Token | the |
Token ID | 262 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Klux | +1.272 |
sleeper | +1.245 |
disasters | +1.121 |
liquids | +1.099 |
senal | +1.073 |
Neg logit contributions | |
ieth | -2.101 |
龍� | -1.942 |
iaries | -1.923 |
iary | -1.793 |
shire | -1.751 |
Token | rebels |
Token ID | 12669 |
Feature activation | +6.40e+00 |
Pos logit contributions | |
Klux | +1.427 |
sleeper | +1.395 |
disasters | +1.252 |
liquids | +1.233 |
senal | +1.193 |
Neg logit contributions | |
ieth | -2.450 |
龍� | -2.272 |
iaries | -2.249 |
iary | -2.101 |
eded | -2.049 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
sleeper | +5.219 |
Klux | +5.193 |
disasters | +4.699 |
liquids | +4.657 |
plane | +4.570 |
Neg logit contributions | |
ieth | -6.606 |
龍� | -6.155 |
iaries | -6.071 |
iary | -5.530 |
shire | -5.375 |
Token | not |
Token ID | 407 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Klux | +0.980 |
sleeper | +0.959 |
disasters | +0.871 |
liquids | +0.859 |
senal | +0.852 |
Neg logit contributions | |
ieth | -1.414 |
龍� | -1.299 |
iaries | -1.288 |
iary | -1.199 |
eded | -1.167 |
Token | the |
Token ID | 262 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Klux | +0.800 |
sleeper | +0.777 |
disasters | +0.692 |
liquids | +0.681 |
senal | +0.675 |
Neg logit contributions | |
ieth | -1.514 |
龍� | -1.401 |
iaries | -1.393 |
iary | -1.307 |
eded | -1.276 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
Klux | +1.129 |
sleeper | +1.101 |
disasters | +0.980 |
liquids | +0.964 |
senal | +0.945 |
Neg logit contributions | |
ieth | -2.155 |
龍� | -2.001 |
iaries | -1.983 |
iary | -1.861 |
eded | -1.814 |
Token | government |
Token ID | 1230 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
sleeper | +5.655 |
Klux | +5.550 |
disasters | +4.818 |
liquids | +4.718 |
plane | +4.587 |
Neg logit contributions | |
ieth | -15.090 |
龍� | -14.204 |
iaries | -13.939 |
iary | -13.068 |
姫 | -12.974 |
Token | , |
Token ID | 11 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
sleeper | +4.095 |
Klux | +3.996 |
disasters | +3.690 |
liquids | +3.667 |
plane | +3.598 |
Neg logit contributions | |
ieth | -5.181 |
龍� | -4.824 |
iaries | -4.715 |
iary | -4.308 |
urations | -4.221 |
Token | that |
Token ID | 326 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
Klux | +0.663 |
sleeper | +0.651 |
disasters | +0.589 |
liquids | +0.581 |
senal | +0.572 |
Neg logit contributions | |
ieth | -1.025 |
龍� | -0.944 |
iaries | -0.937 |
iary | -0.872 |
shire | -0.850 |
Token | used |
Token ID | 973 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Klux | +2.740 |
sleeper | +2.707 |
disasters | +2.459 |
liquids | +2.424 |
senal | +2.357 |
Neg logit contributions | |
ieth | -4.077 |
龍� | -3.764 |
iaries | -3.713 |
iary | -3.455 |
shire | -3.346 |
Token | Sar |
Token ID | 6866 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Klux | +0.929 |
sleeper | +0.909 |
disasters | +0.766 |
liquids | +0.751 |
senal | +0.727 |
Neg logit contributions | |
ieth | -2.832 |
龍� | -2.652 |
iaries | -2.631 |
iary | -2.494 |
shire | -2.443 |
Token | a |
Token ID | 257 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Klux | +1.146 |
sleeper | +1.110 |
disasters | +1.000 |
senal | +0.998 |
liquids | +0.987 |
Neg logit contributions | |
ieth | -1.822 |
龍� | -1.668 |
iaries | -1.663 |
iary | -1.558 |
shire | -1.516 |
Token | long |
Token ID | 890 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ieth | +0.255 |
龍� | +0.232 |
iaries | +0.231 |
iary | +0.216 |
shire | +0.210 |
Neg logit contributions | |
Klux | -0.185 |
sleeper | -0.179 |
disasters | -0.164 |
senal | -0.164 |
liquids | -0.162 |
Token | time |
Token ID | 640 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ieth | +1.618 |
龍� | +1.484 |
iaries | +1.474 |
iary | +1.368 |
eded | +1.334 |
Neg logit contributions | |
Klux | -1.173 |
sleeper | -1.150 |
disasters | -1.044 |
liquids | -1.032 |
senal | -1.018 |
Token | ." |
Token ID | 526 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
Klux | +0.121 |
sleeper | +0.118 |
disasters | +0.110 |
liquids | +0.108 |
senal | +0.107 |
Neg logit contributions | |
ieth | -0.123 |
龍� | -0.111 |
iaries | -0.110 |
iary | -0.101 |
eded | -0.098 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
ieth | +0.656 |
龍� | +0.596 |
iaries | +0.590 |
iary | +0.535 |
eded | +0.527 |
Neg logit contributions | |
Klux | -0.613 |
sleeper | -0.595 |
disasters | -0.552 |
liquids | -0.546 |
senal | -0.538 |
Token | Oil |
Token ID | 44142 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
Klux | +2.997 |
sleeper | +2.910 |
disasters | +2.683 |
liquids | +2.651 |
plane | +2.646 |
Neg logit contributions | |
ieth | -3.214 |
龍� | -2.918 |
iaries | -2.912 |
iary | -2.649 |
shire | -2.567 |
Token | from |
Token ID | 422 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
Klux | +8.924 |
sleeper | +8.706 |
disasters | +8.301 |
liquids | +8.191 |
plane | +7.690 |
Neg logit contributions | |
ieth | -11.098 |
龍� | -10.486 |
iaries | -10.075 |
iary | -9.284 |
姫 | -8.907 |
Token | a |
Token ID | 257 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Klux | +2.043 |
sleeper | +2.003 |
disasters | +1.816 |
liquids | +1.789 |
senal | +1.705 |
Neg logit contributions | |
ieth | -3.667 |
龍� | -3.409 |
iaries | -3.356 |
iary | -3.147 |
eded | -3.061 |
Token | wrecked |
Token ID | 44770 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
Klux | +1.314 |
sleeper | +1.285 |
disasters | +1.150 |
liquids | +1.136 |
senal | +1.103 |
Neg logit contributions | |
ieth | -2.306 |
龍� | -2.141 |
iaries | -2.115 |
iary | -1.974 |
eded | -1.930 |
Token | tanker |
Token ID | 46335 |
Feature activation | +6.95e+00 |
Pos logit contributions | |
Klux | +2.223 |
sleeper | +2.188 |
disasters | +1.951 |
liquids | +1.915 |
plane | +1.860 |
Neg logit contributions | |
ieth | -3.965 |
龍� | -3.706 |
iaries | -3.656 |
iary | -3.405 |
eded | -3.325 |
Token | is |
Token ID | 318 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
sleeper | +5.389 |
Klux | +5.323 |
disasters | +5.010 |
liquids | +4.874 |
plane | +4.736 |
Neg logit contributions | |
ieth | -7.379 |
龍� | -7.065 |
iaries | -6.835 |
iary | -6.309 |
姫 | -6.165 |
Token | nationals |
Token ID | 22970 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ieth | +0.524 |
龍� | +0.474 |
iaries | +0.470 |
iary | +0.432 |
eded | +0.419 |
Neg logit contributions | |
Klux | -0.500 |
sleeper | -0.490 |
disasters | -0.452 |
liquids | -0.447 |
senal | -0.444 |
Token | in |
Token ID | 287 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
ieth | +1.559 |
iaries | +1.408 |
龍� | +1.398 |
iary | +1.307 |
eded | +1.268 |
Neg logit contributions | |
Klux | -1.288 |
sleeper | -1.244 |
senal | -1.163 |
disasters | -1.137 |
liquids | -1.125 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ieth | +0.472 |
龍� | +0.435 |
iaries | +0.433 |
iary | +0.405 |
eded | +0.395 |
Neg logit contributions | |
Klux | -0.275 |
sleeper | -0.267 |
disasters | -0.240 |
liquids | -0.237 |
senal | -0.235 |
Token | service |
Token ID | 2139 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
Klux | +0.983 |
sleeper | +0.961 |
disasters | +0.866 |
liquids | +0.853 |
senal | +0.839 |
Neg logit contributions | |
ieth | -1.605 |
龍� | -1.482 |
iaries | -1.470 |
iary | -1.374 |
eded | -1.339 |
Token | of |
Token ID | 286 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
Klux | +3.196 |
sleeper | +3.173 |
disasters | +2.951 |
liquids | +2.910 |
plane | +2.852 |
Neg logit contributions | |
ieth | -3.575 |
龍� | -3.381 |
iaries | -3.253 |
iary | -2.998 |
姫 | -2.914 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
Klux | +0.485 |
sleeper | +0.470 |
disasters | +0.416 |
liquids | +0.409 |
senal | +0.407 |
Neg logit contributions | |
ieth | -0.980 |
龍� | -0.909 |
iaries | -0.904 |
iary | -0.849 |
eded | -0.831 |
Token | intelligence |
Token ID | 4430 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
sleeper | +7.067 |
Klux | +6.735 |
disasters | +6.337 |
liquids | +6.096 |
superpower | +5.769 |
Neg logit contributions | |
ieth | -12.939 |
龍� | -12.268 |
iaries | -11.858 |
iary | -11.126 |
shire | -10.883 |
Token | — |
Token ID | 960 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
Klux | +0.903 |
sleeper | +0.893 |
disasters | +0.819 |
liquids | +0.809 |
senal | +0.796 |
Neg logit contributions | |
ieth | -1.081 |
龍� | -0.991 |
iaries | -0.976 |
iary | -0.902 |
shire | -0.878 |
Token | got |
Token ID | 23442 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
Klux | +0.671 |
sleeper | +0.659 |
disasters | +0.611 |
liquids | +0.604 |
senal | +0.601 |
Neg logit contributions | |
ieth | -0.640 |
龍� | -0.577 |
iaries | -0.572 |
iary | -0.522 |
eded | -0.505 |
Token | underway |
Token ID | 17715 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Klux | +1.971 |
sleeper | +1.926 |
disasters | +1.729 |
liquids | +1.704 |
senal | +1.676 |
Neg logit contributions | |
ieth | -3.382 |
龍� | -3.137 |
iaries | -3.101 |
iary | -2.898 |
shire | -2.834 |
Token | in |
Token ID | 287 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ieth | +1.687 |
龍� | +1.522 |
iaries | +1.522 |
iary | +1.416 |
shire | +1.378 |
Neg logit contributions | |
Klux | -1.344 |
sleeper | -1.308 |
senal | -1.200 |
disasters | -1.194 |
liquids | -1.186 |
Token | face |
Token ID | 1986 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
Klux | +0.040 |
sleeper | +0.039 |
disasters | +0.036 |
liquids | +0.035 |
senal | +0.035 |
Neg logit contributions | |
ieth | -0.050 |
龍� | -0.046 |
iaries | -0.045 |
iary | -0.042 |
eded | -0.041 |
Token | facts |
Token ID | 6419 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
sleeper | +2.796 |
Klux | +2.787 |
disasters | +2.508 |
liquids | +2.449 |
senal | +2.290 |
Neg logit contributions | |
ieth | -6.487 |
iaries | -5.994 |
龍� | -5.987 |
iary | -5.638 |
shire | -5.538 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ieth | +1.329 |
龍� | +1.203 |
iaries | +1.194 |
iary | +1.100 |
eded | +1.066 |
Neg logit contributions | |
Klux | -1.241 |
sleeper | -1.214 |
disasters | -1.119 |
liquids | -1.107 |
senal | -1.106 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Klux | +1.177 |
sleeper | +1.151 |
disasters | +1.064 |
liquids | +1.051 |
senal | +1.045 |
Neg logit contributions | |
ieth | -1.272 |
龍� | -1.151 |
iaries | -1.144 |
iary | -1.053 |
eded | -1.021 |
Token |
|
Token ID | 198 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Klux | +2.123 |
sleeper | +2.076 |
disasters | +1.926 |
liquids | +1.907 |
senal | +1.880 |
Neg logit contributions | |
ieth | -2.084 |
龍� | -1.875 |
iaries | -1.865 |
iary | -1.704 |
eded | -1.647 |
Token | Turkey |
Token ID | 31632 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
Klux | +1.934 |
sleeper | +1.884 |
disasters | +1.745 |
liquids | +1.725 |
plane | +1.696 |
Neg logit contributions | |
ieth | -2.094 |
龍� | -1.897 |
iaries | -1.888 |
iary | -1.733 |
eded | -1.676 |
Token | and |
Token ID | 290 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
Klux | +8.166 |
sleeper | +8.147 |
disasters | +7.538 |
liquids | +7.395 |
plane | +7.177 |
Neg logit contributions | |
ieth | -10.534 |
龍� | -9.867 |
iaries | -9.807 |
iary | -8.961 |
urations | -8.688 |
Token | Azerbaijan |
Token ID | 33605 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
Klux | +1.877 |
sleeper | +1.834 |
disasters | +1.618 |
liquids | +1.595 |
senal | +1.558 |
Neg logit contributions | |
ieth | -3.923 |
龍� | -3.651 |
iaries | -3.624 |
iary | -3.405 |
shire | -3.324 |
Token | threaten |
Token ID | 16180 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
Klux | +3.594 |
sleeper | +3.539 |
disasters | +3.244 |
liquids | +3.216 |
plane | +3.122 |
Neg logit contributions | |
ieth | -4.523 |
龍� | -4.173 |
iaries | -4.101 |
iary | -3.786 |
eded | -3.667 |
Token | the |
Token ID | 262 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Klux | +2.883 |
sleeper | +2.849 |
disasters | +2.566 |
liquids | +2.536 |
senal | +2.448 |
Neg logit contributions | |
ieth | -4.819 |
龍� | -4.482 |
iaries | -4.428 |
iary | -4.146 |
shire | -4.026 |
Token | Armenian |
Token ID | 29388 |
Feature activation | +7.47e+00 |
Pos logit contributions | |
Klux | +1.260 |
sleeper | +1.234 |
disasters | +1.100 |
liquids | +1.084 |
senal | +1.068 |
Neg logit contributions | |
ieth | -2.285 |
龍� | -2.118 |
iaries | -2.104 |
iary | -1.971 |
eded | -1.922 |
Token | has |
Token ID | 468 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Klux | +6.703 |
sleeper | +6.684 |
disasters | +6.112 |
liquids | +6.027 |
plane | +5.850 |
Neg logit contributions | |
ieth | -8.484 |
龍� | -7.965 |
iaries | -7.816 |
iary | -7.141 |
urations | -6.938 |
Token | accused |
Token ID | 5371 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
Klux | +1.359 |
sleeper | +1.327 |
disasters | +1.201 |
liquids | +1.185 |
senal | +1.173 |
Neg logit contributions | |
ieth | -2.069 |
龍� | -1.906 |
iaries | -1.889 |
iary | -1.761 |
eded | -1.715 |
Token | Ukraine |
Token ID | 7049 |
Feature activation | +8.59e+00 |
Pos logit contributions | |
Klux | +1.810 |
sleeper | +1.779 |
disasters | +1.582 |
liquids | +1.548 |
senal | +1.509 |
Neg logit contributions | |
ieth | -3.466 |
龍� | -3.228 |
iaries | -3.193 |
iary | -2.991 |
eded | -2.919 |
Token | of |
Token ID | 286 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
sleeper | +7.066 |
Klux | +7.061 |
disasters | +6.549 |
liquids | +6.480 |
senal | +6.383 |
Neg logit contributions | |
ieth | -8.385 |
龍� | -7.847 |
iaries | -7.629 |
iary | -6.937 |
urations | -6.849 |
Token | stealing |
Token ID | 16568 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
Klux | +1.287 |
sleeper | +1.249 |
disasters | +1.108 |
liquids | +1.090 |
senal | +1.081 |
Neg logit contributions | |
ieth | -2.555 |
龍� | -2.368 |
iaries | -2.354 |
iary | -2.211 |
eded | -2.161 |
Token | gas |
Token ID | 3623 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
Klux | +3.000 |
sleeper | +2.991 |
disasters | +2.658 |
liquids | +2.649 |
plane | +2.522 |
Neg logit contributions | |
ieth | -5.456 |
龍� | -5.097 |
iaries | -5.025 |
iary | -4.704 |
姫 | -4.564 |
Token | meant |
Token ID | 4001 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
sleeper | +7.962 |
Klux | +7.887 |
liquids | +7.527 |
disasters | +7.419 |
plane | +6.991 |
Neg logit contributions | |
ieth | -11.011 |
龍� | -10.435 |
iaries | -10.072 |
iary | -9.303 |
urations | -9.003 |
Token | for |
Token ID | 329 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Klux | +1.913 |
sleeper | +1.898 |
disasters | +1.728 |
liquids | +1.698 |
senal | +1.660 |
Neg logit contributions | |
ieth | -2.793 |
龍� | -2.581 |
iaries | -2.548 |
iary | -2.355 |
eded | -2.289 |
Token | Europe |
Token ID | 2031 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
Klux | +1.894 |
sleeper | +1.848 |
disasters | +1.638 |
liquids | +1.611 |
senal | +1.580 |
Neg logit contributions | |
ieth | -3.840 |
龍� | -3.564 |
iaries | -3.540 |
iary | -3.326 |
shire | -3.248 |
Token | Russian |
Token ID | 3394 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
Klux | +2.767 |
sleeper | +2.753 |
disasters | +2.536 |
liquids | +2.514 |
senal | +2.441 |
Neg logit contributions | |
ieth | -2.988 |
龍� | -2.719 |
iaries | -2.706 |
iary | -2.482 |
eded | -2.396 |
Token | state |
Token ID | 1181 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
Klux | +3.743 |
sleeper | +3.733 |
disasters | +3.241 |
liquids | +3.199 |
senal | +3.017 |
Neg logit contributions | |
ieth | -8.497 |
龍� | -7.946 |
iaries | -7.870 |
iary | -7.401 |
shire | -7.226 |
Token | of |
Token ID | 286 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ieth | +0.434 |
龍� | +0.398 |
iaries | +0.390 |
iary | +0.356 |
shire | +0.347 |
Neg logit contributions | |
Klux | -0.437 |
sleeper | -0.432 |
disasters | -0.400 |
liquids | -0.399 |
senal | -0.389 |
Token | winter |
Token ID | 7374 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
Klux | +0.372 |
sleeper | +0.357 |
disasters | +0.314 |
senal | +0.313 |
liquids | +0.307 |
Neg logit contributions | |
ieth | -0.812 |
龍� | -0.751 |
iaries | -0.750 |
iary | -0.707 |
eded | -0.692 |
Token | supplies |
Token ID | 9416 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Klux | +1.951 |
sleeper | +1.934 |
disasters | +1.724 |
liquids | +1.712 |
senal | +1.631 |
Neg logit contributions | |
ieth | -3.518 |
龍� | -3.262 |
iaries | -3.225 |
iary | -3.024 |
eded | -2.950 |
Token | bound |
Token ID | 5421 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Klux | +1.600 |
sleeper | +1.573 |
disasters | +1.445 |
liquids | +1.431 |
senal | +1.388 |
Neg logit contributions | |
ieth | -1.984 |
龍� | -1.822 |
iaries | -1.802 |
iary | -1.663 |
shire | -1.614 |
Token | for |
Token ID | 329 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
Klux | +0.209 |
sleeper | +0.205 |
disasters | +0.187 |
liquids | +0.186 |
senal | +0.181 |
Neg logit contributions | |
ieth | -0.275 |
龍� | -0.253 |
iaries | -0.251 |
iary | -0.232 |
eded | -0.226 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
Klux | +1.533 |
sleeper | +1.506 |
disasters | +1.350 |
liquids | +1.327 |
senal | +1.295 |
Neg logit contributions | |
ieth | -2.729 |
龍� | -2.531 |
iaries | -2.502 |
iary | -2.346 |
eded | -2.288 |
Token | refugees |
Token ID | 8015 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
sleeper | +6.471 |
Klux | +6.055 |
disasters | +5.695 |
liquids | +5.516 |
turkey | +5.201 |
Neg logit contributions | |
ieth | -12.986 |
龍� | -12.338 |
iaries | -11.881 |
iary | -11.200 |
姫 | -11.083 |
Token | who |
Token ID | 508 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
sleeper | +3.880 |
Klux | +3.811 |
disasters | +3.529 |
liquids | +3.466 |
plane | +3.335 |
Neg logit contributions | |
ieth | -4.938 |
龍� | -4.644 |
iaries | -4.494 |
iary | -4.131 |
shire | -4.043 |
Token | have |
Token ID | 423 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Klux | +2.044 |
sleeper | +2.018 |
disasters | +1.849 |
liquids | +1.827 |
senal | +1.774 |
Neg logit contributions | |
ieth | -2.512 |
龍� | -2.312 |
iaries | -2.264 |
iary | -2.096 |
shire | -2.033 |
Token | no |
Token ID | 645 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Klux | +0.855 |
sleeper | +0.838 |
disasters | +0.754 |
liquids | +0.742 |
senal | +0.726 |
Neg logit contributions | |
ieth | -1.421 |
龍� | -1.315 |
iaries | -1.300 |
iary | -1.216 |
shire | -1.186 |
Token | idea |
Token ID | 2126 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Klux | +1.083 |
sleeper | +1.051 |
disasters | +0.947 |
liquids | +0.933 |
senal | +0.932 |
Neg logit contributions | |
ieth | -1.776 |
龍� | -1.635 |
iaries | -1.626 |
iary | -1.521 |
eded | -1.483 |
Token | een |
Token ID | 6429 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
ieth | +0.395 |
iaries | +0.327 |
龍� | +0.323 |
iary | +0.281 |
eded | +0.262 |
Neg logit contributions | |
Klux | -0.907 |
sleeper | -0.895 |
senal | -0.852 |
disasters | -0.847 |
liquids | -0.839 |
Token | , |
Token ID | 11 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ieth | +1.004 |
iaries | +0.907 |
龍� | +0.907 |
iary | +0.840 |
shire | +0.815 |
Neg logit contributions | |
Klux | -0.857 |
sleeper | -0.832 |
disasters | -0.766 |
senal | -0.766 |
liquids | -0.758 |
Token | run |
Token ID | 1057 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
Klux | +0.234 |
sleeper | +0.228 |
disasters | +0.208 |
liquids | +0.205 |
senal | +0.204 |
Neg logit contributions | |
ieth | -0.324 |
龍� | -0.297 |
iaries | -0.295 |
iary | -0.274 |
eded | -0.267 |
Token | by |
Token ID | 416 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Klux | +2.995 |
sleeper | +2.987 |
disasters | +2.648 |
liquids | +2.633 |
plane | +2.561 |
Neg logit contributions | |
ieth | -4.381 |
龍� | -4.108 |
iaries | -3.992 |
iary | -3.656 |
eded | -3.622 |
Token | Indian |
Token ID | 3942 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
Klux | +1.198 |
sleeper | +1.172 |
disasters | +1.051 |
liquids | +1.035 |
senal | +1.018 |
Neg logit contributions | |
ieth | -1.982 |
龍� | -1.833 |
iaries | -1.815 |
iary | -1.697 |
eded | -1.652 |
Token | Rail |
Token ID | 12950 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
Klux | +3.967 |
sleeper | +3.895 |
disasters | +3.503 |
liquids | +3.477 |
senal | +3.377 |
Neg logit contributions | |
ieth | -5.736 |
iaries | -5.307 |
龍� | -5.303 |
iary | -4.919 |
eded | -4.772 |
Token | ways |
Token ID | 1322 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
Klux | +6.129 |
sleeper | +6.070 |
disasters | +5.401 |
plane | +5.260 |
liquids | +5.157 |
Neg logit contributions | |
ieth | -12.187 |
iaries | -11.708 |
龍� | -11.663 |
iary | -10.771 |
eded | -10.418 |
Token | , |
Token ID | 11 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
sleeper | +4.387 |
Klux | +4.364 |
disasters | +3.980 |
liquids | +3.936 |
senal | +3.836 |
Neg logit contributions | |
ieth | -4.987 |
龍� | -4.599 |
iaries | -4.573 |
iary | -4.165 |
eded | -4.073 |
Token | operates |
Token ID | 14051 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
Klux | +0.043 |
sleeper | +0.042 |
disasters | +0.039 |
liquids | +0.039 |
senal | +0.038 |
Neg logit contributions | |
ieth | -0.051 |
龍� | -0.046 |
iaries | -0.046 |
iary | -0.042 |
eded | -0.041 |
Token | from |
Token ID | 422 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Klux | +0.422 |
sleeper | +0.410 |
disasters | +0.374 |
senal | +0.371 |
liquids | +0.369 |
Neg logit contributions | |
ieth | -0.576 |
龍� | -0.525 |
iaries | -0.524 |
iary | -0.488 |
shire | -0.474 |
Token | Room |
Token ID | 10096 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
Klux | +1.257 |
sleeper | +1.234 |
disasters | +1.116 |
liquids | +1.100 |
senal | +1.084 |
Neg logit contributions | |
ieth | -1.826 |
龍� | -1.683 |
iaries | -1.664 |
iary | -1.549 |
eded | -1.508 |
Token |
|
Token ID | 198 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
Klux | +0.468 |
sleeper | +0.462 |
senal | +0.460 |
disasters | +0.427 |
liquids | +0.422 |
Neg logit contributions | |
ieth | -0.379 |
龍� | -0.336 |
iaries | -0.331 |
iary | -0.308 |
shire | -0.299 |
Token | Me |
Token ID | 5308 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
Klux | +0.356 |
sleeper | +0.348 |
disasters | +0.321 |
liquids | +0.318 |
senal | +0.312 |
Neg logit contributions | |
ieth | -0.382 |
龍� | -0.345 |
iaries | -0.344 |
iary | -0.314 |
eded | -0.305 |
Token | ant |
Token ID | 415 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
ieth | +0.069 |
龍� | +0.063 |
iaries | +0.062 |
iary | +0.056 |
shire | +0.054 |
Neg logit contributions | |
Klux | -0.081 |
sleeper | -0.079 |
disasters | -0.074 |
liquids | -0.073 |
senal | -0.071 |
Token | ime |
Token ID | 524 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Klux | +0.082 |
sleeper | +0.081 |
disasters | +0.076 |
liquids | +0.075 |
senal | +0.074 |
Neg logit contributions | |
ieth | -0.053 |
龍� | -0.048 |
iaries | -0.047 |
iary | -0.041 |
shire | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Klux | +2.217 |
sleeper | +2.200 |
disasters | +2.012 |
senal | +1.963 |
liquids | +1.959 |
Neg logit contributions | |
ieth | -2.754 |
龍� | -2.533 |
iaries | -2.524 |
iary | -2.294 |
eded | -2.259 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
ieth | +0.196 |
龍� | +0.180 |
iaries | +0.179 |
iary | +0.167 |
eded | +0.162 |
Neg logit contributions | |
Klux | -0.130 |
sleeper | -0.127 |
disasters | -0.115 |
liquids | -0.113 |
senal | -0.113 |
Token | Kurds |
Token ID | 23880 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
sleeper | +6.553 |
Klux | +6.266 |
disasters | +5.722 |
liquids | +5.648 |
plane | +5.433 |
Neg logit contributions | |
ieth | -12.193 |
龍� | -11.422 |
iaries | -11.215 |
iary | -10.452 |
urations | -10.132 |
Token | are |
Token ID | 389 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Klux | +4.583 |
sleeper | +4.545 |
disasters | +4.126 |
liquids | +4.091 |
plane | +4.008 |
Neg logit contributions | |
ieth | -5.774 |
龍� | -5.338 |
iaries | -5.249 |
iary | -4.816 |
eded | -4.643 |
Token | assembling |
Token ID | 40525 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
Klux | +1.311 |
sleeper | +1.272 |
disasters | +1.137 |
liquids | +1.121 |
senal | +1.115 |
Neg logit contributions | |
ieth | -2.379 |
龍� | -2.197 |
iaries | -2.185 |
iary | -2.050 |
eded | -2.002 |
Token | a |
Token ID | 257 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
ieth | +3.603 |
iaries | +3.271 |
龍� | +3.251 |
iary | +3.059 |
eded | +2.987 |
Neg logit contributions | |
Klux | -2.499 |
sleeper | -2.394 |
senal | -2.218 |
disasters | -2.198 |
liquids | -2.183 |
Token | draft |
Token ID | 4538 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
Klux | +0.333 |
sleeper | +0.323 |
disasters | +0.289 |
liquids | +0.285 |
senal | +0.283 |
Neg logit contributions | |
ieth | -0.614 |
龍� | -0.567 |
iaries | -0.564 |
iary | -0.530 |
eded | -0.517 |
Token | Earlier |
Token ID | 13689 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
Klux | +3.128 |
sleeper | +3.038 |
disasters | +2.803 |
liquids | +2.770 |
plane | +2.764 |
Neg logit contributions | |
ieth | -3.346 |
龍� | -3.035 |
iaries | -3.030 |
iary | -2.756 |
shire | -2.669 |
Token | today |
Token ID | 1909 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Klux | +1.425 |
sleeper | +1.385 |
disasters | +1.249 |
liquids | +1.214 |
senal | +1.194 |
Neg logit contributions | |
ieth | -2.716 |
龍� | -2.540 |
iaries | -2.511 |
iary | -2.355 |
shire | -2.308 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Klux | +1.604 |
sleeper | +1.583 |
disasters | +1.448 |
liquids | +1.428 |
senal | +1.412 |
Neg logit contributions | |
ieth | -1.977 |
龍� | -1.823 |
iaries | -1.801 |
iary | -1.662 |
eded | -1.620 |
Token | the |
Token ID | 262 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Klux | +1.296 |
sleeper | +1.267 |
disasters | +1.149 |
liquids | +1.132 |
senal | +1.118 |
Neg logit contributions | |
ieth | -1.940 |
龍� | -1.785 |
iaries | -1.770 |
iary | -1.650 |
eded | -1.609 |
Token | first |
Token ID | 717 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
Klux | +1.759 |
sleeper | +1.728 |
disasters | +1.567 |
liquids | +1.549 |
senal | +1.512 |
Neg logit contributions | |
ieth | -2.457 |
龍� | -2.266 |
iaries | -2.240 |
iary | -2.080 |
eded | -2.026 |
Token | Ebola |
Token ID | 15825 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Klux | +0.586 |
sleeper | +0.576 |
disasters | +0.522 |
liquids | +0.517 |
senal | +0.502 |
Neg logit contributions | |
ieth | -0.880 |
龍� | -0.814 |
iaries | -0.805 |
iary | -0.749 |
eded | -0.732 |
Token | patient |
Token ID | 5827 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
sleeper | +6.947 |
Klux | +6.595 |
disasters | +6.250 |
liquids | +6.059 |
plane | +5.723 |
Neg logit contributions | |
ieth | -11.520 |
龍� | -11.019 |
iaries | -10.547 |
姫 | -9.941 |
iary | -9.753 |
Token | to |
Token ID | 284 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
sleeper | +4.486 |
Klux | +4.361 |
disasters | +4.083 |
liquids | +4.022 |
plane | +3.863 |
Neg logit contributions | |
ieth | -6.129 |
龍� | -5.823 |
iaries | -5.617 |
iary | -5.191 |
姫 | -5.137 |
Token | have |
Token ID | 423 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Klux | +0.501 |
sleeper | +0.493 |
disasters | +0.454 |
liquids | +0.450 |
senal | +0.439 |
Neg logit contributions | |
ieth | -0.581 |
龍� | -0.530 |
iaries | -0.524 |
iary | -0.484 |
shire | -0.470 |
Token | been |
Token ID | 587 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Klux | +1.379 |
sleeper | +1.366 |
disasters | +1.234 |
liquids | +1.217 |
plane | +1.175 |
Neg logit contributions | |
ieth | -2.173 |
龍� | -2.017 |
iaries | -1.989 |
iary | -1.855 |
shire | -1.813 |
Token | diagnosed |
Token ID | 14641 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
Klux | +1.163 |
sleeper | +1.146 |
disasters | +1.042 |
liquids | +1.028 |
senal | +1.006 |
Neg logit contributions | |
ieth | -1.590 |
龍� | -1.463 |
iaries | -1.446 |
iary | -1.342 |
shire | -1.306 |
Token | on |
Token ID | 319 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Klux | +2.217 |
sleeper | +2.174 |
disasters | +1.979 |
liquids | +1.931 |
plane | +1.886 |
Neg logit contributions | |
ieth | -3.540 |
龍� | -3.295 |
iaries | -3.255 |
iary | -3.027 |
eded | -2.946 |
Token | the |
Token ID | 262 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
Klux | +0.623 |
sleeper | +0.604 |
disasters | +0.530 |
liquids | +0.521 |
senal | +0.516 |
Neg logit contributions | |
ieth | -1.377 |
龍� | -1.280 |
iaries | -1.273 |
iary | -1.199 |
eded | -1.172 |
Token | administration |
Token ID | 3662 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
Klux | +0.184 |
sleeper | +0.177 |
disasters | +0.156 |
senal | +0.154 |
liquids | +0.153 |
Neg logit contributions | |
ieth | -0.405 |
龍� | -0.375 |
iaries | -0.374 |
iary | -0.352 |
eded | -0.345 |
Token | of |
Token ID | 286 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
ieth | +0.977 |
龍� | +0.885 |
iaries | +0.879 |
iary | +0.811 |
shire | +0.786 |
Neg logit contributions | |
Klux | -0.881 |
sleeper | -0.859 |
disasters | -0.792 |
senal | -0.785 |
liquids | -0.784 |
Token | embattled |
Token ID | 49118 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
ieth | +0.394 |
龍� | +0.364 |
iaries | +0.362 |
iary | +0.341 |
eded | +0.334 |
Neg logit contributions | |
Klux | -0.196 |
sleeper | -0.190 |
disasters | -0.169 |
senal | -0.167 |
liquids | -0.166 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
ieth | +0.748 |
龍� | +0.688 |
iaries | +0.688 |
iary | +0.649 |
eded | +0.635 |
Neg logit contributions | |
Klux | -0.376 |
sleeper | -0.363 |
senal | -0.331 |
disasters | -0.325 |
liquids | -0.319 |
Token | President |
Token ID | 1992 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
sleeper | +3.867 |
Klux | +3.671 |
disasters | +2.964 |
liquids | +2.824 |
plane | +2.754 |
Neg logit contributions | |
ieth | -14.864 |
龍� | -13.884 |
iaries | -13.797 |
iary | -13.054 |
shire | -12.787 |
Token | Bashar |
Token ID | 24463 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ieth | +2.544 |
龍� | +2.364 |
iaries | +2.362 |
iary | +2.234 |
eded | +2.190 |
Neg logit contributions | |
Klux | -1.059 |
sleeper | -1.010 |
disasters | -0.882 |
senal | -0.874 |
liquids | -0.865 |
Token | Assad |
Token ID | 13032 |
Feature activation | +7.89e+00 |
Pos logit contributions | |
Klux | +1.960 |
sleeper | +1.917 |
disasters | +1.720 |
liquids | +1.696 |
plane | +1.663 |
Neg logit contributions | |
ieth | -3.246 |
龍� | -2.967 |
iaries | -2.941 |
iary | -2.733 |
eded | -2.677 |
Token | and |
Token ID | 290 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Klux | +6.769 |
sleeper | +6.699 |
disasters | +6.176 |
liquids | +6.056 |
plane | +6.004 |
Neg logit contributions | |
ieth | -7.622 |
龍� | -7.011 |
iaries | -6.915 |
iary | -6.250 |
eded | -6.049 |
Token | for |
Token ID | 329 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Klux | +1.353 |
sleeper | +1.322 |
disasters | +1.205 |
liquids | +1.189 |
senal | +1.175 |
Neg logit contributions | |
ieth | -1.870 |
龍� | -1.715 |
iaries | -1.702 |
iary | -1.580 |
eded | -1.537 |
Token | � |
Token ID | 447 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
Klux | +2.740 |
sleeper | +2.706 |
disasters | +2.513 |
liquids | +2.503 |
plane | +2.401 |
Neg logit contributions | |
ieth | -2.924 |
龍� | -2.678 |
iaries | -2.657 |
iary | -2.421 |
eded | -2.354 |
Token | � |
Token ID | 247 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Klux | +0.731 |
sleeper | +0.724 |
senal | +0.675 |
disasters | +0.673 |
liquids | +0.665 |
Neg logit contributions | |
ieth | -0.624 |
龍� | -0.560 |
iaries | -0.552 |
iary | -0.505 |
shire | -0.498 |
Token | s |
Token ID | 82 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Klux | +2.385 |
sleeper | +2.356 |
senal | +2.255 |
disasters | +2.249 |
liquids | +2.230 |
Neg logit contributions | |
ieth | -0.520 |
龍� | -0.373 |
iaries | -0.361 |
iary | -0.259 |
shire | -0.231 |
Token | Trans |
Token ID | 3602 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
ieth | +2.143 |
龍� | +1.951 |
iaries | +1.943 |
iary | +1.817 |
eded | +1.779 |
Neg logit contributions | |
Klux | -1.376 |
sleeper | -1.327 |
senal | -1.212 |
disasters | -1.195 |
liquids | -1.176 |
Token | Mountain |
Token ID | 9638 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
Klux | +3.724 |
sleeper | +3.616 |
disasters | +3.305 |
liquids | +3.277 |
plane | +3.164 |
Neg logit contributions | |
ieth | -5.037 |
龍� | -4.668 |
iaries | -4.632 |
iary | -4.259 |
urations | -4.104 |
Token | pipeline |
Token ID | 11523 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Klux | +2.975 |
sleeper | +2.966 |
liquids | +2.654 |
disasters | +2.645 |
plane | +2.464 |
Neg logit contributions | |
ieth | -5.812 |
龍� | -5.477 |
iaries | -5.425 |
iary | -5.051 |
eded | -4.954 |
Token | expansion |
Token ID | 7118 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
sleeper | +7.428 |
Klux | +7.043 |
liquids | +6.801 |
disasters | +6.789 |
plane | +6.292 |
Neg logit contributions | |
ieth | -10.681 |
龍� | -10.328 |
iaries | -10.083 |
iary | -9.094 |
urations | -9.060 |
Token | , |
Token ID | 11 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
Klux | +0.315 |
sleeper | +0.311 |
disasters | +0.285 |
liquids | +0.282 |
senal | +0.275 |
Neg logit contributions | |
ieth | -0.402 |
龍� | -0.370 |
iaries | -0.366 |
iary | -0.337 |
eded | -0.329 |
Token | which |
Token ID | 543 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
ieth | +0.427 |
龍� | +0.389 |
iaries | +0.387 |
iary | +0.359 |
eded | +0.350 |
Neg logit contributions | |
Klux | -0.327 |
sleeper | -0.319 |
disasters | -0.292 |
liquids | -0.288 |
senal | -0.288 |
Token | Trudeau |
Token ID | 17524 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Klux | +1.690 |
sleeper | +1.653 |
disasters | +1.513 |
liquids | +1.498 |
senal | +1.466 |
Neg logit contributions | |
ieth | -2.189 |
龍� | -2.008 |
iaries | -1.991 |
iary | -1.845 |
eded | -1.791 |
Token | � |
Token ID | 447 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Klux | +1.237 |
sleeper | +1.209 |
disasters | +1.114 |
liquids | +1.099 |
senal | +1.076 |
Neg logit contributions | |
ieth | -1.501 |
龍� | -1.375 |
iaries | -1.361 |
iary | -1.258 |
eded | -1.214 |
Token | photo |
Token ID | 4590 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
Klux | +1.137 |
sleeper | +1.116 |
disasters | +1.021 |
liquids | +1.009 |
senal | +0.997 |
Neg logit contributions | |
ieth | -1.412 |
龍� | -1.291 |
iaries | -1.281 |
iary | -1.185 |
eded | -1.152 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Klux | +3.704 |
sleeper | +3.668 |
disasters | +3.368 |
liquids | +3.300 |
plane | +3.237 |
Neg logit contributions | |
ieth | -4.753 |
龍� | -4.379 |
iaries | -4.348 |
iary | -3.991 |
eded | -3.883 |
Token | showing |
Token ID | 4478 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Klux | +0.799 |
sleeper | +0.782 |
disasters | +0.711 |
liquids | +0.701 |
senal | +0.693 |
Neg logit contributions | |
ieth | -1.127 |
龍� | -1.035 |
iaries | -1.029 |
iary | -0.956 |
eded | -0.930 |
Token | a |
Token ID | 257 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Klux | +1.395 |
sleeper | +1.372 |
disasters | +1.220 |
liquids | +1.202 |
senal | +1.170 |
Neg logit contributions | |
ieth | -2.677 |
龍� | -2.487 |
iaries | -2.457 |
iary | -2.306 |
eded | -2.251 |
Token | dead |
Token ID | 2636 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
Klux | +0.835 |
sleeper | +0.810 |
disasters | +0.721 |
liquids | +0.710 |
senal | +0.706 |
Neg logit contributions | |
ieth | -1.606 |
龍� | -1.486 |
iaries | -1.478 |
iary | -1.387 |
eded | -1.356 |
Token | Palestinian |
Token ID | 8501 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
sleeper | +2.178 |
Klux | +2.150 |
disasters | +1.863 |
liquids | +1.838 |
plane | +1.812 |
Neg logit contributions | |
ieth | -4.455 |
龍� | -4.183 |
iaries | -4.099 |
iary | -3.830 |
姫 | -3.745 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
sleeper | +6.799 |
Klux | +6.374 |
disasters | +5.752 |
liquids | +5.695 |
plane | +5.639 |
Neg logit contributions | |
ieth | -11.525 |
龍� | -10.843 |
iaries | -10.602 |
iary | -9.682 |
urations | -9.612 |
Token | covered |
Token ID | 5017 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Klux | +1.261 |
sleeper | +1.251 |
disasters | +1.139 |
liquids | +1.127 |
plane | +1.095 |
Neg logit contributions | |
ieth | -1.666 |
龍� | -1.533 |
iaries | -1.517 |
iary | -1.402 |
eded | -1.364 |
Token | in |
Token ID | 287 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Klux | +1.065 |
sleeper | +1.052 |
disasters | +0.952 |
liquids | +0.937 |
plane | +0.911 |
Neg logit contributions | |
ieth | -1.521 |
龍� | -1.416 |
iaries | -1.392 |
iary | -1.283 |
eded | -1.258 |
Token | blood |
Token ID | 2910 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
ieth | +1.710 |
iaries | +1.589 |
龍� | +1.583 |
iary | +1.502 |
eded | +1.471 |
Neg logit contributions | |
Klux | -0.710 |
sleeper | -0.669 |
senal | -0.601 |
disasters | -0.585 |
liquids | -0.566 |
Token | in |
Token ID | 287 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
sleeper | +4.083 |
Klux | +4.078 |
liquids | +3.733 |
disasters | +3.726 |
plane | +3.638 |
Neg logit contributions | |
ieth | -5.021 |
龍� | -4.710 |
iaries | -4.583 |
iary | -4.159 |
姫 | -4.070 |
Token | Although |
Token ID | 7003 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Klux | +0.866 |
sleeper | +0.847 |
disasters | +0.777 |
liquids | +0.769 |
senal | +0.757 |
Neg logit contributions | |
ieth | -1.021 |
龍� | -0.931 |
iaries | -0.925 |
iary | -0.851 |
eded | -0.825 |
Token | some |
Token ID | 617 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
Klux | +1.683 |
sleeper | +1.653 |
disasters | +1.478 |
liquids | +1.451 |
senal | +1.424 |
Neg logit contributions | |
ieth | -3.145 |
龍� | -2.921 |
iaries | -2.898 |
iary | -2.712 |
eded | -2.645 |
Token | believe |
Token ID | 1975 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Klux | +0.298 |
sleeper | +0.290 |
disasters | +0.263 |
liquids | +0.259 |
senal | +0.258 |
Neg logit contributions | |
ieth | -0.455 |
龍� | -0.418 |
iaries | -0.415 |
iary | -0.387 |
eded | -0.378 |
Token | that |
Token ID | 326 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
Klux | +1.307 |
sleeper | +1.281 |
disasters | +1.138 |
liquids | +1.117 |
senal | +1.100 |
Neg logit contributions | |
ieth | -2.560 |
龍� | -2.378 |
iaries | -2.359 |
iary | -2.210 |
eded | -2.164 |
Token | the |
Token ID | 262 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Klux | +1.995 |
sleeper | +1.974 |
disasters | +1.763 |
liquids | +1.729 |
senal | +1.684 |
Neg logit contributions | |
ieth | -3.699 |
龍� | -3.436 |
iaries | -3.403 |
iary | -3.178 |
eded | -3.105 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +9.91e+00 |
Pos logit contributions | |
Klux | +1.105 |
sleeper | +1.081 |
disasters | +0.981 |
liquids | +0.967 |
senal | +0.957 |
Neg logit contributions | |
ieth | -1.644 |
龍� | -1.512 |
iaries | -1.500 |
iary | -1.397 |
eded | -1.360 |
Token | government |
Token ID | 1230 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
sleeper | +5.601 |
Klux | +5.477 |
disasters | +4.976 |
liquids | +4.756 |
plane | +4.608 |
Neg logit contributions | |
ieth | -12.680 |
龍� | -11.963 |
iaries | -11.652 |
iary | -10.849 |
姫 | -10.726 |
Token | helped |
Token ID | 4193 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
sleeper | +3.389 |
Klux | +3.381 |
disasters | +3.107 |
liquids | +3.060 |
plane | +2.966 |
Neg logit contributions | |
ieth | -4.224 |
龍� | -3.947 |
iaries | -3.823 |
iary | -3.503 |
shire | -3.408 |
Token | facilitate |
Token ID | 15570 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Klux | +1.407 |
sleeper | +1.372 |
disasters | +1.239 |
liquids | +1.221 |
senal | +1.212 |
Neg logit contributions | |
ieth | -2.232 |
龍� | -2.055 |
iaries | -2.041 |
iary | -1.906 |
eded | -1.858 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ieth | +1.723 |
龍� | +1.581 |
iaries | +1.578 |
iary | +1.487 |
eded | +1.456 |
Neg logit contributions | |
Klux | -0.907 |
sleeper | -0.864 |
senal | -0.774 |
disasters | -0.769 |
liquids | -0.764 |
Token | P |
Token ID | 350 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Klux | +0.758 |
sleeper | +0.739 |
disasters | +0.668 |
liquids | +0.659 |
senal | +0.654 |
Neg logit contributions | |
ieth | -1.189 |
龍� | -1.094 |
iaries | -1.087 |
iary | -1.015 |
eded | -0.989 |
Token | to |
Token ID | 284 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
Klux | +0.622 |
sleeper | +0.608 |
disasters | +0.554 |
liquids | +0.547 |
senal | +0.532 |
Neg logit contributions | |
ieth | -0.911 |
龍� | -0.837 |
iaries | -0.834 |
iary | -0.773 |
shire | -0.748 |
Token | an |
Token ID | 281 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ieth | +1.145 |
龍� | +1.059 |
iaries | +1.053 |
iary | +0.989 |
eded | +0.968 |
Neg logit contributions | |
Klux | -0.588 |
sleeper | -0.569 |
disasters | -0.506 |
liquids | -0.498 |
senal | -0.497 |
Token | En |
Token ID | 2039 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
ieth | +0.315 |
龍� | +0.291 |
iaries | +0.289 |
iary | +0.271 |
eded | +0.265 |
Neg logit contributions | |
Klux | -0.174 |
sleeper | -0.168 |
disasters | -0.151 |
liquids | -0.148 |
senal | -0.148 |
Token | bridge |
Token ID | 9458 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
ieth | +0.760 |
龍� | +0.685 |
iaries | +0.680 |
iary | +0.627 |
shire | +0.609 |
Neg logit contributions | |
Klux | -0.727 |
sleeper | -0.713 |
disasters | -0.658 |
senal | -0.655 |
liquids | -0.650 |
Token | Inc |
Token ID | 3457 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Klux | +2.408 |
sleeper | +2.377 |
disasters | +2.142 |
liquids | +2.117 |
senal | +2.026 |
Neg logit contributions | |
ieth | -4.078 |
龍� | -3.787 |
iaries | -3.767 |
iary | -3.502 |
eded | -3.411 |
Token | pipeline |
Token ID | 11523 |
Feature activation | +9.89e+00 |
Pos logit contributions | |
ieth | +2.624 |
龍� | +2.419 |
iaries | +2.410 |
iary | +2.268 |
shire | +2.220 |
Neg logit contributions | |
Klux | -1.346 |
sleeper | -1.292 |
disasters | -1.149 |
senal | -1.144 |
liquids | -1.126 |
Token | . |
Token ID | 13 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
sleeper | +8.407 |
Klux | +7.948 |
disasters | +7.760 |
liquids | +7.640 |
plane | +7.241 |
Neg logit contributions | |
ieth | -9.524 |
龍� | -9.186 |
iaries | -8.995 |
姫 | -8.035 |
urations | -8.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ieth | +0.067 |
龍� | +0.060 |
iaries | +0.060 |
iary | +0.055 |
shire | +0.053 |
Neg logit contributions | |
Klux | -0.074 |
sleeper | -0.073 |
senal | -0.068 |
disasters | -0.068 |
liquids | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Klux | +1.373 |
sleeper | +1.352 |
senal | +1.333 |
disasters | +1.249 |
liquids | +1.234 |
Neg logit contributions | |
ieth | -1.136 |
龍� | -1.003 |
iaries | -0.990 |
iary | -0.920 |
shire | -0.895 |
Token | File |
Token ID | 8979 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
Klux | +1.059 |
sleeper | +1.026 |
disasters | +0.949 |
liquids | +0.942 |
plane | +0.927 |
Neg logit contributions | |
ieth | -1.259 |
龍� | -1.156 |
iaries | -1.150 |
iary | -1.057 |
eded | -1.023 |
Token | Photo |
Token ID | 5555 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
Klux | +1.686 |
sleeper | +1.640 |
disasters | +1.469 |
liquids | +1.429 |
senal | +1.394 |
Neg logit contributions | |
ieth | -3.255 |
龍� | -3.047 |
iaries | -2.988 |
iary | -2.802 |
eded | -2.762 |
Token | away |
Token ID | 1497 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
Klux | +1.049 |
sleeper | +1.023 |
disasters | +0.915 |
liquids | +0.902 |
senal | +0.891 |
Neg logit contributions | |
ieth | -1.837 |
龍� | -1.699 |
iaries | -1.687 |
iary | -1.579 |
eded | -1.542 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Klux | +2.935 |
sleeper | +2.898 |
disasters | +2.672 |
liquids | +2.604 |
plane | +2.574 |
Neg logit contributions | |
ieth | -3.238 |
龍� | -2.993 |
iaries | -2.965 |
iary | -2.700 |
eded | -2.626 |
Token | according |
Token ID | 1864 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ieth | +0.199 |
龍� | +0.181 |
iaries | +0.180 |
iary | +0.168 |
shire | +0.163 |
Neg logit contributions | |
Klux | -0.151 |
sleeper | -0.146 |
disasters | -0.134 |
liquids | -0.132 |
senal | -0.132 |
Token | to |
Token ID | 284 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
ieth | +1.324 |
iaries | +1.192 |
龍� | +1.188 |
iary | +1.125 |
shire | +1.096 |
Neg logit contributions | |
senal | -1.205 |
Klux | -1.200 |
sleeper | -1.177 |
disasters | -1.078 |
liquids | -1.063 |
Token | the |
Token ID | 262 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
ieth | +0.801 |
龍� | +0.737 |
iaries | +0.735 |
iary | +0.688 |
shire | +0.674 |
Neg logit contributions | |
Klux | -0.467 |
sleeper | -0.451 |
disasters | -0.405 |
senal | -0.401 |
liquids | -0.400 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +9.86e+00 |
Pos logit contributions | |
Klux | +0.058 |
sleeper | +0.056 |
disasters | +0.051 |
liquids | +0.050 |
senal | +0.050 |
Neg logit contributions | |
ieth | -0.095 |
龍� | -0.087 |
iaries | -0.087 |
iary | -0.081 |
eded | -0.079 |
Token | Observatory |
Token ID | 25758 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
sleeper | +5.937 |
Klux | +5.790 |
disasters | +5.159 |
liquids | +5.013 |
plane | +4.921 |
Neg logit contributions | |
ieth | -12.185 |
龍� | -11.497 |
iaries | -11.279 |
iary | -10.539 |
姫 | -10.369 |
Token | for |
Token ID | 329 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ieth | +0.595 |
龍� | +0.548 |
iaries | +0.541 |
iary | +0.501 |
shire | +0.489 |
Neg logit contributions | |
Klux | -0.456 |
sleeper | -0.449 |
disasters | -0.409 |
liquids | -0.405 |
senal | -0.401 |
Token | Human |
Token ID | 5524 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
Klux | +1.338 |
sleeper | +1.281 |
disasters | +1.146 |
senal | +1.141 |
liquids | +1.132 |
Neg logit contributions | |
ieth | -2.341 |
iaries | -2.157 |
龍� | -2.153 |
iary | -2.021 |
eded | -1.974 |
Token | Rights |
Token ID | 6923 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
Klux | +2.890 |
sleeper | +2.807 |
disasters | +2.496 |
liquids | +2.447 |
senal | +2.404 |
Neg logit contributions | |
ieth | -6.064 |
龍� | -5.655 |
iaries | -5.588 |
iary | -5.255 |
eded | -5.146 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
sleeper | +5.514 |
Klux | +5.353 |
disasters | +5.080 |
liquids | +4.982 |
plane | +4.897 |
Neg logit contributions | |
ieth | -5.390 |
龍� | -5.106 |
iaries | -4.843 |
iary | -4.381 |
eded | -4.313 |
Token | Western |
Token ID | 4885 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
ieth | +0.596 |
龍� | +0.549 |
iaries | +0.546 |
iary | +0.515 |
eded | +0.503 |
Neg logit contributions | |
Klux | -0.307 |
sleeper | -0.296 |
disasters | -0.263 |
senal | -0.261 |
liquids | -0.259 |
Token | defence |
Token ID | 9366 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
Klux | +0.152 |
sleeper | +0.147 |
disasters | +0.127 |
liquids | +0.124 |
senal | +0.122 |
Neg logit contributions | |
ieth | -0.396 |
龍� | -0.371 |
iaries | -0.368 |
iary | -0.348 |
eded | -0.341 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
sleeper | +4.084 |
Klux | +4.044 |
disasters | +3.810 |
liquids | +3.721 |
plane | +3.668 |
Neg logit contributions | |
ieth | -4.123 |
龍� | -3.904 |
iaries | -3.815 |
iary | -3.445 |
eded | -3.347 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
ieth | +0.152 |
龍� | +0.140 |
iaries | +0.137 |
iary | +0.125 |
eded | +0.122 |
Neg logit contributions | |
Klux | -0.138 |
sleeper | -0.134 |
disasters | -0.124 |
plane | -0.122 |
liquids | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
Klux | +0.378 |
senal | +0.377 |
sleeper | +0.373 |
disasters | +0.345 |
liquids | +0.342 |
Neg logit contributions | |
ieth | -0.301 |
龍� | -0.262 |
iaries | -0.261 |
iary | -0.245 |
shire | -0.237 |
Token | Syria |
Token ID | 40029 |
Feature activation | +9.85e+00 |
Pos logit contributions | |
Klux | +0.330 |
sleeper | +0.321 |
disasters | +0.296 |
liquids | +0.293 |
plane | +0.288 |
Neg logit contributions | |
ieth | -0.370 |
龍� | -0.337 |
iaries | -0.335 |
iary | -0.307 |
eded | -0.298 |
Token | , |
Token ID | 11 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
sleeper | +7.871 |
Klux | +7.671 |
disasters | +7.272 |
liquids | +7.008 |
plane | +6.848 |
Neg logit contributions | |
ieth | -10.085 |
龍� | -9.639 |
iaries | -9.237 |
iary | -8.385 |
urations | -8.222 |
Token | terrorism |
Token ID | 8649 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
Klux | +0.128 |
sleeper | +0.123 |
senal | +0.111 |
disasters | +0.111 |
liquids | +0.110 |
Neg logit contributions | |
ieth | -0.202 |
iaries | -0.184 |
龍� | -0.184 |
iary | -0.172 |
shire | -0.168 |
Token | and |
Token ID | 290 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
sleeper | +4.117 |
Klux | +4.070 |
disasters | +3.806 |
liquids | +3.704 |
plane | +3.600 |
Neg logit contributions | |
ieth | -4.405 |
龍� | -4.148 |
iaries | -3.959 |
iary | -3.612 |
eded | -3.508 |
Token | Russia |
Token ID | 3284 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
Klux | +1.152 |
sleeper | +1.107 |
disasters | +0.974 |
senal | +0.965 |
liquids | +0.960 |
Neg logit contributions | |
ieth | -2.459 |
龍� | -2.275 |
iaries | -2.266 |
iary | -2.136 |
eded | -2.092 |
Token | will |
Token ID | 481 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
sleeper | +3.219 |
Klux | +3.217 |
disasters | +2.968 |
liquids | +2.912 |
plane | +2.792 |
Neg logit contributions | |
ieth | -4.066 |
龍� | -3.788 |
iaries | -3.690 |
iary | -3.394 |
urations | -3.292 |
Token | here |
Token ID | 994 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Klux | +1.050 |
sleeper | +1.030 |
disasters | +0.936 |
liquids | +0.919 |
senal | +0.902 |
Neg logit contributions | |
ieth | -1.613 |
龍� | -1.485 |
iaries | -1.471 |
iary | -1.373 |
eded | -1.337 |
Token | . |
Token ID | 13 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
Klux | +0.246 |
sleeper | +0.242 |
disasters | +0.225 |
liquids | +0.222 |
senal | +0.220 |
Neg logit contributions | |
ieth | -0.226 |
龍� | -0.204 |
iaries | -0.203 |
iary | -0.183 |
eded | -0.177 |
Token |
|
Token ID | 198 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
ieth | +0.546 |
龍� | +0.491 |
iaries | +0.489 |
iary | +0.447 |
eded | +0.435 |
Neg logit contributions | |
Klux | -0.521 |
sleeper | -0.510 |
disasters | -0.470 |
liquids | -0.465 |
senal | -0.459 |
Token |
|
Token ID | 198 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Klux | +0.194 |
senal | +0.192 |
sleeper | +0.192 |
disasters | +0.177 |
liquids | +0.175 |
Neg logit contributions | |
ieth | -0.156 |
龍� | -0.138 |
iaries | -0.136 |
iary | -0.127 |
eded | -0.123 |
Token | The |
Token ID | 464 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Klux | +0.181 |
sleeper | +0.177 |
disasters | +0.163 |
liquids | +0.161 |
senal | +0.160 |
Neg logit contributions | |
ieth | -0.198 |
龍� | -0.179 |
iaries | -0.178 |
iary | -0.164 |
eded | -0.159 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +9.75e+00 |
Pos logit contributions | |
Klux | +1.133 |
sleeper | +1.109 |
disasters | +0.999 |
liquids | +0.983 |
senal | +0.970 |
Neg logit contributions | |
ieth | -1.831 |
龍� | -1.689 |
iaries | -1.674 |
iary | -1.562 |
eded | -1.524 |
Token | army |
Token ID | 5428 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
sleeper | +6.212 |
Klux | +6.139 |
disasters | +5.575 |
liquids | +5.396 |
plane | +5.245 |
Neg logit contributions | |
ieth | -11.777 |
龍� | -11.053 |
iaries | -10.732 |
iary | -9.981 |
姫 | -9.825 |
Token | and |
Token ID | 290 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Klux | +4.421 |
sleeper | +4.400 |
disasters | +4.029 |
liquids | +3.958 |
plane | +3.901 |
Neg logit contributions | |
ieth | -5.525 |
龍� | -5.167 |
iaries | -5.065 |
iary | -4.630 |
eded | -4.493 |
Token | its |
Token ID | 663 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
Klux | +1.391 |
sleeper | +1.354 |
disasters | +1.204 |
liquids | +1.185 |
senal | +1.175 |
Neg logit contributions | |
ieth | -2.671 |
龍� | -2.474 |
iaries | -2.458 |
iary | -2.307 |
eded | -2.252 |
Token | allies |
Token ID | 7681 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Klux | +0.012 |
sleeper | +0.011 |
senal | +0.010 |
disasters | +0.010 |
liquids | +0.010 |
Neg logit contributions | |
ieth | -0.023 |
iaries | -0.021 |
龍� | -0.021 |
iary | -0.020 |
eded | -0.020 |
Token | captured |
Token ID | 7907 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ieth | +1.245 |
龍� | +1.125 |
iaries | +1.125 |
iary | +1.043 |
eded | +1.015 |
Neg logit contributions | |
Klux | -1.064 |
sleeper | -1.034 |
disasters | -0.952 |
senal | -0.946 |
liquids | -0.940 |
Token | - |
Token ID | 12 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
ieth | +5.202 |
龍� | +4.661 |
iaries | +4.645 |
iary | +4.328 |
shire | +4.164 |
Neg logit contributions | |
Klux | -4.597 |
sleeper | -4.459 |
senal | -4.139 |
disasters | -4.133 |
liquids | -4.091 |
Token | year |
Token ID | 1941 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ieth | +0.253 |
龍� | +0.233 |
iaries | +0.230 |
iary | +0.209 |
eded | +0.204 |
Neg logit contributions | |
Klux | -0.250 |
sleeper | -0.248 |
disasters | -0.227 |
liquids | -0.225 |
plane | -0.225 |
Token | - |
Token ID | 12 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
ieth | +2.100 |
龍� | +1.922 |
iaries | +1.897 |
iary | +1.749 |
eded | +1.713 |
Neg logit contributions | |
Klux | -1.664 |
sleeper | -1.640 |
disasters | -1.499 |
liquids | -1.478 |
senal | -1.456 |
Token | old |
Token ID | 727 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
ieth | +0.316 |
iaries | +0.259 |
龍� | +0.253 |
iary | +0.223 |
shire | +0.218 |
Neg logit contributions | |
Klux | -0.726 |
sleeper | -0.711 |
senal | -0.698 |
disasters | -0.675 |
liquids | -0.673 |
Token | natural |
Token ID | 3288 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
Klux | +0.662 |
sleeper | +0.650 |
disasters | +0.583 |
liquids | +0.575 |
senal | +0.559 |
Neg logit contributions | |
ieth | -1.091 |
龍� | -1.012 |
iaries | -1.003 |
iary | -0.935 |
eded | -0.914 |
Token | gas |
Token ID | 3623 |
Feature activation | +9.65e+00 |
Pos logit contributions | |
sleeper | +2.129 |
Klux | +2.114 |
disasters | +1.899 |
liquids | +1.778 |
plane | +1.652 |
Neg logit contributions | |
ieth | -6.203 |
龍� | -5.840 |
iaries | -5.733 |
iary | -5.377 |
eded | -5.339 |
Token | well |
Token ID | 880 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
sleeper | +5.635 |
Klux | +5.598 |
liquids | +5.181 |
disasters | +5.118 |
plane | +4.825 |
Neg logit contributions | |
ieth | -11.852 |
龍� | -11.399 |
iaries | -10.979 |
姫 | -10.157 |
urations | -10.145 |
Token | in |
Token ID | 287 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ieth | +0.583 |
龍� | +0.532 |
iaries | +0.528 |
iary | +0.491 |
shire | +0.478 |
Neg logit contributions | |
Klux | -0.448 |
sleeper | -0.436 |
disasters | -0.398 |
liquids | -0.393 |
senal | -0.393 |
Token | northeastern |
Token ID | 38131 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
ieth | +1.288 |
龍� | +1.175 |
iaries | +1.169 |
iary | +1.085 |
eded | +1.057 |
Neg logit contributions | |
Klux | -0.984 |
sleeper | -0.959 |
disasters | -0.875 |
senal | -0.865 |
liquids | -0.865 |
Token | British |
Token ID | 3517 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
Klux | +0.219 |
sleeper | +0.214 |
disasters | +0.197 |
liquids | +0.195 |
senal | +0.192 |
Neg logit contributions | |
ieth | -0.261 |
龍� | -0.238 |
iaries | -0.235 |
iary | -0.218 |
eded | -0.211 |
Token | Columbia |
Token ID | 9309 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Klux | +0.607 |
sleeper | +0.596 |
disasters | +0.544 |
liquids | +0.536 |
senal | +0.530 |
Neg logit contributions | |
ieth | -0.803 |
龍� | -0.739 |
iaries | -0.731 |
iary | -0.678 |
eded | -0.659 |
Token | ratch |
Token ID | 36722 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
ieth | +2.500 |
龍� | +2.189 |
iaries | +2.161 |
iary | +1.921 |
eded | +1.838 |
Neg logit contributions | |
Klux | -3.974 |
sleeper | -3.907 |
disasters | -3.670 |
liquids | -3.641 |
senal | -3.625 |
Token | Reader |
Token ID | 25342 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ieth | +0.205 |
龍� | +0.187 |
iaries | +0.184 |
iary | +0.169 |
eded | +0.165 |
Neg logit contributions | |
Klux | -0.182 |
sleeper | -0.179 |
disasters | -0.165 |
liquids | -0.162 |
senal | -0.161 |
Token | : |
Token ID | 25 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
ieth | +1.222 |
龍� | +1.111 |
iaries | +1.100 |
iary | +1.012 |
eded | +0.986 |
Neg logit contributions | |
Klux | -1.083 |
sleeper | -1.065 |
disasters | -0.979 |
liquids | -0.966 |
senal | -0.959 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
Klux | +0.437 |
sleeper | +0.435 |
disasters | +0.399 |
senal | +0.394 |
liquids | +0.393 |
Neg logit contributions | |
ieth | -0.417 |
龍� | -0.374 |
iaries | -0.371 |
iary | -0.335 |
eded | -0.326 |
Token | The |
Token ID | 464 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
Klux | +3.587 |
sleeper | +3.479 |
disasters | +3.209 |
plane | +3.175 |
liquids | +3.171 |
Neg logit contributions | |
ieth | -3.835 |
龍� | -3.479 |
iaries | -3.478 |
iary | -3.157 |
shire | -3.060 |
Token | Korean |
Token ID | 6983 |
Feature activation | +9.50e+00 |
Pos logit contributions | |
Klux | +3.192 |
sleeper | +3.144 |
disasters | +2.853 |
liquids | +2.807 |
senal | +2.717 |
Neg logit contributions | |
ieth | -4.469 |
龍� | -4.141 |
iaries | -4.076 |
iary | -3.768 |
eded | -3.681 |
Token | Fair |
Token ID | 7011 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Klux | +6.995 |
sleeper | +6.890 |
disasters | +6.272 |
liquids | +6.053 |
turkey | +5.842 |
Neg logit contributions | |
ieth | -10.465 |
iaries | -9.653 |
龍� | -9.587 |
iary | -8.944 |
shire | -8.664 |
Token | Trade |
Token ID | 9601 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
ieth | +0.238 |
龍� | +0.217 |
iaries | +0.216 |
iary | +0.200 |
eded | +0.195 |
Neg logit contributions | |
Klux | -0.185 |
sleeper | -0.180 |
disasters | -0.165 |
liquids | -0.163 |
senal | -0.162 |
Token | Commission |
Token ID | 4513 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Klux | +5.562 |
sleeper | +5.451 |
disasters | +5.079 |
liquids | +4.953 |
plane | +4.820 |
Neg logit contributions | |
ieth | -8.080 |
龍� | -7.537 |
iaries | -7.470 |
iary | -6.901 |
shire | -6.677 |
Token | , |
Token ID | 11 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ieth | +1.196 |
龍� | +1.076 |
iaries | +1.071 |
iary | +0.988 |
eded | +0.960 |
Neg logit contributions | |
Klux | -1.122 |
sleeper | -1.097 |
disasters | -1.010 |
senal | -1.002 |
liquids | -1.000 |
Token | that |
Token ID | 326 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
Klux | +1.299 |
sleeper | +1.271 |
disasters | +1.156 |
liquids | +1.136 |
senal | +1.126 |
Neg logit contributions | |
ieth | -1.865 |
龍� | -1.717 |
iaries | -1.704 |
iary | -1.580 |
eded | -1.540 |
Token | ."[ |
Token ID | 18161 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
ieth | +0.563 |
龍� | +0.508 |
iaries | +0.506 |
iary | +0.468 |
eded | +0.454 |
Neg logit contributions | |
Klux | -0.506 |
sleeper | -0.493 |
senal | -0.454 |
disasters | -0.453 |
liquids | -0.449 |
Token | 43 |
Token ID | 3559 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
Klux | +0.073 |
sleeper | +0.072 |
disasters | +0.069 |
liquids | +0.069 |
plane | +0.068 |
Neg logit contributions | |
ieth | -0.021 |
龍� | -0.016 |
iaries | -0.016 |
iary | -0.012 |
eded | -0.011 |
Token | ] |
Token ID | 60 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
ieth | +3.411 |
龍� | +2.832 |
iaries | +2.785 |
iary | +2.680 |
shire | +2.524 |
Neg logit contributions | |
senal | -6.695 |
Klux | -6.338 |
sleeper | -6.338 |
disasters | -5.929 |
liquids | -5.817 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Klux | +0.830 |
sleeper | +0.813 |
disasters | +0.755 |
liquids | +0.744 |
plane | +0.733 |
Neg logit contributions | |
ieth | -0.865 |
龍� | -0.783 |
iaries | -0.776 |
iary | -0.708 |
eded | -0.691 |
Token |
|
Token ID | 198 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
Klux | +0.160 |
senal | +0.158 |
sleeper | +0.157 |
disasters | +0.146 |
liquids | +0.144 |
Neg logit contributions | |
ieth | -0.127 |
龍� | -0.112 |
iaries | -0.110 |
iary | -0.103 |
eded | -0.100 |
Token | Syrian |
Token ID | 42747 |
Feature activation | +9.42e+00 |
Pos logit contributions | |
Klux | +0.089 |
sleeper | +0.087 |
disasters | +0.080 |
liquids | +0.079 |
senal | +0.079 |
Neg logit contributions | |
ieth | -0.096 |
龍� | -0.087 |
iaries | -0.086 |
iary | -0.079 |
eded | -0.077 |
Token | activities |
Token ID | 4568 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
sleeper | +6.630 |
Klux | +6.391 |
disasters | +5.930 |
liquids | +5.801 |
plane | +5.544 |
Neg logit contributions | |
ieth | -10.749 |
龍� | -10.111 |
iaries | -9.756 |
iary | -9.146 |
shire | -8.936 |
Token | then |
Token ID | 788 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ieth | +1.613 |
iaries | +1.456 |
龍� | +1.450 |
iary | +1.352 |
eded | +1.321 |
Neg logit contributions | |
Klux | -1.299 |
sleeper | -1.258 |
senal | -1.161 |
disasters | -1.151 |
liquids | -1.140 |
Token | resulted |
Token ID | 8724 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
Klux | +0.298 |
sleeper | +0.292 |
disasters | +0.267 |
liquids | +0.263 |
senal | +0.261 |
Neg logit contributions | |
ieth | -0.383 |
龍� | -0.351 |
iaries | -0.348 |
iary | -0.322 |
eded | -0.313 |
Token | in |
Token ID | 287 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ieth | +3.451 |
龍� | +3.176 |
iaries | +3.143 |
iary | +2.909 |
eded | +2.841 |
Neg logit contributions | |
Klux | -2.498 |
sleeper | -2.442 |
disasters | -2.236 |
liquids | -2.193 |
senal | -2.180 |
Token | a |
Token ID | 257 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ieth | +1.877 |
iaries | +1.728 |
龍� | +1.722 |
iary | +1.621 |
eded | +1.587 |
Neg logit contributions | |
Klux | -1.010 |
sleeper | -0.961 |
senal | -0.863 |
disasters | -0.855 |
liquids | -0.848 |
Token | rationality |
Token ID | 45627 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
ieth | +1.127 |
龍� | +1.035 |
iaries | +1.034 |
iary | +0.975 |
eded | +0.955 |
Neg logit contributions | |
Klux | -0.590 |
sleeper | -0.561 |
senal | -0.509 |
disasters | -0.495 |
liquids | -0.492 |
Token | . |
Token ID | 13 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
ieth | +2.709 |
龍� | +2.433 |
iaries | +2.420 |
iary | +2.231 |
eded | +2.163 |
Neg logit contributions | |
Klux | -2.702 |
sleeper | -2.631 |
senal | -2.432 |
disasters | -2.426 |
liquids | -2.407 |
Token | In |
Token ID | 554 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
ieth | +0.774 |
龍� | +0.695 |
iaries | +0.689 |
iary | +0.633 |
eded | +0.611 |
Neg logit contributions | |
Klux | -0.825 |
sleeper | -0.810 |
disasters | -0.750 |
senal | -0.745 |
liquids | -0.743 |
Token | order |
Token ID | 1502 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
ieth | +3.367 |
龍� | +3.071 |
iaries | +3.048 |
iary | +2.847 |
eded | +2.759 |
Neg logit contributions | |
Klux | -2.556 |
sleeper | -2.490 |
senal | -2.260 |
disasters | -2.251 |
liquids | -2.238 |
Token | to |
Token ID | 284 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
Klux | +0.514 |
sleeper | +0.504 |
disasters | +0.458 |
liquids | +0.449 |
senal | +0.443 |
Neg logit contributions | |
ieth | -0.833 |
龍� | -0.767 |
iaries | -0.762 |
iary | -0.707 |
shire | -0.694 |
Token | substant |
Token ID | 5925 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
ieth | +0.899 |
龍� | +0.811 |
iaries | +0.810 |
iary | +0.750 |
eded | +0.729 |
Neg logit contributions | |
Klux | -0.821 |
sleeper | -0.795 |
senal | -0.748 |
disasters | -0.731 |
liquids | -0.723 |
Token | iate |
Token ID | 9386 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ieth | +5.977 |
iaries | +4.731 |
iary | +4.570 |
龍� | +3.980 |
ibility | +3.724 |
Neg logit contributions | |
senal | -15.521 |
Klux | -15.124 |
sleeper | -15.022 |
liquids | -14.269 |
disasters | -14.165 |
Token | this |
Token ID | 428 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
ieth | +1.741 |
龍� | +1.605 |
iaries | +1.596 |
iary | +1.498 |
eded | +1.462 |
Neg logit contributions | |
Klux | -0.974 |
sleeper | -0.943 |
disasters | -0.844 |
liquids | -0.833 |
senal | -0.833 |
Token | claim |
Token ID | 1624 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ieth | +0.515 |
龍� | +0.470 |
iaries | +0.467 |
iary | +0.432 |
eded | +0.420 |
Neg logit contributions | |
Klux | -0.411 |
sleeper | -0.402 |
disasters | -0.368 |
liquids | -0.363 |
senal | -0.361 |
Token | He |
Token ID | 679 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
ieth | +1.678 |
龍� | +1.518 |
iaries | +1.510 |
iary | +1.397 |
shire | +1.354 |
Neg logit contributions | |
Klux | -1.492 |
sleeper | -1.456 |
disasters | -1.340 |
senal | -1.329 |
liquids | -1.327 |
Token | ikes |
Token ID | 7938 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
ieth | +5.099 |
iaries | +4.688 |
龍� | +4.565 |
iary | +4.380 |
eded | +4.307 |
Neg logit contributions | |
sleeper | -2.806 |
Klux | -2.761 |
senal | -2.681 |
disasters | -2.439 |
liquids | -2.354 |
Token | is |
Token ID | 318 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
Klux | +0.690 |
sleeper | +0.675 |
disasters | +0.618 |
liquids | +0.611 |
senal | +0.604 |
Neg logit contributions | |
ieth | -0.879 |
龍� | -0.804 |
iaries | -0.797 |
iary | -0.739 |
eded | -0.718 |
Token | credited |
Token ID | 18141 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
ieth | +0.313 |
龍� | +0.287 |
iaries | +0.285 |
iary | +0.266 |
eded | +0.259 |
Neg logit contributions | |
Klux | -0.215 |
sleeper | -0.209 |
disasters | -0.190 |
liquids | -0.188 |
senal | -0.187 |
Token | with |
Token ID | 351 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ieth | +4.414 |
龍� | +4.030 |
iaries | +4.002 |
iary | +3.704 |
eded | +3.603 |
Neg logit contributions | |
Klux | -3.524 |
sleeper | -3.448 |
disasters | -3.156 |
liquids | -3.117 |
senal | -3.105 |
Token | engineering |
Token ID | 8705 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
Klux | +0.668 |
sleeper | +0.649 |
disasters | +0.580 |
liquids | +0.571 |
senal | +0.567 |
Neg logit contributions | |
ieth | -1.231 |
龍� | -1.138 |
iaries | -1.131 |
iary | -1.061 |
eded | -1.036 |
Token | the |
Token ID | 262 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ieth | +0.687 |
龍� | +0.635 |
iaries | +0.632 |
iary | +0.593 |
eded | +0.579 |
Neg logit contributions | |
Klux | -0.359 |
sleeper | -0.349 |
disasters | -0.311 |
liquids | -0.305 |
senal | -0.303 |
Token | ingen |
Token ID | 27016 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
Klux | +0.078 |
sleeper | +0.076 |
disasters | +0.068 |
liquids | +0.067 |
senal | +0.066 |
Neg logit contributions | |
ieth | -0.133 |
龍� | -0.123 |
iaries | -0.122 |
iary | -0.114 |
eded | -0.112 |
Token | ius |
Token ID | 3754 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ieth | +9.148 |
iaries | +7.955 |
龍� | +7.677 |
iary | +7.339 |
ibility | +6.873 |
Neg logit contributions | |
Klux | -12.218 |
sleeper | -12.002 |
senal | -11.423 |
liquids | -11.190 |
disasters | -11.103 |
Token | irrigation |
Token ID | 35425 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
ieth | +2.011 |
龍� | +1.850 |
iaries | +1.840 |
iary | +1.721 |
eded | +1.676 |
Neg logit contributions | |
Klux | -1.259 |
sleeper | -1.220 |
disasters | -1.100 |
senal | -1.087 |
liquids | -1.087 |
Token | system |
Token ID | 1080 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
sleeper | +3.328 |
Klux | +3.308 |
disasters | +3.064 |
liquids | +2.970 |
plane | +2.846 |
Neg logit contributions | |
ieth | -5.850 |
龍� | -5.447 |
iaries | -5.377 |
iary | -5.000 |
eded | -4.918 |
Token | more |
Token ID | 517 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
Klux | +1.197 |
sleeper | +1.186 |
disasters | +1.095 |
liquids | +1.074 |
senal | +1.053 |
Neg logit contributions | |
ieth | -1.473 |
龍� | -1.345 |
iaries | -1.342 |
iary | -1.235 |
eded | -1.197 |
Token | than |
Token ID | 621 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
Klux | +0.370 |
sleeper | +0.364 |
disasters | +0.334 |
liquids | +0.328 |
senal | +0.321 |
Neg logit contributions | |
ieth | -0.506 |
龍� | -0.464 |
iaries | -0.461 |
iary | -0.428 |
shire | -0.416 |
Token | M |
Token ID | 44 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ieth | +2.866 |
龍� | +2.585 |
iaries | +2.565 |
iary | +2.342 |
eded | +2.276 |
Neg logit contributions | |
Klux | -2.888 |
sleeper | -2.836 |
disasters | -2.630 |
liquids | -2.597 |
senal | -2.588 |
Token | DB |
Token ID | 11012 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
Klux | +1.443 |
sleeper | +1.423 |
senal | +1.363 |
disasters | +1.343 |
liquids | +1.332 |
Neg logit contributions | |
ieth | -0.656 |
龍� | -0.564 |
iaries | -0.545 |
iary | -0.478 |
eded | -0.451 |
Token | provide |
Token ID | 2148 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ieth | +3.536 |
iaries | +3.207 |
龍� | +3.167 |
iary | +2.967 |
eded | +2.897 |
Neg logit contributions | |
Klux | -3.038 |
sleeper | -2.949 |
senal | -2.753 |
disasters | -2.684 |
liquids | -2.649 |
Token | documentation |
Token ID | 10314 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ieth | +2.386 |
iaries | +2.189 |
龍� | +2.182 |
iary | +2.059 |
eded | +2.004 |
Neg logit contributions | |
Klux | -1.410 |
sleeper | -1.344 |
senal | -1.227 |
disasters | -1.205 |
liquids | -1.188 |
Token | to |
Token ID | 284 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ieth | +2.978 |
龍� | +2.696 |
iaries | +2.689 |
iary | +2.502 |
eded | +2.432 |
Neg logit contributions | |
Klux | -2.419 |
sleeper | -2.346 |
senal | -2.151 |
disasters | -2.141 |
liquids | -2.121 |
Token | substant |
Token ID | 5925 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
ieth | +1.533 |
iaries | +1.410 |
龍� | +1.406 |
iary | +1.319 |
eded | +1.283 |
Neg logit contributions | |
Klux | -0.967 |
sleeper | -0.932 |
senal | -0.841 |
disasters | -0.834 |
liquids | -0.829 |
Token | iate |
Token ID | 9386 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
ieth | +6.265 |
iaries | +5.168 |
iary | +4.826 |
龍� | +4.628 |
ibility | +3.983 |
Neg logit contributions | |
Klux | -14.709 |
senal | -14.557 |
sleeper | -14.536 |
disasters | -13.748 |
liquids | -13.656 |
Token | its |
Token ID | 663 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
ieth | +0.797 |
龍� | +0.739 |
iaries | +0.734 |
iary | +0.689 |
eded | +0.674 |
Neg logit contributions | |
Klux | -0.408 |
sleeper | -0.396 |
disasters | -0.353 |
liquids | -0.347 |
senal | -0.343 |
Token | claims |
Token ID | 3667 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
ieth | +0.987 |
龍� | +0.906 |
iaries | +0.902 |
iary | +0.844 |
eded | +0.823 |
Neg logit contributions | |
Klux | -0.620 |
sleeper | -0.601 |
disasters | -0.541 |
senal | -0.536 |
liquids | -0.534 |
Token | . |
Token ID | 13 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
ieth | +1.428 |
龍� | +1.288 |
iaries | +1.276 |
iary | +1.167 |
eded | +1.129 |
Neg logit contributions | |
Klux | -1.483 |
sleeper | -1.454 |
disasters | -1.349 |
liquids | -1.335 |
senal | -1.326 |
Token | " |
Token ID | 366 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ieth | +0.822 |
龍� | +0.744 |
iaries | +0.737 |
iary | +0.670 |
eded | +0.656 |
Neg logit contributions | |
Klux | -0.792 |
sleeper | -0.772 |
disasters | -0.717 |
liquids | -0.708 |
plane | -0.700 |
Token | 45 |
Token ID | 4153 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
Klux | +0.804 |
sleeper | +0.787 |
disasters | +0.715 |
liquids | +0.706 |
senal | +0.695 |
Neg logit contributions | |
ieth | -1.131 |
龍� | -1.037 |
iaries | -1.032 |
iary | -0.959 |
shire | -0.933 |
Token | HD |
Token ID | 5572 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
ieth | +5.827 |
龍� | +5.203 |
iaries | +5.123 |
iary | +4.714 |
eded | +4.610 |
Neg logit contributions | |
Klux | -6.001 |
sleeper | -5.879 |
senal | -5.458 |
disasters | -5.415 |
liquids | -5.359 |
Token | Bs |
Token ID | 37000 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
Klux | +0.672 |
sleeper | +0.660 |
disasters | +0.612 |
liquids | +0.606 |
senal | +0.598 |
Neg logit contributions | |
ieth | -0.719 |
龍� | -0.652 |
iaries | -0.650 |
iary | -0.599 |
shire | -0.581 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ieth | +3.059 |
龍� | +2.758 |
iaries | +2.731 |
iary | +2.511 |
eded | +2.442 |
Neg logit contributions | |
Klux | -3.016 |
sleeper | -2.953 |
disasters | -2.728 |
senal | -2.702 |
liquids | -2.696 |
Token | Patrick |
Token ID | 9925 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
Klux | +1.083 |
sleeper | +1.060 |
disasters | +0.970 |
liquids | +0.959 |
senal | +0.950 |
Neg logit contributions | |
ieth | -1.364 |
龍� | -1.244 |
iaries | -1.236 |
iary | -1.145 |
eded | -1.112 |
Token | Bert |
Token ID | 22108 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
ieth | +2.909 |
龍� | +2.637 |
iaries | +2.618 |
iary | +2.413 |
eded | +2.342 |
Neg logit contributions | |
Klux | -2.632 |
sleeper | -2.575 |
disasters | -2.373 |
liquids | -2.347 |
senal | -2.338 |
Token | ole |
Token ID | 2305 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
ieth | +10.895 |
iaries | +9.683 |
龍� | +9.582 |
iary | +9.079 |
shire | +8.816 |
Neg logit contributions | |
Klux | -9.953 |
sleeper | -9.634 |
senal | -9.051 |
liquids | -8.948 |
disasters | -8.910 |
Token | tti |
Token ID | 35671 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Klux | +2.519 |
sleeper | +2.429 |
disasters | +2.226 |
liquids | +2.199 |
senal | +2.166 |
Neg logit contributions | |
ieth | -3.369 |
iaries | -3.112 |
龍� | -3.090 |
iary | -2.859 |
eded | -2.754 |
Token | finished |
Token ID | 5201 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
ieth | +1.745 |
龍� | +1.586 |
iaries | +1.578 |
iary | +1.454 |
eded | +1.411 |
Neg logit contributions | |
Klux | -1.519 |
sleeper | -1.485 |
disasters | -1.365 |
liquids | -1.350 |
senal | -1.341 |
Token | third |
Token ID | 2368 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
ieth | +0.563 |
龍� | +0.510 |
iaries | +0.508 |
iary | +0.471 |
eded | +0.456 |
Neg logit contributions | |
Klux | -0.469 |
sleeper | -0.457 |
disasters | -0.420 |
senal | -0.417 |
liquids | -0.415 |
Token | with |
Token ID | 351 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
ieth | +3.297 |
龍� | +2.987 |
iaries | +2.964 |
iary | +2.756 |
eded | +2.676 |
Neg logit contributions | |
Klux | -2.776 |
sleeper | -2.702 |
disasters | -2.486 |
senal | -2.474 |
liquids | -2.457 |
Token | It |
Token ID | 1026 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ieth | +0.399 |
龍� | +0.362 |
iaries | +0.359 |
iary | +0.331 |
eded | +0.321 |
Neg logit contributions | |
Klux | -0.362 |
sleeper | -0.354 |
disasters | -0.327 |
liquids | -0.323 |
senal | -0.322 |
Token | was |
Token ID | 373 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
Klux | +0.095 |
sleeper | +0.093 |
disasters | +0.085 |
liquids | +0.084 |
senal | +0.084 |
Neg logit contributions | |
ieth | -0.111 |
龍� | -0.101 |
iaries | -0.100 |
iary | -0.093 |
eded | -0.090 |
Token | , |
Token ID | 11 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ieth | +0.030 |
龍� | +0.028 |
iaries | +0.028 |
iary | +0.026 |
eded | +0.025 |
Neg logit contributions | |
Klux | -0.019 |
sleeper | -0.018 |
disasters | -0.016 |
liquids | -0.016 |
senal | -0.016 |
Token | but |
Token ID | 475 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
ieth | +0.441 |
龍� | +0.400 |
iaries | +0.397 |
iary | +0.368 |
eded | +0.358 |
Neg logit contributions | |
Klux | -0.380 |
sleeper | -0.369 |
senal | -0.342 |
disasters | -0.339 |
liquids | -0.337 |
Token | in |
Token ID | 287 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
Klux | +0.635 |
sleeper | +0.618 |
disasters | +0.558 |
liquids | +0.550 |
senal | +0.548 |
Neg logit contributions | |
ieth | -1.007 |
龍� | -0.926 |
iaries | -0.920 |
iary | -0.860 |
eded | -0.839 |
Token | retrospect |
Token ID | 23583 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
ieth | +3.033 |
龍� | +2.788 |
iaries | +2.758 |
iary | +2.581 |
eded | +2.527 |
Neg logit contributions | |
Klux | -1.940 |
sleeper | -1.873 |
senal | -1.704 |
disasters | -1.679 |
liquids | -1.672 |
Token | it |
Token ID | 340 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ieth | +11.017 |
iaries | +10.040 |
龍� | +9.987 |
iary | +9.439 |
shire | +9.286 |
Neg logit contributions | |
Klux | -9.207 |
sleeper | -8.636 |
senal | -8.523 |
liquids | -7.966 |
plane | -7.878 |
Token | will |
Token ID | 481 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ieth | +1.244 |
龍� | +1.127 |
iaries | +1.121 |
iary | +1.035 |
eded | +1.006 |
Neg logit contributions | |
Klux | -1.095 |
sleeper | -1.069 |
disasters | -0.982 |
senal | -0.976 |
liquids | -0.973 |
Token | be |
Token ID | 307 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ieth | +1.801 |
龍� | +1.630 |
iaries | +1.621 |
iary | +1.495 |
eded | +1.450 |
Neg logit contributions | |
Klux | -1.636 |
sleeper | -1.599 |
disasters | -1.473 |
senal | -1.458 |
liquids | -1.458 |
Token | seen |
Token ID | 1775 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ieth | +2.213 |
龍� | +2.027 |
iaries | +2.027 |
iary | +1.897 |
shire | +1.850 |
Neg logit contributions | |
Klux | -1.325 |
sleeper | -1.277 |
senal | -1.158 |
disasters | -1.144 |
liquids | -1.139 |
Token | as |
Token ID | 355 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Klux | +0.851 |
sleeper | +0.841 |
disasters | +0.769 |
liquids | +0.753 |
senal | +0.730 |
Neg logit contributions | |
ieth | -1.111 |
龍� | -1.027 |
iaries | -1.015 |
iary | -0.932 |
eded | -0.911 |
Token | basically |
Token ID | 6209 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
ieth | +0.972 |
龍� | +0.891 |
iaries | +0.888 |
iary | +0.831 |
shire | +0.808 |
Neg logit contributions | |
Klux | -0.644 |
sleeper | -0.618 |
senal | -0.562 |
disasters | -0.561 |
liquids | -0.554 |
Token | an |
Token ID | 281 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
ieth | +0.485 |
龍� | +0.446 |
iaries | +0.444 |
iary | +0.416 |
shire | +0.405 |
Neg logit contributions | |
Klux | -0.292 |
sleeper | -0.282 |
disasters | -0.254 |
senal | -0.252 |
liquids | -0.251 |
Token | also |
Token ID | 635 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
ieth | +0.862 |
龍� | +0.792 |
iaries | +0.787 |
iary | +0.735 |
eded | +0.717 |
Neg logit contributions | |
Klux | -0.548 |
sleeper | -0.531 |
disasters | -0.481 |
senal | -0.474 |
liquids | -0.474 |
Token | - |
Token ID | 12 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ieth | +3.239 |
龍� | +2.952 |
iaries | +2.932 |
iary | +2.715 |
eded | +2.639 |
Neg logit contributions | |
Klux | -2.622 |
sleeper | -2.562 |
disasters | -2.348 |
liquids | -2.320 |
senal | -2.310 |
Token | ran |
Token ID | 2596 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ieth | +1.333 |
龍� | +1.185 |
iaries | +1.175 |
iary | +1.055 |
eded | +1.015 |
Neg logit contributions | |
Klux | -1.808 |
sleeper | -1.778 |
disasters | -1.662 |
liquids | -1.647 |
senal | -1.639 |
Token | Benn |
Token ID | 14025 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
Klux | +1.407 |
sleeper | +1.396 |
disasters | +1.264 |
liquids | +1.248 |
senal | +1.240 |
Neg logit contributions | |
ieth | -1.716 |
龍� | -1.581 |
iaries | -1.557 |
iary | -1.419 |
eded | -1.401 |
Token | igan |
Token ID | 5516 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
ieth | +10.513 |
iaries | +9.375 |
龍� | +9.094 |
iary | +8.650 |
shire | +8.397 |
Neg logit contributions | |
Klux | -10.183 |
sleeper | -9.989 |
senal | -9.357 |
disasters | -9.352 |
liquids | -9.255 |
Token | 's |
Token ID | 338 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Klux | +0.505 |
sleeper | +0.497 |
disasters | +0.453 |
liquids | +0.448 |
senal | +0.443 |
Neg logit contributions | |
ieth | -0.594 |
龍� | -0.541 |
iaries | -0.537 |
iary | -0.494 |
eded | -0.483 |
Token | surviving |
Token ID | 16997 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ieth | +0.164 |
龍� | +0.149 |
iaries | +0.148 |
iary | +0.136 |
eded | +0.133 |
Neg logit contributions | |
Klux | -0.143 |
sleeper | -0.140 |
disasters | -0.129 |
liquids | -0.127 |
senal | -0.126 |
Token | at |
Token ID | 379 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ieth | +2.350 |
iaries | +2.150 |
龍� | +2.139 |
iary | +2.015 |
shire | +1.956 |
Neg logit contributions | |
Klux | -1.449 |
sleeper | -1.393 |
senal | -1.260 |
disasters | -1.259 |
liquids | -1.240 |
Token | the |
Token ID | 262 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
ieth | +2.202 |
iaries | +2.010 |
龍� | +2.010 |
iary | +1.874 |
shire | +1.826 |
Neg logit contributions | |
Klux | -1.475 |
sleeper | -1.430 |
disasters | -1.299 |
liquids | -1.285 |
senal | -1.278 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Klux | +0.195 |
senal | +0.193 |
sleeper | +0.193 |
disasters | +0.178 |
liquids | +0.176 |
Neg logit contributions | |
ieth | -0.157 |
龍� | -0.138 |
iaries | -0.137 |
iary | -0.128 |
eded | -0.124 |
Token | German |
Token ID | 16010 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
Klux | +0.168 |
sleeper | +0.164 |
disasters | +0.152 |
liquids | +0.150 |
plane | +0.147 |
Neg logit contributions | |
ieth | -0.185 |
龍� | -0.168 |
iaries | -0.167 |
iary | -0.153 |
eded | -0.149 |
Token | environment |
Token ID | 2858 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
Klux | +1.630 |
sleeper | +1.589 |
disasters | +1.445 |
liquids | +1.412 |
senal | +1.382 |
Neg logit contributions | |
ieth | -2.630 |
龍� | -2.429 |
iaries | -2.414 |
iary | -2.250 |
eded | -2.191 |
Token | minister |
Token ID | 5342 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
Klux | +3.193 |
sleeper | +3.137 |
disasters | +2.934 |
liquids | +2.845 |
senal | +2.773 |
Neg logit contributions | |
ieth | -3.949 |
龍� | -3.646 |
iaries | -3.619 |
iary | -3.325 |
shire | -3.250 |
Token | Barbara |
Token ID | 16685 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
ieth | +0.824 |
龍� | +0.746 |
iaries | +0.740 |
iary | +0.680 |
eded | +0.658 |
Neg logit contributions | |
Klux | -0.789 |
sleeper | -0.773 |
disasters | -0.715 |
liquids | -0.707 |
senal | -0.703 |
Token | Hendricks |
Token ID | 42476 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
ieth | +2.491 |
龍� | +2.188 |
iaries | +2.169 |
iary | +1.986 |
shire | +1.905 |
Neg logit contributions | |
Klux | -3.096 |
sleeper | -3.089 |
senal | -2.855 |
disasters | -2.847 |
liquids | -2.832 |
Token | said |
Token ID | 531 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ieth | +10.775 |
龍� | +9.420 |
iaries | +9.321 |
shire | +8.786 |
iary | +8.766 |
Neg logit contributions | |
Klux | -9.327 |
sleeper | -9.260 |
senal | -8.793 |
liquids | -8.397 |
disasters | -8.322 |
Token | there |
Token ID | 612 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
Klux | +1.378 |
sleeper | +1.345 |
disasters | +1.218 |
liquids | +1.197 |
senal | +1.179 |
Neg logit contributions | |
ieth | -2.268 |
龍� | -2.096 |
iaries | -2.080 |
iary | -1.942 |
eded | -1.898 |
Token | was |
Token ID | 373 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
Klux | +0.640 |
sleeper | +0.627 |
disasters | +0.579 |
liquids | +0.571 |
senal | +0.563 |
Neg logit contributions | |
ieth | -0.719 |
龍� | -0.653 |
iaries | -0.648 |
iary | -0.595 |
eded | -0.577 |
Token | a |
Token ID | 257 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
Klux | +0.319 |
sleeper | +0.313 |
disasters | +0.282 |
liquids | +0.278 |
senal | +0.273 |
Neg logit contributions | |
ieth | -0.496 |
龍� | -0.456 |
iaries | -0.455 |
iary | -0.423 |
eded | -0.412 |
Token | � |
Token ID | 564 |
Feature activation | -7.59e-03 |
Pos logit contributions | |
Klux | +0.225 |
sleeper | +0.219 |
disasters | +0.199 |
liquids | +0.196 |
senal | +0.195 |
Neg logit contributions | |
ieth | -0.335 |
龍� | -0.307 |
iaries | -0.305 |
iary | -0.285 |
eded | -0.277 |
Token | building |
Token ID | 2615 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Klux | +0.262 |
sleeper | +0.255 |
disasters | +0.230 |
liquids | +0.227 |
senal | +0.225 |
Neg logit contributions | |
ieth | -0.420 |
龍� | -0.386 |
iaries | -0.384 |
iary | -0.359 |
eded | -0.350 |
Token | became |
Token ID | 2627 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
Klux | +0.987 |
sleeper | +0.968 |
disasters | +0.891 |
liquids | +0.879 |
senal | +0.861 |
Neg logit contributions | |
ieth | -1.190 |
龍� | -1.089 |
iaries | -1.083 |
iary | -0.997 |
eded | -0.970 |
Token | obsolete |
Token ID | 26533 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Klux | +0.245 |
sleeper | +0.239 |
disasters | +0.214 |
liquids | +0.210 |
senal | +0.208 |
Neg logit contributions | |
ieth | -0.433 |
龍� | -0.400 |
iaries | -0.398 |
iary | -0.372 |
eded | -0.364 |
Token | in |
Token ID | 287 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
ieth | +2.431 |
龍� | +2.205 |
iaries | +2.184 |
iary | +2.038 |
shire | +1.994 |
Neg logit contributions | |
Klux | -1.900 |
sleeper | -1.848 |
senal | -1.710 |
disasters | -1.679 |
liquids | -1.679 |
Token | the |
Token ID | 262 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ieth | +2.360 |
龍� | +2.126 |
iaries | +2.114 |
iary | +1.956 |
eded | +1.918 |
Neg logit contributions | |
Klux | -2.125 |
sleeper | -2.047 |
senal | -1.936 |
liquids | -1.871 |
disasters | -1.869 |
Token | sevent |
Token ID | 10037 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
ieth | +0.267 |
龍� | +0.241 |
iaries | +0.239 |
iary | +0.221 |
shire | +0.217 |
Neg logit contributions | |
Klux | -0.235 |
sleeper | -0.227 |
senal | -0.214 |
disasters | -0.209 |
liquids | -0.208 |
Token | ies |
Token ID | 444 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
ieth | +5.018 |
iaries | +3.146 |
龍� | +2.704 |
iary | +2.673 |
eenth | +2.647 |
Neg logit contributions | |
senal | -15.433 |
sleeper | -15.057 |
Klux | -14.821 |
disasters | -14.217 |
liquids | -14.198 |
Token | , |
Token ID | 11 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
ieth | +0.203 |
龍� | +0.185 |
iaries | +0.184 |
iary | +0.169 |
eded | +0.164 |
Neg logit contributions | |
Klux | -0.180 |
sleeper | -0.176 |
disasters | -0.162 |
liquids | -0.160 |
senal | -0.158 |
Token | when |
Token ID | 618 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ieth | +1.013 |
龍� | +0.926 |
iaries | +0.918 |
iary | +0.852 |
eded | +0.830 |
Neg logit contributions | |
Klux | -0.785 |
sleeper | -0.765 |
disasters | -0.698 |
senal | -0.693 |
liquids | -0.692 |
Token | the |
Token ID | 262 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Klux | +1.731 |
sleeper | +1.693 |
disasters | +1.537 |
liquids | +1.500 |
senal | +1.456 |
Neg logit contributions | |
ieth | -3.019 |
iaries | -2.790 |
龍� | -2.786 |
iary | -2.607 |
eded | -2.540 |
Token | shipping |
Token ID | 8440 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
ieth | +0.205 |
龍� | +0.189 |
iaries | +0.188 |
iary | +0.176 |
eded | +0.172 |
Neg logit contributions | |
Klux | -0.124 |
sleeper | -0.121 |
disasters | -0.109 |
liquids | -0.107 |
senal | -0.107 |
Token | at |
Token ID | 379 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Klux | +3.499 |
sleeper | +3.460 |
disasters | +3.189 |
liquids | +3.155 |
plane | +3.093 |
Neg logit contributions | |
ieth | -3.859 |
龍� | -3.523 |
iaries | -3.503 |
iary | -3.175 |
eded | -3.141 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ieth | +2.115 |
龍� | +1.936 |
iaries | +1.931 |
iary | +1.804 |
shire | +1.763 |
Neg logit contributions | |
Klux | -1.332 |
sleeper | -1.287 |
disasters | -1.163 |
liquids | -1.150 |
senal | -1.147 |
Token | end |
Token ID | 886 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ieth | +0.216 |
龍� | +0.198 |
iaries | +0.197 |
iary | +0.184 |
eded | +0.180 |
Neg logit contributions | |
Klux | -0.136 |
sleeper | -0.132 |
disasters | -0.120 |
liquids | -0.118 |
senal | -0.118 |
Token | of |
Token ID | 286 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
ieth | +1.663 |
龍� | +1.431 |
iaries | +1.427 |
iary | +1.314 |
shire | +1.261 |
Neg logit contributions | |
Klux | -2.175 |
sleeper | -2.126 |
senal | -2.068 |
disasters | -1.965 |
liquids | -1.949 |
Token | West |
Token ID | 2688 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
ieth | +0.700 |
龍� | +0.648 |
iaries | +0.643 |
iary | +0.601 |
eded | +0.587 |
Neg logit contributions | |
Klux | -0.418 |
sleeper | -0.409 |
disasters | -0.368 |
liquids | -0.362 |
senal | -0.358 |
Token | Fif |
Token ID | 12830 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
ieth | +0.362 |
龍� | +0.330 |
iaries | +0.327 |
iary | +0.301 |
eded | +0.292 |
Neg logit contributions | |
Klux | -0.320 |
sleeper | -0.313 |
disasters | -0.288 |
liquids | -0.285 |
senal | -0.283 |
Token | teenth |
Token ID | 20283 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
ieth | +8.163 |
iaries | +6.709 |
龍� | +6.467 |
iary | +6.006 |
shire | +5.905 |
Neg logit contributions | |
sleeper | -11.754 |
Klux | -11.661 |
senal | -11.410 |
liquids | -11.057 |
disasters | -10.993 |
Token | Street |
Token ID | 3530 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ieth | +4.554 |
龍� | +4.046 |
iaries | +4.015 |
iary | +3.697 |
shire | +3.605 |
Neg logit contributions | |
Klux | -4.874 |
sleeper | -4.767 |
disasters | -4.433 |
senal | -4.407 |
liquids | -4.396 |
Token | . |
Token ID | 13 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
Klux | +2.484 |
sleeper | +2.454 |
disasters | +2.256 |
liquids | +2.236 |
plane | +2.209 |
Neg logit contributions | |
ieth | -2.480 |
iaries | -2.270 |
龍� | -2.266 |
iary | -2.057 |
eded | -2.009 |
Token | Built |
Token ID | 28477 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
ieth | +0.600 |
龍� | +0.542 |
iaries | +0.538 |
iary | +0.495 |
eded | +0.480 |
Neg logit contributions | |
Klux | -0.569 |
sleeper | -0.557 |
disasters | -0.514 |
liquids | -0.509 |
senal | -0.507 |
Token | in |
Token ID | 287 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Klux | +0.535 |
sleeper | +0.523 |
disasters | +0.477 |
liquids | +0.469 |
senal | +0.462 |
Neg logit contributions | |
ieth | -0.726 |
龍� | -0.668 |
iaries | -0.661 |
iary | -0.613 |
eded | -0.599 |
Token | For |
Token ID | 1114 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ieth | +1.074 |
龍� | +0.965 |
iaries | +0.957 |
iary | +0.875 |
eded | +0.846 |
Neg logit contributions | |
Klux | -1.147 |
sleeper | -1.125 |
disasters | -1.044 |
liquids | -1.033 |
senal | -1.030 |
Token | many |
Token ID | 867 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Klux | +0.953 |
sleeper | +0.928 |
disasters | +0.837 |
liquids | +0.825 |
senal | +0.819 |
Neg logit contributions | |
ieth | -1.556 |
龍� | -1.433 |
iaries | -1.425 |
iary | -1.331 |
eded | -1.299 |
Token | people |
Token ID | 661 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ieth | +1.856 |
龍� | +1.677 |
iaries | +1.665 |
iary | +1.536 |
eded | +1.492 |
Neg logit contributions | |
Klux | -1.657 |
sleeper | -1.612 |
disasters | -1.483 |
senal | -1.477 |
liquids | -1.470 |
Token | , |
Token ID | 11 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
Klux | +1.147 |
sleeper | +1.132 |
disasters | +1.039 |
liquids | +1.024 |
senal | +1.009 |
Neg logit contributions | |
ieth | -1.415 |
iaries | -1.296 |
龍� | -1.291 |
iary | -1.195 |
eded | -1.153 |
Token | he |
Token ID | 339 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
ieth | +0.811 |
龍� | +0.748 |
iaries | +0.743 |
iary | +0.695 |
eded | +0.679 |
Neg logit contributions | |
Klux | -0.478 |
sleeper | -0.464 |
disasters | -0.417 |
liquids | -0.411 |
senal | -0.410 |
Token | exempl |
Token ID | 21433 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
ieth | +4.081 |
龍� | +3.666 |
iaries | +3.632 |
iary | +3.372 |
eded | +3.341 |
Neg logit contributions | |
Klux | -3.639 |
sleeper | -3.552 |
senal | -3.320 |
disasters | -3.247 |
liquids | -3.220 |
Token | ifies |
Token ID | 6945 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ieth | +5.558 |
iaries | +4.499 |
龍� | +4.138 |
iary | +3.871 |
eded | +3.715 |
Neg logit contributions | |
sleeper | -14.197 |
Klux | -14.184 |
senal | -13.788 |
disasters | -13.245 |
liquids | -13.161 |
Token | the |
Token ID | 262 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
ieth | +3.157 |
龍� | +2.904 |
iaries | +2.884 |
iary | +2.718 |
eded | +2.663 |
Neg logit contributions | |
Klux | -1.655 |
sleeper | -1.587 |
senal | -1.416 |
disasters | -1.410 |
liquids | -1.393 |
Token | true |
Token ID | 2081 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ieth | +0.496 |
龍� | +0.458 |
iaries | +0.455 |
iary | +0.425 |
eded | +0.415 |
Neg logit contributions | |
Klux | -0.298 |
sleeper | -0.290 |
disasters | -0.261 |
liquids | -0.257 |
senal | -0.255 |
Token | meaning |
Token ID | 3616 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
ieth | +1.315 |
龍� | +1.208 |
iaries | +1.201 |
iary | +1.129 |
shire | +1.102 |
Neg logit contributions | |
Klux | -0.757 |
sleeper | -0.730 |
disasters | -0.654 |
senal | -0.652 |
liquids | -0.646 |
Token | of |
Token ID | 286 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
ieth | +0.859 |
龍� | +0.779 |
iaries | +0.775 |
iary | +0.707 |
eded | +0.691 |
Neg logit contributions | |
Klux | -0.845 |
sleeper | -0.833 |
disasters | -0.774 |
liquids | -0.766 |
senal | -0.752 |
Token | TA |
Token ID | 5603 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ieth | +1.878 |
龍� | +1.701 |
iaries | +1.659 |
iary | +1.531 |
eded | +1.489 |
Neg logit contributions | |
Klux | -2.049 |
sleeper | -2.019 |
disasters | -1.875 |
senal | -1.868 |
liquids | -1.846 |
Token | 8 |
Token ID | 807 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
Klux | +1.113 |
sleeper | +1.111 |
disasters | +1.010 |
liquids | +0.994 |
senal | +0.976 |
Neg logit contributions | |
ieth | -1.583 |
龍� | -1.451 |
iaries | -1.441 |
iary | -1.334 |
eded | -1.290 |
Token | Dan |
Token ID | 6035 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
ieth | +0.770 |
龍� | +0.700 |
iaries | +0.695 |
iary | +0.643 |
eded | +0.624 |
Neg logit contributions | |
Klux | -0.655 |
sleeper | -0.640 |
disasters | -0.588 |
liquids | -0.582 |
senal | -0.579 |
Token | ie |
Token ID | 494 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
ieth | +3.595 |
龍� | +3.067 |
iaries | +3.056 |
iary | +2.744 |
eded | +2.615 |
Neg logit contributions | |
Klux | -5.534 |
sleeper | -5.496 |
senal | -5.158 |
disasters | -5.154 |
liquids | -5.132 |
Token | le |
Token ID | 293 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
Klux | +2.275 |
sleeper | +2.208 |
disasters | +2.015 |
liquids | +1.983 |
senal | +1.948 |
Neg logit contributions | |
ieth | -3.163 |
龍� | -2.897 |
iaries | -2.880 |
iary | -2.670 |
eded | -2.596 |
Token | Benn |
Token ID | 14025 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Klux | +2.969 |
sleeper | +2.855 |
liquids | +2.710 |
disasters | +2.697 |
plane | +2.669 |
Neg logit contributions | |
ieth | -2.207 |
龍� | -1.919 |
iaries | -1.917 |
iary | -1.696 |
eded | -1.610 |
Token | ati |
Token ID | 7246 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ieth | +7.649 |
iaries | +6.683 |
龍� | +6.320 |
iary | +6.026 |
eded | +5.802 |
Neg logit contributions | |
Klux | -11.885 |
sleeper | -11.425 |
senal | -11.127 |
disasters | -10.856 |
liquids | -10.647 |
Token | ( |
Token ID | 357 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Klux | +0.134 |
sleeper | +0.132 |
disasters | +0.122 |
liquids | +0.120 |
plane | +0.120 |
Neg logit contributions | |
ieth | -0.138 |
龍� | -0.129 |
iaries | -0.127 |
iary | -0.115 |
shire | -0.112 |
Token | Radio |
Token ID | 26093 |
Feature activation | +6.95e+00 |
Pos logit contributions | |
ieth | +1.089 |
龍� | +0.986 |
iaries | +0.979 |
iary | +0.902 |
eded | +0.876 |
Neg logit contributions | |
Klux | -0.992 |
sleeper | -0.970 |
disasters | -0.895 |
liquids | -0.885 |
senal | -0.881 |
Token | Sh |
Token ID | 2484 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
sleeper | +4.733 |
Klux | +4.701 |
disasters | +4.191 |
liquids | +4.174 |
plane | +4.048 |
Neg logit contributions | |
ieth | -8.148 |
龍� | -7.592 |
iaries | -7.494 |
eded | -6.913 |
iary | -6.883 |
Token | ack |
Token ID | 441 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Klux | +3.231 |
sleeper | +3.200 |
disasters | +2.940 |
liquids | +2.916 |
plane | +2.806 |
Neg logit contributions | |
ieth | -3.722 |
龍� | -3.474 |
iaries | -3.352 |
iary | -3.059 |
shire | -3.049 |
Token | mittedly |
Token ID | 43011 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
ieth | +0.063 |
龍� | +0.057 |
iaries | +0.056 |
iary | +0.051 |
eded | +0.050 |
Neg logit contributions | |
Klux | -0.067 |
sleeper | -0.066 |
disasters | -0.061 |
liquids | -0.061 |
senal | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
ieth | +2.676 |
龍� | +2.421 |
iaries | +2.403 |
iary | +2.230 |
eded | +2.157 |
Neg logit contributions | |
Klux | -2.425 |
sleeper | -2.362 |
senal | -2.191 |
liquids | -2.155 |
disasters | -2.152 |
Token | the |
Token ID | 262 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ieth | +0.268 |
龍� | +0.247 |
iaries | +0.246 |
iary | +0.231 |
shire | +0.225 |
Neg logit contributions | |
Klux | -0.159 |
sleeper | -0.153 |
senal | -0.140 |
liquids | -0.136 |
disasters | -0.136 |
Token | case |
Token ID | 1339 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Klux | +0.303 |
sleeper | +0.292 |
senal | +0.261 |
disasters | +0.261 |
liquids | +0.258 |
Neg logit contributions | |
ieth | -0.553 |
龍� | -0.509 |
iaries | -0.508 |
iary | -0.477 |
shire | -0.466 |
Token | was |
Token ID | 373 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
Klux | +0.898 |
sleeper | +0.878 |
disasters | +0.804 |
liquids | +0.791 |
senal | +0.782 |
Neg logit contributions | |
ieth | -1.210 |
龍� | -1.112 |
iaries | -1.099 |
iary | -1.018 |
eded | -0.996 |
Token | circumst |
Token ID | 5397 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
Klux | +0.030 |
sleeper | +0.029 |
senal | +0.026 |
disasters | +0.026 |
liquids | +0.026 |
Neg logit contributions | |
ieth | -0.046 |
龍� | -0.042 |
iaries | -0.042 |
iary | -0.040 |
eded | -0.039 |
Token | ant |
Token ID | 415 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ieth | +5.427 |
iaries | +4.561 |
龍� | +4.062 |
eded | +3.795 |
iary | +3.776 |
Neg logit contributions | |
Klux | -13.971 |
sleeper | -13.773 |
senal | -13.632 |
disasters | -13.199 |
liquids | -13.053 |
Token | ial |
Token ID | 498 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ieth | +0.576 |
iaries | +0.465 |
龍� | +0.431 |
iary | +0.385 |
eded | +0.329 |
Neg logit contributions | |
Klux | -1.861 |
sleeper | -1.837 |
senal | -1.786 |
disasters | -1.747 |
liquids | -1.729 |
Token | . |
Token ID | 13 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Klux | +1.225 |
sleeper | +1.220 |
disasters | +1.132 |
liquids | +1.119 |
plane | +1.091 |
Neg logit contributions | |
ieth | -1.144 |
龍� | -1.037 |
iaries | -1.016 |
iary | -0.916 |
shire | -0.903 |
Token | There |
Token ID | 1318 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
ieth | +0.335 |
龍� | +0.302 |
iaries | +0.299 |
iary | +0.275 |
shire | +0.266 |
Neg logit contributions | |
Klux | -0.351 |
sleeper | -0.345 |
disasters | -0.319 |
senal | -0.318 |
liquids | -0.317 |
Token | was |
Token ID | 373 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Klux | +0.072 |
sleeper | +0.070 |
disasters | +0.065 |
liquids | +0.064 |
senal | +0.063 |
Neg logit contributions | |
ieth | -0.082 |
龍� | -0.075 |
iaries | -0.074 |
iary | -0.068 |
eded | -0.066 |
Token | Buddhist |
Token ID | 20838 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ieth | +0.970 |
龍� | +0.893 |
iaries | +0.888 |
iary | +0.832 |
eded | +0.811 |
Neg logit contributions | |
Klux | -0.580 |
sleeper | -0.564 |
disasters | -0.508 |
liquids | -0.502 |
senal | -0.500 |
Token | bishop |
Token ID | 24233 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
ieth | +1.455 |
龍� | +1.331 |
iaries | +1.323 |
iary | +1.232 |
shire | +1.198 |
Neg logit contributions | |
Klux | -1.058 |
sleeper | -1.029 |
disasters | -0.939 |
liquids | -0.929 |
senal | -0.928 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ieth | +5.177 |
龍� | +4.714 |
iaries | +4.694 |
iary | +4.390 |
eded | +4.266 |
Neg logit contributions | |
Klux | -3.735 |
sleeper | -3.627 |
disasters | -3.296 |
senal | -3.290 |
liquids | -3.277 |
Token | � |
Token ID | 447 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ieth | +1.240 |
龍� | +1.135 |
iaries | +1.129 |
iary | +1.051 |
eded | +1.024 |
Neg logit contributions | |
Klux | -0.873 |
sleeper | -0.850 |
disasters | -0.773 |
liquids | -0.764 |
senal | -0.761 |
Token | � |
Token ID | 251 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
Klux | +0.017 |
sleeper | +0.016 |
disasters | +0.015 |
liquids | +0.015 |
senal | +0.015 |
Neg logit contributions | |
ieth | -0.020 |
龍� | -0.018 |
iaries | -0.018 |
iary | -0.017 |
eded | -0.016 |
Token | Griffith |
Token ID | 30469 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
ieth | +4.616 |
龍� | +4.205 |
iaries | +4.178 |
iary | +3.910 |
shire | +3.807 |
Neg logit contributions | |
Klux | -3.305 |
sleeper | -3.215 |
disasters | -2.926 |
senal | -2.912 |
liquids | -2.899 |
Token | wrote |
Token ID | 2630 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ieth | +10.172 |
龍� | +9.129 |
iaries | +8.931 |
shire | +8.544 |
iary | +8.401 |
Neg logit contributions | |
Klux | -8.823 |
sleeper | -8.733 |
senal | -8.017 |
liquids | -7.945 |
disasters | -7.831 |
Token | . |
Token ID | 764 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
ieth | +1.647 |
龍� | +1.486 |
iaries | +1.474 |
iary | +1.348 |
eded | +1.307 |
Neg logit contributions | |
Klux | -1.695 |
sleeper | -1.660 |
disasters | -1.540 |
liquids | -1.521 |
senal | -1.512 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ieth | +0.478 |
龍� | +0.433 |
iaries | +0.430 |
iary | +0.394 |
eded | +0.383 |
Neg logit contributions | |
Klux | -0.451 |
sleeper | -0.440 |
disasters | -0.407 |
liquids | -0.402 |
senal | -0.399 |
Token |
|
Token ID | 198 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
Klux | +0.120 |
sleeper | +0.119 |
senal | +0.118 |
disasters | +0.110 |
liquids | +0.108 |
Neg logit contributions | |
ieth | -0.096 |
龍� | -0.085 |
iaries | -0.084 |
iary | -0.078 |
shire | -0.076 |
Token | Method |
Token ID | 17410 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Klux | +0.079 |
sleeper | +0.076 |
disasters | +0.071 |
liquids | +0.070 |
plane | +0.069 |
Neg logit contributions | |
ieth | -0.086 |
龍� | -0.078 |
iaries | -0.078 |
iary | -0.071 |
eded | -0.069 |
Token | year |
Token ID | 1941 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
ieth | +1.218 |
龍� | +1.086 |
iaries | +1.075 |
iary | +0.971 |
eded | +0.935 |
Neg logit contributions | |
Klux | -1.551 |
sleeper | -1.523 |
disasters | -1.422 |
liquids | -1.409 |
senal | -1.403 |
Token | fight |
Token ID | 1907 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
ieth | +3.741 |
龍� | +3.415 |
iaries | +3.412 |
iary | +3.218 |
eded | +3.130 |
Neg logit contributions | |
Klux | -2.407 |
sleeper | -2.286 |
senal | -2.113 |
disasters | -2.070 |
liquids | -2.048 |
Token | against |
Token ID | 1028 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
Klux | +3.416 |
sleeper | +3.335 |
disasters | +3.060 |
liquids | +3.002 |
plane | +2.925 |
Neg logit contributions | |
ieth | -4.883 |
龍� | -4.540 |
iaries | -4.516 |
iary | -4.155 |
姫 | -4.011 |
Token | the |
Token ID | 262 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
Klux | +2.837 |
sleeper | +2.805 |
disasters | +2.562 |
liquids | +2.530 |
senal | +2.455 |
Neg logit contributions | |
ieth | -4.364 |
龍� | -4.047 |
iaries | -4.020 |
iary | -3.731 |
shire | -3.643 |
Token | deal |
Token ID | 1730 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Klux | +0.039 |
sleeper | +0.038 |
disasters | +0.035 |
senal | +0.034 |
liquids | +0.034 |
Neg logit contributions | |
ieth | -0.056 |
龍� | -0.051 |
iaries | -0.051 |
iary | -0.047 |
eded | -0.046 |
Token | exempl |
Token ID | 21433 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
ieth | +0.442 |
龍� | +0.404 |
iaries | +0.401 |
iary | +0.372 |
eded | +0.362 |
Neg logit contributions | |
Klux | -0.340 |
sleeper | -0.332 |
disasters | -0.304 |
liquids | -0.300 |
senal | -0.298 |
Token | ifies |
Token ID | 6945 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ieth | +5.585 |
iaries | +4.478 |
龍� | +4.095 |
iary | +3.876 |
eded | +3.670 |
Neg logit contributions | |
Klux | -13.675 |
sleeper | -13.632 |
senal | -13.318 |
liquids | -12.639 |
disasters | -12.591 |
Token | Washington |
Token ID | 2669 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ieth | +2.355 |
龍� | +2.171 |
iaries | +2.161 |
iary | +2.030 |
eded | +1.983 |
Neg logit contributions | |
Klux | -1.289 |
sleeper | -1.246 |
disasters | -1.110 |
liquids | -1.098 |
senal | -1.097 |
Token | � |
Token ID | 447 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ieth | +1.410 |
龍� | +1.283 |
iaries | +1.279 |
iary | +1.174 |
eded | +1.143 |
Neg logit contributions | |
Klux | -1.213 |
sleeper | -1.191 |
disasters | -1.095 |
liquids | -1.081 |
senal | -1.072 |
Token | � |
Token ID | 247 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ieth | +0.098 |
龍� | +0.088 |
iaries | +0.086 |
iary | +0.079 |
shire | +0.077 |
Neg logit contributions | |
Klux | -0.115 |
sleeper | -0.113 |
senal | -0.106 |
disasters | -0.106 |
liquids | -0.104 |
Token | s |
Token ID | 82 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
Klux | +1.597 |
sleeper | +1.577 |
disasters | +1.504 |
liquids | +1.495 |
senal | +1.491 |
Neg logit contributions | |
ieth | -0.390 |
龍� | -0.293 |
iaries | -0.286 |
iary | -0.213 |
eded | -0.187 |
Token | Kara |
Token ID | 34856 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
Klux | +1.354 |
sleeper | +1.331 |
disasters | +1.218 |
liquids | +1.200 |
senal | +1.179 |
Neg logit contributions | |
ieth | -1.762 |
龍� | -1.621 |
iaries | -1.599 |
iary | -1.484 |
shire | -1.440 |
Token | Lang |
Token ID | 16332 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
Klux | +0.341 |
sleeper | +0.330 |
disasters | +0.304 |
liquids | +0.300 |
senal | +0.296 |
Neg logit contributions | |
ieth | -0.362 |
龍� | -0.334 |
iaries | -0.328 |
iary | -0.300 |
shire | -0.293 |
Token | will |
Token ID | 481 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ieth | +2.721 |
龍� | +2.460 |
iaries | +2.444 |
iary | +2.251 |
eded | +2.185 |
Neg logit contributions | |
Klux | -2.554 |
sleeper | -2.499 |
disasters | -2.305 |
liquids | -2.280 |
senal | -2.278 |
Token | officially |
Token ID | 8720 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ieth | +1.086 |
龍� | +0.998 |
iaries | +0.981 |
iary | +0.910 |
eded | +0.885 |
Neg logit contributions | |
Klux | -0.854 |
sleeper | -0.838 |
disasters | -0.767 |
liquids | -0.759 |
senal | -0.744 |
Token | be |
Token ID | 307 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ieth | +2.216 |
iaries | +2.001 |
龍� | +1.998 |
iary | +1.851 |
eded | +1.796 |
Neg logit contributions | |
Klux | -1.905 |
sleeper | -1.858 |
disasters | -1.708 |
senal | -1.707 |
liquids | -1.687 |
Token | induct |
Token ID | 28948 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
ieth | +1.049 |
龍� | +0.958 |
iaries | +0.950 |
iary | +0.880 |
eded | +0.855 |
Neg logit contributions | |
Klux | -0.841 |
sleeper | -0.822 |
disasters | -0.753 |
liquids | -0.744 |
senal | -0.740 |
Token | ed |
Token ID | 276 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
ieth | +5.305 |
iaries | +4.250 |
eded | +3.872 |
iary | +3.755 |
龍� | +3.689 |
Neg logit contributions | |
senal | -13.410 |
Klux | -13.303 |
sleeper | -13.192 |
disasters | -12.408 |
liquids | -12.396 |
Token | into |
Token ID | 656 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ieth | +1.064 |
龍� | +0.983 |
iaries | +0.977 |
iary | +0.915 |
eded | +0.893 |
Neg logit contributions | |
Klux | -0.611 |
sleeper | -0.594 |
disasters | -0.533 |
liquids | -0.525 |
senal | -0.521 |
Token | Canada |
Token ID | 3340 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Klux | +0.085 |
sleeper | +0.084 |
disasters | +0.073 |
liquids | +0.071 |
senal | +0.069 |
Neg logit contributions | |
ieth | -0.196 |
龍� | -0.184 |
iaries | -0.182 |
iary | -0.171 |
shire | -0.167 |
Token | 's |
Token ID | 338 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
Klux | +1.990 |
sleeper | +1.964 |
disasters | +1.789 |
liquids | +1.764 |
senal | +1.746 |
Neg logit contributions | |
ieth | -2.416 |
龍� | -2.224 |
iaries | -2.210 |
iary | -2.032 |
eded | -1.974 |
Token | Soccer |
Token ID | 15872 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
Klux | +0.633 |
sleeper | +0.620 |
disasters | +0.569 |
liquids | +0.562 |
senal | +0.557 |
Neg logit contributions | |
ieth | -0.726 |
龍� | -0.663 |
iaries | -0.657 |
iary | -0.606 |
shire | -0.587 |
Token | paths |
Token ID | 13532 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Klux | +0.594 |
sleeper | +0.579 |
disasters | +0.517 |
liquids | +0.509 |
senal | +0.502 |
Neg logit contributions | |
ieth | -1.093 |
龍� | -1.013 |
iaries | -1.006 |
iary | -0.942 |
eded | -0.921 |
Token | that |
Token ID | 326 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Klux | +0.946 |
sleeper | +0.927 |
disasters | +0.850 |
liquids | +0.841 |
senal | +0.832 |
Neg logit contributions | |
ieth | -1.160 |
龍� | -1.059 |
iaries | -1.050 |
iary | -0.971 |
eded | -0.943 |
Token | lead |
Token ID | 1085 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Klux | +1.457 |
sleeper | +1.429 |
disasters | +1.305 |
liquids | +1.291 |
senal | +1.267 |
Neg logit contributions | |
ieth | -1.878 |
龍� | -1.721 |
iaries | -1.705 |
iary | -1.579 |
shire | -1.530 |
Token | up |
Token ID | 510 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
ieth | +1.654 |
iaries | +1.504 |
龍� | +1.502 |
iary | +1.407 |
shire | +1.374 |
Neg logit contributions | |
Klux | -1.151 |
sleeper | -1.109 |
senal | -1.020 |
disasters | -1.011 |
liquids | -0.993 |
Token | to |
Token ID | 284 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
ieth | +0.083 |
龍� | +0.077 |
iaries | +0.076 |
iary | +0.071 |
eded | +0.069 |
Neg logit contributions | |
Klux | -0.056 |
sleeper | -0.055 |
disasters | -0.050 |
liquids | -0.049 |
senal | -0.048 |
Token | Lynd |
Token ID | 33561 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
ieth | +1.173 |
龍� | +1.085 |
iaries | +1.078 |
iary | +1.010 |
eded | +0.986 |
Neg logit contributions | |
Klux | -0.651 |
sleeper | -0.633 |
disasters | -0.567 |
liquids | -0.558 |
senal | -0.552 |
Token | ale |
Token ID | 1000 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ieth | +6.030 |
iaries | +5.148 |
iary | +5.077 |
eded | +4.833 |
shire | +4.803 |
Neg logit contributions | |
senal | -12.826 |
sleeper | -11.685 |
Klux | -11.604 |
disasters | -11.103 |
�� | -11.046 |
Token | , |
Token ID | 11 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
Klux | +1.307 |
sleeper | +1.285 |
disasters | +1.182 |
liquids | +1.174 |
senal | +1.152 |
Neg logit contributions | |
ieth | -1.406 |
龍� | -1.280 |
iaries | -1.277 |
iary | -1.163 |
eded | -1.127 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ieth | +0.663 |
龍� | +0.611 |
iaries | +0.608 |
iary | +0.571 |
eded | +0.559 |
Neg logit contributions | |
Klux | -0.368 |
sleeper | -0.354 |
disasters | -0.317 |
senal | -0.317 |
liquids | -0.312 |
Token | street |
Token ID | 4675 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
Klux | +0.115 |
sleeper | +0.112 |
disasters | +0.101 |
liquids | +0.100 |
senal | +0.099 |
Neg logit contributions | |
ieth | -0.187 |
龍� | -0.173 |
iaries | -0.172 |
iary | -0.160 |
eded | -0.156 |
Token | crossing |
Token ID | 12538 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Klux | +4.298 |
sleeper | +4.289 |
disasters | +3.861 |
liquids | +3.826 |
plane | +3.801 |
Neg logit contributions | |
ieth | -5.363 |
龍� | -5.018 |
iaries | -4.960 |
iary | -4.523 |
shire | -4.405 |
Token | I |
Token ID | 314 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
ieth | +1.746 |
龍� | +1.589 |
iaries | +1.578 |
iary | +1.460 |
eded | +1.418 |
Neg logit contributions | |
Klux | -1.455 |
sleeper | -1.422 |
disasters | -1.305 |
liquids | -1.290 |
senal | -1.285 |
Token | thought |
Token ID | 1807 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ieth | +2.849 |
龍� | +2.567 |
iaries | +2.554 |
iary | +2.348 |
eded | +2.325 |
Neg logit contributions | |
Klux | -2.935 |
sleeper | -2.848 |
senal | -2.733 |
disasters | -2.637 |
liquids | -2.594 |
Token | that |
Token ID | 326 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Klux | +1.695 |
sleeper | +1.653 |
disasters | +1.501 |
liquids | +1.479 |
senal | +1.441 |
Neg logit contributions | |
ieth | -2.626 |
龍� | -2.424 |
iaries | -2.409 |
iary | -2.243 |
eded | -2.189 |
Token | . |
Token ID | 13 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
Klux | +1.867 |
sleeper | +1.839 |
disasters | +1.699 |
liquids | +1.679 |
senal | +1.633 |
Neg logit contributions | |
ieth | -2.076 |
龍� | -1.893 |
iaries | -1.884 |
iary | -1.733 |
shire | -1.675 |
Token | In |
Token ID | 554 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
ieth | +0.812 |
龍� | +0.732 |
iaries | +0.727 |
iary | +0.667 |
eded | +0.646 |
Neg logit contributions | |
Klux | -0.811 |
sleeper | -0.795 |
disasters | -0.735 |
liquids | -0.728 |
senal | -0.725 |
Token | retrospect |
Token ID | 23583 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
ieth | +3.456 |
龍� | +3.182 |
iaries | +3.168 |
iary | +2.979 |
eded | +2.899 |
Neg logit contributions | |
Klux | -1.960 |
sleeper | -1.890 |
senal | -1.679 |
disasters | -1.678 |
liquids | -1.660 |
Token | , |
Token ID | 11 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
ieth | +9.941 |
iaries | +8.875 |
龍� | +8.849 |
iary | +8.286 |
shire | +7.991 |
Neg logit contributions | |
Klux | -8.641 |
sleeper | -8.206 |
senal | -7.854 |
liquids | -7.407 |
disasters | -7.386 |
Token | that |
Token ID | 326 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ieth | +0.569 |
龍� | +0.521 |
iaries | +0.518 |
iary | +0.484 |
eded | +0.473 |
Neg logit contributions | |
Klux | -0.383 |
sleeper | -0.370 |
senal | -0.335 |
disasters | -0.333 |
liquids | -0.330 |
Token | was |
Token ID | 373 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
Klux | +1.545 |
sleeper | +1.525 |
disasters | +1.400 |
liquids | +1.380 |
senal | +1.351 |
Neg logit contributions | |
ieth | -1.864 |
龍� | -1.699 |
iaries | -1.691 |
iary | -1.560 |
eded | -1.512 |
Token | getting |
Token ID | 1972 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
ieth | +0.033 |
龍� | +0.030 |
iaries | +0.030 |
iary | +0.028 |
eded | +0.028 |
Neg logit contributions | |
Klux | -0.019 |
sleeper | -0.019 |
disasters | -0.017 |
senal | -0.017 |
liquids | -0.016 |
Token | ahead |
Token ID | 4058 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
Klux | +2.619 |
sleeper | +2.580 |
disasters | +2.313 |
liquids | +2.256 |
senal | +2.177 |
Neg logit contributions | |
ieth | -4.739 |
龍� | -4.405 |
iaries | -4.356 |
iary | -4.075 |
shire | -3.996 |
Token | st |
Token ID | 336 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Klux | +0.196 |
sleeper | +0.191 |
disasters | +0.172 |
liquids | +0.170 |
senal | +0.167 |
Neg logit contributions | |
ieth | -0.319 |
龍� | -0.294 |
iaries | -0.292 |
iary | -0.272 |
eded | -0.265 |
Token | eeper |
Token ID | 41278 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ieth | +1.998 |
龍� | +1.837 |
iaries | +1.804 |
iary | +1.666 |
shire | +1.632 |
Neg logit contributions | |
Klux | -1.705 |
sleeper | -1.664 |
disasters | -1.526 |
liquids | -1.510 |
senal | -1.485 |
Token | paths |
Token ID | 13532 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Klux | +0.925 |
sleeper | +0.913 |
disasters | +0.819 |
liquids | +0.810 |
senal | +0.783 |
Neg logit contributions | |
ieth | -1.492 |
龍� | -1.385 |
iaries | -1.371 |
iary | -1.277 |
eded | -1.246 |
Token | up |
Token ID | 510 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Klux | +1.078 |
sleeper | +1.059 |
disasters | +0.973 |
liquids | +0.963 |
senal | +0.946 |
Neg logit contributions | |
ieth | -1.253 |
龍� | -1.143 |
iaries | -1.134 |
iary | -1.045 |
shire | -1.013 |
Token | to |
Token ID | 284 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
Klux | +0.331 |
sleeper | +0.323 |
disasters | +0.292 |
liquids | +0.289 |
senal | +0.285 |
Neg logit contributions | |
ieth | -0.488 |
龍� | -0.451 |
iaries | -0.447 |
iary | -0.415 |
eded | -0.403 |
Token | Lynd |
Token ID | 33561 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
ieth | +0.907 |
龍� | +0.833 |
iaries | +0.827 |
iary | +0.770 |
eded | +0.750 |
Neg logit contributions | |
Klux | -0.627 |
sleeper | -0.612 |
disasters | -0.555 |
liquids | -0.548 |
senal | -0.545 |
Token | ale |
Token ID | 1000 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ieth | +6.081 |
iaries | +5.176 |
iary | +5.147 |
eded | +4.898 |
shire | +4.813 |
Neg logit contributions | |
senal | -12.690 |
sleeper | -11.583 |
Klux | -11.448 |
disasters | -10.989 |
�� | -10.910 |
Token | , |
Token ID | 11 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
Klux | +1.693 |
sleeper | +1.668 |
disasters | +1.538 |
liquids | +1.524 |
plane | +1.500 |
Neg logit contributions | |
ieth | -1.727 |
龍� | -1.566 |
iaries | -1.565 |
iary | -1.421 |
shire | -1.371 |
Token | and |
Token ID | 290 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ieth | +0.638 |
龍� | +0.579 |
iaries | +0.575 |
iary | +0.532 |
eded | +0.517 |
Neg logit contributions | |
Klux | -0.545 |
sleeper | -0.532 |
disasters | -0.489 |
senal | -0.484 |
liquids | -0.484 |
Token | would |
Token ID | 561 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Klux | +1.017 |
sleeper | +0.991 |
disasters | +0.899 |
liquids | +0.887 |
senal | +0.883 |
Neg logit contributions | |
ieth | -1.521 |
龍� | -1.396 |
iaries | -1.388 |
iary | -1.294 |
eded | -1.261 |
Token | prefer |
Token ID | 4702 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Klux | +0.097 |
sleeper | +0.094 |
disasters | +0.086 |
senal | +0.085 |
liquids | +0.084 |
Neg logit contributions | |
ieth | -0.138 |
龍� | -0.126 |
iaries | -0.126 |
iary | -0.117 |
eded | -0.114 |
Token | the |
Token ID | 262 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Klux | +0.925 |
sleeper | +0.904 |
disasters | +0.811 |
liquids | +0.799 |
senal | +0.785 |
Neg logit contributions | |
ieth | -1.591 |
龍� | -1.471 |
iaries | -1.460 |
iary | -1.365 |
shire | -1.332 |
Token | super |
Token ID | 2208 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ieth | +0.264 |
龍� | +0.242 |
iaries | +0.240 |
iary | +0.223 |
eded | +0.217 |
Neg logit contributions | |
Klux | -0.192 |
sleeper | -0.187 |
disasters | -0.171 |
liquids | -0.169 |
senal | -0.168 |
Token | - |
Token ID | 12 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Klux | +1.595 |
sleeper | +1.583 |
disasters | +1.423 |
liquids | +1.405 |
plane | +1.371 |
Neg logit contributions | |
ieth | -2.152 |
龍� | -1.997 |
iaries | -1.966 |
iary | -1.825 |
shire | -1.789 |
Token | rich |
Token ID | 7527 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ieth | +1.561 |
龍� | +1.386 |
iaries | +1.376 |
iary | +1.247 |
eded | +1.203 |
Neg logit contributions | |
Klux | -1.946 |
sleeper | -1.910 |
disasters | -1.783 |
liquids | -1.767 |
senal | -1.765 |
Token | together |
Token ID | 1978 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
ieth | +1.800 |
龍� | +1.645 |
iaries | +1.636 |
iary | +1.524 |
eded | +1.483 |
Neg logit contributions | |
Klux | -1.301 |
sleeper | -1.264 |
disasters | -1.152 |
senal | -1.138 |
liquids | -1.137 |
Token | constit |
Token ID | 7892 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
ieth | +3.039 |
龍� | +2.785 |
iaries | +2.767 |
iary | +2.583 |
eded | +2.517 |
Neg logit contributions | |
Klux | -2.063 |
sleeper | -2.006 |
disasters | -1.821 |
liquids | -1.796 |
senal | -1.796 |
Token | uting |
Token ID | 15129 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
ieth | +8.124 |
龍� | +6.989 |
iaries | +6.966 |
eded | +6.373 |
iary | +6.263 |
Neg logit contributions | |
sleeper | -10.196 |
Klux | -10.192 |
senal | -9.633 |
disasters | -9.429 |
liquids | -9.268 |
Token | the |
Token ID | 262 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ieth | +0.946 |
龍� | +0.878 |
iaries | +0.871 |
iary | +0.818 |
eded | +0.800 |
Neg logit contributions | |
Klux | -0.484 |
sleeper | -0.472 |
disasters | -0.419 |
liquids | -0.412 |
senal | -0.406 |
Token | top |
Token ID | 1353 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ieth | +0.356 |
龍� | +0.325 |
iaries | +0.323 |
iary | +0.300 |
eded | +0.292 |
Neg logit contributions | |
Klux | -0.257 |
sleeper | -0.249 |
disasters | -0.228 |
senal | -0.226 |
liquids | -0.225 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
ieth | +1.920 |
iaries | +1.744 |
龍� | +1.744 |
iary | +1.629 |
eded | +1.579 |
Neg logit contributions | |
Klux | -1.335 |
sleeper | -1.285 |
disasters | -1.174 |
senal | -1.172 |
liquids | -1.154 |
Token | % |
Token ID | 4 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ieth | +2.333 |
龍� | +2.080 |
iaries | +2.054 |
iary | +1.850 |
eded | +1.779 |
Neg logit contributions | |
Klux | -3.132 |
sleeper | -3.082 |
disasters | -2.881 |
liquids | -2.858 |
senal | -2.838 |
Token | makes |
Token ID | 1838 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
ieth | +5.530 |
龍� | +4.969 |
iaries | +4.962 |
iary | +4.636 |
shire | +4.521 |
Neg logit contributions | |
Klux | -4.418 |
sleeper | -4.293 |
senal | -3.966 |
liquids | -3.913 |
disasters | -3.907 |
Token | the |
Token ID | 262 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Klux | +0.587 |
sleeper | +0.571 |
disasters | +0.510 |
liquids | +0.501 |
senal | +0.495 |
Neg logit contributions | |
ieth | -1.057 |
龍� | -0.976 |
iaries | -0.970 |
iary | -0.908 |
eded | -0.888 |
Token | acquaintance |
Token ID | 35552 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
Klux | +0.256 |
sleeper | +0.248 |
disasters | +0.224 |
liquids | +0.221 |
senal | +0.220 |
Neg logit contributions | |
ieth | -0.427 |
龍� | -0.394 |
iaries | -0.391 |
iary | -0.366 |
eded | -0.357 |
Token | of |
Token ID | 286 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
ieth | +5.220 |
龍� | +4.673 |
iaries | +4.631 |
iary | +4.226 |
eded | +4.081 |
Neg logit contributions | |
Klux | -5.884 |
sleeper | -5.770 |
disasters | -5.369 |
liquids | -5.318 |
senal | -5.294 |
Token | its |
Token ID | 663 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
ieth | +0.542 |
龍� | +0.499 |
iaries | +0.496 |
iary | +0.462 |
eded | +0.450 |
Neg logit contributions | |
Klux | -0.351 |
sleeper | -0.342 |
disasters | -0.309 |
liquids | -0.303 |
senal | -0.302 |
Token | propriet |
Token ID | 38090 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
ieth | +0.966 |
龍� | +0.886 |
iaries | +0.881 |
iary | +0.826 |
eded | +0.807 |
Neg logit contributions | |
Klux | -0.599 |
sleeper | -0.582 |
disasters | -0.527 |
liquids | -0.520 |
senal | -0.519 |
Token | or |
Token ID | 273 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
ieth | +5.430 |
iaries | +4.386 |
龍� | +4.231 |
iary | +3.827 |
eded | +3.632 |
Neg logit contributions | |
Klux | -12.905 |
sleeper | -12.845 |
senal | -12.184 |
liquids | -12.159 |
disasters | -12.156 |
Token | , |
Token ID | 11 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
ieth | +0.329 |
龍� | +0.301 |
iaries | +0.298 |
iary | +0.270 |
shire | +0.264 |
Neg logit contributions | |
Klux | -0.312 |
sleeper | -0.305 |
disasters | -0.279 |
senal | -0.275 |
liquids | -0.275 |
Token | alone |
Token ID | 3436 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
ieth | +0.929 |
龍� | +0.851 |
iaries | +0.844 |
iary | +0.780 |
shire | +0.760 |
Neg logit contributions | |
Klux | -0.728 |
sleeper | -0.710 |
disasters | -0.648 |
liquids | -0.638 |
senal | -0.637 |
Token | ly |
Token ID | 306 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
ieth | +0.970 |
龍� | +0.883 |
iaries | +0.880 |
iary | +0.804 |
shire | +0.777 |
Neg logit contributions | |
Klux | -0.912 |
sleeper | -0.896 |
disasters | -0.821 |
liquids | -0.814 |
senal | -0.805 |
Token | young |
Token ID | 1862 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ieth | +1.045 |
龍� | +0.966 |
iaries | +0.960 |
iary | +0.893 |
shire | +0.872 |
Neg logit contributions | |
Klux | -0.652 |
sleeper | -0.638 |
disasters | -0.575 |
liquids | -0.566 |
senal | -0.555 |
Token | 20 |
Token ID | 1160 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
Klux | +1.675 |
sleeper | +1.647 |
disasters | +1.487 |
liquids | +1.469 |
senal | +1.440 |
Neg logit contributions | |
ieth | -2.498 |
iaries | -2.290 |
龍� | -2.286 |
iary | -2.118 |
eded | -2.065 |
Token | % |
Token ID | 4 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ieth | +3.232 |
龍� | +2.880 |
iaries | +2.855 |
iary | +2.586 |
eded | +2.492 |
Neg logit contributions | |
Klux | -4.001 |
sleeper | -3.927 |
disasters | -3.664 |
liquids | -3.630 |
senal | -3.615 |
Token | cooler |
Token ID | 19346 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
Klux | +0.876 |
sleeper | +0.871 |
disasters | +0.798 |
liquids | +0.790 |
senal | +0.780 |
Neg logit contributions | |
ieth | -1.003 |
龍� | -0.916 |
iaries | -0.912 |
iary | -0.835 |
eded | -0.812 |
Token | ( |
Token ID | 357 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
sleeper | +3.794 |
Klux | +3.779 |
disasters | +3.450 |
liquids | +3.431 |
senal | +3.295 |
Neg logit contributions | |
ieth | -4.862 |
龍� | -4.510 |
iaries | -4.472 |
iary | -4.102 |
shire | -4.023 |
Token | aka |
Token ID | 8130 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ieth | +0.489 |
龍� | +0.440 |
iaries | +0.436 |
iary | +0.400 |
eded | +0.387 |
Neg logit contributions | |
Klux | -0.503 |
sleeper | -0.493 |
disasters | -0.457 |
liquids | -0.452 |
senal | -0.451 |
Token | Rainbow |
Token ID | 19909 |
Feature activation | +8.79e+00 |
Pos logit contributions | |
Klux | +1.352 |
sleeper | +1.328 |
disasters | +1.201 |
liquids | +1.187 |
senal | +1.164 |
Neg logit contributions | |
ieth | -2.003 |
龍� | -1.841 |
iaries | -1.830 |
iary | -1.700 |
eded | -1.657 |
Token | Dash |
Token ID | 16189 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
sleeper | +6.499 |
Klux | +6.477 |
disasters | +5.881 |
liquids | +5.800 |
plane | +5.781 |
Neg logit contributions | |
ieth | -9.288 |
龍� | -8.795 |
iaries | -8.778 |
iary | -7.906 |
urations | -7.670 |
Token | any |
Token ID | 597 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Klux | +3.268 |
sleeper | +3.268 |
disasters | +2.989 |
liquids | +2.964 |
plane | +2.891 |
Neg logit contributions | |
ieth | -3.653 |
龍� | -3.359 |
iaries | -3.333 |
iary | -3.026 |
eded | -2.931 |
Token | %) |
Token ID | 4407 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
Klux | +0.200 |
sleeper | +0.197 |
disasters | +0.183 |
liquids | +0.182 |
senal | +0.181 |
Neg logit contributions | |
ieth | -0.162 |
龍� | -0.145 |
iaries | -0.145 |
iary | -0.129 |
shire | -0.126 |
Token | [ |
Token ID | 685 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
ieth | +0.798 |
龍� | +0.727 |
iaries | +0.722 |
iary | +0.668 |
eded | +0.649 |
Neg logit contributions | |
Klux | -0.664 |
sleeper | -0.649 |
disasters | -0.596 |
liquids | -0.589 |
senal | -0.586 |
Token | b |
Token ID | 65 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Klux | +3.147 |
sleeper | +3.099 |
plane | +2.875 |
liquids | +2.841 |
disasters | +2.821 |
Neg logit contributions | |
ieth | -3.516 |
龍� | -3.229 |
iaries | -3.198 |
iary | -2.913 |
shire | -2.783 |
Token | Being |
Token ID | 11204 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ieth | +0.345 |
龍� | +0.312 |
iaries | +0.310 |
iary | +0.286 |
shire | +0.277 |
Neg logit contributions | |
Klux | -0.319 |
sleeper | -0.312 |
disasters | -0.288 |
liquids | -0.285 |
senal | -0.285 |
Token | the |
Token ID | 262 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
Klux | +1.038 |
sleeper | +1.010 |
disasters | +0.907 |
liquids | +0.892 |
senal | +0.882 |
Neg logit contributions | |
ieth | -1.781 |
龍� | -1.646 |
iaries | -1.634 |
iary | -1.528 |
eded | -1.493 |
Token | product |
Token ID | 1720 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Klux | +0.650 |
sleeper | +0.634 |
disasters | +0.572 |
liquids | +0.563 |
senal | +0.556 |
Neg logit contributions | |
ieth | -1.031 |
龍� | -0.951 |
iaries | -0.944 |
iary | -0.880 |
eded | -0.859 |
Token | of |
Token ID | 286 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Klux | +1.165 |
sleeper | +1.162 |
disasters | +1.075 |
liquids | +1.054 |
plane | +1.025 |
Neg logit contributions | |
ieth | -1.240 |
龍� | -1.149 |
iaries | -1.128 |
iary | -1.023 |
eded | -1.008 |
Token | a |
Token ID | 257 |
Feature activation | -7.64e-03 |
Pos logit contributions | |
Klux | +0.153 |
sleeper | +0.149 |
disasters | +0.133 |
liquids | +0.130 |
senal | +0.129 |
Neg logit contributions | |
ieth | -0.288 |
龍� | -0.267 |
iaries | -0.266 |
iary | -0.249 |
eded | -0.244 |
Token | racist |
Token ID | 9811 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
ieth | +0.010 |
龍� | +0.009 |
iaries | +0.009 |
iary | +0.008 |
shire | +0.008 |
Neg logit contributions | |
Klux | -0.005 |
sleeper | -0.005 |
disasters | -0.004 |
liquids | -0.004 |
senal | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Klux | +5.142 |
sleeper | +5.048 |
disasters | +4.516 |
liquids | +4.402 |
turkey | +4.315 |
Neg logit contributions | |
ieth | -7.771 |
龍� | -7.365 |
iaries | -7.201 |
iary | -6.575 |
eded | -6.521 |
Token | class |
Token ID | 1398 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
ieth | +0.364 |
龍� | +0.339 |
iaries | +0.337 |
iary | +0.317 |
eded | +0.310 |
Neg logit contributions | |
Klux | -0.170 |
sleeper | -0.165 |
disasters | -0.145 |
liquids | -0.143 |
senal | -0.141 |
Token | ist |
Token ID | 396 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ieth | +2.260 |
龍� | +2.009 |
iaries | +1.991 |
iary | +1.801 |
eded | +1.735 |
Neg logit contributions | |
Klux | -2.875 |
sleeper | -2.822 |
disasters | -2.635 |
liquids | -2.611 |
senal | -2.602 |
Token | , |
Token ID | 11 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
ieth | +0.282 |
龍� | +0.260 |
iaries | +0.259 |
iary | +0.243 |
eded | +0.237 |
Neg logit contributions | |
Klux | -0.154 |
sleeper | -0.150 |
disasters | -0.134 |
liquids | -0.132 |
senal | -0.132 |
Token | misogyn |
Token ID | 22795 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ieth | +0.574 |
龍� | +0.530 |
iaries | +0.526 |
iary | +0.491 |
eded | +0.480 |
Neg logit contributions | |
Klux | -0.359 |
sleeper | -0.349 |
disasters | -0.315 |
liquids | -0.311 |
senal | -0.307 |
Token | I |
Token ID | 40 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Klux | +0.533 |
sleeper | +0.522 |
disasters | +0.481 |
liquids | +0.476 |
senal | +0.473 |
Neg logit contributions | |
ieth | -0.576 |
龍� | -0.522 |
iaries | -0.518 |
iary | -0.476 |
eded | -0.462 |
Token | know |
Token ID | 760 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ieth | +1.090 |
龍� | +0.987 |
iaries | +0.982 |
iary | +0.905 |
eded | +0.881 |
Neg logit contributions | |
Klux | -1.006 |
sleeper | -0.985 |
disasters | -0.908 |
senal | -0.905 |
liquids | -0.897 |
Token | about |
Token ID | 546 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
Klux | +1.170 |
sleeper | +1.137 |
disasters | +1.026 |
senal | +1.020 |
liquids | +1.014 |
Neg logit contributions | |
ieth | -1.823 |
龍� | -1.672 |
iaries | -1.665 |
iary | -1.557 |
eded | -1.516 |
Token | self |
Token ID | 2116 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Klux | +1.916 |
sleeper | +1.866 |
disasters | +1.673 |
liquids | +1.641 |
senal | +1.602 |
Neg logit contributions | |
ieth | -3.539 |
龍� | -3.281 |
iaries | -3.258 |
iary | -3.051 |
eded | -2.983 |
Token | - |
Token ID | 12 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Klux | +1.328 |
sleeper | +1.290 |
disasters | +1.218 |
liquids | +1.186 |
plane | +1.135 |
Neg logit contributions | |
ieth | -1.766 |
龍� | -1.681 |
iaries | -1.634 |
iary | -1.507 |
shire | -1.485 |
Token | hate |
Token ID | 37035 |
Feature activation | +8.20e+00 |
Pos logit contributions | |
ieth | +1.007 |
龍� | +0.915 |
iaries | +0.905 |
iary | +0.827 |
shire | +0.799 |
Neg logit contributions | |
Klux | -1.040 |
sleeper | -1.016 |
disasters | -0.947 |
liquids | -0.933 |
senal | -0.921 |
Token | . |
Token ID | 13 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Klux | +7.448 |
sleeper | +7.361 |
disasters | +6.978 |
liquids | +6.778 |
turkey | +6.517 |
Neg logit contributions | |
ieth | -7.667 |
龍� | -7.191 |
iaries | -6.879 |
iary | -6.304 |
姫 | -6.104 |
Token | I |
Token ID | 314 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
ieth | +0.227 |
龍� | +0.206 |
iaries | +0.204 |
iary | +0.189 |
shire | +0.183 |
Neg logit contributions | |
Klux | -0.203 |
sleeper | -0.199 |
disasters | -0.183 |
senal | -0.181 |
liquids | -0.181 |
Token | know |
Token ID | 760 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
ieth | +2.252 |
iaries | +2.030 |
龍� | +2.027 |
iary | +1.858 |
eded | +1.818 |
Neg logit contributions | |
Klux | -2.277 |
sleeper | -2.230 |
senal | -2.097 |
disasters | -2.062 |
liquids | -2.037 |
Token | about |
Token ID | 546 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
Klux | +0.595 |
sleeper | +0.577 |
disasters | +0.518 |
liquids | +0.510 |
senal | +0.510 |
Neg logit contributions | |
ieth | -1.034 |
龍� | -0.953 |
iaries | -0.949 |
iary | -0.889 |
eded | -0.867 |
Token | this |
Token ID | 428 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
Klux | +1.487 |
sleeper | +1.445 |
disasters | +1.284 |
liquids | +1.259 |
senal | +1.227 |
Neg logit contributions | |
ieth | -3.045 |
龍� | -2.830 |
iaries | -2.808 |
iary | -2.637 |
eded | -2.580 |
Token | would |
Token ID | 561 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
ieth | +1.065 |
龍� | +0.964 |
iaries | +0.956 |
iary | +0.880 |
shire | +0.852 |
Neg logit contributions | |
Klux | -1.000 |
sleeper | -0.979 |
disasters | -0.904 |
liquids | -0.894 |
senal | -0.888 |
Token | have |
Token ID | 423 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
Klux | +0.657 |
sleeper | +0.640 |
disasters | +0.585 |
senal | +0.579 |
liquids | +0.578 |
Neg logit contributions | |
ieth | -0.846 |
龍� | -0.772 |
iaries | -0.768 |
iary | -0.713 |
eded | -0.694 |
Token | to |
Token ID | 284 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
Klux | +0.326 |
sleeper | +0.317 |
disasters | +0.287 |
liquids | +0.283 |
senal | +0.281 |
Neg logit contributions | |
ieth | -0.512 |
龍� | -0.472 |
iaries | -0.468 |
iary | -0.437 |
eded | -0.426 |
Token | buy |
Token ID | 2822 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
ieth | +1.003 |
iaries | +0.916 |
龍� | +0.912 |
iary | +0.853 |
eded | +0.834 |
Neg logit contributions | |
Klux | -0.753 |
sleeper | -0.730 |
senal | -0.675 |
disasters | -0.663 |
liquids | -0.651 |
Token | their |
Token ID | 511 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
Klux | +2.058 |
sleeper | +2.033 |
disasters | +1.831 |
liquids | +1.814 |
senal | +1.746 |
Neg logit contributions | |
ieth | -3.521 |
龍� | -3.277 |
iaries | -3.241 |
iary | -3.026 |
shire | -2.963 |
Token | oil |
Token ID | 3056 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
Klux | +0.037 |
sleeper | +0.036 |
disasters | +0.032 |
senal | +0.032 |
liquids | +0.032 |
Neg logit contributions | |
ieth | -0.058 |
龍� | -0.053 |
iaries | -0.053 |
iary | -0.050 |
eded | -0.049 |
Token | directly |
Token ID | 3264 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
sleeper | +5.177 |
Klux | +5.168 |
disasters | +4.772 |
liquids | +4.770 |
plane | +4.510 |
Neg logit contributions | |
ieth | -7.250 |
龍� | -6.820 |
iaries | -6.601 |
iary | -6.084 |
shire | -5.964 |
Token | from |
Token ID | 422 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Klux | +0.202 |
sleeper | +0.197 |
disasters | +0.181 |
liquids | +0.179 |
senal | +0.178 |
Neg logit contributions | |
ieth | -0.241 |
龍� | -0.220 |
iaries | -0.218 |
iary | -0.201 |
eded | -0.195 |
Token | the |
Token ID | 262 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
Klux | +0.754 |
sleeper | +0.738 |
disasters | +0.665 |
liquids | +0.654 |
senal | +0.645 |
Neg logit contributions | |
ieth | -1.303 |
龍� | -1.206 |
iaries | -1.196 |
iary | -1.118 |
shire | -1.092 |
Token | government |
Token ID | 1230 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Klux | +0.062 |
sleeper | +0.060 |
disasters | +0.054 |
senal | +0.054 |
liquids | +0.053 |
Neg logit contributions | |
ieth | -0.095 |
龍� | -0.087 |
iaries | -0.086 |
iary | -0.081 |
eded | -0.079 |
Token | of |
Token ID | 286 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Klux | +1.968 |
sleeper | +1.960 |
disasters | +1.815 |
liquids | +1.797 |
senal | +1.746 |
Neg logit contributions | |
ieth | -2.133 |
龍� | -1.953 |
iaries | -1.920 |
iary | -1.757 |
shire | -1.713 |
Token | to |
Token ID | 284 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ieth | +0.588 |
龍� | +0.539 |
iaries | +0.533 |
iary | +0.493 |
eded | +0.481 |
Neg logit contributions | |
Klux | -0.433 |
sleeper | -0.424 |
disasters | -0.389 |
liquids | -0.383 |
senal | -0.376 |
Token | the |
Token ID | 262 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ieth | +1.709 |
iaries | +1.583 |
龍� | +1.578 |
iary | +1.485 |
eded | +1.452 |
Neg logit contributions | |
Klux | -0.842 |
sleeper | -0.806 |
senal | -0.714 |
disasters | -0.707 |
liquids | -0.704 |
Token | families |
Token ID | 4172 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
ieth | +0.408 |
iaries | +0.377 |
龍� | +0.377 |
iary | +0.355 |
eded | +0.347 |
Neg logit contributions | |
Klux | -0.200 |
sleeper | -0.192 |
senal | -0.169 |
disasters | -0.169 |
liquids | -0.167 |
Token | of |
Token ID | 286 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ieth | +0.716 |
龍� | +0.653 |
iaries | +0.641 |
iary | +0.589 |
shire | +0.574 |
Neg logit contributions | |
Klux | -0.696 |
sleeper | -0.687 |
disasters | -0.639 |
liquids | -0.629 |
senal | -0.617 |
Token | the |
Token ID | 262 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ieth | +0.739 |
龍� | +0.684 |
iaries | +0.682 |
iary | +0.641 |
eded | +0.627 |
Neg logit contributions | |
Klux | -0.356 |
sleeper | -0.343 |
disasters | -0.302 |
senal | -0.299 |
liquids | -0.298 |
Token | Turkish |
Token ID | 9663 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
ieth | +0.571 |
龍� | +0.528 |
iaries | +0.527 |
iary | +0.495 |
eded | +0.485 |
Neg logit contributions | |
Klux | -0.274 |
sleeper | -0.263 |
disasters | -0.231 |
senal | -0.231 |
liquids | -0.228 |
Token | citizens |
Token ID | 4290 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Klux | +3.661 |
sleeper | +3.655 |
disasters | +3.338 |
liquids | +3.231 |
plane | +3.133 |
Neg logit contributions | |
ieth | -6.685 |
龍� | -6.318 |
iaries | -6.174 |
iary | -5.801 |
姫 | -5.681 |
Token | who |
Token ID | 508 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
ieth | +0.320 |
龍� | +0.295 |
iaries | +0.293 |
iary | +0.273 |
shire | +0.266 |
Neg logit contributions | |
Klux | -0.202 |
sleeper | -0.198 |
disasters | -0.179 |
liquids | -0.176 |
senal | -0.174 |
Token | were |
Token ID | 547 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
Klux | +0.816 |
sleeper | +0.799 |
disasters | +0.735 |
liquids | +0.725 |
senal | +0.714 |
Neg logit contributions | |
ieth | -1.007 |
龍� | -0.919 |
iaries | -0.910 |
iary | -0.843 |
shire | -0.819 |
Token | killed |
Token ID | 2923 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
Klux | +0.588 |
sleeper | +0.571 |
disasters | +0.510 |
liquids | +0.502 |
senal | +0.498 |
Neg logit contributions | |
ieth | -1.082 |
龍� | -1.000 |
iaries | -0.994 |
iary | -0.933 |
eded | -0.911 |
Token | or |
Token ID | 393 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
Klux | +3.131 |
sleeper | +3.088 |
disasters | +2.888 |
liquids | +2.804 |
plane | +2.780 |
Neg logit contributions | |
ieth | -3.488 |
龍� | -3.221 |
iaries | -3.167 |
iary | -2.906 |
姫 | -2.804 |
Token | : |
Token ID | 25 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ieth | +1.879 |
龍� | +1.704 |
iaries | +1.690 |
iary | +1.554 |
eded | +1.509 |
Neg logit contributions | |
Klux | -1.754 |
sleeper | -1.718 |
disasters | -1.586 |
liquids | -1.568 |
senal | -1.559 |
Token | The |
Token ID | 383 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
Klux | +0.490 |
sleeper | +0.479 |
disasters | +0.442 |
liquids | +0.436 |
senal | +0.433 |
Neg logit contributions | |
ieth | -0.547 |
龍� | -0.498 |
iaries | -0.494 |
iary | -0.454 |
eded | -0.441 |
Token | oret |
Token ID | 9997 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Klux | +0.623 |
sleeper | +0.609 |
disasters | +0.550 |
liquids | +0.541 |
senal | +0.534 |
Neg logit contributions | |
ieth | -0.981 |
龍� | -0.904 |
iaries | -0.899 |
iary | -0.837 |
eded | -0.817 |
Token | ical |
Token ID | 605 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
ieth | +0.187 |
龍� | +0.173 |
iaries | +0.166 |
iary | +0.149 |
eded | +0.146 |
Neg logit contributions | |
Klux | -0.246 |
sleeper | -0.240 |
disasters | -0.226 |
liquids | -0.223 |
plane | -0.219 |
Token | perspectives |
Token ID | 22582 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Klux | +0.563 |
sleeper | +0.557 |
disasters | +0.512 |
liquids | +0.503 |
senal | +0.488 |
Neg logit contributions | |
ieth | -0.724 |
龍� | -0.666 |
iaries | -0.658 |
iary | -0.604 |
eded | -0.592 |
Token | and |
Token ID | 290 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ieth | +2.324 |
龍� | +2.123 |
iaries | +2.100 |
iary | +1.925 |
eded | +1.872 |
Neg logit contributions | |
Klux | -2.053 |
sleeper | -2.015 |
disasters | -1.861 |
liquids | -1.840 |
senal | -1.822 |
Token | their |
Token ID | 511 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
Klux | +0.981 |
sleeper | +0.973 |
disasters | +0.874 |
liquids | +0.852 |
senal | +0.820 |
Neg logit contributions | |
ieth | -1.770 |
龍� | -1.645 |
iaries | -1.629 |
iary | -1.516 |
shire | -1.485 |
Token | implications |
Token ID | 10939 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
Klux | +0.252 |
sleeper | +0.247 |
disasters | +0.222 |
liquids | +0.218 |
senal | +0.214 |
Neg logit contributions | |
ieth | -0.426 |
龍� | -0.393 |
iaries | -0.391 |
iary | -0.364 |
shire | -0.356 |
Token | . |
Token ID | 764 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ieth | +4.915 |
龍� | +4.497 |
iaries | +4.454 |
iary | +4.102 |
eded | +4.006 |
Neg logit contributions | |
Klux | -4.041 |
sleeper | -3.966 |
disasters | -3.645 |
liquids | -3.598 |
senal | -3.569 |
Token | School |
Token ID | 3961 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
ieth | +0.194 |
龍� | +0.179 |
iaries | +0.178 |
iary | +0.165 |
eded | +0.161 |
Neg logit contributions | |
Klux | -0.139 |
sleeper | -0.136 |
disasters | -0.124 |
liquids | -0.122 |
senal | -0.121 |
Token | Psychology |
Token ID | 18430 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
ieth | +2.713 |
龍� | +2.462 |
iaries | +2.447 |
iary | +2.292 |
shire | +2.247 |
Neg logit contributions | |
Klux | -1.963 |
sleeper | -1.920 |
senal | -1.735 |
disasters | -1.725 |
liquids | -1.722 |
Token | times |
Token ID | 1661 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
ieth | +0.138 |
龍� | +0.128 |
iaries | +0.128 |
iary | +0.120 |
eded | +0.118 |
Neg logit contributions | |
Klux | -0.063 |
sleeper | -0.061 |
disasters | -0.054 |
senal | -0.053 |
liquids | -0.053 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ieth | +1.073 |
龍� | +0.983 |
iaries | +0.979 |
iary | +0.914 |
shire | +0.895 |
Neg logit contributions | |
Klux | -0.683 |
sleeper | -0.663 |
senal | -0.601 |
disasters | -0.596 |
liquids | -0.591 |
Token | has |
Token ID | 468 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
Klux | +1.145 |
sleeper | +1.122 |
disasters | +1.036 |
liquids | +1.020 |
senal | +0.999 |
Neg logit contributions | |
ieth | -1.337 |
龍� | -1.223 |
iaries | -1.209 |
iary | -1.116 |
shire | -1.074 |
Token | said |
Token ID | 531 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ieth | +0.665 |
龍� | +0.606 |
iaries | +0.604 |
iary | +0.562 |
eded | +0.550 |
Neg logit contributions | |
Klux | -0.483 |
sleeper | -0.470 |
disasters | -0.427 |
senal | -0.426 |
liquids | -0.423 |
Token | he |
Token ID | 339 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
Klux | +1.257 |
sleeper | +1.228 |
disasters | +1.113 |
liquids | +1.091 |
senal | +1.059 |
Neg logit contributions | |
ieth | -2.059 |
龍� | -1.904 |
iaries | -1.889 |
iary | -1.762 |
shire | -1.719 |
Token | � |
Token ID | 447 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
ieth | +2.986 |
龍� | +2.670 |
iaries | +2.664 |
iary | +2.463 |
eded | +2.431 |
Neg logit contributions | |
Klux | -2.751 |
sleeper | -2.690 |
senal | -2.537 |
disasters | -2.466 |
liquids | -2.453 |
Token | � |
Token ID | 247 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Klux | +0.946 |
sleeper | +0.937 |
disasters | +0.869 |
senal | +0.865 |
liquids | +0.856 |
Neg logit contributions | |
ieth | -0.860 |
龍� | -0.776 |
iaries | -0.766 |
iary | -0.699 |
eded | -0.690 |
Token | ll |
Token ID | 297 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
Klux | +1.871 |
sleeper | +1.837 |
disasters | +1.738 |
liquids | +1.730 |
senal | +1.703 |
Neg logit contributions | |
ieth | -0.931 |
龍� | -0.803 |
iaries | -0.789 |
iary | -0.691 |
shire | -0.644 |
Token | hire |
Token ID | 11078 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
ieth | +4.417 |
龍� | +4.055 |
iaries | +4.041 |
iary | +3.792 |
shire | +3.690 |
Neg logit contributions | |
Klux | -2.869 |
sleeper | -2.831 |
senal | -2.599 |
disasters | -2.553 |
liquids | -2.519 |
Token | the |
Token ID | 262 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
ieth | +1.063 |
龍� | +0.982 |
iaries | +0.978 |
iary | +0.919 |
eded | +0.900 |
Neg logit contributions | |
Klux | -0.534 |
sleeper | -0.517 |
disasters | -0.458 |
senal | -0.454 |
liquids | -0.452 |
Token | best |
Token ID | 1266 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
Klux | +0.414 |
sleeper | +0.404 |
disasters | +0.370 |
liquids | +0.365 |
senal | +0.365 |
Neg logit contributions | |
ieth | -0.526 |
龍� | -0.480 |
iaries | -0.477 |
iary | -0.442 |
eded | -0.430 |
Token | odd |
Token ID | 5088 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
ieth | +1.871 |
龍� | +1.692 |
iaries | +1.680 |
iary | +1.544 |
eded | +1.496 |
Neg logit contributions | |
Klux | -1.790 |
sleeper | -1.753 |
disasters | -1.619 |
liquids | -1.602 |
senal | -1.595 |
Token | channels |
Token ID | 9619 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
ieth | +5.240 |
龍� | +4.719 |
iaries | +4.713 |
iary | +4.388 |
shire | +4.334 |
Neg logit contributions | |
Klux | -3.790 |
sleeper | -3.559 |
senal | -3.406 |
disasters | -3.250 |
liquids | -3.240 |
Token | of |
Token ID | 286 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
Klux | +0.472 |
sleeper | +0.460 |
disasters | +0.412 |
liquids | +0.406 |
senal | +0.402 |
Neg logit contributions | |
ieth | -0.835 |
龍� | -0.772 |
iaries | -0.767 |
iary | -0.718 |
eded | -0.701 |
Token | real |
Token ID | 1103 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ieth | +0.603 |
龍� | +0.557 |
iaries | +0.554 |
iary | +0.521 |
eded | +0.510 |
Neg logit contributions | |
Klux | -0.313 |
sleeper | -0.301 |
disasters | -0.268 |
senal | -0.266 |
liquids | -0.265 |
Token | - |
Token ID | 12 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Klux | +1.380 |
sleeper | +1.366 |
disasters | +1.238 |
liquids | +1.205 |
senal | +1.185 |
Neg logit contributions | |
ieth | -2.019 |
龍� | -1.884 |
iaries | -1.852 |
iary | -1.716 |
eded | -1.686 |
Token | time |
Token ID | 2435 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
ieth | +2.109 |
龍� | +1.911 |
iaries | +1.905 |
iary | +1.776 |
shire | +1.731 |
Neg logit contributions | |
Klux | -1.605 |
sleeper | -1.555 |
disasters | -1.423 |
liquids | -1.411 |
senal | -1.407 |
Token | viewing |
Token ID | 11681 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Klux | +0.381 |
sleeper | +0.368 |
disasters | +0.329 |
senal | +0.326 |
liquids | +0.325 |
Neg logit contributions | |
ieth | -0.690 |
龍� | -0.636 |
iaries | -0.633 |
iary | -0.594 |
shire | -0.580 |
Token | you |
Token ID | 345 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Klux | +1.351 |
sleeper | +1.328 |
disasters | +1.226 |
liquids | +1.209 |
senal | +1.182 |
Neg logit contributions | |
ieth | -1.658 |
龍� | -1.521 |
iaries | -1.505 |
iary | -1.393 |
eded | -1.351 |
Token | can |
Token ID | 460 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
ieth | +1.470 |
iaries | +1.328 |
龍� | +1.320 |
iary | +1.214 |
eded | +1.190 |
Neg logit contributions | |
Klux | -1.513 |
sleeper | -1.464 |
senal | -1.384 |
disasters | -1.360 |
liquids | -1.339 |
Token | get |
Token ID | 651 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
ieth | +0.811 |
龍� | +0.742 |
iaries | +0.741 |
iary | +0.691 |
eded | +0.673 |
Neg logit contributions | |
Klux | -0.559 |
sleeper | -0.539 |
senal | -0.492 |
disasters | -0.491 |
liquids | -0.482 |
Token | from |
Token ID | 422 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
Klux | +2.331 |
sleeper | +2.312 |
disasters | +2.102 |
liquids | +2.075 |
plane | +2.014 |
Neg logit contributions | |
ieth | -3.266 |
龍� | -3.028 |
iaries | -2.998 |
iary | -2.776 |
eded | -2.693 |
Token | ie |
Token ID | 494 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
Klux | +1.646 |
sleeper | +1.629 |
disasters | +1.529 |
liquids | +1.509 |
plane | +1.490 |
Neg logit contributions | |
ieth | -0.995 |
龍� | -0.883 |
iaries | -0.861 |
iary | -0.756 |
eded | -0.734 |
Token |
|
Token ID | 198 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
Klux | +2.497 |
sleeper | +2.472 |
disasters | +2.265 |
liquids | +2.265 |
plane | +2.216 |
Neg logit contributions | |
ieth | -2.882 |
iaries | -2.649 |
龍� | -2.611 |
iary | -2.390 |
eded | -2.296 |
Token |
|
Token ID | 198 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
Klux | +0.298 |
senal | +0.295 |
sleeper | +0.293 |
disasters | +0.271 |
liquids | +0.267 |
Neg logit contributions | |
ieth | -0.235 |
龍� | -0.205 |
iaries | -0.204 |
iary | -0.191 |
eded | -0.185 |
Token | Nick |
Token ID | 23609 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Klux | +0.252 |
sleeper | +0.246 |
disasters | +0.227 |
liquids | +0.225 |
plane | +0.223 |
Neg logit contributions | |
ieth | -0.258 |
龍� | -0.232 |
iaries | -0.232 |
iary | -0.211 |
shire | -0.205 |
Token | las |
Token ID | 21921 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
ieth | +1.378 |
龍� | +1.260 |
iaries | +1.247 |
iary | +1.149 |
eded | +1.114 |
Neg logit contributions | |
Klux | -1.189 |
sleeper | -1.160 |
disasters | -1.065 |
liquids | -1.051 |
senal | -1.045 |
Token | Back |
Token ID | 5157 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
Klux | +1.963 |
sleeper | +1.908 |
plane | +1.698 |
disasters | +1.679 |
liquids | +1.678 |
Neg logit contributions | |
ieth | -3.503 |
龍� | -3.357 |
iaries | -3.263 |
shire | -3.028 |
姫 | -2.988 |
Token | strom |
Token ID | 20282 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
Klux | +2.814 |
sleeper | +2.762 |
plane | +2.592 |
disasters | +2.579 |
liquids | +2.523 |
Neg logit contributions | |
ieth | -2.515 |
龍� | -2.339 |
iaries | -2.278 |
iary | -2.051 |
姫 | -1.996 |
Token |
|
Token ID | 198 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ieth | +0.942 |
龍� | +0.852 |
iaries | +0.850 |
iary | +0.774 |
eded | +0.747 |
Neg logit contributions | |
Klux | -0.904 |
sleeper | -0.891 |
disasters | -0.822 |
liquids | -0.815 |
senal | -0.806 |
Token |
|
Token ID | 198 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
Klux | +0.467 |
senal | +0.462 |
sleeper | +0.460 |
disasters | +0.425 |
liquids | +0.419 |
Neg logit contributions | |
ieth | -0.373 |
龍� | -0.327 |
iaries | -0.324 |
iary | -0.303 |
eded | -0.294 |
Token | Ass |
Token ID | 8021 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Klux | +0.355 |
sleeper | +0.348 |
disasters | +0.321 |
liquids | +0.318 |
plane | +0.315 |
Neg logit contributions | |
ieth | -0.364 |
龍� | -0.329 |
iaries | -0.328 |
iary | -0.299 |
shire | -0.290 |
Token | ists |
Token ID | 1023 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ieth | +1.134 |
龍� | +1.034 |
iaries | +0.998 |
iary | +0.885 |
shire | +0.864 |
Neg logit contributions | |
Klux | -1.614 |
sleeper | -1.577 |
disasters | -1.485 |
liquids | -1.468 |
plane | -1.447 |
Token | the |
Token ID | 262 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Klux | +0.880 |
sleeper | +0.857 |
disasters | +0.761 |
liquids | +0.746 |
senal | +0.736 |
Neg logit contributions | |
ieth | -1.780 |
龍� | -1.652 |
iaries | -1.642 |
iary | -1.543 |
eded | -1.507 |
Token | dragon |
Token ID | 10441 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ieth | +0.250 |
龍� | +0.230 |
iaries | +0.229 |
iary | +0.216 |
eded | +0.212 |
Neg logit contributions | |
Klux | -0.124 |
sleeper | -0.117 |
senal | -0.107 |
disasters | -0.104 |
liquids | -0.103 |
Token | to |
Token ID | 284 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Klux | +1.208 |
sleeper | +1.196 |
disasters | +1.084 |
liquids | +1.063 |
senal | +1.047 |
Neg logit contributions | |
ieth | -1.762 |
龍� | -1.627 |
iaries | -1.612 |
iary | -1.493 |
eded | -1.457 |
Token | stir |
Token ID | 11240 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ieth | +1.497 |
iaries | +1.368 |
龍� | +1.357 |
iary | +1.280 |
eded | +1.250 |
Neg logit contributions | |
Klux | -1.062 |
sleeper | -1.004 |
senal | -0.960 |
disasters | -0.916 |
liquids | -0.904 |
Token | and |
Token ID | 290 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Klux | +1.283 |
sleeper | +1.260 |
disasters | +1.167 |
liquids | +1.154 |
senal | +1.142 |
Neg logit contributions | |
ieth | -1.276 |
龍� | -1.155 |
iaries | -1.144 |
iary | -1.048 |
eded | -1.015 |
Token | leave |
Token ID | 2666 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
Klux | +1.031 |
sleeper | +1.003 |
disasters | +0.908 |
liquids | +0.897 |
senal | +0.895 |
Neg logit contributions | |
ieth | -1.554 |
龍� | -1.426 |
iaries | -1.419 |
iary | -1.324 |
eded | -1.290 |
Token | . |
Token ID | 13 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
Klux | +1.745 |
sleeper | +1.712 |
disasters | +1.549 |
liquids | +1.528 |
senal | +1.491 |
Neg logit contributions | |
ieth | -2.699 |
龍� | -2.489 |
iaries | -2.470 |
iary | -2.302 |
eded | -2.243 |
Token | The |
Token ID | 383 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ieth | +0.639 |
龍� | +0.574 |
iaries | +0.569 |
iary | +0.521 |
eded | +0.504 |
Neg logit contributions | |
Klux | -0.680 |
sleeper | -0.666 |
disasters | -0.618 |
liquids | -0.612 |
senal | -0.610 |
Token | young |
Token ID | 1862 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
ieth | +0.202 |
龍� | +0.187 |
iaries | +0.186 |
iary | +0.175 |
shire | +0.171 |
Neg logit contributions | |
Klux | -0.104 |
sleeper | -0.099 |
senal | -0.089 |
disasters | -0.089 |
liquids | -0.088 |
Token | man |
Token ID | 582 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
ieth | +0.549 |
龍� | +0.507 |
iaries | +0.504 |
iary | +0.470 |
eded | +0.457 |
Neg logit contributions | |
Klux | -0.328 |
sleeper | -0.323 |
disasters | -0.289 |
liquids | -0.284 |
senal | -0.277 |
Token | begged |
Token ID | 32946 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Klux | +0.229 |
sleeper | +0.224 |
disasters | +0.206 |
liquids | +0.203 |
senal | +0.202 |
Neg logit contributions | |
ieth | -0.265 |
龍� | -0.241 |
iaries | -0.239 |
iary | -0.221 |
eded | -0.214 |
Token | - |
Token ID | 12 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
ieth | +3.233 |
龍� | +2.921 |
iaries | +2.916 |
iary | +2.703 |
eded | +2.615 |
Neg logit contributions | |
Klux | -2.783 |
sleeper | -2.723 |
disasters | -2.506 |
liquids | -2.483 |
senal | -2.474 |
Token | E |
Token ID | 36 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ieth | +0.636 |
龍� | +0.575 |
iaries | +0.571 |
iary | +0.524 |
eded | +0.508 |
Neg logit contributions | |
Klux | -0.611 |
sleeper | -0.598 |
disasters | -0.552 |
liquids | -0.546 |
senal | -0.543 |
Token | ps |
Token ID | 862 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
Klux | +1.373 |
sleeper | +1.330 |
disasters | +1.228 |
liquids | +1.214 |
senal | +1.202 |
Neg logit contributions | |
ieth | -1.498 |
龍� | -1.375 |
iaries | -1.354 |
iary | -1.240 |
eded | -1.196 |
Token | ch |
Token ID | 354 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
ieth | +0.435 |
龍� | +0.399 |
iaries | +0.394 |
iary | +0.364 |
eded | +0.355 |
Neg logit contributions | |
Klux | -0.357 |
sleeper | -0.348 |
disasters | -0.319 |
liquids | -0.315 |
senal | -0.313 |
Token | tein |
Token ID | 22006 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
ieth | +0.912 |
龍� | +0.826 |
iaries | +0.819 |
iary | +0.752 |
eded | +0.729 |
Neg logit contributions | |
Klux | -0.868 |
sleeper | -0.848 |
disasters | -0.784 |
liquids | -0.776 |
senal | -0.771 |
Token | Pt |
Token ID | 34352 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
Klux | +0.406 |
sleeper | +0.395 |
disasters | +0.363 |
liquids | +0.359 |
senal | +0.357 |
Neg logit contributions | |
ieth | -0.479 |
龍� | -0.439 |
iaries | -0.434 |
iary | -0.400 |
eded | -0.390 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ieth | +3.924 |
龍� | +3.476 |
iaries | +3.472 |
iary | +3.157 |
eded | +3.031 |
Neg logit contributions | |
Klux | -4.797 |
sleeper | -4.717 |
disasters | -4.394 |
liquids | -4.359 |
senal | -4.343 |
Token | - |
Token ID | 12 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ieth | +1.679 |
龍� | +1.530 |
iaries | +1.517 |
iary | +1.398 |
eded | +1.360 |
Neg logit contributions | |
Klux | -1.448 |
sleeper | -1.417 |
disasters | -1.301 |
liquids | -1.286 |
senal | -1.280 |
Token | Greg |
Token ID | 25025 |
Feature activation | -8.75e+00 |
Pos logit contributions | |
ieth | +1.173 |
龍� | +1.059 |
iaries | +1.052 |
iary | +0.965 |
eded | +0.935 |
Neg logit contributions | |
Klux | -1.152 |
sleeper | -1.127 |
disasters | -1.042 |
liquids | -1.031 |
senal | -1.027 |
Token | orio |
Token ID | 40974 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ieth | +8.633 |
iaries | +7.720 |
龍� | +7.669 |
iary | +7.218 |
shire | +7.062 |
Neg logit contributions | |
sleeper | -7.414 |
Klux | -7.408 |
disasters | -6.775 |
liquids | -6.761 |
senal | -6.692 |
Token | Antonio |
Token ID | 11366 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Klux | +0.878 |
sleeper | +0.858 |
disasters | +0.791 |
liquids | +0.780 |
senal | +0.776 |
Neg logit contributions | |
ieth | -1.011 |
龍� | -0.925 |
iaries | -0.915 |
iary | -0.841 |
eded | -0.818 |
Token | — |
Token ID | 851 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
ieth | +0.518 |
龍� | +0.467 |
iaries | +0.463 |
iary | +0.425 |
eded | +0.411 |
Neg logit contributions | |
Klux | -0.523 |
sleeper | -0.512 |
disasters | -0.474 |
liquids | -0.469 |
senal | -0.467 |
Token | ACLU |
Token ID | 24381 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Klux | +0.495 |
sleeper | +0.480 |
disasters | +0.438 |
liquids | +0.433 |
senal | +0.427 |
Neg logit contributions | |
ieth | -0.602 |
iaries | -0.547 |
龍� | -0.544 |
iary | -0.504 |
eded | -0.487 |
Token | of |
Token ID | 286 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ieth | +1.460 |
龍� | +1.283 |
iaries | +1.254 |
iary | +1.174 |
shire | +1.127 |
Neg logit contributions | |
Klux | -2.031 |
sleeper | -2.018 |
senal | -1.988 |
disasters | -1.869 |
liquids | -1.829 |
Token | Oregon |
Token ID | 8819 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Klux | +0.110 |
sleeper | +0.108 |
senal | +0.105 |
disasters | +0.099 |
liquids | +0.098 |
Neg logit contributions | |
ieth | -0.096 |
龍� | -0.085 |
iaries | -0.085 |
iary | -0.078 |
shire | -0.076 |
Token | (@ |
Token ID | 4275 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ieth | +1.680 |
龍� | +1.495 |
iaries | +1.418 |
iary | +1.340 |
shire | +1.296 |
Neg logit contributions | |
Klux | -2.591 |
sleeper | -2.585 |
senal | -2.577 |
disasters | -2.405 |
liquids | -2.359 |
Token | AC |
Token ID | 2246 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ieth | +0.172 |
龍� | +0.152 |
iaries | +0.146 |
iary | +0.132 |
eded | +0.128 |
Neg logit contributions | |
sleeper | -0.285 |
Klux | -0.285 |
senal | -0.277 |
disasters | -0.268 |
liquids | -0.265 |
Token | LU |
Token ID | 41596 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ieth | +1.331 |
龍� | +1.230 |
iaries | +1.172 |
iary | +1.086 |
eded | +1.073 |
Neg logit contributions | |
sleeper | -1.551 |
Klux | -1.540 |
senal | -1.505 |
disasters | -1.456 |
liquids | -1.398 |
Token | _ |
Token ID | 62 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Klux | +1.216 |
sleeper | +1.201 |
senal | +1.144 |
disasters | +1.116 |
liquids | +1.098 |
Neg logit contributions | |
ieth | -1.074 |
龍� | -0.968 |
iaries | -0.952 |
iary | -0.880 |
eded | -0.850 |
Token | OR |
Token ID | 1581 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
Klux | +1.418 |
sleeper | +1.403 |
senal | +1.350 |
disasters | +1.317 |
liquids | +1.306 |
Neg logit contributions | |
ieth | -0.755 |
龍� | -0.662 |
iaries | -0.633 |
iary | -0.566 |
eded | -0.538 |
Token | ) |
Token ID | 8 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Klux | +0.519 |
sleeper | +0.512 |
senal | +0.503 |
disasters | +0.476 |
liquids | +0.470 |
Neg logit contributions | |
ieth | -0.399 |
龍� | -0.356 |
iaries | -0.348 |
iary | -0.323 |
shire | -0.312 |
Token | May |
Token ID | 1737 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
ieth | +0.177 |
龍� | +0.151 |
iaries | +0.150 |
iary | +0.138 |
shire | +0.135 |
Neg logit contributions | |
Klux | -0.246 |
sleeper | -0.244 |
senal | -0.241 |
disasters | -0.227 |
liquids | -0.225 |
Token | neglect |
Token ID | 17985 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
ieth | +0.771 |
龍� | +0.711 |
iaries | +0.710 |
iary | +0.668 |
eded | +0.653 |
Neg logit contributions | |
Klux | -0.431 |
sleeper | -0.414 |
senal | -0.372 |
disasters | -0.369 |
liquids | -0.365 |
Token | ing |
Token ID | 278 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
ieth | +2.621 |
龍� | +2.217 |
iaries | +2.174 |
iary | +1.878 |
eded | +1.794 |
Neg logit contributions | |
Klux | -5.654 |
sleeper | -5.550 |
senal | -5.241 |
disasters | -5.228 |
liquids | -5.202 |
Token | the |
Token ID | 262 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ieth | +0.612 |
龍� | +0.565 |
iaries | +0.562 |
iary | +0.529 |
eded | +0.517 |
Neg logit contributions | |
Klux | -0.331 |
sleeper | -0.317 |
senal | -0.283 |
disasters | -0.281 |
liquids | -0.278 |
Token | next |
Token ID | 1306 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
Klux | +0.180 |
sleeper | +0.174 |
disasters | +0.156 |
senal | +0.154 |
liquids | +0.154 |
Neg logit contributions | |
ieth | -0.321 |
龍� | -0.296 |
iaries | -0.295 |
iary | -0.277 |
eded | -0.270 |
Token | generation |
Token ID | 5270 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
Klux | +0.577 |
sleeper | +0.567 |
disasters | +0.512 |
liquids | +0.504 |
senal | +0.492 |
Neg logit contributions | |
ieth | -0.929 |
龍� | -0.862 |
iaries | -0.854 |
iary | -0.796 |
shire | -0.778 |
Token | of |
Token ID | 286 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
ieth | +0.726 |
龍� | +0.655 |
iaries | +0.649 |
iary | +0.594 |
eded | +0.576 |
Neg logit contributions | |
Klux | -0.746 |
sleeper | -0.735 |
disasters | -0.681 |
liquids | -0.673 |
senal | -0.667 |
Token | space |
Token ID | 2272 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
ieth | +0.486 |
龍� | +0.446 |
iaries | +0.445 |
iary | +0.418 |
eded | +0.409 |
Neg logit contributions | |
Klux | -0.264 |
sleeper | -0.251 |
senal | -0.226 |
disasters | -0.223 |
liquids | -0.221 |
Token | exploration |
Token ID | 13936 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
Klux | +2.256 |
sleeper | +2.237 |
disasters | +2.024 |
liquids | +1.969 |
plane | +1.932 |
Neg logit contributions | |
ieth | -4.232 |
龍� | -3.968 |
iaries | -3.928 |
iary | -3.672 |
shire | -3.605 |
Token | that |
Token ID | 326 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Klux | +0.802 |
sleeper | +0.791 |
disasters | +0.734 |
liquids | +0.724 |
senal | +0.713 |
Neg logit contributions | |
ieth | -0.839 |
龍� | -0.763 |
iaries | -0.756 |
iary | -0.693 |
eded | -0.673 |
Token | is |
Token ID | 318 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Klux | +1.441 |
sleeper | +1.414 |
disasters | +1.293 |
liquids | +1.272 |
senal | +1.253 |
Neg logit contributions | |
ieth | -1.916 |
龍� | -1.755 |
iaries | -1.744 |
iary | -1.615 |
eded | -1.569 |
Token | going |
Token ID | 1016 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
ieth | +0.409 |
龍� | +0.376 |
iaries | +0.375 |
iary | +0.352 |
eded | +0.344 |
Neg logit contributions | |
Klux | -0.229 |
sleeper | -0.220 |
senal | -0.198 |
disasters | -0.197 |
liquids | -0.195 |
Token |
|
Token ID | 198 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ieth | +0.979 |
龍� | +0.882 |
iaries | +0.875 |
iary | +0.804 |
eded | +0.777 |
Neg logit contributions | |
Klux | -0.999 |
sleeper | -0.977 |
disasters | -0.905 |
senal | -0.896 |
liquids | -0.896 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ieth | +0.198 |
龍� | +0.176 |
iaries | +0.172 |
iary | +0.162 |
eded | +0.156 |
Neg logit contributions | |
Klux | -0.257 |
senal | -0.256 |
sleeper | -0.253 |
disasters | -0.234 |
liquids | -0.230 |
Token | The |
Token ID | 464 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
ieth | +0.204 |
龍� | +0.185 |
iaries | +0.184 |
iary | +0.169 |
eded | +0.164 |
Neg logit contributions | |
Klux | -0.190 |
sleeper | -0.186 |
disasters | -0.172 |
liquids | -0.170 |
senal | -0.169 |
Token | Joker |
Token ID | 23582 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
Klux | +0.912 |
sleeper | +0.900 |
disasters | +0.826 |
liquids | +0.817 |
senal | +0.807 |
Neg logit contributions | |
ieth | -0.961 |
龍� | -0.877 |
iaries | -0.863 |
iary | -0.790 |
eded | -0.769 |
Token | ( |
Token ID | 357 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ieth | +3.167 |
龍� | +2.869 |
iaries | +2.837 |
iary | +2.652 |
shire | +2.587 |
Neg logit contributions | |
Klux | -2.680 |
sleeper | -2.598 |
senal | -2.393 |
disasters | -2.390 |
liquids | -2.366 |
Token | 060 |
Token ID | 41322 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
ieth | +0.899 |
龍� | +0.805 |
iaries | +0.799 |
iary | +0.728 |
eded | +0.704 |
Neg logit contributions | |
Klux | -1.008 |
sleeper | -0.988 |
disasters | -0.918 |
liquids | -0.909 |
senal | -0.906 |
Token | ) |
Token ID | 8 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
ieth | +2.910 |
龍� | +2.619 |
iaries | +2.609 |
iary | +2.373 |
eded | +2.305 |
Neg logit contributions | |
Klux | -3.070 |
sleeper | -3.020 |
disasters | -2.802 |
liquids | -2.778 |
senal | -2.749 |
Token | provided |
Token ID | 2810 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
ieth | +0.222 |
龍� | +0.202 |
iaries | +0.200 |
iary | +0.185 |
eded | +0.180 |
Neg logit contributions | |
Klux | -0.191 |
sleeper | -0.187 |
disasters | -0.172 |
liquids | -0.170 |
senal | -0.169 |
Token | another |
Token ID | 1194 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ieth | +1.132 |
龍� | +1.045 |
iaries | +1.040 |
iary | +0.976 |
shire | +0.953 |
Neg logit contributions | |
Klux | -0.621 |
sleeper | -0.600 |
disasters | -0.537 |
liquids | -0.529 |
senal | -0.529 |
Token | amazing |
Token ID | 4998 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
Klux | +0.998 |
sleeper | +0.982 |
disasters | +0.877 |
liquids | +0.862 |
senal | +0.849 |
Neg logit contributions | |
ieth | -1.725 |
龍� | -1.595 |
iaries | -1.585 |
iary | -1.479 |
eded | -1.447 |
Token | Master |
Token ID | 5599 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ieth | +0.091 |
龍� | +0.084 |
iaries | +0.084 |
iary | +0.078 |
eded | +0.076 |
Neg logit contributions | |
Klux | -0.055 |
sleeper | -0.054 |
disasters | -0.048 |
liquids | -0.048 |
senal | -0.047 |
Token | rad |
Token ID | 6335 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ieth | +0.845 |
龍� | +0.745 |
iaries | +0.732 |
iary | +0.648 |
eded | +0.621 |
Neg logit contributions | |
Klux | -1.351 |
sleeper | -1.326 |
disasters | -1.248 |
liquids | -1.236 |
senal | -1.230 |
Token | , |
Token ID | 11 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
Klux | +0.170 |
sleeper | +0.166 |
disasters | +0.154 |
liquids | +0.152 |
senal | +0.151 |
Neg logit contributions | |
ieth | -0.187 |
龍� | -0.171 |
iaries | -0.169 |
iary | -0.154 |
eded | -0.152 |
Token | co |
Token ID | 763 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
ieth | +0.936 |
龍� | +0.856 |
iaries | +0.854 |
iary | +0.800 |
shire | +0.779 |
Neg logit contributions | |
Klux | -0.578 |
sleeper | -0.557 |
senal | -0.502 |
disasters | -0.500 |
liquids | -0.495 |
Token | - |
Token ID | 12 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
ieth | +4.833 |
龍� | +4.386 |
iaries | +4.353 |
iary | +4.014 |
eded | +3.895 |
Neg logit contributions | |
Klux | -4.324 |
sleeper | -4.230 |
disasters | -3.896 |
liquids | -3.853 |
senal | -3.837 |
Token | author |
Token ID | 9800 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
ieth | +1.926 |
龍� | +1.729 |
iaries | +1.717 |
iary | +1.573 |
eded | +1.526 |
Neg logit contributions | |
Klux | -1.986 |
sleeper | -1.944 |
disasters | -1.802 |
liquids | -1.784 |
senal | -1.780 |
Token | of |
Token ID | 286 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
ieth | +5.852 |
龍� | +5.253 |
iaries | +5.208 |
iary | +4.752 |
eded | +4.595 |
Neg logit contributions | |
Klux | -6.448 |
sleeper | -6.323 |
disasters | -5.874 |
liquids | -5.816 |
senal | -5.795 |
Token | Millenn |
Token ID | 19007 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
ieth | +0.909 |
龍� | +0.833 |
iaries | +0.827 |
iary | +0.769 |
eded | +0.749 |
Neg logit contributions | |
Klux | -0.657 |
sleeper | -0.643 |
disasters | -0.586 |
liquids | -0.577 |
senal | -0.573 |
Token | ial |
Token ID | 498 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ieth | +2.017 |
iaries | +1.619 |
龍� | +1.612 |
iary | +1.346 |
eded | +1.227 |
Neg logit contributions | |
Klux | -5.574 |
sleeper | -5.511 |
disasters | -5.225 |
liquids | -5.195 |
senal | -5.188 |
Token | Moment |
Token ID | 29278 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
Klux | +0.918 |
sleeper | +0.898 |
disasters | +0.820 |
liquids | +0.808 |
senal | +0.802 |
Neg logit contributions | |
ieth | -1.234 |
龍� | -1.131 |
iaries | -1.121 |
iary | -1.041 |
eded | -1.013 |
Token | um |
Token ID | 388 |
Feature activation | +1.15e-03 |
Pos logit contributions | |
ieth | +3.067 |
龍� | +2.723 |
iaries | +2.695 |
iary | +2.431 |
eded | +2.343 |
Neg logit contributions | |
Klux | -4.027 |
sleeper | -3.956 |
disasters | -3.699 |
liquids | -3.664 |
senal | -3.650 |
Token | : |
Token ID | 25 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
Klux | +0.001 |
sleeper | +0.001 |
disasters | +0.001 |
liquids | +0.001 |
senal | +0.001 |
Neg logit contributions | |
ieth | -0.001 |
龍� | -0.001 |
iaries | -0.001 |
iary | -0.001 |
eded | -0.001 |
Token | lingu |
Token ID | 20280 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
ieth | +0.558 |
龍� | +0.509 |
iaries | +0.505 |
iary | +0.468 |
eded | +0.455 |
Neg logit contributions | |
Klux | -0.441 |
sleeper | -0.431 |
disasters | -0.395 |
liquids | -0.390 |
senal | -0.388 |
Token | ist |
Token ID | 396 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
ieth | +2.566 |
龍� | +2.259 |
iaries | +2.239 |
iary | +2.014 |
eded | +1.932 |
Neg logit contributions | |
Klux | -3.605 |
sleeper | -3.539 |
disasters | -3.314 |
liquids | -3.285 |
senal | -3.278 |
Token | who |
Token ID | 508 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
ieth | +0.333 |
龍� | +0.305 |
iaries | +0.304 |
iary | +0.276 |
eded | +0.269 |
Neg logit contributions | |
Klux | -0.305 |
sleeper | -0.301 |
disasters | -0.276 |
liquids | -0.273 |
senal | -0.269 |
Token | co |
Token ID | 763 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
Klux | +0.660 |
sleeper | +0.644 |
disasters | +0.592 |
liquids | +0.584 |
senal | +0.574 |
Neg logit contributions | |
ieth | -0.839 |
龍� | -0.770 |
iaries | -0.764 |
iary | -0.707 |
shire | -0.686 |
Token | - |
Token ID | 12 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ieth | +4.867 |
龍� | +4.406 |
iaries | +4.374 |
iary | +4.027 |
eded | +3.908 |
Neg logit contributions | |
Klux | -4.517 |
sleeper | -4.422 |
disasters | -4.079 |
liquids | -4.034 |
senal | -4.019 |
Token | authored |
Token ID | 39351 |
Feature activation | -6.55e+00 |
Pos logit contributions | |
ieth | +1.753 |
龍� | +1.566 |
iaries | +1.555 |
iary | +1.418 |
eded | +1.375 |
Neg logit contributions | |
Klux | -1.971 |
sleeper | -1.933 |
disasters | -1.796 |
liquids | -1.777 |
senal | -1.777 |
Token | the |
Token ID | 262 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
ieth | +7.576 |
龍� | +6.962 |
iaries | +6.900 |
iary | +6.466 |
shire | +6.351 |
Neg logit contributions | |
Klux | -4.565 |
sleeper | -4.403 |
disasters | -3.939 |
senal | -3.913 |
liquids | -3.907 |
Token | century |
Token ID | 4289 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
ieth | +0.227 |
龍� | +0.207 |
iaries | +0.205 |
iary | +0.191 |
shire | +0.186 |
Neg logit contributions | |
Klux | -0.169 |
sleeper | -0.164 |
disasters | -0.150 |
senal | -0.148 |
liquids | -0.148 |
Token | - |
Token ID | 12 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
ieth | +3.069 |
龍� | +2.782 |
iaries | +2.765 |
iary | +2.558 |
shire | +2.481 |
Neg logit contributions | |
Klux | -2.649 |
sleeper | -2.588 |
disasters | -2.381 |
liquids | -2.358 |
senal | -2.349 |
Token | en |
Token ID | 268 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ieth | +1.461 |
龍� | +1.264 |
iaries | +1.248 |
iary | +1.096 |
eded | +1.041 |
Neg logit contributions | |
Klux | -2.634 |
sleeper | -2.594 |
disasters | -2.443 |
liquids | -2.422 |
senal | -2.415 |
Token | comp |
Token ID | 5589 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
ieth | +1.096 |
龍� | +0.988 |
iaries | +0.982 |
iary | +0.909 |
eded | +0.886 |
Neg logit contributions | |
Klux | -1.009 |
sleeper | -0.991 |
disasters | -0.914 |
senal | -0.912 |
liquids | -0.906 |
Token | to |
Token ID | 284 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ieth | +0.606 |
龍� | +0.558 |
iaries | +0.555 |
iary | +0.515 |
eded | +0.503 |
Neg logit contributions | |
Klux | -0.394 |
sleeper | -0.384 |
disasters | -0.350 |
liquids | -0.345 |
senal | -0.341 |
Token | play |
Token ID | 711 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
ieth | +1.437 |
龍� | +1.308 |
iaries | +1.304 |
iary | +1.221 |
eded | +1.195 |
Neg logit contributions | |
Klux | -1.039 |
sleeper | -1.005 |
senal | -0.941 |
disasters | -0.915 |
liquids | -0.901 |
Token | down |
Token ID | 866 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
ieth | +2.069 |
龍� | +1.909 |
iaries | +1.894 |
iary | +1.781 |
eded | +1.745 |
Neg logit contributions | |
Klux | -1.202 |
sleeper | -1.155 |
disasters | -1.041 |
senal | -1.039 |
liquids | -1.029 |
Token | reports |
Token ID | 3136 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
ieth | +0.465 |
龍� | +0.429 |
iaries | +0.427 |
iary | +0.400 |
eded | +0.391 |
Neg logit contributions | |
Klux | -0.264 |
sleeper | -0.256 |
disasters | -0.229 |
liquids | -0.226 |
senal | -0.226 |
Token | of |
Token ID | 286 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
ieth | +2.661 |
龍� | +2.445 |
iaries | +2.422 |
iary | +2.265 |
shire | +2.204 |
Neg logit contributions | |
Klux | -1.831 |
sleeper | -1.781 |
disasters | -1.616 |
senal | -1.604 |
liquids | -1.599 |
Token | discord |
Token ID | 36446 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
ieth | +0.856 |
龍� | +0.790 |
iaries | +0.785 |
iary | +0.741 |
eded | +0.722 |
Neg logit contributions | |
Klux | -0.476 |
sleeper | -0.460 |
senal | -0.414 |
disasters | -0.411 |
liquids | -0.407 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ieth | +6.742 |
龍� | +6.013 |
iaries | +5.940 |
iary | +5.624 |
eded | +5.548 |
Neg logit contributions | |
Klux | -5.621 |
sleeper | -5.495 |
senal | -5.106 |
disasters | -5.061 |
liquids | -5.037 |
Token |
|
Token ID | 198 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
ieth | +1.305 |
龍� | +1.178 |
iaries | +1.169 |
iary | +1.073 |
eded | +1.040 |
Neg logit contributions | |
Klux | -1.283 |
sleeper | -1.255 |
disasters | -1.161 |
liquids | -1.149 |
senal | -1.143 |
Token |
|
Token ID | 198 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
ieth | +0.321 |
龍� | +0.283 |
iaries | +0.278 |
iary | +0.261 |
shire | +0.254 |
Neg logit contributions | |
senal | -0.413 |
Klux | -0.412 |
sleeper | -0.407 |
disasters | -0.377 |
liquids | -0.372 |
Token | A |
Token ID | 32 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
ieth | +0.410 |
龍� | +0.371 |
iaries | +0.369 |
iary | +0.339 |
eded | +0.329 |
Neg logit contributions | |
Klux | -0.371 |
sleeper | -0.362 |
disasters | -0.334 |
liquids | -0.330 |
senal | -0.327 |
Token | spokesman |
Token ID | 6523 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
Klux | +0.761 |
sleeper | +0.742 |
disasters | +0.672 |
liquids | +0.663 |
senal | +0.658 |
Neg logit contributions | |
ieth | -1.107 |
龍� | -1.017 |
iaries | -1.010 |
iary | -0.940 |
eded | -0.916 |
Token | in |
Token ID | 287 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Klux | +0.508 |
sleeper | +0.498 |
disasters | +0.459 |
liquids | +0.454 |
senal | +0.451 |
Neg logit contributions | |
ieth | -0.555 |
龍� | -0.504 |
iaries | -0.500 |
iary | -0.460 |
eded | -0.446 |
Token | the |
Token ID | 262 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
ieth | +2.767 |
龍� | +2.555 |
iaries | +2.547 |
iary | +2.392 |
eded | +2.340 |
Neg logit contributions | |
Klux | -1.421 |
sleeper | -1.374 |
disasters | -1.221 |
senal | -1.204 |
liquids | -1.200 |
Token | press |
Token ID | 1803 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
ieth | +0.224 |
龍� | +0.209 |
iaries | +0.208 |
iary | +0.197 |
eded | +0.193 |
Neg logit contributions | |
Klux | -0.077 |
sleeper | -0.074 |
disasters | -0.063 |
liquids | -0.062 |
senal | -0.061 |
Token | box |
Token ID | 3091 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
Klux | +0.357 |
sleeper | +0.352 |
disasters | +0.299 |
liquids | +0.291 |
plane | +0.276 |
Neg logit contributions | |
ieth | -1.112 |
龍� | -1.049 |
iaries | -1.033 |
iary | -0.978 |
shire | -0.965 |
Token | . |
Token ID | 13 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
Klux | +2.735 |
sleeper | +2.717 |
disasters | +2.505 |
liquids | +2.483 |
plane | +2.431 |
Neg logit contributions | |
ieth | -2.768 |
龍� | -2.544 |
iaries | -2.484 |
iary | -2.263 |
eded | -2.208 |
Token | Nin |
Token ID | 10516 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
ieth | +0.495 |
龍� | +0.446 |
iaries | +0.442 |
iary | +0.406 |
shire | +0.393 |
Neg logit contributions | |
Klux | -0.506 |
sleeper | -0.496 |
disasters | -0.459 |
senal | -0.456 |
liquids | -0.455 |
Token | ers |
Token ID | 364 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
ieth | +4.178 |
iaries | +3.587 |
龍� | +3.577 |
iary | +3.170 |
eded | +2.996 |
Neg logit contributions | |
Klux | -7.128 |
sleeper | -7.030 |
senal | -6.591 |
disasters | -6.585 |
liquids | -6.535 |
Token | - |
Token ID | 12 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
ieth | +0.529 |
龍� | +0.486 |
iaries | +0.483 |
iary | +0.452 |
eded | +0.441 |
Neg logit contributions | |
Klux | -0.339 |
sleeper | -0.329 |
disasters | -0.297 |
senal | -0.294 |
liquids | -0.294 |
Token | S |
Token ID | 50 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ieth | +0.827 |
龍� | +0.746 |
iaries | +0.740 |
iary | +0.677 |
eded | +0.654 |
Neg logit contributions | |
Klux | -0.847 |
sleeper | -0.829 |
disasters | -0.768 |
liquids | -0.760 |
senal | -0.756 |
Token | eah |
Token ID | 4617 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
ieth | +1.136 |
龍� | +0.995 |
iaries | +0.985 |
iary | +0.881 |
eded | +0.845 |
Neg logit contributions | |
Klux | -1.717 |
sleeper | -1.690 |
disasters | -1.583 |
liquids | -1.570 |
senal | -1.569 |
Token | awks |
Token ID | 11890 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Klux | +0.043 |
sleeper | +0.042 |
senal | +0.040 |
disasters | +0.040 |
liquids | +0.039 |
Neg logit contributions | |
ieth | -0.035 |
iaries | -0.031 |
龍� | -0.030 |
iary | -0.028 |
eded | -0.027 |
Token | esp |
Token ID | 9774 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Klux | +1.819 |
sleeper | +1.767 |
disasters | +1.653 |
liquids | +1.638 |
plane | +1.625 |
Neg logit contributions | |
ieth | -1.603 |
龍� | -1.453 |
iaries | -1.435 |
iary | -1.306 |
shire | -1.267 |
Token | ère |
Token ID | 35979 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
ieth | +1.255 |
龍� | +1.121 |
iaries | +1.103 |
iary | +0.995 |
shire | +0.957 |
Neg logit contributions | |
Klux | -1.655 |
sleeper | -1.625 |
disasters | -1.519 |
liquids | -1.508 |
senal | -1.492 |
Token | que |
Token ID | 8358 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Klux | +2.376 |
sleeper | +2.335 |
disasters | +2.162 |
liquids | +2.118 |
senal | +2.070 |
Neg logit contributions | |
ieth | -3.048 |
龍� | -2.826 |
iaries | -2.776 |
iary | -2.573 |
eded | -2.462 |
Token | v |
Token ID | 410 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
Klux | +1.520 |
sleeper | +1.489 |
disasters | +1.367 |
liquids | +1.347 |
senal | +1.321 |
Neg logit contributions | |
ieth | -2.078 |
龍� | -1.926 |
iaries | -1.900 |
iary | -1.761 |
shire | -1.696 |
Token | ous |
Token ID | 516 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ieth | +0.693 |
龍� | +0.626 |
iaries | +0.612 |
iary | +0.552 |
shire | +0.534 |
Neg logit contributions | |
Klux | -0.865 |
sleeper | -0.845 |
disasters | -0.791 |
liquids | -0.784 |
plane | -0.770 |
Token | comp |
Token ID | 552 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
Klux | +0.886 |
sleeper | +0.871 |
disasters | +0.799 |
liquids | +0.790 |
senal | +0.767 |
Neg logit contributions | |
ieth | -1.200 |
龍� | -1.107 |
iaries | -1.095 |
iary | -1.016 |
eded | -0.981 |
Token | rend |
Token ID | 10920 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
ieth | +5.913 |
iaries | +5.238 |
龍� | +5.220 |
iary | +4.784 |
eded | +4.716 |
Neg logit contributions | |
Klux | -6.358 |
sleeper | -6.199 |
senal | -5.807 |
disasters | -5.755 |
liquids | -5.680 |
Token | rez |
Token ID | 21107 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
ieth | +1.738 |
龍� | +1.544 |
iaries | +1.526 |
iary | +1.378 |
eded | +1.325 |
Neg logit contributions | |
Klux | -2.285 |
sleeper | -2.246 |
disasters | -2.101 |
liquids | -2.082 |
senal | -2.067 |
Token | que |
Token ID | 8358 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Klux | +2.514 |
sleeper | +2.494 |
disasters | +2.304 |
liquids | +2.270 |
senal | +2.211 |
Neg logit contributions | |
ieth | -3.167 |
龍� | -2.941 |
iaries | -2.870 |
iary | -2.651 |
姫 | -2.551 |
Token | n |
Token ID | 299 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
Klux | +1.356 |
sleeper | +1.331 |
disasters | +1.223 |
liquids | +1.207 |
senal | +1.183 |
Neg logit contributions | |
ieth | -1.830 |
龍� | -1.693 |
iaries | -1.673 |
iary | -1.550 |
shire | -1.492 |
Token | ous |
Token ID | 516 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Klux | +0.769 |
sleeper | +0.749 |
disasters | +0.704 |
liquids | +0.700 |
plane | +0.684 |
Neg logit contributions | |
ieth | -0.650 |
龍� | -0.600 |
iaries | -0.582 |
iary | -0.526 |
姫 | -0.509 |
Token | Texas |
Token ID | 3936 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
ieth | +5.134 |
iaries | +4.638 |
龍� | +4.613 |
iary | +4.307 |
shire | +4.212 |
Neg logit contributions | |
Klux | -4.210 |
sleeper | -4.125 |
senal | -3.814 |
liquids | -3.788 |
disasters | -3.782 |
Token | Theater |
Token ID | 22207 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ieth | +0.389 |
龍� | +0.357 |
iaries | +0.352 |
iary | +0.325 |
eded | +0.318 |
Neg logit contributions | |
Klux | -0.316 |
sleeper | -0.310 |
disasters | -0.283 |
liquids | -0.279 |
senal | -0.276 |
Token | , |
Token ID | 11 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
ieth | +0.971 |
龍� | +0.873 |
iaries | +0.864 |
iary | +0.785 |
eded | +0.761 |
Neg logit contributions | |
Klux | -1.096 |
sleeper | -1.078 |
disasters | -1.001 |
liquids | -0.990 |
senal | -0.983 |
Token | for |
Token ID | 329 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ieth | +0.793 |
龍� | +0.724 |
iaries | +0.718 |
iary | +0.662 |
eded | +0.644 |
Neg logit contributions | |
Klux | -0.664 |
sleeper | -0.651 |
disasters | -0.596 |
liquids | -0.589 |
senal | -0.584 |
Token | over |
Token ID | 625 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Klux | +0.956 |
sleeper | +0.935 |
disasters | +0.842 |
liquids | +0.827 |
senal | +0.816 |
Neg logit contributions | |
ieth | -1.608 |
龍� | -1.485 |
iaries | -1.473 |
iary | -1.375 |
eded | -1.345 |
Token | 60 |
Token ID | 3126 |
Feature activation | -6.39e+00 |
Pos logit contributions | |
Klux | +1.021 |
sleeper | +0.996 |
disasters | +0.909 |
liquids | +0.898 |
senal | +0.896 |
Neg logit contributions | |
ieth | -1.373 |
龍� | -1.254 |
iaries | -1.246 |
iary | -1.158 |
eded | -1.127 |
Token | years |
Token ID | 812 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
ieth | +5.715 |
iaries | +5.095 |
龍� | +5.055 |
iary | +4.646 |
shire | +4.516 |
Neg logit contributions | |
Klux | -6.226 |
sleeper | -6.028 |
senal | -5.658 |
liquids | -5.615 |
disasters | -5.584 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ieth | +3.292 |
龍� | +2.931 |
iaries | +2.904 |
iary | +2.644 |
shire | +2.549 |
Neg logit contributions | |
Klux | -3.994 |
sleeper | -3.911 |
disasters | -3.649 |
liquids | -3.621 |
senal | -3.614 |
Token |
|
Token ID | 198 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
ieth | +1.434 |
龍� | +1.294 |
iaries | +1.287 |
iary | +1.179 |
eded | +1.143 |
Neg logit contributions | |
Klux | -1.421 |
sleeper | -1.391 |
disasters | -1.288 |
liquids | -1.273 |
senal | -1.258 |
Token |
|
Token ID | 198 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
ieth | +0.267 |
龍� | +0.235 |
iaries | +0.231 |
iary | +0.217 |
shire | +0.210 |
Neg logit contributions | |
senal | -0.342 |
Klux | -0.342 |
sleeper | -0.337 |
disasters | -0.311 |
liquids | -0.308 |
Token | They |
Token ID | 2990 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
ieth | +0.261 |
龍� | +0.236 |
iaries | +0.234 |
iary | +0.215 |
eded | +0.208 |
Neg logit contributions | |
Klux | -0.251 |
sleeper | -0.245 |
disasters | -0.226 |
liquids | -0.224 |
senal | -0.220 |