Token | . |
Token ID | 764 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
hyde | +0.313 |
Hole | +0.266 |
rio | +0.254 |
antioxid | +0.249 |
warm | +0.247 |
Neg logit contributions | |
eele | -0.329 |
ilda | -0.321 |
lishes | -0.292 |
ods | -0.291 |
zl | -0.279 |
Token | vertex |
Token ID | 37423 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
hyde | +0.930 |
Hole | +0.818 |
rio | +0.786 |
warm | +0.765 |
antioxid | +0.762 |
Neg logit contributions | |
eele | -0.685 |
ilda | -0.660 |
lishes | -0.588 |
ods | -0.585 |
zl | -0.550 |
Token | . |
Token ID | 764 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
eele | +1.092 |
ilda | +1.057 |
ods | +0.956 |
lishes | +0.953 |
zl | +0.923 |
Neg logit contributions | |
hyde | -1.135 |
Hole | -0.964 |
rio | -0.925 |
antioxid | -0.924 |
warm | -0.900 |
Token | x |
Token ID | 2124 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
hyde | +0.383 |
Hole | +0.335 |
rio | +0.316 |
antioxid | +0.313 |
warm | +0.310 |
Neg logit contributions | |
eele | -0.379 |
ilda | -0.363 |
ods | -0.330 |
lishes | -0.324 |
zl | -0.321 |
Token | yz |
Token ID | 45579 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
hyde | +1.685 |
Hole | +1.458 |
rio | +1.413 |
warm | +1.379 |
antioxid | +1.327 |
Neg logit contributions | |
eele | -1.426 |
ilda | -1.378 |
lishes | -1.256 |
ods | -1.229 |
opsis | -1.173 |
Token | += |
Token ID | 15853 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
hyde | +0.434 |
Hole | +0.391 |
rio | +0.376 |
antioxid | +0.371 |
warm | +0.370 |
Neg logit contributions | |
eele | -0.236 |
ilda | -0.224 |
lishes | -0.196 |
ods | -0.195 |
zl | -0.182 |
Token | v |
Token ID | 410 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
hyde | +5.196 |
Hole | +4.429 |
rio | +4.172 |
warm | +4.090 |
antioxid | +3.979 |
Neg logit contributions | |
eele | -6.888 |
ilda | -6.652 |
lishes | -6.252 |
ods | -6.130 |
escription | -5.934 |
Token | . |
Token ID | 764 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
hyde | +2.478 |
Hole | +2.123 |
rio | +2.012 |
warm | +1.956 |
antioxid | +1.878 |
Neg logit contributions | |
eele | -3.086 |
ilda | -2.983 |
lishes | -2.775 |
ods | -2.736 |
escription | -2.619 |
Token | normal |
Token ID | 3487 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
hyde | +1.806 |
Hole | +1.528 |
rio | +1.454 |
warm | +1.435 |
antioxid | +1.411 |
Neg logit contributions | |
eele | -2.211 |
ilda | -2.144 |
lishes | -2.018 |
ods | -1.988 |
arcity | -1.902 |
Token | * |
Token ID | 1635 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
hyde | +1.252 |
Hole | +1.107 |
rio | +1.066 |
antioxid | +1.052 |
warm | +1.043 |
Neg logit contributions | |
eele | -0.802 |
ilda | -0.764 |
lishes | -0.676 |
ods | -0.675 |
zl | -0.635 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
hyde | +1.221 |
Hole | +1.023 |
rio | +0.970 |
warm | +0.939 |
antioxid | +0.931 |
Neg logit contributions | |
eele | -1.568 |
ilda | -1.536 |
lishes | -1.408 |
ods | -1.406 |
zl | -1.346 |
Token | ver |
Token ID | 332 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
hyde | +0.086 |
Hole | +0.074 |
rio | +0.071 |
warm | +0.069 |
antioxid | +0.068 |
Neg logit contributions | |
eele | -0.089 |
ilda | -0.086 |
lishes | -0.079 |
ods | -0.078 |
zl | -0.075 |
Token | tex |
Token ID | 16886 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
hyde | +0.085 |
Hole | +0.074 |
rio | +0.070 |
antioxid | +0.070 |
warm | +0.069 |
Neg logit contributions | |
eele | -0.075 |
ilda | -0.072 |
ods | -0.066 |
lishes | -0.065 |
zl | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
hyde | +1.552 |
Hole | +1.352 |
rio | +1.290 |
warm | +1.255 |
antioxid | +1.204 |
Neg logit contributions | |
eele | -1.546 |
ilda | -1.521 |
lishes | -1.419 |
ods | -1.372 |
opsis | -1.318 |
Token | xy |
Token ID | 5431 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
hyde | +0.243 |
Hole | +0.206 |
rio | +0.196 |
warm | +0.191 |
antioxid | +0.186 |
Neg logit contributions | |
eele | -0.291 |
ilda | -0.282 |
lishes | -0.261 |
ods | -0.258 |
zl | -0.246 |
Token | z |
Token ID | 89 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
hyde | +1.611 |
Hole | +1.359 |
rio | +1.314 |
warm | +1.265 |
antioxid | +1.185 |
Neg logit contributions | |
eele | -1.973 |
ilda | -1.921 |
lishes | -1.790 |
ods | -1.732 |
opsis | -1.680 |
Token | += |
Token ID | 15853 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
hyde | +0.607 |
Hole | +0.535 |
rio | +0.514 |
warm | +0.504 |
antioxid | +0.492 |
Neg logit contributions | |
eele | -0.459 |
ilda | -0.443 |
lishes | -0.402 |
ods | -0.392 |
opsis | -0.372 |
Token | v |
Token ID | 410 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
hyde | +5.636 |
Hole | +4.944 |
rio | +4.608 |
warm | +4.503 |
antioxid | +4.487 |
Neg logit contributions | |
eele | -6.089 |
ilda | -5.829 |
lishes | -5.544 |
ods | -5.277 |
arcity | -5.174 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
hyde | +1.592 |
Hole | +1.389 |
rio | +1.337 |
warm | +1.285 |
antioxid | +1.271 |
Neg logit contributions | |
eele | -1.507 |
ilda | -1.467 |
lishes | -1.353 |
ods | -1.307 |
opsis | -1.257 |
Token | normal |
Token ID | 11265 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
hyde | +0.573 |
Hole | +0.481 |
rio | +0.458 |
warm | +0.449 |
antioxid | +0.433 |
Neg logit contributions | |
eele | -0.752 |
ilda | -0.727 |
lishes | -0.679 |
ods | -0.668 |
opsis | -0.642 |
Token | * |
Token ID | 1635 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
hyde | +0.387 |
Hole | +0.337 |
rio | +0.327 |
warm | +0.318 |
antioxid | +0.311 |
Neg logit contributions | |
eele | -0.319 |
ilda | -0.311 |
lishes | -0.283 |
ods | -0.276 |
opsis | -0.264 |
Token | time |
Token ID | 640 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
hyde | +1.452 |
Hole | +1.235 |
rio | +1.163 |
warm | +1.128 |
antioxid | +1.109 |
Neg logit contributions | |
eele | -1.832 |
ilda | -1.769 |
lishes | -1.650 |
ods | -1.622 |
zl | -1.554 |
Token | ver |
Token ID | 332 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
eele | +0.078 |
ilda | +0.076 |
ods | +0.070 |
lishes | +0.069 |
zl | +0.067 |
Neg logit contributions | |
hyde | -0.071 |
Hole | -0.061 |
rio | -0.058 |
antioxid | -0.056 |
warm | -0.056 |
Token | tex |
Token ID | 16886 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
eele | +1.132 |
ilda | +1.091 |
lishes | +0.998 |
ods | +0.987 |
zl | +0.940 |
Neg logit contributions | |
hyde | -1.199 |
Hole | -1.038 |
rio | -0.993 |
warm | -0.970 |
antioxid | -0.959 |
Token | . |
Token ID | 13 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
hyde | +0.257 |
Hole | +0.221 |
rio | +0.211 |
warm | +0.206 |
antioxid | +0.202 |
Neg logit contributions | |
eele | -0.267 |
ilda | -0.258 |
lishes | -0.237 |
ods | -0.234 |
zl | -0.223 |
Token | xy |
Token ID | 5431 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
hyde | +0.222 |
Hole | +0.191 |
rio | +0.182 |
warm | +0.176 |
antioxid | +0.176 |
Neg logit contributions | |
eele | -0.236 |
ilda | -0.229 |
lishes | -0.209 |
ods | -0.209 |
zl | -0.200 |
Token | z |
Token ID | 89 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
hyde | +0.185 |
Hole | +0.160 |
rio | +0.153 |
warm | +0.149 |
antioxid | +0.144 |
Neg logit contributions | |
eele | -0.195 |
ilda | -0.188 |
lishes | -0.173 |
ods | -0.171 |
opsis | -0.163 |
Token | += |
Token ID | 15853 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
hyde | +1.084 |
Hole | +0.932 |
rio | +0.888 |
warm | +0.866 |
antioxid | +0.842 |
Neg logit contributions | |
eele | -1.155 |
ilda | -1.118 |
lishes | -1.031 |
ods | -1.012 |
opsis | -0.969 |
Token | v |
Token ID | 410 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
hyde | +5.660 |
Hole | +4.897 |
rio | +4.634 |
warm | +4.557 |
antioxid | +4.432 |
Neg logit contributions | |
eele | -5.999 |
ilda | -5.784 |
lishes | -5.396 |
ods | -5.230 |
arcity | -5.033 |
Token | . |
Token ID | 13 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
hyde | +1.091 |
Hole | +0.946 |
rio | +0.911 |
warm | +0.884 |
antioxid | +0.857 |
Neg logit contributions | |
eele | -1.025 |
ilda | -0.990 |
lishes | -0.918 |
ods | -0.882 |
opsis | -0.852 |
Token | normal |
Token ID | 11265 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
eele | +0.301 |
ilda | +0.291 |
ods | +0.263 |
lishes | +0.263 |
zl | +0.252 |
Neg logit contributions | |
hyde | -0.326 |
Hole | -0.283 |
rio | -0.270 |
antioxid | -0.262 |
warm | -0.262 |
Token | * |
Token ID | 1635 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
hyde | +0.107 |
Hole | +0.093 |
rio | +0.089 |
warm | +0.087 |
antioxid | +0.085 |
Neg logit contributions | |
eele | -0.103 |
ilda | -0.099 |
lishes | -0.091 |
ods | -0.090 |
opsis | -0.085 |
Token | 1 |
Token ID | 352 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
hyde | +1.246 |
Hole | +1.071 |
rio | +1.019 |
warm | +0.994 |
antioxid | +0.976 |
Neg logit contributions | |
eele | -1.342 |
ilda | -1.298 |
lishes | -1.196 |
ods | -1.181 |
zl | -1.123 |
Token | t |
Token ID | 83 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
hyde | +1.271 |
Hole | +1.099 |
rio | +1.056 |
warm | +1.032 |
antioxid | +1.007 |
Neg logit contributions | |
eele | -1.197 |
ilda | -1.157 |
lishes | -1.058 |
ods | -1.045 |
zl | -0.990 |
Token | weet |
Token ID | 7277 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
hyde | +0.307 |
Hole | +0.277 |
rio | +0.271 |
warm | +0.266 |
antioxid | +0.261 |
Neg logit contributions | |
eele | -0.114 |
ilda | -0.107 |
lishes | -0.091 |
ods | -0.088 |
zl | -0.079 |
Token | / |
Token ID | 14 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
hyde | +1.575 |
Hole | +1.355 |
rio | +1.290 |
warm | +1.269 |
antioxid | +1.218 |
Neg logit contributions | |
eele | -1.700 |
ilda | -1.642 |
lishes | -1.513 |
ods | -1.486 |
opsis | -1.423 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
eele | +1.986 |
ilda | +1.922 |
lishes | +1.758 |
ods | +1.750 |
zl | +1.675 |
Neg logit contributions | |
hyde | -1.931 |
Hole | -1.677 |
rio | -1.589 |
warm | -1.554 |
antioxid | -1.541 |
Token | Story |
Token ID | 11605 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
hyde | +0.185 |
Hole | +0.159 |
rio | +0.152 |
warm | +0.149 |
antioxid | +0.145 |
Neg logit contributions | |
eele | -0.195 |
ilda | -0.188 |
lishes | -0.173 |
ods | -0.170 |
zl | -0.162 |
Token | highlights |
Token ID | 11330 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
eele | +0.111 |
ilda | +0.106 |
lishes | +0.096 |
ods | +0.095 |
zl | +0.090 |
Neg logit contributions | |
hyde | -0.129 |
Hole | -0.114 |
rio | -0.109 |
warm | -0.106 |
antioxid | -0.104 |
Token | Secretary |
Token ID | 4986 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
hyde | +5.440 |
Hole | +5.044 |
rio | +4.524 |
warm | +4.425 |
Liver | +4.293 |
Neg logit contributions | |
eele | -5.816 |
ilda | -5.570 |
lishes | -5.158 |
ods | -5.088 |
escription | -4.921 |
Token | of |
Token ID | 286 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
hyde | +0.287 |
Hole | +0.246 |
rio | +0.232 |
warm | +0.226 |
antioxid | +0.222 |
Neg logit contributions | |
eele | -0.356 |
ilda | -0.344 |
lishes | -0.319 |
ods | -0.317 |
zl | -0.303 |
Token | Defense |
Token ID | 5947 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
hyde | +1.352 |
Hole | +1.159 |
rio | +1.085 |
warm | +1.046 |
antioxid | +1.026 |
Neg logit contributions | |
eele | -1.767 |
ilda | -1.706 |
lishes | -1.582 |
ods | -1.567 |
zl | -1.504 |
Token | Chuck |
Token ID | 14663 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
hyde | +0.704 |
Hole | +0.600 |
rio | +0.572 |
warm | +0.556 |
antioxid | +0.548 |
Neg logit contributions | |
eele | -0.787 |
ilda | -0.764 |
lishes | -0.704 |
ods | -0.697 |
zl | -0.664 |
Token | Hag |
Token ID | 21375 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ilda | +1.660 |
eele | +1.646 |
ods | +1.523 |
lishes | +1.518 |
opsis | +1.434 |
Neg logit contributions | |
hyde | -1.236 |
Hole | -0.963 |
antioxid | -0.934 |
rio | -0.928 |
warm | -0.894 |
Token | vote |
Token ID | 3015 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
eele | +0.247 |
ilda | +0.242 |
ods | +0.222 |
lishes | +0.219 |
zl | +0.209 |
Neg logit contributions | |
hyde | -0.217 |
Hole | -0.183 |
rio | -0.174 |
warm | -0.168 |
antioxid | -0.167 |
Token | accordingly |
Token ID | 16062 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
eele | +0.652 |
ilda | +0.632 |
ods | +0.572 |
lishes | +0.571 |
zl | +0.542 |
Neg logit contributions | |
hyde | -0.679 |
Hole | -0.581 |
rio | -0.560 |
warm | -0.541 |
antioxid | -0.539 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
eele | +2.902 |
ilda | +2.822 |
ods | +2.556 |
lishes | +2.507 |
zl | +2.381 |
Neg logit contributions | |
hyde | -3.670 |
Hole | -3.166 |
rio | -3.054 |
antioxid | -3.012 |
warm | -3.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
eele | +0.605 |
ilda | +0.588 |
lishes | +0.536 |
ods | +0.534 |
zl | +0.509 |
Neg logit contributions | |
hyde | -0.582 |
Hole | -0.496 |
rio | -0.476 |
warm | -0.463 |
antioxid | -0.458 |
Token | Story |
Token ID | 11605 |
Feature activation | +2.32e-03 |
Pos logit contributions | |
eele | +0.120 |
ilda | +0.116 |
lishes | +0.107 |
ods | +0.105 |
zl | +0.100 |
Neg logit contributions | |
hyde | -0.114 |
Hole | -0.098 |
rio | -0.094 |
warm | -0.092 |
antioxid | -0.089 |
Token | highlights |
Token ID | 11330 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
hyde | +0.015 |
Hole | +0.013 |
rio | +0.012 |
warm | +0.012 |
antioxid | +0.012 |
Neg logit contributions | |
eele | -0.013 |
ilda | -0.012 |
lishes | -0.011 |
ods | -0.011 |
zl | -0.010 |
Token | Police |
Token ID | 4287 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
hyde | +5.277 |
Hole | +4.897 |
rio | +4.388 |
warm | +4.302 |
Liver | +4.166 |
Neg logit contributions | |
eele | -5.660 |
ilda | -5.413 |
lishes | -5.015 |
ods | -4.945 |
escription | -4.778 |
Token | chief |
Token ID | 4039 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
eele | +1.072 |
ilda | +1.056 |
lishes | +0.964 |
ods | +0.955 |
zl | +0.912 |
Neg logit contributions | |
hyde | -0.965 |
Hole | -0.807 |
rio | -0.774 |
warm | -0.749 |
antioxid | -0.744 |
Token | vows |
Token ID | 36605 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
hyde | +0.922 |
Hole | +0.803 |
rio | +0.769 |
warm | +0.751 |
antioxid | +0.740 |
Neg logit contributions | |
eele | -0.827 |
ilda | -0.798 |
lishes | -0.727 |
ods | -0.720 |
zl | -0.682 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
hyde | +0.825 |
Hole | +0.711 |
rio | +0.673 |
warm | +0.657 |
antioxid | +0.644 |
Neg logit contributions | |
eele | -0.961 |
ilda | -0.930 |
lishes | -0.864 |
ods | -0.852 |
zl | -0.815 |
Token | suspect |
Token ID | 4099 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
hyde | +1.618 |
Hole | +1.388 |
rio | +1.318 |
warm | +1.291 |
antioxid | +1.256 |
Neg logit contributions | |
eele | -1.810 |
ilda | -1.753 |
lishes | -1.611 |
ods | -1.591 |
zl | -1.519 |
Token | : |
Token ID | 25 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
hyde | +0.547 |
Hole | +0.469 |
rio | +0.454 |
antioxid | +0.448 |
warm | +0.440 |
Neg logit contributions | |
eele | -0.425 |
ilda | -0.414 |
ods | -0.369 |
lishes | -0.364 |
zl | -0.347 |
Token |
|
Token ID | 198 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
eele | +1.282 |
ilda | +1.257 |
ods | +1.129 |
lishes | +1.089 |
NB | +1.057 |
Neg logit contributions | |
hyde | -1.624 |
Hole | -1.394 |
rio | -1.342 |
antioxid | -1.331 |
warm | -1.300 |
Token |
|
Token ID | 198 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
hyde | +0.233 |
Hole | +0.200 |
rio | +0.191 |
antioxid | +0.190 |
warm | +0.186 |
Neg logit contributions | |
eele | -0.197 |
ilda | -0.193 |
ods | -0.173 |
lishes | -0.171 |
zl | -0.164 |
Token | Happy |
Token ID | 25082 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
hyde | +0.795 |
Hole | +0.662 |
rio | +0.634 |
warm | +0.623 |
antioxid | +0.593 |
Neg logit contributions | |
eele | -1.104 |
ilda | -1.067 |
lishes | -1.000 |
ods | -0.985 |
opsis | -0.950 |
Token | it |
Token ID | 340 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
hyde | +0.527 |
Hole | +0.448 |
rio | +0.431 |
warm | +0.417 |
antioxid | +0.414 |
Neg logit contributions | |
eele | -0.477 |
ilda | -0.467 |
ods | -0.422 |
lishes | -0.412 |
zl | -0.404 |
Token | worked |
Token ID | 3111 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
hyde | +0.943 |
Hole | +0.787 |
rio | +0.745 |
warm | +0.718 |
antioxid | +0.714 |
Neg logit contributions | |
eele | -1.164 |
ilda | -1.143 |
ods | -1.051 |
lishes | -1.047 |
zl | -1.006 |
Token | out |
Token ID | 503 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
hyde | +3.842 |
Hole | +3.161 |
rio | +2.885 |
warm | +2.847 |
antioxid | +2.676 |
Neg logit contributions | |
eele | -7.325 |
ilda | -7.090 |
lishes | -6.736 |
ods | -6.527 |
escription | -6.386 |
Token | . |
Token ID | 13 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
hyde | +0.116 |
Hole | +0.101 |
rio | +0.098 |
antioxid | +0.096 |
warm | +0.095 |
Neg logit contributions | |
eele | -0.079 |
ilda | -0.077 |
ods | -0.068 |
lishes | -0.067 |
zl | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
hyde | +2.009 |
Hole | +1.809 |
rio | +1.679 |
warm | +1.598 |
antioxid | +1.575 |
Neg logit contributions | |
eele | -2.268 |
ilda | -2.215 |
lishes | -2.049 |
ods | -2.023 |
adle | -1.936 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
hyde | +0.374 |
Hole | +0.321 |
rio | +0.308 |
antioxid | +0.303 |
warm | +0.299 |
Neg logit contributions | |
eele | -0.331 |
ilda | -0.323 |
ods | -0.292 |
lishes | -0.290 |
zl | -0.276 |
Token | If |
Token ID | 1532 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
hyde | +1.013 |
Hole | +0.869 |
rio | +0.835 |
warm | +0.816 |
antioxid | +0.789 |
Neg logit contributions | |
eele | -1.129 |
ilda | -1.091 |
lishes | -1.009 |
ods | -0.988 |
opsis | -0.948 |
Token | --+ |
Token ID | 44785 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
eele | +1.141 |
ilda | +1.110 |
ods | +1.014 |
lishes | +1.008 |
opsis | +0.962 |
Neg logit contributions | |
hyde | -1.020 |
Hole | -0.880 |
rio | -0.821 |
warm | -0.804 |
antioxid | -0.792 |
Token | + |
Token ID | 1343 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
hyde | +0.502 |
Hole | +0.427 |
rio | +0.405 |
warm | +0.382 |
antioxid | +0.378 |
Neg logit contributions | |
eele | -0.709 |
ilda | -0.688 |
lishes | -0.637 |
ods | -0.631 |
opsis | -0.604 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
hyde | +1.433 |
Hole | +1.236 |
rio | +1.178 |
warm | +1.148 |
antioxid | +1.137 |
Neg logit contributions | |
eele | -1.437 |
ilda | -1.394 |
lishes | -1.269 |
ods | -1.266 |
zl | -1.202 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
eele | +0.824 |
ilda | +0.802 |
ods | +0.732 |
lishes | +0.729 |
opsis | +0.696 |
Neg logit contributions | |
hyde | -0.724 |
Hole | -0.623 |
rio | -0.580 |
warm | -0.570 |
antioxid | -0.562 |
Token | < |
Token ID | 1279 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
eele | +0.544 |
ilda | +0.522 |
lishes | +0.469 |
ods | +0.461 |
zl | +0.433 |
Neg logit contributions | |
hyde | -0.744 |
Hole | -0.660 |
rio | -0.635 |
warm | -0.617 |
antioxid | -0.608 |
Token | -- |
Token ID | 438 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
hyde | +1.405 |
Hole | +1.194 |
rio | +1.117 |
antioxid | +1.090 |
warm | +1.078 |
Neg logit contributions | |
eele | -1.710 |
ilda | -1.675 |
ods | -1.536 |
lishes | -1.528 |
zl | -1.465 |
Token | Start |
Token ID | 7253 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
hyde | +5.084 |
Hole | +4.567 |
rio | +4.210 |
warm | +4.096 |
antioxid | +4.011 |
Neg logit contributions | |
eele | -5.815 |
ilda | -5.601 |
lishes | -5.105 |
ods | -5.096 |
cussion | -4.856 |
Token | of |
Token ID | 286 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
hyde | +1.680 |
Hole | +1.429 |
rio | +1.360 |
warm | +1.315 |
antioxid | +1.314 |
Neg logit contributions | |
eele | -1.792 |
ilda | -1.745 |
lishes | -1.588 |
ods | -1.588 |
opsis | -1.517 |
Token | system |
Token ID | 1080 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
hyde | +2.183 |
Hole | +1.910 |
rio | +1.834 |
warm | +1.746 |
antioxid | +1.740 |
Neg logit contributions | |
eele | -2.738 |
ilda | -2.698 |
lishes | -2.450 |
ods | -2.442 |
cussion | -2.319 |
Token | () |
Token ID | 3419 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
eele | +1.096 |
ilda | +1.085 |
ods | +0.990 |
lishes | +0.979 |
opsis | +0.949 |
Neg logit contributions | |
hyde | -0.922 |
Hole | -0.773 |
rio | -0.735 |
antioxid | -0.711 |
warm | -0.705 |
Token | ' |
Token ID | 6 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
hyde | +0.650 |
Hole | +0.528 |
rio | +0.498 |
warm | +0.481 |
antioxid | +0.479 |
Neg logit contributions | |
eele | -0.880 |
ilda | -0.858 |
ods | -0.790 |
lishes | -0.786 |
zl | -0.760 |
Token | --+ |
Token ID | 44785 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
eele | +0.892 |
ilda | +0.866 |
ods | +0.793 |
lishes | +0.787 |
opsis | +0.753 |
Neg logit contributions | |
hyde | -0.789 |
Hole | -0.680 |
rio | -0.635 |
warm | -0.621 |
antioxid | -0.612 |
Token | + |
Token ID | 1343 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
hyde | +0.480 |
Hole | +0.404 |
rio | +0.381 |
warm | +0.361 |
antioxid | +0.357 |
Neg logit contributions | |
eele | -0.708 |
ilda | -0.687 |
lishes | -0.639 |
ods | -0.631 |
opsis | -0.605 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
hyde | +0.886 |
Hole | +0.766 |
rio | +0.730 |
warm | +0.711 |
antioxid | +0.709 |
Neg logit contributions | |
eele | -0.861 |
ilda | -0.838 |
ods | -0.761 |
lishes | -0.758 |
zl | -0.720 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
eele | +0.790 |
ilda | +0.767 |
ods | +0.702 |
lishes | +0.697 |
opsis | +0.667 |
Neg logit contributions | |
hyde | -0.697 |
Hole | -0.601 |
rio | -0.559 |
warm | -0.549 |
antioxid | -0.542 |
Token | < |
Token ID | 1279 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
eele | +0.574 |
ilda | +0.550 |
lishes | +0.494 |
ods | +0.486 |
zl | +0.456 |
Neg logit contributions | |
hyde | -0.802 |
Hole | -0.711 |
rio | -0.683 |
warm | -0.667 |
antioxid | -0.657 |
Token | -- |
Token ID | 438 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
hyde | +1.558 |
Hole | +1.323 |
rio | +1.239 |
antioxid | +1.206 |
warm | +1.196 |
Neg logit contributions | |
eele | -1.912 |
ilda | -1.871 |
ods | -1.718 |
lishes | -1.710 |
zl | -1.638 |
Token | Start |
Token ID | 7253 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
hyde | +5.135 |
Hole | +4.610 |
rio | +4.238 |
warm | +4.142 |
antioxid | +4.035 |
Neg logit contributions | |
eele | -5.764 |
ilda | -5.547 |
lishes | -5.058 |
ods | -5.029 |
cussion | -4.780 |
Token | of |
Token ID | 286 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
hyde | +1.863 |
Hole | +1.584 |
rio | +1.510 |
warm | +1.462 |
antioxid | +1.455 |
Neg logit contributions | |
eele | -2.002 |
ilda | -1.947 |
ods | -1.777 |
lishes | -1.776 |
opsis | -1.698 |
Token | system |
Token ID | 1080 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
hyde | +2.653 |
Hole | +2.332 |
rio | +2.215 |
warm | +2.138 |
antioxid | +2.114 |
Neg logit contributions | |
eele | -2.769 |
ilda | -2.705 |
lishes | -2.454 |
ods | -2.428 |
zl | -2.301 |
Token | () |
Token ID | 3419 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
eele | +0.885 |
ilda | +0.870 |
ods | +0.799 |
lishes | +0.793 |
opsis | +0.766 |
Neg logit contributions | |
hyde | -0.728 |
Hole | -0.610 |
rio | -0.581 |
antioxid | -0.559 |
warm | -0.559 |
Token | ' |
Token ID | 6 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
hyde | +0.684 |
Hole | +0.563 |
rio | +0.526 |
warm | +0.506 |
antioxid | +0.491 |
Neg logit contributions | |
eele | -1.280 |
ilda | -1.256 |
lishes | -1.174 |
ods | -1.158 |
zl | -1.116 |
Token | _ |
Token ID | 4808 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
hyde | +1.662 |
Hole | +1.462 |
rio | +1.408 |
warm | +1.379 |
antioxid | +1.365 |
Neg logit contributions | |
eele | -1.183 |
ilda | -1.138 |
lishes | -1.015 |
ods | -1.009 |
zl | -0.952 |
Token | full |
Token ID | 1336 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
hyde | +2.191 |
Hole | +1.784 |
rio | +1.719 |
warm | +1.659 |
antioxid | +1.607 |
Neg logit contributions | |
eele | -3.311 |
ilda | -3.223 |
lishes | -3.026 |
ods | -2.990 |
zl | -2.840 |
Token | v |
Token ID | 410 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
eele | +1.825 |
ilda | +1.795 |
ods | +1.589 |
lishes | +1.563 |
zl | +1.553 |
Neg logit contributions | |
hyde | -2.116 |
Hole | -1.862 |
rio | -1.743 |
warm | -1.725 |
antioxid | -1.696 |
Token | ) |
Token ID | 1267 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
eele | +1.528 |
ilda | +1.491 |
ods | +1.349 |
lishes | +1.305 |
cs | +1.285 |
Neg logit contributions | |
hyde | -1.753 |
Hole | -1.527 |
antioxid | -1.478 |
rio | -1.430 |
warm | -1.427 |
Token | { |
Token ID | 1391 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
hyde | +1.650 |
Hole | +1.468 |
rio | +1.411 |
antioxid | +1.394 |
warm | +1.390 |
Neg logit contributions | |
eele | -0.908 |
ilda | -0.870 |
lishes | -0.765 |
ods | -0.757 |
opsis | -0.701 |
Token | // |
Token ID | 3373 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
hyde | +3.809 |
Hole | +3.484 |
rio | +3.272 |
warm | +3.177 |
fireplace | +3.155 |
Neg logit contributions | |
eele | -2.791 |
ilda | -2.687 |
lishes | -2.437 |
ods | -2.414 |
zl | -2.276 |
Token | Time |
Token ID | 3862 |
Feature activation | -5.76e-03 |
Pos logit contributions | |
hyde | +4.071 |
Hole | +3.626 |
rio | +3.058 |
warm | +3.052 |
antioxid | +2.926 |
Neg logit contributions | |
eele | -6.563 |
ilda | -6.399 |
lishes | -6.142 |
ods | -5.974 |
arcity | -5.772 |
Token | component |
Token ID | 7515 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
eele | +0.044 |
ilda | +0.043 |
lishes | +0.040 |
ods | +0.040 |
cs | +0.038 |
Neg logit contributions | |
hyde | -0.024 |
Hole | -0.019 |
rio | -0.018 |
warm | -0.017 |
antioxid | -0.017 |
Token | const |
Token ID | 1500 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
eele | +2.727 |
ilda | +2.646 |
lishes | +2.427 |
ods | +2.396 |
cs | +2.300 |
Neg logit contributions | |
hyde | -2.552 |
Hole | -2.094 |
rio | -2.027 |
antioxid | -1.937 |
warm | -1.929 |
Token | float |
Token ID | 12178 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
eele | +0.883 |
ilda | +0.846 |
lishes | +0.740 |
ods | +0.732 |
zl | +0.705 |
Neg logit contributions | |
hyde | -1.270 |
Hole | -1.090 |
rio | -1.070 |
warm | -1.045 |
antioxid | -1.040 |
Token | TA |
Token ID | 21664 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
eele | +0.598 |
ilda | +0.576 |
ods | +0.510 |
lishes | +0.508 |
zl | +0.479 |
Neg logit contributions | |
hyde | -0.826 |
Hole | -0.719 |
rio | -0.697 |
warm | -0.687 |
antioxid | -0.675 |
Token | that |
Token ID | 326 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
hyde | +0.165 |
Hole | +0.143 |
rio | +0.137 |
warm | +0.133 |
antioxid | +0.131 |
Neg logit contributions | |
eele | -0.159 |
ilda | -0.154 |
lishes | -0.141 |
ods | -0.139 |
zl | -0.133 |
Token | � |
Token ID | 564 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
hyde | +1.155 |
Hole | +0.997 |
rio | +0.946 |
warm | +0.924 |
antioxid | +0.907 |
Neg logit contributions | |
eele | -1.253 |
ilda | -1.212 |
lishes | -1.116 |
ods | -1.104 |
zl | -1.055 |
Token | � |
Token ID | 250 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
eele | +1.627 |
ilda | +1.578 |
lishes | +1.453 |
ods | +1.445 |
zl | +1.376 |
Neg logit contributions | |
hyde | -1.367 |
Hole | -1.164 |
rio | -1.103 |
warm | -1.073 |
antioxid | -1.060 |
Token | had |
Token ID | 18108 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
hyde | +0.380 |
Hole | +0.329 |
rio | +0.313 |
warm | +0.305 |
antioxid | +0.302 |
Neg logit contributions | |
eele | -0.383 |
ilda | -0.371 |
lishes | -0.339 |
ods | -0.337 |
zl | -0.320 |
Token | Andrew |
Token ID | 6858 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
eele | +0.253 |
ilda | +0.245 |
lishes | +0.225 |
ods | +0.224 |
zl | +0.213 |
Neg logit contributions | |
hyde | -0.233 |
Hole | -0.200 |
rio | -0.190 |
warm | -0.185 |
antioxid | -0.183 |
Token | Jackson |
Token ID | 6612 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
hyde | +3.465 |
Hole | +3.011 |
rio | +2.867 |
warm | +2.764 |
antioxid | +2.672 |
Neg logit contributions | |
eele | -3.971 |
ilda | -3.759 |
lishes | -3.531 |
ods | -3.453 |
opsis | -3.341 |
Token | been |
Token ID | 587 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
hyde | +4.869 |
Hole | +4.160 |
rio | +3.926 |
warm | +3.822 |
antioxid | +3.650 |
Neg logit contributions | |
eele | -5.955 |
ilda | -5.664 |
lishes | -5.351 |
ods | -5.167 |
escription | -5.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
hyde | +1.219 |
Hole | +1.041 |
rio | +0.987 |
warm | +0.959 |
antioxid | +0.948 |
Neg logit contributions | |
eele | -1.404 |
ilda | -1.364 |
lishes | -1.254 |
ods | -1.246 |
zl | -1.191 |
Token | little |
Token ID | 1310 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
hyde | +0.580 |
Hole | +0.492 |
rio | +0.470 |
warm | +0.455 |
antioxid | +0.450 |
Neg logit contributions | |
eele | -0.681 |
ilda | -0.660 |
lishes | -0.607 |
ods | -0.604 |
zl | -0.577 |
Token | later |
Token ID | 1568 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
eele | +0.285 |
ilda | +0.278 |
lishes | +0.254 |
ods | +0.254 |
zl | +0.243 |
Neg logit contributions | |
hyde | -0.270 |
Hole | -0.232 |
rio | -0.221 |
warm | -0.213 |
antioxid | -0.212 |
Token | , |
Token ID | 11 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
hyde | +1.077 |
Hole | +0.918 |
rio | +0.876 |
warm | +0.852 |
antioxid | +0.830 |
Neg logit contributions | |
eele | -1.240 |
ilda | -1.199 |
lishes | -1.107 |
ods | -1.095 |
zl | -1.047 |
Token | Environmental |
Token ID | 13272 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
eele | +0.438 |
ilda | +0.424 |
lishes | +0.390 |
ods | +0.386 |
zl | +0.367 |
Neg logit contributions | |
hyde | -0.418 |
Hole | -0.358 |
rio | -0.343 |
warm | -0.333 |
antioxid | -0.329 |
Token | Grant |
Token ID | 12181 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
hyde | +1.717 |
Hole | +1.515 |
rio | +1.385 |
warm | +1.349 |
antioxid | +1.325 |
Neg logit contributions | |
eele | -2.238 |
ilda | -2.176 |
lishes | -1.999 |
ods | -1.998 |
zl | -1.923 |
Token | makers |
Token ID | 6620 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
eele | +2.315 |
ilda | +2.290 |
ods | +2.097 |
lishes | +2.084 |
zl | +1.962 |
Neg logit contributions | |
hyde | -2.584 |
Hole | -2.261 |
antioxid | -2.136 |
rio | -2.132 |
warm | -2.044 |
Token | Association |
Token ID | 5396 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
hyde | +1.156 |
Hole | +1.010 |
rio | +0.934 |
warm | +0.926 |
antioxid | +0.905 |
Neg logit contributions | |
eele | -1.354 |
ilda | -1.289 |
ods | -1.196 |
lishes | -1.191 |
zl | -1.153 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
hyde | +1.868 |
Hole | +1.654 |
rio | +1.542 |
warm | +1.519 |
antioxid | +1.495 |
Neg logit contributions | |
eele | -2.106 |
ilda | -2.031 |
ods | -1.845 |
lishes | -1.841 |
zl | -1.784 |
Token | Rockefeller |
Token ID | 32764 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
eele | +0.905 |
ilda | +0.880 |
lishes | +0.821 |
ods | +0.815 |
zl | +0.783 |
Neg logit contributions | |
hyde | -0.547 |
Hole | -0.451 |
rio | -0.421 |
warm | -0.406 |
antioxid | -0.397 |
Token | Family |
Token ID | 7884 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
hyde | +4.052 |
Hole | +3.426 |
rio | +3.161 |
warm | +3.048 |
antioxid | +2.932 |
Neg logit contributions | |
eele | -6.700 |
ilda | -6.456 |
lishes | -6.073 |
ods | -5.993 |
escription | -5.802 |
Token | Fund |
Token ID | 7557 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
hyde | +2.301 |
Hole | +1.820 |
rio | +1.711 |
warm | +1.638 |
antioxid | +1.611 |
Neg logit contributions | |
eele | -4.276 |
ilda | -4.181 |
lishes | -3.898 |
ods | -3.877 |
zl | -3.737 |
Token | , |
Token ID | 11 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
hyde | +0.823 |
Hole | +0.723 |
rio | +0.676 |
warm | +0.665 |
antioxid | +0.651 |
Neg logit contributions | |
eele | -0.921 |
ilda | -0.889 |
lishes | -0.813 |
ods | -0.810 |
zl | -0.777 |
Token | Inc |
Token ID | 3457 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
eele | +3.126 |
ilda | +3.003 |
lishes | +2.704 |
ods | +2.680 |
zl | +2.526 |
Neg logit contributions | |
hyde | -4.075 |
Hole | -3.591 |
rio | -3.442 |
warm | -3.370 |
antioxid | -3.325 |
Token | .: |
Token ID | 11207 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
eele | +0.859 |
ilda | +0.824 |
ods | +0.734 |
lishes | +0.730 |
zl | +0.701 |
Neg logit contributions | |
hyde | -1.084 |
Hole | -0.961 |
rio | -0.922 |
warm | -0.901 |
antioxid | -0.889 |
Token | � |
Token ID | 447 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
hyde | +0.545 |
Hole | +0.466 |
rio | +0.446 |
warm | +0.434 |
antioxid | +0.422 |
Neg logit contributions | |
eele | -0.585 |
ilda | -0.564 |
lishes | -0.525 |
ods | -0.513 |
zl | -0.488 |
Token | � |
Token ID | 247 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
eele | +0.074 |
ilda | +0.071 |
lishes | +0.067 |
ods | +0.066 |
zl | +0.063 |
Neg logit contributions | |
hyde | -0.048 |
Hole | -0.040 |
rio | -0.038 |
warm | -0.036 |
antioxid | -0.036 |
Token | ) |
Token ID | 8 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
eele | +0.803 |
ilda | +0.775 |
lishes | +0.706 |
ods | +0.700 |
zl | +0.664 |
Neg logit contributions | |
hyde | -0.877 |
Hole | -0.763 |
rio | -0.730 |
warm | -0.712 |
antioxid | -0.703 |
Token | exp |
Token ID | 1033 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
hyde | +1.333 |
Hole | +1.135 |
rio | +1.077 |
warm | +1.047 |
antioxid | +1.026 |
Neg logit contributions | |
eele | -1.553 |
ilda | -1.506 |
lishes | -1.391 |
ods | -1.374 |
zl | -1.312 |
Token | ( |
Token ID | 7 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
eele | +0.344 |
ilda | +0.334 |
lishes | +0.307 |
ods | +0.304 |
zl | +0.290 |
Neg logit contributions | |
hyde | -0.306 |
Hole | -0.261 |
rio | -0.249 |
warm | -0.242 |
antioxid | -0.238 |
Token | -( |
Token ID | 30420 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
hyde | +0.300 |
Hole | +0.258 |
rio | +0.247 |
warm | +0.241 |
antioxid | +0.236 |
Neg logit contributions | |
eele | -0.306 |
ilda | -0.296 |
lishes | -0.272 |
ods | -0.269 |
zl | -0.255 |
Token | t |
Token ID | 83 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
hyde | +4.444 |
Hole | +3.571 |
warm | +3.500 |
rio | +3.478 |
antioxid | +3.169 |
Neg logit contributions | |
eele | -6.056 |
ilda | -5.850 |
lishes | -5.563 |
ods | -5.254 |
arcity | -5.106 |
Token | - |
Token ID | 12 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
hyde | +1.802 |
Hole | +1.519 |
rio | +1.467 |
warm | +1.426 |
antioxid | +1.362 |
Neg logit contributions | |
eele | -2.121 |
ilda | -2.037 |
lishes | -1.930 |
ods | -1.852 |
opsis | -1.772 |
Token | t |
Token ID | 83 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
hyde | +2.097 |
Hole | +1.763 |
rio | +1.684 |
warm | +1.651 |
antioxid | +1.585 |
Neg logit contributions | |
eele | -2.586 |
ilda | -2.505 |
lishes | -2.342 |
ods | -2.279 |
opsis | -2.181 |
Token | � |
Token ID | 447 |
Feature activation | -1.96e-04 |
Pos logit contributions | |
hyde | +1.377 |
Hole | +1.127 |
rio | +1.077 |
warm | +1.036 |
antioxid | +0.995 |
Neg logit contributions | |
eele | -2.167 |
ilda | -2.092 |
lishes | -1.983 |
ods | -1.925 |
opsis | -1.844 |
Token | � |
Token ID | 247 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
eele | +0.001 |
ilda | +0.001 |
ods | +0.001 |
lishes | +0.001 |
zl | +0.001 |
Neg logit contributions | |
hyde | -0.001 |
Hole | -0.001 |
rio | -0.001 |
warm | -0.001 |
antioxid | -0.001 |
Token | --+ |
Token ID | 44785 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
eele | +0.716 |
ilda | +0.697 |
ods | +0.637 |
lishes | +0.635 |
opsis | +0.605 |
Neg logit contributions | |
hyde | -0.628 |
Hole | -0.539 |
rio | -0.505 |
warm | -0.493 |
antioxid | -0.484 |
Token | + |
Token ID | 1343 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
hyde | +1.020 |
Hole | +0.844 |
rio | +0.812 |
warm | +0.796 |
antioxid | +0.787 |
Neg logit contributions | |
eele | -1.184 |
ilda | -1.162 |
ods | -1.056 |
lishes | -1.054 |
zl | -1.016 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
hyde | +0.714 |
Hole | +0.618 |
rio | +0.589 |
antioxid | +0.573 |
warm | +0.573 |
Neg logit contributions | |
eele | -0.687 |
ilda | -0.668 |
ods | -0.607 |
lishes | -0.604 |
zl | -0.575 |
Token | --+ |
Token ID | 44785 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
eele | +0.438 |
ilda | +0.427 |
ods | +0.390 |
lishes | +0.389 |
opsis | +0.371 |
Neg logit contributions | |
hyde | -0.380 |
Hole | -0.327 |
rio | -0.306 |
warm | -0.299 |
antioxid | -0.294 |
Token | < |
Token ID | 1279 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
hyde | +0.193 |
Hole | +0.172 |
rio | +0.164 |
warm | +0.160 |
antioxid | +0.158 |
Neg logit contributions | |
eele | -0.141 |
ilda | -0.135 |
lishes | -0.122 |
ods | -0.119 |
opsis | -0.112 |
Token | -- |
Token ID | 438 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
hyde | +1.568 |
Hole | +1.326 |
rio | +1.249 |
antioxid | +1.207 |
warm | +1.203 |
Neg logit contributions | |
eele | -1.962 |
ilda | -1.915 |
ods | -1.757 |
lishes | -1.756 |
zl | -1.680 |
Token | Start |
Token ID | 7253 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
hyde | +4.870 |
Hole | +4.331 |
rio | +4.028 |
warm | +3.926 |
antioxid | +3.883 |
Neg logit contributions | |
eele | -5.492 |
ilda | -5.300 |
lishes | -4.853 |
ods | -4.819 |
cussion | -4.582 |
Token | of |
Token ID | 286 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
hyde | +1.948 |
Hole | +1.657 |
rio | +1.577 |
warm | +1.525 |
antioxid | +1.517 |
Neg logit contributions | |
eele | -2.181 |
ilda | -2.121 |
lishes | -1.940 |
ods | -1.933 |
zl | -1.847 |
Token | system |
Token ID | 1080 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
hyde | +2.278 |
Hole | +1.963 |
rio | +1.870 |
warm | +1.764 |
antioxid | +1.756 |
Neg logit contributions | |
eele | -3.454 |
ilda | -3.410 |
lishes | -3.140 |
ods | -3.098 |
cussion | -2.974 |
Token | () |
Token ID | 3419 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
eele | +0.745 |
ilda | +0.736 |
ods | +0.673 |
lishes | +0.667 |
zl | +0.644 |
Neg logit contributions | |
hyde | -0.606 |
Hole | -0.509 |
rio | -0.483 |
antioxid | -0.467 |
warm | -0.463 |
Token | ' |
Token ID | 6 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
hyde | +1.101 |
Hole | +0.897 |
rio | +0.849 |
antioxid | +0.820 |
warm | +0.816 |
Neg logit contributions | |
eele | -1.506 |
ilda | -1.475 |
ods | -1.357 |
lishes | -1.345 |
zl | -1.304 |
Token | ) |
Token ID | 1267 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
hyde | +0.512 |
Hole | +0.438 |
rio | +0.417 |
warm | +0.396 |
antioxid | +0.383 |
Neg logit contributions | |
eele | -0.656 |
ilda | -0.639 |
lishes | -0.592 |
ods | -0.580 |
zl | -0.564 |
Token | $ |
Token ID | 720 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
hyde | +3.744 |
Hole | +3.297 |
rio | +3.113 |
warm | +3.002 |
antioxid | +2.924 |
Neg logit contributions | |
eele | -3.744 |
ilda | -3.641 |
lishes | -3.323 |
ods | -3.251 |
cussion | -3.109 |
Token | s |
Token ID | 82 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
eele | +1.185 |
ilda | +1.143 |
lishes | +1.037 |
ods | +1.026 |
zl | +0.970 |
Neg logit contributions | |
hyde | -1.383 |
Hole | -1.207 |
rio | -1.160 |
warm | -1.133 |
antioxid | -1.114 |
Token | z |
Token ID | 89 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
eele | +0.514 |
ilda | +0.492 |
lishes | +0.450 |
ods | +0.442 |
opsis | +0.420 |
Neg logit contributions | |
hyde | -0.554 |
Hole | -0.481 |
rio | -0.464 |
warm | -0.451 |
antioxid | -0.438 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
eele | +0.098 |
ilda | +0.095 |
lishes | +0.088 |
ods | +0.087 |
zl | +0.083 |
Neg logit contributions | |
hyde | -0.084 |
Hole | -0.071 |
rio | -0.068 |
warm | -0.066 |
antioxid | -0.064 |
Token | = |
Token ID | 796 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
eele | +0.779 |
ilda | +0.755 |
lishes | +0.698 |
ods | +0.686 |
opsis | +0.658 |
Neg logit contributions | |
hyde | -0.648 |
Hole | -0.550 |
rio | -0.526 |
warm | -0.508 |
antioxid | -0.492 |
Token | [ |
Token ID | 685 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
hyde | +4.698 |
Hole | +4.185 |
rio | +3.837 |
warm | +3.778 |
antioxid | +3.624 |
Neg logit contributions | |
eele | -5.512 |
ilda | -5.400 |
lishes | -4.959 |
ods | -4.826 |
cussion | -4.718 |
Token | system |
Token ID | 10057 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
hyde | +1.695 |
Hole | +1.476 |
rio | +1.407 |
warm | +1.378 |
antioxid | +1.321 |
Neg logit contributions | |
eele | -1.760 |
ilda | -1.706 |
lishes | -1.570 |
ods | -1.530 |
adle | -1.462 |
Token | . |
Token ID | 13 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
hyde | +1.403 |
Hole | +1.232 |
rio | +1.183 |
warm | +1.156 |
antioxid | +1.144 |
Neg logit contributions | |
eele | -1.094 |
ilda | -1.054 |
lishes | -0.950 |
ods | -0.942 |
zl | -0.888 |
Token | windows |
Token ID | 28457 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
hyde | +0.862 |
Hole | +0.692 |
rio | +0.670 |
warm | +0.649 |
antioxid | +0.588 |
Neg logit contributions | |
eele | -1.595 |
ilda | -1.562 |
lishes | -1.454 |
ods | -1.423 |
adle | -1.379 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
eele | +1.763 |
ilda | +1.694 |
lishes | +1.549 |
ods | +1.516 |
opsis | +1.437 |
Neg logit contributions | |
hyde | -1.970 |
Hole | -1.728 |
rio | -1.671 |
warm | -1.620 |
antioxid | -1.588 |
Token | --+ |
Token ID | 44785 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
eele | +0.978 |
ilda | +0.949 |
ods | +0.872 |
lishes | +0.865 |
opsis | +0.827 |
Neg logit contributions | |
hyde | -0.861 |
Hole | -0.742 |
rio | -0.691 |
warm | -0.677 |
antioxid | -0.669 |
Token | + |
Token ID | 1343 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
hyde | +0.557 |
Hole | +0.478 |
rio | +0.456 |
warm | +0.446 |
antioxid | +0.439 |
Neg logit contributions | |
eele | -0.571 |
ilda | -0.553 |
lishes | -0.507 |
ods | -0.503 |
zl | -0.479 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
hyde | +0.709 |
Hole | +0.607 |
rio | +0.579 |
warm | +0.561 |
antioxid | +0.546 |
Neg logit contributions | |
eele | -0.828 |
ilda | -0.795 |
lishes | -0.739 |
ods | -0.720 |
zl | -0.694 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
eele | +0.373 |
ilda | +0.362 |
ods | +0.332 |
lishes | +0.331 |
opsis | +0.316 |
Neg logit contributions | |
hyde | -0.317 |
Hole | -0.272 |
rio | -0.254 |
warm | -0.249 |
antioxid | -0.245 |
Token | < |
Token ID | 1279 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
eele | +0.128 |
ilda | +0.124 |
lishes | +0.112 |
ods | +0.111 |
zl | +0.106 |
Neg logit contributions | |
hyde | -0.151 |
Hole | -0.131 |
rio | -0.126 |
warm | -0.123 |
antioxid | -0.121 |
Token | -- |
Token ID | 438 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
hyde | +1.470 |
Hole | +1.217 |
rio | +1.176 |
warm | +1.132 |
antioxid | +1.093 |
Neg logit contributions | |
eele | -2.223 |
ilda | -2.140 |
lishes | -2.010 |
ods | -1.957 |
arcity | -1.898 |
Token | Start |
Token ID | 7253 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
hyde | +4.770 |
Hole | +4.194 |
rio | +3.907 |
warm | +3.814 |
antioxid | +3.751 |
Neg logit contributions | |
eele | -5.511 |
ilda | -5.301 |
lishes | -4.860 |
ods | -4.842 |
arcity | -4.589 |
Token | of |
Token ID | 286 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
hyde | +0.999 |
Hole | +0.840 |
rio | +0.800 |
warm | +0.773 |
antioxid | +0.760 |
Neg logit contributions | |
eele | -1.357 |
ilda | -1.318 |
lishes | -1.217 |
ods | -1.207 |
zl | -1.152 |
Token | system |
Token ID | 1080 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
hyde | +1.276 |
Hole | +1.104 |
rio | +1.052 |
warm | +1.021 |
antioxid | +1.006 |
Neg logit contributions | |
eele | -1.350 |
ilda | -1.307 |
lishes | -1.198 |
ods | -1.188 |
zl | -1.129 |
Token | () |
Token ID | 3419 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
eele | +1.497 |
ilda | +1.452 |
lishes | +1.355 |
ods | +1.337 |
zl | +1.290 |
Neg logit contributions | |
hyde | -0.941 |
Hole | -0.779 |
rio | -0.731 |
warm | -0.706 |
antioxid | -0.692 |
Token | ' |
Token ID | 6 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
hyde | +0.751 |
Hole | +0.615 |
rio | +0.579 |
warm | +0.555 |
antioxid | +0.538 |
Neg logit contributions | |
eele | -1.389 |
ilda | -1.363 |
lishes | -1.273 |
ods | -1.259 |
zl | -1.210 |
Token | rop |
Token ID | 1773 |
Feature activation | +2.24e-04 |
Pos logit contributions | |
hyde | +0.587 |
Hole | +0.502 |
rio | +0.487 |
warm | +0.465 |
antioxid | +0.455 |
Neg logit contributions | |
eele | -0.636 |
ilda | -0.621 |
lishes | -0.578 |
ods | -0.559 |
zl | -0.544 |
Token | yl |
Token ID | 2645 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
hyde | +0.001 |
Hole | +0.001 |
rio | +0.001 |
warm | +0.001 |
antioxid | +0.001 |
Neg logit contributions | |
eele | -0.002 |
ilda | -0.001 |
lishes | -0.001 |
ods | -0.001 |
zl | -0.001 |
Token | methyl |
Token ID | 43654 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
eele | +0.075 |
ilda | +0.072 |
lishes | +0.066 |
ods | +0.065 |
zl | +0.061 |
Neg logit contributions | |
hyde | -0.083 |
Hole | -0.073 |
rio | -0.070 |
warm | -0.068 |
antioxid | -0.067 |
Token | - |
Token ID | 12 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
hyde | +1.175 |
Hole | +1.019 |
rio | +0.983 |
warm | +0.957 |
antioxid | +0.941 |
Neg logit contributions | |
eele | -1.040 |
ilda | -1.007 |
lishes | -0.919 |
ods | -0.901 |
zl | -0.853 |
Token | 7 |
Token ID | 22 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
hyde | +1.432 |
Hole | +1.220 |
rio | +1.176 |
warm | +1.151 |
antioxid | +1.124 |
Neg logit contributions | |
eele | -1.459 |
ilda | -1.414 |
lishes | -1.293 |
ods | -1.276 |
zl | -1.215 |
Token | -( |
Token ID | 30420 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
hyde | +2.479 |
Hole | +2.150 |
rio | +2.031 |
warm | +1.966 |
antioxid | +1.951 |
Neg logit contributions | |
eele | -2.739 |
ilda | -2.664 |
lishes | -2.476 |
ods | -2.390 |
zl | -2.307 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
hyde | +4.151 |
Hole | +3.441 |
rio | +3.331 |
warm | +3.129 |
antioxid | +3.004 |
Neg logit contributions | |
eele | -6.160 |
ilda | -5.916 |
lishes | -5.534 |
ods | -5.287 |
opsis | -5.175 |
Token | , |
Token ID | 11 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
hyde | +1.604 |
Hole | +1.393 |
rio | +1.338 |
warm | +1.274 |
antioxid | +1.267 |
Neg logit contributions | |
eele | -1.725 |
ilda | -1.666 |
lishes | -1.536 |
ods | -1.492 |
zl | -1.446 |
Token | 6 |
Token ID | 21 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
hyde | +1.211 |
Hole | +1.000 |
rio | +0.949 |
warm | +0.907 |
antioxid | +0.876 |
Neg logit contributions | |
eele | -1.888 |
ilda | -1.847 |
lishes | -1.721 |
ods | -1.690 |
zl | -1.630 |
Token | - |
Token ID | 12 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
hyde | +1.194 |
Hole | +1.038 |
rio | +0.980 |
warm | +0.947 |
antioxid | +0.928 |
Neg logit contributions | |
eele | -1.300 |
ilda | -1.270 |
lishes | -1.171 |
ods | -1.124 |
opsis | -1.092 |
Token | dim |
Token ID | 27740 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
hyde | +1.712 |
Hole | +1.505 |
rio | +1.454 |
warm | +1.412 |
antioxid | +1.383 |
Neg logit contributions | |
eele | -1.282 |
ilda | -1.239 |
lishes | -1.116 |
ods | -1.072 |
zl | -1.033 |
Token | org |
Token ID | 2398 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
hyde | +0.628 |
Hole | +0.532 |
rio | +0.504 |
antioxid | +0.482 |
warm | +0.469 |
Neg logit contributions | |
eele | -0.745 |
ilda | -0.731 |
ods | -0.671 |
lishes | -0.658 |
adle | -0.632 |
Token | / |
Token ID | 14 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
hyde | +0.630 |
Hole | +0.549 |
rio | +0.526 |
antioxid | +0.515 |
warm | +0.515 |
Neg logit contributions | |
eele | -0.477 |
ilda | -0.464 |
lishes | -0.417 |
ods | -0.414 |
zl | -0.389 |
Token | index |
Token ID | 9630 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
eele | +0.893 |
ilda | +0.868 |
lishes | +0.789 |
ods | +0.789 |
zl | +0.753 |
Neg logit contributions | |
hyde | -0.833 |
Hole | -0.718 |
rio | -0.681 |
warm | -0.661 |
antioxid | -0.659 |
Token | . |
Token ID | 13 |
Feature activation | +7.37e-03 |
Pos logit contributions | |
eele | +0.633 |
ilda | +0.617 |
ods | +0.546 |
lishes | +0.541 |
zl | +0.512 |
Neg logit contributions | |
hyde | -0.895 |
Hole | -0.793 |
rio | -0.759 |
antioxid | -0.745 |
warm | -0.738 |
Token | php |
Token ID | 10121 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
hyde | +0.052 |
Hole | +0.047 |
rio | +0.044 |
antioxid | +0.044 |
warm | +0.043 |
Neg logit contributions | |
eele | -0.035 |
ilda | -0.034 |
ods | -0.030 |
lishes | -0.030 |
zl | -0.028 |
Token | ? |
Token ID | 30 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
hyde | +1.582 |
Hole | +1.348 |
rio | +1.280 |
warm | +1.242 |
antioxid | +1.225 |
Neg logit contributions | |
eele | -1.826 |
ilda | -1.776 |
lishes | -1.631 |
ods | -1.623 |
zl | -1.549 |
Token | topic |
Token ID | 26652 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
hyde | +3.700 |
Hole | +3.036 |
rio | +2.886 |
warm | +2.780 |
antioxid | +2.578 |
Neg logit contributions | |
eele | -6.407 |
ilda | -6.117 |
lishes | -5.758 |
ods | -5.586 |
opsis | -5.512 |
Token | = |
Token ID | 28 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
hyde | +0.175 |
Hole | +0.148 |
rio | +0.139 |
warm | +0.136 |
antioxid | +0.135 |
Neg logit contributions | |
eele | -0.228 |
ilda | -0.225 |
ods | -0.206 |
lishes | -0.205 |
zl | -0.198 |
Token | 28 |
Token ID | 2078 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
hyde | +1.090 |
Hole | +0.929 |
rio | +0.886 |
warm | +0.862 |
antioxid | +0.843 |
Neg logit contributions | |
eele | -1.242 |
ilda | -1.203 |
lishes | -1.110 |
ods | -1.098 |
zl | -1.047 |
Token | 18 |
Token ID | 1507 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
hyde | +1.234 |
Hole | +1.053 |
rio | +1.004 |
warm | +0.977 |
antioxid | +0.950 |
Neg logit contributions | |
eele | -1.402 |
ilda | -1.358 |
lishes | -1.253 |
ods | -1.239 |
zl | -1.179 |
Token | 48 |
Token ID | 2780 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
hyde | +0.430 |
Hole | +0.368 |
rio | +0.350 |
warm | +0.342 |
antioxid | +0.332 |
Neg logit contributions | |
eele | -0.471 |
ilda | -0.456 |
lishes | -0.420 |
ods | -0.415 |
opsis | -0.394 |
Token | founder |
Token ID | 9119 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
hyde | +0.852 |
Hole | +0.736 |
rio | +0.695 |
warm | +0.678 |
antioxid | +0.664 |
Neg logit contributions | |
eele | -0.949 |
ilda | -0.917 |
lishes | -0.845 |
ods | -0.838 |
zl | -0.798 |
Token | Rev |
Token ID | 5416 |
Feature activation | -1.64e-03 |
Pos logit contributions | |
hyde | +1.758 |
Hole | +1.551 |
rio | +1.474 |
warm | +1.444 |
antioxid | +1.416 |
Neg logit contributions | |
eele | -1.586 |
ilda | -1.514 |
lishes | -1.381 |
ods | -1.375 |
zl | -1.303 |
Token | . |
Token ID | 13 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
eele | +0.009 |
ilda | +0.009 |
lishes | +0.008 |
ods | +0.008 |
zl | +0.008 |
Neg logit contributions | |
hyde | -0.010 |
Hole | -0.009 |
rio | -0.008 |
warm | -0.008 |
antioxid | -0.008 |
Token | Ted |
Token ID | 11396 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
eele | +0.956 |
ilda | +0.929 |
lishes | +0.841 |
ods | +0.831 |
zl | +0.788 |
Neg logit contributions | |
hyde | -1.133 |
Hole | -0.979 |
rio | -0.945 |
warm | -0.923 |
antioxid | -0.916 |
Token | H |
Token ID | 367 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
eele | +0.891 |
ilda | +0.862 |
lishes | +0.791 |
ods | +0.784 |
zl | +0.749 |
Neg logit contributions | |
hyde | -0.852 |
Hole | -0.730 |
rio | -0.696 |
warm | -0.681 |
antioxid | -0.676 |
Token | agg |
Token ID | 9460 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
hyde | +0.272 |
Hole | +0.236 |
rio | +0.231 |
warm | +0.223 |
antioxid | +0.213 |
Neg logit contributions | |
eele | -0.232 |
ilda | -0.222 |
lishes | -0.206 |
ods | -0.199 |
zl | -0.192 |
Token | ard |
Token ID | 446 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
hyde | +5.971 |
Hole | +5.246 |
rio | +5.070 |
warm | +4.961 |
antioxid | +4.726 |
Neg logit contributions | |
eele | -4.062 |
ilda | -3.779 |
lishes | -3.473 |
ods | -3.312 |
escription | -3.232 |
Token | is |
Token ID | 318 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
hyde | +0.425 |
Hole | +0.366 |
rio | +0.350 |
warm | +0.341 |
antioxid | +0.335 |
Neg logit contributions | |
eele | -0.435 |
ilda | -0.421 |
lishes | -0.386 |
ods | -0.382 |
zl | -0.364 |
Token | prof |
Token ID | 1534 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
eele | +0.809 |
ilda | +0.792 |
lishes | +0.724 |
ods | +0.724 |
zl | +0.690 |
Neg logit contributions | |
hyde | -0.738 |
Hole | -0.623 |
rio | -0.594 |
warm | -0.578 |
antioxid | -0.574 |
Token | iled |
Token ID | 3902 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
eele | +1.345 |
ilda | +1.304 |
lishes | +1.199 |
ods | +1.189 |
zl | +1.135 |
Neg logit contributions | |
hyde | -1.206 |
Hole | -1.032 |
rio | -0.982 |
warm | -0.955 |
antioxid | -0.941 |
Token | in |
Token ID | 287 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
eele | +1.053 |
ilda | +1.025 |
lishes | +0.935 |
ods | +0.929 |
zl | +0.887 |
Neg logit contributions | |
hyde | -1.023 |
Hole | -0.877 |
rio | -0.840 |
warm | -0.816 |
antioxid | -0.807 |
Token | --+ |
Token ID | 44785 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
eele | +0.882 |
ilda | +0.858 |
ods | +0.785 |
lishes | +0.781 |
opsis | +0.745 |
Neg logit contributions | |
hyde | -0.775 |
Hole | -0.667 |
rio | -0.624 |
warm | -0.609 |
antioxid | -0.599 |
Token | + |
Token ID | 1343 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
hyde | +0.888 |
Hole | +0.735 |
rio | +0.706 |
warm | +0.693 |
antioxid | +0.681 |
Neg logit contributions | |
eele | -1.041 |
ilda | -1.019 |
lishes | -0.928 |
ods | -0.928 |
zl | -0.893 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
hyde | +0.688 |
Hole | +0.595 |
rio | +0.567 |
antioxid | +0.552 |
warm | +0.552 |
Neg logit contributions | |
eele | -0.661 |
ilda | -0.643 |
ods | -0.584 |
lishes | -0.581 |
zl | -0.553 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
eele | +0.659 |
ilda | +0.641 |
ods | +0.586 |
lishes | +0.584 |
opsis | +0.557 |
Neg logit contributions | |
hyde | -0.575 |
Hole | -0.495 |
rio | -0.462 |
warm | -0.452 |
antioxid | -0.446 |
Token | < |
Token ID | 1279 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
eele | +0.083 |
ilda | +0.079 |
lishes | +0.071 |
ods | +0.070 |
opsis | +0.066 |
Neg logit contributions | |
hyde | -0.115 |
Hole | -0.102 |
rio | -0.098 |
warm | -0.095 |
antioxid | -0.094 |
Token | -- |
Token ID | 438 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
hyde | +1.363 |
Hole | +1.154 |
rio | +1.086 |
antioxid | +1.053 |
warm | +1.045 |
Neg logit contributions | |
eele | -1.683 |
ilda | -1.645 |
ods | -1.509 |
lishes | -1.505 |
zl | -1.440 |
Token | Start |
Token ID | 7253 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
hyde | +4.320 |
Hole | +3.895 |
rio | +3.554 |
warm | +3.446 |
antioxid | +3.376 |
Neg logit contributions | |
eele | -5.657 |
ilda | -5.437 |
lishes | -5.019 |
ods | -5.004 |
arcity | -4.761 |
Token | of |
Token ID | 286 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
hyde | +1.825 |
Hole | +1.552 |
rio | +1.478 |
warm | +1.429 |
antioxid | +1.423 |
Neg logit contributions | |
eele | -2.018 |
ilda | -1.964 |
lishes | -1.794 |
ods | -1.789 |
zl | -1.708 |
Token | system |
Token ID | 1080 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
hyde | +2.443 |
Hole | +2.132 |
rio | +2.043 |
warm | +1.943 |
antioxid | +1.932 |
Neg logit contributions | |
eele | -3.262 |
ilda | -3.229 |
lishes | -2.949 |
ods | -2.911 |
cussion | -2.791 |
Token | () |
Token ID | 3419 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
eele | +0.800 |
ilda | +0.789 |
ods | +0.722 |
lishes | +0.715 |
zl | +0.691 |
Neg logit contributions | |
hyde | -0.652 |
Hole | -0.548 |
rio | -0.519 |
antioxid | -0.503 |
warm | -0.497 |
Token | ' |
Token ID | 6 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
hyde | +1.051 |
Hole | +0.854 |
rio | +0.809 |
antioxid | +0.781 |
warm | +0.778 |
Neg logit contributions | |
eele | -1.425 |
ilda | -1.395 |
ods | -1.283 |
lishes | -1.273 |
zl | -1.234 |
Token | x |
Token ID | 87 |
Feature activation | +9.71e-02 |
Pos logit contributions | |
hyde | +1.263 |
Hole | +1.088 |
rio | +1.029 |
antioxid | +1.005 |
warm | +0.999 |
Neg logit contributions | |
eele | -1.328 |
ilda | -1.291 |
ods | -1.176 |
lishes | -1.174 |
zl | -1.122 |
Token | . |
Token ID | 13 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
hyde | +0.657 |
Hole | +0.576 |
rio | +0.553 |
warm | +0.539 |
antioxid | +0.539 |
Neg logit contributions | |
eele | -0.495 |
ilda | -0.479 |
lishes | -0.427 |
ods | -0.427 |
zl | -0.402 |
Token | x |
Token ID | 87 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
eele | +0.312 |
ilda | +0.306 |
ods | +0.278 |
lishes | +0.271 |
zl | +0.267 |
Neg logit contributions | |
hyde | -0.320 |
Hole | -0.280 |
antioxid | -0.264 |
rio | -0.260 |
warm | -0.251 |
Token | . |
Token ID | 13 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
eele | +1.393 |
ilda | +1.374 |
ods | +1.205 |
lishes | +1.169 |
zl | +1.143 |
Neg logit contributions | |
hyde | -2.092 |
Hole | -1.850 |
antioxid | -1.778 |
rio | -1.765 |
warm | -1.717 |
Token | 89 |
Token ID | 4531 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
eele | +3.636 |
ilda | +3.526 |
lishes | +3.263 |
ods | +3.235 |
zl | +3.091 |
Neg logit contributions | |
hyde | -2.875 |
Hole | -2.428 |
rio | -2.301 |
warm | -2.237 |
antioxid | -2.190 |
Token | 12 |
Token ID | 1105 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
hyde | +2.446 |
Hole | +2.159 |
rio | +2.059 |
warm | +2.014 |
antioxid | +1.975 |
Neg logit contributions | |
eele | -2.004 |
ilda | -1.925 |
lishes | -1.755 |
ods | -1.724 |
zl | -1.632 |
Token | 09 |
Token ID | 2931 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
hyde | +4.401 |
Hole | +3.790 |
rio | +3.561 |
warm | +3.478 |
antioxid | +3.220 |
Neg logit contributions | |
eele | -5.588 |
ilda | -5.377 |
lishes | -5.040 |
ods | -4.971 |
arcity | -4.760 |
Token | 209 |
Token ID | 22567 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
hyde | +0.951 |
Hole | +0.811 |
rio | +0.775 |
warm | +0.755 |
antioxid | +0.731 |
Neg logit contributions | |
eele | -1.054 |
ilda | -1.019 |
lishes | -0.941 |
ods | -0.929 |
zl | -0.883 |
Token | x |
Token ID | 2124 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
eele | +0.278 |
ilda | +0.271 |
ods | +0.250 |
lishes | +0.247 |
zl | +0.242 |
Neg logit contributions | |
hyde | -0.199 |
Hole | -0.158 |
rio | -0.151 |
warm | -0.147 |
antioxid | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
hyde | +0.682 |
Hole | +0.598 |
rio | +0.574 |
antioxid | +0.561 |
warm | +0.560 |
Neg logit contributions | |
eele | -0.509 |
ilda | -0.493 |
lishes | -0.439 |
ods | -0.439 |
zl | -0.414 |
Token | x |
Token ID | 87 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
hyde | +1.547 |
Hole | +1.330 |
rio | +1.260 |
warm | +1.225 |
antioxid | +1.223 |
Neg logit contributions | |
eele | -1.649 |
ilda | -1.602 |
lishes | -1.462 |
ods | -1.459 |
zl | -1.392 |
Token | My |
Token ID | 2011 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
eele | +0.630 |
ilda | +0.610 |
lishes | +0.559 |
ods | +0.558 |
zl | +0.535 |
Neg logit contributions | |
hyde | -0.618 |
Hole | -0.515 |
rio | -0.501 |
warm | -0.488 |
antioxid | -0.488 |
Token | condolences |
Token ID | 38671 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
hyde | +0.394 |
Hole | +0.332 |
rio | +0.316 |
warm | +0.307 |
antioxid | +0.304 |
Neg logit contributions | |
eele | -0.443 |
ilda | -0.427 |
ods | -0.394 |
lishes | -0.392 |
zl | -0.374 |
Token | and |
Token ID | 290 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
eele | +2.374 |
ilda | +2.292 |
ods | +2.106 |
lishes | +2.079 |
zl | +2.002 |
Neg logit contributions | |
hyde | -2.084 |
Hole | -1.754 |
rio | -1.670 |
antioxid | -1.622 |
warm | -1.608 |
Token | prayers |
Token ID | 15707 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
hyde | +0.137 |
Hole | +0.115 |
rio | +0.110 |
antioxid | +0.105 |
warm | +0.104 |
Neg logit contributions | |
eele | -0.165 |
ilda | -0.160 |
ods | -0.147 |
lishes | -0.146 |
zl | -0.140 |
Token | go |
Token ID | 467 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
eele | +2.377 |
ilda | +2.298 |
ods | +2.109 |
lishes | +2.073 |
zl | +2.008 |
Neg logit contributions | |
hyde | -1.997 |
Hole | -1.666 |
rio | -1.582 |
antioxid | -1.553 |
warm | -1.520 |
Token | out |
Token ID | 503 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
eele | +3.183 |
ilda | +3.082 |
ods | +2.861 |
lishes | +2.825 |
zl | +2.738 |
Neg logit contributions | |
hyde | -2.208 |
Hole | -1.829 |
rio | -1.731 |
warm | -1.647 |
antioxid | -1.646 |
Token | to |
Token ID | 284 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
eele | +6.381 |
ilda | +6.177 |
ods | +5.591 |
lishes | +5.493 |
adle | +5.313 |
Neg logit contributions | |
hyde | -6.821 |
Hole | -5.905 |
rio | -5.661 |
antioxid | -5.473 |
warm | -5.411 |
Token | the |
Token ID | 262 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
eele | +3.219 |
ilda | +3.097 |
lishes | +2.812 |
ods | +2.800 |
zl | +2.655 |
Neg logit contributions | |
hyde | -3.743 |
Hole | -3.241 |
rio | -3.127 |
warm | -3.051 |
antioxid | -3.012 |
Token | families |
Token ID | 4172 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
eele | +2.963 |
ilda | +2.820 |
ods | +2.561 |
lishes | +2.546 |
zl | +2.454 |
Neg logit contributions | |
hyde | -3.340 |
Hole | -2.833 |
rio | -2.731 |
warm | -2.678 |
antioxid | -2.610 |
Token | of |
Token ID | 286 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
eele | +0.570 |
ilda | +0.546 |
lishes | +0.513 |
ods | +0.504 |
zl | +0.480 |
Neg logit contributions | |
hyde | -0.426 |
Hole | -0.363 |
rio | -0.346 |
warm | -0.335 |
antioxid | -0.324 |
Token | the |
Token ID | 262 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
eele | +0.573 |
ilda | +0.551 |
lishes | +0.499 |
ods | +0.494 |
zl | +0.466 |
Neg logit contributions | |
hyde | -0.705 |
Hole | -0.618 |
rio | -0.593 |
warm | -0.580 |
antioxid | -0.572 |
Token | Fight |
Token ID | 10480 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
eele | +0.409 |
ilda | +0.396 |
lishes | +0.362 |
ods | +0.359 |
zl | +0.341 |
Neg logit contributions | |
hyde | -0.410 |
Hole | -0.354 |
rio | -0.338 |
warm | -0.329 |
antioxid | -0.324 |
Token | With |
Token ID | 2080 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
eele | +0.956 |
ilda | +0.928 |
lishes | +0.850 |
ods | +0.846 |
zl | +0.801 |
Neg logit contributions | |
hyde | -0.942 |
Hole | -0.805 |
rio | -0.772 |
warm | -0.752 |
antioxid | -0.745 |
Token | Each |
Token ID | 5501 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
eele | +0.081 |
ilda | +0.078 |
lishes | +0.071 |
ods | +0.070 |
zl | +0.067 |
Neg logit contributions | |
hyde | -0.083 |
Hole | -0.073 |
rio | -0.069 |
warm | -0.067 |
antioxid | -0.066 |
Token | other |
Token ID | 847 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
eele | +0.220 |
ilda | +0.214 |
lishes | +0.195 |
ods | +0.192 |
zl | +0.186 |
Neg logit contributions | |
hyde | -0.177 |
Hole | -0.153 |
rio | -0.143 |
warm | -0.139 |
antioxid | -0.133 |
Token | 200 |
Token ID | 939 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
eele | +1.562 |
ilda | +1.508 |
lishes | +1.382 |
ods | +1.362 |
zl | +1.303 |
Neg logit contributions | |
hyde | -1.548 |
Hole | -1.352 |
rio | -1.280 |
warm | -1.252 |
antioxid | -1.225 |
Token | 80 |
Token ID | 1795 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
eele | +3.725 |
ilda | +3.579 |
lishes | +3.204 |
ods | +3.180 |
zl | +2.978 |
Neg logit contributions | |
hyde | -5.272 |
Hole | -4.666 |
rio | -4.494 |
warm | -4.392 |
antioxid | -4.342 |
Token | 205 |
Token ID | 21261 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
eele | +4.912 |
ilda | +4.691 |
ods | +4.320 |
cs | +4.087 |
NB | +4.073 |
Neg logit contributions | |
hyde | -7.328 |
rio | -6.455 |
Hole | -6.424 |
opio | -6.244 |
antioxid | -6.200 |
Token | O |
Token ID | 440 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
eele | +0.250 |
ilda | +0.247 |
ods | +0.227 |
lishes | +0.219 |
opsis | +0.213 |
Neg logit contributions | |
hyde | -0.272 |
Hole | -0.222 |
rio | -0.217 |
antioxid | -0.215 |
warm | -0.215 |
Token | & |
Token ID | 5 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
hyde | +0.335 |
Hole | +0.275 |
rio | +0.254 |
antioxid | +0.252 |
warm | +0.246 |
Neg logit contributions | |
eele | -0.505 |
ilda | -0.496 |
ods | -0.458 |
lishes | -0.452 |
zl | -0.438 |
Token | A |
Token ID | 32 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
eele | +1.469 |
ilda | +1.457 |
ods | +1.305 |
lishes | +1.266 |
NB | +1.265 |
Neg logit contributions | |
hyde | -1.899 |
Hole | -1.645 |
rio | -1.571 |
antioxid | -1.558 |
warm | -1.532 |
Token | - |
Token ID | 12 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
ilda | +2.281 |
eele | +2.277 |
ods | +2.019 |
lishes | +1.949 |
NB | +1.933 |
Neg logit contributions | |
hyde | -3.187 |
Hole | -2.714 |
antioxid | -2.691 |
rio | -2.618 |
fireplace | -2.537 |
Token | decade |
Token ID | 5707 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
eele | +1.172 |
ilda | +1.141 |
lishes | +1.059 |
ods | +1.047 |
zl | +1.005 |
Neg logit contributions | |
hyde | -1.014 |
Hole | -0.839 |
rio | -0.808 |
warm | -0.776 |
antioxid | -0.763 |
Token | following |
Token ID | 1708 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
eele | +0.373 |
ilda | +0.366 |
lishes | +0.335 |
ods | +0.333 |
zl | +0.317 |
Neg logit contributions | |
hyde | -0.341 |
Hole | -0.289 |
rio | -0.276 |
warm | -0.265 |
antioxid | -0.264 |
Token | the |
Token ID | 262 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
eele | +1.523 |
ilda | +1.476 |
lishes | +1.353 |
ods | +1.338 |
zl | +1.271 |
Neg logit contributions | |
hyde | -1.546 |
Hole | -1.329 |
rio | -1.273 |
warm | -1.239 |
antioxid | -1.222 |
Token | will |
Token ID | 481 |
Feature activation | -1.98e-03 |
Pos logit contributions | |
eele | +1.438 |
ilda | +1.403 |
lishes | +1.300 |
ods | +1.290 |
zl | +1.232 |
Neg logit contributions | |
hyde | -1.278 |
Hole | -1.058 |
rio | -1.022 |
warm | -0.987 |
antioxid | -0.976 |
Token | o |
Token ID | 267 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
eele | +0.013 |
ilda | +0.013 |
lishes | +0.012 |
ods | +0.011 |
zl | +0.011 |
Neg logit contributions | |
hyde | -0.010 |
Hole | -0.009 |
rio | -0.008 |
warm | -0.008 |
antioxid | -0.008 |
Token | ' |
Token ID | 6 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
eele | +1.135 |
ilda | +1.098 |
ods | +1.018 |
lishes | +1.015 |
opsis | +0.967 |
Neg logit contributions | |
hyde | -0.904 |
Hole | -0.763 |
rio | -0.716 |
warm | -0.703 |
antioxid | -0.689 |
Token | the |
Token ID | 262 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
eele | +6.006 |
ilda | +5.887 |
ods | +5.486 |
lishes | +5.291 |
NB | +5.159 |
Neg logit contributions | |
hyde | -5.936 |
Hole | -5.180 |
rio | -4.893 |
antioxid | -4.853 |
warm | -4.680 |
Token | w |
Token ID | 266 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
eele | +1.223 |
ilda | +1.184 |
ods | +1.094 |
lishes | +1.094 |
zl | +1.041 |
Neg logit contributions | |
hyde | -1.056 |
Hole | -0.887 |
rio | -0.848 |
warm | -0.824 |
antioxid | -0.808 |
Token | isp |
Token ID | 8802 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
eele | +0.593 |
ilda | +0.572 |
lishes | +0.520 |
ods | +0.514 |
zl | +0.487 |
Neg logit contributions | |
hyde | -0.687 |
Hole | -0.600 |
rio | -0.575 |
warm | -0.562 |
antioxid | -0.553 |
Token | of |
Token ID | 286 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
hyde | +0.296 |
Hole | +0.253 |
rio | +0.241 |
warm | +0.234 |
antioxid | +0.229 |
Neg logit contributions | |
eele | -0.341 |
ilda | -0.330 |
lishes | -0.304 |
ods | -0.301 |
zl | -0.288 |
Token | a |
Token ID | 257 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
eele | +2.153 |
ilda | +2.089 |
lishes | +1.930 |
ods | +1.916 |
zl | +1.812 |
Neg logit contributions | |
hyde | -2.021 |
Hole | -1.703 |
rio | -1.630 |
warm | -1.588 |
antioxid | -1.565 |
Token | l |
Token ID | 75 |
Feature activation | -3.87e-03 |
Pos logit contributions | |
hyde | +1.003 |
Hole | +0.873 |
rio | +0.844 |
warm | +0.819 |
antioxid | +0.783 |
Neg logit contributions | |
eele | -0.855 |
ilda | -0.825 |
lishes | -0.752 |
ods | -0.738 |
opsis | -0.709 |
Token | inson |
Token ID | 7899 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
eele | +0.019 |
ilda | +0.018 |
lishes | +0.016 |
ods | +0.016 |
zl | +0.015 |
Neg logit contributions | |
hyde | -0.027 |
Hole | -0.024 |
rio | -0.023 |
warm | -0.023 |
antioxid | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
eele | +0.348 |
ilda | +0.337 |
lishes | +0.315 |
ods | +0.307 |
zl | +0.295 |
Neg logit contributions | |
hyde | -0.295 |
Hole | -0.258 |
rio | -0.244 |
warm | -0.238 |
antioxid | -0.229 |
Token | John |
Token ID | 1757 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
eele | +0.482 |
ilda | +0.465 |
lishes | +0.421 |
ods | +0.418 |
zl | +0.394 |
Neg logit contributions | |
hyde | -0.573 |
Hole | -0.499 |
rio | -0.480 |
warm | -0.468 |
antioxid | -0.462 |
Token | O |
Token ID | 440 |
Feature activation | +9.55e-04 |
Pos logit contributions | |
hyde | +0.261 |
Hole | +0.227 |
rio | +0.217 |
warm | +0.211 |
antioxid | +0.208 |
Neg logit contributions | |
eele | -0.249 |
ilda | -0.241 |
lishes | -0.220 |
ods | -0.217 |
zl | -0.207 |
Token | ' |
Token ID | 6 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
hyde | +0.004 |
Hole | +0.003 |
rio | +0.003 |
warm | +0.003 |
antioxid | +0.003 |
Neg logit contributions | |
eele | -0.007 |
ilda | -0.007 |
lishes | -0.006 |
ods | -0.006 |
zl | -0.006 |
Token | K |
Token ID | 42 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
eele | +5.110 |
ilda | +4.970 |
ods | +4.561 |
NB | +4.428 |
lishes | +4.295 |
Neg logit contributions | |
hyde | -6.927 |
Hole | -6.072 |
rio | -5.851 |
antioxid | -5.851 |
warm | -5.709 |
Token | ane |
Token ID | 1531 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
eele | +0.869 |
ilda | +0.839 |
lishes | +0.765 |
ods | +0.758 |
zl | +0.719 |
Neg logit contributions | |
hyde | -0.927 |
Hole | -0.805 |
rio | -0.770 |
warm | -0.751 |
antioxid | -0.740 |
Token | , |
Token ID | 11 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
eele | +0.348 |
ilda | +0.337 |
lishes | +0.314 |
ods | +0.305 |
zl | +0.293 |
Neg logit contributions | |
hyde | -0.306 |
Hole | -0.262 |
rio | -0.249 |
warm | -0.245 |
antioxid | -0.236 |
Token | J |
Token ID | 449 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
eele | +0.489 |
ilda | +0.472 |
lishes | +0.427 |
ods | +0.424 |
zl | +0.400 |
Neg logit contributions | |
hyde | -0.580 |
Hole | -0.505 |
rio | -0.486 |
warm | -0.474 |
antioxid | -0.468 |
Token | ovan |
Token ID | 22590 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
hyde | +0.328 |
Hole | +0.286 |
rio | +0.274 |
warm | +0.266 |
antioxid | +0.261 |
Neg logit contributions | |
eele | -0.299 |
ilda | -0.289 |
lishes | -0.265 |
ods | -0.259 |
zl | -0.248 |
Token | With |
Token ID | 2080 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
eele | +0.832 |
ilda | +0.792 |
lishes | +0.732 |
ods | +0.718 |
opsis | +0.692 |
Neg logit contributions | |
hyde | -0.736 |
Hole | -0.652 |
rio | -0.603 |
warm | -0.589 |
antioxid | -0.570 |
Token | Dr |
Token ID | 1583 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
hyde | +0.254 |
Hole | +0.222 |
rio | +0.211 |
warm | +0.205 |
antioxid | +0.201 |
Neg logit contributions | |
eele | -0.244 |
ilda | -0.236 |
lishes | -0.216 |
ods | -0.213 |
zl | -0.202 |
Token | . |
Token ID | 13 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
eele | +0.176 |
ilda | +0.170 |
lishes | +0.154 |
ods | +0.153 |
opsis | +0.145 |
Neg logit contributions | |
hyde | -0.196 |
Hole | -0.172 |
rio | -0.164 |
warm | -0.160 |
antioxid | -0.156 |
Token | Steve |
Token ID | 6542 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
eele | +0.390 |
ilda | +0.376 |
lishes | +0.343 |
ods | +0.340 |
zl | +0.322 |
Neg logit contributions | |
hyde | -0.420 |
Hole | -0.365 |
rio | -0.349 |
warm | -0.340 |
antioxid | -0.334 |
Token | 200 |
Token ID | 939 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
eele | +0.798 |
ilda | +0.772 |
lishes | +0.706 |
ods | +0.700 |
zl | +0.668 |
Neg logit contributions | |
hyde | -0.768 |
Hole | -0.658 |
rio | -0.630 |
warm | -0.612 |
antioxid | -0.606 |
Token | 80 |
Token ID | 1795 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
eele | +3.793 |
ilda | +3.647 |
lishes | +3.252 |
ods | +3.248 |
zl | +3.029 |
Neg logit contributions | |
hyde | -5.469 |
Hole | -4.857 |
rio | -4.685 |
warm | -4.568 |
antioxid | -4.529 |
Token | 204 |
Token ID | 18638 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
eele | +5.881 |
ilda | +5.632 |
lishes | +5.132 |
ods | +5.123 |
opsis | +4.826 |
Neg logit contributions | |
hyde | -6.510 |
Hole | -5.701 |
rio | -5.419 |
warm | -5.258 |
antioxid | -5.191 |
Token | O |
Token ID | 440 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
eele | +0.141 |
ilda | +0.140 |
ods | +0.128 |
lishes | +0.124 |
opsis | +0.121 |
Neg logit contributions | |
hyde | -0.153 |
Hole | -0.126 |
rio | -0.123 |
antioxid | -0.122 |
warm | -0.122 |
Token | & |
Token ID | 5 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
hyde | +0.208 |
Hole | +0.170 |
rio | +0.158 |
antioxid | +0.157 |
warm | +0.152 |
Neg logit contributions | |
eele | -0.310 |
ilda | -0.305 |
ods | -0.282 |
lishes | -0.277 |
NB | -0.269 |
Token | A |
Token ID | 32 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
eele | +1.579 |
ilda | +1.569 |
ods | +1.402 |
NB | +1.364 |
lishes | +1.357 |
Neg logit contributions | |
hyde | -2.066 |
Hole | -1.790 |
rio | -1.711 |
antioxid | -1.699 |
warm | -1.670 |
Token | - |
Token ID | 12 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
ilda | +2.360 |
eele | +2.354 |
ods | +2.090 |
lishes | +2.017 |
NB | +2.003 |
Neg logit contributions | |
hyde | -3.298 |
Hole | -2.802 |
antioxid | -2.789 |
rio | -2.712 |
fireplace | -2.627 |
Token | or |
Token ID | 393 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
eele | +0.146 |
ilda | +0.142 |
lishes | +0.132 |
ods | +0.131 |
opsis | +0.125 |
Neg logit contributions | |
hyde | -0.105 |
Hole | -0.087 |
rio | -0.082 |
warm | -0.080 |
antioxid | -0.078 |
Token | call |
Token ID | 869 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
hyde | +1.757 |
Hole | +1.470 |
rio | +1.386 |
warm | +1.339 |
antioxid | +1.311 |
Neg logit contributions | |
eele | -2.506 |
ilda | -2.436 |
lishes | -2.265 |
ods | -2.243 |
zl | -2.156 |
Token | 03 |
Token ID | 7643 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
hyde | +0.867 |
Hole | +0.743 |
rio | +0.712 |
warm | +0.707 |
antioxid | +0.691 |
Neg logit contributions | |
eele | -0.834 |
ilda | -0.814 |
ods | -0.750 |
lishes | -0.724 |
adle | -0.697 |
Token | 30 |
Token ID | 1270 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
eele | +1.975 |
ilda | +1.849 |
NB | +1.651 |
ods | +1.646 |
lishes | +1.629 |
Neg logit contributions | |
hyde | -2.316 |
Hole | -1.947 |
antioxid | -1.873 |
rio | -1.850 |
warm | -1.841 |
Token | 333 |
Token ID | 23460 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
eele | +1.435 |
ilda | +1.381 |
lishes | +1.246 |
ods | +1.238 |
NB | +1.162 |
Neg logit contributions | |
hyde | -1.754 |
Hole | -1.527 |
rio | -1.464 |
warm | -1.435 |
antioxid | -1.416 |
Token | 68 |
Token ID | 8257 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
eele | +3.053 |
ilda | +3.010 |
ods | +2.560 |
NB | +2.511 |
cs | +2.438 |
Neg logit contributions | |
hyde | -4.693 |
Hole | -3.957 |
warm | -3.935 |
antioxid | -3.888 |
rio | -3.794 |
Token | 46 |
Token ID | 3510 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
eele | +6.508 |
ilda | +6.352 |
lishes | +5.751 |
ods | +5.727 |
NB | +5.640 |
Neg logit contributions | |
hyde | -5.612 |
Hole | -4.568 |
antioxid | -4.384 |
rio | -4.329 |
warm | -4.201 |
Token | . |
Token ID | 13 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
eele | +4.341 |
ilda | +4.203 |
lishes | +3.568 |
ods | +3.545 |
NB | +3.480 |
Neg logit contributions | |
hyde | -6.619 |
Hole | -5.789 |
rio | -5.580 |
antioxid | -5.541 |
warm | -5.489 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
eele | +3.606 |
ilda | +3.506 |
lishes | +3.103 |
ods | +3.077 |
NB | +3.017 |
Neg logit contributions | |
hyde | -4.218 |
Hole | -3.463 |
warm | -3.403 |
rio | -3.382 |
antioxid | -3.354 |
Token | ( |
Token ID | 7 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
hyde | +0.076 |
Hole | +0.065 |
rio | +0.063 |
warm | +0.061 |
antioxid | +0.059 |
Neg logit contributions | |
eele | -0.080 |
ilda | -0.077 |
lishes | -0.071 |
ods | -0.070 |
zl | -0.067 |
Token | FIL |
Token ID | 46700 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
hyde | +3.257 |
Hole | +2.832 |
rio | +2.724 |
warm | +2.651 |
antioxid | +2.551 |
Neg logit contributions | |
eele | -3.344 |
ilda | -3.225 |
lishes | -2.956 |
ods | -2.915 |
opsis | -2.784 |
Token | - |
Token ID | 12 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
eele | +0.754 |
ilda | +0.731 |
lishes | +0.669 |
ods | +0.655 |
zl | +0.633 |
Neg logit contributions | |
hyde | -0.698 |
Hole | -0.612 |
rio | -0.576 |
warm | -0.563 |
antioxid | -0.549 |
Token | Car |
Token ID | 9914 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
hyde | +0.078 |
Hole | +0.068 |
rio | +0.065 |
warm | +0.063 |
antioxid | +0.062 |
Neg logit contributions | |
eele | -0.077 |
ilda | -0.075 |
lishes | -0.068 |
ods | -0.068 |
zl | -0.064 |
Token | Crash |
Token ID | 23653 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
eele | +0.433 |
ilda | +0.418 |
lishes | +0.383 |
ods | +0.380 |
zl | +0.361 |
Neg logit contributions | |
hyde | -0.427 |
Hole | -0.369 |
rio | -0.352 |
warm | -0.343 |
antioxid | -0.337 |
Token | Comedy |
Token ID | 22329 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
eele | +0.082 |
ilda | +0.078 |
lishes | +0.072 |
ods | +0.071 |
zl | +0.069 |
Neg logit contributions | |
hyde | -0.072 |
Hole | -0.063 |
rio | -0.059 |
warm | -0.057 |
antioxid | -0.056 |
Token | 200 |
Token ID | 939 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
hyde | +1.194 |
Hole | +1.067 |
rio | +0.999 |
warm | +0.964 |
antioxid | +0.930 |
Neg logit contributions | |
eele | -1.351 |
ilda | -1.293 |
lishes | -1.191 |
ods | -1.161 |
zl | -1.130 |
Token | 80 |
Token ID | 1795 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
eele | +2.927 |
ilda | +2.874 |
ods | +2.530 |
lishes | +2.400 |
zl | +2.292 |
Neg logit contributions | |
hyde | -5.277 |
Hole | -4.775 |
rio | -4.657 |
antioxid | -4.600 |
warm | -4.469 |
Token | 206 |
Token ID | 22136 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
eele | +3.990 |
ilda | +3.713 |
ods | +3.158 |
cs | +3.033 |
lishes | +2.991 |
Neg logit contributions | |
hyde | -7.649 |
rio | -6.812 |
Hole | -6.759 |
antioxid | -6.665 |
warm | -6.561 |
Token | O |
Token ID | 440 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
eele | +0.872 |
ilda | +0.867 |
ods | +0.795 |
lishes | +0.761 |
NB | +0.748 |
Neg logit contributions | |
hyde | -0.994 |
Hole | -0.811 |
rio | -0.796 |
antioxid | -0.793 |
warm | -0.786 |
Token | & |
Token ID | 5 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
hyde | +0.702 |
Hole | +0.574 |
rio | +0.533 |
antioxid | +0.523 |
warm | +0.515 |
Neg logit contributions | |
eele | -1.082 |
ilda | -1.060 |
ods | -0.980 |
lishes | -0.971 |
zl | -0.939 |
Token | A |
Token ID | 32 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
eele | +1.166 |
ilda | +1.153 |
ods | +1.034 |
lishes | +1.008 |
NB | +0.999 |
Neg logit contributions | |
hyde | -1.477 |
Hole | -1.278 |
rio | -1.221 |
antioxid | -1.207 |
warm | -1.192 |
Token | - |
Token ID | 12 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
eele | +2.003 |
ilda | +2.000 |
ods | +1.773 |
lishes | +1.719 |
NB | +1.694 |
Neg logit contributions | |
hyde | -2.739 |
Hole | -2.337 |
antioxid | -2.307 |
rio | -2.252 |
warm | -2.178 |
Token | Pictures |
Token ID | 20051 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
eele | +0.863 |
ilda | +0.836 |
lishes | +0.767 |
ods | +0.766 |
zl | +0.724 |
Neg logit contributions | |
hyde | -0.972 |
Hole | -0.859 |
rio | -0.817 |
warm | -0.786 |
antioxid | -0.773 |
Token | and |
Token ID | 290 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
eele | +1.565 |
ilda | +1.512 |
ods | +1.366 |
lishes | +1.366 |
zl | +1.310 |
Neg logit contributions | |
hyde | -1.528 |
Hole | -1.293 |
rio | -1.257 |
warm | -1.225 |
antioxid | -1.222 |
Token | 20 |
Token ID | 1160 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
hyde | +4.259 |
Hole | +3.784 |
rio | +3.524 |
warm | +3.449 |
antioxid | +3.362 |
Neg logit contributions | |
eele | -4.527 |
ilda | -4.369 |
lishes | -4.084 |
ods | -4.031 |
opsis | -3.843 |
Token | th |
Token ID | 400 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
hyde | +2.531 |
Hole | +2.226 |
rio | +2.128 |
warm | +2.051 |
antioxid | +2.014 |
Neg logit contributions | |
eele | -2.407 |
ilda | -2.307 |
lishes | -2.157 |
ods | -2.086 |
opsis | -2.013 |
Token | Century |
Token ID | 13641 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
eele | +1.290 |
ilda | +1.240 |
lishes | +1.097 |
ods | +1.095 |
zl | +1.028 |
Neg logit contributions | |
hyde | -1.827 |
Hole | -1.590 |
rio | -1.557 |
warm | -1.514 |
antioxid | -1.501 |
Token | Fox |
Token ID | 5426 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
eele | +2.628 |
ilda | +2.566 |
lishes | +2.380 |
ods | +2.374 |
zl | +2.281 |
Neg logit contributions | |
hyde | -1.673 |
Hole | -1.370 |
rio | -1.300 |
warm | -1.252 |
antioxid | -1.222 |
Token |
|
Token ID | 198 |
Feature activation | -9.62e-03 |
Pos logit contributions | |
eele | +5.847 |
ilda | +5.613 |
ods | +5.006 |
lishes | +4.966 |
zl | +4.777 |
Neg logit contributions | |
hyde | -5.737 |
Hole | -4.829 |
rio | -4.828 |
antioxid | -4.747 |
warm | -4.660 |
Token |
|
Token ID | 198 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
eele | +0.053 |
ilda | +0.052 |
ods | +0.047 |
lishes | +0.047 |
zl | +0.045 |
Neg logit contributions | |
hyde | -0.061 |
Hole | -0.052 |
rio | -0.050 |
antioxid | -0.049 |
warm | -0.048 |
Token | NOT |
Token ID | 11929 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
hyde | +0.446 |
Hole | +0.384 |
rio | +0.367 |
warm | +0.357 |
antioxid | +0.352 |
Neg logit contributions | |
eele | -0.460 |
ilda | -0.445 |
lishes | -0.408 |
ods | -0.404 |
zl | -0.385 |
Token | ICE |
Token ID | 8476 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
eele | +2.158 |
ilda | +2.083 |
lishes | +1.866 |
ods | +1.860 |
zl | +1.750 |
Neg logit contributions | |
hyde | -2.684 |
Hole | -2.339 |
rio | -2.247 |
warm | -2.195 |
antioxid | -2.182 |
Token | : |
Token ID | 25 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
eele | +1.571 |
ilda | +1.517 |
lishes | +1.373 |
ods | +1.362 |
zl | +1.287 |
Neg logit contributions | |
hyde | -1.797 |
Hole | -1.557 |
rio | -1.502 |
warm | -1.463 |
antioxid | -1.447 |
Token | . |
Token ID | 13 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
eele | +0.254 |
ilda | +0.246 |
ods | +0.218 |
lishes | +0.218 |
zl | +0.206 |
Neg logit contributions | |
hyde | -0.353 |
Hole | -0.309 |
rio | -0.297 |
antioxid | -0.292 |
warm | -0.289 |
Token | get |
Token ID | 1136 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
eele | +2.577 |
ilda | +2.512 |
ods | +2.234 |
lishes | +2.189 |
cs | +2.163 |
Neg logit contributions | |
hyde | -3.165 |
Hole | -2.799 |
antioxid | -2.661 |
rio | -2.613 |
fireplace | -2.554 |
Token | Struct |
Token ID | 44909 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
eele | +1.772 |
ilda | +1.740 |
ods | +1.556 |
lishes | +1.546 |
NB | +1.510 |
Neg logit contributions | |
hyde | -2.436 |
Hole | -2.132 |
rio | -2.038 |
warm | -1.997 |
antioxid | -1.996 |
Token | uring |
Token ID | 870 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
hyde | +0.751 |
Hole | +0.647 |
rio | +0.610 |
warm | +0.596 |
antioxid | +0.589 |
Neg logit contributions | |
eele | -0.812 |
ilda | -0.793 |
lishes | -0.724 |
ods | -0.718 |
zl | -0.689 |
Token | Element |
Token ID | 20180 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
eele | +1.161 |
ilda | +1.135 |
ods | +0.925 |
lishes | +0.922 |
NB | +0.894 |
Neg logit contributions | |
hyde | -2.357 |
Hole | -2.094 |
rio | -2.076 |
warm | -2.028 |
antioxid | -2.012 |
Token | ( |
Token ID | 7 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
eele | +1.504 |
ilda | +1.475 |
ods | +1.335 |
lishes | +1.298 |
NB | +1.278 |
Neg logit contributions | |
hyde | -1.601 |
Hole | -1.378 |
rio | -1.325 |
antioxid | -1.313 |
warm | -1.264 |
Token | cv |
Token ID | 33967 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
eele | +2.168 |
ilda | +1.958 |
ods | +1.637 |
cs | +1.572 |
zl | +1.411 |
Neg logit contributions | |
hyde | -9.532 |
Hole | -8.882 |
antioxid | -8.482 |
rio | -8.338 |
fireplace | -8.281 |
Token | 2 |
Token ID | 17 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
eele | +1.579 |
ilda | +1.544 |
ods | +1.405 |
lishes | +1.381 |
zl | +1.334 |
Neg logit contributions | |
hyde | -1.536 |
Hole | -1.315 |
rio | -1.247 |
antioxid | -1.244 |
warm | -1.201 |
Token | . |
Token ID | 13 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
eele | +0.463 |
ilda | +0.448 |
ods | +0.398 |
lishes | +0.396 |
zl | +0.375 |
Neg logit contributions | |
hyde | -0.640 |
Hole | -0.560 |
rio | -0.539 |
antioxid | -0.529 |
warm | -0.525 |
Token | M |
Token ID | 44 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
eele | +2.338 |
ilda | +2.322 |
ods | +1.950 |
NB | +1.932 |
lishes | +1.885 |
Neg logit contributions | |
hyde | -4.460 |
Hole | -3.962 |
rio | -3.840 |
antioxid | -3.820 |
warm | -3.718 |
Token | OR |
Token ID | 1581 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
eele | +0.627 |
ilda | +0.613 |
ods | +0.560 |
NB | +0.543 |
lishes | +0.539 |
Neg logit contributions | |
hyde | -0.518 |
Hole | -0.442 |
rio | -0.411 |
warm | -0.403 |
antioxid | -0.400 |
Token | by |
Token ID | 416 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
eele | +1.112 |
ilda | +1.074 |
lishes | +0.990 |
ods | +0.979 |
opsis | +0.932 |
Neg logit contributions | |
hyde | -1.007 |
Hole | -0.864 |
rio | -0.822 |
warm | -0.799 |
antioxid | -0.787 |
Token | an |
Token ID | 281 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
eele | +1.070 |
ilda | +1.032 |
lishes | +0.954 |
ods | +0.937 |
zl | +0.892 |
Neg logit contributions | |
hyde | -1.022 |
Hole | -0.867 |
rio | -0.834 |
warm | -0.808 |
antioxid | -0.793 |
Token | accused |
Token ID | 5371 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
hyde | +0.219 |
Hole | +0.189 |
rio | +0.179 |
warm | +0.174 |
antioxid | +0.171 |
Neg logit contributions | |
eele | -0.244 |
ilda | -0.235 |
lishes | -0.217 |
ods | -0.215 |
zl | -0.203 |
Token | student |
Token ID | 3710 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
hyde | +1.007 |
Hole | +0.858 |
rio | +0.816 |
warm | +0.793 |
antioxid | +0.780 |
Neg logit contributions | |
eele | -1.168 |
ilda | -1.132 |
lishes | -1.043 |
ods | -1.034 |
zl | -0.988 |
Token | , |
Token ID | 11 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
hyde | +1.445 |
Hole | +1.239 |
rio | +1.184 |
warm | +1.152 |
antioxid | +1.131 |
Neg logit contributions | |
eele | -1.539 |
ilda | -1.489 |
lishes | -1.367 |
ods | -1.357 |
zl | -1.293 |
Token | but |
Token ID | 475 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
eele | +2.095 |
ilda | +2.017 |
lishes | +1.864 |
ods | +1.839 |
adle | +1.751 |
Neg logit contributions | |
hyde | -2.038 |
Hole | -1.748 |
rio | -1.679 |
warm | -1.626 |
antioxid | -1.607 |
Token | because |
Token ID | 780 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
eele | +5.148 |
ilda | +4.999 |
ods | +4.547 |
lishes | +4.543 |
adle | +4.284 |
Neg logit contributions | |
hyde | -5.958 |
Hole | -5.101 |
rio | -4.907 |
warm | -4.810 |
antioxid | -4.736 |
Token | it |
Token ID | 340 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
eele | +2.340 |
ilda | +2.269 |
lishes | +2.071 |
ods | +2.034 |
zl | +1.942 |
Neg logit contributions | |
hyde | -2.471 |
Hole | -2.115 |
rio | -2.014 |
warm | -1.988 |
antioxid | -1.940 |
Token | allows |
Token ID | 3578 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
eele | +0.477 |
ilda | +0.463 |
lishes | +0.428 |
ods | +0.422 |
zl | +0.401 |
Neg logit contributions | |
hyde | -0.450 |
Hole | -0.382 |
rio | -0.366 |
warm | -0.356 |
antioxid | -0.353 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
eele | +0.565 |
ilda | +0.545 |
lishes | +0.499 |
ods | +0.493 |
zl | +0.469 |
Neg logit contributions | |
hyde | -0.591 |
Hole | -0.509 |
rio | -0.487 |
warm | -0.477 |
antioxid | -0.469 |
Token | school |
Token ID | 1524 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
eele | +0.897 |
ilda | +0.857 |
lishes | +0.774 |
ods | +0.765 |
zl | +0.721 |
Neg logit contributions | |
hyde | -1.103 |
Hole | -0.955 |
rio | -0.921 |
warm | -0.907 |
antioxid | -0.888 |
Token | according |
Token ID | 1864 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
hyde | +0.031 |
Hole | +0.026 |
rio | +0.025 |
warm | +0.025 |
antioxid | +0.024 |
Neg logit contributions | |
eele | -0.032 |
ilda | -0.031 |
lishes | -0.028 |
ods | -0.028 |
zl | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
hyde | +0.542 |
Hole | +0.462 |
rio | +0.444 |
warm | +0.431 |
antioxid | +0.428 |
Neg logit contributions | |
eele | -0.540 |
ilda | -0.522 |
lishes | -0.474 |
ods | -0.474 |
zl | -0.451 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
eele | +0.185 |
ilda | +0.179 |
lishes | +0.164 |
ods | +0.162 |
zl | +0.155 |
Neg logit contributions | |
hyde | -0.179 |
Hole | -0.157 |
rio | -0.148 |
warm | -0.144 |
antioxid | -0.142 |
Token | University |
Token ID | 2059 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
eele | +0.097 |
ilda | +0.094 |
lishes | +0.086 |
ods | +0.085 |
zl | +0.082 |
Neg logit contributions | |
hyde | -0.087 |
Hole | -0.074 |
rio | -0.070 |
warm | -0.068 |
antioxid | -0.067 |
Token | of |
Token ID | 286 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
eele | +0.207 |
ilda | +0.202 |
lishes | +0.186 |
ods | +0.185 |
zl | +0.176 |
Neg logit contributions | |
hyde | -0.168 |
Hole | -0.145 |
rio | -0.136 |
warm | -0.132 |
antioxid | -0.130 |
Token | Hawai |
Token ID | 10847 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
eele | +0.369 |
ilda | +0.357 |
lishes | +0.324 |
ods | +0.322 |
zl | +0.304 |
Neg logit contributions | |
hyde | -0.412 |
Hole | -0.355 |
rio | -0.342 |
warm | -0.334 |
antioxid | -0.330 |
Token | � |
Token ID | 447 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
ilda | +4.628 |
eele | +4.514 |
ods | +4.112 |
lishes | +4.073 |
zl | +3.885 |
Neg logit contributions | |
hyde | -6.320 |
Hole | -5.497 |
warm | -5.219 |
rio | -5.217 |
antioxid | -5.153 |
Token | � |
Token ID | 247 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
eele | +2.589 |
ilda | +2.514 |
lishes | +2.337 |
ods | +2.317 |
zl | +2.224 |
Neg logit contributions | |
hyde | -1.808 |
Hole | -1.508 |
rio | -1.426 |
warm | -1.374 |
antioxid | -1.348 |
Token | i |
Token ID | 72 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
eele | +1.774 |
ilda | +1.712 |
lishes | +1.562 |
ods | +1.546 |
zl | +1.463 |
Neg logit contributions | |
hyde | -1.963 |
Hole | -1.706 |
rio | -1.631 |
warm | -1.596 |
antioxid | -1.574 |
Token | , |
Token ID | 11 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
eele | +2.248 |
ilda | +2.174 |
lishes | +1.992 |
ods | +1.974 |
zl | +1.878 |
Neg logit contributions | |
hyde | -2.179 |
Hole | -1.868 |
rio | -1.790 |
warm | -1.743 |
antioxid | -1.715 |
Token | there |
Token ID | 612 |
Feature activation | -1.54e-04 |
Pos logit contributions | |
eele | +0.257 |
ilda | +0.249 |
lishes | +0.228 |
ods | +0.226 |
zl | +0.215 |
Neg logit contributions | |
hyde | -0.250 |
Hole | -0.214 |
rio | -0.205 |
warm | -0.199 |
antioxid | -0.197 |
Token | was |
Token ID | 373 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
eele | +2.312 |
ilda | +2.312 |
ods | +2.104 |
lishes | +2.073 |
opsis | +1.993 |
Neg logit contributions | |
hyde | -2.206 |
Hole | -1.883 |
antioxid | -1.804 |
rio | -1.768 |
warm | -1.729 |
Token | the |
Token ID | 262 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
eele | +0.456 |
ilda | +0.445 |
lishes | +0.406 |
ods | +0.405 |
zl | +0.386 |
Neg logit contributions | |
hyde | -0.433 |
Hole | -0.372 |
rio | -0.353 |
warm | -0.344 |
antioxid | -0.341 |
Token | commander |
Token ID | 11561 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
eele | +0.523 |
ilda | +0.512 |
ods | +0.474 |
lishes | +0.468 |
zl | +0.449 |
Neg logit contributions | |
hyde | -0.410 |
Hole | -0.341 |
rio | -0.325 |
warm | -0.314 |
antioxid | -0.313 |
Token | - |
Token ID | 12 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
eele | +0.197 |
ilda | +0.189 |
lishes | +0.177 |
ods | +0.171 |
zl | +0.165 |
Neg logit contributions | |
hyde | -0.164 |
Hole | -0.139 |
rio | -0.134 |
warm | -0.132 |
antioxid | -0.125 |
Token | in |
Token ID | 259 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
eele | +1.868 |
ilda | +1.826 |
ods | +1.669 |
lishes | +1.650 |
zl | +1.580 |
Neg logit contributions | |
hyde | -1.741 |
Hole | -1.520 |
rio | -1.416 |
antioxid | -1.397 |
warm | -1.372 |
Token | - |
Token ID | 12 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
eele | +1.519 |
ilda | +1.493 |
ods | +1.318 |
lishes | +1.299 |
zl | +1.249 |
Neg logit contributions | |
hyde | -1.934 |
Hole | -1.718 |
antioxid | -1.619 |
rio | -1.614 |
warm | -1.539 |
Token | chief |
Token ID | 17351 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
eele | +3.258 |
ilda | +3.234 |
ods | +2.606 |
adle | +2.520 |
cs | +2.499 |
Neg logit contributions | |
hyde | -7.311 |
antioxid | -6.906 |
Hole | -6.891 |
contrace | -6.513 |
rio | -6.374 |
Token | of |
Token ID | 286 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
hyde | +0.235 |
Hole | +0.201 |
rio | +0.191 |
warm | +0.186 |
antioxid | +0.183 |
Neg logit contributions | |
eele | -0.267 |
ilda | -0.259 |
lishes | -0.238 |
ods | -0.236 |
zl | -0.225 |
Token | the |
Token ID | 262 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
eele | +0.261 |
ilda | +0.253 |
lishes | +0.231 |
ods | +0.228 |
zl | +0.219 |
Neg logit contributions | |
hyde | -0.264 |
Hole | -0.229 |
rio | -0.218 |
warm | -0.212 |
antioxid | -0.208 |
Token | United |
Token ID | 1578 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
eele | +0.637 |
ilda | +0.619 |
lishes | +0.573 |
ods | +0.569 |
zl | +0.543 |
Neg logit contributions | |
hyde | -0.476 |
Hole | -0.398 |
rio | -0.377 |
warm | -0.366 |
antioxid | -0.359 |
Token | States |
Token ID | 1829 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
eele | +1.058 |
ilda | +1.041 |
ods | +0.942 |
lishes | +0.937 |
opsis | +0.883 |
Neg logit contributions | |
hyde | -1.193 |
Hole | -0.999 |
rio | -0.969 |
antioxid | -0.956 |
warm | -0.954 |
Token | fades |
Token ID | 41381 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
eele | +0.811 |
ilda | +0.788 |
lishes | +0.721 |
ods | +0.720 |
zl | +0.688 |
Neg logit contributions | |
hyde | -0.700 |
Hole | -0.594 |
rio | -0.570 |
warm | -0.553 |
antioxid | -0.545 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
eele | +0.413 |
ilda | +0.400 |
lishes | +0.366 |
ods | +0.362 |
zl | +0.344 |
Neg logit contributions | |
hyde | -0.422 |
Hole | -0.364 |
rio | -0.348 |
warm | -0.339 |
antioxid | -0.335 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
eele | +0.148 |
ilda | +0.143 |
lishes | +0.131 |
ods | +0.130 |
zl | +0.125 |
Neg logit contributions | |
hyde | -0.134 |
Hole | -0.111 |
rio | -0.108 |
warm | -0.106 |
antioxid | -0.105 |
Token |
|
Token ID | 198 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
eele | +0.098 |
ilda | +0.095 |
ods | +0.086 |
lishes | +0.085 |
zl | +0.081 |
Neg logit contributions | |
hyde | -0.109 |
Hole | -0.094 |
rio | -0.090 |
antioxid | -0.089 |
warm | -0.087 |
Token | R |
Token ID | 49 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
hyde | +0.098 |
Hole | +0.084 |
rio | +0.081 |
warm | +0.078 |
antioxid | +0.076 |
Neg logit contributions | |
eele | -0.115 |
ilda | -0.111 |
lishes | -0.103 |
ods | -0.101 |
opsis | -0.097 |
Token | ANK |
Token ID | 15154 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
hyde | +0.457 |
Hole | +0.392 |
rio | +0.371 |
warm | +0.362 |
antioxid | +0.360 |
Neg logit contributions | |
eele | -0.502 |
ilda | -0.486 |
ods | -0.445 |
lishes | -0.441 |
NB | -0.421 |
Token | 5 |
Token ID | 642 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ilda | +4.827 |
eele | +4.777 |
ods | +4.263 |
NB | +4.249 |
lishes | +4.221 |
Neg logit contributions | |
hyde | -6.119 |
rio | -4.908 |
antioxid | -4.874 |
Hole | -4.847 |
warm | -4.808 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
eele | +1.694 |
ilda | +1.643 |
lishes | +1.472 |
ods | +1.469 |
zl | +1.384 |
Neg logit contributions | |
hyde | -2.141 |
Hole | -1.835 |
rio | -1.794 |
warm | -1.753 |
antioxid | -1.738 |
Token | Smith |
Token ID | 4176 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
eele | +1.779 |
ilda | +1.749 |
lishes | +1.591 |
ods | +1.571 |
zl | +1.486 |
Neg logit contributions | |
hyde | -2.051 |
Hole | -1.732 |
antioxid | -1.665 |
rio | -1.662 |
warm | -1.640 |
Token | , |
Token ID | 11 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
eele | +0.336 |
ilda | +0.325 |
ods | +0.293 |
lishes | +0.287 |
zl | +0.275 |
Neg logit contributions | |
hyde | -0.402 |
Hole | -0.343 |
rio | -0.331 |
antioxid | -0.326 |
warm | -0.323 |
Token | Ravens |
Token ID | 20091 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
eele | +1.106 |
ilda | +1.064 |
lishes | +0.932 |
ods | +0.930 |
zl | +0.865 |
Neg logit contributions | |
hyde | -1.855 |
Hole | -1.632 |
rio | -1.586 |
warm | -1.556 |
antioxid | -1.547 |
Token | call |
Token ID | 869 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
hyde | +1.757 |
Hole | +1.470 |
rio | +1.386 |
warm | +1.339 |
antioxid | +1.311 |
Neg logit contributions | |
eele | -2.506 |
ilda | -2.436 |
lishes | -2.265 |
ods | -2.243 |
zl | -2.156 |
Token | 03 |
Token ID | 7643 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
hyde | +0.867 |
Hole | +0.743 |
rio | +0.712 |
warm | +0.707 |
antioxid | +0.691 |
Neg logit contributions | |
eele | -0.834 |
ilda | -0.814 |
ods | -0.750 |
lishes | -0.724 |
adle | -0.697 |
Token | 30 |
Token ID | 1270 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
eele | +1.975 |
ilda | +1.849 |
NB | +1.651 |
ods | +1.646 |
lishes | +1.629 |
Neg logit contributions | |
hyde | -2.316 |
Hole | -1.947 |
antioxid | -1.873 |
rio | -1.850 |
warm | -1.841 |
Token | 333 |
Token ID | 23460 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
eele | +1.435 |
ilda | +1.381 |
lishes | +1.246 |
ods | +1.238 |
NB | +1.162 |
Neg logit contributions | |
hyde | -1.754 |
Hole | -1.527 |
rio | -1.464 |
warm | -1.435 |
antioxid | -1.416 |
Token | 68 |
Token ID | 8257 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
eele | +3.053 |
ilda | +3.010 |
ods | +2.560 |
NB | +2.511 |
cs | +2.438 |
Neg logit contributions | |
hyde | -4.693 |
Hole | -3.957 |
warm | -3.935 |
antioxid | -3.888 |
rio | -3.794 |
Token | 46 |
Token ID | 3510 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
eele | +6.508 |
ilda | +6.352 |
lishes | +5.751 |
ods | +5.727 |
NB | +5.640 |
Neg logit contributions | |
hyde | -5.612 |
Hole | -4.568 |
antioxid | -4.384 |
rio | -4.329 |
warm | -4.201 |
Token | . |
Token ID | 13 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
eele | +4.341 |
ilda | +4.203 |
lishes | +3.568 |
ods | +3.545 |
NB | +3.480 |
Neg logit contributions | |
hyde | -6.619 |
Hole | -5.789 |
rio | -5.580 |
antioxid | -5.541 |
warm | -5.489 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
eele | +3.606 |
ilda | +3.506 |
lishes | +3.103 |
ods | +3.077 |
NB | +3.017 |
Neg logit contributions | |
hyde | -4.218 |
Hole | -3.463 |
warm | -3.403 |
rio | -3.382 |
antioxid | -3.354 |
Token | ( |
Token ID | 7 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
hyde | +0.076 |
Hole | +0.065 |
rio | +0.063 |
warm | +0.061 |
antioxid | +0.059 |
Neg logit contributions | |
eele | -0.080 |
ilda | -0.077 |
lishes | -0.071 |
ods | -0.070 |
zl | -0.067 |
Token | FIL |
Token ID | 46700 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
hyde | +3.257 |
Hole | +2.832 |
rio | +2.724 |
warm | +2.651 |
antioxid | +2.551 |
Neg logit contributions | |
eele | -3.344 |
ilda | -3.225 |
lishes | -2.956 |
ods | -2.915 |
opsis | -2.784 |
Token | ES |
Token ID | 1546 |
Feature activation | -9.95e-03 |
Pos logit contributions | |
eele | +1.720 |
ilda | +1.660 |
lishes | +1.508 |
ods | +1.496 |
opsis | +1.418 |
Neg logit contributions | |
hyde | -2.004 |
Hole | -1.732 |
rio | -1.666 |
warm | -1.632 |
antioxid | -1.610 |
Token | awaits |
Token ID | 37180 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
hyde | +0.342 |
Hole | +0.293 |
rio | +0.279 |
warm | +0.271 |
antioxid | +0.267 |
Neg logit contributions | |
eele | -0.371 |
ilda | -0.359 |
lishes | -0.330 |
ods | -0.327 |
zl | -0.312 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
hyde | +1.731 |
Hole | +1.504 |
rio | +1.422 |
warm | +1.391 |
antioxid | +1.367 |
Neg logit contributions | |
eele | -1.844 |
ilda | -1.778 |
lishes | -1.637 |
ods | -1.625 |
opsis | -1.545 |
Token |
|
Token ID | 198 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
eele | +0.162 |
ilda | +0.157 |
lishes | +0.144 |
ods | +0.143 |
zl | +0.136 |
Neg logit contributions | |
hyde | -0.161 |
Hole | -0.138 |
rio | -0.132 |
warm | -0.129 |
antioxid | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
eele | +0.401 |
ilda | +0.392 |
ods | +0.353 |
lishes | +0.351 |
zl | +0.334 |
Neg logit contributions | |
hyde | -0.456 |
Hole | -0.393 |
rio | -0.375 |
antioxid | -0.371 |
warm | -0.363 |
Token | R |
Token ID | 49 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
hyde | +0.110 |
Hole | +0.093 |
rio | +0.091 |
warm | +0.088 |
antioxid | +0.083 |
Neg logit contributions | |
eele | -0.145 |
ilda | -0.139 |
lishes | -0.130 |
ods | -0.128 |
opsis | -0.123 |
Token | ANK |
Token ID | 15154 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
hyde | +0.309 |
Hole | +0.264 |
rio | +0.251 |
warm | +0.243 |
antioxid | +0.243 |
Neg logit contributions | |
eele | -0.341 |
ilda | -0.331 |
ods | -0.302 |
lishes | -0.301 |
NB | -0.287 |
Token | 6 |
Token ID | 718 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ilda | +4.601 |
eele | +4.600 |
ods | +4.090 |
NB | +4.016 |
lishes | +4.009 |
Neg logit contributions | |
hyde | -6.188 |
antioxid | -5.031 |
rio | -4.997 |
warm | -4.989 |
Hole | -4.973 |
Token | Jal |
Token ID | 28649 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
eele | +1.209 |
ilda | +1.168 |
lishes | +1.053 |
ods | +1.045 |
zl | +0.987 |
Neg logit contributions | |
hyde | -1.498 |
Hole | -1.298 |
rio | -1.257 |
warm | -1.228 |
antioxid | -1.215 |
Token | en |
Token ID | 268 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
hyde | +1.808 |
Hole | +1.570 |
rio | +1.499 |
warm | +1.456 |
antioxid | +1.428 |
Neg logit contributions | |
eele | -1.767 |
ilda | -1.702 |
lishes | -1.559 |
ods | -1.544 |
zl | -1.472 |
Token | Ramsey |
Token ID | 30552 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
hyde | +0.972 |
Hole | +0.824 |
rio | +0.787 |
warm | +0.763 |
antioxid | +0.751 |
Neg logit contributions | |
eele | -1.138 |
ilda | -1.107 |
lishes | -1.016 |
ods | -1.009 |
zl | -0.962 |
Token | , |
Token ID | 11 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
hyde | +1.460 |
Hole | +1.262 |
rio | +1.210 |
warm | +1.178 |
antioxid | +1.172 |
Neg logit contributions | |
eele | -1.306 |
ilda | -1.263 |
ods | -1.141 |
lishes | -1.141 |
zl | -1.080 |
Token | ) |
Token ID | 8 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
hyde | +0.238 |
Hole | +0.207 |
rio | +0.198 |
antioxid | +0.196 |
warm | +0.192 |
Neg logit contributions | |
eele | -0.198 |
ilda | -0.192 |
ods | -0.173 |
lishes | -0.171 |
zl | -0.163 |
Token |
|
Token ID | 198 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
eele | +1.481 |
ilda | +1.428 |
lishes | +1.316 |
ods | +1.297 |
zl | +1.242 |
Neg logit contributions | |
hyde | -1.344 |
Hole | -1.172 |
rio | -1.100 |
warm | -1.079 |
antioxid | -1.050 |
Token |
|
Token ID | 198 |
Feature activation | +5.97e-03 |
Pos logit contributions | |
eele | +1.032 |
ilda | +1.014 |
ods | +0.912 |
lishes | +0.893 |
zl | +0.858 |
Neg logit contributions | |
hyde | -1.265 |
Hole | -1.088 |
antioxid | -1.049 |
rio | -1.039 |
warm | -1.001 |
Token | 13 |
Token ID | 1485 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
hyde | +0.024 |
Hole | +0.019 |
rio | +0.018 |
warm | +0.018 |
antioxid | +0.017 |
Neg logit contributions | |
eele | -0.047 |
ilda | -0.046 |
lishes | -0.043 |
ods | -0.042 |
opsis | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
eele | +0.863 |
ilda | +0.842 |
ods | +0.741 |
lishes | +0.734 |
zl | +0.698 |
Neg logit contributions | |
hyde | -1.253 |
Hole | -1.083 |
rio | -1.050 |
antioxid | -1.036 |
warm | -1.021 |
Token | Mark |
Token ID | 2940 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
eele | +2.065 |
ilda | +2.003 |
lishes | +1.815 |
ods | +1.805 |
zl | +1.721 |
Neg logit contributions | |
hyde | -2.182 |
Hole | -1.871 |
rio | -1.803 |
warm | -1.756 |
antioxid | -1.740 |
Token | Bennett |
Token ID | 17468 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
eele | +2.942 |
ilda | +2.780 |
ods | +2.256 |
lishes | +2.253 |
NB | +2.050 |
Neg logit contributions | |
hyde | -7.948 |
Hole | -7.054 |
rio | -6.955 |
antioxid | -6.801 |
warm | -6.783 |
Token | ( |
Token ID | 357 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
eele | +0.693 |
ilda | +0.675 |
lishes | +0.631 |
ods | +0.610 |
opsis | +0.592 |
Neg logit contributions | |
hyde | -0.596 |
Hole | -0.516 |
rio | -0.487 |
warm | -0.476 |
antioxid | -0.458 |
Token | 63 |
Token ID | 5066 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
eele | +1.582 |
ilda | +1.555 |
ods | +1.409 |
lishes | +1.381 |
NB | +1.366 |
Neg logit contributions | |
hyde | -1.598 |
Hole | -1.355 |
antioxid | -1.297 |
rio | -1.274 |
fireplace | -1.227 |
Token | ) |
Token ID | 8 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
eele | +0.766 |
ilda | +0.742 |
ods | +0.668 |
lishes | +0.658 |
zl | +0.631 |
Neg logit contributions | |
hyde | -0.943 |
Hole | -0.819 |
rio | -0.783 |
antioxid | -0.778 |
warm | -0.760 |
Token | ( |
Token ID | 357 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
hyde | +0.792 |
Hole | +0.679 |
rio | +0.653 |
antioxid | +0.634 |
warm | +0.633 |
Neg logit contributions | |
eele | -0.750 |
ilda | -0.728 |
ods | -0.658 |
lishes | -0.658 |
zl | -0.626 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
eele | +0.392 |
ilda | +0.381 |
ods | +0.338 |
lishes | +0.336 |
zl | +0.319 |
Neg logit contributions | |
hyde | -0.541 |
Hole | -0.470 |
rio | -0.456 |
antioxid | -0.446 |
warm | -0.445 |
Token | Brian |
Token ID | 8403 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
eele | +1.506 |
ilda | +1.459 |
lishes | +1.316 |
ods | +1.310 |
zl | +1.241 |
Neg logit contributions | |
hyde | -1.747 |
Hole | -1.502 |
rio | -1.455 |
warm | -1.416 |
antioxid | -1.404 |
Token | Al |
Token ID | 978 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
eele | +0.758 |
ilda | +0.727 |
lishes | +0.668 |
ods | +0.660 |
zl | +0.625 |
Neg logit contributions | |
hyde | -0.837 |
Hole | -0.737 |
rio | -0.699 |
warm | -0.685 |
antioxid | -0.668 |
Token | ain |
Token ID | 391 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
hyde | +1.235 |
Hole | +1.012 |
rio | +0.947 |
warm | +0.913 |
antioxid | +0.894 |
Neg logit contributions | |
eele | -2.043 |
ilda | -1.990 |
lishes | -1.855 |
ods | -1.842 |
zl | -1.771 |
Token | u |
Token ID | 84 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
eele | +0.974 |
ilda | +0.950 |
ods | +0.853 |
lishes | +0.822 |
zl | +0.814 |
Neg logit contributions | |
hyde | -1.148 |
Hole | -1.009 |
antioxid | -0.961 |
rio | -0.935 |
warm | -0.922 |
Token | ' |
Token ID | 6 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
hyde | +0.408 |
Hole | +0.334 |
rio | +0.315 |
warm | +0.303 |
antioxid | +0.292 |
Neg logit contributions | |
eele | -0.701 |
ilda | -0.679 |
lishes | -0.640 |
ods | -0.630 |
zl | -0.604 |
Token | uese |
Token ID | 20506 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
eele | +2.124 |
ilda | +1.959 |
ods | +1.580 |
lishes | +1.505 |
opsis | +1.451 |
Neg logit contributions | |
hyde | -8.496 |
Hole | -8.160 |
fireplace | -7.514 |
antioxid | -7.427 |
warm | -7.426 |
Token | ( |
Token ID | 357 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
eele | +0.803 |
ilda | +0.777 |
lishes | +0.722 |
ods | +0.711 |
opsis | +0.677 |
Neg logit contributions | |
hyde | -0.696 |
Hole | -0.600 |
rio | -0.567 |
warm | -0.555 |
antioxid | -0.545 |
Token | 6 |
Token ID | 21 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
hyde | +1.224 |
Hole | +1.051 |
rio | +1.001 |
warm | +0.973 |
antioxid | +0.960 |
Neg logit contributions | |
eele | -1.315 |
ilda | -1.274 |
lishes | -1.168 |
ods | -1.159 |
zl | -1.105 |
Token | ) |
Token ID | 8 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
hyde | +0.584 |
Hole | +0.510 |
rio | +0.485 |
warm | +0.473 |
antioxid | +0.447 |
Neg logit contributions | |
eele | -0.651 |
ilda | -0.630 |
lishes | -0.595 |
ods | -0.570 |
opsis | -0.552 |
Token | ( |
Token ID | 357 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
hyde | +1.806 |
Hole | +1.597 |
rio | +1.459 |
warm | +1.456 |
antioxid | +1.413 |
Neg logit contributions | |
eele | -2.338 |
ilda | -2.231 |
lishes | -2.080 |
ods | -2.034 |
opsis | -1.968 |
Token | . |
Token ID | 13 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
eele | +1.163 |
ilda | +1.124 |
lishes | +1.025 |
ods | +1.021 |
zl | +0.964 |
Neg logit contributions | |
hyde | -1.251 |
Hole | -1.083 |
rio | -1.036 |
warm | -1.004 |
antioxid | -0.995 |
Token | � |
Token ID | 447 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
eele | +0.207 |
ilda | +0.201 |
lishes | +0.185 |
ods | +0.184 |
zl | +0.177 |
Neg logit contributions | |
hyde | -0.171 |
Hole | -0.144 |
rio | -0.137 |
warm | -0.133 |
antioxid | -0.132 |
Token | � |
Token ID | 251 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
eele | +0.102 |
ilda | +0.099 |
ods | +0.092 |
lishes | +0.090 |
zl | +0.086 |
Neg logit contributions | |
hyde | -0.098 |
Hole | -0.084 |
rio | -0.080 |
warm | -0.079 |
antioxid | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
eele | +1.802 |
ilda | +1.743 |
lishes | +1.597 |
ods | +1.582 |
zl | +1.506 |
Neg logit contributions | |
hyde | -1.769 |
Hole | -1.525 |
rio | -1.456 |
warm | -1.418 |
antioxid | -1.396 |
Token |
|
Token ID | 198 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
hyde | +0.240 |
Hole | +0.207 |
rio | +0.198 |
antioxid | +0.194 |
warm | +0.191 |
Neg logit contributions | |
eele | -0.215 |
ilda | -0.210 |
ods | -0.190 |
lishes | -0.188 |
zl | -0.179 |
Token | Who |
Token ID | 8241 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
hyde | +0.524 |
Hole | +0.450 |
rio | +0.429 |
warm | +0.417 |
antioxid | +0.412 |
Neg logit contributions | |
eele | -0.554 |
ilda | -0.536 |
lishes | -0.492 |
ods | -0.488 |
zl | -0.465 |
Token | does |
Token ID | 857 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
eele | +5.274 |
ilda | +5.070 |
ods | +4.749 |
lishes | +4.647 |
opsis | +4.502 |
Neg logit contributions | |
hyde | -5.327 |
Hole | -4.434 |
rio | -4.257 |
antioxid | -4.223 |
warm | -4.138 |
Token | Obama |
Token ID | 2486 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
eele | +2.481 |
ilda | +2.384 |
ods | +2.202 |
lishes | +2.177 |
zl | +2.092 |
Neg logit contributions | |
hyde | -2.476 |
Hole | -2.102 |
rio | -2.020 |
warm | -1.944 |
antioxid | -1.944 |
Token | think |
Token ID | 892 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
eele | +2.506 |
ilda | +2.453 |
ods | +2.303 |
lishes | +2.243 |
zl | +2.177 |
Neg logit contributions | |
hyde | -1.727 |
Hole | -1.423 |
rio | -1.334 |
antioxid | -1.294 |
warm | -1.261 |
Token | he |
Token ID | 339 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
eele | +0.922 |
ilda | +0.892 |
lishes | +0.822 |
ods | +0.818 |
zl | +0.780 |
Neg logit contributions | |
hyde | -0.824 |
Hole | -0.697 |
rio | -0.666 |
warm | -0.644 |
antioxid | -0.637 |
Token | is |
Token ID | 318 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
eele | +1.328 |
ilda | +1.293 |
lishes | +1.191 |
ods | +1.186 |
zl | +1.123 |
Neg logit contributions | |
hyde | -1.238 |
Hole | -1.056 |
rio | -0.999 |
antioxid | -0.975 |
warm | -0.967 |
Token | - |
Token ID | 12 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
eele | +0.399 |
ilda | +0.383 |
lishes | +0.353 |
ods | +0.347 |
zl | +0.336 |
Neg logit contributions | |
hyde | -0.364 |
Hole | -0.321 |
rio | -0.300 |
warm | -0.293 |
antioxid | -0.284 |
Token | Ret |
Token ID | 9781 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
hyde | +0.063 |
Hole | +0.055 |
rio | +0.053 |
warm | +0.051 |
antioxid | +0.050 |
Neg logit contributions | |
eele | -0.063 |
ilda | -0.061 |
lishes | -0.056 |
ods | -0.055 |
zl | -0.052 |
Token | arded |
Token ID | 10676 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
eele | +0.749 |
ilda | +0.716 |
lishes | +0.655 |
ods | +0.647 |
opsis | +0.607 |
Neg logit contributions | |
hyde | -0.932 |
Hole | -0.819 |
rio | -0.792 |
warm | -0.772 |
antioxid | -0.754 |
Token | Cook |
Token ID | 8261 |
Feature activation | +2.25e-03 |
Pos logit contributions | |
eele | +0.989 |
ilda | +0.959 |
lishes | +0.880 |
ods | +0.873 |
zl | +0.831 |
Neg logit contributions | |
hyde | -0.929 |
Hole | -0.795 |
rio | -0.760 |
warm | -0.740 |
antioxid | -0.730 |
Token | 200 |
Token ID | 939 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
hyde | +0.013 |
Hole | +0.012 |
rio | +0.011 |
warm | +0.011 |
antioxid | +0.011 |
Neg logit contributions | |
eele | -0.013 |
ilda | -0.013 |
lishes | -0.012 |
ods | -0.011 |
zl | -0.011 |
Token | 80 |
Token ID | 1795 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
eele | +3.336 |
ilda | +3.212 |
ods | +2.870 |
lishes | +2.852 |
zl | +2.677 |
Neg logit contributions | |
hyde | -4.697 |
Hole | -4.168 |
rio | -4.022 |
antioxid | -3.916 |
warm | -3.915 |
Token | 202 |
Token ID | 19004 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
eele | +4.348 |
ilda | +4.142 |
ods | +3.745 |
lishes | +3.679 |
NB | +3.460 |
Neg logit contributions | |
hyde | -6.262 |
Hole | -5.576 |
rio | -5.400 |
warm | -5.229 |
antioxid | -5.196 |
Token | O |
Token ID | 440 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ilda | +1.753 |
eele | +1.748 |
ods | +1.596 |
lishes | +1.512 |
opsis | +1.505 |
Neg logit contributions | |
hyde | -2.138 |
Hole | -1.723 |
antioxid | -1.714 |
warm | -1.701 |
rio | -1.690 |
Token | & |
Token ID | 5 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
hyde | +0.524 |
Hole | +0.429 |
rio | +0.398 |
antioxid | +0.391 |
warm | +0.384 |
Neg logit contributions | |
eele | -0.803 |
ilda | -0.787 |
ods | -0.727 |
lishes | -0.720 |
zl | -0.697 |
Token | A |
Token ID | 32 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
eele | +1.528 |
ilda | +1.516 |
ods | +1.356 |
NB | +1.317 |
lishes | +1.315 |
Neg logit contributions | |
hyde | -1.983 |
Hole | -1.718 |
rio | -1.642 |
antioxid | -1.628 |
warm | -1.603 |
Token | - |
Token ID | 12 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
eele | +2.113 |
ilda | +2.112 |
ods | +1.873 |
lishes | +1.814 |
NB | +1.792 |
Neg logit contributions | |
hyde | -2.917 |
Hole | -2.480 |
antioxid | -2.458 |
rio | -2.398 |
warm | -2.321 |
Token | — |
Token ID | 851 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
hyde | +0.521 |
Hole | +0.449 |
rio | +0.429 |
warm | +0.418 |
antioxid | +0.412 |
Neg logit contributions | |
eele | -0.522 |
ilda | -0.506 |
lishes | -0.462 |
ods | -0.458 |
zl | -0.436 |
Token | and |
Token ID | 290 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
eele | +0.907 |
ilda | +0.879 |
lishes | +0.796 |
ods | +0.794 |
zl | +0.754 |
Neg logit contributions | |
hyde | -0.965 |
Hole | -0.832 |
rio | -0.798 |
warm | -0.779 |
antioxid | -0.773 |
Token | girlfriend |
Token ID | 11077 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
eele | +0.529 |
ilda | +0.515 |
ods | +0.467 |
lishes | +0.465 |
zl | +0.447 |
Neg logit contributions | |
hyde | -0.519 |
Hole | -0.440 |
rio | -0.422 |
warm | -0.414 |
antioxid | -0.408 |
Token | — |
Token ID | 851 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
hyde | +0.086 |
Hole | +0.073 |
rio | +0.069 |
warm | +0.067 |
antioxid | +0.066 |
Neg logit contributions | |
eele | -0.107 |
ilda | -0.103 |
lishes | -0.096 |
ods | -0.095 |
zl | -0.090 |
Token | sent |
Token ID | 1908 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
eele | +1.523 |
ilda | +1.499 |
lishes | +1.351 |
ods | +1.347 |
zl | +1.282 |
Neg logit contributions | |
hyde | -1.449 |
Hole | -1.224 |
rio | -1.170 |
warm | -1.146 |
antioxid | -1.134 |
Token | out |
Token ID | 503 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
eele | +2.058 |
ilda | +1.991 |
ods | +1.815 |
lishes | +1.798 |
zl | +1.742 |
Neg logit contributions | |
hyde | -1.978 |
Hole | -1.656 |
rio | -1.602 |
warm | -1.560 |
antioxid | -1.558 |
Token | an |
Token ID | 281 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
eele | +4.820 |
ilda | +4.604 |
ods | +4.131 |
lishes | +4.085 |
zl | +3.906 |
Neg logit contributions | |
hyde | -5.783 |
Hole | -4.870 |
rio | -4.790 |
antioxid | -4.648 |
warm | -4.622 |
Token | e |
Token ID | 304 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
eele | +0.824 |
ilda | +0.792 |
lishes | +0.706 |
ods | +0.705 |
zl | +0.664 |
Neg logit contributions | |
hyde | -1.035 |
Hole | -0.890 |
rio | -0.859 |
warm | -0.838 |
antioxid | -0.830 |
Token | - |
Token ID | 12 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
hyde | +0.282 |
Hole | +0.243 |
rio | +0.234 |
warm | +0.228 |
antioxid | +0.221 |
Neg logit contributions | |
eele | -0.293 |
ilda | -0.282 |
lishes | -0.262 |
ods | -0.257 |
opsis | -0.244 |
Token | mail |
Token ID | 4529 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
eele | +0.697 |
ilda | +0.682 |
lishes | +0.616 |
ods | +0.612 |
zl | +0.586 |
Neg logit contributions | |
hyde | -0.772 |
Hole | -0.672 |
rio | -0.639 |
antioxid | -0.627 |
warm | -0.616 |
Token | to |
Token ID | 284 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
eele | +0.853 |
ilda | +0.828 |
lishes | +0.757 |
ods | +0.752 |
zl | +0.719 |
Neg logit contributions | |
hyde | -0.791 |
Hole | -0.671 |
rio | -0.643 |
warm | -0.623 |
antioxid | -0.616 |
Token | finale |
Token ID | 19523 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
eele | +0.368 |
ilda | +0.356 |
lishes | +0.324 |
ods | +0.321 |
zl | +0.305 |
Neg logit contributions | |
hyde | -0.392 |
Hole | -0.340 |
rio | -0.325 |
warm | -0.317 |
antioxid | -0.312 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
hyde | +0.655 |
Hole | +0.569 |
rio | +0.544 |
warm | +0.530 |
antioxid | +0.522 |
Neg logit contributions | |
eele | -0.617 |
ilda | -0.596 |
lishes | -0.544 |
ods | -0.539 |
zl | -0.512 |
Token | . |
Token ID | 764 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
eele | +1.213 |
ilda | +1.176 |
lishes | +1.068 |
ods | +1.054 |
NB | +1.008 |
Neg logit contributions | |
hyde | -1.346 |
Hole | -1.151 |
rio | -1.114 |
warm | -1.098 |
antioxid | -1.083 |
Token | En |
Token ID | 4834 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
hyde | +0.200 |
Hole | +0.173 |
rio | +0.166 |
warm | +0.162 |
antioxid | +0.160 |
Neg logit contributions | |
eele | -0.188 |
ilda | -0.181 |
lishes | -0.165 |
ods | -0.164 |
zl | -0.155 |
Token | ag |
Token ID | 556 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
eele | +2.648 |
ilda | +2.586 |
lishes | +2.369 |
ods | +2.352 |
opsis | +2.245 |
Neg logit contributions | |
hyde | -2.523 |
Hole | -2.158 |
rio | -2.043 |
warm | -2.008 |
antioxid | -1.974 |
Token | iss |
Token ID | 747 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
hyde | +1.996 |
Hole | +1.700 |
rio | +1.660 |
warm | +1.577 |
antioxid | +1.500 |
Neg logit contributions | |
eele | -2.318 |
ilda | -2.243 |
lishes | -2.064 |
ods | -2.044 |
zl | -1.954 |
Token | ant |
Token ID | 415 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
hyde | +3.088 |
Hole | +2.676 |
rio | +2.617 |
warm | +2.518 |
antioxid | +2.404 |
Neg logit contributions | |
eele | -2.880 |
ilda | -2.779 |
lishes | -2.568 |
ods | -2.496 |
zl | -2.412 |
Token | comm |
Token ID | 725 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
eele | +1.776 |
ilda | +1.707 |
lishes | +1.554 |
ods | +1.540 |
zl | +1.464 |
Neg logit contributions | |
hyde | -1.920 |
Hole | -1.661 |
rio | -1.586 |
warm | -1.560 |
antioxid | -1.526 |
Token | e |
Token ID | 68 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
hyde | +1.428 |
Hole | +1.247 |
rio | +1.221 |
warm | +1.183 |
antioxid | +1.140 |
Neg logit contributions | |
eele | -1.085 |
ilda | -1.050 |
lishes | -0.949 |
ods | -0.931 |
zl | -0.884 |
Token | il |
Token ID | 4229 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
eele | +0.536 |
ilda | +0.519 |
lishes | +0.474 |
ods | +0.469 |
zl | +0.447 |
Neg logit contributions | |
hyde | -0.557 |
Hole | -0.482 |
rio | -0.460 |
warm | -0.450 |
antioxid | -0.442 |
Token | s |
Token ID | 82 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
hyde | +2.420 |
Hole | +2.090 |
rio | +1.998 |
warm | +1.946 |
antioxid | +1.915 |
Neg logit contributions | |
eele | -2.414 |
ilda | -2.334 |
lishes | -2.135 |
ods | -2.115 |
zl | -2.012 |
Token | 'll |
Token ID | 1183 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
eele | +0.903 |
ilda | +0.888 |
ods | +0.799 |
lishes | +0.797 |
opsis | +0.760 |
Neg logit contributions | |
hyde | -0.977 |
Hole | -0.852 |
rio | -0.807 |
antioxid | -0.796 |
warm | -0.786 |
Token | be |
Token ID | 307 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
eele | +1.403 |
ilda | +1.361 |
lishes | +1.250 |
ods | +1.241 |
zl | +1.184 |
Neg logit contributions | |
hyde | -1.231 |
Hole | -1.053 |
rio | -1.001 |
warm | -0.972 |
antioxid | -0.958 |
Token | in |
Token ID | 287 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
hyde | +0.364 |
Hole | +0.312 |
rio | +0.297 |
warm | +0.289 |
antioxid | +0.285 |
Neg logit contributions | |
eele | -0.397 |
ilda | -0.385 |
lishes | -0.353 |
ods | -0.351 |
zl | -0.335 |
Token | custody |
Token ID | 10804 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
hyde | +0.145 |
Hole | +0.128 |
rio | +0.124 |
warm | +0.121 |
antioxid | +0.119 |
Neg logit contributions | |
eele | -0.103 |
ilda | -0.099 |
lishes | -0.087 |
ods | -0.087 |
zl | -0.082 |
Token | pretty |
Token ID | 2495 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
eele | +0.333 |
ilda | +0.320 |
lishes | +0.296 |
ods | +0.294 |
zl | +0.281 |
Neg logit contributions | |
hyde | -0.282 |
Hole | -0.239 |
rio | -0.229 |
warm | -0.222 |
antioxid | -0.219 |
Token | quickly |
Token ID | 2952 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
hyde | +1.897 |
Hole | +1.619 |
rio | +1.544 |
warm | +1.500 |
antioxid | +1.472 |
Neg logit contributions | |
eele | -2.163 |
ilda | -2.093 |
lishes | -1.929 |
ods | -1.913 |
zl | -1.825 |
Token | ." |
Token ID | 526 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
hyde | +2.797 |
Hole | +2.351 |
rio | +2.225 |
warm | +2.152 |
antioxid | +2.087 |
Neg logit contributions | |
eele | -3.878 |
ilda | -3.714 |
lishes | -3.453 |
ods | -3.423 |
zl | -3.283 |
Token |
|
Token ID | 198 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
hyde | +1.268 |
Hole | +1.098 |
rio | +1.028 |
warm | +1.003 |
antioxid | +0.966 |
Neg logit contributions | |
eele | -1.522 |
ilda | -1.481 |
lishes | -1.371 |
ods | -1.334 |
opsis | -1.299 |
Token |
|
Token ID | 198 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
hyde | +1.495 |
Hole | +1.291 |
rio | +1.233 |
warm | +1.201 |
antioxid | +1.186 |
Neg logit contributions | |
eele | -1.476 |
ilda | -1.428 |
lishes | -1.305 |
ods | -1.295 |
zl | -1.231 |
Token | ' |
Token ID | 6 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
hyde | +1.613 |
Hole | +1.381 |
rio | +1.331 |
warm | +1.308 |
antioxid | +1.248 |
Neg logit contributions | |
eele | -1.772 |
ilda | -1.711 |
lishes | -1.574 |
ods | -1.548 |
opsis | -1.484 |
Token | A |
Token ID | 32 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
eele | +0.408 |
ilda | +0.398 |
lishes | +0.365 |
ods | +0.363 |
zl | +0.347 |
Neg logit contributions | |
hyde | -0.377 |
Hole | -0.320 |
rio | -0.306 |
antioxid | -0.296 |
warm | -0.295 |
Token | state |
Token ID | 1181 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
hyde | +0.950 |
Hole | +0.777 |
rio | +0.713 |
warm | +0.693 |
antioxid | +0.669 |
Neg logit contributions | |
eele | -1.774 |
ilda | -1.717 |
lishes | -1.618 |
ods | -1.605 |
zl | -1.556 |
Token | , |
Token ID | 11 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
hyde | +2.537 |
Hole | +2.216 |
rio | +2.113 |
warm | +2.078 |
antioxid | +2.019 |
Neg logit contributions | |
eele | -2.440 |
ilda | -2.343 |
lishes | -2.150 |
ods | -2.134 |
zl | -2.033 |
Token | and |
Token ID | 290 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
hyde | +1.019 |
Hole | +0.873 |
rio | +0.829 |
warm | +0.808 |
antioxid | +0.794 |
Neg logit contributions | |
eele | -1.153 |
ilda | -1.115 |
lishes | -1.027 |
ods | -1.019 |
zl | -0.972 |
Token | which |
Token ID | 543 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
hyde | +1.359 |
Hole | +1.160 |
rio | +1.099 |
warm | +1.069 |
antioxid | +1.049 |
Neg logit contributions | |
eele | -1.627 |
ilda | -1.576 |
lishes | -1.456 |
ods | -1.443 |
zl | -1.379 |
Token | is |
Token ID | 318 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
hyde | +1.126 |
Hole | +0.962 |
rio | +0.907 |
warm | +0.884 |
antioxid | +0.866 |
Neg logit contributions | |
eele | -1.407 |
ilda | -1.369 |
lishes | -1.266 |
ods | -1.254 |
zl | -1.206 |
Token | the |
Token ID | 262 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
hyde | +2.144 |
Hole | +1.868 |
rio | +1.761 |
warm | +1.734 |
antioxid | +1.682 |
Neg logit contributions | |
eele | -2.271 |
ilda | -2.176 |
lishes | -2.010 |
ods | -1.990 |
zl | -1.917 |
Token | " |
Token ID | 366 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
hyde | +2.641 |
Hole | +2.265 |
rio | +2.132 |
warm | +2.087 |
antioxid | +2.047 |
Neg logit contributions | |
eele | -3.182 |
ilda | -3.083 |
lishes | -2.852 |
ods | -2.820 |
zl | -2.710 |
Token | authent |
Token ID | 41299 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
hyde | +0.806 |
Hole | +0.695 |
rio | +0.664 |
warm | +0.649 |
antioxid | +0.635 |
Neg logit contributions | |
eele | -0.809 |
ilda | -0.782 |
lishes | -0.716 |
ods | -0.709 |
zl | -0.675 |
Token | ic |
Token ID | 291 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
hyde | +0.807 |
Hole | +0.707 |
rio | +0.686 |
warm | +0.667 |
antioxid | +0.647 |
Neg logit contributions | |
eele | -0.674 |
ilda | -0.646 |
lishes | -0.583 |
ods | -0.580 |
zl | -0.549 |
Token | " |
Token ID | 1 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
eele | +0.191 |
ilda | +0.186 |
lishes | +0.171 |
ods | +0.170 |
zl | +0.162 |
Neg logit contributions | |
hyde | -0.146 |
Hole | -0.123 |
rio | -0.116 |
warm | -0.112 |
antioxid | -0.111 |
Token | one |
Token ID | 530 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
hyde | +0.748 |
Hole | +0.631 |
rio | +0.603 |
warm | +0.581 |
antioxid | +0.572 |
Neg logit contributions | |
eele | -0.902 |
ilda | -0.879 |
lishes | -0.806 |
ods | -0.800 |
zl | -0.764 |
Token | more |
Token ID | 517 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
hyde | +1.707 |
Hole | +1.472 |
rio | +1.407 |
warm | +1.368 |
antioxid | +1.344 |
Neg logit contributions | |
eele | -1.804 |
ilda | -1.738 |
lishes | -1.598 |
ods | -1.583 |
zl | -1.507 |
Token | gradual |
Token ID | 24972 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
eele | +0.211 |
ilda | +0.207 |
lishes | +0.189 |
ods | +0.187 |
zl | +0.179 |
Neg logit contributions | |
hyde | -0.190 |
Hole | -0.161 |
rio | -0.153 |
warm | -0.150 |
antioxid | -0.146 |
Token | and |
Token ID | 290 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
hyde | +1.546 |
Hole | +1.329 |
rio | +1.270 |
warm | +1.239 |
antioxid | +1.209 |
Neg logit contributions | |
eele | -1.623 |
ilda | -1.554 |
lishes | -1.434 |
ods | -1.418 |
zl | -1.355 |
Token | softer |
Token ID | 32359 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
hyde | +0.341 |
Hole | +0.291 |
rio | +0.277 |
warm | +0.269 |
antioxid | +0.265 |
Neg logit contributions | |
eele | -0.369 |
ilda | -0.359 |
lishes | -0.327 |
ods | -0.326 |
zl | -0.311 |
Token | , |
Token ID | 11 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
hyde | +0.637 |
Hole | +0.550 |
rio | +0.525 |
warm | +0.512 |
antioxid | +0.502 |
Neg logit contributions | |
eele | -0.654 |
ilda | -0.629 |
lishes | -0.579 |
ods | -0.573 |
zl | -0.547 |
Token | rather |
Token ID | 2138 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
hyde | +0.360 |
Hole | +0.306 |
rio | +0.292 |
warm | +0.282 |
antioxid | +0.279 |
Neg logit contributions | |
eele | -0.401 |
ilda | -0.392 |
lishes | -0.359 |
ods | -0.357 |
zl | -0.339 |
Token | than |
Token ID | 621 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
hyde | +3.527 |
Hole | +3.031 |
rio | +2.876 |
warm | +2.869 |
antioxid | +2.789 |
Neg logit contributions | |
eele | -4.382 |
ilda | -4.108 |
lishes | -3.906 |
ods | -3.837 |
zl | -3.695 |
Token | an |
Token ID | 281 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
hyde | +1.421 |
Hole | +1.215 |
rio | +1.158 |
warm | +1.126 |
antioxid | +1.108 |
Neg logit contributions | |
eele | -1.570 |
ilda | -1.522 |
lishes | -1.398 |
ods | -1.387 |
zl | -1.323 |
Token | abrupt |
Token ID | 19363 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
hyde | +1.753 |
Hole | +1.503 |
rio | +1.431 |
warm | +1.392 |
antioxid | +1.368 |
Neg logit contributions | |
eele | -1.946 |
ilda | -1.883 |
lishes | -1.733 |
ods | -1.717 |
zl | -1.638 |
Token | change |
Token ID | 1487 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
hyde | +1.652 |
Hole | +1.415 |
rio | +1.344 |
warm | +1.309 |
antioxid | +1.285 |
Neg logit contributions | |
eele | -1.834 |
ilda | -1.774 |
lishes | -1.633 |
ods | -1.616 |
zl | -1.541 |
Token | . |
Token ID | 13 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
hyde | +0.101 |
Hole | +0.088 |
rio | +0.084 |
warm | +0.082 |
antioxid | +0.081 |
Neg logit contributions | |
eele | -0.099 |
ilda | -0.096 |
lishes | -0.087 |
ods | -0.087 |
zl | -0.082 |
Token | � |
Token ID | 447 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
hyde | +0.730 |
Hole | +0.617 |
rio | +0.584 |
warm | +0.567 |
antioxid | +0.560 |
Neg logit contributions | |
eele | -0.908 |
ilda | -0.883 |
lishes | -0.813 |
ods | -0.810 |
zl | -0.773 |
Token | � |
Token ID | 247 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
hyde | +0.526 |
Hole | +0.442 |
rio | +0.416 |
warm | +0.404 |
antioxid | +0.397 |
Neg logit contributions | |
eele | -0.714 |
ilda | -0.695 |
lishes | -0.641 |
ods | -0.640 |
zl | -0.611 |
Token | re |
Token ID | 260 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
hyde | +1.763 |
Hole | +1.540 |
rio | +1.480 |
warm | +1.448 |
antioxid | +1.419 |
Neg logit contributions | |
eele | -1.494 |
ilda | -1.439 |
lishes | -1.307 |
ods | -1.291 |
zl | -1.220 |
Token | quizz |
Token ID | 48258 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
hyde | +1.278 |
Hole | +1.097 |
rio | +1.043 |
warm | +1.017 |
antioxid | +0.997 |
Neg logit contributions | |
eele | -1.422 |
ilda | -1.376 |
lishes | -1.267 |
ods | -1.253 |
zl | -1.197 |
Token | ed |
Token ID | 276 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
hyde | +1.260 |
Hole | +1.089 |
rio | +1.040 |
warm | +1.023 |
antioxid | +0.979 |
Neg logit contributions | |
eele | -1.209 |
ilda | -1.169 |
lishes | -1.076 |
ods | -1.048 |
opsis | -1.015 |
Token | . |
Token ID | 13 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
hyde | +0.876 |
Hole | +0.758 |
rio | +0.724 |
warm | +0.707 |
antioxid | +0.692 |
Neg logit contributions | |
eele | -0.893 |
ilda | -0.859 |
lishes | -0.791 |
ods | -0.779 |
zl | -0.744 |
Token | But |
Token ID | 887 |
Feature activation | -8.00e-03 |
Pos logit contributions | |
hyde | +2.663 |
Hole | +2.325 |
rio | +2.170 |
warm | +2.109 |
antioxid | +2.033 |
Neg logit contributions | |
eele | -3.215 |
ilda | -3.106 |
lishes | -2.877 |
ods | -2.834 |
opsis | -2.716 |
Token | seems |
Token ID | 2331 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
eele | +0.049 |
ilda | +0.048 |
ods | +0.044 |
lishes | +0.044 |
zl | +0.042 |
Neg logit contributions | |
hyde | -0.045 |
Hole | -0.038 |
rio | -0.037 |
warm | -0.036 |
antioxid | -0.035 |
Token | we |
Token ID | 356 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
hyde | +0.379 |
Hole | +0.326 |
rio | +0.309 |
warm | +0.302 |
antioxid | +0.295 |
Neg logit contributions | |
eele | -0.422 |
ilda | -0.409 |
lishes | -0.377 |
ods | -0.372 |
zl | -0.355 |
Token | � |
Token ID | 447 |
Feature activation | +7.99e-03 |
Pos logit contributions | |
hyde | +0.214 |
Hole | +0.180 |
rio | +0.171 |
warm | +0.166 |
antioxid | +0.163 |
Neg logit contributions | |
eele | -0.274 |
ilda | -0.266 |
lishes | -0.246 |
ods | -0.244 |
zl | -0.234 |
Token | � |
Token ID | 247 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
hyde | +0.039 |
Hole | +0.032 |
rio | +0.030 |
warm | +0.029 |
antioxid | +0.029 |
Neg logit contributions | |
eele | -0.056 |
ilda | -0.054 |
lishes | -0.051 |
ods | -0.050 |
zl | -0.048 |
Token | before |
Token ID | 878 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
hyde | +1.714 |
Hole | +1.465 |
rio | +1.395 |
warm | +1.354 |
antioxid | +1.331 |
Neg logit contributions | |
eele | -1.985 |
ilda | -1.922 |
lishes | -1.773 |
ods | -1.756 |
zl | -1.679 |
Token | and |
Token ID | 290 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
eele | +0.435 |
ilda | +0.420 |
lishes | +0.382 |
ods | +0.379 |
zl | +0.359 |
Neg logit contributions | |
hyde | -0.479 |
Hole | -0.416 |
rio | -0.399 |
warm | -0.389 |
antioxid | -0.383 |
Token | under |
Token ID | 739 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
hyde | +1.543 |
Hole | +1.324 |
rio | +1.262 |
warm | +1.224 |
antioxid | +1.206 |
Neg logit contributions | |
eele | -1.694 |
ilda | -1.639 |
lishes | -1.508 |
ods | -1.493 |
zl | -1.423 |
Token | the |
Token ID | 262 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
hyde | +0.894 |
Hole | +0.775 |
rio | +0.739 |
warm | +0.719 |
antioxid | +0.708 |
Neg logit contributions | |
eele | -0.905 |
ilda | -0.868 |
lishes | -0.799 |
ods | -0.790 |
opsis | -0.750 |
Token | law |
Token ID | 1099 |
Feature activation | -4.71e-03 |
Pos logit contributions | |
eele | +0.141 |
ilda | +0.138 |
lishes | +0.128 |
ods | +0.127 |
zl | +0.122 |
Neg logit contributions | |
hyde | -0.091 |
Hole | -0.074 |
rio | -0.070 |
warm | -0.068 |
antioxid | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
eele | +0.028 |
ilda | +0.028 |
lishes | +0.025 |
ods | +0.025 |
zl | +0.024 |
Neg logit contributions | |
hyde | -0.027 |
Hole | -0.023 |
rio | -0.022 |
warm | -0.022 |
antioxid | -0.022 |
Token | has |
Token ID | 468 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
hyde | +1.336 |
Hole | +1.142 |
rio | +1.089 |
warm | +1.066 |
antioxid | +1.045 |
Neg logit contributions | |
eele | -1.425 |
ilda | -1.381 |
lishes | -1.267 |
ods | -1.256 |
zl | -1.196 |
Token | the |
Token ID | 262 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
hyde | +2.238 |
Hole | +1.945 |
rio | +1.862 |
warm | +1.808 |
antioxid | +1.779 |
Neg logit contributions | |
eele | -2.270 |
ilda | -2.187 |
lishes | -2.000 |
ods | -1.985 |
zl | -1.895 |
Token | right |
Token ID | 826 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
hyde | +1.200 |
Hole | +0.954 |
rio | +0.882 |
warm | +0.839 |
antioxid | +0.816 |
Neg logit contributions | |
eele | -2.514 |
ilda | -2.451 |
lishes | -2.302 |
ods | -2.284 |
zl | -2.207 |
Token | to |
Token ID | 284 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
hyde | +1.598 |
Hole | +1.363 |
rio | +1.302 |
warm | +1.268 |
antioxid | +1.229 |
Neg logit contributions | |
eele | -2.105 |
ilda | -2.032 |
lishes | -1.893 |
ods | -1.835 |
zl | -1.806 |
Token | the |
Token ID | 262 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
hyde | +1.036 |
Hole | +0.881 |
rio | +0.837 |
warm | +0.817 |
antioxid | +0.803 |
Neg logit contributions | |
eele | -1.182 |
ilda | -1.148 |
lishes | -1.053 |
ods | -1.048 |
zl | -0.999 |
Token | last |
Token ID | 938 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
eele | +1.871 |
ilda | +1.828 |
ods | +1.683 |
lishes | +1.681 |
zl | +1.594 |
Neg logit contributions | |
hyde | -1.541 |
Hole | -1.250 |
rio | -1.216 |
warm | -1.178 |
antioxid | -1.158 |
Token | five |
Token ID | 1936 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
hyde | +0.546 |
Hole | +0.476 |
rio | +0.459 |
warm | +0.449 |
antioxid | +0.443 |
Neg logit contributions | |
eele | -0.411 |
ilda | -0.396 |
lishes | -0.357 |
ods | -0.354 |
zl | -0.333 |
Token | weeks |
Token ID | 2745 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
eele | +0.146 |
ilda | +0.140 |
lishes | +0.127 |
ods | +0.125 |
zl | +0.119 |
Neg logit contributions | |
hyde | -0.183 |
Hole | -0.161 |
rio | -0.155 |
warm | -0.151 |
antioxid | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
eele | +0.672 |
ilda | +0.649 |
lishes | +0.591 |
ods | +0.584 |
zl | +0.555 |
Neg logit contributions | |
hyde | -0.738 |
Hole | -0.643 |
rio | -0.615 |
warm | -0.601 |
antioxid | -0.591 |
Token |
|
Token ID | 198 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
hyde | +1.044 |
Hole | +0.911 |
rio | +0.857 |
warm | +0.834 |
antioxid | +0.816 |
Neg logit contributions | |
eele | -1.121 |
ilda | -1.084 |
lishes | -0.998 |
ods | -0.985 |
opsis | -0.939 |
Token |
|
Token ID | 198 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
hyde | +0.491 |
Hole | +0.424 |
rio | +0.405 |
antioxid | +0.396 |
warm | +0.392 |
Neg logit contributions | |
eele | -0.448 |
ilda | -0.436 |
ods | -0.394 |
lishes | -0.393 |
zl | -0.373 |
Token | Congress |
Token ID | 25916 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
hyde | +0.303 |
Hole | +0.261 |
rio | +0.249 |
warm | +0.242 |
antioxid | +0.239 |
Neg logit contributions | |
eele | -0.316 |
ilda | -0.306 |
lishes | -0.280 |
ods | -0.278 |
zl | -0.265 |
Token | itself |
Token ID | 2346 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
eele | +0.458 |
ilda | +0.447 |
lishes | +0.411 |
ods | +0.406 |
zl | +0.387 |
Neg logit contributions | |
hyde | -0.410 |
Hole | -0.347 |
rio | -0.332 |
warm | -0.324 |
antioxid | -0.319 |
Token | has |
Token ID | 468 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
hyde | +0.917 |
Hole | +0.785 |
rio | +0.750 |
warm | +0.730 |
antioxid | +0.720 |
Neg logit contributions | |
eele | -0.963 |
ilda | -0.935 |
lishes | -0.858 |
ods | -0.850 |
zl | -0.809 |
Token | seemed |
Token ID | 3947 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
hyde | +1.442 |
Hole | +1.240 |
rio | +1.183 |
warm | +1.152 |
antioxid | +1.133 |
Neg logit contributions | |
eele | -1.512 |
ilda | -1.463 |
lishes | -1.342 |
ods | -1.331 |
zl | -1.267 |
Token | relatively |
Token ID | 5365 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
hyde | +0.984 |
Hole | +0.836 |
rio | +0.787 |
warm | +0.781 |
antioxid | +0.756 |
Neg logit contributions | |
eele | -1.149 |
ilda | -1.118 |
lishes | -1.034 |
ods | -1.016 |
zl | -0.974 |
Token | bid |
Token ID | 8406 |
Feature activation | -9.55e-02 |
Pos logit contributions | |
hyde | +0.740 |
Hole | +0.624 |
rio | +0.589 |
antioxid | +0.578 |
warm | +0.575 |
Neg logit contributions | |
eele | -0.842 |
ilda | -0.827 |
lishes | -0.753 |
ods | -0.752 |
zl | -0.718 |
Token | up |
Token ID | 510 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
eele | +0.588 |
ilda | +0.571 |
lishes | +0.523 |
ods | +0.522 |
zl | +0.499 |
Neg logit contributions | |
hyde | -0.541 |
Hole | -0.461 |
rio | -0.436 |
warm | -0.427 |
antioxid | -0.422 |
Token | the |
Token ID | 262 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
eele | +0.853 |
ilda | +0.832 |
lishes | +0.756 |
ods | +0.752 |
zl | +0.716 |
Neg logit contributions | |
hyde | -0.874 |
Hole | -0.753 |
rio | -0.721 |
warm | -0.704 |
antioxid | -0.695 |
Token | price |
Token ID | 2756 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
eele | +0.224 |
ilda | +0.218 |
lishes | +0.197 |
ods | +0.197 |
zl | +0.188 |
Neg logit contributions | |
hyde | -0.235 |
Hole | -0.200 |
rio | -0.193 |
warm | -0.188 |
antioxid | -0.185 |
Token | of |
Token ID | 286 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
hyde | +0.328 |
Hole | +0.277 |
rio | +0.262 |
warm | +0.254 |
antioxid | +0.251 |
Neg logit contributions | |
eele | -0.414 |
ilda | -0.398 |
lishes | -0.369 |
ods | -0.364 |
zl | -0.349 |
Token | existing |
Token ID | 4683 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
hyde | +0.364 |
Hole | +0.305 |
rio | +0.289 |
warm | +0.280 |
antioxid | +0.275 |
Neg logit contributions | |
eele | -0.480 |
ilda | -0.467 |
lishes | -0.432 |
ods | -0.428 |
zl | -0.411 |
Token | dwellings |
Token ID | 50078 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
hyde | +0.769 |
Hole | +0.655 |
rio | +0.622 |
warm | +0.604 |
antioxid | +0.593 |
Neg logit contributions | |
eele | -0.923 |
ilda | -0.894 |
lishes | -0.825 |
ods | -0.817 |
zl | -0.781 |
Token | , |
Token ID | 11 |
Feature activation | +9.94e-03 |
Pos logit contributions | |
hyde | +1.894 |
Hole | +1.633 |
rio | +1.558 |
warm | +1.518 |
antioxid | +1.485 |
Neg logit contributions | |
eele | -1.994 |
ilda | -1.922 |
lishes | -1.768 |
ods | -1.746 |
zl | -1.664 |
Token | squeezing |
Token ID | 40237 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
hyde | +0.057 |
Hole | +0.048 |
rio | +0.046 |
warm | +0.045 |
antioxid | +0.044 |
Neg logit contributions | |
eele | -0.061 |
ilda | -0.060 |
lishes | -0.054 |
ods | -0.054 |
zl | -0.051 |
Token | first |
Token ID | 717 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
eele | +0.479 |
ilda | +0.469 |
lishes | +0.430 |
ods | +0.425 |
zl | +0.408 |
Neg logit contributions | |
hyde | -0.426 |
Hole | -0.359 |
rio | -0.344 |
warm | -0.333 |
antioxid | -0.327 |
Token | - |
Token ID | 12 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
hyde | +0.344 |
Hole | +0.298 |
rio | +0.283 |
warm | +0.276 |
antioxid | +0.269 |
Neg logit contributions | |
eele | -0.391 |
ilda | -0.374 |
lishes | -0.344 |
ods | -0.340 |
opsis | -0.326 |
Token | Alec |
Token ID | 38285 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
hyde | +0.532 |
Hole | +0.474 |
rio | +0.450 |
warm | +0.441 |
antioxid | +0.431 |
Neg logit contributions | |
eele | -0.452 |
ilda | -0.431 |
lishes | -0.398 |
ods | -0.390 |
zl | -0.369 |
Token | Baldwin |
Token ID | 26402 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
eele | +1.138 |
ilda | +1.116 |
ods | +0.992 |
lishes | +0.974 |
NB | +0.931 |
Neg logit contributions | |
hyde | -1.506 |
Hole | -1.275 |
rio | -1.249 |
antioxid | -1.221 |
warm | -1.202 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e-03 |
Pos logit contributions | |
eele | +0.140 |
ilda | +0.136 |
ods | +0.122 |
lishes | +0.121 |
zl | +0.115 |
Neg logit contributions | |
hyde | -0.159 |
Hole | -0.136 |
rio | -0.130 |
antioxid | -0.129 |
warm | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
eele | +0.009 |
ilda | +0.009 |
ods | +0.008 |
lishes | +0.008 |
zl | +0.007 |
Neg logit contributions | |
hyde | -0.010 |
Hole | -0.009 |
rio | -0.008 |
antioxid | -0.008 |
warm | -0.008 |
Token | 2008 |
Token ID | 11528 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
hyde | +1.238 |
Hole | +1.071 |
rio | +1.035 |
warm | +1.019 |
antioxid | +0.971 |
Neg logit contributions | |
eele | -1.227 |
ilda | -1.167 |
lishes | -1.088 |
ods | -1.066 |
arcity | -1.018 |
Token | Steve |
Token ID | 6542 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
hyde | +2.086 |
Hole | +1.889 |
rio | +1.769 |
warm | +1.736 |
antioxid | +1.683 |
Neg logit contributions | |
eele | -1.868 |
ilda | -1.773 |
lishes | -1.666 |
ods | -1.613 |
arcity | -1.533 |
Token | Care |
Token ID | 7276 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
hyde | +0.571 |
Hole | +0.489 |
rio | +0.471 |
warm | +0.459 |
antioxid | +0.459 |
Neg logit contributions | |
eele | -0.496 |
ilda | -0.481 |
lishes | -0.433 |
ods | -0.432 |
zl | -0.409 |
Token | ll |
Token ID | 297 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
eele | +0.539 |
ilda | +0.519 |
ods | +0.452 |
lishes | +0.445 |
zl | +0.422 |
Neg logit contributions | |
hyde | -0.961 |
Hole | -0.862 |
rio | -0.823 |
antioxid | -0.822 |
warm | -0.802 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
eele | +0.828 |
ilda | +0.808 |
ods | +0.729 |
lishes | +0.723 |
zl | +0.688 |
Neg logit contributions | |
hyde | -0.933 |
Hole | -0.800 |
rio | -0.770 |
antioxid | -0.753 |
warm | -0.745 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
eele | +0.766 |
ilda | +0.750 |
ods | +0.673 |
lishes | +0.665 |
zl | +0.637 |
Neg logit contributions | |
hyde | -0.903 |
Hole | -0.775 |
rio | -0.742 |
antioxid | -0.740 |
warm | -0.716 |
Token | 2008 |
Token ID | 11528 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
eele | +0.073 |
ilda | +0.070 |
lishes | +0.064 |
ods | +0.063 |
zl | +0.060 |
Neg logit contributions | |
hyde | -0.082 |
Hole | -0.072 |
rio | -0.069 |
warm | -0.067 |
antioxid | -0.066 |
Token | won |
Token ID | 1839 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
eele | +0.621 |
ilda | +0.606 |
lishes | +0.553 |
ods | +0.550 |
zl | +0.527 |
Neg logit contributions | |
hyde | -0.595 |
Hole | -0.506 |
rio | -0.486 |
warm | -0.471 |
antioxid | -0.463 |
Token | , |
Token ID | 11 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
hyde | +0.590 |
Hole | +0.512 |
rio | +0.486 |
warm | +0.477 |
antioxid | +0.469 |
Neg logit contributions | |
eele | -0.599 |
ilda | -0.575 |
lishes | -0.532 |
ods | -0.523 |
opsis | -0.495 |
Token | but |
Token ID | 475 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
eele | +0.839 |
ilda | +0.818 |
lishes | +0.751 |
ods | +0.749 |
zl | +0.717 |
Neg logit contributions | |
hyde | -0.680 |
Hole | -0.574 |
rio | -0.548 |
warm | -0.528 |
antioxid | -0.521 |
Token | there |
Token ID | 612 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
eele | +0.945 |
ilda | +0.922 |
ods | +0.833 |
lishes | +0.832 |
zl | +0.795 |
Neg logit contributions | |
hyde | -0.985 |
Hole | -0.840 |
rio | -0.810 |
warm | -0.784 |
antioxid | -0.774 |
Token | will |
Token ID | 481 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
hyde | +0.194 |
Hole | +0.164 |
rio | +0.154 |
warm | +0.150 |
antioxid | +0.146 |
Neg logit contributions | |
eele | -0.257 |
ilda | -0.249 |
lishes | -0.234 |
ods | -0.229 |
zl | -0.220 |
Token | also |
Token ID | 635 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
hyde | +0.368 |
Hole | +0.310 |
rio | +0.293 |
warm | +0.288 |
antioxid | +0.280 |
Neg logit contributions | |
eele | -0.459 |
ilda | -0.441 |
lishes | -0.419 |
ods | -0.405 |
zl | -0.389 |
Token | be |
Token ID | 307 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
hyde | +0.443 |
Hole | +0.366 |
rio | +0.344 |
warm | +0.338 |
antioxid | +0.326 |
Neg logit contributions | |
eele | -0.618 |
ilda | -0.592 |
lishes | -0.574 |
ods | -0.546 |
zl | -0.528 |
Token | a |
Token ID | 257 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
eele | +0.083 |
ilda | +0.080 |
lishes | +0.073 |
ods | +0.073 |
zl | +0.069 |
Neg logit contributions | |
hyde | -0.077 |
Hole | -0.066 |
rio | -0.063 |
warm | -0.061 |
antioxid | -0.060 |
Token | ton |
Token ID | 5680 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
eele | +0.416 |
ilda | +0.402 |
lishes | +0.368 |
ods | +0.367 |
zl | +0.350 |
Neg logit contributions | |
hyde | -0.390 |
Hole | -0.333 |
rio | -0.319 |
warm | -0.310 |
antioxid | -0.306 |
Token | of |
Token ID | 286 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
eele | +0.708 |
ilda | +0.676 |
lishes | +0.636 |
ods | +0.623 |
opsis | +0.596 |
Neg logit contributions | |
hyde | -0.518 |
Hole | -0.432 |
rio | -0.415 |
warm | -0.405 |
antioxid | -0.385 |
Token | pressure |
Token ID | 3833 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
eele | +0.206 |
ilda | +0.200 |
lishes | +0.184 |
ods | +0.183 |
zl | +0.175 |
Neg logit contributions | |
hyde | -0.180 |
Hole | -0.152 |
rio | -0.145 |
warm | -0.141 |
antioxid | -0.138 |
Token | hers |
Token ID | 7084 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
eele | +0.972 |
ilda | +0.941 |
lishes | +0.863 |
ods | +0.853 |
zl | +0.811 |
Neg logit contributions | |
hyde | -0.962 |
Hole | -0.831 |
rio | -0.796 |
warm | -0.774 |
antioxid | -0.761 |
Token | *) |
Token ID | 28104 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
eele | +0.121 |
ilda | +0.117 |
lishes | +0.108 |
ods | +0.105 |
zl | +0.101 |
Neg logit contributions | |
hyde | -0.115 |
Hole | -0.101 |
rio | -0.096 |
warm | -0.094 |
antioxid | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
hyde | +2.063 |
Hole | +1.783 |
rio | +1.690 |
warm | +1.638 |
antioxid | +1.559 |
Neg logit contributions | |
eele | -2.634 |
ilda | -2.549 |
lishes | -2.371 |
ods | -2.303 |
zl | -2.247 |
Token |
|
Token ID | 198 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
hyde | +0.539 |
Hole | +0.465 |
rio | +0.444 |
antioxid | +0.434 |
warm | +0.431 |
Neg logit contributions | |
eele | -0.499 |
ilda | -0.485 |
ods | -0.438 |
lishes | -0.438 |
zl | -0.415 |
Token | 2017 |
Token ID | 5539 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
eele | +0.208 |
ilda | +0.203 |
lishes | +0.190 |
ods | +0.189 |
zl | +0.182 |
Neg logit contributions | |
hyde | -0.099 |
Hole | -0.078 |
rio | -0.072 |
warm | -0.069 |
antioxid | -0.067 |
Token | salary |
Token ID | 9588 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
eele | +1.143 |
ilda | +1.119 |
lishes | +1.048 |
ods | +1.038 |
zl | +1.002 |
Neg logit contributions | |
hyde | -0.683 |
Hole | -0.574 |
rio | -0.543 |
warm | -0.513 |
antioxid | -0.503 |
Token | and |
Token ID | 290 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
eele | +3.339 |
ilda | +3.279 |
ods | +2.976 |
lishes | +2.906 |
zl | +2.808 |
Neg logit contributions | |
hyde | -3.466 |
Hole | -2.926 |
rio | -2.800 |
antioxid | -2.752 |
warm | -2.719 |
Token | bonuses |
Token ID | 17568 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
eele | +1.747 |
ilda | +1.694 |
ods | +1.553 |
lishes | +1.510 |
NB | +1.449 |
Neg logit contributions | |
hyde | -1.905 |
Hole | -1.628 |
rio | -1.541 |
warm | -1.493 |
antioxid | -1.459 |
Token | : |
Token ID | 25 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
eele | +0.777 |
ilda | +0.761 |
ods | +0.677 |
lishes | +0.669 |
zl | +0.635 |
Neg logit contributions | |
hyde | -1.004 |
Hole | -0.867 |
rio | -0.837 |
antioxid | -0.829 |
warm | -0.813 |
Token | $ |
Token ID | 720 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
eele | +0.133 |
ilda | +0.130 |
lishes | +0.116 |
ods | +0.114 |
zl | +0.108 |
Neg logit contributions | |
hyde | -0.180 |
Hole | -0.161 |
rio | -0.154 |
warm | -0.150 |
antioxid | -0.148 |
Token | 8 |
Token ID | 23 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
hyde | +0.417 |
Hole | +0.351 |
rio | +0.331 |
warm | +0.321 |
antioxid | +0.320 |
Neg logit contributions | |
eele | -0.548 |
ilda | -0.533 |
lishes | -0.492 |
ods | -0.490 |
zl | -0.471 |
Token | / |
Token ID | 14 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
eele | +1.045 |
ilda | +1.032 |
ods | +0.905 |
lishes | +0.892 |
NB | +0.846 |
Neg logit contributions | |
hyde | -1.599 |
Hole | -1.375 |
antioxid | -1.315 |
rio | -1.305 |
warm | -1.283 |
Token | Michael |
Token ID | 13256 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
hyde | +2.153 |
Hole | +1.889 |
rio | +1.811 |
warm | +1.764 |
antioxid | +1.730 |
Neg logit contributions | |
eele | -1.912 |
ilda | -1.834 |
lishes | -1.670 |
ods | -1.650 |
opsis | -1.567 |
Token | K |
Token ID | 509 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
hyde | +0.105 |
Hole | +0.092 |
rio | +0.089 |
warm | +0.088 |
antioxid | +0.087 |
Neg logit contributions | |
eele | -0.067 |
ilda | -0.065 |
lishes | -0.057 |
ods | -0.057 |
zl | -0.054 |
Token | lim |
Token ID | 2475 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
hyde | +0.985 |
Hole | +0.821 |
rio | +0.746 |
antioxid | +0.746 |
warm | +0.741 |
Neg logit contributions | |
eele | -1.336 |
ilda | -1.319 |
ods | -1.213 |
lishes | -1.198 |
adle | -1.149 |
Token | enty |
Token ID | 3787 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
hyde | +1.250 |
Hole | +1.079 |
rio | +1.028 |
warm | +1.009 |
antioxid | +0.992 |
Neg logit contributions | |
eele | -1.203 |
ilda | -1.162 |
lishes | -1.072 |
ods | -1.042 |
zl | -1.003 |
Token | ev |
Token ID | 1990 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
eele | +0.553 |
ilda | +0.525 |
lishes | +0.444 |
ods | +0.440 |
zl | +0.400 |
Neg logit contributions | |
hyde | -1.373 |
Hole | -1.241 |
rio | -1.200 |
warm | -1.174 |
antioxid | -1.174 |
Token | / |
Token ID | 14 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
eele | +1.111 |
ilda | +1.056 |
lishes | +0.969 |
ods | +0.955 |
zl | +0.909 |
Neg logit contributions | |
hyde | -1.112 |
Hole | -0.971 |
rio | -0.928 |
warm | -0.906 |
antioxid | -0.879 |
Token | R |
Token ID | 49 |
Feature activation | +5.55e-03 |
Pos logit contributions | |
eele | +1.908 |
ilda | +1.851 |
lishes | +1.690 |
ods | +1.688 |
zl | +1.600 |
Neg logit contributions | |
hyde | -2.171 |
Hole | -1.870 |
rio | -1.770 |
warm | -1.753 |
antioxid | -1.734 |
Token | IA |
Token ID | 3539 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
hyde | +0.032 |
Hole | +0.027 |
rio | +0.026 |
warm | +0.025 |
antioxid | +0.025 |
Neg logit contributions | |
eele | -0.034 |
ilda | -0.033 |
lishes | -0.030 |
ods | -0.030 |
zl | -0.028 |
Token | Nov |
Token ID | 5267 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
eele | +2.207 |
ilda | +2.159 |
lishes | +1.961 |
ods | +1.951 |
zl | +1.858 |
Neg logit contributions | |
hyde | -2.639 |
Hole | -2.284 |
rio | -2.182 |
warm | -2.129 |
antioxid | -2.098 |
Token | ost |
Token ID | 455 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
ilda | +0.107 |
ods | +0.106 |
eele | +0.104 |
zl | +0.099 |
adle | +0.098 |
Neg logit contributions | |
hyde | -0.053 |
Hole | -0.041 |
rio | -0.037 |
warm | -0.036 |
fireplace | -0.035 |
Token | ewski |
Token ID | 46151 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
eele | +0.853 |
ilda | +0.798 |
ods | +0.695 |
lishes | +0.672 |
zl | +0.654 |
Neg logit contributions | |
hyde | -1.781 |
Hole | -1.594 |
rio | -1.534 |
antioxid | -1.522 |
warm | -1.489 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
eele | +0.924 |
ilda | +0.900 |
lishes | +0.835 |
ods | +0.809 |
zl | +0.773 |
Neg logit contributions | |
hyde | -0.977 |
Hole | -0.869 |
rio | -0.817 |
warm | -0.806 |
antioxid | -0.785 |
Token | " |
Token ID | 366 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
eele | +0.079 |
ilda | +0.077 |
lishes | +0.071 |
ods | +0.070 |
opsis | +0.067 |
Neg logit contributions | |
hyde | -0.069 |
Hole | -0.060 |
rio | -0.057 |
warm | -0.055 |
antioxid | -0.053 |
Token | In |
Token ID | 818 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
eele | +0.136 |
ilda | +0.133 |
lishes | +0.120 |
ods | +0.120 |
NB | +0.115 |
Neg logit contributions | |
hyde | -0.141 |
Hole | -0.121 |
rio | -0.116 |
antioxid | -0.113 |
warm | -0.112 |
Token | particular |
Token ID | 1948 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
eele | +0.107 |
ilda | +0.103 |
lishes | +0.094 |
ods | +0.094 |
zl | +0.089 |
Neg logit contributions | |
hyde | -0.106 |
Hole | -0.092 |
rio | -0.088 |
warm | -0.086 |
antioxid | -0.084 |
Token | they |
Token ID | 484 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
eele | +0.977 |
ilda | +0.945 |
lishes | +0.872 |
ods | +0.859 |
zl | +0.816 |
Neg logit contributions | |
hyde | -0.977 |
Hole | -0.848 |
rio | -0.808 |
warm | -0.785 |
antioxid | -0.774 |
Token | 're |
Token ID | 821 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
eele | +0.623 |
ilda | +0.612 |
ods | +0.557 |
lishes | +0.555 |
zl | +0.533 |
Neg logit contributions | |
hyde | -0.569 |
Hole | -0.482 |
rio | -0.456 |
antioxid | -0.450 |
warm | -0.444 |
Token | not |
Token ID | 407 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
eele | +0.706 |
ilda | +0.696 |
lishes | +0.627 |
ods | +0.626 |
zl | +0.602 |
Neg logit contributions | |
hyde | -0.679 |
Hole | -0.575 |
rio | -0.549 |
warm | -0.539 |
antioxid | -0.529 |
Token | in |
Token ID | 287 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
eele | +0.208 |
ilda | +0.203 |
lishes | +0.185 |
ods | +0.184 |
zl | +0.176 |
Neg logit contributions | |
hyde | -0.196 |
Hole | -0.167 |
rio | -0.159 |
warm | -0.156 |
antioxid | -0.153 |
Token | the |
Token ID | 262 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
hyde | +1.152 |
Hole | +0.996 |
rio | +0.947 |
warm | +0.925 |
antioxid | +0.910 |
Neg logit contributions | |
eele | -1.172 |
ilda | -1.132 |
lishes | -1.040 |
ods | -1.031 |
zl | -0.977 |
Token | large |
Token ID | 1588 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
hyde | +0.617 |
Hole | +0.520 |
rio | +0.499 |
warm | +0.484 |
antioxid | +0.475 |
Neg logit contributions | |
eele | -0.722 |
ilda | -0.702 |
lishes | -0.645 |
ods | -0.639 |
zl | -0.612 |
Token | and |
Token ID | 290 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
eele | +1.103 |
ilda | +1.069 |
lishes | +0.979 |
ods | +0.973 |
zl | +0.923 |
Neg logit contributions | |
hyde | -1.095 |
Hole | -0.937 |
rio | -0.897 |
warm | -0.870 |
antioxid | -0.864 |
Token | said |
Token ID | 531 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
eele | +1.406 |
ilda | +1.361 |
lishes | +1.235 |
ods | +1.225 |
zl | +1.165 |
Neg logit contributions | |
hyde | -1.510 |
Hole | -1.287 |
rio | -1.238 |
warm | -1.206 |
antioxid | -1.198 |
Token | that |
Token ID | 326 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
eele | +1.183 |
ilda | +1.144 |
lishes | +1.044 |
ods | +1.036 |
zl | +0.985 |
Neg logit contributions | |
hyde | -1.194 |
Hole | -1.026 |
rio | -0.983 |
warm | -0.956 |
antioxid | -0.945 |
Token | Exxon |
Token ID | 27879 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
eele | +0.555 |
ilda | +0.538 |
lishes | +0.494 |
ods | +0.490 |
zl | +0.467 |
Neg logit contributions | |
hyde | -0.504 |
Hole | -0.430 |
rio | -0.410 |
warm | -0.399 |
antioxid | -0.393 |
Token | Mobil |
Token ID | 47100 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
hyde | +0.812 |
Hole | +0.693 |
rio | +0.656 |
warm | +0.639 |
antioxid | +0.620 |
Neg logit contributions | |
eele | -0.990 |
ilda | -0.956 |
lishes | -0.884 |
ods | -0.879 |
zl | -0.839 |
Token | , |
Token ID | 11 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
hyde | +0.833 |
Hole | +0.710 |
rio | +0.674 |
warm | +0.656 |
antioxid | +0.643 |
Neg logit contributions | |
eele | -0.978 |
ilda | -0.948 |
lishes | -0.874 |
ods | -0.866 |
zl | -0.827 |
Token | the |
Token ID | 262 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
eele | +1.310 |
ilda | +1.277 |
lishes | +1.190 |
ods | +1.185 |
zl | +1.135 |
Neg logit contributions | |
hyde | -0.885 |
Hole | -0.719 |
rio | -0.686 |
warm | -0.659 |
antioxid | -0.656 |
Token | only |
Token ID | 691 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
hyde | +0.201 |
Hole | +0.169 |
rio | +0.161 |
warm | +0.157 |
antioxid | +0.154 |
Neg logit contributions | |
eele | -0.236 |
ilda | -0.230 |
lishes | -0.212 |
ods | -0.210 |
zl | -0.201 |
Token | other |
Token ID | 584 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
hyde | +0.492 |
Hole | +0.416 |
rio | +0.396 |
warm | +0.384 |
antioxid | +0.377 |
Neg logit contributions | |
eele | -0.595 |
ilda | -0.576 |
lishes | -0.532 |
ods | -0.528 |
zl | -0.505 |
Token | U |
Token ID | 471 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
hyde | +1.308 |
Hole | +1.105 |
rio | +1.048 |
warm | +1.017 |
antioxid | +0.998 |
Neg logit contributions | |
eele | -1.645 |
ilda | -1.596 |
lishes | -1.475 |
ods | -1.463 |
zl | -1.400 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
hyde | +0.164 |
Hole | +0.144 |
rio | +0.138 |
warm | +0.135 |
antioxid | +0.135 |
Neg logit contributions | |
eele | -0.119 |
ilda | -0.115 |
lishes | -0.103 |
ods | -0.102 |
zl | -0.096 |
Token |
|
Token ID | 198 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
eele | +0.476 |
ilda | +0.464 |
ods | +0.417 |
lishes | +0.413 |
NB | +0.398 |
Neg logit contributions | |
hyde | -0.547 |
Hole | -0.471 |
rio | -0.451 |
antioxid | -0.444 |
warm | -0.438 |
Token | The |
Token ID | 464 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
eele | +0.228 |
ilda | +0.221 |
lishes | +0.202 |
ods | +0.200 |
zl | +0.191 |
Neg logit contributions | |
hyde | -0.220 |
Hole | -0.189 |
rio | -0.181 |
warm | -0.176 |
antioxid | -0.173 |
Token | situation |
Token ID | 3074 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
hyde | +0.213 |
Hole | +0.179 |
rio | +0.171 |
warm | +0.166 |
antioxid | +0.163 |
Neg logit contributions | |
eele | -0.259 |
ilda | -0.251 |
lishes | -0.232 |
ods | -0.231 |
zl | -0.221 |
Token | remained |
Token ID | 6150 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
eele | +0.543 |
ilda | +0.527 |
lishes | +0.484 |
ods | +0.479 |
zl | +0.457 |
Neg logit contributions | |
hyde | -0.505 |
Hole | -0.431 |
rio | -0.411 |
warm | -0.400 |
antioxid | -0.395 |
Token | calm |
Token ID | 9480 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
eele | +1.262 |
ilda | +1.231 |
lishes | +1.129 |
ods | +1.117 |
zl | +1.064 |
Neg logit contributions | |
hyde | -1.188 |
Hole | -1.017 |
rio | -0.968 |
warm | -0.933 |
antioxid | -0.930 |
Token | in |
Token ID | 287 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
eele | +0.986 |
ilda | +0.958 |
lishes | +0.880 |
ods | +0.871 |
zl | +0.829 |
Neg logit contributions | |
hyde | -0.944 |
Hole | -0.811 |
rio | -0.773 |
warm | -0.749 |
antioxid | -0.742 |
Token | Chern |
Token ID | 37243 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
eele | +1.080 |
ilda | +1.046 |
lishes | +0.960 |
ods | +0.952 |
zl | +0.908 |
Neg logit contributions | |
hyde | -1.030 |
Hole | -0.876 |
rio | -0.842 |
warm | -0.819 |
antioxid | -0.803 |
Token | iv |
Token ID | 452 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
eele | +0.763 |
ilda | +0.738 |
lishes | +0.678 |
ods | +0.666 |
zl | +0.637 |
Neg logit contributions | |
hyde | -0.753 |
Hole | -0.651 |
rio | -0.625 |
warm | -0.604 |
antioxid | -0.593 |
Token | ts |
Token ID | 912 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
hyde | +0.794 |
Hole | +0.694 |
rio | +0.661 |
warm | +0.645 |
antioxid | +0.634 |
Neg logit contributions | |
eele | -0.743 |
ilda | -0.715 |
lishes | -0.654 |
ods | -0.641 |
zl | -0.612 |
Token | i |
Token ID | 72 |
Feature activation | +5.28e-03 |
Pos logit contributions | |
eele | +0.493 |
ilda | +0.478 |
lishes | +0.436 |
ods | +0.434 |
zl | +0.414 |
Neg logit contributions | |
hyde | -0.474 |
Hole | -0.407 |
rio | -0.387 |
warm | -0.378 |
antioxid | -0.372 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
hyde | +0.031 |
Hole | +0.026 |
rio | +0.025 |
warm | +0.025 |
antioxid | +0.024 |
Neg logit contributions | |
eele | -0.032 |
ilda | -0.031 |
lishes | -0.028 |
ods | -0.028 |
zl | -0.027 |
Token | at |
Token ID | 379 |
Feature activation | +3.70e-03 |
Pos logit contributions | |
eele | +0.644 |
ilda | +0.624 |
lishes | +0.570 |
ods | +0.567 |
opsis | +0.543 |
Neg logit contributions | |
hyde | -0.595 |
Hole | -0.507 |
rio | -0.483 |
warm | -0.469 |
antioxid | -0.468 |
Token | work |
Token ID | 670 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
hyde | +0.022 |
Hole | +0.019 |
rio | +0.018 |
warm | +0.018 |
antioxid | +0.017 |
Neg logit contributions | |
eele | -0.022 |
ilda | -0.021 |
lishes | -0.019 |
ods | -0.019 |
zl | -0.018 |
Token | ! |
Token ID | 0 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
hyde | +0.640 |
Hole | +0.550 |
rio | +0.524 |
warm | +0.510 |
antioxid | +0.503 |
Neg logit contributions | |
eele | -0.675 |
ilda | -0.654 |
lishes | -0.599 |
ods | -0.595 |
zl | -0.567 |
Token |
|
Token ID | 198 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
hyde | +0.878 |
Hole | +0.759 |
rio | +0.715 |
warm | +0.697 |
antioxid | +0.682 |
Neg logit contributions | |
eele | -0.982 |
ilda | -0.948 |
lishes | -0.880 |
ods | -0.865 |
zl | -0.825 |
Token |
|
Token ID | 198 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
eele | +0.192 |
ilda | +0.188 |
ods | +0.169 |
lishes | +0.168 |
zl | +0.160 |
Neg logit contributions | |
hyde | -0.219 |
Hole | -0.189 |
rio | -0.181 |
antioxid | -0.179 |
warm | -0.175 |
Token | Who |
Token ID | 8241 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
eele | +0.138 |
ilda | +0.134 |
lishes | +0.123 |
ods | +0.122 |
zl | +0.116 |
Neg logit contributions | |
hyde | -0.131 |
Hole | -0.113 |
rio | -0.108 |
warm | -0.105 |
antioxid | -0.103 |
Token | a |
Token ID | 64 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
eele | +3.917 |
ilda | +3.839 |
ods | +3.514 |
lishes | +3.459 |
opsis | +3.385 |
Neg logit contributions | |
hyde | -4.194 |
Hole | -3.513 |
rio | -3.416 |
antioxid | -3.357 |
warm | -3.320 |
Token | ! |
Token ID | 0 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
hyde | +0.739 |
Hole | +0.640 |
rio | +0.607 |
warm | +0.592 |
antioxid | +0.580 |
Neg logit contributions | |
eele | -0.817 |
ilda | -0.785 |
lishes | -0.728 |
ods | -0.714 |
zl | -0.682 |
Token | This |
Token ID | 770 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
eele | +0.806 |
ilda | +0.789 |
ods | +0.721 |
lishes | +0.711 |
zl | +0.685 |
Neg logit contributions | |
hyde | -0.759 |
Hole | -0.626 |
rio | -0.616 |
warm | -0.594 |
antioxid | -0.589 |
Token | is |
Token ID | 318 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
eele | +0.708 |
ilda | +0.686 |
lishes | +0.628 |
ods | +0.628 |
zl | +0.598 |
Neg logit contributions | |
hyde | -0.630 |
Hole | -0.533 |
rio | -0.511 |
warm | -0.497 |
antioxid | -0.489 |
Token | some |
Token ID | 617 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
eele | +2.023 |
ilda | +1.982 |
ods | +1.834 |
lishes | +1.793 |
opsis | +1.727 |
Neg logit contributions | |
hyde | -1.919 |
Hole | -1.590 |
rio | -1.524 |
warm | -1.486 |
antioxid | -1.476 |
Token | Chair |
Token ID | 9369 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
eele | +0.936 |
ilda | +0.910 |
lishes | +0.831 |
ods | +0.820 |
zl | +0.780 |
Neg logit contributions | |
hyde | -0.998 |
Hole | -0.852 |
rio | -0.825 |
warm | -0.799 |
antioxid | -0.788 |
Token | , |
Token ID | 11 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
hyde | +0.109 |
Hole | +0.094 |
rio | +0.089 |
warm | +0.088 |
antioxid | +0.086 |
Neg logit contributions | |
eele | -0.118 |
ilda | -0.114 |
lishes | -0.104 |
ods | -0.104 |
zl | -0.099 |
Token | Democratic |
Token ID | 4390 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
eele | +0.754 |
ilda | +0.731 |
lishes | +0.675 |
ods | +0.668 |
zl | +0.639 |
Neg logit contributions | |
hyde | -0.655 |
Hole | -0.554 |
rio | -0.530 |
warm | -0.512 |
antioxid | -0.504 |
Token | Senator |
Token ID | 8962 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
eele | +0.686 |
ilda | +0.666 |
lishes | +0.616 |
ods | +0.610 |
zl | +0.583 |
Neg logit contributions | |
hyde | -0.572 |
Hole | -0.483 |
rio | -0.460 |
warm | -0.445 |
antioxid | -0.438 |
Token | ial |
Token ID | 498 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
eele | +0.950 |
ilda | +0.923 |
lishes | +0.845 |
ods | +0.834 |
zl | +0.793 |
Neg logit contributions | |
hyde | -0.973 |
Hole | -0.835 |
rio | -0.802 |
warm | -0.776 |
antioxid | -0.769 |
Token | Campaign |
Token ID | 13718 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
eele | +0.480 |
ilda | +0.466 |
lishes | +0.431 |
ods | +0.427 |
zl | +0.409 |
Neg logit contributions | |
hyde | -0.375 |
Hole | -0.314 |
rio | -0.297 |
warm | -0.287 |
antioxid | -0.284 |
Token | Committee |
Token ID | 4606 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
eele | +2.991 |
ilda | +2.884 |
lishes | +2.605 |
ods | +2.553 |
zl | +2.397 |
Neg logit contributions | |
hyde | -4.489 |
Hole | -3.917 |
rio | -3.788 |
antioxid | -3.685 |
warm | -3.678 |
Token |
|
Token ID | 198 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
eele | +1.618 |
ilda | +1.567 |
lishes | +1.435 |
ods | +1.417 |
zl | +1.350 |
Neg logit contributions | |
hyde | -1.698 |
Hole | -1.457 |
rio | -1.402 |
warm | -1.360 |
antioxid | -1.345 |
Token |
|
Token ID | 198 |
Feature activation | +4.69e-03 |
Pos logit contributions | |
eele | +0.433 |
ilda | +0.423 |
ods | +0.381 |
lishes | +0.377 |
zl | +0.360 |
Neg logit contributions | |
hyde | -0.504 |
Hole | -0.433 |
rio | -0.415 |
antioxid | -0.413 |
warm | -0.402 |
Token | Comment |
Token ID | 21357 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
hyde | +0.028 |
Hole | +0.024 |
rio | +0.023 |
warm | +0.022 |
antioxid | +0.022 |
Neg logit contributions | |
eele | -0.028 |
ilda | -0.027 |
lishes | -0.025 |
ods | -0.024 |
zl | -0.023 |
Token | ing |
Token ID | 278 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
eele | +1.583 |
ilda | +1.533 |
lishes | +1.399 |
ods | +1.388 |
zl | +1.320 |
Neg logit contributions | |
hyde | -1.622 |
Hole | -1.395 |
rio | -1.339 |
warm | -1.303 |
antioxid | -1.293 |
Token | itz |
Token ID | 4224 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
eele | +1.011 |
ilda | +0.977 |
lishes | +0.898 |
ods | +0.894 |
zl | +0.849 |
Neg logit contributions | |
hyde | -0.973 |
Hole | -0.837 |
rio | -0.794 |
warm | -0.778 |
antioxid | -0.767 |
Token | - |
Token ID | 12 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
hyde | +0.087 |
Hole | +0.075 |
rio | +0.071 |
warm | +0.070 |
antioxid | +0.068 |
Neg logit contributions | |
eele | -0.092 |
ilda | -0.089 |
lishes | -0.082 |
ods | -0.081 |
zl | -0.077 |
Token | class |
Token ID | 4871 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
eele | +0.612 |
ilda | +0.590 |
lishes | +0.527 |
ods | +0.527 |
zl | +0.496 |
Neg logit contributions | |
hyde | -0.807 |
Hole | -0.710 |
rio | -0.677 |
warm | -0.664 |
antioxid | -0.662 |
Token | carriers |
Token ID | 16651 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
eele | +1.212 |
ilda | +1.182 |
ods | +1.089 |
lishes | +1.086 |
zl | +1.030 |
Neg logit contributions | |
hyde | -1.013 |
Hole | -0.847 |
rio | -0.801 |
warm | -0.773 |
antioxid | -0.765 |
Token | in |
Token ID | 287 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
eele | +0.299 |
ilda | +0.292 |
lishes | +0.266 |
ods | +0.265 |
zl | +0.253 |
Neg logit contributions | |
hyde | -0.277 |
Hole | -0.235 |
rio | -0.223 |
warm | -0.217 |
antioxid | -0.216 |
Token | service |
Token ID | 2139 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
hyde | +0.901 |
Hole | +0.761 |
rio | +0.724 |
warm | +0.702 |
antioxid | +0.690 |
Neg logit contributions | |
eele | -1.092 |
ilda | -1.061 |
lishes | -0.978 |
ods | -0.970 |
zl | -0.928 |
Token | ( |
Token ID | 357 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
eele | +3.778 |
ilda | +3.678 |
ods | +3.360 |
lishes | +3.332 |
opsis | +3.203 |
Neg logit contributions | |
hyde | -3.799 |
Hole | -3.173 |
rio | -3.079 |
antioxid | -2.928 |
warm | -2.923 |
Token | CV |
Token ID | 33538 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
eele | +0.250 |
ilda | +0.243 |
lishes | +0.221 |
ods | +0.220 |
zl | +0.209 |
Neg logit contributions | |
hyde | -0.255 |
Hole | -0.220 |
rio | -0.209 |
antioxid | -0.203 |
warm | -0.203 |
Token | N |
Token ID | 45 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
eele | +1.423 |
ilda | +1.385 |
ods | +1.249 |
lishes | +1.238 |
NB | +1.188 |
Neg logit contributions | |
hyde | -1.635 |
Hole | -1.410 |
rio | -1.339 |
warm | -1.314 |
antioxid | -1.312 |
Token | 68 |
Token ID | 8257 |
Feature activation | -3.04e-03 |
Pos logit contributions | |
hyde | +0.923 |
Hole | +0.801 |
rio | +0.767 |
warm | +0.748 |
antioxid | +0.736 |
Neg logit contributions | |
eele | -0.867 |
ilda | -0.837 |
lishes | -0.764 |
ods | -0.757 |
zl | -0.718 |
Token | - |
Token ID | 12 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
eele | +0.017 |
ilda | +0.017 |
lishes | +0.015 |
ods | +0.015 |
zl | +0.014 |
Neg logit contributions | |
hyde | -0.019 |
Hole | -0.016 |
rio | -0.015 |
warm | -0.015 |
antioxid | -0.015 |
Token | not |
Token ID | 407 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
eele | +0.123 |
ilda | +0.120 |
lishes | +0.109 |
ods | +0.109 |
zl | +0.103 |
Neg logit contributions | |
hyde | -0.133 |
Hole | -0.115 |
rio | -0.110 |
warm | -0.107 |
antioxid | -0.105 |
Token | only |
Token ID | 691 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
hyde | +0.267 |
Hole | +0.229 |
rio | +0.216 |
warm | +0.211 |
antioxid | +0.208 |
Neg logit contributions | |
eele | -0.303 |
ilda | -0.294 |
lishes | -0.271 |
ods | -0.269 |
zl | -0.257 |
Token | their |
Token ID | 511 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
hyde | +0.678 |
Hole | +0.586 |
rio | +0.559 |
warm | +0.545 |
antioxid | +0.536 |
Neg logit contributions | |
eele | -0.673 |
ilda | -0.651 |
lishes | -0.596 |
ods | -0.591 |
zl | -0.562 |
Token | legal |
Token ID | 2742 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
hyde | +0.316 |
Hole | +0.263 |
rio | +0.249 |
warm | +0.243 |
antioxid | +0.237 |
Neg logit contributions | |
eele | -0.400 |
ilda | -0.391 |
lishes | -0.359 |
ods | -0.359 |
zl | -0.344 |
Token | headquarters |
Token ID | 10043 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
hyde | +0.202 |
Hole | +0.167 |
rio | +0.157 |
warm | +0.153 |
antioxid | +0.149 |
Neg logit contributions | |
eele | -0.288 |
ilda | -0.281 |
lishes | -0.260 |
ods | -0.259 |
zl | -0.248 |
Token | but |
Token ID | 475 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
hyde | +0.156 |
Hole | +0.133 |
rio | +0.127 |
warm | +0.123 |
antioxid | +0.121 |
Neg logit contributions | |
eele | -0.176 |
ilda | -0.170 |
lishes | -0.157 |
ods | -0.155 |
zl | -0.148 |
Token | , |
Token ID | 11 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
eele | +3.412 |
ilda | +3.334 |
lishes | +3.015 |
ods | +3.003 |
zl | +2.847 |
Neg logit contributions | |
hyde | -4.221 |
Hole | -3.662 |
rio | -3.500 |
warm | -3.460 |
antioxid | -3.367 |
Token | more |
Token ID | 517 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
eele | +0.902 |
ilda | +0.879 |
ods | +0.797 |
lishes | +0.796 |
zl | +0.754 |
Neg logit contributions | |
hyde | -0.948 |
Hole | -0.810 |
rio | -0.777 |
warm | -0.758 |
antioxid | -0.746 |
Token | significantly |
Token ID | 5566 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
eele | +1.769 |
ilda | +1.733 |
ods | +1.582 |
lishes | +1.580 |
opsis | +1.510 |
Neg logit contributions | |
hyde | -1.493 |
Hole | -1.239 |
rio | -1.174 |
warm | -1.150 |
antioxid | -1.115 |
Token | , |
Token ID | 11 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
eele | +1.711 |
ilda | +1.654 |
lishes | +1.523 |
ods | +1.503 |
zl | +1.431 |
Neg logit contributions | |
hyde | -1.619 |
Hole | -1.399 |
rio | -1.336 |
warm | -1.297 |
antioxid | -1.292 |
Token | some |
Token ID | 617 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
eele | +0.531 |
ilda | +0.515 |
lishes | +0.471 |
ods | +0.467 |
zl | +0.444 |
Neg logit contributions | |
hyde | -0.562 |
Hole | -0.484 |
rio | -0.464 |
warm | -0.453 |
antioxid | -0.443 |
Token | as |
Token ID | 355 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
eele | +2.550 |
ilda | +2.490 |
ods | +2.248 |
lishes | +2.186 |
zl | +2.096 |
Neg logit contributions | |
hyde | -3.200 |
Hole | -2.711 |
rio | -2.636 |
warm | -2.562 |
antioxid | -2.549 |
Token | I |
Token ID | 314 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
hyde | +1.510 |
Hole | +1.334 |
rio | +1.246 |
warm | +1.220 |
antioxid | +1.193 |
Neg logit contributions | |
eele | -1.564 |
ilda | -1.516 |
lishes | -1.395 |
ods | -1.366 |
zl | -1.309 |
Token | was |
Token ID | 373 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
hyde | +0.980 |
Hole | +0.842 |
rio | +0.803 |
warm | +0.783 |
antioxid | +0.782 |
Neg logit contributions | |
eele | -0.974 |
ilda | -0.948 |
lishes | -0.864 |
ods | -0.861 |
zl | -0.818 |
Token | thinking |
Token ID | 3612 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
hyde | +0.712 |
Hole | +0.624 |
rio | +0.600 |
warm | +0.587 |
antioxid | +0.580 |
Neg logit contributions | |
eele | -0.558 |
ilda | -0.539 |
lishes | -0.486 |
ods | -0.481 |
zl | -0.454 |
Token | [ |
Token ID | 685 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
eele | +2.257 |
ilda | +2.207 |
ods | +2.008 |
lishes | +1.962 |
zl | +1.891 |
Neg logit contributions | |
hyde | -2.429 |
Hole | -2.074 |
rio | -2.011 |
warm | -1.945 |
antioxid | -1.921 |
Token | about |
Token ID | 10755 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
eele | +1.971 |
ilda | +1.920 |
ods | +1.744 |
lishes | +1.725 |
zl | +1.655 |
Neg logit contributions | |
hyde | -2.296 |
Hole | -1.999 |
rio | -1.905 |
antioxid | -1.882 |
warm | -1.843 |
Token | it |
Token ID | 340 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
eele | +3.803 |
ilda | +3.708 |
ods | +3.412 |
lishes | +3.340 |
zl | +3.230 |
Neg logit contributions | |
hyde | -3.959 |
Hole | -3.365 |
rio | -3.268 |
warm | -3.192 |
antioxid | -3.187 |
Token | ] |
Token ID | 60 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
eele | +1.091 |
ilda | +1.055 |
lishes | +0.963 |
ods | +0.955 |
zl | +0.907 |
Neg logit contributions | |
hyde | -1.150 |
Hole | -0.997 |
rio | -0.953 |
warm | -0.930 |
antioxid | -0.917 |
Token | everything |
Token ID | 2279 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
eele | +0.434 |
ilda | +0.420 |
lishes | +0.388 |
ods | +0.384 |
zl | +0.367 |
Neg logit contributions | |
hyde | -0.365 |
Hole | -0.311 |
rio | -0.294 |
warm | -0.287 |
antioxid | -0.281 |
Token | got |
Token ID | 1392 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
eele | +1.322 |
ilda | +1.294 |
ods | +1.180 |
lishes | +1.178 |
zl | +1.124 |
Neg logit contributions | |
hyde | -1.265 |
Hole | -1.061 |
rio | -1.036 |
warm | -0.986 |
antioxid | -0.985 |
Token | huge |
Token ID | 3236 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
hyde | +0.541 |
Hole | +0.453 |
rio | +0.432 |
warm | +0.419 |
antioxid | +0.414 |
Neg logit contributions | |
eele | -0.610 |
ilda | -0.594 |
lishes | -0.548 |
ods | -0.544 |
zl | -0.521 |