Token | D |
Token ID | 360 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Debor | +1.030 |
� | +0.904 |
ト | +0.848 |
MSM | +0.845 |
unsus | +0.825 |
Neg logit contributions | |
grain | -1.048 |
urdue | -1.008 |
ellar | -1.004 |
Windsor | -0.984 |
font | -0.972 |
Token | DoS |
Token ID | 46498 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
grain | +0.994 |
urdue | +0.949 |
ellar | +0.947 |
Windsor | +0.927 |
font | +0.913 |
Neg logit contributions | |
Debor | -1.230 |
� | -1.092 |
ト | -1.032 |
MSM | -1.026 |
unsus | -1.006 |
Token | traffic |
Token ID | 4979 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
grain | +2.078 |
urdue | +1.998 |
ellar | +1.997 |
Windsor | +1.978 |
font | +1.957 |
Neg logit contributions | |
Debor | -1.562 |
� | -1.328 |
ト | -1.243 |
MSM | -1.219 |
� | -1.207 |
Token | would |
Token ID | 561 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
Debor | +0.302 |
� | +0.268 |
ト | +0.253 |
MSM | +0.253 |
unsus | +0.248 |
Neg logit contributions | |
grain | -0.244 |
urdue | -0.233 |
ellar | -0.232 |
Windsor | -0.226 |
font | -0.223 |
Token | be |
Token ID | 307 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
Debor | +2.435 |
� | +2.128 |
ト | +2.021 |
MSM | +2.017 |
unsus | +1.999 |
Neg logit contributions | |
grain | -2.367 |
urdue | -2.273 |
ellar | -2.244 |
Windsor | -2.208 |
font | -2.198 |
Token | mit |
Token ID | 10255 |
Feature activation | +9.25e+00 |
Pos logit contributions | |
Debor | +2.967 |
� | +2.550 |
MSM | +2.439 |
unsus | +2.399 |
ト | +2.396 |
Neg logit contributions | |
grain | -3.301 |
urdue | -3.206 |
ellar | -3.181 |
font | -3.082 |
Windsor | -3.070 |
Token | igated |
Token ID | 26963 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
Debor | +6.882 |
� | +5.933 |
ト | +5.751 |
MSM | +5.692 |
Swordsman | +5.548 |
Neg logit contributions | |
grain | -6.183 |
urdue | -6.141 |
Windsor | -6.010 |
ellar | -5.869 |
afety | -5.753 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Debor | +3.656 |
� | +3.213 |
MSM | +2.980 |
ト | +2.976 |
unsus | +2.957 |
Neg logit contributions | |
grain | -3.851 |
ellar | -3.668 |
urdue | -3.656 |
Windsor | -3.593 |
font | -3.519 |
Token | there |
Token ID | 612 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
Debor | +1.691 |
� | +1.495 |
ト | +1.413 |
MSM | +1.410 |
unsus | +1.383 |
Neg logit contributions | |
grain | -1.515 |
urdue | -1.445 |
ellar | -1.443 |
Windsor | -1.409 |
font | -1.391 |
Token | would |
Token ID | 561 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
Debor | +0.050 |
� | +0.044 |
ト | +0.042 |
MSM | +0.042 |
unsus | +0.041 |
Neg logit contributions | |
grain | -0.042 |
urdue | -0.040 |
ellar | -0.040 |
Windsor | -0.039 |
font | -0.039 |
Token | be |
Token ID | 307 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
Debor | +0.598 |
� | +0.530 |
ト | +0.501 |
MSM | +0.498 |
unsus | +0.488 |
Neg logit contributions | |
grain | -0.513 |
urdue | -0.490 |
ellar | -0.487 |
Windsor | -0.479 |
font | -0.471 |
Token | Flake |
Token ID | 39727 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
Debor | +0.869 |
� | +0.740 |
ト | +0.679 |
MSM | +0.672 |
unsus | +0.652 |
Neg logit contributions | |
grain | -1.290 |
urdue | -1.248 |
ellar | -1.243 |
Windsor | -1.229 |
font | -1.213 |
Token | ( |
Token ID | 7 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Debor | +0.517 |
� | +0.458 |
ト | +0.432 |
MSM | +0.430 |
unsus | +0.421 |
Neg logit contributions | |
grain | -0.442 |
urdue | -0.422 |
ellar | -0.421 |
Windsor | -0.412 |
font | -0.405 |
Token | R |
Token ID | 49 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
Debor | +1.072 |
� | +0.925 |
ト | +0.862 |
MSM | +0.854 |
unsus | +0.828 |
Neg logit contributions | |
grain | -1.337 |
urdue | -1.288 |
ellar | -1.285 |
Windsor | -1.264 |
font | -1.247 |
Token | - |
Token ID | 12 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
grain | +0.488 |
urdue | +0.465 |
ellar | +0.463 |
Windsor | +0.453 |
font | +0.446 |
Neg logit contributions | |
Debor | -0.685 |
� | -0.612 |
ト | -0.581 |
MSM | -0.579 |
unsus | -0.569 |
Token | Ari |
Token ID | 26529 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
Debor | +1.832 |
� | +1.512 |
ト | +1.373 |
MSM | +1.330 |
機 | +1.263 |
Neg logit contributions | |
grain | -3.964 |
urdue | -3.921 |
ellar | -3.874 |
Windsor | -3.817 |
font | -3.733 |
Token | z |
Token ID | 89 |
Feature activation | +8.98e+00 |
Pos logit contributions | |
Debor | +2.759 |
� | +2.450 |
MSM | +2.324 |
ト | +2.316 |
unsus | +2.297 |
Neg logit contributions | |
grain | -2.106 |
ellar | -2.087 |
urdue | -2.078 |
afety | -2.028 |
Windsor | -1.979 |
Token | .) |
Token ID | 2014 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Debor | +5.587 |
� | +4.862 |
ト | +4.524 |
MSM | +4.456 |
機 | +4.347 |
Neg logit contributions | |
grain | -7.362 |
ellar | -7.176 |
urdue | -7.001 |
Windsor | -6.971 |
font | -6.937 |
Token | after |
Token ID | 706 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
grain | +0.170 |
urdue | +0.162 |
ellar | +0.162 |
Windsor | +0.159 |
font | +0.156 |
Neg logit contributions | |
Debor | -0.207 |
� | -0.184 |
ト | -0.174 |
MSM | -0.173 |
unsus | -0.170 |
Token | he |
Token ID | 339 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Debor | +0.325 |
� | +0.287 |
ト | +0.271 |
MSM | +0.268 |
unsus | +0.263 |
Neg logit contributions | |
grain | -0.304 |
urdue | -0.291 |
ellar | -0.290 |
Windsor | -0.286 |
font | -0.281 |
Token | was |
Token ID | 373 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
Debor | +1.508 |
� | +1.327 |
ト | +1.261 |
MSM | +1.255 |
unsus | +1.244 |
Neg logit contributions | |
grain | -1.174 |
urdue | -1.122 |
ellar | -1.120 |
Windsor | -1.087 |
font | -1.076 |
Token | heard |
Token ID | 2982 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
Debor | +0.682 |
� | +0.609 |
ト | +0.579 |
MSM | +0.576 |
unsus | +0.566 |
Neg logit contributions | |
grain | -0.485 |
urdue | -0.462 |
ellar | -0.461 |
Windsor | -0.449 |
font | -0.442 |
Token |
|
Token ID | 198 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
grain | +1.468 |
ellar | +1.406 |
urdue | +1.397 |
Windsor | +1.389 |
font | +1.363 |
Neg logit contributions | |
Debor | -1.524 |
� | -1.341 |
ト | -1.264 |
MSM | -1.237 |
� | -1.228 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
grain | +1.314 |
urdue | +1.259 |
ellar | +1.256 |
Windsor | +1.233 |
font | +1.217 |
Neg logit contributions | |
Debor | -1.359 |
� | -1.195 |
ト | -1.123 |
MSM | -1.115 |
unsus | -1.092 |
Token | D |
Token ID | 35 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
grain | +1.035 |
ellar | +0.982 |
urdue | +0.979 |
Windsor | +0.960 |
font | +0.958 |
Neg logit contributions | |
Debor | -1.170 |
� | -1.019 |
MSM | -0.961 |
ト | -0.960 |
unsus | -0.949 |
Token | DoS |
Token ID | 46498 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
grain | +0.122 |
urdue | +0.117 |
ellar | +0.116 |
Windsor | +0.114 |
font | +0.112 |
Neg logit contributions | |
Debor | -0.152 |
� | -0.135 |
ト | -0.128 |
MSM | -0.127 |
unsus | -0.124 |
Token | Mit |
Token ID | 11707 |
Feature activation | +8.10e+00 |
Pos logit contributions | |
grain | +0.244 |
urdue | +0.235 |
ellar | +0.234 |
Windsor | +0.231 |
font | +0.227 |
Neg logit contributions | |
Debor | -0.225 |
� | -0.196 |
ト | -0.184 |
MSM | -0.182 |
unsus | -0.178 |
Token | igation |
Token ID | 7065 |
Feature activation | +8.74e+00 |
Pos logit contributions | |
Debor | +6.638 |
� | +5.795 |
MSM | +5.539 |
ト | +5.506 |
� | +5.298 |
Neg logit contributions | |
grain | -5.006 |
urdue | -4.934 |
Windsor | -4.705 |
ellar | -4.693 |
afety | -4.522 |
Token | – |
Token ID | 784 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Debor | +6.601 |
� | +5.735 |
MSM | +5.616 |
ト | +5.250 |
Swordsman | +5.222 |
Neg logit contributions | |
grain | -6.082 |
ellar | -6.045 |
urdue | -5.994 |
afety | -5.650 |
Windsor | -5.641 |
Token | No |
Token ID | 1400 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
Debor | +1.732 |
� | +1.531 |
MSM | +1.447 |
ト | +1.444 |
unsus | +1.405 |
Neg logit contributions | |
grain | -1.504 |
urdue | -1.445 |
ellar | -1.439 |
Windsor | -1.400 |
font | -1.385 |
Token | Silver |
Token ID | 7698 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Debor | +3.521 |
� | +3.103 |
MSM | +3.002 |
ト | +2.958 |
unsus | +2.894 |
Neg logit contributions | |
grain | -2.902 |
urdue | -2.819 |
ellar | -2.772 |
Windsor | -2.700 |
font | -2.674 |
Token | Bullet |
Token ID | 18003 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Debor | +2.501 |
� | +2.224 |
MSM | +2.110 |
ト | +2.085 |
unsus | +2.035 |
Neg logit contributions | |
grain | -1.802 |
urdue | -1.798 |
ellar | -1.764 |
Windsor | -1.674 |
afety | -1.662 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Debor | +1.938 |
� | +1.698 |
MSM | +1.600 |
ト | +1.588 |
unsus | +1.544 |
Neg logit contributions | |
grain | -1.919 |
urdue | -1.859 |
ellar | -1.851 |
Windsor | -1.798 |
font | -1.776 |
Token | v |
Token ID | 85 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
Debor | +2.181 |
� | +1.890 |
ト | +1.795 |
MSM | +1.759 |
unsus | +1.697 |
Neg logit contributions | |
grain | -2.657 |
urdue | -2.615 |
ellar | -2.607 |
Windsor | -2.563 |
afety | -2.548 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
Debor | +1.895 |
� | +1.649 |
ト | +1.566 |
MSM | +1.499 |
KEY | +1.453 |
Neg logit contributions | |
grain | -2.643 |
urdue | -2.603 |
ellar | -2.582 |
afety | -2.549 |
Windsor | -2.535 |
Token | . |
Token ID | 764 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
Debor | +1.712 |
� | +1.469 |
ト | +1.366 |
MSM | +1.366 |
機 | +1.285 |
Neg logit contributions | |
grain | -2.342 |
urdue | -2.291 |
ellar | -2.274 |
afety | -2.217 |
Windsor | -2.209 |
Token | COL |
Token ID | 20444 |
Feature activation | +5.11e+00 |
Pos logit contributions | |
Debor | +3.551 |
� | +3.159 |
MSM | +3.024 |
ト | +2.922 |
melanch | +2.863 |
Neg logit contributions | |
grain | -3.265 |
urdue | -3.151 |
ellar | -3.151 |
Windsor | -3.051 |
afety | -3.026 |
Token | OR |
Token ID | 1581 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
Debor | +3.435 |
� | +3.057 |
ト | +2.896 |
MSM | +2.848 |
KEY | +2.842 |
Neg logit contributions | |
grain | -3.953 |
urdue | -3.922 |
ellar | -3.834 |
afety | -3.822 |
Windsor | -3.742 |
Token | _ |
Token ID | 62 |
Feature activation | +8.62e+00 |
Pos logit contributions | |
Debor | +3.767 |
� | +3.369 |
ト | +3.184 |
KEY | +3.144 |
MSM | +3.093 |
Neg logit contributions | |
grain | -5.181 |
urdue | -5.097 |
ellar | -5.048 |
afety | -5.014 |
Windsor | -4.891 |
Token | B |
Token ID | 33 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
Debor | +4.122 |
� | +3.718 |
KEY | +3.370 |
MSM | +3.345 |
ト | +3.278 |
Neg logit contributions | |
grain | -8.114 |
ellar | -8.028 |
urdue | -8.027 |
afety | -7.906 |
Windsor | -7.767 |
Token | GR |
Token ID | 10761 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
Debor | +2.029 |
� | +1.786 |
MSM | +1.598 |
ト | +1.593 |
KEY | +1.575 |
Neg logit contributions | |
grain | -3.608 |
urdue | -3.561 |
ellar | -3.531 |
afety | -3.498 |
Windsor | -3.479 |
Token | 2 |
Token ID | 17 |
Feature activation | +7.46e+00 |
Pos logit contributions | |
Debor | +3.644 |
� | +3.278 |
ト | +3.093 |
KEY | +3.045 |
MSM | +2.953 |
Neg logit contributions | |
grain | -5.914 |
urdue | -5.911 |
ellar | -5.881 |
afety | -5.871 |
Windsor | -5.651 |
Token | G |
Token ID | 38 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
Debor | +4.434 |
� | +4.101 |
KEY | +3.909 |
MSM | +3.844 |
ト | +3.753 |
Neg logit contributions | |
grain | -5.996 |
ellar | -5.996 |
urdue | -5.982 |
afety | -5.921 |
ossession | -5.642 |
Token | RAY |
Token ID | 30631 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
Debor | +2.456 |
� | +2.198 |
ト | +2.025 |
MSM | +2.022 |
KEY | +2.015 |
Neg logit contributions | |
grain | -2.558 |
urdue | -2.501 |
afety | -2.470 |
ellar | -2.464 |
Windsor | -2.444 |
Token | trans |
Token ID | 7645 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
grain | +0.307 |
ellar | +0.294 |
urdue | +0.293 |
Windsor | +0.288 |
font | +0.285 |
Neg logit contributions | |
Debor | -0.294 |
� | -0.256 |
ト | -0.240 |
MSM | -0.239 |
unsus | -0.234 |
Token | cript |
Token ID | 6519 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
Debor | +2.593 |
� | +2.354 |
ト | +2.291 |
MSM | +2.270 |
unsus | +2.217 |
Neg logit contributions | |
grain | -1.107 |
urdue | -1.054 |
ellar | -1.051 |
Windsor | -1.019 |
afety | -0.959 |
Token | s |
Token ID | 82 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Debor | +3.154 |
� | +2.820 |
ト | +2.643 |
MSM | +2.560 |
機 | +2.532 |
Neg logit contributions | |
grain | -3.563 |
urdue | -3.516 |
ellar | -3.475 |
Windsor | -3.441 |
afety | -3.362 |
Token | / |
Token ID | 14 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
Debor | +1.522 |
� | +1.345 |
ト | +1.267 |
MSM | +1.258 |
機 | +1.222 |
Neg logit contributions | |
grain | -1.406 |
urdue | -1.347 |
ellar | -1.342 |
Windsor | -1.317 |
font | -1.291 |
Token | sc |
Token ID | 1416 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
Debor | +2.281 |
� | +2.069 |
ト | +1.976 |
MSM | +1.955 |
� | +1.912 |
Neg logit contributions | |
grain | -1.372 |
urdue | -1.331 |
ellar | -1.307 |
Windsor | -1.284 |
afety | -1.235 |
Token | aling |
Token ID | 4272 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
Debor | +1.782 |
� | +1.573 |
ト | +1.499 |
MSM | +1.492 |
unsus | +1.455 |
Neg logit contributions | |
grain | -1.563 |
urdue | -1.520 |
Windsor | -1.487 |
ellar | -1.483 |
font | -1.447 |
Token | bitcoin |
Token ID | 35395 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
Debor | +3.421 |
� | +2.668 |
ト | +2.491 |
MSM | +2.395 |
KEY | +2.254 |
Neg logit contributions | |
urdue | -8.671 |
grain | -8.644 |
ellar | -8.564 |
Windsor | -8.529 |
Craft | -8.294 |
Token | / |
Token ID | 14 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Debor | +0.690 |
� | +0.610 |
ト | +0.575 |
MSM | +0.572 |
unsus | +0.558 |
Neg logit contributions | |
grain | -0.616 |
urdue | -0.589 |
ellar | -0.588 |
Windsor | -0.576 |
font | -0.567 |
Token | h |
Token ID | 71 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Debor | +2.392 |
� | +2.131 |
ト | +2.003 |
MSM | +1.985 |
� | +1.944 |
Neg logit contributions | |
grain | -2.094 |
urdue | -2.039 |
ellar | -2.026 |
Windsor | -1.984 |
font | -1.920 |
Token | ong |
Token ID | 506 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
Debor | +1.889 |
� | +1.725 |
ト | +1.663 |
MSM | +1.639 |
unsus | +1.630 |
Neg logit contributions | |
grain | -0.867 |
urdue | -0.825 |
ellar | -0.822 |
Windsor | -0.813 |
font | -0.763 |
Token | - |
Token ID | 12 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Debor | +2.629 |
� | +2.333 |
ト | +2.217 |
MSM | +2.194 |
unsus | +2.116 |
Neg logit contributions | |
grain | -2.336 |
urdue | -2.268 |
ellar | -2.250 |
Windsor | -2.215 |
afety | -2.170 |
Token | ara |
Token ID | 3301 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
Debor | +0.435 |
� | +0.387 |
ト | +0.366 |
MSM | +0.364 |
unsus | +0.356 |
Neg logit contributions | |
grain | -0.358 |
urdue | -0.342 |
ellar | -0.341 |
Windsor | -0.333 |
font | -0.328 |
Token | P |
Token ID | 350 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
grain | +0.429 |
urdue | +0.410 |
ellar | +0.409 |
Windsor | +0.401 |
font | +0.394 |
Neg logit contributions | |
Debor | -0.517 |
� | -0.460 |
ト | -0.434 |
MSM | -0.432 |
unsus | -0.423 |
Token | 217 |
Token ID | 24591 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
grain | +0.222 |
urdue | +0.213 |
ellar | +0.212 |
Windsor | +0.208 |
font | +0.205 |
Neg logit contributions | |
Debor | -0.229 |
� | -0.201 |
ト | -0.189 |
MSM | -0.188 |
unsus | -0.184 |
Token | Gibson |
Token ID | 20400 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Debor | +0.905 |
� | +0.801 |
ト | +0.754 |
MSM | +0.750 |
unsus | +0.731 |
Neg logit contributions | |
grain | -0.831 |
urdue | -0.796 |
ellar | -0.794 |
Windsor | -0.776 |
font | -0.766 |
Token | came |
Token ID | 1625 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Debor | +1.069 |
� | +0.945 |
ト | +0.888 |
MSM | +0.888 |
unsus | +0.866 |
Neg logit contributions | |
grain | -0.986 |
urdue | -0.944 |
ellar | -0.943 |
Windsor | -0.915 |
font | -0.909 |
Token | fourth |
Token ID | 5544 |
Feature activation | +8.37e+00 |
Pos logit contributions | |
Debor | +0.913 |
� | +0.799 |
ト | +0.750 |
MSM | +0.744 |
unsus | +0.730 |
Neg logit contributions | |
grain | -0.953 |
urdue | -0.913 |
ellar | -0.912 |
Windsor | -0.890 |
font | -0.881 |
Token | , |
Token ID | 11 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
Debor | +5.347 |
� | +4.450 |
unsus | +4.315 |
MSM | +4.260 |
ト | +4.158 |
Neg logit contributions | |
grain | -6.918 |
ellar | -6.724 |
urdue | -6.670 |
afety | -6.506 |
ˈ | -6.400 |
Token | ahead |
Token ID | 4058 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
Debor | +1.805 |
� | +1.570 |
ト | +1.484 |
MSM | +1.480 |
unsus | +1.451 |
Neg logit contributions | |
grain | -1.801 |
ellar | -1.729 |
urdue | -1.722 |
Windsor | -1.661 |
afety | -1.661 |
Token | of |
Token ID | 286 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
Debor | +3.428 |
� | +2.959 |
ト | +2.810 |
MSM | +2.780 |
� | +2.726 |
Neg logit contributions | |
grain | -3.683 |
urdue | -3.530 |
ellar | -3.520 |
font | -3.412 |
afety | -3.406 |
Token | the |
Token ID | 262 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Debor | +0.658 |
� | +0.579 |
ト | +0.546 |
MSM | +0.544 |
unsus | +0.531 |
Neg logit contributions | |
grain | -0.604 |
urdue | -0.578 |
ellar | -0.576 |
Windsor | -0.561 |
font | -0.556 |
Token | fastest |
Token ID | 14162 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Debor | +0.319 |
� | +0.281 |
ト | +0.265 |
MSM | +0.264 |
unsus | +0.258 |
Neg logit contributions | |
grain | -0.290 |
urdue | -0.278 |
ellar | -0.277 |
Windsor | -0.270 |
font | -0.267 |
Token | noted |
Token ID | 4367 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
Debor | +0.398 |
� | +0.363 |
ト | +0.346 |
MSM | +0.344 |
unsus | +0.338 |
Neg logit contributions | |
grain | -0.192 |
urdue | -0.180 |
ellar | -0.180 |
Windsor | -0.174 |
font | -0.171 |
Token | . |
Token ID | 13 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
grain | +0.581 |
urdue | +0.561 |
ellar | +0.556 |
Windsor | +0.548 |
font | +0.540 |
Neg logit contributions | |
Debor | -0.602 |
� | -0.529 |
ト | -0.501 |
MSM | -0.496 |
unsus | -0.486 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Debor | +0.187 |
� | +0.164 |
ト | +0.154 |
MSM | +0.154 |
� | +0.149 |
Neg logit contributions | |
grain | -0.178 |
ellar | -0.170 |
urdue | -0.170 |
Windsor | -0.166 |
font | -0.164 |
Token | T |
Token ID | 51 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
Debor | +0.900 |
� | +0.802 |
ト | +0.757 |
MSM | +0.748 |
機 | +0.730 |
Neg logit contributions | |
grain | -0.801 |
urdue | -0.771 |
ellar | -0.768 |
Windsor | -0.752 |
font | -0.735 |
Token | EL |
Token ID | 3698 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
Debor | +0.712 |
� | +0.632 |
ト | +0.597 |
MSM | +0.593 |
unsus | +0.582 |
Neg logit contributions | |
grain | -0.594 |
urdue | -0.566 |
ellar | -0.564 |
Windsor | -0.553 |
font | -0.545 |
Token | AV |
Token ID | 14661 |
Feature activation | +8.26e+00 |
Pos logit contributions | |
grain | +2.852 |
Windsor | +2.774 |
urdue | +2.722 |
font | +2.710 |
ellar | +2.658 |
Neg logit contributions | |
Debor | -3.411 |
� | -2.900 |
unsus | -2.749 |
� | -2.738 |
ト | -2.700 |
Token | IV |
Token ID | 3824 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
Debor | +1.411 |
� | +0.838 |
機 | +0.297 |
unsus | +0.295 |
ト | +0.268 |
Neg logit contributions | |
grain | -10.760 |
urdue | -10.418 |
font | -10.282 |
afety | -10.189 |
ellar | -10.182 |
Token | – |
Token ID | 784 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Debor | +3.264 |
� | +2.891 |
MSM | +2.726 |
ト | +2.699 |
機 | +2.646 |
Neg logit contributions | |
grain | -2.776 |
ellar | -2.654 |
urdue | -2.653 |
Windsor | -2.561 |
font | -2.531 |
Token | A |
Token ID | 317 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Debor | +1.490 |
� | +1.301 |
MSM | +1.232 |
ト | +1.223 |
unsus | +1.178 |
Neg logit contributions | |
grain | -1.376 |
ellar | -1.321 |
urdue | -1.313 |
Windsor | -1.264 |
font | -1.260 |
Token | clandestine |
Token ID | 39903 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Debor | +1.106 |
� | +0.973 |
ト | +0.918 |
MSM | +0.913 |
unsus | +0.890 |
Neg logit contributions | |
grain | -1.044 |
ellar | -0.999 |
urdue | -0.996 |
Windsor | -0.967 |
font | -0.965 |
Token | Israeli |
Token ID | 6085 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
grain | +0.417 |
urdue | +0.401 |
ellar | +0.400 |
Windsor | +0.396 |
font | +0.388 |
Neg logit contributions | |
Debor | -0.386 |
� | -0.339 |
ト | -0.317 |
MSM | -0.312 |
� | -0.307 |
Token | day |
Token ID | 1110 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
Debor | +1.593 |
� | +1.409 |
ト | +1.332 |
MSM | +1.327 |
unsus | +1.296 |
Neg logit contributions | |
grain | -1.417 |
urdue | -1.368 |
ellar | -1.365 |
Windsor | -1.322 |
font | -1.312 |
Token | of |
Token ID | 286 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
Debor | +1.582 |
� | +1.390 |
ト | +1.309 |
MSM | +1.304 |
unsus | +1.272 |
Neg logit contributions | |
grain | -1.477 |
ellar | -1.420 |
urdue | -1.420 |
Windsor | -1.380 |
font | -1.365 |
Token | the |
Token ID | 262 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
Debor | +0.605 |
� | +0.533 |
ト | +0.502 |
MSM | +0.499 |
unsus | +0.488 |
Neg logit contributions | |
grain | -0.568 |
urdue | -0.544 |
ellar | -0.543 |
Windsor | -0.532 |
font | -0.525 |
Token | year |
Token ID | 614 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
grain | +0.502 |
urdue | +0.481 |
ellar | +0.478 |
Windsor | +0.473 |
font | +0.464 |
Neg logit contributions | |
Debor | -0.538 |
� | -0.476 |
ト | -0.447 |
MSM | -0.443 |
unsus | -0.435 |
Token | was |
Token ID | 373 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Debor | +2.069 |
� | +1.818 |
ト | +1.718 |
MSM | +1.704 |
unsus | +1.662 |
Neg logit contributions | |
grain | -1.896 |
ellar | -1.823 |
urdue | -1.820 |
Windsor | -1.760 |
font | -1.749 |
Token | cold |
Token ID | 4692 |
Feature activation | +8.21e+00 |
Pos logit contributions | |
Debor | +1.925 |
� | +1.676 |
ト | +1.581 |
MSM | +1.575 |
unsus | +1.559 |
Neg logit contributions | |
grain | -1.811 |
urdue | -1.746 |
ellar | -1.739 |
font | -1.670 |
afety | -1.665 |
Token | and |
Token ID | 290 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
Debor | +5.648 |
� | +4.763 |
melanch | +4.567 |
unsus | +4.506 |
MSM | +4.466 |
Neg logit contributions | |
grain | -6.377 |
ellar | -6.207 |
urdue | -6.174 |
Windsor | -6.040 |
afety | -5.939 |
Token | over |
Token ID | 625 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
Debor | +2.223 |
� | +1.940 |
ト | +1.835 |
MSM | +1.824 |
unsus | +1.799 |
Neg logit contributions | |
grain | -2.132 |
urdue | -2.056 |
ellar | -2.042 |
Windsor | -1.985 |
font | -1.971 |
Token | cast |
Token ID | 2701 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Debor | +0.530 |
� | +0.466 |
MSM | +0.439 |
ト | +0.439 |
� | +0.428 |
Neg logit contributions | |
grain | -0.496 |
urdue | -0.473 |
ellar | -0.471 |
Windsor | -0.465 |
font | -0.460 |
Token | , |
Token ID | 11 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
Debor | +1.702 |
� | +1.490 |
ト | +1.397 |
MSM | +1.391 |
unsus | +1.361 |
Neg logit contributions | |
grain | -1.709 |
urdue | -1.640 |
ellar | -1.636 |
Windsor | -1.601 |
font | -1.581 |
Token | but |
Token ID | 475 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Debor | +2.193 |
� | +1.915 |
ト | +1.808 |
MSM | +1.797 |
unsus | +1.774 |
Neg logit contributions | |
grain | -2.071 |
urdue | -1.991 |
ellar | -1.988 |
Windsor | -1.928 |
font | -1.910 |
Token | network |
Token ID | 3127 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
Debor | +0.933 |
� | +0.805 |
ト | +0.748 |
MSM | +0.741 |
unsus | +0.722 |
Neg logit contributions | |
grain | -1.174 |
urdue | -1.132 |
ellar | -1.129 |
Windsor | -1.111 |
font | -1.097 |
Token |
|
Token ID | 198 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
grain | +1.468 |
ellar | +1.406 |
urdue | +1.397 |
Windsor | +1.389 |
font | +1.363 |
Neg logit contributions | |
Debor | -1.524 |
� | -1.341 |
ト | -1.264 |
MSM | -1.237 |
� | -1.228 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
grain | +1.314 |
urdue | +1.259 |
ellar | +1.256 |
Windsor | +1.233 |
font | +1.217 |
Neg logit contributions | |
Debor | -1.359 |
� | -1.195 |
ト | -1.123 |
MSM | -1.115 |
unsus | -1.092 |
Token | D |
Token ID | 35 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
grain | +1.035 |
ellar | +0.982 |
urdue | +0.979 |
Windsor | +0.960 |
font | +0.958 |
Neg logit contributions | |
Debor | -1.170 |
� | -1.019 |
MSM | -0.961 |
ト | -0.960 |
unsus | -0.949 |
Token | DoS |
Token ID | 46498 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
grain | +0.122 |
urdue | +0.117 |
ellar | +0.116 |
Windsor | +0.114 |
font | +0.112 |
Neg logit contributions | |
Debor | -0.152 |
� | -0.135 |
ト | -0.128 |
MSM | -0.127 |
unsus | -0.124 |
Token | Mit |
Token ID | 11707 |
Feature activation | +8.10e+00 |
Pos logit contributions | |
grain | +0.244 |
urdue | +0.235 |
ellar | +0.234 |
Windsor | +0.231 |
font | +0.227 |
Neg logit contributions | |
Debor | -0.225 |
� | -0.196 |
ト | -0.184 |
MSM | -0.182 |
unsus | -0.178 |
Token | igation |
Token ID | 7065 |
Feature activation | +8.74e+00 |
Pos logit contributions | |
Debor | +6.638 |
� | +5.795 |
MSM | +5.539 |
ト | +5.506 |
� | +5.298 |
Neg logit contributions | |
grain | -5.006 |
urdue | -4.934 |
Windsor | -4.705 |
ellar | -4.693 |
afety | -4.522 |
Token | – |
Token ID | 784 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Debor | +6.601 |
� | +5.735 |
MSM | +5.616 |
ト | +5.250 |
Swordsman | +5.222 |
Neg logit contributions | |
grain | -6.082 |
ellar | -6.045 |
urdue | -5.994 |
afety | -5.650 |
Windsor | -5.641 |
Token | No |
Token ID | 1400 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
Debor | +1.732 |
� | +1.531 |
MSM | +1.447 |
ト | +1.444 |
unsus | +1.405 |
Neg logit contributions | |
grain | -1.504 |
urdue | -1.445 |
ellar | -1.439 |
Windsor | -1.400 |
font | -1.385 |
Token | Silver |
Token ID | 7698 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Debor | +3.521 |
� | +3.103 |
MSM | +3.002 |
ト | +2.958 |
unsus | +2.894 |
Neg logit contributions | |
grain | -2.902 |
urdue | -2.819 |
ellar | -2.772 |
Windsor | -2.700 |
font | -2.674 |
Token | Bullet |
Token ID | 18003 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Debor | +2.501 |
� | +2.224 |
MSM | +2.110 |
ト | +2.085 |
unsus | +2.035 |
Neg logit contributions | |
grain | -1.802 |
urdue | -1.798 |
ellar | -1.764 |
Windsor | -1.674 |
afety | -1.662 |
Token | problems |
Token ID | 2761 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Debor | +0.436 |
� | +0.378 |
ト | +0.353 |
MSM | +0.351 |
unsus | +0.343 |
Neg logit contributions | |
grain | -0.504 |
urdue | -0.485 |
ellar | -0.484 |
Windsor | -0.475 |
font | -0.469 |
Token | . |
Token ID | 13 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
grain | +0.224 |
urdue | +0.215 |
ellar | +0.214 |
Windsor | +0.210 |
font | +0.207 |
Neg logit contributions | |
Debor | -0.235 |
� | -0.207 |
ト | -0.195 |
MSM | -0.193 |
unsus | -0.189 |
Token | I |
Token ID | 314 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
grain | +0.410 |
urdue | +0.392 |
ellar | +0.391 |
Windsor | +0.385 |
font | +0.379 |
Neg logit contributions | |
Debor | -0.438 |
� | -0.386 |
ト | -0.364 |
MSM | -0.361 |
unsus | -0.354 |
Token | 've |
Token ID | 1053 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
grain | +0.306 |
urdue | +0.292 |
ellar | +0.291 |
Windsor | +0.286 |
font | +0.281 |
Neg logit contributions | |
Debor | -0.371 |
� | -0.329 |
ト | -0.311 |
MSM | -0.309 |
unsus | -0.303 |
Token | Mac |
Token ID | 4100 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
Debor | +0.669 |
� | +0.592 |
ト | +0.560 |
MSM | +0.559 |
unsus | +0.551 |
Neg logit contributions | |
grain | -0.542 |
ellar | -0.518 |
urdue | -0.518 |
Windsor | -0.504 |
font | -0.497 |
Token | Gy |
Token ID | 44802 |
Feature activation | +8.06e+00 |
Pos logit contributions | |
grain | +0.589 |
urdue | +0.565 |
ellar | +0.564 |
Windsor | +0.554 |
font | +0.549 |
Neg logit contributions | |
Debor | -0.554 |
� | -0.486 |
ト | -0.455 |
MSM | -0.453 |
unsus | -0.441 |
Token | vered |
Token ID | 21917 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
Debor | +5.625 |
� | +4.620 |
ト | +4.603 |
unsus | +4.455 |
MSM | +4.392 |
Neg logit contributions | |
urdue | -5.790 |
Windsor | -5.649 |
grain | -5.528 |
ellar | -5.442 |
afety | -5.439 |
Token | mental |
Token ID | 5110 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
Debor | +0.687 |
� | +0.604 |
ト | +0.569 |
MSM | +0.567 |
unsus | +0.555 |
Neg logit contributions | |
grain | -0.637 |
urdue | -0.610 |
ellar | -0.609 |
Windsor | -0.595 |
font | -0.587 |
Token | upgrades |
Token ID | 16608 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
grain | +0.445 |
urdue | +0.427 |
ellar | +0.426 |
Windsor | +0.418 |
font | +0.412 |
Neg logit contributions | |
Debor | -0.459 |
� | -0.404 |
ト | -0.379 |
MSM | -0.377 |
unsus | -0.368 |
Token | out |
Token ID | 503 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
Debor | +1.558 |
� | +1.372 |
MSM | +1.284 |
ト | +1.282 |
unsus | +1.270 |
Neg logit contributions | |
grain | -1.480 |
ellar | -1.420 |
urdue | -1.418 |
Windsor | -1.382 |
font | -1.358 |
Token | of |
Token ID | 286 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Debor | +0.309 |
� | +0.273 |
ト | +0.257 |
MSM | +0.255 |
unsus | +0.249 |
Neg logit contributions | |
grain | -0.287 |
urdue | -0.274 |
ellar | -0.274 |
Windsor | -0.269 |
font | -0.265 |
Token | c |
Token ID | 269 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Debor | +1.272 |
� | +1.143 |
MSM | +1.099 |
ト | +1.093 |
unsus | +1.074 |
Neg logit contributions | |
grain | -0.744 |
urdue | -0.705 |
ellar | -0.699 |
Windsor | -0.677 |
afety | -0.669 |
Token | v |
Token ID | 85 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Debor | +1.486 |
� | +1.292 |
ト | +1.228 |
MSM | +1.199 |
unsus | +1.160 |
Neg logit contributions | |
grain | -1.743 |
urdue | -1.703 |
ellar | -1.693 |
Windsor | -1.670 |
afety | -1.655 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
Debor | +1.747 |
� | +1.509 |
ト | +1.450 |
MSM | +1.380 |
KEY | +1.335 |
Neg logit contributions | |
grain | -2.448 |
urdue | -2.407 |
ellar | -2.391 |
afety | -2.361 |
Windsor | -2.342 |
Token | . |
Token ID | 764 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
Debor | +1.614 |
� | +1.374 |
ト | +1.288 |
MSM | +1.281 |
機 | +1.203 |
Neg logit contributions | |
grain | -2.199 |
urdue | -2.146 |
ellar | -2.134 |
afety | -2.075 |
Windsor | -2.068 |
Token | Ga |
Token ID | 12822 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
Debor | +2.480 |
� | +2.170 |
MSM | +2.085 |
ト | +2.047 |
melanch | +2.017 |
Neg logit contributions | |
grain | -2.313 |
ellar | -2.237 |
urdue | -2.225 |
Windsor | -2.163 |
afety | -2.135 |
Token | ussian |
Token ID | 31562 |
Feature activation | +8.05e+00 |
Pos logit contributions | |
Debor | +2.176 |
� | +1.836 |
ト | +1.697 |
MSM | +1.561 |
unsus | +1.498 |
Neg logit contributions | |
grain | -5.129 |
Windsor | -5.123 |
urdue | -5.063 |
afety | -4.976 |
ellar | -4.949 |
Token | Bl |
Token ID | 3629 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
Debor | +3.364 |
� | +2.854 |
ト | +2.649 |
BM | +2.382 |
機 | +2.314 |
Neg logit contributions | |
grain | -8.164 |
ellar | -8.079 |
urdue | -8.067 |
afety | -7.988 |
Windsor | -7.782 |
Token | ur |
Token ID | 333 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
Debor | +2.772 |
� | +2.500 |
ト | +2.473 |
MSM | +2.368 |
unsus | +2.357 |
Neg logit contributions | |
grain | -1.687 |
urdue | -1.660 |
ellar | -1.645 |
Windsor | -1.639 |
afety | -1.618 |
Token | ( |
Token ID | 357 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
Debor | +2.844 |
� | +2.523 |
ト | +2.416 |
MSM | +2.384 |
機 | +2.271 |
Neg logit contributions | |
grain | -3.071 |
ellar | -3.029 |
urdue | -3.022 |
afety | -2.952 |
Windsor | -2.868 |
Token | gray |
Token ID | 12768 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
Debor | +2.738 |
� | +2.097 |
MSM | +2.083 |
unsus | +2.014 |
melanch | +1.998 |
Neg logit contributions | |
grain | -4.533 |
afety | -4.482 |
ellar | -4.476 |
urdue | -4.463 |
Windsor | -4.319 |
Token | , |
Token ID | 837 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Debor | +1.497 |
� | +1.315 |
ト | +1.246 |
MSM | +1.241 |
unsus | +1.185 |
Neg logit contributions | |
grain | -1.547 |
ellar | -1.511 |
urdue | -1.504 |
afety | -1.471 |
Windsor | -1.454 |
Token | is |
Token ID | 318 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Debor | +0.733 |
� | +0.655 |
ト | +0.621 |
MSM | +0.618 |
unsus | +0.606 |
Neg logit contributions | |
grain | -0.542 |
urdue | -0.516 |
ellar | -0.514 |
Windsor | -0.503 |
font | -0.495 |
Token | officially |
Token ID | 8720 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
Debor | +1.363 |
� | +1.204 |
ト | +1.137 |
MSM | +1.133 |
unsus | +1.109 |
Neg logit contributions | |
grain | -1.226 |
urdue | -1.175 |
ellar | -1.170 |
Windsor | -1.147 |
font | -1.130 |
Token | supported |
Token ID | 4855 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
Debor | +2.656 |
� | +2.244 |
MSM | +2.133 |
ト | +2.075 |
unsus | +2.059 |
Neg logit contributions | |
grain | -3.746 |
urdue | -3.609 |
ellar | -3.582 |
Windsor | -3.525 |
afety | -3.512 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Debor | +1.647 |
� | +1.444 |
ト | +1.349 |
MSM | +1.347 |
unsus | +1.314 |
Neg logit contributions | |
grain | -1.677 |
ellar | -1.606 |
urdue | -1.602 |
Windsor | -1.573 |
font | -1.542 |
Token | For |
Token ID | 1114 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
grain | +0.099 |
urdue | +0.095 |
ellar | +0.095 |
Windsor | +0.093 |
font | +0.092 |
Neg logit contributions | |
Debor | -0.109 |
� | -0.096 |
ト | -0.090 |
MSM | -0.090 |
unsus | -0.088 |
Token | now |
Token ID | 783 |
Feature activation | +7.91e+00 |
Pos logit contributions | |
Debor | +0.629 |
� | +0.556 |
ト | +0.524 |
MSM | +0.523 |
unsus | +0.509 |
Neg logit contributions | |
grain | -0.568 |
urdue | -0.548 |
ellar | -0.544 |
Windsor | -0.533 |
font | -0.525 |
Token | , |
Token ID | 11 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
Debor | +5.239 |
� | +4.511 |
MSM | +4.320 |
ト | +4.226 |
melanch | +4.093 |
Neg logit contributions | |
grain | -6.297 |
urdue | -6.161 |
ellar | -6.137 |
Windsor | -5.945 |
afety | -5.920 |
Token | the |
Token ID | 262 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Debor | +1.646 |
� | +1.440 |
ト | +1.355 |
MSM | +1.354 |
unsus | +1.313 |
Neg logit contributions | |
grain | -1.672 |
urdue | -1.615 |
ellar | -1.609 |
Windsor | -1.571 |
font | -1.550 |
Token | lens |
Token ID | 10317 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
Debor | +1.525 |
� | +1.346 |
MSM | +1.278 |
ト | +1.269 |
unsus | +1.241 |
Neg logit contributions | |
grain | -1.359 |
urdue | -1.313 |
ellar | -1.305 |
Windsor | -1.273 |
font | -1.256 |
Token | is |
Token ID | 318 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
grain | +0.410 |
urdue | +0.388 |
ellar | +0.388 |
Windsor | +0.379 |
font | +0.374 |
Neg logit contributions | |
Debor | -0.559 |
� | -0.499 |
ト | -0.474 |
MSM | -0.469 |
unsus | -0.463 |
Token | excellent |
Token ID | 6275 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
Debor | +2.190 |
� | +1.931 |
MSM | +1.821 |
ト | +1.812 |
unsus | +1.766 |
Neg logit contributions | |
grain | -2.080 |
urdue | -2.010 |
ellar | -2.002 |
Windsor | -1.956 |
font | -1.927 |
Token | finding |
Token ID | 4917 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
grain | +0.114 |
urdue | +0.109 |
ellar | +0.109 |
Windsor | +0.107 |
font | +0.105 |
Neg logit contributions | |
Debor | -0.137 |
� | -0.122 |
ト | -0.115 |
MSM | -0.114 |
unsus | -0.112 |
Token | a |
Token ID | 257 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
grain | +1.261 |
urdue | +1.209 |
ellar | +1.201 |
Windsor | +1.196 |
font | +1.168 |
Neg logit contributions | |
Debor | -1.296 |
� | -1.148 |
ト | -1.077 |
MSM | -1.058 |
� | -1.045 |
Token | safety |
Token ID | 3747 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
grain | +0.312 |
urdue | +0.300 |
ellar | +0.298 |
Windsor | +0.295 |
font | +0.290 |
Neg logit contributions | |
Debor | -0.262 |
� | -0.227 |
ト | -0.211 |
MSM | -0.209 |
unsus | -0.204 |
Token | . |
Token ID | 13 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
grain | +1.006 |
urdue | +0.962 |
ellar | +0.957 |
Windsor | +0.948 |
font | +0.935 |
Neg logit contributions | |
Debor | -1.154 |
� | -1.011 |
ト | -0.966 |
MSM | -0.949 |
� | -0.936 |
Token | For |
Token ID | 1114 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
grain | +1.414 |
urdue | +1.352 |
ellar | +1.339 |
Windsor | +1.329 |
font | +1.303 |
Neg logit contributions | |
Debor | -1.713 |
� | -1.533 |
ト | -1.445 |
MSM | -1.429 |
unsus | -1.423 |
Token | now |
Token ID | 783 |
Feature activation | +7.88e+00 |
Pos logit contributions | |
grain | +0.020 |
urdue | +0.019 |
ellar | +0.019 |
Windsor | +0.018 |
font | +0.018 |
Neg logit contributions | |
Debor | -0.022 |
� | -0.019 |
ト | -0.018 |
MSM | -0.018 |
unsus | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Debor | +5.354 |
� | +4.619 |
MSM | +4.358 |
ト | +4.329 |
機 | +4.165 |
Neg logit contributions | |
grain | -6.258 |
ellar | -6.065 |
urdue | -5.939 |
Windsor | -5.770 |
afety | -5.768 |
Token | coaches |
Token ID | 11070 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Debor | +1.570 |
� | +1.373 |
MSM | +1.299 |
ト | +1.298 |
unsus | +1.263 |
Neg logit contributions | |
grain | -1.434 |
ellar | -1.378 |
urdue | -1.374 |
Windsor | -1.335 |
font | -1.321 |
Token | have |
Token ID | 423 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Debor | +1.164 |
� | +1.034 |
ト | +0.977 |
MSM | +0.973 |
unsus | +0.953 |
Neg logit contributions | |
grain | -0.931 |
urdue | -0.888 |
ellar | -0.887 |
Windsor | -0.867 |
font | -0.854 |
Token | David |
Token ID | 3271 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Debor | +0.488 |
� | +0.434 |
ト | +0.409 |
MSM | +0.406 |
unsus | +0.398 |
Neg logit contributions | |
grain | -0.417 |
urdue | -0.399 |
ellar | -0.397 |
Windsor | -0.391 |
font | -0.384 |
Token | Brut |
Token ID | 30291 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
grain | +1.578 |
urdue | +1.513 |
ellar | +1.509 |
Windsor | +1.482 |
font | +1.460 |
Neg logit contributions | |
Debor | -1.644 |
� | -1.448 |
ト | -1.361 |
MSM | -1.352 |
unsus | -1.322 |
Token | two |
Token ID | 734 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
grain | +0.537 |
urdue | +0.513 |
ellar | +0.512 |
Windsor | +0.504 |
font | +0.496 |
Neg logit contributions | |
Debor | -0.576 |
� | -0.509 |
ト | -0.477 |
MSM | -0.475 |
unsus | -0.464 |
Token | options |
Token ID | 3689 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
Debor | +0.104 |
� | +0.090 |
ト | +0.084 |
MSM | +0.083 |
unsus | +0.081 |
Neg logit contributions | |
grain | -0.130 |
urdue | -0.125 |
ellar | -0.125 |
Windsor | -0.123 |
font | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
Debor | +2.268 |
� | +1.986 |
ト | +1.840 |
MSM | +1.830 |
unsus | +1.781 |
Neg logit contributions | |
grain | -2.508 |
ellar | -2.412 |
urdue | -2.404 |
Windsor | -2.351 |
font | -2.300 |
Token | The |
Token ID | 383 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Debor | +2.266 |
� | +2.007 |
ト | +1.912 |
MSM | +1.895 |
機 | +1.835 |
Neg logit contributions | |
grain | -1.715 |
ellar | -1.633 |
urdue | -1.631 |
Windsor | -1.573 |
afety | -1.556 |
Token | first |
Token ID | 717 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
Debor | +1.912 |
� | +1.658 |
ト | +1.559 |
MSM | +1.551 |
unsus | +1.510 |
Neg logit contributions | |
grain | -2.085 |
urdue | -2.011 |
ellar | -2.007 |
Windsor | -1.959 |
afety | -1.925 |
Token | is |
Token ID | 318 |
Feature activation | +7.79e+00 |
Pos logit contributions | |
Debor | +2.295 |
� | +2.037 |
ト | +1.926 |
MSM | +1.921 |
unsus | +1.874 |
Neg logit contributions | |
grain | -1.884 |
ellar | -1.810 |
urdue | -1.809 |
Windsor | -1.755 |
font | -1.722 |
Token | an |
Token ID | 281 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
Debor | +5.255 |
� | +4.616 |
ト | +4.354 |
MSM | +4.263 |
unsus | +4.135 |
Neg logit contributions | |
grain | -6.077 |
urdue | -5.873 |
ellar | -5.818 |
Windsor | -5.687 |
afety | -5.536 |
Token | illegal |
Token ID | 5293 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Debor | +2.397 |
� | +2.104 |
ト | +1.968 |
MSM | +1.965 |
unsus | +1.932 |
Neg logit contributions | |
grain | -2.469 |
urdue | -2.381 |
ellar | -2.356 |
Windsor | -2.315 |
font | -2.272 |
Token | hack |
Token ID | 8156 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
grain | +0.202 |
urdue | +0.194 |
ellar | +0.194 |
Windsor | +0.190 |
font | +0.188 |
Neg logit contributions | |
Debor | -0.211 |
� | -0.186 |
ト | -0.174 |
MSM | -0.174 |
unsus | -0.170 |
Token | to |
Token ID | 284 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
grain | +1.066 |
urdue | +1.025 |
ellar | +1.022 |
Windsor | +0.998 |
font | +0.992 |
Neg logit contributions | |
Debor | -1.227 |
� | -1.084 |
ト | -1.021 |
MSM | -1.020 |
unsus | -0.995 |
Token | remove |
Token ID | 4781 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
grain | +0.596 |
urdue | +0.569 |
ellar | +0.567 |
Windsor | +0.557 |
font | +0.548 |
Neg logit contributions | |
Debor | -0.724 |
� | -0.643 |
ト | -0.607 |
MSM | -0.604 |
unsus | -0.590 |
Token | Virginia |
Token ID | 6025 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Debor | +0.561 |
� | +0.492 |
MSM | +0.467 |
ト | +0.465 |
unsus | +0.452 |
Neg logit contributions | |
grain | -0.519 |
ellar | -0.495 |
urdue | -0.495 |
Windsor | -0.479 |
font | -0.479 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Debor | +1.274 |
� | +1.116 |
MSM | +1.057 |
ト | +1.042 |
unsus | +1.034 |
Neg logit contributions | |
grain | -1.204 |
ellar | -1.148 |
urdue | -1.140 |
Windsor | -1.102 |
font | -1.091 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Debor | +1.030 |
� | +0.906 |
MSM | +0.863 |
ト | +0.855 |
機 | +0.823 |
Neg logit contributions | |
grain | -0.909 |
ellar | -0.866 |
urdue | -0.864 |
Windsor | -0.835 |
afety | -0.829 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Debor | +1.039 |
� | +0.906 |
ト | +0.856 |
MSM | +0.855 |
機 | +0.808 |
Neg logit contributions | |
grain | -1.214 |
urdue | -1.179 |
ellar | -1.178 |
afety | -1.147 |
Windsor | -1.143 |
Token | Di |
Token ID | 18683 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Debor | +1.163 |
� | +1.043 |
ト | +0.986 |
MSM | +0.977 |
機 | +0.951 |
Neg logit contributions | |
grain | -1.015 |
urdue | -0.975 |
ellar | -0.971 |
Windsor | -0.950 |
afety | -0.931 |
Token | plom |
Token ID | 7302 |
Feature activation | +7.69e+00 |
Pos logit contributions | |
Debor | +2.809 |
� | +2.545 |
MSM | +2.411 |
ト | +2.402 |
unsus | +2.361 |
Neg logit contributions | |
grain | -1.703 |
urdue | -1.606 |
ellar | -1.565 |
Windsor | -1.532 |
font | -1.522 |
Token | atic |
Token ID | 1512 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Debor | +5.443 |
� | +4.521 |
MSM | +4.329 |
ト | +4.250 |
unsus | +4.178 |
Neg logit contributions | |
grain | -5.852 |
urdue | -5.605 |
ellar | -5.530 |
Windsor | -5.470 |
font | -5.390 |
Token | cables |
Token ID | 18018 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
Debor | +1.729 |
� | +1.498 |
MSM | +1.414 |
ト | +1.407 |
unsus | +1.377 |
Neg logit contributions | |
grain | -1.717 |
urdue | -1.649 |
ellar | -1.643 |
Windsor | -1.597 |
font | -1.585 |
Token | are |
Token ID | 389 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Debor | +0.285 |
� | +0.253 |
ト | +0.239 |
MSM | +0.238 |
unsus | +0.233 |
Neg logit contributions | |
grain | -0.242 |
urdue | -0.232 |
ellar | -0.231 |
Windsor | -0.226 |
font | -0.223 |
Token | internal |
Token ID | 5387 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
grain | +1.187 |
ellar | +1.138 |
urdue | +1.135 |
Windsor | +1.128 |
font | +1.097 |
Neg logit contributions | |
Debor | -1.362 |
� | -1.226 |
ト | -1.155 |
MSM | -1.126 |
� | -1.115 |
Token | documents |
Token ID | 4963 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Debor | +1.323 |
� | +1.169 |
MSM | +1.104 |
ト | +1.104 |
unsus | +1.076 |
Neg logit contributions | |
grain | -1.154 |
urdue | -1.104 |
ellar | -1.099 |
Windsor | -1.074 |
font | -1.060 |
Token | _ |
Token ID | 62 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
Debor | +1.379 |
� | +1.219 |
ト | +1.149 |
MSM | +1.142 |
unsus | +1.116 |
Neg logit contributions | |
grain | -1.244 |
urdue | -1.192 |
ellar | -1.189 |
Windsor | -1.164 |
font | -1.146 |
Token | in |
Token ID | 259 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
Debor | +2.943 |
� | +2.616 |
ト | +2.468 |
MSM | +2.439 |
unsus | +2.389 |
Neg logit contributions | |
grain | -2.656 |
urdue | -2.585 |
ellar | -2.576 |
Windsor | -2.521 |
font | -2.431 |
Token | jury |
Token ID | 21871 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
Debor | +2.111 |
� | +1.887 |
ト | +1.791 |
MSM | +1.781 |
unsus | +1.741 |
Neg logit contributions | |
grain | -1.573 |
ellar | -1.510 |
urdue | -1.502 |
Windsor | -1.462 |
font | -1.437 |
Token | _ |
Token ID | 62 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
Debor | +2.743 |
� | +2.408 |
MSM | +2.254 |
ト | +2.242 |
unsus | +2.176 |
Neg logit contributions | |
grain | -2.720 |
ellar | -2.613 |
urdue | -2.608 |
Windsor | -2.531 |
font | -2.494 |
Token | pre |
Token ID | 3866 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
Debor | +3.434 |
� | +3.070 |
ト | +2.892 |
MSM | +2.853 |
unsus | +2.793 |
Neg logit contributions | |
grain | -3.140 |
urdue | -3.070 |
ellar | -3.062 |
Windsor | -2.986 |
font | -2.877 |
Token | vention |
Token ID | 4018 |
Feature activation | +7.69e+00 |
Pos logit contributions | |
Debor | +3.614 |
� | +3.156 |
MSM | +2.963 |
ト | +2.950 |
unsus | +2.836 |
Neg logit contributions | |
grain | -3.811 |
ellar | -3.761 |
urdue | -3.753 |
Windsor | -3.599 |
afety | -3.546 |
Token | / |
Token ID | 14 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Debor | +5.364 |
� | +4.657 |
MSM | +4.428 |
ト | +4.269 |
機 | +4.149 |
Neg logit contributions | |
grain | -5.876 |
ellar | -5.696 |
urdue | -5.655 |
Windsor | -5.423 |
font | -5.336 |
Token | key |
Token ID | 2539 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
Debor | +2.402 |
� | +2.151 |
ト | +2.031 |
MSM | +2.025 |
unsus | +1.975 |
Neg logit contributions | |
grain | -1.873 |
ellar | -1.798 |
urdue | -1.797 |
Windsor | -1.743 |
font | -1.706 |
Token | _ |
Token ID | 62 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
Debor | +2.645 |
� | +2.338 |
ト | +2.190 |
MSM | +2.183 |
unsus | +2.115 |
Neg logit contributions | |
grain | -2.629 |
urdue | -2.534 |
ellar | -2.525 |
Windsor | -2.466 |
font | -2.408 |
Token | facts |
Token ID | 37473 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
Debor | +2.985 |
� | +2.683 |
ト | +2.537 |
MSM | +2.516 |
機 | +2.455 |
Neg logit contributions | |
grain | -2.332 |
urdue | -2.268 |
ellar | -2.246 |
Windsor | -2.203 |
afety | -2.119 |
Token | / |
Token ID | 14 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Debor | +0.441 |
� | +0.389 |
ト | +0.366 |
MSM | +0.362 |
unsus | +0.356 |
Neg logit contributions | |
grain | -0.419 |
urdue | -0.401 |
ellar | -0.400 |
Windsor | -0.394 |
font | -0.388 |
Token | Civil |
Token ID | 32610 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
grain | +1.317 |
urdue | +1.259 |
ellar | +1.256 |
Windsor | +1.236 |
font | +1.228 |
Neg logit contributions | |
Debor | -1.251 |
� | -1.077 |
ト | -1.014 |
MSM | -1.013 |
unsus | -1.005 |
Token | Beat |
Token ID | 12568 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
grain | +2.185 |
urdue | +2.125 |
ellar | +2.114 |
Windsor | +2.097 |
font | +2.074 |
Neg logit contributions | |
Debor | -1.122 |
� | -0.937 |
ト | -0.842 |
MSM | -0.823 |
unsus | -0.809 |
Token |
|
Token ID | 198 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
grain | +1.178 |
urdue | +1.146 |
ellar | +1.131 |
Windsor | +1.121 |
font | +1.099 |
Neg logit contributions | |
Debor | -1.294 |
� | -1.148 |
ト | -1.091 |
MSM | -1.072 |
unsus | -1.069 |
Token |
|
Token ID | 198 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
grain | +1.555 |
urdue | +1.489 |
ellar | +1.486 |
Windsor | +1.459 |
font | +1.442 |
Neg logit contributions | |
Debor | -1.629 |
� | -1.433 |
ト | -1.346 |
MSM | -1.337 |
unsus | -1.313 |
Token | C |
Token ID | 34 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
grain | +0.113 |
urdue | +0.108 |
ellar | +0.108 |
Windsor | +0.106 |
font | +0.104 |
Neg logit contributions | |
Debor | -0.138 |
� | -0.123 |
ト | -0.116 |
MSM | -0.115 |
unsus | -0.113 |
Token | ald |
Token ID | 1940 |
Feature activation | +7.68e+00 |
Pos logit contributions | |
Debor | +0.934 |
� | +0.743 |
ト | +0.646 |
MSM | +0.632 |
機 | +0.611 |
Neg logit contributions | |
grain | -2.374 |
urdue | -2.272 |
Windsor | -2.247 |
ellar | -2.231 |
font | -2.223 |
Token | well |
Token ID | 4053 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
Debor | +4.523 |
� | +3.858 |
ト | +3.827 |
unsus | +3.637 |
MSM | +3.608 |
Neg logit contributions | |
grain | -6.241 |
urdue | -5.946 |
ˈ | -5.944 |
Windsor | -5.778 |
afety | -5.774 |
Token | also |
Token ID | 635 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
Debor | +2.068 |
� | +1.845 |
ト | +1.738 |
MSM | +1.726 |
unsus | +1.701 |
Neg logit contributions | |
grain | -1.549 |
ellar | -1.470 |
urdue | -1.461 |
Windsor | -1.424 |
font | -1.406 |
Token | wants |
Token ID | 3382 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
grain | +0.447 |
urdue | +0.426 |
ellar | +0.425 |
Windsor | +0.415 |
font | +0.409 |
Neg logit contributions | |
Debor | -0.598 |
� | -0.534 |
ト | -0.506 |
MSM | -0.503 |
unsus | -0.494 |
Token | to |
Token ID | 284 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
grain | +0.841 |
urdue | +0.809 |
ellar | +0.807 |
Windsor | +0.797 |
font | +0.780 |
Neg logit contributions | |
Debor | -0.850 |
� | -0.749 |
ト | -0.706 |
MSM | -0.697 |
unsus | -0.686 |
Token | enact |
Token ID | 10865 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
grain | +1.299 |
urdue | +1.242 |
ellar | +1.237 |
Windsor | +1.213 |
font | +1.191 |
Neg logit contributions | |
Debor | -1.709 |
� | -1.522 |
ト | -1.444 |
MSM | -1.433 |
unsus | -1.404 |
Token | , |
Token ID | 11 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
grain | +0.919 |
urdue | +0.884 |
ellar | +0.878 |
Windsor | +0.867 |
font | +0.856 |
Neg logit contributions | |
Debor | -1.018 |
� | -0.899 |
ト | -0.855 |
MSM | -0.843 |
� | -0.824 |
Token | with |
Token ID | 351 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
Debor | +0.337 |
� | +0.297 |
ト | +0.280 |
MSM | +0.278 |
unsus | +0.272 |
Neg logit contributions | |
grain | -0.311 |
ellar | -0.298 |
urdue | -0.296 |
Windsor | -0.290 |
font | -0.286 |
Token | � |
Token ID | 564 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
grain | +1.384 |
urdue | +1.322 |
ellar | +1.318 |
Windsor | +1.295 |
font | +1.272 |
Neg logit contributions | |
Debor | -1.640 |
� | -1.458 |
ト | -1.376 |
MSM | -1.367 |
unsus | -1.339 |
Token | � |
Token ID | 250 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
grain | +0.836 |
urdue | +0.805 |
ellar | +0.803 |
Windsor | +0.789 |
font | +0.780 |
Neg logit contributions | |
Debor | -0.710 |
� | -0.616 |
ト | -0.571 |
MSM | -0.570 |
unsus | -0.556 |
Token | La |
Token ID | 14772 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
Debor | +0.134 |
� | +0.118 |
ト | +0.112 |
MSM | +0.111 |
unsus | +0.108 |
Neg logit contributions | |
grain | -0.121 |
urdue | -0.116 |
ellar | -0.116 |
Windsor | -0.114 |
font | -0.112 |
Token | La |
Token ID | 4689 |
Feature activation | +7.65e+00 |
Pos logit contributions | |
Debor | +2.629 |
� | +2.336 |
ト | +2.215 |
MSM | +2.201 |
unsus | +2.140 |
Neg logit contributions | |
grain | -2.120 |
urdue | -2.029 |
ellar | -2.012 |
Windsor | -1.960 |
afety | -1.952 |
Token | Land |
Token ID | 6379 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
Debor | +5.432 |
� | +4.766 |
MSM | +4.498 |
ト | +4.479 |
� | +4.329 |
Neg logit contributions | |
grain | -5.714 |
urdue | -5.517 |
ellar | -5.464 |
afety | -5.381 |
Windsor | -5.283 |
Token | � |
Token ID | 447 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
Debor | +3.497 |
� | +3.070 |
ト | +2.870 |
MSM | +2.809 |
unsus | +2.808 |
Neg logit contributions | |
grain | -3.541 |
urdue | -3.398 |
ellar | -3.371 |
Windsor | -3.276 |
afety | -3.262 |
Token | � |
Token ID | 251 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Debor | +2.117 |
� | +1.786 |
ト | +1.687 |
MSM | +1.636 |
機 | +1.586 |
Neg logit contributions | |
grain | -3.333 |
urdue | -3.241 |
ellar | -3.205 |
Windsor | -3.151 |
font | -3.129 |
Token | producer |
Token ID | 9920 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Debor | +1.269 |
� | +1.119 |
ト | +1.053 |
MSM | +1.045 |
unsus | +1.025 |
Neg logit contributions | |
grain | -1.140 |
urdue | -1.094 |
ellar | -1.088 |
Windsor | -1.063 |
font | -1.049 |
Token | Jordan |
Token ID | 8078 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
grain | +0.222 |
urdue | +0.212 |
ellar | +0.212 |
Windsor | +0.208 |
font | +0.205 |
Neg logit contributions | |
Debor | -0.251 |
� | -0.223 |
ト | -0.210 |
MSM | -0.208 |
unsus | -0.204 |
Token | ried |
Token ID | 2228 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
grain | +2.241 |
urdue | +2.133 |
ellar | +2.118 |
Windsor | +2.108 |
font | +2.102 |
Neg logit contributions | |
Debor | -2.170 |
� | -1.871 |
ト | -1.738 |
MSM | -1.734 |
unsus | -1.720 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Debor | +0.388 |
� | +0.343 |
ト | +0.324 |
MSM | +0.321 |
unsus | +0.315 |
Neg logit contributions | |
grain | -0.346 |
urdue | -0.332 |
ellar | -0.331 |
Windsor | -0.324 |
font | -0.320 |
Token | who |
Token ID | 508 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Debor | +0.854 |
� | +0.754 |
ト | +0.710 |
MSM | +0.705 |
unsus | +0.691 |
Neg logit contributions | |
grain | -0.784 |
urdue | -0.752 |
ellar | -0.749 |
Windsor | -0.736 |
font | -0.725 |
Token | also |
Token ID | 635 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Debor | +1.578 |
� | +1.389 |
ト | +1.306 |
MSM | +1.302 |
unsus | +1.272 |
Neg logit contributions | |
grain | -1.498 |
urdue | -1.432 |
ellar | -1.429 |
Windsor | -1.395 |
font | -1.378 |
Token | had |
Token ID | 550 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
Debor | +1.104 |
� | +0.966 |
ト | +0.908 |
MSM | +0.903 |
unsus | +0.883 |
Neg logit contributions | |
grain | -1.118 |
urdue | -1.072 |
ellar | -1.070 |
Windsor | -1.045 |
font | -1.033 |
Token | history |
Token ID | 2106 |
Feature activation | +7.65e+00 |
Pos logit contributions | |
Debor | +1.887 |
� | +1.652 |
ト | +1.553 |
MSM | +1.552 |
unsus | +1.523 |
Neg logit contributions | |
grain | -1.796 |
urdue | -1.715 |
ellar | -1.711 |
Windsor | -1.658 |
font | -1.646 |
Token | on |
Token ID | 319 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Debor | +5.270 |
� | +4.511 |
MSM | +4.197 |
ト | +4.161 |
unsus | +4.109 |
Neg logit contributions | |
grain | -6.075 |
ellar | -5.845 |
urdue | -5.774 |
Windsor | -5.610 |
afety | -5.595 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
grain | +0.237 |
urdue | +0.227 |
ellar | +0.226 |
Windsor | +0.223 |
font | +0.219 |
Neg logit contributions | |
Debor | -0.309 |
� | -0.277 |
ト | -0.261 |
MSM | -0.259 |
unsus | -0.255 |
Token | trading |
Token ID | 7313 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
grain | +1.068 |
urdue | +1.019 |
ellar | +1.018 |
Windsor | +1.007 |
font | +0.988 |
Neg logit contributions | |
Debor | -1.204 |
� | -1.069 |
ト | -1.008 |
MSM | -0.992 |
unsus | -0.978 |
Token | side |
Token ID | 1735 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Debor | +0.669 |
� | +0.587 |
ト | +0.551 |
MSM | +0.549 |
unsus | +0.536 |
Neg logit contributions | |
grain | -0.665 |
urdue | -0.639 |
ellar | -0.637 |
Windsor | -0.623 |
font | -0.615 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
grain | +0.782 |
urdue | +0.752 |
ellar | +0.742 |
Windsor | +0.739 |
font | +0.730 |
Neg logit contributions | |
Debor | -0.877 |
� | -0.774 |
ト | -0.737 |
MSM | -0.729 |
unsus | -0.714 |
Token | um |
Token ID | 388 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
Debor | +1.386 |
� | +1.239 |
ト | +1.205 |
MSM | +1.187 |
unsus | +1.161 |
Neg logit contributions | |
grain | -0.897 |
urdue | -0.868 |
Windsor | -0.849 |
ellar | -0.846 |
afety | -0.815 |
Token | acher |
Token ID | 3493 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
grain | +2.233 |
ellar | +2.224 |
urdue | +2.088 |
font | +2.070 |
Windsor | +2.031 |
Neg logit contributions | |
Debor | -3.632 |
� | -3.299 |
ト | -3.084 |
MSM | -3.069 |
機 | -3.044 |
Token | 's |
Token ID | 338 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
grain | +0.540 |
urdue | +0.517 |
ellar | +0.515 |
Windsor | +0.505 |
font | +0.497 |
Neg logit contributions | |
Debor | -0.639 |
� | -0.568 |
ト | -0.536 |
MSM | -0.532 |
unsus | -0.521 |
Token | Mercedes |
Token ID | 21279 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
grain | +0.738 |
urdue | +0.707 |
ellar | +0.704 |
Windsor | +0.694 |
font | +0.680 |
Neg logit contributions | |
Debor | -0.871 |
� | -0.775 |
ト | -0.730 |
MSM | -0.724 |
unsus | -0.708 |
Token | was |
Token ID | 373 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
grain | +0.087 |
urdue | +0.084 |
ellar | +0.083 |
Windsor | +0.081 |
font | +0.080 |
Neg logit contributions | |
Debor | -0.110 |
� | -0.098 |
ト | -0.092 |
MSM | -0.092 |
unsus | -0.090 |
Token | third |
Token ID | 2368 |
Feature activation | +7.64e+00 |
Pos logit contributions | |
grain | +0.078 |
urdue | +0.075 |
ellar | +0.075 |
Windsor | +0.073 |
font | +0.072 |
Neg logit contributions | |
Debor | -0.081 |
� | -0.072 |
ト | -0.067 |
MSM | -0.067 |
unsus | -0.066 |
Token | ahead |
Token ID | 4058 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
Debor | +5.045 |
� | +4.240 |
MSM | +4.121 |
unsus | +4.117 |
ト | +3.966 |
Neg logit contributions | |
grain | -6.195 |
ellar | -6.041 |
urdue | -5.968 |
afety | -5.809 |
ˈ | -5.698 |
Token | of |
Token ID | 286 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
Debor | +3.107 |
� | +2.649 |
MSM | +2.525 |
ト | +2.496 |
unsus | +2.478 |
Neg logit contributions | |
grain | -3.391 |
ellar | -3.291 |
urdue | -3.248 |
afety | -3.131 |
font | -3.108 |
Token | McLaren |
Token ID | 33017 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Debor | +0.329 |
� | +0.291 |
ト | +0.275 |
MSM | +0.274 |
unsus | +0.267 |
Neg logit contributions | |
grain | -0.286 |
urdue | -0.272 |
ellar | -0.272 |
Windsor | -0.264 |
font | -0.262 |
Token | 's |
Token ID | 338 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Debor | +0.483 |
� | +0.425 |
ト | +0.399 |
MSM | +0.398 |
unsus | +0.389 |
Neg logit contributions | |
grain | -0.468 |
urdue | -0.448 |
ellar | -0.448 |
Windsor | -0.437 |
font | -0.432 |
Token | Lewis |
Token ID | 10174 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
Debor | +0.148 |
� | +0.130 |
MSM | +0.123 |
ト | +0.123 |
unsus | +0.120 |
Neg logit contributions | |
grain | -0.132 |
urdue | -0.126 |
ellar | -0.126 |
Windsor | -0.122 |
font | -0.121 |
Token | downright |
Token ID | 31464 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
grain | +0.113 |
urdue | +0.108 |
ellar | +0.108 |
Windsor | +0.106 |
font | +0.104 |
Neg logit contributions | |
Debor | -0.132 |
� | -0.117 |
ト | -0.111 |
MSM | -0.110 |
unsus | -0.108 |
Token | optimistic |
Token ID | 16915 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
grain | +0.965 |
urdue | +0.918 |
ellar | +0.916 |
Windsor | +0.902 |
font | +0.884 |
Neg logit contributions | |
Debor | -1.296 |
� | -1.158 |
ト | -1.094 |
MSM | -1.086 |
� | -1.067 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Debor | +1.078 |
� | +0.944 |
ト | +0.887 |
MSM | +0.882 |
unsus | +0.863 |
Neg logit contributions | |
grain | -1.081 |
urdue | -1.035 |
ellar | -1.034 |
Windsor | -1.012 |
font | -0.997 |
Token | The |
Token ID | 383 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
Debor | +0.959 |
� | +0.839 |
MSM | +0.795 |
ト | +0.795 |
機 | +0.763 |
Neg logit contributions | |
grain | -0.885 |
urdue | -0.850 |
ellar | -0.846 |
Windsor | -0.819 |
afety | -0.812 |
Token | original |
Token ID | 2656 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
grain | +0.040 |
urdue | +0.039 |
ellar | +0.039 |
Windsor | +0.038 |
font | +0.037 |
Neg logit contributions | |
Debor | -0.044 |
� | -0.039 |
ト | -0.037 |
MSM | -0.036 |
unsus | -0.036 |
Token | End |
Token ID | 5268 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
grain | +1.587 |
ellar | +1.511 |
urdue | +1.510 |
Windsor | +1.498 |
font | +1.478 |
Neg logit contributions | |
Debor | -1.715 |
� | -1.530 |
ト | -1.431 |
MSM | -1.415 |
� | -1.408 |
Token | bringer |
Token ID | 48046 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
grain | +5.378 |
ellar | +5.023 |
font | +4.912 |
Windsor | +4.791 |
urdue | +4.761 |
Neg logit contributions | |
Debor | -9.289 |
� | -8.602 |
� | -8.109 |
unsus | -8.104 |
ト | -8.029 |
Token | stood |
Token ID | 6204 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
grain | +1.524 |
urdue | +1.454 |
ellar | +1.452 |
Windsor | +1.441 |
font | +1.425 |
Neg logit contributions | |
Debor | -1.750 |
� | -1.565 |
ト | -1.463 |
� | -1.442 |
MSM | -1.440 |
Token | about |
Token ID | 546 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
grain | +0.038 |
urdue | +0.037 |
ellar | +0.036 |
Windsor | +0.036 |
font | +0.035 |
Neg logit contributions | |
Debor | -0.044 |
� | -0.039 |
ト | -0.036 |
MSM | -0.036 |
unsus | -0.035 |
Token | forty |
Token ID | 16571 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
Debor | +2.111 |
� | +1.857 |
MSM | +1.760 |
ト | +1.760 |
unsus | +1.733 |
Neg logit contributions | |
grain | -1.753 |
urdue | -1.679 |
ellar | -1.667 |
Windsor | -1.604 |
font | -1.604 |
Token | five |
Token ID | 1936 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
Debor | +1.712 |
� | +1.491 |
ト | +1.379 |
MSM | +1.378 |
unsus | +1.350 |
Neg logit contributions | |
grain | -1.986 |
urdue | -1.916 |
ellar | -1.915 |
Windsor | -1.859 |
afety | -1.841 |
Token | that |
Token ID | 326 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Debor | +2.228 |
� | +1.960 |
ト | +1.848 |
MSM | +1.848 |
unsus | +1.814 |
Neg logit contributions | |
grain | -1.842 |
ellar | -1.754 |
urdue | -1.748 |
Windsor | -1.701 |
font | -1.687 |
Token | the |
Token ID | 262 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
grain | +0.313 |
urdue | +0.299 |
ellar | +0.299 |
Windsor | +0.294 |
font | +0.289 |
Neg logit contributions | |
Debor | -0.355 |
� | -0.315 |
ト | -0.298 |
MSM | -0.294 |
unsus | -0.288 |
Token | crackdown |
Token ID | 22671 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
Debor | +0.420 |
� | +0.367 |
ト | +0.344 |
MSM | +0.343 |
unsus | +0.334 |
Neg logit contributions | |
grain | -0.434 |
urdue | -0.417 |
ellar | -0.416 |
Windsor | -0.407 |
font | -0.403 |
Token | s |
Token ID | 82 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Debor | +0.517 |
� | +0.455 |
ト | +0.428 |
MSM | +0.427 |
unsus | +0.418 |
Neg logit contributions | |
grain | -0.483 |
ellar | -0.462 |
urdue | -0.462 |
Windsor | -0.450 |
font | -0.445 |
Token | against |
Token ID | 1028 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
grain | +0.836 |
urdue | +0.800 |
ellar | +0.798 |
Windsor | +0.784 |
font | +0.771 |
Neg logit contributions | |
Debor | -0.918 |
� | -0.812 |
ト | -0.766 |
MSM | -0.759 |
unsus | -0.743 |
Token | Occupy |
Token ID | 25551 |
Feature activation | -9.76e+00 |
Pos logit contributions | |
grain | +1.416 |
urdue | +1.356 |
ellar | +1.353 |
Windsor | +1.337 |
font | +1.305 |
Neg logit contributions | |
Debor | -1.812 |
� | -1.614 |
ト | -1.530 |
MSM | -1.506 |
� | -1.493 |
Token | protesters |
Token ID | 9584 |
Feature activation | -6.77e+00 |
Pos logit contributions | |
Windsor | +5.933 |
grain | +5.927 |
urdue | +5.842 |
font | +5.617 |
ellar | +5.597 |
Neg logit contributions | |
Debor | -8.113 |
� | -7.193 |
ト | -6.851 |
� | -6.811 |
MSM | -6.776 |
Token | appear |
Token ID | 1656 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
grain | +4.349 |
urdue | +4.249 |
Windsor | +4.185 |
ellar | +4.095 |
font | +4.076 |
Neg logit contributions | |
Debor | -5.529 |
� | -4.995 |
ト | -4.753 |
機 | -4.685 |
� | -4.664 |
Token | to |
Token ID | 284 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Debor | +0.008 |
� | +0.007 |
ト | +0.007 |
MSM | +0.007 |
unsus | +0.006 |
Neg logit contributions | |
grain | -0.008 |
urdue | -0.008 |
ellar | -0.008 |
Windsor | -0.008 |
font | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Debor | +1.547 |
� | +1.363 |
ト | +1.288 |
MSM | +1.285 |
unsus | +1.263 |
Neg logit contributions | |
grain | -1.461 |
ellar | -1.390 |
urdue | -1.389 |
Windsor | -1.350 |
font | -1.345 |
Token | violating |
Token ID | 18134 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
Debor | +1.192 |
� | +1.050 |
MSM | +0.998 |
ト | +0.988 |
unsus | +0.977 |
Neg logit contributions | |
grain | -1.055 |
urdue | -1.010 |
ellar | -1.002 |
Windsor | -0.974 |
font | -0.970 |
Token | =" |
Token ID | 2625 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
grain | +1.298 |
ellar | +1.216 |
urdue | +1.213 |
Windsor | +1.187 |
font | +1.177 |
Neg logit contributions | |
Debor | -2.499 |
� | -2.260 |
ト | -2.160 |
MSM | -2.154 |
unsus | -2.119 |
Token | phone |
Token ID | 4862 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
grain | +1.008 |
urdue | +0.957 |
ellar | +0.957 |
font | +0.941 |
Windsor | +0.941 |
Neg logit contributions | |
Debor | -1.106 |
� | -0.969 |
MSM | -0.912 |
ト | -0.912 |
unsus | -0.893 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Debor | +0.521 |
� | +0.464 |
ト | +0.440 |
MSM | +0.437 |
unsus | +0.428 |
Neg logit contributions | |
grain | -0.406 |
urdue | -0.387 |
ellar | -0.386 |
Windsor | -0.378 |
font | -0.372 |
Token | name |
Token ID | 3672 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Debor | +1.513 |
� | +1.341 |
ト | +1.267 |
MSM | +1.248 |
unsus | +1.222 |
Neg logit contributions | |
grain | -1.386 |
urdue | -1.335 |
ellar | -1.329 |
Windsor | -1.302 |
afety | -1.270 |
Token | "> |
Token ID | 23984 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
Debor | +1.146 |
� | +1.037 |
ト | +0.994 |
MSM | +0.987 |
unsus | +0.971 |
Neg logit contributions | |
grain | -0.597 |
urdue | -0.560 |
ellar | -0.557 |
Windsor | -0.538 |
font | -0.525 |
Token | span |
Token ID | 12626 |
Feature activation | -9.22e+00 |
Pos logit contributions | |
grain | +2.886 |
font | +2.726 |
urdue | +2.718 |
ellar | +2.689 |
Windsor | +2.654 |
Neg logit contributions | |
Debor | -3.594 |
� | -3.187 |
ト | -3.014 |
MSM | -3.001 |
� | -2.966 |
Token | > |
Token ID | 29 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
grain | +3.572 |
font | +3.283 |
Windsor | +3.242 |
ellar | +3.215 |
urdue | +3.200 |
Neg logit contributions | |
Debor | -10.058 |
� | -9.179 |
ト | -8.824 |
MSM | -8.706 |
melanch | -8.614 |
Token | < |
Token ID | 1279 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
grain | +1.241 |
urdue | +1.151 |
ellar | +1.150 |
Windsor | +1.121 |
font | +1.094 |
Neg logit contributions | |
Debor | -3.329 |
� | -3.049 |
ト | -2.925 |
MSM | -2.906 |
� | -2.873 |
Token | p |
Token ID | 79 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
grain | +1.511 |
urdue | +1.425 |
ellar | +1.423 |
font | +1.406 |
Windsor | +1.395 |
Neg logit contributions | |
Debor | -1.983 |
� | -1.761 |
MSM | -1.670 |
ト | -1.668 |
� | -1.639 |
Token | ng |
Token ID | 23370 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
grain | +2.100 |
urdue | +2.014 |
ellar | +1.980 |
Windsor | +1.943 |
font | +1.939 |
Neg logit contributions | |
Debor | -4.698 |
� | -4.267 |
MSM | -4.057 |
ト | -4.048 |
� | -3.983 |
Token | - |
Token ID | 12 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
grain | +2.683 |
ellar | +2.505 |
font | +2.491 |
urdue | +2.484 |
Windsor | +2.461 |
Neg logit contributions | |
Debor | -4.147 |
� | -3.704 |
MSM | -3.533 |
ト | -3.508 |
melanch | -3.466 |
Token | John |
Token ID | 1757 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Debor | +0.208 |
� | +0.181 |
ト | +0.170 |
MSM | +0.168 |
unsus | +0.164 |
Neg logit contributions | |
grain | -0.230 |
urdue | -0.221 |
ellar | -0.220 |
Windsor | -0.217 |
font | -0.214 |
Token | Murd |
Token ID | 20305 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Debor | +0.932 |
� | +0.821 |
ト | +0.775 |
MSM | +0.775 |
unsus | +0.752 |
Neg logit contributions | |
grain | -0.804 |
urdue | -0.771 |
ellar | -0.761 |
Windsor | -0.741 |
afety | -0.736 |
Token | y |
Token ID | 88 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
grain | +1.280 |
ellar | +1.208 |
urdue | +1.202 |
Windsor | +1.160 |
font | +1.142 |
Neg logit contributions | |
Debor | -2.521 |
� | -2.292 |
ト | -2.188 |
MSM | -2.168 |
機 | -2.137 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Debor | +0.865 |
� | +0.764 |
ト | +0.719 |
MSM | +0.714 |
unsus | +0.698 |
Neg logit contributions | |
grain | -0.812 |
urdue | -0.778 |
ellar | -0.775 |
Windsor | -0.760 |
font | -0.747 |
Token | Halloween |
Token ID | 16032 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
Debor | +1.090 |
� | +0.968 |
MSM | +0.915 |
ト | +0.914 |
unsus | +0.892 |
Neg logit contributions | |
grain | -0.889 |
urdue | -0.848 |
ellar | -0.842 |
Windsor | -0.819 |
font | -0.810 |
Token | Horror |
Token ID | 22732 |
Feature activation | -8.81e+00 |
Pos logit contributions | |
grain | +1.738 |
ellar | +1.657 |
urdue | +1.654 |
Windsor | +1.632 |
font | +1.601 |
Neg logit contributions | |
Debor | -2.168 |
� | -1.927 |
ト | -1.823 |
MSM | -1.811 |
� | -1.778 |
Token | Nights |
Token ID | 27760 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
grain | +4.977 |
ellar | +4.836 |
Windsor | +4.833 |
urdue | +4.790 |
Citizens | +4.756 |
Neg logit contributions | |
Debor | -7.543 |
� | -6.731 |
� | -6.383 |
MSM | -6.349 |
ト | -6.326 |
Token | ' |
Token ID | 6 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
grain | +1.096 |
urdue | +1.047 |
ellar | +1.044 |
Windsor | +1.023 |
font | +1.007 |
Neg logit contributions | |
Debor | -1.330 |
� | -1.182 |
ト | -1.118 |
MSM | -1.110 |
unsus | -1.087 |
Token | Creative |
Token ID | 17404 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
grain | +2.680 |
ellar | +2.565 |
urdue | +2.561 |
Windsor | +2.556 |
font | +2.468 |
Neg logit contributions | |
Debor | -3.657 |
� | -3.289 |
ト | -3.115 |
MSM | -3.065 |
機 | -3.048 |
Token | Director |
Token ID | 5890 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
grain | +1.704 |
ellar | +1.586 |
urdue | +1.572 |
Windsor | +1.569 |
font | +1.504 |
Neg logit contributions | |
Debor | -4.404 |
� | -4.047 |
ト | -3.885 |
MSM | -3.825 |
機 | -3.818 |
Token | , |
Token ID | 11 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
grain | +2.884 |
urdue | +2.783 |
ellar | +2.777 |
Windsor | +2.740 |
font | +2.720 |
Neg logit contributions | |
Debor | -3.105 |
� | -2.755 |
ト | -2.605 |
MSM | -2.580 |
unsus | -2.549 |
Token | not |
Token ID | 407 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
grain | +1.284 |
urdue | +1.226 |
ellar | +1.222 |
Windsor | +1.203 |
font | +1.181 |
Neg logit contributions | |
Debor | -1.660 |
� | -1.483 |
ト | -1.405 |
MSM | -1.389 |
� | -1.367 |
Token | protecting |
Token ID | 10192 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
grain | +0.869 |
urdue | +0.829 |
ellar | +0.827 |
Windsor | +0.813 |
font | +0.799 |
Neg logit contributions | |
Debor | -1.081 |
� | -0.962 |
ト | -0.912 |
MSM | -0.903 |
� | -0.886 |
Token | the |
Token ID | 262 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
Debor | +0.591 |
� | +0.521 |
ト | +0.491 |
MSM | +0.489 |
unsus | +0.478 |
Neg logit contributions | |
grain | -0.556 |
urdue | -0.532 |
ellar | -0.531 |
Windsor | -0.519 |
font | -0.513 |
Token | rights |
Token ID | 2489 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
grain | +0.358 |
urdue | +0.343 |
ellar | +0.342 |
Windsor | +0.336 |
font | +0.331 |
Neg logit contributions | |
Debor | -0.370 |
� | -0.325 |
ト | -0.306 |
MSM | -0.304 |
unsus | -0.297 |
Token | of |
Token ID | 286 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
Debor | +0.606 |
� | +0.534 |
ト | +0.503 |
MSM | +0.499 |
unsus | +0.488 |
Neg logit contributions | |
grain | -0.570 |
urdue | -0.546 |
ellar | -0.545 |
Windsor | -0.534 |
font | -0.527 |
Token | Occupy |
Token ID | 25551 |
Feature activation | -8.58e+00 |
Pos logit contributions | |
Debor | +0.038 |
� | +0.033 |
ト | +0.031 |
MSM | +0.031 |
unsus | +0.030 |
Neg logit contributions | |
grain | -0.037 |
urdue | -0.036 |
ellar | -0.036 |
Windsor | -0.035 |
font | -0.035 |
Token | demonstrators |
Token ID | 25016 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
grain | +4.955 |
Windsor | +4.952 |
urdue | +4.805 |
font | +4.670 |
Citizens | +4.669 |
Neg logit contributions | |
Debor | -7.547 |
� | -6.623 |
ト | -6.377 |
� | -6.326 |
機 | -6.263 |
Token | whose |
Token ID | 3025 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
grain | +3.836 |
urdue | +3.766 |
Windsor | +3.730 |
font | +3.631 |
ellar | +3.615 |
Neg logit contributions | |
Debor | -4.662 |
� | -4.183 |
ト | -3.983 |
機 | -3.929 |
MSM | -3.912 |
Token | protests |
Token ID | 8536 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
Debor | +0.031 |
� | +0.027 |
ト | +0.025 |
MSM | +0.025 |
unsus | +0.025 |
Neg logit contributions | |
grain | -0.030 |
urdue | -0.029 |
ellar | -0.028 |
Windsor | -0.028 |
font | -0.028 |
Token | are |
Token ID | 389 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
grain | +2.447 |
urdue | +2.354 |
Windsor | +2.321 |
ellar | +2.318 |
font | +2.263 |
Neg logit contributions | |
Debor | -2.929 |
� | -2.615 |
ト | -2.479 |
MSM | -2.430 |
機 | -2.407 |
Token | being |
Token ID | 852 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
grain | +0.483 |
urdue | +0.462 |
ellar | +0.461 |
Windsor | +0.451 |
font | +0.445 |
Neg logit contributions | |
Debor | -0.521 |
� | -0.459 |
ト | -0.432 |
MSM | -0.430 |
unsus | -0.422 |
Token | phone |
Token ID | 4862 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
grain | +0.741 |
urdue | +0.708 |
ellar | +0.707 |
Windsor | +0.694 |
font | +0.694 |
Neg logit contributions | |
Debor | -0.679 |
� | -0.587 |
ト | -0.549 |
MSM | -0.548 |
unsus | -0.536 |
Token | in |
Token ID | 287 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Debor | +0.073 |
� | +0.063 |
ト | +0.058 |
MSM | +0.058 |
unsus | +0.056 |
Neg logit contributions | |
grain | -0.088 |
urdue | -0.085 |
ellar | -0.085 |
Windsor | -0.083 |
font | -0.082 |
Token | phones |
Token ID | 9512 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
Debor | +0.827 |
� | +0.728 |
ト | +0.683 |
MSM | +0.680 |
unsus | +0.664 |
Neg logit contributions | |
grain | -0.817 |
urdue | -0.783 |
ellar | -0.782 |
Windsor | -0.765 |
font | -0.754 |
Token | "> |
Token ID | 5320 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
Debor | +0.099 |
� | +0.090 |
ト | +0.087 |
MSM | +0.086 |
unsus | +0.085 |
Neg logit contributions | |
grain | -0.039 |
urdue | -0.036 |
ellar | -0.036 |
Windsor | -0.035 |
font | -0.034 |
Token | < |
Token ID | 1279 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
grain | +1.200 |
urdue | +1.114 |
ellar | +1.099 |
Windsor | +1.082 |
font | +1.063 |
Neg logit contributions | |
Debor | -3.172 |
� | -2.897 |
MSM | -2.768 |
ト | -2.761 |
unsus | -2.729 |
Token | span |
Token ID | 12626 |
Feature activation | -8.55e+00 |
Pos logit contributions | |
grain | +0.258 |
urdue | +0.244 |
ellar | +0.243 |
Windsor | +0.237 |
font | +0.236 |
Neg logit contributions | |
Debor | -0.376 |
� | -0.336 |
ト | -0.320 |
MSM | -0.318 |
unsus | -0.314 |
Token | ng |
Token ID | 23370 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
grain | +4.219 |
font | +4.132 |
Windsor | +4.008 |
ellar | +3.996 |
urdue | +3.992 |
Neg logit contributions | |
Debor | -8.245 |
� | -7.479 |
ト | -7.153 |
MSM | -6.996 |
機 | -6.931 |
Token | - |
Token ID | 12 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
grain | +2.748 |
font | +2.590 |
ellar | +2.552 |
Windsor | +2.510 |
urdue | +2.504 |
Neg logit contributions | |
Debor | -4.488 |
� | -4.009 |
MSM | -3.837 |
ト | -3.810 |
unsus | -3.795 |
Token | bind |
Token ID | 21653 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
grain | +1.122 |
ellar | +1.061 |
urdue | +1.059 |
font | +1.047 |
Windsor | +1.039 |
Neg logit contributions | |
Debor | -1.235 |
� | -1.084 |
MSM | -1.024 |
ト | -1.023 |
unsus | -0.998 |
Token | =" |
Token ID | 2625 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
grain | +1.298 |
ellar | +1.216 |
urdue | +1.213 |
Windsor | +1.187 |
font | +1.177 |
Neg logit contributions | |
Debor | -2.499 |
� | -2.260 |
ト | -2.160 |
MSM | -2.154 |
unsus | -2.119 |
Token | phone |
Token ID | 4862 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
grain | +1.008 |
urdue | +0.957 |
ellar | +0.957 |
font | +0.941 |
Windsor | +0.941 |
Neg logit contributions | |
Debor | -1.106 |
� | -0.969 |
MSM | -0.912 |
ト | -0.912 |
unsus | -0.893 |
Token | to |
Token ID | 284 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Debor | +0.803 |
� | +0.704 |
ト | +0.661 |
MSM | +0.659 |
unsus | +0.642 |
Neg logit contributions | |
grain | -0.789 |
urdue | -0.758 |
ellar | -0.756 |
Windsor | -0.740 |
font | -0.730 |
Token | the |
Token ID | 262 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
Debor | +1.183 |
� | +1.027 |
ト | +0.959 |
MSM | +0.953 |
unsus | +0.928 |
Neg logit contributions | |
grain | -1.365 |
urdue | -1.314 |
ellar | -1.311 |
Windsor | -1.285 |
font | -1.271 |
Token | hugely |
Token ID | 22641 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
grain | +0.002 |
urdue | +0.002 |
ellar | +0.002 |
Windsor | +0.002 |
font | +0.002 |
Neg logit contributions | |
Debor | -0.002 |
� | -0.002 |
ト | -0.002 |
MSM | -0.002 |
unsus | -0.002 |
Token | popular |
Token ID | 2968 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Debor | +2.230 |
� | +1.944 |
ト | +1.830 |
MSM | +1.819 |
unsus | +1.786 |
Neg logit contributions | |
grain | -2.562 |
urdue | -2.454 |
ellar | -2.438 |
afety | -2.400 |
Windsor | -2.374 |
Token | Halloween |
Token ID | 16032 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Debor | +0.928 |
� | +0.820 |
ト | +0.775 |
MSM | +0.770 |
unsus | +0.753 |
Neg logit contributions | |
grain | -0.817 |
urdue | -0.781 |
ellar | -0.780 |
Windsor | -0.762 |
font | -0.752 |
Token | Horror |
Token ID | 22732 |
Feature activation | -8.24e+00 |
Pos logit contributions | |
grain | +1.067 |
ellar | +1.020 |
urdue | +1.019 |
Windsor | +1.010 |
font | +0.990 |
Neg logit contributions | |
Debor | -1.216 |
� | -1.076 |
MSM | -1.008 |
ト | -1.007 |
� | -0.988 |
Token | Nights |
Token ID | 27760 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
grain | +5.051 |
Craft | +4.904 |
Windsor | +4.898 |
Citizens | +4.802 |
urdue | +4.794 |
Neg logit contributions | |
Debor | -6.864 |
� | -6.121 |
� | -5.787 |
機 | -5.688 |
MSM | -5.666 |
Token | , |
Token ID | 11 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Debor | +0.246 |
� | +0.218 |
ト | +0.206 |
MSM | +0.204 |
unsus | +0.200 |
Neg logit contributions | |
grain | -0.220 |
urdue | -0.210 |
ellar | -0.210 |
Windsor | -0.205 |
font | -0.202 |
Token | I |
Token ID | 314 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
grain | +0.246 |
urdue | +0.236 |
ellar | +0.235 |
Windsor | +0.231 |
font | +0.228 |
Neg logit contributions | |
Debor | -0.239 |
� | -0.210 |
ト | -0.197 |
MSM | -0.196 |
unsus | -0.191 |
Token | returned |
Token ID | 4504 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Debor | +0.074 |
� | +0.065 |
ト | +0.061 |
MSM | +0.061 |
unsus | +0.060 |
Neg logit contributions | |
grain | -0.069 |
urdue | -0.066 |
ellar | -0.066 |
Windsor | -0.064 |
font | -0.063 |
Token | for |
Token ID | 329 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
grain | +1.117 |
urdue | +1.069 |
ellar | +1.061 |
Windsor | +1.061 |
font | +1.033 |
Neg logit contributions | |
Debor | -1.180 |
� | -1.049 |
ト | -0.984 |
MSM | -0.979 |
機 | -0.960 |
Token | Manufacturing |
Token ID | 32760 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Debor | +3.982 |
� | +3.457 |
MSM | +3.385 |
ト | +3.250 |
socket | +3.171 |
Neg logit contributions | |
grain | -4.270 |
urdue | -4.138 |
ellar | -4.105 |
afety | -4.012 |
Windsor | -3.926 |
Token | Process |
Token ID | 10854 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Debor | +1.762 |
� | +1.576 |
MSM | +1.511 |
ト | +1.494 |
unsus | +1.462 |
Neg logit contributions | |
grain | -1.257 |
urdue | -1.204 |
ellar | -1.202 |
Windsor | -1.157 |
font | -1.145 |
Token | 14 |
Token ID | 1478 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
grain | +0.928 |
urdue | +0.885 |
ellar | +0.881 |
Windsor | +0.867 |
font | +0.852 |
Neg logit contributions | |
Debor | -1.135 |
� | -1.011 |
ト | -0.954 |
MSM | -0.941 |
unsus | -0.935 |
Token | nm |
Token ID | 21533 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
grain | +0.695 |
urdue | +0.662 |
ellar | +0.654 |
Windsor | +0.651 |
font | +0.638 |
Neg logit contributions | |
Debor | -0.797 |
� | -0.704 |
ト | -0.661 |
MSM | -0.654 |
unsus | -0.650 |
Token | 28 |
Token ID | 2579 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
grain | +3.416 |
Windsor | +3.244 |
urdue | +3.200 |
ellar | +3.126 |
font | +3.100 |
Neg logit contributions | |
Debor | -6.036 |
� | -5.436 |
ト | -5.139 |
unsus | -5.106 |
melanch | -5.049 |
Token | nm |
Token ID | 21533 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
grain | +1.429 |
urdue | +1.357 |
ellar | +1.348 |
Windsor | +1.336 |
font | +1.309 |
Neg logit contributions | |
Debor | -1.719 |
� | -1.526 |
ト | -1.430 |
MSM | -1.416 |
unsus | -1.409 |
Token | 28 |
Token ID | 2579 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
grain | +4.246 |
Windsor | +4.097 |
urdue | +3.963 |
Craft | +3.913 |
font | +3.885 |
Neg logit contributions | |
Debor | -7.598 |
� | -6.980 |
unsus | -6.676 |
ト | -6.576 |
� | -6.564 |
Token | nm |
Token ID | 21533 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
grain | +3.035 |
ellar | +2.869 |
urdue | +2.850 |
font | +2.798 |
Windsor | +2.796 |
Neg logit contributions | |
Debor | -3.831 |
� | -3.364 |
ト | -3.151 |
unsus | -3.123 |
MSM | -3.123 |
Token | 16 |
Token ID | 1467 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
grain | +3.378 |
Windsor | +3.201 |
urdue | +3.175 |
ellar | +3.141 |
font | +3.095 |
Neg logit contributions | |
Debor | -5.805 |
� | -5.295 |
ト | -5.019 |
unsus | -5.013 |
� | -4.982 |
Token | nm |
Token ID | 21533 |
Feature activation | -5.66e+00 |
Pos logit contributions | |
grain | +0.836 |
urdue | +0.796 |
ellar | +0.795 |
Windsor | +0.780 |
font | +0.770 |
Neg logit contributions | |
Debor | -0.948 |
� | -0.837 |
ト | -0.788 |
MSM | -0.780 |
unsus | -0.771 |
Token | 16 |
Token ID | 1467 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
grain | +3.024 |
Windsor | +2.867 |
urdue | +2.819 |
ellar | +2.777 |
font | +2.739 |
Neg logit contributions | |
Debor | -5.363 |
� | -4.890 |
ト | -4.641 |
unsus | -4.632 |
� | -4.568 |
Token | t |
Token ID | 83 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
grain | +2.476 |
ellar | +2.264 |
font | +2.230 |
urdue | +2.216 |
Windsor | +2.195 |
Neg logit contributions | |
Debor | -3.685 |
� | -3.328 |
ト | -3.146 |
� | -3.110 |
MSM | -3.081 |
Token | ong |
Token ID | 506 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
grain | +1.029 |
ellar | +0.952 |
urdue | +0.924 |
Windsor | +0.888 |
font | +0.868 |
Neg logit contributions | |
Debor | -2.917 |
� | -2.687 |
ト | -2.555 |
MSM | -2.554 |
� | -2.527 |
Token | ue |
Token ID | 518 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
grain | +1.834 |
ellar | +1.737 |
urdue | +1.731 |
Windsor | +1.713 |
font | +1.684 |
Neg logit contributions | |
Debor | -1.937 |
� | -1.731 |
ト | -1.619 |
MSM | -1.595 |
unsus | -1.573 |
Token | . |
Token ID | 13 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
grain | +1.414 |
urdue | +1.350 |
ellar | +1.346 |
Windsor | +1.330 |
font | +1.315 |
Neg logit contributions | |
Debor | -1.556 |
� | -1.376 |
ト | -1.301 |
MSM | -1.293 |
� | -1.263 |
Token | Th |
Token ID | 536 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
grain | +0.421 |
urdue | +0.403 |
ellar | +0.402 |
Windsor | +0.392 |
font | +0.387 |
Neg logit contributions | |
Debor | -0.470 |
� | -0.414 |
ト | -0.391 |
MSM | -0.389 |
unsus | -0.379 |
Token | é |
Token ID | 2634 |
Feature activation | -8.11e+00 |
Pos logit contributions | |
grain | +1.507 |
ellar | +1.447 |
urdue | +1.443 |
Windsor | +1.408 |
font | +1.400 |
Neg logit contributions | |
Debor | -1.780 |
� | -1.587 |
ト | -1.495 |
MSM | -1.486 |
� | -1.458 |
Token | od |
Token ID | 375 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
grain | +3.679 |
ellar | +3.437 |
urdue | +3.354 |
font | +3.316 |
Windsor | +3.282 |
Neg logit contributions | |
Debor | -8.437 |
� | -7.684 |
MSM | -7.380 |
unden | -7.265 |
ト | -7.255 |
Token | en |
Token ID | 268 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
grain | +3.023 |
ellar | +2.905 |
urdue | +2.829 |
font | +2.821 |
Windsor | +2.776 |
Neg logit contributions | |
Debor | -5.861 |
� | -5.289 |
MSM | -5.089 |
ト | -5.036 |
� | -5.007 |
Token | must |
Token ID | 1276 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
grain | +1.991 |
urdue | +1.917 |
ellar | +1.893 |
Windsor | +1.887 |
font | +1.839 |
Neg logit contributions | |
Debor | -2.699 |
� | -2.425 |
ト | -2.298 |
MSM | -2.281 |
� | -2.250 |
Token | ers |
Token ID | 364 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
grain | +1.331 |
ellar | +1.271 |
urdue | +1.270 |
Windsor | +1.240 |
font | +1.222 |
Neg logit contributions | |
Debor | -1.715 |
� | -1.531 |
ト | -1.446 |
MSM | -1.437 |
� | -1.406 |
Token | his |
Token ID | 465 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
grain | +1.698 |
urdue | +1.612 |
ellar | +1.610 |
Windsor | +1.587 |
font | +1.558 |
Neg logit contributions | |
Debor | -2.062 |
� | -1.833 |
ト | -1.733 |
MSM | -1.721 |
� | -1.687 |
Token | shareholders |
Token ID | 19195 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
grain | +0.281 |
urdue | +0.269 |
ellar | +0.269 |
font | +0.259 |
Windsor | +0.259 |
Neg logit contributions | |
Debor | -0.299 |
� | -0.261 |
MSM | -0.247 |
ト | -0.246 |
unsus | -0.241 |
Token | ," |
Token ID | 553 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
grain | +2.730 |
Windsor | +2.633 |
urdue | +2.607 |
ellar | +2.576 |
font | +2.527 |
Neg logit contributions | |
Debor | -3.237 |
� | -2.909 |
ト | -2.779 |
� | -2.735 |
MSM | -2.704 |
Token | deputy |
Token ID | 10636 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
grain | +1.388 |
urdue | +1.326 |
ellar | +1.323 |
Windsor | +1.309 |
font | +1.273 |
Neg logit contributions | |
Debor | -1.722 |
� | -1.539 |
ト | -1.456 |
MSM | -1.440 |
unsus | -1.414 |
Token | Conservative |
Token ID | 11132 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
grain | +2.073 |
urdue | +1.977 |
ellar | +1.973 |
Windsor | +1.950 |
font | +1.903 |
Neg logit contributions | |
Debor | -2.549 |
� | -2.268 |
ト | -2.148 |
MSM | -2.129 |
unsus | -2.090 |
Token | leader |
Token ID | 3554 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
grain | +4.249 |
Windsor | +4.189 |
ellar | +4.048 |
urdue | +4.007 |
Citizens | +3.894 |
Neg logit contributions | |
Debor | -5.247 |
� | -4.771 |
ト | -4.507 |
� | -4.433 |
MSM | -4.419 |
Token | Lisa |
Token ID | 15378 |
Feature activation | -8.06e+00 |
Pos logit contributions | |
grain | +2.172 |
urdue | +2.072 |
Windsor | +2.072 |
ellar | +2.067 |
font | +2.010 |
Neg logit contributions | |
Debor | -2.565 |
� | -2.319 |
ト | -2.183 |
MSM | -2.159 |
機 | -2.136 |
Token | Ra |
Token ID | 7567 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
grain | +3.530 |
Windsor | +3.454 |
ellar | +3.322 |
font | +3.200 |
Craft | +3.164 |
Neg logit contributions | |
Debor | -8.397 |
� | -7.797 |
ト | -7.440 |
MSM | -7.317 |
unsus | -7.311 |
Token | itt |
Token ID | 715 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
Debor | +0.862 |
� | +0.752 |
ト | +0.712 |
MSM | +0.702 |
unsus | +0.682 |
Neg logit contributions | |
grain | -0.938 |
urdue | -0.905 |
ellar | -0.904 |
Windsor | -0.888 |
afety | -0.875 |
Token | said |
Token ID | 531 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
grain | +1.789 |
ellar | +1.684 |
urdue | +1.681 |
Windsor | +1.648 |
font | +1.598 |
Neg logit contributions | |
Debor | -3.298 |
� | -2.985 |
ト | -2.854 |
MSM | -2.832 |
unsus | -2.793 |
Token | . |
Token ID | 13 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
grain | +2.586 |
urdue | +2.517 |
Windsor | +2.516 |
ellar | +2.485 |
font | +2.428 |
Neg logit contributions | |
Debor | -2.767 |
� | -2.493 |
ト | -2.357 |
MSM | -2.297 |
� | -2.286 |
Token | " |
Token ID | 366 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
grain | +1.541 |
urdue | +1.464 |
ellar | +1.460 |
Windsor | +1.432 |
font | +1.403 |
Neg logit contributions | |
Debor | -2.284 |
� | -2.053 |
ト | -1.952 |
MSM | -1.936 |
unsus | -1.909 |
Token | fossils |
Token ID | 34066 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
grain | +1.531 |
ellar | +1.462 |
urdue | +1.454 |
Windsor | +1.430 |
font | +1.398 |
Neg logit contributions | |
Debor | -2.018 |
� | -1.808 |
ト | -1.718 |
MSM | -1.689 |
� | -1.667 |
Token | , |
Token ID | 11 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
grain | +1.971 |
ellar | +1.878 |
urdue | +1.877 |
Windsor | +1.837 |
font | +1.813 |
Neg logit contributions | |
Debor | -2.262 |
� | -2.013 |
ト | -1.895 |
MSM | -1.871 |
� | -1.841 |
Token | geographic |
Token ID | 22987 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
grain | +2.084 |
urdue | +1.987 |
ellar | +1.983 |
Windsor | +1.956 |
font | +1.911 |
Neg logit contributions | |
Debor | -2.571 |
� | -2.297 |
ト | -2.175 |
MSM | -2.138 |
� | -2.116 |
Token | regions |
Token ID | 7652 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
grain | +2.643 |
ellar | +2.552 |
urdue | +2.469 |
Windsor | +2.463 |
font | +2.418 |
Neg logit contributions | |
Debor | -3.005 |
� | -2.684 |
ト | -2.546 |
� | -2.473 |
MSM | -2.464 |
Token | and |
Token ID | 290 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
grain | +2.816 |
ellar | +2.689 |
urdue | +2.647 |
Windsor | +2.613 |
font | +2.573 |
Neg logit contributions | |
Debor | -3.447 |
� | -3.096 |
ト | -2.936 |
MSM | -2.854 |
� | -2.838 |
Token | strat |
Token ID | 25369 |
Feature activation | -8.03e+00 |
Pos logit contributions | |
grain | +1.567 |
ellar | +1.498 |
urdue | +1.479 |
Windsor | +1.465 |
font | +1.426 |
Neg logit contributions | |
Debor | -1.920 |
� | -1.720 |
ト | -1.626 |
MSM | -1.585 |
機 | -1.572 |
Token | ig |
Token ID | 328 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
grain | +3.319 |
ellar | +3.237 |
urdue | +2.986 |
font | +2.852 |
Windsor | +2.797 |
Neg logit contributions | |
Debor | -8.710 |
� | -7.982 |
ト | -7.714 |
MSM | -7.606 |
機 | -7.574 |
Token | raphic |
Token ID | 22262 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
grain | +0.749 |
urdue | +0.700 |
ellar | +0.689 |
Windsor | +0.682 |
font | +0.653 |
Neg logit contributions | |
Debor | -1.908 |
� | -1.746 |
MSM | -1.672 |
ト | -1.668 |
unsus | -1.640 |
Token | positions |
Token ID | 6116 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
grain | +4.186 |
ellar | +4.057 |
Windsor | +3.918 |
font | +3.891 |
urdue | +3.875 |
Neg logit contributions | |
Debor | -4.346 |
� | -3.838 |
ト | -3.701 |
� | -3.596 |
機 | -3.533 |
Token | make |
Token ID | 787 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
grain | +3.092 |
urdue | +2.932 |
ellar | +2.924 |
Windsor | +2.880 |
font | +2.842 |
Neg logit contributions | |
Debor | -3.654 |
� | -3.257 |
ト | -3.092 |
MSM | -3.027 |
� | -3.011 |
Token | random |
Token ID | 4738 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
grain | +0.718 |
ellar | +0.687 |
urdue | +0.683 |
Windsor | +0.673 |
font | +0.660 |
Neg logit contributions | |
Debor | -0.766 |
� | -0.678 |
ト | -0.639 |
MSM | -0.627 |
機 | -0.617 |
Token | . |
Token ID | 13 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
Debor | +0.860 |
� | +0.757 |
ト | +0.714 |
MSM | +0.709 |
� | +0.690 |
Neg logit contributions | |
grain | -0.812 |
urdue | -0.780 |
ellar | -0.775 |
Windsor | -0.763 |
font | -0.753 |
Token | � |
Token ID | 564 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
Debor | +2.145 |
� | +1.899 |
ト | +1.795 |
MSM | +1.787 |
機 | +1.732 |
Neg logit contributions | |
grain | -1.820 |
ellar | -1.741 |
urdue | -1.737 |
Windsor | -1.678 |
afety | -1.661 |
Token | � |
Token ID | 250 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
grain | +0.275 |
urdue | +0.265 |
ellar | +0.264 |
Windsor | +0.260 |
font | +0.256 |
Neg logit contributions | |
Debor | -0.218 |
� | -0.188 |
ト | -0.175 |
MSM | -0.173 |
unsus | -0.168 |
Token | For |
Token ID | 1890 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
grain | +0.030 |
urdue | +0.028 |
ellar | +0.028 |
Windsor | +0.028 |
font | +0.027 |
Neg logit contributions | |
Debor | -0.035 |
� | -0.031 |
ト | -0.029 |
MSM | -0.029 |
unsus | -0.028 |
Token | give |
Token ID | 26535 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
grain | +0.084 |
urdue | +0.080 |
ellar | +0.080 |
Windsor | +0.078 |
font | +0.077 |
Neg logit contributions | |
Debor | -0.111 |
� | -0.099 |
ト | -0.094 |
MSM | -0.093 |
unsus | -0.091 |
Token | me |
Token ID | 502 |
Feature activation | -8.02e+00 |
Pos logit contributions | |
grain | +2.592 |
urdue | +2.477 |
ellar | +2.469 |
Windsor | +2.466 |
font | +2.417 |
Neg logit contributions | |
Debor | -2.525 |
� | -2.244 |
ト | -2.069 |
MSM | -2.066 |
� | -2.054 |
Token | ! |
Token ID | 0 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
grain | +4.969 |
Windsor | +4.659 |
ellar | +4.609 |
urdue | +4.587 |
font | +4.581 |
Neg logit contributions | |
Debor | -6.558 |
� | -5.942 |
ト | -5.742 |
� | -5.662 |
MSM | -5.572 |
Token | Please |
Token ID | 4222 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
grain | +1.747 |
urdue | +1.664 |
ellar | +1.653 |
Windsor | +1.636 |
font | +1.613 |
Neg logit contributions | |
Debor | -1.968 |
� | -1.745 |
ト | -1.648 |
MSM | -1.630 |
unsus | -1.621 |
Token | forgive |
Token ID | 20927 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Debor | +0.441 |
� | +0.389 |
ト | +0.367 |
MSM | +0.365 |
unsus | +0.357 |
Neg logit contributions | |
grain | -0.404 |
urdue | -0.387 |
ellar | -0.387 |
Windsor | -0.378 |
font | -0.372 |
Token | me |
Token ID | 502 |
Feature activation | -5.53e+00 |
Pos logit contributions | |
grain | +1.347 |
urdue | +1.294 |
ellar | +1.291 |
Windsor | +1.279 |
font | +1.256 |
Neg logit contributions | |
Debor | -1.233 |
� | -1.085 |
ト | -1.010 |
MSM | -0.999 |
� | -0.988 |
Token | ! |
Token ID | 0 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
grain | +3.518 |
urdue | +3.379 |
ellar | +3.347 |
Windsor | +3.313 |
font | +3.262 |
Neg logit contributions | |
Debor | -4.566 |
� | -4.088 |
ト | -3.923 |
MSM | -3.875 |
� | -3.843 |
Token | It |
Token ID | 632 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
grain | +1.447 |
urdue | +1.384 |
ellar | +1.370 |
Windsor | +1.365 |
font | +1.342 |
Neg logit contributions | |
Debor | -1.642 |
� | -1.462 |
ト | -1.379 |
unsus | -1.358 |
MSM | -1.355 |
Token | � |
Token ID | 447 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
grain | +1.530 |
urdue | +1.463 |
ellar | +1.450 |
Windsor | +1.419 |
font | +1.414 |
Neg logit contributions | |
Debor | -1.855 |
� | -1.641 |
MSM | -1.551 |
ト | -1.548 |
unsus | -1.516 |
Token | � |
Token ID | 247 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
grain | +0.030 |
urdue | +0.029 |
ellar | +0.029 |
Windsor | +0.028 |
font | +0.028 |
Neg logit contributions | |
Debor | -0.034 |
� | -0.030 |
ト | -0.029 |
MSM | -0.028 |
unsus | -0.028 |
Token | s |
Token ID | 82 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Debor | +0.086 |
� | +0.076 |
ト | +0.072 |
MSM | +0.071 |
unsus | +0.070 |
Neg logit contributions | |
grain | -0.078 |
urdue | -0.075 |
ellar | -0.075 |
Windsor | -0.073 |
font | -0.072 |
Token | my |
Token ID | 616 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
grain | +0.705 |
urdue | +0.674 |
ellar | +0.671 |
Windsor | +0.660 |
font | +0.649 |
Neg logit contributions | |
Debor | -0.826 |
� | -0.733 |
ト | -0.692 |
MSM | -0.687 |
unsus | -0.673 |
Token | fault |
Token ID | 8046 |
Feature activation | -7.92e+00 |
Pos logit contributions | |
grain | +1.251 |
urdue | +1.200 |
ellar | +1.189 |
Windsor | +1.173 |
font | +1.158 |
Neg logit contributions | |
Debor | -1.414 |
� | -1.251 |
ト | -1.177 |
MSM | -1.171 |
� | -1.148 |
Token | . |
Token ID | 13 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
grain | +4.857 |
ellar | +4.712 |
urdue | +4.696 |
font | +4.637 |
Windsor | +4.636 |
Neg logit contributions | |
Debor | -6.509 |
� | -5.894 |
ト | -5.694 |
� | -5.496 |
機 | -5.466 |
Token | # |
Token ID | 1303 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
grain | +0.272 |
urdue | +0.260 |
ellar | +0.259 |
Windsor | +0.255 |
font | +0.252 |
Neg logit contributions | |
Debor | -0.286 |
� | -0.253 |
ト | -0.238 |
MSM | -0.235 |
unsus | -0.232 |
Token | atl |
Token ID | 25864 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
grain | +0.845 |
ellar | +0.801 |
urdue | +0.799 |
Windsor | +0.784 |
font | +0.780 |
Neg logit contributions | |
Debor | -0.942 |
� | -0.828 |
ト | -0.780 |
MSM | -0.777 |
unsus | -0.765 |
Token | weather |
Token ID | 23563 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
grain | +2.009 |
urdue | +1.888 |
ellar | +1.859 |
font | +1.818 |
Windsor | +1.815 |
Neg logit contributions | |
Debor | -2.998 |
� | -2.691 |
ト | -2.533 |
MSM | -2.528 |
unsus | -2.488 |
Token | # |
Token ID | 1303 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Debor | +1.155 |
� | +1.025 |
ト | +0.967 |
MSM | +0.962 |
unsus | +0.940 |
Neg logit contributions | |
grain | -0.985 |
urdue | -0.946 |
ellar | -0.944 |
Windsor | -0.925 |
font | -0.906 |
Token | , |
Token ID | 11 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
grain | +1.751 |
urdue | +1.650 |
ellar | +1.648 |
font | +1.598 |
Windsor | +1.597 |
Neg logit contributions | |
Debor | -2.001 |
� | -1.776 |
ト | -1.677 |
MSM | -1.658 |
� | -1.631 |
Token | and |
Token ID | 290 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
grain | +1.448 |
urdue | +1.366 |
ellar | +1.355 |
Windsor | +1.327 |
font | +1.310 |
Neg logit contributions | |
Debor | -2.044 |
� | -1.834 |
ト | -1.731 |
MSM | -1.714 |
� | -1.694 |
Token | Prof |
Token ID | 4415 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
grain | +0.664 |
urdue | +0.631 |
ellar | +0.627 |
Windsor | +0.617 |
font | +0.607 |
Neg logit contributions | |
Debor | -0.789 |
� | -0.702 |
ト | -0.661 |
MSM | -0.654 |
� | -0.643 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
grain | +1.734 |
ellar | +1.659 |
urdue | +1.659 |
Windsor | +1.631 |
font | +1.608 |
Neg logit contributions | |
Debor | -1.881 |
� | -1.672 |
ト | -1.578 |
MSM | -1.557 |
unsus | -1.532 |
Token | Loren |
Token ID | 32035 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
grain | +1.678 |
urdue | +1.605 |
ellar | +1.592 |
Windsor | +1.582 |
font | +1.553 |
Neg logit contributions | |
Debor | -1.840 |
� | -1.634 |
ト | -1.541 |
MSM | -1.529 |
unsus | -1.508 |
Token | Cord |
Token ID | 21119 |
Feature activation | -7.91e+00 |
Pos logit contributions | |
grain | +3.710 |
ellar | +3.495 |
urdue | +3.492 |
Windsor | +3.491 |
font | +3.480 |
Neg logit contributions | |
Debor | -4.959 |
� | -4.474 |
ト | -4.218 |
MSM | -4.133 |
unsus | -4.115 |
Token | ain |
Token ID | 391 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
grain | +2.958 |
ellar | +2.546 |
urdue | +2.471 |
font | +2.436 |
Windsor | +2.301 |
Neg logit contributions | |
Debor | -8.816 |
� | -8.384 |
ト | -7.976 |
unsus | -7.936 |
� | -7.922 |
Token | comes |
Token ID | 2058 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
grain | +2.355 |
urdue | +2.251 |
ellar | +2.217 |
Windsor | +2.172 |
font | +2.161 |
Neg logit contributions | |
Debor | -2.951 |
� | -2.626 |
MSM | -2.475 |
ト | -2.472 |
unsus | -2.422 |
Token | down |
Token ID | 866 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
grain | +1.174 |
urdue | +1.118 |
ellar | +1.110 |
Windsor | +1.096 |
font | +1.080 |
Neg logit contributions | |
Debor | -1.573 |
� | -1.406 |
ト | -1.330 |
MSM | -1.325 |
� | -1.298 |
Token | pretty |
Token ID | 2495 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Debor | +0.725 |
� | +0.638 |
ト | +0.600 |
MSM | +0.596 |
unsus | +0.582 |
Neg logit contributions | |
grain | -0.704 |
urdue | -0.675 |
ellar | -0.674 |
Windsor | -0.661 |
font | -0.651 |
Token | hard |
Token ID | 1327 |
Feature activation | +4.48e-04 |
Pos logit contributions | |
Debor | +2.321 |
� | +2.058 |
ト | +1.952 |
MSM | +1.936 |
unsus | +1.898 |
Neg logit contributions | |
grain | -2.085 |
urdue | -2.006 |
ellar | -1.990 |
Windsor | -1.929 |
afety | -1.918 |
Token | � |
Token ID | 250 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
grain | +1.612 |
urdue | +1.544 |
ellar | +1.537 |
Windsor | +1.520 |
font | +1.498 |
Neg logit contributions | |
Debor | -1.508 |
� | -1.319 |
ト | -1.224 |
MSM | -1.224 |
unsus | -1.206 |
Token | We |
Token ID | 1135 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
grain | +1.409 |
ellar | +1.338 |
urdue | +1.337 |
Windsor | +1.317 |
font | +1.302 |
Neg logit contributions | |
Debor | -1.788 |
� | -1.586 |
MSM | -1.496 |
ト | -1.495 |
unsus | -1.488 |
Token | � |
Token ID | 447 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
grain | +1.348 |
ellar | +1.287 |
urdue | +1.286 |
Windsor | +1.260 |
font | +1.239 |
Neg logit contributions | |
Debor | -1.637 |
� | -1.462 |
ト | -1.374 |
MSM | -1.368 |
� | -1.340 |
Token | � |
Token ID | 247 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
grain | +0.335 |
urdue | +0.322 |
ellar | +0.321 |
Windsor | +0.315 |
font | +0.311 |
Neg logit contributions | |
Debor | -0.314 |
� | -0.274 |
ト | -0.257 |
MSM | -0.255 |
unsus | -0.249 |
Token | ve |
Token ID | 303 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
grain | +0.505 |
urdue | +0.482 |
ellar | +0.480 |
Windsor | +0.470 |
font | +0.464 |
Neg logit contributions | |
Debor | -0.616 |
� | -0.549 |
ト | -0.517 |
MSM | -0.514 |
unsus | -0.504 |
Token | seen |
Token ID | 1775 |
Feature activation | -7.88e+00 |
Pos logit contributions | |
Debor | +0.146 |
� | +0.129 |
ト | +0.122 |
MSM | +0.121 |
unsus | +0.118 |
Neg logit contributions | |
grain | -0.128 |
urdue | -0.123 |
ellar | -0.122 |
Windsor | -0.120 |
font | -0.118 |
Token | it |
Token ID | 340 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
grain | +4.959 |
Windsor | +4.772 |
ellar | +4.765 |
urdue | +4.679 |
font | +4.628 |
Neg logit contributions | |
Debor | -6.350 |
� | -5.742 |
ト | -5.379 |
� | -5.324 |
MSM | -5.254 |
Token | with |
Token ID | 351 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
grain | +0.749 |
urdue | +0.717 |
ellar | +0.713 |
Windsor | +0.701 |
font | +0.690 |
Neg logit contributions | |
Debor | -0.933 |
� | -0.831 |
ト | -0.784 |
MSM | -0.782 |
unsus | -0.764 |
Token | [ |
Token ID | 685 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
grain | +0.954 |
urdue | +0.914 |
ellar | +0.910 |
Windsor | +0.897 |
font | +0.882 |
Neg logit contributions | |
Debor | -1.025 |
� | -0.905 |
ト | -0.850 |
MSM | -0.844 |
unsus | -0.828 |
Token | alcohol |
Token ID | 42142 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Debor | +0.096 |
� | +0.084 |
ト | +0.079 |
MSM | +0.079 |
unsus | +0.077 |
Neg logit contributions | |
grain | -0.094 |
urdue | -0.090 |
ellar | -0.089 |
Windsor | -0.088 |
font | -0.087 |
Token | ] |
Token ID | 60 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
grain | +0.304 |
urdue | +0.292 |
ellar | +0.289 |
Windsor | +0.285 |
font | +0.280 |
Neg logit contributions | |
Debor | -0.319 |
� | -0.281 |
ト | -0.264 |
MSM | -0.262 |
unsus | -0.257 |
Token | so |
Token ID | 523 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
Debor | +1.198 |
� | +1.065 |
ト | +1.002 |
MSM | +1.001 |
unsus | +0.984 |
Neg logit contributions | |
grain | -1.039 |
urdue | -0.995 |
ellar | -0.994 |
Windsor | -0.967 |
afety | -0.949 |
Token | I |
Token ID | 314 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
grain | +0.402 |
urdue | +0.384 |
ellar | +0.383 |
Windsor | +0.376 |
font | +0.371 |
Neg logit contributions | |
Debor | -0.471 |
� | -0.418 |
ト | -0.394 |
MSM | -0.391 |
unsus | -0.383 |
Token | added |
Token ID | 2087 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Debor | +0.731 |
� | +0.649 |
ト | +0.614 |
MSM | +0.611 |
unsus | +0.601 |
Neg logit contributions | |
grain | -0.623 |
urdue | -0.599 |
ellar | -0.596 |
Windsor | -0.582 |
afety | -0.572 |
Token | a |
Token ID | 257 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Debor | +0.365 |
� | +0.322 |
ト | +0.303 |
MSM | +0.301 |
unsus | +0.295 |
Neg logit contributions | |
grain | -0.332 |
urdue | -0.318 |
ellar | -0.317 |
Windsor | -0.311 |
font | -0.306 |
Token | < |
Token ID | 1279 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
grain | +0.237 |
urdue | +0.227 |
ellar | +0.226 |
Windsor | +0.222 |
font | +0.218 |
Neg logit contributions | |
Debor | -0.266 |
� | -0.235 |
ト | -0.222 |
MSM | -0.220 |
unsus | -0.215 |
Token | span |
Token ID | 12626 |
Feature activation | -7.87e+00 |
Pos logit contributions | |
Debor | +0.090 |
� | +0.080 |
ト | +0.076 |
MSM | +0.075 |
unsus | +0.074 |
Neg logit contributions | |
grain | -0.072 |
urdue | -0.069 |
ellar | -0.068 |
Windsor | -0.067 |
font | -0.066 |
Token | > |
Token ID | 29 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
grain | +3.616 |
font | +3.463 |
Windsor | +3.396 |
urdue | +3.387 |
ellar | +3.336 |
Neg logit contributions | |
Debor | -7.892 |
� | -7.137 |
ト | -6.846 |
MSM | -6.741 |
機 | -6.689 |
Token | around |
Token ID | 1088 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
grain | +1.214 |
urdue | +1.160 |
ellar | +1.157 |
Windsor | +1.142 |
font | +1.139 |
Neg logit contributions | |
Debor | -1.063 |
� | -0.919 |
ト | -0.861 |
MSM | -0.855 |
unsus | -0.832 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Debor | +0.120 |
� | +0.106 |
ト | +0.100 |
MSM | +0.100 |
unsus | +0.097 |
Neg logit contributions | |
grain | -0.107 |
urdue | -0.103 |
ellar | -0.102 |
Windsor | -0.100 |
font | -0.099 |
Token | phone |
Token ID | 3072 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Debor | +1.156 |
� | +1.026 |
MSM | +0.973 |
ト | +0.972 |
unsus | +0.952 |
Neg logit contributions | |
grain | -0.921 |
urdue | -0.880 |
ellar | -0.877 |
Windsor | -0.851 |
afety | -0.837 |
Token | name |
Token ID | 1438 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
Debor | +1.165 |
� | +1.020 |
ト | +0.954 |
MSM | +0.946 |
unsus | +0.926 |
Neg logit contributions | |
grain | -1.244 |
urdue | -1.197 |
ellar | -1.193 |
Windsor | -1.168 |
font | -1.148 |
Token | in |
Token ID | 287 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
grain | +0.569 |
urdue | +0.545 |
ellar | +0.544 |
Windsor | +0.534 |
font | +0.527 |
Neg logit contributions | |
Debor | -0.562 |
� | -0.493 |
ト | -0.463 |
MSM | -0.459 |
unsus | -0.448 |
Token | a |
Token ID | 257 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
grain | +0.680 |
urdue | +0.645 |
ellar | +0.644 |
Windsor | +0.636 |
font | +0.623 |
Neg logit contributions | |
Debor | -0.787 |
� | -0.702 |
ト | -0.661 |
MSM | -0.649 |
� | -0.644 |
Token | table |
Token ID | 3084 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
grain | +1.527 |
urdue | +1.457 |
ellar | +1.452 |
Windsor | +1.444 |
font | +1.411 |
Neg logit contributions | |
Debor | -1.410 |
� | -1.238 |
ト | -1.154 |
MSM | -1.130 |
� | -1.125 |
Token | or |
Token ID | 393 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
grain | +0.343 |
urdue | +0.329 |
ellar | +0.328 |
Windsor | +0.322 |
font | +0.317 |
Neg logit contributions | |
Debor | -0.351 |
� | -0.309 |
ト | -0.290 |
MSM | -0.288 |
unsus | -0.282 |
Token | chart |
Token ID | 8262 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
grain | +0.938 |
ellar | +0.894 |
urdue | +0.893 |
Windsor | +0.886 |
font | +0.867 |
Neg logit contributions | |
Debor | -0.930 |
� | -0.820 |
ト | -0.763 |
MSM | -0.747 |
� | -0.747 |
Token | format |
Token ID | 5794 |
Feature activation | -7.86e+00 |
Pos logit contributions | |
grain | +1.201 |
urdue | +1.147 |
ellar | +1.144 |
Windsor | +1.122 |
font | +1.109 |
Neg logit contributions | |
Debor | -1.238 |
� | -1.087 |
ト | -1.022 |
MSM | -1.015 |
� | -0.993 |
Token | ). |
Token ID | 737 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
grain | +5.241 |
urdue | +4.946 |
ellar | +4.932 |
Windsor | +4.866 |
font | +4.837 |
Neg logit contributions | |
Debor | -6.248 |
� | -5.600 |
� | -5.278 |
ト | -5.234 |
機 | -5.108 |
Token | It |
Token ID | 632 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
Debor | +0.867 |
� | +0.759 |
ト | +0.716 |
MSM | +0.715 |
unsus | +0.690 |
Neg logit contributions | |
grain | -0.835 |
urdue | -0.800 |
ellar | -0.799 |
Windsor | -0.779 |
font | -0.770 |
Token | may |
Token ID | 743 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Debor | +0.016 |
� | +0.014 |
ト | +0.014 |
MSM | +0.013 |
unsus | +0.013 |
Neg logit contributions | |
grain | -0.014 |
urdue | -0.013 |
ellar | -0.013 |
Windsor | -0.013 |
font | -0.013 |
Token | also |
Token ID | 635 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Debor | +0.226 |
� | +0.200 |
ト | +0.189 |
MSM | +0.188 |
unsus | +0.184 |
Neg logit contributions | |
grain | -0.193 |
urdue | -0.184 |
ellar | -0.184 |
Windsor | -0.180 |
font | -0.177 |
Token | have |
Token ID | 423 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Debor | +0.851 |
� | +0.754 |
ト | +0.714 |
MSM | +0.707 |
unsus | +0.696 |
Neg logit contributions | |
grain | -0.752 |
urdue | -0.721 |
ellar | -0.717 |
Windsor | -0.704 |
font | -0.694 |
Token | > |
Token ID | 29 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
grain | +2.043 |
urdue | +1.930 |
ellar | +1.909 |
Windsor | +1.877 |
font | +1.835 |
Neg logit contributions | |
Debor | -4.547 |
� | -4.114 |
ト | -3.959 |
MSM | -3.927 |
� | -3.871 |
Token | |
Token ID | 7359 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
grain | +0.676 |
urdue | +0.624 |
ellar | +0.623 |
Windsor | +0.601 |
font | +0.586 |
Neg logit contributions | |
Debor | -2.018 |
� | -1.855 |
ト | -1.784 |
MSM | -1.769 |
unsus | -1.751 |
Token | li |
Token ID | 4528 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
grain | +2.269 |
font | +2.067 |
urdue | +2.020 |
ellar | +2.014 |
Windsor | +1.933 |
Neg logit contributions | |
Debor | -5.668 |
� | -5.107 |
� | -4.929 |
ト | -4.923 |
MSM | -4.915 |
Token | > |
Token ID | 29 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
grain | +2.667 |
urdue | +2.480 |
Windsor | +2.469 |
ellar | +2.456 |
font | +2.411 |
Neg logit contributions | |
Debor | -6.213 |
� | -5.571 |
ト | -5.380 |
MSM | -5.371 |
melanch | -5.275 |
Token | |
Token ID | 7359 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
grain | +0.112 |
urdue | +0.104 |
ellar | +0.103 |
Windsor | +0.099 |
font | +0.097 |
Neg logit contributions | |
Debor | -0.307 |
� | -0.282 |
ト | -0.271 |
MSM | -0.269 |
unsus | -0.265 |
Token | ul |
Token ID | 377 |
Feature activation | -7.85e+00 |
Pos logit contributions | |
grain | +1.527 |
urdue | +1.423 |
ellar | +1.419 |
font | +1.392 |
Windsor | +1.376 |
Neg logit contributions | |
Debor | -2.661 |
� | -2.380 |
ト | -2.287 |
MSM | -2.272 |
� | -2.269 |
Token | > |
Token ID | 29 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
grain | +3.112 |
urdue | +2.865 |
font | +2.862 |
Windsor | +2.840 |
ellar | +2.818 |
Neg logit contributions | |
Debor | -8.534 |
� | -7.623 |
ト | -7.398 |
MSM | -7.397 |
unden | -7.332 |
Token | |
Token ID | 7359 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Debor | +0.767 |
� | +0.699 |
ト | +0.670 |
MSM | +0.667 |
unsus | +0.656 |
Neg logit contributions | |
grain | -0.339 |
urdue | -0.317 |
ellar | -0.315 |
Windsor | -0.305 |
font | -0.297 |
Token | body |
Token ID | 2618 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
grain | +0.862 |
ellar | +0.784 |
urdue | +0.780 |
font | +0.769 |
Windsor | +0.760 |
Neg logit contributions | |
Debor | -2.071 |
� | -1.868 |
ト | -1.798 |
MSM | -1.795 |
unsus | -1.783 |
Token | > |
Token ID | 29 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
grain | +1.173 |
urdue | +1.102 |
ellar | +1.098 |
Windsor | +1.069 |
font | +1.049 |
Neg logit contributions | |
Debor | -2.241 |
� | -2.029 |
ト | -1.939 |
MSM | -1.931 |
unsus | -1.899 |
Token |
|
Token ID | 198 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
grain | +0.355 |
urdue | +0.334 |
ellar | +0.333 |
Windsor | +0.323 |
font | +0.317 |
Neg logit contributions | |
Debor | -0.707 |
� | -0.642 |
ト | -0.614 |
MSM | -0.610 |
unsus | -0.602 |
Token | putting |
Token ID | 5137 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
grain | +0.684 |
urdue | +0.657 |
ellar | +0.656 |
Windsor | +0.645 |
font | +0.635 |
Neg logit contributions | |
Debor | -0.668 |
� | -0.585 |
ト | -0.549 |
MSM | -0.545 |
unsus | -0.532 |
Token | together |
Token ID | 1978 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Debor | +1.726 |
� | +1.509 |
ト | +1.425 |
MSM | +1.420 |
unsus | +1.388 |
Neg logit contributions | |
grain | -1.709 |
urdue | -1.647 |
ellar | -1.634 |
Windsor | -1.590 |
font | -1.577 |
Token | an |
Token ID | 281 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
grain | +1.201 |
ellar | +1.145 |
urdue | +1.142 |
Windsor | +1.127 |
font | +1.109 |
Neg logit contributions | |
Debor | -1.411 |
� | -1.255 |
ト | -1.186 |
MSM | -1.170 |
� | -1.153 |
Token | event |
Token ID | 1785 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
grain | +0.780 |
ellar | +0.749 |
urdue | +0.743 |
Windsor | +0.735 |
font | +0.721 |
Neg logit contributions | |
Debor | -0.967 |
� | -0.864 |
ト | -0.814 |
MSM | -0.800 |
� | -0.795 |
Token | like |
Token ID | 588 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
grain | +2.131 |
ellar | +2.057 |
urdue | +2.040 |
Windsor | +1.994 |
font | +1.977 |
Neg logit contributions | |
Debor | -2.612 |
� | -2.323 |
ト | -2.190 |
MSM | -2.169 |
� | -2.139 |
Token | Horror |
Token ID | 22732 |
Feature activation | -7.83e+00 |
Pos logit contributions | |
grain | +0.515 |
urdue | +0.493 |
ellar | +0.492 |
Windsor | +0.482 |
font | +0.475 |
Neg logit contributions | |
Debor | -0.556 |
� | -0.491 |
ト | -0.462 |
MSM | -0.459 |
unsus | -0.449 |
Token | Nights |
Token ID | 27760 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
grain | +4.407 |
Windsor | +4.245 |
ellar | +4.222 |
urdue | +4.199 |
Craft | +4.195 |
Neg logit contributions | |
Debor | -6.884 |
� | -6.183 |
� | -5.896 |
MSM | -5.788 |
ト | -5.757 |
Token | ... |
Token ID | 986 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Debor | +0.067 |
� | +0.059 |
ト | +0.055 |
MSM | +0.055 |
unsus | +0.054 |
Neg logit contributions | |
grain | -0.065 |
urdue | -0.063 |
ellar | -0.063 |
Windsor | -0.061 |
font | -0.060 |
Token | tanks |
Token ID | 11657 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
grain | +0.193 |
urdue | +0.185 |
ellar | +0.184 |
Windsor | +0.181 |
font | +0.179 |
Neg logit contributions | |
Debor | -0.210 |
� | -0.185 |
ト | -0.175 |
MSM | -0.173 |
unsus | -0.170 |
Token | included |
Token ID | 3017 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Debor | +1.878 |
� | +1.658 |
ト | +1.557 |
MSM | +1.550 |
unsus | +1.530 |
Neg logit contributions | |
grain | -1.715 |
urdue | -1.629 |
ellar | -1.623 |
Windsor | -1.592 |
font | -1.565 |
Token | . |
Token ID | 13 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
Debor | +0.793 |
� | +0.696 |
ト | +0.653 |
MSM | +0.649 |
unsus | +0.634 |
Neg logit contributions | |
grain | -0.791 |
urdue | -0.758 |
ellar | -0.756 |
Windsor | -0.741 |
font | -0.730 |
Token | ua |
Token ID | 6413 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Debor | +1.923 |
� | +1.729 |
ト | +1.657 |
MSM | +1.640 |
unsus | +1.607 |
Neg logit contributions | |
grain | -1.182 |
ellar | -1.117 |
urdue | -1.115 |
Windsor | -1.081 |
font | -1.058 |
Token | , |
Token ID | 11 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
Debor | +0.809 |
� | +0.711 |
ト | +0.668 |
MSM | +0.665 |
unsus | +0.649 |
Neg logit contributions | |
grain | -0.780 |
urdue | -0.747 |
ellar | -0.746 |
Windsor | -0.729 |
font | -0.720 |
Token | New |
Token ID | 968 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
grain | +2.087 |
Windsor | +2.021 |
urdue | +2.006 |
ellar | +1.961 |
font | +1.935 |
Neg logit contributions | |
Debor | -2.081 |
� | -1.844 |
ト | -1.732 |
機 | -1.714 |
� | -1.712 |
Token | Hampshire |
Token ID | 13910 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
grain | +0.695 |
urdue | +0.662 |
ellar | +0.659 |
Windsor | +0.647 |
font | +0.636 |
Neg logit contributions | |
Debor | -0.918 |
� | -0.820 |
ト | -0.776 |
MSM | -0.771 |
unsus | -0.758 |
Token | . |
Token ID | 13 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
Debor | +0.521 |
� | +0.457 |
ト | +0.429 |
MSM | +0.426 |
unsus | +0.416 |
Neg logit contributions | |
grain | -0.529 |
urdue | -0.507 |
ellar | -0.506 |
Windsor | -0.496 |
font | -0.490 |
Token | Hide |
Token ID | 10415 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
grain | +1.773 |
urdue | +1.684 |
ellar | +1.663 |
Windsor | +1.653 |
font | +1.612 |
Neg logit contributions | |
Debor | -3.344 |
� | -3.054 |
ト | -2.915 |
unsus | -2.883 |
MSM | -2.880 |
Token | Caption |
Token ID | 11260 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
grain | +3.932 |
Windsor | +3.683 |
urdue | +3.670 |
ellar | +3.624 |
font | +3.619 |
Neg logit contributions | |
Debor | -7.584 |
� | -6.959 |
unden | -6.665 |
unsus | -6.651 |
vertisement | -6.575 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
Debor | +0.288 |
� | +0.253 |
MSM | +0.249 |
ト | +0.248 |
機 | +0.238 |
Neg logit contributions | |
grain | -0.191 |
urdue | -0.185 |
ellar | -0.185 |
afety | -0.174 |
Windsor | -0.174 |
Token | of |
Token ID | 286 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
grain | +2.137 |
ellar | +2.031 |
urdue | +2.030 |
Windsor | +1.993 |
font | +1.978 |
Neg logit contributions | |
Debor | -2.420 |
� | -2.139 |
ト | -2.007 |
MSM | -1.998 |
unsus | -1.975 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
grain | +0.287 |
urdue | +0.273 |
ellar | +0.270 |
Windsor | +0.259 |
afety | +0.257 |
Neg logit contributions | |
Debor | -0.498 |
� | -0.449 |
ト | -0.431 |
MSM | -0.430 |
� | -0.419 |
Token | Photos |
Token ID | 9434 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
grain | +0.132 |
urdue | +0.126 |
ellar | +0.125 |
Windsor | +0.120 |
afety | +0.119 |
Neg logit contributions | |
Debor | -0.236 |
� | -0.214 |
ト | -0.204 |
MSM | -0.203 |
� | -0.198 |
Token | his |
Token ID | 465 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Debor | +0.189 |
� | +0.166 |
ト | +0.157 |
MSM | +0.156 |
unsus | +0.152 |
Neg logit contributions | |
grain | -0.183 |
urdue | -0.176 |
ellar | -0.175 |
Windsor | -0.173 |
font | -0.170 |
Token | initial |
Token ID | 4238 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
grain | +1.078 |
urdue | +1.022 |
ellar | +1.020 |
Windsor | +1.011 |
font | +1.000 |
Neg logit contributions | |
Debor | -1.291 |
� | -1.139 |
ト | -1.085 |
MSM | -1.078 |
unsus | -1.050 |
Token | pick |
Token ID | 2298 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
grain | +0.929 |
urdue | +0.889 |
ellar | +0.885 |
Windsor | +0.879 |
font | +0.868 |
Neg logit contributions | |
Debor | -0.891 |
� | -0.775 |
ト | -0.730 |
MSM | -0.724 |
unsus | -0.706 |
Token | from |
Token ID | 422 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Debor | +1.726 |
� | +1.528 |
ト | +1.430 |
MSM | +1.421 |
unsus | +1.390 |
Neg logit contributions | |
grain | -1.647 |
urdue | -1.584 |
ellar | -1.578 |
Windsor | -1.543 |
font | -1.510 |
Token | Lone |
Token ID | 23405 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
grain | +1.039 |
urdue | +0.991 |
ellar | +0.987 |
Windsor | +0.984 |
font | +0.961 |
Neg logit contributions | |
Debor | -1.155 |
� | -1.024 |
ト | -0.961 |
MSM | -0.953 |
unsus | -0.939 |
Token | Druid |
Token ID | 32685 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
grain | +0.994 |
ellar | +0.933 |
urdue | +0.930 |
Windsor | +0.916 |
font | +0.907 |
Neg logit contributions | |
Debor | -1.525 |
� | -1.373 |
ト | -1.308 |
MSM | -1.294 |
� | -1.281 |
Token | to |
Token ID | 284 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
Debor | +3.301 |
� | +2.910 |
ト | +2.727 |
MSM | +2.694 |
melanch | +2.617 |
Neg logit contributions | |
grain | -3.682 |
urdue | -3.570 |
ellar | -3.561 |
Windsor | -3.452 |
afety | -3.396 |
Token | Templar |
Token ID | 41741 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
grain | +0.024 |
urdue | +0.023 |
ellar | +0.023 |
Windsor | +0.023 |
font | +0.022 |
Neg logit contributions | |
Debor | -0.028 |
� | -0.024 |
ト | -0.023 |
MSM | -0.023 |
unsus | -0.022 |
Token | Assassin |
Token ID | 21401 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
Debor | +1.122 |
� | +0.994 |
MSM | +0.940 |
ト | +0.938 |
unsus | +0.919 |
Neg logit contributions | |
grain | -0.929 |
urdue | -0.890 |
ellar | -0.889 |
Windsor | -0.863 |
font | -0.852 |
Token | . |
Token ID | 13 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
Debor | +2.309 |
� | +2.038 |
ト | +1.912 |
MSM | +1.896 |
unsus | +1.856 |
Neg logit contributions | |
grain | -2.279 |
ellar | -2.186 |
urdue | -2.185 |
Windsor | -2.131 |
font | -2.097 |
Token | He |
Token ID | 679 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
grain | +0.315 |
urdue | +0.301 |
ellar | +0.300 |
Windsor | +0.295 |
font | +0.290 |
Neg logit contributions | |
Debor | -0.377 |
� | -0.335 |
ト | -0.317 |
MSM | -0.314 |
unsus | -0.309 |
Token | capital |
Token ID | 3139 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
grain | +0.082 |
urdue | +0.078 |
ellar | +0.078 |
Windsor | +0.076 |
font | +0.075 |
Neg logit contributions | |
Debor | -0.089 |
� | -0.079 |
ト | -0.074 |
MSM | -0.074 |
unsus | -0.072 |
Token | is |
Token ID | 318 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
Debor | +0.015 |
� | +0.013 |
ト | +0.012 |
MSM | +0.012 |
unsus | +0.012 |
Neg logit contributions | |
grain | -0.012 |
urdue | -0.011 |
ellar | -0.011 |
Windsor | -0.011 |
font | -0.011 |
Token | rep |
Token ID | 1128 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
Debor | +2.655 |
� | +2.333 |
MSM | +2.199 |
ト | +2.193 |
unsus | +2.161 |
Neg logit contributions | |
grain | -2.504 |
urdue | -2.389 |
ellar | -2.383 |
afety | -2.295 |
font | -2.287 |
Token | lete |
Token ID | 5807 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Debor | +2.138 |
� | +1.843 |
ト | +1.720 |
MSM | +1.700 |
unsus | +1.664 |
Neg logit contributions | |
grain | -2.547 |
urdue | -2.450 |
ellar | -2.447 |
Windsor | -2.425 |
afety | -2.370 |
Token | with |
Token ID | 351 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
Debor | +1.285 |
� | +1.100 |
ト | +1.021 |
MSM | +1.013 |
unsus | +0.986 |
Neg logit contributions | |
grain | -1.706 |
urdue | -1.645 |
ellar | -1.644 |
Windsor | -1.617 |
font | -1.595 |
Token | memorial |
Token ID | 17357 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
Debor | +0.184 |
� | +0.159 |
ト | +0.149 |
MSM | +0.147 |
unsus | +0.143 |
Neg logit contributions | |
grain | -0.217 |
urdue | -0.209 |
ellar | -0.208 |
Windsor | -0.205 |
font | -0.202 |
Token | s |
Token ID | 82 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
Debor | +3.827 |
� | +3.429 |
ト | +3.200 |
MSM | +3.148 |
melanch | +3.073 |
Neg logit contributions | |
grain | -3.986 |
urdue | -3.866 |
ellar | -3.850 |
Windsor | -3.722 |
afety | -3.713 |
Token | to |
Token ID | 284 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
Debor | +0.731 |
� | +0.646 |
ト | +0.608 |
MSM | +0.605 |
unsus | +0.592 |
Neg logit contributions | |
grain | -0.660 |
urdue | -0.632 |
ellar | -0.630 |
Windsor | -0.617 |
font | -0.608 |
Token | presidents |
Token ID | 19033 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
grain | +0.362 |
urdue | +0.346 |
ellar | +0.345 |
Windsor | +0.339 |
font | +0.333 |
Neg logit contributions | |
Debor | -0.433 |
� | -0.385 |
ト | -0.363 |
MSM | -0.360 |
unsus | -0.352 |
Token | and |
Token ID | 290 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Debor | +0.655 |
� | +0.579 |
ト | +0.546 |
MSM | +0.543 |
unsus | +0.531 |
Neg logit contributions | |
grain | -0.584 |
urdue | -0.559 |
ellar | -0.557 |
Windsor | -0.546 |
font | -0.538 |
Token | veterans |
Token ID | 11255 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
grain | +0.903 |
urdue | +0.867 |
ellar | +0.861 |
Windsor | +0.857 |
font | +0.836 |
Neg logit contributions | |
Debor | -1.029 |
� | -0.916 |
ト | -0.865 |
MSM | -0.849 |
� | -0.836 |
Token | a |
Token ID | 257 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Debor | +2.236 |
� | +1.928 |
MSM | +1.876 |
ト | +1.832 |
unsus | +1.813 |
Neg logit contributions | |
grain | -1.979 |
urdue | -1.907 |
ellar | -1.897 |
Windsor | -1.821 |
font | -1.821 |
Token | program |
Token ID | 1430 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Debor | +1.883 |
� | +1.641 |
MSM | +1.576 |
ト | +1.562 |
melanch | +1.526 |
Neg logit contributions | |
grain | -1.765 |
urdue | -1.705 |
ellar | -1.702 |
font | -1.636 |
afety | -1.636 |
Token | he |
Token ID | 339 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Debor | +1.790 |
� | +1.567 |
MSM | +1.481 |
ト | +1.476 |
unsus | +1.447 |
Neg logit contributions | |
grain | -1.662 |
urdue | -1.601 |
ellar | -1.586 |
Windsor | -1.547 |
font | -1.531 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Debor | +1.004 |
� | +0.889 |
ト | +0.841 |
MSM | +0.836 |
unsus | +0.823 |
Neg logit contributions | |
grain | -0.879 |
ellar | -0.841 |
urdue | -0.835 |
Windsor | -0.820 |
font | -0.805 |
Token | was |
Token ID | 373 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
grain | +0.764 |
urdue | +0.729 |
Windsor | +0.720 |
ellar | +0.720 |
font | +0.705 |
Neg logit contributions | |
Debor | -0.877 |
� | -0.778 |
ト | -0.732 |
MSM | -0.719 |
� | -0.711 |
Token | rational |
Token ID | 9377 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
Debor | +2.300 |
� | +2.014 |
MSM | +1.934 |
unsus | +1.910 |
ト | +1.905 |
Neg logit contributions | |
grain | -2.010 |
ellar | -1.932 |
urdue | -1.932 |
afety | -1.853 |
Windsor | -1.848 |
Token | over |
Token ID | 625 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
Debor | +3.478 |
� | +3.040 |
MSM | +2.885 |
ト | +2.837 |
unsus | +2.765 |
Neg logit contributions | |
grain | -3.587 |
urdue | -3.432 |
ellar | -3.419 |
Windsor | -3.373 |
font | -3.315 |
Token | the |
Token ID | 262 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
grain | +0.014 |
urdue | +0.013 |
ellar | +0.013 |
Windsor | +0.013 |
font | +0.013 |
Neg logit contributions | |
Debor | -0.017 |
� | -0.015 |
ト | -0.014 |
MSM | -0.014 |
unsus | -0.014 |
Token | objections |
Token ID | 21954 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
grain | +0.328 |
urdue | +0.315 |
ellar | +0.314 |
Windsor | +0.306 |
font | +0.303 |
Neg logit contributions | |
Debor | -0.346 |
� | -0.304 |
ト | -0.287 |
MSM | -0.286 |
unsus | -0.279 |
Token | of |
Token ID | 286 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
grain | +1.103 |
ellar | +1.057 |
urdue | +1.057 |
Windsor | +1.044 |
font | +1.014 |
Neg logit contributions | |
Debor | -1.287 |
� | -1.147 |
ト | -1.086 |
MSM | -1.063 |
unsus | -1.059 |
Token | the |
Token ID | 262 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Debor | +0.491 |
� | +0.431 |
ト | +0.405 |
MSM | +0.403 |
unsus | +0.393 |
Neg logit contributions | |
grain | -0.485 |
urdue | -0.465 |
ellar | -0.464 |
Windsor | -0.455 |
font | -0.449 |
Token | those |
Token ID | 883 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Debor | +1.881 |
� | +1.664 |
ト | +1.566 |
MSM | +1.559 |
unsus | +1.526 |
Neg logit contributions | |
grain | -1.695 |
urdue | -1.628 |
ellar | -1.612 |
Windsor | -1.577 |
font | -1.560 |
Token | of |
Token ID | 286 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Debor | +2.226 |
� | +1.948 |
ト | +1.841 |
MSM | +1.837 |
unsus | +1.809 |
Neg logit contributions | |
grain | -2.113 |
urdue | -2.033 |
ellar | -2.018 |
Windsor | -1.965 |
afety | -1.941 |
Token | ausp |
Token ID | 45062 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Debor | +1.211 |
� | +1.066 |
ト | +1.001 |
MSM | +1.000 |
unsus | +0.981 |
Neg logit contributions | |
grain | -1.099 |
urdue | -1.059 |
ellar | -1.052 |
Windsor | -1.021 |
font | -1.016 |
Token | icious |
Token ID | 6243 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
grain | +0.126 |
urdue | +0.122 |
ellar | +0.121 |
Windsor | +0.119 |
font | +0.117 |
Neg logit contributions | |
Debor | -0.130 |
� | -0.114 |
ト | -0.108 |
MSM | -0.107 |
unsus | -0.104 |
Token | or |
Token ID | 393 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Debor | +0.915 |
� | +0.811 |
ト | +0.766 |
MSM | +0.762 |
unsus | +0.746 |
Neg logit contributions | |
grain | -0.777 |
urdue | -0.743 |
ellar | -0.741 |
Windsor | -0.724 |
font | -0.714 |
Token | ( |
Token ID | 357 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
Debor | +1.200 |
� | +1.059 |
ト | +0.997 |
MSM | +0.993 |
unsus | +0.974 |
Neg logit contributions | |
grain | -1.122 |
urdue | -1.077 |
ellar | -1.072 |
Windsor | -1.047 |
font | -1.035 |
Token | for |
Token ID | 1640 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
Debor | +3.721 |
� | +3.372 |
ト | +3.209 |
MSM | +3.115 |
� | +3.076 |
Neg logit contributions | |
grain | -2.873 |
urdue | -2.843 |
ellar | -2.810 |
Windsor | -2.761 |
afety | -2.691 |
Token | boys |
Token ID | 6510 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
Debor | +3.030 |
� | +2.652 |
ト | +2.518 |
MSM | +2.508 |
unsus | +2.438 |
Neg logit contributions | |
grain | -2.860 |
urdue | -2.806 |
ellar | -2.787 |
Windsor | -2.687 |
font | -2.686 |
Token | ) |
Token ID | 8 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
Debor | +3.408 |
� | +3.004 |
ト | +2.848 |
MSM | +2.835 |
unsus | +2.810 |
Neg logit contributions | |
grain | -3.232 |
urdue | -3.085 |
ellar | -3.072 |
Windsor | -3.016 |
font | -2.968 |
Token | man |
Token ID | 582 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
Debor | +1.847 |
� | +1.632 |
ト | +1.531 |
MSM | +1.527 |
unsus | +1.496 |
Neg logit contributions | |
grain | -1.761 |
urdue | -1.703 |
ellar | -1.690 |
Windsor | -1.647 |
font | -1.625 |
Token | ly |
Token ID | 306 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Debor | +3.137 |
� | +2.775 |
ト | +2.632 |
MSM | +2.585 |
melanch | +2.538 |
Neg logit contributions | |
grain | -2.658 |
urdue | -2.565 |
ellar | -2.499 |
Windsor | -2.489 |
afety | -2.432 |
Token | / |
Token ID | 14 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Debor | +0.527 |
� | +0.466 |
MSM | +0.442 |
ト | +0.439 |
unsus | +0.431 |
Neg logit contributions | |
grain | -0.419 |
urdue | -0.401 |
ellar | -0.400 |
Windsor | -0.389 |
font | -0.384 |
Token | or |
Token ID | 273 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Debor | +1.799 |
� | +1.574 |
ト | +1.486 |
MSM | +1.451 |
unsus | +1.394 |
Neg logit contributions | |
grain | -2.145 |
urdue | -2.095 |
ellar | -2.072 |
Windsor | -2.056 |
afety | -2.016 |
Token | Survival |
Token ID | 20303 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
Debor | +0.958 |
� | +0.843 |
MSM | +0.807 |
ト | +0.794 |
unsus | +0.784 |
Neg logit contributions | |
grain | -0.749 |
urdue | -0.721 |
ellar | -0.717 |
Windsor | -0.694 |
font | -0.689 |
Token | + |
Token ID | 10 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
Debor | +2.421 |
� | +2.145 |
MSM | +2.031 |
ト | +2.023 |
unsus | +1.963 |
Neg logit contributions | |
grain | -2.062 |
ellar | -1.998 |
urdue | -1.996 |
Windsor | -1.932 |
font | -1.902 |
Token | The |
Token ID | 383 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
grain | +0.064 |
urdue | +0.061 |
ellar | +0.061 |
Windsor | +0.060 |
font | +0.059 |
Neg logit contributions | |
Debor | -0.067 |
� | -0.059 |
ト | -0.056 |
MSM | -0.055 |
unsus | -0.054 |
Token | Prim |
Token ID | 11460 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
Debor | +0.428 |
� | +0.378 |
MSM | +0.359 |
ト | +0.359 |
unsus | +0.350 |
Neg logit contributions | |
grain | -0.340 |
urdue | -0.327 |
ellar | -0.325 |
Windsor | -0.317 |
font | -0.312 |
Token | er |
Token ID | 263 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
Debor | +3.700 |
� | +3.091 |
MSM | +3.012 |
ト | +2.967 |
unsus | +2.910 |
Neg logit contributions | |
grain | -3.966 |
urdue | -3.864 |
ellar | -3.787 |
Windsor | -3.709 |
afety | -3.668 |
Token | from |
Token ID | 422 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
Debor | +0.748 |
� | +0.658 |
ト | +0.620 |
MSM | +0.620 |
unsus | +0.605 |
Neg logit contributions | |
grain | -0.679 |
urdue | -0.652 |
ellar | -0.651 |
Windsor | -0.635 |
font | -0.626 |
Token | your |
Token ID | 534 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Debor | +0.751 |
� | +0.656 |
MSM | +0.622 |
ト | +0.621 |
unsus | +0.604 |
Neg logit contributions | |
grain | -0.645 |
urdue | -0.620 |
ellar | -0.618 |
Windsor | -0.598 |
font | -0.592 |
Token | local |
Token ID | 1957 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
Debor | +1.061 |
� | +0.935 |
ト | +0.882 |
MSM | +0.878 |
unsus | +0.858 |
Neg logit contributions | |
grain | -0.966 |
urdue | -0.926 |
ellar | -0.923 |
Windsor | -0.903 |
font | -0.890 |
Token | book |
Token ID | 1492 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
Debor | +3.425 |
� | +3.006 |
MSM | +2.921 |
ト | +2.843 |
unsus | +2.808 |
Neg logit contributions | |
grain | -2.938 |
urdue | -2.874 |
ellar | -2.826 |
Windsor | -2.705 |
afety | -2.689 |
Token | be |
Token ID | 307 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
grain | +0.283 |
urdue | +0.270 |
ellar | +0.269 |
Windsor | +0.264 |
font | +0.260 |
Neg logit contributions | |
Debor | -0.338 |
� | -0.300 |
ト | -0.283 |
MSM | -0.281 |
unsus | -0.275 |
Token | confronted |
Token ID | 16675 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
grain | +0.703 |
urdue | +0.674 |
ellar | +0.669 |
Windsor | +0.660 |
font | +0.649 |
Neg logit contributions | |
Debor | -0.833 |
� | -0.744 |
ト | -0.704 |
MSM | -0.694 |
� | -0.684 |
Token | almost |
Token ID | 2048 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
grain | +0.107 |
urdue | +0.103 |
ellar | +0.103 |
Windsor | +0.101 |
font | +0.100 |
Neg logit contributions | |
Debor | -0.096 |
� | -0.084 |
ト | -0.079 |
MSM | -0.078 |
unsus | -0.076 |
Token | immediately |
Token ID | 3393 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
Debor | +0.305 |
� | +0.269 |
ト | +0.252 |
MSM | +0.250 |
� | +0.244 |
Neg logit contributions | |
grain | -0.293 |
urdue | -0.281 |
ellar | -0.280 |
Windsor | -0.275 |
font | -0.271 |
Token | by |
Token ID | 416 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
grain | +0.697 |
urdue | +0.672 |
ellar | +0.667 |
Windsor | +0.656 |
font | +0.650 |
Neg logit contributions | |
Debor | -0.699 |
� | -0.616 |
ト | -0.579 |
MSM | -0.574 |
機 | -0.560 |
Token | the |
Token ID | 262 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Debor | +0.696 |
� | +0.613 |
ト | +0.577 |
MSM | +0.575 |
unsus | +0.561 |
Neg logit contributions | |
grain | -0.653 |
urdue | -0.626 |
ellar | -0.624 |
Windsor | -0.611 |
font | -0.603 |
Token | staggering |
Token ID | 23508 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Debor | +0.208 |
� | +0.183 |
ト | +0.172 |
MSM | +0.171 |
unsus | +0.167 |
Neg logit contributions | |
grain | -0.202 |
urdue | -0.194 |
ellar | -0.193 |
Windsor | -0.189 |
font | -0.187 |
Token | dimensions |
Token ID | 15225 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Debor | +1.437 |
� | +1.259 |
MSM | +1.188 |
ト | +1.181 |
unsus | +1.154 |
Neg logit contributions | |
grain | -1.449 |
urdue | -1.391 |
ellar | -1.387 |
Windsor | -1.353 |
font | -1.336 |
Token | of |
Token ID | 286 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Debor | +0.927 |
� | +0.819 |
ト | +0.772 |
MSM | +0.766 |
unsus | +0.749 |
Neg logit contributions | |
grain | -0.858 |
urdue | -0.822 |
ellar | -0.819 |
Windsor | -0.804 |
font | -0.793 |
Token | my |
Token ID | 616 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
Debor | +1.488 |
� | +1.294 |
MSM | +1.225 |
ト | +1.216 |
unsus | +1.189 |
Neg logit contributions | |
grain | -1.525 |
ellar | -1.464 |
urdue | -1.463 |
Windsor | -1.422 |
font | -1.412 |
Token | own |
Token ID | 898 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
Debor | +0.612 |
� | +0.536 |
ト | +0.503 |
MSM | +0.500 |
unsus | +0.489 |
Neg logit contributions | |
grain | -0.636 |
urdue | -0.610 |
ellar | -0.609 |
Windsor | -0.597 |
font | -0.590 |
Token | Writ |
Token ID | 20257 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Debor | +0.327 |
� | +0.289 |
ト | +0.272 |
MSM | +0.270 |
unsus | +0.263 |
Neg logit contributions | |
grain | -0.305 |
urdue | -0.292 |
ellar | -0.291 |
Windsor | -0.285 |
font | -0.281 |
Token | ters |
Token ID | 1010 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
grain | +1.440 |
ellar | +1.377 |
urdue | +1.373 |
Windsor | +1.351 |
font | +1.332 |
Neg logit contributions | |
Debor | -1.511 |
� | -1.344 |
ト | -1.263 |
MSM | -1.242 |
unsus | -1.224 |
Token | Strike |
Token ID | 12282 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
Debor | +0.474 |
� | +0.419 |
ト | +0.397 |
MSM | +0.395 |
unsus | +0.386 |
Neg logit contributions | |
grain | -0.389 |
urdue | -0.373 |
ellar | -0.371 |
Windsor | -0.362 |
font | -0.357 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
grain | +1.540 |
urdue | +1.464 |
ellar | +1.462 |
Windsor | +1.440 |
font | +1.415 |
Neg logit contributions | |
Debor | -2.040 |
� | -1.831 |
ト | -1.733 |
MSM | -1.714 |
unsus | -1.689 |
Token | 01 |
Token ID | 486 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
grain | +1.006 |
urdue | +0.964 |
ellar | +0.962 |
Windsor | +0.945 |
font | +0.932 |
Neg logit contributions | |
Debor | -1.054 |
� | -0.929 |
ト | -0.872 |
MSM | -0.868 |
unsus | -0.850 |
Token | 04 |
Token ID | 3023 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
grain | +0.025 |
urdue | +0.023 |
ellar | +0.023 |
Windsor | +0.023 |
font | +0.022 |
Neg logit contributions | |
Debor | -0.036 |
� | -0.033 |
ト | -0.031 |
MSM | -0.031 |
unsus | -0.030 |
Token | O |
Token ID | 440 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Debor | +0.464 |
� | +0.418 |
MSM | +0.399 |
ト | +0.398 |
unsus | +0.388 |
Neg logit contributions | |
grain | -0.274 |
ellar | -0.258 |
urdue | -0.258 |
Windsor | -0.248 |
font | -0.245 |
Token | & |
Token ID | 5 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
grain | +1.589 |
urdue | +1.531 |
ellar | +1.531 |
Windsor | +1.504 |
font | +1.490 |
Neg logit contributions | |
Debor | -1.162 |
� | -0.988 |
ト | -0.914 |
MSM | -0.906 |
unsus | -0.888 |
Token | A |
Token ID | 32 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Debor | +0.344 |
� | +0.300 |
MSM | +0.275 |
ト | +0.274 |
機 | +0.264 |
Neg logit contributions | |
grain | -0.472 |
urdue | -0.460 |
ellar | -0.454 |
Windsor | -0.444 |
afety | -0.439 |
Token | - |
Token ID | 12 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
grain | +1.169 |
urdue | +1.118 |
ellar | +1.116 |
Windsor | +1.101 |
font | +1.076 |
Neg logit contributions | |
Debor | -1.691 |
� | -1.524 |
ト | -1.449 |
MSM | -1.430 |
unsus | -1.422 |
Token | WOR |
Token ID | 45359 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
Debor | +0.037 |
� | +0.033 |
ト | +0.031 |
MSM | +0.031 |
unsus | +0.030 |
Neg logit contributions | |
grain | -0.034 |
urdue | -0.033 |
ellar | -0.033 |
Windsor | -0.032 |
font | -0.032 |
Token | ? |
Token ID | 30 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
grain | +0.496 |
urdue | +0.475 |
ellar | +0.474 |
Windsor | +0.465 |
font | +0.457 |
Neg logit contributions | |
Debor | -0.582 |
� | -0.516 |
ト | -0.487 |
MSM | -0.484 |
unsus | -0.474 |
Token | She |
Token ID | 1375 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Debor | +0.395 |
� | +0.353 |
ト | +0.335 |
MSM | +0.334 |
unsus | +0.327 |
Neg logit contributions | |
grain | -0.273 |
urdue | -0.260 |
ellar | -0.260 |
Windsor | -0.252 |
font | -0.248 |
Token | said |
Token ID | 531 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
grain | +0.174 |
urdue | +0.166 |
ellar | +0.165 |
Windsor | +0.162 |
font | +0.159 |
Neg logit contributions | |
Debor | -0.245 |
� | -0.219 |
ト | -0.208 |
MSM | -0.207 |
unsus | -0.203 |
Token | : |
Token ID | 25 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
grain | +0.265 |
urdue | +0.254 |
ellar | +0.253 |
Windsor | +0.249 |
font | +0.245 |
Neg logit contributions | |
Debor | -0.273 |
� | -0.240 |
ト | -0.226 |
MSM | -0.224 |
unsus | -0.219 |
Token | I |
Token ID | 314 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Debor | +1.013 |
� | +0.886 |
MSM | +0.847 |
ト | +0.842 |
unsus | +0.817 |
Neg logit contributions | |
grain | -0.843 |
urdue | -0.813 |
ellar | -0.810 |
Windsor | -0.776 |
font | -0.775 |
Token | I |
Token ID | 314 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
grain | +0.215 |
urdue | +0.205 |
ellar | +0.205 |
Windsor | +0.201 |
font | +0.198 |
Neg logit contributions | |
Debor | -0.252 |
� | -0.224 |
ト | -0.211 |
MSM | -0.210 |
unsus | -0.206 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Debor | +0.102 |
� | +0.090 |
ト | +0.085 |
MSM | +0.085 |
unsus | +0.083 |
Neg logit contributions | |
grain | -0.083 |
urdue | -0.079 |
ellar | -0.079 |
Windsor | -0.077 |
font | -0.076 |
Token | : |
Token ID | 25 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
grain | +1.229 |
urdue | +1.171 |
ellar | +1.167 |
Windsor | +1.145 |
font | +1.124 |
Neg logit contributions | |
Debor | -1.624 |
� | -1.452 |
ト | -1.378 |
MSM | -1.365 |
unsus | -1.339 |
Token | What |
Token ID | 1867 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Debor | +0.805 |
� | +0.708 |
MSM | +0.677 |
ト | +0.669 |
unsus | +0.658 |
Neg logit contributions | |
grain | -0.646 |
urdue | -0.623 |
ellar | -0.623 |
Windsor | -0.596 |
font | -0.592 |
Token | is |
Token ID | 318 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
grain | +0.946 |
urdue | +0.900 |
ellar | +0.897 |
Windsor | +0.880 |
font | +0.866 |
Neg logit contributions | |
Debor | -1.217 |
� | -1.085 |
ト | -1.028 |
MSM | -1.021 |
unsus | -1.001 |
Token | the |
Token ID | 262 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
grain | +1.518 |
urdue | +1.444 |
ellar | +1.438 |
Windsor | +1.426 |
font | +1.395 |
Neg logit contributions | |
Debor | -1.896 |
� | -1.696 |
ト | -1.601 |
MSM | -1.582 |
機 | -1.563 |
Token | SOLD |
Token ID | 48671 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
Debor | +0.995 |
� | +0.867 |
ト | +0.810 |
MSM | +0.807 |
unsus | +0.785 |
Neg logit contributions | |
grain | -1.098 |
urdue | -1.055 |
ellar | -1.052 |
Windsor | -1.032 |
font | -1.019 |
Token | IER |
Token ID | 38311 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
grain | +0.394 |
urdue | +0.381 |
ellar | +0.378 |
Windsor | +0.374 |
font | +0.368 |
Neg logit contributions | |
Debor | -0.408 |
� | -0.356 |
ト | -0.337 |
MSM | -0.331 |
unsus | -0.329 |
Token | L |
Token ID | 406 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Debor | +0.967 |
� | +0.852 |
ト | +0.799 |
MSM | +0.798 |
unsus | +0.776 |
Neg logit contributions | |
grain | -0.942 |
urdue | -0.902 |
ellar | -0.900 |
Windsor | -0.880 |
font | -0.868 |
Token | : |
Token ID | 25 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
Debor | +1.295 |
� | +1.127 |
ト | +1.054 |
MSM | +1.046 |
unsus | +1.020 |
Neg logit contributions | |
grain | -1.449 |
urdue | -1.394 |
ellar | -1.391 |
Windsor | -1.366 |
font | -1.348 |
Token | VB |
Token ID | 44526 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Debor | +2.179 |
� | +1.918 |
MSM | +1.801 |
ト | +1.800 |
unsus | +1.735 |
Neg logit contributions | |
grain | -2.209 |
ellar | -2.119 |
urdue | -2.117 |
Windsor | -2.056 |
font | -2.037 |
Token | 5 |
Token ID | 642 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Debor | +1.055 |
� | +0.924 |
ト | +0.866 |
MSM | +0.861 |
unsus | +0.839 |
Neg logit contributions | |
grain | -1.107 |
urdue | -1.062 |
ellar | -1.060 |
Windsor | -1.039 |
font | -1.025 |
Token | 92 |
Token ID | 5892 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Debor | +1.724 |
� | +1.512 |
ト | +1.414 |
MSM | +1.408 |
unsus | +1.367 |
Neg logit contributions | |
grain | -1.838 |
urdue | -1.765 |
ellar | -1.763 |
Windsor | -1.726 |
font | -1.704 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Debor | +2.120 |
� | +1.871 |
ト | +1.758 |
MSM | +1.754 |
機 | +1.696 |
Neg logit contributions | |
grain | -2.044 |
urdue | -1.961 |
ellar | -1.960 |
Windsor | -1.910 |
font | -1.885 |
Token | 78 |
Token ID | 3695 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Debor | +1.223 |
� | +1.063 |
ト | +0.992 |
MSM | +0.985 |
unsus | +0.958 |
Neg logit contributions | |
grain | -1.413 |
urdue | -1.360 |
ellar | -1.357 |
Windsor | -1.332 |
font | -1.315 |
Token | T |
Token ID | 309 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Debor | +1.943 |
� | +1.724 |
ト | +1.628 |
MSM | +1.626 |
unsus | +1.574 |
Neg logit contributions | |
grain | -1.646 |
ellar | -1.573 |
urdue | -1.572 |
Windsor | -1.524 |
font | -1.507 |
Token | : |
Token ID | 25 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
Debor | +1.638 |
� | +1.428 |
ト | +1.335 |
MSM | +1.326 |
unsus | +1.291 |
Neg logit contributions | |
grain | -1.833 |
urdue | -1.761 |
ellar | -1.756 |
Windsor | -1.725 |
font | -1.702 |
Token | s |
Token ID | 82 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
Debor | +0.532 |
� | +0.469 |
ト | +0.441 |
MSM | +0.439 |
unsus | +0.429 |
Neg logit contributions | |
grain | -0.502 |
urdue | -0.481 |
ellar | -0.480 |
Windsor | -0.470 |
font | -0.463 |
Token | is |
Token ID | 318 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
grain | +1.807 |
urdue | +1.722 |
ellar | +1.709 |
Windsor | +1.690 |
font | +1.666 |
Neg logit contributions | |
Debor | -2.542 |
� | -2.289 |
ト | -2.174 |
MSM | -2.162 |
機 | -2.137 |
Token | a |
Token ID | 257 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
Debor | +0.682 |
� | +0.603 |
ト | +0.568 |
MSM | +0.566 |
unsus | +0.553 |
Neg logit contributions | |
grain | -0.603 |
urdue | -0.577 |
ellar | -0.576 |
Windsor | -0.563 |
font | -0.555 |
Token | modern |
Token ID | 3660 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
grain | +0.025 |
urdue | +0.024 |
ellar | +0.024 |
Windsor | +0.023 |
font | +0.023 |
Neg logit contributions | |
Debor | -0.026 |
� | -0.023 |
ト | -0.022 |
MSM | -0.022 |
unsus | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
grain | +0.073 |
urdue | +0.070 |
ellar | +0.070 |
Windsor | +0.068 |
font | +0.067 |
Neg logit contributions | |
Debor | -0.077 |
� | -0.068 |
ト | -0.064 |
MSM | -0.063 |
unsus | -0.062 |
Token | multi |
Token ID | 5021 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
grain | +0.384 |
urdue | +0.367 |
ellar | +0.367 |
Windsor | +0.362 |
font | +0.356 |
Neg logit contributions | |
Debor | -0.404 |
� | -0.356 |
ト | -0.335 |
MSM | -0.331 |
� | -0.324 |
Token | - |
Token ID | 12 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Debor | +1.655 |
� | +1.484 |
ト | +1.405 |
MSM | +1.396 |
unsus | +1.366 |
Neg logit contributions | |
grain | -1.270 |
urdue | -1.217 |
ellar | -1.211 |
Windsor | -1.184 |
font | -1.158 |
Token | billion |
Token ID | 24540 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
grain | +1.388 |
ellar | +1.298 |
urdue | +1.291 |
font | +1.284 |
Windsor | +1.272 |
Neg logit contributions | |
Debor | -1.718 |
� | -1.523 |
MSM | -1.433 |
ト | -1.432 |
unsus | -1.401 |
Token | dollar |
Token ID | 8872 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Debor | +1.431 |
� | +1.240 |
ト | +1.153 |
MSM | +1.139 |
unsus | +1.108 |
Neg logit contributions | |
grain | -1.832 |
urdue | -1.777 |
ellar | -1.769 |
Windsor | -1.737 |
font | -1.711 |
Token | campaign |
Token ID | 1923 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Debor | +1.247 |
� | +1.091 |
ト | +1.026 |
MSM | +1.025 |
unsus | +0.998 |
Neg logit contributions | |
grain | -1.254 |
urdue | -1.204 |
ellar | -1.202 |
Windsor | -1.174 |
font | -1.158 |
Token | to |
Token ID | 284 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
Debor | +1.103 |
� | +0.967 |
ト | +0.909 |
MSM | +0.905 |
unsus | +0.884 |
Neg logit contributions | |
grain | -1.091 |
urdue | -1.046 |
ellar | -1.045 |
Windsor | -1.023 |
font | -1.008 |
Token | OF |
Token ID | 3963 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Debor | +0.077 |
� | +0.067 |
ト | +0.063 |
MSM | +0.062 |
unsus | +0.062 |
Neg logit contributions | |
grain | -0.079 |
urdue | -0.076 |
ellar | -0.076 |
Windsor | -0.075 |
font | -0.074 |
Token | EXT |
Token ID | 27489 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
Debor | +0.138 |
� | +0.122 |
ト | +0.115 |
MSM | +0.113 |
unsus | +0.112 |
Neg logit contributions | |
grain | -0.134 |
urdue | -0.129 |
ellar | -0.129 |
Windsor | -0.127 |
font | -0.125 |
Token | REM |
Token ID | 40726 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
grain | +0.525 |
urdue | +0.500 |
ellar | +0.499 |
Windsor | +0.487 |
font | +0.478 |
Neg logit contributions | |
Debor | -0.752 |
� | -0.673 |
ト | -0.640 |
MSM | -0.635 |
unsus | -0.624 |
Token | ELY |
Token ID | 30943 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
Debor | +0.032 |
� | +0.028 |
ト | +0.027 |
MSM | +0.026 |
unsus | +0.026 |
Neg logit contributions | |
grain | -0.033 |
urdue | -0.031 |
ellar | -0.031 |
Windsor | -0.031 |
font | -0.030 |
Token | EXP |
Token ID | 25703 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
grain | +0.472 |
urdue | +0.453 |
ellar | +0.452 |
Windsor | +0.444 |
font | +0.438 |
Neg logit contributions | |
Debor | -0.449 |
� | -0.393 |
ト | -0.368 |
MSM | -0.365 |
unsus | -0.357 |
Token | ENS |
Token ID | 16938 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
grain | +0.992 |
ellar | +0.951 |
urdue | +0.951 |
Windsor | +0.937 |
font | +0.924 |
Neg logit contributions | |
Debor | -1.120 |
� | -0.989 |
ト | -0.935 |
MSM | -0.925 |
unsus | -0.914 |
Token | IVE |
Token ID | 9306 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
grain | +1.418 |
ellar | +1.380 |
urdue | +1.374 |
Windsor | +1.362 |
font | +1.350 |
Neg logit contributions | |
Debor | -0.568 |
� | -0.436 |
ト | -0.384 |
MSM | -0.376 |
unsus | -0.374 |
Token | BE |
Token ID | 9348 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Debor | +0.239 |
� | +0.209 |
ト | +0.196 |
MSM | +0.195 |
unsus | +0.190 |
Neg logit contributions | |
grain | -0.256 |
urdue | -0.246 |
ellar | -0.246 |
Windsor | -0.241 |
font | -0.238 |
Token | ER |
Token ID | 1137 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
grain | +1.152 |
urdue | +1.106 |
ellar | +1.106 |
Windsor | +1.087 |
font | +1.078 |
Neg logit contributions | |
Debor | -1.129 |
� | -0.976 |
ト | -0.929 |
MSM | -0.912 |
unsus | -0.907 |
Token | WITHOUT |
Token ID | 42881 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
grain | +1.307 |
urdue | +1.252 |
ellar | +1.248 |
Windsor | +1.233 |
font | +1.216 |
Neg logit contributions | |
Debor | -1.470 |
� | -1.282 |
ト | -1.218 |
unsus | -1.207 |
MSM | -1.189 |
Token | THE |
Token ID | 3336 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
Debor | +0.313 |
� | +0.273 |
ト | +0.257 |
MSM | +0.254 |
unsus | +0.250 |
Neg logit contributions | |
grain | -0.326 |
urdue | -0.313 |
ellar | -0.312 |
Windsor | -0.307 |
font | -0.303 |
Token | larger |
Token ID | 4025 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
grain | +0.969 |
ellar | +0.922 |
urdue | +0.921 |
Windsor | +0.907 |
font | +0.891 |
Neg logit contributions | |
Debor | -1.163 |
� | -1.038 |
ト | -0.979 |
MSM | -0.965 |
� | -0.951 |
Token | ( |
Token ID | 357 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
grain | +0.087 |
urdue | +0.083 |
ellar | +0.083 |
Windsor | +0.082 |
font | +0.080 |
Neg logit contributions | |
Debor | -0.104 |
� | -0.092 |
ト | -0.087 |
MSM | -0.087 |
unsus | -0.085 |
Token | 3 |
Token ID | 18 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Debor | +0.619 |
� | +0.546 |
ト | +0.514 |
MSM | +0.508 |
unsus | +0.497 |
Neg logit contributions | |
grain | -0.624 |
urdue | -0.604 |
ellar | -0.602 |
Windsor | -0.590 |
afety | -0.579 |
Token | . |
Token ID | 13 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
grain | +1.621 |
urdue | +1.550 |
ellar | +1.544 |
Windsor | +1.531 |
font | +1.510 |
Neg logit contributions | |
Debor | -1.760 |
� | -1.533 |
ト | -1.457 |
MSM | -1.440 |
unsus | -1.423 |
Token | 9 |
Token ID | 24 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
grain | +0.373 |
urdue | +0.358 |
ellar | +0.357 |
Windsor | +0.350 |
font | +0.345 |
Neg logit contributions | |
Debor | -0.402 |
� | -0.354 |
ト | -0.334 |
MSM | -0.331 |
unsus | -0.325 |
Token | – |
Token ID | 784 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Debor | +0.127 |
� | +0.112 |
ト | +0.105 |
MSM | +0.105 |
unsus | +0.102 |
Neg logit contributions | |
grain | -0.125 |
urdue | -0.120 |
ellar | -0.119 |
Windsor | -0.117 |
font | -0.115 |
Token | 4 |
Token ID | 604 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
grain | +1.203 |
urdue | +1.137 |
ellar | +1.131 |
Windsor | +1.115 |
font | +1.092 |
Neg logit contributions | |
Debor | -1.841 |
� | -1.659 |
ト | -1.578 |
MSM | -1.563 |
unsus | -1.536 |
Token | . |
Token ID | 13 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Debor | +0.445 |
� | +0.391 |
ト | +0.365 |
MSM | +0.364 |
unsus | +0.354 |
Neg logit contributions | |
grain | -0.464 |
urdue | -0.446 |
ellar | -0.445 |
Windsor | -0.436 |
font | -0.430 |
Token | 5 |
Token ID | 20 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Debor | +1.754 |
� | +1.541 |
ト | +1.451 |
MSM | +1.438 |
unsus | +1.402 |
Neg logit contributions | |
grain | -1.723 |
ellar | -1.647 |
urdue | -1.645 |
Windsor | -1.614 |
afety | -1.584 |
Token | kg |
Token ID | 14211 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Debor | +0.829 |
� | +0.724 |
MSM | +0.672 |
ト | +0.670 |
� | +0.649 |
Neg logit contributions | |
grain | -1.006 |
urdue | -0.971 |
ellar | -0.968 |
Windsor | -0.947 |
font | -0.933 |
Token | ), |
Token ID | 828 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
grain | +1.151 |
urdue | +1.098 |
ellar | +1.085 |
Windsor | +1.073 |
font | +1.058 |
Neg logit contributions | |
Debor | -1.432 |
� | -1.271 |
ト | -1.206 |
MSM | -1.187 |
unsus | -1.170 |
Token | located |
Token ID | 5140 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
grain | +0.438 |
urdue | +0.420 |
ellar | +0.417 |
Windsor | +0.411 |
font | +0.405 |
Neg logit contributions | |
Debor | -0.484 |
� | -0.425 |
ト | -0.400 |
MSM | -0.399 |
unsus | -0.389 |
Token | the |
Token ID | 262 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
grain | +1.602 |
urdue | +1.528 |
ellar | +1.527 |
Windsor | +1.518 |
font | +1.483 |
Neg logit contributions | |
Debor | -1.829 |
� | -1.619 |
ト | -1.523 |
MSM | -1.510 |
� | -1.480 |
Token | legendary |
Token ID | 13273 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Debor | +0.247 |
� | +0.219 |
ト | +0.207 |
MSM | +0.207 |
unsus | +0.203 |
Neg logit contributions | |
grain | -0.210 |
urdue | -0.201 |
ellar | -0.200 |
Windsor | -0.195 |
font | -0.192 |
Token | war |
Token ID | 1175 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Debor | +0.158 |
� | +0.140 |
ト | +0.132 |
MSM | +0.131 |
unsus | +0.128 |
Neg logit contributions | |
grain | -0.139 |
urdue | -0.133 |
ellar | -0.133 |
Windsor | -0.130 |
font | -0.128 |
Token | for |
Token ID | 329 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
grain | +0.900 |
urdue | +0.859 |
ellar | +0.853 |
Windsor | +0.840 |
font | +0.831 |
Neg logit contributions | |
Debor | -1.000 |
� | -0.880 |
ト | -0.830 |
MSM | -0.823 |
unsus | -0.805 |
Token | Helen |
Token ID | 22695 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
grain | +1.753 |
urdue | +1.663 |
ellar | +1.656 |
Windsor | +1.645 |
font | +1.616 |
Neg logit contributions | |
Debor | -1.947 |
� | -1.727 |
ト | -1.608 |
MSM | -1.606 |
機 | -1.575 |
Token | that |
Token ID | 326 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
grain | +2.389 |
urdue | +2.242 |
ellar | +2.233 |
Windsor | +2.224 |
font | +2.216 |
Neg logit contributions | |
Debor | -2.674 |
� | -2.340 |
MSM | -2.227 |
ト | -2.200 |
unsus | -2.166 |
Token | would |
Token ID | 561 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
grain | +0.408 |
urdue | +0.390 |
ellar | +0.387 |
Windsor | +0.383 |
font | +0.375 |
Neg logit contributions | |
Debor | -0.485 |
� | -0.431 |
ト | -0.407 |
MSM | -0.404 |
unsus | -0.395 |
Token | become |
Token ID | 1716 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
grain | +0.931 |
urdue | +0.887 |
ellar | +0.885 |
Windsor | +0.867 |
font | +0.852 |
Neg logit contributions | |
Debor | -1.238 |
� | -1.105 |
ト | -1.047 |
MSM | -1.040 |
unsus | -1.019 |
Token | parad |
Token ID | 11497 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Debor | +0.423 |
� | +0.376 |
ト | +0.355 |
MSM | +0.353 |
unsus | +0.346 |
Neg logit contributions | |
grain | -0.351 |
urdue | -0.335 |
ellar | -0.334 |
Windsor | -0.326 |
font | -0.322 |
Token | igmatic |
Token ID | 38860 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
grain | +0.069 |
urdue | +0.065 |
ellar | +0.065 |
Windsor | +0.063 |
font | +0.062 |
Neg logit contributions | |
Debor | -0.125 |
� | -0.113 |
ト | -0.108 |
MSM | -0.107 |
unsus | -0.105 |
Token | The |
Token ID | 383 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
Debor | +0.676 |
� | +0.593 |
ト | +0.559 |
MSM | +0.559 |
unsus | +0.538 |
Neg logit contributions | |
grain | -0.627 |
urdue | -0.600 |
ellar | -0.599 |
Windsor | -0.580 |
font | -0.576 |
Token | bulldo |
Token ID | 44767 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Debor | +0.551 |
� | +0.480 |
MSM | +0.451 |
ト | +0.449 |
unsus | +0.438 |
Neg logit contributions | |
grain | -0.584 |
urdue | -0.561 |
ellar | -0.560 |
Windsor | -0.546 |
font | -0.542 |
Token | zers |
Token ID | 47031 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Debor | +0.125 |
� | +0.108 |
ト | +0.100 |
MSM | +0.100 |
unsus | +0.097 |
Neg logit contributions | |
grain | -0.155 |
urdue | -0.149 |
ellar | -0.149 |
Windsor | -0.147 |
font | -0.145 |
Token | that |
Token ID | 326 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Debor | +0.272 |
� | +0.240 |
ト | +0.227 |
MSM | +0.225 |
unsus | +0.221 |
Neg logit contributions | |
grain | -0.239 |
urdue | -0.229 |
ellar | -0.228 |
Windsor | -0.224 |
font | -0.220 |
Token | are |
Token ID | 389 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
grain | +0.784 |
urdue | +0.749 |
ellar | +0.746 |
Windsor | +0.736 |
font | +0.721 |
Neg logit contributions | |
Debor | -0.908 |
� | -0.806 |
ト | -0.761 |
MSM | -0.754 |
� | -0.740 |
Token | responsible |
Token ID | 4497 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Debor | +0.305 |
� | +0.269 |
ト | +0.253 |
MSM | +0.252 |
unsus | +0.247 |
Neg logit contributions | |
grain | -0.275 |
urdue | -0.263 |
ellar | -0.263 |
Windsor | -0.257 |
font | -0.253 |
Token | for |
Token ID | 329 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
grain | +1.121 |
urdue | +1.072 |
ellar | +1.069 |
Windsor | +1.044 |
font | +1.031 |
Neg logit contributions | |
Debor | -1.494 |
� | -1.332 |
ト | -1.270 |
MSM | -1.258 |
unsus | -1.238 |
Token | destroying |
Token ID | 13897 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
grain | +1.998 |
ellar | +1.907 |
urdue | +1.900 |
Windsor | +1.899 |
font | +1.842 |
Neg logit contributions | |
Debor | -2.446 |
� | -2.182 |
ト | -2.073 |
MSM | -2.029 |
� | -2.021 |
Token | land |
Token ID | 1956 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
grain | +1.737 |
Windsor | +1.649 |
ellar | +1.646 |
urdue | +1.645 |
font | +1.601 |
Neg logit contributions | |
Debor | -1.927 |
� | -1.724 |
ト | -1.621 |
MSM | -1.593 |
� | -1.583 |
Token | and |
Token ID | 290 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
Debor | +0.706 |
� | +0.618 |
ト | +0.581 |
MSM | +0.576 |
unsus | +0.567 |
Neg logit contributions | |
grain | -0.706 |
urdue | -0.682 |
ellar | -0.682 |
Windsor | -0.666 |
font | -0.655 |
Token | buildings |
Token ID | 6832 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
grain | +0.485 |
urdue | +0.463 |
ellar | +0.462 |
Windsor | +0.453 |
font | +0.446 |
Neg logit contributions | |
Debor | -0.581 |
� | -0.516 |
ト | -0.487 |
MSM | -0.484 |
unsus | -0.474 |
Token | their |
Token ID | 511 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
Debor | +1.584 |
� | +1.377 |
ト | +1.294 |
MSM | +1.290 |
unsus | +1.260 |
Neg logit contributions | |
grain | -1.668 |
urdue | -1.605 |
ellar | -1.601 |
Windsor | -1.558 |
font | -1.546 |
Token | territory |
Token ID | 7674 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
grain | +0.403 |
urdue | +0.385 |
ellar | +0.385 |
Windsor | +0.381 |
font | +0.374 |
Neg logit contributions | |
Debor | -0.407 |
� | -0.360 |
ト | -0.338 |
MSM | -0.334 |
� | -0.327 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
grain | +0.647 |
urdue | +0.620 |
ellar | +0.616 |
Windsor | +0.610 |
font | +0.600 |
Neg logit contributions | |
Debor | -0.722 |
� | -0.640 |
ト | -0.605 |
MSM | -0.602 |
unsus | -0.587 |
Token | But |
Token ID | 887 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Debor | +0.900 |
� | +0.792 |
ト | +0.747 |
MSM | +0.745 |
unsus | +0.721 |
Neg logit contributions | |
grain | -0.809 |
urdue | -0.773 |
ellar | -0.772 |
Windsor | -0.750 |
font | -0.742 |
Token | we |
Token ID | 356 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Debor | +0.348 |
� | +0.308 |
ト | +0.290 |
MSM | +0.287 |
unsus | +0.281 |
Neg logit contributions | |
grain | -0.322 |
urdue | -0.309 |
ellar | -0.308 |
Windsor | -0.303 |
font | -0.298 |
Token | should |
Token ID | 815 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
grain | +0.904 |
ellar | +0.862 |
urdue | +0.861 |
Windsor | +0.850 |
font | +0.832 |
Neg logit contributions | |
Debor | -1.139 |
� | -1.021 |
ト | -0.969 |
MSM | -0.952 |
� | -0.946 |
Token | applaud |
Token ID | 22517 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
grain | +0.727 |
urdue | +0.696 |
ellar | +0.691 |
Windsor | +0.679 |
font | +0.670 |
Neg logit contributions | |
Debor | -0.925 |
� | -0.823 |
ト | -0.780 |
MSM | -0.773 |
� | -0.757 |
Token | them |
Token ID | 606 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
grain | +2.336 |
Windsor | +2.269 |
urdue | +2.261 |
ellar | +2.229 |
font | +2.190 |
Neg logit contributions | |
Debor | -2.800 |
� | -2.529 |
ト | -2.398 |
� | -2.341 |
機 | -2.336 |
Token | for |
Token ID | 329 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
grain | +2.037 |
urdue | +1.977 |
ellar | +1.954 |
Windsor | +1.939 |
font | +1.911 |
Neg logit contributions | |
Debor | -2.652 |
� | -2.367 |
ト | -2.263 |
MSM | -2.243 |
機 | -2.205 |
Token | their |
Token ID | 511 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
grain | +0.966 |
urdue | +0.930 |
ellar | +0.925 |
Windsor | +0.913 |
font | +0.893 |
Neg logit contributions | |
Debor | -1.169 |
� | -1.040 |
ト | -0.984 |
MSM | -0.973 |
機 | -0.953 |
Token | realism |
Token ID | 30787 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
grain | +1.492 |
urdue | +1.433 |
ellar | +1.428 |
Windsor | +1.411 |
font | +1.377 |
Neg logit contributions | |
Debor | -1.741 |
� | -1.543 |
ト | -1.458 |
MSM | -1.438 |
機 | -1.415 |
Token | - |
Token ID | 12 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
grain | +1.249 |
urdue | +1.169 |
ellar | +1.168 |
Windsor | +1.153 |
font | +1.151 |
Neg logit contributions | |
Debor | -1.808 |
� | -1.613 |
MSM | -1.532 |
ト | -1.529 |
unsus | -1.508 |
Token | cl |
Token ID | 565 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Debor | +0.706 |
� | +0.623 |
ト | +0.585 |
MSM | +0.579 |
unsus | +0.567 |
Neg logit contributions | |
grain | -0.688 |
urdue | -0.664 |
ellar | -0.661 |
Windsor | -0.648 |
font | -0.634 |
Token | oak |
Token ID | 15877 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
grain | +0.161 |
ellar | +0.153 |
urdue | +0.153 |
Windsor | +0.149 |
font | +0.145 |
Neg logit contributions | |
Debor | -0.233 |
� | -0.209 |
ト | -0.199 |
MSM | -0.197 |
unsus | -0.194 |
Token | to |
Token ID | 284 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Debor | +0.414 |
� | +0.367 |
ト | +0.345 |
MSM | +0.343 |
unsus | +0.336 |
Neg logit contributions | |
grain | -0.377 |
urdue | -0.362 |
ellar | -0.361 |
Windsor | -0.353 |
font | -0.347 |
Token | this |
Token ID | 428 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Debor | +1.340 |
� | +1.193 |
MSM | +1.127 |
ト | +1.125 |
unsus | +1.107 |
Neg logit contributions | |
grain | -1.162 |
urdue | -1.126 |
ellar | -1.117 |
Windsor | -1.084 |
afety | -1.073 |
Token | end |
Token ID | 886 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
Debor | +1.158 |
� | +1.020 |
MSM | +0.956 |
ト | +0.955 |
unsus | +0.937 |
Neg logit contributions | |
grain | -1.115 |
urdue | -1.076 |
ellar | -1.073 |
Windsor | -1.045 |
font | -1.031 |
Token | . |
Token ID | 13 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
grain | +3.882 |
urdue | +3.628 |
ellar | +3.604 |
font | +3.575 |
Windsor | +3.518 |
Neg logit contributions | |
Debor | -4.579 |
� | -4.027 |
ト | -3.857 |
MSM | -3.799 |
� | -3.778 |
Token | It |
Token ID | 632 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
Debor | +0.059 |
� | +0.052 |
ト | +0.049 |
MSM | +0.049 |
unsus | +0.048 |
Neg logit contributions | |
grain | -0.051 |
urdue | -0.049 |
ellar | -0.049 |
Windsor | -0.048 |
font | -0.047 |
Token | works |
Token ID | 2499 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
Debor | +0.377 |
� | +0.336 |
ト | +0.317 |
MSM | +0.316 |
unsus | +0.310 |
Neg logit contributions | |
grain | -0.303 |
urdue | -0.289 |
ellar | -0.289 |
Windsor | -0.282 |
font | -0.277 |
Token | by |
Token ID | 416 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Debor | +3.081 |
� | +2.709 |
MSM | +2.558 |
unsus | +2.528 |
ト | +2.527 |
Neg logit contributions | |
grain | -2.916 |
urdue | -2.820 |
ellar | -2.795 |
Windsor | -2.696 |
afety | -2.674 |
Token | injecting |
Token ID | 41750 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Debor | +1.275 |
� | +1.134 |
MSM | +1.070 |
ト | +1.069 |
unsus | +1.053 |
Neg logit contributions | |
grain | -1.009 |
urdue | -0.964 |
ellar | -0.960 |
Windsor | -0.933 |
font | -0.919 |
Token | Mag |
Token ID | 2944 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Debor | +0.918 |
� | +0.808 |
ト | +0.760 |
MSM | +0.759 |
unsus | +0.738 |
Neg logit contributions | |
grain | -0.852 |
urdue | -0.819 |
ellar | -0.818 |
Windsor | -0.795 |
font | -0.786 |
Token | ico |
Token ID | 3713 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Debor | +0.842 |
� | +0.746 |
ト | +0.707 |
MSM | +0.701 |
unsus | +0.685 |
Neg logit contributions | |
grain | -0.719 |
urdue | -0.693 |
ellar | -0.688 |
Windsor | -0.676 |
font | -0.661 |
Token | and |
Token ID | 290 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
grain | +1.231 |
urdue | +1.171 |
ellar | +1.166 |
Windsor | +1.151 |
font | +1.136 |
Neg logit contributions | |
Debor | -1.412 |
� | -1.241 |
ト | -1.179 |
MSM | -1.167 |
unsus | -1.151 |
Token | V |
Token ID | 569 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
grain | +0.305 |
urdue | +0.292 |
ellar | +0.291 |
Windsor | +0.287 |
font | +0.282 |
Neg logit contributions | |
Debor | -0.332 |
� | -0.294 |
ト | -0.277 |
MSM | -0.274 |
unsus | -0.269 |
Token | ivid |
Token ID | 1699 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
Debor | +0.119 |
� | +0.105 |
ト | +0.098 |
MSM | +0.098 |
unsus | +0.096 |
Neg logit contributions | |
grain | -0.110 |
urdue | -0.106 |
ellar | -0.106 |
Windsor | -0.103 |
font | -0.102 |
Token | Audio |
Token ID | 13491 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
Debor | +0.691 |
� | +0.615 |
ト | +0.580 |
MSM | +0.577 |
unsus | +0.564 |
Neg logit contributions | |
grain | -0.580 |
urdue | -0.556 |
ellar | -0.554 |
Windsor | -0.542 |
font | -0.533 |
Token | -- |
Token ID | 1377 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
grain | +3.666 |
urdue | +3.476 |
Windsor | +3.440 |
font | +3.409 |
ellar | +3.397 |
Neg logit contributions | |
Debor | -4.439 |
� | -3.834 |
ト | -3.703 |
unsus | -3.655 |
MSM | -3.631 |
Token | and |
Token ID | 290 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
grain | +1.135 |
urdue | +1.081 |
ellar | +1.077 |
Windsor | +1.060 |
font | +1.048 |
Neg logit contributions | |
Debor | -1.309 |
� | -1.157 |
ト | -1.095 |
MSM | -1.081 |
� | -1.070 |
Token | their |
Token ID | 511 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
Debor | +0.601 |
� | +0.531 |
ト | +0.501 |
MSM | +0.499 |
unsus | +0.488 |
Neg logit contributions | |
grain | -0.536 |
urdue | -0.514 |
ellar | -0.513 |
Windsor | -0.502 |
font | -0.494 |
Token | lowest |
Token ID | 9016 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Debor | +0.048 |
� | +0.042 |
ト | +0.040 |
MSM | +0.039 |
unsus | +0.038 |
Neg logit contributions | |
grain | -0.044 |
urdue | -0.042 |
ellar | -0.042 |
Windsor | -0.042 |
font | -0.041 |
Token | - |
Token ID | 12 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
grain | +0.818 |
ellar | +0.781 |
urdue | +0.778 |
Windsor | +0.762 |
font | +0.752 |
Neg logit contributions | |
Debor | -1.021 |
� | -0.905 |
ト | -0.860 |
MSM | -0.852 |
unsus | -0.837 |
Token | capacity |
Token ID | 5339 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
grain | +1.591 |
urdue | +1.517 |
ellar | +1.515 |
Windsor | +1.496 |
font | +1.464 |
Neg logit contributions | |
Debor | -1.739 |
� | -1.540 |
ト | -1.452 |
MSM | -1.438 |
unsus | -1.406 |
Token | to |
Token ID | 284 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
grain | +2.466 |
urdue | +2.349 |
Windsor | +2.331 |
ellar | +2.316 |
font | +2.267 |
Neg logit contributions | |
Debor | -2.830 |
� | -2.530 |
ト | -2.412 |
MSM | -2.385 |
� | -2.329 |
Token | 300 |
Token ID | 5867 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
grain | +1.430 |
urdue | +1.368 |
ellar | +1.366 |
Windsor | +1.347 |
font | +1.317 |
Neg logit contributions | |
Debor | -1.598 |
� | -1.417 |
ト | -1.337 |
MSM | -1.321 |
unsus | -1.295 |
Token | , |
Token ID | 11 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
grain | +1.025 |
urdue | +0.979 |
ellar | +0.977 |
Windsor | +0.964 |
font | +0.947 |
Neg logit contributions | |
Debor | -1.071 |
� | -0.942 |
ト | -0.888 |
MSM | -0.880 |
unsus | -0.863 |
Token | 000 |
Token ID | 830 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
grain | +1.657 |
urdue | +1.595 |
ellar | +1.587 |
Windsor | +1.572 |
font | +1.541 |
Neg logit contributions | |
Debor | -1.549 |
� | -1.353 |
ト | -1.264 |
MSM | -1.258 |
unsus | -1.227 |
Token | barrels |
Token ID | 17907 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
grain | +0.651 |
urdue | +0.615 |
ellar | +0.614 |
Windsor | +0.601 |
font | +0.588 |
Neg logit contributions | |
Debor | -1.037 |
� | -0.933 |
ト | -0.889 |
MSM | -0.884 |
unsus | -0.869 |
Token | a |
Token ID | 257 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
grain | +3.860 |
Windsor | +3.639 |
urdue | +3.582 |
font | +3.537 |
afety | +3.535 |
Neg logit contributions | |
Debor | -6.096 |
� | -5.416 |
ト | -5.277 |
機 | -5.177 |
MSM | -5.142 |
Token | day |
Token ID | 1110 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
Debor | +2.323 |
� | +2.058 |
ト | +1.909 |
MSM | +1.889 |
unsus | +1.847 |
Neg logit contributions | |
grain | -2.530 |
urdue | -2.457 |
ellar | -2.451 |
font | -2.363 |
afety | -2.353 |
Token | . |
Token ID | 13 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
Debor | +0.034 |
� | +0.030 |
ト | +0.028 |
MSM | +0.028 |
unsus | +0.027 |
Neg logit contributions | |
grain | -0.031 |
urdue | -0.030 |
ellar | -0.029 |
Windsor | -0.029 |
font | -0.029 |
Token | Virt |
Token ID | 11285 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
grain | +0.451 |
urdue | +0.432 |
ellar | +0.431 |
Windsor | +0.425 |
font | +0.417 |
Neg logit contributions | |
Debor | -0.487 |
� | -0.430 |
ト | -0.406 |
MSM | -0.402 |
unsus | -0.397 |
Token | ually |
Token ID | 935 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
grain | +0.276 |
urdue | +0.262 |
ellar | +0.262 |
Windsor | +0.257 |
font | +0.252 |
Neg logit contributions | |
Debor | -0.364 |
� | -0.324 |
ト | -0.307 |
MSM | -0.305 |
unsus | -0.299 |
Token | her |
Token ID | 607 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
grain | +0.783 |
urdue | +0.751 |
ellar | +0.750 |
Windsor | +0.740 |
font | +0.726 |
Neg logit contributions | |
Debor | -0.819 |
� | -0.724 |
ト | -0.683 |
MSM | -0.675 |
unsus | -0.661 |
Token | and |
Token ID | 290 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
grain | +1.184 |
urdue | +1.137 |
ellar | +1.135 |
Windsor | +1.123 |
font | +1.097 |
Neg logit contributions | |
Debor | -1.322 |
� | -1.169 |
ト | -1.112 |
MSM | -1.096 |
unsus | -1.074 |
Token | another |
Token ID | 1194 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
grain | +1.834 |
urdue | +1.759 |
ellar | +1.756 |
Windsor | +1.749 |
font | +1.700 |
Neg logit contributions | |
Debor | -1.901 |
� | -1.687 |
ト | -1.594 |
MSM | -1.571 |
機 | -1.543 |
Token | employee |
Token ID | 6538 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
grain | +1.002 |
urdue | +0.959 |
ellar | +0.956 |
Windsor | +0.938 |
font | +0.922 |
Neg logit contributions | |
Debor | -1.152 |
� | -1.021 |
ト | -0.964 |
MSM | -0.957 |
unsus | -0.937 |
Token | , |
Token ID | 11 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
grain | +1.031 |
urdue | +0.991 |
ellar | +0.986 |
Windsor | +0.972 |
font | +0.955 |
Neg logit contributions | |
Debor | -1.113 |
� | -0.983 |
ト | -0.929 |
MSM | -0.922 |
unsus | -0.900 |
Token | Desire |
Token ID | 41042 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
Debor | +0.071 |
� | +0.063 |
ト | +0.059 |
MSM | +0.059 |
unsus | +0.057 |
Neg logit contributions | |
grain | -0.062 |
urdue | -0.060 |
ellar | -0.059 |
Windsor | -0.058 |
font | -0.057 |
Token | e |
Token ID | 68 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
grain | +3.116 |
Windsor | +3.024 |
ellar | +2.988 |
urdue | +2.946 |
font | +2.869 |
Neg logit contributions | |
Debor | -5.269 |
� | -4.896 |
ト | -4.644 |
MSM | -4.622 |
� | -4.581 |
Token | La |
Token ID | 4689 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
grain | +1.699 |
ellar | +1.623 |
urdue | +1.622 |
Windsor | +1.619 |
font | +1.578 |
Neg logit contributions | |
Debor | -1.829 |
� | -1.633 |
ト | -1.537 |
MSM | -1.521 |
unsus | -1.503 |
Token | Feb |
Token ID | 15146 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Debor | +0.026 |
� | +0.023 |
ト | +0.021 |
MSM | +0.021 |
unsus | +0.021 |
Neg logit contributions | |
grain | -0.024 |
urdue | -0.023 |
ellar | -0.023 |
Windsor | -0.023 |
font | -0.022 |
Token | re |
Token ID | 260 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Debor | +1.451 |
� | +1.290 |
ト | +1.226 |
MSM | +1.213 |
unsus | +1.192 |
Neg logit contributions | |
grain | -1.096 |
urdue | -1.044 |
ellar | -1.029 |
Windsor | -1.014 |
font | -0.996 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Debor | +0.870 |
� | +0.768 |
ト | +0.723 |
MSM | +0.718 |
unsus | +0.703 |
Neg logit contributions | |
grain | -0.806 |
urdue | -0.771 |
ellar | -0.769 |
Windsor | -0.755 |
font | -0.744 |
Token | rebutt |
Token ID | 46472 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
Debor | +0.965 |
� | +0.838 |
ト | +0.785 |
MSM | +0.781 |
unsus | +0.763 |
Neg logit contributions | |
grain | -1.093 |
urdue | -1.051 |
ellar | -1.049 |
Windsor | -1.027 |
font | -1.016 |
Token | als |
Token ID | 874 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Debor | +0.707 |
� | +0.619 |
ト | +0.581 |
MSM | +0.577 |
unsus | +0.563 |
Neg logit contributions | |
grain | -0.732 |
urdue | -0.704 |
ellar | -0.701 |
Windsor | -0.689 |
font | -0.679 |
Token | toward |
Token ID | 3812 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
Debor | +1.448 |
� | +1.275 |
ト | +1.200 |
MSM | +1.191 |
unsus | +1.171 |
Neg logit contributions | |
grain | -1.405 |
ellar | -1.343 |
urdue | -1.343 |
Windsor | -1.311 |
font | -1.288 |
Token | cliché |
Token ID | 43973 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
grain | +0.473 |
urdue | +0.452 |
ellar | +0.451 |
Windsor | +0.446 |
font | +0.436 |
Neg logit contributions | |
Debor | -0.511 |
� | -0.455 |
ト | -0.427 |
MSM | -0.421 |
� | -0.416 |
Token | bo |
Token ID | 1489 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Debor | +0.589 |
� | +0.522 |
ト | +0.493 |
MSM | +0.490 |
unsus | +0.480 |
Neg logit contributions | |
grain | -0.501 |
urdue | -0.479 |
ellar | -0.477 |
Windsor | -0.467 |
font | -0.460 |
Token | hem |
Token ID | 4411 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
grain | +0.134 |
urdue | +0.128 |
ellar | +0.128 |
Windsor | +0.125 |
font | +0.123 |
Neg logit contributions | |
Debor | -0.170 |
� | -0.151 |
ト | -0.143 |
MSM | -0.142 |
unsus | -0.140 |
Token | ian |
Token ID | 666 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
grain | +3.382 |
ellar | +3.097 |
urdue | +3.030 |
font | +3.002 |
Windsor | +2.970 |
Neg logit contributions | |
Debor | -6.381 |
� | -5.709 |
� | -5.490 |
ト | -5.457 |
機 | -5.427 |
Token | ideals |
Token ID | 22247 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Debor | +1.437 |
� | +1.257 |
ト | +1.183 |
MSM | +1.180 |
unsus | +1.151 |
Neg logit contributions | |
grain | -1.448 |
urdue | -1.393 |
ellar | -1.385 |
Windsor | -1.357 |
font | -1.341 |
Token | that |
Token ID | 326 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
Debor | +1.116 |
� | +0.984 |
ト | +0.925 |
MSM | +0.921 |
unsus | +0.905 |
Neg logit contributions | |
grain | -1.037 |
urdue | -0.993 |
ellar | -0.991 |
Windsor | -0.969 |
font | -0.954 |
Token | have |
Token ID | 423 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Debor | +0.587 |
� | +0.516 |
ト | +0.485 |
MSM | +0.482 |
unsus | +0.471 |
Neg logit contributions | |
grain | -0.577 |
urdue | -0.554 |
ellar | -0.552 |
Windsor | -0.542 |
font | -0.534 |
Token | been |
Token ID | 587 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Debor | +1.295 |
� | +1.153 |
ト | +1.095 |
MSM | +1.092 |
unsus | +1.074 |
Neg logit contributions | |
grain | -0.948 |
urdue | -0.903 |
ellar | -0.902 |
Windsor | -0.879 |
font | -0.866 |