Token | and |
Token ID | 290 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
est | +2.233 |
ォ | +2.184 |
anas | +1.938 |
ィ | +1.938 |
itals | +1.878 |
Neg logit contributions | |
ktop | -1.894 |
Groups | -1.867 |
kernels | -1.804 |
targ | -1.678 |
aurus | -1.666 |
Token | other |
Token ID | 584 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
est | +1.762 |
ォ | +1.713 |
anas | +1.503 |
ィ | +1.468 |
itals | +1.450 |
Neg logit contributions | |
ktop | -1.758 |
Groups | -1.728 |
kernels | -1.692 |
aurus | -1.558 |
targ | -1.558 |
Token | offenses |
Token ID | 18514 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
est | +3.212 |
ォ | +3.097 |
anas | +2.762 |
ィ | +2.699 |
itals | +2.670 |
Neg logit contributions | |
ktop | -2.677 |
Groups | -2.603 |
kernels | -2.568 |
targ | -2.376 |
aurus | -2.351 |
Token | , |
Token ID | 11 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
est | +2.059 |
ォ | +2.004 |
anas | +1.785 |
ィ | +1.745 |
itals | +1.717 |
Neg logit contributions | |
ktop | -1.782 |
Groups | -1.774 |
kernels | -1.750 |
targ | -1.609 |
aurus | -1.569 |
Token | and |
Token ID | 290 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
est | +2.722 |
ォ | +2.603 |
anas | +2.338 |
ィ | +2.285 |
itals | +2.250 |
Neg logit contributions | |
ktop | -2.440 |
Groups | -2.371 |
kernels | -2.358 |
targ | -2.176 |
aurus | -2.139 |
Token | nearly |
Token ID | 3016 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ォ | +1.536 |
est | +1.532 |
anas | +1.330 |
ィ | +1.313 |
itals | +1.282 |
Neg logit contributions | |
ktop | -1.466 |
Groups | -1.456 |
kernels | -1.426 |
targ | -1.312 |
aurus | -1.300 |
Token | 200 |
Token ID | 939 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
est | +9.098 |
ォ | +7.748 |
anas | +6.964 |
ィ | +6.926 |
itals | +6.741 |
Neg logit contributions | |
ktop | -12.399 |
Groups | -11.480 |
kernels | -11.295 |
aurus | -10.807 |
Writer | -10.703 |
Token | publishers |
Token ID | 17604 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
est | +1.576 |
ォ | +1.543 |
anas | +1.367 |
ィ | +1.360 |
itals | +1.352 |
Neg logit contributions | |
ktop | -1.227 |
Groups | -1.194 |
kernels | -1.174 |
targ | -1.086 |
aurus | -1.064 |
Token | were |
Token ID | 547 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
Groups | +0.786 |
ktop | +0.781 |
kernels | +0.765 |
targ | +0.702 |
aurus | +0.690 |
Neg logit contributions | |
ォ | -0.982 |
est | -0.961 |
anas | -0.854 |
ィ | -0.844 |
arest | -0.821 |
Token | kicked |
Token ID | 12165 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
est | +2.107 |
ォ | +2.062 |
anas | +1.777 |
ィ | +1.714 |
itals | +1.707 |
Neg logit contributions | |
ktop | -2.633 |
Groups | -2.627 |
kernels | -2.560 |
targ | -2.382 |
aurus | -2.375 |
Token | out |
Token ID | 503 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
est | +3.200 |
ォ | +3.018 |
anas | +2.659 |
ィ | +2.554 |
itals | +2.506 |
Neg logit contributions | |
Groups | -4.244 |
ktop | -4.243 |
kernels | -4.091 |
targ | -3.940 |
Instr | -3.769 |
Token | woes |
Token ID | 34072 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ktop | +0.255 |
Groups | +0.255 |
kernels | +0.245 |
targ | +0.225 |
aurus | +0.222 |
Neg logit contributions | |
ォ | -0.328 |
est | -0.326 |
anas | -0.286 |
ィ | -0.282 |
itals | -0.276 |
Token | , |
Token ID | 11 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Groups | +0.778 |
ktop | +0.773 |
kernels | +0.758 |
targ | +0.704 |
aurus | +0.690 |
Neg logit contributions | |
ォ | -0.788 |
est | -0.776 |
anas | -0.678 |
ィ | -0.668 |
itals | -0.648 |
Token | it |
Token ID | 340 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Groups | +1.215 |
ktop | +1.202 |
kernels | +1.180 |
targ | +1.078 |
aurus | +1.055 |
Neg logit contributions | |
ォ | -1.657 |
est | -1.622 |
anas | -1.448 |
ィ | -1.433 |
itals | -1.395 |
Token | 's |
Token ID | 338 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ktop | +0.387 |
Groups | +0.383 |
kernels | +0.371 |
targ | +0.340 |
aurus | +0.331 |
Neg logit contributions | |
ォ | -0.546 |
est | -0.541 |
anas | -0.481 |
ィ | -0.474 |
arest | -0.465 |
Token | the |
Token ID | 262 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Groups | +0.618 |
ktop | +0.616 |
kernels | +0.603 |
targ | +0.556 |
aurus | +0.547 |
Neg logit contributions | |
ォ | -0.681 |
est | -0.669 |
anas | -0.588 |
ィ | -0.581 |
arest | -0.564 |
Token | nearly |
Token ID | 3016 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
ォ | +0.966 |
est | +0.949 |
anas | +0.830 |
ィ | +0.820 |
arest | +0.799 |
Neg logit contributions | |
ktop | -0.858 |
Groups | -0.850 |
kernels | -0.833 |
targ | -0.767 |
aurus | -0.757 |
Token | universally |
Token ID | 26208 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
est | +9.232 |
ォ | +8.270 |
iverse | +7.193 |
usterity | +7.093 |
anas | +7.034 |
Neg logit contributions | |
ktop | -11.245 |
Groups | -10.942 |
kernels | -10.359 |
aurus | -10.021 |
20439 | -9.951 |
Token | ad |
Token ID | 512 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
est | +5.208 |
ォ | +5.162 |
ィ | +4.254 |
anas | +4.180 |
arest | +4.074 |
Neg logit contributions | |
Groups | -6.007 |
ktop | -5.979 |
kernels | -5.806 |
aurus | -5.409 |
targ | -5.293 |
Token | ored |
Token ID | 1850 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
ォ | +1.365 |
est | +1.352 |
anas | +1.158 |
ィ | +1.128 |
arest | +1.094 |
Neg logit contributions | |
Groups | -1.688 |
ktop | -1.685 |
kernels | -1.652 |
targ | -1.540 |
aurus | -1.520 |
Token | Burger |
Token ID | 28983 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ォ | +1.195 |
est | +1.185 |
anas | +1.030 |
ィ | +1.017 |
arest | +0.986 |
Neg logit contributions | |
ktop | -1.082 |
Groups | -1.062 |
kernels | -1.042 |
targ | -0.956 |
aurus | -0.950 |
Token | Guys |
Token ID | 29899 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Groups | +4.693 |
ktop | +4.371 |
kernels | +4.312 |
aurus | +3.962 |
targ | +3.893 |
Neg logit contributions | |
ォ | -6.315 |
est | -6.109 |
ィ | -5.518 |
anas | -5.501 |
itals | -5.362 |
Token | otherwise |
Token ID | 4306 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ォ | +0.398 |
est | +0.393 |
anas | +0.346 |
ィ | +0.341 |
itals | +0.333 |
Neg logit contributions | |
ktop | -0.344 |
Groups | -0.342 |
kernels | -0.335 |
targ | -0.308 |
aurus | -0.303 |
Token | . |
Token ID | 13 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
est | +2.814 |
ォ | +2.781 |
anas | +2.446 |
ィ | +2.393 |
arest | +2.347 |
Neg logit contributions | |
ktop | -2.455 |
Groups | -2.438 |
kernels | -2.379 |
targ | -2.217 |
aurus | -2.178 |
Token |
|
Token ID | 198 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
est | +3.123 |
ォ | +3.095 |
anas | +2.660 |
ィ | +2.628 |
arest | +2.532 |
Neg logit contributions | |
ktop | -3.400 |
kernels | -3.303 |
Groups | -3.195 |
targ | -3.110 |
aurus | -2.993 |
Token |
|
Token ID | 198 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
ォ | +0.308 |
est | +0.289 |
anas | +0.258 |
ィ | +0.258 |
itals | +0.249 |
Neg logit contributions | |
Groups | -0.316 |
ktop | -0.309 |
kernels | -0.306 |
aurus | -0.280 |
targ | -0.275 |
Token | The |
Token ID | 464 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
est | +1.960 |
ォ | +1.935 |
anas | +1.674 |
ィ | +1.638 |
arest | +1.598 |
Neg logit contributions | |
ktop | -2.122 |
Groups | -2.105 |
kernels | -2.085 |
targ | -1.969 |
aurus | -1.891 |
Token | ONE |
Token ID | 16329 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
est | +2.224 |
ォ | +2.201 |
anas | +1.937 |
ィ | +1.897 |
itals | +1.865 |
Neg logit contributions | |
ktop | -1.913 |
Groups | -1.854 |
kernels | -1.827 |
targ | -1.691 |
aurus | -1.676 |
Token | way |
Token ID | 835 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
est | +10.066 |
ォ | +8.893 |
anas | +8.178 |
arest | +7.963 |
ィ | +7.848 |
Neg logit contributions | |
ktop | -9.703 |
kernels | -9.132 |
Groups | -8.868 |
aurus | -8.319 |
targ | -8.235 |
Token | I |
Token ID | 314 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
est | +3.366 |
ォ | +3.273 |
anas | +2.964 |
ィ | +2.874 |
itals | +2.854 |
Neg logit contributions | |
ktop | -2.852 |
Groups | -2.728 |
kernels | -2.708 |
targ | -2.538 |
aurus | -2.452 |
Token | know |
Token ID | 760 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
est | +3.129 |
ォ | +3.064 |
anas | +2.748 |
ィ | +2.697 |
itals | +2.661 |
Neg logit contributions | |
ktop | -2.310 |
Groups | -2.218 |
kernels | -2.189 |
targ | -2.027 |
aurus | -1.943 |
Token | this |
Token ID | 428 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
est | +7.544 |
ォ | +6.798 |
anas | +6.310 |
itals | +6.141 |
arest | +6.052 |
Neg logit contributions | |
ktop | -7.348 |
kernels | -6.648 |
Groups | -6.619 |
targ | -6.355 |
aurus | -6.263 |
Token | was |
Token ID | 373 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
est | +2.035 |
ォ | +1.988 |
anas | +1.714 |
ィ | +1.665 |
itals | +1.648 |
Neg logit contributions | |
ktop | -2.306 |
Groups | -2.253 |
kernels | -2.210 |
aurus | -2.060 |
targ | -2.053 |
Token | had |
Token ID | 550 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Groups | +0.443 |
ktop | +0.442 |
kernels | +0.430 |
targ | +0.394 |
aurus | +0.389 |
Neg logit contributions | |
ォ | -0.576 |
est | -0.570 |
anas | -0.505 |
ィ | -0.498 |
itals | -0.486 |
Token | been |
Token ID | 587 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Groups | +0.557 |
ktop | +0.557 |
kernels | +0.539 |
targ | +0.502 |
aurus | +0.495 |
Neg logit contributions | |
ォ | -0.605 |
est | -0.605 |
anas | -0.530 |
ィ | -0.521 |
itals | -0.507 |
Token | str |
Token ID | 965 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
Groups | +1.293 |
ktop | +1.287 |
kernels | +1.270 |
targ | +1.182 |
aurus | +1.157 |
Neg logit contributions | |
ォ | -1.189 |
est | -1.141 |
anas | -0.996 |
ィ | -0.991 |
arest | -0.951 |
Token | angled |
Token ID | 22393 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Groups | +0.133 |
ktop | +0.132 |
kernels | +0.129 |
targ | +0.118 |
aurus | +0.115 |
Neg logit contributions | |
ォ | -0.191 |
est | -0.191 |
anas | -0.170 |
ィ | -0.166 |
arest | -0.164 |
Token | and |
Token ID | 290 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
est | +0.680 |
ォ | +0.666 |
anas | +0.595 |
ィ | +0.582 |
itals | +0.570 |
Neg logit contributions | |
Groups | -0.544 |
ktop | -0.536 |
kernels | -0.519 |
targ | -0.478 |
aurus | -0.469 |
Token | sexually |
Token ID | 11363 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
est | +2.495 |
ォ | +2.417 |
anas | +2.107 |
ィ | +2.057 |
itals | +2.055 |
Neg logit contributions | |
Groups | -2.531 |
ktop | -2.510 |
kernels | -2.399 |
targ | -2.237 |
aurus | -2.236 |
Token | assaulted |
Token ID | 18513 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
est | +6.698 |
ォ | +5.009 |
itals | +4.708 |
abused | +4.415 |
nesia | +4.354 |
Neg logit contributions | |
Groups | -12.950 |
20439 | -12.347 |
ktop | -12.343 |
kernels | -12.241 |
Writer | -11.468 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
est | +4.856 |
ォ | +4.381 |
anas | +4.076 |
ィ | +3.882 |
itals | +3.822 |
Neg logit contributions | |
Groups | -4.953 |
ktop | -4.787 |
kernels | -4.691 |
targ | -4.398 |
Instr | -4.332 |
Token | She |
Token ID | 1375 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ォ | +1.118 |
est | +1.101 |
anas | +0.956 |
ィ | +0.950 |
itals | +0.910 |
Neg logit contributions | |
ktop | -1.050 |
kernels | -1.030 |
Groups | -1.023 |
targ | -0.957 |
aurus | -0.927 |
Token | was |
Token ID | 373 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
est | +0.855 |
ォ | +0.851 |
anas | +0.749 |
ィ | +0.736 |
itals | +0.719 |
Neg logit contributions | |
Groups | -0.682 |
ktop | -0.680 |
kernels | -0.653 |
targ | -0.603 |
aurus | -0.591 |
Token | taken |
Token ID | 2077 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
Groups | +0.569 |
ktop | +0.566 |
kernels | +0.556 |
targ | +0.514 |
aurus | +0.506 |
Neg logit contributions | |
ォ | -0.592 |
est | -0.577 |
anas | -0.507 |
ィ | -0.501 |
itals | -0.486 |
Token | he |
Token ID | 339 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
Groups | +1.328 |
ktop | +1.325 |
kernels | +1.291 |
targ | +1.177 |
aurus | +1.154 |
Neg logit contributions | |
ォ | -1.877 |
est | -1.851 |
anas | -1.653 |
ィ | -1.631 |
itals | -1.593 |
Token | was |
Token ID | 373 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
Groups | +0.730 |
ktop | +0.725 |
kernels | +0.710 |
targ | +0.649 |
aurus | +0.638 |
Neg logit contributions | |
ォ | -0.951 |
est | -0.933 |
anas | -0.830 |
ィ | -0.821 |
itals | -0.799 |
Token | t |
Token ID | 256 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
Groups | +0.344 |
ktop | +0.342 |
kernels | +0.336 |
targ | +0.314 |
aurus | +0.310 |
Neg logit contributions | |
ォ | -0.275 |
est | -0.268 |
anas | -0.230 |
ィ | -0.227 |
itals | -0.219 |
Token | aunted |
Token ID | 20227 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ktop | +4.793 |
Groups | +4.772 |
kernels | +4.695 |
aurus | +4.440 |
targ | +4.385 |
Neg logit contributions | |
ォ | -3.324 |
est | -3.057 |
ィ | -2.667 |
anas | -2.642 |
itals | -2.487 |
Token | and |
Token ID | 290 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
est | +5.000 |
ォ | +4.411 |
anas | +4.104 |
ィ | +4.002 |
itals | +3.888 |
Neg logit contributions | |
ktop | -5.320 |
Groups | -5.245 |
kernels | -4.978 |
targ | -4.721 |
aurus | -4.612 |
Token | falsely |
Token ID | 24566 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
est | +2.717 |
ォ | +2.599 |
anas | +2.193 |
ィ | +2.169 |
itals | +2.106 |
Neg logit contributions | |
ktop | -3.744 |
Groups | -3.741 |
kernels | -3.587 |
aurus | -3.323 |
targ | -3.305 |
Token | arrested |
Token ID | 5169 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
est | +7.747 |
ォ | +6.735 |
anas | +5.848 |
acle | +5.580 |
ィ | +5.497 |
Neg logit contributions | |
Groups | -11.536 |
ktop | -11.476 |
kernels | -10.798 |
vg | -10.424 |
20439 | -10.220 |
Token | by |
Token ID | 416 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
est | +2.932 |
ォ | +2.750 |
anas | +2.495 |
ィ | +2.443 |
itals | +2.341 |
Neg logit contributions | |
Groups | -2.890 |
ktop | -2.885 |
kernels | -2.789 |
targ | -2.606 |
aurus | -2.524 |
Token | police |
Token ID | 1644 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
est | +1.839 |
ォ | +1.796 |
anas | +1.593 |
ィ | +1.545 |
itals | +1.539 |
Neg logit contributions | |
ktop | -1.521 |
Groups | -1.472 |
kernels | -1.450 |
targ | -1.325 |
aurus | -1.296 |
Token | officers |
Token ID | 3790 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
est | +1.586 |
ォ | +1.541 |
anas | +1.368 |
ィ | +1.324 |
itals | +1.295 |
Neg logit contributions | |
ktop | -1.487 |
Groups | -1.474 |
kernels | -1.437 |
targ | -1.330 |
aurus | -1.302 |
Token | after |
Token ID | 706 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
est | +1.279 |
ォ | +1.255 |
anas | +1.107 |
ィ | +1.074 |
itals | +1.047 |
Neg logit contributions | |
Groups | -1.230 |
ktop | -1.221 |
kernels | -1.197 |
targ | -1.105 |
aurus | -1.077 |
Token | violating |
Token ID | 18134 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
Groups | +0.539 |
ktop | +0.536 |
kernels | +0.526 |
targ | +0.487 |
aurus | +0.479 |
Neg logit contributions | |
ォ | -0.565 |
est | -0.553 |
anas | -0.486 |
ィ | -0.480 |
itals | -0.465 |
Token | our |
Token ID | 674 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
est | +1.674 |
ォ | +1.619 |
anas | +1.426 |
ィ | +1.370 |
arest | +1.365 |
Neg logit contributions | |
ktop | -1.838 |
Groups | -1.778 |
kernels | -1.760 |
targ | -1.644 |
aurus | -1.640 |
Token | policies |
Token ID | 4788 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
est | +3.027 |
ォ | +2.923 |
anas | +2.578 |
ィ | +2.538 |
arest | +2.504 |
Neg logit contributions | |
ktop | -2.700 |
kernels | -2.566 |
Groups | -2.560 |
aurus | -2.387 |
targ | -2.378 |
Token | , |
Token ID | 11 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
est | +3.437 |
ォ | +3.298 |
anas | +2.916 |
ィ | +2.895 |
arest | +2.790 |
Neg logit contributions | |
Groups | -3.190 |
ktop | -3.183 |
kernels | -3.146 |
targ | -2.881 |
aurus | -2.813 |
Token | both |
Token ID | 1111 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
est | +1.585 |
ォ | +1.563 |
anas | +1.380 |
ィ | +1.350 |
itals | +1.326 |
Neg logit contributions | |
ktop | -1.376 |
Groups | -1.353 |
kernels | -1.325 |
targ | -1.218 |
aurus | -1.214 |
Token | misrepresent |
Token ID | 26521 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
est | +1.679 |
ォ | +1.648 |
anas | +1.467 |
ィ | +1.441 |
itals | +1.412 |
Neg logit contributions | |
ktop | -1.512 |
Groups | -1.489 |
kernels | -1.460 |
targ | -1.346 |
aurus | -1.335 |
Token | ation |
Token ID | 341 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
est | +6.658 |
ォ | +5.730 |
anas | +5.150 |
acle | +4.866 |
ィ | +4.778 |
Neg logit contributions | |
ktop | -11.937 |
Groups | -11.383 |
kernels | -11.345 |
targ | -10.994 |
enthusi | -10.813 |
Token | and |
Token ID | 290 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
est | +2.233 |
ォ | +2.184 |
anas | +1.938 |
ィ | +1.938 |
itals | +1.878 |
Neg logit contributions | |
ktop | -1.894 |
Groups | -1.867 |
kernels | -1.804 |
targ | -1.678 |
aurus | -1.666 |
Token | other |
Token ID | 584 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
est | +1.762 |
ォ | +1.713 |
anas | +1.503 |
ィ | +1.468 |
itals | +1.450 |
Neg logit contributions | |
ktop | -1.758 |
Groups | -1.728 |
kernels | -1.692 |
aurus | -1.558 |
targ | -1.558 |
Token | offenses |
Token ID | 18514 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
est | +3.212 |
ォ | +3.097 |
anas | +2.762 |
ィ | +2.699 |
itals | +2.670 |
Neg logit contributions | |
ktop | -2.677 |
Groups | -2.603 |
kernels | -2.568 |
targ | -2.376 |
aurus | -2.351 |
Token | , |
Token ID | 11 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
est | +2.059 |
ォ | +2.004 |
anas | +1.785 |
ィ | +1.745 |
itals | +1.717 |
Neg logit contributions | |
ktop | -1.782 |
Groups | -1.774 |
kernels | -1.750 |
targ | -1.609 |
aurus | -1.569 |
Token | city |
Token ID | 1748 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Groups | +0.149 |
ktop | +0.149 |
kernels | +0.146 |
targ | +0.134 |
aurus | +0.132 |
Neg logit contributions | |
ォ | -0.178 |
est | -0.175 |
anas | -0.154 |
ィ | -0.153 |
arest | -0.149 |
Token | manager |
Token ID | 4706 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
ォ | +0.809 |
est | +0.806 |
anas | +0.707 |
ィ | +0.705 |
arest | +0.682 |
Neg logit contributions | |
ktop | -0.676 |
Groups | -0.668 |
kernels | -0.652 |
targ | -0.601 |
aurus | -0.593 |
Token | , |
Token ID | 11 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
est | +2.467 |
ォ | +2.459 |
anas | +2.144 |
ィ | +2.143 |
arest | +2.057 |
Neg logit contributions | |
ktop | -2.259 |
Groups | -2.231 |
kernels | -2.189 |
targ | -2.022 |
aurus | -1.992 |
Token | is |
Token ID | 318 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
est | +3.157 |
ォ | +3.103 |
anas | +2.723 |
ィ | +2.665 |
arest | +2.635 |
Neg logit contributions | |
ktop | -2.896 |
Groups | -2.850 |
kernels | -2.818 |
aurus | -2.588 |
targ | -2.579 |
Token | the |
Token ID | 262 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
est | +5.690 |
ォ | +5.397 |
anas | +4.830 |
ィ | +4.696 |
arest | +4.684 |
Neg logit contributions | |
ktop | -5.165 |
Groups | -5.079 |
kernels | -5.006 |
targ | -4.598 |
aurus | -4.571 |
Token | one |
Token ID | 530 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
est | +2.083 |
ォ | +2.045 |
anas | +1.784 |
ィ | +1.776 |
arest | +1.741 |
Neg logit contributions | |
ktop | -1.852 |
Groups | -1.801 |
kernels | -1.770 |
targ | -1.613 |
aurus | -1.613 |
Token | common |
Token ID | 2219 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
est | +9.059 |
ォ | +7.544 |
arest | +6.815 |
anas | +6.680 |
ィ | +6.672 |
Neg logit contributions | |
ktop | -9.670 |
Groups | -9.450 |
kernels | -9.341 |
aurus | -8.624 |
targ | -8.583 |
Token | factor |
Token ID | 5766 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
est | +2.705 |
ォ | +2.631 |
anas | +2.262 |
ィ | +2.261 |
arest | +2.189 |
Neg logit contributions | |
ktop | -2.584 |
Groups | -2.581 |
kernels | -2.504 |
aurus | -2.288 |
targ | -2.283 |
Token | through |
Token ID | 832 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
est | +2.249 |
ォ | +2.222 |
anas | +1.954 |
ィ | +1.927 |
arest | +1.879 |
Neg logit contributions | |
ktop | -1.917 |
Groups | -1.891 |
kernels | -1.862 |
targ | -1.719 |
aurus | -1.683 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ォ | +1.093 |
est | +1.081 |
anas | +0.934 |
ィ | +0.921 |
arest | +0.897 |
Neg logit contributions | |
Groups | -1.114 |
ktop | -1.109 |
kernels | -1.090 |
targ | -1.011 |
aurus | -0.998 |
Token | many |
Token ID | 867 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
Groups | +0.522 |
ktop | +0.517 |
kernels | +0.508 |
targ | +0.467 |
aurus | +0.458 |
Neg logit contributions | |
ォ | -0.615 |
est | -0.601 |
anas | -0.533 |
ィ | -0.527 |
itals | -0.513 |
Token | who |
Token ID | 508 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
est | +2.021 |
ォ | +1.979 |
anas | +1.719 |
ィ | +1.692 |
arest | +1.657 |
Neg logit contributions | |
Groups | -2.058 |
ktop | -2.051 |
kernels | -1.989 |
targ | -1.860 |
aurus | -1.808 |
Token | was |
Token ID | 373 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
est | +1.080 |
ォ | +1.078 |
anas | +0.936 |
ィ | +0.926 |
itals | +0.896 |
Neg logit contributions | |
Groups | -1.056 |
ktop | -1.052 |
kernels | -1.016 |
targ | -0.948 |
aurus | -0.932 |
Token | imprisoned |
Token ID | 21125 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Groups | +0.109 |
ktop | +0.109 |
kernels | +0.106 |
targ | +0.099 |
aurus | +0.097 |
Neg logit contributions | |
ォ | -0.101 |
est | -0.100 |
anas | -0.087 |
ィ | -0.085 |
arest | -0.083 |
Token | after |
Token ID | 706 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
est | +1.180 |
ォ | +1.154 |
anas | +1.024 |
ィ | +1.005 |
itals | +0.976 |
Neg logit contributions | |
Groups | -1.073 |
ktop | -1.065 |
kernels | -1.038 |
targ | -0.960 |
aurus | -0.944 |
Token | authorities |
Token ID | 4773 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Groups | +1.217 |
ktop | +1.211 |
kernels | +1.185 |
targ | +1.089 |
aurus | +1.070 |
Neg logit contributions | |
ォ | -1.465 |
est | -1.442 |
anas | -1.274 |
ィ | -1.258 |
itals | -1.225 |
Token | falsely |
Token ID | 24566 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
Groups | +0.718 |
ktop | +0.713 |
kernels | +0.700 |
targ | +0.648 |
aurus | +0.638 |
Neg logit contributions | |
ォ | -0.718 |
est | -0.704 |
anas | -0.615 |
ィ | -0.607 |
itals | -0.588 |
Token | identified |
Token ID | 5174 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
est | +7.978 |
ォ | +7.138 |
anas | +5.985 |
ィ | +5.817 |
acle | +5.702 |
Neg logit contributions | |
Groups | -10.900 |
ktop | -10.841 |
kernels | -10.353 |
vg | -9.831 |
aurus | -9.541 |
Token | him |
Token ID | 683 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
est | +4.138 |
ォ | +3.914 |
anas | +3.537 |
ィ | +3.391 |
itals | +3.336 |
Neg logit contributions | |
ktop | -4.573 |
Groups | -4.385 |
kernels | -4.238 |
targ | -4.041 |
aurus | -3.998 |
Token | as |
Token ID | 355 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
est | +0.797 |
ォ | +0.789 |
anas | +0.682 |
ィ | +0.675 |
itals | +0.648 |
Neg logit contributions | |
Groups | -0.839 |
ktop | -0.831 |
kernels | -0.811 |
targ | -0.757 |
aurus | -0.739 |
Token | an |
Token ID | 281 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Groups | +2.527 |
ktop | +2.487 |
kernels | +2.449 |
targ | +2.242 |
aurus | +2.203 |
Neg logit contributions | |
ォ | -3.573 |
est | -3.479 |
anas | -3.115 |
ィ | -3.094 |
itals | -3.012 |
Token | illegal |
Token ID | 5293 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Groups | +0.574 |
ktop | +0.573 |
kernels | +0.561 |
targ | +0.517 |
aurus | +0.509 |
Neg logit contributions | |
ォ | -0.592 |
est | -0.590 |
anas | -0.517 |
ィ | -0.504 |
itals | -0.491 |
Token | during |
Token ID | 1141 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Groups | +1.341 |
ktop | +1.335 |
kernels | +1.311 |
targ | +1.206 |
aurus | +1.185 |
Neg logit contributions | |
ォ | -1.519 |
est | -1.471 |
anas | -1.303 |
ィ | -1.293 |
arest | -1.255 |
Token | World |
Token ID | 2159 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
est | +0.593 |
ォ | +0.592 |
anas | +0.512 |
ィ | +0.497 |
itals | +0.493 |
Neg logit contributions | |
ktop | -0.517 |
Groups | -0.510 |
kernels | -0.498 |
targ | -0.457 |
aurus | -0.455 |
Token | War |
Token ID | 1810 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
Groups | +0.678 |
ktop | +0.659 |
kernels | +0.647 |
targ | +0.589 |
aurus | +0.584 |
Neg logit contributions | |
ォ | -0.794 |
est | -0.762 |
anas | -0.684 |
ィ | -0.681 |
itals | -0.658 |
Token | II |
Token ID | 2873 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
Groups | +1.805 |
ktop | +1.792 |
kernels | +1.754 |
targ | +1.595 |
aurus | +1.564 |
Neg logit contributions | |
ォ | -2.602 |
est | -2.554 |
anas | -2.284 |
ィ | -2.260 |
itals | -2.203 |
Token | . |
Token ID | 13 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
Groups | +2.026 |
ktop | +2.007 |
kernels | +1.975 |
targ | +1.795 |
aurus | +1.766 |
Neg logit contributions | |
ォ | -2.715 |
est | -2.635 |
anas | -2.357 |
ィ | -2.340 |
itals | -2.271 |
Token | Nearly |
Token ID | 21233 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
est | +2.498 |
ォ | +2.488 |
ィ | +2.142 |
anas | +2.126 |
arest | +2.030 |
Neg logit contributions | |
ktop | -2.672 |
kernels | -2.589 |
Groups | -2.459 |
targ | -2.440 |
enthusi | -2.333 |
Token | 400 |
Token ID | 7337 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
est | +7.975 |
ォ | +6.600 |
anas | +6.300 |
ィ | +5.960 |
itals | +5.950 |
Neg logit contributions | |
ktop | -10.650 |
Groups | -9.938 |
kernels | -9.659 |
aurus | -9.411 |
gart | -9.395 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
Groups | +0.759 |
ktop | +0.758 |
kernels | +0.741 |
targ | +0.687 |
aurus | +0.676 |
Neg logit contributions | |
ォ | -0.795 |
est | -0.781 |
anas | -0.684 |
ィ | -0.676 |
itals | -0.656 |
Token | 000 |
Token ID | 830 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
Groups | +0.055 |
ktop | +0.054 |
kernels | +0.053 |
aurus | +0.047 |
targ | +0.046 |
Neg logit contributions | |
ォ | -0.091 |
est | -0.087 |
anas | -0.079 |
ィ | -0.079 |
itals | -0.077 |
Token | others |
Token ID | 1854 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Groups | +1.794 |
ktop | +1.774 |
kernels | +1.749 |
targ | +1.591 |
aurus | +1.562 |
Neg logit contributions | |
ォ | -2.353 |
est | -2.294 |
anas | -2.048 |
ィ | -2.026 |
arest | -1.976 |
Token | have |
Token ID | 423 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
est | +0.976 |
ォ | +0.972 |
anas | +0.853 |
ィ | +0.837 |
itals | +0.827 |
Neg logit contributions | |
Groups | -0.820 |
ktop | -0.818 |
kernels | -0.793 |
targ | -0.741 |
aurus | -0.717 |
Token | , |
Token ID | 11 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
ォ | +0.641 |
est | +0.640 |
anas | +0.564 |
ィ | +0.550 |
itals | +0.536 |
Neg logit contributions | |
Groups | -0.537 |
ktop | -0.536 |
kernels | -0.521 |
targ | -0.478 |
aurus | -0.472 |
Token | specifically |
Token ID | 5734 |
Feature activation | -9.95e-02 |
Pos logit contributions | |
est | +0.248 |
ォ | +0.247 |
anas | +0.217 |
ィ | +0.213 |
itals | +0.209 |
Neg logit contributions | |
ktop | -0.210 |
Groups | -0.209 |
kernels | -0.205 |
targ | -0.188 |
aurus | -0.185 |
Token | concerning |
Token ID | 9305 |
Feature activation | -8.82e-03 |
Pos logit contributions | |
ktop | +0.379 |
Groups | +0.377 |
kernels | +0.371 |
targ | +0.337 |
aurus | +0.334 |
Neg logit contributions | |
ォ | -0.451 |
est | -0.447 |
anas | -0.393 |
ィ | -0.388 |
itals | -0.379 |
Token | " |
Token ID | 366 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
ktop | +0.033 |
Groups | +0.032 |
kernels | +0.032 |
targ | +0.029 |
aurus | +0.029 |
Neg logit contributions | |
ォ | -0.041 |
est | -0.041 |
anas | -0.036 |
ィ | -0.035 |
itals | -0.035 |
Token | mis |
Token ID | 25413 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
est | +3.380 |
ォ | +3.249 |
anas | +2.900 |
ィ | +2.841 |
itals | +2.762 |
Neg logit contributions | |
ktop | -3.075 |
Groups | -3.068 |
kernels | -3.018 |
targ | -2.773 |
aurus | -2.734 |
Token | represent |
Token ID | 15603 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
est | +7.189 |
ォ | +6.675 |
anas | +5.825 |
ィ | +5.588 |
itals | +5.541 |
Neg logit contributions | |
Groups | -7.832 |
ktop | -7.829 |
kernels | -7.766 |
targ | -7.108 |
slic | -7.044 |
Token | ations |
Token ID | 602 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
est | +8.119 |
ォ | +7.142 |
anas | +6.706 |
itals | +6.311 |
ィ | +6.269 |
Neg logit contributions | |
ktop | -10.379 |
kernels | -9.904 |
Groups | -9.607 |
targ | -9.414 |
enthusi | -9.076 |
Token | " |
Token ID | 1 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
est | +4.499 |
ォ | +4.320 |
ィ | +3.896 |
anas | +3.806 |
itals | +3.727 |
Neg logit contributions | |
ktop | -4.327 |
Groups | -4.305 |
kernels | -4.227 |
targ | -3.896 |
vg | -3.735 |
Token | made |
Token ID | 925 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
est | +0.794 |
ォ | +0.788 |
anas | +0.694 |
ィ | +0.689 |
itals | +0.668 |
Neg logit contributions | |
ktop | -0.716 |
Groups | -0.713 |
kernels | -0.698 |
targ | -0.641 |
aurus | -0.629 |
Token | to |
Token ID | 284 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
est | +4.247 |
ォ | +3.988 |
ィ | +3.592 |
anas | +3.575 |
arest | +3.385 |
Neg logit contributions | |
ktop | -4.235 |
Groups | -4.221 |
kernels | -4.105 |
targ | -3.798 |
aurus | -3.696 |
Token | the |
Token ID | 262 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
est | +2.309 |
ォ | +2.259 |
anas | +2.016 |
ィ | +1.994 |
itals | +1.967 |
Neg logit contributions | |
ktop | -1.954 |
kernels | -1.892 |
Groups | -1.879 |
aurus | -1.703 |
targ | -1.697 |
Token | men |
Token ID | 1450 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
est | +1.651 |
ォ | +1.631 |
anas | +1.421 |
ィ | +1.376 |
arest | +1.370 |
Neg logit contributions | |
ktop | -1.555 |
Groups | -1.539 |
kernels | -1.486 |
aurus | -1.393 |
targ | -1.390 |
Token | who |
Token ID | 508 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
est | +2.272 |
ォ | +2.214 |
anas | +1.942 |
ィ | +1.895 |
arest | +1.874 |
Neg logit contributions | |
Groups | -2.042 |
ktop | -2.029 |
kernels | -1.993 |
targ | -1.824 |
aurus | -1.770 |
Token | cat |
Token ID | 3797 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
ォ | +1.432 |
est | +1.424 |
anas | +1.242 |
ィ | +1.221 |
arest | +1.189 |
Neg logit contributions | |
Groups | -1.377 |
ktop | -1.373 |
kernels | -1.338 |
targ | -1.234 |
aurus | -1.213 |
Token | call |
Token ID | 13345 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Groups | +2.416 |
ktop | +2.391 |
kernels | +2.358 |
targ | +2.190 |
aurus | +2.153 |
Neg logit contributions | |
ォ | -2.386 |
est | -2.317 |
anas | -2.030 |
ィ | -2.009 |
itals | -1.944 |
Token | and |
Token ID | 290 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
est | +5.249 |
ォ | +4.866 |
anas | +4.526 |
ィ | +4.273 |
itals | +4.253 |
Neg logit contributions | |
ktop | -4.705 |
Groups | -4.668 |
kernels | -4.565 |
targ | -4.218 |
aurus | -4.075 |
Token | harass |
Token ID | 7671 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
est | +4.181 |
ォ | +4.019 |
anas | +3.563 |
ィ | +3.463 |
arest | +3.457 |
Neg logit contributions | |
ktop | -3.710 |
Groups | -3.671 |
kernels | -3.551 |
aurus | -3.229 |
targ | -3.223 |
Token | her |
Token ID | 607 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
est | +9.499 |
ォ | +8.195 |
anas | +7.729 |
ィ | +7.246 |
arest | +7.241 |
Neg logit contributions | |
ktop | -8.706 |
Groups | -8.499 |
kernels | -8.363 |
targ | -7.841 |
aurus | -7.684 |
Token | on |
Token ID | 319 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
est | +4.949 |
ォ | +4.582 |
anas | +4.149 |
itals | +4.011 |
ィ | +3.988 |
Neg logit contributions | |
ktop | -4.921 |
Groups | -4.824 |
kernels | -4.660 |
aurus | -4.420 |
targ | -4.330 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Groups | +0.572 |
ktop | +0.570 |
kernels | +0.558 |
targ | +0.512 |
aurus | +0.506 |
Neg logit contributions | |
est | -0.742 |
ォ | -0.738 |
anas | -0.655 |
ィ | -0.636 |
itals | -0.633 |
Token | street |
Token ID | 4675 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
est | +0.603 |
ォ | +0.601 |
anas | +0.526 |
ィ | +0.509 |
arest | +0.505 |
Neg logit contributions | |
ktop | -0.567 |
Groups | -0.566 |
kernels | -0.555 |
targ | -0.512 |
aurus | -0.510 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Groups | +0.217 |
ktop | +0.215 |
kernels | +0.211 |
targ | +0.195 |
aurus | +0.190 |
Neg logit contributions | |
ォ | -0.264 |
est | -0.262 |
anas | -0.231 |
ィ | -0.228 |
itals | -0.222 |
Token | damage |
Token ID | 2465 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
ォ | +0.995 |
est | +0.993 |
anas | +0.874 |
ィ | +0.853 |
itals | +0.835 |
Neg logit contributions | |
ktop | -0.832 |
Groups | -0.827 |
kernels | -0.797 |
targ | -0.744 |
aurus | -0.736 |
Token | we |
Token ID | 356 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
est | +1.503 |
ォ | +1.481 |
anas | +1.319 |
ィ | +1.272 |
itals | +1.238 |
Neg logit contributions | |
ktop | -1.318 |
Groups | -1.299 |
kernels | -1.253 |
targ | -1.170 |
aurus | -1.149 |
Token | are |
Token ID | 389 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
est | +3.731 |
ォ | +3.654 |
anas | +3.230 |
ィ | +3.167 |
itals | +3.136 |
Neg logit contributions | |
ktop | -3.242 |
Groups | -3.197 |
kernels | -3.075 |
targ | -2.876 |
Writer | -2.739 |
Token | unconsciously |
Token ID | 48570 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
est | +5.430 |
ォ | +4.952 |
anas | +4.388 |
arest | +4.311 |
itals | +4.308 |
Neg logit contributions | |
ktop | -6.483 |
Groups | -6.465 |
kernels | -6.207 |
targ | -5.893 |
aurus | -5.741 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
est | +8.085 |
ォ | +7.166 |
anas | +6.231 |
nesia | +6.228 |
arest | +6.146 |
Neg logit contributions | |
Groups | -9.413 |
ktop | -9.309 |
kernels | -8.764 |
aurus | -8.456 |
targ | -8.223 |
Token | consciously |
Token ID | 30410 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
est | +5.821 |
ォ | +5.160 |
anas | +4.691 |
itals | +4.592 |
acle | +4.572 |
Neg logit contributions | |
Groups | -6.361 |
ktop | -6.303 |
kernels | -5.936 |
targ | -5.682 |
aurus | -5.659 |
Token | causing |
Token ID | 6666 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
est | +8.215 |
ォ | +7.679 |
anas | +6.460 |
nesia | +6.429 |
ィ | +6.353 |
Neg logit contributions | |
Groups | -9.860 |
ktop | -9.590 |
kernels | -9.159 |
aurus | -8.679 |
vg | -8.607 |
Token | to |
Token ID | 284 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
est | +4.038 |
ォ | +3.921 |
anas | +3.493 |
ィ | +3.395 |
nesia | +3.298 |
Neg logit contributions | |
ktop | -3.298 |
Groups | -3.278 |
kernels | -3.174 |
targ | -3.000 |
aurus | -2.894 |
Token | the |
Token ID | 262 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
est | +2.758 |
ォ | +2.738 |
anas | +2.398 |
ィ | +2.341 |
itals | +2.286 |
Neg logit contributions | |
ktop | -2.558 |
Groups | -2.544 |
kernels | -2.465 |
targ | -2.347 |
aurus | -2.284 |
Token | ocean |
Token ID | 9151 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
est | +3.333 |
ォ | +3.239 |
anas | +2.896 |
ィ | +2.807 |
itals | +2.792 |
Neg logit contributions | |
ktop | -2.586 |
Groups | -2.570 |
kernels | -2.437 |
aurus | -2.325 |
targ | -2.295 |
Token | . |
Token ID | 13 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
est | +3.489 |
ォ | +3.439 |
anas | +3.014 |
ィ | +2.961 |
itals | +2.944 |
Neg logit contributions | |
ktop | -3.232 |
Groups | -3.171 |
kernels | -3.038 |
targ | -2.898 |
aurus | -2.838 |
Token | � |
Token ID | 447 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Groups | +0.329 |
ktop | +0.327 |
kernels | +0.320 |
targ | +0.295 |
aurus | +0.290 |
Neg logit contributions | |
ォ | -0.370 |
est | -0.364 |
anas | -0.320 |
ィ | -0.317 |
itals | -0.308 |
Token | � |
Token ID | 250 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
ォ | +1.317 |
est | +1.287 |
anas | +1.117 |
ィ | +1.103 |
itals | +1.067 |
Neg logit contributions | |
Groups | -1.443 |
ktop | -1.436 |
kernels | -1.411 |
targ | -1.314 |
aurus | -1.292 |
Token | ; |
Token ID | 26 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Groups | +1.640 |
ktop | +1.626 |
kernels | +1.599 |
targ | +1.474 |
aurus | +1.448 |
Neg logit contributions | |
ォ | -1.941 |
est | -1.892 |
anas | -1.681 |
ィ | -1.663 |
arest | -1.616 |
Token | a |
Token ID | 257 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
est | +1.172 |
ォ | +1.157 |
anas | +1.013 |
ィ | +1.004 |
itals | +0.976 |
Neg logit contributions | |
ktop | -0.981 |
Groups | -0.950 |
kernels | -0.924 |
targ | -0.849 |
aurus | -0.834 |
Token | tweet |
Token ID | 6126 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
est | +2.574 |
ォ | +2.552 |
anas | +2.227 |
ィ | +2.218 |
itals | +2.150 |
Neg logit contributions | |
ktop | -2.040 |
Groups | -1.987 |
kernels | -1.929 |
targ | -1.737 |
aurus | -1.721 |
Token | falsely |
Token ID | 24566 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
est | +4.734 |
ォ | +4.532 |
anas | +3.891 |
ィ | +3.848 |
itals | +3.755 |
Neg logit contributions | |
ktop | -4.479 |
Groups | -4.449 |
kernels | -4.219 |
targ | -3.878 |
aurus | -3.778 |
Token | stating |
Token ID | 12316 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
est | +8.899 |
ォ | +7.857 |
anas | +6.833 |
ィ | +6.546 |
nesia | +6.400 |
Neg logit contributions | |
ktop | -9.655 |
Groups | -9.463 |
kernels | -8.916 |
aurus | -8.275 |
vg | -8.246 |
Token | that |
Token ID | 326 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
est | +1.742 |
ォ | +1.726 |
ィ | +1.520 |
anas | +1.497 |
itals | +1.462 |
Neg logit contributions | |
ktop | -1.400 |
Groups | -1.336 |
kernels | -1.308 |
aurus | -1.200 |
targ | -1.197 |
Token | Donald |
Token ID | 3759 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
est | +1.260 |
ォ | +1.246 |
anas | +1.102 |
ィ | +1.089 |
itals | +1.056 |
Neg logit contributions | |
ktop | -1.098 |
Groups | -1.049 |
kernels | -1.030 |
aurus | -0.951 |
targ | -0.949 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ktop | +0.295 |
Groups | +0.292 |
kernels | +0.285 |
targ | +0.259 |
aurus | +0.254 |
Neg logit contributions | |
ォ | -0.421 |
est | -0.419 |
anas | -0.369 |
ィ | -0.368 |
arest | -0.356 |
Token | survived |
Token ID | 11803 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
ktop | +0.677 |
Groups | +0.677 |
kernels | +0.660 |
targ | +0.608 |
aurus | +0.598 |
Neg logit contributions | |
ォ | -0.787 |
est | -0.773 |
anas | -0.681 |
ィ | -0.676 |
itals | -0.656 |
Token | press |
Token ID | 1803 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Groups | +0.551 |
ktop | +0.550 |
kernels | +0.539 |
targ | +0.497 |
aurus | +0.488 |
Neg logit contributions | |
est | -0.624 |
ォ | -0.624 |
anas | -0.547 |
ィ | -0.538 |
itals | -0.524 |
Token | release |
Token ID | 2650 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
est | +1.190 |
ォ | +1.172 |
ィ | +1.029 |
anas | +1.027 |
itals | +0.993 |
Neg logit contributions | |
ktop | -0.819 |
Groups | -0.813 |
kernels | -0.785 |
targ | -0.721 |
aurus | -0.702 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Groups | +0.180 |
ktop | +0.179 |
kernels | +0.175 |
targ | +0.160 |
aurus | +0.157 |
Neg logit contributions | |
ォ | -0.217 |
est | -0.216 |
anas | -0.188 |
ィ | -0.187 |
arest | -0.181 |
Token | � |
Token ID | 564 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
ォ | +0.761 |
est | +0.758 |
ィ | +0.644 |
anas | +0.642 |
arest | +0.614 |
Neg logit contributions | |
ktop | -0.867 |
kernels | -0.851 |
Groups | -0.833 |
targ | -0.798 |
aurus | -0.768 |
Token | � |
Token ID | 250 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
ktop | +0.151 |
Groups | +0.149 |
kernels | +0.147 |
targ | +0.137 |
aurus | +0.134 |
Neg logit contributions | |
ォ | -0.143 |
est | -0.140 |
ィ | -0.121 |
anas | -0.121 |
arest | -0.116 |
Token | Almost |
Token ID | 23379 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Groups | +1.892 |
ktop | +1.849 |
kernels | +1.820 |
targ | +1.677 |
aurus | +1.667 |
Neg logit contributions | |
ォ | -1.926 |
est | -1.866 |
anas | -1.651 |
ィ | -1.622 |
itals | -1.583 |
Token | half |
Token ID | 2063 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
est | +7.945 |
ォ | +6.628 |
ィ | +6.102 |
anas | +6.062 |
itals | +5.752 |
Neg logit contributions | |
ktop | -10.328 |
Groups | -9.604 |
kernels | -9.511 |
gart | -9.135 |
targ | -9.085 |
Token | of |
Token ID | 286 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
est | +3.370 |
ォ | +3.359 |
ィ | +2.935 |
anas | +2.892 |
arest | +2.859 |
Neg logit contributions | |
ktop | -2.749 |
Groups | -2.695 |
kernels | -2.617 |
targ | -2.446 |
slic | -2.343 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
est | +0.979 |
ォ | +0.978 |
anas | +0.853 |
ィ | +0.845 |
arest | +0.824 |
Neg logit contributions | |
ktop | -0.813 |
Groups | -0.799 |
kernels | -0.791 |
targ | -0.733 |
aurus | -0.716 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
est | +1.805 |
ォ | +1.799 |
ィ | +1.601 |
itals | +1.572 |
anas | +1.571 |
Neg logit contributions | |
ktop | -1.076 |
kernels | -1.010 |
Groups | -1.008 |
targ | -0.926 |
aurus | -0.909 |
Token | � |
Token ID | 447 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ォ | +0.533 |
est | +0.532 |
ィ | +0.469 |
anas | +0.460 |
arest | +0.455 |
Neg logit contributions | |
ktop | -0.378 |
Groups | -0.363 |
kernels | -0.360 |
targ | -0.330 |
aurus | -0.325 |
Token | of |
Token ID | 286 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
est | +3.538 |
ォ | +3.509 |
ィ | +3.108 |
anas | +3.098 |
arest | +3.012 |
Neg logit contributions | |
ktop | -2.679 |
Groups | -2.662 |
kernels | -2.573 |
targ | -2.412 |
aurus | -2.296 |
Token | the |
Token ID | 262 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
est | +1.379 |
ォ | +1.369 |
anas | +1.216 |
ィ | +1.183 |
arest | +1.163 |
Neg logit contributions | |
ktop | -1.136 |
Groups | -1.118 |
kernels | -1.091 |
targ | -1.008 |
aurus | -0.996 |
Token | Philippines |
Token ID | 13316 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
est | +2.188 |
ォ | +2.175 |
anas | +1.923 |
ィ | +1.871 |
arest | +1.838 |
Neg logit contributions | |
ktop | -1.853 |
Groups | -1.826 |
kernels | -1.772 |
targ | -1.645 |
aurus | -1.639 |
Token | � |
Token ID | 447 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
est | +2.727 |
ォ | +2.723 |
anas | +2.402 |
ィ | +2.377 |
itals | +2.311 |
Neg logit contributions | |
ktop | -1.984 |
Groups | -1.962 |
kernels | -1.902 |
targ | -1.781 |
aurus | -1.689 |
Token | � |
Token ID | 247 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Groups | +0.181 |
ktop | +0.179 |
kernels | +0.176 |
targ | +0.163 |
aurus | +0.160 |
Neg logit contributions | |
ォ | -0.195 |
est | -0.190 |
anas | -0.168 |
ィ | -0.165 |
itals | -0.161 |
Token | nearly |
Token ID | 3016 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
ォ | +0.723 |
est | +0.722 |
anas | +0.629 |
ィ | +0.622 |
arest | +0.605 |
Neg logit contributions | |
ktop | -0.627 |
Groups | -0.624 |
kernels | -0.611 |
targ | -0.567 |
aurus | -0.551 |
Token | 100 |
Token ID | 1802 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
est | +7.655 |
ォ | +6.454 |
anas | +5.970 |
ィ | +5.771 |
itals | +5.610 |
Neg logit contributions | |
ktop | -10.493 |
Groups | -9.727 |
kernels | -9.497 |
gart | -9.303 |
aurus | -9.114 |
Token | million |
Token ID | 1510 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ktop | +0.328 |
Groups | +0.327 |
kernels | +0.319 |
targ | +0.297 |
aurus | +0.292 |
Neg logit contributions | |
ォ | -0.339 |
est | -0.334 |
anas | -0.291 |
ィ | -0.287 |
itals | -0.279 |
Token | population |
Token ID | 3265 |
Feature activation | +8.21e-03 |
Pos logit contributions | |
Groups | +0.688 |
ktop | +0.685 |
kernels | +0.671 |
targ | +0.620 |
aurus | +0.609 |
Neg logit contributions | |
ォ | -0.763 |
est | -0.749 |
anas | -0.659 |
ィ | -0.652 |
itals | -0.631 |
Token | are |
Token ID | 389 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
ォ | +0.035 |
est | +0.034 |
anas | +0.030 |
ィ | +0.030 |
itals | +0.029 |
Neg logit contributions | |
Groups | -0.034 |
ktop | -0.034 |
kernels | -0.033 |
targ | -0.031 |
aurus | -0.030 |
Token | Catholic |
Token ID | 7835 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
est | +2.157 |
ォ | +2.136 |
anas | +1.872 |
ィ | +1.857 |
arest | +1.791 |
Neg logit contributions | |
ktop | -1.813 |
Groups | -1.790 |
kernels | -1.749 |
targ | -1.629 |
aurus | -1.606 |
Token | Breaking |
Token ID | 24942 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
est | +1.619 |
ォ | +1.604 |
anas | +1.401 |
ィ | +1.372 |
itals | +1.343 |
Neg logit contributions | |
ktop | -1.550 |
Groups | -1.501 |
kernels | -1.491 |
targ | -1.390 |
aurus | -1.353 |
Token | Bad |
Token ID | 7772 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
Groups | +2.209 |
ktop | +2.155 |
kernels | +2.148 |
targ | +1.971 |
aurus | +1.935 |
Neg logit contributions | |
ォ | -2.233 |
est | -2.134 |
anas | -1.901 |
ィ | -1.891 |
itals | -1.828 |
Token | AMC |
Token ID | 36239 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ォ | +0.066 |
est | +0.065 |
anas | +0.057 |
ィ | +0.056 |
itals | +0.055 |
Neg logit contributions | |
ktop | -0.064 |
Groups | -0.064 |
kernels | -0.063 |
targ | -0.058 |
aurus | -0.057 |
Token | Julian |
Token ID | 18322 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
ォ | +0.491 |
est | +0.485 |
anas | +0.424 |
ィ | +0.418 |
arest | +0.406 |
Neg logit contributions | |
ktop | -0.467 |
Groups | -0.458 |
kernels | -0.453 |
targ | -0.419 |
aurus | -0.411 |
Token | na |
Token ID | 2616 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
est | +3.329 |
ォ | +3.296 |
anas | +2.848 |
ィ | +2.773 |
arest | +2.725 |
Neg logit contributions | |
ktop | -3.732 |
Groups | -3.639 |
kernels | -3.631 |
targ | -3.359 |
aurus | -3.357 |
Token | Marg |
Token ID | 11899 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ォ | +0.870 |
est | +0.865 |
anas | +0.724 |
ィ | +0.700 |
arest | +0.667 |
Neg logit contributions | |
ktop | -1.487 |
Groups | -1.469 |
kernels | -1.452 |
targ | -1.367 |
aurus | -1.349 |
Token | ul |
Token ID | 377 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
est | +7.763 |
anas | +7.389 |
ォ | +6.639 |
arest | +6.181 |
itals | +5.906 |
Neg logit contributions | |
ktop | -10.743 |
kernels | -10.719 |
targ | -10.693 |
enthusi | -10.645 |
Groups | -10.635 |
Token | ies |
Token ID | 444 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
est | +3.744 |
ォ | +3.356 |
anas | +3.228 |
itals | +3.018 |
arest | +2.981 |
Neg logit contributions | |
Groups | -3.831 |
ktop | -3.808 |
kernels | -3.728 |
targ | -3.526 |
aurus | -3.420 |
Token | The |
Token ID | 383 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
ォ | +0.144 |
est | +0.143 |
anas | +0.125 |
ィ | +0.123 |
itals | +0.120 |
Neg logit contributions | |
ktop | -0.138 |
Groups | -0.137 |
kernels | -0.135 |
targ | -0.125 |
aurus | -0.122 |
Token | Good |
Token ID | 4599 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
ォ | +0.238 |
est | +0.231 |
anas | +0.199 |
ィ | +0.196 |
itals | +0.190 |
Neg logit contributions | |
Groups | -0.295 |
ktop | -0.292 |
kernels | -0.288 |
targ | -0.268 |
aurus | -0.265 |
Token | Wife |
Token ID | 34188 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Groups | +1.186 |
ktop | +1.137 |
kernels | +1.132 |
aurus | +1.028 |
Writer | +1.013 |
Neg logit contributions | |
ォ | -1.196 |
est | -1.101 |
anas | -0.997 |
ィ | -0.993 |
itals | -0.959 |
Token | do |
Token ID | 466 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
Groups | +2.019 |
ktop | +1.983 |
kernels | +1.963 |
targ | +1.769 |
aurus | +1.757 |
Neg logit contributions | |
ォ | -2.849 |
est | -2.750 |
anas | -2.469 |
ィ | -2.459 |
itals | -2.385 |
Token | you |
Token ID | 345 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
est | +2.923 |
ォ | +2.765 |
anas | +2.497 |
ィ | +2.405 |
arest | +2.370 |
Neg logit contributions | |
ktop | -2.885 |
Groups | -2.818 |
kernels | -2.783 |
targ | -2.626 |
aurus | -2.515 |
Token | know |
Token ID | 760 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
est | +1.318 |
ォ | +1.297 |
anas | +1.159 |
ィ | +1.137 |
arest | +1.120 |
Neg logit contributions | |
ktop | -0.810 |
Groups | -0.799 |
kernels | -0.776 |
targ | -0.697 |
aurus | -0.690 |
Token | ? |
Token ID | 30 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
est | +5.013 |
ォ | +4.683 |
anas | +4.138 |
ィ | +3.995 |
arest | +3.975 |
Neg logit contributions | |
ktop | -5.184 |
Groups | -5.044 |
kernels | -4.922 |
targ | -4.736 |
Instr | -4.526 |
Token | Virt |
Token ID | 11285 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
Groups | +2.264 |
ktop | +2.181 |
kernels | +2.158 |
targ | +1.989 |
aurus | +1.987 |
Neg logit contributions | |
ォ | -2.271 |
est | -2.190 |
anas | -1.934 |
ィ | -1.912 |
itals | -1.869 |
Token | ually |
Token ID | 935 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
est | +1.270 |
ォ | +1.166 |
anas | +0.879 |
arest | +0.766 |
itals | +0.760 |
Neg logit contributions | |
ktop | -4.354 |
Groups | -4.307 |
kernels | -4.224 |
targ | -4.095 |
slic | -3.993 |
Token | every |
Token ID | 790 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
est | +7.465 |
ォ | +6.131 |
anas | +5.676 |
ィ | +5.518 |
arest | +5.494 |
Neg logit contributions | |
ktop | -10.478 |
Groups | -9.526 |
kernels | -9.467 |
gart | -9.278 |
Writer | -9.041 |
Token | major |
Token ID | 1688 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
Groups | +0.820 |
ktop | +0.819 |
kernels | +0.801 |
targ | +0.736 |
aurus | +0.725 |
Neg logit contributions | |
ォ | -0.954 |
est | -0.939 |
anas | -0.828 |
ィ | -0.818 |
arest | -0.795 |
Token | medical |
Token ID | 3315 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ォ | +0.170 |
est | +0.169 |
anas | +0.150 |
ィ | +0.148 |
arest | +0.144 |
Neg logit contributions | |
ktop | -0.127 |
Groups | -0.127 |
kernels | -0.124 |
targ | -0.113 |
aurus | -0.111 |
Token | association |
Token ID | 8112 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
ktop | +0.539 |
Groups | +0.536 |
kernels | +0.525 |
targ | +0.481 |
aurus | +0.477 |
Neg logit contributions | |
ォ | -0.638 |
est | -0.637 |
anas | -0.556 |
ィ | -0.549 |
itals | -0.538 |
Token | supports |
Token ID | 6971 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
est | +0.750 |
ォ | +0.749 |
anas | +0.644 |
ィ | +0.631 |
itals | +0.618 |
Neg logit contributions | |
ktop | -0.765 |
Groups | -0.757 |
kernels | -0.746 |
targ | -0.691 |
aurus | -0.684 |
Token | sites |
Token ID | 5043 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
Groups | +1.080 |
ktop | +1.065 |
kernels | +1.052 |
targ | +0.968 |
aurus | +0.950 |
Neg logit contributions | |
ォ | -1.217 |
est | -1.186 |
anas | -1.049 |
ィ | -1.037 |
itals | -1.005 |
Token | that |
Token ID | 326 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
Groups | +1.557 |
ktop | +1.528 |
kernels | +1.513 |
targ | +1.394 |
aurus | +1.371 |
Neg logit contributions | |
ォ | -1.939 |
est | -1.871 |
anas | -1.675 |
ィ | -1.662 |
arest | -1.618 |
Token | were |
Token ID | 547 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
est | +2.206 |
ォ | +2.180 |
anas | +1.897 |
ィ | +1.869 |
itals | +1.826 |
Neg logit contributions | |
ktop | -2.115 |
Groups | -2.090 |
kernels | -2.055 |
targ | -1.860 |
aurus | -1.855 |
Token | suspected |
Token ID | 9885 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
ォ | +0.286 |
est | +0.281 |
anas | +0.244 |
ィ | +0.240 |
itals | +0.233 |
Neg logit contributions | |
Groups | -0.308 |
ktop | -0.307 |
kernels | -0.301 |
targ | -0.280 |
aurus | -0.276 |
Token | of |
Token ID | 286 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
est | +1.537 |
ォ | +1.503 |
anas | +1.343 |
ィ | +1.341 |
itals | +1.307 |
Neg logit contributions | |
ktop | -1.124 |
Groups | -1.077 |
kernels | -1.063 |
targ | -0.965 |
aurus | -0.960 |
Token | misrepresent |
Token ID | 26521 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
est | +1.670 |
ォ | +1.641 |
anas | +1.425 |
ィ | +1.397 |
itals | +1.371 |
Neg logit contributions | |
ktop | -1.719 |
Groups | -1.684 |
kernels | -1.657 |
aurus | -1.526 |
targ | -1.520 |
Token | ing |
Token ID | 278 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
est | +6.275 |
ォ | +5.410 |
anas | +4.867 |
acle | +4.528 |
itals | +4.475 |
Neg logit contributions | |
ktop | -11.654 |
Groups | -11.081 |
kernels | -11.055 |
targ | -10.834 |
enthusi | -10.790 |
Token | content |
Token ID | 2695 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
est | +1.918 |
ォ | +1.853 |
anas | +1.668 |
itals | +1.617 |
ィ | +1.606 |
Neg logit contributions | |
ktop | -1.686 |
Groups | -1.609 |
kernels | -1.577 |
aurus | -1.483 |
targ | -1.467 |
Token | to |
Token ID | 284 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
Groups | +0.186 |
ktop | +0.186 |
kernels | +0.181 |
targ | +0.167 |
aurus | +0.164 |
Neg logit contributions | |
ォ | -0.224 |
est | -0.222 |
anas | -0.196 |
ィ | -0.193 |
itals | -0.188 |
Token | users |
Token ID | 2985 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
ォ | +0.053 |
est | +0.053 |
anas | +0.047 |
ィ | +0.046 |
itals | +0.045 |
Neg logit contributions | |
ktop | -0.046 |
Groups | -0.046 |
kernels | -0.045 |
targ | -0.041 |
aurus | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Groups | +1.967 |
ktop | +1.941 |
kernels | +1.902 |
targ | +1.741 |
aurus | +1.721 |
Neg logit contributions | |
ォ | -2.549 |
est | -2.470 |
anas | -2.212 |
ィ | -2.184 |
arest | -2.132 |
Token | Foundation |
Token ID | 5693 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Groups | +1.040 |
ktop | +1.028 |
kernels | +1.012 |
targ | +0.936 |
aurus | +0.919 |
Neg logit contributions | |
ォ | -1.064 |
est | -1.037 |
anas | -0.910 |
ィ | -0.898 |
arest | -0.872 |
Token | ( |
Token ID | 357 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
est | +1.212 |
ォ | +1.211 |
ィ | +1.037 |
anas | +1.033 |
itals | +0.981 |
Neg logit contributions | |
ktop | -1.401 |
Groups | -1.346 |
kernels | -1.340 |
targ | -1.247 |
aurus | -1.229 |
Token | NS |
Token ID | 8035 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
est | +1.635 |
ォ | +1.609 |
anas | +1.447 |
ィ | +1.397 |
arest | +1.386 |
Neg logit contributions | |
Groups | -1.259 |
ktop | -1.255 |
kernels | -1.221 |
targ | -1.130 |
aurus | -1.088 |
Token | F |
Token ID | 37 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
Groups | +0.371 |
ktop | +0.368 |
kernels | +0.361 |
targ | +0.331 |
aurus | +0.326 |
Neg logit contributions | |
ォ | -0.442 |
est | -0.432 |
anas | -0.383 |
ィ | -0.379 |
itals | -0.368 |
Token | ), |
Token ID | 828 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
est | +2.137 |
ォ | +2.061 |
anas | +1.715 |
ィ | +1.690 |
arest | +1.645 |
Neg logit contributions | |
ktop | -3.546 |
kernels | -3.445 |
Groups | -3.439 |
targ | -3.281 |
aurus | -3.221 |
Token | nearly |
Token ID | 3016 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
est | +4.143 |
ォ | +3.908 |
anas | +3.574 |
ィ | +3.474 |
itals | +3.377 |
Neg logit contributions | |
ktop | -3.998 |
Groups | -3.830 |
kernels | -3.657 |
targ | -3.475 |
aurus | -3.453 |
Token | 70 |
Token ID | 4317 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
est | +7.415 |
ォ | +6.196 |
anas | +5.921 |
ィ | +5.614 |
acle | +5.415 |
Neg logit contributions | |
ktop | -10.414 |
Groups | -9.498 |
kernels | -9.377 |
targ | -8.988 |
aurus | -8.956 |
Token | % |
Token ID | 4 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
est | +0.708 |
ォ | +0.707 |
anas | +0.616 |
ィ | +0.609 |
arest | +0.589 |
Neg logit contributions | |
ktop | -0.648 |
Groups | -0.636 |
kernels | -0.618 |
targ | -0.579 |
aurus | -0.566 |
Token | of |
Token ID | 286 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
est | +4.358 |
ォ | +4.304 |
ィ | +3.823 |
anas | +3.744 |
arest | +3.646 |
Neg logit contributions | |
ktop | -3.704 |
Groups | -3.594 |
kernels | -3.474 |
targ | -3.237 |
slic | -3.092 |
Token | South |
Token ID | 2520 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
est | +1.183 |
ォ | +1.172 |
anas | +1.025 |
ィ | +1.010 |
itals | +0.982 |
Neg logit contributions | |
ktop | -1.055 |
Groups | -1.045 |
kernels | -1.008 |
targ | -0.943 |
aurus | -0.933 |
Token | Koreans |
Token ID | 25999 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
est | +2.382 |
ォ | +2.307 |
ィ | +2.043 |
anas | +2.035 |
itals | +1.979 |
Neg logit contributions | |
ktop | -1.931 |
Groups | -1.870 |
kernels | -1.811 |
aurus | -1.723 |
targ | -1.716 |
Token | this |
Token ID | 428 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
est | +0.525 |
ォ | +0.523 |
anas | +0.460 |
ィ | +0.446 |
arest | +0.438 |
Neg logit contributions | |
Groups | -0.449 |
ktop | -0.449 |
kernels | -0.435 |
targ | -0.402 |
aurus | -0.394 |
Token | year |
Token ID | 614 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
Groups | +0.167 |
ktop | +0.167 |
kernels | +0.163 |
targ | +0.152 |
aurus | +0.150 |
Neg logit contributions | |
ォ | -0.145 |
est | -0.143 |
anas | -0.123 |
ィ | -0.120 |
itals | -0.117 |
Token | , |
Token ID | 11 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Groups | +0.361 |
ktop | +0.358 |
kernels | +0.350 |
targ | +0.323 |
aurus | +0.316 |
Neg logit contributions | |
ォ | -0.418 |
est | -0.415 |
anas | -0.365 |
ィ | -0.357 |
arest | -0.348 |
Token | including |
Token ID | 1390 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
est | +1.104 |
ォ | +1.092 |
anas | +0.964 |
ィ | +0.932 |
arest | +0.919 |
Neg logit contributions | |
Groups | -0.975 |
ktop | -0.973 |
kernels | -0.946 |
targ | -0.872 |
aurus | -0.864 |
Token | a |
Token ID | 257 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
Groups | +1.129 |
ktop | +1.123 |
kernels | +1.099 |
targ | +1.008 |
aurus | +0.992 |
Neg logit contributions | |
ォ | -1.398 |
est | -1.373 |
anas | -1.217 |
ィ | -1.202 |
itals | -1.170 |
Token | nearly |
Token ID | 3016 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
est | +2.267 |
ォ | +2.260 |
anas | +1.952 |
ィ | +1.913 |
arest | +1.863 |
Neg logit contributions | |
ktop | -2.146 |
Groups | -2.113 |
kernels | -2.053 |
aurus | -1.883 |
targ | -1.872 |
Token | quarter |
Token ID | 3860 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
est | +8.232 |
ォ | +7.229 |
anas | +6.564 |
usterity | +6.423 |
iverse | +6.267 |
Neg logit contributions | |
ktop | -9.476 |
Groups | -9.220 |
kernels | -8.753 |
aurus | -8.325 |
Writer | -8.202 |
Token | - |
Token ID | 12 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
ォ | +5.072 |
est | +5.040 |
anas | +4.218 |
arest | +4.111 |
ィ | +4.098 |
Neg logit contributions | |
ktop | -5.606 |
Groups | -5.534 |
kernels | -5.316 |
targ | -4.878 |
vg | -4.832 |
Token | ton |
Token ID | 1122 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
est | +2.753 |
ォ | +2.696 |
anas | +2.433 |
ィ | +2.341 |
arest | +2.325 |
Neg logit contributions | |
Groups | -1.980 |
ktop | -1.976 |
kernels | -1.896 |
targ | -1.705 |
slic | -1.652 |
Token | ginger |
Token ID | 25072 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ォ | +0.350 |
est | +0.347 |
anas | +0.302 |
ィ | +0.297 |
itals | +0.289 |
Neg logit contributions | |
Groups | -0.344 |
ktop | -0.343 |
kernels | -0.334 |
targ | -0.309 |
aurus | -0.304 |
Token | bread |
Token ID | 29573 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
est | +3.531 |
ォ | +3.412 |
anas | +2.809 |
ィ | +2.714 |
esan | +2.592 |
Neg logit contributions | |
Groups | -5.365 |
ktop | -5.359 |
kernels | -5.101 |
targ | -4.790 |
aurus | -4.752 |
Token | � |
Token ID | 251 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ktop | +0.674 |
Groups | +0.672 |
kernels | +0.661 |
targ | +0.621 |
aurus | +0.611 |
Neg logit contributions | |
ォ | -0.491 |
est | -0.477 |
anas | -0.403 |
ィ | -0.401 |
itals | -0.383 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Groups | +1.119 |
ktop | +1.111 |
kernels | +1.093 |
targ | +1.014 |
aurus | +0.999 |
Neg logit contributions | |
ォ | -1.054 |
est | -1.030 |
anas | -0.898 |
ィ | -0.886 |
itals | -0.858 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
ォ | +0.587 |
est | +0.556 |
anas | +0.493 |
ィ | +0.489 |
itals | +0.474 |
Neg logit contributions | |
Groups | -0.622 |
ktop | -0.608 |
kernels | -0.602 |
aurus | -0.553 |
targ | -0.545 |
Token | Conservative |
Token ID | 42039 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
ォ | +0.089 |
est | +0.087 |
anas | +0.076 |
ィ | +0.075 |
arest | +0.073 |
Neg logit contributions | |
Groups | -0.088 |
ktop | -0.088 |
kernels | -0.086 |
targ | -0.080 |
aurus | -0.078 |
Token | blog |
Token ID | 4130 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Groups | +2.699 |
kernels | +2.595 |
ktop | +2.562 |
targ | +2.366 |
aurus | +2.301 |
Neg logit contributions | |
ォ | -3.538 |
est | -3.405 |
anas | -3.066 |
ィ | -3.047 |
itals | -2.969 |
Token | Hot |
Token ID | 6964 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Groups | +6.116 |
kernels | +5.871 |
ktop | +5.699 |
targ | +5.460 |
aurus | +5.379 |
Neg logit contributions | |
ォ | -4.899 |
est | -4.547 |
ィ | -4.088 |
anas | -4.025 |
arest | -3.910 |
Token | Air |
Token ID | 3701 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Groups | +8.256 |
kernels | +7.411 |
ktop | +7.039 |
Writer | +6.826 |
aurus | +6.580 |
Neg logit contributions | |
ォ | -12.443 |
ィ | -11.529 |
itals | -11.016 |
est | -10.948 |
anas | -10.516 |
Token | declared |
Token ID | 6875 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Groups | +4.933 |
kernels | +4.819 |
ktop | +4.669 |
aurus | +4.366 |
targ | +4.351 |
Neg logit contributions | |
ォ | -5.264 |
est | -5.122 |
anas | -4.635 |
ィ | -4.510 |
arest | -4.422 |
Token | that |
Token ID | 326 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
ktop | +0.713 |
Groups | +0.711 |
kernels | +0.695 |
targ | +0.637 |
aurus | +0.627 |
Neg logit contributions | |
ォ | -0.867 |
est | -0.854 |
anas | -0.751 |
ィ | -0.746 |
itals | -0.725 |
Token | � |
Token ID | 564 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
Groups | +2.369 |
ktop | +2.335 |
kernels | +2.300 |
targ | +2.115 |
aurus | +2.078 |
Neg logit contributions | |
ォ | -2.819 |
est | -2.751 |
anas | -2.442 |
ィ | -2.412 |
arest | -2.347 |
Token | � |
Token ID | 250 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
ォ | +1.632 |
est | +1.599 |
anas | +1.410 |
ィ | +1.394 |
itals | +1.354 |
Neg logit contributions | |
Groups | -1.438 |
ktop | -1.429 |
kernels | -1.402 |
targ | -1.293 |
aurus | -1.270 |
Token | the |
Token ID | 262 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Groups | +1.690 |
ktop | +1.664 |
kernels | +1.638 |
targ | +1.497 |
aurus | +1.466 |
Neg logit contributions | |
ォ | -2.274 |
est | -2.214 |
anas | -1.979 |
ィ | -1.963 |
arest | -1.905 |
Token | far |
Token ID | 1290 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
Groups | +1.275 |
ktop | +1.256 |
kernels | +1.239 |
targ | +1.138 |
aurus | +1.112 |
Neg logit contributions | |
ォ | -1.576 |
est | -1.532 |
anas | -1.365 |
ィ | -1.351 |
itals | -1.311 |
Token | - |
Token ID | 12 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
est | +2.469 |
ォ | +2.432 |
anas | +2.108 |
ィ | +2.061 |
arest | +2.041 |
Neg logit contributions | |
ktop | -2.354 |
Groups | -2.341 |
kernels | -2.291 |
targ | -2.139 |
aurus | -2.117 |
Token | right |
Token ID | 3506 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
est | +1.193 |
ォ | +1.182 |
anas | +1.043 |
ィ | +1.018 |
arest | +1.002 |
Neg logit contributions | |
Groups | -1.010 |
ktop | -1.002 |
kernels | -0.985 |
targ | -0.913 |
aurus | -0.889 |
Token | website |
Token ID | 3052 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Groups | +2.679 |
kernels | +2.569 |
ktop | +2.557 |
targ | +2.376 |
aurus | +2.303 |
Neg logit contributions | |
ォ | -3.346 |
est | -3.167 |
anas | -2.854 |
ィ | -2.845 |
arest | -2.758 |
Token | Daily |
Token ID | 6714 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Groups | +4.834 |
kernels | +4.479 |
ktop | +4.250 |
targ | +4.225 |
aurus | +4.025 |
Neg logit contributions | |
ォ | -6.210 |
est | -5.655 |
ィ | -5.204 |
anas | -5.172 |
arest | -5.078 |
Token | Caller |
Token ID | 10244 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Groups | +6.813 |
kernels | +6.265 |
targ | +5.687 |
Writer | +5.634 |
Group | +5.501 |
Neg logit contributions | |
ォ | -11.553 |
est | -10.657 |
esan | -10.224 |
ィ | -10.144 |
itals | -9.916 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
Groups | +1.232 |
ktop | +1.231 |
kernels | +1.202 |
targ | +1.105 |
aurus | +1.082 |
Neg logit contributions | |
ォ | -1.549 |
est | -1.524 |
anas | -1.350 |
ィ | -1.334 |
itals | -1.298 |
Token |
|
Token ID | 198 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ォ | +1.190 |
est | +1.183 |
anas | +1.001 |
ィ | +0.995 |
itals | +0.961 |
Neg logit contributions | |
ktop | -1.388 |
kernels | -1.356 |
Groups | -1.350 |
targ | -1.270 |
aurus | -1.234 |
Token |
|
Token ID | 198 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
Groups | +0.634 |
ktop | +0.609 |
kernels | +0.607 |
aurus | +0.556 |
Writer | +0.547 |
Neg logit contributions | |
ォ | -0.672 |
est | -0.617 |
ィ | -0.562 |
anas | -0.561 |
itals | -0.546 |
Token | In |
Token ID | 818 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
ォ | +0.248 |
est | +0.246 |
anas | +0.213 |
ィ | +0.210 |
arest | +0.204 |
Neg logit contributions | |
Groups | -0.258 |
ktop | -0.258 |
kernels | -0.253 |
targ | -0.236 |
aurus | -0.230 |
Token | gets |
Token ID | 3011 |
Feature activation | -8.99e-03 |
Pos logit contributions | |
Groups | +2.524 |
ktop | +2.481 |
kernels | +2.471 |
targ | +2.263 |
aurus | +2.230 |
Neg logit contributions | |
ォ | -2.594 |
est | -2.502 |
anas | -2.221 |
ィ | -2.181 |
arest | -2.134 |
Token | down |
Token ID | 866 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ktop | +0.033 |
Groups | +0.033 |
kernels | +0.032 |
targ | +0.029 |
aurus | +0.029 |
Neg logit contributions | |
ォ | -0.042 |
est | -0.042 |
anas | -0.037 |
ィ | -0.037 |
itals | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
ktop | +4.070 |
Groups | +4.053 |
kernels | +3.995 |
targ | +3.585 |
aurus | +3.476 |
Neg logit contributions | |
ォ | -6.715 |
est | -6.430 |
anas | -5.882 |
ィ | -5.836 |
itals | -5.686 |
Token | the |
Token ID | 262 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
Groups | +2.461 |
ktop | +2.419 |
kernels | +2.410 |
targ | +2.139 |
aurus | +2.102 |
Neg logit contributions | |
ォ | -3.888 |
est | -3.812 |
anas | -3.430 |
ィ | -3.396 |
arest | -3.309 |
Token | n |
Token ID | 299 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Groups | +2.227 |
kernels | +2.186 |
ktop | +2.182 |
targ | +1.977 |
aurus | +1.933 |
Neg logit contributions | |
ォ | -2.877 |
est | -2.782 |
anas | -2.482 |
ィ | -2.475 |
itals | -2.392 |
Token | itty |
Token ID | 9760 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Groups | +1.318 |
ktop | +1.313 |
kernels | +1.289 |
targ | +1.205 |
aurus | +1.180 |
Neg logit contributions | |
ォ | -1.149 |
est | -1.135 |
anas | -0.980 |
ィ | -0.958 |
itals | -0.935 |
Token | - |
Token ID | 12 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
Groups | +5.973 |
kernels | +5.836 |
ktop | +5.481 |
cal | +4.949 |
grou | +4.812 |
Neg logit contributions | |
ォ | -11.859 |
est | -11.467 |
anas | -10.864 |
ィ | -10.723 |
itals | -10.404 |
Token | gr |
Token ID | 2164 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Groups | +2.820 |
kernels | +2.816 |
ktop | +2.812 |
aurus | +2.423 |
rings | +2.419 |
Neg logit contributions | |
ォ | -4.381 |
est | -4.161 |
anas | -3.785 |
ィ | -3.765 |
usterity | -3.651 |
Token | itty |
Token ID | 9760 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
ktop | +1.459 |
Groups | +1.442 |
kernels | +1.427 |
aurus | +1.309 |
vg | +1.278 |
Neg logit contributions | |
ォ | -1.558 |
est | -1.469 |
ィ | -1.307 |
anas | -1.281 |
usterity | -1.232 |
Token | of |
Token ID | 286 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Groups | +1.602 |
ktop | +1.588 |
kernels | +1.558 |
targ | +1.415 |
aurus | +1.387 |
Neg logit contributions | |
ォ | -2.318 |
est | -2.271 |
anas | -2.034 |
ィ | -2.014 |
itals | -1.962 |
Token | applying |
Token ID | 11524 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
ォ | +0.556 |
est | +0.551 |
anas | +0.487 |
ィ | +0.480 |
itals | +0.470 |
Neg logit contributions | |
ktop | -0.439 |
Groups | -0.437 |
kernels | -0.423 |
targ | -0.392 |
aurus | -0.385 |
Token | has |
Token ID | 468 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Groups | +2.572 |
ktop | +2.512 |
kernels | +2.476 |
targ | +2.271 |
aurus | +2.240 |
Neg logit contributions | |
ォ | -2.995 |
est | -2.891 |
anas | -2.576 |
ィ | -2.555 |
itals | -2.469 |
Token | never |
Token ID | 1239 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
Groups | +0.695 |
ktop | +0.690 |
kernels | +0.678 |
targ | +0.625 |
aurus | +0.615 |
Neg logit contributions | |
ォ | -0.766 |
est | -0.750 |
anas | -0.661 |
ィ | -0.653 |
itals | -0.634 |
Token | released |
Token ID | 2716 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Groups | +2.523 |
ktop | +2.504 |
kernels | +2.481 |
targ | +2.304 |
reckoned | +2.266 |
Neg logit contributions | |
ォ | -2.682 |
est | -2.487 |
ィ | -2.250 |
anas | -2.218 |
itals | -2.145 |
Token | a |
Token ID | 257 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Groups | +3.731 |
kernels | +3.687 |
ktop | +3.625 |
targ | +3.264 |
slic | +3.114 |
Neg logit contributions | |
ォ | -5.670 |
est | -5.294 |
ィ | -4.914 |
anas | -4.804 |
itals | -4.703 |
Token | death |
Token ID | 1918 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Groups | +1.949 |
ktop | +1.916 |
kernels | +1.895 |
targ | +1.742 |
aurus | +1.684 |
Neg logit contributions | |
ォ | -2.581 |
est | -2.483 |
anas | -2.229 |
ィ | -2.214 |
itals | -2.161 |
Token | toll |
Token ID | 13592 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Groups | +4.247 |
ktop | +4.210 |
kernels | +4.161 |
targ | +3.767 |
aurus | +3.624 |
Neg logit contributions | |
ォ | -7.491 |
est | -7.119 |
ィ | -6.623 |
anas | -6.552 |
itals | -6.380 |
Token | from |
Token ID | 422 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ktop | +7.082 |
Groups | +7.017 |
kernels | +6.915 |
targ | +6.374 |
reckoned | +6.353 |
Neg logit contributions | |
ォ | -11.232 |
est | -9.700 |
ィ | -9.673 |
itals | -9.327 |
anas | -9.307 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
est | +0.577 |
ォ | +0.572 |
anas | +0.511 |
ィ | +0.490 |
itals | +0.489 |
Neg logit contributions | |
ktop | -0.437 |
Groups | -0.434 |
kernels | -0.425 |
aurus | -0.388 |
targ | -0.387 |
Token | crackdown |
Token ID | 22671 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
Groups | +0.503 |
ktop | +0.501 |
kernels | +0.491 |
targ | +0.451 |
aurus | +0.445 |
Neg logit contributions | |
ォ | -0.591 |
est | -0.585 |
anas | -0.516 |
ィ | -0.505 |
itals | -0.494 |
Token | after |
Token ID | 706 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
Groups | +3.109 |
ktop | +3.064 |
kernels | +3.028 |
targ | +2.770 |
aurus | +2.703 |
Neg logit contributions | |
ォ | -4.095 |
est | -3.905 |
anas | -3.510 |
ィ | -3.508 |
itals | -3.402 |
Token | troops |
Token ID | 6553 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Groups | +1.446 |
ktop | +1.436 |
kernels | +1.407 |
targ | +1.287 |
aurus | +1.263 |
Neg logit contributions | |
ォ | -1.888 |
est | -1.851 |
anas | -1.647 |
ィ | -1.629 |
itals | -1.586 |
Token | in |
Token ID | 287 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
Groups | +0.845 |
ktop | +0.840 |
kernels | +0.821 |
targ | +0.754 |
aurus | +0.740 |
Neg logit contributions | |
ォ | -1.064 |
est | -1.058 |
anas | -0.934 |
ィ | -0.920 |
itals | -0.897 |
Token | dro |
Token ID | 3102 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Groups | +1.168 |
ktop | +1.165 |
kernels | +1.138 |
targ | +1.045 |
aurus | +1.028 |
Neg logit contributions | |
ォ | -1.444 |
est | -1.420 |
anas | -1.258 |
ィ | -1.242 |
itals | -1.210 |
Token | ves |
Token ID | 1158 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Groups | +1.666 |
ktop | +1.601 |
kernels | +1.425 |
aurus | +1.097 |
targ | +1.085 |
Neg logit contributions | |
ォ | -7.689 |
est | -7.342 |
ィ | -6.891 |
anas | -6.808 |
arest | -6.719 |
Token | , |
Token ID | 11 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
Groups | +2.045 |
ktop | +2.029 |
kernels | +1.991 |
targ | +1.816 |
aurus | +1.787 |
Neg logit contributions | |
ォ | -2.740 |
est | -2.653 |
anas | -2.377 |
ィ | -2.364 |
itals | -2.293 |
Token | some |
Token ID | 617 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Groups | +0.322 |
ktop | +0.321 |
kernels | +0.314 |
targ | +0.290 |
aurus | +0.286 |
Neg logit contributions | |
ォ | -0.363 |
est | -0.362 |
anas | -0.317 |
ィ | -0.311 |
arest | -0.303 |
Token | driving |
Token ID | 5059 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
est | +0.806 |
ォ | +0.785 |
anas | +0.691 |
ィ | +0.674 |
arest | +0.657 |
Neg logit contributions | |
ktop | -0.779 |
Groups | -0.778 |
kernels | -0.756 |
targ | -0.703 |
aurus | -0.696 |
Token | hundreds |
Token ID | 5179 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
Groups | +7.959 |
kernels | +7.748 |
ktop | +7.228 |
targ | +6.861 |
leagues | +6.759 |
Neg logit contributions | |
ォ | -10.680 |
est | -9.374 |
ィ | -8.812 |
arest | -8.543 |
anas | -8.473 |
Token | of |
Token ID | 286 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Groups | +2.070 |
ktop | +2.056 |
kernels | +2.005 |
targ | +1.817 |
aurus | +1.774 |
Neg logit contributions | |
ォ | -3.302 |
est | -3.258 |
anas | -2.922 |
ィ | -2.889 |
itals | -2.821 |
Token | miles |
Token ID | 4608 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
Groups | +3.620 |
kernels | +3.522 |
ktop | +3.460 |
targ | +3.095 |
leagues | +3.018 |
Neg logit contributions | |
ォ | -5.862 |
est | -5.565 |
anas | -5.053 |
ィ | -5.050 |
arest | -4.923 |
Token | , |
Token ID | 11 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
Groups | +2.253 |
ktop | +2.233 |
kernels | +2.201 |
targ | +1.992 |
aurus | +1.976 |
Neg logit contributions | |
ォ | -3.040 |
est | -2.914 |
ィ | -2.617 |
anas | -2.609 |
itals | -2.526 |
Token | and |
Token ID | 290 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
est | +0.356 |
ォ | +0.348 |
anas | +0.310 |
ィ | +0.300 |
arest | +0.296 |
Neg logit contributions | |
ktop | -0.321 |
Groups | -0.320 |
kernels | -0.312 |
targ | -0.290 |
aurus | -0.285 |
Token | by |
Token ID | 416 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
est | +2.623 |
ォ | +2.528 |
anas | +2.278 |
ィ | +2.226 |
arest | +2.191 |
Neg logit contributions | |
ktop | -2.159 |
Groups | -2.089 |
kernels | -2.016 |
targ | -1.890 |
aurus | -1.880 |
Token | a |
Token ID | 257 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
est | +2.189 |
ォ | +2.121 |
anas | +1.916 |
ィ | +1.843 |
itals | +1.835 |
Neg logit contributions | |
ktop | -1.843 |
Groups | -1.788 |
kernels | -1.772 |
targ | -1.650 |
aurus | -1.629 |
Token | Brazilian |
Token ID | 17036 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
est | +1.756 |
ォ | +1.742 |
anas | +1.524 |
ィ | +1.493 |
arest | +1.468 |
Neg logit contributions | |
ktop | -1.644 |
Groups | -1.606 |
kernels | -1.595 |
targ | -1.455 |
aurus | -1.455 |
Token | prosecutor |
Token ID | 13683 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
Groups | +1.123 |
ktop | +1.116 |
kernels | +1.092 |
targ | +0.998 |
aurus | +0.981 |
Neg logit contributions | |
ォ | -1.486 |
est | -1.461 |
anas | -1.300 |
ィ | -1.286 |
arest | -1.251 |
Token | that |
Token ID | 326 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
Groups | +1.334 |
ktop | +1.326 |
kernels | +1.297 |
targ | +1.174 |
aurus | +1.155 |
Neg logit contributions | |
ォ | -2.001 |
est | -1.972 |
anas | -1.763 |
ィ | -1.744 |
arest | -1.700 |
Token | Rolls |
Token ID | 40074 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
est | +0.437 |
ォ | +0.428 |
anas | +0.387 |
ィ | +0.376 |
itals | +0.367 |
Neg logit contributions | |
ktop | -0.352 |
Groups | -0.346 |
kernels | -0.338 |
targ | -0.311 |
aurus | -0.310 |
Token | - |
Token ID | 12 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Groups | +7.823 |
kernels | +7.446 |
ktop | +7.391 |
reckoned | +6.891 |
targ | +6.865 |
Neg logit contributions | |
ォ | -10.434 |
est | -9.579 |
ィ | -8.671 |
anas | -8.654 |
itals | -8.621 |
Token | Roy |
Token ID | 32027 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Groups | +0.434 |
ktop | +0.430 |
kernels | +0.415 |
targ | +0.357 |
aurus | +0.346 |
Neg logit contributions | |
ォ | -1.184 |
est | -1.169 |
anas | -1.069 |
ィ | -1.060 |
arest | -1.039 |
Token | ce |
Token ID | 344 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
Groups | +1.390 |
ktop | +1.376 |
kernels | +1.359 |
aurus | +1.284 |
targ | +1.270 |
Neg logit contributions | |
ォ | -0.660 |
est | -0.603 |
anas | -0.485 |
ィ | -0.476 |
usterity | -0.446 |
Token | is |
Token ID | 318 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
Groups | +2.645 |
ktop | +2.595 |
kernels | +2.568 |
targ | +2.364 |
aurus | +2.325 |
Neg logit contributions | |
ォ | -3.023 |
est | -2.930 |
anas | -2.592 |
ィ | -2.563 |
itals | -2.490 |
Token | co |
Token ID | 763 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
est | +0.091 |
ォ | +0.090 |
anas | +0.078 |
ィ | +0.077 |
arest | +0.075 |
Neg logit contributions | |
Groups | -0.089 |
ktop | -0.089 |
kernels | -0.087 |
targ | -0.080 |
aurus | -0.079 |
Token | emaker |
Token ID | 32174 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
est | +2.763 |
ォ | +2.464 |
anas | +2.011 |
ィ | +1.797 |
itals | +1.785 |
Neg logit contributions | |
Groups | -6.302 |
ktop | -6.302 |
kernels | -6.226 |
targ | -5.865 |
rings | -5.777 |
Token | ), |
Token ID | 828 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ォ | +1.107 |
est | +1.106 |
anas | +0.943 |
ィ | +0.943 |
itals | +0.912 |
Neg logit contributions | |
Groups | -1.192 |
ktop | -1.183 |
kernels | -1.156 |
targ | -1.073 |
aurus | -1.059 |
Token | but |
Token ID | 475 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
est | +2.202 |
ォ | +2.193 |
ィ | +1.947 |
anas | +1.918 |
itals | +1.881 |
Neg logit contributions | |
ktop | -1.827 |
Groups | -1.805 |
kernels | -1.763 |
targ | -1.646 |
aurus | -1.599 |
Token | these |
Token ID | 777 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
est | +2.136 |
ォ | +2.117 |
anas | +1.868 |
ィ | +1.856 |
itals | +1.815 |
Neg logit contributions | |
ktop | -1.926 |
Groups | -1.888 |
kernels | -1.843 |
targ | -1.723 |
aurus | -1.715 |
Token | are |
Token ID | 389 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ォ | +0.166 |
est | +0.165 |
anas | +0.146 |
ィ | +0.145 |
itals | +0.142 |
Neg logit contributions | |
ktop | -0.116 |
Groups | -0.116 |
kernels | -0.111 |
targ | -0.102 |
aurus | -0.101 |
Token | exhaust |
Token ID | 12142 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Groups | +0.791 |
ktop | +0.787 |
kernels | +0.770 |
targ | +0.711 |
aurus | +0.699 |
Neg logit contributions | |
ォ | -0.887 |
est | -0.871 |
anas | -0.767 |
ィ | -0.758 |
itals | -0.737 |
Token | ingly |
Token ID | 4420 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
kernels | +6.556 |
Groups | +6.554 |
ktop | +6.004 |
targ | +5.693 |
leagues | +5.578 |
Neg logit contributions | |
ォ | -11.042 |
est | -10.680 |
anas | -9.542 |
itals | -9.510 |
usterity | -9.438 |
Token | studied |
Token ID | 9713 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ォ | +1.067 |
est | +1.059 |
anas | +0.900 |
ィ | +0.876 |
arest | +0.850 |
Neg logit contributions | |
Groups | -1.337 |
ktop | -1.329 |
kernels | -1.287 |
targ | -1.208 |
aurus | -1.203 |
Token | prior |
Token ID | 3161 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Groups | +0.541 |
ktop | +0.540 |
kernels | +0.525 |
targ | +0.486 |
aurus | +0.479 |
Neg logit contributions | |
ォ | -0.655 |
est | -0.647 |
anas | -0.572 |
ィ | -0.564 |
itals | -0.551 |
Token | to |
Token ID | 284 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
Groups | +1.349 |
ktop | +1.342 |
kernels | +1.300 |
targ | +1.180 |
aurus | +1.153 |
Neg logit contributions | |
ォ | -2.231 |
est | -2.209 |
anas | -1.975 |
ィ | -1.964 |
itals | -1.924 |
Token | actually |
Token ID | 1682 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
est | +0.127 |
ォ | +0.126 |
anas | +0.111 |
ィ | +0.108 |
itals | +0.107 |
Neg logit contributions | |
ktop | -0.112 |
Groups | -0.112 |
kernels | -0.108 |
targ | -0.100 |
aurus | -0.099 |
Token | a |
Token ID | 257 |
Feature activation | +6.38e-03 |
Pos logit contributions | |
Groups | +1.327 |
ktop | +1.319 |
kernels | +1.291 |
targ | +1.179 |
aurus | +1.157 |
Neg logit contributions | |
ォ | -1.787 |
est | -1.755 |
anas | -1.563 |
ィ | -1.546 |
itals | -1.505 |
Token | group |
Token ID | 1448 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ォ | +0.030 |
est | +0.029 |
anas | +0.026 |
ィ | +0.026 |
itals | +0.025 |
Neg logit contributions | |
Groups | -0.024 |
ktop | -0.023 |
kernels | -0.023 |
targ | -0.021 |
aurus | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Groups | +0.807 |
ktop | +0.800 |
kernels | +0.779 |
targ | +0.704 |
aurus | +0.686 |
Neg logit contributions | |
ォ | -1.232 |
est | -1.224 |
anas | -1.091 |
ィ | -1.080 |
arest | -1.038 |
Token | clergy |
Token ID | 26014 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
est | +1.506 |
ォ | +1.503 |
anas | +1.317 |
ィ | +1.291 |
itals | +1.259 |
Neg logit contributions | |
ktop | -1.328 |
Groups | -1.303 |
kernels | -1.272 |
targ | -1.173 |
aurus | -1.163 |
Token | asked |
Token ID | 1965 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
ォ | +0.997 |
est | +0.995 |
anas | +0.873 |
ィ | +0.860 |
itals | +0.834 |
Neg logit contributions | |
ktop | -0.788 |
Groups | -0.787 |
kernels | -0.768 |
targ | -0.703 |
aurus | -0.686 |
Token | how |
Token ID | 703 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Groups | +2.570 |
ktop | +2.530 |
kernels | +2.496 |
targ | +2.292 |
aurus | +2.247 |
Neg logit contributions | |
ォ | -3.109 |
est | -3.016 |
anas | -2.681 |
ィ | -2.660 |
arest | -2.582 |
Token | they |
Token ID | 484 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Groups | +7.371 |
kernels | +7.081 |
ktop | +6.639 |
targ | +6.368 |
aurus | +6.260 |
Neg logit contributions | |
ォ | -10.424 |
est | -9.495 |
ィ | -8.690 |
arest | -8.497 |
itals | -8.493 |
Token | could |
Token ID | 714 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
Groups | +2.878 |
ktop | +2.774 |
kernels | +2.773 |
targ | +2.424 |
aurus | +2.393 |
Neg logit contributions | |
ォ | -6.528 |
est | -6.324 |
anas | -5.802 |
ィ | -5.741 |
itals | -5.676 |
Token | help |
Token ID | 1037 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Groups | +2.231 |
ktop | +2.194 |
kernels | +2.171 |
targ | +1.989 |
aurus | +1.941 |
Neg logit contributions | |
ォ | -2.890 |
est | -2.784 |
anas | -2.504 |
ィ | -2.486 |
itals | -2.407 |
Token | get |
Token ID | 651 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
Groups | +1.547 |
ktop | +1.543 |
kernels | +1.510 |
targ | +1.385 |
aurus | +1.362 |
Neg logit contributions | |
ォ | -1.922 |
est | -1.890 |
anas | -1.675 |
ィ | -1.655 |
itals | -1.608 |
Token | young |
Token ID | 1862 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Groups | +1.373 |
ktop | +1.362 |
kernels | +1.337 |
targ | +1.228 |
aurus | +1.206 |
Neg logit contributions | |
ォ | -1.659 |
est | -1.624 |
anas | -1.439 |
ィ | -1.423 |
itals | -1.384 |
Token | issues |
Token ID | 2428 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
ォ | +0.463 |
est | +0.460 |
anas | +0.406 |
ィ | +0.398 |
itals | +0.390 |
Neg logit contributions | |
ktop | -0.399 |
Groups | -0.397 |
kernels | -0.385 |
targ | -0.356 |
aurus | -0.352 |
Token | , |
Token ID | 11 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Groups | +1.367 |
ktop | +1.357 |
kernels | +1.332 |
targ | +1.222 |
aurus | +1.201 |
Neg logit contributions | |
ォ | -1.655 |
est | -1.618 |
anas | -1.435 |
ィ | -1.419 |
itals | -1.379 |
Token | about |
Token ID | 546 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Groups | +0.730 |
ktop | +0.727 |
kernels | +0.710 |
targ | +0.653 |
aurus | +0.642 |
Neg logit contributions | |
ォ | -0.883 |
est | -0.871 |
anas | -0.769 |
ィ | -0.758 |
itals | -0.740 |
Token | the |
Token ID | 262 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ォ | +0.690 |
est | +0.688 |
anas | +0.606 |
ィ | +0.594 |
itals | +0.582 |
Neg logit contributions | |
ktop | -0.571 |
Groups | -0.564 |
kernels | -0.548 |
targ | -0.507 |
aurus | -0.505 |
Token | n |
Token ID | 299 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
Groups | +0.889 |
ktop | +0.884 |
kernels | +0.866 |
targ | +0.797 |
aurus | +0.784 |
Neg logit contributions | |
ォ | -1.044 |
est | -1.024 |
anas | -0.905 |
ィ | -0.894 |
itals | -0.869 |
Token | itty |
Token ID | 9760 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
est | +0.015 |
ォ | +0.015 |
anas | +0.013 |
ィ | +0.013 |
itals | +0.013 |
Neg logit contributions | |
ktop | -0.015 |
Groups | -0.015 |
kernels | -0.015 |
targ | -0.014 |
aurus | -0.013 |
Token | gritty |
Token ID | 39679 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
Groups | +5.137 |
kernels | +4.960 |
ktop | +4.675 |
targ | +4.072 |
cal | +4.055 |
Neg logit contributions | |
ォ | -11.703 |
est | -11.265 |
anas | -10.707 |
ィ | -10.603 |
itals | -10.313 |
Token | on |
Token ID | 319 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Groups | +1.881 |
ktop | +1.860 |
kernels | +1.838 |
targ | +1.664 |
aurus | +1.620 |
Neg logit contributions | |
ォ | -2.780 |
est | -2.704 |
anas | -2.436 |
ィ | -2.416 |
arest | -2.354 |
Token | legislative |
Token ID | 10828 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Groups | +0.813 |
ktop | +0.809 |
kernels | +0.792 |
targ | +0.729 |
aurus | +0.718 |
Neg logit contributions | |
ォ | -0.951 |
est | -0.935 |
anas | -0.826 |
ィ | -0.815 |
itals | -0.794 |
Token | proposals |
Token ID | 11628 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
est | +1.371 |
ォ | +1.363 |
anas | +1.193 |
ィ | +1.184 |
itals | +1.176 |
Neg logit contributions | |
ktop | -1.021 |
Groups | -0.992 |
kernels | -0.954 |
aurus | -0.891 |
targ | -0.883 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
est | +1.714 |
ォ | +1.698 |
anas | +1.478 |
ィ | +1.459 |
itals | +1.417 |
Neg logit contributions | |
ktop | -1.710 |
Groups | -1.708 |
kernels | -1.667 |
targ | -1.553 |
aurus | -1.511 |
Token | Further |
Token ID | 7735 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
ォ | +0.949 |
est | +0.930 |
ィ | +0.810 |
anas | +0.810 |
itals | +0.772 |
Neg logit contributions | |
ktop | -0.930 |
Groups | -0.911 |
kernels | -0.910 |
targ | -0.846 |
aurus | -0.818 |
Token | investigation |
Token ID | 3645 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
est | +2.701 |
ォ | +2.673 |
ィ | +2.326 |
anas | +2.319 |
itals | +2.216 |
Neg logit contributions | |
ktop | -2.650 |
Groups | -2.598 |
kernels | -2.522 |
aurus | -2.335 |
targ | -2.329 |
Token | revealed |
Token ID | 4602 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ktop | +0.194 |
Groups | +0.193 |
kernels | +0.188 |
targ | +0.174 |
aurus | +0.171 |
Neg logit contributions | |
ォ | -0.221 |
est | -0.220 |
anas | -0.193 |
ィ | -0.190 |
itals | -0.185 |
Token | he |
Token ID | 339 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ォ | +1.358 |
est | +1.350 |
anas | +1.189 |
ィ | +1.182 |
arest | +1.136 |
Neg logit contributions | |
Groups | -1.055 |
ktop | -1.054 |
kernels | -1.011 |
targ | -0.934 |
aurus | -0.924 |
Token | was |
Token ID | 373 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Groups | +0.487 |
ktop | +0.484 |
kernels | +0.472 |
targ | +0.431 |
aurus | +0.422 |
Neg logit contributions | |
ォ | -0.668 |
est | -0.659 |
anas | -0.586 |
ィ | -0.580 |
itals | -0.565 |
Token | driving |
Token ID | 5059 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Groups | +1.731 |
ktop | +1.724 |
kernels | +1.698 |
targ | +1.571 |
aurus | +1.548 |
Neg logit contributions | |
ォ | -1.802 |
est | -1.728 |
anas | -1.526 |
ィ | -1.514 |
itals | -1.468 |
Token | with |
Token ID | 351 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
Groups | +7.356 |
ktop | +7.346 |
kernels | +7.341 |
targ | +6.720 |
aurus | +6.594 |
Neg logit contributions | |
ォ | -9.637 |
est | -8.533 |
anas | -7.831 |
arest | -7.831 |
itals | -7.828 |
Token | a |
Token ID | 257 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Groups | +2.632 |
ktop | +2.609 |
kernels | +2.572 |
targ | +2.356 |
aurus | +2.309 |
Neg logit contributions | |
ォ | -3.192 |
est | -3.108 |
anas | -2.749 |
ィ | -2.721 |
arest | -2.662 |
Token | suspended |
Token ID | 9951 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
Groups | +1.365 |
ktop | +1.357 |
kernels | +1.338 |
targ | +1.252 |
aurus | +1.233 |
Neg logit contributions | |
ォ | -1.043 |
est | -1.015 |
anas | -0.868 |
ィ | -0.855 |
itals | -0.823 |
Token | license |
Token ID | 5964 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Groups | +0.248 |
ktop | +0.246 |
kernels | +0.241 |
targ | +0.220 |
aurus | +0.217 |
Neg logit contributions | |
ォ | -0.324 |
est | -0.319 |
anas | -0.283 |
ィ | -0.280 |
itals | -0.273 |
Token | . |
Token ID | 13 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
Groups | +1.289 |
ktop | +1.283 |
kernels | +1.259 |
targ | +1.155 |
aurus | +1.137 |
Neg logit contributions | |
ォ | -1.604 |
est | -1.558 |
anas | -1.388 |
ィ | -1.372 |
arest | -1.339 |
Token | The |
Token ID | 383 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Groups | +1.255 |
ktop | +1.234 |
kernels | +1.214 |
targ | +1.117 |
aurus | +1.104 |
Neg logit contributions | |
ォ | -1.351 |
est | -1.321 |
anas | -1.166 |
ィ | -1.148 |
itals | -1.122 |
Token | Belgian |
Token ID | 21402 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Groups | +1.080 |
ktop | +1.074 |
kernels | +1.052 |
targ | +0.969 |
aurus | +0.954 |
Neg logit contributions | |
ォ | -1.245 |
est | -1.221 |
anas | -1.077 |
ィ | -1.065 |
itals | -1.034 |
Token | rode |
Token ID | 22075 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Groups | +0.930 |
ktop | +0.924 |
kernels | +0.905 |
targ | +0.829 |
aurus | +0.815 |
Neg logit contributions | |
ォ | -1.184 |
est | -1.162 |
anas | -1.032 |
ィ | -1.021 |
itals | -0.993 |
Token | 49 |
Token ID | 5125 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Groups | +2.334 |
ktop | +2.310 |
kernels | +2.271 |
targ | +2.078 |
aurus | +2.033 |
Neg logit contributions | |
ォ | -3.040 |
est | -2.955 |
anas | -2.641 |
ィ | -2.607 |
arest | -2.550 |
Token | . |
Token ID | 13 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Groups | +4.186 |
ktop | +4.129 |
kernels | +4.071 |
targ | +3.691 |
slic | +3.609 |
Neg logit contributions | |
ォ | -5.905 |
est | -5.532 |
anas | -5.069 |
ィ | -5.065 |
arest | -4.899 |
Token | 431 |
Token ID | 50080 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Groups | +1.646 |
ktop | +1.602 |
kernels | +1.577 |
targ | +1.427 |
aurus | +1.425 |
Neg logit contributions | |
ォ | -2.107 |
est | -2.044 |
anas | -1.841 |
ィ | -1.806 |
itals | -1.771 |
Token | kilometers |
Token ID | 18212 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Groups | +6.599 |
kernels | +6.567 |
ktop | +6.528 |
rpm | +5.776 |
slic | +5.762 |
Neg logit contributions | |
ォ | -10.257 |
est | -9.309 |
anas | -8.776 |
ィ | -8.748 |
usterity | -8.705 |
Token | on |
Token ID | 319 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
Groups | +0.728 |
ktop | +0.724 |
kernels | +0.710 |
targ | +0.652 |
aurus | +0.642 |
Neg logit contributions | |
ォ | -0.867 |
est | -0.847 |
anas | -0.750 |
ィ | -0.742 |
itals | -0.721 |
Token | the |
Token ID | 262 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
Groups | +0.987 |
ktop | +0.983 |
kernels | +0.960 |
targ | +0.875 |
aurus | +0.863 |
Neg logit contributions | |
ォ | -1.372 |
est | -1.360 |
anas | -1.205 |
ィ | -1.193 |
itals | -1.166 |
Token | traditional |
Token ID | 4569 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ォ | +0.306 |
est | +0.304 |
anas | +0.265 |
ィ | +0.261 |
itals | +0.255 |
Neg logit contributions | |
Groups | -0.281 |
ktop | -0.279 |
kernels | -0.274 |
targ | -0.252 |
aurus | -0.250 |
Token | road |
Token ID | 2975 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
est | +1.383 |
ォ | +1.360 |
anas | +1.179 |
ィ | +1.165 |
itals | +1.138 |
Neg logit contributions | |
Groups | -1.202 |
ktop | -1.199 |
kernels | -1.162 |
aurus | -1.076 |
targ | -1.068 |
Token | beat |
Token ID | 4405 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
Groups | +2.713 |
ktop | +2.707 |
kernels | +2.680 |
targ | +2.454 |
reckoned | +2.427 |
Neg logit contributions | |
ォ | -3.235 |
est | -3.075 |
anas | -2.757 |
ィ | -2.729 |
itals | -2.659 |
Token | him |
Token ID | 683 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Groups | +2.461 |
ktop | +2.438 |
kernels | +2.399 |
targ | +2.209 |
aurus | +2.159 |
Neg logit contributions | |
ォ | -2.878 |
est | -2.792 |
anas | -2.487 |
ィ | -2.456 |
itals | -2.388 |
Token | by |
Token ID | 416 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Groups | +1.274 |
ktop | +1.265 |
kernels | +1.240 |
targ | +1.135 |
aurus | +1.115 |
Neg logit contributions | |
ォ | -1.618 |
est | -1.589 |
anas | -1.410 |
ィ | -1.395 |
itals | -1.357 |
Token | 0 |
Token ID | 657 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
Groups | +1.371 |
ktop | +1.363 |
kernels | +1.338 |
targ | +1.236 |
aurus | +1.199 |
Neg logit contributions | |
ォ | -1.634 |
est | -1.576 |
anas | -1.404 |
ィ | -1.394 |
arest | -1.354 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
Groups | +2.132 |
ktop | +2.084 |
kernels | +2.020 |
aurus | +1.795 |
vg | +1.775 |
Neg logit contributions | |
ォ | -4.144 |
est | -3.787 |
ィ | -3.587 |
anas | -3.544 |
usterity | -3.491 |
Token | 132 |
Token ID | 19924 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Groups | +0.685 |
ktop | +0.670 |
kernels | +0.655 |
aurus | +0.592 |
targ | +0.585 |
Neg logit contributions | |
ォ | -1.006 |
est | -0.974 |
anas | -0.881 |
ィ | -0.867 |
itals | -0.852 |
Token | seconds |
Token ID | 4201 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Groups | +5.596 |
kernels | +5.470 |
ktop | +5.435 |
targ | +4.887 |
cal | +4.885 |
Neg logit contributions | |
ォ | -11.118 |
est | -9.964 |
usterity | -9.468 |
ィ | -9.449 |
anas | -9.401 |
Token | late |
Token ID | 2739 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Groups | +2.052 |
ktop | +2.040 |
kernels | +2.007 |
targ | +1.826 |
aurus | +1.804 |
Neg logit contributions | |
ォ | -2.739 |
est | -2.615 |
anas | -2.353 |
ィ | -2.343 |
itals | -2.276 |
Token | in |
Token ID | 287 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Groups | +0.542 |
ktop | +0.542 |
kernels | +0.527 |
targ | +0.484 |
aurus | +0.479 |
Neg logit contributions | |
est | -0.616 |
ォ | -0.609 |
anas | -0.536 |
ィ | -0.527 |
itals | -0.513 |
Token | the |
Token ID | 262 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ktop | +1.063 |
Groups | +1.056 |
kernels | +1.038 |
targ | +0.945 |
aurus | +0.937 |
Neg logit contributions | |
ォ | -1.332 |
est | -1.332 |
anas | -1.172 |
ィ | -1.152 |
itals | -1.126 |
Token | afternoon |
Token ID | 6672 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Groups | +1.817 |
ktop | +1.790 |
kernels | +1.763 |
targ | +1.625 |
aurus | +1.583 |
Neg logit contributions | |
ォ | -2.176 |
est | -2.113 |
anas | -1.883 |
ィ | -1.866 |
itals | -1.811 |
Token | GTX |
Token ID | 12646 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
est | +0.810 |
ォ | +0.805 |
anas | +0.703 |
ィ | +0.694 |
arest | +0.665 |
Neg logit contributions | |
ktop | -0.802 |
Groups | -0.790 |
kernels | -0.778 |
targ | -0.715 |
aurus | -0.703 |
Token | 1080 |
Token ID | 24045 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
ktop | +0.311 |
Groups | +0.310 |
kernels | +0.304 |
targ | +0.285 |
aurus | +0.279 |
Neg logit contributions | |
ォ | -0.240 |
est | -0.237 |
anas | -0.204 |
ィ | -0.200 |
arest | -0.193 |
Token | ships |
Token ID | 7937 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Groups | +1.651 |
ktop | +1.635 |
kernels | +1.612 |
targ | +1.490 |
aurus | +1.468 |
Neg logit contributions | |
ォ | -1.745 |
est | -1.697 |
anas | -1.496 |
ィ | -1.476 |
itals | -1.436 |
Token | with |
Token ID | 351 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
Groups | +0.565 |
ktop | +0.563 |
kernels | +0.547 |
targ | +0.501 |
aurus | +0.493 |
Neg logit contributions | |
ォ | -0.776 |
est | -0.767 |
anas | -0.680 |
ィ | -0.673 |
itals | -0.655 |
Token | 25 |
Token ID | 1679 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
ォ | +0.067 |
est | +0.067 |
anas | +0.059 |
ィ | +0.058 |
arest | +0.056 |
Neg logit contributions | |
ktop | -0.056 |
Groups | -0.056 |
kernels | -0.054 |
targ | -0.050 |
aurus | -0.049 |
Token | 60 |
Token ID | 1899 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Groups | +1.814 |
ktop | +1.790 |
kernels | +1.761 |
targ | +1.592 |
aurus | +1.561 |
Neg logit contributions | |
ォ | -2.731 |
est | -2.677 |
anas | -2.406 |
ィ | -2.378 |
itals | -2.322 |
Token | CU |
Token ID | 29369 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
Groups | +6.470 |
kernels | +6.370 |
ktop | +5.896 |
targ | +5.481 |
rpm | +5.438 |
Neg logit contributions | |
ォ | -10.165 |
est | -9.584 |
anas | -8.803 |
usterity | -8.698 |
itals | -8.539 |
Token | DA |
Token ID | 5631 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
est | +0.343 |
ォ | +0.331 |
anas | +0.305 |
arest | +0.284 |
ィ | +0.284 |
Neg logit contributions | |
ktop | -0.371 |
Groups | -0.354 |
kernels | -0.342 |
targ | -0.328 |
aurus | -0.322 |
Token | cores |
Token ID | 21758 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
kernels | +3.749 |
Groups | +3.656 |
ktop | +3.348 |
targ | +2.908 |
aurus | +2.856 |
Neg logit contributions | |
ォ | -9.864 |
est | -9.136 |
anas | -8.638 |
ィ | -8.439 |
itals | -8.368 |
Token | and |
Token ID | 290 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
kernels | +4.391 |
Groups | +4.380 |
ktop | +4.254 |
targ | +3.928 |
aurus | +3.912 |
Neg logit contributions | |
ォ | -6.028 |
est | -5.556 |
anas | -5.117 |
ィ | -5.064 |
itals | -5.025 |
Token | 20 |
Token ID | 1160 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Groups | +1.622 |
ktop | +1.602 |
kernels | +1.587 |
targ | +1.471 |
aurus | +1.442 |
Neg logit contributions | |
ォ | -1.588 |
est | -1.535 |
anas | -1.345 |
ィ | -1.331 |
itals | -1.295 |
Token | Har |
Token ID | 2113 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ォ | +0.566 |
est | +0.564 |
anas | +0.494 |
ィ | +0.482 |
arest | +0.474 |
Neg logit contributions | |
ktop | -0.538 |
Groups | -0.525 |
kernels | -0.521 |
targ | -0.483 |
aurus | -0.475 |
Token | v |
Token ID | 85 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Groups | +0.495 |
ktop | +0.492 |
kernels | +0.483 |
targ | +0.442 |
aurus | +0.433 |
Neg logit contributions | |
ォ | -0.648 |
est | -0.640 |
anas | -0.568 |
ィ | -0.559 |
itals | -0.547 |
Token | ests |
Token ID | 3558 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
est | +1.352 |
ォ | +1.248 |
anas | +1.036 |
itals | +0.938 |
ィ | +0.930 |
Neg logit contributions | |
ktop | -3.024 |
Groups | -3.014 |
kernels | -2.989 |
targ | -2.819 |
aurus | -2.801 |
Token |
|
Token ID | 198 |
Feature activation | -1.77e-03 |
Pos logit contributions | |
ォ | +0.569 |
est | +0.568 |
anas | +0.481 |
ィ | +0.480 |
arest | +0.460 |
Neg logit contributions | |
ktop | -0.683 |
Groups | -0.682 |
kernels | -0.672 |
targ | -0.625 |
aurus | -0.608 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Groups | +0.008 |
ktop | +0.007 |
kernels | +0.007 |
aurus | +0.007 |
targ | +0.006 |
Neg logit contributions | |
ォ | -0.008 |
est | -0.007 |
anas | -0.006 |
ィ | -0.006 |
itals | -0.006 |
Token | Hot |
Token ID | 21352 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Groups | +0.479 |
ktop | +0.476 |
kernels | +0.468 |
targ | +0.433 |
aurus | +0.424 |
Neg logit contributions | |
ォ | -0.508 |
est | -0.500 |
anas | -0.438 |
ィ | -0.433 |
arest | -0.420 |
Token | Soup |
Token ID | 34011 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Groups | +8.635 |
ktop | +8.230 |
kernels | +8.169 |
aurus | +7.644 |
targ | +7.446 |
Neg logit contributions | |
ォ | -7.834 |
est | -6.964 |
ィ | -6.689 |
itals | -6.541 |
anas | -6.402 |
Token | vs |
Token ID | 3691 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
est | +1.474 |
ォ | +1.470 |
anas | +1.269 |
ィ | +1.263 |
arest | +1.219 |
Neg logit contributions | |
ktop | -1.383 |
Groups | -1.361 |
kernels | -1.334 |
targ | -1.237 |
aurus | -1.213 |
Token | Block |
Token ID | 9726 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
Groups | +1.361 |
ktop | +1.350 |
kernels | +1.327 |
targ | +1.228 |
aurus | +1.211 |
Neg logit contributions | |
ォ | -1.383 |
est | -1.351 |
anas | -1.184 |
ィ | -1.169 |
itals | -1.135 |
Token | buster |
Token ID | 24899 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
est | +1.711 |
ォ | +1.706 |
anas | +1.463 |
ィ | +1.423 |
arest | +1.411 |
Neg logit contributions | |
ktop | -1.864 |
Groups | -1.835 |
kernels | -1.821 |
targ | -1.690 |
aurus | -1.622 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ォ | +0.629 |
est | +0.622 |
anas | +0.535 |
ィ | +0.529 |
arest | +0.511 |
Neg logit contributions | |
ktop | -0.695 |
Groups | -0.689 |
kernels | -0.679 |
targ | -0.632 |
aurus | -0.616 |
Token | on |
Token ID | 319 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Groups | +0.126 |
ktop | +0.125 |
kernels | +0.123 |
targ | +0.112 |
aurus | +0.110 |
Neg logit contributions | |
est | -0.154 |
ォ | -0.154 |
anas | -0.135 |
ィ | -0.133 |
itals | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
est | +1.413 |
ォ | +1.400 |
anas | +1.222 |
ィ | +1.213 |
arest | +1.190 |
Neg logit contributions | |
ktop | -1.198 |
Groups | -1.196 |
kernels | -1.176 |
targ | -1.088 |
aurus | -1.062 |
Token | This |
Token ID | 770 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
ォ | +0.917 |
est | +0.912 |
anas | +0.794 |
ィ | +0.778 |
arest | +0.758 |
Neg logit contributions | |
ktop | -0.945 |
Groups | -0.932 |
kernels | -0.924 |
targ | -0.858 |
aurus | -0.842 |
Token | charity |
Token ID | 11016 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ktop | +0.107 |
Groups | +0.106 |
kernels | +0.104 |
targ | +0.097 |
aurus | +0.096 |
Neg logit contributions | |
ォ | -0.109 |
est | -0.108 |
anas | -0.094 |
ィ | -0.093 |
itals | -0.090 |
Token | helps |
Token ID | 5419 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Groups | +0.706 |
ktop | +0.705 |
kernels | +0.691 |
targ | +0.641 |
aurus | +0.632 |
Neg logit contributions | |
ォ | -0.678 |
est | -0.665 |
anas | -0.579 |
ィ | -0.572 |
itals | -0.554 |
Token | Bur |
Token ID | 5481 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
ktop | +0.396 |
Groups | +0.395 |
kernels | +0.386 |
targ | +0.357 |
aurus | +0.351 |
Neg logit contributions | |
ォ | -0.464 |
est | -0.460 |
anas | -0.404 |
ィ | -0.400 |
arest | -0.388 |
Token | m |
Token ID | 76 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
Groups | +4.640 |
ktop | +4.511 |
kernels | +4.394 |
aurus | +3.727 |
rings | +3.522 |
Neg logit contributions | |
ォ | -12.056 |
est | -11.426 |
ィ | -10.565 |
usterity | -10.414 |
anas | -10.292 |
Token | ese |
Token ID | 2771 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
est | +0.048 |
ォ | +0.046 |
anas | +0.039 |
ィ | +0.038 |
itals | +0.037 |
Neg logit contributions | |
ktop | -0.071 |
Groups | -0.071 |
kernels | -0.070 |
targ | -0.065 |
aurus | -0.064 |
Token | refugees |
Token ID | 8015 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
Groups | +2.458 |
ktop | +2.396 |
kernels | +2.365 |
targ | +2.155 |
aurus | +2.119 |
Neg logit contributions | |
ォ | -2.901 |
est | -2.782 |
anas | -2.507 |
ィ | -2.451 |
itals | -2.409 |
Token | in |
Token ID | 287 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Groups | +1.438 |
ktop | +1.423 |
kernels | +1.397 |
targ | +1.275 |
aurus | +1.260 |
Neg logit contributions | |
ォ | -1.786 |
est | -1.738 |
anas | -1.549 |
ィ | -1.530 |
itals | -1.489 |
Token | Thailand |
Token ID | 16952 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
Groups | +0.883 |
ktop | +0.878 |
kernels | +0.859 |
targ | +0.784 |
aurus | +0.769 |
Neg logit contributions | |
ォ | -1.221 |
est | -1.200 |
anas | -1.070 |
ィ | -1.058 |
itals | -1.032 |
Token | perceptions |
Token ID | 23574 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
est | +1.805 |
ォ | +1.728 |
anas | +1.556 |
ィ | +1.496 |
itals | +1.471 |
Neg logit contributions | |
ktop | -1.545 |
Groups | -1.523 |
kernels | -1.433 |
aurus | -1.358 |
targ | -1.326 |
Token | that |
Token ID | 326 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
est | +1.597 |
ォ | +1.548 |
anas | +1.375 |
ィ | +1.350 |
arest | +1.320 |
Neg logit contributions | |
ktop | -1.357 |
Groups | -1.351 |
kernels | -1.301 |
targ | -1.196 |
aurus | -1.189 |
Token | regimes |
Token ID | 25879 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ォ | +1.313 |
est | +1.309 |
anas | +1.161 |
ィ | +1.142 |
arest | +1.116 |
Neg logit contributions | |
ktop | -1.054 |
Groups | -1.029 |
kernels | -1.003 |
targ | -0.912 |
aurus | -0.910 |
Token | promoted |
Token ID | 13722 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Groups | +4.042 |
ktop | +3.998 |
kernels | +3.959 |
targ | +3.637 |
aurus | +3.632 |
Neg logit contributions | |
ォ | -5.277 |
est | -4.963 |
anas | -4.513 |
ィ | -4.507 |
arest | -4.350 |
Token | in |
Token ID | 287 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
Groups | +0.921 |
ktop | +0.915 |
kernels | +0.897 |
targ | +0.823 |
aurus | +0.808 |
Neg logit contributions | |
ォ | -1.141 |
est | -1.119 |
anas | -0.992 |
ィ | -0.981 |
itals | -0.955 |
Token | order |
Token ID | 1502 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
est | +0.312 |
ォ | +0.312 |
anas | +0.276 |
ィ | +0.271 |
arest | +0.266 |
Neg logit contributions | |
ktop | -0.245 |
Groups | -0.244 |
kernels | -0.236 |
targ | -0.218 |
aurus | -0.215 |
Token | to |
Token ID | 284 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
Groups | +4.428 |
ktop | +4.415 |
kernels | +4.314 |
targ | +3.804 |
aurus | +3.747 |
Neg logit contributions | |
ォ | -11.958 |
est | -11.064 |
anas | -10.597 |
ィ | -10.293 |
usterity | -10.201 |
Token | slow |
Token ID | 3105 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Groups | +1.866 |
ktop | +1.846 |
kernels | +1.820 |
targ | +1.680 |
aurus | +1.647 |
Neg logit contributions | |
ォ | -2.116 |
est | -2.052 |
anas | -1.823 |
ィ | -1.804 |
itals | -1.746 |
Token | down |
Token ID | 866 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
est | +0.656 |
ォ | +0.645 |
anas | +0.564 |
ィ | +0.553 |
arest | +0.539 |
Neg logit contributions | |
ktop | -0.619 |
Groups | -0.617 |
kernels | -0.599 |
targ | -0.557 |
aurus | -0.552 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Groups | +0.705 |
ktop | +0.703 |
kernels | +0.685 |
targ | +0.628 |
aurus | +0.617 |
Neg logit contributions | |
ォ | -0.931 |
est | -0.920 |
anas | -0.816 |
ィ | -0.806 |
arest | -0.786 |
Token | momentum |
Token ID | 12858 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
Groups | +0.389 |
ktop | +0.388 |
kernels | +0.378 |
targ | +0.348 |
aurus | +0.343 |
Neg logit contributions | |
ォ | -0.471 |
est | -0.466 |
anas | -0.411 |
ィ | -0.406 |
arest | -0.395 |
Token | ster |
Token ID | 1706 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Groups | +3.134 |
ktop | +3.066 |
kernels | +3.027 |
targ | +2.794 |
aurus | +2.778 |
Neg logit contributions | |
ォ | -3.261 |
est | -3.097 |
ィ | -2.758 |
anas | -2.736 |
itals | -2.646 |
Token | ," |
Token ID | 553 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
Groups | +1.724 |
ktop | +1.711 |
kernels | +1.681 |
targ | +1.552 |
aurus | +1.529 |
Neg logit contributions | |
ォ | -1.845 |
est | -1.802 |
anas | -1.585 |
ィ | -1.567 |
itals | -1.520 |
Token | from |
Token ID | 422 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
ォ | +1.409 |
est | +1.403 |
anas | +1.222 |
ィ | +1.200 |
arest | +1.167 |
Neg logit contributions | |
ktop | -1.388 |
Groups | -1.374 |
kernels | -1.344 |
targ | -1.248 |
aurus | -1.215 |
Token | 1971 |
Token ID | 16382 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ォ | +0.384 |
est | +0.378 |
anas | +0.333 |
ィ | +0.325 |
arest | +0.315 |
Neg logit contributions | |
ktop | -0.349 |
Groups | -0.342 |
kernels | -0.338 |
targ | -0.312 |
aurus | -0.305 |
Token | 's |
Token ID | 338 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Groups | +3.757 |
ktop | +3.645 |
kernels | +3.624 |
targ | +3.298 |
aurus | +3.230 |
Neg logit contributions | |
ォ | -5.517 |
est | -5.358 |
anas | -4.812 |
ィ | -4.794 |
itals | -4.684 |
Token | Electric |
Token ID | 13944 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Groups | +5.669 |
ktop | +5.422 |
kernels | +5.419 |
targ | +4.975 |
aurus | +4.961 |
Neg logit contributions | |
ォ | -6.055 |
est | -5.805 |
anas | -5.155 |
ィ | -5.126 |
itals | -5.032 |
Token | Warrior |
Token ID | 14019 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Groups | +8.090 |
ktop | +7.535 |
kernels | +7.223 |
aurus | +7.210 |
Writer | +6.936 |
Neg logit contributions | |
ォ | -9.059 |
est | -7.760 |
itals | -7.451 |
usterity | -7.288 |
ィ | -7.214 |
Token | . |
Token ID | 13 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
ktop | +1.122 |
Groups | +1.114 |
kernels | +1.093 |
targ | +1.011 |
aurus | +0.986 |
Neg logit contributions | |
ォ | -1.305 |
est | -1.290 |
anas | -1.135 |
ィ | -1.118 |
arest | -1.088 |
Token | Not |
Token ID | 1892 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
Groups | +1.317 |
ktop | +1.289 |
kernels | +1.268 |
targ | +1.169 |
aurus | +1.156 |
Neg logit contributions | |
ォ | -1.431 |
est | -1.400 |
anas | -1.237 |
ィ | -1.219 |
itals | -1.193 |
Token | metal |
Token ID | 6147 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
est | +0.389 |
ォ | +0.389 |
anas | +0.344 |
ィ | +0.336 |
arest | +0.329 |
Neg logit contributions | |
ktop | -0.297 |
Groups | -0.296 |
kernels | -0.286 |
targ | -0.262 |
aurus | -0.255 |
Token | but |
Token ID | 475 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Groups | +4.069 |
kernels | +4.027 |
ktop | +3.953 |
targ | +3.638 |
aurus | +3.569 |
Neg logit contributions | |
ォ | -5.150 |
est | -4.824 |
ィ | -4.425 |
anas | -4.372 |
itals | -4.225 |
Token | to |
Token ID | 284 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
est | +0.249 |
ォ | +0.248 |
anas | +0.218 |
ィ | +0.214 |
itals | +0.208 |
Neg logit contributions | |
Groups | -0.213 |
ktop | -0.213 |
kernels | -0.203 |
targ | -0.191 |
aurus | -0.187 |
Token | mind |
Token ID | 2000 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
est | +0.039 |
ォ | +0.039 |
anas | +0.032 |
arest | +0.031 |
ィ | +0.031 |
Neg logit contributions | |
Groups | -0.067 |
ktop | -0.067 |
kernels | -0.065 |
targ | -0.062 |
aurus | -0.061 |
Token | a |
Token ID | 257 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
Groups | +1.335 |
ktop | +1.329 |
kernels | +1.291 |
targ | +1.187 |
aurus | +1.168 |
Neg logit contributions | |
ォ | -1.738 |
est | -1.713 |
anas | -1.523 |
ィ | -1.499 |
arest | -1.463 |
Token | modern |
Token ID | 3660 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
Groups | +1.596 |
ktop | +1.584 |
kernels | +1.565 |
targ | +1.441 |
aurus | +1.410 |
Neg logit contributions | |
ォ | -1.855 |
est | -1.804 |
anas | -1.600 |
ィ | -1.587 |
itals | -1.549 |
Token | - |
Token ID | 12 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Groups | +3.019 |
ktop | +3.013 |
kernels | +2.996 |
targ | +2.744 |
aurus | +2.679 |
Neg logit contributions | |
ォ | -3.840 |
est | -3.652 |
anas | -3.307 |
ィ | -3.303 |
itals | -3.216 |
Token | day |
Token ID | 820 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ktop | +3.275 |
Groups | +3.157 |
kernels | +3.143 |
cal | +2.689 |
targ | +2.633 |
Neg logit contributions | |
ォ | -8.440 |
est | -7.963 |
ィ | -7.486 |
anas | -7.412 |
itals | -7.284 |
Token | English |
Token ID | 3594 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
kernels | +7.488 |
Groups | +7.374 |
ktop | +7.238 |
targ | +6.887 |
aurus | +6.604 |
Neg logit contributions | |
ォ | -8.732 |
est | -8.017 |
ィ | -7.445 |
anas | -7.359 |
itals | -7.305 |
Token | tea |
Token ID | 8887 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
Groups | +0.608 |
ktop | +0.604 |
kernels | +0.592 |
targ | +0.542 |
aurus | +0.533 |
Neg logit contributions | |
ォ | -0.743 |
est | -0.730 |
anas | -0.645 |
ィ | -0.638 |
arest | -0.620 |
Token | cake |
Token ID | 12187 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
Groups | +0.091 |
ktop | +0.090 |
kernels | +0.088 |
targ | +0.081 |
aurus | +0.080 |
Neg logit contributions | |
ォ | -0.110 |
est | -0.109 |
anas | -0.096 |
ィ | -0.095 |
arest | -0.093 |
Token | -- |
Token ID | 1377 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Groups | +1.778 |
ktop | +1.768 |
kernels | +1.747 |
targ | +1.600 |
aurus | +1.565 |
Neg logit contributions | |
ォ | -2.244 |
est | -2.177 |
anas | -1.944 |
ィ | -1.932 |
itals | -1.882 |
Token | we |
Token ID | 356 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
Groups | +0.801 |
ktop | +0.799 |
kernels | +0.776 |
targ | +0.714 |
aurus | +0.701 |
Neg logit contributions | |
ォ | -1.027 |
est | -1.012 |
anas | -0.898 |
ィ | -0.886 |
arest | -0.863 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Groups | +1.063 |
ktop | +1.058 |
kernels | +1.036 |
targ | +0.950 |
aurus | +0.932 |
Neg logit contributions | |
ォ | -1.333 |
est | -1.312 |
anas | -1.161 |
ィ | -1.148 |
arest | -1.117 |
Token | There |
Token ID | 1318 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Groups | +0.468 |
ktop | +0.464 |
kernels | +0.456 |
targ | +0.419 |
aurus | +0.413 |
Neg logit contributions | |
ォ | -0.535 |
est | -0.524 |
anas | -0.463 |
ィ | -0.457 |
itals | -0.444 |
Token | are |
Token ID | 389 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Groups | +0.770 |
ktop | +0.766 |
kernels | +0.751 |
targ | +0.699 |
aurus | +0.686 |
Neg logit contributions | |
ォ | -0.739 |
est | -0.728 |
anas | -0.635 |
ィ | -0.626 |
itals | -0.607 |
Token | no |
Token ID | 645 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
Groups | +0.494 |
ktop | +0.492 |
kernels | +0.480 |
targ | +0.444 |
aurus | +0.437 |
Neg logit contributions | |
ォ | -0.570 |
est | -0.561 |
anas | -0.495 |
ィ | -0.490 |
arest | -0.475 |
Token | credible |
Token ID | 18409 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
Groups | +2.670 |
kernels | +2.622 |
ktop | +2.592 |
targ | +2.369 |
leagues | +2.305 |
Neg logit contributions | |
ォ | -3.174 |
est | -3.046 |
anas | -2.724 |
ィ | -2.682 |
itals | -2.640 |
Token | grounds |
Token ID | 9384 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Groups | +1.797 |
kernels | +1.756 |
ktop | +1.756 |
targ | +1.580 |
aurus | +1.521 |
Neg logit contributions | |
ォ | -2.755 |
est | -2.665 |
anas | -2.408 |
ィ | -2.383 |
itals | -2.333 |
Token | even |
Token ID | 772 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
Groups | +5.816 |
ktop | +5.656 |
kernels | +5.617 |
targ | +4.934 |
leagues | +4.885 |
Neg logit contributions | |
ォ | -10.451 |
est | -9.897 |
anas | -9.157 |
usterity | -9.093 |
ィ | -9.006 |
Token | to |
Token ID | 284 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
Groups | +2.700 |
ktop | +2.666 |
kernels | +2.633 |
targ | +2.390 |
aurus | +2.341 |
Neg logit contributions | |
ォ | -3.919 |
est | -3.765 |
anas | -3.416 |
ィ | -3.380 |
itals | -3.280 |
Token | imagine |
Token ID | 5967 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Groups | +1.775 |
ktop | +1.753 |
kernels | +1.725 |
targ | +1.579 |
aurus | +1.527 |
Neg logit contributions | |
ォ | -2.627 |
est | -2.547 |
anas | -2.306 |
ィ | -2.288 |
itals | -2.222 |
Token | than |
Token ID | 621 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
est | +1.175 |
ォ | +1.152 |
anas | +1.014 |
ィ | +1.006 |
arest | +0.984 |
Neg logit contributions | |
ktop | -0.887 |
Groups | -0.868 |
kernels | -0.849 |
aurus | -0.780 |
targ | -0.774 |
Token | an |
Token ID | 281 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
Groups | +2.544 |
ktop | +2.495 |
kernels | +2.464 |
targ | +2.243 |
aurus | +2.193 |
Neg logit contributions | |
ォ | -3.502 |
est | -3.397 |
anas | -3.064 |
ィ | -3.022 |
itals | -2.955 |
Token | particular |
Token ID | 1948 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Groups | +0.278 |
ktop | +0.277 |
kernels | +0.271 |
targ | +0.249 |
aurus | +0.244 |
Neg logit contributions | |
ォ | -0.340 |
est | -0.333 |
anas | -0.296 |
ィ | -0.292 |
itals | -0.284 |
Token | sonic |
Token ID | 36220 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Groups | +1.943 |
ktop | +1.939 |
kernels | +1.923 |
targ | +1.748 |
aurus | +1.693 |
Neg logit contributions | |
ォ | -2.610 |
est | -2.501 |
anas | -2.289 |
ィ | -2.245 |
itals | -2.199 |
Token | grain |
Token ID | 13020 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
ォ | +0.740 |
est | +0.739 |
anas | +0.640 |
ィ | +0.637 |
arest | +0.619 |
Neg logit contributions | |
Groups | -0.601 |
ktop | -0.595 |
kernels | -0.577 |
targ | -0.530 |
aurus | -0.527 |
Token | : |
Token ID | 25 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
Groups | +2.237 |
ktop | +2.223 |
kernels | +2.190 |
targ | +1.996 |
aurus | +1.951 |
Neg logit contributions | |
ォ | -2.920 |
est | -2.847 |
anas | -2.556 |
ィ | -2.520 |
itals | -2.462 |
Token | a |
Token ID | 257 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
Groups | +2.093 |
ktop | +2.067 |
kernels | +2.044 |
targ | +1.869 |
aurus | +1.832 |
Neg logit contributions | |
ォ | -2.516 |
est | -2.461 |
anas | -2.187 |
ィ | -2.151 |
itals | -2.103 |
Token | ground |
Token ID | 2323 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
ォ | +0.097 |
est | +0.096 |
anas | +0.084 |
ィ | +0.084 |
arest | +0.081 |
Neg logit contributions | |
Groups | -0.079 |
ktop | -0.079 |
kernels | -0.077 |
targ | -0.071 |
aurus | -0.070 |
Token | level |
Token ID | 1241 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
kernels | +7.063 |
Groups | +6.892 |
ktop | +6.877 |
targ | +6.608 |
aurus | +6.356 |
Neg logit contributions | |
ォ | -8.802 |
est | -8.333 |
anas | -7.855 |
ィ | -7.611 |
usterity | -7.483 |
Token | of |
Token ID | 286 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Groups | +1.826 |
ktop | +1.819 |
kernels | +1.796 |
targ | +1.654 |
aurus | +1.616 |
Neg logit contributions | |
ォ | -2.223 |
est | -2.151 |
anas | -1.933 |
ィ | -1.899 |
itals | -1.859 |
Token | noise |
Token ID | 7838 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Groups | +0.521 |
ktop | +0.518 |
kernels | +0.507 |
targ | +0.467 |
aurus | +0.460 |
Neg logit contributions | |
ォ | -0.601 |
est | -0.589 |
anas | -0.520 |
ィ | -0.514 |
arest | -0.499 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
Groups | +2.032 |
ktop | +2.019 |
kernels | +1.999 |
targ | +1.823 |
aurus | +1.787 |
Neg logit contributions | |
ォ | -2.534 |
est | -2.448 |
anas | -2.199 |
ィ | -2.174 |
itals | -2.126 |
Token | which |
Token ID | 543 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
Groups | +2.038 |
ktop | +2.036 |
kernels | +2.011 |
targ | +1.853 |
aurus | +1.816 |
Neg logit contributions | |
ォ | -2.018 |
est | -1.961 |
anas | -1.726 |
ィ | -1.705 |
itals | -1.653 |
Token | became |
Token ID | 2627 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
ktop | +0.563 |
Groups | +0.560 |
kernels | +0.545 |
targ | +0.500 |
aurus | +0.497 |
Neg logit contributions | |
est | -0.682 |
ォ | -0.681 |
anas | -0.603 |
ィ | -0.584 |
itals | -0.576 |
Token | long |
Token ID | 890 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
est | +1.819 |
ォ | +1.799 |
anas | +1.597 |
ィ | +1.544 |
itals | +1.531 |
Neg logit contributions | |
ktop | -1.455 |
Groups | -1.448 |
kernels | -1.394 |
aurus | -1.281 |
targ | -1.267 |
Token | and |
Token ID | 290 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Groups | +0.633 |
ktop | +0.628 |
kernels | +0.616 |
targ | +0.566 |
aurus | +0.555 |
Neg logit contributions | |
ォ | -0.783 |
est | -0.767 |
anas | -0.681 |
ィ | -0.674 |
itals | -0.655 |
Token | mandatory |
Token ID | 13677 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
est | +1.634 |
ォ | +1.611 |
anas | +1.414 |
ィ | +1.371 |
itals | +1.349 |
Neg logit contributions | |
Groups | -1.517 |
ktop | -1.512 |
kernels | -1.448 |
aurus | -1.352 |
targ | -1.342 |
Token | . |
Token ID | 13 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
est | +2.687 |
ォ | +2.652 |
anas | +2.319 |
ィ | +2.245 |
itals | +2.230 |
Neg logit contributions | |
ktop | -2.371 |
Groups | -2.332 |
kernels | -2.267 |
targ | -2.105 |
aurus | -2.102 |
Token | Nearly |
Token ID | 21233 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ォ | +1.819 |
est | +1.800 |
anas | +1.539 |
ィ | +1.531 |
itals | +1.457 |
Neg logit contributions | |
ktop | -2.003 |
kernels | -1.957 |
Groups | -1.908 |
targ | -1.839 |
aurus | -1.773 |
Token | the |
Token ID | 262 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
est | +7.348 |
ォ | +6.237 |
anas | +5.880 |
ィ | +5.570 |
itals | +5.559 |
Neg logit contributions | |
ktop | -9.913 |
Groups | -9.124 |
kernels | -8.908 |
gart | -8.648 |
aurus | -8.575 |
Token | whole |
Token ID | 2187 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
est | +3.369 |
ォ | +3.249 |
anas | +2.788 |
ィ | +2.730 |
itals | +2.650 |
Neg logit contributions | |
ktop | -4.659 |
Groups | -4.505 |
kernels | -4.394 |
aurus | -4.198 |
targ | -4.187 |
Token | of |
Token ID | 286 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
est | +1.555 |
ォ | +1.532 |
anas | +1.340 |
ィ | +1.321 |
itals | +1.277 |
Neg logit contributions | |
ktop | -1.461 |
Groups | -1.453 |
kernels | -1.417 |
targ | -1.305 |
aurus | -1.301 |
Token | the |
Token ID | 262 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
est | +1.526 |
ォ | +1.523 |
anas | +1.341 |
ィ | +1.299 |
itals | +1.282 |
Neg logit contributions | |
ktop | -1.350 |
Groups | -1.329 |
kernels | -1.302 |
targ | -1.194 |
aurus | -1.189 |
Token | change |
Token ID | 1487 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
est | +2.858 |
ォ | +2.776 |
anas | +2.458 |
ィ | +2.389 |
itals | +2.319 |
Neg logit contributions | |
ktop | -2.737 |
Groups | -2.684 |
kernels | -2.618 |
aurus | -2.451 |
targ | -2.431 |
Token | sphere |
Token ID | 16558 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Groups | +1.094 |
ktop | +1.089 |
kernels | +1.066 |
targ | +0.980 |
aurus | +0.966 |
Neg logit contributions | |
ォ | -1.258 |
est | -1.235 |
anas | -1.089 |
ィ | -1.076 |
arest | -1.046 |
Token | to |
Token ID | 284 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
est | +0.860 |
ォ | +0.858 |
anas | +0.758 |
ィ | +0.750 |
arest | +0.728 |
Neg logit contributions | |
Groups | -0.626 |
ktop | -0.620 |
kernels | -0.600 |
targ | -0.541 |
aurus | -0.534 |
Token | try |
Token ID | 1949 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
Groups | +1.647 |
ktop | +1.634 |
kernels | +1.604 |
targ | +1.482 |
aurus | +1.456 |
Neg logit contributions | |
ォ | -1.832 |
est | -1.790 |
anas | -1.578 |
ィ | -1.562 |
itals | -1.519 |
Token | to |
Token ID | 284 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Groups | +1.726 |
ktop | +1.714 |
kernels | +1.678 |
targ | +1.522 |
aurus | +1.497 |
Neg logit contributions | |
ォ | -2.418 |
est | -2.390 |
anas | -2.127 |
ィ | -2.105 |
arest | -2.053 |
Token | kill |
Token ID | 1494 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
Groups | +1.427 |
ktop | +1.418 |
kernels | +1.392 |
targ | +1.283 |
aurus | +1.258 |
Neg logit contributions | |
ォ | -1.689 |
est | -1.647 |
anas | -1.462 |
ィ | -1.446 |
itals | -1.406 |
Token | Gand |
Token ID | 17727 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
est | +0.172 |
ォ | +0.171 |
anas | +0.149 |
ィ | +0.146 |
arest | +0.142 |
Neg logit contributions | |
ktop | -0.173 |
Groups | -0.171 |
kernels | -0.168 |
targ | -0.156 |
aurus | -0.154 |
Token | alf |
Token ID | 1604 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
est | +4.343 |
ォ | +3.781 |
anas | +3.309 |
arest | +3.165 |
ィ | +2.993 |
Neg logit contributions | |
ktop | -8.776 |
Groups | -8.648 |
kernels | -8.618 |
targ | -8.393 |
enthusi | -8.274 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Groups | +0.349 |
ktop | +0.347 |
kernels | +0.339 |
targ | +0.312 |
aurus | +0.306 |
Neg logit contributions | |
ォ | -0.411 |
est | -0.411 |
anas | -0.361 |
ィ | -0.355 |
arest | -0.348 |
Token | P |
Token ID | 350 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ォ | +0.811 |
est | +0.803 |
anas | +0.697 |
ィ | +0.689 |
arest | +0.666 |
Neg logit contributions | |
ktop | -0.823 |
Groups | -0.806 |
kernels | -0.801 |
targ | -0.743 |
aurus | -0.728 |
Token | ipp |
Token ID | 3974 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
Groups | +0.431 |
ktop | +0.429 |
kernels | +0.419 |
targ | +0.381 |
aurus | +0.373 |
Neg logit contributions | |
ォ | -0.592 |
est | -0.587 |
anas | -0.523 |
ィ | -0.513 |
arest | -0.504 |
Token | in |
Token ID | 259 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
Groups | +2.827 |
ktop | +2.793 |
kernels | +2.728 |
aurus | +2.604 |
rings | +2.563 |
Neg logit contributions | |
ォ | -3.847 |
est | -3.293 |
ィ | -3.242 |
usterity | -3.168 |
��� | -3.125 |
Token | ad |
Token ID | 324 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
ktop | +0.574 |
Groups | +0.566 |
kernels | +0.556 |
targ | +0.523 |
aurus | +0.516 |
Neg logit contributions | |
est | -0.473 |
ォ | -0.468 |
anas | -0.410 |
ィ | -0.396 |
arest | -0.382 |
Token | ans |
Token ID | 504 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Groups | +2.029 |
ktop | +1.969 |
kernels | +1.949 |
targ | +1.739 |
aurus | +1.733 |
Neg logit contributions | |
ォ | -3.783 |
est | -3.629 |
ィ | -3.299 |
anas | -3.271 |
itals | -3.239 |
Token | asserting |
Token ID | 33183 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
Groups | +4.421 |
ktop | +4.307 |
kernels | +4.271 |
aurus | +3.921 |
targ | +3.900 |
Neg logit contributions | |
ォ | -5.020 |
est | -4.829 |
anas | -4.361 |
ィ | -4.245 |
itals | -4.167 |
Token | by |
Token ID | 416 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
Groups | +2.530 |
ktop | +2.487 |
kernels | +2.452 |
targ | +2.205 |
aurus | +2.157 |
Neg logit contributions | |
ォ | -3.910 |
est | -3.791 |
anas | -3.439 |
ィ | -3.375 |
arest | -3.323 |
Token | an |
Token ID | 281 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
ォ | +0.233 |
est | +0.232 |
anas | +0.204 |
ィ | +0.202 |
itals | +0.196 |
Neg logit contributions | |
ktop | -0.192 |
Groups | -0.191 |
kernels | -0.186 |
targ | -0.172 |
aurus | -0.169 |
Token | almost |
Token ID | 2048 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
est | +1.925 |
ォ | +1.836 |
anas | +1.634 |
ィ | +1.557 |
itals | +1.518 |
Neg logit contributions | |
ktop | -2.263 |
Groups | -2.253 |
kernels | -2.194 |
targ | -2.074 |
aurus | -2.036 |
Token | 2 |
Token ID | 362 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
est | +5.940 |
ォ | +5.137 |
anas | +4.701 |
ィ | +4.535 |
arest | +4.483 |
Neg logit contributions | |
ktop | -7.353 |
Groups | -7.133 |
kernels | -6.836 |
aurus | -6.658 |
targ | -6.587 |
Token | - |
Token ID | 12 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
est | +1.729 |
ォ | +1.693 |
anas | +1.456 |
ィ | +1.449 |
arest | +1.414 |
Neg logit contributions | |
ktop | -1.702 |
Groups | -1.657 |
kernels | -1.627 |
targ | -1.519 |
aurus | -1.486 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ktop | +0.846 |
Groups | +0.845 |
kernels | +0.824 |
targ | +0.750 |
aurus | +0.737 |
Neg logit contributions | |
est | -1.177 |
ォ | -1.174 |
anas | -1.039 |
ィ | -1.022 |
arest | -1.003 |
Token | margin |
Token ID | 10330 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
est | +0.521 |
ォ | +0.519 |
anas | +0.454 |
ィ | +0.450 |
arest | +0.435 |
Neg logit contributions | |
ktop | -0.431 |
Groups | -0.428 |
kernels | -0.417 |
targ | -0.386 |
aurus | -0.378 |
Token | that |
Token ID | 326 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
est | +0.315 |
ォ | +0.315 |
ィ | +0.277 |
anas | +0.275 |
arest | +0.268 |
Neg logit contributions | |
ktop | -0.232 |
Groups | -0.229 |
kernels | -0.225 |
targ | -0.208 |
aurus | -0.202 |
Token | Nicholas |
Token ID | 20320 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
ォ | +0.863 |
est | +0.856 |
anas | +0.748 |
ィ | +0.741 |
arest | +0.713 |
Neg logit contributions | |
ktop | -0.779 |
Groups | -0.777 |
kernels | -0.761 |
targ | -0.695 |
aurus | -0.694 |
Token | . |
Token ID | 13 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
Groups | +2.219 |
ktop | +2.199 |
kernels | +2.155 |
targ | +1.984 |
aurus | +1.960 |
Neg logit contributions | |
ォ | -2.610 |
est | -2.535 |
anas | -2.244 |
ィ | -2.234 |
itals | -2.174 |
Token |
|
Token ID | 198 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ォ | +0.341 |
est | +0.335 |
anas | +0.292 |
ィ | +0.288 |
arest | +0.278 |
Neg logit contributions | |
ktop | -0.344 |
Groups | -0.342 |
kernels | -0.337 |
targ | -0.313 |
aurus | -0.307 |
Token |
|
Token ID | 198 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
ォ | +0.786 |
est | +0.749 |
anas | +0.660 |
ィ | +0.655 |
itals | +0.634 |
Neg logit contributions | |
Groups | -0.857 |
ktop | -0.842 |
kernels | -0.832 |
aurus | -0.763 |
targ | -0.761 |
Token | Some |
Token ID | 4366 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
est | +1.257 |
ォ | +1.256 |
anas | +1.082 |
ィ | +1.061 |
arest | +1.027 |
Neg logit contributions | |
ktop | -1.305 |
Groups | -1.293 |
kernels | -1.276 |
targ | -1.196 |
aurus | -1.160 |
Token | Mong |
Token ID | 18428 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
est | +2.935 |
ォ | +2.892 |
anas | +2.520 |
ィ | +2.483 |
arest | +2.422 |
Neg logit contributions | |
ktop | -2.623 |
Groups | -2.517 |
kernels | -2.468 |
aurus | -2.304 |
targ | -2.263 |
Token | ols |
Token ID | 10220 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
est | +4.835 |
ォ | +4.231 |
anas | +4.000 |
itals | +3.749 |
arest | +3.593 |
Neg logit contributions | |
ktop | -7.929 |
Groups | -7.652 |
kernels | -7.633 |
enthusi | -7.412 |
targ | -7.394 |
Token | had |
Token ID | 550 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
Groups | +0.739 |
ktop | +0.735 |
kernels | +0.721 |
targ | +0.666 |
aurus | +0.656 |
Neg logit contributions | |
ォ | -0.783 |
est | -0.769 |
anas | -0.673 |
ィ | -0.665 |
itals | -0.646 |
Token | Chinese |
Token ID | 3999 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Groups | +1.464 |
ktop | +1.451 |
kernels | +1.425 |
targ | +1.306 |
aurus | +1.279 |
Neg logit contributions | |
ォ | -1.861 |
est | -1.821 |
anas | -1.618 |
ィ | -1.603 |
itals | -1.560 |
Token | names |
Token ID | 3891 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
est | +1.298 |
ォ | +1.295 |
anas | +1.138 |
ィ | +1.120 |
arest | +1.087 |
Neg logit contributions | |
ktop | -1.033 |
Groups | -1.015 |
kernels | -0.982 |
aurus | -0.905 |
targ | -0.905 |
Token | . |
Token ID | 13 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
Groups | +0.322 |
ktop | +0.320 |
kernels | +0.313 |
targ | +0.288 |
aurus | +0.283 |
Neg logit contributions | |
ォ | -0.381 |
est | -0.377 |
anas | -0.333 |
ィ | -0.328 |
itals | -0.318 |
Token | , |
Token ID | 11 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
est | +2.082 |
ォ | +2.061 |
ィ | +1.763 |
anas | +1.762 |
itals | +1.667 |
Neg logit contributions | |
ktop | -2.186 |
Groups | -2.161 |
kernels | -2.114 |
targ | -1.962 |
aurus | -1.908 |
Token | Comcast |
Token ID | 21830 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
est | +0.752 |
ォ | +0.744 |
anas | +0.659 |
ィ | +0.645 |
itals | +0.634 |
Neg logit contributions | |
ktop | -0.647 |
Groups | -0.638 |
kernels | -0.625 |
targ | -0.574 |
aurus | -0.565 |
Token | has |
Token ID | 468 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
est | +3.633 |
ォ | +3.447 |
anas | +3.104 |
ィ | +3.048 |
itals | +3.009 |
Neg logit contributions | |
ktop | -3.434 |
kernels | -3.229 |
Groups | -3.185 |
targ | -3.027 |
vg | -2.915 |
Token | started |
Token ID | 2067 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
est | +0.439 |
ォ | +0.438 |
anas | +0.380 |
ィ | +0.375 |
itals | +0.363 |
Neg logit contributions | |
ktop | -0.453 |
Groups | -0.452 |
kernels | -0.439 |
targ | -0.409 |
aurus | -0.405 |
Token | " |
Token ID | 366 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
Groups | +1.174 |
ktop | +1.169 |
kernels | +1.145 |
targ | +1.051 |
aurus | +1.034 |
Neg logit contributions | |
ォ | -1.415 |
est | -1.391 |
anas | -1.229 |
ィ | -1.215 |
itals | -1.182 |
Token | im |
Token ID | 320 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
est | +3.715 |
ォ | +3.561 |
anas | +3.159 |
ィ | +3.070 |
arest | +3.033 |
Neg logit contributions | |
Groups | -3.254 |
ktop | -3.228 |
kernels | -3.178 |
targ | -2.945 |
aurus | -2.852 |
Token | posing |
Token ID | 32927 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
est | +8.060 |
ォ | +7.499 |
nesia | +6.716 |
anas | +6.711 |
ィ | +6.627 |
Neg logit contributions | |
ktop | -6.177 |
kernels | -6.169 |
Groups | -6.088 |
targ | -5.751 |
aurus | -5.428 |
Token | extra |
Token ID | 3131 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
est | +3.264 |
ォ | +3.156 |
anas | +2.828 |
usterity | +2.718 |
arest | +2.707 |
Neg logit contributions | |
ktop | -2.884 |
Groups | -2.835 |
kernels | -2.753 |
aurus | -2.542 |
targ | -2.523 |
Token | fees |
Token ID | 6642 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ォ | +0.212 |
est | +0.209 |
anas | +0.183 |
ィ | +0.180 |
itals | +0.175 |
Neg logit contributions | |
Groups | -0.207 |
ktop | -0.207 |
kernels | -0.202 |
targ | -0.187 |
aurus | -0.184 |
Token | on |
Token ID | 319 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
est | +4.695 |
ォ | +4.319 |
anas | +4.010 |
ィ | +3.811 |
arest | +3.768 |
Neg logit contributions | |
ktop | -4.473 |
Groups | -4.423 |
kernels | -4.360 |
targ | -3.998 |
aurus | -3.863 |
Token | Internet |
Token ID | 4455 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
est | +1.331 |
ォ | +1.315 |
anas | +1.173 |
ィ | +1.141 |
itals | +1.126 |
Neg logit contributions | |
ktop | -1.014 |
Groups | -1.007 |
kernels | -0.983 |
targ | -0.906 |
aurus | -0.890 |
Token |
|
Token ID | 198 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
est | +1.154 |
ォ | +1.145 |
anas | +0.987 |
ィ | +0.963 |
itals | +0.921 |
Neg logit contributions | |
ktop | -1.473 |
kernels | -1.442 |
Groups | -1.416 |
targ | -1.350 |
aurus | -1.311 |
Token |
|
Token ID | 198 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
Groups | +1.457 |
ktop | +1.385 |
kernels | +1.383 |
aurus | +1.265 |
Writer | +1.248 |
Neg logit contributions | |
ォ | -1.634 |
est | -1.475 |
ィ | -1.363 |
anas | -1.359 |
usterity | -1.331 |
Token | Sp |
Token ID | 4561 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
ktop | +0.393 |
Groups | +0.392 |
kernels | +0.385 |
targ | +0.357 |
aurus | +0.348 |
Neg logit contributions | |
ォ | -0.428 |
est | -0.425 |
anas | -0.372 |
ィ | -0.367 |
arest | -0.356 |
Token | as |
Token ID | 292 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
est | +1.485 |
ォ | +1.453 |
anas | +1.249 |
itals | +1.167 |
arest | +1.147 |
Neg logit contributions | |
Groups | -2.623 |
ktop | -2.619 |
kernels | -2.596 |
targ | -2.467 |
aurus | -2.356 |
Token | ov |
Token ID | 709 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
ォ | +0.722 |
est | +0.688 |
ィ | +0.625 |
anas | +0.623 |
itals | +0.603 |
Neg logit contributions | |
Groups | -0.459 |
ktop | -0.458 |
kernels | -0.445 |
aurus | -0.403 |
targ | -0.393 |
Token | ski |
Token ID | 20545 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Groups | +0.292 |
ktop | +0.292 |
kernels | +0.286 |
aurus | +0.264 |
targ | +0.263 |
Neg logit contributions | |
ォ | -0.265 |
est | -0.248 |
anas | -0.218 |
ィ | -0.217 |
arest | -0.207 |
Token | said |
Token ID | 531 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
ォ | +0.630 |
est | +0.626 |
anas | +0.543 |
ィ | +0.536 |
arest | +0.519 |
Neg logit contributions | |
Groups | -0.639 |
ktop | -0.637 |
kernels | -0.624 |
targ | -0.577 |
aurus | -0.570 |
Token | the |
Token ID | 262 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ktop | +0.250 |
Groups | +0.246 |
kernels | +0.241 |
targ | +0.220 |
aurus | +0.217 |
Neg logit contributions | |
est | -0.335 |
ォ | -0.333 |
anas | -0.297 |
ィ | -0.291 |
itals | -0.284 |
Token | SJ |
Token ID | 31766 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
Groups | +1.522 |
ktop | +1.499 |
kernels | +1.475 |
targ | +1.347 |
aurus | +1.314 |
Neg logit contributions | |
ォ | -2.143 |
est | -2.088 |
anas | -1.867 |
ィ | -1.854 |
itals | -1.808 |
Token | O |
Token ID | 46 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ォ | +1.308 |
est | +1.266 |
anas | +1.120 |
ィ | +1.109 |
itals | +1.080 |
Neg logit contributions | |
Groups | -1.216 |
ktop | -1.200 |
kernels | -1.181 |
targ | -1.079 |
aurus | -1.074 |
Token | investigator |
Token ID | 20725 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
ktop | +0.688 |
Groups | +0.685 |
kernels | +0.671 |
targ | +0.610 |
aurus | +0.604 |
Neg logit contributions | |
ォ | -0.889 |
est | -0.879 |
anas | -0.777 |
ィ | -0.770 |
itals | -0.747 |
Token | — |
Token ID | 851 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
est | +1.579 |
ォ | +1.569 |
anas | +1.383 |
ィ | +1.364 |
itals | +1.338 |
Neg logit contributions | |
ktop | -1.238 |
Groups | -1.220 |
kernels | -1.200 |
targ | -1.104 |
aurus | -1.066 |
Token | Michael |
Token ID | 3899 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
ォ | +0.550 |
est | +0.545 |
anas | +0.474 |
ィ | +0.470 |
arest | +0.451 |
Neg logit contributions | |
ktop | -0.550 |
Groups | -0.539 |
kernels | -0.530 |
targ | -0.486 |
aurus | -0.483 |
Token | G |
Token ID | 402 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
ォ | +2.712 |
est | +2.647 |
ィ | +2.330 |
anas | +2.298 |
arest | +2.177 |
Neg logit contributions | |
ktop | -2.610 |
Groups | -2.568 |
kernels | -2.546 |
targ | -2.328 |
aurus | -2.279 |
Token | Flynn |
Token ID | 14654 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Groups | +0.104 |
ktop | +0.103 |
kernels | +0.101 |
targ | +0.091 |
aurus | +0.090 |
Neg logit contributions | |
ォ | -0.150 |
est | -0.146 |
anas | -0.131 |
ィ | -0.130 |
itals | -0.127 |
Token | � |
Token ID | 12520 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
ォ | +1.744 |
est | +1.744 |
ィ | +1.452 |
anas | +1.409 |
itals | +1.369 |
Neg logit contributions | |
ktop | -2.491 |
Groups | -2.393 |
kernels | -2.372 |
targ | -2.226 |
aurus | -2.199 |
Token | � |
Token ID | 229 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Groups | +1.582 |
ktop | +1.563 |
kernels | +1.530 |
targ | +1.384 |
aurus | +1.360 |
Neg logit contributions | |
ォ | -2.481 |
est | -2.436 |
anas | -2.190 |
ィ | -2.162 |
itals | -2.112 |
Token | � |
Token ID | 118 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
ォ | +0.541 |
est | +0.530 |
anas | +0.469 |
ィ | +0.463 |
itals | +0.450 |
Neg logit contributions | |
Groups | -0.467 |
ktop | -0.464 |
kernels | -0.455 |
targ | -0.419 |
aurus | -0.412 |
Token | � |
Token ID | 8582 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Groups | +2.806 |
ktop | +2.711 |
kernels | +2.689 |
targ | +2.389 |
aurus | +2.365 |
Neg logit contributions | |
ォ | -4.973 |
est | -4.863 |
anas | -4.438 |
ィ | -4.340 |
usterity | -4.290 |
Token | � |
Token ID | 229 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
Groups | +2.428 |
ktop | +2.235 |
kernels | +2.223 |
aurus | +1.988 |
cal | +1.858 |
Neg logit contributions | |
ォ | -6.271 |
est | -5.964 |
anas | -5.567 |
ィ | -5.458 |
usterity | -5.376 |
Token | � |
Token ID | 116 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ォ | +0.253 |
est | +0.247 |
anas | +0.217 |
ィ | +0.214 |
itals | +0.208 |
Neg logit contributions | |
Groups | -0.245 |
ktop | -0.244 |
kernels | -0.239 |
targ | -0.221 |
aurus | -0.218 |
Token | (@ |
Token ID | 4275 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
Groups | +1.120 |
ktop | +1.119 |
kernels | +1.096 |
targ | +1.019 |
aurus | +1.002 |
Neg logit contributions | |
ォ | -1.013 |
est | -0.989 |
anas | -0.854 |
ィ | -0.848 |
arest | -0.815 |
Token | za |
Token ID | 4496 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
est | +1.943 |
ォ | +1.914 |
anas | +1.681 |
ィ | +1.596 |
itals | +1.555 |
Neg logit contributions | |
ktop | -2.324 |
Groups | -2.279 |
kernels | -2.252 |
aurus | -2.104 |
targ | -2.099 |
Token | � |
Token ID | 447 |
Feature activation | +3.16e-03 |
Pos logit contributions | |
Groups | +2.122 |
ktop | +2.098 |
kernels | +2.066 |
targ | +1.906 |
aurus | +1.881 |
Neg logit contributions | |
ォ | -2.262 |
est | -2.204 |
anas | -1.945 |
ィ | -1.916 |
itals | -1.865 |
Token | � |
Token ID | 247 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
ォ | +0.011 |
est | +0.011 |
anas | +0.009 |
ィ | +0.009 |
arest | +0.009 |
Neg logit contributions | |
ktop | -0.015 |
Groups | -0.015 |
kernels | -0.015 |
targ | -0.014 |
aurus | -0.014 |
Token | s |
Token ID | 82 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
est | +1.937 |
ォ | +1.911 |
anas | +1.705 |
ィ | +1.681 |
itals | +1.646 |
Neg logit contributions | |
ktop | -1.296 |
Groups | -1.285 |
kernels | -1.253 |
targ | -1.136 |
aurus | -1.098 |
Token | che |
Token ID | 1125 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
est | +0.831 |
ォ | +0.831 |
anas | +0.718 |
ィ | +0.710 |
arest | +0.693 |
Neg logit contributions | |
ktop | -0.769 |
Groups | -0.760 |
kernels | -0.744 |
targ | -0.684 |
aurus | -0.674 |
Token | c |
Token ID | 66 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
est | +1.304 |
ォ | +1.283 |
anas | +1.132 |
arest | +1.098 |
ィ | +1.091 |
Neg logit contributions | |
Groups | -1.185 |
kernels | -1.160 |
ktop | -1.158 |
targ | -1.067 |
aurus | -1.039 |
Token | kered |
Token ID | 28970 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ォ | +2.309 |
est | +2.261 |
ィ | +1.774 |
anas | +1.753 |
itals | +1.570 |
Neg logit contributions | |
ktop | -5.003 |
Groups | -4.852 |
kernels | -4.777 |
targ | -4.535 |
Instr | -4.458 |
Token | history |
Token ID | 2106 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Groups | +1.763 |
ktop | +1.747 |
kernels | +1.733 |
targ | +1.600 |
aurus | +1.562 |
Neg logit contributions | |
ォ | -1.718 |
est | -1.648 |
anas | -1.467 |
ィ | -1.435 |
arest | -1.397 |
Token | at |
Token ID | 379 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Groups | +0.662 |
ktop | +0.660 |
kernels | +0.646 |
targ | +0.596 |
aurus | +0.586 |
Neg logit contributions | |
ォ | -0.758 |
est | -0.747 |
anas | -0.656 |
ィ | -0.649 |
arest | -0.629 |
Token | the |
Token ID | 262 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
est | +2.087 |
ォ | +2.043 |
anas | +1.804 |
ィ | +1.728 |
itals | +1.727 |
Neg logit contributions | |
ktop | -1.908 |
Groups | -1.860 |
kernels | -1.849 |
targ | -1.702 |
reckoned | -1.660 |
Token | Congress |
Token ID | 3162 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
ォ | +1.788 |
est | +1.782 |
anas | +1.552 |
ィ | +1.523 |
arest | +1.498 |
Neg logit contributions | |
ktop | -1.566 |
Groups | -1.558 |
kernels | -1.523 |
targ | -1.403 |
aurus | -1.392 |
Token | a |
Token ID | 257 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
est | +1.057 |
ォ | +1.044 |
anas | +0.930 |
ィ | +0.901 |
itals | +0.886 |
Neg logit contributions | |
ktop | -0.868 |
Groups | -0.849 |
kernels | -0.835 |
targ | -0.763 |
aurus | -0.757 |
Token | generous |
Token ID | 14431 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
ォ | +1.388 |
est | +1.381 |
anas | +1.188 |
ィ | +1.175 |
arest | +1.143 |
Neg logit contributions | |
ktop | -1.367 |
Groups | -1.353 |
kernels | -1.331 |
targ | -1.218 |
aurus | -1.209 |
Token | tower |
Token ID | 10580 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
est | +3.050 |
ォ | +2.917 |
anas | +2.543 |
ィ | +2.465 |
arest | +2.378 |
Neg logit contributions | |
ktop | -3.357 |
Groups | -3.334 |
kernels | -3.246 |
aurus | -3.020 |
targ | -2.990 |
Token | separation |
Token ID | 14139 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Groups | +0.441 |
ktop | +0.439 |
kernels | +0.430 |
targ | +0.395 |
aurus | +0.388 |
Neg logit contributions | |
ォ | -0.524 |
est | -0.515 |
anas | -0.455 |
ィ | -0.449 |
itals | -0.437 |
Token | is |
Token ID | 318 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
est | +0.663 |
ォ | +0.656 |
anas | +0.575 |
ィ | +0.558 |
arest | +0.543 |
Neg logit contributions | |
ktop | -0.669 |
Groups | -0.668 |
kernels | -0.648 |
targ | -0.598 |
aurus | -0.595 |
Token | afforded |
Token ID | 28109 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
est | +1.847 |
ォ | +1.781 |
anas | +1.573 |
itals | +1.519 |
ィ | +1.516 |
Neg logit contributions | |
ktop | -1.883 |
Groups | -1.867 |
kernels | -1.827 |
targ | -1.671 |
aurus | -1.657 |
Token | on |
Token ID | 319 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
est | +2.980 |
ォ | +2.889 |
anas | +2.602 |
ィ | +2.494 |
arest | +2.467 |
Neg logit contributions | |
ktop | -2.483 |
Groups | -2.465 |
kernels | -2.409 |
targ | -2.229 |
aurus | -2.177 |
Token | both |
Token ID | 1111 |
Feature activation | +4.22e-03 |
Pos logit contributions | |
Groups | +0.843 |
ktop | +0.842 |
kernels | +0.822 |
targ | +0.756 |
aurus | +0.745 |
Neg logit contributions | |
ォ | -1.045 |
est | -1.038 |
anas | -0.917 |
ィ | -0.897 |
itals | -0.881 |
Token | sides |
Token ID | 5389 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
est | +0.020 |
ォ | +0.019 |
anas | +0.017 |
ィ | +0.017 |
itals | +0.017 |
Neg logit contributions | |
ktop | -0.016 |
Groups | -0.015 |
kernels | -0.015 |
targ | -0.014 |
aurus | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
Groups | +0.261 |
ktop | +0.260 |
kernels | +0.254 |
targ | +0.232 |
aurus | +0.226 |
Neg logit contributions | |
ォ | -0.365 |
est | -0.365 |
anas | -0.324 |
ィ | -0.320 |
arest | -0.312 |
Token | the |
Token ID | 262 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
est | +2.470 |
ォ | +2.371 |
anas | +2.113 |
itals | +2.017 |
ィ | +2.015 |
Neg logit contributions | |
ktop | -2.353 |
Groups | -2.274 |
kernels | -2.259 |
targ | -2.078 |
aurus | -2.066 |
Token | or |
Token ID | 393 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
est | +1.426 |
ォ | +1.396 |
anas | +1.249 |
ィ | +1.212 |
arest | +1.200 |
Neg logit contributions | |
ktop | -1.232 |
Groups | -1.224 |
kernels | -1.195 |
targ | -1.109 |
aurus | -1.082 |
Token | the |
Token ID | 262 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Groups | +3.669 |
ktop | +3.609 |
kernels | +3.576 |
targ | +3.256 |
aurus | +3.193 |
Neg logit contributions | |
ォ | -5.133 |
est | -4.835 |
ィ | -4.408 |
anas | -4.354 |
itals | -4.229 |
Token | occasion |
Token ID | 6695 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Groups | +1.046 |
ktop | +1.038 |
kernels | +1.020 |
targ | +0.936 |
aurus | +0.920 |
Neg logit contributions | |
ォ | -1.251 |
est | -1.223 |
anas | -1.083 |
ィ | -1.072 |
itals | -1.042 |
Token | of |
Token ID | 286 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
Groups | +1.133 |
ktop | +1.125 |
kernels | +1.101 |
targ | +0.998 |
aurus | +0.981 |
Neg logit contributions | |
ォ | -1.708 |
est | -1.662 |
anas | -1.493 |
ィ | -1.486 |
itals | -1.442 |
Token | the |
Token ID | 262 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
est | +2.458 |
ォ | +2.346 |
anas | +2.146 |
arest | +2.048 |
ィ | +2.027 |
Neg logit contributions | |
ktop | -2.004 |
Groups | -1.996 |
kernels | -1.925 |
targ | -1.771 |
aurus | -1.735 |
Token | argument |
Token ID | 4578 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
est | +1.313 |
ォ | +1.292 |
anas | +1.147 |
ィ | +1.111 |
arest | +1.103 |
Neg logit contributions | |
Groups | -1.121 |
ktop | -1.118 |
kernels | -1.079 |
targ | -0.999 |
aurus | -0.980 |
Token | offer |
Token ID | 2897 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
est | +4.179 |
ォ | +3.944 |
anas | +3.625 |
arest | +3.534 |
itals | +3.438 |
Neg logit contributions | |
Groups | -3.314 |
ktop | -3.281 |
kernels | -3.209 |
targ | -3.018 |
aurus | -2.835 |
Token | , |
Token ID | 11 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
est | +2.004 |
ォ | +1.930 |
anas | +1.733 |
arest | +1.688 |
ィ | +1.675 |
Neg logit contributions | |
Groups | -1.695 |
ktop | -1.673 |
kernels | -1.639 |
targ | -1.523 |
aurus | -1.476 |
Token | partly |
Token ID | 11476 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
est | +0.732 |
ォ | +0.721 |
anas | +0.642 |
ィ | +0.623 |
arest | +0.619 |
Neg logit contributions | |
ktop | -0.632 |
Groups | -0.630 |
kernels | -0.615 |
targ | -0.570 |
aurus | -0.555 |
Token | , |
Token ID | 11 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
est | +4.101 |
ォ | +3.808 |
anas | +3.500 |
arest | +3.354 |
ィ | +3.330 |
Neg logit contributions | |
Groups | -3.778 |
ktop | -3.742 |
kernels | -3.585 |
targ | -3.340 |
Writer | -3.231 |
Token | too |
Token ID | 1165 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
est | +2.151 |
ォ | +2.087 |
anas | +1.885 |
ィ | +1.826 |
itals | +1.806 |
Neg logit contributions | |
ktop | -1.781 |
Groups | -1.760 |
kernels | -1.711 |
targ | -1.587 |
aurus | -1.535 |
Token | break |
Token ID | 2270 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
ォ | +0.750 |
est | +0.746 |
anas | +0.656 |
ィ | +0.649 |
itals | +0.633 |
Neg logit contributions | |
Groups | -0.583 |
ktop | -0.580 |
kernels | -0.565 |
targ | -0.516 |
aurus | -0.505 |
Token | into |
Token ID | 656 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
est | +2.713 |
ォ | +2.647 |
anas | +2.320 |
ィ | +2.254 |
arest | +2.206 |
Neg logit contributions | |
ktop | -2.585 |
Groups | -2.552 |
kernels | -2.462 |
targ | -2.304 |
aurus | -2.285 |
Token | some |
Token ID | 617 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
ktop | +0.269 |
Groups | +0.269 |
kernels | +0.262 |
targ | +0.241 |
aurus | +0.237 |
Neg logit contributions | |
ォ | -0.338 |
est | -0.335 |
anas | -0.296 |
ィ | -0.292 |
itals | -0.285 |
Token | stranger |
Token ID | 16195 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
est | +1.873 |
ォ | +1.854 |
anas | +1.609 |
ィ | +1.592 |
itals | +1.542 |
Neg logit contributions | |
ktop | -1.787 |
Groups | -1.762 |
kernels | -1.705 |
targ | -1.597 |
aurus | -1.585 |
Token | � |
Token ID | 447 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
ォ | +1.702 |
est | +1.701 |
ィ | +1.500 |
anas | +1.491 |
itals | +1.443 |
Neg logit contributions | |
ktop | -1.213 |
Groups | -1.197 |
kernels | -1.169 |
targ | -1.059 |
aurus | -1.053 |
Token | � |
Token ID | 247 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
Groups | +1.803 |
ktop | +1.730 |
kernels | +1.714 |
aurus | +1.599 |
targ | +1.546 |
Neg logit contributions | |
ォ | -2.003 |
est | -1.939 |
anas | -1.732 |
ィ | -1.691 |
usterity | -1.655 |
Token | s |
Token ID | 82 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Groups | +1.712 |
ktop | +1.697 |
kernels | +1.662 |
targ | +1.518 |
aurus | +1.491 |
Neg logit contributions | |
ォ | -2.439 |
est | -2.372 |
anas | -2.134 |
ィ | -2.109 |
itals | -2.054 |
Token | apartment |
Token ID | 7962 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
Groups | +1.335 |
ktop | +1.328 |
kernels | +1.310 |
targ | +1.229 |
aurus | +1.212 |
Neg logit contributions | |
ォ | -0.937 |
est | -0.910 |
anas | -0.773 |
ィ | -0.760 |
itals | -0.730 |
Token | and |
Token ID | 290 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
est | +2.727 |
ォ | +2.649 |
anas | +2.345 |
ィ | +2.318 |
arest | +2.253 |
Neg logit contributions | |
ktop | -2.438 |
Groups | -2.437 |
kernels | -2.362 |
targ | -2.180 |
aurus | -2.113 |
Token | hide |
Token ID | 7808 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
est | +2.141 |
ォ | +2.099 |
anas | +1.857 |
ィ | +1.827 |
itals | +1.816 |
Neg logit contributions | |
ktop | -1.718 |
Groups | -1.711 |
kernels | -1.647 |
targ | -1.518 |
aurus | -1.500 |
Token | under |
Token ID | 739 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
est | +2.578 |
ォ | +2.545 |
anas | +2.234 |
ィ | +2.218 |
itals | +2.145 |
Neg logit contributions | |
Groups | -2.378 |
ktop | -2.377 |
kernels | -2.298 |
targ | -2.155 |
aurus | -2.102 |
Token | eight |
Token ID | 3624 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Groups | +1.535 |
ktop | +1.527 |
kernels | +1.505 |
targ | +1.415 |
aurus | +1.395 |
Neg logit contributions | |
ォ | -1.024 |
est | -0.993 |
anas | -0.840 |
ィ | -0.826 |
itals | -0.793 |
Token | - |
Token ID | 12 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
ォ | +0.609 |
est | +0.608 |
anas | +0.524 |
ィ | +0.517 |
itals | +0.503 |
Neg logit contributions | |
Groups | -0.542 |
ktop | -0.538 |
kernels | -0.528 |
targ | -0.485 |
aurus | -0.479 |
Token | store |
Token ID | 8095 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
est | +0.065 |
ォ | +0.065 |
anas | +0.057 |
ィ | +0.056 |
arest | +0.055 |
Neg logit contributions | |
Groups | -0.054 |
ktop | -0.053 |
kernels | -0.053 |
targ | -0.048 |
aurus | -0.047 |
Token | y |
Token ID | 88 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Groups | +1.344 |
ktop | +1.328 |
kernels | +1.308 |
aurus | +1.209 |
targ | +1.191 |
Neg logit contributions | |
ォ | -1.599 |
est | -1.549 |
anas | -1.384 |
ィ | -1.363 |
itals | -1.325 |
Token | mural |
Token ID | 36192 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ォ | +0.564 |
est | +0.558 |
anas | +0.481 |
ィ | +0.475 |
arest | +0.460 |
Neg logit contributions | |
Groups | -0.579 |
ktop | -0.578 |
kernels | -0.565 |
targ | -0.519 |
aurus | -0.515 |
Token | . |
Token ID | 13 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
est | +4.928 |
ォ | +4.645 |
anas | +4.142 |
arest | +3.956 |
ィ | +3.950 |
Neg logit contributions | |
ktop | -4.433 |
Groups | -4.410 |
kernels | -4.246 |
aurus | -3.868 |
targ | -3.861 |
Token | Dep |
Token ID | 2129 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
ktop | +0.315 |
Groups | +0.315 |
kernels | +0.309 |
targ | +0.286 |
aurus | +0.281 |
Neg logit contributions | |
ォ | -0.332 |
est | -0.326 |
anas | -0.285 |
ィ | -0.282 |
arest | -0.273 |
Token | ict |
Token ID | 713 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Groups | +0.947 |
ktop | +0.941 |
kernels | +0.921 |
targ | +0.843 |
aurus | +0.830 |
Neg logit contributions | |
ォ | -1.210 |
est | -1.183 |
anas | -1.052 |
ィ | -1.043 |
itals | -1.013 |
Token | ing |
Token ID | 278 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
est | +1.537 |
ォ | +1.525 |
anas | +1.297 |
ィ | +1.242 |
arest | +1.206 |
Neg logit contributions | |
ktop | -2.206 |
Groups | -2.163 |
kernels | -2.123 |
targ | -2.010 |
aurus | -1.991 |
Token | a |
Token ID | 257 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Groups | +2.042 |
ktop | +2.021 |
kernels | +1.989 |
targ | +1.818 |
aurus | +1.781 |
Neg logit contributions | |
ォ | -2.638 |
est | -2.578 |
anas | -2.298 |
ィ | -2.276 |
itals | -2.212 |
Token | crou |
Token ID | 33838 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Groups | +0.445 |
ktop | +0.443 |
kernels | +0.434 |
targ | +0.401 |
aurus | +0.395 |
Neg logit contributions | |
ォ | -0.483 |
est | -0.473 |
anas | -0.415 |
ィ | -0.411 |
arest | -0.398 |
Token | 11 |
Token ID | 1157 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
Groups | +0.368 |
ktop | +0.367 |
kernels | +0.360 |
targ | +0.336 |
aurus | +0.326 |
Neg logit contributions | |
ォ | -0.401 |
est | -0.399 |
anas | -0.349 |
ィ | -0.344 |
arest | -0.336 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ォ | +2.373 |
est | +2.349 |
anas | +2.081 |
ィ | +2.058 |
arest | +2.003 |
Neg logit contributions | |
ktop | -1.782 |
Groups | -1.772 |
kernels | -1.741 |
targ | -1.611 |
aurus | -1.555 |
Token | Al |
Token ID | 978 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
Groups | +0.709 |
ktop | +0.706 |
kernels | +0.693 |
targ | +0.640 |
aurus | +0.629 |
Neg logit contributions | |
ォ | -0.757 |
est | -0.742 |
anas | -0.651 |
ィ | -0.643 |
arest | -0.624 |
Token | P |
Token ID | 350 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
ォ | +0.167 |
est | +0.165 |
anas | +0.146 |
ィ | +0.143 |
arest | +0.139 |
Neg logit contributions | |
Groups | -0.145 |
ktop | -0.145 |
kernels | -0.142 |
targ | -0.131 |
aurus | -0.128 |
Token | urdy |
Token ID | 22876 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
Groups | +1.975 |
ktop | +1.947 |
kernels | +1.914 |
targ | +1.769 |
aurus | +1.764 |
Neg logit contributions | |
ォ | -2.000 |
est | -1.909 |
anas | -1.688 |
ィ | -1.685 |
itals | -1.628 |
Token | � |
Token ID | 447 |
Feature activation | +4.03e-04 |
Pos logit contributions | |
Groups | +0.202 |
ktop | +0.201 |
kernels | +0.198 |
targ | +0.183 |
aurus | +0.179 |
Neg logit contributions | |
ォ | -0.217 |
est | -0.214 |
anas | -0.187 |
ィ | -0.184 |
arest | -0.179 |
Token | � |
Token ID | 247 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
ォ | +0.001 |
est | +0.001 |
anas | +0.001 |
ィ | +0.001 |
itals | +0.001 |
Neg logit contributions | |
ktop | -0.002 |
Groups | -0.002 |
kernels | -0.002 |
targ | -0.002 |
aurus | -0.002 |
Token | s |
Token ID | 82 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Groups | +0.523 |
ktop | +0.522 |
kernels | +0.512 |
targ | +0.473 |
aurus | +0.463 |
Neg logit contributions | |
ォ | -0.567 |
est | -0.557 |
anas | -0.489 |
ィ | -0.483 |
arest | -0.468 |
Token | statue |
Token ID | 15207 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ォ | +1.057 |
est | +1.048 |
anas | +0.912 |
ィ | +0.898 |
arest | +0.872 |
Neg logit contributions | |
ktop | -0.995 |
Groups | -0.988 |
kernels | -0.977 |
targ | -0.903 |
aurus | -0.875 |
Token | , |
Token ID | 11 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
est | +4.435 |
ォ | +4.384 |
anas | +3.802 |
ィ | +3.744 |
arest | +3.599 |
Neg logit contributions | |
ktop | -4.542 |
kernels | -4.419 |
Groups | -4.402 |
targ | -4.095 |
aurus | -3.916 |
Token | Queen |
Token ID | 7542 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
ォ | +0.799 |
est | +0.795 |
anas | +0.692 |
ィ | +0.678 |
arest | +0.660 |
Neg logit contributions | |
ktop | -0.783 |
Groups | -0.770 |
kernels | -0.760 |
targ | -0.701 |
aurus | -0.688 |
Token | work |
Token ID | 670 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Groups | +0.021 |
ktop | +0.021 |
kernels | +0.020 |
targ | +0.019 |
aurus | +0.018 |
Neg logit contributions | |
ォ | -0.025 |
est | -0.025 |
anas | -0.022 |
ィ | -0.022 |
itals | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Groups | +1.170 |
ktop | +1.163 |
kernels | +1.144 |
targ | +1.047 |
aurus | +1.031 |
Neg logit contributions | |
ォ | -1.368 |
est | -1.334 |
anas | -1.183 |
ィ | -1.169 |
arest | -1.136 |
Token | No |
Token ID | 1400 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
Groups | +2.205 |
ktop | +2.126 |
kernels | +2.107 |
targ | +1.915 |
aurus | +1.893 |
Neg logit contributions | |
ォ | -2.391 |
est | -2.309 |
anas | -2.067 |
ィ | -2.026 |
arest | -1.988 |
Token | big |
Token ID | 1263 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Groups | +0.948 |
ktop | +0.944 |
kernels | +0.922 |
targ | +0.851 |
aurus | +0.838 |
Neg logit contributions | |
ォ | -1.087 |
est | -1.069 |
anas | -0.941 |
ィ | -0.930 |
itals | -0.904 |
Token | gie |
Token ID | 22699 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Groups | +1.391 |
ktop | +1.378 |
kernels | +1.353 |
targ | +1.229 |
aurus | +1.205 |
Neg logit contributions | |
ォ | -1.973 |
est | -1.928 |
anas | -1.726 |
ィ | -1.709 |
arest | -1.663 |
Token | , |
Token ID | 11 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Groups | +3.715 |
kernels | +3.687 |
ktop | +3.644 |
targ | +3.223 |
aurus | +3.182 |
Neg logit contributions | |
ォ | -4.973 |
est | -4.691 |
anas | -4.300 |
ィ | -4.258 |
arest | -4.113 |
Token | because |
Token ID | 780 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Groups | +1.293 |
ktop | +1.278 |
kernels | +1.262 |
targ | +1.147 |
aurus | +1.125 |
Neg logit contributions | |
ォ | -1.706 |
est | -1.664 |
anas | -1.486 |
ィ | -1.470 |
arest | -1.430 |
Token | I |
Token ID | 314 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Groups | +1.122 |
ktop | +1.111 |
kernels | +1.097 |
targ | +1.000 |
aurus | +0.981 |
Neg logit contributions | |
ォ | -1.370 |
est | -1.333 |
anas | -1.186 |
ィ | -1.173 |
arest | -1.141 |
Token | got |
Token ID | 1392 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Groups | +0.839 |
ktop | +0.833 |
kernels | +0.816 |
targ | +0.744 |
aurus | +0.731 |
Neg logit contributions | |
ォ | -1.157 |
est | -1.134 |
anas | -1.013 |
ィ | -1.002 |
itals | -0.976 |
Token | your |
Token ID | 534 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
ォ | +0.774 |
est | +0.762 |
anas | +0.672 |
ィ | +0.667 |
itals | +0.647 |
Neg logit contributions | |
Groups | -0.640 |
ktop | -0.639 |
kernels | -0.619 |
targ | -0.576 |
aurus | -0.566 |
Token | back |
Token ID | 736 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
ォ | +0.359 |
est | +0.353 |
anas | +0.309 |
ィ | +0.307 |
arest | +0.299 |
Neg logit contributions | |
Groups | -0.317 |
ktop | -0.316 |
kernels | -0.307 |
targ | -0.285 |
aurus | -0.282 |
Token | mode |
Token ID | 4235 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
Groups | +2.139 |
kernels | +2.083 |
ktop | +2.082 |
targ | +1.894 |
aurus | +1.841 |
Neg logit contributions | |
ォ | -2.814 |
est | -2.727 |
anas | -2.453 |
ィ | -2.435 |
arest | -2.365 |
Token | involving |
Token ID | 7411 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
Groups | +2.875 |
ktop | +2.815 |
kernels | +2.795 |
targ | +2.548 |
aurus | +2.496 |
Neg logit contributions | |
ォ | -3.622 |
est | -3.525 |
anas | -3.142 |
ィ | -3.104 |
arest | -3.054 |
Token | player |
Token ID | 2137 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Groups | +2.444 |
ktop | +2.392 |
kernels | +2.372 |
targ | +2.178 |
aurus | +2.123 |
Neg logit contributions | |
ォ | -2.890 |
est | -2.813 |
anas | -2.492 |
ィ | -2.478 |
itals | -2.408 |
Token | - |
Token ID | 12 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
ォ | +0.587 |
est | +0.577 |
anas | +0.511 |
ィ | +0.505 |
itals | +0.488 |
Neg logit contributions | |
ktop | -0.492 |
Groups | -0.482 |
kernels | -0.474 |
aurus | -0.436 |
targ | -0.434 |
Token | controlled |
Token ID | 14401 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Groups | +1.204 |
ktop | +1.203 |
kernels | +1.178 |
targ | +1.096 |
aurus | +1.083 |
Neg logit contributions | |
ォ | -1.117 |
est | -1.104 |
anas | -0.957 |
ィ | -0.942 |
arest | -0.912 |
Token | zombies |
Token ID | 19005 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
Groups | +1.012 |
ktop | +1.009 |
kernels | +0.985 |
targ | +0.900 |
aurus | +0.886 |
Neg logit contributions | |
ォ | -1.353 |
est | -1.330 |
anas | -1.183 |
ィ | -1.169 |
itals | -1.140 |
Token | . |
Token ID | 13 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
Groups | +0.130 |
ktop | +0.130 |
kernels | +0.127 |
targ | +0.117 |
aurus | +0.114 |
Neg logit contributions | |
ォ | -0.157 |
est | -0.155 |
anas | -0.137 |
ィ | -0.135 |
itals | -0.131 |
Token | That |
Token ID | 1320 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
Groups | +2.117 |
ktop | +2.031 |
kernels | +2.006 |
targ | +1.840 |
aurus | +1.833 |
Neg logit contributions | |
ォ | -2.206 |
est | -2.150 |
anas | -1.911 |
ィ | -1.865 |
arest | -1.839 |
Token | inspiration |
Token ID | 12141 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
Groups | +1.596 |
ktop | +1.576 |
kernels | +1.551 |
targ | +1.418 |
aurus | +1.391 |
Neg logit contributions | |
ォ | -2.051 |
est | -2.008 |
anas | -1.790 |
ィ | -1.769 |
arest | -1.726 |
Token | has |
Token ID | 468 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Groups | +1.880 |
ktop | +1.860 |
kernels | +1.835 |
targ | +1.681 |
aurus | +1.657 |
Neg logit contributions | |
ォ | -2.183 |
est | -2.132 |
anas | -1.894 |
ィ | -1.863 |
itals | -1.815 |
Token | led |
Token ID | 2957 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
Groups | +0.539 |
ktop | +0.535 |
kernels | +0.525 |
targ | +0.487 |
aurus | +0.478 |
Neg logit contributions | |
ォ | -0.585 |
est | -0.576 |
anas | -0.505 |
ィ | -0.501 |
itals | -0.484 |
Token | . |
Token ID | 13 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
ォ | +0.123 |
est | +0.123 |
anas | +0.108 |
ィ | +0.107 |
arest | +0.104 |
Neg logit contributions | |
ktop | -0.106 |
Groups | -0.105 |
kernels | -0.102 |
targ | -0.094 |
aurus | -0.092 |
Token | Nor |
Token ID | 5414 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
Groups | +1.860 |
ktop | +1.838 |
kernels | +1.809 |
targ | +1.676 |
aurus | +1.656 |
Neg logit contributions | |
ォ | -1.770 |
est | -1.727 |
anas | -1.510 |
ィ | -1.486 |
itals | -1.444 |
Token | has |
Token ID | 468 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Groups | +3.098 |
ktop | +3.070 |
kernels | +3.018 |
targ | +2.762 |
aurus | +2.738 |
Neg logit contributions | |
ォ | -3.519 |
est | -3.398 |
anas | -3.009 |
ィ | -2.985 |
arest | -2.884 |
Token | he |
Token ID | 339 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
ktop | +0.795 |
Groups | +0.792 |
kernels | +0.772 |
targ | +0.703 |
aurus | +0.684 |
Neg logit contributions | |
ォ | -1.222 |
est | -1.221 |
anas | -1.087 |
ィ | -1.074 |
itals | -1.048 |
Token | discussed |
Token ID | 6693 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Groups | +3.445 |
ktop | +3.414 |
kernels | +3.407 |
targ | +3.136 |
aurus | +3.101 |
Neg logit contributions | |
ォ | -3.866 |
est | -3.639 |
ィ | -3.269 |
anas | -3.248 |
itals | -3.145 |
Token | how |
Token ID | 703 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Groups | +1.525 |
ktop | +1.514 |
kernels | +1.481 |
targ | +1.346 |
aurus | +1.320 |
Neg logit contributions | |
ォ | -2.221 |
est | -2.181 |
anas | -1.951 |
ィ | -1.931 |
itals | -1.882 |
Token | he |
Token ID | 339 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
Groups | +4.023 |
kernels | +3.888 |
ktop | +3.808 |
targ | +3.444 |
aurus | +3.395 |
Neg logit contributions | |
ォ | -6.815 |
est | -6.530 |
anas | -5.924 |
ィ | -5.885 |
arest | -5.825 |
Token | plans |
Token ID | 3352 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
Groups | +2.357 |
kernels | +2.295 |
ktop | +2.283 |
targ | +2.051 |
aurus | +2.041 |
Neg logit contributions | |
ォ | -3.618 |
est | -3.515 |
anas | -3.184 |
ィ | -3.122 |
itals | -3.094 |
Token | to |
Token ID | 284 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
est | +0.479 |
ォ | +0.478 |
anas | +0.424 |
ィ | +0.421 |
itals | +0.409 |
Neg logit contributions | |
ktop | -0.312 |
Groups | -0.311 |
kernels | -0.303 |
targ | -0.275 |
aurus | -0.266 |
Token | vote |
Token ID | 3015 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
ォ | +0.990 |
est | +0.980 |
anas | +0.861 |
ィ | +0.850 |
itals | +0.829 |
Neg logit contributions | |
ktop | -0.824 |
Groups | -0.821 |
kernels | -0.798 |
targ | -0.734 |
aurus | -0.723 |
Token | on |
Token ID | 319 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
est | +2.404 |
ォ | +2.383 |
ィ | +2.084 |
anas | +2.083 |
arest | +2.008 |
Neg logit contributions | |
ktop | -2.014 |
Groups | -1.975 |
kernels | -1.943 |
targ | -1.789 |
aurus | -1.742 |
Token | that |
Token ID | 326 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ォ | +1.965 |
est | +1.939 |
anas | +1.702 |
ィ | +1.668 |
arest | +1.607 |
Neg logit contributions | |
ktop | -1.950 |
Groups | -1.926 |
kernels | -1.871 |
targ | -1.735 |
aurus | -1.684 |
Token | has |
Token ID | 468 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ォ | +2.058 |
est | +2.045 |
anas | +1.788 |
ィ | +1.733 |
arest | +1.667 |
Neg logit contributions | |
Groups | -2.160 |
ktop | -2.159 |
kernels | -2.084 |
targ | -1.948 |
aurus | -1.897 |
Token | got |
Token ID | 1392 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
ォ | +0.687 |
est | +0.685 |
anas | +0.605 |
ィ | +0.595 |
itals | +0.572 |
Neg logit contributions | |
Groups | -0.590 |
ktop | -0.589 |
kernels | -0.567 |
targ | -0.528 |
aurus | -0.516 |
Token | good |
Token ID | 922 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Groups | +1.898 |
ktop | +1.879 |
kernels | +1.850 |
targ | +1.684 |
aurus | +1.656 |
Neg logit contributions | |
ォ | -2.582 |
est | -2.524 |
anas | -2.254 |
ィ | -2.230 |
arest | -2.177 |
Token | reviews |
Token ID | 8088 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
ォ | +0.686 |
est | +0.685 |
anas | +0.602 |
ィ | +0.595 |
arest | +0.577 |
Neg logit contributions | |
ktop | -0.510 |
Groups | -0.508 |
kernels | -0.488 |
targ | -0.449 |
aurus | -0.441 |
Token | so |
Token ID | 523 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Groups | +1.671 |
ktop | +1.654 |
kernels | +1.625 |
targ | +1.484 |
aurus | +1.474 |
Neg logit contributions | |
ォ | -2.039 |
est | -1.988 |
anas | -1.773 |
ィ | -1.750 |
arest | -1.704 |
Token | far |
Token ID | 1290 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
Groups | +4.474 |
kernels | +4.383 |
ktop | +4.382 |
targ | +3.947 |
aurus | +3.937 |
Neg logit contributions | |
ォ | -6.945 |
est | -6.644 |
anas | -6.019 |
ィ | -5.950 |
itals | -5.850 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ォ | +0.899 |
est | +0.893 |
anas | +0.780 |
ィ | +0.772 |
arest | +0.750 |
Neg logit contributions | |
Groups | -0.765 |
ktop | -0.764 |
kernels | -0.745 |
targ | -0.687 |
aurus | -0.674 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e-03 |
Pos logit contributions | |
Groups | +0.819 |
ktop | +0.814 |
kernels | +0.799 |
targ | +0.740 |
aurus | +0.729 |
Neg logit contributions | |
ォ | -0.826 |
est | -0.808 |
anas | -0.708 |
ィ | -0.699 |
itals | -0.677 |
Token |
|
Token ID | 198 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
Groups | +0.006 |
ktop | +0.005 |
kernels | +0.005 |
aurus | +0.005 |
Writer | +0.005 |
Neg logit contributions | |
ォ | -0.006 |
est | -0.005 |
anas | -0.005 |
ィ | -0.005 |
itals | -0.005 |
Token | And |
Token ID | 1870 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
Groups | +0.092 |
ktop | +0.092 |
kernels | +0.090 |
targ | +0.084 |
aurus | +0.082 |
Neg logit contributions | |
ォ | -0.090 |
est | -0.089 |
anas | -0.077 |
ィ | -0.076 |
arest | -0.074 |
Token | can |
Token ID | 460 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Groups | +3.113 |
ktop | +3.053 |
kernels | +3.039 |
targ | +2.796 |
aurus | +2.754 |
Neg logit contributions | |
ォ | -3.311 |
est | -3.190 |
anas | -2.813 |
ィ | -2.800 |
itals | -2.718 |
Token | be |
Token ID | 307 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Groups | +1.516 |
ktop | +1.505 |
kernels | +1.473 |
targ | +1.348 |
aurus | +1.322 |
Neg logit contributions | |
ォ | -1.988 |
est | -1.958 |
anas | -1.737 |
ィ | -1.717 |
itals | -1.675 |
Token | traced |
Token ID | 23246 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
est | +0.474 |
ォ | +0.472 |
anas | +0.411 |
ィ | +0.402 |
arest | +0.393 |
Neg logit contributions | |
Groups | -0.468 |
ktop | -0.467 |
kernels | -0.450 |
targ | -0.420 |
aurus | -0.416 |
Token | back |
Token ID | 736 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ォ | +0.275 |
est | +0.273 |
anas | +0.230 |
ィ | +0.226 |
arest | +0.218 |
Neg logit contributions | |
Groups | -0.370 |
ktop | -0.370 |
kernels | -0.361 |
targ | -0.341 |
aurus | -0.334 |
Token | to |
Token ID | 284 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
Groups | +3.299 |
kernels | +3.260 |
ktop | +3.252 |
targ | +2.914 |
aurus | +2.857 |
Neg logit contributions | |
ォ | -5.603 |
est | -5.320 |
anas | -4.868 |
ィ | -4.846 |
itals | -4.740 |
Token | 1800 |
Token ID | 21431 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Groups | +3.479 |
kernels | +3.415 |
ktop | +3.371 |
targ | +3.102 |
aurus | +3.037 |
Neg logit contributions | |
ォ | -4.276 |
est | -4.150 |
ィ | -3.719 |
anas | -3.687 |
itals | -3.595 |
Token | . |
Token ID | 13 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
Groups | +4.793 |
kernels | +4.683 |
ktop | +4.493 |
targ | +4.107 |
aurus | +4.042 |
Neg logit contributions | |
ォ | -7.213 |
est | -6.847 |
ィ | -6.246 |
anas | -6.168 |
arest | -6.108 |
Token | Learn |
Token ID | 14365 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
Groups | +2.751 |
ktop | +2.599 |
kernels | +2.588 |
aurus | +2.370 |
targ | +2.354 |
Neg logit contributions | |
ォ | -2.884 |
est | -2.806 |
anas | -2.487 |
ィ | -2.453 |
itals | -2.431 |
Token | about |
Token ID | 546 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
est | +2.867 |
ォ | +2.762 |
anas | +2.440 |
ィ | +2.304 |
itals | +2.299 |
Neg logit contributions | |
ktop | -2.999 |
Groups | -2.893 |
kernels | -2.799 |
targ | -2.679 |
aurus | -2.600 |
Token | the |
Token ID | 262 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
est | +3.092 |
ォ | +3.059 |
anas | +2.722 |
ィ | +2.596 |
itals | +2.565 |
Neg logit contributions | |
ktop | -2.464 |
Groups | -2.332 |
kernels | -2.273 |
targ | -2.107 |
aurus | -2.093 |
Token | history |
Token ID | 2106 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
ktop | +0.775 |
Groups | +0.775 |
kernels | +0.755 |
targ | +0.700 |
aurus | +0.690 |
Neg logit contributions | |
ォ | -0.826 |
est | -0.814 |
anas | -0.714 |
ィ | -0.702 |
itals | -0.682 |
Token |
|
Token ID | 198 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Groups | +1.484 |
kernels | +1.432 |
ktop | +1.429 |
Writer | +1.298 |
aurus | +1.297 |
Neg logit contributions | |
ォ | -1.630 |
est | -1.491 |
anas | -1.361 |
ィ | -1.355 |
itals | -1.339 |
Token | The |
Token ID | 464 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Groups | +1.324 |
ktop | +1.319 |
kernels | +1.297 |
targ | +1.195 |
aurus | +1.179 |
Neg logit contributions | |
ォ | -1.356 |
est | -1.319 |
anas | -1.158 |
ィ | -1.146 |
itals | -1.112 |
Token | first |
Token ID | 717 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Groups | +1.062 |
ktop | +1.056 |
kernels | +1.034 |
targ | +0.954 |
aurus | +0.938 |
Neg logit contributions | |
ォ | -1.210 |
est | -1.187 |
anas | -1.048 |
ィ | -1.034 |
itals | -1.004 |
Token | instances |
Token ID | 10245 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
est | +4.802 |
ォ | +4.432 |
anas | +4.093 |
ィ | +3.972 |
arest | +3.857 |
Neg logit contributions | |
ktop | -4.033 |
Groups | -3.909 |
kernels | -3.610 |
aurus | -3.550 |
targ | -3.520 |
Token | on |
Token ID | 319 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Groups | +1.117 |
ktop | +1.109 |
kernels | +1.079 |
targ | +0.986 |
aurus | +0.966 |
Neg logit contributions | |
ォ | -1.644 |
est | -1.625 |
anas | -1.453 |
ィ | -1.435 |
itals | -1.398 |
Token | EC |
Token ID | 13182 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Groups | +0.755 |
ktop | +0.750 |
kernels | +0.732 |
targ | +0.675 |
aurus | +0.666 |
Neg logit contributions | |
ォ | -0.912 |
est | -0.901 |
anas | -0.796 |
ィ | -0.783 |
itals | -0.764 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
Groups | +5.697 |
kernels | +5.674 |
ktop | +5.522 |
targ | +4.996 |
aurus | +4.833 |
Neg logit contributions | |
ォ | -6.814 |
est | -6.419 |
ィ | -5.799 |
anas | -5.784 |
itals | -5.614 |
Token | were |
Token ID | 547 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
Groups | +0.096 |
ktop | +0.095 |
kernels | +0.092 |
targ | +0.086 |
aurus | +0.085 |
Neg logit contributions | |
ォ | -0.115 |
est | -0.114 |
anas | -0.100 |
ィ | -0.099 |
itals | -0.096 |
Token | configured |
Token ID | 17839 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Groups | +1.783 |
ktop | +1.766 |
kernels | +1.752 |
targ | +1.610 |
aurus | +1.577 |
Neg logit contributions | |
ォ | -1.864 |
est | -1.801 |
anas | -1.586 |
ィ | -1.575 |
arest | -1.529 |
Token | like |
Token ID | 588 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
Groups | +1.210 |
ktop | +1.201 |
kernels | +1.178 |
targ | +1.074 |
aurus | +1.054 |
Neg logit contributions | |
ォ | -1.636 |
est | -1.602 |
anas | -1.429 |
ィ | -1.415 |
itals | -1.377 |
Token | this |
Token ID | 428 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
Groups | +2.720 |
ktop | +2.673 |
kernels | +2.667 |
targ | +2.438 |
aurus | +2.386 |
Neg logit contributions | |
ォ | -2.937 |
est | -2.837 |
ィ | -2.506 |
anas | -2.503 |
arest | -2.422 |
Token | happened |
Token ID | 3022 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Groups | +3.222 |
kernels | +3.139 |
ktop | +3.134 |
targ | +2.788 |
aurus | +2.760 |
Neg logit contributions | |
ォ | -5.293 |
est | -5.103 |
anas | -4.600 |
ィ | -4.571 |
arest | -4.475 |
Token | . |
Token ID | 13 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Groups | +1.621 |
ktop | +1.605 |
kernels | +1.578 |
targ | +1.443 |
aurus | +1.428 |
Neg logit contributions | |
ォ | -1.995 |
est | -1.932 |
anas | -1.717 |
ィ | -1.707 |
itals | -1.657 |
Token | A |
Token ID | 317 |
Feature activation | +3.61e-03 |
Pos logit contributions | |
Groups | +0.930 |
ktop | +0.909 |
kernels | +0.896 |
targ | +0.823 |
aurus | +0.814 |
Neg logit contributions | |
ォ | -1.031 |
est | -1.006 |
anas | -0.890 |
ィ | -0.879 |
itals | -0.856 |
Token | Redd |
Token ID | 42734 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ォ | +0.016 |
est | +0.015 |
anas | +0.014 |
ィ | +0.013 |
itals | +0.013 |
Neg logit contributions | |
Groups | -0.014 |
ktop | -0.014 |
kernels | -0.014 |
targ | -0.013 |
aurus | -0.013 |
Token | itor |
Token ID | 2072 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Groups | +4.610 |
ktop | +4.418 |
kernels | +4.415 |
aurus | +4.007 |
Writer | +3.969 |
Neg logit contributions | |
ォ | -6.608 |
est | -6.022 |
anas | -5.649 |
ィ | -5.627 |
usterity | -5.408 |
Token | posted |
Token ID | 4481 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Groups | +4.702 |
kernels | +4.566 |
ktop | +4.526 |
targ | +4.234 |
reckoned | +4.216 |
Neg logit contributions | |
ォ | -5.436 |
est | -5.084 |
anas | -4.602 |
ィ | -4.565 |
arest | -4.487 |
Token | what |
Token ID | 644 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
Groups | +4.260 |
kernels | +4.164 |
ktop | +3.963 |
targ | +3.736 |
aurus | +3.644 |
Neg logit contributions | |
ォ | -6.524 |
est | -6.229 |
anas | -5.715 |
ィ | -5.649 |
arest | -5.579 |
Token | they |
Token ID | 484 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
ktop | +0.297 |
Groups | +0.295 |
kernels | +0.286 |
targ | +0.262 |
aurus | +0.255 |
Neg logit contributions | |
ォ | -0.429 |
est | -0.426 |
anas | -0.380 |
ィ | -0.375 |
itals | -0.366 |
Token | claimed |
Token ID | 4752 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
Groups | +1.485 |
ktop | +1.470 |
kernels | +1.445 |
targ | +1.319 |
aurus | +1.299 |
Neg logit contributions | |
ォ | -1.960 |
est | -1.918 |
anas | -1.712 |
ィ | -1.693 |
itals | -1.648 |
Token | was |
Token ID | 373 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
est | +2.694 |
ォ | +2.660 |
anas | +2.319 |
ィ | +2.277 |
itals | +2.261 |
Neg logit contributions | |
ktop | -2.270 |
Groups | -2.172 |
kernels | -2.149 |
targ | -1.974 |
aurus | -1.898 |
Token | photographic |
Token ID | 35788 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ktop | +0.537 |
Groups | +0.531 |
kernels | +0.514 |
targ | +0.471 |
aurus | +0.457 |
Neg logit contributions | |
ォ | -0.785 |
est | -0.776 |
anas | -0.692 |
ィ | -0.683 |
itals | -0.668 |