Token | ence |
Token ID | 594 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
disag | +0.737 |
Sah | +0.692 |
Saharan | +0.690 |
pleas | +0.680 |
ucket | +0.675 |
Neg logit contributions | |
isphere | -0.409 |
orth | -0.402 |
л | -0.389 |
arthed | -0.370 |
cliffe | -0.368 |
Token | , |
Token ID | 11 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
disag | +4.469 |
Sah | +4.134 |
Saharan | +4.113 |
pleas | +4.048 |
ucket | +4.008 |
Neg logit contributions | |
isphere | -3.931 |
orth | -3.821 |
л | -3.726 |
arthed | -3.638 |
cliffe | -3.565 |
Token | 8 |
Token ID | 807 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
disag | +2.848 |
Sah | +2.694 |
Saharan | +2.633 |
pleas | +2.612 |
uffy | +2.500 |
Neg logit contributions | |
isphere | -2.952 |
orth | -2.823 |
arthed | -2.721 |
л | -2.703 |
enza | -2.646 |
Token | , |
Token ID | 11 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
disag | +2.487 |
Sah | +2.309 |
Saharan | +2.288 |
pleas | +2.264 |
ucket | +2.238 |
Neg logit contributions | |
isphere | -2.018 |
orth | -1.988 |
л | -1.924 |
arthed | -1.861 |
cliffe | -1.840 |
Token | 333 |
Token ID | 23460 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
disag | +2.001 |
Sah | +1.864 |
pleas | +1.828 |
Saharan | +1.822 |
uffy | +1.765 |
Neg logit contributions | |
isphere | -1.777 |
orth | -1.720 |
л | -1.649 |
arthed | -1.625 |
cliffe | -1.604 |
Token | - |
Token ID | 532 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
orth | +2.181 |
isphere | +2.150 |
л | +2.097 |
cliffe | +1.922 |
arthed | +1.912 |
Neg logit contributions | |
disag | -5.233 |
Saharan | -4.829 |
Sah | -4.828 |
ucket | -4.793 |
pleas | -4.778 |
Token | 354 |
Token ID | 46752 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
л | +9.257 |
orth | +8.767 |
irc | +8.186 |
Ost | +8.141 |
herer | +8.118 |
Neg logit contributions | |
disag | -20.019 |
Saharan | -18.889 |
ucket | -18.328 |
uffy | -18.248 |
Sah | -17.738 |
Token | . |
Token ID | 764 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
isphere | +0.179 |
orth | +0.176 |
л | +0.170 |
arthed | +0.165 |
enza | +0.163 |
Neg logit contributions | |
disag | -0.227 |
Sah | -0.212 |
Saharan | -0.210 |
pleas | -0.208 |
ucket | -0.205 |
Token |
|
Token ID | 198 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
disag | +0.612 |
Sah | +0.579 |
Saharan | +0.574 |
pleas | +0.569 |
ucket | +0.556 |
Neg logit contributions | |
isphere | -0.440 |
orth | -0.425 |
л | -0.411 |
arthed | -0.399 |
enza | -0.393 |
Token |
|
Token ID | 198 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
disag | +1.630 |
Sah | +1.563 |
Saharan | +1.547 |
pleas | +1.533 |
uffy | +1.478 |
Neg logit contributions | |
isphere | -1.335 |
orth | -1.265 |
л | -1.229 |
arthed | -1.212 |
enza | -1.191 |
Token | Google |
Token ID | 11708 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
Sah | +4.119 |
Saharan | +3.855 |
disag | +3.692 |
pleas | +3.523 |
ucket | +3.437 |
Neg logit contributions | |
isphere | -5.659 |
liner | -5.392 |
arthed | -5.299 |
orth | -5.271 |
enza | -5.203 |
Token | Drawing |
Token ID | 40027 |
Feature activation | +5.92e-03 |
Pos logit contributions | |
isphere | +3.258 |
orth | +3.257 |
л | +3.105 |
arthed | +2.950 |
cliffe | +2.940 |
Neg logit contributions | |
disag | -5.893 |
Sah | -5.520 |
Saharan | -5.478 |
ucket | -5.395 |
pleas | -5.372 |
Token | . |
Token ID | 13 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
isphere | +0.046 |
orth | +0.045 |
л | +0.043 |
arthed | +0.042 |
enza | +0.042 |
Neg logit contributions | |
disag | -0.056 |
Sah | -0.052 |
Saharan | -0.052 |
pleas | -0.051 |
ucket | -0.050 |
Token | Solid |
Token ID | 46933 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
isphere | +2.178 |
orth | +2.171 |
л | +2.101 |
arthed | +2.006 |
cliffe | +1.987 |
Neg logit contributions | |
disag | -3.012 |
Sah | -2.768 |
Saharan | -2.747 |
pleas | -2.734 |
ucket | -2.704 |
Token | Br |
Token ID | 9414 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
orth | +2.942 |
isphere | +2.869 |
л | +2.844 |
cliffe | +2.675 |
arthed | +2.651 |
Neg logit contributions | |
disag | -4.847 |
pleas | -4.343 |
ucket | -4.340 |
Sah | -4.324 |
Saharan | -4.301 |
Token | ush |
Token ID | 1530 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
disag | +3.953 |
Saharan | +3.919 |
Sah | +3.867 |
uffy | +3.784 |
ucket | +3.765 |
Neg logit contributions | |
isphere | -6.860 |
л | -6.577 |
orth | -6.485 |
arthed | -6.407 |
liner | -6.373 |
Token | ( |
Token ID | 357 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
orth | +3.112 |
isphere | +3.080 |
л | +3.045 |
cliffe | +2.893 |
arthed | +2.885 |
Neg logit contributions | |
disag | -3.359 |
Sah | -3.037 |
Saharan | -3.017 |
pleas | -3.002 |
ucket | -2.964 |
Token | [ |
Token ID | 685 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
orth | +5.684 |
irc | +5.157 |
л | +5.147 |
isphere | +4.929 |
cliffe | +4.262 |
Neg logit contributions | |
disag | -18.840 |
Saharan | -17.911 |
pleas | -17.783 |
Sah | -17.764 |
ucket | -17.365 |
Token | System |
Token ID | 11964 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
orth | +2.567 |
isphere | +2.468 |
л | +2.431 |
cliffe | +2.160 |
arthed | +2.155 |
Neg logit contributions | |
disag | -8.014 |
pleas | -7.387 |
ucket | -7.375 |
Saharan | -7.337 |
Sah | -7.307 |
Token | . |
Token ID | 13 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
disag | +0.261 |
Sah | +0.246 |
Saharan | +0.243 |
pleas | +0.241 |
ucket | +0.236 |
Neg logit contributions | |
isphere | -0.220 |
orth | -0.214 |
л | -0.207 |
arthed | -0.202 |
enza | -0.200 |
Token | Draw |
Token ID | 25302 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
isphere | +0.283 |
orth | +0.276 |
л | +0.266 |
arthed | +0.259 |
enza | +0.257 |
Neg logit contributions | |
disag | -0.368 |
Sah | -0.349 |
Saharan | -0.345 |
pleas | -0.339 |
ucket | -0.333 |
Token | ing |
Token ID | 278 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
orth | +2.099 |
isphere | +2.077 |
л | +1.995 |
cliffe | +1.888 |
arthed | +1.880 |
Neg logit contributions | |
disag | -3.741 |
Sah | -3.455 |
Saharan | -3.429 |
pleas | -3.412 |
ucket | -3.377 |
Token | From |
Token ID | 4863 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
orth | +4.623 |
л | +4.518 |
isphere | +3.955 |
irc | +3.882 |
arthed | +3.747 |
Neg logit contributions | |
disag | -13.318 |
ucket | -11.965 |
srf | -11.846 |
uffy | -11.716 |
uncons | -11.640 |
Token | Ar |
Token ID | 3163 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
orth | +3.819 |
л | +3.481 |
isphere | +3.255 |
irc | +3.193 |
cliffe | +3.113 |
Neg logit contributions | |
disag | -12.723 |
ucket | -11.536 |
pleas | -11.398 |
uffy | -11.309 |
uncons | -11.137 |
Token | gb |
Token ID | 22296 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
isphere | +1.876 |
orth | +1.854 |
л | +1.788 |
cliffe | +1.723 |
arthed | +1.714 |
Neg logit contributions | |
disag | -2.240 |
Sah | -2.064 |
pleas | -2.026 |
Saharan | -2.024 |
ucket | -1.994 |
Token | ($ |
Token ID | 16763 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
orth | +4.161 |
л | +4.029 |
isphere | +3.893 |
cliffe | +3.724 |
enza | +3.630 |
Neg logit contributions | |
disag | -7.788 |
Sah | -7.056 |
pleas | -6.970 |
Saharan | -6.947 |
ucket | -6.917 |
Token | FC |
Token ID | 4851 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
orth | +3.407 |
isphere | +3.405 |
л | +3.296 |
arthed | +3.192 |
cliffe | +3.171 |
Neg logit contributions | |
disag | -2.831 |
Sah | -2.545 |
pleas | -2.509 |
Saharan | -2.508 |
ucket | -2.455 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
isphere | +3.666 |
orth | +3.640 |
л | +3.616 |
arthed | +3.382 |
irc | +3.352 |
Neg logit contributions | |
disag | -4.962 |
Sah | -4.509 |
pleas | -4.440 |
Saharan | -4.438 |
ucket | -4.355 |
Token | [ |
Token ID | 58 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
orth | +4.693 |
irc | +4.310 |
л | +4.256 |
isphere | +3.720 |
herer | +3.294 |
Neg logit contributions | |
disag | -20.362 |
srf | -19.468 |
Sah | -18.603 |
uncons | -18.588 |
Saharan | -18.561 |
Token | 0 |
Token ID | 15 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
orth | +3.870 |
isphere | +3.747 |
л | +3.671 |
arthed | +3.510 |
cliffe | +3.435 |
Neg logit contributions | |
disag | -6.340 |
Sah | -5.833 |
pleas | -5.730 |
Saharan | -5.686 |
uncons | -5.539 |
Token | ], |
Token ID | 4357 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
isphere | +1.237 |
orth | +1.227 |
л | +1.189 |
arthed | +1.141 |
cliffe | +1.130 |
Neg logit contributions | |
disag | -1.656 |
Sah | -1.535 |
Saharan | -1.519 |
pleas | -1.506 |
ucket | -1.489 |
Token | $ |
Token ID | 3 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
orth | +6.603 |
л | +6.345 |
isphere | +6.169 |
cliffe | +5.980 |
irc | +5.980 |
Neg logit contributions | |
disag | -9.401 |
pleas | -8.372 |
ucket | -8.330 |
Sah | -8.196 |
Saharan | -8.102 |
Token | FC |
Token ID | 4851 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
orth | +4.008 |
isphere | +3.997 |
л | +3.896 |
arthed | +3.747 |
cliffe | +3.741 |
Neg logit contributions | |
disag | -3.228 |
Sah | -2.885 |
Saharan | -2.842 |
pleas | -2.836 |
ucket | -2.799 |
Token | but |
Token ID | 475 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
isphere | +1.586 |
orth | +1.572 |
л | +1.516 |
arthed | +1.449 |
cliffe | +1.439 |
Neg logit contributions | |
disag | -2.396 |
Sah | -2.239 |
Saharan | -2.222 |
pleas | -2.194 |
ucket | -2.174 |
Token | doctors |
Token ID | 7519 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
isphere | +2.676 |
orth | +2.676 |
л | +2.608 |
cliffe | +2.496 |
arthed | +2.479 |
Neg logit contributions | |
disag | -3.242 |
Sah | -3.026 |
Saharan | -3.019 |
ucket | -2.930 |
pleas | -2.859 |
Token | said |
Token ID | 531 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
isphere | +1.169 |
orth | +1.155 |
л | +1.117 |
arthed | +1.066 |
cliffe | +1.054 |
Neg logit contributions | |
disag | -1.817 |
Sah | -1.697 |
Saharan | -1.689 |
pleas | -1.662 |
ucket | -1.650 |
Token | she |
Token ID | 673 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
disag | +0.355 |
Sah | +0.322 |
Saharan | +0.318 |
pleas | +0.317 |
ucket | +0.308 |
Neg logit contributions | |
isphere | -0.472 |
orth | -0.467 |
л | -0.454 |
arthed | -0.444 |
enza | -0.439 |
Token | risked |
Token ID | 42179 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
disag | +5.021 |
pleas | +4.705 |
Sah | +4.624 |
Saharan | +4.381 |
uffy | +4.283 |
Neg logit contributions | |
isphere | -5.722 |
л | -5.612 |
orth | -5.574 |
enza | -5.352 |
arthed | -5.347 |
Token | severe |
Token ID | 6049 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
disag | +0.273 |
Sah | +0.248 |
Saharan | +0.245 |
pleas | +0.244 |
ucket | +0.236 |
Neg logit contributions | |
isphere | -0.322 |
orth | -0.319 |
л | -0.312 |
arthed | -0.303 |
enza | -0.299 |
Token | infection |
Token ID | 10280 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
л | +3.237 |
orth | +3.023 |
liner | +2.997 |
ional | +2.769 |
enza | +2.749 |
Neg logit contributions | |
disag | -20.186 |
Sah | -19.964 |
ucket | -19.563 |
Saharan | -19.539 |
maxwell | -19.307 |
Token | and |
Token ID | 290 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
isphere | +0.832 |
orth | +0.821 |
л | +0.795 |
arthed | +0.767 |
enza | +0.758 |
Neg logit contributions | |
disag | -1.023 |
Sah | -0.949 |
Saharan | -0.941 |
pleas | -0.934 |
ucket | -0.919 |
Token | scar |
Token ID | 10153 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
disag | +0.146 |
Sah | +0.132 |
Saharan | +0.130 |
pleas | +0.129 |
ucket | +0.125 |
Neg logit contributions | |
isphere | -0.218 |
orth | -0.216 |
л | -0.210 |
arthed | -0.206 |
enza | -0.203 |
Token | ring |
Token ID | 1806 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
disag | +0.253 |
Sah | +0.231 |
Saharan | +0.229 |
pleas | +0.226 |
ucket | +0.220 |
Neg logit contributions | |
isphere | -0.315 |
orth | -0.312 |
л | -0.303 |
arthed | -0.296 |
enza | -0.293 |
Token | if |
Token ID | 611 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
disag | +0.983 |
Sah | +0.906 |
pleas | +0.899 |
Saharan | +0.893 |
ucket | +0.882 |
Neg logit contributions | |
isphere | -0.971 |
orth | -0.951 |
л | -0.924 |
arthed | -0.900 |
enza | -0.893 |
Token | 6 |
Token ID | 21 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
isphere | +3.419 |
orth | +3.413 |
л | +3.233 |
cliffe | +3.107 |
enza | +3.073 |
Neg logit contributions | |
disag | -5.911 |
Sah | -5.527 |
Saharan | -5.475 |
pleas | -5.361 |
ucket | -5.357 |
Token | { |
Token ID | 1391 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
isphere | +6.310 |
orth | +6.199 |
л | +6.077 |
irc | +5.875 |
cliffe | +5.832 |
Neg logit contributions | |
disag | -10.435 |
ucket | -9.639 |
Sah | -9.419 |
uffy | -9.386 |
Saharan | -9.385 |
Token | ( |
Token ID | 7 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
disag | +1.056 |
Sah | +1.013 |
Saharan | +0.997 |
pleas | +0.981 |
ucket | +0.956 |
Neg logit contributions | |
isphere | -1.016 |
orth | -0.978 |
л | -0.950 |
arthed | -0.936 |
enza | -0.927 |
Token | 6 |
Token ID | 21 |
Feature activation | +2.08e-03 |
Pos logit contributions | |
isphere | +3.137 |
orth | +3.135 |
л | +3.054 |
arthed | +2.921 |
cliffe | +2.903 |
Neg logit contributions | |
disag | -3.329 |
Sah | -3.033 |
Saharan | -3.026 |
pleas | -2.987 |
ucket | -2.953 |
Token | s |
Token ID | 82 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
isphere | +0.015 |
orth | +0.015 |
л | +0.015 |
arthed | +0.014 |
cliffe | +0.014 |
Neg logit contributions | |
disag | -0.020 |
Sah | -0.019 |
Saharan | -0.019 |
pleas | -0.019 |
ucket | -0.018 |
Token | )} |
Token ID | 38165 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
disag | +0.924 |
Sah | +0.867 |
pleas | +0.857 |
Saharan | +0.854 |
ucket | +0.834 |
Neg logit contributions | |
isphere | -0.928 |
orth | -0.904 |
л | -0.879 |
arthed | -0.853 |
enza | -0.849 |
Token | 38 |
Token ID | 4353 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
isphere | +5.527 |
л | +5.377 |
orth | +5.354 |
cliffe | +5.185 |
irc | +4.998 |
Neg logit contributions | |
disag | -18.255 |
Saharan | -16.985 |
uffy | -16.901 |
Sah | -16.889 |
pleas | -16.837 |
Token | . |
Token ID | 13 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
orth | +3.580 |
л | +3.492 |
isphere | +3.471 |
cliffe | +3.251 |
irc | +3.213 |
Neg logit contributions | |
disag | -6.432 |
ucket | -5.782 |
Saharan | -5.780 |
Sah | -5.771 |
uffy | -5.716 |
Token | N |
Token ID | 399 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
orth | +4.874 |
isphere | +4.866 |
л | +4.721 |
cliffe | +4.537 |
enza | +4.463 |
Neg logit contributions | |
disag | -6.725 |
Saharan | -6.358 |
Sah | -6.288 |
uffy | -6.204 |
ucket | -6.152 |
Token | d |
Token ID | 67 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
orth | +4.240 |
isphere | +4.236 |
л | +4.059 |
cliffe | +3.919 |
bey | +3.896 |
Neg logit contributions | |
disag | -5.109 |
Sah | -4.663 |
Saharan | -4.644 |
pleas | -4.561 |
ucket | -4.479 |
Token | 4 |
Token ID | 19 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
isphere | +3.787 |
orth | +3.748 |
л | +3.609 |
cliffe | +3.449 |
enza | +3.421 |
Neg logit contributions | |
disag | -5.242 |
Sah | -4.839 |
Saharan | -4.785 |
ucket | -4.707 |
pleas | -4.705 |
Token | states |
Token ID | 2585 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
isphere | +2.419 |
orth | +2.390 |
л | +2.311 |
arthed | +2.210 |
cliffe | +2.200 |
Neg logit contributions | |
disag | -3.467 |
Sah | -3.239 |
Saharan | -3.212 |
pleas | -3.167 |
ucket | -3.148 |
Token | , |
Token ID | 11 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
isphere | +0.204 |
orth | +0.202 |
л | +0.197 |
arthed | +0.192 |
enza | +0.189 |
Neg logit contributions | |
disag | -0.195 |
Sah | -0.177 |
Saharan | -0.176 |
pleas | -0.175 |
ucket | -0.171 |
Token | � |
Token ID | 447 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
disag | +0.370 |
Sah | +0.341 |
Saharan | +0.337 |
pleas | +0.337 |
ucket | +0.327 |
Neg logit contributions | |
isphere | -0.333 |
orth | -0.330 |
л | -0.318 |
arthed | -0.313 |
enza | -0.309 |
Token | � |
Token ID | 251 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
disag | +0.441 |
Sah | +0.397 |
Saharan | +0.392 |
pleas | +0.389 |
ucket | +0.381 |
Neg logit contributions | |
isphere | -0.774 |
orth | -0.768 |
л | -0.746 |
arthed | -0.728 |
cliffe | -0.725 |
Token | Ms |
Token ID | 6997 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
isphere | +2.424 |
orth | +2.400 |
л | +2.333 |
arthed | +2.244 |
cliffe | +2.240 |
Neg logit contributions | |
disag | -2.564 |
Sah | -2.369 |
Saharan | -2.346 |
pleas | -2.311 |
ucket | -2.298 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
orth | +2.392 |
isphere | +2.386 |
л | +2.322 |
cliffe | +2.187 |
arthed | +2.184 |
Neg logit contributions | |
disag | -3.551 |
Sah | -3.246 |
Saharan | -3.237 |
pleas | -3.212 |
ucket | -3.176 |
Token | Set |
Token ID | 5345 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
orth | +7.546 |
л | +7.546 |
isphere | +7.509 |
Ost | +7.080 |
enza | +6.951 |
Neg logit contributions | |
disag | -14.496 |
pleas | -13.214 |
Sah | -13.180 |
Saharan | -13.065 |
uffy | -13.006 |
Token | zer |
Token ID | 9107 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
isphere | +1.373 |
orth | +1.357 |
л | +1.231 |
cliffe | +1.117 |
enza | +1.107 |
Neg logit contributions | |
disag | -6.316 |
Sah | -5.969 |
Saharan | -5.910 |
pleas | -5.909 |
ucket | -5.826 |
Token | said |
Token ID | 531 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
disag | +1.223 |
Sah | +1.139 |
Saharan | +1.130 |
pleas | +1.121 |
ucket | +1.106 |
Neg logit contributions | |
isphere | -0.852 |
orth | -0.837 |
л | -0.809 |
arthed | -0.781 |
cliffe | -0.770 |
Token | . |
Token ID | 13 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
disag | +0.970 |
Sah | +0.901 |
Saharan | +0.894 |
pleas | +0.886 |
ucket | +0.874 |
Neg logit contributions | |
isphere | -0.748 |
orth | -0.738 |
л | -0.714 |
arthed | -0.689 |
cliffe | -0.681 |
Token | � |
Token ID | 564 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
disag | +2.184 |
Sah | +2.053 |
Saharan | +2.030 |
pleas | +2.008 |
ucket | +1.973 |
Neg logit contributions | |
isphere | -1.645 |
orth | -1.585 |
л | -1.515 |
arthed | -1.490 |
enza | -1.469 |
Token | ) |
Token ID | 1267 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
orth | +3.138 |
л | +3.092 |
isphere | +3.052 |
cliffe | +2.750 |
arthed | +2.606 |
Neg logit contributions | |
disag | -12.892 |
Sah | -12.059 |
Saharan | -12.038 |
ucket | -11.873 |
pleas | -11.816 |
Token | $ |
Token ID | 720 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
orth | +2.933 |
isphere | +2.903 |
л | +2.840 |
cliffe | +2.694 |
arthed | +2.693 |
Neg logit contributions | |
disag | -3.957 |
Sah | -3.724 |
Saharan | -3.721 |
pleas | -3.569 |
ucket | -3.558 |
Token | s |
Token ID | 82 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
orth | +3.402 |
isphere | +3.400 |
л | +3.251 |
arthed | +3.113 |
cliffe | +3.088 |
Neg logit contributions | |
disag | -4.697 |
Sah | -4.308 |
Saharan | -4.285 |
pleas | -4.259 |
ucket | -4.192 |
Token | z |
Token ID | 89 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
isphere | +2.407 |
orth | +2.399 |
л | +2.200 |
arthed | +2.004 |
cliffe | +1.987 |
Neg logit contributions | |
disag | -9.780 |
Sah | -9.065 |
pleas | -9.051 |
Saharan | -9.018 |
ucket | -8.828 |
Token | 2 |
Token ID | 17 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
isphere | +3.691 |
orth | +3.653 |
л | +3.561 |
arthed | +3.365 |
irc | +3.335 |
Neg logit contributions | |
disag | -4.832 |
Sah | -4.379 |
Saharan | -4.354 |
pleas | -4.319 |
uffy | -4.245 |
Token | = |
Token ID | 796 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
orth | +2.768 |
л | +2.686 |
isphere | +2.650 |
+= | +2.297 |
irc | +2.284 |
Neg logit contributions | |
disag | -12.240 |
Saharan | -11.144 |
Sah | -11.092 |
pleas | -11.089 |
uffy | -11.017 |
Token | [ |
Token ID | 685 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
orth | +5.081 |
л | +4.915 |
isphere | +4.765 |
irc | +4.764 |
liner | +4.444 |
Neg logit contributions | |
disag | -16.057 |
Saharan | -15.612 |
Sah | -15.508 |
pleas | -15.260 |
ucket | -15.022 |
Token | system |
Token ID | 10057 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
orth | +1.728 |
isphere | +1.722 |
л | +1.552 |
cliffe | +1.384 |
arthed | +1.376 |
Neg logit contributions | |
disag | -7.793 |
Sah | -7.343 |
pleas | -7.316 |
Saharan | -7.314 |
ucket | -7.260 |
Token | . |
Token ID | 13 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
disag | +1.622 |
Sah | +1.549 |
Saharan | +1.522 |
pleas | +1.513 |
ucket | +1.469 |
Neg logit contributions | |
isphere | -1.515 |
orth | -1.458 |
л | -1.414 |
arthed | -1.400 |
enza | -1.382 |
Token | windows |
Token ID | 28457 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
orth | +3.033 |
isphere | +3.018 |
л | +2.840 |
cliffe | +2.697 |
arthed | +2.682 |
Neg logit contributions | |
disag | -6.391 |
Sah | -5.961 |
pleas | -5.952 |
Saharan | -5.898 |
ucket | -5.797 |
Token | . |
Token ID | 13 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
isphere | +1.284 |
orth | +1.274 |
л | +1.233 |
arthed | +1.179 |
cliffe | +1.171 |
Neg logit contributions | |
disag | -1.768 |
Sah | -1.639 |
Saharan | -1.627 |
pleas | -1.608 |
ucket | -1.594 |
Token | Se |
Token ID | 1001 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
isphere | +0.572 |
orth | +0.565 |
л | +0.543 |
arthed | +0.519 |
cliffe | +0.513 |
Neg logit contributions | |
disag | -0.965 |
Sah | -0.903 |
Saharan | -0.896 |
pleas | -0.889 |
ucket | -0.878 |
Token | eker |
Token ID | 28233 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
disag | +1.105 |
Sah | +1.036 |
Saharan | +1.033 |
ucket | +1.012 |
pleas | +1.008 |
Neg logit contributions | |
orth | -0.980 |
isphere | -0.980 |
л | -0.959 |
arthed | -0.914 |
cliffe | -0.899 |
Token | wrote |
Token ID | 2630 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
disag | +1.438 |
Sah | +1.348 |
pleas | +1.339 |
Saharan | +1.333 |
ucket | +1.303 |
Neg logit contributions | |
isphere | -0.971 |
orth | -0.959 |
л | -0.918 |
arthed | -0.893 |
enza | -0.879 |
Token | : |
Token ID | 25 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
disag | +3.238 |
Sah | +3.148 |
pleas | +3.123 |
Saharan | +3.112 |
uffy | +2.940 |
Neg logit contributions | |
isphere | -2.931 |
orth | -2.801 |
arthed | -2.722 |
л | -2.694 |
enza | -2.659 |
Token |
|
Token ID | 198 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
orth | +2.495 |
isphere | +2.468 |
л | +2.409 |
cliffe | +2.260 |
arthed | +2.236 |
Neg logit contributions | |
disag | -4.543 |
Sah | -4.163 |
Saharan | -4.155 |
pleas | -4.120 |
ucket | -4.112 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
orth | +4.140 |
л | +3.942 |
isphere | +3.746 |
cliffe | +3.625 |
bey | +3.508 |
Neg logit contributions | |
disag | -10.111 |
ucket | -9.091 |
uffy | -8.989 |
srf | -8.963 |
Saharan | -8.962 |
Token | Cl |
Token ID | 2601 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
orth | +4.907 |
isphere | +4.486 |
л | +4.336 |
cliffe | +4.267 |
irc | +3.847 |
Neg logit contributions | |
disag | -18.248 |
pleas | -16.445 |
uncons | -16.377 |
uffy | -16.361 |
ucket | -16.138 |
Token | arity |
Token ID | 6806 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
isphere | +0.873 |
orth | +0.860 |
л | +0.841 |
arthed | +0.805 |
cliffe | +0.794 |
Neg logit contributions | |
disag | -1.146 |
Sah | -1.069 |
Saharan | -1.062 |
pleas | -1.044 |
ucket | -1.039 |
Token | Gaming |
Token ID | 14426 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
disag | +1.411 |
Sah | +1.275 |
Saharan | +1.254 |
pleas | +1.252 |
ucket | +1.203 |
Neg logit contributions | |
isphere | -2.205 |
orth | -2.194 |
л | -2.156 |
arthed | -2.109 |
enza | -2.076 |
Token | will |
Token ID | 481 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
isphere | +3.751 |
orth | +3.739 |
л | +3.633 |
cliffe | +3.471 |
arthed | +3.430 |
Neg logit contributions | |
disag | -5.081 |
Saharan | -4.730 |
Sah | -4.724 |
ucket | -4.617 |
uffy | -4.571 |
Token | also |
Token ID | 635 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
isphere | +1.712 |
orth | +1.695 |
л | +1.648 |
arthed | +1.595 |
cliffe | +1.580 |
Neg logit contributions | |
disag | -1.706 |
Sah | -1.569 |
Saharan | -1.554 |
pleas | -1.537 |
ucket | -1.514 |
Token | millionaires |
Token ID | 48675 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
disag | +1.597 |
pleas | +1.469 |
Sah | +1.451 |
Saharan | +1.443 |
ucket | +1.422 |
Neg logit contributions | |
isphere | -1.573 |
orth | -1.547 |
л | -1.483 |
arthed | -1.457 |
enza | -1.451 |
Token | , |
Token ID | 11 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
isphere | +1.165 |
orth | +1.155 |
л | +1.121 |
arthed | +1.073 |
cliffe | +1.065 |
Neg logit contributions | |
disag | -1.511 |
Sah | -1.405 |
Saharan | -1.395 |
pleas | -1.376 |
ucket | -1.360 |
Token | � |
Token ID | 447 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
isphere | +3.006 |
orth | +2.997 |
л | +2.924 |
arthed | +2.794 |
cliffe | +2.789 |
Neg logit contributions | |
disag | -3.152 |
Sah | -2.910 |
Saharan | -2.885 |
pleas | -2.830 |
ucket | -2.810 |
Token | � |
Token ID | 251 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
disag | +0.627 |
Sah | +0.574 |
Saharan | +0.568 |
pleas | +0.564 |
ucket | +0.554 |
Neg logit contributions | |
isphere | -0.727 |
orth | -0.721 |
л | -0.699 |
arthed | -0.676 |
cliffe | -0.675 |
Token | Ms |
Token ID | 6997 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
orth | +3.784 |
isphere | +3.764 |
л | +3.666 |
arthed | +3.520 |
cliffe | +3.507 |
Neg logit contributions | |
disag | -3.669 |
Sah | -3.353 |
Saharan | -3.333 |
pleas | -3.265 |
ucket | -3.259 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
orth | +4.870 |
л | +4.704 |
isphere | +4.683 |
cliffe | +4.311 |
irc | +4.259 |
Neg logit contributions | |
disag | -8.213 |
Saharan | -7.409 |
pleas | -7.382 |
Sah | -7.372 |
ucket | -7.153 |
Token | Ole |
Token ID | 30093 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
orth | +7.733 |
л | +7.453 |
Ost | +7.408 |
isphere | +7.104 |
liner | +6.711 |
Neg logit contributions | |
disag | -14.322 |
Saharan | -12.714 |
Sah | -12.604 |
pleas | -12.442 |
uffy | -12.317 |
Token | ch |
Token ID | 354 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
isphere | +0.683 |
orth | +0.667 |
л | +0.640 |
arthed | +0.605 |
enza | +0.593 |
Neg logit contributions | |
disag | -1.569 |
Sah | -1.483 |
Saharan | -1.475 |
pleas | -1.459 |
ucket | -1.449 |
Token | owski |
Token ID | 12079 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
orth | +4.068 |
isphere | +4.041 |
л | +3.868 |
cliffe | +3.729 |
arthed | +3.654 |
Neg logit contributions | |
disag | -7.429 |
Sah | -6.863 |
pleas | -6.813 |
Saharan | -6.756 |
ucket | -6.542 |
Token | said |
Token ID | 531 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
isphere | +0.091 |
orth | +0.089 |
л | +0.086 |
arthed | +0.083 |
cliffe | +0.082 |
Neg logit contributions | |
disag | -0.130 |
Sah | -0.121 |
Saharan | -0.120 |
pleas | -0.119 |
ucket | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
disag | +2.055 |
Sah | +1.896 |
Saharan | +1.884 |
pleas | +1.876 |
ucket | +1.844 |
Neg logit contributions | |
isphere | -1.675 |
orth | -1.645 |
л | -1.586 |
arthed | -1.550 |
cliffe | -1.527 |
Token | x |
Token ID | 2124 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
isphere | +1.144 |
orth | +1.132 |
л | +1.078 |
arthed | +0.995 |
cliffe | +0.991 |
Neg logit contributions | |
disag | -3.252 |
Sah | -3.079 |
Saharan | -3.062 |
pleas | -3.025 |
ucket | -3.010 |
Token | . |
Token ID | 13 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
isphere | +1.194 |
orth | +1.181 |
л | +1.143 |
arthed | +1.098 |
cliffe | +1.088 |
Neg logit contributions | |
disag | -1.594 |
Sah | -1.480 |
Saharan | -1.469 |
pleas | -1.454 |
ucket | -1.437 |
Token | x |
Token ID | 87 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
orth | +2.904 |
isphere | +2.827 |
л | +2.747 |
cliffe | +2.625 |
arthed | +2.556 |
Neg logit contributions | |
disag | -5.464 |
Sah | -4.997 |
Saharan | -4.948 |
pleas | -4.935 |
ucket | -4.900 |
Token | . |
Token ID | 13 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
orth | +3.332 |
isphere | +3.228 |
л | +3.189 |
cliffe | +3.016 |
arthed | +2.963 |
Neg logit contributions | |
disag | -5.556 |
Sah | -5.020 |
Saharan | -5.001 |
ucket | -4.985 |
pleas | -4.949 |
Token | x |
Token ID | 87 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
orth | +4.669 |
isphere | +4.374 |
л | +4.179 |
irc | +4.037 |
cliffe | +4.006 |
Neg logit contributions | |
disag | -9.870 |
Sah | -8.881 |
pleas | -8.876 |
ucket | -8.811 |
uncons | -8.775 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
orth | +6.949 |
irc | +6.389 |
л | +6.099 |
isphere | +6.031 |
ional | +5.809 |
Neg logit contributions | |
disag | -14.888 |
srf | -14.125 |
ucket | -13.312 |
uncons | -13.267 |
pleas | -13.203 |
Token | 112 |
Token ID | 14686 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
orth | +4.737 |
irc | +4.072 |
isphere | +4.044 |
ional | +3.377 |
л | +3.327 |
Neg logit contributions | |
disag | -17.780 |
ucket | -16.746 |
pleas | -16.650 |
uffy | -16.564 |
Sah | -16.459 |
Token | 10 |
Token ID | 838 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
orth | +4.580 |
isphere | +4.495 |
л | +4.427 |
arthed | +4.247 |
cliffe | +4.183 |
Neg logit contributions | |
disag | -6.388 |
Saharan | -5.920 |
Sah | -5.898 |
ucket | -5.838 |
pleas | -5.826 |
Token | 25 |
Token ID | 1495 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
orth | +3.263 |
isphere | +3.232 |
л | +3.181 |
arthed | +3.033 |
cliffe | +3.029 |
Neg logit contributions | |
disag | -3.538 |
Sah | -3.208 |
Saharan | -3.202 |
pleas | -3.162 |
ucket | -3.130 |
Token | 151 |
Token ID | 24309 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
disag | +0.612 |
Sah | +0.563 |
Saharan | +0.555 |
pleas | +0.550 |
ucket | +0.539 |
Neg logit contributions | |
isphere | -0.707 |
orth | -0.694 |
л | -0.676 |
arthed | -0.659 |
cliffe | -0.653 |
Token | x |
Token ID | 2124 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
orth | +1.635 |
isphere | +1.627 |
л | +1.566 |
cliffe | +1.434 |
arthed | +1.405 |
Neg logit contributions | |
disag | -5.187 |
Sah | -4.917 |
Saharan | -4.897 |
ucket | -4.820 |
pleas | -4.810 |
Token | Boston |
Token ID | 6182 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
disag | +0.077 |
Sah | +0.071 |
Saharan | +0.070 |
pleas | +0.070 |
ucket | +0.068 |
Neg logit contributions | |
isphere | -0.078 |
orth | -0.077 |
л | -0.075 |
arthed | -0.073 |
enza | -0.072 |
Token | College |
Token ID | 5535 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
isphere | +0.587 |
orth | +0.573 |
л | +0.558 |
arthed | +0.541 |
enza | +0.528 |
Neg logit contributions | |
disag | -0.855 |
Sah | -0.795 |
Saharan | -0.788 |
pleas | -0.784 |
ucket | -0.775 |
Token | on |
Token ID | 319 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
isphere | +2.249 |
orth | +2.233 |
л | +2.140 |
enza | +2.060 |
cliffe | +2.057 |
Neg logit contributions | |
disag | -2.807 |
Sah | -2.619 |
Saharan | -2.604 |
pleas | -2.576 |
ucket | -2.527 |
Token | January |
Token ID | 3269 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
isphere | +1.355 |
orth | +1.340 |
л | +1.299 |
arthed | +1.251 |
cliffe | +1.244 |
Neg logit contributions | |
disag | -1.569 |
Sah | -1.453 |
Saharan | -1.441 |
pleas | -1.424 |
ucket | -1.407 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
isphere | +0.854 |
orth | +0.844 |
л | +0.820 |
arthed | +0.793 |
enza | +0.785 |
Neg logit contributions | |
disag | -0.890 |
Sah | -0.822 |
Saharan | -0.814 |
pleas | -0.805 |
ucket | -0.792 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
disag | +1.484 |
Sah | +1.366 |
Saharan | +1.351 |
pleas | +1.342 |
ucket | +1.324 |
Neg logit contributions | |
isphere | -1.237 |
orth | -1.207 |
л | -1.182 |
arthed | -1.145 |
enza | -1.126 |
Token | 112 |
Token ID | 14686 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
orth | +5.544 |
isphere | +5.235 |
arthed | +4.601 |
irc | +4.421 |
л | +4.344 |
Neg logit contributions | |
disag | -16.323 |
pleas | -15.183 |
Sah | -15.107 |
Saharan | -15.047 |
ucket | -15.030 |
Token | ] |
Token ID | 60 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
disag | +1.217 |
Sah | +1.130 |
Saharan | +1.121 |
pleas | +1.108 |
ucket | +1.093 |
Neg logit contributions | |
isphere | -0.958 |
orth | -0.948 |
л | -0.918 |
arthed | -0.885 |
cliffe | -0.873 |
Token | earning |
Token ID | 13748 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
isphere | +1.030 |
orth | +1.018 |
л | +0.988 |
arthed | +0.953 |
cliffe | +0.944 |
Neg logit contributions | |
disag | -1.178 |
Sah | -1.089 |
Saharan | -1.079 |
pleas | -1.069 |
ucket | -1.053 |
Token | his |
Token ID | 465 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
disag | +0.674 |
Sah | +0.623 |
pleas | +0.620 |
Saharan | +0.617 |
ucket | +0.606 |
Neg logit contributions | |
isphere | -0.549 |
orth | -0.540 |
л | -0.528 |
arthed | -0.506 |
enza | -0.502 |
Token | fifth |
Token ID | 8150 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
disag | +1.126 |
pleas | +1.036 |
Sah | +1.031 |
Saharan | +1.021 |
ucket | +1.004 |
Neg logit contributions | |
isphere | -0.882 |
orth | -0.863 |
л | -0.841 |
arthed | -0.822 |
enza | -0.801 |
Token | # |
Token ID | 1303 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
disag | +2.467 |
pleas | +2.258 |
Sah | +2.225 |
Saharan | +2.204 |
uncons | +2.133 |
Neg logit contributions | |
isphere | -2.343 |
orth | -2.304 |
arthed | -2.199 |
л | -2.195 |
cliffe | -2.147 |
Token | We |
Token ID | 1135 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
isphere | +3.207 |
orth | +3.189 |
л | +3.151 |
arthed | +2.953 |
enza | +2.948 |
Neg logit contributions | |
disag | -3.419 |
Saharan | -3.090 |
Sah | -3.089 |
pleas | -3.061 |
ucket | -3.036 |
Token | � |
Token ID | 447 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
disag | +1.259 |
Sah | +1.187 |
Saharan | +1.163 |
pleas | +1.157 |
ucket | +1.125 |
Neg logit contributions | |
isphere | -1.097 |
orth | -1.083 |
л | -1.030 |
arthed | -1.016 |
cliffe | -1.010 |
Token | � |
Token ID | 247 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
disag | +2.945 |
Sah | +2.748 |
Saharan | +2.739 |
pleas | +2.703 |
ucket | +2.691 |
Neg logit contributions | |
orth | -3.500 |
isphere | -3.469 |
л | -3.310 |
cliffe | -3.242 |
arthed | -3.198 |
Token | ve |
Token ID | 303 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
disag | +0.110 |
Sah | +0.101 |
Saharan | +0.100 |
pleas | +0.099 |
ucket | +0.097 |
Neg logit contributions | |
isphere | -0.134 |
orth | -0.132 |
л | -0.128 |
arthed | -0.125 |
cliffe | -0.124 |
Token | Had |
Token ID | 25383 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
isphere | +2.648 |
orth | +2.629 |
л | +2.592 |
arthed | +2.504 |
enza | +2.465 |
Neg logit contributions | |
disag | -2.099 |
Saharan | -1.869 |
Sah | -1.868 |
pleas | -1.845 |
ucket | -1.822 |
Token | Enough |
Token ID | 47323 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
л | +4.847 |
orth | +4.752 |
isphere | +4.405 |
arthed | +3.906 |
enza | +3.819 |
Neg logit contributions | |
disag | -17.877 |
pleas | -15.853 |
Saharan | -15.849 |
DAV | -15.815 |
Sah | -15.786 |
Token | protester |
Token ID | 34678 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
disag | +2.757 |
Sah | +2.531 |
pleas | +2.521 |
Saharan | +2.488 |
uffy | +2.397 |
Neg logit contributions | |
isphere | -2.892 |
orth | -2.837 |
arthed | -2.716 |
л | -2.714 |
cliffe | -2.688 |
Token | in |
Token ID | 287 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
isphere | +0.911 |
orth | +0.902 |
л | +0.872 |
arthed | +0.845 |
enza | +0.837 |
Neg logit contributions | |
disag | -1.041 |
Sah | -0.960 |
Saharan | -0.950 |
pleas | -0.948 |
ucket | -0.929 |
Token | Petersburg |
Token ID | 27051 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
disag | +1.073 |
Sah | +0.986 |
pleas | +0.983 |
Saharan | +0.976 |
ucket | +0.958 |
Neg logit contributions | |
isphere | -0.894 |
orth | -0.865 |
л | -0.833 |
arthed | -0.821 |
enza | -0.808 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
isphere | +0.141 |
orth | +0.140 |
л | +0.135 |
arthed | +0.132 |
enza | +0.130 |
Neg logit contributions | |
disag | -0.156 |
Sah | -0.144 |
pleas | -0.143 |
Saharan | -0.142 |
ucket | -0.139 |
Token | Font |
Token ID | 23252 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
isphere | +0.622 |
orth | +0.616 |
л | +0.583 |
arthed | +0.549 |
cliffe | +0.542 |
Neg logit contributions | |
disag | -1.511 |
Sah | -1.418 |
Saharan | -1.409 |
pleas | -1.402 |
ucket | -1.386 |
Token | Name |
Token ID | 5376 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
disag | +1.529 |
Sah | +1.427 |
Saharan | +1.414 |
pleas | +1.386 |
ucket | +1.373 |
Neg logit contributions | |
isphere | -1.523 |
orth | -1.495 |
л | -1.450 |
arthed | -1.414 |
enza | -1.401 |
Token | , |
Token ID | 11 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
orth | +2.256 |
isphere | +2.250 |
л | +2.186 |
arthed | +2.076 |
cliffe | +2.075 |
Neg logit contributions | |
disag | -3.068 |
Sah | -2.830 |
Saharan | -2.809 |
pleas | -2.778 |
ucket | -2.757 |
Token | $ |
Token ID | 3 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
orth | +5.081 |
isphere | +4.993 |
л | +4.887 |
cliffe | +4.672 |
arthed | +4.649 |
Neg logit contributions | |
disag | -5.974 |
pleas | -5.428 |
Sah | -5.401 |
Saharan | -5.377 |
ucket | -5.328 |
Token | FS |
Token ID | 10652 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
orth | +5.433 |
isphere | +5.356 |
л | +5.219 |
arthed | +4.989 |
cliffe | +4.977 |
Neg logit contributions | |
disag | -4.916 |
Sah | -4.363 |
pleas | -4.355 |
Saharan | -4.322 |
ucket | -4.217 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
isphere | +2.089 |
orth | +2.084 |
л | +2.028 |
arthed | +1.916 |
cliffe | +1.898 |
Neg logit contributions | |
disag | -3.004 |
Sah | -2.760 |
Saharan | -2.740 |
pleas | -2.718 |
ucket | -2.695 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
orth | +7.066 |
л | +6.609 |
irc | +6.423 |
isphere | +6.350 |
herer | +5.797 |
Neg logit contributions | |
disag | -14.417 |
Sah | -13.332 |
Saharan | -13.226 |
uffy | -13.079 |
ucket | -12.841 |
Token | System |
Token ID | 11964 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
orth | +2.749 |
isphere | +2.662 |
л | +2.578 |
arthed | +2.328 |
cliffe | +2.326 |
Neg logit contributions | |
disag | -8.396 |
pleas | -7.774 |
Saharan | -7.763 |
Sah | -7.756 |
ucket | -7.705 |
Token | . |
Token ID | 13 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
disag | +1.449 |
Sah | +1.382 |
Saharan | +1.360 |
pleas | +1.350 |
ucket | +1.313 |
Neg logit contributions | |
isphere | -1.335 |
orth | -1.287 |
л | -1.243 |
arthed | -1.228 |
enza | -1.219 |
Token | Draw |
Token ID | 25302 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
isphere | +0.697 |
orth | +0.683 |
л | +0.659 |
arthed | +0.638 |
enza | +0.634 |
Neg logit contributions | |
disag | -0.932 |
Sah | -0.880 |
Saharan | -0.871 |
pleas | -0.858 |
ucket | -0.846 |
Token | ing |
Token ID | 278 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
orth | +2.227 |
isphere | +2.201 |
л | +2.120 |
cliffe | +2.004 |
arthed | +1.992 |
Neg logit contributions | |
disag | -4.049 |
Sah | -3.730 |
Saharan | -3.698 |
pleas | -3.685 |
ucket | -3.644 |
Token | E |
Token ID | 36 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
isphere | +2.631 |
orth | +2.621 |
л | +2.555 |
cliffe | +2.360 |
arthed | +2.355 |
Neg logit contributions | |
disag | -5.273 |
Sah | -4.877 |
Saharan | -4.864 |
pleas | -4.821 |
ucket | -4.817 |
Token | , |
Token ID | 11 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
disag | +2.440 |
Sah | +2.239 |
Saharan | +2.215 |
pleas | +2.200 |
ucket | +2.169 |
Neg logit contributions | |
isphere | -2.045 |
orth | -2.008 |
л | -1.938 |
arthed | -1.881 |
cliffe | -1.865 |
Token | DP |
Token ID | 6322 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
disag | +0.398 |
Sah | +0.359 |
Saharan | +0.355 |
pleas | +0.348 |
ucket | +0.343 |
Neg logit contributions | |
isphere | -0.588 |
orth | -0.582 |
л | -0.569 |
arthed | -0.553 |
cliffe | -0.549 |
Token | 02 |
Token ID | 2999 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
isphere | +1.286 |
orth | +1.278 |
л | +1.250 |
arthed | +1.217 |
cliffe | +1.200 |
Neg logit contributions | |
disag | -1.106 |
Sah | -1.005 |
Saharan | -0.992 |
pleas | -0.982 |
ucket | -0.959 |
Token | _ |
Token ID | 62 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
orth | +1.639 |
isphere | +1.639 |
л | +1.583 |
arthed | +1.486 |
cliffe | +1.480 |
Neg logit contributions | |
disag | -3.163 |
Sah | -2.924 |
Saharan | -2.907 |
pleas | -2.892 |
ucket | -2.870 |
Token | 00 |
Token ID | 405 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
disag | +2.229 |
Sah | +2.049 |
Saharan | +2.025 |
pleas | +1.976 |
ucket | +1.959 |
Neg logit contributions | |
isphere | -2.989 |
orth | -2.931 |
л | -2.855 |
arthed | -2.765 |
cliffe | -2.762 |
Token | 64 |
Token ID | 2414 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
orth | +6.231 |
л | +5.955 |
isphere | +5.662 |
irc | +5.147 |
cliffe | +5.049 |
Neg logit contributions | |
disag | -15.343 |
ucket | -13.899 |
uffy | -13.858 |
pleas | -13.857 |
uncons | -13.688 |
Token | E |
Token ID | 36 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
л | +3.424 |
orth | +3.418 |
isphere | +3.344 |
cliffe | +3.018 |
enza | +3.012 |
Neg logit contributions | |
disag | -8.053 |
ucket | -7.349 |
Saharan | -7.315 |
Sah | -7.289 |
pleas | -7.271 |
Token | , |
Token ID | 11 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
disag | +2.324 |
Sah | +2.139 |
Saharan | +2.117 |
pleas | +2.101 |
ucket | +2.074 |
Neg logit contributions | |
isphere | -1.923 |
orth | -1.890 |
л | -1.825 |
arthed | -1.766 |
cliffe | -1.753 |
Token | DP |
Token ID | 6322 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
disag | +0.688 |
Sah | +0.620 |
Saharan | +0.613 |
pleas | +0.600 |
ucket | +0.592 |
Neg logit contributions | |
isphere | -1.031 |
orth | -1.020 |
л | -0.997 |
arthed | -0.969 |
cliffe | -0.964 |
Token | 02 |
Token ID | 2999 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
isphere | +0.617 |
orth | +0.607 |
л | +0.590 |
arthed | +0.575 |
enza | +0.572 |
Neg logit contributions | |
disag | -0.449 |
Sah | -0.413 |
Saharan | -0.407 |
pleas | -0.401 |
ucket | -0.394 |
Token | land |
Token ID | 1956 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
disag | +3.136 |
pleas | +2.856 |
Sah | +2.833 |
Saharan | +2.777 |
ucket | +2.686 |
Neg logit contributions | |
isphere | -2.959 |
orth | -2.874 |
л | -2.848 |
arthed | -2.790 |
enza | -2.732 |
Token | remain |
Token ID | 3520 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
isphere | +0.332 |
orth | +0.327 |
л | +0.318 |
arthed | +0.308 |
enza | +0.304 |
Neg logit contributions | |
disag | -0.401 |
Sah | -0.371 |
Saharan | -0.366 |
pleas | -0.365 |
ucket | -0.357 |
Token | Kenyan |
Token ID | 47214 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
disag | +2.769 |
Sah | +2.515 |
pleas | +2.493 |
Saharan | +2.480 |
uffy | +2.391 |
Neg logit contributions | |
isphere | -2.881 |
orth | -2.794 |
л | -2.748 |
arthed | -2.675 |
enza | -2.644 |
Token | . |
Token ID | 13 |
Feature activation | +9.46e-02 |
Pos logit contributions | |
disag | +2.714 |
Sah | +2.531 |
pleas | +2.488 |
Saharan | +2.475 |
ucket | +2.399 |
Neg logit contributions | |
isphere | -2.359 |
orth | -2.302 |
л | -2.258 |
enza | -2.204 |
arthed | -2.198 |
Token | In |
Token ID | 554 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
isphere | +0.705 |
orth | +0.691 |
л | +0.667 |
arthed | +0.647 |
enza | +0.638 |
Neg logit contributions | |
disag | -0.920 |
Sah | -0.861 |
Saharan | -0.852 |
pleas | -0.843 |
ucket | -0.828 |
Token | June |
Token ID | 2795 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
isphere | +1.800 |
orth | +1.781 |
л | +1.727 |
arthed | +1.666 |
cliffe | +1.654 |
Neg logit contributions | |
disag | -2.054 |
Sah | -1.900 |
Saharan | -1.883 |
pleas | -1.862 |
ucket | -1.839 |
Token | 1962 |
Token ID | 20033 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
isphere | +7.617 |
orth | +7.474 |
л | +7.334 |
cliffe | +7.305 |
liner | +6.899 |
Neg logit contributions | |
disag | -13.036 |
Sah | -12.494 |
Saharan | -12.418 |
uffy | -12.210 |
ucket | -12.025 |
Token | , |
Token ID | 11 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
disag | +1.291 |
Sah | +1.188 |
Saharan | +1.180 |
pleas | +1.177 |
ucket | +1.151 |
Neg logit contributions | |
isphere | -1.137 |
orth | -1.119 |
л | -1.088 |
arthed | -1.053 |
enza | -1.035 |
Token | Ken |
Token ID | 7148 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
disag | +1.104 |
Sah | +1.007 |
pleas | +1.003 |
Saharan | +0.999 |
ucket | +0.970 |
Neg logit contributions | |
isphere | -1.074 |
orth | -1.061 |
л | -1.032 |
arthed | -1.003 |
enza | -0.990 |
Token | y |
Token ID | 88 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
disag | +2.018 |
Sah | +1.886 |
pleas | +1.882 |
Saharan | +1.861 |
ucket | +1.843 |
Neg logit contributions | |
isphere | -1.895 |
л | -1.782 |
orth | -1.767 |
arthed | -1.718 |
liner | -1.683 |
Token | atta |
Token ID | 25014 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
disag | +1.997 |
Saharan | +1.877 |
Sah | +1.871 |
ucket | +1.860 |
pleas | +1.848 |
Neg logit contributions | |
isphere | -1.435 |
orth | -1.362 |
л | -1.355 |
arthed | -1.287 |
liner | -1.270 |
Token | accepted |
Token ID | 6292 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
isphere | +0.311 |
orth | +0.308 |
л | +0.299 |
arthed | +0.289 |
enza | +0.286 |
Neg logit contributions | |
disag | -0.342 |
Sah | -0.315 |
Saharan | -0.311 |
pleas | -0.310 |
ucket | -0.303 |
Token | its |
Token ID | 663 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
disag | +5.816 |
pleas | +5.406 |
Saharan | +5.206 |
Sah | +5.179 |
ucket | +4.927 |
Neg logit contributions | |
orth | -6.433 |
isphere | -6.389 |
л | -6.167 |
arthed | -6.058 |
bey | -5.827 |
Token | presidency |
Token ID | 12112 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
disag | +3.100 |
pleas | +2.873 |
Sah | +2.824 |
Saharan | +2.791 |
uffy | +2.658 |
Neg logit contributions | |
orth | -3.094 |
isphere | -3.087 |
arthed | -2.997 |
л | -2.975 |
cliffe | -2.860 |
Token | . |
Token ID | 13 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
disag | +3.439 |
pleas | +3.169 |
Sah | +3.135 |
Saharan | +3.087 |
ucket | +2.971 |
Neg logit contributions | |
isphere | -3.153 |
orth | -3.110 |
л | -3.007 |
arthed | -2.999 |
enza | -2.915 |
Token | In |
Token ID | 554 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
isphere | +0.218 |
orth | +0.213 |
л | +0.204 |
arthed | +0.199 |
enza | +0.197 |
Neg logit contributions | |
disag | -0.286 |
Sah | -0.270 |
Saharan | -0.267 |
pleas | -0.263 |
ucket | -0.258 |
Token | January |
Token ID | 3269 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
isphere | +1.132 |
orth | +1.118 |
л | +1.087 |
arthed | +1.052 |
enza | +1.038 |
Neg logit contributions | |
disag | -1.252 |
Sah | -1.155 |
Saharan | -1.145 |
pleas | -1.136 |
ucket | -1.116 |
Token | 1962 |
Token ID | 20033 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
isphere | +7.244 |
л | +6.891 |
orth | +6.829 |
cliffe | +6.663 |
enza | +6.509 |
Neg logit contributions | |
disag | -13.608 |
Sah | -13.013 |
Saharan | -12.849 |
uffy | -12.841 |
ucket | -12.704 |
Token | he |
Token ID | 339 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
disag | +0.409 |
Sah | +0.379 |
Saharan | +0.375 |
pleas | +0.372 |
ucket | +0.367 |
Neg logit contributions | |
isphere | -0.338 |
orth | -0.334 |
л | -0.323 |
arthed | -0.312 |
cliffe | -0.308 |
Token | was |
Token ID | 373 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
disag | +0.374 |
pleas | +0.340 |
Sah | +0.338 |
Saharan | +0.336 |
ucket | +0.326 |
Neg logit contributions | |
isphere | -0.360 |
orth | -0.357 |
л | -0.348 |
arthed | -0.339 |
enza | -0.334 |
Token | elected |
Token ID | 7018 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
isphere | +1.438 |
orth | +1.420 |
л | +1.383 |
arthed | +1.333 |
cliffe | +1.319 |
Neg logit contributions | |
disag | -1.611 |
Sah | -1.483 |
Saharan | -1.472 |
pleas | -1.461 |
ucket | -1.434 |
Token | un |
Token ID | 555 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
isphere | +2.835 |
orth | +2.832 |
л | +2.720 |
cliffe | +2.612 |
arthed | +2.604 |
Neg logit contributions | |
disag | -3.400 |
Sah | -3.176 |
Saharan | -3.138 |
ucket | -3.095 |
pleas | -3.092 |
Token | ing |
Token ID | 278 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
orth | +3.159 |
isphere | +3.049 |
л | +2.963 |
cliffe | +2.812 |
enza | +2.753 |
Neg logit contributions | |
disag | -6.334 |
Sah | -5.746 |
Saharan | -5.713 |
pleas | -5.708 |
ucket | -5.650 |
Token | . |
Token ID | 13 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
isphere | +1.276 |
orth | +1.260 |
л | +1.219 |
arthed | +1.174 |
cliffe | +1.161 |
Neg logit contributions | |
disag | -1.680 |
Sah | -1.562 |
Saharan | -1.549 |
pleas | -1.534 |
ucket | -1.514 |
Token | Rect |
Token ID | 45474 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
orth | +2.935 |
isphere | +2.898 |
л | +2.796 |
arthed | +2.603 |
cliffe | +2.590 |
Neg logit contributions | |
disag | -5.759 |
pleas | -5.290 |
Sah | -5.279 |
Saharan | -5.233 |
ucket | -5.191 |
Token | angle |
Token ID | 9248 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
isphere | +0.347 |
orth | +0.340 |
л | +0.321 |
arthed | +0.299 |
cliffe | +0.293 |
Neg logit contributions | |
disag | -1.035 |
Sah | -0.979 |
Saharan | -0.973 |
pleas | -0.967 |
ucket | -0.958 |
Token | F |
Token ID | 37 |
Feature activation | +6.95e-04 |
Pos logit contributions | |
isphere | +1.040 |
orth | +1.030 |
л | +0.994 |
arthed | +0.957 |
cliffe | +0.950 |
Neg logit contributions | |
disag | -1.331 |
Sah | -1.233 |
Saharan | -1.222 |
pleas | -1.213 |
ucket | -1.196 |
Token | ( |
Token ID | 357 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
isphere | +0.005 |
orth | +0.005 |
л | +0.005 |
arthed | +0.005 |
cliffe | +0.005 |
Neg logit contributions | |
disag | -0.006 |
Sah | -0.006 |
Saharan | -0.006 |
pleas | -0.006 |
ucket | -0.006 |
Token | 0 |
Token ID | 15 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
orth | +7.600 |
isphere | +7.196 |
irc | +7.141 |
л | +6.996 |
cliffe | +6.625 |
Neg logit contributions | |
disag | -13.311 |
pleas | -12.479 |
Sah | -12.357 |
Saharan | -12.284 |
ucket | -12.186 |
Token | , |
Token ID | 11 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
orth | +2.673 |
isphere | +2.657 |
л | +2.547 |
arthed | +2.401 |
irc | +2.398 |
Neg logit contributions | |
disag | -4.032 |
Sah | -3.787 |
Saharan | -3.744 |
pleas | -3.687 |
ucket | -3.629 |
Token | ($ |
Token ID | 16763 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
orth | +5.113 |
isphere | +5.026 |
л | +4.883 |
irc | +4.671 |
arthed | +4.646 |
Neg logit contributions | |
disag | -6.815 |
pleas | -6.249 |
Sah | -6.232 |
Saharan | -6.196 |
ucket | -6.070 |
Token | s |
Token ID | 82 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
isphere | +0.655 |
orth | +0.645 |
л | +0.626 |
arthed | +0.602 |
enza | +0.597 |
Neg logit contributions | |
disag | -0.878 |
Sah | -0.819 |
Saharan | -0.812 |
pleas | -0.803 |
ucket | -0.794 |
Token | z |
Token ID | 89 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
orth | +2.884 |
isphere | +2.717 |
л | +2.608 |
cliffe | +2.263 |
irc | +2.262 |
Neg logit contributions | |
disag | -14.421 |
pleas | -13.177 |
Sah | -13.088 |
Saharan | -13.024 |
ucket | -12.973 |
Token | any |
Token ID | 1092 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
isphere | +0.482 |
orth | +0.476 |
л | +0.461 |
arthed | +0.444 |
cliffe | +0.440 |
Neg logit contributions | |
disag | -0.603 |
Sah | -0.559 |
Saharan | -0.554 |
pleas | -0.549 |
ucket | -0.542 |
Token | Mode |
Token ID | 10363 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
disag | +2.281 |
Sah | +2.051 |
pleas | +2.039 |
Saharan | +2.013 |
ucket | +1.972 |
Neg logit contributions | |
isphere | -2.986 |
orth | -2.946 |
л | -2.865 |
arthed | -2.833 |
cliffe | -2.790 |
Token | : |
Token ID | 25 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
isphere | +0.352 |
orth | +0.346 |
л | +0.333 |
arthed | +0.323 |
enza | +0.318 |
Neg logit contributions | |
disag | -0.522 |
Sah | -0.490 |
Saharan | -0.486 |
pleas | -0.482 |
ucket | -0.474 |
Token | Man |
Token ID | 5124 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
orth | +1.380 |
isphere | +1.379 |
л | +1.327 |
arthed | +1.265 |
enza | +1.248 |
Neg logit contributions | |
disag | -2.084 |
Sah | -1.923 |
Saharan | -1.915 |
pleas | -1.902 |
ucket | -1.886 |
Token | aged |
Token ID | 1886 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
disag | +0.646 |
Saharan | +0.596 |
Sah | +0.594 |
pleas | +0.575 |
ucket | +0.571 |
Neg logit contributions | |
isphere | -0.914 |
orth | -0.894 |
л | -0.889 |
cliffe | -0.852 |
liner | -0.852 |
Token | Access |
Token ID | 8798 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
orth | +2.992 |
isphere | +2.903 |
л | +2.836 |
cliffe | +2.646 |
bey | +2.595 |
Neg logit contributions | |
disag | -6.768 |
Sah | -6.359 |
Saharan | -6.306 |
ucket | -6.260 |
uffy | -6.212 |
Token | Point |
Token ID | 6252 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
orth | +3.613 |
л | +3.199 |
cliffe | +2.940 |
herer | +2.931 |
Ost | +2.843 |
Neg logit contributions | |
disag | -17.866 |
Sah | -16.680 |
Saharan | -16.670 |
ucket | -16.261 |
pleas | -16.198 |
Token | : |
Token ID | 25 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
orth | +2.315 |
isphere | +2.287 |
л | +2.231 |
cliffe | +2.088 |
arthed | +2.061 |
Neg logit contributions | |
disag | -4.280 |
Sah | -3.938 |
Saharan | -3.917 |
ucket | -3.871 |
pleas | -3.868 |
Token | Not |
Token ID | 1892 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
orth | +4.406 |
isphere | +4.333 |
л | +4.269 |
cliffe | +4.034 |
enza | +4.027 |
Neg logit contributions | |
disag | -4.532 |
Sah | -4.185 |
Saharan | -4.183 |
pleas | -4.072 |
ucket | -4.040 |
Token | - |
Token ID | 12 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
isphere | +1.420 |
orth | +1.398 |
л | +1.358 |
arthed | +1.304 |
enza | +1.290 |
Neg logit contributions | |
disag | -1.875 |
Sah | -1.744 |
Saharan | -1.730 |
pleas | -1.714 |
ucket | -1.688 |
Token | Associated |
Token ID | 29014 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
orth | +2.737 |
isphere | +2.701 |
л | +2.592 |
arthed | +2.470 |
cliffe | +2.421 |
Neg logit contributions | |
disag | -5.638 |
Sah | -5.201 |
pleas | -5.196 |
Saharan | -5.162 |
ucket | -5.153 |
Token | 203 |
Token ID | 22416 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
disag | +0.817 |
Sah | +0.752 |
Saharan | +0.742 |
pleas | +0.736 |
ucket | +0.722 |
Neg logit contributions | |
isphere | -0.919 |
orth | -0.903 |
л | -0.878 |
arthed | -0.855 |
cliffe | -0.848 |
Token | x |
Token ID | 2124 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
isphere | +1.144 |
orth | +1.132 |
л | +1.078 |
arthed | +0.995 |
cliffe | +0.991 |
Neg logit contributions | |
disag | -3.252 |
Sah | -3.079 |
Saharan | -3.062 |
pleas | -3.025 |
ucket | -3.010 |
Token | . |
Token ID | 13 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
isphere | +1.194 |
orth | +1.181 |
л | +1.143 |
arthed | +1.098 |
cliffe | +1.088 |
Neg logit contributions | |
disag | -1.594 |
Sah | -1.480 |
Saharan | -1.469 |
pleas | -1.454 |
ucket | -1.437 |
Token | x |
Token ID | 87 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
orth | +2.904 |
isphere | +2.827 |
л | +2.747 |
cliffe | +2.625 |
arthed | +2.556 |
Neg logit contributions | |
disag | -5.464 |
Sah | -4.997 |
Saharan | -4.948 |
pleas | -4.935 |
ucket | -4.900 |
Token | . |
Token ID | 13 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
orth | +3.332 |
isphere | +3.228 |
л | +3.189 |
cliffe | +3.016 |
arthed | +2.963 |
Neg logit contributions | |
disag | -5.556 |
Sah | -5.020 |
Saharan | -5.001 |
ucket | -4.985 |
pleas | -4.949 |
Token | x |
Token ID | 87 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
orth | +4.669 |
isphere | +4.374 |
л | +4.179 |
irc | +4.037 |
cliffe | +4.006 |
Neg logit contributions | |
disag | -9.870 |
Sah | -8.881 |
pleas | -8.876 |
ucket | -8.811 |
uncons | -8.775 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
orth | +6.949 |
irc | +6.389 |
л | +6.099 |
isphere | +6.031 |
ional | +5.809 |
Neg logit contributions | |
disag | -14.888 |
srf | -14.125 |
ucket | -13.312 |
uncons | -13.267 |
pleas | -13.203 |
Token | 112 |
Token ID | 14686 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
orth | +4.737 |
irc | +4.072 |
isphere | +4.044 |
ional | +3.377 |
л | +3.327 |
Neg logit contributions | |
disag | -17.780 |
ucket | -16.746 |
pleas | -16.650 |
uffy | -16.564 |
Sah | -16.459 |
Token | 10 |
Token ID | 838 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
orth | +4.580 |
isphere | +4.495 |
л | +4.427 |
arthed | +4.247 |
cliffe | +4.183 |
Neg logit contributions | |
disag | -6.388 |
Saharan | -5.920 |
Sah | -5.898 |
ucket | -5.838 |
pleas | -5.826 |
Token | 25 |
Token ID | 1495 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
orth | +3.263 |
isphere | +3.232 |
л | +3.181 |
arthed | +3.033 |
cliffe | +3.029 |
Neg logit contributions | |
disag | -3.538 |
Sah | -3.208 |
Saharan | -3.202 |
pleas | -3.162 |
ucket | -3.130 |
Token | 151 |
Token ID | 24309 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
disag | +0.612 |
Sah | +0.563 |
Saharan | +0.555 |
pleas | +0.550 |
ucket | +0.539 |
Neg logit contributions | |
isphere | -0.707 |
orth | -0.694 |
л | -0.676 |
arthed | -0.659 |
cliffe | -0.653 |
Token | [ |
Token ID | 58 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
orth | +4.693 |
irc | +4.310 |
л | +4.256 |
isphere | +3.720 |
herer | +3.294 |
Neg logit contributions | |
disag | -20.362 |
srf | -19.468 |
Sah | -18.603 |
uncons | -18.588 |
Saharan | -18.561 |
Token | 0 |
Token ID | 15 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
orth | +3.870 |
isphere | +3.747 |
л | +3.671 |
arthed | +3.510 |
cliffe | +3.435 |
Neg logit contributions | |
disag | -6.340 |
Sah | -5.833 |
pleas | -5.730 |
Saharan | -5.686 |
uncons | -5.539 |
Token | ], |
Token ID | 4357 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
isphere | +1.237 |
orth | +1.227 |
л | +1.189 |
arthed | +1.141 |
cliffe | +1.130 |
Neg logit contributions | |
disag | -1.656 |
Sah | -1.535 |
Saharan | -1.519 |
pleas | -1.506 |
ucket | -1.489 |
Token | $ |
Token ID | 3 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
orth | +6.603 |
л | +6.345 |
isphere | +6.169 |
cliffe | +5.980 |
irc | +5.980 |
Neg logit contributions | |
disag | -9.401 |
pleas | -8.372 |
ucket | -8.330 |
Sah | -8.196 |
Saharan | -8.102 |
Token | FC |
Token ID | 4851 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
orth | +4.008 |
isphere | +3.997 |
л | +3.896 |
arthed | +3.747 |
cliffe | +3.741 |
Neg logit contributions | |
disag | -3.228 |
Sah | -2.885 |
Saharan | -2.842 |
pleas | -2.836 |
ucket | -2.799 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
orth | +3.616 |
isphere | +3.602 |
л | +3.538 |
arthed | +3.332 |
cliffe | +3.311 |
Neg logit contributions | |
disag | -4.371 |
Sah | -3.907 |
Saharan | -3.867 |
pleas | -3.857 |
ucket | -3.848 |
Token | [ |
Token ID | 58 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
orth | +3.746 |
л | +3.400 |
irc | +3.282 |
isphere | +2.769 |
cliffe | +2.551 |
Neg logit contributions | |
disag | -17.715 |
srf | -17.598 |
uncons | -16.230 |
ucket | -16.152 |
uffy | -16.089 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
isphere | +1.176 |
orth | +1.163 |
л | +1.123 |
arthed | +1.078 |
cliffe | +1.066 |
Neg logit contributions | |
disag | -1.679 |
Sah | -1.562 |
Saharan | -1.550 |
pleas | -1.536 |
ucket | -1.517 |
Token | ], |
Token ID | 4357 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
isphere | +1.543 |
orth | +1.533 |
л | +1.487 |
arthed | +1.423 |
cliffe | +1.408 |
Neg logit contributions | |
disag | -2.133 |
Sah | -1.973 |
Saharan | -1.954 |
pleas | -1.938 |
ucket | -1.918 |
Token | $ |
Token ID | 3 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
orth | +5.598 |
л | +5.413 |
isphere | +5.314 |
cliffe | +5.123 |
irc | +5.060 |
Neg logit contributions | |
disag | -7.502 |
pleas | -6.645 |
ucket | -6.633 |
Sah | -6.555 |
Saharan | -6.501 |
Token | FC |
Token ID | 4851 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
isphere | +3.178 |
orth | +3.170 |
л | +3.089 |
arthed | +2.984 |
cliffe | +2.972 |
Neg logit contributions | |
disag | -2.442 |
Sah | -2.188 |
Saharan | -2.159 |
pleas | -2.146 |
ucket | -2.114 |
Token | x |
Token ID | 2124 |
Feature activation | -9.42e-03 |
Pos logit contributions | |
isphere | +0.852 |
orth | +0.837 |
л | +0.794 |
arthed | +0.745 |
cliffe | +0.733 |
Neg logit contributions | |
disag | -2.257 |
Sah | -2.132 |
Saharan | -2.118 |
pleas | -2.102 |
ucket | -2.082 |
Token | . |
Token ID | 13 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
disag | +0.088 |
Sah | +0.082 |
Saharan | +0.081 |
pleas | +0.081 |
ucket | +0.079 |
Neg logit contributions | |
isphere | -0.074 |
orth | -0.072 |
л | -0.070 |
arthed | -0.068 |
enza | -0.067 |
Token | x |
Token ID | 87 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
orth | +2.334 |
isphere | +2.306 |
л | +2.224 |
cliffe | +2.118 |
arthed | +2.091 |
Neg logit contributions | |
disag | -4.133 |
Sah | -3.803 |
Saharan | -3.768 |
pleas | -3.755 |
ucket | -3.720 |
Token | . |
Token ID | 13 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
isphere | +0.464 |
orth | +0.456 |
л | +0.442 |
arthed | +0.427 |
enza | +0.422 |
Neg logit contributions | |
disag | -0.591 |
Sah | -0.552 |
Saharan | -0.547 |
pleas | -0.542 |
ucket | -0.533 |
Token | x |
Token ID | 87 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
isphere | +0.242 |
orth | +0.237 |
л | +0.230 |
arthed | +0.222 |
enza | +0.218 |
Neg logit contributions | |
disag | -0.353 |
Sah | -0.332 |
Saharan | -0.330 |
pleas | -0.326 |
ucket | -0.322 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
disag | +3.017 |
Sah | +2.904 |
Saharan | +2.859 |
pleas | +2.814 |
uffy | +2.751 |
Neg logit contributions | |
isphere | -3.002 |
orth | -2.849 |
л | -2.811 |
arthed | -2.753 |
enza | -2.737 |
Token | 99 |
Token ID | 2079 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
disag | +6.295 |
Sah | +5.726 |
Saharan | +5.396 |
uffy | +5.345 |
pleas | +5.320 |
Neg logit contributions | |
isphere | -17.938 |
л | -17.866 |
cliffe | -17.288 |
enza | -16.959 |
arthed | -16.938 |
Token | 10 |
Token ID | 838 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
orth | +3.573 |
isphere | +3.532 |
л | +3.464 |
arthed | +3.306 |
cliffe | +3.262 |
Neg logit contributions | |
disag | -4.817 |
Saharan | -4.442 |
Sah | -4.428 |
pleas | -4.379 |
ucket | -4.371 |
Token | 88 |
Token ID | 3459 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
disag | +0.639 |
Sah | +0.605 |
Saharan | +0.590 |
pleas | +0.587 |
ucket | +0.575 |
Neg logit contributions | |
isphere | -0.643 |
orth | -0.618 |
л | -0.600 |
arthed | -0.589 |
enza | -0.583 |
Token | 350 |
Token ID | 14877 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
isphere | +0.683 |
orth | +0.676 |
л | +0.658 |
arthed | +0.638 |
cliffe | +0.632 |
Neg logit contributions | |
disag | -0.618 |
Sah | -0.566 |
Saharan | -0.560 |
pleas | -0.553 |
ucket | -0.545 |
Token | x |
Token ID | 2124 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
isphere | +0.632 |
orth | +0.617 |
л | +0.583 |
arthed | +0.555 |
enza | +0.543 |
Neg logit contributions | |
disag | -1.551 |
Sah | -1.463 |
Saharan | -1.451 |
pleas | -1.448 |
ucket | -1.427 |
Token | � |
Token ID | 247 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
disag | +0.922 |
Sah | +0.847 |
Saharan | +0.845 |
pleas | +0.829 |
ucket | +0.822 |
Neg logit contributions | |
isphere | -1.024 |
orth | -1.014 |
л | -0.979 |
arthed | -0.944 |
cliffe | -0.944 |
Token | ble |
Token ID | 903 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
disag | +4.248 |
Sah | +4.082 |
Saharan | +3.982 |
pleas | +3.903 |
uffy | +3.812 |
Neg logit contributions | |
isphere | -4.235 |
orth | -4.112 |
л | -3.962 |
arthed | -3.936 |
cliffe | -3.881 |
Token | Prime |
Token ID | 5537 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
disag | +2.456 |
Sah | +2.275 |
Saharan | +2.231 |
pleas | +2.229 |
ucket | +2.150 |
Neg logit contributions | |
isphere | -2.658 |
orth | -2.585 |
л | -2.497 |
arthed | -2.487 |
enza | -2.461 |
Token | Minister |
Token ID | 4139 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
disag | +4.173 |
Sah | +3.903 |
pleas | +3.811 |
Saharan | +3.729 |
ucket | +3.668 |
Neg logit contributions | |
isphere | -6.326 |
orth | -6.099 |
л | -5.953 |
arthed | -5.936 |
enza | -5.823 |
Token | Sh |
Token ID | 911 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
disag | +3.779 |
pleas | +3.465 |
Sah | +3.425 |
Saharan | +3.359 |
ucket | +3.295 |
Neg logit contributions | |
isphere | -4.431 |
orth | -4.301 |
л | -4.197 |
arthed | -4.177 |
enza | -4.115 |
Token | ri |
Token ID | 380 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
disag | +2.765 |
Sah | +2.588 |
pleas | +2.568 |
Saharan | +2.546 |
ucket | +2.509 |
Neg logit contributions | |
isphere | -2.081 |
orth | -1.987 |
л | -1.928 |
arthed | -1.907 |
cliffe | -1.891 |
Token | Narendra |
Token ID | 28113 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
disag | +10.419 |
pleas | +10.005 |
Sah | +9.939 |
Saharan | +9.818 |
ucket | +9.647 |
Neg logit contributions | |
isphere | -11.985 |
orth | -11.181 |
enza | -10.749 |
cliffe | -10.679 |
л | -10.642 |
Token | Modi |
Token ID | 14637 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
disag | +1.957 |
pleas | +1.609 |
Sah | +1.576 |
Saharan | +1.488 |
uffy | +1.312 |
Neg logit contributions | |
isphere | -8.331 |
orth | -8.238 |
л | -8.053 |
arthed | -8.007 |
enza | -7.997 |
Token | has |
Token ID | 468 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
isphere | +1.863 |
orth | +1.843 |
л | +1.783 |
arthed | +1.701 |
cliffe | +1.701 |
Neg logit contributions | |
disag | -2.255 |
Sah | -2.107 |
Saharan | -2.093 |
ucket | -2.048 |
pleas | -2.041 |
Token | approved |
Token ID | 6325 |
Feature activation | +1.73e-03 |
Pos logit contributions | |
disag | +1.107 |
pleas | +1.012 |
Sah | +1.010 |
Saharan | +1.003 |
ucket | +0.976 |
Neg logit contributions | |
isphere | -0.904 |
orth | -0.897 |
л | -0.870 |
arthed | -0.841 |
enza | -0.835 |
Token | the |
Token ID | 262 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
isphere | +0.014 |
orth | +0.014 |
л | +0.014 |
arthed | +0.013 |
cliffe | +0.013 |
Neg logit contributions | |
disag | -0.015 |
Sah | -0.014 |
Saharan | -0.014 |
pleas | -0.014 |
ucket | -0.014 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
disag | +0.184 |
Sah | +0.171 |
Saharan | +0.170 |
pleas | +0.168 |
ucket | +0.166 |
Neg logit contributions | |
isphere | -0.141 |
orth | -0.139 |
л | -0.135 |
arthed | -0.130 |
enza | -0.129 |
Token | 98 |
Token ID | 4089 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
disag | +1.565 |
Sah | +1.438 |
Saharan | +1.419 |
pleas | +1.389 |
uffy | +1.369 |
Neg logit contributions | |
isphere | -1.968 |
orth | -1.924 |
л | -1.896 |
enza | -1.836 |
cliffe | -1.823 |
Token | ] |
Token ID | 60 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
isphere | +0.220 |
orth | +0.219 |
л | +0.212 |
arthed | +0.207 |
enza | +0.201 |
Neg logit contributions | |
disag | -0.302 |
Sah | -0.280 |
Saharan | -0.279 |
pleas | -0.276 |
ucket | -0.271 |
Token | Sporting |
Token ID | 31790 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
isphere | +2.271 |
orth | +2.259 |
л | +2.182 |
arthed | +2.105 |
cliffe | +2.096 |
Neg logit contributions | |
disag | -2.632 |
Sah | -2.440 |
Saharan | -2.425 |
pleas | -2.392 |
ucket | -2.365 |
Token | News |
Token ID | 3000 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
disag | +2.056 |
Sah | +1.926 |
Saharan | +1.893 |
pleas | +1.862 |
uffy | +1.808 |
Neg logit contributions | |
isphere | -2.197 |
orth | -2.186 |
л | -2.145 |
arthed | -2.073 |
enza | -2.059 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
disag | +1.873 |
Sah | +1.733 |
Saharan | +1.718 |
pleas | +1.694 |
ucket | +1.679 |
Neg logit contributions | |
isphere | -1.548 |
orth | -1.510 |
л | -1.478 |
arthed | -1.416 |
enza | -1.412 |
Token | 99 |
Token ID | 2079 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
disag | +6.561 |
Sah | +6.026 |
uffy | +5.847 |
pleas | +5.770 |
Saharan | +5.763 |
Neg logit contributions | |
isphere | -15.073 |
л | -14.750 |
cliffe | -14.374 |
enza | -14.336 |
rity | -14.252 |
Token | ] |
Token ID | 60 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
disag | +0.163 |
Sah | +0.152 |
Saharan | +0.151 |
pleas | +0.149 |
ucket | +0.147 |
Neg logit contributions | |
isphere | -0.124 |
orth | -0.123 |
л | -0.120 |
arthed | -0.116 |
enza | -0.113 |
Token | SB |
Token ID | 18056 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
isphere | +2.804 |
orth | +2.797 |
л | +2.695 |
arthed | +2.598 |
cliffe | +2.594 |
Neg logit contributions | |
disag | -3.237 |
Sah | -3.003 |
Saharan | -2.989 |
pleas | -2.943 |
ucket | -2.912 |
Token | Nation |
Token ID | 8741 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
disag | +1.976 |
Sah | +1.831 |
Saharan | +1.811 |
ucket | +1.758 |
pleas | +1.753 |
Neg logit contributions | |
isphere | -2.450 |
orth | -2.401 |
л | -2.370 |
enza | -2.278 |
arthed | -2.278 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
disag | +2.626 |
Sah | +2.425 |
Saharan | +2.406 |
pleas | +2.374 |
ucket | +2.351 |
Neg logit contributions | |
isphere | -2.272 |
orth | -2.211 |
л | -2.170 |
enza | -2.078 |
arthed | -2.072 |
Token | Pick |
Token ID | 12346 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
disag | +5.389 |
Saharan | +5.020 |
uffy | +5.018 |
Sah | +5.005 |
pleas | +4.958 |
Neg logit contributions | |
isphere | -8.870 |
enza | -8.701 |
rity | -8.627 |
orth | -8.549 |
arthed | -8.526 |
Token | J |
Token ID | 449 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
disag | +3.531 |
Sah | +3.251 |
pleas | +3.209 |
Saharan | +3.207 |
ucket | +3.157 |
Neg logit contributions | |
isphere | -3.161 |
orth | -3.067 |
л | -2.975 |
arthed | -2.898 |
enza | -2.877 |
Token | AB |
Token ID | 6242 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
disag | +4.762 |
Sah | +4.560 |
Saharan | +4.448 |
uffy | +4.429 |
ucket | +4.389 |
Neg logit contributions | |
isphere | -3.731 |
orth | -3.530 |
л | -3.457 |
arthed | -3.402 |
enza | -3.294 |
Token | arry |
Token ID | 6532 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
disag | +3.141 |
Sah | +2.915 |
pleas | +2.880 |
Saharan | +2.874 |
uffy | +2.862 |
Neg logit contributions | |
isphere | -2.845 |
orth | -2.758 |
л | -2.702 |
arthed | -2.627 |
enza | -2.621 |
Token | Maryland |
Token ID | 10769 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
disag | +5.829 |
Sah | +5.535 |
Saharan | +5.371 |
ucket | +5.357 |
pleas | +5.339 |
Neg logit contributions | |
isphere | -5.080 |
orth | -4.821 |
arthed | -4.713 |
л | -4.675 |
enza | -4.570 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
disag | +5.072 |
pleas | +4.644 |
Sah | +4.638 |
Saharan | +4.570 |
ucket | +4.482 |
Neg logit contributions | |
isphere | -5.083 |
orth | -4.872 |
arthed | -4.746 |
л | -4.723 |
enza | -4.621 |
Token | hour |
Token ID | 1711 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
disag | +10.500 |
Sah | +10.221 |
pleas | +10.025 |
Saharan | +9.961 |
uffy | +9.386 |
Neg logit contributions | |
isphere | -10.737 |
arthed | -10.142 |
orth | -9.653 |
cliffe | -9.492 |
hetti | -9.370 |
Token | ago |
Token ID | 2084 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
disag | +3.063 |
Saharan | +2.828 |
Sah | +2.825 |
pleas | +2.822 |
ucket | +2.741 |
Neg logit contributions | |
isphere | -2.572 |
orth | -2.475 |
л | -2.423 |
arthed | -2.393 |
enza | -2.345 |
Token | This |
Token ID | 770 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
disag | +2.351 |
Sah | +2.191 |
pleas | +2.190 |
Saharan | +2.163 |
uffy | +2.098 |
Neg logit contributions | |
isphere | -2.003 |
orth | -1.931 |
л | -1.858 |
arthed | -1.842 |
enza | -1.810 |
Token | election |
Token ID | 3071 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
disag | +0.243 |
Sah | +0.222 |
pleas | +0.221 |
Saharan | +0.220 |
ucket | +0.214 |
Neg logit contributions | |
isphere | -0.223 |
orth | -0.221 |
л | -0.215 |
arthed | -0.210 |
cliffe | -0.206 |
Token | was |
Token ID | 373 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
disag | +2.571 |
pleas | +2.325 |
Sah | +2.306 |
Saharan | +2.291 |
uffy | +2.207 |
Neg logit contributions | |
orth | -2.486 |
isphere | -2.461 |
л | -2.434 |
arthed | -2.372 |
cliffe | -2.340 |
Token | , |
Token ID | 11 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
disag | +2.298 |
pleas | +2.071 |
Sah | +2.067 |
Saharan | +2.040 |
uffy | +2.003 |
Neg logit contributions | |
isphere | -2.025 |
orth | -2.004 |
л | -1.961 |
arthed | -1.916 |
enza | -1.901 |
Token | and |
Token ID | 290 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
disag | +2.450 |
pleas | +2.209 |
Sah | +2.196 |
Saharan | +2.154 |
uffy | +2.106 |
Neg logit contributions | |
isphere | -2.349 |
orth | -2.289 |
л | -2.254 |
arthed | -2.199 |
enza | -2.190 |
Token | four |
Token ID | 1440 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
disag | +2.427 |
pleas | +2.201 |
Sah | +2.186 |
Saharan | +2.135 |
uffy | +2.103 |
Neg logit contributions | |
isphere | -2.500 |
orth | -2.431 |
л | -2.394 |
arthed | -2.345 |
enza | -2.308 |
Token | panel |
Token ID | 6103 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
disag | +5.065 |
pleas | +4.573 |
Sah | +4.411 |
uffy | +4.349 |
Saharan | +4.285 |
Neg logit contributions | |
isphere | -5.336 |
orth | -5.235 |
arthed | -5.176 |
л | -5.114 |
enza | -5.113 |
Token | ists |
Token ID | 1023 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
disag | +3.660 |
pleas | +3.430 |
Sah | +3.347 |
Saharan | +3.304 |
uffy | +3.289 |
Neg logit contributions | |
isphere | -3.093 |
orth | -3.027 |
л | -2.948 |
enza | -2.924 |
arthed | -2.920 |
Token | voting |
Token ID | 6709 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
disag | +8.509 |
pleas | +7.613 |
uncons | +6.935 |
uffy | +6.783 |
Sah | +6.620 |
Neg logit contributions | |
arthed | -10.411 |
orth | -10.329 |
enza | -10.289 |
isphere | -10.260 |
л | -10.102 |
Token | in |
Token ID | 287 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
disag | +9.230 |
pleas | +7.938 |
uncons | +7.618 |
uffy | +7.444 |
Saharan | +7.409 |
Neg logit contributions | |
arthed | -11.877 |
orth | -11.725 |
isphere | -11.495 |
л | -11.366 |
rity | -11.346 |
Token | favour |
Token ID | 7075 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
disag | +7.567 |
pleas | +6.761 |
uffy | +6.616 |
Sah | +6.487 |
Saharan | +6.400 |
Neg logit contributions | |
isphere | -9.615 |
л | -9.161 |
orth | -9.142 |
arthed | -9.032 |
enza | -8.987 |
Token | of |
Token ID | 286 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
disag | +3.736 |
pleas | +3.401 |
Sah | +3.393 |
Saharan | +3.369 |
uffy | +3.283 |
Neg logit contributions | |
isphere | -3.187 |
orth | -3.150 |
л | -3.061 |
arthed | -2.972 |
enza | -2.942 |
Token | a |
Token ID | 257 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
isphere | +2.046 |
orth | +2.032 |
л | +1.966 |
arthed | +1.896 |
cliffe | +1.881 |
Neg logit contributions | |
disag | -2.298 |
Sah | -2.148 |
Saharan | -2.127 |
pleas | -2.085 |
ucket | -2.085 |
Token | redesign |
Token ID | 27135 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
isphere | +0.442 |
orth | +0.435 |
л | +0.423 |
arthed | +0.409 |
enza | +0.405 |
Neg logit contributions | |
disag | -0.501 |
Sah | -0.460 |
Saharan | -0.456 |
pleas | -0.454 |
ucket | -0.444 |
Token | — |
Token ID | 851 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
disag | +0.725 |
Sah | +0.669 |
pleas | +0.669 |
Saharan | +0.662 |
uffy | +0.644 |
Neg logit contributions | |
isphere | -0.611 |
orth | -0.598 |
л | -0.576 |
arthed | -0.563 |
enza | -0.559 |
Token | Golden |
Token ID | 8407 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
disag | +2.446 |
Sah | +2.257 |
pleas | +2.222 |
Saharan | +2.202 |
uffy | +2.128 |
Neg logit contributions | |
isphere | -2.319 |
orth | -2.281 |
л | -2.194 |
arthed | -2.146 |
enza | -2.135 |
Token | State |
Token ID | 9012 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
disag | +0.869 |
Sah | +0.821 |
Saharan | +0.807 |
pleas | +0.802 |
ucket | +0.788 |
Neg logit contributions | |
isphere | -0.533 |
orth | -0.513 |
л | -0.497 |
arthed | -0.481 |
enza | -0.477 |
Token | War |
Token ID | 13195 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
disag | +0.205 |
Sah | +0.188 |
Saharan | +0.186 |
pleas | +0.183 |
ucket | +0.180 |
Neg logit contributions | |
isphere | -0.240 |
orth | -0.237 |
л | -0.231 |
arthed | -0.224 |
cliffe | -0.223 |
Token | riors |
Token ID | 8657 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
disag | +4.105 |
Sah | +3.699 |
pleas | +3.645 |
Saharan | +3.584 |
ucket | +3.554 |
Neg logit contributions | |
isphere | -5.783 |
orth | -5.647 |
arthed | -5.534 |
л | -5.451 |
enza | -5.429 |
Token | (@ |
Token ID | 4275 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
isphere | +1.497 |
orth | +1.490 |
л | +1.449 |
arthed | +1.398 |
cliffe | +1.386 |
Neg logit contributions | |
disag | -1.582 |
Sah | -1.454 |
Saharan | -1.444 |
pleas | -1.431 |
ucket | -1.411 |
Token | war |
Token ID | 5767 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
Sah | +10.305 |
disag | +10.028 |
Saharan | +9.881 |
pleas | +9.287 |
uffy | +9.274 |
Neg logit contributions | |
isphere | -9.511 |
liner | -9.450 |
enza | -9.074 |
Baltic | -8.837 |
orth | -8.834 |
Token | riors |
Token ID | 8657 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
disag | +4.292 |
pleas | +3.845 |
uffy | +3.812 |
Sah | +3.809 |
ucket | +3.757 |
Neg logit contributions | |
orth | -5.444 |
isphere | -5.441 |
л | -5.414 |
arthed | -5.375 |
enza | -5.265 |
Token | ) |
Token ID | 8 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
isphere | +0.683 |
orth | +0.675 |
л | +0.647 |
arthed | +0.619 |
cliffe | +0.611 |
Neg logit contributions | |
disag | -1.211 |
Sah | -1.134 |
Saharan | -1.129 |
pleas | -1.120 |
ucket | -1.107 |
Token | September |
Token ID | 2693 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
isphere | +2.699 |
orth | +2.691 |
л | +2.622 |
cliffe | +2.499 |
arthed | +2.487 |
Neg logit contributions | |
disag | -3.420 |
Sah | -3.171 |
Saharan | -3.166 |
pleas | -3.107 |
ucket | -3.097 |
Token | 24 |
Token ID | 1987 |
Feature activation | -4.00e-03 |
Pos logit contributions | |
isphere | +0.241 |
orth | +0.236 |
л | +0.229 |
arthed | +0.223 |
enza | +0.221 |
Neg logit contributions | |
disag | -0.235 |
Sah | -0.219 |
Saharan | -0.216 |
pleas | -0.214 |
ucket | -0.208 |
Token | 11 |
Token ID | 1367 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
isphere | +2.125 |
orth | +2.094 |
л | +2.034 |
arthed | +1.959 |
cliffe | +1.952 |
Neg logit contributions | |
disag | -2.373 |
Sah | -2.210 |
Saharan | -2.186 |
pleas | -2.136 |
ucket | -2.134 |
Token | : |
Token ID | 25 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
disag | +3.980 |
pleas | +3.722 |
Sah | +3.691 |
Saharan | +3.648 |
ucket | +3.600 |
Neg logit contributions | |
isphere | -3.189 |
orth | -3.054 |
arthed | -2.951 |
л | -2.943 |
enza | -2.871 |
Token | 50 |
Token ID | 1120 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
disag | +2.671 |
Sah | +2.603 |
Saharan | +2.549 |
pleas | +2.518 |
ucket | +2.399 |
Neg logit contributions | |
isphere | -3.386 |
orth | -3.239 |
arthed | -3.138 |
л | -3.121 |
enza | -3.100 |
Token | AM |
Token ID | 3001 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
disag | +5.786 |
Sah | +5.546 |
pleas | +5.508 |
Saharan | +5.454 |
uffy | +5.362 |
Neg logit contributions | |
isphere | -8.800 |
orth | -8.275 |
arthed | -8.187 |
л | -8.026 |
liner | -7.899 |
Token | ET |
Token ID | 12152 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
disag | +4.331 |
pleas | +3.945 |
Sah | +3.864 |
Saharan | +3.848 |
uffy | +3.785 |
Neg logit contributions | |
isphere | -4.323 |
orth | -4.142 |
arthed | -4.084 |
л | -3.990 |
rity | -3.925 |
Token | Fri |
Token ID | 19480 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
disag | +4.470 |
pleas | +4.443 |
Sah | +4.197 |
Saharan | +4.040 |
DAV | +3.780 |
Neg logit contributions | |
isphere | -9.288 |
arthed | -8.619 |
orth | -8.564 |
rity | -8.466 |
л | -8.050 |
Token | , |
Token ID | 11 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
disag | +7.607 |
pleas | +7.088 |
Saharan | +6.725 |
Sah | +6.569 |
ucket | +6.446 |
Neg logit contributions | |
isphere | -12.423 |
arthed | -12.321 |
rity | -12.055 |
orth | -11.660 |
liner | -11.160 |
Token | 28 |
Token ID | 2579 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
disag | +5.330 |
Sah | +5.308 |
pleas | +5.111 |
Saharan | +5.033 |
DAV | +4.697 |
Neg logit contributions | |
isphere | -7.956 |
orth | -7.438 |
arthed | -7.394 |
enza | -7.170 |
rity | -7.067 |
Token | July |
Token ID | 2901 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
disag | +3.036 |
pleas | +2.844 |
Sah | +2.842 |
Saharan | +2.808 |
uffy | +2.608 |
Neg logit contributions | |
isphere | -3.687 |
orth | -3.552 |
arthed | -3.483 |
enza | -3.407 |
л | -3.391 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
isphere | +0.124 |
orth | +0.120 |
л | +0.118 |
arthed | +0.115 |
enza | +0.114 |
Neg logit contributions | |
disag | -0.100 |
Sah | -0.091 |
Saharan | -0.091 |
pleas | -0.091 |
ucket | -0.088 |
Token | | |
Token ID | 930 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
disag | +3.472 |
pleas | +3.391 |
Saharan | +3.348 |
Sah | +3.339 |
DAV | +3.174 |
Neg logit contributions | |
isphere | -3.015 |
orth | -2.819 |
arthed | -2.775 |
л | -2.665 |
rity | -2.633 |
Token | Reserve |
Token ID | 12224 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
isphere | +1.613 |
orth | +1.593 |
л | +1.543 |
arthed | +1.489 |
cliffe | +1.471 |
Neg logit contributions | |
disag | -2.033 |
Sah | -1.885 |
Saharan | -1.868 |
pleas | -1.854 |
ucket | -1.825 |
Token | and |
Token ID | 290 |
Feature activation | -6.59e-03 |
Pos logit contributions | |
isphere | +2.986 |
orth | +2.975 |
л | +2.928 |
cliffe | +2.741 |
arthed | +2.738 |
Neg logit contributions | |
disag | -4.914 |
Sah | -4.566 |
Saharan | -4.560 |
ucket | -4.500 |
pleas | -4.495 |
Token | Western |
Token ID | 4885 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
disag | +0.059 |
Sah | +0.054 |
Saharan | +0.054 |
pleas | +0.054 |
ucket | +0.052 |
Neg logit contributions | |
isphere | -0.054 |
orth | -0.054 |
л | -0.052 |
arthed | -0.050 |
enza | -0.050 |
Token | Front |
Token ID | 8880 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
disag | +0.585 |
Sah | +0.545 |
Saharan | +0.540 |
pleas | +0.538 |
ucket | +0.524 |
Neg logit contributions | |
isphere | -0.445 |
orth | -0.436 |
л | -0.422 |
arthed | -0.411 |
enza | -0.403 |
Token | s |
Token ID | 82 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
disag | +3.718 |
Sah | +3.404 |
pleas | +3.368 |
Saharan | +3.349 |
uffy | +3.236 |
Neg logit contributions | |
isphere | -3.332 |
orth | -3.244 |
л | -3.156 |
arthed | -3.121 |
enza | -3.085 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
isphere | +0.082 |
orth | +0.081 |
л | +0.079 |
arthed | +0.076 |
enza | +0.075 |
Neg logit contributions | |
disag | -0.102 |
Sah | -0.095 |
Saharan | -0.094 |
pleas | -0.093 |
ucket | -0.091 |
Token | 30 |
Token ID | 1270 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
Sah | +7.097 |
disag | +7.017 |
Saharan | +6.773 |
pleas | +6.314 |
uffy | +6.238 |
Neg logit contributions | |
isphere | -12.635 |
orth | -12.608 |
liner | -12.100 |
enza | -12.030 |
л | -11.965 |
Token | ] |
Token ID | 60 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
isphere | +0.516 |
orth | +0.507 |
л | +0.492 |
arthed | +0.475 |
enza | +0.471 |
Neg logit contributions | |
disag | -0.617 |
Sah | -0.574 |
Saharan | -0.568 |
pleas | -0.563 |
ucket | -0.554 |
Token | On |
Token ID | 1550 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
isphere | +1.179 |
orth | +1.155 |
л | +1.111 |
arthed | +1.074 |
enza | +1.063 |
Neg logit contributions | |
disag | -1.648 |
Sah | -1.545 |
Saharan | -1.528 |
pleas | -1.514 |
ucket | -1.489 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
isphere | +2.404 |
orth | +2.381 |
л | +2.311 |
arthed | +2.222 |
cliffe | +2.218 |
Neg logit contributions | |
disag | -2.642 |
Sah | -2.439 |
Saharan | -2.420 |
pleas | -2.385 |
ucket | -2.375 |
Token | October |
Token ID | 3267 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
isphere | +1.316 |
orth | +1.302 |
л | +1.260 |
arthed | +1.211 |
cliffe | +1.200 |
Neg logit contributions | |
disag | -1.707 |
Sah | -1.586 |
Saharan | -1.573 |
pleas | -1.557 |
ucket | -1.539 |
Token | paper |
Token ID | 3348 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
disag | +2.164 |
pleas | +1.904 |
Sah | +1.888 |
Saharan | +1.856 |
uffy | +1.785 |
Neg logit contributions | |
isphere | -4.216 |
orth | -4.150 |
л | -4.102 |
enza | -3.978 |
arthed | -3.963 |
Token | towel |
Token ID | 24808 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
isphere | +1.793 |
orth | +1.777 |
л | +1.725 |
arthed | +1.668 |
cliffe | +1.655 |
Neg logit contributions | |
disag | -1.916 |
Sah | -1.769 |
Saharan | -1.753 |
pleas | -1.731 |
ucket | -1.709 |
Token | - |
Token ID | 12 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
orth | +3.165 |
isphere | +3.130 |
л | +3.008 |
cliffe | +2.888 |
arthed | +2.888 |
Neg logit contributions | |
disag | -5.065 |
Sah | -4.775 |
Saharan | -4.758 |
ucket | -4.651 |
pleas | -4.627 |
Token | lined |
Token ID | 10837 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
orth | +4.560 |
isphere | +4.316 |
cliffe | +4.158 |
л | +4.150 |
arthed | +4.033 |
Neg logit contributions | |
disag | -8.480 |
Sah | -7.802 |
pleas | -7.706 |
ucket | -7.675 |
Saharan | -7.647 |
Token | plate |
Token ID | 7480 |
Feature activation | +3.54e-03 |
Pos logit contributions | |
disag | +0.123 |
Sah | +0.112 |
Saharan | +0.111 |
pleas | +0.110 |
ucket | +0.108 |
Neg logit contributions | |
isphere | -0.131 |
orth | -0.130 |
л | -0.126 |
arthed | -0.122 |
cliffe | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
isphere | +0.027 |
orth | +0.026 |
л | +0.025 |
arthed | +0.024 |
enza | +0.024 |
Neg logit contributions | |
disag | -0.034 |
Sah | -0.032 |
Saharan | -0.031 |
pleas | -0.031 |
ucket | -0.031 |
Token | Serve |
Token ID | 35557 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
disag | +3.690 |
Sah | +3.537 |
pleas | +3.483 |
Saharan | +3.063 |
DAV | +2.859 |
Neg logit contributions | |
isphere | -16.763 |
orth | -16.488 |
enza | -15.797 |
л | -15.643 |
arthed | -15.612 |
Token | hot |
Token ID | 3024 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
isphere | +1.351 |
orth | +1.340 |
л | +1.300 |
arthed | +1.251 |
cliffe | +1.239 |
Neg logit contributions | |
disag | -1.658 |
Sah | -1.540 |
Saharan | -1.529 |
pleas | -1.501 |
ucket | -1.491 |
Token | ! |
Token ID | 0 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
disag | +1.616 |
Sah | +1.532 |
pleas | +1.521 |
Saharan | +1.503 |
ucket | +1.484 |
Neg logit contributions | |
isphere | -1.253 |
orth | -1.216 |
л | -1.161 |
arthed | -1.152 |
enza | -1.134 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
disag | +2.500 |
Sah | +2.327 |
Saharan | +2.307 |
pleas | +2.298 |
ucket | +2.265 |
Neg logit contributions | |
isphere | -1.759 |
orth | -1.745 |
л | -1.672 |
arthed | -1.608 |
enza | -1.594 |
Token | Image |
Token ID | 5159 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
disag | +2.964 |
Sah | +2.932 |
Saharan | +2.869 |
pleas | +2.767 |
ucket | +2.738 |
Neg logit contributions | |
isphere | -2.516 |
orth | -2.425 |
л | -2.342 |
arthed | -2.308 |
liner | -2.296 |
Token | [ |
Token ID | 685 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
isphere | +0.168 |
orth | +0.164 |
л | +0.158 |
arthed | +0.153 |
enza | +0.151 |
Neg logit contributions | |
disag | -0.217 |
Sah | -0.204 |
Saharan | -0.201 |
pleas | -0.199 |
ucket | -0.196 |
Token | UPDATE |
Token ID | 16977 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
isphere | +0.119 |
orth | +0.117 |
л | +0.114 |
arthed | +0.110 |
enza | +0.109 |
Neg logit contributions | |
disag | -0.145 |
Sah | -0.137 |
Saharan | -0.135 |
pleas | -0.133 |
ucket | -0.130 |
Token | , |
Token ID | 11 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
disag | +0.489 |
Sah | +0.454 |
Saharan | +0.449 |
pleas | +0.448 |
ucket | +0.436 |
Neg logit contributions | |
isphere | -0.375 |
orth | -0.368 |
л | -0.353 |
arthed | -0.346 |
cliffe | -0.342 |
Token | 7 |
Token ID | 767 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
disag | +3.451 |
pleas | +3.107 |
Sah | +3.107 |
Saharan | +3.055 |
uffy | +2.907 |
Neg logit contributions | |
isphere | -3.781 |
orth | -3.693 |
arthed | -3.556 |
л | -3.537 |
enza | -3.488 |
Token | : |
Token ID | 25 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
disag | +6.405 |
Sah | +5.957 |
pleas | +5.955 |
Saharan | +5.798 |
uffy | +5.666 |
Neg logit contributions | |
isphere | -5.819 |
orth | -5.510 |
arthed | -5.402 |
enza | -5.212 |
cliffe | -5.208 |
Token | 01 |
Token ID | 486 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
disag | +2.448 |
Sah | +2.400 |
Saharan | +2.344 |
pleas | +2.305 |
ucket | +2.180 |
Neg logit contributions | |
isphere | -3.368 |
orth | -3.214 |
arthed | -3.125 |
л | -3.101 |
enza | -3.099 |
Token | p |
Token ID | 279 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
disag | +6.862 |
pleas | +6.268 |
Sah | +6.050 |
Saharan | +5.838 |
uffy | +5.712 |
Neg logit contributions | |
isphere | -13.354 |
orth | -12.842 |
arthed | -12.597 |
л | -12.410 |
enza | -12.280 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
disag | +3.269 |
Sah | +3.184 |
Saharan | +3.115 |
pleas | +3.100 |
uffy | +2.968 |
Neg logit contributions | |
isphere | -3.507 |
orth | -3.306 |
arthed | -3.248 |
л | -3.221 |
enza | -3.217 |
Token | m |
Token ID | 76 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
disag | +1.752 |
Sah | +1.694 |
Saharan | +1.688 |
pleas | +1.664 |
uffy | +1.625 |
Neg logit contributions | |
isphere | -0.986 |
orth | -0.918 |
л | -0.896 |
arthed | -0.882 |
liner | -0.873 |
Token | .: |
Token ID | 11207 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
disag | +2.285 |
Sah | +2.143 |
Saharan | +2.127 |
pleas | +2.113 |
ucket | +2.089 |
Neg logit contributions | |
isphere | -1.264 |
orth | -1.241 |
л | -1.190 |
arthed | -1.144 |
cliffe | -1.127 |
Token | CNN |
Token ID | 8100 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
isphere | +1.248 |
orth | +1.233 |
л | +1.196 |
arthed | +1.153 |
cliffe | +1.141 |
Neg logit contributions | |
disag | -1.494 |
Sah | -1.384 |
Saharan | -1.372 |
pleas | -1.358 |
ucket | -1.340 |
Token | everything |
Token ID | 2279 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
isphere | +0.320 |
orth | +0.317 |
л | +0.308 |
arthed | +0.298 |
enza | +0.296 |
Neg logit contributions | |
disag | -0.336 |
Sah | -0.306 |
pleas | -0.305 |
Saharan | -0.304 |
ucket | -0.296 |
Token | ? |
Token ID | 30 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
disag | +0.988 |
Sah | +0.914 |
pleas | +0.910 |
Saharan | +0.904 |
ucket | +0.884 |
Neg logit contributions | |
isphere | -0.768 |
orth | -0.764 |
л | -0.736 |
arthed | -0.715 |
enza | -0.704 |
Token | Flag |
Token ID | 19762 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
disag | +4.626 |
Sah | +4.318 |
pleas | +4.287 |
Saharan | +4.183 |
uffy | +4.059 |
Neg logit contributions | |
isphere | -4.468 |
orth | -4.349 |
arthed | -4.315 |
enza | -4.173 |
л | -4.147 |
Token |
|
Token ID | 198 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
disag | +4.974 |
Sah | +4.776 |
Saharan | +4.693 |
pleas | +4.633 |
uffy | +4.539 |
Neg logit contributions | |
isphere | -4.166 |
orth | -4.051 |
arthed | -3.869 |
л | -3.860 |
enza | -3.823 |
Token |
|
Token ID | 198 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
disag | +3.405 |
Sah | +3.300 |
Saharan | +3.263 |
pleas | +3.247 |
uffy | +3.090 |
Neg logit contributions | |
isphere | -3.192 |
orth | -2.991 |
arthed | -2.917 |
л | -2.916 |
enza | -2.845 |
Token | Flag |
Token ID | 34227 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Sah | +3.573 |
Saharan | +3.480 |
disag | +3.273 |
pleas | +3.034 |
ucket | +2.998 |
Neg logit contributions | |
isphere | -7.425 |
liner | -7.153 |
orth | -7.118 |
arthed | -7.095 |
rity | -6.952 |
Token | Reply |
Token ID | 14883 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
disag | +4.550 |
pleas | +4.221 |
Sah | +3.868 |
Saharan | +3.808 |
uncons | +3.367 |
Neg logit contributions | |
isphere | -15.217 |
orth | -15.097 |
arthed | -14.931 |
enza | -14.639 |
rity | -14.401 |
Token |
|
Token ID | 198 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
disag | +2.363 |
Sah | +2.238 |
Saharan | +2.218 |
pleas | +2.215 |
ucket | +2.142 |
Neg logit contributions | |
isphere | -1.850 |
orth | -1.781 |
л | -1.722 |
arthed | -1.690 |
enza | -1.653 |
Token |
|
Token ID | 198 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
disag | +3.229 |
Sah | +3.132 |
Saharan | +3.095 |
pleas | +3.075 |
uffy | +2.925 |
Neg logit contributions | |
isphere | -2.957 |
orth | -2.758 |
arthed | -2.702 |
л | -2.692 |
enza | -2.626 |
Token | 27 |
Token ID | 1983 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
Sah | +4.325 |
disag | +4.219 |
Saharan | +4.168 |
pleas | +4.010 |
ucket | +3.842 |
Neg logit contributions | |
isphere | -5.156 |
orth | -4.816 |
arthed | -4.787 |
liner | -4.674 |
rity | -4.670 |
Token | Recommend |
Token ID | 30361 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
disag | +3.686 |
Sah | +3.388 |
Saharan | +3.386 |
pleas | +3.258 |
uffy | +2.971 |
Neg logit contributions | |
isphere | -9.238 |
orth | -8.699 |
arthed | -8.656 |
rity | -8.608 |
enza | -8.604 |
Token | Recommend |
Token ID | 41248 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
Saharan | +3.638 |
disag | +3.612 |
Sah | +3.592 |
pleas | +3.121 |
ucket | +3.104 |
Neg logit contributions | |
isphere | -8.779 |
arthed | -8.549 |
liner | -8.380 |
cliffe | -8.355 |
л | -8.351 |
Token | Share |
Token ID | 8734 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
disag | +3.081 |
Sah | +2.646 |
ucket | +2.537 |
Saharan | +2.534 |
pleas | +2.495 |
Neg logit contributions | |
isphere | -11.058 |
arthed | -11.026 |
orth | -10.911 |
л | -10.722 |
cliffe | -10.659 |
Token | this |
Token ID | 428 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
disag | +4.858 |
pleas | +4.492 |
Saharan | +4.399 |
Sah | +4.398 |
ucket | +4.276 |
Neg logit contributions | |
isphere | -4.982 |
orth | -4.731 |
л | -4.591 |
arthed | -4.504 |
enza | -4.426 |
Token | comment |
Token ID | 2912 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
disag | +4.031 |
pleas | +3.776 |
Saharan | +3.491 |
Sah | +3.490 |
uncons | +3.426 |
Neg logit contributions | |
isphere | -5.761 |
orth | -5.512 |
arthed | -5.479 |
л | -5.309 |
rity | -5.217 |
Token | on |
Token ID | 319 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
disag | +5.584 |
pleas | +5.235 |
Saharan | +5.084 |
Sah | +5.028 |
ucket | +4.726 |
Neg logit contributions | |
isphere | -8.800 |
orth | -8.184 |
arthed | -8.047 |
rity | -8.026 |
enza | -7.976 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
disag | +2.870 |
Sah | +2.681 |
pleas | +2.643 |
Saharan | +2.597 |
ucket | +2.522 |
Neg logit contributions | |
isphere | -4.876 |
orth | -4.754 |
arthed | -4.626 |
enza | -4.524 |
л | -4.490 |
Token | Share |
Token ID | 8734 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
disag | +3.316 |
Sah | +2.908 |
pleas | +2.884 |
Saharan | +2.716 |
DAV | +2.124 |
Neg logit contributions | |
isphere | -16.817 |
orth | -16.657 |
arthed | -16.470 |
enza | -15.891 |
л | -15.860 |
Token | this |
Token ID | 428 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
disag | +4.551 |
pleas | +4.303 |
Saharan | +4.173 |
Sah | +4.142 |
ucket | +4.040 |
Neg logit contributions | |
isphere | -4.580 |
orth | -4.376 |
л | -4.239 |
arthed | -4.228 |
enza | -4.130 |
Token | comment |
Token ID | 2912 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
disag | +4.734 |
pleas | +4.473 |
Saharan | +4.112 |
Sah | +4.060 |
uncons | +4.010 |
Neg logit contributions | |
isphere | -6.897 |
orth | -6.661 |
arthed | -6.604 |
л | -6.388 |
rity | -6.298 |
Token | on |
Token ID | 319 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
disag | +5.808 |
pleas | +5.533 |
Saharan | +5.322 |
Sah | +5.229 |
uffy | +4.922 |
Neg logit contributions | |
isphere | -9.180 |
orth | -8.654 |
arthed | -8.564 |
rity | -8.480 |
ortunately | -8.474 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
isphere | +0.180 |
orth | +0.178 |
л | +0.173 |
arthed | +0.169 |
enza | +0.167 |
Neg logit contributions | |
disag | -0.143 |
Sah | -0.131 |
Saharan | -0.130 |
pleas | -0.128 |
ucket | -0.125 |
Token | make |
Token ID | 787 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
disag | +1.885 |
Sah | +1.727 |
pleas | +1.717 |
Saharan | +1.697 |
ucket | +1.663 |
Neg logit contributions | |
isphere | -1.784 |
orth | -1.746 |
arthed | -1.705 |
л | -1.679 |
cliffe | -1.648 |
Token | a |
Token ID | 257 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
disag | +0.522 |
Sah | +0.482 |
pleas | +0.479 |
Saharan | +0.477 |
ucket | +0.469 |
Neg logit contributions | |
isphere | -0.491 |
orth | -0.483 |
л | -0.466 |
arthed | -0.459 |
enza | -0.451 |
Token | living |
Token ID | 2877 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
disag | +0.165 |
Sah | +0.152 |
Saharan | +0.150 |
pleas | +0.150 |
ucket | +0.147 |
Neg logit contributions | |
isphere | -0.165 |
orth | -0.163 |
л | -0.158 |
arthed | -0.154 |
cliffe | -0.152 |
Token | doing |
Token ID | 1804 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
disag | +0.596 |
Sah | +0.547 |
pleas | +0.545 |
Saharan | +0.541 |
ucket | +0.528 |
Neg logit contributions | |
isphere | -0.548 |
orth | -0.539 |
л | -0.515 |
arthed | -0.512 |
enza | -0.503 |
Token | something |
Token ID | 1223 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
disag | +2.349 |
pleas | +2.188 |
Saharan | +2.146 |
Sah | +2.138 |
ucket | +2.086 |
Neg logit contributions | |
isphere | -2.128 |
orth | -2.070 |
л | -1.976 |
arthed | -1.972 |
enza | -1.936 |
Token | you |
Token ID | 345 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
disag | +4.068 |
pleas | +3.921 |
Sah | +3.789 |
Saharan | +3.738 |
uffy | +3.672 |
Neg logit contributions | |
isphere | -2.608 |
orth | -2.525 |
arthed | -2.460 |
л | -2.434 |
enza | -2.376 |
Token | not |
Token ID | 407 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
disag | +8.389 |
pleas | +8.139 |
Sah | +7.419 |
Saharan | +7.349 |
uncons | +7.230 |
Neg logit contributions | |
isphere | -11.229 |
arthed | -10.919 |
orth | -10.504 |
cliffe | -10.339 |
enza | -10.121 |
Token | only |
Token ID | 691 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
disag | +7.697 |
pleas | +7.641 |
ucket | +7.007 |
Sah | +6.954 |
Saharan | +6.867 |
Neg logit contributions | |
isphere | -8.902 |
arthed | -8.541 |
orth | -8.323 |
cliffe | -8.215 |
л | -8.210 |
Token | like |
Token ID | 588 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
disag | +2.095 |
pleas | +1.911 |
Sah | +1.863 |
Saharan | +1.831 |
ucket | +1.787 |
Neg logit contributions | |
isphere | -3.478 |
orth | -3.379 |
arthed | -3.318 |
л | -3.313 |
cliffe | -3.249 |
Token | doing |
Token ID | 1804 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
disag | +2.614 |
pleas | +2.442 |
Sah | +2.417 |
Saharan | +2.402 |
ucket | +2.358 |
Neg logit contributions | |
isphere | -2.329 |
orth | -2.243 |
arthed | -2.155 |
л | -2.151 |
enza | -2.123 |
Token | , |
Token ID | 11 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
disag | +0.502 |
Sah | +0.464 |
Saharan | +0.462 |
pleas | +0.461 |
ucket | +0.452 |
Neg logit contributions | |
isphere | -0.406 |
orth | -0.397 |
л | -0.383 |
arthed | -0.376 |
enza | -0.369 |
Token | available |
Token ID | 1695 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
isphere | +3.789 |
orth | +3.745 |
л | +3.615 |
arthed | +3.504 |
enza | +3.459 |
Neg logit contributions | |
disag | -4.225 |
Sah | -3.970 |
Saharan | -3.917 |
ucket | -3.867 |
pleas | -3.841 |
Token | since |
Token ID | 1201 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
isphere | +2.601 |
orth | +2.566 |
л | +2.491 |
arthed | +2.384 |
enza | +2.370 |
Neg logit contributions | |
disag | -3.218 |
Sah | -3.027 |
Saharan | -2.994 |
ucket | -2.942 |
pleas | -2.939 |
Token | 16 |
Token ID | 1467 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
disag | +0.405 |
Sah | +0.369 |
Saharan | +0.365 |
pleas | +0.363 |
ucket | +0.351 |
Neg logit contributions | |
isphere | -0.401 |
orth | -0.395 |
л | -0.382 |
arthed | -0.371 |
enza | -0.367 |
Token | July |
Token ID | 2901 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
disag | +1.418 |
Sah | +1.313 |
Saharan | +1.293 |
pleas | +1.283 |
ucket | +1.253 |
Neg logit contributions | |
isphere | -1.390 |
orth | -1.347 |
arthed | -1.295 |
л | -1.294 |
enza | -1.269 |
Token | 2007 |
Token ID | 4343 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
isphere | +2.059 |
orth | +2.038 |
л | +1.979 |
arthed | +1.909 |
cliffe | +1.892 |
Neg logit contributions | |
disag | -2.307 |
Sah | -2.133 |
Saharan | -2.115 |
pleas | -2.090 |
ucket | -2.064 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
disag | +2.243 |
Sah | +2.034 |
Saharan | +2.015 |
pleas | +2.006 |
ucket | +1.956 |
Neg logit contributions | |
isphere | -1.969 |
orth | -1.929 |
л | -1.889 |
arthed | -1.842 |
enza | -1.819 |
Token | 19 |
Token ID | 1129 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
disag | +6.756 |
Sah | +6.510 |
Saharan | +6.302 |
pleas | +6.187 |
ucket | +5.934 |
Neg logit contributions | |
isphere | -12.018 |
л | -11.611 |
liner | -11.422 |
arthed | -11.411 |
orth | -11.354 |
Token | ] |
Token ID | 60 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
disag | +3.436 |
Sah | +3.181 |
Saharan | +3.143 |
pleas | +3.116 |
ucket | +3.075 |
Neg logit contributions | |
isphere | -3.054 |
orth | -2.987 |
л | -2.904 |
cliffe | -2.799 |
arthed | -2.793 |
Token |
|
Token ID | 198 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
isphere | +0.269 |
orth | +0.264 |
л | +0.255 |
arthed | +0.245 |
enza | +0.243 |
Neg logit contributions | |
disag | -0.375 |
Sah | -0.349 |
Saharan | -0.347 |
pleas | -0.342 |
ucket | -0.337 |
Token |
|
Token ID | 198 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
isphere | +0.560 |
orth | +0.548 |
л | +0.529 |
arthed | +0.509 |
enza | +0.502 |
Neg logit contributions | |
disag | -0.846 |
Sah | -0.793 |
Saharan | -0.787 |
pleas | -0.780 |
ucket | -0.768 |
Token | $ |
Token ID | 3 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
disag | +2.243 |
Sah | +2.176 |
Saharan | +2.151 |
pleas | +2.038 |
ucket | +2.020 |
Neg logit contributions | |
isphere | -2.045 |
orth | -1.959 |
л | -1.917 |
arthed | -1.877 |
cliffe | -1.876 |
Token | Sven |
Token ID | 44611 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
isphere | +2.034 |
orth | +2.017 |
л | +1.952 |
arthed | +1.883 |
enza | +1.865 |
Neg logit contributions | |
disag | -2.307 |
Sah | -2.131 |
Saharan | -2.115 |
pleas | -2.092 |
ucket | -2.062 |
Token | s |
Token ID | 82 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
isphere | +3.139 |
orth | +3.125 |
л | +2.995 |
enza | +2.861 |
arthed | +2.859 |
Neg logit contributions | |
disag | -4.429 |
Saharan | -4.112 |
Sah | -4.111 |
pleas | -4.067 |
ucket | -4.023 |
Token | ka |
Token ID | 4914 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
isphere | +2.385 |
orth | +2.360 |
л | +2.285 |
arthed | +2.199 |
cliffe | +2.182 |
Neg logit contributions | |
disag | -2.953 |
Sah | -2.731 |
Saharan | -2.713 |
pleas | -2.684 |
ucket | -2.650 |
Token | Te |
Token ID | 1665 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
isphere | +2.729 |
orth | +2.716 |
л | +2.625 |
arthed | +2.520 |
enza | +2.513 |
Neg logit contributions | |
disag | -3.174 |
Sah | -2.940 |
Saharan | -2.930 |
pleas | -2.880 |
ucket | -2.849 |
Token | ater |
Token ID | 729 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
isphere | +3.113 |
orth | +3.088 |
л | +2.981 |
arthed | +2.875 |
enza | +2.851 |
Neg logit contributions | |
disag | -3.454 |
Sah | -3.182 |
Saharan | -3.175 |
pleas | -3.123 |
ucket | -3.087 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
isphere | +1.335 |
orth | +1.318 |
л | +1.279 |
arthed | +1.233 |
cliffe | +1.219 |
Neg logit contributions | |
disag | -1.677 |
Sah | -1.557 |
Saharan | -1.541 |
pleas | -1.527 |
ucket | -1.508 |
Token | 26 |
Token ID | 2075 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
disag | +6.734 |
Sah | +6.521 |
Saharan | +6.248 |
pleas | +5.953 |
uffy | +5.902 |
Neg logit contributions | |
isphere | -12.148 |
orth | -11.907 |
л | -11.711 |
rity | -11.519 |
enza | -11.504 |
Token | ] |
Token ID | 60 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
disag | +3.331 |
Sah | +3.089 |
Saharan | +3.050 |
pleas | +3.027 |
ucket | +2.990 |
Neg logit contributions | |
isphere | -2.908 |
orth | -2.863 |
л | -2.770 |
cliffe | -2.675 |
arthed | -2.672 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
isphere | +0.220 |
orth | +0.217 |
л | +0.207 |
enza | +0.200 |
arthed | +0.200 |
Neg logit contributions | |
disag | -0.282 |
Sah | -0.263 |
Saharan | -0.261 |
pleas | -0.258 |
ucket | -0.254 |
Token |
|
Token ID | 198 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
disag | +1.668 |
Sah | +1.597 |
Saharan | +1.583 |
pleas | +1.569 |
ucket | +1.512 |
Neg logit contributions | |
isphere | -1.347 |
orth | -1.279 |
л | -1.238 |
arthed | -1.223 |
enza | -1.206 |
Token | In |
Token ID | 818 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
disag | +2.227 |
Sah | +2.182 |
Saharan | +2.150 |
pleas | +2.051 |
ucket | +2.046 |
Neg logit contributions | |
isphere | -2.098 |
orth | -2.038 |
л | -1.960 |
enza | -1.930 |
arthed | -1.928 |
Token | St |
Token ID | 520 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
disag | +5.014 |
Saharan | +4.677 |
pleas | +4.673 |
Sah | +4.620 |
ucket | +4.475 |
Neg logit contributions | |
isphere | -4.898 |
л | -4.642 |
orth | -4.602 |
arthed | -4.525 |
enza | -4.372 |
Token | Lucia |
Token ID | 48158 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
disag | +2.641 |
Sah | +2.457 |
Saharan | +2.439 |
uffy | +2.415 |
ucket | +2.413 |
Neg logit contributions | |
isphere | -2.341 |
л | -2.268 |
orth | -2.266 |
arthed | -2.213 |
cliffe | -2.147 |
Token | from |
Token ID | 422 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
disag | +2.515 |
pleas | +2.294 |
Sah | +2.281 |
Saharan | +2.276 |
ucket | +2.232 |
Neg logit contributions | |
isphere | -2.366 |
orth | -2.310 |
л | -2.290 |
arthed | -2.231 |
enza | -2.168 |
Token | £ |
Token ID | 4248 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
disag | +2.503 |
Sah | +2.308 |
Saharan | +2.301 |
pleas | +2.290 |
uffy | +2.218 |
Neg logit contributions | |
isphere | -1.978 |
orth | -1.908 |
л | -1.847 |
arthed | -1.821 |
enza | -1.768 |
Token | 1 |
Token ID | 16 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
disag | +2.174 |
Sah | +2.053 |
Saharan | +2.023 |
pleas | +1.992 |
uffy | +1.932 |
Neg logit contributions | |
isphere | -2.394 |
orth | -2.313 |
л | -2.243 |
arthed | -2.223 |
enza | -2.190 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
disag | +2.631 |
Sah | +2.434 |
Saharan | +2.412 |
pleas | +2.396 |
ucket | +2.358 |
Neg logit contributions | |
isphere | -2.220 |
orth | -2.168 |
л | -2.097 |
arthed | -2.057 |
cliffe | -2.011 |
Token | 8 |
Token ID | 23 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
disag | +8.533 |
Sah | +7.848 |
pleas | +7.843 |
Saharan | +7.688 |
uffy | +7.550 |
Neg logit contributions | |
isphere | -10.660 |
orth | -9.804 |
л | -9.468 |
liner | -9.452 |
cliffe | -9.443 |
Token | 29 |
Token ID | 1959 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
orth | +3.472 |
isphere | +3.440 |
л | +3.374 |
cliffe | +3.222 |
arthed | +3.207 |
Neg logit contributions | |
disag | -4.065 |
Sah | -3.689 |
Saharan | -3.678 |
pleas | -3.647 |
ucket | -3.630 |
Token | all |
Token ID | 477 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
disag | +2.382 |
Sah | +2.180 |
pleas | +2.175 |
Saharan | +2.157 |
ucket | +2.101 |
Neg logit contributions | |
isphere | -2.338 |
orth | -2.311 |
л | -2.216 |
arthed | -2.188 |
enza | -2.153 |
Token | - |
Token ID | 12 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
isphere | +3.893 |
orth | +3.875 |
л | +3.741 |
cliffe | +3.608 |
arthed | +3.578 |
Neg logit contributions | |
disag | -4.665 |
Sah | -4.321 |
Saharan | -4.257 |
ucket | -4.235 |
pleas | -4.203 |
Token | in |
Token ID | 259 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
orth | +4.416 |
isphere | +4.310 |
л | +4.112 |
cliffe | +4.028 |
enza | +3.915 |
Neg logit contributions | |
disag | -5.641 |
Sah | -5.133 |
pleas | -5.104 |
ucket | -5.078 |
uffy | -5.050 |
Token | x |
Token ID | 2124 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
orth | +1.566 |
isphere | +1.559 |
л | +1.504 |
cliffe | +1.374 |
arthed | +1.347 |
Neg logit contributions | |
disag | -5.067 |
Sah | -4.811 |
Saharan | -4.791 |
pleas | -4.704 |
ucket | -4.703 |
Token | . |
Token ID | 13 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
isphere | +0.816 |
orth | +0.803 |
л | +0.777 |
arthed | +0.751 |
enza | +0.743 |
Neg logit contributions | |
disag | -1.045 |
Sah | -0.975 |
Saharan | -0.966 |
pleas | -0.957 |
ucket | -0.942 |
Token | x |
Token ID | 87 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
isphere | +1.792 |
orth | +1.790 |
л | +1.717 |
cliffe | +1.629 |
arthed | +1.628 |
Neg logit contributions | |
disag | -3.004 |
Sah | -2.784 |
Saharan | -2.759 |
pleas | -2.743 |
ucket | -2.713 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
isphere | +1.380 |
orth | +1.372 |
л | +1.327 |
arthed | +1.270 |
cliffe | +1.261 |
Neg logit contributions | |
disag | -1.910 |
Sah | -1.766 |
Saharan | -1.753 |
pleas | -1.736 |
ucket | -1.720 |
Token | x |
Token ID | 87 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
isphere | +1.167 |
orth | +1.152 |
л | +1.111 |
arthed | +1.063 |
cliffe | +1.052 |
Neg logit contributions | |
disag | -1.822 |
Sah | -1.702 |
Saharan | -1.688 |
pleas | -1.674 |
ucket | -1.654 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
disag | +4.357 |
Sah | +4.240 |
Saharan | +4.182 |
pleas | +4.100 |
ucket | +4.017 |
Neg logit contributions | |
isphere | -4.838 |
orth | -4.563 |
liner | -4.479 |
enza | -4.433 |
л | -4.429 |
Token | 149 |
Token ID | 19442 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
disag | +4.488 |
ucket | +3.987 |
Saharan | +3.962 |
Sah | +3.960 |
pleas | +3.856 |
Neg logit contributions | |
isphere | -14.596 |
liner | -14.330 |
enza | -14.171 |
л | -14.108 |
rity | -14.104 |
Token | 110 |
Token ID | 9796 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
orth | +2.763 |
isphere | +2.759 |
л | +2.683 |
arthed | +2.579 |
cliffe | +2.551 |
Neg logit contributions | |
disag | -3.350 |
Sah | -3.083 |
Saharan | -3.076 |
pleas | -3.034 |
ucket | -3.016 |
Token | 22 |
Token ID | 1828 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
isphere | +0.717 |
orth | +0.702 |
л | +0.679 |
arthed | +0.661 |
enza | +0.655 |
Neg logit contributions | |
disag | -0.747 |
Sah | -0.697 |
Saharan | -0.687 |
pleas | -0.680 |
ucket | -0.668 |
Token | 26 |
Token ID | 2075 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
isphere | +0.923 |
orth | +0.907 |
л | +0.881 |
arthed | +0.855 |
enza | +0.846 |
Neg logit contributions | |
disag | -0.992 |
Sah | -0.920 |
Saharan | -0.910 |
pleas | -0.901 |
ucket | -0.886 |
Token | x |
Token ID | 2124 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
orth | +1.844 |
isphere | +1.803 |
л | +1.767 |
cliffe | +1.599 |
arthed | +1.559 |
Neg logit contributions | |
disag | -6.363 |
Sah | -6.026 |
Saharan | -6.008 |
ucket | -5.922 |
pleas | -5.878 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
disag | +1.868 |
pleas | +1.726 |
Sah | +1.698 |
Saharan | +1.690 |
ucket | +1.657 |
Neg logit contributions | |
isphere | -1.678 |
orth | -1.662 |
л | -1.603 |
arthed | -1.562 |
enza | -1.534 |
Token | died |
Token ID | 3724 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
disag | +1.368 |
pleas | +1.258 |
Sah | +1.258 |
Saharan | +1.238 |
ucket | +1.211 |
Neg logit contributions | |
isphere | -1.218 |
orth | -1.201 |
л | -1.168 |
arthed | -1.134 |
enza | -1.120 |
Token | at |
Token ID | 379 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
disag | +3.590 |
pleas | +3.354 |
Sah | +3.219 |
Saharan | +3.169 |
uncons | +3.088 |
Neg logit contributions | |
isphere | -3.531 |
orth | -3.477 |
arthed | -3.362 |
л | -3.362 |
enza | -3.279 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
disag | +4.931 |
pleas | +4.584 |
Sah | +4.548 |
Saharan | +4.508 |
ucket | +4.376 |
Neg logit contributions | |
isphere | -5.517 |
orth | -5.207 |
л | -5.112 |
arthed | -5.065 |
enza | -4.956 |
Token | : |
Token ID | 25 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
disag | +7.942 |
pleas | +7.662 |
Sah | +7.608 |
Saharan | +7.517 |
uffy | +7.436 |
Neg logit contributions | |
isphere | -8.353 |
orth | -7.934 |
arthed | -7.893 |
л | -7.798 |
enza | -7.589 |
Token | 20 |
Token ID | 1238 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Sah | +4.826 |
Saharan | +4.682 |
disag | +4.583 |
pleas | +4.565 |
ucket | +4.163 |
Neg logit contributions | |
isphere | -7.719 |
orth | -7.232 |
arthed | -7.167 |
liner | -7.129 |
enza | -7.093 |
Token | p |
Token ID | 279 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
disag | +6.552 |
pleas | +6.461 |
Saharan | +6.050 |
Sah | +6.042 |
ucket | +5.903 |
Neg logit contributions | |
isphere | -12.293 |
orth | -11.681 |
arthed | -11.516 |
л | -11.417 |
rity | -11.114 |
Token | . |
Token ID | 13 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
Sah | +4.847 |
disag | +4.779 |
pleas | +4.692 |
Saharan | +4.688 |
uffy | +4.472 |
Neg logit contributions | |
isphere | -6.235 |
arthed | -5.766 |
liner | -5.752 |
orth | -5.752 |
enza | -5.724 |
Token | m |
Token ID | 76 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
disag | +4.222 |
Saharan | +4.135 |
Sah | +4.108 |
pleas | +4.077 |
uffy | +3.977 |
Neg logit contributions | |
isphere | -2.762 |
liner | -2.516 |
orth | -2.509 |
arthed | -2.479 |
л | -2.470 |
Token | . |
Token ID | 13 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
disag | +5.941 |
pleas | +5.480 |
Sah | +5.457 |
ucket | +5.430 |
Saharan | +5.409 |
Neg logit contributions | |
isphere | -5.632 |
orth | -5.416 |
arthed | -5.262 |
л | -5.198 |
enza | -5.099 |
Token | at |
Token ID | 379 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
disag | +4.958 |
pleas | +4.599 |
Sah | +4.457 |
Saharan | +4.443 |
ucket | +4.321 |
Neg logit contributions | |
isphere | -4.770 |
orth | -4.496 |
л | -4.421 |
arthed | -4.395 |
enza | -4.301 |
Token | broccoli |
Token ID | 44653 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
disag | +2.611 |
pleas | +2.142 |
uncons | +1.937 |
Saharan | +1.891 |
uffy | +1.876 |
Neg logit contributions | |
isphere | -8.869 |
orth | -8.796 |
л | -8.438 |
arthed | -8.425 |
cliffe | -8.290 |
Token | for |
Token ID | 329 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
disag | +3.275 |
pleas | +3.001 |
Sah | +2.962 |
Saharan | +2.889 |
uffy | +2.848 |
Neg logit contributions | |
isphere | -3.486 |
orth | -3.359 |
л | -3.314 |
arthed | -3.297 |
enza | -3.235 |
Token | a |
Token ID | 257 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
disag | +4.001 |
pleas | +3.716 |
Sah | +3.707 |
Saharan | +3.651 |
uffy | +3.496 |
Neg logit contributions | |
isphere | -5.503 |
orth | -5.287 |
л | -5.163 |
arthed | -5.059 |
cliffe | -5.004 |
Token | few |
Token ID | 1178 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
disag | +3.040 |
pleas | +2.842 |
Sah | +2.771 |
Saharan | +2.696 |
uffy | +2.626 |
Neg logit contributions | |
isphere | -4.433 |
orth | -4.338 |
л | -4.217 |
arthed | -4.184 |
enza | -4.089 |
Token | minutes |
Token ID | 2431 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
disag | +1.295 |
pleas | +1.205 |
Sah | +1.165 |
Saharan | +1.124 |
ucket | +1.086 |
Neg logit contributions | |
isphere | -2.436 |
orth | -2.405 |
л | -2.343 |
arthed | -2.293 |
enza | -2.274 |
Token | until |
Token ID | 1566 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
disag | +5.294 |
pleas | +4.805 |
Sah | +4.782 |
Saharan | +4.761 |
ucket | +4.482 |
Neg logit contributions | |
isphere | -7.010 |
orth | -6.868 |
л | -6.725 |
arthed | -6.506 |
enza | -6.405 |
Token | fork |
Token ID | 15563 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
disag | +5.160 |
pleas | +4.460 |
uncons | +4.121 |
Saharan | +3.948 |
uffy | +3.818 |
Neg logit contributions | |
isphere | -14.245 |
arthed | -13.802 |
л | -13.690 |
orth | -13.651 |
enza | -13.605 |
Token | - |
Token ID | 12 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
disag | +4.286 |
pleas | +3.969 |
Sah | +3.885 |
Saharan | +3.872 |
uffy | +3.755 |
Neg logit contributions | |
isphere | -4.607 |
л | -4.314 |
orth | -4.305 |
arthed | -4.235 |
enza | -4.207 |
Token | t |
Token ID | 83 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
disag | +0.338 |
Saharan | +0.317 |
Sah | +0.317 |
pleas | +0.312 |
ucket | +0.308 |
Neg logit contributions | |
isphere | -0.239 |
orth | -0.228 |
л | -0.226 |
arthed | -0.217 |
enza | -0.214 |
Token | ender |
Token ID | 2194 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
disag | +5.104 |
Saharan | +4.956 |
ucket | +4.902 |
uffy | +4.900 |
Sah | +4.813 |
Neg logit contributions | |
isphere | -3.435 |
л | -3.342 |
orth | -3.154 |
arthed | -3.131 |
enza | -3.061 |
Token | . |
Token ID | 13 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
disag | +3.491 |
Sah | +3.353 |
pleas | +3.297 |
Saharan | +3.295 |
ucket | +3.129 |
Neg logit contributions | |
isphere | -3.768 |
orth | -3.562 |
arthed | -3.488 |
л | -3.464 |
enza | -3.423 |
Token | racist |
Token ID | 9811 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
disag | +4.746 |
pleas | +4.375 |
Sah | +4.266 |
Saharan | +4.130 |
uffy | +4.116 |
Neg logit contributions | |
isphere | -4.690 |
orth | -4.576 |
л | -4.371 |
arthed | -4.366 |
enza | -4.271 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
disag | +2.630 |
Sah | +2.414 |
pleas | +2.410 |
Saharan | +2.364 |
uffy | +2.317 |
Neg logit contributions | |
isphere | -2.257 |
orth | -2.219 |
arthed | -2.122 |
л | -2.121 |
enza | -2.072 |
Token | Flag |
Token ID | 19762 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
disag | +2.119 |
Sah | +1.978 |
pleas | +1.963 |
Saharan | +1.944 |
ucket | +1.874 |
Neg logit contributions | |
isphere | -1.983 |
orth | -1.933 |
л | -1.854 |
arthed | -1.853 |
enza | -1.812 |
Token |
|
Token ID | 198 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
disag | +4.207 |
Sah | +4.002 |
Saharan | +3.949 |
pleas | +3.901 |
ucket | +3.830 |
Neg logit contributions | |
isphere | -3.427 |
orth | -3.352 |
л | -3.210 |
arthed | -3.206 |
enza | -3.164 |
Token |
|
Token ID | 198 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
disag | +3.643 |
Sah | +3.546 |
Saharan | +3.501 |
pleas | +3.485 |
uffy | +3.307 |
Neg logit contributions | |
isphere | -3.497 |
orth | -3.262 |
arthed | -3.196 |
л | -3.183 |
enza | -3.112 |
Token | Flag |
Token ID | 34227 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Sah | +3.681 |
Saharan | +3.586 |
disag | +3.279 |
ucket | +3.047 |
pleas | +3.042 |
Neg logit contributions | |
isphere | -8.098 |
liner | -7.798 |
arthed | -7.742 |
orth | -7.718 |
rity | -7.580 |
Token | Reply |
Token ID | 14883 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
disag | +4.334 |
pleas | +3.952 |
Sah | +3.704 |
Saharan | +3.632 |
uncons | +3.197 |
Neg logit contributions | |
isphere | -14.469 |
orth | -14.332 |
arthed | -14.166 |
enza | -13.805 |
rity | -13.685 |
Token |
|
Token ID | 198 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
disag | +2.659 |
Sah | +2.523 |
Saharan | +2.499 |
pleas | +2.496 |
ucket | +2.411 |
Neg logit contributions | |
isphere | -2.126 |
orth | -2.044 |
л | -1.974 |
arthed | -1.943 |
enza | -1.895 |
Token |
|
Token ID | 198 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
disag | +2.570 |
Sah | +2.477 |
Saharan | +2.446 |
pleas | +2.433 |
uffy | +2.327 |
Neg logit contributions | |
isphere | -2.231 |
orth | -2.094 |
л | -2.040 |
arthed | -2.039 |
enza | -1.982 |
Token | 19 |
Token ID | 1129 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
Sah | +3.222 |
disag | +3.209 |
Saharan | +3.117 |
pleas | +3.017 |
ucket | +2.907 |
Neg logit contributions | |
isphere | -3.585 |
orth | -3.369 |
arthed | -3.325 |
л | -3.257 |
cliffe | -3.256 |
Token | Recommend |
Token ID | 30361 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
disag | +4.146 |
Sah | +3.705 |
Saharan | +3.622 |
pleas | +3.580 |
uffy | +3.258 |
Neg logit contributions | |
isphere | -10.733 |
arthed | -10.087 |
enza | -9.983 |
orth | -9.972 |
rity | -9.895 |
Token | x |
Token ID | 2124 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
isphere | +0.530 |
orth | +0.518 |
л | +0.491 |
arthed | +0.464 |
enza | +0.454 |
Neg logit contributions | |
disag | -1.368 |
Sah | -1.292 |
Saharan | -1.284 |
pleas | -1.276 |
ucket | -1.261 |
Token | . |
Token ID | 13 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
isphere | +0.771 |
orth | +0.758 |
л | +0.734 |
arthed | +0.709 |
enza | +0.702 |
Neg logit contributions | |
disag | -0.980 |
Sah | -0.915 |
Saharan | -0.906 |
pleas | -0.898 |
ucket | -0.883 |
Token | x |
Token ID | 87 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
orth | +1.849 |
isphere | +1.848 |
л | +1.770 |
cliffe | +1.681 |
arthed | +1.680 |
Neg logit contributions | |
disag | -3.119 |
Sah | -2.888 |
Saharan | -2.863 |
pleas | -2.847 |
ucket | -2.818 |
Token | . |
Token ID | 13 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
orth | +2.388 |
isphere | +2.364 |
л | +2.295 |
cliffe | +2.174 |
arthed | +2.169 |
Neg logit contributions | |
disag | -3.611 |
Sah | -3.299 |
Saharan | -3.277 |
pleas | -3.254 |
ucket | -3.240 |
Token | x |
Token ID | 87 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
orth | +3.984 |
isphere | +3.880 |
л | +3.668 |
cliffe | +3.477 |
irc | +3.466 |
Neg logit contributions | |
disag | -7.371 |
Sah | -6.719 |
pleas | -6.672 |
Saharan | -6.590 |
ucket | -6.562 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
orth | +5.920 |
isphere | +5.490 |
л | +5.368 |
irc | +5.270 |
cliffe | +4.915 |
Neg logit contributions | |
disag | -11.821 |
srf | -10.585 |
pleas | -10.469 |
Sah | -10.467 |
uncons | -10.429 |
Token | 138 |
Token ID | 20107 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
orth | +4.510 |
isphere | +4.104 |
л | +3.601 |
irc | +3.555 |
arthed | +3.215 |
Neg logit contributions | |
disag | -15.288 |
Sah | -14.065 |
pleas | -14.033 |
uffy | -14.005 |
uncons | -13.836 |
Token | 11 |
Token ID | 1367 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
orth | +3.591 |
isphere | +3.548 |
л | +3.470 |
arthed | +3.344 |
cliffe | +3.298 |
Neg logit contributions | |
disag | -4.819 |
Saharan | -4.453 |
Sah | -4.436 |
pleas | -4.384 |
ucket | -4.380 |
Token | 30 |
Token ID | 1270 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
isphere | +1.129 |
orth | +1.112 |
л | +1.079 |
arthed | +1.047 |
enza | +1.037 |
Neg logit contributions | |
disag | -1.152 |
Sah | -1.065 |
Saharan | -1.054 |
pleas | -1.043 |
ucket | -1.026 |
Token | 277 |
Token ID | 27019 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
disag | +1.717 |
Sah | +1.583 |
Saharan | +1.551 |
pleas | +1.546 |
ucket | +1.506 |
Neg logit contributions | |
isphere | -2.071 |
orth | -2.017 |
л | -1.964 |
arthed | -1.926 |
cliffe | -1.905 |
Token | x |
Token ID | 2124 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
orth | +1.630 |
isphere | +1.607 |
л | +1.559 |
cliffe | +1.420 |
arthed | +1.390 |
Neg logit contributions | |
disag | -5.307 |
Sah | -5.029 |
Saharan | -5.013 |
ucket | -4.934 |
pleas | -4.921 |
Token | Massachusetts |
Token ID | 10140 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
disag | +0.224 |
Sah | +0.205 |
Saharan | +0.203 |
pleas | +0.200 |
ucket | +0.197 |
Neg logit contributions | |
isphere | -0.243 |
orth | -0.241 |
л | -0.235 |
arthed | -0.227 |
cliffe | -0.225 |
Token | were |
Token ID | 547 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
isphere | +1.825 |
orth | +1.811 |
л | +1.752 |
arthed | +1.698 |
cliffe | +1.677 |
Neg logit contributions | |
disag | -1.957 |
Sah | -1.794 |
Saharan | -1.790 |
pleas | -1.755 |
ucket | -1.741 |
Token | the |
Token ID | 262 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
isphere | +0.312 |
orth | +0.307 |
л | +0.299 |
arthed | +0.289 |
enza | +0.287 |
Neg logit contributions | |
disag | -0.315 |
Sah | -0.290 |
Saharan | -0.287 |
pleas | -0.285 |
ucket | -0.279 |
Token | Y |
Token ID | 575 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
disag | +0.420 |
Sah | +0.388 |
Saharan | +0.383 |
pleas | +0.383 |
ucket | +0.378 |
Neg logit contributions | |
isphere | -0.372 |
orth | -0.365 |
л | -0.356 |
arthed | -0.345 |
enza | -0.340 |
Token | aw |
Token ID | 707 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
disag | +0.591 |
Sah | +0.554 |
Saharan | +0.551 |
pleas | +0.539 |
ucket | +0.535 |
Neg logit contributions | |
isphere | -0.549 |
orth | -0.532 |
л | -0.525 |
arthed | -0.506 |
enza | -0.497 |
Token | key |
Token ID | 2539 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
disag | +1.910 |
Saharan | +1.842 |
Sah | +1.828 |
ucket | +1.816 |
pleas | +1.808 |
Neg logit contributions | |
isphere | -0.737 |
л | -0.707 |
orth | -0.693 |
arthed | -0.671 |
enza | -0.642 |
Token | Center |
Token ID | 3337 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
orth | +6.715 |
isphere | +6.496 |
cliffe | +6.433 |
irc | +6.324 |
л | +6.220 |
Neg logit contributions | |
disag | -14.011 |
Saharan | -12.906 |
Sah | -12.879 |
uffy | -12.747 |
ucket | -12.528 |
Token | at |
Token ID | 379 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
isphere | +2.139 |
orth | +2.136 |
л | +2.056 |
cliffe | +1.961 |
arthed | +1.960 |
Neg logit contributions | |
disag | -3.305 |
Sah | -3.073 |
Saharan | -3.053 |
pleas | -3.013 |
ucket | -2.994 |
Token | Emmanuel |
Token ID | 32390 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
isphere | +0.241 |
orth | +0.237 |
л | +0.231 |
arthed | +0.225 |
cliffe | +0.222 |
Neg logit contributions | |
disag | -0.212 |
Sah | -0.194 |
Saharan | -0.192 |
pleas | -0.190 |
ucket | -0.186 |
Token | College |
Token ID | 5535 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
orth | +4.738 |
л | +4.387 |
cliffe | +4.305 |
isphere | +4.244 |
bey | +4.158 |
Neg logit contributions | |
disag | -11.913 |
Sah | -11.137 |
Saharan | -11.062 |
ucket | -10.825 |
uffy | -10.709 |
Token | in |
Token ID | 287 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
disag | +1.928 |
Sah | +1.797 |
pleas | +1.783 |
Saharan | +1.777 |
ucket | +1.722 |
Neg logit contributions | |
isphere | -1.848 |
orth | -1.796 |
л | -1.754 |
arthed | -1.723 |
enza | -1.683 |
Token | [ |
Token ID | 58 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
orth | +3.746 |
л | +3.400 |
irc | +3.282 |
isphere | +2.769 |
cliffe | +2.551 |
Neg logit contributions | |
disag | -17.715 |
srf | -17.598 |
uncons | -16.230 |
ucket | -16.152 |
uffy | -16.089 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
isphere | +1.176 |
orth | +1.163 |
л | +1.123 |
arthed | +1.078 |
cliffe | +1.066 |
Neg logit contributions | |
disag | -1.679 |
Sah | -1.562 |
Saharan | -1.550 |
pleas | -1.536 |
ucket | -1.517 |
Token | ], |
Token ID | 4357 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
isphere | +1.543 |
orth | +1.533 |
л | +1.487 |
arthed | +1.423 |
cliffe | +1.408 |
Neg logit contributions | |
disag | -2.133 |
Sah | -1.973 |
Saharan | -1.954 |
pleas | -1.938 |
ucket | -1.918 |
Token | $ |
Token ID | 3 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
orth | +5.598 |
л | +5.413 |
isphere | +5.314 |
cliffe | +5.123 |
irc | +5.060 |
Neg logit contributions | |
disag | -7.502 |
pleas | -6.645 |
ucket | -6.633 |
Sah | -6.555 |
Saharan | -6.501 |
Token | FC |
Token ID | 4851 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
isphere | +3.178 |
orth | +3.170 |
л | +3.089 |
arthed | +2.984 |
cliffe | +2.972 |
Neg logit contributions | |
disag | -2.442 |
Sah | -2.188 |
Saharan | -2.159 |
pleas | -2.146 |
ucket | -2.114 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
orth | +3.436 |
isphere | +3.420 |
л | +3.360 |
arthed | +3.169 |
cliffe | +3.147 |
Neg logit contributions | |
disag | -4.126 |
Sah | -3.685 |
Saharan | -3.652 |
pleas | -3.638 |
ucket | -3.634 |
Token | [ |
Token ID | 58 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
orth | +3.703 |
л | +3.436 |
irc | +3.190 |
isphere | +2.751 |
cliffe | +2.594 |
Neg logit contributions | |
disag | -17.185 |
srf | -17.056 |
uncons | -15.670 |
ucket | -15.661 |
uffy | -15.588 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
orth | +4.062 |
isphere | +3.995 |
л | +3.906 |
cliffe | +3.729 |
irc | +3.677 |
Neg logit contributions | |
disag | -5.244 |
Sah | -4.628 |
ucket | -4.605 |
Saharan | -4.592 |
pleas | -4.578 |
Token | ]) |
Token ID | 12962 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
isphere | +2.183 |
orth | +2.167 |
л | +2.114 |
arthed | +2.023 |
enza | +1.951 |
Neg logit contributions | |
disag | -3.772 |
Sah | -3.499 |
Saharan | -3.472 |
pleas | -3.431 |
uffy | -3.364 |
Token | ) |
Token ID | 1267 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
orth | +3.138 |
л | +3.092 |
isphere | +3.052 |
cliffe | +2.750 |
arthed | +2.606 |
Neg logit contributions | |
disag | -12.892 |
Sah | -12.059 |
Saharan | -12.038 |
ucket | -11.873 |
pleas | -11.816 |
Token | $ |
Token ID | 720 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
orth | +2.933 |
isphere | +2.903 |
л | +2.840 |
cliffe | +2.694 |
arthed | +2.693 |
Neg logit contributions | |
disag | -3.957 |
Sah | -3.724 |
Saharan | -3.721 |
pleas | -3.569 |
ucket | -3.558 |
Token | to |
Token ID | 284 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
isphere | +0.575 |
orth | +0.569 |
л | +0.551 |
arthed | +0.532 |
cliffe | +0.526 |
Neg logit contributions | |
disag | -0.693 |
Sah | -0.642 |
Saharan | -0.637 |
pleas | -0.631 |
ucket | -0.622 |
Token | subscribe |
Token ID | 12383 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
disag | +1.457 |
Saharan | +1.344 |
Sah | +1.336 |
pleas | +1.329 |
ucket | +1.306 |
Neg logit contributions | |
isphere | -1.287 |
orth | -1.260 |
л | -1.219 |
arthed | -1.198 |
cliffe | -1.176 |
Token | to |
Token ID | 284 |
Feature activation | -1.42e-03 |
Pos logit contributions | |
isphere | +1.697 |
orth | +1.687 |
л | +1.647 |
cliffe | +1.571 |
arthed | +1.560 |
Neg logit contributions | |
disag | -2.254 |
Sah | -2.082 |
Saharan | -2.058 |
pleas | -2.036 |
ucket | -2.030 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
disag | +0.013 |
Sah | +0.013 |
Saharan | +0.012 |
pleas | +0.012 |
ucket | +0.012 |
Neg logit contributions | |
isphere | -0.011 |
orth | -0.011 |
л | -0.010 |
arthed | -0.010 |
enza | -0.010 |
Token | Sign |
Token ID | 5865 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
isphere | +1.929 |
orth | +1.905 |
л | +1.846 |
arthed | +1.785 |
enza | +1.766 |
Neg logit contributions | |
disag | -2.158 |
Sah | -1.998 |
Saharan | -1.980 |
pleas | -1.960 |
ucket | -1.928 |
Token | Up |
Token ID | 3205 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
orth | +4.122 |
isphere | +4.034 |
л | +4.023 |
cliffe | +3.852 |
bey | +3.773 |
Neg logit contributions | |
disag | -6.141 |
Sah | -5.567 |
pleas | -5.540 |
ucket | -5.521 |
Saharan | -5.486 |
Token | You |
Token ID | 921 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
л | +2.720 |
orth | +2.293 |
isphere | +2.194 |
bey | +2.173 |
Ost | +2.150 |
Neg logit contributions | |
disag | -16.780 |
ucket | -15.754 |
Sah | -15.344 |
pleas | -15.238 |
srf | -15.193 |
Token | will |
Token ID | 481 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
orth | +2.820 |
isphere | +2.795 |
л | +2.731 |
cliffe | +2.602 |
bey | +2.598 |
Neg logit contributions | |
disag | -3.702 |
Sah | -3.432 |
Saharan | -3.400 |
ucket | -3.318 |
uffy | -3.299 |
Token | receive |
Token ID | 3328 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
orth | +0.916 |
isphere | +0.907 |
л | +0.859 |
cliffe | +0.802 |
arthed | +0.786 |
Neg logit contributions | |
disag | -2.528 |
Sah | -2.395 |
Saharan | -2.366 |
pleas | -2.341 |
ucket | -2.324 |
Token | emails |
Token ID | 7237 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
isphere | +3.198 |
orth | +3.075 |
л | +3.028 |
cliffe | +2.890 |
arthed | +2.829 |
Neg logit contributions | |
disag | -6.611 |
Sah | -6.313 |
Saharan | -6.173 |
ucket | -6.156 |
uffy | -6.029 |
Token | containing |
Token ID | 7268 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
isphere | +1.991 |
orth | +1.967 |
л | +1.913 |
cliffe | +1.820 |
arthed | +1.811 |
Neg logit contributions | |
disag | -2.916 |
Sah | -2.745 |
Saharan | -2.706 |
ucket | -2.660 |
pleas | -2.651 |
Token | the |
Token ID | 262 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
disag | +0.361 |
Sah | +0.329 |
pleas | +0.327 |
Saharan | +0.326 |
ucket | +0.318 |
Neg logit contributions | |
isphere | -0.363 |
orth | -0.355 |
л | -0.345 |
arthed | -0.337 |
cliffe | -0.333 |
Token | worst |
Token ID | 5290 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
orth | +2.817 |
isphere | +2.816 |
л | +2.739 |
arthed | +2.634 |
enza | +2.614 |
Neg logit contributions | |
disag | -2.859 |
Sah | -2.645 |
Saharan | -2.625 |
pleas | -2.564 |
ucket | -2.562 |
Token | ne |
Token ID | 497 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
isphere | +1.358 |
orth | +1.341 |
л | +1.301 |
arthed | +1.258 |
cliffe | +1.246 |
Neg logit contributions | |
disag | -1.534 |
Sah | -1.416 |
Saharan | -1.404 |
pleas | -1.391 |
ucket | -1.370 |
Token | |
Token ID | 3907 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
isphere | +3.367 |
orth | +3.366 |
л | +3.297 |
arthed | +3.170 |
cliffe | +3.133 |
Neg logit contributions | |
disag | -3.892 |
Sah | -3.623 |
Saharan | -3.610 |
pleas | -3.499 |
ucket | -3.483 |
Token | go |
Token ID | 2188 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
isphere | +5.664 |
orth | +5.662 |
л | +5.321 |
bey | +5.267 |
arthed | +5.167 |
Neg logit contributions | |
disag | -7.513 |
Sah | -6.918 |
Saharan | -6.791 |
uffy | -6.693 |
pleas | -6.632 |
Token | |
Token ID | 3907 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
isphere | +2.782 |
orth | +2.756 |
л | +2.679 |
arthed | +2.593 |
cliffe | +2.569 |
Neg logit contributions | |
disag | -2.714 |
Sah | -2.493 |
Saharan | -2.469 |
pleas | -2.441 |
ucket | -2.405 |
Token | ti |
Token ID | 20259 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
orth | +7.543 |
isphere | +7.106 |
rity | +6.425 |
enza | +6.359 |
bey | +6.296 |
Neg logit contributions | |
disag | -13.843 |
uffy | -12.712 |
ucket | -12.698 |
Sah | -12.509 |
DAV | -12.209 |
Token | |
Token ID | 3907 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
isphere | +0.011 |
orth | +0.011 |
л | +0.011 |
arthed | +0.010 |
cliffe | +0.010 |
Neg logit contributions | |
disag | -0.010 |
Sah | -0.009 |
Saharan | -0.009 |
pleas | -0.009 |
ucket | -0.009 |
Token | at |
Token ID | 265 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
orth | +7.884 |
isphere | +7.359 |
rity | +7.259 |
enza | +7.208 |
bey | +7.025 |
Neg logit contributions | |
disag | -9.330 |
Sah | -8.493 |
pleas | -8.310 |
ucket | -8.302 |
Saharan | -8.143 |
Token | |
Token ID | 3907 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
isphere | +1.426 |
orth | +1.410 |
л | +1.368 |
arthed | +1.322 |
cliffe | +1.309 |
Neg logit contributions | |
disag | -1.581 |
Sah | -1.460 |
Saharan | -1.447 |
pleas | -1.432 |
ucket | -1.412 |
Token | or |
Token ID | 273 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
isphere | +2.595 |
orth | +2.584 |
л | +2.440 |
enza | +2.322 |
arthed | +2.319 |
Neg logit contributions | |
disag | -4.524 |
Sah | -4.267 |
Saharan | -4.206 |
pleas | -4.168 |
ucket | -4.098 |
Token | king |
Token ID | 5822 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
isphere | +0.747 |
orth | +0.737 |
л | +0.715 |
arthed | +0.690 |
cliffe | +0.683 |
Neg logit contributions | |
disag | -0.908 |
Sah | -0.840 |
Saharan | -0.828 |
pleas | -0.827 |
ucket | -0.810 |
Token | Xer |
Token ID | 44264 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
isphere | +3.176 |
orth | +3.156 |
л | +3.062 |
arthed | +2.959 |
cliffe | +2.925 |
Neg logit contributions | |
disag | -3.722 |
Sah | -3.441 |
Saharan | -3.437 |
pleas | -3.359 |
ucket | -3.354 |
Token | xes |
Token ID | 48169 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
isphere | +1.203 |
orth | +1.187 |
л | +1.162 |
arthed | +1.126 |
enza | +1.118 |
Neg logit contributions | |
disag | -0.960 |
Sah | -0.874 |
Saharan | -0.864 |
pleas | -0.857 |
ucket | -0.839 |
Token | sent |
Token ID | 1908 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
isphere | +3.764 |
orth | +3.737 |
л | +3.626 |
arthed | +3.488 |
cliffe | +3.467 |
Neg logit contributions | |
disag | -4.344 |
Sah | -4.059 |
Saharan | -4.022 |
ucket | -3.942 |
pleas | -3.923 |
Token | his |
Token ID | 465 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
isphere | +3.023 |
orth | +3.008 |
л | +2.936 |
arthed | +2.823 |
enza | +2.799 |
Neg logit contributions | |
disag | -3.498 |
Sah | -3.234 |
Saharan | -3.207 |
ucket | -3.150 |
pleas | -3.143 |
Token | massive |
Token ID | 4858 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
isphere | +2.958 |
orth | +2.935 |
л | +2.865 |
arthed | +2.739 |
cliffe | +2.725 |
Neg logit contributions | |
disag | -3.536 |
Sah | -3.283 |
Saharan | -3.263 |
ucket | -3.221 |
pleas | -3.197 |
Token | army |
Token ID | 5428 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
isphere | +2.723 |
orth | +2.694 |
л | +2.620 |
arthed | +2.485 |
cliffe | +2.459 |
Neg logit contributions | |
disag | -4.176 |
Sah | -3.911 |
Saharan | -3.889 |
ucket | -3.832 |
pleas | -3.827 |
Token | across |
Token ID | 1973 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
isphere | +2.667 |
orth | +2.629 |
л | +2.551 |
arthed | +2.452 |
enza | +2.429 |
Neg logit contributions | |
disag | -3.238 |
Sah | -3.022 |
Saharan | -2.998 |
ucket | -2.947 |
pleas | -2.942 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
isphere | +0.305 |
orth | +0.301 |
л | +0.292 |
arthed | +0.283 |
enza | +0.280 |
Neg logit contributions | |
disag | -0.323 |
Sah | -0.299 |
Saharan | -0.297 |
pleas | -0.293 |
ucket | -0.287 |
Token | stra |
Token ID | 3534 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
disag | +1.280 |
Sah | +1.189 |
Saharan | +1.167 |
pleas | +1.154 |
ucket | +1.104 |
Neg logit contributions | |
isphere | -1.333 |
orth | -1.314 |
л | -1.285 |
arthed | -1.249 |
enza | -1.234 |
Token | it |
Token ID | 270 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
disag | +2.411 |
Saharan | +2.282 |
Sah | +2.234 |
uffy | +2.172 |
pleas | +2.058 |
Neg logit contributions | |
л | -4.559 |
isphere | -4.524 |
arthed | -4.512 |
orth | -4.499 |
liner | -4.453 |
Token | Gentle |
Token ID | 25066 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
disag | +0.533 |
Sah | +0.476 |
Saharan | +0.470 |
pleas | +0.462 |
ucket | +0.453 |
Neg logit contributions | |
isphere | -0.891 |
orth | -0.884 |
л | -0.864 |
arthed | -0.842 |
cliffe | -0.836 |
Token | men |
Token ID | 3653 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
isphere | +1.299 |
orth | +1.295 |
л | +1.202 |
arthed | +1.118 |
cliffe | +1.116 |
Neg logit contributions | |
disag | -3.737 |
Sah | -3.521 |
Saharan | -3.502 |
pleas | -3.445 |
ucket | -3.444 |
Token | tried |
Token ID | 3088 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
disag | +2.970 |
pleas | +2.700 |
Sah | +2.623 |
Saharan | +2.600 |
ucket | +2.546 |
Neg logit contributions | |
orth | -3.199 |
isphere | -3.183 |
л | -3.155 |
arthed | -3.089 |
cliffe | -3.010 |
Token | to |
Token ID | 284 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
disag | +1.892 |
pleas | +1.733 |
Sah | +1.723 |
Saharan | +1.705 |
ucket | +1.669 |
Neg logit contributions | |
isphere | -1.722 |
orth | -1.710 |
л | -1.658 |
arthed | -1.615 |
enza | -1.596 |
Token | record |
Token ID | 1700 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
isphere | +0.173 |
orth | +0.171 |
л | +0.168 |
arthed | +0.164 |
cliffe | +0.161 |
Neg logit contributions | |
disag | -0.136 |
Sah | -0.122 |
pleas | -0.121 |
Saharan | -0.121 |
ucket | -0.117 |
Token | live |
Token ID | 2107 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
disag | +1.392 |
pleas | +1.275 |
Sah | +1.266 |
Saharan | +1.261 |
ucket | +1.225 |
Neg logit contributions | |
orth | -1.266 |
isphere | -1.263 |
л | -1.226 |
arthed | -1.192 |
enza | -1.174 |
Token | -- |
Token ID | 1377 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
isphere | +2.106 |
orth | +2.075 |
л | +2.010 |
arthed | +1.929 |
enza | +1.913 |
Neg logit contributions | |
disag | -2.694 |
Sah | -2.506 |
Saharan | -2.484 |
pleas | -2.447 |
ucket | -2.433 |
Token | first |
Token ID | 717 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
disag | +0.126 |
Sah | +0.116 |
pleas | +0.115 |
Saharan | +0.115 |
ucket | +0.112 |
Neg logit contributions | |
isphere | -0.100 |
orth | -0.098 |
л | -0.095 |
arthed | -0.093 |
enza | -0.091 |
Token | of |
Token ID | 286 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
isphere | +0.832 |
orth | +0.825 |
л | +0.802 |
arthed | +0.772 |
cliffe | +0.764 |
Neg logit contributions | |
disag | -0.981 |
Sah | -0.907 |
Saharan | -0.896 |
pleas | -0.894 |
ucket | -0.875 |
Token | all |
Token ID | 477 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
isphere | +1.278 |
orth | +1.258 |
л | +1.226 |
arthed | +1.186 |
enza | +1.172 |
Neg logit contributions | |
disag | -1.331 |
Sah | -1.219 |
Saharan | -1.209 |
pleas | -1.206 |
ucket | -1.177 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
isphere | +1.393 |
orth | +1.376 |
л | +1.334 |
arthed | +1.275 |
cliffe | +1.267 |
Neg logit contributions | |
disag | -1.806 |
Sah | -1.682 |
Saharan | -1.669 |
pleas | -1.640 |
ucket | -1.629 |
Token | golden |
Token ID | 10861 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
disag | +1.403 |
Sah | +1.277 |
pleas | +1.262 |
Saharan | +1.262 |
ucket | +1.227 |
Neg logit contributions | |
isphere | -1.510 |
orth | -1.485 |
л | -1.445 |
arthed | -1.421 |
cliffe | -1.400 |
Token | child |
Token ID | 1200 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
disag | +3.455 |
Sah | +3.219 |
Saharan | +3.144 |
pleas | +3.126 |
ucket | +3.037 |
Neg logit contributions | |
isphere | -3.090 |
orth | -2.952 |
л | -2.913 |
arthed | -2.899 |
cliffe | -2.851 |
Token | right |
Token ID | 826 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
isphere | +0.833 |
orth | +0.821 |
л | +0.800 |
arthed | +0.760 |
enza | +0.754 |
Neg logit contributions | |
disag | -1.109 |
Sah | -1.031 |
Saharan | -1.025 |
pleas | -1.007 |
ucket | -0.998 |
Token | now |
Token ID | 783 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
disag | +4.100 |
pleas | +3.779 |
Sah | +3.739 |
Saharan | +3.673 |
ucket | +3.566 |
Neg logit contributions | |
isphere | -4.395 |
orth | -4.250 |
arthed | -4.116 |
л | -4.034 |
enza | -3.960 |
Token | , |
Token ID | 11 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
isphere | +2.864 |
orth | +2.844 |
л | +2.767 |
enza | +2.584 |
cliffe | +2.583 |
Neg logit contributions | |
disag | -3.855 |
Sah | -3.617 |
Saharan | -3.598 |
pleas | -3.504 |
ucket | -3.482 |
Token | but |
Token ID | 475 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
disag | +0.644 |
Sah | +0.593 |
pleas | +0.587 |
Saharan | +0.587 |
ucket | +0.574 |
Neg logit contributions | |
isphere | -0.548 |
orth | -0.537 |
л | -0.521 |
arthed | -0.509 |
enza | -0.502 |
Token | I |
Token ID | 314 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
isphere | +3.094 |
orth | +3.065 |
л | +2.960 |
enza | +2.834 |
cliffe | +2.830 |
Neg logit contributions | |
disag | -3.595 |
Sah | -3.353 |
Saharan | -3.306 |
pleas | -3.253 |
ucket | -3.250 |
Token | � |
Token ID | 447 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
disag | +1.763 |
Sah | +1.621 |
pleas | +1.592 |
Saharan | +1.583 |
uffy | +1.532 |
Neg logit contributions | |
isphere | -1.690 |
orth | -1.635 |
arthed | -1.580 |
л | -1.576 |
cliffe | -1.538 |
Token | � |
Token ID | 247 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
isphere | +0.524 |
orth | +0.522 |
л | +0.501 |
arthed | +0.484 |
cliffe | +0.484 |
Neg logit contributions | |
disag | -0.528 |
Sah | -0.489 |
Saharan | -0.485 |
pleas | -0.480 |
ucket | -0.474 |
Token | ve |
Token ID | 303 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
isphere | +0.525 |
orth | +0.507 |
л | +0.487 |
arthed | +0.466 |
cliffe | +0.462 |
Neg logit contributions | |
disag | -0.951 |
Sah | -0.892 |
Saharan | -0.885 |
pleas | -0.880 |
uffy | -0.866 |
Token | also |
Token ID | 635 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
disag | +0.808 |
Sah | +0.737 |
pleas | +0.731 |
Saharan | +0.724 |
ucket | +0.699 |
Neg logit contributions | |
isphere | -0.821 |
orth | -0.807 |
л | -0.781 |
arthed | -0.764 |
cliffe | -0.760 |
Token | be |
Token ID | 307 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
disag | +1.507 |
Sah | +1.378 |
Saharan | +1.372 |
pleas | +1.367 |
ucket | +1.328 |
Neg logit contributions | |
isphere | -1.578 |
orth | -1.545 |
л | -1.505 |
arthed | -1.482 |
cliffe | -1.454 |
Token | . |
Token ID | 13 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
disag | +2.240 |
pleas | +2.051 |
Sah | +2.049 |
Saharan | +2.031 |
ucket | +1.982 |
Neg logit contributions | |
isphere | -1.949 |
orth | -1.907 |
л | -1.849 |
arthed | -1.840 |
cliffe | -1.799 |
Token |
|
Token ID | 198 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
disag | +1.775 |
Sah | +1.673 |
Saharan | +1.647 |
pleas | +1.631 |
ucket | +1.608 |
Neg logit contributions | |
isphere | -1.337 |
orth | -1.289 |
л | -1.229 |
arthed | -1.213 |
enza | -1.186 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
disag | +0.344 |
Sah | +0.326 |
Saharan | +0.323 |
pleas | +0.320 |
ucket | +0.312 |
Neg logit contributions | |
isphere | -0.250 |
orth | -0.241 |
л | -0.232 |
arthed | -0.227 |
enza | -0.223 |
Token | Mal |
Token ID | 15029 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
disag | +1.237 |
Sah | +1.188 |
Saharan | +1.163 |
pleas | +1.136 |
ucket | +1.129 |
Neg logit contributions | |
isphere | -1.075 |
orth | -1.040 |
л | -1.000 |
arthed | -0.992 |
cliffe | -0.974 |
Token | colm |
Token ID | 18414 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
isphere | +0.241 |
orth | +0.238 |
л | +0.232 |
arthed | +0.224 |
enza | +0.222 |
Neg logit contributions | |
disag | -0.252 |
Sah | -0.232 |
Saharan | -0.229 |
pleas | -0.227 |
ucket | -0.225 |
Token | Grim |
Token ID | 17525 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
isphere | +3.913 |
orth | +3.911 |
л | +3.782 |
cliffe | +3.647 |
arthed | +3.626 |
Neg logit contributions | |
disag | -4.297 |
Sah | -4.009 |
Saharan | -4.000 |
pleas | -3.906 |
ucket | -3.854 |
Token | ston |
Token ID | 3743 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
isphere | +3.215 |
orth | +3.207 |
л | +3.077 |
cliffe | +2.962 |
arthed | +2.955 |
Neg logit contributions | |
disag | -3.992 |
Sah | -3.711 |
Saharan | -3.688 |
pleas | -3.628 |
ucket | -3.577 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
isphere | +2.709 |
orth | +2.685 |
л | +2.594 |
cliffe | +2.474 |
arthed | +2.473 |
Neg logit contributions | |
disag | -3.518 |
Sah | -3.271 |
Saharan | -3.245 |
pleas | -3.203 |
ucket | -3.161 |
Token | a |
Token ID | 257 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
disag | +0.945 |
Sah | +0.871 |
Saharan | +0.866 |
pleas | +0.860 |
ucket | +0.844 |
Neg logit contributions | |
isphere | -0.853 |
orth | -0.837 |
л | -0.813 |
arthed | -0.791 |
cliffe | -0.779 |
Token | nuclear |
Token ID | 4523 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
disag | +2.943 |
pleas | +2.697 |
Saharan | +2.663 |
Sah | +2.659 |
ucket | +2.594 |
Neg logit contributions | |
isphere | -2.850 |
orth | -2.773 |
л | -2.699 |
arthed | -2.678 |
enza | -2.604 |
Token | you |
Token ID | 345 |
Feature activation | +3.61e-03 |
Pos logit contributions | |
disag | +0.096 |
Sah | +0.089 |
pleas | +0.088 |
Saharan | +0.087 |
ucket | +0.085 |
Neg logit contributions | |
isphere | -0.080 |
orth | -0.080 |
л | -0.077 |
arthed | -0.074 |
cliffe | -0.074 |
Token | do |
Token ID | 466 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
isphere | +0.032 |
orth | +0.031 |
л | +0.030 |
arthed | +0.030 |
cliffe | +0.029 |
Neg logit contributions | |
disag | -0.030 |
Sah | -0.028 |
Saharan | -0.028 |
pleas | -0.027 |
ucket | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
disag | +0.342 |
Sah | +0.316 |
Saharan | +0.313 |
pleas | +0.312 |
ucket | +0.307 |
Neg logit contributions | |
isphere | -0.287 |
orth | -0.281 |
л | -0.271 |
arthed | -0.267 |
enza | -0.263 |
Token |
|
Token ID | 198 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
disag | +0.845 |
Sah | +0.799 |
pleas | +0.785 |
Saharan | +0.783 |
ucket | +0.762 |
Neg logit contributions | |
isphere | -0.667 |
orth | -0.651 |
л | -0.622 |
arthed | -0.613 |
enza | -0.605 |
Token |
|
Token ID | 198 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
disag | +0.882 |
Sah | +0.838 |
Saharan | +0.829 |
pleas | +0.825 |
ucket | +0.800 |
Neg logit contributions | |
isphere | -0.664 |
orth | -0.637 |
л | -0.616 |
arthed | -0.603 |
enza | -0.592 |
Token | Lyn |
Token ID | 37207 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
disag | +2.563 |
Sah | +2.523 |
Saharan | +2.441 |
pleas | +2.381 |
uffy | +2.342 |
Neg logit contributions | |
isphere | -2.216 |
orth | -2.134 |
л | -2.075 |
arthed | -2.051 |
enza | -2.024 |
Token | n |
Token ID | 77 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
isphere | +2.915 |
orth | +2.900 |
л | +2.788 |
arthed | +2.681 |
cliffe | +2.676 |
Neg logit contributions | |
disag | -3.565 |
Sah | -3.298 |
Saharan | -3.290 |
pleas | -3.233 |
ucket | -3.196 |
Token | Rogers |
Token ID | 15372 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
orth | +3.423 |
isphere | +3.420 |
л | +3.305 |
cliffe | +3.173 |
arthed | +3.152 |
Neg logit contributions | |
disag | -4.072 |
Saharan | -3.746 |
Sah | -3.738 |
pleas | -3.651 |
ucket | -3.628 |
Token | , |
Token ID | 11 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
isphere | +0.947 |
orth | +0.933 |
л | +0.903 |
arthed | +0.871 |
enza | +0.861 |
Neg logit contributions | |
disag | -1.212 |
Sah | -1.126 |
Saharan | -1.115 |
pleas | -1.107 |
ucket | -1.090 |
Token | Bi |
Token ID | 8436 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
disag | +3.502 |
Sah | +3.231 |
pleas | +3.209 |
Saharan | +3.181 |
ucket | +3.085 |
Neg logit contributions | |
isphere | -3.302 |
orth | -3.203 |
л | -3.108 |
arthed | -3.045 |
enza | -2.997 |
Token | ologist |
Token ID | 7451 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
disag | +2.007 |
Sah | +1.866 |
Saharan | +1.846 |
pleas | +1.829 |
ucket | +1.803 |
Neg logit contributions | |
isphere | -2.137 |
orth | -2.072 |
л | -2.063 |
enza | -1.978 |
arthed | -1.978 |
Token | costume |
Token ID | 16569 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
disag | +0.869 |
Sah | +0.792 |
Saharan | +0.786 |
pleas | +0.782 |
ucket | +0.761 |
Neg logit contributions | |
isphere | -0.880 |
orth | -0.860 |
л | -0.839 |
arthed | -0.819 |
enza | -0.806 |
Token | were |
Token ID | 547 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
isphere | +0.829 |
orth | +0.820 |
л | +0.795 |
arthed | +0.769 |
cliffe | +0.761 |
Neg logit contributions | |
disag | -0.921 |
Sah | -0.850 |
Saharan | -0.842 |
pleas | -0.835 |
ucket | -0.822 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
disag | +2.530 |
pleas | +2.356 |
Sah | +2.255 |
Saharan | +2.207 |
uffy | +2.179 |
Neg logit contributions | |
isphere | -2.379 |
orth | -2.365 |
л | -2.311 |
enza | -2.242 |
arthed | -2.227 |
Token | , |
Token ID | 11 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
disag | +1.454 |
pleas | +1.352 |
Sah | +1.327 |
Saharan | +1.292 |
ucket | +1.288 |
Neg logit contributions | |
isphere | -1.270 |
orth | -1.243 |
л | -1.201 |
arthed | -1.186 |
enza | -1.173 |
Token | anticipating |
Token ID | 40807 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
disag | +4.794 |
pleas | +4.475 |
Sah | +4.232 |
uncons | +4.110 |
Saharan | +4.057 |
Neg logit contributions | |
isphere | -5.006 |
orth | -4.834 |
enza | -4.695 |
л | -4.694 |
arthed | -4.680 |
Token | an |
Token ID | 281 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
disag | +0.840 |
pleas | +0.775 |
Sah | +0.764 |
Saharan | +0.752 |
ucket | +0.740 |
Neg logit contributions | |
isphere | -0.812 |
orth | -0.805 |
л | -0.789 |
arthed | -0.767 |
enza | -0.758 |
Token | evening |
Token ID | 6180 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
isphere | +1.040 |
orth | +1.024 |
л | +1.004 |
arthed | +0.964 |
cliffe | +0.952 |
Neg logit contributions | |
disag | -1.299 |
Sah | -1.193 |
pleas | -1.187 |
Saharan | -1.183 |
ucket | -1.159 |
Token | of |
Token ID | 286 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
disag | +2.698 |
pleas | +2.513 |
Sah | +2.411 |
Saharan | +2.385 |
uffy | +2.372 |
Neg logit contributions | |
isphere | -2.523 |
orth | -2.513 |
л | -2.491 |
arthed | -2.404 |
cliffe | -2.386 |
Token | trick |
Token ID | 6908 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
disag | +0.240 |
pleas | +0.218 |
Sah | +0.217 |
Saharan | +0.214 |
ucket | +0.209 |
Neg logit contributions | |
isphere | -0.256 |
orth | -0.254 |
л | -0.248 |
arthed | -0.240 |
enza | -0.238 |
Token | or |
Token ID | 393 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
disag | +0.920 |
pleas | +0.858 |
Sah | +0.849 |
Saharan | +0.838 |
uffy | +0.826 |
Neg logit contributions | |
isphere | -0.762 |
orth | -0.746 |
л | -0.732 |
arthed | -0.706 |
enza | -0.700 |
Token | treating |
Token ID | 13622 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
isphere | +2.511 |
orth | +2.481 |
л | +2.373 |
cliffe | +2.260 |
arthed | +2.241 |
Neg logit contributions | |
disag | -4.110 |
Sah | -3.929 |
Saharan | -3.887 |
ucket | -3.811 |
pleas | -3.716 |
Token | ). |
Token ID | 737 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
isphere | +0.047 |
orth | +0.046 |
л | +0.045 |
arthed | +0.043 |
enza | +0.042 |
Neg logit contributions | |
disag | -0.065 |
Sah | -0.061 |
Saharan | -0.060 |
pleas | -0.060 |
ucket | -0.059 |
Token | Gl |
Token ID | 2671 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
isphere | +0.512 |
orth | +0.498 |
л | +0.478 |
arthed | +0.468 |
enza | +0.461 |
Neg logit contributions | |
disag | -0.651 |
Sah | -0.610 |
Saharan | -0.602 |
pleas | -0.598 |
ucket | -0.586 |
Token | ü |
Token ID | 9116 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
disag | +1.489 |
Sah | +1.347 |
ucket | +1.333 |
Saharan | +1.330 |
uffy | +1.329 |
Neg logit contributions | |
isphere | -2.516 |
л | -2.416 |
orth | -2.408 |
arthed | -2.361 |
cliffe | -2.314 |
Token | ck |
Token ID | 694 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
isphere | +1.986 |
orth | +1.972 |
л | +1.908 |
arthed | +1.795 |
cliffe | +1.786 |
Neg logit contributions | |
disag | -3.720 |
Sah | -3.479 |
Saharan | -3.455 |
pleas | -3.421 |
ucket | -3.372 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
disag | +4.598 |
pleas | +4.229 |
Saharan | +4.105 |
Sah | +4.082 |
ucket | +4.047 |
Neg logit contributions | |
isphere | -4.328 |
orth | -4.163 |
arthed | -4.088 |
л | -4.075 |
enza | -3.947 |
Token | much |
Token ID | 881 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
disag | +0.914 |
pleas | +0.837 |
Sah | +0.835 |
Saharan | +0.833 |
ucket | +0.810 |
Neg logit contributions | |
isphere | -0.849 |
orth | -0.837 |
л | -0.807 |
arthed | -0.796 |
enza | -0.781 |
Token | from |
Token ID | 422 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
isphere | +0.665 |
orth | +0.656 |
л | +0.636 |
arthed | +0.619 |
enza | +0.611 |
Neg logit contributions | |
disag | -0.711 |
Sah | -0.652 |
Saharan | -0.647 |
pleas | -0.646 |
ucket | -0.631 |
Token | Pl |
Token ID | 1345 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
isphere | +1.578 |
orth | +1.562 |
л | +1.518 |
arthed | +1.468 |
cliffe | +1.455 |
Neg logit contributions | |
disag | -1.615 |
Sah | -1.487 |
Saharan | -1.473 |
pleas | -1.456 |
ucket | -1.435 |
Token | ath |
Token ID | 776 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
orth | +2.844 |
isphere | +2.769 |
л | +2.588 |
enza | +2.453 |
cliffe | +2.441 |
Neg logit contributions | |
disag | -6.605 |
Sah | -6.162 |
pleas | -6.137 |
Saharan | -6.103 |
ucket | -5.933 |
Token | about |
Token ID | 546 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
isphere | +1.752 |
orth | +1.724 |
л | +1.646 |
arthed | +1.535 |
cliffe | +1.534 |
Neg logit contributions | |
disag | -3.984 |
Sah | -3.747 |
Saharan | -3.701 |
pleas | -3.677 |
uffy | -3.632 |
Token | how |
Token ID | 703 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
isphere | +1.633 |
orth | +1.615 |
л | +1.570 |
arthed | +1.516 |
cliffe | +1.503 |
Neg logit contributions | |
disag | -1.716 |
Sah | -1.582 |
Saharan | -1.567 |
pleas | -1.549 |
ucket | -1.528 |
Token | the |
Token ID | 262 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
isphere | +2.933 |
orth | +2.918 |
л | +2.833 |
arthed | +2.717 |
cliffe | +2.706 |
Neg logit contributions | |
disag | -3.380 |
Sah | -3.145 |
Saharan | -3.121 |
pleas | -3.053 |
ucket | -3.028 |
Token | charity |
Token ID | 11016 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
isphere | +2.104 |
orth | +2.081 |
л | +2.022 |
arthed | +1.953 |
cliffe | +1.935 |
Neg logit contributions | |
disag | -2.267 |
Sah | -2.091 |
Saharan | -2.072 |
pleas | -2.051 |
ucket | -2.021 |
Token | � |
Token ID | 447 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
isphere | +0.343 |
orth | +0.337 |
л | +0.328 |
arthed | +0.319 |
enza | +0.315 |
Neg logit contributions | |
disag | -0.401 |
Sah | -0.371 |
Saharan | -0.367 |
pleas | -0.367 |
ucket | -0.359 |
Token | � |
Token ID | 247 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
isphere | +0.773 |
orth | +0.767 |
л | +0.741 |
arthed | +0.715 |
cliffe | +0.711 |
Neg logit contributions | |
disag | -0.844 |
Sah | -0.784 |
Saharan | -0.778 |
pleas | -0.769 |
ucket | -0.759 |
Token | s |
Token ID | 82 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
isphere | +0.984 |
orth | +0.968 |
л | +0.940 |
arthed | +0.907 |
cliffe | +0.897 |
Neg logit contributions | |
disag | -1.227 |
Sah | -1.141 |
Saharan | -1.132 |
pleas | -1.121 |
ucket | -1.103 |
Token | obligations |
Token ID | 13675 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
isphere | +0.416 |
orth | +0.409 |
л | +0.398 |
arthed | +0.388 |
cliffe | +0.383 |
Neg logit contributions | |
disag | -0.438 |
Sah | -0.401 |
pleas | -0.398 |
Saharan | -0.398 |
ucket | -0.386 |
Token | to |
Token ID | 284 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
isphere | +0.531 |
orth | +0.524 |
л | +0.508 |
arthed | +0.492 |
enza | +0.485 |
Neg logit contributions | |
disag | -0.658 |
Sah | -0.608 |
Saharan | -0.603 |
pleas | -0.601 |
ucket | -0.590 |
Token | the |
Token ID | 262 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
isphere | +2.535 |
orth | +2.529 |
л | +2.446 |
arthed | +2.353 |
cliffe | +2.341 |
Neg logit contributions | |
disag | -2.771 |
Sah | -2.590 |
Saharan | -2.566 |
pleas | -2.516 |
ucket | -2.501 |
Token | public |
Token ID | 1171 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
isphere | +3.213 |
orth | +3.201 |
л | +3.086 |
arthed | +2.941 |
enza | +2.935 |
Neg logit contributions | |
disag | -4.336 |
Sah | -4.059 |
Saharan | -4.025 |
pleas | -3.936 |
ucket | -3.914 |
Token | during |
Token ID | 1141 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
disag | +1.140 |
pleas | +1.051 |
Sah | +1.040 |
Saharan | +1.020 |
ucket | +1.008 |
Neg logit contributions | |
isphere | -0.969 |
orth | -0.944 |
л | -0.920 |
arthed | -0.903 |
enza | -0.892 |
Token | the |
Token ID | 262 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
isphere | +2.388 |
orth | +2.369 |
л | +2.300 |
arthed | +2.222 |
cliffe | +2.205 |
Neg logit contributions | |
disag | -2.502 |
Sah | -2.312 |
Saharan | -2.289 |
pleas | -2.253 |
ucket | -2.230 |
Token | States |
Token ID | 1829 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
isphere | +0.114 |
orth | +0.112 |
л | +0.109 |
arthed | +0.105 |
cliffe | +0.103 |
Neg logit contributions | |
disag | -0.144 |
Sah | -0.134 |
Saharan | -0.132 |
pleas | -0.131 |
ucket | -0.129 |
Token | is |
Token ID | 318 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
disag | +1.206 |
Sah | +1.104 |
pleas | +1.098 |
Saharan | +1.098 |
ucket | +1.072 |
Neg logit contributions | |
isphere | -1.099 |
orth | -1.086 |
л | -1.047 |
arthed | -1.021 |
enza | -1.009 |
Token | spir |
Token ID | 9158 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
disag | +0.600 |
Sah | +0.546 |
pleas | +0.546 |
Saharan | +0.544 |
ucket | +0.526 |
Neg logit contributions | |
isphere | -0.600 |
orth | -0.590 |
л | -0.576 |
arthed | -0.560 |
cliffe | -0.554 |
Token | alling |
Token ID | 9221 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
isphere | +1.582 |
orth | +1.549 |
л | +1.457 |
enza | +1.367 |
arthed | +1.358 |
Neg logit contributions | |
disag | -3.403 |
Sah | -3.200 |
Saharan | -3.170 |
pleas | -3.156 |
ucket | -3.108 |
Token | down |
Token ID | 866 |
Feature activation | +5.82e-03 |
Pos logit contributions | |
isphere | +0.763 |
orth | +0.755 |
л | +0.734 |
arthed | +0.712 |
cliffe | +0.705 |
Neg logit contributions | |
disag | -0.743 |
Sah | -0.681 |
Saharan | -0.675 |
pleas | -0.669 |
ucket | -0.656 |
Token | into |
Token ID | 656 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
isphere | +0.049 |
orth | +0.049 |
л | +0.047 |
arthed | +0.046 |
cliffe | +0.045 |
Neg logit contributions | |
disag | -0.051 |
Sah | -0.047 |
Saharan | -0.046 |
pleas | -0.046 |
ucket | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
disag | +0.763 |
Sah | +0.694 |
pleas | +0.687 |
Saharan | +0.686 |
ucket | +0.666 |
Neg logit contributions | |
isphere | -0.785 |
orth | -0.777 |
л | -0.758 |
arthed | -0.735 |
cliffe | -0.729 |
Token | basic |
Token ID | 4096 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
disag | +0.419 |
Sah | +0.383 |
pleas | +0.379 |
Saharan | +0.378 |
ucket | +0.367 |
Neg logit contributions | |
isphere | -0.401 |
orth | -0.396 |
л | -0.386 |
arthed | -0.377 |
cliffe | -0.372 |
Token | indec |
Token ID | 29077 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
disag | +0.617 |
Sah | +0.560 |
Saharan | +0.555 |
pleas | +0.555 |
ucket | +0.541 |
Neg logit contributions | |
isphere | -0.556 |
orth | -0.544 |
л | -0.532 |
arthed | -0.529 |
cliffe | -0.514 |
Token | ency |
Token ID | 1387 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
disag | +0.668 |
Sah | +0.603 |
Saharan | +0.600 |
pleas | +0.591 |
ucket | +0.584 |
Neg logit contributions | |
isphere | -0.812 |
orth | -0.802 |
л | -0.786 |
arthed | -0.767 |
cliffe | -0.756 |
Token | and |
Token ID | 290 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
isphere | +2.764 |
orth | +2.731 |
л | +2.641 |
enza | +2.528 |
arthed | +2.520 |
Neg logit contributions | |
disag | -3.159 |
Sah | -2.950 |
Saharan | -2.923 |
pleas | -2.861 |
ucket | -2.856 |
Token | but |
Token ID | 475 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
isphere | +1.201 |
orth | +1.184 |
л | +1.146 |
arthed | +1.108 |
enza | +1.094 |
Neg logit contributions | |
disag | -1.565 |
Sah | -1.451 |
Saharan | -1.438 |
pleas | -1.433 |
ucket | -1.406 |
Token | respecting |
Token ID | 30796 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
isphere | +1.964 |
orth | +1.943 |
л | +1.886 |
arthed | +1.813 |
cliffe | +1.804 |
Neg logit contributions | |
disag | -2.256 |
Sah | -2.089 |
Saharan | -2.075 |
pleas | -2.041 |
ucket | -2.024 |
Token | them |
Token ID | 606 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
disag | +2.337 |
pleas | +2.187 |
Sah | +2.150 |
Saharan | +2.084 |
uffy | +2.063 |
Neg logit contributions | |
isphere | -2.416 |
orth | -2.377 |
arthed | -2.317 |
л | -2.305 |
enza | -2.270 |
Token | in |
Token ID | 287 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
disag | +0.970 |
pleas | +0.894 |
Sah | +0.889 |
Saharan | +0.875 |
uffy | +0.856 |
Neg logit contributions | |
isphere | -0.892 |
orth | -0.876 |
arthed | -0.853 |
л | -0.852 |
enza | -0.824 |
Token | their |
Token ID | 511 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
disag | +0.057 |
Sah | +0.052 |
pleas | +0.052 |
Saharan | +0.052 |
ucket | +0.051 |
Neg logit contributions | |
isphere | -0.055 |
orth | -0.054 |
л | -0.052 |
arthed | -0.051 |
enza | -0.051 |
Token | choice |
Token ID | 3572 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
isphere | +1.455 |
orth | +1.437 |
л | +1.397 |
arthed | +1.358 |
enza | +1.342 |
Neg logit contributions | |
disag | -1.652 |
Sah | -1.520 |
pleas | -1.510 |
Saharan | -1.503 |
ucket | -1.467 |
Token | not |
Token ID | 407 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
isphere | +0.512 |
orth | +0.507 |
л | +0.491 |
arthed | +0.480 |
cliffe | +0.471 |
Neg logit contributions | |
disag | -0.601 |
Sah | -0.556 |
pleas | -0.550 |
Saharan | -0.550 |
ucket | -0.539 |
Token | to |
Token ID | 284 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
disag | +2.899 |
pleas | +2.670 |
Sah | +2.654 |
Saharan | +2.632 |
ucket | +2.585 |
Neg logit contributions | |
isphere | -2.649 |
orth | -2.614 |
л | -2.554 |
arthed | -2.477 |
cliffe | -2.441 |
Token | talk |
Token ID | 1561 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
isphere | +1.452 |
orth | +1.436 |
л | +1.402 |
arthed | +1.362 |
cliffe | +1.344 |
Neg logit contributions | |
disag | -1.318 |
Sah | -1.197 |
Saharan | -1.182 |
pleas | -1.181 |
ucket | -1.151 |
Token | is |
Token ID | 318 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
disag | +2.225 |
pleas | +2.037 |
Sah | +1.992 |
Saharan | +1.970 |
ucket | +1.941 |
Neg logit contributions | |
isphere | -2.111 |
orth | -2.067 |
л | -2.035 |
arthed | -2.006 |
enza | -1.959 |
Token | more |
Token ID | 517 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
disag | +2.807 |
pleas | +2.623 |
Sah | +2.535 |
Saharan | +2.494 |
uncons | +2.464 |
Neg logit contributions | |
isphere | -2.740 |
orth | -2.640 |
arthed | -2.607 |
л | -2.597 |
enza | -2.507 |
Token | that |
Token ID | 326 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
disag | +1.921 |
Sah | +1.752 |
Saharan | +1.735 |
pleas | +1.714 |
ucket | +1.679 |
Neg logit contributions | |
isphere | -2.054 |
orth | -2.011 |
л | -1.967 |
arthed | -1.916 |
enza | -1.904 |
Token | if |
Token ID | 611 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
disag | +1.556 |
Sah | +1.420 |
Saharan | +1.406 |
pleas | +1.391 |
ucket | +1.347 |
Neg logit contributions | |
isphere | -1.520 |
orth | -1.488 |
л | -1.465 |
arthed | -1.417 |
enza | -1.405 |
Token | all |
Token ID | 477 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
isphere | +0.476 |
orth | +0.470 |
л | +0.458 |
arthed | +0.442 |
cliffe | +0.438 |
Neg logit contributions | |
disag | -0.495 |
Sah | -0.456 |
Saharan | -0.452 |
pleas | -0.447 |
ucket | -0.439 |
Token | the |
Token ID | 262 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
isphere | +1.493 |
orth | +1.477 |
л | +1.435 |
arthed | +1.387 |
cliffe | +1.375 |
Neg logit contributions | |
disag | -1.569 |
Sah | -1.446 |
Saharan | -1.432 |
pleas | -1.417 |
ucket | -1.396 |
Token | 63 |
Token ID | 8093 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
disag | +1.962 |
Sah | +1.772 |
pleas | +1.750 |
Saharan | +1.732 |
uffy | +1.664 |
Neg logit contributions | |
isphere | -2.020 |
orth | -1.994 |
л | -1.956 |
enza | -1.896 |
arthed | -1.887 |
Token | , |
Token ID | 11 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
disag | +3.711 |
Sah | +3.405 |
Saharan | +3.349 |
pleas | +3.315 |
ucket | +3.210 |
Neg logit contributions | |
isphere | -3.802 |
orth | -3.736 |
л | -3.668 |
arthed | -3.606 |
enza | -3.591 |
Token | 511 |
Token ID | 41647 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
disag | +5.143 |
Sah | +4.707 |
pleas | +4.652 |
Saharan | +4.617 |
uffy | +4.529 |
Neg logit contributions | |
isphere | -6.314 |
orth | -6.093 |
л | -5.947 |
cliffe | -5.778 |
arthed | -5.773 |
Token | coaches |
Token ID | 11070 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
disag | +3.444 |
Sah | +3.166 |
pleas | +3.117 |
Saharan | +3.105 |
ucket | +2.996 |
Neg logit contributions | |
isphere | -3.514 |
orth | -3.480 |
л | -3.385 |
arthed | -3.345 |
enza | -3.325 |
Token | under |
Token ID | 739 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
disag | +3.474 |
Sah | +3.116 |
pleas | +3.107 |
Saharan | +3.095 |
ucket | +3.025 |
Neg logit contributions | |
isphere | -3.505 |
orth | -3.490 |
л | -3.463 |
arthed | -3.351 |
enza | -3.272 |
Token | operation |
Token ID | 4905 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
disag | +1.908 |
Sah | +1.740 |
Saharan | +1.729 |
pleas | +1.689 |
uffy | +1.639 |
Neg logit contributions | |
isphere | -2.023 |
orth | -1.982 |
л | -1.940 |
enza | -1.879 |
arthed | -1.850 |
Token | are |
Token ID | 389 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
disag | +1.933 |
Sah | +1.754 |
Saharan | +1.741 |
pleas | +1.737 |
ucket | +1.693 |
Neg logit contributions | |
isphere | -1.901 |
orth | -1.882 |
л | -1.851 |
arthed | -1.782 |
cliffe | -1.755 |
Token | the |
Token ID | 262 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
disag | +2.734 |
Sah | +2.495 |
Saharan | +2.474 |
pleas | +2.473 |
ucket | +2.389 |
Neg logit contributions | |
isphere | -2.927 |
orth | -2.844 |
л | -2.780 |
arthed | -2.701 |
enza | -2.678 |
Token | day |
Token ID | 1110 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
disag | +2.052 |
Sah | +1.869 |
pleas | +1.868 |
Saharan | +1.853 |
ucket | +1.787 |
Neg logit contributions | |
isphere | -1.882 |
orth | -1.838 |
л | -1.784 |
arthed | -1.737 |
cliffe | -1.722 |
Token | a |
Token ID | 257 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
isphere | +0.688 |
orth | +0.683 |
л | +0.660 |
arthed | +0.632 |
cliffe | +0.629 |
Neg logit contributions | |
disag | -0.898 |
Sah | -0.836 |
Saharan | -0.829 |
pleas | -0.814 |
ucket | -0.809 |
Token | man |
Token ID | 582 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
disag | +4.259 |
pleas | +3.930 |
Sah | +3.847 |
Saharan | +3.809 |
ucket | +3.656 |
Neg logit contributions | |
isphere | -4.390 |
orth | -4.215 |
л | -4.160 |
arthed | -4.089 |
enza | -3.975 |
Token | was |
Token ID | 373 |
Feature activation | -9.83e-03 |
Pos logit contributions | |
disag | +1.477 |
pleas | +1.361 |
Sah | +1.349 |
Saharan | +1.331 |
ucket | +1.304 |
Neg logit contributions | |
isphere | -1.366 |
orth | -1.345 |
л | -1.320 |
arthed | -1.286 |
enza | -1.257 |
Token | pronounced |
Token ID | 16293 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
disag | +0.099 |
Sah | +0.092 |
pleas | +0.091 |
Saharan | +0.091 |
ucket | +0.089 |
Neg logit contributions | |
isphere | -0.070 |
orth | -0.069 |
л | -0.067 |
arthed | -0.064 |
enza | -0.063 |
Token | dead |
Token ID | 2636 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
disag | +5.100 |
pleas | +4.907 |
uncons | +4.511 |
Sah | +4.424 |
Saharan | +4.319 |
Neg logit contributions | |
isphere | -8.964 |
arthed | -8.627 |
л | -8.563 |
orth | -8.556 |
rity | -8.369 |
Token | after |
Token ID | 706 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
disag | +2.467 |
pleas | +2.280 |
Sah | +2.251 |
Saharan | +2.220 |
uffy | +2.167 |
Neg logit contributions | |
isphere | -2.237 |
orth | -2.175 |
arthed | -2.105 |
л | -2.104 |
enza | -2.039 |
Token | he |
Token ID | 339 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
isphere | +0.926 |
orth | +0.914 |
л | +0.886 |
arthed | +0.853 |
cliffe | +0.843 |
Neg logit contributions | |
disag | -1.183 |
Sah | -1.098 |
Saharan | -1.088 |
pleas | -1.080 |
ucket | -1.063 |
Token | was |
Token ID | 373 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
isphere | +2.279 |
orth | +2.260 |
л | +2.187 |
arthed | +2.098 |
cliffe | +2.094 |
Neg logit contributions | |
disag | -2.725 |
Sah | -2.528 |
Saharan | -2.510 |
pleas | -2.467 |
ucket | -2.455 |
Token | shot |
Token ID | 2823 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
isphere | +1.583 |
orth | +1.567 |
л | +1.507 |
arthed | +1.441 |
cliffe | +1.429 |
Neg logit contributions | |
disag | -2.508 |
Sah | -2.346 |
Saharan | -2.329 |
pleas | -2.301 |
ucket | -2.281 |
Token | and |
Token ID | 290 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
disag | +4.454 |
Sah | +4.194 |
pleas | +4.176 |
Saharan | +4.110 |
uffy | +4.034 |
Neg logit contributions | |
isphere | -3.849 |
orth | -3.753 |
л | -3.638 |
arthed | -3.569 |
enza | -3.531 |
Token | Producer |
Token ID | 30436 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
disag | +3.781 |
Sah | +3.555 |
pleas | +3.507 |
Saharan | +3.487 |
uffy | +3.393 |
Neg logit contributions | |
isphere | -4.117 |
orth | -3.967 |
л | -3.845 |
enza | -3.745 |
arthed | -3.698 |
Token | , |
Token ID | 11 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
disag | +3.302 |
pleas | +3.057 |
Sah | +3.046 |
Saharan | +2.997 |
uffy | +2.921 |
Neg logit contributions | |
isphere | -3.330 |
orth | -3.304 |
л | -3.177 |
arthed | -3.112 |
enza | -3.109 |
Token |
|
Token ID | 198 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
disag | +1.821 |
Sah | +1.666 |
pleas | +1.637 |
Saharan | +1.633 |
uffy | +1.570 |
Neg logit contributions | |
isphere | -2.584 |
orth | -2.551 |
л | -2.461 |
enza | -2.420 |
arthed | -2.409 |
Token |
|
Token ID | 198 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
disag | +0.222 |
Sah | +0.211 |
Saharan | +0.209 |
pleas | +0.207 |
ucket | +0.202 |
Neg logit contributions | |
isphere | -0.161 |
orth | -0.156 |
л | -0.151 |
arthed | -0.146 |
enza | -0.145 |
Token | DA |
Token ID | 5631 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
Sah | +3.197 |
disag | +3.155 |
Saharan | +3.082 |
pleas | +2.944 |
uffy | +2.892 |
Neg logit contributions | |
isphere | -3.972 |
orth | -3.856 |
л | -3.726 |
enza | -3.718 |
liner | -3.701 |
Token | VID |
Token ID | 11008 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
Sah | +3.632 |
DAV | +3.498 |
disag | +3.462 |
pleas | +3.459 |
Saharan | +3.370 |
Neg logit contributions | |
isphere | -8.888 |
orth | -8.505 |
enza | -8.283 |
cliffe | -8.239 |
rity | -8.142 |
Token | SL |
Token ID | 12419 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
orth | +3.436 |
isphere | +3.403 |
л | +3.400 |
cliffe | +3.146 |
arthed | +3.135 |
Neg logit contributions | |
disag | -4.131 |
Sah | -3.808 |
Saharan | -3.801 |
ucket | -3.747 |
pleas | -3.678 |
Token | ACK |
Token ID | 8120 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
disag | +0.235 |
Sah | +0.222 |
Saharan | +0.220 |
pleas | +0.216 |
ucket | +0.214 |
Neg logit contributions | |
isphere | -0.211 |
orth | -0.204 |
л | -0.195 |
arthed | -0.193 |
enza | -0.193 |
Token |
|
Token ID | 198 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
disag | +1.026 |
Sah | +0.956 |
pleas | +0.945 |
Saharan | +0.944 |
ucket | +0.925 |
Neg logit contributions | |
isphere | -0.763 |
orth | -0.744 |
л | -0.712 |
arthed | -0.692 |
enza | -0.692 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
isphere | +0.207 |
orth | +0.202 |
л | +0.195 |
arthed | +0.188 |
enza | +0.186 |
Neg logit contributions | |
disag | -0.304 |
Sah | -0.286 |
Saharan | -0.283 |
pleas | -0.281 |
ucket | -0.276 |
Token | own |
Token ID | 898 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
disag | +6.611 |
pleas | +6.391 |
Sah | +6.190 |
Saharan | +6.119 |
ucket | +5.800 |
Neg logit contributions | |
isphere | -8.196 |
enza | -7.815 |
orth | -7.733 |
arthed | -7.710 |
л | -7.652 |
Token | best |
Token ID | 1266 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
disag | +4.650 |
pleas | +4.566 |
Sah | +3.973 |
uncons | +3.780 |
uffy | +3.719 |
Neg logit contributions | |
isphere | -10.573 |
arthed | -9.850 |
orth | -9.828 |
enza | -9.690 |
cliffe | -9.665 |
Token | selling |
Token ID | 6301 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
disag | +3.125 |
pleas | +2.870 |
Sah | +2.672 |
uffy | +2.585 |
Saharan | +2.570 |
Neg logit contributions | |
isphere | -7.934 |
orth | -7.668 |
л | -7.604 |
enza | -7.520 |
irc | -7.479 |
Token | Kindle |
Token ID | 27114 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
disag | +3.037 |
pleas | +2.837 |
Sah | +2.699 |
Saharan | +2.610 |
uffy | +2.471 |
Neg logit contributions | |
isphere | -10.113 |
orth | -9.841 |
rity | -9.790 |
arthed | -9.684 |
л | -9.446 |
Token | book |
Token ID | 1492 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
disag | +2.867 |
pleas | +2.470 |
Sah | +2.215 |
Saharan | +2.020 |
uffy | +1.943 |
Neg logit contributions | |
isphere | -10.910 |
orth | -10.384 |
arthed | -10.304 |
rity | -10.303 |
л | -10.271 |
Token | . |
Token ID | 13 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
disag | +4.188 |
Sah | +4.158 |
pleas | +3.985 |
Saharan | +3.971 |
ucket | +3.783 |
Neg logit contributions | |
isphere | -4.735 |
orth | -4.529 |
enza | -4.380 |
arthed | -4.368 |
rity | -4.283 |
Token | We |
Token ID | 775 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
disag | +4.482 |
Sah | +4.450 |
pleas | +4.358 |
Saharan | +4.110 |
ucket | +3.890 |
Neg logit contributions | |
isphere | -8.368 |
orth | -8.088 |
enza | -7.804 |
arthed | -7.801 |
bey | -7.692 |
Token | � |
Token ID | 447 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
isphere | +1.357 |
orth | +1.343 |
л | +1.303 |
arthed | +1.254 |
cliffe | +1.242 |
Neg logit contributions | |
disag | -1.710 |
Sah | -1.582 |
Saharan | -1.575 |
pleas | -1.555 |
ucket | -1.535 |
Token | � |
Token ID | 247 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
disag | +2.671 |
Sah | +2.548 |
Saharan | +2.514 |
ucket | +2.508 |
pleas | +2.481 |
Neg logit contributions | |
orth | -3.205 |
isphere | -3.177 |
л | -3.014 |
cliffe | -2.940 |
bey | -2.899 |
Token | ll |
Token ID | 297 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
disag | +1.599 |
Sah | +1.484 |
pleas | +1.479 |
ucket | +1.460 |
Saharan | +1.451 |
Neg logit contributions | |
isphere | -1.439 |
orth | -1.394 |
л | -1.344 |
arthed | -1.310 |
enza | -1.290 |
Token | announce |
Token ID | 5453 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
disag | +6.122 |
Sah | +5.254 |
pleas | +5.065 |
Saharan | +5.001 |
uffy | +4.859 |
Neg logit contributions | |
isphere | -11.599 |
orth | -11.301 |
cliffe | -10.741 |
enza | -10.738 |
л | -10.725 |
Token | racist |
Token ID | 9811 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
disag | +4.746 |
pleas | +4.375 |
Sah | +4.266 |
Saharan | +4.130 |
uffy | +4.116 |
Neg logit contributions | |
isphere | -4.690 |
orth | -4.576 |
л | -4.371 |
arthed | -4.366 |
enza | -4.271 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
disag | +2.630 |
Sah | +2.414 |
pleas | +2.410 |
Saharan | +2.364 |
uffy | +2.317 |
Neg logit contributions | |
isphere | -2.257 |
orth | -2.219 |
arthed | -2.122 |
л | -2.121 |
enza | -2.072 |
Token | Flag |
Token ID | 19762 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
disag | +2.119 |
Sah | +1.978 |
pleas | +1.963 |
Saharan | +1.944 |
ucket | +1.874 |
Neg logit contributions | |
isphere | -1.983 |
orth | -1.933 |
л | -1.854 |
arthed | -1.853 |
enza | -1.812 |
Token |
|
Token ID | 198 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
disag | +4.207 |
Sah | +4.002 |
Saharan | +3.949 |
pleas | +3.901 |
ucket | +3.830 |
Neg logit contributions | |
isphere | -3.427 |
orth | -3.352 |
л | -3.210 |
arthed | -3.206 |
enza | -3.164 |
Token |
|
Token ID | 198 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
disag | +3.643 |
Sah | +3.546 |
Saharan | +3.501 |
pleas | +3.485 |
uffy | +3.307 |
Neg logit contributions | |
isphere | -3.497 |
orth | -3.262 |
arthed | -3.196 |
л | -3.183 |
enza | -3.112 |
Token | Flag |
Token ID | 34227 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Sah | +3.681 |
Saharan | +3.586 |
disag | +3.279 |
ucket | +3.047 |
pleas | +3.042 |
Neg logit contributions | |
isphere | -8.098 |
liner | -7.798 |
arthed | -7.742 |
orth | -7.718 |
rity | -7.580 |
Token | Reply |
Token ID | 14883 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
disag | +4.334 |
pleas | +3.952 |
Sah | +3.704 |
Saharan | +3.632 |
uncons | +3.197 |
Neg logit contributions | |
isphere | -14.469 |
orth | -14.332 |
arthed | -14.166 |
enza | -13.805 |
rity | -13.685 |
Token |
|
Token ID | 198 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
disag | +2.659 |
Sah | +2.523 |
Saharan | +2.499 |
pleas | +2.496 |
ucket | +2.411 |
Neg logit contributions | |
isphere | -2.126 |
orth | -2.044 |
л | -1.974 |
arthed | -1.943 |
enza | -1.895 |
Token |
|
Token ID | 198 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
disag | +2.570 |
Sah | +2.477 |
Saharan | +2.446 |
pleas | +2.433 |
uffy | +2.327 |
Neg logit contributions | |
isphere | -2.231 |
orth | -2.094 |
л | -2.040 |
arthed | -2.039 |
enza | -1.982 |
Token | 19 |
Token ID | 1129 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
Sah | +3.222 |
disag | +3.209 |
Saharan | +3.117 |
pleas | +3.017 |
ucket | +2.907 |
Neg logit contributions | |
isphere | -3.585 |
orth | -3.369 |
arthed | -3.325 |
л | -3.257 |
cliffe | -3.256 |
Token | Recommend |
Token ID | 30361 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
disag | +4.146 |
Sah | +3.705 |
Saharan | +3.622 |
pleas | +3.580 |
uffy | +3.258 |
Neg logit contributions | |
isphere | -10.733 |
arthed | -10.087 |
enza | -9.983 |
orth | -9.972 |
rity | -9.895 |