Token | revolt |
Token ID | 27360 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
estern | +0.440 |
Sally | +0.425 |
roo | +0.403 |
tons | +0.397 |
puppies | +0.355 |
Neg logit contributions | |
omial | -0.587 |
unden | -0.456 |
scorer | -0.450 |
usal | -0.443 |
anches | -0.419 |
Token | than |
Token ID | 621 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
estern | +0.812 |
Sally | +0.781 |
roo | +0.744 |
tons | +0.733 |
puppies | +0.652 |
Neg logit contributions | |
omial | -1.118 |
unden | -0.879 |
scorer | -0.859 |
usal | -0.848 |
anches | -0.802 |
Token | the |
Token ID | 262 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
estern | +0.744 |
Sally | +0.722 |
roo | +0.684 |
tons | +0.678 |
puppies | +0.604 |
Neg logit contributions | |
omial | -1.031 |
unden | -0.804 |
scorer | -0.794 |
usal | -0.783 |
anches | -0.741 |
Token | un |
Token ID | 555 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
estern | +0.374 |
Sally | +0.363 |
roo | +0.346 |
tons | +0.344 |
puppies | +0.310 |
Neg logit contributions | |
omial | -0.430 |
unden | -0.327 |
scorer | -0.322 |
usal | -0.319 |
acing | -0.299 |
Token | ifying |
Token ID | 4035 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
omial | +0.727 |
unden | +0.518 |
scorer | +0.504 |
usal | +0.489 |
acing | +0.451 |
Neg logit contributions | |
estern | -0.964 |
Sally | -0.936 |
roo | -0.907 |
tons | -0.894 |
puppies | -0.820 |
Token | tut |
Token ID | 9732 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
omial | +0.124 |
unden | +0.095 |
scorer | +0.093 |
usal | +0.092 |
acing | +0.087 |
Neg logit contributions | |
estern | -0.100 |
Sally | -0.097 |
roo | -0.093 |
tons | -0.092 |
puppies | -0.083 |
Token | el |
Token ID | 417 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
estern | +7.641 |
Sally | +7.170 |
roo | +6.995 |
tons | +6.971 |
TON | +5.999 |
Neg logit contributions | |
omial | -12.439 |
unden | -10.110 |
scorer | -9.804 |
usal | -9.560 |
exha | -9.499 |
Token | age |
Token ID | 496 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
estern | +2.996 |
Sally | +2.893 |
roo | +2.773 |
tons | +2.706 |
TON | +2.377 |
Neg logit contributions | |
omial | -4.371 |
unden | -3.487 |
scorer | -3.413 |
usal | -3.353 |
exha | -3.178 |
Token | of |
Token ID | 286 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
estern | +3.200 |
Sally | +3.117 |
roo | +2.974 |
tons | +2.961 |
puppies | +2.675 |
Neg logit contributions | |
omial | -3.719 |
unden | -2.853 |
scorer | -2.791 |
usal | -2.749 |
acing | -2.585 |
Token | a |
Token ID | 257 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
estern | +0.779 |
Sally | +0.753 |
roo | +0.716 |
tons | +0.705 |
puppies | +0.630 |
Neg logit contributions | |
omial | -1.052 |
unden | -0.820 |
scorer | -0.806 |
usal | -0.795 |
acing | -0.752 |
Token | bourgeois |
Token ID | 19749 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
estern | +0.685 |
Sally | +0.664 |
roo | +0.633 |
tons | +0.624 |
puppies | +0.562 |
Neg logit contributions | |
omial | -0.807 |
unden | -0.618 |
scorer | -0.605 |
usal | -0.599 |
acing | -0.566 |
Token | , |
Token ID | 11 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
omial | +2.212 |
unden | +1.721 |
scorer | +1.687 |
usal | +1.664 |
anches | +1.572 |
Neg logit contributions | |
estern | -1.724 |
Sally | -1.662 |
roo | -1.592 |
tons | -1.557 |
puppies | -1.393 |
Token | and |
Token ID | 290 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
estern | +0.143 |
Sally | +0.138 |
roo | +0.132 |
tons | +0.130 |
puppies | +0.117 |
Neg logit contributions | |
omial | -0.170 |
unden | -0.130 |
scorer | -0.128 |
usal | -0.126 |
acing | -0.119 |
Token | this |
Token ID | 428 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
omial | +0.830 |
unden | +0.646 |
scorer | +0.636 |
usal | +0.627 |
anches | +0.592 |
Neg logit contributions | |
estern | -0.623 |
Sally | -0.604 |
roo | -0.575 |
tons | -0.565 |
puppies | -0.504 |
Token | morning |
Token ID | 3329 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
estern | +1.197 |
Sally | +1.159 |
roo | +1.107 |
tons | +1.083 |
puppies | +0.977 |
Neg logit contributions | |
omial | -1.490 |
unden | -1.146 |
scorer | -1.127 |
usal | -1.112 |
anches | -1.055 |
Token | I |
Token ID | 314 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
estern | +3.423 |
Sally | +3.398 |
roo | +3.172 |
tons | +3.155 |
puppies | +2.786 |
Neg logit contributions | |
omial | -5.054 |
unden | -3.983 |
scorer | -3.897 |
usal | -3.872 |
exha | -3.657 |
Token | clot |
Token ID | 5148 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
estern | +1.221 |
Sally | +1.194 |
roo | +1.138 |
tons | +1.113 |
puppies | +0.992 |
Neg logit contributions | |
omial | -1.624 |
unden | -1.267 |
scorer | -1.238 |
usal | -1.219 |
anches | -1.154 |
Token | he |
Token ID | 258 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
Sally | +5.426 |
estern | +5.354 |
roo | +5.096 |
tons | +4.863 |
TON | +4.046 |
Neg logit contributions | |
omial | -13.672 |
unden | -11.207 |
scorer | -11.066 |
usal | -10.927 |
anches | -10.560 |
Token | myself |
Token ID | 3589 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
estern | +1.833 |
Sally | +1.796 |
roo | +1.693 |
tons | +1.678 |
puppies | +1.498 |
Neg logit contributions | |
omial | -2.473 |
unden | -1.914 |
scorer | -1.886 |
usal | -1.862 |
anches | -1.763 |
Token | with |
Token ID | 351 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
estern | +0.729 |
Sally | +0.705 |
roo | +0.672 |
tons | +0.657 |
puppies | +0.587 |
Neg logit contributions | |
omial | -0.969 |
unden | -0.755 |
scorer | -0.742 |
usal | -0.731 |
anches | -0.692 |
Token | Christ |
Token ID | 1951 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
estern | +2.250 |
Sally | +2.207 |
roo | +2.060 |
tons | +2.050 |
puppies | +1.838 |
Neg logit contributions | |
omial | -3.119 |
unden | -2.417 |
scorer | -2.390 |
usal | -2.368 |
anches | -2.234 |
Token | , |
Token ID | 11 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
estern | +2.657 |
Sally | +2.579 |
roo | +2.470 |
tons | +2.430 |
puppies | +2.171 |
Neg logit contributions | |
omial | -3.552 |
unden | -2.760 |
scorer | -2.721 |
usal | -2.675 |
anches | -2.531 |
Token | will |
Token ID | 481 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
estern | +0.676 |
Sally | +0.675 |
roo | +0.629 |
tons | +0.624 |
puppies | +0.564 |
Neg logit contributions | |
omial | -0.926 |
unden | -0.730 |
scorer | -0.700 |
usal | -0.699 |
exha | -0.660 |
Token | consider |
Token ID | 2074 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
Sally | +2.779 |
estern | +2.698 |
roo | +2.615 |
tons | +2.553 |
puppies | +2.353 |
Neg logit contributions | |
omial | -3.550 |
unden | -2.812 |
usal | -2.646 |
scorer | -2.600 |
exha | -2.509 |
Token | the |
Token ID | 262 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
estern | +0.575 |
Sally | +0.568 |
roo | +0.533 |
tons | +0.523 |
puppies | +0.469 |
Neg logit contributions | |
omial | -0.875 |
unden | -0.690 |
scorer | -0.672 |
usal | -0.663 |
anches | -0.633 |
Token | role |
Token ID | 2597 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Sally | +0.925 |
estern | +0.921 |
roo | +0.871 |
tons | +0.855 |
puppies | +0.777 |
Neg logit contributions | |
omial | -1.184 |
unden | -0.917 |
scorer | -0.888 |
usal | -0.875 |
anches | -0.838 |
Token | of |
Token ID | 286 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
omial | +3.295 |
unden | +2.441 |
scorer | +2.420 |
usal | +2.358 |
acing | +2.230 |
Neg logit contributions | |
estern | -3.719 |
Sally | -3.535 |
roo | -3.438 |
tons | -3.397 |
enegger | -3.109 |
Token | ment |
Token ID | 6229 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
omial | +0.086 |
unden | +0.066 |
scorer | +0.064 |
usal | +0.063 |
anches | +0.060 |
Neg logit contributions | |
estern | -0.069 |
Sally | -0.067 |
roo | -0.064 |
tons | -0.062 |
puppies | -0.057 |
Token | hol |
Token ID | 3937 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
estern | +3.983 |
Sally | +3.961 |
roo | +3.914 |
tons | +3.314 |
eers | +2.664 |
Neg logit contributions | |
omial | -14.788 |
unden | -12.925 |
scorer | -12.562 |
exha | -12.364 |
usal | -12.100 |
Token | and |
Token ID | 290 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
estern | +0.630 |
Sally | +0.607 |
roo | +0.581 |
tons | +0.567 |
puppies | +0.507 |
Neg logit contributions | |
omial | -0.878 |
unden | -0.689 |
scorer | -0.675 |
usal | -0.667 |
anches | -0.632 |
Token | other |
Token ID | 584 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
omial | +0.796 |
unden | +0.610 |
scorer | +0.598 |
usal | +0.592 |
anches | +0.560 |
Neg logit contributions | |
estern | -0.641 |
Sally | -0.626 |
roo | -0.596 |
tons | -0.583 |
puppies | -0.528 |
Token | flavors |
Token ID | 17361 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
omial | +0.120 |
unden | +0.092 |
scorer | +0.090 |
usal | +0.090 |
anches | +0.085 |
Neg logit contributions | |
estern | -0.089 |
Sally | -0.086 |
roo | -0.082 |
tons | -0.080 |
puppies | -0.073 |
Token | in |
Token ID | 287 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
estern | +1.522 |
Sally | +1.479 |
roo | +1.412 |
tons | +1.379 |
puppies | +1.245 |
Neg logit contributions | |
omial | -1.998 |
unden | -1.565 |
scorer | -1.513 |
usal | -1.497 |
exha | -1.420 |
Token | highlights |
Token ID | 11330 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
omial | +3.021 |
unden | +2.099 |
scorer | +2.042 |
usal | +1.990 |
acing | +1.834 |
Neg logit contributions | |
estern | -4.361 |
Sally | -4.229 |
roo | -4.105 |
tons | -4.040 |
enegger | -3.731 |
Token | Secretary |
Token ID | 4986 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
estern | +0.011 |
Sally | +0.011 |
roo | +0.010 |
tons | +0.010 |
puppies | +0.009 |
Neg logit contributions | |
omial | -0.015 |
unden | -0.012 |
scorer | -0.012 |
usal | -0.012 |
anches | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
estern | +0.120 |
Sally | +0.117 |
roo | +0.111 |
tons | +0.110 |
puppies | +0.099 |
Neg logit contributions | |
omial | -0.126 |
unden | -0.095 |
scorer | -0.093 |
usal | -0.091 |
anches | -0.086 |
Token | Defense |
Token ID | 5947 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
estern | +0.402 |
Sally | +0.391 |
roo | +0.374 |
tons | +0.367 |
puppies | +0.333 |
Neg logit contributions | |
omial | -0.427 |
unden | -0.324 |
scorer | -0.316 |
usal | -0.311 |
anches | -0.292 |
Token | Chuck |
Token ID | 14663 |
Feature activation | +9.44e+00 |
Pos logit contributions | |
Sally | +2.966 |
estern | +2.683 |
roo | +2.561 |
tons | +2.545 |
puppies | +2.248 |
Neg logit contributions | |
omial | -5.069 |
unden | -4.029 |
scorer | -3.865 |
usal | -3.830 |
exha | -3.725 |
Token | Hag |
Token ID | 21375 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
Sally | +3.400 |
estern | +2.825 |
tons | +2.759 |
roo | +2.649 |
hire | +2.073 |
Neg logit contributions | |
omial | -14.252 |
unden | -12.597 |
usal | -11.915 |
scorer | -11.842 |
exha | -11.741 |
Token | el |
Token ID | 417 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
Sally | +5.266 |
estern | +4.897 |
roo | +4.757 |
tons | +4.309 |
puppies | +3.901 |
Neg logit contributions | |
omial | -13.878 |
unden | -11.757 |
exha | -11.300 |
scorer | -11.291 |
usal | -11.188 |
Token | will |
Token ID | 481 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
Sally | +3.998 |
estern | +3.928 |
roo | +3.680 |
tons | +3.586 |
puppies | +3.315 |
Neg logit contributions | |
omial | -5.178 |
unden | -4.024 |
usal | -3.861 |
scorer | -3.817 |
exha | -3.648 |
Token | step |
Token ID | 2239 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
Sally | +3.252 |
estern | +3.250 |
roo | +3.042 |
tons | +2.969 |
puppies | +2.720 |
Neg logit contributions | |
omial | -4.057 |
unden | -3.157 |
scorer | -2.997 |
usal | -2.997 |
exha | -2.844 |
Token | down |
Token ID | 866 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
estern | +3.081 |
Sally | +2.999 |
roo | +2.892 |
tons | +2.838 |
puppies | +2.604 |
Neg logit contributions | |
omial | -2.688 |
unden | -1.957 |
scorer | -1.877 |
usal | -1.853 |
anches | -1.732 |
Token | , |
Token ID | 11 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
omial | +0.773 |
unden | +0.609 |
scorer | +0.595 |
usal | +0.589 |
anches | +0.558 |
Neg logit contributions | |
estern | -0.535 |
Sally | -0.519 |
roo | -0.492 |
tons | -0.480 |
puppies | -0.428 |
Token | . |
Token ID | 13 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
estern | +0.418 |
Sally | +0.404 |
roo | +0.386 |
tons | +0.376 |
puppies | +0.336 |
Neg logit contributions | |
omial | -0.570 |
unden | -0.449 |
scorer | -0.439 |
usal | -0.431 |
anches | -0.409 |
Token | � |
Token ID | 447 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
estern | +0.619 |
Sally | +0.610 |
roo | +0.574 |
tons | +0.562 |
TON | +0.504 |
Neg logit contributions | |
omial | -0.818 |
unden | -0.648 |
scorer | -0.630 |
usal | -0.619 |
exha | -0.592 |
Token | � |
Token ID | 247 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
estern | +0.711 |
Sally | +0.682 |
roo | +0.652 |
tons | +0.637 |
puppies | +0.565 |
Neg logit contributions | |
omial | -1.007 |
unden | -0.793 |
scorer | -0.779 |
usal | -0.768 |
acing | -0.728 |
Token | � |
Token ID | 447 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
estern | +0.606 |
Sally | +0.600 |
roo | +0.561 |
tons | +0.551 |
TON | +0.487 |
Neg logit contributions | |
omial | -0.876 |
unden | -0.700 |
scorer | -0.682 |
usal | -0.668 |
exha | -0.642 |
Token | � |
Token ID | 251 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
estern | +1.081 |
Sally | +1.047 |
roo | +1.000 |
tons | +0.975 |
puppies | +0.872 |
Neg logit contributions | |
omial | -1.506 |
unden | -1.180 |
scorer | -1.161 |
usal | -1.145 |
anches | -1.086 |
Token | Gale |
Token ID | 36483 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
estern | +0.671 |
Sally | +0.665 |
roo | +0.622 |
tons | +0.609 |
TON | +0.541 |
Neg logit contributions | |
omial | -0.983 |
unden | -0.785 |
scorer | -0.765 |
usal | -0.752 |
exha | -0.720 |
Token | otti |
Token ID | 26380 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
estern | +5.687 |
roo | +5.311 |
Sally | +5.134 |
tons | +5.129 |
TON | +4.267 |
Neg logit contributions | |
omial | -11.834 |
unden | -10.968 |
exha | -10.505 |
usal | -9.918 |
scorer | -9.634 |
Token | doesn |
Token ID | 1595 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
estern | +2.543 |
Sally | +2.504 |
roo | +2.338 |
tons | +2.319 |
enegger | +2.121 |
Neg logit contributions | |
omial | -3.122 |
unden | -2.417 |
scorer | -2.336 |
usal | -2.330 |
exha | -2.217 |
Token | � |
Token ID | 447 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
omial | +3.934 |
scorer | +2.905 |
unden | +2.903 |
usal | +2.872 |
acing | +2.701 |
Neg logit contributions | |
estern | -3.714 |
Sally | -3.577 |
roo | -3.434 |
tons | -3.359 |
puppies | -3.064 |
Token | � |
Token ID | 247 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
estern | +1.089 |
Sally | +1.082 |
roo | +1.058 |
tons | +1.003 |
hire | +0.863 |
Neg logit contributions | |
omial | -2.262 |
unden | -1.875 |
scorer | -1.807 |
usal | -1.772 |
exha | -1.740 |
Token | t |
Token ID | 83 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
estern | +0.538 |
Sally | +0.518 |
roo | +0.501 |
tons | +0.481 |
hire | +0.397 |
Neg logit contributions | |
omial | -1.451 |
unden | -1.256 |
scorer | -1.187 |
exha | -1.177 |
usal | -1.159 |
Token | , |
Token ID | 11 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
estern | +3.147 |
Sally | +3.096 |
roo | +2.878 |
tons | +2.826 |
puppies | +2.522 |
Neg logit contributions | |
omial | -4.998 |
unden | -3.972 |
scorer | -3.859 |
usal | -3.856 |
anches | -3.690 |
Token | and |
Token ID | 290 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
estern | +0.410 |
Sally | +0.404 |
roo | +0.379 |
tons | +0.368 |
puppies | +0.333 |
Neg logit contributions | |
omial | -0.596 |
unden | -0.470 |
scorer | -0.458 |
usal | -0.455 |
anches | -0.433 |
Token | her |
Token ID | 607 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
omial | +0.458 |
unden | +0.358 |
scorer | +0.349 |
usal | +0.346 |
acing | +0.328 |
Neg logit contributions | |
estern | -0.329 |
Sally | -0.322 |
roo | -0.303 |
tons | -0.298 |
puppies | -0.267 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
omial | +0.366 |
unden | +0.292 |
scorer | +0.286 |
usal | +0.284 |
anches | +0.270 |
Neg logit contributions | |
estern | -0.214 |
Sally | -0.208 |
roo | -0.196 |
tons | -0.191 |
puppies | -0.168 |
Token | is |
Token ID | 318 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
estern | +1.187 |
Sally | +1.159 |
roo | +1.099 |
tons | +1.077 |
puppies | +0.971 |
Neg logit contributions | |
omial | -1.457 |
unden | -1.124 |
scorer | -1.101 |
usal | -1.088 |
acing | -1.021 |
Token | Cant |
Token ID | 16821 |
Feature activation | +9.82e+00 |
Pos logit contributions | |
estern | +0.550 |
Sally | +0.539 |
roo | +0.505 |
tons | +0.496 |
puppies | +0.441 |
Neg logit contributions | |
omial | -0.810 |
unden | -0.633 |
scorer | -0.622 |
usal | -0.616 |
anches | -0.585 |
Token | ones |
Token ID | 1952 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
Sally | +5.047 |
roo | +4.927 |
estern | +4.900 |
tons | +4.576 |
TON | +3.772 |
Neg logit contributions | |
omial | -12.744 |
unden | -10.612 |
scorer | -10.321 |
usal | -10.061 |
exha | -9.966 |
Token | e |
Token ID | 68 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
omial | +0.751 |
unden | +0.615 |
scorer | +0.598 |
usal | +0.591 |
exha | +0.569 |
Neg logit contributions | |
estern | -0.383 |
Sally | -0.367 |
roo | -0.344 |
tons | -0.335 |
hire | -0.287 |
Token | . |
Token ID | 13 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
estern | +1.494 |
Sally | +1.450 |
roo | +1.372 |
tons | +1.345 |
puppies | +1.202 |
Neg logit contributions | |
omial | -2.105 |
unden | -1.653 |
scorer | -1.618 |
usal | -1.604 |
anches | -1.523 |
Token | And |
Token ID | 843 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Sally | +0.261 |
estern | +0.259 |
roo | +0.241 |
tons | +0.237 |
TON | +0.211 |
Neg logit contributions | |
omial | -0.384 |
unden | -0.310 |
scorer | -0.298 |
usal | -0.295 |
exha | -0.286 |
Token | she |
Token ID | 673 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Sally | +1.390 |
estern | +1.375 |
roo | +1.273 |
tons | +1.270 |
puppies | +1.134 |
Neg logit contributions | |
omial | -2.162 |
unden | -1.706 |
scorer | -1.652 |
usal | -1.646 |
exha | -1.562 |
Token | � |
Token ID | 447 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
omial | +1.665 |
unden | +1.312 |
scorer | +1.289 |
usal | +1.271 |
acing | +1.206 |
Neg logit contributions | |
estern | -1.162 |
Sally | -1.116 |
roo | -1.066 |
tons | -1.041 |
puppies | -0.923 |
Token | � |
Token ID | 247 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
omial | +0.023 |
unden | +0.018 |
scorer | +0.018 |
usal | +0.018 |
acing | +0.017 |
Neg logit contributions | |
estern | -0.017 |
Sally | -0.016 |
roo | -0.016 |
tons | -0.015 |
puppies | -0.014 |
Token | s |
Token ID | 82 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
estern | +0.256 |
Sally | +0.245 |
roo | +0.237 |
tons | +0.232 |
TON | +0.208 |
Neg logit contributions | |
omial | -0.314 |
unden | -0.244 |
scorer | -0.239 |
usal | -0.235 |
anches | -0.221 |
Token | Land |
Token ID | 6379 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
omial | +0.492 |
unden | +0.386 |
scorer | +0.378 |
usal | +0.370 |
acing | +0.352 |
Neg logit contributions | |
estern | -0.369 |
Sally | -0.359 |
roo | -0.342 |
tons | -0.333 |
puppies | -0.297 |
Token | scape |
Token ID | 6794 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
estern | +0.518 |
Sally | +0.506 |
roo | +0.488 |
tons | +0.478 |
puppies | +0.437 |
Neg logit contributions | |
omial | -0.434 |
unden | -0.320 |
scorer | -0.309 |
usal | -0.299 |
anches | -0.279 |
Token | Gard |
Token ID | 12790 |
Feature activation | +9.80e+00 |
Pos logit contributions | |
estern | +1.423 |
Sally | +1.398 |
roo | +1.321 |
tons | +1.284 |
eers | +1.150 |
Neg logit contributions | |
omial | -1.911 |
unden | -1.516 |
scorer | -1.469 |
usal | -1.441 |
acing | -1.368 |
Token | ening |
Token ID | 3101 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
estern | +6.111 |
Sally | +5.871 |
roo | +5.610 |
tons | +5.303 |
eers | +4.634 |
Neg logit contributions | |
omial | -12.122 |
unden | -10.148 |
scorer | -9.610 |
exha | -9.313 |
usal | -9.302 |
Token | – |
Token ID | 784 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
estern | +1.107 |
Sally | +1.083 |
roo | +1.022 |
tons | +1.007 |
puppies | +0.894 |
Neg logit contributions | |
omial | -1.527 |
unden | -1.202 |
scorer | -1.172 |
usal | -1.154 |
acing | -1.097 |
Token | Land |
Token ID | 6379 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
estern | +1.366 |
Sally | +1.361 |
roo | +1.273 |
tons | +1.241 |
puppies | +1.122 |
Neg logit contributions | |
omial | -1.845 |
unden | -1.434 |
scorer | -1.398 |
usal | -1.376 |
anches | -1.317 |
Token | sc |
Token ID | 1416 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
omial | +0.068 |
unden | +0.050 |
scorer | +0.048 |
usal | +0.047 |
anches | +0.044 |
Neg logit contributions | |
estern | -0.079 |
Sally | -0.077 |
roo | -0.075 |
tons | -0.073 |
puppies | -0.067 |
Token | aping |
Token ID | 9269 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
omial | +2.485 |
unden | +2.032 |
scorer | +2.011 |
usal | +1.995 |
acing | +1.916 |
Neg logit contributions | |
estern | -1.070 |
Sally | -1.010 |
roo | -0.945 |
tons | -0.919 |
puppies | -0.773 |
Token | letter |
Token ID | 3850 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
estern | +0.235 |
Sally | +0.224 |
roo | +0.207 |
tons | +0.202 |
puppies | +0.173 |
Neg logit contributions | |
omial | -0.515 |
unden | -0.419 |
scorer | -0.410 |
usal | -0.407 |
anches | -0.392 |
Token | to |
Token ID | 284 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
estern | +1.762 |
Sally | +1.727 |
roo | +1.616 |
tons | +1.585 |
puppies | +1.430 |
Neg logit contributions | |
omial | -2.336 |
unden | -1.806 |
scorer | -1.749 |
usal | -1.737 |
anches | -1.654 |
Token | Senate |
Token ID | 3845 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
omial | +0.743 |
unden | +0.599 |
scorer | +0.591 |
usal | +0.583 |
acing | +0.557 |
Neg logit contributions | |
estern | -0.414 |
Sally | -0.392 |
roo | -0.374 |
tons | -0.364 |
puppies | -0.314 |
Token | Majority |
Token ID | 22171 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
estern | +3.058 |
Sally | +3.016 |
roo | +2.790 |
tons | +2.741 |
puppies | +2.435 |
Neg logit contributions | |
omial | -4.781 |
unden | -3.794 |
scorer | -3.695 |
usal | -3.672 |
anches | -3.486 |
Token | Leader |
Token ID | 10540 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
estern | +0.677 |
Sally | +0.642 |
roo | +0.603 |
tons | +0.583 |
puppies | +0.491 |
Neg logit contributions | |
omial | -1.530 |
unden | -1.254 |
scorer | -1.236 |
usal | -1.222 |
acing | -1.171 |
Token | Mitch |
Token ID | 20472 |
Feature activation | +9.68e+00 |
Pos logit contributions | |
omial | +1.908 |
unden | +1.504 |
scorer | +1.497 |
usal | +1.479 |
acing | +1.402 |
Neg logit contributions | |
estern | -1.258 |
Sally | -1.168 |
roo | -1.144 |
tons | -1.102 |
enegger | -0.981 |
Token | McConnell |
Token ID | 18184 |
Feature activation | +7.88e+00 |
Pos logit contributions | |
Sally | +3.386 |
roo | +2.695 |
estern | +2.694 |
tons | +2.424 |
puppies | +1.737 |
Neg logit contributions | |
omial | -14.878 |
unden | -12.972 |
scorer | -12.283 |
exha | -12.214 |
usal | -12.022 |
Token | expressing |
Token ID | 16621 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Sally | +5.509 |
estern | +5.326 |
roo | +4.988 |
tons | +4.763 |
puppies | +4.381 |
Neg logit contributions | |
omial | -9.212 |
unden | -7.346 |
scorer | -7.052 |
usal | -7.044 |
anches | -6.741 |
Token | their |
Token ID | 511 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
omial | +1.391 |
unden | +1.087 |
scorer | +1.066 |
usal | +1.053 |
anches | +0.997 |
Neg logit contributions | |
estern | -1.005 |
Sally | -0.973 |
roo | -0.923 |
tons | -0.906 |
puppies | -0.808 |
Token | concerns |
Token ID | 4786 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
estern | +1.351 |
Sally | +1.344 |
tons | +1.241 |
roo | +1.233 |
puppies | +1.122 |
Neg logit contributions | |
omial | -1.904 |
unden | -1.467 |
scorer | -1.433 |
usal | -1.430 |
anches | -1.359 |
Token | over |
Token ID | 625 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
estern | +1.720 |
Sally | +1.669 |
roo | +1.561 |
tons | +1.513 |
puppies | +1.335 |
Neg logit contributions | |
omial | -3.077 |
unden | -2.489 |
scorer | -2.431 |
usal | -2.413 |
anches | -2.294 |
Token | " |
Token ID | 366 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
estern | +0.445 |
Sally | +0.434 |
roo | +0.413 |
tons | +0.397 |
puppies | +0.354 |
Neg logit contributions | |
omial | -0.760 |
unden | -0.606 |
scorer | -0.591 |
usal | -0.582 |
anches | -0.557 |
Token | 78 |
Token ID | 3695 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
estern | +0.805 |
Sally | +0.772 |
roo | +0.743 |
tons | +0.726 |
TON | +0.649 |
Neg logit contributions | |
omial | -1.044 |
unden | -0.813 |
scorer | -0.797 |
usal | -0.783 |
anches | -0.742 |
Token | th |
Token ID | 400 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
omial | +0.229 |
unden | +0.180 |
scorer | +0.177 |
usal | +0.175 |
acing | +0.166 |
Neg logit contributions | |
estern | -0.160 |
Sally | -0.154 |
roo | -0.147 |
tons | -0.144 |
puppies | -0.127 |
Token | Tata |
Token ID | 49963 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
omial | +6.995 |
unden | +5.528 |
scorer | +5.474 |
usal | +5.294 |
acing | +5.058 |
Neg logit contributions | |
estern | -5.072 |
Sally | -4.717 |
roo | -4.685 |
tons | -4.481 |
enegger | -4.064 |
Token | Steel |
Token ID | 7851 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
estern | +3.481 |
Sally | +3.425 |
roo | +3.210 |
tons | +3.150 |
TON | +2.820 |
Neg logit contributions | |
omial | -5.257 |
unden | -4.231 |
scorer | -4.078 |
usal | -4.014 |
anches | -3.860 |
Token | Chess |
Token ID | 25774 |
Feature activation | +9.65e+00 |
Pos logit contributions | |
estern | +3.065 |
Sally | +2.989 |
roo | +2.829 |
tons | +2.767 |
TON | +2.457 |
Neg logit contributions | |
omial | -4.481 |
unden | -3.587 |
scorer | -3.469 |
usal | -3.427 |
anches | -3.282 |
Token | Chall |
Token ID | 10772 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
estern | +6.869 |
Sally | +6.706 |
roo | +6.351 |
tons | +6.122 |
TON | +5.542 |
Neg logit contributions | |
omial | -10.950 |
unden | -8.853 |
usal | -8.475 |
scorer | -8.457 |
exha | -8.278 |
Token | engers |
Token ID | 9302 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
estern | +0.987 |
Sally | +0.905 |
roo | +0.810 |
tons | +0.685 |
hire | +0.483 |
Neg logit contributions | |
omial | -5.147 |
unden | -4.436 |
scorer | -4.341 |
usal | -4.252 |
exha | -4.214 |
Token | "] |
Token ID | 8973 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
estern | +1.765 |
Sally | +1.702 |
roo | +1.605 |
tons | +1.568 |
TON | +1.388 |
Neg logit contributions | |
omial | -2.717 |
unden | -2.158 |
scorer | -2.115 |
usal | -2.085 |
anches | -1.997 |
Token | [ |
Token ID | 685 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
Sally | +2.074 |
estern | +2.035 |
roo | +1.859 |
tons | +1.704 |
TON | +1.652 |
Neg logit contributions | |
omial | -5.403 |
unden | -4.485 |
usal | -4.340 |
exha | -4.318 |
scorer | -4.297 |
Token | Site |
Token ID | 29123 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
estern | +3.106 |
Sally | +3.043 |
roo | +2.894 |
tons | +2.787 |
TON | +2.692 |
Neg logit contributions | |
omial | -3.346 |
unden | -2.569 |
scorer | -2.411 |
usal | -2.303 |
anches | -2.289 |
Token | than |
Token ID | 621 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
estern | +2.462 |
Sally | +2.414 |
roo | +2.274 |
tons | +2.229 |
puppies | +1.975 |
Neg logit contributions | |
omial | -3.737 |
unden | -2.993 |
scorer | -2.894 |
usal | -2.867 |
anches | -2.729 |
Token | normal |
Token ID | 3487 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
estern | +0.285 |
Sally | +0.284 |
roo | +0.267 |
tons | +0.262 |
puppies | +0.237 |
Neg logit contributions | |
omial | -0.380 |
unden | -0.294 |
scorer | -0.287 |
usal | -0.284 |
acing | -0.270 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
omial | +0.208 |
unden | +0.163 |
scorer | +0.160 |
usal | +0.157 |
anches | +0.149 |
Neg logit contributions | |
estern | -0.151 |
Sally | -0.146 |
roo | -0.139 |
tons | -0.136 |
puppies | -0.122 |
Token | says |
Token ID | 1139 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
omial | +0.165 |
unden | +0.128 |
scorer | +0.124 |
usal | +0.124 |
anches | +0.118 |
Neg logit contributions | |
Sally | -0.121 |
estern | -0.120 |
roo | -0.112 |
tons | -0.111 |
puppies | -0.100 |
Token | Timothy |
Token ID | 22283 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
omial | +1.053 |
unden | +0.831 |
scorer | +0.816 |
usal | +0.805 |
anches | +0.766 |
Neg logit contributions | |
estern | -0.711 |
Sally | -0.689 |
roo | -0.652 |
tons | -0.636 |
puppies | -0.564 |
Token | Cot |
Token ID | 42266 |
Feature activation | +9.62e+00 |
Pos logit contributions | |
estern | +1.909 |
Sally | +1.888 |
roo | +1.768 |
tons | +1.742 |
TON | +1.520 |
Neg logit contributions | |
omial | -2.815 |
unden | -2.245 |
scorer | -2.190 |
usal | -2.157 |
exha | -2.062 |
Token | é |
Token ID | 2634 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
estern | +7.110 |
Sally | +6.812 |
tons | +6.721 |
roo | +6.714 |
TON | +5.807 |
Neg logit contributions | |
omial | -10.436 |
unden | -8.696 |
scorer | -8.282 |
exha | -8.162 |
usal | -7.858 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
estern | +0.758 |
Sally | +0.728 |
roo | +0.696 |
tons | +0.680 |
TON | +0.599 |
Neg logit contributions | |
omial | -1.106 |
unden | -0.875 |
scorer | -0.858 |
usal | -0.845 |
acing | -0.802 |
Token | founder |
Token ID | 9119 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
estern | +0.188 |
Sally | +0.186 |
roo | +0.173 |
tons | +0.169 |
puppies | +0.153 |
Neg logit contributions | |
omial | -0.245 |
unden | -0.189 |
scorer | -0.183 |
usal | -0.183 |
anches | -0.173 |
Token | of |
Token ID | 286 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
omial | +0.045 |
unden | +0.034 |
scorer | +0.034 |
usal | +0.033 |
acing | +0.031 |
Neg logit contributions | |
estern | -0.043 |
Sally | -0.042 |
roo | -0.040 |
tons | -0.039 |
puppies | -0.036 |
Token | Cot |
Token ID | 42266 |
Feature activation | +8.23e+00 |
Pos logit contributions | |
estern | +0.045 |
Sally | +0.044 |
roo | +0.041 |
tons | +0.040 |
puppies | +0.036 |
Neg logit contributions | |
omial | -0.060 |
unden | -0.047 |
scorer | -0.046 |
usal | -0.046 |
anches | -0.043 |
Token | re |
Token ID | 260 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
omial | +0.566 |
unden | +0.428 |
scorer | +0.419 |
usal | +0.411 |
acing | +0.385 |
Neg logit contributions | |
estern | -0.544 |
Sally | -0.526 |
roo | -0.506 |
tons | -0.496 |
puppies | -0.450 |
Token | pt |
Token ID | 457 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
omial | +1.484 |
unden | +1.134 |
scorer | +1.113 |
usal | +1.105 |
anches | +1.040 |
Neg logit contributions | |
estern | -1.240 |
Sally | -1.195 |
roo | -1.144 |
tons | -1.126 |
TON | -1.014 |
Token | ococ |
Token ID | 34403 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
estern | +2.510 |
Sally | +2.442 |
roo | +2.347 |
tons | +2.329 |
puppies | +2.100 |
Neg logit contributions | |
omial | -2.281 |
unden | -1.787 |
scorer | -1.681 |
exha | -1.619 |
usal | -1.585 |
Token | cus |
Token ID | 9042 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
omial | +0.352 |
unden | +0.256 |
scorer | +0.249 |
usal | +0.245 |
acing | +0.227 |
Neg logit contributions | |
estern | -0.417 |
Sally | -0.405 |
roo | -0.391 |
tons | -0.384 |
puppies | -0.352 |
Token | , |
Token ID | 11 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
estern | +0.998 |
Sally | +0.959 |
roo | +0.914 |
tons | +0.891 |
puppies | +0.792 |
Neg logit contributions | |
omial | -1.463 |
unden | -1.156 |
scorer | -1.135 |
usal | -1.118 |
acing | -1.061 |
Token | Gard |
Token ID | 12790 |
Feature activation | +9.52e+00 |
Pos logit contributions | |
omial | +0.269 |
unden | +0.212 |
scorer | +0.208 |
usal | +0.205 |
acing | +0.194 |
Neg logit contributions | |
estern | -0.191 |
Sally | -0.185 |
roo | -0.175 |
tons | -0.172 |
puppies | -0.153 |
Token | n |
Token ID | 77 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
estern | +7.647 |
Sally | +7.340 |
roo | +6.968 |
tons | +6.959 |
hire | +6.124 |
Neg logit contributions | |
omial | -9.757 |
unden | -7.899 |
scorer | -7.637 |
exha | -7.477 |
usal | -7.139 |
Token | erella |
Token ID | 36648 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
omial | +4.055 |
unden | +3.209 |
scorer | +3.189 |
usal | +3.175 |
acing | +3.051 |
Neg logit contributions | |
estern | -2.192 |
Sally | -2.117 |
roo | -1.999 |
tons | -1.951 |
TON | -1.695 |
Token | vaginal |
Token ID | 30131 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
estern | +1.655 |
Sally | +1.596 |
roo | +1.523 |
tons | +1.488 |
puppies | +1.328 |
Neg logit contributions | |
omial | -2.336 |
unden | -1.832 |
scorer | -1.801 |
usal | -1.777 |
anches | -1.683 |
Token | is |
Token ID | 271 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
estern | +3.787 |
Sally | +3.583 |
roo | +3.421 |
tons | +3.389 |
puppies | +2.993 |
Neg logit contributions | |
omial | -6.024 |
unden | -4.847 |
scorer | -4.739 |
usal | -4.663 |
anches | -4.416 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
omial | +0.421 |
unden | +0.329 |
scorer | +0.323 |
usal | +0.318 |
acing | +0.302 |
Neg logit contributions | |
estern | -0.315 |
Sally | -0.303 |
roo | -0.290 |
tons | -0.284 |
TON | -0.253 |
Token | to |
Token ID | 284 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
omial | +1.243 |
unden | +0.949 |
scorer | +0.931 |
usal | +0.916 |
acing | +0.862 |
Neg logit contributions | |
estern | -1.102 |
Sally | -1.063 |
roo | -1.022 |
tons | -1.001 |
puppies | -0.903 |
Token | break |
Token ID | 2270 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
omial | +0.192 |
unden | +0.147 |
scorer | +0.142 |
usal | +0.142 |
exha | +0.133 |
Neg logit contributions | |
Sally | -0.155 |
estern | -0.155 |
roo | -0.147 |
tons | -0.144 |
puppies | -0.131 |
Token | the |
Token ID | 262 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
omial | +0.891 |
unden | +0.684 |
scorer | +0.669 |
usal | +0.660 |
anches | +0.623 |
Neg logit contributions | |
estern | -0.745 |
Sally | -0.724 |
roo | -0.693 |
tons | -0.678 |
puppies | -0.613 |
Token | NRA |
Token ID | 23962 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
estern | +0.824 |
Sally | +0.806 |
roo | +0.768 |
tons | +0.755 |
puppies | +0.682 |
Neg logit contributions | |
omial | -0.984 |
unden | -0.761 |
scorer | -0.735 |
usal | -0.727 |
anches | -0.689 |
Token | 's |
Token ID | 338 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
estern | +1.456 |
Sally | +1.430 |
roo | +1.385 |
tons | +1.347 |
puppies | +1.218 |
Neg logit contributions | |
omial | -1.594 |
unden | -1.214 |
scorer | -1.178 |
usal | -1.157 |
acing | -1.091 |
Token | special |
Token ID | 2041 |
Feature activation | +9.49e+00 |
Pos logit contributions | |
estern | +2.149 |
Sally | +2.097 |
roo | +2.000 |
tons | +1.965 |
puppies | +1.767 |
Neg logit contributions | |
omial | -2.745 |
unden | -2.134 |
scorer | -2.060 |
usal | -2.040 |
acing | -1.940 |
Token | interest |
Token ID | 1393 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
estern | +7.099 |
Sally | +7.039 |
roo | +6.681 |
tons | +6.566 |
TON | +5.931 |
Neg logit contributions | |
omial | -10.265 |
unden | -8.107 |
usal | -7.823 |
scorer | -7.650 |
anches | -7.537 |
Token | control |
Token ID | 1630 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
estern | +3.169 |
Sally | +3.120 |
roo | +2.966 |
tons | +2.916 |
puppies | +2.632 |
Neg logit contributions | |
omial | -4.174 |
unden | -3.269 |
usal | -3.132 |
scorer | -3.131 |
anches | -2.974 |
Token | over |
Token ID | 625 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
estern | +2.470 |
Sally | +2.415 |
roo | +2.309 |
tons | +2.267 |
puppies | +2.042 |
Neg logit contributions | |
omial | -3.074 |
unden | -2.393 |
scorer | -2.323 |
usal | -2.287 |
acing | -2.173 |
Token | Congress |
Token ID | 3162 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
estern | +1.322 |
Sally | +1.291 |
roo | +1.220 |
tons | +1.203 |
puppies | +1.083 |
Neg logit contributions | |
omial | -1.757 |
unden | -1.369 |
scorer | -1.335 |
usal | -1.325 |
anches | -1.247 |
Token | ." |
Token ID | 526 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
estern | +1.535 |
Sally | +1.492 |
roo | +1.424 |
tons | +1.390 |
puppies | +1.241 |
Neg logit contributions | |
omial | -2.139 |
unden | -1.685 |
scorer | -1.648 |
usal | -1.624 |
anches | -1.535 |
Token | . |
Token ID | 13 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
omial | +0.369 |
unden | +0.287 |
scorer | +0.283 |
usal | +0.278 |
acing | +0.263 |
Neg logit contributions | |
estern | -0.300 |
Sally | -0.284 |
roo | -0.274 |
tons | -0.270 |
TON | -0.241 |
Token |
|
Token ID | 198 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
omial | +0.666 |
unden | +0.519 |
scorer | +0.516 |
usal | +0.506 |
anches | +0.484 |
Neg logit contributions | |
estern | -0.507 |
Sally | -0.476 |
roo | -0.465 |
tons | -0.456 |
puppies | -0.404 |
Token |
|
Token ID | 198 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
omial | +0.542 |
unden | +0.444 |
scorer | +0.426 |
usal | +0.420 |
exha | +0.409 |
Neg logit contributions | |
estern | -0.334 |
Sally | -0.324 |
roo | -0.308 |
tons | -0.300 |
TON | -0.263 |
Token | Senior |
Token ID | 31224 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
omial | +0.444 |
unden | +0.349 |
scorer | +0.340 |
usal | +0.334 |
acing | +0.317 |
Neg logit contributions | |
estern | -0.330 |
Sally | -0.319 |
roo | -0.306 |
tons | -0.299 |
TON | -0.267 |
Token | advocate |
Token ID | 12811 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
omial | +0.911 |
unden | +0.693 |
scorer | +0.671 |
usal | +0.667 |
acing | +0.627 |
Neg logit contributions | |
estern | -0.809 |
Sally | -0.792 |
roo | -0.753 |
tons | -0.741 |
puppies | -0.670 |
Token | Muk |
Token ID | 31509 |
Feature activation | +9.45e+00 |
Pos logit contributions | |
estern | +0.080 |
Sally | +0.079 |
roo | +0.073 |
tons | +0.072 |
puppies | +0.064 |
Neg logit contributions | |
omial | -0.119 |
unden | -0.094 |
scorer | -0.091 |
usal | -0.090 |
acing | -0.086 |
Token | ul |
Token ID | 377 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Sally | +6.779 |
estern | +6.762 |
roo | +6.635 |
tons | +6.352 |
hire | +5.631 |
Neg logit contributions | |
omial | -10.354 |
unden | -8.450 |
scorer | -8.442 |
exha | -7.919 |
\\\\\\\\\\\\\\\\ | -7.579 |
Token | Roh |
Token ID | 32694 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
omial | +1.227 |
unden | +0.972 |
scorer | +0.959 |
usal | +0.949 |
acing | +0.901 |
Neg logit contributions | |
estern | -0.786 |
Sally | -0.750 |
roo | -0.714 |
tons | -0.700 |
puppies | -0.617 |
Token | at |
Token ID | 265 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
omial | +2.212 |
unden | +1.741 |
scorer | +1.710 |
usal | +1.683 |
acing | +1.596 |
Neg logit contributions | |
estern | -1.570 |
Sally | -1.510 |
roo | -1.445 |
tons | -1.410 |
puppies | -1.251 |
Token | gi |
Token ID | 12397 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
estern | +1.878 |
Sally | +1.838 |
roo | +1.791 |
tons | +1.734 |
TON | +1.589 |
Neg logit contributions | |
omial | -1.718 |
unden | -1.273 |
scorer | -1.223 |
usal | -1.210 |
anches | -1.124 |
Token | appearing |
Token ID | 12655 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
estern | +1.584 |
Sally | +1.568 |
roo | +1.487 |
tons | +1.435 |
puppies | +1.285 |
Neg logit contributions | |
omial | -2.220 |
unden | -1.738 |
scorer | -1.688 |
usal | -1.667 |
anches | -1.585 |
Token | Monday |
Token ID | 3321 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
estern | +0.734 |
Sally | +0.720 |
roo | +0.675 |
tons | +0.659 |
puppies | +0.589 |
Neg logit contributions | |
omial | -1.118 |
unden | -0.880 |
scorer | -0.859 |
usal | -0.853 |
acing | -0.808 |
Token | that |
Token ID | 326 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
estern | +1.128 |
Sally | +1.100 |
roo | +1.041 |
tons | +1.021 |
puppies | +0.918 |
Neg logit contributions | |
omial | -1.486 |
unden | -1.153 |
scorer | -1.126 |
usal | -1.114 |
acing | -1.053 |
Token | Defense |
Token ID | 5947 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
estern | +0.084 |
Sally | +0.081 |
roo | +0.077 |
tons | +0.075 |
puppies | +0.066 |
Neg logit contributions | |
omial | -0.138 |
unden | -0.110 |
scorer | -0.108 |
usal | -0.106 |
anches | -0.101 |
Token | Secretary |
Token ID | 4986 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
Sally | +2.341 |
estern | +2.251 |
roo | +2.072 |
tons | +1.973 |
puppies | +1.694 |
Neg logit contributions | |
omial | -5.855 |
unden | -4.794 |
scorer | -4.653 |
usal | -4.605 |
anches | -4.427 |
Token | Chuck |
Token ID | 14663 |
Feature activation | +9.12e+00 |
Pos logit contributions | |
estern | +0.549 |
Sally | +0.539 |
roo | +0.497 |
tons | +0.484 |
puppies | +0.414 |
Neg logit contributions | |
omial | -1.152 |
unden | -0.938 |
scorer | -0.921 |
usal | -0.909 |
anches | -0.873 |
Token | Hag |
Token ID | 21375 |
Feature activation | +9.44e+00 |
Pos logit contributions | |
Sally | +3.252 |
estern | +2.814 |
roo | +2.546 |
tons | +2.377 |
hire | +1.783 |
Neg logit contributions | |
omial | -13.837 |
unden | -12.541 |
exha | -11.919 |
scorer | -11.529 |
usal | -11.501 |
Token | el |
Token ID | 417 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
estern | +5.081 |
Sally | +4.841 |
roo | +4.811 |
tons | +4.514 |
hire | +4.065 |
Neg logit contributions | |
omial | -11.941 |
unden | -11.270 |
exha | -10.815 |
scorer | -10.029 |
mathemat | -9.633 |
Token | will |
Token ID | 481 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
estern | +3.377 |
Sally | +3.355 |
roo | +3.099 |
tons | +3.041 |
puppies | +2.738 |
Neg logit contributions | |
omial | -4.704 |
unden | -3.700 |
scorer | -3.571 |
usal | -3.542 |
exha | -3.359 |
Token | step |
Token ID | 2239 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
estern | +2.590 |
Sally | +2.580 |
roo | +2.378 |
tons | +2.286 |
puppies | +2.021 |
Neg logit contributions | |
omial | -4.999 |
unden | -4.071 |
scorer | -3.924 |
usal | -3.899 |
exha | -3.736 |
Token | down |
Token ID | 866 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
estern | +2.777 |
Sally | +2.703 |
roo | +2.612 |
tons | +2.560 |
puppies | +2.358 |
Neg logit contributions | |
omial | -2.240 |
unden | -1.602 |
scorer | -1.558 |
usal | -1.532 |
anches | -1.420 |
Token | from |
Token ID | 422 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
omial | +1.352 |
unden | +1.060 |
scorer | +1.042 |
usal | +1.026 |
acing | +0.973 |
Neg logit contributions | |
estern | -0.988 |
Sally | -0.949 |
roo | -0.908 |
tons | -0.888 |
puppies | -0.789 |
Token | Story |
Token ID | 11605 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
estern | +2.011 |
Sally | +1.929 |
roo | +1.880 |
tons | +1.844 |
TON | +1.665 |
Neg logit contributions | |
omial | -2.756 |
unden | -2.191 |
scorer | -2.121 |
usal | -2.063 |
exha | -2.024 |
Token | highlights |
Token ID | 11330 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
omial | +3.021 |
unden | +2.099 |
scorer | +2.042 |
usal | +1.990 |
acing | +1.834 |
Neg logit contributions | |
estern | -4.361 |
Sally | -4.229 |
roo | -4.105 |
tons | -4.040 |
enegger | -3.731 |
Token | Secretary |
Token ID | 4986 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
estern | +0.011 |
Sally | +0.011 |
roo | +0.010 |
tons | +0.010 |
puppies | +0.009 |
Neg logit contributions | |
omial | -0.015 |
unden | -0.012 |
scorer | -0.012 |
usal | -0.012 |
anches | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
estern | +0.120 |
Sally | +0.117 |
roo | +0.111 |
tons | +0.110 |
puppies | +0.099 |
Neg logit contributions | |
omial | -0.126 |
unden | -0.095 |
scorer | -0.093 |
usal | -0.091 |
anches | -0.086 |
Token | Defense |
Token ID | 5947 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
estern | +0.402 |
Sally | +0.391 |
roo | +0.374 |
tons | +0.367 |
puppies | +0.333 |
Neg logit contributions | |
omial | -0.427 |
unden | -0.324 |
scorer | -0.316 |
usal | -0.311 |
anches | -0.292 |
Token | Chuck |
Token ID | 14663 |
Feature activation | +9.44e+00 |
Pos logit contributions | |
Sally | +2.966 |
estern | +2.683 |
roo | +2.561 |
tons | +2.545 |
puppies | +2.248 |
Neg logit contributions | |
omial | -5.069 |
unden | -4.029 |
scorer | -3.865 |
usal | -3.830 |
exha | -3.725 |
Token | Hag |
Token ID | 21375 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
Sally | +3.400 |
estern | +2.825 |
tons | +2.759 |
roo | +2.649 |
hire | +2.073 |
Neg logit contributions | |
omial | -14.252 |
unden | -12.597 |
usal | -11.915 |
scorer | -11.842 |
exha | -11.741 |
Token | el |
Token ID | 417 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
Sally | +5.266 |
estern | +4.897 |
roo | +4.757 |
tons | +4.309 |
puppies | +3.901 |
Neg logit contributions | |
omial | -13.878 |
unden | -11.757 |
exha | -11.300 |
scorer | -11.291 |
usal | -11.188 |
Token | will |
Token ID | 481 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
Sally | +3.998 |
estern | +3.928 |
roo | +3.680 |
tons | +3.586 |
puppies | +3.315 |
Neg logit contributions | |
omial | -5.178 |
unden | -4.024 |
usal | -3.861 |
scorer | -3.817 |
exha | -3.648 |
Token | step |
Token ID | 2239 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
Sally | +3.252 |
estern | +3.250 |
roo | +3.042 |
tons | +2.969 |
puppies | +2.720 |
Neg logit contributions | |
omial | -4.057 |
unden | -3.157 |
scorer | -2.997 |
usal | -2.997 |
exha | -2.844 |
Token | down |
Token ID | 866 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
estern | +3.081 |
Sally | +2.999 |
roo | +2.892 |
tons | +2.838 |
puppies | +2.604 |
Neg logit contributions | |
omial | -2.688 |
unden | -1.957 |
scorer | -1.877 |
usal | -1.853 |
anches | -1.732 |
Token | that |
Token ID | 326 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
estern | +1.312 |
Sally | +1.306 |
roo | +1.232 |
tons | +1.199 |
puppies | +1.081 |
Neg logit contributions | |
omial | -1.834 |
unden | -1.432 |
scorer | -1.391 |
usal | -1.390 |
anches | -1.335 |
Token | should |
Token ID | 815 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Sally | +0.481 |
estern | +0.476 |
roo | +0.448 |
tons | +0.442 |
puppies | +0.401 |
Neg logit contributions | |
omial | -0.642 |
unden | -0.491 |
usal | -0.482 |
scorer | -0.479 |
anches | -0.460 |
Token | 've |
Token ID | 1053 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
estern | +1.777 |
Sally | +1.741 |
roo | +1.674 |
tons | +1.639 |
puppies | +1.448 |
Neg logit contributions | |
omial | -2.607 |
unden | -2.095 |
scorer | -2.028 |
usal | -1.992 |
anches | -1.909 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
estern | +1.534 |
Sally | +1.525 |
roo | +1.434 |
tons | +1.406 |
puppies | +1.253 |
Neg logit contributions | |
omial | -2.547 |
unden | -2.020 |
scorer | -1.976 |
usal | -1.972 |
anches | -1.897 |
Token | him |
Token ID | 683 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
estern | +0.948 |
Sally | +0.942 |
roo | +0.885 |
tons | +0.866 |
puppies | +0.779 |
Neg logit contributions | |
omial | -1.404 |
unden | -1.093 |
usal | -1.071 |
scorer | -1.068 |
anches | -1.017 |
Token | cold |
Token ID | 4692 |
Feature activation | +9.40e+00 |
Pos logit contributions | |
omial | +0.500 |
unden | +0.388 |
scorer | +0.380 |
usal | +0.375 |
anches | +0.354 |
Neg logit contributions | |
estern | -0.391 |
Sally | -0.379 |
roo | -0.362 |
tons | -0.354 |
puppies | -0.318 |
Token | . |
Token ID | 13 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Sally | +6.736 |
estern | +6.709 |
roo | +6.275 |
tons | +6.099 |
puppies | +5.534 |
Neg logit contributions | |
omial | -10.562 |
unden | -8.472 |
scorer | -8.086 |
usal | -8.059 |
anches | -7.725 |
Token | It |
Token ID | 632 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
estern | +0.152 |
Sally | +0.149 |
roo | +0.141 |
tons | +0.138 |
puppies | +0.122 |
Neg logit contributions | |
omial | -0.216 |
unden | -0.171 |
scorer | -0.167 |
usal | -0.165 |
exha | -0.156 |
Token | doesn |
Token ID | 1595 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
estern | +0.549 |
Sally | +0.545 |
roo | +0.518 |
tons | +0.508 |
puppies | +0.459 |
Neg logit contributions | |
omial | -0.693 |
unden | -0.544 |
scorer | -0.521 |
usal | -0.516 |
anches | -0.492 |
Token | 't |
Token ID | 470 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
omial | +4.013 |
scorer | +2.822 |
usal | +2.803 |
unden | +2.727 |
acing | +2.618 |
Neg logit contributions | |
estern | -4.764 |
Sally | -4.572 |
roo | -4.404 |
tons | -4.305 |
enegger | -4.011 |
Token | matter |
Token ID | 2300 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
estern | +0.158 |
Sally | +0.157 |
roo | +0.150 |
tons | +0.146 |
puppies | +0.131 |
Neg logit contributions | |
omial | -0.221 |
unden | -0.176 |
scorer | -0.169 |
usal | -0.167 |
anches | -0.159 |
Token | his |
Token ID | 465 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
omial | +4.510 |
unden | +3.518 |
scorer | +3.473 |
usal | +3.402 |
acing | +3.215 |
Neg logit contributions | |
estern | -3.610 |
Sally | -3.433 |
roo | -3.339 |
tons | -3.255 |
TON | -2.913 |
Token | case |
Token ID | 1339 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
estern | +0.106 |
Sally | +0.104 |
roo | +0.099 |
tons | +0.097 |
puppies | +0.089 |
Neg logit contributions | |
omial | -0.119 |
unden | -0.090 |
scorer | -0.086 |
usal | -0.086 |
anches | -0.082 |
Token | against |
Token ID | 1028 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
estern | +2.427 |
Sally | +2.399 |
roo | +2.254 |
tons | +2.195 |
puppies | +1.977 |
Neg logit contributions | |
omial | -3.462 |
unden | -2.713 |
scorer | -2.640 |
usal | -2.617 |
anches | -2.481 |
Token | Sen |
Token ID | 2311 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
estern | +1.110 |
Sally | +1.075 |
roo | +1.012 |
tons | +0.992 |
puppies | +0.881 |
Neg logit contributions | |
omial | -1.684 |
unden | -1.331 |
scorer | -1.304 |
usal | -1.288 |
anches | -1.226 |
Token | . |
Token ID | 13 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
Sally | +3.057 |
estern | +3.049 |
roo | +2.902 |
tons | +2.829 |
hire | +2.473 |
Neg logit contributions | |
omial | -4.860 |
unden | -4.163 |
exha | -3.879 |
scorer | -3.849 |
usal | -3.707 |
Token | Mitch |
Token ID | 20472 |
Feature activation | +9.36e+00 |
Pos logit contributions | |
omial | +0.865 |
unden | +0.692 |
scorer | +0.687 |
usal | +0.675 |
acing | +0.648 |
Neg logit contributions | |
estern | -0.513 |
Sally | -0.477 |
roo | -0.462 |
tons | -0.450 |
TON | -0.392 |
Token | McConnell |
Token ID | 18184 |
Feature activation | +7.19e+00 |
Pos logit contributions | |
Sally | +3.637 |
estern | +3.383 |
roo | +3.127 |
tons | +2.799 |
puppies | +2.186 |
Neg logit contributions | |
omial | -14.088 |
unden | -11.929 |
scorer | -11.468 |
usal | -11.386 |
anches | -11.124 |
Token | for |
Token ID | 329 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Sally | +5.524 |
estern | +5.394 |
roo | +5.112 |
tons | +4.850 |
puppies | +4.437 |
Neg logit contributions | |
omial | -7.954 |
unden | -6.349 |
scorer | -6.024 |
usal | -6.016 |
anches | -5.749 |
Token | refusing |
Token ID | 15487 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
estern | +1.141 |
Sally | +1.110 |
roo | +1.047 |
tons | +1.027 |
puppies | +0.916 |
Neg logit contributions | |
omial | -1.635 |
unden | -1.281 |
scorer | -1.252 |
usal | -1.238 |
anches | -1.178 |
Token | to |
Token ID | 284 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
omial | +2.693 |
unden | +2.034 |
scorer | +2.006 |
usal | +1.972 |
itive | +1.821 |
Neg logit contributions | |
estern | -3.014 |
roo | -2.813 |
Sally | -2.812 |
tons | -2.783 |
TON | -2.495 |
Token | denounce |
Token ID | 38639 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
omial | +0.183 |
unden | +0.141 |
scorer | +0.136 |
usal | +0.135 |
acing | +0.127 |
Neg logit contributions | |
estern | -0.155 |
Sally | -0.152 |
roo | -0.145 |
tons | -0.141 |
puppies | -0.129 |
Token | not |
Token ID | 407 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
estern | +0.383 |
Sally | +0.372 |
roo | +0.351 |
tons | +0.345 |
puppies | +0.305 |
Neg logit contributions | |
omial | -0.575 |
unden | -0.454 |
scorer | -0.446 |
usal | -0.440 |
acing | -0.418 |
Token | today |
Token ID | 1909 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
omial | +1.351 |
unden | +1.052 |
scorer | +1.033 |
usal | +1.019 |
acing | +0.964 |
Neg logit contributions | |
estern | -1.019 |
Sally | -0.986 |
roo | -0.939 |
tons | -0.922 |
puppies | -0.824 |
Token | , |
Token ID | 11 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
estern | +2.396 |
Sally | +2.332 |
roo | +2.190 |
tons | +2.150 |
puppies | +1.889 |
Neg logit contributions | |
omial | -3.857 |
unden | -3.079 |
scorer | -3.020 |
usal | -2.979 |
anches | -2.833 |
Token | then |
Token ID | 788 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
estern | +0.277 |
Sally | +0.270 |
roo | +0.253 |
tons | +0.249 |
puppies | +0.221 |
Neg logit contributions | |
omial | -0.423 |
unden | -0.336 |
scorer | -0.328 |
usal | -0.324 |
anches | -0.309 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
estern | +2.002 |
Sally | +1.999 |
tons | +1.823 |
roo | +1.820 |
puppies | +1.592 |
Neg logit contributions | |
omial | -3.675 |
unden | -2.941 |
scorer | -2.861 |
usal | -2.856 |
anches | -2.738 |
Token | sickness |
Token ID | 26359 |
Feature activation | +9.35e+00 |
Pos logit contributions | |
estern | +1.746 |
Sally | +1.709 |
roo | +1.614 |
tons | +1.575 |
puppies | +1.394 |
Neg logit contributions | |
omial | -2.660 |
unden | -2.113 |
scorer | -2.076 |
usal | -2.044 |
anches | -1.940 |
Token | and |
Token ID | 290 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Sally | +6.980 |
estern | +6.905 |
roo | +6.570 |
tons | +6.382 |
puppies | +5.814 |
Neg logit contributions | |
omial | -10.028 |
unden | -8.010 |
scorer | -7.750 |
usal | -7.600 |
exha | -7.271 |
Token | death |
Token ID | 1918 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
estern | +0.205 |
Sally | +0.200 |
roo | +0.190 |
tons | +0.187 |
puppies | +0.169 |
Neg logit contributions | |
omial | -0.268 |
unden | -0.207 |
scorer | -0.203 |
usal | -0.201 |
anches | -0.190 |
Token | will |
Token ID | 481 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
omial | +0.813 |
unden | +0.624 |
scorer | +0.610 |
usal | +0.601 |
anches | +0.564 |
Neg logit contributions | |
estern | -0.705 |
Sally | -0.686 |
roo | -0.657 |
tons | -0.644 |
puppies | -0.584 |
Token | come |
Token ID | 1282 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Sally | +2.082 |
estern | +2.078 |
roo | +1.985 |
tons | +1.939 |
puppies | +1.753 |
Neg logit contributions | |
omial | -2.879 |
unden | -2.291 |
scorer | -2.206 |
usal | -2.196 |
anches | -2.073 |
Token | ( |
Token ID | 357 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
estern | +1.240 |
Sally | +1.228 |
roo | +1.162 |
tons | +1.135 |
puppies | +1.022 |
Neg logit contributions | |
omial | -1.701 |
unden | -1.334 |
scorer | -1.302 |
usal | -1.291 |
anches | -1.214 |
Token |
|
Token ID | 198 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
omial | +0.820 |
unden | +0.665 |
scorer | +0.643 |
usal | +0.633 |
exha | +0.610 |
Neg logit contributions | |
estern | -0.516 |
Sally | -0.497 |
roo | -0.474 |
tons | -0.463 |
TON | -0.406 |
Token | Hur |
Token ID | 42633 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
omial | +0.760 |
unden | +0.600 |
scorer | +0.584 |
usal | +0.573 |
exha | +0.546 |
Neg logit contributions | |
estern | -0.559 |
Sally | -0.537 |
roo | -0.519 |
tons | -0.507 |
TON | -0.452 |
Token | tt |
Token ID | 926 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
omial | +3.057 |
unden | +2.563 |
scorer | +2.502 |
usal | +2.473 |
exha | +2.386 |
Neg logit contributions | |
estern | -1.121 |
Sally | -1.052 |
roo | -0.985 |
tons | -0.955 |
TON | -0.769 |
Token | has |
Token ID | 468 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
estern | +2.627 |
Sally | +2.574 |
roo | +2.415 |
tons | +2.393 |
puppies | +2.138 |
Neg logit contributions | |
omial | -3.569 |
unden | -2.811 |
usal | -2.686 |
scorer | -2.664 |
exha | -2.561 |
Token | also |
Token ID | 635 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
estern | +0.157 |
Sally | +0.152 |
roo | +0.143 |
tons | +0.142 |
puppies | +0.127 |
Neg logit contributions | |
omial | -0.221 |
unden | -0.171 |
scorer | -0.167 |
usal | -0.166 |
anches | -0.158 |
Token | tut |
Token ID | 9732 |
Feature activation | +9.32e+00 |
Pos logit contributions | |
estern | +2.571 |
Sally | +2.525 |
roo | +2.366 |
tons | +2.316 |
puppies | +2.104 |
Neg logit contributions | |
omial | -3.719 |
unden | -2.932 |
usal | -2.799 |
scorer | -2.784 |
anches | -2.662 |
Token | ored |
Token ID | 1850 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
estern | +8.236 |
Sally | +8.155 |
roo | +8.027 |
tons | +7.794 |
hire | +7.142 |
Neg logit contributions | |
omial | -8.823 |
unden | -7.050 |
exha | -6.629 |
scorer | -6.599 |
usal | -6.486 |
Token | outside |
Token ID | 2354 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
estern | +1.244 |
Sally | +1.231 |
roo | +1.164 |
tons | +1.141 |
puppies | +1.046 |
Neg logit contributions | |
omial | -1.420 |
unden | -1.068 |
usal | -1.036 |
scorer | -1.025 |
anches | -0.970 |
Token | linebacker |
Token ID | 18961 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
omial | +1.609 |
unden | +1.248 |
scorer | +1.216 |
usal | +1.204 |
anches | +1.136 |
Neg logit contributions | |
estern | -1.278 |
Sally | -1.234 |
roo | -1.180 |
tons | -1.156 |
puppies | -1.039 |
Token | Willie |
Token ID | 28623 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
omial | +1.790 |
unden | +1.412 |
scorer | +1.386 |
usal | +1.367 |
acing | +1.297 |
Neg logit contributions | |
estern | -1.237 |
Sally | -1.191 |
roo | -1.135 |
tons | -1.108 |
puppies | -0.983 |
Token | Young |
Token ID | 6960 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
omial | +1.445 |
unden | +1.130 |
scorer | +1.099 |
usal | +1.086 |
anches | +1.033 |
Neg logit contributions | |
estern | -1.061 |
Sally | -1.041 |
roo | -0.980 |
tons | -0.963 |
puppies | -0.860 |
Token | , |
Token ID | 11 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
omial | +0.769 |
unden | +0.610 |
scorer | +0.600 |
usal | +0.591 |
acing | +0.562 |
Neg logit contributions | |
estern | -0.503 |
Sally | -0.482 |
roo | -0.460 |
tons | -0.449 |
puppies | -0.396 |
Token | I |
Token ID | 314 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
omial | +0.389 |
unden | +0.309 |
scorer | +0.303 |
usal | +0.299 |
acing | +0.284 |
Neg logit contributions | |
estern | -0.251 |
Sally | -0.243 |
roo | -0.231 |
tons | -0.225 |
puppies | -0.199 |
Token | found |
Token ID | 1043 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
estern | +0.406 |
Sally | +0.396 |
roo | +0.377 |
tons | +0.369 |
puppies | +0.331 |
Neg logit contributions | |
omial | -0.532 |
unden | -0.418 |
scorer | -0.403 |
usal | -0.397 |
acing | -0.378 |
Token | his |
Token ID | 465 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
omial | +3.720 |
unden | +2.898 |
scorer | +2.853 |
usal | +2.822 |
acing | +2.662 |
Neg logit contributions | |
estern | -2.935 |
Sally | -2.784 |
roo | -2.679 |
tons | -2.621 |
TON | -2.346 |
Token | style |
Token ID | 3918 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
estern | +0.021 |
Sally | +0.021 |
roo | +0.020 |
tons | +0.019 |
puppies | +0.018 |
Neg logit contributions | |
omial | -0.028 |
unden | -0.022 |
scorer | -0.021 |
usal | -0.021 |
anches | -0.020 |
Token | cold |
Token ID | 4692 |
Feature activation | +9.24e+00 |
Pos logit contributions | |
estern | +0.354 |
Sally | +0.346 |
roo | +0.328 |
tons | +0.324 |
puppies | +0.292 |
Neg logit contributions | |
omial | -0.452 |
unden | -0.350 |
scorer | -0.339 |
usal | -0.334 |
anches | -0.319 |
Token | and |
Token ID | 290 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
estern | +6.299 |
Sally | +6.269 |
tons | +5.806 |
roo | +5.789 |
puppies | +5.088 |
Neg logit contributions | |
omial | -10.609 |
unden | -8.375 |
scorer | -8.149 |
usal | -8.024 |
anches | -7.915 |
Token | stiff |
Token ID | 15175 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
omial | +0.451 |
unden | +0.345 |
scorer | +0.338 |
usal | +0.332 |
anches | +0.315 |
Neg logit contributions | |
estern | -0.380 |
Sally | -0.370 |
roo | -0.353 |
tons | -0.348 |
puppies | -0.313 |
Token | , |
Token ID | 11 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
estern | +1.556 |
Sally | +1.505 |
roo | +1.434 |
tons | +1.406 |
enegger | +1.244 |
Neg logit contributions | |
omial | -2.343 |
unden | -1.854 |
scorer | -1.819 |
usal | -1.785 |
anches | -1.712 |
Token | especially |
Token ID | 2592 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
omial | +0.352 |
unden | +0.276 |
scorer | +0.270 |
usal | +0.266 |
anches | +0.255 |
Neg logit contributions | |
estern | -0.248 |
Sally | -0.241 |
roo | -0.229 |
tons | -0.225 |
puppies | -0.200 |
Token | in |
Token ID | 287 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
estern | +2.336 |
Sally | +2.331 |
roo | +2.170 |
tons | +2.157 |
puppies | +1.905 |
Neg logit contributions | |
omial | -3.715 |
unden | -2.940 |
scorer | -2.853 |
usal | -2.839 |
anches | -2.739 |
Token | mass |
Token ID | 2347 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
omial | +0.614 |
unden | +0.462 |
scorer | +0.452 |
usal | +0.448 |
acing | +0.422 |
Neg logit contributions | |
estern | -0.578 |
Sally | -0.566 |
roo | -0.539 |
tons | -0.536 |
puppies | -0.484 |
Token | - |
Token ID | 12 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
estern | +0.742 |
Sally | +0.727 |
roo | +0.695 |
tons | +0.685 |
puppies | +0.611 |
Neg logit contributions | |
omial | -0.991 |
unden | -0.775 |
scorer | -0.752 |
usal | -0.747 |
acing | -0.708 |
Token | mass |
Token ID | 22208 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
omial | +0.794 |
unden | +0.605 |
scorer | +0.592 |
usal | +0.576 |
exha | +0.544 |
Neg logit contributions | |
estern | -0.731 |
Sally | -0.709 |
roo | -0.685 |
tons | -0.677 |
TON | -0.606 |
Token | gets |
Token ID | 3011 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
omial | +0.890 |
unden | +0.681 |
scorer | +0.665 |
usal | +0.653 |
anches | +0.616 |
Neg logit contributions | |
estern | -0.793 |
Sally | -0.776 |
roo | -0.744 |
tons | -0.732 |
puppies | -0.661 |
Token | " |
Token ID | 366 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
omial | +0.705 |
unden | +0.549 |
scorer | +0.534 |
usal | +0.525 |
exha | +0.494 |
Neg logit contributions | |
estern | -0.598 |
Sally | -0.582 |
roo | -0.559 |
tons | -0.553 |
puppies | -0.492 |
Token | bl |
Token ID | 2436 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
estern | +1.007 |
Sally | +0.972 |
roo | +0.954 |
tons | +0.938 |
TON | +0.839 |
Neg logit contributions | |
omial | -1.128 |
unden | -0.869 |
scorer | -0.848 |
usal | -0.820 |
exha | -0.789 |
Token | urry |
Token ID | 16682 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
omial | +12.009 |
usal | +8.793 |
scorer | +8.539 |
anches | +8.380 |
acing | +8.344 |
Neg logit contributions | |
estern | -12.048 |
Sally | -11.853 |
tons | -10.868 |
roo | -10.827 |
Mechdragon | -10.646 |
Token | " |
Token ID | 1 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
omial | +2.358 |
unden | +1.867 |
scorer | +1.832 |
usal | +1.806 |
anches | +1.716 |
Neg logit contributions | |
estern | -1.581 |
Sally | -1.523 |
roo | -1.451 |
tons | -1.418 |
puppies | -1.255 |
Token | and |
Token ID | 290 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
estern | +0.190 |
Sally | +0.187 |
roo | +0.178 |
tons | +0.175 |
puppies | +0.157 |
Neg logit contributions | |
omial | -0.262 |
unden | -0.208 |
scorer | -0.200 |
usal | -0.199 |
exha | -0.189 |
Token | loses |
Token ID | 14754 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
omial | +0.907 |
unden | +0.699 |
scorer | +0.681 |
usal | +0.675 |
acing | +0.640 |
Neg logit contributions | |
estern | -0.721 |
Sally | -0.708 |
roo | -0.674 |
tons | -0.666 |
puppies | -0.600 |
Token | detail |
Token ID | 3703 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
omial | +3.895 |
unden | +3.015 |
scorer | +2.959 |
usal | +2.911 |
acing | +2.749 |
Neg logit contributions | |
estern | -3.163 |
Sally | -3.041 |
roo | -2.921 |
tons | -2.853 |
puppies | -2.560 |
Token | practice |
Token ID | 3357 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Sally | +3.253 |
estern | +3.236 |
tons | +3.039 |
roo | +3.016 |
puppies | +2.661 |
Neg logit contributions | |
omial | -4.906 |
unden | -3.833 |
usal | -3.744 |
scorer | -3.715 |
anches | -3.588 |
Token | of |
Token ID | 286 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
estern | +1.678 |
Sally | +1.611 |
roo | +1.564 |
tons | +1.526 |
enegger | +1.402 |
Neg logit contributions | |
omial | -1.490 |
unden | -1.102 |
scorer | -1.075 |
usal | -1.056 |
acing | -0.981 |
Token | hydraulic |
Token ID | 34797 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
estern | +0.318 |
Sally | +0.312 |
roo | +0.296 |
tons | +0.292 |
puppies | +0.264 |
Neg logit contributions | |
omial | -0.361 |
unden | -0.273 |
scorer | -0.267 |
usal | -0.264 |
acing | -0.248 |
Token | fracturing |
Token ID | 48690 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
omial | +1.095 |
unden | +0.813 |
scorer | +0.794 |
usal | +0.780 |
anches | +0.729 |
Neg logit contributions | |
estern | -1.148 |
Sally | -1.117 |
roo | -1.074 |
tons | -1.056 |
puppies | -0.963 |
Token | ( |
Token ID | 357 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
omial | +1.682 |
unden | +1.325 |
scorer | +1.302 |
usal | +1.281 |
acing | +1.217 |
Neg logit contributions | |
estern | -1.200 |
Sally | -1.144 |
roo | -1.097 |
tons | -1.067 |
puppies | -0.947 |
Token | bl |
Token ID | 2436 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
estern | +1.224 |
Sally | +1.201 |
roo | +1.169 |
tons | +1.132 |
hire | +1.009 |
Neg logit contributions | |
omial | -1.824 |
unden | -1.430 |
scorer | -1.404 |
usal | -1.364 |
anches | -1.305 |
Token | asting |
Token ID | 9222 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
omial | +11.606 |
usal | +8.585 |
acing | +8.356 |
scorer | +8.242 |
umer | +8.102 |
Neg logit contributions | |
estern | -11.587 |
Sally | -11.568 |
tons | -10.934 |
roo | -10.703 |
TON | -10.150 |
Token | a |
Token ID | 257 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
omial | +4.114 |
unden | +3.166 |
scorer | +3.112 |
usal | +3.054 |
anches | +2.876 |
Neg logit contributions | |
estern | -3.581 |
Sally | -3.434 |
roo | -3.319 |
tons | -3.229 |
TON | -2.910 |
Token | high |
Token ID | 1029 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
omial | +0.044 |
unden | +0.034 |
scorer | +0.033 |
usal | +0.033 |
anches | +0.031 |
Neg logit contributions | |
estern | -0.037 |
Sally | -0.036 |
roo | -0.034 |
tons | -0.033 |
TON | -0.030 |
Token | - |
Token ID | 12 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
estern | +0.040 |
Sally | +0.039 |
roo | +0.037 |
tons | +0.037 |
hire | +0.033 |
Neg logit contributions | |
omial | -0.057 |
unden | -0.045 |
scorer | -0.043 |
usal | -0.043 |
anches | -0.041 |
Token | pressure |
Token ID | 36151 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
omial | +0.823 |
unden | +0.577 |
scorer | +0.557 |
usal | +0.541 |
anches | +0.497 |
Neg logit contributions | |
estern | -1.187 |
Sally | -1.157 |
roo | -1.125 |
tons | -1.114 |
TON | -1.023 |
Token | screen |
Token ID | 3159 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
omial | +0.352 |
unden | +0.270 |
scorer | +0.261 |
usal | +0.259 |
anches | +0.248 |
Neg logit contributions | |
estern | -0.289 |
Sally | -0.285 |
roo | -0.272 |
tons | -0.269 |
TON | -0.240 |
Token | also |
Token ID | 635 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
omial | +3.281 |
unden | +2.564 |
scorer | +2.511 |
usal | +2.478 |
anches | +2.344 |
Neg logit contributions | |
estern | -2.472 |
Sally | -2.384 |
roo | -2.280 |
tons | -2.233 |
puppies | -1.991 |
Token | includes |
Token ID | 3407 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Sally | +2.902 |
estern | +2.862 |
tons | +2.762 |
roo | +2.747 |
puppies | +2.512 |
Neg logit contributions | |
omial | -3.057 |
unden | -2.296 |
usal | -2.196 |
scorer | -2.162 |
exha | -2.064 |
Token | a |
Token ID | 257 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
estern | +1.250 |
Sally | +1.224 |
roo | +1.159 |
tons | +1.150 |
puppies | +1.013 |
Neg logit contributions | |
omial | -1.700 |
unden | -1.320 |
scorer | -1.292 |
usal | -1.277 |
anches | -1.216 |
Token | native |
Token ID | 6868 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
omial | +0.499 |
unden | +0.387 |
scorer | +0.378 |
usal | +0.374 |
anches | +0.355 |
Neg logit contributions | |
estern | -0.390 |
Sally | -0.380 |
roo | -0.363 |
tons | -0.357 |
TON | -0.317 |
Token | Bl |
Token ID | 1086 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
omial | +3.032 |
unden | +2.380 |
scorer | +2.336 |
usal | +2.303 |
anches | +2.183 |
Neg logit contributions | |
estern | -2.189 |
Sally | -2.107 |
roo | -2.013 |
tons | -1.968 |
puppies | -1.749 |
Token | ur |
Token ID | 333 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
omial | +9.733 |
scorer | +6.612 |
usal | +6.597 |
itive | +6.364 |
acing | +6.238 |
Neg logit contributions | |
estern | -13.683 |
Sally | -13.149 |
roo | -12.495 |
tons | -12.250 |
puppies | -11.608 |
Token | Reduction |
Token ID | 33396 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
omial | +3.142 |
unden | +2.392 |
scorer | +2.357 |
usal | +2.310 |
acing | +2.182 |
Neg logit contributions | |
estern | -2.812 |
Sally | -2.705 |
roo | -2.589 |
tons | -2.550 |
puppies | -2.301 |
Token | mode |
Token ID | 4235 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
omial | +2.710 |
unden | +2.098 |
scorer | +2.057 |
usal | +2.026 |
anches | +1.914 |
Neg logit contributions | |
estern | -2.193 |
Sally | -2.116 |
roo | -2.029 |
tons | -1.986 |
puppies | -1.780 |
Token | to |
Token ID | 284 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
omial | +5.149 |
unden | +3.943 |
scorer | +3.901 |
usal | +3.814 |
acing | +3.602 |
Neg logit contributions | |
estern | -4.491 |
Sally | -4.286 |
roo | -4.114 |
tons | -4.016 |
enegger | -3.650 |
Token | help |
Token ID | 1037 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
omial | +1.691 |
unden | +1.277 |
scorer | +1.243 |
usal | +1.229 |
anches | +1.153 |
Neg logit contributions | |
estern | -1.583 |
Sally | -1.549 |
roo | -1.485 |
tons | -1.459 |
puppies | -1.324 |
Token | to |
Token ID | 284 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
estern | +0.504 |
Sally | +0.489 |
roo | +0.466 |
tons | +0.456 |
puppies | +0.408 |
Neg logit contributions | |
omial | -0.682 |
unden | -0.534 |
scorer | -0.519 |
usal | -0.515 |
anches | -0.489 |
Token | bring |
Token ID | 2222 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
omial | +0.576 |
unden | +0.445 |
scorer | +0.425 |
usal | +0.423 |
acing | +0.401 |
Neg logit contributions | |
estern | -0.483 |
Sally | -0.480 |
roo | -0.457 |
tons | -0.450 |
puppies | -0.408 |
Token | big |
Token ID | 1263 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Sally | +2.225 |
estern | +2.201 |
roo | +2.087 |
tons | +2.072 |
puppies | +1.862 |
Neg logit contributions | |
omial | -2.991 |
unden | -2.319 |
usal | -2.245 |
scorer | -2.194 |
anches | -2.123 |
Token | man |
Token ID | 582 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
omial | +2.631 |
unden | +2.047 |
scorer | +2.016 |
usal | +1.979 |
acing | +1.873 |
Neg logit contributions | |
estern | -2.057 |
Sally | -1.973 |
roo | -1.891 |
tons | -1.847 |
puppies | -1.652 |
Token | - |
Token ID | 12 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
omial | +2.934 |
unden | +2.262 |
scorer | +2.208 |
usal | +2.182 |
anches | +2.060 |
Neg logit contributions | |
estern | -2.407 |
Sally | -2.339 |
roo | -2.239 |
tons | -2.195 |
puppies | -1.973 |
Token | bl |
Token ID | 2436 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
omial | +0.673 |
unden | +0.533 |
scorer | +0.518 |
usal | +0.510 |
anches | +0.485 |
Neg logit contributions | |
estern | -0.475 |
Sally | -0.460 |
roo | -0.444 |
tons | -0.432 |
TON | -0.383 |
Token | itz |
Token ID | 4224 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
omial | +11.355 |
usal | +8.427 |
acing | +8.089 |
scorer | +7.950 |
anches | +7.945 |
Neg logit contributions | |
estern | -11.450 |
Sally | -11.277 |
tons | -10.573 |
roo | -10.193 |
TON | -10.011 |
Token | es |
Token ID | 274 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
estern | +0.899 |
Sally | +0.877 |
roo | +0.845 |
tons | +0.825 |
puppies | +0.739 |
Neg logit contributions | |
omial | -1.233 |
unden | -0.975 |
scorer | -0.934 |
usal | -0.932 |
exha | -0.880 |
Token | to |
Token ID | 284 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
estern | +0.057 |
Sally | +0.056 |
roo | +0.053 |
tons | +0.052 |
puppies | +0.047 |
Neg logit contributions | |
omial | -0.072 |
unden | -0.056 |
scorer | -0.054 |
usal | -0.054 |
anches | -0.051 |
Token | accompany |
Token ID | 13873 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
omial | +0.482 |
unden | +0.378 |
scorer | +0.366 |
usal | +0.362 |
acing | +0.343 |
Neg logit contributions | |
estern | -0.359 |
Sally | -0.350 |
roo | -0.334 |
tons | -0.326 |
TON | -0.292 |
Token | Stri |
Token ID | 26137 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
estern | +0.631 |
Sally | +0.624 |
roo | +0.595 |
tons | +0.581 |
puppies | +0.523 |
Neg logit contributions | |
omial | -0.829 |
unden | -0.643 |
usal | -0.621 |
scorer | -0.616 |
acing | -0.586 |
Token | ro |
Token ID | 305 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
omial | +1.597 |
unden | +1.238 |
usal | +1.232 |
scorer | +1.214 |
acing | +1.159 |
Neg logit contributions | |
estern | -1.220 |
Sally | -1.173 |
tons | -1.091 |
roo | -1.088 |
puppies | -0.988 |
Token | ‑ |
Token ID | 20977 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
omial | +0.815 |
unden | +0.630 |
usal | +0.615 |
scorer | +0.611 |
acing | +0.579 |
Neg logit contributions | |
estern | -0.675 |
Sally | -0.653 |
roo | -0.629 |
tons | -0.608 |
enegger | -0.562 |
Token | Cub |
Token ID | 43632 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
estern | +0.243 |
Sally | +0.229 |
roo | +0.213 |
tons | +0.205 |
puppies | +0.175 |
Neg logit contributions | |
omial | -0.585 |
unden | -0.480 |
scorer | -0.474 |
usal | -0.473 |
acing | -0.453 |
Token | ans |
Token ID | 504 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
omial | +0.017 |
unden | +0.012 |
scorer | +0.012 |
usal | +0.012 |
acing | +0.011 |
Neg logit contributions | |
estern | -0.021 |
Sally | -0.020 |
roo | -0.020 |
tons | -0.019 |
puppies | -0.018 |
Token | ( |
Token ID | 357 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
omial | +0.758 |
unden | +0.595 |
scorer | +0.584 |
usal | +0.576 |
acing | +0.546 |
Neg logit contributions | |
estern | -0.546 |
Sally | -0.525 |
roo | -0.502 |
tons | -0.491 |
puppies | -0.436 |
Token | bl |
Token ID | 2436 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
estern | +1.177 |
Sally | +1.136 |
roo | +1.094 |
tons | +1.077 |
TON | +0.952 |
Neg logit contributions | |
omial | -1.611 |
unden | -1.269 |
scorer | -1.245 |
usal | -1.214 |
exha | -1.165 |
Token | acks |
Token ID | 4595 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
omial | +8.694 |
anches | +5.477 |
usal | +5.468 |
acing | +5.294 |
scorer | +5.285 |
Neg logit contributions | |
estern | -14.217 |
Sally | -14.108 |
roo | -13.316 |
tons | -13.273 |
Mechdragon | -12.781 |
Token | and |
Token ID | 290 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
omial | +3.908 |
unden | +3.045 |
scorer | +2.999 |
usal | +2.952 |
acing | +2.808 |
Neg logit contributions | |
estern | -2.935 |
Sally | -2.818 |
roo | -2.704 |
tons | -2.643 |
puppies | -2.353 |
Token | mul |
Token ID | 35971 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
omial | +0.796 |
unden | +0.620 |
scorer | +0.609 |
usal | +0.600 |
acing | +0.567 |
Neg logit contributions | |
estern | -0.606 |
Sally | -0.586 |
roo | -0.559 |
tons | -0.549 |
puppies | -0.490 |
Token | att |
Token ID | 1078 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
omial | +1.436 |
unden | +1.089 |
scorer | +1.066 |
usal | +1.051 |
acing | +0.988 |
Neg logit contributions | |
estern | -1.329 |
Sally | -1.282 |
roo | -1.236 |
tons | -1.207 |
puppies | -1.094 |
Token | os |
Token ID | 418 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
omial | +3.302 |
unden | +2.501 |
scorer | +2.452 |
usal | +2.449 |
acing | +2.314 |
Neg logit contributions | |
estern | -2.941 |
Sally | -2.823 |
roo | -2.697 |
tons | -2.648 |
enegger | -2.406 |
Token | was |
Token ID | 373 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
estern | +1.048 |
Sally | +1.019 |
roo | +0.978 |
tons | +0.956 |
puppies | +0.860 |
Neg logit contributions | |
omial | -1.272 |
unden | -0.994 |
scorer | -0.962 |
usal | -0.939 |
anches | -0.895 |
Token | incredible |
Token ID | 8082 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
omial | +0.100 |
unden | +0.078 |
scorer | +0.077 |
usal | +0.076 |
anches | +0.072 |
Neg logit contributions | |
estern | -0.074 |
Sally | -0.072 |
roo | -0.068 |
tons | -0.067 |
puppies | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
omial | +0.619 |
unden | +0.486 |
scorer | +0.478 |
usal | +0.471 |
anches | +0.447 |
Neg logit contributions | |
estern | -0.437 |
Sally | -0.421 |
roo | -0.401 |
tons | -0.392 |
puppies | -0.349 |
Token |
|
Token ID | 198 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
estern | +0.111 |
Sally | +0.109 |
roo | +0.103 |
tons | +0.100 |
TON | +0.089 |
Neg logit contributions | |
omial | -0.160 |
unden | -0.127 |
scorer | -0.124 |
usal | -0.122 |
anches | -0.116 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
omial | +0.095 |
unden | +0.078 |
scorer | +0.075 |
usal | +0.074 |
exha | +0.073 |
Neg logit contributions | |
estern | -0.058 |
Sally | -0.056 |
roo | -0.053 |
tons | -0.052 |
TON | -0.046 |
Token | Bl |
Token ID | 3629 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
omial | +0.155 |
unden | +0.122 |
scorer | +0.119 |
usal | +0.116 |
exha | +0.112 |
Neg logit contributions | |
estern | -0.112 |
Sally | -0.108 |
roo | -0.104 |
tons | -0.102 |
TON | -0.091 |
Token | acks |
Token ID | 4595 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
omial | +12.442 |
usal | +9.454 |
scorer | +9.197 |
anches | +9.175 |
unden | +9.100 |
Neg logit contributions | |
estern | -9.640 |
Sally | -9.623 |
tons | -8.933 |
roo | -8.885 |
enegger | -8.180 |
Token | in |
Token ID | 287 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
omial | +3.550 |
unden | +2.767 |
scorer | +2.717 |
usal | +2.677 |
acing | +2.533 |
Neg logit contributions | |
estern | -2.718 |
Sally | -2.615 |
roo | -2.504 |
tons | -2.449 |
puppies | -2.188 |
Token | Philly |
Token ID | 30029 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
estern | +0.547 |
Sally | +0.531 |
roo | +0.504 |
tons | +0.490 |
puppies | +0.439 |
Neg logit contributions | |
omial | -0.738 |
unden | -0.576 |
scorer | -0.564 |
usal | -0.557 |
anches | -0.527 |
Token | have |
Token ID | 423 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
estern | +0.167 |
Sally | +0.163 |
roo | +0.154 |
tons | +0.152 |
puppies | +0.136 |
Neg logit contributions | |
omial | -0.219 |
unden | -0.171 |
scorer | -0.167 |
usal | -0.165 |
anches | -0.156 |
Token | a |
Token ID | 257 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
estern | +0.803 |
Sally | +0.783 |
roo | +0.740 |
tons | +0.727 |
puppies | +0.655 |
Neg logit contributions | |
omial | -1.090 |
unden | -0.843 |
scorer | -0.829 |
usal | -0.820 |
anches | -0.782 |
Token | white |
Token ID | 2330 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
omial | +0.170 |
unden | +0.131 |
usal | +0.127 |
scorer | +0.126 |
anches | +0.120 |
Neg logit contributions | |
estern | -0.132 |
Sally | -0.129 |
roo | -0.122 |
tons | -0.119 |
puppies | -0.108 |
Token | SUV |
Token ID | 26763 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
estern | +0.271 |
Sally | +0.264 |
roo | +0.250 |
tons | +0.244 |
puppies | +0.220 |
Neg logit contributions | |
omial | -0.376 |
unden | -0.294 |
scorer | -0.286 |
usal | -0.284 |
anches | -0.271 |
Token | turn |
Token ID | 1210 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
omial | +0.162 |
unden | +0.124 |
scorer | +0.120 |
usal | +0.119 |
anches | +0.113 |
Neg logit contributions | |
estern | -0.135 |
Sally | -0.133 |
roo | -0.127 |
tons | -0.124 |
puppies | -0.112 |
Token | left |
Token ID | 1364 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
omial | +4.196 |
unden | +3.244 |
scorer | +3.187 |
usal | +3.134 |
acing | +2.960 |
Neg logit contributions | |
estern | -3.432 |
Sally | -3.302 |
roo | -3.170 |
tons | -3.103 |
puppies | -2.782 |
Token | from |
Token ID | 422 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
omial | +0.729 |
unden | +0.573 |
scorer | +0.557 |
usal | +0.551 |
anches | +0.520 |
Neg logit contributions | |
estern | -0.538 |
Sally | -0.520 |
roo | -0.495 |
tons | -0.485 |
puppies | -0.433 |
Token | Bl |
Token ID | 1086 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
omial | +1.224 |
unden | +0.964 |
scorer | +0.946 |
usal | +0.933 |
anches | +0.885 |
Neg logit contributions | |
estern | -0.862 |
Sally | -0.829 |
roo | -0.791 |
tons | -0.772 |
puppies | -0.686 |
Token | oor |
Token ID | 2675 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
omial | +10.652 |
usal | +7.429 |
scorer | +7.084 |
anches | +7.082 |
acing | +7.023 |
Neg logit contributions | |
estern | -12.040 |
Sally | -11.745 |
tons | -10.976 |
roo | -10.931 |
enegger | -10.612 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
omial | +1.842 |
unden | +1.410 |
scorer | +1.386 |
usal | +1.360 |
acing | +1.286 |
Neg logit contributions | |
estern | -1.618 |
Sally | -1.558 |
roo | -1.502 |
tons | -1.468 |
puppies | -1.325 |
Token | south |
Token ID | 5366 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
omial | +1.468 |
unden | +1.139 |
scorer | +1.108 |
usal | +1.100 |
anches | +1.041 |
Neg logit contributions | |
estern | -1.118 |
Sally | -1.093 |
roo | -1.037 |
tons | -1.016 |
TON | -0.911 |
Token | bound |
Token ID | 7784 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
omial | +5.744 |
unden | +4.294 |
scorer | +4.274 |
usal | +4.208 |
acing | +3.988 |
Neg logit contributions | |
estern | -5.598 |
Sally | -5.402 |
roo | -5.256 |
tons | -5.133 |
enegger | -4.659 |
Token | onto |
Token ID | 4291 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
omial | +3.203 |
unden | +2.502 |
scorer | +2.468 |
usal | +2.426 |
acing | +2.305 |
Neg logit contributions | |
estern | -2.407 |
Sally | -2.302 |
roo | -2.219 |
tons | -2.164 |
enegger | -1.927 |
Token | ations |
Token ID | 602 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
estern | +0.316 |
Sally | +0.303 |
roo | +0.292 |
tons | +0.287 |
TON | +0.252 |
Neg logit contributions | |
omial | -0.443 |
unden | -0.358 |
scorer | -0.346 |
usal | -0.334 |
exha | -0.326 |
Token | reflect |
Token ID | 4079 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
estern | +1.093 |
Sally | +1.083 |
roo | +1.015 |
tons | +1.013 |
puppies | +0.914 |
Neg logit contributions | |
omial | -1.368 |
unden | -1.088 |
scorer | -1.027 |
usal | -1.021 |
exha | -0.974 |
Token | the |
Token ID | 262 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
estern | +0.325 |
Sally | +0.317 |
roo | +0.298 |
tons | +0.296 |
puppies | +0.266 |
Neg logit contributions | |
omial | -0.421 |
unden | -0.324 |
scorer | -0.318 |
usal | -0.314 |
anches | -0.298 |
Token | avoiding |
Token ID | 14928 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
estern | +0.851 |
Sally | +0.830 |
roo | +0.780 |
tons | +0.778 |
puppies | +0.705 |
Neg logit contributions | |
omial | -0.988 |
unden | -0.747 |
scorer | -0.727 |
usal | -0.726 |
anches | -0.691 |
Token | - |
Token ID | 12 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
estern | +0.469 |
Sally | +0.454 |
roo | +0.435 |
tons | +0.430 |
puppies | +0.390 |
Neg logit contributions | |
omial | -0.487 |
unden | -0.367 |
scorer | -0.358 |
usal | -0.353 |
anches | -0.333 |
Token | bl |
Token ID | 2436 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
omial | +0.423 |
unden | +0.325 |
scorer | +0.317 |
usal | +0.310 |
anches | +0.293 |
Neg logit contributions | |
estern | -0.372 |
Sally | -0.360 |
roo | -0.347 |
tons | -0.341 |
TON | -0.306 |
Token | ame |
Token ID | 480 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
omial | +11.860 |
usal | +8.939 |
acing | +8.544 |
anches | +8.500 |
scorer | +8.462 |
Neg logit contributions | |
estern | -10.457 |
Sally | -10.240 |
roo | -9.472 |
tons | -9.451 |
puppies | -8.921 |
Token | � |
Token ID | 564 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
omial | +3.333 |
unden | +2.604 |
scorer | +2.571 |
usal | +2.532 |
acing | +2.394 |
Neg logit contributions | |
estern | -2.469 |
Sally | -2.366 |
roo | -2.266 |
tons | -2.204 |
puppies | -1.966 |
Token | � |
Token ID | 250 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
omial | +0.423 |
unden | +0.328 |
scorer | +0.318 |
usal | +0.310 |
anches | +0.295 |
Neg logit contributions | |
estern | -0.370 |
Sally | -0.360 |
roo | -0.351 |
tons | -0.341 |
puppies | -0.307 |
Token | yes |
Token ID | 8505 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
omial | +1.801 |
unden | +1.384 |
scorer | +1.357 |
usal | +1.335 |
acing | +1.258 |
Neg logit contributions | |
estern | -1.535 |
Sally | -1.481 |
roo | -1.422 |
tons | -1.393 |
puppies | -1.253 |
Token | - |
Token ID | 12 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
omial | +0.915 |
unden | +0.703 |
scorer | +0.693 |
usal | +0.684 |
acing | +0.642 |
Neg logit contributions | |
estern | -0.758 |
Sally | -0.731 |
roo | -0.701 |
tons | -0.683 |
enegger | -0.616 |
Token | peanut |
Token ID | 26636 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
omial | +0.119 |
unden | +0.091 |
scorer | +0.089 |
usal | +0.089 |
anches | +0.085 |
Neg logit contributions | |
estern | -0.093 |
Sally | -0.092 |
roo | -0.086 |
tons | -0.084 |
puppies | -0.076 |
Token | butter |
Token ID | 9215 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
estern | +2.027 |
Sally | +1.987 |
roo | +1.888 |
tons | +1.834 |
TON | +1.645 |
Neg logit contributions | |
omial | -2.719 |
unden | -2.124 |
usal | -2.067 |
scorer | -2.066 |
anches | -1.968 |
Token | : |
Token ID | 25 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
estern | +2.863 |
Sally | +2.827 |
roo | +2.659 |
tons | +2.569 |
puppies | +2.318 |
Neg logit contributions | |
omial | -4.166 |
unden | -3.301 |
scorer | -3.234 |
usal | -3.230 |
anches | -3.071 |
Token |
|
Token ID | 198 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
estern | +0.567 |
Sally | +0.534 |
roo | +0.518 |
tons | +0.508 |
enegger | +0.455 |
Neg logit contributions | |
omial | -0.783 |
unden | -0.616 |
scorer | -0.603 |
usal | -0.595 |
acing | -0.566 |
Token |
|
Token ID | 198 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
omial | +0.400 |
unden | +0.330 |
scorer | +0.315 |
usal | +0.310 |
exha | +0.305 |
Neg logit contributions | |
estern | -0.242 |
Sally | -0.235 |
roo | -0.224 |
tons | -0.219 |
TON | -0.191 |
Token | Bl |
Token ID | 3629 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
omial | +0.371 |
unden | +0.295 |
scorer | +0.288 |
usal | +0.282 |
exha | +0.272 |
Neg logit contributions | |
estern | -0.258 |
Sally | -0.250 |
roo | -0.242 |
tons | -0.235 |
TON | -0.211 |
Token | end |
Token ID | 437 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
omial | +9.559 |
usal | +6.724 |
scorer | +6.497 |
anches | +6.417 |
acing | +6.250 |
Neg logit contributions | |
estern | -12.246 |
Sally | -12.136 |
tons | -11.489 |
roo | -11.415 |
puppies | -10.866 |
Token | , |
Token ID | 11 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
omial | +2.053 |
unden | +1.611 |
scorer | +1.582 |
usal | +1.560 |
acing | +1.478 |
Neg logit contributions | |
estern | -1.484 |
Sally | -1.430 |
roo | -1.366 |
tons | -1.334 |
puppies | -1.188 |
Token | adding |
Token ID | 4375 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
omial | +0.317 |
unden | +0.246 |
usal | +0.241 |
scorer | +0.241 |
anches | +0.228 |
Neg logit contributions | |
estern | -0.227 |
Sally | -0.224 |
roo | -0.211 |
tons | -0.206 |
puppies | -0.184 |
Token | more |
Token ID | 517 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
estern | +0.359 |
Sally | +0.356 |
roo | +0.332 |
tons | +0.330 |
puppies | +0.294 |
Neg logit contributions | |
omial | -0.498 |
unden | -0.385 |
scorer | -0.378 |
usal | -0.377 |
anches | -0.360 |
Token | almond |
Token ID | 26948 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
estern | +0.192 |
Sally | +0.192 |
roo | +0.179 |
tons | +0.178 |
puppies | +0.159 |
Neg logit contributions | |
omial | -0.253 |
unden | -0.196 |
usal | -0.191 |
scorer | -0.191 |
anches | -0.181 |
Token | v |
Token ID | 85 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
estern | +2.071 |
Sally | +1.951 |
roo | +1.937 |
tons | +1.926 |
hire | +1.661 |
Neg logit contributions | |
omial | -3.198 |
unden | -2.815 |
exha | -2.640 |
scorer | -2.584 |
usal | -2.456 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
estern | +0.732 |
Sally | +0.710 |
roo | +0.697 |
tons | +0.682 |
TON | +0.615 |
Neg logit contributions | |
omial | -0.811 |
unden | -0.680 |
scorer | -0.622 |
exha | -0.621 |
usal | -0.589 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
estern | +0.839 |
Sally | +0.821 |
roo | +0.794 |
tons | +0.782 |
TON | +0.685 |
Neg logit contributions | |
omial | -1.254 |
unden | -1.070 |
exha | -0.995 |
scorer | -0.988 |
usal | -0.958 |
Token | Ga |
Token ID | 35389 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
omial | +1.615 |
unden | +1.261 |
scorer | +1.238 |
usal | +1.217 |
acing | +1.152 |
Neg logit contributions | |
estern | -1.233 |
Sally | -1.187 |
roo | -1.138 |
tons | -1.113 |
puppies | -0.992 |
Token | ussian |
Token ID | 31562 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
omial | +3.024 |
unden | +2.238 |
scorer | +2.180 |
usal | +2.125 |
acing | +1.985 |
Neg logit contributions | |
estern | -3.414 |
Sally | -3.310 |
roo | -3.206 |
tons | -3.139 |
TON | -2.870 |
Token | Bl |
Token ID | 3629 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
estern | +0.350 |
Sally | +0.339 |
roo | +0.327 |
tons | +0.317 |
TON | +0.287 |
Neg logit contributions | |
omial | -0.422 |
unden | -0.330 |
scorer | -0.321 |
usal | -0.317 |
acing | -0.299 |
Token | ur |
Token ID | 333 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
omial | +10.140 |
usal | +7.002 |
scorer | +6.866 |
anches | +6.668 |
acing | +6.656 |
Neg logit contributions | |
estern | -12.156 |
Sally | -11.763 |
tons | -11.025 |
roo | -10.964 |
puppies | -10.460 |
Token | ( |
Token ID | 7 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
omial | +2.374 |
unden | +1.776 |
scorer | +1.755 |
usal | +1.723 |
acing | +1.630 |
Neg logit contributions | |
estern | -2.183 |
Sally | -2.096 |
roo | -2.002 |
tons | -1.976 |
puppies | -1.791 |
Token | gray |
Token ID | 44605 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
estern | +0.261 |
Sally | +0.252 |
roo | +0.242 |
tons | +0.237 |
TON | +0.211 |
Neg logit contributions | |
omial | -0.344 |
unden | -0.269 |
scorer | -0.263 |
usal | -0.259 |
anches | -0.245 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
estern | +0.102 |
Sally | +0.098 |
roo | +0.094 |
tons | +0.092 |
puppies | +0.082 |
Neg logit contributions | |
omial | -0.132 |
unden | -0.102 |
scorer | -0.101 |
usal | -0.099 |
acing | -0.094 |
Token | ( |
Token ID | 357 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
omial | +1.480 |
unden | +1.147 |
scorer | +1.123 |
usal | +1.107 |
anches | +1.045 |
Neg logit contributions | |
estern | -1.182 |
Sally | -1.144 |
roo | -1.095 |
tons | -1.071 |
puppies | -0.962 |
Token | lighter |
Token ID | 14871 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
omial | +0.443 |
unden | +0.340 |
scorer | +0.332 |
usal | +0.330 |
anches | +0.315 |
Neg logit contributions | |
estern | -0.341 |
Sally | -0.335 |
roo | -0.316 |
tons | -0.312 |
puppies | -0.282 |
Token | than |
Token ID | 621 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
estern | +2.474 |
Sally | +2.415 |
roo | +2.287 |
tons | +2.271 |
puppies | +2.022 |
Neg logit contributions | |
omial | -3.555 |
unden | -2.788 |
scorer | -2.728 |
usal | -2.710 |
anches | -2.598 |
Token | ambient |
Token ID | 25237 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
omial | +0.645 |
unden | +0.496 |
scorer | +0.487 |
usal | +0.481 |
anches | +0.456 |
Neg logit contributions | |
estern | -0.510 |
Sally | -0.497 |
roo | -0.474 |
tons | -0.466 |
puppies | -0.418 |
Token | . |
Token ID | 13 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
omial | +1.435 |
unden | +1.116 |
scorer | +1.096 |
usal | +1.080 |
anches | +1.021 |
Neg logit contributions | |
estern | -1.112 |
Sally | -1.072 |
roo | -1.027 |
tons | -1.005 |
puppies | -0.899 |
Token | The |
Token ID | 383 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
omial | +0.729 |
unden | +0.580 |
scorer | +0.568 |
usal | +0.559 |
exha | +0.532 |
Neg logit contributions | |
estern | -0.486 |
Sally | -0.478 |
roo | -0.451 |
tons | -0.441 |
TON | -0.389 |
Token | bl |
Token ID | 698 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
omial | +0.149 |
unden | +0.116 |
scorer | +0.113 |
usal | +0.112 |
anches | +0.106 |
Neg logit contributions | |
estern | -0.117 |
Sally | -0.114 |
roo | -0.109 |
tons | -0.107 |
puppies | -0.097 |
Token | uish |
Token ID | 32091 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
omial | +9.644 |
usal | +6.856 |
anches | +6.551 |
scorer | +6.551 |
acing | +6.530 |
Neg logit contributions | |
estern | -11.931 |
Sally | -11.797 |
roo | -11.127 |
tons | -11.025 |
Mechdragon | -10.639 |
Token | v |
Token ID | 410 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
estern | +0.966 |
Sally | +0.929 |
roo | +0.888 |
tons | +0.868 |
puppies | +0.771 |
Neg logit contributions | |
omial | -1.352 |
unden | -1.063 |
scorer | -1.044 |
usal | -1.029 |
anches | -0.976 |
Token | ort |
Token ID | 419 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
estern | +2.420 |
roo | +2.207 |
Sally | +2.178 |
tons | +2.148 |
hire | +1.828 |
Neg logit contributions | |
omial | -4.915 |
unden | -4.439 |
exha | -4.139 |
scorer | -4.017 |
usal | -3.882 |
Token | on |
Token ID | 261 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
estern | +1.216 |
Sally | +1.153 |
roo | +1.133 |
tons | +1.109 |
TON | +0.944 |
Neg logit contributions | |
omial | -2.198 |
unden | -1.883 |
scorer | -1.770 |
exha | -1.750 |
usal | -1.731 |
Token | has |
Token ID | 468 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
omial | +0.688 |
unden | +0.531 |
scorer | +0.519 |
usal | +0.512 |
anches | +0.482 |
Neg logit contributions | |
estern | -0.567 |
Sally | -0.551 |
roo | -0.527 |
tons | -0.518 |
puppies | -0.465 |
Token | (/ |
Token ID | 50247 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
omial | +0.741 |
unden | +0.574 |
scorer | +0.559 |
usal | +0.550 |
anches | +0.521 |
Neg logit contributions | |
estern | -0.620 |
Sally | -0.604 |
roo | -0.578 |
tons | -0.568 |
puppies | -0.508 |
Token | dev |
Token ID | 7959 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
omial | +3.759 |
unden | +2.884 |
scorer | +2.836 |
usal | +2.802 |
acing | +2.638 |
Neg logit contributions | |
estern | -3.210 |
Sally | -3.086 |
roo | -2.953 |
tons | -2.884 |
puppies | -2.612 |
Token | / |
Token ID | 14 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
omial | +2.777 |
unden | +1.998 |
scorer | +1.983 |
usal | +1.949 |
anches | +1.818 |
Neg logit contributions | |
estern | -3.213 |
Sally | -3.124 |
roo | -2.993 |
tons | -2.950 |
puppies | -2.717 |
Token | mm |
Token ID | 3020 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
omial | +1.169 |
unden | +0.898 |
scorer | +0.879 |
usal | +0.864 |
anches | +0.812 |
Neg logit contributions | |
estern | -1.026 |
Sally | -0.990 |
roo | -0.954 |
tons | -0.937 |
puppies | -0.841 |
Token | c |
Token ID | 66 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
estern | +0.769 |
Sally | +0.759 |
roo | +0.739 |
tons | +0.735 |
puppies | +0.650 |
Neg logit contributions | |
omial | -0.822 |
unden | -0.639 |
usal | -0.601 |
scorer | -0.599 |
anches | -0.560 |
Token | bl |
Token ID | 2436 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
estern | +0.645 |
Sally | +0.627 |
roo | +0.601 |
tons | +0.589 |
puppies | +0.524 |
Neg logit contributions | |
omial | -0.872 |
unden | -0.687 |
scorer | -0.667 |
usal | -0.657 |
acing | -0.623 |
Token | k |
Token ID | 74 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
omial | +10.453 |
scorer | +7.820 |
usal | +7.690 |
unden | +7.641 |
acing | +7.164 |
Neg logit contributions | |
estern | -11.427 |
Sally | -10.634 |
roo | -10.056 |
tons | -9.689 |
Mechdragon | -9.291 |
Token | 0 |
Token ID | 15 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
estern | +0.656 |
Sally | +0.641 |
roo | +0.627 |
tons | +0.610 |
puppies | +0.549 |
Neg logit contributions | |
omial | -0.784 |
unden | -0.606 |
scorer | -0.583 |
usal | -0.577 |
acing | -0.549 |
Token | p |
Token ID | 79 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
omial | +1.291 |
unden | +0.984 |
scorer | +0.961 |
usal | +0.945 |
anches | +0.889 |
Neg logit contributions | |
estern | -1.176 |
Sally | -1.137 |
roo | -1.097 |
tons | -1.073 |
puppies | -0.970 |
Token | 25 |
Token ID | 1495 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
omial | +0.447 |
unden | +0.343 |
scorer | +0.331 |
usal | +0.326 |
anches | +0.308 |
Neg logit contributions | |
estern | -0.398 |
Sally | -0.386 |
roo | -0.377 |
tons | -0.369 |
puppies | -0.330 |
Token | - |
Token ID | 532 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
omial | +1.374 |
unden | +1.049 |
scorer | +1.022 |
usal | +1.005 |
anches | +0.945 |
Neg logit contributions | |
estern | -1.256 |
Sally | -1.216 |
roo | -1.174 |
tons | -1.149 |
puppies | -1.038 |
Token | E |
Token ID | 412 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
omial | +2.388 |
unden | +1.876 |
scorer | +1.843 |
usal | +1.818 |
acing | +1.723 |
Neg logit contributions | |
estern | -1.704 |
Sally | -1.637 |
roo | -1.565 |
tons | -1.529 |
puppies | -1.358 |
Token | , |
Token ID | 11 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
estern | +2.913 |
Sally | +2.808 |
roo | +2.661 |
tons | +2.603 |
TON | +2.296 |
Neg logit contributions | |
omial | -4.312 |
unden | -3.403 |
scorer | -3.349 |
usal | -3.298 |
anches | -3.127 |
Token | Miller |
Token ID | 7920 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
omial | +0.304 |
unden | +0.241 |
scorer | +0.236 |
usal | +0.233 |
acing | +0.221 |
Neg logit contributions | |
estern | -0.209 |
Sally | -0.201 |
roo | -0.191 |
tons | -0.187 |
puppies | -0.165 |
Token | TR |
Token ID | 7579 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
Sally | +2.456 |
estern | +2.446 |
roo | +2.311 |
tons | +2.273 |
TON | +2.012 |
Neg logit contributions | |
omial | -3.762 |
unden | -3.048 |
scorer | -2.907 |
usal | -2.865 |
exha | -2.803 |
Token | , |
Token ID | 11 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
omial | +4.062 |
unden | +3.156 |
scorer | +3.082 |
usal | +3.030 |
acing | +2.958 |
Neg logit contributions | |
estern | -3.370 |
Sally | -3.178 |
roo | -3.113 |
tons | -3.063 |
puppies | -2.750 |
Token | Bl |
Token ID | 1086 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
omial | +0.263 |
unden | +0.208 |
scorer | +0.204 |
usal | +0.201 |
acing | +0.191 |
Neg logit contributions | |
estern | -0.181 |
Sally | -0.175 |
roo | -0.166 |
tons | -0.162 |
puppies | -0.144 |
Token | in |
Token ID | 259 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
omial | +11.268 |
usal | +8.401 |
umer | +7.983 |
anches | +7.937 |
scorer | +7.923 |
Neg logit contributions | |
Sally | -10.114 |
estern | -10.051 |
tons | -9.378 |
roo | -9.358 |
puppies | -8.855 |
Token | coe |
Token ID | 49270 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
omial | +1.447 |
unden | +1.132 |
scorer | +1.112 |
usal | +1.090 |
anches | +1.034 |
Neg logit contributions | |
estern | -1.122 |
Sally | -1.083 |
roo | -1.038 |
tons | -1.014 |
TON | -0.904 |
Token | L |
Token ID | 406 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
omial | +0.574 |
unden | +0.451 |
scorer | +0.439 |
usal | +0.433 |
exha | +0.410 |
Neg logit contributions | |
estern | -0.429 |
Sally | -0.419 |
roo | -0.399 |
tons | -0.391 |
TON | -0.349 |
Token | J |
Token ID | 41 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
estern | +0.186 |
Sally | +0.179 |
roo | +0.171 |
tons | +0.168 |
puppies | +0.149 |
Neg logit contributions | |
omial | -0.246 |
unden | -0.193 |
scorer | -0.190 |
usal | -0.185 |
acing | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
omial | +0.190 |
unden | +0.150 |
scorer | +0.146 |
usal | +0.143 |
acing | +0.138 |
Neg logit contributions | |
estern | -0.144 |
Sally | -0.138 |
roo | -0.133 |
tons | -0.130 |
puppies | -0.115 |
Token | day |
Token ID | 1110 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
estern | +0.721 |
Sally | +0.694 |
roo | +0.661 |
tons | +0.643 |
puppies | +0.569 |
Neg logit contributions | |
omial | -1.091 |
unden | -0.865 |
scorer | -0.848 |
usal | -0.838 |
anches | -0.797 |
Token | , |
Token ID | 11 |
Feature activation | +2.90e-03 |
Pos logit contributions | |
estern | +2.556 |
Sally | +2.492 |
roo | +2.339 |
tons | +2.289 |
puppies | +2.028 |
Neg logit contributions | |
omial | -4.074 |
unden | -3.238 |
scorer | -3.152 |
usal | -3.132 |
anches | -2.964 |
Token | the |
Token ID | 262 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
estern | +0.002 |
Sally | +0.002 |
roo | +0.002 |
tons | +0.002 |
puppies | +0.002 |
Neg logit contributions | |
omial | -0.003 |
unden | -0.003 |
scorer | -0.003 |
usal | -0.002 |
anches | -0.002 |
Token | intersection |
Token ID | 16246 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
estern | +0.336 |
Sally | +0.329 |
roo | +0.310 |
tons | +0.304 |
puppies | +0.276 |
Neg logit contributions | |
omial | -0.450 |
unden | -0.350 |
scorer | -0.338 |
usal | -0.337 |
anches | -0.319 |
Token | of |
Token ID | 286 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
omial | +0.458 |
unden | +0.340 |
scorer | +0.333 |
usal | +0.327 |
acing | +0.305 |
Neg logit contributions | |
estern | -0.485 |
Sally | -0.469 |
roo | -0.453 |
tons | -0.444 |
puppies | -0.405 |
Token | Bl |
Token ID | 1086 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
omial | +0.349 |
unden | +0.274 |
scorer | +0.268 |
usal | +0.264 |
anches | +0.250 |
Neg logit contributions | |
estern | -0.257 |
Sally | -0.249 |
roo | -0.237 |
tons | -0.232 |
puppies | -0.206 |
Token | oor |
Token ID | 2675 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
omial | +11.300 |
usal | +8.338 |
anches | +8.043 |
scorer | +7.997 |
acing | +7.889 |
Neg logit contributions | |
estern | -9.960 |
Sally | -9.880 |
tons | -9.301 |
roo | -9.275 |
enegger | -8.649 |
Token | St |
Token ID | 520 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
omial | +1.128 |
unden | +0.872 |
scorer | +0.856 |
usal | +0.842 |
acing | +0.797 |
Neg logit contributions | |
estern | -0.920 |
Sally | -0.885 |
roo | -0.850 |
tons | -0.831 |
puppies | -0.747 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
estern | +0.440 |
Sally | +0.423 |
roo | +0.406 |
tons | +0.397 |
puppies | +0.357 |
Neg logit contributions | |
omial | -0.548 |
unden | -0.424 |
scorer | -0.417 |
usal | -0.411 |
acing | -0.389 |
Token | W |
Token ID | 370 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
omial | +1.335 |
unden | +1.044 |
scorer | +1.023 |
usal | +1.009 |
anches | +0.955 |
Neg logit contributions | |
estern | -1.000 |
Sally | -0.966 |
roo | -0.922 |
tons | -0.901 |
puppies | -0.804 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
estern | +1.058 |
Sally | +1.022 |
roo | +0.976 |
tons | +0.956 |
TON | +0.853 |
Neg logit contributions | |
omial | -1.443 |
unden | -1.132 |
scorer | -1.108 |
usal | -1.089 |
anches | -1.034 |
Token | v |
Token ID | 85 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
estern | +2.208 |
Sally | +2.097 |
roo | +2.068 |
tons | +2.061 |
hire | +1.775 |
Neg logit contributions | |
omial | -3.434 |
unden | -3.025 |
exha | -2.824 |
scorer | -2.749 |
usal | -2.634 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
estern | +0.807 |
Sally | +0.786 |
roo | +0.767 |
tons | +0.752 |
TON | +0.682 |
Neg logit contributions | |
omial | -0.897 |
unden | -0.749 |
scorer | -0.684 |
exha | -0.683 |
usal | -0.651 |
Token | . |
Token ID | 764 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
estern | +0.744 |
Sally | +0.735 |
roo | +0.697 |
tons | +0.681 |
TON | +0.589 |
Neg logit contributions | |
omial | -1.412 |
unden | -1.213 |
scorer | -1.129 |
exha | -1.127 |
usal | -1.108 |
Token | Ga |
Token ID | 12822 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
omial | +0.598 |
unden | +0.467 |
scorer | +0.458 |
usal | +0.450 |
anches | +0.427 |
Neg logit contributions | |
estern | -0.462 |
Sally | -0.448 |
roo | -0.428 |
tons | -0.418 |
puppies | -0.374 |
Token | ussian |
Token ID | 31562 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
omial | +2.203 |
unden | +1.648 |
scorer | +1.596 |
usal | +1.547 |
exha | +1.453 |
Neg logit contributions | |
estern | -2.470 |
Sally | -2.393 |
roo | -2.318 |
tons | -2.273 |
TON | -2.070 |
Token | Bl |
Token ID | 3629 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
estern | +0.433 |
Sally | +0.421 |
roo | +0.413 |
tons | +0.394 |
TON | +0.360 |
Neg logit contributions | |
omial | -0.586 |
unden | -0.483 |
scorer | -0.454 |
usal | -0.448 |
exha | -0.440 |
Token | ur |
Token ID | 333 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
omial | +8.471 |
usal | +5.587 |
scorer | +5.190 |
acing | +5.078 |
anches | +5.075 |
Neg logit contributions | |
estern | -13.164 |
Sally | -12.941 |
tons | -12.078 |
roo | -11.989 |
puppies | -11.672 |
Token | ( |
Token ID | 357 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
omial | +2.400 |
unden | +1.916 |
scorer | +1.849 |
usal | +1.827 |
exha | +1.740 |
Neg logit contributions | |
estern | -1.770 |
Sally | -1.715 |
roo | -1.642 |
tons | -1.604 |
TON | -1.432 |
Token | gray |
Token ID | 12768 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
estern | +0.373 |
Sally | +0.365 |
roo | +0.347 |
tons | +0.340 |
puppies | +0.303 |
Neg logit contributions | |
omial | -0.593 |
unden | -0.484 |
scorer | -0.460 |
usal | -0.456 |
exha | -0.438 |
Token | , |
Token ID | 837 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
estern | +1.175 |
Sally | +1.139 |
roo | +1.090 |
tons | +1.075 |
TON | +0.921 |
Neg logit contributions | |
omial | -2.110 |
unden | -1.795 |
scorer | -1.677 |
exha | -1.663 |
usal | -1.660 |
Token | ( |
Token ID | 357 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
omial | +0.833 |
unden | +0.673 |
scorer | +0.639 |
usal | +0.638 |
exha | +0.613 |
Neg logit contributions | |
estern | -0.583 |
Sally | -0.573 |
roo | -0.540 |
tons | -0.528 |
puppies | -0.473 |
Token | : |
Token ID | 25 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
omial | +0.810 |
unden | +0.640 |
scorer | +0.626 |
usal | +0.618 |
anches | +0.587 |
Neg logit contributions | |
estern | -0.565 |
Sally | -0.549 |
roo | -0.520 |
tons | -0.507 |
puppies | -0.454 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
omial | +1.167 |
unden | +0.909 |
scorer | +0.891 |
usal | +0.881 |
acing | +0.843 |
Neg logit contributions | |
estern | -0.890 |
Sally | -0.840 |
roo | -0.816 |
tons | -0.801 |
enegger | -0.711 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
omial | +1.256 |
unden | +1.013 |
scorer | +0.983 |
usal | +0.969 |
exha | +0.928 |
Neg logit contributions | |
estern | -0.798 |
Sally | -0.768 |
roo | -0.732 |
tons | -0.715 |
TON | -0.627 |
Token | Ga |
Token ID | 35389 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
omial | +1.184 |
unden | +0.938 |
scorer | +0.914 |
usal | +0.892 |
exha | +0.855 |
Neg logit contributions | |
estern | -0.866 |
Sally | -0.831 |
roo | -0.809 |
tons | -0.793 |
TON | -0.704 |
Token | ussian |
Token ID | 31562 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
omial | +3.010 |
unden | +2.174 |
scorer | +2.126 |
usal | +2.110 |
acing | +1.940 |
Neg logit contributions | |
estern | -3.565 |
Sally | -3.454 |
roo | -3.330 |
tons | -3.291 |
puppies | -3.007 |
Token | bl |
Token ID | 698 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
estern | +0.314 |
Sally | +0.305 |
roo | +0.292 |
tons | +0.284 |
puppies | +0.256 |
Neg logit contributions | |
omial | -0.403 |
unden | -0.315 |
scorer | -0.307 |
usal | -0.304 |
anches | -0.287 |
Token | urring |
Token ID | 14924 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
omial | +10.223 |
usal | +7.443 |
scorer | +7.226 |
acing | +7.181 |
anches | +7.137 |
Neg logit contributions | |
estern | -10.900 |
Sally | -10.727 |
tons | -10.068 |
roo | -10.046 |
TON | -9.480 |
Token | is |
Token ID | 318 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
omial | +3.963 |
unden | +3.051 |
scorer | +3.015 |
usal | +2.959 |
acing | +2.799 |
Neg logit contributions | |
estern | -3.256 |
Sally | -3.098 |
roo | -2.974 |
tons | -2.914 |
TON | -2.617 |
Token | applied |
Token ID | 5625 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
omial | +0.585 |
unden | +0.453 |
scorer | +0.444 |
usal | +0.438 |
anches | +0.417 |
Neg logit contributions | |
estern | -0.456 |
Sally | -0.444 |
roo | -0.423 |
tons | -0.416 |
puppies | -0.371 |
Token | on |
Token ID | 319 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
omial | +1.267 |
unden | +0.984 |
scorer | +0.959 |
usal | +0.946 |
anches | +0.895 |
Neg logit contributions | |
estern | -1.028 |
Sally | -0.996 |
roo | -0.953 |
tons | -0.932 |
puppies | -0.838 |
Token | Line |
Token ID | 6910 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
omial | +0.987 |
unden | +0.772 |
scorer | +0.756 |
usal | +0.745 |
anches | +0.706 |
Neg logit contributions | |
estern | -0.728 |
Sally | -0.705 |
roo | -0.671 |
tons | -0.660 |
puppies | -0.589 |
Token | them |
Token ID | 606 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
omial | +0.636 |
unden | +0.492 |
scorer | +0.477 |
usal | +0.474 |
anches | +0.449 |
Neg logit contributions | |
estern | -0.505 |
Sally | -0.493 |
roo | -0.472 |
tons | -0.465 |
puppies | -0.420 |
Token | full |
Token ID | 1336 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
estern | +1.354 |
Sally | +1.350 |
roo | +1.282 |
tons | +1.252 |
puppies | +1.156 |
Neg logit contributions | |
omial | -1.717 |
unden | -1.316 |
scorer | -1.280 |
usal | -1.277 |
anches | -1.215 |
Token | , |
Token ID | 11 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
omial | +1.227 |
unden | +0.961 |
scorer | +0.940 |
usal | +0.924 |
anches | +0.882 |
Neg logit contributions | |
estern | -0.894 |
Sally | -0.867 |
roo | -0.825 |
tons | -0.815 |
puppies | -0.726 |
Token | causing |
Token ID | 6666 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
omial | +0.223 |
unden | +0.174 |
scorer | +0.170 |
usal | +0.169 |
anches | +0.162 |
Neg logit contributions | |
estern | -0.151 |
Sally | -0.149 |
roo | -0.141 |
tons | -0.138 |
puppies | -0.124 |
Token | buffer |
Token ID | 11876 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
omial | +3.472 |
unden | +2.661 |
scorer | +2.614 |
usal | +2.566 |
acing | +2.419 |
Neg logit contributions | |
estern | -3.049 |
Sally | -2.935 |
roo | -2.821 |
tons | -2.754 |
enegger | -2.483 |
Token | bl |
Token ID | 2436 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
estern | +0.320 |
Sally | +0.313 |
roo | +0.300 |
tons | +0.298 |
puppies | +0.273 |
Neg logit contributions | |
omial | -0.297 |
unden | -0.221 |
scorer | -0.212 |
usal | -0.208 |
anches | -0.196 |
Token | oat |
Token ID | 15073 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
omial | +8.006 |
usal | +5.257 |
scorer | +5.090 |
acing | +4.977 |
anches | +4.797 |
Neg logit contributions | |
estern | -13.275 |
Sally | -12.834 |
tons | -12.060 |
roo | -11.994 |
Mechdragon | -11.750 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
estern | +0.009 |
Sally | +0.009 |
roo | +0.008 |
tons | +0.008 |
puppies | +0.007 |
Neg logit contributions | |
omial | -0.013 |
unden | -0.010 |
scorer | -0.010 |
usal | -0.010 |
anches | -0.009 |
Token | When |
Token ID | 1649 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
omial | +0.260 |
unden | +0.207 |
scorer | +0.201 |
usal | +0.199 |
exha | +0.190 |
Neg logit contributions | |
estern | -0.181 |
Sally | -0.178 |
roo | -0.169 |
tons | -0.166 |
TON | -0.147 |
Token | bottleneck |
Token ID | 49936 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
estern | +0.064 |
Sally | +0.062 |
roo | +0.060 |
tons | +0.059 |
puppies | +0.053 |
Neg logit contributions | |
omial | -0.075 |
unden | -0.057 |
scorer | -0.055 |
usal | -0.055 |
anches | -0.052 |
Token | buffers |
Token ID | 39334 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
estern | +0.515 |
Sally | +0.501 |
roo | +0.485 |
tons | +0.479 |
puppies | +0.443 |
Neg logit contributions | |
omial | -0.373 |
unden | -0.262 |
scorer | -0.253 |
usal | -0.249 |
anches | -0.228 |
Token | Heath |
Token ID | 25846 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
omial | +4.772 |
unden | +3.713 |
scorer | +3.670 |
usal | +3.650 |
acing | +3.471 |
Neg logit contributions | |
estern | -3.275 |
Sally | -3.092 |
roo | -2.982 |
tons | -2.905 |
enegger | -2.643 |
Token |
|
Token ID | 198 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
omial | +0.811 |
unden | +0.632 |
scorer | +0.620 |
usal | +0.611 |
acing | +0.578 |
Neg logit contributions | |
estern | -0.624 |
Sally | -0.600 |
roo | -0.574 |
tons | -0.562 |
puppies | -0.502 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
estern | +0.129 |
Sally | +0.126 |
roo | +0.119 |
tons | +0.117 |
TON | +0.102 |
Neg logit contributions | |
omial | -0.213 |
unden | -0.176 |
scorer | -0.168 |
usal | -0.165 |
exha | -0.163 |
Token | M |
Token ID | 44 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
omial | +0.109 |
unden | +0.085 |
scorer | +0.084 |
usal | +0.082 |
acing | +0.078 |
Neg logit contributions | |
estern | -0.084 |
Sally | -0.081 |
roo | -0.077 |
tons | -0.076 |
TON | -0.068 |
Token | ire |
Token ID | 557 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
estern | +0.982 |
Sally | +0.938 |
roo | +0.911 |
tons | +0.885 |
TON | +0.797 |
Neg logit contributions | |
omial | -1.134 |
unden | -0.881 |
scorer | -0.860 |
usal | -0.834 |
exha | -0.795 |
Token | Bl |
Token ID | 1086 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
estern | +1.113 |
Sally | +1.086 |
roo | +1.037 |
tons | +1.009 |
puppies | +0.899 |
Neg logit contributions | |
omial | -1.432 |
unden | -1.129 |
scorer | -1.099 |
usal | -1.070 |
exha | -1.010 |
Token | ight |
Token ID | 432 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
omial | +9.628 |
usal | +6.821 |
anches | +6.475 |
acing | +6.428 |
scorer | +6.377 |
Neg logit contributions | |
estern | -11.032 |
Sally | -11.005 |
roo | -10.384 |
tons | -10.291 |
TON | -9.875 |
Token | vs |
Token ID | 3691 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
omial | +1.627 |
unden | +1.195 |
scorer | +1.187 |
usal | +1.170 |
acing | +1.108 |
Neg logit contributions | |
estern | -1.628 |
Sally | -1.568 |
roo | -1.509 |
tons | -1.496 |
TON | -1.370 |
Token | Dark |
Token ID | 3801 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
estern | +0.560 |
Sally | +0.541 |
roo | +0.515 |
tons | +0.503 |
puppies | +0.447 |
Neg logit contributions | |
omial | -0.786 |
unden | -0.619 |
scorer | -0.607 |
usal | -0.598 |
anches | -0.567 |
Token | Tut |
Token ID | 22792 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
estern | +2.082 |
Sally | +2.017 |
roo | +1.942 |
tons | +1.881 |
puppies | +1.666 |
Neg logit contributions | |
omial | -2.797 |
unden | -2.216 |
scorer | -2.165 |
usal | -2.112 |
anches | -2.009 |
Token | el |
Token ID | 417 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
estern | +3.318 |
Sally | +3.204 |
roo | +3.052 |
tons | +3.009 |
TON | +2.645 |
Neg logit contributions | |
omial | -4.378 |
unden | -3.481 |
scorer | -3.368 |
usal | -3.303 |
exha | -3.176 |
Token | the |
Token ID | 262 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
omial | +3.245 |
unden | +2.528 |
scorer | +2.479 |
usal | +2.440 |
acing | +2.304 |
Neg logit contributions | |
estern | -2.646 |
Sally | -2.522 |
roo | -2.441 |
tons | -2.380 |
puppies | -2.134 |
Token | next |
Token ID | 1306 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Sally | +0.578 |
estern | +0.576 |
roo | +0.537 |
tons | +0.534 |
puppies | +0.480 |
Neg logit contributions | |
omial | -0.745 |
unden | -0.574 |
scorer | -0.555 |
usal | -0.555 |
anches | -0.533 |
Token | Y |
Token ID | 575 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
estern | +0.320 |
Sally | +0.318 |
roo | +0.299 |
tons | +0.294 |
TON | +0.264 |
Neg logit contributions | |
omial | -0.418 |
unden | -0.324 |
scorer | -0.314 |
usal | -0.312 |
anches | -0.298 |
Token | onge |
Token ID | 14220 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
estern | +1.156 |
Sally | +1.122 |
roo | +1.085 |
tons | +1.066 |
puppies | +0.979 |
Neg logit contributions | |
omial | -0.942 |
unden | -0.681 |
scorer | -0.663 |
usal | -0.649 |
acing | -0.601 |
Token | - |
Token ID | 12 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
omial | +1.072 |
unden | +0.832 |
scorer | +0.815 |
usal | +0.803 |
anches | +0.760 |
Neg logit contributions | |
estern | -0.852 |
Sally | -0.822 |
roo | -0.787 |
tons | -0.771 |
puppies | -0.690 |
Token | Bl |
Token ID | 3629 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
estern | +0.409 |
Sally | +0.397 |
roo | +0.380 |
tons | +0.369 |
TON | +0.332 |
Neg logit contributions | |
omial | -0.579 |
unden | -0.459 |
scorer | -0.446 |
usal | -0.437 |
anches | -0.420 |
Token | oor |
Token ID | 2675 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
omial | +9.222 |
usal | +6.439 |
scorer | +6.234 |
itive | +5.979 |
acing | +5.977 |
Neg logit contributions | |
estern | -11.613 |
Sally | -11.138 |
tons | -10.901 |
roo | -10.409 |
puppies | -9.984 |
Token | , |
Token ID | 11 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
omial | +0.895 |
unden | +0.701 |
scorer | +0.687 |
usal | +0.676 |
anches | +0.645 |
Neg logit contributions | |
estern | -0.657 |
Sally | -0.635 |
roo | -0.606 |
tons | -0.595 |
TON | -0.528 |
Token | then |
Token ID | 788 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
estern | +0.058 |
Sally | +0.057 |
roo | +0.054 |
tons | +0.053 |
puppies | +0.047 |
Neg logit contributions | |
omial | -0.081 |
unden | -0.063 |
scorer | -0.062 |
usal | -0.061 |
anches | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
Sally | +2.271 |
estern | +2.251 |
roo | +2.134 |
tons | +2.108 |
puppies | +1.862 |
Neg logit contributions | |
omial | -3.410 |
unden | -2.646 |
scorer | -2.588 |
usal | -2.563 |
anches | -2.461 |
Token | transit |
Token ID | 11168 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
estern | +0.619 |
Sally | +0.616 |
roo | +0.582 |
tons | +0.574 |
puppies | +0.517 |
Neg logit contributions | |
omial | -0.758 |
unden | -0.580 |
scorer | -0.561 |
usal | -0.559 |
anches | -0.536 |
Token | adapt |
Token ID | 6068 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
omial | +0.538 |
unden | +0.414 |
scorer | +0.405 |
usal | +0.398 |
anches | +0.375 |
Neg logit contributions | |
estern | -0.451 |
Sally | -0.439 |
roo | -0.421 |
tons | -0.412 |
puppies | -0.371 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
estern | +1.715 |
Sally | +1.671 |
roo | +1.577 |
tons | +1.527 |
puppies | +1.345 |
Neg logit contributions | |
omial | -2.765 |
unden | -2.194 |
scorer | -2.151 |
usal | -2.117 |
anches | -2.017 |
Token | lur |
Token ID | 20605 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
estern | +0.765 |
Sally | +0.748 |
roo | +0.709 |
tons | +0.688 |
puppies | +0.608 |
Neg logit contributions | |
omial | -1.206 |
unden | -0.955 |
scorer | -0.932 |
usal | -0.918 |
anches | -0.879 |
Token | id |
Token ID | 312 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
omial | +5.142 |
usal | +3.785 |
unden | +3.772 |
scorer | +3.749 |
acing | +3.581 |
Neg logit contributions | |
estern | -5.166 |
Sally | -4.956 |
roo | -4.727 |
tons | -4.716 |
TON | -4.285 |
Token | Robert |
Token ID | 5199 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
omial | +4.538 |
unden | +3.575 |
scorer | +3.526 |
usal | +3.473 |
acing | +3.308 |
Neg logit contributions | |
estern | -3.233 |
Sally | -3.063 |
roo | -2.938 |
tons | -2.876 |
TON | -2.559 |
Token | Bl |
Token ID | 1086 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
omial | +4.208 |
unden | +3.292 |
scorer | +3.245 |
usal | +3.203 |
acing | +3.041 |
Neg logit contributions | |
estern | -3.107 |
Sally | -2.960 |
roo | -2.847 |
tons | -2.783 |
TON | -2.484 |
Token | och |
Token ID | 5374 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
omial | +9.423 |
usal | +6.651 |
umer | +6.285 |
scorer | +6.216 |
itive | +6.216 |
Neg logit contributions | |
estern | -10.900 |
Sally | -10.796 |
tons | -10.279 |
roo | -10.271 |
TON | -9.781 |
Token | novel |
Token ID | 5337 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
omial | +0.259 |
unden | +0.205 |
scorer | +0.201 |
usal | +0.198 |
anches | +0.188 |
Neg logit contributions | |
estern | -0.175 |
Sally | -0.169 |
roo | -0.161 |
tons | -0.157 |
puppies | -0.139 |
Token | , |
Token ID | 11 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
estern | +3.150 |
Sally | +3.142 |
roo | +2.926 |
tons | +2.886 |
TON | +2.557 |
Neg logit contributions | |
omial | -4.483 |
unden | -3.497 |
scorer | -3.406 |
usal | -3.353 |
anches | -3.224 |
Token | Psycho |
Token ID | 38955 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
estern | +0.147 |
Sally | +0.144 |
roo | +0.136 |
tons | +0.133 |
puppies | +0.118 |
Neg logit contributions | |
omial | -0.204 |
unden | -0.160 |
scorer | -0.157 |
usal | -0.154 |
anches | -0.147 |
Token | , |
Token ID | 11 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
estern | +1.287 |
Sally | +1.243 |
roo | +1.182 |
tons | +1.152 |
puppies | +1.022 |
Neg logit contributions | |
omial | -1.900 |
unden | -1.503 |
scorer | -1.474 |
usal | -1.451 |
anches | -1.383 |
Token | … |
Token ID | 3926 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
omial | +2.251 |
unden | +1.764 |
scorer | +1.736 |
usal | +1.713 |
acing | +1.621 |
Neg logit contributions | |
estern | -1.657 |
Sally | -1.590 |
roo | -1.521 |
tons | -1.485 |
puppies | -1.324 |
Token | another |
Token ID | 1194 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
estern | +2.164 |
Sally | +2.149 |
roo | +2.013 |
tons | +1.995 |
puppies | +1.790 |
Neg logit contributions | |
omial | -3.086 |
unden | -2.403 |
scorer | -2.329 |
usal | -2.291 |
anches | -2.211 |
Token | father |
Token ID | 2988 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
omial | +0.452 |
unden | +0.354 |
scorer | +0.345 |
usal | +0.343 |
anches | +0.327 |
Neg logit contributions | |
estern | -0.311 |
Sally | -0.302 |
roo | -0.286 |
tons | -0.282 |
puppies | -0.251 |
Token | carrying |
Token ID | 6872 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
omial | +1.739 |
unden | +1.304 |
scorer | +1.274 |
usal | +1.252 |
anches | +1.172 |
Neg logit contributions | |
estern | -1.740 |
Sally | -1.686 |
roo | -1.623 |
tons | -1.593 |
puppies | -1.449 |
Token | his |
Token ID | 465 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
omial | +0.026 |
unden | +0.020 |
scorer | +0.020 |
usal | +0.019 |
anches | +0.018 |
Neg logit contributions | |
estern | -0.020 |
Sally | -0.020 |
roo | -0.019 |
tons | -0.018 |
puppies | -0.017 |
Token | child |
Token ID | 1200 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
omial | +0.133 |
unden | +0.106 |
scorer | +0.104 |
usal | +0.103 |
anches | +0.098 |
Neg logit contributions | |
estern | -0.079 |
Sally | -0.076 |
roo | -0.072 |
tons | -0.071 |
puppies | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Sally | +4.318 |
estern | +4.317 |
roo | +4.090 |
tons | +3.996 |
puppies | +3.648 |
Neg logit contributions | |
omial | -5.833 |
unden | -4.516 |
usal | -4.296 |
scorer | -4.251 |
exha | -4.138 |
Token | a |
Token ID | 257 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
omial | +1.170 |
unden | +0.916 |
scorer | +0.899 |
usal | +0.886 |
acing | +0.839 |
Neg logit contributions | |
estern | -0.862 |
Sally | -0.830 |
roo | -0.793 |
tons | -0.775 |
puppies | -0.691 |
Token | grave |
Token ID | 12296 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
omial | +0.594 |
unden | +0.456 |
scorer | +0.442 |
usal | +0.440 |
anches | +0.416 |
Neg logit contributions | |
estern | -0.481 |
Sally | -0.468 |
roo | -0.447 |
tons | -0.434 |
puppies | -0.394 |
Token | in |
Token ID | 287 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
estern | +0.494 |
Sally | +0.481 |
roo | +0.458 |
tons | +0.443 |
puppies | +0.394 |
Neg logit contributions | |
omial | -0.769 |
unden | -0.611 |
scorer | -0.591 |
usal | -0.586 |
anches | -0.559 |
Token | # |
Token ID | 1303 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
omial | +0.126 |
unden | +0.098 |
scorer | +0.096 |
usal | +0.095 |
anches | +0.090 |
Neg logit contributions | |
estern | -0.091 |
Sally | -0.088 |
roo | -0.084 |
tons | -0.082 |
puppies | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
omial | +0.804 |
unden | +0.638 |
scorer | +0.622 |
usal | +0.615 |
anches | +0.584 |
Neg logit contributions | |
estern | -0.552 |
Sally | -0.536 |
roo | -0.508 |
tons | -0.498 |
TON | -0.442 |
Token |
|
Token ID | 198 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
omial | +0.964 |
unden | +0.786 |
scorer | +0.757 |
usal | +0.747 |
exha | +0.722 |
Neg logit contributions | |
estern | -0.599 |
Sally | -0.576 |
roo | -0.550 |
tons | -0.535 |
TON | -0.474 |
Token | For |
Token ID | 1890 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
omial | +0.856 |
unden | +0.673 |
scorer | +0.657 |
usal | +0.645 |
exha | +0.612 |
Neg logit contributions | |
estern | -0.633 |
Sally | -0.609 |
roo | -0.587 |
tons | -0.575 |
TON | -0.514 |
Token | beginner |
Token ID | 31516 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
omial | +1.942 |
unden | +1.484 |
scorer | +1.455 |
usal | +1.431 |
acing | +1.346 |
Neg logit contributions | |
estern | -1.723 |
Sally | -1.663 |
roo | -1.598 |
tons | -1.566 |
puppies | -1.413 |
Token | Horror |
Token ID | 22732 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
estern | +1.250 |
Sally | +1.218 |
roo | +1.158 |
tons | +1.146 |
puppies | +1.038 |
Neg logit contributions | |
omial | -1.542 |
unden | -1.193 |
scorer | -1.144 |
usal | -1.140 |
anches | -1.089 |
Token | GM |
Token ID | 6951 |
Feature activation | +5.11e+00 |
Pos logit contributions | |
estern | +0.714 |
Sally | +0.688 |
roo | +0.659 |
tons | +0.642 |
puppies | +0.578 |
Neg logit contributions | |
omial | -0.983 |
unden | -0.778 |
scorer | -0.751 |
usal | -0.744 |
anches | -0.707 |
Token | � |
Token ID | 447 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
estern | +4.268 |
Sally | +4.160 |
roo | +3.890 |
tons | +3.845 |
puppies | +3.510 |
Neg logit contributions | |
omial | -5.432 |
unden | -4.239 |
scorer | -4.058 |
usal | -3.989 |
anches | -3.825 |
Token | � |
Token ID | 247 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
estern | +0.523 |
Sally | +0.507 |
roo | +0.489 |
tons | +0.476 |
puppies | +0.431 |
Neg logit contributions | |
omial | -0.568 |
unden | -0.431 |
scorer | -0.421 |
usal | -0.412 |
anches | -0.387 |
Token | s |
Token ID | 82 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
estern | +0.555 |
Sally | +0.535 |
roo | +0.511 |
tons | +0.501 |
TON | +0.445 |
Neg logit contributions | |
omial | -0.748 |
unden | -0.587 |
scorer | -0.572 |
usal | -0.562 |
anches | -0.534 |
Token | , |
Token ID | 11 |
Feature activation | -2.18e-04 |
Pos logit contributions | |
estern | +0.128 |
Sally | +0.123 |
roo | +0.117 |
tons | +0.114 |
puppies | +0.101 |
Neg logit contributions | |
omial | -0.192 |
unden | -0.153 |
scorer | -0.150 |
usal | -0.148 |
anches | -0.140 |
Token | we |
Token ID | 356 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
omial | +0.000 |
unden | +0.000 |
scorer | +0.000 |
usal | +0.000 |
anches | +0.000 |
Neg logit contributions | |
estern | -0.000 |
Sally | -0.000 |
roo | -0.000 |
tons | -0.000 |
puppies | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
omial | +1.530 |
unden | +1.200 |
scorer | +1.179 |
usal | +1.161 |
acing | +1.100 |
Neg logit contributions | |
estern | -1.113 |
Sally | -1.070 |
roo | -1.023 |
tons | -1.000 |
puppies | -0.890 |
Token | but |
Token ID | 475 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
omial | +0.544 |
unden | +0.429 |
scorer | +0.418 |
usal | +0.416 |
acing | +0.394 |
Neg logit contributions | |
estern | -0.379 |
Sally | -0.368 |
roo | -0.349 |
tons | -0.341 |
puppies | -0.305 |
Token | not |
Token ID | 407 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
estern | +1.368 |
Sally | +1.353 |
roo | +1.257 |
tons | +1.256 |
puppies | +1.109 |
Neg logit contributions | |
omial | -2.087 |
unden | -1.639 |
usal | -1.590 |
scorer | -1.589 |
anches | -1.509 |
Token | many |
Token ID | 867 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
omial | +1.565 |
unden | +1.237 |
scorer | +1.212 |
usal | +1.198 |
acing | +1.137 |
Neg logit contributions | |
estern | -1.051 |
Sally | -1.014 |
roo | -0.963 |
tons | -0.943 |
puppies | -0.834 |
Token | like |
Token ID | 588 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
omial | +2.349 |
unden | +1.817 |
scorer | +1.781 |
usal | +1.758 |
acing | +1.659 |
Neg logit contributions | |
estern | -1.869 |
Sally | -1.810 |
roo | -1.728 |
tons | -1.697 |
puppies | -1.523 |
Token | Pat |
Token ID | 3208 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
estern | +1.888 |
Sally | +1.857 |
roo | +1.740 |
tons | +1.706 |
puppies | +1.529 |
Neg logit contributions | |
omial | -2.755 |
unden | -2.160 |
scorer | -2.099 |
usal | -2.092 |
anches | -1.987 |
Token | On |
Token ID | 1550 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
estern | +4.378 |
Sally | +4.362 |
roo | +4.101 |
tons | +3.984 |
TON | +3.481 |
Neg logit contributions | |
omial | -6.473 |
unden | -5.209 |
scorer | -5.023 |
usal | -5.009 |
exha | -4.775 |
Token | stad |
Token ID | 24107 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
estern | +0.327 |
Sally | +0.316 |
roo | +0.301 |
tons | +0.294 |
TON | +0.258 |
Neg logit contributions | |
omial | -0.498 |
unden | -0.395 |
scorer | -0.388 |
usal | -0.383 |
anches | -0.365 |
Token | 's |
Token ID | 338 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
omial | +1.655 |
unden | +1.253 |
scorer | +1.232 |
usal | +1.209 |
acing | +1.138 |
Neg logit contributions | |
estern | -1.539 |
Sally | -1.486 |
roo | -1.427 |
tons | -1.400 |
puppies | -1.268 |
Token | . |
Token ID | 13 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
estern | +1.111 |
Sally | +1.090 |
roo | +1.028 |
tons | +1.008 |
puppies | +0.906 |
Neg logit contributions | |
omial | -1.469 |
unden | -1.135 |
scorer | -1.106 |
usal | -1.102 |
anches | -1.046 |
Token |
|
Token ID | 198 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
omial | +0.643 |
unden | +0.511 |
scorer | +0.498 |
usal | +0.492 |
anches | +0.467 |
Neg logit contributions | |
estern | -0.442 |
Sally | -0.428 |
roo | -0.406 |
tons | -0.397 |
TON | -0.352 |
Token | turnover |
Token ID | 25079 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
estern | +2.522 |
Sally | +2.467 |
roo | +2.322 |
tons | +2.284 |
puppies | +2.074 |
Neg logit contributions | |
omial | -3.534 |
unden | -2.753 |
scorer | -2.680 |
usal | -2.641 |
anches | -2.524 |
Token | may |
Token ID | 743 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
estern | +0.380 |
Sally | +0.372 |
roo | +0.354 |
tons | +0.347 |
puppies | +0.314 |
Neg logit contributions | |
omial | -0.476 |
unden | -0.368 |
scorer | -0.357 |
usal | -0.355 |
anches | -0.335 |
Token | be |
Token ID | 307 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
estern | +1.277 |
Sally | +1.264 |
roo | +1.196 |
tons | +1.172 |
puppies | +1.059 |
Neg logit contributions | |
omial | -1.809 |
unden | -1.445 |
scorer | -1.385 |
usal | -1.376 |
anches | -1.311 |
Token | higher |
Token ID | 2440 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
omial | +0.137 |
unden | +0.104 |
scorer | +0.101 |
usal | +0.100 |
anches | +0.096 |
Neg logit contributions | |
estern | -0.115 |
Sally | -0.114 |
roo | -0.107 |
tons | -0.106 |
puppies | -0.096 |
Token | in |
Token ID | 287 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
estern | +2.392 |
Sally | +2.338 |
roo | +2.187 |
tons | +2.168 |
puppies | +1.939 |
Neg logit contributions | |
omial | -3.422 |
unden | -2.694 |
scorer | -2.611 |
usal | -2.590 |
anches | -2.471 |
Token | charter |
Token ID | 17422 |
Feature activation | +6.96e+00 |
Pos logit contributions | |
estern | +0.768 |
Sally | +0.747 |
roo | +0.706 |
tons | +0.692 |
puppies | +0.622 |
Neg logit contributions | |
omial | -1.100 |
unden | -0.861 |
scorer | -0.842 |
usal | -0.831 |
acing | -0.790 |
Token | schools |
Token ID | 4266 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
estern | +3.844 |
Sally | +3.706 |
roo | +3.387 |
tons | +3.349 |
puppies | +2.884 |
Neg logit contributions | |
omial | -9.276 |
unden | -7.571 |
scorer | -7.382 |
usal | -7.328 |
exha | -7.035 |
Token | because |
Token ID | 780 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
estern | +1.367 |
Sally | +1.325 |
roo | +1.249 |
tons | +1.232 |
puppies | +1.097 |
Neg logit contributions | |
omial | -2.022 |
unden | -1.598 |
scorer | -1.556 |
usal | -1.539 |
anches | -1.465 |
Token | charter |
Token ID | 17422 |
Feature activation | +7.12e+00 |
Pos logit contributions | |
estern | +1.858 |
Sally | +1.832 |
roo | +1.715 |
tons | +1.710 |
puppies | +1.541 |
Neg logit contributions | |
omial | -2.670 |
unden | -2.077 |
scorer | -2.021 |
usal | -2.004 |
acing | -1.904 |
Token | school |
Token ID | 1524 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
estern | +4.204 |
Sally | +4.091 |
roo | +3.778 |
tons | +3.763 |
puppies | +3.315 |
Neg logit contributions | |
omial | -9.118 |
unden | -7.446 |
scorer | -7.179 |
usal | -7.144 |
exha | -6.888 |
Token | teachers |
Token ID | 7799 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
estern | +1.493 |
Sally | +1.451 |
roo | +1.324 |
tons | +1.311 |
puppies | +1.120 |
Neg logit contributions | |
omial | -3.690 |
unden | -3.026 |
scorer | -2.950 |
usal | -2.923 |
acing | -2.811 |
Token | of |
Token ID | 286 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
omial | +3.055 |
unden | +2.316 |
scorer | +2.269 |
usal | +2.230 |
acing | +2.094 |
Neg logit contributions | |
estern | -2.866 |
Sally | -2.769 |
roo | -2.665 |
tons | -2.613 |
puppies | -2.366 |
Token | the |
Token ID | 262 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
omial | +0.307 |
unden | +0.240 |
scorer | +0.236 |
usal | +0.233 |
anches | +0.221 |
Neg logit contributions | |
estern | -0.217 |
Sally | -0.211 |
roo | -0.199 |
tons | -0.195 |
puppies | -0.174 |
Token | Hon |
Token ID | 8835 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
estern | +0.524 |
Sally | +0.520 |
roo | +0.485 |
tons | +0.482 |
puppies | +0.435 |
Neg logit contributions | |
omial | -0.755 |
unden | -0.589 |
scorer | -0.575 |
usal | -0.574 |
anches | -0.541 |
Token | ick |
Token ID | 624 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
omial | +0.927 |
unden | +0.660 |
scorer | +0.654 |
usal | +0.648 |
anches | +0.613 |
Neg logit contributions | |
estern | -1.106 |
Sally | -1.074 |
roo | -1.031 |
tons | -1.007 |
TON | -0.933 |
Token | man |
Token ID | 805 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
estern | +2.616 |
Sally | +2.494 |
roo | +2.358 |
tons | +2.295 |
puppies | +1.973 |
Neg logit contributions | |
omial | -5.027 |
unden | -4.073 |
scorer | -4.012 |
usal | -3.960 |
acing | -3.783 |
Token | children |
Token ID | 1751 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
omial | +0.969 |
unden | +0.762 |
scorer | +0.748 |
usal | +0.736 |
acing | +0.697 |
Neg logit contributions | |
estern | -0.688 |
Sally | -0.663 |
roo | -0.633 |
tons | -0.620 |
puppies | -0.551 |
Token | , |
Token ID | 11 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
Sally | +4.128 |
estern | +4.042 |
roo | +3.774 |
tons | +3.743 |
puppies | +3.378 |
Neg logit contributions | |
omial | -5.926 |
unden | -4.647 |
usal | -4.533 |
scorer | -4.514 |
exha | -4.281 |
Token | Shirley |
Token ID | 40902 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
estern | +0.614 |
Sally | +0.610 |
roo | +0.565 |
tons | +0.551 |
puppies | +0.496 |
Neg logit contributions | |
omial | -0.918 |
unden | -0.719 |
scorer | -0.704 |
usal | -0.700 |
anches | -0.662 |
Token | , |
Token ID | 11 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
estern | +0.254 |
Sally | +0.244 |
roo | +0.233 |
tons | +0.227 |
puppies | +0.201 |
Neg logit contributions | |
omial | -0.379 |
unden | -0.300 |
scorer | -0.295 |
usal | -0.290 |
anches | -0.276 |
Token | is |
Token ID | 318 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
estern | +0.483 |
Sally | +0.479 |
roo | +0.448 |
tons | +0.439 |
puppies | +0.401 |
Neg logit contributions | |
omial | -0.632 |
unden | -0.487 |
usal | -0.475 |
scorer | -0.473 |
acing | -0.445 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
estern | +0.415 |
Sally | +0.407 |
roo | +0.382 |
tons | +0.374 |
puppies | +0.336 |
Neg logit contributions | |
omial | -0.571 |
unden | -0.442 |
scorer | -0.432 |
usal | -0.430 |
anches | -0.407 |
Token | routes |
Token ID | 11926 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
estern | +3.702 |
Sally | +3.685 |
tons | +3.520 |
roo | +3.464 |
puppies | +3.206 |
Neg logit contributions | |
omial | -4.563 |
unden | -3.511 |
usal | -3.413 |
scorer | -3.272 |
anches | -3.208 |
Token | to |
Token ID | 284 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
omial | +1.054 |
unden | +0.822 |
scorer | +0.802 |
usal | +0.791 |
anches | +0.749 |
Neg logit contributions | |
estern | -0.815 |
Sally | -0.787 |
roo | -0.752 |
tons | -0.737 |
puppies | -0.661 |
Token | the |
Token ID | 262 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
omial | +0.834 |
unden | +0.647 |
scorer | +0.625 |
usal | +0.622 |
anches | +0.589 |
Neg logit contributions | |
estern | -0.636 |
Sally | -0.624 |
roo | -0.596 |
tons | -0.581 |
puppies | -0.524 |
Token | defense |
Token ID | 3761 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
omial | +0.482 |
unden | +0.366 |
usal | +0.356 |
scorer | +0.348 |
anches | +0.337 |
Neg logit contributions | |
estern | -0.403 |
Sally | -0.398 |
roo | -0.377 |
tons | -0.371 |
puppies | -0.340 |
Token | . |
Token ID | 13 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
estern | +0.623 |
Sally | +0.607 |
roo | +0.578 |
tons | +0.565 |
puppies | +0.504 |
Neg logit contributions | |
omial | -0.889 |
unden | -0.703 |
scorer | -0.680 |
usal | -0.675 |
anches | -0.642 |
Token | While |
Token ID | 2893 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
omial | +0.612 |
unden | +0.490 |
scorer | +0.474 |
usal | +0.469 |
exha | +0.448 |
Neg logit contributions | |
estern | -0.426 |
Sally | -0.418 |
roo | -0.395 |
tons | -0.387 |
TON | -0.343 |
Token | a |
Token ID | 257 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
omial | +0.632 |
unden | +0.496 |
scorer | +0.484 |
usal | +0.479 |
anches | +0.454 |
Neg logit contributions | |
estern | -0.448 |
Sally | -0.435 |
roo | -0.414 |
tons | -0.406 |
puppies | -0.360 |
Token | corner |
Token ID | 5228 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
omial | +0.724 |
unden | +0.556 |
usal | +0.532 |
scorer | +0.529 |
anches | +0.505 |
Neg logit contributions | |
estern | -0.634 |
Sally | -0.620 |
roo | -0.593 |
tons | -0.577 |
puppies | -0.520 |
Token | may |
Token ID | 743 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
estern | +0.764 |
Sally | +0.740 |
roo | +0.714 |
tons | +0.692 |
TON | +0.622 |
Neg logit contributions | |
omial | -0.957 |
unden | -0.752 |
scorer | -0.718 |
usal | -0.715 |
anches | -0.679 |
Token | think |
Token ID | 892 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
estern | +0.110 |
Sally | +0.108 |
roo | +0.103 |
tons | +0.101 |
puppies | +0.090 |
Neg logit contributions | |
omial | -0.145 |
unden | -0.114 |
scorer | -0.110 |
usal | -0.109 |
anches | -0.103 |
Token | he |
Token ID | 339 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
omial | +0.524 |
unden | +0.413 |
scorer | +0.400 |
usal | +0.396 |
anches | +0.379 |
Neg logit contributions | |
estern | -0.366 |
Sally | -0.357 |
roo | -0.339 |
tons | -0.332 |
puppies | -0.295 |
Token | ib |
Token ID | 571 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
omial | +1.179 |
unden | +0.858 |
scorer | +0.842 |
usal | +0.840 |
anches | +0.779 |
Neg logit contributions | |
estern | -1.305 |
Sally | -1.257 |
roo | -1.213 |
tons | -1.193 |
enegger | -1.088 |
Token | in |
Token ID | 259 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
estern | +0.158 |
Sally | +0.153 |
roo | +0.149 |
tons | +0.145 |
puppies | +0.127 |
Neg logit contributions | |
omial | -0.220 |
unden | -0.177 |
scorer | -0.172 |
usal | -0.165 |
exha | -0.163 |
Token | ol |
Token ID | 349 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
estern | +0.527 |
Sally | +0.512 |
roo | +0.493 |
tons | +0.478 |
puppies | +0.435 |
Neg logit contributions | |
omial | -0.608 |
unden | -0.470 |
scorer | -0.460 |
usal | -0.450 |
anches | -0.426 |
Token | can |
Token ID | 460 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
omial | +1.831 |
unden | +1.424 |
scorer | +1.396 |
usal | +1.373 |
anches | +1.299 |
Neg logit contributions | |
estern | -1.431 |
Sally | -1.383 |
roo | -1.323 |
tons | -1.295 |
puppies | -1.159 |
Token | be |
Token ID | 307 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
estern | +0.739 |
Sally | +0.726 |
roo | +0.694 |
tons | +0.681 |
puppies | +0.610 |
Neg logit contributions | |
omial | -0.950 |
unden | -0.746 |
scorer | -0.722 |
usal | -0.715 |
anches | -0.676 |
Token | a |
Token ID | 257 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
omial | +1.360 |
unden | +1.039 |
scorer | +1.018 |
usal | +1.002 |
anches | +0.948 |
Neg logit contributions | |
estern | -1.175 |
Sally | -1.140 |
roo | -1.089 |
tons | -1.068 |
puppies | -0.964 |
Token | daunting |
Token ID | 30496 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
estern | +0.326 |
Sally | +0.318 |
roo | +0.303 |
tons | +0.295 |
TON | +0.262 |
Neg logit contributions | |
omial | -0.449 |
unden | -0.351 |
scorer | -0.340 |
usal | -0.338 |
anches | -0.323 |
Token | mouth |
Token ID | 5422 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
estern | +1.036 |
Sally | +1.027 |
roo | +0.975 |
tons | +0.959 |
TON | +0.861 |
Neg logit contributions | |
omial | -1.322 |
unden | -1.021 |
scorer | -0.994 |
usal | -0.987 |
anches | -0.960 |
Token | ful |
Token ID | 913 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
omial | +1.273 |
unden | +0.938 |
scorer | +0.909 |
usal | +0.888 |
anches | +0.838 |
Neg logit contributions | |
estern | -1.435 |
Sally | -1.397 |
roo | -1.353 |
tons | -1.322 |
puppies | -1.209 |
Token | , |
Token ID | 11 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
omial | +0.466 |
unden | +0.364 |
scorer | +0.357 |
usal | +0.351 |
anches | +0.332 |
Neg logit contributions | |
estern | -0.356 |
Sally | -0.343 |
roo | -0.329 |
tons | -0.322 |
puppies | -0.287 |
Token | in |
Token ID | 287 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
estern | +0.040 |
Sally | +0.039 |
roo | +0.037 |
tons | +0.037 |
puppies | +0.033 |
Neg logit contributions | |
omial | -0.055 |
unden | -0.043 |
scorer | -0.042 |
usal | -0.042 |
anches | -0.040 |
Token | Albion |
Token ID | 47995 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
estern | +1.014 |
Sally | +0.994 |
roo | +0.932 |
tons | +0.916 |
puppies | +0.821 |
Neg logit contributions | |
omial | -1.426 |
unden | -1.099 |
scorer | -1.079 |
usal | -1.075 |
anches | -1.025 |
Token | 's |
Token ID | 338 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
omial | +4.944 |
unden | +3.756 |
scorer | +3.700 |
usal | +3.620 |
acing | +3.427 |
Neg logit contributions | |
estern | -4.908 |
Sally | -4.742 |
roo | -4.579 |
tons | -4.502 |
enegger | -4.109 |
Token | first |
Token ID | 717 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
estern | +1.316 |
Sally | +1.309 |
roo | +1.229 |
tons | +1.210 |
puppies | +1.109 |
Neg logit contributions | |
omial | -1.575 |
unden | -1.196 |
usal | -1.160 |
scorer | -1.156 |
anches | -1.105 |
Token | partnership |
Token ID | 10413 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
estern | +1.939 |
Sally | +1.936 |
roo | +1.810 |
tons | +1.788 |
puppies | +1.599 |
Neg logit contributions | |
omial | -2.885 |
unden | -2.223 |
usal | -2.166 |
scorer | -2.161 |
anches | -2.083 |
Token | with |
Token ID | 351 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
estern | +2.644 |
Sally | +2.620 |
roo | +2.456 |
tons | +2.441 |
puppies | +2.163 |
Neg logit contributions | |
omial | -3.961 |
unden | -3.078 |
usal | -2.999 |
scorer | -2.970 |
anches | -2.870 |
Token | 12 |
Token ID | 1105 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
estern | +2.183 |
Sally | +2.147 |
roo | +2.018 |
tons | +1.975 |
puppies | +1.770 |
Neg logit contributions | |
omial | -3.015 |
unden | -2.326 |
usal | -2.257 |
scorer | -2.250 |
anches | -2.164 |
Token | B |
Token ID | 33 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
estern | +3.215 |
Sally | +3.091 |
roo | +2.977 |
tons | +2.918 |
TON | +2.619 |
Neg logit contributions | |
omial | -4.134 |
unden | -3.198 |
scorer | -3.146 |
usal | -3.119 |
acing | -2.921 |
Token | ET |
Token ID | 2767 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
omial | +4.665 |
unden | +3.643 |
scorer | +3.612 |
usal | +3.561 |
acing | +3.395 |
Neg logit contributions | |
estern | -3.207 |
Sally | -3.092 |
roo | -2.940 |
tons | -2.874 |
puppies | -2.555 |
Token | . |
Token ID | 13 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
estern | +3.154 |
Sally | +3.124 |
roo | +2.939 |
tons | +2.884 |
puppies | +2.537 |
Neg logit contributions | |
omial | -5.199 |
unden | -4.102 |
usal | -4.002 |
scorer | -3.943 |
anches | -3.791 |
Token | Form |
Token ID | 5178 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
omial | +0.399 |
unden | +0.316 |
scorer | +0.309 |
usal | +0.306 |
anches | +0.290 |
Neg logit contributions | |
estern | -0.271 |
Sally | -0.261 |
roo | -0.249 |
tons | -0.242 |
TON | -0.215 |
Token | ed |
Token ID | 276 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
estern | +0.305 |
Sally | +0.294 |
roo | +0.281 |
tons | +0.275 |
TON | +0.244 |
Neg logit contributions | |
omial | -0.416 |
unden | -0.325 |
scorer | -0.318 |
usal | -0.314 |
anches | -0.297 |
Token | $ |
Token ID | 720 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
omial | +0.060 |
unden | +0.047 |
scorer | +0.046 |
usal | +0.046 |
anches | +0.044 |
Neg logit contributions | |
estern | -0.041 |
Sally | -0.040 |
roo | -0.038 |
tons | -0.037 |
puppies | -0.033 |
Token | 20 |
Token ID | 1238 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
estern | +1.143 |
Sally | +1.113 |
roo | +1.067 |
tons | +1.045 |
TON | +0.938 |
Neg logit contributions | |
omial | -1.663 |
unden | -1.363 |
scorer | -1.300 |
usal | -1.273 |
exha | -1.259 |
Token | billion |
Token ID | 2997 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
omial | +0.337 |
unden | +0.266 |
scorer | +0.262 |
usal | +0.258 |
anches | +0.245 |
Neg logit contributions | |
estern | -0.233 |
Sally | -0.223 |
roo | -0.213 |
tons | -0.209 |
TON | -0.185 |
Token | , |
Token ID | 11 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
omial | +0.128 |
unden | +0.101 |
scorer | +0.099 |
usal | +0.098 |
anches | +0.093 |
Neg logit contributions | |
estern | -0.089 |
Sally | -0.086 |
roo | -0.082 |
tons | -0.080 |
puppies | -0.071 |
Token | more |
Token ID | 517 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
estern | +0.052 |
Sally | +0.051 |
roo | +0.048 |
tons | +0.048 |
puppies | +0.043 |
Neg logit contributions | |
omial | -0.068 |
unden | -0.053 |
usal | -0.051 |
scorer | -0.051 |
anches | -0.048 |
Token | than |
Token ID | 621 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
estern | +0.638 |
Sally | +0.618 |
roo | +0.586 |
tons | +0.577 |
puppies | +0.517 |
Neg logit contributions | |
omial | -0.859 |
unden | -0.666 |
scorer | -0.656 |
usal | -0.651 |
anches | -0.614 |
Token | half |
Token ID | 2063 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
estern | +0.246 |
Sally | +0.243 |
roo | +0.230 |
tons | +0.226 |
puppies | +0.202 |
Neg logit contributions | |
omial | -0.358 |
unden | -0.277 |
usal | -0.273 |
scorer | -0.270 |
acing | -0.256 |
Token | of |
Token ID | 286 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
estern | +0.535 |
Sally | +0.519 |
roo | +0.497 |
tons | +0.488 |
puppies | +0.442 |
Neg logit contributions | |
omial | -0.576 |
unden | -0.435 |
scorer | -0.426 |
usal | -0.421 |
acing | -0.395 |
Token | the |
Token ID | 262 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
omial | +0.662 |
unden | +0.514 |
scorer | +0.504 |
usal | +0.497 |
acing | +0.470 |
Neg logit contributions | |
estern | -0.519 |
Sally | -0.501 |
roo | -0.479 |
tons | -0.469 |
puppies | -0.420 |
Token | population |
Token ID | 3265 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
omial | +0.089 |
unden | +0.068 |
scorer | +0.067 |
usal | +0.066 |
anches | +0.062 |
Neg logit contributions | |
estern | -0.078 |
Sally | -0.076 |
roo | -0.072 |
tons | -0.071 |
puppies | -0.065 |
Token | working |
Token ID | 1762 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
omial | +4.332 |
unden | +3.341 |
scorer | +3.280 |
usal | +3.222 |
anches | +3.046 |
Neg logit contributions | |
estern | -3.654 |
Sally | -3.512 |
roo | -3.388 |
tons | -3.299 |
puppies | -2.965 |
Token | accent |
Token ID | 18702 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
estern | +0.640 |
Sally | +0.635 |
roo | +0.600 |
tons | +0.596 |
puppies | +0.552 |
Neg logit contributions | |
omial | -0.514 |
unden | -0.364 |
scorer | -0.360 |
usal | -0.354 |
anches | -0.329 |
Token | , |
Token ID | 11 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
omial | +3.140 |
unden | +2.469 |
scorer | +2.424 |
usal | +2.389 |
acing | +2.265 |
Neg logit contributions | |
estern | -2.246 |
Sally | -2.160 |
roo | -2.063 |
tons | -2.016 |
puppies | -1.792 |
Token | speak |
Token ID | 2740 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
omial | +0.047 |
unden | +0.036 |
scorer | +0.035 |
usal | +0.035 |
anches | +0.033 |
Neg logit contributions | |
estern | -0.036 |
Sally | -0.035 |
roo | -0.033 |
tons | -0.033 |
puppies | -0.030 |
Token | pretty |
Token ID | 2495 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
omial | +2.573 |
unden | +2.007 |
scorer | +1.967 |
usal | +1.943 |
anches | +1.840 |
Neg logit contributions | |
estern | -1.913 |
Sally | -1.854 |
roo | -1.760 |
tons | -1.726 |
puppies | -1.548 |
Token | uniformly |
Token ID | 42096 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
omial | +4.504 |
unden | +3.531 |
scorer | +3.464 |
usal | +3.419 |
acing | +3.240 |
Neg logit contributions | |
estern | -3.251 |
Sally | -3.136 |
roo | -2.987 |
tons | -2.925 |
puppies | -2.607 |
Token | . |
Token ID | 13 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
estern | +0.522 |
Sally | +0.509 |
roo | +0.477 |
tons | +0.468 |
puppies | +0.418 |
Neg logit contributions | |
omial | -0.765 |
unden | -0.607 |
scorer | -0.591 |
usal | -0.585 |
anches | -0.558 |
Token | Black |
Token ID | 2619 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
estern | +0.021 |
Sally | +0.021 |
roo | +0.020 |
tons | +0.019 |
TON | +0.017 |
Neg logit contributions | |
omial | -0.030 |
unden | -0.024 |
scorer | -0.024 |
usal | -0.023 |
exha | -0.022 |
Token | Phil |
Token ID | 4543 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
omial | +1.918 |
unden | +1.499 |
scorer | +1.473 |
usal | +1.452 |
acing | +1.375 |
Neg logit contributions | |
estern | -1.445 |
Sally | -1.384 |
roo | -1.331 |
tons | -1.297 |
TON | -1.157 |
Token | adel |
Token ID | 6959 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
estern | +0.549 |
Sally | +0.517 |
roo | +0.496 |
tons | +0.492 |
TON | +0.426 |
Neg logit contributions | |
omial | -0.818 |
unden | -0.678 |
scorer | -0.648 |
usal | -0.626 |
exha | -0.623 |
Token | ph |
Token ID | 746 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
omial | +2.209 |
unden | +1.445 |
scorer | +1.440 |
usal | +1.426 |
acing | +1.302 |
Neg logit contributions | |
estern | -3.409 |
Sally | -3.327 |
roo | -3.226 |
tons | -3.145 |
enegger | -2.942 |
Token | ians |
Token ID | 1547 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
omial | +0.274 |
unden | +0.212 |
scorer | +0.204 |
usal | +0.195 |
exha | +0.192 |
Neg logit contributions | |
estern | -0.270 |
Sally | -0.261 |
roo | -0.254 |
tons | -0.249 |
puppies | -0.225 |
Token | U |
Token ID | 471 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
omial | +0.467 |
unden | +0.365 |
scorer | +0.356 |
usal | +0.353 |
anches | +0.336 |
Neg logit contributions | |
estern | -0.337 |
Sally | -0.329 |
roo | -0.310 |
tons | -0.304 |
puppies | -0.271 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
omial | +1.926 |
unden | +1.556 |
scorer | +1.495 |
usal | +1.451 |
exha | +1.423 |
Neg logit contributions | |
estern | -1.367 |
Sally | -1.321 |
roo | -1.277 |
tons | -1.252 |
TON | -1.122 |
Token | S |
Token ID | 50 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
omial | +2.596 |
unden | +2.002 |
scorer | +1.968 |
usal | +1.955 |
acing | +1.841 |
Neg logit contributions | |
estern | -2.079 |
Sally | -1.990 |
roo | -1.921 |
tons | -1.885 |
puppies | -1.684 |
Token | . |
Token ID | 13 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
omial | +3.135 |
unden | +2.359 |
usal | +2.355 |
scorer | +2.313 |
acing | +2.203 |
Neg logit contributions | |
estern | -2.967 |
Sally | -2.843 |
roo | -2.738 |
tons | -2.715 |
puppies | -2.461 |
Token | Treasury |
Token ID | 13419 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
omial | +1.952 |
unden | +1.532 |
scorer | +1.498 |
usal | +1.480 |
anches | +1.400 |
Neg logit contributions | |
estern | -1.442 |
Sally | -1.396 |
roo | -1.327 |
tons | -1.293 |
puppies | -1.154 |
Token | Department |
Token ID | 2732 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
estern | +0.309 |
Sally | +0.301 |
roo | +0.285 |
tons | +0.278 |
TON | +0.246 |
Neg logit contributions | |
omial | -0.442 |
unden | -0.349 |
scorer | -0.342 |
usal | -0.337 |
acing | -0.319 |
Token | . |
Token ID | 13 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
omial | +2.439 |
unden | +1.876 |
scorer | +1.845 |
usal | +1.814 |
acing | +1.714 |
Neg logit contributions | |
estern | -2.033 |
Sally | -1.953 |
roo | -1.879 |
tons | -1.841 |
puppies | -1.654 |
Token | Ext |
Token ID | 5683 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
omial | +0.522 |
unden | +0.413 |
scorer | +0.405 |
usal | +0.399 |
anches | +0.378 |
Neg logit contributions | |
estern | -0.362 |
Sally | -0.349 |
roo | -0.332 |
tons | -0.324 |
puppies | -0.287 |
Token | ortion |
Token ID | 5817 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
estern | +1.813 |
Sally | +1.746 |
roo | +1.705 |
tons | +1.648 |
hire | +1.493 |
Neg logit contributions | |
omial | -2.002 |
unden | -1.567 |
scorer | -1.516 |
usal | -1.448 |
exha | -1.413 |
Token | , |
Token ID | 11 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
omial | +0.463 |
unden | +0.364 |
scorer | +0.356 |
usal | +0.352 |
anches | +0.332 |
Neg logit contributions | |
estern | -0.343 |
Sally | -0.330 |
roo | -0.316 |
tons | -0.310 |
puppies | -0.275 |
Token | loan |
Token ID | 8063 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
omial | +0.096 |
unden | +0.076 |
scorer | +0.074 |
usal | +0.073 |
anches | +0.069 |
Neg logit contributions | |
estern | -0.067 |
Sally | -0.066 |
roo | -0.062 |
tons | -0.060 |
puppies | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
omial | +0.075 |
unden | +0.061 |
scorer | +0.059 |
usal | +0.058 |
exha | +0.057 |
Neg logit contributions | |
estern | -0.046 |
Sally | -0.044 |
roo | -0.042 |
tons | -0.041 |
TON | -0.036 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
omial | +0.238 |
unden | +0.188 |
scorer | +0.183 |
usal | +0.179 |
exha | +0.172 |
Neg logit contributions | |
estern | -0.174 |
Sally | -0.168 |
roo | -0.163 |
tons | -0.159 |
TON | -0.142 |
Token | a |
Token ID | 64 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
omial | +1.294 |
unden | +0.960 |
scorer | +0.943 |
usal | +0.928 |
acing | +0.866 |
Neg logit contributions | |
estern | -1.347 |
Sally | -1.302 |
roo | -1.255 |
tons | -1.229 |
TON | -1.127 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
omial | +1.761 |
unden | +1.336 |
scorer | +1.312 |
usal | +1.289 |
acing | +1.215 |
Neg logit contributions | |
estern | -1.622 |
Sally | -1.551 |
roo | -1.494 |
tons | -1.477 |
TON | -1.339 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
estern | +0.224 |
Sally | +0.216 |
roo | +0.207 |
tons | +0.202 |
puppies | +0.180 |
Neg logit contributions | |
omial | -0.292 |
unden | -0.229 |
scorer | -0.224 |
usal | -0.220 |
anches | -0.208 |
Token | Sw |
Token ID | 2451 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
omial | +1.574 |
unden | +1.238 |
scorer | +1.212 |
usal | +1.198 |
anches | +1.136 |
Neg logit contributions | |
estern | -1.124 |
Sally | -1.087 |
roo | -1.036 |
tons | -1.012 |
puppies | -0.899 |
Token | immer |
Token ID | 10957 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
omial | +4.654 |
unden | +3.474 |
scorer | +3.444 |
usal | +3.440 |
acing | +3.264 |
Neg logit contributions | |
estern | -4.215 |
Sally | -4.104 |
roo | -3.911 |
tons | -3.828 |
puppies | -3.523 |
Token | means |
Token ID | 1724 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
estern | +0.231 |
Sally | +0.224 |
roo | +0.214 |
tons | +0.210 |
puppies | +0.188 |
Neg logit contributions | |
omial | -0.292 |
unden | -0.227 |
scorer | -0.219 |
usal | -0.218 |
anches | -0.207 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
estern | +0.088 |
Sally | +0.086 |
roo | +0.082 |
tons | +0.080 |
puppies | +0.072 |
Neg logit contributions | |
omial | -0.111 |
unden | -0.086 |
usal | -0.084 |
scorer | -0.084 |
anches | -0.079 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
omial | +1.279 |
unden | +0.986 |
scorer | +0.959 |
usal | +0.950 |
anches | +0.894 |
Neg logit contributions | |
estern | -1.067 |
Sally | -1.036 |
roo | -0.993 |
tons | -0.971 |
puppies | -0.875 |
Token | fit |
Token ID | 4197 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
omial | +2.049 |
unden | +1.567 |
scorer | +1.527 |
usal | +1.517 |
anches | +1.426 |
Neg logit contributions | |
estern | -1.747 |
Sally | -1.694 |
roo | -1.619 |
tons | -1.587 |
puppies | -1.438 |
Token | same |
Token ID | 976 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
estern | +0.860 |
Sally | +0.858 |
roo | +0.798 |
tons | +0.793 |
puppies | +0.713 |
Neg logit contributions | |
omial | -1.159 |
unden | -0.901 |
scorer | -0.872 |
usal | -0.870 |
anches | -0.826 |
Token | P |
Token ID | 350 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Sally | +3.332 |
estern | +3.240 |
tons | +3.077 |
roo | +3.028 |
puppies | +2.766 |
Neg logit contributions | |
omial | -4.384 |
unden | -3.358 |
usal | -3.286 |
scorer | -3.227 |
anches | -3.107 |
Token | PP |
Token ID | 10246 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
estern | +1.807 |
Sally | +1.720 |
roo | +1.643 |
tons | +1.620 |
TON | +1.465 |
Neg logit contributions | |
omial | -2.570 |
unden | -2.044 |
scorer | -1.988 |
usal | -1.912 |
exha | -1.859 |
Token | results |
Token ID | 2482 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
estern | +3.874 |
Sally | +3.794 |
roo | +3.591 |
tons | +3.583 |
TON | +3.203 |
Neg logit contributions | |
omial | -4.911 |
unden | -3.833 |
usal | -3.664 |
scorer | -3.656 |
anches | -3.447 |
Token | found |
Token ID | 1043 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
omial | +2.537 |
unden | +1.961 |
scorer | +1.911 |
usal | +1.894 |
anches | +1.784 |
Neg logit contributions | |
estern | -2.088 |
Sally | -2.026 |
roo | -1.933 |
tons | -1.896 |
puppies | -1.704 |
Token | public |
Token ID | 1171 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
omial | +3.103 |
unden | +2.417 |
scorer | +2.373 |
usal | +2.330 |
acing | +2.204 |
Neg logit contributions | |
estern | -2.476 |
Sally | -2.367 |
roo | -2.282 |
tons | -2.228 |
enegger | -1.992 |
Token | support |
Token ID | 1104 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
omial | +1.080 |
unden | +0.809 |
scorer | +0.790 |
usal | +0.780 |
anches | +0.730 |
Neg logit contributions | |
estern | -1.033 |
Sally | -1.010 |
roo | -0.967 |
tons | -0.954 |
puppies | -0.866 |
Token | for |
Token ID | 329 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
estern | +0.911 |
Sally | +0.904 |
roo | +0.856 |
tons | +0.842 |
puppies | +0.757 |
Neg logit contributions | |
omial | -1.283 |
unden | -1.006 |
scorer | -0.970 |
usal | -0.970 |
anches | -0.911 |
Token | the |
Token ID | 262 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
estern | +0.810 |
Sally | +0.783 |
roo | +0.743 |
tons | +0.727 |
puppies | +0.645 |
Neg logit contributions | |
omial | -1.183 |
unden | -0.933 |
scorer | -0.914 |
usal | -0.902 |
anches | -0.856 |
Token | Affordable |
Token ID | 19258 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
estern | +0.432 |
Sally | +0.423 |
roo | +0.400 |
tons | +0.391 |
puppies | +0.350 |
Neg logit contributions | |
omial | -0.614 |
unden | -0.482 |
scorer | -0.468 |
usal | -0.465 |
anches | -0.442 |
Token | Care |
Token ID | 7276 |
Feature activation | +7.77e+00 |
Pos logit contributions | |
Sally | +2.529 |
estern | +2.528 |
roo | +2.341 |
tons | +2.273 |
TON | +1.945 |
Neg logit contributions | |
omial | -5.357 |
unden | -4.516 |
scorer | -4.287 |
usal | -4.270 |
exha | -4.185 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
omial | +0.550 |
unden | +0.429 |
scorer | +0.416 |
usal | +0.413 |
anches | +0.393 |
Neg logit contributions | |
estern | -0.416 |
Sally | -0.404 |
roo | -0.386 |
tons | -0.375 |
puppies | -0.336 |
Token | 's |
Token ID | 338 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Sally | +1.567 |
estern | +1.560 |
roo | +1.472 |
tons | +1.452 |
TON | +1.304 |
Neg logit contributions | |
omial | -1.741 |
unden | -1.406 |
scorer | -1.303 |
exha | -1.286 |
usal | -1.271 |
Token | Play |
Token ID | 3811 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
estern | +1.505 |
Sally | +1.443 |
roo | +1.367 |
tons | +1.330 |
puppies | +1.166 |
Neg logit contributions | |
omial | -2.534 |
unden | -2.029 |
scorer | -1.991 |
usal | -1.969 |
anches | -1.876 |
Token | of |
Token ID | 286 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
omial | +1.869 |
unden | +1.458 |
scorer | +1.418 |
usal | +1.404 |
anches | +1.331 |
Neg logit contributions | |
estern | -1.446 |
Sally | -1.399 |
roo | -1.336 |
tons | -1.305 |
puppies | -1.172 |
Token | a |
Token ID | 257 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
estern | +0.012 |
Sally | +0.011 |
roo | +0.011 |
tons | +0.011 |
puppies | +0.009 |
Neg logit contributions | |
omial | -0.016 |
unden | -0.013 |
scorer | -0.012 |
usal | -0.012 |
anches | -0.012 |
Token | popular |
Token ID | 2968 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
omial | +0.188 |
unden | +0.146 |
scorer | +0.142 |
usal | +0.141 |
anches | +0.134 |
Neg logit contributions | |
estern | -0.144 |
Sally | -0.141 |
roo | -0.134 |
tons | -0.130 |
puppies | -0.117 |
Token | Halo |
Token ID | 18597 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
omial | +2.998 |
unden | +2.317 |
scorer | +2.269 |
usal | +2.239 |
anches | +2.113 |
Neg logit contributions | |
estern | -2.444 |
Sally | -2.360 |
roo | -2.261 |
tons | -2.214 |
puppies | -1.988 |
Token | : |
Token ID | 25 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
omial | +1.445 |
unden | +1.113 |
scorer | +1.083 |
usal | +1.073 |
anches | +1.015 |
Neg logit contributions | |
estern | -1.218 |
Sally | -1.181 |
roo | -1.133 |
tons | -1.107 |
puppies | -0.998 |
Token | Reach |
Token ID | 25146 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
estern | +0.615 |
Sally | +0.593 |
roo | +0.568 |
tons | +0.556 |
puppies | +0.498 |
Neg logit contributions | |
omial | -0.781 |
unden | -0.607 |
scorer | -0.595 |
usal | -0.586 |
anches | -0.554 |
Token | map |
Token ID | 3975 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
omial | +4.061 |
unden | +3.095 |
scorer | +3.043 |
usal | +2.983 |
acing | +2.809 |
Neg logit contributions | |
estern | -3.677 |
Sally | -3.542 |
roo | -3.405 |
tons | -3.342 |
puppies | -3.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
omial | +1.123 |
unden | +0.881 |
scorer | +0.858 |
usal | +0.854 |
anches | +0.811 |
Neg logit contributions | |
estern | -0.796 |
Sally | -0.776 |
roo | -0.737 |
tons | -0.719 |
puppies | -0.641 |
Token | said |
Token ID | 531 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
omial | +2.565 |
unden | +1.985 |
scorer | +1.951 |
usal | +1.920 |
acing | +1.822 |
Neg logit contributions | |
estern | -2.061 |
Sally | -1.982 |
roo | -1.904 |
tons | -1.864 |
puppies | -1.666 |
Token | . |
Token ID | 13 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
omial | +2.150 |
unden | +1.658 |
scorer | +1.634 |
usal | +1.598 |
acing | +1.524 |
Neg logit contributions | |
estern | -1.831 |
Sally | -1.737 |
roo | -1.682 |
tons | -1.656 |
enegger | -1.485 |
Token |
|
Token ID | 198 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
omial | +0.878 |
unden | +0.682 |
scorer | +0.672 |
usal | +0.658 |
acing | +0.631 |
Neg logit contributions | |
estern | -0.669 |
Sally | -0.642 |
roo | -0.613 |
tons | -0.608 |
enegger | -0.541 |
Token |
|
Token ID | 198 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
omial | +0.747 |
unden | +0.607 |
scorer | +0.586 |
usal | +0.578 |
exha | +0.558 |
Neg logit contributions | |
estern | -0.468 |
Sally | -0.452 |
roo | -0.431 |
tons | -0.420 |
TON | -0.369 |
Token | � |
Token ID | 447 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
omial | +0.661 |
unden | +0.511 |
scorer | +0.501 |
usal | +0.493 |
acing | +0.465 |
Neg logit contributions | |
estern | -0.537 |
Sally | -0.518 |
roo | -0.497 |
tons | -0.487 |
TON | -0.436 |
Token | � |
Token ID | 250 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
omial | +0.605 |
unden | +0.460 |
scorer | +0.450 |
usal | +0.443 |
anches | +0.416 |
Neg logit contributions | |
estern | -0.556 |
Sally | -0.538 |
roo | -0.518 |
tons | -0.507 |
puppies | -0.459 |
Token | M |
Token ID | 44 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
omial | +2.776 |
unden | +2.169 |
scorer | +2.133 |
usal | +2.100 |
acing | +1.991 |
Neg logit contributions | |
estern | -2.071 |
Sally | -1.992 |
roo | -1.904 |
tons | -1.860 |
puppies | -1.661 |
Token | itch |
Token ID | 2007 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
estern | +1.686 |
Sally | +1.634 |
roo | +1.587 |
tons | +1.556 |
TON | +1.443 |
Neg logit contributions | |
omial | -1.155 |
unden | -0.799 |
scorer | -0.777 |
usal | -0.753 |
exha | -0.688 |
Token | has |
Token ID | 468 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
estern | +2.062 |
Sally | +1.996 |
roo | +1.916 |
tons | +1.858 |
TON | +1.692 |
Neg logit contributions | |
omial | -2.691 |
unden | -2.074 |
usal | -2.013 |
scorer | -2.010 |
exha | -1.882 |
Token | exce |
Token ID | 43748 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
estern | +0.266 |
Sally | +0.258 |
roo | +0.246 |
tons | +0.242 |
puppies | +0.218 |
Neg logit contributions | |
omial | -0.329 |
unden | -0.252 |
scorer | -0.247 |
usal | -0.245 |
anches | -0.231 |
Token | lled |
Token ID | 3353 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
omial | +4.372 |
unden | +2.868 |
scorer | +2.828 |
usal | +2.774 |
acing | +2.520 |
Neg logit contributions | |
estern | -7.327 |
Sally | -7.130 |
roo | -6.886 |
tons | -6.809 |
enegger | -6.347 |
Token | including |
Token ID | 1390 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
omial | +0.864 |
unden | +0.676 |
scorer | +0.661 |
usal | +0.654 |
anches | +0.619 |
Neg logit contributions | |
estern | -0.630 |
Sally | -0.610 |
roo | -0.580 |
tons | -0.567 |
puppies | -0.506 |
Token | on |
Token ID | 319 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
estern | +1.205 |
Sally | +1.201 |
roo | +1.107 |
tons | +1.094 |
puppies | +0.984 |
Neg logit contributions | |
omial | -1.765 |
unden | -1.377 |
scorer | -1.329 |
usal | -1.323 |
anches | -1.256 |
Token | assault |
Token ID | 4641 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
omial | +0.990 |
unden | +0.765 |
scorer | +0.744 |
usal | +0.735 |
anches | +0.693 |
Neg logit contributions | |
estern | -0.811 |
Sally | -0.794 |
roo | -0.752 |
tons | -0.741 |
puppies | -0.670 |
Token | charges |
Token ID | 4530 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
omial | +2.819 |
unden | +2.176 |
scorer | +2.145 |
usal | +2.111 |
acing | +1.997 |
Neg logit contributions | |
estern | -2.321 |
Sally | -2.218 |
roo | -2.137 |
tons | -2.084 |
enegger | -1.877 |
Token | , |
Token ID | 11 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
omial | +0.218 |
unden | +0.172 |
scorer | +0.168 |
usal | +0.166 |
anches | +0.157 |
Neg logit contributions | |
estern | -0.156 |
Sally | -0.152 |
roo | -0.144 |
tons | -0.141 |
puppies | -0.126 |
Token | according |
Token ID | 1864 |
Feature activation | -7.42e+00 |
Pos logit contributions | |
omial | +0.966 |
unden | +0.750 |
scorer | +0.732 |
usal | +0.725 |
anches | +0.685 |
Neg logit contributions | |
estern | -0.747 |
Sally | -0.726 |
roo | -0.691 |
tons | -0.675 |
puppies | -0.607 |
Token | to |
Token ID | 284 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
omial | +6.725 |
scorer | +5.005 |
usal | +4.898 |
unden | +4.664 |
acing | +4.597 |
Neg logit contributions | |
estern | -7.193 |
Sally | -6.706 |
roo | -6.576 |
tons | -6.446 |
enegger | -6.041 |
Token | the |
Token ID | 262 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
omial | +3.160 |
unden | +2.453 |
scorer | +2.431 |
usal | +2.380 |
acing | +2.259 |
Neg logit contributions | |
estern | -2.538 |
Sally | -2.412 |
roo | -2.339 |
tons | -2.294 |
enegger | -2.053 |
Token | chief |
Token ID | 4039 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
omial | +1.569 |
unden | +1.241 |
scorer | +1.203 |
usal | +1.196 |
anches | +1.139 |
Neg logit contributions | |
estern | -1.017 |
Sally | -1.001 |
roo | -0.939 |
tons | -0.912 |
puppies | -0.819 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
omial | +3.288 |
unden | +2.513 |
scorer | +2.500 |
usal | +2.410 |
acing | +2.329 |
Neg logit contributions | |
estern | -3.098 |
roo | -2.862 |
Sally | -2.850 |
tons | -2.788 |
enegger | -2.514 |
Token |
|
Token ID | 198 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
omial | +1.486 |
unden | +1.161 |
scorer | +1.147 |
usal | +1.133 |
acing | +1.083 |
Neg logit contributions | |
estern | -1.040 |
Sally | -0.986 |
roo | -0.953 |
tons | -0.927 |
puppies | -0.825 |
Token | Texas |
Token ID | 3936 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
omial | +6.363 |
unden | +4.787 |
usal | +4.744 |
scorer | +4.741 |
acing | +4.455 |
Neg logit contributions | |
estern | -5.957 |
Sally | -5.679 |
roo | -5.511 |
tons | -5.409 |
puppies | -4.943 |
Token | . |
Token ID | 13 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
omial | +5.413 |
unden | +4.178 |
scorer | +4.103 |
usal | +4.038 |
anches | +3.880 |
Neg logit contributions | |
estern | -4.552 |
Sally | -4.340 |
roo | -4.200 |
tons | -4.107 |
enegger | -3.681 |
Token | � |
Token ID | 447 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
omial | +0.374 |
unden | +0.295 |
scorer | +0.289 |
usal | +0.285 |
acing | +0.269 |
Neg logit contributions | |
estern | -0.263 |
Sally | -0.255 |
roo | -0.242 |
tons | -0.236 |
puppies | -0.210 |
Token | � |
Token ID | 251 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
omial | +0.174 |
unden | +0.137 |
scorer | +0.135 |
usal | +0.133 |
acing | +0.127 |
Neg logit contributions | |
estern | -0.123 |
Sally | -0.117 |
roo | -0.111 |
tons | -0.109 |
TON | -0.097 |
Token | The |
Token ID | 383 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
estern | +0.055 |
Sally | +0.053 |
roo | +0.050 |
tons | +0.050 |
TON | +0.044 |
Neg logit contributions | |
omial | -0.082 |
unden | -0.065 |
scorer | -0.064 |
usal | -0.063 |
acing | -0.059 |
Token | ob |
Token ID | 909 |
Feature activation | -7.46e+00 |
Pos logit contributions | |
estern | +0.478 |
Sally | +0.474 |
roo | +0.449 |
tons | +0.437 |
puppies | +0.402 |
Neg logit contributions | |
omial | -0.579 |
unden | -0.438 |
scorer | -0.424 |
usal | -0.423 |
anches | -0.394 |
Token | it |
Token ID | 270 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
omial | +6.393 |
usal | +4.588 |
unden | +4.565 |
scorer | +4.553 |
itive | +4.339 |
Neg logit contributions | |
estern | -7.546 |
Sally | -7.266 |
roo | -6.977 |
tons | -6.911 |
TON | -6.394 |
Token | uary |
Token ID | 2838 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
estern | +1.369 |
Sally | +1.338 |
roo | +1.274 |
tons | +1.245 |
puppies | +1.117 |
Neg logit contributions | |
omial | -1.837 |
unden | -1.443 |
scorer | -1.397 |
usal | -1.367 |
exha | -1.305 |
Token | reported |
Token ID | 2098 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
estern | +0.423 |
Sally | +0.419 |
roo | +0.392 |
tons | +0.390 |
puppies | +0.351 |
Neg logit contributions | |
omial | -0.549 |
unden | -0.425 |
usal | -0.410 |
scorer | -0.409 |
anches | -0.387 |
Token | that |
Token ID | 326 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
omial | +4.411 |
unden | +3.421 |
scorer | +3.360 |
usal | +3.284 |
anches | +3.117 |
Neg logit contributions | |
estern | -3.958 |
Sally | -3.726 |
roo | -3.660 |
tons | -3.551 |
enegger | -3.208 |
Token | Danny |
Token ID | 15105 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
omial | +0.851 |
unden | +0.668 |
scorer | +0.656 |
usal | +0.649 |
acing | +0.614 |
Neg logit contributions | |
estern | -0.587 |
Sally | -0.570 |
roo | -0.539 |
tons | -0.529 |
puppies | -0.470 |
Token | who |
Token ID | 508 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
omial | +1.936 |
unden | +1.502 |
scorer | +1.468 |
usal | +1.452 |
anches | +1.371 |
Neg logit contributions | |
estern | -1.516 |
Sally | -1.466 |
roo | -1.396 |
tons | -1.371 |
puppies | -1.229 |
Token | has |
Token ID | 468 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
omial | +1.779 |
unden | +1.392 |
scorer | +1.337 |
usal | +1.333 |
exha | +1.251 |
Neg logit contributions | |
estern | -1.447 |
Sally | -1.408 |
roo | -1.336 |
tons | -1.314 |
puppies | -1.189 |
Token | don |
Token ID | 836 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
estern | +0.217 |
Sally | +0.213 |
roo | +0.200 |
tons | +0.198 |
puppies | +0.180 |
Neg logit contributions | |
omial | -0.294 |
unden | -0.229 |
usal | -0.222 |
scorer | -0.221 |
anches | -0.209 |
Token | ned |
Token ID | 2817 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
omial | +4.699 |
unden | +3.408 |
scorer | +3.358 |
usal | +3.302 |
acing | +3.105 |
Neg logit contributions | |
estern | -5.375 |
Sally | -5.177 |
roo | -5.045 |
tons | -4.904 |
enegger | -4.512 |
Token | the |
Token ID | 262 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
omial | +3.496 |
unden | +2.720 |
scorer | +2.704 |
usal | +2.638 |
acing | +2.505 |
Neg logit contributions | |
estern | -2.708 |
Sally | -2.588 |
roo | -2.523 |
tons | -2.431 |
enegger | -2.191 |
Token | ble |
Token ID | 7245 |
Feature activation | -8.20e+00 |
Pos logit contributions | |
estern | +0.409 |
Sally | +0.399 |
roo | +0.373 |
tons | +0.372 |
puppies | +0.333 |
Neg logit contributions | |
omial | -0.537 |
unden | -0.417 |
scorer | -0.403 |
usal | -0.402 |
anches | -0.383 |
Token | u |
Token ID | 84 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
omial | +7.486 |
usal | +5.668 |
scorer | +5.446 |
unden | +5.335 |
acing | +5.272 |
Neg logit contributions | |
estern | -7.715 |
Sally | -7.435 |
roo | -7.096 |
tons | -6.908 |
enegger | -6.726 |
Token | , |
Token ID | 11 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
estern | +0.991 |
Sally | +0.956 |
roo | +0.911 |
tons | +0.903 |
puppies | +0.803 |
Neg logit contributions | |
omial | -1.278 |
unden | -1.012 |
scorer | -0.979 |
usal | -0.967 |
anches | -0.923 |
Token | bl |
Token ID | 698 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
omial | +0.475 |
unden | +0.372 |
scorer | +0.363 |
usal | +0.361 |
anches | +0.341 |
Neg logit contributions | |
estern | -0.346 |
Sally | -0.336 |
roo | -0.318 |
tons | -0.313 |
puppies | -0.280 |
Token | anc |
Token ID | 1192 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
omial | +9.362 |
usal | +6.773 |
scorer | +6.588 |
anches | +6.513 |
acing | +6.403 |
Neg logit contributions | |
estern | -10.775 |
Sally | -10.729 |
tons | -10.058 |
roo | -9.921 |
enegger | -9.487 |
Token | , |
Token ID | 11 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
omial | +4.533 |
scorer | +3.486 |
unden | +3.465 |
usal | +3.414 |
anches | +3.268 |
Neg logit contributions | |
estern | -3.319 |
Sally | -3.206 |
roo | -3.039 |
tons | -2.989 |
enegger | -2.678 |
Token | ever |
Token ID | 964 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
estern | +1.275 |
Sally | +1.222 |
roo | +1.200 |
tons | +1.169 |
hire | +1.108 |
Neg logit contributions | |
omial | -0.824 |
unden | -0.618 |
scorer | -0.566 |
exha | -0.550 |
usal | -0.529 |
Token | ka |
Token ID | 4914 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
omial | +1.996 |
unden | +1.580 |
scorer | +1.538 |
usal | +1.508 |
exha | +1.434 |
Neg logit contributions | |
estern | -1.488 |
Sally | -1.430 |
roo | -1.375 |
tons | -1.346 |
TON | -1.195 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
omial | +0.179 |
unden | +0.139 |
scorer | +0.136 |
usal | +0.133 |
acing | +0.127 |
Neg logit contributions | |
estern | -0.149 |
Sally | -0.143 |
roo | -0.138 |
tons | -0.136 |
TON | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
omial | +0.154 |
unden | +0.122 |
scorer | +0.119 |
usal | +0.118 |
acing | +0.112 |
Neg logit contributions | |
estern | -0.106 |
Sally | -0.101 |
roo | -0.097 |
tons | -0.095 |
puppies | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
estern | +0.186 |
Sally | +0.183 |
roo | +0.173 |
tons | +0.169 |
TON | +0.149 |
Neg logit contributions | |
omial | -0.319 |
unden | -0.266 |
scorer | -0.252 |
usal | -0.248 |
exha | -0.248 |
Token | Sur |
Token ID | 14214 |
Feature activation | -7.74e+00 |
Pos logit contributions | |
estern | +0.208 |
Sally | +0.203 |
roo | +0.198 |
tons | +0.193 |
TON | +0.175 |
Neg logit contributions | |
omial | -0.300 |
unden | -0.239 |
scorer | -0.232 |
usal | -0.227 |
exha | -0.223 |
Token | ve |
Token ID | 303 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
omial | +6.084 |
unden | +4.180 |
usal | +4.180 |
scorer | +4.172 |
acing | +3.935 |
Neg logit contributions | |
estern | -8.468 |
Sally | -8.161 |
roo | -7.854 |
tons | -7.727 |
puppies | -7.233 |
Token | ying |
Token ID | 1112 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
estern | +2.093 |
Sally | +2.034 |
roo | +1.959 |
tons | +1.907 |
eers | +1.733 |
Neg logit contributions | |
omial | -2.058 |
unden | -1.555 |
scorer | -1.496 |
usal | -1.467 |
exha | -1.374 |
Token | the |
Token ID | 262 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
omial | +1.006 |
unden | +0.777 |
scorer | +0.765 |
usal | +0.757 |
anches | +0.714 |
Neg logit contributions | |
estern | -0.738 |
Sally | -0.725 |
roo | -0.686 |
tons | -0.671 |
puppies | -0.599 |
Token | current |
Token ID | 1459 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
estern | +0.881 |
Sally | +0.880 |
roo | +0.827 |
tons | +0.808 |
puppies | +0.735 |
Neg logit contributions | |
omial | -1.164 |
unden | -0.887 |
scorer | -0.870 |
usal | -0.866 |
anches | -0.817 |
Token | scene |
Token ID | 3715 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
Sally | +3.577 |
estern | +3.491 |
tons | +3.265 |
roo | +3.255 |
puppies | +2.985 |
Neg logit contributions | |
omial | -4.699 |
unden | -3.588 |
usal | -3.533 |
scorer | -3.448 |
anches | -3.349 |
Token | that |
Token ID | 326 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
omial | +0.859 |
unden | +0.663 |
scorer | +0.648 |
usal | +0.639 |
anches | +0.607 |
Neg logit contributions | |
estern | -0.680 |
Sally | -0.666 |
roo | -0.638 |
tons | -0.622 |
puppies | -0.559 |
Token | require |
Token ID | 2421 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
omial | +0.060 |
unden | +0.046 |
scorer | +0.045 |
usal | +0.045 |
anches | +0.042 |
Neg logit contributions | |
estern | -0.047 |
Sally | -0.046 |
roo | -0.044 |
tons | -0.043 |
puppies | -0.039 |
Token | it |
Token ID | 340 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
Sally | +1.001 |
estern | +0.998 |
roo | +0.948 |
tons | +0.945 |
puppies | +0.846 |
Neg logit contributions | |
omial | -1.273 |
unden | -0.991 |
scorer | -0.949 |
usal | -0.942 |
anches | -0.894 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
estern | +0.480 |
Sally | +0.463 |
roo | +0.444 |
tons | +0.434 |
puppies | +0.388 |
Neg logit contributions | |
omial | -0.621 |
unden | -0.484 |
scorer | -0.474 |
usal | -0.467 |
anches | -0.442 |
Token | ' |
Token ID | 705 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
omial | +0.197 |
unden | +0.155 |
scorer | +0.152 |
usal | +0.150 |
anches | +0.142 |
Neg logit contributions | |
estern | -0.143 |
Sally | -0.140 |
roo | -0.133 |
tons | -0.129 |
TON | -0.115 |
Token | Th |
Token ID | 817 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
estern | +0.058 |
Sally | +0.056 |
roo | +0.054 |
tons | +0.053 |
TON | +0.048 |
Neg logit contributions | |
omial | -0.080 |
unden | -0.063 |
scorer | -0.062 |
usal | -0.060 |
exha | -0.058 |
Token | reat |
Token ID | 630 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
omial | +7.010 |
usal | +5.198 |
scorer | +5.156 |
unden | +5.147 |
acing | +4.934 |
Neg logit contributions | |
estern | -6.842 |
Sally | -6.646 |
roo | -6.223 |
tons | -6.207 |
enegger | -5.752 |
Token | defence |
Token ID | 9366 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
omial | +0.689 |
unden | +0.552 |
scorer | +0.541 |
usal | +0.535 |
anches | +0.510 |
Neg logit contributions | |
estern | -0.411 |
Sally | -0.395 |
roo | -0.376 |
tons | -0.365 |
puppies | -0.320 |
Token | ' |
Token ID | 6 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
estern | +2.641 |
Sally | +2.592 |
roo | +2.475 |
tons | +2.405 |
puppies | +2.143 |
Neg logit contributions | |
omial | -4.218 |
unden | -3.376 |
scorer | -3.243 |
usal | -3.216 |
anches | -3.091 |
Token | It |
Token ID | 632 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
estern | +0.969 |
Sally | +0.962 |
roo | +0.912 |
tons | +0.890 |
TON | +0.798 |
Neg logit contributions | |
omial | -1.313 |
unden | -1.020 |
usal | -0.991 |
scorer | -0.990 |
anches | -0.943 |
Token | is |
Token ID | 318 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
estern | +0.993 |
Sally | +0.977 |
roo | +0.932 |
tons | +0.910 |
enegger | +0.816 |
Neg logit contributions | |
omial | -1.232 |
unden | -0.964 |
scorer | -0.928 |
usal | -0.916 |
exha | -0.875 |