Token |
|
Token ID | 198 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
ploma | +0.983 |
sucker | +0.969 |
rongh | +0.942 |
ォ | +0.932 |
EVER | +0.918 |
Neg logit contributions | |
ging | -1.435 |
chin | -1.358 |
keeping | -1.320 |
�� | -1.292 |
gers | -1.270 |
Token |
|
Token ID | 198 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
ging | +1.885 |
chin | +1.737 |
keeping | +1.736 |
gers | +1.655 |
keepers | +1.598 |
Neg logit contributions | |
sucker | -1.630 |
ploma | -1.628 |
rongh | -1.601 |
ォ | -1.580 |
sqor | -1.522 |
Token | Facebook |
Token ID | 12025 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ging | +1.891 |
chin | +1.714 |
keeping | +1.689 |
gers | +1.581 |
nutrition | +1.568 |
Neg logit contributions | |
ploma | -2.614 |
sucker | -2.600 |
ォ | -2.562 |
rongh | -2.552 |
babe | -2.516 |
Token |
|
Token ID | 198 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
ploma | +0.167 |
sucker | +0.165 |
rongh | +0.162 |
ォ | +0.160 |
babe | +0.155 |
Neg logit contributions | |
ging | -0.219 |
chin | -0.204 |
keeping | -0.202 |
gers | -0.192 |
�� | -0.189 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ging | +0.632 |
chin | +0.587 |
keeping | +0.580 |
gers | +0.556 |
keepers | +0.537 |
Neg logit contributions | |
ploma | -0.500 |
sucker | -0.497 |
rongh | -0.486 |
ォ | -0.481 |
babe | -0.462 |
Token | St |
Token ID | 1273 |
Feature activation | +1.69e+01 |
Pos logit contributions | |
ging | +1.483 |
chin | +1.388 |
keeping | +1.375 |
gers | +1.304 |
nutrition | +1.297 |
Neg logit contributions | |
ploma | -0.906 |
sucker | -0.890 |
ォ | -0.871 |
rongh | -0.857 |
babe | -0.829 |
Token | umble |
Token ID | 10344 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
rongh | +3.174 |
date | +2.613 |
ickers | +2.329 |
nee | +1.997 |
EVER | +1.899 |
Neg logit contributions | |
�� | -19.967 |
�� | -19.802 |
ging | -18.909 |
chin | -18.760 |
keeping | -18.691 |
Token | Upon |
Token ID | 23792 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
ploma | +1.349 |
sucker | +1.302 |
EVER | +1.250 |
rongh | +1.244 |
babe | +1.241 |
Neg logit contributions | |
ging | -2.721 |
chin | -2.580 |
�� | -2.517 |
keeping | -2.499 |
gers | -2.440 |
Token | What |
Token ID | 1867 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
ploma | +1.386 |
sucker | +1.367 |
EVER | +1.306 |
babe | +1.279 |
Turks | +1.276 |
Neg logit contributions | |
ging | -2.692 |
chin | -2.602 |
�� | -2.505 |
keeping | -2.496 |
gers | -2.411 |
Token | are |
Token ID | 389 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ploma | +2.094 |
sucker | +2.059 |
EVER | +2.028 |
sth | +2.018 |
babe | +2.018 |
Neg logit contributions | |
ging | -2.842 |
chin | -2.678 |
keeping | -2.618 |
�� | -2.598 |
gers | -2.526 |
Token | these |
Token ID | 777 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
ploma | +1.257 |
sucker | +1.244 |
rongh | +1.214 |
ォ | +1.210 |
sth | +1.182 |
Neg logit contributions | |
ging | -1.445 |
chin | -1.356 |
keeping | -1.308 |
�� | -1.272 |
gers | -1.252 |
Token |
|
Token ID | 198 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
ploma | +1.109 |
sucker | +1.094 |
rongh | +1.064 |
ォ | +1.052 |
EVER | +1.035 |
Neg logit contributions | |
ging | -1.611 |
chin | -1.523 |
keeping | -1.480 |
�� | -1.447 |
gers | -1.425 |
Token |
|
Token ID | 198 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
ging | +1.765 |
chin | +1.628 |
keeping | +1.626 |
gers | +1.549 |
keepers | +1.499 |
Neg logit contributions | |
sucker | -1.506 |
ploma | -1.504 |
rongh | -1.478 |
ォ | -1.459 |
sqor | -1.403 |
Token | Facebook |
Token ID | 12025 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
ging | +1.912 |
chin | +1.727 |
keeping | +1.718 |
gers | +1.601 |
nutrition | +1.583 |
Neg logit contributions | |
ploma | -2.650 |
sucker | -2.630 |
rongh | -2.590 |
ォ | -2.589 |
babe | -2.545 |
Token |
|
Token ID | 198 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
ploma | +0.303 |
sucker | +0.299 |
rongh | +0.294 |
ォ | +0.291 |
babe | +0.281 |
Neg logit contributions | |
ging | -0.403 |
chin | -0.376 |
keeping | -0.371 |
gers | -0.354 |
�� | -0.349 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ging | +0.401 |
chin | +0.373 |
keeping | +0.368 |
gers | +0.353 |
keepers | +0.341 |
Neg logit contributions | |
ploma | -0.311 |
sucker | -0.309 |
rongh | -0.303 |
ォ | -0.299 |
babe | -0.288 |
Token | St |
Token ID | 1273 |
Feature activation | +1.63e+01 |
Pos logit contributions | |
ging | +1.252 |
chin | +1.171 |
keeping | +1.163 |
gers | +1.103 |
keepers | +1.095 |
Neg logit contributions | |
ploma | -0.744 |
sucker | -0.728 |
ォ | -0.713 |
rongh | -0.700 |
Clause | -0.680 |
Token | umble |
Token ID | 10344 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
rongh | +3.440 |
date | +2.813 |
ickers | +2.447 |
nee | +2.241 |
ploma | +2.184 |
Neg logit contributions | |
�� | -19.011 |
�� | -18.830 |
ging | -18.131 |
chin | -18.069 |
keeping | -17.835 |
Token | Upon |
Token ID | 23792 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ploma | +1.487 |
sucker | +1.429 |
EVER | +1.385 |
babe | +1.372 |
rongh | +1.358 |
Neg logit contributions | |
ging | -3.126 |
chin | -2.961 |
�� | -2.907 |
keeping | -2.868 |
gers | -2.801 |
Token | What |
Token ID | 1867 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
ploma | +1.413 |
sucker | +1.402 |
EVER | +1.350 |
Turks | +1.314 |
babe | +1.312 |
Neg logit contributions | |
ging | -2.885 |
chin | -2.800 |
�� | -2.684 |
keeping | -2.675 |
nutrition | -2.582 |
Token | are |
Token ID | 389 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ploma | +1.917 |
sucker | +1.882 |
babe | +1.858 |
EVER | +1.855 |
date | +1.852 |
Neg logit contributions | |
ging | -2.674 |
chin | -2.523 |
keeping | -2.474 |
�� | -2.455 |
gers | -2.384 |
Token | these |
Token ID | 777 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
ploma | +1.415 |
sucker | +1.401 |
rongh | +1.366 |
ォ | +1.355 |
babe | +1.327 |
Neg logit contributions | |
ging | -1.709 |
chin | -1.604 |
keeping | -1.557 |
�� | -1.512 |
gers | -1.493 |
Token | - |
Token ID | 532 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ging | +1.231 |
chin | +1.090 |
keeping | +1.028 |
gers | +0.930 |
gin | +0.862 |
Neg logit contributions | |
sucker | -3.462 |
ploma | -3.424 |
ォ | -3.380 |
rongh | -3.380 |
EVER | -3.353 |
Token | signed |
Token ID | 4488 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ploma | +1.592 |
sucker | +1.568 |
rongh | +1.539 |
ォ | +1.515 |
sth | +1.493 |
Neg logit contributions | |
ging | -1.912 |
chin | -1.800 |
keeping | -1.741 |
�� | -1.734 |
gers | -1.669 |
Token | the |
Token ID | 262 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
ploma | +1.276 |
sucker | +1.275 |
rongh | +1.215 |
ォ | +1.196 |
date | +1.191 |
Neg logit contributions | |
ging | -1.978 |
chin | -1.889 |
keeping | -1.822 |
�� | -1.816 |
nutrition | -1.756 |
Token | algorithm |
Token ID | 11862 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
sucker | +2.943 |
ploma | +2.846 |
date | +2.807 |
EVER | +2.729 |
Turks | +2.721 |
Neg logit contributions | |
ging | -4.160 |
chin | -3.989 |
�� | -3.924 |
keeping | -3.814 |
�� | -3.755 |
Token | and |
Token ID | 290 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
ploma | +0.733 |
sucker | +0.728 |
rongh | +0.704 |
ォ | +0.696 |
EVER | +0.685 |
Neg logit contributions | |
ging | -1.088 |
chin | -1.030 |
keeping | -1.000 |
�� | -0.981 |
gers | -0.964 |
Token | North |
Token ID | 2258 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
sucker | +1.647 |
ploma | +1.633 |
rongh | +1.562 |
ォ | +1.555 |
date | +1.550 |
Neg logit contributions | |
ging | -2.242 |
chin | -2.123 |
�� | -2.056 |
keeping | -2.046 |
nutrition | -1.978 |
Token | rop |
Token ID | 1773 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
ploma | +4.608 |
rongh | +4.373 |
sucker | +4.288 |
sth | +4.281 |
Turks | +4.193 |
Neg logit contributions | |
�� | -15.412 |
ging | -14.727 |
�� | -14.424 |
nutrition | -14.241 |
chin | -14.125 |
Token | Gr |
Token ID | 1902 |
Feature activation | +6.86e+00 |
Pos logit contributions | |
sucker | +2.314 |
ploma | +2.270 |
EVER | +2.164 |
date | +2.151 |
babe | +2.150 |
Neg logit contributions | |
ging | -2.978 |
chin | -2.829 |
�� | -2.763 |
keeping | -2.739 |
nutrition | -2.649 |
Token | um |
Token ID | 388 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ploma | +3.906 |
sucker | +3.767 |
rongh | +3.705 |
sth | +3.652 |
EVER | +3.631 |
Neg logit contributions | |
ging | -5.616 |
�� | -5.601 |
chin | -5.352 |
�� | -5.320 |
keeping | -5.245 |
Token | man |
Token ID | 805 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
ging | +0.758 |
chin | +0.699 |
keeping | +0.674 |
gers | +0.651 |
nutrition | +0.615 |
Neg logit contributions | |
ploma | -0.900 |
sucker | -0.887 |
ォ | -0.879 |
rongh | -0.874 |
babe | -0.851 |
Token | , |
Token ID | 11 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
sucker | +2.140 |
ploma | +2.113 |
EVER | +2.009 |
rongh | +2.006 |
babe | +2.005 |
Neg logit contributions | |
ging | -2.935 |
chin | -2.779 |
�� | -2.718 |
keeping | -2.692 |
nutrition | -2.605 |
Token | De |
Token ID | 1024 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
ploma | +0.902 |
sucker | +0.895 |
ォ | +0.870 |
rongh | +0.867 |
EVER | +0.860 |
Neg logit contributions | |
ging | -1.097 |
chin | -1.027 |
keeping | -0.996 |
�� | -0.984 |
gers | -0.957 |
Token | vers |
Token ID | 690 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
ging | +2.361 |
chin | +2.207 |
keeping | +2.127 |
gers | +2.068 |
�� | +2.023 |
Neg logit contributions | |
ploma | -2.025 |
sucker | -2.004 |
rongh | -1.961 |
ォ | -1.954 |
EVER | -1.904 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ploma | +0.498 |
sucker | +0.495 |
rongh | +0.477 |
ォ | +0.473 |
EVER | +0.464 |
Neg logit contributions | |
ging | -0.870 |
chin | -0.821 |
keeping | -0.803 |
�� | -0.791 |
gers | -0.777 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ploma | +0.857 |
sucker | +0.846 |
ォ | +0.823 |
rongh | +0.823 |
EVER | +0.807 |
Neg logit contributions | |
ging | -1.275 |
chin | -1.198 |
keeping | -1.163 |
�� | -1.152 |
gers | -1.128 |
Token |
|
Token ID | 198 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
ploma | +0.878 |
sucker | +0.867 |
rongh | +0.842 |
ォ | +0.835 |
EVER | +0.820 |
Neg logit contributions | |
ging | -1.280 |
chin | -1.209 |
keeping | -1.174 |
�� | -1.155 |
gers | -1.131 |
Token | Sl |
Token ID | 11122 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
ging | +0.073 |
chin | +0.068 |
keeping | +0.066 |
�� | +0.064 |
gers | +0.064 |
Neg logit contributions | |
ploma | -0.061 |
sucker | -0.060 |
rongh | -0.058 |
ォ | -0.058 |
babe | -0.057 |
Token | ov |
Token ID | 709 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
ploma | +4.965 |
rongh | +4.708 |
sucker | +4.319 |
ovan | +4.246 |
Turks | +4.216 |
Neg logit contributions | |
�� | -15.458 |
�� | -15.352 |
ging | -14.709 |
keeping | -13.928 |
chin | -13.733 |
Token | akia |
Token ID | 21897 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
ploma | +1.101 |
sucker | +1.079 |
rongh | +1.031 |
ォ | +0.996 |
EVER | +0.980 |
Neg logit contributions | |
ging | -3.399 |
chin | -3.244 |
keeping | -3.179 |
�� | -3.161 |
gers | -3.083 |
Token | : |
Token ID | 25 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ploma | +2.387 |
sucker | +2.372 |
ォ | +2.294 |
rongh | +2.293 |
Turks | +2.272 |
Neg logit contributions | |
ging | -4.292 |
chin | -4.051 |
�� | -3.994 |
keeping | -3.905 |
gers | -3.826 |
Token | Gre |
Token ID | 11955 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
ploma | +0.694 |
sucker | +0.687 |
rongh | +0.667 |
ォ | +0.667 |
EVER | +0.657 |
Neg logit contributions | |
ging | -0.841 |
chin | -0.787 |
keeping | -0.763 |
�� | -0.752 |
gers | -0.734 |
Token | if |
Token ID | 361 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ploma | +1.895 |
sucker | +1.874 |
rongh | +1.834 |
EVER | +1.807 |
ォ | +1.796 |
Neg logit contributions | |
ging | -1.924 |
chin | -1.779 |
�� | -1.762 |
keeping | -1.759 |
�� | -1.669 |
Token | Parser |
Token ID | 46677 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
ploma | +0.545 |
sucker | +0.540 |
rongh | +0.529 |
ォ | +0.526 |
EVER | +0.518 |
Neg logit contributions | |
ging | -0.407 |
chin | -0.375 |
keeping | -0.361 |
�� | -0.349 |
gers | -0.341 |
Token | () |
Token ID | 3419 |
Feature activation | +9.23e+00 |
Pos logit contributions | |
ploma | +1.486 |
sucker | +1.464 |
rongh | +1.419 |
ォ | +1.413 |
EVER | +1.396 |
Neg logit contributions | |
ging | -2.141 |
chin | -2.023 |
keeping | -1.959 |
�� | -1.953 |
gers | -1.886 |
Token | ap |
Token ID | 2471 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
sucker | +4.417 |
date | +4.292 |
ploma | +4.197 |
babe | +4.043 |
EVER | +4.008 |
Neg logit contributions | |
�� | -8.465 |
ging | -8.439 |
chin | -8.201 |
keeping | -7.960 |
�� | -7.894 |
Token | . |
Token ID | 13 |
Feature activation | +9.12e+00 |
Pos logit contributions | |
ploma | +2.528 |
sucker | +2.487 |
EVER | +2.428 |
date | +2.424 |
sth | +2.401 |
Neg logit contributions | |
ging | -5.141 |
�� | -5.036 |
chin | -4.931 |
�� | -4.831 |
keeping | -4.751 |
Token | add |
Token ID | 2860 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
sth | +5.543 |
ploma | +5.471 |
sucker | +5.402 |
rongh | +5.386 |
date | +5.337 |
Neg logit contributions | |
�� | -7.085 |
�� | -6.605 |
ging | -6.519 |
chin | -6.306 |
keeping | -6.022 |
Token | _ |
Token ID | 62 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
sth | +3.493 |
ploma | +3.483 |
date | +3.459 |
nee | +3.349 |
EVER | +3.294 |
Neg logit contributions | |
�� | -11.344 |
�� | -10.587 |
ging | -10.424 |
chin | -10.237 |
keeping | -9.825 |
Token | argument |
Token ID | 49140 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
sth | +4.632 |
date | +4.535 |
nee | +4.519 |
sucker | +4.319 |
ploma | +4.157 |
Neg logit contributions | |
�� | -16.142 |
�� | -14.840 |
ging | -13.745 |
chin | -13.479 |
ograp | -13.374 |
Token | (" |
Token ID | 7203 |
Feature activation | +7.65e+00 |
Pos logit contributions | |
date | +5.985 |
EVER | +5.929 |
sth | +5.889 |
sucker | +5.843 |
ploma | +5.829 |
Neg logit contributions | |
�� | -10.269 |
ging | -10.145 |
chin | -9.770 |
�� | -9.671 |
nutrition | -9.215 |
Token | - |
Token ID | 12 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
sth | +3.756 |
ploma | +3.717 |
date | +3.609 |
sucker | +3.604 |
rongh | +3.567 |
Neg logit contributions | |
�� | -6.816 |
ging | -6.627 |
�� | -6.361 |
chin | -6.262 |
keeping | -6.038 |
Token | i |
Token ID | 72 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
sth | +5.168 |
nee | +5.064 |
ploma | +5.010 |
rongh | +4.991 |
date | +4.819 |
Neg logit contributions | |
�� | -11.266 |
�� | -10.972 |
ging | -10.533 |
chin | -9.969 |
keeping | -9.686 |
Token | ", |
Token ID | 1600 |
Feature activation | +9.35e+00 |
Pos logit contributions | |
ploma | +2.634 |
sucker | +2.575 |
rongh | +2.527 |
sth | +2.488 |
ォ | +2.475 |
Neg logit contributions | |
ging | -3.942 |
chin | -3.727 |
�� | -3.712 |
keeping | -3.625 |
�� | -3.530 |
Token | . |
Token ID | 13 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
ging | +0.662 |
chin | +0.625 |
keeping | +0.609 |
�� | +0.593 |
gers | +0.586 |
Neg logit contributions | |
ploma | -0.443 |
sucker | -0.438 |
rongh | -0.425 |
ォ | -0.421 |
babe | -0.412 |
Token | He |
Token ID | 679 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
ploma | +1.951 |
sucker | +1.911 |
EVER | +1.886 |
ォ | +1.867 |
Turks | +1.848 |
Neg logit contributions | |
ging | -2.866 |
chin | -2.712 |
�� | -2.631 |
keeping | -2.624 |
nutrition | -2.542 |
Token | complained |
Token ID | 13832 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
sucker | +1.599 |
ploma | +1.557 |
rongh | +1.510 |
EVER | +1.509 |
babe | +1.498 |
Neg logit contributions | |
ging | -1.869 |
chin | -1.750 |
keeping | -1.706 |
�� | -1.706 |
nutrition | -1.629 |
Token | to |
Token ID | 284 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
sucker | +2.113 |
ploma | +2.066 |
EVER | +1.986 |
rongh | +1.982 |
babe | +1.979 |
Neg logit contributions | |
ging | -3.396 |
chin | -3.262 |
keeping | -3.148 |
�� | -3.113 |
nutrition | -3.029 |
Token | Alfred |
Token ID | 22044 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
sucker | +1.869 |
ploma | +1.858 |
rongh | +1.769 |
date | +1.768 |
EVER | +1.754 |
Neg logit contributions | |
ging | -3.023 |
chin | -2.885 |
keeping | -2.790 |
�� | -2.765 |
nutrition | -2.680 |
Token | Kn |
Token ID | 6102 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
ploma | +0.458 |
sucker | +0.456 |
rongh | +0.441 |
ォ | +0.438 |
EVER | +0.430 |
Neg logit contributions | |
ging | -0.649 |
chin | -0.612 |
keeping | -0.596 |
�� | -0.581 |
gers | -0.573 |
Token | op |
Token ID | 404 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
ploma | +4.751 |
rongh | +4.635 |
nee | +4.437 |
sth | +4.402 |
date | +4.294 |
Neg logit contributions | |
�� | -14.612 |
ging | -14.372 |
�� | -14.183 |
keeping | -13.201 |
chin | -13.181 |
Token | f |
Token ID | 69 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
ploma | +1.454 |
sucker | +1.432 |
rongh | +1.394 |
ォ | +1.359 |
sth | +1.358 |
Neg logit contributions | |
ging | -2.562 |
chin | -2.420 |
�� | -2.360 |
keeping | -2.358 |
gers | -2.284 |
Token | , |
Token ID | 11 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
sucker | +1.331 |
ploma | +1.324 |
rongh | +1.279 |
EVER | +1.260 |
ォ | +1.258 |
Neg logit contributions | |
ging | -1.984 |
chin | -1.884 |
keeping | -1.818 |
�� | -1.787 |
gers | -1.752 |
Token | who |
Token ID | 508 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
sucker | +2.537 |
ploma | +2.495 |
date | +2.411 |
EVER | +2.399 |
babe | +2.386 |
Neg logit contributions | |
ging | -4.260 |
chin | -4.097 |
�� | -3.942 |
keeping | -3.933 |
gers | -3.813 |
Token | wrote |
Token ID | 2630 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
sucker | +0.891 |
ploma | +0.884 |
rongh | +0.852 |
ォ | +0.841 |
EVER | +0.841 |
Neg logit contributions | |
ging | -1.126 |
chin | -1.059 |
keeping | -1.027 |
�� | -1.014 |
gers | -0.985 |
Token | 10 |
Token ID | 940 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ging | +2.525 |
chin | +2.355 |
keeping | +2.296 |
gers | +2.148 |
keepers | +2.100 |
Neg logit contributions | |
sucker | -2.639 |
ploma | -2.620 |
rongh | -2.565 |
ォ | -2.546 |
babe | -2.458 |
Token | : |
Token ID | 25 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ploma | +0.827 |
sucker | +0.817 |
rongh | +0.792 |
ォ | +0.785 |
EVER | +0.768 |
Neg logit contributions | |
ging | -1.343 |
chin | -1.271 |
keeping | -1.237 |
�� | -1.213 |
gers | -1.194 |
Token | 47 |
Token ID | 2857 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
ploma | +1.189 |
sucker | +1.179 |
rongh | +1.147 |
ォ | +1.138 |
EVER | +1.123 |
Neg logit contributions | |
ging | -1.443 |
chin | -1.354 |
keeping | -1.311 |
�� | -1.294 |
gers | -1.259 |
Token | ] |
Token ID | 60 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
ging | +1.716 |
chin | +1.552 |
keeping | +1.526 |
gers | +1.444 |
keepers | +1.359 |
Neg logit contributions | |
sucker | -2.450 |
ploma | -2.441 |
rongh | -2.403 |
ォ | -2.375 |
babe | -2.306 |
Token | < |
Token ID | 1279 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
ging | +4.761 |
chin | +4.396 |
keeping | +4.232 |
�� | +4.120 |
gers | +4.075 |
Neg logit contributions | |
ploma | -5.843 |
sucker | -5.809 |
rongh | -5.771 |
ォ | -5.676 |
sth | -5.547 |
Token | ok |
Token ID | 482 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
ploma | +2.538 |
sucker | +2.503 |
rongh | +2.472 |
sth | +2.450 |
ォ | +2.426 |
Neg logit contributions | |
ging | -2.710 |
chin | -2.533 |
�� | -2.511 |
keeping | -2.487 |
�� | -2.388 |
Token | clock |
Token ID | 15750 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
sth | +8.226 |
ploma | +7.838 |
date | +7.717 |
sucker | +7.535 |
nee | +7.429 |
Neg logit contributions | |
ging | -9.859 |
�� | -9.391 |
�� | -9.288 |
keeping | -9.166 |
chin | -8.964 |
Token | zy |
Token ID | 7357 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
ploma | +2.387 |
sucker | +2.373 |
rongh | +2.326 |
ォ | +2.310 |
sth | +2.303 |
Neg logit contributions | |
ging | -0.898 |
chin | -0.785 |
keeping | -0.741 |
�� | -0.734 |
gers | -0.675 |
Token | > |
Token ID | 29 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
ploma | +2.386 |
sucker | +2.362 |
rongh | +2.314 |
ォ | +2.306 |
EVER | +2.302 |
Neg logit contributions | |
ging | -1.552 |
chin | -1.429 |
�� | -1.376 |
keeping | -1.362 |
�� | -1.287 |
Token | lol |
Token ID | 19462 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
sucker | +2.358 |
ploma | +2.321 |
babe | +2.247 |
EVER | +2.233 |
rongh | +2.196 |
Neg logit contributions | |
ging | -3.737 |
chin | -3.542 |
keeping | -3.462 |
�� | -3.435 |
gers | -3.341 |
Token | m |
Token ID | 285 |
Feature activation | +9.66e+00 |
Pos logit contributions | |
sucker | +2.238 |
ploma | +2.185 |
babe | +2.102 |
rongh | +2.086 |
EVER | +2.058 |
Neg logit contributions | |
ging | -4.459 |
chin | -4.259 |
keeping | -4.190 |
�� | -4.105 |
gers | -4.034 |
Token | over |
Token ID | 625 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
sucker | +4.543 |
ploma | +4.346 |
date | +4.312 |
EVER | +4.248 |
babe | +4.158 |
Neg logit contributions | |
ging | -6.950 |
�� | -6.850 |
chin | -6.783 |
�� | -6.556 |
nutrition | -6.529 |
Token | a |
Token ID | 257 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
sucker | +2.305 |
ploma | +2.304 |
rongh | +2.234 |
EVER | +2.176 |
date | +2.167 |
Neg logit contributions | |
ging | -3.310 |
chin | -3.151 |
�� | -3.053 |
keeping | -3.051 |
gers | -2.936 |
Token | million |
Token ID | 1510 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
sucker | +2.137 |
ploma | +2.026 |
date | +1.973 |
rongh | +1.911 |
babe | +1.910 |
Neg logit contributions | |
ging | -4.756 |
chin | -4.596 |
�� | -4.493 |
keeping | -4.465 |
nutrition | -4.376 |
Token | dollars |
Token ID | 5054 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
sucker | +1.071 |
ploma | +1.062 |
rongh | +0.987 |
ォ | +0.950 |
EVER | +0.940 |
Neg logit contributions | |
ging | -3.984 |
chin | -3.835 |
keeping | -3.736 |
�� | -3.729 |
nutrition | -3.642 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ging | +2.738 |
chin | +2.551 |
keeping | +2.518 |
gers | +2.395 |
�� | +2.374 |
Neg logit contributions | |
ploma | -1.954 |
sucker | -1.915 |
ォ | -1.915 |
rongh | -1.884 |
babe | -1.811 |
Token | Kn |
Token ID | 6102 |
Feature activation | +1.40e+01 |
Pos logit contributions | |
ploma | +1.413 |
sucker | +1.393 |
ォ | +1.353 |
rongh | +1.349 |
EVER | +1.348 |
Neg logit contributions | |
ging | -1.890 |
chin | -1.779 |
keeping | -1.726 |
�� | -1.719 |
gers | -1.659 |
Token | op |
Token ID | 404 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ploma | +4.698 |
rongh | +4.543 |
nee | +4.142 |
sth | +4.138 |
date | +3.947 |
Neg logit contributions | |
ging | -13.775 |
�� | -13.360 |
�� | -13.317 |
keeping | -12.765 |
gers | -12.648 |
Token | f |
Token ID | 69 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ploma | +1.764 |
sucker | +1.739 |
rongh | +1.689 |
sth | +1.656 |
ォ | +1.647 |
Neg logit contributions | |
ging | -3.172 |
chin | -2.999 |
�� | -2.955 |
keeping | -2.918 |
�� | -2.842 |
Token | was |
Token ID | 373 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ploma | +0.197 |
sucker | +0.195 |
rongh | +0.190 |
ォ | +0.188 |
babe | +0.185 |
Neg logit contributions | |
ging | -0.250 |
chin | -0.235 |
keeping | -0.228 |
�� | -0.222 |
gers | -0.219 |
Token | panicked |
Token ID | 38225 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
sucker | +0.577 |
ploma | +0.575 |
rongh | +0.550 |
ォ | +0.541 |
EVER | +0.540 |
Neg logit contributions | |
ging | -0.875 |
chin | -0.828 |
keeping | -0.804 |
�� | -0.794 |
gers | -0.773 |
Token | that |
Token ID | 326 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
ging | +0.810 |
chin | +0.760 |
keeping | +0.743 |
�� | +0.716 |
gers | +0.715 |
Neg logit contributions | |
ploma | -0.583 |
sucker | -0.570 |
rongh | -0.560 |
ォ | -0.557 |
sth | -0.537 |
Token | parse |
Token ID | 29572 |
Feature activation | +9.10e+00 |
Pos logit contributions | |
ploma | +2.056 |
sucker | +2.025 |
rongh | +1.978 |
sth | +1.956 |
ォ | +1.955 |
Neg logit contributions | |
ging | -2.409 |
chin | -2.283 |
�� | -2.224 |
keeping | -2.205 |
�� | -2.120 |
Token | import |
Token ID | 1330 |
Feature activation | +7.29e+00 |
Pos logit contributions | |
date | +3.456 |
sucker | +3.361 |
ploma | +3.269 |
EVER | +3.162 |
REG | +3.158 |
Neg logit contributions | |
�� | -9.175 |
ging | -9.153 |
chin | -8.880 |
�� | -8.739 |
keeping | -8.526 |
Token | im |
Token ID | 545 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
sucker | +2.423 |
date | +2.303 |
EVER | +2.221 |
ploma | +2.201 |
babe | +2.188 |
Neg logit contributions | |
ging | -7.809 |
�� | -7.764 |
chin | -7.582 |
keeping | -7.457 |
�� | -7.398 |
Token | utils |
Token ID | 26791 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
sucker | +2.556 |
ploma | +2.552 |
sth | +2.438 |
ォ | +2.436 |
EVER | +2.409 |
Neg logit contributions | |
ging | -5.943 |
�� | -5.928 |
chin | -5.738 |
�� | -5.619 |
keeping | -5.508 |
Token | import |
Token ID | 1330 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
sucker | +3.119 |
date | +3.111 |
ploma | +3.017 |
EVER | +2.938 |
REG | +2.919 |
Neg logit contributions | |
ging | -8.071 |
�� | -7.910 |
chin | -7.807 |
�� | -7.568 |
keeping | -7.538 |
Token | c |
Token ID | 269 |
Feature activation | +1.40e+01 |
Pos logit contributions | |
sucker | +1.497 |
ploma | +1.405 |
date | +1.383 |
babe | +1.335 |
EVER | +1.300 |
Neg logit contributions | |
ging | -5.509 |
chin | -5.333 |
�� | -5.272 |
keeping | -5.266 |
nutrition | -5.112 |
Token | v |
Token ID | 85 |
Feature activation | +9.46e+00 |
Pos logit contributions | |
sth | +5.417 |
date | +5.160 |
sucker | +5.102 |
rongh | +5.040 |
ploma | +4.903 |
Neg logit contributions | |
�� | -13.834 |
�� | -13.222 |
ging | -12.083 |
chin | -11.358 |
keeping | -11.353 |
Token | 2 |
Token ID | 17 |
Feature activation | +9.94e+00 |
Pos logit contributions | |
ploma | +2.372 |
date | +2.337 |
sucker | +2.243 |
sth | +2.222 |
EVER | +2.202 |
Neg logit contributions | |
�� | -10.702 |
�� | -10.168 |
ging | -10.077 |
chin | -9.937 |
keeping | -9.536 |
Token | # |
Token ID | 1303 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
sucker | +3.348 |
date | +3.251 |
ploma | +3.066 |
babe | +2.908 |
REG | +2.896 |
Neg logit contributions | |
ging | -10.209 |
chin | -10.059 |
�� | -9.842 |
keeping | -9.584 |
nutrition | -9.509 |
Token | construct |
Token ID | 5678 |
Feature activation | +7.56e+00 |
Pos logit contributions | |
ploma | +0.154 |
sucker | +0.152 |
rongh | +0.147 |
ォ | +0.146 |
babe | +0.142 |
Neg logit contributions | |
ging | -0.264 |
chin | -0.250 |
keeping | -0.244 |
�� | -0.239 |
gers | -0.235 |
Token | the |
Token ID | 262 |
Feature activation | +9.90e+00 |
Pos logit contributions | |
sucker | +3.596 |
date | +3.561 |
ploma | +3.550 |
EVER | +3.383 |
sth | +3.381 |
Neg logit contributions | |
ging | -6.867 |
�� | -6.800 |
chin | -6.668 |
�� | -6.432 |
keeping | -6.363 |
Token | ' |
Token ID | 705 |
Feature activation | +7.69e+00 |
Pos logit contributions | |
sucker | +3.174 |
ploma | +3.047 |
EVER | +3.016 |
babe | +2.990 |
rongh | +2.989 |
Neg logit contributions | |
ging | -4.491 |
chin | -4.199 |
�� | -4.186 |
keeping | -4.110 |
gers | -4.011 |
Token | a |
Token ID | 64 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
sucker | +4.787 |
ploma | +4.581 |
EVER | +4.567 |
date | +4.556 |
rongh | +4.542 |
Neg logit contributions | |
ging | -5.928 |
�� | -5.496 |
chin | -5.485 |
keeping | -5.390 |
gers | -5.254 |
Token | > |
Token ID | 1875 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
sucker | +2.607 |
ploma | +2.532 |
babe | +2.475 |
date | +2.453 |
Clause | +2.428 |
Neg logit contributions | |
ging | -4.250 |
chin | -3.975 |
�� | -3.922 |
keeping | -3.910 |
gers | -3.773 |
Token | ( |
Token ID | 357 |
Feature activation | +8.68e+00 |
Pos logit contributions | |
sucker | +1.482 |
ploma | +1.449 |
rongh | +1.386 |
ォ | +1.379 |
EVER | +1.367 |
Neg logit contributions | |
ging | -2.888 |
chin | -2.748 |
keeping | -2.666 |
�� | -2.643 |
gers | -2.594 |
Token | & |
Token ID | 1222 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
sucker | +3.960 |
date | +3.645 |
babe | +3.595 |
EVER | +3.471 |
ploma | +3.456 |
Neg logit contributions | |
ging | -8.171 |
�� | -7.866 |
chin | -7.751 |
keeping | -7.572 |
�� | -7.476 |
Token | self |
Token ID | 2116 |
Feature activation | +1.40e+01 |
Pos logit contributions | |
sucker | +2.327 |
ploma | +2.231 |
rongh | +2.204 |
ォ | +2.145 |
babe | +2.143 |
Neg logit contributions | |
ging | -4.410 |
chin | -4.146 |
�� | -4.118 |
keeping | -4.110 |
gers | -3.990 |
Token | , |
Token ID | 837 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
sucker | +5.532 |
sth | +4.937 |
date | +4.931 |
babe | +4.910 |
EVER | +4.905 |
Neg logit contributions | |
�� | -12.787 |
ging | -12.574 |
chin | -12.558 |
�� | -12.045 |
keeping | -11.923 |
Token | ord |
Token ID | 2760 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
sucker | +4.693 |
date | +4.417 |
babe | +4.327 |
EVER | +4.214 |
ploma | +4.157 |
Neg logit contributions | |
ging | -7.766 |
�� | -7.490 |
chin | -7.315 |
keeping | -7.082 |
�� | -7.029 |
Token | : |
Token ID | 1058 |
Feature activation | +7.81e+00 |
Pos logit contributions | |
sucker | +1.979 |
ploma | +1.966 |
rongh | +1.912 |
babe | +1.882 |
ォ | +1.859 |
Neg logit contributions | |
ging | -3.316 |
chin | -3.193 |
�� | -3.133 |
keeping | -3.107 |
�� | -2.999 |
Token | Order |
Token ID | 8284 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
sucker | +3.900 |
ploma | +3.730 |
EVER | +3.729 |
babe | +3.704 |
date | +3.699 |
Neg logit contributions | |
ging | -7.090 |
chin | -6.688 |
�� | -6.651 |
keeping | -6.544 |
gers | -6.460 |
Token | ing |
Token ID | 278 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
ploma | +0.586 |
sucker | +0.581 |
rongh | +0.567 |
ォ | +0.559 |
babe | +0.553 |
Neg logit contributions | |
ging | -0.628 |
chin | -0.589 |
keeping | -0.569 |
�� | -0.562 |
gers | -0.550 |
Token | or |
Token ID | 393 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ploma | +0.233 |
sucker | +0.232 |
rongh | +0.223 |
ォ | +0.221 |
EVER | +0.218 |
Neg logit contributions | |
ging | -0.359 |
chin | -0.340 |
keeping | -0.330 |
�� | -0.324 |
gers | -0.318 |
Token | called |
Token ID | 1444 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ging | +2.218 |
chin | +2.070 |
keeping | +2.016 |
gers | +1.951 |
�� | +1.918 |
Neg logit contributions | |
ploma | -1.751 |
rongh | -1.703 |
sucker | -1.702 |
ォ | -1.687 |
sth | -1.624 |
Token | female |
Token ID | 4048 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ging | +1.002 |
chin | +0.942 |
keeping | +0.917 |
�� | +0.888 |
gers | +0.882 |
Neg logit contributions | |
ploma | -0.743 |
sucker | -0.732 |
rongh | -0.717 |
ォ | -0.711 |
EVER | -0.691 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -8.67e+00 |
Pos logit contributions | |
ging | +0.108 |
chin | +0.101 |
keeping | +0.099 |
�� | +0.096 |
gers | +0.095 |
Neg logit contributions | |
ploma | -0.081 |
sucker | -0.081 |
rongh | -0.078 |
ォ | -0.077 |
babe | -0.076 |
Token | supporters |
Token ID | 5941 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ging | +6.776 |
chin | +6.335 |
keeping | +6.120 |
gers | +6.012 |
keepers | +5.804 |
Neg logit contributions | |
ploma | -5.495 |
ォ | -5.353 |
rongh | -5.295 |
sqor | -5.151 |
sucker | -5.125 |
Token | sl |
Token ID | 1017 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
sucker | +1.244 |
ploma | +1.212 |
babe | +1.171 |
EVER | +1.161 |
rongh | +1.156 |
Neg logit contributions | |
ging | -1.966 |
chin | -1.858 |
keeping | -1.809 |
�� | -1.805 |
nutrition | -1.741 |
Token | uts |
Token ID | 5500 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
rongh | +5.587 |
ploma | +5.027 |
sucker | +5.017 |
onest | +4.927 |
ickers | +4.919 |
Neg logit contributions | |
�� | -13.193 |
�� | -12.769 |
ging | -12.624 |
keeping | -12.384 |
chin | -11.935 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ging | +0.246 |
chin | +0.232 |
keeping | +0.225 |
�� | +0.219 |
gers | +0.217 |
Neg logit contributions | |
ploma | -0.179 |
sucker | -0.177 |
rongh | -0.172 |
ォ | -0.171 |
babe | -0.167 |
Token | wh |
Token ID | 348 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
ging | +1.069 |
chin | +1.012 |
keeping | +0.986 |
�� | +0.953 |
gers | +0.953 |
Neg logit contributions | |
ploma | -0.658 |
sucker | -0.642 |
rongh | -0.633 |
ォ | -0.624 |
EVER | -0.604 |
Token | ores |
Token ID | 2850 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
rongh | +3.113 |
ploma | +2.889 |
sucker | +2.839 |
ォ | +2.729 |
sth | +2.688 |
Neg logit contributions | |
ging | -8.693 |
�� | -8.624 |
keeping | -8.427 |
�� | -8.328 |
chin | -8.277 |
Token | ? |
Token ID | 30 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
sucker | +1.171 |
ploma | +1.163 |
rongh | +1.118 |
ォ | +1.110 |
babe | +1.107 |
Neg logit contributions | |
ging | -1.667 |
chin | -1.580 |
keeping | -1.531 |
�� | -1.511 |
gers | -1.468 |
Token | d |
Token ID | 67 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ploma | +1.521 |
sucker | +1.491 |
rongh | +1.445 |
ォ | +1.427 |
sth | +1.416 |
Neg logit contributions | |
ging | -2.619 |
chin | -2.459 |
�� | -2.426 |
keeping | -2.419 |
gers | -2.344 |
Token | pa |
Token ID | 8957 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
ploma | +1.080 |
sucker | +1.056 |
rongh | +1.030 |
ォ | +1.015 |
sth | +0.998 |
Neg logit contributions | |
ging | -1.772 |
chin | -1.677 |
keeping | -1.650 |
�� | -1.626 |
gers | -1.581 |
Token | , |
Token ID | 11 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
sucker | +2.831 |
ploma | +2.808 |
sth | +2.733 |
Syd | +2.728 |
date | +2.721 |
Neg logit contributions | |
ging | -6.150 |
chin | -5.824 |
�� | -5.774 |
keeping | -5.719 |
gers | -5.578 |
Token | br |
Token ID | 865 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
ploma | +1.543 |
sucker | +1.534 |
rongh | +1.481 |
ォ | +1.463 |
babe | +1.458 |
Neg logit contributions | |
ging | -2.044 |
chin | -1.916 |
keeping | -1.879 |
�� | -1.862 |
gers | -1.800 |
Token | , |
Token ID | 11 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
sucker | +5.892 |
date | +5.626 |
sth | +5.586 |
rongh | +5.553 |
Turks | +5.502 |
Neg logit contributions | |
�� | -8.193 |
ging | -8.146 |
keeping | -7.967 |
chin | -7.708 |
�� | -7.616 |
Token | ok |
Token ID | 12876 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
sucker | +1.698 |
ploma | +1.697 |
rongh | +1.620 |
babe | +1.605 |
date | +1.599 |
Neg logit contributions | |
ging | -2.869 |
chin | -2.713 |
keeping | -2.660 |
�� | -2.659 |
�� | -2.578 |
Token | to |
Token ID | 1462 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
sth | +8.001 |
ploma | +7.906 |
sucker | +7.693 |
date | +7.688 |
rongh | +7.675 |
Neg logit contributions | |
ging | -9.799 |
�� | -9.449 |
�� | -9.349 |
chin | -9.142 |
keeping | -9.023 |
Token | ber |
Token ID | 527 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
ploma | +1.604 |
sucker | +1.594 |
rongh | +1.570 |
ォ | +1.547 |
date | +1.538 |
Neg logit contributions | |
ging | -1.085 |
chin | -0.995 |
keeping | -0.967 |
�� | -0.938 |
gers | -0.889 |
Token | fest |
Token ID | 23411 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
ploma | +2.148 |
sucker | +2.130 |
rongh | +2.075 |
ォ | +2.050 |
sth | +2.041 |
Neg logit contributions | |
ging | -2.989 |
chin | -2.840 |
keeping | -2.768 |
�� | -2.759 |
�� | -2.659 |
Token | . |
Token ID | 13 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
ploma | +2.179 |
sucker | +2.160 |
rongh | +2.092 |
ォ | +2.075 |
sth | +2.075 |
Neg logit contributions | |
ging | -3.595 |
chin | -3.370 |
�� | -3.332 |
keeping | -3.318 |
gers | -3.194 |
Token | de |
Token ID | 2934 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
ploma | +2.381 |
sucker | +2.342 |
rongh | +2.330 |
sth | +2.324 |
EVER | +2.277 |
Neg logit contributions | |
ging | -2.211 |
chin | -2.043 |
�� | -2.005 |
keeping | -2.003 |
�� | -1.941 |
Token | bit |
Token ID | 1643 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
sucker | +0.657 |
ploma | +0.657 |
rongh | +0.626 |
ォ | +0.616 |
babe | +0.608 |
Neg logit contributions | |
ging | -1.370 |
chin | -1.306 |
keeping | -1.273 |
�� | -1.250 |
gers | -1.233 |
Token | , |
Token ID | 11 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
ging | +0.210 |
chin | +0.198 |
keeping | +0.193 |
�� | +0.187 |
gers | +0.186 |
Neg logit contributions | |
ploma | -0.138 |
sucker | -0.136 |
rongh | -0.133 |
ォ | -0.132 |
EVER | -0.128 |
Token | and |
Token ID | 290 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ging | +0.453 |
chin | +0.427 |
keeping | +0.417 |
�� | +0.405 |
gers | +0.401 |
Neg logit contributions | |
ploma | -0.302 |
sucker | -0.299 |
rongh | -0.291 |
ォ | -0.288 |
babe | -0.281 |
Token | said |
Token ID | 531 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ploma | +1.780 |
sucker | +1.775 |
rongh | +1.667 |
babe | +1.666 |
EVER | +1.657 |
Neg logit contributions | |
ging | -2.794 |
chin | -2.645 |
keeping | -2.565 |
�� | -2.559 |
gers | -2.482 |
Token | -- |
Token ID | 1377 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
ging | +0.141 |
chin | +0.134 |
keeping | +0.130 |
�� | +0.127 |
gers | +0.126 |
Neg logit contributions | |
ploma | -0.086 |
sucker | -0.085 |
rongh | -0.083 |
ォ | -0.082 |
babe | -0.080 |
Token | Hey |
Token ID | 14690 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
sucker | +1.802 |
ploma | +1.798 |
rongh | +1.709 |
babe | +1.701 |
EVER | +1.692 |
Neg logit contributions | |
ging | -2.734 |
chin | -2.584 |
keeping | -2.500 |
�� | -2.480 |
gers | -2.428 |
Token | there |
Token ID | 612 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
sucker | +5.672 |
babe | +5.584 |
date | +5.077 |
Syd | +4.941 |
dear | +4.826 |
Neg logit contributions | |
ging | -12.752 |
�� | -12.641 |
chin | -12.018 |
nutrition | -11.907 |
keeping | -11.789 |
Token | , |
Token ID | 11 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
sucker | +1.510 |
ploma | +1.463 |
babe | +1.420 |
EVER | +1.375 |
ォ | +1.374 |
Neg logit contributions | |
ging | -2.733 |
chin | -2.591 |
keeping | -2.525 |
�� | -2.520 |
nutrition | -2.456 |
Token | Am |
Token ID | 1703 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
sucker | +2.117 |
ploma | +2.032 |
babe | +1.993 |
date | +1.941 |
EVER | +1.932 |
Neg logit contributions | |
ging | -3.367 |
chin | -3.180 |
�� | -3.107 |
keeping | -3.093 |
nutrition | -3.006 |
Token | ade |
Token ID | 671 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
ploma | +3.212 |
sucker | +3.187 |
ォ | +3.084 |
EVER | +3.055 |
babe | +3.044 |
Neg logit contributions | |
ging | -2.411 |
chin | -2.223 |
keeping | -2.182 |
�� | -2.157 |
�� | -2.079 |
Token | us |
Token ID | 385 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
ging | +2.805 |
chin | +2.631 |
keeping | +2.472 |
gers | +2.395 |
gin | +2.306 |
Neg logit contributions | |
ploma | -3.149 |
ォ | -3.042 |
rongh | -3.038 |
sucker | -3.035 |
sqor | -2.915 |
Token | high |
Token ID | 1029 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ploma | +0.767 |
sucker | +0.763 |
rongh | +0.744 |
ォ | +0.738 |
babe | +0.727 |
Neg logit contributions | |
ging | -0.760 |
chin | -0.710 |
keeping | -0.687 |
�� | -0.669 |
gers | -0.656 |
Token | at |
Token ID | 379 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
ging | +1.740 |
chin | +1.638 |
keeping | +1.601 |
�� | +1.546 |
gers | +1.539 |
Neg logit contributions | |
ploma | -1.183 |
sucker | -1.166 |
rongh | -1.134 |
ォ | -1.126 |
babe | -1.096 |
Token | charter |
Token ID | 17422 |
Feature activation | -8.61e+00 |
Pos logit contributions | |
ging | +1.608 |
chin | +1.501 |
keeping | +1.461 |
�� | +1.408 |
gers | +1.403 |
Neg logit contributions | |
ploma | -1.373 |
sucker | -1.360 |
rongh | -1.331 |
ォ | -1.319 |
babe | -1.292 |
Token | schools |
Token ID | 4266 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
ging | +4.618 |
chin | +4.148 |
keeping | +3.983 |
gers | +3.812 |
keepers | +3.588 |
Neg logit contributions | |
ploma | -7.553 |
rongh | -7.443 |
sucker | -7.360 |
ォ | -7.300 |
sth | -7.195 |
Token | ( |
Token ID | 357 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ging | +3.458 |
chin | +3.238 |
keeping | +3.156 |
gers | +3.003 |
�� | +2.967 |
Neg logit contributions | |
ploma | -3.080 |
sucker | -3.028 |
rongh | -2.970 |
ォ | -2.943 |
babe | -2.885 |
Token | St |
Token ID | 1273 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
ging | +1.212 |
chin | +1.141 |
keeping | +1.109 |
�� | +1.070 |
gers | +1.066 |
Neg logit contributions | |
ploma | -0.915 |
sucker | -0.906 |
rongh | -0.881 |
ォ | -0.875 |
babe | -0.855 |
Token | uit |
Token ID | 5013 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
rongh | +11.586 |
ploma | +11.570 |
sth | +11.203 |
date | +11.105 |
sucker | +11.052 |
Neg logit contributions | |
�� | -6.396 |
ging | -6.365 |
�� | -6.261 |
keeping | -5.724 |
chin | -5.684 |
Token | and |
Token ID | 290 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
sucker | +2.046 |
ploma | +2.040 |
EVER | +1.941 |
rongh | +1.938 |
sth | +1.938 |
Neg logit contributions | |
ging | -3.640 |
chin | -3.433 |
�� | -3.380 |
keeping | -3.360 |
gers | -3.235 |
Token | Smith |
Token ID | 4176 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ploma | +0.407 |
sucker | +0.405 |
rongh | +0.393 |
ォ | +0.390 |
EVER | +0.386 |
Neg logit contributions | |
ging | -0.482 |
chin | -0.453 |
keeping | -0.440 |
�� | -0.429 |
gers | -0.419 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -5.78e+00 |
Pos logit contributions | |
ploma | +0.145 |
sucker | +0.143 |
rongh | +0.139 |
ォ | +0.138 |
EVER | +0.135 |
Neg logit contributions | |
ging | -0.191 |
chin | -0.180 |
keeping | -0.175 |
�� | -0.171 |
gers | -0.168 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ging | +4.419 |
chin | +4.106 |
keeping | +4.006 |
gers | +3.817 |
nutrition | +3.721 |
Neg logit contributions | |
ploma | -3.906 |
sucker | -3.790 |
rongh | -3.733 |
ォ | -3.703 |
EVER | -3.603 |
Token | hasn |
Token ID | 5818 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
ploma | +0.733 |
sucker | +0.730 |
rongh | +0.703 |
ォ | +0.700 |
babe | +0.689 |
Neg logit contributions | |
ging | -0.931 |
chin | -0.876 |
keeping | -0.851 |
�� | -0.833 |
gers | -0.817 |
Token | � |
Token ID | 447 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ploma | +0.597 |
sucker | +0.590 |
rongh | +0.574 |
ォ | +0.569 |
babe | +0.556 |
Neg logit contributions | |
ging | -0.839 |
chin | -0.790 |
keeping | -0.769 |
�� | -0.748 |
gers | -0.740 |
Token | � |
Token ID | 247 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ploma | +0.132 |
sucker | +0.131 |
rongh | +0.128 |
ォ | +0.127 |
babe | +0.124 |
Neg logit contributions | |
ging | -0.136 |
chin | -0.127 |
keeping | -0.124 |
�� | -0.121 |
gers | -0.118 |
Token | t |
Token ID | 83 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ploma | +0.166 |
sucker | +0.164 |
rongh | +0.159 |
ォ | +0.158 |
babe | +0.154 |
Neg logit contributions | |
ging | -0.261 |
chin | -0.246 |
keeping | -0.240 |
gers | -0.232 |
�� | -0.231 |
Token | stopped |
Token ID | 5025 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
ploma | +0.369 |
sucker | +0.365 |
rongh | +0.356 |
ォ | +0.353 |
babe | +0.346 |
Neg logit contributions | |
ging | -0.447 |
chin | -0.419 |
keeping | -0.407 |
�� | -0.395 |
gers | -0.391 |
Token | Sch |
Token ID | 3059 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
ging | +3.348 |
chin | +3.141 |
keeping | +3.027 |
gers | +2.960 |
�� | +2.879 |
Neg logit contributions | |
ploma | -2.409 |
rongh | -2.341 |
sucker | -2.333 |
ォ | -2.314 |
babe | -2.226 |
Token | um |
Token ID | 388 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
ploma | +6.516 |
rongh | +6.162 |
nee | +6.125 |
sth | +5.956 |
EVER | +5.896 |
Neg logit contributions | |
�� | -11.667 |
ging | -11.214 |
�� | -10.894 |
chin | -10.791 |
keeping | -10.488 |
Token | acher |
Token ID | 3493 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ging | +1.951 |
chin | +1.825 |
keeping | +1.768 |
gers | +1.701 |
nutrition | +1.614 |
Neg logit contributions | |
ploma | -1.950 |
sucker | -1.929 |
ォ | -1.906 |
rongh | -1.879 |
Syd | -1.845 |
Token | from |
Token ID | 422 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
sucker | +1.573 |
ploma | +1.572 |
ォ | +1.506 |
rongh | +1.503 |
EVER | +1.496 |
Neg logit contributions | |
ging | -2.311 |
chin | -2.202 |
keeping | -2.125 |
�� | -2.122 |
nutrition | -2.053 |
Token | asking |
Token ID | 4737 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ging | +1.526 |
chin | +1.428 |
keeping | +1.391 |
gers | +1.336 |
�� | +1.327 |
Neg logit contributions | |
ploma | -1.248 |
sucker | -1.220 |
rongh | -1.214 |
ォ | -1.193 |
sth | -1.162 |
Token | .) |
Token ID | 2014 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
ging | +1.687 |
chin | +1.584 |
keeping | +1.539 |
gers | +1.497 |
�� | +1.476 |
Neg logit contributions | |
ploma | -1.217 |
sucker | -1.184 |
rongh | -1.184 |
ォ | -1.169 |
babe | -1.122 |
Token | battery |
Token ID | 6555 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ging | +1.704 |
chin | +1.579 |
keeping | +1.551 |
gers | +1.480 |
nutrition | +1.429 |
Neg logit contributions | |
ploma | -1.482 |
ォ | -1.430 |
rongh | -1.421 |
sucker | -1.415 |
sth | -1.367 |
Token | is |
Token ID | 318 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
ging | +1.327 |
chin | +1.211 |
keeping | +1.193 |
gers | +1.139 |
nutrition | +1.095 |
Neg logit contributions | |
ploma | -1.469 |
ォ | -1.425 |
sucker | -1.423 |
rongh | -1.419 |
sqor | -1.377 |
Token | constructed |
Token ID | 12006 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ploma | +0.226 |
sucker | +0.222 |
rongh | +0.219 |
ォ | +0.218 |
babe | +0.210 |
Neg logit contributions | |
ging | -0.267 |
chin | -0.250 |
keeping | -0.244 |
gers | -0.233 |
�� | -0.229 |
Token | . |
Token ID | 13 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
ploma | +1.001 |
sucker | +0.988 |
rongh | +0.958 |
ォ | +0.947 |
EVER | +0.932 |
Neg logit contributions | |
ging | -1.667 |
chin | -1.577 |
keeping | -1.536 |
�� | -1.520 |
gers | -1.482 |
Token | How |
Token ID | 1374 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ploma | +0.344 |
sucker | +0.338 |
ォ | +0.338 |
rongh | +0.330 |
Syd | +0.327 |
Neg logit contributions | |
ging | -0.439 |
chin | -0.412 |
keeping | -0.402 |
�� | -0.394 |
gers | -0.383 |
Token | St |
Token ID | 1273 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
ploma | +1.034 |
sucker | +1.020 |
rongh | +0.983 |
ォ | +0.971 |
babe | +0.945 |
Neg logit contributions | |
ging | -2.130 |
chin | -2.024 |
keeping | -1.978 |
�� | -1.936 |
gers | -1.913 |
Token | uff |
Token ID | 1648 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
ploma | +4.899 |
sth | +4.601 |
sucker | +4.538 |
rongh | +4.452 |
EVER | +4.444 |
Neg logit contributions | |
�� | -13.293 |
�� | -12.820 |
ging | -12.629 |
chin | -12.184 |
keeping | -12.138 |
Token | Works |
Token ID | 23044 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
ploma | +1.427 |
sucker | +1.377 |
EVER | +1.341 |
sth | +1.338 |
ォ | +1.337 |
Neg logit contributions | |
ging | -2.509 |
chin | -2.369 |
�� | -2.344 |
keeping | -2.298 |
�� | -2.238 |
Token | . |
Token ID | 13 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
ploma | +2.488 |
EVER | +2.410 |
date | +2.374 |
sucker | +2.365 |
sth | +2.350 |
Neg logit contributions | |
ging | -5.141 |
�� | -5.063 |
chin | -4.897 |
�� | -4.837 |
keeping | -4.723 |
Token | com |
Token ID | 785 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
ploma | +2.746 |
EVER | +2.685 |
sucker | +2.664 |
sth | +2.658 |
date | +2.655 |
Neg logit contributions | |
ging | -3.542 |
�� | -3.411 |
chin | -3.315 |
�� | -3.258 |
keeping | -3.189 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ging | +0.596 |
chin | +0.563 |
keeping | +0.548 |
�� | +0.534 |
gers | +0.526 |
Neg logit contributions | |
ploma | -0.421 |
sucker | -0.417 |
rongh | -0.406 |
ォ | -0.403 |
babe | -0.394 |
Token | . |
Token ID | 13 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
ploma | +0.129 |
sucker | +0.128 |
rongh | +0.124 |
ォ | +0.123 |
babe | +0.120 |
Neg logit contributions | |
ging | -0.197 |
chin | -0.186 |
keeping | -0.182 |
�� | -0.177 |
gers | -0.175 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
ploma | +0.541 |
sucker | +0.536 |
rongh | +0.520 |
ォ | +0.516 |
EVER | +0.505 |
Neg logit contributions | |
ging | -0.774 |
chin | -0.730 |
keeping | -0.710 |
�� | -0.692 |
gers | -0.684 |
Token |
|
Token ID | 198 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
ging | +0.249 |
chin | +0.233 |
keeping | +0.229 |
gers | +0.219 |
�� | +0.214 |
Neg logit contributions | |
ploma | -0.188 |
sucker | -0.186 |
rongh | -0.182 |
ォ | -0.180 |
babe | -0.174 |
Token | Co |
Token ID | 7222 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
ging | +0.040 |
chin | +0.037 |
keeping | +0.036 |
�� | +0.035 |
gers | +0.035 |
Neg logit contributions | |
ploma | -0.028 |
sucker | -0.028 |
rongh | -0.027 |
ォ | -0.026 |
babe | -0.026 |
Token | inc |
Token ID | 1939 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
ploma | +2.316 |
sucker | +2.307 |
rongh | +2.256 |
EVER | +2.187 |
sth | +2.184 |
Neg logit contributions | |
ging | -2.649 |
keeping | -2.449 |
chin | -2.436 |
�� | -2.427 |
gers | -2.319 |
Token | identally |
Token ID | 23961 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
sucker | +2.996 |
ploma | +2.938 |
rongh | +2.892 |
EVER | +2.815 |
babe | +2.811 |
Neg logit contributions | |
ging | -5.631 |
�� | -5.375 |
chin | -5.369 |
keeping | -5.241 |
�� | -5.170 |
Token | , |
Token ID | 11 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
sucker | +5.079 |
date | +4.967 |
EVER | +4.827 |
Syd | +4.816 |
Clause | +4.618 |
Neg logit contributions | |
ging | -12.162 |
chin | -11.965 |
�� | -11.788 |
nutrition | -11.751 |
�� | -11.374 |
Token | the |
Token ID | 262 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
sucker | +2.149 |
ploma | +2.117 |
EVER | +2.024 |
date | +2.023 |
rongh | +2.020 |
Neg logit contributions | |
ging | -3.158 |
chin | -2.988 |
keeping | -2.917 |
�� | -2.903 |
nutrition | -2.813 |
Token | Doors |
Token ID | 33775 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
ploma | +0.286 |
sucker | +0.282 |
rongh | +0.275 |
ォ | +0.272 |
babe | +0.265 |
Neg logit contributions | |
ging | -0.423 |
chin | -0.399 |
keeping | -0.389 |
�� | -0.377 |
gers | -0.375 |
Token | were |
Token ID | 547 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
ging | +0.042 |
chin | +0.039 |
keeping | +0.038 |
�� | +0.037 |
gers | +0.036 |
Neg logit contributions | |
ploma | -0.035 |
sucker | -0.035 |
rongh | -0.034 |
ォ | -0.034 |
babe | -0.033 |
Token | formed |
Token ID | 7042 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
sucker | +2.807 |
ploma | +2.667 |
EVER | +2.631 |
date | +2.606 |
babe | +2.563 |
Neg logit contributions | |
ging | -3.818 |
chin | -3.649 |
�� | -3.561 |
keeping | -3.519 |
nutrition | -3.413 |
Token | Rob |
Token ID | 3851 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
ging | +5.739 |
chin | +5.366 |
keeping | +5.200 |
gers | +5.030 |
nutrition | +4.866 |
Neg logit contributions | |
ploma | -4.361 |
sucker | -4.253 |
ォ | -4.162 |
rongh | -4.140 |
sqor | -4.032 |
Token | Qu |
Token ID | 2264 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
ging | +5.522 |
chin | +5.155 |
keeping | +4.961 |
gers | +4.826 |
�� | +4.692 |
Neg logit contributions | |
ploma | -4.492 |
sucker | -4.390 |
rongh | -4.267 |
ォ | -4.256 |
EVER | -4.141 |
Token | ist |
Token ID | 396 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ging | +2.314 |
chin | +2.187 |
keeping | +2.106 |
gers | +2.056 |
vim | +1.976 |
Neg logit contributions | |
ォ | -1.829 |
ploma | -1.818 |
sucker | -1.815 |
rongh | -1.738 |
babe | -1.731 |
Token | , |
Token ID | 11 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
ploma | +0.758 |
sucker | +0.752 |
rongh | +0.725 |
ォ | +0.720 |
babe | +0.712 |
Neg logit contributions | |
ging | -1.272 |
chin | -1.204 |
keeping | -1.177 |
�� | -1.165 |
gers | -1.132 |
Token | with |
Token ID | 351 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ploma | +0.244 |
sucker | +0.241 |
rongh | +0.234 |
ォ | +0.232 |
babe | +0.228 |
Neg logit contributions | |
ging | -0.381 |
chin | -0.360 |
keeping | -0.351 |
�� | -0.344 |
gers | -0.339 |
Token | Mont |
Token ID | 5575 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
ploma | +0.922 |
sucker | +0.916 |
rongh | +0.890 |
ォ | +0.878 |
babe | +0.865 |
Neg logit contributions | |
ging | -1.291 |
chin | -1.218 |
keeping | -1.188 |
�� | -1.166 |
gers | -1.139 |
Token | an |
Token ID | 272 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
ploma | +7.685 |
sucker | +7.579 |
rongh | +7.554 |
nee | +7.483 |
babe | +7.372 |
Neg logit contributions | |
ging | -9.832 |
�� | -9.660 |
�� | -9.096 |
keeping | -8.993 |
chin | -8.912 |
Token | ans |
Token ID | 504 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ploma | +1.505 |
sucker | +1.489 |
rongh | +1.453 |
ォ | +1.434 |
EVER | +1.411 |
Neg logit contributions | |
ging | -1.750 |
chin | -1.640 |
keeping | -1.595 |
�� | -1.553 |
gers | -1.522 |
Token | across |
Token ID | 1973 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
sucker | +0.940 |
ploma | +0.937 |
rongh | +0.903 |
ォ | +0.896 |
babe | +0.887 |
Neg logit contributions | |
ging | -1.196 |
chin | -1.126 |
keeping | -1.091 |
�� | -1.084 |
gers | -1.054 |
Token | the |
Token ID | 262 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
ploma | +1.612 |
sucker | +1.600 |
rongh | +1.572 |
EVER | +1.512 |
ォ | +1.504 |
Neg logit contributions | |
ging | -2.603 |
chin | -2.456 |
keeping | -2.412 |
�� | -2.384 |
gers | -2.322 |
Token | state |
Token ID | 1181 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
sucker | +1.924 |
ploma | +1.901 |
rongh | +1.852 |
date | +1.810 |
Turks | +1.794 |
Neg logit contributions | |
ging | -3.201 |
chin | -3.042 |
keeping | -2.988 |
�� | -2.975 |
gers | -2.872 |
Token | are |
Token ID | 389 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
ploma | +0.142 |
sucker | +0.141 |
rongh | +0.137 |
ォ | +0.136 |
EVER | +0.134 |
Neg logit contributions | |
ging | -0.162 |
chin | -0.152 |
keeping | -0.147 |
�� | -0.144 |
gers | -0.142 |
Token | off |
Token ID | 572 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
ploma | +0.377 |
sucker | +0.375 |
rongh | +0.360 |
ォ | +0.358 |
EVER | +0.350 |
Neg logit contributions | |
ging | -0.627 |
chin | -0.593 |
keeping | -0.577 |
�� | -0.568 |
gers | -0.558 |
Token | . |
Token ID | 13 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
ging | +3.309 |
chin | +3.073 |
keeping | +3.063 |
gers | +2.871 |
�� | +2.829 |
Neg logit contributions | |
ploma | -2.415 |
sucker | -2.326 |
ォ | -2.301 |
rongh | -2.294 |
sth | -2.210 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ging | +0.688 |
chin | +0.648 |
keeping | +0.631 |
�� | +0.609 |
gers | +0.605 |
Neg logit contributions | |
ploma | -0.508 |
sucker | -0.502 |
rongh | -0.489 |
ォ | -0.484 |
babe | -0.472 |
Token |
|
Token ID | 198 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
ging | +1.005 |
chin | +0.938 |
keeping | +0.925 |
gers | +0.884 |
keepers | +0.853 |
Neg logit contributions | |
ploma | -0.804 |
sucker | -0.799 |
rongh | -0.784 |
ォ | -0.771 |
babe | -0.743 |
Token | St |
Token ID | 1273 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
ging | +0.491 |
chin | +0.462 |
keeping | +0.450 |
�� | +0.437 |
gers | +0.432 |
Neg logit contributions | |
ploma | -0.360 |
sucker | -0.356 |
rongh | -0.346 |
ォ | -0.343 |
babe | -0.335 |
Token | oring |
Token ID | 3255 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
rongh | +8.582 |
ploma | +7.794 |
sucker | +7.676 |
date | +7.494 |
sth | +7.413 |
Neg logit contributions | |
�� | -9.457 |
chin | -9.167 |
�� | -9.142 |
ging | -9.103 |
keeping | -8.547 |
Token |
|
Token ID | 198 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
sucker | +2.253 |
ploma | +2.199 |
rongh | +2.155 |
date | +2.140 |
babe | +2.127 |
Neg logit contributions | |
ging | -3.796 |
chin | -3.604 |
�� | -3.503 |
keeping | -3.466 |
gers | -3.412 |
Token |
|
Token ID | 198 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
ploma | +0.118 |
sucker | +0.117 |
rongh | +0.114 |
ォ | +0.112 |
babe | +0.109 |
Neg logit contributions | |
ging | -0.162 |
chin | -0.152 |
keeping | -0.149 |
gers | -0.143 |
�� | -0.142 |
Token | St |
Token ID | 1273 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
ploma | +0.228 |
sucker | +0.225 |
rongh | +0.219 |
ォ | +0.217 |
babe | +0.213 |
Neg logit contributions | |
ging | -0.323 |
chin | -0.306 |
keeping | -0.296 |
�� | -0.293 |
gers | -0.286 |
Token | oring |
Token ID | 3255 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
rongh | +6.976 |
ploma | +6.539 |
sucker | +6.392 |
date | +6.224 |
EVER | +6.208 |
Neg logit contributions | |
chin | -7.158 |
ging | -7.119 |
�� | -7.023 |
�� | -6.834 |
keeping | -6.582 |
Token | , |
Token ID | 11 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ploma | +0.343 |
sucker | +0.341 |
rongh | +0.330 |
ォ | +0.327 |
babe | +0.321 |
Neg logit contributions | |
ging | -0.498 |
chin | -0.470 |
keeping | -0.458 |
�� | -0.448 |
gers | -0.441 |
Token | whose |
Token ID | 3025 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ging | +1.438 |
chin | +1.348 |
keeping | +1.318 |
�� | +1.260 |
gers | +1.259 |
Neg logit contributions | |
ploma | -1.105 |
sucker | -1.088 |
rongh | -1.064 |
ォ | -1.062 |
babe | -1.026 |
Token | occupation |
Token ID | 13755 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
sucker | +1.129 |
ploma | +1.125 |
rongh | +1.083 |
ォ | +1.069 |
babe | +1.065 |
Neg logit contributions | |
ging | -1.590 |
chin | -1.512 |
keeping | -1.459 |
�� | -1.447 |
gers | -1.405 |
Token | structure |
Token ID | 4645 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ging | +0.380 |
chin | +0.357 |
keeping | +0.347 |
�� | +0.338 |
gers | +0.333 |
Neg logit contributions | |
ploma | -0.303 |
sucker | -0.300 |
rongh | -0.293 |
ォ | -0.290 |
babe | -0.284 |
Token | more |
Token ID | 517 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
sucker | +1.201 |
ploma | +1.199 |
rongh | +1.162 |
ォ | +1.149 |
date | +1.137 |
Neg logit contributions | |
ging | -1.460 |
chin | -1.378 |
keeping | -1.330 |
�� | -1.313 |
gers | -1.281 |
Token | closely |
Token ID | 7173 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
ging | +0.296 |
chin | +0.280 |
keeping | +0.274 |
�� | +0.267 |
gers | +0.265 |
Neg logit contributions | |
ploma | -0.154 |
sucker | -0.152 |
rongh | -0.147 |
ォ | -0.145 |
babe | -0.141 |
Token | matches |
Token ID | 7466 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
date | +4.969 |
sucker | +4.879 |
dates | +4.337 |
rongh | +4.303 |
ploma | +4.294 |
Neg logit contributions | |
ging | -12.743 |
chin | -12.499 |
�� | -12.462 |
�� | -12.354 |
keeping | -11.784 |
Token | our |
Token ID | 674 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
ploma | +1.685 |
sucker | +1.678 |
rongh | +1.605 |
ォ | +1.587 |
babe | +1.577 |
Neg logit contributions | |
ging | -2.728 |
chin | -2.596 |
keeping | -2.519 |
�� | -2.500 |
gers | -2.436 |
Token | established |
Token ID | 4920 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ging | +0.170 |
chin | +0.161 |
keeping | +0.157 |
�� | +0.153 |
gers | +0.151 |
Neg logit contributions | |
ploma | -0.104 |
sucker | -0.102 |
rongh | -0.099 |
ォ | -0.098 |
babe | -0.096 |
Token | notions |
Token ID | 26226 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
ging | +1.590 |
chin | +1.493 |
keeping | +1.461 |
�� | +1.401 |
gers | +1.397 |
Neg logit contributions | |
ploma | -1.075 |
sucker | -1.054 |
rongh | -1.035 |
ォ | -1.021 |
EVER | -0.990 |
Token | of |
Token ID | 286 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
ploma | +0.378 |
sucker | +0.374 |
rongh | +0.362 |
ォ | +0.362 |
EVER | +0.354 |
Neg logit contributions | |
ging | -0.554 |
chin | -0.523 |
keeping | -0.508 |
�� | -0.497 |
gers | -0.494 |
Token | were |
Token ID | 547 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ging | +1.210 |
chin | +1.136 |
keeping | +1.105 |
�� | +1.056 |
gers | +1.055 |
Neg logit contributions | |
ploma | -1.041 |
sucker | -1.023 |
rongh | -1.001 |
ォ | -0.994 |
EVER | -0.971 |
Token | gradually |
Token ID | 11835 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
ploma | +0.714 |
sucker | +0.709 |
rongh | +0.687 |
ォ | +0.680 |
EVER | +0.668 |
Neg logit contributions | |
ging | -0.980 |
chin | -0.925 |
keeping | -0.898 |
�� | -0.878 |
gers | -0.863 |
Token | merged |
Token ID | 23791 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
sucker | +2.163 |
ploma | +2.110 |
ォ | +2.013 |
rongh | +2.003 |
babe | +2.002 |
Neg logit contributions | |
ging | -3.303 |
chin | -3.128 |
keeping | -3.058 |
�� | -3.042 |
nutrition | -2.953 |
Token | into |
Token ID | 656 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ging | +0.945 |
chin | +0.883 |
keeping | +0.857 |
�� | +0.830 |
gers | +0.819 |
Neg logit contributions | |
ploma | -0.902 |
sucker | -0.896 |
rongh | -0.874 |
ォ | -0.867 |
babe | -0.852 |
Token | an |
Token ID | 281 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ging | +0.956 |
chin | +0.903 |
keeping | +0.880 |
�� | +0.858 |
gers | +0.848 |
Neg logit contributions | |
ploma | -0.608 |
sucker | -0.601 |
rongh | -0.584 |
ォ | -0.577 |
babe | -0.564 |
Token | all |
Token ID | 477 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
ploma | +0.480 |
sucker | +0.472 |
rongh | +0.442 |
EVER | +0.423 |
ォ | +0.421 |
Neg logit contributions | |
ging | -1.923 |
chin | -1.847 |
keeping | -1.811 |
�� | -1.775 |
gers | -1.756 |
Token | - |
Token ID | 12 |
Feature activation | -6.26e+00 |
Pos logit contributions | |
ging | +8.340 |
chin | +7.771 |
keeping | +7.692 |
gers | +7.231 |
gin | +6.769 |
Neg logit contributions | |
ploma | -10.857 |
rongh | -10.852 |
ォ | -10.799 |
sucker | -10.542 |
sqor | -10.149 |
Token | en |
Token ID | 268 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
ging | +4.370 |
chin | +4.196 |
keeping | +4.005 |
gers | +3.727 |
nutrition | +3.706 |
Neg logit contributions | |
ploma | -4.746 |
sucker | -4.632 |
ォ | -4.610 |
rongh | -4.545 |
Clause | -4.464 |
Token | comp |
Token ID | 5589 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
ging | +2.834 |
chin | +2.615 |
keeping | +2.558 |
gers | +2.381 |
gin | +2.344 |
Neg logit contributions | |
sucker | -3.311 |
ploma | -3.282 |
ォ | -3.259 |
rongh | -3.181 |
babe | -3.166 |
Token | assing |
Token ID | 19696 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
ging | +4.645 |
chin | +4.307 |
keeping | +4.163 |
ience | +3.783 |
gin | +3.734 |
Neg logit contributions | |
sucker | -6.535 |
ploma | -6.514 |
ォ | -6.507 |
rongh | -6.445 |
babe | -6.351 |
Token | stereotype |
Token ID | 31240 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
ging | +2.611 |
chin | +2.425 |
keeping | +2.362 |
�� | +2.284 |
gers | +2.270 |
Neg logit contributions | |
ploma | -2.211 |
sucker | -2.127 |
rongh | -2.104 |
ォ | -2.092 |
EVER | -2.059 |
Token | supporters |
Token ID | 5941 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
sucker | +2.448 |
ploma | +2.410 |
rongh | +2.328 |
babe | +2.322 |
date | +2.310 |
Neg logit contributions | |
ging | -4.305 |
chin | -4.116 |
�� | -4.025 |
keeping | -3.956 |
nutrition | -3.845 |
Token | joined |
Token ID | 5399 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
sucker | +1.767 |
ploma | +1.749 |
rongh | +1.708 |
ォ | +1.679 |
EVER | +1.664 |
Neg logit contributions | |
ging | -2.262 |
chin | -2.130 |
keeping | -2.061 |
�� | -2.061 |
gers | -1.985 |
Token | a |
Token ID | 257 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
sucker | +1.926 |
ploma | +1.926 |
rongh | +1.855 |
EVER | +1.810 |
Turks | +1.806 |
Neg logit contributions | |
ging | -3.084 |
chin | -2.937 |
�� | -2.857 |
keeping | -2.856 |
nutrition | -2.742 |
Token | large |
Token ID | 1588 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ging | +0.404 |
chin | +0.381 |
keeping | +0.371 |
�� | +0.360 |
gers | +0.357 |
Neg logit contributions | |
ploma | -0.285 |
sucker | -0.281 |
rongh | -0.274 |
ォ | -0.271 |
babe | -0.265 |
Token | fleet |
Token ID | 11026 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
sucker | +0.886 |
ploma | +0.883 |
rongh | +0.850 |
ォ | +0.834 |
babe | +0.825 |
Neg logit contributions | |
ging | -1.556 |
chin | -1.477 |
keeping | -1.438 |
�� | -1.425 |
gers | -1.386 |
Token | led |
Token ID | 2957 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
ging | +2.560 |
chin | +2.402 |
keeping | +2.354 |
gers | +2.242 |
�� | +2.228 |
Neg logit contributions | |
ploma | -1.929 |
sucker | -1.877 |
rongh | -1.846 |
ォ | -1.841 |
babe | -1.781 |
Token | by |
Token ID | 416 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
ging | +7.041 |
chin | +5.938 |
gers | +5.829 |
keeping | +5.797 |
�� | +5.371 |
Neg logit contributions | |
ploma | -11.959 |
sucker | -11.563 |
rongh | -11.484 |
ォ | -11.422 |
Clause | -11.256 |
Token | the |
Token ID | 262 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
ging | +0.232 |
chin | +0.220 |
keeping | +0.214 |
�� | +0.209 |
gers | +0.207 |
Neg logit contributions | |
ploma | -0.139 |
sucker | -0.137 |
rongh | -0.133 |
ォ | -0.132 |
babe | -0.128 |
Token | sons |
Token ID | 11989 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ploma | +0.514 |
sucker | +0.507 |
rongh | +0.492 |
ォ | +0.488 |
babe | +0.474 |
Neg logit contributions | |
ging | -0.852 |
chin | -0.805 |
keeping | -0.785 |
�� | -0.764 |
gers | -0.758 |
Token | of |
Token ID | 286 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
ploma | +0.603 |
sucker | +0.599 |
rongh | +0.584 |
ォ | +0.575 |
EVER | +0.566 |
Neg logit contributions | |
ging | -0.891 |
chin | -0.841 |
keeping | -0.823 |
�� | -0.801 |
gers | -0.789 |
Token | S |
Token ID | 311 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ging | +0.324 |
chin | +0.307 |
keeping | +0.299 |
�� | +0.291 |
gers | +0.289 |
Neg logit contributions | |
ploma | -0.191 |
sucker | -0.189 |
rongh | -0.183 |
ォ | -0.181 |
babe | -0.176 |
Token | . |
Token ID | 13 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
ploma | +1.869 |
sucker | +1.860 |
rongh | +1.811 |
ォ | +1.764 |
EVER | +1.753 |
Neg logit contributions | |
ging | -2.657 |
chin | -2.515 |
�� | -2.448 |
keeping | -2.428 |
gers | -2.354 |
Token |
|
Token ID | 198 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
ploma | +0.595 |
sucker | +0.587 |
rongh | +0.571 |
ォ | +0.568 |
EVER | +0.559 |
Neg logit contributions | |
ging | -0.826 |
chin | -0.779 |
keeping | -0.756 |
�� | -0.744 |
gers | -0.729 |
Token |
|
Token ID | 198 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
ploma | +0.505 |
sucker | +0.500 |
rongh | +0.487 |
ォ | +0.482 |
babe | +0.470 |
Neg logit contributions | |
ging | -0.700 |
chin | -0.658 |
keeping | -0.643 |
gers | -0.618 |
�� | -0.616 |
Token | At |
Token ID | 2953 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ploma | +0.400 |
sucker | +0.392 |
rongh | +0.382 |
ォ | +0.380 |
EVER | +0.372 |
Neg logit contributions | |
ging | -0.579 |
chin | -0.547 |
keeping | -0.531 |
�� | -0.527 |
gers | -0.513 |
Token | a |
Token ID | 257 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
ploma | +1.100 |
sucker | +1.088 |
rongh | +1.061 |
ォ | +1.035 |
date | +1.033 |
Neg logit contributions | |
ging | -1.765 |
chin | -1.675 |
keeping | -1.639 |
�� | -1.616 |
gers | -1.571 |
Token | curs |
Token ID | 13882 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
ging | +3.175 |
chin | +2.959 |
keeping | +2.884 |
gers | +2.770 |
�� | +2.744 |
Neg logit contributions | |
ploma | -2.399 |
sucker | -2.338 |
rongh | -2.317 |
ォ | -2.296 |
EVER | -2.230 |
Token | ory |
Token ID | 652 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
ging | +2.867 |
chin | +2.010 |
keeping | +1.720 |
gers | +1.336 |
gin | +1.102 |
Neg logit contributions | |
ォ | -16.050 |
sucker | -15.809 |
ploma | -15.790 |
Turks | -15.752 |
babe | -15.598 |
Token | glance |
Token ID | 16086 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
ging | +3.151 |
chin | +2.878 |
keeping | +2.800 |
gers | +2.644 |
�� | +2.598 |
Neg logit contributions | |
ploma | -3.686 |
rongh | -3.601 |
sucker | -3.584 |
ォ | -3.567 |
sth | -3.467 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ging | +0.661 |
chin | +0.626 |
keeping | +0.611 |
�� | +0.598 |
gers | +0.590 |
Neg logit contributions | |
ploma | -0.384 |
sucker | -0.380 |
rongh | -0.367 |
ォ | -0.364 |
babe | -0.356 |
Token | this |
Token ID | 428 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
ploma | +1.229 |
sucker | +1.227 |
rongh | +1.177 |
ォ | +1.163 |
babe | +1.154 |
Neg logit contributions | |
ging | -1.849 |
chin | -1.753 |
keeping | -1.695 |
�� | -1.686 |
gers | -1.641 |
Token | makes |
Token ID | 1838 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
ploma | +0.179 |
sucker | +0.179 |
rongh | +0.173 |
ォ | +0.172 |
babe | +0.170 |
Neg logit contributions | |
ging | -0.197 |
chin | -0.184 |
keeping | -0.179 |
�� | -0.175 |
gers | -0.171 |
Token | of |
Token ID | 286 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
ging | +4.569 |
chin | +4.260 |
keeping | +4.124 |
gers | +3.985 |
�� | +3.906 |
Neg logit contributions | |
ploma | -3.764 |
rongh | -3.651 |
sucker | -3.645 |
ォ | -3.588 |
EVER | -3.453 |
Token | a |
Token ID | 257 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
ging | +3.240 |
chin | +3.037 |
keeping | +2.960 |
�� | +2.848 |
gers | +2.840 |
Neg logit contributions | |
ploma | -2.538 |
sucker | -2.478 |
rongh | -2.434 |
ォ | -2.397 |
sth | -2.352 |
Token | monkey |
Token ID | 21657 |
Feature activation | -6.26e+00 |
Pos logit contributions | |
ging | +2.581 |
chin | +2.420 |
keeping | +2.356 |
�� | +2.279 |
gers | +2.263 |
Neg logit contributions | |
ploma | -1.860 |
sucker | -1.814 |
rongh | -1.781 |
ォ | -1.759 |
EVER | -1.720 |
Token | in |
Token ID | 287 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
ging | +4.977 |
chin | +4.617 |
keeping | +4.565 |
gers | +4.334 |
�� | +4.255 |
Neg logit contributions | |
ploma | -3.987 |
rongh | -3.866 |
sucker | -3.852 |
ォ | -3.822 |
sqor | -3.715 |
Token | a |
Token ID | 257 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
ging | +4.580 |
chin | +4.281 |
keeping | +4.190 |
�� | +4.018 |
gers | +4.013 |
Neg logit contributions | |
ploma | -3.608 |
sucker | -3.521 |
rongh | -3.454 |
ォ | -3.399 |
EVER | -3.338 |
Token | wheelchair |
Token ID | 27181 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
ging | +5.803 |
chin | +5.370 |
keeping | +5.246 |
�� | +5.039 |
gers | +5.020 |
Neg logit contributions | |
ploma | -4.486 |
rongh | -4.319 |
sucker | -4.306 |
ォ | -4.273 |
sth | -4.159 |
Token | ) |
Token ID | 8 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ging | +9.571 |
keeping | +8.668 |
chin | +8.405 |
gers | +8.112 |
gin | +7.909 |
Neg logit contributions | |
ploma | -8.571 |
rongh | -8.476 |
ォ | -8.283 |
sucker | -8.157 |
sqor | -8.111 |
Token | and |
Token ID | 290 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
ging | +1.265 |
chin | +1.183 |
keeping | +1.149 |
�� | +1.107 |
gers | +1.100 |
Neg logit contributions | |
ploma | -1.141 |
sucker | -1.126 |
rongh | -1.101 |
ォ | -1.094 |
babe | -1.069 |
Token | the |
Token ID | 262 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ging | +0.464 |
chin | +0.437 |
keeping | +0.426 |
�� | +0.414 |
gers | +0.410 |
Neg logit contributions | |
ploma | -0.332 |
sucker | -0.329 |
rongh | -0.320 |
ォ | -0.317 |
babe | -0.310 |
Token | reward |
Token ID | 6721 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
sucker | +1.491 |
ploma | +1.462 |
rongh | +1.415 |
babe | +1.413 |
ォ | +1.407 |
Neg logit contributions | |
ging | -1.957 |
chin | -1.857 |
�� | -1.783 |
keeping | -1.782 |
gers | -1.727 |
Token | position |
Token ID | 2292 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
ging | +0.352 |
chin | +0.332 |
keeping | +0.324 |
�� | +0.315 |
gers | +0.312 |
Neg logit contributions | |
ploma | -0.236 |
sucker | -0.233 |
rongh | -0.226 |
ォ | -0.224 |
babe | -0.219 |
Token | of |
Token ID | 286 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ploma | +4.051 |
sucker | +4.008 |
date | +3.927 |
rongh | +3.772 |
babe | +3.730 |
Neg logit contributions | |
ging | -7.121 |
�� | -6.882 |
chin | -6.788 |
keeping | -6.480 |
gers | -6.451 |
Token | national |
Token ID | 2260 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
ging | +0.134 |
chin | +0.127 |
keeping | +0.124 |
�� | +0.121 |
gers | +0.119 |
Neg logit contributions | |
ploma | -0.089 |
sucker | -0.088 |
rongh | -0.085 |
ォ | -0.084 |
EVER | -0.083 |
Token | policy |
Token ID | 2450 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ging | +1.792 |
chin | +1.659 |
keeping | +1.626 |
gers | +1.564 |
�� | +1.550 |
Neg logit contributions | |
ploma | -1.472 |
sucker | -1.454 |
rongh | -1.418 |
ォ | -1.407 |
EVER | -1.374 |
Token | in |
Token ID | 287 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ploma | +0.178 |
sucker | +0.177 |
rongh | +0.172 |
ォ | +0.170 |
babe | +0.167 |
Neg logit contributions | |
ging | -0.235 |
chin | -0.222 |
keeping | -0.215 |
�� | -0.211 |
gers | -0.207 |
Token | dozens |
Token ID | 9264 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
ploma | +0.850 |
sucker | +0.846 |
rongh | +0.819 |
ォ | +0.804 |
EVER | +0.799 |
Neg logit contributions | |
ging | -1.250 |
chin | -1.191 |
keeping | -1.149 |
�� | -1.138 |
gers | -1.105 |
Token | if |
Token ID | 611 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
ging | +2.223 |
chin | +2.087 |
keeping | +2.034 |
�� | +1.970 |
gers | +1.952 |
Neg logit contributions | |
ploma | -1.684 |
sucker | -1.666 |
rongh | -1.620 |
ォ | -1.610 |
babe | -1.572 |
Token | not |
Token ID | 407 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
ging | +7.985 |
keeping | +7.254 |
gers | +7.095 |
chin | +6.948 |
gin | +6.613 |
Neg logit contributions | |
ploma | -9.315 |
ォ | -9.236 |
sucker | -8.913 |
rongh | -8.747 |
sth | -8.550 |
Token | all |
Token ID | 477 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
ging | +6.158 |
chin | +5.417 |
keeping | +5.378 |
gers | +5.196 |
keepers | +4.924 |
Neg logit contributions | |
ォ | -8.061 |
ploma | -7.996 |
rongh | -7.651 |
sucker | -7.607 |
sth | -7.575 |
Token | countries |
Token ID | 2678 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ging | +4.794 |
chin | +4.386 |
keeping | +4.365 |
gers | +4.152 |
nutrition | +4.053 |
Neg logit contributions | |
ploma | -3.769 |
ォ | -3.633 |
sucker | -3.628 |
rongh | -3.558 |
sth | -3.496 |
Token | in |
Token ID | 287 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ging | +1.415 |
chin | +1.322 |
keeping | +1.297 |
gers | +1.242 |
�� | +1.227 |
Neg logit contributions | |
ploma | -1.024 |
sucker | -1.000 |
rongh | -0.984 |
ォ | -0.978 |
babe | -0.944 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ploma | +0.721 |
sucker | +0.717 |
rongh | +0.691 |
EVER | +0.682 |
date | +0.677 |
Neg logit contributions | |
ging | -1.130 |
chin | -1.077 |
keeping | -1.035 |
�� | -1.029 |
gers | -1.002 |
Token | going |
Token ID | 1016 |
Feature activation | -6.47e+00 |
Pos logit contributions | |
ging | +0.773 |
chin | +0.726 |
keeping | +0.709 |
�� | +0.682 |
gers | +0.680 |
Neg logit contributions | |
ploma | -0.576 |
sucker | -0.567 |
rongh | -0.557 |
ォ | -0.552 |
babe | -0.536 |
Token | to |
Token ID | 284 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
ging | +5.418 |
chin | +5.023 |
keeping | +4.943 |
gers | +4.778 |
�� | +4.761 |
Neg logit contributions | |
ploma | -3.851 |
sucker | -3.750 |
rongh | -3.691 |
ォ | -3.664 |
babe | -3.539 |
Token | stay |
Token ID | 2652 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
ging | +4.031 |
chin | +3.758 |
keeping | +3.680 |
gers | +3.559 |
ience | +3.406 |
Neg logit contributions | |
ploma | -3.243 |
ォ | -3.115 |
rongh | -3.102 |
sucker | -3.056 |
sqor | -3.004 |
Token | on |
Token ID | 319 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
ploma | +0.351 |
sucker | +0.347 |
rongh | +0.338 |
ォ | +0.335 |
babe | +0.328 |
Neg logit contributions | |
ging | -0.461 |
chin | -0.434 |
keeping | -0.422 |
�� | -0.410 |
gers | -0.405 |
Token | their |
Token ID | 511 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
ging | +2.604 |
chin | +2.458 |
keeping | +2.400 |
gers | +2.287 |
�� | +2.285 |
Neg logit contributions | |
ploma | -1.841 |
sucker | -1.796 |
ォ | -1.765 |
rongh | -1.761 |
EVER | -1.696 |
Token | lifes |
Token ID | 25622 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
ging | +2.481 |
chin | +2.315 |
keeping | +2.271 |
gers | +2.147 |
nutrition | +2.118 |
Neg logit contributions | |
ploma | -2.154 |
sucker | -2.080 |
rongh | -2.064 |
ォ | -2.063 |
EVER | -2.002 |
Token | aving |
Token ID | 2703 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
ging | +7.960 |
chin | +7.584 |
keeping | +7.234 |
gers | +6.840 |
vim | +6.727 |
Neg logit contributions | |
ploma | -9.541 |
sucker | -9.378 |
ォ | -9.179 |
rongh | -9.161 |
babe | -8.998 |
Token | medications |
Token ID | 17638 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
ging | +4.480 |
keeping | +4.136 |
chin | +4.132 |
gers | +3.908 |
nutrition | +3.850 |
Neg logit contributions | |
ploma | -3.390 |
rongh | -3.239 |
ォ | -3.234 |
sucker | -3.190 |
sqor | -3.071 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ging | +3.688 |
chin | +3.444 |
keeping | +3.390 |
gers | +3.239 |
nutrition | +3.182 |
Neg logit contributions | |
ploma | -2.658 |
sucker | -2.586 |
ォ | -2.548 |
rongh | -2.545 |
sth | -2.416 |
Token | He |
Token ID | 679 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ging | +1.062 |
chin | +1.000 |
keeping | +0.973 |
�� | +0.940 |
gers | +0.935 |
Neg logit contributions | |
ploma | -0.782 |
sucker | -0.776 |
rongh | -0.755 |
ォ | -0.745 |
babe | -0.730 |
Token | cites |
Token ID | 23474 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
ging | +0.971 |
chin | +0.910 |
keeping | +0.881 |
gers | +0.846 |
�� | +0.842 |
Neg logit contributions | |
ploma | -0.864 |
sucker | -0.851 |
rongh | -0.834 |
ォ | -0.824 |
babe | -0.809 |
Token | / |
Token ID | 14 |
Feature activation | -7.49e+00 |
Pos logit contributions | |
ging | +1.621 |
chin | +1.539 |
keeping | +1.523 |
gers | +1.466 |
nutrition | +1.434 |
Neg logit contributions | |
ploma | -0.729 |
sucker | -0.728 |
rongh | -0.712 |
ォ | -0.697 |
babe | -0.651 |
Token | CBC |
Token ID | 29208 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
ging | +3.166 |
chin | +2.796 |
keeping | +2.674 |
gers | +2.491 |
nutrition | +2.308 |
Neg logit contributions | |
sucker | -7.829 |
rongh | -7.572 |
ploma | -7.408 |
ォ | -7.389 |
sqor | -7.312 |
Token | ) |
Token ID | 8 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ging | +2.633 |
chin | +2.432 |
keeping | +2.407 |
gers | +2.310 |
nutrition | +2.234 |
Neg logit contributions | |
sucker | -2.172 |
ploma | -2.153 |
rongh | -2.116 |
ォ | -2.103 |
babe | -2.016 |
Token | Carter |
Token ID | 10831 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
ging | +2.040 |
chin | +1.920 |
keeping | +1.869 |
�� | +1.816 |
gers | +1.798 |
Neg logit contributions | |
ploma | -1.486 |
sucker | -1.471 |
rongh | -1.432 |
ォ | -1.418 |
babe | -1.385 |
Token | was |
Token ID | 373 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
ging | +3.618 |
chin | +3.410 |
keeping | +3.320 |
gers | +3.164 |
nutrition | +3.092 |
Neg logit contributions | |
ploma | -3.189 |
rongh | -3.065 |
ォ | -3.050 |
sucker | -3.023 |
sth | -2.917 |
Token | motivated |
Token ID | 13338 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
ging | +2.460 |
chin | +2.291 |
keeping | +2.257 |
gers | +2.176 |
�� | +2.121 |
Neg logit contributions | |
ploma | -1.698 |
ォ | -1.660 |
rongh | -1.656 |
sucker | -1.612 |
sqor | -1.564 |
Token | to |
Token ID | 284 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
ging | +8.853 |
keeping | +7.771 |
gers | +7.714 |
chin | +7.660 |
gin | +7.270 |
Neg logit contributions | |
ploma | -8.745 |
ォ | -8.529 |
rongh | -8.519 |
sucker | -8.084 |
sth | -7.989 |
Token | start |
Token ID | 923 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ging | +4.582 |
chin | +4.232 |
keeping | +4.063 |
gers | +4.057 |
gin | +3.887 |
Neg logit contributions | |
ploma | -3.832 |
ォ | -3.777 |
rongh | -3.670 |
sqor | -3.537 |
Clause | -3.536 |
Token | Work |
Token ID | 5521 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
ging | +1.831 |
chin | +1.724 |
keeping | +1.678 |
�� | +1.630 |
gers | +1.613 |
Neg logit contributions | |
ploma | -1.332 |
sucker | -1.317 |
rongh | -1.282 |
ォ | -1.271 |
babe | -1.242 |
Token | It |
Token ID | 632 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ploma | +1.739 |
sucker | +1.723 |
rongh | +1.652 |
EVER | +1.624 |
babe | +1.620 |
Neg logit contributions | |
ging | -2.862 |
chin | -2.709 |
keeping | -2.648 |
�� | -2.636 |
gers | -2.549 |
Token | Y |
Token ID | 575 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
ploma | +0.321 |
sucker | +0.318 |
rongh | +0.310 |
ォ | +0.307 |
EVER | +0.303 |
Neg logit contributions | |
ging | -0.356 |
chin | -0.333 |
keeping | -0.323 |
�� | -0.315 |
gers | -0.309 |
Token | then |
Token ID | 788 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ploma | +0.009 |
sucker | +0.009 |
rongh | +0.008 |
ォ | +0.008 |
babe | +0.008 |
Neg logit contributions | |
ging | -0.018 |
chin | -0.017 |
keeping | -0.017 |
�� | -0.017 |
gers | -0.016 |
Token | use |
Token ID | 779 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ging | +0.942 |
chin | +0.873 |
keeping | +0.841 |
�� | +0.805 |
gers | +0.801 |
Neg logit contributions | |
ploma | -1.122 |
sucker | -1.107 |
rongh | -1.093 |
ォ | -1.087 |
babe | -1.062 |
Token | it |
Token ID | 340 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
ploma | +0.093 |
sucker | +0.091 |
rongh | +0.090 |
ォ | +0.090 |
babe | +0.086 |
Neg logit contributions | |
ging | -0.136 |
chin | -0.128 |
keeping | -0.125 |
gers | -0.121 |
�� | -0.120 |
Token | to |
Token ID | 284 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ploma | +0.336 |
sucker | +0.331 |
rongh | +0.326 |
ォ | +0.324 |
babe | +0.310 |
Neg logit contributions | |
ging | -0.515 |
chin | -0.483 |
keeping | -0.474 |
gers | -0.457 |
�� | -0.451 |
Token | ' |
Token ID | 705 |
Feature activation | -6.46e+00 |
Pos logit contributions | |
ging | +1.178 |
chin | +1.097 |
keeping | +1.065 |
gers | +1.033 |
�� | +1.019 |
Neg logit contributions | |
ploma | -0.962 |
sucker | -0.947 |
ォ | -0.933 |
rongh | -0.930 |
sth | -0.898 |
Token | lead |
Token ID | 28230 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
ging | +2.544 |
chin | +2.221 |
keeping | +2.138 |
gers | +1.926 |
nutrition | +1.745 |
Neg logit contributions | |
ploma | -6.940 |
sucker | -6.879 |
ォ | -6.862 |
Clause | -6.745 |
Syd | -6.730 |
Token | by |
Token ID | 416 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ging | +5.794 |
keeping | +4.849 |
gers | +4.822 |
chin | +4.412 |
gin | +4.100 |
Neg logit contributions | |
ォ | -11.945 |
ploma | -11.593 |
rongh | -11.434 |
sucker | -11.319 |
sqor | -11.165 |
Token | example |
Token ID | 1672 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
ploma | +1.212 |
sucker | +1.205 |
rongh | +1.168 |
ォ | +1.154 |
babe | +1.145 |
Neg logit contributions | |
ging | -1.358 |
chin | -1.276 |
keeping | -1.232 |
�� | -1.209 |
gers | -1.182 |
Token | with |
Token ID | 351 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ging | +4.482 |
chin | +4.204 |
keeping | +4.105 |
gers | +3.943 |
�� | +3.905 |
Neg logit contributions | |
ploma | -3.716 |
sucker | -3.624 |
rongh | -3.607 |
ォ | -3.594 |
EVER | -3.431 |
Token | hope |
Token ID | 2911 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
ploma | +1.680 |
sucker | +1.674 |
rongh | +1.628 |
ォ | +1.605 |
babe | +1.603 |
Neg logit contributions | |
ging | -1.397 |
chin | -1.297 |
keeping | -1.244 |
�� | -1.227 |
gers | -1.185 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ging | +0.831 |
chin | +0.788 |
keeping | +0.766 |
�� | +0.751 |
gers | +0.742 |
Neg logit contributions | |
ploma | -0.476 |
sucker | -0.470 |
rongh | -0.454 |
ォ | -0.450 |
EVER | -0.441 |
Token | has |
Token ID | 468 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
ging | +0.198 |
chin | +0.185 |
keeping | +0.180 |
�� | +0.174 |
gers | +0.172 |
Neg logit contributions | |
ploma | -0.176 |
sucker | -0.174 |
rongh | -0.170 |
ォ | -0.169 |
babe | -0.165 |
Token | don |
Token ID | 836 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ploma | +0.274 |
sucker | +0.271 |
rongh | +0.265 |
ォ | +0.262 |
babe | +0.257 |
Neg logit contributions | |
ging | -0.349 |
chin | -0.328 |
keeping | -0.319 |
�� | -0.310 |
gers | -0.306 |
Token | ned |
Token ID | 2817 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
ging | +1.581 |
chin | +1.489 |
keeping | +1.446 |
�� | +1.406 |
gers | +1.405 |
Neg logit contributions | |
ploma | -0.982 |
sucker | -0.972 |
rongh | -0.944 |
ォ | -0.928 |
babe | -0.912 |
Token | the |
Token ID | 262 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
ploma | +0.047 |
sucker | +0.047 |
rongh | +0.046 |
ォ | +0.045 |
EVER | +0.044 |
Neg logit contributions | |
ging | -0.070 |
chin | -0.066 |
keeping | -0.064 |
�� | -0.063 |
gers | -0.062 |
Token | ble |
Token ID | 7245 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
ging | +0.230 |
chin | +0.217 |
keeping | +0.211 |
�� | +0.205 |
gers | +0.203 |
Neg logit contributions | |
ploma | -0.162 |
sucker | -0.160 |
rongh | -0.156 |
ォ | -0.154 |
babe | -0.151 |
Token | u |
Token ID | 84 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
ging | +3.884 |
chin | +3.638 |
keeping | +3.536 |
gers | +3.435 |
nutrition | +3.292 |
Neg logit contributions | |
ploma | -2.832 |
sucker | -2.777 |
ォ | -2.735 |
rongh | -2.694 |
babe | -2.641 |
Token | , |
Token ID | 11 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ging | +10.034 |
chin | +9.153 |
keeping | +8.955 |
gers | +8.836 |
gin | +8.670 |
Neg logit contributions | |
ploma | -6.698 |
ォ | -6.543 |
rongh | -6.523 |
sucker | -6.498 |
sqor | -6.421 |
Token | bl |
Token ID | 698 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
sucker | +1.039 |
ploma | +1.033 |
rongh | +0.992 |
ォ | +0.985 |
EVER | +0.979 |
Neg logit contributions | |
ging | -1.600 |
chin | -1.522 |
keeping | -1.469 |
�� | -1.448 |
gers | -1.418 |
Token | anc |
Token ID | 1192 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
ploma | +0.665 |
sucker | +0.657 |
rongh | +0.644 |
ォ | +0.637 |
EVER | +0.625 |
Neg logit contributions | |
ging | -0.730 |
chin | -0.684 |
keeping | -0.663 |
�� | -0.646 |
gers | -0.634 |
Token | , |
Token ID | 11 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
ploma | +1.671 |
sucker | +1.663 |
rongh | +1.610 |
ォ | +1.590 |
babe | +1.570 |
Neg logit contributions | |
ging | -2.700 |
chin | -2.553 |
keeping | -2.477 |
�� | -2.451 |
gers | -2.391 |
Token | et |
Token ID | 2123 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
ging | +0.145 |
chin | +0.137 |
keeping | +0.133 |
�� | +0.130 |
gers | +0.128 |
Neg logit contributions | |
ploma | -0.095 |
sucker | -0.094 |
rongh | -0.091 |
ォ | -0.090 |
babe | -0.088 |
Token | sequence |
Token ID | 8379 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
ging | +3.098 |
chin | +2.935 |
keeping | +2.877 |
gers | +2.778 |
�� | +2.709 |
Neg logit contributions | |
ploma | -1.687 |
rongh | -1.637 |
ォ | -1.620 |
sucker | -1.612 |
EVER | -1.505 |
Token | takes |
Token ID | 2753 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ging | +0.534 |
chin | +0.507 |
keeping | +0.490 |
gers | +0.467 |
keepers | +0.454 |
Neg logit contributions | |
ploma | -0.525 |
sucker | -0.516 |
ォ | -0.515 |
rongh | -0.512 |
sqor | -0.493 |
Token | place |
Token ID | 1295 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
ging | +0.975 |
chin | +0.932 |
keeping | +0.917 |
gers | +0.874 |
keepers | +0.856 |
Neg logit contributions | |
ploma | -0.578 |
rongh | -0.557 |
sucker | -0.556 |
ォ | -0.552 |
sqor | -0.515 |
Token | in |
Token ID | 287 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ging | +0.709 |
chin | +0.664 |
keeping | +0.649 |
gers | +0.617 |
�� | +0.610 |
Neg logit contributions | |
ploma | -0.639 |
sucker | -0.629 |
rongh | -0.617 |
ォ | -0.612 |
babe | -0.594 |
Token | the |
Token ID | 262 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
ging | +1.419 |
chin | +1.326 |
keeping | +1.307 |
gers | +1.246 |
�� | +1.212 |
Neg logit contributions | |
ploma | -1.122 |
sucker | -1.119 |
rongh | -1.099 |
ォ | -1.087 |
babe | -1.048 |
Token | library |
Token ID | 5888 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
ging | +2.514 |
chin | +2.348 |
keeping | +2.319 |
gers | +2.198 |
�� | +2.148 |
Neg logit contributions | |
ploma | -2.179 |
sucker | -2.134 |
ォ | -2.125 |
rongh | -2.116 |
sth | -2.027 |
Token | inside |
Token ID | 2641 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
ging | +6.798 |
keeping | +6.544 |
chin | +6.334 |
gers | +5.814 |
keepers | +5.797 |
Neg logit contributions | |
ploma | -10.541 |
ォ | -10.497 |
rongh | -10.377 |
sucker | -9.796 |
sqor | -9.587 |
Token | the |
Token ID | 262 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
ging | +3.854 |
chin | +3.575 |
keeping | +3.562 |
gers | +3.350 |
keepers | +3.263 |
Neg logit contributions | |
sucker | -3.579 |
ploma | -3.560 |
rongh | -3.544 |
ォ | -3.462 |
sqor | -3.319 |
Token | in |
Token ID | 259 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ging | +4.154 |
chin | +3.892 |
keeping | +3.808 |
gers | +3.611 |
vim | +3.534 |
Neg logit contributions | |
ploma | -4.205 |
sucker | -4.158 |
ォ | -4.093 |
rongh | -4.070 |
babe | -3.836 |
Token | Border |
Token ID | 15443 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
ploma | +0.315 |
sucker | +0.311 |
rongh | +0.304 |
ォ | +0.299 |
EVER | +0.295 |
Neg logit contributions | |
ging | -0.387 |
chin | -0.363 |
keeping | -0.353 |
�� | -0.345 |
gers | -0.339 |
Token | land |
Token ID | 1044 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ploma | +1.365 |
sucker | +1.353 |
rongh | +1.314 |
sth | +1.291 |
EVER | +1.269 |
Neg logit contributions | |
ging | -2.552 |
�� | -2.428 |
chin | -2.420 |
keeping | -2.350 |
�� | -2.318 |
Token | the |
Token ID | 262 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
sucker | +1.500 |
ploma | +1.489 |
rongh | +1.423 |
babe | +1.416 |
EVER | +1.412 |
Neg logit contributions | |
ging | -2.252 |
chin | -2.140 |
�� | -2.081 |
keeping | -2.067 |
gers | -1.994 |
Token | Ob |
Token ID | 1835 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ging | +0.272 |
chin | +0.256 |
keeping | +0.250 |
�� | +0.243 |
gers | +0.241 |
Neg logit contributions | |
ploma | -0.182 |
sucker | -0.180 |
rongh | -0.175 |
ォ | -0.173 |
babe | -0.169 |
Token | amas |
Token ID | 17485 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
ploma | +0.253 |
sucker | +0.251 |
rongh | +0.246 |
ォ | +0.245 |
babe | +0.240 |
Neg logit contributions | |
ging | -0.186 |
chin | -0.171 |
keeping | -0.165 |
�� | -0.157 |
gers | -0.156 |
Token | have |
Token ID | 423 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ging | +0.755 |
chin | +0.708 |
keeping | +0.686 |
�� | +0.668 |
gers | +0.658 |
Neg logit contributions | |
ploma | -0.659 |
sucker | -0.653 |
rongh | -0.637 |
ォ | -0.631 |
babe | -0.620 |
Token | gone |
Token ID | 3750 |
Feature activation | -7.40e+00 |
Pos logit contributions | |
ploma | +0.129 |
sucker | +0.129 |
rongh | +0.125 |
ォ | +0.123 |
EVER | +0.122 |
Neg logit contributions | |
ging | -0.166 |
chin | -0.156 |
keeping | -0.152 |
�� | -0.148 |
gers | -0.146 |
Token | all |
Token ID | 477 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
ging | +5.931 |
chin | +5.432 |
keeping | +5.421 |
gers | +5.191 |
keepers | +5.006 |
Neg logit contributions | |
ploma | -4.715 |
ォ | -4.629 |
rongh | -4.508 |
sucker | -4.380 |
sqor | -4.295 |
Token | out |
Token ID | 503 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
ging | +9.683 |
chin | +9.130 |
keeping | +8.942 |
gers | +8.369 |
keepers | +8.247 |
Neg logit contributions | |
ploma | -7.276 |
rongh | -7.092 |
ォ | -7.087 |
sth | -6.791 |
sqor | -6.611 |
Token | in |
Token ID | 287 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
ging | +2.853 |
chin | +2.676 |
keeping | +2.627 |
gers | +2.507 |
�� | +2.439 |
Neg logit contributions | |
ploma | -2.141 |
ォ | -2.063 |
rongh | -2.047 |
sucker | -2.042 |
sth | -1.967 |
Token | decor |
Token ID | 11705 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
sucker | +0.332 |
ploma | +0.331 |
rongh | +0.319 |
ォ | +0.315 |
EVER | +0.313 |
Neg logit contributions | |
ging | -0.441 |
chin | -0.417 |
keeping | -0.403 |
�� | -0.398 |
gers | -0.387 |
Token | ating |
Token ID | 803 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ging | +2.159 |
chin | +2.003 |
keeping | +1.955 |
gers | +1.865 |
�� | +1.861 |
Neg logit contributions | |
ploma | -1.915 |
sucker | -1.882 |
ォ | -1.845 |
rongh | -1.845 |
babe | -1.797 |
Token | their |
Token ID | 511 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
ging | +1.043 |
chin | +0.981 |
keeping | +0.959 |
gers | +0.922 |
�� | +0.920 |
Neg logit contributions | |
ploma | -0.711 |
sucker | -0.694 |
rongh | -0.680 |
ォ | -0.677 |
babe | -0.654 |
Token | AD |
Token ID | 2885 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
ploma | +3.506 |
sucker | +3.361 |
rongh | +3.348 |
EVER | +3.323 |
babe | +3.303 |
Neg logit contributions | |
ging | -3.967 |
�� | -3.744 |
chin | -3.727 |
keeping | -3.609 |
�� | -3.503 |
Token | U |
Token ID | 52 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
ging | +0.287 |
chin | +0.271 |
keeping | +0.264 |
�� | +0.256 |
gers | +0.255 |
Neg logit contributions | |
ploma | -0.185 |
sucker | -0.183 |
rongh | -0.178 |
ォ | -0.176 |
babe | -0.172 |
Token | ), |
Token ID | 828 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ging | +2.293 |
chin | +2.141 |
keeping | +2.091 |
�� | +2.009 |
gers | +2.003 |
Neg logit contributions | |
ploma | -1.849 |
sucker | -1.845 |
rongh | -1.789 |
ォ | -1.785 |
babe | -1.737 |
Token | which |
Token ID | 543 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
ging | +1.154 |
chin | +1.091 |
keeping | +1.063 |
�� | +1.035 |
gers | +1.025 |
Neg logit contributions | |
ploma | -0.724 |
sucker | -0.716 |
rongh | -0.695 |
ォ | -0.688 |
babe | -0.671 |
Token | was |
Token ID | 373 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
ging | +2.641 |
chin | +2.457 |
keeping | +2.366 |
gers | +2.268 |
�� | +2.226 |
Neg logit contributions | |
ploma | -2.725 |
sucker | -2.670 |
rongh | -2.648 |
ォ | -2.627 |
sth | -2.563 |
Token | led |
Token ID | 2957 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
ging | +2.133 |
chin | +1.999 |
keeping | +1.946 |
gers | +1.869 |
�� | +1.843 |
Neg logit contributions | |
ploma | -1.640 |
sucker | -1.609 |
ォ | -1.591 |
rongh | -1.590 |
babe | -1.527 |
Token | largely |
Token ID | 5688 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
ging | +6.455 |
chin | +5.599 |
keeping | +5.450 |
gers | +5.289 |
gin | +4.866 |
Neg logit contributions | |
ploma | -10.685 |
ォ | -10.500 |
rongh | -10.493 |
sucker | -10.469 |
sqor | -10.277 |
Token | by |
Token ID | 416 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
ging | +0.260 |
chin | +0.242 |
keeping | +0.232 |
�� | +0.229 |
gers | +0.220 |
Neg logit contributions | |
ploma | -0.321 |
sucker | -0.320 |
rongh | -0.312 |
ォ | -0.308 |
babe | -0.306 |
Token | members |
Token ID | 1866 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
ging | +0.185 |
chin | +0.174 |
keeping | +0.170 |
�� | +0.166 |
gers | +0.162 |
Neg logit contributions | |
ploma | -0.151 |
sucker | -0.149 |
rongh | -0.145 |
ォ | -0.144 |
babe | -0.142 |
Token | of |
Token ID | 286 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ploma | +0.278 |
sucker | +0.276 |
rongh | +0.267 |
ォ | +0.263 |
babe | +0.261 |
Neg logit contributions | |
ging | -0.398 |
chin | -0.377 |
keeping | -0.367 |
�� | -0.359 |
gers | -0.353 |
Token | smaller |
Token ID | 4833 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ging | +1.451 |
chin | +1.364 |
keeping | +1.326 |
�� | +1.282 |
gers | +1.275 |
Neg logit contributions | |
ploma | -1.106 |
sucker | -1.096 |
rongh | -1.067 |
ォ | -1.060 |
babe | -1.033 |
Token | a |
Token ID | 257 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
ging | +4.150 |
chin | +3.878 |
keeping | +3.810 |
gers | +3.643 |
�� | +3.540 |
Neg logit contributions | |
ploma | -3.293 |
rongh | -3.207 |
ォ | -3.171 |
sucker | -3.123 |
sqor | -3.018 |
Token | real |
Token ID | 1103 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
ging | +2.179 |
chin | +2.058 |
keeping | +2.003 |
gers | +1.931 |
�� | +1.931 |
Neg logit contributions | |
ploma | -1.404 |
sucker | -1.349 |
rongh | -1.346 |
ォ | -1.329 |
sth | -1.291 |
Token | actor |
Token ID | 8674 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
sucker | +0.491 |
ploma | +0.489 |
rongh | +0.471 |
ォ | +0.465 |
babe | +0.460 |
Neg logit contributions | |
ging | -0.754 |
chin | -0.713 |
keeping | -0.694 |
�� | -0.682 |
gers | -0.669 |
Token | 's |
Token ID | 338 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ging | +0.396 |
chin | +0.373 |
keeping | +0.364 |
�� | +0.351 |
gers | +0.349 |
Neg logit contributions | |
ploma | -0.283 |
sucker | -0.277 |
rongh | -0.272 |
ォ | -0.268 |
EVER | -0.262 |
Token | body |
Token ID | 1767 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ging | +1.673 |
chin | +1.577 |
keeping | +1.544 |
gers | +1.483 |
�� | +1.468 |
Neg logit contributions | |
ploma | -1.108 |
sucker | -1.068 |
rongh | -1.066 |
ォ | -1.054 |
sth | -1.019 |
Token | hidden |
Token ID | 7104 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
ging | +1.805 |
chin | +1.707 |
keeping | +1.675 |
gers | +1.610 |
�� | +1.593 |
Neg logit contributions | |
ploma | -0.976 |
rongh | -0.938 |
sucker | -0.933 |
ォ | -0.924 |
sth | -0.880 |
Token | underneath |
Token ID | 14638 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
ging | +8.582 |
keeping | +7.712 |
chin | +7.696 |
gers | +7.415 |
ience | +7.090 |
Neg logit contributions | |
ploma | -8.604 |
ォ | -8.273 |
rongh | -8.106 |
sqor | -7.754 |
sth | -7.747 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ging | +2.977 |
chin | +2.784 |
keeping | +2.712 |
gers | +2.614 |
�� | +2.590 |
Neg logit contributions | |
ploma | -2.205 |
sucker | -2.123 |
rongh | -2.105 |
ォ | -2.094 |
sth | -2.023 |
Token | bed |
Token ID | 3996 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ging | +0.115 |
chin | +0.108 |
keeping | +0.105 |
�� | +0.103 |
gers | +0.101 |
Neg logit contributions | |
ploma | -0.082 |
sucker | -0.082 |
rongh | -0.079 |
ォ | -0.078 |
babe | -0.077 |
Token | there |
Token ID | 612 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
ging | +1.008 |
chin | +0.948 |
keeping | +0.926 |
gers | +0.889 |
�� | +0.888 |
Neg logit contributions | |
ploma | -0.687 |
sucker | -0.670 |
rongh | -0.658 |
ォ | -0.654 |
EVER | -0.631 |
Token | and |
Token ID | 290 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
ging | +0.176 |
chin | +0.166 |
keeping | +0.162 |
�� | +0.157 |
gers | +0.156 |
Neg logit contributions | |
ploma | -0.114 |
sucker | -0.113 |
rongh | -0.109 |
ォ | -0.108 |
babe | -0.106 |
Token | there |
Token ID | 612 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
ging | +1.941 |
chin | +1.823 |
keeping | +1.776 |
gers | +1.706 |
�� | +1.705 |
Neg logit contributions | |
ploma | -1.511 |
sucker | -1.477 |
rongh | -1.457 |
ォ | -1.444 |
sth | -1.396 |
Token | � |
Token ID | 447 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ging | +0.411 |
chin | +0.385 |
keeping | +0.374 |
�� | +0.364 |
gers | +0.358 |
Neg logit contributions | |
ploma | -0.360 |
sucker | -0.357 |
rongh | -0.348 |
ォ | -0.344 |
EVER | -0.339 |
Token | � |
Token ID | 247 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ging | +1.118 |
chin | +1.041 |
keeping | +1.006 |
�� | +0.981 |
gers | +0.961 |
Neg logit contributions | |
ploma | -1.172 |
sucker | -1.162 |
rongh | -1.139 |
ォ | -1.128 |
babe | -1.107 |
Token | s |
Token ID | 82 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
ploma | +0.122 |
sucker | +0.121 |
rongh | +0.118 |
ォ | +0.117 |
babe | +0.115 |
Neg logit contributions | |
ging | -0.157 |
chin | -0.147 |
keeping | -0.143 |
�� | -0.140 |
gers | -0.138 |
Token | people |
Token ID | 661 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
ging | +3.107 |
chin | +2.921 |
keeping | +2.856 |
gers | +2.759 |
�� | +2.735 |
Neg logit contributions | |
ploma | -2.053 |
sucker | -1.998 |
rongh | -1.953 |
ォ | -1.942 |
sth | -1.870 |
Token | motivated |
Token ID | 13338 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
ging | +0.170 |
chin | +0.159 |
keeping | +0.155 |
�� | +0.150 |
gers | +0.149 |
Neg logit contributions | |
ploma | -0.128 |
sucker | -0.126 |
rongh | -0.123 |
ォ | -0.122 |
babe | -0.119 |
Token | , |
Token ID | 11 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
ging | +9.121 |
chin | +8.193 |
keeping | +8.133 |
gers | +8.058 |
gin | +7.675 |
Neg logit contributions | |
ploma | -7.794 |
ォ | -7.616 |
sucker | -7.483 |
rongh | -7.471 |
EVER | -7.009 |
Token | they |
Token ID | 484 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
ging | +2.704 |
chin | +2.538 |
keeping | +2.476 |
gers | +2.391 |
�� | +2.375 |
Neg logit contributions | |
ploma | -1.994 |
sucker | -1.950 |
rongh | -1.926 |
ォ | -1.922 |
babe | -1.849 |
Token | just |
Token ID | 655 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
ploma | +0.022 |
sucker | +0.022 |
rongh | +0.021 |
ォ | +0.021 |
babe | +0.021 |
Neg logit contributions | |
ging | -0.028 |
chin | -0.026 |
keeping | -0.025 |
�� | -0.024 |
gers | -0.024 |
Token | do |
Token ID | 466 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
ging | +5.970 |
chin | +5.671 |
keeping | +5.531 |
gers | +5.306 |
keepers | +5.083 |
Neg logit contributions | |
ploma | -4.926 |
rongh | -4.666 |
ォ | -4.630 |
sucker | -4.516 |
sqor | -4.434 |
Token | it |
Token ID | 340 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
ging | +2.718 |
chin | +2.567 |
keeping | +2.491 |
gers | +2.411 |
�� | +2.376 |
Neg logit contributions | |
ploma | -1.726 |
sucker | -1.692 |
rongh | -1.653 |
ォ | -1.643 |
EVER | -1.589 |
Token | BE |
Token ID | 9348 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ging | +0.738 |
chin | +0.696 |
keeping | +0.678 |
�� | +0.659 |
gers | +0.653 |
Neg logit contributions | |
ploma | -0.510 |
sucker | -0.505 |
rongh | -0.491 |
ォ | -0.486 |
babe | -0.475 |
Token | ER |
Token ID | 1137 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
ging | +1.702 |
chin | +1.602 |
keeping | +1.565 |
gers | +1.508 |
�� | +1.495 |
Neg logit contributions | |
ploma | -1.238 |
sucker | -1.235 |
rongh | -1.206 |
ォ | -1.186 |
babe | -1.160 |
Token | WITHOUT |
Token ID | 42881 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
ploma | +0.319 |
sucker | +0.316 |
ォ | +0.306 |
EVER | +0.306 |
rongh | +0.304 |
Neg logit contributions | |
ging | -0.432 |
chin | -0.408 |
keeping | -0.395 |
�� | -0.392 |
gers | -0.380 |
Token | THE |
Token ID | 3336 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
ging | +2.220 |
chin | +2.091 |
keeping | +2.044 |
gers | +1.969 |
�� | +1.965 |
Neg logit contributions | |
ploma | -1.450 |
sucker | -1.434 |
rongh | -1.398 |
ォ | -1.373 |
babe | -1.341 |
Token | QU |
Token ID | 19604 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
ploma | +1.319 |
sucker | +1.311 |
EVER | +1.301 |
ォ | +1.266 |
rongh | +1.245 |
Neg logit contributions | |
ging | -2.046 |
chin | -1.933 |
keeping | -1.882 |
�� | -1.868 |
gers | -1.813 |
Token | ANT |
Token ID | 8643 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
ging | +3.289 |
chin | +3.086 |
keeping | +3.033 |
gers | +2.913 |
�� | +2.880 |
Neg logit contributions | |
sucker | -2.249 |
ploma | -2.231 |
rongh | -2.183 |
ォ | -2.129 |
babe | -2.121 |
Token | ITY |
Token ID | 9050 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
ging | +6.842 |
chin | +6.023 |
keeping | +6.016 |
gers | +5.636 |
ience | +5.536 |
Neg logit contributions | |
sucker | -10.190 |
rongh | -10.061 |
ploma | -10.018 |
ォ | -9.530 |
babe | -9.503 |
Token | OF |
Token ID | 3963 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
ging | +0.308 |
chin | +0.291 |
keeping | +0.283 |
�� | +0.278 |
gers | +0.272 |
Neg logit contributions | |
ploma | -0.203 |
sucker | -0.201 |
rongh | -0.194 |
ォ | -0.194 |
EVER | -0.192 |
Token | A |
Token ID | 317 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
EVER | +1.873 |
ploma | +1.842 |
sucker | +1.834 |
ォ | +1.778 |
date | +1.768 |
Neg logit contributions | |
ging | -2.815 |
chin | -2.670 |
�� | -2.619 |
keeping | -2.585 |
gers | -2.496 |
Token | LC |
Token ID | 5639 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
ploma | +2.069 |
sucker | +2.056 |
EVER | +2.039 |
ォ | +1.988 |
date | +1.958 |
Neg logit contributions | |
ging | -3.095 |
chin | -2.945 |
keeping | -2.874 |
�� | -2.861 |
gers | -2.756 |
Token | OH |
Token ID | 12096 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ploma | +0.309 |
sucker | +0.304 |
rongh | +0.293 |
ォ | +0.287 |
babe | +0.278 |
Neg logit contributions | |
ging | -0.775 |
chin | -0.738 |
keeping | -0.723 |
�� | -0.706 |
gers | -0.700 |
Token | . |
Token ID | 13 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
sucker | +1.255 |
ploma | +1.249 |
rongh | +1.196 |
ォ | +1.185 |
EVER | +1.183 |
Neg logit contributions | |
ging | -2.099 |
chin | -2.004 |
�� | -1.926 |
keeping | -1.926 |
gers | -1.873 |
Token |
|
Token ID | 198 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
ploma | +0.572 |
sucker | +0.561 |
ォ | +0.549 |
rongh | +0.547 |
EVER | +0.540 |
Neg logit contributions | |
ging | -0.791 |
chin | -0.745 |
keeping | -0.723 |
�� | -0.716 |
gers | -0.698 |
Token |
|
Token ID | 198 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
ploma | +0.236 |
sucker | +0.234 |
rongh | +0.228 |
ォ | +0.226 |
babe | +0.220 |
Neg logit contributions | |
ging | -0.323 |
chin | -0.303 |
keeping | -0.296 |
gers | -0.285 |
�� | -0.282 |
Token | At |
Token ID | 2953 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ging | +0.183 |
chin | +0.172 |
keeping | +0.167 |
�� | +0.165 |
gers | +0.161 |
Neg logit contributions | |
ploma | -0.134 |
sucker | -0.132 |
rongh | -0.128 |
ォ | -0.127 |
EVER | -0.125 |
Token | an |
Token ID | 281 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
ploma | +0.578 |
sucker | +0.569 |
rongh | +0.556 |
ォ | +0.548 |
babe | +0.539 |
Neg logit contributions | |
ging | -0.875 |
chin | -0.825 |
keeping | -0.807 |
�� | -0.792 |
gers | -0.777 |
Token | all |
Token ID | 477 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
ging | +3.188 |
chin | +3.006 |
keeping | +2.923 |
gers | +2.815 |
�� | +2.813 |
Neg logit contributions | |
ploma | -2.133 |
sucker | -2.123 |
ォ | -2.084 |
rongh | -2.067 |
babe | -1.965 |
Token | - |
Token ID | 12 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
ging | +9.257 |
chin | +8.880 |
keeping | +8.450 |
gers | +8.121 |
ience | +8.016 |
Neg logit contributions | |
ploma | -7.581 |
rongh | -7.442 |
ォ | -7.377 |
sucker | -7.355 |
sth | -6.999 |
Token | India |
Token ID | 21569 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
ging | +7.580 |
chin | +7.286 |
keeping | +7.067 |
gers | +6.651 |
nutrition | +6.631 |
Neg logit contributions | |
ploma | -5.581 |
ォ | -5.483 |
sucker | -5.438 |
rongh | -5.380 |
Clause | -5.229 |
Token | level |
Token ID | 1241 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
ging | +2.559 |
chin | +2.399 |
keeping | +2.323 |
�� | +2.224 |
gers | +2.222 |
Neg logit contributions | |
ploma | -2.091 |
sucker | -2.048 |
rongh | -2.022 |
ォ | -2.002 |
EVER | -1.935 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ging | +4.744 |
chin | +4.487 |
keeping | +4.383 |
�� | +4.172 |
gers | +4.172 |
Neg logit contributions | |
ploma | -3.131 |
sucker | -3.095 |
rongh | -3.032 |
ォ | -2.973 |
EVER | -2.870 |
Token | rural |
Token ID | 10016 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ging | +1.025 |
chin | +0.964 |
keeping | +0.940 |
�� | +0.905 |
gers | +0.901 |
Neg logit contributions | |
ploma | -0.750 |
sucker | -0.740 |
rongh | -0.723 |
ォ | -0.717 |
babe | -0.697 |
Token | more |
Token ID | 517 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
ploma | +0.022 |
sucker | +0.022 |
rongh | +0.021 |
ォ | +0.021 |
babe | +0.021 |
Neg logit contributions | |
ging | -0.027 |
chin | -0.026 |
keeping | -0.025 |
�� | -0.024 |
gers | -0.024 |
Token | conventional |
Token ID | 10224 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
ging | +4.727 |
chin | +4.436 |
keeping | +4.276 |
gers | +4.122 |
�� | +3.995 |
Neg logit contributions | |
ploma | -3.582 |
rongh | -3.538 |
ォ | -3.506 |
sucker | -3.448 |
sqor | -3.315 |
Token | be |
Token ID | 307 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
ging | +2.174 |
chin | +2.046 |
keeping | +1.993 |
gers | +1.917 |
�� | +1.908 |
Neg logit contributions | |
ploma | -1.509 |
sucker | -1.453 |
rongh | -1.445 |
ォ | -1.423 |
EVER | -1.385 |
Token | aver |
Token ID | 8770 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
ging | +4.966 |
chin | +4.688 |
keeping | +4.482 |
gers | +4.349 |
ga | +4.192 |
Neg logit contributions | |
ploma | -3.953 |
sucker | -3.870 |
ォ | -3.831 |
sqor | -3.778 |
rongh | -3.767 |
Token | and |
Token ID | 290 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
ging | +2.810 |
chin | +2.639 |
keeping | +2.583 |
gers | +2.479 |
�� | +2.434 |
Neg logit contributions | |
ploma | -1.866 |
sucker | -1.781 |
rongh | -1.777 |
ォ | -1.757 |
EVER | -1.698 |
Token | fox |
Token ID | 21831 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
ging | +3.332 |
chin | +3.107 |
keeping | +3.023 |
gers | +2.925 |
�� | +2.872 |
Neg logit contributions | |
ploma | -2.410 |
ォ | -2.299 |
rongh | -2.297 |
sucker | -2.290 |
sth | -2.219 |
Token | .) |
Token ID | 2014 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ging | +9.576 |
keeping | +8.874 |
chin | +8.872 |
gers | +8.393 |
keepers | +8.135 |
Neg logit contributions | |
ploma | -7.236 |
rongh | -6.941 |
ォ | -6.902 |
Turks | -6.673 |
EVER | -6.578 |
Token | On |
Token ID | 1550 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ging | +0.160 |
chin | +0.151 |
keeping | +0.147 |
�� | +0.143 |
gers | +0.141 |
Neg logit contributions | |
ploma | -0.117 |
sucker | -0.115 |
rongh | -0.112 |
ォ | -0.111 |
babe | -0.109 |
Token | a |
Token ID | 257 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ploma | +0.713 |
sucker | +0.712 |
rongh | +0.685 |
ォ | +0.673 |
EVER | +0.666 |
Neg logit contributions | |
ging | -1.147 |
chin | -1.091 |
keeping | -1.061 |
�� | -1.043 |
gers | -1.017 |
Token | recent |
Token ID | 2274 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
ging | +1.147 |
chin | +1.080 |
keeping | +1.051 |
�� | +1.023 |
gers | +1.010 |
Neg logit contributions | |
ploma | -0.846 |
sucker | -0.839 |
rongh | -0.814 |
ォ | -0.807 |
babe | -0.791 |
Token | visit |
Token ID | 3187 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
ging | +2.861 |
chin | +2.693 |
keeping | +2.624 |
�� | +2.535 |
gers | +2.533 |
Neg logit contributions | |
ploma | -1.877 |
sucker | -1.824 |
rongh | -1.805 |
ォ | -1.787 |
EVER | -1.719 |
Token | com |
Token ID | 785 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ploma | +1.242 |
sucker | +1.222 |
rongh | +1.194 |
ォ | +1.178 |
EVER | +1.175 |
Neg logit contributions | |
ging | -1.331 |
chin | -1.236 |
keeping | -1.203 |
�� | -1.177 |
gers | -1.149 |
Token | The |
Token ID | 383 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
ging | +1.501 |
chin | +1.409 |
keeping | +1.370 |
gers | +1.324 |
�� | +1.323 |
Neg logit contributions | |
ploma | -1.077 |
sucker | -1.066 |
rongh | -1.041 |
ォ | -1.031 |
babe | -1.000 |
Token | old |
Token ID | 1468 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
ging | +3.686 |
chin | +3.437 |
keeping | +3.348 |
gers | +3.216 |
�� | +3.182 |
Neg logit contributions | |
ploma | -2.870 |
sucker | -2.828 |
rongh | -2.751 |
ォ | -2.718 |
EVER | -2.696 |
Token | building |
Token ID | 16894 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
ging | +6.253 |
chin | +5.917 |
keeping | +5.814 |
gers | +5.593 |
�� | +5.589 |
Neg logit contributions | |
ploma | -3.220 |
sucker | -3.203 |
ォ | -3.084 |
rongh | -3.066 |
babe | -2.947 |
Token | was |
Token ID | 373 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
ging | +0.434 |
chin | +0.406 |
keeping | +0.391 |
�� | +0.381 |
gers | +0.374 |
Neg logit contributions | |
ploma | -0.446 |
sucker | -0.445 |
rongh | -0.434 |
ォ | -0.431 |
babe | -0.424 |
Token | renamed |
Token ID | 25121 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
ploma | +0.365 |
sucker | +0.362 |
rongh | +0.354 |
ォ | +0.352 |
EVER | +0.345 |
Neg logit contributions | |
ging | -0.349 |
chin | -0.325 |
keeping | -0.314 |
�� | -0.306 |
gers | -0.299 |
Token | for |
Token ID | 1640 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
ging | +9.022 |
chin | +8.427 |
keeping | +8.314 |
gers | +7.939 |
gin | +7.727 |
Neg logit contributions | |
sucker | -7.516 |
ォ | -7.397 |
ploma | -7.319 |
babe | -7.032 |
EVER | -6.978 |
Token | the |
Token ID | 262 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
ging | +4.655 |
chin | +4.327 |
keeping | +4.242 |
�� | +4.081 |
gers | +4.069 |
Neg logit contributions | |
ploma | -3.571 |
sucker | -3.551 |
rongh | -3.462 |
ォ | -3.441 |
babe | -3.352 |
Token | shooting |
Token ID | 4395 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
ging | +3.577 |
keeping | +3.267 |
chin | +3.257 |
gers | +3.027 |
gin | +2.909 |
Neg logit contributions | |
ploma | -3.906 |
ォ | -3.807 |
sucker | -3.767 |
rongh | -3.754 |
Syd | -3.611 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ploma | +0.402 |
sucker | +0.399 |
rongh | +0.387 |
ォ | +0.383 |
babe | +0.373 |
Neg logit contributions | |
ging | -0.625 |
chin | -0.591 |
keeping | -0.577 |
�� | -0.556 |
gers | -0.555 |
Token |
|
Token ID | 198 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
ging | +1.267 |
chin | +1.195 |
keeping | +1.163 |
�� | +1.132 |
gers | +1.119 |
Neg logit contributions | |
ploma | -0.888 |
sucker | -0.878 |
rongh | -0.853 |
ォ | -0.845 |
babe | -0.827 |
Token | NFL |
Token ID | 5134 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ploma | +0.337 |
sucker | +0.334 |
rongh | +0.324 |
ォ | +0.320 |
EVER | +0.314 |
Neg logit contributions | |
ging | -0.479 |
chin | -0.453 |
keeping | -0.440 |
�� | -0.429 |
gers | -0.423 |
Token | may |
Token ID | 743 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ploma | +1.500 |
sucker | +1.489 |
rongh | +1.444 |
ォ | +1.423 |
EVER | +1.411 |
Neg logit contributions | |
ging | -1.982 |
chin | -1.878 |
keeping | -1.804 |
�� | -1.800 |
gers | -1.738 |
Token | have |
Token ID | 423 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ploma | +0.873 |
sucker | +0.872 |
rongh | +0.850 |
EVER | +0.834 |
ォ | +0.834 |
Neg logit contributions | |
ging | -0.922 |
chin | -0.862 |
keeping | -0.834 |
�� | -0.816 |
gers | -0.796 |
Token | used |
Token ID | 973 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
ging | +1.007 |
chin | +0.942 |
keeping | +0.922 |
gers | +0.882 |
�� | +0.877 |
Neg logit contributions | |
ploma | -0.866 |
sucker | -0.841 |
rongh | -0.838 |
ォ | -0.833 |
babe | -0.805 |
Token | a |
Token ID | 257 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ging | +0.329 |
chin | +0.311 |
keeping | +0.303 |
�� | +0.294 |
gers | +0.292 |
Neg logit contributions | |
ploma | -0.222 |
sucker | -0.219 |
rongh | -0.213 |
ォ | -0.211 |
babe | -0.206 |
Token | faire |
Token ID | 37063 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
sucker | +0.979 |
ploma | +0.977 |
rongh | +0.936 |
ォ | +0.928 |
babe | +0.918 |
Neg logit contributions | |
ging | -1.258 |
chin | -1.193 |
keeping | -1.153 |
�� | -1.133 |
gers | -1.105 |
Token | r |
Token ID | 81 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
ging | +10.664 |
keeping | +9.437 |
gers | +9.403 |
chin | +9.337 |
gin | +8.808 |
Neg logit contributions | |
rongh | -6.326 |
ploma | -6.316 |
sucker | -6.166 |
ォ | -6.128 |
Turks | -6.012 |
Token | procedure |
Token ID | 8771 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
ging | +2.289 |
chin | +2.139 |
keeping | +2.115 |
gers | +2.027 |
�� | +2.010 |
Neg logit contributions | |
ploma | -1.504 |
rongh | -1.456 |
sucker | -1.448 |
ォ | -1.441 |
sth | -1.375 |
Token | and |
Token ID | 290 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
ploma | +0.268 |
sucker | +0.265 |
rongh | +0.257 |
ォ | +0.254 |
EVER | +0.250 |
Neg logit contributions | |
ging | -0.402 |
chin | -0.380 |
keeping | -0.369 |
�� | -0.361 |
gers | -0.356 |
Token | may |
Token ID | 743 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
ging | +2.351 |
chin | +2.203 |
keeping | +2.173 |
gers | +2.078 |
�� | +2.051 |
Neg logit contributions | |
ploma | -1.815 |
rongh | -1.762 |
sucker | -1.755 |
ォ | -1.745 |
babe | -1.676 |
Token | have |
Token ID | 423 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
sucker | +2.218 |
ploma | +2.203 |
rongh | +2.145 |
date | +2.132 |
EVER | +2.130 |
Neg logit contributions | |
ging | -2.409 |
chin | -2.260 |
keeping | -2.172 |
�� | -2.170 |
nutrition | -2.084 |
Token | on |
Token ID | 319 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ging | +2.374 |
chin | +2.214 |
keeping | +2.186 |
gers | +2.095 |
�� | +2.063 |
Neg logit contributions | |
ploma | -1.652 |
sucker | -1.614 |
rongh | -1.586 |
ォ | -1.575 |
babe | -1.515 |
Token | what |
Token ID | 644 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ging | +1.970 |
chin | +1.828 |
keeping | +1.804 |
gers | +1.731 |
�� | +1.712 |
Neg logit contributions | |
ploma | -1.563 |
sucker | -1.539 |
rongh | -1.512 |
ォ | -1.498 |
babe | -1.455 |
Token | he |
Token ID | 339 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ging | +1.196 |
chin | +1.125 |
keeping | +1.095 |
�� | +1.060 |
gers | +1.051 |
Neg logit contributions | |
ploma | -0.913 |
sucker | -0.904 |
rongh | -0.881 |
ォ | -0.873 |
babe | -0.854 |
Token | called |
Token ID | 1444 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
ploma | +0.897 |
sucker | +0.892 |
rongh | +0.867 |
ォ | +0.865 |
EVER | +0.845 |
Neg logit contributions | |
ging | -1.225 |
chin | -1.149 |
keeping | -1.118 |
�� | -1.105 |
gers | -1.078 |
Token | " |
Token ID | 366 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
ging | +4.124 |
chin | +3.823 |
keeping | +3.778 |
gers | +3.622 |
�� | +3.579 |
Neg logit contributions | |
ploma | -3.032 |
sucker | -2.980 |
rongh | -2.928 |
ォ | -2.899 |
babe | -2.829 |
Token | ex |
Token ID | 1069 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
ging | +3.842 |
chin | +3.580 |
keeping | +3.518 |
gers | +3.312 |
nutrition | +3.302 |
Neg logit contributions | |
ploma | -3.446 |
sucker | -3.431 |
rongh | -3.339 |
ォ | -3.324 |
EVER | -3.260 |
Token | orbit |
Token ID | 42594 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ging | +7.948 |
chin | +7.444 |
keeping | +7.140 |
gers | +6.883 |
conn | +6.637 |
Neg logit contributions | |
ォ | -8.667 |
sucker | -8.447 |
ploma | -8.249 |
Syd | -8.224 |
babe | -8.185 |
Token | ant |
Token ID | 415 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ging | +1.439 |
chin | +1.358 |
keeping | +1.324 |
�� | +1.281 |
gers | +1.272 |
Neg logit contributions | |
ploma | -0.976 |
sucker | -0.964 |
rongh | -0.939 |
ォ | -0.934 |
babe | -0.909 |
Token | " |
Token ID | 1 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
ging | +0.205 |
chin | +0.193 |
keeping | +0.187 |
�� | +0.183 |
gers | +0.180 |
Neg logit contributions | |
ploma | -0.154 |
sucker | -0.153 |
rongh | -0.148 |
ォ | -0.147 |
babe | -0.144 |
Token | pay |
Token ID | 1414 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ging | +1.453 |
chin | +1.363 |
keeping | +1.335 |
�� | +1.282 |
gers | +1.281 |
Neg logit contributions | |
ploma | -1.056 |
sucker | -1.039 |
rongh | -1.017 |
ォ | -1.007 |
babe | -0.980 |
Token | . |
Token ID | 13 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
ging | +1.046 |
chin | +0.987 |
keeping | +0.962 |
�� | +0.936 |
gers | +0.926 |
Neg logit contributions | |
ploma | -0.693 |
sucker | -0.685 |
rongh | -0.666 |
ォ | -0.659 |
babe | -0.644 |
Token | bio |
Token ID | 13401 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
ploma | +0.362 |
sucker | +0.360 |
rongh | +0.349 |
ォ | +0.345 |
EVER | +0.339 |
Neg logit contributions | |
ging | -0.515 |
chin | -0.485 |
keeping | -0.473 |
�� | -0.462 |
gers | -0.455 |
Token | ap |
Token ID | 499 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
ging | +4.298 |
chin | +4.032 |
keeping | +3.856 |
gers | +3.687 |
gin | +3.621 |
Neg logit contributions | |
ploma | -4.274 |
sucker | -4.173 |
rongh | -4.038 |
ォ | -3.979 |
EVER | -3.964 |
Token | at |
Token ID | 265 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
ging | +0.633 |
chin | +0.587 |
keeping | +0.568 |
gers | +0.542 |
�� | +0.536 |
Neg logit contributions | |
ploma | -0.712 |
sucker | -0.707 |
rongh | -0.690 |
ォ | -0.688 |
babe | -0.678 |
Token | ite |
Token ID | 578 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
ging | +0.013 |
chin | +0.013 |
keeping | +0.012 |
�� | +0.012 |
gers | +0.012 |
Neg logit contributions | |
ploma | -0.013 |
sucker | -0.013 |
rongh | -0.012 |
ォ | -0.012 |
babe | -0.012 |
Token | ( |
Token ID | 357 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
ploma | +0.043 |
sucker | +0.042 |
rongh | +0.041 |
ォ | +0.041 |
babe | +0.040 |
Neg logit contributions | |
ging | -0.060 |
chin | -0.057 |
keeping | -0.055 |
�� | -0.054 |
gers | -0.053 |
Token | hard |
Token ID | 10424 |
Feature activation | +9.25e+00 |
Pos logit contributions | |
ging | +1.901 |
chin | +1.788 |
keeping | +1.732 |
�� | +1.667 |
gers | +1.660 |
Neg logit contributions | |
ploma | -1.552 |
sucker | -1.534 |
rongh | -1.490 |
ォ | -1.477 |
babe | -1.450 |
Token | carbon |
Token ID | 6588 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
sucker | +5.278 |
date | +5.142 |
ォ | +5.008 |
ploma | +4.977 |
babe | +4.971 |
Neg logit contributions | |
ging | -7.268 |
�� | -7.084 |
chin | -6.873 |
keeping | -6.791 |
�� | -6.721 |
Token | ate |
Token ID | 378 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
ging | +0.781 |
chin | +0.737 |
keeping | +0.718 |
�� | +0.698 |
gers | +0.691 |
Neg logit contributions | |
ploma | -0.531 |
sucker | -0.524 |
rongh | -0.510 |
ォ | -0.504 |
babe | -0.493 |
Token | bone |
Token ID | 9970 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ging | +2.075 |
chin | +1.958 |
keeping | +1.900 |
gers | +1.823 |
�� | +1.818 |
Neg logit contributions | |
ploma | -1.530 |
sucker | -1.486 |
rongh | -1.462 |
ォ | -1.441 |
babe | -1.405 |
Token | mineral |
Token ID | 18352 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
sucker | +0.870 |
ploma | +0.861 |
ォ | +0.830 |
rongh | +0.829 |
date | +0.814 |
Neg logit contributions | |
ging | -1.355 |
chin | -1.278 |
keeping | -1.249 |
�� | -1.235 |
gers | -1.203 |
Token | ) |
Token ID | 8 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ging | +2.605 |
chin | +2.446 |
keeping | +2.372 |
gers | +2.285 |
�� | +2.265 |
Neg logit contributions | |
ploma | -1.907 |
sucker | -1.846 |
rongh | -1.818 |
ォ | -1.800 |
EVER | -1.757 |
Token | isa |
Token ID | 9160 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
ging | +0.576 |
chin | +0.533 |
keeping | +0.511 |
�� | +0.491 |
gers | +0.485 |
Neg logit contributions | |
ploma | -0.737 |
sucker | -0.732 |
rongh | -0.717 |
ォ | -0.712 |
babe | -0.701 |
Token | Des |
Token ID | 2935 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
ging | +4.736 |
chin | +4.455 |
keeping | +4.296 |
gers | +4.132 |
�� | +4.129 |
Neg logit contributions | |
ploma | -3.852 |
sucker | -3.825 |
rongh | -3.744 |
ォ | -3.643 |
sqor | -3.599 |
Token | isa |
Token ID | 9160 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ging | +3.557 |
chin | +3.368 |
keeping | +3.194 |
gers | +3.103 |
�� | +3.073 |
Neg logit contributions | |
sucker | -3.155 |
ploma | -3.148 |
ォ | -3.042 |
rongh | -3.025 |
babe | -2.982 |
Token | , |
Token ID | 11 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
ging | +0.925 |
chin | +0.874 |
keeping | +0.852 |
�� | +0.830 |
gers | +0.821 |
Neg logit contributions | |
ploma | -0.591 |
sucker | -0.584 |
rongh | -0.567 |
ォ | -0.561 |
babe | -0.548 |
Token | and |
Token ID | 290 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
ploma | +0.015 |
sucker | +0.015 |
rongh | +0.014 |
ォ | +0.014 |
babe | +0.014 |
Neg logit contributions | |
ging | -0.024 |
chin | -0.023 |
keeping | -0.022 |
�� | -0.022 |
gers | -0.021 |
Token | half |
Token ID | 2063 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
ploma | +0.485 |
sucker | +0.483 |
rongh | +0.464 |
ォ | +0.459 |
babe | +0.458 |
Neg logit contributions | |
ging | -0.669 |
chin | -0.634 |
keeping | -0.616 |
�� | -0.602 |
gers | -0.591 |
Token | marathon |
Token ID | 22336 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
ploma | +5.645 |
sucker | +5.596 |
rongh | +5.457 |
babe | +5.447 |
date | +5.432 |
Neg logit contributions | |
ging | -9.164 |
�� | -8.741 |
chin | -8.734 |
keeping | -8.719 |
�� | -8.332 |
Token | world |
Token ID | 995 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
sucker | +1.750 |
ploma | +1.740 |
babe | +1.663 |
EVER | +1.631 |
ォ | +1.630 |
Neg logit contributions | |
ging | -3.099 |
chin | -2.959 |
keeping | -2.887 |
�� | -2.867 |
nutrition | -2.779 |
Token | record |
Token ID | 1700 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
ploma | +1.172 |
sucker | +1.168 |
ォ | +1.114 |
babe | +1.112 |
rongh | +1.106 |
Neg logit contributions | |
ging | -2.500 |
chin | -2.379 |
keeping | -2.322 |
�� | -2.301 |
gers | -2.257 |
Token | - |
Token ID | 12 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
sucker | +3.242 |
ploma | +3.150 |
babe | +3.079 |
date | +3.073 |
ォ | +3.055 |
Neg logit contributions | |
ging | -5.023 |
chin | -4.797 |
�� | -4.760 |
keeping | -4.517 |
�� | -4.514 |
Token | holder |
Token ID | 13829 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
ploma | +0.857 |
sucker | +0.855 |
rongh | +0.826 |
ォ | +0.815 |
babe | +0.809 |
Neg logit contributions | |
ging | -1.274 |
chin | -1.205 |
�� | -1.174 |
keeping | -1.160 |
gers | -1.129 |
Token | walks |
Token ID | 11114 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ging | +0.050 |
chin | +0.047 |
keeping | +0.046 |
�� | +0.045 |
gers | +0.044 |
Neg logit contributions | |
ploma | -0.035 |
sucker | -0.035 |
rongh | -0.034 |
ォ | -0.034 |
babe | -0.033 |
Token | through |
Token ID | 832 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
ploma | +0.142 |
sucker | +0.142 |
rongh | +0.137 |
ォ | +0.135 |
babe | +0.134 |
Neg logit contributions | |
ging | -0.182 |
chin | -0.172 |
keeping | -0.167 |
�� | -0.164 |
gers | -0.160 |
Token | the |
Token ID | 262 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
sucker | +1.772 |
ploma | +1.761 |
rongh | +1.715 |
Turks | +1.697 |
babe | +1.669 |
Neg logit contributions | |
ging | -2.343 |
chin | -2.232 |
keeping | -2.164 |
�� | -2.146 |
gers | -2.078 |
Token | countryside |
Token ID | 25708 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
sucker | +0.319 |
ploma | +0.319 |
rongh | +0.309 |
ォ | +0.303 |
babe | +0.301 |
Neg logit contributions | |
ging | -0.452 |
chin | -0.428 |
keeping | -0.416 |
�� | -0.409 |
gers | -0.400 |
Token | , |
Token ID | 11 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
sucker | +1.232 |
ploma | +1.204 |
rongh | +1.174 |
babe | +1.157 |
Turks | +1.151 |
Neg logit contributions | |
ging | -2.011 |
chin | -1.925 |
�� | -1.856 |
keeping | -1.854 |
gers | -1.796 |
Token | sn |
Token ID | 3013 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
sucker | +0.542 |
ploma | +0.535 |
rongh | +0.517 |
babe | +0.512 |
Turks | +0.509 |
Neg logit contributions | |
ging | -0.792 |
chin | -0.750 |
keeping | -0.730 |
�� | -0.729 |
gers | -0.704 |
Token | or |
Token ID | 273 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
rongh | +3.512 |
ploma | +3.327 |
sucker | +3.104 |
ickers | +2.990 |
date | +2.964 |
Neg logit contributions | |
�� | -9.877 |
ging | -9.630 |
�� | -9.375 |
chin | -9.357 |
keeping | -9.266 |
Token | ke |
Token ID | 365 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
ging | +1.869 |
chin | +1.717 |
keeping | +1.649 |
gers | +1.572 |
nutrition | +1.503 |
Neg logit contributions | |
sucker | -2.416 |
ploma | -2.396 |
ォ | -2.343 |
rongh | -2.341 |
sqor | -2.316 |
Token | lling |
Token ID | 2680 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
sucker | +3.396 |
ploma | +3.383 |
rongh | +3.327 |
ォ | +3.248 |
babe | +3.247 |
Neg logit contributions | |
ging | -2.036 |
�� | -1.944 |
chin | -1.938 |
keeping | -1.815 |
�� | -1.781 |
Token | over |
Token ID | 625 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
sucker | +3.071 |
Turks | +2.934 |
ploma | +2.916 |
date | +2.880 |
babe | +2.873 |
Neg logit contributions | |
ging | -4.747 |
chin | -4.557 |
�� | -4.521 |
keeping | -4.431 |
�� | -4.288 |
Token | coral |
Token ID | 29537 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
sucker | +3.667 |
Turks | +3.556 |
ploma | +3.533 |
rongh | +3.531 |
date | +3.428 |
Neg logit contributions | |
ging | -5.152 |
chin | -4.919 |
�� | -4.906 |
keeping | -4.858 |
gers | -4.620 |
Token | people |
Token ID | 661 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ging | +2.387 |
chin | +2.231 |
keeping | +2.174 |
gers | +2.098 |
�� | +2.076 |
Neg logit contributions | |
ploma | -1.815 |
sucker | -1.755 |
rongh | -1.739 |
ォ | -1.725 |
sth | -1.676 |
Token | as |
Token ID | 355 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
sucker | +1.102 |
ploma | +1.093 |
rongh | +1.046 |
ォ | +1.044 |
babe | +1.040 |
Neg logit contributions | |
ging | -1.676 |
chin | -1.587 |
keeping | -1.535 |
�� | -1.526 |
gers | -1.490 |
Token | this |
Token ID | 428 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
ging | +0.241 |
chin | +0.227 |
keeping | +0.221 |
�� | +0.216 |
gers | +0.212 |
Neg logit contributions | |
sucker | -0.176 |
ploma | -0.176 |
rongh | -0.169 |
ォ | -0.168 |
babe | -0.166 |
Token | sort |
Token ID | 3297 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
ploma | +0.275 |
sucker | +0.275 |
rongh | +0.265 |
ォ | +0.262 |
babe | +0.259 |
Neg logit contributions | |
ging | -0.411 |
chin | -0.389 |
keeping | -0.378 |
�� | -0.371 |
gers | -0.364 |
Token | of |
Token ID | 286 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
ploma | +1.909 |
sucker | +1.898 |
rongh | +1.836 |
ォ | +1.809 |
EVER | +1.799 |
Neg logit contributions | |
ging | -2.863 |
chin | -2.700 |
�� | -2.654 |
keeping | -2.618 |
gers | -2.538 |
Token | Mid |
Token ID | 7215 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
ging | +0.678 |
chin | +0.640 |
keeping | +0.624 |
�� | +0.608 |
gers | +0.601 |
Neg logit contributions | |
ploma | -0.458 |
sucker | -0.453 |
rongh | -0.440 |
ォ | -0.435 |
babe | -0.426 |
Token | western |
Token ID | 14197 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
ploma | +6.035 |
sucker | +5.933 |
date | +5.897 |
sth | +5.892 |
Syd | +5.829 |
Neg logit contributions | |
ging | -7.913 |
�� | -7.782 |
keeping | -7.645 |
chin | -7.571 |
nutrition | -7.200 |
Token | ice |
Token ID | 4771 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
sucker | +3.617 |
babe | +3.534 |
ploma | +3.478 |
date | +3.450 |
Syd | +3.339 |
Neg logit contributions | |
ging | -5.457 |
chin | -5.225 |
�� | -5.213 |
keeping | -5.147 |
gers | -4.889 |
Token | - |
Token ID | 12 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
sucker | +2.494 |
ploma | +2.424 |
babe | +2.413 |
ォ | +2.329 |
date | +2.323 |
Neg logit contributions | |
ging | -4.171 |
chin | -3.936 |
�� | -3.898 |
keeping | -3.824 |
gers | -3.686 |
Token | f |
Token ID | 69 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
sucker | +1.256 |
ploma | +1.250 |
rongh | +1.205 |
babe | +1.201 |
ォ | +1.198 |
Neg logit contributions | |
ging | -1.729 |
chin | -1.616 |
�� | -1.598 |
keeping | -1.575 |
gers | -1.528 |
Token | ishing |
Token ID | 3929 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ging | +1.804 |
chin | +1.684 |
keeping | +1.643 |
gers | +1.577 |
�� | +1.558 |
Neg logit contributions | |
ploma | -1.482 |
sucker | -1.472 |
ォ | -1.439 |
rongh | -1.429 |
babe | -1.395 |
Token | the |
Token ID | 262 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ging | +0.043 |
chin | +0.040 |
keeping | +0.039 |
gers | +0.038 |
�� | +0.038 |
Neg logit contributions | |
ploma | -0.031 |
sucker | -0.031 |
rongh | -0.030 |
ォ | -0.030 |
babe | -0.029 |
Token | main |
Token ID | 1388 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ploma | +1.458 |
sucker | +1.450 |
rongh | +1.406 |
ォ | +1.389 |
EVER | +1.379 |
Neg logit contributions | |
ging | -1.571 |
chin | -1.475 |
keeping | -1.425 |
�� | -1.402 |
gers | -1.365 |
Token | story |
Token ID | 1621 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
ploma | +0.782 |
sucker | +0.771 |
rongh | +0.748 |
ォ | +0.742 |
babe | +0.720 |
Neg logit contributions | |
ging | -1.363 |
chin | -1.290 |
keeping | -1.259 |
�� | -1.224 |
gers | -1.216 |
Token | Please |
Token ID | 4222 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
ging | +4.511 |
chin | +4.269 |
keeping | +4.222 |
gers | +3.944 |
keepers | +3.828 |
Neg logit contributions | |
rongh | -4.366 |
ォ | -4.358 |
sqor | -4.290 |
sucker | -4.282 |
ploma | -4.231 |
Token | verify |
Token ID | 11767 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
ging | +5.764 |
chin | +5.327 |
keeping | +5.280 |
gers | +5.074 |
keepers | +4.846 |
Neg logit contributions | |
sucker | -3.552 |
ploma | -3.529 |
ォ | -3.512 |
rongh | -3.499 |
sth | -3.444 |
Token | you |
Token ID | 345 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
ging | +1.667 |
chin | +1.547 |
keeping | +1.510 |
gers | +1.437 |
�� | +1.400 |
Neg logit contributions | |
ploma | -1.670 |
sucker | -1.650 |
ォ | -1.639 |
rongh | -1.631 |
babe | -1.578 |
Token | 're |
Token ID | 821 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
date | +4.068 |
sucker | +3.982 |
ploma | +3.894 |
rongh | +3.862 |
EVER | +3.799 |
Neg logit contributions | |
ging | -10.227 |
�� | -9.969 |
chin | -9.773 |
�� | -9.729 |
keeping | -9.400 |
Token | not |
Token ID | 407 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
sucker | +2.630 |
ploma | +2.614 |
date | +2.496 |
EVER | +2.461 |
babe | +2.455 |
Neg logit contributions | |
ging | -5.828 |
chin | -5.577 |
�� | -5.471 |
keeping | -5.353 |
�� | -5.307 |
Token | a |
Token ID | 257 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
ploma | +0.495 |
sucker | +0.489 |
rongh | +0.479 |
ォ | +0.476 |
babe | +0.461 |
Neg logit contributions | |
ging | -0.642 |
chin | -0.603 |
keeping | -0.589 |
gers | -0.563 |
�� | -0.563 |
Token | robot |
Token ID | 9379 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
ploma | +2.073 |
sucker | +2.043 |
rongh | +1.992 |
ォ | +1.972 |
EVER | +1.917 |
Neg logit contributions | |
ging | -3.448 |
chin | -3.261 |
keeping | -3.181 |
�� | -3.081 |
gers | -3.064 |
Token | by |
Token ID | 416 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ging | +2.025 |
chin | +1.786 |
keeping | +1.774 |
gers | +1.677 |
keepers | +1.568 |
Neg logit contributions | |
ploma | -3.353 |
sucker | -3.269 |
ォ | -3.268 |
rongh | -3.253 |
sth | -3.151 |
Token | � |
Token ID | 247 |
Feature activation | -7.63e-02 |
Pos logit contributions | |
ploma | +0.219 |
sucker | +0.217 |
rongh | +0.211 |
ォ | +0.209 |
babe | +0.205 |
Neg logit contributions | |
ging | -0.270 |
chin | -0.254 |
keeping | -0.247 |
�� | -0.240 |
gers | -0.237 |
Token | s |
Token ID | 82 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
ging | +0.068 |
chin | +0.065 |
keeping | +0.063 |
�� | +0.062 |
gers | +0.061 |
Neg logit contributions | |
ploma | -0.042 |
sucker | -0.041 |
rongh | -0.040 |
ォ | -0.039 |
EVER | -0.039 |
Token | his |
Token ID | 465 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ging | +2.771 |
chin | +2.603 |
keeping | +2.532 |
gers | +2.431 |
�� | +2.406 |
Neg logit contributions | |
ploma | -2.162 |
sucker | -2.115 |
rongh | -2.108 |
ォ | -2.083 |
babe | -2.006 |
Token | � |
Token ID | 564 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
ging | +1.112 |
chin | +1.045 |
keeping | +1.018 |
�� | +0.981 |
gers | +0.977 |
Neg logit contributions | |
ploma | -0.855 |
sucker | -0.838 |
rongh | -0.824 |
ォ | -0.816 |
EVER | -0.794 |
Token | � |
Token ID | 250 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ging | +3.854 |
chin | +3.607 |
keeping | +3.470 |
�� | +3.435 |
�� | +3.292 |
Neg logit contributions | |
sucker | -4.670 |
ploma | -4.635 |
rongh | -4.582 |
ォ | -4.455 |
sth | -4.443 |
Token | stem |
Token ID | 927 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ploma | +0.736 |
sucker | +0.727 |
rongh | +0.711 |
ォ | +0.700 |
sth | +0.698 |
Neg logit contributions | |
ging | -0.833 |
chin | -0.776 |
�� | -0.762 |
keeping | -0.751 |
gers | -0.727 |
Token | , |
Token ID | 11 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
ploma | +1.449 |
sucker | +1.443 |
ォ | +1.401 |
rongh | +1.389 |
EVER | +1.367 |
Neg logit contributions | |
ging | -1.686 |
chin | -1.587 |
keeping | -1.536 |
�� | -1.510 |
gers | -1.480 |
Token | � |
Token ID | 447 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
sucker | +0.409 |
ploma | +0.408 |
rongh | +0.391 |
ォ | +0.389 |
babe | +0.386 |
Neg logit contributions | |
ging | -0.614 |
chin | -0.581 |
keeping | -0.563 |
�� | -0.555 |
gers | -0.546 |
Token | � |
Token ID | 251 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
ging | +0.595 |
chin | +0.552 |
keeping | +0.535 |
�� | +0.521 |
gers | +0.509 |
Neg logit contributions | |
ploma | -0.646 |
sucker | -0.643 |
rongh | -0.627 |
ォ | -0.619 |
babe | -0.611 |
Token | or |
Token ID | 393 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
ging | +2.529 |
chin | +2.372 |
keeping | +2.326 |
gers | +2.229 |
�� | +2.218 |
Neg logit contributions | |
ploma | -1.765 |
sucker | -1.719 |
rongh | -1.696 |
ォ | -1.681 |
babe | -1.618 |
Token | the |
Token ID | 262 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ging | +2.783 |
chin | +2.630 |
keeping | +2.552 |
�� | +2.458 |
gers | +2.446 |
Neg logit contributions | |
ploma | -1.929 |
sucker | -1.885 |
rongh | -1.866 |
ォ | -1.835 |
sth | -1.780 |
Token | our |
Token ID | 674 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ploma | +0.423 |
sucker | +0.418 |
rongh | +0.406 |
ォ | +0.402 |
babe | +0.393 |
Neg logit contributions | |
ging | -0.634 |
chin | -0.598 |
keeping | -0.582 |
�� | -0.568 |
gers | -0.561 |
Token | first |
Token ID | 717 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
ging | +1.128 |
chin | +1.058 |
keeping | +1.030 |
�� | +0.995 |
gers | +0.992 |
Neg logit contributions | |
ploma | -0.846 |
sucker | -0.829 |
rongh | -0.812 |
ォ | -0.808 |
EVER | -0.784 |
Token | idea |
Token ID | 2126 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ploma | +0.124 |
sucker | +0.122 |
rongh | +0.119 |
ォ | +0.118 |
babe | +0.115 |
Neg logit contributions | |
ging | -0.177 |
chin | -0.167 |
keeping | -0.163 |
�� | -0.158 |
gers | -0.157 |
Token | was |
Token ID | 373 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
sucker | +1.589 |
ploma | +1.578 |
rongh | +1.528 |
ォ | +1.518 |
EVER | +1.511 |
Neg logit contributions | |
ging | -1.682 |
chin | -1.577 |
keeping | -1.521 |
�� | -1.502 |
gers | -1.463 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ploma | +0.262 |
sucker | +0.260 |
rongh | +0.252 |
ォ | +0.249 |
EVER | +0.244 |
Neg logit contributions | |
ging | -0.404 |
chin | -0.383 |
keeping | -0.372 |
�� | -0.364 |
gers | -0.359 |
Token | seek |
Token ID | 5380 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ging | +0.993 |
chin | +0.932 |
keeping | +0.905 |
gers | +0.874 |
�� | +0.872 |
Neg logit contributions | |
ploma | -0.789 |
sucker | -0.769 |
rongh | -0.757 |
ォ | -0.751 |
sth | -0.731 |
Token | an |
Token ID | 281 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ploma | +0.916 |
sucker | +0.912 |
rongh | +0.882 |
ォ | +0.867 |
EVER | +0.855 |
Neg logit contributions | |
ging | -1.422 |
chin | -1.351 |
keeping | -1.313 |
�� | -1.285 |
gers | -1.266 |
Token | over |
Token ID | 625 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ploma | +1.522 |
sucker | +1.514 |
rongh | +1.476 |
EVER | +1.447 |
babe | +1.430 |
Neg logit contributions | |
ging | -1.932 |
chin | -1.820 |
keeping | -1.767 |
�� | -1.723 |
gers | -1.689 |
Token | - |
Token ID | 12 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
ploma | +1.373 |
sucker | +1.369 |
rongh | +1.334 |
ォ | +1.316 |
EVER | +1.295 |
Neg logit contributions | |
ging | -1.733 |
chin | -1.625 |
keeping | -1.584 |
�� | -1.549 |
gers | -1.523 |
Token | the |
Token ID | 1169 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
sucker | +3.655 |
ploma | +3.612 |
rongh | +3.577 |
sth | +3.535 |
date | +3.485 |
Neg logit contributions | |
ging | -3.824 |
�� | -3.622 |
chin | -3.558 |
keeping | -3.451 |
�� | -3.398 |
Token | - |
Token ID | 12 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ploma | +2.691 |
sucker | +2.682 |
rongh | +2.594 |
sth | +2.582 |
date | +2.566 |
Neg logit contributions | |
ging | -3.995 |
chin | -3.771 |
�� | -3.733 |
keeping | -3.670 |
gers | -3.540 |
Token | up |
Token ID | 510 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
ging | +0.242 |
chin | +0.227 |
keeping | +0.221 |
�� | +0.215 |
gers | +0.209 |
Neg logit contributions | |
ploma | -0.237 |
sucker | -0.236 |
rongh | -0.228 |
ォ | -0.227 |
babe | -0.224 |
Token | references |
Token ID | 10288 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
sucker | +1.587 |
ploma | +1.564 |
rongh | +1.488 |
date | +1.486 |
ォ | +1.482 |
Neg logit contributions | |
ging | -2.608 |
chin | -2.479 |
�� | -2.414 |
keeping | -2.406 |
�� | -2.338 |
Token | to |
Token ID | 284 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
ploma | +0.009 |
sucker | +0.009 |
rongh | +0.009 |
ォ | +0.009 |
EVER | +0.009 |
Neg logit contributions | |
ging | -0.015 |
chin | -0.015 |
keeping | -0.014 |
�� | -0.014 |
gers | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
ging | +2.128 |
chin | +1.994 |
keeping | +1.948 |
gers | +1.882 |
�� | +1.861 |
Neg logit contributions | |
ploma | -1.521 |
sucker | -1.485 |
rongh | -1.463 |
ォ | -1.454 |
sth | -1.405 |
Token | Franklin |
Token ID | 14021 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ging | +0.193 |
chin | +0.182 |
keeping | +0.178 |
�� | +0.173 |
gers | +0.171 |
Neg logit contributions | |
ploma | -0.134 |
sucker | -0.132 |
rongh | -0.129 |
ォ | -0.128 |
babe | -0.124 |
Token | Institute |
Token ID | 5136 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
sucker | +1.448 |
ploma | +1.444 |
rongh | +1.392 |
ォ | +1.383 |
babe | +1.374 |
Neg logit contributions | |
ging | -1.755 |
chin | -1.651 |
keeping | -1.592 |
�� | -1.570 |
gers | -1.527 |
Token | � |
Token ID | 447 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
sucker | +1.809 |
ploma | +1.792 |
rongh | +1.725 |
ォ | +1.705 |
date | +1.697 |
Neg logit contributions | |
ging | -3.040 |
chin | -2.885 |
�� | -2.792 |
keeping | -2.780 |
nutrition | -2.716 |
Token | � |
Token ID | 247 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
ploma | +0.591 |
sucker | +0.586 |
rongh | +0.573 |
ォ | +0.569 |
babe | +0.559 |
Neg logit contributions | |
ging | -0.539 |
chin | -0.501 |
keeping | -0.484 |
�� | -0.468 |
gers | -0.461 |
Token | s |
Token ID | 82 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
ging | +1.752 |
chin | +1.652 |
keeping | +1.616 |
gers | +1.551 |
�� | +1.545 |
Neg logit contributions | |
ploma | -1.186 |
sucker | -1.173 |
rongh | -1.133 |
ォ | -1.129 |
babe | -1.104 |
Token | autom |
Token ID | 3557 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ging | +0.649 |
chin | +0.612 |
keeping | +0.596 |
�� | +0.578 |
gers | +0.573 |
Neg logit contributions | |
ploma | -0.459 |
sucker | -0.453 |
rongh | -0.441 |
ォ | -0.437 |
babe | -0.427 |
Token | aton |
Token ID | 13951 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
ging | +0.884 |
chin | +0.819 |
keeping | +0.791 |
�� | +0.758 |
gers | +0.752 |
Neg logit contributions | |
ploma | -1.041 |
sucker | -1.036 |
rongh | -1.011 |
ォ | -1.007 |
babe | -0.991 |
Token | world |
Token ID | 995 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ploma | +2.258 |
sucker | +2.249 |
date | +2.169 |
rongh | +2.157 |
EVER | +2.139 |
Neg logit contributions | |
ging | -3.675 |
chin | -3.520 |
keeping | -3.360 |
�� | -3.346 |
�� | -3.250 |
Token | 's |
Token ID | 338 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ging | +1.264 |
chin | +1.192 |
keeping | +1.161 |
�� | +1.119 |
gers | +1.119 |
Neg logit contributions | |
ploma | -0.882 |
sucker | -0.867 |
rongh | -0.850 |
ォ | -0.841 |
babe | -0.817 |
Token | first |
Token ID | 717 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
ging | +0.164 |
chin | +0.155 |
keeping | +0.151 |
�� | +0.147 |
gers | +0.146 |
Neg logit contributions | |
ploma | -0.103 |
sucker | -0.101 |
rongh | -0.098 |
ォ | -0.097 |
babe | -0.095 |
Token | functioning |
Token ID | 15025 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
sucker | +1.282 |
ploma | +1.280 |
rongh | +1.224 |
EVER | +1.218 |
ォ | +1.208 |
Neg logit contributions | |
ging | -1.834 |
chin | -1.732 |
keeping | -1.678 |
�� | -1.658 |
gers | -1.614 |
Token | carbon |
Token ID | 6588 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
sucker | +2.263 |
ploma | +2.227 |
date | +2.160 |
EVER | +2.135 |
rongh | +2.131 |
Neg logit contributions | |
ging | -3.225 |
chin | -3.057 |
�� | -2.960 |
keeping | -2.944 |
gers | -2.835 |
Token | trading |
Token ID | 7313 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
sucker | +2.539 |
ploma | +2.481 |
ォ | +2.414 |
date | +2.414 |
rongh | +2.399 |
Neg logit contributions | |
ging | -3.523 |
chin | -3.333 |
�� | -3.243 |
keeping | -3.201 |
gers | -3.091 |
Token | scheme |
Token ID | 7791 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
sucker | +3.779 |
date | +3.697 |
ploma | +3.636 |
rongh | +3.572 |
babe | +3.538 |
Neg logit contributions | |
ging | -5.443 |
chin | -5.213 |
�� | -5.211 |
keeping | -4.957 |
�� | -4.922 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
sucker | +3.364 |
ploma | +3.333 |
rongh | +3.258 |
date | +3.246 |
EVER | +3.209 |
Neg logit contributions | |
ging | -6.485 |
chin | -6.209 |
�� | -5.984 |
keeping | -5.935 |
nutrition | -5.867 |
Token | deployed |
Token ID | 12380 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
ploma | +0.807 |
sucker | +0.806 |
rongh | +0.775 |
ォ | +0.768 |
babe | +0.761 |
Neg logit contributions | |
ging | -1.092 |
chin | -1.032 |
keeping | -0.997 |
�� | -0.984 |
gers | -0.961 |
Token | its |
Token ID | 663 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ploma | +1.363 |
sucker | +1.360 |
rongh | +1.308 |
ォ | +1.284 |
EVER | +1.278 |
Neg logit contributions | |
ging | -2.055 |
chin | -1.953 |
keeping | -1.887 |
�� | -1.873 |
gers | -1.815 |
Token | first |
Token ID | 717 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
sucker | +1.266 |
ploma | +1.263 |
rongh | +1.217 |
ォ | +1.197 |
babe | +1.190 |
Neg logit contributions | |
ging | -1.804 |
chin | -1.710 |
keeping | -1.654 |
�� | -1.633 |
gers | -1.587 |
Token | there |
Token ID | 612 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
ging | +1.528 |
chin | +1.432 |
keeping | +1.397 |
gers | +1.347 |
�� | +1.335 |
Neg logit contributions | |
ploma | -1.115 |
sucker | -1.089 |
rongh | -1.071 |
ォ | -1.071 |
babe | -1.031 |
Token | will |
Token ID | 481 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ging | +0.495 |
chin | +0.465 |
keeping | +0.451 |
�� | +0.440 |
gers | +0.432 |
Neg logit contributions | |
ploma | -0.437 |
sucker | -0.433 |
rongh | -0.422 |
ォ | -0.417 |
EVER | -0.411 |
Token | be |
Token ID | 307 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
ging | +0.941 |
chin | +0.884 |
keeping | +0.859 |
�� | +0.836 |
gers | +0.823 |
Neg logit contributions | |
ploma | -0.775 |
sucker | -0.769 |
rongh | -0.748 |
ォ | -0.739 |
EVER | -0.731 |
Token | a |
Token ID | 257 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ging | +4.173 |
chin | +3.860 |
keeping | +3.818 |
gers | +3.698 |
�� | +3.563 |
Neg logit contributions | |
ploma | -2.733 |
ォ | -2.633 |
rongh | -2.600 |
sucker | -2.598 |
babe | -2.479 |
Token | pre |
Token ID | 662 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ging | +1.629 |
chin | +1.527 |
keeping | +1.488 |
gers | +1.435 |
�� | +1.433 |
Neg logit contributions | |
ploma | -1.178 |
sucker | -1.148 |
rongh | -1.131 |
ォ | -1.125 |
babe | -1.091 |
Token | - |
Token ID | 12 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
sucker | +1.532 |
ploma | +1.515 |
rongh | +1.462 |
date | +1.444 |
EVER | +1.429 |
Neg logit contributions | |
ging | -2.437 |
chin | -2.307 |
�� | -2.259 |
keeping | -2.256 |
gers | -2.162 |
Token | order |
Token ID | 2875 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
sucker | +1.325 |
ploma | +1.323 |
rongh | +1.273 |
sth | +1.235 |
ォ | +1.233 |
Neg logit contributions | |
ging | -2.413 |
chin | -2.296 |
�� | -2.265 |
keeping | -2.231 |
gers | -2.163 |
Token | through |
Token ID | 832 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
ploma | +0.691 |
sucker | +0.685 |
rongh | +0.664 |
ォ | +0.658 |
EVER | +0.644 |
Neg logit contributions | |
ging | -0.992 |
chin | -0.936 |
keeping | -0.911 |
�� | -0.889 |
gers | -0.877 |
Token |
|
Token ID | 198 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
ploma | +0.209 |
sucker | +0.206 |
rongh | +0.201 |
ォ | +0.199 |
babe | +0.195 |
Neg logit contributions | |
ging | -0.268 |
chin | -0.252 |
keeping | -0.245 |
�� | -0.238 |
gers | -0.235 |
Token |
|
Token ID | 198 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
ploma | +0.512 |
sucker | +0.507 |
rongh | +0.493 |
ォ | +0.488 |
babe | +0.477 |
Neg logit contributions | |
ging | -0.724 |
chin | -0.683 |
keeping | -0.665 |
�� | -0.644 |
gers | -0.640 |
Token | UPDATE |
Token ID | 16977 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ploma | +0.428 |
sucker | +0.422 |
rongh | +0.412 |
ォ | +0.405 |
sth | +0.402 |
Neg logit contributions | |
ging | -0.557 |
chin | -0.524 |
keeping | -0.510 |
�� | -0.507 |
gers | -0.491 |
Token | least |
Token ID | 1551 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
sucker | +1.213 |
ploma | +1.209 |
rongh | +1.171 |
ォ | +1.150 |
babe | +1.140 |
Neg logit contributions | |
ging | -1.998 |
chin | -1.891 |
keeping | -1.847 |
�� | -1.828 |
gers | -1.773 |
Token | one |
Token ID | 530 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ging | +2.125 |
chin | +1.993 |
keeping | +1.956 |
gers | +1.866 |
�� | +1.849 |
Neg logit contributions | |
ploma | -1.673 |
sucker | -1.607 |
rongh | -1.602 |
ォ | -1.587 |
sth | -1.539 |
Token | v |
Token ID | 410 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
sucker | +0.586 |
ploma | +0.579 |
rongh | +0.559 |
ォ | +0.552 |
babe | +0.546 |
Neg logit contributions | |
ging | -0.921 |
chin | -0.873 |
keeping | -0.846 |
�� | -0.834 |
gers | -0.818 |
Token | ort |
Token ID | 419 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
ploma | +0.742 |
sucker | +0.736 |
rongh | +0.721 |
ォ | +0.711 |
EVER | +0.699 |
Neg logit contributions | |
ging | -0.742 |
chin | -0.692 |
keeping | -0.671 |
�� | -0.654 |
gers | -0.641 |
Token | on |
Token ID | 261 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
ging | +1.591 |
chin | +1.507 |
keeping | +1.469 |
�� | +1.418 |
gers | +1.418 |
Neg logit contributions | |
ploma | -0.916 |
sucker | -0.893 |
ォ | -0.874 |
rongh | -0.873 |
EVER | -0.840 |
Token | per |
Token ID | 583 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
ging | +1.911 |
chin | +1.785 |
keeping | +1.767 |
gers | +1.689 |
�� | +1.664 |
Neg logit contributions | |
ploma | -1.312 |
sucker | -1.255 |
rongh | -1.244 |
ォ | -1.242 |
sth | -1.188 |
Token | cell |
Token ID | 2685 |
Feature activation | -7.75e+00 |
Pos logit contributions | |
ging | +0.446 |
chin | +0.419 |
keeping | +0.407 |
�� | +0.394 |
gers | +0.391 |
Neg logit contributions | |
ploma | -0.364 |
sucker | -0.358 |
rongh | -0.350 |
ォ | -0.348 |
EVER | -0.340 |
Token | , |
Token ID | 11 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
ging | +6.130 |
keeping | +5.730 |
chin | +5.726 |
gers | +5.268 |
gin | +5.251 |
Neg logit contributions | |
ploma | -4.971 |
ォ | -4.649 |
rongh | -4.594 |
sucker | -4.506 |
sth | -4.384 |
Token | spontaneously |
Token ID | 37512 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ging | +2.518 |
chin | +2.343 |
keeping | +2.334 |
gers | +2.209 |
�� | +2.175 |
Neg logit contributions | |
ploma | -1.813 |
sucker | -1.740 |
ォ | -1.720 |
rongh | -1.717 |
sth | -1.658 |
Token | creating |
Token ID | 4441 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
sucker | +1.025 |
ploma | +1.002 |
ォ | +0.979 |
rongh | +0.974 |
EVER | +0.961 |
Neg logit contributions | |
ging | -1.488 |
chin | -1.416 |
�� | -1.371 |
keeping | -1.362 |
gers | -1.324 |
Token | v |
Token ID | 410 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
sucker | +1.993 |
ploma | +1.897 |
rongh | +1.861 |
EVER | +1.851 |
babe | +1.841 |
Neg logit contributions | |
ging | -2.901 |
chin | -2.775 |
�� | -2.710 |
keeping | -2.668 |
�� | -2.571 |
Token | his |
Token ID | 465 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
sucker | +1.396 |
ploma | +1.385 |
rongh | +1.331 |
ォ | +1.317 |
babe | +1.308 |
Neg logit contributions | |
ging | -2.207 |
chin | -2.096 |
keeping | -2.035 |
�� | -2.014 |
gers | -1.960 |
Token | way |
Token ID | 835 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
sucker | +1.315 |
ploma | +1.311 |
rongh | +1.249 |
babe | +1.235 |
ォ | +1.235 |
Neg logit contributions | |
ging | -2.053 |
chin | -1.948 |
keeping | -1.891 |
�� | -1.873 |
gers | -1.825 |
Token | of |
Token ID | 286 |
Feature activation | -6.86e-03 |
Pos logit contributions | |
ploma | +0.521 |
sucker | +0.520 |
rongh | +0.502 |
ォ | +0.497 |
EVER | +0.494 |
Neg logit contributions | |
ging | -0.615 |
chin | -0.578 |
keeping | -0.560 |
�� | -0.552 |
gers | -0.538 |
Token | speaking |
Token ID | 5486 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
ging | +0.006 |
chin | +0.005 |
keeping | +0.005 |
�� | +0.005 |
gers | +0.005 |
Neg logit contributions | |
ploma | -0.004 |
sucker | -0.004 |
rongh | -0.004 |
ォ | -0.004 |
babe | -0.004 |
Token | within |
Token ID | 1626 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
sucker | +2.059 |
ploma | +2.025 |
babe | +1.950 |
date | +1.946 |
EVER | +1.943 |
Neg logit contributions | |
ging | -2.797 |
chin | -2.641 |
�� | -2.605 |
keeping | -2.556 |
nutrition | -2.512 |
Token | a |
Token ID | 257 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
ploma | +0.628 |
sucker | +0.627 |
rongh | +0.604 |
ォ | +0.592 |
EVER | +0.590 |
Neg logit contributions | |
ging | -0.963 |
chin | -0.914 |
keeping | -0.886 |
�� | -0.869 |
gers | -0.854 |
Token | more |
Token ID | 517 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
ploma | +0.113 |
sucker | +0.112 |
rongh | +0.108 |
ォ | +0.107 |
babe | +0.105 |
Neg logit contributions | |
ging | -0.168 |
chin | -0.159 |
keeping | -0.155 |
�� | -0.151 |
gers | -0.149 |
Token | general |
Token ID | 2276 |
Feature activation | -6.99e+00 |
Pos logit contributions | |
ging | +4.360 |
chin | +4.048 |
keeping | +3.956 |
gers | +3.784 |
�� | +3.712 |
Neg logit contributions | |
ploma | -3.473 |
ォ | -3.442 |
rongh | -3.428 |
sucker | -3.367 |
sqor | -3.270 |
Token | , |
Token ID | 11 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
ging | +5.929 |
chin | +5.480 |
keeping | +5.428 |
gers | +5.211 |
�� | +5.134 |
Neg logit contributions | |
ploma | -4.005 |
ォ | -3.966 |
rongh | -3.863 |
sucker | -3.805 |
sth | -3.690 |
Token | city |
Token ID | 1748 |
Feature activation | -5.61e+00 |
Pos logit contributions | |
ging | +5.635 |
chin | +5.181 |
keeping | +5.149 |
gers | +4.930 |
�� | +4.819 |
Neg logit contributions | |
ploma | -4.101 |
ォ | -4.043 |
rongh | -4.040 |
sucker | -3.910 |
sqor | -3.815 |
Token | wide |
Token ID | 4421 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
ging | +4.796 |
chin | +4.501 |
keeping | +4.429 |
gers | +4.215 |
�� | +4.141 |
Neg logit contributions | |
ploma | -3.262 |
sucker | -3.195 |
rongh | -3.157 |
ォ | -3.138 |
EVER | -3.039 |
Token | environments |
Token ID | 12493 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
ging | +1.253 |
chin | +1.178 |
keeping | +1.156 |
gers | +1.113 |
�� | +1.103 |
Neg logit contributions | |
ploma | -0.855 |
sucker | -0.828 |
rongh | -0.811 |
ォ | -0.806 |
EVER | -0.781 |
Token | and |
Token ID | 290 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
ploma | +0.391 |
sucker | +0.389 |
rongh | +0.377 |
ォ | +0.372 |
EVER | +0.366 |
Neg logit contributions | |
ging | -0.598 |
chin | -0.565 |
keeping | -0.549 |
�� | -0.537 |
gers | -0.530 |
Token | planetary |
Token ID | 27047 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ging | +0.534 |
chin | +0.503 |
keeping | +0.489 |
�� | +0.475 |
gers | +0.470 |
Neg logit contributions | |
ploma | -0.401 |
sucker | -0.396 |
rongh | -0.386 |
ォ | -0.383 |
babe | -0.374 |
Token | processes |
Token ID | 7767 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
ging | +1.497 |
chin | +1.399 |
keeping | +1.374 |
gers | +1.315 |
�� | +1.306 |
Neg logit contributions | |
ploma | -1.275 |
sucker | -1.252 |
rongh | -1.225 |
ォ | -1.213 |
EVER | -1.184 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ploma | +0.468 |
sucker | +0.466 |
rongh | +0.452 |
ォ | +0.446 |
EVER | +0.438 |
Neg logit contributions | |
ging | -0.740 |
chin | -0.700 |
keeping | -0.680 |
�� | -0.667 |
gers | -0.657 |
Token |
|
Token ID | 198 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ging | +0.126 |
chin | +0.119 |
keeping | +0.116 |
�� | +0.114 |
gers | +0.111 |
Neg logit contributions | |
ploma | -0.091 |
sucker | -0.090 |
rongh | -0.087 |
ォ | -0.087 |
EVER | -0.085 |
Token |
|
Token ID | 198 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ging | +0.426 |
chin | +0.399 |
keeping | +0.391 |
gers | +0.376 |
�� | +0.367 |
Neg logit contributions | |
ploma | -0.321 |
sucker | -0.319 |
rongh | -0.311 |
ォ | -0.307 |
babe | -0.298 |
Token | " |
Token ID | 1 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
ging | +0.996 |
chin | +0.937 |
keeping | +0.910 |
�� | +0.891 |
gers | +0.876 |
Neg logit contributions | |
ploma | -0.761 |
sucker | -0.751 |
rongh | -0.732 |
ォ | -0.726 |
babe | -0.711 |
Token | This |
Token ID | 1212 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
ging | +3.620 |
chin | +3.362 |
keeping | +3.339 |
gers | +3.166 |
vim | +3.074 |
Neg logit contributions | |
sucker | -3.060 |
ploma | -3.016 |
rongh | -2.973 |
ォ | -2.869 |
babe | -2.855 |
Token | rock |
Token ID | 3881 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
ging | +2.468 |
chin | +2.298 |
keeping | +2.255 |
gers | +2.154 |
�� | +2.130 |
Neg logit contributions | |
ploma | -2.040 |
rongh | -1.964 |
ォ | -1.952 |
sucker | -1.952 |
sth | -1.876 |
Token | is |
Token ID | 318 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
sucker | +0.605 |
ploma | +0.603 |
rongh | +0.582 |
ォ | +0.579 |
babe | +0.572 |
Neg logit contributions | |
ging | -0.689 |
chin | -0.646 |
keeping | -0.622 |
�� | -0.616 |
gers | -0.599 |
Token | and |
Token ID | 290 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ploma | +0.412 |
sucker | +0.408 |
rongh | +0.395 |
ォ | +0.392 |
babe | +0.384 |
Neg logit contributions | |
ging | -0.603 |
chin | -0.569 |
keeping | -0.554 |
�� | -0.541 |
gers | -0.534 |
Token | it |
Token ID | 340 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
ploma | +0.794 |
sucker | +0.791 |
rongh | +0.762 |
ォ | +0.756 |
EVER | +0.747 |
Neg logit contributions | |
ging | -1.103 |
chin | -1.038 |
keeping | -1.010 |
�� | -0.992 |
gers | -0.973 |
Token | � |
Token ID | 447 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
sucker | +2.368 |
ploma | +2.348 |
ォ | +2.278 |
rongh | +2.266 |
EVER | +2.248 |
Neg logit contributions | |
ging | -2.799 |
chin | -2.606 |
keeping | -2.561 |
�� | -2.539 |
gers | -2.452 |
Token | � |
Token ID | 247 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ploma | +0.428 |
sucker | +0.424 |
rongh | +0.413 |
ォ | +0.411 |
babe | +0.402 |
Neg logit contributions | |
ging | -0.537 |
chin | -0.505 |
keeping | -0.491 |
�� | -0.474 |
gers | -0.470 |
Token | s |
Token ID | 82 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ploma | +0.857 |
sucker | +0.851 |
rongh | +0.823 |
ォ | +0.814 |
sth | +0.799 |
Neg logit contributions | |
ging | -1.339 |
chin | -1.266 |
keeping | -1.236 |
�� | -1.215 |
gers | -1.188 |
Token | now |
Token ID | 783 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
ging | +0.858 |
chin | +0.807 |
keeping | +0.785 |
�� | +0.757 |
gers | +0.755 |
Neg logit contributions | |
ploma | -0.627 |
sucker | -0.618 |
rongh | -0.607 |
ォ | -0.600 |
babe | -0.583 |
Token | more |
Token ID | 517 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
ging | +0.160 |
chin | +0.151 |
keeping | +0.147 |
�� | +0.143 |
gers | +0.141 |
Neg logit contributions | |
ploma | -0.114 |
sucker | -0.113 |
rongh | -0.110 |
ォ | -0.109 |
babe | -0.107 |
Token | a |
Token ID | 257 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ging | +1.812 |
chin | +1.682 |
keeping | +1.621 |
gers | +1.561 |
�� | +1.553 |
Neg logit contributions | |
ploma | -1.657 |
rongh | -1.622 |
sucker | -1.621 |
ォ | -1.602 |
sqor | -1.548 |
Token | matter |
Token ID | 2300 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ploma | +0.850 |
sucker | +0.849 |
ォ | +0.813 |
rongh | +0.811 |
babe | +0.797 |
Neg logit contributions | |
ging | -1.359 |
chin | -1.287 |
keeping | -1.256 |
�� | -1.231 |
gers | -1.212 |
Token | of |
Token ID | 286 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
ging | +1.184 |
chin | +1.116 |
keeping | +1.084 |
�� | +1.056 |
gers | +1.047 |
Neg logit contributions | |
ploma | -0.853 |
sucker | -0.844 |
rongh | -0.818 |
ォ | -0.814 |
babe | -0.797 |
Token | incorporating |
Token ID | 29927 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
ging | +0.844 |
chin | +0.797 |
keeping | +0.778 |
�� | +0.752 |
gers | +0.750 |
Neg logit contributions | |
ploma | -0.523 |
sucker | -0.512 |
rongh | -0.503 |
ォ | -0.495 |
EVER | -0.481 |
Token | " |
Token ID | 366 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
ging | +1.389 |
chin | +1.308 |
keeping | +1.275 |
�� | +1.234 |
gers | +1.229 |
Neg logit contributions | |
ploma | -0.976 |
sucker | -0.966 |
rongh | -0.945 |
ォ | -0.933 |
babe | -0.907 |
Token | It |
Token ID | 1026 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ging | +1.813 |
chin | +1.704 |
keeping | +1.661 |
�� | +1.594 |
gers | +1.593 |
Neg logit contributions | |
ploma | -1.374 |
sucker | -1.368 |
rongh | -1.332 |
ォ | -1.315 |
babe | -1.285 |
Token | 's |
Token ID | 338 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
ging | +1.229 |
chin | +1.156 |
keeping | +1.120 |
�� | +1.079 |
gers | +1.077 |
Neg logit contributions | |
ploma | -0.984 |
sucker | -0.969 |
rongh | -0.950 |
ォ | -0.942 |
EVER | -0.917 |
Token | all |
Token ID | 477 |
Feature activation | -6.87e+00 |
Pos logit contributions | |
ging | +2.710 |
chin | +2.535 |
keeping | +2.483 |
gers | +2.391 |
�� | +2.356 |
Neg logit contributions | |
ploma | -1.911 |
rongh | -1.870 |
sucker | -1.866 |
ォ | -1.855 |
sth | -1.780 |
Token | about |
Token ID | 546 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ging | +4.926 |
chin | +4.516 |
keeping | +4.446 |
gers | +4.259 |
ience | +4.118 |
Neg logit contributions | |
rongh | -4.806 |
ォ | -4.779 |
ploma | -4.766 |
sucker | -4.637 |
sqor | -4.603 |
Token | learning |
Token ID | 4673 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
ging | +1.393 |
chin | +1.305 |
keeping | +1.275 |
gers | +1.225 |
�� | +1.222 |
Neg logit contributions | |
ploma | -1.063 |
sucker | -1.043 |
rongh | -1.027 |
ォ | -1.019 |
sth | -0.990 |
Token | the |
Token ID | 262 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
ging | +0.319 |
chin | +0.300 |
keeping | +0.293 |
�� | +0.282 |
gers | +0.282 |
Neg logit contributions | |
ploma | -0.220 |
sucker | -0.216 |
rongh | -0.212 |
ォ | -0.211 |
EVER | -0.204 |
Token | racing |
Token ID | 11717 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
sucker | +2.583 |
ploma | +2.511 |
babe | +2.423 |
date | +2.408 |
rongh | +2.403 |
Neg logit contributions | |
ging | -3.136 |
chin | -2.977 |
�� | -2.896 |
keeping | -2.855 |
nutrition | -2.764 |
Token | lines |
Token ID | 3951 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
sucker | +3.280 |
babe | +3.161 |
ploma | +3.149 |
date | +3.101 |
Turks | +3.034 |
Neg logit contributions | |
ging | -4.503 |
chin | -4.358 |
�� | -4.297 |
keeping | -4.085 |
nutrition | -4.071 |
Token | first |
Token ID | 717 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ploma | +1.306 |
sucker | +1.298 |
rongh | +1.246 |
babe | +1.226 |
EVER | +1.222 |
Neg logit contributions | |
ging | -2.050 |
chin | -1.940 |
keeping | -1.877 |
�� | -1.867 |
gers | -1.813 |
Token | ," |
Token ID | 553 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
sucker | +1.155 |
ploma | +1.152 |
rongh | +1.099 |
babe | +1.084 |
EVER | +1.078 |
Neg logit contributions | |
ging | -1.858 |
chin | -1.760 |
keeping | -1.707 |
�� | -1.696 |
gers | -1.648 |
Token | HAVE |
Token ID | 21515 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ging | +2.611 |
chin | +2.479 |
keeping | +2.412 |
gers | +2.314 |
�� | +2.308 |
Neg logit contributions | |
ploma | -1.794 |
sucker | -1.769 |
rongh | -1.748 |
ォ | -1.703 |
babe | -1.648 |
Token | BE |
Token ID | 9348 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
ging | +0.952 |
chin | +0.899 |
keeping | +0.875 |
�� | +0.854 |
gers | +0.843 |
Neg logit contributions | |
ploma | -0.640 |
sucker | -0.633 |
rongh | -0.614 |
ォ | -0.609 |
EVER | -0.598 |
Token | EN |
Token ID | 1677 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ging | +2.359 |
chin | +2.234 |
keeping | +2.179 |
gers | +2.102 |
�� | +2.093 |
Neg logit contributions | |
ploma | -1.435 |
sucker | -1.422 |
rongh | -1.392 |
ォ | -1.359 |
babe | -1.320 |
Token | T |
Token ID | 309 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
ploma | +0.608 |
sucker | +0.607 |
EVER | +0.589 |
ォ | +0.581 |
rongh | +0.573 |
Neg logit contributions | |
ging | -0.898 |
chin | -0.848 |
�� | -0.826 |
keeping | -0.824 |
gers | -0.792 |
Token | AK |
Token ID | 10206 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ging | +0.257 |
chin | +0.238 |
keeping | +0.231 |
�� | +0.225 |
gers | +0.220 |
Neg logit contributions | |
ploma | -0.278 |
sucker | -0.274 |
rongh | -0.268 |
ォ | -0.267 |
EVER | -0.263 |
Token | EN |
Token ID | 1677 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
ging | +0.144 |
chin | +0.136 |
keeping | +0.133 |
�� | +0.129 |
gers | +0.128 |
Neg logit contributions | |
ploma | -0.084 |
sucker | -0.083 |
rongh | -0.081 |
ォ | -0.079 |
babe | -0.077 |
Token | DOWN |
Token ID | 30320 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ging | +5.331 |
chin | +4.962 |
keeping | +4.851 |
gers | +4.722 |
vim | +4.557 |
Neg logit contributions | |
ploma | -4.087 |
sucker | -4.014 |
rongh | -4.009 |
ォ | -3.859 |
babe | -3.758 |
Token | UP |
Token ID | 15958 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
ging | +1.133 |
chin | +1.072 |
keeping | +1.046 |
�� | +1.012 |
gers | +1.007 |
Neg logit contributions | |
ploma | -0.706 |
sucker | -0.699 |
rongh | -0.680 |
ォ | -0.670 |
babe | -0.652 |
Token | ON |
Token ID | 1340 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ploma | +1.135 |
sucker | +1.100 |
EVER | +1.084 |
rongh | +1.053 |
ォ | +1.052 |
Neg logit contributions | |
ging | -2.731 |
chin | -2.603 |
keeping | -2.523 |
�� | -2.512 |
gers | -2.464 |
Token | PAR |
Token ID | 29463 |
Feature activation | +9.95e+00 |
Pos logit contributions | |
ging | +1.168 |
chin | +1.106 |
keeping | +1.078 |
�� | +1.052 |
gers | +1.041 |
Neg logit contributions | |
ploma | -0.692 |
sucker | -0.684 |
rongh | -0.663 |
ォ | -0.656 |
babe | -0.640 |
Token | AM |
Token ID | 2390 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
EVER | +4.062 |
ploma | +3.980 |
sth | +3.802 |
date | +3.798 |
REG | +3.776 |
Neg logit contributions | |
�� | -9.852 |
ging | -9.839 |
chin | -9.276 |
�� | -9.160 |
gers | -8.831 |
Token | officials |
Token ID | 2828 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
ging | +0.544 |
chin | +0.513 |
keeping | +0.501 |
�� | +0.484 |
gers | +0.481 |
Neg logit contributions | |
ploma | -0.381 |
sucker | -0.376 |
rongh | -0.366 |
ォ | -0.364 |
babe | -0.354 |
Token | with |
Token ID | 351 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ploma | +0.284 |
sucker | +0.281 |
rongh | +0.273 |
ォ | +0.270 |
babe | +0.264 |
Neg logit contributions | |
ging | -0.439 |
chin | -0.415 |
keeping | -0.404 |
�� | -0.395 |
gers | -0.389 |
Token | a |
Token ID | 257 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
ploma | +1.083 |
sucker | +1.077 |
rongh | +1.035 |
ォ | +1.029 |
date | +1.013 |
Neg logit contributions | |
ging | -1.599 |
chin | -1.514 |
keeping | -1.471 |
�� | -1.459 |
gers | -1.416 |
Token | proposal |
Token ID | 6961 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
ploma | +0.568 |
sucker | +0.567 |
rongh | +0.544 |
ォ | +0.539 |
babe | +0.533 |
Neg logit contributions | |
ging | -0.775 |
chin | -0.732 |
keeping | -0.712 |
�� | -0.702 |
gers | -0.685 |
Token | to |
Token ID | 284 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
ploma | +2.343 |
sucker | +2.302 |
ォ | +2.199 |
rongh | +2.198 |
date | +2.197 |
Neg logit contributions | |
ging | -4.157 |
chin | -3.936 |
keeping | -3.814 |
�� | -3.792 |
gers | -3.739 |
Token | fly |
Token ID | 6129 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
ploma | +0.309 |
sucker | +0.306 |
rongh | +0.297 |
ォ | +0.295 |
babe | +0.288 |
Neg logit contributions | |
ging | -0.429 |
chin | -0.405 |
keeping | -0.394 |
�� | -0.383 |
gers | -0.379 |
Token | a |
Token ID | 257 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
ging | +5.688 |
chin | +5.411 |
keeping | +5.227 |
gers | +5.001 |
gin | +4.889 |
Neg logit contributions | |
ploma | -4.484 |
rongh | -4.338 |
ォ | -4.336 |
sucker | -4.318 |
babe | -4.179 |
Token | shuttle |
Token ID | 20992 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
ging | +2.329 |
chin | +2.207 |
keeping | +2.142 |
�� | +2.058 |
gers | +2.057 |
Neg logit contributions | |
ploma | -1.620 |
sucker | -1.570 |
rongh | -1.553 |
ォ | -1.540 |
babe | -1.493 |
Token | mission |
Token ID | 4365 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
ging | +2.757 |
chin | +2.600 |
keeping | +2.532 |
gers | +2.414 |
�� | +2.396 |
Neg logit contributions | |
ploma | -2.079 |
sucker | -2.013 |
rongh | -2.007 |
ォ | -1.985 |
babe | -1.919 |
Token | using |
Token ID | 1262 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ging | +4.843 |
chin | +4.540 |
keeping | +4.446 |
gers | +4.234 |
�� | +4.144 |
Neg logit contributions | |
ploma | -3.782 |
rongh | -3.657 |
ォ | -3.620 |
sucker | -3.620 |
babe | -3.478 |
Token | a |
Token ID | 257 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ging | +0.985 |
chin | +0.929 |
keeping | +0.904 |
�� | +0.879 |
gers | +0.870 |
Neg logit contributions | |
ploma | -0.692 |
sucker | -0.684 |
rongh | -0.666 |
ォ | -0.660 |
babe | -0.645 |
Token |
|
Token ID | 198 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ging | +1.566 |
chin | +1.463 |
keeping | +1.445 |
gers | +1.376 |
vim | +1.333 |
Neg logit contributions | |
sucker | -1.279 |
ploma | -1.264 |
rongh | -1.239 |
ォ | -1.215 |
babe | -1.183 |
Token | 2011 |
Token ID | 9804 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
ging | +1.608 |
chin | +1.512 |
keeping | +1.476 |
gers | +1.416 |
�� | +1.412 |
Neg logit contributions | |
ploma | -1.161 |
sucker | -1.159 |
rongh | -1.123 |
ォ | -1.113 |
babe | -1.090 |
Token | polymer |
Token ID | 30528 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ging | +2.622 |
chin | +2.458 |
keeping | +2.399 |
gers | +2.314 |
�� | +2.296 |
Neg logit contributions | |
ploma | -1.779 |
sucker | -1.756 |
rongh | -1.711 |
ォ | -1.706 |
babe | -1.651 |
Token | series |
Token ID | 2168 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ploma | +1.470 |
sucker | +1.456 |
rongh | +1.407 |
ォ | +1.381 |
date | +1.368 |
Neg logit contributions | |
ging | -2.345 |
chin | -2.229 |
keeping | -2.168 |
�� | -2.143 |
gers | -2.089 |
Token | [ |
Token ID | 685 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
ploma | +0.799 |
sucker | +0.790 |
rongh | +0.763 |
ォ | +0.749 |
EVER | +0.746 |
Neg logit contributions | |
ging | -1.212 |
chin | -1.146 |
keeping | -1.111 |
�� | -1.101 |
gers | -1.072 |
Token | edit |
Token ID | 4370 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
ging | +5.387 |
chin | +5.025 |
keeping | +4.969 |
gers | +4.648 |
nutrition | +4.617 |
Neg logit contributions | |
sucker | -4.819 |
ォ | -4.777 |
ploma | -4.769 |
rongh | -4.703 |
babe | -4.493 |
Token | ] |
Token ID | 2361 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
ging | +4.314 |
chin | +3.846 |
keeping | +3.809 |
gers | +3.589 |
ga | +3.229 |
Neg logit contributions | |
ploma | -10.346 |
rongh | -10.215 |
sucker | -9.954 |
ォ | -9.714 |
babe | -9.631 |
Token |
|
Token ID | 198 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ging | +5.511 |
keeping | +5.081 |
chin | +5.016 |
gers | +4.747 |
keepers | +4.582 |
Neg logit contributions | |
sucker | -5.783 |
rongh | -5.730 |
ploma | -5.683 |
ォ | -5.495 |
babe | -5.334 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ging | +1.428 |
chin | +1.328 |
keeping | +1.314 |
gers | +1.256 |
keepers | +1.209 |
Neg logit contributions | |
ploma | -1.171 |
sucker | -1.167 |
rongh | -1.146 |
ォ | -1.128 |
babe | -1.085 |
Token | $ |
Token ID | 3 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
ging | +1.487 |
chin | +1.398 |
keeping | +1.364 |
gers | +1.310 |
�� | +1.309 |
Neg logit contributions | |
sucker | -1.053 |
ploma | -1.052 |
rongh | -1.018 |
ォ | -1.007 |
babe | -0.989 |
Token | 1 |
Token ID | 16 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
ploma | +1.735 |
sucker | +1.716 |
rongh | +1.683 |
ォ | +1.648 |
EVER | +1.636 |
Neg logit contributions | |
ging | -2.439 |
chin | -2.298 |
keeping | -2.236 |
�� | -2.200 |
gers | -2.156 |
Token | driver |
Token ID | 4639 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
sucker | +0.820 |
ploma | +0.809 |
rongh | +0.761 |
ォ | +0.756 |
babe | +0.755 |
Neg logit contributions | |
ging | -2.359 |
chin | -2.257 |
keeping | -2.212 |
�� | -2.199 |
gers | -2.149 |
Token | are |
Token ID | 389 |
Feature activation | +7.03e+00 |
Pos logit contributions | |
sucker | +4.959 |
date | +4.890 |
ploma | +4.751 |
EVER | +4.673 |
sth | +4.626 |
Neg logit contributions | |
ging | -6.368 |
chin | -6.152 |
�� | -6.053 |
�� | -5.917 |
keeping | -5.851 |
Token | under |
Token ID | 739 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
ploma | +3.950 |
sucker | +3.919 |
date | +3.839 |
EVER | +3.784 |
Turks | +3.726 |
Neg logit contributions | |
ging | -5.854 |
chin | -5.679 |
�� | -5.646 |
keeping | -5.382 |
�� | -5.341 |
Token | investigation |
Token ID | 3645 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
sucker | +2.294 |
ploma | +2.251 |
ォ | +2.198 |
rongh | +2.189 |
date | +2.186 |
Neg logit contributions | |
ging | -3.308 |
chin | -3.172 |
keeping | -3.032 |
�� | -3.005 |
gers | -2.946 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ploma | +0.723 |
sucker | +0.723 |
rongh | +0.695 |
ォ | +0.682 |
EVER | +0.682 |
Neg logit contributions | |
ging | -1.143 |
chin | -1.084 |
keeping | -1.049 |
�� | -1.036 |
gers | -1.014 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.23e+00 |
Pos logit contributions | |
ploma | +0.869 |
sucker | +0.858 |
EVER | +0.838 |
ォ | +0.836 |
rongh | +0.824 |
Neg logit contributions | |
ging | -1.319 |
chin | -1.242 |
�� | -1.209 |
keeping | -1.205 |
gers | -1.169 |
Token | Ready |
Token ID | 35474 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
ging | +6.582 |
chin | +6.169 |
keeping | +6.074 |
gers | +5.741 |
vim | +5.700 |
Neg logit contributions | |
sucker | -5.206 |
rongh | -5.040 |
ploma | -4.983 |
ォ | -4.958 |
sqor | -4.830 |
Token | to |
Token ID | 284 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ploma | +2.823 |
sucker | +2.791 |
babe | +2.768 |
date | +2.677 |
EVER | +2.650 |
Neg logit contributions | |
ging | -5.074 |
chin | -4.890 |
�� | -4.837 |
keeping | -4.655 |
nutrition | -4.571 |
Token | fight |
Token ID | 1907 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ploma | +0.658 |
sucker | +0.658 |
rongh | +0.633 |
ォ | +0.623 |
EVER | +0.620 |
Neg logit contributions | |
ging | -0.923 |
chin | -0.869 |
keeping | -0.849 |
�� | -0.833 |
gers | -0.814 |
Token | back |
Token ID | 736 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ging | +2.124 |
chin | +1.978 |
keeping | +1.941 |
gers | +1.867 |
�� | +1.829 |
Neg logit contributions | |
ploma | -1.570 |
sucker | -1.517 |
ォ | -1.513 |
rongh | -1.506 |
sth | -1.443 |
Token | ? |
Token ID | 30 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
sucker | +1.739 |
ploma | +1.706 |
rongh | +1.667 |
babe | +1.656 |
EVER | +1.642 |
Neg logit contributions | |
ging | -2.010 |
chin | -1.918 |
�� | -1.848 |
keeping | -1.839 |
gers | -1.756 |
Token | display |
Token ID | 3359 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
ging | +0.241 |
chin | +0.224 |
keeping | +0.216 |
�� | +0.209 |
gers | +0.206 |
Neg logit contributions | |
ploma | -0.265 |
sucker | -0.263 |
rongh | -0.257 |
ォ | -0.255 |
babe | -0.251 |
Token | at |
Token ID | 379 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
ging | +0.628 |
chin | +0.590 |
keeping | +0.577 |
gers | +0.553 |
�� | +0.552 |
Neg logit contributions | |
ploma | -0.456 |
sucker | -0.447 |
rongh | -0.438 |
ォ | -0.435 |
babe | -0.420 |
Token | the |
Token ID | 262 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
ging | +2.658 |
chin | +2.508 |
keeping | +2.430 |
gers | +2.326 |
�� | +2.325 |
Neg logit contributions | |
ploma | -1.999 |
sucker | -1.974 |
ォ | -1.928 |
rongh | -1.927 |
babe | -1.870 |
Token | Shu |
Token ID | 32344 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
ging | +4.591 |
chin | +4.360 |
keeping | +4.184 |
gers | +3.991 |
�� | +3.960 |
Neg logit contributions | |
ploma | -3.465 |
sucker | -3.378 |
rongh | -3.331 |
ォ | -3.326 |
babe | -3.201 |
Token | Bro |
Token ID | 2806 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
ging | +1.882 |
chin | +1.767 |
keeping | +1.707 |
�� | +1.639 |
gers | +1.632 |
Neg logit contributions | |
ploma | -1.710 |
sucker | -1.704 |
rongh | -1.655 |
ォ | -1.650 |
EVER | -1.618 |
Token | cade |
Token ID | 46395 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
ging | +1.788 |
chin | +1.675 |
keeping | +1.625 |
�� | +1.574 |
gers | +1.556 |
Neg logit contributions | |
ploma | -1.584 |
sucker | -1.569 |
rongh | -1.530 |
ォ | -1.519 |
babe | -1.489 |
Token | Museum |
Token ID | 9594 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ging | +5.327 |
chin | +5.047 |
keeping | +4.873 |
gers | +4.632 |
�� | +4.582 |
Neg logit contributions | |
ploma | -4.179 |
sucker | -4.129 |
ォ | -4.047 |
rongh | -4.025 |
EVER | -3.914 |
Token | . |
Token ID | 13 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ging | +1.198 |
chin | +1.129 |
keeping | +1.102 |
�� | +1.063 |
gers | +1.055 |
Neg logit contributions | |
ploma | -0.841 |
sucker | -0.831 |
rongh | -0.806 |
ォ | -0.801 |
babe | -0.783 |
Token |
|
Token ID | 198 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
ploma | +0.170 |
sucker | +0.167 |
rongh | +0.163 |
ォ | +0.163 |
EVER | +0.160 |
Neg logit contributions | |
ging | -0.243 |
chin | -0.229 |
keeping | -0.223 |
�� | -0.219 |
gers | -0.215 |
Token |
|
Token ID | 198 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
ploma | +0.360 |
sucker | +0.357 |
rongh | +0.347 |
ォ | +0.344 |
babe | +0.335 |
Neg logit contributions | |
ging | -0.499 |
chin | -0.469 |
keeping | -0.458 |
gers | -0.440 |
�� | -0.439 |
Token | Late |
Token ID | 26302 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
ging | +0.083 |
chin | +0.078 |
keeping | +0.076 |
�� | +0.075 |
gers | +0.073 |
Neg logit contributions | |
ploma | -0.061 |
sucker | -0.060 |
rongh | -0.058 |
ォ | -0.058 |
EVER | -0.057 |