Token | Donald |
Token ID | 3759 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ASC | +0.640 |
Agric | +0.565 |
eur | +0.564 |
Ribbon | +0.558 |
PLA | +0.556 |
Neg logit contributions | |
anasia | -0.505 |
vas | -0.464 |
Bengals | -0.446 |
[* | -0.442 |
cius | -0.436 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
anasia | +0.953 |
vas | +0.875 |
Bengals | +0.847 |
[* | +0.830 |
cius | +0.806 |
Neg logit contributions | |
ASC | -1.415 |
eur | -1.256 |
Agric | -1.251 |
PLA | -1.243 |
Ribbon | -1.239 |
Token | Donald |
Token ID | 3759 |
Feature activation | -6.64e-03 |
Pos logit contributions | |
anasia | +0.684 |
vas | +0.632 |
Bengals | +0.612 |
[* | +0.603 |
cius | +0.591 |
Neg logit contributions | |
ASC | -0.871 |
eur | -0.768 |
Agric | -0.766 |
PLA | -0.757 |
Ribbon | -0.757 |
Token | John |
Token ID | 1757 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
anasia | +0.003 |
vas | +0.003 |
Bengals | +0.003 |
[* | +0.003 |
cius | +0.003 |
Neg logit contributions | |
ASC | -0.007 |
Agric | -0.006 |
eur | -0.006 |
PLA | -0.006 |
Ribbon | -0.006 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ASC | +1.544 |
eur | +1.370 |
Agric | +1.363 |
Ribbon | +1.349 |
orate | +1.347 |
Neg logit contributions | |
anasia | -1.152 |
vas | -1.054 |
Bengals | -1.020 |
[* | -1.007 |
cius | -0.994 |
Token | READ |
Token ID | 15675 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
ASC | +1.707 |
eur | +1.494 |
PLA | +1.486 |
Agric | +1.477 |
Ribbon | +1.456 |
Neg logit contributions | |
anasia | -1.441 |
vas | -1.345 |
Bengals | -1.301 |
[* | -1.286 |
cius | -1.265 |
Token | : |
Token ID | 25 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ASC | +3.916 |
orate | +3.347 |
Ribbon | +3.304 |
PLA | +3.289 |
parity | +3.263 |
Neg logit contributions | |
anasia | -4.578 |
vas | -4.200 |
cius | -4.114 |
Bengals | -4.022 |
[* | -4.016 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
anasia | +0.211 |
vas | +0.198 |
Bengals | +0.192 |
[* | +0.189 |
cius | +0.183 |
Neg logit contributions | |
ASC | -0.253 |
eur | -0.223 |
Agric | -0.221 |
orate | -0.219 |
Ribbon | -0.218 |
Token | testimony |
Token ID | 9709 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
ASC | +0.042 |
eur | +0.037 |
Agric | +0.037 |
Ribbon | +0.036 |
PLA | +0.036 |
Neg logit contributions | |
anasia | -0.034 |
vas | -0.032 |
Bengals | -0.031 |
[* | -0.030 |
cius | -0.030 |
Token | alleges |
Token ID | 24763 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
anasia | +0.454 |
vas | +0.421 |
Bengals | +0.411 |
[* | +0.402 |
cius | +0.391 |
Neg logit contributions | |
ASC | -0.623 |
eur | -0.555 |
Agric | -0.553 |
Ribbon | -0.543 |
orate | -0.543 |
Token | Trump |
Token ID | 1301 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
anasia | +0.286 |
vas | +0.262 |
Bengals | +0.255 |
[* | +0.252 |
cius | +0.247 |
Neg logit contributions | |
ASC | -0.323 |
eur | -0.281 |
Agric | -0.281 |
Ribbon | -0.278 |
PLA | -0.277 |
Token | 64 |
Token ID | 2414 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
ASC | +0.177 |
eur | +0.152 |
Agric | +0.152 |
Ribbon | +0.150 |
PLA | +0.150 |
Neg logit contributions | |
anasia | -0.193 |
vas | -0.181 |
Bengals | -0.176 |
[* | -0.174 |
cius | -0.171 |
Token | 406 |
Token ID | 29703 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ASC | +1.440 |
eur | +1.220 |
Agric | +1.214 |
Ribbon | +1.199 |
PLA | +1.197 |
Neg logit contributions | |
anasia | -1.785 |
vas | -1.673 |
Bengals | -1.627 |
[* | -1.613 |
cius | -1.602 |
Token | Mem |
Token ID | 4942 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ASC | +0.985 |
eur | +0.856 |
Agric | +0.854 |
Ribbon | +0.846 |
PLA | +0.844 |
Neg logit contributions | |
anasia | -0.897 |
vas | -0.829 |
Bengals | -0.801 |
[* | -0.793 |
cius | -0.787 |
Token | c |
Token ID | 66 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
ASC | +1.453 |
eur | +1.246 |
Agric | +1.224 |
PLA | +1.213 |
orate | +1.212 |
Neg logit contributions | |
anasia | -1.758 |
vas | -1.654 |
Bengals | -1.610 |
[* | -1.580 |
cius | -1.554 |
Token | py |
Token ID | 9078 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ASC | +1.111 |
eur | +0.955 |
Agric | +0.947 |
PLA | +0.938 |
orate | +0.935 |
Neg logit contributions | |
anasia | -1.294 |
vas | -1.215 |
Bengals | -1.184 |
[* | -1.167 |
cius | -1.149 |
Token | Reading |
Token ID | 36120 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
anasia | +0.091 |
vas | +0.085 |
Bengals | +0.083 |
[* | +0.082 |
cius | +0.081 |
Neg logit contributions | |
ASC | -0.077 |
eur | -0.066 |
Agric | -0.066 |
Ribbon | -0.065 |
PLA | -0.065 |
Token | 55 |
Token ID | 5996 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
ASC | +4.126 |
Ribbon | +3.521 |
eur | +3.517 |
Agric | +3.511 |
orate | +3.496 |
Neg logit contributions | |
anasia | -3.899 |
vas | -3.624 |
Bengals | -3.502 |
cius | -3.433 |
[* | -3.421 |
Token | 80 |
Token ID | 1795 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ASC | +1.741 |
eur | +1.478 |
Agric | +1.475 |
Ribbon | +1.459 |
PLA | +1.456 |
Neg logit contributions | |
anasia | -2.058 |
vas | -1.924 |
Bengals | -1.861 |
[* | -1.851 |
cius | -1.841 |
Token | 953 |
Token ID | 49649 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
ASC | +1.165 |
eur | +0.983 |
Agric | +0.982 |
Ribbon | +0.967 |
PLA | +0.966 |
Neg logit contributions | |
anasia | -1.505 |
vas | -1.414 |
Bengals | -1.372 |
[* | -1.361 |
cius | -1.352 |
Token | 16 |
Token ID | 1467 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
ASC | +0.750 |
eur | +0.654 |
Agric | +0.654 |
Ribbon | +0.645 |
PLA | +0.643 |
Neg logit contributions | |
anasia | -0.696 |
vas | -0.645 |
Bengals | -0.623 |
[* | -0.615 |
cius | -0.609 |
Token | 27 |
Token ID | 1983 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ASC | +0.223 |
eur | +0.189 |
Agric | +0.188 |
Ribbon | +0.185 |
PLA | +0.185 |
Neg logit contributions | |
anasia | -0.296 |
vas | -0.278 |
Bengals | -0.272 |
[* | -0.268 |
cius | -0.265 |
Token | Donald |
Token ID | 3759 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
anasia | +0.124 |
vas | +0.109 |
Bengals | +0.103 |
[* | +0.101 |
cius | +0.098 |
Neg logit contributions | |
ASC | -0.313 |
eur | -0.284 |
Agric | -0.283 |
Ribbon | -0.281 |
PLA | -0.281 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
anasia | +0.219 |
vas | +0.201 |
Bengals | +0.195 |
[* | +0.192 |
cius | +0.186 |
Neg logit contributions | |
ASC | -0.317 |
eur | -0.281 |
Agric | -0.280 |
PLA | -0.278 |
Ribbon | -0.277 |
Token | Donald |
Token ID | 3759 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ASC | +0.251 |
eur | +0.228 |
Agric | +0.228 |
PLA | +0.226 |
Ribbon | +0.226 |
Neg logit contributions | |
anasia | -0.097 |
vas | -0.085 |
Bengals | -0.080 |
[* | -0.078 |
cius | -0.076 |
Token | John |
Token ID | 1757 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
ASC | +1.460 |
eur | +1.312 |
Agric | +1.297 |
Ribbon | +1.293 |
orate | +1.293 |
Neg logit contributions | |
anasia | -0.818 |
vas | -0.743 |
Bengals | -0.703 |
[* | -0.695 |
cius | -0.691 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
ASC | +1.975 |
eur | +1.753 |
Agric | +1.743 |
Ribbon | +1.727 |
orate | +1.725 |
Neg logit contributions | |
anasia | -1.476 |
vas | -1.351 |
Bengals | -1.308 |
[* | -1.290 |
cius | -1.274 |
Token | House |
Token ID | 18102 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
ASC | +2.369 |
PLA | +2.067 |
eur | +2.058 |
Agric | +2.030 |
orate | +2.009 |
Neg logit contributions | |
anasia | -2.039 |
vas | -1.913 |
Bengals | -1.847 |
[* | -1.828 |
cius | -1.802 |
Token | committee |
Token ID | 5583 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ASC | +4.568 |
eur | +4.035 |
Agric | +4.032 |
Ribbon | +3.989 |
PLA | +3.984 |
Neg logit contributions | |
anasia | -3.441 |
vas | -3.160 |
Bengals | -3.053 |
[* | -3.016 |
cius | -2.967 |
Token | believes |
Token ID | 5804 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
anasia | +0.633 |
vas | +0.598 |
Bengals | +0.595 |
[* | +0.565 |
cius | +0.537 |
Neg logit contributions | |
ASC | -0.980 |
eur | -0.878 |
Agric | -0.869 |
Ribbon | -0.859 |
PLA | -0.849 |
Token | it |
Token ID | 340 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
anasia | +0.272 |
vas | +0.250 |
Bengals | +0.244 |
[* | +0.237 |
cius | +0.231 |
Neg logit contributions | |
ASC | -0.371 |
eur | -0.328 |
Agric | -0.326 |
PLA | -0.325 |
Ribbon | -0.325 |
Token | has |
Token ID | 468 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ASC | +0.561 |
eur | +0.486 |
Agric | +0.484 |
PLA | +0.478 |
Ribbon | +0.477 |
Neg logit contributions | |
anasia | -0.584 |
vas | -0.546 |
Bengals | -0.532 |
[* | -0.524 |
cius | -0.515 |
Token | evidence |
Token ID | 2370 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
ASC | +0.313 |
eur | +0.266 |
Agric | +0.265 |
Ribbon | +0.262 |
PLA | +0.260 |
Neg logit contributions | |
anasia | -0.385 |
vas | -0.361 |
Bengals | -0.352 |
[* | -0.348 |
cius | -0.343 |
Token | Donald |
Token ID | 3759 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
anasia | +0.747 |
vas | +0.689 |
Bengals | +0.667 |
[* | +0.655 |
cius | +0.642 |
Neg logit contributions | |
ASC | -1.006 |
eur | -0.891 |
Agric | -0.886 |
PLA | -0.878 |
Ribbon | -0.877 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
anasia | +0.865 |
vas | +0.794 |
Bengals | +0.769 |
[* | +0.754 |
cius | +0.735 |
Neg logit contributions | |
ASC | -1.252 |
eur | -1.111 |
Agric | -1.107 |
PLA | -1.098 |
Ribbon | -1.095 |
Token | Donald |
Token ID | 3759 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
anasia | +0.319 |
vas | +0.294 |
Bengals | +0.284 |
[* | +0.279 |
cius | +0.274 |
Neg logit contributions | |
ASC | -0.434 |
eur | -0.384 |
Agric | -0.383 |
PLA | -0.379 |
Ribbon | -0.379 |
Token | John |
Token ID | 1757 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ASC | +0.799 |
eur | +0.719 |
Agric | +0.719 |
PLA | +0.712 |
Ribbon | +0.711 |
Neg logit contributions | |
anasia | -0.405 |
vas | -0.364 |
Bengals | -0.350 |
[* | -0.341 |
cius | -0.331 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ASC | +2.089 |
eur | +1.855 |
Agric | +1.842 |
Ribbon | +1.828 |
orate | +1.823 |
Neg logit contributions | |
anasia | -1.622 |
vas | -1.477 |
Bengals | -1.433 |
[* | -1.419 |
cius | -1.409 |
Token | House |
Token ID | 18102 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
ASC | +2.076 |
PLA | +1.812 |
eur | +1.810 |
Agric | +1.789 |
orate | +1.766 |
Neg logit contributions | |
anasia | -1.793 |
vas | -1.676 |
Bengals | -1.622 |
[* | -1.610 |
cius | -1.580 |
Token | committee |
Token ID | 5583 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
ASC | +4.447 |
eur | +3.930 |
Agric | +3.924 |
Ribbon | +3.884 |
PLA | +3.880 |
Neg logit contributions | |
anasia | -3.324 |
vas | -3.052 |
Bengals | -2.948 |
[* | -2.912 |
cius | -2.863 |
Token | believes |
Token ID | 5804 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
anasia | +0.262 |
vas | +0.246 |
Bengals | +0.244 |
[* | +0.234 |
cius | +0.222 |
Neg logit contributions | |
ASC | -0.391 |
Agric | -0.348 |
eur | -0.347 |
Ribbon | -0.341 |
PLA | -0.338 |
Token | it |
Token ID | 340 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
ASC | +0.177 |
eur | +0.157 |
Agric | +0.156 |
PLA | +0.156 |
Ribbon | +0.156 |
Neg logit contributions | |
anasia | -0.119 |
vas | -0.109 |
Bengals | -0.105 |
[* | -0.103 |
cius | -0.100 |
Token | has |
Token ID | 468 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ASC | +0.782 |
eur | +0.685 |
Agric | +0.684 |
PLA | +0.677 |
Ribbon | +0.673 |
Neg logit contributions | |
anasia | -0.687 |
vas | -0.641 |
Bengals | -0.623 |
[* | -0.609 |
cius | -0.596 |
Token | evidence |
Token ID | 2370 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
ASC | +0.329 |
eur | +0.282 |
Agric | +0.280 |
PLA | +0.277 |
Ribbon | +0.275 |
Neg logit contributions | |
anasia | -0.394 |
vas | -0.370 |
Bengals | -0.361 |
[* | -0.356 |
cius | -0.350 |
Token | . |
Token ID | 13 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
ASC | +0.639 |
eur | +0.559 |
Agric | +0.557 |
Ribbon | +0.555 |
PLA | +0.554 |
Neg logit contributions | |
anasia | -0.567 |
vas | -0.524 |
Bengals | -0.508 |
[* | -0.499 |
cius | -0.497 |
Token |
|
Token ID | 198 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
anasia | +0.335 |
vas | +0.310 |
Bengals | +0.300 |
[* | +0.295 |
cius | +0.292 |
Neg logit contributions | |
ASC | -0.398 |
eur | -0.350 |
Agric | -0.349 |
Ribbon | -0.345 |
PLA | -0.345 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
anasia | +0.013 |
vas | +0.012 |
Bengals | +0.011 |
[* | +0.011 |
cius | +0.011 |
Neg logit contributions | |
ASC | -0.020 |
eur | -0.018 |
Agric | -0.018 |
Ribbon | -0.018 |
PLA | -0.018 |
Token | Article |
Token ID | 14906 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
anasia | +0.117 |
vas | +0.109 |
Bengals | +0.106 |
[* | +0.104 |
cius | +0.102 |
Neg logit contributions | |
ASC | -0.124 |
eur | -0.108 |
Agric | -0.108 |
PLA | -0.107 |
Ribbon | -0.106 |
Token | Continued |
Token ID | 22168 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
anasia | +3.070 |
vas | +2.931 |
Bengals | +2.871 |
[* | +2.768 |
cius | +2.682 |
Neg logit contributions | |
ASC | -3.182 |
Ribbon | -2.718 |
orate | -2.689 |
Agric | -2.684 |
PLA | -2.660 |
Token | Below |
Token ID | 10383 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
ASC | +0.555 |
eur | +0.493 |
Agric | +0.493 |
Ribbon | +0.487 |
PLA | +0.485 |
Neg logit contributions | |
anasia | -0.394 |
vas | -0.361 |
Bengals | -0.344 |
cius | -0.341 |
[* | -0.340 |
Token |
|
Token ID | 198 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ASC | +3.863 |
eur | +3.433 |
PLA | +3.343 |
Agric | +3.326 |
Ribbon | +3.311 |
Neg logit contributions | |
anasia | -3.276 |
vas | -3.025 |
cius | -2.906 |
Bengals | -2.852 |
[* | -2.825 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ASC | +1.160 |
eur | +1.035 |
Agric | +1.024 |
PLA | +1.015 |
Ribbon | +1.013 |
Neg logit contributions | |
anasia | -0.819 |
vas | -0.750 |
Bengals | -0.720 |
[* | -0.707 |
cius | -0.706 |
Token | The |
Token ID | 464 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
ASC | +0.787 |
eur | +0.684 |
PLA | +0.677 |
Agric | +0.674 |
orate | +0.664 |
Neg logit contributions | |
anasia | -0.746 |
vas | -0.698 |
Bengals | -0.676 |
[* | -0.662 |
cius | -0.658 |
Token | T |
Token ID | 309 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ASC | +0.075 |
eur | +0.066 |
Agric | +0.066 |
PLA | +0.065 |
Ribbon | +0.065 |
Neg logit contributions | |
anasia | -0.060 |
vas | -0.055 |
Bengals | -0.053 |
[* | -0.053 |
cius | -0.052 |
Token | PA |
Token ID | 4537 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ASC | +0.124 |
eur | +0.095 |
Agric | +0.095 |
Ribbon | +0.092 |
orate | +0.091 |
Neg logit contributions | |
anasia | -0.328 |
vas | -0.312 |
Bengals | -0.306 |
[* | -0.304 |
cius | -0.300 |
Token | ) |
Token ID | 8 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
anasia | +0.081 |
vas | +0.076 |
Bengals | +0.074 |
[* | +0.073 |
cius | +0.072 |
Neg logit contributions | |
ASC | -0.074 |
eur | -0.064 |
Agric | -0.064 |
PLA | -0.063 |
Ribbon | -0.063 |
Token | that |
Token ID | 326 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
anasia | +0.123 |
vas | +0.114 |
Bengals | +0.111 |
[* | +0.109 |
cius | +0.107 |
Neg logit contributions | |
ASC | -0.143 |
eur | -0.126 |
Agric | -0.125 |
Ribbon | -0.124 |
PLA | -0.124 |
Token | tore |
Token ID | 26197 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
anasia | +0.195 |
vas | +0.182 |
Bengals | +0.176 |
[* | +0.173 |
cius | +0.170 |
Neg logit contributions | |
ASC | -0.228 |
eur | -0.200 |
Agric | -0.199 |
PLA | -0.197 |
Ribbon | -0.197 |
Token | the |
Token ID | 262 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ASC | +0.976 |
eur | +0.852 |
Agric | +0.851 |
Ribbon | +0.837 |
orate | +0.835 |
Neg logit contributions | |
anasia | -0.940 |
vas | -0.866 |
Bengals | -0.841 |
[* | -0.830 |
cius | -0.828 |
Token | country |
Token ID | 1499 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
ASC | +0.092 |
eur | +0.080 |
Agric | +0.079 |
PLA | +0.078 |
Ribbon | +0.078 |
Neg logit contributions | |
anasia | -0.097 |
vas | -0.091 |
Bengals | -0.088 |
[* | -0.087 |
cius | -0.086 |
Token | apart |
Token ID | 5475 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
ASC | +0.378 |
eur | +0.318 |
Agric | +0.316 |
Ribbon | +0.311 |
PLA | +0.311 |
Neg logit contributions | |
anasia | -0.539 |
vas | -0.508 |
Bengals | -0.496 |
[* | -0.490 |
cius | -0.484 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ASC | +3.449 |
eur | +3.035 |
Agric | +3.022 |
orate | +2.963 |
parity | +2.961 |
Neg logit contributions | |
anasia | -3.567 |
vas | -3.296 |
Bengals | -3.238 |
cius | -3.226 |
[* | -3.136 |
Token | Likewise |
Token ID | 22660 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
ASC | +0.101 |
eur | +0.088 |
Agric | +0.088 |
Ribbon | +0.087 |
PLA | +0.087 |
Neg logit contributions | |
anasia | -0.087 |
vas | -0.080 |
Bengals | -0.078 |
[* | -0.076 |
cius | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
anasia | +0.254 |
vas | +0.235 |
Bengals | +0.228 |
[* | +0.224 |
cius | +0.220 |
Neg logit contributions | |
ASC | -0.313 |
eur | -0.276 |
Agric | -0.274 |
Ribbon | -0.271 |
PLA | -0.271 |
Token | the |
Token ID | 262 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
anasia | +0.497 |
vas | +0.461 |
Bengals | +0.447 |
[* | +0.440 |
cius | +0.433 |
Neg logit contributions | |
ASC | -0.568 |
eur | -0.498 |
Agric | -0.495 |
PLA | -0.490 |
Ribbon | -0.490 |
Token | neoliberal |
Token ID | 31972 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ASC | +0.109 |
eur | +0.096 |
Agric | +0.095 |
Ribbon | +0.094 |
PLA | +0.094 |
Neg logit contributions | |
anasia | -0.101 |
vas | -0.094 |
Bengals | -0.091 |
[* | -0.090 |
cius | -0.089 |
Token | President |
Token ID | 1992 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
ASC | +1.989 |
Agric | +1.760 |
eur | +1.758 |
Ribbon | +1.745 |
parity | +1.745 |
Neg logit contributions | |
anasia | -1.658 |
vas | -1.511 |
[* | -1.449 |
cius | -1.444 |
Bengals | -1.443 |
Token | Trump |
Token ID | 1301 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
anasia | +0.341 |
vas | +0.312 |
Bengals | +0.301 |
[* | +0.295 |
cius | +0.291 |
Neg logit contributions | |
ASC | -0.507 |
eur | -0.452 |
Agric | -0.450 |
Ribbon | -0.446 |
orate | -0.444 |
Token | Donald |
Token ID | 3759 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
anasia | +0.258 |
vas | +0.239 |
Bengals | +0.231 |
[* | +0.228 |
cius | +0.223 |
Neg logit contributions | |
ASC | -0.320 |
Agric | -0.281 |
eur | -0.281 |
PLA | -0.278 |
Ribbon | -0.278 |
Token | John |
Token ID | 1757 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
anasia | +0.235 |
vas | +0.208 |
Bengals | +0.203 |
[* | +0.196 |
cius | +0.186 |
Neg logit contributions | |
ASC | -0.513 |
Agric | -0.467 |
eur | -0.464 |
PLA | -0.464 |
Ribbon | -0.459 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
ASC | +1.349 |
eur | +1.197 |
Agric | +1.190 |
Ribbon | +1.179 |
orate | +1.177 |
Neg logit contributions | |
anasia | -1.008 |
vas | -0.923 |
Bengals | -0.895 |
[* | -0.884 |
cius | -0.871 |
Token | House |
Token ID | 18102 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
ASC | +1.752 |
eur | +1.524 |
PLA | +1.518 |
Agric | +1.499 |
orate | +1.486 |
Neg logit contributions | |
anasia | -1.533 |
vas | -1.437 |
Bengals | -1.392 |
[* | -1.372 |
cius | -1.346 |
Token | committee |
Token ID | 5583 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
ASC | +4.022 |
Agric | +3.551 |
eur | +3.549 |
Ribbon | +3.513 |
PLA | +3.508 |
Neg logit contributions | |
anasia | -3.019 |
vas | -2.770 |
Bengals | -2.673 |
[* | -2.648 |
cius | -2.604 |
Token | believes |
Token ID | 5804 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
anasia | +0.481 |
Bengals | +0.450 |
vas | +0.450 |
[* | +0.428 |
cius | +0.417 |
Neg logit contributions | |
ASC | -0.725 |
Agric | -0.643 |
eur | -0.641 |
Ribbon | -0.631 |
PLA | -0.629 |
Token | it |
Token ID | 340 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
ASC | +0.025 |
eur | +0.022 |
Agric | +0.022 |
PLA | +0.022 |
Ribbon | +0.022 |
Neg logit contributions | |
anasia | -0.017 |
vas | -0.015 |
Bengals | -0.015 |
[* | -0.015 |
cius | -0.014 |
Token | has |
Token ID | 468 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
ASC | +0.558 |
Agric | +0.485 |
eur | +0.484 |
PLA | +0.481 |
Ribbon | +0.474 |
Neg logit contributions | |
anasia | -0.553 |
vas | -0.521 |
Bengals | -0.509 |
[* | -0.495 |
cius | -0.484 |
Token | evidence |
Token ID | 2370 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
ASC | +0.468 |
eur | +0.401 |
Agric | +0.398 |
PLA | +0.394 |
Ribbon | +0.392 |
Neg logit contributions | |
anasia | -0.566 |
vas | -0.532 |
Bengals | -0.519 |
[* | -0.512 |
cius | -0.504 |
Token | seriously |
Token ID | 6411 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
anasia | +0.372 |
vas | +0.344 |
Bengals | +0.333 |
[* | +0.328 |
cius | +0.323 |
Neg logit contributions | |
ASC | -0.448 |
eur | -0.395 |
Agric | -0.393 |
Ribbon | -0.388 |
PLA | -0.387 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ASC | +0.183 |
eur | +0.161 |
Agric | +0.161 |
Ribbon | +0.159 |
PLA | +0.159 |
Neg logit contributions | |
anasia | -0.149 |
vas | -0.137 |
Bengals | -0.133 |
[* | -0.131 |
cius | -0.129 |
Token |
|
Token ID | 198 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ASC | +0.212 |
eur | +0.189 |
Agric | +0.188 |
PLA | +0.186 |
Ribbon | +0.186 |
Neg logit contributions | |
anasia | -0.142 |
vas | -0.130 |
Bengals | -0.125 |
[* | -0.123 |
cius | -0.121 |
Token | Article |
Token ID | 14906 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
anasia | +0.188 |
vas | +0.174 |
Bengals | +0.169 |
[* | +0.167 |
cius | +0.164 |
Neg logit contributions | |
ASC | -0.209 |
eur | -0.183 |
Agric | -0.182 |
Ribbon | -0.180 |
PLA | -0.180 |
Token | Continued |
Token ID | 22168 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
anasia | +2.524 |
vas | +2.408 |
Bengals | +2.387 |
[* | +2.235 |
cius | +2.235 |
Neg logit contributions | |
ASC | -2.818 |
orate | -2.406 |
Agric | -2.406 |
Ribbon | -2.387 |
PLA | -2.367 |
Token | Below |
Token ID | 10383 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
ASC | +0.504 |
eur | +0.447 |
Agric | +0.446 |
Ribbon | +0.441 |
PLA | +0.440 |
Neg logit contributions | |
anasia | -0.356 |
vas | -0.326 |
Bengals | -0.310 |
cius | -0.308 |
[* | -0.307 |
Token |
|
Token ID | 198 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
ASC | +3.742 |
eur | +3.326 |
PLA | +3.242 |
Agric | +3.232 |
Ribbon | +3.229 |
Neg logit contributions | |
anasia | -3.174 |
vas | -2.940 |
cius | -2.829 |
Bengals | -2.753 |
[* | -2.740 |
Token |
|
Token ID | 198 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
ASC | +0.629 |
eur | +0.561 |
Agric | +0.556 |
PLA | +0.551 |
Ribbon | +0.551 |
Neg logit contributions | |
anasia | -0.430 |
vas | -0.393 |
Bengals | -0.378 |
[* | -0.372 |
cius | -0.368 |
Token | � |
Token ID | 447 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
ASC | +0.337 |
eur | +0.291 |
Agric | +0.289 |
PLA | +0.287 |
Ribbon | +0.285 |
Neg logit contributions | |
anasia | -0.340 |
vas | -0.318 |
Bengals | -0.309 |
[* | -0.304 |
cius | -0.300 |
Token | � |
Token ID | 250 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
ASC | +0.681 |
eur | +0.603 |
Agric | +0.600 |
PLA | +0.594 |
Ribbon | +0.593 |
Neg logit contributions | |
anasia | -0.510 |
vas | -0.470 |
Bengals | -0.454 |
[* | -0.447 |
cius | -0.440 |
Token | Tax |
Token ID | 27017 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ASC | +0.413 |
eur | +0.360 |
Agric | +0.358 |
Ribbon | +0.354 |
PLA | +0.354 |
Neg logit contributions | |
anasia | -0.388 |
vas | -0.361 |
Bengals | -0.350 |
[* | -0.345 |
cius | -0.340 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ASC | +0.436 |
eur | +0.381 |
Agric | +0.378 |
Ribbon | +0.374 |
PLA | +0.372 |
Neg logit contributions | |
anasia | -0.406 |
vas | -0.379 |
Bengals | -0.367 |
[* | -0.360 |
cius | -0.355 |
Token | forms |
Token ID | 23914 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ASC | +1.826 |
eur | +1.613 |
Agric | +1.584 |
Ribbon | +1.581 |
PLA | +1.580 |
Neg logit contributions | |
anasia | -1.338 |
vas | -1.239 |
Bengals | -1.189 |
[* | -1.166 |
cius | -1.142 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ASC | +0.947 |
eur | +0.817 |
Agric | +0.812 |
Ribbon | +0.803 |
orate | +0.799 |
Neg logit contributions | |
anasia | -0.996 |
vas | -0.931 |
Bengals | -0.902 |
[* | -0.889 |
cius | -0.879 |
Token | text |
Token ID | 5239 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
ASC | +1.353 |
eur | +1.146 |
Agric | +1.129 |
Ribbon | +1.126 |
PLA | +1.126 |
Neg logit contributions | |
anasia | -1.590 |
vas | -1.494 |
Bengals | -1.452 |
[* | -1.428 |
cius | -1.405 |
Token | rend |
Token ID | 10920 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
ASC | +2.382 |
eur | +2.028 |
Agric | +2.005 |
Ribbon | +2.004 |
orate | +1.985 |
Neg logit contributions | |
anasia | -2.473 |
vas | -2.309 |
Bengals | -2.228 |
[* | -2.188 |
cius | -2.173 |
Token | erer |
Token ID | 11882 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
ASC | +1.218 |
eur | +0.948 |
Agric | +0.911 |
Ribbon | +0.898 |
orate | +0.888 |
Neg logit contributions | |
anasia | -3.237 |
vas | -3.095 |
Bengals | -3.016 |
[* | -2.969 |
cius | -2.968 |
Token | ] |
Token ID | 60 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ASC | +3.337 |
eur | +2.822 |
Ribbon | +2.811 |
Agric | +2.798 |
parity | +2.773 |
Neg logit contributions | |
anasia | -3.563 |
vas | -3.321 |
Bengals | -3.185 |
[* | -3.137 |
cius | -3.116 |
Token | :: |
Token ID | 3712 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ASC | +1.199 |
eur | +1.020 |
Agric | +1.010 |
Ribbon | +1.000 |
PLA | +0.998 |
Neg logit contributions | |
anasia | -1.416 |
vas | -1.326 |
Bengals | -1.286 |
[* | -1.265 |
cius | -1.250 |
Token | Measure |
Token ID | 47384 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ASC | +1.633 |
eur | +1.390 |
Agric | +1.377 |
PLA | +1.371 |
Ribbon | +1.365 |
Neg logit contributions | |
anasia | -1.802 |
vas | -1.685 |
Bengals | -1.639 |
[* | -1.612 |
cius | -1.587 |
Token | Text |
Token ID | 8206 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
ASC | +1.631 |
eur | +1.389 |
Ribbon | +1.370 |
Agric | +1.368 |
orate | +1.359 |
Neg logit contributions | |
anasia | -1.777 |
vas | -1.661 |
Bengals | -1.608 |
[* | -1.581 |
cius | -1.563 |
Token | ($ |
Token ID | 16763 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ASC | +2.162 |
eur | +1.871 |
Ribbon | +1.856 |
Agric | +1.838 |
orate | +1.817 |
Neg logit contributions | |
anasia | -2.148 |
vas | -1.998 |
Bengals | -1.913 |
cius | -1.879 |
[* | -1.876 |
Token | � |
Token ID | 251 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
anasia | +0.418 |
vas | +0.383 |
Bengals | +0.370 |
[* | +0.364 |
cius | +0.357 |
Neg logit contributions | |
ASC | -0.595 |
eur | -0.528 |
Agric | -0.526 |
PLA | -0.521 |
Ribbon | -0.521 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ASC | +0.057 |
eur | +0.050 |
Agric | +0.050 |
Ribbon | +0.050 |
PLA | +0.050 |
Neg logit contributions | |
anasia | -0.042 |
vas | -0.038 |
Bengals | -0.037 |
[* | -0.036 |
cius | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
anasia | +0.075 |
vas | +0.068 |
Bengals | +0.066 |
[* | +0.065 |
cius | +0.064 |
Neg logit contributions | |
ASC | -0.112 |
eur | -0.099 |
Agric | -0.099 |
PLA | -0.098 |
Ribbon | -0.098 |
Token | He |
Token ID | 1544 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
anasia | +0.406 |
vas | +0.379 |
Bengals | +0.368 |
[* | +0.362 |
cius | +0.358 |
Neg logit contributions | |
ASC | -0.403 |
eur | -0.349 |
Agric | -0.347 |
PLA | -0.344 |
Ribbon | -0.342 |
Token | took |
Token ID | 1718 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
anasia | +0.352 |
vas | +0.325 |
Bengals | +0.315 |
[* | +0.310 |
cius | +0.304 |
Neg logit contributions | |
ASC | -0.438 |
eur | -0.386 |
Agric | -0.385 |
Ribbon | -0.380 |
PLA | -0.380 |
Token | apart |
Token ID | 5475 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
ASC | +1.406 |
Agric | +1.245 |
eur | +1.244 |
Ribbon | +1.229 |
orate | +1.222 |
Neg logit contributions | |
anasia | -1.142 |
vas | -1.038 |
Bengals | -1.008 |
[* | -0.998 |
cius | -0.994 |
Token | some |
Token ID | 617 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
ASC | +3.399 |
Agric | +3.014 |
eur | +2.990 |
Ribbon | +2.965 |
Dynam | +2.933 |
Neg logit contributions | |
anasia | -3.379 |
vas | -3.047 |
cius | -2.991 |
[* | -2.955 |
Bengals | -2.939 |
Token | elements |
Token ID | 4847 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
anasia | +0.612 |
vas | +0.568 |
Bengals | +0.550 |
[* | +0.539 |
cius | +0.526 |
Neg logit contributions | |
ASC | -0.832 |
eur | -0.737 |
Agric | -0.733 |
PLA | -0.727 |
Ribbon | -0.726 |
Token | of |
Token ID | 286 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
anasia | +0.686 |
vas | +0.634 |
Bengals | +0.615 |
[* | +0.605 |
cius | +0.592 |
Neg logit contributions | |
ASC | -0.878 |
eur | -0.775 |
Agric | -0.772 |
PLA | -0.764 |
Ribbon | -0.763 |
Token | the |
Token ID | 262 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
anasia | +0.473 |
vas | +0.439 |
Bengals | +0.426 |
[* | +0.420 |
cius | +0.413 |
Neg logit contributions | |
ASC | -0.522 |
eur | -0.457 |
Agric | -0.455 |
Ribbon | -0.450 |
PLA | -0.450 |
Token | mechanism |
Token ID | 9030 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
anasia | +0.503 |
vas | +0.470 |
Bengals | +0.457 |
[* | +0.450 |
cius | +0.442 |
Neg logit contributions | |
ASC | -0.514 |
eur | -0.446 |
Agric | -0.444 |
PLA | -0.440 |
Ribbon | -0.439 |
Token | away |
Token ID | 1497 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
anasia | +0.383 |
vas | +0.355 |
Bengals | +0.344 |
[* | +0.340 |
cius | +0.333 |
Neg logit contributions | |
ASC | -0.443 |
eur | -0.388 |
Agric | -0.387 |
PLA | -0.383 |
Ribbon | -0.383 |
Token | from |
Token ID | 422 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
ASC | +0.948 |
eur | +0.822 |
Agric | +0.819 |
orate | +0.801 |
Dynam | +0.799 |
Neg logit contributions | |
anasia | -0.993 |
vas | -0.919 |
Bengals | -0.894 |
[* | -0.878 |
cius | -0.875 |
Token | Kirby |
Token ID | 23965 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
ASC | +0.565 |
eur | +0.496 |
Agric | +0.495 |
Ribbon | +0.488 |
orate | +0.487 |
Neg logit contributions | |
anasia | -0.493 |
vas | -0.455 |
Bengals | -0.441 |
[* | -0.434 |
cius | -0.431 |
Token | 's |
Token ID | 338 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ASC | +0.505 |
eur | +0.444 |
Agric | +0.442 |
Ribbon | +0.438 |
PLA | +0.436 |
Neg logit contributions | |
anasia | -0.418 |
vas | -0.384 |
Bengals | -0.373 |
[* | -0.368 |
cius | -0.362 |
Token | bomb |
Token ID | 5194 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ASC | +1.118 |
Agric | +0.982 |
eur | +0.980 |
Ribbon | +0.974 |
Dynam | +0.965 |
Neg logit contributions | |
anasia | -0.944 |
vas | -0.859 |
Bengals | -0.835 |
[* | -0.826 |
cius | -0.818 |
Token | astic |
Token ID | 3477 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
ASC | +0.914 |
eur | +0.698 |
Agric | +0.684 |
orate | +0.673 |
PLA | +0.673 |
Neg logit contributions | |
anasia | -2.350 |
vas | -2.227 |
Bengals | -2.186 |
[* | -2.167 |
cius | -2.155 |
Token | style |
Token ID | 3918 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ASC | +3.544 |
eur | +3.154 |
Dynam | +3.140 |
Ribbon | +3.126 |
Agric | +3.120 |
Neg logit contributions | |
anasia | -3.067 |
vas | -2.749 |
Bengals | -2.685 |
cius | -2.676 |
[* | -2.658 |
Token | of |
Token ID | 286 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
ASC | +1.537 |
eur | +1.354 |
Agric | +1.338 |
Dynam | +1.329 |
parity | +1.327 |
Neg logit contributions | |
anasia | -1.366 |
vas | -1.251 |
Bengals | -1.217 |
[* | -1.204 |
cius | -1.189 |
Token | storytelling |
Token ID | 23689 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
ASC | +0.567 |
eur | +0.497 |
Agric | +0.495 |
Ribbon | +0.489 |
PLA | +0.489 |
Neg logit contributions | |
anasia | -0.501 |
vas | -0.464 |
Bengals | -0.451 |
[* | -0.444 |
cius | -0.437 |
Token | . |
Token ID | 13 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
ASC | +0.327 |
eur | +0.287 |
Agric | +0.285 |
Ribbon | +0.282 |
orate | +0.281 |
Neg logit contributions | |
anasia | -0.299 |
vas | -0.275 |
Bengals | -0.268 |
[* | -0.264 |
cius | -0.261 |
Token | According |
Token ID | 4784 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
anasia | +0.033 |
vas | +0.030 |
Bengals | +0.029 |
[* | +0.029 |
cius | +0.028 |
Neg logit contributions | |
ASC | -0.039 |
Agric | -0.034 |
eur | -0.034 |
Ribbon | -0.034 |
PLA | -0.034 |
Token | ) |
Token ID | 8 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
anasia | +0.116 |
vas | +0.108 |
Bengals | +0.105 |
[* | +0.104 |
cius | +0.102 |
Neg logit contributions | |
ASC | -0.117 |
eur | -0.101 |
Agric | -0.101 |
Ribbon | -0.100 |
PLA | -0.100 |
Token | Mem |
Token ID | 4942 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
ASC | +1.231 |
eur | +1.073 |
Agric | +1.071 |
Ribbon | +1.061 |
PLA | +1.052 |
Neg logit contributions | |
anasia | -1.121 |
vas | -1.031 |
Bengals | -1.000 |
[* | -0.984 |
cius | -0.975 |
Token | c |
Token ID | 66 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ASC | +2.215 |
eur | +1.922 |
Agric | +1.896 |
Ribbon | +1.888 |
orate | +1.875 |
Neg logit contributions | |
anasia | -2.368 |
vas | -2.227 |
Bengals | -2.165 |
[* | -2.115 |
cius | -2.085 |
Token | py |
Token ID | 9078 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
ASC | +1.017 |
eur | +0.812 |
Agric | +0.807 |
orate | +0.792 |
PLA | +0.785 |
Neg logit contributions | |
anasia | -2.080 |
vas | -1.979 |
Bengals | -1.937 |
[* | -1.914 |
cius | -1.897 |
Token | In |
Token ID | 818 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
anasia | +0.372 |
vas | +0.346 |
Bengals | +0.337 |
[* | +0.332 |
cius | +0.326 |
Neg logit contributions | |
ASC | -0.392 |
eur | -0.342 |
Agric | -0.341 |
PLA | -0.337 |
Ribbon | -0.336 |
Token | Memory |
Token ID | 30871 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
ASC | +1.268 |
eur | +1.105 |
Agric | +1.099 |
Ribbon | +1.087 |
PLA | +1.086 |
Neg logit contributions | |
anasia | -1.193 |
vas | -1.108 |
Bengals | -1.077 |
[* | -1.059 |
cius | -1.043 |
Token | 4 |
Token ID | 604 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
ASC | +3.242 |
eur | +2.779 |
Agric | +2.748 |
Ribbon | +2.741 |
parity | +2.717 |
Neg logit contributions | |
anasia | -3.429 |
vas | -3.193 |
Bengals | -3.098 |
cius | -3.029 |
[* | -3.025 |
Token | 66 |
Token ID | 2791 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
ASC | +2.138 |
eur | +1.854 |
Agric | +1.839 |
Ribbon | +1.829 |
PLA | +1.820 |
Neg logit contributions | |
anasia | -2.127 |
vas | -1.977 |
Bengals | -1.907 |
[* | -1.894 |
cius | -1.877 |
Token | 284 |
Token ID | 30336 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ASC | +2.636 |
eur | +2.277 |
Agric | +2.259 |
Ribbon | +2.239 |
PLA | +2.236 |
Neg logit contributions | |
anasia | -2.594 |
vas | -2.416 |
Bengals | -2.328 |
[* | -2.308 |
cius | -2.289 |
Token | 4 |
Token ID | 604 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
ASC | +0.890 |
eur | +0.774 |
Agric | +0.771 |
PLA | +0.760 |
Ribbon | +0.760 |
Neg logit contributions | |
anasia | -0.849 |
vas | -0.790 |
Bengals | -0.763 |
[* | -0.755 |
cius | -0.744 |
Token | 64 |
Token ID | 2414 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
ASC | +0.177 |
eur | +0.152 |
Agric | +0.152 |
Ribbon | +0.150 |
PLA | +0.150 |
Neg logit contributions | |
anasia | -0.193 |
vas | -0.181 |
Bengals | -0.176 |
[* | -0.174 |
cius | -0.171 |
Token | nat |
Token ID | 34664 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ASC | +3.515 |
Agric | +3.224 |
Ribbon | +3.185 |
eur | +3.175 |
parity | +3.142 |
Neg logit contributions | |
anasia | -2.539 |
Bengals | -2.231 |
vas | -2.187 |
[* | -2.154 |
cius | -2.153 |
Token | ut |
Token ID | 315 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ASC | +1.456 |
eur | +1.290 |
orate | +1.263 |
Agric | +1.256 |
PLA | +1.250 |
Neg logit contributions | |
anasia | -1.356 |
vas | -1.271 |
Bengals | -1.252 |
[* | -1.227 |
cius | -1.193 |
Token | u |
Token ID | 84 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ASC | +1.520 |
eur | +1.345 |
orate | +1.324 |
Agric | +1.324 |
PLA | +1.312 |
Neg logit contributions | |
anasia | -1.356 |
vas | -1.253 |
Bengals | -1.231 |
[* | -1.204 |
cius | -1.181 |
Token | wa |
Token ID | 10247 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ASC | +1.591 |
eur | +1.418 |
orate | +1.404 |
Agric | +1.400 |
PLA | +1.393 |
Neg logit contributions | |
anasia | -1.340 |
Bengals | -1.215 |
vas | -1.213 |
[* | -1.175 |
cius | -1.153 |
Token | na |
Token ID | 12385 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
ASC | +1.468 |
eur | +1.311 |
Agric | +1.297 |
orate | +1.292 |
Ribbon | +1.287 |
Neg logit contributions | |
anasia | -1.169 |
Bengals | -1.061 |
vas | -1.057 |
[* | -1.019 |
cius | -1.018 |
Token | ang |
Token ID | 3550 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
ASC | +1.835 |
eur | +1.649 |
Agric | +1.645 |
Ribbon | +1.639 |
orate | +1.632 |
Neg logit contributions | |
anasia | -1.400 |
Bengals | -1.255 |
vas | -1.244 |
[* | -1.206 |
cius | -1.204 |
Token | kan |
Token ID | 43998 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
ASC | +3.710 |
Agric | +3.382 |
eur | +3.366 |
Ribbon | +3.351 |
parity | +3.313 |
Neg logit contributions | |
anasia | -2.719 |
Bengals | -2.420 |
vas | -2.370 |
[* | -2.334 |
cius | -2.324 |
Token | il |
Token ID | 346 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
ASC | +1.922 |
eur | +1.711 |
Agric | +1.684 |
orate | +1.681 |
PLA | +1.670 |
Neg logit contributions | |
anasia | -1.829 |
vas | -1.699 |
Bengals | -1.689 |
[* | -1.647 |
cius | -1.602 |
Token | ang |
Token ID | 648 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
ASC | +0.549 |
eur | +0.484 |
Agric | +0.479 |
orate | +0.477 |
PLA | +0.474 |
Neg logit contributions | |
anasia | -0.498 |
vas | -0.461 |
Bengals | -0.453 |
[* | -0.443 |
cius | -0.435 |
Token | an |
Token ID | 281 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ASC | +2.351 |
eur | +2.102 |
Agric | +2.097 |
Ribbon | +2.079 |
orate | +2.076 |
Neg logit contributions | |
anasia | -1.788 |
Bengals | -1.607 |
vas | -1.589 |
[* | -1.541 |
cius | -1.539 |
Token | ak |
Token ID | 461 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ASC | +0.850 |
eur | +0.750 |
Agric | +0.736 |
orate | +0.730 |
Ribbon | +0.725 |
Neg logit contributions | |
anasia | -0.856 |
vas | -0.798 |
Bengals | -0.787 |
[* | -0.767 |
cius | -0.754 |
Token | re |
Token ID | 260 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
ASC | +0.875 |
eur | +0.792 |
orate | +0.782 |
Agric | +0.777 |
PLA | +0.773 |
Neg logit contributions | |
anasia | -0.517 |
vas | -0.475 |
Bengals | -0.456 |
[* | -0.443 |
cius | -0.430 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ASC | +0.033 |
eur | +0.029 |
Agric | +0.029 |
PLA | +0.028 |
orate | +0.028 |
Neg logit contributions | |
anasia | -0.031 |
vas | -0.029 |
Bengals | -0.028 |
[* | -0.028 |
cius | -0.027 |
Token | kov |
Token ID | 21862 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ASC | +0.795 |
eur | +0.690 |
Agric | +0.681 |
PLA | +0.673 |
orate | +0.673 |
Neg logit contributions | |
anasia | -0.850 |
vas | -0.794 |
Bengals | -0.773 |
[* | -0.762 |
cius | -0.749 |
Token | id |
Token ID | 312 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
ASC | +1.304 |
eur | +1.137 |
Agric | +1.128 |
orate | +1.117 |
PLA | +1.109 |
Neg logit contributions | |
anasia | -1.230 |
vas | -1.151 |
Bengals | -1.117 |
[* | -1.099 |
cius | -1.068 |
Token | g |
Token ID | 70 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
ASC | +1.660 |
eur | +1.459 |
Agric | +1.438 |
orate | +1.431 |
PLA | +1.409 |
Neg logit contributions | |
anasia | -1.618 |
vas | -1.511 |
Bengals | -1.466 |
[* | -1.447 |
cius | -1.397 |
Token | oyal |
Token ID | 4815 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
ASC | +2.320 |
eur | +2.026 |
Agric | +1.994 |
orate | +1.983 |
PLA | +1.977 |
Neg logit contributions | |
anasia | -2.244 |
vas | -2.099 |
Bengals | -2.045 |
[* | -1.996 |
cius | -1.937 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ASC | +3.198 |
eur | +2.827 |
Agric | +2.716 |
orate | +2.703 |
Ribbon | +2.678 |
Neg logit contributions | |
anasia | -3.352 |
vas | -3.131 |
Bengals | -3.061 |
[* | -3.034 |
cius | -2.893 |
Token | net |
Token ID | 3262 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ASC | +1.366 |
eur | +1.191 |
Agric | +1.165 |
orate | +1.158 |
PLA | +1.153 |
Neg logit contributions | |
anasia | -1.528 |
vas | -1.424 |
Bengals | -1.393 |
[* | -1.372 |
cius | -1.343 |
Token | ) |
Token ID | 8 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
ASC | +1.123 |
eur | +0.973 |
Agric | +0.968 |
PLA | +0.957 |
Ribbon | +0.951 |
Neg logit contributions | |
anasia | -1.225 |
vas | -1.139 |
Bengals | -1.110 |
[* | -1.091 |
cius | -1.085 |
Token | or |
Token ID | 393 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ASC | +0.364 |
eur | +0.321 |
Agric | +0.320 |
Ribbon | +0.317 |
PLA | +0.316 |
Neg logit contributions | |
anasia | -0.279 |
vas | -0.257 |
Bengals | -0.248 |
[* | -0.244 |
cius | -0.240 |
Token | Stan |
Token ID | 7299 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
anasia | +0.191 |
vas | +0.179 |
Bengals | +0.175 |
[* | +0.173 |
cius | +0.168 |
Neg logit contributions | |
ASC | -0.197 |
eur | -0.172 |
Agric | -0.169 |
PLA | -0.169 |
orate | -0.168 |
Token | ong |
Token ID | 506 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ASC | +1.512 |
eur | +1.277 |
orate | +1.254 |
PLA | +1.245 |
Agric | +1.234 |
Neg logit contributions | |
anasia | -1.948 |
vas | -1.856 |
Bengals | -1.810 |
[* | -1.794 |
cius | -1.752 |
Token | Ch |
Token ID | 1925 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
ASC | +1.518 |
eur | +1.285 |
Agric | +1.270 |
PLA | +1.267 |
Ribbon | +1.263 |
Neg logit contributions | |
anasia | -1.906 |
vas | -1.786 |
Bengals | -1.746 |
[* | -1.724 |
cius | -1.698 |
Token | oya |
Token ID | 23790 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
ASC | +3.018 |
eur | +2.746 |
orate | +2.720 |
Agric | +2.719 |
PLA | +2.707 |
Neg logit contributions | |
anasia | -1.576 |
vas | -1.448 |
Bengals | -1.407 |
[* | -1.363 |
cius | -1.319 |
Token | Week |
Token ID | 20916 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
ASC | +1.787 |
eur | +1.550 |
PLA | +1.526 |
Ribbon | +1.522 |
Agric | +1.522 |
Neg logit contributions | |
anasia | -1.788 |
vas | -1.664 |
Bengals | -1.618 |
[* | -1.603 |
cius | -1.575 |
Token | end |
Token ID | 437 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
ASC | +2.284 |
eur | +2.026 |
orate | +2.000 |
Agric | +1.973 |
PLA | +1.970 |
Neg logit contributions | |
anasia | -2.167 |
vas | -2.024 |
Bengals | -1.975 |
cius | -1.923 |
[* | -1.921 |
Token | T |
Token ID | 51 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
ASC | +1.690 |
eur | +1.476 |
Agric | +1.462 |
PLA | +1.454 |
Ribbon | +1.454 |
Neg logit contributions | |
anasia | -1.506 |
vas | -1.396 |
Bengals | -1.354 |
[* | -1.338 |
cius | -1.315 |
Token | ear |
Token ID | 451 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ASC | +2.888 |
eur | +2.466 |
orate | +2.405 |
PLA | +2.393 |
Agric | +2.332 |
Neg logit contributions | |
anasia | -3.678 |
vas | -3.494 |
Bengals | -3.412 |
[* | -3.373 |
cius | -3.339 |
Token | V |
Token ID | 53 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ASC | +1.329 |
eur | +1.151 |
Agric | +1.138 |
PLA | +1.129 |
Ribbon | +1.128 |
Neg logit contributions | |
anasia | -1.388 |
vas | -1.293 |
Bengals | -1.260 |
[* | -1.247 |
cius | -1.225 |
Token | oid |
Token ID | 1868 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ASC | +1.658 |
eur | +1.475 |
Agric | +1.458 |
orate | +1.457 |
PLA | +1.450 |
Neg logit contributions | |
anasia | -1.117 |
vas | -1.027 |
Bengals | -0.991 |
[* | -0.972 |
cius | -0.944 |
Token | Ray |
Token ID | 19591 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ASC | +0.788 |
eur | +0.686 |
Agric | +0.680 |
PLA | +0.674 |
Ribbon | +0.674 |
Neg logit contributions | |
anasia | -0.774 |
vas | -0.722 |
Bengals | -0.702 |
[* | -0.691 |
cius | -0.682 |
Token | J |
Token ID | 41 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
ASC | +1.342 |
eur | +1.169 |
PLA | +1.150 |
Agric | +1.148 |
Ribbon | +1.145 |
Neg logit contributions | |
anasia | -1.269 |
vas | -1.181 |
Bengals | -1.147 |
[* | -1.136 |
cius | -1.115 |
Token | args |
Token ID | 22046 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
anasia | +0.040 |
vas | +0.037 |
Bengals | +0.035 |
[* | +0.035 |
cius | +0.034 |
Neg logit contributions | |
ASC | -0.051 |
eur | -0.045 |
Agric | -0.044 |
PLA | -0.044 |
Ribbon | -0.044 |
Token | [" |
Token ID | 14692 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
anasia | +0.555 |
vas | +0.515 |
[* | +0.499 |
Bengals | +0.494 |
cius | +0.482 |
Neg logit contributions | |
ASC | -0.700 |
Agric | -0.622 |
eur | -0.614 |
Ribbon | -0.614 |
orate | -0.612 |
Token | images |
Token ID | 17566 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
anasia | +0.138 |
vas | +0.118 |
Bengals | +0.111 |
[* | +0.107 |
cius | +0.104 |
Neg logit contributions | |
ASC | -0.431 |
eur | -0.393 |
Agric | -0.393 |
Ribbon | -0.390 |
PLA | -0.389 |
Token | "] |
Token ID | 8973 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
ASC | +1.135 |
eur | +0.944 |
Agric | +0.922 |
PLA | +0.918 |
orate | +0.906 |
Neg logit contributions | |
anasia | -1.734 |
vas | -1.635 |
Bengals | -1.601 |
[* | -1.576 |
cius | -1.569 |
Token | ): |
Token ID | 2599 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ASC | +0.611 |
eur | +0.515 |
Agric | +0.512 |
PLA | +0.505 |
Ribbon | +0.503 |
Neg logit contributions | |
anasia | -0.847 |
vas | -0.797 |
Bengals | -0.778 |
[* | -0.769 |
cius | -0.760 |
Token | # |
Token ID | 1303 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
ASC | +0.993 |
eur | +0.878 |
Agric | +0.871 |
Ribbon | +0.865 |
PLA | +0.861 |
Neg logit contributions | |
anasia | -0.874 |
vas | -0.788 |
Bengals | -0.771 |
[* | -0.758 |
cius | -0.756 |
Token | load |
Token ID | 3440 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ASC | +3.268 |
Agric | +2.863 |
PLA | +2.857 |
Dynam | +2.817 |
parity | +2.814 |
Neg logit contributions | |
anasia | -3.329 |
vas | -2.913 |
Bengals | -2.907 |
cius | -2.897 |
[* | -2.794 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ASC | +1.754 |
eur | +1.522 |
Agric | +1.507 |
PLA | +1.496 |
Ribbon | +1.486 |
Neg logit contributions | |
anasia | -1.791 |
vas | -1.642 |
Bengals | -1.604 |
cius | -1.582 |
[* | -1.571 |
Token | image |
Token ID | 2939 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ASC | +0.218 |
eur | +0.191 |
Agric | +0.190 |
Ribbon | +0.188 |
PLA | +0.187 |
Neg logit contributions | |
anasia | -0.206 |
vas | -0.191 |
Bengals | -0.185 |
[* | -0.183 |
cius | -0.180 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ASC | +0.144 |
eur | +0.127 |
Agric | +0.126 |
Ribbon | +0.125 |
PLA | +0.125 |
Neg logit contributions | |
anasia | -0.116 |
vas | -0.107 |
Bengals | -0.104 |
[* | -0.102 |
cius | -0.100 |
Token | resize |
Token ID | 47558 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
ASC | +0.756 |
eur | +0.640 |
Agric | +0.634 |
orate | +0.625 |
PLA | +0.625 |
Neg logit contributions | |
anasia | -1.038 |
vas | -0.970 |
Bengals | -0.953 |
[* | -0.938 |
cius | -0.928 |
Token | Trump |
Token ID | 6170 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
anasia | +0.121 |
vas | +0.112 |
Bengals | +0.109 |
[* | +0.107 |
cius | +0.106 |
Neg logit contributions | |
ASC | -0.128 |
eur | -0.112 |
Agric | -0.111 |
PLA | -0.110 |
Ribbon | -0.110 |
Token | � |
Token ID | 447 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ASC | +0.851 |
eur | +0.751 |
Agric | +0.743 |
Ribbon | +0.737 |
PLA | +0.736 |
Neg logit contributions | |
anasia | -0.725 |
vas | -0.666 |
Bengals | -0.645 |
[* | -0.635 |
cius | -0.626 |
Token | � |
Token ID | 247 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
ASC | +1.214 |
eur | +1.081 |
Agric | +1.072 |
Ribbon | +1.063 |
PLA | +1.062 |
Neg logit contributions | |
anasia | -0.864 |
vas | -0.791 |
Bengals | -0.764 |
[* | -0.751 |
cius | -0.736 |
Token | s |
Token ID | 82 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ASC | +0.264 |
eur | +0.232 |
Agric | +0.230 |
PLA | +0.228 |
Ribbon | +0.228 |
Neg logit contributions | |
anasia | -0.220 |
vas | -0.203 |
Bengals | -0.196 |
[* | -0.194 |
cius | -0.190 |
Token | sal |
Token ID | 3664 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
anasia | +0.124 |
vas | +0.115 |
Bengals | +0.111 |
[* | +0.110 |
cius | +0.108 |
Neg logit contributions | |
ASC | -0.151 |
eur | -0.133 |
Agric | -0.132 |
Ribbon | -0.131 |
PLA | -0.131 |
Token | vo |
Token ID | 13038 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
ASC | +0.260 |
eur | +0.218 |
Agric | +0.217 |
Ribbon | +0.213 |
PLA | +0.213 |
Neg logit contributions | |
anasia | -0.381 |
vas | -0.359 |
Bengals | -0.351 |
[* | -0.347 |
cius | -0.342 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ASC | +3.372 |
eur | +3.043 |
parity | +2.929 |
PLA | +2.917 |
Agric | +2.917 |
Neg logit contributions | |
anasia | -3.089 |
vas | -2.818 |
Bengals | -2.742 |
cius | -2.727 |
[* | -2.670 |
Token | counter |
Token ID | 3753 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ASC | +0.113 |
eur | +0.100 |
Agric | +0.099 |
Ribbon | +0.098 |
PLA | +0.098 |
Neg logit contributions | |
anasia | -0.088 |
vas | -0.081 |
Bengals | -0.078 |
[* | -0.077 |
cius | -0.076 |
Token | to |
Token ID | 284 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ASC | +0.892 |
eur | +0.780 |
Agric | +0.775 |
PLA | +0.772 |
orate | +0.765 |
Neg logit contributions | |
anasia | -0.839 |
vas | -0.777 |
Bengals | -0.758 |
[* | -0.743 |
cius | -0.737 |
Token | efforts |
Token ID | 4040 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
anasia | +0.157 |
vas | +0.145 |
Bengals | +0.141 |
[* | +0.139 |
cius | +0.136 |
Neg logit contributions | |
ASC | -0.186 |
eur | -0.163 |
Agric | -0.162 |
Ribbon | -0.161 |
PLA | -0.161 |
Token | this |
Token ID | 428 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
anasia | +0.591 |
vas | +0.550 |
Bengals | +0.535 |
[* | +0.527 |
cius | +0.516 |
Neg logit contributions | |
ASC | -0.707 |
eur | -0.619 |
Agric | -0.618 |
Ribbon | -0.611 |
PLA | -0.611 |
Token | things |
Token ID | 1243 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
anasia | +0.717 |
vas | +0.669 |
Bengals | +0.644 |
[* | +0.639 |
cius | +0.619 |
Neg logit contributions | |
ASC | -0.880 |
eur | -0.775 |
Agric | -0.774 |
orate | -0.766 |
PLA | -0.766 |
Token | . |
Token ID | 13 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
anasia | +0.867 |
vas | +0.805 |
Bengals | +0.778 |
[* | +0.772 |
cius | +0.751 |
Neg logit contributions | |
ASC | -1.024 |
eur | -0.901 |
Agric | -0.900 |
PLA | -0.889 |
Ribbon | -0.886 |
Token | See |
Token ID | 4091 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
anasia | +0.483 |
vas | +0.450 |
Bengals | +0.436 |
[* | +0.432 |
cius | +0.422 |
Neg logit contributions | |
ASC | -0.516 |
eur | -0.451 |
Agric | -0.449 |
PLA | -0.444 |
orate | -0.444 |
Token | | |
Token ID | 930 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
anasia | +0.814 |
vas | +0.758 |
Bengals | +0.735 |
[* | +0.727 |
cius | +0.713 |
Neg logit contributions | |
ASC | -0.867 |
eur | -0.756 |
Agric | -0.753 |
PLA | -0.744 |
Ribbon | -0.743 |
Token | aut |
Token ID | 2306 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ASC | +0.446 |
eur | +0.389 |
Agric | +0.383 |
PLA | +0.380 |
Ribbon | +0.380 |
Neg logit contributions | |
anasia | -0.416 |
vas | -0.387 |
Bengals | -0.378 |
[* | -0.368 |
cius | -0.364 |
Token | oc |
Token ID | 420 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
anasia | +1.194 |
vas | +1.114 |
Bengals | +1.075 |
[* | +1.073 |
cius | +1.061 |
Neg logit contributions | |
ASC | -1.152 |
Agric | -1.004 |
eur | -0.987 |
Ribbon | -0.981 |
PLA | -0.981 |
Token | omm |
Token ID | 2002 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
ASC | +3.496 |
orate | +3.078 |
eur | +3.070 |
Agric | +2.988 |
Ribbon | +2.970 |
Neg logit contributions | |
anasia | -2.984 |
vas | -2.796 |
Bengals | -2.725 |
[* | -2.629 |
cius | -2.596 |
Token | and |
Token ID | 392 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ASC | +1.753 |
eur | +1.525 |
orate | +1.509 |
Agric | +1.500 |
Ribbon | +1.498 |
Neg logit contributions | |
anasia | -1.879 |
vas | -1.781 |
Bengals | -1.731 |
[* | -1.675 |
cius | -1.662 |
Token | | |
Token ID | 91 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
ASC | +0.865 |
eur | +0.736 |
Agric | +0.718 |
Ribbon | +0.711 |
orate | +0.710 |
Neg logit contributions | |
anasia | -1.183 |
vas | -1.115 |
Bengals | -1.090 |
[* | -1.070 |
cius | -1.057 |
Token | . |
Token ID | 13 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
ASC | +0.009 |
eur | +0.008 |
Agric | +0.008 |
Ribbon | +0.008 |
PLA | +0.008 |
Neg logit contributions | |
anasia | -0.008 |
vas | -0.008 |
Bengals | -0.008 |
[* | -0.007 |
cius | -0.007 |
Token | 3 |
Token ID | 513 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
anasia | +0.388 |
vas | +0.359 |
Bengals | +0.349 |
[* | +0.343 |
cius | +0.338 |
Neg logit contributions | |
ASC | -0.445 |
eur | -0.390 |
Agric | -0.388 |
Ribbon | -0.384 |
PLA | -0.383 |
Token | . |
Token ID | 13 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ASC | +0.804 |
eur | +0.700 |
Agric | +0.691 |
PLA | +0.689 |
orate | +0.683 |
Neg logit contributions | |
anasia | -0.763 |
vas | -0.708 |
Bengals | -0.689 |
[* | -0.674 |
cius | -0.670 |
Token | parse |
Token ID | 29572 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ASC | +0.224 |
Agric | +0.194 |
eur | +0.194 |
Ribbon | +0.192 |
PLA | +0.191 |
Neg logit contributions | |
anasia | -0.230 |
vas | -0.214 |
Bengals | -0.208 |
[* | -0.206 |
cius | -0.203 |
Token | _ |
Token ID | 62 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ASC | +1.820 |
eur | +1.580 |
PLA | +1.553 |
Agric | +1.545 |
orate | +1.535 |
Neg logit contributions | |
anasia | -1.893 |
vas | -1.768 |
Bengals | -1.711 |
cius | -1.686 |
[* | -1.680 |
Token | args |
Token ID | 22046 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
ASC | +1.509 |
eur | +1.327 |
PLA | +1.308 |
orate | +1.301 |
Agric | +1.285 |
Neg logit contributions | |
anasia | -1.301 |
vas | -1.217 |
Bengals | -1.179 |
[* | -1.148 |
cius | -1.148 |
Token | ()) |
Token ID | 28955 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
ASC | +0.069 |
eur | +0.061 |
Agric | +0.061 |
Ribbon | +0.060 |
orate | +0.060 |
Neg logit contributions | |
anasia | -0.054 |
vas | -0.050 |
Bengals | -0.049 |
[* | -0.048 |
cius | -0.047 |
Token | # |
Token ID | 1303 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
anasia | +0.180 |
vas | +0.164 |
Bengals | +0.160 |
[* | +0.157 |
cius | +0.156 |
Neg logit contributions | |
ASC | -0.221 |
eur | -0.194 |
Agric | -0.194 |
Ribbon | -0.191 |
PLA | -0.191 |
Token | initialize |
Token ID | 41216 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ASC | +3.059 |
Agric | +2.655 |
eur | +2.633 |
orate | +2.630 |
PLA | +2.628 |
Neg logit contributions | |
anasia | -3.433 |
vas | -3.112 |
Bengals | -3.104 |
cius | -3.041 |
[* | -2.983 |
Token | a |
Token ID | 257 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ASC | +1.397 |
eur | +1.227 |
Agric | +1.214 |
Ribbon | +1.199 |
PLA | +1.197 |
Neg logit contributions | |
anasia | -1.285 |
vas | -1.178 |
Bengals | -1.152 |
[* | -1.132 |
cius | -1.131 |
Token | rectangular |
Token ID | 36954 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ASC | +0.822 |
eur | +0.683 |
Agric | +0.679 |
Ribbon | +0.667 |
PLA | +0.664 |
Neg logit contributions | |
anasia | -1.311 |
vas | -1.233 |
Bengals | -1.207 |
[* | -1.194 |
cius | -1.181 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
anasia | +0.203 |
vas | +0.186 |
Bengals | +0.181 |
[* | +0.178 |
cius | +0.175 |
Neg logit contributions | |
ASC | -0.259 |
eur | -0.229 |
Agric | -0.227 |
Ribbon | -0.225 |
PLA | -0.225 |
Token | square |
Token ID | 6616 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
anasia | +0.881 |
vas | +0.834 |
Bengals | +0.808 |
[* | +0.803 |
cius | +0.779 |
Neg logit contributions | |
ASC | -0.793 |
Agric | -0.683 |
eur | -0.683 |
PLA | -0.677 |
Ribbon | -0.670 |
Token | make |
Token ID | 787 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
ASC | +0.302 |
eur | +0.266 |
Agric | +0.266 |
PLA | +0.263 |
Ribbon | +0.263 |
Neg logit contributions | |
anasia | -0.235 |
vas | -0.216 |
Bengals | -0.208 |
[* | -0.206 |
cius | -0.203 |
Token | it |
Token ID | 340 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
ASC | +0.150 |
eur | +0.132 |
Agric | +0.131 |
Ribbon | +0.130 |
PLA | +0.130 |
Neg logit contributions | |
anasia | -0.128 |
vas | -0.118 |
Bengals | -0.114 |
[* | -0.113 |
cius | -0.111 |
Token | through |
Token ID | 832 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
ASC | +0.500 |
eur | +0.442 |
Agric | +0.442 |
Ribbon | +0.437 |
PLA | +0.435 |
Neg logit contributions | |
anasia | -0.400 |
vas | -0.367 |
Bengals | -0.355 |
[* | -0.351 |
cius | -0.348 |
Token | the |
Token ID | 262 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
ASC | +0.012 |
eur | +0.010 |
Agric | +0.010 |
Ribbon | +0.010 |
PLA | +0.010 |
Neg logit contributions | |
anasia | -0.010 |
vas | -0.010 |
Bengals | -0.009 |
[* | -0.009 |
cius | -0.009 |
Token | g |
Token ID | 308 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ASC | +0.556 |
Agric | +0.491 |
eur | +0.491 |
Ribbon | +0.484 |
PLA | +0.482 |
Neg logit contributions | |
anasia | -0.441 |
vas | -0.404 |
Bengals | -0.391 |
[* | -0.386 |
cius | -0.381 |
Token | auntlet |
Token ID | 32633 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
ASC | +1.525 |
eur | +1.276 |
Agric | +1.274 |
orate | +1.245 |
PLA | +1.237 |
Neg logit contributions | |
anasia | -2.219 |
vas | -2.110 |
Bengals | -2.066 |
[* | -2.036 |
cius | -2.015 |
Token | of |
Token ID | 286 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
ASC | +3.383 |
Agric | +2.984 |
eur | +2.967 |
parity | +2.924 |
Ribbon | +2.909 |
Neg logit contributions | |
anasia | -3.057 |
vas | -2.773 |
cius | -2.712 |
Bengals | -2.687 |
[* | -2.660 |
Token | the |
Token ID | 262 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
ASC | +0.810 |
Agric | +0.717 |
eur | +0.714 |
Ribbon | +0.704 |
orate | +0.701 |
Neg logit contributions | |
anasia | -0.665 |
vas | -0.608 |
Bengals | -0.590 |
[* | -0.580 |
cius | -0.577 |
Token | Oregon |
Token ID | 8819 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
ASC | +0.024 |
eur | +0.021 |
Agric | +0.021 |
Ribbon | +0.021 |
PLA | +0.021 |
Neg logit contributions | |
anasia | -0.018 |
vas | -0.017 |
Bengals | -0.016 |
[* | -0.016 |
cius | -0.016 |
Token | State |
Token ID | 1812 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ASC | +0.604 |
Agric | +0.538 |
eur | +0.538 |
Ribbon | +0.531 |
PLA | +0.531 |
Neg logit contributions | |
anasia | -0.390 |
vas | -0.356 |
Bengals | -0.343 |
[* | -0.338 |
cius | -0.331 |
Token | voter |
Token ID | 10765 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ASC | +0.119 |
eur | +0.104 |
Agric | +0.104 |
Ribbon | +0.102 |
PLA | +0.102 |
Neg logit contributions | |
anasia | -0.102 |
vas | -0.094 |
Bengals | -0.091 |
[* | -0.090 |
cius | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
ASC | +0.764 |
eur | +0.681 |
Agric | +0.673 |
PLA | +0.668 |
Ribbon | +0.665 |
Neg logit contributions | |
anasia | -0.534 |
vas | -0.488 |
Bengals | -0.471 |
[* | -0.461 |
cius | -0.460 |
Token | impl |
Token ID | 23928 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ASC | +0.695 |
eur | +0.609 |
Agric | +0.605 |
PLA | +0.599 |
orate | +0.596 |
Neg logit contributions | |
anasia | -0.606 |
vas | -0.563 |
Bengals | -0.546 |
[* | -0.537 |
cius | -0.528 |
Token | Board |
Token ID | 5926 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
anasia | +1.262 |
vas | +1.160 |
Bengals | +1.119 |
[* | +1.112 |
cius | +1.066 |
Neg logit contributions | |
ASC | -1.788 |
eur | -1.581 |
PLA | -1.570 |
Agric | -1.567 |
Ribbon | -1.555 |
Token | { |
Token ID | 1391 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
ASC | +0.359 |
eur | +0.323 |
Agric | +0.323 |
Ribbon | +0.319 |
PLA | +0.319 |
Neg logit contributions | |
anasia | -0.180 |
vas | -0.161 |
Bengals | -0.154 |
[* | -0.149 |
cius | -0.149 |
Token | pub |
Token ID | 2240 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
anasia | +2.079 |
vas | +1.947 |
Bengals | +1.886 |
[* | +1.862 |
cius | +1.773 |
Neg logit contributions | |
ASC | -3.005 |
eur | -2.667 |
PLA | -2.640 |
Agric | -2.617 |
orate | -2.602 |
Token | fn |
Token ID | 24714 |
Feature activation | -7.33e+00 |
Pos logit contributions | |
anasia | +1.167 |
vas | +1.073 |
Bengals | +1.027 |
[* | +1.009 |
cius | +0.986 |
Neg logit contributions | |
ASC | -1.852 |
eur | -1.651 |
Agric | -1.639 |
PLA | -1.636 |
Ribbon | -1.630 |
Token | copy |
Token ID | 4866 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
anasia | +4.126 |
vas | +4.002 |
[* | +3.740 |
Bengals | +3.723 |
cius | +3.454 |
Neg logit contributions | |
ASC | -6.497 |
eur | -5.801 |
PLA | -5.792 |
Agric | -5.705 |
orate | -5.678 |
Token | _ |
Token ID | 62 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ASC | +1.257 |
Agric | +1.115 |
eur | +1.113 |
orate | +1.100 |
PLA | +1.099 |
Neg logit contributions | |
anasia | -0.816 |
vas | -0.747 |
Bengals | -0.718 |
[* | -0.695 |
cius | -0.692 |
Token | board |
Token ID | 3526 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ASC | +1.387 |
eur | +1.215 |
Agric | +1.199 |
orate | +1.188 |
PLA | +1.181 |
Neg logit contributions | |
anasia | -1.301 |
vas | -1.212 |
Bengals | -1.182 |
[* | -1.151 |
cius | -1.138 |
Token | ( |
Token ID | 357 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ASC | +1.094 |
eur | +0.969 |
Agric | +0.967 |
orate | +0.956 |
PLA | +0.953 |
Neg logit contributions | |
anasia | -0.750 |
vas | -0.686 |
Bengals | -0.665 |
cius | -0.644 |
[* | -0.642 |
Token | & |
Token ID | 1222 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
anasia | +0.786 |
vas | +0.723 |
Bengals | +0.698 |
[* | +0.687 |
cius | +0.673 |
Neg logit contributions | |
ASC | -1.098 |
eur | -0.974 |
Agric | -0.969 |
PLA | -0.960 |
Ribbon | -0.960 |
Token | < |
Token ID | 1279 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
ASC | +0.767 |
eur | +0.685 |
Agric | +0.683 |
PLA | +0.677 |
orate | +0.677 |
Neg logit contributions | |
anasia | -0.410 |
vas | -0.372 |
Bengals | -0.356 |
[* | -0.344 |
cius | -0.344 |
Token | T |
Token ID | 309 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
ASC | +0.444 |
Agric | +0.393 |
eur | +0.390 |
Ribbon | +0.389 |
orate | +0.385 |
Neg logit contributions | |
anasia | -0.347 |
vas | -0.319 |
Bengals | -0.307 |
[* | -0.303 |
cius | -0.301 |
Token | > |
Token ID | 1875 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
anasia | +0.265 |
vas | +0.231 |
Bengals | +0.219 |
[* | +0.212 |
cius | +0.210 |
Neg logit contributions | |
ASC | -0.725 |
eur | -0.659 |
Agric | -0.656 |
PLA | -0.653 |
Ribbon | -0.653 |
Token | { |
Token ID | 1391 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
anasia | +0.435 |
vas | +0.398 |
Bengals | +0.383 |
[* | +0.376 |
cius | +0.370 |
Neg logit contributions | |
ASC | -0.660 |
eur | -0.587 |
Agric | -0.585 |
Ribbon | -0.580 |
PLA | -0.579 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
anasia | +1.540 |
vas | +1.419 |
Bengals | +1.368 |
[* | +1.357 |
cius | +1.298 |
Neg logit contributions | |
ASC | -2.394 |
eur | -2.131 |
PLA | -2.120 |
Agric | -2.109 |
orate | -2.091 |
Token | fn |
Token ID | 24714 |
Feature activation | -6.87e+00 |
Pos logit contributions | |
anasia | +0.630 |
vas | +0.573 |
Bengals | +0.553 |
[* | +0.543 |
cius | +0.531 |
Neg logit contributions | |
ASC | -1.011 |
eur | -0.904 |
Agric | -0.902 |
Ribbon | -0.892 |
PLA | -0.890 |
Token | new |
Token ID | 649 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
anasia | +4.275 |
vas | +4.106 |
[* | +3.887 |
Bengals | +3.860 |
cius | +3.709 |
Neg logit contributions | |
ASC | -5.746 |
PLA | -5.105 |
eur | -5.098 |
Agric | -4.997 |
orate | -4.942 |
Token | ( |
Token ID | 357 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
anasia | +0.188 |
vas | +0.170 |
Bengals | +0.163 |
[* | +0.159 |
cius | +0.155 |
Neg logit contributions | |
ASC | -0.357 |
eur | -0.321 |
Agric | -0.320 |
orate | -0.317 |
Ribbon | -0.316 |
Token | t |
Token ID | 256 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
anasia | +0.857 |
vas | +0.787 |
Bengals | +0.760 |
[* | +0.747 |
cius | +0.733 |
Neg logit contributions | |
ASC | -1.209 |
eur | -1.073 |
Agric | -1.069 |
PLA | -1.058 |
Ribbon | -1.058 |
Token | : |
Token ID | 1058 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
anasia | +0.130 |
vas | +0.118 |
Bengals | +0.114 |
[* | +0.112 |
cius | +0.111 |
Neg logit contributions | |
ASC | -0.172 |
Agric | -0.154 |
eur | -0.153 |
Ribbon | -0.152 |
PLA | -0.151 |
Token | T |
Token ID | 309 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
anasia | +0.726 |
vas | +0.668 |
Bengals | +0.646 |
[* | +0.636 |
cius | +0.624 |
Neg logit contributions | |
ASC | -0.965 |
eur | -0.854 |
Agric | -0.851 |
Ribbon | -0.842 |
PLA | -0.841 |
Token | < |
Token ID | 1279 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
ASC | +0.906 |
eur | +0.815 |
Agric | +0.814 |
PLA | +0.808 |
orate | +0.806 |
Neg logit contributions | |
anasia | -0.422 |
vas | -0.379 |
Bengals | -0.358 |
cius | -0.346 |
[* | -0.345 |
Token | T |
Token ID | 309 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
ASC | +0.253 |
Agric | +0.223 |
eur | +0.222 |
Ribbon | +0.221 |
PLA | +0.219 |
Neg logit contributions | |
anasia | -0.192 |
vas | -0.176 |
Bengals | -0.170 |
[* | -0.167 |
cius | -0.166 |
Token | > |
Token ID | 1875 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
anasia | +0.258 |
vas | +0.223 |
Bengals | +0.212 |
[* | +0.205 |
cius | +0.202 |
Neg logit contributions | |
ASC | -0.755 |
eur | -0.687 |
Agric | -0.684 |
PLA | -0.682 |
Ribbon | -0.681 |
Token | { |
Token ID | 1391 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
anasia | +0.281 |
vas | +0.249 |
Bengals | +0.237 |
[* | +0.231 |
cius | +0.230 |
Neg logit contributions | |
ASC | -0.591 |
Agric | -0.534 |
eur | -0.533 |
Ribbon | -0.528 |
PLA | -0.527 |
Token | pub |
Token ID | 2240 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
anasia | +1.734 |
vas | +1.602 |
Bengals | +1.545 |
[* | +1.527 |
cius | +1.481 |
Neg logit contributions | |
ASC | -2.571 |
eur | -2.289 |
Agric | -2.264 |
PLA | -2.262 |
Ribbon | -2.243 |
Token | fn |
Token ID | 24714 |
Feature activation | -6.61e+00 |
Pos logit contributions | |
anasia | +0.443 |
vas | +0.401 |
Bengals | +0.391 |
[* | +0.382 |
cius | +0.378 |
Neg logit contributions | |
ASC | -0.612 |
Agric | -0.543 |
eur | -0.543 |
orate | -0.536 |
Ribbon | -0.535 |
Token | load |
Token ID | 3440 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
anasia | +3.874 |
vas | +3.748 |
[* | +3.548 |
Bengals | +3.528 |
cius | +3.346 |
Neg logit contributions | |
ASC | -5.714 |
eur | -5.115 |
PLA | -5.068 |
Agric | -5.033 |
orate | -5.007 |
Token | < |
Token ID | 1279 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
ASC | +1.850 |
Agric | +1.628 |
eur | +1.624 |
PLA | +1.616 |
Dynam | +1.607 |
Neg logit contributions | |
anasia | -1.036 |
vas | -0.942 |
Bengals | -0.901 |
cius | -0.871 |
[* | -0.862 |
Token | ' |
Token ID | 705 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ASC | +0.523 |
Agric | +0.465 |
eur | +0.464 |
Ribbon | +0.460 |
PLA | +0.458 |
Neg logit contributions | |
anasia | -0.357 |
vas | -0.326 |
Bengals | -0.314 |
[* | -0.309 |
cius | -0.305 |
Token | a |
Token ID | 64 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
ASC | +1.039 |
eur | +0.885 |
Agric | +0.877 |
Ribbon | +0.865 |
PLA | +0.856 |
Neg logit contributions | |
anasia | -1.246 |
vas | -1.167 |
Bengals | -1.136 |
[* | -1.125 |
cius | -1.115 |
Token | > |
Token ID | 1875 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
ASC | +0.829 |
eur | +0.744 |
Agric | +0.738 |
Ribbon | +0.736 |
orate | +0.734 |
Neg logit contributions | |
anasia | -0.494 |
vas | -0.442 |
Bengals | -0.428 |
[* | -0.420 |
cius | -0.414 |
Token | null |
Token ID | 9242 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
ASC | +0.548 |
eur | +0.477 |
Agric | +0.474 |
Ribbon | +0.470 |
orate | +0.469 |
Neg logit contributions | |
anasia | -0.534 |
vas | -0.493 |
Bengals | -0.482 |
[* | -0.471 |
cius | -0.467 |
Token | atomic |
Token ID | 17226 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
anasia | +0.442 |
vas | +0.410 |
Bengals | +0.399 |
[* | +0.393 |
cius | +0.386 |
Neg logit contributions | |
ASC | -0.479 |
eur | -0.419 |
Agric | -0.417 |
Ribbon | -0.412 |
PLA | -0.411 |
Token | pointer |
Token ID | 17562 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
anasia | +1.586 |
vas | +1.482 |
Bengals | +1.428 |
[* | +1.420 |
cius | +1.380 |
Neg logit contributions | |
ASC | -1.960 |
eur | -1.721 |
Agric | -1.717 |
PLA | -1.711 |
Ribbon | -1.695 |
Token | . |
Token ID | 13 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
anasia | +1.094 |
vas | +1.023 |
Bengals | +0.990 |
[* | +0.979 |
cius | +0.957 |
Neg logit contributions | |
ASC | -1.250 |
eur | -1.096 |
Agric | -1.088 |
PLA | -1.085 |
Ribbon | -1.077 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ASC | +0.518 |
Agric | +0.455 |
eur | +0.455 |
Ribbon | +0.450 |
orate | +0.448 |
Neg logit contributions | |
anasia | -0.445 |
vas | -0.408 |
Bengals | -0.397 |
[* | -0.390 |
cius | -0.385 |
Token | fn |
Token ID | 24714 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
anasia | +1.086 |
vas | +0.992 |
Bengals | +0.953 |
[* | +0.937 |
cius | +0.915 |
Neg logit contributions | |
ASC | -1.762 |
eur | -1.574 |
Agric | -1.568 |
PLA | -1.555 |
Ribbon | -1.553 |
Token | null |
Token ID | 9242 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
anasia | +3.341 |
vas | +3.191 |
[* | +2.983 |
Bengals | +2.936 |
cius | +2.839 |
Neg logit contributions | |
ASC | -6.181 |
PLA | -5.601 |
eur | -5.587 |
Agric | -5.515 |
orate | -5.432 |
Token | () |
Token ID | 7499 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ASC | +0.496 |
eur | +0.444 |
Agric | +0.441 |
orate | +0.439 |
PLA | +0.436 |
Neg logit contributions | |
anasia | -0.277 |
vas | -0.253 |
Bengals | -0.242 |
[* | -0.234 |
cius | -0.231 |
Token | -> |
Token ID | 4613 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
anasia | +0.439 |
vas | +0.384 |
Bengals | +0.367 |
[* | +0.355 |
cius | +0.348 |
Neg logit contributions | |
ASC | -1.057 |
eur | -0.957 |
Agric | -0.954 |
Ribbon | -0.947 |
PLA | -0.945 |
Token | Atomic |
Token ID | 28976 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
anasia | +1.472 |
vas | +1.379 |
Bengals | +1.342 |
[* | +1.327 |
cius | +1.303 |
Neg logit contributions | |
ASC | -1.386 |
eur | -1.198 |
Agric | -1.189 |
PLA | -1.179 |
Ribbon | -1.173 |
Token | < |
Token ID | 1279 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
ASC | +1.489 |
eur | +1.342 |
Agric | +1.331 |
Ribbon | +1.328 |
orate | +1.324 |
Neg logit contributions | |
anasia | -0.684 |
vas | -0.616 |
Bengals | -0.588 |
cius | -0.557 |
[* | -0.556 |
Token | Guard |
Token ID | 4932 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
anasia | +3.503 |
vas | +3.323 |
Bengals | +3.242 |
[* | +3.204 |
cius | +3.113 |
Neg logit contributions | |
ASC | -3.554 |
PLA | -3.055 |
eur | -3.014 |
orate | -3.004 |
Agric | -2.952 |
Token | { |
Token ID | 1391 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
anasia | +0.061 |
vas | +0.054 |
Bengals | +0.052 |
[* | +0.050 |
cius | +0.049 |
Neg logit contributions | |
ASC | -0.140 |
eur | -0.127 |
Agric | -0.126 |
Ribbon | -0.125 |
PLA | -0.125 |
Token | ... |
Token ID | 2644 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
anasia | +2.698 |
vas | +2.548 |
Bengals | +2.464 |
[* | +2.430 |
cius | +2.373 |
Neg logit contributions | |
ASC | -3.338 |
eur | -2.909 |
PLA | -2.909 |
Agric | -2.868 |
orate | -2.863 |
Token | } |
Token ID | 1782 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
anasia | +0.631 |
vas | +0.580 |
Bengals | +0.561 |
[* | +0.552 |
cius | +0.542 |
Neg logit contributions | |
ASC | -0.851 |
eur | -0.754 |
Agric | -0.752 |
Ribbon | -0.743 |
PLA | -0.743 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
anasia | +0.089 |
vas | +0.082 |
Bengals | +0.079 |
[* | +0.077 |
cius | +0.076 |
Neg logit contributions | |
ASC | -0.130 |
eur | -0.116 |
Agric | -0.115 |
Ribbon | -0.114 |
PLA | -0.114 |
Token | fn |
Token ID | 24714 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
anasia | +0.851 |
vas | +0.771 |
Bengals | +0.735 |
[* | +0.718 |
cius | +0.700 |
Neg logit contributions | |
ASC | -1.696 |
eur | -1.525 |
Agric | -1.517 |
PLA | -1.512 |
Ribbon | -1.507 |
Token | pin |
Token ID | 6757 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
anasia | +3.640 |
vas | +3.477 |
Bengals | +3.298 |
[* | +3.270 |
cius | +3.150 |
Neg logit contributions | |
ASC | -5.246 |
PLA | -4.653 |
eur | -4.622 |
Agric | -4.524 |
orate | -4.519 |
Token | () |
Token ID | 7499 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
anasia | +0.475 |
vas | +0.431 |
Bengals | +0.415 |
[* | +0.407 |
cius | +0.398 |
Neg logit contributions | |
ASC | -0.791 |
eur | -0.707 |
Agric | -0.705 |
Ribbon | -0.698 |
PLA | -0.698 |
Token | -> |
Token ID | 4613 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
anasia | +0.556 |
vas | +0.493 |
Bengals | +0.468 |
[* | +0.457 |
cius | +0.438 |
Neg logit contributions | |
ASC | -1.445 |
eur | -1.314 |
Agric | -1.307 |
PLA | -1.300 |
Ribbon | -1.297 |
Token | Guard |
Token ID | 4932 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
anasia | +1.132 |
vas | +1.053 |
Bengals | +1.022 |
[* | +1.007 |
cius | +0.988 |
Neg logit contributions | |
ASC | -1.327 |
eur | -1.163 |
Agric | -1.153 |
PLA | -1.147 |
orate | -1.141 |
Token | ; |
Token ID | 2162 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
ASC | +1.818 |
eur | +1.649 |
Agric | +1.643 |
Ribbon | +1.626 |
PLA | +1.619 |
Neg logit contributions | |
anasia | -0.821 |
vas | -0.728 |
Bengals | -0.694 |
cius | -0.658 |
[* | -0.654 |
Token | 172 |
Token ID | 23120 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
anasia | +0.249 |
vas | +0.232 |
Bengals | +0.226 |
[* | +0.221 |
cius | +0.216 |
Neg logit contributions | |
ASC | -0.287 |
eur | -0.251 |
Agric | -0.250 |
PLA | -0.248 |
Ribbon | -0.246 |
Token | games |
Token ID | 1830 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
anasia | +0.825 |
vas | +0.778 |
Bengals | +0.761 |
[* | +0.744 |
cius | +0.723 |
Neg logit contributions | |
ASC | -0.916 |
eur | -0.804 |
Agric | -0.796 |
PLA | -0.794 |
orate | -0.792 |
Token | and |
Token ID | 290 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
anasia | +0.510 |
vas | +0.474 |
Bengals | +0.462 |
[* | +0.454 |
cius | +0.441 |
Neg logit contributions | |
ASC | -0.637 |
eur | -0.557 |
Agric | -0.556 |
PLA | -0.552 |
orate | -0.550 |
Token | two |
Token ID | 734 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
anasia | +0.332 |
vas | +0.310 |
Bengals | +0.302 |
[* | +0.296 |
cius | +0.289 |
Neg logit contributions | |
ASC | -0.386 |
eur | -0.337 |
Agric | -0.336 |
PLA | -0.334 |
orate | -0.332 |
Token | Super |
Token ID | 3115 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
anasia | +0.143 |
vas | +0.134 |
Bengals | +0.130 |
[* | +0.127 |
cius | +0.125 |
Neg logit contributions | |
ASC | -0.155 |
eur | -0.136 |
Agric | -0.135 |
PLA | -0.134 |
orate | -0.133 |
Token | Bowl |
Token ID | 8693 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
anasia | +1.735 |
vas | +1.660 |
Bengals | +1.635 |
[* | +1.610 |
cius | +1.593 |
Neg logit contributions | |
ASC | -0.830 |
eur | -0.665 |
Agric | -0.653 |
orate | -0.647 |
PLA | -0.645 |
Token | s |
Token ID | 82 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
anasia | +3.163 |
vas | +2.939 |
Bengals | +2.865 |
[* | +2.704 |
cius | +2.617 |
Neg logit contributions | |
ASC | -5.061 |
orate | -4.502 |
Agric | -4.493 |
PLA | -4.467 |
eur | -4.384 |
Token | in |
Token ID | 287 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
anasia | +1.074 |
vas | +1.001 |
Bengals | +0.977 |
[* | +0.964 |
cius | +0.928 |
Neg logit contributions | |
ASC | -1.363 |
Agric | -1.188 |
eur | -1.187 |
PLA | -1.181 |
orate | -1.175 |
Token | the |
Token ID | 262 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
anasia | +0.705 |
vas | +0.661 |
Bengals | +0.645 |
[* | +0.633 |
cius | +0.620 |
Neg logit contributions | |
ASC | -0.691 |
eur | -0.597 |
Agric | -0.595 |
PLA | -0.589 |
Ribbon | -0.585 |
Token | NFL |
Token ID | 5134 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
anasia | +0.131 |
vas | +0.122 |
Bengals | +0.119 |
[* | +0.117 |
cius | +0.114 |
Neg logit contributions | |
ASC | -0.142 |
eur | -0.123 |
Agric | -0.123 |
PLA | -0.122 |
orate | -0.121 |
Token | : |
Token ID | 25 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
anasia | +0.094 |
vas | +0.088 |
Bengals | +0.085 |
[* | +0.084 |
cius | +0.082 |
Neg logit contributions | |
ASC | -0.115 |
eur | -0.101 |
Agric | -0.101 |
PLA | -0.099 |
Ribbon | -0.099 |
Token | wrap |
Token ID | 37150 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ASC | +2.163 |
eur | +1.865 |
orate | +1.838 |
Agric | +1.821 |
PLA | +1.802 |
Neg logit contributions | |
anasia | -2.428 |
vas | -2.277 |
Bengals | -2.210 |
[* | -2.166 |
cius | -2.145 |
Token | ()) |
Token ID | 32865 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ASC | +2.378 |
eur | +2.135 |
Agric | +2.111 |
orate | +2.102 |
Ribbon | +2.091 |
Neg logit contributions | |
anasia | -1.330 |
vas | -1.215 |
Bengals | -1.157 |
[* | -1.123 |
cius | -1.097 |
Token | } |
Token ID | 1782 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
anasia | +0.696 |
vas | +0.636 |
Bengals | +0.612 |
[* | +0.602 |
cius | +0.588 |
Neg logit contributions | |
ASC | -1.103 |
eur | -0.983 |
Agric | -0.980 |
PLA | -0.972 |
Ribbon | -0.971 |
Token | } |
Token ID | 1782 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
anasia | +0.212 |
vas | +0.192 |
Bengals | +0.185 |
[* | +0.181 |
cius | +0.177 |
Neg logit contributions | |
ASC | -0.372 |
eur | -0.333 |
Agric | -0.332 |
PLA | -0.329 |
Ribbon | -0.329 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
anasia | +0.028 |
vas | +0.025 |
Bengals | +0.024 |
[* | +0.024 |
cius | +0.024 |
Neg logit contributions | |
ASC | -0.044 |
eur | -0.039 |
Agric | -0.039 |
Ribbon | -0.039 |
PLA | -0.038 |
Token | fn |
Token ID | 24714 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
anasia | +0.680 |
vas | +0.623 |
Bengals | +0.600 |
[* | +0.590 |
cius | +0.577 |
Neg logit contributions | |
ASC | -1.017 |
eur | -0.904 |
Agric | -0.901 |
PLA | -0.893 |
Ribbon | -0.892 |
Token | apply |
Token ID | 4174 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
anasia | +3.478 |
vas | +3.344 |
Bengals | +3.181 |
[* | +3.150 |
cius | +3.015 |
Neg logit contributions | |
ASC | -3.845 |
eur | -3.324 |
PLA | -3.323 |
Agric | -3.303 |
Ribbon | -3.256 |
Token | _ |
Token ID | 62 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
anasia | +0.360 |
vas | +0.335 |
Bengals | +0.325 |
[* | +0.321 |
cius | +0.316 |
Neg logit contributions | |
ASC | -0.386 |
eur | -0.338 |
Agric | -0.336 |
PLA | -0.332 |
Ribbon | -0.331 |
Token | move |
Token ID | 21084 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
ASC | +1.735 |
eur | +1.550 |
orate | +1.516 |
Agric | +1.499 |
PLA | +1.494 |
Neg logit contributions | |
anasia | -1.558 |
vas | -1.459 |
Bengals | -1.442 |
[* | -1.391 |
cius | -1.366 |
Token | ( |
Token ID | 357 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
ASC | +0.644 |
eur | +0.575 |
Agric | +0.570 |
orate | +0.567 |
PLA | +0.561 |
Neg logit contributions | |
anasia | -0.452 |
vas | -0.412 |
Bengals | -0.405 |
cius | -0.390 |
[* | -0.389 |
Token | & |
Token ID | 1222 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
anasia | +0.328 |
vas | +0.300 |
Bengals | +0.290 |
[* | +0.285 |
cius | +0.281 |
Neg logit contributions | |
ASC | -0.459 |
eur | -0.407 |
Agric | -0.406 |
Ribbon | -0.401 |
PLA | -0.401 |
Token | the |
Token ID | 262 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
anasia | +0.132 |
vas | +0.122 |
Bengals | +0.119 |
[* | +0.117 |
cius | +0.115 |
Neg logit contributions | |
ASC | -0.157 |
eur | -0.138 |
Agric | -0.137 |
Ribbon | -0.136 |
PLA | -0.136 |
Token | space |
Token ID | 2272 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
anasia | +0.279 |
vas | +0.257 |
Bengals | +0.249 |
[* | +0.245 |
cius | +0.241 |
Neg logit contributions | |
ASC | -0.357 |
eur | -0.315 |
Agric | -0.314 |
Ribbon | -0.310 |
PLA | -0.310 |
Token | let |
Token ID | 1309 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
anasia | +0.469 |
vas | +0.431 |
Bengals | +0.417 |
[* | +0.411 |
cius | +0.404 |
Neg logit contributions | |
ASC | -0.608 |
eur | -0.538 |
Agric | -0.535 |
Ribbon | -0.530 |
PLA | -0.529 |
Token | ob |
Token ID | 909 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
anasia | +2.134 |
vas | +2.009 |
Bengals | +1.936 |
[* | +1.919 |
cius | +1.853 |
Neg logit contributions | |
ASC | -2.670 |
eur | -2.357 |
Agric | -2.344 |
PLA | -2.335 |
Ribbon | -2.324 |
Token | b |
Token ID | 65 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
anasia | +0.553 |
vas | +0.516 |
Bengals | +0.502 |
[* | +0.495 |
cius | +0.488 |
Neg logit contributions | |
ASC | -0.532 |
eur | -0.461 |
Agric | -0.459 |
Ribbon | -0.453 |
PLA | -0.453 |
Token | = |
Token ID | 796 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
anasia | +0.578 |
vas | +0.536 |
Bengals | +0.520 |
[* | +0.512 |
cius | +0.503 |
Neg logit contributions | |
ASC | -0.672 |
eur | -0.590 |
Agric | -0.587 |
Ribbon | -0.581 |
PLA | -0.580 |
Token | fit |
Token ID | 4197 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
anasia | +3.124 |
vas | +3.045 |
Bengals | +2.928 |
[* | +2.919 |
cius | +2.756 |
Neg logit contributions | |
ASC | -4.030 |
eur | -3.596 |
PLA | -3.558 |
orate | -3.516 |
Agric | -3.495 |
Token | ( |
Token ID | 7 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ASC | +0.286 |
eur | +0.248 |
Agric | +0.247 |
Ribbon | +0.244 |
PLA | +0.244 |
Neg logit contributions | |
anasia | -0.279 |
vas | -0.259 |
Bengals | -0.252 |
[* | -0.248 |
cius | -0.245 |
Token | space |
Token ID | 13200 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
anasia | +0.828 |
vas | +0.764 |
Bengals | +0.738 |
[* | +0.727 |
cius | +0.712 |
Neg logit contributions | |
ASC | -1.122 |
eur | -0.996 |
Agric | -0.992 |
Ribbon | -0.982 |
PLA | -0.982 |
Token | ); |
Token ID | 1776 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
ASC | +0.116 |
eur | +0.100 |
Agric | +0.100 |
PLA | +0.099 |
Ribbon | +0.099 |
Neg logit contributions | |
anasia | -0.115 |
vas | -0.107 |
Bengals | -0.104 |
[* | -0.102 |
cius | -0.101 |
Token | // |
Token ID | 3373 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
anasia | +0.267 |
vas | +0.243 |
Bengals | +0.234 |
[* | +0.230 |
cius | +0.226 |
Neg logit contributions | |
ASC | -0.414 |
eur | -0.370 |
Agric | -0.369 |
Ribbon | -0.365 |
PLA | -0.364 |
Token | this |
Token ID | 428 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
anasia | +0.058 |
vas | +0.054 |
Bengals | +0.053 |
[* | +0.052 |
cius | +0.051 |
Neg logit contributions | |
ASC | -0.060 |
eur | -0.052 |
Agric | -0.052 |
PLA | -0.051 |
orate | -0.051 |
Token | public |
Token ID | 1171 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
anasia | +0.541 |
vas | +0.506 |
Bengals | +0.490 |
[* | +0.481 |
cius | +0.468 |
Neg logit contributions | |
ASC | -0.659 |
eur | -0.579 |
Agric | -0.574 |
PLA | -0.572 |
orate | -0.570 |
Token | sculpture |
Token ID | 26924 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
ASC | +0.831 |
eur | +0.732 |
Agric | +0.727 |
Ribbon | +0.719 |
orate | +0.718 |
Neg logit contributions | |
anasia | -0.710 |
vas | -0.654 |
Bengals | -0.638 |
[* | -0.628 |
cius | -0.621 |
Token | by |
Token ID | 416 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
anasia | +0.162 |
vas | +0.150 |
Bengals | +0.145 |
[* | +0.143 |
cius | +0.141 |
Neg logit contributions | |
ASC | -0.186 |
eur | -0.163 |
Agric | -0.162 |
Ribbon | -0.160 |
PLA | -0.160 |
Token | Eld |
Token ID | 19208 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
ASC | +0.301 |
eur | +0.265 |
Agric | +0.264 |
PLA | +0.261 |
Ribbon | +0.261 |
Neg logit contributions | |
anasia | -0.253 |
vas | -0.234 |
Bengals | -0.227 |
[* | -0.223 |
cius | -0.219 |
Token | on |
Token ID | 261 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
ASC | +0.664 |
eur | +0.596 |
Agric | +0.589 |
orate | +0.584 |
Ribbon | +0.581 |
Neg logit contributions | |
anasia | -0.485 |
vas | -0.450 |
Bengals | -0.436 |
[* | -0.428 |
cius | -0.418 |
Token | Garn |
Token ID | 30937 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
anasia | +3.424 |
vas | +3.184 |
Bengals | +3.129 |
[* | +3.061 |
cius | +2.993 |
Neg logit contributions | |
ASC | -3.818 |
PLA | -3.347 |
eur | -3.265 |
orate | -3.240 |
parity | -3.239 |
Token | et |
Token ID | 316 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
anasia | +0.821 |
vas | +0.752 |
Bengals | +0.725 |
[* | +0.713 |
cius | +0.700 |
Neg logit contributions | |
ASC | -1.207 |
eur | -1.072 |
Agric | -1.068 |
PLA | -1.059 |
Ribbon | -1.057 |
Token | uses |
Token ID | 3544 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ASC | +0.044 |
eur | +0.039 |
Agric | +0.039 |
PLA | +0.038 |
Ribbon | +0.038 |
Neg logit contributions | |
anasia | -0.038 |
vas | -0.036 |
Bengals | -0.035 |
[* | -0.034 |
cius | -0.033 |
Token | just |
Token ID | 655 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
ASC | +0.886 |
eur | +0.778 |
Agric | +0.775 |
Ribbon | +0.768 |
orate | +0.764 |
Neg logit contributions | |
anasia | -0.787 |
vas | -0.723 |
Bengals | -0.702 |
[* | -0.695 |
cius | -0.684 |
Token | a |
Token ID | 257 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
ASC | +0.666 |
eur | +0.588 |
Agric | +0.585 |
Ribbon | +0.578 |
orate | +0.578 |
Neg logit contributions | |
anasia | -0.540 |
vas | -0.497 |
Bengals | -0.482 |
[* | -0.475 |
cius | -0.468 |
Token | state |
Token ID | 5219 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
anasia | +0.061 |
vas | +0.057 |
Bengals | +0.056 |
[* | +0.055 |
cius | +0.054 |
Neg logit contributions | |
ASC | -0.042 |
eur | -0.036 |
Agric | -0.035 |
PLA | -0.035 |
orate | -0.035 |
Token | ); |
Token ID | 5619 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
anasia | +0.737 |
vas | +0.670 |
Bengals | +0.644 |
[* | +0.630 |
cius | +0.619 |
Neg logit contributions | |
ASC | -1.227 |
eur | -1.098 |
Agric | -1.093 |
Ribbon | -1.083 |
PLA | -1.082 |
Token | ... |
Token ID | 2644 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
anasia | +0.736 |
vas | +0.672 |
Bengals | +0.644 |
[* | +0.633 |
cius | +0.613 |
Neg logit contributions | |
ASC | -1.305 |
eur | -1.167 |
Agric | -1.159 |
PLA | -1.155 |
Ribbon | -1.148 |
Token | } |
Token ID | 1782 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
anasia | +0.481 |
vas | +0.437 |
Bengals | +0.420 |
[* | +0.412 |
cius | +0.401 |
Neg logit contributions | |
ASC | -0.838 |
eur | -0.751 |
Agric | -0.747 |
PLA | -0.742 |
Ribbon | -0.741 |
Token | pub |
Token ID | 2240 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
ASC | +0.069 |
eur | +0.061 |
Agric | +0.061 |
Ribbon | +0.060 |
PLA | +0.060 |
Neg logit contributions | |
anasia | -0.046 |
vas | -0.042 |
Bengals | -0.041 |
[* | -0.040 |
cius | -0.039 |
Token | fn |
Token ID | 24714 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
anasia | +0.524 |
vas | +0.479 |
Bengals | +0.464 |
[* | +0.455 |
cius | +0.447 |
Neg logit contributions | |
ASC | -0.761 |
eur | -0.678 |
Agric | -0.676 |
Ribbon | -0.669 |
PLA | -0.668 |
Token | undo |
Token ID | 23981 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
anasia | +3.534 |
vas | +3.403 |
Bengals | +3.234 |
[* | +3.225 |
cius | +3.086 |
Neg logit contributions | |
ASC | -3.569 |
eur | -3.085 |
PLA | -3.077 |
Agric | -3.054 |
Ribbon | -3.023 |
Token | _ |
Token ID | 62 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ASC | +0.046 |
eur | +0.041 |
Agric | +0.040 |
PLA | +0.040 |
Ribbon | +0.040 |
Neg logit contributions | |
anasia | -0.043 |
vas | -0.040 |
Bengals | -0.039 |
[* | -0.039 |
cius | -0.038 |
Token | move |
Token ID | 21084 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
ASC | +1.555 |
eur | +1.380 |
orate | +1.345 |
PLA | +1.336 |
Agric | +1.325 |
Neg logit contributions | |
anasia | -1.377 |
vas | -1.287 |
Bengals | -1.267 |
[* | -1.224 |
cius | -1.215 |
Token | ( |
Token ID | 357 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
ASC | +0.556 |
eur | +0.496 |
Agric | +0.490 |
orate | +0.489 |
Ribbon | +0.485 |
Neg logit contributions | |
anasia | -0.364 |
vas | -0.331 |
Bengals | -0.323 |
cius | -0.314 |
[* | -0.312 |
Token | & |
Token ID | 1222 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
anasia | +0.423 |
vas | +0.388 |
Bengals | +0.375 |
[* | +0.368 |
cius | +0.362 |
Neg logit contributions | |
ASC | -0.594 |
eur | -0.527 |
Agric | -0.526 |
Ribbon | -0.520 |
PLA | -0.520 |
Token | active |
Token ID | 4075 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
anasia | +0.287 |
vas | +0.264 |
Bengals | +0.257 |
[* | +0.252 |
cius | +0.249 |
Neg logit contributions | |
ASC | -0.337 |
eur | -0.297 |
Agric | -0.296 |
Ribbon | -0.292 |
PLA | -0.291 |
Token | : |
Token ID | 25 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
anasia | +1.028 |
vas | +0.953 |
Bengals | +0.924 |
[* | +0.912 |
cius | +0.895 |
Neg logit contributions | |
ASC | -1.212 |
eur | -1.063 |
Agric | -1.059 |
PLA | -1.047 |
Ribbon | -1.046 |
Token |
|
Token ID | 198 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
anasia | +0.076 |
vas | +0.069 |
Bengals | +0.067 |
[* | +0.066 |
cius | +0.065 |
Neg logit contributions | |
ASC | -0.110 |
eur | -0.098 |
Agric | -0.098 |
Ribbon | -0.097 |
PLA | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ASC | +0.293 |
eur | +0.261 |
Agric | +0.259 |
PLA | +0.256 |
Ribbon | +0.256 |
Neg logit contributions | |
anasia | -0.199 |
vas | -0.182 |
Bengals | -0.175 |
[* | -0.172 |
cius | -0.170 |
Token | pub |
Token ID | 12984 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ASC | +0.159 |
eur | +0.139 |
Agric | +0.138 |
Ribbon | +0.137 |
PLA | +0.137 |
Neg logit contributions | |
anasia | -0.142 |
vas | -0.132 |
Bengals | -0.128 |
[* | -0.126 |
cius | -0.124 |
Token | struct |
Token ID | 2878 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
anasia | +0.911 |
vas | +0.826 |
Bengals | +0.789 |
[* | +0.772 |
cius | +0.752 |
Neg logit contributions | |
ASC | -1.760 |
eur | -1.576 |
Agric | -1.570 |
PLA | -1.566 |
Ribbon | -1.560 |
Token | Guard |
Token ID | 4932 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
anasia | +3.503 |
vas | +3.323 |
Bengals | +3.242 |
[* | +3.204 |
cius | +3.113 |
Neg logit contributions | |
ASC | -3.554 |
PLA | -3.055 |
eur | -3.014 |
orate | -3.004 |
Agric | -2.952 |
Token | { |
Token ID | 1391 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
anasia | +0.061 |
vas | +0.054 |
Bengals | +0.052 |
[* | +0.050 |
cius | +0.049 |
Neg logit contributions | |
ASC | -0.140 |
eur | -0.127 |
Agric | -0.126 |
Ribbon | -0.125 |
PLA | -0.125 |
Token | ... |
Token ID | 2644 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
anasia | +2.698 |
vas | +2.548 |
Bengals | +2.464 |
[* | +2.430 |
cius | +2.373 |
Neg logit contributions | |
ASC | -3.338 |
eur | -2.909 |
PLA | -2.909 |
Agric | -2.868 |
orate | -2.863 |
Token | } |
Token ID | 1782 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
anasia | +0.631 |
vas | +0.580 |
Bengals | +0.561 |
[* | +0.552 |
cius | +0.542 |
Neg logit contributions | |
ASC | -0.851 |
eur | -0.754 |
Agric | -0.752 |
Ribbon | -0.743 |
PLA | -0.743 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
anasia | +0.089 |
vas | +0.082 |
Bengals | +0.079 |
[* | +0.077 |
cius | +0.076 |
Neg logit contributions | |
ASC | -0.130 |
eur | -0.116 |
Agric | -0.115 |
Ribbon | -0.114 |
PLA | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ASC | +1.309 |
Agric | +1.147 |
eur | +1.144 |
Ribbon | +1.133 |
orate | +1.126 |
Neg logit contributions | |
anasia | -1.248 |
vas | -1.144 |
Bengals | -1.106 |
[* | -1.098 |
cius | -1.087 |
Token | Fine |
Token ID | 17867 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ASC | +1.241 |
Agric | +1.094 |
Ribbon | +1.087 |
eur | +1.082 |
PLA | +1.072 |
Neg logit contributions | |
anasia | -1.157 |
vas | -1.057 |
Bengals | -1.009 |
cius | -1.005 |
[* | -1.005 |
Token | cut |
Token ID | 2005 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ASC | +0.097 |
eur | +0.086 |
Agric | +0.085 |
PLA | +0.085 |
Ribbon | +0.084 |
Neg logit contributions | |
anasia | -0.070 |
vas | -0.065 |
Bengals | -0.063 |
[* | -0.061 |
cius | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
anasia | +0.122 |
vas | +0.112 |
Bengals | +0.109 |
[* | +0.107 |
cius | +0.105 |
Neg logit contributions | |
ASC | -0.157 |
eur | -0.138 |
Agric | -0.138 |
PLA | -0.136 |
Ribbon | -0.136 |
Token | 4 |
Token ID | 604 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
anasia | +0.131 |
vas | +0.120 |
Bengals | +0.117 |
[* | +0.115 |
cius | +0.113 |
Neg logit contributions | |
ASC | -0.161 |
eur | -0.142 |
Agric | -0.142 |
Ribbon | -0.140 |
PLA | -0.140 |
Token | garlic |
Token ID | 17644 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
ASC | +0.188 |
eur | +0.166 |
Agric | +0.165 |
Ribbon | +0.164 |
orate | +0.163 |
Neg logit contributions | |
anasia | -0.156 |
vas | -0.143 |
Bengals | -0.138 |
[* | -0.137 |
cius | -0.135 |
Token | cloves |
Token ID | 45025 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
anasia | +1.895 |
vas | +1.742 |
Bengals | +1.652 |
[* | +1.543 |
cius | +1.471 |
Neg logit contributions | |
ASC | -5.118 |
eur | -4.692 |
PLA | -4.668 |
Agric | -4.616 |
Ribbon | -4.602 |
Token | and |
Token ID | 290 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
anasia | +2.555 |
vas | +2.401 |
Bengals | +2.313 |
[* | +2.280 |
cius | +2.213 |
Neg logit contributions | |
ASC | -3.420 |
eur | -3.035 |
PLA | -3.001 |
Agric | -2.999 |
Ribbon | -2.957 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
anasia | +0.505 |
vas | +0.460 |
Bengals | +0.446 |
[* | +0.439 |
cius | +0.432 |
Neg logit contributions | |
ASC | -0.680 |
eur | -0.602 |
Agric | -0.601 |
Ribbon | -0.595 |
orate | -0.594 |
Token | ginger |
Token ID | 25072 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
ASC | +0.091 |
eur | +0.081 |
Agric | +0.081 |
Ribbon | +0.080 |
orate | +0.080 |
Neg logit contributions | |
anasia | -0.068 |
vas | -0.062 |
Bengals | -0.060 |
[* | -0.059 |
cius | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
anasia | +2.173 |
vas | +2.028 |
Bengals | +1.961 |
[* | +1.918 |
cius | +1.875 |
Neg logit contributions | |
ASC | -2.782 |
eur | -2.452 |
PLA | -2.427 |
Agric | -2.427 |
Ribbon | -2.404 |
Token | of |
Token ID | 286 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ASC | +0.519 |
eur | +0.458 |
Agric | +0.457 |
Ribbon | +0.452 |
PLA | +0.451 |
Neg logit contributions | |
anasia | -0.402 |
vas | -0.370 |
Bengals | -0.358 |
[* | -0.352 |
cius | -0.346 |
Token | Sciences |
Token ID | 13473 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
anasia | +0.124 |
vas | +0.116 |
Bengals | +0.113 |
[* | +0.112 |
cius | +0.111 |
Neg logit contributions | |
ASC | -0.109 |
eur | -0.094 |
Agric | -0.093 |
Ribbon | -0.092 |
PLA | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
anasia | +0.593 |
vas | +0.548 |
Bengals | +0.532 |
[* | +0.523 |
cius | +0.515 |
Neg logit contributions | |
ASC | -0.712 |
eur | -0.626 |
Agric | -0.624 |
Ribbon | -0.616 |
PLA | -0.616 |
Token |
|
Token ID | 198 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
ASC | +0.136 |
eur | +0.121 |
Agric | +0.121 |
Ribbon | +0.119 |
PLA | +0.119 |
Neg logit contributions | |
anasia | -0.096 |
vas | -0.088 |
Bengals | -0.085 |
cius | -0.083 |
[* | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ASC | +0.028 |
eur | +0.025 |
Agric | +0.025 |
PLA | +0.024 |
Ribbon | +0.024 |
Neg logit contributions | |
anasia | -0.019 |
vas | -0.017 |
Bengals | -0.017 |
[* | -0.016 |
cius | -0.016 |
Token | Explore |
Token ID | 35433 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
anasia | +0.176 |
vas | +0.164 |
Bengals | +0.159 |
[* | +0.156 |
cius | +0.154 |
Neg logit contributions | |
ASC | -0.192 |
eur | -0.168 |
Agric | -0.166 |
PLA | -0.165 |
orate | -0.164 |
Token | further |
Token ID | 2252 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
anasia | +1.790 |
vas | +1.573 |
Bengals | +1.490 |
[* | +1.460 |
cius | +1.334 |
Neg logit contributions | |
ASC | -5.079 |
Agric | -4.610 |
eur | -4.608 |
orate | -4.572 |
Ribbon | -4.566 |
Token | : |
Token ID | 25 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
anasia | +1.114 |
vas | +1.033 |
Bengals | +1.003 |
[* | +0.988 |
cius | +0.975 |
Neg logit contributions | |
ASC | -1.211 |
eur | -1.059 |
Agric | -1.053 |
Ribbon | -1.041 |
PLA | -1.041 |
Token | New |
Token ID | 968 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
anasia | +0.509 |
vas | +0.474 |
Bengals | +0.461 |
[* | +0.455 |
cius | +0.447 |
Neg logit contributions | |
ASC | -0.530 |
eur | -0.462 |
Agric | -0.459 |
PLA | -0.454 |
Ribbon | -0.453 |
Token | Insight |
Token ID | 39917 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
anasia | +0.291 |
vas | +0.269 |
Bengals | +0.260 |
[* | +0.256 |
cius | +0.252 |
Neg logit contributions | |
ASC | -0.359 |
eur | -0.316 |
Agric | -0.315 |
Ribbon | -0.311 |
PLA | -0.311 |
Token | Into |
Token ID | 20008 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
anasia | +0.527 |
vas | +0.489 |
Bengals | +0.475 |
[* | +0.468 |
cius | +0.459 |
Neg logit contributions | |
ASC | -0.586 |
eur | -0.513 |
Agric | -0.510 |
PLA | -0.504 |
Ribbon | -0.504 |
Token | only |
Token ID | 691 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
anasia | +1.306 |
vas | +1.213 |
Bengals | +1.169 |
[* | +1.160 |
cius | +1.125 |
Neg logit contributions | |
ASC | -1.687 |
eur | -1.478 |
Agric | -1.472 |
PLA | -1.468 |
Ribbon | -1.460 |
Token | within |
Token ID | 1626 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ASC | +0.391 |
eur | +0.345 |
Agric | +0.344 |
Ribbon | +0.340 |
PLA | +0.339 |
Neg logit contributions | |
anasia | -0.317 |
vas | -0.292 |
Bengals | -0.284 |
[* | -0.279 |
cius | -0.275 |
Token | the |
Token ID | 262 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
anasia | +0.725 |
vas | +0.677 |
Bengals | +0.655 |
[* | +0.648 |
cius | +0.637 |
Neg logit contributions | |
ASC | -0.765 |
eur | -0.666 |
Agric | -0.662 |
PLA | -0.656 |
Ribbon | -0.655 |
Token | subject |
Token ID | 2426 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ASC | +0.296 |
eur | +0.257 |
Agric | +0.256 |
Ribbon | +0.252 |
PLA | +0.252 |
Neg logit contributions | |
anasia | -0.316 |
vas | -0.294 |
Bengals | -0.287 |
[* | -0.283 |
cius | -0.279 |
Token | areas |
Token ID | 3006 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
ASC | +1.122 |
eur | +0.991 |
Agric | +0.982 |
orate | +0.980 |
parity | +0.967 |
Neg logit contributions | |
anasia | -1.005 |
vas | -0.921 |
Bengals | -0.903 |
[* | -0.884 |
cius | -0.873 |
Token | enumer |
Token ID | 27056 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
anasia | +0.403 |
vas | +0.373 |
Bengals | +0.362 |
[* | +0.356 |
cius | +0.350 |
Neg logit contributions | |
ASC | -0.489 |
eur | -0.430 |
Agric | -0.429 |
PLA | -0.424 |
Ribbon | -0.424 |
Token | ated |
Token ID | 515 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
anasia | +3.678 |
vas | +3.453 |
Bengals | +3.405 |
[* | +3.364 |
cius | +3.312 |
Neg logit contributions | |
ASC | -3.185 |
eur | -2.705 |
Agric | -2.700 |
Ribbon | -2.691 |
PLA | -2.680 |
Token | under |
Token ID | 739 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
anasia | +1.085 |
vas | +1.002 |
Bengals | +0.967 |
[* | +0.956 |
cius | +0.934 |
Neg logit contributions | |
ASC | -1.461 |
eur | -1.291 |
Agric | -1.287 |
PLA | -1.275 |
Ribbon | -1.273 |
Token | section |
Token ID | 2665 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
ASC | +0.233 |
eur | +0.204 |
Agric | +0.203 |
Ribbon | +0.201 |
orate | +0.200 |
Neg logit contributions | |
anasia | -0.218 |
vas | -0.202 |
Bengals | -0.197 |
[* | -0.193 |
cius | -0.190 |
Token | 51 |
Token ID | 6885 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
anasia | +2.080 |
vas | +1.957 |
Bengals | +1.896 |
[* | +1.866 |
cius | +1.788 |
Neg logit contributions | |
ASC | -2.513 |
eur | -2.185 |
PLA | -2.172 |
Agric | -2.164 |
orate | -2.162 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ASC | +0.334 |
eur | +0.293 |
Agric | +0.292 |
Ribbon | +0.288 |
PLA | +0.288 |
Neg logit contributions | |
anasia | -0.290 |
vas | -0.269 |
Bengals | -0.261 |
[* | -0.257 |
cius | -0.252 |
Token | ( |
Token ID | 357 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
ASC | +0.544 |
eur | +0.478 |
Agric | +0.474 |
Ribbon | +0.472 |
PLA | +0.472 |
Neg logit contributions | |
anasia | -0.423 |
vas | -0.390 |
Bengals | -0.376 |
[* | -0.369 |
cius | -0.368 |
Token | path |
Token ID | 3108 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
anasia | +1.454 |
vas | +1.341 |
Bengals | +1.295 |
[* | +1.280 |
cius | +1.247 |
Neg logit contributions | |
ASC | -1.987 |
eur | -1.763 |
Agric | -1.758 |
Ribbon | -1.736 |
PLA | -1.736 |
Token | , |
Token ID | 837 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
anasia | +0.356 |
vas | +0.326 |
Bengals | +0.316 |
[* | +0.309 |
cius | +0.305 |
Neg logit contributions | |
ASC | -0.499 |
eur | -0.442 |
Agric | -0.439 |
PLA | -0.436 |
Ribbon | -0.435 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
anasia | +0.961 |
vas | +0.889 |
Bengals | +0.858 |
[* | +0.847 |
cius | +0.827 |
Neg logit contributions | |
ASC | -1.262 |
eur | -1.116 |
Agric | -1.112 |
PLA | -1.100 |
Ribbon | -1.099 |
Token | ) |
Token ID | 1267 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ASC | +0.097 |
eur | +0.086 |
Agric | +0.086 |
PLA | +0.085 |
Ribbon | +0.085 |
Neg logit contributions | |
anasia | -0.060 |
vas | -0.054 |
Bengals | -0.052 |
[* | -0.051 |
cius | -0.051 |
Token | = |
Token ID | 796 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
anasia | +1.300 |
vas | +1.205 |
Bengals | +1.170 |
[* | +1.154 |
cius | +1.113 |
Neg logit contributions | |
ASC | -1.702 |
eur | -1.515 |
Agric | -1.513 |
orate | -1.496 |
PLA | -1.492 |
Token | '. |
Token ID | 45302 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
anasia | +2.658 |
vas | +2.501 |
[* | +2.403 |
Bengals | +2.403 |
cius | +2.260 |
Neg logit contributions | |
ASC | -3.983 |
eur | -3.569 |
Agric | -3.551 |
PLA | -3.530 |
orate | -3.527 |
Token | cl |
Token ID | 565 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
anasia | +1.213 |
vas | +1.139 |
Bengals | +1.109 |
[* | +1.100 |
cius | +1.083 |
Neg logit contributions | |
ASC | -1.020 |
Agric | -0.874 |
eur | -0.871 |
Ribbon | -0.861 |
PLA | -0.856 |
Token | j |
Token ID | 73 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ASC | +2.163 |
eur | +1.926 |
orate | +1.897 |
Agric | +1.883 |
Ribbon | +1.873 |
Neg logit contributions | |
anasia | -1.844 |
vas | -1.710 |
Bengals | -1.669 |
[* | -1.630 |
cius | -1.608 |
Token | ' |
Token ID | 6 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
ASC | +0.944 |
eur | +0.838 |
Agric | +0.825 |
PLA | +0.821 |
Ribbon | +0.818 |
Neg logit contributions | |
anasia | -0.715 |
vas | -0.652 |
Bengals | -0.633 |
[* | -0.619 |
cius | -0.617 |
Token | OR |
Token ID | 6375 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
ASC | +3.022 |
eur | +2.632 |
Ribbon | +2.622 |
Agric | +2.615 |
parity | +2.604 |
Neg logit contributions | |
anasia | -2.519 |
vas | -2.287 |
cius | -2.199 |
Bengals | -2.191 |
[* | -2.148 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
anasia | +0.199 |
vas | +0.183 |
Bengals | +0.178 |
[* | +0.175 |
cius | +0.173 |
Neg logit contributions | |
ASC | -0.238 |
eur | -0.209 |
Agric | -0.208 |
PLA | -0.205 |
Ribbon | -0.205 |
Token | images |
Token ID | 4263 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
anasia | +0.063 |
vas | +0.058 |
Bengals | +0.056 |
[* | +0.055 |
cius | +0.054 |
Neg logit contributions | |
ASC | -0.087 |
eur | -0.077 |
Agric | -0.077 |
PLA | -0.076 |
Ribbon | -0.076 |
Token | directory |
Token ID | 8619 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
anasia | +0.093 |
vas | +0.086 |
Bengals | +0.083 |
[* | +0.082 |
cius | +0.081 |
Neg logit contributions | |
ASC | -0.108 |
eur | -0.095 |
Agric | -0.094 |
Ribbon | -0.093 |
PLA | -0.093 |
Token | ") |
Token ID | 4943 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
anasia | +0.401 |
vas | +0.370 |
Bengals | +0.359 |
[* | +0.354 |
cius | +0.348 |
Neg logit contributions | |
ASC | -0.471 |
eur | -0.413 |
Agric | -0.411 |
Ribbon | -0.407 |
PLA | -0.406 |
Token | args |
Token ID | 26498 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ASC | +0.111 |
eur | +0.098 |
Agric | +0.097 |
Ribbon | +0.096 |
PLA | +0.096 |
Neg logit contributions | |
anasia | -0.091 |
vas | -0.084 |
Bengals | -0.081 |
[* | -0.080 |
cius | -0.079 |
Token | = |
Token ID | 796 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
anasia | +0.648 |
vas | +0.595 |
Bengals | +0.576 |
[* | +0.567 |
cius | +0.556 |
Neg logit contributions | |
ASC | -0.901 |
eur | -0.799 |
Agric | -0.797 |
Ribbon | -0.789 |
PLA | -0.788 |
Token | v |
Token ID | 410 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
anasia | +2.814 |
vas | +2.686 |
[* | +2.589 |
Bengals | +2.560 |
cius | +2.427 |
Neg logit contributions | |
ASC | -3.845 |
eur | -3.422 |
Agric | -3.396 |
orate | -3.378 |
PLA | -3.367 |
Token | ars |
Token ID | 945 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
ASC | +0.073 |
eur | +0.063 |
Agric | +0.063 |
PLA | +0.062 |
Ribbon | +0.062 |
Neg logit contributions | |
anasia | -0.077 |
vas | -0.072 |
Bengals | -0.070 |
[* | -0.069 |
cius | -0.068 |
Token | ( |
Token ID | 7 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
anasia | +0.574 |
vas | +0.534 |
Bengals | +0.519 |
[* | +0.513 |
cius | +0.504 |
Neg logit contributions | |
ASC | -0.600 |
eur | -0.522 |
Agric | -0.520 |
Ribbon | -0.514 |
PLA | -0.514 |
Token | ap |
Token ID | 499 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
anasia | +1.824 |
vas | +1.702 |
Bengals | +1.652 |
[* | +1.639 |
cius | +1.606 |
Neg logit contributions | |
ASC | -1.748 |
Agric | -1.527 |
eur | -1.521 |
Ribbon | -1.511 |
orate | -1.498 |
Token | . |
Token ID | 13 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
ASC | +0.713 |
eur | +0.619 |
Agric | +0.614 |
PLA | +0.612 |
orate | +0.609 |
Neg logit contributions | |
anasia | -0.663 |
vas | -0.616 |
Bengals | -0.598 |
[* | -0.586 |
cius | -0.578 |
Token | ulse |
Token ID | 9615 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
anasia | +0.013 |
vas | +0.011 |
Bengals | +0.011 |
[* | +0.011 |
cius | +0.010 |
Neg logit contributions | |
ASC | -0.032 |
eur | -0.029 |
Agric | -0.029 |
PLA | -0.028 |
Ribbon | -0.028 |
Token | period |
Token ID | 2278 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
anasia | +0.802 |
vas | +0.744 |
Bengals | +0.723 |
[* | +0.712 |
cius | +0.702 |
Neg logit contributions | |
ASC | -0.877 |
eur | -0.768 |
Agric | -0.763 |
Ribbon | -0.755 |
PLA | -0.754 |
Token | ", |
Token ID | 1600 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
anasia | +0.668 |
vas | +0.614 |
Bengals | +0.596 |
[* | +0.585 |
cius | +0.577 |
Neg logit contributions | |
ASC | -0.857 |
eur | -0.763 |
Agric | -0.754 |
Ribbon | -0.747 |
orate | -0.747 |
Token | Float |
Token ID | 48436 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
anasia | +0.508 |
vas | +0.472 |
Bengals | +0.459 |
[* | +0.452 |
cius | +0.445 |
Neg logit contributions | |
ASC | -0.537 |
eur | -0.468 |
Agric | -0.466 |
Ribbon | -0.461 |
PLA | -0.460 |
Token | ) |
Token ID | 8 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
anasia | +0.948 |
vas | +0.888 |
Bengals | +0.865 |
[* | +0.854 |
cius | +0.840 |
Neg logit contributions | |
ASC | -0.888 |
eur | -0.768 |
Agric | -0.766 |
PLA | -0.755 |
Ribbon | -0.754 |
Token | = |
Token ID | 796 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
anasia | +0.688 |
vas | +0.629 |
Bengals | +0.610 |
[* | +0.596 |
cius | +0.591 |
Neg logit contributions | |
ASC | -0.941 |
eur | -0.835 |
Agric | -0.830 |
Ribbon | -0.822 |
PLA | -0.821 |
Token | 1 |
Token ID | 352 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
anasia | +2.735 |
vas | +2.617 |
[* | +2.485 |
Bengals | +2.477 |
cius | +2.397 |
Neg logit contributions | |
ASC | -3.870 |
eur | -3.442 |
Agric | -3.393 |
PLA | -3.383 |
orate | -3.374 |
Token | // |
Token ID | 3373 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ASC | +0.485 |
eur | +0.429 |
Agric | +0.427 |
Ribbon | +0.423 |
PLA | +0.422 |
Neg logit contributions | |
anasia | -0.390 |
vas | -0.356 |
Bengals | -0.346 |
[* | -0.339 |
cius | -0.337 |
Token | seconds |
Token ID | 4201 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
ASC | +1.316 |
eur | +1.170 |
Agric | +1.167 |
PLA | +1.155 |
Ribbon | +1.153 |
Neg logit contributions | |
anasia | -0.867 |
vas | -0.780 |
Bengals | -0.757 |
[* | -0.740 |
cius | -0.729 |
Token | 1 |
Token ID | 352 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
anasia | +1.169 |
vas | +1.084 |
Bengals | +1.045 |
[* | +1.031 |
cius | +1.006 |
Neg logit contributions | |
ASC | -1.586 |
eur | -1.403 |
Agric | -1.394 |
PLA | -1.382 |
Ribbon | -1.378 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
anasia | +0.473 |
vas | +0.436 |
Bengals | +0.422 |
[* | +0.415 |
cius | +0.411 |
Neg logit contributions | |
ASC | -0.559 |
eur | -0.493 |
Agric | -0.490 |
Ribbon | -0.484 |
PLA | -0.484 |
Token | | |
Token ID | 930 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
ASC | +0.506 |
eur | +0.444 |
Agric | +0.442 |
PLA | +0.437 |
Ribbon | +0.436 |
Neg logit contributions | |
anasia | -0.445 |
vas | -0.412 |
Bengals | -0.399 |
[* | -0.393 |
cius | -0.388 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
anasia | +0.448 |
vas | +0.415 |
Bengals | +0.403 |
[* | +0.397 |
cius | +0.389 |
Neg logit contributions | |
ASC | -0.531 |
eur | -0.466 |
Agric | -0.464 |
PLA | -0.461 |
orate | -0.459 |
Token | | |
Token ID | 930 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
anasia | +0.980 |
vas | +0.904 |
Bengals | +0.878 |
[* | +0.864 |
cius | +0.844 |
Neg logit contributions | |
ASC | -1.249 |
eur | -1.102 |
Agric | -1.097 |
Ribbon | -1.086 |
PLA | -1.086 |
Token | struct |
Token ID | 2878 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
anasia | +0.618 |
vas | +0.572 |
Bengals | +0.555 |
[* | +0.547 |
cius | +0.534 |
Neg logit contributions | |
ASC | -0.769 |
eur | -0.678 |
Agric | -0.673 |
PLA | -0.668 |
Ribbon | -0.667 |
Token | Board |
Token ID | 5926 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
anasia | +2.476 |
vas | +2.308 |
Bengals | +2.249 |
[* | +2.214 |
cius | +2.118 |
Neg logit contributions | |
ASC | -3.058 |
eur | -2.654 |
PLA | -2.651 |
orate | -2.639 |
Agric | -2.600 |
Token | { |
Token ID | 1391 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
anasia | +0.988 |
vas | +0.873 |
Bengals | +0.831 |
[* | +0.813 |
cius | +0.783 |
Neg logit contributions | |
ASC | -2.349 |
eur | -2.130 |
Agric | -2.123 |
PLA | -2.106 |
Ribbon | -2.106 |
Token | | |
Token ID | 930 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
anasia | +2.816 |
vas | +2.628 |
Bengals | +2.534 |
[* | +2.487 |
cius | +2.421 |
Neg logit contributions | |
ASC | -3.824 |
eur | -3.382 |
PLA | -3.346 |
Ribbon | -3.318 |
Agric | -3.316 |
Token | ^ |
Token ID | 10563 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
anasia | +1.104 |
vas | +1.023 |
Bengals | +0.991 |
[* | +0.976 |
cius | +0.955 |
Neg logit contributions | |
ASC | -1.350 |
eur | -1.188 |
Agric | -1.180 |
PLA | -1.171 |
Ribbon | -1.169 |
Token | ^^^^ |
Token ID | 39397 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
anasia | +0.611 |
vas | +0.566 |
Bengals | +0.549 |
[* | +0.541 |
cius | +0.530 |
Neg logit contributions | |
ASC | -0.729 |
eur | -0.641 |
Agric | -0.638 |
PLA | -0.631 |
Ribbon | -0.631 |
Token | ^^^^ |
Token ID | 39397 |
Feature activation | +3.49e-04 |
Pos logit contributions | |
ASC | +0.561 |
eur | +0.484 |
Agric | +0.483 |
PLA | +0.476 |
Ribbon | +0.475 |
Neg logit contributions | |
anasia | -0.609 |
vas | -0.569 |
Bengals | -0.552 |
[* | -0.544 |
cius | -0.541 |
Token | ^^ |
Token ID | 18237 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
ASC | +0.000 |
eur | +0.000 |
Agric | +0.000 |
PLA | +0.000 |
Ribbon | +0.000 |
Neg logit contributions | |
anasia | -0.000 |
vas | -0.000 |
Bengals | -0.000 |
[* | -0.000 |
cius | -0.000 |
Token | out |
Token ID | 503 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
anasia | +0.132 |
vas | +0.120 |
Bengals | +0.116 |
[* | +0.114 |
cius | +0.112 |
Neg logit contributions | |
ASC | -0.194 |
eur | -0.173 |
Agric | -0.172 |
Ribbon | -0.170 |
PLA | -0.170 |
Token | at |
Token ID | 379 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
anasia | +0.962 |
vas | +0.887 |
Bengals | +0.858 |
[* | +0.845 |
cius | +0.830 |
Neg logit contributions | |
ASC | -1.236 |
eur | -1.092 |
Agric | -1.087 |
Ribbon | -1.075 |
PLA | -1.075 |
Token | http |
Token ID | 2638 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
anasia | +0.531 |
vas | +0.490 |
Bengals | +0.474 |
[* | +0.467 |
cius | +0.459 |
Neg logit contributions | |
ASC | -0.662 |
eur | -0.584 |
Agric | -0.582 |
Ribbon | -0.575 |
PLA | -0.575 |
Token | :// |
Token ID | 1378 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
anasia | +0.846 |
vas | +0.780 |
Bengals | +0.754 |
[* | +0.749 |
cius | +0.722 |
Neg logit contributions | |
ASC | -1.197 |
Agric | -1.063 |
eur | -1.060 |
Ribbon | -1.055 |
orate | -1.050 |
Token | w |
Token ID | 86 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
anasia | +1.522 |
vas | +1.413 |
Bengals | +1.371 |
[* | +1.352 |
cius | +1.337 |
Neg logit contributions | |
ASC | -1.586 |
Agric | -1.377 |
eur | -1.368 |
Ribbon | -1.363 |
PLA | -1.355 |
Token | ashington |
Token ID | 2542 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
anasia | +2.027 |
vas | +1.892 |
Bengals | +1.849 |
[* | +1.820 |
cius | +1.803 |
Neg logit contributions | |
ASC | -1.624 |
Agric | -1.379 |
eur | -1.377 |
Ribbon | -1.371 |
PLA | -1.360 |
Token | beer |
Token ID | 42428 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
anasia | +2.372 |
vas | +2.118 |
Bengals | +2.040 |
cius | +2.010 |
[* | +1.968 |
Neg logit contributions | |
ASC | -4.274 |
Agric | -3.830 |
Ribbon | -3.823 |
parity | -3.806 |
Dynam | -3.786 |
Token | . |
Token ID | 13 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
anasia | +0.340 |
vas | +0.317 |
Bengals | +0.307 |
[* | +0.303 |
cius | +0.297 |
Neg logit contributions | |
ASC | -0.366 |
eur | -0.321 |
Agric | -0.318 |
PLA | -0.315 |
Ribbon | -0.314 |
Token | com |
Token ID | 785 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ASC | +0.262 |
eur | +0.227 |
Agric | +0.225 |
PLA | +0.222 |
orate | +0.222 |
Neg logit contributions | |
anasia | -0.285 |
vas | -0.267 |
Bengals | -0.260 |
[* | -0.256 |
cius | -0.252 |
Token | / |
Token ID | 14 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
anasia | +0.816 |
vas | +0.754 |
Bengals | +0.731 |
[* | +0.720 |
cius | +0.705 |
Neg logit contributions | |
ASC | -1.037 |
eur | -0.914 |
Agric | -0.910 |
PLA | -0.900 |
Ribbon | -0.899 |
Token | w |
Token ID | 86 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
ASC | +0.406 |
eur | +0.359 |
Agric | +0.356 |
Ribbon | +0.352 |
PLA | +0.352 |
Neg logit contributions | |
anasia | -0.350 |
vas | -0.324 |
Bengals | -0.314 |
[* | -0.309 |
cius | -0.304 |
Token | component |
Token ID | 7515 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ASC | +0.538 |
eur | +0.474 |
Agric | +0.473 |
Ribbon | +0.467 |
PLA | +0.466 |
Neg logit contributions | |
anasia | -0.437 |
vas | -0.399 |
Bengals | -0.389 |
[* | -0.380 |
cius | -0.377 |
Token | const |
Token ID | 1500 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
anasia | +0.790 |
vas | +0.730 |
Bengals | +0.705 |
[* | +0.695 |
cius | +0.681 |
Neg logit contributions | |
ASC | -1.029 |
eur | -0.909 |
Agric | -0.905 |
PLA | -0.896 |
Ribbon | -0.895 |
Token | float |
Token ID | 12178 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
anasia | +1.751 |
vas | +1.637 |
Bengals | +1.566 |
[* | +1.541 |
cius | +1.504 |
Neg logit contributions | |
ASC | -2.663 |
eur | -2.356 |
Agric | -2.352 |
PLA | -2.338 |
Ribbon | -2.327 |
Token | TA |
Token ID | 21664 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
anasia | +2.712 |
vas | +2.594 |
Bengals | +2.489 |
[* | +2.469 |
cius | +2.385 |
Neg logit contributions | |
ASC | -3.442 |
eur | -3.028 |
Agric | -3.018 |
PLA | -2.992 |
orate | -2.982 |
Token | U |
Token ID | 52 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
ASC | +0.710 |
eur | +0.624 |
Agric | +0.616 |
PLA | +0.613 |
Ribbon | +0.610 |
Neg logit contributions | |
anasia | -0.623 |
vas | -0.575 |
Bengals | -0.559 |
[* | -0.550 |
cius | -0.543 |
Token | = |
Token ID | 796 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
anasia | +0.561 |
vas | +0.519 |
Bengals | +0.503 |
[* | +0.495 |
cius | +0.486 |
Neg logit contributions | |
ASC | -0.696 |
eur | -0.613 |
Agric | -0.611 |
Ribbon | -0.604 |
PLA | -0.603 |
Token | 6 |
Token ID | 718 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
anasia | +2.771 |
vas | +2.663 |
Bengals | +2.533 |
[* | +2.490 |
cius | +2.435 |
Neg logit contributions | |
ASC | -3.750 |
eur | -3.324 |
PLA | -3.286 |
Agric | -3.254 |
orate | -3.249 |
Token | . |
Token ID | 13 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
anasia | +0.415 |
vas | +0.384 |
Bengals | +0.373 |
[* | +0.367 |
cius | +0.361 |
Neg logit contributions | |
ASC | -0.481 |
eur | -0.422 |
Agric | -0.420 |
Ribbon | -0.415 |
PLA | -0.415 |
Token | 283 |
Token ID | 30290 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
anasia | +0.601 |
vas | +0.569 |
Bengals | +0.556 |
[* | +0.552 |
cius | +0.543 |
Neg logit contributions | |
ASC | -0.357 |
eur | -0.295 |
Agric | -0.295 |
PLA | -0.289 |
Ribbon | -0.289 |
Token | 185 |
Token ID | 21652 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
ASC | +0.027 |
eur | +0.025 |
Agric | +0.024 |
PLA | +0.024 |
Ribbon | +0.024 |
Neg logit contributions | |
anasia | -0.017 |
vas | -0.016 |
Bengals | -0.015 |
[* | -0.015 |
cius | -0.015 |
Token | 307 |
Token ID | 22996 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
ASC | +0.373 |
eur | +0.327 |
Agric | +0.325 |
PLA | +0.321 |
Ribbon | +0.321 |
Neg logit contributions | |
anasia | -0.330 |
vas | -0.306 |
Bengals | -0.296 |
[* | -0.292 |
cius | -0.288 |
Token | had |
Token ID | 550 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ASC | +0.688 |
eur | +0.613 |
Agric | +0.604 |
orate | +0.598 |
parity | +0.598 |
Neg logit contributions | |
anasia | -0.597 |
vas | -0.547 |
Bengals | -0.534 |
cius | -0.523 |
[* | -0.522 |
Token | come |
Token ID | 1282 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
anasia | +0.821 |
vas | +0.760 |
Bengals | +0.736 |
[* | +0.725 |
cius | +0.708 |
Neg logit contributions | |
ASC | -1.034 |
eur | -0.910 |
Agric | -0.907 |
PLA | -0.899 |
Ribbon | -0.897 |
Token | on |
Token ID | 319 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
ASC | +1.060 |
eur | +0.934 |
Agric | +0.930 |
orate | +0.920 |
parity | +0.919 |
Neg logit contributions | |
anasia | -0.942 |
vas | -0.865 |
Bengals | -0.841 |
cius | -0.826 |
[* | -0.826 |
Token | a |
Token ID | 257 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
ASC | +0.766 |
eur | +0.671 |
Agric | +0.668 |
orate | +0.660 |
Ribbon | +0.659 |
Neg logit contributions | |
anasia | -0.707 |
vas | -0.651 |
Bengals | -0.634 |
[* | -0.624 |
cius | -0.617 |
Token | P |
Token ID | 350 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
ASC | +1.320 |
eur | +1.166 |
Agric | +1.159 |
Ribbon | +1.153 |
orate | +1.152 |
Neg logit contributions | |
anasia | -1.078 |
vas | -0.977 |
Bengals | -0.954 |
[* | -0.939 |
cius | -0.930 |
Token | IL |
Token ID | 4146 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
ASC | +0.033 |
eur | +0.028 |
Agric | +0.027 |
orate | +0.027 |
PLA | +0.027 |
Neg logit contributions | |
anasia | -0.042 |
vas | -0.039 |
Bengals | -0.038 |
[* | -0.038 |
cius | -0.037 |
Token | by |
Token ID | 416 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
ASC | +1.970 |
eur | +1.734 |
Agric | +1.719 |
PLA | +1.702 |
Ribbon | +1.700 |
Neg logit contributions | |
anasia | -1.822 |
vas | -1.670 |
Bengals | -1.620 |
[* | -1.595 |
cius | -1.590 |
Token | Raj |
Token ID | 13308 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
ASC | +0.274 |
eur | +0.240 |
Agric | +0.239 |
Ribbon | +0.236 |
PLA | +0.236 |
Neg logit contributions | |
anasia | -0.248 |
vas | -0.230 |
Bengals | -0.223 |
[* | -0.220 |
cius | -0.216 |
Token | endra |
Token ID | 48286 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
ASC | +0.027 |
eur | +0.024 |
Agric | +0.024 |
Ribbon | +0.024 |
orate | +0.024 |
Neg logit contributions | |
anasia | -0.027 |
vas | -0.025 |
Bengals | -0.024 |
[* | -0.024 |
cius | -0.023 |
Token | S |
Token ID | 311 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
ASC | +0.746 |
Agric | +0.663 |
eur | +0.662 |
Ribbon | +0.655 |
PLA | +0.649 |
Neg logit contributions | |
anasia | -0.563 |
vas | -0.514 |
Bengals | -0.497 |
[* | -0.492 |
cius | -0.485 |
Token | ont |
Token ID | 756 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
anasia | +0.051 |
vas | +0.047 |
Bengals | +0.046 |
[* | +0.045 |
cius | +0.045 |
Neg logit contributions | |
ASC | -0.052 |
eur | -0.045 |
Agric | -0.045 |
PLA | -0.044 |
Ribbon | -0.044 |
Token | Han |
Token ID | 9530 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
ASC | +0.067 |
eur | +0.059 |
Agric | +0.059 |
PLA | +0.058 |
Ribbon | +0.058 |
Neg logit contributions | |
anasia | -0.055 |
vas | -0.051 |
Bengals | -0.050 |
[* | -0.049 |
cius | -0.048 |
Token | Solo |
Token ID | 20284 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
anasia | +0.285 |
vas | +0.267 |
Bengals | +0.260 |
[* | +0.257 |
cius | +0.253 |
Neg logit contributions | |
ASC | -0.243 |
eur | -0.209 |
Agric | -0.208 |
Ribbon | -0.205 |
PLA | -0.205 |
Token | in |
Token ID | 287 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
anasia | +0.037 |
vas | +0.034 |
Bengals | +0.033 |
[* | +0.032 |
cius | +0.032 |
Neg logit contributions | |
ASC | -0.045 |
eur | -0.040 |
Agric | -0.040 |
Ribbon | -0.039 |
PLA | -0.039 |
Token | his |
Token ID | 465 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
anasia | +0.069 |
vas | +0.064 |
Bengals | +0.063 |
[* | +0.062 |
cius | +0.061 |
Neg logit contributions | |
ASC | -0.073 |
eur | -0.064 |
Agric | -0.063 |
PLA | -0.063 |
orate | -0.063 |
Token | classic |
Token ID | 6833 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ASC | +0.228 |
eur | +0.201 |
Agric | +0.200 |
Ribbon | +0.198 |
PLA | +0.197 |
Neg logit contributions | |
anasia | -0.188 |
vas | -0.173 |
Bengals | -0.168 |
[* | -0.166 |
cius | -0.163 |
Token | delivery |
Token ID | 7585 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ASC | +2.028 |
Agric | +1.797 |
eur | +1.794 |
Ribbon | +1.785 |
PLA | +1.763 |
Neg logit contributions | |
anasia | -1.627 |
vas | -1.484 |
Bengals | -1.437 |
[* | -1.423 |
cius | -1.416 |
Token | stride |
Token ID | 33769 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
ASC | +2.062 |
eur | +1.854 |
Agric | +1.818 |
Ribbon | +1.811 |
orate | +1.797 |
Neg logit contributions | |
anasia | -1.772 |
vas | -1.600 |
Bengals | -1.568 |
cius | -1.550 |
[* | -1.539 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
ASC | +0.791 |
eur | +0.700 |
Agric | +0.693 |
Ribbon | +0.686 |
PLA | +0.685 |
Neg logit contributions | |
anasia | -0.666 |
vas | -0.615 |
Bengals | -0.597 |
[* | -0.586 |
cius | -0.583 |
Token | Cricket |
Token ID | 34761 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
ASC | +0.008 |
eur | +0.007 |
Agric | +0.007 |
Ribbon | +0.007 |
PLA | +0.007 |
Neg logit contributions | |
anasia | -0.007 |
vas | -0.006 |
Bengals | -0.006 |
[* | -0.006 |
cius | -0.006 |
Token | nerd |
Token ID | 34712 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ASC | +0.047 |
eur | +0.042 |
Agric | +0.042 |
Ribbon | +0.041 |
PLA | +0.041 |
Neg logit contributions | |
anasia | -0.038 |
vas | -0.035 |
Bengals | -0.034 |
[* | -0.034 |
cius | -0.033 |
Token | os |
Token ID | 418 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
ASC | +0.259 |
eur | +0.229 |
Agric | +0.228 |
Ribbon | +0.226 |
PLA | +0.225 |
Neg logit contributions | |
anasia | -0.200 |
vas | -0.184 |
Bengals | -0.178 |
[* | -0.176 |
cius | -0.173 |
Token | just |
Token ID | 655 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
anasia | +0.244 |
vas | +0.223 |
Bengals | +0.215 |
[* | +0.211 |
cius | +0.206 |
Neg logit contributions | |
ASC | -0.385 |
eur | -0.344 |
Agric | -0.342 |
PLA | -0.339 |
Ribbon | -0.339 |
Token | make |
Token ID | 787 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
anasia | +0.172 |
vas | +0.157 |
Bengals | +0.151 |
[* | +0.149 |
cius | +0.145 |
Neg logit contributions | |
ASC | -0.267 |
eur | -0.238 |
Agric | -0.237 |
Ribbon | -0.235 |
PLA | -0.235 |
Token | K |
Token ID | 509 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
anasia | +0.217 |
vas | +0.202 |
Bengals | +0.196 |
[* | +0.194 |
cius | +0.190 |
Neg logit contributions | |
ASC | -0.224 |
eur | -0.194 |
Agric | -0.193 |
PLA | -0.191 |
Ribbon | -0.191 |
Token | essel |
Token ID | 7878 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
ASC | +0.225 |
eur | +0.187 |
Agric | +0.184 |
PLA | +0.182 |
orate | +0.181 |
Neg logit contributions | |
anasia | -0.362 |
vas | -0.342 |
Bengals | -0.335 |
[* | -0.331 |
cius | -0.327 |
Token | go |
Token ID | 467 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ASC | +0.774 |
eur | +0.687 |
Agric | +0.683 |
Ribbon | +0.676 |
PLA | +0.674 |
Neg logit contributions | |
anasia | -0.588 |
vas | -0.539 |
Bengals | -0.521 |
[* | -0.514 |
cius | -0.508 |
Token | away |
Token ID | 1497 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ASC | +0.832 |
eur | +0.735 |
Agric | +0.731 |
Ribbon | +0.724 |
orate | +0.718 |
Neg logit contributions | |
anasia | -0.720 |
vas | -0.663 |
Bengals | -0.644 |
[* | -0.635 |
cius | -0.630 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ASC | +2.116 |
eur | +1.864 |
Agric | +1.850 |
Ribbon | +1.828 |
parity | +1.810 |
Neg logit contributions | |
anasia | -2.007 |
vas | -1.850 |
Bengals | -1.801 |
cius | -1.780 |
[* | -1.762 |
Token | You |
Token ID | 921 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ASC | +0.924 |
Agric | +0.811 |
eur | +0.811 |
Ribbon | +0.802 |
PLA | +0.796 |
Neg logit contributions | |
anasia | -0.821 |
vas | -0.760 |
Bengals | -0.726 |
cius | -0.720 |
[* | -0.719 |
Token | even |
Token ID | 772 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ASC | +0.856 |
eur | +0.756 |
Agric | +0.751 |
PLA | +0.743 |
Ribbon | +0.743 |
Neg logit contributions | |
anasia | -0.690 |
vas | -0.635 |
Bengals | -0.615 |
[* | -0.605 |
cius | -0.596 |
Token | went |
Token ID | 1816 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ASC | +0.929 |
eur | +0.820 |
Agric | +0.814 |
Ribbon | +0.805 |
PLA | +0.803 |
Neg logit contributions | |
anasia | -0.801 |
vas | -0.735 |
Bengals | -0.714 |
[* | -0.702 |
cius | -0.696 |
Token | as |
Token ID | 355 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ASC | +1.124 |
eur | +1.004 |
Agric | +0.997 |
Ribbon | +0.994 |
PLA | +0.992 |
Neg logit contributions | |
anasia | -0.755 |
vas | -0.679 |
Bengals | -0.648 |
cius | -0.647 |
[* | -0.641 |
Token | meet |
Token ID | 1826 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
anasia | +0.258 |
vas | +0.237 |
Bengals | +0.229 |
[* | +0.226 |
cius | +0.222 |
Neg logit contributions | |
ASC | -0.347 |
eur | -0.308 |
Agric | -0.307 |
Ribbon | -0.304 |
PLA | -0.303 |
Token | government |
Token ID | 1230 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ASC | +0.210 |
eur | +0.183 |
Agric | +0.183 |
Ribbon | +0.180 |
PLA | +0.180 |
Neg logit contributions | |
anasia | -0.198 |
vas | -0.182 |
Bengals | -0.178 |
[* | -0.175 |
cius | -0.172 |
Token | commitments |
Token ID | 19405 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ASC | +1.151 |
eur | +1.012 |
parity | +1.006 |
Agric | +1.006 |
orate | +0.998 |
Neg logit contributions | |
anasia | -1.007 |
vas | -0.913 |
Bengals | -0.904 |
[* | -0.878 |
cius | -0.876 |
Token | without |
Token ID | 1231 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
ASC | +1.571 |
eur | +1.386 |
Agric | +1.373 |
Ribbon | +1.359 |
PLA | +1.358 |
Neg logit contributions | |
anasia | -1.377 |
vas | -1.264 |
Bengals | -1.226 |
[* | -1.203 |
cius | -1.187 |
Token | added |
Token ID | 2087 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ASC | +0.217 |
eur | +0.191 |
Agric | +0.190 |
Ribbon | +0.188 |
PLA | +0.187 |
Neg logit contributions | |
anasia | -0.190 |
vas | -0.175 |
Bengals | -0.170 |
[* | -0.168 |
cius | -0.166 |
Token | borrowing |
Token ID | 23669 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
ASC | +0.330 |
eur | +0.292 |
Agric | +0.292 |
Ribbon | +0.288 |
PLA | +0.287 |
Neg logit contributions | |
anasia | -0.259 |
vas | -0.237 |
Bengals | -0.231 |
[* | -0.227 |
cius | -0.225 |
Token | , |
Token ID | 11 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ASC | +2.304 |
eur | +2.034 |
Agric | +2.026 |
parity | +2.020 |
orate | +1.999 |
Neg logit contributions | |
anasia | -2.093 |
vas | -1.898 |
Bengals | -1.846 |
cius | -1.828 |
[* | -1.809 |
Token | those |
Token ID | 883 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
ASC | +0.260 |
eur | +0.227 |
Agric | +0.226 |
PLA | +0.224 |
Ribbon | +0.223 |
Neg logit contributions | |
anasia | -0.234 |
vas | -0.216 |
Bengals | -0.210 |
[* | -0.207 |
cius | -0.204 |
Token | " |
Token ID | 366 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
anasia | +0.050 |
vas | +0.045 |
Bengals | +0.044 |
[* | +0.043 |
cius | +0.043 |
Neg logit contributions | |
ASC | -0.062 |
eur | -0.055 |
Agric | -0.054 |
Ribbon | -0.054 |
orate | -0.054 |
Token | extra |
Token ID | 26086 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
anasia | +0.175 |
vas | +0.164 |
Bengals | +0.159 |
[* | +0.157 |
cius | +0.155 |
Neg logit contributions | |
ASC | -0.170 |
eur | -0.147 |
Agric | -0.146 |
PLA | -0.145 |
Ribbon | -0.144 |
Token | ordinary |
Token ID | 35947 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
ASC | +0.181 |
eur | +0.156 |
Agric | +0.156 |
PLA | +0.155 |
orate | +0.154 |
Neg logit contributions | |
anasia | -0.196 |
vas | -0.182 |
Bengals | -0.178 |
[* | -0.175 |
cius | -0.174 |
Token | than |
Token ID | 621 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
ASC | +0.573 |
eur | +0.511 |
Agric | +0.509 |
parity | +0.503 |
Ribbon | +0.502 |
Neg logit contributions | |
anasia | -0.412 |
vas | -0.374 |
Bengals | -0.362 |
[* | -0.356 |
cius | -0.351 |
Token | 60 |
Token ID | 3126 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
anasia | +0.292 |
vas | +0.267 |
Bengals | +0.258 |
[* | +0.253 |
cius | +0.250 |
Neg logit contributions | |
ASC | -0.409 |
eur | -0.364 |
Agric | -0.363 |
Ribbon | -0.358 |
PLA | -0.357 |
Token | percent |
Token ID | 1411 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
ASC | +0.094 |
eur | +0.081 |
Agric | +0.081 |
Ribbon | +0.080 |
PLA | +0.080 |
Neg logit contributions | |
anasia | -0.100 |
vas | -0.093 |
Bengals | -0.090 |
[* | -0.089 |
cius | -0.088 |
Token | of |
Token ID | 286 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ASC | +0.689 |
eur | +0.609 |
Agric | +0.604 |
parity | +0.599 |
PLA | +0.596 |
Neg logit contributions | |
anasia | -0.581 |
vas | -0.534 |
Bengals | -0.518 |
[* | -0.507 |
cius | -0.502 |
Token | our |
Token ID | 674 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
anasia | +0.192 |
vas | +0.177 |
Bengals | +0.172 |
[* | +0.170 |
cius | +0.167 |
Neg logit contributions | |
ASC | -0.217 |
eur | -0.190 |
Agric | -0.190 |
Ribbon | -0.187 |
PLA | -0.187 |
Token | gross |
Token ID | 10319 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
anasia | +0.124 |
vas | +0.115 |
Bengals | +0.112 |
[* | +0.110 |
cius | +0.109 |
Neg logit contributions | |
ASC | -0.124 |
eur | -0.108 |
Agric | -0.108 |
Ribbon | -0.106 |
PLA | -0.106 |
Token | domestic |
Token ID | 5928 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ASC | +1.817 |
eur | +1.550 |
Agric | +1.528 |
parity | +1.513 |
PLA | +1.509 |
Neg logit contributions | |
anasia | -2.347 |
vas | -2.186 |
Bengals | -2.141 |
[* | -2.106 |
cius | -2.097 |
Token | product |
Token ID | 1720 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
ASC | +1.327 |
eur | +1.196 |
Agric | +1.189 |
parity | +1.180 |
Ribbon | +1.179 |
Neg logit contributions | |
anasia | -0.673 |
vas | -0.603 |
Bengals | -0.574 |
[* | -0.560 |
cius | -0.558 |
Token | and |
Token ID | 290 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
anasia | +0.073 |
vas | +0.067 |
Bengals | +0.065 |
[* | +0.064 |
cius | +0.063 |
Neg logit contributions | |
ASC | -0.086 |
eur | -0.076 |
Agric | -0.075 |
PLA | -0.075 |
Ribbon | -0.074 |
Token | possess |
Token ID | 8588 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ASC | +0.321 |
eur | +0.284 |
Agric | +0.283 |
Ribbon | +0.279 |
PLA | +0.279 |
Neg logit contributions | |
anasia | -0.251 |
vas | -0.231 |
Bengals | -0.223 |
[* | -0.220 |
cius | -0.216 |
Token | enormous |
Token ID | 9812 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
anasia | +0.111 |
vas | +0.102 |
Bengals | +0.099 |
[* | +0.097 |
cius | +0.096 |
Neg logit contributions | |
ASC | -0.147 |
eur | -0.130 |
Agric | -0.129 |
Ribbon | -0.128 |
PLA | -0.127 |
Token | hiring |
Token ID | 12965 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
ASC | +0.304 |
eur | +0.262 |
Agric | +0.262 |
Ribbon | +0.258 |
PLA | +0.258 |
Neg logit contributions | |
anasia | -0.322 |
vas | -0.299 |
Bengals | -0.292 |
[* | -0.288 |
cius | -0.284 |
Token | for |
Token ID | 329 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
ASC | +0.431 |
eur | +0.378 |
Agric | +0.376 |
Ribbon | +0.372 |
PLA | +0.372 |
Neg logit contributions | |
anasia | -0.382 |
vas | -0.353 |
Bengals | -0.343 |
[* | -0.338 |
cius | -0.332 |
Token | entry |
Token ID | 5726 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
anasia | +0.434 |
vas | +0.401 |
Bengals | +0.390 |
[* | +0.384 |
cius | +0.379 |
Neg logit contributions | |
ASC | -0.470 |
eur | -0.412 |
Agric | -0.410 |
Ribbon | -0.405 |
PLA | -0.404 |
Token | - |
Token ID | 12 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
anasia | +0.290 |
vas | +0.267 |
Bengals | +0.259 |
[* | +0.254 |
cius | +0.250 |
Neg logit contributions | |
ASC | -0.382 |
eur | -0.338 |
Agric | -0.337 |
PLA | -0.333 |
Ribbon | -0.333 |
Token | level |
Token ID | 5715 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
anasia | +0.127 |
vas | +0.115 |
Bengals | +0.111 |
[* | +0.109 |
cius | +0.106 |
Neg logit contributions | |
ASC | -0.206 |
eur | -0.183 |
Agric | -0.183 |
PLA | -0.181 |
Ribbon | -0.181 |
Token | HR |
Token ID | 15172 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
anasia | +0.067 |
vas | +0.062 |
Bengals | +0.060 |
[* | +0.059 |
cius | +0.058 |
Neg logit contributions | |
ASC | -0.070 |
eur | -0.061 |
Agric | -0.061 |
Ribbon | -0.060 |
PLA | -0.060 |
Token | positions |
Token ID | 6116 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
anasia | +0.214 |
vas | +0.199 |
Bengals | +0.193 |
[* | +0.191 |
cius | +0.187 |
Neg logit contributions | |
ASC | -0.228 |
eur | -0.199 |
Agric | -0.198 |
Ribbon | -0.196 |
PLA | -0.196 |
Token | . |
Token ID | 13 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
ASC | +0.321 |
eur | +0.281 |
Agric | +0.280 |
PLA | +0.276 |
Ribbon | +0.276 |
Neg logit contributions | |
anasia | -0.284 |
vas | -0.263 |
Bengals | -0.255 |
[* | -0.251 |
cius | -0.247 |
Token | We |
Token ID | 775 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
ASC | +0.455 |
Agric | +0.396 |
eur | +0.395 |
Ribbon | +0.391 |
PLA | +0.389 |
Neg logit contributions | |
anasia | -0.452 |
vas | -0.421 |
Bengals | -0.405 |
[* | -0.399 |
cius | -0.398 |
Token | have |
Token ID | 423 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ASC | +0.685 |
eur | +0.603 |
Agric | +0.601 |
Ribbon | +0.594 |
orate | +0.593 |
Neg logit contributions | |
anasia | -0.559 |
vas | -0.512 |
Bengals | -0.497 |
[* | -0.489 |
cius | -0.481 |
Token | our |
Token ID | 674 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
ASC | +1.225 |
eur | +1.074 |
Agric | +1.073 |
Ribbon | +1.062 |
PLA | +1.058 |
Neg logit contributions | |
anasia | -1.062 |
vas | -0.974 |
Bengals | -0.944 |
[* | -0.932 |
cius | -0.922 |
Token | six |
Token ID | 2237 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
anasia | +0.887 |
vas | +0.823 |
Bengals | +0.800 |
[* | +0.788 |
cius | +0.775 |
Neg logit contributions | |
ASC | -0.988 |
eur | -0.864 |
Agric | -0.860 |
Ribbon | -0.850 |
PLA | -0.850 |
Token | financial |
Token ID | 3176 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
anasia | +0.777 |
vas | +0.717 |
Bengals | +0.694 |
[* | +0.683 |
cius | +0.670 |
Neg logit contributions | |
ASC | -1.000 |
eur | -0.883 |
Agric | -0.879 |
Ribbon | -0.870 |
PLA | -0.869 |
Token | institutions |
Token ID | 6712 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
anasia | +1.670 |
vas | +1.564 |
Bengals | +1.520 |
[* | +1.500 |
cius | +1.461 |
Neg logit contributions | |
ASC | -1.790 |
eur | -1.563 |
Agric | -1.549 |
PLA | -1.544 |
Ribbon | -1.544 |
Token | in |
Token ID | 287 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
anasia | +1.305 |
vas | +1.213 |
Bengals | +1.176 |
[* | +1.165 |
cius | +1.139 |
Neg logit contributions | |
ASC | -1.644 |
eur | -1.448 |
PLA | -1.443 |
Agric | -1.439 |
Ribbon | -1.438 |
Token | this |
Token ID | 428 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
anasia | +0.548 |
vas | +0.507 |
Bengals | +0.492 |
[* | +0.485 |
cius | +0.477 |
Neg logit contributions | |
ASC | -0.611 |
eur | -0.534 |
Agric | -0.533 |
Ribbon | -0.525 |
PLA | -0.525 |
Token | country |
Token ID | 1499 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
ASC | +0.312 |
eur | +0.272 |
Agric | +0.271 |
Ribbon | +0.267 |
PLA | +0.267 |
Neg logit contributions | |
anasia | -0.297 |
vas | -0.276 |
Bengals | -0.268 |
[* | -0.264 |
cius | -0.260 |
Token | own |
Token ID | 898 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
anasia | +0.059 |
vas | +0.055 |
Bengals | +0.053 |
[* | +0.052 |
cius | +0.052 |
Neg logit contributions | |
ASC | -0.070 |
eur | -0.061 |
Agric | -0.061 |
Ribbon | -0.060 |
PLA | -0.060 |
Token | assets |
Token ID | 6798 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
anasia | +0.776 |
vas | +0.713 |
Bengals | +0.689 |
[* | +0.678 |
cius | +0.666 |
Neg logit contributions | |
ASC | -1.056 |
eur | -0.935 |
Agric | -0.932 |
Ribbon | -0.922 |
PLA | -0.921 |
Token | equal |
Token ID | 4961 |
Feature activation | +4.90e-03 |
Pos logit contributions | |
anasia | +1.375 |
vas | +1.279 |
Bengals | +1.245 |
[* | +1.234 |
cius | +1.193 |
Neg logit contributions | |
ASC | -1.651 |
eur | -1.447 |
Agric | -1.446 |
PLA | -1.441 |
Ribbon | -1.436 |
Token | to |
Token ID | 284 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ASC | +0.004 |
eur | +0.003 |
Agric | +0.003 |
orate | +0.003 |
PLA | +0.003 |
Neg logit contributions | |
anasia | -0.003 |
vas | -0.003 |
Bengals | -0.003 |
[* | -0.003 |
cius | -0.003 |
Token | more |
Token ID | 517 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
ASC | +0.224 |
eur | +0.199 |
Agric | +0.198 |
parity | +0.197 |
Ribbon | +0.196 |
Neg logit contributions | |
anasia | -0.171 |
vas | -0.156 |
Bengals | -0.150 |
[* | -0.148 |
cius | -0.147 |
Token | about |
Token ID | 546 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
anasia | +1.293 |
vas | +1.211 |
Bengals | +1.173 |
[* | +1.162 |
cius | +1.129 |
Neg logit contributions | |
ASC | -1.501 |
eur | -1.316 |
Agric | -1.307 |
PLA | -1.301 |
Ribbon | -1.297 |
Token | differing |
Token ID | 28742 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
ASC | +0.574 |
eur | +0.502 |
Agric | +0.501 |
Ribbon | +0.495 |
orate | +0.492 |
Neg logit contributions | |
anasia | -0.521 |
vas | -0.480 |
Bengals | -0.466 |
[* | -0.458 |
cius | -0.455 |
Token | interpretation |
Token ID | 10794 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
anasia | +0.040 |
vas | +0.037 |
Bengals | +0.036 |
[* | +0.035 |
cius | +0.035 |
Neg logit contributions | |
ASC | -0.040 |
eur | -0.035 |
Agric | -0.035 |
Ribbon | -0.034 |
PLA | -0.034 |
Token | of |
Token ID | 286 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
ASC | +1.094 |
eur | +0.965 |
Agric | +0.955 |
PLA | +0.947 |
Ribbon | +0.945 |
Neg logit contributions | |
anasia | -0.936 |
vas | -0.862 |
Bengals | -0.836 |
[* | -0.812 |
cius | -0.811 |
Token | the |
Token ID | 262 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
anasia | +0.404 |
vas | +0.373 |
Bengals | +0.361 |
[* | +0.355 |
cius | +0.352 |
Neg logit contributions | |
ASC | -0.447 |
eur | -0.392 |
Agric | -0.390 |
Ribbon | -0.386 |
PLA | -0.384 |
Token | words |
Token ID | 2456 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
anasia | +0.423 |
vas | +0.390 |
Bengals | +0.378 |
[* | +0.372 |
cius | +0.365 |
Neg logit contributions | |
ASC | -0.532 |
eur | -0.469 |
Agric | -0.467 |
Ribbon | -0.462 |
PLA | -0.462 |
Token | in |
Token ID | 287 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ASC | +0.499 |
eur | +0.437 |
Agric | +0.436 |
Ribbon | +0.431 |
PLA | +0.430 |
Neg logit contributions | |
anasia | -0.423 |
vas | -0.388 |
Bengals | -0.376 |
[* | -0.368 |
cius | -0.366 |
Token | the |
Token ID | 262 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
ASC | +0.237 |
eur | +0.206 |
Agric | +0.205 |
Ribbon | +0.202 |
PLA | +0.202 |
Neg logit contributions | |
anasia | -0.241 |
vas | -0.223 |
Bengals | -0.217 |
[* | -0.213 |
cius | -0.212 |
Token | statements |
Token ID | 6299 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
anasia | +0.297 |
vas | +0.275 |
Bengals | +0.267 |
[* | +0.264 |
cius | +0.259 |
Neg logit contributions | |
ASC | -0.334 |
eur | -0.292 |
Agric | -0.291 |
PLA | -0.288 |
Ribbon | -0.288 |
Token | , |
Token ID | 11 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
anasia | +0.664 |
vas | +0.614 |
Bengals | +0.595 |
[* | +0.585 |
cius | +0.576 |
Neg logit contributions | |
ASC | -0.784 |
eur | -0.689 |
Agric | -0.686 |
Ribbon | -0.678 |
PLA | -0.678 |
Token | or |
Token ID | 393 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
ASC | +0.182 |
eur | +0.160 |
Agric | +0.160 |
Ribbon | +0.158 |
PLA | +0.157 |
Neg logit contributions | |
anasia | -0.147 |
vas | -0.135 |
Bengals | -0.131 |
[* | -0.128 |
cius | -0.127 |
Token | Carter |
Token ID | 10831 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
ASC | +0.417 |
eur | +0.369 |
Agric | +0.368 |
Ribbon | +0.364 |
PLA | +0.364 |
Neg logit contributions | |
anasia | -0.308 |
vas | -0.283 |
Bengals | -0.273 |
[* | -0.269 |
cius | -0.264 |
Token | re |
Token ID | 302 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
ASC | +0.579 |
eur | +0.506 |
Agric | +0.502 |
Ribbon | +0.498 |
PLA | +0.496 |
Neg logit contributions | |
anasia | -0.547 |
vas | -0.507 |
Bengals | -0.493 |
[* | -0.487 |
cius | -0.479 |
Token | run |
Token ID | 5143 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
anasia | +0.332 |
vas | +0.306 |
Bengals | +0.297 |
[* | +0.292 |
cius | +0.287 |
Neg logit contributions | |
ASC | -0.417 |
eur | -0.368 |
Agric | -0.366 |
Ribbon | -0.362 |
PLA | -0.362 |
Token | is |
Token ID | 318 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
anasia | +0.471 |
vas | +0.437 |
Bengals | +0.423 |
[* | +0.417 |
cius | +0.407 |
Neg logit contributions | |
ASC | -0.593 |
Agric | -0.521 |
eur | -0.521 |
PLA | -0.515 |
Ribbon | -0.514 |
Token | probably |
Token ID | 2192 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
ASC | +0.450 |
eur | +0.398 |
Agric | +0.396 |
Ribbon | +0.391 |
orate | +0.390 |
Neg logit contributions | |
anasia | -0.369 |
vas | -0.338 |
Bengals | -0.328 |
[* | -0.322 |
cius | -0.319 |
Token | a |
Token ID | 257 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
ASC | +0.169 |
eur | +0.148 |
Agric | +0.147 |
PLA | +0.145 |
Ribbon | +0.145 |
Neg logit contributions | |
anasia | -0.151 |
vas | -0.140 |
Bengals | -0.136 |
[* | -0.134 |
cius | -0.132 |
Token | best |
Token ID | 1266 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ASC | +0.067 |
eur | +0.059 |
Agric | +0.058 |
PLA | +0.058 |
Ribbon | +0.058 |
Neg logit contributions | |
anasia | -0.053 |
vas | -0.049 |
Bengals | -0.048 |
[* | -0.047 |
cius | -0.046 |
Token | - |
Token ID | 12 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ASC | +0.959 |
eur | +0.860 |
Agric | +0.855 |
Ribbon | +0.846 |
orate | +0.846 |
Neg logit contributions | |
anasia | -0.585 |
vas | -0.528 |
Bengals | -0.510 |
[* | -0.501 |
cius | -0.492 |
Token | case |
Token ID | 7442 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ASC | +0.778 |
eur | +0.641 |
Agric | +0.631 |
PLA | +0.625 |
Ribbon | +0.615 |
Neg logit contributions | |
anasia | -1.200 |
vas | -1.136 |
Bengals | -1.110 |
[* | -1.098 |
cius | -1.076 |
Token | scenario |
Token ID | 8883 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
ASC | +1.127 |
eur | +0.980 |
Agric | +0.975 |
orate | +0.957 |
Ribbon | +0.954 |
Neg logit contributions | |
anasia | -1.241 |
vas | -1.147 |
Bengals | -1.121 |
[* | -1.106 |
cius | -1.101 |
Token | . |
Token ID | 13 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
ASC | +0.419 |
eur | +0.367 |
Agric | +0.365 |
Ribbon | +0.360 |
PLA | +0.360 |
Neg logit contributions | |
anasia | -0.389 |
vas | -0.361 |
Bengals | -0.351 |
[* | -0.346 |
cius | -0.341 |
Token | . |
Token ID | 13 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
ASC | +0.995 |
eur | +0.881 |
Agric | +0.875 |
orate | +0.869 |
Ribbon | +0.866 |
Neg logit contributions | |
anasia | -0.832 |
vas | -0.762 |
Bengals | -0.740 |
[* | -0.723 |
cius | -0.716 |
Token | But |
Token ID | 887 |
Feature activation | -5.64e-03 |
Pos logit contributions | |
ASC | +0.533 |
eur | +0.468 |
Agric | +0.468 |
Ribbon | +0.463 |
PLA | +0.461 |
Neg logit contributions | |
anasia | -0.455 |
vas | -0.421 |
Bengals | -0.406 |
[* | -0.399 |
cius | -0.397 |
Token | Fox |
Token ID | 5426 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
anasia | +0.004 |
vas | +0.004 |
Bengals | +0.003 |
[* | +0.003 |
cius | +0.003 |
Neg logit contributions | |
ASC | -0.005 |
eur | -0.004 |
Agric | -0.004 |
PLA | -0.004 |
Ribbon | -0.004 |
Token | News |
Token ID | 3000 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ASC | +0.944 |
eur | +0.835 |
Agric | +0.829 |
PLA | +0.821 |
Ribbon | +0.821 |
Neg logit contributions | |
anasia | -0.771 |
vas | -0.711 |
Bengals | -0.688 |
[* | -0.677 |
cius | -0.669 |
Token | / |
Token ID | 14 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ASC | +1.421 |
eur | +1.251 |
Agric | +1.243 |
Ribbon | +1.233 |
PLA | +1.228 |
Neg logit contributions | |
anasia | -1.213 |
vas | -1.116 |
Bengals | -1.079 |
[* | -1.064 |
cius | -1.056 |
Token | O |
Token ID | 46 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ASC | +1.001 |
eur | +0.846 |
Agric | +0.829 |
PLA | +0.824 |
orate | +0.822 |
Neg logit contributions | |
anasia | -1.358 |
vas | -1.277 |
Bengals | -1.245 |
[* | -1.226 |
cius | -1.218 |
Token | pin |
Token ID | 11635 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
ASC | +1.088 |
eur | +0.981 |
Agric | +0.968 |
PLA | +0.960 |
Ribbon | +0.957 |
Neg logit contributions | |
anasia | -0.584 |
vas | -0.524 |
Bengals | -0.506 |
[* | -0.493 |
cius | -0.479 |
Token | ion |
Token ID | 295 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
anasia | +0.469 |
vas | +0.439 |
Bengals | +0.428 |
[* | +0.423 |
cius | +0.416 |
Neg logit contributions | |
ASC | -0.398 |
eur | -0.341 |
Agric | -0.339 |
PLA | -0.335 |
Ribbon | -0.334 |
Token | Dynamics |
Token ID | 33806 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
ASC | +0.972 |
eur | +0.850 |
Agric | +0.847 |
Ribbon | +0.837 |
PLA | +0.837 |
Neg logit contributions | |
anasia | -0.871 |
vas | -0.809 |
Bengals | -0.785 |
[* | -0.774 |
cius | -0.761 |
Token | did |
Token ID | 750 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ASC | +0.381 |
eur | +0.336 |
Agric | +0.334 |
Ribbon | +0.331 |
PLA | +0.330 |
Neg logit contributions | |
anasia | -0.306 |
vas | -0.283 |
Bengals | -0.274 |
[* | -0.270 |
cius | -0.265 |
Token | a |
Token ID | 257 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
ASC | +0.205 |
eur | +0.180 |
Agric | +0.179 |
PLA | +0.177 |
Ribbon | +0.177 |
Neg logit contributions | |
anasia | -0.169 |
vas | -0.157 |
Bengals | -0.152 |
[* | -0.150 |
cius | -0.146 |
Token | , |
Token ID | 11 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
anasia | +0.167 |
vas | +0.154 |
Bengals | +0.150 |
[* | +0.148 |
cius | +0.145 |
Neg logit contributions | |
ASC | -0.192 |
eur | -0.168 |
Agric | -0.168 |
Ribbon | -0.166 |
PLA | -0.166 |
Token | by |
Token ID | 416 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
anasia | +0.979 |
vas | +0.909 |
Bengals | +0.881 |
[* | +0.870 |
cius | +0.853 |
Neg logit contributions | |
ASC | -1.158 |
eur | -1.016 |
Agric | -1.010 |
PLA | -1.007 |
Ribbon | -1.002 |
Token | building |
Token ID | 2615 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
anasia | +0.567 |
vas | +0.528 |
Bengals | +0.512 |
[* | +0.505 |
cius | +0.496 |
Neg logit contributions | |
ASC | -0.610 |
eur | -0.532 |
Agric | -0.529 |
PLA | -0.524 |
Ribbon | -0.524 |
Token | up |
Token ID | 510 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
anasia | +0.144 |
vas | +0.134 |
Bengals | +0.130 |
[* | +0.128 |
cius | +0.125 |
Neg logit contributions | |
ASC | -0.165 |
eur | -0.144 |
Agric | -0.144 |
Ribbon | -0.142 |
PLA | -0.142 |
Token | their |
Token ID | 511 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
anasia | +0.503 |
vas | +0.469 |
Bengals | +0.455 |
[* | +0.448 |
cius | +0.440 |
Neg logit contributions | |
ASC | -0.554 |
eur | -0.484 |
Agric | -0.482 |
Ribbon | -0.477 |
PLA | -0.477 |
Token | military |
Token ID | 2422 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
anasia | +0.463 |
vas | +0.435 |
Bengals | +0.423 |
[* | +0.418 |
cius | +0.410 |
Neg logit contributions | |
ASC | -0.433 |
eur | -0.373 |
Agric | -0.372 |
Ribbon | -0.368 |
PLA | -0.368 |
Token | and |
Token ID | 290 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
anasia | +0.640 |
vas | +0.602 |
Bengals | +0.581 |
[* | +0.571 |
cius | +0.557 |
Neg logit contributions | |
ASC | -0.806 |
Agric | -0.706 |
eur | -0.704 |
Ribbon | -0.697 |
PLA | -0.695 |
Token | asking |
Token ID | 4737 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
anasia | +0.333 |
vas | +0.310 |
Bengals | +0.301 |
[* | +0.297 |
cius | +0.292 |
Neg logit contributions | |
ASC | -0.357 |
eur | -0.311 |
Agric | -0.309 |
PLA | -0.306 |
Ribbon | -0.306 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
anasia | +0.209 |
vas | +0.193 |
Bengals | +0.187 |
[* | +0.185 |
cius | +0.181 |
Neg logit contributions | |
ASC | -0.245 |
eur | -0.215 |
Agric | -0.214 |
PLA | -0.212 |
Ribbon | -0.212 |
Token | United |
Token ID | 1578 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
anasia | +0.976 |
vas | +0.921 |
Bengals | +0.896 |
[* | +0.880 |
cius | +0.866 |
Neg logit contributions | |
ASC | -0.923 |
eur | -0.796 |
Agric | -0.790 |
PLA | -0.786 |
orate | -0.784 |
Token | States |
Token ID | 1829 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
anasia | +0.109 |
vas | +0.103 |
Bengals | +0.100 |
[* | +0.100 |
cius | +0.098 |
Neg logit contributions | |
ASC | -0.061 |
eur | -0.049 |
Agric | -0.049 |
PLA | -0.048 |
Ribbon | -0.048 |
Token | has |
Token ID | 468 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
anasia | +1.239 |
vas | +1.153 |
Bengals | +1.116 |
[* | +1.099 |
cius | +1.071 |
Neg logit contributions | |
ASC | -1.577 |
eur | -1.386 |
Agric | -1.384 |
PLA | -1.372 |
orate | -1.369 |
Token | remained |
Token ID | 6150 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
anasia | +0.255 |
vas | +0.236 |
Bengals | +0.229 |
[* | +0.226 |
cius | +0.222 |
Neg logit contributions | |
ASC | -0.294 |
eur | -0.258 |
Agric | -0.257 |
Ribbon | -0.254 |
PLA | -0.253 |
Token | so |
Token ID | 523 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
anasia | +0.567 |
vas | +0.519 |
Bengals | +0.502 |
[* | +0.494 |
cius | +0.486 |
Neg logit contributions | |
ASC | -0.765 |
eur | -0.678 |
Agric | -0.676 |
PLA | -0.668 |
Ribbon | -0.668 |
Token | elusive |
Token ID | 29885 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ASC | +0.442 |
eur | +0.394 |
Agric | +0.391 |
parity | +0.386 |
Ribbon | +0.385 |
Neg logit contributions | |
anasia | -0.344 |
vas | -0.312 |
Bengals | -0.304 |
[* | -0.299 |
cius | -0.296 |
Token | , |
Token ID | 11 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
anasia | +0.227 |
vas | +0.210 |
Bengals | +0.204 |
[* | +0.201 |
cius | +0.197 |
Neg logit contributions | |
ASC | -0.270 |
eur | -0.237 |
Agric | -0.236 |
Ribbon | -0.234 |
PLA | -0.233 |
Token | physicists |
Token ID | 37898 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
anasia | +0.204 |
vas | +0.189 |
Bengals | +0.184 |
[* | +0.181 |
cius | +0.178 |
Neg logit contributions | |
ASC | -0.230 |
eur | -0.202 |
Agric | -0.201 |
PLA | -0.198 |
Ribbon | -0.198 |
Token | have |
Token ID | 423 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
anasia | +1.424 |
vas | +1.341 |
Bengals | +1.292 |
[* | +1.272 |
cius | +1.250 |
Neg logit contributions | |
ASC | -1.832 |
eur | -1.620 |
PLA | -1.614 |
Agric | -1.605 |
orate | -1.594 |
Token | turned |
Token ID | 2900 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ASC | +0.299 |
eur | +0.263 |
Agric | +0.262 |
Ribbon | +0.259 |
PLA | +0.259 |
Neg logit contributions | |
anasia | -0.252 |
vas | -0.233 |
Bengals | -0.226 |
[* | -0.223 |
cius | -0.219 |
Token | their |
Token ID | 511 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
ASC | +0.220 |
Agric | +0.193 |
eur | +0.192 |
Ribbon | +0.189 |
orate | +0.189 |
Neg logit contributions | |
anasia | -0.203 |
vas | -0.187 |
Bengals | -0.182 |
[* | -0.180 |
cius | -0.177 |
Token | sights |
Token ID | 21343 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ASC | +0.583 |
eur | +0.516 |
Agric | +0.513 |
orate | +0.507 |
Ribbon | +0.506 |
Neg logit contributions | |
anasia | -0.468 |
vas | -0.428 |
Bengals | -0.414 |
[* | -0.409 |
cius | -0.404 |
Token | to |
Token ID | 284 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
ASC | +1.251 |
eur | +1.102 |
Agric | +1.097 |
orate | +1.075 |
parity | +1.073 |
Neg logit contributions | |
anasia | -1.221 |
vas | -1.119 |
Bengals | -1.089 |
[* | -1.069 |
cius | -1.065 |
Token | ence |
Token ID | 594 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
anasia | +0.923 |
vas | +0.857 |
Bengals | +0.833 |
[* | +0.820 |
cius | +0.807 |
Neg logit contributions | |
ASC | -1.003 |
eur | -0.876 |
Agric | -0.872 |
PLA | -0.863 |
Ribbon | -0.863 |
Token | of |
Token ID | 286 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
anasia | +1.229 |
vas | +1.136 |
Bengals | +1.095 |
[* | +1.083 |
cius | +1.059 |
Neg logit contributions | |
ASC | -1.619 |
eur | -1.423 |
Agric | -1.421 |
PLA | -1.414 |
Ribbon | -1.410 |
Token | office |
Token ID | 2607 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
anasia | +0.532 |
vas | +0.494 |
Bengals | +0.478 |
[* | +0.471 |
cius | +0.462 |
Neg logit contributions | |
ASC | -0.634 |
eur | -0.556 |
Agric | -0.554 |
PLA | -0.550 |
Ribbon | -0.548 |
Token | , |
Token ID | 11 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
anasia | +0.347 |
vas | +0.322 |
Bengals | +0.312 |
[* | +0.308 |
cius | +0.303 |
Neg logit contributions | |
ASC | -0.393 |
eur | -0.344 |
Agric | -0.343 |
Ribbon | -0.338 |
PLA | -0.338 |
Token | and |
Token ID | 290 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
anasia | +0.867 |
vas | +0.803 |
Bengals | +0.778 |
[* | +0.767 |
cius | +0.753 |
Neg logit contributions | |
ASC | -1.024 |
eur | -0.899 |
Agric | -0.895 |
PLA | -0.886 |
Ribbon | -0.885 |
Token | the |
Token ID | 262 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
anasia | +0.994 |
vas | +0.925 |
Bengals | +0.892 |
[* | +0.883 |
cius | +0.868 |
Neg logit contributions | |
ASC | -1.161 |
eur | -1.013 |
Agric | -1.011 |
PLA | -1.005 |
Ribbon | -1.001 |
Token | sp |
Token ID | 599 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
anasia | +1.147 |
vas | +1.074 |
Bengals | +1.034 |
[* | +1.025 |
cius | +1.003 |
Neg logit contributions | |
ASC | -1.265 |
PLA | -1.097 |
Agric | -1.095 |
eur | -1.095 |
Ribbon | -1.084 |
Token | urn |
Token ID | 700 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
ASC | +0.327 |
eur | +0.285 |
Agric | +0.283 |
orate | +0.280 |
PLA | +0.280 |
Neg logit contributions | |
anasia | -0.312 |
vas | -0.292 |
Bengals | -0.284 |
[* | -0.279 |
cius | -0.275 |
Token | s |
Token ID | 82 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
anasia | +0.643 |
vas | +0.592 |
Bengals | +0.573 |
[* | +0.564 |
cius | +0.554 |
Neg logit contributions | |
ASC | -0.835 |
eur | -0.735 |
Agric | -0.735 |
PLA | -0.728 |
Ribbon | -0.726 |
Token |
|
Token ID | 198 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
anasia | +1.312 |
vas | +1.215 |
Bengals | +1.168 |
[* | +1.159 |
cius | +1.132 |
Neg logit contributions | |
ASC | -1.739 |
eur | -1.526 |
Agric | -1.526 |
PLA | -1.523 |
Ribbon | -1.516 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
ASC | +0.217 |
eur | +0.193 |
Agric | +0.192 |
PLA | +0.190 |
Ribbon | +0.190 |
Neg logit contributions | |
anasia | -0.148 |
vas | -0.135 |
Bengals | -0.130 |
[* | -0.128 |
cius | -0.127 |
Token | dB |
Token ID | 30221 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
ASC | +0.390 |
eur | +0.334 |
Agric | +0.333 |
PLA | +0.330 |
orate | +0.329 |
Neg logit contributions | |
anasia | -0.419 |
vas | -0.391 |
Bengals | -0.384 |
[* | -0.378 |
cius | -0.370 |
Token | m |
Token ID | 76 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
ASC | +0.273 |
eur | +0.238 |
Agric | +0.237 |
PLA | +0.234 |
Ribbon | +0.234 |
Neg logit contributions | |
anasia | -0.258 |
vas | -0.240 |
Bengals | -0.234 |
[* | -0.230 |
cius | -0.226 |
Token | Ret |
Token ID | 4990 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ASC | +0.322 |
eur | +0.274 |
Agric | +0.273 |
Ribbon | +0.269 |
PLA | +0.268 |
Neg logit contributions | |
anasia | -0.419 |
vas | -0.393 |
Bengals | -0.383 |
[* | -0.378 |
cius | -0.374 |
Token | ry |
Token ID | 563 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
anasia | +0.065 |
vas | +0.059 |
Bengals | +0.057 |
[* | +0.056 |
cius | +0.054 |
Neg logit contributions | |
ASC | -0.109 |
eur | -0.097 |
Agric | -0.097 |
PLA | -0.096 |
Ribbon | -0.096 |
Token | short |
Token ID | 1790 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
ASC | +0.580 |
eur | +0.499 |
Ribbon | +0.498 |
Agric | +0.496 |
parity | +0.491 |
Neg logit contributions | |
anasia | -0.670 |
vas | -0.621 |
Bengals | -0.612 |
[* | -0.599 |
cius | -0.597 |
Token | limit |
Token ID | 4179 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
anasia | +0.181 |
vas | +0.168 |
Bengals | +0.163 |
[* | +0.161 |
cius | +0.158 |
Neg logit contributions | |
ASC | -0.207 |
eur | -0.181 |
Agric | -0.180 |
Ribbon | -0.178 |
PLA | -0.178 |
Token | : |
Token ID | 25 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
anasia | +0.726 |
vas | +0.674 |
Bengals | +0.655 |
[* | +0.647 |
cius | +0.630 |
Neg logit contributions | |
ASC | -0.845 |
Agric | -0.741 |
eur | -0.740 |
Ribbon | -0.733 |
orate | -0.731 |
Token | 7 |
Token ID | 22 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ASC | +1.361 |
eur | +1.151 |
Agric | +1.133 |
PLA | +1.124 |
Ribbon | +1.123 |
Neg logit contributions | |
anasia | -1.765 |
vas | -1.657 |
Bengals | -1.614 |
[* | -1.591 |
cius | -1.578 |
Token | R |
Token ID | 371 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ASC | +1.068 |
eur | +0.922 |
Agric | +0.920 |
Ribbon | +0.919 |
orate | +0.897 |
Neg logit contributions | |
anasia | -1.212 |
vas | -1.131 |
Bengals | -1.095 |
cius | -1.078 |
[* | -1.075 |
Token | TS |
Token ID | 4694 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
ASC | +0.779 |
eur | +0.671 |
Agric | +0.667 |
PLA | +0.663 |
orate | +0.658 |
Neg logit contributions | |
anasia | -0.796 |
vas | -0.746 |
Bengals | -0.725 |
[* | -0.715 |
cius | -0.703 |
Token | thr |
Token ID | 5636 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ASC | +0.520 |
eur | +0.458 |
Agric | +0.453 |
Ribbon | +0.447 |
orate | +0.447 |
Neg logit contributions | |
anasia | -0.446 |
vas | -0.410 |
Bengals | -0.400 |
[* | -0.392 |
cius | -0.390 |
Token | web |
Token ID | 3992 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
anasia | +0.149 |
vas | +0.138 |
Bengals | +0.134 |
[* | +0.132 |
cius | +0.130 |
Neg logit contributions | |
ASC | -0.166 |
eur | -0.146 |
Agric | -0.145 |
Ribbon | -0.143 |
PLA | -0.143 |
Token | browser |
Token ID | 6444 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
anasia | +0.074 |
vas | +0.068 |
Bengals | +0.066 |
[* | +0.065 |
cius | +0.064 |
Neg logit contributions | |
ASC | -0.101 |
eur | -0.090 |
Agric | -0.089 |
Ribbon | -0.089 |
PLA | -0.088 |
Token | , |
Token ID | 11 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
ASC | +0.893 |
eur | +0.786 |
Agric | +0.782 |
Ribbon | +0.774 |
PLA | +0.772 |
Neg logit contributions | |
anasia | -0.754 |
vas | -0.696 |
Bengals | -0.675 |
[* | -0.664 |
cius | -0.655 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
anasia | +0.016 |
vas | +0.015 |
Bengals | +0.014 |
[* | +0.014 |
cius | +0.014 |
Neg logit contributions | |
ASC | -0.017 |
eur | -0.015 |
Agric | -0.015 |
Ribbon | -0.015 |
PLA | -0.015 |
Token | its |
Token ID | 663 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
anasia | +1.556 |
vas | +1.450 |
Bengals | +1.407 |
[* | +1.386 |
cius | +1.352 |
Neg logit contributions | |
ASC | -1.787 |
eur | -1.564 |
Agric | -1.560 |
PLA | -1.546 |
orate | -1.535 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
anasia | +0.858 |
vas | +0.796 |
Bengals | +0.772 |
[* | +0.760 |
cius | +0.743 |
Neg logit contributions | |
ASC | -1.068 |
eur | -0.939 |
Agric | -0.936 |
PLA | -0.927 |
orate | -0.924 |
Token | revenue |
Token ID | 6426 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
anasia | +0.727 |
vas | +0.673 |
Bengals | +0.652 |
[* | +0.642 |
cius | +0.630 |
Neg logit contributions | |
ASC | -0.884 |
eur | -0.777 |
Agric | -0.774 |
PLA | -0.766 |
Ribbon | -0.765 |
Token | increase |
Token ID | 2620 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
anasia | +0.014 |
vas | +0.013 |
Bengals | +0.013 |
[* | +0.012 |
cius | +0.012 |
Neg logit contributions | |
ASC | -0.020 |
eur | -0.018 |
Agric | -0.018 |
Ribbon | -0.018 |
orate | -0.018 |
Token | 24 |
Token ID | 1987 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
anasia | +1.030 |
vas | +0.954 |
Bengals | +0.928 |
[* | +0.913 |
cius | +0.885 |
Neg logit contributions | |
ASC | -1.330 |
eur | -1.163 |
Agric | -1.162 |
PLA | -1.156 |
Ribbon | -1.145 |
Token | percent |
Token ID | 1411 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
anasia | +0.057 |
vas | +0.053 |
Bengals | +0.052 |
[* | +0.051 |
cius | +0.050 |
Neg logit contributions | |
ASC | -0.055 |
eur | -0.048 |
Agric | -0.048 |
Ribbon | -0.047 |
PLA | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
ASC | +0.266 |
eur | +0.234 |
Agric | +0.233 |
Ribbon | +0.230 |
PLA | +0.230 |
Neg logit contributions | |
anasia | -0.231 |
vas | -0.214 |
Bengals | -0.207 |
[* | -0.204 |
cius | -0.201 |
Token | uring |
Token ID | 870 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
anasia | +2.428 |
vas | +2.276 |
Bengals | +2.196 |
[* | +2.171 |
cius | +2.099 |
Neg logit contributions | |
ASC | -2.962 |
Agric | -2.585 |
PLA | -2.562 |
eur | -2.560 |
orate | -2.557 |
Token | kernel |
Token ID | 9720 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
anasia | +1.099 |
vas | +1.023 |
Bengals | +0.986 |
[* | +0.973 |
cius | +0.944 |
Neg logit contributions | |
ASC | -1.497 |
eur | -1.320 |
Agric | -1.319 |
PLA | -1.305 |
Ribbon | -1.304 |
Token | rect |
Token ID | 13621 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
anasia | +1.641 |
vas | +1.540 |
Bengals | +1.484 |
[* | +1.467 |
cius | +1.412 |
Neg logit contributions | |
ASC | -2.056 |
eur | -1.805 |
Agric | -1.800 |
PLA | -1.788 |
orate | -1.787 |
Token | K |
Token ID | 42 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
anasia | +1.434 |
vas | +1.310 |
Bengals | +1.272 |
[* | +1.254 |
cius | +1.227 |
Neg logit contributions | |
ASC | -1.960 |
Agric | -1.738 |
eur | -1.728 |
Ribbon | -1.721 |
PLA | -1.721 |
Token | ernel |
Token ID | 7948 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ASC | +0.541 |
eur | +0.483 |
PLA | +0.475 |
Agric | +0.474 |
Ribbon | +0.472 |
Neg logit contributions | |
anasia | -0.383 |
vas | -0.350 |
Bengals | -0.339 |
[* | -0.334 |
cius | -0.323 |
Token | = |
Token ID | 796 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
anasia | +0.150 |
vas | +0.138 |
Bengals | +0.134 |
[* | +0.132 |
cius | +0.129 |
Neg logit contributions | |
ASC | -0.203 |
eur | -0.180 |
Agric | -0.180 |
Ribbon | -0.178 |
PLA | -0.178 |
Token | c |
Token ID | 269 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
anasia | +2.697 |
vas | +2.608 |
Bengals | +2.498 |
[* | +2.479 |
cius | +2.355 |
Neg logit contributions | |
ASC | -3.506 |
eur | -3.086 |
PLA | -3.061 |
orate | -3.043 |
Agric | -3.037 |
Token | v |
Token ID | 85 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ASC | +0.609 |
eur | +0.547 |
Agric | +0.541 |
orate | +0.536 |
PLA | +0.535 |
Neg logit contributions | |
anasia | -0.384 |
vas | -0.346 |
Bengals | -0.336 |
[* | -0.328 |
cius | -0.321 |
Token | 2 |
Token ID | 17 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
anasia | +1.089 |
vas | +1.011 |
Bengals | +0.980 |
[* | +0.970 |
cius | +0.952 |
Neg logit contributions | |
ASC | -1.256 |
eur | -1.103 |
Agric | -1.100 |
Ribbon | -1.087 |
PLA | -1.085 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
anasia | +0.489 |
vas | +0.454 |
Bengals | +0.441 |
[* | +0.434 |
cius | +0.427 |
Neg logit contributions | |
ASC | -0.524 |
eur | -0.458 |
Agric | -0.456 |
PLA | -0.450 |
Ribbon | -0.450 |
Token | get |
Token ID | 1136 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
anasia | +0.844 |
vas | +0.791 |
Bengals | +0.770 |
[* | +0.762 |
cius | +0.753 |
Neg logit contributions | |
ASC | -0.769 |
eur | -0.666 |
Agric | -0.665 |
Ribbon | -0.657 |
orate | -0.654 |
Token | open |
Token ID | 1280 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
anasia | +0.725 |
vas | +0.670 |
Bengals | +0.647 |
[* | +0.637 |
cius | +0.620 |
Neg logit contributions | |
ASC | -1.020 |
eur | -0.902 |
Agric | -0.898 |
PLA | -0.892 |
Ribbon | -0.888 |
Token | new |
Token ID | 649 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
anasia | +0.624 |
vas | +0.580 |
Bengals | +0.563 |
[* | +0.553 |
cius | +0.543 |
Neg logit contributions | |
ASC | -0.751 |
eur | -0.659 |
Agric | -0.653 |
PLA | -0.649 |
Ribbon | -0.648 |
Token | store |
Token ID | 3650 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
anasia | +0.607 |
vas | +0.564 |
Bengals | +0.547 |
[* | +0.537 |
cius | +0.528 |
Neg logit contributions | |
ASC | -0.732 |
eur | -0.642 |
Agric | -0.637 |
PLA | -0.633 |
Ribbon | -0.632 |
Token | at |
Token ID | 379 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
anasia | +1.468 |
vas | +1.360 |
Bengals | +1.321 |
[* | +1.294 |
cius | +1.258 |
Neg logit contributions | |
ASC | -2.068 |
eur | -1.820 |
Agric | -1.810 |
PLA | -1.806 |
orate | -1.800 |
Token | Five |
Token ID | 10579 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
anasia | +0.385 |
vas | +0.358 |
Bengals | +0.347 |
[* | +0.342 |
cius | +0.336 |
Neg logit contributions | |
ASC | -0.431 |
eur | -0.377 |
Agric | -0.376 |
PLA | -0.371 |
Ribbon | -0.371 |
Token | Corn |
Token ID | 11424 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
anasia | +0.540 |
vas | +0.503 |
Bengals | +0.492 |
[* | +0.484 |
cius | +0.476 |
Neg logit contributions | |
ASC | -0.523 |
eur | -0.451 |
Agric | -0.449 |
PLA | -0.447 |
orate | -0.443 |
Token | ers |
Token ID | 364 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
anasia | +2.424 |
vas | +2.205 |
Bengals | +2.182 |
[* | +2.117 |
cius | +2.099 |
Neg logit contributions | |
ASC | -3.872 |
PLA | -3.407 |
eur | -3.387 |
Agric | -3.358 |
orate | -3.347 |
Token | in |
Token ID | 287 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
anasia | +0.291 |
vas | +0.269 |
Bengals | +0.260 |
[* | +0.256 |
cius | +0.252 |
Neg logit contributions | |
ASC | -0.363 |
eur | -0.320 |
Agric | -0.318 |
PLA | -0.315 |
Ribbon | -0.315 |
Token | Bur |
Token ID | 5481 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
anasia | +0.062 |
vas | +0.057 |
Bengals | +0.056 |
[* | +0.055 |
cius | +0.054 |
Neg logit contributions | |
ASC | -0.073 |
eur | -0.064 |
Agric | -0.064 |
Ribbon | -0.063 |
PLA | -0.063 |
Token | ien |
Token ID | 2013 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
ASC | +0.571 |
eur | +0.492 |
Agric | +0.490 |
Ribbon | +0.484 |
PLA | +0.484 |
Neg logit contributions | |
anasia | -0.628 |
vas | -0.587 |
Bengals | -0.571 |
[* | -0.564 |
cius | -0.556 |
Token |
|
Token ID | 198 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
anasia | +0.396 |
vas | +0.366 |
Bengals | +0.355 |
[* | +0.349 |
cius | +0.343 |
Neg logit contributions | |
ASC | -0.495 |
eur | -0.436 |
Agric | -0.434 |
PLA | -0.429 |
Ribbon | -0.429 |
Token | only |
Token ID | 691 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
anasia | +1.306 |
vas | +1.213 |
Bengals | +1.169 |
[* | +1.160 |
cius | +1.125 |
Neg logit contributions | |
ASC | -1.687 |
eur | -1.478 |
Agric | -1.472 |
PLA | -1.468 |
Ribbon | -1.460 |
Token | within |
Token ID | 1626 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ASC | +0.391 |
eur | +0.345 |
Agric | +0.344 |
Ribbon | +0.340 |
PLA | +0.339 |
Neg logit contributions | |
anasia | -0.317 |
vas | -0.292 |
Bengals | -0.284 |
[* | -0.279 |
cius | -0.275 |
Token | the |
Token ID | 262 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
anasia | +0.725 |
vas | +0.677 |
Bengals | +0.655 |
[* | +0.648 |
cius | +0.637 |
Neg logit contributions | |
ASC | -0.765 |
eur | -0.666 |
Agric | -0.662 |
PLA | -0.656 |
Ribbon | -0.655 |
Token | subject |
Token ID | 2426 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ASC | +0.296 |
eur | +0.257 |
Agric | +0.256 |
Ribbon | +0.252 |
PLA | +0.252 |
Neg logit contributions | |
anasia | -0.316 |
vas | -0.294 |
Bengals | -0.287 |
[* | -0.283 |
cius | -0.279 |
Token | areas |
Token ID | 3006 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
ASC | +1.122 |
eur | +0.991 |
Agric | +0.982 |
orate | +0.980 |
parity | +0.967 |
Neg logit contributions | |
anasia | -1.005 |
vas | -0.921 |
Bengals | -0.903 |
[* | -0.884 |
cius | -0.873 |
Token | enumer |
Token ID | 27056 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
anasia | +0.403 |
vas | +0.373 |
Bengals | +0.362 |
[* | +0.356 |
cius | +0.350 |
Neg logit contributions | |
ASC | -0.489 |
eur | -0.430 |
Agric | -0.429 |
PLA | -0.424 |
Ribbon | -0.424 |
Token | ated |
Token ID | 515 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
anasia | +3.678 |
vas | +3.453 |
Bengals | +3.405 |
[* | +3.364 |
cius | +3.312 |
Neg logit contributions | |
ASC | -3.185 |
eur | -2.705 |
Agric | -2.700 |
Ribbon | -2.691 |
PLA | -2.680 |
Token | under |
Token ID | 739 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
anasia | +1.085 |
vas | +1.002 |
Bengals | +0.967 |
[* | +0.956 |
cius | +0.934 |
Neg logit contributions | |
ASC | -1.461 |
eur | -1.291 |
Agric | -1.287 |
PLA | -1.275 |
Ribbon | -1.273 |
Token | section |
Token ID | 2665 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
ASC | +0.233 |
eur | +0.204 |
Agric | +0.203 |
Ribbon | +0.201 |
orate | +0.200 |
Neg logit contributions | |
anasia | -0.218 |
vas | -0.202 |
Bengals | -0.197 |
[* | -0.193 |
cius | -0.190 |
Token | 51 |
Token ID | 6885 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
anasia | +2.080 |
vas | +1.957 |
Bengals | +1.896 |
[* | +1.866 |
cius | +1.788 |
Neg logit contributions | |
ASC | -2.513 |
eur | -2.185 |
PLA | -2.172 |
Agric | -2.164 |
orate | -2.162 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ASC | +0.334 |
eur | +0.293 |
Agric | +0.292 |
Ribbon | +0.288 |
PLA | +0.288 |
Neg logit contributions | |
anasia | -0.290 |
vas | -0.269 |
Bengals | -0.261 |
[* | -0.257 |
cius | -0.252 |
Token | of |
Token ID | 286 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
anasia | +0.686 |
vas | +0.636 |
Bengals | +0.617 |
[* | +0.608 |
cius | +0.598 |
Neg logit contributions | |
ASC | -0.779 |
eur | -0.683 |
Agric | -0.680 |
Ribbon | -0.672 |
PLA | -0.672 |
Token | improvement |
Token ID | 9025 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
anasia | +0.127 |
vas | +0.119 |
Bengals | +0.115 |
[* | +0.114 |
cius | +0.112 |
Neg logit contributions | |
ASC | -0.130 |
eur | -0.113 |
Agric | -0.112 |
Ribbon | -0.111 |
PLA | -0.111 |
Token | that |
Token ID | 326 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
anasia | +0.326 |
vas | +0.302 |
Bengals | +0.294 |
[* | +0.289 |
cius | +0.284 |
Neg logit contributions | |
ASC | -0.369 |
eur | -0.323 |
Agric | -0.322 |
Ribbon | -0.318 |
PLA | -0.318 |
Token | values |
Token ID | 3815 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
anasia | +0.599 |
vas | +0.555 |
Bengals | +0.539 |
[* | +0.531 |
cius | +0.523 |
Neg logit contributions | |
ASC | -0.644 |
eur | -0.563 |
Agric | -0.560 |
Ribbon | -0.553 |
PLA | -0.553 |
Token | defect |
Token ID | 11855 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
anasia | +0.080 |
vas | +0.074 |
Bengals | +0.072 |
[* | +0.071 |
cius | +0.070 |
Neg logit contributions | |
ASC | -0.081 |
eur | -0.070 |
Agric | -0.070 |
Ribbon | -0.069 |
PLA | -0.069 |
Token | prevention |
Token ID | 14196 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
ASC | +0.136 |
eur | +0.120 |
Agric | +0.119 |
orate | +0.118 |
Ribbon | +0.117 |
Neg logit contributions | |
anasia | -0.120 |
vas | -0.111 |
Bengals | -0.108 |
[* | -0.106 |
cius | -0.104 |
Token | over |
Token ID | 625 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
anasia | +2.653 |
vas | +2.461 |
[* | +2.376 |
Bengals | +2.374 |
cius | +2.283 |
Neg logit contributions | |
ASC | -3.615 |
eur | -3.199 |
Agric | -3.198 |
PLA | -3.162 |
orate | -3.142 |
Token | defect |
Token ID | 11855 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
anasia | +0.789 |
vas | +0.739 |
Bengals | +0.716 |
[* | +0.709 |
cius | +0.694 |
Neg logit contributions | |
ASC | -0.805 |
eur | -0.697 |
Agric | -0.694 |
PLA | -0.689 |
Ribbon | -0.684 |
Token | detection |
Token ID | 13326 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ASC | +0.581 |
eur | +0.512 |
Agric | +0.507 |
orate | +0.501 |
Ribbon | +0.500 |
Neg logit contributions | |
anasia | -0.533 |
vas | -0.494 |
Bengals | -0.481 |
[* | -0.472 |
cius | -0.468 |
Token | . |
Token ID | 13 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
anasia | +0.889 |
vas | +0.822 |
Bengals | +0.797 |
[* | +0.787 |
cius | +0.771 |
Neg logit contributions | |
ASC | -1.065 |
eur | -0.935 |
Agric | -0.932 |
Ribbon | -0.921 |
PLA | -0.921 |
Token | It |
Token ID | 632 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
anasia | +0.025 |
vas | +0.023 |
Bengals | +0.022 |
[* | +0.022 |
cius | +0.022 |
Neg logit contributions | |
ASC | -0.028 |
eur | -0.024 |
Agric | -0.024 |
Ribbon | -0.024 |
PLA | -0.024 |
Token | in |
Token ID | 287 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
ASC | +0.504 |
eur | +0.439 |
Agric | +0.437 |
PLA | +0.432 |
Ribbon | +0.432 |
Neg logit contributions | |
anasia | -0.488 |
vas | -0.455 |
Bengals | -0.442 |
[* | -0.437 |
cius | -0.429 |
Token | the |
Token ID | 262 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
ASC | +0.645 |
eur | +0.564 |
Agric | +0.561 |
PLA | +0.554 |
Ribbon | +0.554 |
Neg logit contributions | |
anasia | -0.585 |
vas | -0.539 |
Bengals | -0.522 |
[* | -0.514 |
cius | -0.512 |
Token | presence |
Token ID | 4931 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
ASC | +0.063 |
eur | +0.056 |
Agric | +0.056 |
PLA | +0.055 |
Ribbon | +0.055 |
Neg logit contributions | |
anasia | -0.045 |
vas | -0.042 |
Bengals | -0.040 |
[* | -0.040 |
cius | -0.039 |
Token | of |
Token ID | 286 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
anasia | +0.358 |
vas | +0.330 |
Bengals | +0.319 |
[* | +0.315 |
cius | +0.308 |
Neg logit contributions | |
ASC | -0.475 |
eur | -0.419 |
Agric | -0.419 |
Ribbon | -0.414 |
PLA | -0.414 |
Token | a |
Token ID | 257 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
anasia | +0.685 |
vas | +0.633 |
Bengals | +0.613 |
[* | +0.604 |
cius | +0.596 |
Neg logit contributions | |
ASC | -0.820 |
eur | -0.721 |
Agric | -0.719 |
Ribbon | -0.710 |
PLA | -0.709 |
Token | TSA |
Token ID | 32453 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
anasia | +0.516 |
vas | +0.476 |
Bengals | +0.459 |
[* | +0.452 |
cius | +0.441 |
Neg logit contributions | |
ASC | -0.735 |
eur | -0.653 |
Agric | -0.651 |
PLA | -0.644 |
Ribbon | -0.644 |
Token | agent |
Token ID | 5797 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
anasia | +2.205 |
vas | +2.037 |
[* | +1.944 |
Bengals | +1.943 |
cius | +1.832 |
Neg logit contributions | |
ASC | -3.768 |
Agric | -3.383 |
eur | -3.354 |
orate | -3.352 |
PLA | -3.343 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
anasia | +1.361 |
vas | +1.263 |
Bengals | +1.221 |
[* | +1.213 |
cius | +1.177 |
Neg logit contributions | |
ASC | -1.612 |
Agric | -1.417 |
eur | -1.409 |
PLA | -1.403 |
Ribbon | -1.398 |
Token | Maybe |
Token ID | 6674 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
anasia | +0.012 |
vas | +0.011 |
Bengals | +0.011 |
cius | +0.011 |
[* | +0.011 |
Neg logit contributions | |
ASC | -0.013 |
Agric | -0.012 |
eur | -0.011 |
Ribbon | -0.011 |
Dynam | -0.011 |
Token | you |
Token ID | 345 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
ASC | +0.192 |
eur | +0.167 |
Agric | +0.166 |
Ribbon | +0.164 |
PLA | +0.164 |
Neg logit contributions | |
anasia | -0.199 |
vas | -0.184 |
Bengals | -0.179 |
[* | -0.177 |
cius | -0.175 |
Token | acted |
Token ID | 13134 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ASC | +0.579 |
eur | +0.511 |
Agric | +0.508 |
Ribbon | +0.501 |
orate | +0.500 |
Neg logit contributions | |
anasia | -0.504 |
vas | -0.461 |
Bengals | -0.449 |
[* | -0.441 |
cius | -0.437 |