |
chio | -0.054 |
edi | -0.051 |
oulos | -0.051 |
Token | Diane |
Token ID | 26542 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
anmar | +0.879 |
mil | +0.774 |
hub | +0.739 |
fabrication | +0.681 |
snap | +0.669 |
Neg logit contributions | |
owitz | -4.209 |
illance | -3.890 |
chio | -3.879 |
edi | -3.782 |
oulos | -3.745 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
anmar | +1.120 |
mil | +1.102 |
hub | +1.067 |
snap | +1.044 |
interstitial | +1.043 |
Neg logit contributions | |
owitz | -0.566 |
illance | -0.472 |
chio | -0.452 |
edi | -0.435 |
oded | -0.410 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
anmar | +0.385 |
mil | +0.376 |
hub | +0.359 |
fabrication | +0.358 |
vg | +0.352 |
Neg logit contributions | |
owitz | -0.266 |
illance | -0.228 |
chio | -0.221 |
edi | -0.208 |
oulos | -0.205 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
anmar | +2.600 |
mil | +2.526 |
hub | +2.408 |
fabrication | +2.398 |
vg | +2.373 |
Neg logit contributions | |
owitz | -2.166 |
illance | -1.877 |
chio | -1.839 |
oulos | -1.745 |
edi | -1.725 |
Token | : |
Token ID | 25 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
anmar | +1.454 |
mil | +1.395 |
hub | +1.338 |
fabrication | +1.320 |
reluct | +1.303 |
Neg logit contributions | |
owitz | -1.821 |
illance | -1.654 |
chio | -1.604 |
edi | -1.547 |
oulos | -1.513 |
Token | ' |
Token ID | 705 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
owitz | +1.359 |
illance | +1.223 |
chio | +1.212 |
edi | +1.166 |
oulos | +1.160 |
Neg logit contributions | |
anmar | -0.708 |
mil | -0.661 |
reluct | -0.625 |
hub | -0.624 |
fabrication | -0.616 |
Token | I |
Token ID | 40 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
owitz | +6.413 |
chio | +5.583 |
illance | +5.331 |
ilon | +5.166 |
itarian | +5.117 |
Neg logit contributions | |
anmar | -6.792 |
confir | -6.218 |
reluct | -6.174 |
mil | -6.066 |
vg | -6.063 |
Token | fully |
Token ID | 3938 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
owitz | +0.364 |
illance | +0.327 |
chio | +0.323 |
edi | +0.311 |
oulos | +0.311 |
Neg logit contributions | |
anmar | -0.190 |
mil | -0.178 |
hub | -0.169 |
reluct | -0.169 |
fabrication | -0.166 |
Token | expect |
Token ID | 1607 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
anmar | +0.454 |
mil | +0.427 |
hub | +0.407 |
reluct | +0.406 |
fabrication | +0.401 |
Neg logit contributions | |
owitz | -0.744 |
illance | -0.665 |
chio | -0.657 |
edi | -0.632 |
oulos | -0.627 |
Token | ' |
Token ID | 6 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
owitz | +0.853 |
illance | +0.730 |
chio | +0.718 |
edi | +0.677 |
oulos | +0.673 |
Neg logit contributions | |
anmar | -1.010 |
mil | -0.968 |
reluct | -0.936 |
hub | -0.935 |
fabrication | -0.927 |
Token | fair |
Token ID | 3148 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
owitz | +1.257 |
illance | +1.114 |
chio | +1.080 |
edi | +1.043 |
ilon | +1.036 |
Neg logit contributions | |
anmar | -1.025 |
mil | -0.991 |
hub | -0.971 |
fabrication | -0.943 |
reluct | -0.931 |
Token | or |
Token ID | 393 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
anmar | +1.269 |
mil | +1.181 |
reluct | +1.133 |
hub | +1.101 |
fabrication | +1.092 |
Neg logit contributions | |
owitz | -1.991 |
illance | -1.768 |
chio | -1.756 |
edi | -1.683 |
oulos | -1.671 |
Token | two |
Token ID | 734 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
owitz | +2.287 |
illance | +1.998 |
chio | +1.984 |
edi | +1.896 |
oulos | +1.870 |
Neg logit contributions | |
anmar | -1.844 |
mil | -1.750 |
reluct | -1.686 |
fabrication | -1.632 |
interstitial | -1.630 |
Token | things |
Token ID | 1243 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
anmar | +1.159 |
mil | +1.081 |
reluct | +1.041 |
hub | +1.013 |
fabrication | +1.003 |
Neg logit contributions | |
owitz | -1.722 |
illance | -1.518 |
chio | -1.511 |
edi | -1.448 |
oulos | -1.437 |
Token | , |
Token ID | 11 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
owitz | +0.382 |
illance | +0.333 |
chio | +0.330 |
edi | +0.316 |
oulos | +0.313 |
Neg logit contributions | |
anmar | -0.310 |
mil | -0.293 |
reluct | -0.283 |
hub | -0.275 |
fabrication | -0.274 |
Token | and |
Token ID | 290 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
owitz | +0.424 |
illance | +0.373 |
chio | +0.370 |
edi | +0.357 |
oulos | +0.353 |
Neg logit contributions | |
anmar | -0.299 |
mil | -0.280 |
reluct | -0.269 |
hub | -0.263 |
fabrication | -0.261 |
Token | watch |
Token ID | 2342 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
anmar | +1.150 |
mil | +1.076 |
reluct | +1.027 |
hub | +1.015 |
fabrication | +1.004 |
Neg logit contributions | |
owitz | -1.895 |
illance | -1.688 |
chio | -1.672 |
edi | -1.609 |
oulos | -1.596 |
Token | as |
Token ID | 355 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
owitz | +6.821 |
illance | +5.910 |
chio | +5.693 |
edi | +5.675 |
itar | +5.434 |
Neg logit contributions | |
anmar | -6.266 |
mil | -5.698 |
interstitial | -5.684 |
reluct | -5.645 |
vg | -5.428 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
anmar | +0.448 |
mil | +0.418 |
reluct | +0.401 |
hub | +0.389 |
fabrication | +0.387 |
Neg logit contributions | |
owitz | -0.673 |
illance | -0.596 |
chio | -0.589 |
edi | -0.569 |
oulos | -0.563 |
Token | party |
Token ID | 2151 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
owitz | +0.656 |
illance | +0.580 |
chio | +0.577 |
edi | +0.552 |
oulos | +0.549 |
Neg logit contributions | |
anmar | -0.422 |
mil | -0.396 |
reluct | -0.380 |
interstitial | -0.366 |
vg | -0.366 |
Token | explores |
Token ID | 25409 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
owitz | +1.060 |
illance | +0.929 |
chio | +0.923 |
edi | +0.886 |
oulos | +0.872 |
Neg logit contributions | |
anmar | -0.793 |
mil | -0.733 |
reluct | -0.706 |
fabrication | -0.691 |
interstitial | -0.690 |
Token | and |
Token ID | 290 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
owitz | +1.447 |
illance | +1.269 |
chio | +1.258 |
edi | +1.211 |
oulos | +1.192 |
Neg logit contributions | |
anmar | -1.052 |
mil | -0.983 |
reluct | -0.943 |
interstitial | -0.915 |
vg | -0.908 |
Token | Q |
Token ID | 1195 |
Feature activation | +6.55e-03 |
Pos logit contributions | |
anmar | +0.230 |
mil | +0.216 |
reluct | +0.211 |
hub | +0.207 |
fabrication | +0.206 |
Neg logit contributions | |
owitz | -0.282 |
illance | -0.245 |
chio | -0.244 |
edi | -0.233 |
oulos | -0.231 |
Token | ut |
Token ID | 315 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
anmar | +0.025 |
mil | +0.024 |
reluct | +0.023 |
hub | +0.023 |
fabrication | +0.023 |
Neg logit contributions | |
owitz | -0.025 |
illance | -0.022 |
chio | -0.022 |
edi | -0.021 |
oulos | -0.020 |
Token | lu |
Token ID | 2290 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
anmar | +0.517 |
mil | +0.492 |
reluct | +0.480 |
hub | +0.475 |
fabrication | +0.471 |
Neg logit contributions | |
owitz | -0.570 |
illance | -0.497 |
chio | -0.492 |
edi | -0.468 |
oulos | -0.465 |
Token | gh |
Token ID | 456 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
anmar | +0.857 |
mil | +0.815 |
reluct | +0.798 |
hub | +0.788 |
fabrication | +0.782 |
Neg logit contributions | |
owitz | -0.861 |
illance | -0.745 |
chio | -0.740 |
edi | -0.701 |
oulos | -0.693 |
Token | and |
Token ID | 290 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
anmar | +0.641 |
mil | +0.611 |
reluct | +0.596 |
hub | +0.592 |
fabrication | +0.588 |
Neg logit contributions | |
owitz | -0.581 |
illance | -0.499 |
chio | -0.494 |
edi | -0.467 |
oulos | -0.463 |
Token | so |
Token ID | 523 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
owitz | +1.995 |
chio | +1.729 |
illance | +1.710 |
edi | +1.641 |
ilon | +1.629 |
Neg logit contributions | |
anmar | -1.686 |
mil | -1.584 |
reluct | -1.556 |
fabrication | -1.506 |
vg | -1.499 |
Token | on |
Token ID | 319 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
owitz | +6.156 |
illance | +5.295 |
chio | +5.176 |
edi | +5.007 |
ilon | +4.970 |
Neg logit contributions | |
anmar | -6.241 |
interstitial | -6.075 |
mil | -6.068 |
reluct | -6.040 |
fabrication | -5.896 |
Token | ). |
Token ID | 737 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
owitz | +1.209 |
illance | +1.007 |
chio | +1.001 |
edi | +0.945 |
oulos | +0.926 |
Neg logit contributions | |
anmar | -1.581 |
mil | -1.515 |
reluct | -1.487 |
hub | -1.469 |
fabrication | -1.461 |
Token | However |
Token ID | 2102 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
anmar | +1.429 |
mil | +1.361 |
hub | +1.294 |
reluct | +1.281 |
fabrication | +1.277 |
Neg logit contributions | |
owitz | -1.980 |
illance | -1.764 |
chio | -1.734 |
edi | -1.660 |
oulos | -1.655 |
Token | , |
Token ID | 11 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
anmar | +0.516 |
mil | +0.493 |
reluct | +0.478 |
hub | +0.475 |
fabrication | +0.470 |
Neg logit contributions | |
owitz | -0.457 |
illance | -0.391 |
chio | -0.386 |
edi | -0.365 |
oulos | -0.361 |
Token | names |
Token ID | 3891 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
anmar | +1.222 |
mil | +1.152 |
reluct | +1.102 |
hub | +1.094 |
fabrication | +1.081 |
Neg logit contributions | |
owitz | -1.835 |
illance | -1.629 |
chio | -1.615 |
edi | -1.548 |
oulos | -1.538 |
Token | a |
Token ID | 257 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
anmar | +0.695 |
mil | +0.654 |
reluct | +0.629 |
hub | +0.613 |
fabrication | +0.611 |
Neg logit contributions | |
owitz | -0.981 |
illance | -0.861 |
chio | -0.854 |
edi | -0.819 |
oulos | -0.818 |
Token | result |
Token ID | 1255 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
anmar | +0.404 |
mil | +0.375 |
reluct | +0.358 |
hub | +0.346 |
fabrication | +0.344 |
Neg logit contributions | |
owitz | -0.805 |
illance | -0.722 |
chio | -0.721 |
edi | -0.690 |
oulos | -0.688 |
Token | . |
Token ID | 13 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
owitz | +1.341 |
illance | +1.121 |
chio | +1.112 |
edi | +1.063 |
oulos | +1.046 |
Neg logit contributions | |
anmar | -1.507 |
mil | -1.419 |
reluct | -1.388 |
hub | -1.355 |
fabrication | -1.354 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
owitz | +0.351 |
illance | +0.304 |
chio | +0.303 |
edi | +0.289 |
oulos | +0.288 |
Neg logit contributions | |
anmar | -0.290 |
mil | -0.271 |
reluct | -0.268 |
hub | -0.260 |
fabrication | -0.259 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
anmar | +0.039 |
mil | +0.038 |
hub | +0.036 |
fabrication | +0.036 |
vg | +0.035 |
Neg logit contributions | |
owitz | -0.055 |
illance | -0.049 |
chio | -0.048 |
oulos | -0.046 |
edi | -0.046 |
Token | Watch |
Token ID | 10723 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
anmar | +0.578 |
mil | +0.547 |
reluct | +0.532 |
hub | +0.528 |
fabrication | +0.522 |
Neg logit contributions | |
owitz | -0.654 |
illance | -0.570 |
chio | -0.565 |
edi | -0.537 |
oulos | -0.533 |
Token | dog |
Token ID | 9703 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
owitz | +6.221 |
illance | +5.233 |
chio | +5.134 |
edi | +4.986 |
oulos | +4.918 |
Neg logit contributions | |
anmar | -6.706 |
reluct | -6.371 |
mil | -6.149 |
vg | -6.023 |
confir | -5.992 |
Token | groups |
Token ID | 2628 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
owitz | +1.894 |
illance | +1.655 |
chio | +1.638 |
edi | +1.544 |
oulos | +1.537 |
Neg logit contributions | |
anmar | -1.847 |
mil | -1.749 |
reluct | -1.708 |
fabrication | -1.669 |
hub | -1.666 |
Token | filed |
Token ID | 5717 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
owitz | +2.887 |
illance | +2.536 |
chio | +2.525 |
edi | +2.399 |
oulos | +2.397 |
Neg logit contributions | |
anmar | -2.136 |
mil | -2.001 |
reluct | -1.912 |
fabrication | -1.907 |
hub | -1.897 |
Token | Federal |
Token ID | 5618 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
anmar | +0.219 |
mil | +0.208 |
reluct | +0.200 |
hub | +0.199 |
fabrication | +0.197 |
Neg logit contributions | |
owitz | -0.258 |
illance | -0.226 |
chio | -0.223 |
edi | -0.212 |
oulos | -0.211 |
Token | Election |
Token ID | 14219 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
owitz | +0.574 |
illance | +0.506 |
chio | +0.500 |
edi | +0.477 |
oulos | +0.474 |
Neg logit contributions | |
anmar | -0.455 |
mil | -0.431 |
reluct | -0.417 |
hub | -0.412 |
fabrication | -0.408 |
Token | own |
Token ID | 898 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
anmar | +0.118 |
mil | +0.110 |
reluct | +0.106 |
hub | +0.104 |
fabrication | +0.104 |
Neg logit contributions | |
owitz | -0.205 |
illance | -0.183 |
chio | -0.182 |
edi | -0.174 |
oulos | -0.173 |
Token | will |
Token ID | 481 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
anmar | +0.941 |
mil | +0.883 |
reluct | +0.853 |
hub | +0.839 |
fabrication | +0.832 |
Neg logit contributions | |
owitz | -1.383 |
illance | -1.226 |
chio | -1.214 |
edi | -1.163 |
oulos | -1.156 |
Token | be |
Token ID | 307 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
anmar | +1.685 |
mil | +1.578 |
reluct | +1.522 |
hub | +1.496 |
fabrication | +1.484 |
Neg logit contributions | |
owitz | -2.639 |
illance | -2.346 |
chio | -2.336 |
edi | -2.240 |
oulos | -2.221 |
Token | ready |
Token ID | 3492 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
anmar | +1.748 |
mil | +1.650 |
reluct | +1.575 |
hub | +1.573 |
fabrication | +1.554 |
Neg logit contributions | |
owitz | -2.559 |
illance | -2.275 |
chio | -2.248 |
edi | -2.153 |
oulos | -2.143 |
Token | and |
Token ID | 290 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
anmar | +1.684 |
mil | +1.591 |
reluct | +1.523 |
hub | +1.516 |
fabrication | +1.500 |
Neg logit contributions | |
owitz | -2.376 |
illance | -2.107 |
chio | -2.082 |
edi | -1.993 |
oulos | -1.982 |
Token | waiting |
Token ID | 4953 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
owitz | +1.126 |
illance | +0.993 |
chio | +0.988 |
edi | +0.942 |
ilon | +0.933 |
Neg logit contributions | |
anmar | -0.799 |
mil | -0.743 |
reluct | -0.712 |
fabrication | -0.697 |
hub | -0.696 |
Token | for |
Token ID | 329 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
owitz | +6.114 |
illance | +5.296 |
™: | +5.212 |
chio | +5.105 |
ilon | +4.936 |
Neg logit contributions | |
anmar | -6.450 |
reluct | -6.119 |
interstitial | -6.087 |
mil | -5.980 |
vg | -5.793 |
Token | you |
Token ID | 345 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
owitz | +1.955 |
illance | +1.781 |
chio | +1.748 |
edi | +1.709 |
™: | +1.684 |
Neg logit contributions | |
anmar | -0.770 |
mil | -0.694 |
reluct | -0.665 |
interstitial | -0.628 |
fabrication | -0.626 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
owitz | +1.132 |
illance | +0.998 |
chio | +0.984 |
edi | +0.944 |
oulos | +0.936 |
Neg logit contributions | |
anmar | -0.872 |
mil | -0.821 |
reluct | -0.804 |
fabrication | -0.786 |
hub | -0.782 |
Token | But |
Token ID | 887 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
owitz | +0.469 |
illance | +0.410 |
chio | +0.408 |
edi | +0.389 |
oulos | +0.387 |
Neg logit contributions | |
anmar | -0.359 |
mil | -0.334 |
reluct | -0.330 |
hub | -0.319 |
fabrication | -0.319 |
Token | when |
Token ID | 618 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
anmar | +0.910 |
mil | +0.859 |
reluct | +0.820 |
hub | +0.818 |
fabrication | +0.809 |
Neg logit contributions | |
owitz | -1.354 |
illance | -1.205 |
chio | -1.191 |
edi | -1.141 |
oulos | -1.135 |
Token | of |
Token ID | 286 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
owitz | +1.533 |
illance | +1.372 |
chio | +1.358 |
ilon | +1.291 |
edi | +1.290 |
Neg logit contributions | |
anmar | -0.916 |
mil | -0.844 |
reluct | -0.799 |
fabrication | -0.793 |
hub | -0.790 |
Token | fans |
Token ID | 3296 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
owitz | +1.360 |
illance | +1.216 |
chio | +1.204 |
edi | +1.152 |
oulos | +1.145 |
Neg logit contributions | |
anmar | -0.779 |
mil | -0.728 |
reluct | -0.689 |
fabrication | -0.668 |
hub | -0.663 |
Token | who |
Token ID | 508 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
owitz | +0.744 |
illance | +0.654 |
chio | +0.646 |
edi | +0.617 |
oulos | +0.611 |
Neg logit contributions | |
anmar | -0.582 |
mil | -0.550 |
reluct | -0.530 |
hub | -0.523 |
fabrication | -0.523 |
Token | enjoy |
Token ID | 2883 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
owitz | +0.785 |
illance | +0.698 |
chio | +0.692 |
edi | +0.665 |
oulos | +0.658 |
Neg logit contributions | |
anmar | -0.513 |
mil | -0.480 |
reluct | -0.459 |
fabrication | -0.452 |
hub | -0.451 |
Token | nothing |
Token ID | 2147 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
owitz | +1.500 |
chio | +1.308 |
illance | +1.308 |
edi | +1.256 |
oulos | +1.227 |
Neg logit contributions | |
anmar | -1.200 |
mil | -1.131 |
reluct | -1.092 |
fabrication | -1.061 |
hub | -1.059 |
Token | more |
Token ID | 517 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
anmar | +0.987 |
mil | +0.918 |
reluct | +0.869 |
hub | +0.863 |
fabrication | +0.852 |
Neg logit contributions | |
owitz | -1.937 |
illance | -1.742 |
chio | -1.726 |
edi | -1.662 |
oulos | -1.654 |
Token | than |
Token ID | 621 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
anmar | +2.505 |
mil | +2.338 |
hub | +2.184 |
reluct | +2.165 |
fabrication | +2.121 |
Neg logit contributions | |
owitz | -7.115 |
illance | -6.492 |
chio | -6.423 |
edi | -6.213 |
oulos | -6.190 |
Token | slaughter |
Token ID | 17968 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
anmar | +0.713 |
mil | +0.673 |
reluct | +0.646 |
hub | +0.637 |
fabrication | +0.634 |
Neg logit contributions | |
owitz | -0.914 |
illance | -0.806 |
chio | -0.797 |
edi | -0.761 |
oulos | -0.756 |
Token | ing |
Token ID | 278 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
anmar | +0.874 |
mil | +0.830 |
reluct | +0.814 |
hub | +0.801 |
fabrication | +0.795 |
Neg logit contributions | |
owitz | -0.740 |
illance | -0.632 |
chio | -0.621 |
edi | -0.587 |
oulos | -0.578 |
Token | zombies |
Token ID | 19005 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
anmar | +1.455 |
mil | +1.372 |
reluct | +1.309 |
hub | +1.305 |
fabrication | +1.290 |
Neg logit contributions | |
owitz | -2.185 |
illance | -1.944 |
chio | -1.922 |
edi | -1.842 |
oulos | -1.832 |
Token | in |
Token ID | 287 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
anmar | +0.547 |
mil | +0.518 |
reluct | +0.499 |
hub | +0.494 |
fabrication | +0.491 |
Neg logit contributions | |
owitz | -0.669 |
illance | -0.586 |
chio | -0.580 |
edi | -0.554 |
oulos | -0.550 |
Token | Kitchen |
Token ID | 22541 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
owitz | +0.908 |
chio | +0.795 |
illance | +0.789 |
edi | +0.751 |
oulos | +0.746 |
Neg logit contributions | |
anmar | -0.704 |
mil | -0.661 |
reluct | -0.645 |
vg | -0.623 |
fabrication | -0.621 |
Token | owner |
Token ID | 4870 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
owitz | +3.054 |
chio | +2.686 |
illance | +2.668 |
oulos | +2.541 |
edi | +2.514 |
Neg logit contributions | |
anmar | -2.349 |
mil | -2.181 |
reluct | -2.109 |
vg | -2.065 |
interstitial | -2.046 |
Token | , |
Token ID | 11 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
owitz | +0.983 |
illance | +0.847 |
chio | +0.846 |
edi | +0.804 |
oulos | +0.800 |
Neg logit contributions | |
anmar | -0.872 |
mil | -0.825 |
reluct | -0.800 |
hub | -0.784 |
fabrication | -0.780 |
Token | John |
Token ID | 1757 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
anmar | +1.099 |
mil | +1.046 |
reluct | +1.005 |
hub | +0.999 |
fabrication | +0.989 |
Neg logit contributions | |
owitz | -1.265 |
illance | -1.105 |
chio | -1.093 |
edi | -1.041 |
oulos | -1.036 |
Token | Nguyen |
Token ID | 42379 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
anmar | +0.349 |
mil | +0.330 |
reluct | +0.319 |
hub | +0.315 |
fabrication | +0.313 |
Neg logit contributions | |
owitz | -0.468 |
illance | -0.412 |
chio | -0.409 |
edi | -0.391 |
oulos | -0.389 |
Token | | |
Token ID | 930 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
anmar | +1.678 |
mil | +1.602 |
reluct | +1.544 |
hub | +1.541 |
fabrication | +1.527 |
Neg logit contributions | |
owitz | -1.662 |
illance | -1.441 |
chio | -1.421 |
edi | -1.347 |
oulos | -1.339 |
Token | C |
Token ID | 327 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
anmar | +4.047 |
mil | +3.871 |
hub | +3.702 |
reluct | +3.639 |
fabrication | +3.634 |
Neg logit contributions | |
owitz | -5.868 |
illance | -5.243 |
chio | -5.176 |
edi | -4.975 |
oulos | -4.928 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
owitz | +1.501 |
illance | +1.255 |
chio | +1.232 |
edi | +1.153 |
oulos | +1.143 |
Neg logit contributions | |
anmar | -2.207 |
mil | -2.122 |
reluct | -2.069 |
hub | -2.057 |
fabrication | -2.042 |
Token | un |
Token ID | 403 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
owitz | +1.121 |
illance | +0.999 |
chio | +0.986 |
edi | +0.941 |
oulos | +0.938 |
Neg logit contributions | |
anmar | -0.801 |
mil | -0.759 |
hub | -0.719 |
fabrication | -0.706 |
reluct | -0.706 |
Token | Kitchen |
Token ID | 22541 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
owitz | +0.217 |
illance | +0.193 |
chio | +0.192 |
oulos | +0.184 |
edi | +0.184 |
Neg logit contributions | |
anmar | -0.125 |
mil | -0.116 |
reluct | -0.112 |
vg | -0.108 |
fabrication | -0.107 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
owitz | +2.376 |
illance | +2.054 |
chio | +2.038 |
oulos | +1.957 |
edi | +1.919 |
Neg logit contributions | |
anmar | -2.071 |
mil | -1.945 |
reluct | -1.901 |
vg | -1.838 |
fabrication | -1.836 |
Token | � |
Token ID | 247 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
anmar | +1.339 |
mil | +1.292 |
hub | +1.238 |
reluct | +1.218 |
fabrication | +1.215 |
Neg logit contributions | |
owitz | -1.323 |
illance | -1.153 |
chio | -1.137 |
oulos | -1.072 |
edi | -1.068 |
Token | s |
Token ID | 82 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
anmar | +0.287 |
mil | +0.264 |
reluct | +0.255 |
hub | +0.253 |
fabrication | +0.249 |
Neg logit contributions | |
owitz | -0.533 |
illance | -0.477 |
chio | -0.473 |
edi | -0.457 |
oulos | -0.453 |
Token | living |
Token ID | 2877 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
anmar | +1.109 |
mil | +1.051 |
hub | +1.009 |
reluct | +1.004 |
fabrication | +0.996 |
Neg logit contributions | |
owitz | -1.482 |
illance | -1.317 |
chio | -1.297 |
edi | -1.239 |
oulos | -1.233 |
Token | in |
Token ID | 287 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
owitz | +2.063 |
illance | +1.802 |
chio | +1.765 |
edi | +1.699 |
oulos | +1.675 |
Neg logit contributions | |
anmar | -1.662 |
mil | -1.572 |
reluct | -1.541 |
vg | -1.495 |
hub | -1.480 |
Token | an |
Token ID | 281 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
owitz | +1.312 |
illance | +1.142 |
chio | +1.128 |
edi | +1.073 |
oulos | +1.063 |
Neg logit contributions | |
anmar | -1.079 |
mil | -1.023 |
reluct | -1.002 |
hub | -0.965 |
vg | -0.963 |
Token | alternate |
Token ID | 13527 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
owitz | +0.096 |
illance | +0.085 |
chio | +0.084 |
edi | +0.081 |
oulos | +0.080 |
Neg logit contributions | |
anmar | -0.065 |
mil | -0.062 |
reluct | -0.059 |
hub | -0.058 |
fabrication | -0.058 |
Token | reality |
Token ID | 3950 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
anmar | +3.626 |
mil | +3.437 |
hub | +3.357 |
fabrication | +3.275 |
reluct | +3.174 |
Neg logit contributions | |
owitz | -6.158 |
illance | -5.548 |
chio | -5.464 |
oulos | -5.238 |
edi | -5.203 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
anmar | +1.265 |
mil | +1.205 |
reluct | +1.163 |
hub | +1.152 |
fabrication | +1.143 |
Neg logit contributions | |
owitz | -1.358 |
illance | -1.185 |
chio | -1.168 |
edi | -1.109 |
oulos | -1.102 |
Token | Those |
Token ID | 5845 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
anmar | +0.108 |
mil | +0.102 |
reluct | +0.099 |
hub | +0.097 |
fabrication | +0.097 |
Neg logit contributions | |
owitz | -0.143 |
illance | -0.126 |
chio | -0.124 |
edi | -0.119 |
oulos | -0.118 |
Token | are |
Token ID | 389 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
anmar | +0.653 |
mil | +0.616 |
reluct | +0.590 |
hub | +0.584 |
fabrication | +0.580 |
Neg logit contributions | |
owitz | -0.924 |
illance | -0.819 |
chio | -0.810 |
edi | -0.775 |
oulos | -0.769 |
Token | the |
Token ID | 262 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
anmar | +0.265 |
mil | +0.250 |
reluct | +0.240 |
hub | +0.238 |
fabrication | +0.236 |
Neg logit contributions | |
owitz | -0.371 |
illance | -0.329 |
chio | -0.325 |
edi | -0.311 |
oulos | -0.310 |
Token | --> |
Token ID | 46904 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
owitz | +0.762 |
illance | +0.657 |
chio | +0.653 |
edi | +0.628 |
oulos | +0.611 |
Neg logit contributions | |
anmar | -0.693 |
mil | -0.650 |
reluct | -0.647 |
hub | -0.641 |
fabrication | -0.630 |
Token | src |
Token ID | 12351 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
anmar | +1.559 |
mil | +1.476 |
reluct | +1.416 |
hub | +1.410 |
fabrication | +1.395 |
Neg logit contributions | |
owitz | -1.988 |
illance | -1.752 |
chio | -1.730 |
edi | -1.655 |
oulos | -1.644 |
Token | / |
Token ID | 14 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
anmar | +3.959 |
mil | +3.844 |
hub | +3.699 |
fabrication | +3.655 |
reluct | +3.643 |
Neg logit contributions | |
owitz | -3.833 |
illance | -3.318 |
chio | -3.259 |
oulos | -3.091 |
edi | -3.080 |
Token | main |
Token ID | 12417 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
anmar | +1.533 |
mil | +1.454 |
reluct | +1.408 |
hub | +1.401 |
fabrication | +1.389 |
Neg logit contributions | |
owitz | -1.657 |
illance | -1.442 |
chio | -1.424 |
edi | -1.359 |
oulos | -1.346 |
Token | . |
Token ID | 13 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
anmar | +0.355 |
mil | +0.338 |
reluct | +0.328 |
fabrication | +0.325 |
hub | +0.323 |
Neg logit contributions | |
owitz | -0.308 |
illance | -0.266 |
chio | -0.258 |
edi | -0.249 |
ilon | -0.241 |
Token | rs |
Token ID | 3808 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
anmar | +2.648 |
mil | +2.523 |
hub | +2.365 |
reluct | +2.338 |
vg | +2.325 |
Neg logit contributions | |
owitz | -4.377 |
illance | -3.932 |
chio | -3.878 |
oulos | -3.720 |
edi | -3.708 |
Token | : |
Token ID | 25 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
anmar | +5.171 |
mil | +5.017 |
hub | +4.835 |
fabrication | +4.746 |
reluct | +4.735 |
Neg logit contributions | |
owitz | -5.923 |
illance | -5.203 |
chio | -5.110 |
oulos | -4.912 |
ilon | -4.801 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
anmar | +2.994 |
mil | +2.866 |
hub | +2.722 |
fabrication | +2.669 |
reluct | +2.661 |
Neg logit contributions | |
owitz | -4.472 |
illance | -4.000 |
chio | -3.957 |
oulos | -3.776 |
edi | -3.752 |
Token | : |
Token ID | 25 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
anmar | +0.217 |
mil | +0.205 |
reluct | +0.200 |
hub | +0.197 |
fabrication | +0.196 |
Neg logit contributions | |
owitz | -0.224 |
illance | -0.194 |
chio | -0.191 |
edi | -0.184 |
oulos | -0.180 |
Token | 1 |
Token ID | 16 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
anmar | +0.426 |
mil | +0.401 |
reluct | +0.387 |
hub | +0.383 |
fabrication | +0.380 |
Neg logit contributions | |
owitz | -0.556 |
illance | -0.490 |
chio | -0.484 |
edi | -0.465 |
oulos | -0.460 |
Token | | |
Token ID | 930 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
owitz | +3.153 |
illance | +2.708 |
chio | +2.639 |
edi | +2.601 |
™: | +2.537 |
Neg logit contributions | |
anmar | -3.266 |
mil | -3.066 |
reluct | -3.006 |
hub | -2.918 |
fabrication | -2.911 |
Token | 's |
Token ID | 338 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
anmar | +1.271 |
mil | +1.213 |
reluct | +1.176 |
hub | +1.170 |
fabrication | +1.162 |
Neg logit contributions | |
owitz | -1.060 |
illance | -0.905 |
chio | -0.891 |
edi | -0.838 |
oulos | -0.833 |
Token | truck |
Token ID | 7779 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
anmar | +2.257 |
mil | +2.149 |
hub | +2.082 |
reluct | +2.049 |
fabrication | +2.043 |
Neg logit contributions | |
owitz | -2.943 |
illance | -2.602 |
chio | -2.564 |
edi | -2.453 |
oulos | -2.445 |
Token | leader |
Token ID | 3554 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
anmar | +0.199 |
mil | +0.186 |
reluct | +0.182 |
vg | +0.176 |
fabrication | +0.174 |
Neg logit contributions | |
owitz | -0.244 |
illance | -0.217 |
chio | -0.212 |
edi | -0.203 |
oulos | -0.200 |
Token | , |
Token ID | 11 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
anmar | +1.436 |
mil | +1.369 |
reluct | +1.316 |
hub | +1.315 |
fabrication | +1.302 |
Neg logit contributions | |
owitz | -1.564 |
illance | -1.366 |
chio | -1.347 |
edi | -1.281 |
oulos | -1.274 |
Token | today |
Token ID | 1909 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
anmar | +1.357 |
mil | +1.276 |
reluct | +1.219 |
hub | +1.212 |
fabrication | +1.198 |
Neg logit contributions | |
owitz | -2.094 |
illance | -1.866 |
chio | -1.845 |
edi | -1.769 |
oulos | -1.760 |
Token | introduced |
Token ID | 5495 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
anmar | +1.308 |
mil | +1.239 |
hub | +1.178 |
reluct | +1.171 |
fabrication | +1.161 |
Neg logit contributions | |
owitz | -2.138 |
illance | -1.912 |
chio | -1.886 |
edi | -1.812 |
oulos | -1.804 |
Token | the |
Token ID | 262 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
anmar | +4.167 |
mil | +3.964 |
hub | +3.877 |
fabrication | +3.812 |
reluct | +3.757 |
Neg logit contributions | |
owitz | -5.726 |
illance | -5.105 |
chio | -5.028 |
edi | -4.781 |
oulos | -4.765 |
Token | all |
Token ID | 477 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
anmar | +1.048 |
mil | +0.989 |
reluct | +0.944 |
hub | +0.942 |
fabrication | +0.931 |
Neg logit contributions | |
owitz | -1.572 |
illance | -1.399 |
chio | -1.383 |
edi | -1.325 |
oulos | -1.319 |
Token | - |
Token ID | 12 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
anmar | +1.463 |
mil | +1.383 |
reluct | +1.335 |
hub | +1.317 |
fabrication | +1.305 |
Neg logit contributions | |
owitz | -1.827 |
illance | -1.605 |
chio | -1.579 |
edi | -1.515 |
oulos | -1.505 |
Token | new |
Token ID | 3605 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
anmar | +0.427 |
reluct | +0.386 |
mil | +0.381 |
hub | +0.367 |
fabrication | +0.361 |
Neg logit contributions | |
owitz | -0.971 |
illance | -0.870 |
chio | -0.864 |
edi | -0.840 |
oulos | -0.828 |
Token | F |
Token ID | 376 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
anmar | +0.523 |
mil | +0.495 |
reluct | +0.475 |
hub | +0.472 |
fabrication | +0.467 |
Neg logit contributions | |
owitz | -0.695 |
illance | -0.614 |
chio | -0.606 |
edi | -0.581 |
oulos | -0.577 |
Token | product |
Token ID | 1720 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
owitz | +0.198 |
chio | +0.178 |
illance | +0.178 |
edi | +0.171 |
oulos | +0.169 |
Neg logit contributions | |
anmar | -0.106 |
mil | -0.099 |
reluct | -0.096 |
vg | -0.093 |
hub | -0.091 |
Token | - |
Token ID | 532 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
anmar | +0.961 |
mil | +0.907 |
reluct | +0.888 |
fabrication | +0.870 |
hub | +0.868 |
Neg logit contributions | |
owitz | -1.103 |
illance | -0.968 |
chio | -0.955 |
edi | -0.908 |
oulos | -0.907 |
Token | due |
Token ID | 2233 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
anmar | +2.054 |
mil | +1.940 |
hub | +1.848 |
reluct | +1.846 |
fabrication | +1.823 |
Neg logit contributions | |
owitz | -3.155 |
illance | -2.816 |
chio | -2.779 |
edi | -2.663 |
oulos | -2.652 |
Token | to |
Token ID | 284 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
owitz | +0.621 |
illance | +0.547 |
chio | +0.540 |
edi | +0.522 |
oulos | +0.519 |
Neg logit contributions | |
anmar | -0.433 |
mil | -0.410 |
reluct | -0.390 |
hub | -0.385 |
fabrication | -0.383 |
Token | a |
Token ID | 257 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
anmar | +0.272 |
mil | +0.259 |
reluct | +0.248 |
hub | +0.245 |
fabrication | +0.243 |
Neg logit contributions | |
owitz | -0.346 |
illance | -0.304 |
chio | -0.300 |
edi | -0.287 |
oulos | -0.286 |
Token | handful |
Token ID | 10089 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
owitz | +1.147 |
illance | +1.012 |
chio | +1.006 |
edi | +0.963 |
oulos | +0.959 |
Neg logit contributions | |
anmar | -0.799 |
mil | -0.753 |
reluct | -0.720 |
hub | -0.702 |
fabrication | -0.699 |
Token | of |
Token ID | 286 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
anmar | +1.024 |
mil | +0.965 |
hub | +0.909 |
fabrication | +0.883 |
vg | +0.865 |
Neg logit contributions | |
owitz | -2.175 |
illance | -1.979 |
chio | -1.949 |
oulos | -1.877 |
edi | -1.874 |
Token | multinational |
Token ID | 28061 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
anmar | +0.708 |
mil | +0.669 |
reluct | +0.639 |
hub | +0.632 |
fabrication | +0.626 |
Neg logit contributions | |
owitz | -1.053 |
illance | -0.934 |
chio | -0.924 |
edi | -0.886 |
oulos | -0.881 |
Token | s |
Token ID | 82 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
owitz | +1.583 |
illance | +1.410 |
chio | +1.406 |
edi | +1.356 |
oulos | +1.346 |
Neg logit contributions | |
anmar | -0.992 |
mil | -0.928 |
reluct | -0.891 |
vg | -0.855 |
fabrication | -0.853 |
Token | � |
Token ID | 447 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
owitz | +1.953 |
illance | +1.722 |
chio | +1.709 |
edi | +1.659 |
oulos | +1.634 |
Neg logit contributions | |
anmar | -1.428 |
mil | -1.332 |
reluct | -1.276 |
hub | -1.240 |
fabrication | -1.234 |
Token | � |
Token ID | 247 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
anmar | +0.094 |
mil | +0.090 |
reluct | +0.088 |
hub | +0.087 |
fabrication | +0.087 |
Neg logit contributions | |
owitz | -0.075 |
illance | -0.064 |
chio | -0.062 |
edi | -0.059 |
oulos | -0.058 |
Token | cast |
Token ID | 3350 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
owitz | +1.285 |
chio | +1.136 |
illance | +1.132 |
edi | +1.085 |
oulos | +1.071 |
Neg logit contributions | |
anmar | -0.903 |
mil | -0.840 |
reluct | -0.803 |
hub | -0.784 |
vg | -0.775 |
Token | in |
Token ID | 287 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
owitz | +2.297 |
illance | +1.995 |
chio | +1.987 |
oulos | +1.887 |
edi | +1.883 |
Neg logit contributions | |
anmar | -1.936 |
mil | -1.832 |
reluct | -1.805 |
hub | -1.749 |
vg | -1.725 |
Token | bronze |
Token ID | 22101 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
owitz | +1.603 |
illance | +1.414 |
chio | +1.404 |
edi | +1.346 |
oulos | +1.330 |
Neg logit contributions | |
anmar | -1.115 |
mil | -1.050 |
reluct | -1.016 |
hub | -0.986 |
vg | -0.979 |
Token | , |
Token ID | 11 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
owitz | +1.356 |
chio | +1.155 |
illance | +1.154 |
edi | +1.087 |
oulos | +1.082 |
Neg logit contributions | |
anmar | -1.575 |
mil | -1.483 |
reluct | -1.461 |
hub | -1.423 |
vg | -1.414 |
Token | balance |
Token ID | 5236 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
owitz | +1.121 |
chio | +1.001 |
illance | +0.998 |
edi | +0.956 |
oulos | +0.945 |
Neg logit contributions | |
anmar | -0.708 |
mil | -0.653 |
reluct | -0.629 |
fabrication | -0.610 |
hub | -0.608 |
Token | perfectly |
Token ID | 7138 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
owitz | +1.295 |
illance | +1.138 |
chio | +1.126 |
edi | +1.081 |
oulos | +1.068 |
Neg logit contributions | |
anmar | -0.996 |
mil | -0.930 |
reluct | -0.897 |
hub | -0.875 |
fabrication | -0.875 |
Token | on |
Token ID | 319 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
anmar | +0.463 |
mil | +0.438 |
reluct | +0.421 |
hub | +0.418 |
fabrication | +0.414 |
Neg logit contributions | |
owitz | -0.595 |
illance | -0.524 |
chio | -0.518 |
edi | -0.495 |
oulos | -0.492 |
Token | opposite |
Token ID | 6697 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
anmar | +1.112 |
mil | +1.051 |
reluct | +1.014 |
hub | +1.003 |
fabrication | +0.997 |
Neg logit contributions | |
owitz | -1.286 |
illance | -1.126 |
chio | -1.110 |
edi | -1.059 |
oulos | -1.052 |
Token | ends |
Token ID | 5645 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
owitz | +1.187 |
illance | +1.045 |
chio | +1.039 |
edi | +1.004 |
ilon | +0.987 |
Neg logit contributions | |
anmar | -0.804 |
mil | -0.735 |
reluct | -0.710 |
hub | -0.685 |
fabrication | -0.684 |
Token | of |
Token ID | 286 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
anmar | +0.261 |
mil | +0.242 |
reluct | +0.234 |
hub | +0.229 |
fabrication | +0.228 |
Neg logit contributions | |
owitz | -0.378 |
illance | -0.333 |
chio | -0.331 |
edi | -0.317 |
oulos | -0.314 |
Token | a |
Token ID | 257 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
owitz | +2.501 |
illance | +2.152 |
chio | +2.108 |
oulos | +1.996 |
ilon | +1.985 |
Neg logit contributions | |
anmar | -2.591 |
mil | -2.397 |
reluct | -2.349 |
confir | -2.288 |
vg | -2.279 |
Token | I |
Token ID | 314 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
anmar | +2.421 |
mil | +2.301 |
hub | +2.201 |
reluct | +2.198 |
fabrication | +2.178 |
Neg logit contributions | |
owitz | -3.143 |
illance | -2.774 |
chio | -2.743 |
edi | -2.619 |
oulos | -2.604 |
Token | created |
Token ID | 2727 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
anmar | +0.768 |
mil | +0.716 |
reluct | +0.685 |
hub | +0.677 |
fabrication | +0.671 |
Neg logit contributions | |
owitz | -1.195 |
illance | -1.068 |
chio | -1.059 |
edi | -1.020 |
oulos | -1.009 |
Token | from |
Token ID | 422 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
owitz | +0.200 |
illance | +0.175 |
chio | +0.174 |
edi | +0.166 |
oulos | +0.164 |
Neg logit contributions | |
anmar | -0.163 |
mil | -0.154 |
reluct | -0.149 |
hub | -0.146 |
fabrication | -0.146 |
Token | the |
Token ID | 262 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
owitz | +1.071 |
illance | +0.940 |
chio | +0.928 |
edi | +0.889 |
oulos | +0.880 |
Neg logit contributions | |
anmar | -0.868 |
mil | -0.807 |
reluct | -0.791 |
hub | -0.771 |
fabrication | -0.766 |
Token | pull |
Token ID | 2834 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
anmar | +0.273 |
mil | +0.255 |
reluct | +0.246 |
hub | +0.240 |
fabrication | +0.238 |
Neg logit contributions | |
owitz | -0.415 |
illance | -0.370 |
chio | -0.365 |
oulos | -0.350 |
edi | -0.349 |
Token | . |
Token ID | 13 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
anmar | +2.095 |
mil | +1.949 |
hub | +1.825 |
reluct | +1.811 |
fabrication | +1.782 |
Neg logit contributions | |
owitz | -4.865 |
illance | -4.409 |
chio | -4.369 |
edi | -4.211 |
oulos | -4.201 |
Token |
|
Token ID | 198 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
anmar | +2.920 |
mil | +2.771 |
reluct | +2.639 |
hub | +2.638 |
fabrication | +2.606 |
Neg logit contributions | |
owitz | -4.015 |
illance | -3.557 |
chio | -3.513 |
edi | -3.360 |
oulos | -3.344 |
Token |
|
Token ID | 198 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
mil | +1.757 |
anmar | +1.712 |
hub | +1.632 |
vg | +1.598 |
snap | +1.570 |
Neg logit contributions | |
owitz | -2.814 |
illance | -2.595 |
chio | -2.508 |
oulos | -2.430 |
edi | -2.394 |
Token | http |
Token ID | 4023 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
anmar | +2.129 |
mil | +2.016 |
reluct | +1.939 |
hub | +1.932 |
fabrication | +1.911 |
Neg logit contributions | |
owitz | -2.696 |
illance | -2.376 |
chio | -2.347 |
edi | -2.242 |
oulos | -2.228 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
anmar | +0.441 |
mil | +0.430 |
hub | +0.412 |
vg | +0.405 |
fabrication | +0.405 |
Neg logit contributions | |
owitz | -0.401 |
illance | -0.347 |
chio | -0.340 |
oulos | -0.321 |
edi | -0.321 |
Token | api |
Token ID | 15042 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
anmar | +0.574 |
mil | +0.534 |
reluct | +0.532 |
hub | +0.524 |
fabrication | +0.520 |
Neg logit contributions | |
owitz | -0.742 |
illance | -0.658 |
chio | -0.649 |
edi | -0.622 |
oulos | -0.615 |
Token | sign |
Token ID | 1051 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
anmar | +1.324 |
mil | +1.256 |
hub | +1.196 |
reluct | +1.176 |
fabrication | +1.176 |
Neg logit contributions | |
owitz | -2.341 |
illance | -2.105 |
chio | -2.068 |
edi | -1.988 |
oulos | -1.986 |
Token | the |
Token ID | 262 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
anmar | +0.819 |
mil | +0.770 |
reluct | +0.737 |
hub | +0.731 |
fabrication | +0.724 |
Neg logit contributions | |
owitz | -1.172 |
illance | -1.037 |
chio | -1.026 |
edi | -0.986 |
oulos | -0.978 |
Token | players |
Token ID | 1938 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
anmar | +0.756 |
mil | +0.714 |
hub | +0.681 |
reluct | +0.681 |
fabrication | +0.672 |
Neg logit contributions | |
owitz | -1.160 |
illance | -1.035 |
chio | -1.023 |
edi | -0.979 |
oulos | -0.975 |
Token | when |
Token ID | 618 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
anmar | +0.202 |
mil | +0.189 |
reluct | +0.181 |
hub | +0.179 |
fabrication | +0.178 |
Neg logit contributions | |
owitz | -0.281 |
illance | -0.247 |
chio | -0.244 |
edi | -0.236 |
oulos | -0.234 |
Token | over |
Token ID | 625 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
anmar | +1.453 |
mil | +1.358 |
reluct | +1.290 |
hub | +1.281 |
fabrication | +1.267 |
Neg logit contributions | |
owitz | -2.459 |
illance | -2.197 |
chio | -2.175 |
edi | -2.094 |
oulos | -2.081 |
Token | the |
Token ID | 262 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
anmar | +2.756 |
mil | +2.643 |
hub | +2.534 |
reluct | +2.520 |
fabrication | +2.498 |
Neg logit contributions | |
owitz | -3.174 |
illance | -2.790 |
chio | -2.763 |
edi | -2.608 |
oulos | -2.597 |
Token | cap |
Token ID | 1451 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
anmar | +1.548 |
mil | +1.442 |
reluct | +1.360 |
hub | +1.357 |
fabrication | +1.335 |
Neg logit contributions | |
owitz | -3.199 |
illance | -2.886 |
chio | -2.857 |
edi | -2.752 |
oulos | -2.741 |
Token | , |
Token ID | 11 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
anmar | +3.529 |
mil | +3.417 |
hub | +3.294 |
reluct | +3.268 |
fabrication | +3.246 |
Neg logit contributions | |
owitz | -3.841 |
illance | -3.390 |
chio | -3.327 |
edi | -3.147 |
oulos | -3.132 |
Token | functionally |
Token ID | 48410 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
anmar | +0.763 |
mil | +0.712 |
reluct | +0.681 |
hub | +0.673 |
fabrication | +0.666 |
Neg logit contributions | |
owitz | -1.140 |
illance | -1.006 |
chio | -1.001 |
edi | -0.962 |
oulos | -0.950 |
Token | useless |
Token ID | 13894 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
anmar | +0.434 |
mil | +0.406 |
reluct | +0.386 |
hub | +0.383 |
fabrication | +0.378 |
Neg logit contributions | |
owitz | -0.711 |
illance | -0.633 |
chio | -0.630 |
edi | -0.605 |
oulos | -0.599 |
Token | . |
Token ID | 13 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
owitz | +0.305 |
illance | +0.264 |
chio | +0.262 |
edi | +0.251 |
oulos | +0.248 |
Neg logit contributions | |
anmar | -0.295 |
mil | -0.278 |
reluct | -0.269 |
hub | -0.264 |
fabrication | -0.263 |
Token | See |
Token ID | 4091 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
anmar | +1.360 |
mil | +1.296 |
hub | +1.230 |
reluct | +1.222 |
fabrication | +1.215 |
Neg logit contributions | |
owitz | -1.985 |
illance | -1.776 |
chio | -1.748 |
edi | -1.680 |
oulos | -1.672 |
Token | more |
Token ID | 517 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
owitz | +3.705 |
illance | +3.364 |
chio | +3.292 |
edi | +3.175 |
™: | +3.165 |
Neg logit contributions | |
anmar | -1.761 |
mil | -1.579 |
reluct | -1.555 |
fabrication | -1.441 |
interstitial | -1.429 |
Token | Virtual |
Token ID | 15595 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
anmar | +0.285 |
mil | +0.269 |
hub | +0.261 |
vg | +0.252 |
fabrication | +0.252 |
Neg logit contributions | |
owitz | -0.603 |
illance | -0.543 |
chio | -0.534 |
edi | -0.522 |
oulos | -0.514 |
Token | Console |
Token ID | 24371 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
anmar | +1.949 |
mil | +1.872 |
hub | +1.813 |
fabrication | +1.720 |
vg | +1.687 |
Neg logit contributions | |
owitz | -3.967 |
illance | -3.624 |
chio | -3.556 |
ilon | -3.494 |
oulos | -3.482 |
Token | games |
Token ID | 1830 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
owitz | +1.227 |
illance | +1.109 |
chio | +1.095 |
edi | +1.056 |
oulos | +1.053 |
Neg logit contributions | |
anmar | -0.581 |
mil | -0.541 |
hub | -0.513 |
fabrication | -0.505 |
reluct | -0.505 |
Token | for |
Token ID | 329 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
owitz | +0.832 |
illance | +0.726 |
chio | +0.721 |
edi | +0.694 |
oulos | +0.684 |
Neg logit contributions | |
anmar | -0.714 |
mil | -0.671 |
reluct | -0.658 |
hub | -0.636 |
fabrication | -0.631 |
Token | Wii |
Token ID | 16591 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
anmar | +1.315 |
mil | +1.257 |
hub | +1.229 |
fabrication | +1.212 |
vg | +1.180 |
Neg logit contributions | |
owitz | -1.641 |
chio | -1.430 |
illance | -1.425 |
oulos | -1.367 |
edi | -1.360 |
Token | U |
Token ID | 471 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
anmar | +0.412 |
mil | +0.390 |
reluct | +0.381 |
fabrication | +0.373 |
hub | +0.371 |
Neg logit contributions | |
owitz | -0.426 |
chio | -0.370 |
illance | -0.370 |
edi | -0.349 |
ilon | -0.344 |
Token | . |
Token ID | 13 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
owitz | +4.004 |
chio | +3.472 |
illance | +3.419 |
™: | +3.339 |
ilon | +3.213 |
Neg logit contributions | |
anmar | -3.788 |
reluct | -3.555 |
mil | -3.522 |
interstitial | -3.465 |
fabrication | -3.382 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
anmar | +0.163 |
mil | +0.153 |
reluct | +0.151 |
fabrication | +0.148 |
hub | +0.148 |
Neg logit contributions | |
owitz | -0.153 |
illance | -0.132 |
chio | -0.131 |
oulos | -0.123 |
edi | -0.122 |
Token | The |
Token ID | 464 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
owitz | +2.130 |
illance | +1.836 |
chio | +1.833 |
edi | +1.755 |
ilon | +1.699 |
Neg logit contributions | |
anmar | -1.914 |
reluct | -1.853 |
hub | -1.790 |
fabrication | -1.757 |
confir | -1.755 |
Token | extend |
Token ID | 9117 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
owitz | +0.041 |
illance | +0.037 |
chio | +0.037 |
edi | +0.035 |
oulos | +0.035 |
Neg logit contributions | |
anmar | -0.025 |
mil | -0.024 |
reluct | -0.023 |
hub | -0.022 |
fabrication | -0.022 |
Token | human |
Token ID | 1692 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
owitz | +1.664 |
illance | +1.463 |
chio | +1.457 |
edi | +1.399 |
ilon | +1.384 |
Neg logit contributions | |
anmar | -1.217 |
mil | -1.128 |
reluct | -1.092 |
vg | -1.050 |
interstitial | -1.043 |
Token | consciousness |
Token ID | 10510 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
owitz | +1.205 |
illance | +1.080 |
chio | +1.067 |
edi | +1.030 |
ilon | +1.013 |
Neg logit contributions | |
anmar | -0.728 |
mil | -0.678 |
reluct | -0.660 |
vg | -0.633 |
hub | -0.632 |
Token | throughout |
Token ID | 3690 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
owitz | +1.210 |
illance | +1.060 |
chio | +1.045 |
edi | +1.003 |
ilon | +0.991 |
Neg logit contributions | |
anmar | -0.986 |
mil | -0.923 |
reluct | -0.898 |
hub | -0.875 |
fabrication | -0.870 |
Token | the |
Token ID | 262 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
owitz | +0.559 |
illance | +0.488 |
chio | +0.482 |
edi | +0.462 |
oulos | +0.456 |
Neg logit contributions | |
anmar | -0.472 |
mil | -0.447 |
reluct | -0.431 |
hub | -0.421 |
vg | -0.417 |
Token | universe |
Token ID | 6881 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
anmar | +0.263 |
mil | +0.250 |
reluct | +0.241 |
hub | +0.236 |
fabrication | +0.234 |
Neg logit contributions | |
owitz | -0.296 |
illance | -0.258 |
chio | -0.255 |
edi | -0.243 |
oulos | -0.241 |
Token | . |
Token ID | 13 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
owitz | +0.661 |
illance | +0.572 |
chio | +0.564 |
edi | +0.538 |
oulos | +0.534 |
Neg logit contributions | |
anmar | -0.650 |
mil | -0.612 |
reluct | -0.597 |
hub | -0.583 |
fabrication | -0.580 |
Token | But |
Token ID | 887 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
owitz | +1.301 |
illance | +1.134 |
chio | +1.127 |
edi | +1.074 |
oulos | +1.066 |
Neg logit contributions | |
anmar | -1.088 |
mil | -1.010 |
reluct | -1.006 |
fabrication | -0.968 |
hub | -0.967 |
Token | the |
Token ID | 262 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
anmar | +0.656 |
mil | +0.622 |
hub | +0.596 |
reluct | +0.595 |
fabrication | +0.588 |
Neg logit contributions | |
owitz | -0.915 |
illance | -0.812 |
chio | -0.802 |
edi | -0.767 |
oulos | -0.763 |
Token | presence |
Token ID | 4931 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
anmar | +0.500 |
mil | +0.471 |
reluct | +0.449 |
hub | +0.444 |
fabrication | +0.440 |
Neg logit contributions | |
owitz | -0.766 |
illance | -0.681 |
chio | -0.675 |
edi | -0.646 |
oulos | -0.644 |
Token | of |
Token ID | 286 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
owitz | +2.497 |
illance | +2.225 |
chio | +2.199 |
edi | +2.112 |
oulos | +2.097 |
Neg logit contributions | |
anmar | -1.650 |
mil | -1.526 |
reluct | -1.421 |
interstitial | -1.399 |
vg | -1.398 |
Token | who |
Token ID | 8727 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
owitz | +0.465 |
illance | +0.404 |
chio | +0.401 |
edi | +0.383 |
oulos | +0.378 |
Neg logit contributions | |
anmar | -0.420 |
mil | -0.394 |
reluct | -0.388 |
hub | -0.384 |
fabrication | -0.381 |
Token | can |
Token ID | 460 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
owitz | +0.755 |
illance | +0.672 |
chio | +0.666 |
edi | +0.640 |
oulos | +0.633 |
Neg logit contributions | |
anmar | -0.521 |
mil | -0.483 |
reluct | -0.466 |
hub | -0.458 |
fabrication | -0.458 |
Token | we |
Token ID | 356 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
anmar | +0.007 |
mil | +0.007 |
reluct | +0.006 |
hub | +0.006 |
fabrication | +0.006 |
Neg logit contributions | |
owitz | -0.012 |
illance | -0.011 |
chio | -0.011 |
edi | -0.010 |
oulos | -0.010 |
Token | find |
Token ID | 1064 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
owitz | +0.828 |
illance | +0.740 |
chio | +0.734 |
edi | +0.706 |
oulos | +0.702 |
Neg logit contributions | |
anmar | -0.475 |
mil | -0.444 |
reluct | -0.423 |
hub | -0.420 |
fabrication | -0.415 |
Token | to |
Token ID | 284 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
anmar | +0.103 |
mil | +0.097 |
reluct | +0.093 |
hub | +0.092 |
fabrication | +0.092 |
Neg logit contributions | |
owitz | -0.135 |
illance | -0.119 |
chio | -0.118 |
edi | -0.113 |
oulos | -0.112 |
Token | replace |
Token ID | 6330 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
anmar | +0.248 |
mil | +0.232 |
reluct | +0.221 |
hub | +0.219 |
fabrication | +0.217 |
Neg logit contributions | |
owitz | -0.424 |
illance | -0.379 |
chio | -0.376 |
edi | -0.361 |
oulos | -0.359 |
Token | them |
Token ID | 606 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
owitz | +0.107 |
chio | +0.094 |
illance | +0.094 |
edi | +0.091 |
oulos | +0.089 |
Neg logit contributions | |
anmar | -0.081 |
mil | -0.076 |
reluct | -0.073 |
fabrication | -0.072 |
hub | -0.071 |
Token | ", |
Token ID | 1600 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
owitz | +1.553 |
illance | +1.339 |
chio | +1.333 |
edi | +1.275 |
oulos | +1.260 |
Neg logit contributions | |
anmar | -1.516 |
mil | -1.438 |
reluct | -1.395 |
fabrication | -1.374 |
hub | -1.370 |
Token | rather |
Token ID | 2138 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
anmar | +0.085 |
mil | +0.080 |
reluct | +0.076 |
hub | +0.075 |
fabrication | +0.075 |
Neg logit contributions | |
owitz | -0.120 |
illance | -0.106 |
chio | -0.105 |
edi | -0.101 |
oulos | -0.100 |
Token | than |
Token ID | 621 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
anmar | +0.048 |
mil | +0.044 |
reluct | +0.040 |
fabrication | +0.040 |
vg | +0.040 |
Neg logit contributions | |
owitz | -0.102 |
illance | -0.093 |
chio | -0.091 |
edi | -0.088 |
oulos | -0.088 |
Token | lets |
Token ID | 8781 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
anmar | +0.231 |
mil | +0.219 |
reluct | +0.210 |
hub | +0.209 |
fabrication | +0.207 |
Neg logit contributions | |
owitz | -0.283 |
illance | -0.249 |
chio | -0.247 |
edi | -0.235 |
oulos | -0.233 |
Token | is |
Token ID | 318 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
owitz | +0.197 |
illance | +0.177 |
chio | +0.174 |
edi | +0.168 |
oulos | +0.167 |
Neg logit contributions | |
anmar | -0.117 |
mil | -0.109 |
reluct | -0.105 |
hub | -0.102 |
fabrication | -0.102 |
Token | an |
Token ID | 281 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
owitz | +1.302 |
illance | +1.143 |
chio | +1.127 |
oulos | +1.073 |
edi | +1.069 |
Neg logit contributions | |
anmar | -1.168 |
mil | -1.113 |
reluct | -1.067 |
hub | -1.049 |
fabrication | -1.043 |
Token | interview |
Token ID | 2720 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
owitz | +0.187 |
illance | +0.166 |
chio | +0.165 |
edi | +0.158 |
oulos | +0.157 |
Neg logit contributions | |
anmar | -0.126 |
mil | -0.120 |
reluct | -0.114 |
hub | -0.112 |
fabrication | -0.111 |
Token | with |
Token ID | 351 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
anmar | +0.216 |
mil | +0.204 |
reluct | +0.193 |
hub | +0.191 |
fabrication | +0.190 |
Neg logit contributions | |
owitz | -0.321 |
illance | -0.285 |
chio | -0.282 |
edi | -0.270 |
oulos | -0.269 |
Token | one |
Token ID | 530 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
anmar | +2.016 |
mil | +1.915 |
hub | +1.844 |
reluct | +1.841 |
fabrication | +1.823 |
Neg logit contributions | |
owitz | -2.401 |
illance | -2.110 |
chio | -2.082 |
edi | -1.981 |
oulos | -1.968 |
Token | of |
Token ID | 286 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
owitz | +0.767 |
illance | +0.680 |
chio | +0.672 |
edi | +0.653 |
oulos | +0.644 |
Neg logit contributions | |
anmar | -0.496 |
mil | -0.458 |
reluct | -0.434 |
hub | -0.426 |
fabrication | -0.423 |
Token | the |
Token ID | 262 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
anmar | +0.128 |
mil | +0.121 |
reluct | +0.116 |
hub | +0.115 |
fabrication | +0.114 |
Neg logit contributions | |
owitz | -0.157 |
illance | -0.138 |
chio | -0.136 |
edi | -0.131 |
oulos | -0.130 |
Token | largest |
Token ID | 4387 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
anmar | +0.216 |
mil | +0.203 |
reluct | +0.194 |
hub | +0.193 |
fabrication | +0.191 |
Neg logit contributions | |
owitz | -0.293 |
illance | -0.259 |
chio | -0.257 |
edi | -0.246 |
oulos | -0.244 |
Token | anarchist |
Token ID | 26177 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
owitz | +2.598 |
illance | +2.277 |
chio | +2.274 |
edi | +2.186 |
itar | +2.168 |
Neg logit contributions | |
anmar | -2.087 |
mil | -1.954 |
reluct | -1.845 |
vg | -1.816 |
interstitial | -1.815 |
Token | groups |
Token ID | 2628 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
owitz | +1.024 |
illance | +0.898 |
chio | +0.890 |
edi | +0.853 |
oulos | +0.841 |
Neg logit contributions | |
anmar | -0.876 |
mil | -0.827 |
reluct | -0.786 |
hub | -0.776 |
fabrication | -0.773 |
Token | in |
Token ID | 287 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
owitz | +0.961 |
illance | +0.843 |
chio | +0.829 |
edi | +0.800 |
oulos | +0.791 |
Neg logit contributions | |
anmar | -0.756 |
mil | -0.712 |
reluct | -0.680 |
hub | -0.670 |
fabrication | -0.670 |
Token | football |
Token ID | 4346 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
owitz | +2.673 |
illance | +2.385 |
chio | +2.379 |
edi | +2.282 |
ilon | +2.279 |
Neg logit contributions | |
anmar | -1.270 |
mil | -1.132 |
reluct | -1.072 |
vg | -1.029 |
interstitial | -1.016 |
Token | coverage |
Token ID | 5197 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
owitz | +0.833 |
illance | +0.717 |
chio | +0.711 |
edi | +0.677 |
oulos | +0.674 |
Neg logit contributions | |
anmar | -0.770 |
mil | -0.723 |
reluct | -0.701 |
hub | -0.685 |
fabrication | -0.683 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
owitz | +1.474 |
illance | +1.241 |
chio | +1.229 |
edi | +1.176 |
oulos | +1.159 |
Neg logit contributions | |
anmar | -1.623 |
mil | -1.526 |
reluct | -1.491 |
fabrication | -1.457 |
vg | -1.449 |
Token | has |
Token ID | 468 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
anmar | +0.871 |
mil | +0.816 |
reluct | +0.781 |
hub | +0.774 |
fabrication | +0.768 |
Neg logit contributions | |
owitz | -1.261 |
illance | -1.116 |
chio | -1.107 |
edi | -1.060 |
oulos | -1.055 |
Token | shown |
Token ID | 3402 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
owitz | +2.104 |
chio | +1.816 |
illance | +1.813 |
edi | +1.730 |
oulos | +1.712 |
Neg logit contributions | |
anmar | -1.835 |
mil | -1.727 |
reluct | -1.653 |
vg | -1.623 |
hub | -1.623 |
Token | a |
Token ID | 257 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
anmar | +1.123 |
mil | +1.060 |
reluct | +1.011 |
hub | +1.008 |
fabrication | +0.997 |
Neg logit contributions | |
owitz | -1.576 |
illance | -1.394 |
chio | -1.379 |
edi | -1.320 |
oulos | -1.313 |
Token | highly |
Token ID | 4047 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
owitz | +0.355 |
illance | +0.316 |
chio | +0.314 |
edi | +0.300 |
oulos | +0.299 |
Neg logit contributions | |
anmar | -0.216 |
mil | -0.200 |
reluct | -0.189 |
hub | -0.186 |
fabrication | -0.185 |
Token | un |
Token ID | 555 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
owitz | +3.013 |
illance | +2.638 |
chio | +2.605 |
edi | +2.518 |
oulos | +2.487 |
Neg logit contributions | |
anmar | -2.190 |
mil | -2.047 |
reluct | -1.923 |
fabrication | -1.905 |
hub | -1.901 |
Token | character |
Token ID | 22769 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
anmar | +0.304 |
mil | +0.288 |
reluct | +0.284 |
hub | +0.279 |
fabrication | +0.278 |
Neg logit contributions | |
owitz | -0.298 |
illance | -0.258 |
chio | -0.255 |
edi | -0.243 |
oulos | -0.241 |
Token | istic |
Token ID | 2569 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
anmar | +0.173 |
mil | +0.164 |
reluct | +0.160 |
hub | +0.158 |
fabrication | +0.156 |
Neg logit contributions | |
owitz | -0.166 |
illance | -0.142 |
chio | -0.141 |
edi | -0.134 |
oulos | -0.132 |
Token | interest |
Token ID | 1393 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
anmar | +0.962 |
mil | +0.900 |
reluct | +0.852 |
hub | +0.849 |
fabrication | +0.838 |
Neg logit contributions | |
owitz | -1.755 |
illance | -1.575 |
chio | -1.558 |
edi | -1.499 |
oulos | -1.492 |
Token | their |
Token ID | 511 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
owitz | +0.106 |
illance | +0.093 |
chio | +0.092 |
edi | +0.088 |
oulos | +0.087 |
Neg logit contributions | |
anmar | -0.086 |
mil | -0.081 |
reluct | -0.078 |
hub | -0.077 |
fabrication | -0.077 |
Token | company |
Token ID | 1664 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
owitz | +1.135 |
illance | +1.014 |
chio | +1.000 |
oulos | +0.953 |
edi | +0.952 |
Neg logit contributions | |
anmar | -0.712 |
mil | -0.668 |
reluct | -0.630 |
vg | -0.616 |
hub | -0.613 |
Token | . |
Token ID | 13 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
owitz | +1.256 |
illance | +1.085 |
chio | +1.050 |
edi | +0.999 |
oulos | +0.984 |
Neg logit contributions | |
anmar | -1.362 |
mil | -1.293 |
reluct | -1.254 |
vg | -1.235 |
hub | -1.227 |
Token | I |
Token ID | 314 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
anmar | +0.082 |
mil | +0.077 |
reluct | +0.076 |
hub | +0.074 |
fabrication | +0.074 |
Neg logit contributions | |
owitz | -0.103 |
illance | -0.090 |
chio | -0.090 |
edi | -0.085 |
oulos | -0.085 |
Token | see |
Token ID | 766 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
anmar | +1.410 |
mil | +1.331 |
reluct | +1.271 |
hub | +1.267 |
fabrication | +1.253 |
Neg logit contributions | |
owitz | -2.076 |
illance | -1.845 |
chio | -1.824 |
edi | -1.748 |
oulos | -1.739 |
Token | this |
Token ID | 428 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
owitz | +1.142 |
illance | +0.999 |
chio | +0.991 |
edi | +0.948 |
oulos | +0.944 |
Neg logit contributions | |
anmar | -0.864 |
mil | -0.815 |
reluct | -0.783 |
hub | -0.769 |
fabrication | -0.765 |
Token | when |
Token ID | 618 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
owitz | +1.159 |
illance | +1.011 |
chio | +1.009 |
edi | +0.962 |
oulos | +0.958 |
Neg logit contributions | |
anmar | -0.876 |
mil | -0.816 |
reluct | -0.775 |
hub | -0.765 |
vg | -0.761 |
Token | I |
Token ID | 314 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
anmar | +1.975 |
mil | +1.852 |
hub | +1.766 |
reluct | +1.758 |
fabrication | +1.738 |
Neg logit contributions | |
owitz | -3.423 |
illance | -3.068 |
chio | -3.034 |
edi | -2.910 |
oulos | -2.898 |
Token | join |
Token ID | 4654 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
anmar | +1.284 |
mil | +1.210 |
reluct | +1.153 |
hub | +1.151 |
fabrication | +1.136 |
Neg logit contributions | |
owitz | -1.995 |
illance | -1.778 |
chio | -1.757 |
edi | -1.685 |
oulos | -1.677 |
Token | Bour |
Token ID | 20576 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
anmar | +0.524 |
mil | +0.499 |
reluct | +0.480 |
hub | +0.474 |
fabrication | +0.472 |
Neg logit contributions | |
owitz | -0.628 |
illance | -0.548 |
chio | -0.542 |
edi | -0.519 |
oulos | -0.515 |
Token | dain |
Token ID | 27162 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
owitz | +0.014 |
illance | +0.012 |
chio | +0.012 |
edi | +0.011 |
oulos | +0.011 |
Neg logit contributions | |
anmar | -0.024 |
mil | -0.024 |
reluct | -0.023 |
hub | -0.023 |
fabrication | -0.023 |
Token | algorithm |
Token ID | 11862 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
owitz | +1.305 |
illance | +1.163 |
chio | +1.155 |
edi | +1.107 |
oulos | +1.098 |
Neg logit contributions | |
anmar | -0.839 |
mil | -0.785 |
reluct | -0.750 |
vg | -0.727 |
hub | -0.723 |
Token | and |
Token ID | 290 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
owitz | +1.780 |
illance | +1.557 |
chio | +1.547 |
edi | +1.485 |
ilon | +1.459 |
Neg logit contributions | |
anmar | -1.414 |
mil | -1.319 |
reluct | -1.266 |
hub | -1.235 |
interstitial | -1.233 |
Token | North |
Token ID | 2258 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
owitz | +1.617 |
illance | +1.430 |
chio | +1.413 |
edi | +1.367 |
oulos | +1.347 |
Neg logit contributions | |
anmar | -1.320 |
mil | -1.238 |
reluct | -1.184 |
vg | -1.165 |
hub | -1.160 |
Token | rop |
Token ID | 1773 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
owitz | +1.165 |
illance | +1.028 |
chio | +1.017 |
edi | +0.972 |
oulos | +0.965 |
Neg logit contributions | |
anmar | -0.887 |
mil | -0.836 |
reluct | -0.818 |
hub | -0.799 |
fabrication | -0.793 |
Token | Gr |
Token ID | 1902 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
owitz | +3.645 |
illance | +3.209 |
chio | +3.169 |
edi | +3.064 |
oulos | +3.052 |
Neg logit contributions | |
anmar | -3.241 |
mil | -2.969 |
interstitial | -2.917 |
reluct | -2.895 |
vg | -2.836 |
Token | um |
Token ID | 388 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
owitz | +1.443 |
illance | +1.206 |
chio | +1.190 |
edi | +1.114 |
oulos | +1.094 |
Neg logit contributions | |
anmar | -2.116 |
mil | -2.024 |
reluct | -2.007 |
hub | -1.972 |
fabrication | -1.959 |
Token | man |
Token ID | 805 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
owitz | +4.588 |
chio | +3.888 |
illance | +3.805 |
edi | +3.665 |
ilon | +3.515 |
Neg logit contributions | |
anmar | -5.214 |
reluct | -5.184 |
confir | -4.913 |
interstitial | -4.827 |
carbohyd | -4.806 |
Token | , |
Token ID | 11 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
owitz | +4.824 |
illance | +4.279 |
chio | +4.235 |
edi | +4.134 |
ilon | +4.039 |
Neg logit contributions | |
anmar | -4.113 |
mil | -3.755 |
interstitial | -3.678 |
reluct | -3.628 |
vg | -3.623 |
Token | the |
Token ID | 262 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
owitz | +1.222 |
illance | +1.072 |
chio | +1.056 |
edi | +1.018 |
oulos | +1.015 |
Neg logit contributions | |
anmar | -1.011 |
mil | -0.947 |
reluct | -0.910 |
hub | -0.896 |
fabrication | -0.896 |
Token | manufacturer |
Token ID | 11554 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
anmar | +0.305 |
mil | +0.287 |
reluct | +0.273 |
hub | +0.266 |
vg | +0.264 |
Neg logit contributions | |
owitz | -0.492 |
illance | -0.439 |
chio | -0.435 |
edi | -0.417 |
oulos | -0.415 |
Token | of |
Token ID | 286 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
anmar | +0.516 |
mil | +0.485 |
reluct | +0.466 |
hub | +0.460 |
fabrication | +0.455 |
Neg logit contributions | |
owitz | -0.663 |
illance | -0.583 |
chio | -0.577 |
edi | -0.553 |
oulos | -0.548 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
owitz | +0.503 |
illance | +0.440 |
chio | +0.435 |
edi | +0.419 |
oulos | +0.415 |
Neg logit contributions | |
anmar | -0.415 |
mil | -0.391 |
reluct | -0.377 |
hub | -0.370 |
fabrication | -0.367 |
Token | institutional |
Token ID | 15855 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
anmar | +0.634 |
mil | +0.600 |
reluct | +0.575 |
hub | +0.569 |
fabrication | +0.565 |
Neg logit contributions | |
owitz | -0.838 |
illance | -0.741 |
chio | -0.731 |
edi | -0.699 |
oulos | -0.697 |
Token | church |
Token ID | 4928 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
owitz | +1.431 |
illance | +1.281 |
chio | +1.251 |
edi | +1.206 |
itar | +1.190 |
Neg logit contributions | |
anmar | -1.046 |
mil | -0.965 |
reluct | -0.932 |
vg | -0.904 |
interstitial | -0.902 |
Token | , |
Token ID | 11 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
owitz | +2.367 |
illance | +2.087 |
chio | +2.010 |
edi | +1.948 |
ilon | +1.931 |
Neg logit contributions | |
anmar | -2.038 |
mil | -1.859 |
reluct | -1.857 |
vg | -1.793 |
interstitial | -1.780 |
Token | said |
Token ID | 531 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
owitz | +1.036 |
illance | +0.892 |
chio | +0.873 |
edi | +0.844 |
oulos | +0.842 |
Neg logit contributions | |
anmar | -1.013 |
mil | -0.945 |
reluct | -0.919 |
hub | -0.904 |
fabrication | -0.899 |
Token | Lauren |
Token ID | 25672 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
owitz | +0.607 |
chio | +0.511 |
illance | +0.511 |
oulos | +0.488 |
edi | +0.487 |
Neg logit contributions | |
anmar | -0.629 |
mil | -0.594 |
reluct | -0.577 |
hub | -0.565 |
fabrication | -0.564 |
Token | Sand |
Token ID | 3837 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
owitz | +4.530 |
chio | +3.853 |
illance | +3.779 |
edi | +3.639 |
oulos | +3.620 |
Neg logit contributions | |
anmar | -4.161 |
reluct | -3.933 |
confir | -3.754 |
mil | -3.727 |
fabrication | -3.704 |
Token | ler |
Token ID | 1754 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
anmar | +1.314 |
mil | +1.253 |
reluct | +1.216 |
hub | +1.209 |
fabrication | +1.200 |
Neg logit contributions | |
owitz | -1.247 |
illance | -1.075 |
chio | -1.060 |
edi | -1.004 |
oulos | -0.997 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
anmar | +0.727 |
mil | +0.687 |
reluct | +0.674 |
hub | +0.667 |
fabrication | +0.664 |
Neg logit contributions | |
owitz | -0.649 |
illance | -0.550 |
chio | -0.545 |
edi | -0.515 |
oulos | -0.512 |
Token | author |
Token ID | 1772 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
anmar | +0.004 |
mil | +0.004 |
reluct | +0.004 |
hub | +0.004 |
fabrication | +0.004 |
Neg logit contributions | |
owitz | -0.004 |
illance | -0.004 |
chio | -0.004 |
edi | -0.004 |
oulos | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
owitz | +2.060 |
illance | +1.815 |
chio | +1.784 |
edi | +1.722 |
oulos | +1.721 |
Neg logit contributions | |
anmar | -1.239 |
mil | -1.137 |
reluct | -1.103 |
fabrication | -1.083 |
hub | -1.083 |
Token | think |
Token ID | 892 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
owitz | +2.140 |
illance | +1.915 |
chio | +1.902 |
oulos | +1.814 |
edi | +1.813 |
Neg logit contributions | |
anmar | -1.399 |
mil | -1.285 |
reluct | -1.243 |
fabrication | -1.211 |
interstitial | -1.209 |
Token | Putin |
Token ID | 8144 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
owitz | +0.135 |
illance | +0.119 |
chio | +0.118 |
edi | +0.113 |
oulos | +0.112 |
Neg logit contributions | |
anmar | -0.092 |
mil | -0.086 |
reluct | -0.083 |
hub | -0.081 |
fabrication | -0.080 |
Token | will |
Token ID | 481 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
anmar | +0.748 |
mil | +0.691 |
reluct | +0.666 |
hub | +0.659 |
fabrication | +0.651 |
Neg logit contributions | |
owitz | -1.209 |
illance | -1.079 |
chio | -1.068 |
edi | -1.026 |
oulos | -1.019 |
Token | be |
Token ID | 307 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
owitz | +0.212 |
illance | +0.188 |
chio | +0.187 |
edi | +0.180 |
oulos | +0.178 |
Neg logit contributions | |
anmar | -0.139 |
mil | -0.129 |
reluct | -0.125 |
hub | -0.122 |
fabrication | -0.121 |
Token | talked |
Token ID | 6619 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
anmar | +0.409 |
mil | +0.388 |
reluct | +0.372 |
hub | +0.372 |
fabrication | +0.367 |
Neg logit contributions | |
owitz | -0.527 |
illance | -0.465 |
chio | -0.459 |
edi | -0.438 |
oulos | -0.436 |
Token | out |
Token ID | 503 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
owitz | +2.121 |
illance | +1.834 |
chio | +1.799 |
edi | +1.727 |
itar | +1.708 |
Neg logit contributions | |
anmar | -1.796 |
mil | -1.680 |
reluct | -1.623 |
vg | -1.589 |
interstitial | -1.574 |
Token | of |
Token ID | 286 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
owitz | +4.753 |
illance | +4.195 |
chio | +4.082 |
oulos | +3.937 |
itar | +3.919 |
Neg logit contributions | |
anmar | -3.377 |
mil | -3.015 |
interstitial | -2.957 |
reluct | -2.909 |
fabrication | -2.892 |
Token | his |
Token ID | 465 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
owitz | +4.060 |
illance | +3.503 |
chio | +3.490 |
edi | +3.392 |
oulos | +3.330 |
Neg logit contributions | |
anmar | -3.164 |
mil | -2.946 |
reluct | -2.797 |
interstitial | -2.730 |
vg | -2.711 |
Token | decades |
Token ID | 4647 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
owitz | +0.750 |
illance | +0.663 |
chio | +0.656 |
oulos | +0.625 |
edi | +0.624 |
Neg logit contributions | |
anmar | -0.477 |
mil | -0.453 |
reluct | -0.432 |
vg | -0.423 |
interstitial | -0.419 |
Token | - |
Token ID | 12 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
owitz | +0.883 |
illance | +0.794 |
chio | +0.770 |
oulos | +0.739 |
edi | +0.739 |
Neg logit contributions | |
anmar | -0.699 |
mil | -0.648 |
reluct | -0.636 |
hub | -0.619 |
vg | -0.617 |
Token | long |
Token ID | 6511 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
owitz | +1.748 |
illance | +1.484 |
chio | +1.453 |
edi | +1.399 |
ilon | +1.368 |
Neg logit contributions | |
anmar | -1.989 |
reluct | -1.886 |
mil | -1.846 |
hub | -1.839 |
fabrication | -1.828 |
Token | t |
Token ID | 83 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
owitz | +0.777 |
illance | +0.692 |
chio | +0.680 |
oulos | +0.650 |
edi | +0.649 |
Neg logit contributions | |
anmar | -0.546 |
mil | -0.522 |
hub | -0.492 |
fabrication | -0.485 |
reluct | -0.485 |
Token | u |
Token ID | 334 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
owitz | +3.719 |
chio | +3.212 |
illance | +3.158 |
edi | +3.101 |
ilon | +3.079 |
Neg logit contributions | |
anmar | -4.143 |
reluct | -3.823 |
mil | -3.811 |
confir | -3.688 |
fabrication | -3.677 |
Token | Part |
Token ID | 7841 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
owitz | +1.314 |
chio | +1.101 |
illance | +1.079 |
edi | +1.021 |
ilon | +1.017 |
Neg logit contributions | |
anmar | -2.091 |
mil | -1.983 |
reluct | -1.970 |
hub | -1.960 |
fabrication | -1.938 |
Token | icle |
Token ID | 1548 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
owitz | +1.941 |
illance | +1.641 |
chio | +1.637 |
edi | +1.529 |
ilon | +1.528 |
Neg logit contributions | |
anmar | -2.472 |
reluct | -2.377 |
mil | -2.373 |
hub | -2.307 |
fabrication | -2.295 |
Token | = |
Token ID | 796 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
owitz | +1.557 |
illance | +1.346 |
chio | +1.346 |
edi | +1.275 |
ilon | +1.269 |
Neg logit contributions | |
anmar | -1.712 |
mil | -1.596 |
reluct | -1.577 |
hub | -1.560 |
fabrication | -1.557 |
Token | 0 |
Token ID | 657 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
owitz | +3.132 |
chio | +2.678 |
illance | +2.660 |
edi | +2.586 |
ilon | +2.574 |
Neg logit contributions | |
anmar | -3.549 |
mil | -3.288 |
reluct | -3.251 |
interstitial | -3.143 |
fabrication | -3.087 |
Token | ; |
Token ID | 2162 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
owitz | +2.604 |
illance | +2.116 |
chio | +2.085 |
edi | +2.013 |
ilon | +1.974 |
Neg logit contributions | |
anmar | -5.004 |
fabrication | -4.645 |
mil | -4.636 |
reluct | -4.619 |
hub | -4.575 |
Token | u |
Token ID | 334 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
owitz | +2.350 |
chio | +2.070 |
illance | +2.066 |
edi | +1.980 |
™: | +1.980 |
Neg logit contributions | |
anmar | -2.022 |
mil | -1.875 |
reluct | -1.830 |
hub | -1.756 |
interstitial | -1.754 |
Token | Part |
Token ID | 7841 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
owitz | +0.921 |
illance | +0.799 |
chio | +0.795 |
edi | +0.755 |
oulos | +0.747 |
Neg logit contributions | |
anmar | -0.861 |
mil | -0.817 |
reluct | -0.797 |
hub | -0.788 |
fabrication | -0.779 |
Token | icle |
Token ID | 1548 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
owitz | +2.146 |
illance | +1.845 |
chio | +1.827 |
edi | +1.725 |
oulos | +1.706 |
Neg logit contributions | |
anmar | -2.349 |
mil | -2.241 |
reluct | -2.214 |
hub | -2.171 |
fabrication | -2.153 |
Token | < |
Token ID | 1279 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
owitz | +2.566 |
illance | +2.261 |
chio | +2.207 |
edi | +2.140 |
ilon | +2.111 |
Neg logit contributions | |
anmar | -2.657 |
mil | -2.431 |
reluct | -2.417 |
fabrication | -2.371 |
hub | -2.371 |
Token | Rouhani |
Token ID | 34915 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
anmar | +0.139 |
mil | +0.131 |
reluct | +0.129 |
fabrication | +0.127 |
hub | +0.127 |
Neg logit contributions | |
owitz | -0.117 |
illance | -0.099 |
chio | -0.097 |
edi | -0.093 |
oulos | -0.092 |
Token | has |
Token ID | 468 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
anmar | +3.400 |
mil | +3.258 |
hub | +3.097 |
reluct | +3.083 |
fabrication | +3.050 |
Neg logit contributions | |
owitz | -4.336 |
illance | -3.854 |
chio | -3.775 |
edi | -3.610 |
oulos | -3.586 |
Token | shown |
Token ID | 3402 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
owitz | +1.156 |
illance | +1.010 |
chio | +1.006 |
edi | +0.958 |
ilon | +0.952 |
Neg logit contributions | |
anmar | -0.958 |
mil | -0.904 |
reluct | -0.874 |
hub | -0.857 |
fabrication | -0.856 |
Token | he |
Token ID | 339 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
anmar | +1.626 |
mil | +1.542 |
reluct | +1.479 |
hub | +1.476 |
fabrication | +1.460 |
Neg logit contributions | |
owitz | -2.074 |
illance | -1.830 |
chio | -1.807 |
edi | -1.726 |
oulos | -1.716 |
Token | is |
Token ID | 318 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
owitz | +0.966 |
illance | +0.860 |
chio | +0.851 |
edi | +0.818 |
oulos | +0.805 |
Neg logit contributions | |
anmar | -0.613 |
mil | -0.564 |
reluct | -0.547 |
interstitial | -0.535 |
fabrication | -0.534 |
Token | listening |
Token ID | 8680 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
owitz | +0.876 |
illance | +0.777 |
chio | +0.770 |
edi | +0.740 |
ilon | +0.734 |
Neg logit contributions | |
anmar | -0.550 |
mil | -0.511 |
reluct | -0.492 |
hub | -0.482 |
fabrication | -0.479 |
Token | , |
Token ID | 11 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
owitz | +5.997 |
illance | +5.188 |
chio | +5.037 |
ilon | +4.922 |
edi | +4.922 |
Neg logit contributions | |
anmar | -5.073 |
interstitial | -4.762 |
reluct | -4.759 |
mil | -4.731 |
fabrication | -4.622 |
Token | referring |
Token ID | 9759 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
owitz | +3.514 |
illance | +3.068 |
chio | +3.013 |
edi | +2.932 |
oulos | +2.920 |
Neg logit contributions | |
anmar | -2.555 |
mil | -2.385 |
reluct | -2.291 |
interstitial | -2.240 |
vg | -2.240 |
Token | to |
Token ID | 284 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
anmar | +0.032 |
mil | +0.031 |
reluct | +0.029 |
fabrication | +0.029 |
hub | +0.029 |
Neg logit contributions | |
owitz | -0.047 |
illance | -0.041 |
chio | -0.041 |
edi | -0.039 |
oulos | -0.039 |
Token | Ur |
Token ID | 8799 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
owitz | +1.371 |
illance | +1.189 |
chio | +1.180 |
oulos | +1.127 |
edi | +1.126 |
Neg logit contributions | |
anmar | -1.209 |
mil | -1.153 |
reluct | -1.116 |
vg | -1.091 |
fabrication | -1.088 |
Token | mia |
Token ID | 20730 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
anmar | +1.235 |
mil | +1.193 |
hub | +1.112 |
fabrication | +1.099 |
vg | +1.097 |
Neg logit contributions | |
owitz | -1.447 |
illance | -1.282 |
chio | -1.248 |
oulos | -1.197 |
edi | -1.197 |