Token | but |
Token ID | 475 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
ileaks | +0.705 |
burgh | +0.699 |
roid | +0.659 |
ocrates | +0.655 |
paren | +0.654 |
Neg logit contributions | |
LY | -0.863 |
lore | -0.803 |
iliate | -0.795 |
rys | -0.777 |
yg | -0.771 |
Token | screen |
Token ID | 3159 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
LY | +0.457 |
lore | +0.423 |
iliate | +0.419 |
rys | +0.409 |
yg | +0.405 |
Neg logit contributions | |
ileaks | -0.408 |
burgh | -0.403 |
ocrates | -0.381 |
roid | -0.380 |
paren | -0.379 |
Token | door |
Token ID | 3420 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ileaks | +3.281 |
burgh | +3.178 |
roid | +3.048 |
ocrates | +2.985 |
paren | +2.905 |
Neg logit contributions | |
LY | -5.486 |
lore | -5.143 |
iliate | -5.069 |
rys | -4.930 |
yg | -4.844 |
Token | effect |
Token ID | 1245 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
LY | +1.350 |
lore | +1.249 |
iliate | +1.234 |
rys | +1.209 |
yg | +1.207 |
Neg logit contributions | |
ileaks | -1.138 |
burgh | -1.119 |
ocrates | -1.054 |
roid | -1.045 |
paren | -1.042 |
Token | " |
Token ID | 1 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
LY | +2.015 |
lore | +1.876 |
iliate | +1.860 |
yg | +1.821 |
rys | +1.820 |
Neg logit contributions | |
ileaks | -1.308 |
burgh | -1.277 |
ocrates | -1.195 |
roid | -1.182 |
paren | -1.176 |
Token | Cra |
Token ID | 33800 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
LY | +0.775 |
lore | +0.719 |
iliate | +0.711 |
rys | +0.697 |
yg | +0.694 |
Neg logit contributions | |
ileaks | -0.632 |
burgh | -0.621 |
ocrates | -0.585 |
roid | -0.583 |
paren | -0.580 |
Token | ppy |
Token ID | 14097 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
LY | +8.274 |
iliate | +7.518 |
lore | +7.487 |
rys | +7.461 |
yg | +7.178 |
Neg logit contributions | |
ileaks | -10.278 |
burgh | -9.933 |
paren | -9.677 |
ocrates | -9.641 |
ocrat | -9.524 |
Token | job |
Token ID | 1693 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
LY | +1.026 |
lore | +0.948 |
iliate | +0.937 |
rys | +0.916 |
yg | +0.912 |
Neg logit contributions | |
ileaks | -0.945 |
burgh | -0.930 |
ocrates | -0.880 |
roid | -0.876 |
paren | -0.872 |
Token | doing |
Token ID | 1804 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
LY | +1.052 |
lore | +0.973 |
iliate | +0.962 |
rys | +0.941 |
yg | +0.937 |
Neg logit contributions | |
ileaks | -0.933 |
burgh | -0.917 |
ocrates | -0.867 |
roid | -0.862 |
paren | -0.859 |
Token | the |
Token ID | 262 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
LY | +0.086 |
lore | +0.080 |
iliate | +0.079 |
rys | +0.077 |
yg | +0.077 |
Neg logit contributions | |
ileaks | -0.081 |
burgh | -0.080 |
ocrates | -0.076 |
roid | -0.076 |
paren | -0.075 |
Token | pics |
Token ID | 27618 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
LY | +0.216 |
lore | +0.199 |
iliate | +0.197 |
rys | +0.192 |
yg | +0.191 |
Neg logit contributions | |
ileaks | -0.224 |
burgh | -0.221 |
ocrates | -0.209 |
roid | -0.209 |
paren | -0.209 |
Token | corner |
Token ID | 5228 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
burgh | +0.785 |
ileaks | +0.776 |
roid | +0.732 |
ocrates | +0.726 |
paren | +0.711 |
Neg logit contributions | |
LY | -0.896 |
lore | -0.846 |
iliate | -0.843 |
rys | -0.821 |
yg | -0.811 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
burgh | +1.251 |
ileaks | +1.244 |
roid | +1.180 |
ocrates | +1.164 |
paren | +1.147 |
Neg logit contributions | |
LY | -1.488 |
lore | -1.395 |
iliate | -1.394 |
rys | -1.359 |
yg | -1.346 |
Token | As |
Token ID | 1081 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
burgh | +1.284 |
ileaks | +1.270 |
ocrates | +1.183 |
roid | +1.180 |
paren | +1.172 |
Neg logit contributions | |
LY | -1.483 |
iliate | -1.391 |
lore | -1.377 |
rys | -1.361 |
yg | -1.333 |
Token | well |
Token ID | 880 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
LY | +2.756 |
lore | +2.555 |
iliate | +2.516 |
rys | +2.469 |
yg | +2.464 |
Neg logit contributions | |
ileaks | -2.425 |
burgh | -2.381 |
ocrates | -2.248 |
roid | -2.241 |
paren | -2.237 |
Token | , |
Token ID | 11 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
ileaks | +2.741 |
burgh | +2.721 |
ocrates | +2.577 |
paren | +2.549 |
roid | +2.532 |
Neg logit contributions | |
LY | -3.114 |
lore | -2.916 |
iliate | -2.906 |
rys | -2.835 |
yg | -2.789 |
Token | Cow |
Token ID | 10417 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
ileaks | +0.562 |
burgh | +0.557 |
ocrates | +0.525 |
roid | +0.522 |
paren | +0.519 |
Neg logit contributions | |
LY | -0.616 |
lore | -0.572 |
iliate | -0.569 |
rys | -0.553 |
yg | -0.546 |
Token | bell |
Token ID | 7923 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
LY | +8.480 |
lore | +8.004 |
rys | +7.838 |
look | +7.749 |
yg | +7.688 |
Neg logit contributions | |
ileaks | -9.293 |
burgh | -8.716 |
ocrates | -8.626 |
roid | -8.605 |
ocrat | -8.411 |
Token | Lane |
Token ID | 15016 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
LY | +0.732 |
lore | +0.673 |
iliate | +0.665 |
rys | +0.648 |
yg | +0.645 |
Neg logit contributions | |
ileaks | -0.776 |
burgh | -0.766 |
ocrates | -0.726 |
roid | -0.723 |
paren | -0.720 |
Token | will |
Token ID | 481 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
LY | +0.819 |
lore | +0.749 |
iliate | +0.739 |
rys | +0.720 |
yg | +0.716 |
Neg logit contributions | |
ileaks | -0.975 |
burgh | -0.962 |
ocrates | -0.916 |
roid | -0.913 |
paren | -0.909 |
Token | be |
Token ID | 307 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
burgh | +1.088 |
ileaks | +1.086 |
roid | +1.029 |
ocrates | +1.016 |
paren | +1.009 |
Neg logit contributions | |
LY | -1.182 |
lore | -1.102 |
iliate | -1.079 |
rys | -1.052 |
yg | -1.044 |
Token | completely |
Token ID | 3190 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
burgh | +2.318 |
ileaks | +2.308 |
roid | +2.178 |
ocrates | +2.159 |
paren | +2.132 |
Neg logit contributions | |
LY | -2.864 |
lore | -2.691 |
iliate | -2.675 |
rys | -2.612 |
yg | -2.560 |
Token | her |
Token ID | 607 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
ileaks | +0.391 |
burgh | +0.385 |
ocrates | +0.366 |
roid | +0.365 |
paren | +0.363 |
Neg logit contributions | |
LY | -0.310 |
iliate | -0.282 |
lore | -0.281 |
rys | -0.272 |
yg | -0.270 |
Token | family |
Token ID | 1641 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
burgh | +3.402 |
ileaks | +3.376 |
roid | +3.128 |
ocrates | +3.108 |
paren | +3.092 |
Neg logit contributions | |
LY | -4.490 |
iliate | -4.291 |
lore | -4.202 |
rys | -4.120 |
yg | -4.065 |
Token | learned |
Token ID | 4499 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
LY | +2.753 |
lore | +2.551 |
iliate | +2.499 |
rys | +2.454 |
yg | +2.445 |
Neg logit contributions | |
ileaks | -2.165 |
burgh | -2.128 |
ocrates | -2.014 |
paren | -1.995 |
roid | -1.991 |
Token | first |
Token ID | 717 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
LY | +3.101 |
lore | +2.860 |
iliate | +2.760 |
yg | +2.709 |
rys | +2.708 |
Neg logit contributions | |
ileaks | -3.114 |
burgh | -3.083 |
ocrates | -2.937 |
roid | -2.922 |
paren | -2.912 |
Token | - |
Token ID | 12 |
Feature activation | +9.98e+00 |
Pos logit contributions | |
LY | +5.794 |
lore | +5.148 |
look | +5.003 |
iliate | +4.991 |
yg | +4.965 |
Neg logit contributions | |
ileaks | -3.988 |
burgh | -3.963 |
ocrates | -3.712 |
paren | -3.680 |
roid | -3.594 |
Token | hand |
Token ID | 4993 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
LY | +3.946 |
lore | +3.387 |
look | +3.315 |
rys | +3.010 |
yg | +2.951 |
Neg logit contributions | |
ileaks | -9.850 |
burgh | -9.585 |
ocrates | -9.470 |
ocrat | -9.203 |
roid | -9.201 |
Token | about |
Token ID | 546 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
LY | +8.119 |
lore | +7.363 |
look | +6.728 |
ly | +6.629 |
rys | +6.616 |
Neg logit contributions | |
ileaks | -9.716 |
burgh | -9.681 |
paren | -9.345 |
ocrates | -9.325 |
roid | -9.237 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
LY | +2.310 |
lore | +2.106 |
iliate | +2.035 |
rys | +1.996 |
yg | +1.985 |
Neg logit contributions | |
ileaks | -3.179 |
burgh | -3.134 |
ocrates | -3.000 |
paren | -2.981 |
roid | -2.978 |
Token | positive |
Token ID | 3967 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
LY | +1.522 |
lore | +1.414 |
iliate | +1.380 |
rys | +1.362 |
yg | +1.356 |
Neg logit contributions | |
ileaks | -1.339 |
burgh | -1.309 |
ocrates | -1.238 |
roid | -1.231 |
paren | -1.224 |
Token | impact |
Token ID | 2928 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
LY | +1.902 |
lore | +1.759 |
iliate | +1.721 |
yg | +1.690 |
rys | +1.690 |
Neg logit contributions | |
ileaks | -1.640 |
burgh | -1.616 |
ocrates | -1.523 |
roid | -1.498 |
paren | -1.496 |
Token | the |
Token ID | 262 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
ileaks | +3.417 |
burgh | +3.364 |
paren | +3.204 |
roid | +3.191 |
ocrates | +3.185 |
Neg logit contributions | |
LY | -3.478 |
iliate | -3.227 |
lore | -3.169 |
rys | -3.092 |
yg | -3.083 |
Token | Simon |
Token ID | 35475 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
LY | +0.987 |
lore | +0.910 |
iliate | +0.899 |
rys | +0.878 |
yg | +0.874 |
Neg logit contributions | |
ileaks | -0.984 |
burgh | -0.969 |
ocrates | -0.919 |
roid | -0.915 |
paren | -0.911 |
Token | King |
Token ID | 2677 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
LY | +0.877 |
lore | +0.799 |
iliate | +0.786 |
rys | +0.765 |
yg | +0.765 |
Neg logit contributions | |
ileaks | -1.089 |
burgh | -1.067 |
ocrates | -1.023 |
roid | -1.019 |
paren | -1.018 |
Token | , |
Token ID | 11 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
LY | +2.958 |
lore | +2.731 |
iliate | +2.679 |
rys | +2.621 |
yg | +2.615 |
Neg logit contributions | |
ileaks | -2.807 |
burgh | -2.726 |
ocrates | -2.611 |
roid | -2.597 |
paren | -2.576 |
Token | Albion |
Token ID | 47995 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
LY | +0.326 |
lore | +0.300 |
iliate | +0.294 |
rys | +0.288 |
yg | +0.288 |
Neg logit contributions | |
ileaks | -0.357 |
burgh | -0.355 |
ocrates | -0.336 |
roid | -0.334 |
paren | -0.331 |
Token | 's |
Token ID | 338 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
LY | +1.110 |
lore | +1.028 |
iliate | +1.016 |
rys | +0.994 |
yg | +0.990 |
Neg logit contributions | |
ileaks | -0.971 |
burgh | -0.954 |
ocrates | -0.902 |
roid | -0.897 |
paren | -0.894 |
Token | Chief |
Token ID | 5953 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
LY | +0.767 |
lore | +0.705 |
iliate | +0.696 |
rys | +0.679 |
yg | +0.677 |
Neg logit contributions | |
ileaks | -0.793 |
burgh | -0.784 |
ocrates | -0.743 |
roid | -0.739 |
paren | -0.736 |
Token | Commercial |
Token ID | 22724 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
LY | +7.498 |
iliate | +6.898 |
lore | +6.792 |
look | +6.418 |
ly | +6.358 |
Neg logit contributions | |
ileaks | -10.102 |
burgh | -9.431 |
roid | -9.250 |
ocrates | -9.216 |
ocene | -9.177 |
Token | Officer |
Token ID | 10391 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
LY | +3.848 |
iliate | +3.578 |
lore | +3.574 |
yg | +3.435 |
rys | +3.435 |
Neg logit contributions | |
ileaks | -3.532 |
burgh | -3.446 |
ocrates | -3.290 |
roid | -3.242 |
paren | -3.235 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
LY | +4.156 |
lore | +3.815 |
iliate | +3.780 |
rys | +3.703 |
yg | +3.663 |
Neg logit contributions | |
ileaks | -4.072 |
burgh | -3.891 |
paren | -3.780 |
ocrates | -3.762 |
roid | -3.755 |
Token | said |
Token ID | 531 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
LY | +1.084 |
lore | +1.013 |
iliate | +1.003 |
rys | +0.984 |
yg | +0.980 |
Neg logit contributions | |
ileaks | -0.704 |
burgh | -0.692 |
ocrates | -0.645 |
roid | -0.640 |
paren | -0.637 |
Token | : |
Token ID | 25 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
burgh | +1.161 |
ileaks | +1.155 |
roid | +1.086 |
ocrates | +1.084 |
paren | +1.059 |
Neg logit contributions | |
LY | -1.348 |
lore | -1.250 |
iliate | -1.232 |
rys | -1.210 |
yg | -1.208 |
Token | Joshua |
Token ID | 20700 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
LY | +0.133 |
lore | +0.122 |
iliate | +0.120 |
rys | +0.117 |
yg | +0.116 |
Neg logit contributions | |
ileaks | -0.159 |
burgh | -0.157 |
ocrates | -0.149 |
roid | -0.149 |
paren | -0.148 |
Token | E |
Token ID | 412 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
LY | +0.674 |
lore | +0.616 |
iliate | +0.607 |
rys | +0.591 |
yg | +0.589 |
Neg logit contributions | |
ileaks | -0.812 |
burgh | -0.799 |
ocrates | -0.763 |
roid | -0.759 |
paren | -0.757 |
Token | ern |
Token ID | 1142 |
Feature activation | +8.49e+00 |
Pos logit contributions | |
LY | +0.717 |
lore | +0.662 |
iliate | +0.653 |
rys | +0.644 |
yg | +0.640 |
Neg logit contributions | |
ileaks | -0.635 |
burgh | -0.623 |
ocrates | -0.589 |
roid | -0.586 |
paren | -0.584 |
Token | isse |
Token ID | 20782 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
LY | +5.662 |
lore | +5.300 |
iliate | +5.200 |
rys | +5.181 |
yg | +5.155 |
Neg logit contributions | |
ileaks | -5.894 |
burgh | -5.602 |
paren | -5.437 |
ocrates | -5.339 |
roid | -5.310 |
Token | and |
Token ID | 290 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
LY | +2.439 |
lore | +2.226 |
iliate | +2.194 |
yg | +2.156 |
rys | +2.147 |
Neg logit contributions | |
ileaks | -2.840 |
burgh | -2.775 |
ocrates | -2.672 |
paren | -2.644 |
roid | -2.642 |
Token | Beau |
Token ID | 32831 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
LY | +0.889 |
lore | +0.806 |
iliate | +0.794 |
rys | +0.772 |
yg | +0.768 |
Neg logit contributions | |
ileaks | -1.181 |
burgh | -1.163 |
ocrates | -1.113 |
roid | -1.108 |
paren | -1.105 |
Token | Sch |
Token ID | 3059 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
LY | +8.016 |
lore | +7.760 |
rys | +7.471 |
yg | +7.427 |
iliate | +7.415 |
Neg logit contributions | |
ileaks | -8.866 |
ocene | -8.544 |
ocrates | -8.437 |
paren | -8.436 |
burgh | -8.300 |
Token | oen |
Token ID | 6571 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ileaks | +1.207 |
burgh | +1.193 |
ocrates | +1.121 |
roid | +1.121 |
paren | +1.112 |
Neg logit contributions | |
LY | -1.337 |
lore | -1.221 |
iliate | -1.212 |
rys | -1.176 |
yg | -1.176 |
Token | hard |
Token ID | 10424 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
ileaks | +0.842 |
burgh | +0.836 |
ocrates | +0.787 |
roid | +0.784 |
paren | +0.780 |
Neg logit contributions | |
LY | -0.800 |
lore | -0.733 |
iliate | -0.727 |
rys | -0.704 |
yg | -0.703 |
Token | — |
Token ID | 851 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
burgh | +1.589 |
ileaks | +1.575 |
roid | +1.492 |
ocrates | +1.472 |
paren | +1.467 |
Neg logit contributions | |
LY | -1.558 |
lore | -1.431 |
iliate | -1.430 |
rys | -1.374 |
yg | -1.352 |
Token | were |
Token ID | 547 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
LY | +0.478 |
lore | +0.440 |
iliate | +0.434 |
rys | +0.424 |
yg | +0.422 |
Neg logit contributions | |
ileaks | -0.495 |
burgh | -0.490 |
roid | -0.462 |
ocrates | -0.462 |
paren | -0.457 |
Token | my |
Token ID | 616 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
ileaks | +1.507 |
burgh | +1.467 |
roid | +1.399 |
ocrates | +1.396 |
paren | +1.389 |
Neg logit contributions | |
LY | -1.860 |
lore | -1.755 |
iliate | -1.731 |
rys | -1.713 |
yg | -1.684 |
Token | code |
Token ID | 2438 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
ileaks | +3.521 |
burgh | +3.514 |
roid | +3.371 |
ocrates | +3.332 |
paren | +3.293 |
Neg logit contributions | |
LY | -3.564 |
lore | -3.305 |
iliate | -3.297 |
rys | -3.231 |
yg | -3.209 |
Token | ). |
Token ID | 737 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
LY | +3.293 |
lore | +3.027 |
iliate | +2.969 |
rys | +2.899 |
yg | +2.870 |
Neg logit contributions | |
ileaks | -3.241 |
burgh | -3.152 |
ocrates | -2.982 |
roid | -2.973 |
paren | -2.954 |
Token |
|
Token ID | 198 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
ileaks | +0.304 |
burgh | +0.301 |
ocrates | +0.283 |
roid | +0.283 |
paren | +0.281 |
Neg logit contributions | |
LY | -0.330 |
lore | -0.306 |
iliate | -0.305 |
rys | -0.299 |
yg | -0.295 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ileaks | +0.260 |
burgh | +0.258 |
roid | +0.242 |
paren | +0.240 |
ocrates | +0.240 |
Neg logit contributions | |
LY | -0.317 |
lore | -0.295 |
iliate | -0.293 |
rys | -0.288 |
yg | -0.285 |
Token | Lot |
Token ID | 48601 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
ileaks | +1.064 |
burgh | +1.050 |
roid | +0.994 |
paren | +0.990 |
ocrates | +0.984 |
Neg logit contributions | |
LY | -1.137 |
iliate | -1.058 |
lore | -1.054 |
rys | -1.037 |
yg | -1.027 |
Token | Sub |
Token ID | 3834 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
LY | +8.353 |
lore | +7.460 |
iliate | +7.206 |
rys | +7.158 |
look | +6.984 |
Neg logit contributions | |
burgh | -9.283 |
ileaks | -9.100 |
ocrates | -8.729 |
paren | -8.574 |
ocrat | -8.388 |
Token | division |
Token ID | 21426 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
ileaks | +1.807 |
burgh | +1.757 |
roid | +1.661 |
paren | +1.637 |
ocrates | +1.608 |
Neg logit contributions | |
LY | -3.090 |
lore | -2.862 |
iliate | -2.832 |
yg | -2.790 |
rys | -2.778 |
Token |
|
Token ID | 198 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
LY | +2.829 |
lore | +2.582 |
iliate | +2.531 |
rys | +2.481 |
yg | +2.460 |
Neg logit contributions | |
ileaks | -3.058 |
burgh | -2.973 |
ocrates | -2.870 |
paren | -2.849 |
roid | -2.791 |
Token |
|
Token ID | 198 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
burgh | +1.307 |
ileaks | +1.296 |
roid | +1.220 |
paren | +1.206 |
ocrates | +1.192 |
Neg logit contributions | |
LY | -1.745 |
iliate | -1.638 |
lore | -1.633 |
rys | -1.609 |
yg | -1.580 |
Token | After |
Token ID | 3260 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
ileaks | +2.670 |
burgh | +2.648 |
roid | +2.535 |
paren | +2.506 |
ocrates | +2.461 |
Neg logit contributions | |
LY | -2.535 |
iliate | -2.395 |
lore | -2.349 |
rys | -2.338 |
yg | -2.315 |
Token | of |
Token ID | 286 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
burgh | +1.612 |
ileaks | +1.599 |
ocrates | +1.508 |
roid | +1.497 |
paren | +1.476 |
Neg logit contributions | |
LY | -1.761 |
iliate | -1.643 |
lore | -1.636 |
yg | -1.594 |
rys | -1.585 |
Token | the |
Token ID | 262 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
LY | +0.885 |
lore | +0.815 |
iliate | +0.806 |
rys | +0.787 |
yg | +0.784 |
Neg logit contributions | |
ileaks | -0.877 |
burgh | -0.865 |
ocrates | -0.819 |
roid | -0.815 |
paren | -0.812 |
Token | city |
Token ID | 1748 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
LY | +0.227 |
lore | +0.210 |
iliate | +0.208 |
rys | +0.203 |
yg | +0.202 |
Neg logit contributions | |
ileaks | -0.224 |
burgh | -0.224 |
ocrates | -0.210 |
roid | -0.209 |
paren | -0.208 |
Token | 's |
Token ID | 338 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
burgh | +2.423 |
ileaks | +2.387 |
roid | +2.235 |
ocrates | +2.213 |
paren | +2.186 |
Neg logit contributions | |
LY | -3.280 |
lore | -3.108 |
iliate | -3.082 |
yg | -3.023 |
rys | -3.012 |
Token | famous |
Token ID | 5863 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
LY | +0.498 |
lore | +0.459 |
iliate | +0.453 |
rys | +0.442 |
yg | +0.441 |
Neg logit contributions | |
ileaks | -0.518 |
burgh | -0.514 |
ocrates | -0.486 |
roid | -0.484 |
paren | -0.480 |
Token | Cock |
Token ID | 23769 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
LY | +0.782 |
lore | +0.716 |
iliate | +0.708 |
rys | +0.689 |
yg | +0.686 |
Neg logit contributions | |
ileaks | -0.902 |
burgh | -0.892 |
ocrates | -0.847 |
roid | -0.844 |
paren | -0.840 |
Token | ers |
Token ID | 364 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
LY | +9.072 |
lore | +8.899 |
rys | +8.791 |
yg | +8.777 |
iliate | +8.651 |
Neg logit contributions | |
ileaks | -7.670 |
burgh | -6.862 |
paren | -6.861 |
ocrates | -6.773 |
roid | -6.650 |
Token | Roses |
Token ID | 41244 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
LY | +1.463 |
lore | +1.343 |
iliate | +1.320 |
rys | +1.291 |
yg | +1.287 |
Neg logit contributions | |
ileaks | -1.616 |
burgh | -1.579 |
ocrates | -1.510 |
roid | -1.503 |
paren | -1.499 |
Token | business |
Token ID | 1597 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
LY | +4.677 |
lore | +4.338 |
iliate | +4.153 |
rys | +4.146 |
yg | +4.088 |
Neg logit contributions | |
ileaks | -5.399 |
burgh | -5.012 |
paren | -4.967 |
ocrates | -4.959 |
roid | -4.927 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
LY | +3.142 |
lore | +2.906 |
iliate | +2.846 |
rys | +2.792 |
yg | +2.757 |
Neg logit contributions | |
ileaks | -2.809 |
burgh | -2.680 |
ocrates | -2.580 |
paren | -2.555 |
roid | -2.529 |
Token |
|
Token ID | 198 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
LY | +0.130 |
lore | +0.120 |
iliate | +0.119 |
rys | +0.116 |
yg | +0.116 |
Neg logit contributions | |
ileaks | -0.115 |
burgh | -0.114 |
ocrates | -0.107 |
roid | -0.107 |
paren | -0.106 |
Token | crisis |
Token ID | 4902 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
LY | +1.851 |
lore | +1.698 |
iliate | +1.678 |
rys | +1.641 |
yg | +1.634 |
Neg logit contributions | |
ileaks | -1.908 |
burgh | -1.876 |
ocrates | -1.782 |
roid | -1.776 |
paren | -1.764 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
ileaks | +0.132 |
burgh | +0.130 |
ocrates | +0.122 |
roid | +0.122 |
paren | +0.121 |
Neg logit contributions | |
LY | -0.155 |
lore | -0.144 |
iliate | -0.143 |
rys | -0.140 |
yg | -0.139 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
burgh | +1.442 |
ileaks | +1.434 |
roid | +1.351 |
ocrates | +1.340 |
paren | +1.338 |
Neg logit contributions | |
LY | -1.609 |
lore | -1.509 |
iliate | -1.507 |
rys | -1.477 |
yg | -1.457 |
Token |
|
Token ID | 198 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
burgh | +0.785 |
ileaks | +0.782 |
roid | +0.732 |
paren | +0.726 |
ocrates | +0.720 |
Neg logit contributions | |
LY | -1.011 |
lore | -0.943 |
iliate | -0.943 |
rys | -0.927 |
yg | -0.912 |
Token | High |
Token ID | 11922 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ileaks | +1.535 |
burgh | +1.520 |
roid | +1.439 |
paren | +1.437 |
ocrates | +1.423 |
Neg logit contributions | |
LY | -1.575 |
lore | -1.461 |
iliate | -1.455 |
rys | -1.423 |
yg | -1.413 |
Token | Ear |
Token ID | 2905 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
LY | +1.061 |
lore | +0.972 |
iliate | +0.959 |
rys | +0.938 |
yg | +0.936 |
Neg logit contributions | |
ileaks | -1.031 |
burgh | -1.011 |
ocrates | -0.964 |
roid | -0.955 |
paren | -0.952 |
Token | ning |
Token ID | 768 |
Feature activation | +6.89e+00 |
Pos logit contributions | |
LY | +7.977 |
lore | +7.178 |
rys | +6.979 |
iliate | +6.941 |
ly | +6.608 |
Neg logit contributions | |
ileaks | -9.119 |
burgh | -8.820 |
ocrates | -8.451 |
ocene | -8.410 |
paren | -8.282 |
Token | Potential |
Token ID | 32480 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
LY | +4.411 |
lore | +3.939 |
iliate | +3.864 |
rys | +3.807 |
yg | +3.735 |
Neg logit contributions | |
ileaks | -5.295 |
burgh | -5.088 |
ocrates | -4.914 |
paren | -4.862 |
ocene | -4.777 |
Token | – |
Token ID | 784 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
ileaks | +1.177 |
burgh | +1.170 |
roid | +1.111 |
ocrates | +1.106 |
paren | +1.102 |
Neg logit contributions | |
LY | -1.052 |
lore | -0.971 |
iliate | -0.956 |
rys | -0.934 |
yg | -0.930 |
Token | CAT |
Token ID | 38348 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
burgh | +2.008 |
ileaks | +2.000 |
roid | +1.891 |
ocrates | +1.870 |
paren | +1.868 |
Neg logit contributions | |
LY | -2.077 |
lore | -1.949 |
iliate | -1.927 |
rys | -1.879 |
yg | -1.871 |
Token | adjust |
Token ID | 4532 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
LY | +0.363 |
lore | +0.334 |
iliate | +0.330 |
rys | +0.323 |
yg | +0.321 |
Neg logit contributions | |
ileaks | -0.347 |
burgh | -0.341 |
ocrates | -0.323 |
roid | -0.321 |
paren | -0.320 |
Token | an |
Token ID | 281 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
LY | +0.078 |
lore | +0.072 |
iliate | +0.071 |
rys | +0.070 |
yg | +0.069 |
Neg logit contributions | |
ileaks | -0.072 |
burgh | -0.071 |
ocrates | -0.067 |
roid | -0.067 |
paren | -0.066 |
Token | intricate |
Token ID | 28746 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
ileaks | +0.885 |
burgh | +0.868 |
roid | +0.821 |
ocrates | +0.821 |
paren | +0.806 |
Neg logit contributions | |
LY | -1.022 |
lore | -0.947 |
iliate | -0.936 |
yg | -0.919 |
rys | -0.919 |
Token | network |
Token ID | 3127 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
LY | +2.718 |
lore | +2.508 |
iliate | +2.459 |
rys | +2.419 |
yg | +2.401 |
Neg logit contributions | |
ileaks | -2.603 |
burgh | -2.559 |
paren | -2.423 |
ocrates | -2.419 |
roid | -2.389 |
Token | of |
Token ID | 286 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
LY | +0.451 |
lore | +0.414 |
iliate | +0.408 |
rys | +0.398 |
yg | +0.397 |
Neg logit contributions | |
ileaks | -0.486 |
burgh | -0.479 |
ocrates | -0.455 |
roid | -0.453 |
paren | -0.452 |
Token | c |
Token ID | 269 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
LY | +2.129 |
lore | +1.967 |
iliate | +1.923 |
rys | +1.888 |
yg | +1.880 |
Neg logit contributions | |
ileaks | -2.164 |
burgh | -2.119 |
ocrates | -2.012 |
paren | -2.009 |
roid | -1.993 |
Token | ree |
Token ID | 631 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
LY | +1.519 |
lore | +1.383 |
iliate | +1.373 |
rys | +1.332 |
yg | +1.318 |
Neg logit contributions | |
ileaks | -2.074 |
burgh | -2.048 |
ocrates | -1.953 |
paren | -1.945 |
roid | -1.938 |
Token | ks |
Token ID | 591 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
LY | +6.608 |
yg | +6.153 |
iliate | +6.142 |
look | +6.083 |
lore | +6.073 |
Neg logit contributions | |
ileaks | -9.162 |
━ | -8.823 |
burgh | -8.806 |
ocrates | -8.737 |
visor | -8.604 |
Token | and |
Token ID | 290 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
LY | +0.848 |
lore | +0.783 |
iliate | +0.771 |
rys | +0.753 |
yg | +0.750 |
Neg logit contributions | |
ileaks | -0.853 |
burgh | -0.837 |
ocrates | -0.795 |
roid | -0.791 |
paren | -0.790 |
Token | channels |
Token ID | 9619 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ileaks | +0.484 |
burgh | +0.478 |
roid | +0.455 |
ocrates | +0.454 |
paren | +0.448 |
Neg logit contributions | |
LY | -0.470 |
lore | -0.432 |
iliate | -0.429 |
rys | -0.417 |
yg | -0.415 |
Token | , |
Token ID | 11 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
LY | +1.307 |
lore | +1.215 |
iliate | +1.191 |
rys | +1.168 |
yg | +1.165 |
Neg logit contributions | |
ileaks | -1.152 |
burgh | -1.128 |
ocrates | -1.066 |
paren | -1.062 |
roid | -1.059 |
Token | or |
Token ID | 393 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ileaks | +1.389 |
burgh | +1.371 |
ocrates | +1.309 |
roid | +1.300 |
paren | +1.266 |
Neg logit contributions | |
LY | -1.587 |
iliate | -1.468 |
lore | -1.460 |
rys | -1.424 |
yg | -1.418 |
Token | � |
Token ID | 564 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
LY | +0.553 |
lore | +0.503 |
iliate | +0.495 |
rys | +0.482 |
yg | +0.480 |
Neg logit contributions | |
ileaks | -0.704 |
burgh | -0.693 |
ocrates | -0.662 |
roid | -0.659 |
paren | -0.657 |
Token | � |
Token ID | 250 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ileaks | +0.184 |
burgh | +0.181 |
ocrates | +0.172 |
roid | +0.171 |
paren | +0.170 |
Neg logit contributions | |
LY | -0.177 |
lore | -0.163 |
iliate | -0.161 |
rys | -0.157 |
yg | -0.156 |
Token | Environmental |
Token ID | 47213 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
LY | +0.186 |
lore | +0.171 |
iliate | +0.169 |
rys | +0.165 |
yg | +0.165 |
Neg logit contributions | |
ileaks | -0.187 |
burgh | -0.185 |
ocrates | -0.175 |
roid | -0.174 |
paren | -0.174 |
Token | Justice |
Token ID | 4796 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
burgh | +2.734 |
ileaks | +2.734 |
paren | +2.560 |
roid | +2.557 |
ocrates | +2.547 |
Neg logit contributions | |
LY | -2.715 |
lore | -2.510 |
iliate | -2.492 |
yg | -2.447 |
rys | -2.430 |
Token | , |
Token ID | 11 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ileaks | +1.811 |
burgh | +1.781 |
roid | +1.673 |
ocrates | +1.670 |
paren | +1.661 |
Neg logit contributions | |
LY | -2.205 |
lore | -2.040 |
iliate | -2.029 |
rys | -1.986 |
yg | -1.984 |
Token | Den |
Token ID | 5601 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
ileaks | +0.207 |
burgh | +0.203 |
ocrates | +0.191 |
roid | +0.190 |
paren | +0.189 |
Neg logit contributions | |
LY | -0.277 |
lore | -0.258 |
iliate | -0.255 |
rys | -0.250 |
yg | -0.249 |
Token | ied |
Token ID | 798 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
LY | +7.856 |
lore | +7.326 |
rys | +7.208 |
yg | +7.149 |
iliate | +6.939 |
Neg logit contributions | |
ileaks | -8.342 |
burgh | -8.164 |
ocrates | -8.053 |
nature | -7.898 |
paren | -7.860 |
Token | , |
Token ID | 11 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
LY | +3.245 |
lore | +2.952 |
iliate | +2.922 |
rys | +2.852 |
yg | +2.803 |
Neg logit contributions | |
ileaks | -3.166 |
burgh | -3.053 |
ocrates | -2.950 |
roid | -2.902 |
paren | -2.862 |
Token | � |
Token ID | 447 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ileaks | +0.042 |
burgh | +0.041 |
ocrates | +0.039 |
roid | +0.039 |
paren | +0.039 |
Neg logit contributions | |
LY | -0.036 |
lore | -0.033 |
iliate | -0.033 |
rys | -0.032 |
yg | -0.032 |
Token | � |
Token ID | 251 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
ileaks | +0.921 |
burgh | +0.909 |
ocrates | +0.862 |
roid | +0.860 |
paren | +0.855 |
Neg logit contributions | |
LY | -0.833 |
lore | -0.764 |
iliate | -0.755 |
rys | -0.735 |
yg | -0.732 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ileaks | +0.491 |
burgh | +0.484 |
ocrates | +0.457 |
roid | +0.455 |
paren | +0.454 |
Neg logit contributions | |
LY | -0.524 |
lore | -0.484 |
iliate | -0.479 |
rys | -0.468 |
yg | -0.466 |
Token | somewhat |
Token ID | 6454 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
LY | +1.205 |
lore | +1.112 |
iliate | +1.098 |
rys | +1.075 |
yg | +1.071 |
Neg logit contributions | |
ileaks | -1.126 |
burgh | -1.102 |
ocrates | -1.046 |
roid | -1.040 |
paren | -1.036 |
Token | hack |
Token ID | 8156 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
LY | +0.106 |
lore | +0.098 |
iliate | +0.097 |
rys | +0.095 |
yg | +0.094 |
Neg logit contributions | |
ileaks | -0.099 |
burgh | -0.098 |
ocrates | -0.093 |
roid | -0.092 |
paren | -0.092 |
Token | y |
Token ID | 88 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
LY | +1.878 |
lore | +1.612 |
iliate | +1.610 |
yg | +1.565 |
rys | +1.518 |
Neg logit contributions | |
ileaks | -4.778 |
burgh | -4.745 |
ocrates | -4.600 |
paren | -4.543 |
roid | -4.538 |
Token | way |
Token ID | 835 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
ileaks | +0.077 |
burgh | +0.076 |
ocrates | +0.071 |
roid | +0.071 |
paren | +0.071 |
Neg logit contributions | |
LY | -0.080 |
lore | -0.074 |
iliate | -0.073 |
rys | -0.071 |
yg | -0.071 |
Token | of |
Token ID | 286 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
LY | +2.516 |
lore | +2.285 |
iliate | +2.263 |
yg | +2.201 |
rys | +2.199 |
Neg logit contributions | |
ileaks | -2.790 |
burgh | -2.750 |
ocrates | -2.598 |
roid | -2.585 |
paren | -2.569 |
Token | conve |
Token ID | 24748 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
LY | +1.438 |
lore | +1.336 |
iliate | +1.322 |
rys | +1.293 |
yg | +1.291 |
Neg logit contributions | |
ileaks | -1.127 |
burgh | -1.106 |
ocrates | -1.042 |
roid | -1.035 |
paren | -1.031 |
Token | ying |
Token ID | 1112 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
LY | +5.838 |
iliate | +5.683 |
yg | +5.621 |
lore | +5.546 |
rys | +5.369 |
Neg logit contributions | |
burgh | -10.503 |
ileaks | -10.263 |
ocrates | -9.933 |
ocene | -9.727 |
paren | -9.619 |
Token | that |
Token ID | 326 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
LY | +3.895 |
lore | +3.561 |
iliate | +3.537 |
yg | +3.406 |
rys | +3.403 |
Neg logit contributions | |
ileaks | -4.398 |
burgh | -4.322 |
ocrates | -4.125 |
paren | -4.073 |
roid | -4.029 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
LY | +1.029 |
lore | +0.945 |
iliate | +0.934 |
rys | +0.911 |
yg | +0.909 |
Neg logit contributions | |
ileaks | -1.055 |
burgh | -1.038 |
ocrates | -0.987 |
roid | -0.978 |
paren | -0.978 |
Token | lifetime |
Token ID | 10869 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
LY | +0.881 |
lore | +0.812 |
iliate | +0.802 |
rys | +0.783 |
yg | +0.780 |
Neg logit contributions | |
ileaks | -0.881 |
burgh | -0.866 |
ocrates | -0.824 |
roid | -0.816 |
paren | -0.815 |
Token | of |
Token ID | 286 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ileaks | +2.183 |
burgh | +2.161 |
roid | +2.064 |
ocrates | +2.048 |
paren | +2.039 |
Neg logit contributions | |
LY | -2.322 |
lore | -2.138 |
iliate | -2.131 |
rys | -2.106 |
yg | -2.086 |
Token | . |
Token ID | 13 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
LY | +1.251 |
lore | +1.160 |
iliate | +1.128 |
rys | +1.098 |
yg | +1.088 |
Neg logit contributions | |
ileaks | -1.418 |
burgh | -1.390 |
ocrates | -1.332 |
roid | -1.313 |
paren | -1.308 |
Token | Although |
Token ID | 4900 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
LY | +0.507 |
lore | +0.465 |
iliate | +0.463 |
rys | +0.451 |
yg | +0.448 |
Neg logit contributions | |
ileaks | -0.541 |
burgh | -0.536 |
ocrates | -0.506 |
roid | -0.506 |
paren | -0.503 |
Token | I |
Token ID | 314 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
LY | +0.995 |
lore | +0.914 |
iliate | +0.904 |
rys | +0.882 |
yg | +0.879 |
Neg logit contributions | |
ileaks | -1.035 |
burgh | -1.021 |
ocrates | -0.969 |
roid | -0.966 |
paren | -0.961 |
Token | talked |
Token ID | 6619 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
LY | +0.261 |
lore | +0.240 |
iliate | +0.237 |
rys | +0.231 |
yg | +0.230 |
Neg logit contributions | |
ileaks | -0.270 |
burgh | -0.266 |
ocrates | -0.252 |
roid | -0.251 |
paren | -0.250 |
Token | a |
Token ID | 257 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
LY | +3.505 |
lore | +3.094 |
iliate | +3.040 |
yg | +2.897 |
rys | +2.870 |
Neg logit contributions | |
ileaks | -5.615 |
burgh | -5.567 |
ocrates | -5.321 |
roid | -5.252 |
paren | -5.247 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
LY | +2.281 |
lore | +2.037 |
iliate | +1.983 |
rys | +1.940 |
yg | +1.928 |
Neg logit contributions | |
ileaks | -3.552 |
burgh | -3.482 |
ocrates | -3.351 |
paren | -3.304 |
roid | -3.302 |
Token | about |
Token ID | 546 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
LY | +5.732 |
lore | +4.914 |
iliate | +4.686 |
ly | +4.440 |
yg | +4.432 |
Neg logit contributions | |
ileaks | -10.744 |
burgh | -10.647 |
ocrates | -10.256 |
paren | -10.097 |
roid | -10.058 |
Token | the |
Token ID | 262 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
LY | +2.054 |
lore | +1.891 |
iliate | +1.861 |
rys | +1.810 |
yg | +1.801 |
Neg logit contributions | |
ileaks | -2.206 |
burgh | -2.163 |
ocrates | -2.058 |
roid | -2.040 |
paren | -2.038 |
Token | laughing |
Token ID | 14376 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
LY | +1.684 |
lore | +1.553 |
iliate | +1.528 |
rys | +1.493 |
yg | +1.487 |
Neg logit contributions | |
ileaks | -1.663 |
burgh | -1.629 |
ocrates | -1.549 |
roid | -1.538 |
paren | -1.533 |
Token | Joker |
Token ID | 23582 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
LY | +1.964 |
lore | +1.813 |
iliate | +1.789 |
rys | +1.751 |
yg | +1.750 |
Neg logit contributions | |
ileaks | -1.798 |
burgh | -1.763 |
ocrates | -1.673 |
roid | -1.655 |
paren | -1.655 |
Token | ( |
Token ID | 357 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
ileaks | +0.052 |
burgh | +0.052 |
roid | +0.049 |
ocrates | +0.049 |
paren | +0.048 |
Neg logit contributions | |
LY | -0.057 |
lore | -0.052 |
iliate | -0.052 |
yg | -0.051 |
rys | -0.051 |
Token | AN |
Token ID | 1565 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
burgh | +3.615 |
ileaks | +3.553 |
roid | +3.426 |
paren | +3.391 |
ocrates | +3.384 |
Neg logit contributions | |
LY | -3.027 |
lore | -2.965 |
rys | -2.873 |
iliate | -2.870 |
yg | -2.776 |
Token | TS |
Token ID | 4694 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
burgh | +2.724 |
ileaks | +2.700 |
roid | +2.620 |
ocrates | +2.595 |
paren | +2.593 |
Neg logit contributions | |
LY | -0.635 |
lore | -0.592 |
iliate | -0.582 |
rys | -0.532 |
yg | -0.522 |
Token | � |
Token ID | 447 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
LY | +1.041 |
lore | +0.968 |
iliate | +0.958 |
rys | +0.939 |
yg | +0.939 |
Neg logit contributions | |
ileaks | -0.651 |
burgh | -0.636 |
ocrates | -0.594 |
roid | -0.591 |
paren | -0.586 |
Token | � |
Token ID | 247 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
LY | +0.762 |
lore | +0.721 |
iliate | +0.716 |
rys | +0.704 |
yg | +0.703 |
Neg logit contributions | |
ileaks | -0.240 |
burgh | -0.231 |
ocrates | -0.207 |
roid | -0.204 |
paren | -0.202 |
Token | C |
Token ID | 327 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
LY | +2.015 |
lore | +1.792 |
iliate | +1.749 |
yg | +1.718 |
rys | +1.706 |
Neg logit contributions | |
ileaks | -2.696 |
burgh | -2.650 |
roid | -2.531 |
ocrates | -2.530 |
paren | -2.521 |
Token | OU |
Token ID | 2606 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
LY | +3.257 |
lore | +2.569 |
iliate | +2.529 |
yg | +2.442 |
look | +2.364 |
Neg logit contributions | |
ileaks | -6.797 |
burgh | -6.533 |
ocrates | -6.270 |
roid | -6.212 |
paren | -6.197 |
Token | NS |
Token ID | 8035 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
LY | +5.737 |
MW | +4.311 |
yg | +4.036 |
VP | +4.011 |
lore | +3.996 |
Neg logit contributions | |
ileaks | -11.766 |
ocrates | -11.236 |
burgh | -11.135 |
tremend | -11.060 |
��� | -11.011 |
Token | EL |
Token ID | 3698 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
LY | +0.663 |
lore | +0.583 |
iliate | +0.571 |
rys | +0.550 |
yg | +0.546 |
Neg logit contributions | |
ileaks | -1.375 |
burgh | -1.359 |
ocrates | -1.308 |
roid | -1.303 |
paren | -1.300 |
Token | : |
Token ID | 25 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
LY | +0.870 |
lore | +0.798 |
iliate | +0.787 |
rys | +0.767 |
yg | +0.767 |
Neg logit contributions | |
ileaks | -0.883 |
burgh | -0.867 |
ocrates | -0.825 |
roid | -0.820 |
paren | -0.817 |
Token | We |
Token ID | 775 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
LY | +1.110 |
lore | +1.016 |
iliate | +1.002 |
rys | +0.976 |
yg | +0.974 |
Neg logit contributions | |
ileaks | -1.212 |
burgh | -1.191 |
ocrates | -1.134 |
roid | -1.129 |
paren | -1.125 |
Token | can |
Token ID | 460 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
LY | +0.308 |
lore | +0.282 |
iliate | +0.279 |
rys | +0.272 |
yg | +0.271 |
Neg logit contributions | |
ileaks | -0.340 |
burgh | -0.335 |
ocrates | -0.319 |
roid | -0.317 |
paren | -0.316 |
Token | can |
Token ID | 460 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
LY | +2.329 |
lore | +2.104 |
iliate | +2.063 |
rys | +2.011 |
yg | +1.991 |
Neg logit contributions | |
ileaks | -3.154 |
burgh | -3.079 |
ocrates | -2.953 |
paren | -2.946 |
roid | -2.935 |
Token | now |
Token ID | 783 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
LY | +0.226 |
lore | +0.210 |
iliate | +0.206 |
rys | +0.201 |
yg | +0.200 |
Neg logit contributions | |
ileaks | -0.207 |
burgh | -0.206 |
roid | -0.194 |
ocrates | -0.193 |
paren | -0.191 |
Token | hop |
Token ID | 1725 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
LY | +0.432 |
lore | +0.401 |
iliate | +0.396 |
rys | +0.386 |
yg | +0.384 |
Neg logit contributions | |
ileaks | -0.396 |
burgh | -0.393 |
roid | -0.371 |
ocrates | -0.370 |
paren | -0.366 |
Token | off |
Token ID | 572 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
ileaks | +1.981 |
burgh | +1.970 |
roid | +1.847 |
ocrates | +1.843 |
paren | +1.811 |
Neg logit contributions | |
LY | -2.333 |
lore | -2.166 |
iliate | -2.157 |
rys | -2.094 |
yg | -2.067 |
Token | their |
Token ID | 511 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ileaks | +2.034 |
burgh | +2.032 |
roid | +1.932 |
ocrates | +1.918 |
paren | +1.875 |
Neg logit contributions | |
LY | -2.401 |
lore | -2.253 |
iliate | -2.223 |
yg | -2.146 |
rys | -2.129 |
Token | cou |
Token ID | 2284 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
burgh | +0.955 |
ileaks | +0.951 |
roid | +0.901 |
ocrates | +0.899 |
paren | +0.885 |
Neg logit contributions | |
LY | -0.891 |
lore | -0.829 |
iliate | -0.814 |
yg | -0.789 |
rys | -0.782 |
Token | ches |
Token ID | 2052 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
LY | +5.550 |
rys | +5.463 |
lore | +5.334 |
yg | +5.252 |
look | +4.921 |
Neg logit contributions | |
ileaks | -10.474 |
burgh | -10.453 |
ocrates | -10.181 |
ocene | -9.824 |
ocrat | -9.790 |
Token | and |
Token ID | 290 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
LY | +1.964 |
lore | +1.791 |
iliate | +1.761 |
rys | +1.727 |
yg | +1.722 |
Neg logit contributions | |
ileaks | -2.323 |
burgh | -2.286 |
ocrates | -2.178 |
paren | -2.162 |
roid | -2.153 |
Token | get |
Token ID | 651 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
LY | +0.856 |
lore | +0.790 |
iliate | +0.781 |
rys | +0.762 |
yg | +0.759 |
Neg logit contributions | |
ileaks | -0.813 |
burgh | -0.801 |
ocrates | -0.758 |
roid | -0.755 |
paren | -0.751 |
Token | active |
Token ID | 4075 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
LY | +1.453 |
lore | +1.339 |
iliate | +1.323 |
rys | +1.292 |
yg | +1.287 |
Neg logit contributions | |
ileaks | -1.410 |
burgh | -1.387 |
ocrates | -1.315 |
roid | -1.309 |
paren | -1.304 |
Token | with |
Token ID | 351 |
Feature activation | +5.17e-03 |
Pos logit contributions | |
LY | +0.371 |
lore | +0.346 |
iliate | +0.342 |
rys | +0.334 |
yg | +0.333 |
Neg logit contributions | |
ileaks | -0.332 |
burgh | -0.330 |
roid | -0.311 |
ocrates | -0.310 |
paren | -0.308 |
Token | ategic |
Token ID | 47917 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
ileaks | +0.239 |
burgh | +0.234 |
ocrates | +0.221 |
roid | +0.220 |
paren | +0.219 |
Neg logit contributions | |
LY | -0.305 |
lore | -0.283 |
iliate | -0.280 |
rys | -0.274 |
yg | -0.274 |
Token | Human |
Token ID | 5524 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ileaks | +1.940 |
burgh | +1.922 |
roid | +1.824 |
ocrates | +1.810 |
paren | +1.809 |
Neg logit contributions | |
LY | -1.918 |
lore | -1.774 |
iliate | -1.749 |
rys | -1.716 |
yg | -1.714 |
Token | Resource |
Token ID | 20857 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
LY | +1.482 |
lore | +1.340 |
iliate | +1.328 |
rys | +1.277 |
yg | +1.268 |
Neg logit contributions | |
ileaks | -2.023 |
burgh | -1.997 |
ocrates | -1.911 |
paren | -1.896 |
roid | -1.885 |
Token | Management |
Token ID | 8549 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
LY | +0.360 |
lore | +0.329 |
iliate | +0.325 |
rys | +0.316 |
yg | +0.315 |
Neg logit contributions | |
ileaks | -0.427 |
burgh | -0.422 |
ocrates | -0.401 |
roid | -0.400 |
paren | -0.398 |
Token | ) |
Token ID | 8 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
LY | +1.745 |
lore | +1.612 |
iliate | +1.598 |
rys | +1.566 |
yg | +1.555 |
Neg logit contributions | |
ileaks | -1.467 |
burgh | -1.424 |
ocrates | -1.360 |
paren | -1.344 |
roid | -1.336 |
Token | Cur |
Token ID | 4424 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
LY | +0.267 |
lore | +0.247 |
iliate | +0.243 |
rys | +0.238 |
yg | +0.237 |
Neg logit contributions | |
ileaks | -0.255 |
burgh | -0.252 |
ocrates | -0.238 |
roid | -0.237 |
paren | -0.236 |
Token | ric |
Token ID | 1173 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
LY | +3.395 |
rys | +3.181 |
iliate | +2.715 |
lore | +2.550 |
look | +2.479 |
Neg logit contributions | |
ileaks | -12.784 |
ocrates | -12.328 |
burgh | -12.142 |
paren | -12.003 |
nature | -11.937 |
Token | ulum |
Token ID | 14452 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
LY | +2.520 |
lore | +2.256 |
iliate | +2.218 |
yg | +2.146 |
rys | +2.119 |
Neg logit contributions | |
ileaks | -4.992 |
burgh | -4.893 |
ocrates | -4.723 |
paren | -4.704 |
roid | -4.639 |
Token | guidelines |
Token ID | 9949 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
LY | +2.124 |
lore | +1.952 |
iliate | +1.933 |
rys | +1.890 |
yg | +1.874 |
Neg logit contributions | |
ileaks | -2.017 |
burgh | -1.967 |
ocrates | -1.879 |
roid | -1.860 |
paren | -1.858 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
ileaks | +2.508 |
burgh | +2.499 |
ocrates | +2.330 |
paren | +2.308 |
roid | +2.307 |
Neg logit contributions | |
LY | -3.322 |
lore | -3.124 |
iliate | -3.104 |
rys | -3.037 |
yg | -3.007 |
Token |
|
Token ID | 198 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
burgh | +1.248 |
ileaks | +1.233 |
ocrates | +1.159 |
roid | +1.158 |
paren | +1.147 |
Neg logit contributions | |
LY | -1.328 |
iliate | -1.248 |
lore | -1.242 |
rys | -1.219 |
yg | -1.190 |
Token | even |
Token ID | 772 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
LY | +0.570 |
lore | +0.524 |
iliate | +0.517 |
rys | +0.505 |
yg | +0.503 |
Neg logit contributions | |
ileaks | -0.596 |
burgh | -0.588 |
ocrates | -0.558 |
roid | -0.556 |
paren | -0.552 |
Token | if |
Token ID | 611 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
ileaks | +2.742 |
burgh | +2.737 |
roid | +2.593 |
ocrates | +2.581 |
paren | +2.521 |
Neg logit contributions | |
LY | -3.171 |
iliate | -2.959 |
lore | -2.950 |
rys | -2.891 |
yg | -2.840 |
Token | that |
Token ID | 326 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
ileaks | +0.525 |
burgh | +0.518 |
roid | +0.489 |
ocrates | +0.487 |
paren | +0.484 |
Neg logit contributions | |
LY | -0.560 |
lore | -0.516 |
iliate | -0.514 |
yg | -0.498 |
rys | -0.498 |
Token | closer |
Token ID | 5699 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ileaks | +2.234 |
burgh | +2.207 |
roid | +2.114 |
visor | +2.087 |
paren | +2.083 |
Neg logit contributions | |
LY | -2.185 |
lore | -2.042 |
iliate | -2.017 |
rys | -1.959 |
yg | -1.955 |
Token | was |
Token ID | 373 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
LY | +1.463 |
lore | +1.335 |
iliate | +1.317 |
rys | +1.285 |
yg | +1.279 |
Neg logit contributions | |
ileaks | -1.689 |
burgh | -1.665 |
ocrates | -1.587 |
roid | -1.574 |
paren | -1.571 |
Token | Craig |
Token ID | 13854 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
LY | +0.443 |
lore | +0.408 |
iliate | +0.404 |
rys | +0.392 |
yg | +0.391 |
Neg logit contributions | |
ileaks | -0.455 |
burgh | -0.449 |
roid | -0.425 |
ocrates | -0.425 |
paren | -0.422 |
Token | Kim |
Token ID | 6502 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
LY | +5.552 |
lore | +5.312 |
iliate | +5.047 |
yg | +5.041 |
rys | +4.888 |
Neg logit contributions | |
ileaks | -10.268 |
burgh | -10.126 |
paren | -9.804 |
roid | -9.598 |
━ | -9.436 |
Token | b |
Token ID | 65 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
ileaks | +0.596 |
burgh | +0.584 |
ocrates | +0.555 |
roid | +0.552 |
paren | +0.544 |
Neg logit contributions | |
LY | -0.622 |
lore | -0.576 |
iliate | -0.569 |
rys | -0.559 |
yg | -0.553 |
Token | rel |
Token ID | 2411 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ileaks | +2.912 |
burgh | +2.894 |
roid | +2.840 |
ocrates | +2.833 |
nature | +2.742 |
Neg logit contributions | |
LY | -2.462 |
iliate | -2.325 |
lore | -2.238 |
yg | -2.077 |
look | -2.067 |
Token | . |
Token ID | 13 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
ileaks | +1.126 |
burgh | +1.112 |
roid | +1.041 |
ocrates | +1.038 |
paren | +1.035 |
Neg logit contributions | |
LY | -1.396 |
lore | -1.299 |
iliate | -1.281 |
rys | -1.258 |
yg | -1.256 |
Token | Kim |
Token ID | 6502 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ileaks | +0.369 |
burgh | +0.368 |
roid | +0.345 |
ocrates | +0.345 |
paren | +0.342 |
Neg logit contributions | |
LY | -0.367 |
iliate | -0.339 |
lore | -0.338 |
rys | -0.331 |
yg | -0.327 |
Token | . |
Token ID | 13 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
LY | +2.223 |
lore | +2.025 |
iliate | +2.020 |
rys | +1.958 |
yg | +1.947 |
Neg logit contributions | |
ileaks | -2.146 |
burgh | -2.097 |
ocrates | -1.998 |
roid | -1.977 |
paren | -1.976 |
Token | O |
Token ID | 440 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
LY | +0.067 |
lore | +0.062 |
iliate | +0.062 |
rys | +0.061 |
yg | +0.060 |
Neg logit contributions | |
ileaks | -0.062 |
burgh | -0.062 |
ocrates | -0.058 |
roid | -0.058 |
paren | -0.058 |
Token | urs |
Token ID | 1834 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
LY | +0.982 |
lore | +0.883 |
iliate | +0.872 |
rys | +0.856 |
yg | +0.850 |
Neg logit contributions | |
ileaks | -1.135 |
burgh | -1.113 |
ocrates | -1.064 |
roid | -1.055 |
paren | -1.053 |
Token | is |
Token ID | 318 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
LY | +3.402 |
lore | +3.024 |
iliate | +3.000 |
rys | +2.921 |
yg | +2.883 |
Neg logit contributions | |
ileaks | -4.687 |
burgh | -4.558 |
ocrates | -4.390 |
paren | -4.356 |
roid | -4.347 |
Token | a |
Token ID | 257 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
LY | +1.600 |
lore | +1.474 |
iliate | +1.457 |
rys | +1.423 |
yg | +1.418 |
Neg logit contributions | |
ileaks | -1.482 |
burgh | -1.454 |
ocrates | -1.374 |
roid | -1.370 |
paren | -1.365 |
Token | Bachelor |
Token ID | 33399 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
LY | +1.087 |
lore | +0.999 |
iliate | +0.987 |
rys | +0.965 |
yg | +0.961 |
Neg logit contributions | |
ileaks | -1.083 |
burgh | -1.064 |
ocrates | -1.009 |
roid | -1.005 |
paren | -1.002 |
Token | of |
Token ID | 286 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
LY | +8.042 |
iliate | +7.193 |
rys | +6.878 |
lore | +6.866 |
ly | +6.795 |
Neg logit contributions | |
ileaks | -8.313 |
burgh | -8.257 |
ocrates | -7.926 |
paren | -7.858 |
roid | -7.522 |
Token | Science |
Token ID | 5800 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
burgh | +3.335 |
ileaks | +3.314 |
ocrates | +3.163 |
ocrat | +3.111 |
paren | +3.070 |
Neg logit contributions | |
LY | -3.906 |
iliate | -3.620 |
lore | -3.601 |
rys | -3.578 |
yg | -3.494 |
Token | degree |
Token ID | 4922 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
LY | +1.798 |
lore | +1.636 |
iliate | +1.633 |
rys | +1.588 |
yg | +1.573 |
Neg logit contributions | |
ileaks | -1.793 |
burgh | -1.753 |
ocrates | -1.666 |
paren | -1.660 |
roid | -1.652 |
Token | in |
Token ID | 287 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
LY | +3.878 |
iliate | +3.508 |
lore | +3.495 |
rys | +3.371 |
yg | +3.321 |
Neg logit contributions | |
ileaks | -4.195 |
burgh | -4.041 |
ocrates | -3.871 |
paren | -3.845 |
roid | -3.808 |
Token | business |
Token ID | 1597 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ileaks | +1.443 |
burgh | +1.437 |
ocrates | +1.348 |
roid | +1.337 |
paren | +1.333 |
Neg logit contributions | |
LY | -1.795 |
lore | -1.666 |
iliate | -1.644 |
rys | -1.624 |
yg | -1.619 |
Token | in |
Token ID | 287 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
LY | +0.413 |
lore | +0.385 |
iliate | +0.380 |
yg | +0.368 |
rys | +0.367 |
Neg logit contributions | |
ileaks | -0.395 |
burgh | -0.390 |
ocrates | -0.371 |
roid | -0.368 |
paren | -0.365 |
Token | Brown |
Token ID | 4373 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
ileaks | +2.164 |
burgh | +2.153 |
ocrates | +2.021 |
roid | +1.975 |
paren | +1.943 |
Neg logit contributions | |
LY | -3.078 |
lore | -2.900 |
iliate | -2.890 |
yg | -2.772 |
rys | -2.727 |
Token | � |
Token ID | 447 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
LY | +2.946 |
lore | +2.733 |
iliate | +2.696 |
rys | +2.648 |
yg | +2.633 |
Neg logit contributions | |
ileaks | -2.289 |
burgh | -2.228 |
ocrates | -2.118 |
roid | -2.101 |
paren | -2.078 |
Token | � |
Token ID | 247 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
ileaks | +0.241 |
burgh | +0.234 |
ocrates | +0.206 |
roid | +0.205 |
paren | +0.203 |
Neg logit contributions | |
LY | -0.795 |
lore | -0.754 |
iliate | -0.748 |
rys | -0.738 |
yg | -0.736 |
Token | s |
Token ID | 82 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
LY | +0.319 |
lore | +0.296 |
iliate | +0.293 |
rys | +0.285 |
yg | +0.285 |
Neg logit contributions | |
ileaks | -0.262 |
burgh | -0.258 |
ocrates | -0.242 |
roid | -0.242 |
paren | -0.240 |
Token | ear |
Token ID | 1027 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
LY | +1.528 |
lore | +1.414 |
iliate | +1.398 |
rys | +1.367 |
yg | +1.362 |
Neg logit contributions | |
ileaks | -1.348 |
burgh | -1.326 |
ocrates | -1.253 |
roid | -1.247 |
paren | -1.241 |
Token | about |
Token ID | 546 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
LY | +7.554 |
lore | +6.916 |
rys | +6.677 |
iliate | +6.636 |
yg | +6.493 |
Neg logit contributions | |
ileaks | -8.728 |
burgh | -8.554 |
ocrates | -7.970 |
paren | -7.964 |
nature | -7.909 |
Token | kicking |
Token ID | 17997 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
LY | +1.968 |
lore | +1.818 |
iliate | +1.798 |
rys | +1.760 |
yg | +1.749 |
Neg logit contributions | |
ileaks | -1.729 |
burgh | -1.697 |
ocrates | -1.600 |
roid | -1.593 |
paren | -1.590 |
Token | football |
Token ID | 4346 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
LY | +3.637 |
lore | +3.360 |
iliate | +3.288 |
rys | +3.248 |
yg | +3.213 |
Neg logit contributions | |
ileaks | -3.775 |
burgh | -3.686 |
ocrates | -3.482 |
paren | -3.475 |
roid | -3.451 |
Token | s |
Token ID | 82 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
LY | +1.570 |
lore | +1.454 |
iliate | +1.437 |
rys | +1.405 |
yg | +1.400 |
Neg logit contributions | |
ileaks | -1.362 |
burgh | -1.338 |
ocrates | -1.264 |
roid | -1.258 |
paren | -1.252 |
Token | . |
Token ID | 13 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
LY | +3.332 |
lore | +3.089 |
iliate | +3.015 |
rys | +2.952 |
yg | +2.930 |
Neg logit contributions | |
ileaks | -3.249 |
burgh | -3.156 |
roid | -3.004 |
paren | -2.991 |
ocrates | -2.983 |
Token | awareness |
Token ID | 47812 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
LY | +4.161 |
lore | +4.009 |
iliate | +3.839 |
yg | +3.828 |
rys | +3.813 |
Neg logit contributions | |
ileaks | -3.828 |
burgh | -3.675 |
ocrates | -3.542 |
roid | -3.527 |
ocene | -3.480 |
Token | that |
Token ID | 326 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
LY | +2.428 |
lore | +2.240 |
iliate | +2.202 |
yg | +2.154 |
rys | +2.140 |
Neg logit contributions | |
ileaks | -2.387 |
burgh | -2.341 |
ocrates | -2.221 |
paren | -2.198 |
roid | -2.197 |
Token | they |
Token ID | 484 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
ileaks | +0.945 |
burgh | +0.922 |
ocrates | +0.875 |
paren | +0.871 |
roid | +0.869 |
Neg logit contributions | |
LY | -1.018 |
lore | -0.944 |
iliate | -0.939 |
rys | -0.909 |
yg | -0.902 |
Token | are |
Token ID | 389 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
LY | +1.644 |
lore | +1.493 |
iliate | +1.477 |
yg | +1.445 |
rys | +1.436 |
Neg logit contributions | |
ileaks | -1.947 |
burgh | -1.923 |
ocrates | -1.824 |
paren | -1.814 |
roid | -1.806 |
Token | openly |
Token ID | 11764 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
LY | +3.412 |
lore | +3.103 |
yg | +3.025 |
iliate | +3.007 |
rys | +2.971 |
Neg logit contributions | |
ileaks | -3.333 |
burgh | -3.267 |
ocrates | -3.052 |
roid | -3.050 |
paren | -3.037 |
Token | lying |
Token ID | 9105 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
LY | +3.529 |
lore | +3.223 |
iliate | +3.166 |
yg | +3.150 |
rys | +3.117 |
Neg logit contributions | |
ileaks | -2.699 |
burgh | -2.641 |
ocrates | -2.515 |
roid | -2.486 |
paren | -2.464 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
LY | +7.091 |
lore | +6.237 |
iliate | +6.118 |
yg | +6.048 |
ly | +5.915 |
Neg logit contributions | |
ileaks | -8.919 |
burgh | -8.910 |
ocrates | -8.461 |
roid | -8.424 |
paren | -8.419 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
ileaks | +1.595 |
burgh | +1.587 |
ocrates | +1.484 |
roid | +1.478 |
paren | +1.470 |
Neg logit contributions | |
LY | -1.751 |
iliate | -1.655 |
lore | -1.631 |
rys | -1.613 |
yg | -1.580 |
Token |
|
Token ID | 198 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
ileaks | +1.052 |
burgh | +1.051 |
roid | +0.981 |
paren | +0.974 |
ocrates | +0.967 |
Neg logit contributions | |
LY | -1.356 |
iliate | -1.272 |
lore | -1.270 |
rys | -1.248 |
yg | -1.230 |
Token | With |
Token ID | 3152 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ileaks | +1.905 |
burgh | +1.877 |
roid | +1.770 |
paren | +1.766 |
ocrates | +1.747 |
Neg logit contributions | |
LY | -2.089 |
iliate | -1.988 |
lore | -1.960 |
rys | -1.934 |
yg | -1.901 |
Token | Paul |
Token ID | 3362 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
ileaks | +1.237 |
burgh | +1.211 |
ocrates | +1.146 |
paren | +1.140 |
roid | +1.136 |
Neg logit contributions | |
LY | -1.355 |
lore | -1.255 |
iliate | -1.245 |
rys | -1.210 |
yg | -1.204 |
Token | or |
Token ID | 393 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
LY | +0.381 |
lore | +0.351 |
iliate | +0.346 |
rys | +0.338 |
yg | +0.336 |
Neg logit contributions | |
ileaks | -0.394 |
burgh | -0.388 |
ocrates | -0.369 |
roid | -0.367 |
paren | -0.366 |
Token | angry |
Token ID | 7954 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
LY | +0.717 |
lore | +0.655 |
iliate | +0.651 |
yg | +0.637 |
rys | +0.636 |
Neg logit contributions | |
ileaks | -0.696 |
burgh | -0.683 |
ocrates | -0.652 |
roid | -0.641 |
paren | -0.641 |
Token | , |
Token ID | 11 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
LY | +2.873 |
lore | +2.602 |
iliate | +2.569 |
yg | +2.512 |
rys | +2.490 |
Neg logit contributions | |
ileaks | -3.259 |
burgh | -3.195 |
ocrates | -3.045 |
paren | -3.009 |
roid | -2.994 |
Token | have |
Token ID | 423 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
LY | +0.051 |
lore | +0.047 |
iliate | +0.046 |
rys | +0.045 |
yg | +0.045 |
Neg logit contributions | |
ileaks | -0.053 |
burgh | -0.052 |
ocrates | -0.050 |
roid | -0.049 |
paren | -0.049 |
Token | trouble |
Token ID | 5876 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
LY | +0.501 |
lore | +0.464 |
iliate | +0.458 |
rys | +0.448 |
yg | +0.446 |
Neg logit contributions | |
ileaks | -0.459 |
burgh | -0.452 |
ocrates | -0.427 |
roid | -0.426 |
paren | -0.424 |
Token | forming |
Token ID | 14583 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
LY | +1.519 |
lore | +1.403 |
iliate | +1.389 |
yg | +1.366 |
rys | +1.356 |
Neg logit contributions | |
ileaks | -1.223 |
burgh | -1.204 |
ocrates | -1.135 |
roid | -1.120 |
paren | -1.118 |
Token | relationships |
Token ID | 6958 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
LY | +7.340 |
lore | +6.554 |
iliate | +6.530 |
ly | +6.378 |
yg | +6.290 |
Neg logit contributions | |
ileaks | -8.646 |
burgh | -8.334 |
ocrates | -8.182 |
visor | -8.007 |
roid | -7.917 |
Token | and |
Token ID | 290 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
LY | +3.024 |
iliate | +2.743 |
lore | +2.728 |
yg | +2.635 |
rys | +2.600 |
Neg logit contributions | |
ileaks | -3.770 |
burgh | -3.698 |
ocrates | -3.514 |
roid | -3.478 |
paren | -3.438 |
Token | suffer |
Token ID | 8659 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
ileaks | +0.345 |
burgh | +0.340 |
ocrates | +0.322 |
roid | +0.322 |
paren | +0.320 |
Neg logit contributions | |
LY | -0.330 |
lore | -0.304 |
iliate | -0.300 |
rys | -0.293 |
yg | -0.291 |
Token | from |
Token ID | 422 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ileaks | +2.198 |
burgh | +2.196 |
roid | +2.117 |
paren | +2.076 |
ocrates | +2.042 |
Neg logit contributions | |
LY | -2.397 |
lore | -2.243 |
iliate | -2.215 |
rys | -2.161 |
yg | -2.120 |
Token | decreased |
Token ID | 11832 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ileaks | +0.629 |
burgh | +0.625 |
roid | +0.593 |
paren | +0.585 |
ocrates | +0.580 |
Neg logit contributions | |
LY | -0.802 |
lore | -0.749 |
iliate | -0.743 |
rys | -0.724 |
yg | -0.718 |
Token | are |
Token ID | 389 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
ileaks | +0.480 |
burgh | +0.476 |
roid | +0.452 |
ocrates | +0.448 |
paren | +0.445 |
Neg logit contributions | |
LY | -0.492 |
lore | -0.451 |
iliate | -0.448 |
rys | -0.438 |
yg | -0.436 |
Token | what |
Token ID | 644 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
LY | +0.698 |
lore | +0.646 |
iliate | +0.640 |
rys | +0.624 |
yg | +0.622 |
Neg logit contributions | |
ileaks | -0.631 |
burgh | -0.622 |
ocrates | -0.588 |
roid | -0.586 |
paren | -0.582 |
Token | destabil |
Token ID | 27397 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
LY | +0.276 |
lore | +0.254 |
iliate | +0.251 |
rys | +0.245 |
yg | +0.244 |
Neg logit contributions | |
ileaks | -0.290 |
burgh | -0.286 |
ocrates | -0.272 |
roid | -0.271 |
paren | -0.268 |
Token | ize |
Token ID | 1096 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
LY | +2.416 |
iliate | +2.223 |
lore | +2.220 |
rys | +2.138 |
yg | +2.131 |
Neg logit contributions | |
ileaks | -2.498 |
burgh | -2.469 |
ocrates | -2.345 |
paren | -2.325 |
roid | -2.307 |
Token | the |
Token ID | 262 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
LY | +1.462 |
lore | +1.344 |
iliate | +1.328 |
rys | +1.296 |
yg | +1.292 |
Neg logit contributions | |
ileaks | -1.466 |
burgh | -1.442 |
ocrates | -1.368 |
roid | -1.362 |
paren | -1.357 |
Token | super |
Token ID | 2208 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
LY | +0.462 |
lore | +0.426 |
iliate | +0.420 |
rys | +0.411 |
yg | +0.408 |
Neg logit contributions | |
ileaks | -0.480 |
burgh | -0.474 |
ocrates | -0.449 |
roid | -0.448 |
paren | -0.445 |
Token | conduct |
Token ID | 36495 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
burgh | +6.278 |
visor | +6.161 |
ileaks | +6.045 |
nature | +5.978 |
paren | +5.777 |
Neg logit contributions | |
LY | -11.570 |
iliate | -10.560 |
lore | -10.414 |
yg | -10.403 |
rys | -10.307 |
Token | ing |
Token ID | 278 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
ileaks | +2.760 |
burgh | +2.734 |
roid | +2.647 |
ocrates | +2.573 |
ocrat | +2.564 |
Neg logit contributions | |
LY | -3.565 |
lore | -3.245 |
iliate | -3.169 |
yg | -3.140 |
rys | -3.129 |
Token | state |
Token ID | 1181 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
LY | +0.680 |
lore | +0.633 |
iliate | +0.626 |
rys | +0.610 |
yg | +0.607 |
Neg logit contributions | |
ileaks | -0.668 |
burgh | -0.661 |
roid | -0.628 |
ocrates | -0.622 |
paren | -0.618 |
Token | above |
Token ID | 2029 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
LY | +0.280 |
lore | +0.261 |
iliate | +0.259 |
rys | +0.252 |
yg | +0.250 |
Neg logit contributions | |
ileaks | -0.247 |
burgh | -0.244 |
roid | -0.231 |
ocrates | -0.230 |
paren | -0.227 |
Token | the |
Token ID | 262 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
LY | +2.426 |
lore | +2.212 |
iliate | +2.177 |
rys | +2.137 |
yg | +2.135 |
Neg logit contributions | |
ileaks | -2.512 |
burgh | -2.466 |
ocrates | -2.352 |
roid | -2.345 |
paren | -2.333 |
Token | order |
Token ID | 1502 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
ileaks | +1.210 |
burgh | +1.203 |
roid | +1.124 |
ocrates | +1.117 |
paren | +1.109 |
Neg logit contributions | |
LY | -1.570 |
lore | -1.460 |
iliate | -1.448 |
rys | -1.417 |
yg | -1.411 |
Token | to |
Token ID | 284 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
LY | +2.058 |
lore | +1.875 |
iliate | +1.865 |
rys | +1.801 |
yg | +1.798 |
Neg logit contributions | |
ileaks | -2.177 |
burgh | -2.132 |
ocrates | -2.021 |
paren | -2.005 |
roid | -2.004 |
Token | enc |
Token ID | 2207 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
LY | +1.212 |
lore | +1.113 |
iliate | +1.101 |
rys | +1.074 |
yg | +1.069 |
Neg logit contributions | |
ileaks | -1.255 |
burgh | -1.235 |
ocrates | -1.173 |
roid | -1.164 |
paren | -1.163 |
Token | ase |
Token ID | 589 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
LY | +3.331 |
iliate | +3.184 |
lore | +3.099 |
rys | +3.006 |
yg | +2.967 |
Neg logit contributions | |
ileaks | -5.798 |
burgh | -5.763 |
ocrates | -5.560 |
paren | -5.463 |
visor | -5.301 |
Token | the |
Token ID | 262 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
LY | +0.193 |
lore | +0.177 |
iliate | +0.175 |
rys | +0.171 |
yg | +0.170 |
Neg logit contributions | |
ileaks | -0.195 |
burgh | -0.192 |
ocrates | -0.182 |
roid | -0.181 |
paren | -0.180 |
Token | super |
Token ID | 2208 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
ileaks | +0.604 |
burgh | +0.596 |
roid | +0.562 |
ocrates | +0.561 |
paren | +0.555 |
Neg logit contributions | |
LY | -0.615 |
lore | -0.567 |
iliate | -0.563 |
rys | -0.549 |
yg | -0.546 |
Token | secret |
Token ID | 3200 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
burgh | +7.936 |
ileaks | +7.868 |
visor | +7.685 |
nature | +7.603 |
roid | +7.450 |
Neg logit contributions | |
LY | -9.325 |
iliate | -8.739 |
lore | -8.526 |
rys | -8.372 |
yg | -8.357 |
Token | Cooper |
Token ID | 10382 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
LY | +0.233 |
lore | +0.215 |
iliate | +0.213 |
rys | +0.208 |
yg | +0.207 |
Neg logit contributions | |
ileaks | -0.231 |
burgh | -0.228 |
roid | -0.215 |
ocrates | -0.215 |
paren | -0.213 |
Token | Vault |
Token ID | 23450 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
LY | +1.908 |
lore | +1.757 |
iliate | +1.735 |
rys | +1.692 |
yg | +1.684 |
Neg logit contributions | |
ileaks | -1.943 |
burgh | -1.907 |
ocrates | -1.840 |
paren | -1.819 |
roid | -1.801 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
LY | +2.597 |
lore | +2.396 |
iliate | +2.360 |
rys | +2.312 |
yg | +2.295 |
Neg logit contributions | |
ileaks | -2.410 |
burgh | -2.351 |
ocrates | -2.250 |
paren | -2.243 |
roid | -2.218 |
Token | There |
Token ID | 1318 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
burgh | +1.907 |
ileaks | +1.888 |
roid | +1.778 |
ocrates | +1.765 |
paren | +1.763 |
Neg logit contributions | |
LY | -2.060 |
iliate | -1.935 |
lore | -1.904 |
rys | -1.898 |
yg | -1.854 |
Token | c |
Token ID | 269 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ileaks | +2.763 |
burgh | +2.746 |
roid | +2.590 |
ocrates | +2.577 |
paren | +2.543 |
Neg logit contributions | |
LY | -3.147 |
lore | -2.954 |
iliate | -2.884 |
rys | -2.836 |
yg | -2.785 |
Token | ot |
Token ID | 313 |
Feature activation | +9.14e+00 |
Pos logit contributions | |
LY | +0.755 |
lore | +0.691 |
iliate | +0.688 |
rys | +0.669 |
yg | +0.667 |
Neg logit contributions | |
ileaks | -0.816 |
burgh | -0.804 |
ocrates | -0.764 |
roid | -0.759 |
paren | -0.759 |
Token | erie |
Token ID | 18287 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
LY | +2.728 |
yg | +2.309 |
lore | +2.242 |
rys | +2.189 |
iliate | +2.116 |
Neg logit contributions | |
ileaks | -9.663 |
burgh | -9.623 |
ocrates | -9.366 |
paren | -9.311 |
roid | -9.159 |
Token | of |
Token ID | 286 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
ileaks | +1.793 |
burgh | +1.760 |
roid | +1.676 |
ocrates | +1.675 |
paren | +1.644 |
Neg logit contributions | |
LY | -1.896 |
lore | -1.758 |
iliate | -1.739 |
rys | -1.709 |
yg | -1.683 |
Token | the |
Token ID | 262 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
ileaks | +0.595 |
burgh | +0.591 |
ocrates | +0.557 |
roid | +0.554 |
paren | +0.547 |
Neg logit contributions | |
LY | -0.699 |
lore | -0.652 |
iliate | -0.644 |
rys | -0.629 |
yg | -0.623 |
Token | super |
Token ID | 2208 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
ileaks | +0.548 |
burgh | +0.542 |
ocrates | +0.511 |
roid | +0.509 |
paren | +0.504 |
Neg logit contributions | |
LY | -0.634 |
lore | -0.589 |
iliate | -0.580 |
rys | -0.567 |
yg | -0.563 |
Token | - |
Token ID | 12 |
Feature activation | -6.36e+00 |
Pos logit contributions | |
burgh | +6.845 |
ileaks | +6.841 |
ocrat | +6.661 |
paren | +6.290 |
ocrates | +6.278 |
Neg logit contributions | |
LY | -10.327 |
lore | -9.908 |
iliate | -9.367 |
rys | -9.187 |
yg | -9.029 |
Token | rich |
Token ID | 7527 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
burgh | +4.197 |
ileaks | +4.154 |
roid | +3.982 |
paren | +3.923 |
ocrat | +3.888 |
Neg logit contributions | |
LY | -4.507 |
lore | -4.213 |
iliate | -4.160 |
rys | -4.036 |
yg | -3.984 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ileaks | +1.502 |
burgh | +1.483 |
roid | +1.405 |
ocrates | +1.402 |
paren | +1.388 |
Neg logit contributions | |
LY | -1.720 |
lore | -1.607 |
iliate | -1.585 |
rys | -1.552 |
yg | -1.534 |
Token | And |
Token ID | 843 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
ileaks | +0.914 |
burgh | +0.907 |
ocrates | +0.855 |
roid | +0.849 |
paren | +0.844 |
Neg logit contributions | |
LY | -0.981 |
iliate | -0.912 |
lore | -0.910 |
rys | -0.891 |
yg | -0.875 |
Token | then |
Token ID | 788 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
LY | +0.616 |
lore | +0.567 |
iliate | +0.560 |
rys | +0.547 |
yg | +0.545 |
Neg logit contributions | |
ileaks | -0.608 |
burgh | -0.599 |
ocrates | -0.568 |
roid | -0.565 |
paren | -0.563 |
Token | Dick |
Token ID | 11740 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
burgh | +0.374 |
ileaks | +0.372 |
ocrates | +0.354 |
roid | +0.353 |
paren | +0.348 |
Neg logit contributions | |
LY | -0.368 |
lore | -0.340 |
iliate | -0.338 |
rys | -0.328 |
yg | -0.327 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
LY | +1.062 |
lore | +0.991 |
iliate | +0.980 |
rys | +0.962 |
yg | +0.958 |
Neg logit contributions | |
ileaks | -0.729 |
burgh | -0.712 |
ocrates | -0.667 |
roid | -0.662 |
paren | -0.661 |
Token | Even |
Token ID | 3412 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
LY | +1.355 |
lore | +1.239 |
iliate | +1.214 |
rys | +1.184 |
yg | +1.184 |
Neg logit contributions | |
ileaks | -1.526 |
burgh | -1.490 |
ocrates | -1.423 |
roid | -1.414 |
paren | -1.412 |
Token | with |
Token ID | 351 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
burgh | +2.276 |
ileaks | +2.249 |
roid | +2.163 |
ocrates | +2.155 |
paren | +2.124 |
Neg logit contributions | |
LY | -2.530 |
iliate | -2.374 |
lore | -2.357 |
rys | -2.315 |
yg | -2.257 |
Token | no |
Token ID | 645 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
burgh | +1.728 |
ileaks | +1.707 |
roid | +1.638 |
ocrates | +1.626 |
paren | +1.613 |
Neg logit contributions | |
LY | -1.729 |
lore | -1.601 |
iliate | -1.595 |
rys | -1.548 |
yg | -1.541 |
Token | super |
Token ID | 2208 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
burgh | +2.548 |
ileaks | +2.474 |
roid | +2.375 |
ocrates | +2.364 |
paren | +2.359 |
Neg logit contributions | |
LY | -2.612 |
iliate | -2.398 |
lore | -2.394 |
rys | -2.322 |
yg | -2.295 |
Token | powers |
Token ID | 5635 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
burgh | +7.522 |
nature | +7.207 |
paren | +7.139 |
visor | +7.070 |
ileaks | +6.992 |
Neg logit contributions | |
LY | -9.463 |
iliate | -8.611 |
rys | -8.525 |
lore | -8.447 |
yg | -8.313 |
Token | , |
Token ID | 11 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
ileaks | +1.154 |
burgh | +1.145 |
roid | +1.079 |
ocrates | +1.076 |
paren | +1.064 |
Neg logit contributions | |
LY | -1.446 |
lore | -1.336 |
iliate | -1.329 |
rys | -1.301 |
yg | -1.292 |
Token | he |
Token ID | 339 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
ileaks | +1.804 |
burgh | +1.800 |
roid | +1.710 |
ocrates | +1.700 |
paren | +1.680 |
Neg logit contributions | |
LY | -1.876 |
iliate | -1.740 |
lore | -1.738 |
rys | -1.680 |
yg | -1.670 |
Token | can |
Token ID | 460 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
burgh | +2.293 |
ileaks | +2.293 |
roid | +2.210 |
ocrates | +2.149 |
paren | +2.146 |
Neg logit contributions | |
LY | -2.349 |
iliate | -2.163 |
lore | -2.159 |
yg | -2.079 |
rys | -2.076 |
Token | go |
Token ID | 467 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
ileaks | +0.614 |
burgh | +0.612 |
roid | +0.583 |
ocrates | +0.579 |
paren | +0.579 |
Neg logit contributions | |
LY | -0.539 |
lore | -0.497 |
iliate | -0.489 |
rys | -0.474 |
yg | -0.473 |
Token | these |
Token ID | 777 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ileaks | +1.022 |
burgh | +1.001 |
roid | +0.947 |
ocrates | +0.944 |
paren | +0.936 |
Neg logit contributions | |
LY | -1.189 |
lore | -1.106 |
iliate | -1.090 |
rys | -1.071 |
yg | -1.063 |
Token | fluctuations |
Token ID | 31101 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
LY | +1.492 |
lore | +1.379 |
iliate | +1.363 |
rys | +1.332 |
yg | +1.327 |
Neg logit contributions | |
ileaks | -1.359 |
burgh | -1.336 |
ocrates | -1.264 |
roid | -1.257 |
paren | -1.253 |
Token | falls |
Token ID | 8953 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
LY | +3.191 |
lore | +2.957 |
iliate | +2.898 |
rys | +2.807 |
yg | +2.792 |
Neg logit contributions | |
ileaks | -3.575 |
burgh | -3.500 |
ocrates | -3.360 |
paren | -3.318 |
roid | -3.264 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ileaks | +0.211 |
burgh | +0.209 |
ocrates | +0.197 |
roid | +0.197 |
paren | +0.194 |
Neg logit contributions | |
LY | -0.220 |
lore | -0.204 |
iliate | -0.202 |
rys | -0.198 |
yg | -0.196 |
Token | the |
Token ID | 262 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
LY | +1.156 |
lore | +1.065 |
iliate | +1.053 |
rys | +1.027 |
yg | +1.024 |
Neg logit contributions | |
ileaks | -1.138 |
burgh | -1.120 |
ocrates | -1.062 |
roid | -1.058 |
paren | -1.052 |
Token | super |
Token ID | 2208 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
ileaks | +0.414 |
burgh | +0.410 |
roid | +0.389 |
ocrates | +0.387 |
paren | +0.384 |
Neg logit contributions | |
LY | -0.414 |
lore | -0.382 |
iliate | -0.379 |
rys | -0.369 |
yg | -0.367 |
Token | conduct |
Token ID | 36495 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
burgh | +4.868 |
ileaks | +4.745 |
visor | +4.656 |
nature | +4.624 |
paren | +4.535 |
Neg logit contributions | |
LY | -12.094 |
iliate | -11.148 |
yg | -11.148 |
rys | -10.843 |
lore | -10.819 |
Token | ivity |
Token ID | 3458 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
ileaks | +3.123 |
burgh | +3.091 |
roid | +3.001 |
ocrates | +2.909 |
ocrat | +2.900 |
Neg logit contributions | |
LY | -3.884 |
lore | -3.515 |
iliate | -3.446 |
yg | -3.423 |
rys | -3.404 |
Token | state |
Token ID | 1181 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ileaks | +1.669 |
burgh | +1.656 |
roid | +1.605 |
ocrates | +1.553 |
paren | +1.542 |
Neg logit contributions | |
LY | -1.816 |
lore | -1.675 |
iliate | -1.668 |
rys | -1.628 |
yg | -1.627 |
Token | takes |
Token ID | 2753 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
LY | +1.062 |
lore | +0.977 |
iliate | +0.963 |
rys | +0.942 |
yg | +0.937 |
Neg logit contributions | |
ileaks | -1.072 |
burgh | -1.054 |
ocrates | -1.001 |
roid | -0.993 |
paren | -0.993 |
Token | over |
Token ID | 625 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
LY | +0.397 |
lore | +0.367 |
iliate | +0.363 |
rys | +0.352 |
yg | +0.351 |
Neg logit contributions | |
ileaks | -0.355 |
burgh | -0.352 |
ocrates | -0.334 |
roid | -0.332 |
paren | -0.329 |
Token | deton |
Token ID | 20413 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
ileaks | +1.287 |
burgh | +1.254 |
roid | +1.197 |
paren | +1.192 |
ocrates | +1.185 |
Neg logit contributions | |
LY | -1.351 |
lore | -1.254 |
iliate | -1.242 |
rys | -1.217 |
yg | -1.207 |
Token | ation |
Token ID | 341 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
ileaks | +2.347 |
burgh | +2.306 |
roid | +2.216 |
ocrates | +2.178 |
paren | +2.162 |
Neg logit contributions | |
LY | -2.101 |
lore | -1.902 |
iliate | -1.886 |
rys | -1.837 |
yg | -1.822 |
Token | of |
Token ID | 286 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ileaks | +1.615 |
burgh | +1.592 |
roid | +1.514 |
paren | +1.493 |
ocrates | +1.490 |
Neg logit contributions | |
LY | -1.778 |
lore | -1.655 |
iliate | -1.647 |
rys | -1.615 |
yg | -1.601 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
ileaks | +1.141 |
burgh | +1.115 |
roid | +1.051 |
ocrates | +1.050 |
paren | +1.046 |
Neg logit contributions | |
LY | -1.350 |
lore | -1.256 |
iliate | -1.244 |
rys | -1.214 |
yg | -1.203 |
Token | PAT |
Token ID | 28748 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
ileaks | +1.473 |
burgh | +1.457 |
roid | +1.386 |
ocrates | +1.357 |
paren | +1.350 |
Neg logit contributions | |
LY | -1.538 |
lore | -1.427 |
iliate | -1.410 |
rys | -1.377 |
yg | -1.355 |
Token | super |
Token ID | 2208 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
ileaks | +0.314 |
burgh | +0.309 |
roid | +0.293 |
ocrates | +0.293 |
paren | +0.290 |
Neg logit contributions | |
LY | -0.313 |
lore | -0.290 |
iliate | -0.286 |
rys | -0.279 |
yg | -0.279 |
Token | nova |
Token ID | 38438 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
visor | +6.516 |
burgh | +6.374 |
ileaks | +6.336 |
nature | +6.271 |
paren | +6.154 |
Neg logit contributions | |
LY | -10.289 |
lore | -9.396 |
iliate | -9.305 |
rys | -9.183 |
yg | -8.804 |
Token | . |
Token ID | 13 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
ileaks | +3.096 |
burgh | +3.074 |
roid | +3.001 |
paren | +2.857 |
visor | +2.835 |
Neg logit contributions | |
LY | -3.735 |
lore | -3.515 |
iliate | -3.508 |
rys | -3.416 |
yg | -3.408 |
Token | Nobody |
Token ID | 15658 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
burgh | +2.003 |
ileaks | +1.999 |
ocrates | +1.876 |
roid | +1.869 |
paren | +1.861 |
Neg logit contributions | |
LY | -2.336 |
iliate | -2.208 |
lore | -2.181 |
rys | -2.176 |
yg | -2.117 |
Token | has |
Token ID | 468 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
LY | +0.623 |
lore | +0.565 |
iliate | +0.554 |
rys | +0.539 |
yg | +0.537 |
Neg logit contributions | |
ileaks | -0.843 |
burgh | -0.831 |
ocrates | -0.794 |
roid | -0.790 |
paren | -0.789 |
Token | any |
Token ID | 597 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ileaks | +1.617 |
burgh | +1.595 |
ocrates | +1.528 |
roid | +1.523 |
paren | +1.508 |
Neg logit contributions | |
LY | -1.702 |
iliate | -1.584 |
lore | -1.583 |
rys | -1.548 |
yg | -1.513 |
Token | he |
Token ID | 339 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
ileaks | +1.804 |
burgh | +1.800 |
roid | +1.710 |
ocrates | +1.700 |
paren | +1.680 |
Neg logit contributions | |
LY | -1.876 |
iliate | -1.740 |
lore | -1.738 |
rys | -1.680 |
yg | -1.670 |
Token | can |
Token ID | 460 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
burgh | +2.293 |
ileaks | +2.293 |
roid | +2.210 |
ocrates | +2.149 |
paren | +2.146 |
Neg logit contributions | |
LY | -2.349 |
iliate | -2.163 |
lore | -2.159 |
yg | -2.079 |
rys | -2.076 |
Token | go |
Token ID | 467 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
ileaks | +0.614 |
burgh | +0.612 |
roid | +0.583 |
ocrates | +0.579 |
paren | +0.579 |
Neg logit contributions | |
LY | -0.539 |
lore | -0.497 |
iliate | -0.489 |
rys | -0.474 |
yg | -0.473 |
Token | beyond |
Token ID | 3675 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
burgh | +2.223 |
ileaks | +2.193 |
roid | +2.094 |
ocrates | +2.088 |
paren | +2.061 |
Neg logit contributions | |
LY | -2.362 |
lore | -2.232 |
iliate | -2.205 |
rys | -2.152 |
yg | -2.113 |
Token | the |
Token ID | 262 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
ileaks | +0.128 |
burgh | +0.128 |
ocrates | +0.121 |
roid | +0.121 |
paren | +0.120 |
Neg logit contributions | |
LY | -0.130 |
lore | -0.120 |
iliate | -0.119 |
rys | -0.116 |
yg | -0.115 |
Token | super |
Token ID | 2208 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
ileaks | +0.592 |
burgh | +0.590 |
roid | +0.557 |
ocrates | +0.554 |
paren | +0.550 |
Neg logit contributions | |
LY | -0.648 |
lore | -0.598 |
iliate | -0.596 |
rys | -0.579 |
yg | -0.576 |
Token | powered |
Token ID | 13232 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
burgh | +7.476 |
visor | +7.182 |
nature | +7.048 |
ileaks | +7.008 |
roid | +7.003 |
Neg logit contributions | |
LY | -9.339 |
iliate | -8.611 |
lore | -8.426 |
rys | -8.266 |
yg | -8.197 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
burgh | +2.118 |
ileaks | +2.094 |
roid | +2.023 |
ocrates | +1.977 |
paren | +1.974 |
Neg logit contributions | |
LY | -2.292 |
iliate | -2.123 |
lore | -2.122 |
rys | -2.028 |
yg | -2.026 |
Token |
|
Token ID | 198 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
burgh | +0.732 |
ileaks | +0.729 |
roid | +0.691 |
ocrates | +0.689 |
paren | +0.684 |
Neg logit contributions | |
LY | -0.674 |
iliate | -0.624 |
lore | -0.620 |
rys | -0.607 |
yg | -0.599 |
Token |
|
Token ID | 198 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
ileaks | +0.261 |
burgh | +0.260 |
roid | +0.243 |
paren | +0.242 |
ocrates | +0.242 |
Neg logit contributions | |
LY | -0.319 |
lore | -0.297 |
iliate | -0.295 |
rys | -0.289 |
yg | -0.286 |
Token | CV |
Token ID | 33538 |
Feature activation | +8.14e+00 |
Pos logit contributions | |
LY | +0.229 |
lore | +0.213 |
iliate | +0.212 |
rys | +0.206 |
yg | +0.205 |
Neg logit contributions | |
ileaks | -0.237 |
burgh | -0.235 |
roid | -0.222 |
ocrates | -0.222 |
paren | -0.221 |
Token | complicity |
Token ID | 48234 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
LY | +1.340 |
lore | +1.233 |
iliate | +1.217 |
rys | +1.190 |
yg | +1.185 |
Neg logit contributions | |
ileaks | -1.271 |
burgh | -1.252 |
ocrates | -1.188 |
roid | -1.180 |
paren | -1.175 |
Token | among |
Token ID | 1871 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ileaks | +0.538 |
burgh | +0.529 |
ocrates | +0.500 |
roid | +0.499 |
paren | +0.497 |
Neg logit contributions | |
LY | -0.549 |
lore | -0.509 |
iliate | -0.501 |
rys | -0.491 |
yg | -0.487 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ileaks | +0.965 |
burgh | +0.941 |
roid | +0.890 |
ocrates | +0.883 |
paren | +0.874 |
Neg logit contributions | |
LY | -1.070 |
lore | -1.005 |
iliate | -0.990 |
rys | -0.969 |
yg | -0.961 |
Token | GOP |
Token ID | 6796 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ileaks | +0.886 |
burgh | +0.868 |
roid | +0.818 |
ocrates | +0.814 |
paren | +0.807 |
Neg logit contributions | |
LY | -0.916 |
lore | -0.858 |
iliate | -0.845 |
rys | -0.824 |
yg | -0.816 |
Token | rank |
Token ID | 4279 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
LY | +0.919 |
lore | +0.846 |
iliate | +0.839 |
rys | +0.819 |
yg | +0.816 |
Neg logit contributions | |
ileaks | -0.840 |
burgh | -0.827 |
ocrates | -0.784 |
roid | -0.778 |
paren | -0.777 |
Token | and |
Token ID | 290 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
ileaks | +3.278 |
burgh | +3.164 |
ocrat | +2.994 |
roid | +2.975 |
paren | +2.966 |
Neg logit contributions | |
LY | -3.536 |
lore | -3.324 |
iliate | -3.285 |
rys | -3.213 |
yg | -3.152 |
Token | file |
Token ID | 2393 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ileaks | +6.671 |
roid | +6.383 |
burgh | +5.918 |
ocrates | +5.850 |
ocrat | +5.840 |
Neg logit contributions | |
LY | -9.754 |
lore | -9.353 |
iliate | -9.011 |
rys | -8.906 |
look | -8.882 |
Token | , |
Token ID | 11 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
LY | +1.383 |
lore | +1.274 |
iliate | +1.260 |
rys | +1.229 |
yg | +1.227 |
Neg logit contributions | |
ileaks | -1.267 |
burgh | -1.245 |
ocrates | -1.180 |
roid | -1.172 |
paren | -1.169 |
Token | Letter |
Token ID | 18121 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ileaks | +0.596 |
burgh | +0.584 |
ocrates | +0.551 |
roid | +0.549 |
paren | +0.545 |
Neg logit contributions | |
LY | -0.678 |
lore | -0.631 |
iliate | -0.623 |
rys | -0.612 |
yg | -0.608 |
Token | said |
Token ID | 531 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ileaks | +0.082 |
burgh | +0.080 |
ocrates | +0.075 |
roid | +0.074 |
paren | +0.074 |
Neg logit contributions | |
LY | -0.126 |
lore | -0.118 |
iliate | -0.117 |
rys | -0.115 |
yg | -0.114 |
Token | she |
Token ID | 673 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
ileaks | +0.991 |
burgh | +0.969 |
ocrates | +0.917 |
roid | +0.915 |
paren | +0.910 |
Neg logit contributions | |
LY | -1.072 |
lore | -0.995 |
iliate | -0.985 |
rys | -0.963 |
yg | -0.950 |
Token | piece |
Token ID | 3704 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
ileaks | +0.321 |
burgh | +0.318 |
ocrates | +0.300 |
roid | +0.298 |
paren | +0.298 |
Neg logit contributions | |
LY | -0.328 |
lore | -0.303 |
iliate | -0.299 |
rys | -0.291 |
yg | -0.291 |
Token | of |
Token ID | 286 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
LY | +0.265 |
lore | +0.243 |
iliate | +0.240 |
rys | +0.234 |
yg | +0.233 |
Neg logit contributions | |
ileaks | -0.284 |
burgh | -0.279 |
ocrates | -0.266 |
roid | -0.264 |
paren | -0.263 |
Token | this |
Token ID | 428 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ileaks | +1.793 |
burgh | +1.771 |
paren | +1.653 |
ocrates | +1.649 |
roid | +1.643 |
Neg logit contributions | |
LY | -2.018 |
iliate | -1.845 |
lore | -1.837 |
rys | -1.806 |
yg | -1.793 |
Token | � |
Token ID | 564 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
LY | +1.067 |
lore | +0.983 |
iliate | +0.969 |
rys | +0.948 |
yg | +0.945 |
Neg logit contributions | |
ileaks | -1.042 |
burgh | -1.024 |
ocrates | -0.972 |
roid | -0.966 |
paren | -0.961 |
Token | � |
Token ID | 250 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
ileaks | +1.295 |
burgh | +1.276 |
roid | +1.198 |
ocrates | +1.193 |
paren | +1.187 |
Neg logit contributions | |
LY | -1.650 |
lore | -1.532 |
iliate | -1.517 |
rys | -1.492 |
yg | -1.488 |
Token | super |
Token ID | 16668 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
LY | +0.184 |
lore | +0.169 |
iliate | +0.169 |
rys | +0.164 |
yg | +0.164 |
Neg logit contributions | |
ileaks | -0.157 |
burgh | -0.154 |
roid | -0.145 |
ocrates | -0.145 |
paren | -0.144 |
Token | - |
Token ID | 12 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
ileaks | +7.808 |
visor | +7.749 |
burgh | +7.616 |
nature | +7.462 |
paren | +7.429 |
Neg logit contributions | |
LY | -8.362 |
lore | -7.547 |
iliate | -7.525 |
yg | -7.502 |
rys | -7.219 |
Token | growth |
Token ID | 27922 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
ileaks | +4.086 |
burgh | +4.085 |
roid | +3.889 |
visor | +3.880 |
paren | +3.873 |
Neg logit contributions | |
LY | -4.247 |
iliate | -3.922 |
lore | -3.855 |
yg | -3.817 |
rys | -3.777 |
Token | pie |
Token ID | 2508 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
ileaks | +2.056 |
burgh | +2.015 |
roid | +1.920 |
paren | +1.895 |
ocrates | +1.881 |
Neg logit contributions | |
LY | -2.247 |
lore | -2.071 |
iliate | -2.065 |
rys | -2.013 |
yg | -1.999 |
Token | � |
Token ID | 447 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
ileaks | +1.290 |
burgh | +1.267 |
roid | +1.194 |
ocrates | +1.188 |
paren | +1.187 |
Neg logit contributions | |
LY | -1.504 |
lore | -1.397 |
iliate | -1.385 |
rys | -1.349 |
yg | -1.344 |
Token | � |
Token ID | 251 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
ileaks | +1.583 |
burgh | +1.576 |
roid | +1.446 |
ocrates | +1.431 |
paren | +1.410 |
Neg logit contributions | |
LY | -3.168 |
lore | -2.998 |
iliate | -2.961 |
rys | -2.926 |
yg | -2.915 |
Token | pleaded |
Token ID | 16407 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
ileaks | +1.799 |
burgh | +1.766 |
roid | +1.663 |
ocrates | +1.647 |
paren | +1.633 |
Neg logit contributions | |
LY | -2.476 |
lore | -2.316 |
iliate | -2.295 |
rys | -2.238 |
yg | -2.221 |
Token | with |
Token ID | 351 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
ileaks | +0.464 |
burgh | +0.456 |
ocrates | +0.432 |
roid | +0.431 |
paren | +0.429 |
Neg logit contributions | |
LY | -0.504 |
lore | -0.468 |
iliate | -0.462 |
rys | -0.451 |
yg | -0.449 |
Token | voters |
Token ID | 4446 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
LY | +0.432 |
lore | +0.401 |
iliate | +0.395 |
rys | +0.386 |
yg | +0.383 |
Neg logit contributions | |
ileaks | -0.403 |
burgh | -0.397 |
ocrates | -0.376 |
roid | -0.375 |
paren | -0.372 |
Token | to |
Token ID | 284 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ileaks | +0.235 |
burgh | +0.231 |
ocrates | +0.219 |
roid | +0.218 |
paren | +0.217 |
Neg logit contributions | |
LY | -0.256 |
lore | -0.237 |
iliate | -0.234 |
rys | -0.229 |
yg | -0.228 |
Token | support |
Token ID | 1104 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
LY | +1.160 |
lore | +1.063 |
iliate | +1.053 |
rys | +1.028 |
yg | +1.024 |
Neg logit contributions | |
ileaks | -1.187 |
burgh | -1.168 |
ocrates | -1.108 |
roid | -1.101 |
paren | -1.099 |
Token | Ms |
Token ID | 6997 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
ileaks | +2.243 |
burgh | +2.196 |
ocrates | +2.112 |
roid | +2.104 |
paren | +2.082 |
Neg logit contributions | |
LY | -2.364 |
lore | -2.214 |
iliate | -2.174 |
rys | -2.128 |
yg | -2.107 |
Token | . |
Token ID | 13 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
burgh | +5.179 |
ileaks | +4.638 |
roid | +4.614 |
nature | +4.485 |
paren | +4.366 |
Neg logit contributions | |
LY | -10.564 |
iliate | -10.247 |
rys | -10.087 |
lore | -10.000 |
yg | -9.695 |
Token | Co |
Token ID | 1766 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ileaks | +0.727 |
burgh | +0.718 |
ocrates | +0.686 |
roid | +0.685 |
paren | +0.681 |
Neg logit contributions | |
LY | -0.498 |
lore | -0.449 |
iliate | -0.443 |
rys | -0.430 |
yg | -0.427 |
Token | ak |
Token ID | 461 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
ileaks | +1.301 |
burgh | +1.280 |
roid | +1.217 |
ocrates | +1.215 |
paren | +1.202 |
Neg logit contributions | |
LY | -1.418 |
lore | -1.310 |
iliate | -1.284 |
rys | -1.255 |
yg | -1.241 |
Token | ley |
Token ID | 1636 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ileaks | +0.331 |
burgh | +0.327 |
ocrates | +0.310 |
roid | +0.310 |
paren | +0.309 |
Neg logit contributions | |
LY | -0.274 |
lore | -0.250 |
iliate | -0.247 |
rys | -0.241 |
yg | -0.240 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ileaks | +0.953 |
burgh | +0.938 |
ocrates | +0.888 |
roid | +0.883 |
paren | +0.882 |
Neg logit contributions | |
LY | -1.039 |
lore | -0.964 |
iliate | -0.952 |
rys | -0.929 |
yg | -0.927 |
Token | But |
Token ID | 1537 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ileaks | +1.487 |
burgh | +1.482 |
ocrates | +1.398 |
roid | +1.388 |
paren | +1.382 |
Neg logit contributions | |
LY | -1.450 |
iliate | -1.348 |
lore | -1.341 |
rys | -1.309 |
yg | -1.282 |
Token | this |
Token ID | 428 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
LY | +0.123 |
lore | +0.113 |
iliate | +0.112 |
rys | +0.109 |
yg | +0.108 |
Neg logit contributions | |
ileaks | -0.119 |
burgh | -0.117 |
ocrates | -0.111 |
roid | -0.110 |
paren | -0.110 |
Token | revolt |
Token ID | 27360 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
LY | +0.084 |
lore | +0.077 |
iliate | +0.076 |
rys | +0.075 |
yg | +0.074 |
Neg logit contributions | |
ileaks | -0.085 |
burgh | -0.084 |
ocrates | -0.080 |
roid | -0.080 |
paren | -0.079 |
Token | against |
Token ID | 1028 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
LY | +1.534 |
lore | +1.408 |
iliate | +1.389 |
rys | +1.353 |
yg | +1.350 |
Neg logit contributions | |
ileaks | -1.678 |
burgh | -1.649 |
ocrates | -1.572 |
paren | -1.559 |
roid | -1.558 |
Token | the |
Token ID | 262 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
ileaks | +1.067 |
burgh | +1.055 |
ocrates | +1.003 |
roid | +0.991 |
paren | +0.983 |
Neg logit contributions | |
LY | -1.206 |
lore | -1.123 |
iliate | -1.111 |
rys | -1.084 |
yg | -1.074 |
Token | pseudo |
Token ID | 24543 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
ileaks | +1.964 |
burgh | +1.956 |
ocrates | +1.848 |
roid | +1.836 |
paren | +1.821 |
Neg logit contributions | |
LY | -2.242 |
lore | -2.092 |
iliate | -2.070 |
rys | -2.023 |
yg | -2.001 |
Token | - |
Token ID | 12 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
ileaks | +6.664 |
burgh | +6.511 |
ocrat | +6.395 |
ocrates | +6.313 |
roid | +6.201 |
Neg logit contributions | |
LY | -9.064 |
iliate | -8.501 |
rys | -8.491 |
lore | -8.439 |
yg | -8.326 |
Token | centres |
Token ID | 19788 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
ileaks | +2.041 |
burgh | +2.029 |
roid | +1.918 |
paren | +1.901 |
ocrates | +1.894 |
Neg logit contributions | |
LY | -2.578 |
iliate | -2.410 |
lore | -2.379 |
rys | -2.340 |
yg | -2.313 |
Token | was |
Token ID | 373 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ileaks | +3.083 |
burgh | +3.065 |
roid | +2.901 |
ocrates | +2.890 |
paren | +2.856 |
Neg logit contributions | |
LY | -3.215 |
lore | -2.942 |
iliate | -2.930 |
rys | -2.871 |
yg | -2.818 |
Token | far |
Token ID | 1290 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
LY | +0.009 |
lore | +0.008 |
iliate | +0.008 |
rys | +0.008 |
yg | +0.008 |
Neg logit contributions | |
ileaks | -0.009 |
burgh | -0.008 |
ocrates | -0.008 |
roid | -0.008 |
paren | -0.008 |
Token | from |
Token ID | 422 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
burgh | +3.602 |
ileaks | +3.493 |
roid | +3.363 |
paren | +3.351 |
ocrates | +3.311 |
Neg logit contributions | |
LY | -3.713 |
lore | -3.442 |
iliate | -3.437 |
rys | -3.389 |
yg | -3.346 |
Token | not |
Token ID | 407 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
burgh | +3.349 |
ileaks | +3.326 |
ocrates | +3.176 |
roid | +3.154 |
paren | +3.072 |
Neg logit contributions | |
LY | -3.597 |
iliate | -3.407 |
lore | -3.381 |
rys | -3.324 |
yg | -3.279 |
Token | easy |
Token ID | 2562 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
LY | +1.646 |
lore | +1.509 |
iliate | +1.482 |
yg | +1.446 |
rys | +1.446 |
Neg logit contributions | |
ileaks | -1.737 |
burgh | -1.700 |
ocrates | -1.614 |
roid | -1.606 |
paren | -1.604 |
Token | even |
Token ID | 772 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
ileaks | +0.533 |
burgh | +0.524 |
ocrates | +0.496 |
roid | +0.494 |
paren | +0.493 |
Neg logit contributions | |
LY | -0.602 |
lore | -0.558 |
iliate | -0.551 |
rys | -0.541 |
yg | -0.536 |
Token | for |
Token ID | 329 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ileaks | +1.654 |
burgh | +1.635 |
ocrates | +1.552 |
roid | +1.543 |
paren | +1.533 |
Neg logit contributions | |
LY | -2.031 |
lore | -1.890 |
iliate | -1.878 |
rys | -1.846 |
yg | -1.822 |
Token | the |
Token ID | 262 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
ileaks | +1.316 |
burgh | +1.315 |
ocrates | +1.243 |
roid | +1.237 |
paren | +1.228 |
Neg logit contributions | |
LY | -1.424 |
lore | -1.318 |
iliate | -1.305 |
rys | -1.269 |
yg | -1.267 |
Token | super |
Token ID | 2208 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
ileaks | +1.324 |
burgh | +1.318 |
ocrates | +1.246 |
roid | +1.244 |
paren | +1.225 |
Neg logit contributions | |
LY | -1.457 |
lore | -1.349 |
iliate | -1.341 |
yg | -1.302 |
rys | -1.299 |
Token | com |
Token ID | 785 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
ileaks | +7.192 |
burgh | +7.185 |
visor | +7.024 |
nature | +7.008 |
roid | +6.889 |
Neg logit contributions | |
LY | -8.555 |
iliate | -8.032 |
lore | -7.996 |
yg | -7.716 |
rys | -7.559 |
Token | puters |
Token ID | 41510 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
ileaks | +2.797 |
burgh | +2.717 |
roid | +2.509 |
ocrates | +2.470 |
ocrat | +2.421 |
Neg logit contributions | |
LY | -6.131 |
lore | -5.730 |
iliate | -5.665 |
rys | -5.573 |
yg | -5.568 |
Token | , |
Token ID | 11 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ileaks | +2.457 |
burgh | +2.439 |
roid | +2.297 |
ocrates | +2.291 |
paren | +2.247 |
Neg logit contributions | |
LY | -2.927 |
iliate | -2.703 |
lore | -2.701 |
rys | -2.640 |
yg | -2.632 |
Token | but |
Token ID | 475 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
ileaks | +0.893 |
burgh | +0.878 |
ocrates | +0.832 |
roid | +0.829 |
paren | +0.824 |
Neg logit contributions | |
LY | -0.984 |
lore | -0.907 |
iliate | -0.899 |
rys | -0.877 |
yg | -0.874 |
Token | it |
Token ID | 340 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
LY | +2.048 |
lore | +1.884 |
iliate | +1.857 |
rys | +1.825 |
yg | +1.816 |
Neg logit contributions | |
ileaks | -2.090 |
burgh | -2.047 |
ocrates | -1.933 |
roid | -1.925 |
paren | -1.915 |
Token | s |
Token ID | 82 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ileaks | +0.831 |
burgh | +0.824 |
roid | +0.770 |
ocrates | +0.761 |
paren | +0.752 |
Neg logit contributions | |
LY | -1.056 |
lore | -0.984 |
iliate | -0.972 |
yg | -0.951 |
rys | -0.948 |
Token | scored |
Token ID | 7781 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
LY | +1.038 |
lore | +0.953 |
iliate | +0.941 |
rys | +0.917 |
yg | +0.914 |
Neg logit contributions | |
ileaks | -1.104 |
burgh | -1.087 |
ocrates | -1.033 |
roid | -1.028 |
paren | -1.024 |
Token | 49 |
Token ID | 5125 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
ileaks | +1.214 |
burgh | +1.197 |
roid | +1.135 |
ocrates | +1.134 |
paren | +1.125 |
Neg logit contributions | |
LY | -1.121 |
lore | -1.034 |
iliate | -1.021 |
yg | -0.996 |
rys | -0.994 |
Token | % |
Token ID | 4 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
burgh | +1.879 |
ileaks | +1.873 |
ocrates | +1.748 |
roid | +1.742 |
paren | +1.734 |
Neg logit contributions | |
LY | -2.220 |
lore | -2.081 |
iliate | -2.048 |
rys | -2.011 |
yg | -1.983 |
Token | of |
Token ID | 286 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
LY | +0.827 |
lore | +0.763 |
iliate | +0.754 |
rys | +0.737 |
yg | +0.735 |
Neg logit contributions | |
ileaks | -0.811 |
burgh | -0.799 |
ocrates | -0.756 |
roid | -0.754 |
paren | -0.750 |
Token | even |
Token ID | 772 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
LY | +0.152 |
lore | +0.140 |
iliate | +0.138 |
rys | +0.135 |
yg | +0.134 |
Neg logit contributions | |
ileaks | -0.156 |
burgh | -0.153 |
ocrates | -0.145 |
roid | -0.145 |
paren | -0.144 |
Token | strength |
Token ID | 4202 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
burgh | +8.467 |
roid | +8.111 |
ileaks | +8.090 |
visor | +7.836 |
ocrat | +7.632 |
Neg logit contributions | |
LY | -6.994 |
lore | -6.893 |
iliate | -6.723 |
yg | -6.474 |
rys | -6.335 |
Token | goals |
Token ID | 4661 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
LY | +0.231 |
lore | +0.213 |
iliate | +0.211 |
rys | +0.206 |
yg | +0.205 |
Neg logit contributions | |
ileaks | -0.216 |
burgh | -0.213 |
ocrates | -0.201 |
roid | -0.200 |
paren | -0.200 |
Token | against |
Token ID | 1028 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
LY | +0.467 |
lore | +0.432 |
iliate | +0.427 |
rys | +0.417 |
yg | +0.416 |
Neg logit contributions | |
ileaks | -0.418 |
burgh | -0.411 |
ocrates | -0.389 |
roid | -0.387 |
paren | -0.385 |
Token | opponents |
Token ID | 7691 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
ileaks | +0.471 |
burgh | +0.463 |
ocrates | +0.436 |
roid | +0.436 |
paren | +0.433 |
Neg logit contributions | |
LY | -0.543 |
lore | -0.504 |
iliate | -0.499 |
rys | -0.487 |
yg | -0.486 |
Token | while |
Token ID | 981 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
ileaks | +2.184 |
burgh | +2.152 |
roid | +2.022 |
ocrates | +2.021 |
paren | +2.015 |
Neg logit contributions | |
LY | -2.402 |
lore | -2.248 |
iliate | -2.230 |
rys | -2.169 |
yg | -2.166 |
Token |
|
Token ID | 198 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ileaks | +0.697 |
burgh | +0.694 |
roid | +0.648 |
paren | +0.646 |
ocrates | +0.644 |
Neg logit contributions | |
LY | -0.859 |
iliate | -0.799 |
lore | -0.799 |
rys | -0.783 |
yg | -0.775 |
Token | San |
Token ID | 15017 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
ileaks | +1.436 |
burgh | +1.420 |
roid | +1.341 |
paren | +1.337 |
ocrates | +1.333 |
Neg logit contributions | |
LY | -1.397 |
iliate | -1.304 |
lore | -1.292 |
rys | -1.263 |
yg | -1.254 |
Token | Francisco |
Token ID | 6033 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
ileaks | +0.198 |
burgh | +0.195 |
ocrates | +0.187 |
roid | +0.187 |
paren | +0.186 |
Neg logit contributions | |
LY | -0.117 |
lore | -0.105 |
iliate | -0.103 |
rys | -0.100 |
yg | -0.099 |
Token | Board |
Token ID | 5926 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
burgh | +2.753 |
ileaks | +2.741 |
roid | +2.587 |
ocrates | +2.572 |
visor | +2.543 |
Neg logit contributions | |
LY | -2.729 |
iliate | -2.520 |
lore | -2.517 |
yg | -2.462 |
rys | -2.462 |
Token | of |
Token ID | 286 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
LY | +1.575 |
lore | +1.450 |
iliate | +1.426 |
yg | +1.388 |
rys | +1.384 |
Neg logit contributions | |
ileaks | -1.774 |
burgh | -1.750 |
ocrates | -1.667 |
roid | -1.656 |
paren | -1.654 |
Token | Super |
Token ID | 3115 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
LY | +1.436 |
lore | +1.301 |
iliate | +1.274 |
rys | +1.232 |
yg | +1.229 |
Neg logit contributions | |
ileaks | -2.053 |
burgh | -2.018 |
ocrates | -1.939 |
roid | -1.931 |
paren | -1.928 |
Token | visors |
Token ID | 27681 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
visor | +2.814 |
burgh | +2.548 |
ileaks | +2.450 |
ocrat | +2.010 |
nature | +1.951 |
Neg logit contributions | |
LY | -13.881 |
iliate | -13.086 |
yg | -13.045 |
rys | -12.989 |
lore | -12.811 |
Token |
|
Token ID | 198 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
burgh | +2.998 |
ileaks | +2.988 |
roid | +2.789 |
visor | +2.755 |
paren | +2.752 |
Neg logit contributions | |
LY | -3.395 |
iliate | -3.183 |
lore | -3.176 |
rys | -3.106 |
yg | -3.069 |
Token |
|
Token ID | 198 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
burgh | +1.188 |
ileaks | +1.181 |
roid | +1.106 |
paren | +1.098 |
ocrates | +1.088 |
Neg logit contributions | |
LY | -1.562 |
iliate | -1.457 |
lore | -1.457 |
rys | -1.432 |
yg | -1.410 |
Token | San |
Token ID | 15017 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
ileaks | +2.629 |
burgh | +2.602 |
roid | +2.452 |
paren | +2.446 |
ocrates | +2.421 |
Neg logit contributions | |
LY | -2.762 |
iliate | -2.620 |
lore | -2.589 |
rys | -2.534 |
yg | -2.518 |
Token | Francisco |
Token ID | 6033 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
ileaks | +1.898 |
burgh | +1.877 |
ocrates | +1.792 |
roid | +1.786 |
paren | +1.781 |
Neg logit contributions | |
LY | -1.275 |
lore | -1.143 |
iliate | -1.126 |
rys | -1.091 |
yg | -1.082 |
Token | sway |
Token ID | 20009 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
LY | +0.765 |
lore | +0.704 |
iliate | +0.696 |
rys | +0.679 |
yg | +0.677 |
Neg logit contributions | |
ileaks | -0.757 |
burgh | -0.745 |
ocrates | -0.706 |
roid | -0.703 |
paren | -0.700 |
Token | the |
Token ID | 262 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
ileaks | +0.382 |
burgh | +0.375 |
ocrates | +0.356 |
roid | +0.356 |
paren | +0.354 |
Neg logit contributions | |
LY | -0.429 |
lore | -0.402 |
iliate | -0.394 |
rys | -0.388 |
yg | -0.382 |
Token | system |
Token ID | 1080 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
ileaks | +0.054 |
burgh | +0.054 |
ocrates | +0.051 |
roid | +0.050 |
paren | +0.050 |
Neg logit contributions | |
LY | -0.062 |
lore | -0.058 |
iliate | -0.057 |
rys | -0.056 |
yg | -0.055 |
Token | through |
Token ID | 832 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
LY | +0.464 |
lore | +0.428 |
iliate | +0.423 |
rys | +0.413 |
yg | +0.411 |
Neg logit contributions | |
ileaks | -0.467 |
burgh | -0.460 |
ocrates | -0.437 |
roid | -0.435 |
paren | -0.433 |
Token | ult |
Token ID | 3789 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
ileaks | +0.463 |
burgh | +0.454 |
ocrates | +0.430 |
roid | +0.428 |
paren | +0.427 |
Neg logit contributions | |
LY | -0.522 |
lore | -0.483 |
iliate | -0.477 |
rys | -0.467 |
yg | -0.465 |
Token | im |
Token ID | 320 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
ileaks | +3.037 |
burgh | +2.781 |
roid | +2.660 |
paren | +2.590 |
ocrat | +2.585 |
Neg logit contributions | |
LY | -6.187 |
lore | -5.685 |
iliate | -5.632 |
yg | -5.596 |
rys | -5.526 |
Token | at |
Token ID | 265 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
ileaks | +7.299 |
ocrates | +7.149 |
ocrat | +7.043 |
burgh | +7.018 |
paren | +6.937 |
Neg logit contributions | |
LY | -8.429 |
lore | -7.531 |
iliate | -7.344 |
look | -7.341 |
rys | -7.281 |
Token | ums |
Token ID | 5700 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
LY | +0.590 |
lore | +0.552 |
iliate | +0.547 |
rys | +0.540 |
yg | +0.538 |
Neg logit contributions | |
ileaks | -0.305 |
burgh | -0.299 |
ocrates | -0.276 |
roid | -0.273 |
paren | -0.271 |
Token | , |
Token ID | 11 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
ileaks | +1.617 |
burgh | +1.588 |
roid | +1.504 |
ocrates | +1.503 |
paren | +1.500 |
Neg logit contributions | |
LY | -1.702 |
lore | -1.578 |
iliate | -1.553 |
rys | -1.530 |
yg | -1.513 |
Token | are |
Token ID | 389 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ileaks | +3.022 |
burgh | +2.946 |
paren | +2.841 |
ocrates | +2.822 |
roid | +2.819 |
Neg logit contributions | |
LY | -2.984 |
lore | -2.737 |
iliate | -2.703 |
rys | -2.647 |
yg | -2.622 |
Token | based |
Token ID | 1912 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
ileaks | +1.041 |
burgh | +1.034 |
ocrates | +0.984 |
paren | +0.977 |
roid | +0.972 |
Neg logit contributions | |
LY | -1.063 |
lore | -0.985 |
iliate | -0.983 |
rys | -0.958 |
yg | -0.950 |
Token | analyses |
Token ID | 13523 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
ileaks | +1.454 |
burgh | +1.435 |
roid | +1.355 |
paren | +1.333 |
ocrates | +1.321 |
Neg logit contributions | |
LY | -2.400 |
iliate | -2.273 |
lore | -2.267 |
rys | -2.195 |
yg | -2.179 |
Token | , |
Token ID | 11 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
ileaks | +1.901 |
burgh | +1.894 |
roid | +1.791 |
paren | +1.768 |
ocrates | +1.763 |
Neg logit contributions | |
LY | -2.338 |
lore | -2.215 |
iliate | -2.176 |
rys | -2.127 |
yg | -2.100 |
Token | we |
Token ID | 356 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ileaks | +2.433 |
burgh | +2.414 |
roid | +2.314 |
paren | +2.283 |
ocrates | +2.270 |
Neg logit contributions | |
LY | -2.718 |
iliate | -2.555 |
lore | -2.551 |
rys | -2.432 |
yg | -2.413 |
Token | will |
Token ID | 481 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
ileaks | +1.063 |
burgh | +1.055 |
roid | +1.001 |
ocrates | +0.996 |
paren | +0.972 |
Neg logit contributions | |
LY | -1.275 |
lore | -1.194 |
iliate | -1.183 |
rys | -1.140 |
yg | -1.133 |
Token | perform |
Token ID | 1620 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
LY | +0.458 |
lore | +0.423 |
iliate | +0.417 |
rys | +0.406 |
yg | +0.405 |
Neg logit contributions | |
ileaks | -0.443 |
burgh | -0.437 |
ocrates | -0.414 |
roid | -0.414 |
paren | -0.410 |
Token | meta |
Token ID | 13634 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
burgh | +1.770 |
ileaks | +1.764 |
roid | +1.669 |
ocrates | +1.660 |
paren | +1.649 |
Neg logit contributions | |
LY | -2.108 |
lore | -1.981 |
iliate | -1.951 |
rys | -1.917 |
yg | -1.894 |
Token | - |
Token ID | 12 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
burgh | +4.494 |
ileaks | +4.449 |
roid | +4.389 |
paren | +4.175 |
nature | +4.109 |
Neg logit contributions | |
LY | -11.116 |
rys | -10.333 |
lore | -10.331 |
yg | -10.230 |
iliate | -10.212 |
Token | reg |
Token ID | 2301 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ileaks | +0.349 |
burgh | +0.342 |
roid | +0.320 |
ocrates | +0.319 |
paren | +0.317 |
Neg logit contributions | |
LY | -0.519 |
lore | -0.484 |
iliate | -0.480 |
rys | -0.470 |
yg | -0.469 |
Token | ression |
Token ID | 2234 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
LY | +1.677 |
lore | +1.496 |
iliate | +1.449 |
rys | +1.421 |
yg | +1.403 |
Neg logit contributions | |
ileaks | -2.774 |
burgh | -2.766 |
ocrates | -2.661 |
roid | -2.608 |
paren | -2.608 |
Token | if |
Token ID | 611 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
ileaks | +2.544 |
burgh | +2.542 |
roid | +2.375 |
paren | +2.333 |
ocrates | +2.308 |
Neg logit contributions | |
LY | -4.039 |
lore | -3.842 |
iliate | -3.827 |
rys | -3.729 |
yg | -3.665 |
Token | a |
Token ID | 257 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
ileaks | +0.051 |
burgh | +0.050 |
ocrates | +0.047 |
roid | +0.047 |
paren | +0.047 |
Neg logit contributions | |
LY | -0.055 |
lore | -0.051 |
iliate | -0.050 |
rys | -0.049 |
yg | -0.049 |
Token | won |
Token ID | 1839 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
ileaks | +1.162 |
burgh | +1.158 |
roid | +1.093 |
ocrates | +1.090 |
paren | +1.066 |
Neg logit contributions | |
LY | -1.515 |
lore | -1.418 |
iliate | -1.416 |
rys | -1.367 |
yg | -1.360 |
Token | 172 |
Token ID | 23120 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
LY | +0.459 |
lore | +0.425 |
iliate | +0.419 |
yg | +0.409 |
rys | +0.409 |
Neg logit contributions | |
ileaks | -0.428 |
burgh | -0.422 |
ocrates | -0.400 |
paren | -0.398 |
roid | -0.397 |
Token | games |
Token ID | 1830 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
LY | +0.131 |
lore | +0.123 |
iliate | +0.121 |
rys | +0.119 |
yg | +0.119 |
Neg logit contributions | |
ileaks | -0.097 |
burgh | -0.097 |
ocrates | -0.090 |
paren | -0.090 |
roid | -0.090 |
Token | and |
Token ID | 290 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ileaks | +0.999 |
burgh | +0.992 |
ocrates | +0.938 |
paren | +0.933 |
roid | +0.931 |
Neg logit contributions | |
LY | -1.170 |
lore | -1.097 |
iliate | -1.086 |
yg | -1.066 |
rys | -1.063 |
Token | two |
Token ID | 734 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
LY | +0.146 |
lore | +0.135 |
iliate | +0.134 |
yg | +0.130 |
rys | +0.130 |
Neg logit contributions | |
ileaks | -0.142 |
burgh | -0.140 |
ocrates | -0.133 |
roid | -0.132 |
paren | -0.131 |
Token | Super |
Token ID | 3115 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
ileaks | +0.790 |
burgh | +0.788 |
ocrates | +0.750 |
roid | +0.748 |
paren | +0.747 |
Neg logit contributions | |
LY | -0.631 |
lore | -0.581 |
iliate | -0.571 |
yg | -0.557 |
rys | -0.550 |
Token | Bowl |
Token ID | 8693 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
burgh | +6.426 |
roid | +6.140 |
paren | +6.063 |
visor | +5.935 |
ileaks | +5.884 |
Neg logit contributions | |
LY | -9.461 |
iliate | -8.614 |
yg | -8.500 |
lore | -8.443 |
rys | -8.316 |
Token | s |
Token ID | 82 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
burgh | +2.540 |
ileaks | +2.503 |
paren | +2.421 |
ocrates | +2.398 |
roid | +2.352 |
Neg logit contributions | |
LY | -3.492 |
lore | -3.307 |
iliate | -3.270 |
yg | -3.247 |
rys | -3.127 |
Token | in |
Token ID | 287 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
ileaks | +0.701 |
burgh | +0.697 |
ocrates | +0.660 |
roid | +0.655 |
paren | +0.654 |
Neg logit contributions | |
LY | -0.749 |
lore | -0.694 |
iliate | -0.687 |
rys | -0.671 |
yg | -0.671 |
Token | the |
Token ID | 262 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
burgh | +3.169 |
ileaks | +3.123 |
ocrates | +2.986 |
paren | +2.960 |
roid | +2.936 |
Neg logit contributions | |
LY | -3.730 |
iliate | -3.516 |
lore | -3.508 |
yg | -3.463 |
rys | -3.404 |
Token | NFL |
Token ID | 5134 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
LY | +1.823 |
lore | +1.676 |
iliate | +1.655 |
rys | +1.615 |
yg | +1.608 |
Neg logit contributions | |
ileaks | -1.891 |
burgh | -1.860 |
ocrates | -1.766 |
roid | -1.759 |
paren | -1.752 |
Token | expensive |
Token ID | 5789 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
LY | +1.630 |
lore | +1.485 |
iliate | +1.466 |
rys | +1.436 |
yg | +1.420 |
Neg logit contributions | |
ileaks | -1.659 |
burgh | -1.629 |
ocrates | -1.549 |
paren | -1.539 |
roid | -1.534 |
Token | . |
Token ID | 13 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
LY | +1.549 |
lore | +1.428 |
iliate | +1.411 |
rys | +1.378 |
yg | +1.374 |
Neg logit contributions | |
ileaks | -1.414 |
burgh | -1.389 |
ocrates | -1.313 |
roid | -1.305 |
paren | -1.299 |
Token | Materials |
Token ID | 24310 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
LY | +0.405 |
lore | +0.374 |
iliate | +0.371 |
rys | +0.362 |
yg | +0.360 |
Neg logit contributions | |
ileaks | -0.418 |
burgh | -0.415 |
ocrates | -0.392 |
roid | -0.391 |
paren | -0.388 |
Token | that |
Token ID | 326 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ileaks | +0.514 |
burgh | +0.507 |
ocrates | +0.478 |
roid | +0.477 |
paren | +0.471 |
Neg logit contributions | |
LY | -0.599 |
lore | -0.554 |
iliate | -0.549 |
rys | -0.537 |
yg | -0.535 |
Token | achieve |
Token ID | 4620 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
ileaks | +0.832 |
burgh | +0.821 |
roid | +0.787 |
ocrates | +0.778 |
paren | +0.765 |
Neg logit contributions | |
LY | -0.753 |
lore | -0.689 |
iliate | -0.684 |
yg | -0.666 |
rys | -0.662 |
Token | super |
Token ID | 2208 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
LY | +0.215 |
lore | +0.199 |
iliate | +0.198 |
rys | +0.192 |
yg | +0.191 |
Neg logit contributions | |
ileaks | -0.210 |
burgh | -0.207 |
ocrates | -0.196 |
roid | -0.195 |
paren | -0.194 |
Token | conduct |
Token ID | 36495 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
burgh | +4.252 |
ileaks | +4.161 |
nature | +4.014 |
visor | +3.930 |
paren | +3.913 |
Neg logit contributions | |
LY | -11.079 |
iliate | -10.331 |
yg | -10.212 |
Reloaded | -9.955 |
lore | -9.926 |
Token | ivity |
Token ID | 3458 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ileaks | +1.778 |
burgh | +1.750 |
roid | +1.677 |
ocrates | +1.640 |
paren | +1.618 |
Neg logit contributions | |
LY | -2.876 |
lore | -2.645 |
iliate | -2.620 |
yg | -2.577 |
rys | -2.570 |
Token | at |
Token ID | 379 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
ileaks | +1.317 |
burgh | +1.312 |
roid | +1.257 |
ocrates | +1.236 |
paren | +1.212 |
Neg logit contributions | |
LY | -1.404 |
lore | -1.308 |
iliate | -1.291 |
rys | -1.267 |
yg | -1.261 |
Token | a |
Token ID | 257 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
LY | +3.923 |
lore | +3.560 |
iliate | +3.472 |
yg | +3.443 |
rys | +3.426 |
Neg logit contributions | |
ileaks | -3.995 |
burgh | -3.889 |
ocrates | -3.731 |
roid | -3.704 |
paren | -3.702 |
Token | higher |
Token ID | 2440 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
LY | +0.545 |
lore | +0.506 |
iliate | +0.502 |
rys | +0.489 |
yg | +0.486 |
Neg logit contributions | |
ileaks | -0.486 |
burgh | -0.480 |
ocrates | -0.452 |
roid | -0.451 |
paren | -0.448 |
Token | constructed |
Token ID | 12006 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ileaks | +1.643 |
burgh | +1.624 |
roid | +1.534 |
paren | +1.525 |
ocrates | +1.525 |
Neg logit contributions | |
LY | -1.727 |
lore | -1.612 |
iliate | -1.611 |
rys | -1.560 |
yg | -1.539 |
Token | from |
Token ID | 422 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
ileaks | +0.136 |
burgh | +0.134 |
ocrates | +0.128 |
roid | +0.127 |
paren | +0.127 |
Neg logit contributions | |
LY | -0.136 |
lore | -0.126 |
iliate | -0.125 |
rys | -0.121 |
yg | -0.120 |
Token | green |
Token ID | 4077 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ileaks | +1.964 |
burgh | +1.923 |
paren | +1.820 |
ocrates | +1.815 |
roid | +1.811 |
Neg logit contributions | |
LY | -2.075 |
iliate | -1.942 |
lore | -1.940 |
rys | -1.870 |
yg | -1.854 |
Token | pant |
Token ID | 15857 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
ileaks | +0.120 |
burgh | +0.118 |
roid | +0.112 |
paren | +0.112 |
ocrates | +0.112 |
Neg logit contributions | |
LY | -0.117 |
lore | -0.108 |
iliate | -0.107 |
rys | -0.104 |
yg | -0.103 |
Token | y |
Token ID | 88 |
Feature activation | -9.65e+00 |
Pos logit contributions | |
LY | +1.241 |
lore | +1.081 |
iliate | +1.062 |
rys | +1.028 |
yg | +1.022 |
Neg logit contributions | |
ileaks | -2.980 |
burgh | -2.951 |
ocrates | -2.838 |
roid | -2.818 |
paren | -2.818 |
Token | h |
Token ID | 71 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
ileaks | +5.306 |
visor | +5.018 |
roid | +5.008 |
burgh | +4.994 |
paren | +4.884 |
Neg logit contributions | |
LY | -7.710 |
iliate | -7.109 |
rys | -6.953 |
lore | -6.858 |
yg | -6.731 |
Token | ose |
Token ID | 577 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
ileaks | +4.965 |
ocrates | +4.626 |
burgh | +4.554 |
paren | +4.514 |
roid | +4.509 |
Neg logit contributions | |
LY | -10.613 |
lore | -9.758 |
look | -9.626 |
iliate | -9.603 |
rys | -9.398 |
Token | hanging |
Token ID | 10938 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
LY | +2.864 |
lore | +2.635 |
iliate | +2.574 |
rys | +2.540 |
yg | +2.526 |
Neg logit contributions | |
ileaks | -2.835 |
burgh | -2.797 |
ocrates | -2.655 |
roid | -2.621 |
paren | -2.603 |
Token | from |
Token ID | 422 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
LY | +2.107 |
lore | +1.918 |
iliate | +1.869 |
rys | +1.850 |
yg | +1.840 |
Neg logit contributions | |
ileaks | -2.303 |
burgh | -2.283 |
ocrates | -2.169 |
roid | -2.149 |
paren | -2.140 |
Token | the |
Token ID | 262 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
ileaks | +1.349 |
burgh | +1.312 |
paren | +1.249 |
ocrates | +1.245 |
roid | +1.239 |
Neg logit contributions | |
LY | -1.601 |
lore | -1.500 |
iliate | -1.493 |
rys | -1.444 |
yg | -1.437 |
Token | top |
Token ID | 1353 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
ileaks | +1.235 |
burgh | +1.207 |
ocrates | +1.120 |
roid | +1.116 |
paren | +1.115 |
Neg logit contributions | |
LY | -2.048 |
iliate | -1.943 |
lore | -1.941 |
rys | -1.883 |
yg | -1.869 |
Token | likely |
Token ID | 1884 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
LY | +0.605 |
lore | +0.552 |
iliate | +0.543 |
rys | +0.529 |
yg | +0.528 |
Neg logit contributions | |
ileaks | -0.708 |
burgh | -0.697 |
ocrates | -0.664 |
roid | -0.660 |
paren | -0.659 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ileaks | +0.609 |
burgh | +0.599 |
roid | +0.570 |
ocrates | +0.568 |
paren | +0.564 |
Neg logit contributions | |
LY | -0.620 |
lore | -0.577 |
iliate | -0.572 |
rys | -0.560 |
yg | -0.554 |
Token | get |
Token ID | 651 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
ileaks | +0.643 |
burgh | +0.635 |
roid | +0.601 |
ocrates | +0.593 |
paren | +0.592 |
Neg logit contributions | |
LY | -0.800 |
lore | -0.750 |
iliate | -0.737 |
rys | -0.723 |
yg | -0.719 |
Token | sued |
Token ID | 16334 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
LY | +0.507 |
lore | +0.473 |
iliate | +0.468 |
rys | +0.458 |
yg | +0.456 |
Neg logit contributions | |
ileaks | -0.391 |
burgh | -0.384 |
ocrates | -0.361 |
roid | -0.360 |
paren | -0.357 |
Token | for |
Token ID | 329 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
burgh | +3.190 |
ileaks | +3.175 |
roid | +2.978 |
ocrates | +2.964 |
ocrat | +2.899 |
Neg logit contributions | |
LY | -4.961 |
lore | -4.692 |
iliate | -4.657 |
rys | -4.578 |
yg | -4.491 |
Token | damages |
Token ID | 12616 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
ileaks | +0.791 |
burgh | +0.790 |
roid | +0.743 |
ocrates | +0.739 |
paren | +0.736 |
Neg logit contributions | |
LY | -0.920 |
lore | -0.858 |
iliate | -0.848 |
rys | -0.836 |
yg | -0.829 |
Token | ," |
Token ID | 553 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
burgh | +5.540 |
ileaks | +5.254 |
roid | +5.196 |
ocrat | +5.013 |
ocrates | +4.894 |
Neg logit contributions | |
LY | -9.535 |
iliate | -9.098 |
rys | -9.039 |
lore | -8.993 |
yg | -8.745 |
Token | Wal |
Token ID | 6445 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
ileaks | +1.647 |
burgh | +1.625 |
ocrates | +1.533 |
roid | +1.516 |
paren | +1.492 |
Neg logit contributions | |
LY | -1.884 |
lore | -1.734 |
iliate | -1.715 |
rys | -1.679 |
yg | -1.668 |
Token | cz |
Token ID | 26691 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
ileaks | +0.385 |
burgh | +0.379 |
ocrates | +0.351 |
roid | +0.350 |
paren | +0.344 |
Neg logit contributions | |
LY | -0.662 |
lore | -0.616 |
iliate | -0.611 |
rys | -0.597 |
yg | -0.597 |
Token | ak |
Token ID | 461 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ileaks | +1.552 |
burgh | +1.542 |
roid | +1.459 |
ocrates | +1.442 |
paren | +1.433 |
Neg logit contributions | |
LY | -1.767 |
lore | -1.613 |
iliate | -1.592 |
rys | -1.556 |
yg | -1.527 |
Token | said |
Token ID | 531 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
LY | +0.202 |
lore | +0.189 |
iliate | +0.187 |
rys | +0.183 |
yg | +0.183 |
Neg logit contributions | |
ileaks | -0.128 |
burgh | -0.125 |
ocrates | -0.117 |
roid | -0.116 |
paren | -0.115 |
Token | Zimmerman |
Token ID | 24332 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
LY | +4.966 |
lore | +4.618 |
rys | +4.419 |
iliate | +4.408 |
yg | +4.365 |
Neg logit contributions | |
ileaks | -6.095 |
burgh | -5.892 |
ocrates | -5.720 |
paren | -5.677 |
roid | -5.622 |
Token | could |
Token ID | 714 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
LY | +0.447 |
lore | +0.411 |
iliate | +0.407 |
rys | +0.397 |
yg | +0.396 |
Neg logit contributions | |
ileaks | -0.453 |
burgh | -0.448 |
ocrates | -0.423 |
roid | -0.422 |
paren | -0.420 |
Token | also |
Token ID | 635 |
Feature activation | -9.10e+00 |
Pos logit contributions | |
burgh | +3.390 |
ileaks | +3.387 |
roid | +3.218 |
paren | +3.199 |
ocrat | +3.105 |
Neg logit contributions | |
LY | -3.928 |
lore | -3.711 |
iliate | -3.581 |
yg | -3.520 |
rys | -3.459 |
Token | take |
Token ID | 1011 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
burgh | +5.351 |
ileaks | +5.161 |
roid | +5.132 |
ocrat | +4.895 |
paren | +4.875 |
Neg logit contributions | |
LY | -6.674 |
lore | -6.392 |
iliate | -6.109 |
yg | -6.014 |
rys | -5.915 |
Token | over |
Token ID | 625 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ileaks | +0.588 |
burgh | +0.582 |
ocrates | +0.550 |
roid | +0.549 |
paren | +0.544 |
Neg logit contributions | |
LY | -0.686 |
lore | -0.637 |
iliate | -0.628 |
yg | -0.612 |
rys | -0.612 |
Token | at |
Token ID | 379 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
LY | +1.377 |
lore | +1.273 |
iliate | +1.252 |
rys | +1.230 |
yg | +1.222 |
Neg logit contributions | |
ileaks | -1.295 |
burgh | -1.264 |
ocrates | -1.203 |
roid | -1.189 |
paren | -1.188 |
Token | first |
Token ID | 717 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
LY | +4.822 |
lore | +4.539 |
iliate | +4.377 |
rys | +4.360 |
yg | +4.291 |
Neg logit contributions | |
ileaks | -5.319 |
burgh | -5.057 |
ocrates | -4.956 |
paren | -4.917 |
roid | -4.895 |
Token | base |
Token ID | 2779 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
LY | +2.167 |
lore | +1.945 |
iliate | +1.899 |
rys | +1.858 |
yg | +1.848 |
Neg logit contributions | |
ileaks | -3.520 |
burgh | -3.431 |
ocrates | -3.315 |
paren | -3.288 |
roid | -3.282 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
LY | +0.831 |
lore | +0.768 |
iliate | +0.759 |
rys | +0.741 |
yg | +0.738 |
Neg logit contributions | |
ileaks | -0.755 |
burgh | -0.741 |
ocrates | -0.701 |
roid | -0.697 |
paren | -0.694 |
Token | The |
Token ID | 383 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
ileaks | +0.199 |
burgh | +0.198 |
ocrates | +0.187 |
roid | +0.186 |
paren | +0.186 |
Neg logit contributions | |
LY | -0.182 |
iliate | -0.167 |
lore | -0.167 |
rys | -0.163 |
yg | -0.161 |
Token | outfield |
Token ID | 28307 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ileaks | +0.447 |
burgh | +0.445 |
roid | +0.423 |
ocrates | +0.421 |
paren | +0.419 |
Neg logit contributions | |
LY | -0.325 |
lore | -0.295 |
iliate | -0.291 |
rys | -0.281 |
yg | -0.280 |
Token | ? |
Token ID | 30 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
LY | +2.437 |
lore | +2.234 |
iliate | +2.209 |
rys | +2.157 |
yg | +2.144 |
Neg logit contributions | |
ileaks | -2.462 |
burgh | -2.442 |
ocrates | -2.307 |
paren | -2.299 |
roid | -2.278 |
Token | Chinese |
Token ID | 3999 |
Feature activation | +7.65e+00 |
Pos logit contributions | |
LY | +0.838 |
lore | +0.770 |
iliate | +0.761 |
rys | +0.742 |
yg | +0.739 |
Neg logit contributions | |
ileaks | -0.906 |
burgh | -0.893 |
ocrates | -0.849 |
roid | -0.846 |
paren | -0.841 |
Token | production |
Token ID | 3227 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
LY | +5.179 |
lore | +4.693 |
iliate | +4.582 |
rys | +4.465 |
yg | +4.448 |
Neg logit contributions | |
ileaks | -5.552 |
burgh | -5.393 |
paren | -5.108 |
ocrates | -5.108 |
roid | -5.071 |
Token | value |
Token ID | 1988 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
LY | +2.529 |
lore | +2.320 |
iliate | +2.255 |
rys | +2.221 |
yg | +2.196 |
Neg logit contributions | |
ileaks | -2.813 |
burgh | -2.753 |
ocrates | -2.614 |
paren | -2.599 |
roid | -2.590 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
LY | +0.940 |
lore | +0.863 |
iliate | +0.852 |
rys | +0.831 |
yg | +0.827 |
Neg logit contributions | |
ileaks | -0.994 |
burgh | -0.979 |
ocrates | -0.930 |
roid | -0.925 |
paren | -0.922 |
Token | | |
Token ID | 930 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
LY | +1.131 |
lore | +1.040 |
iliate | +1.030 |
rys | +1.005 |
yg | +1.000 |
Neg logit contributions | |
ileaks | -1.177 |
burgh | -1.159 |
ocrates | -1.101 |
roid | -1.098 |
paren | -1.091 |
Token | I |
Token ID | 314 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
LY | +5.094 |
lore | +4.659 |
iliate | +4.512 |
rys | +4.428 |
yg | +4.421 |
Neg logit contributions | |
ileaks | -5.886 |
burgh | -5.759 |
ocrates | -5.458 |
paren | -5.452 |
roid | -5.358 |
Token | thought |
Token ID | 1807 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
ileaks | +1.016 |
burgh | +1.005 |
roid | +0.960 |
ocrates | +0.959 |
paren | +0.947 |
Neg logit contributions | |
LY | -0.973 |
iliate | -0.912 |
lore | -0.911 |
rys | -0.869 |
yg | -0.868 |
Token | he |
Token ID | 339 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
ileaks | +0.632 |
burgh | +0.623 |
roid | +0.598 |
ocrates | +0.593 |
paren | +0.586 |
Neg logit contributions | |
LY | -0.654 |
iliate | -0.608 |
lore | -0.604 |
rys | -0.589 |
yg | -0.588 |
Token | had |
Token ID | 550 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ileaks | +0.008 |
burgh | +0.008 |
roid | +0.007 |
ocrates | +0.007 |
paren | +0.007 |
Neg logit contributions | |
LY | -0.007 |
lore | -0.007 |
iliate | -0.007 |
rys | -0.006 |
yg | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ileaks | +0.945 |
burgh | +0.934 |
roid | +0.897 |
ocrates | +0.886 |
paren | +0.881 |
Neg logit contributions | |
LY | -1.072 |
iliate | -1.001 |
lore | -1.001 |
rys | -0.972 |
yg | -0.968 |
Token | portray |
Token ID | 10993 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ileaks | +0.502 |
burgh | +0.495 |
roid | +0.468 |
ocrates | +0.466 |
paren | +0.463 |
Neg logit contributions | |
LY | -0.524 |
lore | -0.485 |
iliate | -0.476 |
rys | -0.466 |
yg | -0.465 |
Token | me |
Token ID | 502 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ileaks | +0.869 |
burgh | +0.851 |
roid | +0.807 |
ocrates | +0.806 |
paren | +0.798 |
Neg logit contributions | |
LY | -0.965 |
lore | -0.898 |
iliate | -0.888 |
rys | -0.869 |
yg | -0.862 |
Token | as |
Token ID | 355 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ileaks | +0.802 |
burgh | +0.790 |
ocrates | +0.749 |
roid | +0.746 |
paren | +0.745 |
Neg logit contributions | |
LY | -0.805 |
lore | -0.745 |
iliate | -0.734 |
rys | -0.719 |
yg | -0.715 |
Token | a |
Token ID | 257 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
LY | +1.083 |
lore | +1.001 |
iliate | +0.988 |
yg | +0.971 |
rys | +0.965 |
Neg logit contributions | |
ileaks | -0.935 |
burgh | -0.920 |
ocrates | -0.866 |
paren | -0.861 |
roid | -0.860 |
Token | r |
Token ID | 374 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
LY | +1.680 |
lore | +1.542 |
iliate | +1.522 |
yg | +1.501 |
rys | +1.487 |
Neg logit contributions | |
ileaks | -1.507 |
burgh | -1.465 |
ocrates | -1.394 |
paren | -1.384 |
roid | -1.374 |
Token | aving |
Token ID | 2703 |
Feature activation | +8.43e+00 |
Pos logit contributions | |
LY | +3.387 |
lore | +3.135 |
iliate | +3.090 |
yg | +3.065 |
rys | +3.023 |
Neg logit contributions | |
ileaks | -3.232 |
burgh | -3.187 |
ocrates | -3.034 |
paren | -2.995 |
roid | -2.993 |
Token | lun |
Token ID | 14678 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
LY | +6.286 |
lore | +5.629 |
yg | +5.627 |
iliate | +5.549 |
ly | +5.360 |
Neg logit contributions | |
ileaks | -5.443 |
burgh | -5.177 |
paren | -4.989 |
ocrates | -4.907 |
ocene | -4.797 |
Token | atic |
Token ID | 1512 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
LY | +3.039 |
lore | +2.888 |
iliate | +2.844 |
yg | +2.802 |
rys | +2.761 |
Neg logit contributions | |
ileaks | -2.127 |
burgh | -2.086 |
paren | -1.950 |
ocrates | -1.949 |
roid | -1.900 |
Token | who |
Token ID | 508 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
LY | +0.277 |
lore | +0.256 |
iliate | +0.253 |
rys | +0.247 |
yg | +0.246 |
Neg logit contributions | |
ileaks | -0.248 |
burgh | -0.244 |
ocrates | -0.231 |
roid | -0.229 |
paren | -0.229 |
Token | hates |
Token ID | 24702 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
LY | +0.054 |
lore | +0.049 |
iliate | +0.049 |
rys | +0.047 |
yg | +0.047 |
Neg logit contributions | |
ileaks | -0.056 |
burgh | -0.055 |
ocrates | -0.052 |
roid | -0.052 |
paren | -0.052 |
Token | all |
Token ID | 477 |
Feature activation | -9.39e+00 |
Pos logit contributions | |
LY | +0.761 |
lore | +0.707 |
iliate | +0.699 |
rys | +0.684 |
yg | +0.683 |
Neg logit contributions | |
ileaks | -0.583 |
burgh | -0.572 |
ocrates | -0.538 |
roid | -0.535 |
paren | -0.533 |
Token | region |
Token ID | 3814 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
LY | +0.912 |
lore | +0.837 |
iliate | +0.828 |
rys | +0.805 |
yg | +0.803 |
Neg logit contributions | |
ileaks | -0.970 |
burgh | -0.957 |
ocrates | -0.908 |
roid | -0.904 |
paren | -0.899 |
Token | � |
Token ID | 447 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
ileaks | +0.898 |
burgh | +0.883 |
roid | +0.831 |
ocrates | +0.828 |
paren | +0.822 |
Neg logit contributions | |
LY | -1.114 |
lore | -1.039 |
iliate | -1.028 |
yg | -1.004 |
rys | -1.000 |
Token | � |
Token ID | 247 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ileaks | +0.355 |
burgh | +0.349 |
ocrates | +0.319 |
roid | +0.318 |
paren | +0.315 |
Neg logit contributions | |
LY | -0.758 |
lore | -0.715 |
iliate | -0.709 |
rys | -0.696 |
yg | -0.694 |
Token | s |
Token ID | 82 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
LY | +1.076 |
lore | +0.994 |
iliate | +0.983 |
rys | +0.961 |
yg | +0.957 |
Neg logit contributions | |
ileaks | -0.979 |
burgh | -0.963 |
ocrates | -0.911 |
roid | -0.906 |
paren | -0.902 |
Token | natural |
Token ID | 3288 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
LY | +1.183 |
lore | +1.089 |
iliate | +1.074 |
rys | +1.052 |
yg | +1.046 |
Neg logit contributions | |
ileaks | -1.171 |
burgh | -1.151 |
ocrates | -1.092 |
roid | -1.087 |
paren | -1.084 |
Token | bird |
Token ID | 6512 |
Feature activation | +7.47e+00 |
Pos logit contributions | |
LY | +2.837 |
lore | +2.585 |
iliate | +2.524 |
rys | +2.504 |
yg | +2.454 |
Neg logit contributions | |
ileaks | -3.015 |
burgh | -2.985 |
ocrates | -2.819 |
paren | -2.798 |
roid | -2.786 |
Token | migration |
Token ID | 13472 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
LY | +5.588 |
lore | +5.303 |
rys | +5.101 |
iliate | +5.066 |
look | +4.924 |
Neg logit contributions | |
ileaks | -4.714 |
burgh | -4.598 |
ocrates | -4.420 |
paren | -4.365 |
roid | -4.293 |
Token | . |
Token ID | 13 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
LY | +1.107 |
lore | +0.976 |
iliate | +0.955 |
rys | +0.921 |
yg | +0.913 |
Neg logit contributions | |
ileaks | -2.196 |
burgh | -2.167 |
ocrates | -2.085 |
roid | -2.076 |
paren | -2.073 |
Token | All |
Token ID | 1439 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
LY | +0.206 |
lore | +0.191 |
iliate | +0.189 |
rys | +0.185 |
yg | +0.184 |
Neg logit contributions | |
ileaks | -0.184 |
burgh | -0.181 |
ocrates | -0.171 |
roid | -0.170 |
paren | -0.169 |
Token | those |
Token ID | 883 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
ileaks | +1.692 |
burgh | +1.665 |
roid | +1.567 |
ocrates | +1.555 |
paren | +1.541 |
Neg logit contributions | |
LY | -1.796 |
iliate | -1.663 |
lore | -1.655 |
rys | -1.585 |
yg | -1.581 |
Token | ripe |
Token ID | 29036 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
ileaks | +1.548 |
burgh | +1.525 |
roid | +1.449 |
ocrates | +1.446 |
paren | +1.428 |
Neg logit contributions | |
LY | -1.598 |
iliate | -1.479 |
lore | -1.471 |
rys | -1.418 |
yg | -1.415 |
Token | sovereign |
Token ID | 18901 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
ileaks | +0.058 |
burgh | +0.057 |
ocrates | +0.054 |
roid | +0.054 |
paren | +0.053 |
Neg logit contributions | |
LY | -0.065 |
lore | -0.061 |
iliate | -0.060 |
rys | -0.059 |
yg | -0.058 |
Token | nation |
Token ID | 3277 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ileaks | +0.557 |
burgh | +0.547 |
roid | +0.517 |
ocrates | +0.516 |
paren | +0.513 |
Neg logit contributions | |
LY | -0.611 |
lore | -0.568 |
iliate | -0.561 |
rys | -0.548 |
yg | -0.545 |
Token | ). |
Token ID | 737 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ileaks | +1.762 |
burgh | +1.738 |
roid | +1.640 |
ocrates | +1.638 |
paren | +1.623 |
Neg logit contributions | |
LY | -2.082 |
lore | -1.934 |
iliate | -1.913 |
rys | -1.879 |
yg | -1.865 |
Token |
|
Token ID | 198 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
ileaks | +1.040 |
burgh | +1.035 |
ocrates | +0.970 |
roid | +0.965 |
paren | +0.965 |
Neg logit contributions | |
LY | -1.079 |
iliate | -1.005 |
lore | -1.001 |
rys | -0.988 |
yg | -0.964 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ileaks | +0.247 |
burgh | +0.246 |
roid | +0.230 |
ocrates | +0.229 |
paren | +0.229 |
Neg logit contributions | |
LY | -0.301 |
lore | -0.280 |
iliate | -0.279 |
rys | -0.273 |
yg | -0.270 |
Token | At |
Token ID | 2953 |
Feature activation | +9.20e+00 |
Pos logit contributions | |
ileaks | +1.132 |
burgh | +1.114 |
paren | +1.058 |
roid | +1.051 |
ocrates | +1.048 |
Neg logit contributions | |
LY | -1.200 |
iliate | -1.117 |
lore | -1.116 |
rys | -1.091 |
yg | -1.072 |
Token | present |
Token ID | 1944 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
LY | +5.777 |
lore | +5.358 |
yg | +5.236 |
iliate | +5.185 |
look | +5.086 |
Neg logit contributions | |
ileaks | -6.731 |
burgh | -6.673 |
roid | -6.360 |
ocrates | -6.288 |
paren | -6.217 |
Token | , |
Token ID | 11 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
ileaks | +0.434 |
burgh | +0.424 |
ocrates | +0.401 |
paren | +0.399 |
roid | +0.398 |
Neg logit contributions | |
LY | -0.511 |
lore | -0.473 |
iliate | -0.471 |
rys | -0.462 |
yg | -0.452 |
Token | it |
Token ID | 340 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
LY | +0.245 |
lore | +0.226 |
iliate | +0.224 |
rys | +0.220 |
yg | +0.217 |
Neg logit contributions | |
ileaks | -0.230 |
burgh | -0.225 |
ocrates | -0.214 |
paren | -0.213 |
roid | -0.212 |
Token | is |
Token ID | 318 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ileaks | +1.351 |
burgh | +1.330 |
ocrates | +1.267 |
roid | +1.263 |
paren | +1.257 |
Neg logit contributions | |
LY | -1.104 |
lore | -1.015 |
iliate | -0.999 |
rys | -0.973 |
yg | -0.961 |
Token | unrealistic |
Token ID | 31363 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ileaks | +0.742 |
burgh | +0.729 |
ocrates | +0.694 |
paren | +0.685 |
roid | +0.684 |
Neg logit contributions | |
LY | -0.775 |
lore | -0.719 |
iliate | -0.718 |
rys | -0.700 |
yg | -0.689 |
Token | put |
Token ID | 1234 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
ileaks | +1.494 |
burgh | +1.493 |
ocrates | +1.399 |
roid | +1.397 |
paren | +1.383 |
Neg logit contributions | |
LY | -1.788 |
lore | -1.681 |
iliate | -1.662 |
rys | -1.612 |
yg | -1.598 |
Token | on |
Token ID | 319 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
burgh | +2.674 |
ileaks | +2.644 |
roid | +2.480 |
ocrates | +2.472 |
paren | +2.444 |
Neg logit contributions | |
LY | -3.017 |
lore | -2.823 |
iliate | -2.768 |
rys | -2.679 |
yg | -2.678 |
Token | the |
Token ID | 262 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
LY | +1.807 |
lore | +1.653 |
iliate | +1.630 |
rys | +1.599 |
yg | +1.596 |
Neg logit contributions | |
ileaks | -1.881 |
burgh | -1.841 |
ocrates | -1.747 |
roid | -1.744 |
paren | -1.736 |
Token | floor |
Token ID | 4314 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
LY | +2.037 |
lore | +1.848 |
iliate | +1.820 |
rys | +1.778 |
yg | +1.769 |
Neg logit contributions | |
ileaks | -2.453 |
burgh | -2.396 |
ocrates | -2.291 |
paren | -2.275 |
roid | -2.274 |
Token | in |
Token ID | 287 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
LY | +0.355 |
lore | +0.327 |
iliate | +0.323 |
rys | +0.315 |
yg | +0.314 |
Neg logit contributions | |
ileaks | -0.365 |
burgh | -0.360 |
ocrates | -0.342 |
roid | -0.340 |
paren | -0.339 |
Token | the |
Token ID | 262 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
burgh | +1.498 |
ileaks | +1.479 |
ocrates | +1.391 |
roid | +1.388 |
paren | +1.375 |
Neg logit contributions | |
LY | -1.764 |
lore | -1.639 |
iliate | -1.632 |
rys | -1.574 |
yg | -1.565 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
LY | +2.964 |
lore | +2.695 |
iliate | +2.639 |
rys | +2.606 |
yg | +2.599 |
Neg logit contributions | |
ileaks | -3.284 |
burgh | -3.173 |
paren | -3.061 |
ocrates | -3.055 |
roid | -3.037 |
Token | th |
Token ID | 400 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
burgh | +1.947 |
ileaks | +1.947 |
ocrates | +1.822 |
paren | +1.806 |
roid | +1.805 |
Neg logit contributions | |
LY | -1.996 |
lore | -1.849 |
iliate | -1.815 |
rys | -1.769 |
yg | -1.760 |
Token | round |
Token ID | 2835 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
LY | +0.524 |
lore | +0.480 |
iliate | +0.473 |
rys | +0.460 |
yg | +0.458 |
Neg logit contributions | |
ileaks | -0.614 |
burgh | -0.606 |
ocrates | -0.577 |
roid | -0.575 |
paren | -0.572 |
Token | , |
Token ID | 11 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
LY | +1.453 |
lore | +1.334 |
iliate | +1.318 |
rys | +1.289 |
yg | +1.281 |
Neg logit contributions | |
ileaks | -1.444 |
burgh | -1.419 |
ocrates | -1.350 |
roid | -1.341 |
paren | -1.331 |
Token | are |
Token ID | 389 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ileaks | +0.406 |
burgh | +0.399 |
roid | +0.380 |
ocrates | +0.380 |
paren | +0.378 |
Neg logit contributions | |
LY | -0.354 |
lore | -0.324 |
iliate | -0.319 |
rys | -0.312 |
yg | -0.310 |
Token | You |
Token ID | 1639 |
Feature activation | +5.08e-03 |
Pos logit contributions | |
LY | +1.868 |
lore | +1.721 |
iliate | +1.682 |
rys | +1.649 |
yg | +1.647 |
Neg logit contributions | |
ileaks | -1.826 |
burgh | -1.794 |
ocrates | -1.710 |
roid | -1.693 |
paren | -1.689 |
Token | � |
Token ID | 447 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
LY | +0.003 |
lore | +0.003 |
iliate | +0.003 |
rys | +0.003 |
yg | +0.003 |
Neg logit contributions | |
ileaks | -0.004 |
burgh | -0.004 |
ocrates | -0.003 |
roid | -0.003 |
paren | -0.003 |
Token | � |
Token ID | 247 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
LY | +0.637 |
lore | +0.589 |
iliate | +0.581 |
rys | +0.568 |
yg | +0.567 |
Neg logit contributions | |
ileaks | -0.586 |
burgh | -0.575 |
ocrates | -0.546 |
paren | -0.540 |
roid | -0.540 |
Token | re |
Token ID | 260 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
LY | +0.336 |
lore | +0.305 |
iliate | +0.301 |
rys | +0.292 |
yg | +0.291 |
Neg logit contributions | |
ileaks | -0.445 |
burgh | -0.439 |
ocrates | -0.419 |
roid | -0.419 |
paren | -0.416 |
Token | impossible |
Token ID | 5340 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
LY | +0.065 |
lore | +0.059 |
iliate | +0.059 |
rys | +0.057 |
yg | +0.057 |
Neg logit contributions | |
ileaks | -0.071 |
burgh | -0.070 |
ocrates | -0.067 |
roid | -0.066 |
paren | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ileaks | +0.136 |
burgh | +0.134 |
ocrates | +0.126 |
roid | +0.126 |
paren | +0.125 |
Neg logit contributions | |
LY | -0.165 |
lore | -0.154 |
iliate | -0.152 |
rys | -0.149 |
yg | -0.148 |
Token | C |
Token ID | 327 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
LY | +0.235 |
lore | +0.220 |
iliate | +0.219 |
rys | +0.215 |
yg | +0.214 |
Neg logit contributions | |
ileaks | -0.143 |
burgh | -0.141 |
ocrates | -0.131 |
roid | -0.130 |
paren | -0.130 |
Token | � |
Token ID | 447 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
LY | +2.657 |
iliate | +2.423 |
lore | +2.417 |
rys | +2.378 |
yg | +2.365 |
Neg logit contributions | |
ileaks | -2.586 |
burgh | -2.508 |
ocrates | -2.374 |
paren | -2.356 |
roid | -2.350 |
Token | � |
Token ID | 247 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
LY | +2.361 |
lore | +2.168 |
iliate | +2.134 |
yg | +2.093 |
rys | +2.091 |
Neg logit contributions | |
ileaks | -2.072 |
burgh | -2.021 |
ocrates | -1.939 |
roid | -1.901 |
paren | -1.899 |
Token | mon |
Token ID | 2144 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
LY | +1.335 |
lore | +1.229 |
iliate | +1.212 |
rys | +1.188 |
yg | +1.183 |
Neg logit contributions | |
ileaks | -1.306 |
burgh | -1.285 |
ocrates | -1.220 |
roid | -1.208 |
paren | -1.208 |
Token | . |
Token ID | 13 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
LY | +4.199 |
lore | +3.850 |
iliate | +3.778 |
yg | +3.724 |
rys | +3.700 |
Neg logit contributions | |
ileaks | -3.539 |
burgh | -3.470 |
ocrates | -3.278 |
paren | -3.265 |
roid | -3.257 |
Token | reckon |
Token ID | 43851 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
ileaks | +0.492 |
burgh | +0.486 |
roid | +0.462 |
ocrates | +0.458 |
paren | +0.456 |
Neg logit contributions | |
LY | -0.520 |
lore | -0.483 |
iliate | -0.475 |
rys | -0.462 |
yg | -0.461 |
Token | with |
Token ID | 351 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ileaks | +2.694 |
burgh | +2.628 |
ocrates | +2.521 |
paren | +2.508 |
roid | +2.508 |
Neg logit contributions | |
LY | -2.261 |
lore | -2.068 |
iliate | -2.042 |
rys | -2.005 |
yg | -1.963 |
Token | A |
Token ID | 317 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ileaks | +0.157 |
burgh | +0.154 |
ocrates | +0.146 |
roid | +0.145 |
paren | +0.144 |
Neg logit contributions | |
LY | -0.173 |
lore | -0.159 |
iliate | -0.158 |
rys | -0.155 |
yg | -0.154 |
Token | vel |
Token ID | 626 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
LY | +0.102 |
lore | +0.094 |
iliate | +0.093 |
rys | +0.090 |
yg | +0.090 |
Neg logit contributions | |
ileaks | -0.101 |
burgh | -0.099 |
roid | -0.094 |
ocrates | -0.094 |
paren | -0.093 |
Token | ine |
Token ID | 500 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
LY | +1.456 |
lore | +1.368 |
iliate | +1.351 |
rys | +1.323 |
yg | +1.314 |
Neg logit contributions | |
ileaks | -1.037 |
burgh | -1.025 |
paren | -0.960 |
ocrates | -0.959 |
roid | -0.951 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
LY | +0.804 |
lore | +0.742 |
iliate | +0.733 |
rys | +0.716 |
yg | +0.713 |
Neg logit contributions | |
ileaks | -0.757 |
burgh | -0.744 |
ocrates | -0.705 |
roid | -0.701 |
paren | -0.700 |
Token | an |
Token ID | 281 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
LY | +0.149 |
lore | +0.137 |
iliate | +0.136 |
yg | +0.133 |
rys | +0.133 |
Neg logit contributions | |
ileaks | -0.139 |
burgh | -0.137 |
ocrates | -0.130 |
roid | -0.129 |
paren | -0.128 |
Token | Assassin |
Token ID | 21401 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
ileaks | +2.024 |
burgh | +1.980 |
roid | +1.890 |
ocrates | +1.859 |
ocrat | +1.833 |
Neg logit contributions | |
LY | -2.561 |
lore | -2.393 |
iliate | -2.362 |
yg | -2.343 |
rys | -2.336 |
Token | with |
Token ID | 351 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
LY | +3.643 |
lore | +3.334 |
iliate | +3.297 |
rys | +3.198 |
yg | +3.148 |
Neg logit contributions | |
ileaks | -3.588 |
burgh | -3.492 |
paren | -3.331 |
ocrates | -3.319 |
roid | -3.263 |
Token | a |
Token ID | 257 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
ileaks | +1.597 |
burgh | +1.587 |
roid | +1.501 |
ocrates | +1.491 |
paren | +1.467 |
Neg logit contributions | |
LY | -1.905 |
lore | -1.767 |
iliate | -1.762 |
rys | -1.724 |
yg | -1.721 |
Token | French |
Token ID | 4141 |
Feature activation | +6.01e+00 |
Pos logit contributions | |
ileaks | +0.148 |
burgh | +0.147 |
roid | +0.138 |
ocrates | +0.138 |
paren | +0.137 |
Neg logit contributions | |
LY | -0.151 |
lore | -0.139 |
iliate | -0.138 |
rys | -0.134 |
yg | -0.134 |
Token | Port |
Token ID | 4347 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
LY | +0.172 |
lore | +0.159 |
iliate | +0.157 |
rys | +0.153 |
yg | +0.153 |
Neg logit contributions | |
ileaks | -0.156 |
burgh | -0.154 |
ocrates | -0.146 |
roid | -0.145 |
paren | -0.144 |
Token | Sok |
Token ID | 37641 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
burgh | +2.125 |
ileaks | +2.119 |
ocrates | +2.003 |
roid | +1.976 |
paren | +1.941 |
Neg logit contributions | |
LY | -1.924 |
lore | -1.768 |
iliate | -1.749 |
rys | -1.687 |
yg | -1.664 |
Token | h |
Token ID | 71 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
ileaks | +0.967 |
burgh | +0.952 |
ocrates | +0.904 |
roid | +0.899 |
paren | +0.892 |
Neg logit contributions | |
LY | -0.976 |
lore | -0.895 |
iliate | -0.888 |
rys | -0.862 |
yg | -0.861 |
Token | na |
Token ID | 2616 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
ileaks | +4.049 |
burgh | +3.993 |
roid | +3.739 |
ocrates | +3.738 |
paren | +3.669 |
Neg logit contributions | |
LY | -4.069 |
lore | -3.713 |
iliate | -3.642 |
yg | -3.547 |
rys | -3.512 |
Token | ( |
Token ID | 357 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
LY | +0.634 |
lore | +0.582 |
iliate | +0.576 |
rys | +0.562 |
yg | +0.560 |
Neg logit contributions | |
ileaks | -0.657 |
burgh | -0.645 |
ocrates | -0.614 |
paren | -0.610 |
roid | -0.609 |
Token | for |
Token ID | 1640 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
LY | +0.764 |
lore | +0.705 |
iliate | +0.696 |
rys | +0.681 |
yg | +0.679 |
Neg logit contributions | |
ileaks | -0.699 |
burgh | -0.687 |
ocrates | -0.651 |
roid | -0.647 |
paren | -0.644 |
Token | Cairo |
Token ID | 23732 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
LY | +0.332 |
lore | +0.307 |
iliate | +0.303 |
rys | +0.296 |
yg | +0.295 |
Neg logit contributions | |
ileaks | -0.320 |
burgh | -0.316 |
ocrates | -0.298 |
roid | -0.297 |
paren | -0.295 |
Token | ) |
Token ID | 8 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
ileaks | +0.211 |
burgh | +0.208 |
ocrates | +0.196 |
roid | +0.195 |
paren | +0.193 |
Neg logit contributions | |
LY | -0.242 |
lore | -0.224 |
iliate | -0.222 |
rys | -0.217 |
yg | -0.216 |
Token | and |
Token ID | 290 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
ileaks | +0.022 |
burgh | +0.022 |
ocrates | +0.021 |
roid | +0.021 |
paren | +0.021 |
Neg logit contributions | |
LY | -0.020 |
lore | -0.018 |
iliate | -0.018 |
rys | -0.017 |
yg | -0.017 |
Token | Saf |
Token ID | 6895 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
LY | +0.251 |
lore | +0.231 |
iliate | +0.228 |
rys | +0.222 |
yg | +0.221 |
Neg logit contributions | |
ileaks | -0.267 |
burgh | -0.263 |
ocrates | -0.250 |
roid | -0.249 |
paren | -0.247 |
Token | aga |
Token ID | 8126 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ileaks | +0.476 |
burgh | +0.469 |
ocrates | +0.444 |
roid | +0.442 |
paren | +0.440 |
Neg logit contributions | |
LY | -0.508 |
lore | -0.469 |
iliate | -0.463 |
rys | -0.452 |
yg | -0.450 |
Token | line |
Token ID | 1627 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
LY | +1.490 |
lore | +1.324 |
rys | +1.277 |
iliate | +1.266 |
yg | +1.262 |
Neg logit contributions | |
ileaks | -2.590 |
burgh | -2.528 |
ocrates | -2.450 |
paren | -2.434 |
roid | -2.410 |
Token | during |
Token ID | 1141 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
ileaks | +0.082 |
burgh | +0.081 |
ocrates | +0.076 |
roid | +0.076 |
paren | +0.076 |
Neg logit contributions | |
LY | -0.087 |
lore | -0.080 |
iliate | -0.079 |
rys | -0.078 |
yg | -0.077 |
Token | Commons |
Token ID | 13815 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
LY | +2.766 |
lore | +2.531 |
iliate | +2.502 |
rys | +2.466 |
yg | +2.437 |
Neg logit contributions | |
ileaks | -2.866 |
burgh | -2.849 |
ocrates | -2.708 |
roid | -2.702 |
paren | -2.669 |
Token | Question |
Token ID | 18233 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
LY | +1.379 |
lore | +1.275 |
iliate | +1.254 |
rys | +1.233 |
yg | +1.224 |
Neg logit contributions | |
ileaks | -1.294 |
burgh | -1.276 |
ocrates | -1.211 |
roid | -1.205 |
paren | -1.194 |
Token | Period |
Token ID | 18581 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
LY | +1.084 |
lore | +0.997 |
iliate | +0.984 |
rys | +0.972 |
yg | +0.964 |
Neg logit contributions | |
ileaks | -0.903 |
burgh | -0.897 |
ocrates | -0.857 |
roid | -0.835 |
paren | -0.833 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
ileaks | +0.180 |
burgh | +0.177 |
ocrates | +0.167 |
roid | +0.166 |
paren | +0.165 |
Neg logit contributions | |
LY | -0.217 |
lore | -0.201 |
iliate | -0.199 |
rys | -0.195 |
yg | -0.194 |
Token | as |
Token ID | 355 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
LY | +0.696 |
lore | +0.641 |
iliate | +0.633 |
rys | +0.618 |
yg | +0.616 |
Neg logit contributions | |
ileaks | -0.682 |
burgh | -0.671 |
ocrates | -0.637 |
roid | -0.634 |
paren | -0.631 |
Token | Conservative |
Token ID | 11132 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
LY | +1.331 |
lore | +1.226 |
iliate | +1.210 |
rys | +1.182 |
yg | +1.178 |
Neg logit contributions | |
ileaks | -1.337 |
burgh | -1.317 |
ocrates | -1.249 |
roid | -1.244 |
paren | -1.238 |
Token | MPs |
Token ID | 14952 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
LY | +2.597 |
lore | +2.368 |
iliate | +2.320 |
rys | +2.293 |
yg | +2.284 |
Neg logit contributions | |
ileaks | -3.047 |
burgh | -3.002 |
ocrates | -2.873 |
paren | -2.830 |
roid | -2.825 |
Token | accused |
Token ID | 5371 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
LY | +0.459 |
lore | +0.425 |
iliate | +0.421 |
rys | +0.412 |
yg | +0.411 |
Neg logit contributions | |
ileaks | -0.387 |
burgh | -0.380 |
ocrates | -0.359 |
roid | -0.357 |
paren | -0.357 |
Token | him |
Token ID | 683 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
LY | +2.503 |
lore | +2.286 |
iliate | +2.250 |
rys | +2.210 |
yg | +2.202 |
Neg logit contributions | |
ileaks | -2.665 |
burgh | -2.640 |
ocrates | -2.505 |
paren | -2.489 |
roid | -2.479 |
Token | and |
Token ID | 290 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
LY | +0.072 |
lore | +0.067 |
iliate | +0.066 |
rys | +0.064 |
yg | +0.064 |
Neg logit contributions | |
ileaks | -0.070 |
burgh | -0.068 |
ocrates | -0.065 |
roid | -0.065 |
paren | -0.064 |
Token | do |
Token ID | 466 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
LY | +0.490 |
lore | +0.452 |
iliate | +0.445 |
rys | +0.434 |
yg | +0.433 |
Neg logit contributions | |
ileaks | -0.495 |
burgh | -0.486 |
ocrates | -0.462 |
roid | -0.461 |
paren | -0.457 |
Token | their |
Token ID | 511 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ileaks | +1.021 |
burgh | +1.003 |
ocrates | +0.955 |
roid | +0.951 |
paren | +0.951 |
Neg logit contributions | |
LY | -1.027 |
lore | -0.955 |
iliate | -0.935 |
rys | -0.910 |
yg | -0.904 |
Token | best |
Token ID | 1266 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
ileaks | +0.809 |
burgh | +0.794 |
ocrates | +0.746 |
roid | +0.745 |
paren | +0.738 |
Neg logit contributions | |
LY | -0.934 |
lore | -0.858 |
iliate | -0.854 |
rys | -0.834 |
yg | -0.831 |
Token | to |
Token ID | 284 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
LY | +4.402 |
lore | +4.028 |
iliate | +3.979 |
rys | +3.895 |
yg | +3.867 |
Neg logit contributions | |
burgh | -4.971 |
ileaks | -4.947 |
ocrates | -4.768 |
paren | -4.690 |
roid | -4.652 |
Token | public |
Token ID | 1171 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
LY | +1.219 |
lore | +1.115 |
iliate | +1.108 |
rys | +1.082 |
yg | +1.077 |
Neg logit contributions | |
ileaks | -1.327 |
burgh | -1.307 |
ocrates | -1.249 |
paren | -1.236 |
roid | -1.229 |
Token | ize |
Token ID | 1096 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ileaks | +0.692 |
burgh | +0.677 |
roid | +0.640 |
paren | +0.639 |
ocrates | +0.639 |
Neg logit contributions | |
LY | -0.762 |
lore | -0.711 |
iliate | -0.699 |
rys | -0.688 |
yg | -0.680 |
Token | their |
Token ID | 511 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
LY | +0.077 |
lore | +0.071 |
iliate | +0.071 |
rys | +0.069 |
yg | +0.068 |
Neg logit contributions | |
ileaks | -0.077 |
burgh | -0.076 |
roid | -0.072 |
ocrates | -0.072 |
paren | -0.072 |
Token | positions |
Token ID | 6116 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
LY | +0.569 |
lore | +0.525 |
iliate | +0.521 |
rys | +0.506 |
yg | +0.505 |
Neg logit contributions | |
ileaks | -0.560 |
burgh | -0.552 |
roid | -0.522 |
ocrates | -0.522 |
paren | -0.519 |
Token | in |
Token ID | 287 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
LY | +3.288 |
lore | +3.013 |
iliate | +2.933 |
yg | +2.895 |
rys | +2.858 |
Neg logit contributions | |
ileaks | -3.470 |
burgh | -3.434 |
ocrates | -3.268 |
roid | -3.229 |
paren | -3.228 |
Token | the |
Token ID | 262 |
Feature activation | +7.29e+00 |
Pos logit contributions | |
LY | +1.916 |
lore | +1.788 |
iliate | +1.779 |
yg | +1.747 |
rys | +1.739 |
Neg logit contributions | |
ileaks | -1.178 |
burgh | -1.153 |
ocrates | -1.082 |
roid | -1.074 |
paren | -1.061 |
Token | and |
Token ID | 290 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
LY | +5.712 |
iliate | +5.209 |
lore | +5.196 |
yg | +5.088 |
rys | +5.074 |
Neg logit contributions | |
ileaks | -4.234 |
burgh | -4.014 |
ocrates | -3.752 |
paren | -3.701 |
roid | -3.627 |
Token | reproductive |
Token ID | 18391 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
LY | +1.078 |
lore | +0.996 |
iliate | +0.985 |
rys | +0.962 |
yg | +0.962 |
Neg logit contributions | |
ileaks | -0.975 |
burgh | -0.961 |
ocrates | -0.905 |
roid | -0.898 |
paren | -0.892 |
Token | capabilities |
Token ID | 9889 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
LY | +3.466 |
lore | +3.162 |
iliate | +3.083 |
yg | +3.068 |
rys | +3.028 |
Neg logit contributions | |
ileaks | -3.476 |
burgh | -3.338 |
ocrates | -3.154 |
paren | -3.127 |
roid | -3.116 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
LY | +1.941 |
lore | +1.784 |
iliate | +1.763 |
yg | +1.726 |
rys | +1.712 |
Neg logit contributions | |
ileaks | -1.878 |
burgh | -1.832 |
ocrates | -1.729 |
roid | -1.719 |
paren | -1.717 |
Token | Some |
Token ID | 2773 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ileaks | +0.986 |
burgh | +0.984 |
ocrates | +0.934 |
roid | +0.927 |
paren | +0.923 |
Neg logit contributions | |
LY | -1.059 |
lore | -0.986 |
iliate | -0.984 |
rys | -0.970 |
yg | -0.949 |
Token | said |
Token ID | 531 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
LY | +0.879 |
lore | +0.813 |
iliate | +0.803 |
rys | +0.785 |
yg | +0.783 |
Neg logit contributions | |
ileaks | -0.792 |
burgh | -0.779 |
ocrates | -0.736 |
roid | -0.733 |
paren | -0.730 |
Token | that |
Token ID | 326 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ileaks | +0.509 |
burgh | +0.498 |
ocrates | +0.476 |
paren | +0.471 |
roid | +0.471 |
Neg logit contributions | |
LY | -0.647 |
lore | -0.603 |
iliate | -0.597 |
rys | -0.585 |
yg | -0.579 |
Token | a |
Token ID | 257 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
ileaks | +0.124 |
burgh | +0.121 |
ocrates | +0.116 |
roid | +0.115 |
paren | +0.115 |
Neg logit contributions | |
LY | -0.140 |
lore | -0.130 |
iliate | -0.129 |
rys | -0.126 |
yg | -0.125 |
Token | woman |
Token ID | 2415 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
ileaks | +0.518 |
burgh | +0.512 |
ocrates | +0.486 |
paren | +0.482 |
roid | +0.481 |
Neg logit contributions | |
LY | -0.646 |
lore | -0.603 |
iliate | -0.596 |
rys | -0.581 |
yg | -0.578 |
Token | would |
Token ID | 561 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
ileaks | +0.469 |
burgh | +0.462 |
ocrates | +0.441 |
roid | +0.439 |
paren | +0.437 |
Neg logit contributions | |
LY | -0.424 |
lore | -0.390 |
iliate | -0.385 |
rys | -0.376 |
yg | -0.374 |
Token | neglect |
Token ID | 17985 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
ileaks | +0.023 |
burgh | +0.022 |
ocrates | +0.021 |
roid | +0.021 |
paren | +0.021 |
Neg logit contributions | |
LY | -0.024 |
lore | -0.022 |
iliate | -0.021 |
rys | -0.021 |
yg | -0.021 |
Token | it |
Token ID | 340 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
LY | +3.323 |
lore | +2.996 |
iliate | +2.984 |
yg | +2.908 |
rys | +2.900 |
Neg logit contributions | |
ileaks | -3.342 |
burgh | -3.227 |
ocrates | -3.089 |
paren | -3.037 |
roid | -3.015 |
Token | anyway |
Token ID | 6949 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
LY | +3.384 |
lore | +3.094 |
iliate | +3.039 |
rys | +2.968 |
yg | +2.961 |
Neg logit contributions | |
ileaks | -3.317 |
burgh | -3.197 |
ocrates | -3.044 |
roid | -3.032 |
paren | -3.005 |
Token | ) |
Token ID | 8 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
LY | +1.376 |
lore | +1.271 |
iliate | +1.255 |
rys | +1.225 |
yg | +1.223 |
Neg logit contributions | |
ileaks | -1.206 |
burgh | -1.180 |
ocrates | -1.116 |
roid | -1.112 |
paren | -1.106 |
Token | or |
Token ID | 393 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
LY | +0.712 |
lore | +0.656 |
iliate | +0.648 |
rys | +0.633 |
yg | +0.630 |
Neg logit contributions | |
ileaks | -0.709 |
burgh | -0.699 |
ocrates | -0.663 |
roid | -0.660 |
paren | -0.657 |
Token | anyone |
Token ID | 2687 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
LY | +1.760 |
lore | +1.602 |
iliate | +1.578 |
rys | +1.537 |
yg | +1.535 |
Neg logit contributions | |
ileaks | -2.105 |
burgh | -2.067 |
ocrates | -1.972 |
roid | -1.960 |
paren | -1.958 |
Token | looking |
Token ID | 2045 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ileaks | +0.542 |
burgh | +0.534 |
ocrates | +0.507 |
roid | +0.505 |
paren | +0.502 |
Neg logit contributions | |
LY | -0.568 |
lore | -0.525 |
iliate | -0.520 |
rys | -0.508 |
yg | -0.505 |
Token | to |
Token ID | 284 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
ileaks | +0.724 |
burgh | +0.711 |
ocrates | +0.670 |
roid | +0.667 |
paren | +0.664 |
Neg logit contributions | |
LY | -0.900 |
lore | -0.835 |
iliate | -0.826 |
rys | -0.809 |
yg | -0.806 |
Token | get |
Token ID | 651 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
burgh | +1.900 |
ileaks | +1.890 |
roid | +1.821 |
paren | +1.772 |
ocrates | +1.769 |
Neg logit contributions | |
LY | -1.997 |
lore | -1.874 |
iliate | -1.811 |
yg | -1.776 |
rys | -1.765 |
Token | a |
Token ID | 257 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
LY | +1.112 |
lore | +1.024 |
iliate | +1.012 |
rys | +0.988 |
yg | +0.984 |
Neg logit contributions | |
ileaks | -1.104 |
burgh | -1.086 |
ocrates | -1.030 |
roid | -1.025 |
paren | -1.021 |
Token | CL |
Token ID | 7852 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
LY | +1.322 |
lore | +1.213 |
iliate | +1.198 |
rys | +1.168 |
yg | +1.163 |
Neg logit contributions | |
ileaks | -1.432 |
burgh | -1.411 |
ocrates | -1.341 |
roid | -1.335 |
paren | -1.330 |
Token | Y |
Token ID | 56 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
LY | +0.073 |
lore | +0.066 |
iliate | +0.065 |
rys | +0.063 |
yg | +0.062 |
Neg logit contributions | |
ileaks | -0.116 |
burgh | -0.115 |
ocrates | -0.110 |
roid | -0.110 |
paren | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
LY | +1.735 |
lore | +1.602 |
iliate | +1.575 |
yg | +1.545 |
rys | +1.528 |
Neg logit contributions | |
ileaks | -1.766 |
burgh | -1.726 |
ocrates | -1.633 |
roid | -1.619 |
paren | -1.616 |
Token | By |
Token ID | 2750 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
burgh | +0.417 |
ileaks | +0.417 |
ocrates | +0.396 |
roid | +0.392 |
paren | +0.390 |
Neg logit contributions | |
LY | -0.406 |
iliate | -0.374 |
lore | -0.372 |
rys | -0.365 |
yg | -0.358 |
Token | saying |
Token ID | 2282 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ileaks | +1.223 |
burgh | +1.206 |
ocrates | +1.153 |
roid | +1.143 |
paren | +1.136 |
Neg logit contributions | |
LY | -1.267 |
lore | -1.163 |
iliate | -1.156 |
rys | -1.134 |
yg | -1.117 |
Token | � |
Token ID | 564 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ileaks | +0.886 |
burgh | +0.868 |
ocrates | +0.821 |
paren | +0.811 |
roid | +0.806 |
Neg logit contributions | |
LY | -1.302 |
lore | -1.215 |
iliate | -1.205 |
rys | -1.186 |
yg | -1.173 |
Token | � |
Token ID | 250 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ileaks | +1.363 |
burgh | +1.347 |
ocrates | +1.266 |
roid | +1.263 |
paren | +1.259 |
Neg logit contributions | |
LY | -1.571 |
lore | -1.455 |
iliate | -1.442 |
rys | -1.410 |
yg | -1.400 |
Token | this |
Token ID | 5661 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
ileaks | +0.895 |
burgh | +0.885 |
ocrates | +0.832 |
paren | +0.828 |
roid | +0.827 |
Neg logit contributions | |
LY | -1.097 |
lore | -1.016 |
iliate | -1.015 |
rys | -0.989 |
yg | -0.981 |
Token | is |
Token ID | 318 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ileaks | +0.477 |
burgh | +0.469 |
ocrates | +0.445 |
roid | +0.442 |
paren | +0.441 |
Neg logit contributions | |
LY | -0.505 |
lore | -0.466 |
iliate | -0.462 |
rys | -0.451 |
yg | -0.448 |
Token | so |
Token ID | 523 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
LY | +0.014 |
lore | +0.013 |
iliate | +0.013 |
rys | +0.012 |
yg | +0.012 |
Neg logit contributions | |
ileaks | -0.014 |
burgh | -0.013 |
ocrates | -0.013 |
roid | -0.013 |
paren | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
ileaks | +0.526 |
burgh | +0.517 |
ocrates | +0.485 |
roid | +0.481 |
paren | +0.480 |
Neg logit contributions | |
LY | -0.730 |
lore | -0.682 |
iliate | -0.675 |
rys | -0.661 |
yg | -0.658 |
Token | so |
Token ID | 523 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
ileaks | +0.458 |
burgh | +0.451 |
ocrates | +0.428 |
roid | +0.426 |
paren | +0.424 |
Neg logit contributions | |
LY | -0.502 |
lore | -0.464 |
iliate | -0.460 |
rys | -0.448 |
yg | -0.446 |
Token | , |
Token ID | 11 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
ileaks | +0.192 |
burgh | +0.189 |
ocrates | +0.178 |
roid | +0.177 |
paren | +0.176 |
Neg logit contributions | |
LY | -0.246 |
lore | -0.229 |
iliate | -0.227 |
rys | -0.222 |
yg | -0.221 |
Token | Pharma |
Token ID | 41845 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
ileaks | +1.405 |
burgh | +1.359 |
roid | +1.232 |
ocrates | +1.231 |
paren | +1.209 |
Neg logit contributions | |
LY | -3.753 |
lore | -3.555 |
iliate | -3.522 |
rys | -3.475 |
yg | -3.468 |
Token | - |
Token ID | 532 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
ileaks | +5.137 |
burgh | +5.070 |
paren | +4.816 |
roid | +4.801 |
ocrates | +4.786 |
Neg logit contributions | |
LY | -6.743 |
lore | -6.603 |
iliate | -6.511 |
yg | -6.208 |
rys | -6.071 |
Token | Quick |
Token ID | 12029 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
ileaks | +3.926 |
burgh | +3.792 |
paren | +3.714 |
ocrates | +3.656 |
visor | +3.652 |
Neg logit contributions | |
LY | -3.336 |
iliate | -3.147 |
lore | -3.085 |
yg | -2.994 |
rys | -2.961 |
Token | step |
Token ID | 9662 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
ileaks | +1.739 |
burgh | +1.704 |
ocrates | +1.589 |
roid | +1.580 |
paren | +1.572 |
Neg logit contributions | |
LY | -2.713 |
lore | -2.535 |
iliate | -2.509 |
rys | -2.463 |
yg | -2.455 |
Token | ) |
Token ID | 8 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
burgh | +2.108 |
ileaks | +2.092 |
paren | +1.929 |
ocrates | +1.925 |
roid | +1.918 |
Neg logit contributions | |
LY | -3.425 |
iliate | -3.251 |
lore | -3.243 |
rys | -3.163 |
yg | -3.135 |
Token | s |
Token ID | 264 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
ileaks | +0.363 |
burgh | +0.359 |
ocrates | +0.335 |
roid | +0.334 |
paren | +0.330 |
Neg logit contributions | |
LY | -0.533 |
lore | -0.501 |
iliate | -0.496 |
rys | -0.483 |
yg | -0.481 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
burgh | +1.707 |
ileaks | +1.675 |
roid | +1.590 |
paren | +1.557 |
ocrates | +1.549 |
Neg logit contributions | |
LY | -2.460 |
iliate | -2.325 |
lore | -2.314 |
rys | -2.279 |
yg | -2.234 |
Token | t |
Token ID | 83 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
LY | +1.885 |
lore | +1.727 |
iliate | +1.677 |
yg | +1.643 |
rys | +1.630 |
Neg logit contributions | |
ileaks | -2.584 |
burgh | -2.515 |
ocrates | -2.444 |
paren | -2.387 |
roid | -2.385 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ileaks | +0.473 |
burgh | +0.472 |
roid | +0.441 |
ocrates | +0.438 |
paren | +0.437 |
Neg logit contributions | |
LY | -0.617 |
lore | -0.575 |
iliate | -0.572 |
rys | -0.561 |
yg | -0.554 |
Token | A |
Token ID | 317 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
LY | +0.867 |
lore | +0.792 |
iliate | +0.781 |
rys | +0.761 |
yg | +0.758 |
Neg logit contributions | |
ileaks | -1.015 |
burgh | -0.999 |
ocrates | -0.952 |
roid | -0.948 |
paren | -0.945 |
Token | US |
Token ID | 2937 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
ileaks | +0.506 |
burgh | +0.500 |
roid | +0.472 |
ocrates | +0.471 |
paren | +0.467 |
Neg logit contributions | |
LY | -0.533 |
lore | -0.495 |
iliate | -0.492 |
rys | -0.481 |
yg | -0.477 |
Token | brother |
Token ID | 3956 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
LY | +4.045 |
lore | +3.695 |
iliate | +3.591 |
rys | +3.584 |
yg | +3.574 |
Neg logit contributions | |
ileaks | -3.391 |
burgh | -3.237 |
ocrates | -3.151 |
paren | -3.080 |
roid | -3.061 |
Token | , |
Token ID | 11 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
LY | +4.745 |
lore | +4.300 |
iliate | +4.159 |
rys | +4.149 |
yg | +4.101 |
Neg logit contributions | |
ileaks | -5.046 |
burgh | -4.858 |
ocrates | -4.692 |
paren | -4.679 |
roid | -4.622 |
Token | Jacob |
Token ID | 12806 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
LY | +1.923 |
lore | +1.750 |
iliate | +1.718 |
rys | +1.677 |
yg | +1.671 |
Neg logit contributions | |
ileaks | -2.456 |
burgh | -2.415 |
ocrates | -2.307 |
roid | -2.298 |
paren | -2.296 |
Token | , |
Token ID | 11 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
LY | +3.995 |
lore | +3.682 |
yg | +3.608 |
iliate | +3.586 |
rys | +3.562 |
Neg logit contributions | |
ileaks | -4.160 |
burgh | -4.033 |
ocrates | -3.857 |
paren | -3.850 |
roid | -3.788 |
Token | is |
Token ID | 318 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
LY | +1.466 |
lore | +1.349 |
iliate | +1.331 |
rys | +1.302 |
yg | +1.297 |
Neg logit contributions | |
ileaks | -1.428 |
burgh | -1.403 |
ocrates | -1.332 |
roid | -1.325 |
paren | -1.322 |
Token | also |
Token ID | 635 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
ileaks | +0.556 |
burgh | +0.552 |
ocrates | +0.519 |
roid | +0.517 |
paren | +0.515 |
Neg logit contributions | |
LY | -0.628 |
lore | -0.585 |
iliate | -0.582 |
rys | -0.567 |
yg | -0.561 |
Token | living |
Token ID | 2877 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
burgh | +4.112 |
ileaks | +3.998 |
roid | +3.855 |
ocrates | +3.807 |
paren | +3.767 |
Neg logit contributions | |
LY | -5.303 |
iliate | -5.163 |
lore | -5.051 |
rys | -4.974 |
yg | -4.809 |
Token | on |
Token ID | 319 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
LY | +0.463 |
lore | +0.430 |
iliate | +0.425 |
rys | +0.415 |
yg | +0.414 |
Neg logit contributions | |
ileaks | -0.429 |
burgh | -0.423 |
ocrates | -0.400 |
roid | -0.398 |
paren | -0.396 |
Token | his |
Token ID | 465 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
LY | +1.294 |
lore | +1.191 |
iliate | +1.176 |
rys | +1.149 |
yg | +1.145 |
Neg logit contributions | |
ileaks | -1.277 |
burgh | -1.256 |
ocrates | -1.191 |
roid | -1.186 |
paren | -1.181 |
Token | own |
Token ID | 898 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
burgh | +0.436 |
ileaks | +0.434 |
ocrates | +0.400 |
roid | +0.398 |
paren | +0.394 |
Neg logit contributions | |
LY | -0.745 |
lore | -0.706 |
iliate | -0.700 |
rys | -0.682 |
yg | -0.680 |
Token | playing |
Token ID | 2712 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
LY | +3.128 |
lore | +2.820 |
iliate | +2.804 |
rys | +2.735 |
yg | +2.722 |
Neg logit contributions | |
ileaks | -3.139 |
burgh | -3.024 |
ocrates | -2.892 |
roid | -2.867 |
paren | -2.847 |
Token | to |
Token ID | 284 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
ileaks | +2.053 |
burgh | +2.013 |
roid | +1.884 |
paren | +1.879 |
ocrates | +1.878 |
Neg logit contributions | |
LY | -2.404 |
lore | -2.248 |
iliate | -2.223 |
rys | -2.185 |
yg | -2.152 |
Token | set |
Token ID | 900 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
ileaks | +1.798 |
burgh | +1.786 |
roid | +1.694 |
ocrates | +1.661 |
paren | +1.657 |
Neg logit contributions | |
LY | -1.785 |
lore | -1.665 |
iliate | -1.628 |
rys | -1.587 |
yg | -1.575 |
Token | the |
Token ID | 262 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
LY | +0.607 |
lore | +0.562 |
iliate | +0.555 |
rys | +0.543 |
yg | +0.541 |
Neg logit contributions | |
ileaks | -0.539 |
burgh | -0.530 |
ocrates | -0.501 |
roid | -0.499 |
paren | -0.497 |
Token | stage |
Token ID | 3800 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
LY | +0.790 |
lore | +0.727 |
iliate | +0.716 |
rys | +0.700 |
yg | +0.697 |
Neg logit contributions | |
ileaks | -0.770 |
burgh | -0.755 |
ocrates | -0.719 |
roid | -0.714 |
paren | -0.712 |
Token | for |
Token ID | 329 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ileaks | +0.485 |
burgh | +0.477 |
paren | +0.446 |
ocrates | +0.446 |
roid | +0.445 |
Neg logit contributions | |
LY | -0.668 |
lore | -0.623 |
iliate | -0.620 |
rys | -0.607 |
yg | -0.603 |
Token | non |
Token ID | 1729 |
Feature activation | -6.99e+00 |
Pos logit contributions | |
LY | +0.792 |
lore | +0.731 |
iliate | +0.723 |
rys | +0.706 |
yg | +0.703 |
Neg logit contributions | |
ileaks | -0.745 |
burgh | -0.733 |
ocrates | -0.695 |
roid | -0.691 |
paren | -0.688 |
Token | - |
Token ID | 12 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
ileaks | +2.899 |
burgh | +2.783 |
paren | +2.596 |
roid | +2.521 |
visor | +2.479 |
Neg logit contributions | |
LY | -6.685 |
lore | -6.300 |
iliate | -6.272 |
rys | -6.250 |
yg | -6.066 |
Token | band |
Token ID | 3903 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
ileaks | +1.129 |
burgh | +1.112 |
paren | +1.030 |
roid | +1.030 |
ocrates | +1.008 |
Neg logit contributions | |
LY | -1.998 |
iliate | -1.865 |
lore | -1.861 |
rys | -1.835 |
yg | -1.813 |
Token | width |
Token ID | 10394 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
ileaks | +2.378 |
burgh | +2.334 |
paren | +2.227 |
roid | +2.220 |
ocrates | +2.210 |
Neg logit contributions | |
LY | -1.844 |
lore | -1.645 |
iliate | -1.644 |
rys | -1.600 |
yg | -1.572 |
Token | - |
Token ID | 12 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
ileaks | +1.664 |
burgh | +1.633 |
roid | +1.526 |
paren | +1.505 |
ocrates | +1.486 |
Neg logit contributions | |
LY | -2.585 |
lore | -2.442 |
iliate | -2.423 |
rys | -2.384 |
yg | -2.364 |
Token | incre |
Token ID | 24988 |
Feature activation | +6.52e+00 |
Pos logit contributions | |
ileaks | +1.372 |
burgh | +1.354 |
roid | +1.272 |
paren | +1.270 |
ocrates | +1.251 |
Neg logit contributions | |
LY | -1.882 |
lore | -1.748 |
iliate | -1.739 |
rys | -1.710 |
yg | -1.689 |
Token | inating |
Token ID | 6010 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ileaks | +1.091 |
burgh | +1.057 |
ocrates | +0.965 |
roid | +0.964 |
paren | +0.945 |
Neg logit contributions | |
LY | -2.734 |
lore | -2.572 |
iliate | -2.547 |
rys | -2.511 |
yg | -2.509 |
Token | Black |
Token ID | 2619 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
LY | +0.853 |
lore | +0.791 |
iliate | +0.778 |
rys | +0.764 |
yg | +0.762 |
Neg logit contributions | |
ileaks | -0.681 |
burgh | -0.667 |
ocrates | -0.629 |
roid | -0.625 |
paren | -0.622 |
Token | Women |
Token ID | 6926 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
LY | +2.790 |
lore | +2.609 |
iliate | +2.504 |
yg | +2.478 |
rys | +2.477 |
Neg logit contributions | |
ileaks | -2.167 |
burgh | -2.103 |
ocrates | -1.991 |
roid | -1.980 |
paren | -1.948 |
Token | of |
Token ID | 286 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
LY | +0.628 |
lore | +0.583 |
iliate | +0.572 |
rys | +0.561 |
yg | +0.559 |
Neg logit contributions | |
ileaks | -0.535 |
burgh | -0.526 |
ocrates | -0.497 |
roid | -0.494 |
paren | -0.493 |
Token | the |
Token ID | 262 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ileaks | +0.449 |
burgh | +0.443 |
ocrates | +0.420 |
roid | +0.417 |
paren | +0.416 |
Neg logit contributions | |
LY | -0.437 |
lore | -0.400 |
iliate | -0.398 |
rys | -0.389 |
yg | -0.386 |
Token | 20 |
Token ID | 1160 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
ileaks | +0.340 |
burgh | +0.337 |
ocrates | +0.319 |
roid | +0.319 |
paren | +0.316 |
Neg logit contributions | |
LY | -0.289 |
iliate | -0.262 |
lore | -0.261 |
rys | -0.255 |
yg | -0.253 |
Token | th |
Token ID | 400 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
burgh | +4.835 |
ileaks | +4.594 |
roid | +4.426 |
ocrates | +4.341 |
ocrat | +4.314 |
Neg logit contributions | |
LY | -6.285 |
iliate | -5.909 |
lore | -5.824 |
yg | -5.654 |
rys | -5.629 |
Token | century |
Token ID | 4289 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
burgh | +1.948 |
ileaks | +1.927 |
roid | +1.832 |
ocrates | +1.808 |
paren | +1.783 |
Neg logit contributions | |
LY | -2.185 |
lore | -2.036 |
iliate | -2.024 |
yg | -1.973 |
rys | -1.948 |
Token | ."[ |
Token ID | 18161 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ileaks | +1.377 |
burgh | +1.353 |
ocrates | +1.244 |
roid | +1.242 |
paren | +1.216 |
Neg logit contributions | |
LY | -2.743 |
lore | -2.580 |
iliate | -2.572 |
rys | -2.521 |
yg | -2.512 |
Token | 54 |
Token ID | 4051 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
LY | +0.441 |
lore | +0.410 |
iliate | +0.405 |
yg | +0.396 |
rys | +0.396 |
Neg logit contributions | |
ileaks | -0.352 |
burgh | -0.346 |
ocrates | -0.326 |
roid | -0.324 |
paren | -0.322 |
Token | ] |
Token ID | 60 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
LY | +0.782 |
lore | +0.719 |
iliate | +0.708 |
rys | +0.690 |
yg | +0.690 |
Neg logit contributions | |
ileaks | -0.815 |
burgh | -0.800 |
ocrates | -0.762 |
roid | -0.757 |
paren | -0.752 |
Token | plans |
Token ID | 3352 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
ileaks | +1.139 |
burgh | +1.122 |
ocrates | +1.052 |
roid | +1.044 |
paren | +1.042 |
Neg logit contributions | |
LY | -1.463 |
lore | -1.372 |
iliate | -1.364 |
rys | -1.326 |
yg | -1.325 |
Token | towards |
Token ID | 3371 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ileaks | +0.579 |
burgh | +0.569 |
ocrates | +0.536 |
roid | +0.534 |
paren | +0.532 |
Neg logit contributions | |
LY | -0.693 |
lore | -0.643 |
iliate | -0.637 |
rys | -0.623 |
yg | -0.620 |
Token | helping |
Token ID | 5742 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
LY | +2.331 |
lore | +2.154 |
iliate | +2.127 |
rys | +2.079 |
yg | +2.069 |
Neg logit contributions | |
ileaks | -1.895 |
burgh | -1.885 |
ocrates | -1.772 |
roid | -1.753 |
paren | -1.741 |
Token | achieve |
Token ID | 4620 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ileaks | +0.987 |
burgh | +0.966 |
ocrates | +0.916 |
roid | +0.912 |
paren | +0.907 |
Neg logit contributions | |
LY | -1.039 |
lore | -0.964 |
iliate | -0.950 |
rys | -0.933 |
yg | -0.925 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ileaks | +0.800 |
burgh | +0.783 |
ocrates | +0.740 |
roid | +0.733 |
paren | +0.733 |
Neg logit contributions | |
LY | -0.973 |
lore | -0.904 |
iliate | -0.896 |
rys | -0.878 |
yg | -0.872 |
Token | target |
Token ID | 2496 |
Feature activation | -9.35e+00 |
Pos logit contributions | |
ileaks | +0.670 |
burgh | +0.658 |
ocrates | +0.616 |
roid | +0.613 |
paren | +0.610 |
Neg logit contributions | |
LY | -0.884 |
lore | -0.824 |
iliate | -0.817 |
rys | -0.801 |
yg | -0.796 |
Token | eyed |
Token ID | 45320 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
ileaks | +5.360 |
burgh | +5.210 |
roid | +4.972 |
paren | +4.813 |
ocrates | +4.765 |
Neg logit contributions | |
LY | -7.134 |
iliate | -6.825 |
lore | -6.674 |
rys | -6.616 |
yg | -6.519 |
Token | at |
Token ID | 379 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
ileaks | +0.530 |
burgh | +0.521 |
ocrates | +0.495 |
roid | +0.494 |
paren | +0.492 |
Neg logit contributions | |
LY | -0.506 |
lore | -0.466 |
iliate | -0.460 |
rys | -0.448 |
yg | -0.445 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
LY | +1.549 |
lore | +1.432 |
iliate | +1.409 |
yg | +1.386 |
rys | +1.381 |
Neg logit contributions | |
ileaks | -1.333 |
burgh | -1.312 |
ocrates | -1.238 |
roid | -1.235 |
paren | -1.228 |
Token | Paris |
Token ID | 6342 |
Feature activation | -7.58e+00 |
Pos logit contributions | |
ileaks | +0.158 |
burgh | +0.155 |
ocrates | +0.146 |
roid | +0.145 |
paren | +0.144 |
Neg logit contributions | |
LY | -0.215 |
lore | -0.200 |
iliate | -0.198 |
rys | -0.194 |
yg | -0.193 |
Token | meeting |
Token ID | 3249 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
burgh | +4.869 |
ileaks | +4.845 |
roid | +4.434 |
paren | +4.373 |
nature | +4.356 |
Neg logit contributions | |
LY | -5.388 |
lore | -5.107 |
rys | -5.092 |
iliate | -5.064 |
yg | -4.955 |
Token | ho |
Token ID | 8169 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
LY | +0.773 |
lore | +0.713 |
iliate | +0.705 |
rys | +0.689 |
yg | +0.686 |
Neg logit contributions | |
ileaks | -0.733 |
burgh | -0.721 |
ocrates | -0.683 |
roid | -0.680 |
paren | -0.677 |
Token | � |
Token ID | 134 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
LY | +2.669 |
lore | +2.509 |
iliate | +2.468 |
yg | +2.442 |
rys | +2.430 |
Neg logit contributions | |
ileaks | -1.621 |
burgh | -1.572 |
paren | -1.452 |
ocrates | -1.450 |
roid | -1.449 |
Token | � |
Token ID | 119 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
LY | +0.243 |
lore | +0.218 |
iliate | +0.214 |
rys | +0.208 |
yg | +0.207 |
Neg logit contributions | |
ileaks | -0.384 |
burgh | -0.379 |
ocrates | -0.363 |
roid | -0.362 |
paren | -0.361 |
Token | op |
Token ID | 404 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
ileaks | +1.065 |
burgh | +1.053 |
ocrates | +0.992 |
roid | +0.986 |
paren | +0.974 |
Neg logit contributions | |
LY | -1.579 |
lore | -1.456 |
iliate | -1.451 |
rys | -1.423 |
yg | -1.411 |
Token | ā |
Token ID | 10235 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ileaks | +1.647 |
burgh | +1.640 |
ocrates | +1.549 |
roid | +1.517 |
paren | +1.503 |
Neg logit contributions | |
LY | -3.535 |
lore | -3.299 |
iliate | -3.277 |
rys | -3.237 |
yg | -3.209 |
Token | p |
Token ID | 79 |
Feature activation | -7.98e+00 |
Pos logit contributions | |
ileaks | +0.859 |
burgh | +0.852 |
ocrates | +0.805 |
paren | +0.804 |
roid | +0.802 |
Neg logit contributions | |
LY | -0.984 |
lore | -0.906 |
iliate | -0.900 |
rys | -0.878 |
yg | -0.871 |
Token | ā |
Token ID | 10235 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
burgh | +2.894 |
ileaks | +2.833 |
ocrates | +2.751 |
roid | +2.680 |
paren | +2.636 |
Neg logit contributions | |
LY | -7.970 |
lore | -7.347 |
iliate | -7.346 |
rys | -7.295 |
yg | -7.286 |
Token | a |
Token ID | 257 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
LY | +2.080 |
lore | +1.924 |
iliate | +1.895 |
rys | +1.853 |
yg | +1.852 |
Neg logit contributions | |
ileaks | -1.977 |
burgh | -1.927 |
ocrates | -1.822 |
roid | -1.812 |
paren | -1.804 |
Token | ku |
Token ID | 23063 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
ileaks | +1.467 |
burgh | +1.462 |
ocrates | +1.385 |
roid | +1.381 |
paren | +1.372 |
Neg logit contributions | |
LY | -1.652 |
lore | -1.522 |
iliate | -1.518 |
rys | -1.474 |
yg | -1.459 |
Token | i |
Token ID | 1312 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
LY | +0.706 |
lore | +0.653 |
iliate | +0.645 |
rys | +0.631 |
yg | +0.629 |
Neg logit contributions | |
ileaks | -0.638 |
burgh | -0.627 |
ocrates | -0.592 |
roid | -0.590 |
paren | -0.588 |
Token | n |
Token ID | 299 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
ileaks | +0.667 |
burgh | +0.663 |
ocrates | +0.628 |
roid | +0.623 |
paren | +0.621 |
Neg logit contributions | |
LY | -0.736 |
lore | -0.678 |
iliate | -0.675 |
rys | -0.658 |
yg | -0.654 |