Token | ) |
Token ID | 8 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
liners | +0.700 |
disguise | +0.663 |
DRAGON | +0.650 |
idth | +0.647 |
tails | +0.645 |
Neg logit contributions | |
ILCS | -0.931 |
illo | -0.902 |
ESA | -0.881 |
Fed | -0.871 |
ilt | -0.869 |
Token | s |
Token ID | 264 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
ILCS | +0.142 |
illo | +0.139 |
ESA | +0.135 |
Fed | +0.134 |
ilt | +0.133 |
Neg logit contributions | |
liners | -0.103 |
disguise | -0.097 |
idth | -0.096 |
DRAGON | -0.095 |
tails | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
liners | +0.470 |
disguise | +0.442 |
DRAGON | +0.436 |
tails | +0.436 |
idth | +0.429 |
Neg logit contributions | |
ILCS | -0.527 |
illo | -0.504 |
ESA | -0.492 |
Fed | -0.483 |
ilt | -0.482 |
Token | t |
Token ID | 83 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
liners | +0.537 |
disguise | +0.492 |
tails | +0.491 |
idth | +0.482 |
DRAGON | +0.480 |
Neg logit contributions | |
ILCS | -0.874 |
illo | -0.841 |
ESA | -0.827 |
Fed | -0.812 |
ilt | -0.809 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ILCS | +0.521 |
illo | +0.502 |
ESA | +0.489 |
Fed | +0.482 |
ilt | +0.480 |
Neg logit contributions | |
liners | -0.503 |
disguise | -0.479 |
DRAGON | -0.473 |
tails | -0.469 |
idth | -0.468 |
Token | GER |
Token ID | 44186 |
Feature activation | +7.47e+00 |
Pos logit contributions | |
liners | +1.286 |
disguise | +1.238 |
DRAGON | +1.230 |
tails | +1.204 |
idth | +1.202 |
Neg logit contributions | |
ILCS | -1.309 |
illo | -1.261 |
ESA | -1.226 |
ilt | -1.213 |
Fed | -1.209 |
Token | 15 |
Token ID | 1315 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
liners | +3.836 |
disguise | +3.606 |
DRAGON | +3.547 |
tails | +3.470 |
idth | +3.467 |
Neg logit contributions | |
ILCS | -6.488 |
illo | -6.331 |
nard | -6.109 |
ESA | -6.065 |
Fed | -6.053 |
Token | Gerald |
Token ID | 27027 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
liners | +1.698 |
disguise | +1.617 |
DRAGON | +1.594 |
idth | +1.582 |
tails | +1.577 |
Neg logit contributions | |
ILCS | -2.062 |
illo | -1.999 |
ESA | -1.951 |
ilt | -1.926 |
Fed | -1.920 |
Token | C |
Token ID | 327 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
liners | +3.149 |
disguise | +3.062 |
idth | +2.984 |
tails | +2.958 |
DRAGON | +2.952 |
Neg logit contributions | |
ILCS | -3.531 |
illo | -3.352 |
ESA | -3.346 |
Fed | -3.279 |
ilt | -3.209 |
Token | io |
Token ID | 952 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
illo | +1.609 |
ILCS | +1.599 |
ESA | +1.535 |
ilt | +1.529 |
Fed | +1.521 |
Neg logit contributions | |
liners | -1.541 |
disguise | -1.490 |
DRAGON | -1.467 |
idth | -1.448 |
tails | -1.421 |
Token | le |
Token ID | 293 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
ILCS | +1.047 |
illo | +1.037 |
ESA | +1.007 |
ilt | +0.998 |
Fed | +0.996 |
Neg logit contributions | |
liners | -0.937 |
disguise | -0.902 |
DRAGON | -0.886 |
idth | -0.873 |
tails | -0.869 |
Token | ( |
Token ID | 357 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
ILCS | +0.295 |
illo | +0.287 |
Fed | +0.279 |
ESA | +0.279 |
ilt | +0.278 |
Neg logit contributions | |
liners | -0.240 |
disguise | -0.228 |
idth | -0.226 |
DRAGON | -0.223 |
tails | -0.222 |
Token | 3 |
Token ID | 18 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
ILCS | +0.061 |
illo | +0.059 |
ESA | +0.058 |
Fed | +0.057 |
ilt | +0.057 |
Neg logit contributions | |
liners | -0.064 |
disguise | -0.062 |
DRAGON | -0.061 |
idth | -0.061 |
tails | -0.060 |
Token | or |
Token ID | 393 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
liners | +1.396 |
disguise | +1.323 |
DRAGON | +1.301 |
idth | +1.296 |
tails | +1.291 |
Neg logit contributions | |
ILCS | -1.797 |
illo | -1.745 |
ESA | -1.712 |
Fed | -1.693 |
ilt | -1.684 |
Token | 10 |
Token ID | 838 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ILCS | +0.500 |
illo | +0.484 |
ESA | +0.473 |
Fed | +0.469 |
ilt | +0.466 |
Neg logit contributions | |
liners | -0.393 |
disguise | -0.374 |
DRAGON | -0.367 |
idth | -0.366 |
tails | -0.364 |
Token | mg |
Token ID | 11296 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
liners | +1.292 |
disguise | +1.219 |
DRAGON | +1.194 |
idth | +1.190 |
tails | +1.183 |
Neg logit contributions | |
ILCS | -1.958 |
illo | -1.905 |
ESA | -1.865 |
Fed | -1.846 |
ilt | -1.840 |
Token | / |
Token ID | 14 |
Feature activation | +7.45e+00 |
Pos logit contributions | |
liners | +1.169 |
disguise | +1.115 |
DRAGON | +1.095 |
idth | +1.094 |
tails | +1.088 |
Neg logit contributions | |
ILCS | -1.271 |
illo | -1.229 |
ESA | -1.197 |
Fed | -1.184 |
ilt | -1.179 |
Token | kg |
Token ID | 10025 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
liners | +4.206 |
tails | +3.825 |
idth | +3.805 |
disguise | +3.792 |
DRAGON | +3.759 |
Neg logit contributions | |
ILCS | -6.082 |
illo | -5.839 |
ESA | -5.769 |
Fed | -5.704 |
ilt | -5.648 |
Token | ), |
Token ID | 828 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
liners | +2.287 |
disguise | +2.151 |
DRAGON | +2.130 |
tails | +2.085 |
idth | +2.084 |
Neg logit contributions | |
ILCS | -3.475 |
illo | -3.395 |
ESA | -3.352 |
Fed | -3.295 |
ilt | -3.287 |
Token | but |
Token ID | 475 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
liners | +0.434 |
disguise | +0.411 |
idth | +0.405 |
DRAGON | +0.402 |
tails | +0.401 |
Neg logit contributions | |
ILCS | -0.552 |
illo | -0.536 |
ESA | -0.521 |
Fed | -0.518 |
ilt | -0.515 |
Token | not |
Token ID | 407 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
liners | +0.380 |
disguise | +0.360 |
DRAGON | +0.353 |
idth | +0.353 |
tails | +0.350 |
Neg logit contributions | |
ILCS | -0.536 |
illo | -0.523 |
ESA | -0.510 |
Fed | -0.506 |
ilt | -0.504 |
Token | flu |
Token ID | 6562 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
liners | +0.353 |
disguise | +0.334 |
idth | +0.329 |
DRAGON | +0.328 |
tails | +0.326 |
Neg logit contributions | |
ILCS | -0.431 |
illo | -0.418 |
ESA | -0.407 |
Fed | -0.403 |
ilt | -0.401 |
Token | Bird |
Token ID | 42562 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ILCS | +0.817 |
illo | +0.789 |
ESA | +0.774 |
Fed | +0.764 |
ilt | +0.757 |
Neg logit contributions | |
liners | -0.851 |
disguise | -0.818 |
idth | -0.803 |
DRAGON | -0.803 |
tails | -0.796 |
Token | sey |
Token ID | 4397 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
ILCS | +0.825 |
illo | +0.798 |
ESA | +0.776 |
Fed | +0.766 |
ilt | +0.763 |
Neg logit contributions | |
liners | -0.904 |
disguise | -0.867 |
DRAGON | -0.854 |
idth | -0.853 |
tails | -0.845 |
Token | e |
Token ID | 68 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ILCS | +0.517 |
illo | +0.500 |
ESA | +0.485 |
Fed | +0.479 |
ilt | +0.477 |
Neg logit contributions | |
liners | -0.617 |
disguise | -0.593 |
DRAGON | -0.584 |
idth | -0.582 |
tails | -0.579 |
Token | view |
Token ID | 1570 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ILCS | +0.125 |
illo | +0.121 |
ESA | +0.118 |
Fed | +0.116 |
ilt | +0.116 |
Neg logit contributions | |
liners | -0.106 |
disguise | -0.100 |
DRAGON | -0.099 |
idth | -0.098 |
tails | -0.098 |
Token | of |
Token ID | 286 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ILCS | +0.917 |
illo | +0.889 |
ESA | +0.867 |
Fed | +0.857 |
ilt | +0.854 |
Neg logit contributions | |
liners | -0.751 |
disguise | -0.714 |
DRAGON | -0.701 |
idth | -0.699 |
tails | -0.696 |
Token | Brigham |
Token ID | 37434 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
liners | +0.666 |
disguise | +0.631 |
DRAGON | +0.616 |
idth | +0.613 |
tails | +0.608 |
Neg logit contributions | |
ILCS | -1.019 |
illo | -0.990 |
ESA | -0.969 |
Fed | -0.959 |
ilt | -0.955 |
Token | City |
Token ID | 2254 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
liners | +3.977 |
disguise | +3.839 |
DRAGON | +3.669 |
ROCK | +3.646 |
idth | +3.579 |
Neg logit contributions | |
ILCS | -6.169 |
ESA | -5.933 |
Fed | -5.903 |
illo | -5.845 |
ilt | -5.844 |
Token | , |
Token ID | 11 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
liners | +1.811 |
disguise | +1.745 |
DRAGON | +1.717 |
ROCK | +1.674 |
idth | +1.673 |
Neg logit contributions | |
ILCS | -2.252 |
illo | -2.179 |
ESA | -2.135 |
Fed | -2.121 |
ilt | -2.089 |
Token | Utah |
Token ID | 10202 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
liners | +2.595 |
disguise | +2.516 |
DRAGON | +2.468 |
ROCK | +2.400 |
tails | +2.381 |
Neg logit contributions | |
ILCS | -3.099 |
illo | -2.994 |
ESA | -2.928 |
Fed | -2.891 |
ilt | -2.856 |
Token | Date |
Token ID | 7536 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
liners | +1.579 |
disguise | +1.507 |
DRAGON | +1.486 |
idth | +1.456 |
tails | +1.450 |
Neg logit contributions | |
ILCS | -1.924 |
illo | -1.860 |
ESA | -1.824 |
Fed | -1.815 |
ilt | -1.794 |
Token | : |
Token ID | 25 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
ILCS | +1.175 |
illo | +1.141 |
ESA | +1.112 |
Fed | +1.100 |
ilt | +1.097 |
Neg logit contributions | |
liners | -0.976 |
disguise | -0.925 |
DRAGON | -0.911 |
idth | -0.906 |
tails | -0.906 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
liners | +0.078 |
disguise | +0.074 |
DRAGON | +0.073 |
idth | +0.073 |
tails | +0.072 |
Neg logit contributions | |
ILCS | -0.087 |
illo | -0.085 |
ESA | -0.082 |
Fed | -0.081 |
ilt | -0.081 |
Token | Because |
Token ID | 4362 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
liners | +0.194 |
disguise | +0.183 |
idth | +0.180 |
DRAGON | +0.178 |
tails | +0.178 |
Neg logit contributions | |
ILCS | -0.271 |
illo | -0.263 |
ESA | -0.257 |
Fed | -0.255 |
ilt | -0.253 |
Token | of |
Token ID | 286 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ILCS | +0.084 |
illo | +0.081 |
ESA | +0.079 |
Fed | +0.079 |
ilt | +0.079 |
Neg logit contributions | |
liners | -0.065 |
disguise | -0.062 |
idth | -0.061 |
tails | -0.060 |
DRAGON | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ILCS | +0.874 |
illo | +0.852 |
ESA | +0.827 |
Fed | +0.823 |
ilt | +0.820 |
Neg logit contributions | |
liners | -0.757 |
disguise | -0.712 |
idth | -0.703 |
tails | -0.703 |
DRAGON | -0.690 |
Token | T |
Token ID | 309 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
liners | +0.642 |
disguise | +0.607 |
DRAGON | +0.594 |
idth | +0.592 |
tails | +0.589 |
Neg logit contributions | |
ILCS | -0.935 |
illo | -0.908 |
ESA | -0.887 |
Fed | -0.878 |
ilt | -0.875 |
Token | & |
Token ID | 5 |
Feature activation | +7.34e+00 |
Pos logit contributions | |
ILCS | +0.174 |
illo | +0.169 |
ESA | +0.164 |
ilt | +0.161 |
Fed | +0.161 |
Neg logit contributions | |
liners | -0.206 |
disguise | -0.198 |
DRAGON | -0.194 |
idth | -0.194 |
tails | -0.193 |
Token | A |
Token ID | 32 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
liners | +4.881 |
DRAGON | +4.787 |
tails | +4.743 |
ROCK | +4.674 |
disguise | +4.637 |
Neg logit contributions | |
ILCS | -5.098 |
illo | -4.894 |
nard | -4.785 |
ilt | -4.701 |
ESA | -4.666 |
Token | , |
Token ID | 11 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
liners | +1.379 |
disguise | +1.319 |
DRAGON | +1.287 |
idth | +1.278 |
tails | +1.276 |
Neg logit contributions | |
ILCS | -1.796 |
illo | -1.740 |
ESA | -1.704 |
Fed | -1.680 |
ilt | -1.672 |
Token | this |
Token ID | 428 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
liners | +0.310 |
disguise | +0.293 |
idth | +0.288 |
DRAGON | +0.287 |
tails | +0.286 |
Neg logit contributions | |
ILCS | -0.411 |
illo | -0.399 |
ESA | -0.389 |
Fed | -0.386 |
ilt | -0.385 |
Token | title |
Token ID | 3670 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
liners | +0.832 |
disguise | +0.790 |
DRAGON | +0.776 |
idth | +0.771 |
tails | +0.767 |
Neg logit contributions | |
ILCS | -1.101 |
illo | -1.066 |
ESA | -1.043 |
Fed | -1.031 |
ilt | -1.026 |
Token | is |
Token ID | 318 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
ILCS | +0.859 |
illo | +0.841 |
ESA | +0.811 |
Fed | +0.808 |
ilt | +0.807 |
Neg logit contributions | |
liners | -0.759 |
disguise | -0.722 |
idth | -0.716 |
tails | -0.709 |
DRAGON | -0.708 |
Token | In |
Token ID | 818 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
liners | +0.886 |
disguise | +0.842 |
DRAGON | +0.831 |
tails | +0.828 |
idth | +0.827 |
Neg logit contributions | |
ILCS | -0.871 |
illo | -0.840 |
ESA | -0.811 |
ilt | -0.800 |
Fed | -0.799 |
Token | the |
Token ID | 262 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
ILCS | +0.210 |
illo | +0.204 |
ESA | +0.199 |
Fed | +0.197 |
ilt | +0.196 |
Neg logit contributions | |
liners | -0.163 |
disguise | -0.154 |
idth | -0.151 |
tails | -0.151 |
DRAGON | -0.151 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
liners | +0.348 |
disguise | +0.328 |
idth | +0.323 |
DRAGON | +0.321 |
tails | +0.321 |
Neg logit contributions | |
ILCS | -0.462 |
illo | -0.448 |
ESA | -0.438 |
Fed | -0.433 |
ilt | -0.433 |
Token | film |
Token ID | 2646 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
liners | +0.724 |
disguise | +0.684 |
DRAGON | +0.670 |
idth | +0.668 |
tails | +0.664 |
Neg logit contributions | |
ILCS | -1.079 |
illo | -1.048 |
ESA | -1.025 |
Fed | -1.015 |
ilt | -1.011 |
Token | The |
Token ID | 383 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ILCS | +1.133 |
illo | +1.099 |
ESA | +1.066 |
Fed | +1.061 |
ilt | +1.060 |
Neg logit contributions | |
liners | -0.907 |
disguise | -0.856 |
idth | -0.847 |
tails | -0.842 |
DRAGON | -0.836 |
Token | Secret |
Token ID | 3943 |
Feature activation | +7.30e+00 |
Pos logit contributions | |
liners | +1.196 |
disguise | +1.137 |
DRAGON | +1.118 |
idth | +1.111 |
tails | +1.106 |
Neg logit contributions | |
ILCS | -1.429 |
illo | -1.384 |
ESA | -1.352 |
Fed | -1.334 |
ilt | -1.329 |
Token | Life |
Token ID | 5155 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
liners | +3.536 |
disguise | +3.298 |
DRAGON | +3.242 |
idth | +3.141 |
atures | +3.094 |
Neg logit contributions | |
ILCS | -6.575 |
illo | -6.352 |
ESA | -6.350 |
Fed | -6.221 |
nard | -6.180 |
Token | of |
Token ID | 286 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
liners | +1.992 |
disguise | +1.896 |
DRAGON | +1.835 |
idth | +1.809 |
tails | +1.805 |
Neg logit contributions | |
ILCS | -2.991 |
illo | -2.880 |
ESA | -2.838 |
ilt | -2.798 |
nard | -2.795 |
Token | Walter |
Token ID | 15819 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
liners | +0.828 |
disguise | +0.787 |
DRAGON | +0.774 |
idth | +0.767 |
tails | +0.762 |
Neg logit contributions | |
ILCS | -1.158 |
illo | -1.122 |
ESA | -1.094 |
Fed | -1.082 |
ilt | -1.079 |
Token | M |
Token ID | 337 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
ILCS | +0.252 |
illo | +0.244 |
ESA | +0.238 |
Fed | +0.235 |
ilt | +0.234 |
Neg logit contributions | |
liners | -0.229 |
disguise | -0.218 |
DRAGON | -0.215 |
idth | -0.214 |
tails | -0.213 |
Token | itty |
Token ID | 9760 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ILCS | +2.232 |
illo | +2.182 |
ESA | +2.115 |
ilt | +2.103 |
nard | +2.065 |
Neg logit contributions | |
liners | -2.273 |
disguise | -2.196 |
DRAGON | -2.159 |
tails | -2.116 |
idth | -2.099 |
Token | as |
Token ID | 355 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
liners | +0.835 |
disguise | +0.795 |
DRAGON | +0.779 |
tails | +0.767 |
idth | +0.767 |
Neg logit contributions | |
ILCS | -1.099 |
illo | -1.065 |
ESA | -1.041 |
Fed | -1.029 |
ilt | -1.022 |
Token | if |
Token ID | 611 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ILCS | +0.076 |
illo | +0.074 |
ESA | +0.072 |
ilt | +0.071 |
Fed | +0.071 |
Neg logit contributions | |
liners | -0.060 |
disguise | -0.057 |
idth | -0.056 |
tails | -0.056 |
DRAGON | -0.056 |
Token | that |
Token ID | 326 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
liners | +0.803 |
disguise | +0.765 |
DRAGON | +0.749 |
idth | +0.742 |
tails | +0.740 |
Neg logit contributions | |
ILCS | -1.037 |
illo | -1.004 |
ESA | -0.980 |
Fed | -0.969 |
ilt | -0.966 |
Token | wasn |
Token ID | 2492 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
liners | +0.657 |
disguise | +0.614 |
idth | +0.612 |
tails | +0.607 |
DRAGON | +0.607 |
Neg logit contributions | |
ILCS | -0.959 |
illo | -0.936 |
ESA | -0.915 |
Fed | -0.905 |
ilt | -0.902 |
Token | 't |
Token ID | 470 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
liners | +1.551 |
disguise | +1.450 |
tails | +1.421 |
DRAGON | +1.408 |
idth | +1.380 |
Neg logit contributions | |
ILCS | -2.245 |
illo | -2.136 |
ESA | -2.090 |
ilt | -2.061 |
Fed | -2.059 |
Token | enough |
Token ID | 1576 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
liners | +1.925 |
disguise | +1.842 |
DRAGON | +1.776 |
tails | +1.749 |
idth | +1.738 |
Neg logit contributions | |
ILCS | -3.298 |
illo | -3.183 |
ESA | -3.110 |
Fed | -3.101 |
ilt | -3.091 |
Token | to |
Token ID | 284 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
liners | +4.142 |
disguise | +4.025 |
DRAGON | +3.812 |
tails | +3.735 |
idth | +3.717 |
Neg logit contributions | |
ILCS | -5.613 |
illo | -5.363 |
ilt | -5.273 |
Fed | -5.259 |
ESA | -5.208 |
Token | tick |
Token ID | 4378 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
liners | +1.523 |
disguise | +1.475 |
DRAGON | +1.419 |
idth | +1.402 |
tails | +1.401 |
Neg logit contributions | |
ILCS | -1.945 |
illo | -1.873 |
ESA | -1.829 |
Fed | -1.813 |
ilt | -1.795 |
Token | le |
Token ID | 293 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
liners | +0.520 |
disguise | +0.493 |
DRAGON | +0.484 |
idth | +0.483 |
tails | +0.480 |
Neg logit contributions | |
ILCS | -0.677 |
illo | -0.657 |
ESA | -0.641 |
Fed | -0.635 |
ilt | -0.633 |
Token | God |
Token ID | 1793 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
liners | +1.276 |
disguise | +1.216 |
DRAGON | +1.193 |
idth | +1.178 |
tails | +1.173 |
Neg logit contributions | |
ILCS | -1.616 |
illo | -1.562 |
ESA | -1.529 |
Fed | -1.511 |
ilt | -1.504 |
Token | 's |
Token ID | 338 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
liners | +0.445 |
disguise | +0.423 |
DRAGON | +0.415 |
idth | +0.413 |
tails | +0.411 |
Neg logit contributions | |
ILCS | -0.525 |
illo | -0.508 |
ESA | -0.497 |
Fed | -0.490 |
ilt | -0.488 |
Token | for |
Token ID | 329 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
liners | +0.207 |
disguise | +0.196 |
DRAGON | +0.193 |
idth | +0.193 |
tails | +0.192 |
Neg logit contributions | |
ILCS | -0.229 |
illo | -0.222 |
ESA | -0.216 |
Fed | -0.213 |
ilt | -0.213 |
Token | ( |
Token ID | 7 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
ILCS | +0.197 |
illo | +0.191 |
ESA | +0.186 |
Fed | +0.184 |
ilt | +0.183 |
Neg logit contributions | |
liners | -0.190 |
disguise | -0.181 |
DRAGON | -0.178 |
idth | -0.178 |
tails | -0.177 |
Token | size |
Token ID | 2546 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ILCS | +1.360 |
illo | +1.306 |
ilt | +1.266 |
ESA | +1.260 |
Fed | +1.254 |
Neg logit contributions | |
liners | -1.285 |
disguise | -1.225 |
DRAGON | -1.219 |
idth | -1.196 |
tails | -1.192 |
Token | _ |
Token ID | 62 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
liners | +0.966 |
disguise | +0.926 |
DRAGON | +0.910 |
idth | +0.910 |
tails | +0.903 |
Neg logit contributions | |
ILCS | -0.857 |
illo | -0.831 |
ESA | -0.809 |
Fed | -0.796 |
ilt | -0.794 |
Token | t |
Token ID | 83 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
liners | +0.638 |
disguise | +0.605 |
DRAGON | +0.594 |
idth | +0.589 |
tails | +0.584 |
Neg logit contributions | |
ILCS | -0.935 |
illo | -0.909 |
ESA | -0.888 |
Fed | -0.881 |
ilt | -0.878 |
Token | u |
Token ID | 334 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
liners | +0.877 |
disguise | +0.829 |
DRAGON | +0.815 |
tails | +0.811 |
idth | +0.809 |
Neg logit contributions | |
ILCS | -1.164 |
illo | -1.127 |
ESA | -1.096 |
ilt | -1.088 |
Fed | -1.085 |
Token | Part |
Token ID | 7841 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
liners | +3.566 |
idth | +3.377 |
disguise | +3.341 |
DRAGON | +3.221 |
tails | +3.217 |
Neg logit contributions | |
ILCS | -6.041 |
illo | -5.881 |
ESA | -5.788 |
Fed | -5.751 |
nard | -5.621 |
Token | icle |
Token ID | 1548 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
liners | +0.722 |
disguise | +0.674 |
DRAGON | +0.660 |
idth | +0.651 |
tails | +0.648 |
Neg logit contributions | |
ILCS | -1.526 |
illo | -1.491 |
ESA | -1.458 |
Fed | -1.448 |
ilt | -1.442 |
Token | = |
Token ID | 796 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
liners | +2.310 |
disguise | +2.215 |
idth | +2.172 |
DRAGON | +2.161 |
tails | +2.149 |
Neg logit contributions | |
ILCS | -2.489 |
illo | -2.409 |
ESA | -2.343 |
Fed | -2.313 |
ilt | -2.304 |
Token | 0 |
Token ID | 657 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
ILCS | +0.666 |
illo | +0.645 |
ESA | +0.625 |
ilt | +0.623 |
nard | +0.618 |
Neg logit contributions | |
liners | -0.533 |
disguise | -0.505 |
DRAGON | -0.497 |
idth | -0.496 |
tails | -0.494 |
Token | ; |
Token ID | 2162 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ILCS | +0.593 |
illo | +0.577 |
ESA | +0.564 |
Fed | +0.558 |
ilt | +0.558 |
Neg logit contributions | |
liners | -0.345 |
disguise | -0.323 |
DRAGON | -0.318 |
idth | -0.314 |
tails | -0.313 |
Token | twitter |
Token ID | 6956 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
liners | +0.570 |
disguise | +0.518 |
tails | +0.511 |
DRAGON | +0.502 |
idth | +0.500 |
Neg logit contributions | |
ILCS | -1.267 |
illo | -1.230 |
ESA | -1.210 |
Fed | -1.196 |
ilt | -1.194 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
liners | +1.229 |
disguise | +1.149 |
tails | +1.135 |
DRAGON | +1.135 |
idth | +1.110 |
Neg logit contributions | |
ILCS | -1.456 |
illo | -1.394 |
ESA | -1.362 |
ilt | -1.340 |
Fed | -1.336 |
Token | com |
Token ID | 785 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
liners | +1.138 |
disguise | +1.068 |
tails | +1.065 |
DRAGON | +1.050 |
idth | +1.040 |
Neg logit contributions | |
ILCS | -1.252 |
illo | -1.193 |
ESA | -1.172 |
Fed | -1.150 |
ilt | -1.147 |
Token | / |
Token ID | 14 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
liners | +0.778 |
disguise | +0.738 |
DRAGON | +0.727 |
tails | +0.725 |
idth | +0.714 |
Neg logit contributions | |
ILCS | -0.822 |
illo | -0.789 |
ESA | -0.770 |
Fed | -0.756 |
ilt | -0.755 |
Token | Eh |
Token ID | 43894 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
liners | +3.033 |
tails | +2.853 |
idth | +2.838 |
disguise | +2.838 |
DRAGON | +2.798 |
Neg logit contributions | |
ILCS | -3.044 |
illo | -2.898 |
ESA | -2.780 |
ilt | -2.737 |
Fed | -2.735 |
Token | U |
Token ID | 52 |
Feature activation | +6.95e+00 |
Pos logit contributions | |
liners | +3.581 |
tails | +3.369 |
idth | +3.350 |
disguise | +3.338 |
DRAGON | +3.285 |
Neg logit contributions | |
ILCS | -3.526 |
illo | -3.330 |
ESA | -3.183 |
Irma | -3.145 |
nard | -3.143 |
Token | g |
Token ID | 70 |
Feature activation | +6.51e+00 |
Pos logit contributions | |
liners | +4.670 |
tails | +4.410 |
idth | +4.376 |
disguise | +4.326 |
atures | +4.246 |
Neg logit contributions | |
ILCS | -4.995 |
illo | -4.641 |
Irma | -4.469 |
ESA | -4.439 |
nard | -4.424 |
Token | I |
Token ID | 40 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
liners | +4.574 |
tails | +4.305 |
idth | +4.301 |
disguise | +4.230 |
DRAGON | +4.179 |
Neg logit contributions | |
ILCS | -4.445 |
illo | -4.146 |
Irma | -3.976 |
ESA | -3.953 |
nard | -3.915 |
Token | x |
Token ID | 87 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
liners | +3.418 |
tails | +3.215 |
disguise | +3.206 |
idth | +3.205 |
DRAGON | +3.141 |
Neg logit contributions | |
ILCS | -3.670 |
illo | -3.455 |
ESA | -3.345 |
nard | -3.295 |
Fed | -3.293 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
liners | +2.872 |
tails | +2.695 |
disguise | +2.693 |
idth | +2.687 |
DRAGON | +2.651 |
Neg logit contributions | |
ILCS | -2.791 |
illo | -2.644 |
ESA | -2.542 |
ilt | -2.503 |
nard | -2.499 |
Token | N |
Token ID | 45 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
liners | +2.396 |
disguise | +2.251 |
tails | +2.247 |
idth | +2.239 |
DRAGON | +2.220 |
Neg logit contributions | |
ILCS | -2.373 |
illo | -2.265 |
ESA | -2.181 |
ilt | -2.152 |
Fed | -2.149 |
Token | Country |
Token ID | 12946 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ILCS | +0.352 |
illo | +0.341 |
ESA | +0.333 |
Fed | +0.329 |
ilt | +0.327 |
Neg logit contributions | |
liners | -0.279 |
disguise | -0.266 |
idth | -0.260 |
DRAGON | -0.258 |
tails | -0.258 |
Token | Result |
Token ID | 25414 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
liners | +0.992 |
disguise | +0.941 |
DRAGON | +0.924 |
idth | +0.922 |
tails | +0.917 |
Neg logit contributions | |
ILCS | -1.214 |
illo | -1.175 |
ESA | -1.147 |
Fed | -1.135 |
ilt | -1.131 |
Token | Name |
Token ID | 6530 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
liners | +0.899 |
disguise | +0.853 |
DRAGON | +0.839 |
idth | +0.836 |
tails | +0.834 |
Neg logit contributions | |
ILCS | -1.076 |
illo | -1.041 |
ESA | -1.019 |
Fed | -1.007 |
ilt | -1.003 |
Token | Team |
Token ID | 4816 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
liners | +1.246 |
disguise | +1.180 |
DRAGON | +1.163 |
idth | +1.155 |
tails | +1.153 |
Neg logit contributions | |
ILCS | -1.465 |
illo | -1.418 |
ESA | -1.387 |
Fed | -1.372 |
ilt | -1.366 |
Token | Time |
Token ID | 3862 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
liners | +2.209 |
disguise | +2.084 |
DRAGON | +2.052 |
tails | +2.031 |
idth | +2.020 |
Neg logit contributions | |
ILCS | -3.174 |
illo | -3.075 |
ESA | -3.020 |
Fed | -2.989 |
ilt | -2.966 |
Token | GER |
Token ID | 44186 |
Feature activation | +6.95e+00 |
Pos logit contributions | |
liners | +2.022 |
disguise | +1.922 |
DRAGON | +1.895 |
idth | +1.885 |
tails | +1.876 |
Neg logit contributions | |
ILCS | -2.308 |
illo | -2.228 |
ESA | -2.185 |
Fed | -2.150 |
ilt | -2.146 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
liners | +4.574 |
disguise | +4.377 |
DRAGON | +4.358 |
tails | +4.305 |
ROCK | +4.298 |
Neg logit contributions | |
ILCS | -5.008 |
illo | -4.799 |
ESA | -4.629 |
ilt | -4.611 |
nard | -4.593 |
Token | Andre |
Token ID | 10948 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
liners | +1.548 |
disguise | +1.473 |
DRAGON | +1.453 |
idth | +1.439 |
tails | +1.436 |
Neg logit contributions | |
ILCS | -1.806 |
illo | -1.746 |
ESA | -1.702 |
ilt | -1.680 |
Fed | -1.677 |
Token | Gre |
Token ID | 11955 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
liners | +0.288 |
disguise | +0.278 |
DRAGON | +0.273 |
idth | +0.272 |
tails | +0.270 |
Neg logit contributions | |
ILCS | -0.256 |
illo | -0.252 |
ESA | -0.241 |
ilt | -0.238 |
Fed | -0.237 |
Token | ipel |
Token ID | 40634 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
liners | +1.222 |
disguise | +1.140 |
idth | +1.125 |
tails | +1.107 |
DRAGON | +1.107 |
Neg logit contributions | |
ILCS | -1.889 |
ESA | -1.817 |
illo | -1.813 |
Fed | -1.784 |
nard | -1.753 |
Token | ( |
Token ID | 357 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
liners | +0.301 |
disguise | +0.286 |
idth | +0.282 |
DRAGON | +0.279 |
tails | +0.279 |
Neg logit contributions | |
ILCS | -0.349 |
illo | -0.339 |
ESA | -0.329 |
Fed | -0.326 |
ilt | -0.325 |
Token | t |
Token ID | 83 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
liners | +1.022 |
tails | +0.937 |
disguise | +0.936 |
idth | +0.922 |
DRAGON | +0.906 |
Neg logit contributions | |
ILCS | -1.686 |
illo | -1.618 |
ESA | -1.597 |
Fed | -1.572 |
ilt | -1.560 |
Token | . |
Token ID | 13 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
liners | +0.077 |
disguise | +0.073 |
DRAGON | +0.072 |
tails | +0.072 |
idth | +0.071 |
Neg logit contributions | |
ILCS | -0.083 |
illo | -0.079 |
ESA | -0.077 |
Fed | -0.076 |
ilt | -0.076 |
Token | co |
Token ID | 1073 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
liners | +1.095 |
tails | +0.972 |
disguise | +0.956 |
idth | +0.935 |
DRAGON | +0.917 |
Neg logit contributions | |
ILCS | -2.799 |
ESA | -2.680 |
illo | -2.679 |
Fed | -2.634 |
ilt | -2.614 |
Token | / |
Token ID | 14 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
liners | +0.572 |
disguise | +0.542 |
tails | +0.533 |
DRAGON | +0.532 |
idth | +0.527 |
Neg logit contributions | |
ILCS | -0.599 |
illo | -0.572 |
ESA | -0.560 |
Fed | -0.548 |
ilt | -0.547 |
Token | l |
Token ID | 75 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
liners | +3.570 |
tails | +3.362 |
idth | +3.339 |
disguise | +3.324 |
DRAGON | +3.278 |
Neg logit contributions | |
ILCS | -3.616 |
illo | -3.429 |
ESA | -3.286 |
Irma | -3.240 |
ilt | -3.236 |
Token | g |
Token ID | 70 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
liners | +3.776 |
idth | +3.543 |
tails | +3.542 |
disguise | +3.513 |
DRAGON | +3.467 |
Neg logit contributions | |
ILCS | -3.748 |
illo | -3.537 |
ESA | -3.389 |
Irma | -3.357 |
nard | -3.347 |
Token | S |
Token ID | 50 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
liners | +4.840 |
tails | +4.566 |
idth | +4.565 |
disguise | +4.477 |
DRAGON | +4.432 |
Neg logit contributions | |
ILCS | -4.703 |
illo | -4.389 |
Irma | -4.211 |
ESA | -4.199 |
nard | -4.166 |
Token | wh |
Token ID | 1929 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
liners | +3.519 |
idth | +3.311 |
tails | +3.307 |
disguise | +3.277 |
DRAGON | +3.221 |
Neg logit contributions | |
ILCS | -3.575 |
illo | -3.358 |
ESA | -3.238 |
Fed | -3.193 |
nard | -3.188 |
Token | X |
Token ID | 55 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
liners | +4.162 |
tails | +3.927 |
idth | +3.904 |
disguise | +3.874 |
DRAGON | +3.822 |
Neg logit contributions | |
ILCS | -4.122 |
illo | -3.880 |
ESA | -3.706 |
Irma | -3.696 |
nard | -3.665 |
Token | Um |
Token ID | 37280 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
liners | +2.234 |
disguise | +2.103 |
tails | +2.095 |
idth | +2.087 |
DRAGON | +2.069 |
Neg logit contributions | |
ILCS | -2.259 |
illo | -2.152 |
ESA | -2.077 |
ilt | -2.048 |
Fed | -2.047 |
Token | ek |
Token ID | 988 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
liners | +3.590 |
tails | +3.367 |
disguise | +3.361 |
idth | +3.359 |
DRAGON | +3.314 |
Neg logit contributions | |
ILCS | -3.490 |
illo | -3.297 |
ESA | -3.170 |
nard | -3.132 |
ilt | -3.122 |
Token | = |
Token ID | 796 |
Feature activation | +4.86e-03 |
Pos logit contributions | |
liners | +1.496 |
disguise | +1.415 |
DRAGON | +1.388 |
idth | +1.387 |
tails | +1.368 |
Neg logit contributions | |
ILCS | -2.296 |
illo | -2.234 |
ESA | -2.177 |
Fed | -2.147 |
ilt | -2.147 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
liners | +0.003 |
disguise | +0.003 |
idth | +0.003 |
DRAGON | +0.003 |
tails | +0.003 |
Neg logit contributions | |
ILCS | -0.004 |
illo | -0.004 |
ESA | -0.003 |
ilt | -0.003 |
Fed | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
liners | +1.439 |
disguise | +1.376 |
idth | +1.344 |
DRAGON | +1.344 |
tails | +1.343 |
Neg logit contributions | |
ILCS | -1.450 |
illo | -1.398 |
ESA | -1.361 |
Fed | -1.347 |
ilt | -1.338 |
Token | 0 |
Token ID | 15 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
liners | +1.615 |
disguise | +1.540 |
idth | +1.503 |
tails | +1.498 |
DRAGON | +1.494 |
Neg logit contributions | |
ILCS | -2.029 |
illo | -1.945 |
ESA | -1.916 |
Fed | -1.887 |
ilt | -1.875 |
Token | f |
Token ID | 69 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
liners | +1.001 |
disguise | +0.959 |
idth | +0.943 |
DRAGON | +0.942 |
tails | +0.939 |
Neg logit contributions | |
ILCS | -0.868 |
illo | -0.834 |
ESA | -0.810 |
Fed | -0.800 |
ilt | -0.796 |
Token | / |
Token ID | 1220 |
Feature activation | +6.86e+00 |
Pos logit contributions | |
liners | +0.415 |
disguise | +0.392 |
DRAGON | +0.384 |
idth | +0.383 |
tails | +0.380 |
Neg logit contributions | |
ILCS | -0.610 |
illo | -0.593 |
ESA | -0.579 |
Fed | -0.574 |
ilt | -0.572 |
Token | density |
Token ID | 12109 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
liners | +3.891 |
disguise | +3.722 |
DRAGON | +3.603 |
ROCK | +3.573 |
idth | +3.563 |
Neg logit contributions | |
ILCS | -5.540 |
illo | -5.342 |
ESA | -5.267 |
Fed | -5.253 |
ilt | -5.112 |
Token | Grid |
Token ID | 41339 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
liners | +3.272 |
disguise | +3.078 |
idth | +3.077 |
DRAGON | +3.062 |
tails | +3.021 |
Neg logit contributions | |
ILCS | -3.428 |
illo | -3.292 |
ESA | -3.236 |
Fed | -3.154 |
ilt | -3.144 |
Token | . |
Token ID | 13 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
liners | +1.126 |
disguise | +1.075 |
DRAGON | +1.056 |
idth | +1.055 |
tails | +1.046 |
Neg logit contributions | |
ILCS | -1.179 |
illo | -1.139 |
ESA | -1.111 |
Fed | -1.097 |
ilt | -1.089 |
Token | Get |
Token ID | 3855 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
liners | +0.738 |
disguise | +0.707 |
DRAGON | +0.696 |
idth | +0.694 |
tails | +0.691 |
Neg logit contributions | |
ILCS | -0.658 |
illo | -0.635 |
ESA | -0.617 |
Fed | -0.610 |
ilt | -0.607 |
Token | Cell |
Token ID | 28780 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ILCS | +2.017 |
illo | +1.956 |
ESA | +1.921 |
Fed | +1.912 |
ilt | +1.891 |
Neg logit contributions | |
liners | -1.614 |
disguise | -1.545 |
idth | -1.514 |
DRAGON | -1.510 |
tails | -1.491 |
Token | also |
Token ID | 635 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
liners | +0.591 |
disguise | +0.562 |
DRAGON | +0.549 |
idth | +0.547 |
tails | +0.545 |
Neg logit contributions | |
ILCS | -0.742 |
illo | -0.719 |
ESA | -0.702 |
Fed | -0.695 |
ilt | -0.691 |
Token | performs |
Token ID | 17706 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
liners | +0.414 |
disguise | +0.395 |
DRAGON | +0.388 |
idth | +0.387 |
tails | +0.385 |
Neg logit contributions | |
ILCS | -0.451 |
illo | -0.436 |
ESA | -0.425 |
Fed | -0.420 |
ilt | -0.418 |
Token | " |
Token ID | 366 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
liners | +1.380 |
disguise | +1.319 |
DRAGON | +1.289 |
idth | +1.269 |
tails | +1.268 |
Neg logit contributions | |
ILCS | -1.867 |
illo | -1.807 |
ESA | -1.777 |
Fed | -1.752 |
ilt | -1.742 |
Token | Sm |
Token ID | 7556 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
liners | +0.460 |
disguise | +0.439 |
DRAGON | +0.432 |
idth | +0.431 |
tails | +0.430 |
Neg logit contributions | |
ILCS | -0.455 |
illo | -0.440 |
ESA | -0.427 |
Fed | -0.421 |
ilt | -0.421 |
Token | ells |
Token ID | 19187 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ILCS | +0.040 |
illo | +0.039 |
ESA | +0.038 |
Fed | +0.037 |
ilt | +0.037 |
Neg logit contributions | |
liners | -0.045 |
disguise | -0.043 |
DRAGON | -0.042 |
idth | -0.042 |
tails | -0.042 |
Token | Like |
Token ID | 4525 |
Feature activation | +6.84e+00 |
Pos logit contributions | |
liners | +2.084 |
disguise | +1.995 |
DRAGON | +1.972 |
tails | +1.950 |
idth | +1.944 |
Neg logit contributions | |
ILCS | -1.778 |
illo | -1.692 |
ESA | -1.668 |
Fed | -1.635 |
ilt | -1.618 |
Token | Teen |
Token ID | 21432 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
liners | +3.575 |
ROCK | +3.467 |
DRAGON | +3.427 |
disguise | +3.333 |
Patron | +3.274 |
Neg logit contributions | |
ILCS | -5.851 |
ESA | -5.726 |
illo | -5.600 |
Fed | -5.540 |
ilt | -5.430 |
Token | Spirit |
Token ID | 7710 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
liners | +0.227 |
disguise | +0.209 |
idth | +0.206 |
DRAGON | +0.203 |
tails | +0.198 |
Neg logit contributions | |
ILCS | -0.513 |
illo | -0.504 |
ESA | -0.490 |
ilt | -0.489 |
Fed | -0.486 |
Token | " |
Token ID | 1 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
liners | +0.141 |
disguise | +0.134 |
idth | +0.132 |
DRAGON | +0.131 |
tails | +0.130 |
Neg logit contributions | |
ILCS | -0.169 |
illo | -0.165 |
ESA | -0.159 |
Fed | -0.158 |
ilt | -0.158 |
Token | in |
Token ID | 287 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ILCS | +0.858 |
illo | +0.837 |
ESA | +0.810 |
Fed | +0.808 |
ilt | +0.804 |
Neg logit contributions | |
liners | -0.684 |
idth | -0.648 |
disguise | -0.643 |
DRAGON | -0.640 |
tails | -0.637 |
Token | a |
Token ID | 257 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ILCS | +0.823 |
illo | +0.801 |
ESA | +0.775 |
ilt | +0.771 |
Fed | +0.771 |
Neg logit contributions | |
liners | -0.650 |
idth | -0.609 |
tails | -0.603 |
DRAGON | -0.601 |
disguise | -0.596 |
Token | > |
Token ID | 1875 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
liners | +1.387 |
disguise | +1.309 |
idth | +1.274 |
DRAGON | +1.269 |
tails | +1.259 |
Neg logit contributions | |
ILCS | -2.419 |
illo | -2.350 |
ESA | -2.302 |
Fed | -2.279 |
nard | -2.259 |
Token | ( |
Token ID | 357 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
liners | +1.024 |
disguise | +0.976 |
DRAGON | +0.958 |
idth | +0.954 |
tails | +0.952 |
Neg logit contributions | |
ILCS | -1.162 |
illo | -1.120 |
ESA | -1.093 |
Fed | -1.081 |
ilt | -1.075 |
Token | & |
Token ID | 1222 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
liners | +0.140 |
disguise | +0.132 |
DRAGON | +0.130 |
idth | +0.130 |
tails | +0.128 |
Neg logit contributions | |
ILCS | -0.187 |
illo | -0.183 |
ESA | -0.177 |
ilt | -0.176 |
Fed | -0.176 |
Token | self |
Token ID | 2116 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
liners | +1.800 |
disguise | +1.734 |
tails | +1.672 |
DRAGON | +1.657 |
idth | +1.638 |
Neg logit contributions | |
ILCS | -3.197 |
illo | -3.067 |
ESA | -3.054 |
nard | -2.992 |
ilt | -2.981 |
Token | , |
Token ID | 837 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
liners | +2.385 |
disguise | +2.317 |
idth | +2.219 |
tails | +2.218 |
DRAGON | +2.139 |
Neg logit contributions | |
ILCS | -5.901 |
illo | -5.710 |
ESA | -5.635 |
Fed | -5.546 |
nard | -5.508 |
Token | ord |
Token ID | 2760 |
Feature activation | +6.81e+00 |
Pos logit contributions | |
ILCS | +0.416 |
illo | +0.404 |
ESA | +0.390 |
Fed | +0.388 |
ilt | +0.388 |
Neg logit contributions | |
liners | -0.341 |
disguise | -0.322 |
idth | -0.319 |
DRAGON | -0.317 |
tails | -0.315 |
Token | : |
Token ID | 1058 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
liners | +3.573 |
disguise | +3.404 |
idth | +3.294 |
DRAGON | +3.234 |
tails | +3.203 |
Neg logit contributions | |
ILCS | -5.921 |
illo | -5.667 |
ESA | -5.655 |
Fed | -5.540 |
nard | -5.487 |
Token | Order |
Token ID | 8284 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
liners | +1.952 |
disguise | +1.873 |
DRAGON | +1.827 |
tails | +1.802 |
idth | +1.802 |
Neg logit contributions | |
ILCS | -2.673 |
illo | -2.599 |
ESA | -2.557 |
Fed | -2.520 |
ilt | -2.505 |
Token | ing |
Token ID | 278 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
liners | +1.785 |
disguise | +1.700 |
idth | +1.654 |
tails | +1.649 |
DRAGON | +1.637 |
Neg logit contributions | |
ILCS | -2.287 |
illo | -2.208 |
ESA | -2.182 |
ilt | -2.118 |
nard | -2.113 |
Token | , |
Token ID | 837 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
liners | +0.827 |
disguise | +0.790 |
DRAGON | +0.770 |
idth | +0.768 |
tails | +0.766 |
Neg logit contributions | |
ILCS | -1.030 |
illo | -1.000 |
ESA | -0.977 |
Fed | -0.962 |
ilt | -0.959 |
Token | _ |
Token ID | 4808 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
liners | +1.144 |
disguise | +1.092 |
DRAGON | +1.069 |
idth | +1.065 |
tails | +1.060 |
Neg logit contributions | |
ILCS | -1.330 |
illo | -1.287 |
ESA | -1.259 |
Fed | -1.243 |
ilt | -1.237 |
Token | an |
Token ID | 281 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
liners | +1.174 |
disguise | +1.113 |
DRAGON | +1.094 |
idth | +1.086 |
tails | +1.081 |
Neg logit contributions | |
ILCS | -1.573 |
illo | -1.524 |
ESA | -1.492 |
Fed | -1.473 |
ilt | -1.469 |
Token | EP |
Token ID | 14724 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
liners | +1.663 |
disguise | +1.583 |
DRAGON | +1.561 |
tails | +1.534 |
idth | +1.531 |
Neg logit contributions | |
ILCS | -1.971 |
illo | -1.902 |
ESA | -1.880 |
Fed | -1.849 |
ilt | -1.844 |
Token | called |
Token ID | 1444 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
liners | +0.050 |
disguise | +0.048 |
DRAGON | +0.047 |
idth | +0.047 |
tails | +0.047 |
Neg logit contributions | |
ILCS | -0.059 |
illo | -0.058 |
ESA | -0.056 |
Fed | -0.055 |
ilt | -0.055 |
Token | You |
Token ID | 921 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
liners | +1.491 |
disguise | +1.421 |
DRAGON | +1.407 |
idth | +1.384 |
tails | +1.382 |
Neg logit contributions | |
ILCS | -1.756 |
illo | -1.699 |
ESA | -1.668 |
Fed | -1.639 |
ilt | -1.636 |
Token | Look |
Token ID | 6803 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
liners | +0.681 |
disguise | +0.645 |
DRAGON | +0.635 |
idth | +0.632 |
tails | +0.628 |
Neg logit contributions | |
ILCS | -0.882 |
illo | -0.855 |
ESA | -0.835 |
Fed | -0.824 |
ilt | -0.822 |
Token | Like |
Token ID | 4525 |
Feature activation | +6.76e+00 |
Pos logit contributions | |
liners | +1.610 |
disguise | +1.523 |
DRAGON | +1.509 |
tails | +1.494 |
idth | +1.493 |
Neg logit contributions | |
ILCS | -1.840 |
illo | -1.779 |
ESA | -1.742 |
ilt | -1.712 |
Fed | -1.711 |
Token | an |
Token ID | 281 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
liners | +4.018 |
DRAGON | +3.905 |
ROCK | +3.830 |
disguise | +3.799 |
idth | +3.730 |
Neg logit contributions | |
ILCS | -5.250 |
ESA | -5.072 |
illo | -5.044 |
ilt | -4.910 |
Fed | -4.904 |
Token | Id |
Token ID | 5121 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
liners | +0.701 |
disguise | +0.668 |
DRAGON | +0.663 |
idth | +0.654 |
tails | +0.650 |
Neg logit contributions | |
ILCS | -0.808 |
illo | -0.782 |
ESA | -0.770 |
Fed | -0.758 |
ilt | -0.755 |
Token | iot |
Token ID | 5151 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
ILCS | +0.381 |
illo | +0.371 |
ESA | +0.359 |
Fed | +0.356 |
ilt | +0.356 |
Neg logit contributions | |
liners | -0.329 |
disguise | -0.313 |
DRAGON | -0.308 |
tails | -0.307 |
idth | -0.307 |
Token | and |
Token ID | 290 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
ILCS | +0.029 |
illo | +0.029 |
ESA | +0.028 |
Fed | +0.028 |
ilt | +0.027 |
Neg logit contributions | |
liners | -0.025 |
disguise | -0.024 |
idth | -0.024 |
DRAGON | -0.024 |
tails | -0.024 |
Token | Your |
Token ID | 3406 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
liners | +0.054 |
disguise | +0.051 |
idth | +0.051 |
DRAGON | +0.050 |
tails | +0.050 |
Neg logit contributions | |
ILCS | -0.069 |
illo | -0.067 |
ESA | -0.065 |
Fed | -0.064 |
ilt | -0.064 |
Token | first |
Token ID | 717 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
liners | +0.609 |
disguise | +0.569 |
idth | +0.561 |
DRAGON | +0.560 |
tails | +0.554 |
Neg logit contributions | |
ILCS | -1.064 |
illo | -1.039 |
ESA | -1.017 |
Fed | -1.009 |
ilt | -1.004 |
Token | received |
Token ID | 2722 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
ILCS | +0.735 |
illo | +0.720 |
ESA | +0.710 |
Fed | +0.703 |
ilt | +0.695 |
Neg logit contributions | |
liners | -0.400 |
idth | -0.372 |
disguise | -0.371 |
DRAGON | -0.369 |
tails | -0.362 |
Token | 4 |
Token ID | 604 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
ILCS | +0.172 |
illo | +0.167 |
ESA | +0.164 |
Fed | +0.162 |
ilt | +0.161 |
Neg logit contributions | |
liners | -0.142 |
disguise | -0.134 |
idth | -0.133 |
DRAGON | -0.132 |
tails | -0.131 |
Token | weeks |
Token ID | 2745 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
liners | +0.550 |
disguise | +0.522 |
DRAGON | +0.512 |
idth | +0.511 |
tails | +0.509 |
Neg logit contributions | |
ILCS | -0.700 |
illo | -0.678 |
ESA | -0.662 |
Fed | -0.655 |
ilt | -0.653 |
Token | of |
Token ID | 286 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
liners | +0.230 |
disguise | +0.219 |
DRAGON | +0.215 |
idth | +0.214 |
tails | +0.213 |
Neg logit contributions | |
ILCS | -0.286 |
illo | -0.277 |
ESA | -0.270 |
Fed | -0.267 |
ilt | -0.266 |
Token | sham |
Token ID | 23565 |
Feature activation | +6.72e+00 |
Pos logit contributions | |
liners | +0.759 |
disguise | +0.729 |
DRAGON | +0.715 |
idth | +0.707 |
tails | +0.707 |
Neg logit contributions | |
ILCS | -0.855 |
illo | -0.824 |
ESA | -0.801 |
Fed | -0.792 |
ilt | -0.789 |
Token | ta |
Token ID | 20486 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
liners | +4.327 |
disguise | +4.196 |
tails | +4.132 |
DRAGON | +4.036 |
idth | +3.978 |
Neg logit contributions | |
ILCS | -5.090 |
illo | -4.795 |
Fed | -4.585 |
ESA | -4.582 |
nard | -4.549 |
Token | V |
Token ID | 53 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
liners | +0.168 |
disguise | +0.162 |
DRAGON | +0.160 |
idth | +0.160 |
tails | +0.159 |
Neg logit contributions | |
ILCS | -0.114 |
illo | -0.109 |
ESA | -0.105 |
Fed | -0.103 |
ilt | -0.102 |
Token | NS |
Token ID | 8035 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
liners | +1.246 |
disguise | +1.177 |
tails | +1.164 |
idth | +1.161 |
DRAGON | +1.154 |
Neg logit contributions | |
ILCS | -1.411 |
illo | -1.351 |
Fed | -1.301 |
ESA | -1.296 |
ilt | -1.280 |
Token | followed |
Token ID | 3940 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
liners | +1.169 |
disguise | +1.111 |
DRAGON | +1.091 |
idth | +1.087 |
tails | +1.082 |
Neg logit contributions | |
ILCS | -1.419 |
illo | -1.374 |
ESA | -1.340 |
Fed | -1.326 |
ilt | -1.321 |
Token | by |
Token ID | 416 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
liners | +0.496 |
disguise | +0.470 |
DRAGON | +0.460 |
idth | +0.459 |
tails | +0.458 |
Neg logit contributions | |
ILCS | -0.653 |
illo | -0.632 |
ESA | -0.617 |
Fed | -0.611 |
ilt | -0.609 |
Token | name |
Token ID | 1438 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
ILCS | +0.269 |
illo | +0.262 |
ESA | +0.256 |
Fed | +0.253 |
ilt | +0.252 |
Neg logit contributions | |
liners | -0.202 |
disguise | -0.189 |
idth | -0.187 |
tails | -0.186 |
DRAGON | -0.186 |
Token | for |
Token ID | 329 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ILCS | +0.732 |
illo | +0.713 |
ESA | +0.694 |
Fed | +0.688 |
ilt | +0.684 |
Neg logit contributions | |
liners | -0.620 |
disguise | -0.588 |
idth | -0.581 |
DRAGON | -0.579 |
tails | -0.576 |
Token | Trump |
Token ID | 1301 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
liners | +0.786 |
disguise | +0.744 |
DRAGON | +0.728 |
idth | +0.724 |
tails | +0.720 |
Neg logit contributions | |
ILCS | -1.184 |
illo | -1.149 |
ESA | -1.123 |
Fed | -1.112 |
ilt | -1.108 |
Token | apparently |
Token ID | 5729 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
liners | +0.331 |
disguise | +0.314 |
DRAGON | +0.309 |
idth | +0.308 |
tails | +0.306 |
Neg logit contributions | |
ILCS | -0.406 |
illo | -0.394 |
ESA | -0.384 |
Fed | -0.380 |
ilt | -0.379 |
Token | caught |
Token ID | 4978 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
liners | +1.509 |
disguise | +1.436 |
DRAGON | +1.389 |
tails | +1.382 |
idth | +1.370 |
Neg logit contributions | |
ILCS | -2.171 |
illo | -2.092 |
ESA | -2.047 |
Fed | -2.021 |
ilt | -2.016 |
Token | on |
Token ID | 319 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
ILCS | +0.204 |
illo | +0.199 |
ESA | +0.194 |
Fed | +0.192 |
ilt | +0.191 |
Neg logit contributions | |
liners | -0.190 |
disguise | -0.179 |
idth | -0.178 |
DRAGON | -0.177 |
tails | -0.176 |
Token | last |
Token ID | 938 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
liners | +3.673 |
disguise | +3.471 |
DRAGON | +3.382 |
ancest | +3.309 |
tails | +3.300 |
Neg logit contributions | |
ILCS | -5.443 |
illo | -5.193 |
ESA | -5.141 |
ilt | -5.090 |
Fed | -5.043 |
Token | spring |
Token ID | 6076 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
liners | +1.911 |
disguise | +1.845 |
DRAGON | +1.772 |
idth | +1.737 |
tails | +1.729 |
Neg logit contributions | |
ILCS | -2.832 |
illo | -2.724 |
ESA | -2.657 |
ilt | -2.637 |
nard | -2.614 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
liners | +0.843 |
disguise | +0.798 |
DRAGON | +0.782 |
idth | +0.779 |
tails | +0.778 |
Neg logit contributions | |
ILCS | -0.990 |
illo | -0.959 |
ESA | -0.937 |
Fed | -0.926 |
ilt | -0.925 |
Token | New |
Token ID | 968 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
liners | +0.856 |
disguise | +0.811 |
DRAGON | +0.801 |
tails | +0.788 |
idth | +0.788 |
Neg logit contributions | |
ILCS | -1.205 |
illo | -1.168 |
ESA | -1.139 |
ilt | -1.128 |
Fed | -1.126 |
Token | York |
Token ID | 1971 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
liners | +0.734 |
disguise | +0.695 |
DRAGON | +0.680 |
idth | +0.676 |
tails | +0.674 |
Neg logit contributions | |
ILCS | -0.992 |
illo | -0.956 |
ESA | -0.935 |
Fed | -0.925 |
ilt | -0.921 |
Token | , |
Token ID | 11 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
ILCS | +0.809 |
illo | +0.786 |
ESA | +0.764 |
Fed | +0.758 |
ilt | +0.753 |
Neg logit contributions | |
liners | -0.718 |
disguise | -0.683 |
DRAGON | -0.673 |
idth | -0.673 |
tails | -0.668 |
Token | that |
Token ID | 326 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
liners | +0.528 |
disguise | +0.501 |
DRAGON | +0.492 |
idth | +0.491 |
tails | +0.488 |
Neg logit contributions | |
ILCS | -0.662 |
illo | -0.643 |
ESA | -0.627 |
Fed | -0.620 |
ilt | -0.618 |
Token | 's |
Token ID | 338 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
liners | +1.405 |
disguise | +1.342 |
DRAGON | +1.310 |
tails | +1.285 |
idth | +1.282 |
Neg logit contributions | |
ILCS | -2.024 |
illo | -1.957 |
ESA | -1.913 |
Fed | -1.893 |
ilt | -1.884 |
Token | not |
Token ID | 407 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
liners | +1.896 |
disguise | +1.814 |
DRAGON | +1.768 |
tails | +1.735 |
idth | +1.721 |
Neg logit contributions | |
ILCS | -2.654 |
illo | -2.558 |
ESA | -2.491 |
Fed | -2.473 |
ilt | -2.463 |
Token | the |
Token ID | 262 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
liners | +2.256 |
disguise | +2.167 |
DRAGON | +2.114 |
idth | +2.072 |
tails | +2.072 |
Neg logit contributions | |
ILCS | -3.234 |
illo | -3.133 |
ESA | -3.044 |
Fed | -3.026 |
ilt | -3.024 |
Token | only |
Token ID | 691 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
liners | +1.457 |
disguise | +1.383 |
DRAGON | +1.355 |
idth | +1.345 |
tails | +1.340 |
Neg logit contributions | |
ILCS | -2.070 |
illo | -2.009 |
ESA | -1.962 |
Fed | -1.943 |
ilt | -1.937 |
Token | thing |
Token ID | 1517 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
liners | +3.595 |
disguise | +3.537 |
DRAGON | +3.429 |
idth | +3.286 |
ROCK | +3.276 |
Neg logit contributions | |
ILCS | -5.510 |
illo | -5.316 |
ESA | -5.193 |
Fed | -5.150 |
ilt | -5.149 |
Token | that |
Token ID | 326 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
liners | +1.422 |
disguise | +1.354 |
DRAGON | +1.329 |
idth | +1.316 |
tails | +1.311 |
Neg logit contributions | |
ILCS | -1.897 |
illo | -1.837 |
ESA | -1.794 |
Fed | -1.777 |
ilt | -1.769 |
Token | drives |
Token ID | 10182 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
ILCS | +0.177 |
illo | +0.173 |
ESA | +0.169 |
ilt | +0.168 |
Fed | +0.167 |
Neg logit contributions | |
liners | -0.140 |
disguise | -0.132 |
idth | -0.131 |
tails | -0.130 |
DRAGON | -0.129 |
Token | them |
Token ID | 606 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
ILCS | +0.764 |
illo | +0.748 |
ESA | +0.730 |
ilt | +0.723 |
Fed | +0.721 |
Neg logit contributions | |
liners | -0.600 |
disguise | -0.562 |
idth | -0.557 |
tails | -0.552 |
DRAGON | -0.547 |
Token | toward |
Token ID | 3812 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
ILCS | +0.228 |
illo | +0.222 |
ESA | +0.216 |
Fed | +0.214 |
ilt | +0.212 |
Neg logit contributions | |
liners | -0.195 |
disguise | -0.186 |
idth | -0.184 |
DRAGON | -0.182 |
tails | -0.182 |
Token | Add |
Token ID | 4550 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
liners | +0.661 |
disguise | +0.631 |
DRAGON | +0.622 |
idth | +0.620 |
tails | +0.619 |
Neg logit contributions | |
ILCS | -0.602 |
illo | -0.580 |
ESA | -0.562 |
Fed | -0.554 |
ilt | -0.554 |
Token | in |
Token ID | 259 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
ILCS | +2.045 |
illo | +2.031 |
ilt | +1.959 |
Fed | +1.949 |
ESA | +1.939 |
Neg logit contributions | |
liners | -1.805 |
disguise | -1.725 |
DRAGON | -1.700 |
idth | -1.676 |
tails | -1.658 |
Token | Audio |
Token ID | 13491 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
liners | +1.854 |
disguise | +1.758 |
idth | +1.721 |
DRAGON | +1.718 |
tails | +1.714 |
Neg logit contributions | |
ILCS | -2.208 |
illo | -2.116 |
ESA | -2.095 |
Fed | -2.043 |
ilt | -2.034 |
Token | To |
Token ID | 1675 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
ILCS | +0.139 |
illo | +0.135 |
ESA | +0.130 |
Fed | +0.129 |
ilt | +0.129 |
Neg logit contributions | |
liners | -0.142 |
disguise | -0.136 |
DRAGON | -0.134 |
idth | -0.134 |
tails | -0.133 |
Token | O |
Token ID | 440 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
liners | +1.551 |
disguise | +1.470 |
DRAGON | +1.448 |
tails | +1.440 |
idth | +1.435 |
Neg logit contributions | |
ILCS | -1.899 |
illo | -1.836 |
ESA | -1.795 |
Fed | -1.763 |
ilt | -1.758 |
Token | & |
Token ID | 5 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
liners | +0.783 |
disguise | +0.742 |
DRAGON | +0.729 |
idth | +0.726 |
tails | +0.722 |
Neg logit contributions | |
ILCS | -1.058 |
illo | -1.029 |
ESA | -1.005 |
Fed | -0.995 |
ilt | -0.991 |
Token | A |
Token ID | 32 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
liners | +4.093 |
tails | +3.921 |
DRAGON | +3.916 |
ROCK | +3.882 |
disguise | +3.872 |
Neg logit contributions | |
ILCS | -4.822 |
illo | -4.647 |
ilt | -4.572 |
nard | -4.516 |
ESA | -4.397 |
Token | Bits |
Token ID | 44733 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
liners | +1.709 |
disguise | +1.631 |
DRAGON | +1.610 |
tails | +1.596 |
idth | +1.595 |
Neg logit contributions | |
ILCS | -1.631 |
illo | -1.570 |
ESA | -1.535 |
ilt | -1.506 |
Fed | -1.506 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
liners | +1.267 |
disguise | +1.209 |
DRAGON | +1.191 |
idth | +1.187 |
tails | +1.185 |
Neg logit contributions | |
ILCS | -1.201 |
illo | -1.157 |
ESA | -1.130 |
Fed | -1.111 |
ilt | -1.107 |
Token | 01 |
Token ID | 486 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
ILCS | +0.100 |
illo | +0.096 |
ESA | +0.094 |
Fed | +0.093 |
ilt | +0.093 |
Neg logit contributions | |
liners | -0.084 |
disguise | -0.080 |
DRAGON | -0.078 |
idth | -0.078 |
tails | -0.078 |
Token | 11 |
Token ID | 1157 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ILCS | +0.221 |
illo | +0.214 |
ESA | +0.208 |
Fed | +0.206 |
ilt | +0.203 |
Neg logit contributions | |
liners | -0.269 |
disguise | -0.259 |
idth | -0.255 |
DRAGON | -0.254 |
tails | -0.251 |
Token | arts |
Token ID | 5889 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
liners | +0.270 |
disguise | +0.258 |
DRAGON | +0.254 |
idth | +0.254 |
tails | +0.252 |
Neg logit contributions | |
ILCS | -0.245 |
illo | -0.237 |
ESA | -0.230 |
Fed | -0.227 |
ilt | -0.226 |
Token | 200 |
Token ID | 939 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ILCS | +0.146 |
illo | +0.142 |
ESA | +0.137 |
Fed | +0.136 |
ilt | +0.136 |
Neg logit contributions | |
liners | -0.152 |
disguise | -0.145 |
DRAGON | -0.143 |
idth | -0.143 |
tails | -0.141 |
Token | 80 |
Token ID | 1795 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
liners | +1.431 |
disguise | +1.367 |
DRAGON | +1.346 |
idth | +1.342 |
tails | +1.338 |
Neg logit contributions | |
ILCS | -1.323 |
illo | -1.279 |
ESA | -1.245 |
Fed | -1.225 |
ilt | -1.222 |
Token | 201 |
Token ID | 1264 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ILCS | +0.413 |
illo | +0.394 |
ESA | +0.382 |
Fed | +0.377 |
ilt | +0.375 |
Neg logit contributions | |
liners | -0.546 |
disguise | -0.524 |
DRAGON | -0.516 |
idth | -0.515 |
tails | -0.514 |
Token | O |
Token ID | 440 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
ILCS | +1.161 |
illo | +1.105 |
ESA | +1.072 |
Fed | +1.069 |
ilt | +1.050 |
Neg logit contributions | |
liners | -1.325 |
disguise | -1.269 |
idth | -1.255 |
tails | -1.249 |
DRAGON | -1.238 |
Token | & |
Token ID | 5 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
liners | +0.458 |
disguise | +0.431 |
DRAGON | +0.423 |
idth | +0.421 |
tails | +0.420 |
Neg logit contributions | |
ILCS | -0.658 |
illo | -0.639 |
ESA | -0.623 |
Fed | -0.617 |
ilt | -0.615 |
Token | A |
Token ID | 32 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
liners | +3.910 |
DRAGON | +3.745 |
tails | +3.722 |
ROCK | +3.697 |
disguise | +3.652 |
Neg logit contributions | |
ILCS | -4.940 |
illo | -4.777 |
ilt | -4.673 |
nard | -4.599 |
tein | -4.474 |
Token | - |
Token ID | 12 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
liners | +2.087 |
disguise | +1.992 |
DRAGON | +1.979 |
tails | +1.961 |
idth | +1.956 |
Neg logit contributions | |
ILCS | -1.510 |
illo | -1.444 |
ESA | -1.406 |
Fed | -1.379 |
ilt | -1.375 |
Token | Sports |
Token ID | 18153 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
liners | +0.148 |
disguise | +0.142 |
idth | +0.139 |
DRAGON | +0.139 |
tails | +0.138 |
Neg logit contributions | |
ILCS | -0.136 |
illo | -0.131 |
ESA | -0.128 |
Fed | -0.127 |
ilt | -0.126 |
Token | - |
Token ID | 12 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ILCS | +1.899 |
illo | +1.867 |
Fed | +1.814 |
nard | +1.796 |
ilt | +1.786 |
Neg logit contributions | |
liners | -1.723 |
disguise | -1.664 |
idth | -1.633 |
DRAGON | -1.632 |
tails | -1.616 |
Token | Lou |
Token ID | 24016 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
ILCS | +0.879 |
illo | +0.850 |
ESA | +0.836 |
Fed | +0.835 |
ilt | +0.817 |
Neg logit contributions | |
liners | -0.975 |
disguise | -0.941 |
idth | -0.926 |
DRAGON | -0.923 |
tails | -0.910 |
Token | . |
Token ID | 13 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
ILCS | +0.603 |
illo | +0.583 |
ESA | +0.567 |
Fed | +0.560 |
ilt | +0.559 |
Neg logit contributions | |
liners | -0.598 |
disguise | -0.571 |
DRAGON | -0.563 |
idth | -0.561 |
tails | -0.558 |
Token | Arg |
Token ID | 28100 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
liners | +0.515 |
disguise | +0.485 |
DRAGON | +0.473 |
idth | +0.471 |
tails | +0.469 |
Neg logit contributions | |
ILCS | -0.757 |
illo | -0.733 |
ESA | -0.717 |
Fed | -0.708 |
ilt | -0.707 |
Token | ument |
Token ID | 1713 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
liners | +0.051 |
disguise | +0.048 |
DRAGON | +0.047 |
idth | +0.047 |
tails | +0.047 |
Neg logit contributions | |
ILCS | -0.071 |
illo | -0.069 |
ESA | -0.067 |
Fed | -0.066 |
ilt | -0.066 |
Token | Parser |
Token ID | 46677 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
liners | +0.935 |
disguise | +0.896 |
DRAGON | +0.879 |
tails | +0.875 |
idth | +0.873 |
Neg logit contributions | |
ILCS | -0.838 |
illo | -0.795 |
ESA | -0.774 |
ilt | -0.761 |
Fed | -0.758 |
Token | () |
Token ID | 3419 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
liners | +0.448 |
disguise | +0.427 |
DRAGON | +0.417 |
idth | +0.415 |
tails | +0.414 |
Neg logit contributions | |
ILCS | -0.569 |
illo | -0.550 |
ESA | -0.537 |
ilt | -0.530 |
Fed | -0.530 |
Token | ap |
Token ID | 2471 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
ILCS | +0.066 |
illo | +0.064 |
ESA | +0.062 |
Fed | +0.062 |
ilt | +0.062 |
Neg logit contributions | |
liners | -0.055 |
disguise | -0.052 |
DRAGON | -0.052 |
idth | -0.051 |
tails | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
liners | +4.113 |
disguise | +3.887 |
idth | +3.819 |
tails | +3.754 |
DRAGON | +3.707 |
Neg logit contributions | |
ILCS | -5.000 |
ESA | -4.733 |
illo | -4.680 |
Fed | -4.594 |
nard | -4.519 |
Token | add |
Token ID | 2860 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
liners | +1.650 |
disguise | +1.573 |
tails | +1.551 |
DRAGON | +1.539 |
idth | +1.537 |
Neg logit contributions | |
ILCS | -1.305 |
illo | -1.227 |
ESA | -1.204 |
ilt | -1.177 |
Fed | -1.166 |
Token | _ |
Token ID | 62 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ILCS | +1.139 |
illo | +1.095 |
ESA | +1.063 |
Fed | +1.048 |
ilt | +1.044 |
Neg logit contributions | |
liners | -1.347 |
disguise | -1.290 |
DRAGON | -1.271 |
idth | -1.268 |
tails | -1.263 |
Token | argument |
Token ID | 49140 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
liners | +1.247 |
disguise | +1.187 |
tails | +1.173 |
DRAGON | +1.166 |
idth | +1.165 |
Neg logit contributions | |
ILCS | -0.795 |
illo | -0.748 |
ESA | -0.730 |
Fed | -0.708 |
ilt | -0.707 |
Token | (" |
Token ID | 7203 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
liners | +0.356 |
disguise | +0.342 |
DRAGON | +0.337 |
idth | +0.337 |
tails | +0.335 |
Neg logit contributions | |
ILCS | -0.265 |
illo | -0.255 |
ESA | -0.247 |
Fed | -0.244 |
ilt | -0.242 |
Token | : |
Token ID | 25 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
ILCS | +3.674 |
illo | +3.666 |
Fed | +3.560 |
ESA | +3.494 |
ilt | +3.486 |
Neg logit contributions | |
proble | -3.870 |
liners | -3.841 |
disguise | -3.732 |
idth | -3.716 |
ancest | -3.704 |
Token | j |
Token ID | 474 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ILCS | +2.802 |
illo | +2.709 |
ilt | +2.618 |
Fed | +2.603 |
ESA | +2.602 |
Neg logit contributions | |
liners | -2.209 |
idth | -2.079 |
disguise | -2.058 |
tails | -2.040 |
DRAGON | -2.010 |
Token | wt |
Token ID | 46569 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
liners | +1.410 |
disguise | +1.326 |
tails | +1.318 |
idth | +1.315 |
DRAGON | +1.298 |
Neg logit contributions | |
ILCS | -1.379 |
illo | -1.307 |
ESA | -1.288 |
Fed | -1.267 |
ilt | -1.246 |
Token | 0001 |
Token ID | 18005 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
ILCS | +1.581 |
illo | +1.543 |
ESA | +1.484 |
ilt | +1.480 |
Fed | +1.470 |
Neg logit contributions | |
liners | -1.524 |
disguise | -1.461 |
DRAGON | -1.440 |
idth | -1.418 |
tails | -1.416 |
Token | - |
Token ID | 532 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
ILCS | +2.100 |
illo | +2.050 |
ESA | +1.981 |
ilt | +1.972 |
Fed | +1.966 |
Neg logit contributions | |
liners | -1.902 |
disguise | -1.809 |
idth | -1.779 |
DRAGON | -1.776 |
tails | -1.754 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
ILCS | +3.072 |
illo | +3.032 |
ilt | +2.879 |
Fed | +2.865 |
nard | +2.850 |
Neg logit contributions | |
liners | -4.658 |
idth | -4.523 |
disguise | -4.448 |
tails | -4.415 |
DRAGON | -4.407 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.97e+00 |
Pos logit contributions | |
illo | +4.871 |
ILCS | +4.838 |
nard | +4.545 |
ilt | +4.433 |
Fed | +4.373 |
Neg logit contributions | |
liners | -9.140 |
idth | -9.068 |
proble | -8.978 |
retty | -8.919 |
comings | -8.878 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.46e+00 |
Pos logit contributions | |
illo | +4.744 |
ILCS | +4.728 |
nard | +4.429 |
ilt | +4.347 |
Fed | +4.295 |
Neg logit contributions | |
liners | -8.499 |
idth | -8.419 |
proble | -8.271 |
retty | -8.231 |
comings | -8.188 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
illo | +4.415 |
ILCS | +4.387 |
ilt | +4.068 |
nard | +4.055 |
Fed | +4.000 |
Neg logit contributions | |
liners | -7.023 |
idth | -6.783 |
DRAGON | -6.703 |
disguise | -6.691 |
tails | -6.624 |
Token | - |
Token ID | 532 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ILCS | +4.368 |
illo | +4.327 |
ilt | +4.060 |
Fed | +4.032 |
nard | +4.031 |
Neg logit contributions | |
liners | -5.058 |
disguise | -4.830 |
DRAGON | -4.812 |
idth | -4.797 |
tails | -4.711 |
Token | July |
Token ID | 2901 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
ILCS | +0.995 |
illo | +0.966 |
ESA | +0.944 |
Fed | +0.937 |
ilt | +0.932 |
Neg logit contributions | |
liners | -0.688 |
disguise | -0.647 |
idth | -0.640 |
DRAGON | -0.634 |
tails | -0.634 |
Token | k |
Token ID | 479 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
ILCS | +2.715 |
illo | +2.623 |
ilt | +2.535 |
Fed | +2.524 |
ESA | +2.523 |
Neg logit contributions | |
liners | -2.127 |
idth | -2.008 |
disguise | -1.986 |
tails | -1.964 |
DRAGON | -1.938 |
Token | imp |
Token ID | 11011 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
liners | +1.616 |
disguise | +1.524 |
idth | +1.514 |
tails | +1.510 |
DRAGON | +1.498 |
Neg logit contributions | |
ILCS | -1.631 |
illo | -1.557 |
ESA | -1.528 |
Fed | -1.504 |
nard | -1.477 |
Token | unk |
Token ID | 2954 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ILCS | +1.096 |
illo | +1.068 |
ESA | +1.030 |
ilt | +1.025 |
Fed | +1.021 |
Neg logit contributions | |
liners | -1.052 |
disguise | -1.008 |
DRAGON | -0.992 |
idth | -0.982 |
tails | -0.974 |
Token | rock |
Token ID | 10823 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
liners | +1.437 |
disguise | +1.358 |
tails | +1.345 |
idth | +1.337 |
DRAGON | +1.334 |
Neg logit contributions | |
ILCS | -1.634 |
illo | -1.560 |
ESA | -1.549 |
Fed | -1.527 |
ilt | -1.503 |
Token | - |
Token ID | 532 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
liners | +0.077 |
disguise | +0.073 |
DRAGON | +0.072 |
tails | +0.072 |
idth | +0.072 |
Neg logit contributions | |
ILCS | -0.094 |
illo | -0.090 |
ESA | -0.089 |
Fed | -0.087 |
ilt | -0.087 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
ILCS | +2.968 |
illo | +2.891 |
ilt | +2.778 |
Fed | +2.740 |
ESA | +2.725 |
Neg logit contributions | |
liners | -4.444 |
idth | -4.303 |
disguise | -4.262 |
DRAGON | -4.217 |
tails | -4.211 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
illo | +4.899 |
ILCS | +4.853 |
ilt | +4.516 |
Fed | +4.447 |
nard | +4.411 |
Neg logit contributions | |
liners | -9.054 |
idth | -8.749 |
DRAGON | -8.616 |
disguise | -8.614 |
tails | -8.607 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.60e+00 |
Pos logit contributions | |
illo | +4.858 |
ILCS | +4.805 |
ilt | +4.492 |
Fed | +4.420 |
nard | +4.395 |
Neg logit contributions | |
liners | -8.392 |
idth | -8.052 |
DRAGON | -7.990 |
disguise | -7.990 |
tails | -7.932 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
illo | +4.679 |
ILCS | +4.651 |
ilt | +4.341 |
nard | +4.285 |
Fed | +4.280 |
Neg logit contributions | |
liners | -6.989 |
idth | -6.670 |
DRAGON | -6.666 |
disguise | -6.656 |
tails | -6.562 |
Token | - |
Token ID | 532 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ILCS | +4.599 |
illo | +4.583 |
ilt | +4.301 |
Fed | +4.273 |
ESA | +4.262 |
Neg logit contributions | |
liners | -5.540 |
disguise | -5.272 |
DRAGON | -5.265 |
idth | -5.259 |
tails | -5.167 |
Token | December |
Token ID | 3426 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ILCS | +1.415 |
illo | +1.376 |
ESA | +1.344 |
Fed | +1.332 |
ilt | +1.329 |
Neg logit contributions | |
liners | -0.952 |
disguise | -0.897 |
DRAGON | -0.883 |
idth | -0.882 |
tails | -0.878 |
Token | j |
Token ID | 474 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ILCS | +2.802 |
illo | +2.709 |
ilt | +2.618 |
Fed | +2.603 |
ESA | +2.602 |
Neg logit contributions | |
liners | -2.209 |
idth | -2.079 |
disguise | -2.058 |
tails | -2.040 |
DRAGON | -2.010 |
Token | wt |
Token ID | 46569 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
liners | +1.410 |
disguise | +1.326 |
tails | +1.318 |
idth | +1.315 |
DRAGON | +1.298 |
Neg logit contributions | |
ILCS | -1.379 |
illo | -1.307 |
ESA | -1.288 |
Fed | -1.267 |
ilt | -1.246 |
Token | 0001 |
Token ID | 18005 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
ILCS | +1.581 |
illo | +1.543 |
ESA | +1.484 |
ilt | +1.480 |
Fed | +1.470 |
Neg logit contributions | |
liners | -1.524 |
disguise | -1.461 |
DRAGON | -1.440 |
idth | -1.418 |
tails | -1.416 |
Token | - |
Token ID | 532 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
ILCS | +2.100 |
illo | +2.050 |
ESA | +1.981 |
ilt | +1.972 |
Fed | +1.966 |
Neg logit contributions | |
liners | -1.902 |
disguise | -1.809 |
idth | -1.779 |
DRAGON | -1.776 |
tails | -1.754 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
ILCS | +3.072 |
illo | +3.032 |
ilt | +2.879 |
Fed | +2.865 |
nard | +2.850 |
Neg logit contributions | |
liners | -4.658 |
idth | -4.523 |
disguise | -4.448 |
tails | -4.415 |
DRAGON | -4.407 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.97e+00 |
Pos logit contributions | |
illo | +4.871 |
ILCS | +4.838 |
nard | +4.545 |
ilt | +4.433 |
Fed | +4.373 |
Neg logit contributions | |
liners | -9.140 |
idth | -9.068 |
proble | -8.978 |
retty | -8.919 |
comings | -8.878 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.46e+00 |
Pos logit contributions | |
illo | +4.744 |
ILCS | +4.728 |
nard | +4.429 |
ilt | +4.347 |
Fed | +4.295 |
Neg logit contributions | |
liners | -8.499 |
idth | -8.419 |
proble | -8.271 |
retty | -8.231 |
comings | -8.188 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
illo | +4.415 |
ILCS | +4.387 |
ilt | +4.068 |
nard | +4.055 |
Fed | +4.000 |
Neg logit contributions | |
liners | -7.023 |
idth | -6.783 |
DRAGON | -6.703 |
disguise | -6.691 |
tails | -6.624 |
Token | - |
Token ID | 532 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ILCS | +4.368 |
illo | +4.327 |
ilt | +4.060 |
Fed | +4.032 |
nard | +4.031 |
Neg logit contributions | |
liners | -5.058 |
disguise | -4.830 |
DRAGON | -4.812 |
idth | -4.797 |
tails | -4.711 |
Token | July |
Token ID | 2901 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
ILCS | +0.995 |
illo | +0.966 |
ESA | +0.944 |
Fed | +0.937 |
ilt | +0.932 |
Neg logit contributions | |
liners | -0.688 |
disguise | -0.647 |
idth | -0.640 |
DRAGON | -0.634 |
tails | -0.634 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
ILCS | +1.864 |
illo | +1.817 |
ESA | +1.761 |
Fed | +1.755 |
ilt | +1.746 |
Neg logit contributions | |
liners | -1.616 |
disguise | -1.540 |
idth | -1.534 |
tails | -1.508 |
DRAGON | -1.504 |
Token | imp |
Token ID | 11011 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
liners | +1.616 |
disguise | +1.524 |
idth | +1.514 |
tails | +1.510 |
DRAGON | +1.498 |
Neg logit contributions | |
ILCS | -1.631 |
illo | -1.557 |
ESA | -1.528 |
Fed | -1.504 |
nard | -1.477 |
Token | unk |
Token ID | 2954 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ILCS | +1.096 |
illo | +1.068 |
ESA | +1.030 |
ilt | +1.025 |
Fed | +1.021 |
Neg logit contributions | |
liners | -1.052 |
disguise | -1.008 |
DRAGON | -0.992 |
idth | -0.982 |
tails | -0.974 |
Token | rock |
Token ID | 10823 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
liners | +1.437 |
disguise | +1.358 |
tails | +1.345 |
idth | +1.337 |
DRAGON | +1.334 |
Neg logit contributions | |
ILCS | -1.634 |
illo | -1.560 |
ESA | -1.549 |
Fed | -1.527 |
ilt | -1.503 |
Token | - |
Token ID | 532 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
liners | +0.077 |
disguise | +0.073 |
DRAGON | +0.072 |
tails | +0.072 |
idth | +0.072 |
Neg logit contributions | |
ILCS | -0.094 |
illo | -0.090 |
ESA | -0.089 |
Fed | -0.087 |
ilt | -0.087 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
ILCS | +2.968 |
illo | +2.891 |
ilt | +2.778 |
Fed | +2.740 |
ESA | +2.725 |
Neg logit contributions | |
liners | -4.444 |
idth | -4.303 |
disguise | -4.262 |
DRAGON | -4.217 |
tails | -4.211 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
illo | +4.899 |
ILCS | +4.853 |
ilt | +4.516 |
Fed | +4.447 |
nard | +4.411 |
Neg logit contributions | |
liners | -9.054 |
idth | -8.749 |
DRAGON | -8.616 |
disguise | -8.614 |
tails | -8.607 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.60e+00 |
Pos logit contributions | |
illo | +4.858 |
ILCS | +4.805 |
ilt | +4.492 |
Fed | +4.420 |
nard | +4.395 |
Neg logit contributions | |
liners | -8.392 |
idth | -8.052 |
DRAGON | -7.990 |
disguise | -7.990 |
tails | -7.932 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
illo | +4.679 |
ILCS | +4.651 |
ilt | +4.341 |
nard | +4.285 |
Fed | +4.280 |
Neg logit contributions | |
liners | -6.989 |
idth | -6.670 |
DRAGON | -6.666 |
disguise | -6.656 |
tails | -6.562 |
Token | - |
Token ID | 532 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ILCS | +4.599 |
illo | +4.583 |
ilt | +4.301 |
Fed | +4.273 |
ESA | +4.262 |
Neg logit contributions | |
liners | -5.540 |
disguise | -5.272 |
DRAGON | -5.265 |
idth | -5.259 |
tails | -5.167 |
Token | December |
Token ID | 3426 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ILCS | +1.415 |
illo | +1.376 |
ESA | +1.344 |
Fed | +1.332 |
ilt | +1.329 |
Neg logit contributions | |
liners | -0.952 |
disguise | -0.897 |
DRAGON | -0.883 |
idth | -0.882 |
tails | -0.878 |
Token | 13 |
Token ID | 1511 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
ILCS | +0.931 |
illo | +0.905 |
ESA | +0.880 |
Fed | +0.874 |
ilt | +0.871 |
Neg logit contributions | |
liners | -0.750 |
disguise | -0.711 |
idth | -0.702 |
DRAGON | -0.695 |
tails | -0.695 |
Token | Happy |
Token ID | 25082 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ILCS | +1.150 |
illo | +1.120 |
ESA | +1.087 |
Fed | +1.081 |
ilt | +1.074 |
Neg logit contributions | |
liners | -1.172 |
disguise | -1.128 |
DRAGON | -1.105 |
idth | -1.099 |
tails | -1.090 |
Token | L |
Token ID | 43 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
liners | +1.190 |
disguise | +1.133 |
DRAGON | +1.119 |
idth | +1.115 |
tails | +1.114 |
Neg logit contributions | |
ILCS | -1.169 |
illo | -1.126 |
ESA | -1.097 |
ilt | -1.080 |
Fed | -1.080 |
Token | ur |
Token ID | 333 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
ILCS | +0.079 |
illo | +0.076 |
ESA | +0.074 |
ilt | +0.073 |
Fed | +0.073 |
Neg logit contributions | |
liners | -0.078 |
disguise | -0.074 |
DRAGON | -0.073 |
idth | -0.073 |
tails | -0.073 |
Token | ker |
Token ID | 6122 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ILCS | +0.255 |
illo | +0.246 |
ESA | +0.238 |
Fed | +0.236 |
ilt | +0.235 |
Neg logit contributions | |
liners | -0.294 |
disguise | -0.282 |
DRAGON | -0.278 |
idth | -0.276 |
tails | -0.276 |
Token | - |
Token ID | 532 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
ILCS | +1.470 |
illo | +1.430 |
ESA | +1.388 |
Fed | +1.379 |
ilt | +1.373 |
Neg logit contributions | |
liners | -1.268 |
disguise | -1.207 |
DRAGON | -1.185 |
idth | -1.183 |
tails | -1.170 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.79e+00 |
Pos logit contributions | |
ILCS | +2.705 |
illo | +2.654 |
ilt | +2.520 |
Fed | +2.513 |
nard | +2.499 |
Neg logit contributions | |
liners | -3.947 |
idth | -3.819 |
disguise | -3.774 |
DRAGON | -3.739 |
tails | -3.735 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.10e+00 |
Pos logit contributions | |
illo | +4.704 |
ILCS | +4.685 |
nard | +4.424 |
ilt | +4.299 |
Fed | +4.263 |
Neg logit contributions | |
liners | -8.337 |
idth | -8.239 |
proble | -8.141 |
retty | -8.055 |
comings | -8.045 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.43e+00 |
Pos logit contributions | |
illo | +4.503 |
ILCS | +4.500 |
nard | +4.233 |
ilt | +4.145 |
Fed | +4.115 |
Neg logit contributions | |
liners | -7.676 |
idth | -7.568 |
proble | -7.433 |
retty | -7.358 |
tails | -7.357 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
illo | +3.966 |
ILCS | +3.952 |
ilt | +3.680 |
nard | +3.673 |
Fed | +3.628 |
Neg logit contributions | |
liners | -6.124 |
idth | -5.954 |
DRAGON | -5.830 |
disguise | -5.815 |
tails | -5.792 |
Token | favorite |
Token ID | 4004 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
ILCS | +3.779 |
illo | +3.727 |
ilt | +3.515 |
ESA | +3.504 |
Fed | +3.503 |
Neg logit contributions | |
liners | -4.376 |
disguise | -4.174 |
DRAGON | -4.154 |
idth | -4.141 |
tails | -4.085 |
Token | - |
Token ID | 532 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
ILCS | +3.356 |
illo | +3.281 |
ESA | +3.148 |
Fed | +3.137 |
ilt | +3.132 |
Neg logit contributions | |
liners | -2.960 |
disguise | -2.813 |
DRAGON | -2.782 |
idth | -2.774 |
tails | -2.738 |
Token | hey |
Token ID | 17207 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
ILCS | +2.754 |
illo | +2.663 |
ilt | +2.572 |
Fed | +2.560 |
ESA | +2.558 |
Neg logit contributions | |
liners | -2.198 |
idth | -2.070 |
disguise | -2.045 |
tails | -2.030 |
DRAGON | -1.997 |
Token | _ |
Token ID | 62 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ILCS | +0.445 |
illo | +0.431 |
ESA | +0.420 |
Fed | +0.415 |
ilt | +0.414 |
Neg logit contributions | |
liners | -0.414 |
disguise | -0.396 |
DRAGON | -0.389 |
idth | -0.387 |
tails | -0.385 |
Token | ler |
Token ID | 1754 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
liners | +0.911 |
disguise | +0.864 |
idth | +0.852 |
DRAGON | +0.852 |
tails | +0.852 |
Neg logit contributions | |
ILCS | -0.939 |
illo | -0.905 |
ESA | -0.883 |
Fed | -0.870 |
ilt | -0.865 |
Token | oy |
Token ID | 726 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
liners | +0.324 |
disguise | +0.308 |
DRAGON | +0.303 |
idth | +0.302 |
tails | +0.301 |
Neg logit contributions | |
ILCS | -0.361 |
illo | -0.350 |
ESA | -0.341 |
Fed | -0.337 |
ilt | -0.336 |
Token | - |
Token ID | 532 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
liners | +0.146 |
disguise | +0.139 |
DRAGON | +0.137 |
idth | +0.137 |
tails | +0.136 |
Neg logit contributions | |
ILCS | -0.171 |
illo | -0.165 |
ESA | -0.161 |
Fed | -0.160 |
ilt | -0.159 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.73e+00 |
Pos logit contributions | |
ILCS | +2.256 |
illo | +2.197 |
Fed | +2.090 |
ilt | +2.084 |
ESA | +2.082 |
Neg logit contributions | |
liners | -3.135 |
idth | -3.007 |
disguise | -2.997 |
DRAGON | -2.965 |
tails | -2.960 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
illo | +4.732 |
ILCS | +4.701 |
nard | +4.435 |
ilt | +4.288 |
Fed | +4.277 |
Neg logit contributions | |
liners | -8.232 |
idth | -8.154 |
proble | -8.114 |
comings | -7.982 |
retty | -7.978 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.83e+00 |
Pos logit contributions | |
illo | +4.504 |
ILCS | +4.491 |
nard | +4.220 |
ilt | +4.104 |
Fed | +4.098 |
Neg logit contributions | |
liners | -7.652 |
idth | -7.561 |
proble | -7.472 |
comings | -7.360 |
retty | -7.355 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
ILCS | +4.147 |
illo | +4.132 |
nard | +3.873 |
ilt | +3.795 |
Fed | +3.793 |
Neg logit contributions | |
liners | -6.467 |
idth | -6.346 |
DRAGON | -6.198 |
tails | -6.165 |
proble | -6.164 |
Token | - |
Token ID | 532 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
ILCS | +4.081 |
illo | +4.045 |
ilt | +3.771 |
nard | +3.761 |
Fed | +3.754 |
Neg logit contributions | |
liners | -5.316 |
DRAGON | -5.086 |
disguise | -5.079 |
idth | -5.066 |
tails | -4.990 |
Token | January |
Token ID | 3269 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ILCS | +0.609 |
illo | +0.592 |
ESA | +0.579 |
Fed | +0.574 |
ilt | +0.572 |
Neg logit contributions | |
liners | -0.387 |
disguise | -0.364 |
idth | -0.358 |
DRAGON | -0.356 |
tails | -0.355 |
Token | K |
Token ID | 42 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
ILCS | +0.902 |
illo | +0.874 |
ESA | +0.848 |
Fed | +0.839 |
ilt | +0.836 |
Neg logit contributions | |
liners | -0.929 |
disguise | -0.889 |
DRAGON | -0.873 |
idth | -0.871 |
tails | -0.867 |
Token | ATCH |
Token ID | 11417 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
liners | +0.545 |
disguise | +0.520 |
DRAGON | +0.514 |
idth | +0.510 |
tails | +0.510 |
Neg logit contributions | |
ILCS | -0.549 |
illo | -0.527 |
ESA | -0.514 |
Fed | -0.508 |
ilt | -0.505 |
Token | EW |
Token ID | 6217 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
ILCS | +0.997 |
illo | +0.969 |
ESA | +0.945 |
Fed | +0.930 |
ilt | +0.928 |
Neg logit contributions | |
liners | -0.927 |
disguise | -0.881 |
idth | -0.865 |
DRAGON | -0.858 |
tails | -0.856 |
Token | AN |
Token ID | 1565 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
ILCS | +0.055 |
illo | +0.053 |
ESA | +0.052 |
Fed | +0.051 |
ilt | +0.051 |
Neg logit contributions | |
liners | -0.055 |
disguise | -0.052 |
DRAGON | -0.051 |
idth | -0.051 |
tails | -0.051 |
Token | - |
Token ID | 532 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
ILCS | +1.489 |
illo | +1.445 |
ESA | +1.407 |
Fed | +1.388 |
ilt | +1.385 |
Neg logit contributions | |
liners | -1.369 |
disguise | -1.302 |
idth | -1.281 |
DRAGON | -1.273 |
tails | -1.268 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
ILCS | +2.546 |
illo | +2.492 |
ilt | +2.363 |
Fed | +2.362 |
nard | +2.359 |
Neg logit contributions | |
liners | -3.613 |
idth | -3.478 |
disguise | -3.444 |
DRAGON | -3.416 |
tails | -3.411 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.87e+00 |
Pos logit contributions | |
illo | +4.480 |
ILCS | +4.478 |
nard | +4.202 |
ilt | +4.055 |
Fed | +4.052 |
Neg logit contributions | |
liners | -7.832 |
idth | -7.746 |
proble | -7.654 |
comings | -7.561 |
tails | -7.533 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.49e+00 |
Pos logit contributions | |
illo | +4.372 |
ILCS | +4.371 |
nard | +4.093 |
ilt | +3.972 |
Fed | +3.972 |
Neg logit contributions | |
liners | -7.530 |
idth | -7.439 |
proble | -7.322 |
comings | -7.237 |
tails | -7.236 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
ILCS | +3.980 |
illo | +3.953 |
nard | +3.703 |
Fed | +3.634 |
ilt | +3.629 |
Neg logit contributions | |
liners | -6.218 |
idth | -6.088 |
DRAGON | -5.946 |
tails | -5.930 |
proble | -5.911 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
ILCS | +3.718 |
illo | +3.683 |
ilt | +3.429 |
nard | +3.421 |
ESA | +3.419 |
Neg logit contributions | |
liners | -4.995 |
idth | -4.780 |
disguise | -4.774 |
DRAGON | -4.770 |
tails | -4.704 |
Token | - |
Token ID | 532 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
ILCS | +3.635 |
illo | +3.565 |
ESA | +3.398 |
ilt | +3.392 |
Fed | +3.383 |
Neg logit contributions | |
liners | -3.335 |
disguise | -3.175 |
DRAGON | -3.151 |
idth | -3.143 |
tails | -3.100 |
Token | L |
Token ID | 43 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
liners | +1.190 |
disguise | +1.133 |
DRAGON | +1.119 |
idth | +1.115 |
tails | +1.114 |
Neg logit contributions | |
ILCS | -1.169 |
illo | -1.126 |
ESA | -1.097 |
ilt | -1.080 |
Fed | -1.080 |
Token | ur |
Token ID | 333 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
ILCS | +0.079 |
illo | +0.076 |
ESA | +0.074 |
ilt | +0.073 |
Fed | +0.073 |
Neg logit contributions | |
liners | -0.078 |
disguise | -0.074 |
DRAGON | -0.073 |
idth | -0.073 |
tails | -0.073 |
Token | ker |
Token ID | 6122 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ILCS | +0.255 |
illo | +0.246 |
ESA | +0.238 |
Fed | +0.236 |
ilt | +0.235 |
Neg logit contributions | |
liners | -0.294 |
disguise | -0.282 |
DRAGON | -0.278 |
idth | -0.276 |
tails | -0.276 |
Token | - |
Token ID | 532 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
ILCS | +1.470 |
illo | +1.430 |
ESA | +1.388 |
Fed | +1.379 |
ilt | +1.373 |
Neg logit contributions | |
liners | -1.268 |
disguise | -1.207 |
DRAGON | -1.185 |
idth | -1.183 |
tails | -1.170 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.79e+00 |
Pos logit contributions | |
ILCS | +2.705 |
illo | +2.654 |
ilt | +2.520 |
Fed | +2.513 |
nard | +2.499 |
Neg logit contributions | |
liners | -3.947 |
idth | -3.819 |
disguise | -3.774 |
DRAGON | -3.739 |
tails | -3.735 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.10e+00 |
Pos logit contributions | |
illo | +4.704 |
ILCS | +4.685 |
nard | +4.424 |
ilt | +4.299 |
Fed | +4.263 |
Neg logit contributions | |
liners | -8.337 |
idth | -8.239 |
proble | -8.141 |
retty | -8.055 |
comings | -8.045 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.43e+00 |
Pos logit contributions | |
illo | +4.503 |
ILCS | +4.500 |
nard | +4.233 |
ilt | +4.145 |
Fed | +4.115 |
Neg logit contributions | |
liners | -7.676 |
idth | -7.568 |
proble | -7.433 |
retty | -7.358 |
tails | -7.357 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
illo | +3.966 |
ILCS | +3.952 |
ilt | +3.680 |
nard | +3.673 |
Fed | +3.628 |
Neg logit contributions | |
liners | -6.124 |
idth | -5.954 |
DRAGON | -5.830 |
disguise | -5.815 |
tails | -5.792 |
Token | favorite |
Token ID | 4004 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
ILCS | +3.779 |
illo | +3.727 |
ilt | +3.515 |
ESA | +3.504 |
Fed | +3.503 |
Neg logit contributions | |
liners | -4.376 |
disguise | -4.174 |
DRAGON | -4.154 |
idth | -4.141 |
tails | -4.085 |
Token | - |
Token ID | 532 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
ILCS | +3.356 |
illo | +3.281 |
ESA | +3.148 |
Fed | +3.137 |
ilt | +3.132 |
Neg logit contributions | |
liners | -2.960 |
disguise | -2.813 |
DRAGON | -2.782 |
idth | -2.774 |
tails | -2.738 |
Token | February |
Token ID | 3945 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
liners | +0.235 |
disguise | +0.223 |
DRAGON | +0.218 |
idth | +0.216 |
tails | +0.215 |
Neg logit contributions | |
ILCS | -0.339 |
illo | -0.329 |
ESA | -0.322 |
Fed | -0.319 |
ilt | -0.318 |
Token | _ |
Token ID | 62 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ILCS | +0.445 |
illo | +0.431 |
ESA | +0.420 |
Fed | +0.415 |
ilt | +0.414 |
Neg logit contributions | |
liners | -0.414 |
disguise | -0.396 |
DRAGON | -0.389 |
idth | -0.387 |
tails | -0.385 |
Token | ler |
Token ID | 1754 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
liners | +0.911 |
disguise | +0.864 |
idth | +0.852 |
DRAGON | +0.852 |
tails | +0.852 |
Neg logit contributions | |
ILCS | -0.939 |
illo | -0.905 |
ESA | -0.883 |
Fed | -0.870 |
ilt | -0.865 |
Token | oy |
Token ID | 726 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
liners | +0.324 |
disguise | +0.308 |
DRAGON | +0.303 |
idth | +0.302 |
tails | +0.301 |
Neg logit contributions | |
ILCS | -0.361 |
illo | -0.350 |
ESA | -0.341 |
Fed | -0.337 |
ilt | -0.336 |
Token | - |
Token ID | 532 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
liners | +0.146 |
disguise | +0.139 |
DRAGON | +0.137 |
idth | +0.137 |
tails | +0.136 |
Neg logit contributions | |
ILCS | -0.171 |
illo | -0.165 |
ESA | -0.161 |
Fed | -0.160 |
ilt | -0.159 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.73e+00 |
Pos logit contributions | |
ILCS | +2.256 |
illo | +2.197 |
Fed | +2.090 |
ilt | +2.084 |
ESA | +2.082 |
Neg logit contributions | |
liners | -3.135 |
idth | -3.007 |
disguise | -2.997 |
DRAGON | -2.965 |
tails | -2.960 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
illo | +4.732 |
ILCS | +4.701 |
nard | +4.435 |
ilt | +4.288 |
Fed | +4.277 |
Neg logit contributions | |
liners | -8.232 |
idth | -8.154 |
proble | -8.114 |
comings | -7.982 |
retty | -7.978 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.83e+00 |
Pos logit contributions | |
illo | +4.504 |
ILCS | +4.491 |
nard | +4.220 |
ilt | +4.104 |
Fed | +4.098 |
Neg logit contributions | |
liners | -7.652 |
idth | -7.561 |
proble | -7.472 |
comings | -7.360 |
retty | -7.355 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
ILCS | +4.147 |
illo | +4.132 |
nard | +3.873 |
ilt | +3.795 |
Fed | +3.793 |
Neg logit contributions | |
liners | -6.467 |
idth | -6.346 |
DRAGON | -6.198 |
tails | -6.165 |
proble | -6.164 |
Token | - |
Token ID | 532 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
ILCS | +4.081 |
illo | +4.045 |
ilt | +3.771 |
nard | +3.761 |
Fed | +3.754 |
Neg logit contributions | |
liners | -5.316 |
DRAGON | -5.086 |
disguise | -5.079 |
idth | -5.066 |
tails | -4.990 |
Token | January |
Token ID | 3269 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ILCS | +0.609 |
illo | +0.592 |
ESA | +0.579 |
Fed | +0.574 |
ilt | +0.572 |
Neg logit contributions | |
liners | -0.387 |
disguise | -0.364 |
idth | -0.358 |
DRAGON | -0.356 |
tails | -0.355 |
Token | 4 |
Token ID | 604 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ILCS | +2.062 |
illo | +2.019 |
ESA | +1.952 |
Fed | +1.949 |
ilt | +1.937 |
Neg logit contributions | |
liners | -1.798 |
idth | -1.705 |
disguise | -1.698 |
tails | -1.675 |
proble | -1.673 |
Token | ATCH |
Token ID | 11417 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
liners | +0.545 |
disguise | +0.520 |
DRAGON | +0.514 |
idth | +0.510 |
tails | +0.510 |
Neg logit contributions | |
ILCS | -0.549 |
illo | -0.527 |
ESA | -0.514 |
Fed | -0.508 |
ilt | -0.505 |
Token | EW |
Token ID | 6217 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
ILCS | +0.997 |
illo | +0.969 |
ESA | +0.945 |
Fed | +0.930 |
ilt | +0.928 |
Neg logit contributions | |
liners | -0.927 |
disguise | -0.881 |
idth | -0.865 |
DRAGON | -0.858 |
tails | -0.856 |
Token | AN |
Token ID | 1565 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
ILCS | +0.055 |
illo | +0.053 |
ESA | +0.052 |
Fed | +0.051 |
ilt | +0.051 |
Neg logit contributions | |
liners | -0.055 |
disguise | -0.052 |
DRAGON | -0.051 |
idth | -0.051 |
tails | -0.051 |
Token | - |
Token ID | 532 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
ILCS | +1.489 |
illo | +1.445 |
ESA | +1.407 |
Fed | +1.388 |
ilt | +1.385 |
Neg logit contributions | |
liners | -1.369 |
disguise | -1.302 |
idth | -1.281 |
DRAGON | -1.273 |
tails | -1.268 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
ILCS | +2.546 |
illo | +2.492 |
ilt | +2.363 |
Fed | +2.362 |
nard | +2.359 |
Neg logit contributions | |
liners | -3.613 |
idth | -3.478 |
disguise | -3.444 |
DRAGON | -3.416 |
tails | -3.411 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.87e+00 |
Pos logit contributions | |
illo | +4.480 |
ILCS | +4.478 |
nard | +4.202 |
ilt | +4.055 |
Fed | +4.052 |
Neg logit contributions | |
liners | -7.832 |
idth | -7.746 |
proble | -7.654 |
comings | -7.561 |
tails | -7.533 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.49e+00 |
Pos logit contributions | |
illo | +4.372 |
ILCS | +4.371 |
nard | +4.093 |
ilt | +3.972 |
Fed | +3.972 |
Neg logit contributions | |
liners | -7.530 |
idth | -7.439 |
proble | -7.322 |
comings | -7.237 |
tails | -7.236 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
ILCS | +3.980 |
illo | +3.953 |
nard | +3.703 |
Fed | +3.634 |
ilt | +3.629 |
Neg logit contributions | |
liners | -6.218 |
idth | -6.088 |
DRAGON | -5.946 |
tails | -5.930 |
proble | -5.911 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
ILCS | +3.718 |
illo | +3.683 |
ilt | +3.429 |
nard | +3.421 |
ESA | +3.419 |
Neg logit contributions | |
liners | -4.995 |
idth | -4.780 |
disguise | -4.774 |
DRAGON | -4.770 |
tails | -4.704 |
Token | - |
Token ID | 532 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
ILCS | +3.635 |
illo | +3.565 |
ESA | +3.398 |
ilt | +3.392 |
Fed | +3.383 |
Neg logit contributions | |
liners | -3.335 |
disguise | -3.175 |
DRAGON | -3.151 |
idth | -3.143 |
tails | -3.100 |
Token | September |
Token ID | 2693 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ILCS | +0.633 |
illo | +0.615 |
ESA | +0.601 |
Fed | +0.596 |
ilt | +0.594 |
Neg logit contributions | |
liners | -0.429 |
disguise | -0.404 |
idth | -0.399 |
DRAGON | -0.396 |
tails | -0.395 |
Token | B |
Token ID | 347 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ILCS | +2.336 |
illo | +2.260 |
ilt | +2.181 |
ESA | +2.175 |
Fed | +2.173 |
Neg logit contributions | |
liners | -1.865 |
idth | -1.754 |
disguise | -1.742 |
tails | -1.723 |
DRAGON | -1.702 |
Token | iz |
Token ID | 528 |
Feature activation | +3.16e-03 |
Pos logit contributions | |
ILCS | +0.718 |
illo | +0.698 |
ESA | +0.679 |
ilt | +0.672 |
Fed | +0.669 |
Neg logit contributions | |
liners | -0.708 |
disguise | -0.679 |
DRAGON | -0.666 |
idth | -0.662 |
tails | -0.659 |
Token | r |
Token ID | 81 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
liners | +0.002 |
disguise | +0.002 |
DRAGON | +0.002 |
idth | +0.002 |
tails | +0.002 |
Neg logit contributions | |
ILCS | -0.002 |
illo | -0.002 |
ESA | -0.002 |
Fed | -0.002 |
ilt | -0.002 |
Token | Pix |
Token ID | 21642 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ILCS | +0.297 |
illo | +0.286 |
ESA | +0.279 |
Fed | +0.275 |
ilt | +0.274 |
Neg logit contributions | |
liners | -0.305 |
disguise | -0.291 |
DRAGON | -0.287 |
idth | -0.286 |
tails | -0.285 |
Token | - |
Token ID | 532 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
ILCS | +1.265 |
illo | +1.236 |
ESA | +1.189 |
ilt | +1.183 |
Fed | +1.182 |
Neg logit contributions | |
liners | -1.164 |
disguise | -1.114 |
DRAGON | -1.094 |
idth | -1.090 |
tails | -1.078 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.77e+00 |
Pos logit contributions | |
ILCS | +2.135 |
illo | +2.077 |
ilt | +1.971 |
Fed | +1.970 |
ESA | +1.966 |
Neg logit contributions | |
liners | -2.939 |
idth | -2.812 |
disguise | -2.809 |
DRAGON | -2.778 |
tails | -2.770 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.14e+00 |
Pos logit contributions | |
ILCS | +4.373 |
illo | +4.361 |
nard | +4.094 |
ilt | +3.991 |
Fed | +3.976 |
Neg logit contributions | |
liners | -7.442 |
idth | -7.312 |
proble | -7.190 |
tails | -7.121 |
comings | -7.119 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
ILCS | +4.203 |
illo | +4.173 |
nard | +3.922 |
ilt | +3.846 |
Fed | +3.836 |
Neg logit contributions | |
liners | -6.826 |
idth | -6.685 |
proble | -6.532 |
tails | -6.515 |
DRAGON | -6.504 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.12e+00 |
Pos logit contributions | |
ILCS | +3.875 |
illo | +3.871 |
ilt | +3.585 |
nard | +3.578 |
Fed | +3.541 |
Neg logit contributions | |
liners | -5.918 |
idth | -5.696 |
DRAGON | -5.641 |
disguise | -5.629 |
tails | -5.577 |
Token | favorite |
Token ID | 4004 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
ILCS | +3.757 |
illo | +3.708 |
ilt | +3.481 |
ESA | +3.468 |
nard | +3.461 |
Neg logit contributions | |
liners | -4.715 |
disguise | -4.500 |
DRAGON | -4.493 |
idth | -4.471 |
tails | -4.415 |
Token | - |
Token ID | 532 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ILCS | +3.574 |
illo | +3.504 |
ESA | +3.348 |
ilt | +3.338 |
Fed | +3.335 |
Neg logit contributions | |
liners | -3.233 |
disguise | -3.071 |
DRAGON | -3.048 |
idth | -3.035 |
tails | -2.992 |
Token | unk |
Token ID | 2954 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ILCS | +1.096 |
illo | +1.068 |
ESA | +1.030 |
ilt | +1.025 |
Fed | +1.021 |
Neg logit contributions | |
liners | -1.052 |
disguise | -1.008 |
DRAGON | -0.992 |
idth | -0.982 |
tails | -0.974 |
Token | rock |
Token ID | 10823 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
liners | +1.437 |
disguise | +1.358 |
tails | +1.345 |
idth | +1.337 |
DRAGON | +1.334 |
Neg logit contributions | |
ILCS | -1.634 |
illo | -1.560 |
ESA | -1.549 |
Fed | -1.527 |
ilt | -1.503 |
Token | - |
Token ID | 532 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
liners | +0.077 |
disguise | +0.073 |
DRAGON | +0.072 |
tails | +0.072 |
idth | +0.072 |
Neg logit contributions | |
ILCS | -0.094 |
illo | -0.090 |
ESA | -0.089 |
Fed | -0.087 |
ilt | -0.087 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
ILCS | +2.968 |
illo | +2.891 |
ilt | +2.778 |
Fed | +2.740 |
ESA | +2.725 |
Neg logit contributions | |
liners | -4.444 |
idth | -4.303 |
disguise | -4.262 |
DRAGON | -4.217 |
tails | -4.211 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
illo | +4.899 |
ILCS | +4.853 |
ilt | +4.516 |
Fed | +4.447 |
nard | +4.411 |
Neg logit contributions | |
liners | -9.054 |
idth | -8.749 |
DRAGON | -8.616 |
disguise | -8.614 |
tails | -8.607 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.60e+00 |
Pos logit contributions | |
illo | +4.858 |
ILCS | +4.805 |
ilt | +4.492 |
Fed | +4.420 |
nard | +4.395 |
Neg logit contributions | |
liners | -8.392 |
idth | -8.052 |
DRAGON | -7.990 |
disguise | -7.990 |
tails | -7.932 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
illo | +4.679 |
ILCS | +4.651 |
ilt | +4.341 |
nard | +4.285 |
Fed | +4.280 |
Neg logit contributions | |
liners | -6.989 |
idth | -6.670 |
DRAGON | -6.666 |
disguise | -6.656 |
tails | -6.562 |
Token | - |
Token ID | 532 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ILCS | +4.599 |
illo | +4.583 |
ilt | +4.301 |
Fed | +4.273 |
ESA | +4.262 |
Neg logit contributions | |
liners | -5.540 |
disguise | -5.272 |
DRAGON | -5.265 |
idth | -5.259 |
tails | -5.167 |
Token | December |
Token ID | 3426 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ILCS | +1.415 |
illo | +1.376 |
ESA | +1.344 |
Fed | +1.332 |
ilt | +1.329 |
Neg logit contributions | |
liners | -0.952 |
disguise | -0.897 |
DRAGON | -0.883 |
idth | -0.882 |
tails | -0.878 |
Token | 13 |
Token ID | 1511 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
ILCS | +0.931 |
illo | +0.905 |
ESA | +0.880 |
Fed | +0.874 |
ilt | +0.871 |
Neg logit contributions | |
liners | -0.750 |
disguise | -0.711 |
idth | -0.702 |
DRAGON | -0.695 |
tails | -0.695 |
Token | , |
Token ID | 11 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
ILCS | +2.566 |
illo | +2.486 |
Fed | +2.418 |
ESA | +2.407 |
nard | +2.390 |
Neg logit contributions | |
liners | -2.621 |
disguise | -2.494 |
idth | -2.483 |
DRAGON | -2.464 |
tails | -2.442 |
Token | : |
Token ID | 25 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
ILCS | +3.637 |
illo | +3.633 |
Fed | +3.523 |
ESA | +3.450 |
ilt | +3.448 |
Neg logit contributions | |
proble | -3.870 |
liners | -3.829 |
idth | -3.729 |
disguise | -3.722 |
conflic | -3.696 |
Token | Mike |
Token ID | 4995 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
ILCS | +2.311 |
illo | +2.236 |
ilt | +2.159 |
ESA | +2.153 |
Fed | +2.150 |
Neg logit contributions | |
liners | -1.849 |
idth | -1.737 |
disguise | -1.727 |
tails | -1.709 |
DRAGON | -1.687 |
Token | M |
Token ID | 44 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
ILCS | +0.562 |
illo | +0.543 |
ESA | +0.528 |
Fed | +0.522 |
ilt | +0.520 |
Neg logit contributions | |
liners | -0.568 |
disguise | -0.543 |
DRAGON | -0.534 |
idth | -0.533 |
tails | -0.530 |
Token | anners |
Token ID | 15672 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
ILCS | +0.807 |
illo | +0.788 |
ESA | +0.771 |
ilt | +0.761 |
Fed | +0.760 |
Neg logit contributions | |
liners | -0.522 |
disguise | -0.495 |
DRAGON | -0.486 |
idth | -0.478 |
tails | -0.477 |
Token | - |
Token ID | 532 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
ILCS | +0.317 |
illo | +0.306 |
ESA | +0.299 |
Fed | +0.295 |
ilt | +0.294 |
Neg logit contributions | |
liners | -0.281 |
disguise | -0.268 |
DRAGON | -0.263 |
idth | -0.262 |
tails | -0.261 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.59e+00 |
Pos logit contributions | |
ILCS | +2.407 |
illo | +2.355 |
ilt | +2.234 |
Fed | +2.231 |
nard | +2.223 |
Neg logit contributions | |
liners | -3.360 |
idth | -3.230 |
disguise | -3.209 |
DRAGON | -3.180 |
tails | -3.179 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
ILCS | +4.313 |
illo | +4.298 |
nard | +4.037 |
ilt | +3.923 |
Fed | +3.912 |
Neg logit contributions | |
liners | -7.254 |
idth | -7.149 |
proble | -7.060 |
tails | -6.964 |
DRAGON | -6.957 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.88e+00 |
Pos logit contributions | |
ILCS | +4.176 |
illo | +4.155 |
nard | +3.901 |
ilt | +3.809 |
Fed | +3.800 |
Neg logit contributions | |
liners | -6.867 |
idth | -6.757 |
proble | -6.641 |
tails | -6.585 |
DRAGON | -6.581 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
ILCS | +3.760 |
illo | +3.719 |
nard | +3.493 |
ilt | +3.439 |
Fed | +3.437 |
Neg logit contributions | |
liners | -5.650 |
idth | -5.525 |
DRAGON | -5.406 |
tails | -5.382 |
disguise | -5.370 |
Token | favorite |
Token ID | 4004 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
ILCS | +3.582 |
illo | +3.530 |
ilt | +3.314 |
ESA | +3.308 |
nard | +3.299 |
Neg logit contributions | |
liners | -4.411 |
disguise | -4.219 |
DRAGON | -4.205 |
idth | -4.201 |
tails | -4.140 |
Token | - |
Token ID | 532 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ILCS | +3.342 |
illo | +3.273 |
ESA | +3.131 |
ilt | +3.120 |
Fed | +3.117 |
Neg logit contributions | |
liners | -2.974 |
disguise | -2.832 |
DRAGON | -2.801 |
idth | -2.793 |
tails | -2.754 |
Token | wt |
Token ID | 46569 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
liners | +1.410 |
disguise | +1.326 |
tails | +1.318 |
idth | +1.315 |
DRAGON | +1.298 |
Neg logit contributions | |
ILCS | -1.379 |
illo | -1.307 |
ESA | -1.288 |
Fed | -1.267 |
ilt | -1.246 |
Token | 0001 |
Token ID | 18005 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
ILCS | +1.581 |
illo | +1.543 |
ESA | +1.484 |
ilt | +1.480 |
Fed | +1.470 |
Neg logit contributions | |
liners | -1.524 |
disguise | -1.461 |
DRAGON | -1.440 |
idth | -1.418 |
tails | -1.416 |
Token | - |
Token ID | 532 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
ILCS | +2.100 |
illo | +2.050 |
ESA | +1.981 |
ilt | +1.972 |
Fed | +1.966 |
Neg logit contributions | |
liners | -1.902 |
disguise | -1.809 |
idth | -1.779 |
DRAGON | -1.776 |
tails | -1.754 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
ILCS | +3.072 |
illo | +3.032 |
ilt | +2.879 |
Fed | +2.865 |
nard | +2.850 |
Neg logit contributions | |
liners | -4.658 |
idth | -4.523 |
disguise | -4.448 |
tails | -4.415 |
DRAGON | -4.407 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.97e+00 |
Pos logit contributions | |
illo | +4.871 |
ILCS | +4.838 |
nard | +4.545 |
ilt | +4.433 |
Fed | +4.373 |
Neg logit contributions | |
liners | -9.140 |
idth | -9.068 |
proble | -8.978 |
retty | -8.919 |
comings | -8.878 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.46e+00 |
Pos logit contributions | |
illo | +4.744 |
ILCS | +4.728 |
nard | +4.429 |
ilt | +4.347 |
Fed | +4.295 |
Neg logit contributions | |
liners | -8.499 |
idth | -8.419 |
proble | -8.271 |
retty | -8.231 |
comings | -8.188 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
illo | +4.415 |
ILCS | +4.387 |
ilt | +4.068 |
nard | +4.055 |
Fed | +4.000 |
Neg logit contributions | |
liners | -7.023 |
idth | -6.783 |
DRAGON | -6.703 |
disguise | -6.691 |
tails | -6.624 |
Token | - |
Token ID | 532 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ILCS | +4.368 |
illo | +4.327 |
ilt | +4.060 |
Fed | +4.032 |
nard | +4.031 |
Neg logit contributions | |
liners | -5.058 |
disguise | -4.830 |
DRAGON | -4.812 |
idth | -4.797 |
tails | -4.711 |
Token | July |
Token ID | 2901 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
ILCS | +0.995 |
illo | +0.966 |
ESA | +0.944 |
Fed | +0.937 |
ilt | +0.932 |
Neg logit contributions | |
liners | -0.688 |
disguise | -0.647 |
idth | -0.640 |
DRAGON | -0.634 |
tails | -0.634 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
ILCS | +1.864 |
illo | +1.817 |
ESA | +1.761 |
Fed | +1.755 |
ilt | +1.746 |
Neg logit contributions | |
liners | -1.616 |
disguise | -1.540 |
idth | -1.534 |
tails | -1.508 |
DRAGON | -1.504 |
Token | , |
Token ID | 11 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
ILCS | +2.425 |
illo | +2.363 |
ESA | +2.293 |
Fed | +2.291 |
ilt | +2.268 |
Neg logit contributions | |
liners | -2.405 |
disguise | -2.310 |
idth | -2.296 |
DRAGON | -2.277 |
proble | -2.270 |
Token | Mike |
Token ID | 4995 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
ILCS | +2.311 |
illo | +2.236 |
ilt | +2.159 |
ESA | +2.153 |
Fed | +2.150 |
Neg logit contributions | |
liners | -1.849 |
idth | -1.737 |
disguise | -1.727 |
tails | -1.709 |
DRAGON | -1.687 |
Token | M |
Token ID | 44 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
ILCS | +0.562 |
illo | +0.543 |
ESA | +0.528 |
Fed | +0.522 |
ilt | +0.520 |
Neg logit contributions | |
liners | -0.568 |
disguise | -0.543 |
DRAGON | -0.534 |
idth | -0.533 |
tails | -0.530 |
Token | anners |
Token ID | 15672 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
ILCS | +0.807 |
illo | +0.788 |
ESA | +0.771 |
ilt | +0.761 |
Fed | +0.760 |
Neg logit contributions | |
liners | -0.522 |
disguise | -0.495 |
DRAGON | -0.486 |
idth | -0.478 |
tails | -0.477 |
Token | - |
Token ID | 532 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
ILCS | +0.317 |
illo | +0.306 |
ESA | +0.299 |
Fed | +0.295 |
ilt | +0.294 |
Neg logit contributions | |
liners | -0.281 |
disguise | -0.268 |
DRAGON | -0.263 |
idth | -0.262 |
tails | -0.261 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.59e+00 |
Pos logit contributions | |
ILCS | +2.407 |
illo | +2.355 |
ilt | +2.234 |
Fed | +2.231 |
nard | +2.223 |
Neg logit contributions | |
liners | -3.360 |
idth | -3.230 |
disguise | -3.209 |
DRAGON | -3.180 |
tails | -3.179 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
ILCS | +4.313 |
illo | +4.298 |
nard | +4.037 |
ilt | +3.923 |
Fed | +3.912 |
Neg logit contributions | |
liners | -7.254 |
idth | -7.149 |
proble | -7.060 |
tails | -6.964 |
DRAGON | -6.957 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.88e+00 |
Pos logit contributions | |
ILCS | +4.176 |
illo | +4.155 |
nard | +3.901 |
ilt | +3.809 |
Fed | +3.800 |
Neg logit contributions | |
liners | -6.867 |
idth | -6.757 |
proble | -6.641 |
tails | -6.585 |
DRAGON | -6.581 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
ILCS | +3.760 |
illo | +3.719 |
nard | +3.493 |
ilt | +3.439 |
Fed | +3.437 |
Neg logit contributions | |
liners | -5.650 |
idth | -5.525 |
DRAGON | -5.406 |
tails | -5.382 |
disguise | -5.370 |
Token | favorite |
Token ID | 4004 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
ILCS | +3.582 |
illo | +3.530 |
ilt | +3.314 |
ESA | +3.308 |
nard | +3.299 |
Neg logit contributions | |
liners | -4.411 |
disguise | -4.219 |
DRAGON | -4.205 |
idth | -4.201 |
tails | -4.140 |
Token | - |
Token ID | 532 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ILCS | +3.342 |
illo | +3.273 |
ESA | +3.131 |
ilt | +3.120 |
Fed | +3.117 |
Neg logit contributions | |
liners | -2.974 |
disguise | -2.832 |
DRAGON | -2.801 |
idth | -2.793 |
tails | -2.754 |
Token | December |
Token ID | 3426 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ILCS | +0.492 |
illo | +0.479 |
ESA | +0.468 |
Fed | +0.464 |
ilt | +0.462 |
Neg logit contributions | |
liners | -0.298 |
disguise | -0.279 |
idth | -0.274 |
DRAGON | -0.273 |
tails | -0.272 |
Token | iz |
Token ID | 528 |
Feature activation | +3.16e-03 |
Pos logit contributions | |
ILCS | +0.718 |
illo | +0.698 |
ESA | +0.679 |
ilt | +0.672 |
Fed | +0.669 |
Neg logit contributions | |
liners | -0.708 |
disguise | -0.679 |
DRAGON | -0.666 |
idth | -0.662 |
tails | -0.659 |
Token | r |
Token ID | 81 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
liners | +0.002 |
disguise | +0.002 |
DRAGON | +0.002 |
idth | +0.002 |
tails | +0.002 |
Neg logit contributions | |
ILCS | -0.002 |
illo | -0.002 |
ESA | -0.002 |
Fed | -0.002 |
ilt | -0.002 |
Token | Pix |
Token ID | 21642 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ILCS | +0.297 |
illo | +0.286 |
ESA | +0.279 |
Fed | +0.275 |
ilt | +0.274 |
Neg logit contributions | |
liners | -0.305 |
disguise | -0.291 |
DRAGON | -0.287 |
idth | -0.286 |
tails | -0.285 |
Token | - |
Token ID | 532 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
ILCS | +1.265 |
illo | +1.236 |
ESA | +1.189 |
ilt | +1.183 |
Fed | +1.182 |
Neg logit contributions | |
liners | -1.164 |
disguise | -1.114 |
DRAGON | -1.094 |
idth | -1.090 |
tails | -1.078 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.77e+00 |
Pos logit contributions | |
ILCS | +2.135 |
illo | +2.077 |
ilt | +1.971 |
Fed | +1.970 |
ESA | +1.966 |
Neg logit contributions | |
liners | -2.939 |
idth | -2.812 |
disguise | -2.809 |
DRAGON | -2.778 |
tails | -2.770 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.14e+00 |
Pos logit contributions | |
ILCS | +4.373 |
illo | +4.361 |
nard | +4.094 |
ilt | +3.991 |
Fed | +3.976 |
Neg logit contributions | |
liners | -7.442 |
idth | -7.312 |
proble | -7.190 |
tails | -7.121 |
comings | -7.119 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
ILCS | +4.203 |
illo | +4.173 |
nard | +3.922 |
ilt | +3.846 |
Fed | +3.836 |
Neg logit contributions | |
liners | -6.826 |
idth | -6.685 |
proble | -6.532 |
tails | -6.515 |
DRAGON | -6.504 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.12e+00 |
Pos logit contributions | |
ILCS | +3.875 |
illo | +3.871 |
ilt | +3.585 |
nard | +3.578 |
Fed | +3.541 |
Neg logit contributions | |
liners | -5.918 |
idth | -5.696 |
DRAGON | -5.641 |
disguise | -5.629 |
tails | -5.577 |
Token | favorite |
Token ID | 4004 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
ILCS | +3.757 |
illo | +3.708 |
ilt | +3.481 |
ESA | +3.468 |
nard | +3.461 |
Neg logit contributions | |
liners | -4.715 |
disguise | -4.500 |
DRAGON | -4.493 |
idth | -4.471 |
tails | -4.415 |
Token | - |
Token ID | 532 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ILCS | +3.574 |
illo | +3.504 |
ESA | +3.348 |
ilt | +3.338 |
Fed | +3.335 |
Neg logit contributions | |
liners | -3.233 |
disguise | -3.071 |
DRAGON | -3.048 |
idth | -3.035 |
tails | -2.992 |
Token | January |
Token ID | 3269 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
ILCS | +0.123 |
illo | +0.120 |
ESA | +0.117 |
Fed | +0.116 |
ilt | +0.115 |
Neg logit contributions | |
liners | -0.078 |
disguise | -0.074 |
DRAGON | -0.072 |
idth | -0.072 |
tails | -0.072 |
Token | ler |
Token ID | 1754 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
liners | +0.911 |
disguise | +0.864 |
idth | +0.852 |
DRAGON | +0.852 |
tails | +0.852 |
Neg logit contributions | |
ILCS | -0.939 |
illo | -0.905 |
ESA | -0.883 |
Fed | -0.870 |
ilt | -0.865 |
Token | oy |
Token ID | 726 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
liners | +0.324 |
disguise | +0.308 |
DRAGON | +0.303 |
idth | +0.302 |
tails | +0.301 |
Neg logit contributions | |
ILCS | -0.361 |
illo | -0.350 |
ESA | -0.341 |
Fed | -0.337 |
ilt | -0.336 |
Token | - |
Token ID | 532 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
liners | +0.146 |
disguise | +0.139 |
DRAGON | +0.137 |
idth | +0.137 |
tails | +0.136 |
Neg logit contributions | |
ILCS | -0.171 |
illo | -0.165 |
ESA | -0.161 |
Fed | -0.160 |
ilt | -0.159 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.73e+00 |
Pos logit contributions | |
ILCS | +2.256 |
illo | +2.197 |
Fed | +2.090 |
ilt | +2.084 |
ESA | +2.082 |
Neg logit contributions | |
liners | -3.135 |
idth | -3.007 |
disguise | -2.997 |
DRAGON | -2.965 |
tails | -2.960 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
illo | +4.732 |
ILCS | +4.701 |
nard | +4.435 |
ilt | +4.288 |
Fed | +4.277 |
Neg logit contributions | |
liners | -8.232 |
idth | -8.154 |
proble | -8.114 |
comings | -7.982 |
retty | -7.978 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.83e+00 |
Pos logit contributions | |
illo | +4.504 |
ILCS | +4.491 |
nard | +4.220 |
ilt | +4.104 |
Fed | +4.098 |
Neg logit contributions | |
liners | -7.652 |
idth | -7.561 |
proble | -7.472 |
comings | -7.360 |
retty | -7.355 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
ILCS | +4.147 |
illo | +4.132 |
nard | +3.873 |
ilt | +3.795 |
Fed | +3.793 |
Neg logit contributions | |
liners | -6.467 |
idth | -6.346 |
DRAGON | -6.198 |
tails | -6.165 |
proble | -6.164 |
Token | - |
Token ID | 532 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
ILCS | +4.081 |
illo | +4.045 |
ilt | +3.771 |
nard | +3.761 |
Fed | +3.754 |
Neg logit contributions | |
liners | -5.316 |
DRAGON | -5.086 |
disguise | -5.079 |
idth | -5.066 |
tails | -4.990 |
Token | January |
Token ID | 3269 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ILCS | +0.609 |
illo | +0.592 |
ESA | +0.579 |
Fed | +0.574 |
ilt | +0.572 |
Neg logit contributions | |
liners | -0.387 |
disguise | -0.364 |
idth | -0.358 |
DRAGON | -0.356 |
tails | -0.355 |
Token | 4 |
Token ID | 604 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ILCS | +2.062 |
illo | +2.019 |
ESA | +1.952 |
Fed | +1.949 |
ilt | +1.937 |
Neg logit contributions | |
liners | -1.798 |
idth | -1.705 |
disguise | -1.698 |
tails | -1.675 |
proble | -1.673 |
Token | , |
Token ID | 11 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ILCS | +1.552 |
illo | +1.505 |
ESA | +1.465 |
Fed | +1.452 |
ilt | +1.444 |
Neg logit contributions | |
liners | -1.430 |
disguise | -1.365 |
DRAGON | -1.342 |
idth | -1.342 |
tails | -1.331 |
Token | Flag |
Token ID | 19762 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
liners | +0.281 |
disguise | +0.267 |
DRAGON | +0.262 |
idth | +0.261 |
tails | +0.260 |
Neg logit contributions | |
ILCS | -0.361 |
illo | -0.351 |
ESA | -0.342 |
Fed | -0.339 |
ilt | -0.337 |
Token |
|
Token ID | 198 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
ILCS | +0.480 |
illo | +0.473 |
ESA | +0.453 |
Fed | +0.451 |
ilt | +0.444 |
Neg logit contributions | |
liners | -0.444 |
disguise | -0.423 |
tails | -0.418 |
DRAGON | -0.415 |
idth | -0.411 |
Token |
|
Token ID | 198 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
ILCS | +1.653 |
illo | +1.606 |
ESA | +1.569 |
Fed | +1.557 |
ilt | +1.543 |
Neg logit contributions | |
liners | -1.451 |
disguise | -1.388 |
idth | -1.366 |
DRAGON | -1.361 |
tails | -1.343 |
Token | Flag |
Token ID | 34227 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
ILCS | +2.207 |
illo | +2.147 |
ESA | +2.106 |
Fed | +2.094 |
ilt | +2.073 |
Neg logit contributions | |
liners | -2.234 |
disguise | -2.179 |
DRAGON | -2.134 |
idth | -2.127 |
tails | -2.080 |
Token | Reply |
Token ID | 14883 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
ILCS | +1.851 |
illo | +1.781 |
ESA | +1.699 |
Fed | +1.691 |
ilt | +1.678 |
Neg logit contributions | |
liners | -2.601 |
disguise | -2.469 |
tails | -2.456 |
idth | -2.454 |
DRAGON | -2.428 |
Token |
|
Token ID | 198 |
Feature activation | -7.55e+00 |
Pos logit contributions | |
ILCS | +2.275 |
illo | +2.226 |
ESA | +2.133 |
Fed | +2.110 |
ilt | +2.078 |
Neg logit contributions | |
liners | -2.181 |
disguise | -2.065 |
idth | -2.055 |
DRAGON | -2.027 |
tails | -2.011 |
Token |
|
Token ID | 198 |
Feature activation | -6.99e+00 |
Pos logit contributions | |
ILCS | +4.624 |
illo | +4.593 |
Fed | +4.534 |
ESA | +4.472 |
nard | +4.398 |
Neg logit contributions | |
proble | -6.024 |
conflic | -5.888 |
idth | -5.697 |
liners | -5.667 |
thous | -5.653 |
Token | 14 |
Token ID | 1415 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
ILCS | +4.047 |
ESA | +3.977 |
illo | +3.915 |
Fed | +3.908 |
ilt | +3.776 |
Neg logit contributions | |
liners | -5.589 |
disguise | -5.384 |
idth | -5.355 |
DRAGON | -5.299 |
ancest | -5.248 |
Token | Recommend |
Token ID | 30361 |
Feature activation | -7.12e+00 |
Pos logit contributions | |
ILCS | +1.386 |
illo | +1.255 |
ESA | +1.178 |
Fed | +1.174 |
ilt | +1.144 |
Neg logit contributions | |
liners | -4.562 |
disguise | -4.392 |
idth | -4.378 |
tails | -4.350 |
DRAGON | -4.348 |
Token |
|
Token ID | 198 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
ILCS | +4.616 |
illo | +4.561 |
Fed | +4.379 |
ESA | +4.323 |
ilt | +4.266 |
Neg logit contributions | |
liners | -5.298 |
proble | -5.218 |
idth | -5.044 |
disguise | -5.015 |
ancest | -4.991 |
Token |
|
Token ID | 198 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
ILCS | +3.213 |
illo | +3.144 |
ESA | +3.060 |
Fed | +3.052 |
ilt | +3.026 |
Neg logit contributions | |
liners | -3.174 |
idth | -3.076 |
proble | -3.069 |
disguise | -3.039 |
DRAGON | -3.011 |
Token | EW |
Token ID | 6217 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
ILCS | +0.997 |
illo | +0.969 |
ESA | +0.945 |
Fed | +0.930 |
ilt | +0.928 |
Neg logit contributions | |
liners | -0.927 |
disguise | -0.881 |
idth | -0.865 |
DRAGON | -0.858 |
tails | -0.856 |
Token | AN |
Token ID | 1565 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
ILCS | +0.055 |
illo | +0.053 |
ESA | +0.052 |
Fed | +0.051 |
ilt | +0.051 |
Neg logit contributions | |
liners | -0.055 |
disguise | -0.052 |
DRAGON | -0.051 |
idth | -0.051 |
tails | -0.051 |
Token | - |
Token ID | 532 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
ILCS | +1.489 |
illo | +1.445 |
ESA | +1.407 |
Fed | +1.388 |
ilt | +1.385 |
Neg logit contributions | |
liners | -1.369 |
disguise | -1.302 |
idth | -1.281 |
DRAGON | -1.273 |
tails | -1.268 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
ILCS | +2.546 |
illo | +2.492 |
ilt | +2.363 |
Fed | +2.362 |
nard | +2.359 |
Neg logit contributions | |
liners | -3.613 |
idth | -3.478 |
disguise | -3.444 |
DRAGON | -3.416 |
tails | -3.411 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.87e+00 |
Pos logit contributions | |
illo | +4.480 |
ILCS | +4.478 |
nard | +4.202 |
ilt | +4.055 |
Fed | +4.052 |
Neg logit contributions | |
liners | -7.832 |
idth | -7.746 |
proble | -7.654 |
comings | -7.561 |
tails | -7.533 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.49e+00 |
Pos logit contributions | |
illo | +4.372 |
ILCS | +4.371 |
nard | +4.093 |
ilt | +3.972 |
Fed | +3.972 |
Neg logit contributions | |
liners | -7.530 |
idth | -7.439 |
proble | -7.322 |
comings | -7.237 |
tails | -7.236 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
ILCS | +3.980 |
illo | +3.953 |
nard | +3.703 |
Fed | +3.634 |
ilt | +3.629 |
Neg logit contributions | |
liners | -6.218 |
idth | -6.088 |
DRAGON | -5.946 |
tails | -5.930 |
proble | -5.911 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
ILCS | +3.718 |
illo | +3.683 |
ilt | +3.429 |
nard | +3.421 |
ESA | +3.419 |
Neg logit contributions | |
liners | -4.995 |
idth | -4.780 |
disguise | -4.774 |
DRAGON | -4.770 |
tails | -4.704 |
Token | - |
Token ID | 532 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
ILCS | +3.635 |
illo | +3.565 |
ESA | +3.398 |
ilt | +3.392 |
Fed | +3.383 |
Neg logit contributions | |
liners | -3.335 |
disguise | -3.175 |
DRAGON | -3.151 |
idth | -3.143 |
tails | -3.100 |
Token | September |
Token ID | 2693 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ILCS | +0.633 |
illo | +0.615 |
ESA | +0.601 |
Fed | +0.596 |
ilt | +0.594 |
Neg logit contributions | |
liners | -0.429 |
disguise | -0.404 |
idth | -0.399 |
DRAGON | -0.396 |
tails | -0.395 |
Token | 26 |
Token ID | 2608 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
ILCS | +1.214 |
illo | +1.180 |
ESA | +1.148 |
Fed | +1.142 |
ilt | +1.136 |
Neg logit contributions | |
liners | -1.016 |
disguise | -0.966 |
idth | -0.956 |
DRAGON | -0.946 |
tails | -0.944 |
Token | ur |
Token ID | 333 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
ILCS | +0.079 |
illo | +0.076 |
ESA | +0.074 |
ilt | +0.073 |
Fed | +0.073 |
Neg logit contributions | |
liners | -0.078 |
disguise | -0.074 |
DRAGON | -0.073 |
idth | -0.073 |
tails | -0.073 |
Token | ker |
Token ID | 6122 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ILCS | +0.255 |
illo | +0.246 |
ESA | +0.238 |
Fed | +0.236 |
ilt | +0.235 |
Neg logit contributions | |
liners | -0.294 |
disguise | -0.282 |
DRAGON | -0.278 |
idth | -0.276 |
tails | -0.276 |
Token | - |
Token ID | 532 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
ILCS | +1.470 |
illo | +1.430 |
ESA | +1.388 |
Fed | +1.379 |
ilt | +1.373 |
Neg logit contributions | |
liners | -1.268 |
disguise | -1.207 |
DRAGON | -1.185 |
idth | -1.183 |
tails | -1.170 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.79e+00 |
Pos logit contributions | |
ILCS | +2.705 |
illo | +2.654 |
ilt | +2.520 |
Fed | +2.513 |
nard | +2.499 |
Neg logit contributions | |
liners | -3.947 |
idth | -3.819 |
disguise | -3.774 |
DRAGON | -3.739 |
tails | -3.735 |
Token | favorite |
Token ID | 4004 |
Feature activation | -9.10e+00 |
Pos logit contributions | |
illo | +4.704 |
ILCS | +4.685 |
nard | +4.424 |
ilt | +4.299 |
Fed | +4.263 |
Neg logit contributions | |
liners | -8.337 |
idth | -8.239 |
proble | -8.141 |
retty | -8.055 |
comings | -8.045 |
Token | favorite |
Token ID | 4004 |
Feature activation | -7.43e+00 |
Pos logit contributions | |
illo | +4.503 |
ILCS | +4.500 |
nard | +4.233 |
ilt | +4.145 |
Fed | +4.115 |
Neg logit contributions | |
liners | -7.676 |
idth | -7.568 |
proble | -7.433 |
retty | -7.358 |
tails | -7.357 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
illo | +3.966 |
ILCS | +3.952 |
ilt | +3.680 |
nard | +3.673 |
Fed | +3.628 |
Neg logit contributions | |
liners | -6.124 |
idth | -5.954 |
DRAGON | -5.830 |
disguise | -5.815 |
tails | -5.792 |
Token | favorite |
Token ID | 4004 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
ILCS | +3.779 |
illo | +3.727 |
ilt | +3.515 |
ESA | +3.504 |
Fed | +3.503 |
Neg logit contributions | |
liners | -4.376 |
disguise | -4.174 |
DRAGON | -4.154 |
idth | -4.141 |
tails | -4.085 |
Token | - |
Token ID | 532 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
ILCS | +3.356 |
illo | +3.281 |
ESA | +3.148 |
Fed | +3.137 |
ilt | +3.132 |
Neg logit contributions | |
liners | -2.960 |
disguise | -2.813 |
DRAGON | -2.782 |
idth | -2.774 |
tails | -2.738 |
Token | February |
Token ID | 3945 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
liners | +0.235 |
disguise | +0.223 |
DRAGON | +0.218 |
idth | +0.216 |
tails | +0.215 |
Neg logit contributions | |
ILCS | -0.339 |
illo | -0.329 |
ESA | -0.322 |
Fed | -0.319 |
ilt | -0.318 |
Token | 9 |
Token ID | 860 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
ILCS | +1.067 |
illo | +1.039 |
ESA | +1.008 |
Fed | +1.002 |
ilt | +0.998 |
Neg logit contributions | |
liners | -0.889 |
disguise | -0.844 |
idth | -0.835 |
DRAGON | -0.825 |
tails | -0.824 |
Token | S |
Token ID | 311 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
liners | +1.025 |
disguise | +0.978 |
idth | +0.954 |
DRAGON | +0.953 |
tails | +0.941 |
Neg logit contributions | |
ILCS | -1.464 |
illo | -1.414 |
ESA | -1.387 |
ilt | -1.375 |
Fed | -1.375 |
Token | otom |
Token ID | 43125 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
ILCS | +0.167 |
illo | +0.159 |
ESA | +0.154 |
Fed | +0.152 |
ilt | +0.151 |
Neg logit contributions | |
liners | -0.261 |
disguise | -0.251 |
idth | -0.248 |
DRAGON | -0.247 |
tails | -0.245 |
Token | ay |
Token ID | 323 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
liners | +0.324 |
disguise | +0.310 |
idth | +0.303 |
tails | +0.303 |
DRAGON | +0.302 |
Neg logit contributions | |
ILCS | -0.347 |
illo | -0.331 |
ESA | -0.326 |
Fed | -0.321 |
ilt | -0.319 |
Token | or |
Token ID | 273 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
liners | +1.613 |
disguise | +1.473 |
idth | +1.449 |
DRAGON | +1.446 |
tails | +1.442 |
Neg logit contributions | |
ILCS | -2.593 |
ESA | -2.456 |
illo | -2.436 |
Fed | -2.405 |
ilt | -2.362 |
Token | Jr |
Token ID | 7504 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
liners | +1.969 |
disguise | +1.891 |
DRAGON | +1.861 |
idth | +1.851 |
tails | +1.825 |
Neg logit contributions | |
ILCS | -1.901 |
illo | -1.813 |
ESA | -1.793 |
ilt | -1.760 |
Fed | -1.757 |
Token | ., |
Token ID | 1539 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
liners | +1.091 |
disguise | +1.032 |
DRAGON | +1.019 |
idth | +1.013 |
tails | +0.996 |
Neg logit contributions | |
ILCS | -1.446 |
illo | -1.397 |
ESA | -1.370 |
Fed | -1.355 |
ilt | -1.347 |
Token | known |
Token ID | 1900 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
liners | +1.509 |
disguise | +1.420 |
DRAGON | +1.385 |
idth | +1.364 |
tails | +1.335 |
Neg logit contributions | |
ILCS | -2.838 |
illo | -2.738 |
ESA | -2.726 |
Fed | -2.690 |
ilt | -2.664 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
liners | +1.415 |
disguise | +1.331 |
DRAGON | +1.292 |
tails | +1.290 |
idth | +1.278 |
Neg logit contributions | |
ILCS | -2.184 |
illo | -2.098 |
ESA | -2.073 |
ilt | -2.045 |
Fed | -2.040 |
Token | his |
Token ID | 465 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
liners | +0.809 |
disguise | +0.770 |
DRAGON | +0.751 |
idth | +0.746 |
tails | +0.741 |
Neg logit contributions | |
ILCS | -1.163 |
illo | -1.129 |
ESA | -1.104 |
Fed | -1.093 |
ilt | -1.090 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
liners | +0.524 |
disguise | +0.495 |
DRAGON | +0.480 |
idth | +0.476 |
tails | +0.472 |
Neg logit contributions | |
ILCS | -0.984 |
illo | -0.958 |
ESA | -0.941 |
Fed | -0.931 |
ilt | -0.927 |
Token | as |
Token ID | 355 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
liners | +0.946 |
disguise | +0.884 |
DRAGON | +0.867 |
tails | +0.863 |
idth | +0.851 |
Neg logit contributions | |
ILCS | -1.441 |
illo | -1.391 |
ESA | -1.376 |
ilt | -1.356 |
Fed | -1.351 |
Token | , |
Token ID | 11 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
liners | +0.220 |
disguise | +0.210 |
DRAGON | +0.207 |
idth | +0.205 |
tails | +0.204 |
Neg logit contributions | |
ILCS | -0.231 |
illo | -0.223 |
ESA | -0.218 |
ilt | -0.215 |
Fed | -0.215 |
Token | or |
Token ID | 393 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
ILCS | +0.345 |
illo | +0.336 |
ESA | +0.327 |
Fed | +0.324 |
ilt | +0.322 |
Neg logit contributions | |
liners | -0.268 |
disguise | -0.254 |
DRAGON | -0.249 |
idth | -0.249 |
tails | -0.247 |
Token | contact |
Token ID | 2800 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
liners | +0.023 |
disguise | +0.021 |
DRAGON | +0.021 |
tails | +0.021 |
idth | +0.021 |
Neg logit contributions | |
ILCS | -0.026 |
illo | -0.026 |
ESA | -0.025 |
Fed | -0.025 |
ilt | -0.025 |
Token | Customer |
Token ID | 22092 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
liners | +0.630 |
disguise | +0.594 |
DRAGON | +0.581 |
idth | +0.579 |
tails | +0.576 |
Neg logit contributions | |
ILCS | -1.008 |
illo | -0.980 |
ESA | -0.958 |
Fed | -0.949 |
ilt | -0.946 |
Token | Service |
Token ID | 4809 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
liners | +1.425 |
disguise | +1.367 |
DRAGON | +1.349 |
tails | +1.342 |
idth | +1.340 |
Neg logit contributions | |
ILCS | -1.277 |
illo | -1.222 |
ESA | -1.183 |
Fed | -1.166 |
ilt | -1.160 |
Token | at |
Token ID | 379 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
liners | +0.848 |
disguise | +0.805 |
DRAGON | +0.790 |
idth | +0.787 |
tails | +0.783 |
Neg logit contributions | |
ILCS | -1.087 |
illo | -1.054 |
ESA | -1.029 |
Fed | -1.018 |
ilt | -1.014 |
Token | 1 |
Token ID | 352 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
liners | +2.099 |
disguise | +2.001 |
DRAGON | +1.942 |
tails | +1.924 |
idth | +1.918 |
Neg logit contributions | |
ILCS | -2.617 |
illo | -2.527 |
ESA | -2.461 |
ilt | -2.437 |
nard | -2.432 |
Token | - |
Token ID | 12 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
liners | +0.718 |
disguise | +0.691 |
DRAGON | +0.682 |
idth | +0.681 |
tails | +0.677 |
Neg logit contributions | |
ILCS | -0.470 |
illo | -0.449 |
ESA | -0.433 |
Fed | -0.427 |
ilt | -0.424 |
Token | 800 |
Token ID | 7410 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
liners | +1.128 |
disguise | +1.084 |
DRAGON | +1.069 |
idth | +1.066 |
tails | +1.061 |
Neg logit contributions | |
ILCS | -0.853 |
illo | -0.819 |
ESA | -0.794 |
Fed | -0.782 |
ilt | -0.778 |
Token | - |
Token ID | 12 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
liners | +0.243 |
disguise | +0.234 |
DRAGON | +0.231 |
tails | +0.230 |
idth | +0.229 |
Neg logit contributions | |
ILCS | -0.168 |
illo | -0.161 |
ESA | -0.156 |
Fed | -0.153 |
ilt | -0.153 |
Token | 8 |
Token ID | 23 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
ILCS | +0.299 |
illo | +0.290 |
ESA | +0.283 |
Fed | +0.280 |
ilt | +0.277 |
Neg logit contributions | |
liners | -0.300 |
disguise | -0.287 |
DRAGON | -0.282 |
idth | -0.282 |
tails | -0.278 |
Token | size |
Token ID | 2546 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
ILCS | +0.435 |
illo | +0.421 |
ESA | +0.407 |
ilt | +0.405 |
Fed | +0.402 |
Neg logit contributions | |
liners | -0.483 |
disguise | -0.459 |
DRAGON | -0.454 |
idth | -0.452 |
tails | -0.451 |
Token | _ |
Token ID | 62 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
liners | +1.383 |
disguise | +1.321 |
idth | +1.298 |
DRAGON | +1.291 |
tails | +1.278 |
Neg logit contributions | |
ILCS | -1.662 |
illo | -1.608 |
ESA | -1.569 |
Fed | -1.545 |
ilt | -1.543 |
Token | t |
Token ID | 83 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
liners | +0.407 |
disguise | +0.389 |
DRAGON | +0.383 |
idth | +0.380 |
tails | +0.377 |
Neg logit contributions | |
ILCS | -0.466 |
illo | -0.452 |
ESA | -0.440 |
Fed | -0.436 |
ilt | -0.435 |
Token | num |
Token ID | 997 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
liners | +0.758 |
disguise | +0.717 |
DRAGON | +0.704 |
idth | +0.702 |
tails | +0.700 |
Neg logit contributions | |
ILCS | -0.989 |
illo | -0.960 |
ESA | -0.936 |
Fed | -0.926 |
ilt | -0.925 |
Token | Part |
Token ID | 7841 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
liners | +2.008 |
disguise | +1.904 |
tails | +1.889 |
idth | +1.883 |
DRAGON | +1.875 |
Neg logit contributions | |
ILCS | -1.640 |
illo | -1.582 |
ESA | -1.534 |
Fed | -1.497 |
ilt | -1.493 |
Token | icles |
Token ID | 2983 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
liners | +1.371 |
disguise | +1.254 |
tails | +1.218 |
idth | +1.209 |
DRAGON | +1.208 |
Neg logit contributions | |
ILCS | -3.029 |
illo | -2.935 |
ESA | -2.887 |
Fed | -2.848 |
ilt | -2.844 |
Token | = |
Token ID | 796 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
liners | +1.770 |
disguise | +1.670 |
DRAGON | +1.627 |
idth | +1.626 |
tails | +1.618 |
Neg logit contributions | |
ILCS | -2.754 |
illo | -2.670 |
ESA | -2.602 |
ilt | -2.562 |
Fed | -2.561 |
Token | particles |
Token ID | 13166 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
ILCS | +0.046 |
illo | +0.045 |
ESA | +0.043 |
ilt | +0.043 |
Fed | +0.043 |
Neg logit contributions | |
liners | -0.037 |
disguise | -0.035 |
idth | -0.035 |
DRAGON | -0.034 |
tails | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
liners | +2.603 |
disguise | +2.496 |
DRAGON | +2.428 |
idth | +2.417 |
tails | +2.407 |
Neg logit contributions | |
ILCS | -2.973 |
illo | -2.864 |
ESA | -2.808 |
Fed | -2.748 |
nard | -2.727 |
Token | Size |
Token ID | 10699 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
liners | +1.863 |
disguise | +1.779 |
DRAGON | +1.744 |
idth | +1.744 |
tails | +1.744 |
Neg logit contributions | |
ILCS | -1.769 |
illo | -1.705 |
ESA | -1.655 |
Fed | -1.630 |
ilt | -1.626 |
Token | () |
Token ID | 3419 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
ILCS | +0.785 |
illo | +0.761 |
ESA | +0.740 |
Fed | +0.737 |
ilt | +0.731 |
Neg logit contributions | |
liners | -0.733 |
disguise | -0.699 |
DRAGON | -0.689 |
idth | -0.687 |
tails | -0.685 |
Token | potential |
Token ID | 2785 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
liners | +0.496 |
disguise | +0.471 |
DRAGON | +0.462 |
idth | +0.460 |
tails | +0.458 |
Neg logit contributions | |
ILCS | -0.639 |
illo | -0.620 |
ESA | -0.605 |
Fed | -0.599 |
ilt | -0.596 |
Token | side |
Token ID | 1735 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
liners | +0.863 |
disguise | +0.821 |
DRAGON | +0.802 |
idth | +0.799 |
tails | +0.795 |
Neg logit contributions | |
ILCS | -1.173 |
illo | -1.136 |
ESA | -1.110 |
Fed | -1.100 |
ilt | -1.094 |
Token | effects |
Token ID | 3048 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
liners | +1.120 |
disguise | +1.052 |
DRAGON | +1.027 |
idth | +1.024 |
tails | +1.020 |
Neg logit contributions | |
ILCS | -1.901 |
illo | -1.847 |
ESA | -1.809 |
Fed | -1.793 |
ilt | -1.785 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
liners | +0.892 |
disguise | +0.853 |
DRAGON | +0.836 |
idth | +0.833 |
tails | +0.830 |
Neg logit contributions | |
ILCS | -0.959 |
illo | -0.926 |
ESA | -0.904 |
Fed | -0.891 |
ilt | -0.889 |
Token | The |
Token ID | 383 |
Feature activation | +6.09e-03 |
Pos logit contributions | |
ILCS | +0.089 |
illo | +0.087 |
ESA | +0.085 |
Fed | +0.084 |
ilt | +0.084 |
Neg logit contributions | |
liners | -0.067 |
disguise | -0.063 |
idth | -0.062 |
tails | -0.061 |
DRAGON | -0.061 |
Token | aim |
Token ID | 4031 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
liners | +0.003 |
disguise | +0.003 |
DRAGON | +0.003 |
idth | +0.003 |
tails | +0.003 |
Neg logit contributions | |
ILCS | -0.005 |
illo | -0.005 |
ESA | -0.005 |
Fed | -0.005 |
ilt | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
liners | +1.963 |
disguise | +1.851 |
idth | +1.818 |
tails | +1.796 |
DRAGON | +1.785 |
Neg logit contributions | |
ILCS | -2.990 |
illo | -2.865 |
ESA | -2.804 |
Fed | -2.785 |
ilt | -2.772 |
Token | this |
Token ID | 428 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
ILCS | +1.065 |
illo | +1.038 |
ESA | +1.009 |
ilt | +0.995 |
Fed | +0.991 |
Neg logit contributions | |
liners | -1.113 |
disguise | -1.048 |
DRAGON | -1.037 |
tails | -1.035 |
idth | -1.035 |
Token | study |
Token ID | 2050 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ILCS | +0.531 |
illo | +0.516 |
ESA | +0.501 |
Fed | +0.494 |
ilt | +0.493 |
Neg logit contributions | |
liners | -0.505 |
disguise | -0.479 |
idth | -0.472 |
DRAGON | -0.472 |
tails | -0.469 |
Token | is |
Token ID | 318 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
liners | +1.175 |
disguise | +1.123 |
DRAGON | +1.098 |
idth | +1.096 |
tails | +1.087 |
Neg logit contributions | |
ILCS | -1.480 |
illo | -1.430 |
ESA | -1.396 |
Fed | -1.381 |
ilt | -1.377 |
Token | to |
Token ID | 284 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
ILCS | +0.599 |
illo | +0.585 |
ESA | +0.574 |
Fed | +0.563 |
ilt | +0.563 |
Neg logit contributions | |
liners | -0.409 |
disguise | -0.380 |
DRAGON | -0.376 |
tails | -0.374 |
idth | -0.369 |
Token | ik |
Token ID | 1134 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
ILCS | +0.067 |
illo | +0.065 |
ESA | +0.064 |
Fed | +0.063 |
ilt | +0.063 |
Neg logit contributions | |
liners | -0.053 |
disguise | -0.051 |
DRAGON | -0.050 |
idth | -0.050 |
tails | -0.049 |
Token | unta |
Token ID | 44424 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ILCS | +0.400 |
illo | +0.391 |
ESA | +0.379 |
ilt | +0.377 |
Fed | +0.374 |
Neg logit contributions | |
liners | -0.369 |
disguise | -0.353 |
DRAGON | -0.347 |
idth | -0.344 |
tails | -0.341 |
Token | Th |
Token ID | 536 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ILCS | +1.391 |
illo | +1.360 |
ESA | +1.317 |
ilt | +1.310 |
Fed | +1.308 |
Neg logit contributions | |
liners | -1.127 |
disguise | -1.063 |
tails | -1.049 |
idth | -1.049 |
DRAGON | -1.045 |
Token | ad |
Token ID | 324 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ILCS | +1.459 |
illo | +1.436 |
ilt | +1.379 |
ESA | +1.376 |
Fed | +1.364 |
Neg logit contributions | |
liners | -1.592 |
disguise | -1.524 |
DRAGON | -1.509 |
tails | -1.493 |
idth | -1.481 |
Token | ik |
Token ID | 1134 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ILCS | +1.330 |
illo | +1.317 |
ilt | +1.268 |
ESA | +1.253 |
Fed | +1.251 |
Neg logit contributions | |
liners | -1.244 |
disguise | -1.183 |
DRAGON | -1.170 |
tails | -1.162 |
idth | -1.149 |
Token | omb |
Token ID | 2381 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
ILCS | +0.008 |
illo | +0.007 |
ESA | +0.007 |
Fed | +0.007 |
ilt | +0.007 |
Neg logit contributions | |
liners | -0.010 |
disguise | -0.010 |
DRAGON | -0.009 |
idth | -0.009 |
tails | -0.009 |
Token | u |
Token ID | 84 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
liners | +1.580 |
disguise | +1.475 |
idth | +1.424 |
DRAGON | +1.423 |
tails | +1.394 |
Neg logit contributions | |
ILCS | -4.109 |
illo | -3.926 |
ESA | -3.918 |
Fed | -3.869 |
nard | -3.832 |
Token |
|
Token ID | 198 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
ILCS | +0.067 |
illo | +0.065 |
ESA | +0.063 |
Fed | +0.063 |
ilt | +0.063 |
Neg logit contributions | |
liners | -0.057 |
disguise | -0.054 |
DRAGON | -0.053 |
idth | -0.053 |
tails | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
ILCS | +0.554 |
illo | +0.536 |
ESA | +0.523 |
Fed | +0.516 |
ilt | +0.515 |
Neg logit contributions | |
liners | -0.448 |
disguise | -0.426 |
DRAGON | -0.418 |
tails | -0.415 |
idth | -0.414 |
Token | Sound |
Token ID | 21369 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
liners | +0.069 |
disguise | +0.066 |
DRAGON | +0.065 |
idth | +0.065 |
tails | +0.065 |
Neg logit contributions | |
ILCS | -0.065 |
illo | -0.063 |
ESA | -0.061 |
Fed | -0.060 |
ilt | -0.060 |
Token | ar |
Token ID | 283 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
liners | +1.084 |
disguise | +1.016 |
DRAGON | +0.998 |
idth | +0.995 |
tails | +0.990 |
Neg logit contributions | |
ILCS | -1.732 |
illo | -1.669 |
ESA | -1.643 |
Fed | -1.624 |
ilt | -1.613 |
Token | those |
Token ID | 883 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
liners | +0.361 |
disguise | +0.342 |
DRAGON | +0.336 |
idth | +0.335 |
tails | +0.333 |
Neg logit contributions | |
ILCS | -0.457 |
illo | -0.443 |
ESA | -0.432 |
Fed | -0.428 |
ilt | -0.426 |
Token | intentions |
Token ID | 14953 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
liners | +1.720 |
disguise | +1.620 |
tails | +1.558 |
DRAGON | +1.553 |
idth | +1.534 |
Neg logit contributions | |
ILCS | -2.345 |
illo | -2.271 |
ESA | -2.225 |
Fed | -2.219 |
ilt | -2.200 |
Token | are |
Token ID | 389 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
liners | +0.360 |
disguise | +0.342 |
DRAGON | +0.336 |
idth | +0.335 |
tails | +0.333 |
Neg logit contributions | |
ILCS | -0.441 |
illo | -0.428 |
ESA | -0.417 |
Fed | -0.413 |
ilt | -0.412 |
Token | fleeting |
Token ID | 42738 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
liners | +0.627 |
disguise | +0.594 |
DRAGON | +0.584 |
idth | +0.583 |
tails | +0.579 |
Neg logit contributions | |
ILCS | -0.811 |
illo | -0.787 |
ESA | -0.768 |
Fed | -0.760 |
ilt | -0.757 |
Token | and |
Token ID | 290 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
liners | +0.056 |
disguise | +0.053 |
DRAGON | +0.052 |
idth | +0.052 |
tails | +0.052 |
Neg logit contributions | |
ILCS | -0.061 |
illo | -0.059 |
ESA | -0.058 |
Fed | -0.057 |
ilt | -0.057 |
Token | inconsistent |
Token ID | 18326 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
liners | +0.158 |
disguise | +0.149 |
idth | +0.148 |
DRAGON | +0.148 |
tails | +0.146 |
Neg logit contributions | |
ILCS | -0.192 |
illo | -0.186 |
ESA | -0.181 |
Fed | -0.179 |
ilt | -0.179 |
Token | and |
Token ID | 290 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
liners | +1.545 |
disguise | +1.469 |
DRAGON | +1.433 |
idth | +1.428 |
tails | +1.422 |
Neg logit contributions | |
ILCS | -1.860 |
illo | -1.799 |
ESA | -1.766 |
ilt | -1.740 |
Fed | -1.739 |
Token | subject |
Token ID | 2426 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
liners | +0.359 |
disguise | +0.340 |
DRAGON | +0.335 |
idth | +0.335 |
tails | +0.332 |
Neg logit contributions | |
ILCS | -0.431 |
illo | -0.418 |
ESA | -0.407 |
Fed | -0.403 |
ilt | -0.401 |
Token | to |
Token ID | 284 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ILCS | +0.610 |
illo | +0.592 |
ESA | +0.579 |
Fed | +0.573 |
ilt | +0.572 |
Neg logit contributions | |
liners | -0.395 |
disguise | -0.372 |
DRAGON | -0.364 |
idth | -0.363 |
tails | -0.361 |
Token | revision |
Token ID | 18440 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
ILCS | +0.981 |
illo | +0.958 |
ESA | +0.930 |
Fed | +0.922 |
ilt | +0.919 |
Neg logit contributions | |
liners | -0.782 |
disguise | -0.735 |
idth | -0.735 |
DRAGON | -0.732 |
tails | -0.725 |
Token | . |
Token ID | 13 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
liners | +1.623 |
disguise | +1.544 |
tails | +1.504 |
DRAGON | +1.496 |
idth | +1.490 |
Neg logit contributions | |
ILCS | -1.970 |
illo | -1.890 |
ESA | -1.860 |
Fed | -1.832 |
ilt | -1.813 |
Token | her |
Token ID | 607 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
liners | +1.948 |
disguise | +1.872 |
DRAGON | +1.795 |
tails | +1.789 |
idth | +1.782 |
Neg logit contributions | |
ILCS | -2.658 |
illo | -2.615 |
ESA | -2.550 |
Fed | -2.507 |
ilt | -2.493 |
Token | to |
Token ID | 284 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
liners | +0.647 |
disguise | +0.619 |
DRAGON | +0.602 |
tails | +0.595 |
idth | +0.595 |
Neg logit contributions | |
ILCS | -0.930 |
illo | -0.903 |
ESA | -0.885 |
Fed | -0.873 |
ilt | -0.871 |
Token | live |
Token ID | 2107 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
liners | +0.161 |
disguise | +0.154 |
DRAGON | +0.150 |
idth | +0.150 |
tails | +0.149 |
Neg logit contributions | |
ILCS | -0.200 |
illo | -0.194 |
ESA | -0.189 |
Fed | -0.187 |
ilt | -0.186 |
Token | with |
Token ID | 351 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
ILCS | +0.386 |
illo | +0.376 |
ESA | +0.368 |
Fed | +0.364 |
ilt | +0.363 |
Neg logit contributions | |
liners | -0.222 |
disguise | -0.209 |
DRAGON | -0.205 |
idth | -0.204 |
tails | -0.202 |
Token | them |
Token ID | 606 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
ILCS | +0.548 |
illo | +0.532 |
ESA | +0.521 |
Fed | +0.514 |
ilt | +0.514 |
Neg logit contributions | |
liners | -0.404 |
disguise | -0.379 |
DRAGON | -0.375 |
idth | -0.374 |
tails | -0.371 |
Token | . |
Token ID | 13 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
liners | +0.154 |
disguise | +0.146 |
DRAGON | +0.143 |
idth | +0.143 |
tails | +0.143 |
Neg logit contributions | |
ILCS | -0.179 |
illo | -0.173 |
ESA | -0.169 |
Fed | -0.167 |
ilt | -0.167 |
Token | Ang |
Token ID | 2895 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
ILCS | +0.751 |
illo | +0.726 |
ESA | +0.711 |
Fed | +0.702 |
ilt | +0.697 |
Neg logit contributions | |
liners | -0.609 |
disguise | -0.579 |
idth | -0.569 |
DRAGON | -0.565 |
tails | -0.562 |
Token | ie |
Token ID | 494 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
liners | +0.593 |
disguise | +0.568 |
DRAGON | +0.561 |
idth | +0.560 |
tails | +0.559 |
Neg logit contributions | |
ILCS | -0.413 |
illo | -0.394 |
ESA | -0.382 |
Fed | -0.376 |
ilt | -0.374 |
Token | C |
Token ID | 327 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
ILCS | +1.644 |
illo | +1.599 |
ESA | +1.545 |
Fed | +1.536 |
ilt | +1.525 |
Neg logit contributions | |
liners | -1.510 |
disguise | -1.439 |
DRAGON | -1.419 |
idth | -1.413 |
tails | -1.403 |
Token | rouch |
Token ID | 48626 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ILCS | +0.597 |
illo | +0.578 |
ESA | +0.562 |
Fed | +0.555 |
ilt | +0.553 |
Neg logit contributions | |
liners | -0.578 |
disguise | -0.552 |
DRAGON | -0.543 |
idth | -0.541 |
tails | -0.539 |
Token | reports |
Token ID | 3136 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
ILCS | +0.195 |
illo | +0.189 |
ESA | +0.184 |
Fed | +0.182 |
ilt | +0.182 |
Neg logit contributions | |
liners | -0.175 |
disguise | -0.167 |
DRAGON | -0.164 |
idth | -0.163 |
tails | -0.163 |
Token | belief |
Token ID | 4901 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
liners | +1.068 |
disguise | +1.022 |
DRAGON | +0.991 |
idth | +0.982 |
tails | +0.977 |
Neg logit contributions | |
ILCS | -1.442 |
illo | -1.395 |
ESA | -1.367 |
Fed | -1.347 |
ilt | -1.342 |
Token | that |
Token ID | 326 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
ILCS | +0.876 |
illo | +0.854 |
ESA | +0.831 |
Fed | +0.824 |
ilt | +0.819 |
Neg logit contributions | |
liners | -0.751 |
disguise | -0.714 |
idth | -0.706 |
DRAGON | -0.704 |
tails | -0.699 |
Token | many |
Token ID | 867 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
ILCS | +0.710 |
illo | +0.689 |
ESA | +0.670 |
Fed | +0.665 |
ilt | +0.663 |
Neg logit contributions | |
liners | -0.594 |
disguise | -0.562 |
idth | -0.557 |
DRAGON | -0.555 |
tails | -0.552 |
Token | Muslims |
Token ID | 7045 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
ILCS | +0.438 |
illo | +0.426 |
ESA | +0.415 |
ilt | +0.412 |
Fed | +0.412 |
Neg logit contributions | |
liners | -0.266 |
disguise | -0.248 |
idth | -0.248 |
DRAGON | -0.246 |
tails | -0.244 |
Token | and |
Token ID | 290 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ILCS | +0.354 |
illo | +0.347 |
ESA | +0.334 |
ilt | +0.332 |
Fed | +0.332 |
Neg logit contributions | |
liners | -0.307 |
idth | -0.292 |
DRAGON | -0.291 |
disguise | -0.289 |
tails | -0.288 |
Token | Mormons |
Token ID | 33003 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
liners | +0.191 |
disguise | +0.179 |
DRAGON | +0.175 |
idth | +0.174 |
tails | +0.173 |
Neg logit contributions | |
ILCS | -0.334 |
illo | -0.325 |
ESA | -0.318 |
Fed | -0.315 |
ilt | -0.314 |
Token | share |
Token ID | 2648 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
liners | +0.016 |
disguise | +0.015 |
idth | +0.015 |
DRAGON | +0.015 |
tails | +0.015 |
Neg logit contributions | |
ILCS | -0.019 |
illo | -0.019 |
ESA | -0.018 |
Fed | -0.018 |
ilt | -0.018 |
Token | : |
Token ID | 25 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
liners | +0.352 |
disguise | +0.335 |
DRAGON | +0.329 |
idth | +0.326 |
tails | +0.326 |
Neg logit contributions | |
ILCS | -0.420 |
illo | -0.405 |
ESA | -0.396 |
Fed | -0.390 |
ilt | -0.390 |
Token | That |
Token ID | 1320 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
liners | +0.423 |
disguise | +0.403 |
DRAGON | +0.395 |
idth | +0.392 |
tails | +0.390 |
Neg logit contributions | |
ILCS | -0.561 |
illo | -0.544 |
ESA | -0.532 |
Fed | -0.525 |
ilt | -0.522 |
Token | homosexuality |
Token ID | 19822 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ILCS | +0.735 |
illo | +0.714 |
ESA | +0.696 |
Fed | +0.691 |
ilt | +0.691 |
Neg logit contributions | |
liners | -0.544 |
disguise | -0.510 |
idth | -0.508 |
tails | -0.506 |
DRAGON | -0.504 |
Token | is |
Token ID | 318 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
liners | +0.673 |
disguise | +0.641 |
DRAGON | +0.629 |
idth | +0.627 |
tails | +0.624 |
Neg logit contributions | |
ILCS | -0.766 |
illo | -0.742 |
ESA | -0.723 |
Fed | -0.715 |
ilt | -0.712 |
Token | still |
Token ID | 991 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
liners | +0.079 |
disguise | +0.075 |
DRAGON | +0.074 |
idth | +0.074 |
tails | +0.073 |
Neg logit contributions | |
ILCS | -0.091 |
illo | -0.088 |
ESA | -0.086 |
Fed | -0.085 |
ilt | -0.085 |
Token | comes |
Token ID | 2058 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
ILCS | +0.912 |
illo | +0.891 |
ESA | +0.867 |
Fed | +0.861 |
ilt | +0.856 |
Neg logit contributions | |
liners | -0.780 |
disguise | -0.736 |
idth | -0.734 |
DRAGON | -0.731 |
tails | -0.717 |
Token | with |
Token ID | 351 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ILCS | +2.166 |
illo | +2.115 |
ESA | +2.054 |
Fed | +2.046 |
nard | +2.028 |
Neg logit contributions | |
liners | -1.363 |
disguise | -1.268 |
idth | -1.264 |
DRAGON | -1.256 |
tails | -1.226 |
Token | extreme |
Token ID | 3257 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ILCS | +0.907 |
illo | +0.882 |
ESA | +0.857 |
Fed | +0.849 |
ilt | +0.847 |
Neg logit contributions | |
liners | -0.709 |
disguise | -0.659 |
idth | -0.656 |
DRAGON | -0.651 |
tails | -0.648 |
Token | social |
Token ID | 1919 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
liners | +0.102 |
disguise | +0.096 |
DRAGON | +0.095 |
idth | +0.095 |
tails | +0.094 |
Neg logit contributions | |
ILCS | -0.143 |
illo | -0.139 |
ESA | -0.135 |
Fed | -0.134 |
ilt | -0.134 |
Token | stigma |
Token ID | 26695 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
ILCS | +1.944 |
illo | +1.885 |
ESA | +1.815 |
ilt | +1.803 |
Fed | +1.802 |
Neg logit contributions | |
liners | -1.551 |
idth | -1.473 |
DRAGON | -1.456 |
disguise | -1.448 |
tails | -1.426 |
Token | and |
Token ID | 290 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
ILCS | +0.359 |
illo | +0.347 |
ESA | +0.337 |
Fed | +0.334 |
ilt | +0.332 |
Neg logit contributions | |
liners | -0.337 |
disguise | -0.321 |
DRAGON | -0.316 |
idth | -0.316 |
tails | -0.314 |
Token | risk |
Token ID | 2526 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
liners | +0.044 |
disguise | +0.042 |
DRAGON | +0.041 |
idth | +0.041 |
tails | +0.041 |
Neg logit contributions | |
ILCS | -0.054 |
illo | -0.053 |
ESA | -0.051 |
Fed | -0.051 |
ilt | -0.051 |
Token | for |
Token ID | 329 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ILCS | +0.343 |
illo | +0.334 |
ESA | +0.325 |
Fed | +0.322 |
ilt | +0.321 |
Neg logit contributions | |
liners | -0.257 |
disguise | -0.243 |
idth | -0.239 |
DRAGON | -0.239 |
tails | -0.237 |
Token | violence |
Token ID | 3685 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
liners | +0.641 |
disguise | +0.607 |
DRAGON | +0.595 |
idth | +0.593 |
tails | +0.590 |
Neg logit contributions | |
ILCS | -0.873 |
illo | -0.847 |
ESA | -0.827 |
Fed | -0.819 |
ilt | -0.816 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ILCS | +0.258 |
illo | +0.250 |
ESA | +0.243 |
Fed | +0.240 |
ilt | +0.239 |
Neg logit contributions | |
liners | -0.239 |
disguise | -0.228 |
DRAGON | -0.224 |
idth | -0.224 |
tails | -0.223 |
Token | . |
Token ID | 13 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
ILCS | +1.576 |
illo | +1.536 |
ESA | +1.489 |
Fed | +1.479 |
ilt | +1.472 |
Neg logit contributions | |
liners | -1.518 |
disguise | -1.445 |
idth | -1.431 |
DRAGON | -1.427 |
tails | -1.418 |
Token | Having |
Token ID | 11136 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ILCS | +0.442 |
illo | +0.429 |
ESA | +0.421 |
Fed | +0.417 |
ilt | +0.414 |
Neg logit contributions | |
liners | -0.310 |
disguise | -0.293 |
idth | -0.290 |
DRAGON | -0.285 |
tails | -0.285 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ILCS | +1.208 |
illo | +1.181 |
ESA | +1.142 |
Fed | +1.136 |
ilt | +1.131 |
Neg logit contributions | |
liners | -1.087 |
disguise | -1.026 |
idth | -1.021 |
DRAGON | -1.017 |
tails | -1.015 |
Token | with |
Token ID | 351 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
ILCS | +1.111 |
illo | +1.089 |
ESA | +1.056 |
Fed | +1.051 |
ilt | +1.046 |
Neg logit contributions | |
liners | -0.653 |
disguise | -0.614 |
idth | -0.605 |
DRAGON | -0.602 |
tails | -0.594 |
Token | Pam |
Token ID | 24497 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
ILCS | +1.762 |
illo | +1.715 |
ESA | +1.662 |
ilt | +1.650 |
Fed | +1.648 |
Neg logit contributions | |
liners | -1.585 |
disguise | -1.501 |
idth | -1.500 |
DRAGON | -1.483 |
tails | -1.477 |
Token | as |
Token ID | 355 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
ILCS | +2.961 |
illo | +2.909 |
ilt | +2.792 |
Fed | +2.781 |
ESA | +2.771 |
Neg logit contributions | |
liners | -2.625 |
disguise | -2.492 |
DRAGON | -2.487 |
idth | -2.487 |
tails | -2.438 |
Token | long |
Token ID | 890 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ILCS | +0.484 |
illo | +0.471 |
ESA | +0.459 |
Fed | +0.454 |
ilt | +0.454 |
Neg logit contributions | |
liners | -0.371 |
disguise | -0.351 |
DRAGON | -0.345 |
idth | -0.345 |
tails | -0.343 |
Token | as |
Token ID | 355 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
ILCS | +2.075 |
illo | +2.030 |
ESA | +1.960 |
ilt | +1.944 |
Fed | +1.943 |
Neg logit contributions | |
liners | -1.558 |
disguise | -1.497 |
DRAGON | -1.469 |
idth | -1.461 |
tails | -1.434 |
Token | you |
Token ID | 345 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
liners | +0.307 |
disguise | +0.292 |
DRAGON | +0.287 |
idth | +0.285 |
tails | +0.284 |
Neg logit contributions | |
ILCS | -0.379 |
illo | -0.367 |
ESA | -0.358 |
Fed | -0.354 |
ilt | -0.353 |
Token | did |
Token ID | 750 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ILCS | +0.267 |
illo | +0.258 |
ESA | +0.252 |
Fed | +0.249 |
ilt | +0.248 |
Neg logit contributions | |
liners | -0.232 |
disguise | -0.221 |
DRAGON | -0.217 |
idth | -0.216 |
tails | -0.215 |
Token | , |
Token ID | 11 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
liners | +1.419 |
disguise | +1.354 |
DRAGON | +1.328 |
idth | +1.318 |
tails | +1.315 |
Neg logit contributions | |
ILCS | -1.742 |
illo | -1.686 |
ESA | -1.655 |
Fed | -1.623 |
ilt | -1.616 |
Token | Commonwealth |
Token ID | 17165 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
liners | +0.077 |
disguise | +0.073 |
DRAGON | +0.072 |
idth | +0.071 |
tails | +0.071 |
Neg logit contributions | |
ILCS | -0.096 |
illo | -0.093 |
ESA | -0.090 |
Fed | -0.090 |
ilt | -0.089 |
Token | Parliament |
Token ID | 8411 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
ILCS | +0.545 |
illo | +0.529 |
ESA | +0.518 |
Fed | +0.512 |
ilt | +0.510 |
Neg logit contributions | |
liners | -0.368 |
disguise | -0.347 |
idth | -0.342 |
DRAGON | -0.340 |
tails | -0.338 |
Token | abolished |
Token ID | 32424 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
liners | +0.045 |
disguise | +0.042 |
DRAGON | +0.041 |
idth | +0.041 |
tails | +0.041 |
Neg logit contributions | |
ILCS | -0.058 |
illo | -0.056 |
ESA | -0.055 |
Fed | -0.054 |
ilt | -0.054 |
Token | self |
Token ID | 2116 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
liners | +0.152 |
disguise | +0.146 |
DRAGON | +0.142 |
idth | +0.140 |
tails | +0.140 |
Neg logit contributions | |
ILCS | -0.199 |
illo | -0.192 |
ESA | -0.188 |
Fed | -0.186 |
ilt | -0.185 |
Token | - |
Token ID | 12 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
liners | +2.028 |
disguise | +1.950 |
tails | +1.907 |
DRAGON | +1.904 |
idth | +1.882 |
Neg logit contributions | |
ILCS | -1.558 |
illo | -1.483 |
Fed | -1.428 |
ESA | -1.424 |
nard | -1.412 |
Token | government |
Token ID | 14480 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ILCS | +0.896 |
illo | +0.875 |
ESA | +0.850 |
ilt | +0.841 |
Fed | +0.838 |
Neg logit contributions | |
liners | -1.019 |
disguise | -0.986 |
idth | -0.975 |
DRAGON | -0.972 |
tails | -0.950 |
Token | , |
Token ID | 11 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
ILCS | +1.407 |
illo | +1.361 |
ESA | +1.334 |
Fed | +1.316 |
ilt | +1.310 |
Neg logit contributions | |
liners | -1.191 |
idth | -1.131 |
disguise | -1.125 |
DRAGON | -1.119 |
tails | -1.113 |
Token | integrating |
Token ID | 32029 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
liners | +0.462 |
disguise | +0.438 |
DRAGON | +0.429 |
idth | +0.426 |
tails | +0.425 |
Neg logit contributions | |
ILCS | -0.636 |
illo | -0.618 |
ESA | -0.603 |
Fed | -0.596 |
ilt | -0.595 |
Token | Norfolk |
Token ID | 32134 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
liners | +0.120 |
disguise | +0.113 |
DRAGON | +0.111 |
idth | +0.111 |
tails | +0.110 |
Neg logit contributions | |
ILCS | -0.160 |
illo | -0.156 |
ESA | -0.152 |
Fed | -0.150 |
ilt | -0.150 |
Token | Island |
Token ID | 5451 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
liners | +0.545 |
disguise | +0.508 |
DRAGON | +0.494 |
idth | +0.492 |
tails | +0.489 |
Neg logit contributions | |
ILCS | -1.124 |
illo | -1.095 |
ESA | -1.073 |
Fed | -1.064 |
ilt | -1.061 |
Token | into |
Token ID | 656 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
liners | +1.405 |
disguise | +1.326 |
DRAGON | +1.293 |
tails | +1.287 |
idth | +1.283 |
Neg logit contributions | |
ILCS | -2.151 |
illo | -2.090 |
ESA | -2.039 |
Fed | -2.022 |
ilt | -2.013 |
Token | , |
Token ID | 11 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
ILCS | +1.338 |
illo | +1.299 |
ESA | +1.267 |
Fed | +1.263 |
ilt | +1.250 |
Neg logit contributions | |
liners | -1.152 |
disguise | -1.098 |
idth | -1.090 |
DRAGON | -1.087 |
tails | -1.081 |
Token | they |
Token ID | 484 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
ILCS | +0.450 |
illo | +0.437 |
ESA | +0.427 |
Fed | +0.424 |
ilt | +0.422 |
Neg logit contributions | |
liners | -0.347 |
disguise | -0.328 |
idth | -0.324 |
DRAGON | -0.324 |
tails | -0.324 |
Token | were |
Token ID | 547 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ILCS | +0.775 |
illo | +0.756 |
ESA | +0.739 |
Fed | +0.730 |
ilt | +0.729 |
Neg logit contributions | |
liners | -0.626 |
idth | -0.587 |
disguise | -0.586 |
DRAGON | -0.586 |
tails | -0.585 |
Token | cur |
Token ID | 1090 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
ILCS | +0.970 |
illo | +0.945 |
ESA | +0.928 |
Fed | +0.923 |
ilt | +0.915 |
Neg logit contributions | |
liners | -0.717 |
idth | -0.681 |
disguise | -0.678 |
tails | -0.672 |
DRAGON | -0.672 |
Token | t |
Token ID | 83 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
liners | +0.313 |
disguise | +0.296 |
DRAGON | +0.290 |
idth | +0.289 |
tails | +0.288 |
Neg logit contributions | |
ILCS | -0.436 |
illo | -0.423 |
ESA | -0.413 |
Fed | -0.409 |
ilt | -0.407 |
Token | ailing |
Token ID | 11608 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
liners | +0.701 |
disguise | +0.666 |
DRAGON | +0.655 |
idth | +0.652 |
tails | +0.649 |
Neg logit contributions | |
ILCS | -0.875 |
illo | -0.849 |
ESA | -0.828 |
Fed | -0.820 |
ilt | -0.818 |
Token | holiday |
Token ID | 9912 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
ILCS | +1.598 |
illo | +1.557 |
ESA | +1.516 |
Fed | +1.508 |
ilt | +1.497 |
Neg logit contributions | |
liners | -1.395 |
idth | -1.314 |
disguise | -1.313 |
DRAGON | -1.307 |
tails | -1.307 |
Token | decorations |
Token ID | 39011 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ILCS | +2.409 |
illo | +2.362 |
ESA | +2.306 |
Fed | +2.282 |
ilt | +2.277 |
Neg logit contributions | |
liners | -1.916 |
DRAGON | -1.820 |
idth | -1.817 |
disguise | -1.812 |
tails | -1.795 |
Token | to |
Token ID | 284 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
ILCS | +0.907 |
illo | +0.885 |
ESA | +0.861 |
Fed | +0.855 |
ilt | +0.850 |
Neg logit contributions | |
liners | -0.787 |
disguise | -0.748 |
idth | -0.742 |
DRAGON | -0.740 |
tails | -0.735 |
Token | match |
Token ID | 2872 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
ILCS | +0.223 |
illo | +0.217 |
ESA | +0.212 |
Fed | +0.211 |
ilt | +0.210 |
Neg logit contributions | |
liners | -0.168 |
idth | -0.157 |
DRAGON | -0.157 |
tails | -0.157 |
disguise | -0.157 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
liners | +0.435 |
disguise | +0.413 |
DRAGON | +0.406 |
idth | +0.404 |
tails | +0.402 |
Neg logit contributions | |
ILCS | -0.565 |
illo | -0.549 |
ESA | -0.536 |
Fed | -0.530 |
ilt | -0.528 |
Token | frenzy |
Token ID | 31934 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ILCS | +0.606 |
illo | +0.591 |
ESA | +0.577 |
ilt | +0.573 |
Fed | +0.572 |
Neg logit contributions | |
liners | -0.378 |
disguise | -0.352 |
idth | -0.351 |
DRAGON | -0.348 |
tails | -0.347 |
Token | ? |
Token ID | 30 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ILCS | +1.876 |
illo | +1.822 |
ESA | +1.755 |
Fed | +1.754 |
ilt | +1.746 |
Neg logit contributions | |
liners | -1.765 |
disguise | -1.672 |
idth | -1.671 |
tails | -1.657 |
DRAGON | -1.654 |
Token | Sure |
Token ID | 10889 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
liners | +0.934 |
disguise | +0.885 |
DRAGON | +0.871 |
idth | +0.861 |
tails | +0.859 |
Neg logit contributions | |
ILCS | -1.298 |
illo | -1.260 |
ESA | -1.231 |
Fed | -1.217 |
ilt | -1.214 |
Token | , |
Token ID | 11 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
liners | +1.051 |
disguise | +1.002 |
DRAGON | +0.984 |
idth | +0.979 |
tails | +0.976 |
Neg logit contributions | |
ILCS | -1.127 |
illo | -1.088 |
ESA | -1.061 |
Fed | -1.049 |
ilt | -1.044 |
Token | why |
Token ID | 1521 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
liners | +0.039 |
disguise | +0.036 |
idth | +0.036 |
DRAGON | +0.036 |
tails | +0.036 |
Neg logit contributions | |
ILCS | -0.050 |
illo | -0.049 |
ESA | -0.047 |
Fed | -0.047 |
ilt | -0.047 |
Token | not |
Token ID | 407 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
liners | +0.305 |
disguise | +0.287 |
idth | +0.285 |
DRAGON | +0.284 |
tails | +0.282 |
Neg logit contributions | |
ILCS | -0.409 |
illo | -0.398 |
ESA | -0.388 |
ilt | -0.385 |
Fed | -0.384 |
Token | ? |
Token ID | 30 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ILCS | +1.881 |
illo | +1.822 |
ilt | +1.765 |
ESA | +1.763 |
Fed | +1.748 |
Neg logit contributions | |
liners | -2.232 |
idth | -2.139 |
tails | -2.101 |
disguise | -2.086 |
DRAGON | -2.082 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
liners | +1.272 |
disguise | +1.206 |
DRAGON | +1.197 |
tails | +1.170 |
idth | +1.166 |
Neg logit contributions | |
ILCS | -1.714 |
illo | -1.660 |
ESA | -1.620 |
ilt | -1.600 |
Fed | -1.598 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
liners | +0.868 |
disguise | +0.815 |
DRAGON | +0.806 |
tails | +0.800 |
ROCK | +0.779 |
Neg logit contributions | |
ILCS | -1.205 |
illo | -1.160 |
ESA | -1.127 |
ilt | -1.116 |
nard | -1.104 |
Token | Not |
Token ID | 3673 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
liners | +0.761 |
disguise | +0.718 |
DRAGON | +0.710 |
tails | +0.710 |
idth | +0.701 |
Neg logit contributions | |
ILCS | -0.807 |
illo | -0.779 |
ESA | -0.746 |
ilt | -0.739 |
nard | -0.736 |
Token | too |
Token ID | 1165 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ILCS | +0.501 |
illo | +0.487 |
ESA | +0.474 |
Fed | +0.470 |
ilt | +0.468 |
Neg logit contributions | |
liners | -0.399 |
disguise | -0.378 |
DRAGON | -0.372 |
idth | -0.371 |
tails | -0.368 |
Token | ' |
Token ID | 705 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
liners | +0.231 |
disguise | +0.219 |
DRAGON | +0.215 |
idth | +0.214 |
tails | +0.213 |
Neg logit contributions | |
ILCS | -0.297 |
illo | -0.288 |
ESA | -0.281 |
Fed | -0.278 |
ilt | -0.277 |
Token | Very |
Token ID | 16371 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
liners | +0.232 |
disguise | +0.221 |
DRAGON | +0.217 |
idth | +0.216 |
tails | +0.216 |
Neg logit contributions | |
ILCS | -0.267 |
illo | -0.258 |
ESA | -0.251 |
Fed | -0.248 |
ilt | -0.248 |
Token | little |
Token ID | 1310 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
ILCS | +1.748 |
illo | +1.704 |
ESA | +1.652 |
ilt | +1.633 |
Fed | +1.631 |
Neg logit contributions | |
liners | -1.520 |
disguise | -1.435 |
idth | -1.429 |
DRAGON | -1.423 |
tails | -1.415 |
Token | was |
Token ID | 373 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ILCS | +3.680 |
illo | +3.559 |
ESA | +3.497 |
ilt | +3.383 |
nard | +3.363 |
Neg logit contributions | |
liners | -3.664 |
idth | -3.501 |
disguise | -3.389 |
tails | -3.386 |
soType | -3.378 |
Token | known |
Token ID | 1900 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
ILCS | +1.501 |
illo | +1.448 |
ESA | +1.418 |
ilt | +1.380 |
Fed | +1.376 |
Neg logit contributions | |
liners | -1.943 |
idth | -1.858 |
disguise | -1.849 |
DRAGON | -1.846 |
tails | -1.830 |
Token | about |
Token ID | 546 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
liners | +0.500 |
disguise | +0.472 |
DRAGON | +0.462 |
idth | +0.460 |
tails | +0.458 |
Neg logit contributions | |
ILCS | -0.772 |
illo | -0.750 |
ESA | -0.733 |
Fed | -0.726 |
ilt | -0.724 |
Token | the |
Token ID | 262 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
ILCS | +1.962 |
illo | +1.903 |
ESA | +1.846 |
ilt | +1.813 |
Fed | +1.812 |
Neg logit contributions | |
liners | -1.821 |
idth | -1.724 |
disguise | -1.714 |
DRAGON | -1.711 |
tails | -1.706 |
Token | native |
Token ID | 6868 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ILCS | +0.342 |
illo | +0.334 |
ESA | +0.325 |
Fed | +0.321 |
ilt | +0.321 |
Neg logit contributions | |
liners | -0.237 |
disguise | -0.222 |
idth | -0.220 |
DRAGON | -0.220 |
tails | -0.218 |
Token | monkey |
Token ID | 21657 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
liners | +0.180 |
disguise | +0.170 |
DRAGON | +0.168 |
idth | +0.167 |
tails | +0.166 |
Neg logit contributions | |
ILCS | -0.235 |
illo | -0.229 |
ESA | -0.223 |
Fed | -0.221 |
ilt | -0.220 |
Token | from |
Token ID | 422 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
liners | +0.627 |
disguise | +0.596 |
DRAGON | +0.584 |
idth | +0.582 |
tails | +0.580 |
Neg logit contributions | |
ILCS | -0.794 |
illo | -0.770 |
ESA | -0.751 |
Fed | -0.743 |
ilt | -0.741 |
Token | this |
Token ID | 428 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
ILCS | +0.282 |
illo | +0.274 |
ESA | +0.266 |
Fed | +0.263 |
ilt | +0.263 |
Neg logit contributions | |
liners | -0.217 |
disguise | -0.205 |
DRAGON | -0.202 |
idth | -0.202 |
tails | -0.200 |
Token | ifications |
Token ID | 6637 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
ILCS | +0.836 |
illo | +0.818 |
ESA | +0.789 |
ilt | +0.785 |
Fed | +0.782 |
Neg logit contributions | |
liners | -0.860 |
disguise | -0.818 |
idth | -0.816 |
DRAGON | -0.812 |
tails | -0.806 |
Token | that |
Token ID | 326 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
liners | +0.355 |
disguise | +0.339 |
DRAGON | +0.331 |
idth | +0.328 |
tails | +0.327 |
Neg logit contributions | |
ILCS | -0.420 |
illo | -0.406 |
ESA | -0.396 |
Fed | -0.391 |
ilt | -0.389 |
Token | antagonist |
Token ID | 34667 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
liners | +0.224 |
disguise | +0.214 |
DRAGON | +0.210 |
idth | +0.209 |
tails | +0.208 |
Neg logit contributions | |
ILCS | -0.228 |
illo | -0.220 |
ESA | -0.214 |
Fed | -0.212 |
ilt | -0.211 |
Token | Dr |
Token ID | 1583 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ILCS | +1.925 |
illo | +1.881 |
ESA | +1.833 |
ilt | +1.814 |
Fed | +1.810 |
Neg logit contributions | |
liners | -1.581 |
disguise | -1.485 |
idth | -1.482 |
tails | -1.468 |
DRAGON | -1.460 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ILCS | +0.156 |
illo | +0.151 |
ESA | +0.147 |
Fed | +0.145 |
ilt | +0.145 |
Neg logit contributions | |
liners | -0.148 |
disguise | -0.141 |
DRAGON | -0.139 |
idth | -0.138 |
tails | -0.138 |
Token | M |
Token ID | 337 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
ILCS | +0.935 |
illo | +0.907 |
ESA | +0.882 |
Fed | +0.872 |
ilt | +0.870 |
Neg logit contributions | |
liners | -0.816 |
disguise | -0.774 |
idth | -0.761 |
DRAGON | -0.759 |
tails | -0.756 |
Token | has |
Token ID | 468 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ILCS | +1.478 |
illo | +1.441 |
ESA | +1.402 |
ilt | +1.386 |
Fed | +1.373 |
Neg logit contributions | |
liners | -1.538 |
disguise | -1.473 |
DRAGON | -1.447 |
idth | -1.438 |
tails | -1.435 |
Token | constructed |
Token ID | 12006 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ILCS | +0.146 |
illo | +0.142 |
ESA | +0.138 |
Fed | +0.137 |
ilt | +0.136 |
Neg logit contributions | |
liners | -0.107 |
disguise | -0.102 |
DRAGON | -0.100 |
idth | -0.100 |
tails | -0.099 |
Token | in |
Token ID | 287 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ILCS | +0.849 |
illo | +0.823 |
ESA | +0.801 |
Fed | +0.793 |
ilt | +0.790 |
Neg logit contributions | |
liners | -0.747 |
disguise | -0.710 |
idth | -0.701 |
DRAGON | -0.699 |
tails | -0.697 |
Token | order |
Token ID | 1502 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ILCS | +0.984 |
illo | +0.957 |
ESA | +0.932 |
ilt | +0.924 |
Fed | +0.921 |
Neg logit contributions | |
liners | -0.755 |
idth | -0.713 |
tails | -0.704 |
disguise | -0.700 |
DRAGON | -0.697 |
Token | to |
Token ID | 284 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
liners | +0.612 |
disguise | +0.581 |
DRAGON | +0.560 |
idth | +0.559 |
tails | +0.552 |
Neg logit contributions | |
ILCS | -1.035 |
illo | -1.003 |
ESA | -0.984 |
Fed | -0.973 |
ilt | -0.969 |
Token | BEL |
Token ID | 29991 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
liners | +1.246 |
disguise | +1.200 |
DRAGON | +1.189 |
idth | +1.167 |
tails | +1.166 |
Neg logit contributions | |
ILCS | -1.260 |
illo | -1.212 |
ESA | -1.177 |
ilt | -1.165 |
Fed | -1.165 |
Token | 21 |
Token ID | 2310 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
liners | +2.496 |
disguise | +2.371 |
idth | +2.338 |
DRAGON | +2.319 |
tails | +2.275 |
Neg logit contributions | |
ILCS | -3.446 |
illo | -3.319 |
ESA | -3.229 |
ilt | -3.213 |
Fed | -3.207 |
Token | Jul |
Token ID | 5979 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
liners | +1.605 |
disguise | +1.528 |
DRAGON | +1.505 |
idth | +1.495 |
tails | +1.489 |
Neg logit contributions | |
ILCS | -1.941 |
illo | -1.881 |
ESA | -1.837 |
ilt | -1.814 |
Fed | -1.807 |
Token | ien |
Token ID | 2013 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
ILCS | +1.124 |
illo | +1.102 |
ESA | +1.062 |
ilt | +1.054 |
Fed | +1.054 |
Neg logit contributions | |
liners | -1.040 |
disguise | -0.996 |
DRAGON | -0.980 |
idth | -0.974 |
tails | -0.964 |
Token | Ver |
Token ID | 4643 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
ILCS | +2.157 |
illo | +2.101 |
ESA | +2.047 |
ilt | +2.046 |
Fed | +2.027 |
Neg logit contributions | |
liners | -1.836 |
disguise | -1.732 |
idth | -1.730 |
DRAGON | -1.704 |
tails | -1.682 |
Token | m |
Token ID | 76 |
Feature activation | -6.46e+00 |
Pos logit contributions | |
liners | +0.649 |
disguise | +0.618 |
idth | +0.610 |
DRAGON | +0.609 |
tails | +0.607 |
Neg logit contributions | |
ILCS | -0.631 |
illo | -0.605 |
ESA | -0.591 |
Fed | -0.583 |
ilt | -0.580 |
Token | ote |
Token ID | 1258 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
illo | +4.010 |
ilt | +3.936 |
ILCS | +3.771 |
nard | +3.706 |
ESA | +3.668 |
Neg logit contributions | |
disguise | -4.988 |
DRAGON | -4.890 |
liners | -4.798 |
soType | -4.668 |
ROCK | -4.656 |
Token | ( |
Token ID | 357 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
ILCS | +1.285 |
illo | +1.265 |
ESA | +1.220 |
ilt | +1.205 |
Fed | +1.201 |
Neg logit contributions | |
liners | -1.303 |
disguise | -1.252 |
DRAGON | -1.233 |
idth | -1.219 |
tails | -1.216 |
Token | O |
Token ID | 46 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
ILCS | +0.367 |
illo | +0.353 |
ESA | +0.346 |
Fed | +0.341 |
ilt | +0.338 |
Neg logit contributions | |
liners | -0.437 |
disguise | -0.421 |
idth | -0.414 |
DRAGON | -0.413 |
tails | -0.409 |
Token | mega |
Token ID | 13731 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ILCS | +1.570 |
illo | +1.528 |
ESA | +1.487 |
Fed | +1.468 |
ilt | +1.466 |
Neg logit contributions | |
liners | -2.147 |
disguise | -2.070 |
DRAGON | -2.054 |
idth | -2.049 |
tails | -2.004 |
Token | Pharma |
Token ID | 41845 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
ILCS | +1.595 |
illo | +1.561 |
ESA | +1.523 |
Fed | +1.518 |
ilt | +1.513 |
Neg logit contributions | |
liners | -0.702 |
disguise | -0.649 |
idth | -0.636 |
DRAGON | -0.635 |
tails | -0.625 |
Token | M |
Token ID | 44 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
ILCS | +0.562 |
illo | +0.543 |
ESA | +0.528 |
Fed | +0.522 |
ilt | +0.520 |
Neg logit contributions | |
liners | -0.568 |
disguise | -0.543 |
DRAGON | -0.534 |
idth | -0.533 |
tails | -0.530 |
Token | anners |
Token ID | 15672 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
ILCS | +0.807 |
illo | +0.788 |
ESA | +0.771 |
ilt | +0.761 |
Fed | +0.760 |
Neg logit contributions | |
liners | -0.522 |
disguise | -0.495 |
DRAGON | -0.486 |
idth | -0.478 |
tails | -0.477 |
Token | - |
Token ID | 532 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
ILCS | +0.317 |
illo | +0.306 |
ESA | +0.299 |
Fed | +0.295 |
ilt | +0.294 |
Neg logit contributions | |
liners | -0.281 |
disguise | -0.268 |
DRAGON | -0.263 |
idth | -0.262 |
tails | -0.261 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.59e+00 |
Pos logit contributions | |
ILCS | +2.407 |
illo | +2.355 |
ilt | +2.234 |
Fed | +2.231 |
nard | +2.223 |
Neg logit contributions | |
liners | -3.360 |
idth | -3.230 |
disguise | -3.209 |
DRAGON | -3.180 |
tails | -3.179 |
Token | favorite |
Token ID | 4004 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
ILCS | +4.313 |
illo | +4.298 |
nard | +4.037 |
ilt | +3.923 |
Fed | +3.912 |
Neg logit contributions | |
liners | -7.254 |
idth | -7.149 |
proble | -7.060 |
tails | -6.964 |
DRAGON | -6.957 |
Token | favorite |
Token ID | 4004 |
Feature activation | -6.88e+00 |
Pos logit contributions | |
ILCS | +4.176 |
illo | +4.155 |
nard | +3.901 |
ilt | +3.809 |
Fed | +3.800 |
Neg logit contributions | |
liners | -6.867 |
idth | -6.757 |
proble | -6.641 |
tails | -6.585 |
DRAGON | -6.581 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
ILCS | +3.760 |
illo | +3.719 |
nard | +3.493 |
ilt | +3.439 |
Fed | +3.437 |
Neg logit contributions | |
liners | -5.650 |
idth | -5.525 |
DRAGON | -5.406 |
tails | -5.382 |
disguise | -5.370 |
Token | favorite |
Token ID | 4004 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
ILCS | +3.582 |
illo | +3.530 |
ilt | +3.314 |
ESA | +3.308 |
nard | +3.299 |
Neg logit contributions | |
liners | -4.411 |
disguise | -4.219 |
DRAGON | -4.205 |
idth | -4.201 |
tails | -4.140 |
Token | - |
Token ID | 532 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ILCS | +3.342 |
illo | +3.273 |
ESA | +3.131 |
ilt | +3.120 |
Fed | +3.117 |
Neg logit contributions | |
liners | -2.974 |
disguise | -2.832 |
DRAGON | -2.801 |
idth | -2.793 |
tails | -2.754 |
Token | December |
Token ID | 3426 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ILCS | +0.492 |
illo | +0.479 |
ESA | +0.468 |
Fed | +0.464 |
ilt | +0.462 |
Neg logit contributions | |
liners | -0.298 |
disguise | -0.279 |
idth | -0.274 |
DRAGON | -0.273 |
tails | -0.272 |
Token | 5 |
Token ID | 642 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
liners | +0.109 |
disguise | +0.104 |
DRAGON | +0.102 |
idth | +0.102 |
tails | +0.101 |
Neg logit contributions | |
ILCS | -0.140 |
illo | -0.135 |
ESA | -0.132 |
Fed | -0.131 |
ilt | -0.130 |
Token | Share |
Token ID | 8734 |
Feature activation | -6.00e+00 |
Pos logit contributions | |
ILCS | +2.553 |
illo | +2.481 |
ESA | +2.378 |
ilt | +2.365 |
Fed | +2.343 |
Neg logit contributions | |
liners | -3.191 |
disguise | -3.034 |
idth | -3.009 |
DRAGON | -2.996 |
tails | -2.992 |
Token | this |
Token ID | 428 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ILCS | +3.747 |
illo | +3.674 |
ESA | +3.508 |
Fed | +3.485 |
ilt | +3.468 |
Neg logit contributions | |
liners | -4.582 |
idth | -4.414 |
proble | -4.388 |
DRAGON | -4.356 |
tails | -4.354 |
Token | comment |
Token ID | 2912 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
ILCS | +1.712 |
illo | +1.646 |
ESA | +1.595 |
Fed | +1.573 |
ilt | +1.566 |
Neg logit contributions | |
liners | -2.182 |
disguise | -2.095 |
DRAGON | -2.065 |
idth | -2.061 |
tails | -2.052 |
Token | on |
Token ID | 319 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
ILCS | +2.686 |
illo | +2.631 |
ESA | +2.552 |
Fed | +2.537 |
ilt | +2.505 |
Neg logit contributions | |
liners | -3.042 |
idth | -2.942 |
proble | -2.912 |
disguise | -2.884 |
DRAGON | -2.883 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
ILCS | +0.409 |
illo | +0.397 |
ESA | +0.388 |
Fed | +0.384 |
ilt | +0.382 |
Neg logit contributions | |
liners | -0.304 |
disguise | -0.287 |
DRAGON | -0.282 |
idth | -0.281 |
tails | -0.279 |
Token | Share |
Token ID | 8734 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
ILCS | +2.351 |
illo | +2.275 |
ESA | +2.194 |
ilt | +2.179 |
Fed | +2.155 |
Neg logit contributions | |
liners | -2.970 |
idth | -2.826 |
disguise | -2.817 |
DRAGON | -2.811 |
tails | -2.780 |
Token | this |
Token ID | 428 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ILCS | +4.035 |
illo | +3.985 |
ESA | +3.797 |
Fed | +3.779 |
nard | +3.749 |
Neg logit contributions | |
liners | -5.052 |
proble | -4.922 |
idth | -4.868 |
DRAGON | -4.817 |
conflic | -4.811 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ILCS | +0.219 |
illo | +0.209 |
ESA | +0.206 |
Fed | +0.202 |
ilt | +0.199 |
Neg logit contributions | |
liners | -0.243 |
disguise | -0.234 |
DRAGON | -0.226 |
tails | -0.225 |
idth | -0.224 |
Token | on |
Token ID | 319 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ILCS | +1.190 |
illo | +1.151 |
ESA | +1.120 |
Fed | +1.108 |
ilt | +1.103 |
Neg logit contributions | |
liners | -1.130 |
disguise | -1.078 |
DRAGON | -1.061 |
idth | -1.058 |
tails | -1.053 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
liners | +0.990 |
disguise | +0.936 |
DRAGON | +0.926 |
tails | +0.918 |
ROCK | +0.896 |
Neg logit contributions | |
ILCS | -1.515 |
illo | -1.461 |
ESA | -1.434 |
Fed | -1.416 |
ilt | -1.411 |
Token |
|
Token ID | 198 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ILCS | +0.765 |
illo | +0.741 |
ESA | +0.722 |
Fed | +0.716 |
ilt | +0.714 |
Neg logit contributions | |
liners | -0.662 |
disguise | -0.628 |
idth | -0.617 |
DRAGON | -0.616 |
tails | -0.612 |
Token | Share |
Token ID | 8734 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
ILCS | +2.535 |
illo | +2.461 |
ESA | +2.356 |
ilt | +2.345 |
Fed | +2.322 |
Neg logit contributions | |
liners | -3.182 |
disguise | -3.029 |
idth | -3.001 |
tails | -2.988 |
DRAGON | -2.988 |
Token | this |
Token ID | 428 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
ILCS | +3.742 |
illo | +3.666 |
ESA | +3.500 |
Fed | +3.476 |
ilt | +3.459 |
Neg logit contributions | |
liners | -4.575 |
idth | -4.410 |
proble | -4.379 |
tails | -4.347 |
DRAGON | -4.342 |
Token | comment |
Token ID | 2912 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
ILCS | +1.782 |
illo | +1.714 |
ESA | +1.658 |
Fed | +1.638 |
ilt | +1.631 |
Neg logit contributions | |
liners | -2.295 |
disguise | -2.202 |
DRAGON | -2.175 |
idth | -2.172 |
tails | -2.160 |
Token | on |
Token ID | 319 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
ILCS | +2.764 |
illo | +2.710 |
ESA | +2.626 |
Fed | +2.611 |
ilt | +2.578 |
Neg logit contributions | |
liners | -3.129 |
idth | -3.028 |
proble | -2.998 |
disguise | -2.968 |
DRAGON | -2.964 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
ILCS | +0.405 |
illo | +0.393 |
ESA | +0.384 |
Fed | +0.380 |
ilt | +0.378 |
Neg logit contributions | |
liners | -0.299 |
disguise | -0.283 |
DRAGON | -0.277 |
idth | -0.276 |
tails | -0.275 |
Token | Share |
Token ID | 8734 |
Feature activation | -6.38e+00 |
Pos logit contributions | |
ILCS | +2.274 |
illo | +2.197 |
ESA | +2.117 |
ilt | +2.105 |
Fed | +2.082 |
Neg logit contributions | |
liners | -2.860 |
idth | -2.724 |
disguise | -2.715 |
DRAGON | -2.707 |
tails | -2.678 |
Token | this |
Token ID | 428 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
ILCS | +3.927 |
illo | +3.878 |
ESA | +3.698 |
Fed | +3.676 |
nard | +3.650 |
Neg logit contributions | |
liners | -4.909 |
proble | -4.764 |
idth | -4.733 |
DRAGON | -4.677 |
tails | -4.658 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ILCS | +0.276 |
illo | +0.264 |
ESA | +0.259 |
Fed | +0.254 |
ilt | +0.252 |
Neg logit contributions | |
liners | -0.312 |
disguise | -0.300 |
DRAGON | -0.290 |
tails | -0.289 |
idth | -0.287 |
Token | on |
Token ID | 319 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ILCS | +1.242 |
illo | +1.202 |
ESA | +1.170 |
Fed | +1.157 |
ilt | +1.152 |
Neg logit contributions | |
liners | -1.186 |
disguise | -1.131 |
DRAGON | -1.114 |
idth | -1.112 |
tails | -1.105 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
liners | +1.025 |
disguise | +0.969 |
DRAGON | +0.959 |
tails | +0.950 |
ROCK | +0.926 |
Neg logit contributions | |
ILCS | -1.557 |
illo | -1.502 |
ESA | -1.475 |
Fed | -1.456 |
ilt | -1.449 |
Token |
|
Token ID | 198 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
ILCS | +0.683 |
illo | +0.661 |
ESA | +0.644 |
Fed | +0.638 |
ilt | +0.637 |
Neg logit contributions | |
liners | -0.590 |
disguise | -0.560 |
idth | -0.550 |
DRAGON | -0.550 |
tails | -0.546 |
Token | Flag |
Token ID | 19762 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
liners | +0.281 |
disguise | +0.267 |
DRAGON | +0.262 |
idth | +0.261 |
tails | +0.260 |
Neg logit contributions | |
ILCS | -0.361 |
illo | -0.351 |
ESA | -0.342 |
Fed | -0.339 |
ilt | -0.337 |
Token |
|
Token ID | 198 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
ILCS | +0.480 |
illo | +0.473 |
ESA | +0.453 |
Fed | +0.451 |
ilt | +0.444 |
Neg logit contributions | |
liners | -0.444 |
disguise | -0.423 |
tails | -0.418 |
DRAGON | -0.415 |
idth | -0.411 |
Token |
|
Token ID | 198 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
ILCS | +1.653 |
illo | +1.606 |
ESA | +1.569 |
Fed | +1.557 |
ilt | +1.543 |
Neg logit contributions | |
liners | -1.451 |
disguise | -1.388 |
idth | -1.366 |
DRAGON | -1.361 |
tails | -1.343 |
Token | Flag |
Token ID | 34227 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
ILCS | +2.207 |
illo | +2.147 |
ESA | +2.106 |
Fed | +2.094 |
ilt | +2.073 |
Neg logit contributions | |
liners | -2.234 |
disguise | -2.179 |
DRAGON | -2.134 |
idth | -2.127 |
tails | -2.080 |
Token | Reply |
Token ID | 14883 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
ILCS | +1.851 |
illo | +1.781 |
ESA | +1.699 |
Fed | +1.691 |
ilt | +1.678 |
Neg logit contributions | |
liners | -2.601 |
disguise | -2.469 |
tails | -2.456 |
idth | -2.454 |
DRAGON | -2.428 |
Token |
|
Token ID | 198 |
Feature activation | -7.55e+00 |
Pos logit contributions | |
ILCS | +2.275 |
illo | +2.226 |
ESA | +2.133 |
Fed | +2.110 |
ilt | +2.078 |
Neg logit contributions | |
liners | -2.181 |
disguise | -2.065 |
idth | -2.055 |
DRAGON | -2.027 |
tails | -2.011 |
Token |
|
Token ID | 198 |
Feature activation | -6.99e+00 |
Pos logit contributions | |
ILCS | +4.624 |
illo | +4.593 |
Fed | +4.534 |
ESA | +4.472 |
nard | +4.398 |
Neg logit contributions | |
proble | -6.024 |
conflic | -5.888 |
idth | -5.697 |
liners | -5.667 |
thous | -5.653 |
Token | 14 |
Token ID | 1415 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
ILCS | +4.047 |
ESA | +3.977 |
illo | +3.915 |
Fed | +3.908 |
ilt | +3.776 |
Neg logit contributions | |
liners | -5.589 |
disguise | -5.384 |
idth | -5.355 |
DRAGON | -5.299 |
ancest | -5.248 |
Token | Recommend |
Token ID | 30361 |
Feature activation | -7.12e+00 |
Pos logit contributions | |
ILCS | +1.386 |
illo | +1.255 |
ESA | +1.178 |
Fed | +1.174 |
ilt | +1.144 |
Neg logit contributions | |
liners | -4.562 |
disguise | -4.392 |
idth | -4.378 |
tails | -4.350 |
DRAGON | -4.348 |
Token |
|
Token ID | 198 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
ILCS | +4.616 |
illo | +4.561 |
Fed | +4.379 |
ESA | +4.323 |
ilt | +4.266 |
Neg logit contributions | |
liners | -5.298 |
proble | -5.218 |
idth | -5.044 |
disguise | -5.015 |
ancest | -4.991 |
Token |
|
Token ID | 198 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
ILCS | +3.213 |
illo | +3.144 |
ESA | +3.060 |
Fed | +3.052 |
ilt | +3.026 |
Neg logit contributions | |
liners | -3.174 |
idth | -3.076 |
proble | -3.069 |
disguise | -3.039 |
DRAGON | -3.011 |