Token | Don |
Token ID | 2094 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Row | +1.501 |
row | +1.445 |
Legs | +1.389 |
Rodham | +1.364 |
chest | +1.362 |
Neg logit contributions | |
uphem | -2.734 |
abwe | -2.623 |
avail | -2.608 |
ipeg | -2.600 |
ortmund | -2.495 |
Token | � |
Token ID | 447 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
Row | +0.614 |
Legs | +0.591 |
row | +0.587 |
Rodham | +0.585 |
brim | +0.582 |
Neg logit contributions | |
uphem | -0.521 |
avail | -0.492 |
ipeg | -0.487 |
abwe | -0.478 |
ortmund | -0.459 |
Token | � |
Token ID | 247 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Row | +1.630 |
Legs | +1.571 |
row | +1.559 |
Rodham | +1.545 |
chest | +1.524 |
Neg logit contributions | |
uphem | -1.518 |
abwe | -1.413 |
avail | -1.403 |
ipeg | -1.384 |
ortmund | -1.323 |
Token | t |
Token ID | 83 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Row | +0.771 |
Legs | +0.738 |
row | +0.733 |
Rodham | +0.731 |
brim | +0.721 |
Neg logit contributions | |
uphem | -0.601 |
avail | -0.561 |
abwe | -0.557 |
ipeg | -0.557 |
ortmund | -0.527 |
Token | Rid |
Token ID | 23223 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
Row | +0.640 |
row | +0.623 |
Legs | +0.599 |
chest | +0.594 |
Rodham | +0.593 |
Neg logit contributions | |
uphem | -0.930 |
avail | -0.886 |
abwe | -0.886 |
ipeg | -0.877 |
ortmund | -0.836 |
Token | ic |
Token ID | 291 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Row | +1.731 |
row | +1.660 |
Legs | +1.627 |
Rodham | +1.592 |
chest | +1.582 |
Neg logit contributions | |
uphem | -2.210 |
abwe | -2.119 |
ipeg | -2.092 |
avail | -2.078 |
ortmund | -1.993 |
Token | ule |
Token ID | 2261 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Row | +5.012 |
row | +4.882 |
Legs | +4.767 |
Rodham | +4.675 |
chest | +4.669 |
Neg logit contributions | |
uphem | -3.239 |
abwe | -3.097 |
ipeg | -3.024 |
avail | -2.997 |
ortmund | -2.827 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Row | +0.502 |
row | +0.487 |
Legs | +0.470 |
Rodham | +0.465 |
chest | +0.465 |
Neg logit contributions | |
uphem | -0.688 |
abwe | -0.656 |
avail | -0.647 |
ipeg | -0.645 |
ortmund | -0.616 |
Token | Other |
Token ID | 3819 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Row | +0.493 |
row | +0.481 |
Legs | +0.458 |
chest | +0.456 |
Rodham | +0.455 |
Neg logit contributions | |
uphem | -0.769 |
abwe | -0.736 |
avail | -0.729 |
ipeg | -0.728 |
ortmund | -0.694 |
Token | D |
Token ID | 360 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
Row | +1.084 |
row | +1.045 |
Legs | +1.011 |
Rodham | +1.006 |
chest | +1.002 |
Neg logit contributions | |
uphem | -1.459 |
abwe | -1.394 |
ipeg | -1.375 |
avail | -1.367 |
ortmund | -1.312 |
Token | ancers |
Token ID | 20811 |
Feature activation | +2.38e-03 |
Pos logit contributions | |
Row | +0.117 |
Legs | +0.111 |
row | +0.110 |
Guer | +0.110 |
brim | +0.110 |
Neg logit contributions | |
uphem | -0.153 |
abwe | -0.145 |
ipeg | -0.143 |
avail | -0.142 |
ancies | -0.138 |
Token | 3 |
Token ID | 513 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
Row | +1.600 |
row | +1.518 |
Legs | +1.476 |
Rodham | +1.441 |
Guer | +1.440 |
Neg logit contributions | |
uphem | -2.391 |
abwe | -2.313 |
ipeg | -2.285 |
avail | -2.247 |
ortmund | -2.182 |
Token | Next |
Token ID | 7406 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Row | +1.473 |
row | +1.401 |
Legs | +1.367 |
Guer | +1.329 |
Rodham | +1.326 |
Neg logit contributions | |
uphem | -1.892 |
abwe | -1.827 |
ipeg | -1.818 |
avail | -1.762 |
ortmund | -1.717 |
Token | All |
Token ID | 1439 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
uphem | +1.100 |
avail | +1.063 |
abwe | +1.055 |
ipeg | +1.040 |
ortmund | +0.994 |
Neg logit contributions | |
Row | -0.802 |
row | -0.767 |
chest | -0.760 |
Legs | -0.759 |
brim | -0.755 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Row | +0.238 |
row | +0.230 |
Legs | +0.226 |
Rodham | +0.222 |
chest | +0.222 |
Neg logit contributions | |
uphem | -0.233 |
abwe | -0.223 |
avail | -0.220 |
ipeg | -0.218 |
ortmund | -0.210 |
Token | This |
Token ID | 1212 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Row | +0.719 |
row | +0.676 |
Legs | +0.675 |
Rodham | +0.657 |
Guer | +0.654 |
Neg logit contributions | |
uphem | -1.036 |
abwe | -0.989 |
ipeg | -0.983 |
avail | -0.973 |
ortmund | -0.936 |
Token | article |
Token ID | 2708 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Row | +0.807 |
row | +0.775 |
Legs | +0.757 |
chest | +0.743 |
Rodham | +0.742 |
Neg logit contributions | |
uphem | -0.999 |
abwe | -0.960 |
ipeg | -0.950 |
avail | -0.947 |
ortmund | -0.903 |
Token | is |
Token ID | 318 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Row | +3.143 |
row | +3.005 |
Legs | +2.906 |
Rodham | +2.863 |
Guer | +2.856 |
Neg logit contributions | |
uphem | -4.509 |
abwe | -4.340 |
ipeg | -4.254 |
avail | -4.191 |
ortmund | -4.056 |
Token | over |
Token ID | 625 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
Row | +0.947 |
row | +0.906 |
Legs | +0.889 |
Rodham | +0.868 |
chest | +0.864 |
Neg logit contributions | |
uphem | -1.264 |
abwe | -1.216 |
ipeg | -1.201 |
avail | -1.196 |
ortmund | -1.142 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
uphem | +0.464 |
abwe | +0.446 |
avail | +0.440 |
ipeg | +0.437 |
ortmund | +0.415 |
Neg logit contributions | |
Row | -0.363 |
Legs | -0.347 |
row | -0.340 |
Rodham | -0.338 |
chest | -0.335 |
Token | years |
Token ID | 812 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
uphem | +0.038 |
abwe | +0.037 |
avail | +0.037 |
ipeg | +0.037 |
ortmund | +0.034 |
Neg logit contributions | |
Row | -0.036 |
row | -0.034 |
Legs | -0.034 |
Rodham | -0.033 |
Guer | -0.033 |
Token | old |
Token ID | 1468 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
Row | +0.319 |
row | +0.307 |
Legs | +0.301 |
Rodham | +0.295 |
chest | +0.294 |
Neg logit contributions | |
uphem | -0.363 |
abwe | -0.347 |
ipeg | -0.345 |
avail | -0.344 |
ortmund | -0.324 |
Token | went |
Token ID | 1816 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
Row | +0.317 |
row | +0.305 |
Legs | +0.303 |
chest | +0.295 |
Rodham | +0.293 |
Neg logit contributions | |
uphem | -0.326 |
avail | -0.313 |
abwe | -0.309 |
ipeg | -0.306 |
ortmund | -0.288 |
Token | through |
Token ID | 832 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Row | +0.464 |
row | +0.449 |
Legs | +0.437 |
chest | +0.427 |
Rodham | +0.425 |
Neg logit contributions | |
uphem | -0.706 |
avail | -0.686 |
abwe | -0.684 |
ipeg | -0.674 |
ortmund | -0.638 |
Token | weekly |
Token ID | 10273 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
Row | +0.487 |
row | +0.472 |
Legs | +0.463 |
Rodham | +0.455 |
chest | +0.452 |
Neg logit contributions | |
uphem | -0.512 |
abwe | -0.491 |
avail | -0.486 |
ipeg | -0.482 |
ortmund | -0.460 |
Token | " |
Token ID | 366 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
uphem | +0.260 |
avail | +0.249 |
abwe | +0.245 |
ipeg | +0.243 |
ortmund | +0.230 |
Neg logit contributions | |
Row | -0.259 |
row | -0.252 |
Legs | -0.246 |
Rodham | -0.242 |
chest | -0.239 |
Token | re |
Token ID | 260 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Row | +1.197 |
row | +1.137 |
Legs | +1.129 |
Rodham | +1.110 |
Guer | +1.099 |
Neg logit contributions | |
uphem | -1.336 |
abwe | -1.273 |
ipeg | -1.260 |
avail | -1.249 |
ortmund | -1.192 |
Token | par |
Token ID | 1845 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Row | +0.448 |
row | +0.427 |
Legs | +0.425 |
Rodham | +0.416 |
Guer | +0.413 |
Neg logit contributions | |
uphem | -0.477 |
abwe | -0.454 |
ipeg | -0.445 |
avail | -0.443 |
ortmund | -0.421 |
Token | ative |
Token ID | 876 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Row | +3.547 |
row | +3.461 |
Legs | +3.315 |
Rodham | +3.291 |
chest | +3.290 |
Neg logit contributions | |
uphem | -3.932 |
abwe | -3.780 |
ipeg | -3.723 |
avail | -3.668 |
ortmund | -3.539 |
Token | therapy |
Token ID | 9102 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Row | +1.164 |
row | +1.127 |
Legs | +1.115 |
Rodham | +1.092 |
Guer | +1.089 |
Neg logit contributions | |
uphem | -0.790 |
abwe | -0.744 |
avail | -0.737 |
ipeg | -0.730 |
ortmund | -0.682 |
Token | " |
Token ID | 1 |
Feature activation | -1.98e-03 |
Pos logit contributions | |
Row | +0.917 |
row | +0.874 |
Legs | +0.857 |
Rodham | +0.832 |
Guer | +0.830 |
Neg logit contributions | |
uphem | -1.443 |
abwe | -1.386 |
avail | -1.374 |
ipeg | -1.364 |
ortmund | -1.315 |
Token | sessions |
Token ID | 10991 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
uphem | +0.007 |
avail | +0.006 |
abwe | +0.006 |
ipeg | +0.006 |
ortmund | +0.006 |
Neg logit contributions | |
Row | -0.005 |
row | -0.005 |
Legs | -0.004 |
chest | -0.004 |
Rodham | -0.004 |
Token | through |
Token ID | 832 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
Row | +0.520 |
row | +0.499 |
Legs | +0.493 |
chest | +0.476 |
Rodham | +0.475 |
Neg logit contributions | |
uphem | -0.764 |
avail | -0.738 |
abwe | -0.735 |
ipeg | -0.719 |
ortmund | -0.691 |
Token |
|
Token ID | 198 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
Row | +0.302 |
row | +0.291 |
Legs | +0.288 |
Rodham | +0.282 |
brim | +0.282 |
Neg logit contributions | |
uphem | -0.278 |
avail | -0.263 |
ipeg | -0.261 |
abwe | -0.258 |
ortmund | -0.247 |
Token | Trivia |
Token ID | 23854 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
Row | +0.200 |
Legs | +0.190 |
row | +0.187 |
Rodham | +0.185 |
Guer | +0.182 |
Neg logit contributions | |
uphem | -0.291 |
abwe | -0.277 |
ipeg | -0.276 |
avail | -0.275 |
ortmund | -0.263 |
Token |
|
Token ID | 198 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
Row | +2.112 |
row | +2.004 |
Legs | +1.965 |
Guer | +1.920 |
Rodham | +1.906 |
Neg logit contributions | |
uphem | -2.645 |
abwe | -2.555 |
ipeg | -2.535 |
avail | -2.472 |
ortmund | -2.398 |
Token |
|
Token ID | 198 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
Row | +2.266 |
row | +2.176 |
Legs | +2.134 |
Rodham | +2.090 |
chest | +2.083 |
Neg logit contributions | |
uphem | -2.425 |
abwe | -2.332 |
ipeg | -2.289 |
avail | -2.265 |
ortmund | -2.169 |
Token | Originally |
Token ID | 22731 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Row | +1.772 |
row | +1.681 |
Legs | +1.649 |
Rodham | +1.607 |
Guer | +1.594 |
Neg logit contributions | |
uphem | -2.800 |
abwe | -2.694 |
ipeg | -2.665 |
avail | -2.646 |
ortmund | -2.547 |
Token | intended |
Token ID | 5292 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Row | +2.429 |
row | +2.314 |
Legs | +2.261 |
Rodham | +2.204 |
chest | +2.190 |
Neg logit contributions | |
uphem | -3.589 |
abwe | -3.459 |
ipeg | -3.417 |
avail | -3.391 |
ortmund | -3.263 |
Token | as |
Token ID | 355 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Row | +2.511 |
row | +2.346 |
Legs | +2.288 |
Guer | +2.213 |
chest | +2.198 |
Neg logit contributions | |
uphem | -4.902 |
abwe | -4.751 |
ipeg | -4.708 |
avail | -4.657 |
ortmund | -4.510 |
Token | a |
Token ID | 257 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Row | +1.710 |
row | +1.643 |
Legs | +1.613 |
Rodham | +1.580 |
Guer | +1.572 |
Neg logit contributions | |
uphem | -1.742 |
abwe | -1.668 |
ipeg | -1.646 |
avail | -1.630 |
ortmund | -1.558 |
Token | stand |
Token ID | 1302 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
Row | +0.758 |
row | +0.734 |
Legs | +0.720 |
Rodham | +0.706 |
chest | +0.703 |
Neg logit contributions | |
uphem | -0.756 |
abwe | -0.720 |
ipeg | -0.708 |
avail | -0.707 |
ortmund | -0.668 |
Token | - |
Token ID | 12 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Row | +1.210 |
row | +1.158 |
Legs | +1.145 |
Rodham | +1.121 |
Guer | +1.107 |
Neg logit contributions | |
uphem | -1.383 |
abwe | -1.323 |
avail | -1.308 |
ipeg | -1.308 |
ortmund | -1.238 |
Token | alone |
Token ID | 17749 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
Row | +0.690 |
row | +0.645 |
Legs | +0.642 |
Rodham | +0.623 |
Guer | +0.618 |
Neg logit contributions | |
uphem | -1.126 |
abwe | -1.084 |
ipeg | -1.073 |
avail | -1.069 |
ortmund | -1.023 |
Token | in |
Token ID | 287 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
Row | +0.882 |
row | +0.847 |
Legs | +0.827 |
Rodham | +0.812 |
chest | +0.806 |
Neg logit contributions | |
uphem | -1.333 |
abwe | -1.293 |
ipeg | -1.278 |
avail | -1.278 |
ortmund | -1.222 |
Token | Halo |
Token ID | 18597 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Row | +0.159 |
row | +0.155 |
Legs | +0.151 |
Rodham | +0.149 |
chest | +0.149 |
Neg logit contributions | |
uphem | -0.216 |
abwe | -0.208 |
avail | -0.206 |
ipeg | -0.204 |
ortmund | -0.195 |
Token | 3 |
Token ID | 513 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
Row | +0.369 |
row | +0.357 |
Legs | +0.350 |
chest | +0.341 |
Rodham | +0.339 |
Neg logit contributions | |
uphem | -0.529 |
abwe | -0.511 |
avail | -0.504 |
ipeg | -0.503 |
ortmund | -0.481 |
Token | ( |
Token ID | 357 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
Row | +0.221 |
row | +0.214 |
Legs | +0.208 |
chest | +0.204 |
Rodham | +0.203 |
Neg logit contributions | |
uphem | -0.342 |
abwe | -0.330 |
avail | -0.329 |
ipeg | -0.327 |
ortmund | -0.312 |
Token | Myth |
Token ID | 41444 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
uphem | +0.249 |
abwe | +0.239 |
avail | +0.236 |
ipeg | +0.236 |
successful | +0.224 |
Neg logit contributions | |
Row | -0.226 |
Legs | -0.216 |
row | -0.213 |
Rodham | -0.212 |
brim | -0.208 |
Token | ic |
Token ID | 291 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Row | +0.578 |
row | +0.555 |
Legs | +0.547 |
Rodham | +0.536 |
Guer | +0.534 |
Neg logit contributions | |
uphem | -0.621 |
abwe | -0.597 |
ipeg | -0.591 |
avail | -0.585 |
ortmund | -0.559 |
Token | Map |
Token ID | 9347 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
Row | +3.193 |
row | +3.031 |
Legs | +2.977 |
Rodham | +2.890 |
Guer | +2.883 |
Neg logit contributions | |
uphem | -4.243 |
abwe | -4.063 |
ipeg | -4.028 |
avail | -3.955 |
ortmund | -3.815 |
Token | Pack |
Token ID | 6400 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
Row | +0.072 |
row | +0.070 |
Legs | +0.068 |
Rodham | +0.067 |
brim | +0.066 |
Neg logit contributions | |
uphem | -0.092 |
abwe | -0.089 |
avail | -0.088 |
ipeg | -0.087 |
ortmund | -0.084 |
Token | ). |
Token ID | 737 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
uphem | +0.113 |
abwe | +0.109 |
avail | +0.109 |
ipeg | +0.107 |
ortmund | +0.102 |
Neg logit contributions | |
Row | -0.101 |
row | -0.097 |
Legs | -0.096 |
Rodham | -0.094 |
chest | -0.093 |
Token |
|
Token ID | 198 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
uphem | +1.168 |
abwe | +1.111 |
avail | +1.106 |
ipeg | +1.096 |
ortmund | +1.045 |
Neg logit contributions | |
Row | -1.021 |
row | -1.008 |
Rodham | -0.972 |
brim | -0.966 |
Legs | -0.963 |
Token |
|
Token ID | 198 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
Row | +0.215 |
row | +0.208 |
Legs | +0.206 |
brim | +0.203 |
Rodham | +0.202 |
Neg logit contributions | |
uphem | -0.193 |
avail | -0.183 |
ipeg | -0.182 |
abwe | -0.178 |
ortmund | -0.171 |
Token | Human |
Token ID | 5524 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Row | +0.888 |
row | +0.861 |
Legs | +0.840 |
chest | +0.829 |
Rodham | +0.823 |
Neg logit contributions | |
uphem | -0.939 |
abwe | -0.899 |
ipeg | -0.886 |
avail | -0.884 |
ortmund | -0.840 |
Token | Resource |
Token ID | 20857 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
uphem | +0.625 |
abwe | +0.595 |
ipeg | +0.595 |
avail | +0.585 |
ortmund | +0.558 |
Neg logit contributions | |
Row | -0.618 |
row | -0.598 |
Legs | -0.589 |
Rodham | -0.581 |
brim | -0.581 |
Token | Management |
Token ID | 8549 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
uphem | +0.630 |
abwe | +0.608 |
avail | +0.597 |
ipeg | +0.594 |
ortmund | +0.562 |
Neg logit contributions | |
Row | -0.722 |
row | -0.704 |
Legs | -0.689 |
Rodham | -0.684 |
chest | -0.684 |
Token | ) |
Token ID | 8 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
Row | +0.952 |
row | +0.914 |
Legs | +0.898 |
Rodham | +0.880 |
chest | +0.876 |
Neg logit contributions | |
uphem | -1.139 |
abwe | -1.094 |
ipeg | -1.075 |
avail | -1.072 |
ortmund | -1.025 |
Token | Cur |
Token ID | 4424 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Row | +0.058 |
row | +0.056 |
Legs | +0.054 |
Rodham | +0.054 |
chest | +0.054 |
Neg logit contributions | |
uphem | -0.063 |
abwe | -0.059 |
avail | -0.059 |
ipeg | -0.059 |
ortmund | -0.056 |
Token | ric |
Token ID | 1173 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
uphem | +0.488 |
abwe | +0.467 |
avail | +0.462 |
ipeg | +0.459 |
ortmund | +0.437 |
Neg logit contributions | |
Row | -0.388 |
Legs | -0.368 |
row | -0.361 |
Rodham | -0.360 |
Guer | -0.358 |
Token | ulum |
Token ID | 14452 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Row | +3.976 |
row | +3.859 |
Legs | +3.764 |
Rodham | +3.705 |
Guer | +3.692 |
Neg logit contributions | |
uphem | -3.381 |
abwe | -3.231 |
ipeg | -3.174 |
avail | -3.147 |
ortmund | -3.004 |
Token | guidelines |
Token ID | 9949 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
uphem | +0.341 |
abwe | +0.326 |
avail | +0.325 |
ipeg | +0.322 |
ortmund | +0.309 |
Neg logit contributions | |
Row | -0.232 |
row | -0.223 |
Legs | -0.217 |
Rodham | -0.214 |
chest | -0.213 |
Token | . |
Token ID | 13 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
Row | +0.456 |
row | +0.432 |
Legs | +0.428 |
Rodham | +0.415 |
chest | +0.413 |
Neg logit contributions | |
uphem | -0.753 |
abwe | -0.723 |
avail | -0.717 |
ipeg | -0.713 |
ortmund | -0.683 |
Token |
|
Token ID | 198 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
uphem | +0.199 |
abwe | +0.188 |
avail | +0.188 |
ipeg | +0.187 |
ortmund | +0.179 |
Neg logit contributions | |
Row | -0.158 |
row | -0.156 |
chest | -0.149 |
brim | -0.149 |
Legs | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
uphem | +0.172 |
avail | +0.164 |
ipeg | +0.162 |
abwe | +0.158 |
ortmund | +0.153 |
Neg logit contributions | |
Row | -0.194 |
row | -0.187 |
Legs | -0.187 |
brim | -0.184 |
Rodham | -0.183 |
Token | to |
Token ID | 284 |
Feature activation | -2.09e-03 |
Pos logit contributions | |
uphem | +0.562 |
avail | +0.540 |
abwe | +0.536 |
ipeg | +0.536 |
ortmund | +0.501 |
Neg logit contributions | |
Row | -0.504 |
Legs | -0.492 |
row | -0.487 |
chest | -0.480 |
Rodham | -0.470 |
Token | eight |
Token ID | 3624 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
uphem | +0.007 |
abwe | +0.006 |
avail | +0.006 |
ipeg | +0.006 |
ortmund | +0.006 |
Neg logit contributions | |
Row | -0.005 |
Legs | -0.005 |
row | -0.005 |
chest | -0.005 |
Rodham | -0.005 |
Token | years |
Token ID | 812 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
uphem | +0.265 |
avail | +0.254 |
ipeg | +0.251 |
abwe | +0.250 |
ancies | +0.238 |
Neg logit contributions | |
Row | -0.264 |
row | -0.256 |
Legs | -0.256 |
chest | -0.251 |
Rodham | -0.246 |
Token | made |
Token ID | 925 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Row | +0.127 |
row | +0.122 |
Legs | +0.121 |
chest | +0.117 |
Rodham | +0.116 |
Neg logit contributions | |
uphem | -0.177 |
abwe | -0.169 |
avail | -0.169 |
ipeg | -0.168 |
ortmund | -0.158 |
Token | no |
Token ID | 645 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Row | +0.587 |
row | +0.567 |
Legs | +0.560 |
chest | +0.545 |
Rodham | +0.543 |
Neg logit contributions | |
uphem | -0.633 |
abwe | -0.607 |
avail | -0.598 |
ipeg | -0.598 |
ortmund | -0.564 |
Token | distinction |
Token ID | 12941 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Row | +0.664 |
row | +0.642 |
Legs | +0.635 |
chest | +0.622 |
Guer | +0.616 |
Neg logit contributions | |
uphem | -0.639 |
avail | -0.617 |
abwe | -0.608 |
ipeg | -0.605 |
ortmund | -0.563 |
Token | between |
Token ID | 1022 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Row | +2.657 |
row | +2.515 |
Legs | +2.411 |
Rodham | +2.389 |
Guer | +2.363 |
Neg logit contributions | |
uphem | -4.663 |
abwe | -4.504 |
ipeg | -4.476 |
avail | -4.384 |
ortmund | -4.284 |
Token | youth |
Token ID | 6205 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
Row | +0.885 |
row | +0.855 |
Legs | +0.842 |
chest | +0.823 |
Rodham | +0.817 |
Neg logit contributions | |
uphem | -0.997 |
abwe | -0.957 |
avail | -0.947 |
ipeg | -0.942 |
ortmund | -0.891 |
Token | and |
Token ID | 290 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Row | +0.124 |
Legs | +0.119 |
row | +0.118 |
chest | +0.116 |
Rodham | +0.115 |
Neg logit contributions | |
uphem | -0.158 |
avail | -0.153 |
abwe | -0.152 |
ipeg | -0.152 |
ancies | -0.142 |
Token | adult |
Token ID | 4044 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
uphem | +0.553 |
avail | +0.535 |
abwe | +0.529 |
ipeg | +0.522 |
ancies | +0.483 |
Neg logit contributions | |
Row | -0.668 |
row | -0.649 |
Legs | -0.644 |
chest | -0.632 |
Rodham | -0.621 |
Token | punishment |
Token ID | 9837 |
Feature activation | +9.06e-02 |
Pos logit contributions | |
uphem | +0.718 |
avail | +0.701 |
abwe | +0.688 |
ipeg | +0.681 |
ancies | +0.641 |
Neg logit contributions | |
Row | -0.646 |
Legs | -0.632 |
row | -0.623 |
chest | -0.620 |
Rodham | -0.604 |
Token | on |
Token ID | 319 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
uphem | +0.547 |
abwe | +0.531 |
avail | +0.526 |
ipeg | +0.525 |
ortmund | +0.496 |
Neg logit contributions | |
Row | -0.476 |
row | -0.457 |
Legs | -0.454 |
chest | -0.446 |
Rodham | -0.446 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
Row | +0.262 |
row | +0.254 |
Legs | +0.247 |
chest | +0.246 |
Rodham | +0.245 |
Neg logit contributions | |
uphem | -0.252 |
abwe | -0.243 |
avail | -0.241 |
ipeg | -0.239 |
ortmund | -0.225 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
Row | +0.053 |
row | +0.050 |
Legs | +0.050 |
chest | +0.049 |
Rodham | +0.049 |
Neg logit contributions | |
uphem | -0.078 |
abwe | -0.076 |
avail | -0.076 |
ipeg | -0.075 |
ortmund | -0.072 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
Row | +0.030 |
row | +0.029 |
Legs | +0.028 |
Rodham | +0.028 |
brim | +0.028 |
Neg logit contributions | |
uphem | -0.028 |
abwe | -0.026 |
ipeg | -0.026 |
avail | -0.026 |
ortmund | -0.025 |
Token | Media |
Token ID | 13152 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
Row | +0.827 |
row | +0.778 |
Legs | +0.776 |
Rodham | +0.755 |
Guer | +0.752 |
Neg logit contributions | |
uphem | -1.196 |
abwe | -1.143 |
ipeg | -1.135 |
avail | -1.124 |
ortmund | -1.081 |
Token | playback |
Token ID | 16388 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Row | +0.154 |
row | +0.149 |
Legs | +0.147 |
chest | +0.145 |
Rodham | +0.144 |
Neg logit contributions | |
uphem | -0.173 |
abwe | -0.166 |
avail | -0.165 |
ipeg | -0.165 |
ortmund | -0.156 |
Token | is |
Token ID | 318 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Row | +2.832 |
row | +2.669 |
Legs | +2.598 |
Rodham | +2.537 |
Guer | +2.517 |
Neg logit contributions | |
uphem | -4.444 |
abwe | -4.310 |
ipeg | -4.249 |
avail | -4.176 |
ortmund | -4.055 |
Token | unsupported |
Token ID | 24222 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Row | +0.422 |
row | +0.410 |
Legs | +0.404 |
chest | +0.397 |
Rodham | +0.397 |
Neg logit contributions | |
uphem | -0.328 |
abwe | -0.310 |
avail | -0.306 |
ipeg | -0.305 |
ortmund | -0.285 |
Token | on |
Token ID | 319 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
uphem | +0.380 |
avail | +0.368 |
abwe | +0.358 |
ipeg | +0.358 |
ortmund | +0.342 |
Neg logit contributions | |
Row | -0.337 |
row | -0.326 |
Legs | -0.319 |
Rodham | -0.313 |
chest | -0.311 |
Token | your |
Token ID | 534 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
Row | +1.292 |
row | +1.236 |
Legs | +1.210 |
Rodham | +1.188 |
Guer | +1.177 |
Neg logit contributions | |
uphem | -1.632 |
abwe | -1.563 |
avail | -1.549 |
ipeg | -1.547 |
ortmund | -1.477 |
Token | device |
Token ID | 3335 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Row | +2.121 |
row | +2.060 |
Legs | +2.028 |
Rodham | +1.997 |
chest | +1.990 |
Neg logit contributions | |
uphem | -1.219 |
abwe | -1.153 |
ipeg | -1.126 |
avail | -1.104 |
ortmund | -1.038 |
Token | error |
Token ID | 4049 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
Row | +1.050 |
row | +1.002 |
Legs | +1.000 |
chest | +0.969 |
Rodham | +0.964 |
Neg logit contributions | |
uphem | -1.317 |
avail | -1.262 |
ipeg | -1.256 |
abwe | -1.254 |
ortmund | -1.193 |
Token | has |
Token ID | 468 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Row | +1.163 |
row | +1.112 |
Legs | +1.102 |
Rodham | +1.069 |
chest | +1.061 |
Neg logit contributions | |
uphem | -1.446 |
abwe | -1.388 |
ipeg | -1.374 |
avail | -1.372 |
ortmund | -1.304 |
Token | occurred |
Token ID | 5091 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
Row | +1.142 |
row | +1.099 |
Legs | +1.081 |
Rodham | +1.057 |
chest | +1.053 |
Neg logit contributions | |
uphem | -1.153 |
abwe | -1.102 |
ipeg | -1.088 |
avail | -1.082 |
ortmund | -1.028 |
Token | . |
Token ID | 13 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
Row | +0.812 |
row | +0.770 |
Legs | +0.758 |
brim | +0.735 |
Rodham | +0.732 |
Neg logit contributions | |
uphem | -1.382 |
abwe | -1.322 |
avail | -1.319 |
ipeg | -1.317 |
ortmund | -1.262 |
Token | Please |
Token ID | 4222 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
Row | +2.133 |
row | +2.081 |
Legs | +2.040 |
brim | +2.006 |
chest | +2.002 |
Neg logit contributions | |
uphem | -1.832 |
abwe | -1.716 |
avail | -1.715 |
ipeg | -1.712 |
ortmund | -1.606 |
Token | try |
Token ID | 1949 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Row | +1.263 |
row | +1.215 |
Legs | +1.208 |
chest | +1.169 |
Rodham | +1.158 |
Neg logit contributions | |
uphem | -1.667 |
avail | -1.607 |
abwe | -1.567 |
ipeg | -1.562 |
ortmund | -1.499 |
Token | again |
Token ID | 757 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Row | +2.280 |
row | +2.143 |
Legs | +2.079 |
Rodham | +2.014 |
chest | +1.996 |
Neg logit contributions | |
uphem | -4.942 |
abwe | -4.790 |
ipeg | -4.734 |
avail | -4.701 |
ortmund | -4.549 |
Token | later |
Token ID | 1568 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Row | +2.217 |
row | +2.142 |
Legs | +2.122 |
chest | +2.067 |
Rodham | +2.063 |
Neg logit contributions | |
uphem | -1.793 |
abwe | -1.688 |
avail | -1.682 |
ipeg | -1.673 |
ortmund | -1.577 |
Token | . |
Token ID | 13 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
Row | +0.458 |
row | +0.439 |
Legs | +0.436 |
brim | +0.433 |
chest | +0.420 |
Neg logit contributions | |
uphem | -0.734 |
ipeg | -0.700 |
avail | -0.699 |
abwe | -0.692 |
ortmund | -0.667 |
Token | View |
Token ID | 3582 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Row | +2.300 |
row | +2.187 |
Legs | +2.147 |
Rodham | +2.101 |
Guer | +2.090 |
Neg logit contributions | |
uphem | -2.978 |
abwe | -2.865 |
ipeg | -2.830 |
avail | -2.791 |
ortmund | -2.691 |
Token | all |
Token ID | 477 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Row | +1.097 |
row | +1.054 |
Legs | +1.054 |
chest | +1.019 |
Rodham | +1.013 |
Neg logit contributions | |
uphem | -1.372 |
avail | -1.317 |
ipeg | -1.300 |
abwe | -1.295 |
ortmund | -1.238 |
Token | error |
Token ID | 4049 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
Row | +1.047 |
row | +0.999 |
Legs | +0.999 |
chest | +0.967 |
Rodham | +0.962 |
Neg logit contributions | |
uphem | -1.311 |
avail | -1.256 |
ipeg | -1.249 |
abwe | -1.248 |
ortmund | -1.187 |
Token | has |
Token ID | 468 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Row | +1.178 |
row | +1.127 |
Legs | +1.115 |
Rodham | +1.082 |
chest | +1.075 |
Neg logit contributions | |
uphem | -1.473 |
abwe | -1.415 |
ipeg | -1.399 |
avail | -1.396 |
ortmund | -1.329 |
Token | occurred |
Token ID | 5091 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Row | +1.081 |
row | +1.040 |
Legs | +1.024 |
Rodham | +1.001 |
chest | +0.997 |
Neg logit contributions | |
uphem | -1.086 |
abwe | -1.039 |
ipeg | -1.026 |
avail | -1.020 |
ortmund | -0.969 |
Token | . |
Token ID | 13 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
Row | +0.830 |
row | +0.787 |
Legs | +0.776 |
brim | +0.751 |
Rodham | +0.749 |
Neg logit contributions | |
uphem | -1.413 |
abwe | -1.351 |
avail | -1.348 |
ipeg | -1.346 |
ortmund | -1.290 |
Token | Please |
Token ID | 4222 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
Row | +2.182 |
row | +2.127 |
Legs | +2.086 |
brim | +2.049 |
chest | +2.046 |
Neg logit contributions | |
uphem | -1.882 |
abwe | -1.765 |
avail | -1.761 |
ipeg | -1.758 |
ortmund | -1.651 |
Token | try |
Token ID | 1949 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Row | +1.115 |
row | +1.073 |
Legs | +1.071 |
chest | +1.035 |
Rodham | +1.024 |
Neg logit contributions | |
uphem | -1.457 |
avail | -1.407 |
abwe | -1.366 |
ipeg | -1.362 |
ortmund | -1.309 |
Token | again |
Token ID | 757 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
Row | +2.263 |
row | +2.127 |
Legs | +2.063 |
Rodham | +1.998 |
chest | +1.981 |
Neg logit contributions | |
uphem | -4.909 |
abwe | -4.759 |
ipeg | -4.703 |
avail | -4.669 |
ortmund | -4.518 |
Token | later |
Token ID | 1568 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Row | +2.174 |
row | +2.100 |
Legs | +2.080 |
chest | +2.026 |
Rodham | +2.024 |
Neg logit contributions | |
uphem | -1.768 |
abwe | -1.666 |
avail | -1.657 |
ipeg | -1.650 |
ortmund | -1.556 |
Token | . |
Token ID | 13 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
Row | +0.520 |
row | +0.497 |
Legs | +0.494 |
brim | +0.488 |
Guer | +0.475 |
Neg logit contributions | |
uphem | -0.837 |
ipeg | -0.798 |
avail | -0.798 |
abwe | -0.790 |
ortmund | -0.761 |
Token | View |
Token ID | 3582 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Row | +2.324 |
row | +2.210 |
Legs | +2.170 |
Rodham | +2.122 |
Guer | +2.111 |
Neg logit contributions | |
uphem | -3.014 |
abwe | -2.901 |
ipeg | -2.865 |
avail | -2.825 |
ortmund | -2.723 |
Token | all |
Token ID | 477 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
Row | +1.050 |
row | +1.008 |
Legs | +1.008 |
chest | +0.975 |
Rodham | +0.969 |
Neg logit contributions | |
uphem | -1.318 |
avail | -1.264 |
ipeg | -1.248 |
abwe | -1.245 |
ortmund | -1.190 |
Token | error |
Token ID | 4049 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Row | +1.032 |
row | +0.985 |
Legs | +0.985 |
chest | +0.954 |
Rodham | +0.948 |
Neg logit contributions | |
uphem | -1.285 |
avail | -1.235 |
ipeg | -1.226 |
abwe | -1.223 |
ortmund | -1.165 |
Token | has |
Token ID | 468 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Row | +1.284 |
row | +1.228 |
Legs | +1.216 |
Rodham | +1.179 |
chest | +1.171 |
Neg logit contributions | |
uphem | -1.600 |
abwe | -1.535 |
ipeg | -1.520 |
avail | -1.518 |
ortmund | -1.443 |
Token | occurred |
Token ID | 5091 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
Row | +1.186 |
row | +1.141 |
Legs | +1.124 |
Rodham | +1.098 |
chest | +1.094 |
Neg logit contributions | |
uphem | -1.186 |
abwe | -1.133 |
ipeg | -1.120 |
avail | -1.115 |
ortmund | -1.057 |
Token | . |
Token ID | 13 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
Row | +0.833 |
row | +0.790 |
Legs | +0.780 |
brim | +0.757 |
Rodham | +0.751 |
Neg logit contributions | |
uphem | -1.403 |
abwe | -1.340 |
avail | -1.339 |
ipeg | -1.336 |
ortmund | -1.280 |
Token | Please |
Token ID | 4222 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
Row | +2.089 |
row | +2.042 |
Legs | +2.004 |
brim | +1.974 |
chest | +1.965 |
Neg logit contributions | |
uphem | -1.761 |
avail | -1.653 |
ipeg | -1.643 |
abwe | -1.641 |
ortmund | -1.541 |
Token | try |
Token ID | 1949 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Row | +1.156 |
row | +1.114 |
Legs | +1.111 |
chest | +1.074 |
Rodham | +1.061 |
Neg logit contributions | |
uphem | -1.492 |
avail | -1.445 |
abwe | -1.397 |
ipeg | -1.395 |
ortmund | -1.340 |
Token | again |
Token ID | 757 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
Row | +2.268 |
row | +2.133 |
Legs | +2.071 |
Rodham | +2.004 |
chest | +1.988 |
Neg logit contributions | |
uphem | -4.889 |
abwe | -4.733 |
ipeg | -4.683 |
avail | -4.654 |
ortmund | -4.499 |
Token | later |
Token ID | 1568 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Row | +2.297 |
row | +2.219 |
Legs | +2.195 |
chest | +2.139 |
Rodham | +2.138 |
Neg logit contributions | |
uphem | -1.881 |
abwe | -1.775 |
avail | -1.761 |
ipeg | -1.756 |
ortmund | -1.656 |
Token | . |
Token ID | 13 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
Row | +0.574 |
row | +0.550 |
Legs | +0.545 |
brim | +0.542 |
chest | +0.526 |
Neg logit contributions | |
uphem | -0.919 |
ipeg | -0.876 |
avail | -0.875 |
abwe | -0.867 |
ortmund | -0.835 |
Token | View |
Token ID | 3582 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Row | +2.291 |
row | +2.185 |
Legs | +2.144 |
Rodham | +2.097 |
Guer | +2.084 |
Neg logit contributions | |
uphem | -2.930 |
abwe | -2.818 |
ipeg | -2.781 |
avail | -2.749 |
ortmund | -2.645 |
Token | all |
Token ID | 477 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Row | +1.133 |
Legs | +1.091 |
row | +1.090 |
chest | +1.055 |
Rodham | +1.047 |
Neg logit contributions | |
uphem | -1.406 |
avail | -1.352 |
ipeg | -1.331 |
abwe | -1.325 |
ortmund | -1.268 |
Token | large |
Token ID | 1588 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
Row | +0.268 |
row | +0.259 |
Legs | +0.254 |
chest | +0.249 |
Rodham | +0.247 |
Neg logit contributions | |
uphem | -0.282 |
abwe | -0.272 |
avail | -0.271 |
ipeg | -0.266 |
ancies | -0.250 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Row | +0.129 |
row | +0.122 |
Legs | +0.120 |
chest | +0.118 |
Rodham | +0.118 |
Neg logit contributions | |
uphem | -0.168 |
abwe | -0.165 |
avail | -0.163 |
ipeg | -0.161 |
ortmund | -0.152 |
Token | probably |
Token ID | 2192 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
uphem | +0.287 |
avail | +0.278 |
abwe | +0.275 |
ipeg | +0.271 |
successful | +0.252 |
Neg logit contributions | |
Row | -0.381 |
row | -0.370 |
Legs | -0.365 |
chest | -0.361 |
Rodham | -0.357 |
Token | end |
Token ID | 886 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Row | +0.391 |
row | +0.378 |
Legs | +0.372 |
chest | +0.364 |
Rodham | +0.363 |
Neg logit contributions | |
uphem | -0.367 |
avail | -0.353 |
abwe | -0.351 |
ipeg | -0.347 |
ancies | -0.323 |
Token | other |
Token ID | 847 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
uphem | +0.276 |
abwe | +0.261 |
ipeg | +0.257 |
avail | +0.253 |
ancies | +0.235 |
Neg logit contributions | |
Row | -0.473 |
row | -0.456 |
Legs | -0.453 |
Guer | -0.448 |
Rodham | -0.448 |
Token | mic |
Token ID | 9383 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Row | +0.305 |
row | +0.294 |
Legs | +0.289 |
Rodham | +0.283 |
chest | +0.282 |
Neg logit contributions | |
uphem | -0.298 |
abwe | -0.285 |
ipeg | -0.281 |
avail | -0.279 |
ortmund | -0.266 |
Token | ( |
Token ID | 357 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Row | +2.810 |
row | +2.686 |
Legs | +2.615 |
Rodham | +2.551 |
chest | +2.534 |
Neg logit contributions | |
uphem | -4.263 |
abwe | -4.097 |
ipeg | -4.057 |
avail | -4.008 |
ortmund | -3.882 |
Token | warm |
Token ID | 31975 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
Row | +0.911 |
row | +0.860 |
Legs | +0.857 |
Rodham | +0.844 |
Guer | +0.836 |
Neg logit contributions | |
uphem | -0.975 |
abwe | -0.939 |
ipeg | -0.921 |
avail | -0.913 |
ortmund | -0.866 |
Token | blood |
Token ID | 2910 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Row | +0.232 |
row | +0.219 |
Legs | +0.216 |
Rodham | +0.213 |
Guer | +0.210 |
Neg logit contributions | |
uphem | -0.304 |
abwe | -0.294 |
ipeg | -0.291 |
avail | -0.288 |
ortmund | -0.274 |
Token | ed |
Token ID | 276 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Row | +0.618 |
row | +0.589 |
Legs | +0.584 |
Rodham | +0.574 |
Guer | +0.571 |
Neg logit contributions | |
uphem | -0.582 |
abwe | -0.558 |
ipeg | -0.551 |
avail | -0.545 |
ortmund | -0.516 |
Token | ), |
Token ID | 828 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Row | +0.387 |
row | +0.369 |
Legs | +0.360 |
Rodham | +0.355 |
Guer | +0.352 |
Neg logit contributions | |
uphem | -0.496 |
abwe | -0.480 |
avail | -0.472 |
ipeg | -0.472 |
ortmund | -0.446 |
Token | me |
Token ID | 502 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
uphem | +0.438 |
avail | +0.423 |
ipeg | +0.421 |
abwe | +0.412 |
ortmund | +0.392 |
Neg logit contributions | |
Row | -0.326 |
row | -0.320 |
Legs | -0.310 |
chest | -0.307 |
Rodham | -0.306 |
Token | closer |
Token ID | 5699 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Row | +0.185 |
row | +0.176 |
Legs | +0.175 |
Rodham | +0.171 |
Guer | +0.169 |
Neg logit contributions | |
uphem | -0.254 |
avail | -0.245 |
ipeg | -0.241 |
abwe | -0.240 |
ortmund | -0.226 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Row | +0.429 |
row | +0.414 |
Legs | +0.404 |
Rodham | +0.398 |
chest | +0.394 |
Neg logit contributions | |
uphem | -0.628 |
avail | -0.605 |
abwe | -0.599 |
ipeg | -0.599 |
ortmund | -0.563 |
Token | her |
Token ID | 607 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
uphem | +0.384 |
avail | +0.368 |
abwe | +0.364 |
ipeg | +0.363 |
ortmund | +0.341 |
Neg logit contributions | |
Row | -0.318 |
row | -0.310 |
Legs | -0.299 |
Rodham | -0.297 |
chest | -0.294 |
Token | hands |
Token ID | 2832 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
uphem | +0.906 |
avail | +0.871 |
ipeg | +0.856 |
abwe | +0.845 |
Trojan | +0.797 |
Neg logit contributions | |
Row | -0.733 |
row | -0.708 |
Rodham | -0.689 |
Legs | -0.680 |
Guer | -0.675 |
Token | settle |
Token ID | 12259 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Row | +0.665 |
row | +0.642 |
Legs | +0.635 |
Rodham | +0.623 |
chest | +0.619 |
Neg logit contributions | |
uphem | -0.830 |
avail | -0.812 |
ipeg | -0.786 |
abwe | -0.779 |
ortmund | -0.735 |
Token | at |
Token ID | 379 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
Row | +2.876 |
row | +2.745 |
Legs | +2.686 |
Rodham | +2.620 |
chest | +2.604 |
Neg logit contributions | |
uphem | -4.162 |
abwe | -4.006 |
ipeg | -3.964 |
avail | -3.941 |
ortmund | -3.776 |
Token | the |
Token ID | 262 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
Row | +0.216 |
row | +0.210 |
Legs | +0.203 |
Rodham | +0.199 |
Guer | +0.196 |
Neg logit contributions | |
uphem | -0.336 |
abwe | -0.322 |
ipeg | -0.321 |
avail | -0.321 |
ortmund | -0.306 |
Token | back |
Token ID | 736 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Row | +0.095 |
row | +0.091 |
Legs | +0.090 |
Rodham | +0.089 |
Guer | +0.087 |
Neg logit contributions | |
uphem | -0.147 |
avail | -0.143 |
ipeg | -0.140 |
abwe | -0.138 |
ortmund | -0.134 |
Token | of |
Token ID | 286 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
Row | +0.745 |
row | +0.714 |
Legs | +0.701 |
Rodham | +0.689 |
Guer | +0.685 |
Neg logit contributions | |
uphem | -0.860 |
abwe | -0.824 |
ipeg | -0.813 |
avail | -0.810 |
ortmund | -0.773 |
Token | my |
Token ID | 616 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
uphem | +0.899 |
abwe | +0.864 |
ipeg | +0.860 |
avail | +0.854 |
ortmund | +0.821 |
Neg logit contributions | |
Row | -0.534 |
row | -0.516 |
Legs | -0.496 |
Rodham | -0.490 |
chest | -0.482 |
Token | have |
Token ID | 423 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
uphem | +0.252 |
avail | +0.248 |
abwe | +0.240 |
ipeg | +0.234 |
ortmund | +0.225 |
Neg logit contributions | |
Row | -0.230 |
row | -0.222 |
Legs | -0.220 |
chest | -0.217 |
Rodham | -0.216 |
Token | been |
Token ID | 587 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
Row | +0.085 |
row | +0.082 |
Legs | +0.081 |
chest | +0.080 |
Rodham | +0.079 |
Neg logit contributions | |
uphem | -0.094 |
abwe | -0.090 |
avail | -0.090 |
ipeg | -0.089 |
ortmund | -0.084 |
Token | cutting |
Token ID | 7720 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
Row | +0.089 |
row | +0.087 |
Legs | +0.085 |
chest | +0.083 |
Rodham | +0.083 |
Neg logit contributions | |
uphem | -0.092 |
avail | -0.089 |
abwe | -0.086 |
ipeg | -0.085 |
successful | -0.081 |
Token | off |
Token ID | 572 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
uphem | +0.170 |
avail | +0.166 |
abwe | +0.162 |
ipeg | +0.162 |
ortmund | +0.152 |
Neg logit contributions | |
Row | -0.155 |
row | -0.153 |
Legs | -0.150 |
chest | -0.148 |
Rodham | -0.146 |
Token | their |
Token ID | 511 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Row | +0.698 |
row | +0.683 |
Legs | +0.666 |
chest | +0.654 |
Rodham | +0.652 |
Neg logit contributions | |
uphem | -0.705 |
avail | -0.674 |
abwe | -0.669 |
ipeg | -0.666 |
ortmund | -0.620 |
Token | arms |
Token ID | 5101 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Row | +0.664 |
row | +0.649 |
Legs | +0.634 |
Rodham | +0.625 |
chest | +0.623 |
Neg logit contributions | |
uphem | -0.586 |
abwe | -0.555 |
avail | -0.554 |
ipeg | -0.551 |
ortmund | -0.510 |
Token | to |
Token ID | 284 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
Row | +2.847 |
row | +2.711 |
Legs | +2.646 |
chest | +2.560 |
Rodham | +2.559 |
Neg logit contributions | |
uphem | -4.159 |
abwe | -4.022 |
ipeg | -3.973 |
avail | -3.898 |
ortmund | -3.793 |
Token | save |
Token ID | 3613 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
Row | +0.940 |
row | +0.916 |
Legs | +0.896 |
Rodham | +0.879 |
chest | +0.876 |
Neg logit contributions | |
uphem | -0.919 |
avail | -0.873 |
abwe | -0.872 |
ipeg | -0.851 |
ortmund | -0.808 |
Token | their |
Token ID | 511 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Row | +0.239 |
row | +0.236 |
Legs | +0.228 |
chest | +0.225 |
Rodham | +0.223 |
Neg logit contributions | |
uphem | -0.296 |
avail | -0.288 |
abwe | -0.284 |
ipeg | -0.282 |
ancies | -0.262 |
Token | heads |
Token ID | 6665 |
Feature activation | +8.21e-03 |
Pos logit contributions | |
uphem | +0.362 |
avail | +0.349 |
abwe | +0.347 |
ipeg | +0.345 |
ancies | +0.317 |
Neg logit contributions | |
Row | -0.379 |
row | -0.373 |
Legs | -0.363 |
Rodham | -0.358 |
chest | -0.357 |
Token | , |
Token ID | 11 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
Row | +0.019 |
row | +0.018 |
Legs | +0.018 |
Rodham | +0.017 |
Guer | +0.017 |
Neg logit contributions | |
uphem | -0.028 |
abwe | -0.027 |
avail | -0.027 |
ipeg | -0.026 |
ortmund | -0.025 |
Token | � |
Token ID | 447 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
uphem | +0.028 |
abwe | +0.027 |
ipeg | +0.026 |
avail | +0.026 |
ortmund | +0.025 |
Neg logit contributions | |
Row | -0.028 |
row | -0.027 |
Legs | -0.026 |
Rodham | -0.026 |
chest | -0.026 |
Token | � |
Token ID | 251 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
uphem | +0.414 |
abwe | +0.394 |
avail | +0.388 |
ipeg | +0.386 |
ortmund | +0.368 |
Neg logit contributions | |
Row | -0.382 |
row | -0.368 |
Legs | -0.364 |
chest | -0.359 |
Rodham | -0.359 |
Token | Mr |
Token ID | 1770 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
uphem | +0.081 |
abwe | +0.078 |
ipeg | +0.077 |
avail | +0.077 |
ortmund | +0.073 |
Neg logit contributions | |
Row | -0.064 |
row | -0.061 |
Legs | -0.060 |
Rodham | -0.058 |
chest | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Row | +1.109 |
row | +1.051 |
Legs | +1.019 |
Rodham | +0.994 |
Guer | +0.989 |
Neg logit contributions | |
uphem | -2.073 |
abwe | -2.004 |
ipeg | -1.985 |
avail | -1.979 |
ortmund | -1.907 |
Token | Kn |
Token ID | 6102 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
Row | +0.463 |
row | +0.444 |
Legs | +0.434 |
Rodham | +0.423 |
chest | +0.421 |
Neg logit contributions | |
uphem | -0.615 |
abwe | -0.591 |
ipeg | -0.583 |
avail | -0.578 |
ortmund | -0.555 |
Token | iz |
Token ID | 528 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
uphem | +0.129 |
abwe | +0.123 |
ipeg | +0.122 |
avail | +0.119 |
ortmund | +0.115 |
Neg logit contributions | |
Row | -0.137 |
Legs | -0.131 |
row | -0.130 |
Rodham | -0.128 |
Guer | -0.127 |
Token | ak |
Token ID | 461 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
Row | +2.944 |
row | +2.849 |
Legs | +2.729 |
Guer | +2.689 |
chest | +2.688 |
Neg logit contributions | |
uphem | -4.015 |
abwe | -3.867 |
ipeg | -3.811 |
avail | -3.789 |
ortmund | -3.647 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Row | +1.748 |
row | +1.680 |
Legs | +1.632 |
Rodham | +1.595 |
chest | +1.593 |
Neg logit contributions | |
uphem | -2.224 |
abwe | -2.139 |
ipeg | -2.108 |
avail | -2.095 |
ortmund | -2.011 |
Token | the |
Token ID | 262 |
Feature activation | -6.14e-03 |
Pos logit contributions | |
Row | +0.364 |
row | +0.351 |
Legs | +0.343 |
Rodham | +0.336 |
chest | +0.334 |
Neg logit contributions | |
uphem | -0.428 |
abwe | -0.410 |
ipeg | -0.404 |
avail | -0.402 |
ortmund | -0.384 |
Token | gallery |
Token ID | 15604 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
uphem | +0.018 |
abwe | +0.017 |
avail | +0.017 |
ipeg | +0.017 |
ortmund | +0.016 |
Neg logit contributions | |
Row | -0.017 |
row | -0.016 |
Legs | -0.016 |
Rodham | -0.016 |
chest | -0.015 |
Token | director |
Token ID | 3437 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
uphem | +0.077 |
abwe | +0.074 |
avail | +0.073 |
ipeg | +0.073 |
ortmund | +0.069 |
Neg logit contributions | |
Row | -0.069 |
row | -0.066 |
Legs | -0.065 |
Rodham | -0.063 |
chest | -0.063 |
Token | unsupported |
Token ID | 24222 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Row | +0.343 |
row | +0.334 |
Legs | +0.328 |
chest | +0.322 |
Rodham | +0.322 |
Neg logit contributions | |
uphem | -0.268 |
abwe | -0.254 |
avail | -0.250 |
ipeg | -0.249 |
ortmund | -0.233 |
Token | on |
Token ID | 319 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
uphem | +0.456 |
avail | +0.441 |
abwe | +0.429 |
ipeg | +0.429 |
ortmund | +0.410 |
Neg logit contributions | |
Row | -0.406 |
row | -0.393 |
Legs | -0.385 |
Rodham | -0.377 |
chest | -0.376 |
Token | your |
Token ID | 534 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
Row | +1.348 |
row | +1.289 |
Legs | +1.263 |
Rodham | +1.236 |
Guer | +1.226 |
Neg logit contributions | |
uphem | -1.745 |
abwe | -1.674 |
ipeg | -1.655 |
avail | -1.651 |
ortmund | -1.578 |
Token | device |
Token ID | 3335 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Row | +2.017 |
row | +1.958 |
Legs | +1.928 |
Rodham | +1.899 |
chest | +1.892 |
Neg logit contributions | |
uphem | -1.153 |
abwe | -1.090 |
ipeg | -1.064 |
avail | -1.045 |
ortmund | -0.981 |
Token | Media |
Token ID | 6343 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
Row | +1.042 |
row | +1.005 |
Legs | +0.984 |
Rodham | +0.965 |
chest | +0.962 |
Neg logit contributions | |
uphem | -1.070 |
abwe | -1.021 |
ipeg | -1.008 |
avail | -1.003 |
ortmund | -0.954 |
Token | caption |
Token ID | 8305 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Row | +0.180 |
row | +0.172 |
Legs | +0.167 |
chest | +0.164 |
Rodham | +0.163 |
Neg logit contributions | |
uphem | -0.326 |
abwe | -0.313 |
avail | -0.313 |
ipeg | -0.312 |
ortmund | -0.299 |
Token | Nigel |
Token ID | 28772 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
Row | +2.924 |
row | +2.748 |
Legs | +2.718 |
Rodham | +2.643 |
Guer | +2.638 |
Neg logit contributions | |
uphem | -4.099 |
abwe | -3.953 |
ipeg | -3.903 |
avail | -3.874 |
ortmund | -3.725 |
Token | Farage |
Token ID | 33904 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
Row | +1.412 |
row | +1.385 |
Legs | +1.368 |
chest | +1.356 |
brim | +1.339 |
Neg logit contributions | |
uphem | -0.993 |
abwe | -0.920 |
avail | -0.911 |
ipeg | -0.909 |
ortmund | -0.835 |
Token | : |
Token ID | 25 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Row | +0.727 |
row | +0.703 |
Legs | +0.694 |
chest | +0.679 |
Rodham | +0.672 |
Neg logit contributions | |
uphem | -0.959 |
avail | -0.918 |
abwe | -0.915 |
ipeg | -0.909 |
ortmund | -0.861 |
Token | " |
Token ID | 366 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
Row | +0.238 |
row | +0.229 |
Legs | +0.222 |
Rodham | +0.218 |
chest | +0.217 |
Neg logit contributions | |
uphem | -0.374 |
abwe | -0.360 |
ipeg | -0.355 |
avail | -0.353 |
ortmund | -0.340 |
Token | Lord |
Token ID | 22438 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
uphem | +0.290 |
ipeg | +0.275 |
abwe | +0.275 |
avail | +0.272 |
ortmund | +0.262 |
Neg logit contributions | |
Row | -0.203 |
row | -0.190 |
Legs | -0.190 |
Rodham | -0.188 |
brim | -0.186 |
Token | name |
Token ID | 3672 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
Row | +0.613 |
row | +0.586 |
Legs | +0.585 |
Rodham | +0.574 |
Guer | +0.570 |
Neg logit contributions | |
uphem | -0.556 |
abwe | -0.528 |
avail | -0.522 |
ipeg | -0.520 |
ortmund | -0.487 |
Token | }} |
Token ID | 34949 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
Row | +1.771 |
row | +1.705 |
Legs | +1.681 |
Rodham | +1.650 |
chest | +1.640 |
Neg logit contributions | |
uphem | -1.827 |
abwe | -1.731 |
avail | -1.717 |
ipeg | -1.715 |
ortmund | -1.628 |
Token | < |
Token ID | 1279 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Row | +1.853 |
row | +1.767 |
Legs | +1.728 |
Rodham | +1.684 |
Guer | +1.673 |
Neg logit contributions | |
uphem | -2.622 |
abwe | -2.528 |
ipeg | -2.494 |
avail | -2.472 |
ortmund | -2.381 |
Token | p |
Token ID | 79 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
Row | +0.899 |
row | +0.866 |
Legs | +0.862 |
Rodham | +0.854 |
chest | +0.848 |
Neg logit contributions | |
uphem | -0.609 |
ipeg | -0.568 |
abwe | -0.564 |
avail | -0.564 |
ortmund | -0.519 |
Token | > |
Token ID | 29 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
uphem | +0.135 |
avail | +0.131 |
abwe | +0.130 |
ipeg | +0.129 |
ortmund | +0.123 |
Neg logit contributions | |
Row | -0.074 |
Legs | -0.069 |
row | -0.068 |
Rodham | -0.067 |
chest | -0.066 |
Token | {{ |
Token ID | 27007 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Row | +0.179 |
row | +0.173 |
Legs | +0.170 |
Rodham | +0.167 |
brim | +0.166 |
Neg logit contributions | |
uphem | -0.199 |
abwe | -0.189 |
ipeg | -0.188 |
avail | -0.187 |
ortmund | -0.176 |
Token | phone |
Token ID | 3072 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
Row | +3.943 |
row | +3.820 |
Legs | +3.739 |
Rodham | +3.676 |
chest | +3.665 |
Neg logit contributions | |
uphem | -2.992 |
abwe | -2.875 |
ipeg | -2.800 |
avail | -2.741 |
ortmund | -2.643 |
Token | . |
Token ID | 13 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
Row | +1.359 |
row | +1.286 |
Legs | +1.245 |
Rodham | +1.205 |
Guer | +1.201 |
Neg logit contributions | |
uphem | -2.603 |
abwe | -2.539 |
ipeg | -2.505 |
avail | -2.473 |
ortmund | -2.405 |
Token | sn |
Token ID | 16184 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
Row | +0.266 |
Legs | +0.252 |
row | +0.251 |
Rodham | +0.247 |
Guer | +0.246 |
Neg logit contributions | |
uphem | -0.266 |
abwe | -0.252 |
ipeg | -0.249 |
avail | -0.249 |
ortmund | -0.233 |
Token | ipp |
Token ID | 3974 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
Row | +0.165 |
Legs | +0.160 |
row | +0.157 |
Rodham | +0.156 |
Guer | +0.155 |
Neg logit contributions | |
uphem | -0.173 |
ipeg | -0.163 |
abwe | -0.161 |
avail | -0.161 |
ortmund | -0.153 |
Token | et |
Token ID | 316 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Row | +0.185 |
Legs | +0.175 |
row | +0.173 |
Rodham | +0.169 |
Guer | +0.168 |
Neg logit contributions | |
uphem | -0.294 |
ipeg | -0.282 |
avail | -0.281 |
abwe | -0.280 |
ancies | -0.267 |
Token | f |
Token ID | 277 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
uphem | +0.063 |
avail | +0.061 |
abwe | +0.060 |
ipeg | +0.060 |
ancies | +0.057 |
Neg logit contributions | |
Row | -0.041 |
row | -0.039 |
Rodham | -0.038 |
Legs | -0.038 |
Guer | -0.037 |
Token | rit |
Token ID | 799 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
uphem | +0.412 |
ipeg | +0.396 |
abwe | +0.390 |
avail | +0.386 |
ancies | +0.381 |
Neg logit contributions | |
Row | -0.245 |
Legs | -0.231 |
Rodham | -0.224 |
Guer | -0.220 |
row | -0.219 |
Token | ters |
Token ID | 1010 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Row | +0.520 |
row | +0.489 |
Legs | +0.481 |
Rodham | +0.475 |
Guer | +0.473 |
Neg logit contributions | |
uphem | -0.792 |
abwe | -0.761 |
ipeg | -0.757 |
avail | -0.751 |
ortmund | -0.723 |
Token | on |
Token ID | 319 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Row | +0.312 |
row | +0.296 |
Legs | +0.289 |
Rodham | +0.288 |
Guer | +0.285 |
Neg logit contributions | |
uphem | -0.467 |
avail | -0.452 |
abwe | -0.450 |
ipeg | -0.448 |
ancies | -0.424 |
Token | each |
Token ID | 1123 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Row | +0.725 |
row | +0.697 |
Legs | +0.683 |
Rodham | +0.677 |
chest | +0.672 |
Neg logit contributions | |
uphem | -0.826 |
abwe | -0.788 |
ipeg | -0.780 |
avail | -0.779 |
ortmund | -0.735 |
Token | side |
Token ID | 1735 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
uphem | +0.832 |
avail | +0.812 |
abwe | +0.800 |
ipeg | +0.797 |
successful | +0.756 |
Neg logit contributions | |
Row | -0.453 |
Rodham | -0.432 |
Legs | -0.428 |
Guer | -0.425 |
row | -0.425 |
Token | for |
Token ID | 329 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
Row | +2.541 |
row | +2.411 |
Legs | +2.349 |
Rodham | +2.282 |
chest | +2.269 |
Neg logit contributions | |
uphem | -4.409 |
abwe | -4.257 |
ipeg | -4.208 |
avail | -4.177 |
ortmund | -4.030 |
Token | about |
Token ID | 546 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Row | +0.805 |
row | +0.774 |
Legs | +0.760 |
Rodham | +0.748 |
Guer | +0.742 |
Neg logit contributions | |
uphem | -0.978 |
abwe | -0.933 |
avail | -0.931 |
ipeg | -0.922 |
ortmund | -0.877 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Row | +0.726 |
row | +0.698 |
Legs | +0.684 |
Rodham | +0.676 |
Guer | +0.672 |
Neg logit contributions | |
uphem | -0.900 |
avail | -0.861 |
abwe | -0.858 |
ipeg | -0.848 |
ortmund | -0.806 |
Token | / |
Token ID | 14 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
Row | +0.360 |
row | +0.349 |
Legs | +0.345 |
Rodham | +0.342 |
Guer | +0.341 |
Neg logit contributions | |
uphem | -0.230 |
abwe | -0.215 |
avail | -0.215 |
ipeg | -0.212 |
ortmund | -0.196 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Row | +0.140 |
Legs | +0.134 |
Rodham | +0.131 |
Guer | +0.130 |
row | +0.129 |
Neg logit contributions | |
uphem | -0.210 |
abwe | -0.202 |
ipeg | -0.201 |
avail | -0.200 |
ortmund | -0.192 |
Token | Don |
Token ID | 2094 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
Row | +1.858 |
row | +1.796 |
Legs | +1.738 |
Rodham | +1.708 |
chest | +1.701 |
Neg logit contributions | |
uphem | -2.649 |
abwe | -2.533 |
avail | -2.508 |
ipeg | -2.505 |
ortmund | -2.396 |
Token | � |
Token ID | 447 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
Row | +0.613 |
row | +0.587 |
Legs | +0.572 |
Rodham | +0.563 |
chest | +0.560 |
Neg logit contributions | |
uphem | -0.964 |
avail | -0.918 |
abwe | -0.915 |
ipeg | -0.915 |
ortmund | -0.877 |
Token | � |
Token ID | 247 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Row | +1.049 |
row | +1.000 |
Legs | +0.988 |
Rodham | +0.962 |
chest | +0.958 |
Neg logit contributions | |
uphem | -1.444 |
abwe | -1.390 |
ipeg | -1.367 |
avail | -1.361 |
ortmund | -1.312 |
Token | t |
Token ID | 83 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Row | +0.568 |
row | +0.542 |
Legs | +0.534 |
Rodham | +0.525 |
Guer | +0.519 |
Neg logit contributions | |
uphem | -0.717 |
abwe | -0.688 |
ipeg | -0.679 |
avail | -0.676 |
ortmund | -0.646 |
Token | Whis |
Token ID | 28424 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Row | +0.529 |
row | +0.515 |
Legs | +0.497 |
chest | +0.491 |
Rodham | +0.490 |
Neg logit contributions | |
uphem | -0.735 |
abwe | -0.701 |
avail | -0.699 |
ipeg | -0.693 |
ortmund | -0.661 |
Token | per |
Token ID | 525 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Row | +0.464 |
Legs | +0.443 |
Rodham | +0.439 |
row | +0.434 |
Guer | +0.429 |
Neg logit contributions | |
uphem | -0.517 |
ipeg | -0.494 |
abwe | -0.493 |
avail | -0.487 |
ortmund | -0.459 |
Token | to |
Token ID | 284 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
Row | +2.731 |
row | +2.570 |
Legs | +2.525 |
Rodham | +2.436 |
Guer | +2.428 |
Neg logit contributions | |
uphem | -4.195 |
abwe | -4.095 |
ipeg | -4.037 |
avail | -3.993 |
ortmund | -3.865 |
Token | the |
Token ID | 262 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Row | +1.046 |
row | +1.009 |
Legs | +0.981 |
Rodham | +0.964 |
chest | +0.961 |
Neg logit contributions | |
uphem | -1.356 |
abwe | -1.296 |
ipeg | -1.279 |
avail | -1.278 |
ortmund | -1.218 |
Token | Ladies |
Token ID | 37401 |
Feature activation | +4.32e-03 |
Pos logit contributions | |
Row | +0.518 |
row | +0.505 |
Legs | +0.483 |
Rodham | +0.479 |
chest | +0.477 |
Neg logit contributions | |
uphem | -0.731 |
abwe | -0.697 |
avail | -0.692 |
ipeg | -0.690 |
ortmund | -0.657 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Row | +0.010 |
row | +0.009 |
Legs | +0.009 |
Rodham | +0.009 |
brim | +0.009 |
Neg logit contributions | |
uphem | -0.015 |
abwe | -0.014 |
avail | -0.014 |
ipeg | -0.014 |
ortmund | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
Row | +0.524 |
row | +0.500 |
Legs | +0.492 |
Guer | +0.479 |
chest | +0.478 |
Neg logit contributions | |
uphem | -0.588 |
abwe | -0.566 |
ipeg | -0.562 |
avail | -0.553 |
ortmund | -0.530 |
Token | a |
Token ID | 257 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
uphem | +0.098 |
abwe | +0.093 |
ipeg | +0.092 |
avail | +0.092 |
ortmund | +0.086 |
Neg logit contributions | |
Row | -0.104 |
row | -0.101 |
Legs | -0.099 |
Rodham | -0.097 |
chest | -0.097 |
Token | piece |
Token ID | 3704 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
Row | +0.501 |
row | +0.485 |
Legs | +0.476 |
Rodham | +0.467 |
chest | +0.466 |
Neg logit contributions | |
uphem | -0.456 |
abwe | -0.432 |
avail | -0.427 |
ipeg | -0.427 |
ortmund | -0.399 |
Token | of |
Token ID | 286 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
uphem | +0.041 |
abwe | +0.039 |
ipeg | +0.039 |
avail | +0.039 |
ortmund | +0.037 |
Neg logit contributions | |
Row | -0.032 |
row | -0.031 |
Legs | -0.030 |
chest | -0.030 |
Rodham | -0.030 |
Token | open |
Token ID | 1280 |
Feature activation | -7.93e-03 |
Pos logit contributions | |
uphem | +0.720 |
avail | +0.686 |
abwe | +0.683 |
ipeg | +0.670 |
ortmund | +0.623 |
Neg logit contributions | |
Row | -0.803 |
row | -0.784 |
Legs | -0.767 |
Rodham | -0.749 |
chest | -0.749 |
Token | - |
Token ID | 12 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
uphem | +0.023 |
avail | +0.021 |
abwe | +0.021 |
ipeg | +0.021 |
ortmund | +0.020 |
Neg logit contributions | |
Row | -0.023 |
row | -0.022 |
Legs | -0.022 |
Rodham | -0.021 |
Guer | -0.021 |
Token | source |
Token ID | 10459 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Row | +0.768 |
row | +0.726 |
Legs | +0.723 |
Rodham | +0.706 |
Guer | +0.703 |
Neg logit contributions | |
uphem | -0.852 |
abwe | -0.810 |
ipeg | -0.803 |
avail | -0.799 |
ortmund | -0.757 |
Token | technology |
Token ID | 3037 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Row | +3.944 |
row | +3.780 |
Legs | +3.742 |
Rodham | +3.694 |
Guer | +3.688 |
Neg logit contributions | |
uphem | -2.969 |
abwe | -2.825 |
ipeg | -2.776 |
avail | -2.668 |
ortmund | -2.625 |
Token | . |
Token ID | 13 |
Feature activation | +2.50e-03 |
Pos logit contributions | |
Row | +0.698 |
row | +0.665 |
Legs | +0.654 |
Rodham | +0.633 |
chest | +0.628 |
Neg logit contributions | |
uphem | -1.114 |
abwe | -1.075 |
avail | -1.063 |
ipeg | -1.057 |
ortmund | -1.008 |
Token | While |
Token ID | 2893 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
Row | +0.006 |
row | +0.006 |
Legs | +0.006 |
Rodham | +0.006 |
chest | +0.006 |
Neg logit contributions | |
uphem | -0.008 |
abwe | -0.007 |
avail | -0.007 |
ipeg | -0.007 |
ortmund | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | -7.08e-04 |
Pos logit contributions | |
uphem | +0.008 |
avail | +0.008 |
abwe | +0.008 |
ipeg | +0.008 |
ortmund | +0.007 |
Neg logit contributions | |
Row | -0.007 |
row | -0.007 |
Legs | -0.007 |
Rodham | -0.007 |
chest | -0.007 |
Token | sees |
Token ID | 7224 |
Feature activation | -1.05e-03 |
Pos logit contributions | |
uphem | +0.002 |
avail | +0.002 |
abwe | +0.002 |
ipeg | +0.002 |
ancies | +0.002 |
Neg logit contributions | |
Row | -0.002 |
row | -0.002 |
Legs | -0.002 |
Rodham | -0.002 |
chest | -0.002 |
Token | 324 |
Token ID | 38595 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
uphem | +0.630 |
abwe | +0.608 |
ipeg | +0.602 |
avail | +0.600 |
ortmund | +0.570 |
Neg logit contributions | |
Row | -0.551 |
row | -0.534 |
Legs | -0.521 |
chest | -0.513 |
Rodham | -0.509 |
Token | . |
Token ID | 764 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Row | +0.052 |
row | +0.050 |
Legs | +0.048 |
chest | +0.047 |
Rodham | +0.047 |
Neg logit contributions | |
uphem | -0.101 |
abwe | -0.098 |
ipeg | -0.096 |
avail | -0.096 |
ortmund | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
uphem | +2.380 |
avail | +2.336 |
ipeg | +2.208 |
abwe | +2.205 |
Trojan | +2.105 |
Neg logit contributions | |
Row | -3.123 |
row | -3.107 |
chest | -3.075 |
brim | -3.055 |
Legs | -3.009 |
Token |
|
Token ID | 198 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
uphem | +0.069 |
avail | +0.065 |
ipeg | +0.065 |
abwe | +0.063 |
ortmund | +0.062 |
Neg logit contributions | |
Row | -0.080 |
brim | -0.078 |
row | -0.078 |
Legs | -0.077 |
Rodham | -0.076 |
Token | Google |
Token ID | 11708 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Row | +0.200 |
Legs | +0.190 |
row | +0.189 |
Rodham | +0.183 |
brim | +0.183 |
Neg logit contributions | |
uphem | -0.267 |
abwe | -0.254 |
ipeg | -0.253 |
avail | -0.251 |
ortmund | -0.241 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Row | +0.298 |
row | +0.290 |
Legs | +0.281 |
chest | +0.279 |
brim | +0.272 |
Neg logit contributions | |
uphem | -0.460 |
abwe | -0.440 |
avail | -0.439 |
ipeg | -0.435 |
ortmund | -0.418 |
Token | Crossref |
Token ID | 23613 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
uphem | +4.294 |
ipeg | +4.050 |
avail | +4.046 |
abwe | +3.988 |
ancies | +3.799 |
Neg logit contributions | |
Row | -3.571 |
row | -3.545 |
chest | -3.496 |
brim | -3.440 |
Legs | -3.419 |
Token |
|
Token ID | 198 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
uphem | +1.201 |
abwe | +1.163 |
ipeg | +1.150 |
avail | +1.142 |
ortmund | +1.103 |
Neg logit contributions | |
Row | -0.608 |
row | -0.575 |
Legs | -0.559 |
Rodham | -0.542 |
Guer | -0.538 |
Token |
|
Token ID | 198 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
Row | +0.083 |
row | +0.080 |
Legs | +0.079 |
brim | +0.078 |
Rodham | +0.077 |
Neg logit contributions | |
uphem | -0.074 |
avail | -0.070 |
ipeg | -0.070 |
abwe | -0.068 |
ortmund | -0.065 |
Token | M |
Token ID | 44 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Row | +0.106 |
Legs | +0.099 |
row | +0.099 |
brim | +0.096 |
Rodham | +0.096 |
Neg logit contributions | |
uphem | -0.159 |
ipeg | -0.151 |
abwe | -0.151 |
avail | -0.150 |
ortmund | -0.144 |
Token | asure |
Token ID | 5015 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
Row | +0.521 |
Legs | +0.496 |
row | +0.496 |
Rodham | +0.482 |
chest | +0.481 |
Neg logit contributions | |
uphem | -0.545 |
abwe | -0.522 |
ipeg | -0.512 |
avail | -0.505 |
ortmund | -0.485 |
Token | ho |
Token ID | 8873 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
uphem | +1.767 |
ipeg | +1.725 |
abwe | +1.700 |
avail | +1.669 |
agna | +1.622 |
Neg logit contributions | |
Row | -0.918 |
Rodham | -0.841 |
brim | -0.828 |
Legs | -0.818 |
row | -0.811 |
Token | arse |
Token ID | 17208 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
uphem | +0.077 |
abwe | +0.073 |
ipeg | +0.072 |
avail | +0.072 |
ortmund | +0.068 |
Neg logit contributions | |
Row | -0.061 |
row | -0.058 |
Legs | -0.057 |
Rodham | -0.057 |
chest | -0.056 |
Token | wrote |
Token ID | 2630 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Row | +0.499 |
row | +0.472 |
Legs | +0.459 |
Rodham | +0.446 |
chest | +0.443 |
Neg logit contributions | |
uphem | -0.922 |
abwe | -0.891 |
ipeg | -0.881 |
avail | -0.876 |
ortmund | -0.845 |
Token | : |
Token ID | 25 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
uphem | +3.249 |
avail | +3.189 |
ipeg | +3.101 |
ifications | +2.984 |
successful | +2.970 |
Neg logit contributions | |
Seym | -3.160 |
brim | -3.148 |
Row | -3.109 |
Legs | -3.062 |
Rodham | -3.030 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
uphem | +2.098 |
avail | +2.002 |
ipeg | +1.950 |
abwe | +1.838 |
successful | +1.831 |
Neg logit contributions | |
Row | -2.723 |
brim | -2.681 |
row | -2.643 |
Legs | -2.630 |
Rodham | -2.617 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
uphem | +2.878 |
avail | +2.836 |
ipeg | +2.698 |
successful | +2.562 |
Trojan | +2.533 |
Neg logit contributions | |
brim | -4.298 |
Row | -4.279 |
Seym | -4.272 |
row | -4.182 |
Legs | -4.182 |
Token | Show |
Token ID | 15307 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
uphem | +3.678 |
ipeg | +3.451 |
avail | +3.409 |
abwe | +3.379 |
successful | +3.277 |
Neg logit contributions | |
Row | -4.009 |
Legs | -3.803 |
Guer | -3.793 |
Rodham | -3.789 |
brim | -3.729 |
Token | nested |
Token ID | 28376 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
uphem | +2.463 |
avail | +2.337 |
abwe | +2.322 |
ipeg | +2.315 |
successful | +2.224 |
Neg logit contributions | |
Row | -1.953 |
Legs | -1.875 |
row | -1.846 |
chest | -1.839 |
Rodham | -1.836 |
Token | quote |
Token ID | 9577 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
uphem | +1.697 |
avail | +1.650 |
abwe | +1.621 |
ipeg | +1.617 |
successful | +1.535 |
Neg logit contributions | |
Row | -1.109 |
row | -1.045 |
chest | -1.045 |
Legs | -1.041 |
Rodham | -1.030 |
Token | + |
Token ID | 1343 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
uphem | +1.626 |
avail | +1.600 |
abwe | +1.571 |
ipeg | +1.540 |
ancies | +1.491 |
Neg logit contributions | |
Row | -1.181 |
row | -1.114 |
Legs | -1.111 |
chest | -1.092 |
Guer | -1.080 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
uphem | +1.226 |
avail | +1.169 |
ipeg | +1.135 |
abwe | +1.100 |
ortmund | +1.072 |
Neg logit contributions | |
Row | -1.487 |
row | -1.453 |
brim | -1.451 |
Legs | -1.444 |
chest | -1.404 |
Token | � |
Token ID | 247 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
uphem | +0.378 |
abwe | +0.364 |
avail | +0.360 |
ipeg | +0.358 |
ortmund | +0.343 |
Neg logit contributions | |
Row | -0.228 |
row | -0.220 |
Legs | -0.216 |
chest | -0.214 |
Rodham | -0.210 |
Token | s |
Token ID | 82 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Row | +0.208 |
row | +0.199 |
Legs | +0.196 |
Rodham | +0.193 |
chest | +0.190 |
Neg logit contributions | |
uphem | -0.295 |
abwe | -0.285 |
ipeg | -0.282 |
avail | -0.280 |
ortmund | -0.268 |
Token | Gar |
Token ID | 7164 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
uphem | +0.330 |
abwe | +0.317 |
avail | +0.315 |
ipeg | +0.311 |
ortmund | +0.297 |
Neg logit contributions | |
Row | -0.271 |
row | -0.264 |
Legs | -0.259 |
chest | -0.255 |
Rodham | -0.255 |
Token | hi |
Token ID | 5303 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
uphem | +0.347 |
abwe | +0.334 |
ipeg | +0.329 |
avail | +0.325 |
ortmund | +0.308 |
Neg logit contributions | |
Row | -0.324 |
row | -0.308 |
Legs | -0.306 |
Rodham | -0.303 |
Guer | -0.298 |
Token | H |
Token ID | 367 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
Row | +0.385 |
row | +0.369 |
Legs | +0.365 |
Rodham | +0.359 |
chest | +0.357 |
Neg logit contributions | |
uphem | -0.450 |
abwe | -0.434 |
ipeg | -0.428 |
avail | -0.425 |
ortmund | -0.405 |
Token | ars |
Token ID | 945 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Row | +0.287 |
row | +0.276 |
Legs | +0.273 |
Rodham | +0.267 |
chest | +0.266 |
Neg logit contributions | |
uphem | -0.267 |
abwe | -0.255 |
ipeg | -0.251 |
avail | -0.248 |
ortmund | -0.236 |
Token | aru |
Token ID | 11493 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
uphem | +4.267 |
abwe | +4.215 |
ipeg | +4.128 |
avail | +4.072 |
agna | +3.856 |
Neg logit contributions | |
Row | -3.329 |
Legs | -3.151 |
Rodham | -3.110 |
row | -3.040 |
brim | -3.033 |
Token | Junction |
Token ID | 44410 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
Row | +0.537 |
row | +0.515 |
Legs | +0.509 |
Rodham | +0.500 |
chest | +0.497 |
Neg logit contributions | |
uphem | -0.604 |
abwe | -0.582 |
ipeg | -0.573 |
avail | -0.569 |
ortmund | -0.542 |
Token | . |
Token ID | 13 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
uphem | +2.498 |
abwe | +2.425 |
avail | +2.414 |
ipeg | +2.377 |
ortmund | +2.282 |
Neg logit contributions | |
Row | -1.835 |
row | -1.769 |
Legs | -1.766 |
Rodham | -1.736 |
chest | -1.727 |
Token | The |
Token ID | 383 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
uphem | +1.308 |
abwe | +1.247 |
avail | +1.246 |
ipeg | +1.239 |
ortmund | +1.184 |
Neg logit contributions | |
Row | -1.034 |
row | -1.018 |
Legs | -0.981 |
brim | -0.978 |
chest | -0.975 |
Token | train |
Token ID | 4512 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
uphem | +0.721 |
abwe | +0.685 |
avail | +0.682 |
ipeg | +0.674 |
ortmund | +0.637 |
Neg logit contributions | |
Row | -0.734 |
row | -0.717 |
Legs | -0.702 |
chest | -0.696 |
Rodham | -0.691 |
Token | in |
Token ID | 287 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
Row | +0.207 |
row | +0.194 |
Legs | +0.189 |
Rodham | +0.184 |
Guer | +0.182 |
Neg logit contributions | |
uphem | -0.407 |
abwe | -0.394 |
ipeg | -0.390 |
avail | -0.385 |
ortmund | -0.373 |
Token | American |
Token ID | 1605 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
uphem | +1.022 |
avail | +0.969 |
ipeg | +0.969 |
abwe | +0.948 |
ortmund | +0.921 |
Neg logit contributions | |
Row | -0.957 |
row | -0.934 |
Legs | -0.902 |
Rodham | -0.888 |
Guer | -0.888 |
Token | politics |
Token ID | 4819 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
uphem | +0.800 |
ipeg | +0.754 |
avail | +0.750 |
abwe | +0.749 |
ortmund | +0.716 |
Neg logit contributions | |
Row | -0.706 |
row | -0.676 |
Rodham | -0.651 |
Guer | -0.650 |
Legs | -0.648 |
Token | ' |
Token ID | 6 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
uphem | +0.453 |
abwe | +0.436 |
avail | +0.434 |
ipeg | +0.432 |
ortmund | +0.420 |
Neg logit contributions | |
Row | -0.276 |
Legs | -0.260 |
row | -0.259 |
chest | -0.250 |
brim | -0.248 |
Token | MORE |
Token ID | 12011 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Row | +0.108 |
row | +0.100 |
Legs | +0.094 |
chest | +0.088 |
brim | +0.087 |
Neg logit contributions | |
uphem | -0.429 |
abwe | -0.416 |
ipeg | -0.414 |
avail | -0.414 |
ortmund | -0.399 |
Token | completed |
Token ID | 5668 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
uphem | +2.970 |
avail | +2.893 |
ipeg | +2.835 |
abwe | +2.799 |
ancies | +2.633 |
Neg logit contributions | |
Row | -2.770 |
Legs | -2.699 |
row | -2.691 |
chest | -2.644 |
Guer | -2.553 |
Token | a |
Token ID | 257 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
uphem | +3.726 |
avail | +3.653 |
ipeg | +3.559 |
abwe | +3.538 |
successful | +3.319 |
Neg logit contributions | |
Row | -3.612 |
row | -3.575 |
Legs | -3.538 |
chest | -3.478 |
Guer | -3.417 |
Token | swing |
Token ID | 9628 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
uphem | +0.947 |
avail | +0.921 |
abwe | +0.909 |
ipeg | +0.905 |
ortmund | +0.850 |
Neg logit contributions | |
Row | -0.804 |
row | -0.786 |
Legs | -0.769 |
chest | -0.755 |
Guer | -0.744 |
Token | through |
Token ID | 832 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
uphem | +1.223 |
avail | +1.162 |
abwe | +1.160 |
ipeg | +1.158 |
ortmund | +1.087 |
Neg logit contributions | |
Row | -0.901 |
Legs | -0.866 |
row | -0.859 |
Rodham | -0.836 |
Guer | -0.835 |
Token | North |
Token ID | 2258 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
uphem | +0.720 |
abwe | +0.695 |
avail | +0.690 |
ipeg | +0.687 |
ortmund | +0.653 |
Neg logit contributions | |
Row | -0.415 |
row | -0.401 |
Legs | -0.395 |
chest | -0.382 |
Rodham | -0.376 |
Token | Carolina |
Token ID | 5913 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
Row | +0.449 |
row | +0.424 |
Legs | +0.414 |
Rodham | +0.400 |
Guer | +0.395 |
Neg logit contributions | |
uphem | -1.019 |
abwe | -0.985 |
ipeg | -0.978 |
avail | -0.970 |
ortmund | -0.937 |
Token | Se |
Token ID | 1001 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
uphem | +0.146 |
abwe | +0.140 |
avail | +0.139 |
ipeg | +0.138 |
ortmund | +0.132 |
Neg logit contributions | |
Row | -0.100 |
row | -0.096 |
Legs | -0.093 |
Rodham | -0.093 |
chest | -0.092 |
Token | eker |
Token ID | 28233 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
uphem | +0.163 |
abwe | +0.155 |
ipeg | +0.154 |
avail | +0.151 |
ortmund | +0.145 |
Neg logit contributions | |
Row | -0.131 |
Legs | -0.124 |
row | -0.123 |
Rodham | -0.122 |
Guer | -0.120 |
Token | wrote |
Token ID | 2630 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Row | +0.654 |
row | +0.621 |
Legs | +0.612 |
Rodham | +0.601 |
chest | +0.593 |
Neg logit contributions | |
uphem | -0.976 |
abwe | -0.943 |
ipeg | -0.931 |
avail | -0.921 |
ortmund | -0.888 |
Token | : |
Token ID | 25 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
uphem | +3.028 |
avail | +2.945 |
ipeg | +2.880 |
successful | +2.754 |
ifications | +2.754 |
Neg logit contributions | |
brim | -2.792 |
Row | -2.771 |
Seym | -2.761 |
Legs | -2.725 |
Rodham | -2.708 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
uphem | +2.203 |
avail | +2.101 |
ipeg | +2.043 |
abwe | +1.934 |
successful | +1.914 |
Neg logit contributions | |
Row | -2.800 |
brim | -2.739 |
row | -2.725 |
Legs | -2.704 |
Rodham | -2.691 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
uphem | +2.865 |
avail | +2.809 |
ipeg | +2.689 |
successful | +2.560 |
ifications | +2.517 |
Neg logit contributions | |
Row | -4.182 |
brim | -4.178 |
Seym | -4.139 |
Legs | -4.088 |
row | -4.066 |
Token | Cl |
Token ID | 2601 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
uphem | +3.682 |
ipeg | +3.428 |
abwe | +3.406 |
avail | +3.395 |
successful | +3.313 |
Neg logit contributions | |
Row | -3.924 |
Legs | -3.732 |
Guer | -3.675 |
Rodham | -3.675 |
brim | -3.637 |
Token | arity |
Token ID | 6806 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
uphem | +1.038 |
abwe | +0.993 |
ipeg | +0.975 |
avail | +0.959 |
ancies | +0.915 |
Neg logit contributions | |
Row | -1.107 |
Legs | -1.062 |
row | -1.048 |
Rodham | -1.045 |
Guer | -1.037 |
Token | Gaming |
Token ID | 14426 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
Row | +0.580 |
row | +0.557 |
Legs | +0.547 |
Rodham | +0.541 |
chest | +0.537 |
Neg logit contributions | |
uphem | -0.738 |
abwe | -0.713 |
avail | -0.702 |
ipeg | -0.701 |
ortmund | -0.668 |
Token | will |
Token ID | 481 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
Row | +2.016 |
row | +1.935 |
Legs | +1.896 |
Rodham | +1.856 |
chest | +1.848 |
Neg logit contributions | |
uphem | -2.380 |
abwe | -2.284 |
ipeg | -2.253 |
avail | -2.241 |
ortmund | -2.142 |
Token | also |
Token ID | 635 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
uphem | +0.040 |
avail | +0.039 |
abwe | +0.039 |
ipeg | +0.038 |
ortmund | +0.036 |
Neg logit contributions | |
Row | -0.039 |
row | -0.038 |
Legs | -0.037 |
Rodham | -0.036 |
chest | -0.036 |
Token | Dark |
Token ID | 3801 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Row | +0.004 |
row | +0.003 |
Rodham | +0.003 |
Legs | +0.003 |
chest | +0.003 |
Neg logit contributions | |
uphem | -0.005 |
abwe | -0.004 |
avail | -0.004 |
ipeg | -0.004 |
ortmund | -0.004 |
Token | ho |
Token ID | 8873 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
uphem | +1.767 |
ipeg | +1.725 |
abwe | +1.700 |
avail | +1.669 |
agna | +1.622 |
Neg logit contributions | |
Row | -0.918 |
Rodham | -0.841 |
brim | -0.828 |
Legs | -0.818 |
row | -0.811 |
Token | arse |
Token ID | 17208 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
uphem | +0.077 |
abwe | +0.073 |
ipeg | +0.072 |
avail | +0.072 |
ortmund | +0.068 |
Neg logit contributions | |
Row | -0.061 |
row | -0.058 |
Legs | -0.057 |
Rodham | -0.057 |
chest | -0.056 |
Token | wrote |
Token ID | 2630 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Row | +0.499 |
row | +0.472 |
Legs | +0.459 |
Rodham | +0.446 |
chest | +0.443 |
Neg logit contributions | |
uphem | -0.922 |
abwe | -0.891 |
ipeg | -0.881 |
avail | -0.876 |
ortmund | -0.845 |
Token | : |
Token ID | 25 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
uphem | +3.249 |
avail | +3.189 |
ipeg | +3.101 |
ifications | +2.984 |
successful | +2.970 |
Neg logit contributions | |
Seym | -3.160 |
brim | -3.148 |
Row | -3.109 |
Legs | -3.062 |
Rodham | -3.030 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
uphem | +2.098 |
avail | +2.002 |
ipeg | +1.950 |
abwe | +1.838 |
successful | +1.831 |
Neg logit contributions | |
Row | -2.723 |
brim | -2.681 |
row | -2.643 |
Legs | -2.630 |
Rodham | -2.617 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
uphem | +2.878 |
avail | +2.836 |
ipeg | +2.698 |
successful | +2.562 |
Trojan | +2.533 |
Neg logit contributions | |
brim | -4.298 |
Row | -4.279 |
Seym | -4.272 |
row | -4.182 |
Legs | -4.182 |
Token | Show |
Token ID | 15307 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
uphem | +3.678 |
ipeg | +3.451 |
avail | +3.409 |
abwe | +3.379 |
successful | +3.277 |
Neg logit contributions | |
Row | -4.009 |
Legs | -3.803 |
Guer | -3.793 |
Rodham | -3.789 |
brim | -3.729 |
Token | nested |
Token ID | 28376 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
uphem | +2.463 |
avail | +2.337 |
abwe | +2.322 |
ipeg | +2.315 |
successful | +2.224 |
Neg logit contributions | |
Row | -1.953 |
Legs | -1.875 |
row | -1.846 |
chest | -1.839 |
Rodham | -1.836 |
Token | quote |
Token ID | 9577 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
uphem | +1.697 |
avail | +1.650 |
abwe | +1.621 |
ipeg | +1.617 |
successful | +1.535 |
Neg logit contributions | |
Row | -1.109 |
row | -1.045 |
chest | -1.045 |
Legs | -1.041 |
Rodham | -1.030 |
Token | + |
Token ID | 1343 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
uphem | +1.626 |
avail | +1.600 |
abwe | +1.571 |
ipeg | +1.540 |
ancies | +1.491 |
Neg logit contributions | |
Row | -1.181 |
row | -1.114 |
Legs | -1.111 |
chest | -1.092 |
Guer | -1.080 |
Token | ak |
Token ID | 461 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
uphem | +0.533 |
abwe | +0.507 |
ipeg | +0.504 |
avail | +0.502 |
ortmund | +0.479 |
Neg logit contributions | |
Row | -0.436 |
row | -0.413 |
Legs | -0.412 |
Rodham | -0.403 |
Guer | -0.401 |
Token | ushi |
Token ID | 17731 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
Row | +0.755 |
row | +0.712 |
Legs | +0.690 |
Rodham | +0.666 |
chest | +0.665 |
Neg logit contributions | |
uphem | -1.634 |
abwe | -1.585 |
ipeg | -1.567 |
avail | -1.558 |
ortmund | -1.505 |
Token | wrote |
Token ID | 2630 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
Row | +0.041 |
row | +0.039 |
Legs | +0.038 |
Rodham | +0.037 |
chest | +0.036 |
Neg logit contributions | |
uphem | -0.074 |
abwe | -0.072 |
ipeg | -0.071 |
avail | -0.071 |
ortmund | -0.068 |
Token | : |
Token ID | 25 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
uphem | +2.680 |
avail | +2.607 |
ipeg | +2.542 |
successful | +2.437 |
ortmund | +2.435 |
Neg logit contributions | |
Row | -2.322 |
brim | -2.307 |
row | -2.283 |
Legs | -2.258 |
Rodham | -2.254 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
uphem | +1.991 |
avail | +1.896 |
ipeg | +1.840 |
abwe | +1.755 |
successful | +1.734 |
Neg logit contributions | |
Row | -2.503 |
brim | -2.458 |
row | -2.446 |
Rodham | -2.425 |
Legs | -2.415 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
uphem | +2.832 |
avail | +2.753 |
ipeg | +2.646 |
successful | +2.510 |
Trojan | +2.474 |
Neg logit contributions | |
brim | -4.014 |
Row | -3.993 |
Seym | -3.906 |
row | -3.904 |
Legs | -3.885 |
Token | Happy |
Token ID | 25082 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
uphem | +2.811 |
ipeg | +2.627 |
avail | +2.561 |
abwe | +2.465 |
successful | +2.463 |
Neg logit contributions | |
Row | -4.652 |
Legs | -4.465 |
Rodham | -4.457 |
brim | -4.418 |
Guer | -4.394 |
Token | it |
Token ID | 340 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
uphem | +0.885 |
avail | +0.861 |
ipeg | +0.844 |
abwe | +0.821 |
ortmund | +0.791 |
Neg logit contributions | |
Row | -0.771 |
row | -0.762 |
Legs | -0.749 |
Rodham | -0.746 |
chest | -0.728 |
Token | worked |
Token ID | 3111 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Row | +0.081 |
row | +0.077 |
Legs | +0.077 |
Rodham | +0.075 |
chest | +0.075 |
Neg logit contributions | |
uphem | -0.083 |
ipeg | -0.079 |
avail | -0.079 |
abwe | -0.078 |
successful | -0.073 |
Token | out |
Token ID | 503 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
Row | +0.479 |
row | +0.465 |
Legs | +0.459 |
chest | +0.445 |
Rodham | +0.445 |
Neg logit contributions | |
uphem | -0.519 |
avail | -0.503 |
ipeg | -0.493 |
abwe | -0.491 |
ortmund | -0.467 |
Token | . |
Token ID | 13 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Row | +0.069 |
row | +0.066 |
Legs | +0.065 |
Rodham | +0.063 |
brim | +0.063 |
Neg logit contributions | |
uphem | -0.110 |
avail | -0.106 |
ipeg | -0.106 |
abwe | -0.105 |
ortmund | -0.101 |
Token | 44 |
Token ID | 2598 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
Row | +0.176 |
row | +0.168 |
brim | +0.168 |
Legs | +0.166 |
Rodham | +0.166 |
Neg logit contributions | |
uphem | -0.194 |
avail | -0.184 |
ipeg | -0.179 |
abwe | -0.179 |
successful | -0.173 |
Token | Se |
Token ID | 1001 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
uphem | +0.146 |
abwe | +0.140 |
avail | +0.139 |
ipeg | +0.138 |
ortmund | +0.132 |
Neg logit contributions | |
Row | -0.100 |
row | -0.096 |
Legs | -0.093 |
Rodham | -0.093 |
chest | -0.092 |
Token | eker |
Token ID | 28233 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
uphem | +0.163 |
abwe | +0.155 |
ipeg | +0.154 |
avail | +0.151 |
ortmund | +0.145 |
Neg logit contributions | |
Row | -0.131 |
Legs | -0.124 |
row | -0.123 |
Rodham | -0.122 |
Guer | -0.120 |
Token | wrote |
Token ID | 2630 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Row | +0.654 |
row | +0.621 |
Legs | +0.612 |
Rodham | +0.601 |
chest | +0.593 |
Neg logit contributions | |
uphem | -0.976 |
abwe | -0.943 |
ipeg | -0.931 |
avail | -0.921 |
ortmund | -0.888 |
Token | : |
Token ID | 25 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
uphem | +3.028 |
avail | +2.945 |
ipeg | +2.880 |
successful | +2.754 |
ifications | +2.754 |
Neg logit contributions | |
brim | -2.792 |
Row | -2.771 |
Seym | -2.761 |
Legs | -2.725 |
Rodham | -2.708 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
uphem | +2.203 |
avail | +2.101 |
ipeg | +2.043 |
abwe | +1.934 |
successful | +1.914 |
Neg logit contributions | |
Row | -2.800 |
brim | -2.739 |
row | -2.725 |
Legs | -2.704 |
Rodham | -2.691 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
uphem | +2.865 |
avail | +2.809 |
ipeg | +2.689 |
successful | +2.560 |
ifications | +2.517 |
Neg logit contributions | |
Row | -4.182 |
brim | -4.178 |
Seym | -4.139 |
Legs | -4.088 |
row | -4.066 |
Token | Cl |
Token ID | 2601 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
uphem | +3.682 |
ipeg | +3.428 |
abwe | +3.406 |
avail | +3.395 |
successful | +3.313 |
Neg logit contributions | |
Row | -3.924 |
Legs | -3.732 |
Guer | -3.675 |
Rodham | -3.675 |
brim | -3.637 |
Token | arity |
Token ID | 6806 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
uphem | +1.038 |
abwe | +0.993 |
ipeg | +0.975 |
avail | +0.959 |
ancies | +0.915 |
Neg logit contributions | |
Row | -1.107 |
Legs | -1.062 |
row | -1.048 |
Rodham | -1.045 |
Guer | -1.037 |
Token | Gaming |
Token ID | 14426 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
Row | +0.580 |
row | +0.557 |
Legs | +0.547 |
Rodham | +0.541 |
chest | +0.537 |
Neg logit contributions | |
uphem | -0.738 |
abwe | -0.713 |
avail | -0.702 |
ipeg | -0.701 |
ortmund | -0.668 |
Token | will |
Token ID | 481 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
Row | +2.016 |
row | +1.935 |
Legs | +1.896 |
Rodham | +1.856 |
chest | +1.848 |
Neg logit contributions | |
uphem | -2.380 |
abwe | -2.284 |
ipeg | -2.253 |
avail | -2.241 |
ortmund | -2.142 |
Token | United |
Token ID | 1578 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Row | +0.204 |
row | +0.203 |
chest | +0.194 |
Legs | +0.193 |
brim | +0.192 |
Neg logit contributions | |
uphem | -0.291 |
abwe | -0.280 |
ipeg | -0.277 |
avail | -0.277 |
ortmund | -0.266 |
Token | States |
Token ID | 1829 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
uphem | +1.371 |
abwe | +1.340 |
ipeg | +1.302 |
avail | +1.301 |
ortmund | +1.247 |
Neg logit contributions | |
Row | -1.045 |
row | -1.025 |
Legs | -0.977 |
chest | -0.973 |
Rodham | -0.966 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
uphem | +1.524 |
avail | +1.469 |
abwe | +1.464 |
ipeg | +1.453 |
ortmund | +1.385 |
Neg logit contributions | |
row | -1.373 |
Row | -1.362 |
brim | -1.315 |
chest | -1.312 |
Rodham | -1.302 |
Token | 240 |
Token ID | 16102 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
uphem | +0.634 |
abwe | +0.597 |
avail | +0.596 |
ipeg | +0.586 |
ortmund | +0.554 |
Neg logit contributions | |
Row | -0.968 |
row | -0.949 |
Rodham | -0.929 |
Legs | -0.924 |
chest | -0.918 |
Token | Posts |
Token ID | 12043 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
uphem | +0.239 |
avail | +0.215 |
abwe | +0.211 |
ipeg | +0.209 |
ortmund | +0.191 |
Neg logit contributions | |
Row | -0.627 |
row | -0.614 |
Legs | -0.605 |
Rodham | -0.604 |
chest | -0.603 |
Token | # |
Token ID | 1303 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
uphem | +3.723 |
avail | +3.611 |
abwe | +3.576 |
ipeg | +3.534 |
ortmund | +3.429 |
Neg logit contributions | |
Row | -1.941 |
chest | -1.890 |
row | -1.888 |
Rodham | -1.844 |
Legs | -1.828 |
Token | 10 |
Token ID | 940 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
uphem | +3.437 |
avail | +3.284 |
ipeg | +3.202 |
abwe | +3.156 |
successful | +3.151 |
Neg logit contributions | |
Row | -3.464 |
brim | -3.367 |
Rodham | -3.306 |
Legs | -3.267 |
row | -3.265 |
Token | Happy |
Token ID | 14628 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
uphem | +0.066 |
abwe | +0.064 |
avail | +0.063 |
ipeg | +0.063 |
ortmund | +0.060 |
Neg logit contributions | |
Row | -0.053 |
row | -0.051 |
Legs | -0.050 |
Rodham | -0.049 |
chest | -0.049 |
Token | it |
Token ID | 340 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
uphem | +1.086 |
avail | +1.051 |
ipeg | +1.049 |
abwe | +1.045 |
ortmund | +0.990 |
Neg logit contributions | |
Row | -0.766 |
row | -0.751 |
Rodham | -0.733 |
chest | -0.727 |
Legs | -0.724 |
Token | worked |
Token ID | 3111 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Row | +0.049 |
row | +0.046 |
Legs | +0.046 |
Rodham | +0.045 |
chest | +0.044 |
Neg logit contributions | |
uphem | -0.062 |
ipeg | -0.059 |
abwe | -0.059 |
avail | -0.059 |
ortmund | -0.055 |
Token | out |
Token ID | 503 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
Row | +0.343 |
row | +0.332 |
Legs | +0.323 |
Rodham | +0.321 |
chest | +0.319 |
Neg logit contributions | |
uphem | -0.428 |
avail | -0.413 |
abwe | -0.412 |
ipeg | -0.411 |
ortmund | -0.388 |
Token | United |
Token ID | 1578 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
uphem | +0.162 |
abwe | +0.156 |
avail | +0.155 |
ipeg | +0.155 |
ortmund | +0.148 |
Neg logit contributions | |
row | -0.105 |
Row | -0.105 |
chest | -0.100 |
Legs | -0.099 |
brim | -0.098 |
Token | States |
Token ID | 1829 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
uphem | +1.605 |
abwe | +1.554 |
ipeg | +1.527 |
avail | +1.518 |
ortmund | +1.458 |
Neg logit contributions | |
Row | -1.108 |
row | -1.065 |
Legs | -1.033 |
Rodham | -1.010 |
chest | -1.008 |
Token | 5 |
Token ID | 642 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
uphem | +1.765 |
avail | +1.709 |
abwe | +1.696 |
ipeg | +1.685 |
Trojan | +1.597 |
Neg logit contributions | |
row | -1.562 |
Row | -1.557 |
chest | -1.489 |
brim | -1.488 |
Legs | -1.482 |
Token | 667 |
Token ID | 28933 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
uphem | +0.865 |
abwe | +0.822 |
avail | +0.818 |
ipeg | +0.812 |
ortmund | +0.777 |
Neg logit contributions | |
Row | -0.791 |
row | -0.773 |
Legs | -0.748 |
Rodham | -0.748 |
brim | -0.743 |
Token | Posts |
Token ID | 12043 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
Row | +0.300 |
row | +0.297 |
brim | +0.290 |
Legs | +0.289 |
chest | +0.289 |
Neg logit contributions | |
uphem | -0.115 |
avail | -0.104 |
ipeg | -0.102 |
abwe | -0.101 |
ortmund | -0.092 |
Token | # |
Token ID | 1303 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
uphem | +3.689 |
abwe | +3.556 |
avail | +3.537 |
ipeg | +3.516 |
ortmund | +3.398 |
Neg logit contributions | |
Row | -1.753 |
row | -1.689 |
chest | -1.634 |
Legs | -1.625 |
Rodham | -1.613 |
Token | 12 |
Token ID | 1065 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
avail | +2.995 |
uphem | +2.911 |
successful | +2.861 |
ipeg | +2.729 |
availability | +2.656 |
Neg logit contributions | |
brim | -3.842 |
Row | -3.813 |
Legs | -3.667 |
Seym | -3.663 |
Guer | -3.655 |
Token | I |
Token ID | 314 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
uphem | +0.123 |
abwe | +0.118 |
avail | +0.117 |
ipeg | +0.116 |
ortmund | +0.110 |
Neg logit contributions | |
Row | -0.105 |
row | -0.101 |
Legs | -0.098 |
Rodham | -0.097 |
chest | -0.097 |
Token | 'm |
Token ID | 1101 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
uphem | +1.291 |
avail | +1.237 |
abwe | +1.209 |
ipeg | +1.208 |
ortmund | +1.130 |
Neg logit contributions | |
Row | -1.384 |
row | -1.313 |
Legs | -1.298 |
Rodham | -1.294 |
chest | -1.280 |
Token | glad |
Token ID | 9675 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
uphem | +0.693 |
avail | +0.665 |
abwe | +0.661 |
ipeg | +0.650 |
ortmund | +0.608 |
Neg logit contributions | |
Row | -0.705 |
row | -0.681 |
Legs | -0.670 |
Rodham | -0.660 |
chest | -0.655 |
Token | there |
Token ID | 612 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
uphem | +0.493 |
avail | +0.472 |
abwe | +0.472 |
ipeg | +0.467 |
ortmund | +0.442 |
Neg logit contributions | |
Row | -0.399 |
row | -0.385 |
Legs | -0.377 |
Rodham | -0.370 |
chest | -0.366 |
Token | pur |
Token ID | 1308 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Row | +0.643 |
row | +0.618 |
Legs | +0.604 |
Rodham | +0.594 |
chest | +0.589 |
Neg logit contributions | |
uphem | -0.833 |
abwe | -0.801 |
ipeg | -0.790 |
avail | -0.787 |
ortmund | -0.752 |
Token | ak |
Token ID | 461 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
uphem | +0.533 |
abwe | +0.507 |
ipeg | +0.504 |
avail | +0.502 |
ortmund | +0.479 |
Neg logit contributions | |
Row | -0.436 |
row | -0.413 |
Legs | -0.412 |
Rodham | -0.403 |
Guer | -0.401 |
Token | ushi |
Token ID | 17731 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
Row | +0.755 |
row | +0.712 |
Legs | +0.690 |
Rodham | +0.666 |
chest | +0.665 |
Neg logit contributions | |
uphem | -1.634 |
abwe | -1.585 |
ipeg | -1.567 |
avail | -1.558 |
ortmund | -1.505 |
Token | wrote |
Token ID | 2630 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
Row | +0.041 |
row | +0.039 |
Legs | +0.038 |
Rodham | +0.037 |
chest | +0.036 |
Neg logit contributions | |
uphem | -0.074 |
abwe | -0.072 |
ipeg | -0.071 |
avail | -0.071 |
ortmund | -0.068 |
Token | : |
Token ID | 25 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
uphem | +2.680 |
avail | +2.607 |
ipeg | +2.542 |
successful | +2.437 |
ortmund | +2.435 |
Neg logit contributions | |
Row | -2.322 |
brim | -2.307 |
row | -2.283 |
Legs | -2.258 |
Rodham | -2.254 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
uphem | +1.991 |
avail | +1.896 |
ipeg | +1.840 |
abwe | +1.755 |
successful | +1.734 |
Neg logit contributions | |
Row | -2.503 |
brim | -2.458 |
row | -2.446 |
Rodham | -2.425 |
Legs | -2.415 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
uphem | +2.832 |
avail | +2.753 |
ipeg | +2.646 |
successful | +2.510 |
Trojan | +2.474 |
Neg logit contributions | |
brim | -4.014 |
Row | -3.993 |
Seym | -3.906 |
row | -3.904 |
Legs | -3.885 |
Token | Happy |
Token ID | 25082 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
uphem | +2.811 |
ipeg | +2.627 |
avail | +2.561 |
abwe | +2.465 |
successful | +2.463 |
Neg logit contributions | |
Row | -4.652 |
Legs | -4.465 |
Rodham | -4.457 |
brim | -4.418 |
Guer | -4.394 |
Token | it |
Token ID | 340 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
uphem | +0.885 |
avail | +0.861 |
ipeg | +0.844 |
abwe | +0.821 |
ortmund | +0.791 |
Neg logit contributions | |
Row | -0.771 |
row | -0.762 |
Legs | -0.749 |
Rodham | -0.746 |
chest | -0.728 |
Token | worked |
Token ID | 3111 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Row | +0.081 |
row | +0.077 |
Legs | +0.077 |
Rodham | +0.075 |
chest | +0.075 |
Neg logit contributions | |
uphem | -0.083 |
ipeg | -0.079 |
avail | -0.079 |
abwe | -0.078 |
successful | -0.073 |
Token | out |
Token ID | 503 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
Row | +0.479 |
row | +0.465 |
Legs | +0.459 |
chest | +0.445 |
Rodham | +0.445 |
Neg logit contributions | |
uphem | -0.519 |
avail | -0.503 |
ipeg | -0.493 |
abwe | -0.491 |
ortmund | -0.467 |
Token | United |
Token ID | 1578 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
uphem | +0.679 |
abwe | +0.658 |
ipeg | +0.653 |
avail | +0.652 |
ortmund | +0.623 |
Neg logit contributions | |
Row | -0.469 |
row | -0.468 |
chest | -0.448 |
Legs | -0.445 |
brim | -0.442 |
Token | States |
Token ID | 1829 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
uphem | +1.700 |
abwe | +1.645 |
ipeg | +1.617 |
avail | +1.607 |
ortmund | +1.545 |
Neg logit contributions | |
Row | -1.176 |
row | -1.129 |
Legs | -1.096 |
Rodham | -1.072 |
chest | -1.069 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
uphem | +1.968 |
avail | +1.905 |
abwe | +1.889 |
ipeg | +1.880 |
ortmund | +1.780 |
Neg logit contributions | |
row | -1.763 |
Row | -1.759 |
chest | -1.689 |
brim | -1.682 |
Legs | -1.680 |
Token | 53 |
Token ID | 4310 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
uphem | +0.805 |
abwe | +0.765 |
avail | +0.763 |
ipeg | +0.757 |
ortmund | +0.727 |
Neg logit contributions | |
Row | -0.713 |
row | -0.698 |
Legs | -0.672 |
Rodham | -0.672 |
brim | -0.667 |
Token | Posts |
Token ID | 12043 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
uphem | +0.046 |
avail | +0.042 |
ipeg | +0.040 |
abwe | +0.040 |
ortmund | +0.037 |
Neg logit contributions | |
Row | -0.123 |
row | -0.122 |
brim | -0.120 |
Legs | -0.119 |
chest | -0.119 |
Token | # |
Token ID | 1303 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
uphem | +3.728 |
abwe | +3.601 |
avail | +3.580 |
ipeg | +3.555 |
ortmund | +3.431 |
Neg logit contributions | |
Row | -1.738 |
row | -1.675 |
Legs | -1.611 |
chest | -1.604 |
Rodham | -1.590 |
Token | 15 |
Token ID | 1314 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
uphem | +2.901 |
ipeg | +2.842 |
avail | +2.800 |
successful | +2.699 |
availability | +2.544 |
Neg logit contributions | |
Row | -3.888 |
brim | -3.844 |
Seym | -3.759 |
Rodham | -3.717 |
Legs | -3.715 |
Token | honestly |
Token ID | 12698 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
uphem | +0.472 |
abwe | +0.451 |
avail | +0.449 |
ipeg | +0.447 |
ortmund | +0.424 |
Neg logit contributions | |
Row | -0.412 |
row | -0.401 |
Legs | -0.388 |
Rodham | -0.386 |
chest | -0.385 |
Token | if |
Token ID | 611 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
uphem | +0.949 |
abwe | +0.919 |
avail | +0.914 |
ipeg | +0.909 |
ortmund | +0.858 |
Neg logit contributions | |
Row | -0.724 |
row | -0.694 |
Legs | -0.678 |
Rodham | -0.677 |
chest | -0.663 |
Token | we |
Token ID | 356 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
uphem | +1.124 |
abwe | +1.091 |
avail | +1.087 |
ipeg | +1.075 |
ortmund | +1.013 |
Neg logit contributions | |
Row | -0.897 |
row | -0.870 |
Legs | -0.853 |
Rodham | -0.847 |
chest | -0.831 |
Token | just |
Token ID | 655 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
uphem | +0.788 |
avail | +0.763 |
abwe | +0.742 |
ipeg | +0.739 |
ortmund | +0.697 |
Neg logit contributions | |
Row | -0.781 |
row | -0.746 |
Legs | -0.737 |
Rodham | -0.728 |
chest | -0.721 |
Token | . |
Token ID | 13 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
uphem | +0.181 |
abwe | +0.175 |
ipeg | +0.173 |
avail | +0.172 |
ortmund | +0.165 |
Neg logit contributions | |
Row | -0.096 |
row | -0.091 |
Legs | -0.088 |
Rodham | -0.086 |
chest | -0.085 |
Token | C |
Token ID | 327 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
uphem | +0.214 |
avail | +0.204 |
ipeg | +0.204 |
abwe | +0.203 |
ortmund | +0.193 |
Neg logit contributions | |
Row | -0.167 |
row | -0.165 |
brim | -0.159 |
chest | -0.158 |
Legs | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Row | +1.114 |
row | +1.065 |
Legs | +1.009 |
Rodham | +0.970 |
Guer | +0.959 |
Neg logit contributions | |
uphem | -2.369 |
abwe | -2.300 |
avail | -2.284 |
ipeg | -2.265 |
ortmund | -2.188 |
Token | ( |
Token ID | 357 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
Row | +0.240 |
row | +0.232 |
Legs | +0.225 |
chest | +0.221 |
Rodham | +0.221 |
Neg logit contributions | |
uphem | -0.369 |
abwe | -0.354 |
ipeg | -0.352 |
avail | -0.349 |
ortmund | -0.336 |
Token | 1934 |
Token ID | 29300 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
uphem | +0.101 |
avail | +0.097 |
abwe | +0.096 |
ipeg | +0.096 |
ortmund | +0.091 |
Neg logit contributions | |
Row | -0.074 |
row | -0.072 |
Legs | -0.070 |
chest | -0.070 |
brim | -0.069 |
Token | ). |
Token ID | 6739 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
uphem | +0.283 |
abwe | +0.273 |
ipeg | +0.271 |
avail | +0.271 |
ortmund | +0.259 |
Neg logit contributions | |
Row | -0.153 |
row | -0.146 |
Legs | -0.144 |
Rodham | -0.139 |
chest | -0.139 |
Token | The |
Token ID | 383 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
uphem | +3.695 |
abwe | +3.549 |
ipeg | +3.489 |
avail | +3.471 |
Trojan | +3.389 |
Neg logit contributions | |
row | -2.923 |
Row | -2.865 |
brim | -2.816 |
chest | -2.786 |
Rodham | -2.680 |
Token | social |
Token ID | 1919 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
uphem | +0.590 |
abwe | +0.566 |
avail | +0.555 |
ipeg | +0.555 |
ortmund | +0.526 |
Neg logit contributions | |
Row | -0.583 |
row | -0.566 |
Legs | -0.552 |
chest | -0.543 |
Rodham | -0.542 |
Token | order |
Token ID | 1502 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
uphem | +0.042 |
abwe | +0.040 |
avail | +0.040 |
ipeg | +0.040 |
ortmund | +0.037 |
Neg logit contributions | |
Row | -0.047 |
row | -0.045 |
Legs | -0.045 |
chest | -0.044 |
Rodham | -0.044 |
Token | in |
Token ID | 287 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
uphem | +0.840 |
abwe | +0.814 |
avail | +0.802 |
ipeg | +0.797 |
ortmund | +0.763 |
Neg logit contributions | |
Row | -0.554 |
row | -0.525 |
Legs | -0.518 |
chest | -0.501 |
Rodham | -0.499 |
Token | fl |
Token ID | 781 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
Row | +0.463 |
row | +0.447 |
Legs | +0.438 |
chest | +0.429 |
Rodham | +0.428 |
Neg logit contributions | |
uphem | -0.534 |
abwe | -0.514 |
ipeg | -0.505 |
avail | -0.502 |
ortmund | -0.479 |
Token | by |
Token ID | 416 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
Row | +0.645 |
row | +0.618 |
Legs | +0.608 |
Rodham | +0.596 |
chest | +0.591 |
Neg logit contributions | |
uphem | -0.795 |
abwe | -0.765 |
ipeg | -0.753 |
avail | -0.749 |
ortmund | -0.717 |
Token | blocking |
Token ID | 12013 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
uphem | +0.248 |
abwe | +0.237 |
avail | +0.233 |
ipeg | +0.232 |
ortmund | +0.221 |
Neg logit contributions | |
Row | -0.223 |
row | -0.216 |
Legs | -0.211 |
Rodham | -0.209 |
chest | -0.207 |
Token | national |
Token ID | 2260 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
Row | +0.162 |
row | +0.155 |
Legs | +0.152 |
Rodham | +0.148 |
Guer | +0.148 |
Neg logit contributions | |
uphem | -0.189 |
abwe | -0.182 |
ipeg | -0.179 |
avail | -0.177 |
ortmund | -0.170 |
Token | highway |
Token ID | 12763 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
uphem | +2.554 |
avail | +2.429 |
abwe | +2.412 |
ipeg | +2.403 |
ortmund | +2.254 |
Neg logit contributions | |
Row | -2.681 |
row | -2.600 |
Legs | -2.582 |
Rodham | -2.541 |
Guer | -2.505 |
Token | connecting |
Token ID | 14320 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
uphem | +0.293 |
abwe | +0.281 |
avail | +0.279 |
ipeg | +0.277 |
ortmund | +0.265 |
Neg logit contributions | |
Row | -0.210 |
row | -0.202 |
Legs | -0.198 |
Rodham | -0.194 |
chest | -0.194 |
Token | Roh |
Token ID | 32694 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
uphem | +0.981 |
abwe | +0.941 |
avail | +0.940 |
ipeg | +0.931 |
ortmund | +0.885 |
Neg logit contributions | |
Row | -0.767 |
row | -0.749 |
Legs | -0.726 |
Rodham | -0.720 |
chest | -0.717 |
Token | t |
Token ID | 83 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
uphem | +2.919 |
ipeg | +2.777 |
abwe | +2.767 |
avail | +2.637 |
ortmund | +2.554 |
Neg logit contributions | |
Row | -3.849 |
Legs | -3.725 |
Rodham | -3.704 |
row | -3.695 |
brim | -3.654 |
Token | ak |
Token ID | 461 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
uphem | +1.153 |
abwe | +1.099 |
ipeg | +1.095 |
avail | +1.082 |
ortmund | +1.036 |
Neg logit contributions | |
Row | -1.013 |
Legs | -0.963 |
row | -0.954 |
Rodham | -0.947 |
brim | -0.943 |
Token | to |
Token ID | 284 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
uphem | +0.759 |
abwe | +0.735 |
ipeg | +0.725 |
avail | +0.724 |
ortmund | +0.692 |
Neg logit contributions | |
Row | -0.498 |
row | -0.477 |
Legs | -0.469 |
Rodham | -0.463 |
chest | -0.457 |
Token | Delhi |
Token ID | 12517 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
uphem | +1.366 |
avail | +1.320 |
abwe | +1.313 |
ipeg | +1.302 |
ortmund | +1.236 |
Neg logit contributions | |
Row | -1.096 |
row | -1.079 |
Legs | -1.048 |
chest | -1.040 |
Rodham | -1.035 |
Token | . |
Token ID | 13 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
uphem | +1.103 |
abwe | +1.068 |
avail | +1.057 |
ipeg | +1.052 |
ortmund | +1.003 |
Neg logit contributions | |
Row | -0.736 |
row | -0.709 |
Legs | -0.703 |
chest | -0.691 |
Rodham | -0.691 |
Token | 01 |
Token ID | 5534 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Row | +0.334 |
row | +0.329 |
brim | +0.319 |
Legs | +0.317 |
chest | +0.315 |
Neg logit contributions | |
uphem | -0.374 |
avail | -0.363 |
ipeg | -0.354 |
abwe | -0.351 |
ortmund | -0.341 |
Token | : |
Token ID | 25 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
uphem | +0.532 |
avail | +0.517 |
ipeg | +0.505 |
abwe | +0.488 |
ortmund | +0.484 |
Neg logit contributions | |
Row | -0.418 |
brim | -0.404 |
row | -0.401 |
Legs | -0.401 |
Rodham | -0.394 |
Token | 44 |
Token ID | 2598 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
uphem | +1.108 |
avail | +1.065 |
ipeg | +1.024 |
abwe | +1.007 |
successful | +0.996 |
Neg logit contributions | |
Row | -1.034 |
brim | -1.008 |
row | -0.996 |
Legs | -0.992 |
Rodham | -0.984 |
Token | : |
Token ID | 25 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
uphem | +1.750 |
avail | +1.706 |
ipeg | +1.652 |
ortmund | +1.605 |
abwe | +1.591 |
Neg logit contributions | |
Row | -1.435 |
brim | -1.416 |
row | -1.409 |
Legs | -1.363 |
Rodham | -1.361 |
Token | 24 |
Token ID | 1731 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
uphem | +0.852 |
avail | +0.816 |
ipeg | +0.789 |
abwe | +0.780 |
successful | +0.764 |
Neg logit contributions | |
Row | -0.776 |
brim | -0.750 |
row | -0.749 |
Legs | -0.741 |
Rodham | -0.734 |
Token | # |
Token ID | 1303 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
uphem | +2.147 |
avail | +2.130 |
ipeg | +2.062 |
successful | +2.007 |
ortmund | +2.005 |
Neg logit contributions | |
Row | -1.154 |
brim | -1.148 |
row | -1.147 |
Rodham | -1.106 |
chest | -1.071 |
Token | 19 |
Token ID | 1129 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
uphem | +2.977 |
avail | +2.857 |
ipeg | +2.824 |
abwe | +2.686 |
successful | +2.676 |
Neg logit contributions | |
Row | -3.775 |
Legs | -3.631 |
Guer | -3.592 |
brim | -3.576 |
Rodham | -3.573 |
Token | edit |
Token ID | 4370 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
Row | +0.382 |
row | +0.369 |
Legs | +0.360 |
Rodham | +0.355 |
chest | +0.354 |
Neg logit contributions | |
uphem | -0.447 |
abwe | -0.429 |
ipeg | -0.425 |
avail | -0.424 |
ortmund | -0.403 |
Token | , |
Token ID | 11 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
uphem | +2.318 |
avail | +2.249 |
abwe | +2.221 |
ipeg | +2.200 |
ortmund | +2.092 |
Neg logit contributions | |
Row | -1.644 |
row | -1.572 |
Legs | -1.562 |
Rodham | -1.554 |
chest | -1.521 |
Token | n |
Token ID | 299 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
uphem | +0.954 |
abwe | +0.919 |
avail | +0.915 |
ipeg | +0.907 |
ortmund | +0.863 |
Neg logit contributions | |
Row | -0.796 |
row | -0.767 |
Legs | -0.753 |
Rodham | -0.752 |
chest | -0.741 |
Token | vm |
Token ID | 14761 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
uphem | +0.133 |
abwe | +0.127 |
ipeg | +0.125 |
avail | +0.123 |
ortmund | +0.118 |
Neg logit contributions | |
Row | -0.154 |
Legs | -0.147 |
row | -0.147 |
Rodham | -0.146 |
chest | -0.144 |
Token | � |
Token ID | 247 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
uphem | +0.399 |
abwe | +0.372 |
avail | +0.368 |
ipeg | +0.359 |
ortmund | +0.347 |
Neg logit contributions | |
Row | -0.460 |
Legs | -0.447 |
row | -0.443 |
chest | -0.439 |
Rodham | -0.439 |
Token | s |
Token ID | 82 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
Row | +0.614 |
row | +0.587 |
Legs | +0.580 |
Rodham | +0.567 |
Guer | +0.563 |
Neg logit contributions | |
uphem | -0.687 |
abwe | -0.661 |
ipeg | -0.650 |
avail | -0.648 |
ortmund | -0.617 |
Token | agent |
Token ID | 5797 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
uphem | +0.215 |
avail | +0.210 |
abwe | +0.207 |
ipeg | +0.205 |
ortmund | +0.192 |
Neg logit contributions | |
Row | -0.218 |
row | -0.213 |
Legs | -0.208 |
Rodham | -0.205 |
chest | -0.203 |
Token | , |
Token ID | 11 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
Row | +0.111 |
row | +0.107 |
Legs | +0.105 |
chest | +0.102 |
Rodham | +0.101 |
Neg logit contributions | |
uphem | -0.176 |
abwe | -0.170 |
avail | -0.169 |
ipeg | -0.169 |
ortmund | -0.160 |
Token | Scott |
Token ID | 4746 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
uphem | +0.240 |
abwe | +0.233 |
avail | +0.230 |
ipeg | +0.229 |
ortmund | +0.218 |
Neg logit contributions | |
Row | -0.147 |
row | -0.143 |
Legs | -0.139 |
chest | -0.135 |
Rodham | -0.135 |
Token | Bor |
Token ID | 12182 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Row | +0.114 |
row | +0.110 |
Legs | +0.107 |
chest | +0.105 |
Rodham | +0.105 |
Neg logit contributions | |
uphem | -0.155 |
abwe | -0.150 |
ipeg | -0.148 |
avail | -0.146 |
ortmund | -0.140 |
Token | as |
Token ID | 292 |
Feature activation | -3.74e-03 |
Pos logit contributions | |
uphem | +4.476 |
abwe | +4.357 |
ipeg | +4.287 |
avail | +4.175 |
agna | +4.134 |
Neg logit contributions | |
Row | -2.287 |
Legs | -2.199 |
Rodham | -2.143 |
Guer | -2.087 |
brim | -2.030 |
Token | . |
Token ID | 13 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
uphem | +0.013 |
abwe | +0.013 |
ipeg | +0.013 |
avail | +0.013 |
ortmund | +0.012 |
Neg logit contributions | |
Row | -0.008 |
row | -0.007 |
Legs | -0.007 |
Rodham | -0.007 |
chest | -0.007 |
Token | With |
Token ID | 2080 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Row | +0.141 |
row | +0.137 |
Legs | +0.134 |
Rodham | +0.131 |
chest | +0.130 |
Neg logit contributions | |
uphem | -0.162 |
abwe | -0.156 |
ipeg | -0.154 |
avail | -0.153 |
ortmund | -0.146 |
Token | the |
Token ID | 262 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
uphem | +1.284 |
abwe | +1.251 |
avail | +1.244 |
ipeg | +1.235 |
ortmund | +1.164 |
Neg logit contributions | |
Row | -0.990 |
row | -0.971 |
Legs | -0.947 |
chest | -0.933 |
Rodham | -0.930 |
Token | slot |
Token ID | 10852 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
Row | +0.698 |
row | +0.680 |
Legs | +0.665 |
chest | +0.655 |
Rodham | +0.653 |
Neg logit contributions | |
uphem | -0.806 |
abwe | -0.774 |
avail | -0.774 |
ipeg | -0.766 |
ortmund | -0.723 |
Token | 42 |
Token ID | 5433 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
uphem | +1.520 |
avail | +1.510 |
ipeg | +1.451 |
abwe | +1.445 |
Trojan | +1.406 |
Neg logit contributions | |
row | -1.162 |
Row | -1.145 |
chest | -1.096 |
brim | -1.092 |
Legs | -1.088 |
Token | . |
Token ID | 764 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
uphem | +0.140 |
ipeg | +0.135 |
avail | +0.135 |
abwe | +0.132 |
ortmund | +0.129 |
Neg logit contributions | |
Row | -0.052 |
row | -0.050 |
Legs | -0.049 |
brim | -0.049 |
Rodham | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -8.52e-02 |
Pos logit contributions | |
uphem | +1.678 |
avail | +1.588 |
ipeg | +1.555 |
abwe | +1.492 |
ortmund | +1.481 |
Neg logit contributions | |
Row | -2.012 |
row | -2.009 |
brim | -1.983 |
Legs | -1.979 |
chest | -1.967 |
Token |
|
Token ID | 198 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
uphem | +0.224 |
avail | +0.213 |
ipeg | +0.211 |
abwe | +0.205 |
ortmund | +0.198 |
Neg logit contributions | |
Row | -0.255 |
row | -0.247 |
Legs | -0.245 |
brim | -0.243 |
Rodham | -0.240 |
Token | Google |
Token ID | 11708 |
Feature activation | +8.54e-02 |
Pos logit contributions | |
uphem | +0.158 |
abwe | +0.149 |
ipeg | +0.149 |
avail | +0.146 |
ortmund | +0.140 |
Neg logit contributions | |
Row | -0.179 |
row | -0.172 |
Legs | -0.170 |
Rodham | -0.167 |
Guer | -0.166 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Row | +0.196 |
row | +0.196 |
brim | +0.189 |
Legs | +0.189 |
chest | +0.188 |
Neg logit contributions | |
uphem | -0.277 |
avail | -0.268 |
ipeg | -0.265 |
abwe | -0.258 |
ortmund | -0.251 |
Token | Crossref |
Token ID | 23613 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
uphem | +3.747 |
avail | +3.536 |
abwe | +3.521 |
ipeg | +3.510 |
ortmund | +3.320 |
Neg logit contributions | |
Row | -2.937 |
row | -2.870 |
Legs | -2.800 |
chest | -2.784 |
brim | -2.733 |
Token | | |
Token ID | 930 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
uphem | +0.969 |
abwe | +0.936 |
ipeg | +0.925 |
avail | +0.918 |
ortmund | +0.884 |
Neg logit contributions | |
Row | -0.572 |
row | -0.544 |
Legs | -0.529 |
Rodham | -0.516 |
Guer | -0.512 |
Token | ISI |
Token ID | 22048 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
uphem | +0.888 |
avail | +0.838 |
ipeg | +0.814 |
abwe | +0.806 |
ortmund | +0.766 |
Neg logit contributions | |
row | -1.303 |
Row | -1.294 |
chest | -1.275 |
brim | -1.252 |
Legs | -1.244 |
Token |
|
Token ID | 198 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
uphem | +1.755 |
avail | +1.665 |
ipeg | +1.625 |
abwe | +1.623 |
ortmund | +1.544 |
Neg logit contributions | |
Row | -2.070 |
row | -2.044 |
brim | -2.017 |
Legs | -2.015 |
chest | -2.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Row | +0.780 |
row | +0.755 |
Legs | +0.744 |
Rodham | +0.728 |
brim | +0.727 |
Neg logit contributions | |
uphem | -0.743 |
ipeg | -0.701 |
avail | -0.701 |
abwe | -0.697 |
ortmund | -0.662 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
uphem | +0.811 |
avail | +0.787 |
ipeg | +0.776 |
abwe | +0.775 |
ortmund | +0.742 |
Neg logit contributions | |
row | -0.697 |
Row | -0.693 |
brim | -0.670 |
chest | -0.665 |
Legs | -0.662 |
Token | Canada |
Token ID | 3340 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
Row | +0.049 |
row | +0.049 |
chest | +0.047 |
Legs | +0.047 |
Rodham | +0.046 |
Neg logit contributions | |
uphem | -0.075 |
abwe | -0.072 |
ipeg | -0.071 |
avail | -0.071 |
ortmund | -0.068 |
Token | 16 |
Token ID | 1467 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
uphem | +1.375 |
avail | +1.358 |
ipeg | +1.329 |
abwe | +1.320 |
Trojan | +1.271 |
Neg logit contributions | |
row | -1.283 |
Row | -1.262 |
chest | -1.229 |
brim | -1.225 |
Legs | -1.207 |
Token | 10 |
Token ID | 940 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
uphem | +0.667 |
avail | +0.632 |
abwe | +0.631 |
ipeg | +0.623 |
ortmund | +0.601 |
Neg logit contributions | |
Row | -0.596 |
row | -0.586 |
Rodham | -0.563 |
Legs | -0.562 |
brim | -0.560 |
Token | Posts |
Token ID | 12043 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
uphem | +0.133 |
avail | +0.123 |
ipeg | +0.117 |
abwe | +0.115 |
ortmund | +0.108 |
Neg logit contributions | |
Row | -0.352 |
row | -0.351 |
brim | -0.344 |
chest | -0.340 |
Legs | -0.340 |
Token | # |
Token ID | 1303 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
uphem | +3.546 |
abwe | +3.425 |
avail | +3.407 |
ipeg | +3.381 |
ortmund | +3.265 |
Neg logit contributions | |
Row | -1.635 |
row | -1.576 |
Legs | -1.512 |
chest | -1.505 |
Rodham | -1.491 |
Token | 14 |
Token ID | 1415 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
uphem | +3.023 |
avail | +2.974 |
ipeg | +2.897 |
successful | +2.777 |
abwe | +2.730 |
Neg logit contributions | |
Row | -3.614 |
Legs | -3.493 |
Guer | -3.479 |
brim | -3.458 |
Rodham | -3.420 |
Token | On |
Token ID | 1550 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
uphem | +0.835 |
abwe | +0.797 |
avail | +0.796 |
ipeg | +0.791 |
ortmund | +0.749 |
Neg logit contributions | |
Row | -0.718 |
row | -0.700 |
Legs | -0.676 |
Rodham | -0.674 |
chest | -0.674 |
Token | September |
Token ID | 2693 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
uphem | +1.713 |
avail | +1.658 |
ipeg | +1.633 |
abwe | +1.578 |
ortmund | +1.529 |
Neg logit contributions | |
Row | -1.039 |
row | -1.038 |
chest | -1.018 |
Legs | -1.007 |
Rodham | -0.992 |
Token | 20 |
Token ID | 1160 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
Row | +0.865 |
row | +0.823 |
Legs | +0.803 |
Rodham | +0.782 |
Guer | +0.782 |
Neg logit contributions | |
uphem | -1.170 |
abwe | -1.130 |
ipeg | -1.119 |
avail | -1.101 |
ortmund | -1.060 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Row | +1.285 |
row | +1.235 |
Legs | +1.199 |
Rodham | +1.179 |
chest | +1.168 |
Neg logit contributions | |
uphem | -1.985 |
ipeg | -1.905 |
avail | -1.899 |
abwe | -1.885 |
ortmund | -1.811 |
Token | : |
Token ID | 25 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
Row | +1.094 |
row | +1.045 |
Legs | +1.034 |
Rodham | +1.010 |
brim | +1.008 |
Neg logit contributions | |
uphem | -1.605 |
avail | -1.538 |
ipeg | -1.530 |
abwe | -1.518 |
ortmund | -1.461 |
Token | 37 |
Token ID | 2718 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
Row | +0.156 |
row | +0.150 |
Legs | +0.149 |
brim | +0.148 |
Rodham | +0.147 |
Neg logit contributions | |
uphem | -0.181 |
avail | -0.172 |
ipeg | -0.169 |
abwe | -0.168 |
ortmund | -0.162 |
Token | Dark |
Token ID | 3801 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Row | +0.004 |
row | +0.003 |
Rodham | +0.003 |
Legs | +0.003 |
chest | +0.003 |
Neg logit contributions | |
uphem | -0.005 |
abwe | -0.004 |
avail | -0.004 |
ipeg | -0.004 |
ortmund | -0.004 |
Token | ho |
Token ID | 8873 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
uphem | +1.767 |
ipeg | +1.725 |
abwe | +1.700 |
avail | +1.669 |
agna | +1.622 |
Neg logit contributions | |
Row | -0.918 |
Rodham | -0.841 |
brim | -0.828 |
Legs | -0.818 |
row | -0.811 |
Token | arse |
Token ID | 17208 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
uphem | +0.077 |
abwe | +0.073 |
ipeg | +0.072 |
avail | +0.072 |
ortmund | +0.068 |
Neg logit contributions | |
Row | -0.061 |
row | -0.058 |
Legs | -0.057 |
Rodham | -0.057 |
chest | -0.056 |
Token | wrote |
Token ID | 2630 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Row | +0.499 |
row | +0.472 |
Legs | +0.459 |
Rodham | +0.446 |
chest | +0.443 |
Neg logit contributions | |
uphem | -0.922 |
abwe | -0.891 |
ipeg | -0.881 |
avail | -0.876 |
ortmund | -0.845 |
Token | : |
Token ID | 25 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
uphem | +3.249 |
avail | +3.189 |
ipeg | +3.101 |
ifications | +2.984 |
successful | +2.970 |
Neg logit contributions | |
Seym | -3.160 |
brim | -3.148 |
Row | -3.109 |
Legs | -3.062 |
Rodham | -3.030 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
uphem | +2.098 |
avail | +2.002 |
ipeg | +1.950 |
abwe | +1.838 |
successful | +1.831 |
Neg logit contributions | |
Row | -2.723 |
brim | -2.681 |
row | -2.643 |
Legs | -2.630 |
Rodham | -2.617 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
uphem | +2.878 |
avail | +2.836 |
ipeg | +2.698 |
successful | +2.562 |
Trojan | +2.533 |
Neg logit contributions | |
brim | -4.298 |
Row | -4.279 |
Seym | -4.272 |
row | -4.182 |
Legs | -4.182 |
Token | Show |
Token ID | 15307 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
uphem | +3.678 |
ipeg | +3.451 |
avail | +3.409 |
abwe | +3.379 |
successful | +3.277 |
Neg logit contributions | |
Row | -4.009 |
Legs | -3.803 |
Guer | -3.793 |
Rodham | -3.789 |
brim | -3.729 |
Token | nested |
Token ID | 28376 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
uphem | +2.463 |
avail | +2.337 |
abwe | +2.322 |
ipeg | +2.315 |
successful | +2.224 |
Neg logit contributions | |
Row | -1.953 |
Legs | -1.875 |
row | -1.846 |
chest | -1.839 |
Rodham | -1.836 |
Token | , |
Token ID | 11 |
Feature activation | +1.73e-03 |
Pos logit contributions | |
uphem | +2.923 |
abwe | +2.836 |
ipeg | +2.802 |
avail | +2.772 |
ortmund | +2.680 |
Neg logit contributions | |
Row | -1.625 |
row | -1.531 |
Legs | -1.517 |
Rodham | -1.467 |
chest | -1.453 |
Token | M |
Token ID | 337 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
Row | +0.004 |
row | +0.004 |
Legs | +0.004 |
chest | +0.004 |
brim | +0.004 |
Neg logit contributions | |
uphem | -0.005 |
avail | -0.005 |
ipeg | -0.005 |
abwe | -0.005 |
ortmund | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
uphem | +0.361 |
abwe | +0.348 |
ipeg | +0.345 |
avail | +0.344 |
ortmund | +0.331 |
Neg logit contributions | |
Row | -0.187 |
row | -0.177 |
Legs | -0.171 |
Rodham | -0.166 |
chest | -0.165 |
Token | ( |
Token ID | 357 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
uphem | +0.653 |
avail | +0.626 |
ipeg | +0.625 |
abwe | +0.620 |
Trojan | +0.595 |
Neg logit contributions | |
Row | -0.501 |
row | -0.501 |
brim | -0.482 |
chest | -0.479 |
Legs | -0.477 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
uphem | +0.865 |
avail | +0.833 |
ipeg | +0.826 |
abwe | +0.817 |
ortmund | +0.779 |
Neg logit contributions | |
Row | -0.686 |
row | -0.673 |
Legs | -0.653 |
chest | -0.647 |
brim | -0.647 |
Token | ). |
Token ID | 6739 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
uphem | +1.068 |
abwe | +1.034 |
ipeg | +1.023 |
avail | +1.017 |
ortmund | +0.982 |
Neg logit contributions | |
Row | -0.508 |
row | -0.478 |
Legs | -0.465 |
Rodham | -0.450 |
chest | -0.447 |
Token | Cross |
Token ID | 6372 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
uphem | +3.517 |
abwe | +3.360 |
avail | +3.325 |
ipeg | +3.305 |
Trojan | +3.262 |
Neg logit contributions | |
row | -2.950 |
brim | -2.861 |
Row | -2.853 |
chest | -2.785 |
RAY | -2.705 |
Token | - |
Token ID | 12 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
uphem | +0.735 |
abwe | +0.699 |
ipeg | +0.695 |
avail | +0.689 |
ortmund | +0.653 |
Neg logit contributions | |
Row | -0.622 |
row | -0.596 |
Legs | -0.587 |
Rodham | -0.574 |
Guer | -0.573 |
Token | national |
Token ID | 14648 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
uphem | +0.170 |
abwe | +0.162 |
ipeg | +0.160 |
avail | +0.159 |
ortmund | +0.151 |
Neg logit contributions | |
Row | -0.177 |
row | -0.169 |
Legs | -0.168 |
Rodham | -0.164 |
Guer | -0.164 |
Token | time |
Token ID | 640 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
uphem | +0.456 |
abwe | +0.437 |
avail | +0.432 |
ipeg | +0.432 |
ortmund | +0.410 |
Neg logit contributions | |
Row | -0.478 |
row | -0.465 |
Legs | -0.455 |
Rodham | -0.445 |
chest | -0.444 |
Token | trends |
Token ID | 11257 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
uphem | +0.280 |
abwe | +0.270 |
avail | +0.266 |
ipeg | +0.266 |
ortmund | +0.251 |
Neg logit contributions | |
Row | -0.265 |
row | -0.255 |
Legs | -0.251 |
Rodham | -0.245 |
Guer | -0.243 |
Token | Lakes |
Token ID | 24153 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
Row | +0.373 |
row | +0.356 |
Legs | +0.346 |
chest | +0.336 |
Rodham | +0.336 |
Neg logit contributions | |
uphem | -0.619 |
abwe | -0.598 |
avail | -0.593 |
ipeg | -0.593 |
ortmund | -0.564 |
Token | states |
Token ID | 2585 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
uphem | +0.163 |
avail | +0.159 |
abwe | +0.157 |
ipeg | +0.156 |
ancies | +0.147 |
Neg logit contributions | |
Row | -0.122 |
row | -0.120 |
Legs | -0.116 |
chest | -0.114 |
Rodham | -0.112 |
Token | in |
Token ID | 287 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Row | +0.193 |
row | +0.185 |
Legs | +0.183 |
chest | +0.176 |
Guer | +0.176 |
Neg logit contributions | |
uphem | -0.281 |
avail | -0.272 |
abwe | -0.271 |
ipeg | -0.267 |
successful | -0.256 |
Token | preventing |
Token ID | 12174 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
uphem | +0.392 |
avail | +0.384 |
abwe | +0.380 |
ipeg | +0.371 |
ancies | +0.352 |
Neg logit contributions | |
Row | -0.334 |
row | -0.329 |
Legs | -0.322 |
chest | -0.314 |
Guer | -0.307 |
Token | water |
Token ID | 1660 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
uphem | +0.041 |
avail | +0.039 |
abwe | +0.039 |
ipeg | +0.039 |
ancies | +0.037 |
Neg logit contributions | |
Row | -0.034 |
row | -0.033 |
Legs | -0.032 |
chest | -0.031 |
Rodham | -0.031 |
Token | pollution |
Token ID | 12231 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
uphem | +0.562 |
avail | +0.548 |
abwe | +0.543 |
ipeg | +0.528 |
ortmund | +0.498 |
Neg logit contributions | |
Row | -0.694 |
row | -0.664 |
Legs | -0.663 |
Rodham | -0.648 |
Guer | -0.646 |
Token | and |
Token ID | 290 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
Row | +1.730 |
row | +1.644 |
Legs | +1.609 |
chest | +1.561 |
Rodham | +1.560 |
Neg logit contributions | |
uphem | -2.828 |
abwe | -2.730 |
ipeg | -2.692 |
avail | -2.689 |
ortmund | -2.578 |
Token | recommend |
Token ID | 4313 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
uphem | +0.224 |
avail | +0.219 |
abwe | +0.213 |
ipeg | +0.212 |
ancies | +0.200 |
Neg logit contributions | |
Row | -0.205 |
row | -0.199 |
Legs | -0.198 |
chest | -0.188 |
Rodham | -0.187 |
Token | improvements |
Token ID | 8561 |
Feature activation | +8.45e-02 |
Pos logit contributions | |
Row | +0.445 |
Legs | +0.431 |
row | +0.430 |
chest | +0.420 |
Rodham | +0.412 |
Neg logit contributions | |
uphem | -0.428 |
avail | -0.408 |
abwe | -0.402 |
ipeg | -0.402 |
ortmund | -0.378 |
Token | . |
Token ID | 13 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
Row | +0.187 |
row | +0.180 |
Legs | +0.178 |
chest | +0.171 |
Rodham | +0.170 |
Neg logit contributions | |
uphem | -0.295 |
avail | -0.282 |
abwe | -0.282 |
ipeg | -0.278 |
ortmund | -0.267 |
Token | ... |
Token ID | 2644 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
Row | +0.222 |
row | +0.217 |
Legs | +0.209 |
chest | +0.207 |
brim | +0.206 |
Neg logit contributions | |
uphem | -0.298 |
avail | -0.285 |
abwe | -0.283 |
ipeg | -0.281 |
ortmund | -0.267 |
Token | or |
Token ID | 393 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
uphem | +0.111 |
avail | +0.108 |
abwe | +0.106 |
ipeg | +0.105 |
ortmund | +0.101 |
Neg logit contributions | |
Row | -0.092 |
row | -0.088 |
Legs | -0.086 |
Rodham | -0.085 |
chest | -0.085 |
Token | even |
Token ID | 772 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Row | +0.359 |
row | +0.346 |
Legs | +0.340 |
Rodham | +0.334 |
Guer | +0.333 |
Neg logit contributions | |
uphem | -0.361 |
avail | -0.352 |
abwe | -0.341 |
ipeg | -0.339 |
ortmund | -0.322 |
Token | take |
Token ID | 1011 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Row | +0.519 |
row | +0.499 |
Legs | +0.489 |
chest | +0.480 |
Rodham | +0.480 |
Neg logit contributions | |
uphem | -0.540 |
avail | -0.520 |
abwe | -0.513 |
ipeg | -0.508 |
ortmund | -0.482 |
Token | a |
Token ID | 257 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Row | +0.640 |
row | +0.619 |
Legs | +0.607 |
chest | +0.597 |
Rodham | +0.594 |
Neg logit contributions | |
uphem | -0.657 |
abwe | -0.624 |
avail | -0.624 |
ipeg | -0.621 |
ortmund | -0.588 |
Token | small |
Token ID | 1402 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Row | +0.616 |
row | +0.592 |
Legs | +0.580 |
Rodham | +0.567 |
chest | +0.567 |
Neg logit contributions | |
uphem | -0.723 |
avail | -0.695 |
ipeg | -0.692 |
abwe | -0.687 |
ortmund | -0.651 |
Token | nap |
Token ID | 25422 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
Row | +0.461 |
row | +0.443 |
Legs | +0.434 |
chest | +0.425 |
Rodham | +0.424 |
Neg logit contributions | |
uphem | -0.543 |
avail | -0.524 |
ipeg | -0.522 |
abwe | -0.520 |
ortmund | -0.489 |
Token | if |
Token ID | 611 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
Row | +1.745 |
row | +1.655 |
Legs | +1.628 |
Rodham | +1.587 |
Guer | +1.579 |
Neg logit contributions | |
uphem | -2.682 |
abwe | -2.582 |
ipeg | -2.559 |
avail | -2.554 |
ortmund | -2.441 |
Token | you |
Token ID | 345 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Row | +0.122 |
row | +0.117 |
Legs | +0.114 |
Rodham | +0.112 |
chest | +0.112 |
Neg logit contributions | |
uphem | -0.161 |
avail | -0.156 |
abwe | -0.155 |
ipeg | -0.155 |
ortmund | -0.146 |
Token | can |
Token ID | 460 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Row | +0.497 |
row | +0.477 |
Legs | +0.466 |
Rodham | +0.460 |
chest | +0.458 |
Neg logit contributions | |
uphem | -0.509 |
abwe | -0.485 |
avail | -0.485 |
ipeg | -0.481 |
ortmund | -0.454 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
uphem | +0.538 |
avail | +0.525 |
abwe | +0.515 |
ipeg | +0.515 |
ortmund | +0.488 |
Neg logit contributions | |
Row | -0.388 |
row | -0.369 |
Legs | -0.361 |
Guer | -0.355 |
Rodham | -0.354 |
Token |
|
Token ID | 198 |
Feature activation | -6.34e-02 |
Pos logit contributions | |
Row | +0.284 |
row | +0.282 |
brim | +0.272 |
chest | +0.269 |
Rodham | +0.268 |
Neg logit contributions | |
uphem | -0.347 |
avail | -0.333 |
ipeg | -0.330 |
abwe | -0.329 |
ortmund | -0.315 |
Token | important |
Token ID | 1593 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Row | +0.131 |
row | +0.127 |
Legs | +0.126 |
Rodham | +0.123 |
chest | +0.122 |
Neg logit contributions | |
uphem | -0.148 |
avail | -0.141 |
abwe | -0.140 |
ipeg | -0.139 |
ortmund | -0.132 |
Token | step |
Token ID | 2239 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
uphem | +0.396 |
ipeg | +0.381 |
avail | +0.381 |
abwe | +0.378 |
ortmund | +0.362 |
Neg logit contributions | |
Row | -0.235 |
row | -0.227 |
Legs | -0.224 |
Rodham | -0.218 |
chest | -0.217 |
Token | in |
Token ID | 287 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
uphem | +0.133 |
abwe | +0.127 |
ipeg | +0.127 |
avail | +0.127 |
ortmund | +0.120 |
Neg logit contributions | |
Row | -0.084 |
Legs | -0.081 |
row | -0.081 |
Rodham | -0.078 |
chest | -0.077 |
Token | developing |
Token ID | 5922 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
uphem | +1.739 |
avail | +1.686 |
abwe | +1.681 |
ipeg | +1.668 |
ortmund | +1.566 |
Neg logit contributions | |
Row | -1.585 |
row | -1.559 |
Legs | -1.534 |
Rodham | -1.517 |
chest | -1.505 |
Token | a |
Token ID | 257 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
Row | +0.785 |
row | +0.759 |
Legs | +0.748 |
Rodham | +0.737 |
chest | +0.737 |
Neg logit contributions | |
uphem | -0.798 |
abwe | -0.768 |
ipeg | -0.761 |
avail | -0.760 |
ortmund | -0.719 |
Token | positive |
Token ID | 3967 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
Row | +0.122 |
row | +0.118 |
Legs | +0.116 |
Rodham | +0.116 |
chest | +0.115 |
Neg logit contributions | |
uphem | -0.114 |
abwe | -0.110 |
avail | -0.110 |
ipeg | -0.109 |
ortmund | -0.102 |
Token | two |
Token ID | 734 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Row | +2.337 |
row | +2.247 |
Legs | +2.207 |
Rodham | +2.160 |
chest | +2.151 |
Neg logit contributions | |
uphem | -2.610 |
abwe | -2.504 |
ipeg | -2.475 |
avail | -2.460 |
ortmund | -2.346 |
Token | way |
Token ID | 835 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Row | +0.282 |
row | +0.271 |
Legs | +0.267 |
Rodham | +0.265 |
chest | +0.261 |
Neg logit contributions | |
uphem | -0.315 |
avail | -0.302 |
abwe | -0.302 |
ipeg | -0.301 |
ortmund | -0.284 |
Token | communication |
Token ID | 6946 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Row | +0.457 |
row | +0.441 |
Legs | +0.439 |
Rodham | +0.427 |
Guer | +0.423 |
Neg logit contributions | |
uphem | -0.393 |
abwe | -0.378 |
ipeg | -0.377 |
avail | -0.375 |
ortmund | -0.350 |
Token | process |
Token ID | 1429 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Row | +0.542 |
Legs | +0.519 |
row | +0.517 |
Rodham | +0.501 |
chest | +0.499 |
Neg logit contributions | |
uphem | -0.705 |
abwe | -0.682 |
avail | -0.679 |
ipeg | -0.672 |
ortmund | -0.637 |
Token | between |
Token ID | 1022 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Row | +0.788 |
row | +0.754 |
Legs | +0.750 |
Rodham | +0.721 |
chest | +0.721 |
Neg logit contributions | |
uphem | -1.129 |
abwe | -1.097 |
avail | -1.089 |
ipeg | -1.076 |
ortmund | -1.027 |
Token | ISI |
Token ID | 22048 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
uphem | +0.888 |
avail | +0.838 |
ipeg | +0.814 |
abwe | +0.806 |
ortmund | +0.766 |
Neg logit contributions | |
row | -1.303 |
Row | -1.294 |
chest | -1.275 |
brim | -1.252 |
Legs | -1.244 |
Token |
|
Token ID | 198 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
uphem | +1.755 |
avail | +1.665 |
ipeg | +1.625 |
abwe | +1.623 |
ortmund | +1.544 |
Neg logit contributions | |
Row | -2.070 |
row | -2.044 |
brim | -2.017 |
Legs | -2.015 |
chest | -2.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Row | +0.780 |
row | +0.755 |
Legs | +0.744 |
Rodham | +0.728 |
brim | +0.727 |
Neg logit contributions | |
uphem | -0.743 |
ipeg | -0.701 |
avail | -0.701 |
abwe | -0.697 |
ortmund | -0.662 |
Token | M |
Token ID | 44 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Row | +0.730 |
row | +0.693 |
Legs | +0.689 |
Rodham | +0.673 |
brim | +0.668 |
Neg logit contributions | |
uphem | -0.889 |
abwe | -0.847 |
ipeg | -0.844 |
avail | -0.831 |
ortmund | -0.801 |
Token | ol |
Token ID | 349 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
Row | +0.471 |
Legs | +0.450 |
row | +0.447 |
Rodham | +0.437 |
Guer | +0.435 |
Neg logit contributions | |
uphem | -0.474 |
abwe | -0.453 |
ipeg | -0.446 |
avail | -0.437 |
ortmund | -0.421 |
Token | cho |
Token ID | 6679 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
uphem | +0.074 |
abwe | +0.070 |
ipeg | +0.070 |
avail | +0.068 |
ortmund | +0.066 |
Neg logit contributions | |
Row | -0.063 |
Legs | -0.060 |
row | -0.059 |
Rodham | -0.058 |
Guer | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Row | +1.507 |
row | +1.430 |
Legs | +1.389 |
Rodham | +1.349 |
Guer | +1.342 |
Neg logit contributions | |
uphem | -2.723 |
abwe | -2.628 |
ipeg | -2.600 |
avail | -2.585 |
ortmund | -2.491 |
Token | M |
Token ID | 337 |
Feature activation | -2.36e-03 |
Pos logit contributions | |
Row | +0.833 |
row | +0.820 |
Legs | +0.790 |
chest | +0.785 |
brim | +0.778 |
Neg logit contributions | |
uphem | -1.086 |
avail | -1.037 |
ipeg | -1.034 |
abwe | -1.033 |
ortmund | -0.982 |
Token | ., |
Token ID | 1539 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
uphem | +0.009 |
abwe | +0.009 |
ipeg | +0.009 |
avail | +0.009 |
ortmund | +0.008 |
Neg logit contributions | |
Row | -0.005 |
row | -0.004 |
Legs | -0.004 |
Rodham | -0.004 |
Guer | -0.004 |
Token | Craig |
Token ID | 13854 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
uphem | +0.573 |
abwe | +0.552 |
ipeg | +0.547 |
avail | +0.544 |
ortmund | +0.520 |
Neg logit contributions | |
Row | -0.399 |
row | -0.396 |
chest | -0.381 |
Legs | -0.381 |
brim | -0.377 |
Token | , |
Token ID | 11 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
uphem | +0.119 |
abwe | +0.115 |
ipeg | +0.114 |
avail | +0.113 |
ortmund | +0.109 |
Neg logit contributions | |
Row | -0.066 |
row | -0.062 |
Legs | -0.061 |
Rodham | -0.059 |
chest | -0.059 |
Token | versus |
Token ID | 9051 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
uphem | +0.968 |
abwe | +0.936 |
avail | +0.929 |
ipeg | +0.927 |
ortmund | +0.885 |
Neg logit contributions | |
Row | -0.652 |
row | -0.622 |
Legs | -0.614 |
Rodham | -0.602 |
chest | -0.593 |
Token | Kh |
Token ID | 5311 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Row | +0.739 |
row | +0.719 |
Legs | +0.701 |
chest | +0.688 |
Rodham | +0.686 |
Neg logit contributions | |
uphem | -0.999 |
abwe | -0.960 |
avail | -0.952 |
ipeg | -0.946 |
ortmund | -0.894 |
Token | ab |
Token ID | 397 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
uphem | +0.657 |
abwe | +0.624 |
ipeg | +0.618 |
avail | +0.593 |
successful | +0.572 |
Neg logit contributions | |
Row | -0.821 |
Legs | -0.804 |
chest | -0.779 |
Rodham | -0.777 |
brim | -0.775 |
Token | ib |
Token ID | 571 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Row | +0.664 |
Legs | +0.634 |
row | +0.614 |
chest | +0.601 |
brim | +0.598 |
Neg logit contributions | |
uphem | -1.412 |
abwe | -1.362 |
ipeg | -1.354 |
avail | -1.341 |
ortmund | -1.304 |
Token | Nur |
Token ID | 49281 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Row | +0.382 |
row | +0.371 |
Legs | +0.369 |
chest | +0.362 |
brim | +0.359 |
Neg logit contributions | |
uphem | -0.392 |
avail | -0.377 |
abwe | -0.377 |
ipeg | -0.373 |
ortmund | -0.351 |
Token | mag |
Token ID | 19726 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
uphem | +1.104 |
avail | +1.034 |
ipeg | +1.006 |
abwe | +0.998 |
ancies | +0.944 |
Neg logit contributions | |
Row | -1.113 |
Legs | -1.066 |
Guer | -1.053 |
brim | -1.050 |
Rodham | -1.046 |
Token | omed |
Token ID | 12657 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
Row | +2.357 |
row | +2.245 |
Legs | +2.232 |
Rodham | +2.196 |
Guer | +2.185 |
Neg logit contributions | |
uphem | -2.348 |
abwe | -2.205 |
ipeg | -2.200 |
avail | -2.186 |
ortmund | -2.067 |
Token | ov |
Token ID | 709 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Row | +1.233 |
row | +1.174 |
Legs | +1.150 |
Rodham | +1.119 |
chest | +1.116 |
Neg logit contributions | |
uphem | -1.942 |
abwe | -1.873 |
ipeg | -1.850 |
avail | -1.841 |
ortmund | -1.764 |
Token | – |
Token ID | 784 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Row | +0.258 |
row | +0.246 |
Legs | +0.244 |
Rodham | +0.238 |
chest | +0.236 |
Neg logit contributions | |
uphem | -0.405 |
abwe | -0.392 |
ipeg | -0.387 |
avail | -0.387 |
ortmund | -0.370 |
Token | which |
Token ID | 543 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
uphem | +0.412 |
abwe | +0.396 |
avail | +0.392 |
ipeg | +0.390 |
ortmund | +0.372 |
Neg logit contributions | |
Row | -0.312 |
row | -0.301 |
Legs | -0.298 |
Rodham | -0.290 |
chest | -0.288 |
Token | was |
Token ID | 373 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Row | +0.301 |
row | +0.293 |
Legs | +0.287 |
chest | +0.281 |
Rodham | +0.281 |
Neg logit contributions | |
uphem | -0.333 |
abwe | -0.318 |
avail | -0.317 |
ipeg | -0.314 |
ortmund | -0.299 |
Token | is |
Token ID | 318 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Row | +0.962 |
row | +0.935 |
Legs | +0.927 |
chest | +0.904 |
Rodham | +0.883 |
Neg logit contributions | |
uphem | -1.130 |
avail | -1.088 |
abwe | -1.081 |
ipeg | -1.074 |
ancies | -1.017 |
Token | constitutionally |
Token ID | 40800 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Row | +0.267 |
row | +0.264 |
Legs | +0.258 |
chest | +0.255 |
brim | +0.244 |
Neg logit contributions | |
uphem | -0.303 |
avail | -0.294 |
abwe | -0.289 |
ipeg | -0.283 |
ancies | -0.270 |
Token | barred |
Token ID | 23902 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
uphem | +0.475 |
avail | +0.468 |
ipeg | +0.446 |
abwe | +0.444 |
ancies | +0.424 |
Neg logit contributions | |
Row | -0.536 |
Legs | -0.525 |
row | -0.524 |
chest | -0.512 |
Rodham | -0.501 |
Token | from |
Token ID | 422 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Row | +0.714 |
row | +0.676 |
Legs | +0.661 |
chest | +0.634 |
Rodham | +0.633 |
Neg logit contributions | |
uphem | -1.468 |
abwe | -1.419 |
avail | -1.403 |
ipeg | -1.401 |
ortmund | -1.347 |
Token | serving |
Token ID | 7351 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
row | +0.461 |
Row | +0.461 |
Legs | +0.449 |
chest | +0.439 |
Guer | +0.429 |
Neg logit contributions | |
uphem | -0.433 |
avail | -0.429 |
abwe | -0.409 |
ipeg | -0.407 |
ortmund | -0.380 |
Token | a |
Token ID | 257 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
Row | +0.254 |
row | +0.247 |
Legs | +0.242 |
chest | +0.239 |
brim | +0.228 |
Neg logit contributions | |
uphem | -0.463 |
avail | -0.445 |
abwe | -0.443 |
ipeg | -0.440 |
ortmund | -0.420 |
Token | further |
Token ID | 2252 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Row | +0.076 |
row | +0.074 |
Legs | +0.073 |
chest | +0.072 |
Guer | +0.070 |
Neg logit contributions | |
uphem | -0.090 |
avail | -0.086 |
abwe | -0.085 |
ipeg | -0.085 |
ortmund | -0.080 |
Token | term |
Token ID | 3381 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
Row | +0.367 |
row | +0.355 |
Legs | +0.352 |
chest | +0.345 |
Guer | +0.340 |
Neg logit contributions | |
uphem | -0.405 |
avail | -0.393 |
abwe | -0.387 |
ipeg | -0.384 |
ortmund | -0.364 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Row | +0.206 |
row | +0.200 |
Legs | +0.199 |
chest | +0.192 |
Guer | +0.186 |
Neg logit contributions | |
uphem | -0.308 |
avail | -0.301 |
abwe | -0.298 |
ipeg | -0.292 |
ancies | -0.279 |
Token | Moreno |
Token ID | 43269 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
Row | +0.322 |
row | +0.315 |
Legs | +0.306 |
brim | +0.302 |
chest | +0.302 |
Neg logit contributions | |
uphem | -0.336 |
abwe | -0.319 |
ipeg | -0.315 |
avail | -0.313 |
ortmund | -0.299 |
Token | has |
Token ID | 468 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
Row | +0.036 |
row | +0.036 |
Legs | +0.035 |
chest | +0.035 |
Guer | +0.033 |
Neg logit contributions | |
uphem | -0.042 |
avail | -0.041 |
ipeg | -0.040 |
abwe | -0.040 |
ancies | -0.038 |
Token | completely |
Token ID | 3190 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
Row | +0.432 |
row | +0.417 |
Legs | +0.410 |
Rodham | +0.404 |
chest | +0.401 |
Neg logit contributions | |
uphem | -0.494 |
abwe | -0.475 |
avail | -0.471 |
ipeg | -0.469 |
ortmund | -0.445 |
Token | what |
Token ID | 644 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
uphem | +1.201 |
abwe | +1.153 |
avail | +1.152 |
ipeg | +1.136 |
ortmund | +1.077 |
Neg logit contributions | |
Row | -1.136 |
row | -1.106 |
Legs | -1.080 |
Rodham | -1.068 |
chest | -1.056 |
Token | Arena |
Token ID | 10937 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
uphem | +0.436 |
abwe | +0.423 |
avail | +0.417 |
ipeg | +0.411 |
ortmund | +0.393 |
Neg logit contributions | |
Row | -0.381 |
row | -0.367 |
Legs | -0.361 |
Rodham | -0.360 |
chest | -0.355 |
Token | should |
Token ID | 815 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
uphem | +0.406 |
abwe | +0.393 |
avail | +0.391 |
ipeg | +0.387 |
ortmund | +0.365 |
Neg logit contributions | |
Row | -0.388 |
row | -0.373 |
Legs | -0.369 |
chest | -0.363 |
Rodham | -0.362 |
Token | be |
Token ID | 307 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Row | +0.877 |
row | +0.836 |
Legs | +0.827 |
Rodham | +0.808 |
chest | +0.801 |
Neg logit contributions | |
uphem | -1.231 |
abwe | -1.190 |
avail | -1.188 |
ipeg | -1.178 |
ortmund | -1.120 |
Token | . |
Token ID | 13 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
Row | +0.393 |
row | +0.373 |
Legs | +0.368 |
Rodham | +0.357 |
chest | +0.354 |
Neg logit contributions | |
uphem | -0.586 |
avail | -0.569 |
abwe | -0.567 |
ipeg | -0.561 |
ortmund | -0.533 |
Token | Stick |
Token ID | 22994 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
Row | +0.163 |
row | +0.160 |
Legs | +0.154 |
Rodham | +0.153 |
brim | +0.152 |
Neg logit contributions | |
uphem | -0.196 |
abwe | -0.188 |
avail | -0.185 |
ipeg | -0.185 |
ortmund | -0.177 |
Token | to |
Token ID | 284 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
uphem | +1.327 |
abwe | +1.270 |
ipeg | +1.256 |
avail | +1.252 |
ortmund | +1.201 |
Neg logit contributions | |
Row | -0.919 |
row | -0.872 |
Legs | -0.860 |
Rodham | -0.859 |
Guer | -0.826 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
uphem | +0.550 |
abwe | +0.532 |
avail | +0.527 |
ipeg | +0.519 |
ortmund | +0.495 |
Neg logit contributions | |
Row | -0.485 |
row | -0.478 |
Legs | -0.463 |
Rodham | -0.457 |
chest | -0.454 |
Token | blog |
Token ID | 4130 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
uphem | +0.497 |
avail | +0.480 |
abwe | +0.478 |
ipeg | +0.469 |
ortmund | +0.448 |
Neg logit contributions | |
Row | -0.448 |
row | -0.434 |
Legs | -0.424 |
Rodham | -0.417 |
chest | -0.415 |
Token | for |
Token ID | 329 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
uphem | +0.185 |
abwe | +0.178 |
avail | +0.177 |
ipeg | +0.177 |
ortmund | +0.168 |
Neg logit contributions | |
Row | -0.133 |
row | -0.126 |
Legs | -0.125 |
Rodham | -0.123 |
chest | -0.120 |
Token | shot |
Token ID | 9442 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Row | +0.753 |
row | +0.722 |
Legs | +0.713 |
Rodham | +0.700 |
Guer | +0.695 |
Neg logit contributions | |
uphem | -0.740 |
abwe | -0.709 |
ipeg | -0.701 |
avail | -0.691 |
ortmund | -0.661 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Row | +0.777 |
row | +0.752 |
Legs | +0.735 |
Rodham | +0.720 |
chest | +0.717 |
Neg logit contributions | |
uphem | -0.985 |
abwe | -0.956 |
ipeg | -0.948 |
avail | -0.938 |
ortmund | -0.894 |
Token | Blues |
Token ID | 15261 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
uphem | +0.629 |
ipeg | +0.614 |
abwe | +0.614 |
avail | +0.610 |
ortmund | +0.581 |
Neg logit contributions | |
Row | -0.291 |
row | -0.283 |
Legs | -0.272 |
Rodham | -0.269 |
chest | -0.267 |
Token | 10 |
Token ID | 838 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
uphem | +0.326 |
ipeg | +0.316 |
abwe | +0.316 |
avail | +0.315 |
ortmund | +0.298 |
Neg logit contributions | |
Row | -0.256 |
row | -0.248 |
Legs | -0.242 |
Rodham | -0.239 |
chest | -0.236 |
Token | - |
Token ID | 12 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
Row | +0.145 |
row | +0.138 |
Legs | +0.135 |
Rodham | +0.132 |
chest | +0.132 |
Neg logit contributions | |
uphem | -0.191 |
abwe | -0.184 |
ipeg | -0.181 |
avail | -0.179 |
ortmund | -0.172 |
Token | 8 |
Token ID | 23 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
Row | +1.220 |
row | +1.162 |
Legs | +1.142 |
Rodham | +1.115 |
Guer | +1.106 |
Neg logit contributions | |
uphem | -1.688 |
abwe | -1.625 |
ipeg | -1.606 |
avail | -1.594 |
ortmund | -1.530 |
Token | . |
Token ID | 13 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
Row | +1.599 |
row | +1.521 |
Legs | +1.490 |
Rodham | +1.453 |
chest | +1.439 |
Neg logit contributions | |
uphem | -2.549 |
abwe | -2.465 |
ipeg | -2.442 |
avail | -2.423 |
ortmund | -2.328 |
Token | The |
Token ID | 383 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
Row | +0.132 |
row | +0.130 |
brim | +0.125 |
Rodham | +0.124 |
Legs | +0.124 |
Neg logit contributions | |
uphem | -0.183 |
ipeg | -0.178 |
abwe | -0.177 |
avail | -0.174 |
ortmund | -0.168 |
Token | home |
Token ID | 1363 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
uphem | +0.030 |
abwe | +0.029 |
avail | +0.029 |
ipeg | +0.029 |
ortmund | +0.028 |
Neg logit contributions | |
Row | -0.022 |
row | -0.021 |
Legs | -0.021 |
Rodham | -0.021 |
chest | -0.021 |
Token | team |
Token ID | 1074 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
Row | +1.522 |
row | +1.454 |
Legs | +1.425 |
Rodham | +1.393 |
Guer | +1.378 |
Neg logit contributions | |
uphem | -2.244 |
abwe | -2.161 |
ipeg | -2.143 |
avail | -2.131 |
ortmund | -2.043 |
Token | even |
Token ID | 772 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
uphem | +0.502 |
ipeg | +0.485 |
abwe | +0.483 |
avail | +0.482 |
ortmund | +0.459 |
Neg logit contributions | |
Row | -0.443 |
row | -0.429 |
Legs | -0.422 |
Rodham | -0.413 |
chest | -0.412 |
Token | like |
Token ID | 588 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Row | +0.609 |
row | +0.587 |
Legs | +0.578 |
Rodham | +0.566 |
chest | +0.565 |
Neg logit contributions | |
uphem | -0.738 |
abwe | -0.707 |
avail | -0.706 |
ipeg | -0.698 |
ortmund | -0.658 |
Token | looking |
Token ID | 2045 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Row | +0.792 |
row | +0.766 |
Legs | +0.752 |
Rodham | +0.738 |
chest | +0.732 |
Neg logit contributions | |
uphem | -1.095 |
abwe | -1.052 |
avail | -1.044 |
ipeg | -1.039 |
ortmund | -0.982 |
Token | at |
Token ID | 379 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
uphem | +0.847 |
avail | +0.818 |
abwe | +0.815 |
ipeg | +0.806 |
ortmund | +0.762 |
Neg logit contributions | |
Row | -0.620 |
row | -0.599 |
Legs | -0.593 |
Rodham | -0.570 |
chest | -0.570 |
Token | someone |
Token ID | 2130 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
uphem | +1.201 |
abwe | +1.154 |
avail | +1.152 |
ipeg | +1.138 |
ancies | +1.076 |
Neg logit contributions | |
Row | -1.086 |
row | -1.070 |
Legs | -1.045 |
Rodham | -1.037 |
chest | -1.034 |
Token | � |
Token ID | 447 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Row | +0.141 |
row | +0.135 |
Legs | +0.134 |
Rodham | +0.130 |
chest | +0.129 |
Neg logit contributions | |
uphem | -0.200 |
abwe | -0.193 |
avail | -0.191 |
ipeg | -0.189 |
ortmund | -0.180 |
Token | � |
Token ID | 247 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
uphem | +0.279 |
avail | +0.256 |
abwe | +0.255 |
ipeg | +0.249 |
ortmund | +0.239 |
Neg logit contributions | |
Row | -0.334 |
Legs | -0.323 |
row | -0.321 |
Rodham | -0.319 |
chest | -0.318 |
Token | s |
Token ID | 82 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
Row | +0.060 |
Legs | +0.057 |
row | +0.057 |
Rodham | +0.056 |
Guer | +0.056 |
Neg logit contributions | |
uphem | -0.061 |
abwe | -0.059 |
ipeg | -0.058 |
avail | -0.057 |
ortmund | -0.054 |
Token | work |
Token ID | 670 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
uphem | +0.231 |
avail | +0.221 |
abwe | +0.220 |
ipeg | +0.220 |
ortmund | +0.206 |
Neg logit contributions | |
Row | -0.175 |
row | -0.169 |
Legs | -0.164 |
Rodham | -0.163 |
Guer | -0.161 |
Token | , |
Token ID | 11 |
Feature activation | +9.89e-03 |
Pos logit contributions | |
uphem | +0.185 |
abwe | +0.179 |
avail | +0.178 |
ipeg | +0.176 |
ortmund | +0.168 |
Neg logit contributions | |
Row | -0.122 |
row | -0.115 |
Legs | -0.115 |
Rodham | -0.113 |
Guer | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Row | +0.024 |
row | +0.023 |
Legs | +0.023 |
Rodham | +0.022 |
chest | +0.022 |
Neg logit contributions | |
uphem | -0.032 |
abwe | -0.031 |
avail | -0.031 |
ipeg | -0.030 |
ortmund | -0.029 |
Token | your |
Token ID | 534 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
uphem | +0.625 |
avail | +0.605 |
abwe | +0.600 |
ipeg | +0.594 |
ancies | +0.560 |
Neg logit contributions | |
Row | -0.490 |
row | -0.474 |
Legs | -0.465 |
Rodham | -0.460 |
chest | -0.455 |
Token | a |
Token ID | 257 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
uphem | +1.577 |
abwe | +1.523 |
ipeg | +1.493 |
avail | +1.489 |
ortmund | +1.410 |
Neg logit contributions | |
Row | -1.263 |
row | -1.246 |
Legs | -1.216 |
chest | -1.201 |
brim | -1.183 |
Token | Norwegian |
Token ID | 22158 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Row | +0.294 |
row | +0.286 |
Legs | +0.279 |
chest | +0.274 |
Rodham | +0.273 |
Neg logit contributions | |
uphem | -0.360 |
abwe | -0.346 |
ipeg | -0.343 |
avail | -0.341 |
ortmund | -0.323 |
Token | woman |
Token ID | 2415 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Row | +0.735 |
row | +0.711 |
Legs | +0.699 |
Rodham | +0.680 |
chest | +0.680 |
Neg logit contributions | |
uphem | -0.874 |
abwe | -0.839 |
ipeg | -0.829 |
avail | -0.828 |
ortmund | -0.782 |
Token | who |
Token ID | 508 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
Row | +0.285 |
row | +0.277 |
Legs | +0.270 |
chest | +0.262 |
Rodham | +0.260 |
Neg logit contributions | |
uphem | -0.397 |
abwe | -0.385 |
avail | -0.379 |
ipeg | -0.378 |
ortmund | -0.357 |
Token | was |
Token ID | 373 |
Feature activation | +7.38e-02 |
Pos logit contributions | |
Row | +0.196 |
row | +0.191 |
Legs | +0.188 |
chest | +0.184 |
Rodham | +0.182 |
Neg logit contributions | |
uphem | -0.192 |
ipeg | -0.185 |
abwe | -0.183 |
avail | -0.183 |
ancies | -0.169 |
Token | hit |
Token ID | 2277 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
Row | +0.213 |
row | +0.208 |
Legs | +0.205 |
Rodham | +0.199 |
chest | +0.199 |
Neg logit contributions | |
uphem | -0.203 |
abwe | -0.195 |
avail | -0.194 |
ipeg | -0.192 |
ortmund | -0.177 |
Token | by |
Token ID | 416 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
Row | +0.156 |
row | +0.149 |
Legs | +0.148 |
Rodham | +0.143 |
Guer | +0.142 |
Neg logit contributions | |
uphem | -0.221 |
abwe | -0.213 |
ipeg | -0.210 |
avail | -0.210 |
ortmund | -0.199 |
Token | sh |
Token ID | 427 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
uphem | +0.908 |
abwe | +0.866 |
ipeg | +0.843 |
avail | +0.839 |
ortmund | +0.791 |
Neg logit contributions | |
Row | -1.062 |
row | -1.037 |
Legs | -1.023 |
chest | -1.012 |
Rodham | -0.991 |
Token | rapnel |
Token ID | 48766 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
Row | +0.402 |
Legs | +0.382 |
row | +0.374 |
Guer | +0.372 |
Rodham | +0.372 |
Neg logit contributions | |
uphem | -0.437 |
abwe | -0.415 |
ipeg | -0.413 |
avail | -0.399 |
ortmund | -0.389 |
Token | in |
Token ID | 287 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
Row | +1.087 |
row | +1.043 |
Legs | +1.024 |
chest | +0.989 |
Rodham | +0.986 |
Neg logit contributions | |
uphem | -1.575 |
abwe | -1.527 |
avail | -1.502 |
ipeg | -1.496 |
ortmund | -1.426 |
Token | World |
Token ID | 2159 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Row | +0.094 |
row | +0.091 |
Legs | +0.089 |
chest | +0.088 |
Rodham | +0.088 |
Neg logit contributions | |
uphem | -0.107 |
abwe | -0.103 |
ipeg | -0.100 |
avail | -0.100 |
ortmund | -0.096 |
Token | he |
Token ID | 339 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
Row | +0.343 |
row | +0.334 |
Legs | +0.327 |
Rodham | +0.321 |
chest | +0.321 |
Neg logit contributions | |
uphem | -0.424 |
avail | -0.407 |
abwe | -0.405 |
ipeg | -0.405 |
ortmund | -0.382 |
Token | gets |
Token ID | 3011 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
uphem | +0.051 |
avail | +0.049 |
ipeg | +0.049 |
abwe | +0.048 |
ancies | +0.046 |
Neg logit contributions | |
Row | -0.052 |
row | -0.051 |
Legs | -0.050 |
chest | -0.049 |
Rodham | -0.049 |
Token | inside |
Token ID | 2641 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
uphem | +0.375 |
avail | +0.363 |
ipeg | +0.356 |
abwe | +0.356 |
ortmund | +0.337 |
Neg logit contributions | |
Row | -0.313 |
row | -0.308 |
chest | -0.299 |
Legs | -0.299 |
Rodham | -0.297 |
Token | , |
Token ID | 11 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
uphem | +1.621 |
avail | +1.568 |
ipeg | +1.563 |
abwe | +1.561 |
ancies | +1.463 |
Neg logit contributions | |
Row | -1.344 |
row | -1.336 |
chest | -1.286 |
Rodham | -1.284 |
Legs | -1.281 |
Token | turns |
Token ID | 4962 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
uphem | +0.208 |
avail | +0.202 |
abwe | +0.199 |
ipeg | +0.198 |
ortmund | +0.188 |
Neg logit contributions | |
Row | -0.185 |
row | -0.180 |
Legs | -0.176 |
Rodham | -0.173 |
chest | -0.173 |
Token | in |
Token ID | 287 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
uphem | +0.252 |
avail | +0.245 |
ipeg | +0.242 |
abwe | +0.240 |
ortmund | +0.226 |
Neg logit contributions | |
Row | -0.187 |
row | -0.183 |
Legs | -0.178 |
Rodham | -0.176 |
chest | -0.175 |
Token | and |
Token ID | 290 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
uphem | +0.382 |
abwe | +0.367 |
avail | +0.367 |
ipeg | +0.365 |
ortmund | +0.346 |
Neg logit contributions | |
Row | -0.263 |
row | -0.253 |
Legs | -0.249 |
Rodham | -0.245 |
chest | -0.243 |
Token | still |
Token ID | 991 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
uphem | +0.704 |
avail | +0.690 |
ipeg | +0.674 |
abwe | +0.672 |
ancies | +0.637 |
Neg logit contributions | |
Row | -0.637 |
row | -0.624 |
Legs | -0.612 |
chest | -0.602 |
Rodham | -0.601 |
Token | gets |
Token ID | 3011 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
Row | +0.741 |
row | +0.721 |
Legs | +0.708 |
chest | +0.695 |
Rodham | +0.694 |
Neg logit contributions | |
uphem | -0.705 |
avail | -0.682 |
abwe | -0.672 |
ipeg | -0.671 |
ortmund | -0.632 |
Token | the |
Token ID | 262 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
uphem | +0.069 |
avail | +0.067 |
abwe | +0.066 |
ipeg | +0.066 |
ortmund | +0.062 |
Neg logit contributions | |
Row | -0.055 |
row | -0.054 |
Legs | -0.053 |
chest | -0.052 |
Rodham | -0.052 |
Token | power |
Token ID | 1176 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Row | +0.161 |
row | +0.156 |
Legs | +0.154 |
Rodham | +0.152 |
chest | +0.151 |
Neg logit contributions | |
uphem | -0.194 |
avail | -0.187 |
abwe | -0.186 |
ipeg | -0.184 |
ortmund | -0.173 |
Token | - |
Token ID | 12 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
uphem | +0.347 |
avail | +0.331 |
abwe | +0.331 |
ipeg | +0.330 |
ortmund | +0.313 |
Neg logit contributions | |
Row | -0.260 |
row | -0.251 |
Legs | -0.248 |
Rodham | -0.240 |
brim | -0.238 |
Token | winning |
Token ID | 14463 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
uphem | +0.484 |
abwe | +0.462 |
ipeg | +0.459 |
avail | +0.455 |
ortmund | +0.431 |
Neg logit contributions | |
Row | -0.393 |
Legs | -0.374 |
row | -0.373 |
Rodham | -0.363 |
brim | -0.359 |
Token | networks |
Token ID | 7686 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
uphem | +0.075 |
avail | +0.072 |
abwe | +0.071 |
ipeg | +0.071 |
ortmund | +0.066 |
Neg logit contributions | |
Row | -0.085 |
row | -0.082 |
Legs | -0.081 |
chest | -0.080 |
Rodham | -0.079 |
Token | ," |
Token ID | 553 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
uphem | +0.162 |
avail | +0.157 |
abwe | +0.156 |
ipeg | +0.155 |
ortmund | +0.148 |
Neg logit contributions | |
Row | -0.116 |
row | -0.112 |
Legs | -0.110 |
chest | -0.108 |
Rodham | -0.107 |
Token | says |
Token ID | 1139 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Row | +0.192 |
row | +0.187 |
Legs | +0.183 |
chest | +0.181 |
Rodham | +0.180 |
Neg logit contributions | |
uphem | -0.192 |
abwe | -0.184 |
avail | -0.182 |
ipeg | -0.181 |
ortmund | -0.171 |
Token | AMC |
Token ID | 36239 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
uphem | +0.681 |
abwe | +0.653 |
avail | +0.646 |
ipeg | +0.639 |
ortmund | +0.608 |
Neg logit contributions | |
Row | -0.662 |
row | -0.647 |
Legs | -0.632 |
chest | -0.629 |
Rodham | -0.621 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
uphem | +0.202 |
abwe | +0.193 |
ipeg | +0.190 |
avail | +0.189 |
ortmund | +0.182 |
Neg logit contributions | |
Row | -0.179 |
row | -0.172 |
Legs | -0.170 |
chest | -0.168 |
Rodham | -0.167 |
Token | offering |
Token ID | 6011 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
uphem | +0.485 |
abwe | +0.466 |
avail | +0.464 |
ipeg | +0.457 |
ortmund | +0.438 |
Neg logit contributions | |
Row | -0.381 |
row | -0.370 |
Legs | -0.364 |
chest | -0.357 |
Rodham | -0.355 |
Token | these |
Token ID | 777 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
uphem | +0.279 |
abwe | +0.267 |
avail | +0.265 |
ipeg | +0.264 |
ortmund | +0.249 |
Neg logit contributions | |
Row | -0.231 |
row | -0.223 |
Legs | -0.220 |
chest | -0.214 |
Rodham | -0.213 |
Token | fighting |
Token ID | 4330 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
Row | +0.291 |
row | +0.280 |
Legs | +0.278 |
chest | +0.272 |
Rodham | +0.271 |
Neg logit contributions | |
uphem | -0.280 |
avail | -0.268 |
ipeg | -0.266 |
abwe | -0.266 |
ortmund | -0.248 |
Token | words |
Token ID | 2456 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Row | +0.132 |
row | +0.128 |
Legs | +0.125 |
Rodham | +0.123 |
chest | +0.122 |
Neg logit contributions | |
uphem | -0.119 |
avail | -0.114 |
abwe | -0.113 |
ipeg | -0.112 |
ortmund | -0.105 |
Token | I |
Token ID | 314 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
uphem | +0.237 |
avail | +0.227 |
abwe | +0.225 |
ipeg | +0.225 |
ortmund | +0.218 |
Neg logit contributions | |
Row | -0.170 |
row | -0.170 |
brim | -0.163 |
chest | -0.161 |
Rodham | -0.161 |
Token | give |
Token ID | 1577 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Row | +0.110 |
row | +0.105 |
Legs | +0.104 |
Rodham | +0.102 |
chest | +0.101 |
Neg logit contributions | |
uphem | -0.096 |
avail | -0.093 |
abwe | -0.090 |
ipeg | -0.090 |
ortmund | -0.085 |
Token | them |
Token ID | 606 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
uphem | +0.369 |
avail | +0.355 |
abwe | +0.351 |
ipeg | +0.346 |
ortmund | +0.330 |
Neg logit contributions | |
Row | -0.318 |
row | -0.313 |
Legs | -0.302 |
Rodham | -0.298 |
chest | -0.297 |
Token | the |
Token ID | 262 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
uphem | +0.386 |
avail | +0.374 |
abwe | +0.370 |
ipeg | +0.363 |
ortmund | +0.344 |
Neg logit contributions | |
Row | -0.366 |
row | -0.360 |
Legs | -0.349 |
chest | -0.346 |
Rodham | -0.345 |
Token | benefit |
Token ID | 4414 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
Row | +0.061 |
row | +0.060 |
Legs | +0.059 |
Rodham | +0.058 |
chest | +0.057 |
Neg logit contributions | |
uphem | -0.061 |
avail | -0.058 |
abwe | -0.058 |
ipeg | -0.057 |
ortmund | -0.054 |
Token | of |
Token ID | 286 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
Row | +0.786 |
row | +0.750 |
Legs | +0.722 |
Guer | +0.711 |
Rodham | +0.706 |
Neg logit contributions | |
uphem | -1.055 |
abwe | -1.011 |
ipeg | -1.002 |
avail | -0.975 |
ortmund | -0.948 |
Token | doubt |
Token ID | 4719 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
uphem | +0.303 |
abwe | +0.291 |
ipeg | +0.287 |
avail | +0.285 |
ortmund | +0.273 |
Neg logit contributions | |
Row | -0.230 |
row | -0.220 |
Legs | -0.215 |
Rodham | -0.210 |
Guer | -0.209 |
Token | . |
Token ID | 13 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
Row | +0.340 |
row | +0.326 |
Legs | +0.323 |
chest | +0.313 |
Rodham | +0.313 |
Neg logit contributions | |
uphem | -0.460 |
avail | -0.443 |
abwe | -0.443 |
ipeg | -0.437 |
ortmund | -0.416 |
Token | The |
Token ID | 383 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
Row | +0.129 |
row | +0.129 |
brim | +0.123 |
chest | +0.122 |
Legs | +0.121 |
Neg logit contributions | |
uphem | -0.181 |
avail | -0.173 |
abwe | -0.172 |
ipeg | -0.171 |
ortmund | -0.165 |
Token | ICC |
Token ID | 32300 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
uphem | +0.253 |
avail | +0.243 |
abwe | +0.240 |
ipeg | +0.238 |
ortmund | +0.227 |
Neg logit contributions | |
Row | -0.229 |
row | -0.223 |
Legs | -0.218 |
Rodham | -0.217 |
chest | -0.216 |
Token | is |
Token ID | 318 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Row | +0.129 |
row | +0.125 |
Legs | +0.122 |
chest | +0.121 |
Rodham | +0.121 |
Neg logit contributions | |
uphem | -0.151 |
avail | -0.145 |
abwe | -0.144 |
ipeg | -0.143 |
ortmund | -0.138 |
Token | than |
Token ID | 621 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
uphem | +0.720 |
abwe | +0.698 |
avail | +0.686 |
ipeg | +0.685 |
ortmund | +0.648 |
Neg logit contributions | |
Row | -0.595 |
row | -0.572 |
Legs | -0.567 |
Rodham | -0.546 |
chest | -0.546 |
Token | some |
Token ID | 617 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Row | +0.289 |
Legs | +0.279 |
row | +0.278 |
chest | +0.268 |
Guer | +0.264 |
Neg logit contributions | |
uphem | -0.342 |
avail | -0.330 |
abwe | -0.326 |
ipeg | -0.323 |
ortmund | -0.303 |
Token | candidates |
Token ID | 5871 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
uphem | +0.793 |
avail | +0.760 |
abwe | +0.752 |
ipeg | +0.737 |
ortmund | +0.700 |
Neg logit contributions | |
Row | -0.737 |
row | -0.711 |
Legs | -0.706 |
chest | -0.684 |
Guer | -0.677 |
Token | give |
Token ID | 1577 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
uphem | +1.282 |
avail | +1.252 |
abwe | +1.212 |
ipeg | +1.186 |
ortmund | +1.142 |
Neg logit contributions | |
Row | -1.024 |
row | -0.980 |
Legs | -0.967 |
chest | -0.941 |
Guer | -0.921 |
Token | them |
Token ID | 606 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Row | +0.262 |
row | +0.257 |
Legs | +0.250 |
chest | +0.245 |
Rodham | +0.241 |
Neg logit contributions | |
uphem | -0.292 |
avail | -0.280 |
abwe | -0.278 |
ipeg | -0.274 |
ortmund | -0.258 |
Token | credit |
Token ID | 3884 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
uphem | +0.531 |
avail | +0.508 |
abwe | +0.502 |
ipeg | +0.492 |
ortmund | +0.465 |
Neg logit contributions | |
Row | -0.521 |
row | -0.506 |
Legs | -0.494 |
chest | -0.484 |
Rodham | -0.483 |
Token | for |
Token ID | 329 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
uphem | +0.801 |
abwe | +0.772 |
avail | +0.766 |
ipeg | +0.756 |
ortmund | +0.731 |
Neg logit contributions | |
Row | -0.426 |
row | -0.405 |
Legs | -0.399 |
Rodham | -0.383 |
chest | -0.380 |
Token | , |
Token ID | 11 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
uphem | +1.517 |
avail | +1.473 |
abwe | +1.459 |
ipeg | +1.427 |
ortmund | +1.368 |
Neg logit contributions | |
Row | -1.004 |
row | -0.965 |
Legs | -0.955 |
chest | -0.907 |
Guer | -0.894 |
Token | says |
Token ID | 1139 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
uphem | +0.954 |
avail | +0.926 |
abwe | +0.912 |
ipeg | +0.887 |
ortmund | +0.858 |
Neg logit contributions | |
Row | -0.780 |
row | -0.769 |
Legs | -0.756 |
chest | -0.741 |
brim | -0.717 |
Token | Mor |
Token ID | 3461 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
uphem | +0.151 |
abwe | +0.145 |
avail | +0.143 |
ipeg | +0.142 |
ortmund | +0.135 |
Neg logit contributions | |
Row | -0.110 |
row | -0.107 |
Legs | -0.105 |
chest | -0.104 |
brim | -0.101 |
Token | ley |
Token ID | 1636 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
uphem | +0.574 |
abwe | +0.561 |
ipeg | +0.546 |
avail | +0.537 |
ortmund | +0.514 |
Neg logit contributions | |
Row | -0.442 |
Legs | -0.419 |
row | -0.414 |
brim | -0.408 |
Rodham | -0.405 |
Token | with |
Token ID | 351 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
uphem | +1.026 |
abwe | +1.004 |
ipeg | +0.983 |
avail | +0.982 |
ortmund | +0.928 |
Neg logit contributions | |
Row | -0.726 |
row | -0.694 |
Legs | -0.688 |
Rodham | -0.671 |
chest | -0.667 |
Token | $ |
Token ID | 720 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
uphem | +0.469 |
abwe | +0.454 |
avail | +0.451 |
ipeg | +0.445 |
ortmund | +0.421 |
Neg logit contributions | |
Row | -0.385 |
row | -0.377 |
Legs | -0.370 |
Rodham | -0.363 |
chest | -0.359 |
Token | 600 |
Token ID | 8054 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
Row | +0.264 |
row | +0.249 |
Legs | +0.249 |
Rodham | +0.245 |
brim | +0.242 |
Neg logit contributions | |
uphem | -0.308 |
abwe | -0.295 |
avail | -0.293 |
ipeg | -0.291 |
ortmund | -0.278 |
Token | . |
Token ID | 13 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
Row | +0.067 |
row | +0.064 |
Legs | +0.063 |
Rodham | +0.062 |
Guer | +0.061 |
Neg logit contributions | |
uphem | -0.096 |
abwe | -0.092 |
ipeg | -0.091 |
avail | -0.091 |
ortmund | -0.087 |
Token | But |
Token ID | 887 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Row | +0.159 |
row | +0.154 |
Legs | +0.151 |
Rodham | +0.150 |
brim | +0.148 |
Neg logit contributions | |
uphem | -0.162 |
abwe | -0.154 |
ipeg | -0.152 |
avail | -0.151 |
ortmund | -0.144 |
Token | you |
Token ID | 345 |
Feature activation | +5.99e-04 |
Pos logit contributions | |
Row | +0.379 |
row | +0.365 |
Legs | +0.359 |
Rodham | +0.353 |
chest | +0.348 |
Neg logit contributions | |
uphem | -0.489 |
abwe | -0.471 |
avail | -0.468 |
ipeg | -0.465 |
ortmund | -0.444 |
Token | can |
Token ID | 460 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Row | +0.002 |
row | +0.002 |
Legs | +0.002 |
Rodham | +0.002 |
Guer | +0.001 |
Neg logit contributions | |
uphem | -0.002 |
avail | -0.002 |
abwe | -0.002 |
ipeg | -0.002 |
ortmund | -0.002 |
Token | rob |
Token ID | 3857 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
uphem | +0.422 |
avail | +0.407 |
abwe | +0.402 |
ipeg | +0.401 |
ortmund | +0.379 |
Neg logit contributions | |
Row | -0.340 |
row | -0.325 |
Legs | -0.323 |
Rodham | -0.317 |
Guer | -0.313 |
Token | a |
Token ID | 257 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
uphem | +2.093 |
abwe | +1.995 |
avail | +1.994 |
ipeg | +1.972 |
ancies | +1.854 |
Neg logit contributions | |
Row | -2.019 |
row | -1.970 |
Legs | -1.950 |
chest | -1.919 |
Rodham | -1.918 |
Token | credit |
Token ID | 3884 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
uphem | +0.975 |
abwe | +0.936 |
avail | +0.929 |
ipeg | +0.929 |
ortmund | +0.880 |
Neg logit contributions | |
Row | -0.644 |
row | -0.621 |
Legs | -0.613 |
Rodham | -0.593 |
chest | -0.591 |
Token | card |
Token ID | 2657 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
uphem | +1.265 |
abwe | +1.215 |
avail | +1.205 |
ipeg | +1.204 |
ortmund | +1.135 |
Neg logit contributions | |
Row | -1.111 |
Legs | -1.068 |
row | -1.064 |
Rodham | -1.034 |
chest | -1.023 |
Token | clothes |
Token ID | 8242 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
Row | +0.399 |
row | +0.382 |
Legs | +0.370 |
Rodham | +0.363 |
chest | +0.361 |
Neg logit contributions | |
uphem | -0.639 |
avail | -0.611 |
abwe | -0.609 |
ipeg | -0.608 |
ortmund | -0.577 |
Token | ? |
Token ID | 30 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Row | +1.253 |
row | +1.203 |
Legs | +1.177 |
Rodham | +1.151 |
chest | +1.146 |
Neg logit contributions | |
uphem | -1.684 |
abwe | -1.611 |
avail | -1.598 |
ipeg | -1.597 |
ortmund | -1.516 |
Token | That |
Token ID | 1320 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
uphem | +0.528 |
abwe | +0.496 |
avail | +0.495 |
ipeg | +0.492 |
ortmund | +0.474 |
Neg logit contributions | |
Row | -0.412 |
row | -0.411 |
brim | -0.394 |
Rodham | -0.392 |
Legs | -0.391 |
Token | kind |
Token ID | 1611 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
uphem | +0.514 |
avail | +0.483 |
abwe | +0.481 |
ipeg | +0.477 |
ortmund | +0.452 |
Neg logit contributions | |
Row | -0.449 |
row | -0.435 |
Legs | -0.428 |
chest | -0.420 |
Rodham | -0.420 |
Token | of |
Token ID | 286 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
uphem | +0.008 |
abwe | +0.008 |
ipeg | +0.008 |
avail | +0.008 |
ortmund | +0.007 |
Neg logit contributions | |
Row | -0.007 |
row | -0.007 |
Legs | -0.007 |
Rodham | -0.007 |
Guer | -0.007 |
Token | thing |
Token ID | 1517 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
uphem | +1.773 |
avail | +1.675 |
abwe | +1.638 |
ipeg | +1.630 |
ortmund | +1.525 |
Neg logit contributions | |
Row | -1.950 |
row | -1.904 |
Legs | -1.872 |
Rodham | -1.833 |
chest | -1.832 |
Token | was |
Token ID | 373 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
uphem | +2.121 |
avail | +2.032 |
abwe | +1.996 |
ipeg | +1.958 |
ortmund | +1.859 |
Neg logit contributions | |
Row | -1.884 |
Legs | -1.834 |
row | -1.826 |
Rodham | -1.774 |
chest | -1.771 |
Token | absolutely |
Token ID | 5543 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
uphem | +0.974 |
avail | +0.916 |
abwe | +0.909 |
ipeg | +0.901 |
ortmund | +0.839 |
Neg logit contributions | |
Row | -1.031 |
row | -1.017 |
Legs | -0.992 |
chest | -0.974 |
Rodham | -0.973 |
Token | out |
Token ID | 503 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
uphem | +0.718 |
avail | +0.681 |
abwe | +0.663 |
ipeg | +0.661 |
ortmund | +0.611 |
Neg logit contributions | |
Row | -0.950 |
row | -0.938 |
Legs | -0.914 |
chest | -0.898 |
Rodham | -0.896 |
Token | of |
Token ID | 286 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
uphem | +1.228 |
abwe | +1.179 |
ipeg | +1.163 |
avail | +1.155 |
ortmund | +1.104 |
Neg logit contributions | |
Row | -1.029 |
row | -0.986 |
Legs | -0.965 |
Rodham | -0.944 |
chest | -0.941 |
Token | the |
Token ID | 262 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
uphem | +1.032 |
abwe | +0.968 |
avail | +0.966 |
ipeg | +0.957 |
ortmund | +0.906 |
Neg logit contributions | |
Row | -0.852 |
row | -0.851 |
Rodham | -0.821 |
Legs | -0.819 |
chest | -0.796 |
Token | minutes |
Token ID | 2431 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
uphem | +0.559 |
abwe | +0.520 |
avail | +0.518 |
ipeg | +0.513 |
ortmund | +0.472 |
Neg logit contributions | |
Row | -0.913 |
row | -0.889 |
Legs | -0.877 |
Guer | -0.865 |
Rodham | -0.864 |
Token | . |
Token ID | 13 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
uphem | +1.758 |
avail | +1.738 |
abwe | +1.702 |
ipeg | +1.690 |
ortmund | +1.590 |
Neg logit contributions | |
Row | -1.225 |
row | -1.186 |
Legs | -1.173 |
chest | -1.142 |
Rodham | -1.134 |
Token |
|
Token ID | 198 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
uphem | +0.206 |
abwe | +0.197 |
ipeg | +0.194 |
avail | +0.194 |
ortmund | +0.184 |
Neg logit contributions | |
Row | -0.189 |
row | -0.183 |
Legs | -0.179 |
Rodham | -0.176 |
chest | -0.175 |
Token |
|
Token ID | 198 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
Row | +0.260 |
row | +0.251 |
Legs | +0.248 |
Rodham | +0.243 |
brim | +0.243 |
Neg logit contributions | |
uphem | -0.242 |
avail | -0.230 |
ipeg | -0.229 |
abwe | -0.225 |
ortmund | -0.215 |
Token | Real |
Token ID | 15633 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
Row | +0.146 |
row | +0.138 |
Legs | +0.136 |
Rodham | +0.134 |
Guer | +0.132 |
Neg logit contributions | |
uphem | -0.209 |
abwe | -0.199 |
ipeg | -0.198 |
avail | -0.197 |
ortmund | -0.189 |
Token | ising |
Token ID | 1710 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
uphem | +0.129 |
abwe | +0.122 |
avail | +0.121 |
ipeg | +0.121 |
ortmund | +0.116 |
Neg logit contributions | |
Row | -0.122 |
row | -0.118 |
Legs | -0.116 |
Rodham | -0.114 |
Guer | -0.113 |
Token | that |
Token ID | 326 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
uphem | +2.192 |
avail | +2.118 |
ipeg | +2.091 |
abwe | +2.088 |
ortmund | +1.966 |
Neg logit contributions | |
Row | -1.912 |
row | -1.863 |
Legs | -1.839 |
Rodham | -1.806 |
chest | -1.782 |
Token | it |
Token ID | 340 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Row | +0.095 |
row | +0.092 |
Legs | +0.090 |
Rodham | +0.089 |
chest | +0.088 |
Neg logit contributions | |
uphem | -0.109 |
abwe | -0.104 |
avail | -0.103 |
ipeg | -0.103 |
ortmund | -0.097 |
Token | was |
Token ID | 373 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
uphem | +0.548 |
avail | +0.531 |
ipeg | +0.521 |
abwe | +0.520 |
ortmund | +0.493 |
Neg logit contributions | |
Row | -0.501 |
row | -0.486 |
Legs | -0.478 |
Rodham | -0.464 |
chest | -0.463 |
Token | a |
Token ID | 257 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Row | +0.220 |
row | +0.213 |
Legs | +0.208 |
Rodham | +0.204 |
chest | +0.204 |
Neg logit contributions | |
uphem | -0.229 |
abwe | -0.218 |
avail | -0.217 |
ipeg | -0.216 |
ortmund | -0.204 |
Token | " |
Token ID | 366 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
uphem | +0.647 |
avail | +0.615 |
abwe | +0.612 |
ipeg | +0.612 |
ortmund | +0.576 |
Neg logit contributions | |
Row | -0.621 |
row | -0.603 |
Legs | -0.590 |
Rodham | -0.578 |
chest | -0.576 |
Token | temple |
Token ID | 12505 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
Row | +0.187 |
row | +0.181 |
Legs | +0.177 |
Rodham | +0.175 |
chest | +0.173 |
Neg logit contributions | |
uphem | -0.229 |
abwe | -0.222 |
avail | -0.220 |
ipeg | -0.219 |
ortmund | -0.207 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
uphem | +0.124 |
abwe | +0.121 |
avail | +0.119 |
ipeg | +0.118 |
ortmund | +0.114 |
Neg logit contributions | |
Row | -0.078 |
row | -0.074 |
Legs | -0.074 |
Rodham | -0.072 |
chest | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
uphem | +0.046 |
abwe | +0.044 |
ipeg | +0.044 |
avail | +0.044 |
ortmund | +0.042 |
Neg logit contributions | |
Row | -0.036 |
row | -0.035 |
Legs | -0.034 |
Rodham | -0.034 |
chest | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
uphem | +0.446 |
avail | +0.424 |
ipeg | +0.422 |
abwe | +0.409 |
ortmund | +0.397 |
Neg logit contributions | |
Row | -0.507 |
row | -0.490 |
Legs | -0.486 |
brim | -0.481 |
Rodham | -0.478 |
Token | V |
Token ID | 53 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
uphem | +0.776 |
ipeg | +0.743 |
abwe | +0.739 |
avail | +0.735 |
ortmund | +0.706 |
Neg logit contributions | |
Row | -0.538 |
row | -0.506 |
Legs | -0.505 |
Rodham | -0.498 |
Guer | -0.491 |
Token | ish |
Token ID | 680 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
Row | +0.929 |
row | +0.894 |
Legs | +0.882 |
Rodham | +0.866 |
Guer | +0.860 |
Neg logit contributions | |
uphem | -0.864 |
abwe | -0.824 |
ipeg | -0.813 |
avail | -0.805 |
ortmund | -0.766 |
Token | nu |
Token ID | 28803 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
uphem | +2.212 |
abwe | +2.097 |
ipeg | +2.077 |
avail | +2.029 |
ortmund | +1.959 |
Neg logit contributions | |
Row | -2.109 |
Rodham | -1.992 |
Legs | -1.992 |
row | -1.988 |
Guer | -1.927 |
Token | at |
Token ID | 379 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
Row | +0.415 |
row | +0.401 |
Legs | +0.391 |
Rodham | +0.385 |
chest | +0.384 |
Neg logit contributions | |
uphem | -0.540 |
abwe | -0.521 |
ipeg | -0.516 |
avail | -0.514 |
ortmund | -0.490 |
Token | Va |
Token ID | 17668 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
Row | +0.146 |
row | +0.140 |
Legs | +0.137 |
Rodham | +0.135 |
chest | +0.133 |
Neg logit contributions | |
uphem | -0.182 |
abwe | -0.175 |
ipeg | -0.173 |
avail | -0.172 |
ortmund | -0.164 |
Token | ik |
Token ID | 1134 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
uphem | +0.253 |
abwe | +0.241 |
ipeg | +0.237 |
avail | +0.234 |
ortmund | +0.223 |
Neg logit contributions | |
Row | -0.281 |
row | -0.270 |
Legs | -0.267 |
Rodham | -0.263 |
chest | -0.261 |
Token | unta |
Token ID | 44424 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
uphem | +0.232 |
abwe | +0.223 |
ipeg | +0.220 |
avail | +0.218 |
ortmund | +0.209 |
Neg logit contributions | |
Row | -0.185 |
row | -0.177 |
Legs | -0.174 |
Rodham | -0.172 |
Guer | -0.170 |
Token | of |
Token ID | 286 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
Row | +0.223 |
row | +0.213 |
Legs | +0.209 |
Rodham | +0.204 |
chest | +0.203 |
Neg logit contributions | |
uphem | -0.287 |
abwe | -0.275 |
ipeg | -0.272 |
avail | -0.270 |
ortmund | -0.259 |
Token | alone |
Token ID | 3436 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
Row | +0.181 |
row | +0.176 |
Legs | +0.172 |
chest | +0.169 |
Rodham | +0.168 |
Neg logit contributions | |
uphem | -0.215 |
abwe | -0.206 |
avail | -0.204 |
ipeg | -0.202 |
ortmund | -0.192 |
Token | to |
Token ID | 284 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Row | +1.146 |
row | +1.092 |
Legs | +1.070 |
Rodham | +1.039 |
chest | +1.035 |
Neg logit contributions | |
uphem | -1.858 |
abwe | -1.797 |
avail | -1.773 |
ipeg | -1.773 |
ortmund | -1.695 |
Token | the |
Token ID | 262 |
Feature activation | -4.95e-03 |
Pos logit contributions | |
Row | +1.097 |
row | +1.060 |
Legs | +1.040 |
Rodham | +1.017 |
chest | +1.017 |
Neg logit contributions | |
uphem | -1.059 |
abwe | -1.009 |
avail | -0.997 |
ipeg | -0.994 |
ortmund | -0.939 |
Token | tender |
Token ID | 15403 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
uphem | +0.015 |
avail | +0.014 |
abwe | +0.014 |
ipeg | +0.014 |
ortmund | +0.013 |
Neg logit contributions | |
Row | -0.013 |
row | -0.013 |
Legs | -0.013 |
chest | -0.013 |
Rodham | -0.013 |
Token | merc |
Token ID | 11991 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
uphem | +0.968 |
avail | +0.917 |
abwe | +0.915 |
ipeg | +0.908 |
ortmund | +0.852 |
Neg logit contributions | |
Row | -1.030 |
row | -0.997 |
Legs | -0.973 |
Rodham | -0.950 |
Guer | -0.948 |
Token | ies |
Token ID | 444 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
uphem | +3.145 |
ipeg | +3.002 |
avail | +2.977 |
abwe | +2.957 |
ancies | +2.840 |
Neg logit contributions | |
Row | -2.702 |
row | -2.582 |
Legs | -2.559 |
Rodham | -2.530 |
Guer | -2.520 |
Token | of |
Token ID | 286 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
uphem | +0.222 |
abwe | +0.214 |
ipeg | +0.211 |
avail | +0.208 |
ortmund | +0.200 |
Neg logit contributions | |
Row | -0.177 |
row | -0.169 |
Legs | -0.165 |
Rodham | -0.161 |
Guer | -0.160 |
Token | incomp |
Token ID | 13352 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
uphem | +0.223 |
abwe | +0.214 |
avail | +0.211 |
ipeg | +0.210 |
ortmund | +0.199 |
Neg logit contributions | |
Row | -0.187 |
row | -0.181 |
Legs | -0.177 |
chest | -0.174 |
Rodham | -0.173 |
Token | ent |
Token ID | 298 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
uphem | +1.380 |
abwe | +1.324 |
ipeg | +1.298 |
avail | +1.289 |
ortmund | +1.214 |
Neg logit contributions | |
Row | -1.524 |
Legs | -1.453 |
row | -1.448 |
Guer | -1.421 |
Rodham | -1.412 |
Token | fake |
Token ID | 8390 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
uphem | +0.147 |
abwe | +0.140 |
ipeg | +0.138 |
avail | +0.137 |
ortmund | +0.130 |
Neg logit contributions | |
Row | -0.159 |
row | -0.153 |
Legs | -0.151 |
Rodham | -0.148 |
Guer | -0.147 |
Token | amounts |
Token ID | 6867 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
uphem | +1.200 |
avail | +1.179 |
ipeg | +1.162 |
abwe | +1.149 |
ancies | +1.080 |
Neg logit contributions | |
Row | -1.221 |
Legs | -1.183 |
row | -1.179 |
chest | -1.147 |
Rodham | -1.132 |
Token | of |
Token ID | 286 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Row | +0.118 |
row | +0.113 |
Legs | +0.111 |
Rodham | +0.109 |
chest | +0.108 |
Neg logit contributions | |
uphem | -0.137 |
abwe | -0.131 |
ipeg | -0.129 |
avail | -0.129 |
ortmund | -0.123 |
Token | marijuana |
Token ID | 5727 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
uphem | +0.991 |
avail | +0.976 |
ipeg | +0.944 |
abwe | +0.939 |
Trojan | +0.892 |
Neg logit contributions | |
Row | -0.915 |
row | -0.905 |
Legs | -0.901 |
chest | -0.878 |
brim | -0.847 |
Token | for |
Token ID | 329 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
uphem | +0.507 |
avail | +0.495 |
ipeg | +0.487 |
abwe | +0.484 |
ancies | +0.458 |
Neg logit contributions | |
Row | -0.339 |
Legs | -0.324 |
row | -0.318 |
chest | -0.316 |
Rodham | -0.306 |
Token | personal |
Token ID | 2614 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
uphem | +0.207 |
avail | +0.200 |
ipeg | +0.195 |
abwe | +0.193 |
ancies | +0.181 |
Neg logit contributions | |
Row | -0.252 |
Legs | -0.245 |
row | -0.244 |
chest | -0.242 |
Rodham | -0.237 |
Token | use |
Token ID | 779 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
uphem | +0.745 |
avail | +0.722 |
ipeg | +0.690 |
abwe | +0.685 |
ancies | +0.636 |
Neg logit contributions | |
Row | -1.547 |
Legs | -1.517 |
row | -1.507 |
chest | -1.488 |
Rodham | -1.468 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
uphem | +3.193 |
avail | +3.157 |
abwe | +3.062 |
ipeg | +3.026 |
ancies | +2.917 |
Neg logit contributions | |
Row | -2.312 |
Legs | -2.246 |
chest | -2.235 |
row | -2.188 |
brim | -2.127 |
Token |
|
Token ID | 198 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
uphem | +0.412 |
abwe | +0.394 |
ipeg | +0.389 |
avail | +0.385 |
ortmund | +0.367 |
Neg logit contributions | |
Row | -0.376 |
row | -0.364 |
Legs | -0.355 |
chest | -0.349 |
brim | -0.349 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
uphem | +0.223 |
avail | +0.214 |
ipeg | +0.211 |
abwe | +0.205 |
ortmund | +0.198 |
Neg logit contributions | |
Row | -0.258 |
row | -0.250 |
Legs | -0.247 |
brim | -0.245 |
Rodham | -0.243 |
Token | " |
Token ID | 1 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
uphem | +0.479 |
ipeg | +0.455 |
abwe | +0.453 |
avail | +0.448 |
ortmund | +0.429 |
Neg logit contributions | |
Row | -0.321 |
Legs | -0.302 |
row | -0.298 |
brim | -0.296 |
Rodham | -0.291 |
Token | We |
Token ID | 1135 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
uphem | +0.303 |
ipeg | +0.289 |
avail | +0.287 |
abwe | +0.284 |
ortmund | +0.272 |
Neg logit contributions | |
Row | -0.218 |
brim | -0.207 |
Legs | -0.207 |
row | -0.207 |
Rodham | -0.202 |