Token | . |
Token ID | 13 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
sidx | +6.274 |
Norm | +5.869 |
untarily | +4.713 |
itals | +4.587 |
warmed | +4.535 |
Neg logit contributions | |
hyde | -8.602 |
leigh | -8.089 |
appings | -7.719 |
zinski | -7.638 |
pen | -7.570 |
Token | You |
Token ID | 921 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
sidx | +0.697 |
Norm | +0.624 |
untarily | +0.566 |
warmed | +0.537 |
itals | +0.530 |
Neg logit contributions | |
leigh | -0.674 |
hyde | -0.669 |
zinski | -0.627 |
pen | -0.624 |
bane | -0.619 |
Token | can |
Token ID | 460 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
sidx | +2.799 |
Norm | +2.545 |
untarily | +2.255 |
warmed | +2.176 |
caffe | +2.133 |
Neg logit contributions | |
hyde | -2.855 |
leigh | -2.807 |
zinski | -2.622 |
bane | -2.603 |
pen | -2.592 |
Token | read |
Token ID | 1100 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
sidx | +0.464 |
Norm | +0.402 |
untarily | +0.355 |
warmed | +0.331 |
itals | +0.325 |
Neg logit contributions | |
leigh | -0.673 |
hyde | -0.669 |
zinski | -0.635 |
pen | -0.633 |
bane | -0.628 |
Token | our |
Token ID | 674 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
sidx | +3.613 |
Norm | +3.339 |
untarily | +3.020 |
warmed | +2.866 |
itals | +2.844 |
Neg logit contributions | |
hyde | -2.997 |
leigh | -2.940 |
zinski | -2.741 |
bane | -2.726 |
pen | -2.716 |
Token | Privacy |
Token ID | 16777 |
Feature activation | +2.55e+01 |
Pos logit contributions | |
sidx | +7.621 |
Norm | +7.456 |
untarily | +6.295 |
ンジ | +5.834 |
warmed | +5.698 |
Neg logit contributions | |
hyde | -9.597 |
leigh | -8.879 |
zinski | -8.429 |
appings | -8.362 |
bane | -8.244 |
Token | Policy |
Token ID | 7820 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
Norm | +10.933 |
sidx | +7.759 |
Prism | +7.706 |
Class | +7.159 |
Type | +7.045 |
Neg logit contributions | |
hyde | -21.936 |
leigh | -20.001 |
appings | -19.585 |
iamond | -19.139 |
amina | -18.840 |
Token | here |
Token ID | 994 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
sidx | +5.909 |
Norm | +5.583 |
untarily | +4.581 |
warmed | +4.485 |
itals | +4.175 |
Neg logit contributions | |
hyde | -10.029 |
leigh | -9.688 |
zinski | -9.405 |
bane | -9.169 |
appings | -9.011 |
Token | . |
Token ID | 13 |
Feature activation | +6.87e+00 |
Pos logit contributions | |
sidx | +2.191 |
Norm | +1.985 |
untarily | +1.777 |
warmed | +1.691 |
itals | +1.670 |
Neg logit contributions | |
hyde | -2.040 |
leigh | -2.022 |
zinski | -1.883 |
pen | -1.867 |
bane | -1.859 |
Token | Sign |
Token ID | 5865 |
Feature activation | +7.30e+00 |
Pos logit contributions | |
sidx | +3.542 |
Norm | +3.121 |
untarily | +2.487 |
warmed | +2.309 |
caffe | +2.216 |
Neg logit contributions | |
hyde | -6.631 |
leigh | -6.555 |
appings | -6.154 |
zinski | -6.141 |
bane | -6.054 |
Token | up |
Token ID | 510 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
sidx | +5.740 |
Norm | +5.310 |
untarily | +4.759 |
warmed | +4.623 |
caffe | +4.545 |
Neg logit contributions | |
leigh | -4.876 |
hyde | -4.876 |
zinski | -4.413 |
appings | -4.286 |
bane | -4.279 |
Token | central |
Token ID | 4318 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
leigh | +1.014 |
hyde | +1.003 |
pen | +0.934 |
zinski | +0.931 |
Drew | +0.925 |
Neg logit contributions | |
sidx | -1.373 |
Norm | -1.226 |
untarily | -1.134 |
warmed | -1.075 |
itals | -1.067 |
Token | to |
Token ID | 284 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
leigh | +3.641 |
hyde | +3.561 |
pen | +3.425 |
zinski | +3.404 |
Drew | +3.388 |
Neg logit contributions | |
sidx | -5.531 |
Norm | -4.954 |
untarily | -4.598 |
warmed | -4.475 |
streng | -4.355 |
Token | our |
Token ID | 674 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
sidx | +3.326 |
Norm | +3.078 |
untarily | +2.786 |
streng | +2.677 |
warmed | +2.651 |
Neg logit contributions | |
leigh | -2.767 |
hyde | -2.751 |
zinski | -2.562 |
bane | -2.547 |
pen | -2.515 |
Token | nation |
Token ID | 3277 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
sidx | +1.363 |
Norm | +1.234 |
untarily | +1.110 |
warmed | +1.059 |
streng | +1.048 |
Neg logit contributions | |
hyde | -1.349 |
leigh | -1.347 |
zinski | -1.256 |
pen | -1.244 |
bane | -1.241 |
Token | since |
Token ID | 1201 |
Feature activation | +2.16e+01 |
Pos logit contributions | |
sidx | +1.551 |
Norm | +1.405 |
untarily | +1.290 |
warmed | +1.229 |
itals | +1.216 |
Neg logit contributions | |
leigh | -1.304 |
hyde | -1.291 |
zinski | -1.206 |
pen | -1.195 |
bane | -1.189 |
Token | its |
Token ID | 663 |
Feature activation | +2.33e+01 |
Pos logit contributions | |
Norm | +12.492 |
sidx | +11.379 |
untarily | +10.445 |
warmed | +10.005 |
itals | +9.824 |
Neg logit contributions | |
hyde | -14.448 |
leigh | -13.278 |
wordpress | -12.897 |
bane | -12.524 |
zinski | -12.421 |
Token | inception |
Token ID | 30839 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Norm | +11.453 |
sidx | +10.434 |
caffe | +8.687 |
untarily | +8.643 |
warmed | +8.565 |
Neg logit contributions | |
hyde | -17.445 |
leigh | -16.212 |
bane | -15.059 |
appings | -14.938 |
wordpress | -14.904 |
Token | . |
Token ID | 13 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
sidx | +1.815 |
Norm | +1.634 |
untarily | +1.493 |
warmed | +1.420 |
itals | +1.400 |
Neg logit contributions | |
leigh | -1.650 |
hyde | -1.635 |
zinski | -1.525 |
pen | -1.512 |
bane | -1.508 |
Token | � |
Token ID | 447 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
sidx | +3.917 |
Norm | +3.710 |
untarily | +3.245 |
warmed | +3.123 |
itals | +3.112 |
Neg logit contributions | |
leigh | -3.277 |
hyde | -3.255 |
zinski | -3.004 |
appings | -2.996 |
bane | -2.975 |
Token | � |
Token ID | 251 |
Feature activation | +9.45e+00 |
Pos logit contributions | |
sidx | +2.301 |
Norm | +2.110 |
untarily | +1.924 |
warmed | +1.831 |
itals | +1.806 |
Neg logit contributions | |
leigh | -1.962 |
hyde | -1.928 |
zinski | -1.815 |
pen | -1.795 |
bane | -1.778 |
Token |
|
Token ID | 198 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
sidx | +6.088 |
Norm | +5.925 |
untarily | +4.882 |
itals | +4.658 |
warmed | +4.653 |
Neg logit contributions | |
hyde | -7.101 |
leigh | -7.024 |
appings | -6.669 |
bane | -6.621 |
zinski | -6.532 |
Token | been |
Token ID | 587 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
sidx | +0.665 |
Norm | +0.590 |
untarily | +0.530 |
warmed | +0.501 |
streng | +0.492 |
Neg logit contributions | |
leigh | -0.801 |
hyde | -0.793 |
zinski | -0.751 |
pen | -0.746 |
bane | -0.742 |
Token | central |
Token ID | 4318 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
leigh | +1.014 |
hyde | +1.003 |
pen | +0.934 |
zinski | +0.931 |
Drew | +0.925 |
Neg logit contributions | |
sidx | -1.373 |
Norm | -1.226 |
untarily | -1.134 |
warmed | -1.075 |
itals | -1.067 |
Token | to |
Token ID | 284 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
leigh | +3.641 |
hyde | +3.561 |
pen | +3.425 |
zinski | +3.404 |
Drew | +3.388 |
Neg logit contributions | |
sidx | -5.531 |
Norm | -4.954 |
untarily | -4.598 |
warmed | -4.475 |
streng | -4.355 |
Token | our |
Token ID | 674 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
sidx | +3.326 |
Norm | +3.078 |
untarily | +2.786 |
streng | +2.677 |
warmed | +2.651 |
Neg logit contributions | |
leigh | -2.767 |
hyde | -2.751 |
zinski | -2.562 |
bane | -2.547 |
pen | -2.515 |
Token | nation |
Token ID | 3277 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
sidx | +1.363 |
Norm | +1.234 |
untarily | +1.110 |
warmed | +1.059 |
streng | +1.048 |
Neg logit contributions | |
hyde | -1.349 |
leigh | -1.347 |
zinski | -1.256 |
pen | -1.244 |
bane | -1.241 |
Token | since |
Token ID | 1201 |
Feature activation | +2.16e+01 |
Pos logit contributions | |
sidx | +1.551 |
Norm | +1.405 |
untarily | +1.290 |
warmed | +1.229 |
itals | +1.216 |
Neg logit contributions | |
leigh | -1.304 |
hyde | -1.291 |
zinski | -1.206 |
pen | -1.195 |
bane | -1.189 |
Token | its |
Token ID | 663 |
Feature activation | +2.33e+01 |
Pos logit contributions | |
Norm | +12.492 |
sidx | +11.379 |
untarily | +10.445 |
warmed | +10.005 |
itals | +9.824 |
Neg logit contributions | |
hyde | -14.448 |
leigh | -13.278 |
wordpress | -12.897 |
bane | -12.524 |
zinski | -12.421 |
Token | inception |
Token ID | 30839 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Norm | +11.453 |
sidx | +10.434 |
caffe | +8.687 |
untarily | +8.643 |
warmed | +8.565 |
Neg logit contributions | |
hyde | -17.445 |
leigh | -16.212 |
bane | -15.059 |
appings | -14.938 |
wordpress | -14.904 |
Token | . |
Token ID | 13 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
sidx | +1.815 |
Norm | +1.634 |
untarily | +1.493 |
warmed | +1.420 |
itals | +1.400 |
Neg logit contributions | |
leigh | -1.650 |
hyde | -1.635 |
zinski | -1.525 |
pen | -1.512 |
bane | -1.508 |
Token | � |
Token ID | 447 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
sidx | +3.917 |
Norm | +3.710 |
untarily | +3.245 |
warmed | +3.123 |
itals | +3.112 |
Neg logit contributions | |
leigh | -3.277 |
hyde | -3.255 |
zinski | -3.004 |
appings | -2.996 |
bane | -2.975 |
Token | � |
Token ID | 251 |
Feature activation | +9.45e+00 |
Pos logit contributions | |
sidx | +2.301 |
Norm | +2.110 |
untarily | +1.924 |
warmed | +1.831 |
itals | +1.806 |
Neg logit contributions | |
leigh | -1.962 |
hyde | -1.928 |
zinski | -1.815 |
pen | -1.795 |
bane | -1.778 |
Token | . |
Token ID | 13 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
leigh | +0.991 |
hyde | +0.978 |
pen | +0.915 |
zinski | +0.914 |
Drew | +0.906 |
Neg logit contributions | |
sidx | -1.220 |
Norm | -1.091 |
untarily | -1.006 |
warmed | -0.952 |
streng | -0.950 |
Token | The |
Token ID | 383 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
leigh | +1.985 |
hyde | +1.953 |
Drew | +1.864 |
zinski | +1.850 |
pen | +1.848 |
Neg logit contributions | |
sidx | -2.446 |
Norm | -2.135 |
untarily | -2.016 |
streng | -1.944 |
warmed | -1.924 |
Token | insurance |
Token ID | 5096 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
leigh | +0.346 |
hyde | +0.343 |
zinski | +0.321 |
pen | +0.320 |
Drew | +0.317 |
Neg logit contributions | |
sidx | -0.404 |
Norm | -0.363 |
untarily | -0.332 |
warmed | -0.316 |
streng | -0.313 |
Token | market |
Token ID | 1910 |
Feature activation | +6.04e+00 |
Pos logit contributions | |
leigh | +2.573 |
hyde | +2.516 |
pen | +2.395 |
Drew | +2.378 |
zinski | +2.370 |
Neg logit contributions | |
sidx | -2.976 |
Norm | -2.598 |
untarily | -2.404 |
streng | -2.280 |
warmed | -2.262 |
Token | has |
Token ID | 468 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
sidx | +4.303 |
Norm | +4.007 |
untarily | +3.577 |
warmed | +3.574 |
itals | +3.496 |
Neg logit contributions | |
leigh | -4.315 |
hyde | -4.300 |
bane | -4.020 |
appings | -4.011 |
zinski | -3.972 |
Token | indeed |
Token ID | 5600 |
Feature activation | +2.11e+01 |
Pos logit contributions | |
sidx | +9.206 |
Norm | +9.109 |
warmed | +8.792 |
untarily | +8.197 |
itals | +7.851 |
Neg logit contributions | |
hyde | -10.388 |
leigh | -10.378 |
appings | -9.790 |
zinski | -9.770 |
bane | -9.620 |
Token | stabilized |
Token ID | 44945 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
warmed | +11.233 |
Norm | +11.042 |
sidx | +10.754 |
untarily | +9.927 |
caffe | +9.633 |
Neg logit contributions | |
hyde | -13.812 |
leigh | -13.568 |
appings | -13.203 |
zinski | -13.126 |
bane | -12.629 |
Token | … |
Token ID | 3926 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
sidx | +0.845 |
Norm | +0.760 |
untarily | +0.693 |
warmed | +0.661 |
itals | +0.652 |
Neg logit contributions | |
leigh | -0.761 |
hyde | -0.753 |
zinski | -0.706 |
pen | -0.702 |
bane | -0.696 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
sidx | +1.275 |
Norm | +1.154 |
untarily | +1.049 |
warmed | +1.004 |
itals | +0.991 |
Neg logit contributions | |
leigh | -1.133 |
hyde | -1.122 |
zinski | -1.053 |
pen | -1.043 |
bane | -1.038 |
Token | same |
Token ID | 976 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
leigh | +0.764 |
hyde | +0.756 |
zinski | +0.708 |
pen | +0.706 |
Drew | +0.701 |
Neg logit contributions | |
sidx | -0.897 |
Norm | -0.803 |
untarily | -0.737 |
warmed | -0.700 |
streng | -0.694 |
Token | way |
Token ID | 835 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
leigh | +0.487 |
hyde | +0.482 |
zinski | +0.452 |
pen | +0.450 |
Drew | +0.447 |
Neg logit contributions | |
sidx | -0.551 |
Norm | -0.491 |
untarily | -0.450 |
warmed | -0.427 |
streng | -0.423 |
Token | the |
Token ID | 262 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
leigh | +0.106 |
hyde | +0.105 |
zinski | +0.098 |
pen | +0.097 |
bane | +0.096 |
Neg logit contributions | |
sidx | -0.134 |
Norm | -0.121 |
untarily | -0.111 |
warmed | -0.106 |
streng | -0.105 |
Token | DNC |
Token ID | 17824 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
sidx | +2.292 |
Norm | +2.077 |
untarily | +1.839 |
warmed | +1.760 |
itals | +1.735 |
Neg logit contributions | |
hyde | -2.381 |
leigh | -2.326 |
bane | -2.206 |
pen | -2.189 |
zinski | -2.157 |
Token | leak |
Token ID | 13044 |
Feature activation | +8.49e+00 |
Pos logit contributions | |
sidx | +7.257 |
Norm | +6.911 |
warmed | +5.979 |
itals | +5.848 |
caffe | +5.842 |
Neg logit contributions | |
hyde | -6.923 |
leigh | -6.760 |
bane | -6.574 |
appings | -6.203 |
pen | -6.180 |
Token | isn |
Token ID | 2125 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
sidx | +5.807 |
Norm | +5.351 |
warmed | +4.681 |
caffe | +4.434 |
untarily | +4.425 |
Neg logit contributions | |
hyde | -6.340 |
leigh | -6.227 |
appings | -5.813 |
pen | -5.791 |
zinski | -5.785 |
Token | 't |
Token ID | 470 |
Feature activation | +9.89e+00 |
Pos logit contributions | |
leigh | +1.428 |
hyde | +1.367 |
zinski | +1.300 |
pen | +1.299 |
Drew | +1.282 |
Neg logit contributions | |
sidx | -2.544 |
Norm | -2.281 |
streng | -2.164 |
untarily | -2.156 |
warmed | -2.067 |
Token | a |
Token ID | 257 |
Feature activation | +2.08e+01 |
Pos logit contributions | |
sidx | +6.862 |
Norm | +6.638 |
warmed | +5.932 |
caffe | +5.628 |
streng | +5.582 |
Neg logit contributions | |
hyde | -7.059 |
leigh | -6.924 |
appings | -6.402 |
zinski | -6.284 |
bane | -6.255 |
Token | ' |
Token ID | 705 |
Feature activation | +2.07e+01 |
Pos logit contributions | |
sidx | +11.547 |
Norm | +11.459 |
warmed | +10.350 |
caffe | +10.032 |
stereotype | +9.601 |
Neg logit contributions | |
hyde | -14.317 |
leigh | -13.603 |
appings | -13.091 |
bane | -12.904 |
zinski | -12.674 |
Token | cons |
Token ID | 5936 |
Feature activation | +6.61e+00 |
Pos logit contributions | |
sidx | +9.475 |
Norm | +9.303 |
untarily | +8.115 |
warmed | +7.798 |
tar | +7.634 |
Neg logit contributions | |
hyde | -14.939 |
appings | -14.194 |
Drew | -14.114 |
LDL | -13.896 |
leigh | -13.810 |
Token | piracy |
Token ID | 8703 |
Feature activation | +1.85e+01 |
Pos logit contributions | |
sidx | +5.085 |
Norm | +4.560 |
untarily | +4.224 |
warmed | +4.010 |
itals | +3.906 |
Neg logit contributions | |
hyde | -4.577 |
leigh | -4.385 |
Drew | -4.127 |
zinski | -4.122 |
bane | -4.099 |
Token | theory |
Token ID | 4583 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
sidx | +8.065 |
Norm | +7.055 |
stereotype | +5.790 |
warmed | +5.722 |
caffe | +5.705 |
Neg logit contributions | |
hyde | -15.517 |
appings | -15.515 |
leigh | -15.499 |
pen | -14.921 |
zinski | -14.594 |
Token | ' |
Token ID | 6 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
sidx | +3.018 |
Norm | +2.649 |
untarily | +2.061 |
warmed | +2.029 |
itals | +1.917 |
Neg logit contributions | |
leigh | -6.590 |
hyde | -6.530 |
appings | -6.234 |
bane | -6.215 |
pen | -6.190 |
Token | DNC |
Token ID | 17824 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
sidx | +2.292 |
Norm | +2.077 |
untarily | +1.839 |
warmed | +1.760 |
itals | +1.735 |
Neg logit contributions | |
hyde | -2.381 |
leigh | -2.326 |
bane | -2.206 |
pen | -2.189 |
zinski | -2.157 |
Token | leak |
Token ID | 13044 |
Feature activation | +8.49e+00 |
Pos logit contributions | |
sidx | +7.257 |
Norm | +6.911 |
warmed | +5.979 |
itals | +5.848 |
caffe | +5.842 |
Neg logit contributions | |
hyde | -6.923 |
leigh | -6.760 |
bane | -6.574 |
appings | -6.203 |
pen | -6.180 |
Token | isn |
Token ID | 2125 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
sidx | +5.807 |
Norm | +5.351 |
warmed | +4.681 |
caffe | +4.434 |
untarily | +4.425 |
Neg logit contributions | |
hyde | -6.340 |
leigh | -6.227 |
appings | -5.813 |
pen | -5.791 |
zinski | -5.785 |
Token | 't |
Token ID | 470 |
Feature activation | +9.89e+00 |
Pos logit contributions | |
leigh | +1.428 |
hyde | +1.367 |
zinski | +1.300 |
pen | +1.299 |
Drew | +1.282 |
Neg logit contributions | |
sidx | -2.544 |
Norm | -2.281 |
streng | -2.164 |
untarily | -2.156 |
warmed | -2.067 |
Token | a |
Token ID | 257 |
Feature activation | +2.08e+01 |
Pos logit contributions | |
sidx | +6.862 |
Norm | +6.638 |
warmed | +5.932 |
caffe | +5.628 |
streng | +5.582 |
Neg logit contributions | |
hyde | -7.059 |
leigh | -6.924 |
appings | -6.402 |
zinski | -6.284 |
bane | -6.255 |
Token | ' |
Token ID | 705 |
Feature activation | +2.07e+01 |
Pos logit contributions | |
sidx | +11.547 |
Norm | +11.459 |
warmed | +10.350 |
caffe | +10.032 |
stereotype | +9.601 |
Neg logit contributions | |
hyde | -14.317 |
leigh | -13.603 |
appings | -13.091 |
bane | -12.904 |
zinski | -12.674 |
Token | cons |
Token ID | 5936 |
Feature activation | +6.61e+00 |
Pos logit contributions | |
sidx | +9.475 |
Norm | +9.303 |
untarily | +8.115 |
warmed | +7.798 |
tar | +7.634 |
Neg logit contributions | |
hyde | -14.939 |
appings | -14.194 |
Drew | -14.114 |
LDL | -13.896 |
leigh | -13.810 |
Token | piracy |
Token ID | 8703 |
Feature activation | +1.85e+01 |
Pos logit contributions | |
sidx | +5.085 |
Norm | +4.560 |
untarily | +4.224 |
warmed | +4.010 |
itals | +3.906 |
Neg logit contributions | |
hyde | -4.577 |
leigh | -4.385 |
Drew | -4.127 |
zinski | -4.122 |
bane | -4.099 |
Token | theory |
Token ID | 4583 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
sidx | +8.065 |
Norm | +7.055 |
stereotype | +5.790 |
warmed | +5.722 |
caffe | +5.705 |
Neg logit contributions | |
hyde | -15.517 |
appings | -15.515 |
leigh | -15.499 |
pen | -14.921 |
zinski | -14.594 |
Token | ' |
Token ID | 6 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
sidx | +3.018 |
Norm | +2.649 |
untarily | +2.061 |
warmed | +2.029 |
itals | +1.917 |
Neg logit contributions | |
leigh | -6.590 |
hyde | -6.530 |
appings | -6.234 |
bane | -6.215 |
pen | -6.190 |
Token | like |
Token ID | 588 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
sidx | +1.397 |
Norm | +1.266 |
untarily | +1.134 |
warmed | +1.095 |
itals | +1.074 |
Neg logit contributions | |
leigh | -1.295 |
hyde | -1.288 |
zinski | -1.200 |
pen | -1.199 |
bane | -1.194 |
Token | health |
Token ID | 1535 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
sidx | +2.516 |
Norm | +2.252 |
untarily | +2.033 |
warmed | +1.982 |
caffe | +1.973 |
Neg logit contributions | |
leigh | -2.330 |
hyde | -2.310 |
zinski | -2.169 |
bane | -2.144 |
pen | -2.135 |
Token | benefits |
Token ID | 4034 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
sidx | +2.511 |
Norm | +2.199 |
untarily | +1.918 |
itals | +1.871 |
warmed | +1.849 |
Neg logit contributions | |
hyde | -3.436 |
leigh | -3.415 |
zinski | -3.217 |
bane | -3.171 |
pen | -3.153 |
Token | ). |
Token ID | 737 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
leigh | +0.284 |
hyde | +0.281 |
zinski | +0.262 |
pen | +0.262 |
Drew | +0.258 |
Neg logit contributions | |
sidx | -0.360 |
Norm | -0.325 |
untarily | -0.299 |
warmed | -0.284 |
streng | -0.282 |
Token |
|
Token ID | 198 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
sidx | +2.937 |
Norm | +2.764 |
untarily | +2.370 |
caffe | +2.289 |
warmed | +2.284 |
Neg logit contributions | |
leigh | -2.975 |
hyde | -2.970 |
zinski | -2.775 |
pen | -2.775 |
appings | -2.758 |
Token |
|
Token ID | 198 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
leigh | +0.209 |
hyde | +0.206 |
zinski | +0.194 |
pen | +0.194 |
Drew | +0.192 |
Neg logit contributions | |
sidx | -0.241 |
Norm | -0.214 |
untarily | -0.197 |
streng | -0.189 |
warmed | -0.188 |
Token | No |
Token ID | 2949 |
Feature activation | +2.04e+01 |
Pos logit contributions | |
sidx | +4.170 |
Norm | +3.882 |
untarily | +3.513 |
warmed | +3.320 |
itals | +3.314 |
Neg logit contributions | |
hyde | -4.009 |
leigh | -3.941 |
zinski | -3.717 |
Drew | -3.704 |
appings | -3.674 |
Token | breakfast |
Token ID | 12607 |
Feature activation | +6.67e+00 |
Pos logit contributions | |
sidx | +12.643 |
Norm | +12.242 |
caffe | +11.440 |
untarily | +11.177 |
warmed | +10.997 |
Neg logit contributions | |
leigh | -11.912 |
hyde | -11.632 |
bane | -11.196 |
appings | -11.107 |
zinski | -10.846 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
sidx | +4.676 |
Norm | +4.348 |
warmed | +3.854 |
untarily | +3.805 |
caffe | +3.782 |
Neg logit contributions | |
leigh | -4.861 |
hyde | -4.847 |
bane | -4.494 |
zinski | -4.485 |
appings | -4.471 |
Token | lighter |
Token ID | 14871 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
sidx | +7.008 |
Norm | +6.736 |
warmed | +5.944 |
caffe | +5.930 |
untarily | +5.621 |
Neg logit contributions | |
hyde | -7.968 |
leigh | -7.850 |
zinski | -7.335 |
appings | -7.320 |
bane | -7.217 |
Token | lunch |
Token ID | 9965 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
sidx | +6.920 |
Norm | +6.299 |
caffe | +5.675 |
warmed | +5.653 |
untarily | +5.438 |
Neg logit contributions | |
hyde | -7.705 |
leigh | -7.527 |
bane | -7.092 |
appings | -7.066 |
zinski | -6.993 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
sidx | +2.351 |
Norm | +2.114 |
untarily | +1.881 |
warmed | +1.838 |
itals | +1.792 |
Neg logit contributions | |
leigh | -2.351 |
hyde | -2.329 |
zinski | -2.182 |
pen | -2.166 |
Drew | -2.145 |
Token | der |
Token ID | 1082 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
leigh | +0.947 |
hyde | +0.907 |
pen | +0.839 |
zinski | +0.835 |
Drew | +0.812 |
Neg logit contributions | |
sidx | -2.334 |
Norm | -2.143 |
untarily | -2.007 |
streng | -1.980 |
warmed | -1.952 |
Token | 's |
Token ID | 338 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
sidx | +4.656 |
Norm | +4.234 |
untarily | +3.821 |
warmed | +3.620 |
itals | +3.569 |
Neg logit contributions | |
leigh | -4.320 |
hyde | -4.320 |
pen | -4.013 |
zinski | -3.982 |
bane | -3.976 |
Token | season |
Token ID | 1622 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
sidx | +7.488 |
Norm | +7.233 |
untarily | +6.275 |
warmed | +6.030 |
itals | +5.973 |
Neg logit contributions | |
hyde | -8.198 |
leigh | -7.807 |
zinski | -7.509 |
appings | -7.442 |
bane | -7.269 |
Token | with |
Token ID | 351 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
sidx | +4.532 |
Norm | +4.163 |
untarily | +3.696 |
warmed | +3.503 |
streng | +3.435 |
Neg logit contributions | |
hyde | -4.536 |
leigh | -4.462 |
appings | -4.161 |
zinski | -4.160 |
pen | -4.135 |
Token | an |
Token ID | 281 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
sidx | +2.685 |
Norm | +2.464 |
untarily | +2.216 |
warmed | +2.126 |
itals | +2.088 |
Neg logit contributions | |
leigh | -2.455 |
hyde | -2.454 |
zinski | -2.292 |
bane | -2.262 |
pen | -2.258 |
Token | ACL |
Token ID | 17382 |
Feature activation | +1.94e+01 |
Pos logit contributions | |
sidx | +7.405 |
Norm | +6.790 |
untarily | +5.697 |
warmed | +5.503 |
caffe | +5.342 |
Neg logit contributions | |
leigh | -9.623 |
hyde | -9.619 |
zinski | -9.078 |
appings | -8.914 |
bane | -8.863 |
Token | sp |
Token ID | 599 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
sidx | +10.183 |
Norm | +9.939 |
untarily | +8.553 |
warmed | +8.281 |
streng | +8.227 |
Neg logit contributions | |
hyde | -13.826 |
leigh | -13.804 |
appings | -13.252 |
zinski | -13.001 |
bane | -12.651 |
Token | rain |
Token ID | 3201 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
sidx | +1.768 |
Norm | +1.591 |
untarily | +1.470 |
itals | +1.382 |
warmed | +1.377 |
Neg logit contributions | |
hyde | -1.614 |
leigh | -1.609 |
zinski | -1.500 |
pen | -1.486 |
bane | -1.478 |
Token | . |
Token ID | 13 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
sidx | +6.897 |
Norm | +6.484 |
untarily | +5.443 |
warmed | +5.317 |
itals | +5.164 |
Neg logit contributions | |
hyde | -7.849 |
leigh | -7.636 |
appings | -7.139 |
pen | -7.114 |
zinski | -7.082 |
Token | Brian |
Token ID | 8403 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
sidx | +1.654 |
Norm | +1.507 |
untarily | +1.355 |
warmed | +1.302 |
itals | +1.276 |
Neg logit contributions | |
leigh | -1.423 |
hyde | -1.420 |
zinski | -1.319 |
pen | -1.315 |
bane | -1.302 |
Token | Bab |
Token ID | 12400 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
sidx | +5.566 |
Norm | +5.245 |
warmed | +4.370 |
untarily | +4.303 |
caffe | +4.293 |
Neg logit contributions | |
leigh | -6.486 |
hyde | -6.457 |
pen | -6.209 |
zinski | -6.055 |
bane | -5.881 |
Token | carved |
Token ID | 23470 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
leigh | +2.584 |
hyde | +2.506 |
pen | +2.405 |
Drew | +2.396 |
zinski | +2.395 |
Neg logit contributions | |
sidx | -2.744 |
Norm | -2.355 |
untarily | -2.217 |
itals | -2.026 |
ンジ | -2.007 |
Token | in |
Token ID | 287 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
leigh | +4.378 |
hyde | +4.217 |
pen | +4.047 |
Drew | +4.042 |
bane | +4.000 |
Neg logit contributions | |
sidx | -5.979 |
Norm | -5.195 |
untarily | -4.880 |
itals | -4.666 |
pees | -4.603 |
Token | Palestinian |
Token ID | 8501 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
leigh | +0.588 |
hyde | +0.579 |
pen | +0.544 |
zinski | +0.542 |
Drew | +0.539 |
Neg logit contributions | |
sidx | -0.727 |
Norm | -0.649 |
untarily | -0.600 |
warmed | -0.568 |
streng | -0.565 |
Token | soil |
Token ID | 9260 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
leigh | +0.011 |
hyde | +0.011 |
zinski | +0.010 |
pen | +0.010 |
bane | +0.010 |
Neg logit contributions | |
sidx | -0.013 |
Norm | -0.011 |
untarily | -0.010 |
warmed | -0.010 |
streng | -0.010 |
Token | since |
Token ID | 1201 |
Feature activation | +1.79e+01 |
Pos logit contributions | |
leigh | +2.784 |
hyde | +2.725 |
pen | +2.573 |
zinski | +2.544 |
Drew | +2.542 |
Neg logit contributions | |
sidx | -3.674 |
Norm | -3.280 |
untarily | -3.046 |
itals | -2.867 |
streng | -2.866 |
Token | the |
Token ID | 262 |
Feature activation | +1.94e+01 |
Pos logit contributions | |
Norm | +11.143 |
sidx | +10.550 |
warmed | +9.292 |
untarily | +9.155 |
caffe | +8.875 |
Neg logit contributions | |
hyde | -12.487 |
leigh | -11.633 |
zinski | -10.728 |
appings | -10.583 |
bane | -10.560 |
Token | time |
Token ID | 640 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
Norm | +12.501 |
sidx | +11.527 |
warmed | +9.753 |
mono | +9.721 |
caffe | +9.695 |
Neg logit contributions | |
hyde | -13.223 |
leigh | -12.247 |
zinski | -10.953 |
appings | -10.879 |
amina | -10.873 |
Token | of |
Token ID | 286 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
sidx | +2.326 |
Norm | +2.126 |
untarily | +1.909 |
warmed | +1.826 |
itals | +1.796 |
Neg logit contributions | |
hyde | -2.080 |
leigh | -2.078 |
zinski | -1.921 |
pen | -1.898 |
bane | -1.890 |
Token | the |
Token ID | 262 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
Norm | +8.929 |
sidx | +8.881 |
untarily | +7.260 |
warmed | +7.006 |
caffe | +6.966 |
Neg logit contributions | |
hyde | -9.667 |
leigh | -9.450 |
zinski | -8.665 |
pen | -8.507 |
appings | -8.463 |
Token | Canaan |
Token ID | 47047 |
Feature activation | +7.44e+00 |
Pos logit contributions | |
Norm | +9.674 |
sidx | +9.306 |
untarily | +7.779 |
caffe | +7.665 |
warmed | +7.619 |
Neg logit contributions | |
hyde | -9.177 |
leigh | -8.860 |
pen | -7.933 |
zinski | -7.851 |
bane | -7.795 |
Token | ites |
Token ID | 2737 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
sidx | +5.662 |
Norm | +5.379 |
untarily | +4.692 |
itals | +4.608 |
warmed | +4.587 |
Neg logit contributions | |
hyde | -5.048 |
leigh | -5.042 |
zinski | -4.620 |
pen | -4.551 |
bane | -4.474 |
Token | ultimately |
Token ID | 6165 |
Feature activation | +7.77e+00 |
Pos logit contributions | |
sidx | +2.145 |
Norm | +1.964 |
untarily | +1.746 |
warmed | +1.701 |
itals | +1.664 |
Neg logit contributions | |
hyde | -1.861 |
leigh | -1.860 |
zinski | -1.743 |
pen | -1.716 |
bane | -1.701 |
Token | York |
Token ID | 1971 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
sidx | +5.787 |
Norm | +5.434 |
warmed | +4.646 |
untarily | +4.581 |
streng | +4.500 |
Neg logit contributions | |
hyde | -5.378 |
leigh | -5.291 |
zinski | -5.132 |
pen | -4.925 |
wordpress | -4.893 |
Token | was |
Token ID | 373 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
sidx | +0.439 |
Norm | +0.395 |
untarily | +0.361 |
warmed | +0.345 |
streng | +0.341 |
Neg logit contributions | |
leigh | -0.373 |
hyde | -0.370 |
zinski | -0.346 |
pen | -0.345 |
Drew | -0.341 |
Token | burned |
Token ID | 11544 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
leigh | +0.585 |
hyde | +0.577 |
pen | +0.538 |
zinski | +0.538 |
Drew | +0.533 |
Neg logit contributions | |
sidx | -0.752 |
Norm | -0.672 |
untarily | -0.622 |
warmed | -0.589 |
itals | -0.585 |
Token | to |
Token ID | 284 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
sidx | +1.249 |
Norm | +1.125 |
untarily | +1.026 |
warmed | +0.979 |
itals | +0.964 |
Neg logit contributions | |
leigh | -1.074 |
hyde | -1.071 |
zinski | -0.999 |
pen | -0.990 |
bane | -0.981 |
Token | the |
Token ID | 262 |
Feature activation | +1.94e+01 |
Pos logit contributions | |
sidx | +8.155 |
Norm | +7.537 |
untarily | +6.346 |
streng | +6.345 |
warmed | +6.278 |
Neg logit contributions | |
hyde | -8.653 |
leigh | -8.293 |
zinski | -8.111 |
wordpress | -8.000 |
appings | -7.934 |
Token | ground |
Token ID | 2323 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
Norm | +9.802 |
sidx | +9.396 |
mono | +7.458 |
warmed | +7.440 |
streng | +7.295 |
Neg logit contributions | |
hyde | -15.303 |
leigh | -14.532 |
zinski | -14.427 |
appings | -14.037 |
wordpress | -13.908 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
sidx | +2.788 |
Norm | +2.524 |
untarily | +2.256 |
warmed | +2.181 |
itals | +2.126 |
Neg logit contributions | |
hyde | -2.614 |
leigh | -2.601 |
zinski | -2.438 |
pen | -2.401 |
appings | -2.386 |
Token | the |
Token ID | 262 |
Feature activation | +7.78e+00 |
Pos logit contributions | |
Norm | +7.833 |
sidx | +7.714 |
warmed | +6.546 |
untarily | +6.406 |
streng | +6.302 |
Neg logit contributions | |
hyde | -7.280 |
zinski | -7.071 |
leigh | -6.976 |
appings | -6.675 |
pen | -6.673 |
Token | Norman |
Token ID | 19636 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
sidx | +5.824 |
Norm | +5.808 |
untarily | +4.815 |
warmed | +4.719 |
streng | +4.651 |
Neg logit contributions | |
hyde | -5.282 |
leigh | -5.217 |
zinski | -4.914 |
pen | -4.860 |
bane | -4.767 |
Token | garrison |
Token ID | 45416 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
sidx | +2.691 |
Norm | +2.512 |
untarily | +2.231 |
warmed | +2.148 |
streng | +2.132 |
Neg logit contributions | |
hyde | -2.300 |
leigh | -2.298 |
zinski | -2.147 |
pen | -2.135 |
bane | -2.088 |
Token | mistake |
Token ID | 7457 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
sidx | +0.551 |
Norm | +0.498 |
untarily | +0.453 |
warmed | +0.432 |
streng | +0.427 |
Neg logit contributions | |
leigh | -0.484 |
hyde | -0.483 |
zinski | -0.451 |
pen | -0.445 |
bane | -0.444 |
Token | . |
Token ID | 13 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
leigh | +0.980 |
hyde | +0.969 |
pen | +0.909 |
zinski | +0.905 |
Drew | +0.902 |
Neg logit contributions | |
sidx | -1.230 |
Norm | -1.089 |
untarily | -1.012 |
warmed | -0.958 |
streng | -0.957 |
Token | Hitchcock |
Token ID | 49817 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
sidx | +2.966 |
Norm | +2.805 |
untarily | +2.405 |
warmed | +2.292 |
itals | +2.266 |
Neg logit contributions | |
leigh | -2.966 |
hyde | -2.956 |
zinski | -2.759 |
pen | -2.729 |
appings | -2.724 |
Token | shot |
Token ID | 2823 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
sidx | +0.528 |
Norm | +0.475 |
untarily | +0.434 |
warmed | +0.415 |
streng | +0.408 |
Neg logit contributions | |
leigh | -0.455 |
hyde | -0.451 |
zinski | -0.422 |
pen | -0.420 |
bane | -0.416 |
Token | everything |
Token ID | 2279 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
sidx | +5.124 |
Norm | +4.881 |
untarily | +4.346 |
warmed | +4.039 |
itals | +4.002 |
Neg logit contributions | |
leigh | -5.092 |
hyde | -4.992 |
zinski | -4.868 |
bane | -4.660 |
appings | -4.618 |
Token | on |
Token ID | 319 |
Feature activation | +1.93e+01 |
Pos logit contributions | |
sidx | +3.540 |
Norm | +3.293 |
untarily | +2.938 |
warmed | +2.785 |
itals | +2.707 |
Neg logit contributions | |
leigh | -3.439 |
hyde | -3.400 |
zinski | -3.270 |
pen | -3.169 |
appings | -3.168 |
Token | as |
Token ID | 355 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
Norm | +12.425 |
sidx | +11.897 |
untarily | +10.755 |
mono | +10.391 |
warmed | +9.656 |
Neg logit contributions | |
leigh | -12.427 |
hyde | -12.003 |
zinski | -11.975 |
bane | -11.527 |
appings | -11.401 |
Token | ho |
Token ID | 8873 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
sidx | +2.997 |
Norm | +2.760 |
untarily | +2.513 |
warmed | +2.400 |
itals | +2.356 |
Neg logit contributions | |
leigh | -2.363 |
hyde | -2.350 |
zinski | -2.189 |
bane | -2.160 |
Drew | -2.138 |
Token | est |
Token ID | 395 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
sidx | +0.057 |
Norm | +0.051 |
untarily | +0.047 |
warmed | +0.044 |
streng | +0.044 |
Neg logit contributions | |
leigh | -0.047 |
hyde | -0.046 |
zinski | -0.043 |
pen | -0.043 |
Drew | -0.043 |
Token | ring |
Token ID | 1806 |
Feature activation | +8.81e+00 |
Pos logit contributions | |
sidx | +1.354 |
Norm | +1.221 |
untarily | +1.115 |
warmed | +1.062 |
itals | +1.049 |
Neg logit contributions | |
leigh | -1.162 |
hyde | -1.150 |
zinski | -1.081 |
pen | -1.066 |
bane | -1.063 |
Token | budget |
Token ID | 4466 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
sidx | +6.580 |
Norm | +6.221 |
untarily | +5.556 |
warmed | +5.190 |
itals | +5.117 |
Neg logit contributions | |
leigh | -5.829 |
hyde | -5.606 |
zinski | -5.544 |
bane | -5.428 |
appings | -5.372 |
Token | identified |
Token ID | 5174 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
leigh | +3.352 |
hyde | +3.197 |
Drew | +3.094 |
pen | +3.070 |
bane | +2.991 |
Neg logit contributions | |
sidx | -4.532 |
Norm | -3.965 |
untarily | -3.731 |
itals | -3.509 |
ンジ | -3.494 |
Token | as |
Token ID | 355 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
leigh | +3.926 |
hyde | +3.727 |
Drew | +3.585 |
pen | +3.552 |
zinski | +3.543 |
Neg logit contributions | |
sidx | -5.635 |
Norm | -5.009 |
untarily | -4.633 |
streng | -4.517 |
warmed | -4.508 |
Token | � |
Token ID | 564 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
leigh | +3.109 |
hyde | +3.037 |
Drew | +2.916 |
pen | +2.880 |
zinski | +2.830 |
Neg logit contributions | |
sidx | -4.293 |
Norm | -3.748 |
untarily | -3.571 |
streng | -3.391 |
warmed | -3.365 |
Token | � |
Token ID | 250 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
sidx | +2.105 |
Norm | +1.941 |
untarily | +1.810 |
warmed | +1.730 |
itals | +1.719 |
Neg logit contributions | |
leigh | -1.300 |
hyde | -1.268 |
zinski | -1.181 |
pen | -1.163 |
bane | -1.151 |
Token | Gaza |
Token ID | 48790 |
Feature activation | +7.59e+00 |
Pos logit contributions | |
sidx | +0.475 |
Norm | +0.427 |
untarily | +0.391 |
warmed | +0.372 |
itals | +0.368 |
Neg logit contributions | |
leigh | -0.410 |
hyde | -0.406 |
zinski | -0.380 |
pen | -0.378 |
Drew | -0.375 |
Token | Under |
Token ID | 4698 |
Feature activation | +1.92e+01 |
Pos logit contributions | |
sidx | +6.044 |
Norm | +5.576 |
untarily | +5.026 |
itals | +4.883 |
warmed | +4.873 |
Neg logit contributions | |
hyde | -4.707 |
leigh | -4.705 |
zinski | -4.467 |
pen | -4.416 |
appings | -4.363 |
Token | Attack |
Token ID | 8307 |
Feature activation | +7.67e+00 |
Pos logit contributions | |
Norm | +11.457 |
sidx | +10.747 |
untarily | +9.856 |
itals | +9.341 |
Class | +9.086 |
Neg logit contributions | |
hyde | -12.373 |
leigh | -12.086 |
zinski | -11.409 |
appings | -11.086 |
wordpress | -10.645 |
Token | Today |
Token ID | 6288 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
sidx | +5.928 |
Norm | +5.493 |
untarily | +4.926 |
warmed | +4.807 |
itals | +4.795 |
Neg logit contributions | |
leigh | -4.928 |
hyde | -4.916 |
zinski | -4.590 |
appings | -4.584 |
pen | -4.540 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
sidx | +1.011 |
Norm | +0.917 |
untarily | +0.841 |
warmed | +0.807 |
itals | +0.798 |
Neg logit contributions | |
leigh | -0.768 |
hyde | -0.760 |
zinski | -0.709 |
pen | -0.705 |
bane | -0.699 |
Token | � |
Token ID | 447 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
sidx | +0.197 |
Norm | +0.176 |
untarily | +0.161 |
warmed | +0.153 |
itals | +0.151 |
Neg logit contributions | |
leigh | -0.178 |
hyde | -0.177 |
zinski | -0.165 |
pen | -0.165 |
bane | -0.163 |
Token | � |
Token ID | 251 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
leigh | +0.255 |
hyde | +0.252 |
zinski | +0.231 |
pen | +0.230 |
Drew | +0.227 |
Neg logit contributions | |
sidx | -0.452 |
Norm | -0.413 |
untarily | -0.384 |
warmed | -0.369 |
streng | -0.366 |
Token | ap |
Token ID | 2471 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
sidx | +3.189 |
Norm | +2.865 |
untarily | +2.553 |
warmed | +2.470 |
caffe | +2.468 |
Neg logit contributions | |
leigh | -3.131 |
hyde | -3.044 |
zinski | -2.895 |
pen | -2.844 |
Drew | -2.838 |
Token | = |
Token ID | 796 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
leigh | +0.076 |
hyde | +0.075 |
zinski | +0.070 |
pen | +0.070 |
bane | +0.069 |
Neg logit contributions | |
sidx | -0.111 |
Norm | -0.101 |
untarily | -0.093 |
streng | -0.090 |
warmed | -0.089 |
Token | arg |
Token ID | 1822 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
sidx | +6.201 |
Norm | +5.485 |
caffe | +4.713 |
untarily | +4.701 |
warmed | +4.638 |
Neg logit contributions | |
leigh | -8.129 |
hyde | -8.067 |
zinski | -7.558 |
Drew | -7.386 |
bane | -7.292 |
Token | parse |
Token ID | 29572 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
sidx | +8.158 |
Norm | +7.029 |
untarily | +6.901 |
pees | +6.392 |
warmed | +6.264 |
Neg logit contributions | |
hyde | -8.251 |
leigh | -8.004 |
Drew | -7.869 |
LDL | -7.539 |
zinski | -7.412 |
Token | . |
Token ID | 13 |
Feature activation | +8.54e+00 |
Pos logit contributions | |
sidx | +2.097 |
Norm | +1.909 |
untarily | +1.698 |
warmed | +1.619 |
itals | +1.592 |
Neg logit contributions | |
hyde | -2.030 |
leigh | -2.020 |
zinski | -1.870 |
pen | -1.866 |
appings | -1.851 |
Token | Arg |
Token ID | 28100 |
Feature activation | +1.92e+01 |
Pos logit contributions | |
sidx | +6.628 |
Norm | +6.180 |
untarily | +5.476 |
warmed | +5.153 |
ンジ | +5.138 |
Neg logit contributions | |
hyde | -5.670 |
leigh | -5.453 |
zinski | -5.047 |
Drew | -5.011 |
appings | -4.931 |
Token | ument |
Token ID | 1713 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
sidx | +8.971 |
Norm | +8.309 |
untarily | +7.895 |
itals | +7.020 |
iment | +6.754 |
Neg logit contributions | |
hyde | -15.041 |
leigh | -14.795 |
Drew | -14.383 |
zinski | -14.192 |
births | -14.022 |
Token | Parser |
Token ID | 46677 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
sidx | +7.537 |
Norm | +6.997 |
untarily | +5.658 |
ERC | +5.650 |
Tar | +5.234 |
Neg logit contributions | |
hyde | -12.953 |
leigh | -12.069 |
bane | -11.694 |
pen | -11.649 |
appings | -11.606 |
Token | () |
Token ID | 3419 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
sidx | +4.520 |
Norm | +4.150 |
untarily | +3.669 |
warmed | +3.513 |
itals | +3.473 |
Neg logit contributions | |
hyde | -3.962 |
leigh | -3.815 |
pen | -3.595 |
bane | -3.583 |
zinski | -3.576 |
Token | ap |
Token ID | 2471 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
hyde | +1.279 |
leigh | +1.276 |
pen | +1.204 |
zinski | +1.184 |
bane | +1.182 |
Neg logit contributions | |
sidx | -1.789 |
Norm | -1.609 |
untarily | -1.509 |
streng | -1.444 |
itals | -1.426 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
leigh | +1.276 |
hyde | +1.252 |
zinski | +1.187 |
pen | +1.182 |
Drew | +1.171 |
Neg logit contributions | |
sidx | -1.733 |
Norm | -1.551 |
untarily | -1.447 |
streng | -1.443 |
warmed | -1.384 |
Token | s |
Token ID | 82 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
leigh | +5.064 |
hyde | +4.869 |
Drew | +4.787 |
pen | +4.739 |
zinski | +4.568 |
Neg logit contributions | |
sidx | -7.711 |
Norm | -6.675 |
untarily | -6.416 |
streng | -6.312 |
ンジ | -6.175 |
Token | third |
Token ID | 2368 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
sidx | +2.691 |
Norm | +2.458 |
untarily | +2.209 |
warmed | +2.126 |
itals | +2.084 |
Neg logit contributions | |
hyde | -2.320 |
leigh | -2.301 |
zinski | -2.144 |
pen | -2.122 |
appings | -2.104 |
Token | party |
Token ID | 2151 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
sidx | +3.219 |
Norm | +2.856 |
untarily | +2.497 |
warmed | +2.395 |
caffe | +2.340 |
Neg logit contributions | |
hyde | -3.942 |
leigh | -3.896 |
zinski | -3.748 |
pen | -3.627 |
appings | -3.622 |
Token | content |
Token ID | 2695 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
sidx | +1.039 |
Norm | +0.939 |
untarily | +0.853 |
warmed | +0.817 |
itals | +0.802 |
Neg logit contributions | |
hyde | -0.902 |
leigh | -0.901 |
zinski | -0.838 |
pen | -0.833 |
bane | -0.825 |
Token | with |
Token ID | 351 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
sidx | +3.460 |
Norm | +3.130 |
untarily | +2.807 |
warmed | +2.718 |
itals | +2.638 |
Neg logit contributions | |
hyde | -3.398 |
leigh | -3.316 |
zinski | -3.138 |
pen | -3.084 |
appings | -3.072 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e+01 |
Pos logit contributions | |
sidx | +9.742 |
Norm | +9.450 |
untarily | +8.087 |
warmed | +7.910 |
caffe | +7.833 |
Neg logit contributions | |
hyde | -10.295 |
leigh | -9.612 |
zinski | -9.409 |
appings | -9.055 |
pen | -9.011 |
Token | permission |
Token ID | 7170 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
sidx | +11.959 |
Norm | +11.576 |
untarily | +9.800 |
caffe | +9.746 |
warmed | +9.725 |
Neg logit contributions | |
hyde | -12.617 |
leigh | -11.664 |
appings | -11.115 |
pen | -11.061 |
bane | -10.935 |
Token | of |
Token ID | 286 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
sidx | +7.256 |
Norm | +6.531 |
untarily | +5.573 |
warmed | +5.388 |
caffe | +5.252 |
Neg logit contributions | |
hyde | -8.072 |
leigh | -7.942 |
zinski | -7.628 |
appings | -7.587 |
bane | -7.553 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e+01 |
Pos logit contributions | |
sidx | +8.641 |
Norm | +8.492 |
untarily | +7.051 |
itals | +6.749 |
warmed | +6.740 |
Neg logit contributions | |
hyde | -8.782 |
leigh | -8.267 |
zinski | -8.099 |
bane | -8.073 |
appings | -8.023 |
Token | publisher |
Token ID | 9991 |
Feature activation | +9.77e+00 |
Pos logit contributions | |
sidx | +9.247 |
Norm | +8.778 |
untarily | +7.497 |
warmed | +7.197 |
caffe | +7.167 |
Neg logit contributions | |
hyde | -9.920 |
leigh | -9.019 |
bane | -8.974 |
appings | -8.767 |
zinski | -8.726 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
sidx | +6.606 |
Norm | +6.055 |
untarily | +5.214 |
warmed | +5.015 |
itals | +4.932 |
Neg logit contributions | |
hyde | -7.255 |
leigh | -7.023 |
zinski | -6.888 |
appings | -6.747 |
bane | -6.685 |
Token | writer |
Token ID | 6260 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
sidx | +5.419 |
Norm | +4.929 |
untarily | +4.404 |
warmed | +4.377 |
itals | +4.241 |
Neg logit contributions | |
leigh | -4.940 |
hyde | -4.919 |
zinski | -4.607 |
pen | -4.576 |
bane | -4.560 |
Token | Mary |
Token ID | 5335 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
sidx | +0.109 |
Norm | +0.099 |
untarily | +0.090 |
warmed | +0.086 |
streng | +0.085 |
Neg logit contributions | |
leigh | -0.087 |
hyde | -0.087 |
zinski | -0.081 |
pen | -0.080 |
bane | -0.080 |
Token | Elizabeth |
Token ID | 10674 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
leigh | +2.085 |
hyde | +1.989 |
Drew | +1.909 |
pen | +1.901 |
zinski | +1.879 |
Neg logit contributions | |
sidx | -2.534 |
Norm | -2.184 |
untarily | -2.057 |
streng | -1.972 |
warmed | -1.954 |
Token | Williams |
Token ID | 6484 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
leigh | +0.652 |
hyde | +0.646 |
zinski | +0.604 |
pen | +0.602 |
Drew | +0.597 |
Neg logit contributions | |
sidx | -0.747 |
Norm | -0.669 |
untarily | -0.613 |
warmed | -0.583 |
streng | -0.577 |
Token | did |
Token ID | 750 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
sidx | +2.417 |
Norm | +2.199 |
untarily | +1.990 |
warmed | +1.935 |
itals | +1.892 |
Neg logit contributions | |
leigh | -2.004 |
hyde | -1.998 |
zinski | -1.863 |
pen | -1.848 |
bane | -1.835 |
Token | tear |
Token ID | 11626 |
Feature activation | +1.90e+01 |
Pos logit contributions | |
sidx | +1.982 |
Norm | +1.793 |
untarily | +1.621 |
warmed | +1.543 |
streng | +1.522 |
Neg logit contributions | |
leigh | -1.843 |
hyde | -1.824 |
zinski | -1.715 |
pen | -1.696 |
bane | -1.691 |
Token | into |
Token ID | 656 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
Norm | +11.106 |
sidx | +10.777 |
untarily | +9.711 |
warmed | +9.212 |
mono | +8.752 |
Neg logit contributions | |
hyde | -13.034 |
leigh | -12.632 |
zinski | -12.379 |
appings | -11.684 |
OTAL | -11.591 |
Token | the |
Token ID | 262 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
sidx | +3.361 |
Norm | +3.151 |
untarily | +2.779 |
warmed | +2.648 |
itals | +2.614 |
Neg logit contributions | |
hyde | -3.175 |
leigh | -3.167 |
zinski | -2.983 |
bane | -2.951 |
pen | -2.935 |
Token | transgender |
Token ID | 10637 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
sidx | +4.858 |
Norm | +4.608 |
untarily | +4.045 |
warmed | +3.956 |
caffe | +3.899 |
Neg logit contributions | |
hyde | -4.341 |
leigh | -4.322 |
bane | -4.010 |
pen | -4.001 |
zinski | -3.983 |
Token | analogy |
Token ID | 23970 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
sidx | +2.887 |
Norm | +2.654 |
untarily | +2.364 |
warmed | +2.279 |
itals | +2.260 |
Neg logit contributions | |
leigh | -2.612 |
hyde | -2.607 |
zinski | -2.430 |
bane | -2.413 |
pen | -2.409 |
Token | in |
Token ID | 287 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
sidx | +6.007 |
Norm | +5.436 |
untarily | +4.809 |
warmed | +4.655 |
itals | +4.510 |
Neg logit contributions | |
hyde | -6.005 |
leigh | -5.949 |
zinski | -5.584 |
pen | -5.510 |
bane | -5.495 |
Token | pres |
Token ID | 906 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
sidx | +4.408 |
Norm | +4.063 |
untarily | +3.520 |
warmed | +3.510 |
streng | +3.499 |
Neg logit contributions | |
leigh | -3.694 |
hyde | -3.595 |
zinski | -3.369 |
appings | -3.305 |
wordpress | -3.280 |
Token | |
Token ID | 3907 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
sidx | +3.713 |
Norm | +3.285 |
untarily | +2.992 |
warmed | +2.808 |
itals | +2.800 |
Neg logit contributions | |
hyde | -3.765 |
leigh | -3.743 |
Drew | -3.488 |
zinski | -3.487 |
appings | -3.448 |
Token | id |
Token ID | 312 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
sidx | +1.556 |
Norm | +1.353 |
untarily | +1.241 |
itals | +1.144 |
warmed | +1.141 |
Neg logit contributions | |
hyde | -1.886 |
leigh | -1.884 |
zinski | -1.772 |
Drew | -1.767 |
bane | -1.746 |
Token | |
Token ID | 3907 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
sidx | +4.570 |
Norm | +4.226 |
untarily | +3.792 |
itals | +3.609 |
pees | +3.556 |
Neg logit contributions | |
leigh | -4.373 |
hyde | -4.353 |
zinski | -4.049 |
bane | -4.002 |
appings | -3.969 |
Token | ent |
Token ID | 298 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
sidx | +0.842 |
Norm | +0.784 |
untarily | +0.741 |
warmed | +0.715 |
itals | +0.710 |
Neg logit contributions | |
leigh | -0.259 |
hyde | -0.254 |
zinski | -0.221 |
pen | -0.217 |
Drew | -0.215 |
Token | since |
Token ID | 1201 |
Feature activation | +1.89e+01 |
Pos logit contributions | |
sidx | +3.950 |
Norm | +3.567 |
untarily | +3.093 |
warmed | +3.044 |
streng | +2.966 |
Neg logit contributions | |
leigh | -4.046 |
hyde | -3.953 |
zinski | -3.740 |
appings | -3.699 |
pen | -3.683 |
Token | at |
Token ID | 379 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
Norm | +12.918 |
sidx | +12.394 |
warmed | +10.455 |
streng | +10.342 |
caffe | +10.245 |
Neg logit contributions | |
hyde | -11.592 |
leigh | -11.163 |
zinski | -10.272 |
wordpress | -10.264 |
appings | -10.194 |
Token | least |
Token ID | 1551 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
sidx | +2.560 |
Norm | +2.324 |
untarily | +2.079 |
warmed | +1.991 |
streng | +1.989 |
Neg logit contributions | |
hyde | -2.384 |
leigh | -2.384 |
zinski | -2.247 |
pen | -2.177 |
Drew | -2.168 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | +7.74e+00 |
Pos logit contributions | |
sidx | +8.915 |
Norm | +8.904 |
warmed | +7.314 |
caffe | +7.259 |
streng | +7.198 |
Neg logit contributions | |
hyde | -8.421 |
leigh | -8.146 |
appings | -7.542 |
zinski | -7.477 |
wordpress | -7.310 |
Token | Carter |
Token ID | 10831 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
sidx | +4.514 |
Norm | +4.186 |
warmed | +3.418 |
untarily | +3.393 |
caffe | +3.261 |
Neg logit contributions | |
hyde | -6.615 |
leigh | -6.606 |
zinski | -6.254 |
appings | -6.086 |
wordpress | -6.082 |
Token | , |
Token ID | 11 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
sidx | +0.950 |
Norm | +0.857 |
untarily | +0.780 |
warmed | +0.753 |
streng | +0.739 |
Neg logit contributions | |
leigh | -0.786 |
hyde | -0.776 |
zinski | -0.726 |
pen | -0.720 |
bane | -0.713 |
Token | the |
Token ID | 262 |
Feature activation | +7.74e+00 |
Pos logit contributions | |
sidx | +7.214 |
Norm | +6.913 |
untarily | +5.809 |
streng | +5.796 |
warmed | +5.763 |
Neg logit contributions | |
hyde | -6.879 |
leigh | -6.859 |
appings | -6.264 |
zinski | -6.207 |
bane | -6.190 |
Token | new |
Token ID | 649 |
Feature activation | +8.86e+00 |
Pos logit contributions | |
sidx | +5.037 |
Norm | +4.777 |
warmed | +3.947 |
untarily | +3.915 |
caffe | +3.834 |
Neg logit contributions | |
hyde | -6.142 |
leigh | -5.904 |
bane | -5.620 |
zinski | -5.485 |
pen | -5.446 |
Token | Winnipeg |
Token ID | 23434 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
sidx | +6.187 |
Norm | +5.824 |
untarily | +4.897 |
itals | +4.891 |
warmed | +4.824 |
Neg logit contributions | |
hyde | -6.587 |
leigh | -6.325 |
bane | -5.949 |
pen | -5.812 |
zinski | -5.804 |
Token | franchise |
Token ID | 8663 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
sidx | +4.612 |
Norm | +4.273 |
warmed | +3.722 |
untarily | +3.715 |
itals | +3.638 |
Neg logit contributions | |
hyde | -3.974 |
leigh | -3.947 |
bane | -3.577 |
zinski | -3.567 |
pen | -3.536 |
Token | make |
Token ID | 787 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
sidx | +8.924 |
Norm | +8.730 |
warmed | +7.407 |
caffe | +7.364 |
untarily | +7.234 |
Neg logit contributions | |
hyde | -10.037 |
leigh | -9.792 |
zinski | -9.048 |
appings | -9.024 |
wordpress | -8.949 |
Token | its |
Token ID | 663 |
Feature activation | +1.89e+01 |
Pos logit contributions | |
sidx | +7.528 |
Norm | +7.466 |
warmed | +6.173 |
caffe | +6.020 |
streng | +5.872 |
Neg logit contributions | |
hyde | -8.997 |
leigh | -8.764 |
zinski | -8.210 |
bane | -7.923 |
wordpress | -7.902 |
Token | first |
Token ID | 717 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
Norm | +11.618 |
sidx | +11.195 |
caffe | +9.381 |
warmed | +9.051 |
mono | +8.782 |
Neg logit contributions | |
hyde | -13.785 |
leigh | -12.558 |
appings | -11.783 |
zinski | -11.340 |
bane | -11.291 |
Token | appearance |
Token ID | 5585 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Norm | +10.179 |
sidx | +9.963 |
caffe | +8.096 |
mono | +8.046 |
untarily | +7.963 |
Neg logit contributions | |
hyde | -11.164 |
leigh | -10.301 |
bane | -9.628 |
appings | -9.531 |
zinski | -9.476 |
Token | in |
Token ID | 287 |
Feature activation | +8.93e+00 |
Pos logit contributions | |
sidx | +1.957 |
Norm | +1.775 |
untarily | +1.577 |
warmed | +1.506 |
caffe | +1.460 |
Neg logit contributions | |
hyde | -2.070 |
leigh | -2.069 |
zinski | -1.930 |
pen | -1.913 |
bane | -1.902 |
Token | the |
Token ID | 262 |
Feature activation | +8.99e+00 |
Pos logit contributions | |
sidx | +6.468 |
Norm | +6.242 |
untarily | +5.245 |
warmed | +5.033 |
caffe | +4.993 |
Neg logit contributions | |
hyde | -6.477 |
leigh | -6.206 |
zinski | -5.786 |
appings | -5.775 |
bane | -5.762 |
Token | Stanley |
Token ID | 14167 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
sidx | +7.006 |
Norm | +6.890 |
untarily | +5.722 |
caffe | +5.698 |
warmed | +5.674 |
Neg logit contributions | |
hyde | -5.938 |
leigh | -5.569 |
bane | -5.253 |
appings | -5.215 |
zinski | -5.114 |
Token | height |
Token ID | 6001 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
sidx | +3.406 |
Norm | +3.033 |
untarily | +2.556 |
warmed | +2.548 |
caffe | +2.480 |
Neg logit contributions | |
hyde | -5.077 |
leigh | -5.038 |
zinski | -4.764 |
bane | -4.760 |
appings | -4.681 |
Token | = |
Token ID | 796 |
Feature activation | +7.85e+00 |
Pos logit contributions | |
sidx | +3.680 |
Norm | +3.398 |
untarily | +3.004 |
warmed | +2.876 |
caffe | +2.856 |
Neg logit contributions | |
hyde | -3.252 |
leigh | -3.210 |
zinski | -2.962 |
bane | -2.928 |
appings | -2.911 |
Token | 600 |
Token ID | 10053 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
sidx | +4.522 |
Norm | +3.956 |
untarily | +3.466 |
caffe | +3.283 |
warmed | +3.209 |
Neg logit contributions | |
leigh | -7.100 |
hyde | -7.010 |
zinski | -6.460 |
bane | -6.447 |
Drew | -6.403 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
sidx | +3.992 |
Norm | +3.229 |
untarily | +2.243 |
warmed | +2.115 |
caffe | +2.043 |
Neg logit contributions | |
hyde | -10.858 |
leigh | -10.808 |
zinski | -10.286 |
appings | -10.272 |
bane | -10.248 |
Token | gray |
Token ID | 12768 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
sidx | +7.290 |
Norm | +6.601 |
warmed | +5.707 |
caffe | +5.674 |
untarily | +5.577 |
Neg logit contributions | |
leigh | -8.789 |
hyde | -8.400 |
zinski | -8.260 |
pen | -8.125 |
Drew | -7.935 |
Token | = |
Token ID | 796 |
Feature activation | +1.88e+01 |
Pos logit contributions | |
sidx | +1.472 |
Norm | +1.333 |
untarily | +1.226 |
warmed | +1.172 |
itals | +1.155 |
Neg logit contributions | |
leigh | -1.100 |
hyde | -1.094 |
zinski | -1.013 |
pen | -1.007 |
bane | -1.000 |
Token | c |
Token ID | 269 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
sidx | +4.920 |
Norm | +4.658 |
caffe | +3.836 |
warmed | +3.001 |
mono | +2.936 |
Neg logit contributions | |
hyde | -19.783 |
leigh | -19.522 |
bane | -18.041 |
zinski | -18.005 |
appings | -17.892 |
Token | v |
Token ID | 85 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
sidx | +5.985 |
Norm | +5.519 |
untarily | +4.806 |
itals | +4.507 |
warmed | +4.315 |
Neg logit contributions | |
hyde | -12.181 |
leigh | -11.722 |
Drew | -11.248 |
planetary | -11.118 |
Apprentice | -11.075 |
Token | 2 |
Token ID | 17 |
Feature activation | +6.52e+00 |
Pos logit contributions | |
sidx | +5.543 |
Norm | +5.251 |
untarily | +4.148 |
itals | +4.001 |
warmed | +3.851 |
Neg logit contributions | |
hyde | -10.419 |
leigh | -10.047 |
appings | -9.563 |
zinski | -9.454 |
planetary | -9.265 |
Token | . |
Token ID | 764 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
sidx | +4.129 |
Norm | +3.821 |
untarily | +3.192 |
warmed | +3.087 |
caffe | +3.018 |
Neg logit contributions | |
hyde | -5.366 |
leigh | -5.286 |
zinski | -4.903 |
appings | -4.893 |
pen | -4.855 |
Token | c |
Token ID | 269 |
Feature activation | +6.68e+00 |
Pos logit contributions | |
sidx | +9.418 |
Norm | +9.248 |
caffe | +8.067 |
mono | +7.890 |
warmed | +7.811 |
Neg logit contributions | |
hyde | -9.112 |
leigh | -9.042 |
appings | -8.340 |
zinski | -8.253 |
pen | -8.139 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
sidx | +2.640 |
Norm | +2.403 |
untarily | +2.114 |
itals | +2.038 |
warmed | +2.031 |
Neg logit contributions | |
leigh | -2.524 |
hyde | -2.506 |
zinski | -2.332 |
pen | -2.330 |
appings | -2.312 |
Token |
|
Token ID | 198 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
sidx | +0.086 |
Norm | +0.077 |
untarily | +0.071 |
warmed | +0.067 |
streng | +0.067 |
Neg logit contributions | |
leigh | -0.078 |
hyde | -0.077 |
zinski | -0.072 |
pen | -0.072 |
Drew | -0.071 |
Token | Howard |
Token ID | 32434 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
sidx | +2.463 |
Norm | +2.223 |
untarily | +2.005 |
itals | +1.921 |
warmed | +1.913 |
Neg logit contributions | |
hyde | -2.237 |
leigh | -2.236 |
zinski | -2.089 |
appings | -2.054 |
pen | -2.047 |
Token | continues |
Token ID | 4477 |
Feature activation | +7.42e+00 |
Pos logit contributions | |
sidx | +4.170 |
Norm | +3.797 |
warmed | +3.404 |
untarily | +3.381 |
itals | +3.240 |
Neg logit contributions | |
leigh | -3.795 |
hyde | -3.775 |
zinski | -3.537 |
pen | -3.519 |
bane | -3.486 |
Token | to |
Token ID | 284 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
sidx | +5.296 |
Norm | +4.742 |
untarily | +4.107 |
warmed | +4.054 |
itals | +3.986 |
Neg logit contributions | |
leigh | -5.459 |
hyde | -5.448 |
bane | -5.155 |
zinski | -5.065 |
wordpress | -5.004 |
Token | impress |
Token ID | 14947 |
Feature activation | +1.88e+01 |
Pos logit contributions | |
sidx | +2.887 |
Norm | +2.617 |
untarily | +2.367 |
warmed | +2.293 |
caffe | +2.244 |
Neg logit contributions | |
leigh | -2.526 |
hyde | -2.487 |
zinski | -2.325 |
bane | -2.305 |
pen | -2.301 |
Token | people |
Token ID | 661 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
sidx | +11.448 |
Norm | +11.393 |
warmed | +9.119 |
itals | +8.821 |
caffe | +8.818 |
Neg logit contributions | |
leigh | -12.119 |
hyde | -12.070 |
wordpress | -11.556 |
appings | -11.318 |
zinski | -11.282 |
Token | ; |
Token ID | 26 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
sidx | +4.218 |
Norm | +3.858 |
warmed | +3.353 |
untarily | +3.297 |
caffe | +3.188 |
Neg logit contributions | |
hyde | -4.227 |
leigh | -4.190 |
zinski | -3.940 |
pen | -3.911 |
bane | -3.909 |
Token | he |
Token ID | 339 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
sidx | +5.083 |
Norm | +4.726 |
warmed | +4.054 |
untarily | +4.015 |
itals | +3.941 |
Neg logit contributions | |
leigh | -4.959 |
hyde | -4.913 |
zinski | -4.569 |
pen | -4.516 |
wordpress | -4.489 |
Token | has |
Token ID | 468 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
sidx | +2.190 |
Norm | +1.985 |
untarily | +1.788 |
warmed | +1.763 |
itals | +1.705 |
Neg logit contributions | |
leigh | -1.932 |
hyde | -1.922 |
zinski | -1.798 |
pen | -1.788 |
bane | -1.776 |
Token | been |
Token ID | 587 |
Feature activation | +9.18e+00 |
Pos logit contributions | |
sidx | +4.094 |
Norm | +3.862 |
warmed | +3.445 |
untarily | +3.376 |
caffe | +3.283 |
Neg logit contributions | |
hyde | -3.995 |
leigh | -3.950 |
zinski | -3.681 |
bane | -3.672 |
pen | -3.642 |
Token |
|
Token ID | 198 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
sidx | +1.383 |
Norm | +1.249 |
untarily | +1.120 |
warmed | +1.067 |
itals | +1.051 |
Neg logit contributions | |
leigh | -1.365 |
hyde | -1.364 |
zinski | -1.266 |
pen | -1.259 |
bane | -1.251 |
Token | The |
Token ID | 464 |
Feature activation | +7.39e+00 |
Pos logit contributions | |
sidx | +0.521 |
Norm | +0.469 |
untarily | +0.429 |
warmed | +0.408 |
itals | +0.403 |
Neg logit contributions | |
leigh | -0.456 |
hyde | -0.453 |
zinski | -0.423 |
pen | -0.419 |
bane | -0.417 |
Token | loss |
Token ID | 2994 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
sidx | +5.297 |
Norm | +4.936 |
warmed | +4.220 |
untarily | +4.193 |
caffe | +4.090 |
Neg logit contributions | |
hyde | -5.451 |
leigh | -5.369 |
bane | -5.001 |
zinski | -4.930 |
appings | -4.851 |
Token | to |
Token ID | 284 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
sidx | +4.440 |
Norm | +4.107 |
warmed | +3.705 |
untarily | +3.585 |
caffe | +3.469 |
Neg logit contributions | |
hyde | -4.575 |
leigh | -4.540 |
zinski | -4.203 |
appings | -4.178 |
pen | -4.118 |
Token | the |
Token ID | 262 |
Feature activation | +8.47e+00 |
Pos logit contributions | |
sidx | +4.720 |
Norm | +4.408 |
untarily | +3.852 |
warmed | +3.755 |
itals | +3.715 |
Neg logit contributions | |
hyde | -4.052 |
leigh | -4.013 |
zinski | -3.719 |
bane | -3.717 |
appings | -3.651 |
Token | Flyers |
Token ID | 30652 |
Feature activation | +1.87e+01 |
Pos logit contributions | |
sidx | +5.770 |
Norm | +5.464 |
warmed | +4.516 |
untarily | +4.479 |
itals | +4.419 |
Neg logit contributions | |
hyde | -6.454 |
leigh | -6.233 |
bane | -6.024 |
zinski | -5.828 |
appings | -5.816 |
Token | was |
Token ID | 373 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
sidx | +10.113 |
Norm | +10.075 |
warmed | +9.711 |
caffe | +8.300 |
streng | +8.219 |
Neg logit contributions | |
hyde | -13.566 |
leigh | -12.735 |
appings | -12.648 |
OTAL | -11.948 |
zinski | -11.828 |
Token | Chicago |
Token ID | 4842 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
sidx | +2.760 |
Norm | +2.544 |
untarily | +2.245 |
warmed | +2.208 |
streng | +2.148 |
Neg logit contributions | |
hyde | -2.506 |
leigh | -2.500 |
zinski | -2.304 |
appings | -2.266 |
pen | -2.264 |
Token | 's |
Token ID | 338 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
sidx | +4.661 |
Norm | +4.262 |
untarily | +3.802 |
warmed | +3.710 |
itals | +3.600 |
Neg logit contributions | |
hyde | -4.539 |
leigh | -4.455 |
zinski | -4.162 |
appings | -4.106 |
bane | -4.080 |
Token | fourth |
Token ID | 5544 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
sidx | +5.980 |
Norm | +5.699 |
warmed | +4.825 |
caffe | +4.586 |
untarily | +4.573 |
Neg logit contributions | |
hyde | -8.501 |
leigh | -8.067 |
zinski | -7.677 |
appings | -7.649 |
wordpress | -7.528 |
Token | straight |
Token ID | 3892 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
sidx | +2.460 |
Norm | +2.238 |
untarily | +1.994 |
warmed | +1.931 |
caffe | +1.872 |
Neg logit contributions | |
hyde | -2.434 |
leigh | -2.417 |
zinski | -2.273 |
bane | -2.220 |
appings | -2.218 |
Token | x |
Token ID | 2124 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
sidx | +0.340 |
Norm | +0.309 |
untarily | +0.286 |
warmed | +0.273 |
streng | +0.271 |
Neg logit contributions | |
leigh | -0.236 |
hyde | -0.233 |
zinski | -0.216 |
pen | -0.215 |
Drew | -0.213 |
Token | . |
Token ID | 13 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
leigh | +1.761 |
hyde | +1.697 |
zinski | +1.632 |
pen | +1.631 |
Drew | +1.611 |
Neg logit contributions | |
sidx | -2.478 |
Norm | -2.196 |
streng | -2.100 |
untarily | -2.076 |
warmed | -1.977 |
Token | x |
Token ID | 87 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
sidx | +2.461 |
Norm | +2.200 |
untarily | +1.950 |
warmed | +1.830 |
itals | +1.828 |
Neg logit contributions | |
hyde | -2.911 |
leigh | -2.894 |
Drew | -2.703 |
zinski | -2.693 |
appings | -2.676 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
leigh | +0.214 |
hyde | +0.211 |
zinski | +0.198 |
pen | +0.198 |
Drew | +0.196 |
Neg logit contributions | |
sidx | -0.266 |
Norm | -0.238 |
untarily | -0.220 |
streng | -0.211 |
warmed | -0.209 |
Token | x |
Token ID | 87 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
leigh | +1.758 |
hyde | +1.706 |
pen | +1.639 |
zinski | +1.633 |
bane | +1.597 |
Neg logit contributions | |
sidx | -1.974 |
Norm | -1.755 |
streng | -1.628 |
untarily | -1.614 |
warmed | -1.547 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e+01 |
Pos logit contributions | |
leigh | +6.336 |
zinski | +5.494 |
Drew | +5.463 |
pen | +5.351 |
wordpress | +5.321 |
Neg logit contributions | |
streng | -13.550 |
sidx | -13.429 |
newcom | -12.913 |
Norm | -11.987 |
confir | -11.671 |
Token | 149 |
Token ID | 19442 |
Feature activation | -7.43e+00 |
Pos logit contributions | |
leigh | +10.181 |
iddler | +8.877 |
pen | +8.635 |
hyde | +8.460 |
surv | +8.354 |
Neg logit contributions | |
sidx | -19.155 |
Norm | -17.731 |
streng | -17.394 |
newcom | -16.369 |
untarily | -15.626 |
Token | 110 |
Token ID | 9796 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
leigh | +4.099 |
hyde | +3.985 |
Drew | +3.956 |
zinski | +3.749 |
pen | +3.726 |
Neg logit contributions | |
sidx | -6.669 |
untarily | -5.762 |
Norm | -5.687 |
streng | -5.560 |
warmed | -5.426 |
Token | 22 |
Token ID | 1828 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
sidx | +1.231 |
Norm | +1.096 |
untarily | +0.971 |
warmed | +0.916 |
itals | +0.910 |
Neg logit contributions | |
leigh | -1.410 |
hyde | -1.405 |
pen | -1.316 |
zinski | -1.315 |
Drew | -1.303 |
Token | 26 |
Token ID | 2075 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
leigh | +0.243 |
hyde | +0.241 |
zinski | +0.227 |
pen | +0.226 |
bane | +0.224 |
Neg logit contributions | |
sidx | -0.237 |
Norm | -0.211 |
untarily | -0.191 |
warmed | -0.181 |
streng | -0.178 |
Token | x |
Token ID | 2124 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
leigh | +2.123 |
hyde | +2.040 |
Drew | +1.958 |
zinski | +1.955 |
pen | +1.950 |
Neg logit contributions | |
sidx | -3.842 |
Norm | -3.446 |
untarily | -3.349 |
streng | -3.292 |
itals | -3.171 |
Token | x |
Token ID | 2124 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
leigh | +2.389 |
hyde | +2.284 |
Drew | +2.211 |
pen | +2.208 |
zinski | +2.201 |
Neg logit contributions | |
sidx | -4.470 |
Norm | -4.023 |
untarily | -3.921 |
streng | -3.863 |
itals | -3.725 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
leigh | +2.227 |
hyde | +2.133 |
zinski | +2.064 |
pen | +2.063 |
Drew | +2.041 |
Neg logit contributions | |
sidx | -3.283 |
Norm | -2.901 |
streng | -2.836 |
untarily | -2.761 |
warmed | -2.626 |
Token | x |
Token ID | 87 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
sidx | +1.875 |
Norm | +1.674 |
untarily | +1.497 |
warmed | +1.411 |
itals | +1.400 |
Neg logit contributions | |
hyde | -2.114 |
leigh | -2.113 |
zinski | -1.968 |
Drew | -1.965 |
pen | -1.950 |
Token | . |
Token ID | 13 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
leigh | +0.210 |
hyde | +0.207 |
zinski | +0.195 |
pen | +0.194 |
Drew | +0.192 |
Neg logit contributions | |
sidx | -0.260 |
Norm | -0.233 |
untarily | -0.215 |
streng | -0.206 |
warmed | -0.205 |
Token | x |
Token ID | 87 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
leigh | +1.404 |
hyde | +1.374 |
pen | +1.317 |
zinski | +1.308 |
bane | +1.285 |
Neg logit contributions | |
sidx | -1.554 |
Norm | -1.383 |
untarily | -1.266 |
streng | -1.265 |
warmed | -1.211 |
Token | . |
Token ID | 13 |
Feature activation | -2.20e+01 |
Pos logit contributions | |
leigh | +5.901 |
pen | +5.491 |
born | +5.313 |
zinski | +5.313 |
wordpress | +5.242 |
Neg logit contributions | |
streng | -13.711 |
sidx | -13.393 |
newcom | -13.010 |
Norm | -12.258 |
confir | -11.669 |
Token | 145 |
Token ID | 18781 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
pen | +7.290 |
leigh | +6.948 |
execute | +6.518 |
wordpress | +6.397 |
surv | +6.345 |
Neg logit contributions | |
sidx | -20.331 |
streng | -20.039 |
Norm | -19.936 |
newcom | -19.022 |
Wem | -18.042 |
Token | 12 |
Token ID | 1105 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
leigh | +2.148 |
hyde | +2.101 |
Drew | +1.984 |
zinski | +1.969 |
pen | +1.961 |
Neg logit contributions | |
sidx | -3.119 |
Norm | -2.751 |
untarily | -2.639 |
streng | -2.514 |
warmed | -2.504 |
Token | 457 |
Token ID | 33032 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
leigh | +1.282 |
hyde | +1.264 |
zinski | +1.192 |
pen | +1.186 |
Drew | +1.174 |
Neg logit contributions | |
sidx | -1.392 |
Norm | -1.241 |
untarily | -1.144 |
warmed | -1.086 |
streng | -1.083 |
Token | 01 |
Token ID | 486 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
sidx | +1.383 |
Norm | +1.245 |
untarily | +1.097 |
warmed | +1.050 |
itals | +1.026 |
Neg logit contributions | |
hyde | -1.502 |
leigh | -1.492 |
zinski | -1.393 |
pen | -1.379 |
bane | -1.372 |
Token | x |
Token ID | 2124 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
leigh | +2.460 |
hyde | +2.352 |
Drew | +2.276 |
pen | +2.260 |
zinski | +2.242 |
Neg logit contributions | |
sidx | -4.600 |
Norm | -4.155 |
untarily | -4.032 |
streng | -3.929 |
itals | -3.819 |
Token | x |
Token ID | 2124 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
leigh | +0.540 |
hyde | +0.530 |
zinski | +0.496 |
pen | +0.495 |
Drew | +0.491 |
Neg logit contributions | |
sidx | -0.836 |
Norm | -0.757 |
untarily | -0.710 |
streng | -0.682 |
warmed | -0.675 |
Token | . |
Token ID | 13 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
leigh | +1.949 |
hyde | +1.873 |
pen | +1.802 |
zinski | +1.802 |
Drew | +1.792 |
Neg logit contributions | |
sidx | -2.817 |
Norm | -2.486 |
streng | -2.411 |
untarily | -2.365 |
warmed | -2.249 |
Token | x |
Token ID | 87 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
sidx | +2.974 |
Norm | +2.674 |
untarily | +2.352 |
itals | +2.202 |
warmed | +2.197 |
Neg logit contributions | |
hyde | -3.709 |
leigh | -3.680 |
Drew | -3.444 |
zinski | -3.425 |
appings | -3.416 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
sidx | +0.705 |
Norm | +0.635 |
untarily | +0.580 |
warmed | +0.553 |
itals | +0.545 |
Neg logit contributions | |
leigh | -0.604 |
hyde | -0.600 |
zinski | -0.560 |
pen | -0.557 |
bane | -0.551 |
Token | x |
Token ID | 87 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
sidx | +1.316 |
Norm | +1.173 |
untarily | +1.056 |
warmed | +0.996 |
itals | +0.986 |
Neg logit contributions | |
leigh | -1.416 |
hyde | -1.413 |
zinski | -1.323 |
Drew | -1.314 |
pen | -1.312 |
Token | . |
Token ID | 13 |
Feature activation | -2.08e+01 |
Pos logit contributions | |
leigh | +5.411 |
hyde | +4.857 |
born | +4.776 |
pen | +4.746 |
zinski | +4.690 |
Neg logit contributions | |
sidx | -10.752 |
streng | -10.530 |
newcom | -9.977 |
Norm | -9.480 |
untarily | -9.396 |
Token | 169 |
Token ID | 22172 |
Feature activation | -7.64e+00 |
Pos logit contributions | |
leigh | +10.259 |
hyde | +9.761 |
born | +9.732 |
pen | +8.363 |
bane | +8.339 |
Neg logit contributions | |
sidx | -16.906 |
Norm | -15.402 |
streng | -14.762 |
untarily | -14.602 |
ンジ | -14.543 |
Token | 11 |
Token ID | 1367 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
leigh | +4.162 |
Drew | +4.023 |
hyde | +4.020 |
zinski | +3.810 |
pen | +3.761 |
Neg logit contributions | |
sidx | -6.890 |
untarily | -5.983 |
Norm | -5.900 |
streng | -5.787 |
itals | -5.613 |
Token | 66 |
Token ID | 2791 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
leigh | +3.172 |
hyde | +3.117 |
zinski | +2.955 |
pen | +2.946 |
Drew | +2.935 |
Neg logit contributions | |
sidx | -3.209 |
Norm | -2.817 |
untarily | -2.647 |
streng | -2.542 |
warmed | -2.518 |
Token | 589 |
Token ID | 44169 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
sidx | +1.517 |
Norm | +1.339 |
untarily | +1.195 |
warmed | +1.125 |
itals | +1.116 |
Neg logit contributions | |
leigh | -1.743 |
hyde | -1.727 |
zinski | -1.625 |
pen | -1.622 |
Drew | -1.610 |
Token | x |
Token ID | 2124 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
sidx | +0.904 |
Norm | +0.821 |
untarily | +0.753 |
warmed | +0.724 |
itals | +0.712 |
Neg logit contributions | |
leigh | -0.651 |
hyde | -0.646 |
zinski | -0.598 |
pen | -0.594 |
bane | -0.588 |
Token | " |
Token ID | 366 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
leigh | +1.730 |
hyde | +1.699 |
Drew | +1.616 |
zinski | +1.604 |
pen | +1.597 |
Neg logit contributions | |
sidx | -2.264 |
Norm | -1.996 |
untarily | -1.895 |
streng | -1.807 |
warmed | -1.793 |
Token | The |
Token ID | 464 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
sidx | +0.110 |
Norm | +0.099 |
untarily | +0.090 |
warmed | +0.086 |
itals | +0.085 |
Neg logit contributions | |
leigh | -0.098 |
hyde | -0.098 |
zinski | -0.091 |
pen | -0.091 |
bane | -0.090 |
Token | worst |
Token ID | 5290 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
leigh | +4.910 |
hyde | +4.810 |
Drew | +4.722 |
pen | +4.601 |
zinski | +4.577 |
Neg logit contributions | |
sidx | -6.258 |
Norm | -5.340 |
untarily | -5.220 |
itals | -4.855 |
pees | -4.792 |
Token | is |
Token ID | 318 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
leigh | +6.178 |
Drew | +6.167 |
pen | +5.984 |
bite | +5.952 |
hyde | +5.932 |
Neg logit contributions | |
sidx | -9.310 |
untarily | -7.905 |
Norm | -7.844 |
ンジ | -7.270 |
pees | -7.245 |
Token | yet |
Token ID | 1865 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
leigh | +5.764 |
Drew | +5.641 |
hyde | +5.568 |
pen | +5.540 |
bane | +5.290 |
Neg logit contributions | |
sidx | -9.408 |
Norm | -8.076 |
untarily | -7.874 |
ンジ | -7.502 |
streng | -7.491 |
Token | to |
Token ID | 284 |
Feature activation | -2.04e+01 |
Pos logit contributions | |
leigh | +6.258 |
born | +6.151 |
hyde | +6.001 |
pen | +5.971 |
Drew | +5.849 |
Neg logit contributions | |
sidx | -13.245 |
Norm | -11.353 |
untarily | -11.127 |
streng | -10.889 |
ンジ | -10.640 |
Token | come |
Token ID | 1282 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
hyde | +5.714 |
pen | +5.577 |
Drew | +5.379 |
bane | +5.094 |
born | +5.039 |
Neg logit contributions | |
sidx | -20.661 |
untarily | -18.015 |
ンジ | -17.751 |
Norm | -17.693 |
streng | -17.663 |
Token | ." |
Token ID | 526 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
leigh | +4.264 |
hyde | +4.245 |
pen | +4.068 |
Drew | +4.065 |
bane | +3.954 |
Neg logit contributions | |
sidx | -6.806 |
Norm | -5.949 |
untarily | -5.740 |
streng | -5.518 |
ンジ | -5.414 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
leigh | +0.850 |
hyde | +0.840 |
zinski | +0.790 |
pen | +0.787 |
Drew | +0.786 |
Neg logit contributions | |
sidx | -0.942 |
Norm | -0.836 |
untarily | -0.775 |
warmed | -0.732 |
streng | -0.729 |
Token |
|
Token ID | 198 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
leigh | +1.924 |
hyde | +1.853 |
pen | +1.789 |
zinski | +1.786 |
Drew | +1.774 |
Neg logit contributions | |
sidx | -2.539 |
Norm | -2.225 |
streng | -2.131 |
untarily | -2.115 |
warmed | -2.005 |
Token | So |
Token ID | 2396 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
leigh | +1.536 |
hyde | +1.493 |
pen | +1.425 |
zinski | +1.407 |
bane | +1.391 |
Neg logit contributions | |
sidx | -1.928 |
Norm | -1.717 |
untarily | -1.583 |
streng | -1.531 |
warmed | -1.510 |
Token | x |
Token ID | 2124 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
leigh | +0.388 |
hyde | +0.381 |
zinski | +0.357 |
pen | +0.355 |
Drew | +0.352 |
Neg logit contributions | |
sidx | -0.593 |
Norm | -0.536 |
untarily | -0.502 |
streng | -0.480 |
warmed | -0.477 |
Token | . |
Token ID | 13 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
leigh | +1.888 |
hyde | +1.816 |
pen | +1.750 |
zinski | +1.750 |
Drew | +1.732 |
Neg logit contributions | |
sidx | -2.706 |
Norm | -2.393 |
streng | -2.306 |
untarily | -2.269 |
warmed | -2.157 |
Token | x |
Token ID | 87 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
sidx | +2.685 |
Norm | +2.406 |
untarily | +2.122 |
warmed | +1.993 |
itals | +1.989 |
Neg logit contributions | |
hyde | -3.253 |
leigh | -3.232 |
Drew | -3.020 |
zinski | -3.007 |
appings | -2.991 |
Token | . |
Token ID | 13 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
sidx | +0.355 |
Norm | +0.319 |
untarily | +0.293 |
warmed | +0.279 |
streng | +0.276 |
Neg logit contributions | |
leigh | -0.298 |
hyde | -0.295 |
zinski | -0.276 |
pen | -0.274 |
bane | -0.272 |
Token | x |
Token ID | 87 |
Feature activation | -1.65e+01 |
Pos logit contributions | |
leigh | +2.836 |
hyde | +2.725 |
pen | +2.647 |
zinski | +2.618 |
bane | +2.553 |
Neg logit contributions | |
sidx | -3.400 |
Norm | -3.040 |
streng | -2.909 |
untarily | -2.791 |
warmed | -2.691 |
Token | . |
Token ID | 13 |
Feature activation | -2.03e+01 |
Pos logit contributions | |
leigh | +7.544 |
hyde | +6.524 |
wordpress | +6.444 |
Drew | +6.337 |
pen | +6.215 |
Neg logit contributions | |
streng | -15.335 |
sidx | -14.497 |
newcom | -14.464 |
Norm | -13.817 |
thous | -12.815 |
Token | 148 |
Token ID | 18294 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
leigh | +7.692 |
hyde | +6.622 |
surv | +6.229 |
wordpress | +6.063 |
pen | +6.027 |
Neg logit contributions | |
streng | -18.505 |
sidx | -18.309 |
Norm | -18.250 |
newcom | -17.077 |
Prism | -16.574 |
Token | 10 |
Token ID | 838 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
leigh | +3.063 |
hyde | +2.987 |
Drew | +2.893 |
zinski | +2.822 |
pen | +2.799 |
Neg logit contributions | |
sidx | -4.642 |
Norm | -4.017 |
untarily | -3.951 |
streng | -3.819 |
warmed | -3.742 |
Token | 42 |
Token ID | 3682 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
sidx | +0.649 |
Norm | +0.577 |
untarily | +0.516 |
warmed | +0.487 |
itals | +0.482 |
Neg logit contributions | |
leigh | -0.721 |
hyde | -0.718 |
zinski | -0.673 |
pen | -0.671 |
bane | -0.666 |
Token | 170 |
Token ID | 17279 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
sidx | +3.339 |
Norm | +2.986 |
untarily | +2.592 |
warmed | +2.457 |
itals | +2.408 |
Neg logit contributions | |
leigh | -3.839 |
hyde | -3.802 |
zinski | -3.553 |
pen | -3.521 |
bane | -3.506 |
Token | x |
Token ID | 2124 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
sidx | +0.340 |
Norm | +0.309 |
untarily | +0.286 |
warmed | +0.273 |
streng | +0.271 |
Neg logit contributions | |
leigh | -0.236 |
hyde | -0.233 |
zinski | -0.216 |
pen | -0.215 |
Drew | -0.213 |
Token | legislative |
Token ID | 10828 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
sidx | +2.446 |
Norm | +2.242 |
untarily | +2.023 |
warmed | +1.960 |
itals | +1.948 |
Neg logit contributions | |
leigh | -1.973 |
hyde | -1.952 |
zinski | -1.819 |
bane | -1.812 |
pen | -1.802 |
Token | proposals |
Token ID | 11628 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
sidx | +0.259 |
Norm | +0.233 |
untarily | +0.211 |
warmed | +0.202 |
streng | +0.200 |
Neg logit contributions | |
leigh | -0.237 |
hyde | -0.235 |
zinski | -0.221 |
pen | -0.219 |
bane | -0.217 |
Token | and |
Token ID | 290 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
leigh | +0.829 |
hyde | +0.824 |
pen | +0.767 |
zinski | +0.766 |
Drew | +0.762 |
Neg logit contributions | |
sidx | -0.989 |
Norm | -0.883 |
untarily | -0.816 |
warmed | -0.769 |
streng | -0.765 |
Token | policies |
Token ID | 4788 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
leigh | +4.078 |
hyde | +4.046 |
Drew | +3.817 |
zinski | +3.791 |
pen | +3.760 |
Neg logit contributions | |
sidx | -5.503 |
Norm | -4.786 |
untarily | -4.686 |
pees | -4.306 |
itals | -4.196 |
Token | . |
Token ID | 13 |
Feature activation | -7.93e+00 |
Pos logit contributions | |
leigh | +0.629 |
hyde | +0.623 |
zinski | +0.582 |
pen | +0.581 |
Drew | +0.577 |
Neg logit contributions | |
sidx | -0.743 |
Norm | -0.664 |
untarily | -0.612 |
warmed | -0.579 |
streng | -0.573 |
Token | That |
Token ID | 1320 |
Feature activation | -2.03e+01 |
Pos logit contributions | |
leigh | +4.744 |
Drew | +4.674 |
hyde | +4.622 |
zinski | +4.380 |
pen | +4.361 |
Neg logit contributions | |
sidx | -6.764 |
untarily | -5.779 |
streng | -5.640 |
Norm | -5.625 |
warmed | -5.336 |
Token | is |
Token ID | 318 |
Feature activation | -9.59e+00 |
Pos logit contributions | |
leigh | +10.627 |
Drew | +10.193 |
hyde | +10.016 |
born | +9.918 |
pen | +9.765 |
Neg logit contributions | |
sidx | -14.820 |
untarily | -13.088 |
Norm | -12.887 |
pees | -11.936 |
ンジ | -11.757 |
Token | not |
Token ID | 407 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
leigh | +5.716 |
Drew | +5.494 |
hyde | +5.384 |
pen | +5.301 |
bane | +5.164 |
Neg logit contributions | |
sidx | -8.011 |
Norm | -6.838 |
untarily | -6.760 |
ンジ | -6.435 |
pees | -6.260 |
Token | even |
Token ID | 772 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
leigh | +2.647 |
hyde | +2.590 |
Drew | +2.482 |
zinski | +2.464 |
pen | +2.424 |
Neg logit contributions | |
sidx | -3.374 |
Norm | -2.952 |
untarily | -2.800 |
itals | -2.621 |
streng | -2.613 |
Token | the |
Token ID | 262 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
leigh | +6.209 |
hyde | +6.158 |
Drew | +6.072 |
pen | +5.826 |
zinski | +5.818 |
Neg logit contributions | |
sidx | -8.544 |
Norm | -7.207 |
untarily | -7.163 |
ンジ | -6.792 |
pees | -6.554 |
Token | worst |
Token ID | 5290 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
leigh | +1.025 |
hyde | +1.014 |
zinski | +0.956 |
pen | +0.952 |
Drew | +0.947 |
Neg logit contributions | |
sidx | -1.102 |
Norm | -0.978 |
untarily | -0.903 |
warmed | -0.846 |
itals | -0.841 |
Token | Week |
Token ID | 6119 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
leigh | +1.226 |
hyde | +1.196 |
Drew | +1.139 |
pen | +1.129 |
zinski | +1.119 |
Neg logit contributions | |
sidx | -1.742 |
Norm | -1.549 |
untarily | -1.455 |
streng | -1.384 |
warmed | -1.380 |
Token | 14 |
Token ID | 1478 |
Feature activation | -7.81e+00 |
Pos logit contributions | |
sidx | +0.896 |
Norm | +0.821 |
untarily | +0.751 |
warmed | +0.721 |
itals | +0.711 |
Neg logit contributions | |
hyde | -0.633 |
leigh | -0.632 |
zinski | -0.581 |
pen | -0.577 |
bane | -0.570 |
Token | at |
Token ID | 379 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
leigh | +4.719 |
hyde | +4.445 |
Drew | +4.438 |
pen | +4.366 |
zinski | +4.232 |
Neg logit contributions | |
sidx | -6.580 |
Norm | -5.818 |
untarily | -5.578 |
streng | -5.302 |
ンジ | -5.269 |
Token | Miami |
Token ID | 8437 |
Feature activation | -9.45e+00 |
Pos logit contributions | |
Drew | +6.834 |
leigh | +6.450 |
Tucson | +6.087 |
pen | +6.084 |
Stafford | +5.882 |
Neg logit contributions | |
sidx | -11.982 |
untarily | -10.435 |
Norm | -10.044 |
streng | -10.015 |
pees | -9.848 |
Token | when |
Token ID | 618 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
leigh | +5.345 |
hyde | +5.122 |
Drew | +5.090 |
pen | +4.953 |
zinski | +4.808 |
Neg logit contributions | |
sidx | -8.141 |
Norm | -7.247 |
untarily | -7.031 |
streng | -6.565 |
ンジ | -6.498 |
Token | he |
Token ID | 339 |
Feature activation | -2.02e+01 |
Pos logit contributions | |
Drew | +6.699 |
leigh | +6.347 |
pen | +5.962 |
hyde | +5.937 |
Stafford | +5.694 |
Neg logit contributions | |
sidx | -10.347 |
untarily | -8.667 |
Norm | -8.621 |
ンジ | -8.092 |
streng | -8.060 |
Token | had |
Token ID | 550 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
Drew | +10.411 |
leigh | +10.042 |
pen | +9.065 |
Stafford | +8.995 |
hyde | +8.774 |
Neg logit contributions | |
sidx | -16.473 |
Norm | -13.723 |
覚醒 | -13.314 |
untarily | -13.229 |
ンジ | -12.836 |
Token | 35 |
Token ID | 3439 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
leigh | +3.385 |
Drew | +3.288 |
hyde | +3.239 |
pen | +3.190 |
zinski | +3.114 |
Neg logit contributions | |
sidx | -4.520 |
Norm | -3.899 |
untarily | -3.680 |
streng | -3.509 |
ンジ | -3.502 |
Token | Fantasy |
Token ID | 10982 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
leigh | +3.022 |
hyde | +2.942 |
Drew | +2.870 |
pen | +2.863 |
zinski | +2.780 |
Neg logit contributions | |
sidx | -4.038 |
Norm | -3.603 |
untarily | -3.391 |
streng | -3.235 |
warmed | -3.184 |
Token | points |
Token ID | 2173 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
leigh | +5.177 |
pen | +5.039 |
Drew | +5.030 |
hyde | +4.839 |
zinski | +4.679 |
Neg logit contributions | |
sidx | -9.235 |
Norm | -8.267 |
untarily | -8.161 |
streng | -8.140 |
ンジ | -7.843 |
Token | . |
Token ID | 13 |
Feature activation | -9.27e+00 |
Pos logit contributions | |
leigh | +6.341 |
Drew | +6.202 |
pen | +5.974 |
hyde | +5.843 |
zinski | +5.539 |
Neg logit contributions | |
sidx | -9.518 |
Norm | -8.433 |
untarily | -8.155 |
streng | -7.831 |
itals | -7.684 |
Token | is |
Token ID | 318 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
leigh | +4.367 |
hyde | +4.248 |
pen | +4.147 |
Drew | +4.127 |
bane | +4.063 |
Neg logit contributions | |
sidx | -6.460 |
Norm | -5.534 |
untarily | -5.394 |
ンジ | -5.111 |
itals | -4.965 |
Token | reducing |
Token ID | 8868 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
leigh | +3.673 |
hyde | +3.562 |
Drew | +3.484 |
pen | +3.452 |
bane | +3.369 |
Neg logit contributions | |
sidx | -4.878 |
Norm | -4.181 |
untarily | -3.970 |
ンジ | -3.736 |
itals | -3.713 |
Token | , |
Token ID | 11 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
leigh | +3.631 |
hyde | +3.515 |
Drew | +3.428 |
pen | +3.399 |
bane | +3.339 |
Neg logit contributions | |
sidx | -5.134 |
Norm | -4.572 |
untarily | -4.291 |
itals | -4.145 |
pees | -4.111 |
Token | before |
Token ID | 878 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
leigh | +1.914 |
hyde | +1.873 |
zinski | +1.775 |
pen | +1.775 |
Drew | +1.773 |
Neg logit contributions | |
sidx | -2.219 |
Norm | -1.965 |
untarily | -1.823 |
itals | -1.716 |
warmed | -1.698 |
Token | it |
Token ID | 340 |
Feature activation | -8.77e+00 |
Pos logit contributions | |
leigh | +4.398 |
hyde | +4.265 |
Drew | +4.228 |
pen | +4.160 |
zinski | +4.140 |
Neg logit contributions | |
sidx | -4.987 |
Norm | -4.342 |
untarily | -4.055 |
itals | -3.860 |
ンジ | -3.810 |
Token | raises |
Token ID | 12073 |
Feature activation | -2.01e+01 |
Pos logit contributions | |
leigh | +5.559 |
hyde | +5.316 |
Drew | +5.283 |
pen | +5.221 |
zinski | +5.194 |
Neg logit contributions | |
sidx | -7.119 |
Norm | -6.078 |
untarily | -5.730 |
ンジ | -5.518 |
itals | -5.393 |
Token | interest |
Token ID | 1393 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
Drew | +8.348 |
pen | +8.347 |
leigh | +7.756 |
Ultimate | +7.614 |
Stafford | +7.599 |
Neg logit contributions | |
sidx | -17.326 |
untarily | -14.461 |
pees | -14.437 |
Norm | -14.399 |
itals | -14.092 |
Token | rates |
Token ID | 3965 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
pen | +4.458 |
Drew | +4.274 |
hyde | +4.128 |
leigh | +4.101 |
born | +3.970 |
Neg logit contributions | |
sidx | -10.386 |
Norm | -9.101 |
untarily | -8.703 |
itals | -8.493 |
ンジ | -8.410 |
Token | . |
Token ID | 13 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
leigh | +5.917 |
Drew | +5.773 |
pen | +5.756 |
hyde | +5.516 |
zinski | +5.480 |
Neg logit contributions | |
sidx | -8.982 |
Norm | -7.596 |
untarily | -7.373 |
ンジ | -7.262 |
itals | -7.118 |
Token |
|
Token ID | 198 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
leigh | +2.834 |
hyde | +2.809 |
Drew | +2.668 |
pen | +2.663 |
zinski | +2.656 |
Neg logit contributions | |
sidx | -3.308 |
Norm | -2.902 |
untarily | -2.728 |
streng | -2.577 |
warmed | -2.573 |
Token |
|
Token ID | 198 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
leigh | +3.339 |
Drew | +3.124 |
pen | +3.101 |
hyde | +3.094 |
zinski | +3.069 |
Neg logit contributions | |
sidx | -5.259 |
streng | -4.730 |
Norm | -4.492 |
untarily | -4.425 |
newcom | -4.278 |
Token | that |
Token ID | 326 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
sidx | +3.219 |
Norm | +2.929 |
untarily | +2.622 |
warmed | +2.567 |
streng | +2.472 |
Neg logit contributions | |
hyde | -2.863 |
leigh | -2.851 |
zinski | -2.673 |
pen | -2.636 |
appings | -2.636 |
Token | it |
Token ID | 340 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
sidx | +1.493 |
Norm | +1.354 |
untarily | +1.220 |
warmed | +1.186 |
streng | +1.159 |
Neg logit contributions | |
leigh | -1.296 |
hyde | -1.295 |
zinski | -1.202 |
pen | -1.198 |
bane | -1.185 |
Token | happened |
Token ID | 3022 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
leigh | +1.325 |
hyde | +1.310 |
zinski | +1.225 |
pen | +1.215 |
Drew | +1.211 |
Neg logit contributions | |
sidx | -1.628 |
Norm | -1.454 |
untarily | -1.352 |
streng | -1.258 |
itals | -1.256 |
Token | to |
Token ID | 284 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
leigh | +2.457 |
hyde | +2.416 |
zinski | +2.263 |
pen | +2.263 |
Drew | +2.252 |
Neg logit contributions | |
sidx | -3.101 |
Norm | -2.752 |
untarily | -2.583 |
streng | -2.430 |
itals | -2.412 |
Token | keep |
Token ID | 1394 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
sidx | +0.857 |
Norm | +0.778 |
untarily | +0.708 |
warmed | +0.678 |
streng | +0.669 |
Neg logit contributions | |
leigh | -0.710 |
hyde | -0.703 |
zinski | -0.657 |
pen | -0.654 |
bane | -0.647 |
Token | Reagan |
Token ID | 12823 |
Feature activation | -1.98e+01 |
Pos logit contributions | |
leigh | +3.205 |
hyde | +3.149 |
Drew | +3.014 |
pen | +2.974 |
zinski | +2.970 |
Neg logit contributions | |
sidx | -4.575 |
Norm | -4.061 |
untarily | -3.852 |
itals | -3.633 |
warmed | -3.574 |
Token | to |
Token ID | 284 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
hyde | +10.598 |
leigh | +10.591 |
Drew | +10.176 |
born | +10.061 |
pen | +9.772 |
Neg logit contributions | |
sidx | -14.635 |
untarily | -12.667 |
Norm | -12.167 |
itals | -10.915 |
ンジ | -10.818 |
Token | the |
Token ID | 262 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
leigh | +3.106 |
hyde | +3.058 |
pen | +2.927 |
Drew | +2.899 |
zinski | +2.890 |
Neg logit contributions | |
sidx | -2.824 |
Norm | -2.476 |
untarily | -2.254 |
warmed | -2.100 |
itals | -2.084 |
Token | deal |
Token ID | 1730 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
sidx | +1.824 |
Norm | +1.661 |
untarily | +1.489 |
warmed | +1.453 |
streng | +1.421 |
Neg logit contributions | |
leigh | -1.599 |
hyde | -1.595 |
zinski | -1.486 |
bane | -1.477 |
pen | -1.476 |
Token | after |
Token ID | 706 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
leigh | +3.853 |
hyde | +3.846 |
zinski | +3.588 |
pen | +3.582 |
Drew | +3.564 |
Neg logit contributions | |
sidx | -5.133 |
Norm | -4.574 |
untarily | -4.342 |
caffe | -3.997 |
itals | -3.996 |
Token | the |
Token ID | 262 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
sidx | +1.912 |
Norm | +1.747 |
untarily | +1.572 |
warmed | +1.513 |
streng | +1.487 |
Neg logit contributions | |
leigh | -1.633 |
hyde | -1.630 |
pen | -1.506 |
zinski | -1.506 |
bane | -1.491 |
Token | women |
Token ID | 1466 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
leigh | +3.257 |
hyde | +3.214 |
Drew | +3.025 |
pen | +3.008 |
zinski | +2.980 |
Neg logit contributions | |
sidx | -4.472 |
Norm | -3.874 |
untarily | -3.680 |
itals | -3.482 |
streng | -3.443 |
Token | could |
Token ID | 714 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
leigh | +2.833 |
hyde | +2.779 |
Drew | +2.630 |
pen | +2.620 |
bane | +2.597 |
Neg logit contributions | |
sidx | -3.498 |
Norm | -3.074 |
untarily | -2.879 |
streng | -2.701 |
itals | -2.690 |
Token | be |
Token ID | 307 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
leigh | +1.739 |
hyde | +1.706 |
pen | +1.612 |
zinski | +1.596 |
Drew | +1.593 |
Neg logit contributions | |
sidx | -2.313 |
Norm | -2.072 |
untarily | -1.904 |
warmed | -1.827 |
streng | -1.826 |
Token | jailed |
Token ID | 22159 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
sidx | +0.489 |
Norm | +0.438 |
untarily | +0.399 |
warmed | +0.380 |
streng | +0.374 |
Neg logit contributions | |
leigh | -0.458 |
hyde | -0.455 |
zinski | -0.427 |
pen | -0.424 |
bane | -0.420 |
Token | if |
Token ID | 611 |
Feature activation | -8.58e+00 |
Pos logit contributions | |
leigh | +3.080 |
hyde | +2.988 |
pen | +2.906 |
Drew | +2.868 |
zinski | +2.787 |
Neg logit contributions | |
sidx | -4.193 |
Norm | -3.687 |
untarily | -3.444 |
streng | -3.276 |
itals | -3.264 |
Token | they |
Token ID | 484 |
Feature activation | -1.95e+01 |
Pos logit contributions | |
leigh | +4.926 |
Drew | +4.766 |
hyde | +4.754 |
pen | +4.634 |
bane | +4.446 |
Neg logit contributions | |
sidx | -7.430 |
Norm | -6.422 |
untarily | -6.055 |
ンジ | -5.887 |
streng | -5.835 |
Token | were |
Token ID | 547 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
leigh | +9.896 |
Drew | +9.804 |
pen | +9.256 |
wordpress | +9.169 |
hyde | +9.123 |
Neg logit contributions | |
sidx | -14.467 |
Norm | -12.868 |
ンジ | -12.830 |
newcom | -11.958 |
untarily | -11.908 |
Token | found |
Token ID | 1043 |
Feature activation | -1.75e+01 |
Pos logit contributions | |
leigh | +6.956 |
Drew | +6.755 |
pen | +6.709 |
born | +6.603 |
hyde | +6.588 |
Neg logit contributions | |
sidx | -9.252 |
Norm | -7.858 |
untarily | -7.597 |
ンジ | -7.287 |
itals | -7.196 |
Token | looking |
Token ID | 2045 |
Feature activation | -8.60e+00 |
Pos logit contributions | |
leigh | +9.045 |
Drew | +8.562 |
hyde | +8.380 |
pen | +8.304 |
born | +8.188 |
Neg logit contributions | |
sidx | -13.866 |
Norm | -11.987 |
untarily | -11.844 |
streng | -11.291 |
ンジ | -11.259 |
Token | at |
Token ID | 379 |
Feature activation | -9.25e+00 |
Pos logit contributions | |
leigh | +5.380 |
hyde | +5.357 |
Drew | +5.203 |
pen | +5.135 |
bane | +5.103 |
Neg logit contributions | |
sidx | -6.999 |
Norm | -6.007 |
untarily | -5.630 |
streng | -5.317 |
itals | -5.256 |
Token | their |
Token ID | 511 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
leigh | +5.131 |
hyde | +5.049 |
Drew | +4.984 |
pen | +4.899 |
bane | +4.679 |
Neg logit contributions | |
sidx | -8.060 |
Norm | -6.969 |
untarily | -6.528 |
streng | -6.390 |
ンジ | -6.387 |
Token | x |
Token ID | 2124 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
leigh | +2.123 |
hyde | +2.040 |
Drew | +1.958 |
zinski | +1.955 |
pen | +1.950 |
Neg logit contributions | |
sidx | -3.842 |
Norm | -3.446 |
untarily | -3.349 |
streng | -3.292 |
itals | -3.171 |
Token | . |
Token ID | 13 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
leigh | +1.218 |
hyde | +1.184 |
zinski | +1.128 |
pen | +1.126 |
Drew | +1.115 |
Neg logit contributions | |
sidx | -1.636 |
Norm | -1.454 |
untarily | -1.364 |
streng | -1.354 |
warmed | -1.298 |
Token | x |
Token ID | 87 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
sidx | +2.949 |
Norm | +2.646 |
untarily | +2.326 |
itals | +2.182 |
warmed | +2.179 |
Neg logit contributions | |
hyde | -3.664 |
leigh | -3.638 |
Drew | -3.404 |
zinski | -3.381 |
appings | -3.375 |
Token | . |
Token ID | 13 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
sidx | +0.656 |
Norm | +0.591 |
untarily | +0.539 |
warmed | +0.514 |
itals | +0.507 |
Neg logit contributions | |
leigh | -0.561 |
hyde | -0.557 |
zinski | -0.519 |
pen | -0.517 |
bane | -0.512 |
Token | x |
Token ID | 87 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
sidx | +0.353 |
Norm | +0.314 |
untarily | +0.285 |
warmed | +0.270 |
streng | +0.267 |
Neg logit contributions | |
leigh | -0.356 |
hyde | -0.353 |
zinski | -0.332 |
pen | -0.331 |
bane | -0.328 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e+01 |
Pos logit contributions | |
leigh | +5.078 |
zinski | +4.605 |
Drew | +4.584 |
pen | +4.564 |
wordpress | +4.507 |
Neg logit contributions | |
sidx | -9.836 |
streng | -9.559 |
newcom | -8.946 |
Norm | -8.712 |
untarily | -8.451 |
Token | 150 |
Token ID | 8628 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
leigh | +8.246 |
pen | +7.406 |
wordpress | +7.269 |
hyde | +7.208 |
iddler | +6.867 |
Neg logit contributions | |
sidx | -17.254 |
streng | -16.302 |
Norm | -16.281 |
newcom | -15.199 |
caffe | -15.066 |
Token | 110 |
Token ID | 9796 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
leigh | +2.049 |
hyde | +2.026 |
Drew | +1.909 |
zinski | +1.893 |
pen | +1.876 |
Neg logit contributions | |
sidx | -2.919 |
Norm | -2.568 |
untarily | -2.465 |
streng | -2.352 |
warmed | -2.343 |
Token | 81 |
Token ID | 6659 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
sidx | +1.937 |
Norm | +1.738 |
untarily | +1.521 |
warmed | +1.432 |
itals | +1.431 |
Neg logit contributions | |
hyde | -2.303 |
leigh | -2.302 |
pen | -2.147 |
zinski | -2.145 |
Drew | -2.136 |
Token | 12 |
Token ID | 1065 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
sidx | +2.151 |
Norm | +1.941 |
untarily | +1.722 |
warmed | +1.644 |
itals | +1.608 |
Neg logit contributions | |
hyde | -2.134 |
leigh | -2.115 |
zinski | -1.971 |
pen | -1.939 |
bane | -1.932 |
Token | x |
Token ID | 2124 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
leigh | +1.920 |
hyde | +1.857 |
Drew | +1.771 |
pen | +1.767 |
zinski | +1.754 |
Neg logit contributions | |
sidx | -3.385 |
Norm | -3.043 |
untarily | -2.936 |
streng | -2.860 |
itals | -2.785 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
leigh | +2.144 |
hyde | +2.092 |
pen | +1.983 |
Drew | +1.982 |
zinski | +1.963 |
Neg logit contributions | |
sidx | -3.025 |
Norm | -2.656 |
untarily | -2.465 |
streng | -2.366 |
itals | -2.349 |
Token | north |
Token ID | 5093 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
leigh | +0.960 |
hyde | +0.938 |
Drew | +0.884 |
zinski | +0.883 |
pen | +0.881 |
Neg logit contributions | |
sidx | -1.288 |
Norm | -1.146 |
untarily | -1.070 |
itals | -1.012 |
warmed | -1.012 |
Token | but |
Token ID | 475 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
leigh | +1.958 |
hyde | +1.864 |
pen | +1.812 |
Drew | +1.783 |
zinski | +1.767 |
Neg logit contributions | |
sidx | -2.493 |
Norm | -2.212 |
untarily | -2.068 |
streng | -1.964 |
itals | -1.954 |
Token | dismissing |
Token ID | 37514 |
Feature activation | -1.76e+01 |
Pos logit contributions | |
leigh | +2.762 |
hyde | +2.709 |
Drew | +2.577 |
pen | +2.576 |
zinski | +2.549 |
Neg logit contributions | |
sidx | -3.514 |
Norm | -3.084 |
untarily | -2.891 |
ンジ | -2.708 |
itals | -2.690 |
Token | a |
Token ID | 257 |
Feature activation | -1.89e+01 |
Pos logit contributions | |
Drew | +9.211 |
pen | +9.029 |
leigh | +8.707 |
planetary | +8.456 |
Ultimate | +8.442 |
Neg logit contributions | |
sidx | -13.768 |
Norm | -11.189 |
untarily | -11.150 |
ンジ | -11.124 |
覚醒 | -10.981 |
Token | separate |
Token ID | 4553 |
Feature activation | -1.95e+01 |
Pos logit contributions | |
leigh | +10.174 |
Drew | +10.146 |
pen | +9.591 |
planetary | +9.501 |
born | +9.397 |
Neg logit contributions | |
sidx | -14.106 |
untarily | -11.477 |
itals | -11.364 |
Norm | -11.282 |
ンジ | -11.242 |
Token | attempt |
Token ID | 2230 |
Feature activation | -9.56e+00 |
Pos logit contributions | |
leigh | +9.995 |
Drew | +9.900 |
Ultimate | +9.344 |
planetary | +9.325 |
born | +9.278 |
Neg logit contributions | |
sidx | -14.753 |
untarily | -12.103 |
itals | -12.057 |
Norm | -11.883 |
ンジ | -11.861 |
Token | to |
Token ID | 284 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
leigh | +4.995 |
Drew | +4.824 |
hyde | +4.817 |
pen | +4.793 |
zinski | +4.611 |
Neg logit contributions | |
sidx | -8.393 |
Norm | -7.441 |
untarily | -6.997 |
streng | -6.722 |
ンジ | -6.721 |
Token | qu |
Token ID | 627 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
leigh | +3.525 |
hyde | +3.441 |
pen | +3.339 |
zinski | +3.339 |
bane | +3.300 |
Neg logit contributions | |
sidx | -4.238 |
Norm | -3.706 |
untarily | -3.394 |
warmed | -3.282 |
ンジ | -3.256 |
Token | ash |
Token ID | 1077 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
leigh | +1.978 |
hyde | +1.863 |
pen | +1.763 |
zinski | +1.744 |
Drew | +1.715 |
Neg logit contributions | |
sidx | -3.862 |
Norm | -3.539 |
untarily | -3.270 |
warmed | -3.211 |
streng | -3.202 |
Token | changes |
Token ID | 2458 |
Feature activation | -8.81e+00 |
Pos logit contributions | |
leigh | +8.448 |
Drew | +8.339 |
pen | +8.107 |
births | +8.037 |
ore | +7.809 |
Neg logit contributions | |
sidx | -12.826 |
Norm | -10.362 |
untarily | -10.178 |
ンジ | -10.106 |
itals | -9.850 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e+01 |
Pos logit contributions | |
leigh | +5.364 |
hyde | +5.300 |
Drew | +5.240 |
bane | +5.148 |
pen | +5.083 |
Neg logit contributions | |
sidx | -8.806 |
Norm | -7.775 |
untarily | -7.622 |
ンジ | -7.248 |
itals | -7.227 |
Token | newer |
Token ID | 15064 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
leigh | +7.670 |
Drew | +7.571 |
hyde | +7.389 |
Ultimate | +7.304 |
bane | +7.284 |
Neg logit contributions | |
sidx | -10.850 |
untarily | -9.249 |
Norm | -9.124 |
ンジ | -9.028 |
itals | -8.721 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
leigh | +7.699 |
Drew | +7.507 |
hyde | +7.289 |
bane | +7.274 |
Ultimate | +7.202 |
Neg logit contributions | |
sidx | -10.288 |
untarily | -8.645 |
Norm | -8.453 |
ンジ | -8.286 |
streng | -8.131 |
Token | improved |
Token ID | 6596 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
leigh | +9.896 |
Drew | +9.747 |
bane | +9.439 |
Ultimate | +9.422 |
hyde | +9.407 |
Neg logit contributions | |
sidx | -10.877 |
untarily | -9.045 |
Norm | -8.811 |
streng | -8.656 |
ンジ | -8.564 |
Token | variant |
Token ID | 15304 |
Feature activation | -9.67e+00 |
Pos logit contributions | |
leigh | +7.803 |
Drew | +7.555 |
hyde | +7.458 |
bane | +7.457 |
Ultimate | +7.366 |
Neg logit contributions | |
sidx | -10.170 |
untarily | -8.537 |
Norm | -8.384 |
ンジ | -8.065 |
streng | -8.015 |
Token | used |
Token ID | 973 |
Feature activation | -1.91e+01 |
Pos logit contributions | |
leigh | +5.713 |
hyde | +5.465 |
Drew | +5.402 |
bane | +5.305 |
pen | +5.272 |
Neg logit contributions | |
sidx | -7.993 |
Norm | -6.775 |
untarily | -6.737 |
streng | -6.380 |
itals | -6.302 |
Token | a |
Token ID | 257 |
Feature activation | -1.71e+01 |
Pos logit contributions | |
leigh | +11.142 |
Drew | +10.919 |
titanium | +10.633 |
pen | +10.494 |
planetary | +10.463 |
Neg logit contributions | |
sidx | -13.170 |
untarily | -10.887 |
ンジ | -10.605 |
Norm | -10.476 |
itals | -10.271 |
Token | " |
Token ID | 366 |
Feature activation | -9.15e+00 |
Pos logit contributions | |
leigh | +10.857 |
Drew | +10.614 |
titanium | +10.259 |
pen | +10.120 |
planetary | +10.095 |
Neg logit contributions | |
sidx | -11.784 |
untarily | -9.546 |
Norm | -9.327 |
ンジ | -9.132 |
itals | -8.988 |
Token | pe |
Token ID | 431 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
leigh | +6.357 |
hyde | +6.150 |
pen | +6.116 |
bane | +5.896 |
zinski | +5.787 |
Neg logit contributions | |
sidx | -7.006 |
Norm | -6.064 |
untarily | -5.530 |
streng | -5.450 |
warmed | -5.273 |
Token | ep |
Token ID | 538 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
sidx | +1.625 |
Norm | +1.467 |
untarily | +1.342 |
warmed | +1.285 |
itals | +1.265 |
Neg logit contributions | |
leigh | -1.395 |
hyde | -1.383 |
zinski | -1.282 |
Drew | -1.279 |
bane | -1.268 |
Token | " |
Token ID | 1 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
leigh | +3.773 |
hyde | +3.635 |
pen | +3.489 |
bane | +3.400 |
zinski | +3.388 |
Neg logit contributions | |
sidx | -5.093 |
Norm | -4.522 |
untarily | -4.231 |
streng | -4.005 |
warmed | -4.000 |
Token | week |
Token ID | 1285 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
leigh | +2.067 |
hyde | +1.997 |
Drew | +1.918 |
pen | +1.910 |
zinski | +1.883 |
Neg logit contributions | |
sidx | -3.188 |
Norm | -2.847 |
untarily | -2.672 |
streng | -2.546 |
itals | -2.543 |
Token | against |
Token ID | 1028 |
Feature activation | -8.49e+00 |
Pos logit contributions | |
leigh | +2.121 |
hyde | +2.075 |
Drew | +1.972 |
pen | +1.960 |
zinski | +1.933 |
Neg logit contributions | |
sidx | -2.618 |
Norm | -2.330 |
untarily | -2.169 |
streng | -2.055 |
itals | -2.042 |
Token | San |
Token ID | 2986 |
Feature activation | -9.36e+00 |
Pos logit contributions | |
Drew | +4.462 |
leigh | +4.370 |
hyde | +4.133 |
pen | +4.057 |
zinski | +3.881 |
Neg logit contributions | |
sidx | -7.904 |
Norm | -6.738 |
untarily | -6.682 |
pees | -6.429 |
streng | -6.408 |
Token | Diego |
Token ID | 9500 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
leigh | +5.085 |
hyde | +4.905 |
Drew | +4.849 |
pen | +4.799 |
born | +4.619 |
Neg logit contributions | |
sidx | -8.323 |
Norm | -7.443 |
untarily | -7.162 |
streng | -6.930 |
pees | -6.760 |
Token | when |
Token ID | 618 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
leigh | +3.030 |
hyde | +2.929 |
Drew | +2.845 |
pen | +2.786 |
zinski | +2.750 |
Neg logit contributions | |
sidx | -3.969 |
Norm | -3.514 |
untarily | -3.343 |
streng | -3.178 |
ンジ | -3.115 |
Token | he |
Token ID | 339 |
Feature activation | -1.89e+01 |
Pos logit contributions | |
Drew | +6.473 |
leigh | +6.201 |
pen | +5.850 |
hyde | +5.818 |
Stafford | +5.733 |
Neg logit contributions | |
sidx | -10.031 |
untarily | -8.359 |
Norm | -8.355 |
pees | -7.932 |
ンジ | -7.841 |
Token | scored |
Token ID | 7781 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Drew | +9.865 |
leigh | +9.627 |
pen | +8.695 |
hyde | +8.639 |
Stafford | +8.520 |
Neg logit contributions | |
sidx | -15.528 |
Norm | -13.105 |
untarily | -12.546 |
覚醒 | -12.341 |
ンジ | -12.055 |
Token | just |
Token ID | 655 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
sidx | +2.139 |
Norm | +1.952 |
untarily | +1.745 |
warmed | +1.680 |
itals | +1.638 |
Neg logit contributions | |
hyde | -2.076 |
leigh | -2.067 |
zinski | -1.924 |
pen | -1.894 |
appings | -1.889 |
Token | 15 |
Token ID | 1315 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
sidx | +4.208 |
Norm | +3.964 |
untarily | +3.502 |
warmed | +3.400 |
caffe | +3.264 |
Neg logit contributions | |
hyde | -4.366 |
leigh | -4.234 |
zinski | -3.994 |
appings | -3.940 |
bane | -3.900 |
Token | points |
Token ID | 2173 |
Feature activation | -9.59e+00 |
Pos logit contributions | |
leigh | +0.625 |
hyde | +0.616 |
pen | +0.581 |
zinski | +0.578 |
Drew | +0.575 |
Neg logit contributions | |
sidx | -0.733 |
Norm | -0.656 |
untarily | -0.606 |
warmed | -0.575 |
streng | -0.571 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
leigh | +5.576 |
Drew | +5.282 |
pen | +5.170 |
hyde | +5.101 |
zinski | +4.853 |
Neg logit contributions | |
sidx | -8.170 |
Norm | -7.148 |
untarily | -6.995 |
streng | -6.653 |
itals | -6.557 |
Token | 50 |
Token ID | 2026 |
Feature activation | -7.20e+00 |
Pos logit contributions | |
sidx | +1.628 |
Norm | +1.476 |
untarily | +1.338 |
warmed | +1.283 |
itals | +1.258 |
Neg logit contributions | |
hyde | -1.431 |
leigh | -1.426 |
zinski | -1.324 |
pen | -1.308 |
bane | -1.301 |
Token | , |
Token ID | 11 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
leigh | +2.984 |
hyde | +2.904 |
pen | +2.685 |
Drew | +2.646 |
bane | +2.611 |
Neg logit contributions | |
sidx | -7.397 |
Norm | -6.675 |
untarily | -6.471 |
streng | -6.192 |
warmed | -6.189 |
Token | characterized |
Token ID | 16264 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
leigh | +3.810 |
hyde | +3.765 |
pen | +3.603 |
Drew | +3.538 |
zinski | +3.538 |
Neg logit contributions | |
sidx | -4.866 |
Norm | -4.316 |
untarily | -4.113 |
itals | -3.837 |
ンジ | -3.794 |
Token | by |
Token ID | 416 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
leigh | +4.910 |
hyde | +4.891 |
pen | +4.650 |
zinski | +4.550 |
Drew | +4.531 |
Neg logit contributions | |
sidx | -9.256 |
Norm | -8.318 |
pees | -7.765 |
untarily | -7.763 |
warmed | -7.475 |
Token | multiple |
Token ID | 3294 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
pen | +8.448 |
leigh | +8.384 |
Drew | +8.294 |
hyde | +8.219 |
zinski | +7.915 |
Neg logit contributions | |
sidx | -10.924 |
untarily | -8.906 |
Norm | -8.784 |
itals | -8.365 |
pees | -8.340 |
Token | tiny |
Token ID | 7009 |
Feature activation | -1.89e+01 |
Pos logit contributions | |
pen | +8.135 |
leigh | +7.964 |
hyde | +7.726 |
Drew | +7.722 |
births | +7.525 |
Neg logit contributions | |
sidx | -11.023 |
Norm | -9.443 |
untarily | -9.340 |
pees | -8.741 |
ンジ | -8.434 |
Token | ker |
Token ID | 41927 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
pen | +10.722 |
leigh | +10.288 |
Drew | +10.080 |
hyde | +9.882 |
births | +9.616 |
Neg logit contributions | |
sidx | -13.590 |
Norm | -11.927 |
untarily | -11.632 |
pees | -10.986 |
ンジ | -10.805 |
Token | at |
Token ID | 265 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
leigh | +1.955 |
hyde | +1.940 |
pen | +1.868 |
zinski | +1.855 |
bane | +1.839 |
Neg logit contributions | |
sidx | -1.117 |
Norm | -0.949 |
untarily | -0.817 |
warmed | -0.761 |
streng | -0.753 |
Token | otic |
Token ID | 6210 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
hyde | +7.527 |
leigh | +7.486 |
pen | +7.408 |
zinski | +7.242 |
appings | +7.176 |
Neg logit contributions | |
sidx | -7.533 |
Norm | -6.944 |
streng | -6.113 |
untarily | -6.082 |
warmed | -6.044 |
Token | plugs |
Token ID | 37008 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
pen | +7.507 |
leigh | +7.477 |
Drew | +7.277 |
hyde | +7.256 |
births | +7.081 |
Neg logit contributions | |
sidx | -9.926 |
Norm | -8.469 |
untarily | -8.335 |
pees | -7.747 |
ンジ | -7.707 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
leigh | +3.840 |
hyde | +3.734 |
pen | +3.632 |
zinski | +3.514 |
Drew | +3.498 |
Neg logit contributions | |
sidx | -5.002 |
Norm | -4.439 |
untarily | -4.158 |
itals | -3.879 |
streng | -3.861 |
Token | in |
Token ID | 287 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
leigh | +3.473 |
hyde | +3.369 |
pen | +3.246 |
Drew | +3.243 |
zinski | +3.177 |
Neg logit contributions | |
sidx | -4.239 |
Norm | -3.680 |
untarily | -3.431 |
ンジ | -3.247 |
itals | -3.242 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
leigh | +2.144 |
hyde | +2.092 |
pen | +1.983 |
Drew | +1.982 |
zinski | +1.963 |
Neg logit contributions | |
sidx | -3.025 |
Norm | -2.656 |
untarily | -2.465 |
streng | -2.366 |
itals | -2.349 |
Token | north |
Token ID | 5093 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
leigh | +0.960 |
hyde | +0.938 |
Drew | +0.884 |
zinski | +0.883 |
pen | +0.881 |
Neg logit contributions | |
sidx | -1.288 |
Norm | -1.146 |
untarily | -1.070 |
itals | -1.012 |
warmed | -1.012 |
Token | but |
Token ID | 475 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
leigh | +1.958 |
hyde | +1.864 |
pen | +1.812 |
Drew | +1.783 |
zinski | +1.767 |
Neg logit contributions | |
sidx | -2.493 |
Norm | -2.212 |
untarily | -2.068 |
streng | -1.964 |
itals | -1.954 |
Token | dismissing |
Token ID | 37514 |
Feature activation | -1.76e+01 |
Pos logit contributions | |
leigh | +2.762 |
hyde | +2.709 |
Drew | +2.577 |
pen | +2.576 |
zinski | +2.549 |
Neg logit contributions | |
sidx | -3.514 |
Norm | -3.084 |
untarily | -2.891 |
ンジ | -2.708 |
itals | -2.690 |
Token | a |
Token ID | 257 |
Feature activation | -1.89e+01 |
Pos logit contributions | |
Drew | +9.211 |
pen | +9.029 |
leigh | +8.707 |
planetary | +8.456 |
Ultimate | +8.442 |
Neg logit contributions | |
sidx | -13.768 |
Norm | -11.189 |
untarily | -11.150 |
ンジ | -11.124 |
覚醒 | -10.981 |
Token | separate |
Token ID | 4553 |
Feature activation | -1.95e+01 |
Pos logit contributions | |
leigh | +10.174 |
Drew | +10.146 |
pen | +9.591 |
planetary | +9.501 |
born | +9.397 |
Neg logit contributions | |
sidx | -14.106 |
untarily | -11.477 |
itals | -11.364 |
Norm | -11.282 |
ンジ | -11.242 |
Token | attempt |
Token ID | 2230 |
Feature activation | -9.56e+00 |
Pos logit contributions | |
leigh | +9.995 |
Drew | +9.900 |
Ultimate | +9.344 |
planetary | +9.325 |
born | +9.278 |
Neg logit contributions | |
sidx | -14.753 |
untarily | -12.103 |
itals | -12.057 |
Norm | -11.883 |
ンジ | -11.861 |
Token | to |
Token ID | 284 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
leigh | +4.995 |
Drew | +4.824 |
hyde | +4.817 |
pen | +4.793 |
zinski | +4.611 |
Neg logit contributions | |
sidx | -8.393 |
Norm | -7.441 |
untarily | -6.997 |
streng | -6.722 |
ンジ | -6.721 |
Token | qu |
Token ID | 627 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
leigh | +3.525 |
hyde | +3.441 |
pen | +3.339 |
zinski | +3.339 |
bane | +3.300 |
Neg logit contributions | |
sidx | -4.238 |
Norm | -3.706 |
untarily | -3.394 |
warmed | -3.282 |
ンジ | -3.256 |
Token | ash |
Token ID | 1077 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
leigh | +1.978 |
hyde | +1.863 |
pen | +1.763 |
zinski | +1.744 |
Drew | +1.715 |
Neg logit contributions | |
sidx | -3.862 |
Norm | -3.539 |
untarily | -3.270 |
warmed | -3.211 |
streng | -3.202 |
Token | the |
Token ID | 262 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
leigh | +4.985 |
Drew | +4.820 |
hyde | +4.764 |
pen | +4.708 |
bane | +4.485 |
Neg logit contributions | |
sidx | -8.065 |
Norm | -6.923 |
untarily | -6.565 |
itals | -6.346 |
ンジ | -6.339 |
Token | integrity |
Token ID | 11540 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
leigh | +2.644 |
hyde | +2.589 |
Drew | +2.483 |
pen | +2.463 |
zinski | +2.442 |
Neg logit contributions | |
sidx | -3.078 |
Norm | -2.693 |
untarily | -2.507 |
warmed | -2.378 |
itals | -2.368 |
Token | of |
Token ID | 286 |
Feature activation | -1.68e+01 |
Pos logit contributions | |
sidx | +2.596 |
Norm | +2.334 |
untarily | +2.097 |
warmed | +2.014 |
itals | +1.996 |
Neg logit contributions | |
leigh | -2.379 |
hyde | -2.361 |
zinski | -2.200 |
bane | -2.172 |
pen | -2.169 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
Drew | +8.003 |
leigh | +7.659 |
hyde | +7.382 |
pen | +7.342 |
Ultimate | +7.328 |
Neg logit contributions | |
sidx | -14.369 |
Norm | -12.067 |
untarily | -11.547 |
pees | -11.380 |
warmed | -11.137 |
Token | functioning |
Token ID | 15025 |
Feature activation | -9.37e+00 |
Pos logit contributions | |
Drew | +7.461 |
leigh | +7.308 |
hyde | +7.046 |
Ultimate | +7.006 |
pen | +6.969 |
Neg logit contributions | |
sidx | -10.645 |
Norm | -8.908 |
untarily | -8.442 |
pees | -8.349 |
ンジ | -8.112 |
Token | of |
Token ID | 286 |
Feature activation | -1.87e+01 |
Pos logit contributions | |
leigh | +5.017 |
hyde | +4.924 |
Drew | +4.788 |
pen | +4.753 |
bane | +4.555 |
Neg logit contributions | |
sidx | -8.240 |
Norm | -7.353 |
untarily | -6.908 |
warmed | -6.745 |
pees | -6.736 |
Token | our |
Token ID | 674 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
Drew | +9.051 |
leigh | +8.693 |
hyde | +8.385 |
Ultimate | +8.372 |
pen | +8.290 |
Neg logit contributions | |
sidx | -15.119 |
Norm | -12.800 |
untarily | -12.074 |
pees | -11.957 |
warmed | -11.702 |
Token | financial |
Token ID | 3176 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
leigh | +6.069 |
Drew | +6.004 |
hyde | +5.825 |
pen | +5.772 |
Ultimate | +5.627 |
Neg logit contributions | |
sidx | -8.216 |
Norm | -7.025 |
untarily | -6.506 |
pees | -6.381 |
warmed | -6.223 |
Token | system |
Token ID | 1080 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
leigh | +1.485 |
hyde | +1.466 |
pen | +1.377 |
Drew | +1.370 |
zinski | +1.362 |
Neg logit contributions | |
sidx | -1.983 |
Norm | -1.757 |
untarily | -1.637 |
warmed | -1.549 |
streng | -1.538 |
Token | . |
Token ID | 13 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
leigh | +1.947 |
hyde | +1.911 |
pen | +1.801 |
Drew | +1.789 |
zinski | +1.786 |
Neg logit contributions | |
sidx | -2.546 |
Norm | -2.259 |
untarily | -2.099 |
warmed | -1.989 |
streng | -1.982 |
Token | Most |
Token ID | 4042 |
Feature activation | -9.54e+00 |
Pos logit contributions | |
leigh | +3.028 |
hyde | +2.942 |
Drew | +2.904 |
pen | +2.822 |
zinski | +2.814 |
Neg logit contributions | |
sidx | -4.022 |
Norm | -3.407 |
untarily | -3.311 |
streng | -3.234 |
warmed | -3.184 |
Token | is |
Token ID | 271 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
sidx | +1.315 |
Norm | +1.130 |
untarily | +0.990 |
warmed | +0.904 |
itals | +0.901 |
Neg logit contributions | |
leigh | -2.283 |
hyde | -2.277 |
zinski | -2.174 |
Drew | -2.165 |
bane | -2.142 |
Token | - |
Token ID | 12 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
sidx | +1.423 |
Norm | +1.280 |
untarily | +1.166 |
warmed | +1.105 |
itals | +1.094 |
Neg logit contributions | |
leigh | -1.351 |
hyde | -1.348 |
zinski | -1.257 |
pen | -1.247 |
Drew | -1.242 |
Token | the |
Token ID | 1169 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
sidx | +3.528 |
Norm | +3.204 |
untarily | +3.002 |
itals | +2.836 |
warmed | +2.792 |
Neg logit contributions | |
hyde | -3.241 |
leigh | -3.210 |
Drew | -3.068 |
zinski | -3.020 |
appings | -2.960 |
Token | - |
Token ID | 12 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
sidx | +2.559 |
Norm | +2.339 |
untarily | +2.101 |
warmed | +2.009 |
itals | +1.963 |
Neg logit contributions | |
leigh | -2.674 |
hyde | -2.669 |
zinski | -2.490 |
pen | -2.444 |
Drew | -2.437 |
Token | prime |
Token ID | 35505 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
leigh | +0.102 |
hyde | +0.101 |
zinski | +0.094 |
pen | +0.094 |
bane | +0.093 |
Neg logit contributions | |
sidx | -0.127 |
Norm | -0.114 |
untarily | -0.105 |
warmed | -0.100 |
streng | -0.100 |
Token | - |
Token ID | 12 |
Feature activation | -1.87e+01 |
Pos logit contributions | |
leigh | +6.098 |
hyde | +5.897 |
zinski | +5.842 |
Drew | +5.814 |
pen | +5.809 |
Neg logit contributions | |
sidx | -13.029 |
streng | -11.503 |
Norm | -11.091 |
untarily | -10.805 |
覚醒 | -10.578 |
Token | chall |
Token ID | 36747 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
pen | +7.313 |
hyde | +6.986 |
leigh | +6.937 |
inqu | +6.738 |
wordpress | +6.638 |
Neg logit contributions | |
sidx | -18.458 |
streng | -17.036 |
Norm | -16.248 |
newcom | -15.731 |
warmed | -15.513 |
Token | enge |
Token ID | 3540 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
leigh | +1.043 |
hyde | +1.033 |
pen | +0.971 |
zinski | +0.967 |
Drew | +0.958 |
Neg logit contributions | |
sidx | -1.213 |
Norm | -1.077 |
untarily | -0.989 |
warmed | -0.943 |
streng | -0.939 |
Token | - |
Token ID | 12 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
sidx | +3.862 |
Norm | +3.529 |
untarily | +3.170 |
warmed | +3.013 |
itals | +2.996 |
Neg logit contributions | |
leigh | -3.769 |
hyde | -3.758 |
pen | -3.537 |
zinski | -3.528 |
appings | -3.482 |
Token | 35 |
Token ID | 2327 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
sidx | +2.364 |
Norm | +2.121 |
untarily | +1.933 |
warmed | +1.834 |
itals | +1.815 |
Neg logit contributions | |
leigh | -2.450 |
hyde | -2.440 |
zinski | -2.332 |
Drew | -2.306 |
pen | -2.296 |
Token | 790 |
Token ID | 37750 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
sidx | +0.184 |
Norm | +0.163 |
untarily | +0.148 |
warmed | +0.140 |
itals | +0.138 |
Neg logit contributions | |
leigh | -0.191 |
hyde | -0.189 |
zinski | -0.178 |
pen | -0.177 |
Drew | -0.176 |
Token | / |
Token ID | 1220 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
hyde | +4.199 |
leigh | +4.188 |
pen | +3.988 |
Drew | +3.881 |
zinski | +3.868 |
Neg logit contributions | |
sidx | -5.692 |
Norm | -5.117 |
untarily | -4.821 |
pees | -4.673 |
warmed | -4.653 |
Token | @ |
Token ID | 31 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
leigh | +3.670 |
hyde | +3.652 |
pen | +3.490 |
Drew | +3.379 |
zinski | +3.370 |
Neg logit contributions | |
sidx | -4.665 |
Norm | -4.159 |
untarily | -3.966 |
warmed | -3.733 |
streng | -3.695 |
Token | Keys |
Token ID | 26363 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
hyde | +4.373 |
leigh | +4.334 |
pen | +4.095 |
Drew | +4.029 |
bane | +3.982 |
Neg logit contributions | |
sidx | -5.339 |
Norm | -4.804 |
untarily | -4.515 |
warmed | -4.325 |
streng | -4.267 |
Token | [ |
Token ID | 58 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
leigh | +6.889 |
hyde | +6.829 |
pen | +6.648 |
appings | +6.309 |
zinski | +6.303 |
Neg logit contributions | |
sidx | -9.274 |
Norm | -8.420 |
untarily | -8.020 |
streng | -7.823 |
warmed | -7.663 |
Token | step |
Token ID | 9662 |
Feature activation | -6.41e+00 |
Pos logit contributions | |
leigh | +6.401 |
hyde | +6.309 |
pen | +6.124 |
zinski | +5.758 |
appings | +5.751 |
Neg logit contributions | |
sidx | -8.074 |
Norm | -7.180 |
untarily | -6.728 |
streng | -6.519 |
warmed | -6.501 |
Token | Old |
Token ID | 19620 |
Feature activation | -1.87e+01 |
Pos logit contributions | |
leigh | +3.416 |
hyde | +3.347 |
pen | +3.178 |
zinski | +3.089 |
Drew | +3.078 |
Neg logit contributions | |
sidx | -5.825 |
Norm | -5.320 |
untarily | -4.981 |
streng | -4.829 |
warmed | -4.804 |
Token | ], |
Token ID | 4357 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
hyde | +9.698 |
leigh | +9.657 |
pen | +9.608 |
Drew | +9.052 |
bane | +8.958 |
Neg logit contributions | |
sidx | -13.482 |
Norm | -12.021 |
untarily | -11.683 |
pees | -11.596 |
streng | -11.355 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
leigh | +3.635 |
hyde | +3.611 |
pen | +3.396 |
Drew | +3.384 |
zinski | +3.363 |
Neg logit contributions | |
sidx | -4.048 |
Norm | -3.609 |
untarily | -3.384 |
warmed | -3.209 |
pees | -3.185 |
Token | ] |
Token ID | 60 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
leigh | +7.340 |
hyde | +7.245 |
pen | +7.106 |
zinski | +6.777 |
Drew | +6.772 |
Neg logit contributions | |
sidx | -10.280 |
Norm | -9.472 |
untarily | -9.095 |
pees | -8.757 |
streng | -8.719 |
Token | ], |
Token ID | 4357 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
leigh | +6.570 |
pen | +6.567 |
hyde | +6.489 |
Drew | +6.205 |
zinski | +6.193 |
Neg logit contributions | |
sidx | -9.122 |
Norm | -8.165 |
untarily | -7.928 |
streng | -7.541 |
warmed | -7.428 |
Token | step |
Token ID | 2239 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
leigh | +0.892 |
hyde | +0.885 |
zinski | +0.826 |
pen | +0.824 |
Drew | +0.818 |
Neg logit contributions | |
sidx | -1.114 |
Norm | -0.999 |
untarily | -0.925 |
warmed | -0.882 |
streng | -0.873 |
Token | D |
Token ID | 35 |
Feature activation | -7.73e+00 |
Pos logit contributions | |
leigh | +6.002 |
pen | +5.783 |
hyde | +5.663 |
Drew | +5.574 |
bane | +5.541 |
Neg logit contributions | |
sidx | -7.844 |
Norm | -6.772 |
streng | -6.266 |
untarily | -6.250 |
warmed | -6.036 |
Token | ale |
Token ID | 1000 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
leigh | +4.871 |
hyde | +4.729 |
pen | +4.645 |
zinski | +4.544 |
Drew | +4.535 |
Neg logit contributions | |
sidx | -6.682 |
Norm | -5.745 |
untarily | -5.371 |
streng | -5.250 |
warmed | -5.132 |
Token | Th |
Token ID | 536 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
sidx | +0.886 |
Norm | +0.786 |
untarily | +0.729 |
warmed | +0.694 |
streng | +0.690 |
Neg logit contributions | |
leigh | -0.672 |
hyde | -0.663 |
zinski | -0.620 |
pen | -0.615 |
Drew | -0.615 |
Token | ayer |
Token ID | 2794 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
leigh | +7.513 |
zinski | +7.306 |
pen | +7.176 |
appings | +6.798 |
hyde | +6.668 |
Neg logit contributions | |
sidx | -8.491 |
Norm | -7.255 |
streng | -6.919 |
ンジ | -6.830 |
warmed | -6.404 |
Token | : |
Token ID | 25 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
leigh | +4.164 |
hyde | +4.066 |
Drew | +3.866 |
pen | +3.865 |
zinski | +3.838 |
Neg logit contributions | |
sidx | -5.712 |
Norm | -5.012 |
untarily | -4.706 |
streng | -4.413 |
pees | -4.403 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.86e+01 |
Pos logit contributions | |
Drew | +6.534 |
leigh | +6.236 |
pen | +5.977 |
zinski | +5.961 |
hyde | +5.932 |
Neg logit contributions | |
sidx | -13.155 |
Norm | -11.621 |
untarily | -11.246 |
pees | -10.857 |
ンジ | -10.814 |
Token | . |
Token ID | 13 |
Feature activation | -7.76e+00 |
Pos logit contributions | |
Drew | +7.281 |
leigh | +6.809 |
pen | +6.713 |
bane | +6.465 |
Ultimate | +6.408 |
Neg logit contributions | |
sidx | -16.224 |
untarily | -15.071 |
streng | -14.931 |
Norm | -14.621 |
ンジ | -13.781 |
Token | 34 |
Token ID | 2682 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
leigh | +5.041 |
pen | +4.725 |
zinski | +4.667 |
Drew | +4.640 |
hyde | +4.638 |
Neg logit contributions | |
sidx | -6.371 |
Norm | -5.472 |
streng | -5.458 |
untarily | -5.300 |
warmed | -4.996 |
Token | ERA |
Token ID | 18802 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
leigh | +2.379 |
hyde | +2.316 |
Drew | +2.249 |
pen | +2.235 |
zinski | +2.175 |
Neg logit contributions | |
sidx | -5.221 |
Norm | -4.745 |
untarily | -4.552 |
itals | -4.306 |
streng | -4.306 |
Token | in |
Token ID | 287 |
Feature activation | -6.91e+00 |
Pos logit contributions | |
leigh | +5.936 |
Drew | +5.794 |
hyde | +5.655 |
pen | +5.558 |
zinski | +5.556 |
Neg logit contributions | |
sidx | -9.354 |
Norm | -8.505 |
untarily | -8.217 |
streng | -7.611 |
pees | -7.568 |
Token | 65 |
Token ID | 6135 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
leigh | +4.569 |
Drew | +4.418 |
zinski | +4.266 |
pen | +4.259 |
hyde | +4.241 |
Neg logit contributions | |
sidx | -5.491 |
Norm | -4.629 |
untarily | -4.506 |
streng | -4.337 |
itals | -4.236 |
Token | "] |
Token ID | 8973 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
hyde | +3.229 |
leigh | +3.227 |
pen | +3.034 |
Drew | +2.963 |
bane | +2.960 |
Neg logit contributions | |
sidx | -5.424 |
Norm | -4.937 |
untarily | -4.682 |
warmed | -4.479 |
streng | -4.462 |
Token | ' |
Token ID | 6 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
sidx | +2.910 |
Norm | +2.654 |
untarily | +2.405 |
warmed | +2.320 |
streng | +2.293 |
Neg logit contributions | |
leigh | -2.087 |
hyde | -2.065 |
zinski | -1.916 |
pen | -1.876 |
bane | -1.862 |
Token | ) |
Token ID | 1267 |
Feature activation | +8.40e+00 |
Pos logit contributions | |
sidx | +3.033 |
Norm | +2.612 |
untarily | +2.131 |
caffe | +2.003 |
warmed | +1.995 |
Neg logit contributions | |
leigh | -5.366 |
hyde | -5.299 |
zinski | -5.069 |
pen | -5.024 |
bane | -5.014 |
Token | AS |
Token ID | 7054 |
Feature activation | +9.30e+00 |
Pos logit contributions | |
sidx | +6.117 |
Norm | +5.620 |
untarily | +4.898 |
caffe | +4.760 |
warmed | +4.698 |
Neg logit contributions | |
leigh | -6.010 |
hyde | -5.947 |
zinski | -5.686 |
pen | -5.522 |
bane | -5.463 |
Token | library |
Token ID | 5888 |
Feature activation | +1.83e+01 |
Pos logit contributions | |
sidx | +6.924 |
Norm | +6.381 |
caffe | +5.544 |
streng | +5.475 |
untarily | +5.449 |
Neg logit contributions | |
leigh | -6.372 |
hyde | -6.287 |
zinski | -6.126 |
bane | -5.884 |
pen | -5.801 |
Token | , |
Token ID | 837 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
sidx | +11.540 |
Norm | +10.643 |
itals | +8.834 |
untarily | +8.780 |
caffe | +8.772 |
Neg logit contributions | |
leigh | -12.118 |
hyde | -11.910 |
zinski | -11.751 |
bane | -10.905 |
pen | -10.616 |
Token | REG |
Token ID | 23337 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
sidx | +9.711 |
Norm | +8.866 |
caffe | +7.833 |
streng | +7.696 |
warmed | +7.553 |
Neg logit contributions | |
leigh | -8.774 |
hyde | -8.650 |
zinski | -8.479 |
pen | -8.100 |
bane | -8.046 |
Token | EXP |
Token ID | 49864 |
Feature activation | +1.71e+01 |
Pos logit contributions | |
sidx | +7.559 |
Norm | +6.732 |
untarily | +5.485 |
ERC | +5.424 |
caffe | +5.416 |
Neg logit contributions | |
hyde | -11.339 |
leigh | -11.219 |
bane | -10.461 |
zinski | -10.459 |
pen | -10.369 |
Token | _ |
Token ID | 62 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
sidx | +9.412 |
Norm | +8.669 |
caffe | +7.051 |
itals | +6.868 |
untarily | +6.783 |
Neg logit contributions | |
leigh | -12.940 |
hyde | -12.623 |
zinski | -12.357 |
bane | -11.722 |
pen | -11.701 |
Token | EX |
Token ID | 6369 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
sidx | +3.354 |
Norm | +3.040 |
untarily | +2.696 |
warmed | +2.559 |
itals | +2.545 |
Neg logit contributions | |
hyde | -3.222 |
leigh | -3.201 |
zinski | -3.008 |
bane | -2.956 |
pen | -2.948 |
Token | TR |
Token ID | 5446 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
sidx | +3.855 |
Norm | +3.511 |
untarily | +3.102 |
warmed | +2.996 |
caffe | +2.971 |
Neg logit contributions | |
hyde | -3.114 |
leigh | -3.104 |
zinski | -2.918 |
bane | -2.865 |
pen | -2.863 |
Token | ory |
Token ID | 652 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
sidx | +3.832 |
Norm | +3.429 |
untarily | +3.046 |
itals | +2.820 |
warmed | +2.770 |
Neg logit contributions | |
leigh | -5.564 |
hyde | -5.539 |
zinski | -5.178 |
pen | -5.134 |
bane | -5.094 |
Token | , |
Token ID | 11 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
leigh | +0.495 |
hyde | +0.490 |
zinski | +0.460 |
pen | +0.459 |
Drew | +0.454 |
Neg logit contributions | |
sidx | -0.573 |
Norm | -0.513 |
untarily | -0.471 |
warmed | -0.447 |
streng | -0.443 |
Token | however |
Token ID | 2158 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
sidx | +0.271 |
Norm | +0.243 |
untarily | +0.222 |
warmed | +0.212 |
streng | +0.209 |
Neg logit contributions | |
leigh | -0.235 |
hyde | -0.233 |
zinski | -0.218 |
pen | -0.217 |
bane | -0.215 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
sidx | +3.450 |
Norm | +3.129 |
warmed | +2.757 |
untarily | +2.740 |
caffe | +2.664 |
Neg logit contributions | |
leigh | -3.832 |
hyde | -3.822 |
zinski | -3.567 |
pen | -3.512 |
wordpress | -3.492 |
Token | would |
Token ID | 561 |
Feature activation | +6.04e+00 |
Pos logit contributions | |
sidx | +1.664 |
Norm | +1.513 |
untarily | +1.367 |
warmed | +1.330 |
itals | +1.299 |
Neg logit contributions | |
leigh | -1.448 |
hyde | -1.436 |
zinski | -1.336 |
pen | -1.321 |
bane | -1.315 |
Token | put |
Token ID | 1234 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
sidx | +4.455 |
Norm | +4.052 |
untarily | +3.618 |
warmed | +3.542 |
streng | +3.501 |
Neg logit contributions | |
leigh | -4.327 |
hyde | -4.258 |
zinski | -3.957 |
appings | -3.954 |
pen | -3.910 |
Token | wind |
Token ID | 2344 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Norm | +9.621 |
sidx | +9.497 |
warmed | +8.070 |
untarily | +7.868 |
streng | +7.751 |
Neg logit contributions | |
leigh | -10.697 |
hyde | -10.559 |
bane | -9.849 |
zinski | -9.772 |
wordpress | -9.529 |
Token | at |
Token ID | 379 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
leigh | +1.102 |
hyde | +1.090 |
pen | +1.024 |
zinski | +1.018 |
Drew | +1.005 |
Neg logit contributions | |
sidx | -1.380 |
Norm | -1.245 |
untarily | -1.144 |
warmed | -1.084 |
itals | -1.077 |
Token | the |
Token ID | 262 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
sidx | +3.069 |
Norm | +2.802 |
untarily | +2.485 |
warmed | +2.433 |
itals | +2.397 |
Neg logit contributions | |
leigh | -2.856 |
hyde | -2.843 |
zinski | -2.652 |
bane | -2.628 |
pen | -2.603 |
Token | back |
Token ID | 736 |
Feature activation | -7.30e+00 |
Pos logit contributions | |
sidx | +0.852 |
Norm | +0.761 |
untarily | +0.688 |
warmed | +0.662 |
itals | +0.650 |
Neg logit contributions | |
leigh | -0.829 |
hyde | -0.822 |
zinski | -0.770 |
bane | -0.761 |
pen | -0.760 |
Token | of |
Token ID | 286 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
leigh | +4.071 |
pen | +3.834 |
hyde | +3.804 |
Drew | +3.637 |
bane | +3.619 |
Neg logit contributions | |
sidx | -6.376 |
Norm | -5.969 |
untarily | -5.575 |
streng | -5.311 |
warmed | -5.195 |
Token | CON |
Token ID | 7102 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
sidx | +4.753 |
Norm | +4.389 |
warmed | +3.714 |
untarily | +3.707 |
caffe | +3.565 |
Neg logit contributions | |
hyde | -5.419 |
leigh | -5.291 |
appings | -4.939 |
pen | -4.886 |
zinski | -4.867 |
Token | NECT |
Token ID | 48842 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
sidx | +1.936 |
Norm | +1.748 |
untarily | +1.564 |
warmed | +1.464 |
caffe | +1.435 |
Neg logit contributions | |
hyde | -2.009 |
leigh | -1.981 |
zinski | -1.868 |
pen | -1.855 |
appings | -1.853 |
Token | IT |
Token ID | 7283 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
sidx | +0.941 |
Norm | +0.853 |
untarily | +0.775 |
warmed | +0.741 |
itals | +0.727 |
Neg logit contributions | |
leigh | -0.801 |
hyde | -0.796 |
zinski | -0.741 |
pen | -0.736 |
bane | -0.728 |
Token | TO |
Token ID | 5390 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
sidx | +3.714 |
Norm | +3.390 |
untarily | +2.951 |
warmed | +2.858 |
caffe | +2.775 |
Neg logit contributions | |
hyde | -3.876 |
leigh | -3.811 |
zinski | -3.569 |
appings | -3.521 |
pen | -3.519 |
Token | A |
Token ID | 317 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
sidx | +4.640 |
Norm | +4.357 |
untarily | +3.729 |
warmed | +3.648 |
caffe | +3.595 |
Neg logit contributions | |
hyde | -4.539 |
leigh | -4.539 |
appings | -4.261 |
zinski | -4.218 |
pen | -4.124 |
Token | USB |
Token ID | 8450 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
sidx | +7.619 |
Norm | +7.502 |
warmed | +5.967 |
caffe | +5.962 |
mono | +5.896 |
Neg logit contributions | |
hyde | -9.047 |
leigh | -9.002 |
appings | -8.883 |
zinski | -8.445 |
pen | -8.252 |
Token | P |
Token ID | 350 |
Feature activation | +7.93e+00 |
Pos logit contributions | |
sidx | +8.840 |
Norm | +8.421 |
caffe | +6.962 |
warmed | +6.933 |
mono | +6.795 |
Neg logit contributions | |
hyde | -9.492 |
leigh | -9.482 |
zinski | -9.055 |
appings | -9.007 |
pen | -8.573 |
Token | ORT |
Token ID | 9863 |
Feature activation | +9.17e+00 |
Pos logit contributions | |
sidx | +5.301 |
Norm | +4.839 |
itals | +4.066 |
warmed | +4.044 |
untarily | +4.021 |
Neg logit contributions | |
hyde | -5.969 |
leigh | -5.806 |
zinski | -5.533 |
appings | -5.428 |
Drew | -5.357 |
Token | ON |
Token ID | 6177 |
Feature activation | +6.67e+00 |
Pos logit contributions | |
sidx | +6.184 |
Norm | +5.647 |
warmed | +4.782 |
untarily | +4.777 |
caffe | +4.726 |
Neg logit contributions | |
hyde | -6.849 |
leigh | -6.700 |
zinski | -6.364 |
appings | -6.343 |
pen | -6.300 |
Token | A |
Token ID | 317 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
sidx | +4.581 |
Norm | +4.304 |
untarily | +3.675 |
warmed | +3.529 |
caffe | +3.522 |
Neg logit contributions | |
leigh | -5.009 |
hyde | -5.008 |
appings | -4.671 |
zinski | -4.643 |
pen | -4.571 |
Token | COMP |
Token ID | 24301 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
sidx | +4.372 |
Norm | +4.051 |
untarily | +3.467 |
warmed | +3.394 |
caffe | +3.350 |
Neg logit contributions | |
hyde | -4.512 |
leigh | -4.494 |
appings | -4.234 |
zinski | -4.206 |
pen | -4.148 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
sidx | +1.882 |
Norm | +1.715 |
untarily | +1.556 |
warmed | +1.484 |
itals | +1.467 |
Neg logit contributions | |
hyde | -1.538 |
leigh | -1.536 |
zinski | -1.423 |
pen | -1.418 |
bane | -1.397 |
Token | year |
Token ID | 614 |
Feature activation | +6.23e+00 |
Pos logit contributions | |
leigh | +0.736 |
hyde | +0.717 |
zinski | +0.679 |
Drew | +0.678 |
pen | +0.676 |
Neg logit contributions | |
sidx | -0.959 |
Norm | -0.850 |
untarily | -0.796 |
streng | -0.762 |
warmed | -0.758 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
sidx | +4.793 |
Norm | +4.379 |
untarily | +3.889 |
warmed | +3.760 |
streng | +3.645 |
Neg logit contributions | |
hyde | -4.339 |
leigh | -4.265 |
zinski | -4.008 |
bane | -3.984 |
pen | -3.910 |
Token | He |
Token ID | 679 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
sidx | +1.697 |
Norm | +1.565 |
untarily | +1.353 |
warmed | +1.291 |
itals | +1.273 |
Neg logit contributions | |
leigh | -1.807 |
hyde | -1.803 |
zinski | -1.685 |
pen | -1.669 |
bane | -1.664 |
Token | was |
Token ID | 373 |
Feature activation | +8.30e+00 |
Pos logit contributions | |
sidx | +3.274 |
Norm | +3.059 |
warmed | +2.727 |
untarily | +2.727 |
caffe | +2.582 |
Neg logit contributions | |
hyde | -3.238 |
leigh | -3.156 |
zinski | -2.985 |
pen | -2.970 |
bane | -2.960 |
Token | the |
Token ID | 262 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
sidx | +5.675 |
Norm | +5.463 |
warmed | +4.671 |
untarily | +4.661 |
caffe | +4.527 |
Neg logit contributions | |
hyde | -6.272 |
leigh | -5.948 |
zinski | -5.686 |
appings | -5.611 |
wordpress | -5.574 |
Token | first |
Token ID | 717 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
Norm | +9.485 |
sidx | +9.338 |
untarily | +7.788 |
warmed | +7.576 |
caffe | +7.551 |
Neg logit contributions | |
hyde | -10.773 |
leigh | -9.967 |
bane | -9.637 |
appings | -9.432 |
zinski | -9.397 |
Token | freshman |
Token ID | 18621 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
sidx | +9.389 |
Norm | +9.379 |
untarily | +8.007 |
warmed | +7.813 |
mono | +7.772 |
Neg logit contributions | |
hyde | -10.049 |
leigh | -9.422 |
appings | -9.092 |
bane | -9.042 |
zinski | -8.983 |
Token | to |
Token ID | 284 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
sidx | +6.752 |
Norm | +6.439 |
warmed | +5.457 |
untarily | +5.436 |
caffe | +5.230 |
Neg logit contributions | |
hyde | -7.976 |
leigh | -7.700 |
wordpress | -7.310 |
appings | -7.222 |
bane | -7.196 |
Token | win |
Token ID | 1592 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
sidx | +0.372 |
Norm | +0.336 |
untarily | +0.308 |
warmed | +0.293 |
itals | +0.289 |
Neg logit contributions | |
leigh | -0.311 |
hyde | -0.308 |
zinski | -0.288 |
pen | -0.286 |
bane | -0.284 |
Token | ACC |
Token ID | 15859 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
sidx | +7.312 |
Norm | +7.236 |
untarily | +5.979 |
warmed | +5.863 |
caffe | +5.817 |
Neg logit contributions | |
hyde | -8.006 |
leigh | -7.867 |
zinski | -7.540 |
bane | -7.437 |
appings | -7.331 |
Token | Write |
Token ID | 19430 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
sidx | +2.830 |
Norm | +2.612 |
untarily | +2.355 |
warmed | +2.248 |
streng | +2.236 |
Neg logit contributions | |
leigh | -2.209 |
hyde | -2.180 |
zinski | -2.048 |
pen | -2.007 |
bane | -1.995 |
Token | - |
Token ID | 12 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
leigh | +0.510 |
hyde | +0.501 |
pen | +0.472 |
zinski | +0.472 |
Drew | +0.467 |
Neg logit contributions | |
sidx | -0.599 |
Norm | -0.533 |
untarily | -0.490 |
streng | -0.473 |
warmed | -0.469 |
Token | Warning |
Token ID | 20361 |
Feature activation | +9.87e+00 |
Pos logit contributions | |
sidx | +2.214 |
Norm | +2.045 |
untarily | +1.886 |
warmed | +1.799 |
itals | +1.791 |
Neg logit contributions | |
leigh | -1.349 |
hyde | -1.347 |
zinski | -1.242 |
bane | -1.213 |
Drew | -1.210 |
Token | - |
Token ID | 532 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
sidx | +7.255 |
Norm | +6.664 |
untarily | +5.923 |
warmed | +5.487 |
mono | +5.457 |
Neg logit contributions | |
leigh | -6.765 |
hyde | -6.595 |
zinski | -6.527 |
appings | -6.240 |
bane | -6.191 |
Token | Message |
Token ID | 12837 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
sidx | +2.630 |
Norm | +2.384 |
untarily | +2.097 |
warmed | +1.968 |
itals | +1.931 |
Neg logit contributions | |
hyde | -2.995 |
leigh | -2.968 |
zinski | -2.788 |
pen | -2.748 |
Drew | -2.738 |
Token | " |
Token ID | 366 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
sidx | +2.373 |
Norm | +2.167 |
untarily | +1.970 |
warmed | +1.884 |
streng | +1.875 |
Neg logit contributions | |
leigh | -1.809 |
hyde | -1.774 |
zinski | -1.671 |
bane | -1.644 |
pen | -1.640 |
Token | F |
Token ID | 37 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
sidx | +9.308 |
Norm | +9.142 |
untarily | +8.127 |
itals | +7.773 |
warmed | +7.737 |
Neg logit contributions | |
hyde | -8.598 |
leigh | -8.453 |
zinski | -7.984 |
bane | -7.876 |
Drew | -7.711 |
Token | ailed |
Token ID | 6255 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
leigh | +1.524 |
hyde | +1.473 |
pen | +1.394 |
zinski | +1.384 |
bane | +1.370 |
Neg logit contributions | |
sidx | -2.043 |
Norm | -1.862 |
streng | -1.675 |
untarily | -1.668 |
warmed | -1.626 |
Token | to |
Token ID | 284 |
Feature activation | +9.56e+00 |
Pos logit contributions | |
sidx | +7.044 |
Norm | +6.246 |
untarily | +5.514 |
streng | +5.243 |
warmed | +5.230 |
Neg logit contributions | |
leigh | -8.369 |
hyde | -8.321 |
zinski | -7.986 |
bane | -7.922 |
wordpress | -7.683 |
Token | $ |
Token ID | 720 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
sidx | +5.965 |
Norm | +5.455 |
untarily | +4.695 |
streng | +4.471 |
caffe | +4.425 |
Neg logit contributions | |
leigh | -7.824 |
hyde | -7.617 |
zinski | -7.173 |
wordpress | -7.047 |
bane | -7.025 |
Token | ($ |
Token ID | 16763 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
leigh | +0.653 |
hyde | +0.649 |
pen | +0.591 |
zinski | +0.582 |
bane | +0.576 |
Neg logit contributions | |
sidx | -1.348 |
Norm | -1.233 |
untarily | -1.151 |
warmed | -1.111 |
streng | -1.104 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
sidx | +0.002 |
Norm | +0.001 |
untarily | +0.001 |
warmed | +0.001 |
streng | +0.001 |
Neg logit contributions | |
leigh | -0.001 |
hyde | -0.001 |
zinski | -0.001 |
pen | -0.001 |
Drew | -0.001 |
Token | top |
Token ID | 1353 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
leigh | +1.128 |
hyde | +1.107 |
zinski | +1.043 |
pen | +1.041 |
Drew | +1.039 |
Neg logit contributions | |
sidx | -1.358 |
Norm | -1.210 |
untarily | -1.119 |
warmed | -1.061 |
itals | -1.056 |
Token | leadership |
Token ID | 5531 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
leigh | +4.647 |
hyde | +4.504 |
Drew | +4.413 |
pen | +4.361 |
zinski | +4.263 |
Neg logit contributions | |
sidx | -6.078 |
Norm | -5.359 |
untarily | -5.049 |
itals | -4.798 |
warmed | -4.780 |
Token | . |
Token ID | 13 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
leigh | +3.333 |
hyde | +3.251 |
pen | +3.109 |
zinski | +3.096 |
Drew | +3.095 |
Neg logit contributions | |
sidx | -3.539 |
Norm | -3.106 |
untarily | -2.888 |
warmed | -2.700 |
itals | -2.695 |
Token | Instead |
Token ID | 5455 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
leigh | +0.411 |
hyde | +0.406 |
zinski | +0.382 |
pen | +0.381 |
Drew | +0.379 |
Neg logit contributions | |
sidx | -0.475 |
Norm | -0.422 |
untarily | -0.391 |
warmed | -0.371 |
streng | -0.369 |
Token | he |
Token ID | 339 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
sidx | +0.560 |
Norm | +0.504 |
untarily | +0.458 |
warmed | +0.436 |
itals | +0.430 |
Neg logit contributions | |
leigh | -0.513 |
hyde | -0.510 |
zinski | -0.476 |
pen | -0.473 |
bane | -0.470 |
Token | named |
Token ID | 3706 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
sidx | +1.715 |
Norm | +1.557 |
untarily | +1.404 |
warmed | +1.370 |
streng | +1.330 |
Neg logit contributions | |
leigh | -1.666 |
hyde | -1.665 |
zinski | -1.559 |
pen | -1.545 |
bane | -1.533 |
Token | Cohn |
Token ID | 45005 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
leigh | +0.862 |
hyde | +0.848 |
pen | +0.801 |
Drew | +0.801 |
zinski | +0.799 |
Neg logit contributions | |
sidx | -1.016 |
Norm | -0.893 |
untarily | -0.830 |
warmed | -0.787 |
itals | -0.783 |
Token | , |
Token ID | 11 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
sidx | +0.351 |
Norm | +0.316 |
untarily | +0.289 |
warmed | +0.276 |
streng | +0.272 |
Neg logit contributions | |
leigh | -0.298 |
hyde | -0.295 |
zinski | -0.276 |
pen | -0.275 |
bane | -0.272 |
Token | his |
Token ID | 465 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
sidx | +2.022 |
Norm | +1.852 |
untarily | +1.661 |
warmed | +1.604 |
streng | +1.578 |
Neg logit contributions | |
leigh | -1.792 |
hyde | -1.785 |
zinski | -1.655 |
pen | -1.641 |
bane | -1.639 |
Token | long |
Token ID | 890 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
sidx | +0.748 |
Norm | +0.677 |
untarily | +0.618 |
warmed | +0.592 |
streng | +0.583 |
Neg logit contributions | |
leigh | -0.612 |
hyde | -0.609 |
zinski | -0.566 |
pen | -0.564 |
bane | -0.558 |
Token | in |
Token ID | 287 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
leigh | +1.059 |
hyde | +1.055 |
Drew | +0.990 |
pen | +0.986 |
zinski | +0.985 |
Neg logit contributions | |
sidx | -1.269 |
Norm | -1.127 |
untarily | -1.047 |
itals | -0.980 |
warmed | -0.973 |
Token | on |
Token ID | 319 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
leigh | +0.771 |
hyde | +0.768 |
zinski | +0.718 |
pen | +0.717 |
Drew | +0.712 |
Neg logit contributions | |
sidx | -0.926 |
Norm | -0.828 |
untarily | -0.764 |
warmed | -0.723 |
itals | -0.719 |
Token | the |
Token ID | 262 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
hyde | +4.114 |
leigh | +4.023 |
Drew | +3.964 |
pen | +3.926 |
zinski | +3.758 |
Neg logit contributions | |
sidx | -6.063 |
Norm | -5.259 |
untarily | -5.010 |
itals | -4.730 |
warmed | -4.720 |
Token | action |
Token ID | 2223 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
hyde | +4.028 |
leigh | +3.995 |
Drew | +3.892 |
pen | +3.811 |
zinski | +3.732 |
Neg logit contributions | |
sidx | -5.735 |
Norm | -4.937 |
untarily | -4.762 |
itals | -4.510 |
ンジ | -4.509 |
Token | . |
Token ID | 13 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
leigh | +1.013 |
hyde | +1.001 |
pen | +0.938 |
zinski | +0.937 |
Drew | +0.929 |
Neg logit contributions | |
sidx | -1.237 |
Norm | -1.105 |
untarily | -1.019 |
warmed | -0.966 |
itals | -0.961 |
Token | These |
Token ID | 2312 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
leigh | +2.103 |
hyde | +2.062 |
Drew | +1.985 |
zinski | +1.953 |
pen | +1.953 |
Neg logit contributions | |
sidx | -2.600 |
Norm | -2.246 |
untarily | -2.159 |
streng | -2.049 |
warmed | -2.040 |
Token | two |
Token ID | 734 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
sidx | +2.362 |
Norm | +2.168 |
untarily | +1.922 |
warmed | +1.885 |
streng | +1.865 |
Neg logit contributions | |
hyde | -2.256 |
leigh | -2.242 |
zinski | -2.082 |
pen | -2.057 |
bane | -2.028 |
Token | lead |
Token ID | 1085 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
sidx | +3.075 |
Norm | +2.849 |
untarily | +2.519 |
warmed | +2.493 |
streng | +2.454 |
Neg logit contributions | |
hyde | -2.718 |
leigh | -2.702 |
zinski | -2.503 |
pen | -2.468 |
bane | -2.428 |
Token | the |
Token ID | 262 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
leigh | +0.112 |
hyde | +0.111 |
zinski | +0.103 |
pen | +0.103 |
Drew | +0.102 |
Neg logit contributions | |
sidx | -0.141 |
Norm | -0.127 |
untarily | -0.117 |
warmed | -0.112 |
streng | -0.110 |
Token | team |
Token ID | 1074 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
leigh | +0.401 |
hyde | +0.397 |
zinski | +0.372 |
pen | +0.371 |
Drew | +0.368 |
Neg logit contributions | |
sidx | -0.461 |
Norm | -0.411 |
untarily | -0.378 |
warmed | -0.359 |
streng | -0.355 |
Token | in |
Token ID | 287 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
sidx | +2.821 |
Norm | +2.554 |
untarily | +2.258 |
warmed | +2.196 |
streng | +2.138 |
Neg logit contributions | |
leigh | -2.864 |
hyde | -2.855 |
zinski | -2.674 |
pen | -2.644 |
bane | -2.624 |
Token | 1 |
Token ID | 16 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
sidx | +3.952 |
Norm | +3.617 |
untarily | +3.269 |
itals | +3.122 |
warmed | +3.107 |
Neg logit contributions | |
leigh | -3.583 |
hyde | -3.539 |
zinski | -3.338 |
Drew | -3.321 |
appings | -3.299 |
Token | st |
Token ID | 301 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
hyde | +2.842 |
leigh | +2.840 |
pen | +2.673 |
zinski | +2.646 |
bane | +2.611 |
Neg logit contributions | |
sidx | -3.593 |
Norm | -3.241 |
untarily | -2.991 |
warmed | -2.858 |
streng | -2.832 |
Token | ) |
Token ID | 8 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
leigh | +0.232 |
hyde | +0.229 |
zinski | +0.214 |
pen | +0.214 |
Drew | +0.211 |
Neg logit contributions | |
sidx | -0.287 |
Norm | -0.258 |
untarily | -0.238 |
warmed | -0.226 |
streng | -0.224 |
Token | on |
Token ID | 319 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
sidx | +0.218 |
Norm | +0.196 |
untarily | +0.179 |
warmed | +0.171 |
streng | +0.169 |
Neg logit contributions | |
leigh | -0.182 |
hyde | -0.181 |
zinski | -0.169 |
pen | -0.168 |
bane | -0.166 |
Token | Dec |
Token ID | 4280 |
Feature activation | +9.58e+00 |
Pos logit contributions | |
leigh | +2.247 |
hyde | +2.138 |
Drew | +2.085 |
pen | +2.050 |
zinski | +2.044 |
Neg logit contributions | |
sidx | -3.565 |
Norm | -3.169 |
untarily | -3.043 |
streng | -2.952 |
warmed | -2.905 |
Token | 30 |
Token ID | 1542 |
Feature activation | +7.84e+00 |
Pos logit contributions | |
sidx | +6.604 |
Norm | +6.194 |
untarily | +5.370 |
warmed | +5.048 |
itals | +4.982 |
Neg logit contributions | |
hyde | -7.259 |
leigh | -6.605 |
appings | -6.349 |
zinski | -6.212 |
bane | -6.153 |
Token | , |
Token ID | 11 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
sidx | +5.269 |
Norm | +4.562 |
untarily | +4.014 |
warmed | +3.830 |
itals | +3.672 |
Neg logit contributions | |
hyde | -6.356 |
leigh | -6.068 |
appings | -5.788 |
zinski | -5.687 |
pen | -5.637 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
sidx | +2.570 |
Norm | +2.305 |
untarily | +2.069 |
warmed | +1.975 |
itals | +1.947 |
Neg logit contributions | |
hyde | -2.461 |
leigh | -2.408 |
zinski | -2.227 |
appings | -2.216 |
pen | -2.214 |
Token | at |
Token ID | 379 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
hyde | +2.122 |
leigh | +2.121 |
zinski | +2.023 |
Drew | +2.023 |
pen | +2.008 |
Neg logit contributions | |
sidx | -1.913 |
Norm | -1.681 |
untarily | -1.537 |
streng | -1.520 |
warmed | -1.447 |
Token | 10 |
Token ID | 838 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
leigh | +4.644 |
Drew | +4.605 |
bane | +4.136 |
Ultimate | +4.122 |
pen | +4.090 |
Neg logit contributions | |
sidx | -10.351 |
streng | -9.129 |
untarily | -8.972 |
Norm | -8.886 |
pees | -8.726 |
Token | : |
Token ID | 25 |
Feature activation | -6.93e+00 |
Pos logit contributions | |
leigh | +4.236 |
hyde | +3.971 |
pen | +3.917 |
Drew | +3.914 |
zinski | +3.845 |
Neg logit contributions | |
sidx | -6.771 |
Norm | -6.105 |
streng | -6.073 |
untarily | -5.852 |
warmed | -5.569 |
Token | or |
Token ID | 393 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
sidx | +0.837 |
Norm | +0.751 |
untarily | +0.684 |
warmed | +0.654 |
itals | +0.645 |
Neg logit contributions | |
leigh | -0.739 |
hyde | -0.734 |
zinski | -0.689 |
pen | -0.683 |
bane | -0.677 |
Token | roomm |
Token ID | 26255 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
leigh | +2.006 |
hyde | +1.993 |
Drew | +1.883 |
zinski | +1.859 |
pen | +1.854 |
Neg logit contributions | |
sidx | -2.478 |
Norm | -2.199 |
untarily | -2.046 |
warmed | -1.933 |
streng | -1.924 |
Token | ates |
Token ID | 689 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
sidx | +1.653 |
Norm | +1.476 |
untarily | +1.333 |
itals | +1.246 |
warmed | +1.240 |
Neg logit contributions | |
leigh | -1.877 |
hyde | -1.856 |
zinski | -1.760 |
pen | -1.735 |
Drew | -1.729 |
Token | , |
Token ID | 11 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
sidx | +3.582 |
Norm | +3.195 |
untarily | +2.855 |
warmed | +2.777 |
itals | +2.736 |
Neg logit contributions | |
hyde | -3.440 |
leigh | -3.431 |
zinski | -3.258 |
pen | -3.191 |
bane | -3.179 |
Token | for |
Token ID | 329 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
sidx | +2.789 |
Norm | +2.529 |
untarily | +2.258 |
warmed | +2.168 |
itals | +2.144 |
Neg logit contributions | |
leigh | -2.817 |
hyde | -2.810 |
zinski | -2.630 |
pen | -2.600 |
bane | -2.592 |
Token | example |
Token ID | 1672 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
leigh | +0.256 |
hyde | +0.254 |
zinski | +0.236 |
pen | +0.235 |
Drew | +0.233 |
Neg logit contributions | |
sidx | -0.334 |
Norm | -0.301 |
untarily | -0.277 |
warmed | -0.264 |
itals | -0.261 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
sidx | +1.290 |
Norm | +1.158 |
untarily | +1.057 |
warmed | +1.007 |
itals | +0.998 |
Neg logit contributions | |
leigh | -1.131 |
hyde | -1.119 |
zinski | -1.051 |
pen | -1.042 |
bane | -1.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
sidx | +1.776 |
Norm | +1.618 |
untarily | +1.435 |
warmed | +1.365 |
itals | +1.351 |
Neg logit contributions | |
leigh | -1.737 |
hyde | -1.722 |
zinski | -1.615 |
pen | -1.602 |
bane | -1.590 |
Token |
|
Token ID | 198 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
sidx | +1.331 |
Norm | +1.203 |
untarily | +1.078 |
warmed | +1.028 |
itals | +1.014 |
Neg logit contributions | |
leigh | -1.304 |
hyde | -1.303 |
zinski | -1.211 |
pen | -1.204 |
bane | -1.196 |
Token | And |
Token ID | 1870 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
sidx | +1.974 |
Norm | +1.794 |
untarily | +1.641 |
warmed | +1.551 |
itals | +1.544 |
Neg logit contributions | |
leigh | -1.743 |
hyde | -1.738 |
zinski | -1.627 |
bane | -1.595 |
Drew | -1.593 |
Token | that |
Token ID | 326 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
sidx | +2.343 |
Norm | +2.128 |
untarily | +1.925 |
warmed | +1.843 |
itals | +1.826 |
Neg logit contributions | |
leigh | -2.074 |
hyde | -2.069 |
zinski | -1.947 |
bane | -1.906 |
pen | -1.902 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
leigh | +1.148 |
hyde | +1.132 |
pen | +1.062 |
zinski | +1.059 |
Drew | +1.049 |
Neg logit contributions | |
sidx | -1.371 |
Norm | -1.231 |
untarily | -1.133 |
warmed | -1.075 |
streng | -1.062 |
Token | Due |
Token ID | 14444 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
sidx | +3.147 |
Norm | +2.926 |
untarily | +2.521 |
warmed | +2.413 |
itals | +2.408 |
Neg logit contributions | |
leigh | -3.081 |
hyde | -3.058 |
zinski | -2.862 |
pen | -2.827 |
bane | -2.812 |
Token | to |
Token ID | 284 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
leigh | +0.172 |
hyde | +0.170 |
zinski | +0.159 |
pen | +0.158 |
bane | +0.157 |
Neg logit contributions | |
sidx | -0.206 |
Norm | -0.185 |
untarily | -0.169 |
warmed | -0.162 |
streng | -0.160 |
Token | large |
Token ID | 1588 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
sidx | +0.037 |
Norm | +0.034 |
untarily | +0.031 |
warmed | +0.030 |
streng | +0.029 |
Neg logit contributions | |
leigh | -0.030 |
hyde | -0.030 |
zinski | -0.028 |
pen | -0.027 |
bane | -0.027 |
Token | - |
Token ID | 12 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
leigh | +1.797 |
hyde | +1.771 |
pen | +1.639 |
zinski | +1.634 |
Drew | +1.619 |
Neg logit contributions | |
sidx | -2.753 |
Norm | -2.480 |
untarily | -2.314 |
warmed | -2.211 |
itals | -2.197 |
Token | scale |
Token ID | 9888 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
leigh | +1.519 |
hyde | +1.489 |
pen | +1.401 |
zinski | +1.388 |
bane | +1.370 |
Neg logit contributions | |
sidx | -2.272 |
Norm | -2.044 |
untarily | -1.893 |
warmed | -1.820 |
itals | -1.799 |
Token | arson |
Token ID | 35181 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
sidx | +1.182 |
Norm | +1.074 |
untarily | +0.975 |
warmed | +0.935 |
streng | +0.925 |
Neg logit contributions | |
leigh | -0.986 |
hyde | -0.975 |
zinski | -0.916 |
pen | -0.906 |
bane | -0.900 |
Token | , |
Token ID | 11 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
sidx | +2.878 |
Norm | +2.582 |
untarily | +2.305 |
warmed | +2.250 |
itals | +2.212 |
Neg logit contributions | |
leigh | -2.699 |
hyde | -2.682 |
zinski | -2.530 |
pen | -2.478 |
bane | -2.471 |
Token | looting |
Token ID | 39473 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
sidx | +4.923 |
Norm | +4.581 |
untarily | +4.051 |
warmed | +3.953 |
streng | +3.898 |
Neg logit contributions | |
leigh | -4.354 |
hyde | -4.295 |
zinski | -4.114 |
bane | -3.962 |
pen | -3.934 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
sidx | +2.574 |
Norm | +2.327 |
untarily | +2.087 |
warmed | +2.032 |
streng | +1.987 |
Neg logit contributions | |
leigh | -2.435 |
hyde | -2.413 |
zinski | -2.275 |
pen | -2.231 |
bane | -2.224 |
Token | vandalism |
Token ID | 37260 |
Feature activation | +6.84e+00 |
Pos logit contributions | |
leigh | +0.790 |
hyde | +0.785 |
pen | +0.732 |
zinski | +0.730 |
Drew | +0.725 |
Neg logit contributions | |
sidx | -0.962 |
Norm | -0.862 |
untarily | -0.795 |
warmed | -0.754 |
itals | -0.748 |
Token | el |
Token ID | 417 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
leigh | +1.350 |
hyde | +1.338 |
pen | +1.268 |
zinski | +1.265 |
Drew | +1.256 |
Neg logit contributions | |
sidx | -1.232 |
Norm | -1.073 |
untarily | -0.985 |
streng | -0.915 |
warmed | -0.914 |
Token | especially |
Token ID | 2592 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
sidx | +2.068 |
Norm | +1.856 |
untarily | +1.667 |
warmed | +1.615 |
itals | +1.591 |
Neg logit contributions | |
leigh | -1.945 |
hyde | -1.920 |
zinski | -1.813 |
pen | -1.781 |
bane | -1.780 |
Token | , |
Token ID | 11 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
sidx | +2.000 |
Norm | +1.789 |
untarily | +1.606 |
warmed | +1.565 |
streng | +1.532 |
Neg logit contributions | |
leigh | -1.888 |
hyde | -1.871 |
zinski | -1.758 |
pen | -1.731 |
bane | -1.729 |
Token | and |
Token ID | 290 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
leigh | +0.369 |
hyde | +0.365 |
zinski | +0.342 |
pen | +0.342 |
Drew | +0.339 |
Neg logit contributions | |
sidx | -0.436 |
Norm | -0.392 |
untarily | -0.361 |
warmed | -0.342 |
streng | -0.338 |
Token | P |
Token ID | 350 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
leigh | +0.043 |
hyde | +0.042 |
zinski | +0.039 |
pen | +0.039 |
Drew | +0.039 |
Neg logit contributions | |
sidx | -0.050 |
Norm | -0.045 |
untarily | -0.042 |
warmed | -0.039 |
streng | -0.039 |
Token | å |
Token ID | 29090 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
sidx | +3.860 |
Norm | +3.469 |
untarily | +3.124 |
warmed | +3.015 |
itals | +3.014 |
Neg logit contributions | |
hyde | -3.259 |
leigh | -3.216 |
zinski | -3.014 |
Drew | -2.926 |
pen | -2.917 |
Token | l |
Token ID | 75 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
leigh | +0.339 |
hyde | +0.335 |
pen | +0.314 |
zinski | +0.313 |
bane | +0.310 |
Neg logit contributions | |
sidx | -0.397 |
Norm | -0.356 |
untarily | -0.327 |
warmed | -0.311 |
streng | -0.308 |
Token | " |
Token ID | 366 |
Feature activation | +5.11e+00 |
Pos logit contributions | |
leigh | +0.860 |
hyde | +0.852 |
pen | +0.790 |
zinski | +0.786 |
Drew | +0.780 |
Neg logit contributions | |
sidx | -1.236 |
Norm | -1.115 |
untarily | -1.038 |
warmed | -0.988 |
itals | -0.981 |
Token | P |
Token ID | 47 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
sidx | +4.122 |
Norm | +3.702 |
untarily | +3.402 |
warmed | +3.268 |
itals | +3.259 |
Neg logit contributions | |
leigh | -3.264 |
hyde | -3.230 |
zinski | -3.036 |
Drew | -3.012 |
appings | -2.958 |
Token | olly |
Token ID | 5098 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
sidx | +3.075 |
Norm | +2.753 |
untarily | +2.514 |
itals | +2.411 |
warmed | +2.406 |
Neg logit contributions | |
hyde | -2.657 |
leigh | -2.644 |
zinski | -2.488 |
bane | -2.432 |
Drew | -2.430 |
Token | " |
Token ID | 1 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
leigh | +1.195 |
hyde | +1.180 |
pen | +1.109 |
zinski | +1.097 |
bane | +1.096 |
Neg logit contributions | |
sidx | -1.634 |
Norm | -1.472 |
untarily | -1.365 |
warmed | -1.295 |
streng | -1.292 |
Token | : |
Token ID | 1058 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
sidx | +5.713 |
Norm | +5.176 |
warmed | +4.664 |
untarily | +4.605 |
caffe | +4.448 |
Neg logit contributions | |
leigh | -5.419 |
hyde | -5.227 |
zinski | -5.103 |
bane | -4.943 |
appings | -4.941 |
Token | more |
Token ID | 517 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
leigh | +1.182 |
hyde | +1.177 |
pen | +1.101 |
zinski | +1.091 |
Drew | +1.081 |
Neg logit contributions | |
sidx | -1.430 |
Norm | -1.278 |
untarily | -1.179 |
warmed | -1.116 |
itals | -1.108 |
Token | food |
Token ID | 2057 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
leigh | +2.315 |
hyde | +2.286 |
pen | +2.175 |
zinski | +2.145 |
Drew | +2.132 |
Neg logit contributions | |
sidx | -2.526 |
Norm | -2.243 |
untarily | -2.075 |
itals | -1.968 |
pees | -1.923 |
Token | , |
Token ID | 11 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
leigh | +0.348 |
hyde | +0.346 |
zinski | +0.323 |
pen | +0.322 |
bane | +0.319 |
Neg logit contributions | |
sidx | -0.406 |
Norm | -0.364 |
untarily | -0.333 |
warmed | -0.316 |
streng | -0.313 |
Token | bigger |
Token ID | 5749 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
leigh | +2.491 |
hyde | +2.483 |
pen | +2.319 |
zinski | +2.281 |
Drew | +2.276 |
Neg logit contributions | |
sidx | -3.163 |
Norm | -2.816 |
untarily | -2.629 |
itals | -2.485 |
pees | -2.431 |
Token | plants |
Token ID | 6134 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
leigh | +4.088 |
hyde | +4.050 |
pen | +3.830 |
Drew | +3.755 |
zinski | +3.688 |
Neg logit contributions | |
sidx | -4.604 |
Norm | -4.007 |
untarily | -3.738 |
itals | -3.553 |
pees | -3.461 |
Token | and |
Token ID | 290 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
leigh | +2.909 |
hyde | +2.874 |
pen | +2.721 |
bane | +2.677 |
zinski | +2.656 |
Neg logit contributions | |
sidx | -3.791 |
Norm | -3.423 |
untarily | -3.194 |
itals | -2.970 |
pees | -2.956 |
Token | quicker |
Token ID | 20061 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
leigh | +4.071 |
hyde | +3.970 |
pen | +3.782 |
Drew | +3.725 |
zinski | +3.678 |
Neg logit contributions | |
sidx | -5.020 |
Norm | -4.392 |
untarily | -4.181 |
itals | -3.956 |
pees | -3.902 |
Token | growth |
Token ID | 3349 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
leigh | +0.315 |
hyde | +0.313 |
pen | +0.294 |
zinski | +0.293 |
Drew | +0.290 |
Neg logit contributions | |
sidx | -0.314 |
Norm | -0.278 |
untarily | -0.253 |
warmed | -0.239 |
itals | -0.237 |
Token | , |
Token ID | 11 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
leigh | +1.107 |
hyde | +1.092 |
pen | +1.028 |
zinski | +1.024 |
Drew | +1.011 |
Neg logit contributions | |
sidx | -1.391 |
Norm | -1.252 |
untarily | -1.159 |
warmed | -1.091 |
itals | -1.085 |
Token | more |
Token ID | 517 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
leigh | +2.336 |
hyde | +2.302 |
pen | +2.171 |
zinski | +2.150 |
Drew | +2.147 |
Neg logit contributions | |
sidx | -2.905 |
Norm | -2.581 |
untarily | -2.413 |
itals | -2.267 |
pees | -2.238 |
Token | in |
Token ID | 287 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
leigh | +1.757 |
hyde | +1.735 |
pen | +1.630 |
zinski | +1.626 |
Drew | +1.616 |
Neg logit contributions | |
sidx | -2.116 |
Norm | -1.890 |
untarily | -1.745 |
warmed | -1.663 |
streng | -1.661 |
Token | the |
Token ID | 262 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
sidx | +2.040 |
Norm | +1.867 |
untarily | +1.695 |
warmed | +1.616 |
streng | +1.582 |
Neg logit contributions | |
leigh | -1.681 |
hyde | -1.680 |
zinski | -1.557 |
pen | -1.535 |
bane | -1.532 |
Token | April |
Token ID | 3035 |
Feature activation | +6.44e+00 |
Pos logit contributions | |
sidx | +5.048 |
Norm | +4.772 |
untarily | +4.196 |
warmed | +4.072 |
caffe | +3.991 |
Neg logit contributions | |
hyde | -4.025 |
leigh | -3.895 |
zinski | -3.645 |
bane | -3.609 |
pen | -3.569 |
Token | 1986 |
Token ID | 12113 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
sidx | +4.724 |
Norm | +4.377 |
untarily | +3.847 |
warmed | +3.740 |
itals | +3.615 |
Neg logit contributions | |
hyde | -4.617 |
leigh | -4.430 |
zinski | -4.167 |
appings | -4.145 |
bane | -4.142 |
Token | launch |
Token ID | 4219 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
sidx | +2.379 |
Norm | +2.170 |
untarily | +1.941 |
warmed | +1.859 |
streng | +1.837 |
Neg logit contributions | |
hyde | -2.148 |
leigh | -2.140 |
zinski | -2.004 |
pen | -1.986 |
bane | -1.973 |
Token | vehicle |
Token ID | 4038 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
leigh | +2.830 |
hyde | +2.770 |
Drew | +2.620 |
pen | +2.609 |
zinski | +2.604 |
Neg logit contributions | |
sidx | -3.018 |
Norm | -2.652 |
untarily | -2.470 |
streng | -2.346 |
warmed | -2.322 |
Token | accident |
Token ID | 5778 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
leigh | +1.132 |
hyde | +1.116 |
zinski | +1.054 |
pen | +1.052 |
Drew | +1.045 |
Neg logit contributions | |
sidx | -1.072 |
Norm | -0.944 |
untarily | -0.860 |
warmed | -0.810 |
streng | -0.801 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
sidx | +6.008 |
Norm | +5.559 |
untarily | +4.868 |
warmed | +4.670 |
itals | +4.520 |
Neg logit contributions | |
hyde | -6.091 |
leigh | -6.041 |
zinski | -5.627 |
bane | -5.538 |
appings | -5.537 |
Token | Per |
Token ID | 2448 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
sidx | +1.194 |
Norm | +1.081 |
untarily | +0.981 |
warmed | +0.939 |
streng | +0.927 |
Neg logit contributions | |
leigh | -0.997 |
hyde | -0.986 |
zinski | -0.919 |
pen | -0.912 |
bane | -0.903 |
Token | kin |
Token ID | 5116 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
leigh | +0.414 |
hyde | +0.409 |
zinski | +0.384 |
pen | +0.383 |
bane | +0.379 |
Neg logit contributions | |
sidx | -0.456 |
Norm | -0.408 |
untarily | -0.372 |
warmed | -0.354 |
streng | -0.350 |
Token | - |
Token ID | 12 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
leigh | +1.290 |
hyde | +1.273 |
pen | +1.196 |
zinski | +1.190 |
Drew | +1.179 |
Neg logit contributions | |
sidx | -1.490 |
Norm | -1.327 |
untarily | -1.228 |
streng | -1.160 |
warmed | -1.156 |
Token | & |
Token ID | 1222 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
leigh | +0.938 |
hyde | +0.919 |
zinski | +0.856 |
pen | +0.852 |
bane | +0.839 |
Neg logit contributions | |
sidx | -1.524 |
Norm | -1.384 |
untarily | -1.289 |
warmed | -1.234 |
streng | -1.224 |
Token | Cove |
Token ID | 39534 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
leigh | +1.851 |
hyde | +1.815 |
Drew | +1.721 |
zinski | +1.709 |
pen | +1.709 |
Neg logit contributions | |
sidx | -2.101 |
Norm | -1.835 |
untarily | -1.726 |
warmed | -1.629 |
streng | -1.622 |
Token | y |
Token ID | 88 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
sidx | +0.895 |
Norm | +0.810 |
untarily | +0.740 |
warmed | +0.710 |
itals | +0.700 |
Neg logit contributions | |
leigh | -0.732 |
hyde | -0.730 |
zinski | -0.677 |
pen | -0.674 |
Drew | -0.667 |
Token | ( |
Token ID | 357 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
leigh | +0.667 |
hyde | +0.658 |
zinski | +0.614 |
pen | +0.613 |
bane | +0.606 |
Neg logit contributions | |
sidx | -0.849 |
Norm | -0.764 |
untarily | -0.704 |
warmed | -0.670 |
streng | -0.664 |
Token | 1992 |
Token ID | 23847 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
leigh | +0.355 |
hyde | +0.350 |
zinski | +0.329 |
pen | +0.329 |
bane | +0.325 |
Neg logit contributions | |
sidx | -0.406 |
Norm | -0.364 |
untarily | -0.333 |
warmed | -0.317 |
streng | -0.315 |
Token | ); |
Token ID | 1776 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
leigh | +4.964 |
hyde | +4.737 |
zinski | +4.559 |
pen | +4.524 |
Drew | +4.446 |
Neg logit contributions | |
sidx | -9.344 |
Norm | -8.364 |
untarily | -7.984 |
streng | -7.709 |
warmed | -7.671 |
Token | Id |
Token ID | 5121 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
leigh | +3.002 |
hyde | +2.922 |
Drew | +2.809 |
pen | +2.769 |
zinski | +2.752 |
Neg logit contributions | |
sidx | -3.467 |
Norm | -2.988 |
untarily | -2.844 |
itals | -2.677 |
streng | -2.671 |
Token | so |
Token ID | 568 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
leigh | +1.590 |
hyde | +1.557 |
zinski | +1.478 |
pen | +1.474 |
bane | +1.450 |
Neg logit contributions | |
sidx | -1.739 |
Norm | -1.552 |
untarily | -1.417 |
warmed | -1.350 |
streng | -1.339 |
Token | ( |
Token ID | 357 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
leigh | +2.938 |
hyde | +2.887 |
zinski | +2.697 |
pen | +2.697 |
Drew | +2.626 |
Neg logit contributions | |
sidx | -4.465 |
Norm | -3.976 |
untarily | -3.752 |
streng | -3.578 |
warmed | -3.576 |
Token | 1998 |
Token ID | 21113 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
leigh | +0.175 |
hyde | +0.174 |
zinski | +0.163 |
pen | +0.163 |
bane | +0.161 |
Neg logit contributions | |
sidx | -0.186 |
Norm | -0.166 |
untarily | -0.152 |
warmed | -0.144 |
streng | -0.142 |
Token | ); |
Token ID | 1776 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
leigh | +3.830 |
hyde | +3.726 |
zinski | +3.500 |
pen | +3.473 |
Drew | +3.430 |
Neg logit contributions | |
sidx | -6.897 |
Norm | -6.202 |
untarily | -5.892 |
streng | -5.644 |
warmed | -5.622 |
Token | of |
Token ID | 286 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
leigh | +1.552 |
hyde | +1.539 |
pen | +1.440 |
zinski | +1.432 |
Drew | +1.428 |
Neg logit contributions | |
sidx | -1.948 |
Norm | -1.725 |
untarily | -1.603 |
warmed | -1.506 |
itals | -1.502 |
Token | rationality |
Token ID | 45627 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
sidx | +3.502 |
Norm | +3.255 |
untarily | +2.902 |
warmed | +2.815 |
streng | +2.758 |
Neg logit contributions | |
hyde | -3.039 |
leigh | -3.010 |
zinski | -2.771 |
bane | -2.762 |
pen | -2.754 |
Token | is |
Token ID | 318 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
leigh | +1.667 |
hyde | +1.635 |
pen | +1.541 |
zinski | +1.531 |
Drew | +1.529 |
Neg logit contributions | |
sidx | -2.028 |
Norm | -1.803 |
untarily | -1.674 |
itals | -1.567 |
warmed | -1.563 |
Token | complex |
Token ID | 3716 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
leigh | +1.039 |
hyde | +1.026 |
pen | +0.963 |
zinski | +0.961 |
Drew | +0.955 |
Neg logit contributions | |
sidx | -1.230 |
Norm | -1.091 |
untarily | -1.006 |
warmed | -0.946 |
itals | -0.943 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
leigh | +4.047 |
hyde | +3.947 |
pen | +3.744 |
Drew | +3.693 |
zinski | +3.690 |
Neg logit contributions | |
sidx | -5.825 |
Norm | -5.144 |
untarily | -4.843 |
ンジ | -4.577 |
streng | -4.550 |
Token | It |
Token ID | 632 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
sidx | +1.169 |
Norm | +1.070 |
untarily | +0.950 |
warmed | +0.906 |
itals | +0.893 |
Neg logit contributions | |
leigh | -1.103 |
hyde | -1.100 |
zinski | -1.027 |
pen | -1.019 |
bane | -1.010 |
Token | is |
Token ID | 318 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
sidx | +0.011 |
Norm | +0.010 |
untarily | +0.009 |
warmed | +0.009 |
streng | +0.009 |
Neg logit contributions | |
leigh | -0.010 |
hyde | -0.010 |
zinski | -0.009 |
pen | -0.009 |
bane | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
sidx | +0.413 |
Norm | +0.371 |
untarily | +0.339 |
warmed | +0.323 |
streng | +0.318 |
Neg logit contributions | |
leigh | -0.368 |
hyde | -0.365 |
zinski | -0.341 |
pen | -0.340 |
bane | -0.337 |
Token | pity |
Token ID | 26246 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
leigh | +2.116 |
hyde | +2.082 |
pen | +1.962 |
zinski | +1.955 |
Drew | +1.943 |
Neg logit contributions | |
sidx | -2.499 |
Norm | -2.192 |
untarily | -2.040 |
itals | -1.925 |
warmed | -1.917 |
Token | that |
Token ID | 326 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
sidx | +1.301 |
Norm | +1.185 |
untarily | +1.078 |
warmed | +1.029 |
itals | +1.012 |
Neg logit contributions | |
leigh | -1.106 |
hyde | -1.102 |
zinski | -1.027 |
pen | -1.018 |
bane | -1.014 |
Token | He |
Token ID | 679 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
sidx | +0.853 |
Norm | +0.774 |
untarily | +0.705 |
warmed | +0.675 |
streng | +0.665 |
Neg logit contributions | |
leigh | -0.707 |
hyde | -0.704 |
zinski | -0.656 |
pen | -0.651 |
bane | -0.645 |
Token | several |
Token ID | 1811 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
sidx | +2.641 |
Norm | +2.453 |
untarily | +2.160 |
warmed | +2.131 |
streng | +2.074 |
Neg logit contributions | |
hyde | -2.505 |
leigh | -2.490 |
zinski | -2.324 |
bane | -2.291 |
pen | -2.269 |
Token | lessons |
Token ID | 11658 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
sidx | +0.728 |
Norm | +0.656 |
untarily | +0.591 |
warmed | +0.568 |
streng | +0.558 |
Neg logit contributions | |
leigh | -0.695 |
hyde | -0.693 |
zinski | -0.649 |
pen | -0.642 |
bane | -0.639 |
Token | from |
Token ID | 422 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
leigh | +1.631 |
hyde | +1.607 |
pen | +1.522 |
Drew | +1.511 |
zinski | +1.506 |
Neg logit contributions | |
sidx | -2.110 |
Norm | -1.868 |
untarily | -1.757 |
itals | -1.655 |
streng | -1.646 |
Token | former |
Token ID | 1966 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
leigh | +2.537 |
hyde | +2.485 |
Drew | +2.404 |
pen | +2.375 |
zinski | +2.350 |
Neg logit contributions | |
sidx | -3.356 |
Norm | -2.904 |
untarily | -2.792 |
itals | -2.630 |
ンジ | -2.602 |
Token | President |
Token ID | 1992 |
Feature activation | -8.49e+00 |
Pos logit contributions | |
Drew | +7.386 |
leigh | +7.299 |
Apprentice | +7.153 |
Ultimate | +7.066 |
pen | +7.034 |
Neg logit contributions | |
sidx | -12.374 |
untarily | -10.285 |
Norm | -9.770 |
itals | -9.681 |
ンジ | -9.670 |
Token | Harry |
Token ID | 5850 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
leigh | +4.483 |
Drew | +4.385 |
pen | +4.193 |
hyde | +4.119 |
bane | +4.007 |
Neg logit contributions | |
sidx | -8.050 |
untarily | -6.621 |
Norm | -6.590 |
itals | -6.409 |
ンジ | -6.357 |
Token | Truman |
Token ID | 33027 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
leigh | +6.218 |
Drew | +6.165 |
bane | +5.809 |
pen | +5.519 |
Ultimate | +5.498 |
Neg logit contributions | |
sidx | -11.506 |
streng | -9.314 |
Norm | -9.095 |
untarily | -9.069 |
pees | -8.916 |
Token | . |
Token ID | 13 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
leigh | +6.990 |
hyde | +6.954 |
Drew | +6.856 |
pen | +6.549 |
born | +6.294 |
Neg logit contributions | |
sidx | -10.190 |
untarily | -8.723 |
Norm | -8.579 |
ンジ | -8.338 |
itals | -8.317 |
Token |
|
Token ID | 198 |
Feature activation | +5.78e+00 |
Pos logit contributions | |
leigh | +1.860 |
hyde | +1.837 |
Drew | +1.743 |
zinski | +1.735 |
pen | +1.726 |
Neg logit contributions | |
sidx | -2.317 |
Norm | -2.042 |
untarily | -1.931 |
streng | -1.849 |
warmed | -1.840 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
sidx | +3.696 |
Norm | +3.466 |
untarily | +2.905 |
warmed | +2.780 |
itals | +2.749 |
Neg logit contributions | |
hyde | -4.696 |
leigh | -4.564 |
appings | -4.252 |
zinski | -4.233 |
bane | -4.197 |
Token | Ign |
Token ID | 32916 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
leigh | +0.834 |
hyde | +0.817 |
pen | +0.758 |
zinski | +0.756 |
bane | +0.744 |
Neg logit contributions | |
sidx | -1.480 |
Norm | -1.342 |
untarily | -1.253 |
streng | -1.214 |
warmed | -1.208 |
Token | fine |
Token ID | 38125 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
sidx | +2.621 |
Norm | +2.392 |
untarily | +2.181 |
warmed | +2.076 |
itals | +2.030 |
Neg logit contributions | |
hyde | -2.297 |
leigh | -2.286 |
Drew | -2.145 |
zinski | -2.135 |
appings | -2.120 |
Token | line |
Token ID | 1627 |
Feature activation | -6.61e+00 |
Pos logit contributions | |
sidx | +0.855 |
Norm | +0.787 |
untarily | +0.719 |
warmed | +0.695 |
streng | +0.682 |
Neg logit contributions | |
leigh | -0.577 |
hyde | -0.571 |
zinski | -0.530 |
pen | -0.524 |
bane | -0.520 |
Token | that |
Token ID | 326 |
Feature activation | -8.61e+00 |
Pos logit contributions | |
leigh | +3.825 |
hyde | +3.809 |
pen | +3.632 |
Drew | +3.609 |
zinski | +3.482 |
Neg logit contributions | |
sidx | -5.782 |
Norm | -5.075 |
untarily | -4.811 |
streng | -4.626 |
ンジ | -4.596 |
Token | needs |
Token ID | 2476 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
leigh | +5.107 |
hyde | +4.899 |
Drew | +4.850 |
pen | +4.798 |
Ultimate | +4.566 |
Neg logit contributions | |
sidx | -7.342 |
Norm | -6.200 |
untarily | -6.040 |
ンジ | -5.743 |
streng | -5.699 |
Token | to |
Token ID | 284 |
Feature activation | -9.76e+00 |
Pos logit contributions | |
leigh | +3.353 |
hyde | +3.216 |
pen | +3.136 |
Drew | +3.129 |
bane | +2.999 |
Neg logit contributions | |
sidx | -5.357 |
Norm | -4.665 |
untarily | -4.453 |
ンジ | -4.201 |
streng | -4.144 |
Token | be |
Token ID | 307 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
hyde | +4.188 |
leigh | +4.188 |
pen | +4.066 |
Drew | +3.827 |
bane | +3.818 |
Neg logit contributions | |
sidx | -9.863 |
Norm | -8.658 |
untarily | -8.247 |
caffe | -7.805 |
streng | -7.804 |
Token | tread |
Token ID | 23153 |
Feature activation | -8.21e+00 |
Pos logit contributions | |
Drew | +7.812 |
leigh | +7.727 |
pen | +7.651 |
bane | +7.605 |
hyde | +7.529 |
Neg logit contributions | |
sidx | -11.984 |
Norm | -9.910 |
untarily | -9.712 |
ンジ | -9.192 |
覚醒 | -8.987 |
Token | " |
Token ID | 1 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
leigh | +4.521 |
hyde | +4.433 |
pen | +4.374 |
Drew | +4.136 |
bane | +4.125 |
Neg logit contributions | |
sidx | -7.391 |
Norm | -6.514 |
untarily | -6.151 |
streng | -5.921 |
itals | -5.841 |
Token | between |
Token ID | 1022 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
leigh | +3.343 |
hyde | +3.282 |
pen | +3.165 |
Drew | +3.133 |
zinski | +3.106 |
Neg logit contributions | |
sidx | -4.285 |
Norm | -3.739 |
untarily | -3.543 |
streng | -3.337 |
ンジ | -3.322 |
Token | the |
Token ID | 262 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
sidx | +3.891 |
Norm | +3.578 |
untarily | +3.165 |
warmed | +3.046 |
caffe | +3.045 |
Neg logit contributions | |
hyde | -3.619 |
leigh | -3.576 |
zinski | -3.375 |
pen | -3.305 |
bane | -3.304 |
Token | commercial |
Token ID | 5068 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
sidx | +3.780 |
Norm | +3.424 |
untarily | +3.022 |
warmed | +2.897 |
caffe | +2.891 |
Neg logit contributions | |
hyde | -3.852 |
leigh | -3.822 |
zinski | -3.581 |
pen | -3.561 |
bane | -3.536 |
Token | them |
Token ID | 606 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
leigh | +5.377 |
hyde | +5.253 |
pen | +5.137 |
Drew | +5.093 |
Ultimate | +4.957 |
Neg logit contributions | |
sidx | -7.360 |
Norm | -6.282 |
untarily | -6.057 |
itals | -5.704 |
warmed | -5.682 |
Token | efficient |
Token ID | 6942 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
leigh | +4.051 |
hyde | +4.018 |
pen | +3.814 |
Drew | +3.781 |
bane | +3.739 |
Neg logit contributions | |
sidx | -5.639 |
Norm | -4.934 |
untarily | -4.691 |
itals | -4.423 |
warmed | -4.373 |
Token | . |
Token ID | 13 |
Feature activation | -7.05e+00 |
Pos logit contributions | |
leigh | +0.758 |
hyde | +0.750 |
pen | +0.701 |
zinski | +0.699 |
Drew | +0.692 |
Neg logit contributions | |
sidx | -0.924 |
Norm | -0.830 |
untarily | -0.762 |
warmed | -0.727 |
streng | -0.719 |
Token | The |
Token ID | 383 |
Feature activation | -8.46e+00 |
Pos logit contributions | |
leigh | +4.462 |
hyde | +4.289 |
Drew | +4.184 |
zinski | +4.115 |
pen | +4.111 |
Neg logit contributions | |
sidx | -5.837 |
Norm | -4.956 |
untarily | -4.861 |
streng | -4.611 |
warmed | -4.610 |
Token | key |
Token ID | 1994 |
Feature activation | -8.89e+00 |
Pos logit contributions | |
leigh | +5.619 |
hyde | +5.423 |
Drew | +5.236 |
pen | +5.189 |
zinski | +5.173 |
Neg logit contributions | |
sidx | -6.613 |
Norm | -5.633 |
untarily | -5.388 |
itals | -5.047 |
ンジ | -5.045 |
Token | to |
Token ID | 284 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
leigh | +5.588 |
hyde | +5.313 |
pen | +5.300 |
Drew | +5.221 |
zinski | +5.137 |
Neg logit contributions | |
sidx | -7.102 |
Norm | -6.146 |
untarily | -5.963 |
warmed | -5.632 |
streng | -5.492 |
Token | success |
Token ID | 1943 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
leigh | +6.870 |
hyde | +6.520 |
Ultimate | +6.409 |
Drew | +6.398 |
pen | +6.362 |
Neg logit contributions | |
sidx | -9.409 |
Norm | -7.987 |
untarily | -7.934 |
ンジ | -7.354 |
warmed | -7.334 |
Token | is |
Token ID | 318 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
leigh | +1.264 |
hyde | +1.250 |
pen | +1.175 |
zinski | +1.174 |
Drew | +1.159 |
Neg logit contributions | |
sidx | -1.446 |
Norm | -1.290 |
untarily | -1.187 |
warmed | -1.127 |
streng | -1.116 |
Token | management |
Token ID | 4542 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
leigh | +6.448 |
hyde | +6.133 |
pen | +6.017 |
Drew | +5.982 |
Ultimate | +5.917 |
Neg logit contributions | |
sidx | -8.752 |
Norm | -7.476 |
untarily | -7.315 |
itals | -6.826 |
ンジ | -6.819 |
Token | support |
Token ID | 1104 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
leigh | +2.429 |
hyde | +2.384 |
pen | +2.253 |
zinski | +2.231 |
Drew | +2.218 |
Neg logit contributions | |
sidx | -3.027 |
Norm | -2.705 |
untarily | -2.529 |
itals | -2.376 |
warmed | -2.373 |
Token | , |
Token ID | 11 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
leigh | +1.515 |
hyde | +1.502 |
pen | +1.400 |
zinski | +1.398 |
Drew | +1.381 |
Neg logit contributions | |
sidx | -1.870 |
Norm | -1.673 |
untarily | -1.549 |
warmed | -1.471 |
itals | -1.455 |
Token | under |
Token ID | 739 |
Feature activation | +9.28e+00 |
Pos logit contributions | |
leigh | +1.292 |
hyde | +1.273 |
pen | +1.196 |
zinski | +1.194 |
Drew | +1.185 |
Neg logit contributions | |
sidx | -1.486 |
Norm | -1.324 |
untarily | -1.211 |
warmed | -1.150 |
streng | -1.140 |
Token | anesthesia |
Token ID | 49592 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
sidx | +6.389 |
Norm | +6.017 |
untarily | +5.329 |
warmed | +5.028 |
caffe | +4.977 |
Neg logit contributions | |
leigh | -6.643 |
hyde | -6.635 |
zinski | -6.338 |
appings | -6.127 |
bane | -6.115 |
Token | while |
Token ID | 981 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
sidx | +1.070 |
Norm | +0.961 |
untarily | +0.875 |
warmed | +0.834 |
itals | +0.818 |
Neg logit contributions | |
leigh | -1.008 |
hyde | -1.001 |
zinski | -0.938 |
pen | -0.932 |
bane | -0.924 |
Token | the |
Token ID | 262 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
leigh | +2.006 |
hyde | +1.971 |
Drew | +1.882 |
pen | +1.863 |
zinski | +1.850 |
Neg logit contributions | |
sidx | -2.410 |
Norm | -2.106 |
untarily | -1.966 |
itals | -1.837 |
streng | -1.836 |
Token | dentist |
Token ID | 38408 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
leigh | +2.801 |
hyde | +2.779 |
Drew | +2.635 |
zinski | +2.614 |
pen | +2.607 |
Neg logit contributions | |
sidx | -3.435 |
Norm | -3.009 |
untarily | -2.801 |
streng | -2.644 |
warmed | -2.626 |
Token | removed |
Token ID | 4615 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
leigh | +3.791 |
hyde | +3.707 |
Drew | +3.635 |
pen | +3.520 |
zinski | +3.471 |
Neg logit contributions | |
sidx | -4.670 |
Norm | -3.963 |
untarily | -3.817 |
ンジ | -3.568 |
itals | -3.503 |
Token | several |
Token ID | 1811 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
Drew | +7.861 |
leigh | +7.807 |
pen | +7.460 |
hyde | +7.374 |
births | +7.286 |
Neg logit contributions | |
sidx | -12.356 |
Norm | -9.820 |
untarily | -9.641 |
覚醒 | -9.536 |
ンジ | -9.464 |
Token | teeth |
Token ID | 9941 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
leigh | +8.898 |
Drew | +8.761 |
pen | +8.729 |
births | +8.623 |
born | +8.508 |
Neg logit contributions | |
sidx | -11.184 |
Norm | -8.954 |
untarily | -8.804 |
pees | -8.236 |
ンジ | -8.189 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
leigh | +3.814 |
hyde | +3.717 |
pen | +3.555 |
Drew | +3.524 |
bane | +3.460 |
Neg logit contributions | |
sidx | -5.231 |
Norm | -4.610 |
untarily | -4.341 |
streng | -4.092 |
ンジ | -4.039 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
leigh | +0.981 |
hyde | +0.967 |
zinski | +0.913 |
Drew | +0.908 |
pen | +0.907 |
Neg logit contributions | |
sidx | -1.163 |
Norm | -1.028 |
untarily | -0.956 |
warmed | -0.910 |
streng | -0.909 |
Token |
|
Token ID | 198 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
leigh | +0.801 |
hyde | +0.782 |
zinski | +0.745 |
pen | +0.744 |
Drew | +0.737 |
Neg logit contributions | |
sidx | -0.966 |
Norm | -0.856 |
untarily | -0.796 |
streng | -0.779 |
warmed | -0.756 |
Token | strength |
Token ID | 41402 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
leigh | +5.534 |
hyde | +5.420 |
pen | +5.398 |
zinski | +4.958 |
bane | +4.915 |
Neg logit contributions | |
sidx | -7.081 |
Norm | -6.378 |
untarily | -5.966 |
caffe | -5.719 |
pees | -5.696 |
Token | goals |
Token ID | 4661 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
leigh | +6.075 |
Drew | +6.031 |
pen | +5.971 |
hyde | +5.881 |
zinski | +5.723 |
Neg logit contributions | |
sidx | -7.939 |
Norm | -7.107 |
untarily | -6.845 |
ンジ | -6.640 |
pees | -6.502 |
Token | , |
Token ID | 11 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
leigh | +6.712 |
Drew | +6.506 |
pen | +6.488 |
hyde | +6.336 |
bane | +6.031 |
Neg logit contributions | |
sidx | -9.979 |
Norm | -9.112 |
untarily | -8.671 |
pees | -8.116 |
ンジ | -8.055 |
Token | triple |
Token ID | 15055 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
sidx | +1.884 |
Norm | +1.709 |
untarily | +1.528 |
warmed | +1.488 |
streng | +1.456 |
Neg logit contributions | |
hyde | -1.705 |
leigh | -1.702 |
zinski | -1.595 |
bane | -1.566 |
pen | -1.561 |
Token | their |
Token ID | 511 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
sidx | +1.298 |
Norm | +1.167 |
untarily | +1.052 |
warmed | +1.010 |
streng | +0.991 |
Neg logit contributions | |
hyde | -1.207 |
leigh | -1.205 |
zinski | -1.124 |
bane | -1.110 |
pen | -1.109 |
Token | total |
Token ID | 2472 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
leigh | +5.032 |
pen | +4.823 |
Drew | +4.819 |
hyde | +4.775 |
zinski | +4.631 |
Neg logit contributions | |
sidx | -6.469 |
Norm | -5.753 |
untarily | -5.499 |
ンジ | -5.129 |
pees | -5.123 |
Token | entering |
Token ID | 8218 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
Drew | +6.882 |
leigh | +6.697 |
pen | +6.527 |
hyde | +6.371 |
zinski | +6.265 |
Neg logit contributions | |
sidx | -11.095 |
Norm | -9.760 |
untarily | -9.604 |
pees | -9.353 |
itals | -9.156 |
Token | the |
Token ID | 262 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
leigh | +0.444 |
hyde | +0.436 |
pen | +0.409 |
zinski | +0.408 |
Drew | +0.405 |
Neg logit contributions | |
sidx | -0.588 |
Norm | -0.530 |
untarily | -0.489 |
warmed | -0.466 |
streng | -0.463 |
Token | game |
Token ID | 983 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
leigh | +0.633 |
hyde | +0.619 |
zinski | +0.583 |
pen | +0.583 |
Drew | +0.577 |
Neg logit contributions | |
sidx | -0.832 |
Norm | -0.746 |
untarily | -0.692 |
warmed | -0.658 |
streng | -0.654 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
leigh | +4.409 |
hyde | +4.247 |
Drew | +4.126 |
pen | +4.122 |
zinski | +3.975 |
Neg logit contributions | |
sidx | -6.355 |
Norm | -5.722 |
untarily | -5.373 |
streng | -5.108 |
pees | -5.055 |
Token | Brendan |
Token ID | 26134 |
Feature activation | +7.78e+00 |
Pos logit contributions | |
leigh | +1.353 |
hyde | +1.323 |
Drew | +1.263 |
zinski | +1.256 |
pen | +1.255 |
Neg logit contributions | |
sidx | -1.600 |
Norm | -1.410 |
untarily | -1.325 |
warmed | -1.253 |
streng | -1.252 |