Token | Close |
Token ID | 13872 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
arnaev | +0.791 |
rompt | +0.761 |
psey | +0.722 |
ysis | +0.711 |
VIDIA | +0.677 |
Neg logit contributions | |
azel | -1.128 |
Devil | -1.037 |
igg | -1.011 |
Leader | -1.002 |
ten | -0.986 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
arnaev | +0.047 |
rompt | +0.046 |
psey | +0.044 |
ysis | +0.043 |
� | +0.041 |
Neg logit contributions | |
azel | -0.046 |
Devil | -0.042 |
igg | -0.040 |
Leader | -0.040 |
ten | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
arnaev | +0.165 |
rompt | +0.162 |
psey | +0.154 |
ysis | +0.151 |
� | +0.145 |
Neg logit contributions | |
azel | -0.161 |
Devil | -0.145 |
igg | -0.140 |
Leader | -0.138 |
ten | -0.136 |
Token | Email |
Token ID | 15333 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
arnaev | +0.460 |
rompt | +0.447 |
psey | +0.425 |
ysis | +0.416 |
VIDIA | +0.392 |
Neg logit contributions | |
azel | -0.595 |
Devil | -0.542 |
igg | -0.526 |
Leader | -0.522 |
ten | -0.515 |
Token | This |
Token ID | 770 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
arnaev | +0.087 |
rompt | +0.085 |
psey | +0.081 |
ysis | +0.080 |
� | +0.077 |
Neg logit contributions | |
azel | -0.073 |
Devil | -0.065 |
igg | -0.062 |
Leader | -0.062 |
ten | -0.061 |
Token | Story |
Token ID | 8362 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
arnaev | +0.649 |
rompt | +0.630 |
psey | +0.597 |
ysis | +0.584 |
VIDIA | +0.555 |
Neg logit contributions | |
azel | -0.894 |
Devil | -0.821 |
igg | -0.794 |
Leader | -0.785 |
ten | -0.776 |
Token | Send |
Token ID | 16290 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
arnaev | +2.069 |
rompt | +2.007 |
psey | +1.962 |
ysis | +1.820 |
VIDIA | +1.818 |
Neg logit contributions | |
azel | -2.980 |
Devil | -2.831 |
igg | -2.723 |
ten | -2.672 |
Leader | -2.671 |
Token | email |
Token ID | 3053 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
arnaev | +0.387 |
rompt | +0.378 |
psey | +0.363 |
ysis | +0.357 |
VIDIA | +0.341 |
Neg logit contributions | |
azel | -0.337 |
Devil | -0.302 |
igg | -0.290 |
Leader | -0.286 |
ten | -0.282 |
Token | to |
Token ID | 284 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
arnaev | +0.378 |
rompt | +0.370 |
psey | +0.354 |
ysis | +0.347 |
VIDIA | +0.332 |
Neg logit contributions | |
azel | -0.355 |
Devil | -0.320 |
igg | -0.307 |
Leader | -0.303 |
ten | -0.299 |
Token | this |
Token ID | 428 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
azel | +0.162 |
Devil | +0.144 |
igg | +0.139 |
Leader | +0.138 |
erad | +0.135 |
Neg logit contributions | |
arnaev | -0.179 |
rompt | -0.176 |
psey | -0.168 |
ysis | -0.165 |
� | -0.158 |
Token | address |
Token ID | 2209 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
arnaev | +0.389 |
rompt | +0.381 |
psey | +0.366 |
ysis | +0.361 |
VIDIA | +0.346 |
Neg logit contributions | |
azel | -0.276 |
Devil | -0.243 |
igg | -0.232 |
Leader | -0.229 |
ten | -0.225 |
Token | stubborn |
Token ID | 24444 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
arnaev | +0.167 |
rompt | +0.163 |
psey | +0.156 |
ysis | +0.153 |
� | +0.147 |
Neg logit contributions | |
azel | -0.155 |
Devil | -0.139 |
igg | -0.134 |
Leader | -0.132 |
ten | -0.130 |
Token | ." |
Token ID | 526 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
azel | +0.236 |
Devil | +0.212 |
igg | +0.204 |
Leader | +0.202 |
ten | +0.198 |
Neg logit contributions | |
arnaev | -0.256 |
rompt | -0.251 |
psey | -0.240 |
ysis | -0.237 |
� | -0.227 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
arnaev | +0.045 |
rompt | +0.044 |
psey | +0.042 |
ysis | +0.042 |
� | +0.040 |
Neg logit contributions | |
azel | -0.046 |
Devil | -0.041 |
igg | -0.040 |
Leader | -0.039 |
ten | -0.039 |
Token | Every |
Token ID | 6109 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
arnaev | +0.044 |
rompt | +0.043 |
psey | +0.041 |
ysis | +0.040 |
� | +0.039 |
Neg logit contributions | |
azel | -0.043 |
Devil | -0.038 |
igg | -0.037 |
Leader | -0.036 |
erad | -0.036 |
Token | share |
Token ID | 2648 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
arnaev | +0.086 |
rompt | +0.084 |
psey | +0.081 |
ysis | +0.079 |
� | +0.076 |
Neg logit contributions | |
azel | -0.077 |
Devil | -0.069 |
igg | -0.066 |
Leader | -0.065 |
ten | -0.064 |
Token | makes |
Token ID | 1838 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
azel | +0.475 |
Devil | +0.420 |
igg | +0.401 |
Leader | +0.397 |
ten | +0.395 |
Neg logit contributions | |
arnaev | -0.540 |
rompt | -0.527 |
psey | -0.505 |
ysis | -0.495 |
� | -0.480 |
Token | Black |
Token ID | 2619 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
arnaev | +2.401 |
rompt | +2.351 |
psey | +2.258 |
ysis | +2.227 |
VIDIA | +2.176 |
Neg logit contributions | |
azel | -1.811 |
Devil | -1.621 |
igg | -1.575 |
Leader | -1.521 |
erad | -1.510 |
Token | Voice |
Token ID | 15282 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
arnaev | +0.684 |
rompt | +0.671 |
psey | +0.649 |
ysis | +0.641 |
VIDIA | +0.618 |
Neg logit contributions | |
azel | -0.320 |
Devil | -0.273 |
igg | -0.255 |
Leader | -0.251 |
ten | -0.243 |
Token | louder |
Token ID | 27089 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
arnaev | +0.375 |
rompt | +0.366 |
psey | +0.349 |
ysis | +0.342 |
VIDIA | +0.325 |
Neg logit contributions | |
azel | -0.407 |
Devil | -0.368 |
igg | -0.356 |
Leader | -0.352 |
ten | -0.346 |
Token | ! |
Token ID | 0 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
arnaev | +0.501 |
rompt | +0.489 |
psey | +0.467 |
ysis | +0.457 |
VIDIA | +0.436 |
Neg logit contributions | |
azel | -0.508 |
Devil | -0.459 |
igg | -0.442 |
Leader | -0.437 |
ten | -0.430 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
arnaev | +0.191 |
rompt | +0.184 |
psey | +0.170 |
ysis | +0.165 |
VIDIA | +0.151 |
Neg logit contributions | |
azel | -0.429 |
Devil | -0.399 |
igg | -0.389 |
Leader | -0.386 |
ten | -0.382 |
Token | for |
Token ID | 329 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
arnaev | +0.174 |
rompt | +0.171 |
psey | +0.163 |
ysis | +0.160 |
� | +0.153 |
Neg logit contributions | |
azel | -0.164 |
Devil | -0.148 |
igg | -0.142 |
Leader | -0.140 |
ten | -0.138 |
Token | a |
Token ID | 257 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
azel | +0.029 |
Devil | +0.026 |
igg | +0.025 |
Leader | +0.025 |
ten | +0.024 |
Neg logit contributions | |
arnaev | -0.034 |
rompt | -0.033 |
psey | -0.032 |
ysis | -0.031 |
� | -0.030 |
Token | minute |
Token ID | 5664 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
arnaev | +0.485 |
rompt | +0.473 |
psey | +0.449 |
ysis | +0.440 |
VIDIA | +0.418 |
Neg logit contributions | |
azel | -0.569 |
Devil | -0.519 |
igg | -0.501 |
Leader | -0.495 |
ten | -0.490 |
Token | ... |
Token ID | 986 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
azel | +0.225 |
Devil | +0.205 |
igg | +0.199 |
Leader | +0.196 |
erad | +0.194 |
Neg logit contributions | |
arnaev | -0.171 |
rompt | -0.168 |
psey | -0.160 |
ysis | -0.156 |
� | -0.148 |
Token | we |
Token ID | 732 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
arnaev | +0.943 |
rompt | +0.919 |
psey | +0.865 |
ysis | +0.855 |
VIDIA | +0.811 |
Neg logit contributions | |
azel | -1.230 |
Devil | -1.135 |
igg | -1.096 |
Leader | -1.090 |
ten | -1.077 |
Token | 're |
Token ID | 821 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
arnaev | +0.661 |
rompt | +0.644 |
psey | +0.615 |
ysis | +0.606 |
VIDIA | +0.579 |
Neg logit contributions | |
azel | -0.649 |
Devil | -0.583 |
igg | -0.564 |
Leader | -0.553 |
erad | -0.547 |
Token | trying |
Token ID | 2111 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
arnaev | +2.382 |
rompt | +2.242 |
psey | +2.153 |
ysis | +2.144 |
VIDIA | +2.113 |
Neg logit contributions | |
azel | -1.739 |
Devil | -1.557 |
igg | -1.505 |
ten | -1.464 |
erad | -1.458 |
Token | to |
Token ID | 284 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
arnaev | +0.505 |
rompt | +0.494 |
psey | +0.472 |
ysis | +0.464 |
VIDIA | +0.446 |
Neg logit contributions | |
azel | -0.470 |
Devil | -0.422 |
igg | -0.407 |
Leader | -0.401 |
ten | -0.396 |
Token | find |
Token ID | 1064 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
arnaev | +1.450 |
rompt | +1.383 |
psey | +1.336 |
ysis | +1.307 |
VIDIA | +1.272 |
Neg logit contributions | |
azel | -1.631 |
Devil | -1.479 |
igg | -1.429 |
Leader | -1.415 |
erad | -1.389 |
Token | some |
Token ID | 617 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
azel | +0.832 |
Devil | +0.740 |
igg | +0.715 |
Leader | +0.707 |
ten | +0.686 |
Neg logit contributions | |
arnaev | -0.927 |
rompt | -0.919 |
psey | -0.866 |
ysis | -0.854 |
RTX | -0.826 |
Token | more |
Token ID | 517 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
azel | +0.976 |
Devil | +0.880 |
Leader | +0.848 |
igg | +0.842 |
ten | +0.829 |
Neg logit contributions | |
arnaev | -0.916 |
rompt | -0.902 |
psey | -0.866 |
ysis | -0.848 |
RTX | -0.809 |
Token | birth |
Token ID | 4082 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
arnaev | +0.089 |
rompt | +0.087 |
psey | +0.083 |
ysis | +0.082 |
� | +0.078 |
Neg logit contributions | |
azel | -0.091 |
Devil | -0.082 |
igg | -0.079 |
Leader | -0.078 |
ten | -0.077 |
Token | rate |
Token ID | 2494 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
arnaev | +0.549 |
rompt | +0.536 |
psey | +0.509 |
ysis | +0.497 |
VIDIA | +0.478 |
Neg logit contributions | |
azel | -0.600 |
Devil | -0.543 |
igg | -0.524 |
Leader | -0.516 |
ten | -0.511 |
Token | , |
Token ID | 11 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
azel | +0.165 |
Devil | +0.146 |
igg | +0.142 |
Leader | +0.140 |
ten | +0.137 |
Neg logit contributions | |
arnaev | -0.193 |
rompt | -0.189 |
psey | -0.181 |
ysis | -0.178 |
� | -0.172 |
Token | America |
Token ID | 2253 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
azel | +0.641 |
Devil | +0.569 |
igg | +0.551 |
Leader | +0.541 |
ten | +0.534 |
Neg logit contributions | |
arnaev | -0.652 |
rompt | -0.641 |
psey | -0.614 |
ysis | -0.603 |
VIDIA | -0.579 |
Token | needs |
Token ID | 2476 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
azel | +0.725 |
Devil | +0.645 |
igg | +0.625 |
Leader | +0.612 |
ten | +0.601 |
Neg logit contributions | |
arnaev | -0.782 |
rompt | -0.760 |
psey | -0.720 |
ysis | -0.716 |
� | -0.692 |
Token | future |
Token ID | 2003 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
arnaev | +0.743 |
rompt | +0.723 |
psey | +0.689 |
ysis | +0.676 |
VIDIA | +0.647 |
Neg logit contributions | |
azel | -0.721 |
Devil | -0.650 |
igg | -0.626 |
Leader | -0.620 |
erad | -0.610 |
Token | migrants |
Token ID | 12783 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
arnaev | +2.171 |
rompt | +2.160 |
psey | +1.999 |
ysis | +1.972 |
VIDIA | +1.921 |
Neg logit contributions | |
azel | -1.868 |
Devil | -1.682 |
Leader | -1.643 |
igg | -1.616 |
erad | -1.605 |
Token | 4 |
Token ID | 604 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
azel | +0.615 |
Devil | +0.542 |
igg | +0.528 |
Leader | +0.520 |
ten | +0.519 |
Neg logit contributions | |
arnaev | -0.682 |
rompt | -0.664 |
psey | -0.632 |
ysis | -0.627 |
� | -0.602 |
Token | ways |
Token ID | 2842 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
azel | +0.601 |
Devil | +0.530 |
igg | +0.510 |
Leader | +0.502 |
erad | +0.493 |
Neg logit contributions | |
arnaev | -0.677 |
rompt | -0.663 |
psey | -0.644 |
ysis | -0.630 |
� | -0.611 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
arnaev | +0.742 |
rompt | +0.726 |
psey | +0.694 |
ysis | +0.681 |
VIDIA | +0.654 |
Neg logit contributions | |
azel | -0.673 |
Devil | -0.609 |
igg | -0.584 |
Leader | -0.576 |
ten | -0.567 |
Token | looms |
Token ID | 46234 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
arnaev | +0.745 |
rompt | +0.729 |
psey | +0.695 |
ysis | +0.678 |
VIDIA | +0.649 |
Neg logit contributions | |
azel | -0.775 |
Devil | -0.704 |
igg | -0.679 |
Leader | -0.671 |
erad | -0.664 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
arnaev | +0.176 |
rompt | +0.172 |
psey | +0.165 |
ysis | +0.162 |
� | +0.155 |
Neg logit contributions | |
azel | -0.151 |
Devil | -0.135 |
igg | -0.129 |
Leader | -0.128 |
ten | -0.126 |
Token | The |
Token ID | 383 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
arnaev | +0.161 |
rompt | +0.158 |
psey | +0.151 |
ysis | +0.148 |
� | +0.142 |
Neg logit contributions | |
azel | -0.143 |
Devil | -0.128 |
igg | -0.123 |
Leader | -0.122 |
ten | -0.120 |
Token | BBC |
Token ID | 7823 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
arnaev | +0.251 |
rompt | +0.245 |
psey | +0.234 |
ysis | +0.230 |
� | +0.220 |
Neg logit contributions | |
azel | -0.234 |
Devil | -0.211 |
igg | -0.203 |
Leader | -0.200 |
ten | -0.197 |
Token | 's |
Token ID | 338 |
Feature activation | +9.08e-03 |
Pos logit contributions | |
arnaev | +0.170 |
rompt | +0.167 |
psey | +0.159 |
ysis | +0.156 |
� | +0.150 |
Neg logit contributions | |
azel | -0.152 |
Devil | -0.136 |
igg | -0.131 |
Leader | -0.129 |
ten | -0.127 |
Token | Im |
Token ID | 1846 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
arnaev | +0.007 |
rompt | +0.007 |
psey | +0.007 |
ysis | +0.007 |
� | +0.006 |
Neg logit contributions | |
azel | -0.006 |
Devil | -0.006 |
igg | -0.005 |
Leader | -0.005 |
ten | -0.005 |
Token | ogen |
Token ID | 6644 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
azel | +0.098 |
Devil | +0.090 |
igg | +0.087 |
Leader | +0.086 |
erad | +0.085 |
Neg logit contributions | |
arnaev | -0.074 |
rompt | -0.072 |
psey | -0.068 |
ysis | -0.067 |
� | -0.063 |
Token | F |
Token ID | 376 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
arnaev | +1.840 |
rompt | +1.804 |
psey | +1.726 |
ysis | +1.663 |
VIDIA | +1.586 |
Neg logit contributions | |
azel | -1.947 |
Devil | -1.783 |
igg | -1.722 |
ten | -1.680 |
Leader | -1.677 |
Token | oul |
Token ID | 2852 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
arnaev | +0.570 |
rompt | +0.555 |
psey | +0.528 |
ysis | +0.516 |
� | +0.492 |
Neg logit contributions | |
azel | -0.668 |
Devil | -0.602 |
igg | -0.587 |
Leader | -0.575 |
ten | -0.570 |
Token | kes |
Token ID | 5209 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
azel | +0.860 |
Devil | +0.782 |
Leader | +0.751 |
igg | +0.750 |
erad | +0.737 |
Neg logit contributions | |
arnaev | -0.698 |
rompt | -0.687 |
psey | -0.658 |
ysis | -0.639 |
� | -0.611 |
Token | , |
Token ID | 11 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
arnaev | +0.370 |
rompt | +0.362 |
psey | +0.346 |
ysis | +0.340 |
VIDIA | +0.325 |
Neg logit contributions | |
azel | -0.332 |
Devil | -0.298 |
igg | -0.286 |
Leader | -0.282 |
ten | -0.278 |
Token | in |
Token ID | 287 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
azel | +0.019 |
Devil | +0.017 |
igg | +0.017 |
Leader | +0.016 |
ten | +0.016 |
Neg logit contributions | |
arnaev | -0.022 |
rompt | -0.021 |
psey | -0.021 |
ysis | -0.020 |
� | -0.019 |
Token | with |
Token ID | 351 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
azel | +0.056 |
Devil | +0.050 |
igg | +0.048 |
Leader | +0.048 |
ten | +0.047 |
Neg logit contributions | |
arnaev | -0.057 |
rompt | -0.056 |
psey | -0.053 |
ysis | -0.052 |
� | -0.050 |
Token | kindred |
Token ID | 46449 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
arnaev | +0.243 |
rompt | +0.232 |
psey | +0.208 |
ysis | +0.199 |
� | +0.176 |
Neg logit contributions | |
azel | -0.816 |
Devil | -0.765 |
igg | -0.747 |
Leader | -0.741 |
ten | -0.735 |
Token | spirits |
Token ID | 13747 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
azel | +0.098 |
Devil | +0.085 |
igg | +0.080 |
Leader | +0.080 |
ten | +0.078 |
Neg logit contributions | |
arnaev | -0.164 |
rompt | -0.162 |
psey | -0.156 |
ysis | -0.154 |
� | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
arnaev | +0.098 |
rompt | +0.096 |
psey | +0.092 |
ysis | +0.091 |
� | +0.087 |
Neg logit contributions | |
azel | -0.084 |
Devil | -0.075 |
igg | -0.072 |
Leader | -0.071 |
ten | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
arnaev | +0.488 |
rompt | +0.478 |
psey | +0.457 |
ysis | +0.448 |
VIDIA | +0.430 |
Neg logit contributions | |
azel | -0.464 |
Devil | -0.418 |
igg | -0.402 |
Leader | -0.397 |
ten | -0.392 |
Token |
|
Token ID | 198 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
arnaev | +0.202 |
rompt | +0.198 |
psey | +0.189 |
ysis | +0.185 |
� | +0.177 |
Neg logit contributions | |
azel | -0.196 |
Devil | -0.177 |
igg | -0.170 |
Leader | -0.168 |
ten | -0.166 |
Token | Sign |
Token ID | 11712 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
arnaev | +1.870 |
rompt | +1.799 |
psey | +1.742 |
ysis | +1.716 |
VIDIA | +1.655 |
Neg logit contributions | |
azel | -1.638 |
Devil | -1.499 |
Leader | -1.451 |
igg | -1.441 |
ten | -1.403 |
Token | up |
Token ID | 510 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
arnaev | +0.112 |
rompt | +0.109 |
psey | +0.103 |
ysis | +0.101 |
� | +0.095 |
Neg logit contributions | |
azel | -0.153 |
Devil | -0.140 |
igg | -0.136 |
Leader | -0.134 |
ten | -0.133 |
Token | for |
Token ID | 329 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
arnaev | +0.107 |
rompt | +0.105 |
psey | +0.100 |
ysis | +0.099 |
� | +0.094 |
Neg logit contributions | |
azel | -0.105 |
Devil | -0.094 |
igg | -0.091 |
Leader | -0.090 |
ten | -0.088 |
Token | our |
Token ID | 674 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
arnaev | +0.593 |
rompt | +0.580 |
psey | +0.553 |
ysis | +0.544 |
VIDIA | +0.522 |
Neg logit contributions | |
azel | -0.551 |
Devil | -0.498 |
igg | -0.477 |
Leader | -0.470 |
ten | -0.466 |
Token | Wine |
Token ID | 20447 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
arnaev | +0.914 |
rompt | +0.896 |
psey | +0.841 |
ysis | +0.830 |
VIDIA | +0.800 |
Neg logit contributions | |
azel | -1.063 |
Devil | -0.976 |
igg | -0.934 |
Leader | -0.919 |
ten | -0.918 |
Token | an |
Token ID | 281 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
azel | +0.014 |
Devil | +0.013 |
igg | +0.012 |
Leader | +0.012 |
ten | +0.012 |
Neg logit contributions | |
arnaev | -0.016 |
rompt | -0.015 |
psey | -0.015 |
ysis | -0.015 |
� | -0.014 |
Token | appearance |
Token ID | 5585 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
azel | +0.082 |
Devil | +0.074 |
igg | +0.071 |
Leader | +0.070 |
ten | +0.069 |
Neg logit contributions | |
arnaev | -0.087 |
rompt | -0.086 |
psey | -0.081 |
ysis | -0.080 |
� | -0.077 |
Token | with |
Token ID | 351 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
azel | +0.152 |
Devil | +0.136 |
igg | +0.131 |
Leader | +0.129 |
ten | +0.127 |
Neg logit contributions | |
arnaev | -0.165 |
rompt | -0.162 |
psey | -0.154 |
ysis | -0.152 |
� | -0.145 |
Token | Treasury |
Token ID | 13419 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
azel | +0.033 |
Devil | +0.030 |
igg | +0.029 |
Leader | +0.028 |
ten | +0.028 |
Neg logit contributions | |
arnaev | -0.034 |
rompt | -0.034 |
psey | -0.032 |
ysis | -0.031 |
� | -0.030 |
Token | Secretary |
Token ID | 4986 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
azel | +0.365 |
Devil | +0.324 |
igg | +0.311 |
Leader | +0.306 |
ten | +0.301 |
Neg logit contributions | |
arnaev | -0.439 |
rompt | -0.430 |
psey | -0.412 |
ysis | -0.402 |
� | -0.390 |
Token | Steven |
Token ID | 8239 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
arnaev | +1.199 |
rompt | +1.159 |
psey | +1.102 |
ysis | +1.084 |
VIDIA | +1.035 |
Neg logit contributions | |
azel | -1.279 |
Devil | -1.173 |
igg | -1.124 |
erad | -1.099 |
Leader | -1.097 |
Token | Mn |
Token ID | 36030 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
arnaev | +0.906 |
rompt | +0.831 |
psey | +0.784 |
ysis | +0.749 |
VIDIA | +0.715 |
Neg logit contributions | |
azel | -2.589 |
Devil | -2.448 |
igg | -2.370 |
erad | -2.318 |
ten | -2.313 |
Token | uchin |
Token ID | 43416 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
arnaev | +0.472 |
rompt | +0.448 |
psey | +0.412 |
ysis | +0.395 |
RTX | +0.362 |
Neg logit contributions | |
azel | -1.353 |
Devil | -1.258 |
igg | -1.236 |
Leader | -1.216 |
ten | -1.209 |
Token | , |
Token ID | 11 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
arnaev | +0.319 |
rompt | +0.312 |
psey | +0.299 |
ysis | +0.294 |
� | +0.281 |
Neg logit contributions | |
azel | -0.277 |
Devil | -0.248 |
igg | -0.238 |
Leader | -0.235 |
ten | -0.231 |
Token | that |
Token ID | 326 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
arnaev | +0.032 |
rompt | +0.031 |
psey | +0.030 |
ysis | +0.029 |
� | +0.028 |
Neg logit contributions | |
azel | -0.029 |
Devil | -0.026 |
igg | -0.025 |
Leader | -0.024 |
ten | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
arnaev | +0.081 |
rompt | +0.080 |
psey | +0.076 |
ysis | +0.075 |
� | +0.072 |
Neg logit contributions | |
azel | -0.073 |
Devil | -0.065 |
igg | -0.063 |
Leader | -0.062 |
ten | -0.061 |
Token | made |
Token ID | 925 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
arnaev | +0.108 |
rompt | +0.106 |
psey | +0.101 |
ysis | +0.099 |
� | +0.095 |
Neg logit contributions | |
azel | -0.091 |
Devil | -0.081 |
igg | -0.078 |
Leader | -0.077 |
ten | -0.076 |
Token | with |
Token ID | 351 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
arnaev | +0.152 |
rompt | +0.148 |
psey | +0.142 |
ysis | +0.139 |
� | +0.133 |
Neg logit contributions | |
azel | -0.143 |
Devil | -0.129 |
igg | -0.124 |
Leader | -0.122 |
ten | -0.120 |
Token | S |
Token ID | 311 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
arnaev | +0.200 |
rompt | +0.196 |
psey | +0.187 |
ysis | +0.184 |
� | +0.175 |
Neg logit contributions | |
azel | -0.196 |
Devil | -0.176 |
igg | -0.170 |
Leader | -0.168 |
ten | -0.165 |
Token | ich |
Token ID | 488 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
azel | +0.266 |
Devil | +0.239 |
igg | +0.228 |
Leader | +0.227 |
erad | +0.223 |
Neg logit contributions | |
arnaev | -0.304 |
rompt | -0.297 |
psey | -0.285 |
ysis | -0.280 |
� | -0.268 |
Token | uan |
Token ID | 7258 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
azel | +0.528 |
Devil | +0.475 |
igg | +0.459 |
Leader | +0.456 |
erad | +0.447 |
Neg logit contributions | |
arnaev | -0.503 |
rompt | -0.493 |
psey | -0.467 |
ysis | -0.459 |
� | -0.437 |
Token | pe |
Token ID | 613 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
arnaev | +0.070 |
rompt | +0.069 |
psey | +0.066 |
ysis | +0.065 |
� | +0.062 |
Neg logit contributions | |
azel | -0.063 |
Devil | -0.057 |
igg | -0.055 |
Leader | -0.054 |
ten | -0.053 |
Token | pperc |
Token ID | 39921 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
arnaev | +1.567 |
rompt | +1.520 |
psey | +1.448 |
ysis | +1.403 |
VIDIA | +1.365 |
Neg logit contributions | |
azel | -1.874 |
Devil | -1.692 |
igg | -1.635 |
Leader | -1.604 |
ten | -1.602 |
Token | orns |
Token ID | 19942 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
arnaev | +0.214 |
rompt | +0.211 |
psey | +0.203 |
ysis | +0.201 |
� | +0.194 |
Neg logit contributions | |
azel | -0.101 |
Devil | -0.085 |
igg | -0.080 |
Leader | -0.079 |
ten | -0.077 |
Token | ( |
Token ID | 357 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
azel | +0.161 |
Devil | +0.143 |
igg | +0.138 |
Leader | +0.136 |
ten | +0.133 |
Neg logit contributions | |
arnaev | -0.188 |
rompt | -0.184 |
psey | -0.176 |
ysis | -0.173 |
� | -0.166 |
Token | which |
Token ID | 4758 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
arnaev | +0.007 |
rompt | +0.007 |
psey | +0.007 |
ysis | +0.007 |
� | +0.007 |
Neg logit contributions | |
azel | -0.007 |
Devil | -0.007 |
igg | -0.006 |
Leader | -0.006 |
erad | -0.006 |
Token | I |
Token ID | 314 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
azel | +0.358 |
Devil | +0.319 |
igg | +0.309 |
Leader | +0.305 |
ten | +0.300 |
Neg logit contributions | |
arnaev | -0.399 |
rompt | -0.391 |
psey | -0.373 |
ysis | -0.368 |
� | -0.352 |
Token | 220 |
Token ID | 17572 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
arnaev | +0.471 |
rompt | +0.461 |
psey | +0.441 |
ysis | +0.434 |
� | +0.415 |
Neg logit contributions | |
azel | -0.411 |
Devil | -0.367 |
igg | -0.354 |
Leader | -0.349 |
ten | -0.344 |
Token | 22 |
Token ID | 1828 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
arnaev | +0.369 |
rompt | +0.361 |
psey | +0.346 |
ysis | +0.340 |
� | +0.326 |
Neg logit contributions | |
azel | -0.316 |
Devil | -0.282 |
igg | -0.271 |
Leader | -0.268 |
ten | -0.263 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
arnaev | +0.360 |
rompt | +0.353 |
psey | +0.338 |
ysis | +0.332 |
� | +0.318 |
Neg logit contributions | |
azel | -0.298 |
Devil | -0.266 |
igg | -0.255 |
Leader | -0.252 |
ten | -0.248 |
Token | jpg |
Token ID | 9479 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
arnaev | +0.014 |
rompt | +0.013 |
psey | +0.013 |
ysis | +0.013 |
� | +0.012 |
Neg logit contributions | |
azel | -0.009 |
Devil | -0.008 |
igg | -0.008 |
Leader | -0.008 |
erad | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
arnaev | +0.076 |
rompt | +0.075 |
psey | +0.071 |
ysis | +0.070 |
� | +0.067 |
Neg logit contributions | |
azel | -0.075 |
Devil | -0.067 |
igg | -0.065 |
Leader | -0.064 |
ten | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
arnaev | +0.040 |
rompt | +0.039 |
psey | +0.037 |
ysis | +0.036 |
� | +0.035 |
Neg logit contributions | |
azel | -0.039 |
Devil | -0.035 |
igg | -0.034 |
Leader | -0.033 |
ten | -0.033 |
Token | Email |
Token ID | 15333 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
arnaev | +1.620 |
rompt | +1.551 |
psey | +1.496 |
ysis | +1.458 |
VIDIA | +1.405 |
Neg logit contributions | |
azel | -1.838 |
Devil | -1.652 |
igg | -1.634 |
Leader | -1.631 |
ten | -1.568 |
Token |
|
Token ID | 198 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
azel | +0.172 |
Devil | +0.154 |
igg | +0.149 |
Leader | +0.147 |
erad | +0.145 |
Neg logit contributions | |
arnaev | -0.171 |
rompt | -0.167 |
psey | -0.159 |
ysis | -0.157 |
� | -0.151 |
Token |
|
Token ID | 198 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
arnaev | +0.054 |
rompt | +0.053 |
psey | +0.050 |
ysis | +0.050 |
� | +0.048 |
Neg logit contributions | |
azel | -0.053 |
Devil | -0.048 |
igg | -0.046 |
Leader | -0.045 |
ten | -0.045 |
Token | Dis |
Token ID | 7279 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
arnaev | +0.177 |
rompt | +0.174 |
psey | +0.167 |
ysis | +0.164 |
� | +0.158 |
Neg logit contributions | |
azel | -0.126 |
Devil | -0.111 |
igg | -0.106 |
Leader | -0.105 |
ten | -0.103 |
Token | ruption |
Token ID | 6417 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
arnaev | +0.315 |
rompt | +0.302 |
psey | +0.277 |
ysis | +0.267 |
VIDIA | +0.248 |
Neg logit contributions | |
azel | -0.800 |
Devil | -0.745 |
igg | -0.727 |
Leader | -0.721 |
ten | -0.715 |
Token | and |
Token ID | 290 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
arnaev | +0.506 |
rompt | +0.496 |
psey | +0.474 |
ysis | +0.464 |
VIDIA | +0.444 |
Neg logit contributions | |
azel | -0.480 |
Devil | -0.432 |
igg | -0.416 |
Leader | -0.410 |
ten | -0.404 |
Token | running |
Token ID | 2491 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
arnaev | +0.286 |
rompt | +0.279 |
psey | +0.265 |
ysis | +0.260 |
� | +0.247 |
Neg logit contributions | |
azel | -0.321 |
Devil | -0.291 |
igg | -0.281 |
Leader | -0.278 |
ten | -0.274 |
Token | back |
Token ID | 736 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
arnaev | +0.593 |
rompt | +0.580 |
psey | +0.555 |
ysis | +0.544 |
� | +0.522 |
Neg logit contributions | |
azel | -0.491 |
Devil | -0.440 |
igg | -0.421 |
Leader | -0.415 |
ten | -0.409 |
Token | Sam |
Token ID | 3409 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
arnaev | +0.242 |
rompt | +0.237 |
psey | +0.226 |
ysis | +0.222 |
� | +0.212 |
Neg logit contributions | |
azel | -0.223 |
Devil | -0.200 |
igg | -0.193 |
Leader | -0.190 |
ten | -0.187 |
Token | aj |
Token ID | 1228 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
azel | +0.022 |
Devil | +0.020 |
igg | +0.019 |
Leader | +0.019 |
erad | +0.019 |
Neg logit contributions | |
arnaev | -0.023 |
rompt | -0.023 |
psey | -0.022 |
ysis | -0.022 |
� | -0.021 |
Token | e |
Token ID | 68 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
azel | +0.113 |
Devil | +0.103 |
igg | +0.100 |
Leader | +0.099 |
erad | +0.097 |
Neg logit contributions | |
arnaev | -0.093 |
rompt | -0.091 |
psey | -0.086 |
ysis | -0.085 |
� | -0.080 |
Token | Per |
Token ID | 2448 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
arnaev | +1.877 |
rompt | +1.809 |
psey | +1.760 |
ysis | +1.714 |
RTX | +1.660 |
Neg logit contributions | |
azel | -1.576 |
Devil | -1.419 |
igg | -1.339 |
erad | -1.288 |
Leader | -1.287 |
Token | ine |
Token ID | 500 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
azel | +0.384 |
Devil | +0.320 |
Leader | +0.297 |
igg | +0.292 |
ten | +0.282 |
Neg logit contributions | |
arnaev | -0.975 |
rompt | -0.958 |
psey | -0.931 |
ysis | -0.914 |
� | -0.886 |
Token | lead |
Token ID | 1085 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
arnaev | +0.617 |
rompt | +0.604 |
psey | +0.577 |
ysis | +0.566 |
VIDIA | +0.543 |
Neg logit contributions | |
azel | -0.558 |
Devil | -0.500 |
igg | -0.481 |
Leader | -0.474 |
ten | -0.467 |
Token | through |
Token ID | 832 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
arnaev | +0.318 |
rompt | +0.311 |
psey | +0.297 |
ysis | +0.292 |
� | +0.279 |
Neg logit contributions | |
azel | -0.296 |
Devil | -0.266 |
igg | -0.255 |
Leader | -0.252 |
ten | -0.248 |
Token | the |
Token ID | 262 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
arnaev | +0.303 |
rompt | +0.296 |
psey | +0.283 |
ysis | +0.278 |
� | +0.266 |
Neg logit contributions | |
azel | -0.276 |
Devil | -0.248 |
igg | -0.238 |
Leader | -0.235 |
ten | -0.232 |
Token | MAR |
Token ID | 18805 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
arnaev | +1.082 |
rompt | +1.066 |
psey | +1.014 |
ysis | +0.985 |
xus | +0.933 |
Neg logit contributions | |
azel | -1.199 |
Devil | -1.092 |
igg | -1.058 |
Leader | -1.040 |
erad | -1.016 |
Token | G |
Token ID | 38 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
azel | +0.274 |
Devil | +0.235 |
igg | +0.223 |
Leader | +0.218 |
ten | +0.217 |
Neg logit contributions | |
arnaev | -0.482 |
rompt | -0.475 |
psey | -0.458 |
ysis | -0.454 |
� | -0.441 |
Token | IN |
Token ID | 1268 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
azel | +0.775 |
Devil | +0.660 |
igg | +0.629 |
ten | +0.625 |
erad | +0.620 |
Neg logit contributions | |
arnaev | -1.192 |
rompt | -1.172 |
psey | -1.115 |
ysis | -1.100 |
� | -1.093 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
arnaev | +0.081 |
rompt | +0.079 |
psey | +0.075 |
ysis | +0.074 |
� | +0.071 |
Neg logit contributions | |
azel | -0.079 |
Devil | -0.071 |
igg | -0.069 |
Leader | -0.068 |
ten | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
arnaev | +0.033 |
rompt | +0.032 |
psey | +0.031 |
ysis | +0.030 |
� | +0.029 |
Neg logit contributions | |
azel | -0.033 |
Devil | -0.029 |
igg | -0.028 |
Leader | -0.028 |
ten | -0.028 |
Token | You |
Token ID | 1639 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
azel | +0.953 |
Devil | +0.854 |
igg | +0.813 |
erad | +0.802 |
Perspective | +0.794 |
Neg logit contributions | |
arnaev | -0.968 |
rompt | -0.958 |
psey | -0.903 |
ysis | -0.893 |
� | -0.887 |
Token | can |
Token ID | 460 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
arnaev | +1.689 |
rompt | +1.679 |
psey | +1.569 |
ysis | +1.557 |
VIDIA | +1.493 |
Neg logit contributions | |
azel | -1.696 |
Devil | -1.519 |
Leader | -1.453 |
igg | -1.449 |
erad | -1.419 |
Token | check |
Token ID | 2198 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
arnaev | +0.129 |
rompt | +0.126 |
psey | +0.120 |
ysis | +0.118 |
� | +0.112 |
Neg logit contributions | |
azel | -0.141 |
Devil | -0.128 |
igg | -0.124 |
Leader | -0.122 |
ten | -0.121 |
Token | out |
Token ID | 503 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
azel | +0.404 |
Devil | +0.357 |
igg | +0.344 |
Leader | +0.340 |
ten | +0.334 |
Neg logit contributions | |
arnaev | -0.471 |
rompt | -0.462 |
psey | -0.445 |
ysis | -0.438 |
� | -0.419 |
Token | my |
Token ID | 616 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
arnaev | +0.332 |
rompt | +0.324 |
psey | +0.309 |
ysis | +0.303 |
� | +0.288 |
Neg logit contributions | |
azel | -0.364 |
Devil | -0.331 |
igg | -0.319 |
Leader | -0.315 |
ten | -0.311 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
azel | +0.406 |
Devil | +0.362 |
igg | +0.344 |
Leader | +0.343 |
erad | +0.336 |
Neg logit contributions | |
arnaev | -0.487 |
rompt | -0.477 |
psey | -0.460 |
ysis | -0.452 |
� | -0.434 |
Token | Carey |
Token ID | 31612 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
arnaev | +1.464 |
rompt | +1.441 |
psey | +1.391 |
ysis | +1.358 |
VIDIA | +1.321 |
Neg logit contributions | |
azel | -0.855 |
Devil | -0.744 |
igg | -0.705 |
Leader | -0.687 |
ten | -0.677 |
Token | , |
Token ID | 11 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
arnaev | +0.639 |
rompt | +0.625 |
psey | +0.599 |
ysis | +0.586 |
VIDIA | +0.564 |
Neg logit contributions | |
azel | -0.510 |
Devil | -0.454 |
igg | -0.435 |
Leader | -0.427 |
ten | -0.423 |
Token | a |
Token ID | 257 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
azel | +0.052 |
Devil | +0.047 |
igg | +0.045 |
Leader | +0.044 |
ten | +0.043 |
Neg logit contributions | |
arnaev | -0.060 |
rompt | -0.059 |
psey | -0.057 |
ysis | -0.056 |
� | -0.053 |
Token | Fore |
Token ID | 4558 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
azel | +0.385 |
Devil | +0.344 |
igg | +0.335 |
Leader | +0.331 |
ten | +0.327 |
Neg logit contributions | |
arnaev | -0.350 |
rompt | -0.341 |
psey | -0.325 |
ysis | -0.317 |
� | -0.303 |
Token | word |
Token ID | 4775 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
arnaev | +0.915 |
rompt | +0.893 |
psey | +0.862 |
ysis | +0.841 |
VIDIA | +0.814 |
Neg logit contributions | |
azel | -0.777 |
Devil | -0.694 |
igg | -0.670 |
Leader | -0.662 |
ten | -0.654 |
Token | by |
Token ID | 416 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
azel | +0.029 |
Devil | +0.026 |
igg | +0.025 |
Leader | +0.025 |
ten | +0.025 |
Neg logit contributions | |
arnaev | -0.028 |
rompt | -0.028 |
psey | -0.026 |
ysis | -0.026 |
� | -0.025 |
Token | Patrick |
Token ID | 9925 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
arnaev | +1.661 |
rompt | +1.584 |
psey | +1.504 |
ysis | +1.498 |
� | +1.430 |
Neg logit contributions | |
azel | -1.747 |
Devil | -1.576 |
igg | -1.527 |
erad | -1.483 |
ten | -1.482 |
Token | J |
Token ID | 449 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
azel | +0.456 |
Devil | +0.407 |
igg | +0.394 |
Leader | +0.394 |
erad | +0.387 |
Neg logit contributions | |
arnaev | -0.439 |
rompt | -0.428 |
psey | -0.410 |
ysis | -0.404 |
� | -0.387 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
azel | +1.019 |
Devil | +0.922 |
Leader | +0.894 |
erad | +0.882 |
ten | +0.876 |
Neg logit contributions | |
arnaev | -1.105 |
rompt | -1.083 |
psey | -1.025 |
ysis | -0.997 |
� | -0.960 |
Token | Buchanan |
Token ID | 36358 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
azel | +0.851 |
Devil | +0.742 |
Leader | +0.720 |
igg | +0.703 |
erad | +0.696 |
Neg logit contributions | |
arnaev | -1.283 |
rompt | -1.242 |
psey | -1.214 |
ysis | -1.192 |
� | -1.156 |
Token | , |
Token ID | 11 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
azel | +0.890 |
Devil | +0.803 |
igg | +0.778 |
Leader | +0.762 |
erad | +0.746 |
Neg logit contributions | |
arnaev | -0.982 |
rompt | -0.972 |
psey | -0.933 |
ysis | -0.909 |
� | -0.882 |
Token | emails |
Token ID | 7237 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
arnaev | +0.690 |
rompt | +0.674 |
psey | +0.649 |
ysis | +0.636 |
� | +0.610 |
Neg logit contributions | |
azel | -0.548 |
Devil | -0.491 |
igg | -0.468 |
Leader | -0.461 |
ten | -0.453 |
Token | Trump |
Token ID | 1301 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
azel | +0.074 |
Devil | +0.066 |
igg | +0.064 |
Leader | +0.063 |
ten | +0.062 |
Neg logit contributions | |
arnaev | -0.078 |
rompt | -0.077 |
psey | -0.073 |
ysis | -0.072 |
� | -0.069 |
Token | urges |
Token ID | 28804 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
azel | +0.443 |
Devil | +0.396 |
igg | +0.384 |
Leader | +0.376 |
ten | +0.371 |
Neg logit contributions | |
arnaev | -0.453 |
rompt | -0.446 |
psey | -0.422 |
ysis | -0.418 |
� | -0.399 |
Token | North |
Token ID | 2258 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
arnaev | +0.632 |
rompt | +0.620 |
psey | +0.594 |
ysis | +0.584 |
VIDIA | +0.560 |
Neg logit contributions | |
azel | -0.477 |
Devil | -0.426 |
igg | -0.405 |
Leader | -0.401 |
erad | -0.393 |
Token | Korea |
Token ID | 4969 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
azel | +0.586 |
Devil | +0.526 |
igg | +0.514 |
Leader | +0.505 |
ten | +0.498 |
Neg logit contributions | |
arnaev | -0.562 |
rompt | -0.547 |
psey | -0.520 |
ysis | -0.506 |
� | -0.490 |
Token | to |
Token ID | 284 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
azel | +0.039 |
Devil | +0.035 |
igg | +0.034 |
Leader | +0.034 |
ten | +0.033 |
Neg logit contributions | |
arnaev | -0.040 |
rompt | -0.040 |
psey | -0.038 |
ysis | -0.037 |
� | -0.035 |
Token | den |
Token ID | 2853 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
arnaev | +1.772 |
rompt | +1.700 |
psey | +1.631 |
ysis | +1.593 |
VIDIA | +1.552 |
Neg logit contributions | |
azel | -1.582 |
Devil | -1.464 |
Leader | -1.385 |
erad | -1.364 |
igg | -1.358 |
Token | uclear |
Token ID | 4016 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
arnaev | +0.485 |
rompt | +0.474 |
psey | +0.449 |
ysis | +0.437 |
VIDIA | +0.414 |
Neg logit contributions | |
azel | -0.636 |
Devil | -0.582 |
igg | -0.564 |
Leader | -0.558 |
ten | -0.550 |
Token | ize |
Token ID | 1096 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
arnaev | +1.082 |
rompt | +1.046 |
psey | +0.984 |
ysis | +0.950 |
VIDIA | +0.913 |
Neg logit contributions | |
azel | -1.657 |
Devil | -1.528 |
Leader | -1.475 |
igg | -1.472 |
ten | -1.447 |
Token | ahead |
Token ID | 4058 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
arnaev | +1.348 |
rompt | +1.318 |
psey | +1.278 |
ysis | +1.234 |
VIDIA | +1.193 |
Neg logit contributions | |
azel | -1.331 |
Devil | -1.234 |
Leader | -1.166 |
igg | -1.162 |
ten | -1.130 |
Token | of |
Token ID | 286 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
arnaev | +0.189 |
rompt | +0.185 |
psey | +0.178 |
ysis | +0.175 |
� | +0.169 |
Neg logit contributions | |
azel | -0.140 |
Devil | -0.123 |
igg | -0.118 |
Leader | -0.116 |
ten | -0.114 |
Token | head |
Token ID | 1182 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
arnaev | +0.222 |
rompt | +0.217 |
psey | +0.207 |
ysis | +0.203 |
� | +0.194 |
Neg logit contributions | |
azel | -0.217 |
Devil | -0.195 |
igg | -0.188 |
Leader | -0.186 |
ten | -0.183 |
Token | of |
Token ID | 286 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
arnaev | +0.251 |
rompt | +0.246 |
psey | +0.236 |
ysis | +0.233 |
� | +0.223 |
Neg logit contributions | |
azel | -0.185 |
Devil | -0.163 |
igg | -0.156 |
Leader | -0.154 |
ten | -0.151 |
Token | the |
Token ID | 262 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
arnaev | +0.524 |
rompt | +0.512 |
psey | +0.490 |
ysis | +0.481 |
� | +0.460 |
Neg logit contributions | |
azel | -0.473 |
Devil | -0.426 |
igg | -0.409 |
Leader | -0.403 |
ten | -0.397 |
Token | main |
Token ID | 1388 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
arnaev | +0.566 |
rompt | +0.553 |
psey | +0.528 |
ysis | +0.517 |
VIDIA | +0.494 |
Neg logit contributions | |
azel | -0.560 |
Devil | -0.506 |
igg | -0.487 |
Leader | -0.481 |
ten | -0.474 |
Token | ruling |
Token ID | 6922 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
arnaev | +0.563 |
rompt | +0.553 |
psey | +0.530 |
ysis | +0.520 |
VIDIA | +0.500 |
Neg logit contributions | |
azel | -0.432 |
Devil | -0.384 |
igg | -0.367 |
Leader | -0.362 |
ten | -0.356 |
Token | VM |
Token ID | 16990 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
arnaev | +0.940 |
rompt | +0.919 |
psey | +0.876 |
ysis | +0.850 |
VIDIA | +0.813 |
Neg logit contributions | |
azel | -1.022 |
Devil | -0.934 |
igg | -0.901 |
Leader | -0.890 |
ten | -0.878 |
Token | RO |
Token ID | 13252 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
arnaev | +2.275 |
rompt | +2.212 |
psey | +2.157 |
ysis | +2.112 |
VIDIA | +2.054 |
Neg logit contributions | |
azel | -1.080 |
Devil | -0.923 |
igg | -0.878 |
Leader | -0.853 |
erad | -0.822 |
Token | D |
Token ID | 360 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
arnaev | +1.020 |
rompt | +0.997 |
psey | +0.955 |
ysis | +0.929 |
VIDIA | +0.889 |
Neg logit contributions | |
azel | -1.021 |
Devil | -0.925 |
igg | -0.892 |
Leader | -0.882 |
ten | -0.869 |
Token | PM |
Token ID | 5868 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
arnaev | +0.879 |
rompt | +0.855 |
psey | +0.822 |
ysis | +0.802 |
VIDIA | +0.771 |
Neg logit contributions | |
azel | -0.779 |
Devil | -0.694 |
igg | -0.675 |
Leader | -0.661 |
ten | -0.655 |
Token | NE |
Token ID | 12161 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
arnaev | +0.876 |
rompt | +0.855 |
psey | +0.822 |
ysis | +0.802 |
VIDIA | +0.767 |
Neg logit contributions | |
azel | -0.805 |
Devil | -0.728 |
igg | -0.700 |
Leader | -0.692 |
ten | -0.678 |
Token | party |
Token ID | 2151 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
arnaev | +0.870 |
rompt | +0.850 |
psey | +0.813 |
ysis | +0.794 |
VIDIA | +0.758 |
Neg logit contributions | |
azel | -0.868 |
Devil | -0.785 |
igg | -0.756 |
Leader | -0.747 |
ten | -0.736 |
Token | in |
Token ID | 259 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
azel | +0.380 |
Devil | +0.328 |
igg | +0.312 |
Leader | +0.311 |
erad | +0.305 |
Neg logit contributions | |
arnaev | -0.639 |
rompt | -0.630 |
psey | -0.608 |
ysis | -0.595 |
� | -0.576 |
Token | ( |
Token ID | 357 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
azel | +0.259 |
Devil | +0.229 |
igg | +0.219 |
Leader | +0.217 |
erad | +0.212 |
Neg logit contributions | |
arnaev | -0.355 |
rompt | -0.349 |
psey | -0.334 |
ysis | -0.330 |
� | -0.317 |
Token | O |
Token ID | 46 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
arnaev | +0.564 |
rompt | +0.548 |
psey | +0.526 |
ysis | +0.513 |
VIDIA | +0.487 |
Neg logit contributions | |
azel | -0.630 |
Devil | -0.574 |
igg | -0.553 |
Leader | -0.550 |
ten | -0.541 |
Token | mega |
Token ID | 13731 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
arnaev | +0.693 |
rompt | +0.670 |
psey | +0.633 |
ysis | +0.615 |
� | +0.578 |
Neg logit contributions | |
azel | -1.075 |
Devil | -0.985 |
igg | -0.964 |
Leader | -0.949 |
ten | -0.944 |
Token | Pharma |
Token ID | 41845 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
arnaev | +1.018 |
rompt | +0.990 |
psey | +0.952 |
ysis | +0.929 |
� | +0.893 |
Neg logit contributions | |
azel | -0.914 |
Devil | -0.828 |
igg | -0.790 |
Leader | -0.779 |
ten | -0.767 |
Token | - |
Token ID | 532 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
arnaev | +0.858 |
rompt | +0.839 |
psey | +0.810 |
ysis | +0.793 |
� | +0.763 |
Neg logit contributions | |
azel | -0.641 |
Devil | -0.572 |
igg | -0.544 |
Leader | -0.535 |
ten | -0.528 |
Token | Quick |
Token ID | 12029 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
arnaev | +1.700 |
rompt | +1.649 |
psey | +1.609 |
ysis | +1.577 |
VIDIA | +1.506 |
Neg logit contributions | |
azel | -1.549 |
Devil | -1.425 |
igg | -1.342 |
Leader | -1.340 |
ten | -1.320 |
Token | step |
Token ID | 9662 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
azel | +0.310 |
Devil | +0.278 |
igg | +0.267 |
Leader | +0.264 |
erad | +0.261 |
Neg logit contributions | |
arnaev | -0.315 |
rompt | -0.310 |
psey | -0.291 |
ysis | -0.289 |
� | -0.277 |
Token | ) |
Token ID | 8 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
arnaev | +0.276 |
rompt | +0.270 |
psey | +0.258 |
ysis | +0.254 |
� | +0.243 |
Neg logit contributions | |
azel | -0.239 |
Devil | -0.213 |
igg | -0.205 |
Leader | -0.202 |
ten | -0.199 |
Token | s |
Token ID | 264 |
Feature activation | +9.06e-02 |
Pos logit contributions | |
arnaev | +0.118 |
rompt | +0.116 |
psey | +0.111 |
ysis | +0.109 |
� | +0.105 |
Neg logit contributions | |
azel | -0.089 |
Devil | -0.079 |
igg | -0.075 |
Leader | -0.074 |
ten | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
arnaev | +0.071 |
rompt | +0.070 |
psey | +0.067 |
ysis | +0.066 |
� | +0.063 |
Neg logit contributions | |
azel | -0.061 |
Devil | -0.055 |
igg | -0.052 |
Leader | -0.052 |
ten | -0.051 |
Token | 4 |
Token ID | 604 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
azel | +0.615 |
Devil | +0.542 |
igg | +0.528 |
Leader | +0.520 |
ten | +0.519 |
Neg logit contributions | |
arnaev | -0.682 |
rompt | -0.664 |
psey | -0.632 |
ysis | -0.627 |
� | -0.602 |
Token | ways |
Token ID | 2842 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
azel | +0.601 |
Devil | +0.530 |
igg | +0.510 |
Leader | +0.502 |
erad | +0.493 |
Neg logit contributions | |
arnaev | -0.677 |
rompt | -0.663 |
psey | -0.644 |
ysis | -0.630 |
� | -0.611 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
arnaev | +0.742 |
rompt | +0.726 |
psey | +0.694 |
ysis | +0.681 |
VIDIA | +0.654 |
Neg logit contributions | |
azel | -0.673 |
Devil | -0.609 |
igg | -0.584 |
Leader | -0.576 |
ten | -0.567 |
Token | looms |
Token ID | 46234 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
arnaev | +0.745 |
rompt | +0.729 |
psey | +0.695 |
ysis | +0.678 |
VIDIA | +0.649 |
Neg logit contributions | |
azel | -0.775 |
Devil | -0.704 |
igg | -0.679 |
Leader | -0.671 |
erad | -0.664 |
Token | over |
Token ID | 625 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
arnaev | +0.951 |
rompt | +0.933 |
psey | +0.890 |
ysis | +0.881 |
VIDIA | +0.839 |
Neg logit contributions | |
azel | -0.735 |
Devil | -0.663 |
igg | -0.632 |
Leader | -0.626 |
ten | -0.612 |
Token | the |
Token ID | 262 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
arnaev | +0.534 |
rompt | +0.522 |
psey | +0.499 |
ysis | +0.490 |
VIDIA | +0.469 |
Neg logit contributions | |
azel | -0.483 |
Devil | -0.434 |
igg | -0.416 |
Leader | -0.411 |
ten | -0.406 |
Token | 2020 |
Token ID | 12131 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
arnaev | +1.678 |
rompt | +1.655 |
psey | +1.585 |
ysis | +1.536 |
VIDIA | +1.491 |
Neg logit contributions | |
azel | -1.520 |
Devil | -1.391 |
igg | -1.291 |
Leader | -1.290 |
ten | -1.280 |
Token | race |
Token ID | 3234 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
arnaev | +0.234 |
rompt | +0.229 |
psey | +0.218 |
ysis | +0.213 |
� | +0.203 |
Neg logit contributions | |
azel | -0.253 |
Devil | -0.229 |
igg | -0.221 |
Leader | -0.218 |
ten | -0.215 |
Token | Obama |
Token ID | 2486 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
arnaev | +0.868 |
rompt | +0.849 |
psey | +0.820 |
ysis | +0.794 |
VIDIA | +0.764 |
Neg logit contributions | |
azel | -0.755 |
Devil | -0.687 |
igg | -0.652 |
Leader | -0.647 |
erad | -0.637 |
Token | goes |
Token ID | 2925 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
azel | +0.236 |
Devil | +0.213 |
igg | +0.206 |
Leader | +0.202 |
ten | +0.199 |
Neg logit contributions | |
arnaev | -0.215 |
rompt | -0.212 |
psey | -0.200 |
ysis | -0.199 |
� | -0.189 |
Token | viral |
Token ID | 14416 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
arnaev | +0.478 |
rompt | +0.468 |
psey | +0.448 |
ysis | +0.440 |
VIDIA | +0.421 |
Neg logit contributions | |
azel | -0.425 |
Devil | -0.381 |
igg | -0.366 |
Leader | -0.361 |
ten | -0.355 |
Token | to |
Token ID | 284 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
arnaev | +0.208 |
rompt | +0.204 |
psey | +0.195 |
ysis | +0.191 |
� | +0.183 |
Neg logit contributions | |
azel | -0.195 |
Devil | -0.175 |
igg | -0.168 |
Leader | -0.166 |
ten | -0.164 |
Token | the |
Token ID | 262 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
azel | +0.158 |
Devil | +0.139 |
igg | +0.133 |
Leader | +0.131 |
ten | +0.128 |
Neg logit contributions | |
arnaev | -0.217 |
rompt | -0.213 |
psey | -0.205 |
ysis | -0.202 |
� | -0.194 |
Token | n |
Token ID | 299 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
arnaev | +0.169 |
rompt | +0.166 |
psey | +0.159 |
ysis | +0.156 |
� | +0.150 |
Neg logit contributions | |
azel | -0.141 |
Devil | -0.125 |
igg | -0.120 |
Leader | -0.119 |
ten | -0.117 |
Token | itty |
Token ID | 9760 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
arnaev | +0.375 |
rompt | +0.367 |
psey | +0.352 |
ysis | +0.345 |
� | +0.331 |
Neg logit contributions | |
azel | -0.319 |
Devil | -0.285 |
igg | -0.274 |
Leader | -0.270 |
ten | -0.266 |
Token | - |
Token ID | 12 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
arnaev | +0.204 |
rompt | +0.200 |
psey | +0.191 |
ysis | +0.188 |
� | +0.180 |
Neg logit contributions | |
azel | -0.181 |
Devil | -0.162 |
igg | -0.156 |
Leader | -0.154 |
ten | -0.152 |
Token | gr |
Token ID | 2164 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
arnaev | +0.153 |
rompt | +0.150 |
psey | +0.143 |
ysis | +0.141 |
� | +0.135 |
Neg logit contributions | |
azel | -0.140 |
Devil | -0.126 |
igg | -0.121 |
Leader | -0.119 |
ten | -0.117 |
Token | itty |
Token ID | 9760 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
arnaev | +1.802 |
rompt | +1.765 |
psey | +1.691 |
ysis | +1.646 |
VIDIA | +1.614 |
Neg logit contributions | |
azel | -1.389 |
Devil | -1.231 |
igg | -1.214 |
ten | -1.160 |
Leader | -1.143 |
Token | of |
Token ID | 286 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
arnaev | +0.099 |
rompt | +0.097 |
psey | +0.093 |
ysis | +0.091 |
� | +0.088 |
Neg logit contributions | |
azel | -0.078 |
Devil | -0.070 |
igg | -0.067 |
Leader | -0.066 |
ten | -0.065 |
Token | applying |
Token ID | 11524 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
azel | +0.049 |
Devil | +0.044 |
igg | +0.042 |
Leader | +0.042 |
ten | +0.041 |
Neg logit contributions | |
arnaev | -0.055 |
rompt | -0.054 |
psey | -0.052 |
ysis | -0.051 |
� | -0.049 |
Token | for |
Token ID | 329 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
arnaev | +0.054 |
rompt | +0.053 |
psey | +0.050 |
ysis | +0.049 |
� | +0.047 |
Neg logit contributions | |
azel | -0.050 |
Devil | -0.045 |
igg | -0.043 |
Leader | -0.043 |
ten | -0.042 |
Token | business |
Token ID | 1597 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
azel | +0.366 |
Devil | +0.326 |
igg | +0.313 |
Leader | +0.311 |
ten | +0.304 |
Neg logit contributions | |
arnaev | -0.427 |
rompt | -0.418 |
psey | -0.401 |
ysis | -0.397 |
� | -0.379 |
Token | London |
Token ID | 3576 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
azel | +0.040 |
Devil | +0.036 |
igg | +0.034 |
Leader | +0.034 |
ten | +0.033 |
Neg logit contributions | |
arnaev | -0.051 |
rompt | -0.050 |
psey | -0.048 |
ysis | -0.047 |
� | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
azel | +0.019 |
Devil | +0.017 |
igg | +0.016 |
Leader | +0.016 |
ten | +0.016 |
Neg logit contributions | |
arnaev | -0.022 |
rompt | -0.022 |
psey | -0.021 |
ysis | -0.020 |
� | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
azel | +0.166 |
Devil | +0.148 |
igg | +0.143 |
Leader | +0.141 |
ten | +0.138 |
Neg logit contributions | |
arnaev | -0.195 |
rompt | -0.192 |
psey | -0.183 |
ysis | -0.180 |
� | -0.173 |
Token | German |
Token ID | 2679 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
azel | +0.308 |
Devil | +0.271 |
igg | +0.261 |
Leader | +0.257 |
ten | +0.252 |
Neg logit contributions | |
arnaev | -0.404 |
rompt | -0.396 |
psey | -0.380 |
ysis | -0.373 |
� | -0.359 |
Token | magazine |
Token ID | 7093 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
arnaev | +0.314 |
rompt | +0.308 |
psey | +0.296 |
ysis | +0.291 |
� | +0.280 |
Neg logit contributions | |
azel | -0.231 |
Devil | -0.204 |
igg | -0.195 |
Leader | -0.192 |
ten | -0.189 |
Token | Der |
Token ID | 9626 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
arnaev | +0.685 |
rompt | +0.667 |
psey | +0.640 |
ysis | +0.626 |
VIDIA | +0.599 |
Neg logit contributions | |
azel | -0.639 |
Devil | -0.578 |
igg | -0.553 |
Leader | -0.548 |
ten | -0.540 |
Token | Spiegel |
Token ID | 46902 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
arnaev | +1.047 |
rompt | +1.017 |
psey | +0.954 |
ysis | +0.906 |
VIDIA | +0.853 |
Neg logit contributions | |
azel | -2.125 |
Devil | -1.986 |
igg | -1.934 |
Leader | -1.925 |
ten | -1.901 |
Token | on |
Token ID | 319 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
arnaev | +0.560 |
rompt | +0.548 |
psey | +0.526 |
ysis | +0.517 |
VIDIA | +0.495 |
Neg logit contributions | |
azel | -0.468 |
Devil | -0.419 |
igg | -0.401 |
Leader | -0.396 |
ten | -0.390 |
Token | condition |
Token ID | 4006 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
azel | +0.161 |
Devil | +0.144 |
igg | +0.139 |
Leader | +0.138 |
ten | +0.135 |
Neg logit contributions | |
arnaev | -0.168 |
rompt | -0.164 |
psey | -0.157 |
ysis | -0.154 |
� | -0.147 |
Token | that |
Token ID | 326 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
azel | +0.473 |
Devil | +0.422 |
igg | +0.407 |
Leader | +0.404 |
ten | +0.394 |
Neg logit contributions | |
arnaev | -0.524 |
rompt | -0.513 |
psey | -0.490 |
ysis | -0.485 |
� | -0.464 |
Token | they |
Token ID | 484 |
Feature activation | -7.28e-03 |
Pos logit contributions | |
azel | +0.178 |
Devil | +0.159 |
igg | +0.153 |
Leader | +0.151 |
ten | +0.149 |
Neg logit contributions | |
arnaev | -0.192 |
rompt | -0.188 |
psey | -0.180 |
ysis | -0.177 |
� | -0.169 |
Token | Breaking |
Token ID | 24942 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
azel | +0.132 |
Devil | +0.118 |
igg | +0.114 |
Leader | +0.112 |
ten | +0.111 |
Neg logit contributions | |
arnaev | -0.148 |
rompt | -0.145 |
psey | -0.139 |
ysis | -0.137 |
� | -0.131 |
Token | Bad |
Token ID | 7772 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
arnaev | +0.068 |
rompt | +0.067 |
psey | +0.063 |
ysis | +0.062 |
� | +0.059 |
Neg logit contributions | |
azel | -0.086 |
Devil | -0.078 |
igg | -0.075 |
Leader | -0.075 |
ten | -0.074 |
Token | AMC |
Token ID | 36239 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
azel | +0.008 |
Devil | +0.007 |
igg | +0.007 |
Leader | +0.007 |
ten | +0.007 |
Neg logit contributions | |
arnaev | -0.009 |
rompt | -0.009 |
psey | -0.008 |
ysis | -0.008 |
� | -0.008 |
Token | Julian |
Token ID | 18322 |
Feature activation | -8.65e-02 |
Pos logit contributions | |
arnaev | +0.127 |
rompt | +0.124 |
psey | +0.119 |
ysis | +0.117 |
� | +0.112 |
Neg logit contributions | |
azel | -0.118 |
Devil | -0.106 |
igg | -0.102 |
Leader | -0.100 |
ten | -0.099 |
Token | na |
Token ID | 2616 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
azel | +0.057 |
Devil | +0.051 |
igg | +0.049 |
Leader | +0.049 |
ten | +0.048 |
Neg logit contributions | |
arnaev | -0.069 |
rompt | -0.068 |
psey | -0.065 |
ysis | -0.064 |
� | -0.061 |
Token | Marg |
Token ID | 11899 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
azel | +0.355 |
Devil | +0.308 |
igg | +0.297 |
Leader | +0.296 |
ten | +0.288 |
Neg logit contributions | |
arnaev | -0.508 |
rompt | -0.502 |
psey | -0.482 |
ysis | -0.475 |
� | -0.458 |
Token | ul |
Token ID | 377 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
arnaev | +2.179 |
rompt | +2.122 |
psey | +2.057 |
ysis | +2.036 |
VIDIA | +1.989 |
Neg logit contributions | |
azel | -0.968 |
Devil | -0.791 |
igg | -0.780 |
ten | -0.733 |
Leader | -0.717 |
Token | ies |
Token ID | 444 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
arnaev | +0.353 |
rompt | +0.342 |
psey | +0.319 |
ysis | +0.309 |
VIDIA | +0.289 |
Neg logit contributions | |
azel | -0.658 |
Devil | -0.608 |
igg | -0.593 |
Leader | -0.584 |
ten | -0.581 |
Token | The |
Token ID | 383 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
arnaev | +0.156 |
rompt | +0.153 |
psey | +0.147 |
ysis | +0.144 |
� | +0.138 |
Neg logit contributions | |
azel | -0.140 |
Devil | -0.125 |
igg | -0.120 |
Leader | -0.119 |
ten | -0.117 |
Token | Good |
Token ID | 4599 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
arnaev | +0.030 |
rompt | +0.030 |
psey | +0.028 |
ysis | +0.028 |
� | +0.027 |
Neg logit contributions | |
azel | -0.029 |
Devil | -0.026 |
igg | -0.025 |
Leader | -0.025 |
ten | -0.025 |
Token | Wife |
Token ID | 34188 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
azel | +0.277 |
Devil | +0.248 |
igg | +0.240 |
Leader | +0.238 |
erad | +0.234 |
Neg logit contributions | |
arnaev | -0.278 |
rompt | -0.272 |
psey | -0.259 |
ysis | -0.256 |
� | -0.244 |
Token | Germany |
Token ID | 27079 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
azel | +0.083 |
Devil | +0.075 |
igg | +0.072 |
Leader | +0.070 |
erad | +0.070 |
Neg logit contributions | |
arnaev | -0.091 |
rompt | -0.089 |
psey | -0.085 |
ysis | -0.084 |
� | -0.081 |
Token | 's |
Token ID | 338 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
arnaev | +0.032 |
rompt | +0.031 |
psey | +0.030 |
ysis | +0.029 |
� | +0.028 |
Neg logit contributions | |
azel | -0.029 |
Devil | -0.026 |
igg | -0.025 |
Leader | -0.025 |
ten | -0.025 |
Token | leading |
Token ID | 3756 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
arnaev | +0.434 |
rompt | +0.424 |
psey | +0.404 |
ysis | +0.397 |
VIDIA | +0.379 |
Neg logit contributions | |
azel | -0.419 |
Devil | -0.378 |
igg | -0.363 |
Leader | -0.359 |
ten | -0.354 |
Token | news |
Token ID | 1705 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
arnaev | +0.106 |
rompt | +0.104 |
psey | +0.099 |
ysis | +0.098 |
� | +0.093 |
Neg logit contributions | |
azel | -0.096 |
Devil | -0.086 |
igg | -0.083 |
Leader | -0.082 |
ten | -0.081 |
Token | magazine |
Token ID | 7093 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
azel | +0.151 |
Devil | +0.135 |
igg | +0.129 |
Leader | +0.127 |
ten | +0.125 |
Neg logit contributions | |
arnaev | -0.184 |
rompt | -0.181 |
psey | -0.173 |
ysis | -0.171 |
� | -0.164 |
Token | Der |
Token ID | 9626 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
arnaev | +0.347 |
rompt | +0.339 |
psey | +0.324 |
ysis | +0.318 |
� | +0.304 |
Neg logit contributions | |
azel | -0.328 |
Devil | -0.295 |
igg | -0.284 |
Leader | -0.280 |
ten | -0.276 |
Token | Spiegel |
Token ID | 46902 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
arnaev | +1.023 |
rompt | +0.989 |
psey | +0.929 |
ysis | +0.883 |
VIDIA | +0.827 |
Neg logit contributions | |
azel | -2.084 |
Devil | -1.952 |
igg | -1.899 |
Leader | -1.890 |
ten | -1.869 |
Token | said |
Token ID | 531 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
arnaev | +0.090 |
rompt | +0.088 |
psey | +0.084 |
ysis | +0.083 |
� | +0.079 |
Neg logit contributions | |
azel | -0.081 |
Devil | -0.072 |
igg | -0.070 |
Leader | -0.069 |
ten | -0.068 |
Token | in |
Token ID | 287 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
azel | +0.091 |
Devil | +0.082 |
igg | +0.079 |
Leader | +0.078 |
ten | +0.077 |
Neg logit contributions | |
arnaev | -0.097 |
rompt | -0.095 |
psey | -0.091 |
ysis | -0.089 |
� | -0.085 |
Token | a |
Token ID | 257 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
azel | +0.062 |
Devil | +0.055 |
igg | +0.053 |
Leader | +0.053 |
ten | +0.052 |
Neg logit contributions | |
arnaev | -0.070 |
rompt | -0.068 |
psey | -0.065 |
ysis | -0.064 |
� | -0.061 |
Token | strongly |
Token ID | 7634 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
azel | +0.410 |
Devil | +0.363 |
igg | +0.350 |
Leader | +0.345 |
ten | +0.338 |
Neg logit contributions | |
arnaev | -0.498 |
rompt | -0.489 |
psey | -0.468 |
ysis | -0.460 |
RTX | -0.442 |
Token | claim |
Token ID | 6604 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
azel | +0.820 |
Devil | +0.742 |
igg | +0.714 |
Leader | +0.711 |
erad | +0.697 |
Neg logit contributions | |
arnaev | -0.703 |
rompt | -0.695 |
psey | -0.656 |
ysis | -0.638 |
� | -0.610 |
Token | ing |
Token ID | 278 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
azel | +1.096 |
Devil | +0.988 |
igg | +0.944 |
Leader | +0.942 |
erad | +0.933 |
Neg logit contributions | |
arnaev | -0.925 |
rompt | -0.912 |
psey | -0.859 |
ysis | -0.848 |
� | -0.809 |
Token | the |
Token ID | 262 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
arnaev | +0.246 |
rompt | +0.240 |
psey | +0.230 |
ysis | +0.226 |
� | +0.216 |
Neg logit contributions | |
azel | -0.222 |
Devil | -0.199 |
igg | -0.192 |
Leader | -0.189 |
ten | -0.186 |
Token | American |
Token ID | 1605 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
arnaev | +0.688 |
rompt | +0.674 |
psey | +0.650 |
ysis | +0.639 |
VIDIA | +0.617 |
Neg logit contributions | |
azel | -0.421 |
Devil | -0.370 |
igg | -0.351 |
Leader | -0.345 |
ten | -0.339 |
Token | Right |
Token ID | 6498 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
arnaev | +0.255 |
rompt | +0.251 |
psey | +0.242 |
ysis | +0.239 |
� | +0.231 |
Neg logit contributions | |
azel | -0.122 |
Devil | -0.103 |
igg | -0.097 |
Leader | -0.095 |
ten | -0.093 |
Token | : |
Token ID | 25 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
azel | +0.015 |
Devil | +0.013 |
igg | +0.013 |
Leader | +0.013 |
erad | +0.012 |
Neg logit contributions | |
arnaev | -0.018 |
rompt | -0.018 |
psey | -0.017 |
ysis | -0.017 |
� | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
azel | +1.768 |
Devil | +1.545 |
igg | +1.517 |
Leader | +1.511 |
erad | +1.478 |
Neg logit contributions | |
arnaev | -2.029 |
rompt | -1.957 |
psey | -1.864 |
ysis | -1.857 |
RTX | -1.822 |
Token | Lost |
Token ID | 9164 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
azel | +0.573 |
Devil | +0.487 |
igg | +0.469 |
Leader | +0.457 |
ten | +0.453 |
Neg logit contributions | |
arnaev | -0.954 |
rompt | -0.933 |
psey | -0.912 |
ysis | -0.898 |
� | -0.864 |
Token | Legacy |
Token ID | 14843 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
arnaev | +0.605 |
rompt | +0.595 |
psey | +0.566 |
ysis | +0.554 |
VIDIA | +0.529 |
Neg logit contributions | |
azel | -0.607 |
Devil | -0.550 |
igg | -0.529 |
Leader | -0.522 |
ten | -0.514 |
Token | of |
Token ID | 286 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
azel | +0.602 |
Devil | +0.533 |
igg | +0.513 |
Leader | +0.503 |
ten | +0.496 |
Neg logit contributions | |
arnaev | -0.743 |
rompt | -0.719 |
psey | -0.695 |
ysis | -0.692 |
� | -0.665 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
azel | +1.205 |
Devil | +1.086 |
Leader | +1.042 |
igg | +1.037 |
ten | +1.018 |
Neg logit contributions | |
arnaev | -1.190 |
rompt | -1.144 |
psey | -1.116 |
ysis | -1.100 |
� | -1.057 |
Token | An |
Token ID | 1052 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
azel | +1.368 |
Devil | +1.229 |
igg | +1.194 |
Leader | +1.190 |
erad | +1.161 |
Neg logit contributions | |
arnaev | -1.155 |
rompt | -1.120 |
psey | -1.077 |
ysis | -1.054 |
� | -1.016 |
Token | Enemy |
Token ID | 21785 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
azel | +1.623 |
Devil | +1.473 |
igg | +1.426 |
Leader | +1.395 |
erad | +1.394 |
Neg logit contributions | |
arnaev | -1.462 |
rompt | -1.421 |
psey | -1.359 |
ysis | -1.317 |
RTX | -1.290 |
Token | of |
Token ID | 286 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
azel | +0.360 |
Devil | +0.319 |
igg | +0.308 |
Leader | +0.304 |
ten | +0.300 |
Neg logit contributions | |
arnaev | -0.467 |
rompt | -0.458 |
psey | -0.438 |
ysis | -0.431 |
� | -0.416 |
Token | the |
Token ID | 262 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
arnaev | +0.400 |
rompt | +0.391 |
psey | +0.374 |
ysis | +0.367 |
VIDIA | +0.351 |
Neg logit contributions | |
azel | -0.357 |
Devil | -0.321 |
igg | -0.308 |
Leader | -0.304 |
ten | -0.299 |
Token | State |
Token ID | 1812 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
arnaev | +0.352 |
rompt | +0.344 |
psey | +0.328 |
ysis | +0.322 |
VIDIA | +0.308 |
Neg logit contributions | |
azel | -0.329 |
Devil | -0.297 |
igg | -0.285 |
Leader | -0.281 |
ten | -0.277 |
Token | : |
Token ID | 25 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
azel | +0.101 |
Devil | +0.090 |
igg | +0.086 |
Leader | +0.085 |
ten | +0.083 |
Neg logit contributions | |
arnaev | -0.122 |
rompt | -0.119 |
psey | -0.114 |
ysis | -0.112 |
� | -0.108 |
Token | The |
Token ID | 383 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
azel | +1.646 |
Devil | +1.430 |
igg | +1.421 |
Leader | +1.406 |
erad | +1.375 |
Neg logit contributions | |
arnaev | -1.909 |
rompt | -1.854 |
psey | -1.763 |
RTX | -1.741 |
ysis | -1.716 |
Token | Life |
Token ID | 5155 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
azel | +0.870 |
Devil | +0.736 |
igg | +0.730 |
Leader | +0.703 |
erad | +0.696 |
Neg logit contributions | |
arnaev | -1.149 |
rompt | -1.114 |
psey | -1.097 |
ysis | -1.066 |
� | -1.032 |
Token | of |
Token ID | 286 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
arnaev | +0.162 |
rompt | +0.159 |
psey | +0.152 |
ysis | +0.150 |
� | +0.144 |
Neg logit contributions | |
azel | -0.120 |
Devil | -0.106 |
igg | -0.101 |
Leader | -0.100 |
ten | -0.098 |
Token | Murray |
Token ID | 12164 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
azel | +0.805 |
Devil | +0.727 |
igg | +0.705 |
Leader | +0.697 |
Perspective | +0.683 |
Neg logit contributions | |
arnaev | -0.697 |
rompt | -0.677 |
psey | -0.651 |
ysis | -0.643 |
� | -0.614 |
Token | N |
Token ID | 399 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
arnaev | +0.221 |
rompt | +0.216 |
psey | +0.206 |
ysis | +0.202 |
� | +0.193 |
Neg logit contributions | |
azel | -0.227 |
Devil | -0.205 |
igg | -0.197 |
Leader | -0.195 |
ten | -0.192 |
Token | Sh |
Token ID | 911 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
arnaev | +0.249 |
rompt | +0.243 |
psey | +0.232 |
ysis | +0.227 |
� | +0.216 |
Neg logit contributions | |
azel | -0.264 |
Devil | -0.239 |
igg | -0.231 |
Leader | -0.228 |
ten | -0.225 |
Token | and |
Token ID | 392 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
arnaev | +0.119 |
rompt | +0.116 |
psey | +0.111 |
ysis | +0.109 |
� | +0.104 |
Neg logit contributions | |
azel | -0.115 |
Devil | -0.103 |
igg | -0.099 |
Leader | -0.098 |
ten | -0.096 |
Token | ling |
Token ID | 1359 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
azel | +0.285 |
Devil | +0.258 |
igg | +0.247 |
Leader | +0.245 |
erad | +0.241 |
Neg logit contributions | |
arnaev | -0.287 |
rompt | -0.281 |
psey | -0.267 |
ysis | -0.263 |
� | -0.250 |
Token | 1996 |
Token ID | 8235 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
arnaev | +0.198 |
rompt | +0.194 |
psey | +0.185 |
ysis | +0.182 |
� | +0.175 |
Neg logit contributions | |
azel | -0.167 |
Devil | -0.149 |
igg | -0.143 |
Leader | -0.141 |
ten | -0.138 |
Token | John |
Token ID | 1757 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
arnaev | +0.110 |
rompt | +0.108 |
psey | +0.103 |
ysis | +0.102 |
� | +0.097 |
Neg logit contributions | |
azel | -0.093 |
Devil | -0.083 |
igg | -0.080 |
Leader | -0.079 |
ten | -0.077 |
Token | Lith |
Token ID | 19730 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
arnaev | +0.306 |
rompt | +0.299 |
psey | +0.285 |
ysis | +0.279 |
� | +0.266 |
Neg logit contributions | |
azel | -0.329 |
Devil | -0.298 |
igg | -0.288 |
Leader | -0.284 |
ten | -0.280 |
Token | gow |
Token ID | 21175 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
azel | +1.937 |
Devil | +1.796 |
Leader | +1.747 |
erad | +1.721 |
igg | +1.712 |
Neg logit contributions | |
arnaev | -1.486 |
rompt | -1.462 |
psey | -1.406 |
ysis | -1.368 |
� | -1.305 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
azel | +0.022 |
Devil | +0.020 |
igg | +0.019 |
Leader | +0.019 |
ten | +0.018 |
Neg logit contributions | |
arnaev | -0.022 |
rompt | -0.022 |
psey | -0.021 |
ysis | -0.021 |
� | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -3.82e-03 |
Pos logit contributions | |
azel | +0.091 |
Devil | +0.082 |
igg | +0.079 |
Leader | +0.078 |
erad | +0.077 |
Neg logit contributions | |
arnaev | -0.091 |
rompt | -0.089 |
psey | -0.085 |
ysis | -0.083 |
� | -0.080 |
Token | 1996 |
Token ID | 22288 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
azel | +0.002 |
Devil | +0.002 |
igg | +0.002 |
Leader | +0.002 |
erad | +0.002 |
Neg logit contributions | |
arnaev | -0.003 |
rompt | -0.003 |
psey | -0.003 |
ysis | -0.003 |
� | -0.003 |
Token | Kel |
Token ID | 15150 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
arnaev | +0.105 |
rompt | +0.103 |
psey | +0.098 |
ysis | +0.097 |
� | +0.093 |
Neg logit contributions | |
azel | -0.092 |
Devil | -0.082 |
igg | -0.079 |
Leader | -0.078 |
ten | -0.077 |
Token | ials |
Token ID | 8231 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
azel | +0.277 |
Devil | +0.249 |
igg | +0.239 |
Leader | +0.237 |
ten | +0.233 |
Neg logit contributions | |
arnaev | -0.298 |
rompt | -0.292 |
psey | -0.280 |
ysis | -0.273 |
� | -0.263 |
Token | are |
Token ID | 389 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
azel | +1.116 |
Devil | +1.001 |
igg | +0.971 |
Leader | +0.961 |
ten | +0.939 |
Neg logit contributions | |
arnaev | -1.065 |
rompt | -1.051 |
psey | -1.012 |
ysis | -0.983 |
� | -0.948 |
Token | accompanied |
Token ID | 11791 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
azel | +0.250 |
Devil | +0.210 |
igg | +0.202 |
Leader | +0.195 |
ten | +0.192 |
Neg logit contributions | |
arnaev | -0.482 |
rompt | -0.476 |
psey | -0.459 |
ysis | -0.451 |
� | -0.438 |
Token | by |
Token ID | 416 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
azel | +0.104 |
Devil | +0.093 |
igg | +0.090 |
Leader | +0.089 |
ten | +0.088 |
Neg logit contributions | |
arnaev | -0.101 |
rompt | -0.098 |
psey | -0.094 |
ysis | -0.092 |
� | -0.088 |
Token | an |
Token ID | 281 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
azel | +1.651 |
Devil | +1.480 |
igg | +1.420 |
Leader | +1.406 |
erad | +1.389 |
Neg logit contributions | |
rompt | -1.593 |
arnaev | -1.556 |
psey | -1.503 |
ysis | -1.420 |
� | -1.410 |
Token | opposing |
Token ID | 12330 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
azel | +0.272 |
Devil | +0.240 |
igg | +0.229 |
Leader | +0.227 |
ten | +0.222 |
Neg logit contributions | |
arnaev | -0.391 |
rompt | -0.388 |
psey | -0.370 |
ysis | -0.363 |
� | -0.353 |
Token | view |
Token ID | 1570 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
azel | +1.749 |
Devil | +1.559 |
igg | +1.492 |
Leader | +1.468 |
ten | +1.461 |
Neg logit contributions | |
rompt | -1.697 |
arnaev | -1.680 |
psey | -1.624 |
ysis | -1.559 |
� | -1.526 |
Token | — |
Token ID | 851 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
arnaev | +0.233 |
rompt | +0.228 |
psey | +0.218 |
ysis | +0.214 |
� | +0.205 |
Neg logit contributions | |
azel | -0.199 |
Devil | -0.178 |
igg | -0.171 |
Leader | -0.168 |
ten | -0.166 |
Token | a |
Token ID | 257 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
azel | +0.245 |
Devil | +0.218 |
igg | +0.210 |
Leader | +0.207 |
ten | +0.204 |
Neg logit contributions | |
arnaev | -0.272 |
rompt | -0.268 |
psey | -0.257 |
ysis | -0.252 |
� | -0.242 |
Token | unique |
Token ID | 3748 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
azel | +0.712 |
Devil | +0.634 |
igg | +0.613 |
Leader | +0.603 |
erad | +0.596 |
Neg logit contributions | |
arnaev | -0.723 |
rompt | -0.714 |
psey | -0.682 |
ysis | -0.664 |
� | -0.641 |
Token | USA |
Token ID | 4916 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
azel | +0.925 |
Devil | +0.809 |
igg | +0.783 |
Leader | +0.773 |
erad | +0.755 |
Neg logit contributions | |
arnaev | -1.161 |
rompt | -1.146 |
psey | -1.105 |
ysis | -1.071 |
� | -1.052 |
Token |
|
Token ID | 198 |
Feature activation | +6.67e-03 |
Pos logit contributions | |
arnaev | +0.015 |
rompt | +0.014 |
psey | +0.014 |
ysis | +0.013 |
� | +0.013 |
Neg logit contributions | |
azel | -0.013 |
Devil | -0.012 |
igg | -0.011 |
Leader | -0.011 |
ten | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
arnaev | +0.005 |
rompt | +0.005 |
psey | +0.005 |
ysis | +0.004 |
� | +0.004 |
Neg logit contributions | |
azel | -0.005 |
Devil | -0.004 |
igg | -0.004 |
Leader | -0.004 |
ten | -0.004 |
Token | D |
Token ID | 35 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
arnaev | +0.117 |
rompt | +0.114 |
psey | +0.109 |
ysis | +0.107 |
� | +0.102 |
Neg logit contributions | |
azel | -0.119 |
Devil | -0.107 |
igg | -0.103 |
Leader | -0.102 |
ten | -0.100 |
Token | ahl |
Token ID | 15668 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
arnaev | +0.225 |
rompt | +0.221 |
psey | +0.211 |
ysis | +0.208 |
� | +0.199 |
Neg logit contributions | |
azel | -0.195 |
Devil | -0.175 |
igg | -0.168 |
Leader | -0.166 |
ten | -0.163 |
Token | ia |
Token ID | 544 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
azel | +0.395 |
Devil | +0.348 |
igg | +0.330 |
Leader | +0.326 |
erad | +0.319 |
Neg logit contributions | |
arnaev | -0.595 |
rompt | -0.584 |
psey | -0.561 |
ysis | -0.553 |
� | -0.534 |
Token | Lith |
Token ID | 19730 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
azel | +0.362 |
Devil | +0.326 |
igg | +0.316 |
Leader | +0.313 |
ten | +0.308 |
Neg logit contributions | |
arnaev | -0.358 |
rompt | -0.351 |
psey | -0.334 |
ysis | -0.328 |
� | -0.315 |
Token | wick |
Token ID | 16239 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
azel | +1.032 |
Devil | +0.919 |
igg | +0.847 |
Leader | +0.846 |
erad | +0.828 |
Neg logit contributions | |
arnaev | -2.321 |
rompt | -2.285 |
psey | -2.217 |
ysis | -2.170 |
� | -2.138 |
Token | has |
Token ID | 468 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
azel | +0.163 |
Devil | +0.146 |
igg | +0.141 |
Leader | +0.139 |
ten | +0.136 |
Neg logit contributions | |
arnaev | -0.179 |
rompt | -0.175 |
psey | -0.168 |
ysis | -0.165 |
� | -0.159 |
Token | a |
Token ID | 257 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
arnaev | +0.454 |
rompt | +0.445 |
psey | +0.424 |
ysis | +0.417 |
VIDIA | +0.398 |
Neg logit contributions | |
azel | -0.428 |
Devil | -0.385 |
igg | -0.370 |
Leader | -0.366 |
ten | -0.360 |
Token | rundown |
Token ID | 45602 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
arnaev | +0.801 |
rompt | +0.789 |
psey | +0.751 |
ysis | +0.740 |
VIDIA | +0.712 |
Neg logit contributions | |
azel | -0.654 |
Devil | -0.585 |
igg | -0.563 |
Leader | -0.551 |
ten | -0.548 |
Token | of |
Token ID | 286 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
arnaev | +0.026 |
rompt | +0.026 |
psey | +0.025 |
ysis | +0.024 |
� | +0.023 |
Neg logit contributions | |
azel | -0.020 |
Devil | -0.017 |
igg | -0.017 |
Leader | -0.016 |
ten | -0.016 |
Token | Most |
Token ID | 4042 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
azel | +0.207 |
Devil | +0.184 |
igg | +0.177 |
Leader | +0.175 |
ten | +0.171 |
Neg logit contributions | |
arnaev | -0.243 |
rompt | -0.238 |
psey | -0.227 |
ysis | -0.223 |
� | -0.216 |
Token | editor |
Token ID | 5464 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
azel | +0.465 |
Devil | +0.415 |
igg | +0.395 |
Leader | +0.390 |
erad | +0.383 |
Neg logit contributions | |
arnaev | -0.568 |
rompt | -0.555 |
psey | -0.535 |
ysis | -0.524 |
� | -0.508 |
Token | ials |
Token ID | 8231 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
azel | +0.277 |
Devil | +0.249 |
igg | +0.239 |
Leader | +0.237 |
ten | +0.233 |
Neg logit contributions | |
arnaev | -0.298 |
rompt | -0.292 |
psey | -0.280 |
ysis | -0.273 |
� | -0.263 |
Token | are |
Token ID | 389 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
azel | +1.116 |
Devil | +1.001 |
igg | +0.971 |
Leader | +0.961 |
ten | +0.939 |
Neg logit contributions | |
arnaev | -1.065 |
rompt | -1.051 |
psey | -1.012 |
ysis | -0.983 |
� | -0.948 |
Token | accompanied |
Token ID | 11791 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
azel | +0.250 |
Devil | +0.210 |
igg | +0.202 |
Leader | +0.195 |
ten | +0.192 |
Neg logit contributions | |
arnaev | -0.482 |
rompt | -0.476 |
psey | -0.459 |
ysis | -0.451 |
� | -0.438 |
Token | by |
Token ID | 416 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
azel | +0.104 |
Devil | +0.093 |
igg | +0.090 |
Leader | +0.089 |
ten | +0.088 |
Neg logit contributions | |
arnaev | -0.101 |
rompt | -0.098 |
psey | -0.094 |
ysis | -0.092 |
� | -0.088 |
Token | an |
Token ID | 281 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
azel | +1.651 |
Devil | +1.480 |
igg | +1.420 |
Leader | +1.406 |
erad | +1.389 |
Neg logit contributions | |
rompt | -1.593 |
arnaev | -1.556 |
psey | -1.503 |
ysis | -1.420 |
� | -1.410 |
Token | opposing |
Token ID | 12330 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
azel | +0.272 |
Devil | +0.240 |
igg | +0.229 |
Leader | +0.227 |
ten | +0.222 |
Neg logit contributions | |
arnaev | -0.391 |
rompt | -0.388 |
psey | -0.370 |
ysis | -0.363 |
� | -0.353 |
Token | view |
Token ID | 1570 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
azel | +1.749 |
Devil | +1.559 |
igg | +1.492 |
Leader | +1.468 |
ten | +1.461 |
Neg logit contributions | |
rompt | -1.697 |
arnaev | -1.680 |
psey | -1.624 |
ysis | -1.559 |
� | -1.526 |
Token | — |
Token ID | 851 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
arnaev | +0.233 |
rompt | +0.228 |
psey | +0.218 |
ysis | +0.214 |
� | +0.205 |
Neg logit contributions | |
azel | -0.199 |
Devil | -0.178 |
igg | -0.171 |
Leader | -0.168 |
ten | -0.166 |
Token | a |
Token ID | 257 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
azel | +0.245 |
Devil | +0.218 |
igg | +0.210 |
Leader | +0.207 |
ten | +0.204 |
Neg logit contributions | |
arnaev | -0.272 |
rompt | -0.268 |
psey | -0.257 |
ysis | -0.252 |
� | -0.242 |
Token | : |
Token ID | 25 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
azel | +0.015 |
Devil | +0.013 |
igg | +0.013 |
Leader | +0.013 |
erad | +0.012 |
Neg logit contributions | |
arnaev | -0.018 |
rompt | -0.018 |
psey | -0.017 |
ysis | -0.017 |
� | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
azel | +1.768 |
Devil | +1.545 |
igg | +1.517 |
Leader | +1.511 |
erad | +1.478 |
Neg logit contributions | |
arnaev | -2.029 |
rompt | -1.957 |
psey | -1.864 |
ysis | -1.857 |
RTX | -1.822 |
Token | Lost |
Token ID | 9164 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
azel | +0.573 |
Devil | +0.487 |
igg | +0.469 |
Leader | +0.457 |
ten | +0.453 |
Neg logit contributions | |
arnaev | -0.954 |
rompt | -0.933 |
psey | -0.912 |
ysis | -0.898 |
� | -0.864 |
Token | Legacy |
Token ID | 14843 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
arnaev | +0.605 |
rompt | +0.595 |
psey | +0.566 |
ysis | +0.554 |
VIDIA | +0.529 |
Neg logit contributions | |
azel | -0.607 |
Devil | -0.550 |
igg | -0.529 |
Leader | -0.522 |
ten | -0.514 |
Token | of |
Token ID | 286 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
azel | +0.602 |
Devil | +0.533 |
igg | +0.513 |
Leader | +0.503 |
ten | +0.496 |
Neg logit contributions | |
arnaev | -0.743 |
rompt | -0.719 |
psey | -0.695 |
ysis | -0.692 |
� | -0.665 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
azel | +1.205 |
Devil | +1.086 |
Leader | +1.042 |
igg | +1.037 |
ten | +1.018 |
Neg logit contributions | |
arnaev | -1.190 |
rompt | -1.144 |
psey | -1.116 |
ysis | -1.100 |
� | -1.057 |
Token | Conservative |
Token ID | 11132 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
azel | +1.435 |
Devil | +1.234 |
igg | +1.181 |
Leader | +1.181 |
ten | +1.163 |
Neg logit contributions | |
arnaev | -1.682 |
rompt | -1.627 |
psey | -1.585 |
ysis | -1.557 |
� | -1.514 |
Token | Movement |
Token ID | 15477 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
azel | +1.097 |
Devil | +0.983 |
igg | +0.967 |
Leader | +0.947 |
ten | +0.946 |
Neg logit contributions | |
arnaev | -0.799 |
rompt | -0.767 |
psey | -0.732 |
ysis | -0.715 |
� | -0.688 |
Token | , |
Token ID | 11 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
azel | +0.661 |
Devil | +0.593 |
igg | +0.573 |
Leader | +0.560 |
erad | +0.554 |
Neg logit contributions | |
arnaev | -0.735 |
rompt | -0.716 |
psey | -0.688 |
ysis | -0.680 |
� | -0.662 |
Token | with |
Token ID | 351 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
arnaev | +0.323 |
rompt | +0.316 |
psey | +0.302 |
ysis | +0.296 |
� | +0.283 |
Neg logit contributions | |
azel | -0.308 |
Devil | -0.277 |
igg | -0.267 |
Leader | -0.263 |
ten | -0.259 |
Token | an |
Token ID | 281 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
arnaev | +0.184 |
rompt | +0.180 |
psey | +0.173 |
ysis | +0.170 |
� | +0.162 |
Neg logit contributions | |
azel | -0.164 |
Devil | -0.147 |
igg | -0.141 |
Leader | -0.139 |
ten | -0.137 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
arnaev | +0.528 |
rompt | +0.517 |
psey | +0.494 |
ysis | +0.485 |
VIDIA | +0.465 |
Neg logit contributions | |
azel | -0.495 |
Devil | -0.445 |
igg | -0.428 |
Leader | -0.423 |
ten | -0.415 |
Token |
|
Token ID | 198 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
arnaev | +0.134 |
rompt | +0.131 |
psey | +0.125 |
ysis | +0.122 |
� | +0.117 |
Neg logit contributions | |
azel | -0.131 |
Devil | -0.118 |
igg | -0.113 |
Leader | -0.112 |
ten | -0.110 |
Token | You |
Token ID | 1639 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
arnaev | +0.058 |
rompt | +0.057 |
psey | +0.054 |
ysis | +0.053 |
� | +0.051 |
Neg logit contributions | |
azel | -0.052 |
Devil | -0.046 |
igg | -0.044 |
Leader | -0.044 |
ten | -0.043 |
Token | can |
Token ID | 460 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
arnaev | +1.536 |
rompt | +1.510 |
psey | +1.407 |
ysis | +1.393 |
VIDIA | +1.335 |
Neg logit contributions | |
azel | -1.537 |
Devil | -1.373 |
igg | -1.326 |
Leader | -1.314 |
ten | -1.297 |
Token | buy |
Token ID | 2822 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
arnaev | +1.321 |
rompt | +1.301 |
psey | +1.246 |
ysis | +1.233 |
VIDIA | +1.195 |
Neg logit contributions | |
azel | -0.702 |
Devil | -0.606 |
igg | -0.574 |
Leader | -0.554 |
ten | -0.549 |
Token | An |
Token ID | 1052 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
azel | +1.368 |
Devil | +1.229 |
igg | +1.194 |
Leader | +1.190 |
erad | +1.161 |
Neg logit contributions | |
arnaev | -1.155 |
rompt | -1.120 |
psey | -1.077 |
ysis | -1.054 |
� | -1.016 |
Token | Enemy |
Token ID | 21785 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
azel | +1.623 |
Devil | +1.473 |
igg | +1.426 |
Leader | +1.395 |
erad | +1.394 |
Neg logit contributions | |
arnaev | -1.462 |
rompt | -1.421 |
psey | -1.359 |
ysis | -1.317 |
RTX | -1.290 |
Token | of |
Token ID | 286 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
azel | +0.360 |
Devil | +0.319 |
igg | +0.308 |
Leader | +0.304 |
ten | +0.300 |
Neg logit contributions | |
arnaev | -0.467 |
rompt | -0.458 |
psey | -0.438 |
ysis | -0.431 |
� | -0.416 |
Token | the |
Token ID | 262 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
arnaev | +0.400 |
rompt | +0.391 |
psey | +0.374 |
ysis | +0.367 |
VIDIA | +0.351 |
Neg logit contributions | |
azel | -0.357 |
Devil | -0.321 |
igg | -0.308 |
Leader | -0.304 |
ten | -0.299 |
Token | State |
Token ID | 1812 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
arnaev | +0.352 |
rompt | +0.344 |
psey | +0.328 |
ysis | +0.322 |
VIDIA | +0.308 |
Neg logit contributions | |
azel | -0.329 |
Devil | -0.297 |
igg | -0.285 |
Leader | -0.281 |
ten | -0.277 |
Token | : |
Token ID | 25 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
azel | +0.101 |
Devil | +0.090 |
igg | +0.086 |
Leader | +0.085 |
ten | +0.083 |
Neg logit contributions | |
arnaev | -0.122 |
rompt | -0.119 |
psey | -0.114 |
ysis | -0.112 |
� | -0.108 |
Token | most |
Token ID | 749 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
azel | +0.075 |
Devil | +0.067 |
igg | +0.065 |
Leader | +0.064 |
ten | +0.063 |
Neg logit contributions | |
arnaev | -0.083 |
rompt | -0.081 |
psey | -0.078 |
ysis | -0.076 |
� | -0.073 |
Token | have |
Token ID | 423 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
azel | +0.333 |
Devil | +0.298 |
igg | +0.289 |
Leader | +0.286 |
ten | +0.281 |
Neg logit contributions | |
arnaev | -0.337 |
rompt | -0.330 |
psey | -0.316 |
ysis | -0.310 |
� | -0.297 |
Token | deemed |
Token ID | 10762 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
azel | +0.362 |
Devil | +0.326 |
igg | +0.314 |
Leader | +0.313 |
ten | +0.305 |
Neg logit contributions | |
arnaev | -0.364 |
rompt | -0.357 |
psey | -0.341 |
ysis | -0.335 |
� | -0.321 |
Token | UN |
Token ID | 4725 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
azel | +0.120 |
Devil | +0.107 |
igg | +0.103 |
Leader | +0.102 |
ten | +0.100 |
Neg logit contributions | |
arnaev | -0.129 |
rompt | -0.127 |
psey | -0.121 |
ysis | -0.119 |
� | -0.114 |
Token | FOR |
Token ID | 13775 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
azel | +0.342 |
Devil | +0.307 |
igg | +0.296 |
Leader | +0.293 |
erad | +0.287 |
Neg logit contributions | |
arnaev | -0.355 |
rompt | -0.348 |
psey | -0.332 |
ysis | -0.325 |
� | -0.314 |
Token | G |
Token ID | 38 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
azel | +0.506 |
Devil | +0.432 |
igg | +0.413 |
Leader | +0.402 |
erad | +0.392 |
Neg logit contributions | |
arnaev | -0.903 |
rompt | -0.884 |
psey | -0.854 |
ysis | -0.843 |
� | -0.824 |
Token | IV |
Token ID | 3824 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
azel | +1.133 |
Devil | +0.952 |
igg | +0.897 |
Leader | +0.889 |
erad | +0.876 |
Neg logit contributions | |
arnaev | -1.989 |
rompt | -1.950 |
psey | -1.875 |
ysis | -1.837 |
� | -1.816 |
Token | ABLE |
Token ID | 17534 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
azel | +0.426 |
Devil | +0.386 |
igg | +0.375 |
Leader | +0.370 |
ten | +0.365 |
Neg logit contributions | |
arnaev | -0.322 |
rompt | -0.314 |
psey | -0.296 |
ysis | -0.291 |
� | -0.279 |
Token | ( |
Token ID | 357 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
arnaev | +0.089 |
rompt | +0.087 |
psey | +0.083 |
ysis | +0.082 |
� | +0.079 |
Neg logit contributions | |
azel | -0.079 |
Devil | -0.071 |
igg | -0.068 |
Leader | -0.067 |
ten | -0.066 |
Token | though |
Token ID | 2016 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
arnaev | +0.021 |
rompt | +0.020 |
psey | +0.019 |
ysis | +0.019 |
� | +0.018 |
Neg logit contributions | |
azel | -0.019 |
Devil | -0.017 |
igg | -0.017 |
Leader | -0.016 |
ten | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
azel | +0.197 |
Devil | +0.175 |
igg | +0.169 |
Leader | +0.167 |
ten | +0.164 |
Neg logit contributions | |
arnaev | -0.224 |
rompt | -0.219 |
psey | -0.210 |
ysis | -0.206 |
� | -0.198 |
Token | a |
Token ID | 257 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
azel | +0.114 |
Devil | +0.102 |
igg | +0.098 |
Leader | +0.097 |
ten | +0.096 |
Neg logit contributions | |
arnaev | -0.120 |
rompt | -0.118 |
psey | -0.112 |
ysis | -0.110 |
� | -0.106 |
Token | dem |
Token ID | 1357 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
arnaev | +0.028 |
rompt | +0.028 |
psey | +0.027 |
ysis | +0.026 |
� | +0.025 |
Neg logit contributions | |
azel | -0.027 |
Devil | -0.024 |
igg | -0.023 |
Leader | -0.023 |
ten | -0.023 |
Token | ographically |
Token ID | 33145 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
arnaev | +0.238 |
rompt | +0.226 |
psey | +0.203 |
ysis | +0.195 |
VIDIA | +0.176 |
Neg logit contributions | |
azel | -0.752 |
Devil | -0.704 |
igg | -0.687 |
Leader | -0.682 |
ten | -0.675 |
Token | and |
Token ID | 290 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
arnaev | +0.624 |
rompt | +0.610 |
psey | +0.582 |
ysis | +0.571 |
VIDIA | +0.546 |
Neg logit contributions | |
azel | -0.616 |
Devil | -0.554 |
igg | -0.535 |
Leader | -0.528 |
ten | -0.521 |
Token | ideologically |
Token ID | 49764 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
azel | +0.245 |
Devil | +0.222 |
igg | +0.214 |
Leader | +0.212 |
ten | +0.208 |
Neg logit contributions | |
arnaev | -0.218 |
rompt | -0.213 |
psey | -0.203 |
ysis | -0.198 |
� | -0.190 |
Token | diverse |
Token ID | 10084 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
arnaev | +0.734 |
rompt | +0.718 |
psey | +0.684 |
ysis | +0.672 |
VIDIA | +0.640 |
Neg logit contributions | |
azel | -0.773 |
Devil | -0.699 |
igg | -0.674 |
Leader | -0.667 |
ten | -0.658 |
Token | group |
Token ID | 1448 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
azel | +1.732 |
Devil | +1.558 |
igg | +1.481 |
Leader | +1.475 |
erad | +1.461 |
Neg logit contributions | |
arnaev | -1.321 |
rompt | -1.299 |
psey | -1.244 |
ysis | -1.187 |
� | -1.173 |
Token | that |
Token ID | 326 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
azel | +0.585 |
Devil | +0.513 |
igg | +0.494 |
Leader | +0.486 |
erad | +0.474 |
Neg logit contributions | |
arnaev | -0.730 |
rompt | -0.714 |
psey | -0.685 |
ysis | -0.672 |
� | -0.651 |
Token | is |
Token ID | 318 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
azel | +0.089 |
Devil | +0.079 |
igg | +0.076 |
Leader | +0.075 |
ten | +0.074 |
Neg logit contributions | |
arnaev | -0.100 |
rompt | -0.098 |
psey | -0.094 |
ysis | -0.092 |
� | -0.089 |
Token | separate |
Token ID | 4553 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
arnaev | +0.103 |
rompt | +0.101 |
psey | +0.097 |
ysis | +0.095 |
� | +0.091 |
Neg logit contributions | |
azel | -0.093 |
Devil | -0.084 |
igg | -0.080 |
Leader | -0.079 |
ten | -0.078 |
Token | from |
Token ID | 422 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
azel | +0.702 |
Devil | +0.627 |
igg | +0.604 |
Leader | +0.598 |
erad | +0.584 |
Neg logit contributions | |
arnaev | -0.782 |
rompt | -0.764 |
psey | -0.730 |
ysis | -0.720 |
� | -0.693 |
Token | bit |
Token ID | 2545 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
azel | +0.154 |
Devil | +0.137 |
igg | +0.131 |
Leader | +0.129 |
erad | +0.127 |
Neg logit contributions | |
arnaev | -0.204 |
rompt | -0.200 |
psey | -0.192 |
ysis | -0.189 |
� | -0.182 |
Token | 256 |
Token ID | 17759 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
azel | +0.336 |
Devil | +0.297 |
igg | +0.287 |
Leader | +0.284 |
erad | +0.278 |
Neg logit contributions | |
arnaev | -0.404 |
rompt | -0.398 |
psey | -0.380 |
ysis | -0.375 |
RTX | -0.361 |
Token | - |
Token ID | 12 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
azel | +0.074 |
Devil | +0.066 |
igg | +0.063 |
Leader | +0.062 |
ten | +0.061 |
Neg logit contributions | |
arnaev | -0.089 |
rompt | -0.088 |
psey | -0.084 |
ysis | -0.083 |
� | -0.079 |
Token | bit |
Token ID | 2545 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
azel | +0.129 |
Devil | +0.114 |
igg | +0.109 |
Leader | +0.108 |
erad | +0.105 |
Neg logit contributions | |
arnaev | -0.171 |
rompt | -0.167 |
psey | -0.160 |
ysis | -0.158 |
� | -0.152 |
Token | R |
Token ID | 371 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
azel | +0.364 |
Devil | +0.322 |
igg | +0.311 |
Leader | +0.308 |
erad | +0.302 |
Neg logit contributions | |
arnaev | -0.435 |
rompt | -0.428 |
psey | -0.409 |
ysis | -0.404 |
RTX | -0.389 |
Token | OP |
Token ID | 3185 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
azel | +0.564 |
Devil | +0.493 |
Leader | +0.468 |
igg | +0.467 |
erad | +0.458 |
Neg logit contributions | |
arnaev | -0.744 |
rompt | -0.736 |
psey | -0.707 |
ysis | -0.694 |
� | -0.676 |
Token | s |
Token ID | 82 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
azel | +1.278 |
Devil | +1.108 |
Leader | +1.073 |
igg | +1.072 |
erad | +1.047 |
Neg logit contributions | |
rompt | -1.751 |
arnaev | -1.748 |
psey | -1.662 |
ysis | -1.636 |
� | -1.595 |
Token | 32 |
Token ID | 3933 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
azel | +0.351 |
Devil | +0.312 |
igg | +0.301 |
Leader | +0.299 |
ten | +0.293 |
Neg logit contributions | |
arnaev | -0.394 |
rompt | -0.387 |
psey | -0.369 |
ysis | -0.365 |
� | -0.349 |
Token | 32 |
Token ID | 3933 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
azel | +0.242 |
Devil | +0.217 |
igg | +0.209 |
Leader | +0.207 |
ten | +0.204 |
Neg logit contributions | |
arnaev | -0.257 |
rompt | -0.252 |
psey | -0.241 |
ysis | -0.238 |
� | -0.227 |
Token | 56 |
Token ID | 7265 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
azel | +0.246 |
Devil | +0.220 |
igg | +0.212 |
Leader | +0.210 |
ten | +0.206 |
Neg logit contributions | |
arnaev | -0.269 |
rompt | -0.264 |
psey | -0.252 |
ysis | -0.249 |
� | -0.238 |
Token | 48 |
Token ID | 4764 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
azel | +0.096 |
Devil | +0.086 |
igg | +0.083 |
Leader | +0.082 |
ten | +0.081 |
Neg logit contributions | |
arnaev | -0.099 |
rompt | -0.097 |
psey | -0.092 |
ysis | -0.091 |
� | -0.087 |
Token | by |
Token ID | 416 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
arnaev | +0.142 |
rompt | +0.139 |
psey | +0.133 |
ysis | +0.130 |
� | +0.124 |
Neg logit contributions | |
azel | -0.144 |
Devil | -0.130 |
igg | -0.126 |
Leader | -0.124 |
ten | -0.122 |
Token | email |
Token ID | 3053 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
azel | +0.330 |
Devil | +0.296 |
Leader | +0.284 |
igg | +0.284 |
ten | +0.275 |
Neg logit contributions | |
arnaev | -0.353 |
rompt | -0.348 |
psey | -0.333 |
ysis | -0.325 |
� | -0.314 |
Token | and |
Token ID | 290 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
azel | +0.395 |
Devil | +0.353 |
igg | +0.340 |
Leader | +0.339 |
ten | +0.328 |
Neg logit contributions | |
arnaev | -0.440 |
rompt | -0.431 |
psey | -0.416 |
ysis | -0.407 |
� | -0.392 |
Token | never |
Token ID | 1239 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
arnaev | +0.256 |
rompt | +0.250 |
psey | +0.237 |
ysis | +0.232 |
� | +0.220 |
Neg logit contributions | |
azel | -0.315 |
Devil | -0.287 |
igg | -0.278 |
Leader | -0.275 |
ten | -0.271 |
Token | miss |
Token ID | 2051 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
azel | +0.574 |
Devil | +0.506 |
igg | +0.483 |
Leader | +0.478 |
erad | +0.462 |
Neg logit contributions | |
rompt | -0.832 |
arnaev | -0.828 |
psey | -0.787 |
ysis | -0.779 |
� | -0.753 |
Token | our |
Token ID | 674 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
azel | +0.986 |
Devil | +0.888 |
igg | +0.868 |
Leader | +0.848 |
erad | +0.842 |
Neg logit contributions | |
arnaev | -0.924 |
rompt | -0.901 |
psey | -0.859 |
ysis | -0.834 |
� | -0.808 |
Token | top |
Token ID | 1353 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
azel | +1.238 |
Devil | +1.084 |
igg | +1.042 |
Leader | +1.021 |
erad | +0.989 |
Neg logit contributions | |
arnaev | -1.782 |
rompt | -1.750 |
psey | -1.691 |
ysis | -1.679 |
� | -1.614 |
Token | stories |
Token ID | 3923 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
azel | +0.552 |
Devil | +0.483 |
igg | +0.464 |
Leader | +0.461 |
erad | +0.445 |
Neg logit contributions | |
arnaev | -0.722 |
rompt | -0.710 |
psey | -0.688 |
ysis | -0.669 |
RTX | -0.651 |
Token | Free |
Token ID | 3232 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
azel | +0.712 |
Devil | +0.644 |
igg | +0.626 |
Leader | +0.620 |
ten | +0.609 |
Neg logit contributions | |
arnaev | -0.594 |
rompt | -0.570 |
psey | -0.543 |
ysis | -0.532 |
� | -0.512 |
Token | Sign |
Token ID | 5865 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
azel | +0.025 |
Devil | +0.022 |
igg | +0.021 |
Leader | +0.021 |
ten | +0.021 |
Neg logit contributions | |
arnaev | -0.035 |
rompt | -0.035 |
psey | -0.033 |
ysis | -0.033 |
� | -0.032 |
Token | Up |
Token ID | 3205 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
azel | +0.196 |
Devil | +0.178 |
igg | +0.172 |
Leader | +0.171 |
erad | +0.168 |
Neg logit contributions | |
arnaev | -0.159 |
rompt | -0.155 |
psey | -0.146 |
ysis | -0.143 |
� | -0.137 |
Token | ials |
Token ID | 8231 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
azel | +0.228 |
Devil | +0.205 |
igg | +0.198 |
Leader | +0.195 |
ten | +0.192 |
Neg logit contributions | |
arnaev | -0.247 |
rompt | -0.242 |
psey | -0.232 |
ysis | -0.226 |
� | -0.218 |
Token | are |
Token ID | 389 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
azel | +0.504 |
Devil | +0.451 |
igg | +0.437 |
Leader | +0.430 |
ten | +0.424 |
Neg logit contributions | |
arnaev | -0.509 |
rompt | -0.498 |
psey | -0.475 |
ysis | -0.467 |
� | -0.448 |
Token | decided |
Token ID | 3066 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
arnaev | +0.062 |
rompt | +0.061 |
psey | +0.058 |
ysis | +0.057 |
� | +0.055 |
Neg logit contributions | |
azel | -0.058 |
Devil | -0.052 |
igg | -0.050 |
Leader | -0.049 |
ten | -0.048 |
Token | by |
Token ID | 416 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
arnaev | +0.043 |
rompt | +0.042 |
psey | +0.040 |
ysis | +0.039 |
� | +0.038 |
Neg logit contributions | |
azel | -0.044 |
Devil | -0.040 |
igg | -0.038 |
Leader | -0.038 |
ten | -0.037 |
Token | its |
Token ID | 663 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
azel | +0.133 |
Devil | +0.119 |
igg | +0.115 |
Leader | +0.114 |
ten | +0.112 |
Neg logit contributions | |
arnaev | -0.134 |
rompt | -0.131 |
psey | -0.125 |
ysis | -0.122 |
� | -0.117 |
Token | Editorial |
Token ID | 39525 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
azel | +0.148 |
Devil | +0.135 |
igg | +0.131 |
Leader | +0.129 |
ten | +0.127 |
Neg logit contributions | |
arnaev | -0.115 |
rompt | -0.113 |
psey | -0.107 |
ysis | -0.104 |
� | -0.099 |
Token | Board |
Token ID | 5926 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
azel | +1.425 |
Devil | +1.240 |
igg | +1.217 |
Leader | +1.195 |
erad | +1.171 |
Neg logit contributions | |
rompt | -1.569 |
arnaev | -1.552 |
ysis | -1.474 |
psey | -1.473 |
� | -1.409 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
azel | +0.259 |
Devil | +0.230 |
igg | +0.221 |
Leader | +0.219 |
ten | +0.215 |
Neg logit contributions | |
arnaev | -0.300 |
rompt | -0.294 |
psey | -0.280 |
ysis | -0.276 |
� | -0.265 |
Token | a |
Token ID | 257 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
azel | +0.114 |
Devil | +0.102 |
igg | +0.098 |
Leader | +0.097 |
ten | +0.096 |
Neg logit contributions | |
arnaev | -0.120 |
rompt | -0.118 |
psey | -0.112 |
ysis | -0.110 |
� | -0.106 |
Token | dem |
Token ID | 1357 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
arnaev | +0.028 |
rompt | +0.028 |
psey | +0.027 |
ysis | +0.026 |
� | +0.025 |
Neg logit contributions | |
azel | -0.027 |
Devil | -0.024 |
igg | -0.023 |
Leader | -0.023 |
ten | -0.023 |
Token | ographically |
Token ID | 33145 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
arnaev | +0.238 |
rompt | +0.226 |
psey | +0.203 |
ysis | +0.195 |
VIDIA | +0.176 |
Neg logit contributions | |
azel | -0.752 |
Devil | -0.704 |
igg | -0.687 |
Leader | -0.682 |
ten | -0.675 |
Token | : |
Token ID | 25 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
arnaev | +0.836 |
rompt | +0.818 |
psey | +0.786 |
ysis | +0.771 |
VIDIA | +0.740 |
Neg logit contributions | |
azel | -0.650 |
Devil | -0.581 |
igg | -0.555 |
Leader | -0.546 |
ten | -0.539 |
Token |
|
Token ID | 198 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
azel | +0.130 |
Devil | +0.116 |
igg | +0.112 |
Leader | +0.110 |
ten | +0.109 |
Neg logit contributions | |
arnaev | -0.138 |
rompt | -0.135 |
psey | -0.129 |
ysis | -0.127 |
� | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
arnaev | +0.024 |
rompt | +0.024 |
psey | +0.023 |
ysis | +0.022 |
� | +0.021 |
Neg logit contributions | |
azel | -0.024 |
Devil | -0.022 |
igg | -0.021 |
Leader | -0.021 |
ten | -0.020 |
Token | Full |
Token ID | 13295 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
azel | +0.017 |
Devil | +0.016 |
igg | +0.015 |
Leader | +0.015 |
erad | +0.015 |
Neg logit contributions | |
arnaev | -0.018 |
rompt | -0.017 |
psey | -0.017 |
ysis | -0.016 |
� | -0.016 |
Token | Faith |
Token ID | 16463 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
azel | +0.024 |
Devil | +0.021 |
igg | +0.021 |
Leader | +0.020 |
ten | +0.020 |
Neg logit contributions | |
arnaev | -0.028 |
rompt | -0.027 |
psey | -0.026 |
ysis | -0.026 |
� | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
azel | +0.204 |
Devil | +0.182 |
igg | +0.174 |
Leader | +0.173 |
ten | +0.170 |
Neg logit contributions | |
arnaev | -0.238 |
rompt | -0.233 |
psey | -0.222 |
ysis | -0.219 |
� | -0.211 |
Token | Credit |
Token ID | 10504 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
azel | +1.493 |
Devil | +1.308 |
Leader | +1.272 |
igg | +1.270 |
ten | +1.244 |
Neg logit contributions | |
arnaev | -1.503 |
rompt | -1.465 |
psey | -1.393 |
ysis | -1.384 |
� | -1.332 |
Token | shall |
Token ID | 2236 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
arnaev | +0.409 |
rompt | +0.401 |
psey | +0.384 |
ysis | +0.377 |
VIDIA | +0.361 |
Neg logit contributions | |
azel | -0.339 |
Devil | -0.303 |
igg | -0.291 |
Leader | -0.286 |
ten | -0.282 |
Token | be |
Token ID | 307 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
azel | +0.275 |
Devil | +0.246 |
igg | +0.237 |
Leader | +0.235 |
ten | +0.231 |
Neg logit contributions | |
arnaev | -0.289 |
rompt | -0.283 |
psey | -0.270 |
ysis | -0.265 |
� | -0.255 |
Token | given |
Token ID | 1813 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
azel | +0.606 |
Devil | +0.535 |
igg | +0.519 |
Leader | +0.512 |
ten | +0.502 |
Neg logit contributions | |
arnaev | -0.715 |
rompt | -0.701 |
psey | -0.669 |
ysis | -0.657 |
� | -0.640 |
Token | in |
Token ID | 287 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
arnaev | +0.269 |
rompt | +0.263 |
psey | +0.251 |
ysis | +0.246 |
� | +0.234 |
Neg logit contributions | |
azel | -0.288 |
Devil | -0.260 |
igg | -0.251 |
Leader | -0.248 |
ten | -0.245 |
Token | Cavaliers |
Token ID | 29411 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
azel | +0.338 |
Devil | +0.288 |
igg | +0.276 |
Leader | +0.271 |
ten | +0.265 |
Neg logit contributions | |
arnaev | -0.586 |
rompt | -0.575 |
psey | -0.553 |
ysis | -0.546 |
� | -0.528 |
Token | guard |
Token ID | 4860 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
arnaev | +0.363 |
rompt | +0.354 |
psey | +0.337 |
ysis | +0.330 |
VIDIA | +0.314 |
Neg logit contributions | |
azel | -0.394 |
Devil | -0.358 |
igg | -0.345 |
Leader | -0.341 |
ten | -0.336 |
Token | J |
Token ID | 449 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
arnaev | +0.319 |
rompt | +0.313 |
psey | +0.299 |
ysis | +0.293 |
� | +0.281 |
Neg logit contributions | |
azel | -0.288 |
Devil | -0.258 |
igg | -0.248 |
Leader | -0.245 |
ten | -0.241 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
azel | +0.386 |
Devil | +0.345 |
igg | +0.330 |
Leader | +0.330 |
erad | +0.323 |
Neg logit contributions | |
arnaev | -0.438 |
rompt | -0.429 |
psey | -0.407 |
ysis | -0.405 |
� | -0.387 |
Token | R |
Token ID | 49 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
azel | +1.570 |
Devil | +1.404 |
igg | +1.384 |
Leader | +1.365 |
erad | +1.354 |
Neg logit contributions | |
arnaev | -1.092 |
rompt | -1.068 |
ysis | -0.994 |
psey | -0.970 |
� | -0.965 |
Token | . |
Token ID | 13 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
azel | +0.197 |
Devil | +0.176 |
igg | +0.169 |
Leader | +0.168 |
erad | +0.164 |
Neg logit contributions | |
arnaev | -0.226 |
rompt | -0.221 |
psey | -0.211 |
ysis | -0.209 |
� | -0.200 |
Token | Smith |
Token ID | 4176 |
Feature activation | -1.22e-03 |
Pos logit contributions | |
azel | +1.962 |
Devil | +1.779 |
Leader | +1.762 |
igg | +1.750 |
ten | +1.723 |
Neg logit contributions | |
arnaev | -1.000 |
rompt | -0.973 |
ysis | -0.911 |
psey | -0.858 |
RTX | -0.832 |
Token | in |
Token ID | 287 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
azel | +0.001 |
Devil | +0.001 |
igg | +0.001 |
Leader | +0.001 |
ten | +0.001 |
Neg logit contributions | |
arnaev | -0.001 |
rompt | -0.001 |
psey | -0.001 |
ysis | -0.001 |
� | -0.001 |
Token | Game |
Token ID | 3776 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
azel | +0.218 |
Devil | +0.193 |
igg | +0.186 |
Leader | +0.184 |
ten | +0.180 |
Neg logit contributions | |
arnaev | -0.265 |
rompt | -0.260 |
psey | -0.249 |
ysis | -0.245 |
� | -0.235 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
azel | +0.130 |
Devil | +0.115 |
igg | +0.111 |
Leader | +0.110 |
erad | +0.108 |
Neg logit contributions | |
arnaev | -0.150 |
rompt | -0.147 |
psey | -0.141 |
ysis | -0.139 |
� | -0.133 |
Token | of |
Token ID | 286 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
arnaev | +0.084 |
rompt | +0.082 |
psey | +0.079 |
ysis | +0.078 |
� | +0.075 |
Neg logit contributions | |
azel | -0.064 |
Devil | -0.057 |
igg | -0.054 |
Leader | -0.053 |
ten | -0.052 |
Token | Sum |
Token ID | 5060 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
azel | +0.310 |
Devil | +0.276 |
igg | +0.267 |
Leader | +0.263 |
ten | +0.260 |
Neg logit contributions | |
arnaev | -0.310 |
rompt | -0.303 |
psey | -0.290 |
ysis | -0.284 |
� | -0.272 |
Token | ma |
Token ID | 2611 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
arnaev | +0.449 |
rompt | +0.441 |
psey | +0.424 |
ysis | +0.417 |
VIDIA | +0.402 |
Neg logit contributions | |
azel | -0.310 |
Devil | -0.272 |
igg | -0.260 |
Leader | -0.256 |
ten | -0.252 |
Token | , |
Token ID | 11 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
arnaev | +0.087 |
rompt | +0.086 |
psey | +0.082 |
ysis | +0.081 |
� | +0.077 |
Neg logit contributions | |
azel | -0.073 |
Devil | -0.065 |
igg | -0.062 |
Leader | -0.061 |
ten | -0.060 |
Token | Bible |
Token ID | 9111 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
azel | +0.177 |
Devil | +0.160 |
igg | +0.155 |
Leader | +0.153 |
ten | +0.152 |
Neg logit contributions | |
arnaev | -0.153 |
rompt | -0.149 |
psey | -0.142 |
ysis | -0.139 |
RTX | -0.132 |
Token | and |
Token ID | 290 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
azel | +0.585 |
Devil | +0.519 |
igg | +0.499 |
Leader | +0.493 |
ten | +0.491 |
Neg logit contributions | |
arnaev | -0.630 |
rompt | -0.623 |
psey | -0.598 |
ysis | -0.588 |
� | -0.567 |
Token | more |
Token ID | 517 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
azel | +0.014 |
Devil | +0.012 |
igg | +0.012 |
Leader | +0.012 |
ten | +0.012 |
Neg logit contributions | |
arnaev | -0.014 |
rompt | -0.014 |
psey | -0.013 |
ysis | -0.013 |
� | -0.012 |
Token | � |
Token ID | 1587 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
azel | +1.582 |
Devil | +1.411 |
igg | +1.375 |
Leader | +1.373 |
ten | +1.356 |
Neg logit contributions | |
arnaev | -1.345 |
rompt | -1.328 |
psey | -1.278 |
ysis | -1.250 |
� | -1.202 |
Token | � |
Token ID | 245 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
arnaev | +0.289 |
rompt | +0.282 |
psey | +0.267 |
ysis | +0.261 |
� | +0.247 |
Neg logit contributions | |
azel | -0.367 |
Devil | -0.335 |
igg | -0.324 |
Leader | -0.321 |
ten | -0.317 |
Token | all |
Token ID | 477 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
azel | +0.157 |
Devil | +0.141 |
igg | +0.135 |
Leader | +0.134 |
erad | +0.132 |
Neg logit contributions | |
arnaev | -0.161 |
rompt | -0.157 |
psey | -0.150 |
ysis | -0.147 |
� | -0.141 |
Token | for |
Token ID | 329 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
arnaev | +0.160 |
rompt | +0.157 |
psey | +0.150 |
ysis | +0.147 |
� | +0.141 |
Neg logit contributions | |
azel | -0.150 |
Devil | -0.135 |
igg | -0.130 |
Leader | -0.128 |
ten | -0.126 |
Token | only |
Token ID | 691 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
azel | +0.048 |
Devil | +0.044 |
igg | +0.042 |
Leader | +0.042 |
ten | +0.041 |
Neg logit contributions | |
arnaev | -0.049 |
rompt | -0.047 |
psey | -0.045 |
ysis | -0.044 |
� | -0.043 |
Token | entire |
Token ID | 2104 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
azel | +0.067 |
Devil | +0.060 |
igg | +0.058 |
Leader | +0.057 |
ten | +0.056 |
Neg logit contributions | |
arnaev | -0.080 |
rompt | -0.078 |
psey | -0.075 |
ysis | -0.073 |
� | -0.070 |
Token | shif |
Token ID | 7143 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
azel | +0.085 |
Devil | +0.075 |
igg | +0.072 |
Leader | +0.071 |
ten | +0.069 |
Neg logit contributions | |
arnaev | -0.115 |
rompt | -0.113 |
psey | -0.109 |
ysis | -0.107 |
� | -0.103 |
Token | ter |
Token ID | 353 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
azel | +0.100 |
Devil | +0.084 |
igg | +0.079 |
Leader | +0.077 |
erad | +0.075 |
Neg logit contributions | |
arnaev | -0.219 |
rompt | -0.215 |
psey | -0.208 |
ysis | -0.206 |
� | -0.199 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
azel | +0.044 |
Devil | +0.039 |
igg | +0.037 |
Leader | +0.037 |
ten | +0.036 |
Neg logit contributions | |
arnaev | -0.050 |
rompt | -0.049 |
psey | -0.047 |
ysis | -0.046 |
� | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
arnaev | +0.108 |
rompt | +0.106 |
psey | +0.101 |
ysis | +0.100 |
� | +0.095 |
Neg logit contributions | |
azel | -0.095 |
Devil | -0.085 |
igg | -0.082 |
Leader | -0.081 |
ten | -0.079 |
Token | unh |
Token ID | 14274 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
azel | +0.115 |
Devil | +0.103 |
igg | +0.099 |
Leader | +0.098 |
ten | +0.096 |
Neg logit contributions | |
arnaev | -0.128 |
rompt | -0.126 |
psey | -0.120 |
ysis | -0.118 |
� | -0.113 |
Token | ook |
Token ID | 566 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
azel | +1.156 |
Devil | +1.040 |
Leader | +0.981 |
erad | +0.954 |
Perspective | +0.953 |
Neg logit contributions | |
arnaev | -1.749 |
rompt | -1.747 |
psey | -1.674 |
ysis | -1.651 |
� | -1.580 |
Token | them |
Token ID | 606 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
arnaev | +0.143 |
rompt | +0.140 |
psey | +0.134 |
ysis | +0.131 |
� | +0.126 |
Neg logit contributions | |
azel | -0.133 |
Devil | -0.120 |
igg | -0.115 |
Leader | -0.114 |
ten | -0.112 |
Token | from |
Token ID | 422 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
azel | +0.040 |
Devil | +0.036 |
igg | +0.034 |
Leader | +0.034 |
ten | +0.033 |
Neg logit contributions | |
arnaev | -0.044 |
rompt | -0.043 |
psey | -0.041 |
ysis | -0.041 |
� | -0.039 |
Token | underneath |
Token ID | 14638 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
azel | +0.342 |
Devil | +0.305 |
igg | +0.293 |
Leader | +0.291 |
ten | +0.285 |
Neg logit contributions | |
arnaev | -0.382 |
rompt | -0.375 |
psey | -0.358 |
ysis | -0.352 |
� | -0.338 |
Token | , |
Token ID | 11 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
azel | +0.044 |
Devil | +0.039 |
igg | +0.038 |
Leader | +0.037 |
ten | +0.037 |
Neg logit contributions | |
arnaev | -0.049 |
rompt | -0.049 |
psey | -0.046 |
ysis | -0.046 |
� | -0.044 |
Token | � |
Token ID | 447 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
azel | +0.080 |
Devil | +0.071 |
igg | +0.069 |
Leader | +0.068 |
ten | +0.067 |
Neg logit contributions | |
arnaev | -0.085 |
rompt | -0.084 |
psey | -0.080 |
ysis | -0.078 |
� | -0.075 |
Token | � |
Token ID | 251 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
azel | +0.178 |
Devil | +0.160 |
igg | +0.154 |
Leader | +0.152 |
ten | +0.150 |
Neg logit contributions | |
arnaev | -0.188 |
rompt | -0.184 |
psey | -0.175 |
ysis | -0.172 |
� | -0.165 |
Token | bloggers |
Token ID | 30357 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
azel | +0.142 |
Devil | +0.127 |
igg | +0.121 |
Leader | +0.120 |
ten | +0.118 |
Neg logit contributions | |
arnaev | -0.176 |
rompt | -0.172 |
psey | -0.165 |
ysis | -0.162 |
� | -0.156 |
Token | like |
Token ID | 588 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
azel | +0.105 |
Devil | +0.094 |
igg | +0.090 |
Leader | +0.089 |
ten | +0.087 |
Neg logit contributions | |
arnaev | -0.126 |
rompt | -0.124 |
psey | -0.118 |
ysis | -0.117 |
� | -0.112 |
Token | John |
Token ID | 1757 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
arnaev | +0.029 |
rompt | +0.029 |
psey | +0.027 |
ysis | +0.027 |
� | +0.026 |
Neg logit contributions | |
azel | -0.026 |
Devil | -0.024 |
igg | -0.023 |
Leader | -0.023 |
ten | -0.022 |
Token | Scal |
Token ID | 34529 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
arnaev | +0.010 |
rompt | +0.009 |
psey | +0.009 |
ysis | +0.009 |
� | +0.008 |
Neg logit contributions | |
azel | -0.009 |
Devil | -0.009 |
igg | -0.008 |
Leader | -0.008 |
ten | -0.008 |
Token | zi |
Token ID | 17027 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
azel | +1.316 |
Devil | +1.184 |
Leader | +1.132 |
igg | +1.131 |
erad | +1.111 |
Neg logit contributions | |
arnaev | -1.615 |
rompt | -1.578 |
psey | -1.501 |
ysis | -1.498 |
� | -1.434 |
Token | — |
Token ID | 960 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
azel | +0.101 |
Devil | +0.091 |
igg | +0.088 |
Leader | +0.087 |
ten | +0.086 |
Neg logit contributions | |
arnaev | -0.101 |
rompt | -0.099 |
psey | -0.094 |
ysis | -0.093 |
� | -0.089 |
Token | from |
Token ID | 6738 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
azel | +0.058 |
Devil | +0.052 |
igg | +0.049 |
Leader | +0.049 |
erad | +0.048 |
Neg logit contributions | |
arnaev | -0.071 |
rompt | -0.070 |
psey | -0.067 |
ysis | -0.066 |
� | -0.063 |
Token | ever |
Token ID | 1683 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
azel | +0.085 |
Devil | +0.076 |
igg | +0.073 |
Leader | +0.072 |
ten | +0.071 |
Neg logit contributions | |
arnaev | -0.090 |
rompt | -0.088 |
psey | -0.085 |
ysis | -0.083 |
� | -0.080 |
Token | sweeping |
Token ID | 18404 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
azel | +0.197 |
Devil | +0.177 |
igg | +0.170 |
Leader | +0.168 |
ten | +0.166 |
Neg logit contributions | |
arnaev | -0.207 |
rompt | -0.203 |
psey | -0.194 |
ysis | -0.191 |
� | -0.183 |
Token | abuse |
Token ID | 5076 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
arnaev | +0.229 |
rompt | +0.224 |
psey | +0.214 |
ysis | +0.210 |
� | +0.200 |
Neg logit contributions | |
azel | -0.225 |
Devil | -0.203 |
igg | -0.195 |
Leader | -0.193 |
ten | -0.190 |
Token | ), |
Token ID | 828 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
arnaev | +0.137 |
rompt | +0.134 |
psey | +0.129 |
ysis | +0.126 |
� | +0.121 |
Neg logit contributions | |
azel | -0.118 |
Devil | -0.106 |
igg | -0.102 |
Leader | -0.100 |
ten | -0.099 |
Token | John |
Token ID | 1757 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
azel | +0.033 |
Devil | +0.029 |
igg | +0.028 |
Leader | +0.028 |
ten | +0.027 |
Neg logit contributions | |
arnaev | -0.038 |
rompt | -0.037 |
psey | -0.035 |
ysis | -0.035 |
� | -0.033 |
Token | T |
Token ID | 309 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
azel | +0.237 |
Devil | +0.213 |
igg | +0.206 |
Leader | +0.205 |
erad | +0.201 |
Neg logit contributions | |
arnaev | -0.235 |
rompt | -0.230 |
psey | -0.219 |
ysis | -0.216 |
� | -0.206 |
Token | rav |
Token ID | 4108 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
azel | +0.541 |
Devil | +0.483 |
Leader | +0.463 |
igg | +0.458 |
erad | +0.452 |
Neg logit contributions | |
arnaev | -0.682 |
rompt | -0.674 |
psey | -0.644 |
ysis | -0.637 |
� | -0.609 |
Token | olt |
Token ID | 5978 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
azel | +0.247 |
Devil | +0.187 |
Leader | +0.168 |
igg | +0.160 |
erad | +0.155 |
Neg logit contributions | |
arnaev | -1.029 |
rompt | -1.014 |
psey | -0.982 |
ysis | -0.973 |
� | -0.942 |
Token | a |
Token ID | 64 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
azel | +1.741 |
Devil | +1.605 |
Leader | +1.537 |
igg | +1.521 |
erad | +1.510 |
Neg logit contributions | |
rompt | -1.157 |
arnaev | -1.157 |
psey | -1.064 |
ysis | -1.044 |
� | -0.999 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
azel | +0.305 |
Devil | +0.270 |
igg | +0.258 |
Leader | +0.255 |
ten | +0.250 |
Neg logit contributions | |
arnaev | -0.411 |
rompt | -0.404 |
psey | -0.387 |
ysis | -0.382 |
� | -0.368 |
Token | Tom |
Token ID | 4186 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
azel | +0.079 |
Devil | +0.070 |
igg | +0.068 |
Leader | +0.067 |
ten | +0.066 |
Neg logit contributions | |
arnaev | -0.090 |
rompt | -0.088 |
psey | -0.084 |
ysis | -0.083 |
� | -0.079 |
Token | Cruise |
Token ID | 29147 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
arnaev | +0.721 |
rompt | +0.707 |
psey | +0.674 |
ysis | +0.663 |
VIDIA | +0.636 |
Neg logit contributions | |
azel | -0.651 |
Devil | -0.588 |
igg | -0.563 |
Leader | -0.552 |
ten | -0.548 |
Token | ( |
Token ID | 357 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
azel | +0.023 |
Devil | +0.020 |
igg | +0.019 |
Leader | +0.019 |
ten | +0.019 |
Neg logit contributions | |
arnaev | -0.027 |
rompt | -0.027 |
psey | -0.026 |
ysis | -0.025 |
� | -0.024 |
Token | instant |
Token ID | 9113 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
azel | +0.042 |
Devil | +0.037 |
igg | +0.036 |
Leader | +0.036 |
ten | +0.035 |
Neg logit contributions | |
arnaev | -0.053 |
rompt | -0.052 |
psey | -0.050 |
ysis | -0.049 |
� | -0.047 |
Token | download |
Token ID | 4321 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
azel | +0.853 |
Devil | +0.769 |
Leader | +0.743 |
igg | +0.740 |
ten | +0.732 |
Neg logit contributions | |
arnaev | -0.773 |
rompt | -0.754 |
psey | -0.724 |
ysis | -0.712 |
� | -0.679 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
arnaev | +0.065 |
rompt | +0.064 |
psey | +0.061 |
ysis | +0.060 |
� | +0.057 |
Neg logit contributions | |
azel | -0.056 |
Devil | -0.050 |
igg | -0.048 |
Leader | -0.047 |
ten | -0.046 |
Token | Includes |
Token ID | 29581 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
arnaev | +1.023 |
rompt | +1.002 |
psey | +0.961 |
ysis | +0.948 |
VIDIA | +0.920 |
Neg logit contributions | |
azel | -0.675 |
Devil | -0.595 |
igg | -0.562 |
Leader | -0.552 |
ten | -0.542 |
Token | the |
Token ID | 262 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
azel | +0.376 |
Devil | +0.336 |
igg | +0.323 |
Leader | +0.321 |
ten | +0.316 |
Neg logit contributions | |
arnaev | -0.390 |
rompt | -0.381 |
psey | -0.367 |
ysis | -0.356 |
� | -0.344 |
Token | Catholic |
Token ID | 7835 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
azel | +0.384 |
Devil | +0.345 |
igg | +0.335 |
Leader | +0.332 |
ten | +0.328 |
Neg logit contributions | |
arnaev | -0.355 |
rompt | -0.345 |
psey | -0.329 |
ysis | -0.321 |
� | -0.308 |
Token | Encyclopedia |
Token ID | 36732 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
azel | +0.625 |
Devil | +0.434 |
igg | +0.408 |
Leader | +0.395 |
ten | +0.384 |
Neg logit contributions | |
arnaev | -2.232 |
rompt | -2.199 |
psey | -2.144 |
ysis | -2.120 |
� | -2.068 |
Token | , |
Token ID | 11 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
azel | +0.884 |
Devil | +0.784 |
igg | +0.765 |
Leader | +0.756 |
ten | +0.731 |
Neg logit contributions | |
arnaev | -0.949 |
rompt | -0.929 |
psey | -0.879 |
ysis | -0.876 |
� | -0.848 |
Token | Church |
Token ID | 4564 |
Feature activation | +4.55e-03 |
Pos logit contributions | |
azel | +0.712 |
Devil | +0.637 |
igg | +0.612 |
Leader | +0.606 |
ten | +0.603 |
Neg logit contributions | |
arnaev | -0.709 |
rompt | -0.687 |
psey | -0.660 |
ysis | -0.649 |
� | -0.624 |
Token | Fathers |
Token ID | 30969 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
arnaev | +0.003 |
rompt | +0.003 |
psey | +0.003 |
ysis | +0.003 |
� | +0.002 |
Neg logit contributions | |
azel | -0.004 |
Devil | -0.003 |
igg | -0.003 |
Leader | -0.003 |
ten | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
azel | +1.018 |
Devil | +0.901 |
igg | +0.874 |
Leader | +0.865 |
erad | +0.850 |
Neg logit contributions | |
arnaev | -1.072 |
rompt | -1.049 |
ysis | -1.009 |
psey | -0.993 |
� | -0.964 |
Token | birth |
Token ID | 4082 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
arnaev | +0.089 |
rompt | +0.087 |
psey | +0.083 |
ysis | +0.082 |
� | +0.078 |
Neg logit contributions | |
azel | -0.091 |
Devil | -0.082 |
igg | -0.079 |
Leader | -0.078 |
ten | -0.077 |
Token | rate |
Token ID | 2494 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
arnaev | +0.549 |
rompt | +0.536 |
psey | +0.509 |
ysis | +0.497 |
VIDIA | +0.478 |
Neg logit contributions | |
azel | -0.600 |
Devil | -0.543 |
igg | -0.524 |
Leader | -0.516 |
ten | -0.511 |
Token | , |
Token ID | 11 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
azel | +0.165 |
Devil | +0.146 |
igg | +0.142 |
Leader | +0.140 |
ten | +0.137 |
Neg logit contributions | |
arnaev | -0.193 |
rompt | -0.189 |
psey | -0.181 |
ysis | -0.178 |
� | -0.172 |
Token | America |
Token ID | 2253 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
azel | +0.641 |
Devil | +0.569 |
igg | +0.551 |
Leader | +0.541 |
ten | +0.534 |
Neg logit contributions | |
arnaev | -0.652 |
rompt | -0.641 |
psey | -0.614 |
ysis | -0.603 |
VIDIA | -0.579 |
Token | needs |
Token ID | 2476 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
azel | +0.725 |
Devil | +0.645 |
igg | +0.625 |
Leader | +0.612 |
ten | +0.601 |
Neg logit contributions | |
arnaev | -0.782 |
rompt | -0.760 |
psey | -0.720 |
ysis | -0.716 |
� | -0.692 |
Token | future |
Token ID | 2003 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
arnaev | +0.743 |
rompt | +0.723 |
psey | +0.689 |
ysis | +0.676 |
VIDIA | +0.647 |
Neg logit contributions | |
azel | -0.721 |
Devil | -0.650 |
igg | -0.626 |
Leader | -0.620 |
erad | -0.610 |
Token | migrants |
Token ID | 12783 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
arnaev | +2.171 |
rompt | +2.160 |
psey | +1.999 |
ysis | +1.972 |
VIDIA | +1.921 |
Neg logit contributions | |
azel | -1.868 |
Devil | -1.682 |
Leader | -1.643 |
igg | -1.616 |
erad | -1.605 |
Token | 4 |
Token ID | 604 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
azel | +0.615 |
Devil | +0.542 |
igg | +0.528 |
Leader | +0.520 |
ten | +0.519 |
Neg logit contributions | |
arnaev | -0.682 |
rompt | -0.664 |
psey | -0.632 |
ysis | -0.627 |
� | -0.602 |
Token | ways |
Token ID | 2842 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
azel | +0.601 |
Devil | +0.530 |
igg | +0.510 |
Leader | +0.502 |
erad | +0.493 |
Neg logit contributions | |
arnaev | -0.677 |
rompt | -0.663 |
psey | -0.644 |
ysis | -0.630 |
� | -0.611 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
arnaev | +0.742 |
rompt | +0.726 |
psey | +0.694 |
ysis | +0.681 |
VIDIA | +0.654 |
Neg logit contributions | |
azel | -0.673 |
Devil | -0.609 |
igg | -0.584 |
Leader | -0.576 |
ten | -0.567 |
Token | looms |
Token ID | 46234 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
arnaev | +0.745 |
rompt | +0.729 |
psey | +0.695 |
ysis | +0.678 |
VIDIA | +0.649 |
Neg logit contributions | |
azel | -0.775 |
Devil | -0.704 |
igg | -0.679 |
Leader | -0.671 |
erad | -0.664 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
arnaev | +0.176 |
rompt | +0.172 |
psey | +0.165 |
ysis | +0.162 |
� | +0.155 |
Neg logit contributions | |
azel | -0.151 |
Devil | -0.135 |
igg | -0.129 |
Leader | -0.128 |
ten | -0.126 |
Token | The |
Token ID | 383 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
arnaev | +0.161 |
rompt | +0.158 |
psey | +0.151 |
ysis | +0.148 |
� | +0.142 |
Neg logit contributions | |
azel | -0.143 |
Devil | -0.128 |
igg | -0.123 |
Leader | -0.122 |
ten | -0.120 |
Token | BBC |
Token ID | 7823 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
arnaev | +0.251 |
rompt | +0.245 |
psey | +0.234 |
ysis | +0.230 |
� | +0.220 |
Neg logit contributions | |
azel | -0.234 |
Devil | -0.211 |
igg | -0.203 |
Leader | -0.200 |
ten | -0.197 |
Token | 's |
Token ID | 338 |
Feature activation | +9.08e-03 |
Pos logit contributions | |
arnaev | +0.170 |
rompt | +0.167 |
psey | +0.159 |
ysis | +0.156 |
� | +0.150 |
Neg logit contributions | |
azel | -0.152 |
Devil | -0.136 |
igg | -0.131 |
Leader | -0.129 |
ten | -0.127 |
Token | Im |
Token ID | 1846 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
arnaev | +0.007 |
rompt | +0.007 |
psey | +0.007 |
ysis | +0.007 |
� | +0.006 |
Neg logit contributions | |
azel | -0.006 |
Devil | -0.006 |
igg | -0.005 |
Leader | -0.005 |
ten | -0.005 |
Token | ogen |
Token ID | 6644 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
azel | +0.098 |
Devil | +0.090 |
igg | +0.087 |
Leader | +0.086 |
erad | +0.085 |
Neg logit contributions | |
arnaev | -0.074 |
rompt | -0.072 |
psey | -0.068 |
ysis | -0.067 |
� | -0.063 |
Token | F |
Token ID | 376 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
arnaev | +1.840 |
rompt | +1.804 |
psey | +1.726 |
ysis | +1.663 |
VIDIA | +1.586 |
Neg logit contributions | |
azel | -1.947 |
Devil | -1.783 |
igg | -1.722 |
ten | -1.680 |
Leader | -1.677 |
Token | oul |
Token ID | 2852 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
arnaev | +0.570 |
rompt | +0.555 |
psey | +0.528 |
ysis | +0.516 |
� | +0.492 |
Neg logit contributions | |
azel | -0.668 |
Devil | -0.602 |
igg | -0.587 |
Leader | -0.575 |
ten | -0.570 |
Token | kes |
Token ID | 5209 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
azel | +0.860 |
Devil | +0.782 |
Leader | +0.751 |
igg | +0.750 |
erad | +0.737 |
Neg logit contributions | |
arnaev | -0.698 |
rompt | -0.687 |
psey | -0.658 |
ysis | -0.639 |
� | -0.611 |
Token | , |
Token ID | 11 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
arnaev | +0.370 |
rompt | +0.362 |
psey | +0.346 |
ysis | +0.340 |
VIDIA | +0.325 |
Neg logit contributions | |
azel | -0.332 |
Devil | -0.298 |
igg | -0.286 |
Leader | -0.282 |
ten | -0.278 |
Token | in |
Token ID | 287 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
azel | +0.019 |
Devil | +0.017 |
igg | +0.017 |
Leader | +0.016 |
ten | +0.016 |
Neg logit contributions | |
arnaev | -0.022 |
rompt | -0.021 |
psey | -0.021 |
ysis | -0.020 |
� | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
arnaev | +0.208 |
rompt | +0.204 |
psey | +0.195 |
ysis | +0.191 |
� | +0.183 |
Neg logit contributions | |
azel | -0.195 |
Devil | -0.175 |
igg | -0.168 |
Leader | -0.166 |
ten | -0.164 |
Token | the |
Token ID | 262 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
azel | +0.158 |
Devil | +0.139 |
igg | +0.133 |
Leader | +0.131 |
ten | +0.128 |
Neg logit contributions | |
arnaev | -0.217 |
rompt | -0.213 |
psey | -0.205 |
ysis | -0.202 |
� | -0.194 |
Token | n |
Token ID | 299 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
arnaev | +0.169 |
rompt | +0.166 |
psey | +0.159 |
ysis | +0.156 |
� | +0.150 |
Neg logit contributions | |
azel | -0.141 |
Devil | -0.125 |
igg | -0.120 |
Leader | -0.119 |
ten | -0.117 |
Token | itty |
Token ID | 9760 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
arnaev | +0.375 |
rompt | +0.367 |
psey | +0.352 |
ysis | +0.345 |
� | +0.331 |
Neg logit contributions | |
azel | -0.319 |
Devil | -0.285 |
igg | -0.274 |
Leader | -0.270 |
ten | -0.266 |
Token | - |
Token ID | 12 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
arnaev | +0.204 |
rompt | +0.200 |
psey | +0.191 |
ysis | +0.188 |
� | +0.180 |
Neg logit contributions | |
azel | -0.181 |
Devil | -0.162 |
igg | -0.156 |
Leader | -0.154 |
ten | -0.152 |
Token | gr |
Token ID | 2164 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
arnaev | +0.153 |
rompt | +0.150 |
psey | +0.143 |
ysis | +0.141 |
� | +0.135 |
Neg logit contributions | |
azel | -0.140 |
Devil | -0.126 |
igg | -0.121 |
Leader | -0.119 |
ten | -0.117 |
Token | itty |
Token ID | 9760 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
arnaev | +1.802 |
rompt | +1.765 |
psey | +1.691 |
ysis | +1.646 |
VIDIA | +1.614 |
Neg logit contributions | |
azel | -1.389 |
Devil | -1.231 |
igg | -1.214 |
ten | -1.160 |
Leader | -1.143 |
Token | of |
Token ID | 286 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
arnaev | +0.099 |
rompt | +0.097 |
psey | +0.093 |
ysis | +0.091 |
� | +0.088 |
Neg logit contributions | |
azel | -0.078 |
Devil | -0.070 |
igg | -0.067 |
Leader | -0.066 |
ten | -0.065 |
Token | applying |
Token ID | 11524 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
azel | +0.049 |
Devil | +0.044 |
igg | +0.042 |
Leader | +0.042 |
ten | +0.041 |
Neg logit contributions | |
arnaev | -0.055 |
rompt | -0.054 |
psey | -0.052 |
ysis | -0.051 |
� | -0.049 |
Token | for |
Token ID | 329 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
arnaev | +0.054 |
rompt | +0.053 |
psey | +0.050 |
ysis | +0.049 |
� | +0.047 |
Neg logit contributions | |
azel | -0.050 |
Devil | -0.045 |
igg | -0.043 |
Leader | -0.043 |
ten | -0.042 |
Token | business |
Token ID | 1597 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
azel | +0.366 |
Devil | +0.326 |
igg | +0.313 |
Leader | +0.311 |
ten | +0.304 |
Neg logit contributions | |
arnaev | -0.427 |
rompt | -0.418 |
psey | -0.401 |
ysis | -0.397 |
� | -0.379 |
Token | consist |
Token ID | 3473 |
Feature activation | +8.46e-03 |
Pos logit contributions | |
arnaev | +1.625 |
rompt | +1.592 |
psey | +1.533 |
ysis | +1.513 |
VIDIA | +1.483 |
Neg logit contributions | |
azel | -1.043 |
Devil | -0.917 |
igg | -0.861 |
Leader | -0.851 |
erad | -0.841 |
Token | of |
Token ID | 286 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
arnaev | +0.007 |
rompt | +0.007 |
psey | +0.007 |
ysis | +0.007 |
� | +0.006 |
Neg logit contributions | |
azel | -0.005 |
Devil | -0.005 |
igg | -0.004 |
Leader | -0.004 |
ten | -0.004 |
Token | me |
Token ID | 502 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
arnaev | +0.136 |
rompt | +0.132 |
psey | +0.125 |
ysis | +0.123 |
� | +0.116 |
Neg logit contributions | |
azel | -0.171 |
Devil | -0.156 |
igg | -0.151 |
Leader | -0.149 |
ten | -0.147 |
Token | thinking |
Token ID | 3612 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
azel | +0.346 |
Devil | +0.312 |
igg | +0.298 |
Leader | +0.297 |
ten | +0.292 |
Neg logit contributions | |
arnaev | -0.335 |
rompt | -0.327 |
psey | -0.311 |
ysis | -0.305 |
� | -0.293 |
Token | out |
Token ID | 503 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
arnaev | +1.208 |
rompt | +1.181 |
psey | +1.129 |
ysis | +1.116 |
VIDIA | +1.079 |
Neg logit contributions | |
azel | -0.902 |
Devil | -0.803 |
igg | -0.771 |
Leader | -0.752 |
erad | -0.743 |
Token | loud |
Token ID | 7812 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
arnaev | +0.175 |
rompt | +0.170 |
psey | +0.162 |
ysis | +0.159 |
� | +0.151 |
Neg logit contributions | |
azel | -0.201 |
Devil | -0.182 |
igg | -0.176 |
Leader | -0.174 |
ten | -0.172 |
Token | . |
Token ID | 13 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
arnaev | +1.631 |
rompt | +1.590 |
psey | +1.534 |
ysis | +1.505 |
VIDIA | +1.456 |
Neg logit contributions | |
azel | -1.220 |
Devil | -1.083 |
igg | -1.048 |
Leader | -1.023 |
ten | -1.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
arnaev | +0.359 |
rompt | +0.351 |
psey | +0.336 |
ysis | +0.329 |
VIDIA | +0.315 |
Neg logit contributions | |
azel | -0.340 |
Devil | -0.306 |
igg | -0.294 |
Leader | -0.291 |
ten | -0.286 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
arnaev | +0.079 |
rompt | +0.077 |
psey | +0.074 |
ysis | +0.073 |
� | +0.070 |
Neg logit contributions | |
azel | -0.078 |
Devil | -0.070 |
igg | -0.067 |
Leader | -0.067 |
ten | -0.066 |
Token | I |
Token ID | 40 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
arnaev | +0.931 |
rompt | +0.907 |
psey | +0.872 |
ysis | +0.852 |
VIDIA | +0.824 |
Neg logit contributions | |
azel | -0.802 |
Devil | -0.713 |
igg | -0.693 |
Leader | -0.687 |
ten | -0.670 |
Token | � |
Token ID | 447 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
arnaev | +0.182 |
rompt | +0.179 |
psey | +0.171 |
ysis | +0.168 |
� | +0.161 |
Neg logit contributions | |
azel | -0.164 |
Devil | -0.147 |
igg | -0.141 |
Leader | -0.139 |
ten | -0.137 |
Token | stubborn |
Token ID | 24444 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
arnaev | +0.167 |
rompt | +0.163 |
psey | +0.156 |
ysis | +0.153 |
� | +0.147 |
Neg logit contributions | |
azel | -0.155 |
Devil | -0.139 |
igg | -0.134 |
Leader | -0.132 |
ten | -0.130 |
Token | ." |
Token ID | 526 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
azel | +0.236 |
Devil | +0.212 |
igg | +0.204 |
Leader | +0.202 |
ten | +0.198 |
Neg logit contributions | |
arnaev | -0.256 |
rompt | -0.251 |
psey | -0.240 |
ysis | -0.237 |
� | -0.227 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
arnaev | +0.045 |
rompt | +0.044 |
psey | +0.042 |
ysis | +0.042 |
� | +0.040 |
Neg logit contributions | |
azel | -0.046 |
Devil | -0.041 |
igg | -0.040 |
Leader | -0.039 |
ten | -0.039 |
Token | Every |
Token ID | 6109 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
arnaev | +0.044 |
rompt | +0.043 |
psey | +0.041 |
ysis | +0.040 |
� | +0.039 |
Neg logit contributions | |
azel | -0.043 |
Devil | -0.038 |
igg | -0.037 |
Leader | -0.036 |
erad | -0.036 |
Token | share |
Token ID | 2648 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
arnaev | +0.086 |
rompt | +0.084 |
psey | +0.081 |
ysis | +0.079 |
� | +0.076 |
Neg logit contributions | |
azel | -0.077 |
Devil | -0.069 |
igg | -0.066 |
Leader | -0.065 |
ten | -0.064 |
Token | makes |
Token ID | 1838 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
azel | +0.475 |
Devil | +0.420 |
igg | +0.401 |
Leader | +0.397 |
ten | +0.395 |
Neg logit contributions | |
arnaev | -0.540 |
rompt | -0.527 |
psey | -0.505 |
ysis | -0.495 |
� | -0.480 |
Token | Black |
Token ID | 2619 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
arnaev | +2.401 |
rompt | +2.351 |
psey | +2.258 |
ysis | +2.227 |
VIDIA | +2.176 |
Neg logit contributions | |
azel | -1.811 |
Devil | -1.621 |
igg | -1.575 |
Leader | -1.521 |
erad | -1.510 |
Token | Voice |
Token ID | 15282 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
arnaev | +0.684 |
rompt | +0.671 |
psey | +0.649 |
ysis | +0.641 |
VIDIA | +0.618 |
Neg logit contributions | |
azel | -0.320 |
Devil | -0.273 |
igg | -0.255 |
Leader | -0.251 |
ten | -0.243 |
Token | louder |
Token ID | 27089 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
arnaev | +0.375 |
rompt | +0.366 |
psey | +0.349 |
ysis | +0.342 |
VIDIA | +0.325 |
Neg logit contributions | |
azel | -0.407 |
Devil | -0.368 |
igg | -0.356 |
Leader | -0.352 |
ten | -0.346 |
Token | ! |
Token ID | 0 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
arnaev | +0.501 |
rompt | +0.489 |
psey | +0.467 |
ysis | +0.457 |
VIDIA | +0.436 |
Neg logit contributions | |
azel | -0.508 |
Devil | -0.459 |
igg | -0.442 |
Leader | -0.437 |
ten | -0.430 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
arnaev | +0.191 |
rompt | +0.184 |
psey | +0.170 |
ysis | +0.165 |
VIDIA | +0.151 |
Neg logit contributions | |
azel | -0.429 |
Devil | -0.399 |
igg | -0.389 |
Leader | -0.386 |
ten | -0.382 |
Token | � |
Token ID | 134 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
arnaev | +0.033 |
rompt | +0.032 |
psey | +0.030 |
ysis | +0.030 |
� | +0.028 |
Neg logit contributions | |
azel | -0.043 |
Devil | -0.040 |
igg | -0.038 |
Leader | -0.038 |
ten | -0.037 |
Token | � |
Token ID | 119 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
azel | +0.350 |
Devil | +0.321 |
igg | +0.311 |
Leader | +0.308 |
ten | +0.304 |
Neg logit contributions | |
arnaev | -0.254 |
rompt | -0.249 |
psey | -0.234 |
ysis | -0.229 |
� | -0.219 |
Token | i |
Token ID | 72 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
arnaev | +0.329 |
rompt | +0.322 |
psey | +0.307 |
ysis | +0.301 |
� | +0.288 |
Neg logit contributions | |
azel | -0.322 |
Devil | -0.290 |
igg | -0.279 |
Leader | -0.275 |
ten | -0.272 |
Token | me |
Token ID | 502 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
arnaev | +0.120 |
rompt | +0.118 |
psey | +0.112 |
ysis | +0.111 |
� | +0.106 |
Neg logit contributions | |
azel | -0.105 |
Devil | -0.094 |
igg | -0.090 |
Leader | -0.089 |
ten | -0.087 |
Token | Ke |
Token ID | 3873 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
arnaev | +0.245 |
rompt | +0.240 |
psey | +0.229 |
ysis | +0.225 |
� | +0.216 |
Neg logit contributions | |
azel | -0.219 |
Devil | -0.196 |
igg | -0.188 |
Leader | -0.186 |
ten | -0.183 |
Token | K |
Token ID | 509 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
arnaev | +0.358 |
rompt | +0.349 |
psey | +0.331 |
ysis | +0.324 |
� | +0.307 |
Neg logit contributions | |
azel | -0.439 |
Devil | -0.400 |
igg | -0.387 |
Leader | -0.383 |
ten | -0.378 |
Token | ula |
Token ID | 4712 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
arnaev | +0.447 |
rompt | +0.437 |
psey | +0.418 |
ysis | +0.410 |
� | +0.392 |
Neg logit contributions | |
azel | -0.430 |
Devil | -0.387 |
igg | -0.373 |
Leader | -0.368 |
ten | -0.363 |
Token | Kai |
Token ID | 22091 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
arnaev | +0.282 |
rompt | +0.275 |
psey | +0.263 |
ysis | +0.258 |
� | +0.246 |
Neg logit contributions | |
azel | -0.275 |
Devil | -0.248 |
igg | -0.239 |
Leader | -0.236 |
ten | -0.232 |
Token | ap |
Token ID | 499 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
arnaev | +0.229 |
rompt | +0.223 |
psey | +0.210 |
ysis | +0.205 |
� | +0.194 |
Neg logit contributions | |
azel | -0.323 |
Devil | -0.296 |
igg | -0.287 |
Leader | -0.284 |
ten | -0.281 |
Token | uni |
Token ID | 35657 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
arnaev | +0.234 |
rompt | +0.228 |
psey | +0.216 |
ysis | +0.212 |
� | +0.201 |
Neg logit contributions | |
azel | -0.300 |
Devil | -0.273 |
igg | -0.265 |
Leader | -0.262 |
ten | -0.258 |
Token | o |
Token ID | 267 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
arnaev | +0.128 |
rompt | +0.125 |
psey | +0.120 |
ysis | +0.118 |
� | +0.113 |
Neg logit contributions | |
azel | -0.112 |
Devil | -0.100 |
igg | -0.096 |
Leader | -0.095 |
ten | -0.093 |
Token | and |
Token ID | 290 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
arnaev | +0.081 |
rompt | +0.079 |
psey | +0.076 |
ysis | +0.074 |
� | +0.071 |
Neg logit contributions | |
azel | -0.076 |
Devil | -0.068 |
igg | -0.066 |
Leader | -0.065 |
ten | -0.064 |
Token | said |
Token ID | 531 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
azel | +0.013 |
Devil | +0.012 |
igg | +0.011 |
Leader | +0.011 |
ten | +0.011 |
Neg logit contributions | |
arnaev | -0.013 |
rompt | -0.013 |
psey | -0.013 |
ysis | -0.012 |
� | -0.012 |
Token | that |
Token ID | 326 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
azel | +0.077 |
Devil | +0.069 |
igg | +0.066 |
Leader | +0.065 |
ten | +0.064 |
Neg logit contributions | |
arnaev | -0.084 |
rompt | -0.082 |
psey | -0.079 |
ysis | -0.077 |
� | -0.074 |
Token | Exxon |
Token ID | 27879 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
azel | +0.091 |
Devil | +0.082 |
igg | +0.079 |
Leader | +0.078 |
ten | +0.077 |
Neg logit contributions | |
arnaev | -0.097 |
rompt | -0.095 |
psey | -0.091 |
ysis | -0.090 |
� | -0.086 |
Token | Mobil |
Token ID | 47100 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
arnaev | +0.114 |
rompt | +0.112 |
psey | +0.106 |
ysis | +0.104 |
� | +0.099 |
Neg logit contributions | |
azel | -0.130 |
Devil | -0.118 |
igg | -0.114 |
Leader | -0.112 |
ten | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
arnaev | +0.146 |
rompt | +0.143 |
psey | +0.137 |
ysis | +0.134 |
� | +0.128 |
Neg logit contributions | |
azel | -0.144 |
Devil | -0.129 |
igg | -0.125 |
Leader | -0.123 |
ten | -0.121 |
Token | the |
Token ID | 262 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
arnaev | +0.341 |
rompt | +0.333 |
psey | +0.317 |
ysis | +0.311 |
� | +0.296 |
Neg logit contributions | |
azel | -0.371 |
Devil | -0.336 |
igg | -0.324 |
Leader | -0.321 |
ten | -0.316 |
Token | only |
Token ID | 691 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
arnaev | +0.242 |
rompt | +0.237 |
psey | +0.227 |
ysis | +0.223 |
� | +0.214 |
Neg logit contributions | |
azel | -0.204 |
Devil | -0.182 |
igg | -0.174 |
Leader | -0.172 |
ten | -0.169 |
Token | other |
Token ID | 584 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
arnaev | +0.125 |
rompt | +0.123 |
psey | +0.118 |
ysis | +0.116 |
� | +0.111 |
Neg logit contributions | |
azel | -0.098 |
Devil | -0.087 |
igg | -0.083 |
Leader | -0.082 |
ten | -0.080 |
Token | U |
Token ID | 471 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
arnaev | +0.220 |
rompt | +0.215 |
psey | +0.207 |
ysis | +0.204 |
� | +0.196 |
Neg logit contributions | |
azel | -0.161 |
Devil | -0.143 |
igg | -0.136 |
Leader | -0.134 |
ten | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
azel | +0.053 |
Devil | +0.048 |
igg | +0.046 |
Leader | +0.045 |
erad | +0.044 |
Neg logit contributions | |
arnaev | -0.061 |
rompt | -0.060 |
psey | -0.057 |
ysis | -0.057 |
� | -0.055 |
Token | 16 |
Token ID | 1467 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
arnaev | +0.049 |
rompt | +0.048 |
psey | +0.046 |
ysis | +0.045 |
� | +0.043 |
Neg logit contributions | |
azel | -0.039 |
Devil | -0.035 |
igg | -0.034 |
Leader | -0.033 |
ten | -0.033 |
Token | - |
Token ID | 12 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
arnaev | +0.016 |
rompt | +0.015 |
psey | +0.015 |
ysis | +0.014 |
� | +0.014 |
Neg logit contributions | |
azel | -0.013 |
Devil | -0.011 |
igg | -0.011 |
Leader | -0.011 |
ten | -0.010 |
Token | 35 |
Token ID | 2327 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
arnaev | +0.155 |
rompt | +0.152 |
psey | +0.145 |
ysis | +0.142 |
� | +0.136 |
Neg logit contributions | |
azel | -0.148 |
Devil | -0.133 |
igg | -0.128 |
Leader | -0.126 |
ten | -0.124 |
Token | f |
Token ID | 277 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
arnaev | +0.033 |
rompt | +0.032 |
psey | +0.030 |
ysis | +0.030 |
� | +0.028 |
Neg logit contributions | |
azel | -0.038 |
Devil | -0.035 |
igg | -0.033 |
Leader | -0.033 |
ten | -0.033 |
Token | / |
Token ID | 14 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
arnaev | +0.330 |
rompt | +0.322 |
psey | +0.306 |
ysis | +0.300 |
VIDIA | +0.285 |
Neg logit contributions | |
azel | -0.374 |
Devil | -0.339 |
igg | -0.328 |
Leader | -0.324 |
ten | -0.320 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
arnaev | +0.279 |
rompt | +0.272 |
psey | +0.259 |
ysis | +0.253 |
� | +0.240 |
Neg logit contributions | |
azel | -0.338 |
Devil | -0.308 |
igg | -0.298 |
Leader | -0.295 |
ten | -0.291 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
arnaev | +0.445 |
rompt | +0.436 |
psey | +0.418 |
ysis | +0.410 |
� | +0.393 |
Neg logit contributions | |
azel | -0.372 |
Devil | -0.333 |
igg | -0.319 |
Leader | -0.314 |
ten | -0.310 |
Token | 8 |
Token ID | 23 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
arnaev | +0.204 |
rompt | +0.200 |
psey | +0.192 |
ysis | +0.190 |
� | +0.182 |
Neg logit contributions | |
azel | -0.133 |
Devil | -0.116 |
igg | -0.110 |
Leader | -0.109 |
ten | -0.107 |
Token | II |
Token ID | 2873 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
arnaev | +0.257 |
rompt | +0.252 |
psey | +0.243 |
ysis | +0.240 |
� | +0.232 |
Neg logit contributions | |
azel | -0.136 |
Devil | -0.117 |
igg | -0.110 |
Leader | -0.108 |
ten | -0.106 |
Token | at |
Token ID | 379 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
arnaev | +0.101 |
rompt | +0.100 |
psey | +0.096 |
ysis | +0.095 |
� | +0.091 |
Neg logit contributions | |
azel | -0.064 |
Devil | -0.056 |
igg | -0.053 |
Leader | -0.053 |
ten | -0.052 |
Token | 16 |
Token ID | 1467 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
azel | +0.021 |
Devil | +0.019 |
igg | +0.018 |
Leader | +0.018 |
ten | +0.018 |
Neg logit contributions | |
arnaev | -0.025 |
rompt | -0.024 |
psey | -0.023 |
ysis | -0.023 |
� | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
arnaev | +0.041 |
rompt | +0.040 |
psey | +0.039 |
ysis | +0.038 |
� | +0.036 |
Neg logit contributions | |
azel | -0.037 |
Devil | -0.033 |
igg | -0.032 |
Leader | -0.031 |
ten | -0.031 |
Token | Democrat |
Token ID | 9755 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
arnaev | +0.148 |
rompt | +0.145 |
psey | +0.138 |
ysis | +0.136 |
� | +0.129 |
Neg logit contributions | |
azel | -0.146 |
Devil | -0.131 |
igg | -0.127 |
Leader | -0.125 |
ten | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
azel | +0.256 |
Devil | +0.228 |
igg | +0.219 |
Leader | +0.216 |
ten | +0.212 |
Neg logit contributions | |
arnaev | -0.303 |
rompt | -0.297 |
psey | -0.285 |
ysis | -0.281 |
� | -0.269 |
Token | Sen |
Token ID | 2311 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
azel | +0.134 |
Devil | +0.120 |
igg | +0.116 |
Leader | +0.114 |
erad | +0.113 |
Neg logit contributions | |
arnaev | -0.138 |
rompt | -0.135 |
psey | -0.129 |
ysis | -0.127 |
� | -0.122 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
azel | +0.212 |
Devil | +0.189 |
igg | +0.182 |
Leader | +0.180 |
erad | +0.177 |
Neg logit contributions | |
arnaev | -0.246 |
rompt | -0.241 |
psey | -0.231 |
ysis | -0.227 |
� | -0.217 |
Token | Eddie |
Token ID | 19478 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
arnaev | +0.009 |
rompt | +0.009 |
psey | +0.009 |
ysis | +0.009 |
� | +0.008 |
Neg logit contributions | |
azel | -0.008 |
Devil | -0.007 |
igg | -0.007 |
Leader | -0.007 |
ten | -0.007 |
Token | Luc |
Token ID | 7598 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
arnaev | +0.669 |
rompt | +0.653 |
psey | +0.624 |
ysis | +0.610 |
VIDIA | +0.585 |
Neg logit contributions | |
azel | -0.643 |
Devil | -0.582 |
igg | -0.557 |
Leader | -0.549 |
ten | -0.542 |
Token | io |
Token ID | 952 |
Feature activation | -8.20e-03 |
Pos logit contributions | |
azel | +0.155 |
Devil | +0.137 |
igg | +0.130 |
Leader | +0.128 |
erad | +0.126 |
Neg logit contributions | |
arnaev | -0.232 |
rompt | -0.229 |
psey | -0.220 |
ysis | -0.216 |
� | -0.208 |
Token | , |
Token ID | 11 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
azel | +0.006 |
Devil | +0.005 |
igg | +0.005 |
Leader | +0.005 |
ten | +0.005 |
Neg logit contributions | |
arnaev | -0.006 |
rompt | -0.006 |
psey | -0.006 |
ysis | -0.006 |
� | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
arnaev | +0.072 |
rompt | +0.070 |
psey | +0.067 |
ysis | +0.066 |
� | +0.063 |
Neg logit contributions | |
azel | -0.064 |
Devil | -0.058 |
igg | -0.055 |
Leader | -0.055 |
ten | -0.054 |
Token | Browns |
Token ID | 17671 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
arnaev | +0.163 |
rompt | +0.159 |
psey | +0.152 |
ysis | +0.149 |
� | +0.143 |
Neg logit contributions | |
azel | -0.161 |
Devil | -0.145 |
igg | -0.139 |
Leader | -0.138 |
ten | -0.136 |
Token | your |
Token ID | 534 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
arnaev | +0.238 |
rompt | +0.233 |
psey | +0.223 |
ysis | +0.219 |
� | +0.209 |
Neg logit contributions | |
azel | -0.217 |
Devil | -0.195 |
igg | -0.187 |
Leader | -0.185 |
ten | -0.182 |
Token | Asian |
Token ID | 7740 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
arnaev | +0.443 |
rompt | +0.433 |
psey | +0.411 |
ysis | +0.403 |
VIDIA | +0.383 |
Neg logit contributions | |
azel | -0.500 |
Devil | -0.454 |
igg | -0.438 |
Leader | -0.433 |
ten | -0.427 |
Token | friends |
Token ID | 2460 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
arnaev | +0.056 |
rompt | +0.055 |
psey | +0.053 |
ysis | +0.052 |
� | +0.050 |
Neg logit contributions | |
azel | -0.049 |
Devil | -0.044 |
igg | -0.042 |
Leader | -0.041 |
ten | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
azel | +0.065 |
Devil | +0.058 |
igg | +0.056 |
Leader | +0.055 |
ten | +0.054 |
Neg logit contributions | |
arnaev | -0.076 |
rompt | -0.075 |
psey | -0.072 |
ysis | -0.070 |
� | -0.068 |
Token | you |
Token ID | 345 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
arnaev | +0.197 |
rompt | +0.193 |
psey | +0.185 |
ysis | +0.181 |
� | +0.174 |
Neg logit contributions | |
azel | -0.166 |
Devil | -0.148 |
igg | -0.142 |
Leader | -0.140 |
ten | -0.138 |
Token | � |
Token ID | 447 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
arnaev | +0.331 |
rompt | +0.323 |
psey | +0.308 |
ysis | +0.302 |
� | +0.288 |
Neg logit contributions | |
azel | -0.331 |
Devil | -0.299 |
igg | -0.288 |
Leader | -0.284 |
ten | -0.280 |
Token | � |
Token ID | 247 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
arnaev | +0.362 |
rompt | +0.354 |
psey | +0.339 |
ysis | +0.333 |
VIDIA | +0.318 |
Neg logit contributions | |
azel | -0.321 |
Devil | -0.288 |
igg | -0.277 |
Leader | -0.273 |
ten | -0.269 |
Token | re |
Token ID | 260 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
arnaev | +0.042 |
rompt | +0.041 |
psey | +0.039 |
ysis | +0.039 |
� | +0.037 |
Neg logit contributions | |
azel | -0.046 |
Devil | -0.042 |
igg | -0.040 |
Leader | -0.040 |
ten | -0.039 |
Token | able |
Token ID | 1498 |
Feature activation | -7.36e-02 |
Pos logit contributions | |
arnaev | +0.431 |
rompt | +0.421 |
psey | +0.401 |
ysis | +0.394 |
VIDIA | +0.375 |
Neg logit contributions | |
azel | -0.449 |
Devil | -0.406 |
igg | -0.391 |
Leader | -0.386 |
ten | -0.381 |
Token | to |
Token ID | 284 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
azel | +0.053 |
Devil | +0.048 |
igg | +0.046 |
Leader | +0.045 |
ten | +0.045 |
Neg logit contributions | |
arnaev | -0.055 |
rompt | -0.054 |
psey | -0.051 |
ysis | -0.050 |
� | -0.048 |
Token | understand |
Token ID | 1833 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
arnaev | +0.079 |
rompt | +0.078 |
psey | +0.075 |
ysis | +0.073 |
� | +0.070 |
Neg logit contributions | |
azel | -0.068 |
Devil | -0.061 |
igg | -0.058 |
Leader | -0.057 |
ten | -0.056 |
Token | been |
Token ID | 587 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
arnaev | +0.086 |
rompt | +0.084 |
psey | +0.080 |
ysis | +0.078 |
� | +0.075 |
Neg logit contributions | |
azel | -0.085 |
Devil | -0.077 |
igg | -0.074 |
Leader | -0.073 |
ten | -0.072 |
Token | used |
Token ID | 973 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
azel | +0.404 |
Devil | +0.361 |
igg | +0.347 |
Leader | +0.344 |
ten | +0.337 |
Neg logit contributions | |
arnaev | -0.447 |
rompt | -0.438 |
psey | -0.420 |
ysis | -0.411 |
� | -0.394 |
Token | since |
Token ID | 1201 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
azel | +0.116 |
Devil | +0.104 |
igg | +0.100 |
Leader | +0.099 |
ten | +0.097 |
Neg logit contributions | |
arnaev | -0.122 |
rompt | -0.120 |
psey | -0.114 |
ysis | -0.112 |
� | -0.107 |
Token | at |
Token ID | 379 |
Feature activation | -9.90e-03 |
Pos logit contributions | |
azel | +0.216 |
Devil | +0.193 |
igg | +0.186 |
Leader | +0.185 |
ten | +0.181 |
Neg logit contributions | |
arnaev | -0.233 |
rompt | -0.228 |
psey | -0.218 |
ysis | -0.214 |
� | -0.205 |
Token | least |
Token ID | 1551 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
azel | +0.006 |
Devil | +0.005 |
igg | +0.005 |
Leader | +0.005 |
ten | +0.005 |
Neg logit contributions | |
arnaev | -0.009 |
rompt | -0.008 |
psey | -0.008 |
ysis | -0.008 |
� | -0.008 |
Token | 2002 |
Token ID | 6244 |
Feature activation | -6.09e-03 |
Pos logit contributions | |
arnaev | +0.025 |
rompt | +0.024 |
psey | +0.023 |
ysis | +0.023 |
� | +0.022 |
Neg logit contributions | |
azel | -0.022 |
Devil | -0.019 |
igg | -0.019 |
Leader | -0.018 |
ten | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
azel | +0.004 |
Devil | +0.004 |
igg | +0.004 |
Leader | +0.004 |
ten | +0.003 |
Neg logit contributions | |
arnaev | -0.005 |
rompt | -0.005 |
psey | -0.004 |
ysis | -0.004 |
� | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
azel | +0.284 |
Devil | +0.254 |
igg | +0.245 |
Leader | +0.243 |
ten | +0.238 |
Neg logit contributions | |
arnaev | -0.312 |
rompt | -0.305 |
psey | -0.293 |
ysis | -0.288 |
� | -0.275 |
Token | field |
Token ID | 2214 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
azel | +0.435 |
Devil | +0.384 |
igg | +0.372 |
Leader | +0.367 |
ten | +0.360 |
Neg logit contributions | |
arnaev | -0.525 |
rompt | -0.514 |
psey | -0.493 |
ysis | -0.486 |
� | -0.467 |
Token | of |
Token ID | 286 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
azel | +0.091 |
Devil | +0.080 |
igg | +0.077 |
Leader | +0.076 |
ten | +0.074 |
Neg logit contributions | |
arnaev | -0.121 |
rompt | -0.119 |
psey | -0.114 |
ysis | -0.112 |
� | -0.108 |
Token | gravitational |
Token ID | 29973 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
azel | +0.227 |
Devil | +0.203 |
igg | +0.195 |
Leader | +0.194 |
ten | +0.190 |
Neg logit contributions | |
arnaev | -0.252 |
rompt | -0.247 |
psey | -0.236 |
ysis | -0.232 |
� | -0.222 |
Token | 8 |
Token ID | 807 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
arnaev | +0.166 |
rompt | +0.162 |
psey | +0.156 |
ysis | +0.153 |
� | +0.147 |
Neg logit contributions | |
azel | -0.137 |
Devil | -0.122 |
igg | -0.117 |
Leader | -0.115 |
ten | -0.113 |
Token | SS |
Token ID | 6723 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
arnaev | +0.069 |
rompt | +0.067 |
psey | +0.064 |
ysis | +0.063 |
� | +0.060 |
Neg logit contributions | |
azel | -0.066 |
Devil | -0.059 |
igg | -0.057 |
Leader | -0.056 |
ten | -0.055 |
Token | N |
Token ID | 45 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
arnaev | +0.017 |
rompt | +0.017 |
psey | +0.016 |
ysis | +0.016 |
� | +0.015 |
Neg logit contributions | |
azel | -0.018 |
Devil | -0.017 |
igg | -0.016 |
Leader | -0.016 |
ten | -0.016 |
Token | ). |
Token ID | 737 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
arnaev | +0.239 |
rompt | +0.234 |
psey | +0.224 |
ysis | +0.220 |
� | +0.211 |
Neg logit contributions | |
azel | -0.207 |
Devil | -0.185 |
igg | -0.178 |
Leader | -0.175 |
ten | -0.173 |
Token |
|
Token ID | 198 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
azel | +0.153 |
Devil | +0.136 |
igg | +0.131 |
Leader | +0.129 |
erad | +0.126 |
Neg logit contributions | |
arnaev | -0.179 |
rompt | -0.175 |
psey | -0.168 |
ysis | -0.165 |
� | -0.159 |
Token |
|
Token ID | 198 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
arnaev | +0.017 |
rompt | +0.017 |
psey | +0.016 |
ysis | +0.016 |
� | +0.015 |
Neg logit contributions | |
azel | -0.017 |
Devil | -0.015 |
igg | -0.014 |
Leader | -0.014 |
ten | -0.014 |
Token | The |
Token ID | 464 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
azel | +0.185 |
Devil | +0.165 |
igg | +0.159 |
Leader | +0.156 |
erad | +0.154 |
Neg logit contributions | |
arnaev | -0.209 |
rompt | -0.205 |
psey | -0.196 |
ysis | -0.193 |
� | -0.186 |
Token | occupational |
Token ID | 34266 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
arnaev | +0.047 |
rompt | +0.046 |
psey | +0.044 |
ysis | +0.043 |
� | +0.041 |
Neg logit contributions | |
azel | -0.037 |
Devil | -0.032 |
igg | -0.031 |
Leader | -0.031 |
ten | -0.030 |
Token | radiation |
Token ID | 11881 |
Feature activation | +9.92e-03 |
Pos logit contributions | |
arnaev | +0.106 |
rompt | +0.104 |
psey | +0.099 |
ysis | +0.097 |
� | +0.092 |
Neg logit contributions | |
azel | -0.109 |
Devil | -0.099 |
igg | -0.095 |
Leader | -0.094 |
ten | -0.092 |
Token | doses |
Token ID | 16376 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
arnaev | +0.007 |
rompt | +0.007 |
psey | +0.007 |
ysis | +0.007 |
� | +0.006 |
Neg logit contributions | |
azel | -0.007 |
Devil | -0.006 |
igg | -0.006 |
Leader | -0.006 |
ten | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
arnaev | +0.055 |
rompt | +0.054 |
psey | +0.051 |
ysis | +0.050 |
� | +0.048 |
Neg logit contributions | |
azel | -0.046 |
Devil | -0.041 |
igg | -0.040 |
Leader | -0.039 |
ten | -0.039 |
Token | ousse |
Token ID | 28396 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
azel | +0.134 |
Devil | +0.120 |
igg | +0.115 |
Leader | +0.114 |
erad | +0.112 |
Neg logit contributions | |
arnaev | -0.162 |
rompt | -0.159 |
psey | -0.152 |
ysis | -0.150 |
� | -0.143 |
Token | f |
Token ID | 69 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
arnaev | +0.507 |
rompt | +0.491 |
psey | +0.463 |
ysis | +0.451 |
VIDIA | +0.426 |
Neg logit contributions | |
azel | -0.796 |
Devil | -0.731 |
igg | -0.712 |
Leader | -0.703 |
ten | -0.696 |
Token | reported |
Token ID | 2098 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
arnaev | +0.279 |
rompt | +0.273 |
psey | +0.260 |
ysis | +0.255 |
� | +0.244 |
Neg logit contributions | |
azel | -0.285 |
Devil | -0.258 |
igg | -0.248 |
Leader | -0.245 |
ten | -0.242 |
Token | . |
Token ID | 13 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
arnaev | +0.068 |
rompt | +0.067 |
psey | +0.064 |
ysis | +0.063 |
� | +0.060 |
Neg logit contributions | |
azel | -0.061 |
Devil | -0.054 |
igg | -0.052 |
Leader | -0.052 |
ten | -0.051 |
Token | � |
Token ID | 564 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
arnaev | +0.032 |
rompt | +0.032 |
psey | +0.030 |
ysis | +0.030 |
� | +0.028 |
Neg logit contributions | |
azel | -0.030 |
Devil | -0.027 |
igg | -0.026 |
Leader | -0.025 |
ten | -0.025 |
Token | � |
Token ID | 250 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
arnaev | +0.074 |
rompt | +0.072 |
psey | +0.069 |
ysis | +0.067 |
� | +0.064 |
Neg logit contributions | |
azel | -0.084 |
Devil | -0.077 |
igg | -0.074 |
Leader | -0.073 |
ten | -0.072 |
Token | But |
Token ID | 1537 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
arnaev | +0.084 |
rompt | +0.082 |
psey | +0.078 |
ysis | +0.077 |
� | +0.073 |
Neg logit contributions | |
azel | -0.087 |
Devil | -0.079 |
igg | -0.076 |
Leader | -0.075 |
ten | -0.074 |
Token | there |
Token ID | 612 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
azel | +0.157 |
Devil | +0.141 |
igg | +0.136 |
Leader | +0.134 |
ten | +0.132 |
Neg logit contributions | |
arnaev | -0.171 |
rompt | -0.168 |
psey | -0.160 |
ysis | -0.157 |
� | -0.151 |
Token | currently |
Token ID | 3058 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
azel | +0.106 |
Devil | +0.096 |
igg | +0.092 |
Leader | +0.091 |
ten | +0.090 |
Neg logit contributions | |
arnaev | -0.106 |
rompt | -0.103 |
psey | -0.098 |
ysis | -0.097 |
� | -0.093 |
Token | are |
Token ID | 389 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
arnaev | +0.198 |
rompt | +0.194 |
psey | +0.185 |
ysis | +0.181 |
� | +0.173 |
Neg logit contributions | |
azel | -0.193 |
Devil | -0.174 |
igg | -0.167 |
Leader | -0.165 |
ten | -0.163 |
Token | nearly |
Token ID | 3016 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
azel | +0.240 |
Devil | +0.215 |
igg | +0.207 |
Leader | +0.204 |
ten | +0.200 |
Neg logit contributions | |
arnaev | -0.267 |
rompt | -0.262 |
psey | -0.251 |
ysis | -0.247 |
� | -0.237 |
Token | of |
Token ID | 286 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
arnaev | +0.059 |
rompt | +0.057 |
psey | +0.055 |
ysis | +0.054 |
� | +0.052 |
Neg logit contributions | |
azel | -0.044 |
Devil | -0.039 |
igg | -0.037 |
Leader | -0.036 |
ten | -0.036 |
Token | spending |
Token ID | 4581 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
arnaev | +0.229 |
rompt | +0.224 |
psey | +0.214 |
ysis | +0.210 |
� | +0.200 |
Neg logit contributions | |
azel | -0.223 |
Devil | -0.201 |
igg | -0.194 |
Leader | -0.191 |
ten | -0.188 |
Token | , |
Token ID | 11 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
arnaev | +0.227 |
rompt | +0.222 |
psey | +0.213 |
ysis | +0.209 |
� | +0.200 |
Neg logit contributions | |
azel | -0.195 |
Devil | -0.174 |
igg | -0.167 |
Leader | -0.165 |
ten | -0.162 |
Token | � |
Token ID | 447 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
arnaev | +0.199 |
rompt | +0.195 |
psey | +0.186 |
ysis | +0.182 |
� | +0.174 |
Neg logit contributions | |
azel | -0.194 |
Devil | -0.175 |
igg | -0.168 |
Leader | -0.166 |
ten | -0.164 |
Token | � |
Token ID | 251 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
azel | +0.208 |
Devil | +0.187 |
igg | +0.180 |
Leader | +0.178 |
ten | +0.176 |
Neg logit contributions | |
arnaev | -0.207 |
rompt | -0.202 |
psey | -0.193 |
ysis | -0.190 |
� | -0.182 |
Token | says |
Token ID | 1139 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
azel | +0.182 |
Devil | +0.163 |
igg | +0.157 |
Leader | +0.155 |
ten | +0.152 |
Neg logit contributions | |
arnaev | -0.198 |
rompt | -0.194 |
psey | -0.186 |
ysis | -0.182 |
� | -0.175 |
Token | one |
Token ID | 530 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
azel | +0.014 |
Devil | +0.013 |
igg | +0.012 |
Leader | +0.012 |
ten | +0.012 |
Neg logit contributions | |
arnaev | -0.017 |
rompt | -0.017 |
psey | -0.016 |
ysis | -0.016 |
� | -0.015 |
Token | government |
Token ID | 1230 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
arnaev | +0.130 |
rompt | +0.128 |
psey | +0.122 |
ysis | +0.120 |
� | +0.116 |
Neg logit contributions | |
azel | -0.105 |
Devil | -0.094 |
igg | -0.090 |
Leader | -0.089 |
ten | -0.087 |
Token | source |
Token ID | 2723 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
arnaev | +0.082 |
rompt | +0.080 |
psey | +0.077 |
ysis | +0.076 |
� | +0.073 |
Neg logit contributions | |
azel | -0.055 |
Devil | -0.048 |
igg | -0.046 |
Leader | -0.045 |
ten | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -9.76e-02 |
Pos logit contributions | |
arnaev | +0.231 |
rompt | +0.226 |
psey | +0.217 |
ysis | +0.213 |
� | +0.204 |
Neg logit contributions | |
azel | -0.200 |
Devil | -0.179 |
igg | -0.172 |
Leader | -0.170 |
ten | -0.167 |
Token | � |
Token ID | 564 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
azel | +0.070 |
Devil | +0.063 |
igg | +0.060 |
Leader | +0.059 |
ten | +0.059 |
Neg logit contributions | |
arnaev | -0.073 |
rompt | -0.072 |
psey | -0.068 |
ysis | -0.067 |
� | -0.064 |
Token | Institute |
Token ID | 5136 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
arnaev | +0.220 |
rompt | +0.215 |
psey | +0.206 |
ysis | +0.202 |
� | +0.193 |
Neg logit contributions | |
azel | -0.200 |
Devil | -0.179 |
igg | -0.173 |
Leader | -0.170 |
ten | -0.168 |
Token | , |
Token ID | 11 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
arnaev | +0.026 |
rompt | +0.026 |
psey | +0.025 |
ysis | +0.024 |
� | +0.023 |
Neg logit contributions | |
azel | -0.023 |
Devil | -0.021 |
igg | -0.020 |
Leader | -0.020 |
ten | -0.019 |
Token | where |
Token ID | 810 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
azel | +0.012 |
Devil | +0.011 |
igg | +0.010 |
Leader | +0.010 |
ten | +0.010 |
Neg logit contributions | |
arnaev | -0.013 |
rompt | -0.013 |
psey | -0.012 |
ysis | -0.012 |
� | -0.011 |
Token | Mel |
Token ID | 5616 |
Feature activation | -8.65e-02 |
Pos logit contributions | |
azel | +0.020 |
Devil | +0.018 |
igg | +0.018 |
Leader | +0.017 |
ten | +0.017 |
Neg logit contributions | |
arnaev | -0.022 |
rompt | -0.021 |
psey | -0.021 |
ysis | -0.020 |
� | -0.019 |
Token | ko |
Token ID | 7204 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
azel | +0.052 |
Devil | +0.046 |
igg | +0.043 |
Leader | +0.043 |
erad | +0.042 |
Neg logit contributions | |
arnaev | -0.075 |
rompt | -0.073 |
psey | -0.071 |
ysis | -0.069 |
� | -0.067 |
Token | is |
Token ID | 318 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
arnaev | +0.270 |
rompt | +0.265 |
psey | +0.253 |
ysis | +0.249 |
� | +0.238 |
Neg logit contributions | |
azel | -0.244 |
Devil | -0.219 |
igg | -0.210 |
Leader | -0.207 |
ten | -0.204 |
Token | an |
Token ID | 281 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
arnaev | +0.258 |
rompt | +0.253 |
psey | +0.242 |
ysis | +0.237 |
� | +0.227 |
Neg logit contributions | |
azel | -0.229 |
Devil | -0.205 |
igg | -0.197 |
Leader | -0.194 |
ten | -0.191 |
Token | associate |
Token ID | 11602 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
arnaev | +0.313 |
rompt | +0.306 |
psey | +0.294 |
ysis | +0.289 |
� | +0.278 |
Neg logit contributions | |
azel | -0.237 |
Devil | -0.210 |
igg | -0.201 |
Leader | -0.198 |
ten | -0.194 |
Token | faculty |
Token ID | 12829 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
azel | +0.054 |
Devil | +0.046 |
igg | +0.043 |
Leader | +0.042 |
ten | +0.041 |
Neg logit contributions | |
arnaev | -0.107 |
rompt | -0.106 |
psey | -0.102 |
ysis | -0.101 |
� | -0.097 |
Token | member |
Token ID | 2888 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
arnaev | +0.164 |
rompt | +0.161 |
psey | +0.154 |
ysis | +0.151 |
� | +0.145 |
Neg logit contributions | |
azel | -0.130 |
Devil | -0.115 |
igg | -0.111 |
Leader | -0.109 |
ten | -0.107 |
Token | and |
Token ID | 290 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
arnaev | +0.044 |
rompt | +0.043 |
psey | +0.042 |
ysis | +0.041 |
� | +0.039 |
Neg logit contributions | |
azel | -0.038 |
Devil | -0.034 |
igg | -0.033 |
Leader | -0.032 |
ten | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
arnaev | +0.284 |
rompt | +0.278 |
psey | +0.267 |
ysis | +0.262 |
� | +0.251 |
Neg logit contributions | |
azel | -0.235 |
Devil | -0.210 |
igg | -0.201 |
Leader | -0.199 |
ten | -0.195 |
Token | and |
Token ID | 290 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
arnaev | +0.126 |
rompt | +0.124 |
psey | +0.118 |
ysis | +0.116 |
� | +0.111 |
Neg logit contributions | |
azel | -0.123 |
Devil | -0.110 |
igg | -0.106 |
Leader | -0.105 |
ten | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
arnaev | +0.175 |
rompt | +0.171 |
psey | +0.163 |
ysis | +0.160 |
� | +0.153 |
Neg logit contributions | |
azel | -0.178 |
Devil | -0.161 |
igg | -0.155 |
Leader | -0.153 |
ten | -0.151 |
Token | Man |
Token ID | 1869 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
arnaev | +0.082 |
rompt | +0.080 |
psey | +0.076 |
ysis | +0.075 |
� | +0.072 |
Neg logit contributions | |
azel | -0.078 |
Devil | -0.070 |
igg | -0.067 |
Leader | -0.066 |
ten | -0.065 |
Token | Bor |
Token ID | 12182 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
azel | +0.129 |
Devil | +0.115 |
igg | +0.110 |
Leader | +0.109 |
ten | +0.107 |
Neg logit contributions | |
arnaev | -0.152 |
rompt | -0.149 |
psey | -0.143 |
ysis | -0.140 |
� | -0.135 |
Token | om |
Token ID | 296 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
azel | +0.046 |
Devil | +0.041 |
igg | +0.039 |
Leader | +0.039 |
erad | +0.038 |
Neg logit contributions | |
arnaev | -0.059 |
rompt | -0.058 |
psey | -0.055 |
ysis | -0.054 |
� | -0.052 |
Token | ir |
Token ID | 343 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
azel | +0.685 |
Devil | +0.597 |
Leader | +0.562 |
igg | +0.555 |
erad | +0.542 |
Neg logit contributions | |
arnaev | -1.220 |
rompt | -1.199 |
psey | -1.155 |
ysis | -1.147 |
� | -1.108 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
arnaev | +0.093 |
rompt | +0.091 |
psey | +0.087 |
ysis | +0.086 |
� | +0.082 |
Neg logit contributions | |
azel | -0.080 |
Devil | -0.071 |
igg | -0.068 |
Leader | -0.068 |
ten | -0.066 |
Token | son |
Token ID | 3367 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
arnaev | +0.125 |
rompt | +0.122 |
psey | +0.117 |
ysis | +0.115 |
� | +0.110 |
Neg logit contributions | |
azel | -0.106 |
Devil | -0.095 |
igg | -0.091 |
Leader | -0.090 |
ten | -0.089 |
Token | of |
Token ID | 286 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
azel | +0.113 |
Devil | +0.100 |
igg | +0.095 |
Leader | +0.094 |
ten | +0.092 |
Neg logit contributions | |
arnaev | -0.149 |
rompt | -0.146 |
psey | -0.140 |
ysis | -0.138 |
� | -0.132 |
Token | Den |
Token ID | 5601 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
arnaev | +0.237 |
rompt | +0.232 |
psey | +0.222 |
ysis | +0.218 |
� | +0.208 |
Neg logit contributions | |
azel | -0.228 |
Devil | -0.205 |
igg | -0.198 |
Leader | -0.195 |
ten | -0.192 |
Token | under |
Token ID | 739 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
azel | +0.205 |
Devil | +0.184 |
igg | +0.178 |
Leader | +0.175 |
ten | +0.172 |
Neg logit contributions | |
arnaev | -0.218 |
rompt | -0.214 |
psey | -0.205 |
ysis | -0.201 |
� | -0.193 |
Token | secretary |
Token ID | 7705 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
arnaev | +0.191 |
rompt | +0.187 |
psey | +0.179 |
ysis | +0.175 |
� | +0.168 |
Neg logit contributions | |
azel | -0.184 |
Devil | -0.165 |
igg | -0.159 |
Leader | -0.157 |
ten | -0.155 |
Token | Fer |
Token ID | 12880 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
arnaev | +0.071 |
rompt | +0.069 |
psey | +0.066 |
ysis | +0.065 |
� | +0.063 |
Neg logit contributions | |
azel | -0.059 |
Devil | -0.053 |
igg | -0.051 |
Leader | -0.050 |
ten | -0.049 |
Token | id |
Token ID | 312 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
azel | +0.304 |
Devil | +0.267 |
igg | +0.255 |
Leader | +0.252 |
erad | +0.247 |
Neg logit contributions | |
arnaev | -0.457 |
rompt | -0.447 |
psey | -0.431 |
ysis | -0.424 |
� | -0.408 |
Token | un |
Token ID | 403 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
azel | +0.138 |
Devil | +0.125 |
igg | +0.122 |
Leader | +0.121 |
ten | +0.119 |
Neg logit contributions | |
arnaev | -0.103 |
rompt | -0.101 |
psey | -0.095 |
ysis | -0.093 |
� | -0.088 |
Token | Sin |
Token ID | 10884 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
azel | +0.833 |
Devil | +0.746 |
igg | +0.724 |
Leader | +0.718 |
erad | +0.704 |
Neg logit contributions | |
arnaev | -0.838 |
rompt | -0.823 |
psey | -0.785 |
ysis | -0.775 |
� | -0.742 |
Token | irl |
Token ID | 1901 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
azel | +0.696 |
Devil | +0.617 |
Leader | +0.590 |
igg | +0.581 |
erad | +0.569 |
Neg logit contributions | |
arnaev | -1.039 |
rompt | -1.026 |
psey | -0.979 |
ysis | -0.970 |
� | -0.928 |
Token | i |
Token ID | 72 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
arnaev | +0.092 |
rompt | +0.090 |
psey | +0.086 |
ysis | +0.085 |
� | +0.081 |
Neg logit contributions | |
azel | -0.087 |
Devil | -0.078 |
igg | -0.075 |
Leader | -0.074 |
ten | -0.073 |
Token | oglu |
Token ID | 49006 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
azel | +0.261 |
Devil | +0.222 |
igg | +0.209 |
Leader | +0.206 |
erad | +0.201 |
Neg logit contributions | |
arnaev | -0.514 |
rompt | -0.507 |
psey | -0.489 |
ysis | -0.485 |
� | -0.468 |
Token | , |
Token ID | 11 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
azel | +0.066 |
Devil | +0.059 |
igg | +0.057 |
Leader | +0.056 |
ten | +0.055 |
Neg logit contributions | |
arnaev | -0.073 |
rompt | -0.072 |
psey | -0.069 |
ysis | -0.067 |
� | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
azel | +0.107 |
Devil | +0.095 |
igg | +0.092 |
Leader | +0.091 |
ten | +0.089 |
Neg logit contributions | |
arnaev | -0.118 |
rompt | -0.116 |
psey | -0.111 |
ysis | -0.109 |
� | -0.104 |
Token | — |
Token ID | 851 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
azel | +0.205 |
Devil | +0.184 |
igg | +0.177 |
Leader | +0.175 |
ten | +0.171 |
Neg logit contributions | |
arnaev | -0.233 |
rompt | -0.229 |
psey | -0.219 |
ysis | -0.215 |
� | -0.207 |
Token | And |
Token ID | 843 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
arnaev | +0.368 |
rompt | +0.360 |
psey | +0.344 |
ysis | +0.338 |
� | +0.322 |
Neg logit contributions | |
azel | -0.349 |
Devil | -0.314 |
igg | -0.302 |
Leader | -0.298 |
ten | -0.294 |
Token | alus |
Token ID | 46781 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
arnaev | +0.472 |
rompt | +0.465 |
psey | +0.450 |
ysis | +0.445 |
� | +0.431 |
Neg logit contributions | |
azel | -0.170 |
Devil | -0.139 |
igg | -0.129 |
Leader | -0.125 |
ten | -0.121 |
Token | ia |
Token ID | 544 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
arnaev | +0.206 |
rompt | +0.202 |
psey | +0.195 |
ysis | +0.192 |
� | +0.185 |
Neg logit contributions | |
azel | -0.131 |
Devil | -0.114 |
igg | -0.109 |
Leader | -0.107 |
ten | -0.105 |
Token | , |
Token ID | 11 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
arnaev | +0.150 |
rompt | +0.147 |
psey | +0.140 |
ysis | +0.138 |
� | +0.133 |
Neg logit contributions | |
azel | -0.124 |
Devil | -0.110 |
igg | -0.106 |
Leader | -0.104 |
ten | -0.103 |
Token | Ast |
Token ID | 8304 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
arnaev | +0.429 |
rompt | +0.419 |
psey | +0.401 |
ysis | +0.393 |
VIDIA | +0.376 |
Neg logit contributions | |
azel | -0.400 |
Devil | -0.360 |
igg | -0.346 |
Leader | -0.342 |
ten | -0.337 |
Token | ur |
Token ID | 333 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
azel | +1.039 |
Devil | +0.963 |
Leader | +0.933 |
igg | +0.929 |
Perspective | +0.918 |
Neg logit contributions | |
arnaev | -0.581 |
rompt | -0.567 |
psey | -0.526 |
ysis | -0.518 |
� | -0.484 |
Token | ias |
Token ID | 4448 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
azel | +0.209 |
Devil | +0.181 |
igg | +0.170 |
Leader | +0.169 |
erad | +0.164 |
Neg logit contributions | |
arnaev | -0.369 |
rompt | -0.364 |
psey | -0.351 |
ysis | -0.347 |
� | -0.334 |
Token | , |
Token ID | 11 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
arnaev | +0.213 |
rompt | +0.209 |
psey | +0.200 |
ysis | +0.197 |
� | +0.189 |
Neg logit contributions | |
azel | -0.177 |
Devil | -0.157 |
igg | -0.151 |
Leader | -0.149 |
ten | -0.146 |
Token | the |
Token ID | 262 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
arnaev | +0.449 |
rompt | +0.438 |
psey | +0.419 |
ysis | +0.411 |
VIDIA | +0.393 |
Neg logit contributions | |
azel | -0.423 |
Devil | -0.381 |
igg | -0.366 |
Leader | -0.361 |
ten | -0.356 |
Token | Bas |
Token ID | 6455 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
arnaev | +0.417 |
rompt | +0.407 |
psey | +0.389 |
ysis | +0.382 |
� | +0.365 |
Neg logit contributions | |
azel | -0.387 |
Devil | -0.349 |
igg | -0.335 |
Leader | -0.330 |
ten | -0.326 |
Token | Earth |
Token ID | 3668 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
azel | +0.257 |
Devil | +0.227 |
igg | +0.220 |
Leader | +0.217 |
ten | +0.213 |
Neg logit contributions | |
arnaev | -0.293 |
rompt | -0.287 |
psey | -0.273 |
ysis | -0.271 |
� | -0.260 |
Token | takes |
Token ID | 2753 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
azel | +0.063 |
Devil | +0.056 |
igg | +0.054 |
Leader | +0.053 |
ten | +0.053 |
Neg logit contributions | |
arnaev | -0.071 |
rompt | -0.070 |
psey | -0.067 |
ysis | -0.066 |
� | -0.063 |
Token | about |
Token ID | 546 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
azel | +0.160 |
Devil | +0.143 |
igg | +0.138 |
Leader | +0.137 |
ten | +0.134 |
Neg logit contributions | |
arnaev | -0.169 |
rompt | -0.165 |
psey | -0.157 |
ysis | -0.155 |
� | -0.149 |
Token | 365 |
Token ID | 21268 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
azel | +0.203 |
Devil | +0.181 |
igg | +0.175 |
Leader | +0.173 |
ten | +0.169 |
Neg logit contributions | |
arnaev | -0.221 |
rompt | -0.217 |
psey | -0.207 |
ysis | -0.204 |
� | -0.196 |
Token | days |
Token ID | 1528 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
azel | +0.650 |
Devil | +0.577 |
igg | +0.554 |
Leader | +0.552 |
ten | +0.539 |
Neg logit contributions | |
arnaev | -0.766 |
rompt | -0.751 |
psey | -0.721 |
ysis | -0.711 |
� | -0.684 |
Token | to |
Token ID | 284 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
azel | +0.330 |
Devil | +0.296 |
igg | +0.285 |
Leader | +0.282 |
ten | +0.276 |
Neg logit contributions | |
arnaev | -0.349 |
rompt | -0.342 |
psey | -0.326 |
ysis | -0.322 |
� | -0.309 |
Token | orbit |
Token ID | 13066 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
azel | +0.773 |
Devil | +0.685 |
igg | +0.663 |
Leader | +0.660 |
ten | +0.647 |
Neg logit contributions | |
arnaev | -0.830 |
rompt | -0.821 |
psey | -0.785 |
ysis | -0.771 |
� | -0.741 |
Token | the |
Token ID | 262 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
azel | +0.628 |
Devil | +0.560 |
igg | +0.541 |
Leader | +0.539 |
ten | +0.527 |
Neg logit contributions | |
arnaev | -0.668 |
rompt | -0.656 |
psey | -0.627 |
ysis | -0.617 |
� | -0.592 |
Token | sun |
Token ID | 4252 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
azel | +0.432 |
Devil | +0.389 |
igg | +0.378 |
Leader | +0.376 |
ten | +0.370 |
Neg logit contributions | |
arnaev | -0.353 |
rompt | -0.345 |
psey | -0.328 |
ysis | -0.322 |
� | -0.306 |
Token | . |
Token ID | 13 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
azel | +0.247 |
Devil | +0.220 |
igg | +0.212 |
Leader | +0.209 |
ten | +0.205 |
Neg logit contributions | |
arnaev | -0.283 |
rompt | -0.277 |
psey | -0.265 |
ysis | -0.262 |
� | -0.251 |
Token | The |
Token ID | 383 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
azel | +0.249 |
Devil | +0.220 |
igg | +0.213 |
Leader | +0.210 |
erad | +0.207 |
Neg logit contributions | |
arnaev | -0.281 |
rompt | -0.276 |
psey | -0.262 |
ysis | -0.260 |
� | -0.250 |
Token | the |
Token ID | 262 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
arnaev | +0.022 |
rompt | +0.022 |
psey | +0.021 |
ysis | +0.020 |
� | +0.019 |
Neg logit contributions | |
azel | -0.021 |
Devil | -0.019 |
igg | -0.019 |
Leader | -0.018 |
ten | -0.018 |
Token | single |
Token ID | 2060 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
azel | +0.102 |
Devil | +0.091 |
igg | +0.088 |
Leader | +0.087 |
ten | +0.086 |
Neg logit contributions | |
arnaev | -0.108 |
rompt | -0.106 |
psey | -0.101 |
ysis | -0.099 |
� | -0.095 |
Token | ex |
Token ID | 409 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
azel | +0.030 |
Devil | +0.027 |
igg | +0.026 |
Leader | +0.026 |
ten | +0.025 |
Neg logit contributions | |
arnaev | -0.034 |
rompt | -0.033 |
psey | -0.032 |
ysis | -0.031 |
� | -0.030 |
Token | uded |
Token ID | 19289 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
arnaev | +0.055 |
rompt | +0.054 |
psey | +0.051 |
ysis | +0.050 |
� | +0.048 |
Neg logit contributions | |
azel | -0.070 |
Devil | -0.064 |
igg | -0.062 |
Leader | -0.061 |
ten | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
azel | +0.047 |
Devil | +0.042 |
igg | +0.041 |
Leader | +0.040 |
ten | +0.040 |
Neg logit contributions | |
arnaev | -0.049 |
rompt | -0.048 |
psey | -0.046 |
ysis | -0.045 |
� | -0.043 |
Token | Saturday |
Token ID | 3909 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
azel | +0.068 |
Devil | +0.061 |
igg | +0.058 |
Leader | +0.058 |
ten | +0.057 |
Neg logit contributions | |
arnaev | -0.074 |
rompt | -0.073 |
psey | -0.070 |
ysis | -0.068 |
� | -0.065 |
Token | - |
Token ID | 12 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
azel | +0.729 |
Devil | +0.642 |
igg | +0.617 |
Leader | +0.613 |
ten | +0.599 |
Neg logit contributions | |
arnaev | -0.917 |
rompt | -0.903 |
psey | -0.861 |
ysis | -0.850 |
� | -0.820 |
Token | morning |
Token ID | 43911 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
arnaev | +0.022 |
rompt | +0.021 |
psey | +0.020 |
ysis | +0.020 |
� | +0.019 |
Neg logit contributions | |
azel | -0.019 |
Devil | -0.017 |
igg | -0.016 |
Leader | -0.016 |
erad | -0.016 |
Token | kids |
Token ID | 3988 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
arnaev | +0.033 |
rompt | +0.032 |
psey | +0.031 |
ysis | +0.030 |
� | +0.029 |
Neg logit contributions | |
azel | -0.030 |
Devil | -0.027 |
igg | -0.026 |
Leader | -0.026 |
ten | -0.025 |
Token | � |
Token ID | 447 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
azel | +0.166 |
Devil | +0.150 |
igg | +0.145 |
Leader | +0.143 |
ten | +0.141 |
Neg logit contributions | |
arnaev | -0.152 |
rompt | -0.149 |
psey | -0.141 |
ysis | -0.139 |
� | -0.132 |
Token | � |
Token ID | 247 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
azel | +0.229 |
Devil | +0.209 |
igg | +0.202 |
Leader | +0.200 |
ten | +0.198 |
Neg logit contributions | |
arnaev | -0.180 |
rompt | -0.175 |
psey | -0.166 |
ysis | -0.163 |
� | -0.155 |