Token | scrap |
Token ID | 15881 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
emetery | +0.178 |
ospel | +0.176 |
vernment | +0.172 |
ppa | +0.171 |
appa | +0.163 |
Neg logit contributions | |
Frie | -0.185 |
spir | -0.179 |
Male | -0.169 |
AAA | -0.165 |
UCHIJ | -0.162 |
Token | . |
Token ID | 13 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
emetery | +0.296 |
ospel | +0.293 |
vernment | +0.286 |
ppa | +0.286 |
appa | +0.273 |
Neg logit contributions | |
Frie | -0.300 |
spir | -0.290 |
Male | -0.275 |
AAA | -0.267 |
querque | -0.263 |
Token |
|
Token ID | 198 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Frie | +0.502 |
spir | +0.482 |
Male | +0.456 |
AAA | +0.449 |
UCHIJ | +0.437 |
Neg logit contributions | |
emetery | -0.501 |
ospel | -0.493 |
vernment | -0.481 |
ppa | -0.478 |
appa | -0.457 |
Token |
|
Token ID | 198 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
emetery | +0.321 |
ospel | +0.320 |
ppa | +0.312 |
vernment | +0.311 |
appa | +0.298 |
Neg logit contributions | |
Frie | -0.330 |
spir | -0.315 |
Male | -0.297 |
AAA | -0.291 |
querque | -0.290 |
Token | Article |
Token ID | 14906 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
emetery | +0.127 |
ospel | +0.126 |
vernment | +0.124 |
ppa | +0.123 |
appa | +0.118 |
Neg logit contributions | |
Frie | -0.111 |
spir | -0.106 |
Male | -0.100 |
AAA | -0.098 |
UCHIJ | -0.096 |
Token | Continued |
Token ID | 22168 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
Frie | +3.501 |
spir | +3.413 |
Male | +3.207 |
AAA | +3.165 |
UCHIJ | +3.093 |
Neg logit contributions | |
emetery | -2.931 |
ospel | -2.852 |
vernment | -2.822 |
ppa | -2.733 |
appa | -2.609 |
Token | Below |
Token ID | 10383 |
Feature activation | +6.67e+00 |
Pos logit contributions | |
spir | +2.855 |
Frie | +2.552 |
Male | +2.280 |
AAA | +2.264 |
UCHIJ | +1.925 |
Neg logit contributions | |
emetery | -13.241 |
vernment | -13.035 |
ailability | -12.930 |
ospel | -12.698 |
jri | -12.501 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
spir | +4.196 |
Frie | +4.133 |
Male | +3.939 |
AAA | +3.892 |
UCHIJ | +3.719 |
Neg logit contributions | |
emetery | -6.079 |
vernment | -5.856 |
ospel | -5.791 |
ppa | -5.567 |
ailability | -5.563 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ospel | +1.049 |
emetery | +1.045 |
ppa | +1.025 |
vernment | +1.013 |
appa | +0.975 |
Neg logit contributions | |
Frie | -1.133 |
spir | -1.074 |
Male | -1.015 |
querque | -1.014 |
AAA | -0.993 |
Token | The |
Token ID | 464 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
emetery | +1.245 |
ospel | +1.241 |
ppa | +1.218 |
vernment | +1.214 |
appa | +1.166 |
Neg logit contributions | |
Frie | -1.050 |
spir | -0.990 |
Male | -0.922 |
AAA | -0.912 |
querque | -0.911 |
Token | T |
Token ID | 309 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
emetery | +1.056 |
ospel | +1.050 |
vernment | +1.030 |
ppa | +1.024 |
appa | +0.979 |
Neg logit contributions | |
Frie | -1.134 |
spir | -1.096 |
Male | -1.043 |
AAA | -1.003 |
querque | -0.998 |
Token | last |
Token ID | 938 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
emetery | +1.029 |
ospel | +1.016 |
vernment | +0.989 |
ppa | +0.985 |
appa | +0.935 |
Neg logit contributions | |
Frie | -1.249 |
spir | -1.202 |
Male | -1.144 |
AAA | -1.123 |
UCHIJ | -1.101 |
Token | . |
Token ID | 13 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
Frie | +0.675 |
spir | +0.642 |
Male | +0.610 |
AAA | +0.604 |
querque | +0.583 |
Neg logit contributions | |
emetery | -0.672 |
ospel | -0.662 |
vernment | -0.641 |
ppa | -0.640 |
appa | -0.611 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Frie | +0.305 |
spir | +0.293 |
Male | +0.277 |
AAA | +0.272 |
UCHIJ | +0.265 |
Neg logit contributions | |
emetery | -0.313 |
ospel | -0.307 |
vernment | -0.300 |
ppa | -0.298 |
appa | -0.286 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ospel | +1.110 |
emetery | +1.099 |
ppa | +1.089 |
vernment | +1.070 |
appa | +1.033 |
Neg logit contributions | |
Frie | -1.242 |
spir | -1.170 |
querque | -1.126 |
Male | -1.105 |
AAA | -1.083 |
Token | Article |
Token ID | 14906 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
emetery | +1.132 |
ospel | +1.127 |
ppa | +1.102 |
vernment | +1.099 |
appa | +1.048 |
Neg logit contributions | |
Frie | -1.180 |
spir | -1.126 |
Male | -1.061 |
AAA | -1.050 |
querque | -1.040 |
Token | Continued |
Token ID | 22168 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
Frie | +0.448 |
spir | +0.433 |
Male | +0.412 |
AAA | +0.404 |
UCHIJ | +0.397 |
Neg logit contributions | |
emetery | -0.344 |
ospel | -0.339 |
vernment | -0.330 |
ppa | -0.329 |
appa | -0.312 |
Token | Below |
Token ID | 10383 |
Feature activation | +6.76e+00 |
Pos logit contributions | |
spir | +2.754 |
Frie | +2.387 |
Male | +2.122 |
AAA | +2.101 |
UCHIJ | +1.686 |
Neg logit contributions | |
emetery | -13.104 |
vernment | -12.894 |
ailability | -12.750 |
ospel | -12.639 |
jri | -12.322 |
Token |
|
Token ID | 198 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
spir | +4.191 |
Frie | +4.104 |
Male | +3.946 |
AAA | +3.881 |
UCHIJ | +3.695 |
Neg logit contributions | |
emetery | -6.226 |
vernment | -5.998 |
ospel | -5.941 |
ailability | -5.767 |
ppa | -5.684 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
emetery | +0.624 |
ospel | +0.622 |
ppa | +0.607 |
vernment | +0.604 |
appa | +0.578 |
Neg logit contributions | |
Frie | -0.644 |
spir | -0.615 |
Male | -0.581 |
querque | -0.569 |
AAA | -0.569 |
Token | T |
Token ID | 51 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
emetery | +0.970 |
ospel | +0.966 |
ppa | +0.944 |
vernment | +0.944 |
appa | +0.904 |
Neg logit contributions | |
Frie | -0.840 |
spir | -0.799 |
Male | -0.749 |
AAA | -0.737 |
querque | -0.729 |
Token | od |
Token ID | 375 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Frie | +0.999 |
spir | +0.975 |
Male | +0.914 |
AAA | +0.890 |
UCHIJ | +0.865 |
Neg logit contributions | |
emetery | -1.047 |
ospel | -1.035 |
vernment | -1.018 |
ppa | -1.015 |
appa | -0.963 |
Token | mess |
Token ID | 2085 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Frie | +0.462 |
spir | +0.445 |
Male | +0.421 |
AAA | +0.412 |
UCHIJ | +0.403 |
Neg logit contributions | |
emetery | -0.456 |
ospel | -0.451 |
vernment | -0.440 |
ppa | -0.438 |
appa | -0.419 |
Token | seriously |
Token ID | 6411 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
emetery | +1.053 |
ospel | +1.041 |
vernment | +1.015 |
ppa | +1.008 |
appa | +0.953 |
Neg logit contributions | |
Frie | -1.557 |
spir | -1.499 |
Male | -1.433 |
AAA | -1.406 |
UCHIJ | -1.390 |
Token |
|
Token ID | 198 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
emetery | +2.070 |
ospel | +2.056 |
ppa | +2.017 |
vernment | +2.016 |
appa | +1.914 |
Neg logit contributions | |
Frie | -2.161 |
spir | -2.088 |
Male | -1.973 |
querque | -1.921 |
AAA | -1.914 |
Token |
|
Token ID | 198 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
ospel | +1.892 |
emetery | +1.874 |
ppa | +1.869 |
vernment | +1.823 |
appa | +1.767 |
Neg logit contributions | |
Frie | -2.146 |
spir | -2.022 |
querque | -1.960 |
Male | -1.910 |
AAA | -1.875 |
Token | Article |
Token ID | 14906 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
emetery | +1.485 |
ospel | +1.474 |
ppa | +1.445 |
vernment | +1.433 |
appa | +1.358 |
Neg logit contributions | |
Frie | -1.986 |
spir | -1.894 |
Male | -1.796 |
AAA | -1.780 |
querque | -1.772 |
Token | Continued |
Token ID | 22168 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
Frie | +3.416 |
spir | +3.361 |
Male | +3.124 |
AAA | +3.087 |
UCHIJ | +3.006 |
Neg logit contributions | |
emetery | -3.031 |
vernment | -2.942 |
ospel | -2.925 |
ppa | -2.791 |
jri | -2.695 |
Token | Below |
Token ID | 10383 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
spir | +2.899 |
Frie | +2.651 |
Male | +2.352 |
AAA | +2.339 |
UCHIJ | +2.036 |
Neg logit contributions | |
emetery | -12.853 |
vernment | -12.761 |
ailability | -12.470 |
ospel | -12.431 |
jri | -12.179 |
Token |
|
Token ID | 198 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
spir | +4.077 |
Frie | +4.049 |
Male | +3.851 |
AAA | +3.790 |
UCHIJ | +3.630 |
Neg logit contributions | |
emetery | -5.805 |
vernment | -5.591 |
ospel | -5.559 |
ppa | -5.333 |
ailability | -5.277 |
Token |
|
Token ID | 198 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
emetery | +0.287 |
ospel | +0.285 |
ppa | +0.278 |
vernment | +0.278 |
appa | +0.265 |
Neg logit contributions | |
Frie | -0.288 |
spir | -0.276 |
Male | -0.261 |
AAA | -0.255 |
querque | -0.253 |
Token | � |
Token ID | 447 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
emetery | +0.438 |
ospel | +0.434 |
ppa | +0.425 |
vernment | +0.425 |
appa | +0.407 |
Neg logit contributions | |
Frie | -0.344 |
spir | -0.327 |
Male | -0.306 |
AAA | -0.299 |
querque | -0.294 |
Token | � |
Token ID | 250 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
emetery | +0.935 |
ospel | +0.923 |
vernment | +0.910 |
ppa | +0.906 |
appa | +0.868 |
Neg logit contributions | |
Frie | -0.744 |
spir | -0.709 |
Male | -0.665 |
AAA | -0.647 |
UCHIJ | -0.637 |
Token | pell |
Token ID | 23506 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Frie | +0.295 |
spir | +0.281 |
Male | +0.264 |
AAA | +0.257 |
querque | +0.253 |
Neg logit contributions | |
emetery | -0.399 |
ospel | -0.395 |
ppa | -0.389 |
vernment | -0.386 |
appa | -0.373 |
Token | . |
Token ID | 13 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
Frie | +0.810 |
spir | +0.778 |
Male | +0.738 |
AAA | +0.718 |
querque | +0.708 |
Neg logit contributions | |
emetery | -0.797 |
ospel | -0.790 |
ppa | -0.771 |
vernment | -0.771 |
appa | -0.736 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Frie | +0.723 |
spir | +0.697 |
Male | +0.659 |
AAA | +0.647 |
UCHIJ | +0.627 |
Neg logit contributions | |
emetery | -0.755 |
ospel | -0.741 |
vernment | -0.724 |
ppa | -0.719 |
appa | -0.690 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
emetery | +0.089 |
ospel | +0.088 |
ppa | +0.086 |
vernment | +0.086 |
appa | +0.082 |
Neg logit contributions | |
Frie | -0.090 |
spir | -0.086 |
Male | -0.081 |
AAA | -0.080 |
querque | -0.079 |
Token | Story |
Token ID | 11605 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
Frie | +0.089 |
spir | +0.085 |
Male | +0.081 |
AAA | +0.079 |
UCHIJ | +0.077 |
Neg logit contributions | |
emetery | -0.092 |
ospel | -0.090 |
vernment | -0.088 |
ppa | -0.088 |
appa | -0.084 |
Token | continues |
Token ID | 4477 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
spir | +2.822 |
Frie | +2.793 |
Male | +2.554 |
AAA | +2.496 |
UCHIJ | +2.386 |
Neg logit contributions | |
emetery | -4.457 |
ospel | -4.345 |
vernment | -4.305 |
ppa | -4.178 |
appa | -4.076 |
Token | below |
Token ID | 2174 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
spir | +4.226 |
Frie | +3.940 |
AAA | +3.892 |
Male | +3.802 |
UCHIJ | +3.527 |
Neg logit contributions | |
emetery | -10.912 |
ospel | -10.539 |
vernment | -10.525 |
ailability | -10.393 |
ppa | -10.278 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
Frie | +5.208 |
spir | +5.157 |
AAA | +5.065 |
Male | +4.986 |
UCHIJ | +4.791 |
Neg logit contributions | |
emetery | -3.163 |
ospel | -3.058 |
vernment | -2.946 |
ppa | -2.837 |
appa | -2.672 |
Token |
|
Token ID | 198 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
spir | +2.501 |
Frie | +2.486 |
Male | +2.357 |
AAA | +2.308 |
UCHIJ | +2.209 |
Neg logit contributions | |
emetery | -3.315 |
ospel | -3.177 |
vernment | -3.176 |
ppa | -3.063 |
jri | -2.983 |
Token |
|
Token ID | 198 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
ospel | +0.652 |
emetery | +0.649 |
ppa | +0.637 |
vernment | +0.629 |
appa | +0.606 |
Neg logit contributions | |
Frie | -0.707 |
spir | -0.669 |
querque | -0.634 |
Male | -0.632 |
AAA | -0.619 |
Token | " |
Token ID | 1 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
emetery | +0.645 |
ospel | +0.640 |
ppa | +0.626 |
vernment | +0.625 |
appa | +0.599 |
Neg logit contributions | |
Frie | -0.590 |
spir | -0.560 |
Male | -0.526 |
AAA | -0.519 |
querque | -0.513 |
Token | keeper |
Token ID | 13884 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Frie | +1.283 |
spir | +1.257 |
Male | +1.204 |
AAA | +1.177 |
UCHIJ | +1.158 |
Neg logit contributions | |
emetery | -0.728 |
ospel | -0.719 |
vernment | -0.695 |
ppa | -0.686 |
appa | -0.644 |
Token | . |
Token ID | 13 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
Frie | +0.296 |
spir | +0.284 |
Male | +0.268 |
AAA | +0.263 |
UCHIJ | +0.257 |
Neg logit contributions | |
emetery | -0.314 |
ospel | -0.310 |
vernment | -0.303 |
ppa | -0.302 |
appa | -0.289 |
Token |
|
Token ID | 198 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Frie | +0.658 |
spir | +0.632 |
Male | +0.598 |
AAA | +0.586 |
UCHIJ | +0.574 |
Neg logit contributions | |
emetery | -0.665 |
ospel | -0.656 |
vernment | -0.642 |
ppa | -0.637 |
appa | -0.609 |
Token |
|
Token ID | 198 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Frie | +1.236 |
spir | +1.215 |
Male | +1.147 |
AAA | +1.120 |
UCHIJ | +1.088 |
Neg logit contributions | |
emetery | -1.425 |
ospel | -1.387 |
vernment | -1.373 |
ppa | -1.345 |
appa | -1.291 |
Token | Story |
Token ID | 11605 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
Frie | +1.019 |
spir | +0.993 |
Male | +0.942 |
AAA | +0.902 |
UCHIJ | +0.885 |
Neg logit contributions | |
emetery | -1.199 |
ospel | -1.180 |
vernment | -1.161 |
ppa | -1.144 |
appa | -1.100 |
Token | continues |
Token ID | 4477 |
Feature activation | +9.98e+00 |
Pos logit contributions | |
spir | +2.777 |
Frie | +2.724 |
Male | +2.500 |
AAA | +2.447 |
UCHIJ | +2.324 |
Neg logit contributions | |
emetery | -4.323 |
ospel | -4.215 |
vernment | -4.188 |
ppa | -4.055 |
appa | -3.987 |
Token | below |
Token ID | 2174 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
spir | +4.244 |
Frie | +3.904 |
AAA | +3.852 |
Male | +3.820 |
UCHIJ | +3.535 |
Neg logit contributions | |
emetery | -10.694 |
vernment | -10.529 |
ospel | -10.347 |
ailability | -10.278 |
ppa | -10.103 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
Frie | +4.618 |
spir | +4.552 |
AAA | +4.440 |
Male | +4.392 |
UCHIJ | +4.247 |
Neg logit contributions | |
emetery | -2.626 |
ospel | -2.546 |
vernment | -2.471 |
ppa | -2.382 |
appa | -2.235 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
spir | +2.787 |
Frie | +2.774 |
Male | +2.633 |
AAA | +2.583 |
UCHIJ | +2.463 |
Neg logit contributions | |
emetery | -3.751 |
vernment | -3.600 |
ospel | -3.593 |
ppa | -3.460 |
ailability | -3.381 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ospel | +0.965 |
emetery | +0.956 |
ppa | +0.943 |
vernment | +0.927 |
appa | +0.896 |
Neg logit contributions | |
Frie | -1.075 |
spir | -1.012 |
querque | -0.971 |
Male | -0.955 |
AAA | -0.938 |
Token | Story |
Token ID | 11605 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
emetery | +0.844 |
ospel | +0.844 |
ppa | +0.823 |
vernment | +0.804 |
appa | +0.771 |
Neg logit contributions | |
Frie | -1.313 |
spir | -1.242 |
AAA | -1.185 |
querque | -1.182 |
Male | -1.174 |
Token | below |
Token ID | 2174 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
spir | +4.127 |
Frie | +4.069 |
AAA | +3.836 |
Male | +3.797 |
UCHIJ | +3.459 |
Neg logit contributions | |
emetery | -10.509 |
ospel | -10.190 |
vernment | -10.009 |
ppa | -9.955 |
ailability | -9.678 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
Frie | +4.559 |
spir | +4.464 |
Male | +4.304 |
AAA | +4.264 |
UCHIJ | +4.122 |
Neg logit contributions | |
emetery | -2.435 |
ospel | -2.409 |
vernment | -2.269 |
ppa | -2.249 |
jri | -2.098 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
spir | +2.798 |
Frie | +2.783 |
Male | +2.652 |
AAA | +2.588 |
UCHIJ | +2.470 |
Neg logit contributions | |
emetery | -3.788 |
ospel | -3.625 |
vernment | -3.613 |
ppa | -3.490 |
ailability | -3.424 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ospel | +0.766 |
emetery | +0.761 |
ppa | +0.749 |
vernment | +0.738 |
appa | +0.711 |
Neg logit contributions | |
Frie | -0.842 |
spir | -0.795 |
querque | -0.758 |
Male | -0.750 |
AAA | -0.736 |
Token | Story |
Token ID | 11605 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
emetery | +0.741 |
ospel | +0.739 |
ppa | +0.722 |
vernment | +0.712 |
appa | +0.678 |
Neg logit contributions | |
Frie | -1.054 |
spir | -1.003 |
AAA | -0.947 |
querque | -0.946 |
Male | -0.945 |
Token | continues |
Token ID | 4477 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
Frie | +1.685 |
spir | +1.657 |
Male | +1.513 |
AAA | +1.485 |
UCHIJ | +1.430 |
Neg logit contributions | |
emetery | -2.378 |
ospel | -2.340 |
vernment | -2.313 |
ppa | -2.254 |
appa | -2.189 |
Token | below |
Token ID | 2174 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
spir | +4.122 |
Frie | +3.748 |
Male | +3.718 |
AAA | +3.690 |
UCHIJ | +3.401 |
Neg logit contributions | |
emetery | -10.569 |
vernment | -10.361 |
ospel | -10.252 |
ailability | -10.245 |
ppa | -10.057 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Frie | +4.574 |
spir | +4.519 |
AAA | +4.414 |
Male | +4.369 |
UCHIJ | +4.201 |
Neg logit contributions | |
emetery | -2.664 |
ospel | -2.590 |
vernment | -2.508 |
ppa | -2.422 |
appa | -2.294 |
Token |
|
Token ID | 198 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
Frie | +1.998 |
spir | +1.969 |
Male | +1.864 |
AAA | +1.823 |
UCHIJ | +1.764 |
Neg logit contributions | |
emetery | -2.443 |
ospel | -2.363 |
vernment | -2.344 |
ppa | -2.284 |
appa | -2.204 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ospel | +0.696 |
emetery | +0.693 |
ppa | +0.680 |
vernment | +0.672 |
appa | +0.647 |
Neg logit contributions | |
Frie | -0.751 |
spir | -0.711 |
querque | -0.672 |
Male | -0.672 |
AAA | -0.658 |
Token | The |
Token ID | 464 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
emetery | +0.888 |
ospel | +0.886 |
ppa | +0.869 |
vernment | +0.863 |
appa | +0.828 |
Neg logit contributions | |
Frie | -0.823 |
spir | -0.776 |
Male | -0.724 |
querque | -0.721 |
AAA | -0.720 |
Token | dollars |
Token ID | 5054 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
emetery | +0.182 |
ospel | +0.181 |
vernment | +0.177 |
ppa | +0.176 |
appa | +0.168 |
Neg logit contributions | |
Frie | -0.195 |
spir | -0.189 |
Male | -0.178 |
AAA | -0.172 |
querque | -0.171 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Frie | +1.371 |
spir | +1.306 |
Male | +1.242 |
AAA | +1.225 |
UCHIJ | +1.179 |
Neg logit contributions | |
emetery | -1.513 |
ospel | -1.498 |
ppa | -1.453 |
vernment | -1.443 |
appa | -1.393 |
Token |
|
Token ID | 198 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
emetery | +0.151 |
ospel | +0.150 |
vernment | +0.146 |
ppa | +0.146 |
appa | +0.139 |
Neg logit contributions | |
Frie | -0.153 |
spir | -0.147 |
Male | -0.139 |
AAA | -0.136 |
UCHIJ | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Frie | +0.025 |
spir | +0.024 |
Male | +0.022 |
AAA | +0.022 |
UCHIJ | +0.021 |
Neg logit contributions | |
emetery | -0.025 |
ospel | -0.025 |
vernment | -0.024 |
ppa | -0.024 |
appa | -0.023 |
Token | Story |
Token ID | 11605 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
Frie | +0.176 |
spir | +0.169 |
Male | +0.159 |
AAA | +0.155 |
UCHIJ | +0.152 |
Neg logit contributions | |
emetery | -0.197 |
ospel | -0.195 |
vernment | -0.191 |
ppa | -0.190 |
appa | -0.182 |
Token | continues |
Token ID | 4477 |
Feature activation | +9.73e+00 |
Pos logit contributions | |
Frie | +1.830 |
spir | +1.801 |
Male | +1.647 |
AAA | +1.618 |
UCHIJ | +1.568 |
Neg logit contributions | |
emetery | -2.631 |
ospel | -2.605 |
vernment | -2.551 |
ppa | -2.488 |
Kak | -2.398 |
Token | below |
Token ID | 2174 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
spir | +4.127 |
Frie | +4.069 |
AAA | +3.836 |
Male | +3.797 |
UCHIJ | +3.459 |
Neg logit contributions | |
emetery | -10.509 |
ospel | -10.190 |
vernment | -10.009 |
ppa | -9.955 |
ailability | -9.678 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
Frie | +4.559 |
spir | +4.464 |
Male | +4.304 |
AAA | +4.264 |
UCHIJ | +4.122 |
Neg logit contributions | |
emetery | -2.435 |
ospel | -2.409 |
vernment | -2.269 |
ppa | -2.249 |
jri | -2.098 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
spir | +2.798 |
Frie | +2.783 |
Male | +2.652 |
AAA | +2.588 |
UCHIJ | +2.470 |
Neg logit contributions | |
emetery | -3.788 |
ospel | -3.625 |
vernment | -3.613 |
ppa | -3.490 |
ailability | -3.424 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ospel | +0.766 |
emetery | +0.761 |
ppa | +0.749 |
vernment | +0.738 |
appa | +0.711 |
Neg logit contributions | |
Frie | -0.842 |
spir | -0.795 |
querque | -0.758 |
Male | -0.750 |
AAA | -0.736 |
Token | Story |
Token ID | 11605 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
emetery | +0.741 |
ospel | +0.739 |
ppa | +0.722 |
vernment | +0.712 |
appa | +0.678 |
Neg logit contributions | |
Frie | -1.054 |
spir | -1.003 |
AAA | -0.947 |
querque | -0.946 |
Male | -0.945 |
Token | stage |
Token ID | 3800 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
emetery | +0.821 |
ospel | +0.815 |
ppa | +0.802 |
vernment | +0.800 |
appa | +0.770 |
Neg logit contributions | |
Frie | -0.503 |
spir | -0.482 |
Male | -0.444 |
querque | -0.425 |
UCHIJ | -0.423 |
Token | . |
Token ID | 13 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
emetery | +0.279 |
ospel | +0.276 |
vernment | +0.270 |
ppa | +0.270 |
appa | +0.257 |
Neg logit contributions | |
Frie | -0.285 |
spir | -0.274 |
Male | -0.259 |
AAA | -0.253 |
querque | -0.249 |
Token |
|
Token ID | 198 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Frie | +0.505 |
spir | +0.486 |
Male | +0.459 |
AAA | +0.449 |
UCHIJ | +0.440 |
Neg logit contributions | |
emetery | -0.506 |
ospel | -0.501 |
vernment | -0.489 |
ppa | -0.488 |
appa | -0.466 |
Token |
|
Token ID | 198 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
Frie | +1.953 |
spir | +1.936 |
Male | +1.829 |
AAA | +1.783 |
UCHIJ | +1.728 |
Neg logit contributions | |
emetery | -2.352 |
ospel | -2.276 |
vernment | -2.264 |
ppa | -2.203 |
appa | -2.120 |
Token | Story |
Token ID | 11605 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
Frie | +1.919 |
spir | +1.876 |
Male | +1.784 |
AAA | +1.697 |
UCHIJ | +1.652 |
Neg logit contributions | |
emetery | -2.566 |
ospel | -2.521 |
vernment | -2.487 |
ppa | -2.440 |
appa | -2.352 |
Token | continues |
Token ID | 4477 |
Feature activation | +9.39e+00 |
Pos logit contributions | |
Frie | +2.543 |
spir | +2.467 |
Male | +2.266 |
AAA | +2.241 |
UCHIJ | +2.148 |
Neg logit contributions | |
emetery | -3.338 |
ospel | -3.294 |
vernment | -3.242 |
ppa | -3.188 |
appa | -3.056 |
Token | below |
Token ID | 2174 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
Frie | +4.210 |
spir | +4.195 |
AAA | +3.910 |
Male | +3.864 |
UCHIJ | +3.499 |
Neg logit contributions | |
emetery | -9.953 |
ospel | -9.669 |
vernment | -9.644 |
ppa | -9.404 |
ailability | -9.130 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
Frie | +4.084 |
spir | +3.979 |
Male | +3.849 |
AAA | +3.824 |
UCHIJ | +3.703 |
Neg logit contributions | |
emetery | -2.145 |
ospel | -2.109 |
vernment | -2.008 |
ppa | -1.982 |
jri | -1.839 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
spir | +2.692 |
Frie | +2.688 |
Male | +2.553 |
AAA | +2.492 |
UCHIJ | +2.384 |
Neg logit contributions | |
emetery | -3.559 |
ospel | -3.420 |
vernment | -3.408 |
ppa | -3.298 |
jri | -3.208 |
Token |
|
Token ID | 198 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
emetery | +0.111 |
ospel | +0.110 |
ppa | +0.108 |
vernment | +0.107 |
appa | +0.103 |
Neg logit contributions | |
Frie | -0.114 |
spir | -0.109 |
Male | -0.103 |
querque | -0.101 |
AAA | -0.101 |
Token | He |
Token ID | 1544 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
emetery | +0.170 |
ospel | +0.169 |
ppa | +0.166 |
vernment | +0.165 |
appa | +0.159 |
Neg logit contributions | |
Frie | -0.142 |
spir | -0.134 |
Male | -0.125 |
AAA | -0.124 |
querque | -0.122 |
Token | classes |
Token ID | 6097 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Frie | +1.123 |
spir | +1.077 |
Male | +1.024 |
AAA | +1.000 |
UCHIJ | +0.974 |
Neg logit contributions | |
emetery | -1.206 |
ospel | -1.188 |
vernment | -1.159 |
ppa | -1.155 |
appa | -1.109 |
Token | . |
Token ID | 13 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
Frie | +1.202 |
spir | +1.152 |
Male | +1.091 |
AAA | +1.067 |
UCHIJ | +1.042 |
Neg logit contributions | |
emetery | -1.300 |
ospel | -1.286 |
vernment | -1.253 |
ppa | -1.249 |
appa | -1.195 |
Token |
|
Token ID | 198 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Frie | +0.670 |
spir | +0.644 |
Male | +0.609 |
AAA | +0.596 |
UCHIJ | +0.583 |
Neg logit contributions | |
emetery | -0.691 |
ospel | -0.683 |
vernment | -0.666 |
ppa | -0.664 |
appa | -0.636 |
Token |
|
Token ID | 198 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
Frie | +0.454 |
spir | +0.438 |
Male | +0.414 |
AAA | +0.405 |
UCHIJ | +0.396 |
Neg logit contributions | |
emetery | -0.473 |
ospel | -0.467 |
vernment | -0.457 |
ppa | -0.454 |
appa | -0.434 |
Token | [ |
Token ID | 58 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
Frie | +0.533 |
spir | +0.511 |
Male | +0.482 |
AAA | +0.470 |
UCHIJ | +0.460 |
Neg logit contributions | |
emetery | -0.608 |
ospel | -0.602 |
vernment | -0.589 |
ppa | -0.587 |
appa | -0.562 |
Token | np |
Token ID | 37659 |
Feature activation | +9.19e+00 |
Pos logit contributions | |
Frie | +2.329 |
spir | +2.239 |
Male | +2.113 |
AAA | +2.012 |
UCHIJ | +1.950 |
Neg logit contributions | |
emetery | -3.647 |
ospel | -3.600 |
vernment | -3.515 |
ppa | -3.494 |
appa | -3.366 |
Token | - |
Token ID | 12 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
Frie | +5.182 |
spir | +5.121 |
Male | +4.952 |
AAA | +4.694 |
querque | +4.361 |
Neg logit contributions | |
emetery | -8.573 |
ospel | -8.452 |
ppa | -8.217 |
vernment | -8.215 |
appa | -7.881 |
Token | related |
Token ID | 5363 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
Frie | +2.466 |
spir | +2.399 |
Male | +2.258 |
AAA | +2.175 |
UCHIJ | +2.116 |
Neg logit contributions | |
emetery | -3.018 |
ospel | -2.960 |
ppa | -2.890 |
vernment | -2.885 |
Kak | -2.763 |
Token | ] |
Token ID | 60 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Frie | +3.982 |
spir | +3.881 |
Male | +3.679 |
AAA | +3.558 |
UCHIJ | +3.448 |
Neg logit contributions | |
emetery | -4.995 |
ospel | -4.909 |
vernment | -4.807 |
ppa | -4.780 |
appa | -4.536 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
Frie | +2.085 |
spir | +2.018 |
Male | +1.911 |
AAA | +1.866 |
UCHIJ | +1.825 |
Neg logit contributions | |
emetery | -2.271 |
ospel | -2.233 |
vernment | -2.186 |
ppa | -2.175 |
appa | -2.083 |
Token | The |
Token ID | 464 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Frie | +0.516 |
spir | +0.493 |
Male | +0.463 |
AAA | +0.452 |
UCHIJ | +0.442 |
Neg logit contributions | |
emetery | -0.627 |
ospel | -0.622 |
vernment | -0.608 |
ppa | -0.607 |
appa | -0.582 |
Token | statement |
Token ID | 2643 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
Frie | +0.726 |
spir | +0.689 |
Male | +0.640 |
AAA | +0.623 |
UCHIJ | +0.606 |
Neg logit contributions | |
emetery | -1.136 |
ospel | -1.124 |
vernment | -1.103 |
ppa | -1.100 |
appa | -1.058 |
Token | . |
Token ID | 13 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
Frie | +0.450 |
spir | +0.431 |
Male | +0.407 |
AAA | +0.400 |
UCHIJ | +0.391 |
Neg logit contributions | |
emetery | -0.463 |
ospel | -0.457 |
vernment | -0.447 |
ppa | -0.445 |
appa | -0.423 |
Token |
|
Token ID | 198 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
Frie | +0.540 |
spir | +0.519 |
Male | +0.493 |
AAA | +0.484 |
UCHIJ | +0.473 |
Neg logit contributions | |
emetery | -0.501 |
ospel | -0.493 |
vernment | -0.482 |
ppa | -0.479 |
appa | -0.457 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
Frie | +0.464 |
spir | +0.448 |
Male | +0.423 |
AAA | +0.413 |
UCHIJ | +0.405 |
Neg logit contributions | |
emetery | -0.484 |
ospel | -0.478 |
vernment | -0.468 |
ppa | -0.465 |
appa | -0.445 |
Token | Story |
Token ID | 11605 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
Frie | +0.343 |
spir | +0.331 |
Male | +0.314 |
AAA | +0.305 |
UCHIJ | +0.299 |
Neg logit contributions | |
emetery | -0.354 |
ospel | -0.350 |
vernment | -0.342 |
ppa | -0.341 |
appa | -0.326 |
Token | continues |
Token ID | 4477 |
Feature activation | +9.14e+00 |
Pos logit contributions | |
spir | +2.632 |
Frie | +2.603 |
Male | +2.376 |
AAA | +2.328 |
UCHIJ | +2.218 |
Neg logit contributions | |
emetery | -4.099 |
ospel | -4.002 |
vernment | -3.963 |
ppa | -3.851 |
appa | -3.756 |
Token | below |
Token ID | 2174 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
spir | +4.058 |
Frie | +3.799 |
AAA | +3.699 |
Male | +3.673 |
UCHIJ | +3.438 |
Neg logit contributions | |
emetery | -9.699 |
vernment | -9.459 |
ospel | -9.405 |
ppa | -9.230 |
ailability | -9.184 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
Frie | +5.175 |
spir | +5.128 |
AAA | +5.046 |
Male | +4.963 |
UCHIJ | +4.777 |
Neg logit contributions | |
emetery | -3.140 |
ospel | -3.033 |
vernment | -2.931 |
ppa | -2.830 |
appa | -2.653 |
Token |
|
Token ID | 198 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
spir | +2.374 |
Frie | +2.370 |
Male | +2.239 |
AAA | +2.192 |
UCHIJ | +2.106 |
Neg logit contributions | |
emetery | -3.081 |
ospel | -2.961 |
vernment | -2.956 |
ppa | -2.858 |
jri | -2.769 |
Token |
|
Token ID | 198 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
ospel | +0.670 |
emetery | +0.668 |
ppa | +0.655 |
vernment | +0.647 |
appa | +0.623 |
Neg logit contributions | |
Frie | -0.725 |
spir | -0.687 |
querque | -0.649 |
Male | -0.649 |
AAA | -0.636 |
Token | It |
Token ID | 1026 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
emetery | +0.749 |
ospel | +0.745 |
ppa | +0.729 |
vernment | +0.726 |
appa | +0.696 |
Neg logit contributions | |
Frie | -0.692 |
spir | -0.655 |
Male | -0.612 |
AAA | -0.607 |
querque | -0.604 |
Token | AP |
Token ID | 2969 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
Frie | +0.668 |
spir | +0.640 |
Male | +0.600 |
AAA | +0.585 |
querque | +0.573 |
Neg logit contributions | |
emetery | -0.816 |
ospel | -0.809 |
vernment | -0.791 |
ppa | -0.789 |
appa | -0.757 |
Token | ) |
Token ID | 8 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Frie | +2.281 |
spir | +2.208 |
Male | +2.103 |
AAA | +2.053 |
querque | +2.001 |
Neg logit contributions | |
emetery | -2.191 |
ospel | -2.166 |
vernment | -2.148 |
ppa | -2.137 |
appa | -2.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Frie | +1.557 |
spir | +1.505 |
Male | +1.414 |
AAA | +1.389 |
UCHIJ | +1.351 |
Neg logit contributions | |
emetery | -1.667 |
ospel | -1.638 |
vernment | -1.609 |
ppa | -1.592 |
appa | -1.525 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
ospel | +0.883 |
emetery | +0.879 |
ppa | +0.864 |
vernment | +0.851 |
appa | +0.822 |
Neg logit contributions | |
Frie | -0.964 |
spir | -0.912 |
querque | -0.865 |
Male | -0.862 |
AAA | -0.844 |
Token | Story |
Token ID | 11605 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ospel | +1.450 |
emetery | +1.446 |
ppa | +1.434 |
vernment | +1.402 |
appa | +1.362 |
Neg logit contributions | |
Frie | -1.230 |
spir | -1.147 |
querque | -1.078 |
AAA | -1.071 |
Male | -1.064 |
Token | continues |
Token ID | 4477 |
Feature activation | +8.99e+00 |
Pos logit contributions | |
Frie | +1.413 |
spir | +1.372 |
Male | +1.293 |
AAA | +1.280 |
UCHIJ | +1.244 |
Neg logit contributions | |
emetery | -1.150 |
ospel | -1.134 |
vernment | -1.108 |
ppa | -1.092 |
appa | -1.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Frie | +4.299 |
spir | +4.221 |
Male | +3.879 |
AAA | +3.851 |
Ely | +3.476 |
Neg logit contributions | |
emetery | -9.222 |
ospel | -9.076 |
vernment | -9.001 |
ppa | -8.878 |
appa | -8.475 |
Token |
|
Token ID | 198 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Frie | +1.223 |
spir | +1.196 |
Male | +1.133 |
AAA | +1.102 |
UCHIJ | +1.073 |
Neg logit contributions | |
emetery | -1.388 |
ospel | -1.354 |
vernment | -1.338 |
ppa | -1.313 |
appa | -1.261 |
Token | There |
Token ID | 1858 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Frie | +1.132 |
spir | +1.098 |
Male | +1.048 |
AAA | +1.019 |
UCHIJ | +1.001 |
Neg logit contributions | |
emetery | -0.914 |
ospel | -0.900 |
vernment | -0.881 |
ppa | -0.870 |
appa | -0.828 |
Token | were |
Token ID | 547 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
emetery | +1.503 |
ospel | +1.491 |
ppa | +1.460 |
vernment | +1.460 |
appa | +1.398 |
Neg logit contributions | |
Frie | -1.417 |
spir | -1.362 |
Male | -1.287 |
AAA | -1.259 |
UCHIJ | -1.241 |
Token | a |
Token ID | 257 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Frie | +0.050 |
spir | +0.048 |
Male | +0.046 |
AAA | +0.045 |
UCHIJ | +0.044 |
Neg logit contributions | |
emetery | -0.052 |
ospel | -0.051 |
vernment | -0.050 |
ppa | -0.050 |
appa | -0.047 |
Token | relations |
Token ID | 2316 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
emetery | +0.658 |
ospel | +0.652 |
vernment | +0.636 |
ppa | +0.634 |
appa | +0.604 |
Neg logit contributions | |
Frie | -0.717 |
spir | -0.691 |
Male | -0.655 |
AAA | -0.640 |
UCHIJ | -0.629 |
Token | with |
Token ID | 351 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
Frie | +1.356 |
spir | +1.307 |
Male | +1.227 |
AAA | +1.205 |
UCHIJ | +1.170 |
Neg logit contributions | |
emetery | -1.397 |
ospel | -1.381 |
vernment | -1.331 |
ppa | -1.327 |
appa | -1.272 |
Token | Gaddafi |
Token ID | 40320 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Frie | +0.214 |
spir | +0.205 |
Male | +0.194 |
AAA | +0.191 |
UCHIJ | +0.187 |
Neg logit contributions | |
emetery | -0.206 |
ospel | -0.204 |
ppa | -0.198 |
vernment | -0.197 |
appa | -0.189 |
Token | had |
Token ID | 550 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
emetery | +1.180 |
ospel | +1.167 |
vernment | +1.144 |
ppa | +1.136 |
appa | +1.080 |
Neg logit contributions | |
Frie | -1.425 |
spir | -1.374 |
Male | -1.309 |
AAA | -1.282 |
UCHIJ | -1.263 |
Token | s |
Token ID | 264 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
Frie | +0.847 |
spir | +0.815 |
Male | +0.755 |
AAA | +0.747 |
UCHIJ | +0.719 |
Neg logit contributions | |
emetery | -1.029 |
ospel | -1.017 |
vernment | -0.988 |
ppa | -0.985 |
appa | -0.942 |
Token | oured |
Token ID | 8167 |
Feature activation | +8.77e+00 |
Pos logit contributions | |
Frie | +2.418 |
spir | +2.379 |
Male | +2.240 |
AAA | +2.205 |
UCHIJ | +2.156 |
Neg logit contributions | |
emetery | -1.650 |
ospel | -1.600 |
vernment | -1.560 |
ppa | -1.542 |
appa | -1.445 |
Token | . |
Token ID | 13 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
Frie | +6.448 |
spir | +6.163 |
Male | +5.845 |
AAA | +5.775 |
UCHIJ | +5.431 |
Neg logit contributions | |
emetery | -6.761 |
ospel | -6.690 |
ppa | -6.327 |
vernment | -6.306 |
appa | -6.163 |
Token | The |
Token ID | 383 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Frie | +2.338 |
spir | +2.236 |
Male | +2.132 |
AAA | +2.117 |
UCHIJ | +2.046 |
Neg logit contributions | |
emetery | -2.227 |
ospel | -2.150 |
vernment | -2.084 |
ppa | -2.074 |
appa | -2.001 |
Token | Libyan |
Token ID | 28661 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Frie | +0.089 |
spir | +0.085 |
Male | +0.081 |
AAA | +0.080 |
UCHIJ | +0.078 |
Neg logit contributions | |
emetery | -0.082 |
ospel | -0.081 |
vernment | -0.079 |
ppa | -0.078 |
appa | -0.075 |
Token | leader |
Token ID | 3554 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
emetery | +0.928 |
ospel | +0.923 |
vernment | +0.908 |
ppa | +0.898 |
appa | +0.852 |
Neg logit contributions | |
Frie | -1.057 |
spir | -1.018 |
Male | -0.967 |
AAA | -0.940 |
UCHIJ | -0.931 |
Token | demanded |
Token ID | 12284 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
emetery | +0.500 |
ospel | +0.494 |
vernment | +0.478 |
ppa | +0.477 |
appa | +0.454 |
Neg logit contributions | |
Frie | -0.575 |
spir | -0.554 |
Male | -0.526 |
AAA | -0.515 |
UCHIJ | -0.504 |
Token | que |
Token ID | 8358 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
emetery | +0.252 |
ospel | +0.249 |
vernment | +0.245 |
ppa | +0.244 |
appa | +0.234 |
Neg logit contributions | |
Frie | -0.234 |
spir | -0.224 |
Male | -0.212 |
AAA | -0.205 |
UCHIJ | -0.203 |
Token | tr |
Token ID | 491 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Frie | +0.345 |
spir | +0.331 |
Male | +0.311 |
AAA | +0.303 |
UCHIJ | +0.298 |
Neg logit contributions | |
emetery | -0.404 |
ospel | -0.399 |
vernment | -0.392 |
ppa | -0.391 |
appa | -0.374 |
Token | iste |
Token ID | 40833 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
Frie | +1.221 |
spir | +1.181 |
Male | +1.111 |
AAA | +1.077 |
querque | +1.048 |
Neg logit contributions | |
emetery | -1.492 |
ospel | -1.475 |
vernment | -1.444 |
ppa | -1.430 |
appa | -1.375 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
Frie | +1.806 |
spir | +1.733 |
Male | +1.640 |
AAA | +1.605 |
UCHIJ | +1.559 |
Neg logit contributions | |
emetery | -1.976 |
ospel | -1.962 |
vernment | -1.905 |
ppa | -1.901 |
appa | -1.819 |
Token | J |
Token ID | 41 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Frie | +0.252 |
spir | +0.242 |
Male | +0.228 |
AAA | +0.223 |
querque | +0.219 |
Neg logit contributions | |
emetery | -0.268 |
ospel | -0.265 |
vernment | -0.259 |
ppa | -0.258 |
appa | -0.247 |
Token | ' |
Token ID | 6 |
Feature activation | +8.67e+00 |
Pos logit contributions | |
Frie | +0.780 |
spir | +0.748 |
Male | +0.706 |
AAA | +0.689 |
UCHIJ | +0.674 |
Neg logit contributions | |
emetery | -0.864 |
ospel | -0.855 |
vernment | -0.836 |
ppa | -0.834 |
appa | -0.798 |
Token | ai |
Token ID | 1872 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
spir | +6.631 |
Frie | +6.543 |
Male | +6.268 |
AAA | +6.004 |
querque | +5.858 |
Neg logit contributions | |
emetery | -6.150 |
ospel | -5.896 |
ppa | -5.685 |
vernment | -5.678 |
Kak | -5.506 |
Token | l |
Token ID | 300 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
Frie | +1.701 |
spir | +1.637 |
Male | +1.545 |
AAA | +1.512 |
querque | +1.468 |
Neg logit contributions | |
emetery | -1.886 |
ospel | -1.869 |
vernment | -1.814 |
ppa | -1.808 |
appa | -1.732 |
Token | ' |
Token ID | 6 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
Frie | +0.396 |
spir | +0.380 |
Male | +0.356 |
AAA | +0.346 |
UCHIJ | +0.338 |
Neg logit contributions | |
emetery | -0.510 |
ospel | -0.504 |
vernment | -0.493 |
ppa | -0.490 |
appa | -0.472 |
Token | hon |
Token ID | 24130 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
Frie | +4.081 |
spir | +4.040 |
Male | +3.846 |
AAA | +3.699 |
querque | +3.595 |
Neg logit contributions | |
emetery | -4.028 |
ospel | -4.003 |
ppa | -3.872 |
vernment | -3.828 |
Kak | -3.709 |
Token | ne |
Token ID | 710 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Frie | +1.584 |
spir | +1.514 |
Male | +1.415 |
AAA | +1.371 |
querque | +1.338 |
Neg logit contributions | |
emetery | -2.271 |
ospel | -2.247 |
vernment | -2.186 |
ppa | -2.177 |
appa | -2.100 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
emetery | +0.535 |
ospel | +0.531 |
ppa | +0.519 |
vernment | +0.518 |
appa | +0.495 |
Neg logit contributions | |
Frie | -0.500 |
spir | -0.480 |
Male | -0.452 |
AAA | -0.441 |
querque | -0.435 |
Token | BR |
Token ID | 11473 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Frie | +0.642 |
spir | +0.615 |
Male | +0.578 |
AAA | +0.563 |
UCHIJ | +0.551 |
Neg logit contributions | |
emetery | -0.781 |
ospel | -0.773 |
vernment | -0.757 |
ppa | -0.755 |
appa | -0.724 |
Token | USS |
Token ID | 32835 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
emetery | +1.127 |
ospel | +1.115 |
ppa | +1.086 |
vernment | +1.084 |
appa | +1.037 |
Neg logit contributions | |
Frie | -1.159 |
spir | -1.113 |
Male | -1.044 |
AAA | -1.026 |
querque | -1.018 |
Token | ELS |
Token ID | 37142 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
emetery | +0.849 |
ospel | +0.840 |
vernment | +0.822 |
ppa | +0.816 |
Kak | +0.784 |
Neg logit contributions | |
Frie | -0.796 |
spir | -0.765 |
Male | -0.720 |
querque | -0.704 |
AAA | -0.702 |
Token | ( |
Token ID | 357 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Frie | +1.876 |
spir | +1.807 |
Male | +1.719 |
AAA | +1.682 |
UCHIJ | +1.647 |
Neg logit contributions | |
emetery | -1.719 |
ospel | -1.697 |
vernment | -1.653 |
ppa | -1.645 |
appa | -1.571 |
Token | Reuters |
Token ID | 12637 |
Feature activation | +8.55e+00 |
Pos logit contributions | |
Frie | +1.489 |
spir | +1.436 |
Male | +1.359 |
AAA | +1.320 |
UCHIJ | +1.294 |
Neg logit contributions | |
emetery | -1.632 |
ospel | -1.610 |
vernment | -1.572 |
ppa | -1.564 |
appa | -1.499 |
Token | ) |
Token ID | 8 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
spir | +6.123 |
Frie | +6.110 |
Male | +5.902 |
AAA | +5.895 |
UCHIJ | +5.694 |
Neg logit contributions | |
emetery | -6.815 |
vernment | -6.664 |
ospel | -6.591 |
ppa | -6.173 |
jri | -6.152 |
Token | - |
Token ID | 532 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
Frie | +4.044 |
spir | +3.998 |
Male | +3.750 |
AAA | +3.690 |
UCHIJ | +3.576 |
Neg logit contributions | |
emetery | -7.042 |
ospel | -6.743 |
vernment | -6.741 |
ppa | -6.533 |
jri | -6.380 |
Token | The |
Token ID | 383 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
Frie | +2.581 |
spir | +2.464 |
Male | +2.331 |
AAA | +2.313 |
UCHIJ | +2.229 |
Neg logit contributions | |
emetery | -2.669 |
ospel | -2.606 |
vernment | -2.542 |
ppa | -2.520 |
appa | -2.432 |
Token | world |
Token ID | 995 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Frie | +0.213 |
spir | +0.205 |
Male | +0.193 |
AAA | +0.188 |
UCHIJ | +0.184 |
Neg logit contributions | |
emetery | -0.239 |
ospel | -0.236 |
vernment | -0.231 |
ppa | -0.231 |
appa | -0.221 |
Token | � |
Token ID | 447 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Frie | +1.935 |
spir | +1.859 |
Male | +1.753 |
AAA | +1.723 |
UCHIJ | +1.670 |
Neg logit contributions | |
emetery | -2.074 |
ospel | -2.047 |
vernment | -1.991 |
ppa | -1.979 |
appa | -1.905 |
Token | ents |
Token ID | 658 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Frie | +1.246 |
spir | +1.213 |
Male | +1.140 |
AAA | +1.106 |
UCHIJ | +1.085 |
Neg logit contributions | |
emetery | -1.307 |
ospel | -1.292 |
vernment | -1.261 |
ppa | -1.254 |
appa | -1.196 |
Token | ind |
Token ID | 773 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Frie | +0.149 |
spir | +0.142 |
Male | +0.134 |
AAA | +0.131 |
UCHIJ | +0.129 |
Neg logit contributions | |
emetery | -0.161 |
ospel | -0.159 |
vernment | -0.156 |
ppa | -0.155 |
appa | -0.148 |
Token | iqu |
Token ID | 1557 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Frie | +0.267 |
spir | +0.256 |
Male | +0.241 |
AAA | +0.236 |
querque | +0.231 |
Neg logit contributions | |
emetery | -0.285 |
ospel | -0.281 |
vernment | -0.275 |
ppa | -0.274 |
appa | -0.262 |
Token | ent |
Token ID | 298 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
emetery | +1.223 |
ospel | +1.210 |
vernment | +1.195 |
ppa | +1.183 |
appa | +1.136 |
Neg logit contributions | |
Frie | -1.245 |
spir | -1.190 |
Male | -1.136 |
AAA | -1.098 |
UCHIJ | -1.089 |
Token | qu |
Token ID | 627 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
emetery | +0.044 |
ospel | +0.044 |
vernment | +0.043 |
ppa | +0.043 |
appa | +0.041 |
Neg logit contributions | |
Frie | -0.043 |
spir | -0.042 |
Male | -0.039 |
AAA | -0.038 |
UCHIJ | -0.038 |
Token | ' |
Token ID | 6 |
Feature activation | +8.55e+00 |
Pos logit contributions | |
Frie | +1.640 |
spir | +1.587 |
Male | +1.490 |
AAA | +1.457 |
querque | +1.421 |
Neg logit contributions | |
emetery | -1.838 |
ospel | -1.821 |
ppa | -1.769 |
vernment | -1.768 |
appa | -1.696 |
Token | ils |
Token ID | 4487 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
spir | +4.900 |
Frie | +4.763 |
Male | +4.516 |
AAA | +4.158 |
querque | +4.113 |
Neg logit contributions | |
emetery | -7.761 |
ospel | -7.617 |
ppa | -7.337 |
vernment | -7.242 |
Kak | -7.183 |
Token | ont |
Token ID | 39585 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
Frie | +1.970 |
spir | +1.898 |
Male | +1.792 |
AAA | +1.761 |
UCHIJ | +1.709 |
Neg logit contributions | |
emetery | -2.089 |
ospel | -2.065 |
vernment | -2.006 |
ppa | -1.997 |
appa | -1.913 |
Token | mont |
Token ID | 40689 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Frie | +2.899 |
spir | +2.789 |
Male | +2.626 |
AAA | +2.609 |
UCHIJ | +2.502 |
Neg logit contributions | |
emetery | -3.159 |
ospel | -3.118 |
vernment | -3.009 |
ppa | -2.997 |
appa | -2.871 |
Token | é |
Token ID | 2634 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
emetery | +0.096 |
ospel | +0.095 |
vernment | +0.092 |
ppa | +0.092 |
appa | +0.088 |
Neg logit contributions | |
Frie | -0.098 |
spir | -0.094 |
Male | -0.089 |
AAA | -0.087 |
UCHIJ | -0.085 |
Token | une |
Token ID | 17809 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Frie | +1.479 |
spir | +1.421 |
Male | +1.342 |
AAA | +1.317 |
querque | +1.281 |
Neg logit contributions | |
emetery | -1.560 |
ospel | -1.548 |
vernment | -1.507 |
ppa | -1.501 |
appa | -1.436 |
Token | ant |
Token ID | 415 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Frie | +2.113 |
spir | +2.053 |
Male | +1.916 |
AAA | +1.872 |
querque | +1.833 |
Neg logit contributions | |
emetery | -2.363 |
ospel | -2.322 |
vernment | -2.278 |
ppa | -2.265 |
Kak | -2.168 |
Token | neut |
Token ID | 22190 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
Frie | +0.804 |
spir | +0.773 |
Male | +0.730 |
AAA | +0.714 |
UCHIJ | +0.698 |
Neg logit contributions | |
emetery | -0.843 |
ospel | -0.835 |
vernment | -0.815 |
ppa | -0.812 |
appa | -0.777 |
Token | re |
Token ID | 260 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
Frie | +3.718 |
spir | +3.564 |
Male | +3.341 |
AAA | +3.307 |
querque | +3.213 |
Neg logit contributions | |
emetery | -4.673 |
ospel | -4.610 |
ppa | -4.491 |
vernment | -4.474 |
Kak | -4.266 |
Token | . |
Token ID | 13 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
Frie | +0.402 |
spir | +0.386 |
Male | +0.365 |
AAA | +0.356 |
UCHIJ | +0.350 |
Neg logit contributions | |
emetery | -0.418 |
ospel | -0.413 |
vernment | -0.406 |
ppa | -0.404 |
appa | -0.386 |
Token | J |
Token ID | 449 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
emetery | +0.364 |
ospel | +0.361 |
ppa | +0.353 |
vernment | +0.353 |
appa | +0.338 |
Neg logit contributions | |
Frie | -0.332 |
spir | -0.318 |
Male | -0.298 |
AAA | -0.292 |
querque | -0.289 |
Token | ' |
Token ID | 6 |
Feature activation | +8.44e+00 |
Pos logit contributions | |
emetery | +0.577 |
ospel | +0.572 |
ppa | +0.557 |
vernment | +0.556 |
appa | +0.533 |
Neg logit contributions | |
Frie | -0.551 |
spir | -0.527 |
Male | -0.496 |
AAA | -0.487 |
querque | -0.479 |
Token | esp |
Token ID | 9774 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
spir | +5.899 |
Frie | +5.829 |
Male | +5.563 |
AAA | +5.293 |
querque | +5.107 |
Neg logit contributions | |
emetery | -6.588 |
ospel | -6.345 |
vernment | -6.142 |
ppa | -6.098 |
Kak | -5.921 |
Token | ère |
Token ID | 35979 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
Frie | +1.750 |
spir | +1.698 |
Male | +1.554 |
AAA | +1.490 |
querque | +1.463 |
Neg logit contributions | |
emetery | -2.977 |
ospel | -2.928 |
vernment | -2.883 |
ppa | -2.862 |
Kak | -2.788 |
Token | que |
Token ID | 8358 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
Frie | +0.715 |
spir | +0.686 |
Male | +0.648 |
AAA | +0.632 |
UCHIJ | +0.619 |
Neg logit contributions | |
emetery | -0.776 |
ospel | -0.769 |
vernment | -0.751 |
ppa | -0.749 |
appa | -0.716 |
Token | v |
Token ID | 410 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Frie | +0.607 |
spir | +0.581 |
Male | +0.547 |
AAA | +0.533 |
UCHIJ | +0.522 |
Neg logit contributions | |
emetery | -0.718 |
ospel | -0.711 |
vernment | -0.696 |
ppa | -0.694 |
appa | -0.665 |
Token | ous |
Token ID | 516 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
Frie | +0.908 |
spir | +0.878 |
Male | +0.833 |
AAA | +0.807 |
UCHIJ | +0.791 |
Neg logit contributions | |
emetery | -0.938 |
ospel | -0.928 |
vernment | -0.909 |
ppa | -0.901 |
appa | -0.860 |
Token | club |
Token ID | 3430 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
emetery | +0.047 |
ospel | +0.046 |
vernment | +0.045 |
ppa | +0.045 |
appa | +0.043 |
Neg logit contributions | |
Frie | -0.045 |
spir | -0.043 |
Male | -0.041 |
AAA | -0.040 |
UCHIJ | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
emetery | +0.265 |
ospel | +0.262 |
vernment | +0.256 |
ppa | +0.256 |
appa | +0.244 |
Neg logit contributions | |
Frie | -0.271 |
spir | -0.261 |
Male | -0.247 |
AAA | -0.240 |
querque | -0.237 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Frie | +0.636 |
spir | +0.611 |
Male | +0.578 |
AAA | +0.566 |
UCHIJ | +0.554 |
Neg logit contributions | |
emetery | -0.643 |
ospel | -0.635 |
vernment | -0.621 |
ppa | -0.617 |
appa | -0.590 |
Token |
|
Token ID | 198 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Frie | +1.470 |
spir | +1.445 |
Male | +1.365 |
AAA | +1.332 |
UCHIJ | +1.293 |
Neg logit contributions | |
emetery | -1.712 |
ospel | -1.665 |
vernment | -1.649 |
ppa | -1.614 |
appa | -1.551 |
Token | Story |
Token ID | 11605 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
Frie | +1.243 |
spir | +1.212 |
Male | +1.149 |
AAA | +1.100 |
UCHIJ | +1.078 |
Neg logit contributions | |
emetery | -1.515 |
ospel | -1.490 |
vernment | -1.465 |
ppa | -1.446 |
appa | -1.391 |
Token | continues |
Token ID | 4477 |
Feature activation | +8.38e+00 |
Pos logit contributions | |
spir | +2.559 |
Frie | +2.486 |
Male | +2.281 |
AAA | +2.251 |
UCHIJ | +2.135 |
Neg logit contributions | |
emetery | -3.951 |
ospel | -3.853 |
vernment | -3.819 |
ppa | -3.708 |
appa | -3.628 |
Token | below |
Token ID | 2174 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
spir | +3.932 |
Frie | +3.690 |
AAA | +3.543 |
Male | +3.533 |
UCHIJ | +3.351 |
Neg logit contributions | |
emetery | -8.739 |
vernment | -8.576 |
ospel | -8.482 |
ppa | -8.327 |
ailability | -8.232 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
Frie | +4.448 |
spir | +4.401 |
AAA | +4.287 |
Male | +4.239 |
UCHIJ | +4.100 |
Neg logit contributions | |
emetery | -2.508 |
ospel | -2.431 |
vernment | -2.360 |
ppa | -2.276 |
appa | -2.133 |
Token |
|
Token ID | 198 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
Frie | +2.433 |
spir | +2.431 |
Male | +2.294 |
AAA | +2.250 |
UCHIJ | +2.158 |
Neg logit contributions | |
emetery | -3.165 |
ospel | -3.043 |
vernment | -3.038 |
ppa | -2.935 |
jri | -2.848 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ospel | +0.601 |
emetery | +0.599 |
ppa | +0.587 |
vernment | +0.580 |
appa | +0.558 |
Neg logit contributions | |
Frie | -0.647 |
spir | -0.613 |
Male | -0.579 |
querque | -0.578 |
AAA | -0.567 |
Token | He |
Token ID | 1544 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
emetery | +0.979 |
ospel | +0.977 |
ppa | +0.958 |
vernment | +0.950 |
appa | +0.916 |
Neg logit contributions | |
Frie | -0.835 |
spir | -0.784 |
Male | -0.730 |
AAA | -0.727 |
querque | -0.726 |
Token |
|
Token ID | 198 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Frie | +0.205 |
spir | +0.197 |
Male | +0.186 |
AAA | +0.182 |
UCHIJ | +0.178 |
Neg logit contributions | |
emetery | -0.208 |
ospel | -0.206 |
vernment | -0.201 |
ppa | -0.201 |
appa | -0.192 |
Token | K |
Token ID | 42 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
emetery | +0.128 |
ospel | +0.126 |
vernment | +0.123 |
ppa | +0.123 |
appa | +0.117 |
Neg logit contributions | |
Frie | -0.129 |
spir | -0.124 |
Male | -0.118 |
AAA | -0.115 |
UCHIJ | -0.113 |
Token | hal |
Token ID | 14201 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Frie | +0.542 |
spir | +0.520 |
Male | +0.488 |
AAA | +0.473 |
UCHIJ | +0.463 |
Neg logit contributions | |
emetery | -0.723 |
ospel | -0.716 |
vernment | -0.705 |
ppa | -0.702 |
appa | -0.671 |
Token | isha |
Token ID | 19388 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Frie | +1.534 |
spir | +1.491 |
Male | +1.402 |
AAA | +1.369 |
UCHIJ | +1.337 |
Neg logit contributions | |
emetery | -1.845 |
ospel | -1.811 |
vernment | -1.784 |
ppa | -1.742 |
Kak | -1.668 |
Token | told |
Token ID | 1297 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Frie | +0.808 |
spir | +0.774 |
Male | +0.734 |
AAA | +0.719 |
UCHIJ | +0.705 |
Neg logit contributions | |
emetery | -0.769 |
ospel | -0.760 |
vernment | -0.738 |
ppa | -0.732 |
appa | -0.699 |
Token | NBC |
Token ID | 9716 |
Feature activation | +8.33e+00 |
Pos logit contributions | |
emetery | +0.924 |
ospel | +0.914 |
vernment | +0.894 |
ppa | +0.892 |
appa | +0.856 |
Neg logit contributions | |
Frie | -0.919 |
spir | -0.893 |
Male | -0.843 |
AAA | -0.812 |
querque | -0.811 |
Token | news |
Token ID | 1705 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
Frie | +5.989 |
spir | +5.730 |
Male | +5.520 |
AAA | +5.362 |
UCHIJ | +5.124 |
Neg logit contributions | |
emetery | -6.557 |
ospel | -6.478 |
vernment | -6.431 |
ppa | -6.289 |
appa | -5.938 |
Token | that |
Token ID | 326 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
Frie | +2.677 |
spir | +2.588 |
Male | +2.449 |
AAA | +2.407 |
querque | +2.333 |
Neg logit contributions | |
emetery | -2.739 |
ospel | -2.706 |
vernment | -2.663 |
ppa | -2.647 |
appa | -2.507 |
Token | her |
Token ID | 607 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Frie | +0.479 |
spir | +0.460 |
Male | +0.436 |
AAA | +0.429 |
UCHIJ | +0.418 |
Neg logit contributions | |
emetery | -0.445 |
ospel | -0.440 |
vernment | -0.431 |
ppa | -0.428 |
appa | -0.407 |
Token | brother |
Token ID | 3956 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
Frie | +1.364 |
spir | +1.313 |
Male | +1.245 |
AAA | +1.231 |
UCHIJ | +1.195 |
Neg logit contributions | |
emetery | -1.220 |
ospel | -1.200 |
vernment | -1.184 |
ppa | -1.161 |
appa | -1.111 |
Token | survived |
Token ID | 11803 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
emetery | +0.453 |
ospel | +0.448 |
vernment | +0.438 |
ppa | +0.436 |
appa | +0.416 |
Neg logit contributions | |
Frie | -0.456 |
spir | -0.438 |
Male | -0.415 |
AAA | -0.406 |
UCHIJ | -0.398 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
Frie | +0.115 |
spir | +0.111 |
Male | +0.105 |
AAA | +0.102 |
querque | +0.101 |
Neg logit contributions | |
emetery | -0.117 |
ospel | -0.116 |
ppa | -0.113 |
vernment | -0.113 |
appa | -0.108 |
Token | HA |
Token ID | 7801 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Frie | +0.667 |
spir | +0.639 |
Male | +0.600 |
AAA | +0.585 |
UCHIJ | +0.572 |
Neg logit contributions | |
emetery | -0.813 |
ospel | -0.805 |
vernment | -0.788 |
ppa | -0.786 |
appa | -0.754 |
Token | V |
Token ID | 53 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
emetery | +1.268 |
ospel | +1.260 |
ppa | +1.245 |
vernment | +1.237 |
appa | +1.189 |
Neg logit contributions | |
Frie | -0.891 |
spir | -0.847 |
Male | -0.777 |
AAA | -0.758 |
querque | -0.754 |
Token | ANA |
Token ID | 31574 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
emetery | +0.386 |
ospel | +0.382 |
vernment | +0.374 |
ppa | +0.374 |
appa | +0.362 |
Neg logit contributions | |
Frie | -0.266 |
spir | -0.252 |
Male | -0.235 |
AAA | -0.228 |
querque | -0.224 |
Token | ( |
Token ID | 357 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
Frie | +1.785 |
spir | +1.723 |
Male | +1.637 |
AAA | +1.606 |
UCHIJ | +1.572 |
Neg logit contributions | |
emetery | -1.600 |
ospel | -1.581 |
vernment | -1.540 |
ppa | -1.531 |
appa | -1.463 |
Token | Reuters |
Token ID | 12637 |
Feature activation | +8.27e+00 |
Pos logit contributions | |
Frie | +0.636 |
spir | +0.610 |
Male | +0.576 |
AAA | +0.563 |
querque | +0.552 |
Neg logit contributions | |
emetery | -0.667 |
ospel | -0.661 |
vernment | -0.646 |
ppa | -0.644 |
appa | -0.616 |
Token | ) |
Token ID | 8 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
Frie | +5.993 |
spir | +5.988 |
Male | +5.782 |
AAA | +5.751 |
UCHIJ | +5.560 |
Neg logit contributions | |
emetery | -6.528 |
vernment | -6.384 |
ospel | -6.333 |
ppa | -5.940 |
jri | -5.893 |
Token | - |
Token ID | 532 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
Frie | +4.053 |
spir | +4.018 |
Male | +3.763 |
AAA | +3.698 |
UCHIJ | +3.585 |
Neg logit contributions | |
emetery | -7.003 |
ospel | -6.725 |
vernment | -6.711 |
ppa | -6.518 |
jri | -6.349 |
Token | Latin |
Token ID | 9133 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Frie | +2.576 |
spir | +2.476 |
Male | +2.354 |
AAA | +2.328 |
UCHIJ | +2.256 |
Neg logit contributions | |
emetery | -2.282 |
ospel | -2.245 |
vernment | -2.190 |
ppa | -2.172 |
appa | -2.081 |
Token | American |
Token ID | 1605 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
emetery | +0.790 |
ospel | +0.778 |
ppa | +0.755 |
vernment | +0.751 |
appa | +0.701 |
Neg logit contributions | |
Frie | -1.454 |
spir | -1.406 |
Male | -1.348 |
AAA | -1.321 |
UCHIJ | -1.309 |
Token | and |
Token ID | 290 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
Frie | +2.567 |
spir | +2.462 |
Male | +2.326 |
AAA | +2.315 |
UCHIJ | +2.223 |
Neg logit contributions | |
emetery | -2.674 |
ospel | -2.642 |
vernment | -2.569 |
ppa | -2.550 |
appa | -2.468 |
Token | � |
Token ID | 251 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Frie | +0.841 |
spir | +0.797 |
Male | +0.744 |
AAA | +0.722 |
UCHIJ | +0.703 |
Neg logit contributions | |
emetery | -1.306 |
ospel | -1.293 |
vernment | -1.269 |
ppa | -1.263 |
appa | -1.214 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Frie | +0.993 |
spir | +0.954 |
Male | +0.901 |
AAA | +0.889 |
UCHIJ | +0.864 |
Neg logit contributions | |
emetery | -1.057 |
ospel | -1.034 |
vernment | -1.016 |
ppa | -1.007 |
appa | -0.970 |
Token |
|
Token ID | 198 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
emetery | +0.115 |
ospel | +0.114 |
ppa | +0.112 |
vernment | +0.111 |
appa | +0.106 |
Neg logit contributions | |
Frie | -0.117 |
spir | -0.112 |
Male | -0.106 |
AAA | -0.104 |
querque | -0.103 |
Token | [ |
Token ID | 58 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
emetery | +0.298 |
ospel | +0.295 |
vernment | +0.288 |
ppa | +0.287 |
appa | +0.274 |
Neg logit contributions | |
Frie | -0.306 |
spir | -0.295 |
Male | -0.279 |
AAA | -0.273 |
UCHIJ | -0.268 |
Token | H |
Token ID | 39 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Frie | +2.249 |
spir | +2.164 |
Male | +2.047 |
AAA | +1.974 |
UCHIJ | +1.921 |
Neg logit contributions | |
emetery | -2.954 |
ospel | -2.914 |
vernment | -2.854 |
ppa | -2.830 |
appa | -2.713 |
Token | / |
Token ID | 14 |
Feature activation | +8.26e+00 |
Pos logit contributions | |
Frie | +0.708 |
spir | +0.684 |
Male | +0.645 |
AAA | +0.625 |
UCHIJ | +0.610 |
Neg logit contributions | |
emetery | -0.838 |
ospel | -0.827 |
vernment | -0.810 |
ppa | -0.807 |
appa | -0.772 |
Token | t |
Token ID | 83 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
spir | +4.183 |
Frie | +4.116 |
Male | +4.058 |
AAA | +3.758 |
UCHIJ | +3.574 |
Neg logit contributions | |
emetery | -8.296 |
ospel | -8.073 |
vernment | -8.054 |
ppa | -7.694 |
appa | -7.465 |
Token | The |
Token ID | 383 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Frie | +3.215 |
spir | +3.054 |
AAA | +2.900 |
Male | +2.897 |
UCHIJ | +2.788 |
Neg logit contributions | |
emetery | -3.031 |
ospel | -2.985 |
vernment | -2.897 |
ppa | -2.890 |
appa | -2.744 |
Token | Hill |
Token ID | 3327 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Frie | +2.124 |
spir | +2.039 |
Male | +1.929 |
AAA | +1.907 |
UCHIJ | +1.841 |
Neg logit contributions | |
emetery | -2.188 |
ospel | -2.145 |
vernment | -2.113 |
ppa | -2.096 |
appa | -1.997 |
Token | ] |
Token ID | 60 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Frie | +1.788 |
spir | +1.725 |
Male | +1.626 |
AAA | +1.588 |
UCHIJ | +1.544 |
Neg logit contributions | |
emetery | -1.975 |
ospel | -1.950 |
vernment | -1.911 |
ppa | -1.891 |
appa | -1.810 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
Frie | +1.211 |
spir | +1.163 |
Male | +1.095 |
AAA | +1.066 |
UCHIJ | +1.040 |
Neg logit contributions | |
emetery | -1.504 |
ospel | -1.488 |
vernment | -1.456 |
ppa | -1.451 |
appa | -1.391 |
Token | support |
Token ID | 1104 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
emetery | +1.035 |
ospel | +1.026 |
vernment | +1.002 |
ppa | +0.994 |
appa | +0.952 |
Neg logit contributions | |
Frie | -1.267 |
spir | -1.222 |
Male | -1.158 |
AAA | -1.130 |
querque | -1.122 |
Token | from |
Token ID | 422 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Frie | +0.492 |
spir | +0.472 |
Male | +0.444 |
AAA | +0.433 |
UCHIJ | +0.424 |
Neg logit contributions | |
emetery | -0.580 |
ospel | -0.575 |
vernment | -0.562 |
ppa | -0.561 |
appa | -0.538 |
Token | former |
Token ID | 1966 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Frie | +1.576 |
spir | +1.514 |
Male | +1.443 |
AAA | +1.417 |
UCHIJ | +1.387 |
Neg logit contributions | |
emetery | -1.416 |
ospel | -1.397 |
vernment | -1.357 |
ppa | -1.355 |
appa | -1.283 |
Token | Ku |
Token ID | 12554 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ospel | +1.183 |
emetery | +1.182 |
ppa | +1.154 |
vernment | +1.145 |
appa | +1.109 |
Neg logit contributions | |
Frie | -1.494 |
spir | -1.447 |
Male | -1.367 |
AAA | -1.327 |
querque | -1.323 |
Token | Klux |
Token ID | 45092 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
emetery | +0.597 |
ospel | +0.585 |
vernment | +0.571 |
ppa | +0.570 |
appa | +0.530 |
Neg logit contributions | |
Frie | -1.332 |
spir | -1.283 |
Male | -1.233 |
AAA | -1.214 |
UCHIJ | -1.198 |
Token | Klan |
Token ID | 31151 |
Feature activation | -8.31e+00 |
Pos logit contributions | |
ospel | +1.507 |
emetery | +1.407 |
vernment | +1.346 |
ppa | +1.324 |
appa | +1.277 |
Neg logit contributions | |
Frie | -8.167 |
spir | -7.960 |
Male | -7.666 |
querque | -7.649 |
UCHIJ | -7.599 |
Token | leader |
Token ID | 3554 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
emetery | +4.615 |
ospel | +4.525 |
ppa | +4.457 |
vernment | +4.388 |
Kak | +4.337 |
Neg logit contributions | |
Frie | -7.827 |
spir | -7.605 |
Male | -7.208 |
UCHIJ | -7.084 |
querque | -6.915 |
Token | David |
Token ID | 3271 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
emetery | +1.922 |
ospel | +1.901 |
vernment | +1.842 |
ppa | +1.838 |
appa | +1.737 |
Neg logit contributions | |
Frie | -2.864 |
spir | -2.777 |
Male | -2.651 |
AAA | -2.586 |
querque | -2.562 |
Token | Duke |
Token ID | 11083 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
emetery | +1.284 |
ospel | +1.270 |
vernment | +1.224 |
ppa | +1.212 |
appa | +1.146 |
Neg logit contributions | |
Frie | -2.209 |
spir | -2.143 |
Male | -2.064 |
AAA | -2.008 |
querque | -1.998 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
emetery | +1.526 |
ospel | +1.504 |
vernment | +1.482 |
ppa | +1.474 |
appa | +1.409 |
Neg logit contributions | |
Frie | -1.593 |
spir | -1.538 |
Male | -1.453 |
AAA | -1.422 |
UCHIJ | -1.399 |
Token | ( |
Token ID | 357 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Frie | +0.095 |
spir | +0.092 |
Male | +0.087 |
AAA | +0.085 |
querque | +0.084 |
Neg logit contributions | |
emetery | -0.087 |
ospel | -0.086 |
vernment | -0.084 |
ppa | -0.084 |
appa | -0.080 |
Token | lives |
Token ID | 3160 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
emetery | +0.368 |
ospel | +0.364 |
vernment | +0.356 |
ppa | +0.355 |
appa | +0.339 |
Neg logit contributions | |
Frie | -0.346 |
spir | -0.332 |
Male | -0.314 |
AAA | -0.307 |
UCHIJ | -0.300 |
Token | , |
Token ID | 11 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
emetery | +0.127 |
ospel | +0.126 |
vernment | +0.123 |
ppa | +0.123 |
appa | +0.117 |
Neg logit contributions | |
Frie | -0.123 |
spir | -0.118 |
Male | -0.112 |
AAA | -0.109 |
UCHIJ | -0.107 |
Token | or |
Token ID | 393 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Frie | +0.331 |
spir | +0.317 |
Male | +0.301 |
AAA | +0.294 |
UCHIJ | +0.288 |
Neg logit contributions | |
emetery | -0.333 |
ospel | -0.330 |
vernment | -0.322 |
ppa | -0.321 |
appa | -0.306 |
Token | am |
Token ID | 716 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Frie | +0.923 |
spir | +0.883 |
Male | +0.837 |
AAA | +0.818 |
UCHIJ | +0.797 |
Neg logit contributions | |
emetery | -0.996 |
ospel | -0.985 |
vernment | -0.960 |
ppa | -0.958 |
appa | -0.915 |
Token | I |
Token ID | 314 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
Frie | +2.237 |
spir | +2.183 |
Male | +2.068 |
AAA | +2.003 |
UCHIJ | +1.966 |
Neg logit contributions | |
emetery | -1.993 |
ospel | -1.978 |
vernment | -1.959 |
ppa | -1.945 |
appa | -1.816 |
Token | fool |
Token ID | 9192 |
Feature activation | -8.10e+00 |
Pos logit contributions | |
emetery | +2.370 |
ospel | +2.332 |
vernment | +2.302 |
ppa | +2.298 |
Kak | +2.214 |
Neg logit contributions | |
Frie | -2.543 |
spir | -2.431 |
Male | -2.290 |
AAA | -2.258 |
UCHIJ | -2.247 |
Token | ing |
Token ID | 278 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
ospel | +4.629 |
vernment | +4.612 |
emetery | +4.602 |
ppa | +4.470 |
appa | +4.305 |
Neg logit contributions | |
Frie | -7.270 |
spir | -7.022 |
Male | -6.878 |
querque | -6.731 |
UCHIJ | -6.711 |
Token | myself |
Token ID | 3589 |
Feature activation | -7.43e+00 |
Pos logit contributions | |
emetery | +2.676 |
ospel | +2.640 |
vernment | +2.620 |
ppa | +2.582 |
Kak | +2.445 |
Neg logit contributions | |
Frie | -3.516 |
spir | -3.383 |
Male | -3.230 |
querque | -3.158 |
AAA | -3.120 |
Token | ? |
Token ID | 30 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
emetery | +5.221 |
ppa | +5.117 |
vernment | +5.103 |
ospel | +5.074 |
Kak | +4.888 |
Neg logit contributions | |
Frie | -5.884 |
spir | -5.719 |
Male | -5.330 |
querque | -5.304 |
UCHIJ | -5.259 |
Token |
|
Token ID | 198 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
emetery | +0.302 |
ospel | +0.299 |
ppa | +0.293 |
vernment | +0.292 |
appa | +0.279 |
Neg logit contributions | |
Frie | -0.309 |
spir | -0.297 |
Male | -0.281 |
AAA | -0.274 |
querque | -0.271 |
Token |
|
Token ID | 198 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Frie | +0.515 |
spir | +0.495 |
Male | +0.468 |
AAA | +0.458 |
UCHIJ | +0.448 |
Neg logit contributions | |
emetery | -0.529 |
ospel | -0.523 |
vernment | -0.512 |
ppa | -0.509 |
appa | -0.487 |
Token | reliable |
Token ID | 9314 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Frie | +0.100 |
spir | +0.096 |
Male | +0.091 |
AAA | +0.088 |
querque | +0.087 |
Neg logit contributions | |
emetery | -0.097 |
ospel | -0.095 |
vernment | -0.094 |
ppa | -0.093 |
appa | -0.089 |
Token | in |
Token ID | 287 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
emetery | +1.618 |
ospel | +1.600 |
ppa | +1.596 |
vernment | +1.584 |
Kak | +1.513 |
Neg logit contributions | |
Frie | -1.950 |
spir | -1.869 |
Male | -1.795 |
querque | -1.730 |
UCHIJ | -1.709 |
Token | the |
Token ID | 262 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Frie | +0.037 |
spir | +0.035 |
Male | +0.033 |
AAA | +0.033 |
UCHIJ | +0.032 |
Neg logit contributions | |
emetery | -0.034 |
ospel | -0.033 |
vernment | -0.033 |
ppa | -0.033 |
appa | -0.031 |
Token | fight |
Token ID | 1907 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Frie | +0.247 |
spir | +0.238 |
Male | +0.226 |
AAA | +0.220 |
UCHIJ | +0.217 |
Neg logit contributions | |
emetery | -0.240 |
ospel | -0.237 |
vernment | -0.232 |
ppa | -0.231 |
appa | -0.220 |
Token | against |
Token ID | 1028 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
Frie | +1.058 |
spir | +1.003 |
Male | +0.934 |
AAA | +0.911 |
querque | +0.879 |
Neg logit contributions | |
emetery | -1.613 |
ospel | -1.593 |
vernment | -1.555 |
ppa | -1.555 |
appa | -1.497 |
Token | IS |
Token ID | 3180 |
Feature activation | -8.03e+00 |
Pos logit contributions | |
Frie | +0.603 |
spir | +0.580 |
Male | +0.550 |
AAA | +0.543 |
UCHIJ | +0.527 |
Neg logit contributions | |
emetery | -0.533 |
ospel | -0.525 |
ppa | -0.511 |
vernment | -0.508 |
appa | -0.486 |
Token | in |
Token ID | 287 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
emetery | +4.957 |
vernment | +4.884 |
ospel | +4.868 |
ppa | +4.865 |
Kak | +4.675 |
Neg logit contributions | |
Frie | -7.036 |
spir | -6.779 |
Male | -6.398 |
UCHIJ | -6.323 |
querque | -6.290 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
emetery | +0.927 |
ospel | +0.920 |
vernment | +0.903 |
ppa | +0.901 |
Kak | +0.856 |
Neg logit contributions | |
Frie | -1.043 |
spir | -1.010 |
Male | -0.961 |
AAA | -0.927 |
UCHIJ | -0.925 |
Token | north |
Token ID | 5093 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Frie | +0.073 |
spir | +0.070 |
Male | +0.066 |
AAA | +0.064 |
querque | +0.063 |
Neg logit contributions | |
emetery | -0.092 |
ospel | -0.092 |
vernment | -0.090 |
ppa | -0.090 |
appa | -0.086 |
Token | of |
Token ID | 286 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
Frie | +1.148 |
spir | +1.100 |
Male | +1.046 |
AAA | +1.027 |
querque | +0.996 |
Neg logit contributions | |
emetery | -1.090 |
ospel | -1.078 |
vernment | -1.047 |
ppa | -1.041 |
appa | -0.996 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
emetery | +0.062 |
ospel | +0.062 |
vernment | +0.060 |
ppa | +0.060 |
appa | +0.057 |
Neg logit contributions | |
Frie | -0.079 |
spir | -0.076 |
Male | -0.073 |
AAA | -0.071 |
UCHIJ | -0.070 |
Token | partners |
Token ID | 4887 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
Frie | +0.357 |
spir | +0.343 |
Male | +0.325 |
AAA | +0.319 |
UCHIJ | +0.312 |
Neg logit contributions | |
emetery | -0.340 |
ospel | -0.337 |
vernment | -0.328 |
ppa | -0.326 |
appa | -0.311 |
Token | in |
Token ID | 287 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
emetery | +2.400 |
ospel | +2.379 |
vernment | +2.359 |
ppa | +2.354 |
Kak | +2.262 |
Neg logit contributions | |
Frie | -2.460 |
spir | -2.388 |
Male | -2.242 |
querque | -2.172 |
AAA | -2.156 |
Token | the |
Token ID | 262 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
emetery | +0.696 |
ospel | +0.690 |
vernment | +0.679 |
ppa | +0.676 |
appa | +0.641 |
Neg logit contributions | |
Frie | -0.776 |
spir | -0.752 |
Male | -0.713 |
AAA | -0.685 |
querque | -0.682 |
Token | fight |
Token ID | 1907 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
emetery | +0.254 |
ospel | +0.253 |
vernment | +0.248 |
ppa | +0.247 |
appa | +0.234 |
Neg logit contributions | |
Frie | -0.286 |
spir | -0.277 |
Male | -0.263 |
AAA | -0.254 |
UCHIJ | -0.252 |
Token | against |
Token ID | 1028 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
Frie | +0.998 |
spir | +0.946 |
Male | +0.881 |
AAA | +0.860 |
querque | +0.832 |
Neg logit contributions | |
emetery | -1.513 |
ospel | -1.491 |
ppa | -1.457 |
vernment | -1.456 |
appa | -1.402 |
Token | IS |
Token ID | 3180 |
Feature activation | -7.90e+00 |
Pos logit contributions | |
Frie | +0.504 |
spir | +0.485 |
Male | +0.463 |
AAA | +0.459 |
UCHIJ | +0.446 |
Neg logit contributions | |
emetery | -0.375 |
ospel | -0.367 |
ppa | -0.357 |
vernment | -0.354 |
appa | -0.336 |
Token | - |
Token ID | 532 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
emetery | +5.337 |
ospel | +5.312 |
ppa | +5.217 |
vernment | +5.214 |
Kak | +5.055 |
Neg logit contributions | |
Frie | -6.407 |
spir | -6.143 |
Male | -5.743 |
UCHIJ | -5.677 |
querque | -5.651 |
Token | and |
Token ID | 290 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
emetery | +1.248 |
ospel | +1.231 |
vernment | +1.215 |
ppa | +1.205 |
appa | +1.149 |
Neg logit contributions | |
Frie | -1.483 |
spir | -1.435 |
Male | -1.360 |
AAA | -1.323 |
querque | -1.314 |
Token | Russia |
Token ID | 3284 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
emetery | +0.687 |
ospel | +0.680 |
vernment | +0.671 |
ppa | +0.667 |
appa | +0.633 |
Neg logit contributions | |
Frie | -0.754 |
spir | -0.729 |
Male | -0.690 |
AAA | -0.668 |
querque | -0.666 |
Token | . |
Token ID | 13 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
emetery | +0.096 |
ospel | +0.095 |
vernment | +0.093 |
ppa | +0.092 |
appa | +0.088 |
Neg logit contributions | |
Frie | -0.103 |
spir | -0.099 |
Male | -0.094 |
AAA | -0.092 |
UCHIJ | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
Frie | +0.506 |
spir | +0.486 |
Male | +0.460 |
AAA | +0.449 |
querque | +0.442 |
Neg logit contributions | |
emetery | -0.499 |
ospel | -0.495 |
vernment | -0.483 |
ppa | -0.482 |
appa | -0.460 |
Token | � |
Token ID | 447 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
Frie | +0.249 |
spir | +0.236 |
Male | +0.221 |
AAA | +0.218 |
querque | +0.215 |
Neg logit contributions | |
emetery | -0.304 |
ospel | -0.302 |
ppa | -0.296 |
vernment | -0.295 |
appa | -0.283 |
Token | � |
Token ID | 246 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
emetery | +0.682 |
ospel | +0.676 |
ppa | +0.663 |
vernment | +0.663 |
appa | +0.637 |
Neg logit contributions | |
Frie | -0.512 |
spir | -0.486 |
Male | -0.455 |
AAA | -0.442 |
UCHIJ | -0.433 |
Token | We |
Token ID | 1135 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
emetery | +0.402 |
ospel | +0.398 |
vernment | +0.389 |
ppa | +0.388 |
appa | +0.370 |
Neg logit contributions | |
Frie | -0.396 |
spir | -0.381 |
Male | -0.360 |
AAA | -0.351 |
querque | -0.346 |
Token | must |
Token ID | 1276 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
Frie | +0.437 |
spir | +0.420 |
Male | +0.395 |
AAA | +0.386 |
UCHIJ | +0.376 |
Neg logit contributions | |
emetery | -0.491 |
ospel | -0.485 |
vernment | -0.473 |
ppa | -0.472 |
appa | -0.452 |
Token | commit |
Token ID | 4589 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
Frie | +0.734 |
spir | +0.706 |
Male | +0.668 |
AAA | +0.654 |
UCHIJ | +0.638 |
Neg logit contributions | |
emetery | -0.743 |
ospel | -0.733 |
vernment | -0.716 |
ppa | -0.712 |
appa | -0.681 |
Token | ourselves |
Token ID | 6731 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
emetery | +3.579 |
ospel | +3.554 |
vernment | +3.494 |
ppa | +3.464 |
Kak | +3.334 |
Neg logit contributions | |
Frie | -3.766 |
spir | -3.629 |
Male | -3.430 |
UCHIJ | -3.358 |
querque | -3.355 |
Token | very |
Token ID | 845 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
emetery | +5.438 |
ospel | +5.356 |
vernment | +5.356 |
ppa | +5.272 |
Kak | +5.122 |
Neg logit contributions | |
Frie | -6.063 |
spir | -5.821 |
UCHIJ | -5.476 |
Male | -5.449 |
querque | -5.387 |
Token | res |
Token ID | 581 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
emetery | +0.971 |
ospel | +0.957 |
vernment | +0.936 |
ppa | +0.934 |
appa | +0.888 |
Neg logit contributions | |
Frie | -1.296 |
spir | -1.255 |
Male | -1.194 |
AAA | -1.167 |
UCHIJ | -1.164 |
Token | olutely |
Token ID | 16780 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
emetery | +0.654 |
ospel | +0.644 |
ppa | +0.627 |
vernment | +0.624 |
appa | +0.583 |
Neg logit contributions | |
Frie | -1.113 |
spir | -1.073 |
Male | -1.032 |
AAA | -1.015 |
querque | -1.005 |
Token | because |
Token ID | 780 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
emetery | +1.225 |
ospel | +1.217 |
vernment | +1.199 |
ppa | +1.192 |
appa | +1.138 |
Neg logit contributions | |
Frie | -1.163 |
spir | -1.118 |
Male | -1.052 |
AAA | -1.028 |
UCHIJ | -1.017 |
Token | there |
Token ID | 612 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
emetery | +0.766 |
ospel | +0.759 |
vernment | +0.741 |
ppa | +0.739 |
appa | +0.704 |
Neg logit contributions | |
Frie | -0.819 |
spir | -0.790 |
Male | -0.748 |
AAA | -0.728 |
querque | -0.721 |
Token | as |
Token ID | 355 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
emetery | +1.065 |
ospel | +1.050 |
ppa | +1.029 |
vernment | +1.026 |
appa | +0.984 |
Neg logit contributions | |
Frie | -1.042 |
spir | -0.998 |
Male | -0.947 |
AAA | -0.920 |
UCHIJ | -0.909 |
Token | the |
Token ID | 262 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
emetery | +1.129 |
ospel | +1.119 |
ppa | +1.089 |
vernment | +1.085 |
Kak | +1.044 |
Neg logit contributions | |
Frie | -1.307 |
spir | -1.261 |
Male | -1.202 |
AAA | -1.159 |
UCHIJ | -1.156 |
Token | Caps |
Token ID | 23534 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
emetery | +0.480 |
ospel | +0.475 |
ppa | +0.463 |
vernment | +0.463 |
appa | +0.441 |
Neg logit contributions | |
Frie | -0.539 |
spir | -0.520 |
Male | -0.494 |
AAA | -0.481 |
UCHIJ | -0.475 |
Token | out |
Token ID | 503 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
emetery | +1.467 |
ospel | +1.450 |
ppa | +1.421 |
vernment | +1.418 |
appa | +1.353 |
Neg logit contributions | |
Frie | -1.529 |
spir | -1.465 |
Male | -1.391 |
AAA | -1.352 |
UCHIJ | -1.334 |
Token | - |
Token ID | 12 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
emetery | +0.312 |
ospel | +0.309 |
vernment | +0.302 |
ppa | +0.301 |
appa | +0.288 |
Neg logit contributions | |
Frie | -0.286 |
spir | -0.274 |
Male | -0.259 |
AAA | -0.253 |
UCHIJ | -0.247 |
Token | shot |
Token ID | 9442 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
emetery | +1.076 |
ospel | +1.070 |
ppa | +1.050 |
vernment | +1.040 |
appa | +0.998 |
Neg logit contributions | |
Frie | -1.060 |
spir | -0.998 |
Male | -0.952 |
AAA | -0.937 |
querque | -0.923 |
Token | the |
Token ID | 262 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
ospel | +4.915 |
emetery | +4.894 |
ppa | +4.775 |
Kak | +4.742 |
vernment | +4.721 |
Neg logit contributions | |
Frie | -6.451 |
spir | -6.202 |
Male | -6.020 |
querque | -5.753 |
UCHIJ | -5.700 |
Token | Blues |
Token ID | 15261 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
emetery | +2.606 |
ospel | +2.601 |
ppa | +2.562 |
vernment | +2.546 |
Kak | +2.462 |
Neg logit contributions | |
Frie | -1.879 |
spir | -1.789 |
Male | -1.686 |
UCHIJ | -1.603 |
querque | -1.593 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
emetery | +3.300 |
ospel | +3.247 |
ppa | +3.201 |
vernment | +3.178 |
appa | +3.043 |
Neg logit contributions | |
Frie | -3.779 |
spir | -3.609 |
Male | -3.449 |
querque | -3.324 |
UCHIJ | -3.308 |
Token | - |
Token ID | 12 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
emetery | +1.670 |
ospel | +1.640 |
ppa | +1.610 |
vernment | +1.607 |
appa | +1.542 |
Neg logit contributions | |
Frie | -1.448 |
spir | -1.378 |
Male | -1.297 |
AAA | -1.266 |
querque | -1.248 |
Token | 8 |
Token ID | 23 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
emetery | +1.103 |
ospel | +1.096 |
ppa | +1.073 |
vernment | +1.065 |
appa | +1.023 |
Neg logit contributions | |
Frie | -1.195 |
spir | -1.133 |
Male | -1.076 |
AAA | -1.064 |
querque | -1.048 |
Token | training |
Token ID | 3047 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
Frie | +0.126 |
spir | +0.121 |
Male | +0.114 |
AAA | +0.112 |
UCHIJ | +0.109 |
Neg logit contributions | |
emetery | -0.137 |
ospel | -0.136 |
vernment | -0.133 |
ppa | -0.132 |
appa | -0.127 |
Token | ground |
Token ID | 2323 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
emetery | +0.009 |
ospel | +0.009 |
vernment | +0.009 |
ppa | +0.009 |
appa | +0.008 |
Neg logit contributions | |
Frie | -0.008 |
spir | -0.008 |
Male | -0.007 |
AAA | -0.007 |
UCHIJ | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
Frie | +0.279 |
spir | +0.268 |
Male | +0.254 |
AAA | +0.247 |
UCHIJ | +0.243 |
Neg logit contributions | |
emetery | -0.292 |
ospel | -0.289 |
vernment | -0.282 |
ppa | -0.282 |
appa | -0.270 |
Token | I |
Token ID | 314 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
emetery | +0.046 |
ospel | +0.046 |
ppa | +0.045 |
vernment | +0.045 |
appa | +0.043 |
Neg logit contributions | |
Frie | -0.050 |
spir | -0.048 |
Male | -0.045 |
AAA | -0.044 |
querque | -0.044 |
Token | was |
Token ID | 373 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
emetery | +1.149 |
ospel | +1.139 |
vernment | +1.115 |
ppa | +1.111 |
appa | +1.063 |
Neg logit contributions | |
Frie | -1.107 |
spir | -1.061 |
Male | -1.004 |
AAA | -0.981 |
UCHIJ | -0.963 |
Token | lucky |
Token ID | 9670 |
Feature activation | -7.59e+00 |
Pos logit contributions | |
emetery | +2.002 |
ospel | +1.972 |
ppa | +1.942 |
vernment | +1.922 |
appa | +1.863 |
Neg logit contributions | |
Frie | -1.998 |
spir | -1.920 |
Male | -1.810 |
AAA | -1.757 |
querque | -1.754 |
Token | . |
Token ID | 13 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
ospel | +4.411 |
emetery | +4.409 |
ppa | +4.341 |
vernment | +4.304 |
Kak | +4.226 |
Neg logit contributions | |
Frie | -6.786 |
spir | -6.554 |
Male | -6.292 |
querque | -6.269 |
UCHIJ | -6.193 |
Token | I |
Token ID | 314 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
emetery | +0.467 |
ospel | +0.465 |
ppa | +0.454 |
vernment | +0.450 |
Kak | +0.431 |
Neg logit contributions | |
Frie | -0.509 |
spir | -0.492 |
Male | -0.465 |
AAA | -0.453 |
querque | -0.452 |
Token | was |
Token ID | 373 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
emetery | +0.933 |
ospel | +0.925 |
vernment | +0.904 |
ppa | +0.901 |
appa | +0.861 |
Neg logit contributions | |
Frie | -0.940 |
spir | -0.902 |
Male | -0.854 |
AAA | -0.835 |
UCHIJ | -0.820 |
Token | in |
Token ID | 287 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
emetery | +1.172 |
ospel | +1.155 |
ppa | +1.134 |
vernment | +1.125 |
appa | +1.085 |
Neg logit contributions | |
Frie | -1.165 |
spir | -1.122 |
Male | -1.058 |
AAA | -1.026 |
querque | -1.020 |
Token | a |
Token ID | 257 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
emetery | +2.095 |
ospel | +2.094 |
ppa | +2.035 |
vernment | +2.018 |
Kak | +1.947 |
Neg logit contributions | |
Frie | -2.282 |
spir | -2.226 |
Male | -2.108 |
querque | -2.026 |
AAA | -2.021 |
Token | el |
Token ID | 417 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Frie | +1.140 |
spir | +1.098 |
Male | +1.022 |
AAA | +1.001 |
UCHIJ | +0.976 |
Neg logit contributions | |
emetery | -1.295 |
ospel | -1.278 |
vernment | -1.256 |
ppa | -1.250 |
appa | -1.193 |
Token | m |
Token ID | 76 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Frie | +1.486 |
spir | +1.431 |
Male | +1.332 |
AAA | +1.311 |
UCHIJ | +1.275 |
Neg logit contributions | |
emetery | -1.597 |
ospel | -1.569 |
vernment | -1.540 |
ppa | -1.522 |
appa | -1.458 |
Token | ose |
Token ID | 577 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
emetery | +0.778 |
ospel | +0.773 |
ppa | +0.754 |
vernment | +0.751 |
appa | +0.719 |
Neg logit contributions | |
Frie | -0.879 |
spir | -0.846 |
Male | -0.807 |
AAA | -0.787 |
UCHIJ | -0.776 |
Token | , |
Token ID | 11 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
emetery | +0.346 |
ospel | +0.343 |
ppa | +0.336 |
vernment | +0.335 |
appa | +0.318 |
Neg logit contributions | |
Frie | -0.393 |
spir | -0.380 |
Male | -0.362 |
AAA | -0.353 |
UCHIJ | -0.348 |
Token | an |
Token ID | 281 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
emetery | +1.024 |
ospel | +1.013 |
vernment | +0.989 |
ppa | +0.984 |
appa | +0.938 |
Neg logit contributions | |
Frie | -1.175 |
spir | -1.137 |
Male | -1.078 |
AAA | -1.051 |
querque | -1.037 |
Token | Ike |
Token ID | 34880 |
Feature activation | -7.58e+00 |
Pos logit contributions | |
emetery | +1.808 |
ospel | +1.788 |
vernment | +1.738 |
ppa | +1.720 |
appa | +1.646 |
Neg logit contributions | |
Frie | -2.871 |
spir | -2.803 |
Male | -2.678 |
querque | -2.596 |
AAA | -2.591 |
Token | a |
Token ID | 64 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ospel | +4.196 |
ppa | +4.060 |
emetery | +4.053 |
vernment | +3.880 |
appa | +3.879 |
Neg logit contributions | |
Frie | -7.502 |
spir | -7.060 |
querque | -6.841 |
Male | -6.774 |
UCHIJ | -6.622 |
Token | manager |
Token ID | 4706 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
emetery | +1.462 |
ospel | +1.443 |
vernment | +1.410 |
ppa | +1.400 |
appa | +1.335 |
Neg logit contributions | |
Frie | -1.803 |
spir | -1.745 |
Male | -1.659 |
AAA | -1.616 |
querque | -1.600 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
emetery | +1.507 |
ospel | +1.488 |
vernment | +1.459 |
ppa | +1.449 |
appa | +1.392 |
Neg logit contributions | |
Frie | -1.675 |
spir | -1.626 |
Male | -1.535 |
AAA | -1.492 |
querque | -1.487 |
Token | " |
Token ID | 366 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
emetery | +0.985 |
ospel | +0.975 |
vernment | +0.953 |
ppa | +0.950 |
appa | +0.905 |
Neg logit contributions | |
Frie | -1.053 |
spir | -1.013 |
Male | -0.958 |
AAA | -0.940 |
querque | -0.929 |
Token | The |
Token ID | 464 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
Frie | +1.124 |
spir | +1.083 |
Male | +1.031 |
AAA | +0.982 |
UCHIJ | +0.958 |
Neg logit contributions | |
emetery | -1.534 |
ospel | -1.511 |
vernment | -1.488 |
ppa | -1.469 |
appa | -1.421 |
Token | in |
Token ID | 287 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Frie | +0.022 |
spir | +0.021 |
Male | +0.020 |
AAA | +0.019 |
UCHIJ | +0.019 |
Neg logit contributions | |
emetery | -0.022 |
ospel | -0.022 |
vernment | -0.021 |
ppa | -0.021 |
appa | -0.020 |
Token | 1999 |
Token ID | 7358 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
emetery | +0.366 |
ospel | +0.362 |
vernment | +0.353 |
ppa | +0.352 |
appa | +0.335 |
Neg logit contributions | |
Frie | -0.408 |
spir | -0.393 |
Male | -0.373 |
AAA | -0.365 |
UCHIJ | -0.358 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
emetery | +0.641 |
ospel | +0.632 |
vernment | +0.620 |
ppa | +0.618 |
appa | +0.589 |
Neg logit contributions | |
Frie | -0.649 |
spir | -0.626 |
Male | -0.590 |
AAA | -0.577 |
UCHIJ | -0.567 |
Token | Am |
Token ID | 1703 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
Frie | +0.022 |
spir | +0.021 |
Male | +0.020 |
AAA | +0.019 |
querque | +0.019 |
Neg logit contributions | |
emetery | -0.022 |
ospel | -0.021 |
ppa | -0.021 |
vernment | -0.021 |
appa | -0.020 |
Token | ad |
Token ID | 324 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
emetery | +0.640 |
ospel | +0.633 |
vernment | +0.618 |
ppa | +0.616 |
appa | +0.588 |
Neg logit contributions | |
Frie | -0.656 |
spir | -0.631 |
Male | -0.598 |
AAA | -0.585 |
UCHIJ | -0.574 |
Token | ou |
Token ID | 280 |
Feature activation | -7.54e+00 |
Pos logit contributions | |
ospel | +4.112 |
emetery | +4.045 |
ppa | +4.010 |
vernment | +4.007 |
Kak | +3.918 |
Neg logit contributions | |
Frie | -2.314 |
spir | -2.195 |
Male | -2.045 |
AAA | -1.956 |
UCHIJ | -1.908 |
Token | Di |
Token ID | 6031 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
vernment | +5.315 |
ospel | +5.263 |
emetery | +5.208 |
ppa | +5.195 |
Kak | +5.100 |
Neg logit contributions | |
Frie | -5.817 |
spir | -5.778 |
Male | -5.456 |
UCHIJ | -5.289 |
AAA | -5.272 |
Token | allo |
Token ID | 49457 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
emetery | +0.045 |
ospel | +0.044 |
vernment | +0.043 |
ppa | +0.043 |
appa | +0.041 |
Neg logit contributions | |
Frie | -0.040 |
spir | -0.039 |
Male | -0.036 |
AAA | -0.036 |
UCHIJ | -0.035 |
Token | said |
Token ID | 531 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
Frie | +0.207 |
spir | +0.200 |
Male | +0.189 |
AAA | +0.185 |
UCHIJ | +0.183 |
Neg logit contributions | |
emetery | -0.190 |
ospel | -0.188 |
vernment | -0.184 |
ppa | -0.184 |
appa | -0.175 |
Token | he |
Token ID | 339 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
emetery | +0.718 |
ospel | +0.710 |
vernment | +0.692 |
ppa | +0.691 |
appa | +0.661 |
Neg logit contributions | |
Frie | -0.790 |
spir | -0.766 |
Male | -0.724 |
AAA | -0.703 |
UCHIJ | -0.698 |
Token | was |
Token ID | 373 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
Frie | +1.022 |
spir | +0.980 |
Male | +0.922 |
AAA | +0.902 |
UCHIJ | +0.878 |
Neg logit contributions | |
emetery | -1.150 |
ospel | -1.133 |
vernment | -1.100 |
ppa | -1.092 |
appa | -1.047 |
Token | in |
Token ID | 287 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
emetery | +0.384 |
ospel | +0.380 |
vernment | +0.372 |
ppa | +0.371 |
appa | +0.353 |
Neg logit contributions | |
Frie | -0.415 |
spir | -0.399 |
Male | -0.379 |
AAA | -0.369 |
UCHIJ | -0.365 |
Token | Spain |
Token ID | 8602 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
emetery | +1.240 |
ospel | +1.226 |
vernment | +1.206 |
ppa | +1.202 |
Kak | +1.143 |
Neg logit contributions | |
Frie | -1.271 |
spir | -1.218 |
Male | -1.163 |
AAA | -1.119 |
querque | -1.119 |
Token | , |
Token ID | 11 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
emetery | +0.308 |
ospel | +0.304 |
vernment | +0.298 |
ppa | +0.296 |
appa | +0.282 |
Neg logit contributions | |
Frie | -0.345 |
spir | -0.333 |
Male | -0.316 |
AAA | -0.309 |
UCHIJ | -0.304 |
Token | should |
Token ID | 815 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
emetery | +0.662 |
ospel | +0.655 |
vernment | +0.641 |
ppa | +0.639 |
appa | +0.611 |
Neg logit contributions | |
Frie | -0.619 |
spir | -0.595 |
Male | -0.561 |
AAA | -0.547 |
UCHIJ | -0.537 |
Token | expose |
Token ID | 15651 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
emetery | +0.934 |
ospel | +0.926 |
vernment | +0.906 |
ppa | +0.903 |
appa | +0.864 |
Neg logit contributions | |
Frie | -0.884 |
spir | -0.848 |
Male | -0.802 |
AAA | -0.781 |
UCHIJ | -0.768 |
Token | themselves |
Token ID | 2405 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
emetery | +1.217 |
ospel | +1.204 |
vernment | +1.173 |
ppa | +1.168 |
appa | +1.097 |
Neg logit contributions | |
Frie | -1.840 |
spir | -1.780 |
Male | -1.704 |
AAA | -1.664 |
UCHIJ | -1.649 |
Token | to |
Token ID | 284 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
emetery | +5.163 |
vernment | +5.121 |
ospel | +5.091 |
ppa | +5.034 |
Kak | +4.888 |
Neg logit contributions | |
Frie | -6.090 |
spir | -5.735 |
Male | -5.468 |
UCHIJ | -5.439 |
querque | -5.393 |
Token | the |
Token ID | 262 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
emetery | +2.773 |
ospel | +2.759 |
vernment | +2.708 |
ppa | +2.692 |
Kak | +2.584 |
Neg logit contributions | |
Frie | -3.292 |
spir | -3.165 |
Male | -3.014 |
querque | -2.923 |
AAA | -2.900 |
Token | challenge |
Token ID | 4427 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
emetery | +1.665 |
ospel | +1.662 |
vernment | +1.617 |
ppa | +1.617 |
appa | +1.530 |
Neg logit contributions | |
Frie | -2.355 |
spir | -2.267 |
Male | -2.186 |
querque | -2.116 |
UCHIJ | -2.106 |
Token | of |
Token ID | 286 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
Frie | +0.223 |
spir | +0.215 |
Male | +0.203 |
AAA | +0.199 |
UCHIJ | +0.194 |
Neg logit contributions | |
emetery | -0.225 |
ospel | -0.222 |
vernment | -0.216 |
ppa | -0.215 |
appa | -0.206 |
Token | advancing |
Token ID | 19988 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
emetery | +2.434 |
ospel | +2.410 |
vernment | +2.380 |
ppa | +2.375 |
Kak | +2.272 |
Neg logit contributions | |
Frie | -2.626 |
spir | -2.521 |
Male | -2.403 |
querque | -2.327 |
UCHIJ | -2.306 |
Token |
|
Token ID | 198 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
ospel | +0.398 |
emetery | +0.397 |
ppa | +0.389 |
vernment | +0.385 |
appa | +0.370 |
Neg logit contributions | |
Frie | -0.422 |
spir | -0.401 |
Male | -0.379 |
querque | -0.376 |
AAA | -0.371 |
Token | Wiki |
Token ID | 32603 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
emetery | +0.427 |
ospel | +0.424 |
ppa | +0.417 |
vernment | +0.416 |
appa | +0.400 |
Neg logit contributions | |
Frie | -0.360 |
spir | -0.340 |
Male | -0.317 |
AAA | -0.314 |
querque | -0.312 |
Token | Leaks |
Token ID | 17874 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
emetery | +1.101 |
ospel | +1.091 |
ppa | +1.077 |
vernment | +1.071 |
appa | +1.032 |
Neg logit contributions | |
Frie | -0.862 |
spir | -0.809 |
Male | -0.754 |
AAA | -0.740 |
querque | -0.737 |
Token | pr |
Token ID | 778 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
emetery | +3.604 |
vernment | +3.536 |
ppa | +3.514 |
ospel | +3.507 |
Kak | +3.397 |
Neg logit contributions | |
Frie | -4.149 |
spir | -3.992 |
Male | -3.814 |
querque | -3.700 |
AAA | -3.640 |
Token | ides |
Token ID | 1460 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
emetery | +0.159 |
ospel | +0.156 |
vernment | +0.151 |
ppa | +0.150 |
appa | +0.139 |
Neg logit contributions | |
Frie | -0.324 |
spir | -0.315 |
Male | -0.302 |
AAA | -0.297 |
UCHIJ | -0.293 |
Token | itself |
Token ID | 2346 |
Feature activation | -7.50e+00 |
Pos logit contributions | |
vernment | +2.597 |
emetery | +2.583 |
ospel | +2.568 |
ppa | +2.434 |
Kak | +2.364 |
Neg logit contributions | |
Frie | -4.840 |
spir | -4.709 |
Male | -4.494 |
querque | -4.410 |
UCHIJ | -4.373 |
Token | as |
Token ID | 355 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
emetery | +4.818 |
vernment | +4.709 |
ospel | +4.683 |
ppa | +4.467 |
appa | +4.369 |
Neg logit contributions | |
Frie | -6.624 |
spir | -6.315 |
Male | -5.974 |
querque | -5.858 |
AAA | -5.853 |
Token | a |
Token ID | 257 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
emetery | +3.133 |
vernment | +3.097 |
ospel | +3.097 |
ppa | +2.986 |
Kak | +2.889 |
Neg logit contributions | |
Frie | -3.514 |
spir | -3.342 |
Male | -3.179 |
querque | -3.088 |
UCHIJ | -3.080 |
Token | website |
Token ID | 3052 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
emetery | +1.937 |
ospel | +1.923 |
vernment | +1.911 |
ppa | +1.870 |
Kak | +1.791 |
Neg logit contributions | |
Frie | -2.048 |
spir | -1.955 |
Male | -1.861 |
querque | -1.804 |
AAA | -1.787 |
Token | devoted |
Token ID | 13378 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
emetery | +2.358 |
ospel | +2.328 |
vernment | +2.323 |
ppa | +2.273 |
Kak | +2.183 |
Neg logit contributions | |
Frie | -2.477 |
spir | -2.371 |
Male | -2.271 |
AAA | -2.181 |
querque | -2.180 |
Token | to |
Token ID | 284 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
emetery | +3.098 |
ospel | +3.073 |
vernment | +3.061 |
ppa | +2.973 |
appa | +2.846 |
Neg logit contributions | |
Frie | -3.105 |
spir | -2.962 |
Male | -2.813 |
AAA | -2.725 |
UCHIJ | -2.710 |
Token | or |
Token ID | 393 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Frie | +0.331 |
spir | +0.317 |
Male | +0.301 |
AAA | +0.294 |
UCHIJ | +0.288 |
Neg logit contributions | |
emetery | -0.333 |
ospel | -0.330 |
vernment | -0.322 |
ppa | -0.321 |
appa | -0.306 |
Token | am |
Token ID | 716 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Frie | +0.923 |
spir | +0.883 |
Male | +0.837 |
AAA | +0.818 |
UCHIJ | +0.797 |
Neg logit contributions | |
emetery | -0.996 |
ospel | -0.985 |
vernment | -0.960 |
ppa | -0.958 |
appa | -0.915 |
Token | I |
Token ID | 314 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
Frie | +2.237 |
spir | +2.183 |
Male | +2.068 |
AAA | +2.003 |
UCHIJ | +1.966 |
Neg logit contributions | |
emetery | -1.993 |
ospel | -1.978 |
vernment | -1.959 |
ppa | -1.945 |
appa | -1.816 |
Token | fool |
Token ID | 9192 |
Feature activation | -8.10e+00 |
Pos logit contributions | |
emetery | +2.370 |
ospel | +2.332 |
vernment | +2.302 |
ppa | +2.298 |
Kak | +2.214 |
Neg logit contributions | |
Frie | -2.543 |
spir | -2.431 |
Male | -2.290 |
AAA | -2.258 |
UCHIJ | -2.247 |
Token | ing |
Token ID | 278 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
ospel | +4.629 |
vernment | +4.612 |
emetery | +4.602 |
ppa | +4.470 |
appa | +4.305 |
Neg logit contributions | |
Frie | -7.270 |
spir | -7.022 |
Male | -6.878 |
querque | -6.731 |
UCHIJ | -6.711 |
Token | myself |
Token ID | 3589 |
Feature activation | -7.43e+00 |
Pos logit contributions | |
emetery | +2.676 |
ospel | +2.640 |
vernment | +2.620 |
ppa | +2.582 |
Kak | +2.445 |
Neg logit contributions | |
Frie | -3.516 |
spir | -3.383 |
Male | -3.230 |
querque | -3.158 |
AAA | -3.120 |
Token | ? |
Token ID | 30 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
emetery | +5.221 |
ppa | +5.117 |
vernment | +5.103 |
ospel | +5.074 |
Kak | +4.888 |
Neg logit contributions | |
Frie | -5.884 |
spir | -5.719 |
Male | -5.330 |
querque | -5.304 |
UCHIJ | -5.259 |
Token |
|
Token ID | 198 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
emetery | +0.302 |
ospel | +0.299 |
ppa | +0.293 |
vernment | +0.292 |
appa | +0.279 |
Neg logit contributions | |
Frie | -0.309 |
spir | -0.297 |
Male | -0.281 |
AAA | -0.274 |
querque | -0.271 |
Token |
|
Token ID | 198 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Frie | +0.515 |
spir | +0.495 |
Male | +0.468 |
AAA | +0.458 |
UCHIJ | +0.448 |
Neg logit contributions | |
emetery | -0.529 |
ospel | -0.523 |
vernment | -0.512 |
ppa | -0.509 |
appa | -0.487 |
Token | All |
Token ID | 3237 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
emetery | +0.357 |
ospel | +0.355 |
ppa | +0.348 |
vernment | +0.346 |
appa | +0.332 |
Neg logit contributions | |
Frie | -0.309 |
spir | -0.294 |
Male | -0.274 |
AAA | -0.271 |
querque | -0.269 |
Token | these |
Token ID | 777 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Frie | +1.761 |
spir | +1.696 |
Male | +1.612 |
AAA | +1.587 |
UCHIJ | +1.533 |
Neg logit contributions | |
emetery | -1.720 |
ospel | -1.697 |
vernment | -1.671 |
ppa | -1.647 |
appa | -1.578 |
Token | kingdom |
Token ID | 13239 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ospel | +1.184 |
emetery | +1.172 |
vernment | +1.153 |
ppa | +1.127 |
appa | +1.071 |
Neg logit contributions | |
Frie | -1.983 |
spir | -1.928 |
Male | -1.851 |
AAA | -1.806 |
querque | -1.785 |
Token | for |
Token ID | 329 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
emetery | +0.893 |
ospel | +0.883 |
vernment | +0.864 |
ppa | +0.858 |
appa | +0.820 |
Neg logit contributions | |
Frie | -0.975 |
spir | -0.941 |
Male | -0.893 |
AAA | -0.870 |
querque | -0.859 |
Token | alleged |
Token ID | 4260 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Frie | +0.929 |
spir | +0.896 |
Male | +0.848 |
AAA | +0.836 |
UCHIJ | +0.815 |
Neg logit contributions | |
emetery | -0.849 |
ospel | -0.839 |
vernment | -0.818 |
ppa | -0.818 |
appa | -0.778 |
Token | anti |
Token ID | 3098 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
emetery | +0.886 |
ospel | +0.878 |
vernment | +0.857 |
ppa | +0.850 |
Kak | +0.816 |
Neg logit contributions | |
Frie | -0.908 |
spir | -0.873 |
Male | -0.830 |
querque | -0.798 |
AAA | -0.796 |
Token | - |
Token ID | 12 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Frie | +0.188 |
spir | +0.179 |
Male | +0.169 |
AAA | +0.165 |
querque | +0.161 |
Neg logit contributions | |
emetery | -0.233 |
ospel | -0.231 |
vernment | -0.227 |
ppa | -0.226 |
appa | -0.217 |
Token | state |
Token ID | 5219 |
Feature activation | -7.30e+00 |
Pos logit contributions | |
ospel | +1.626 |
emetery | +1.620 |
vernment | +1.592 |
ppa | +1.543 |
appa | +1.507 |
Neg logit contributions | |
Frie | -2.279 |
spir | -2.139 |
AAA | -2.053 |
querque | -2.042 |
Male | -2.040 |
Token | acts |
Token ID | 6529 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
ospel | +4.551 |
emetery | +4.516 |
vernment | +4.476 |
Kak | +4.342 |
ppa | +4.296 |
Neg logit contributions | |
Frie | -6.365 |
spir | -5.949 |
Male | -5.911 |
querque | -5.727 |
UCHIJ | -5.705 |
Token | , |
Token ID | 11 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
emetery | +1.872 |
ospel | +1.828 |
vernment | +1.821 |
ppa | +1.799 |
appa | +1.721 |
Neg logit contributions | |
Frie | -2.237 |
spir | -2.164 |
Male | -2.059 |
AAA | -2.008 |
querque | -1.995 |
Token | died |
Token ID | 3724 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
emetery | +0.339 |
ospel | +0.335 |
vernment | +0.329 |
ppa | +0.328 |
appa | +0.315 |
Neg logit contributions | |
Frie | -0.283 |
spir | -0.271 |
Male | -0.255 |
AAA | -0.247 |
querque | -0.244 |
Token | at |
Token ID | 379 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Frie | +2.539 |
spir | +2.421 |
Male | +2.291 |
AAA | +2.276 |
UCHIJ | +2.203 |
Neg logit contributions | |
emetery | -2.690 |
ospel | -2.688 |
vernment | -2.618 |
ppa | -2.601 |
appa | -2.481 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
emetery | +0.126 |
ospel | +0.124 |
vernment | +0.121 |
ppa | +0.121 |
appa | +0.115 |
Neg logit contributions | |
Frie | -0.137 |
spir | -0.133 |
Male | -0.126 |
AAA | -0.123 |
UCHIJ | -0.121 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
emetery | +0.418 |
ospel | +0.414 |
vernment | +0.405 |
ppa | +0.403 |
appa | +0.384 |
Neg logit contributions | |
Frie | -0.463 |
spir | -0.446 |
Male | -0.423 |
AAA | -0.412 |
querque | -0.409 |
Token | idea |
Token ID | 2126 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Frie | +0.155 |
spir | +0.150 |
Male | +0.142 |
AAA | +0.140 |
UCHIJ | +0.137 |
Neg logit contributions | |
emetery | -0.126 |
ospel | -0.124 |
vernment | -0.121 |
ppa | -0.120 |
appa | -0.114 |
Token | that |
Token ID | 326 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
Frie | +1.187 |
spir | +1.140 |
Male | +1.073 |
AAA | +1.057 |
UCHIJ | +1.024 |
Neg logit contributions | |
emetery | -1.270 |
ospel | -1.254 |
vernment | -1.221 |
ppa | -1.220 |
appa | -1.168 |
Token | a |
Token ID | 257 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
emetery | +0.427 |
ospel | +0.423 |
vernment | +0.414 |
ppa | +0.413 |
appa | +0.394 |
Neg logit contributions | |
Frie | -0.436 |
spir | -0.419 |
Male | -0.397 |
AAA | -0.386 |
querque | -0.382 |
Token | foreign |
Token ID | 3215 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
emetery | +0.104 |
ospel | +0.102 |
vernment | +0.100 |
ppa | +0.100 |
appa | +0.095 |
Neg logit contributions | |
Frie | -0.102 |
spir | -0.098 |
Male | -0.093 |
AAA | -0.091 |
UCHIJ | -0.089 |
Token | state |
Token ID | 1181 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
emetery | +0.187 |
ospel | +0.185 |
vernment | +0.180 |
ppa | +0.179 |
appa | +0.171 |
Neg logit contributions | |
Frie | -0.208 |
spir | -0.200 |
Male | -0.190 |
AAA | -0.186 |
UCHIJ | -0.183 |
Token | could |
Token ID | 714 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
emetery | +4.981 |
ppa | +4.968 |
ospel | +4.901 |
vernment | +4.869 |
Kak | +4.778 |
Neg logit contributions | |
Frie | -5.927 |
spir | -5.478 |
Male | -5.251 |
querque | -5.189 |
UCHIJ | -5.135 |
Token | be |
Token ID | 307 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ospel | +1.731 |
emetery | +1.730 |
ppa | +1.694 |
vernment | +1.684 |
appa | +1.618 |
Neg logit contributions | |
Frie | -1.636 |
spir | -1.547 |
Male | -1.473 |
AAA | -1.420 |
querque | -1.418 |
Token | trying |
Token ID | 2111 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
emetery | +1.562 |
ospel | +1.547 |
ppa | +1.520 |
vernment | +1.511 |
appa | +1.461 |
Neg logit contributions | |
Frie | -1.534 |
spir | -1.456 |
Male | -1.383 |
AAA | -1.336 |
querque | -1.330 |
Token | to |
Token ID | 284 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
emetery | +2.327 |
ospel | +2.304 |
vernment | +2.267 |
ppa | +2.250 |
appa | +2.152 |
Neg logit contributions | |
Frie | -2.245 |
spir | -2.138 |
Male | -2.024 |
AAA | -1.962 |
UCHIJ | -1.938 |
Token | influence |
Token ID | 4588 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ospel | +1.454 |
emetery | +1.453 |
ppa | +1.424 |
vernment | +1.419 |
appa | +1.353 |
Neg logit contributions | |
Frie | -1.627 |
spir | -1.554 |
Male | -1.486 |
querque | -1.433 |
AAA | -1.432 |
Token | enemies |
Token ID | 5775 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
Frie | +0.356 |
spir | +0.344 |
Male | +0.324 |
AAA | +0.319 |
UCHIJ | +0.311 |
Neg logit contributions | |
emetery | -0.343 |
ospel | -0.339 |
vernment | -0.330 |
ppa | -0.329 |
appa | -0.313 |
Token | of |
Token ID | 286 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
emetery | +1.661 |
ospel | +1.641 |
vernment | +1.614 |
ppa | +1.606 |
appa | +1.531 |
Neg logit contributions | |
Frie | -1.786 |
spir | -1.720 |
Male | -1.632 |
AAA | -1.593 |
querque | -1.576 |
Token | the |
Token ID | 262 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
emetery | +1.765 |
ospel | +1.750 |
vernment | +1.719 |
ppa | +1.702 |
Kak | +1.629 |
Neg logit contributions | |
Frie | -1.967 |
spir | -1.898 |
Male | -1.802 |
AAA | -1.753 |
querque | -1.742 |
Token | North |
Token ID | 2258 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
emetery | +1.135 |
ospel | +1.132 |
vernment | +1.111 |
ppa | +1.097 |
Kak | +1.052 |
Neg logit contributions | |
Frie | -1.301 |
spir | -1.256 |
Male | -1.194 |
querque | -1.161 |
AAA | -1.158 |
Token | Korean |
Token ID | 6983 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
emetery | +1.637 |
ospel | +1.619 |
vernment | +1.584 |
ppa | +1.571 |
appa | +1.492 |
Neg logit contributions | |
Frie | -2.123 |
spir | -2.050 |
Male | -1.954 |
AAA | -1.915 |
querque | -1.898 |
Token | state |
Token ID | 1181 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
ospel | +2.389 |
emetery | +2.384 |
vernment | +2.367 |
ppa | +2.322 |
Kak | +2.232 |
Neg logit contributions | |
Frie | -2.843 |
spir | -2.737 |
Male | -2.605 |
querque | -2.558 |
AAA | -2.532 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
emetery | +4.757 |
vernment | +4.745 |
ospel | +4.732 |
ppa | +4.682 |
Kak | +4.557 |
Neg logit contributions | |
Frie | -6.081 |
spir | -5.737 |
Male | -5.537 |
querque | -5.473 |
UCHIJ | -5.426 |
Token | The |
Token ID | 383 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ospel | +1.374 |
emetery | +1.374 |
ppa | +1.347 |
vernment | +1.336 |
Kak | +1.292 |
Neg logit contributions | |
Frie | -1.432 |
spir | -1.388 |
Male | -1.307 |
querque | -1.290 |
AAA | -1.267 |
Token | only |
Token ID | 691 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
emetery | +1.237 |
ospel | +1.224 |
vernment | +1.196 |
ppa | +1.191 |
appa | +1.136 |
Neg logit contributions | |
Frie | -1.409 |
spir | -1.360 |
Male | -1.294 |
AAA | -1.257 |
querque | -1.246 |
Token | recognizable |
Token ID | 30264 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Frie | +0.107 |
spir | +0.103 |
Male | +0.098 |
AAA | +0.097 |
UCHIJ | +0.095 |
Neg logit contributions | |
emetery | -0.091 |
ospel | -0.090 |
vernment | -0.087 |
ppa | -0.087 |
appa | -0.083 |
Token | special |
Token ID | 2041 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
emetery | +1.202 |
ospel | +1.190 |
vernment | +1.159 |
ppa | +1.154 |
appa | +1.097 |
Neg logit contributions | |
Frie | -1.377 |
spir | -1.324 |
Male | -1.258 |
AAA | -1.237 |
UCHIJ | -1.210 |
Token | � |
Token ID | 447 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
emetery | +0.381 |
ospel | +0.376 |
vernment | +0.367 |
ppa | +0.366 |
appa | +0.349 |
Neg logit contributions | |
Frie | -0.418 |
spir | -0.402 |
Male | -0.382 |
AAA | -0.373 |
UCHIJ | -0.367 |
Token | � |
Token ID | 247 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
emetery | +1.125 |
ospel | +1.116 |
vernment | +1.097 |
ppa | +1.095 |
appa | +1.061 |
Neg logit contributions | |
Frie | -0.514 |
spir | -0.484 |
Male | -0.441 |
AAA | -0.425 |
UCHIJ | -0.410 |
Token | which |
Token ID | 543 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
emetery | +0.897 |
ospel | +0.886 |
vernment | +0.865 |
ppa | +0.862 |
appa | +0.822 |
Neg logit contributions | |
Frie | -0.937 |
spir | -0.902 |
Male | -0.855 |
AAA | -0.836 |
UCHIJ | -0.820 |
Token | is |
Token ID | 318 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
emetery | +2.261 |
ospel | +2.245 |
ppa | +2.222 |
vernment | +2.197 |
appa | +2.119 |
Neg logit contributions | |
Frie | -2.099 |
spir | -2.004 |
Male | -1.900 |
querque | -1.832 |
AAA | -1.828 |
Token | the |
Token ID | 262 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
emetery | +1.689 |
ospel | +1.672 |
vernment | +1.636 |
ppa | +1.635 |
appa | +1.561 |
Neg logit contributions | |
Frie | -1.768 |
spir | -1.701 |
Male | -1.613 |
AAA | -1.561 |
querque | -1.553 |
Token | BIOS |
Token ID | 27553 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
emetery | +2.352 |
ospel | +2.345 |
ppa | +2.291 |
vernment | +2.275 |
Kak | +2.188 |
Neg logit contributions | |
Frie | -2.538 |
spir | -2.450 |
Male | -2.327 |
querque | -2.245 |
AAA | -2.230 |
Token | default |
Token ID | 4277 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
emetery | +4.948 |
ospel | +4.932 |
ppa | +4.887 |
vernment | +4.827 |
Kak | +4.714 |
Neg logit contributions | |
Frie | -5.687 |
spir | -5.605 |
Male | -5.305 |
querque | -5.135 |
UCHIJ | -5.060 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Frie | +0.482 |
spir | +0.461 |
Male | +0.437 |
AAA | +0.432 |
UCHIJ | +0.420 |
Neg logit contributions | |
emetery | -0.490 |
ospel | -0.482 |
vernment | -0.472 |
ppa | -0.468 |
appa | -0.447 |
Token | With |
Token ID | 2080 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
emetery | +1.233 |
ospel | +1.229 |
ppa | +1.200 |
vernment | +1.194 |
appa | +1.142 |
Neg logit contributions | |
Frie | -1.291 |
spir | -1.246 |
Male | -1.175 |
AAA | -1.145 |
querque | -1.141 |
Token | two |
Token ID | 734 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
emetery | +0.091 |
ospel | +0.090 |
vernment | +0.088 |
ppa | +0.087 |
appa | +0.083 |
Neg logit contributions | |
Frie | -0.094 |
spir | -0.090 |
Male | -0.086 |
AAA | -0.084 |
UCHIJ | -0.082 |
Token | cards |
Token ID | 4116 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
Frie | +0.785 |
spir | +0.751 |
Male | +0.711 |
AAA | +0.704 |
UCHIJ | +0.684 |
Neg logit contributions | |
emetery | -0.801 |
ospel | -0.792 |
vernment | -0.776 |
ppa | -0.767 |
appa | -0.734 |
Token | – |
Token ID | 784 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
Frie | +0.862 |
spir | +0.831 |
Male | +0.784 |
AAA | +0.770 |
UCHIJ | +0.751 |
Neg logit contributions | |
emetery | -0.835 |
ospel | -0.824 |
vernment | -0.801 |
ppa | -0.800 |
appa | -0.763 |
Token | they |
Token ID | 484 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
emetery | +0.281 |
ospel | +0.278 |
ppa | +0.271 |
vernment | +0.271 |
appa | +0.259 |
Neg logit contributions | |
Frie | -0.306 |
spir | -0.295 |
Male | -0.280 |
AAA | -0.273 |
querque | -0.269 |
Token | have |
Token ID | 423 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Frie | +0.851 |
spir | +0.825 |
Male | +0.766 |
AAA | +0.764 |
UCHIJ | +0.740 |
Neg logit contributions | |
emetery | -0.974 |
ospel | -0.954 |
vernment | -0.924 |
ppa | -0.924 |
appa | -0.882 |
Token | opened |
Token ID | 4721 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Frie | +0.337 |
spir | +0.324 |
Male | +0.305 |
AAA | +0.300 |
UCHIJ | +0.293 |
Neg logit contributions | |
emetery | -0.354 |
ospel | -0.350 |
vernment | -0.341 |
ppa | -0.340 |
appa | -0.325 |
Token | themselves |
Token ID | 2405 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
Frie | +1.739 |
spir | +1.684 |
Male | +1.581 |
AAA | +1.580 |
UCHIJ | +1.519 |
Neg logit contributions | |
emetery | -1.630 |
ospel | -1.613 |
vernment | -1.577 |
ppa | -1.560 |
appa | -1.492 |
Token | up |
Token ID | 510 |
Feature activation | -7.20e+00 |
Pos logit contributions | |
emetery | +3.881 |
ospel | +3.822 |
vernment | +3.743 |
ppa | +3.740 |
Kak | +3.610 |
Neg logit contributions | |
Frie | -3.758 |
spir | -3.553 |
Male | -3.371 |
UCHIJ | -3.268 |
querque | -3.261 |
Token | to |
Token ID | 284 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
emetery | +4.934 |
ospel | +4.906 |
vernment | +4.855 |
ppa | +4.816 |
Kak | +4.695 |
Neg logit contributions | |
Frie | -5.796 |
spir | -5.451 |
Male | -5.232 |
UCHIJ | -5.085 |
querque | -5.076 |
Token | the |
Token ID | 262 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
emetery | +1.453 |
ospel | +1.449 |
ppa | +1.415 |
vernment | +1.407 |
appa | +1.350 |
Neg logit contributions | |
Frie | -1.619 |
spir | -1.563 |
Male | -1.484 |
querque | -1.432 |
AAA | -1.421 |
Token | disbelief |
Token ID | 29894 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
emetery | +0.271 |
ospel | +0.269 |
vernment | +0.262 |
ppa | +0.261 |
appa | +0.248 |
Neg logit contributions | |
Frie | -0.309 |
spir | -0.297 |
Male | -0.283 |
AAA | -0.276 |
UCHIJ | -0.271 |
Token | , |
Token ID | 11 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
Frie | +0.082 |
spir | +0.079 |
Male | +0.075 |
AAA | +0.073 |
UCHIJ | +0.072 |
Neg logit contributions | |
emetery | -0.078 |
ospel | -0.077 |
vernment | -0.075 |
ppa | -0.075 |
appa | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
Frie | +0.462 |
spir | +0.445 |
Male | +0.422 |
AAA | +0.414 |
UCHIJ | +0.406 |
Neg logit contributions | |
emetery | -0.413 |
ospel | -0.408 |
vernment | -0.398 |
ppa | -0.397 |
appa | -0.378 |
Token | to |
Token ID | 284 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
ospel | +4.377 |
ppa | +4.345 |
emetery | +4.316 |
vernment | +4.285 |
appa | +4.126 |
Neg logit contributions | |
Frie | -5.106 |
spir | -4.723 |
querque | -4.652 |
Male | -4.547 |
UCHIJ | -4.377 |
Token | reduce |
Token ID | 4646 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
emetery | +2.365 |
ospel | +2.358 |
ppa | +2.317 |
vernment | +2.304 |
appa | +2.190 |
Neg logit contributions | |
Frie | -2.827 |
spir | -2.695 |
Male | -2.578 |
querque | -2.512 |
AAA | -2.486 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
emetery | +1.370 |
ospel | +1.353 |
vernment | +1.319 |
ppa | +1.319 |
appa | +1.254 |
Neg logit contributions | |
Frie | -1.542 |
spir | -1.489 |
Male | -1.415 |
AAA | -1.366 |
UCHIJ | -1.359 |
Token | motion |
Token ID | 6268 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
emetery | +1.007 |
ospel | +0.997 |
ppa | +0.973 |
vernment | +0.972 |
appa | +0.925 |
Neg logit contributions | |
Frie | -1.131 |
spir | -1.091 |
Male | -1.038 |
AAA | -1.004 |
querque | -0.997 |
Token | blur |
Token ID | 23671 |
Feature activation | -6.05e+00 |
Pos logit contributions | |
emetery | +2.310 |
ospel | +2.289 |
ppa | +2.239 |
vernment | +2.219 |
appa | +2.119 |
Neg logit contributions | |
Frie | -2.816 |
spir | -2.711 |
Male | -2.592 |
AAA | -2.513 |
querque | -2.501 |
Token | even |
Token ID | 772 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
emetery | +4.292 |
ospel | +4.220 |
ppa | +4.194 |
vernment | +4.103 |
Kak | +4.020 |
Neg logit contributions | |
Frie | -4.928 |
spir | -4.711 |
Male | -4.502 |
querque | -4.405 |
UCHIJ | -4.287 |
Token | more |
Token ID | 517 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
emetery | +3.581 |
ppa | +3.480 |
ospel | +3.479 |
vernment | +3.313 |
Kak | +3.269 |
Neg logit contributions | |
Frie | -7.299 |
spir | -7.011 |
Male | -6.742 |
querque | -6.735 |
UCHIJ | -6.601 |
Token | through |
Token ID | 832 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
emetery | +0.724 |
ospel | +0.716 |
vernment | +0.699 |
ppa | +0.696 |
appa | +0.665 |
Neg logit contributions | |
Frie | -0.733 |
spir | -0.705 |
Male | -0.668 |
AAA | -0.653 |
UCHIJ | -0.640 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
emetery | +2.244 |
ospel | +2.233 |
ppa | +2.181 |
vernment | +2.172 |
Kak | +2.089 |
Neg logit contributions | |
Frie | -2.491 |
spir | -2.413 |
Male | -2.282 |
querque | -2.211 |
UCHIJ | -2.197 |
Token | use |
Token ID | 779 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
emetery | +1.267 |
ospel | +1.258 |
ppa | +1.230 |
vernment | +1.223 |
appa | +1.171 |
Neg logit contributions | |
Frie | -1.377 |
spir | -1.330 |
Male | -1.262 |
AAA | -1.216 |
UCHIJ | -1.214 |
Token | of |
Token ID | 286 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
emetery | +0.395 |
ospel | +0.392 |
ppa | +0.382 |
vernment | +0.380 |
appa | +0.364 |
Neg logit contributions | |
Frie | -0.440 |
spir | -0.422 |
Male | -0.400 |
AAA | -0.390 |
querque | -0.389 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ospel | +1.142 |
emetery | +1.128 |
ppa | +1.118 |
vernment | +1.097 |
appa | +1.060 |
Neg logit contributions | |
Frie | -1.288 |
spir | -1.211 |
querque | -1.166 |
Male | -1.145 |
AAA | -1.120 |
Token | …… |
Token ID | 7398 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
emetery | +1.270 |
ospel | +1.263 |
ppa | +1.233 |
vernment | +1.227 |
appa | +1.178 |
Neg logit contributions | |
Frie | -1.226 |
spir | -1.170 |
Male | -1.097 |
AAA | -1.082 |
querque | -1.069 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
emetery | +1.636 |
ospel | +1.622 |
vernment | +1.589 |
ppa | +1.580 |
appa | +1.521 |
Neg logit contributions | |
Frie | -1.130 |
spir | -1.077 |
Male | -0.995 |
AAA | -0.973 |
UCHIJ | -0.953 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
emetery | +0.863 |
ospel | +0.862 |
ppa | +0.841 |
vernment | +0.835 |
appa | +0.801 |
Neg logit contributions | |
Frie | -0.920 |
spir | -0.877 |
Male | -0.826 |
querque | -0.821 |
AAA | -0.809 |
Token |
|
Token ID | 198 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ospel | +1.035 |
emetery | +1.025 |
ppa | +1.013 |
vernment | +0.996 |
appa | +0.961 |
Neg logit contributions | |
Frie | -1.150 |
spir | -1.086 |
querque | -1.039 |
Male | -1.027 |
AAA | -1.003 |
Token | Dear |
Token ID | 20266 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
emetery | +2.129 |
ospel | +2.123 |
ppa | +2.083 |
vernment | +2.071 |
appa | +2.012 |
Neg logit contributions | |
Frie | -1.241 |
spir | -1.153 |
Male | -1.053 |
AAA | -1.042 |
querque | -1.036 |
Token | George |
Token ID | 4502 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
emetery | +4.220 |
ospel | +4.216 |
ppa | +4.104 |
vernment | +4.074 |
Kak | +3.996 |
Neg logit contributions | |
Frie | -6.388 |
spir | -6.371 |
querque | -5.980 |
Male | -5.969 |
UCHIJ | -5.856 |
Token | , |
Token ID | 11 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
emetery | +2.090 |
ospel | +2.066 |
vernment | +2.026 |
ppa | +2.018 |
appa | +1.921 |
Neg logit contributions | |
Frie | -2.569 |
spir | -2.484 |
Male | -2.350 |
AAA | -2.306 |
UCHIJ | -2.289 |
Token |
|
Token ID | 198 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
emetery | +2.162 |
ospel | +2.151 |
ppa | +2.099 |
vernment | +2.095 |
appa | +2.001 |
Neg logit contributions | |
Frie | -2.414 |
spir | -2.302 |
Male | -2.176 |
querque | -2.158 |
AAA | -2.123 |
Token |
|
Token ID | 198 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
ospel | +2.069 |
ppa | +2.039 |
emetery | +2.010 |
vernment | +1.969 |
Kak | +1.928 |
Neg logit contributions | |
Frie | -2.528 |
spir | -2.351 |
querque | -2.346 |
Male | -2.222 |
AAA | -2.174 |
Token | I |
Token ID | 40 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
emetery | +2.434 |
ospel | +2.433 |
ppa | +2.394 |
vernment | +2.369 |
appa | +2.286 |
Neg logit contributions | |
Frie | -2.250 |
spir | -2.098 |
querque | -1.967 |
AAA | -1.964 |
Male | -1.960 |
Token | to |
Token ID | 284 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Frie | +1.450 |
spir | +1.387 |
Male | +1.306 |
AAA | +1.282 |
UCHIJ | +1.243 |
Neg logit contributions | |
emetery | -1.665 |
ospel | -1.647 |
vernment | -1.603 |
ppa | -1.596 |
appa | -1.531 |
Token | get |
Token ID | 651 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
Frie | +1.697 |
spir | +1.634 |
Male | +1.537 |
AAA | +1.516 |
UCHIJ | +1.474 |
Neg logit contributions | |
emetery | -1.828 |
ospel | -1.795 |
vernment | -1.749 |
ppa | -1.733 |
appa | -1.668 |
Token | someone |
Token ID | 2130 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
Frie | +2.170 |
spir | +2.076 |
Male | +1.959 |
AAA | +1.929 |
UCHIJ | +1.866 |
Neg logit contributions | |
emetery | -2.473 |
ospel | -2.445 |
vernment | -2.371 |
ppa | -2.348 |
appa | -2.265 |
Token | to |
Token ID | 284 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
Frie | +3.072 |
spir | +2.959 |
Male | +2.782 |
AAA | +2.750 |
UCHIJ | +2.627 |
Neg logit contributions | |
emetery | -3.736 |
ospel | -3.690 |
vernment | -3.550 |
ppa | -3.502 |
appa | -3.383 |
Token | open |
Token ID | 1280 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
emetery | +0.483 |
ospel | +0.479 |
vernment | +0.468 |
ppa | +0.467 |
appa | +0.442 |
Neg logit contributions | |
Frie | -0.581 |
spir | -0.560 |
Male | -0.533 |
AAA | -0.519 |
UCHIJ | -0.513 |
Token | up |
Token ID | 510 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
emetery | +0.581 |
ospel | +0.574 |
vernment | +0.562 |
ppa | +0.560 |
appa | +0.537 |
Neg logit contributions | |
Frie | -0.474 |
spir | -0.455 |
Male | -0.427 |
AAA | -0.417 |
UCHIJ | -0.405 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
emetery | +4.846 |
vernment | +4.775 |
ospel | +4.772 |
ppa | +4.745 |
Kak | +4.565 |
Neg logit contributions | |
Frie | -5.913 |
spir | -5.578 |
Male | -5.351 |
UCHIJ | -5.263 |
querque | -5.210 |
Token | It |
Token ID | 632 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
Frie | +0.794 |
spir | +0.761 |
Male | +0.722 |
AAA | +0.707 |
UCHIJ | +0.690 |
Neg logit contributions | |
emetery | -0.816 |
ospel | -0.804 |
vernment | -0.787 |
ppa | -0.780 |
appa | -0.748 |
Token | � |
Token ID | 447 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Frie | +0.593 |
spir | +0.572 |
Male | +0.544 |
AAA | +0.532 |
UCHIJ | +0.521 |
Neg logit contributions | |
emetery | -0.514 |
ospel | -0.506 |
vernment | -0.491 |
ppa | -0.489 |
appa | -0.466 |
Token | � |
Token ID | 247 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Frie | +0.513 |
spir | +0.480 |
Male | +0.437 |
AAA | +0.417 |
UCHIJ | +0.401 |
Neg logit contributions | |
emetery | -1.261 |
ospel | -1.251 |
vernment | -1.231 |
ppa | -1.227 |
appa | -1.186 |
Token | s |
Token ID | 82 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Frie | +0.717 |
spir | +0.692 |
Male | +0.647 |
AAA | +0.630 |
UCHIJ | +0.615 |
Neg logit contributions | |
emetery | -0.891 |
ospel | -0.880 |
vernment | -0.860 |
ppa | -0.857 |
appa | -0.823 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ospel | +1.441 |
emetery | +1.426 |
ppa | +1.399 |
vernment | +1.370 |
appa | +1.316 |
Neg logit contributions | |
Frie | -2.304 |
spir | -2.181 |
querque | -2.098 |
Male | -2.092 |
AAA | -2.071 |
Token | ) |
Token ID | 8 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
emetery | +0.155 |
ospel | +0.154 |
ppa | +0.150 |
vernment | +0.149 |
appa | +0.142 |
Neg logit contributions | |
Frie | -0.203 |
spir | -0.196 |
Male | -0.187 |
AAA | -0.182 |
querque | -0.182 |
Token | $ |
Token ID | 720 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Frie | +1.197 |
spir | +1.139 |
Male | +1.065 |
AAA | +1.044 |
UCHIJ | +1.015 |
Neg logit contributions | |
emetery | -1.629 |
ospel | -1.613 |
vernment | -1.580 |
ppa | -1.574 |
appa | -1.512 |
Token | rect |
Token ID | 2554 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
emetery | +0.176 |
ospel | +0.175 |
ppa | +0.171 |
vernment | +0.171 |
appa | +0.163 |
Neg logit contributions | |
Frie | -0.171 |
spir | -0.163 |
Male | -0.155 |
AAA | -0.152 |
UCHIJ | -0.149 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
emetery | +1.263 |
ospel | +1.254 |
vernment | +1.209 |
ppa | +1.209 |
appa | +1.146 |
Neg logit contributions | |
Frie | -1.878 |
spir | -1.801 |
Male | -1.721 |
AAA | -1.703 |
querque | -1.680 |
Token | = |
Token ID | 796 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
Frie | +0.646 |
spir | +0.618 |
Male | +0.578 |
AAA | +0.561 |
UCHIJ | +0.547 |
Neg logit contributions | |
emetery | -0.936 |
ospel | -0.926 |
vernment | -0.909 |
ppa | -0.904 |
appa | -0.870 |
Token | New |
Token ID | 968 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
Frie | +3.539 |
spir | +3.342 |
AAA | +3.171 |
Male | +3.161 |
UCHIJ | +3.084 |
Neg logit contributions | |
emetery | -5.587 |
vernment | -5.390 |
ospel | -5.355 |
ppa | -5.201 |
appa | -5.077 |
Token | - |
Token ID | 12 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
Frie | +1.873 |
spir | +1.828 |
Male | +1.726 |
AAA | +1.674 |
UCHIJ | +1.620 |
Neg logit contributions | |
emetery | -2.728 |
ospel | -2.660 |
vernment | -2.639 |
ppa | -2.587 |
appa | -2.499 |
Token | Object |
Token ID | 10267 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
Frie | +2.178 |
spir | +2.122 |
Male | +2.028 |
AAA | +1.949 |
UCHIJ | +1.916 |
Neg logit contributions | |
emetery | -2.499 |
ospel | -2.459 |
vernment | -2.422 |
ppa | -2.397 |
appa | -2.294 |
Token | System |
Token ID | 4482 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
Frie | +0.662 |
spir | +0.631 |
Male | +0.592 |
AAA | +0.572 |
querque | +0.569 |
Neg logit contributions | |
emetery | -0.872 |
ospel | -0.869 |
vernment | -0.850 |
ppa | -0.847 |
appa | -0.815 |
Token | . |
Token ID | 13 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
Frie | +0.626 |
spir | +0.604 |
Male | +0.572 |
AAA | +0.558 |
UCHIJ | +0.546 |
Neg logit contributions | |
emetery | -0.669 |
ospel | -0.658 |
vernment | -0.646 |
ppa | -0.641 |
appa | -0.614 |
Token | throne |
Token ID | 19262 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
Frie | +1.684 |
spir | +1.596 |
Male | +1.505 |
AAA | +1.490 |
UCHIJ | +1.440 |
Neg logit contributions | |
emetery | -2.056 |
ospel | -2.025 |
vernment | -1.981 |
ppa | -1.977 |
appa | -1.895 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Frie | +3.274 |
spir | +3.109 |
Male | +2.967 |
AAA | +2.913 |
UCHIJ | +2.832 |
Neg logit contributions | |
emetery | -3.753 |
ospel | -3.737 |
vernment | -3.617 |
ppa | -3.579 |
appa | -3.451 |
Token |
|
Token ID | 198 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
Frie | +0.208 |
spir | +0.200 |
Male | +0.190 |
AAA | +0.186 |
UCHIJ | +0.183 |
Neg logit contributions | |
emetery | -0.191 |
ospel | -0.189 |
vernment | -0.184 |
ppa | -0.183 |
appa | -0.175 |
Token |
|
Token ID | 198 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
Frie | +0.719 |
spir | +0.698 |
Male | +0.660 |
AAA | +0.645 |
UCHIJ | +0.629 |
Neg logit contributions | |
emetery | -0.779 |
ospel | -0.764 |
vernment | -0.751 |
ppa | -0.742 |
appa | -0.712 |
Token | See |
Token ID | 6214 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
emetery | +0.216 |
ospel | +0.214 |
ppa | +0.209 |
vernment | +0.208 |
appa | +0.198 |
Neg logit contributions | |
Frie | -0.263 |
spir | -0.253 |
Male | -0.238 |
AAA | -0.236 |
querque | -0.233 |
Token | also |
Token ID | 635 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
emetery | +0.689 |
ospel | +0.681 |
ppa | +0.665 |
vernment | +0.665 |
appa | +0.631 |
Neg logit contributions | |
Frie | -0.815 |
spir | -0.790 |
Male | -0.749 |
AAA | -0.732 |
querque | -0.721 |
Token | [ |
Token ID | 685 |
Feature activation | -9.90e-02 |
Pos logit contributions | |
Frie | +4.399 |
spir | +4.121 |
Male | +3.906 |
AAA | +3.878 |
UCHIJ | +3.731 |
Neg logit contributions | |
ospel | -5.123 |
emetery | -5.097 |
vernment | -5.003 |
ppa | -4.830 |
appa | -4.694 |
Token | edit |
Token ID | 4370 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
emetery | +0.072 |
ospel | +0.072 |
ppa | +0.070 |
vernment | +0.070 |
appa | +0.067 |
Neg logit contributions | |
Frie | -0.081 |
spir | -0.077 |
Male | -0.073 |
AAA | -0.072 |
querque | -0.071 |
Token | ] |
Token ID | 2361 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
Frie | +0.217 |
spir | +0.209 |
Male | +0.197 |
AAA | +0.193 |
querque | +0.189 |
Neg logit contributions | |
emetery | -0.225 |
ospel | -0.223 |
vernment | -0.217 |
ppa | -0.217 |
appa | -0.207 |
Token |
|
Token ID | 198 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
emetery | +1.877 |
ospel | +1.843 |
ppa | +1.811 |
vernment | +1.804 |
appa | +1.728 |
Neg logit contributions | |
Frie | -1.777 |
spir | -1.704 |
Male | -1.607 |
AAA | -1.567 |
querque | -1.546 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
emetery | +0.537 |
ospel | +0.536 |
ppa | +0.525 |
vernment | +0.519 |
appa | +0.499 |
Neg logit contributions | |
Frie | -0.570 |
spir | -0.541 |
Male | -0.511 |
querque | -0.508 |
AAA | -0.500 |
Token | is |
Token ID | 318 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
Frie | +2.014 |
spir | +1.934 |
Male | +1.819 |
AAA | +1.780 |
UCHIJ | +1.722 |
Neg logit contributions | |
emetery | -2.260 |
ospel | -2.230 |
ppa | -2.154 |
vernment | -2.153 |
appa | -2.066 |
Token | gaining |
Token ID | 13977 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Frie | +0.371 |
spir | +0.357 |
Male | +0.338 |
AAA | +0.331 |
UCHIJ | +0.325 |
Neg logit contributions | |
emetery | -0.359 |
ospel | -0.355 |
vernment | -0.346 |
ppa | -0.345 |
appa | -0.329 |
Token | ground |
Token ID | 2323 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
emetery | +1.791 |
ospel | +1.770 |
vernment | +1.736 |
ppa | +1.732 |
appa | +1.649 |
Neg logit contributions | |
Frie | -1.710 |
spir | -1.646 |
Male | -1.553 |
querque | -1.505 |
AAA | -1.505 |
Token | in |
Token ID | 287 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Frie | +0.218 |
spir | +0.209 |
Male | +0.198 |
AAA | +0.193 |
UCHIJ | +0.188 |
Neg logit contributions | |
emetery | -0.233 |
ospel | -0.231 |
vernment | -0.225 |
ppa | -0.224 |
appa | -0.215 |
Token | the |
Token ID | 262 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
emetery | +0.261 |
ospel | +0.258 |
vernment | +0.251 |
ppa | +0.250 |
appa | +0.238 |
Neg logit contributions | |
Frie | -0.294 |
spir | -0.282 |
Male | -0.268 |
AAA | -0.263 |
UCHIJ | -0.258 |
Token | race |
Token ID | 3234 |
Feature activation | +6.37e+00 |
Pos logit contributions | |
Frie | +0.171 |
spir | +0.164 |
Male | +0.156 |
AAA | +0.153 |
UCHIJ | +0.150 |
Neg logit contributions | |
emetery | -0.153 |
ospel | -0.151 |
vernment | -0.147 |
ppa | -0.146 |
appa | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
Frie | +4.465 |
spir | +4.211 |
Male | +3.952 |
AAA | +3.879 |
UCHIJ | +3.649 |
Neg logit contributions | |
emetery | -5.372 |
ospel | -5.303 |
ppa | -5.049 |
vernment | -4.983 |
appa | -4.842 |
Token |
|
Token ID | 198 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Frie | +0.437 |
spir | +0.421 |
Male | +0.398 |
AAA | +0.390 |
UCHIJ | +0.382 |
Neg logit contributions | |
emetery | -0.431 |
ospel | -0.426 |
vernment | -0.416 |
ppa | -0.414 |
appa | -0.395 |
Token |
|
Token ID | 198 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Frie | +0.144 |
spir | +0.139 |
Male | +0.131 |
AAA | +0.128 |
UCHIJ | +0.126 |
Neg logit contributions | |
emetery | -0.149 |
ospel | -0.147 |
vernment | -0.144 |
ppa | -0.143 |
appa | -0.137 |
Token | � |
Token ID | 447 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
Frie | +0.232 |
spir | +0.223 |
Male | +0.210 |
AAA | +0.205 |
UCHIJ | +0.201 |
Neg logit contributions | |
emetery | -0.253 |
ospel | -0.251 |
vernment | -0.245 |
ppa | -0.244 |
appa | -0.234 |
Token | � |
Token ID | 250 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
emetery | +0.679 |
ospel | +0.673 |
ppa | +0.661 |
vernment | +0.661 |
appa | +0.636 |
Neg logit contributions | |
Frie | -0.473 |
spir | -0.451 |
Male | -0.420 |
AAA | -0.409 |
UCHIJ | -0.401 |
Token | attorneys |
Token ID | 14449 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
emetery | +3.047 |
ospel | +3.023 |
vernment | +2.964 |
ppa | +2.960 |
appa | +2.847 |
Neg logit contributions | |
Frie | -3.723 |
spir | -3.561 |
Male | -3.404 |
UCHIJ | -3.312 |
querque | -3.264 |
Token | general |
Token ID | 2276 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
emetery | +1.773 |
ospel | +1.757 |
vernment | +1.723 |
ppa | +1.717 |
appa | +1.652 |
Neg logit contributions | |
Frie | -1.580 |
spir | -1.512 |
Male | -1.421 |
AAA | -1.376 |
querque | -1.373 |
Token | to |
Token ID | 284 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
emetery | +0.494 |
ospel | +0.489 |
vernment | +0.478 |
ppa | +0.477 |
appa | +0.457 |
Neg logit contributions | |
Frie | -0.464 |
spir | -0.446 |
Male | -0.421 |
AAA | -0.411 |
UCHIJ | -0.403 |
Token | oppose |
Token ID | 12856 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Frie | +0.602 |
spir | +0.577 |
Male | +0.545 |
AAA | +0.538 |
UCHIJ | +0.523 |
Neg logit contributions | |
emetery | -0.643 |
ospel | -0.633 |
vernment | -0.615 |
ppa | -0.612 |
appa | -0.585 |
Token | the |
Token ID | 262 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
Frie | +1.704 |
spir | +1.627 |
Male | +1.548 |
AAA | +1.537 |
UCHIJ | +1.490 |
Neg logit contributions | |
emetery | -1.686 |
ospel | -1.664 |
ppa | -1.617 |
vernment | -1.613 |
appa | -1.536 |
Token | confirmation |
Token ID | 12641 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
emetery | +0.410 |
ospel | +0.407 |
vernment | +0.397 |
ppa | +0.395 |
appa | +0.379 |
Neg logit contributions | |
Frie | -0.456 |
spir | -0.440 |
Male | -0.417 |
AAA | -0.404 |
UCHIJ | -0.400 |
Token | of |
Token ID | 286 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
Frie | +4.139 |
spir | +3.965 |
Male | +3.726 |
AAA | +3.681 |
querque | +3.514 |
Neg logit contributions | |
emetery | -4.741 |
ospel | -4.673 |
vernment | -4.543 |
ppa | -4.505 |
jri | -4.288 |
Token | Mer |
Token ID | 4638 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
emetery | +0.058 |
ospel | +0.058 |
vernment | +0.056 |
ppa | +0.056 |
appa | +0.053 |
Neg logit contributions | |
Frie | -0.065 |
spir | -0.063 |
Male | -0.059 |
AAA | -0.058 |
UCHIJ | -0.057 |
Token | rick |
Token ID | 5557 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
emetery | +0.646 |
ospel | +0.638 |
ppa | +0.620 |
vernment | +0.615 |
appa | +0.591 |
Neg logit contributions | |
Frie | -0.872 |
spir | -0.839 |
Male | -0.804 |
AAA | -0.786 |
UCHIJ | -0.775 |
Token | Garland |
Token ID | 35466 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
Frie | +1.743 |
spir | +1.666 |
Male | +1.590 |
AAA | +1.567 |
UCHIJ | +1.539 |
Neg logit contributions | |
emetery | -1.435 |
ospel | -1.422 |
vernment | -1.377 |
ppa | -1.368 |
appa | -1.297 |
Token | to |
Token ID | 284 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
Frie | +2.367 |
spir | +2.261 |
Male | +2.154 |
AAA | +2.098 |
UCHIJ | +2.053 |
Neg logit contributions | |
emetery | -2.462 |
ospel | -2.438 |
ppa | -2.364 |
vernment | -2.358 |
appa | -2.244 |
Token | iji |
Token ID | 20770 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
emetery | +1.556 |
ospel | +1.547 |
ppa | +1.511 |
vernment | +1.510 |
appa | +1.453 |
Neg logit contributions | |
Frie | -1.357 |
spir | -1.298 |
Male | -1.218 |
AAA | -1.187 |
querque | -1.179 |
Token | Press |
Token ID | 4332 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
emetery | +0.960 |
ospel | +0.951 |
vernment | +0.933 |
ppa | +0.925 |
Kak | +0.883 |
Neg logit contributions | |
Frie | -1.242 |
spir | -1.202 |
Male | -1.144 |
AAA | -1.116 |
UCHIJ | -1.103 |
Token | , |
Token ID | 11 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Frie | +1.998 |
spir | +1.930 |
Male | +1.829 |
AAA | +1.796 |
UCHIJ | +1.746 |
Neg logit contributions | |
emetery | -1.950 |
ospel | -1.922 |
vernment | -1.870 |
ppa | -1.864 |
appa | -1.776 |
Token | AFP |
Token ID | 8916 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Frie | +0.185 |
spir | +0.178 |
Male | +0.168 |
AAA | +0.164 |
querque | +0.162 |
Neg logit contributions | |
emetery | -0.176 |
ospel | -0.174 |
vernment | -0.170 |
ppa | -0.169 |
appa | -0.161 |
Token | / |
Token ID | 14 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
Frie | +0.832 |
spir | +0.802 |
Male | +0.761 |
AAA | +0.744 |
UCHIJ | +0.726 |
Neg logit contributions | |
emetery | -0.837 |
ospel | -0.827 |
vernment | -0.807 |
ppa | -0.805 |
appa | -0.770 |
Token | Getty |
Token ID | 6633 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
Frie | +2.135 |
spir | +2.065 |
Male | +1.939 |
AAA | +1.833 |
UCHIJ | +1.762 |
Neg logit contributions | |
emetery | -4.030 |
ospel | -3.988 |
ppa | -3.904 |
vernment | -3.867 |
appa | -3.763 |
Token | Images |
Token ID | 5382 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
Frie | +3.390 |
spir | +3.305 |
Male | +3.131 |
AAA | +2.933 |
UCHIJ | +2.867 |
Neg logit contributions | |
emetery | -6.322 |
ospel | -6.233 |
ppa | -6.136 |
vernment | -6.058 |
appa | -5.897 |
Token | ) |
Token ID | 8 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Frie | +3.844 |
spir | +3.744 |
Male | +3.595 |
AAA | +3.536 |
UCHIJ | +3.404 |
Neg logit contributions | |
emetery | -3.497 |
ospel | -3.468 |
ppa | -3.351 |
vernment | -3.347 |
appa | -3.175 |
Token |
|
Token ID | 198 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Frie | +1.130 |
spir | +1.091 |
Male | +1.032 |
AAA | +1.011 |
UCHIJ | +0.987 |
Neg logit contributions | |
emetery | -1.220 |
ospel | -1.208 |
vernment | -1.180 |
ppa | -1.174 |
appa | -1.120 |
Token |
|
Token ID | 198 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
ospel | +1.746 |
ppa | +1.715 |
emetery | +1.714 |
vernment | +1.664 |
appa | +1.625 |
Neg logit contributions | |
Frie | -2.052 |
spir | -1.918 |
querque | -1.884 |
Male | -1.813 |
AAA | -1.777 |
Token | A |
Token ID | 32 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
emetery | +2.215 |
ospel | +2.203 |
ppa | +2.183 |
vernment | +2.170 |
appa | +2.081 |
Neg logit contributions | |
Frie | -1.921 |
spir | -1.775 |
querque | -1.678 |
AAA | -1.663 |
Male | -1.639 |
Token | , |
Token ID | 11 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
Frie | +0.671 |
spir | +0.645 |
Male | +0.616 |
AAA | +0.608 |
UCHIJ | +0.590 |
Neg logit contributions | |
emetery | -0.623 |
ospel | -0.612 |
vernment | -0.598 |
ppa | -0.595 |
appa | -0.566 |
Token | access |
Token ID | 1895 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
emetery | +0.347 |
ospel | +0.343 |
vernment | +0.335 |
ppa | +0.334 |
appa | +0.317 |
Neg logit contributions | |
Frie | -0.405 |
spir | -0.391 |
Male | -0.371 |
AAA | -0.363 |
UCHIJ | -0.357 |
Token | to |
Token ID | 284 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
Frie | +0.717 |
spir | +0.685 |
Male | +0.646 |
AAA | +0.634 |
UCHIJ | +0.616 |
Neg logit contributions | |
emetery | -0.849 |
ospel | -0.841 |
ppa | -0.820 |
vernment | -0.819 |
appa | -0.786 |
Token | Kindle |
Token ID | 27114 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
emetery | +0.546 |
ospel | +0.540 |
vernment | +0.529 |
ppa | +0.527 |
appa | +0.503 |
Neg logit contributions | |
Frie | -0.576 |
spir | -0.556 |
Male | -0.526 |
AAA | -0.511 |
querque | -0.505 |
Token | Owners |
Token ID | 33147 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
emetery | +1.549 |
ospel | +1.537 |
ppa | +1.506 |
vernment | +1.505 |
appa | +1.441 |
Neg logit contributions | |
Frie | -1.441 |
spir | -1.382 |
Male | -1.297 |
AAA | -1.257 |
querque | -1.250 |
Token | � |
Token ID | 447 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Frie | +0.826 |
spir | +0.791 |
Male | +0.748 |
AAA | +0.734 |
UCHIJ | +0.713 |
Neg logit contributions | |
emetery | -0.954 |
ospel | -0.943 |
vernment | -0.922 |
ppa | -0.917 |
appa | -0.880 |
Token | � |
Token ID | 247 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Frie | +0.981 |
spir | +0.923 |
Male | +0.846 |
AAA | +0.815 |
UCHIJ | +0.786 |
Neg logit contributions | |
emetery | -2.054 |
ospel | -2.042 |
vernment | -2.005 |
ppa | -1.996 |
appa | -1.928 |
Token | L |
Token ID | 406 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Frie | +1.070 |
spir | +1.038 |
Male | +0.971 |
AAA | +0.957 |
UCHIJ | +0.921 |
Neg logit contributions | |
emetery | -1.329 |
ospel | -1.311 |
vernment | -1.278 |
ppa | -1.272 |
appa | -1.226 |
Token | ending |
Token ID | 1571 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
emetery | +0.179 |
ospel | +0.177 |
vernment | +0.173 |
ppa | +0.173 |
appa | +0.165 |
Neg logit contributions | |
Frie | -0.155 |
spir | -0.148 |
Male | -0.140 |
AAA | -0.136 |
UCHIJ | -0.133 |
Token | Library |
Token ID | 10074 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Frie | +0.121 |
spir | +0.116 |
Male | +0.109 |
AAA | +0.107 |
UCHIJ | +0.104 |
Neg logit contributions | |
emetery | -0.139 |
ospel | -0.138 |
vernment | -0.135 |
ppa | -0.135 |
appa | -0.129 |
Token | , |
Token ID | 11 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
emetery | +0.126 |
ospel | +0.125 |
vernment | +0.122 |
ppa | +0.121 |
appa | +0.115 |
Neg logit contributions | |
Frie | -0.142 |
spir | -0.137 |
Male | -0.130 |
AAA | -0.127 |
UCHIJ | -0.125 |
Token | Korean |
Token ID | 6983 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
emetery | +0.226 |
ospel | +0.223 |
vernment | +0.217 |
ppa | +0.216 |
appa | +0.205 |
Neg logit contributions | |
Frie | -0.295 |
spir | -0.285 |
Male | -0.272 |
AAA | -0.266 |
UCHIJ | -0.262 |
Token | retaliation |
Token ID | 24671 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
emetery | +2.270 |
ospel | +2.246 |
vernment | +2.205 |
ppa | +2.196 |
appa | +2.101 |
Neg logit contributions | |
Frie | -2.108 |
spir | -2.013 |
Male | -1.893 |
AAA | -1.840 |
querque | -1.825 |
Token | towards |
Token ID | 3371 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
emetery | +0.463 |
ospel | +0.457 |
vernment | +0.448 |
ppa | +0.447 |
appa | +0.427 |
Neg logit contributions | |
Frie | -0.447 |
spir | -0.429 |
Male | -0.406 |
AAA | -0.396 |
UCHIJ | -0.389 |
Token | Sony |
Token ID | 10184 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
emetery | +0.941 |
ospel | +0.931 |
vernment | +0.910 |
ppa | +0.908 |
appa | +0.866 |
Neg logit contributions | |
Frie | -0.992 |
spir | -0.956 |
Male | -0.906 |
AAA | -0.881 |
querque | -0.870 |
Token | surfaced |
Token ID | 23786 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Frie | +0.348 |
spir | +0.335 |
Male | +0.318 |
AAA | +0.312 |
UCHIJ | +0.304 |
Neg logit contributions | |
emetery | -0.349 |
ospel | -0.346 |
vernment | -0.336 |
ppa | -0.335 |
appa | -0.319 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Frie | +2.253 |
spir | +2.160 |
Male | +2.051 |
AAA | +2.040 |
UCHIJ | +1.956 |
Neg logit contributions | |
emetery | -2.219 |
ospel | -2.198 |
vernment | -2.127 |
ppa | -2.102 |
appa | -2.012 |
Token |
|
Token ID | 198 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
Frie | +1.007 |
spir | +0.971 |
Male | +0.921 |
AAA | +0.905 |
UCHIJ | +0.880 |
Neg logit contributions | |
emetery | -1.013 |
ospel | -0.996 |
vernment | -0.973 |
ppa | -0.964 |
appa | -0.926 |
Token |
|
Token ID | 198 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
Frie | +0.368 |
spir | +0.356 |
Male | +0.337 |
AAA | +0.328 |
UCHIJ | +0.321 |
Neg logit contributions | |
emetery | -0.396 |
ospel | -0.391 |
vernment | -0.383 |
ppa | -0.380 |
appa | -0.364 |
Token | If |
Token ID | 1532 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
Frie | +0.314 |
spir | +0.303 |
Male | +0.285 |
AAA | +0.276 |
UCHIJ | +0.269 |
Neg logit contributions | |
emetery | -0.395 |
ospel | -0.390 |
vernment | -0.383 |
ppa | -0.380 |
appa | -0.365 |
Token | you |
Token ID | 345 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
Frie | +0.347 |
spir | +0.332 |
Male | +0.313 |
AAA | +0.306 |
UCHIJ | +0.298 |
Neg logit contributions | |
emetery | -0.408 |
ospel | -0.404 |
vernment | -0.395 |
ppa | -0.394 |
appa | -0.377 |
Token | aren |
Token ID | 3588 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
emetery | +0.752 |
ospel | +0.745 |
vernment | +0.731 |
ppa | +0.729 |
appa | +0.696 |
Neg logit contributions | |
Frie | -0.699 |
spir | -0.670 |
Male | -0.634 |
AAA | -0.616 |
querque | -0.606 |
Token | people |
Token ID | 661 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
Frie | +0.834 |
spir | +0.799 |
Male | +0.752 |
AAA | +0.739 |
UCHIJ | +0.720 |
Neg logit contributions | |
emetery | -0.909 |
ospel | -0.901 |
vernment | -0.876 |
ppa | -0.875 |
appa | -0.839 |
Token | have |
Token ID | 423 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Frie | +1.567 |
spir | +1.503 |
Male | +1.404 |
AAA | +1.391 |
UCHIJ | +1.347 |
Neg logit contributions | |
emetery | -1.635 |
ospel | -1.621 |
ppa | -1.563 |
vernment | -1.562 |
appa | -1.487 |
Token | visited |
Token ID | 8672 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
emetery | +0.194 |
ospel | +0.192 |
vernment | +0.189 |
ppa | +0.188 |
appa | +0.181 |
Neg logit contributions | |
Frie | -0.150 |
spir | -0.143 |
Male | -0.135 |
AAA | -0.131 |
UCHIJ | -0.128 |
Token | since |
Token ID | 1201 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Frie | +1.356 |
spir | +1.297 |
Male | +1.232 |
AAA | +1.214 |
UCHIJ | +1.186 |
Neg logit contributions | |
emetery | -1.185 |
ospel | -1.180 |
ppa | -1.138 |
vernment | -1.135 |
appa | -1.084 |
Token | it |
Token ID | 340 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
emetery | +0.756 |
ospel | +0.747 |
vernment | +0.729 |
ppa | +0.726 |
appa | +0.691 |
Neg logit contributions | |
Frie | -0.887 |
spir | -0.856 |
Male | -0.814 |
AAA | -0.795 |
querque | -0.782 |
Token | opened |
Token ID | 4721 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
emetery | +0.074 |
ospel | +0.073 |
ppa | +0.072 |
vernment | +0.072 |
appa | +0.068 |
Neg logit contributions | |
Frie | -0.069 |
spir | -0.066 |
Male | -0.063 |
AAA | -0.061 |
UCHIJ | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Frie | +1.907 |
spir | +1.818 |
Male | +1.715 |
AAA | +1.692 |
UCHIJ | +1.639 |
Neg logit contributions | |
emetery | -2.147 |
ospel | -2.136 |
vernment | -2.071 |
ppa | -2.059 |
appa | -1.970 |
Token | Lee |
Token ID | 5741 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
Frie | +0.119 |
spir | +0.114 |
Male | +0.108 |
AAA | +0.106 |
UCHIJ | +0.103 |
Neg logit contributions | |
emetery | -0.115 |
ospel | -0.115 |
vernment | -0.111 |
ppa | -0.111 |
appa | -0.106 |
Token | said |
Token ID | 531 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
ppa | +3.119 |
ospel | +3.114 |
emetery | +3.093 |
vernment | +3.055 |
Kak | +2.940 |
Neg logit contributions | |
Frie | -4.481 |
spir | -4.407 |
Male | -4.211 |
AAA | -4.097 |
querque | -4.083 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Frie | +0.526 |
spir | +0.506 |
Male | +0.479 |
AAA | +0.469 |
UCHIJ | +0.460 |
Neg logit contributions | |
emetery | -0.517 |
ospel | -0.512 |
vernment | -0.500 |
ppa | -0.498 |
appa | -0.476 |
Token |
|
Token ID | 198 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
Frie | +1.051 |
spir | +1.006 |
Male | +0.948 |
AAA | +0.932 |
UCHIJ | +0.905 |
Neg logit contributions | |
emetery | -1.121 |
ospel | -1.105 |
vernment | -1.076 |
ppa | -1.072 |
appa | -1.032 |
Token | won |
Token ID | 1839 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
Frie | +0.987 |
spir | +0.948 |
Male | +0.896 |
AAA | +0.879 |
UCHIJ | +0.859 |
Neg logit contributions | |
emetery | -1.026 |
ospel | -1.014 |
vernment | -0.988 |
ppa | -0.987 |
appa | -0.944 |
Token | , |
Token ID | 11 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Frie | +2.403 |
spir | +2.295 |
Male | +2.186 |
AAA | +2.170 |
UCHIJ | +2.094 |
Neg logit contributions | |
emetery | -2.443 |
ospel | -2.409 |
ppa | -2.331 |
vernment | -2.321 |
appa | -2.253 |
Token | but |
Token ID | 475 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Frie | +1.448 |
spir | +1.391 |
Male | +1.326 |
AAA | +1.303 |
UCHIJ | +1.267 |
Neg logit contributions | |
emetery | -1.285 |
ospel | -1.268 |
ppa | -1.231 |
vernment | -1.230 |
appa | -1.173 |
Token | there |
Token ID | 612 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
Frie | +1.378 |
spir | +1.314 |
Male | +1.245 |
AAA | +1.234 |
UCHIJ | +1.189 |
Neg logit contributions | |
emetery | -1.421 |
ospel | -1.401 |
ppa | -1.362 |
vernment | -1.362 |
appa | -1.304 |
Token | will |
Token ID | 481 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
emetery | +0.626 |
ospel | +0.620 |
vernment | +0.607 |
ppa | +0.605 |
appa | +0.578 |
Neg logit contributions | |
Frie | -0.602 |
spir | -0.579 |
Male | -0.547 |
AAA | -0.534 |
UCHIJ | -0.524 |
Token | also |
Token ID | 635 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
emetery | +0.848 |
ospel | +0.842 |
vernment | +0.826 |
ppa | +0.826 |
appa | +0.793 |
Neg logit contributions | |
Frie | -0.568 |
spir | -0.541 |
Male | -0.504 |
AAA | -0.488 |
querque | -0.480 |
Token | be |
Token ID | 307 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
Frie | +0.761 |
spir | +0.719 |
Male | +0.667 |
AAA | +0.647 |
UCHIJ | +0.624 |
Neg logit contributions | |
emetery | -1.327 |
ospel | -1.315 |
vernment | -1.287 |
ppa | -1.285 |
appa | -1.242 |
Token | a |
Token ID | 257 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
emetery | +0.452 |
ospel | +0.447 |
vernment | +0.436 |
ppa | +0.435 |
appa | +0.415 |
Neg logit contributions | |
Frie | -0.476 |
spir | -0.459 |
Male | -0.435 |
AAA | -0.425 |
UCHIJ | -0.417 |
Token | ton |
Token ID | 5680 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Frie | +0.211 |
spir | +0.202 |
Male | +0.190 |
AAA | +0.186 |
UCHIJ | +0.182 |
Neg logit contributions | |
emetery | -0.248 |
ospel | -0.245 |
vernment | -0.240 |
ppa | -0.239 |
appa | -0.229 |
Token | of |
Token ID | 286 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
Frie | +1.392 |
spir | +1.352 |
Male | +1.270 |
AAA | +1.245 |
UCHIJ | +1.211 |
Neg logit contributions | |
emetery | -1.444 |
ospel | -1.422 |
vernment | -1.388 |
ppa | -1.383 |
appa | -1.331 |
Token | pressure |
Token ID | 3833 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
emetery | +0.527 |
ospel | +0.521 |
vernment | +0.509 |
ppa | +0.507 |
appa | +0.483 |
Neg logit contributions | |
Frie | -0.552 |
spir | -0.531 |
Male | -0.503 |
AAA | -0.492 |
UCHIJ | -0.483 |
Token | easy |
Token ID | 2562 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
emetery | +0.463 |
ospel | +0.458 |
vernment | +0.444 |
ppa | +0.443 |
appa | +0.419 |
Neg logit contributions | |
Frie | -0.704 |
spir | -0.680 |
Male | -0.649 |
AAA | -0.637 |
UCHIJ | -0.629 |
Token | to |
Token ID | 284 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
emetery | +0.165 |
ospel | +0.163 |
vernment | +0.159 |
ppa | +0.159 |
appa | +0.152 |
Neg logit contributions | |
Frie | -0.146 |
spir | -0.140 |
Male | -0.132 |
AAA | -0.129 |
UCHIJ | -0.126 |
Token | respond |
Token ID | 3031 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Frie | +0.095 |
spir | +0.092 |
Male | +0.087 |
AAA | +0.085 |
UCHIJ | +0.083 |
Neg logit contributions | |
emetery | -0.096 |
ospel | -0.095 |
vernment | -0.093 |
ppa | -0.092 |
appa | -0.088 |
Token | to |
Token ID | 284 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
Frie | +0.179 |
spir | +0.172 |
Male | +0.163 |
AAA | +0.159 |
UCHIJ | +0.155 |
Neg logit contributions | |
emetery | -0.192 |
ospel | -0.190 |
vernment | -0.186 |
ppa | -0.185 |
appa | -0.177 |
Token | this |
Token ID | 428 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
emetery | +0.584 |
ospel | +0.578 |
vernment | +0.564 |
ppa | +0.562 |
appa | +0.537 |
Neg logit contributions | |
Frie | -0.643 |
spir | -0.619 |
Male | -0.587 |
AAA | -0.574 |
querque | -0.565 |
Token | woman |
Token ID | 2415 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Frie | +0.065 |
spir | +0.063 |
Male | +0.060 |
AAA | +0.059 |
UCHIJ | +0.057 |
Neg logit contributions | |
emetery | -0.059 |
ospel | -0.059 |
vernment | -0.057 |
ppa | -0.057 |
appa | -0.054 |
Token | with |
Token ID | 351 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Frie | +1.292 |
spir | +1.251 |
Male | +1.176 |
AAA | +1.149 |
UCHIJ | +1.114 |
Neg logit contributions | |
emetery | -1.371 |
ospel | -1.350 |
vernment | -1.310 |
ppa | -1.304 |
appa | -1.246 |
Token | sentimental |
Token ID | 46908 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
emetery | +0.892 |
ospel | +0.884 |
vernment | +0.860 |
ppa | +0.857 |
appa | +0.817 |
Neg logit contributions | |
Frie | -1.031 |
spir | -0.994 |
Male | -0.944 |
AAA | -0.923 |
UCHIJ | -0.910 |
Token | plat |
Token ID | 40315 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
emetery | +0.931 |
ospel | +0.922 |
vernment | +0.899 |
ppa | +0.896 |
appa | +0.854 |
Neg logit contributions | |
Frie | -1.019 |
spir | -0.980 |
Male | -0.931 |
AAA | -0.909 |
UCHIJ | -0.896 |
Token | itudes |
Token ID | 10455 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
Frie | +0.449 |
spir | +0.436 |
Male | +0.416 |
AAA | +0.409 |
UCHIJ | +0.402 |
Neg logit contributions | |
emetery | -0.287 |
ospel | -0.283 |
vernment | -0.275 |
ppa | -0.274 |
appa | -0.258 |
Token | , |
Token ID | 11 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
emetery | +0.636 |
ospel | +0.629 |
vernment | +0.614 |
ppa | +0.612 |
appa | +0.584 |
Neg logit contributions | |
Frie | -0.675 |
spir | -0.649 |
Male | -0.615 |
AAA | -0.602 |
UCHIJ | -0.591 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
emetery | +1.848 |
ospel | +1.822 |
ppa | +1.792 |
vernment | +1.791 |
Kak | +1.723 |
Neg logit contributions | |
Frie | -2.040 |
spir | -1.968 |
Male | -1.871 |
querque | -1.802 |
UCHIJ | -1.792 |
Token | only |
Token ID | 691 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
emetery | +0.617 |
ospel | +0.608 |
vernment | +0.589 |
ppa | +0.587 |
appa | +0.551 |
Neg logit contributions | |
Frie | -1.034 |
spir | -1.003 |
Male | -0.960 |
AAA | -0.943 |
UCHIJ | -0.928 |
Token | workers |
Token ID | 3259 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Frie | +0.794 |
spir | +0.765 |
Male | +0.729 |
AAA | +0.717 |
UCHIJ | +0.702 |
Neg logit contributions | |
emetery | -0.633 |
ospel | -0.626 |
vernment | -0.608 |
ppa | -0.605 |
appa | -0.575 |
Token | getting |
Token ID | 1972 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Frie | +1.241 |
spir | +1.186 |
Male | +1.120 |
AAA | +1.105 |
UCHIJ | +1.076 |
Neg logit contributions | |
emetery | -1.300 |
ospel | -1.293 |
vernment | -1.257 |
ppa | -1.248 |
appa | -1.193 |
Token | extra |
Token ID | 3131 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Frie | +1.283 |
spir | +1.230 |
Male | +1.164 |
AAA | +1.153 |
UCHIJ | +1.120 |
Neg logit contributions | |
emetery | -1.268 |
ospel | -1.255 |
vernment | -1.219 |
ppa | -1.214 |
appa | -1.164 |
Token | benefits |
Token ID | 4034 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
Frie | +1.192 |
spir | +1.145 |
Male | +1.084 |
AAA | +1.069 |
UCHIJ | +1.039 |
Neg logit contributions | |
emetery | -1.195 |
ospel | -1.183 |
vernment | -1.152 |
ppa | -1.146 |
appa | -1.096 |
Token | for |
Token ID | 329 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Frie | +0.627 |
spir | +0.603 |
Male | +0.570 |
AAA | +0.557 |
UCHIJ | +0.546 |
Neg logit contributions | |
emetery | -0.643 |
ospel | -0.636 |
vernment | -0.622 |
ppa | -0.620 |
appa | -0.592 |
Token | tough |
Token ID | 5802 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
Frie | +1.584 |
spir | +1.524 |
Male | +1.435 |
AAA | +1.425 |
UCHIJ | +1.374 |
Neg logit contributions | |
emetery | -1.630 |
ospel | -1.616 |
vernment | -1.566 |
ppa | -1.565 |
appa | -1.496 |
Token | conditions |
Token ID | 3403 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
Frie | +0.450 |
spir | +0.432 |
Male | +0.406 |
AAA | +0.400 |
UCHIJ | +0.388 |
Neg logit contributions | |
emetery | -0.512 |
ospel | -0.507 |
vernment | -0.495 |
ppa | -0.494 |
appa | -0.473 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Frie | +0.061 |
spir | +0.059 |
Male | +0.056 |
AAA | +0.054 |
querque | +0.054 |
Neg logit contributions | |
emetery | -0.060 |
ospel | -0.059 |
vernment | -0.058 |
ppa | -0.058 |
appa | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Frie | +1.439 |
spir | +1.384 |
Male | +1.310 |
AAA | +1.281 |
UCHIJ | +1.256 |
Neg logit contributions | |
emetery | -1.417 |
ospel | -1.401 |
vernment | -1.368 |
ppa | -1.364 |
appa | -1.302 |
Token | the |
Token ID | 262 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
emetery | +1.231 |
ospel | +1.219 |
vernment | +1.190 |
ppa | +1.186 |
appa | +1.130 |
Neg logit contributions | |
Frie | -1.371 |
spir | -1.324 |
Male | -1.255 |
AAA | -1.215 |
querque | -1.208 |
Token | first |
Token ID | 717 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
emetery | +0.342 |
ospel | +0.340 |
vernment | +0.331 |
ppa | +0.330 |
appa | +0.315 |
Neg logit contributions | |
Frie | -0.382 |
spir | -0.369 |
Male | -0.350 |
AAA | -0.340 |
querque | -0.336 |
Token | water |
Token ID | 1660 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
emetery | +0.787 |
ospel | +0.781 |
vernment | +0.767 |
ppa | +0.765 |
appa | +0.728 |
Neg logit contributions | |
Frie | -0.733 |
spir | -0.706 |
Male | -0.663 |
AAA | -0.643 |
querque | -0.638 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
emetery | +1.647 |
ospel | +1.645 |
ppa | +1.619 |
vernment | +1.602 |
Kak | +1.538 |
Neg logit contributions | |
Frie | -1.634 |
spir | -1.580 |
Male | -1.508 |
querque | -1.444 |
AAA | -1.440 |
Token | an |
Token ID | 281 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
emetery | +1.232 |
ospel | +1.214 |
vernment | +1.185 |
ppa | +1.176 |
appa | +1.118 |
Neg logit contributions | |
Frie | -1.434 |
spir | -1.383 |
Male | -1.316 |
querque | -1.272 |
AAA | -1.269 |
Token | enormous |
Token ID | 9812 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
emetery | +1.385 |
ospel | +1.372 |
vernment | +1.339 |
ppa | +1.328 |
appa | +1.275 |
Neg logit contributions | |
Frie | -1.528 |
spir | -1.475 |
Male | -1.401 |
AAA | -1.353 |
querque | -1.341 |
Token | White |
Token ID | 2635 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
emetery | +0.343 |
ospel | +0.340 |
vernment | +0.332 |
ppa | +0.330 |
appa | +0.314 |
Neg logit contributions | |
Frie | -0.393 |
spir | -0.379 |
Male | -0.360 |
AAA | -0.350 |
UCHIJ | -0.345 |
Token | Elephant |
Token ID | 42651 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Frie | +0.681 |
spir | +0.659 |
Male | +0.632 |
AAA | +0.621 |
UCHIJ | +0.610 |
Neg logit contributions | |
emetery | -0.428 |
ospel | -0.421 |
vernment | -0.408 |
ppa | -0.406 |
appa | -0.382 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
emetery | +1.602 |
ospel | +1.593 |
vernment | +1.564 |
ppa | +1.555 |
Kak | +1.486 |
Neg logit contributions | |
Frie | -1.657 |
spir | -1.598 |
Male | -1.516 |
querque | -1.466 |
AAA | -1.462 |
Token | completely |
Token ID | 3190 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
emetery | +1.054 |
ospel | +1.044 |
vernment | +1.025 |
ppa | +1.019 |
appa | +0.973 |
Neg logit contributions | |
Frie | -1.099 |
spir | -1.062 |
Male | -1.005 |
AAA | -0.971 |
querque | -0.971 |
Token | unnecessary |
Token ID | 13114 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
Frie | +0.524 |
spir | +0.504 |
Male | +0.477 |
AAA | +0.463 |
querque | +0.458 |
Neg logit contributions | |
emetery | -0.514 |
ospel | -0.510 |
vernment | -0.500 |
ppa | -0.497 |
appa | -0.475 |
Token | standing |
Token ID | 5646 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
Frie | +1.511 |
spir | +1.472 |
Male | +1.410 |
AAA | +1.371 |
UCHIJ | +1.337 |
Neg logit contributions | |
emetery | -1.214 |
ospel | -1.205 |
vernment | -1.183 |
ppa | -1.173 |
appa | -1.099 |
Token | Actor |
Token ID | 27274 |
Feature activation | +6.25e+00 |
Pos logit contributions | |
Frie | +0.537 |
spir | +0.513 |
Male | +0.473 |
AAA | +0.458 |
querque | +0.450 |
Neg logit contributions | |
emetery | -0.845 |
ospel | -0.839 |
vernment | -0.823 |
ppa | -0.821 |
appa | -0.791 |
Token | in |
Token ID | 287 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
Frie | +4.149 |
spir | +3.958 |
Male | +3.847 |
AAA | +3.772 |
UCHIJ | +3.626 |
Neg logit contributions | |
emetery | -5.327 |
ospel | -5.261 |
ppa | -5.131 |
vernment | -5.094 |
jri | -4.873 |
Token | a |
Token ID | 257 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
Frie | +1.700 |
spir | +1.625 |
Male | +1.543 |
AAA | +1.517 |
UCHIJ | +1.474 |
Neg logit contributions | |
emetery | -1.799 |
ospel | -1.779 |
ppa | -1.734 |
vernment | -1.732 |
appa | -1.657 |
Token | Comedy |
Token ID | 22329 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
emetery | +0.063 |
ospel | +0.063 |
vernment | +0.063 |
ppa | +0.062 |
Kak | +0.060 |
Neg logit contributions | |
Frie | -0.040 |
spir | -0.039 |
Male | -0.035 |
querque | -0.034 |
UCHIJ | -0.034 |
Token | in |
Token ID | 287 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
Frie | +2.182 |
spir | +2.100 |
Male | +1.999 |
AAA | +1.961 |
UCHIJ | +1.916 |
Neg logit contributions | |
emetery | -2.039 |
ospel | -2.019 |
vernment | -1.961 |
ppa | -1.949 |
appa | -1.861 |
Token | Emmy |
Token ID | 33953 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
emetery | +0.218 |
ospel | +0.215 |
vernment | +0.211 |
ppa | +0.209 |
appa | +0.200 |
Neg logit contributions | |
Frie | -0.235 |
spir | -0.228 |
Male | -0.215 |
AAA | -0.208 |
UCHIJ | -0.207 |
Token | history |
Token ID | 2106 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
Frie | +3.143 |
spir | +3.031 |
Male | +2.859 |
AAA | +2.819 |
UCHIJ | +2.742 |
Neg logit contributions | |
emetery | -2.997 |
ospel | -2.967 |
vernment | -2.883 |
ppa | -2.856 |
appa | -2.756 |
Token | — |
Token ID | 851 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
Frie | +0.056 |
spir | +0.054 |
Male | +0.051 |
AAA | +0.050 |
UCHIJ | +0.049 |
Neg logit contributions | |
emetery | -0.054 |
ospel | -0.053 |
vernment | -0.052 |
ppa | -0.052 |
appa | -0.049 |
Token | Robert |
Token ID | 5199 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
emetery | +0.458 |
ospel | +0.452 |
vernment | +0.440 |
ppa | +0.439 |
appa | +0.418 |
Neg logit contributions | |
Frie | -0.548 |
spir | -0.530 |
Male | -0.502 |
AAA | -0.491 |
querque | -0.485 |
Token | Gu |
Token ID | 1962 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
emetery | +0.381 |
ospel | +0.376 |
vernment | +0.367 |
ppa | +0.366 |
appa | +0.348 |
Neg logit contributions | |
Frie | -0.431 |
spir | -0.415 |
Male | -0.394 |
AAA | -0.386 |
UCHIJ | -0.379 |
Token | workload |
Token ID | 26211 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
emetery | +1.441 |
ospel | +1.427 |
ppa | +1.394 |
vernment | +1.393 |
appa | +1.329 |
Neg logit contributions | |
Frie | -1.530 |
spir | -1.476 |
Male | -1.401 |
AAA | -1.354 |
querque | -1.344 |
Token | s |
Token ID | 82 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
emetery | +0.308 |
ospel | +0.305 |
vernment | +0.298 |
ppa | +0.297 |
appa | +0.284 |
Neg logit contributions | |
Frie | -0.264 |
spir | -0.255 |
Male | -0.239 |
AAA | -0.235 |
UCHIJ | -0.229 |
Token | including |
Token ID | 1390 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
emetery | +0.281 |
ospel | +0.278 |
vernment | +0.272 |
ppa | +0.270 |
appa | +0.258 |
Neg logit contributions | |
Frie | -0.289 |
spir | -0.278 |
Male | -0.263 |
AAA | -0.258 |
UCHIJ | -0.253 |
Token | interrupts |
Token ID | 48237 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
Frie | +1.025 |
spir | +0.985 |
Male | +0.932 |
AAA | +0.917 |
UCHIJ | +0.895 |
Neg logit contributions | |
emetery | -1.019 |
ospel | -1.009 |
vernment | -0.986 |
ppa | -0.981 |
appa | -0.935 |
Token | and |
Token ID | 290 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
emetery | +0.038 |
ospel | +0.038 |
vernment | +0.037 |
ppa | +0.036 |
appa | +0.035 |
Neg logit contributions | |
Frie | -0.042 |
spir | -0.040 |
Male | -0.038 |
AAA | -0.038 |
UCHIJ | -0.037 |
Token | timers |
Token ID | 48085 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
Frie | +0.909 |
spir | +0.866 |
Male | +0.812 |
AAA | +0.795 |
UCHIJ | +0.774 |
Neg logit contributions | |
emetery | -1.186 |
ospel | -1.176 |
vernment | -1.150 |
ppa | -1.147 |
appa | -1.101 |
Token | . |
Token ID | 13 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
Frie | +0.737 |
spir | +0.707 |
Male | +0.670 |
AAA | +0.658 |
UCHIJ | +0.645 |
Neg logit contributions | |
emetery | -0.745 |
ospel | -0.739 |
vernment | -0.720 |
ppa | -0.715 |
appa | -0.683 |
Token |
|
Token ID | 198 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
Frie | +0.666 |
spir | +0.637 |
Male | +0.605 |
AAA | +0.594 |
UCHIJ | +0.581 |
Neg logit contributions | |
emetery | -0.675 |
ospel | -0.665 |
vernment | -0.651 |
ppa | -0.645 |
appa | -0.616 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Frie | +0.354 |
spir | +0.341 |
Male | +0.322 |
AAA | +0.315 |
UCHIJ | +0.308 |
Neg logit contributions | |
emetery | -0.367 |
ospel | -0.362 |
vernment | -0.354 |
ppa | -0.352 |
appa | -0.337 |
Token | Things |
Token ID | 22248 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
emetery | +0.200 |
ospel | +0.198 |
ppa | +0.194 |
vernment | +0.194 |
appa | +0.187 |
Neg logit contributions | |
Frie | -0.152 |
spir | -0.144 |
Male | -0.134 |
AAA | -0.132 |
querque | -0.130 |
Token | started |
Token ID | 2067 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
emetery | +1.023 |
ospel | +1.013 |
vernment | +0.991 |
ppa | +0.991 |
appa | +0.947 |
Neg logit contributions | |
Frie | -0.978 |
spir | -0.940 |
Male | -0.888 |
AAA | -0.865 |
querque | -0.852 |
Token | nomination |
Token ID | 11872 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
Frie | +1.278 |
spir | +1.228 |
Male | +1.165 |
AAA | +1.139 |
UCHIJ | +1.116 |
Neg logit contributions | |
emetery | -1.243 |
ospel | -1.227 |
vernment | -1.198 |
ppa | -1.194 |
appa | -1.139 |
Token | locked |
Token ID | 8970 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Frie | +2.162 |
spir | +2.056 |
Male | +1.948 |
AAA | +1.910 |
UCHIJ | +1.871 |
Neg logit contributions | |
emetery | -2.259 |
ospel | -2.242 |
vernment | -2.170 |
ppa | -2.164 |
appa | -2.068 |
Token | up |
Token ID | 510 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Frie | +1.040 |
spir | +0.987 |
Male | +0.933 |
AAA | +0.913 |
UCHIJ | +0.890 |
Neg logit contributions | |
emetery | -1.348 |
ospel | -1.332 |
vernment | -1.307 |
ppa | -1.292 |
appa | -1.240 |
Token | and |
Token ID | 290 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
emetery | +1.459 |
ospel | +1.442 |
vernment | +1.411 |
ppa | +1.408 |
appa | +1.344 |
Neg logit contributions | |
Frie | -1.520 |
spir | -1.469 |
Male | -1.384 |
AAA | -1.354 |
querque | -1.333 |
Token | is |
Token ID | 318 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
emetery | +0.107 |
ospel | +0.106 |
vernment | +0.103 |
ppa | +0.103 |
appa | +0.098 |
Neg logit contributions | |
Frie | -0.113 |
spir | -0.109 |
Male | -0.103 |
AAA | -0.101 |
UCHIJ | -0.099 |
Token | lining |
Token ID | 20883 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
emetery | +0.417 |
ospel | +0.412 |
vernment | +0.403 |
ppa | +0.402 |
appa | +0.384 |
Neg logit contributions | |
Frie | -0.432 |
spir | -0.415 |
Male | -0.394 |
AAA | -0.384 |
UCHIJ | -0.377 |
Token | up |
Token ID | 510 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
emetery | +0.245 |
ospel | +0.243 |
vernment | +0.238 |
ppa | +0.237 |
appa | +0.227 |
Neg logit contributions | |
Frie | -0.196 |
spir | -0.188 |
Male | -0.176 |
AAA | -0.172 |
UCHIJ | -0.168 |
Token | support |
Token ID | 1104 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
emetery | +0.292 |
ospel | +0.289 |
vernment | +0.283 |
ppa | +0.282 |
appa | +0.269 |
Neg logit contributions | |
Frie | -0.276 |
spir | -0.265 |
Male | -0.250 |
AAA | -0.244 |
UCHIJ | -0.239 |
Token | within |
Token ID | 1626 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
emetery | +0.530 |
ospel | +0.524 |
vernment | +0.514 |
ppa | +0.512 |
appa | +0.493 |
Neg logit contributions | |
Frie | -0.449 |
spir | -0.431 |
Male | -0.406 |
AAA | -0.395 |
querque | -0.388 |
Token | his |
Token ID | 465 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
emetery | +1.120 |
ospel | +1.105 |
vernment | +1.085 |
ppa | +1.075 |
appa | +1.028 |
Neg logit contributions | |
Frie | -1.291 |
spir | -1.249 |
Male | -1.189 |
AAA | -1.152 |
querque | -1.145 |
Token | own |
Token ID | 898 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
emetery | +1.008 |
ospel | +0.998 |
vernment | +0.978 |
ppa | +0.973 |
appa | +0.936 |
Neg logit contributions | |
Frie | -1.213 |
spir | -1.180 |
Male | -1.118 |
AAA | -1.084 |
querque | -1.080 |
Token | g |
Token ID | 70 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
Frie | +0.772 |
spir | +0.737 |
Male | +0.696 |
AAA | +0.680 |
UCHIJ | +0.666 |
Neg logit contributions | |
emetery | -0.873 |
ospel | -0.865 |
vernment | -0.846 |
ppa | -0.845 |
appa | -0.809 |
Token | lor |
Token ID | 4685 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Frie | +3.233 |
spir | +3.210 |
Male | +3.000 |
AAA | +2.949 |
UCHIJ | +2.858 |
Neg logit contributions | |
emetery | -2.254 |
ppa | -2.127 |
vernment | -2.121 |
ospel | -2.084 |
Kak | -2.029 |
Token | ious |
Token ID | 699 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
emetery | +1.158 |
ospel | +1.152 |
vernment | +1.114 |
ppa | +1.104 |
appa | +1.040 |
Neg logit contributions | |
Frie | -1.847 |
spir | -1.778 |
Male | -1.706 |
AAA | -1.678 |
querque | -1.657 |
Token | diversity |
Token ID | 9573 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
Frie | +0.522 |
spir | +0.502 |
Male | +0.476 |
AAA | +0.465 |
UCHIJ | +0.456 |
Neg logit contributions | |
emetery | -0.510 |
ospel | -0.505 |
vernment | -0.493 |
ppa | -0.491 |
appa | -0.469 |
Token | ' |
Token ID | 6 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
Frie | +0.470 |
spir | +0.452 |
Male | +0.428 |
AAA | +0.418 |
UCHIJ | +0.410 |
Neg logit contributions | |
emetery | -0.470 |
ospel | -0.465 |
vernment | -0.454 |
ppa | -0.453 |
appa | -0.433 |
Token | of |
Token ID | 286 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
emetery | +0.420 |
ospel | +0.416 |
vernment | +0.406 |
ppa | +0.405 |
appa | +0.386 |
Neg logit contributions | |
Frie | -0.433 |
spir | -0.417 |
Male | -0.395 |
AAA | -0.385 |
querque | -0.378 |
Token | people |
Token ID | 661 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
emetery | +2.678 |
ospel | +2.677 |
ppa | +2.621 |
vernment | +2.618 |
Kak | +2.504 |
Neg logit contributions | |
Frie | -3.210 |
spir | -3.136 |
Male | -2.970 |
querque | -2.884 |
AAA | -2.852 |
Token | of |
Token ID | 286 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
Frie | +1.609 |
spir | +1.541 |
Male | +1.455 |
AAA | +1.428 |
UCHIJ | +1.399 |
Neg logit contributions | |
emetery | -1.616 |
ospel | -1.598 |
vernment | -1.557 |
ppa | -1.550 |
appa | -1.477 |
Token | all |
Token ID | 477 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
emetery | +0.572 |
ospel | +0.566 |
ppa | +0.552 |
vernment | +0.552 |
appa | +0.526 |
Neg logit contributions | |
Frie | -0.629 |
spir | -0.608 |
Male | -0.578 |
AAA | -0.562 |
querque | -0.556 |
Token | faiths |
Token ID | 43028 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Frie | +1.539 |
spir | +1.468 |
Male | +1.377 |
AAA | +1.344 |
UCHIJ | +1.310 |
Neg logit contributions | |
emetery | -2.000 |
ospel | -1.980 |
vernment | -1.941 |
ppa | -1.931 |
appa | -1.857 |
Token | , |
Token ID | 11 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
emetery | +0.848 |
ospel | +0.840 |
vernment | +0.822 |
ppa | +0.821 |
appa | +0.781 |
Neg logit contributions | |
Frie | -0.986 |
spir | -0.954 |
Male | -0.905 |
AAA | -0.887 |
querque | -0.876 |
Token | plant |
Token ID | 4618 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
Frie | +0.357 |
spir | +0.344 |
Male | +0.326 |
AAA | +0.318 |
UCHIJ | +0.313 |
Neg logit contributions | |
emetery | -0.331 |
ospel | -0.327 |
vernment | -0.319 |
ppa | -0.318 |
appa | -0.303 |
Token | to |
Token ID | 284 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Frie | +0.519 |
spir | +0.499 |
Male | +0.472 |
AAA | +0.461 |
UCHIJ | +0.452 |
Neg logit contributions | |
emetery | -0.537 |
ospel | -0.532 |
vernment | -0.520 |
ppa | -0.518 |
appa | -0.495 |
Token | a |
Token ID | 257 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Frie | +0.271 |
spir | +0.262 |
Male | +0.248 |
AAA | +0.241 |
querque | +0.238 |
Neg logit contributions | |
emetery | -0.265 |
ospel | -0.260 |
vernment | -0.256 |
ppa | -0.254 |
appa | -0.242 |
Token | lined |
Token ID | 16566 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
Frie | +0.895 |
spir | +0.847 |
Male | +0.788 |
AAA | +0.770 |
UCHIJ | +0.748 |
Neg logit contributions | |
emetery | -1.369 |
ospel | -1.360 |
vernment | -1.330 |
ppa | -1.330 |
appa | -1.281 |
Token | structural |
Token ID | 13204 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
emetery | +0.729 |
ospel | +0.720 |
vernment | +0.705 |
ppa | +0.700 |
appa | +0.673 |
Neg logit contributions | |
Frie | -0.573 |
spir | -0.551 |
Male | -0.519 |
AAA | -0.502 |
querque | -0.493 |
Token | fill |
Token ID | 6070 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
Frie | +0.795 |
spir | +0.752 |
Male | +0.697 |
AAA | +0.677 |
UCHIJ | +0.658 |
Neg logit contributions | |
emetery | -1.360 |
ospel | -1.349 |
vernment | -1.324 |
ppa | -1.320 |
appa | -1.274 |
Token | solution |
Token ID | 4610 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
emetery | +3.117 |
ospel | +3.081 |
vernment | +2.985 |
ppa | +2.980 |
appa | +2.854 |
Neg logit contributions | |
Frie | -2.978 |
spir | -2.840 |
Male | -2.710 |
AAA | -2.602 |
UCHIJ | -2.568 |
Token | while |
Token ID | 981 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
emetery | +2.409 |
ospel | +2.347 |
vernment | +2.308 |
ppa | +2.284 |
Kak | +2.192 |
Neg logit contributions | |
Frie | -2.725 |
spir | -2.636 |
Male | -2.501 |
querque | -2.437 |
AAA | -2.427 |
Token | continuing |
Token ID | 8282 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
emetery | +0.090 |
ospel | +0.089 |
vernment | +0.087 |
ppa | +0.087 |
appa | +0.083 |
Neg logit contributions | |
Frie | -0.093 |
spir | -0.090 |
Male | -0.085 |
AAA | -0.082 |
querque | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
emetery | +1.286 |
ospel | +1.262 |
vernment | +1.250 |
ppa | +1.230 |
Kak | +1.187 |
Neg logit contributions | |
Frie | -1.263 |
spir | -1.218 |
Male | -1.152 |
AAA | -1.109 |
querque | -1.103 |
Token | search |
Token ID | 2989 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
emetery | +0.181 |
ospel | +0.180 |
vernment | +0.176 |
ppa | +0.176 |
appa | +0.168 |
Neg logit contributions | |
Frie | -0.174 |
spir | -0.167 |
Male | -0.159 |
AAA | -0.154 |
querque | -0.152 |
Token | Some |
Token ID | 2773 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
Frie | +0.570 |
spir | +0.545 |
Male | +0.516 |
AAA | +0.508 |
UCHIJ | +0.493 |
Neg logit contributions | |
emetery | -0.617 |
ospel | -0.606 |
vernment | -0.591 |
ppa | -0.589 |
appa | -0.565 |
Token | Pictures |
Token ID | 20051 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Frie | +0.497 |
spir | +0.473 |
Male | +0.448 |
AAA | +0.445 |
UCHIJ | +0.430 |
Neg logit contributions | |
emetery | -0.522 |
ospel | -0.511 |
vernment | -0.502 |
ppa | -0.494 |
appa | -0.477 |
Token | of |
Token ID | 286 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
emetery | +1.040 |
ospel | +1.030 |
vernment | +1.005 |
ppa | +1.003 |
appa | +0.958 |
Neg logit contributions | |
Frie | -1.027 |
spir | -0.988 |
Male | -0.934 |
AAA | -0.911 |
UCHIJ | -0.895 |
Token | That |
Token ID | 1320 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
emetery | +0.343 |
ospel | +0.340 |
vernment | +0.332 |
ppa | +0.332 |
appa | +0.316 |
Neg logit contributions | |
Frie | -0.349 |
spir | -0.337 |
Male | -0.318 |
AAA | -0.310 |
querque | -0.305 |
Token | Corner |
Token ID | 26212 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
emetery | +0.175 |
ospel | +0.173 |
vernment | +0.169 |
ppa | +0.169 |
appa | +0.161 |
Neg logit contributions | |
Frie | -0.174 |
spir | -0.167 |
Male | -0.158 |
AAA | -0.155 |
UCHIJ | -0.152 |
Token | Vari |
Token ID | 15965 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
emetery | +1.793 |
ospel | +1.776 |
vernment | +1.735 |
ppa | +1.733 |
appa | +1.654 |
Neg logit contributions | |
Frie | -1.768 |
spir | -1.700 |
Male | -1.610 |
AAA | -1.569 |
querque | -1.543 |
Token | ation |
Token ID | 341 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
emetery | +2.797 |
ospel | +2.767 |
ppa | +2.703 |
vernment | +2.679 |
appa | +2.563 |
Neg logit contributions | |
Frie | -4.561 |
spir | -4.381 |
Male | -4.232 |
AAA | -4.108 |
querque | -4.098 |
Token | , |
Token ID | 11 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
emetery | +1.324 |
ospel | +1.311 |
vernment | +1.280 |
ppa | +1.279 |
appa | +1.220 |
Neg logit contributions | |
Frie | -1.309 |
spir | -1.259 |
Male | -1.190 |
AAA | -1.161 |
querque | -1.142 |
Token | Don |
Token ID | 2094 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
emetery | +1.834 |
ospel | +1.832 |
ppa | +1.797 |
vernment | +1.781 |
Kak | +1.736 |
Neg logit contributions | |
Frie | -1.746 |
spir | -1.693 |
Male | -1.576 |
querque | -1.540 |
UCHIJ | -1.515 |
Token | � |
Token ID | 447 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Frie | +0.593 |
spir | +0.568 |
Male | +0.534 |
AAA | +0.520 |
UCHIJ | +0.508 |
Neg logit contributions | |
emetery | -0.738 |
ospel | -0.730 |
vernment | -0.716 |
ppa | -0.712 |
appa | -0.684 |
Token | � |
Token ID | 247 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Frie | +1.002 |
spir | +0.948 |
Male | +0.876 |
AAA | +0.847 |
UCHIJ | +0.823 |
Neg logit contributions | |
emetery | -1.777 |
ospel | -1.762 |
vernment | -1.731 |
ppa | -1.725 |
appa | -1.664 |
Token | finished |
Token ID | 5201 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
Frie | +0.912 |
spir | +0.877 |
Male | +0.831 |
AAA | +0.812 |
UCHIJ | +0.794 |
Neg logit contributions | |
emetery | -0.942 |
ospel | -0.932 |
vernment | -0.904 |
ppa | -0.897 |
appa | -0.860 |
Token | eighth |
Token ID | 16974 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Frie | +0.520 |
spir | +0.502 |
Male | +0.476 |
AAA | +0.465 |
querque | +0.458 |
Neg logit contributions | |
emetery | -0.451 |
ospel | -0.446 |
vernment | -0.434 |
ppa | -0.434 |
appa | -0.413 |
Token | in |
Token ID | 287 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
emetery | +1.037 |
ospel | +1.026 |
vernment | +1.003 |
ppa | +1.002 |
appa | +0.959 |
Neg logit contributions | |
Frie | -1.009 |
spir | -0.973 |
Male | -0.915 |
AAA | -0.891 |
UCHIJ | -0.878 |
Token | D |
Token ID | 360 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
emetery | +0.583 |
ospel | +0.577 |
vernment | +0.563 |
ppa | +0.561 |
appa | +0.535 |
Neg logit contributions | |
Frie | -0.633 |
spir | -0.609 |
Male | -0.578 |
AAA | -0.565 |
UCHIJ | -0.555 |
Token | Y |
Token ID | 56 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
Frie | +0.374 |
spir | +0.360 |
Male | +0.340 |
AAA | +0.332 |
UCHIJ | +0.325 |
Neg logit contributions | |
emetery | -0.387 |
ospel | -0.383 |
vernment | -0.374 |
ppa | -0.373 |
appa | -0.356 |
Token | AR |
Token ID | 1503 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
emetery | +0.598 |
ospel | +0.595 |
vernment | +0.580 |
ppa | +0.575 |
appa | +0.547 |
Neg logit contributions | |
Frie | -0.634 |
spir | -0.618 |
Male | -0.582 |
AAA | -0.572 |
UCHIJ | -0.560 |
Token | ( |
Token ID | 357 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
emetery | +3.063 |
ospel | +3.021 |
vernment | +2.986 |
ppa | +2.968 |
appa | +2.854 |
Neg logit contributions | |
Frie | -3.388 |
spir | -3.256 |
Male | -3.070 |
AAA | -2.994 |
querque | -2.944 |
Token | total |
Token ID | 23350 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
emetery | +2.392 |
ospel | +2.367 |
ppa | +2.324 |
vernment | +2.316 |
appa | +2.219 |
Neg logit contributions | |
Frie | -2.564 |
spir | -2.419 |
Male | -2.274 |
AAA | -2.269 |
querque | -2.234 |
Token | value |
Token ID | 1988 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
emetery | +1.475 |
ospel | +1.462 |
vernment | +1.435 |
ppa | +1.422 |
appa | +1.363 |
Neg logit contributions | |
Frie | -1.683 |
spir | -1.630 |
Male | -1.536 |
AAA | -1.489 |
UCHIJ | -1.471 |
Token | at |
Token ID | 379 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
emetery | +1.798 |
ospel | +1.776 |
vernment | +1.741 |
ppa | +1.739 |
appa | +1.665 |
Neg logit contributions | |
Frie | -1.905 |
spir | -1.826 |
Male | -1.728 |
AAA | -1.680 |
UCHIJ | -1.661 |
Token | his |
Token ID | 465 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
emetery | +1.613 |
ospel | +1.592 |
vernment | +1.569 |
ppa | +1.553 |
Kak | +1.483 |
Neg logit contributions | |
Frie | -1.882 |
spir | -1.820 |
Male | -1.721 |
AAA | -1.662 |
UCHIJ | -1.654 |
Token | five |
Token ID | 1936 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
Frie | +1.227 |
spir | +1.182 |
Male | +1.122 |
AAA | +1.107 |
UCHIJ | +1.074 |
Neg logit contributions | |
emetery | -1.184 |
ospel | -1.175 |
vernment | -1.146 |
ppa | -1.143 |
appa | -1.075 |
Token | - |
Token ID | 12 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
Frie | +0.477 |
spir | +0.455 |
Male | +0.426 |
AAA | +0.415 |
UCHIJ | +0.404 |
Neg logit contributions | |
emetery | -0.650 |
ospel | -0.644 |
vernment | -0.630 |
ppa | -0.628 |
appa | -0.604 |
Token | day |
Token ID | 820 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
emetery | +0.060 |
ospel | +0.059 |
vernment | +0.058 |
ppa | +0.058 |
appa | +0.055 |
Neg logit contributions | |
Frie | -0.065 |
spir | -0.063 |
Male | -0.059 |
AAA | -0.058 |
querque | -0.058 |
Token | custody |
Token ID | 10804 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
emetery | +1.024 |
ospel | +1.014 |
vernment | +0.991 |
ppa | +0.988 |
appa | +0.947 |
Neg logit contributions | |
Frie | -0.971 |
spir | -0.933 |
Male | -0.880 |
AAA | -0.858 |
querque | -0.843 |
Token | of |
Token ID | 286 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Frie | +1.241 |
spir | +1.187 |
Male | +1.132 |
AAA | +1.102 |
UCHIJ | +1.081 |
Neg logit contributions | |
emetery | -1.263 |
ospel | -1.254 |
vernment | -1.222 |
ppa | -1.213 |
appa | -1.156 |
Token | Mr |
Token ID | 1770 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
emetery | +0.871 |
ospel | +0.858 |
vernment | +0.838 |
ppa | +0.834 |
appa | +0.798 |
Neg logit contributions | |
Frie | -1.130 |
spir | -1.090 |
Male | -1.036 |
AAA | -1.013 |
querque | -1.005 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
emetery | +2.386 |
ospel | +2.350 |
vernment | +2.298 |
ppa | +2.285 |
appa | +2.223 |
Neg logit contributions | |
Frie | -3.275 |
spir | -3.149 |
Male | -2.982 |
querque | -2.918 |
AAA | -2.911 |
Token | ar |
Token ID | 283 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
Frie | +1.306 |
spir | +1.298 |
Male | +1.220 |
AAA | +1.200 |
UCHIJ | +1.170 |
Neg logit contributions | |
emetery | -1.078 |
ospel | -1.047 |
vernment | -1.044 |
ppa | -1.006 |
Kak | -0.951 |
Token | . |
Token ID | 13 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
emetery | +1.428 |
ospel | +1.406 |
ppa | +1.397 |
vernment | +1.390 |
appa | +1.340 |
Neg logit contributions | |
Frie | -1.603 |
spir | -1.545 |
Male | -1.456 |
AAA | -1.431 |
querque | -1.423 |
Token |
|
Token ID | 198 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
emetery | +0.294 |
ospel | +0.291 |
vernment | +0.284 |
ppa | +0.283 |
appa | +0.271 |
Neg logit contributions | |
Frie | -0.284 |
spir | -0.273 |
Male | -0.257 |
AAA | -0.252 |
querque | -0.247 |
Token |
|
Token ID | 198 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Frie | +0.064 |
spir | +0.062 |
Male | +0.058 |
AAA | +0.057 |
querque | +0.056 |
Neg logit contributions | |
emetery | -0.065 |
ospel | -0.064 |
vernment | -0.063 |
ppa | -0.063 |
appa | -0.060 |