Token | him |
Token ID | 683 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
Rue | +0.124 |
yss | +0.119 |
Jung | +0.111 |
nir | +0.107 |
Tags | +0.106 |
Neg logit contributions | |
sbm | -0.148 |
bro | -0.142 |
Cub | -0.135 |
worth | -0.128 |
\/ | -0.127 |
Token | on |
Token ID | 319 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Rue | +0.525 |
yss | +0.503 |
Jung | +0.469 |
nir | +0.448 |
Tags | +0.444 |
Neg logit contributions | |
sbm | -0.721 |
bro | -0.691 |
Cub | -0.662 |
worth | -0.631 |
\/ | -0.621 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Rue | +0.547 |
yss | +0.517 |
Jung | +0.471 |
nir | +0.441 |
Tags | +0.436 |
Neg logit contributions | |
sbm | -1.158 |
bro | -1.115 |
Cub | -1.076 |
worth | -1.034 |
\/ | -1.019 |
Token | at |
Token ID | 379 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
Rue | +1.655 |
yss | +1.584 |
Jung | +1.504 |
nir | +1.444 |
Tags | +1.437 |
Neg logit contributions | |
sbm | -1.671 |
bro | -1.572 |
Cub | -1.501 |
worth | -1.419 |
\/ | -1.381 |
Token | @ |
Token ID | 2488 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
sbm | +0.027 |
bro | +0.025 |
Cub | +0.024 |
worth | +0.023 |
\/ | +0.022 |
Neg logit contributions | |
Rue | -0.028 |
yss | -0.028 |
Jung | -0.026 |
nir | -0.025 |
Tags | -0.025 |
Token | Future |
Token ID | 29783 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
Rue | +0.695 |
yss | +0.671 |
Jung | +0.634 |
nir | +0.611 |
Tags | +0.607 |
Neg logit contributions | |
sbm | -0.655 |
bro | -0.621 |
Cub | -0.590 |
worth | -0.557 |
\/ | -0.545 |
Token | Cr |
Token ID | 13916 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
sbm | +3.513 |
bro | +3.378 |
Cub | +3.300 |
worth | +3.074 |
\/ | +2.980 |
Neg logit contributions | |
Rue | -3.438 |
yss | -3.268 |
Jung | -3.103 |
refriger | -2.979 |
nir | -2.929 |
Token | imes |
Token ID | 999 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
sbm | +0.648 |
bro | +0.609 |
Cub | +0.576 |
worth | +0.541 |
\/ | +0.527 |
Neg logit contributions | |
Rue | -0.868 |
yss | -0.845 |
Jung | -0.800 |
nir | -0.775 |
Tags | -0.770 |
Token | . |
Token ID | 13 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
Rue | +0.377 |
yss | +0.364 |
Jung | +0.344 |
nir | +0.330 |
Tags | +0.328 |
Neg logit contributions | |
sbm | -0.372 |
bro | -0.354 |
Cub | -0.337 |
worth | -0.318 |
\/ | -0.311 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
sbm | +0.231 |
bro | +0.220 |
Cub | +0.210 |
worth | +0.200 |
\/ | +0.196 |
Neg logit contributions | |
Rue | -0.207 |
yss | -0.200 |
Jung | -0.186 |
nir | -0.180 |
refriger | -0.177 |
Token | An |
Token ID | 2025 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
Rue | +0.389 |
yss | +0.376 |
Jung | +0.355 |
nir | +0.341 |
refriger | +0.338 |
Neg logit contributions | |
sbm | -0.372 |
bro | -0.355 |
Cub | -0.337 |
worth | -0.318 |
\/ | -0.311 |
Token | � |
Token ID | 250 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
sbm | +1.081 |
bro | +1.027 |
Cub | +0.976 |
worth | +0.923 |
\/ | +0.904 |
Neg logit contributions | |
Rue | -1.100 |
yss | -1.061 |
Jung | -1.002 |
nir | -0.964 |
Tags | -0.958 |
Token | When |
Token ID | 2215 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
sbm | +0.492 |
bro | +0.465 |
Cub | +0.440 |
worth | +0.416 |
\/ | +0.409 |
Neg logit contributions | |
Rue | -0.531 |
yss | -0.512 |
Jung | -0.484 |
nir | -0.467 |
Tags | -0.463 |
Token | you |
Token ID | 345 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
sbm | +0.020 |
bro | +0.019 |
Cub | +0.018 |
worth | +0.017 |
\/ | +0.016 |
Neg logit contributions | |
Rue | -0.021 |
yss | -0.020 |
Jung | -0.019 |
nir | -0.018 |
Tags | -0.018 |
Token | watch |
Token ID | 2342 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
sbm | +0.676 |
bro | +0.650 |
Cub | +0.613 |
worth | +0.588 |
\/ | +0.579 |
Neg logit contributions | |
Rue | -0.589 |
yss | -0.574 |
Jung | -0.528 |
Tags | -0.513 |
nir | -0.509 |
Token | Sarah |
Token ID | 10490 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Rue | +0.646 |
yss | +0.622 |
Jung | +0.587 |
nir | +0.563 |
Tags | +0.560 |
Neg logit contributions | |
sbm | -0.671 |
bro | -0.637 |
Cub | -0.607 |
worth | -0.575 |
\/ | -0.563 |
Token | Huckabee |
Token ID | 38253 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
sbm | +0.988 |
bro | +0.948 |
Cub | +0.906 |
worth | +0.864 |
\/ | +0.850 |
Neg logit contributions | |
Rue | -0.831 |
yss | -0.810 |
Jung | -0.745 |
nir | -0.737 |
Tags | -0.725 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
sbm | +2.775 |
bro | +2.617 |
Cub | +2.454 |
worth | +2.418 |
\/ | +2.282 |
Neg logit contributions | |
Rue | -3.358 |
yss | -3.290 |
Jung | -3.038 |
nir | -3.004 |
refriger | -2.949 |
Token | right |
Token ID | 826 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
sbm | +1.065 |
bro | +1.025 |
Cub | +0.973 |
worth | +0.934 |
\/ | +0.912 |
Neg logit contributions | |
Rue | -1.014 |
yss | -0.990 |
Jung | -0.920 |
nir | -0.895 |
Tags | -0.888 |
Token | now |
Token ID | 783 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
sbm | +0.487 |
bro | +0.462 |
Cub | +0.429 |
worth | +0.407 |
\/ | +0.397 |
Neg logit contributions | |
Rue | -0.682 |
yss | -0.662 |
Jung | -0.627 |
nir | -0.611 |
Tags | -0.610 |
Token | , |
Token ID | 11 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
Rue | +0.174 |
yss | +0.167 |
Jung | +0.157 |
nir | +0.151 |
Tags | +0.150 |
Neg logit contributions | |
sbm | -0.193 |
bro | -0.184 |
Cub | -0.176 |
worth | -0.167 |
\/ | -0.164 |
Token | you |
Token ID | 345 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
sbm | +0.247 |
bro | +0.235 |
Cub | +0.222 |
worth | +0.209 |
\/ | +0.203 |
Neg logit contributions | |
Rue | -0.308 |
yss | -0.299 |
Jung | -0.283 |
nir | -0.275 |
Tags | -0.274 |
Token | the |
Token ID | 262 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
Rue | +0.161 |
yss | +0.156 |
Jung | +0.146 |
nir | +0.141 |
Tags | +0.140 |
Neg logit contributions | |
sbm | -0.175 |
bro | -0.167 |
Cub | -0.159 |
worth | -0.150 |
\/ | -0.148 |
Token | dungeon |
Token ID | 18974 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
sbm | +0.639 |
bro | +0.612 |
Cub | +0.582 |
worth | +0.554 |
\/ | +0.543 |
Neg logit contributions | |
Rue | -0.537 |
yss | -0.520 |
Jung | -0.484 |
nir | -0.468 |
Tags | -0.466 |
Token | ( |
Token ID | 357 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
sbm | +1.293 |
bro | +1.251 |
Cub | +1.176 |
worth | +1.123 |
\/ | +1.103 |
Neg logit contributions | |
Rue | -1.271 |
yss | -1.232 |
Jung | -1.146 |
nir | -1.110 |
Tags | -1.109 |
Token | what |
Token ID | 10919 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
sbm | +0.443 |
bro | +0.423 |
Cub | +0.399 |
worth | +0.377 |
\/ | +0.365 |
Neg logit contributions | |
Rue | -0.515 |
yss | -0.499 |
Jung | -0.472 |
nir | -0.453 |
Tags | -0.452 |
Token | we |
Token ID | 356 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Rue | +0.182 |
yss | +0.176 |
Jung | +0.165 |
nir | +0.158 |
Tags | +0.158 |
Neg logit contributions | |
sbm | -0.182 |
bro | -0.174 |
Cub | -0.165 |
worth | -0.156 |
\/ | -0.153 |
Token | call |
Token ID | 869 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
sbm | +0.832 |
bro | +0.800 |
Cub | +0.750 |
worth | +0.711 |
\/ | +0.696 |
Neg logit contributions | |
Rue | -0.953 |
yss | -0.926 |
Jung | -0.870 |
nir | -0.842 |
Tags | -0.840 |
Token | our |
Token ID | 674 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
sbm | +2.991 |
bro | +2.892 |
Cub | +2.712 |
worth | +2.561 |
\/ | +2.518 |
Neg logit contributions | |
Rue | -2.802 |
yss | -2.776 |
Jung | -2.518 |
Tags | -2.514 |
nir | -2.491 |
Token | tv |
Token ID | 31557 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
sbm | +0.360 |
bro | +0.344 |
Cub | +0.328 |
worth | +0.311 |
\/ | +0.305 |
Neg logit contributions | |
Rue | -0.316 |
yss | -0.306 |
Jung | -0.284 |
nir | -0.275 |
Tags | -0.274 |
Token | room |
Token ID | 2119 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Rue | +0.231 |
yss | +0.223 |
Jung | +0.209 |
nir | +0.200 |
Tags | +0.200 |
Neg logit contributions | |
sbm | -0.257 |
bro | -0.246 |
Cub | -0.234 |
worth | -0.222 |
\/ | -0.218 |
Token | in |
Token ID | 287 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
sbm | +1.554 |
bro | +1.505 |
Cub | +1.424 |
worth | +1.361 |
\/ | +1.337 |
Neg logit contributions | |
Rue | -1.337 |
yss | -1.302 |
Jung | -1.200 |
Tags | -1.174 |
nir | -1.164 |
Token | the |
Token ID | 262 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
sbm | +0.118 |
bro | +0.113 |
Cub | +0.108 |
worth | +0.102 |
\/ | +0.100 |
Neg logit contributions | |
Rue | -0.109 |
yss | -0.105 |
Jung | -0.098 |
nir | -0.095 |
Tags | -0.095 |
Token | publish |
Token ID | 7715 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
Rue | +0.642 |
yss | +0.618 |
Jung | +0.582 |
nir | +0.559 |
Tags | +0.556 |
Neg logit contributions | |
sbm | -0.681 |
bro | -0.648 |
Cub | -0.617 |
worth | -0.585 |
\/ | -0.573 |
Token | it |
Token ID | 340 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
sbm | +0.618 |
bro | +0.589 |
Cub | +0.561 |
worth | +0.533 |
\/ | +0.522 |
Neg logit contributions | |
Rue | -0.567 |
yss | -0.546 |
Jung | -0.514 |
nir | -0.493 |
Tags | -0.490 |
Token | on |
Token ID | 319 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
sbm | +0.114 |
bro | +0.109 |
Cub | +0.104 |
worth | +0.099 |
\/ | +0.097 |
Neg logit contributions | |
Rue | -0.108 |
yss | -0.104 |
Jung | -0.097 |
nir | -0.094 |
Tags | -0.094 |
Token | Ar |
Token ID | 943 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
sbm | +0.476 |
bro | +0.455 |
Cub | +0.432 |
worth | +0.410 |
\/ | +0.406 |
Neg logit contributions | |
Rue | -0.449 |
yss | -0.440 |
Jung | -0.408 |
nir | -0.396 |
Tags | -0.392 |
Token | X |
Token ID | 55 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
sbm | +0.263 |
bro | +0.252 |
Cub | +0.237 |
worth | +0.222 |
\/ | +0.218 |
Neg logit contributions | |
Rue | -0.301 |
yss | -0.288 |
Jung | -0.275 |
nir | -0.264 |
Tags | -0.264 |
Token | iv |
Token ID | 452 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
Rue | +0.527 |
yss | +0.515 |
Jung | +0.493 |
nir | +0.480 |
Tags | +0.476 |
Neg logit contributions | |
sbm | -0.240 |
bro | -0.223 |
Cub | -0.205 |
worth | -0.187 |
\/ | -0.178 |
Token | , |
Token ID | 11 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
sbm | +2.788 |
bro | +2.722 |
Cub | +2.609 |
worth | +2.426 |
\/ | +2.411 |
Neg logit contributions | |
Rue | -2.950 |
yss | -2.886 |
Jung | -2.689 |
nir | -2.617 |
ukong | -2.574 |
Token | before |
Token ID | 878 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
sbm | +0.371 |
bro | +0.355 |
Cub | +0.338 |
worth | +0.321 |
\/ | +0.314 |
Neg logit contributions | |
Rue | -0.361 |
yss | -0.352 |
Jung | -0.328 |
nir | -0.319 |
Tags | -0.316 |
Token | sending |
Token ID | 7216 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
Rue | +0.339 |
yss | +0.329 |
Jung | +0.308 |
nir | +0.298 |
Tags | +0.297 |
Neg logit contributions | |
sbm | -0.340 |
bro | -0.326 |
Cub | -0.310 |
worth | -0.293 |
\/ | -0.288 |
Token | it |
Token ID | 340 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
sbm | +0.331 |
bro | +0.316 |
Cub | +0.295 |
worth | +0.277 |
\/ | +0.275 |
Neg logit contributions | |
Rue | -0.397 |
yss | -0.387 |
Jung | -0.363 |
nir | -0.354 |
Tags | -0.351 |
Token | to |
Token ID | 284 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
sbm | +0.014 |
bro | +0.014 |
Cub | +0.013 |
worth | +0.013 |
\/ | +0.012 |
Neg logit contributions | |
Rue | -0.012 |
yss | -0.012 |
Jung | -0.011 |
Tags | -0.011 |
nir | -0.011 |
Token | for |
Token ID | 329 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
Rue | +0.334 |
yss | +0.325 |
Jung | +0.305 |
nir | +0.297 |
Tags | +0.294 |
Neg logit contributions | |
sbm | -0.296 |
bro | -0.282 |
Cub | -0.267 |
worth | -0.251 |
\/ | -0.247 |
Token | publication |
Token ID | 9207 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
sbm | +0.534 |
bro | +0.515 |
Cub | +0.491 |
worth | +0.464 |
\/ | +0.455 |
Neg logit contributions | |
Rue | -0.513 |
yss | -0.498 |
Jung | -0.462 |
nir | -0.455 |
Tags | -0.446 |
Token | ; |
Token ID | 26 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
sbm | +0.398 |
bro | +0.382 |
Cub | +0.365 |
worth | +0.346 |
\/ | +0.341 |
Neg logit contributions | |
Rue | -0.348 |
yss | -0.339 |
Jung | -0.313 |
nir | -0.306 |
Tags | -0.301 |
Token | ar |
Token ID | 610 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
sbm | +0.774 |
bro | +0.739 |
Cub | +0.707 |
worth | +0.673 |
\/ | +0.660 |
Neg logit contributions | |
Rue | -0.633 |
yss | -0.610 |
Jung | -0.564 |
nir | -0.555 |
Tags | -0.539 |
Token | X |
Token ID | 55 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
sbm | +1.020 |
bro | +0.984 |
Cub | +0.927 |
worth | +0.877 |
\/ | +0.860 |
Neg logit contributions | |
Rue | -1.078 |
yss | -1.031 |
Jung | -0.980 |
nir | -0.944 |
refriger | -0.936 |
Token | iv |
Token ID | 452 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
Rue | +0.140 |
yss | +0.136 |
Jung | +0.131 |
nir | +0.127 |
Tags | +0.126 |
Neg logit contributions | |
sbm | -0.062 |
bro | -0.057 |
Cub | -0.052 |
worth | -0.048 |
\/ | -0.046 |
Token | : |
Token ID | 25 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
sbm | +2.307 |
bro | +2.223 |
Cub | +2.075 |
\/ | +1.940 |
worth | +1.915 |
Neg logit contributions | |
Rue | -3.239 |
yss | -3.132 |
Jung | -2.960 |
nir | -2.950 |
Tags | -2.864 |
Token | 14 |
Token ID | 1478 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
sbm | +1.095 |
bro | +1.044 |
Cub | +0.973 |
worth | +0.925 |
\/ | +0.903 |
Neg logit contributions | |
Rue | -1.281 |
yss | -1.235 |
Jung | -1.175 |
nir | -1.140 |
Tags | -1.120 |
Token | 05 |
Token ID | 2713 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
sbm | +0.794 |
bro | +0.755 |
Cub | +0.708 |
worth | +0.669 |
\/ | +0.659 |
Neg logit contributions | |
Rue | -0.990 |
yss | -0.967 |
Jung | -0.909 |
nir | -0.881 |
refriger | -0.875 |
Token | . |
Token ID | 13 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
sbm | +0.800 |
bro | +0.764 |
Cub | +0.726 |
worth | +0.688 |
\/ | +0.677 |
Neg logit contributions | |
Rue | -0.785 |
yss | -0.759 |
Jung | -0.712 |
nir | -0.686 |
Tags | -0.679 |
Token | 7 |
Token ID | 22 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
sbm | +0.416 |
bro | +0.391 |
Cub | +0.368 |
worth | +0.346 |
\/ | +0.337 |
Neg logit contributions | |
Rue | -0.529 |
yss | -0.514 |
Jung | -0.487 |
nir | -0.472 |
refriger | -0.467 |
Token | he |
Token ID | 339 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
sbm | +0.187 |
bro | +0.180 |
Cub | +0.168 |
worth | +0.159 |
\/ | +0.153 |
Neg logit contributions | |
Rue | -0.247 |
yss | -0.242 |
Jung | -0.227 |
nir | -0.221 |
Tags | -0.220 |
Token | spr |
Token ID | 7500 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
sbm | +0.642 |
bro | +0.628 |
Cub | +0.588 |
worth | +0.562 |
\/ | +0.542 |
Neg logit contributions | |
Rue | -0.700 |
yss | -0.686 |
Jung | -0.636 |
nir | -0.620 |
Tags | -0.618 |
Token | ained |
Token ID | 1328 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
sbm | +1.253 |
bro | +1.192 |
Cub | +1.119 |
worth | +1.055 |
\/ | +1.033 |
Neg logit contributions | |
Rue | -1.580 |
yss | -1.531 |
Jung | -1.455 |
nir | -1.400 |
Tags | -1.399 |
Token | his |
Token ID | 465 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
sbm | +0.778 |
bro | +0.753 |
Cub | +0.714 |
worth | +0.677 |
\/ | +0.663 |
Neg logit contributions | |
Rue | -0.708 |
yss | -0.694 |
Jung | -0.640 |
nir | -0.618 |
Tags | -0.616 |
Token | left |
Token ID | 1364 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
sbm | +1.014 |
bro | +0.978 |
Cub | +0.932 |
worth | +0.879 |
\/ | +0.871 |
Neg logit contributions | |
Rue | -0.916 |
yss | -0.905 |
Jung | -0.825 |
Tags | -0.810 |
nir | -0.805 |
Token | ACL |
Token ID | 17382 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
sbm | +1.789 |
bro | +1.738 |
Cub | +1.667 |
worth | +1.564 |
\/ | +1.551 |
Neg logit contributions | |
Rue | -1.618 |
yss | -1.591 |
Jung | -1.446 |
Tags | -1.423 |
nir | -1.412 |
Token | after |
Token ID | 706 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
sbm | +2.722 |
bro | +2.679 |
Cub | +2.507 |
worth | +2.376 |
\/ | +2.355 |
Neg logit contributions | |
Rue | -2.674 |
yss | -2.627 |
Jung | -2.436 |
nir | -2.405 |
Tags | -2.365 |
Token | a |
Token ID | 257 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
sbm | +0.537 |
bro | +0.518 |
Cub | +0.492 |
worth | +0.468 |
\/ | +0.456 |
Neg logit contributions | |
Rue | -0.515 |
yss | -0.502 |
Jung | -0.467 |
nir | -0.453 |
Tags | -0.450 |
Token | vicious |
Token ID | 17686 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
sbm | +0.954 |
bro | +0.925 |
Cub | +0.879 |
worth | +0.830 |
\/ | +0.814 |
Neg logit contributions | |
Rue | -0.953 |
yss | -0.935 |
Jung | -0.867 |
nir | -0.847 |
Tags | -0.843 |
Token | back |
Token ID | 736 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
sbm | +1.644 |
bro | +1.628 |
Cub | +1.547 |
worth | +1.461 |
\/ | +1.438 |
Neg logit contributions | |
Rue | -1.608 |
yss | -1.597 |
Jung | -1.461 |
nir | -1.441 |
Tags | -1.428 |
Token | hand |
Token ID | 4993 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
sbm | +1.315 |
bro | +1.260 |
Cub | +1.186 |
worth | +1.117 |
\/ | +1.092 |
Neg logit contributions | |
Rue | -1.443 |
yss | -1.402 |
Jung | -1.323 |
Tags | -1.269 |
nir | -1.268 |
Token | TW |
Token ID | 17306 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
sbm | +0.793 |
bro | +0.754 |
Cub | +0.715 |
worth | +0.678 |
\/ | +0.660 |
Neg logit contributions | |
Rue | -0.866 |
yss | -0.843 |
Jung | -0.795 |
nir | -0.771 |
Tags | -0.764 |
Token | EL |
Token ID | 3698 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
sbm | +0.194 |
bro | +0.187 |
Cub | +0.177 |
worth | +0.167 |
EEE | +0.165 |
Neg logit contributions | |
Rue | -0.196 |
yss | -0.190 |
Jung | -0.179 |
nir | -0.173 |
Tags | -0.171 |
Token | VE |
Token ID | 6089 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
sbm | +0.844 |
bro | +0.804 |
Cub | +0.757 |
worth | +0.711 |
EEE | +0.696 |
Neg logit contributions | |
Rue | -1.054 |
yss | -1.024 |
Jung | -0.973 |
nir | -0.944 |
Tags | -0.931 |
Token | ) |
Token ID | 8 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Rue | +0.197 |
yss | +0.189 |
Jung | +0.177 |
nir | +0.170 |
Tags | +0.168 |
Neg logit contributions | |
sbm | -0.235 |
bro | -0.225 |
Cub | -0.215 |
worth | -0.205 |
\/ | -0.201 |
Token | quarterback |
Token ID | 7880 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
sbm | +1.278 |
bro | +1.247 |
Cub | +1.176 |
worth | +1.117 |
\/ | +1.101 |
Neg logit contributions | |
Rue | -1.180 |
yss | -1.170 |
Jung | -1.059 |
nir | -1.046 |
Tags | -1.024 |
Token | hur |
Token ID | 6990 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
sbm | +0.644 |
bro | +0.628 |
Cub | +0.579 |
worth | +0.545 |
\/ | +0.542 |
Neg logit contributions | |
yss | -0.764 |
Rue | -0.761 |
Jung | -0.691 |
nir | -0.686 |
Tags | -0.677 |
Token | ries |
Token ID | 1678 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
sbm | +2.467 |
bro | +2.356 |
Cub | +2.229 |
worth | +2.056 |
\/ | +2.029 |
Neg logit contributions | |
Rue | -3.060 |
yss | -2.970 |
Jung | -2.815 |
nir | -2.700 |
refriger | -2.682 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
sbm | +0.496 |
bro | +0.475 |
Cub | +0.451 |
worth | +0.432 |
\/ | +0.423 |
Neg logit contributions | |
Rue | -0.472 |
yss | -0.459 |
Jung | -0.427 |
nir | -0.415 |
Tags | -0.409 |
Token | He |
Token ID | 679 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
sbm | +1.241 |
bro | +1.182 |
Cub | +1.132 |
worth | +1.084 |
\/ | +1.057 |
Neg logit contributions | |
yss | -1.101 |
Rue | -1.068 |
nir | -0.976 |
Jung | -0.973 |
refriger | -0.964 |
Token | is |
Token ID | 318 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
sbm | +0.877 |
bro | +0.850 |
Cub | +0.797 |
worth | +0.768 |
\/ | +0.746 |
Neg logit contributions | |
Rue | -0.838 |
yss | -0.817 |
Jung | -0.760 |
nir | -0.735 |
Tags | -0.728 |
Token | a |
Token ID | 257 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
sbm | +0.103 |
bro | +0.100 |
Cub | +0.095 |
worth | +0.091 |
\/ | +0.088 |
Neg logit contributions | |
Rue | -0.097 |
yss | -0.095 |
Jung | -0.089 |
nir | -0.086 |
Tags | -0.085 |
Token | if |
Token ID | 361 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
sbm | +0.414 |
bro | +0.394 |
Cub | +0.374 |
worth | +0.351 |
\/ | +0.340 |
Neg logit contributions | |
Rue | -0.490 |
yss | -0.475 |
Jung | -0.450 |
nir | -0.434 |
Tags | -0.430 |
Token | you |
Token ID | 345 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
sbm | +0.341 |
bro | +0.327 |
Cub | +0.309 |
worth | +0.293 |
\/ | +0.285 |
Neg logit contributions | |
Rue | -0.370 |
yss | -0.360 |
Jung | -0.338 |
nir | -0.327 |
Tags | -0.325 |
Token | see |
Token ID | 766 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Rue | +0.047 |
yss | +0.046 |
Jung | +0.043 |
nir | +0.041 |
Tags | +0.041 |
Neg logit contributions | |
sbm | -0.046 |
bro | -0.044 |
Cub | -0.041 |
worth | -0.039 |
\/ | -0.038 |
Token | what |
Token ID | 644 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Rue | +0.346 |
yss | +0.335 |
Jung | +0.315 |
nir | +0.305 |
Tags | +0.302 |
Neg logit contributions | |
sbm | -0.338 |
bro | -0.323 |
Cub | -0.306 |
worth | -0.289 |
\/ | -0.283 |
Token | I |
Token ID | 314 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
Rue | +0.097 |
yss | +0.094 |
Jung | +0.089 |
nir | +0.086 |
Tags | +0.086 |
Neg logit contributions | |
sbm | -0.083 |
bro | -0.079 |
Cub | -0.075 |
worth | -0.070 |
\/ | -0.068 |
Token | mean |
Token ID | 1612 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
sbm | +0.420 |
bro | +0.404 |
Cub | +0.383 |
worth | +0.367 |
\/ | +0.360 |
Neg logit contributions | |
Rue | -0.336 |
yss | -0.325 |
Jung | -0.301 |
nir | -0.290 |
Tags | -0.287 |
Token | ) |
Token ID | 8 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
sbm | +2.770 |
bro | +2.680 |
Cub | +2.560 |
worth | +2.416 |
\/ | +2.389 |
Neg logit contributions | |
Rue | -2.644 |
yss | -2.576 |
Jung | -2.377 |
nir | -2.340 |
ukong | -2.326 |
Token | there |
Token ID | 612 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
sbm | +0.605 |
bro | +0.574 |
Cub | +0.546 |
worth | +0.517 |
\/ | +0.506 |
Neg logit contributions | |
Rue | -0.612 |
yss | -0.592 |
Jung | -0.556 |
nir | -0.539 |
Tags | -0.534 |
Token | could |
Token ID | 714 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
sbm | +0.507 |
bro | +0.483 |
Cub | +0.455 |
worth | +0.429 |
\/ | +0.419 |
Neg logit contributions | |
Rue | -0.608 |
yss | -0.591 |
Jung | -0.555 |
nir | -0.538 |
Tags | -0.535 |
Token | be |
Token ID | 307 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
Rue | +0.040 |
yss | +0.039 |
Jung | +0.037 |
nir | +0.035 |
Tags | +0.035 |
Neg logit contributions | |
sbm | -0.042 |
bro | -0.040 |
Cub | -0.038 |
worth | -0.036 |
\/ | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
sbm | +0.120 |
bro | +0.114 |
Cub | +0.107 |
worth | +0.101 |
\/ | +0.099 |
Neg logit contributions | |
Rue | -0.143 |
yss | -0.138 |
Jung | -0.131 |
nir | -0.127 |
Tags | -0.126 |
Token | " |
Token ID | 366 |
Feature activation | +8.13e-03 |
Pos logit contributions | |
sbm | +0.847 |
bro | +0.824 |
Cub | +0.776 |
worth | +0.739 |
\/ | +0.715 |
Neg logit contributions | |
Rue | -0.901 |
yss | -0.876 |
Jung | -0.819 |
nir | -0.803 |
Tags | -0.791 |
Token | You |
Token ID | 1639 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
sbm | +0.006 |
bro | +0.005 |
Cub | +0.005 |
worth | +0.005 |
\/ | +0.005 |
Neg logit contributions | |
Rue | -0.007 |
yss | -0.006 |
Jung | -0.006 |
nir | -0.006 |
refriger | -0.006 |
Token | know |
Token ID | 760 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
sbm | +0.158 |
bro | +0.154 |
Cub | +0.143 |
worth | +0.137 |
\/ | +0.135 |
Neg logit contributions | |
Rue | -0.164 |
yss | -0.160 |
Jung | -0.149 |
nir | -0.145 |
Tags | -0.144 |
Token | what |
Token ID | 644 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
sbm | +0.150 |
bro | +0.145 |
Cub | +0.136 |
worth | +0.129 |
\/ | +0.127 |
Neg logit contributions | |
Rue | -0.166 |
yss | -0.162 |
Jung | -0.151 |
nir | -0.148 |
Tags | -0.147 |
Token | I |
Token ID | 314 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
sbm | +0.147 |
bro | +0.146 |
Cub | +0.135 |
worth | +0.129 |
\/ | +0.125 |
Neg logit contributions | |
Rue | -0.168 |
yss | -0.164 |
Jung | -0.152 |
Tags | -0.150 |
nir | -0.150 |
Token | mean |
Token ID | 1612 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
sbm | +0.619 |
bro | +0.606 |
Cub | +0.561 |
worth | +0.547 |
EEE | +0.535 |
Neg logit contributions | |
Rue | -0.572 |
yss | -0.562 |
Jung | -0.518 |
nir | -0.504 |
Tags | -0.499 |
Token | ." |
Token ID | 526 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
sbm | +2.608 |
bro | +2.598 |
Cub | +2.457 |
worth | +2.325 |
EEE | +2.303 |
Neg logit contributions | |
Rue | -2.662 |
yss | -2.608 |
nir | -2.398 |
Tags | -2.380 |
Jung | -2.374 |
Token | I |
Token ID | 314 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
sbm | +0.200 |
bro | +0.191 |
Cub | +0.181 |
worth | +0.172 |
\/ | +0.167 |
Neg logit contributions | |
Rue | -0.211 |
yss | -0.205 |
Jung | -0.192 |
nir | -0.188 |
Tags | -0.186 |
Token | pull |
Token ID | 2834 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
Rue | +0.022 |
yss | +0.022 |
Jung | +0.020 |
nir | +0.019 |
Tags | +0.019 |
Neg logit contributions | |
sbm | -0.027 |
bro | -0.026 |
Cub | -0.025 |
worth | -0.024 |
\/ | -0.023 |
Token | away |
Token ID | 1497 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Rue | +0.356 |
yss | +0.345 |
Jung | +0.322 |
nir | +0.314 |
Tags | +0.312 |
Neg logit contributions | |
sbm | -0.362 |
bro | -0.349 |
Cub | -0.329 |
worth | -0.314 |
\/ | -0.308 |
Token | at |
Token ID | 379 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
sbm | +0.911 |
bro | +0.884 |
Cub | +0.829 |
worth | +0.792 |
\/ | +0.770 |
Neg logit contributions | |
Rue | -1.030 |
yss | -1.006 |
Jung | -0.941 |
nir | -0.920 |
Tags | -0.914 |
Token | this |
Token ID | 428 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Rue | +0.146 |
yss | +0.141 |
Jung | +0.132 |
nir | +0.127 |
Tags | +0.126 |
Neg logit contributions | |
sbm | -0.148 |
bro | -0.141 |
Cub | -0.134 |
worth | -0.128 |
\/ | -0.125 |
Token | season |
Token ID | 1622 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
sbm | +0.121 |
bro | +0.115 |
Cub | +0.110 |
worth | +0.104 |
\/ | +0.102 |
Neg logit contributions | |
Rue | -0.117 |
yss | -0.113 |
Jung | -0.106 |
nir | -0.103 |
Tags | -0.102 |
Token | after |
Token ID | 706 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
sbm | +0.938 |
bro | +0.900 |
Cub | +0.852 |
worth | +0.815 |
\/ | +0.797 |
Neg logit contributions | |
Rue | -0.917 |
yss | -0.889 |
Jung | -0.832 |
nir | -0.805 |
Tags | -0.798 |
Token | tearing |
Token ID | 24447 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Rue | +0.015 |
yss | +0.015 |
Jung | +0.014 |
nir | +0.013 |
Tags | +0.013 |
Neg logit contributions | |
sbm | -0.017 |
bro | -0.016 |
Cub | -0.015 |
worth | -0.015 |
\/ | -0.014 |
Token | his |
Token ID | 465 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
sbm | +1.045 |
bro | +1.006 |
Cub | +0.955 |
worth | +0.905 |
\/ | +0.901 |
Neg logit contributions | |
Rue | -0.965 |
yss | -0.944 |
Jung | -0.876 |
nir | -0.851 |
Tags | -0.844 |
Token | ACL |
Token ID | 17382 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
sbm | +1.019 |
bro | +0.987 |
Cub | +0.940 |
\/ | +0.892 |
worth | +0.881 |
Neg logit contributions | |
Rue | -0.955 |
yss | -0.947 |
Jung | -0.861 |
nir | -0.845 |
Tags | -0.838 |
Token | last |
Token ID | 938 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
sbm | +2.685 |
bro | +2.627 |
Cub | +2.445 |
worth | +2.357 |
\/ | +2.343 |
Neg logit contributions | |
Rue | -2.638 |
yss | -2.596 |
Jung | -2.402 |
nir | -2.377 |
Tags | -2.338 |
Token | year |
Token ID | 614 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
sbm | +0.265 |
bro | +0.257 |
Cub | +0.244 |
worth | +0.234 |
\/ | +0.230 |
Neg logit contributions | |
Rue | -0.218 |
yss | -0.212 |
Jung | -0.196 |
nir | -0.191 |
Tags | -0.190 |
Token | . |
Token ID | 13 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
sbm | +0.127 |
bro | +0.121 |
Cub | +0.115 |
worth | +0.109 |
\/ | +0.107 |
Neg logit contributions | |
Rue | -0.118 |
yss | -0.114 |
Jung | -0.107 |
nir | -0.103 |
Tags | -0.102 |
Token |
|
Token ID | 198 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
sbm | +0.370 |
bro | +0.352 |
Cub | +0.338 |
worth | +0.321 |
\/ | +0.311 |
Neg logit contributions | |
Rue | -0.364 |
yss | -0.361 |
Jung | -0.329 |
nir | -0.325 |
Tags | -0.320 |
Token |
|
Token ID | 198 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
sbm | +0.239 |
bro | +0.229 |
Cub | +0.217 |
worth | +0.206 |
\/ | +0.201 |
Neg logit contributions | |
Rue | -0.254 |
yss | -0.248 |
Jung | -0.231 |
nir | -0.225 |
Tags | -0.221 |
Token | she |
Token ID | 673 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
Rue | +0.153 |
yss | +0.149 |
Jung | +0.142 |
nir | +0.138 |
Tags | +0.137 |
Neg logit contributions | |
sbm | -0.094 |
bro | -0.088 |
Cub | -0.083 |
worth | -0.077 |
\/ | -0.074 |
Token | is |
Token ID | 318 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
sbm | +0.541 |
bro | +0.517 |
Cub | +0.486 |
worth | +0.461 |
\/ | +0.452 |
Neg logit contributions | |
Rue | -0.661 |
yss | -0.640 |
Jung | -0.604 |
nir | -0.586 |
Tags | -0.582 |
Token | comfortable |
Token ID | 6792 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
Rue | +0.490 |
yss | +0.475 |
Jung | +0.445 |
nir | +0.431 |
Tags | +0.428 |
Neg logit contributions | |
sbm | -0.507 |
bro | -0.487 |
Cub | -0.462 |
worth | -0.441 |
\/ | -0.432 |
Token | knowing |
Token ID | 6970 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
Rue | +0.578 |
yss | +0.558 |
Jung | +0.526 |
nir | +0.509 |
Tags | +0.505 |
Neg logit contributions | |
sbm | -0.585 |
bro | -0.559 |
Cub | -0.530 |
worth | -0.503 |
\/ | -0.494 |
Token | that |
Token ID | 326 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
sbm | +0.068 |
bro | +0.065 |
Cub | +0.061 |
worth | +0.058 |
\/ | +0.056 |
Neg logit contributions | |
Rue | -0.080 |
yss | -0.078 |
Jung | -0.074 |
nir | -0.072 |
Tags | -0.071 |
Token | Valiant |
Token ID | 47781 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
Rue | +0.650 |
yss | +0.628 |
Jung | +0.594 |
nir | +0.576 |
Tags | +0.572 |
Neg logit contributions | |
sbm | -0.581 |
bro | -0.553 |
Cub | -0.523 |
worth | -0.494 |
\/ | -0.483 |
Token | stands |
Token ID | 6296 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
sbm | +2.405 |
bro | +2.364 |
Cub | +2.210 |
worth | +2.092 |
\/ | +2.067 |
Neg logit contributions | |
Rue | -2.916 |
yss | -2.842 |
Jung | -2.699 |
nir | -2.640 |
Tags | -2.587 |
Token | behind |
Token ID | 2157 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
Rue | +1.188 |
yss | +1.145 |
Jung | +1.067 |
nir | +1.031 |
Tags | +1.015 |
Neg logit contributions | |
sbm | -1.482 |
bro | -1.438 |
Cub | -1.366 |
worth | -1.318 |
\/ | -1.287 |
Token | them |
Token ID | 606 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
Rue | +0.633 |
yss | +0.611 |
Jung | +0.577 |
nir | +0.558 |
Tags | +0.552 |
Neg logit contributions | |
sbm | -0.628 |
bro | -0.599 |
Cub | -0.568 |
worth | -0.539 |
\/ | -0.528 |
Token | and |
Token ID | 290 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
sbm | +0.184 |
bro | +0.175 |
Cub | +0.166 |
worth | +0.158 |
\/ | +0.155 |
Neg logit contributions | |
Rue | -0.180 |
yss | -0.173 |
Jung | -0.164 |
nir | -0.157 |
Tags | -0.156 |
Token | that |
Token ID | 326 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
sbm | +0.265 |
bro | +0.253 |
Cub | +0.239 |
worth | +0.226 |
\/ | +0.221 |
Neg logit contributions | |
Rue | -0.308 |
yss | -0.298 |
Jung | -0.283 |
nir | -0.274 |
Tags | -0.272 |
Token | uck |
Token ID | 1347 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Rue | +0.364 |
yss | +0.350 |
Jung | +0.331 |
nir | +0.318 |
Tags | +0.316 |
Neg logit contributions | |
sbm | -0.373 |
bro | -0.355 |
Cub | -0.338 |
worth | -0.321 |
\/ | -0.314 |
Token | back |
Token ID | 736 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Rue | +0.152 |
yss | +0.148 |
Jung | +0.136 |
nir | +0.132 |
Tags | +0.131 |
Neg logit contributions | |
sbm | -0.201 |
bro | -0.194 |
Cub | -0.184 |
worth | -0.178 |
\/ | -0.173 |
Token | into |
Token ID | 656 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
sbm | +1.035 |
bro | +1.005 |
Cub | +0.951 |
worth | +0.926 |
\/ | +0.902 |
Neg logit contributions | |
Rue | -0.746 |
yss | -0.717 |
Jung | -0.660 |
Tags | -0.644 |
nir | -0.635 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
sbm | +0.797 |
bro | +0.762 |
Cub | +0.728 |
worth | +0.690 |
\/ | +0.678 |
Neg logit contributions | |
Rue | -0.711 |
yss | -0.696 |
Jung | -0.643 |
nir | -0.630 |
Tags | -0.625 |
Token | Alberta |
Token ID | 15555 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
sbm | +0.839 |
bro | +0.805 |
Cub | +0.769 |
worth | +0.729 |
\/ | +0.716 |
Neg logit contributions | |
Rue | -0.733 |
yss | -0.719 |
Jung | -0.664 |
nir | -0.647 |
Tags | -0.645 |
Token | legislature |
Token ID | 15928 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
sbm | +0.683 |
bro | +0.659 |
Cub | +0.626 |
worth | +0.594 |
\/ | +0.589 |
Neg logit contributions | |
Rue | -0.600 |
yss | -0.580 |
Jung | -0.538 |
nir | -0.526 |
Tags | -0.523 |
Token | in |
Token ID | 287 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
sbm | +2.632 |
bro | +2.571 |
Cub | +2.374 |
worth | +2.341 |
\/ | +2.276 |
Neg logit contributions | |
Rue | -2.672 |
yss | -2.628 |
nir | -2.425 |
Jung | -2.418 |
Tags | -2.396 |
Token | 2004 |
Token ID | 5472 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
sbm | +0.153 |
bro | +0.147 |
Cub | +0.137 |
worth | +0.130 |
\/ | +0.127 |
Neg logit contributions | |
Rue | -0.201 |
yss | -0.199 |
Jung | -0.186 |
nir | -0.182 |
Tags | -0.181 |
Token | , |
Token ID | 11 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
sbm | +0.394 |
bro | +0.376 |
Cub | +0.356 |
worth | +0.342 |
\/ | +0.334 |
Neg logit contributions | |
Rue | -0.376 |
yss | -0.364 |
Jung | -0.340 |
nir | -0.329 |
Tags | -0.327 |
Token | admits |
Token ID | 15534 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
sbm | +0.069 |
bro | +0.066 |
Cub | +0.063 |
worth | +0.059 |
\/ | +0.058 |
Neg logit contributions | |
Rue | -0.072 |
yss | -0.069 |
Jung | -0.065 |
nir | -0.063 |
Tags | -0.063 |
Token | he |
Token ID | 339 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
sbm | +1.046 |
bro | +1.008 |
Cub | +0.942 |
worth | +0.893 |
\/ | +0.871 |
Neg logit contributions | |
Rue | -1.224 |
yss | -1.202 |
Jung | -1.119 |
nir | -1.104 |
Tags | -1.095 |
Token | see |
Token ID | 766 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
sbm | +0.424 |
bro | +0.404 |
Cub | +0.386 |
worth | +0.366 |
\/ | +0.359 |
Neg logit contributions | |
Rue | -0.387 |
yss | -0.373 |
Jung | -0.351 |
nir | -0.337 |
Tags | -0.335 |
Token | a |
Token ID | 257 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
sbm | +0.645 |
bro | +0.613 |
Cub | +0.581 |
worth | +0.547 |
\/ | +0.538 |
Neg logit contributions | |
Rue | -0.718 |
yss | -0.697 |
Jung | -0.656 |
nir | -0.638 |
Tags | -0.629 |
Token | softer |
Token ID | 32359 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
sbm | +0.410 |
bro | +0.395 |
Cub | +0.380 |
worth | +0.363 |
\/ | +0.358 |
Neg logit contributions | |
Rue | -0.271 |
yss | -0.260 |
Jung | -0.237 |
nir | -0.231 |
Tags | -0.227 |
Token | corner |
Token ID | 5228 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
Rue | +0.278 |
yss | +0.266 |
Jung | +0.246 |
nir | +0.236 |
Tags | +0.234 |
Neg logit contributions | |
sbm | -0.390 |
bro | -0.375 |
Cub | -0.361 |
worth | -0.344 |
\/ | -0.338 |
Token | or |
Token ID | 393 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
Rue | +0.031 |
yss | +0.030 |
Jung | +0.028 |
nir | +0.027 |
Tags | +0.027 |
Neg logit contributions | |
sbm | -0.035 |
bro | -0.033 |
Cub | -0.032 |
worth | -0.030 |
\/ | -0.030 |
Token | side |
Token ID | 1735 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
sbm | +0.410 |
bro | +0.393 |
Cub | +0.374 |
worth | +0.354 |
\/ | +0.350 |
Neg logit contributions | |
Rue | -0.390 |
yss | -0.377 |
Jung | -0.353 |
nir | -0.341 |
Tags | -0.338 |
Token | ? |
Token ID | 30 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
sbm | +2.721 |
bro | +2.655 |
Cub | +2.546 |
worth | +2.397 |
\/ | +2.365 |
Neg logit contributions | |
Rue | -2.637 |
yss | -2.552 |
Jung | -2.370 |
nir | -2.302 |
Tags | -2.277 |
Token | Well |
Token ID | 3894 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Rue | +0.069 |
yss | +0.067 |
Jung | +0.062 |
nir | +0.061 |
Tags | +0.060 |
Neg logit contributions | |
sbm | -0.081 |
bro | -0.077 |
Cub | -0.074 |
worth | -0.070 |
\/ | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
Rue | +0.157 |
yss | +0.151 |
Jung | +0.142 |
nir | +0.136 |
Tags | +0.135 |
Neg logit contributions | |
sbm | -0.185 |
bro | -0.176 |
Cub | -0.168 |
worth | -0.160 |
\/ | -0.157 |
Token | a |
Token ID | 257 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
sbm | +0.337 |
bro | +0.322 |
Cub | +0.306 |
worth | +0.289 |
\/ | +0.283 |
Neg logit contributions | |
Rue | -0.352 |
yss | -0.341 |
Jung | -0.320 |
nir | -0.311 |
Tags | -0.309 |
Token | few |
Token ID | 1178 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Rue | +0.075 |
yss | +0.072 |
Jung | +0.067 |
nir | +0.065 |
Tags | +0.065 |
Neg logit contributions | |
sbm | -0.082 |
bro | -0.079 |
Cub | -0.075 |
worth | -0.071 |
\/ | -0.070 |
Token | enc |
Token ID | 2207 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
sbm | +0.738 |
bro | +0.718 |
Cub | +0.676 |
worth | +0.648 |
\/ | +0.631 |
Neg logit contributions | |
Rue | -0.722 |
yss | -0.701 |
Jung | -0.651 |
nir | -0.629 |
Tags | -0.627 |
Token | ased |
Token ID | 839 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Rue | +0.305 |
yss | +0.294 |
Jung | +0.282 |
nir | +0.272 |
Tags | +0.271 |
Neg logit contributions | |
sbm | -0.215 |
bro | -0.205 |
Cub | -0.190 |
worth | -0.176 |
\/ | -0.173 |
Token | in |
Token ID | 287 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Rue | +0.814 |
yss | +0.780 |
Jung | +0.728 |
nir | +0.698 |
Tags | +0.692 |
Neg logit contributions | |
sbm | -1.053 |
bro | -1.009 |
Cub | -0.965 |
worth | -0.922 |
\/ | -0.903 |
Token | copper |
Token ID | 15317 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
sbm | +0.174 |
bro | +0.166 |
Cub | +0.157 |
worth | +0.149 |
\/ | +0.146 |
Neg logit contributions | |
Rue | -0.172 |
yss | -0.166 |
Jung | -0.156 |
nir | -0.151 |
Tags | -0.150 |
Token | and |
Token ID | 290 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
sbm | +1.137 |
bro | +1.101 |
Cub | +1.035 |
worth | +0.993 |
\/ | +0.972 |
Neg logit contributions | |
Rue | -1.139 |
yss | -1.102 |
Jung | -1.031 |
nir | -1.000 |
Tags | -0.989 |
Token | dated |
Token ID | 14567 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
Rue | +0.305 |
yss | +0.296 |
Jung | +0.276 |
nir | +0.267 |
Tags | +0.266 |
Neg logit contributions | |
sbm | -0.317 |
bro | -0.306 |
Cub | -0.290 |
worth | -0.277 |
\/ | -0.270 |
Token | from |
Token ID | 422 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
sbm | +2.675 |
bro | +2.612 |
Cub | +2.473 |
worth | +2.363 |
\/ | +2.279 |
Neg logit contributions | |
yss | -2.516 |
Rue | -2.513 |
Jung | -2.259 |
nir | -2.245 |
Tags | -2.236 |
Token | about |
Token ID | 546 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
sbm | +0.321 |
bro | +0.308 |
Cub | +0.293 |
worth | +0.281 |
\/ | +0.273 |
Neg logit contributions | |
Rue | -0.295 |
yss | -0.287 |
Jung | -0.266 |
nir | -0.258 |
Tags | -0.257 |
Token | 200 |
Token ID | 939 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Rue | +0.126 |
yss | +0.123 |
Jung | +0.114 |
nir | +0.111 |
Tags | +0.110 |
Neg logit contributions | |
sbm | -0.141 |
bro | -0.136 |
Cub | -0.129 |
worth | -0.123 |
\/ | -0.121 |
Token | B |
Token ID | 347 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
sbm | +0.104 |
bro | +0.099 |
Cub | +0.094 |
worth | +0.089 |
\/ | +0.088 |
Neg logit contributions | |
Rue | -0.101 |
yss | -0.098 |
Jung | -0.092 |
nir | -0.088 |
Tags | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
sbm | +0.778 |
bro | +0.748 |
Cub | +0.712 |
worth | +0.673 |
\/ | +0.660 |
Neg logit contributions | |
Rue | -0.813 |
yss | -0.788 |
Jung | -0.733 |
nir | -0.718 |
Tags | -0.714 |
Token | in |
Token ID | 287 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
Rue | +0.449 |
yss | +0.434 |
Jung | +0.407 |
nir | +0.393 |
Tags | +0.390 |
Neg logit contributions | |
sbm | -0.472 |
bro | -0.451 |
Cub | -0.428 |
worth | -0.406 |
\/ | -0.399 |
Token | your |
Token ID | 534 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Rue | +0.361 |
yss | +0.348 |
Jung | +0.325 |
nir | +0.312 |
Tags | +0.310 |
Neg logit contributions | |
sbm | -0.443 |
bro | -0.423 |
Cub | -0.404 |
worth | -0.384 |
\/ | -0.378 |
Token | garage |
Token ID | 15591 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
sbm | +0.086 |
bro | +0.082 |
Cub | +0.079 |
worth | +0.075 |
\/ | +0.074 |
Neg logit contributions | |
Rue | -0.066 |
yss | -0.063 |
Jung | -0.059 |
nir | -0.057 |
Tags | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
Rue | +0.872 |
yss | +0.841 |
Jung | +0.791 |
nir | +0.760 |
Tags | +0.754 |
Neg logit contributions | |
sbm | -0.932 |
bro | -0.888 |
Cub | -0.846 |
worth | -0.802 |
\/ | -0.787 |
Token | This |
Token ID | 1212 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
Rue | +0.064 |
yss | +0.063 |
Jung | +0.058 |
nir | +0.056 |
refriger | +0.056 |
Neg logit contributions | |
sbm | -0.071 |
bro | -0.068 |
Cub | -0.065 |
worth | -0.062 |
\/ | -0.061 |
Token | picture |
Token ID | 4286 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
sbm | +0.705 |
bro | +0.675 |
Cub | +0.634 |
worth | +0.603 |
\/ | +0.593 |
Neg logit contributions | |
Rue | -0.765 |
yss | -0.749 |
Jung | -0.698 |
nir | -0.676 |
Tags | -0.669 |
Token | shows |
Token ID | 2523 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
sbm | +2.352 |
bro | +2.293 |
Cub | +2.128 |
worth | +2.035 |
\/ | +1.989 |
Neg logit contributions | |
Rue | -2.911 |
yss | -2.840 |
Jung | -2.662 |
nir | -2.604 |
Tags | -2.554 |
Token | the |
Token ID | 262 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
sbm | +1.019 |
bro | +0.978 |
Cub | +0.914 |
worth | +0.865 |
\/ | +0.853 |
Neg logit contributions | |
Rue | -1.133 |
yss | -1.109 |
Jung | -1.039 |
nir | -1.011 |
Tags | -0.999 |
Token | two |
Token ID | 734 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
sbm | +0.199 |
bro | +0.191 |
Cub | +0.182 |
worth | +0.173 |
\/ | +0.171 |
Neg logit contributions | |
Rue | -0.164 |
yss | -0.159 |
Jung | -0.148 |
nir | -0.143 |
Tags | -0.141 |
Token | seat |
Token ID | 5852 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Rue | +0.414 |
yss | +0.401 |
Jung | +0.377 |
nir | +0.364 |
Tags | +0.361 |
Neg logit contributions | |
sbm | -0.408 |
bro | -0.389 |
Cub | -0.369 |
worth | -0.350 |
\/ | -0.343 |
Token | heater |
Token ID | 39844 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Rue | +0.772 |
yss | +0.737 |
Jung | +0.684 |
nir | +0.649 |
Tags | +0.644 |
Neg logit contributions | |
sbm | -1.202 |
bro | -1.152 |
Cub | -1.107 |
worth | -1.059 |
\/ | -1.041 |
Token | compared |
Token ID | 3688 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
sbm | +0.028 |
bro | +0.027 |
Cub | +0.025 |
worth | +0.024 |
\/ | +0.024 |
Neg logit contributions | |
Rue | -0.027 |
yss | -0.027 |
Jung | -0.025 |
nir | -0.024 |
Tags | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Rue | +0.356 |
yss | +0.341 |
Jung | +0.318 |
nir | +0.304 |
Tags | +0.301 |
Neg logit contributions | |
sbm | -0.488 |
bro | -0.467 |
Cub | -0.447 |
worth | -0.427 |
\/ | -0.419 |
Token | couples |
Token ID | 11886 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Rue | +0.246 |
yss | +0.239 |
Jung | +0.224 |
nir | +0.217 |
Tags | +0.215 |
Neg logit contributions | |
sbm | -0.233 |
bro | -0.223 |
Cub | -0.211 |
worth | -0.200 |
\/ | -0.196 |
Token | where |
Token ID | 810 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
sbm | +1.191 |
bro | +1.162 |
Cub | +1.082 |
worth | +1.044 |
\/ | +1.028 |
Neg logit contributions | |
Rue | -1.139 |
yss | -1.126 |
Jung | -1.021 |
nir | -1.015 |
Tags | -1.004 |
Token | both |
Token ID | 1111 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
Rue | +1.162 |
yss | +1.119 |
Jung | +1.053 |
nir | +1.011 |
Tags | +1.004 |
Neg logit contributions | |
sbm | -1.257 |
bro | -1.197 |
Cub | -1.141 |
worth | -1.082 |
\/ | -1.060 |
Token | partners |
Token ID | 4887 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
Rue | +0.325 |
yss | +0.316 |
Jung | +0.294 |
nir | +0.285 |
Tags | +0.282 |
Neg logit contributions | |
sbm | -0.337 |
bro | -0.323 |
Cub | -0.306 |
worth | -0.292 |
\/ | -0.286 |
Token | are |
Token ID | 389 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
sbm | +2.506 |
bro | +2.473 |
Cub | +2.286 |
worth | +2.228 |
\/ | +2.197 |
Neg logit contributions | |
yss | -2.662 |
Rue | -2.648 |
Jung | -2.399 |
Tags | -2.385 |
nir | -2.360 |
Token | the |
Token ID | 262 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
sbm | +0.136 |
bro | +0.131 |
Cub | +0.124 |
worth | +0.119 |
\/ | +0.116 |
Neg logit contributions | |
Rue | -0.143 |
yss | -0.141 |
Jung | -0.129 |
nir | -0.126 |
Tags | -0.126 |
Token | same |
Token ID | 976 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
sbm | +0.117 |
bro | +0.112 |
Cub | +0.107 |
worth | +0.103 |
\/ | +0.101 |
Neg logit contributions | |
Rue | -0.089 |
yss | -0.087 |
Jung | -0.079 |
nir | -0.077 |
ukong | -0.076 |
Token | age |
Token ID | 2479 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
sbm | +0.512 |
bro | +0.502 |
Cub | +0.474 |
worth | +0.465 |
\/ | +0.457 |
Neg logit contributions | |
Rue | -0.290 |
yss | -0.284 |
Jung | -0.252 |
nir | -0.246 |
ukong | -0.243 |
Token | . |
Token ID | 13 |
Feature activation | -4.40e-03 |
Pos logit contributions | |
Rue | +1.066 |
yss | +1.024 |
Jung | +0.967 |
nir | +0.926 |
Tags | +0.920 |
Neg logit contributions | |
sbm | -1.181 |
bro | -1.122 |
Cub | -1.072 |
worth | -1.016 |
\/ | -0.995 |
Token | some |
Token ID | 617 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
Rue | +0.103 |
yss | +0.099 |
Jung | +0.093 |
nir | +0.089 |
Tags | +0.089 |
Neg logit contributions | |
sbm | -0.115 |
bro | -0.110 |
Cub | -0.104 |
worth | -0.099 |
\/ | -0.097 |
Token | trouble |
Token ID | 5876 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
Rue | +0.286 |
yss | +0.278 |
Jung | +0.260 |
nir | +0.252 |
Tags | +0.249 |
Neg logit contributions | |
sbm | -0.288 |
bro | -0.275 |
Cub | -0.261 |
worth | -0.247 |
\/ | -0.243 |
Token | clearing |
Token ID | 17304 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
sbm | +0.647 |
bro | +0.628 |
Cub | +0.595 |
worth | +0.564 |
\/ | +0.556 |
Neg logit contributions | |
Rue | -0.572 |
yss | -0.551 |
Jung | -0.515 |
nir | -0.493 |
Tags | -0.493 |
Token | it |
Token ID | 340 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
Rue | +0.214 |
yss | +0.207 |
Jung | +0.195 |
nir | +0.188 |
Tags | +0.186 |
Neg logit contributions | |
sbm | -0.221 |
bro | -0.211 |
Cub | -0.201 |
worth | -0.190 |
\/ | -0.186 |
Token | Sh |
Token ID | 2484 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
Rue | +0.423 |
yss | +0.408 |
Jung | +0.383 |
nir | +0.367 |
Tags | +0.366 |
Neg logit contributions | |
sbm | -0.457 |
bro | -0.435 |
Cub | -0.415 |
worth | -0.394 |
\/ | -0.385 |
Token | owing |
Token ID | 7855 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
sbm | +0.478 |
bro | +0.457 |
Cub | +0.428 |
worth | +0.411 |
\/ | +0.393 |
Neg logit contributions | |
Rue | -0.663 |
yss | -0.644 |
Jung | -0.620 |
Tags | -0.594 |
refriger | -0.590 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
sbm | +2.461 |
bro | +2.366 |
Cub | +2.219 |
worth | +2.096 |
\/ | +2.070 |
Neg logit contributions | |
Rue | -2.775 |
yss | -2.691 |
Jung | -2.538 |
nir | -2.470 |
Tags | -2.428 |
Token | location |
Token ID | 4067 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
sbm | +0.829 |
bro | +0.793 |
Cub | +0.755 |
worth | +0.715 |
\/ | +0.704 |
Neg logit contributions | |
Rue | -0.743 |
yss | -0.719 |
Jung | -0.670 |
nir | -0.649 |
Tags | -0.641 |
Token | of |
Token ID | 286 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
sbm | +0.780 |
bro | +0.752 |
Cub | +0.714 |
worth | +0.681 |
\/ | +0.670 |
Neg logit contributions | |
Rue | -0.684 |
yss | -0.663 |
Jung | -0.618 |
nir | -0.595 |
Tags | -0.587 |
Token | the |
Token ID | 262 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
sbm | +1.016 |
bro | +0.976 |
Cub | +0.924 |
worth | +0.873 |
\/ | +0.860 |
Neg logit contributions | |
Rue | -0.954 |
yss | -0.927 |
Jung | -0.864 |
nir | -0.837 |
Tags | -0.824 |
Token | two |
Token ID | 734 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
sbm | +0.712 |
bro | +0.681 |
Cub | +0.647 |
worth | +0.612 |
\/ | +0.603 |
Neg logit contributions | |
Rue | -0.676 |
yss | -0.654 |
Jung | -0.611 |
nir | -0.593 |
Tags | -0.585 |
Token | � |
Token ID | 250 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
sbm | +0.246 |
bro | +0.234 |
Cub | +0.220 |
worth | +0.208 |
\/ | +0.204 |
Neg logit contributions | |
Rue | -0.302 |
yss | -0.293 |
Jung | -0.277 |
nir | -0.269 |
Tags | -0.267 |
Token | et |
Token ID | 316 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
sbm | +0.492 |
bro | +0.473 |
Cub | +0.450 |
worth | +0.427 |
\/ | +0.415 |
Neg logit contributions | |
Rue | -0.555 |
yss | -0.537 |
Jung | -0.510 |
nir | -0.489 |
refriger | -0.488 |
Token | ernal |
Token ID | 35220 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
sbm | +0.766 |
bro | +0.733 |
Cub | +0.696 |
worth | +0.663 |
\/ | +0.650 |
Neg logit contributions | |
Rue | -0.717 |
yss | -0.696 |
Jung | -0.654 |
nir | -0.626 |
Tags | -0.624 |
Token | and |
Token ID | 290 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
Rue | +0.179 |
yss | +0.174 |
Jung | +0.160 |
nir | +0.154 |
Tags | +0.153 |
Neg logit contributions | |
sbm | -0.260 |
bro | -0.249 |
Cub | -0.240 |
worth | -0.230 |
\/ | -0.228 |
Token | und |
Token ID | 3318 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
sbm | +0.252 |
bro | +0.241 |
Cub | +0.228 |
worth | +0.217 |
\/ | +0.213 |
Neg logit contributions | |
Rue | -0.265 |
yss | -0.256 |
Jung | -0.241 |
nir | -0.233 |
Tags | -0.231 |
Token | iv |
Token ID | 452 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
Rue | +0.149 |
yss | +0.145 |
Jung | +0.139 |
nir | +0.136 |
Tags | +0.136 |
Neg logit contributions | |
sbm | -0.068 |
bro | -0.063 |
Cub | -0.057 |
worth | -0.053 |
\/ | -0.050 |
Token | ided |
Token ID | 1384 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
sbm | +2.553 |
bro | +2.516 |
Cub | +2.356 |
worth | +2.294 |
\/ | +2.278 |
Neg logit contributions | |
Rue | -2.618 |
yss | -2.471 |
Jung | -2.370 |
nir | -2.284 |
Tags | -2.261 |
Token | capital |
Token ID | 3139 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
Rue | +0.426 |
yss | +0.410 |
Jung | +0.375 |
nir | +0.358 |
Tags | +0.355 |
Neg logit contributions | |
sbm | -0.714 |
bro | -0.686 |
Cub | -0.661 |
worth | -0.635 |
\/ | -0.628 |
Token | � |
Token ID | 447 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Rue | +0.535 |
yss | +0.516 |
Jung | +0.486 |
nir | +0.468 |
Tags | +0.464 |
Neg logit contributions | |
sbm | -0.554 |
bro | -0.527 |
Cub | -0.502 |
worth | -0.476 |
\/ | -0.467 |
Token | � |
Token ID | 251 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
Rue | +0.801 |
yss | +0.773 |
Jung | +0.730 |
nir | +0.702 |
Tags | +0.698 |
Neg logit contributions | |
sbm | -0.782 |
bro | -0.742 |
Cub | -0.706 |
worth | -0.667 |
\/ | -0.653 |
Token | and |
Token ID | 290 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Rue | +0.287 |
yss | +0.277 |
Jung | +0.261 |
nir | +0.252 |
Tags | +0.250 |
Neg logit contributions | |
sbm | -0.289 |
bro | -0.275 |
Cub | -0.261 |
worth | -0.248 |
\/ | -0.242 |
Token | NY |
Token ID | 6645 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
sbm | +1.299 |
bro | +1.263 |
Cub | +1.190 |
worth | +1.153 |
\/ | +1.129 |
Neg logit contributions | |
Rue | -1.187 |
yss | -1.165 |
nir | -1.080 |
Jung | -1.075 |
Tags | -1.053 |
Token | : |
Token ID | 1058 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Rue | +0.325 |
yss | +0.314 |
Jung | +0.299 |
nir | +0.289 |
Tags | +0.287 |
Neg logit contributions | |
sbm | -0.255 |
bro | -0.240 |
Cub | -0.227 |
worth | -0.213 |
\/ | -0.208 |
Token | Worth |
Token ID | 22301 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
sbm | +0.762 |
bro | +0.728 |
Cub | +0.692 |
worth | +0.662 |
\/ | +0.645 |
Neg logit contributions | |
Rue | -0.796 |
yss | -0.784 |
nir | -0.726 |
Jung | -0.721 |
Tags | -0.707 |
Token | Publishers |
Token ID | 43403 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
sbm | +1.162 |
bro | +1.124 |
Cub | +1.072 |
worth | +1.033 |
\/ | +1.004 |
Neg logit contributions | |
Rue | -0.922 |
yss | -0.897 |
Jung | -0.832 |
nir | -0.805 |
Tags | -0.788 |
Token | . |
Token ID | 764 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
sbm | +0.584 |
bro | +0.551 |
Cub | +0.514 |
worth | +0.483 |
\/ | +0.465 |
Neg logit contributions | |
Rue | -0.981 |
yss | -0.961 |
Jung | -0.910 |
nir | -0.893 |
Tags | -0.885 |
Token |
|
Token ID | 198 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
sbm | +0.799 |
bro | +0.759 |
Cub | +0.723 |
worth | +0.685 |
\/ | +0.670 |
Neg logit contributions | |
Rue | -0.791 |
yss | -0.764 |
Jung | -0.720 |
nir | -0.694 |
Tags | -0.688 |
Token |
|
Token ID | 198 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
sbm | +2.286 |
bro | +2.228 |
Cub | +2.091 |
worth | +1.988 |
\/ | +1.955 |
Neg logit contributions | |
yss | -2.867 |
Rue | -2.847 |
Jung | -2.595 |
nir | -2.588 |
refriger | -2.566 |
Token | Google |
Token ID | 11708 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
sbm | +1.931 |
bro | +1.852 |
Cub | +1.769 |
worth | +1.648 |
\/ | +1.587 |
Neg logit contributions | |
Rue | -2.692 |
yss | -2.643 |
Jung | -2.497 |
refriger | -2.438 |
nir | -2.407 |
Token | Scholar |
Token ID | 11713 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
sbm | +0.892 |
bro | +0.843 |
Cub | +0.797 |
worth | +0.749 |
\/ | +0.740 |
Neg logit contributions | |
Rue | -1.157 |
yss | -1.150 |
Jung | -1.055 |
nir | -1.047 |
refriger | -1.033 |
Token |
|
Token ID | 198 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
sbm | +0.741 |
bro | +0.703 |
Cub | +0.671 |
worth | +0.637 |
\/ | +0.625 |
Neg logit contributions | |
Rue | -0.691 |
yss | -0.672 |
Jung | -0.628 |
nir | -0.609 |
Tags | -0.602 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
sbm | +1.686 |
bro | +1.626 |
Cub | +1.536 |
worth | +1.461 |
\/ | +1.435 |
Neg logit contributions | |
yss | -2.018 |
Rue | -2.012 |
Jung | -1.836 |
nir | -1.822 |
refriger | -1.800 |
Token | just |
Token ID | 655 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
Rue | +0.092 |
yss | +0.090 |
Jung | +0.083 |
nir | +0.081 |
Tags | +0.080 |
Neg logit contributions | |
sbm | -0.095 |
bro | -0.091 |
Cub | -0.086 |
worth | -0.082 |
\/ | -0.080 |
Token | two |
Token ID | 734 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Rue | +0.485 |
yss | +0.469 |
Jung | +0.440 |
nir | +0.425 |
Tags | +0.422 |
Neg logit contributions | |
sbm | -0.483 |
bro | -0.461 |
Cub | -0.437 |
worth | -0.415 |
\/ | -0.405 |
Token | guys |
Token ID | 3730 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
Rue | +0.356 |
yss | +0.345 |
Jung | +0.321 |
nir | +0.312 |
Tags | +0.307 |
Neg logit contributions | |
sbm | -0.389 |
bro | -0.374 |
Cub | -0.356 |
worth | -0.338 |
\/ | -0.331 |
Token | -- |
Token ID | 1377 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
Rue | +0.325 |
yss | +0.316 |
Jung | +0.296 |
nir | +0.288 |
Tags | +0.285 |
Neg logit contributions | |
sbm | -0.303 |
bro | -0.290 |
Cub | -0.274 |
worth | -0.260 |
\/ | -0.254 |
Token | I |
Token ID | 314 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
sbm | +0.700 |
bro | +0.670 |
Cub | +0.633 |
worth | +0.602 |
\/ | +0.583 |
Neg logit contributions | |
Rue | -0.752 |
yss | -0.725 |
Jung | -0.681 |
Tags | -0.663 |
nir | -0.663 |
Token | mean |
Token ID | 1612 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
sbm | +0.150 |
bro | +0.147 |
Cub | +0.138 |
worth | +0.132 |
EEE | +0.130 |
Neg logit contributions | |
Rue | -0.141 |
yss | -0.138 |
Jung | -0.127 |
nir | -0.123 |
Tags | -0.123 |
Token | , |
Token ID | 11 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
sbm | +2.456 |
bro | +2.412 |
Cub | +2.250 |
worth | +2.180 |
\/ | +2.089 |
Neg logit contributions | |
Rue | -2.577 |
yss | -2.492 |
Tags | -2.306 |
nir | -2.298 |
Jung | -2.290 |
Token | that |
Token ID | 326 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
sbm | +1.379 |
bro | +1.324 |
Cub | +1.242 |
worth | +1.196 |
\/ | +1.145 |
Neg logit contributions | |
Rue | -1.520 |
yss | -1.474 |
Jung | -1.363 |
Tags | -1.360 |
nir | -1.357 |
Token | 's |
Token ID | 338 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
sbm | +0.852 |
bro | +0.836 |
Cub | +0.796 |
worth | +0.755 |
\/ | +0.737 |
Neg logit contributions | |
Rue | -0.711 |
yss | -0.696 |
Jung | -0.631 |
nir | -0.616 |
Tags | -0.616 |
Token | the |
Token ID | 262 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
Rue | +0.841 |
yss | +0.813 |
Jung | +0.763 |
nir | +0.740 |
Tags | +0.735 |
Neg logit contributions | |
sbm | -0.799 |
bro | -0.763 |
Cub | -0.722 |
worth | -0.685 |
\/ | -0.666 |
Token | old |
Token ID | 1468 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Rue | +0.062 |
yss | +0.060 |
Jung | +0.056 |
nir | +0.054 |
Tags | +0.054 |
Neg logit contributions | |
sbm | -0.071 |
bro | -0.068 |
Cub | -0.065 |
worth | -0.062 |
\/ | -0.061 |
Token | to |
Token ID | 284 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
sbm | +0.113 |
bro | +0.108 |
Cub | +0.103 |
worth | +0.098 |
\/ | +0.096 |
Neg logit contributions | |
Rue | -0.088 |
yss | -0.084 |
Jung | -0.079 |
nir | -0.075 |
Tags | -0.075 |
Token | disrupt |
Token ID | 10114 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
sbm | +0.025 |
bro | +0.024 |
Cub | +0.023 |
worth | +0.022 |
\/ | +0.021 |
Neg logit contributions | |
Rue | -0.020 |
yss | -0.019 |
Jung | -0.018 |
nir | -0.017 |
Tags | -0.017 |
Token | Democratic |
Token ID | 4390 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
sbm | +0.301 |
bro | +0.291 |
Cub | +0.275 |
worth | +0.261 |
\/ | +0.256 |
Neg logit contributions | |
Rue | -0.280 |
yss | -0.271 |
Jung | -0.254 |
nir | -0.245 |
Tags | -0.242 |
Token | front |
Token ID | 2166 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
Rue | +1.161 |
yss | +1.112 |
Jung | +1.053 |
nir | +1.004 |
Tags | +1.001 |
Neg logit contributions | |
sbm | -1.294 |
bro | -1.225 |
Cub | -1.173 |
worth | -1.109 |
\/ | -1.088 |
Token | - |
Token ID | 12 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Rue | +0.171 |
yss | +0.165 |
Jung | +0.155 |
nir | +0.150 |
Tags | +0.148 |
Neg logit contributions | |
sbm | -0.170 |
bro | -0.161 |
Cub | -0.153 |
worth | -0.145 |
\/ | -0.142 |
Token | runner |
Token ID | 16737 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
Rue | +1.023 |
yss | +0.992 |
Jung | +0.941 |
nir | +0.908 |
Tags | +0.904 |
Neg logit contributions | |
sbm | -0.826 |
bro | -0.783 |
Cub | -0.736 |
worth | -0.693 |
\/ | -0.676 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
Rue | +2.699 |
yss | +2.560 |
Jung | +2.412 |
nir | +2.267 |
Tags | +2.258 |
Neg logit contributions | |
sbm | -3.968 |
bro | -3.767 |
Cub | -3.629 |
worth | -3.459 |
\/ | -3.407 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
sbm | +0.332 |
bro | +0.318 |
Cub | +0.298 |
worth | +0.283 |
\/ | +0.277 |
Neg logit contributions | |
Rue | -0.378 |
yss | -0.370 |
Jung | -0.345 |
nir | -0.339 |
Tags | -0.335 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
sbm | +0.804 |
bro | +0.765 |
Cub | +0.717 |
worth | +0.684 |
\/ | +0.665 |
Neg logit contributions | |
Rue | -0.921 |
yss | -0.899 |
Jung | -0.842 |
nir | -0.822 |
Tags | -0.816 |
Token | 's |
Token ID | 338 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
sbm | +0.444 |
bro | +0.428 |
Cub | +0.404 |
worth | +0.386 |
\/ | +0.377 |
Neg logit contributions | |
Rue | -0.419 |
yss | -0.406 |
Jung | -0.378 |
nir | -0.368 |
Tags | -0.364 |
Token | path |
Token ID | 3108 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
sbm | +0.174 |
bro | +0.168 |
Cub | +0.160 |
worth | +0.152 |
\/ | +0.149 |
Neg logit contributions | |
Rue | -0.155 |
yss | -0.150 |
Jung | -0.140 |
nir | -0.135 |
Tags | -0.134 |
Token | includes |
Token ID | 3407 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
Rue | +0.939 |
yss | +0.911 |
Jung | +0.853 |
nir | +0.824 |
Tags | +0.813 |
Neg logit contributions | |
sbm | -0.956 |
bro | -0.915 |
Cub | -0.868 |
worth | -0.824 |
\/ | -0.811 |
Token | the |
Token ID | 262 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
sbm | +0.543 |
bro | +0.517 |
Cub | +0.489 |
worth | +0.467 |
\/ | +0.459 |
Neg logit contributions | |
Rue | -0.528 |
yss | -0.518 |
Jung | -0.481 |
nir | -0.472 |
Tags | -0.461 |
Token | Walker |
Token ID | 10120 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Rue | +0.049 |
yss | +0.048 |
Jung | +0.044 |
nir | +0.043 |
Tags | +0.042 |
Neg logit contributions | |
sbm | -0.059 |
bro | -0.057 |
Cub | -0.054 |
worth | -0.051 |
\/ | -0.051 |
Token | - |
Token ID | 12 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
sbm | +0.480 |
bro | +0.466 |
Cub | +0.442 |
worth | +0.425 |
\/ | +0.414 |
Neg logit contributions | |
Rue | -0.417 |
yss | -0.406 |
Jung | -0.376 |
nir | -0.368 |
Tags | -0.365 |
Token | over |
Token ID | 2502 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
Rue | +0.566 |
yss | +0.549 |
Jung | +0.519 |
nir | +0.501 |
Tags | +0.496 |
Neg logit contributions | |
sbm | -0.496 |
bro | -0.473 |
Cub | -0.448 |
worth | -0.423 |
\/ | -0.411 |
Token | run |
Token ID | 5143 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
Rue | +0.673 |
yss | +0.655 |
Jung | +0.611 |
nir | +0.592 |
Tags | +0.589 |
Neg logit contributions | |
sbm | -0.689 |
bro | -0.663 |
Cub | -0.623 |
worth | -0.599 |
\/ | -0.584 |
Token | Cell |
Token ID | 12440 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Rue | +3.057 |
yss | +2.904 |
Jung | +2.756 |
nir | +2.617 |
refriger | +2.612 |
Neg logit contributions | |
sbm | -3.578 |
bro | -3.389 |
Cub | -3.254 |
worth | -3.074 |
\/ | -3.006 |
Token | Block |
Token ID | 9726 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Rue | +0.144 |
yss | +0.140 |
Jung | +0.130 |
nir | +0.126 |
Tags | +0.125 |
Neg logit contributions | |
sbm | -0.159 |
bro | -0.153 |
Cub | -0.145 |
worth | -0.139 |
\/ | -0.135 |
Token | D |
Token ID | 360 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
sbm | +0.455 |
bro | +0.439 |
Cub | +0.416 |
worth | +0.400 |
\/ | +0.388 |
Neg logit contributions | |
Rue | -0.424 |
yss | -0.414 |
Jung | -0.383 |
nir | -0.374 |
Tags | -0.369 |
Token | and |
Token ID | 290 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
Rue | +0.331 |
yss | +0.322 |
Jung | +0.302 |
nir | +0.294 |
Tags | +0.293 |
Neg logit contributions | |
sbm | -0.282 |
bro | -0.270 |
Cub | -0.254 |
worth | -0.238 |
\/ | -0.233 |
Token | a |
Token ID | 257 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
Rue | +0.448 |
yss | +0.436 |
Jung | +0.405 |
nir | +0.393 |
Tags | +0.389 |
Neg logit contributions | |
sbm | -0.500 |
bro | -0.477 |
Cub | -0.455 |
worth | -0.432 |
\/ | -0.424 |
Token | cases |
Token ID | 2663 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
sbm | +0.066 |
bro | +0.064 |
Cub | +0.060 |
worth | +0.058 |
\/ | +0.057 |
Neg logit contributions | |
Rue | -0.057 |
yss | -0.055 |
Jung | -0.051 |
nir | -0.050 |
Tags | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
Rue | +1.535 |
yss | +1.478 |
Jung | +1.397 |
nir | +1.342 |
Tags | +1.333 |
Neg logit contributions | |
sbm | -1.552 |
bro | -1.471 |
Cub | -1.402 |
worth | -1.326 |
\/ | -1.298 |
Token | since |
Token ID | 1201 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
Rue | +0.759 |
yss | +0.734 |
Jung | +0.698 |
nir | +0.673 |
Tags | +0.670 |
Neg logit contributions | |
sbm | -0.602 |
bro | -0.567 |
Cub | -0.536 |
worth | -0.502 |
\/ | -0.491 |
Token | Dartmouth |
Token ID | 47888 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
Rue | +0.038 |
yss | +0.037 |
Jung | +0.034 |
nir | +0.033 |
Tags | +0.033 |
Neg logit contributions | |
sbm | -0.040 |
bro | -0.039 |
Cub | -0.037 |
worth | -0.035 |
\/ | -0.034 |
Token | College |
Token ID | 5535 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
sbm | +0.519 |
bro | +0.499 |
Cub | +0.474 |
worth | +0.453 |
\/ | +0.444 |
Neg logit contributions | |
Rue | -0.431 |
yss | -0.418 |
Jung | -0.388 |
nir | -0.375 |
Tags | -0.371 |
Token | v |
Token ID | 410 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
Rue | +0.477 |
yss | +0.461 |
Jung | +0.431 |
nir | +0.414 |
Tags | +0.411 |
Neg logit contributions | |
sbm | -0.555 |
bro | -0.532 |
Cub | -0.507 |
worth | -0.482 |
\/ | -0.474 |
Token | . |
Token ID | 13 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
Rue | +2.922 |
yss | +2.664 |
Jung | +2.636 |
Tags | +2.461 |
nir | +2.403 |
Neg logit contributions | |
sbm | -3.557 |
bro | -3.345 |
Cub | -3.211 |
senal | -3.134 |
worth | -3.035 |
Token | Woodward |
Token ID | 40782 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Rue | +0.545 |
yss | +0.531 |
Jung | +0.494 |
nir | +0.479 |
Tags | +0.474 |
Neg logit contributions | |
sbm | -0.605 |
bro | -0.577 |
Cub | -0.550 |
worth | -0.523 |
\/ | -0.512 |
Token | in |
Token ID | 287 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
sbm | +0.226 |
bro | +0.217 |
Cub | +0.206 |
worth | +0.197 |
\/ | +0.192 |
Neg logit contributions | |
Rue | -0.200 |
yss | -0.194 |
Jung | -0.181 |
nir | -0.175 |
Tags | -0.173 |
Token | 18 |
Token ID | 1248 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
Rue | +0.150 |
yss | +0.148 |
Jung | +0.138 |
nir | +0.134 |
Tags | +0.134 |
Neg logit contributions | |
sbm | -0.132 |
bro | -0.127 |
Cub | -0.120 |
worth | -0.114 |
\/ | -0.111 |
Token | 19 |
Token ID | 1129 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
Rue | +0.040 |
yss | +0.039 |
Jung | +0.037 |
nir | +0.036 |
Tags | +0.036 |
Neg logit contributions | |
sbm | -0.028 |
bro | -0.026 |
Cub | -0.025 |
worth | -0.023 |
\/ | -0.023 |
Token | ] |
Token ID | 60 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
sbm | +0.443 |
bro | +0.425 |
Cub | +0.404 |
worth | +0.384 |
\/ | +0.378 |
Neg logit contributions | |
Rue | -0.416 |
yss | -0.402 |
Jung | -0.377 |
nir | -0.364 |
Tags | -0.360 |
Token | se |
Token ID | 325 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Rue | +0.539 |
yss | +0.518 |
Jung | +0.488 |
nir | +0.468 |
Tags | +0.465 |
Neg logit contributions | |
sbm | -0.587 |
bro | -0.559 |
Cub | -0.533 |
worth | -0.505 |
\/ | -0.495 |
Token | [ |
Token ID | 58 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Rue | +0.798 |
yss | +0.771 |
Jung | +0.728 |
nir | +0.702 |
Tags | +0.699 |
Neg logit contributions | |
sbm | -0.727 |
bro | -0.685 |
Cub | -0.653 |
worth | -0.615 |
\/ | -0.599 |
Token | t |
Token ID | 83 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
sbm | +0.244 |
bro | +0.232 |
Cub | +0.218 |
worth | +0.206 |
\/ | +0.202 |
Neg logit contributions | |
Rue | -0.293 |
yss | -0.283 |
Jung | -0.269 |
nir | -0.259 |
Tags | -0.257 |
Token | ] |
Token ID | 60 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
Rue | +0.811 |
yss | +0.782 |
Jung | +0.738 |
nir | +0.710 |
Tags | +0.706 |
Neg logit contributions | |
sbm | -0.802 |
bro | -0.762 |
Cub | -0.724 |
worth | -0.685 |
\/ | -0.671 |
Token | { |
Token ID | 1391 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
Rue | +0.669 |
yss | +0.645 |
Jung | +0.609 |
nir | +0.585 |
Tags | +0.582 |
Neg logit contributions | |
sbm | -0.664 |
bro | -0.631 |
Cub | -0.600 |
worth | -0.568 |
\/ | -0.556 |
Token | options |
Token ID | 25811 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Rue | +3.025 |
yss | +2.909 |
Jung | +2.747 |
Tags | +2.661 |
nir | +2.638 |
Neg logit contributions | |
sbm | -3.109 |
bro | -2.922 |
Cub | -2.798 |
worth | -2.636 |
��極 | -2.575 |
Token | } |
Token ID | 92 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Rue | +1.393 |
yss | +1.356 |
Jung | +1.302 |
nir | +1.266 |
Tags | +1.261 |
Neg logit contributions | |
sbm | -0.633 |
bro | -0.580 |
Cub | -0.535 |
worth | -0.484 |
\/ | -0.465 |
Token | :[ |
Token ID | 33250 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
Rue | +1.180 |
yss | +1.137 |
Jung | +1.069 |
nir | +1.025 |
Tags | +1.017 |
Neg logit contributions | |
sbm | -1.315 |
bro | -1.253 |
Cub | -1.195 |
worth | -1.134 |
\/ | -1.113 |
Token | text |
Token ID | 5239 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
sbm | +0.524 |
bro | +0.499 |
Cub | +0.472 |
worth | +0.448 |
\/ | +0.440 |
Neg logit contributions | |
Rue | -0.568 |
yss | -0.548 |
Jung | -0.519 |
nir | -0.499 |
refriger | -0.495 |
Token | ] |
Token ID | 60 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Rue | +0.132 |
yss | +0.127 |
Jung | +0.120 |
nir | +0.115 |
Tags | +0.114 |
Neg logit contributions | |
sbm | -0.141 |
bro | -0.136 |
Cub | -0.129 |
worth | -0.122 |
\/ | -0.120 |
Token | s |
Token ID | 82 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
sbm | +0.265 |
bro | +0.250 |
Cub | +0.237 |
worth | +0.222 |
\/ | +0.217 |
Neg logit contributions | |
Rue | -0.322 |
yss | -0.311 |
Jung | -0.296 |
nir | -0.285 |
Tags | -0.283 |
Token | Format |
Token ID | 26227 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
sbm | +0.177 |
bro | +0.169 |
Cub | +0.161 |
worth | +0.153 |
\/ | +0.150 |
Neg logit contributions | |
Rue | -0.155 |
yss | -0.149 |
Jung | -0.140 |
nir | -0.134 |
Tags | -0.133 |
Token | ) |
Token ID | 8 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
Rue | +0.871 |
yss | +0.840 |
Jung | +0.790 |
nir | +0.757 |
Tags | +0.748 |
Neg logit contributions | |
sbm | -0.988 |
bro | -0.944 |
Cub | -0.902 |
worth | -0.854 |
\/ | -0.838 |
Token | } |
Token ID | 1782 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
Rue | +0.398 |
yss | +0.387 |
Jung | +0.368 |
nir | +0.358 |
Tags | +0.355 |
Neg logit contributions | |
sbm | -0.258 |
bro | -0.244 |
Cub | -0.227 |
worth | -0.212 |
\/ | -0.206 |
Token | else |
Token ID | 2073 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Rue | +0.823 |
yss | +0.801 |
Jung | +0.764 |
nir | +0.742 |
Tags | +0.737 |
Neg logit contributions | |
sbm | -0.503 |
bro | -0.472 |
Cub | -0.440 |
worth | -0.407 |
\/ | -0.396 |
Token | { |
Token ID | 1391 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
sbm | +1.004 |
bro | +0.964 |
Cub | +0.903 |
worth | +0.853 |
\/ | +0.830 |
Neg logit contributions | |
Rue | -1.159 |
yss | -1.128 |
Jung | -1.069 |
nir | -1.027 |
Tags | -1.016 |
Token | $ |
Token ID | 720 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Rue | +2.643 |
yss | +2.512 |
Jung | +2.363 |
Tags | +2.266 |
nir | +2.248 |
Neg logit contributions | |
sbm | -3.455 |
bro | -3.250 |
Cub | -3.141 |
worth | -2.996 |
\/ | -2.933 |
Token | font |
Token ID | 10331 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
sbm | +0.176 |
bro | +0.166 |
Cub | +0.157 |
worth | +0.148 |
\/ | +0.144 |
Neg logit contributions | |
Rue | -0.208 |
yss | -0.202 |
Jung | -0.191 |
nir | -0.185 |
Tags | -0.184 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
sbm | +0.532 |
bro | +0.506 |
Cub | +0.481 |
worth | +0.455 |
\/ | +0.445 |
Neg logit contributions | |
Rue | -0.533 |
yss | -0.514 |
Jung | -0.485 |
nir | -0.466 |
Tags | -0.462 |
Token | = |
Token ID | 796 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
sbm | +0.129 |
bro | +0.123 |
Cub | +0.116 |
worth | +0.110 |
\/ | +0.107 |
Neg logit contributions | |
Rue | -0.141 |
yss | -0.137 |
Jung | -0.129 |
nir | -0.124 |
Tags | -0.123 |
Token | New |
Token ID | 968 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Rue | +0.604 |
yss | +0.579 |
Jung | +0.541 |
nir | +0.517 |
Tags | +0.513 |
Neg logit contributions | |
sbm | -0.797 |
bro | -0.762 |
Cub | -0.730 |
worth | -0.695 |
\/ | -0.683 |
Token | Width |
Token ID | 38807 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
sbm | +0.865 |
bro | +0.828 |
Cub | +0.788 |
worth | +0.743 |
\/ | +0.729 |
Neg logit contributions | |
Rue | -0.879 |
yss | -0.850 |
Jung | -0.799 |
nir | -0.769 |
Tags | -0.761 |
Token | , |
Token ID | 11 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
Rue | +0.726 |
yss | +0.697 |
Jung | +0.657 |
nir | +0.629 |
Tags | +0.626 |
Neg logit contributions | |
sbm | -0.799 |
bro | -0.758 |
Cub | -0.723 |
worth | -0.687 |
\/ | -0.672 |
Token | Height |
Token ID | 23106 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
sbm | +0.562 |
bro | +0.542 |
Cub | +0.523 |
worth | +0.499 |
\/ | +0.493 |
Neg logit contributions | |
Rue | -0.331 |
yss | -0.318 |
Jung | -0.292 |
nir | -0.279 |
Tags | -0.274 |
Token | } |
Token ID | 1782 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
sbm | +0.742 |
bro | +0.710 |
Cub | +0.680 |
worth | +0.641 |
\/ | +0.630 |
Neg logit contributions | |
Rue | -0.701 |
yss | -0.680 |
Jung | -0.639 |
nir | -0.617 |
Tags | -0.606 |
Token | else |
Token ID | 2073 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Rue | +0.431 |
yss | +0.417 |
Jung | +0.390 |
nir | +0.375 |
Tags | +0.371 |
Neg logit contributions | |
sbm | -0.511 |
bro | -0.491 |
Cub | -0.466 |
worth | -0.444 |
\/ | -0.437 |
Token | { |
Token ID | 1391 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
sbm | +1.101 |
bro | +1.061 |
Cub | +0.988 |
worth | +0.937 |
\/ | +0.910 |
Neg logit contributions | |
Rue | -1.282 |
yss | -1.251 |
Jung | -1.182 |
nir | -1.139 |
Tags | -1.128 |
Token | Write |
Token ID | 19430 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
Rue | +2.718 |
yss | +2.585 |
Jung | +2.443 |
nir | +2.328 |
Tags | +2.321 |
Neg logit contributions | |
sbm | -3.348 |
bro | -3.164 |
Cub | -3.044 |
worth | -2.899 |
\/ | -2.843 |
Token | - |
Token ID | 12 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Rue | +0.431 |
yss | +0.413 |
Jung | +0.390 |
Tags | +0.374 |
nir | +0.374 |
Neg logit contributions | |
sbm | -0.458 |
bro | -0.431 |
Cub | -0.412 |
worth | -0.391 |
EEE | -0.380 |
Token | Warning |
Token ID | 20361 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
sbm | +0.801 |
bro | +0.769 |
Cub | +0.724 |
worth | +0.674 |
\/ | +0.661 |
Neg logit contributions | |
Rue | -1.031 |
yss | -1.007 |
Jung | -0.950 |
refriger | -0.911 |
nir | -0.908 |
Token | - |
Token ID | 532 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
sbm | +1.040 |
bro | +0.999 |
Cub | +0.948 |
worth | +0.878 |
\/ | +0.873 |
Neg logit contributions | |
Rue | -1.246 |
yss | -1.224 |
Jung | -1.138 |
nir | -1.113 |
ukong | -1.096 |
Token | Message |
Token ID | 12837 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
sbm | +0.235 |
bro | +0.222 |
Cub | +0.210 |
worth | +0.197 |
\/ | +0.193 |
Neg logit contributions | |
Rue | -0.288 |
yss | -0.279 |
Jung | -0.265 |
nir | -0.256 |
Tags | -0.254 |
Token | Want |
Token ID | 16168 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
sbm | +0.152 |
bro | +0.145 |
Cub | +0.137 |
worth | +0.130 |
\/ | +0.128 |
Neg logit contributions | |
Rue | -0.166 |
yss | -0.162 |
Jung | -0.152 |
nir | -0.147 |
Tags | -0.146 |
Token | Some |
Token ID | 2773 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Rue | +0.091 |
yss | +0.088 |
Jung | +0.083 |
nir | +0.079 |
Tags | +0.079 |
Neg logit contributions | |
sbm | -0.105 |
bro | -0.100 |
Cub | -0.096 |
worth | -0.091 |
\/ | -0.089 |
Token | Pictures |
Token ID | 20051 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Rue | +1.115 |
yss | +1.071 |
Jung | +1.014 |
nir | +0.971 |
Tags | +0.967 |
Neg logit contributions | |
sbm | -1.158 |
bro | -1.099 |
Cub | -1.046 |
worth | -0.990 |
\/ | -0.969 |
Token | of |
Token ID | 286 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
sbm | +0.252 |
bro | +0.242 |
Cub | +0.231 |
worth | +0.219 |
\/ | +0.215 |
Neg logit contributions | |
Rue | -0.248 |
yss | -0.240 |
Jung | -0.224 |
nir | -0.217 |
Tags | -0.215 |
Token | That |
Token ID | 1320 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
Rue | +0.669 |
yss | +0.644 |
Jung | +0.606 |
nir | +0.581 |
Tags | +0.577 |
Neg logit contributions | |
sbm | -0.737 |
bro | -0.701 |
Cub | -0.669 |
worth | -0.634 |
\/ | -0.622 |
Token | Corner |
Token ID | 26212 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
Rue | +0.703 |
yss | +0.676 |
Jung | +0.638 |
nir | +0.612 |
Tags | +0.608 |
Neg logit contributions | |
sbm | -0.743 |
bro | -0.706 |
Cub | -0.673 |
worth | -0.637 |
\/ | -0.624 |
Token | Vari |
Token ID | 15965 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
Rue | +2.927 |
yss | +2.786 |
Jung | +2.662 |
nir | +2.540 |
Tags | +2.511 |
Neg logit contributions | |
sbm | -3.080 |
bro | -2.898 |
Cub | -2.756 |
worth | -2.603 |
EEE | -2.559 |
Token | ation |
Token ID | 341 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Rue | +1.642 |
yss | +1.559 |
Jung | +1.462 |
nir | +1.398 |
Tags | +1.377 |
Neg logit contributions | |
sbm | -2.356 |
bro | -2.250 |
Cub | -2.157 |
worth | -2.057 |
\/ | -2.020 |
Token | , |
Token ID | 11 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
Rue | +1.318 |
yss | +1.275 |
Jung | +1.199 |
nir | +1.158 |
Tags | +1.149 |
Neg logit contributions | |
sbm | -1.293 |
bro | -1.229 |
Cub | -1.171 |
worth | -1.107 |
\/ | -1.084 |
Token | Don |
Token ID | 2094 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Rue | +0.365 |
yss | +0.353 |
Jung | +0.330 |
nir | +0.318 |
Tags | +0.316 |
Neg logit contributions | |
sbm | -0.412 |
bro | -0.394 |
Cub | -0.376 |
worth | -0.357 |
\/ | -0.350 |
Token | � |
Token ID | 447 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
Rue | +1.314 |
yss | +1.261 |
Jung | +1.189 |
nir | +1.139 |
Tags | +1.132 |
Neg logit contributions | |
sbm | -1.470 |
bro | -1.400 |
Cub | -1.336 |
worth | -1.267 |
\/ | -1.241 |
Token | in |
Token ID | 287 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
Rue | +0.333 |
yss | +0.326 |
Jung | +0.303 |
nir | +0.294 |
Tags | +0.292 |
Neg logit contributions | |
sbm | -0.394 |
bro | -0.378 |
Cub | -0.360 |
worth | -0.347 |
\/ | -0.338 |
Token | Bram |
Token ID | 35315 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
Rue | +0.314 |
yss | +0.308 |
Jung | +0.285 |
nir | +0.277 |
Tags | +0.276 |
Neg logit contributions | |
sbm | -0.362 |
bro | -0.348 |
Cub | -0.331 |
worth | -0.317 |
\/ | -0.310 |
Token | pton |
Token ID | 10972 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
Rue | +0.540 |
yss | +0.517 |
Jung | +0.487 |
nir | +0.465 |
Tags | +0.461 |
Neg logit contributions | |
sbm | -0.635 |
bro | -0.598 |
Cub | -0.575 |
worth | -0.544 |
EEE | -0.536 |
Token | to |
Token ID | 284 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
sbm | +0.062 |
bro | +0.059 |
Cub | +0.056 |
worth | +0.054 |
\/ | +0.053 |
Neg logit contributions | |
Rue | -0.052 |
yss | -0.051 |
Jung | -0.047 |
nir | -0.046 |
Tags | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
sbm | +0.219 |
bro | +0.210 |
Cub | +0.200 |
worth | +0.190 |
\/ | +0.186 |
Neg logit contributions | |
Rue | -0.198 |
yss | -0.194 |
Jung | -0.180 |
nir | -0.176 |
Tags | -0.175 |
Token | shore |
Token ID | 15191 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
sbm | +0.220 |
bro | +0.210 |
Cub | +0.201 |
worth | +0.191 |
\/ | +0.187 |
Neg logit contributions | |
Rue | -0.191 |
yss | -0.186 |
Jung | -0.173 |
nir | -0.169 |
Tags | -0.168 |
Token | of |
Token ID | 286 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Rue | +2.784 |
yss | +2.667 |
Jung | +2.512 |
nir | +2.396 |
Tags | +2.390 |
Neg logit contributions | |
sbm | -3.186 |
bro | -3.010 |
Cub | -2.889 |
worth | -2.716 |
\/ | -2.676 |
Token | Lake |
Token ID | 6233 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
sbm | +0.160 |
bro | +0.153 |
Cub | +0.144 |
worth | +0.137 |
\/ | +0.133 |
Neg logit contributions | |
Rue | -0.189 |
yss | -0.186 |
Jung | -0.175 |
nir | -0.171 |
Tags | -0.171 |
Token | Ontario |
Token ID | 10553 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Rue | +0.240 |
yss | +0.232 |
Jung | +0.214 |
nir | +0.209 |
Tags | +0.208 |
Neg logit contributions | |
sbm | -0.329 |
bro | -0.317 |
Cub | -0.300 |
worth | -0.293 |
\/ | -0.284 |
Token | south |
Token ID | 5366 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
Rue | +1.141 |
yss | +1.105 |
Jung | +1.035 |
nir | +0.999 |
Tags | +0.992 |
Neg logit contributions | |
sbm | -1.247 |
bro | -1.193 |
Cub | -1.134 |
worth | -1.082 |
\/ | -1.061 |
Token | of |
Token ID | 286 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Rue | +0.658 |
yss | +0.631 |
Jung | +0.591 |
nir | +0.564 |
Tags | +0.560 |
Neg logit contributions | |
sbm | -0.840 |
bro | -0.802 |
Cub | -0.768 |
worth | -0.730 |
\/ | -0.717 |
Token | ex |
Token ID | 1069 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Rue | +0.914 |
yss | +0.891 |
Jung | +0.853 |
nir | +0.833 |
Tags | +0.828 |
Neg logit contributions | |
sbm | -0.442 |
bro | -0.406 |
Cub | -0.377 |
worth | -0.341 |
\/ | -0.328 |
Token | :" |
Token ID | 11097 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Rue | +0.088 |
yss | +0.085 |
Jung | +0.081 |
nir | +0.078 |
Tags | +0.077 |
Neg logit contributions | |
sbm | -0.074 |
bro | -0.070 |
Cub | -0.066 |
worth | -0.062 |
\/ | -0.061 |
Token | [ |
Token ID | 685 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
Rue | +0.724 |
yss | +0.699 |
Jung | +0.651 |
nir | +0.625 |
Tags | +0.616 |
Neg logit contributions | |
sbm | -0.916 |
bro | -0.874 |
Cub | -0.836 |
worth | -0.798 |
\/ | -0.783 |
Token | white |
Token ID | 11186 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
Rue | +0.805 |
yss | +0.782 |
Jung | +0.747 |
nir | +0.725 |
Tags | +0.724 |
Neg logit contributions | |
sbm | -0.475 |
bro | -0.441 |
Cub | -0.413 |
worth | -0.380 |
\/ | -0.369 |
Token | ] |
Token ID | 60 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
sbm | +0.680 |
bro | +0.656 |
Cub | +0.623 |
worth | +0.591 |
\/ | +0.584 |
Neg logit contributions | |
Rue | -0.653 |
yss | -0.633 |
Jung | -0.592 |
nir | -0.573 |
Tags | -0.564 |
Token | optional |
Token ID | 11902 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
Rue | +0.365 |
yss | +0.350 |
Jung | +0.324 |
nir | +0.308 |
Tags | +0.305 |
Neg logit contributions | |
sbm | -0.546 |
bro | -0.524 |
Cub | -0.502 |
worth | -0.481 |
\/ | -0.473 |
Token | white |
Token ID | 2330 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Rue | +2.938 |
yss | +2.809 |
Jung | +2.685 |
Tags | +2.570 |
nir | +2.555 |
Neg logit contributions | |
sbm | -2.809 |
bro | -2.649 |
Cub | -2.536 |
worth | -2.379 |
\/ | -2.312 |
Token | space |
Token ID | 2272 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
sbm | +0.234 |
bro | +0.228 |
Cub | +0.220 |
worth | +0.212 |
\/ | +0.210 |
Neg logit contributions | |
Rue | -0.106 |
yss | -0.102 |
Jung | -0.090 |
nir | -0.085 |
Tags | -0.083 |
Token | se |
Token ID | 384 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
sbm | +0.340 |
bro | +0.324 |
Cub | +0.305 |
worth | +0.287 |
\/ | +0.286 |
Neg logit contributions | |
Rue | -0.386 |
yss | -0.376 |
Jung | -0.354 |
nir | -0.342 |
ukong | -0.337 |
Token | [ |
Token ID | 58 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
Rue | +1.014 |
yss | +0.976 |
Jung | +0.918 |
nir | +0.881 |
Tags | +0.872 |
Neg logit contributions | |
sbm | -1.136 |
bro | -1.084 |
Cub | -1.033 |
worth | -0.981 |
\/ | -0.962 |
Token | t |
Token ID | 83 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
sbm | +0.327 |
bro | +0.312 |
Cub | +0.295 |
worth | +0.282 |
\/ | +0.278 |
Neg logit contributions | |
Rue | -0.314 |
yss | -0.302 |
Jung | -0.286 |
nir | -0.272 |
refriger | -0.272 |
Token |
|
Token ID | 198 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
Rue | +0.777 |
yss | +0.749 |
Jung | +0.707 |
nir | +0.680 |
Tags | +0.676 |
Neg logit contributions | |
sbm | -0.776 |
bro | -0.737 |
Cub | -0.702 |
worth | -0.663 |
\/ | -0.649 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
sbm | +0.395 |
bro | +0.378 |
Cub | +0.359 |
worth | +0.340 |
\/ | +0.333 |
Neg logit contributions | |
Rue | -0.425 |
yss | -0.419 |
Jung | -0.388 |
nir | -0.377 |
refriger | -0.373 |
Token | V |
Token ID | 53 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
sbm | +0.109 |
bro | +0.104 |
Cub | +0.100 |
worth | +0.093 |
\/ | +0.091 |
Neg logit contributions | |
Rue | -0.112 |
yss | -0.108 |
Jung | -0.103 |
nir | -0.098 |
refriger | -0.097 |
Token | il |
Token ID | 346 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Rue | +0.975 |
yss | +0.942 |
Jung | +0.893 |
nir | +0.861 |
Tags | +0.856 |
Neg logit contributions | |
sbm | -0.846 |
bro | -0.801 |
Cub | -0.759 |
worth | -0.714 |
\/ | -0.698 |
Token | ma |
Token ID | 2611 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
sbm | +0.990 |
bro | +0.966 |
Cub | +0.903 |
worth | +0.867 |
\/ | +0.838 |
Neg logit contributions | |
Rue | -1.081 |
yss | -1.048 |
Jung | -0.993 |
Tags | -0.953 |
refriger | -0.948 |
Token | v |
Token ID | 410 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
sbm | +0.208 |
bro | +0.199 |
Cub | +0.190 |
worth | +0.180 |
\/ | +0.176 |
Neg logit contributions | |
Rue | -0.192 |
yss | -0.185 |
Jung | -0.174 |
nir | -0.168 |
Tags | -0.167 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
Rue | +2.736 |
yss | +2.595 |
Jung | +2.466 |
nir | +2.341 |
Tags | +2.338 |
Neg logit contributions | |
sbm | -3.023 |
bro | -2.853 |
Cub | -2.721 |
worth | -2.554 |
\/ | -2.526 |
Token | Goodell |
Token ID | 41648 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
sbm | +0.144 |
bro | +0.138 |
Cub | +0.132 |
worth | +0.125 |
\/ | +0.123 |
Neg logit contributions | |
Rue | -0.130 |
yss | -0.129 |
Jung | -0.119 |
nir | -0.117 |
Tags | -0.114 |
Token | Def |
Token ID | 2896 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
sbm | +0.327 |
bro | +0.313 |
Cub | +0.298 |
worth | +0.284 |
\/ | +0.277 |
Neg logit contributions | |
Rue | -0.297 |
yss | -0.287 |
Jung | -0.270 |
nir | -0.261 |
Tags | -0.257 |
Token | amation |
Token ID | 14755 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Rue | +0.128 |
yss | +0.124 |
Jung | +0.119 |
nir | +0.114 |
Tags | +0.114 |
Neg logit contributions | |
sbm | -0.082 |
bro | -0.077 |
Cub | -0.072 |
worth | -0.067 |
\/ | -0.066 |
Token | / |
Token ID | 1220 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
Rue | +0.781 |
yss | +0.753 |
Jung | +0.700 |
nir | +0.673 |
Tags | +0.666 |
Neg logit contributions | |
sbm | -1.018 |
bro | -0.975 |
Cub | -0.931 |
worth | -0.887 |
\/ | -0.874 |
Token | ] |
Token ID | 60 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
Rue | +0.314 |
yss | +0.303 |
Jung | +0.285 |
nir | +0.274 |
Tags | +0.271 |
Neg logit contributions | |
sbm | -0.320 |
bro | -0.308 |
Cub | -0.291 |
worth | -0.277 |
\/ | -0.273 |
Token | any |
Token ID | 597 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
Rue | +0.709 |
yss | +0.683 |
Jung | +0.644 |
nir | +0.619 |
Tags | +0.613 |
Neg logit contributions | |
sbm | -0.738 |
bro | -0.702 |
Cub | -0.669 |
worth | -0.633 |
\/ | -0.621 |
Token | text |
Token ID | 2420 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Rue | +0.582 |
yss | +0.560 |
Jung | +0.525 |
nir | +0.505 |
Tags | +0.498 |
Neg logit contributions | |
sbm | -0.636 |
bro | -0.607 |
Cub | -0.577 |
worth | -0.549 |
\/ | -0.541 |
Token | or |
Token ID | 393 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
Rue | +0.160 |
yss | +0.155 |
Jung | +0.145 |
nir | +0.140 |
Tags | +0.138 |
Neg logit contributions | |
sbm | -0.169 |
bro | -0.162 |
Cub | -0.153 |
worth | -0.146 |
\/ | -0.144 |
Token | empty |
Token ID | 6565 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Rue | +0.116 |
yss | +0.112 |
Jung | +0.105 |
nir | +0.101 |
Tags | +0.099 |
Neg logit contributions | |
sbm | -0.136 |
bro | -0.130 |
Cub | -0.124 |
worth | -0.117 |
\/ | -0.116 |
Token | { |
Token ID | 1391 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
Rue | +0.723 |
yss | +0.698 |
Jung | +0.655 |
nir | +0.631 |
Tags | +0.623 |
Neg logit contributions | |
sbm | -0.789 |
bro | -0.751 |
Cub | -0.716 |
worth | -0.679 |
\/ | -0.668 |
Token | white |
Token ID | 11186 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
Rue | +2.778 |
yss | +2.668 |
Jung | +2.512 |
Tags | +2.444 |
nir | +2.434 |
Neg logit contributions | |
sbm | -2.869 |
bro | -2.710 |
Cub | -2.583 |
worth | -2.427 |
��極 | -2.366 |
Token | } |
Token ID | 92 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
sbm | +0.457 |
bro | +0.432 |
Cub | +0.402 |
worth | +0.375 |
\/ | +0.367 |
Neg logit contributions | |
Rue | -0.748 |
yss | -0.727 |
Jung | -0.693 |
nir | -0.673 |
Tags | -0.667 |
Token | at |
Token ID | 379 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Rue | +1.205 |
yss | +1.160 |
Jung | +1.092 |
nir | +1.048 |
Tags | +1.041 |
Neg logit contributions | |
sbm | -1.314 |
bro | -1.250 |
Cub | -1.192 |
worth | -1.130 |
\/ | -1.108 |
Token | least |
Token ID | 1551 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
Rue | +0.197 |
yss | +0.189 |
Jung | +0.177 |
nir | +0.170 |
Tags | +0.168 |
Neg logit contributions | |
sbm | -0.222 |
bro | -0.212 |
Cub | -0.202 |
worth | -0.192 |
\/ | -0.189 |
Token | one |
Token ID | 530 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
Rue | +0.345 |
yss | +0.332 |
Jung | +0.312 |
nir | +0.300 |
Tags | +0.298 |
Neg logit contributions | |
sbm | -0.373 |
bro | -0.355 |
Cub | -0.338 |
worth | -0.320 |
\/ | -0.314 |
Token | div |
Token ID | 7146 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
Rue | +1.669 |
yss | +1.613 |
Jung | +1.533 |
nir | +1.486 |
Tags | +1.476 |
Neg logit contributions | |
sbm | -1.316 |
bro | -1.235 |
Cub | -1.170 |
worth | -1.095 |
EEE | -1.070 |
Token | ide |
Token ID | 485 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Rue | +0.601 |
yss | +0.580 |
Jung | +0.544 |
nir | +0.521 |
Tags | +0.516 |
Neg logit contributions | |
sbm | -0.666 |
bro | -0.635 |
Cub | -0.606 |
worth | -0.574 |
\/ | -0.566 |
Token | ( |
Token ID | 7 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
Rue | +0.781 |
yss | +0.752 |
Jung | +0.708 |
nir | +0.680 |
Tags | +0.676 |
Neg logit contributions | |
sbm | -0.853 |
bro | -0.811 |
Cub | -0.774 |
worth | -0.734 |
\/ | -0.719 |
Token | space |
Token ID | 2272 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Rue | +0.780 |
yss | +0.754 |
Jung | +0.716 |
nir | +0.689 |
Tags | +0.685 |
Neg logit contributions | |
sbm | -0.658 |
bro | -0.622 |
Cub | -0.589 |
worth | -0.554 |
\/ | -0.541 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
sbm | +0.150 |
bro | +0.144 |
Cub | +0.137 |
worth | +0.129 |
\/ | +0.127 |
Neg logit contributions | |
Rue | -0.171 |
yss | -0.166 |
Jung | -0.156 |
nir | -0.151 |
refriger | -0.149 |
Token | { |
Token ID | 1391 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
Rue | +0.783 |
yss | +0.756 |
Jung | +0.713 |
nir | +0.686 |
Tags | +0.681 |
Neg logit contributions | |
sbm | -0.781 |
bro | -0.742 |
Cub | -0.706 |
worth | -0.667 |
\/ | -0.653 |
Token | // |
Token ID | 3373 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Rue | +2.448 |
yss | +2.325 |
Jung | +2.206 |
refriger | +2.101 |
nir | +2.098 |
Neg logit contributions | |
sbm | -3.114 |
bro | -2.944 |
Cub | -2.821 |
worth | -2.717 |
EEE | -2.649 |
Token | 1 |
Token ID | 352 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
sbm | +0.539 |
bro | +0.519 |
Cub | +0.497 |
worth | +0.468 |
\/ | +0.459 |
Neg logit contributions | |
Rue | -0.462 |
yss | -0.449 |
Jung | -0.418 |
nir | -0.402 |
Tags | -0.397 |
Token | . |
Token ID | 13 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
Rue | +0.566 |
yss | +0.547 |
Jung | +0.512 |
nir | +0.491 |
Tags | +0.488 |
Neg logit contributions | |
sbm | -0.646 |
bro | -0.618 |
Cub | -0.592 |
worth | -0.558 |
\/ | -0.550 |
Token | Fit |
Token ID | 25048 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Rue | +0.487 |
yss | +0.471 |
Jung | +0.441 |
nir | +0.424 |
Tags | +0.420 |
Neg logit contributions | |
sbm | -0.561 |
bro | -0.534 |
Cub | -0.512 |
worth | -0.484 |
\/ | -0.475 |
Token | an |
Token ID | 281 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
sbm | +1.381 |
bro | +1.323 |
Cub | +1.280 |
worth | +1.190 |
\/ | +1.173 |
Neg logit contributions | |
Rue | -1.233 |
yss | -1.199 |
Jung | -1.118 |
nir | -1.067 |
Tags | -1.056 |
Token |
|
Token ID | 198 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
Rue | +0.169 |
yss | +0.164 |
Jung | +0.154 |
nir | +0.149 |
Tags | +0.147 |
Neg logit contributions | |
sbm | -0.164 |
bro | -0.156 |
Cub | -0.149 |
worth | -0.141 |
\/ | -0.138 |
Token | As |
Token ID | 1722 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
Rue | +0.432 |
yss | +0.419 |
Jung | +0.394 |
nir | +0.377 |
refriger | +0.376 |
Neg logit contributions | |
sbm | -0.399 |
bro | -0.383 |
Cub | -0.365 |
worth | -0.343 |
\/ | -0.335 |
Token | part |
Token ID | 636 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
Rue | +0.439 |
yss | +0.423 |
Jung | +0.395 |
nir | +0.381 |
Tags | +0.377 |
Neg logit contributions | |
sbm | -0.514 |
bro | -0.493 |
Cub | -0.469 |
worth | -0.448 |
\/ | -0.438 |
Token | of |
Token ID | 286 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
Rue | +0.587 |
yss | +0.562 |
Jung | +0.528 |
nir | +0.504 |
Tags | +0.501 |
Neg logit contributions | |
sbm | -0.746 |
bro | -0.711 |
Cub | -0.681 |
worth | -0.648 |
\/ | -0.636 |
Token | that |
Token ID | 326 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
Rue | +0.349 |
yss | +0.336 |
Jung | +0.315 |
nir | +0.303 |
Tags | +0.301 |
Neg logit contributions | |
sbm | -0.390 |
bro | -0.373 |
Cub | -0.355 |
worth | -0.338 |
\/ | -0.331 |
Token | case |
Token ID | 1339 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
Rue | +0.676 |
yss | +0.652 |
Jung | +0.616 |
nir | +0.593 |
Tags | +0.589 |
Neg logit contributions | |
sbm | -0.666 |
bro | -0.632 |
Cub | -0.601 |
worth | -0.568 |
\/ | -0.556 |
Token | , |
Token ID | 11 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Rue | +2.440 |
yss | +2.334 |
Jung | +2.213 |
nir | +2.097 |
refriger | +2.088 |
Neg logit contributions | |
sbm | -3.104 |
bro | -2.932 |
Cub | -2.833 |
worth | -2.678 |
\/ | -2.627 |
Token | P |
Token ID | 350 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Rue | +1.312 |
yss | +1.258 |
Jung | +1.179 |
nir | +1.126 |
Tags | +1.118 |
Neg logit contributions | |
sbm | -1.655 |
bro | -1.580 |
Cub | -1.512 |
worth | -1.439 |
\/ | -1.412 |
Token | eder |
Token ID | 5702 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Rue | +1.004 |
yss | +0.966 |
Jung | +0.906 |
nir | +0.868 |
Tags | +0.860 |
Neg logit contributions | |
sbm | -1.267 |
bro | -1.204 |
Cub | -1.157 |
worth | -1.096 |
\/ | -1.076 |
Token | appeared |
Token ID | 4120 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Rue | +0.746 |
yss | +0.720 |
Jung | +0.677 |
nir | +0.653 |
Tags | +0.649 |
Neg logit contributions | |
sbm | -0.762 |
bro | -0.727 |
Cub | -0.691 |
worth | -0.655 |
\/ | -0.640 |
Token | before |
Token ID | 878 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Rue | +0.082 |
yss | +0.079 |
Jung | +0.073 |
nir | +0.071 |
Tags | +0.071 |
Neg logit contributions | |
sbm | -0.097 |
bro | -0.094 |
Cub | -0.089 |
worth | -0.085 |
\/ | -0.083 |
Token | be |
Token ID | 307 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
Rue | +0.493 |
yss | +0.479 |
Jung | +0.447 |
nir | +0.431 |
Tags | +0.428 |
Neg logit contributions | |
sbm | -0.534 |
bro | -0.513 |
Cub | -0.486 |
worth | -0.463 |
\/ | -0.453 |
Token | the |
Token ID | 262 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Rue | +0.171 |
yss | +0.167 |
Jung | +0.155 |
nir | +0.150 |
Tags | +0.148 |
Neg logit contributions | |
sbm | -0.188 |
bro | -0.181 |
Cub | -0.172 |
worth | -0.164 |
\/ | -0.160 |
Token | equivalent |
Token ID | 7548 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
Rue | +0.234 |
yss | +0.229 |
Jung | +0.211 |
nir | +0.205 |
Tags | +0.202 |
Neg logit contributions | |
sbm | -0.280 |
bro | -0.269 |
Cub | -0.258 |
worth | -0.245 |
\/ | -0.240 |
Token | of |
Token ID | 286 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Rue | +0.423 |
yss | +0.404 |
Jung | +0.379 |
nir | +0.361 |
Tags | +0.359 |
Neg logit contributions | |
sbm | -0.544 |
bro | -0.518 |
Cub | -0.496 |
worth | -0.471 |
\/ | -0.463 |
Token | Loving |
Token ID | 39202 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
Rue | +0.163 |
yss | +0.158 |
Jung | +0.148 |
nir | +0.143 |
Tags | +0.141 |
Neg logit contributions | |
sbm | -0.172 |
bro | -0.164 |
Cub | -0.156 |
worth | -0.148 |
\/ | -0.145 |
Token | v |
Token ID | 410 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
Rue | +0.472 |
yss | +0.450 |
Jung | +0.414 |
nir | +0.392 |
Tags | +0.387 |
Neg logit contributions | |
sbm | -0.824 |
bro | -0.793 |
Cub | -0.763 |
worth | -0.732 |
\/ | -0.720 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
Rue | +2.542 |
yss | +2.332 |
Jung | +2.286 |
Tags | +2.158 |
nir | +2.125 |
Neg logit contributions | |
sbm | -3.039 |
bro | -2.884 |
Cub | -2.731 |
senal | -2.623 |
worth | -2.576 |
Token | Virginia |
Token ID | 6025 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
sbm | +0.021 |
bro | +0.020 |
Cub | +0.019 |
worth | +0.018 |
\/ | +0.018 |
Neg logit contributions | |
Rue | -0.015 |
yss | -0.014 |
Jung | -0.013 |
nir | -0.012 |
Tags | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
sbm | +0.582 |
bro | +0.562 |
Cub | +0.532 |
worth | +0.508 |
\/ | +0.496 |
Neg logit contributions | |
Rue | -0.560 |
yss | -0.549 |
Jung | -0.510 |
nir | -0.495 |
Tags | -0.487 |
Token | which |
Token ID | 543 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
sbm | +0.071 |
bro | +0.068 |
Cub | +0.065 |
worth | +0.062 |
\/ | +0.060 |
Neg logit contributions | |
Rue | -0.067 |
yss | -0.066 |
Jung | -0.061 |
nir | -0.059 |
Tags | -0.059 |
Token | declared |
Token ID | 6875 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
Rue | +0.259 |
yss | +0.254 |
Jung | +0.236 |
nir | +0.230 |
Tags | +0.227 |
Neg logit contributions | |
sbm | -0.253 |
bro | -0.243 |
Cub | -0.230 |
worth | -0.218 |
\/ | -0.212 |
Token | IS |
Token ID | 3180 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
Rue | +0.523 |
yss | +0.508 |
Jung | +0.474 |
nir | +0.458 |
Tags | +0.455 |
Neg logit contributions | |
sbm | -0.549 |
bro | -0.526 |
Cub | -0.500 |
worth | -0.474 |
\/ | -0.468 |
Token | FREE |
Token ID | 17189 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Rue | +0.053 |
yss | +0.052 |
Jung | +0.047 |
nir | +0.046 |
Tags | +0.046 |
Neg logit contributions | |
sbm | -0.063 |
bro | -0.061 |
Cub | -0.058 |
worth | -0.056 |
\/ | -0.055 |
Token | | |
Token ID | 930 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
Rue | +1.267 |
yss | +1.220 |
Jung | +1.142 |
nir | +1.099 |
Tags | +1.091 |
Neg logit contributions | |
sbm | -1.455 |
bro | -1.389 |
Cub | -1.326 |
worth | -1.258 |
\/ | -1.238 |
Token | NO |
Token ID | 8005 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
sbm | +0.430 |
bro | +0.411 |
Cub | +0.392 |
worth | +0.371 |
\/ | +0.369 |
Neg logit contributions | |
Rue | -0.374 |
yss | -0.363 |
Jung | -0.337 |
nir | -0.330 |
Tags | -0.325 |
Token | FE |
Token ID | 18630 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Rue | +0.550 |
yss | +0.528 |
Jung | +0.492 |
nir | +0.474 |
Tags | +0.468 |
Neg logit contributions | |
sbm | -0.692 |
bro | -0.662 |
Cub | -0.632 |
worth | -0.601 |
\/ | -0.593 |
Token | ES |
Token ID | 1546 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
Rue | +0.213 |
yss | +0.205 |
Jung | +0.193 |
nir | +0.186 |
Tags | +0.185 |
Neg logit contributions | |
sbm | -0.219 |
bro | -0.208 |
Cub | -0.198 |
worth | -0.187 |
\/ | -0.184 |
Token | | |
Token ID | 930 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
Rue | +2.696 |
yss | +2.588 |
Jung | +2.461 |
Tags | +2.353 |
nir | +2.350 |
Neg logit contributions | |
sbm | -2.814 |
bro | -2.651 |
Cub | -2.529 |
worth | -2.398 |
\/ | -2.328 |
Token | NO |
Token ID | 8005 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
Rue | +0.221 |
yss | +0.214 |
Jung | +0.199 |
nir | +0.194 |
Tags | +0.192 |
Neg logit contributions | |
sbm | -0.243 |
bro | -0.232 |
Cub | -0.221 |
worth | -0.209 |
\/ | -0.207 |
Token | MIN |
Token ID | 20625 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Rue | +0.550 |
yss | +0.532 |
Jung | +0.491 |
nir | +0.479 |
Tags | +0.470 |
Neg logit contributions | |
sbm | -0.686 |
bro | -0.659 |
Cub | -0.630 |
worth | -0.597 |
\/ | -0.591 |
Token | IM |
Token ID | 3955 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Rue | +0.320 |
yss | +0.310 |
Jung | +0.290 |
nir | +0.284 |
Tags | +0.278 |
Neg logit contributions | |
sbm | -0.312 |
bro | -0.297 |
Cub | -0.284 |
worth | -0.266 |
\/ | -0.264 |
Token | U |
Token ID | 52 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Rue | +0.190 |
yss | +0.180 |
Jung | +0.166 |
nir | +0.161 |
Tags | +0.156 |
Neg logit contributions | |
sbm | -0.325 |
bro | -0.313 |
Cub | -0.301 |
worth | -0.287 |
EEE | -0.285 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
sbm | +0.172 |
bro | +0.165 |
Cub | +0.156 |
worth | +0.148 |
\/ | +0.145 |
Neg logit contributions | |
Rue | -0.184 |
yss | -0.180 |
Jung | -0.167 |
nir | -0.163 |
refriger | -0.160 |
Token | The |
Token ID | 464 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
sbm | +0.086 |
bro | +0.083 |
Cub | +0.079 |
worth | +0.074 |
\/ | +0.072 |
Neg logit contributions | |
Rue | -0.086 |
yss | -0.082 |
Jung | -0.078 |
refriger | -0.074 |
nir | -0.074 |
Token | Icelandic |
Token ID | 41959 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
sbm | +0.110 |
bro | +0.105 |
Cub | +0.101 |
worth | +0.096 |
\/ | +0.094 |
Neg logit contributions | |
Rue | -0.093 |
yss | -0.089 |
Jung | -0.083 |
nir | -0.081 |
Tags | -0.080 |
Token | singer |
Token ID | 14015 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
Rue | +0.278 |
yss | +0.268 |
Jung | +0.249 |
nir | +0.240 |
Tags | +0.238 |
Neg logit contributions | |
sbm | -0.349 |
bro | -0.335 |
Cub | -0.320 |
worth | -0.305 |
\/ | -0.300 |
Token | Bj |
Token ID | 34254 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
sbm | +0.537 |
bro | +0.517 |
Cub | +0.491 |
worth | +0.469 |
\/ | +0.460 |
Neg logit contributions | |
Rue | -0.449 |
yss | -0.435 |
Jung | -0.401 |
nir | -0.389 |
Tags | -0.388 |
Token | ör |
Token ID | 30570 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
Rue | +0.239 |
yss | +0.227 |
Jung | +0.211 |
nir | +0.201 |
Tags | +0.199 |
Neg logit contributions | |
sbm | -0.363 |
bro | -0.349 |
Cub | -0.334 |
worth | -0.320 |
\/ | -0.314 |
Token | k |
Token ID | 74 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Rue | +2.463 |
yss | +2.377 |
Jung | +2.234 |
nir | +2.162 |
Tags | +2.104 |
Neg logit contributions | |
sbm | -3.045 |
bro | -2.868 |
Cub | -2.773 |
worth | -2.632 |
\/ | -2.580 |
Token | has |
Token ID | 468 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
Rue | +1.323 |
yss | +1.275 |
Jung | +1.206 |
nir | +1.157 |
Tags | +1.149 |
Neg logit contributions | |
sbm | -1.338 |
bro | -1.266 |
Cub | -1.206 |
worth | -1.140 |
\/ | -1.117 |
Token | composed |
Token ID | 13160 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
sbm | +0.335 |
bro | +0.327 |
Cub | +0.309 |
worth | +0.293 |
\/ | +0.288 |
Neg logit contributions | |
Rue | -0.304 |
yss | -0.296 |
Jung | -0.272 |
nir | -0.267 |
Tags | -0.264 |
Token | and |
Token ID | 290 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
Rue | +0.460 |
yss | +0.444 |
Jung | +0.417 |
nir | +0.404 |
Tags | +0.400 |
Neg logit contributions | |
sbm | -0.455 |
bro | -0.433 |
Cub | -0.411 |
worth | -0.390 |
\/ | -0.382 |
Token | performed |
Token ID | 6157 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
sbm | +0.057 |
bro | +0.055 |
Cub | +0.052 |
worth | +0.050 |
\/ | +0.049 |
Neg logit contributions | |
Rue | -0.049 |
yss | -0.048 |
Jung | -0.044 |
nir | -0.043 |
Tags | -0.042 |
Token | form |
Token ID | 1296 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
Rue | +0.077 |
yss | +0.075 |
Jung | +0.071 |
nir | +0.068 |
Tags | +0.068 |
Neg logit contributions | |
sbm | -0.072 |
bro | -0.069 |
Cub | -0.065 |
worth | -0.061 |
\/ | -0.060 |
Token | : |
Token ID | 25 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
sbm | +0.313 |
bro | +0.300 |
Cub | +0.283 |
worth | +0.269 |
\/ | +0.265 |
Neg logit contributions | |
Rue | -0.350 |
yss | -0.339 |
Jung | -0.318 |
nir | -0.309 |
Tags | -0.307 |
Token | [ |
Token ID | 685 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
sbm | +0.142 |
bro | +0.135 |
Cub | +0.128 |
worth | +0.122 |
\/ | +0.120 |
Neg logit contributions | |
Rue | -0.132 |
yss | -0.127 |
Jung | -0.119 |
nir | -0.115 |
Tags | -0.114 |
Token | text |
Token ID | 5239 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Rue | +0.313 |
yss | +0.302 |
Jung | +0.286 |
nir | +0.275 |
Tags | +0.273 |
Neg logit contributions | |
sbm | -0.282 |
bro | -0.268 |
Cub | -0.254 |
worth | -0.239 |
\/ | -0.235 |
Token | ] |
Token ID | 60 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Rue | +0.170 |
yss | +0.166 |
Jung | +0.156 |
nir | +0.150 |
refriger | +0.148 |
Neg logit contributions | |
sbm | -0.166 |
bro | -0.160 |
Cub | -0.151 |
worth | -0.144 |
\/ | -0.142 |
Token | { |
Token ID | 90 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
Rue | +0.994 |
yss | +0.959 |
Jung | +0.905 |
nir | +0.871 |
Tags | +0.864 |
Neg logit contributions | |
sbm | -0.968 |
bro | -0.920 |
Cub | -0.874 |
worth | -0.826 |
\/ | -0.810 |
Token | white |
Token ID | 11186 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Rue | +3.019 |
yss | +2.916 |
Jung | +2.770 |
Tags | +2.692 |
nir | +2.685 |
Neg logit contributions | |
sbm | -2.454 |
bro | -2.299 |
Cub | -2.190 |
worth | -2.047 |
EEE | -1.990 |
Token | }{ |
Token ID | 18477 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
sbm | +0.081 |
bro | +0.077 |
Cub | +0.073 |
worth | +0.069 |
\/ | +0.067 |
Neg logit contributions | |
Rue | -0.096 |
yss | -0.093 |
Jung | -0.088 |
nir | -0.085 |
Tags | -0.084 |
Token | vi |
Token ID | 8903 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Rue | +1.359 |
yss | +1.317 |
Jung | +1.250 |
nir | +1.212 |
Tags | +1.207 |
Neg logit contributions | |
sbm | -1.054 |
bro | -0.987 |
Cub | -0.935 |
worth | -0.874 |
\/ | -0.850 |
Token | : |
Token ID | 25 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Rue | +0.214 |
yss | +0.208 |
Jung | +0.198 |
nir | +0.191 |
Tags | +0.190 |
Neg logit contributions | |
sbm | -0.157 |
bro | -0.149 |
Cub | -0.140 |
worth | -0.131 |
\/ | -0.129 |
Token | | |
Token ID | 91 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
Rue | +0.256 |
yss | +0.248 |
Jung | +0.236 |
nir | +0.228 |
Tags | +0.227 |
Neg logit contributions | |
sbm | -0.181 |
bro | -0.170 |
Cub | -0.160 |
worth | -0.149 |
\/ | -0.146 |
Token | :: |
Token ID | 3712 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Rue | +0.766 |
yss | +0.733 |
Jung | +0.690 |
nir | +0.659 |
Tags | +0.658 |
Neg logit contributions | |
sbm | -0.909 |
bro | -0.866 |
Cub | -0.827 |
worth | -0.787 |
\/ | -0.768 |
Token | Center |
Token ID | 23656 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
Rue | +1.537 |
yss | +1.468 |
Jung | +1.397 |
Tags | +1.354 |
nir | +1.347 |
Neg logit contributions | |
sbm | -1.422 |
bro | -1.343 |
Cub | -1.261 |
worth | -1.204 |
\/ | -1.169 |
Token | break |
Token ID | 2270 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Rue | +0.046 |
yss | +0.045 |
Jung | +0.042 |
nir | +0.041 |
Tags | +0.040 |
Neg logit contributions | |
sbm | -0.045 |
bro | -0.043 |
Cub | -0.041 |
worth | -0.039 |
\/ | -0.038 |
Token | } |
Token ID | 1782 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Rue | +1.400 |
yss | +1.362 |
Jung | +1.300 |
nir | +1.263 |
Tags | +1.255 |
Neg logit contributions | |
sbm | -0.813 |
bro | -0.760 |
Cub | -0.709 |
worth | -0.652 |
\/ | -0.633 |
Token | Left |
Token ID | 9578 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
Rue | +1.076 |
yss | +1.047 |
Jung | +0.994 |
nir | +0.964 |
Tags | +0.957 |
Neg logit contributions | |
sbm | -0.781 |
bro | -0.737 |
Cub | -0.694 |
worth | -0.647 |
\/ | -0.632 |
Token | { |
Token ID | 1391 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
sbm | +0.616 |
bro | +0.588 |
Cub | +0.561 |
worth | +0.526 |
\/ | +0.516 |
Neg logit contributions | |
Rue | -0.679 |
yss | -0.658 |
Jung | -0.621 |
nir | -0.602 |
refriger | -0.592 |
Token | $ |
Token ID | 720 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
Rue | +2.497 |
yss | +2.379 |
Jung | +2.245 |
Tags | +2.134 |
nir | +2.130 |
Neg logit contributions | |
sbm | -2.989 |
bro | -2.829 |
Cub | -2.702 |
worth | -2.580 |
\/ | -2.530 |
Token | s |
Token ID | 82 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
sbm | +0.148 |
bro | +0.140 |
Cub | +0.133 |
worth | +0.126 |
\/ | +0.123 |
Neg logit contributions | |
Rue | -0.163 |
yss | -0.158 |
Jung | -0.149 |
nir | -0.144 |
Tags | -0.143 |
Token | Format |
Token ID | 26227 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
sbm | +0.346 |
bro | +0.326 |
Cub | +0.308 |
worth | +0.287 |
\/ | +0.280 |
Neg logit contributions | |
Rue | -0.463 |
yss | -0.449 |
Jung | -0.427 |
nir | -0.413 |
Tags | -0.409 |
Token | . |
Token ID | 13 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
Rue | +0.341 |
yss | +0.330 |
Jung | +0.310 |
nir | +0.298 |
Tags | +0.295 |
Neg logit contributions | |
sbm | -0.361 |
bro | -0.344 |
Cub | -0.328 |
worth | -0.310 |
\/ | -0.304 |
Token | Al |
Token ID | 2348 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Rue | +0.433 |
yss | +0.419 |
Jung | +0.397 |
nir | +0.383 |
Tags | +0.379 |
Neg logit contributions | |
sbm | -0.364 |
bro | -0.344 |
Cub | -0.327 |
worth | -0.306 |
\/ | -0.299 |
Token | a |
Token ID | 257 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
sbm | +0.410 |
bro | +0.397 |
Cub | +0.376 |
worth | +0.359 |
\/ | +0.350 |
Neg logit contributions | |
Rue | -0.405 |
yss | -0.396 |
Jung | -0.369 |
nir | -0.359 |
Tags | -0.356 |
Token | major |
Token ID | 1688 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
sbm | +0.169 |
bro | +0.163 |
Cub | +0.154 |
worth | +0.146 |
\/ | +0.144 |
Neg logit contributions | |
Rue | -0.165 |
yss | -0.159 |
Jung | -0.149 |
nir | -0.145 |
Tags | -0.144 |
Token | Oscars |
Token ID | 46485 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Rue | +0.177 |
yss | +0.171 |
Jung | +0.161 |
nir | +0.157 |
Tags | +0.156 |
Neg logit contributions | |
sbm | -0.173 |
bro | -0.166 |
Cub | -0.157 |
worth | -0.149 |
\/ | -0.146 |
Token |
|
Token ID | 198 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
sbm | +0.296 |
bro | +0.284 |
Cub | +0.270 |
worth | +0.257 |
\/ | +0.254 |
Neg logit contributions | |
Rue | -0.284 |
yss | -0.274 |
Jung | -0.258 |
nir | -0.250 |
Tags | -0.247 |
Token |
|
Token ID | 198 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
sbm | +0.126 |
bro | +0.120 |
Cub | +0.114 |
worth | +0.108 |
\/ | +0.105 |
Neg logit contributions | |
Rue | -0.131 |
yss | -0.128 |
Jung | -0.119 |
nir | -0.115 |
Tags | -0.114 |
Token | cont |
Token ID | 3642 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
Rue | +0.004 |
yss | +0.003 |
Jung | +0.003 |
nir | +0.003 |
refriger | +0.003 |
Neg logit contributions | |
sbm | -0.003 |
bro | -0.003 |
Cub | -0.003 |
worth | -0.003 |
\/ | -0.003 |
Token | ender |
Token ID | 2194 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Rue | +3.050 |
yss | +2.955 |
Jung | +2.793 |
nir | +2.714 |
refriger | +2.659 |
Neg logit contributions | |
sbm | -2.422 |
bro | -2.223 |
Cub | -2.123 |
worth | -1.945 |
\/ | -1.935 |
Token | , |
Token ID | 11 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Rue | +0.929 |
yss | +0.896 |
Jung | +0.842 |
nir | +0.809 |
Tags | +0.804 |
Neg logit contributions | |
sbm | -1.003 |
bro | -0.957 |
Cub | -0.911 |
worth | -0.865 |
\/ | -0.848 |
Token | potentially |
Token ID | 6196 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
sbm | +0.196 |
bro | +0.187 |
Cub | +0.178 |
worth | +0.169 |
\/ | +0.165 |
Neg logit contributions | |
Rue | -0.200 |
yss | -0.194 |
Jung | -0.182 |
nir | -0.176 |
Tags | -0.175 |
Token | picking |
Token ID | 10868 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Rue | +0.583 |
yss | +0.564 |
Jung | +0.529 |
nir | +0.509 |
Tags | +0.506 |
Neg logit contributions | |
sbm | -0.629 |
bro | -0.601 |
Cub | -0.572 |
worth | -0.545 |
\/ | -0.534 |
Token | up |
Token ID | 510 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
sbm | +0.220 |
bro | +0.213 |
Cub | +0.203 |
worth | +0.195 |
\/ | +0.191 |
Neg logit contributions | |
Rue | -0.167 |
yss | -0.162 |
Jung | -0.150 |
nir | -0.145 |
Tags | -0.143 |
Token | search |
Token ID | 12947 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
Rue | +1.660 |
yss | +1.601 |
Jung | +1.512 |
nir | +1.449 |
Tags | +1.440 |
Neg logit contributions | |
sbm | -1.668 |
bro | -1.589 |
Cub | -1.510 |
worth | -1.427 |
\/ | -1.398 |
Token | Space |
Token ID | 14106 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Rue | +0.361 |
yss | +0.349 |
Jung | +0.328 |
nir | +0.313 |
refriger | +0.312 |
Neg logit contributions | |
sbm | -0.371 |
bro | -0.355 |
Cub | -0.340 |
worth | -0.319 |
\/ | -0.316 |
Token | ` |
Token ID | 63 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
sbm | +0.157 |
bro | +0.149 |
Cub | +0.141 |
worth | +0.130 |
\/ | +0.130 |
Neg logit contributions | |
Rue | -0.217 |
yss | -0.211 |
Jung | -0.200 |
nir | -0.193 |
refriger | -0.191 |
Token | *) |
Token ID | 31936 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
Rue | +1.013 |
yss | +0.975 |
Jung | +0.910 |
nir | +0.871 |
Tags | +0.859 |
Neg logit contributions | |
sbm | -1.260 |
bro | -1.206 |
Cub | -1.153 |
worth | -1.095 |
\/ | -1.081 |
Token | (* |
Token ID | 20789 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
sbm | +0.412 |
bro | +0.395 |
Cub | +0.376 |
\/ | +0.355 |
worth | +0.355 |
Neg logit contributions | |
Rue | -0.321 |
yss | -0.316 |
Jung | -0.289 |
ukong | -0.281 |
nir | -0.280 |
Token | { |
Token ID | 1391 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
sbm | +0.794 |
bro | +0.764 |
Cub | +0.724 |
worth | +0.683 |
\/ | +0.677 |
Neg logit contributions | |
Rue | -0.713 |
yss | -0.698 |
Jung | -0.648 |
nir | -0.626 |
ukong | -0.623 |
Token | i |
Token ID | 72 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Rue | +2.766 |
yss | +2.665 |
Jung | +2.525 |
nir | +2.431 |
Tags | +2.422 |
Neg logit contributions | |
sbm | -2.610 |
bro | -2.459 |
Cub | -2.344 |
worth | -2.215 |
\/ | -2.159 |
Token | , |
Token ID | 11 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
sbm | +0.105 |
bro | +0.100 |
Cub | +0.096 |
worth | +0.090 |
\/ | +0.089 |
Neg logit contributions | |
Rue | -0.101 |
yss | -0.098 |
Jung | -0.092 |
nir | -0.089 |
Tags | -0.088 |
Token | { |
Token ID | 90 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
sbm | +1.081 |
bro | +1.036 |
Cub | +0.990 |
worth | +0.939 |
\/ | +0.925 |
Neg logit contributions | |
Rue | -0.869 |
yss | -0.838 |
Jung | -0.775 |
nir | -0.751 |
ukong | -0.739 |
Token | Sub |
Token ID | 7004 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Rue | +1.575 |
yss | +1.521 |
Jung | +1.440 |
nir | +1.387 |
Tags | +1.381 |
Neg logit contributions | |
sbm | -1.465 |
bro | -1.387 |
Cub | -1.318 |
worth | -1.243 |
\/ | -1.216 |
Token | script |
Token ID | 12048 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
sbm | +0.244 |
bro | +0.234 |
Cub | +0.222 |
worth | +0.210 |
\/ | +0.206 |
Neg logit contributions | |
Rue | -0.252 |
yss | -0.244 |
Jung | -0.230 |
nir | -0.220 |
refriger | -0.219 |
Token | " |
Token ID | 366 |
Feature activation | +8.13e-03 |
Pos logit contributions | |
sbm | +0.847 |
bro | +0.824 |
Cub | +0.776 |
worth | +0.739 |
\/ | +0.715 |
Neg logit contributions | |
Rue | -0.901 |
yss | -0.876 |
Jung | -0.819 |
nir | -0.803 |
Tags | -0.791 |
Token | You |
Token ID | 1639 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
sbm | +0.006 |
bro | +0.005 |
Cub | +0.005 |
worth | +0.005 |
\/ | +0.005 |
Neg logit contributions | |
Rue | -0.007 |
yss | -0.006 |
Jung | -0.006 |
nir | -0.006 |
refriger | -0.006 |
Token | know |
Token ID | 760 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
sbm | +0.158 |
bro | +0.154 |
Cub | +0.143 |
worth | +0.137 |
\/ | +0.135 |
Neg logit contributions | |
Rue | -0.164 |
yss | -0.160 |
Jung | -0.149 |
nir | -0.145 |
Tags | -0.144 |
Token | what |
Token ID | 644 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
sbm | +0.150 |
bro | +0.145 |
Cub | +0.136 |
worth | +0.129 |
\/ | +0.127 |
Neg logit contributions | |
Rue | -0.166 |
yss | -0.162 |
Jung | -0.151 |
nir | -0.148 |
Tags | -0.147 |
Token | I |
Token ID | 314 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
sbm | +0.147 |
bro | +0.146 |
Cub | +0.135 |
worth | +0.129 |
\/ | +0.125 |
Neg logit contributions | |
Rue | -0.168 |
yss | -0.164 |
Jung | -0.152 |
Tags | -0.150 |
nir | -0.150 |
Token | mean |
Token ID | 1612 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
sbm | +0.619 |
bro | +0.606 |
Cub | +0.561 |
worth | +0.547 |
EEE | +0.535 |
Neg logit contributions | |
Rue | -0.572 |
yss | -0.562 |
Jung | -0.518 |
nir | -0.504 |
Tags | -0.499 |
Token | ." |
Token ID | 526 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
sbm | +2.608 |
bro | +2.598 |
Cub | +2.457 |
worth | +2.325 |
EEE | +2.303 |
Neg logit contributions | |
Rue | -2.662 |
yss | -2.608 |
nir | -2.398 |
Tags | -2.380 |
Jung | -2.374 |
Token | I |
Token ID | 314 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
sbm | +0.200 |
bro | +0.191 |
Cub | +0.181 |
worth | +0.172 |
\/ | +0.167 |
Neg logit contributions | |
Rue | -0.211 |
yss | -0.205 |
Jung | -0.192 |
nir | -0.188 |
Tags | -0.186 |
Token | pull |
Token ID | 2834 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
Rue | +0.022 |
yss | +0.022 |
Jung | +0.020 |
nir | +0.019 |
Tags | +0.019 |
Neg logit contributions | |
sbm | -0.027 |
bro | -0.026 |
Cub | -0.025 |
worth | -0.024 |
\/ | -0.023 |
Token | away |
Token ID | 1497 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Rue | +0.356 |
yss | +0.345 |
Jung | +0.322 |
nir | +0.314 |
Tags | +0.312 |
Neg logit contributions | |
sbm | -0.362 |
bro | -0.349 |
Cub | -0.329 |
worth | -0.314 |
\/ | -0.308 |
Token | at |
Token ID | 379 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
sbm | +0.911 |
bro | +0.884 |
Cub | +0.829 |
worth | +0.792 |
\/ | +0.770 |
Neg logit contributions | |
Rue | -1.030 |
yss | -1.006 |
Jung | -0.941 |
nir | -0.920 |
Tags | -0.914 |
Token | aluminum |
Token ID | 15955 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
Rue | +0.510 |
yss | +0.492 |
Jung | +0.467 |
nir | +0.450 |
Tags | +0.447 |
Neg logit contributions | |
sbm | -0.443 |
bro | -0.419 |
Cub | -0.397 |
worth | -0.374 |
\/ | -0.365 |
Token | composite |
Token ID | 24185 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
Rue | +0.490 |
yss | +0.474 |
Jung | +0.448 |
nir | +0.433 |
Tags | +0.429 |
Neg logit contributions | |
sbm | -0.435 |
bro | -0.413 |
Cub | -0.391 |
worth | -0.369 |
\/ | -0.361 |
Token | panels |
Token ID | 13043 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
sbm | +0.363 |
bro | +0.346 |
Cub | +0.326 |
worth | +0.309 |
\/ | +0.303 |
Neg logit contributions | |
Rue | -0.412 |
yss | -0.400 |
Jung | -0.376 |
nir | -0.366 |
Tags | -0.360 |
Token | . |
Token ID | 13 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
sbm | +0.202 |
bro | +0.193 |
Cub | +0.183 |
worth | +0.175 |
\/ | +0.171 |
Neg logit contributions | |
Rue | -0.190 |
yss | -0.184 |
Jung | -0.172 |
nir | -0.166 |
Tags | -0.164 |
Token | The |
Token ID | 383 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
sbm | +0.258 |
bro | +0.244 |
Cub | +0.233 |
worth | +0.222 |
\/ | +0.217 |
Neg logit contributions | |
Rue | -0.224 |
yss | -0.220 |
Jung | -0.203 |
nir | -0.198 |
Tags | -0.194 |
Token | core |
Token ID | 4755 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
Rue | +0.348 |
yss | +0.337 |
Jung | +0.316 |
nir | +0.306 |
Tags | +0.302 |
Neg logit contributions | |
sbm | -0.364 |
bro | -0.346 |
Cub | -0.329 |
worth | -0.313 |
\/ | -0.306 |
Token | of |
Token ID | 286 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
sbm | +2.127 |
bro | +2.046 |
Cub | +1.942 |
worth | +1.865 |
\/ | +1.808 |
Neg logit contributions | |
Rue | -1.969 |
yss | -1.894 |
Jung | -1.781 |
nir | -1.734 |
Tags | -1.700 |
Token | many |
Token ID | 867 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
sbm | +0.299 |
bro | +0.285 |
Cub | +0.271 |
worth | +0.257 |
\/ | +0.252 |
Neg logit contributions | |
Rue | -0.277 |
yss | -0.267 |
Jung | -0.251 |
nir | -0.242 |
Tags | -0.239 |
Token | of |
Token ID | 286 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
sbm | +0.416 |
bro | +0.397 |
Cub | +0.377 |
worth | +0.360 |
\/ | +0.354 |
Neg logit contributions | |
Rue | -0.360 |
yss | -0.348 |
Jung | -0.325 |
nir | -0.315 |
Tags | -0.310 |
Token | the |
Token ID | 262 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
Rue | +0.170 |
yss | +0.165 |
Jung | +0.155 |
nir | +0.149 |
Tags | +0.148 |
Neg logit contributions | |
sbm | -0.178 |
bro | -0.169 |
Cub | -0.161 |
worth | -0.153 |
\/ | -0.150 |
Token | panels |
Token ID | 13043 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Rue | +0.045 |
yss | +0.043 |
Jung | +0.040 |
nir | +0.039 |
Tags | +0.038 |
Neg logit contributions | |
sbm | -0.052 |
bro | -0.049 |
Cub | -0.047 |
worth | -0.045 |
\/ | -0.044 |
Token | hit |
Token ID | 2277 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
Rue | +0.193 |
yss | +0.186 |
Jung | +0.175 |
nir | +0.169 |
Tags | +0.169 |
Neg logit contributions | |
sbm | -0.197 |
bro | -0.190 |
Cub | -0.180 |
worth | -0.171 |
\/ | -0.167 |
Token | for |
Token ID | 329 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
sbm | +0.750 |
bro | +0.727 |
Cub | +0.690 |
worth | +0.654 |
\/ | +0.643 |
Neg logit contributions | |
Rue | -0.739 |
yss | -0.715 |
Jung | -0.669 |
nir | -0.646 |
Tags | -0.645 |
Token | the |
Token ID | 262 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
sbm | +0.078 |
bro | +0.076 |
Cub | +0.071 |
worth | +0.068 |
\/ | +0.067 |
Neg logit contributions | |
Rue | -0.072 |
yss | -0.070 |
Jung | -0.065 |
nir | -0.064 |
Tags | -0.063 |
Token | franchise |
Token ID | 8663 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
sbm | +0.179 |
bro | +0.173 |
Cub | +0.163 |
worth | +0.154 |
\/ | +0.151 |
Neg logit contributions | |
Rue | -0.183 |
yss | -0.178 |
Jung | -0.166 |
nir | -0.163 |
Tags | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Rue | +0.152 |
yss | +0.147 |
Jung | +0.138 |
nir | +0.133 |
Tags | +0.132 |
Neg logit contributions | |
sbm | -0.160 |
bro | -0.154 |
Cub | -0.146 |
worth | -0.139 |
\/ | -0.136 |
Token | Granted |
Token ID | 38842 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
sbm | +0.161 |
bro | +0.155 |
Cub | +0.148 |
worth | +0.142 |
\/ | +0.139 |
Neg logit contributions | |
Rue | -0.119 |
yss | -0.118 |
nir | -0.105 |
Jung | -0.105 |
refriger | -0.103 |
Token | , |
Token ID | 11 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
sbm | +1.961 |
bro | +1.904 |
Cub | +1.795 |
worth | +1.699 |
\/ | +1.678 |
Neg logit contributions | |
Rue | -1.884 |
yss | -1.827 |
Jung | -1.695 |
nir | -1.674 |
Tags | -1.651 |
Token | we |
Token ID | 356 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
sbm | +0.676 |
bro | +0.655 |
Cub | +0.614 |
worth | +0.586 |
\/ | +0.573 |
Neg logit contributions | |
Rue | -0.664 |
yss | -0.644 |
Jung | -0.601 |
nir | -0.592 |
Tags | -0.585 |
Token | don |
Token ID | 836 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
sbm | +0.440 |
bro | +0.427 |
Cub | +0.402 |
worth | +0.379 |
\/ | +0.375 |
Neg logit contributions | |
Rue | -0.456 |
yss | -0.442 |
Jung | -0.413 |
nir | -0.401 |
Tags | -0.399 |
Token | � |
Token ID | 447 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
Rue | +0.555 |
yss | +0.537 |
Jung | +0.505 |
nir | +0.487 |
Tags | +0.483 |
Neg logit contributions | |
sbm | -0.548 |
bro | -0.521 |
Cub | -0.495 |
worth | -0.468 |
\/ | -0.459 |
Token | � |
Token ID | 247 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
sbm | +0.218 |
bro | +0.208 |
Cub | +0.197 |
worth | +0.187 |
\/ | +0.184 |
Neg logit contributions | |
Rue | -0.221 |
yss | -0.213 |
Jung | -0.200 |
nir | -0.194 |
Tags | -0.192 |
Token | the |
Token ID | 262 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
sbm | +0.026 |
bro | +0.025 |
Cub | +0.024 |
worth | +0.023 |
\/ | +0.022 |
Neg logit contributions | |
Rue | -0.023 |
yss | -0.022 |
Jung | -0.020 |
nir | -0.020 |
Tags | -0.020 |
Token | Beer |
Token ID | 16971 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
sbm | +0.026 |
bro | +0.025 |
Cub | +0.024 |
worth | +0.023 |
\/ | +0.022 |
Neg logit contributions | |
Rue | -0.020 |
yss | -0.020 |
Jung | -0.018 |
nir | -0.018 |
Tags | -0.017 |
Token | Festival |
Token ID | 11117 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
sbm | +0.307 |
bro | +0.295 |
Cub | +0.280 |
worth | +0.264 |
\/ | +0.258 |
Neg logit contributions | |
Rue | -0.298 |
yss | -0.290 |
Jung | -0.271 |
nir | -0.263 |
Tags | -0.260 |
Token | . |
Token ID | 13 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Rue | +0.182 |
yss | +0.177 |
Jung | +0.165 |
nir | +0.160 |
Tags | +0.158 |
Neg logit contributions | |
sbm | -0.202 |
bro | -0.194 |
Cub | -0.185 |
worth | -0.175 |
\/ | -0.173 |
Token | Make |
Token ID | 6889 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
Rue | +0.227 |
yss | +0.223 |
Jung | +0.205 |
nir | +0.201 |
ukong | +0.197 |
Neg logit contributions | |
sbm | -0.255 |
bro | -0.244 |
Cub | -0.234 |
worth | -0.222 |
\/ | -0.218 |
Token | sure |
Token ID | 1654 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
sbm | +0.028 |
bro | +0.027 |
Cub | +0.026 |
worth | +0.024 |
\/ | +0.024 |
Neg logit contributions | |
Rue | -0.023 |
yss | -0.022 |
Jung | -0.021 |
nir | -0.020 |
Tags | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
sbm | +1.746 |
bro | +1.681 |
Cub | +1.590 |
worth | +1.506 |
\/ | +1.499 |
Neg logit contributions | |
Rue | -1.856 |
yss | -1.808 |
Jung | -1.702 |
nir | -1.644 |
Tags | -1.636 |
Token | get |
Token ID | 651 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
Rue | +0.010 |
yss | +0.010 |
Jung | +0.009 |
nir | +0.009 |
Tags | +0.009 |
Neg logit contributions | |
sbm | -0.012 |
bro | -0.012 |
Cub | -0.011 |
worth | -0.011 |
\/ | -0.011 |
Token | your |
Token ID | 534 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
sbm | +0.021 |
bro | +0.020 |
Cub | +0.019 |
worth | +0.018 |
\/ | +0.018 |
Neg logit contributions | |
Rue | -0.021 |
yss | -0.020 |
Jung | -0.019 |
nir | -0.019 |
Tags | -0.018 |
Token | tickets |
Token ID | 8587 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
sbm | +0.456 |
bro | +0.439 |
Cub | +0.422 |
worth | +0.405 |
\/ | +0.400 |
Neg logit contributions | |
Rue | -0.261 |
yss | -0.250 |
Jung | -0.229 |
nir | -0.219 |
Tags | -0.214 |
Token | ! |
Token ID | 0 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Rue | +0.550 |
yss | +0.532 |
Jung | +0.499 |
nir | +0.483 |
Tags | +0.480 |
Neg logit contributions | |
sbm | -0.565 |
bro | -0.542 |
Cub | -0.513 |
worth | -0.488 |
\/ | -0.481 |
Token | divides |
Token ID | 36319 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
sbm | +0.264 |
bro | +0.257 |
Cub | +0.242 |
worth | +0.229 |
\/ | +0.224 |
Neg logit contributions | |
Rue | -0.256 |
yss | -0.251 |
Jung | -0.229 |
nir | -0.226 |
Tags | -0.224 |
Token | them |
Token ID | 606 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Rue | +0.575 |
yss | +0.558 |
Jung | +0.515 |
nir | +0.501 |
Tags | +0.497 |
Neg logit contributions | |
sbm | -0.649 |
bro | -0.622 |
Cub | -0.590 |
worth | -0.562 |
\/ | -0.552 |
Token | in |
Token ID | 287 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
sbm | +0.367 |
bro | +0.349 |
Cub | +0.332 |
worth | +0.316 |
\/ | +0.310 |
Neg logit contributions | |
Rue | -0.355 |
yss | -0.344 |
Jung | -0.321 |
nir | -0.310 |
Tags | -0.309 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
sbm | +1.007 |
bro | +0.964 |
Cub | +0.918 |
worth | +0.874 |
\/ | +0.859 |
Neg logit contributions | |
Rue | -0.905 |
yss | -0.891 |
Jung | -0.817 |
nir | -0.799 |
Tags | -0.789 |
Token | Hell |
Token ID | 5783 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
sbm | +0.939 |
bro | +0.910 |
Cub | +0.871 |
worth | +0.823 |
\/ | +0.820 |
Neg logit contributions | |
Rue | -0.771 |
yss | -0.762 |
Jung | -0.685 |
nir | -0.681 |
Tags | -0.673 |
Token | esp |
Token ID | 9774 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
sbm | +1.102 |
bro | +1.066 |
Cub | +0.998 |
worth | +0.955 |
\/ | +0.935 |
Neg logit contributions | |
Rue | -1.267 |
yss | -1.220 |
Jung | -1.144 |
Tags | -1.117 |
nir | -1.096 |
Token | ont |
Token ID | 756 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
sbm | +2.014 |
bro | +1.938 |
Cub | +1.788 |
worth | +1.762 |
\/ | +1.703 |
Neg logit contributions | |
Rue | -2.425 |
yss | -2.370 |
Jung | -2.219 |
Tags | -2.181 |
nir | -2.159 |
Token | region |
Token ID | 3814 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
sbm | +0.461 |
bro | +0.440 |
Cub | +0.417 |
worth | +0.397 |
\/ | +0.392 |
Neg logit contributions | |
Rue | -0.446 |
yss | -0.432 |
Jung | -0.403 |
Tags | -0.389 |
nir | -0.387 |
Token | . |
Token ID | 13 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
sbm | +0.185 |
bro | +0.176 |
Cub | +0.167 |
worth | +0.159 |
\/ | +0.156 |
Neg logit contributions | |
Rue | -0.177 |
yss | -0.172 |
Jung | -0.160 |
nir | -0.155 |
Tags | -0.154 |
Token | And |
Token ID | 843 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
sbm | +0.482 |
bro | +0.461 |
Cub | +0.441 |
worth | +0.421 |
\/ | +0.414 |
Neg logit contributions | |
Rue | -0.360 |
yss | -0.357 |
Jung | -0.319 |
nir | -0.316 |
refriger | -0.311 |
Token | cru |
Token ID | 4630 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Rue | +0.381 |
yss | +0.368 |
Jung | +0.343 |
nir | +0.333 |
Tags | +0.331 |
Neg logit contributions | |
sbm | -0.409 |
bro | -0.394 |
Cub | -0.371 |
worth | -0.353 |
\/ | -0.346 |
Token | from |
Token ID | 422 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Rue | +0.205 |
yss | +0.198 |
Jung | +0.186 |
nir | +0.180 |
Tags | +0.178 |
Neg logit contributions | |
sbm | -0.206 |
bro | -0.197 |
Cub | -0.187 |
worth | -0.178 |
\/ | -0.174 |
Token | which |
Token ID | 543 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
Rue | +0.892 |
yss | +0.857 |
Jung | +0.802 |
nir | +0.768 |
Tags | +0.762 |
Neg logit contributions | |
sbm | -1.120 |
bro | -1.070 |
Cub | -1.023 |
worth | -0.975 |
\/ | -0.956 |
Token | we |
Token ID | 356 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Rue | +0.538 |
yss | +0.519 |
Jung | +0.491 |
nir | +0.472 |
Tags | +0.470 |
Neg logit contributions | |
sbm | -0.513 |
bro | -0.485 |
Cub | -0.462 |
worth | -0.436 |
\/ | -0.426 |
Token | will |
Token ID | 481 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
Rue | +1.095 |
yss | +1.047 |
Jung | +0.992 |
nir | +0.942 |
refriger | +0.936 |
Neg logit contributions | |
sbm | -1.318 |
bro | -1.242 |
Cub | -1.199 |
worth | -1.132 |
\/ | -1.107 |
Token | launch |
Token ID | 4219 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Rue | +0.576 |
yss | +0.553 |
Jung | +0.523 |
nir | +0.500 |
Tags | +0.496 |
Neg logit contributions | |
sbm | -0.632 |
bro | -0.597 |
Cub | -0.572 |
worth | -0.539 |
\/ | -0.528 |
Token | all |
Token ID | 477 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
sbm | +0.948 |
bro | +0.910 |
Cub | +0.859 |
worth | +0.820 |
\/ | +0.808 |
Neg logit contributions | |
Rue | -0.953 |
yss | -0.921 |
Jung | -0.867 |
nir | -0.845 |
Tags | -0.836 |
Token | future |
Token ID | 2003 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
sbm | +0.283 |
bro | +0.272 |
Cub | +0.257 |
worth | +0.247 |
\/ | +0.242 |
Neg logit contributions | |
Rue | -0.276 |
yss | -0.265 |
Jung | -0.250 |
nir | -0.243 |
Tags | -0.238 |
Token | stores |
Token ID | 7000 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
sbm | +0.755 |
bro | +0.728 |
Cub | +0.689 |
worth | +0.662 |
\/ | +0.650 |
Neg logit contributions | |
Rue | -0.729 |
yss | -0.709 |
Jung | -0.659 |
nir | -0.647 |
Tags | -0.633 |
Token | . |
Token ID | 13 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Rue | +0.455 |
yss | +0.439 |
Jung | +0.410 |
nir | +0.396 |
Tags | +0.391 |
Neg logit contributions | |
sbm | -0.526 |
bro | -0.503 |
Cub | -0.480 |
worth | -0.458 |
\/ | -0.449 |
Token |
|
Token ID | 198 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
Rue | +0.268 |
yss | +0.258 |
Jung | +0.243 |
nir | +0.233 |
Tags | +0.232 |
Neg logit contributions | |
sbm | -0.274 |
bro | -0.260 |
Cub | -0.248 |
worth | -0.234 |
\/ | -0.230 |
Token |
|
Token ID | 198 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
Rue | +0.035 |
yss | +0.034 |
Jung | +0.032 |
nir | +0.031 |
refriger | +0.030 |
Neg logit contributions | |
sbm | -0.033 |
bro | -0.031 |
Cub | -0.030 |
worth | -0.028 |
\/ | -0.028 |
Token | employee |
Token ID | 6538 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
Rue | +0.526 |
yss | +0.505 |
Jung | +0.474 |
nir | +0.455 |
Tags | +0.451 |
Neg logit contributions | |
sbm | -0.617 |
bro | -0.588 |
Cub | -0.562 |
worth | -0.534 |
\/ | -0.523 |
Token | said |
Token ID | 531 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
Rue | +0.619 |
yss | +0.598 |
Jung | +0.566 |
nir | +0.546 |
Tags | +0.543 |
Neg logit contributions | |
sbm | -0.550 |
bro | -0.520 |
Cub | -0.493 |
worth | -0.465 |
\/ | -0.454 |
Token | . |
Token ID | 13 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Rue | +0.572 |
yss | +0.548 |
Jung | +0.520 |
nir | +0.493 |
Tags | +0.490 |
Neg logit contributions | |
sbm | -0.661 |
bro | -0.628 |
Cub | -0.598 |
worth | -0.568 |
\/ | -0.557 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e-03 |
Pos logit contributions | |
Rue | +0.279 |
yss | +0.270 |
Jung | +0.253 |
nir | +0.244 |
Tags | +0.242 |
Neg logit contributions | |
sbm | -0.289 |
bro | -0.274 |
Cub | -0.261 |
worth | -0.247 |
\/ | -0.242 |
Token |
|
Token ID | 198 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
sbm | +0.001 |
bro | +0.001 |
Cub | +0.001 |
worth | +0.001 |
\/ | +0.001 |
Neg logit contributions | |
Rue | -0.001 |
yss | -0.001 |
Jung | -0.001 |
nir | -0.001 |
Tags | -0.001 |
Token | Looking |
Token ID | 15784 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Rue | +0.288 |
yss | +0.278 |
Jung | +0.264 |
nir | +0.253 |
refriger | +0.251 |
Neg logit contributions | |
sbm | -0.261 |
bro | -0.249 |
Cub | -0.237 |
worth | -0.222 |
\/ | -0.217 |
Token | back |
Token ID | 736 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
sbm | +0.951 |
bro | +0.910 |
Cub | +0.867 |
worth | +0.826 |
\/ | +0.808 |
Neg logit contributions | |
Rue | -0.849 |
yss | -0.821 |
Jung | -0.768 |
nir | -0.736 |
Tags | -0.733 |
Token | now |
Token ID | 783 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
sbm | +0.256 |
bro | +0.244 |
Cub | +0.233 |
worth | +0.221 |
\/ | +0.217 |
Neg logit contributions | |
Rue | -0.225 |
yss | -0.217 |
Jung | -0.203 |
nir | -0.195 |
Tags | -0.194 |
Token | , |
Token ID | 11 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
Rue | +0.243 |
yss | +0.234 |
Jung | +0.220 |
nir | +0.210 |
Tags | +0.208 |
Neg logit contributions | |
sbm | -0.286 |
bro | -0.272 |
Cub | -0.260 |
worth | -0.247 |
\/ | -0.242 |
Token | several |
Token ID | 1811 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
sbm | +0.023 |
bro | +0.022 |
Cub | +0.021 |
worth | +0.020 |
\/ | +0.019 |
Neg logit contributions | |
Rue | -0.025 |
yss | -0.024 |
Jung | -0.022 |
nir | -0.022 |
Tags | -0.022 |
Token | Douglas |
Token ID | 15796 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
sbm | +0.185 |
bro | +0.178 |
Cub | +0.169 |
worth | +0.161 |
\/ | +0.158 |
Neg logit contributions | |
Rue | -0.163 |
yss | -0.158 |
Jung | -0.148 |
nir | -0.143 |
Tags | -0.142 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
sbm | +0.322 |
bro | +0.311 |
Cub | +0.296 |
worth | +0.278 |
\/ | +0.273 |
Neg logit contributions | |
Rue | -0.328 |
yss | -0.318 |
Jung | -0.299 |
nir | -0.290 |
Tags | -0.288 |
Token | UC |
Token ID | 14417 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
sbm | +0.170 |
bro | +0.163 |
Cub | +0.156 |
worth | +0.147 |
\/ | +0.143 |
Neg logit contributions | |
Rue | -0.163 |
yss | -0.158 |
Jung | -0.148 |
nir | -0.143 |
Tags | -0.142 |
Token | I |
Token ID | 40 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
sbm | +0.674 |
bro | +0.641 |
Cub | +0.602 |
worth | +0.562 |
\/ | +0.546 |
Neg logit contributions | |
Rue | -1.019 |
yss | -0.993 |
Jung | -0.938 |
nir | -0.910 |
Tags | -0.908 |
Token | was |
Token ID | 373 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
Rue | +0.491 |
yss | +0.473 |
Jung | +0.445 |
nir | +0.427 |
Tags | +0.424 |
Neg logit contributions | |
sbm | -0.541 |
bro | -0.516 |
Cub | -0.492 |
worth | -0.466 |
\/ | -0.457 |
Token | prompted |
Token ID | 12053 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
sbm | +0.347 |
bro | +0.334 |
Cub | +0.318 |
worth | +0.303 |
\/ | +0.295 |
Neg logit contributions | |
Rue | -0.322 |
yss | -0.311 |
Jung | -0.288 |
nir | -0.281 |
Tags | -0.280 |
Token | to |
Token ID | 284 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
Rue | +0.343 |
yss | +0.329 |
Jung | +0.308 |
nir | +0.294 |
Tags | +0.292 |
Neg logit contributions | |
sbm | -0.441 |
bro | -0.421 |
Cub | -0.403 |
worth | -0.384 |
\/ | -0.377 |
Token | revise |
Token ID | 32548 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
sbm | +0.769 |
bro | +0.747 |
Cub | +0.711 |
worth | +0.683 |
\/ | +0.671 |
Neg logit contributions | |
Rue | -0.577 |
yss | -0.560 |
Jung | -0.515 |
Tags | -0.495 |
nir | -0.494 |
Token | its |
Token ID | 663 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
sbm | +1.178 |
bro | +1.137 |
Cub | +1.085 |
worth | +1.018 |
\/ | +1.004 |
Neg logit contributions | |
Rue | -1.151 |
yss | -1.128 |
Jung | -1.044 |
nir | -1.012 |
ukong | -0.999 |
Token | rules |
Token ID | 3173 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Rue | +0.102 |
yss | +0.098 |
Jung | +0.093 |
nir | +0.089 |
Tags | +0.089 |
Neg logit contributions | |
sbm | -0.105 |
bro | -0.100 |
Cub | -0.095 |
worth | -0.090 |
\/ | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
sbm | +0.302 |
bro | +0.290 |
Cub | +0.275 |
worth | +0.261 |
\/ | +0.257 |
Neg logit contributions | |
Rue | -0.284 |
yss | -0.274 |
Jung | -0.257 |
nir | -0.248 |
Tags | -0.246 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
sbm | +0.160 |
bro | +0.152 |
Cub | +0.147 |
worth | +0.138 |
\/ | +0.135 |
Neg logit contributions | |
Rue | -0.143 |
yss | -0.141 |
Jung | -0.130 |
nir | -0.127 |
Tags | -0.124 |
Token | Jama |
Token ID | 21661 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
sbm | +0.143 |
bro | +0.136 |
Cub | +0.130 |
worth | +0.124 |
\/ | +0.120 |
Neg logit contributions | |
yss | -0.134 |
Rue | -0.134 |
Jung | -0.121 |
nir | -0.121 |
refriger | -0.119 |
Token | al |
Token ID | 282 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Rue | +0.088 |
yss | +0.086 |
Jung | +0.082 |
nir | +0.079 |
Tags | +0.079 |
Neg logit contributions | |
sbm | -0.052 |
bro | -0.049 |
Cub | -0.045 |
worth | -0.042 |
\/ | -0.041 |
Token | Charles |
Token ID | 7516 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
sbm | +1.011 |
bro | +0.991 |
Cub | +0.945 |
worth | +0.914 |
EEE | +0.876 |
Neg logit contributions | |
Rue | -0.737 |
yss | -0.726 |
Jung | -0.663 |
nir | -0.656 |
Tags | -0.650 |
Token | also |
Token ID | 635 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
Rue | +0.535 |
yss | +0.515 |
Jung | +0.485 |
nir | +0.467 |
Tags | +0.464 |
Neg logit contributions | |
sbm | -0.563 |
bro | -0.538 |
Cub | -0.512 |
worth | -0.486 |
\/ | -0.476 |
Token | participated |
Token ID | 14888 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
sbm | +0.270 |
bro | +0.261 |
Cub | +0.247 |
worth | +0.235 |
\/ | +0.230 |
Neg logit contributions | |
Rue | -0.264 |
yss | -0.256 |
Jung | -0.240 |
nir | -0.232 |
Tags | -0.231 |
Token | in |
Token ID | 287 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Rue | +0.247 |
yss | +0.237 |
Jung | +0.222 |
nir | +0.213 |
Tags | +0.211 |
Neg logit contributions | |
sbm | -0.306 |
bro | -0.293 |
Cub | -0.280 |
worth | -0.267 |
\/ | -0.262 |
Token | 11 |
Token ID | 1367 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
sbm | +0.195 |
bro | +0.186 |
Cub | +0.178 |
worth | +0.168 |
\/ | +0.165 |
Neg logit contributions | |
Rue | -0.196 |
yss | -0.191 |
Jung | -0.179 |
nir | -0.175 |
Tags | -0.172 |
Token | - |
Token ID | 12 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
sbm | +0.089 |
bro | +0.085 |
Cub | +0.082 |
worth | +0.077 |
\/ | +0.076 |
Neg logit contributions | |
Rue | -0.080 |
yss | -0.078 |
Jung | -0.073 |
nir | -0.071 |
Tags | -0.069 |
Token | on |
Token ID | 261 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
Rue | +0.070 |
yss | +0.068 |
Jung | +0.064 |
nir | +0.061 |
Tags | +0.061 |
Neg logit contributions | |
sbm | -0.071 |
bro | -0.069 |
Cub | -0.065 |
worth | -0.062 |
\/ | -0.060 |
Token | - |
Token ID | 12 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
sbm | +0.597 |
bro | +0.569 |
Cub | +0.538 |
worth | +0.513 |
\/ | +0.505 |
Neg logit contributions | |
Rue | -0.629 |
yss | -0.611 |
Jung | -0.571 |
nir | -0.553 |
Tags | -0.547 |
Token | 11 |
Token ID | 1157 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
sbm | +0.560 |
bro | +0.532 |
Cub | +0.501 |
worth | +0.474 |
\/ | +0.458 |
Neg logit contributions | |
Rue | -0.752 |
yss | -0.734 |
Jung | -0.696 |
refriger | -0.669 |
nir | -0.666 |
Token | , |
Token ID | 11 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
sbm | +1.365 |
bro | +1.334 |
Cub | +1.257 |
worth | +1.210 |
\/ | +1.173 |
Neg logit contributions | |
Rue | -1.396 |
yss | -1.358 |
Jung | -1.271 |
nir | -1.240 |
Tags | -1.228 |
Token | Ju |
Token ID | 12585 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
sbm | +0.578 |
bro | +0.562 |
Cub | +0.532 |
worth | +0.512 |
\/ | +0.490 |
Neg logit contributions | |
Rue | -0.542 |
yss | -0.540 |
Jung | -0.496 |
nir | -0.491 |
Tags | -0.486 |
Token | wan |
Token ID | 8149 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
sbm | +0.103 |
bro | +0.097 |
Cub | +0.093 |
worth | +0.087 |
\/ | +0.085 |
Neg logit contributions | |
Rue | -0.111 |
yss | -0.108 |
Jung | -0.101 |
nir | -0.098 |
Tags | -0.097 |
Token | Thompson |
Token ID | 11654 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
Rue | +0.300 |
yss | +0.295 |
Jung | +0.271 |
nir | +0.269 |
Tags | +0.268 |
Neg logit contributions | |
sbm | -0.322 |
bro | -0.311 |
Cub | -0.294 |
worth | -0.276 |
\/ | -0.273 |
Token | and |
Token ID | 290 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
sbm | +0.630 |
bro | +0.600 |
Cub | +0.569 |
worth | +0.539 |
\/ | +0.526 |
Neg logit contributions | |
Rue | -0.664 |
yss | -0.641 |
Jung | -0.606 |
nir | -0.583 |
Tags | -0.581 |
Token | rookie |
Token ID | 12302 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
sbm | +0.516 |
bro | +0.500 |
Cub | +0.478 |
worth | +0.455 |
\/ | +0.445 |
Neg logit contributions | |
yss | -0.407 |
Rue | -0.404 |
nir | -0.366 |
Jung | -0.366 |
Tags | -0.360 |
Token | De |
Token ID | 1024 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
sbm | +0.531 |
bro | +0.516 |
Cub | +0.494 |
worth | +0.470 |
\/ | +0.458 |
Neg logit contributions | |
yss | -0.423 |
Rue | -0.418 |
nir | -0.379 |
Jung | -0.378 |
Tags | -0.375 |
Token | � |
Token ID | 447 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
Rue | +0.105 |
yss | +0.101 |
Jung | +0.094 |
nir | +0.089 |
Tags | +0.089 |
Neg logit contributions | |
sbm | -0.143 |
bro | -0.138 |
Cub | -0.133 |
worth | -0.126 |
\/ | -0.123 |
Token | � |
Token ID | 247 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
sbm | +0.293 |
bro | +0.280 |
Cub | +0.267 |
worth | +0.253 |
\/ | +0.248 |
Neg logit contributions | |
Rue | -0.269 |
yss | -0.259 |
Jung | -0.243 |
nir | -0.234 |
Tags | -0.232 |
Token | Angelo |
Token ID | 45585 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
sbm | +0.357 |
bro | +0.341 |
Cub | +0.324 |
worth | +0.307 |
\/ | +0.299 |
Neg logit contributions | |
Rue | -0.373 |
yss | -0.361 |
Jung | -0.341 |
nir | -0.327 |
Tags | -0.327 |
Token | Henderson |
Token ID | 22016 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
sbm | +0.671 |
bro | +0.638 |
Cub | +0.607 |
worth | +0.573 |
\/ | +0.562 |
Neg logit contributions | |
Rue | -0.708 |
yss | -0.687 |
Jung | -0.646 |
nir | -0.627 |
Tags | -0.622 |
Token | serial |
Token ID | 11389 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Rue | +0.582 |
yss | +0.561 |
Jung | +0.530 |
nir | +0.511 |
Tags | +0.507 |
Neg logit contributions | |
sbm | -0.538 |
bro | -0.515 |
Cub | -0.486 |
worth | -0.459 |
\/ | -0.450 |
Token | ization |
Token ID | 1634 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Rue | +1.091 |
yss | +1.051 |
Jung | +0.986 |
nir | +0.953 |
Tags | +0.942 |
Neg logit contributions | |
sbm | -1.115 |
bro | -1.068 |
Cub | -1.014 |
worth | -0.960 |
\/ | -0.942 |
Token | , |
Token ID | 11 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
Rue | +0.767 |
yss | +0.743 |
Jung | +0.696 |
nir | +0.668 |
Tags | +0.665 |
Neg logit contributions | |
sbm | -0.800 |
bro | -0.768 |
Cub | -0.730 |
worth | -0.691 |
\/ | -0.681 |
Token | and |
Token ID | 290 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
Rue | +0.262 |
yss | +0.255 |
Jung | +0.240 |
nir | +0.232 |
Tags | +0.231 |
Neg logit contributions | |
sbm | -0.231 |
bro | -0.220 |
Cub | -0.208 |
worth | -0.197 |
\/ | -0.193 |
Token | for |
Token ID | 329 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Rue | +0.461 |
yss | +0.450 |
Jung | +0.420 |
Tags | +0.405 |
nir | +0.404 |
Neg logit contributions | |
sbm | -0.463 |
bro | -0.446 |
Cub | -0.423 |
worth | -0.401 |
\/ | -0.394 |
Token | that |
Token ID | 326 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
sbm | +0.114 |
bro | +0.108 |
Cub | +0.103 |
worth | +0.097 |
\/ | +0.095 |
Neg logit contributions | |
Rue | -0.125 |
yss | -0.121 |
Jung | -0.114 |
nir | -0.110 |
Tags | -0.110 |
Token | I |
Token ID | 314 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Rue | +0.101 |
yss | +0.099 |
Jung | +0.092 |
Tags | +0.090 |
nir | +0.089 |
Neg logit contributions | |
sbm | -0.085 |
bro | -0.081 |
Cub | -0.077 |
worth | -0.073 |
\/ | -0.071 |
Token | need |
Token ID | 761 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Rue | +0.082 |
yss | +0.080 |
Jung | +0.074 |
nir | +0.072 |
Tags | +0.072 |
Neg logit contributions | |
sbm | -0.077 |
bro | -0.074 |
Cub | -0.070 |
worth | -0.066 |
\/ | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Rue | +0.205 |
yss | +0.198 |
Jung | +0.185 |
nir | +0.177 |
Tags | +0.177 |
Neg logit contributions | |
sbm | -0.229 |
bro | -0.219 |
Cub | -0.208 |
worth | -0.198 |
\/ | -0.195 |
Token | current |
Token ID | 1459 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
Rue | +0.217 |
yss | +0.210 |
Jung | +0.195 |
nir | +0.189 |
Tags | +0.187 |
Neg logit contributions | |
sbm | -0.243 |
bro | -0.233 |
Cub | -0.222 |
worth | -0.210 |
\/ | -0.207 |
Token | version |
Token ID | 2196 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Rue | +0.016 |
yss | +0.015 |
Jung | +0.014 |
nir | +0.014 |
Tags | +0.014 |
Neg logit contributions | |
sbm | -0.016 |
bro | -0.016 |
Cub | -0.015 |
worth | -0.014 |
\/ | -0.014 |
Token | s |
Token ID | 82 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
sbm | +1.224 |
bro | +1.186 |
Cub | +1.117 |
worth | +1.048 |
\/ | +1.032 |
Neg logit contributions | |
Rue | -1.417 |
yss | -1.355 |
Jung | -1.281 |
nir | -1.237 |
Tags | -1.231 |
Token | including |
Token ID | 1390 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
Rue | +0.407 |
yss | +0.392 |
Jung | +0.368 |
nir | +0.354 |
Tags | +0.352 |
Neg logit contributions | |
sbm | -0.442 |
bro | -0.422 |
Cub | -0.403 |
worth | -0.382 |
\/ | -0.375 |
Token | interrupts |
Token ID | 48237 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
sbm | +0.724 |
bro | +0.700 |
Cub | +0.669 |
worth | +0.636 |
\/ | +0.626 |
Neg logit contributions | |
Rue | -0.620 |
yss | -0.595 |
Jung | -0.554 |
nir | -0.538 |
Tags | -0.531 |
Token | and |
Token ID | 290 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
sbm | +1.777 |
bro | +1.727 |
Cub | +1.618 |
worth | +1.545 |
\/ | +1.527 |
Neg logit contributions | |
Rue | -1.924 |
yss | -1.874 |
Jung | -1.742 |
nir | -1.695 |
Tags | -1.686 |
Token | timers |
Token ID | 48085 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
sbm | +0.267 |
bro | +0.259 |
Cub | +0.248 |
worth | +0.237 |
\/ | +0.235 |
Neg logit contributions | |
Rue | -0.172 |
yss | -0.164 |
Jung | -0.150 |
nir | -0.145 |
ukong | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
sbm | +0.317 |
bro | +0.306 |
Cub | +0.289 |
worth | +0.276 |
\/ | +0.271 |
Neg logit contributions | |
Rue | -0.306 |
yss | -0.295 |
Jung | -0.277 |
nir | -0.267 |
Tags | -0.265 |
Token |
|
Token ID | 198 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Rue | +0.134 |
yss | +0.130 |
Jung | +0.121 |
nir | +0.117 |
Tags | +0.115 |
Neg logit contributions | |
sbm | -0.146 |
bro | -0.140 |
Cub | -0.134 |
worth | -0.127 |
EEE | -0.124 |
Token |
|
Token ID | 198 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
Rue | +0.211 |
yss | +0.205 |
Jung | +0.192 |
nir | +0.185 |
Tags | +0.183 |
Neg logit contributions | |
sbm | -0.204 |
bro | -0.194 |
Cub | -0.184 |
worth | -0.175 |
\/ | -0.171 |
Token | Things |
Token ID | 22248 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Rue | +0.477 |
yss | +0.460 |
Jung | +0.436 |
nir | +0.417 |
refriger | +0.415 |
Neg logit contributions | |
sbm | -0.435 |
bro | -0.415 |
Cub | -0.395 |
worth | -0.372 |
\/ | -0.363 |
Token | started |
Token ID | 2067 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
sbm | +0.303 |
bro | +0.292 |
Cub | +0.276 |
worth | +0.263 |
\/ | +0.258 |
Neg logit contributions | |
Rue | -0.280 |
yss | -0.272 |
Jung | -0.254 |
nir | -0.244 |
Tags | -0.244 |
Token | to |
Token ID | 284 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
Rue | +0.197 |
yss | +0.190 |
Jung | +0.178 |
nir | +0.171 |
Tags | +0.170 |
Neg logit contributions | |
sbm | -0.231 |
bro | -0.221 |
Cub | -0.211 |
worth | -0.201 |
\/ | -0.197 |
Token | social |
Token ID | 1919 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
sbm | +0.417 |
bro | +0.405 |
Cub | +0.384 |
worth | +0.363 |
\/ | +0.353 |
Neg logit contributions | |
Rue | -0.437 |
yss | -0.425 |
Jung | -0.396 |
nir | -0.387 |
Tags | -0.382 |
Token | problems |
Token ID | 2761 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
Rue | +0.458 |
yss | +0.439 |
Jung | +0.414 |
nir | +0.395 |
Tags | +0.394 |
Neg logit contributions | |
sbm | -0.542 |
bro | -0.514 |
Cub | -0.491 |
worth | -0.466 |
\/ | -0.458 |
Token | from |
Token ID | 422 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
sbm | +0.030 |
bro | +0.029 |
Cub | +0.028 |
worth | +0.026 |
\/ | +0.026 |
Neg logit contributions | |
Rue | -0.030 |
yss | -0.029 |
Jung | -0.027 |
nir | -0.026 |
Tags | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Rue | +0.383 |
yss | +0.372 |
Jung | +0.346 |
nir | +0.339 |
Tags | +0.333 |
Neg logit contributions | |
sbm | -0.395 |
bro | -0.380 |
Cub | -0.361 |
worth | -0.342 |
\/ | -0.333 |
Token | radical |
Token ID | 7702 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Rue | +0.313 |
yss | +0.303 |
Jung | +0.281 |
nir | +0.275 |
Tags | +0.273 |
Neg logit contributions | |
sbm | -0.330 |
bro | -0.319 |
Cub | -0.304 |
worth | -0.286 |
\/ | -0.279 |
Token | antic |
Token ID | 47792 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Rue | +1.009 |
yss | +0.971 |
Jung | +0.912 |
nir | +0.876 |
Tags | +0.870 |
Neg logit contributions | |
sbm | -1.135 |
bro | -1.083 |
Cub | -1.034 |
worth | -0.981 |
\/ | -0.961 |
Token | ap |
Token ID | 499 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
sbm | +0.069 |
bro | +0.066 |
Cub | +0.062 |
worth | +0.059 |
\/ | +0.057 |
Neg logit contributions | |
Rue | -0.083 |
yss | -0.080 |
Jung | -0.076 |
nir | -0.073 |
Tags | -0.073 |
Token | ital |
Token ID | 1287 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
sbm | +0.368 |
bro | +0.344 |
Cub | +0.309 |
worth | +0.277 |
\/ | +0.265 |
Neg logit contributions | |
Rue | -0.949 |
yss | -0.924 |
Jung | -0.887 |
Tags | -0.862 |
nir | -0.861 |
Token | ist |
Token ID | 396 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
sbm | +0.372 |
bro | +0.358 |
Cub | +0.342 |
worth | +0.330 |
\/ | +0.322 |
Neg logit contributions | |
Rue | -0.290 |
yss | -0.274 |
Jung | -0.256 |
nir | -0.247 |
Tags | -0.244 |
Token | perspective |
Token ID | 6650 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
sbm | +0.954 |
bro | +0.934 |
Cub | +0.890 |
worth | +0.843 |
\/ | +0.832 |
Neg logit contributions | |
Rue | -0.787 |
yss | -0.761 |
Jung | -0.697 |
nir | -0.680 |
Tags | -0.677 |
Token | ," |
Token ID | 553 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
Rue | +0.435 |
yss | +0.419 |
Jung | +0.390 |
nir | +0.374 |
Tags | +0.372 |
Neg logit contributions | |
sbm | -0.533 |
bro | -0.511 |
Cub | -0.488 |
worth | -0.466 |
\/ | -0.456 |
Token | al |
Token ID | 282 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Rue | +0.214 |
yss | +0.208 |
Jung | +0.199 |
nir | +0.193 |
Tags | +0.192 |
Neg logit contributions | |
sbm | -0.131 |
bro | -0.122 |
Cub | -0.114 |
worth | -0.106 |
\/ | -0.103 |
Token | ism |
Token ID | 1042 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
Rue | +0.122 |
yss | +0.118 |
Jung | +0.109 |
nir | +0.105 |
Tags | +0.103 |
Neg logit contributions | |
sbm | -0.171 |
bro | -0.165 |
Cub | -0.158 |
worth | -0.152 |
\/ | -0.149 |
Token | in |
Token ID | 287 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
sbm | +0.509 |
bro | +0.492 |
Cub | +0.468 |
worth | +0.445 |
\/ | +0.438 |
Neg logit contributions | |
Rue | -0.421 |
yss | -0.406 |
Jung | -0.378 |
nir | -0.362 |
Tags | -0.359 |
Token | South |
Token ID | 2520 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
sbm | +0.177 |
bro | +0.171 |
Cub | +0.162 |
worth | +0.152 |
\/ | +0.150 |
Neg logit contributions | |
Rue | -0.185 |
yss | -0.181 |
Jung | -0.168 |
nir | -0.164 |
Tags | -0.162 |
Token | Korea |
Token ID | 4969 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Rue | +0.204 |
yss | +0.198 |
Jung | +0.185 |
nir | +0.179 |
Tags | +0.177 |
Neg logit contributions | |
sbm | -0.219 |
bro | -0.209 |
Cub | -0.199 |
worth | -0.189 |
\/ | -0.186 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
Rue | +0.861 |
yss | +0.825 |
Jung | +0.782 |
nir | +0.748 |
Tags | +0.744 |
Neg logit contributions | |
sbm | -0.928 |
bro | -0.881 |
Cub | -0.841 |
worth | -0.797 |
\/ | -0.780 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
sbm | +0.011 |
bro | +0.010 |
Cub | +0.010 |
worth | +0.009 |
\/ | +0.009 |
Neg logit contributions | |
Rue | -0.010 |
yss | -0.009 |
Jung | -0.009 |
nir | -0.008 |
Tags | -0.008 |
Token | This |
Token ID | 1212 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Rue | +0.680 |
yss | +0.656 |
Jung | +0.620 |
nir | +0.596 |
Tags | +0.592 |
Neg logit contributions | |
sbm | -0.648 |
bro | -0.616 |
Cub | -0.586 |
worth | -0.553 |
\/ | -0.541 |
Token | article |
Token ID | 2708 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
sbm | +0.118 |
bro | +0.112 |
Cub | +0.107 |
worth | +0.101 |
\/ | +0.099 |
Neg logit contributions | |
Rue | -0.115 |
yss | -0.111 |
Jung | -0.104 |
nir | -0.101 |
Tags | -0.101 |
Token | is |
Token ID | 318 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
sbm | +0.440 |
bro | +0.422 |
Cub | +0.398 |
worth | +0.378 |
\/ | +0.369 |
Neg logit contributions | |
Rue | -0.509 |
yss | -0.494 |
Jung | -0.463 |
nir | -0.450 |
Tags | -0.448 |
Token | about |
Token ID | 546 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
sbm | +1.158 |
bro | +1.110 |
Cub | +1.052 |
worth | +1.004 |
\/ | +0.981 |
Neg logit contributions | |
Rue | -1.287 |
yss | -1.263 |
Jung | -1.170 |
nir | -1.143 |
Tags | -1.139 |
Token | than |
Token ID | 621 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
Rue | +0.243 |
yss | +0.235 |
Jung | +0.220 |
nir | +0.213 |
Tags | +0.211 |
Neg logit contributions | |
sbm | -0.246 |
bro | -0.234 |
Cub | -0.223 |
worth | -0.211 |
\/ | -0.207 |
Token | one |
Token ID | 530 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
sbm | +0.566 |
bro | +0.546 |
Cub | +0.513 |
worth | +0.490 |
\/ | +0.476 |
Neg logit contributions | |
Rue | -0.570 |
yss | -0.553 |
Jung | -0.520 |
nir | -0.507 |
Tags | -0.503 |
Token | issued |
Token ID | 4884 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
Rue | +0.364 |
yss | +0.353 |
Jung | +0.330 |
nir | +0.320 |
Tags | +0.318 |
Neg logit contributions | |
sbm | -0.357 |
bro | -0.343 |
Cub | -0.324 |
worth | -0.308 |
\/ | -0.300 |
Token | on |
Token ID | 319 |
Feature activation | -6.72e-02 |
Pos logit contributions | |
Rue | +0.034 |
yss | +0.033 |
Jung | +0.031 |
nir | +0.030 |
Tags | +0.030 |
Neg logit contributions | |
sbm | -0.040 |
bro | -0.038 |
Cub | -0.036 |
worth | -0.034 |
\/ | -0.034 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
Rue | +0.050 |
yss | +0.048 |
Jung | +0.045 |
nir | +0.044 |
Tags | +0.044 |
Neg logit contributions | |
sbm | -0.050 |
bro | -0.048 |
Cub | -0.046 |
worth | -0.044 |
\/ | -0.043 |
Token | by |
Token ID | 416 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
sbm | +0.041 |
bro | +0.039 |
Cub | +0.037 |
worth | +0.036 |
\/ | +0.035 |
Neg logit contributions | |
Rue | -0.036 |
yss | -0.035 |
Jung | -0.033 |
nir | -0.032 |
Tags | -0.032 |
Token | F |
Token ID | 376 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Rue | +0.394 |
yss | +0.383 |
Jung | +0.358 |
nir | +0.348 |
Tags | +0.347 |
Neg logit contributions | |
sbm | -0.397 |
bro | -0.382 |
Cub | -0.360 |
worth | -0.343 |
\/ | -0.334 |
Token | itch |
Token ID | 2007 |
Feature activation | +7.05e-02 |
Pos logit contributions | |
sbm | +0.121 |
bro | +0.116 |
Cub | +0.110 |
worth | +0.104 |
\/ | +0.102 |
Neg logit contributions | |
Rue | -0.115 |
yss | -0.110 |
Jung | -0.105 |
nir | -0.100 |
Tags | -0.100 |
Token | Ratings |
Token ID | 36826 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
sbm | +0.056 |
bro | +0.054 |
Cub | +0.052 |
worth | +0.049 |
\/ | +0.048 |
Neg logit contributions | |
Rue | -0.049 |
yss | -0.047 |
Jung | -0.044 |
nir | -0.043 |
Tags | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
sbm | +0.043 |
bro | +0.041 |
Cub | +0.040 |
worth | +0.038 |
\/ | +0.037 |
Neg logit contributions | |
Rue | -0.040 |
yss | -0.039 |
Jung | -0.036 |
nir | -0.035 |
Tags | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
Rue | +0.451 |
yss | +0.435 |
Jung | +0.410 |
nir | +0.394 |
Tags | +0.391 |
Neg logit contributions | |
sbm | -0.467 |
bro | -0.444 |
Cub | -0.423 |
worth | -0.400 |
\/ | -0.392 |
Token | continually |
Token ID | 17451 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Rue | +0.042 |
yss | +0.041 |
Jung | +0.038 |
nir | +0.037 |
Tags | +0.036 |
Neg logit contributions | |
sbm | -0.043 |
bro | -0.042 |
Cub | -0.040 |
worth | -0.038 |
\/ | -0.037 |
Token | burning |
Token ID | 9482 |
Feature activation | -5.06e-03 |
Pos logit contributions | |
Rue | +0.106 |
yss | +0.102 |
Jung | +0.095 |
nir | +0.092 |
Tags | +0.091 |
Neg logit contributions | |
sbm | -0.127 |
bro | -0.123 |
Cub | -0.117 |
worth | -0.112 |
\/ | -0.110 |
Token | sugar |
Token ID | 7543 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Rue | +0.004 |
yss | +0.004 |
Jung | +0.003 |
nir | +0.003 |
Tags | +0.003 |
Neg logit contributions | |
sbm | -0.004 |
bro | -0.004 |
Cub | -0.003 |
worth | -0.003 |
\/ | -0.003 |
Token | ( |
Token ID | 357 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Rue | +1.645 |
yss | +1.582 |
Jung | +1.495 |
nir | +1.435 |
Tags | +1.427 |
Neg logit contributions | |
sbm | -1.766 |
bro | -1.672 |
Cub | -1.597 |
worth | -1.509 |
\/ | -1.476 |
Token | gl |
Token ID | 4743 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
Rue | +0.149 |
yss | +0.144 |
Jung | +0.137 |
nir | +0.132 |
Tags | +0.131 |
Neg logit contributions | |
sbm | -0.124 |
bro | -0.118 |
Cub | -0.111 |
worth | -0.105 |
\/ | -0.102 |
Token | uc |
Token ID | 1229 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
Rue | +0.536 |
yss | +0.516 |
Jung | +0.486 |
nir | +0.467 |
Tags | +0.463 |
Neg logit contributions | |
sbm | -0.569 |
bro | -0.540 |
Cub | -0.515 |
worth | -0.488 |
\/ | -0.478 |
Token | ose |
Token ID | 577 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Rue | +2.000 |
yss | +1.914 |
Jung | +1.808 |
nir | +1.733 |
Tags | +1.714 |
Neg logit contributions | |
sbm | -2.527 |
bro | -2.391 |
Cub | -2.306 |
worth | -2.186 |
EEE | -2.137 |
Token | ) |
Token ID | 8 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
Rue | +0.858 |
yss | +0.827 |
Jung | +0.778 |
nir | +0.747 |
Tags | +0.742 |
Neg logit contributions | |
sbm | -0.927 |
bro | -0.887 |
Cub | -0.845 |
worth | -0.802 |
\/ | -0.787 |
Token | from |
Token ID | 422 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
sbm | +0.032 |
bro | +0.030 |
Cub | +0.029 |
worth | +0.027 |
\/ | +0.027 |
Neg logit contributions | |
Rue | -0.032 |
yss | -0.031 |
Jung | -0.029 |
nir | -0.028 |
Tags | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Rue | +0.496 |
yss | +0.479 |
Jung | +0.448 |
nir | +0.431 |
Tags | +0.428 |
Neg logit contributions | |
sbm | -0.545 |
bro | -0.523 |
Cub | -0.497 |
worth | -0.472 |
\/ | -0.463 |
Token | fed |
Token ID | 11672 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Rue | +0.160 |
yss | +0.155 |
Jung | +0.143 |
nir | +0.139 |
Tags | +0.137 |
Neg logit contributions | |
sbm | -0.197 |
bro | -0.190 |
Cub | -0.181 |
worth | -0.171 |
\/ | -0.170 |
Token | be |
Token ID | 307 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
Rue | +0.626 |
yss | +0.604 |
Jung | +0.569 |
nir | +0.547 |
Tags | +0.544 |
Neg logit contributions | |
sbm | -0.640 |
bro | -0.609 |
Cub | -0.579 |
worth | -0.548 |
\/ | -0.537 |
Token | more |
Token ID | 517 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
sbm | +0.010 |
bro | +0.009 |
Cub | +0.009 |
worth | +0.008 |
\/ | +0.008 |
Neg logit contributions | |
Rue | -0.013 |
yss | -0.012 |
Jung | -0.012 |
nir | -0.011 |
Tags | -0.011 |
Token | cost |
Token ID | 1575 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
sbm | +0.076 |
bro | +0.074 |
Cub | +0.070 |
worth | +0.067 |
\/ | +0.065 |
Neg logit contributions | |
Rue | -0.070 |
yss | -0.067 |
Jung | -0.063 |
nir | -0.061 |
Tags | -0.060 |
Token | over |
Token ID | 625 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
sbm | +0.920 |
bro | +0.897 |
Cub | +0.849 |
worth | +0.807 |
\/ | +0.797 |
Neg logit contributions | |
Rue | -0.828 |
yss | -0.793 |
Jung | -0.737 |
nir | -0.712 |
Tags | -0.705 |
Token | - |
Token ID | 12 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
Rue | +0.062 |
yss | +0.059 |
Jung | +0.055 |
nir | +0.052 |
Tags | +0.052 |
Neg logit contributions | |
sbm | -0.095 |
bro | -0.091 |
Cub | -0.088 |
worth | -0.084 |
\/ | -0.082 |
Token | runs |
Token ID | 48381 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
Rue | +0.637 |
yss | +0.619 |
Jung | +0.591 |
nir | +0.573 |
Tags | +0.570 |
Neg logit contributions | |
sbm | -0.396 |
bro | -0.369 |
Cub | -0.346 |
worth | -0.320 |
\/ | -0.311 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Rue | +1.691 |
yss | +1.626 |
Jung | +1.535 |
nir | +1.470 |
Tags | +1.460 |
Neg logit contributions | |
sbm | -1.857 |
bro | -1.762 |
Cub | -1.683 |
worth | -1.591 |
\/ | -1.559 |
Token |
|
Token ID | 198 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
Rue | +0.198 |
yss | +0.192 |
Jung | +0.178 |
nir | +0.173 |
Tags | +0.171 |
Neg logit contributions | |
sbm | -0.232 |
bro | -0.222 |
Cub | -0.212 |
worth | -0.202 |
\/ | -0.198 |
Token |
|
Token ID | 198 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
Rue | +0.340 |
yss | +0.330 |
Jung | +0.310 |
nir | +0.299 |
Tags | +0.296 |
Neg logit contributions | |
sbm | -0.333 |
bro | -0.317 |
Cub | -0.301 |
worth | -0.285 |
\/ | -0.279 |
Token | Then |
Token ID | 6423 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Rue | +0.623 |
yss | +0.600 |
Jung | +0.568 |
nir | +0.544 |
Tags | +0.539 |
Neg logit contributions | |
sbm | -0.616 |
bro | -0.587 |
Cub | -0.559 |
worth | -0.528 |
\/ | -0.516 |
Token | there |
Token ID | 612 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
sbm | +0.195 |
bro | +0.187 |
Cub | +0.177 |
worth | +0.169 |
\/ | +0.165 |
Neg logit contributions | |
Rue | -0.183 |
yss | -0.176 |
Jung | -0.165 |
nir | -0.159 |
Tags | -0.159 |
Token | of |
Token ID | 286 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
Rue | +0.455 |
yss | +0.437 |
Jung | +0.410 |
Tags | +0.388 |
refriger | +0.387 |
Neg logit contributions | |
sbm | -0.621 |
bro | -0.591 |
Cub | -0.567 |
worth | -0.536 |
EEE | -0.530 |
Token | all |
Token ID | 477 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
Rue | +0.431 |
yss | +0.416 |
Jung | +0.392 |
nir | +0.378 |
Tags | +0.375 |
Neg logit contributions | |
sbm | -0.422 |
bro | -0.401 |
Cub | -0.381 |
worth | -0.360 |
\/ | -0.352 |
Token | documents |
Token ID | 4963 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
Rue | +0.070 |
yss | +0.068 |
Jung | +0.064 |
nir | +0.061 |
Tags | +0.061 |
Neg logit contributions | |
sbm | -0.074 |
bro | -0.070 |
Cub | -0.067 |
worth | -0.064 |
\/ | -0.062 |
Token | in |
Token ID | 287 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
sbm | +0.663 |
bro | +0.632 |
Cub | +0.600 |
worth | +0.569 |
\/ | +0.556 |
Neg logit contributions | |
Rue | -0.672 |
yss | -0.650 |
Jung | -0.611 |
nir | -0.592 |
Tags | -0.586 |
Token | the |
Token ID | 262 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Rue | +0.396 |
yss | +0.383 |
Jung | +0.358 |
nir | +0.346 |
Tags | +0.342 |
Neg logit contributions | |
sbm | -0.442 |
bro | -0.422 |
Cub | -0.402 |
worth | -0.382 |
\/ | -0.374 |
Token | case |
Token ID | 1339 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
Rue | +0.212 |
yss | +0.205 |
Jung | +0.190 |
nir | +0.184 |
Tags | +0.182 |
Neg logit contributions | |
sbm | -0.270 |
bro | -0.259 |
Cub | -0.248 |
worth | -0.237 |
\/ | -0.232 |
Token | . |
Token ID | 13 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
Rue | +1.815 |
yss | +1.742 |
Jung | +1.652 |
refriger | +1.572 |
nir | +1.563 |
Neg logit contributions | |
sbm | -2.021 |
bro | -1.919 |
Cub | -1.838 |
worth | -1.730 |
EEE | -1.698 |
Token | Two |
Token ID | 4930 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
Rue | +0.064 |
yss | +0.063 |
Jung | +0.058 |
nir | +0.057 |
refriger | +0.056 |
Neg logit contributions | |
sbm | -0.071 |
bro | -0.067 |
Cub | -0.064 |
worth | -0.061 |
\/ | -0.060 |
Token | justices |
Token ID | 27818 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
Rue | +0.592 |
yss | +0.573 |
Jung | +0.534 |
nir | +0.514 |
Tags | +0.509 |
Neg logit contributions | |
sbm | -0.697 |
bro | -0.669 |
Cub | -0.637 |
worth | -0.607 |
\/ | -0.596 |
Token | declined |
Token ID | 7392 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
Rue | +0.316 |
yss | +0.305 |
Jung | +0.286 |
nir | +0.275 |
Tags | +0.274 |
Neg logit contributions | |
sbm | -0.345 |
bro | -0.330 |
Cub | -0.314 |
worth | -0.298 |
\/ | -0.292 |
Token | a |
Token ID | 257 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Rue | +0.225 |
yss | +0.216 |
Jung | +0.202 |
nir | +0.193 |
Tags | +0.192 |
Neg logit contributions | |
sbm | -0.284 |
bro | -0.271 |
Cub | -0.260 |
worth | -0.247 |
\/ | -0.243 |
Token | You |
Token ID | 1639 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Rue | +0.858 |
yss | +0.828 |
Jung | +0.780 |
nir | +0.753 |
Tags | +0.744 |
Neg logit contributions | |
sbm | -0.894 |
bro | -0.850 |
Cub | -0.810 |
worth | -0.768 |
\/ | -0.751 |
Token | contributed |
Token ID | 8639 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
Rue | +0.090 |
yss | +0.087 |
Jung | +0.082 |
nir | +0.079 |
Tags | +0.078 |
Neg logit contributions | |
sbm | -0.091 |
bro | -0.087 |
Cub | -0.083 |
worth | -0.078 |
\/ | -0.077 |
Token | money |
Token ID | 1637 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
sbm | +0.022 |
bro | +0.021 |
Cub | +0.020 |
worth | +0.019 |
\/ | +0.019 |
Neg logit contributions | |
Rue | -0.020 |
yss | -0.019 |
Jung | -0.018 |
nir | -0.018 |
Tags | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
Rue | +0.754 |
yss | +0.724 |
Jung | +0.680 |
nir | +0.652 |
Tags | +0.648 |
Neg logit contributions | |
sbm | -0.876 |
bro | -0.836 |
Cub | -0.798 |
worth | -0.759 |
\/ | -0.745 |
Token | Al |
Token ID | 978 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Rue | +0.014 |
yss | +0.014 |
Jung | +0.013 |
nir | +0.013 |
Tags | +0.013 |
Neg logit contributions | |
sbm | -0.016 |
bro | -0.015 |
Cub | -0.014 |
worth | -0.014 |
\/ | -0.013 |
Token | Qaeda |
Token ID | 17942 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Rue | +0.147 |
yss | +0.142 |
Jung | +0.134 |
nir | +0.129 |
Tags | +0.128 |
Neg logit contributions | |
sbm | -0.144 |
bro | -0.136 |
Cub | -0.130 |
worth | -0.122 |
\/ | -0.120 |
Token | � |
Token ID | 447 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Rue | +1.845 |
yss | +1.780 |
Jung | +1.676 |
nir | +1.599 |
Tags | +1.588 |
Neg logit contributions | |
sbm | -2.025 |
bro | -1.925 |
Cub | -1.835 |
worth | -1.736 |
EEE | -1.696 |
Token | � |
Token ID | 251 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
sbm | +0.085 |
bro | +0.081 |
Cub | +0.077 |
worth | +0.073 |
\/ | +0.071 |
Neg logit contributions | |
Rue | -0.088 |
yss | -0.085 |
Jung | -0.080 |
nir | -0.078 |
Tags | -0.077 |
Token | ) |
Token ID | 8 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
Rue | +0.071 |
yss | +0.068 |
Jung | +0.064 |
nir | +0.062 |
Tags | +0.062 |
Neg logit contributions | |
sbm | -0.078 |
bro | -0.074 |
Cub | -0.071 |
worth | -0.068 |
\/ | -0.066 |
Token | without |
Token ID | 1231 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
sbm | +0.401 |
bro | +0.380 |
Cub | +0.360 |
worth | +0.341 |
\/ | +0.334 |
Neg logit contributions | |
Rue | -0.437 |
yss | -0.421 |
Jung | -0.397 |
nir | -0.387 |
Tags | -0.384 |
Token | revealing |
Token ID | 13477 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
sbm | +0.698 |
bro | +0.669 |
Cub | +0.633 |
worth | +0.599 |
\/ | +0.589 |
Neg logit contributions | |
Rue | -0.711 |
yss | -0.698 |
Jung | -0.645 |
nir | -0.633 |
Tags | -0.629 |
Token | omet |
Token ID | 908 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Rue | +0.500 |
yss | +0.484 |
Jung | +0.459 |
nir | +0.443 |
Tags | +0.440 |
Neg logit contributions | |
sbm | -0.420 |
bro | -0.397 |
Cub | -0.376 |
worth | -0.354 |
\/ | -0.345 |
Token | hin |
Token ID | 20079 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
sbm | +0.255 |
bro | +0.243 |
Cub | +0.228 |
worth | +0.216 |
\/ | +0.211 |
Neg logit contributions | |
Rue | -0.300 |
yss | -0.287 |
Jung | -0.274 |
Tags | -0.264 |
nir | -0.264 |
Token | ' |
Token ID | 6 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
sbm | +0.042 |
bro | +0.040 |
Cub | +0.038 |
worth | +0.036 |
\/ | +0.035 |
Neg logit contributions | |
Rue | -0.048 |
yss | -0.047 |
Jung | -0.044 |
Tags | -0.042 |
nir | -0.042 |
Token | Better |
Token ID | 11625 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
sbm | +1.019 |
bro | +0.990 |
Cub | +0.926 |
worth | +0.889 |
\/ | +0.868 |
Neg logit contributions | |
Rue | -0.919 |
yss | -0.910 |
Jung | -0.826 |
nir | -0.813 |
Tags | -0.809 |
Token | Comes |
Token ID | 34606 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Rue | +0.980 |
yss | +0.940 |
Jung | +0.884 |
nir | +0.846 |
Tags | +0.839 |
Neg logit contributions | |
sbm | -1.161 |
bro | -1.106 |
Cub | -1.058 |
worth | -1.005 |
\/ | -0.985 |
Token | Along |
Token ID | 17159 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Rue | +0.884 |
yss | +0.853 |
Jung | +0.791 |
Tags | +0.758 |
nir | +0.757 |
Neg logit contributions | |
sbm | -1.148 |
bro | -1.102 |
Cub | -1.054 |
worth | -1.008 |
\/ | -0.990 |
Token | !", |
Token ID | 40754 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
Rue | +1.474 |
yss | +1.420 |
Jung | +1.328 |
nir | +1.273 |
Tags | +1.265 |
Neg logit contributions | |
sbm | -1.775 |
bro | -1.699 |
Cub | -1.621 |
worth | -1.543 |
\/ | -1.515 |
Token | a |
Token ID | 257 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Rue | +0.469 |
yss | +0.455 |
Jung | +0.423 |
nir | +0.413 |
Tags | +0.409 |
Neg logit contributions | |
sbm | -0.516 |
bro | -0.495 |
Cub | -0.471 |
worth | -0.451 |
\/ | -0.438 |
Token | song |
Token ID | 3496 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Rue | +0.233 |
yss | +0.226 |
Jung | +0.209 |
nir | +0.204 |
Tags | +0.202 |
Neg logit contributions | |
sbm | -0.262 |
bro | -0.252 |
Cub | -0.240 |
worth | -0.228 |
\/ | -0.223 |
Token | about |
Token ID | 546 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
sbm | +0.278 |
bro | +0.270 |
Cub | +0.258 |
worth | +0.245 |
\/ | +0.236 |
Neg logit contributions | |
Rue | -0.282 |
yss | -0.274 |
Jung | -0.253 |
nir | -0.252 |
Tags | -0.248 |
Token | their |
Token ID | 511 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
Rue | +0.210 |
yss | +0.207 |
Jung | +0.188 |
nir | +0.187 |
Tags | +0.185 |
Neg logit contributions | |
sbm | -0.225 |
bro | -0.219 |
Cub | -0.207 |
worth | -0.199 |
\/ | -0.192 |