Token | the |
Token ID | 262 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
behavi | +0.276 |
subtitles | +0.275 |
Blu | +0.274 |
ophy | +0.267 |
AU | +0.263 |
Neg logit contributions | |
anmar | -0.341 |
eters | -0.297 |
ativity | -0.285 |
warts | -0.273 |
andum | -0.273 |
Token | story |
Token ID | 1621 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
behavi | +0.390 |
subtitles | +0.386 |
Blu | +0.383 |
ophy | +0.376 |
AU | +0.371 |
Neg logit contributions | |
anmar | -0.487 |
eters | -0.425 |
ativity | -0.407 |
andum | -0.391 |
warts | -0.390 |
Token | CLICK |
Token ID | 49583 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
anmar | +0.509 |
eters | +0.448 |
ativity | +0.430 |
andum | +0.415 |
warts | +0.414 |
Neg logit contributions | |
behavi | -0.345 |
subtitles | -0.345 |
Blu | -0.342 |
ophy | -0.333 |
AU | -0.328 |
Token | HERE |
Token ID | 15698 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
subtitles | +2.259 |
Blu | +2.247 |
behavi | +2.217 |
AU | +2.202 |
ophy | +2.145 |
Neg logit contributions | |
anmar | -2.472 |
eters | -2.084 |
ativity | -2.065 |
warts | -1.941 |
andum | -1.928 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
subtitles | +1.422 |
Blu | +1.410 |
behavi | +1.407 |
AU | +1.366 |
ophy | +1.351 |
Neg logit contributions | |
anmar | -2.728 |
eters | -2.408 |
ativity | -2.337 |
warts | -2.260 |
andum | -2.238 |
Token | 0 |
Token ID | 15 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
anmar | +0.622 |
eters | +0.553 |
ativity | +0.532 |
warts | +0.515 |
andum | +0.514 |
Neg logit contributions | |
behavi | -0.365 |
subtitles | -0.361 |
Blu | -0.358 |
ophy | -0.348 |
AU | -0.341 |
Token | Drunk |
Token ID | 42739 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
anmar | +8.999 |
eters | +7.725 |
ativity | +7.648 |
warts | +7.116 |
andum | +7.113 |
Neg logit contributions | |
behavi | -7.221 |
subtitles | -7.027 |
ophy | -6.684 |
puzz | -6.628 |
Blu | -6.567 |
Token | driver |
Token ID | 4639 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Blu | +0.984 |
subtitles | +0.978 |
behavi | +0.972 |
ophy | +0.940 |
AU | +0.929 |
Neg logit contributions | |
anmar | -1.347 |
eters | -1.171 |
ativity | -1.129 |
�� | -1.105 |
warts | -1.104 |
Token | who |
Token ID | 508 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
anmar | +1.013 |
eters | +0.882 |
ativity | +0.841 |
warts | +0.805 |
andum | +0.804 |
Neg logit contributions | |
behavi | -0.887 |
subtitles | -0.878 |
Blu | -0.871 |
ophy | -0.857 |
AU | -0.844 |
Token | killed |
Token ID | 2923 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
anmar | +0.401 |
eters | +0.353 |
ativity | +0.337 |
warts | +0.324 |
andum | +0.324 |
Neg logit contributions | |
behavi | -0.304 |
subtitles | -0.300 |
Blu | -0.298 |
ophy | -0.292 |
AU | -0.287 |
Token | two |
Token ID | 734 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
anmar | +0.879 |
eters | +0.767 |
ativity | +0.734 |
andum | +0.704 |
warts | +0.704 |
Neg logit contributions | |
behavi | -0.713 |
subtitles | -0.707 |
Blu | -0.702 |
ophy | -0.688 |
AU | -0.678 |
Token | big |
Token ID | 1263 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
anmar | +0.694 |
eters | +0.608 |
ativity | +0.583 |
warts | +0.560 |
andum | +0.558 |
Neg logit contributions | |
behavi | -0.528 |
subtitles | -0.517 |
Blu | -0.510 |
ophy | -0.504 |
AU | -0.497 |
Token | bird |
Token ID | 6512 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
anmar | +1.928 |
eters | +1.689 |
ativity | +1.613 |
warts | +1.573 |
andum | +1.540 |
Neg logit contributions | |
behavi | -1.469 |
subtitles | -1.436 |
ophy | -1.404 |
Blu | -1.398 |
AU | -1.368 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
anmar | +1.489 |
eters | +1.319 |
ativity | +1.268 |
warts | +1.227 |
andum | +1.220 |
Neg logit contributions | |
behavi | -0.977 |
subtitles | -0.967 |
Blu | -0.955 |
ophy | -0.941 |
AU | -0.918 |
Token | Home |
Token ID | 5995 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
anmar | +0.792 |
eters | +0.698 |
ativity | +0.667 |
andum | +0.643 |
warts | +0.641 |
Neg logit contributions | |
behavi | -0.608 |
subtitles | -0.595 |
Blu | -0.586 |
ophy | -0.581 |
AU | -0.569 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
anmar | +2.914 |
eters | +2.539 |
ativity | +2.442 |
warts | +2.336 |
andum | +2.327 |
Neg logit contributions | |
behavi | -2.180 |
subtitles | -2.150 |
Blu | -2.119 |
ophy | -2.095 |
AU | -2.048 |
Token | 0 |
Token ID | 15 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
anmar | +1.020 |
eters | +0.907 |
ativity | +0.872 |
warts | +0.844 |
andum | +0.842 |
Neg logit contributions | |
behavi | -0.600 |
subtitles | -0.592 |
Blu | -0.586 |
ophy | -0.570 |
AU | -0.557 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
anmar | +8.798 |
eters | +7.532 |
ativity | +7.471 |
warts | +6.944 |
andum | +6.938 |
Neg logit contributions | |
behavi | -7.179 |
subtitles | -6.992 |
ophy | -6.666 |
puzz | -6.614 |
Blu | -6.546 |
Token |
|
Token ID | 198 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
anmar | +0.798 |
eters | +0.720 |
ativity | +0.683 |
warts | +0.660 |
felt | +0.660 |
Neg logit contributions | |
behavi | -0.701 |
subtitles | -0.639 |
ophy | -0.624 |
Blu | -0.617 |
puzz | -0.613 |
Token | Don |
Token ID | 3987 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
anmar | +2.011 |
eters | +1.798 |
ativity | +1.734 |
warts | +1.679 |
andum | +1.664 |
Neg logit contributions | |
behavi | -1.253 |
subtitles | -1.192 |
Blu | -1.162 |
ophy | -1.144 |
puzz | -1.111 |
Token | � |
Token ID | 447 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
anmar | +0.442 |
eters | +0.377 |
ativity | +0.357 |
warts | +0.343 |
andum | +0.342 |
Neg logit contributions | |
subtitles | -0.439 |
Blu | -0.438 |
behavi | -0.435 |
ophy | -0.426 |
AU | -0.421 |
Token | � |
Token ID | 247 |
Feature activation | -1.79e-05 |
Pos logit contributions | |
subtitles | +1.176 |
Blu | +1.165 |
behavi | +1.165 |
ophy | +1.148 |
AU | +1.137 |
Neg logit contributions | |
anmar | -1.218 |
eters | -1.052 |
ativity | -1.002 |
warts | -0.949 |
andum | -0.943 |
Token | sight |
Token ID | 6504 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
anmar | +1.091 |
eters | +0.957 |
ativity | +0.919 |
andum | +0.883 |
warts | +0.883 |
Neg logit contributions | |
behavi | -0.798 |
subtitles | -0.792 |
Blu | -0.786 |
ophy | -0.769 |
AU | -0.757 |
Token | does |
Token ID | 857 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
anmar | +1.898 |
eters | +1.677 |
ativity | +1.608 |
warts | +1.543 |
andum | +1.538 |
Neg logit contributions | |
behavi | -1.387 |
subtitles | -1.371 |
Blu | -1.359 |
ophy | -1.343 |
AU | -1.315 |
Token | not |
Token ID | 407 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
anmar | +2.397 |
eters | +1.999 |
ativity | +1.888 |
warts | +1.776 |
andum | +1.768 |
Neg logit contributions | |
behavi | -3.354 |
subtitles | -3.331 |
Blu | -3.304 |
ophy | -3.269 |
AU | -3.235 |
Token | mean |
Token ID | 1612 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
anmar | +2.768 |
eters | +2.441 |
ativity | +2.364 |
warts | +2.273 |
andum | +2.249 |
Neg logit contributions | |
behavi | -2.302 |
subtitles | -2.240 |
Blu | -2.224 |
ophy | -2.223 |
AU | -2.177 |
Token | out |
Token ID | 503 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
anmar | +4.412 |
eters | +3.812 |
ativity | +3.620 |
warts | +3.517 |
andum | +3.465 |
Neg logit contributions | |
behavi | -4.359 |
subtitles | -4.251 |
ophy | -4.231 |
Blu | -4.156 |
AU | -4.142 |
Token | of |
Token ID | 286 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
anmar | +5.053 |
eters | +4.430 |
ativity | +4.306 |
warts | +4.136 |
andum | +4.078 |
Neg logit contributions | |
behavi | -3.715 |
subtitles | -3.704 |
Blu | -3.654 |
ophy | -3.552 |
AU | -3.522 |
Token | the |
Token ID | 262 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
anmar | +7.451 |
eters | +6.288 |
ativity | +6.050 |
felt | +5.725 |
warts | +5.665 |
Neg logit contributions | |
behavi | -7.637 |
AU | -7.399 |
subtitles | -7.383 |
Blu | -7.326 |
ophy | -7.282 |
Token | ocean |
Token ID | 9151 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
anmar | +4.284 |
eters | +3.758 |
ativity | +3.637 |
andum | +3.444 |
warts | +3.441 |
Neg logit contributions | |
behavi | -3.065 |
subtitles | -2.972 |
Blu | -2.950 |
ophy | -2.900 |
AU | -2.874 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
anmar | +2.934 |
eters | +2.610 |
ativity | +2.516 |
warts | +2.430 |
andum | +2.423 |
Neg logit contributions | |
behavi | -1.688 |
subtitles | -1.675 |
Blu | -1.660 |
ophy | -1.620 |
AU | -1.587 |
Token | Life |
Token ID | 5155 |
Feature activation | -9.32e-03 |
Pos logit contributions | |
anmar | +0.556 |
eters | +0.488 |
ativity | +0.466 |
andum | +0.448 |
warts | +0.448 |
Neg logit contributions | |
behavi | -0.448 |
subtitles | -0.439 |
Blu | -0.431 |
ophy | -0.428 |
AU | -0.418 |
Token | in |
Token ID | 287 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
behavi | +0.034 |
subtitles | +0.034 |
Blu | +0.033 |
ophy | +0.033 |
AU | +0.032 |
Neg logit contributions | |
anmar | -0.044 |
eters | -0.038 |
ativity | -0.036 |
andum | -0.035 |
warts | -0.035 |
Token | Legislative |
Token ID | 30356 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
anmar | +1.412 |
eters | +1.233 |
ativity | +1.180 |
warts | +1.135 |
andum | +1.132 |
Neg logit contributions | |
behavi | -1.127 |
subtitles | -1.111 |
Blu | -1.104 |
ophy | -1.077 |
AU | -1.060 |
Token | Assembly |
Token ID | 10006 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
anmar | +1.402 |
eters | +1.220 |
ativity | +1.167 |
andum | +1.119 |
warts | +1.119 |
Neg logit contributions | |
behavi | -1.170 |
subtitles | -1.162 |
Blu | -1.154 |
ophy | -1.130 |
AU | -1.113 |
Token | ( |
Token ID | 357 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
anmar | +1.089 |
eters | +0.961 |
ativity | +0.923 |
warts | +0.889 |
andum | +0.889 |
Neg logit contributions | |
behavi | -0.727 |
subtitles | -0.721 |
Blu | -0.716 |
ophy | -0.698 |
AU | -0.687 |
Token | the |
Token ID | 1169 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
anmar | +0.860 |
eters | +0.757 |
ativity | +0.727 |
warts | +0.701 |
andum | +0.700 |
Neg logit contributions | |
behavi | -0.592 |
subtitles | -0.587 |
Blu | -0.582 |
ophy | -0.569 |
AU | -0.558 |
Token | House |
Token ID | 2097 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
anmar | +2.275 |
eters | +1.972 |
ativity | +1.888 |
warts | +1.817 |
andum | +1.814 |
Neg logit contributions | |
behavi | -1.895 |
subtitles | -1.857 |
Blu | -1.844 |
ophy | -1.801 |
AU | -1.769 |
Token | of |
Token ID | 286 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
anmar | +0.964 |
eters | +0.854 |
ativity | +0.818 |
andum | +0.797 |
warts | +0.793 |
Neg logit contributions | |
Blu | -0.564 |
subtitles | -0.564 |
behavi | -0.558 |
ophy | -0.552 |
AU | -0.541 |
Token | Assembly |
Token ID | 10006 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
anmar | +6.474 |
eters | +5.631 |
ativity | +5.164 |
warts | +5.077 |
andum | +4.910 |
Neg logit contributions | |
behavi | -7.796 |
subtitles | -7.420 |
Blu | -7.233 |
puzz | -7.170 |
OVA | -7.139 |
Token | in |
Token ID | 287 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
anmar | +3.978 |
eters | +3.484 |
ativity | +3.329 |
warts | +3.189 |
andum | +3.162 |
Neg logit contributions | |
behavi | -3.414 |
subtitles | -3.317 |
Blu | -3.278 |
ophy | -3.200 |
puzz | -3.176 |
Token | South |
Token ID | 2520 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
anmar | +2.945 |
eters | +2.555 |
ativity | +2.450 |
warts | +2.346 |
andum | +2.335 |
Neg logit contributions | |
behavi | -2.445 |
subtitles | -2.379 |
Blu | -2.374 |
ophy | -2.322 |
AU | -2.280 |
Token | Australia |
Token ID | 4505 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
anmar | +0.349 |
eters | +0.305 |
ativity | +0.292 |
andum | +0.282 |
warts | +0.281 |
Neg logit contributions | |
subtitles | -0.275 |
Blu | -0.273 |
behavi | -0.273 |
ophy | -0.267 |
AU | -0.264 |
Token | and |
Token ID | 290 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
anmar | +0.595 |
eters | +0.519 |
ativity | +0.498 |
andum | +0.480 |
warts | +0.478 |
Neg logit contributions | |
subtitles | -0.454 |
behavi | -0.453 |
Blu | -0.451 |
ophy | -0.441 |
AU | -0.434 |
Token | cl |
Token ID | 565 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
anmar | +0.870 |
eters | +0.763 |
ativity | +0.739 |
andum | +0.712 |
warts | +0.708 |
Neg logit contributions | |
subtitles | -0.571 |
Blu | -0.569 |
behavi | -0.569 |
ophy | -0.556 |
AU | -0.548 |
Token | j |
Token ID | 73 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
anmar | +2.505 |
eters | +2.192 |
ativity | +2.067 |
warts | +2.001 |
andum | +1.982 |
Neg logit contributions | |
behavi | -2.580 |
subtitles | -2.448 |
Blu | -2.433 |
ophy | -2.339 |
AU | -2.332 |
Token | and |
Token ID | 290 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
anmar | +6.239 |
eters | +5.765 |
ativity | +5.364 |
warts | +5.052 |
andum | +5.039 |
Neg logit contributions | |
behavi | -5.959 |
Blu | -5.680 |
subtitles | -5.634 |
AU | -5.552 |
ophy | -5.538 |
Token | build |
Token ID | 1382 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
anmar | +0.714 |
eters | +0.629 |
ativity | +0.603 |
warts | +0.580 |
andum | +0.580 |
Neg logit contributions | |
behavi | -0.508 |
subtitles | -0.503 |
Blu | -0.499 |
ophy | -0.489 |
AU | -0.482 |
Token | . |
Token ID | 13 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
anmar | +1.758 |
eters | +1.572 |
ativity | +1.485 |
warts | +1.453 |
andum | +1.441 |
Neg logit contributions | |
behavi | -1.129 |
subtitles | -1.067 |
Blu | -1.047 |
ophy | -1.041 |
puzz | -1.009 |
Token | boot |
Token ID | 18769 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
anmar | +2.326 |
eters | +2.062 |
ativity | +1.958 |
warts | +1.921 |
felt | +1.891 |
Neg logit contributions | |
behavi | -1.556 |
subtitles | -1.482 |
Blu | -1.447 |
ophy | -1.409 |
AU | -1.384 |
Token | files |
Token ID | 3696 |
Feature activation | +2.96e-04 |
Pos logit contributions | |
anmar | +7.082 |
eters | +6.679 |
ativity | +6.094 |
warts | +5.828 |
felt | +5.700 |
Neg logit contributions | |
behavi | -6.437 |
Blu | -6.174 |
subtitles | -6.052 |
AU | -6.051 |
ophy | -6.050 |
Token | , |
Token ID | 11 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
anmar | +0.001 |
eters | +0.001 |
ativity | +0.001 |
andum | +0.001 |
warts | +0.001 |
Neg logit contributions | |
behavi | -0.001 |
subtitles | -0.001 |
Blu | -0.001 |
ophy | -0.001 |
AU | -0.001 |
Token | splits |
Token ID | 30778 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
behavi | +0.367 |
subtitles | +0.366 |
Blu | +0.363 |
ophy | +0.355 |
AU | +0.349 |
Neg logit contributions | |
anmar | -0.467 |
eters | -0.407 |
ativity | -0.390 |
andum | -0.375 |
warts | -0.374 |
Token | each |
Token ID | 1123 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
subtitles | +2.448 |
Blu | +2.435 |
behavi | +2.378 |
ophy | +2.346 |
puzz | +2.277 |
Neg logit contributions | |
anmar | -4.180 |
eters | -3.628 |
ativity | -3.544 |
andum | -3.457 |
�� | -3.453 |
Token | file |
Token ID | 2393 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
subtitles | +1.107 |
behavi | +1.104 |
Blu | +1.099 |
ophy | +1.072 |
AU | +1.054 |
Neg logit contributions | |
anmar | -1.401 |
eters | -1.215 |
ativity | -1.166 |
warts | -1.121 |
andum | -1.121 |
Token | 20 |
Token ID | 1160 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
anmar | +3.068 |
eters | +2.670 |
ativity | +2.521 |
felt | +2.418 |
andum | +2.402 |
Neg logit contributions | |
behavi | -2.814 |
subtitles | -2.670 |
ophy | -2.631 |
Blu | -2.614 |
AU | -2.565 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
anmar | +2.908 |
eters | +2.552 |
ativity | +2.449 |
warts | +2.354 |
andum | +2.352 |
Neg logit contributions | |
behavi | -2.126 |
subtitles | -2.099 |
Blu | -2.075 |
ophy | -2.042 |
AU | -2.005 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
anmar | +4.781 |
eters | +4.080 |
ativity | +3.815 |
felt | +3.617 |
warts | +3.602 |
Neg logit contributions | |
behavi | -6.040 |
subtitles | -5.655 |
ophy | -5.571 |
AU | -5.527 |
Blu | -5.510 |
Token |
|
Token ID | 198 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
anmar | +0.949 |
eters | +0.840 |
ativity | +0.808 |
andum | +0.779 |
warts | +0.778 |
Neg logit contributions | |
behavi | -0.619 |
subtitles | -0.610 |
Blu | -0.603 |
ophy | -0.591 |
AU | -0.580 |
Token |
|
Token ID | 198 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
anmar | +2.431 |
eters | +2.182 |
ativity | +2.056 |
warts | +2.000 |
felt | +1.998 |
Neg logit contributions | |
behavi | -2.142 |
subtitles | -1.996 |
ophy | -1.942 |
Blu | -1.927 |
puzz | -1.908 |
Token | by |
Token ID | 1525 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
anmar | +3.441 |
eters | +3.077 |
ativity | +2.940 |
warts | +2.870 |
andum | +2.849 |
Neg logit contributions | |
behavi | -2.143 |
subtitles | -2.060 |
Blu | -2.026 |
ophy | -1.964 |
puzz | -1.910 |
Token | Comp |
Token ID | 3082 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
anmar | +7.918 |
eters | +7.011 |
ativity | +6.590 |
andum | +6.405 |
warts | +6.400 |
Neg logit contributions | |
behavi | -5.687 |
subtitles | -5.415 |
AU | -5.217 |
ophy | -5.199 |
Blu | -5.160 |
Token | assion |
Token ID | 11857 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
anmar | +0.376 |
eters | +0.319 |
ativity | +0.303 |
warts | +0.289 |
andum | +0.287 |
Neg logit contributions | |
behavi | -0.415 |
subtitles | -0.415 |
Blu | -0.415 |
ophy | -0.408 |
AU | -0.403 |
Token | Over |
Token ID | 3827 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
Blu | +1.314 |
subtitles | +1.296 |
ophy | +1.292 |
behavi | +1.286 |
AU | +1.257 |
Neg logit contributions | |
anmar | -1.362 |
eters | -1.170 |
ativity | -1.102 |
�� | -1.060 |
warts | -1.058 |
Token | Killing |
Token ID | 25536 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
anmar | +2.048 |
eters | +1.832 |
ativity | +1.765 |
warts | +1.710 |
andum | +1.708 |
Neg logit contributions | |
behavi | -1.033 |
subtitles | -1.028 |
Blu | -1.022 |
ophy | -0.990 |
AU | -0.967 |
Token | Staff |
Token ID | 9983 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
anmar | +0.679 |
eters | +0.598 |
ativity | +0.574 |
warts | +0.552 |
andum | +0.552 |
Neg logit contributions | |
behavi | -0.474 |
subtitles | -0.471 |
Blu | -0.467 |
ophy | -0.456 |
AU | -0.449 |
Token | league |
Token ID | 4652 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Blu | +1.170 |
subtitles | +1.160 |
behavi | +1.147 |
ophy | +1.140 |
AU | +1.103 |
Neg logit contributions | |
anmar | -1.746 |
eters | -1.542 |
ativity | -1.488 |
warts | -1.431 |
andum | -1.424 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
subtitles | +0.860 |
behavi | +0.858 |
Blu | +0.857 |
ophy | +0.834 |
AU | +0.818 |
Neg logit contributions | |
anmar | -1.324 |
eters | -1.162 |
ativity | -1.116 |
warts | -1.079 |
andum | -1.078 |
Token | The |
Token ID | 383 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
anmar | +0.710 |
eters | +0.624 |
ativity | +0.596 |
andum | +0.573 |
warts | +0.572 |
Neg logit contributions | |
behavi | -0.576 |
subtitles | -0.562 |
Blu | -0.552 |
ophy | -0.548 |
AU | -0.536 |
Token | future |
Token ID | 2003 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Blu | +0.729 |
subtitles | +0.726 |
behavi | +0.718 |
ophy | +0.707 |
puzz | +0.690 |
Neg logit contributions | |
anmar | -0.875 |
eters | -0.767 |
ativity | -0.733 |
andum | -0.702 |
warts | -0.701 |
Token | Hall |
Token ID | 4789 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
anmar | +0.990 |
eters | +0.868 |
ativity | +0.832 |
warts | +0.800 |
andum | +0.798 |
Neg logit contributions | |
behavi | -0.747 |
subtitles | -0.739 |
Blu | -0.730 |
ophy | -0.715 |
AU | -0.707 |
Token | of |
Token ID | 286 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Blu | +1.281 |
behavi | +1.269 |
subtitles | +1.260 |
ophy | +1.237 |
puzz | +1.190 |
Neg logit contributions | |
anmar | -2.386 |
eters | -2.122 |
ativity | -2.040 |
andum | -1.969 |
warts | -1.950 |
Token | F |
Token ID | 376 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
anmar | +5.341 |
eters | +4.390 |
ativity | +4.343 |
warts | +4.192 |
felt | +4.090 |
Neg logit contributions | |
behavi | -8.390 |
subtitles | -8.142 |
AU | -7.869 |
Blu | -7.789 |
ophy | -7.783 |
Token | amer |
Token ID | 2382 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
anmar | +2.292 |
eters | +2.022 |
ativity | +1.943 |
andum | +1.865 |
warts | +1.862 |
Neg logit contributions | |
behavi | -2.342 |
subtitles | -2.196 |
Blu | -2.142 |
puzz | -2.070 |
AU | -2.063 |
Token | and |
Token ID | 290 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
anmar | +0.991 |
eters | +0.863 |
ativity | +0.826 |
warts | +0.792 |
andum | +0.792 |
Neg logit contributions | |
behavi | -0.823 |
subtitles | -0.816 |
Blu | -0.811 |
ophy | -0.794 |
AU | -0.782 |
Token | reigning |
Token ID | 40098 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
anmar | +0.483 |
eters | +0.421 |
ativity | +0.403 |
andum | +0.387 |
warts | +0.387 |
Neg logit contributions | |
behavi | -0.398 |
subtitles | -0.395 |
Blu | -0.392 |
ophy | -0.384 |
AU | -0.379 |
Token | Super |
Token ID | 3115 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Blu | +1.870 |
subtitles | +1.833 |
behavi | +1.806 |
ophy | +1.792 |
puzz | +1.756 |
Neg logit contributions | |
anmar | -2.888 |
eters | -2.553 |
ativity | -2.453 |
andum | -2.368 |
warts | -2.355 |
Token | probably |
Token ID | 2192 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
anmar | +0.674 |
eters | +0.592 |
ativity | +0.565 |
andum | +0.542 |
warts | +0.542 |
Neg logit contributions | |
behavi | -0.540 |
subtitles | -0.537 |
Blu | -0.531 |
ophy | -0.523 |
AU | -0.515 |
Token | end |
Token ID | 886 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
anmar | +1.334 |
eters | +1.172 |
ativity | +1.109 |
warts | +1.066 |
andum | +1.063 |
Neg logit contributions | |
behavi | -1.110 |
subtitles | -1.101 |
Blu | -1.084 |
ophy | -1.074 |
AU | -1.061 |
Token | other |
Token ID | 847 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
behavi | +0.504 |
subtitles | +0.503 |
Blu | +0.500 |
ophy | +0.492 |
AU | +0.477 |
Neg logit contributions | |
anmar | -0.864 |
eters | -0.766 |
ativity | -0.739 |
andum | -0.717 |
warts | -0.715 |
Token | mic |
Token ID | 9383 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
anmar | +0.616 |
eters | +0.537 |
ativity | +0.514 |
andum | +0.492 |
warts | +0.492 |
Neg logit contributions | |
behavi | -0.526 |
subtitles | -0.520 |
Blu | -0.515 |
ophy | -0.501 |
AU | -0.498 |
Token | ( |
Token ID | 357 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
anmar | +5.300 |
eters | +4.772 |
ativity | +4.489 |
warts | +4.348 |
felt | +4.215 |
Neg logit contributions | |
behavi | -4.148 |
subtitles | -4.097 |
Blu | -3.994 |
ophy | -3.953 |
AU | -3.946 |
Token | warm |
Token ID | 31975 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
anmar | +0.623 |
eters | +0.547 |
ativity | +0.524 |
warts | +0.506 |
andum | +0.504 |
Neg logit contributions | |
behavi | -0.453 |
subtitles | -0.450 |
Blu | -0.446 |
ophy | -0.435 |
AU | -0.427 |
Token | blood |
Token ID | 2910 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
anmar | +7.467 |
eters | +6.437 |
ativity | +6.144 |
warts | +5.960 |
felt | +5.816 |
Neg logit contributions | |
behavi | -6.305 |
subtitles | -6.048 |
Blu | -5.928 |
ophy | -5.830 |
puzz | -5.761 |
Token | ed |
Token ID | 276 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
subtitles | +0.651 |
Blu | +0.648 |
behavi | +0.644 |
ophy | +0.632 |
AU | +0.621 |
Neg logit contributions | |
anmar | -0.795 |
eters | -0.682 |
ativity | -0.653 |
andum | -0.642 |
warts | -0.633 |
Token | ), |
Token ID | 828 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
anmar | +1.759 |
eters | +1.539 |
ativity | +1.474 |
warts | +1.416 |
andum | +1.410 |
Neg logit contributions | |
behavi | -1.365 |
subtitles | -1.350 |
Blu | -1.341 |
ophy | -1.311 |
AU | -1.293 |
Token | which |
Token ID | 543 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
subtitles | +0.720 |
behavi | +0.718 |
Blu | +0.715 |
ophy | +0.699 |
AU | +0.683 |
Neg logit contributions | |
anmar | -1.034 |
eters | -0.903 |
ativity | -0.868 |
warts | -0.839 |
andum | -0.839 |
Token | made |
Token ID | 925 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
behavi | +0.479 |
subtitles | +0.477 |
Blu | +0.474 |
ophy | +0.464 |
AU | +0.457 |
Neg logit contributions | |
anmar | -0.544 |
eters | -0.470 |
ativity | -0.450 |
warts | -0.431 |
andum | -0.431 |
Token | Follow |
Token ID | 7155 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
anmar | +0.986 |
eters | +0.877 |
ativity | +0.843 |
andum | +0.815 |
warts | +0.814 |
Neg logit contributions | |
behavi | -0.603 |
subtitles | -0.594 |
Blu | -0.589 |
ophy | -0.574 |
AU | -0.559 |
Token | Justin |
Token ID | 10799 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
anmar | +0.339 |
eters | +0.298 |
ativity | +0.287 |
warts | +0.277 |
andum | +0.276 |
Neg logit contributions | |
behavi | -0.223 |
subtitles | -0.222 |
Blu | -0.222 |
ophy | -0.216 |
AU | -0.213 |
Token | on |
Token ID | 319 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
Blu | +2.831 |
subtitles | +2.755 |
AU | +2.562 |
behavi | +2.559 |
ophy | +2.555 |
Neg logit contributions | |
anmar | -5.573 |
eters | -4.828 |
�� | -4.785 |
warts | -4.760 |
ativity | -4.671 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
Blu | +1.113 |
subtitles | +1.110 |
behavi | +1.104 |
ophy | +1.074 |
AU | +1.054 |
Neg logit contributions | |
anmar | -1.797 |
eters | -1.568 |
ativity | -1.514 |
warts | -1.471 |
andum | -1.454 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Blu | +0.932 |
behavi | +0.929 |
subtitles | +0.924 |
AU | +0.896 |
ophy | +0.880 |
Neg logit contributions | |
anmar | -2.019 |
eters | -1.776 |
ativity | -1.720 |
warts | -1.691 |
�� | -1.684 |
Token | by |
Token ID | 1525 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
anmar | +1.132 |
eters | +1.006 |
ativity | +0.968 |
warts | +0.937 |
andum | +0.935 |
Neg logit contributions | |
behavi | -0.665 |
subtitles | -0.656 |
Blu | -0.649 |
ophy | -0.632 |
AU | -0.616 |
Token | Julia |
Token ID | 22300 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
anmar | +7.731 |
eters | +6.790 |
ativity | +6.453 |
warts | +6.236 |
andum | +6.213 |
Neg logit contributions | |
behavi | -5.501 |
subtitles | -5.314 |
ophy | -5.107 |
Blu | -5.096 |
AU | -5.075 |
Token | Py |
Token ID | 9485 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Blu | +1.016 |
subtitles | +1.005 |
behavi | +0.992 |
ophy | +0.982 |
AU | +0.963 |
Neg logit contributions | |
anmar | -1.377 |
eters | -1.200 |
ativity | -1.153 |
warts | -1.115 |
andum | -1.109 |
Token | per |
Token ID | 525 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
anmar | +1.252 |
eters | +1.101 |
ativity | +1.057 |
andum | +1.016 |
warts | +1.016 |
Neg logit contributions | |
behavi | -0.902 |
subtitles | -0.895 |
Blu | -0.887 |
ophy | -0.865 |
AU | -0.853 |
Token |
|
Token ID | 198 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
Blu | +1.945 |
subtitles | +1.939 |
behavi | +1.923 |
ophy | +1.905 |
AU | +1.894 |
Neg logit contributions | |
anmar | -2.922 |
eters | -2.554 |
ativity | -2.486 |
�� | -2.406 |
andum | -2.383 |
Token |
|
Token ID | 198 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
anmar | +2.549 |
eters | +2.292 |
ativity | +2.144 |
felt | +2.116 |
warts | +2.102 |
Neg logit contributions | |
behavi | -2.433 |
subtitles | -2.207 |
ophy | -2.147 |
puzz | -2.129 |
Blu | -2.112 |
Token | LIKE |
Token ID | 34178 |
Feature activation | +1.48e-03 |
Pos logit contributions | |
anmar | +3.844 |
eters | +3.489 |
ativity | +3.362 |
warts | +3.256 |
andum | +3.250 |
Neg logit contributions | |
behavi | -1.730 |
subtitles | -1.689 |
Blu | -1.669 |
ophy | -1.624 |
AU | -1.573 |
Token | ' |
Token ID | 705 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
anmar | +0.007 |
eters | +0.006 |
ativity | +0.006 |
andum | +0.006 |
warts | +0.006 |
Neg logit contributions | |
subtitles | -0.005 |
behavi | -0.005 |
Blu | -0.005 |
ophy | -0.005 |
AU | -0.005 |
Token | % |
Token ID | 4 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
subtitles | +0.043 |
Blu | +0.043 |
behavi | +0.042 |
ophy | +0.042 |
AU | +0.041 |
Neg logit contributions | |
anmar | -0.056 |
eters | -0.049 |
ativity | -0.047 |
andum | -0.045 |
warts | -0.045 |
Token | build |
Token ID | 11249 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Blu | +4.200 |
AU | +4.138 |
ophy | +4.103 |
subtitles | +4.063 |
Wikipedia | +3.932 |
Neg logit contributions | |
anmar | -6.207 |
eters | -5.392 |
ativity | -5.288 |
�� | -5.132 |
andum | -5.126 |
Token | . |
Token ID | 13 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
anmar | +1.147 |
eters | +1.024 |
ativity | +0.992 |
andum | +0.959 |
warts | +0.954 |
Neg logit contributions | |
behavi | -0.585 |
subtitles | -0.582 |
Blu | -0.578 |
ophy | -0.561 |
AU | -0.553 |
Token | boot |
Token ID | 18769 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
anmar | +2.606 |
eters | +2.318 |
ativity | +2.240 |
andum | +2.163 |
warts | +2.154 |
Neg logit contributions | |
behavi | -1.441 |
subtitles | -1.439 |
Blu | -1.433 |
ophy | -1.399 |
AU | -1.371 |
Token | ' |
Token ID | 6 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
anmar | +7.185 |
eters | +6.369 |
ativity | +5.948 |
warts | +5.795 |
andum | +5.691 |
Neg logit contributions | |
behavi | -6.055 |
subtitles | -5.961 |
Blu | -5.895 |
puzz | -5.678 |
ophy | -5.643 |
Token | ) |
Token ID | 1267 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
anmar | +2.529 |
eters | +2.236 |
ativity | +2.115 |
andum | +2.028 |
warts | +2.019 |
Neg logit contributions | |
behavi | -2.286 |
subtitles | -2.234 |
Blu | -2.227 |
ophy | -2.192 |
AU | -2.145 |
Token | H |
Token ID | 367 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
subtitles | +0.169 |
behavi | +0.169 |
Blu | +0.168 |
ophy | +0.164 |
AU | +0.163 |
Neg logit contributions | |
anmar | -0.163 |
eters | -0.138 |
ativity | -0.132 |
warts | -0.126 |
andum | -0.126 |
Token | AV |
Token ID | 10116 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
anmar | +2.837 |
eters | +2.574 |
ativity | +2.467 |
andum | +2.382 |
warts | +2.378 |
Neg logit contributions | |
behavi | -1.618 |
subtitles | -1.576 |
Blu | -1.559 |
ophy | -1.530 |
puzz | -1.477 |
Token | ING |
Token ID | 2751 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
anmar | +4.998 |
eters | +4.433 |
ativity | +4.197 |
andum | +4.107 |
warts | +4.096 |
Neg logit contributions | |
behavi | -3.305 |
subtitles | -3.244 |
Blu | -3.229 |
ophy | -3.203 |
puzz | -3.091 |
Token | Row |
Token ID | 25166 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
behavi | +0.297 |
subtitles | +0.296 |
Blu | +0.294 |
ophy | +0.286 |
AU | +0.282 |
Neg logit contributions | |
anmar | -0.513 |
eters | -0.456 |
ativity | -0.439 |
andum | -0.424 |
warts | -0.424 |
Token | lf |
Token ID | 1652 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
anmar | +2.442 |
eters | +2.148 |
ativity | +2.063 |
warts | +1.985 |
andum | +1.979 |
Neg logit contributions | |
behavi | -1.727 |
subtitles | -1.709 |
Blu | -1.693 |
ophy | -1.658 |
AU | -1.629 |
Token | achieved |
Token ID | 8793 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Blu | +0.129 |
subtitles | +0.128 |
behavi | +0.127 |
ophy | +0.125 |
AU | +0.123 |
Neg logit contributions | |
anmar | -0.171 |
eters | -0.149 |
ativity | -0.143 |
andum | -0.138 |
warts | -0.138 |
Token | movie |
Token ID | 3807 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
anmar | +0.824 |
eters | +0.719 |
ativity | +0.689 |
warts | +0.662 |
andum | +0.658 |
Neg logit contributions | |
behavi | -0.655 |
subtitles | -0.647 |
Blu | -0.642 |
ophy | -0.632 |
AU | -0.623 |
Token | st |
Token ID | 336 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
subtitles | +1.971 |
Blu | +1.959 |
behavi | +1.954 |
ophy | +1.879 |
AU | +1.850 |
Neg logit contributions | |
anmar | -2.936 |
eters | -2.592 |
ativity | -2.471 |
andum | -2.414 |
�� | -2.391 |
Token | ard |
Token ID | 446 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Blu | +2.258 |
subtitles | +2.185 |
ophy | +2.141 |
AU | +2.078 |
behavi | +2.037 |
Neg logit contributions | |
anmar | -4.330 |
eters | -3.831 |
�� | -3.781 |
ativity | -3.652 |
andum | -3.593 |
Token | om |
Token ID | 296 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
anmar | +6.681 |
eters | +6.300 |
ativity | +6.063 |
warts | +5.920 |
felt | +5.484 |
Neg logit contributions | |
behavi | -6.516 |
subtitles | -6.183 |
AU | -5.986 |
Blu | -5.909 |
ophy | -5.668 |
Token | with |
Token ID | 351 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
anmar | +3.650 |
eters | +3.248 |
ativity | +3.080 |
warts | +2.978 |
felt | +2.931 |
Neg logit contributions | |
behavi | -2.988 |
ophy | -2.910 |
subtitles | -2.885 |
Blu | -2.827 |
AU | -2.818 |
Token | his |
Token ID | 465 |
Feature activation | -9.90e-02 |
Pos logit contributions | |
subtitles | +1.512 |
Blu | +1.507 |
behavi | +1.480 |
ophy | +1.443 |
AU | +1.426 |
Neg logit contributions | |
anmar | -2.128 |
eters | -1.878 |
ativity | -1.791 |
andum | -1.749 |
warts | -1.727 |
Token | appearance |
Token ID | 5585 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
behavi | +0.358 |
subtitles | +0.356 |
Blu | +0.354 |
ophy | +0.345 |
AU | +0.340 |
Neg logit contributions | |
anmar | -0.462 |
eters | -0.404 |
ativity | -0.387 |
andum | -0.372 |
warts | -0.372 |
Token | in |
Token ID | 287 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
subtitles | +1.618 |
Blu | +1.617 |
behavi | +1.580 |
ophy | +1.528 |
AU | +1.516 |
Neg logit contributions | |
anmar | -2.335 |
eters | -2.051 |
ativity | -1.968 |
warts | -1.917 |
andum | -1.909 |
Token | Daily |
Token ID | 6714 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
behavi | +0.919 |
subtitles | +0.891 |
Blu | +0.880 |
ophy | +0.861 |
AU | +0.857 |
Neg logit contributions | |
anmar | -1.839 |
eters | -1.640 |
ativity | -1.588 |
warts | -1.542 |
andum | -1.538 |
Token | Dispatch |
Token ID | 35934 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
subtitles | +1.198 |
behavi | +1.197 |
Blu | +1.191 |
ophy | +1.164 |
AU | +1.151 |
Neg logit contributions | |
anmar | -1.080 |
eters | -0.922 |
ativity | -0.875 |
warts | -0.830 |
andum | -0.829 |
Token | and |
Token ID | 290 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
behavi | +0.452 |
subtitles | +0.452 |
Blu | +0.449 |
ophy | +0.438 |
AU | +0.432 |
Neg logit contributions | |
anmar | -0.574 |
eters | -0.502 |
ativity | -0.481 |
andum | -0.461 |
warts | -0.461 |
Token | Editor |
Token ID | 12058 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
subtitles | +0.831 |
Blu | +0.830 |
behavi | +0.823 |
ophy | +0.805 |
AU | +0.795 |
Neg logit contributions | |
anmar | -0.758 |
eters | -0.638 |
ativity | -0.605 |
andum | -0.577 |
warts | -0.574 |
Token | 's |
Token ID | 338 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
subtitles | +0.585 |
behavi | +0.584 |
Blu | +0.581 |
ophy | +0.569 |
AU | +0.562 |
Neg logit contributions | |
anmar | -0.614 |
eters | -0.529 |
ativity | -0.503 |
warts | -0.481 |
andum | -0.480 |
Token | Picks |
Token ID | 33957 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
anmar | +0.435 |
eters | +0.379 |
ativity | +0.362 |
warts | +0.350 |
andum | +0.350 |
Neg logit contributions | |
behavi | -0.355 |
subtitles | -0.345 |
Blu | -0.345 |
ophy | -0.339 |
AU | -0.336 |
Token | . |
Token ID | 13 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
anmar | +6.364 |
eters | +6.011 |
ativity | +5.452 |
felt | +5.273 |
initialized | +5.264 |
Neg logit contributions | |
behavi | -6.888 |
ophy | -6.271 |
puzz | -6.231 |
convol | -6.186 |
subtitles | -6.097 |
Token |
|
Token ID | 198 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
anmar | +0.292 |
eters | +0.265 |
ativity | +0.255 |
warts | +0.248 |
andum | +0.247 |
Neg logit contributions | |
behavi | -0.135 |
subtitles | -0.132 |
Blu | -0.130 |
ophy | -0.127 |
AU | -0.123 |
Token |
|
Token ID | 198 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
anmar | +2.032 |
eters | +1.860 |
ativity | +1.741 |
felt | +1.698 |
warts | +1.687 |
Neg logit contributions | |
behavi | -1.990 |
subtitles | -1.771 |
ophy | -1.743 |
puzz | -1.718 |
Blu | -1.701 |
Token | Much |
Token ID | 20045 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
anmar | +1.205 |
eters | +1.087 |
ativity | +1.039 |
andum | +1.009 |
warts | +1.008 |
Neg logit contributions | |
behavi | -0.750 |
subtitles | -0.728 |
Blu | -0.712 |
ophy | -0.693 |
puzz | -0.673 |
Token | of |
Token ID | 286 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
behavi | +0.598 |
subtitles | +0.594 |
Blu | +0.593 |
ophy | +0.576 |
puzz | +0.564 |
Neg logit contributions | |
anmar | -0.912 |
eters | -0.798 |
ativity | -0.766 |
warts | -0.742 |
andum | -0.740 |
Token | follow |
Token ID | 1061 |
Feature activation | -9.50e-03 |
Pos logit contributions | |
anmar | +0.348 |
eters | +0.310 |
ativity | +0.297 |
warts | +0.287 |
andum | +0.286 |
Neg logit contributions | |
behavi | -0.220 |
subtitles | -0.217 |
Blu | -0.216 |
ophy | -0.210 |
AU | -0.207 |
Token | its |
Token ID | 663 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
behavi | +0.032 |
subtitles | +0.032 |
Blu | +0.031 |
ophy | +0.031 |
AU | +0.030 |
Neg logit contributions | |
anmar | -0.047 |
eters | -0.041 |
ativity | -0.040 |
andum | -0.038 |
warts | -0.038 |
Token | non |
Token ID | 1729 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
anmar | +0.102 |
eters | +0.090 |
ativity | +0.087 |
andum | +0.083 |
warts | +0.083 |
Neg logit contributions | |
behavi | -0.066 |
subtitles | -0.066 |
Blu | -0.065 |
ophy | -0.064 |
AU | -0.063 |
Token | - |
Token ID | 12 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
anmar | +0.038 |
eters | +0.034 |
ativity | +0.032 |
andum | +0.031 |
warts | +0.031 |
Neg logit contributions | |
behavi | -0.023 |
subtitles | -0.023 |
Blu | -0.023 |
ophy | -0.022 |
AU | -0.022 |
Token | h |
Token ID | 71 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
behavi | +0.475 |
subtitles | +0.473 |
Blu | +0.470 |
ophy | +0.463 |
AU | +0.458 |
Neg logit contributions | |
anmar | -0.562 |
eters | -0.490 |
ativity | -0.468 |
andum | -0.450 |
warts | -0.447 |
Token | ij |
Token ID | 2926 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
behavi | +0.639 |
subtitles | +0.636 |
Blu | +0.633 |
ophy | +0.623 |
AU | +0.614 |
Neg logit contributions | |
anmar | -0.715 |
eters | -0.618 |
ativity | -0.588 |
warts | -0.566 |
andum | -0.565 |
Token | ab |
Token ID | 397 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
anmar | +6.014 |
eters | +5.173 |
ativity | +4.912 |
warts | +4.811 |
andum | +4.689 |
Neg logit contributions | |
behavi | -7.374 |
subtitles | -7.232 |
Blu | -7.219 |
AU | -6.942 |
puzz | -6.935 |
Token | policy |
Token ID | 2450 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
anmar | +0.526 |
eters | +0.465 |
ativity | +0.449 |
andum | +0.431 |
warts | +0.430 |
Neg logit contributions | |
behavi | -0.333 |
subtitles | -0.331 |
Blu | -0.328 |
ophy | -0.319 |
AU | -0.314 |
Token | . |
Token ID | 13 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
anmar | +3.625 |
eters | +3.245 |
ativity | +3.088 |
andum | +2.990 |
warts | +2.980 |
Neg logit contributions | |
behavi | -2.370 |
subtitles | -2.341 |
Blu | -2.322 |
ophy | -2.256 |
puzz | -2.235 |
Token |
|
Token ID | 198 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
subtitles | +0.955 |
Blu | +0.953 |
behavi | +0.944 |
ophy | +0.928 |
AU | +0.908 |
Neg logit contributions | |
anmar | -1.636 |
eters | -1.443 |
ativity | -1.391 |
andum | -1.341 |
warts | -1.341 |
Token |
|
Token ID | 198 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
subtitles | +1.487 |
Blu | +1.487 |
behavi | +1.452 |
ophy | +1.436 |
AU | +1.424 |
Neg logit contributions | |
anmar | -2.450 |
eters | -2.150 |
ativity | -2.080 |
andum | -2.003 |
warts | -2.002 |
Token | between |
Token ID | 1022 |
Feature activation | +3.76e-03 |
Pos logit contributions | |
behavi | +0.148 |
subtitles | +0.148 |
Blu | +0.147 |
ophy | +0.141 |
AU | +0.138 |
Neg logit contributions | |
anmar | -0.350 |
eters | -0.312 |
ativity | -0.302 |
andum | -0.295 |
warts | -0.294 |
Token | a |
Token ID | 257 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
anmar | +0.018 |
eters | +0.016 |
ativity | +0.015 |
warts | +0.014 |
andum | +0.014 |
Neg logit contributions | |
behavi | -0.013 |
subtitles | -0.013 |
Blu | -0.013 |
ophy | -0.013 |
AU | -0.013 |
Token | rocket |
Token ID | 10701 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
anmar | +1.104 |
eters | +0.969 |
ativity | +0.930 |
warts | +0.894 |
andum | +0.894 |
Neg logit contributions | |
behavi | -0.806 |
subtitles | -0.801 |
Blu | -0.795 |
ophy | -0.777 |
AU | -0.765 |
Token | and |
Token ID | 290 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
anmar | +3.306 |
eters | +2.927 |
ativity | +2.780 |
andum | +2.662 |
warts | +2.644 |
Neg logit contributions | |
behavi | -2.929 |
subtitles | -2.887 |
Blu | -2.839 |
ophy | -2.792 |
AU | -2.756 |
Token | a |
Token ID | 257 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
anmar | +3.884 |
eters | +3.437 |
ativity | +3.334 |
andum | +3.186 |
warts | +3.176 |
Neg logit contributions | |
behavi | -2.978 |
subtitles | -2.894 |
Blu | -2.830 |
ophy | -2.824 |
AU | -2.801 |
Token | rocket |
Token ID | 10701 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
anmar | +3.164 |
eters | +2.795 |
ativity | +2.683 |
andum | +2.555 |
warts | +2.554 |
Neg logit contributions | |
behavi | -2.511 |
subtitles | -2.460 |
Blu | -2.406 |
ophy | -2.378 |
AU | -2.374 |
Token | with |
Token ID | 351 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
anmar | +7.090 |
eters | +6.503 |
ativity | +6.125 |
warts | +5.830 |
andum | +5.828 |
Neg logit contributions | |
behavi | -5.666 |
subtitles | -5.524 |
Blu | -5.386 |
ophy | -5.289 |
AU | -5.146 |
Token | a |
Token ID | 257 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
anmar | +0.863 |
eters | +0.762 |
ativity | +0.729 |
warts | +0.700 |
andum | +0.699 |
Neg logit contributions | |
behavi | -0.653 |
subtitles | -0.640 |
Blu | -0.637 |
ophy | -0.626 |
AU | -0.619 |
Token | man |
Token ID | 582 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
anmar | +0.548 |
eters | +0.483 |
ativity | +0.463 |
andum | +0.445 |
warts | +0.445 |
Neg logit contributions | |
behavi | -0.389 |
subtitles | -0.384 |
Blu | -0.381 |
ophy | -0.373 |
AU | -0.368 |
Token | on |
Token ID | 319 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
subtitles | +0.041 |
behavi | +0.041 |
Blu | +0.041 |
ophy | +0.040 |
AU | +0.039 |
Neg logit contributions | |
anmar | -0.058 |
eters | -0.051 |
ativity | -0.048 |
warts | -0.047 |
andum | -0.047 |
Token | top |
Token ID | 1353 |
Feature activation | +5.22e-03 |
Pos logit contributions | |
subtitles | +0.788 |
behavi | +0.786 |
Blu | +0.786 |
ophy | +0.761 |
AU | +0.752 |
Neg logit contributions | |
anmar | -1.015 |
eters | -0.878 |
ativity | -0.834 |
warts | -0.807 |
andum | -0.801 |
Token | ari |
Token ID | 2743 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
anmar | +0.709 |
eters | +0.564 |
ativity | +0.522 |
warts | +0.485 |
andum | +0.484 |
Neg logit contributions | |
behavi | -1.329 |
subtitles | -1.325 |
Blu | -1.319 |
ophy | -1.302 |
AU | -1.288 |
Token | ) |
Token ID | 8 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
anmar | +2.675 |
eters | +2.330 |
ativity | +2.217 |
warts | +2.124 |
andum | +2.123 |
Neg logit contributions | |
behavi | -2.247 |
subtitles | -2.218 |
Blu | -2.190 |
ophy | -2.141 |
AU | -2.104 |
Token | on |
Token ID | 319 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
anmar | +2.746 |
eters | +2.450 |
ativity | +2.280 |
felt | +2.181 |
andum | +2.175 |
Neg logit contributions | |
behavi | -3.016 |
ophy | -2.722 |
subtitles | -2.696 |
puzz | -2.666 |
AU | -2.649 |
Token | Jan |
Token ID | 2365 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
anmar | +3.622 |
eters | +3.226 |
ativity | +3.080 |
felt | +2.954 |
initialized | +2.888 |
Neg logit contributions | |
behavi | -3.181 |
subtitles | -2.927 |
ophy | -2.899 |
AU | -2.825 |
puzz | -2.807 |
Token | 16 |
Token ID | 1467 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
anmar | +4.135 |
eters | +3.813 |
felt | +3.435 |
ativity | +3.394 |
initialized | +3.266 |
Neg logit contributions | |
behavi | -5.489 |
ophy | -4.674 |
subtitles | -4.653 |
puzz | -4.611 |
warr | -4.494 |
Token | , |
Token ID | 11 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
anmar | +4.250 |
eters | +4.058 |
felt | +3.691 |
ativity | +3.666 |
andum | +3.532 |
Neg logit contributions | |
behavi | -5.796 |
warr | -4.869 |
subtitles | -4.807 |
puzz | -4.793 |
ophy | -4.760 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
anmar | +4.723 |
eters | +4.314 |
ativity | +3.982 |
felt | +3.691 |
andum | +3.628 |
Neg logit contributions | |
behavi | -8.140 |
subtitles | -7.553 |
puzz | -7.452 |
ophy | -7.360 |
Blu | -7.355 |
Token | at |
Token ID | 379 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
anmar | +2.887 |
eters | +2.646 |
ativity | +2.518 |
andum | +2.379 |
felt | +2.353 |
Neg logit contributions | |
behavi | -2.862 |
subtitles | -2.594 |
ophy | -2.563 |
Blu | -2.530 |
AU | -2.529 |
Token | 9 |
Token ID | 860 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
anmar | +1.968 |
eters | +1.779 |
ativity | +1.658 |
andum | +1.586 |
felt | +1.585 |
Neg logit contributions | |
behavi | -2.076 |
subtitles | -1.859 |
ophy | -1.855 |
AU | -1.823 |
puzz | -1.810 |
Token | : |
Token ID | 25 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
anmar | +2.391 |
eters | +2.197 |
ativity | +2.048 |
andum | +1.974 |
felt | +1.971 |
Neg logit contributions | |
behavi | -2.626 |
subtitles | -2.273 |
puzz | -2.242 |
ophy | -2.238 |
Blu | -2.189 |
Token | 28 |
Token ID | 2078 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
anmar | +3.762 |
eters | +3.534 |
felt | +3.292 |
ativity | +3.274 |
initialized | +3.231 |
Neg logit contributions | |
behavi | -3.606 |
puzz | -2.887 |
subtitles | -2.877 |
ophy | -2.861 |
warr | -2.790 |
Token | system |
Token ID | 10057 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
behavi | +0.169 |
subtitles | +0.169 |
Blu | +0.167 |
ophy | +0.160 |
AU | +0.157 |
Neg logit contributions | |
anmar | -0.586 |
eters | -0.531 |
ativity | -0.517 |
andum | -0.502 |
warts | -0.501 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
anmar | +1.088 |
eters | +0.971 |
ativity | +0.935 |
warts | +0.904 |
andum | +0.903 |
Neg logit contributions | |
behavi | -0.625 |
subtitles | -0.608 |
Blu | -0.599 |
ophy | -0.588 |
AU | -0.572 |
Token | draw |
Token ID | 19334 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
anmar | +1.100 |
eters | +0.961 |
ativity | +0.921 |
andum | +0.885 |
warts | +0.880 |
Neg logit contributions | |
behavi | -0.858 |
subtitles | -0.858 |
Blu | -0.852 |
ophy | -0.834 |
AU | -0.822 |
Token | ing |
Token ID | 278 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
anmar | +0.085 |
eters | +0.074 |
ativity | +0.070 |
warts | +0.067 |
andum | +0.067 |
Neg logit contributions | |
behavi | -0.091 |
subtitles | -0.089 |
Blu | -0.088 |
ophy | -0.086 |
AU | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
anmar | +0.342 |
eters | +0.305 |
ativity | +0.294 |
andum | +0.284 |
warts | +0.284 |
Neg logit contributions | |
behavi | -0.179 |
subtitles | -0.179 |
Blu | -0.177 |
ophy | -0.171 |
AU | -0.169 |
Token | im |
Token ID | 320 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
anmar | +2.244 |
eters | +1.969 |
ativity | +1.878 |
warts | +1.816 |
andum | +1.804 |
Neg logit contributions | |
behavi | -1.796 |
subtitles | -1.769 |
Blu | -1.757 |
ophy | -1.719 |
AU | -1.686 |
Token | aging |
Token ID | 3039 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
anmar | +3.561 |
eters | +2.823 |
ativity | +2.493 |
andum | +2.091 |
warts | +2.087 |
Neg logit contributions | |
behavi | -10.178 |
subtitles | -9.539 |
Blu | -9.350 |
puzz | -9.301 |
warr | -9.203 |
Token | . |
Token ID | 13 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
anmar | +0.947 |
eters | +0.839 |
ativity | +0.803 |
warts | +0.774 |
andum | +0.773 |
Neg logit contributions | |
behavi | -0.662 |
subtitles | -0.652 |
Blu | -0.648 |
ophy | -0.635 |
AU | -0.622 |
Token | image |
Token ID | 9060 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
anmar | +2.836 |
eters | +2.512 |
ativity | +2.382 |
warts | +2.321 |
andum | +2.301 |
Neg logit contributions | |
behavi | -2.167 |
subtitles | -2.110 |
Blu | -2.092 |
ophy | -2.049 |
puzz | -2.004 |
Token | format |
Token ID | 18982 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
anmar | +2.021 |
eters | +1.798 |
ativity | +1.715 |
warts | +1.654 |
andum | +1.652 |
Neg logit contributions | |
behavi | -1.423 |
subtitles | -1.392 |
Blu | -1.381 |
ophy | -1.354 |
AU | -1.323 |
Token | ] |
Token ID | 60 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
anmar | +1.756 |
eters | +1.547 |
ativity | +1.470 |
andum | +1.410 |
warts | +1.409 |
Neg logit contributions | |
behavi | -1.477 |
subtitles | -1.451 |
Blu | -1.441 |
ophy | -1.419 |
AU | -1.391 |
Token | be |
Token ID | 1350 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
anmar | +2.948 |
eters | +2.595 |
ativity | +2.434 |
warts | +2.316 |
andum | +2.309 |
Neg logit contributions | |
behavi | -3.324 |
subtitles | -3.238 |
Blu | -3.192 |
ophy | -3.145 |
AU | -3.093 |
Token | ek |
Token ID | 988 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
behavi | +0.127 |
subtitles | +0.127 |
Blu | +0.127 |
ophy | +0.123 |
AU | +0.122 |
Neg logit contributions | |
anmar | -0.189 |
eters | -0.165 |
ativity | -0.160 |
warts | -0.154 |
andum | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
anmar | +3.381 |
eters | +3.018 |
ativity | +2.874 |
warts | +2.778 |
felt | +2.755 |
Neg logit contributions | |
behavi | -2.304 |
subtitles | -2.236 |
Blu | -2.201 |
ophy | -2.150 |
AU | -2.110 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
subtitles | +0.044 |
behavi | +0.044 |
Blu | +0.044 |
ophy | +0.042 |
AU | +0.042 |
Neg logit contributions | |
anmar | -0.088 |
eters | -0.078 |
ativity | -0.076 |
warts | -0.073 |
andum | -0.073 |
Token | Share |
Token ID | 11649 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
anmar | +0.863 |
eters | +0.767 |
ativity | +0.738 |
warts | +0.714 |
andum | +0.713 |
Neg logit contributions | |
behavi | -0.504 |
subtitles | -0.498 |
Blu | -0.493 |
ophy | -0.480 |
AU | -0.469 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Blu | +1.454 |
subtitles | +1.445 |
behavi | +1.434 |
AU | +1.368 |
ophy | +1.367 |
Neg logit contributions | |
anmar | -2.448 |
eters | -2.174 |
ativity | -2.085 |
warts | -2.044 |
�� | -2.040 |
Token | We |
Token ID | 775 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
anmar | +6.794 |
eters | +6.139 |
ativity | +5.729 |
felt | +5.566 |
warts | +5.517 |
Neg logit contributions | |
behavi | -6.173 |
ophy | -5.464 |
subtitles | -5.367 |
puzz | -5.246 |
AU | -5.122 |
Token | found |
Token ID | 1043 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
anmar | +1.330 |
eters | +1.163 |
ativity | +1.109 |
andum | +1.067 |
warts | +1.063 |
Neg logit contributions | |
behavi | -1.096 |
subtitles | -1.064 |
Blu | -1.054 |
ophy | -1.030 |
AU | -1.018 |
Token | a |
Token ID | 257 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
anmar | +4.036 |
eters | +3.529 |
ativity | +3.319 |
warts | +3.190 |
andum | +3.165 |
Neg logit contributions | |
behavi | -3.706 |
ophy | -3.524 |
subtitles | -3.455 |
AU | -3.431 |
Blu | -3.406 |
Token | home |
Token ID | 1363 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
anmar | +1.743 |
eters | +1.510 |
ativity | +1.442 |
warts | +1.377 |
andum | +1.377 |
Neg logit contributions | |
behavi | -1.495 |
subtitles | -1.463 |
ophy | -1.438 |
Blu | -1.437 |
AU | -1.418 |
Token | for |
Token ID | 329 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
anmar | +1.861 |
eters | +1.612 |
ativity | +1.559 |
warts | +1.478 |
felt | +1.476 |
Neg logit contributions | |
behavi | -1.429 |
subtitles | -1.399 |
ophy | -1.362 |
Blu | -1.361 |
AU | -1.324 |
Token | Daily |
Token ID | 6714 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
behavi | +0.746 |
subtitles | +0.723 |
Blu | +0.712 |
ophy | +0.699 |
AU | +0.697 |
Neg logit contributions | |
anmar | -1.488 |
eters | -1.328 |
ativity | -1.286 |
warts | -1.248 |
andum | -1.244 |
Token | Dispatch |
Token ID | 35934 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
subtitles | +1.071 |
Blu | +1.065 |
behavi | +1.059 |
ophy | +1.033 |
AU | +1.022 |
Neg logit contributions | |
anmar | -0.998 |
eters | -0.858 |
ativity | -0.819 |
�� | -0.773 |
andum | -0.773 |
Token | and |
Token ID | 290 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
behavi | +0.430 |
subtitles | +0.430 |
Blu | +0.428 |
ophy | +0.417 |
AU | +0.411 |
Neg logit contributions | |
anmar | -0.547 |
eters | -0.478 |
ativity | -0.458 |
andum | -0.439 |
warts | -0.439 |
Token | Editor |
Token ID | 12058 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
subtitles | +0.412 |
Blu | +0.412 |
behavi | +0.409 |
ophy | +0.400 |
AU | +0.394 |
Neg logit contributions | |
anmar | -0.374 |
eters | -0.316 |
ativity | -0.299 |
andum | -0.285 |
warts | -0.284 |
Token | 's |
Token ID | 338 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
behavi | +0.350 |
subtitles | +0.349 |
Blu | +0.347 |
ophy | +0.340 |
AU | +0.336 |
Neg logit contributions | |
anmar | -0.361 |
eters | -0.310 |
ativity | -0.296 |
warts | -0.282 |
andum | -0.282 |
Token | Picks |
Token ID | 33957 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
anmar | +0.539 |
eters | +0.471 |
ativity | +0.449 |
warts | +0.435 |
andum | +0.434 |
Neg logit contributions | |
behavi | -0.435 |
subtitles | -0.423 |
Blu | -0.423 |
ophy | -0.415 |
AU | -0.412 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
anmar | +6.254 |
eters | +5.876 |
ativity | +5.237 |
initialized | +5.126 |
felt | +5.118 |
Neg logit contributions | |
behavi | -6.713 |
ophy | -6.141 |
puzz | -6.060 |
convol | -5.973 |
Blu | -5.894 |
Token |
|
Token ID | 198 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
anmar | +0.010 |
eters | +0.009 |
ativity | +0.008 |
warts | +0.008 |
andum | +0.008 |
Neg logit contributions | |
behavi | -0.004 |
subtitles | -0.004 |
Blu | -0.004 |
ophy | -0.004 |
AU | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
anmar | +1.500 |
eters | +1.365 |
ativity | +1.283 |
felt | +1.245 |
warts | +1.243 |
Neg logit contributions | |
behavi | -1.374 |
subtitles | -1.240 |
ophy | -1.217 |
Blu | -1.200 |
puzz | -1.197 |
Token | The |
Token ID | 464 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
anmar | +0.318 |
eters | +0.284 |
ativity | +0.273 |
warts | +0.264 |
andum | +0.264 |
Neg logit contributions | |
behavi | -0.191 |
subtitles | -0.188 |
Blu | -0.186 |
ophy | -0.180 |
AU | -0.176 |
Token | seeds |
Token ID | 11904 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
subtitles | +0.563 |
behavi | +0.562 |
Blu | +0.559 |
ophy | +0.548 |
AU | +0.533 |
Neg logit contributions | |
anmar | -0.686 |
eters | -0.598 |
ativity | -0.574 |
warts | -0.551 |
andum | -0.550 |
Token | � |
Token ID | 250 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
anmar | +2.247 |
eters | +1.827 |
ativity | +1.724 |
warts | +1.656 |
andum | +1.649 |
Neg logit contributions | |
behavi | -3.394 |
subtitles | -3.321 |
Blu | -3.273 |
ophy | -3.203 |
puzz | -3.189 |
Token | dr |
Token ID | 7109 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
anmar | +1.105 |
eters | +0.966 |
ativity | +0.925 |
warts | +0.892 |
andum | +0.889 |
Neg logit contributions | |
behavi | -0.866 |
subtitles | -0.860 |
Blu | -0.850 |
ophy | -0.830 |
AU | -0.815 |
Token | unk |
Token ID | 2954 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
Blu | +0.511 |
behavi | +0.510 |
subtitles | +0.509 |
ophy | +0.505 |
AU | +0.495 |
Neg logit contributions | |
anmar | -0.465 |
eters | -0.397 |
ativity | -0.370 |
�� | -0.357 |
warts | -0.353 |
Token | en |
Token ID | 268 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
anmar | +1.477 |
eters | +1.304 |
ativity | +1.254 |
warts | +1.208 |
andum | +1.207 |
Neg logit contributions | |
behavi | -0.960 |
subtitles | -0.954 |
Blu | -0.945 |
ophy | -0.923 |
AU | -0.908 |
Token | st |
Token ID | 336 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
anmar | +1.926 |
eters | +1.688 |
ativity | +1.618 |
warts | +1.558 |
andum | +1.556 |
Neg logit contributions | |
behavi | -1.441 |
subtitles | -1.429 |
Blu | -1.416 |
ophy | -1.386 |
AU | -1.366 |
Token | up |
Token ID | 929 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Blu | +1.088 |
subtitles | +1.075 |
ophy | +1.065 |
AU | +1.050 |
behavi | +1.040 |
Neg logit contributions | |
anmar | -1.477 |
eters | -1.293 |
ativity | -1.223 |
�� | -1.212 |
andum | -1.183 |
Token | or |
Token ID | 273 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
anmar | +7.143 |
eters | +6.261 |
ativity | +6.158 |
warts | +5.946 |
andum | +5.932 |
Neg logit contributions | |
behavi | -6.054 |
subtitles | -5.586 |
Blu | -5.518 |
AU | -5.299 |
puzz | -5.250 |
Token | � |
Token ID | 447 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
anmar | +1.732 |
eters | +1.534 |
ativity | +1.476 |
warts | +1.426 |
andum | +1.425 |
Neg logit contributions | |
behavi | -1.072 |
subtitles | -1.062 |
Blu | -1.051 |
ophy | -1.028 |
AU | -1.008 |
Token | � |
Token ID | 251 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
subtitles | +0.549 |
behavi | +0.546 |
Blu | +0.545 |
ophy | +0.535 |
AU | +0.526 |
Neg logit contributions | |
anmar | -0.682 |
eters | -0.596 |
ativity | -0.570 |
warts | -0.544 |
andum | -0.544 |
Token | — |
Token ID | 960 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
anmar | +2.031 |
eters | +1.781 |
ativity | +1.706 |
warts | +1.647 |
andum | +1.647 |
Neg logit contributions | |
behavi | -1.573 |
subtitles | -1.553 |
Blu | -1.537 |
ophy | -1.518 |
AU | -1.487 |
Token | and |
Token ID | 392 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
anmar | +1.353 |
eters | +1.186 |
ativity | +1.137 |
warts | +1.102 |
andum | +1.096 |
Neg logit contributions | |
behavi | -0.989 |
subtitles | -0.978 |
Blu | -0.972 |
ophy | -0.950 |
AU | -0.933 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
subtitles | +0.340 |
behavi | +0.339 |
Blu | +0.338 |
ophy | +0.328 |
AU | +0.322 |
Neg logit contributions | |
anmar | -0.498 |
eters | -0.439 |
ativity | -0.423 |
andum | -0.407 |
warts | -0.405 |
Token | game |
Token ID | 983 |
Feature activation | -9.76e-02 |
Pos logit contributions | |
anmar | +1.013 |
eters | +0.893 |
ativity | +0.854 |
warts | +0.830 |
andum | +0.824 |
Neg logit contributions | |
behavi | -0.670 |
subtitles | -0.652 |
Blu | -0.642 |
ophy | -0.635 |
AU | -0.627 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
subtitles | +0.298 |
Blu | +0.296 |
behavi | +0.296 |
ophy | +0.286 |
AU | +0.281 |
Neg logit contributions | |
anmar | -0.511 |
eters | -0.452 |
ativity | -0.437 |
andum | -0.422 |
warts | -0.421 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
anmar | +0.735 |
eters | +0.650 |
ativity | +0.622 |
warts | +0.600 |
andum | +0.600 |
Neg logit contributions | |
behavi | -0.519 |
subtitles | -0.509 |
Blu | -0.503 |
ophy | -0.496 |
AU | -0.485 |
Token | Share |
Token ID | 11649 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
anmar | +0.403 |
eters | +0.358 |
ativity | +0.345 |
andum | +0.333 |
warts | +0.333 |
Neg logit contributions | |
behavi | -0.233 |
subtitles | -0.231 |
Blu | -0.230 |
ophy | -0.224 |
AU | -0.220 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Blu | +1.529 |
subtitles | +1.519 |
behavi | +1.505 |
ophy | +1.437 |
AU | +1.437 |
Neg logit contributions | |
anmar | -2.579 |
eters | -2.288 |
ativity | -2.194 |
warts | -2.153 |
�� | -2.149 |
Token | Two |
Token ID | 4930 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
anmar | +6.741 |
eters | +6.090 |
ativity | +5.695 |
felt | +5.516 |
warts | +5.478 |
Neg logit contributions | |
behavi | -6.115 |
ophy | -5.429 |
subtitles | -5.337 |
puzz | -5.212 |
AU | -5.107 |
Token | iconic |
Token ID | 14133 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
anmar | +1.982 |
eters | +1.741 |
ativity | +1.666 |
warts | +1.613 |
andum | +1.598 |
Neg logit contributions | |
behavi | -1.374 |
subtitles | -1.344 |
Blu | -1.327 |
ophy | -1.315 |
AU | -1.291 |
Token | horror |
Token ID | 9961 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
behavi | +0.110 |
subtitles | +0.109 |
Blu | +0.108 |
ophy | +0.105 |
AU | +0.104 |
Neg logit contributions | |
anmar | -0.194 |
eters | -0.173 |
ativity | -0.167 |
andum | -0.161 |
warts | -0.161 |
Token | titles |
Token ID | 8714 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
subtitles | +1.192 |
Blu | +1.190 |
behavi | +1.172 |
ophy | +1.135 |
AU | +1.111 |
Neg logit contributions | |
anmar | -2.641 |
eters | -2.345 |
ativity | -2.283 |
andum | -2.227 |
�� | -2.191 |
Token | are |
Token ID | 389 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
behavi | +0.662 |
subtitles | +0.661 |
Blu | +0.657 |
ophy | +0.641 |
AU | +0.630 |
Neg logit contributions | |
anmar | -0.914 |
eters | -0.801 |
ativity | -0.770 |
andum | -0.740 |
warts | -0.739 |
Token | prises |
Token ID | 18166 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
Blu | +1.522 |
subtitles | +1.515 |
behavi | +1.493 |
ophy | +1.485 |
AU | +1.450 |
Neg logit contributions | |
anmar | -1.769 |
eters | -1.527 |
ativity | -1.462 |
andum | -1.398 |
warts | -1.376 |
Token |
|
Token ID | 198 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
anmar | +0.243 |
eters | +0.214 |
ativity | +0.205 |
andum | +0.197 |
warts | +0.197 |
Neg logit contributions | |
behavi | -0.174 |
subtitles | -0.173 |
Blu | -0.172 |
ophy | -0.168 |
AU | -0.165 |
Token |
|
Token ID | 198 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
anmar | +2.509 |
eters | +2.254 |
ativity | +2.126 |
felt | +2.070 |
warts | +2.069 |
Neg logit contributions | |
behavi | -2.190 |
subtitles | -2.026 |
ophy | -1.986 |
Blu | -1.955 |
puzz | -1.932 |
Token | P |
Token ID | 47 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
anmar | +1.868 |
eters | +1.657 |
ativity | +1.584 |
warts | +1.537 |
andum | +1.527 |
Neg logit contributions | |
behavi | -1.320 |
subtitles | -1.280 |
Blu | -1.262 |
ophy | -1.231 |
puzz | -1.191 |
Token | AS |
Token ID | 1921 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
subtitles | +0.197 |
Blu | +0.196 |
behavi | +0.195 |
ophy | +0.193 |
AU | +0.191 |
Neg logit contributions | |
anmar | -0.239 |
eters | -0.204 |
ativity | -0.198 |
andum | -0.191 |
warts | -0.190 |
Token | AD |
Token ID | 2885 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Blu | +2.248 |
subtitles | +2.219 |
AU | +2.199 |
ophy | +2.120 |
OVA | +2.056 |
Neg logit contributions | |
anmar | -5.655 |
eters | -4.951 |
ativity | -4.945 |
�� | -4.871 |
warts | -4.785 |
Token | ENA |
Token ID | 45510 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
Blu | +4.563 |
URA | +4.523 |
OVA | +4.521 |
AU | +4.476 |
subtitles | +4.414 |
Neg logit contributions | |
anmar | -10.898 |
eters | -9.744 |
�� | -9.572 |
ativity | -9.468 |
warts | -9.451 |
Token | , |
Token ID | 11 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Blu | +1.786 |
subtitles | +1.769 |
ophy | +1.727 |
AU | +1.725 |
behavi | +1.713 |
Neg logit contributions | |
anmar | -3.103 |
eters | -2.724 |
ativity | -2.655 |
warts | -2.582 |
�� | -2.577 |
Token | Calif |
Token ID | 3192 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
subtitles | +1.040 |
Blu | +1.036 |
behavi | +1.026 |
ophy | +0.991 |
AU | +0.984 |
Neg logit contributions | |
anmar | -2.542 |
eters | -2.282 |
ativity | -2.208 |
warts | -2.147 |
andum | -2.135 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Blu | +3.824 |
AU | +3.769 |
ophy | +3.716 |
subtitles | +3.663 |
behavi | +3.641 |
Neg logit contributions | |
anmar | -6.960 |
eters | -6.187 |
�� | -6.018 |
ativity | -5.981 |
warts | -5.866 |
Token | -- |
Token ID | 1377 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
Blu | +0.527 |
subtitles | +0.524 |
behavi | +0.518 |
ophy | +0.506 |
AU | +0.506 |
Neg logit contributions | |
anmar | -1.011 |
eters | -0.901 |
ativity | -0.868 |
warts | -0.844 |
andum | -0.842 |
Token | the |
Token ID | 262 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
behavi | +0.287 |
subtitles | +0.283 |
Blu | +0.281 |
ophy | +0.276 |
AU | +0.272 |
Neg logit contributions | |
anmar | -0.372 |
eters | -0.325 |
ativity | -0.312 |
andum | -0.299 |
warts | -0.299 |
Token | Marxist |
Token ID | 26305 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
behavi | +0.148 |
subtitles | +0.147 |
Blu | +0.146 |
ophy | +0.143 |
AU | +0.141 |
Neg logit contributions | |
anmar | -0.197 |
eters | -0.173 |
ativity | -0.166 |
warts | -0.159 |
andum | -0.159 |
Token | takeover |
Token ID | 27011 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
subtitles | +1.404 |
behavi | +1.399 |
Blu | +1.394 |
ophy | +1.353 |
AU | +1.334 |
Neg logit contributions | |
anmar | -1.958 |
eters | -1.722 |
ativity | -1.659 |
warts | -1.595 |
andum | -1.594 |
Token | of |
Token ID | 286 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
Blu | +1.812 |
subtitles | +1.810 |
behavi | +1.794 |
ophy | +1.737 |
AU | +1.698 |
Neg logit contributions | |
anmar | -3.272 |
eters | -2.897 |
ativity | -2.811 |
�� | -2.729 |
andum | -2.725 |
Token | V |
Token ID | 569 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
behavi | +0.228 |
subtitles | +0.227 |
Blu | +0.226 |
ophy | +0.220 |
AU | +0.216 |
Neg logit contributions | |
anmar | -0.343 |
eters | -0.303 |
ativity | -0.292 |
andum | -0.281 |
warts | -0.280 |
Token | enez |
Token ID | 11437 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
anmar | +0.956 |
eters | +0.836 |
ativity | +0.802 |
�� | +0.774 |
warts | +0.769 |
Neg logit contributions | |
subtitles | -0.739 |
Blu | -0.737 |
behavi | -0.733 |
ophy | -0.721 |
AU | -0.720 |
Token | ue |
Token ID | 518 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Blu | +5.448 |
ophy | +5.429 |
subtitles | +5.343 |
ci | +4.997 |
AU | +4.995 |
Neg logit contributions | |
anmar | -8.744 |
eters | -7.866 |
�� | -7.801 |
warts | -7.463 |
ativity | -7.395 |
Token | ... |
Token ID | 986 |
Feature activation | +8.69e-03 |
Pos logit contributions | |
subtitles | +0.947 |
behavi | +0.944 |
Blu | +0.939 |
ophy | +0.916 |
AU | +0.905 |
Neg logit contributions | |
anmar | -1.359 |
eters | -1.199 |
ativity | -1.154 |
warts | -1.113 |
andum | -1.107 |
Token |
|
Token ID | 198 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
anmar | +0.045 |
eters | +0.040 |
ativity | +0.038 |
warts | +0.037 |
andum | +0.037 |
Neg logit contributions | |
behavi | -0.027 |
subtitles | -0.027 |
Blu | -0.027 |
ophy | -0.026 |
AU | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
behavi | +0.125 |
subtitles | +0.118 |
Blu | +0.116 |
ophy | +0.115 |
puzz | +0.112 |
Neg logit contributions | |
anmar | -0.164 |
eters | -0.147 |
ativity | -0.139 |
warts | -0.135 |
andum | -0.135 |
Token | From |
Token ID | 4863 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
anmar | +0.670 |
eters | +0.596 |
ativity | +0.572 |
warts | +0.554 |
andum | +0.554 |
Neg logit contributions | |
behavi | -0.404 |
subtitles | -0.395 |
Blu | -0.390 |
ophy | -0.380 |
AU | -0.368 |
Token | radius |
Token ID | 16874 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
behavi | +2.085 |
subtitles | +2.082 |
Blu | +2.080 |
ophy | +2.036 |
AU | +1.990 |
Neg logit contributions | |
anmar | -2.421 |
eters | -2.085 |
ativity | -1.975 |
�� | -1.920 |
warts | -1.911 |
Token | , |
Token ID | 11 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
behavi | +0.376 |
subtitles | +0.376 |
Blu | +0.375 |
ophy | +0.365 |
AU | +0.359 |
Neg logit contributions | |
anmar | -0.486 |
eters | -0.422 |
ativity | -0.405 |
warts | -0.391 |
andum | -0.390 |
Token | combined |
Token ID | 5929 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
anmar | +0.614 |
eters | +0.536 |
ativity | +0.512 |
warts | +0.491 |
andum | +0.491 |
Neg logit contributions | |
behavi | -0.507 |
subtitles | -0.503 |
Blu | -0.496 |
ophy | -0.488 |
AU | -0.482 |
Token | with |
Token ID | 351 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
behavi | +0.105 |
subtitles | +0.104 |
Blu | +0.102 |
ophy | +0.101 |
AU | +0.099 |
Neg logit contributions | |
anmar | -0.139 |
eters | -0.122 |
ativity | -0.117 |
andum | -0.112 |
warts | -0.112 |
Token | his |
Token ID | 465 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Blu | +1.386 |
behavi | +1.385 |
subtitles | +1.376 |
ophy | +1.336 |
AU | +1.303 |
Neg logit contributions | |
anmar | -1.992 |
eters | -1.750 |
ativity | -1.674 |
warts | -1.610 |
andum | -1.608 |
Token | natural |
Token ID | 3288 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
behavi | +1.122 |
Blu | +1.120 |
subtitles | +1.117 |
ophy | +1.089 |
AU | +1.062 |
Neg logit contributions | |
anmar | -1.469 |
eters | -1.287 |
ativity | -1.236 |
warts | -1.185 |
andum | -1.184 |
Token | body |
Token ID | 1767 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
Blu | +5.689 |
behavi | +5.566 |
subtitles | +5.557 |
puzz | +5.485 |
touchdowns | +5.467 |
Neg logit contributions | |
anmar | -8.331 |
eters | -7.256 |
ativity | -7.072 |
�� | -6.843 |
warts | -6.758 |
Token | positioning |
Token ID | 22097 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
behavi | +3.003 |
Blu | +2.954 |
subtitles | +2.924 |
ophy | +2.863 |
puzz | +2.805 |
Neg logit contributions | |
anmar | -4.501 |
eters | -3.901 |
ativity | -3.711 |
�� | -3.679 |
warts | -3.621 |
Token | , |
Token ID | 11 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
behavi | +1.868 |
subtitles | +1.860 |
Blu | +1.854 |
ophy | +1.803 |
AU | +1.753 |
Neg logit contributions | |
anmar | -2.946 |
eters | -2.567 |
ativity | -2.471 |
warts | -2.401 |
andum | -2.381 |
Token | gave |
Token ID | 2921 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
subtitles | +1.447 |
Blu | +1.444 |
behavi | +1.435 |
ophy | +1.398 |
AU | +1.369 |
Neg logit contributions | |
anmar | -2.075 |
eters | -1.811 |
ativity | -1.749 |
andum | -1.677 |
warts | -1.672 |
Token | T |
Token ID | 309 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
anmar | +0.395 |
eters | +0.341 |
ativity | +0.326 |
andum | +0.314 |
warts | +0.312 |
Neg logit contributions | |
behavi | -0.335 |
subtitles | -0.334 |
Blu | -0.333 |
ophy | -0.325 |
AU | -0.320 |
Token | not |
Token ID | 407 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
anmar | +1.423 |
eters | +1.245 |
ativity | +1.188 |
andum | +1.141 |
warts | +1.137 |
Neg logit contributions | |
behavi | -1.106 |
subtitles | -1.102 |
Blu | -1.092 |
ophy | -1.075 |
AU | -1.052 |
Token | the |
Token ID | 262 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
anmar | +2.529 |
eters | +2.156 |
ativity | +2.068 |
felt | +2.001 |
warts | +1.989 |
Neg logit contributions | |
behavi | -2.612 |
puzz | -2.396 |
ophy | -2.393 |
AU | -2.389 |
subtitles | -2.385 |
Token | position |
Token ID | 2292 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
anmar | +0.374 |
eters | +0.323 |
ativity | +0.309 |
felt | +0.292 |
warts | +0.291 |
Neg logit contributions | |
behavi | -0.348 |
AU | -0.334 |
subtitles | -0.332 |
ophy | -0.328 |
Blu | -0.327 |
Token | of |
Token ID | 286 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
anmar | +2.099 |
eters | +1.866 |
ativity | +1.817 |
andum | +1.728 |
warts | +1.715 |
Neg logit contributions | |
behavi | -1.649 |
subtitles | -1.579 |
Blu | -1.531 |
ophy | -1.512 |
AU | -1.501 |
Token | EUR |
Token ID | 27526 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
anmar | +1.901 |
eters | +1.613 |
ativity | +1.550 |
felt | +1.476 |
andum | +1.473 |
Neg logit contributions | |
behavi | -1.701 |
subtitles | -1.658 |
ophy | -1.652 |
puzz | -1.619 |
AU | -1.617 |
Token | OP |
Token ID | 3185 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
behavi | +0.609 |
Blu | +0.593 |
subtitles | +0.584 |
ophy | +0.561 |
puzz | +0.548 |
Neg logit contributions | |
anmar | -1.273 |
eters | -1.138 |
ativity | -1.110 |
andum | -1.072 |
warts | -1.071 |
Token | P |
Token ID | 47 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
subtitles | +4.567 |
AU | +4.297 |
ophy | +4.225 |
Blu | +4.223 |
puzz | +3.866 |
Neg logit contributions | |
anmar | -9.725 |
�� | -8.670 |
eters | -8.506 |
ativity | -8.185 |
felt | -8.047 |
Token | – |
Token ID | 784 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
subtitles | +2.184 |
Blu | +2.146 |
ophy | +2.079 |
AU | +2.076 |
behavi | +2.068 |
Neg logit contributions | |
anmar | -2.985 |
eters | -2.584 |
ativity | -2.535 |
�� | -2.493 |
warts | -2.396 |
Token | European |
Token ID | 3427 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
anmar | +1.943 |
eters | +1.684 |
ativity | +1.613 |
andum | +1.543 |
warts | +1.530 |
Neg logit contributions | |
behavi | -1.531 |
Blu | -1.471 |
subtitles | -1.462 |
ophy | -1.458 |
AU | -1.435 |
Token | Politics |
Token ID | 17554 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
subtitles | +0.813 |
behavi | +0.808 |
Blu | +0.806 |
ophy | +0.799 |
AU | +0.781 |
Neg logit contributions | |
anmar | -0.689 |
eters | -0.589 |
ativity | -0.550 |
�� | -0.529 |
warts | -0.527 |
Token | and |
Token ID | 290 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
subtitles | +1.361 |
Blu | +1.347 |
behavi | +1.303 |
ophy | +1.303 |
AU | +1.285 |
Neg logit contributions | |
anmar | -1.988 |
eters | -1.762 |
ativity | -1.707 |
�� | -1.655 |
warts | -1.618 |
Token | 47 |
Token ID | 2857 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
subtitles | +0.144 |
behavi | +0.144 |
Blu | +0.142 |
ophy | +0.138 |
AU | +0.134 |
Neg logit contributions | |
anmar | -0.379 |
eters | -0.340 |
ativity | -0.329 |
andum | -0.320 |
warts | -0.318 |
Token | ] |
Token ID | 60 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
behavi | +0.068 |
subtitles | +0.065 |
Blu | +0.064 |
ophy | +0.063 |
puzz | +0.062 |
Neg logit contributions | |
anmar | -0.065 |
eters | -0.057 |
ativity | -0.054 |
warts | -0.052 |
andum | -0.052 |
Token | < |
Token ID | 1279 |
Feature activation | +5.89e-02 |
Pos logit contributions | |
anmar | +1.437 |
eters | +1.279 |
ativity | +1.236 |
andum | +1.196 |
warts | +1.194 |
Neg logit contributions | |
behavi | -0.748 |
subtitles | -0.744 |
Blu | -0.737 |
ophy | -0.712 |
AU | -0.703 |
Token | t |
Token ID | 83 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
anmar | +0.278 |
eters | +0.244 |
ativity | +0.234 |
andum | +0.225 |
warts | +0.224 |
Neg logit contributions | |
behavi | -0.209 |
subtitles | -0.208 |
Blu | -0.207 |
ophy | -0.203 |
AU | -0.200 |
Token | it |
Token ID | 270 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
anmar | +0.494 |
eters | +0.429 |
ativity | +0.411 |
andum | +0.394 |
warts | +0.394 |
Neg logit contributions | |
behavi | -0.408 |
subtitles | -0.408 |
Blu | -0.406 |
ophy | -0.399 |
AU | -0.392 |
Token | ou |
Token ID | 280 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
anmar | +1.685 |
eters | +1.467 |
ativity | +1.403 |
warts | +1.348 |
andum | +1.347 |
Neg logit contributions | |
behavi | -1.436 |
subtitles | -1.415 |
Blu | -1.401 |
ophy | -1.366 |
AU | -1.353 |
Token | kay |
Token ID | 5568 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
Blu | +6.391 |
ophy | +6.339 |
AU | +6.335 |
subtitles | +6.308 |
behavi | +6.034 |
Neg logit contributions | |
anmar | -7.073 |
eters | -6.047 |
ativity | -5.947 |
andum | -5.735 |
�� | -5.613 |
Token | > |
Token ID | 29 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Blu | +2.990 |
ophy | +2.979 |
subtitles | +2.978 |
AU | +2.913 |
behavi | +2.863 |
Neg logit contributions | |
anmar | -3.287 |
eters | -2.843 |
ativity | -2.721 |
andum | -2.617 |
�� | -2.595 |
Token | lol |
Token ID | 19462 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
subtitles | +0.964 |
behavi | +0.964 |
Blu | +0.960 |
ophy | +0.934 |
AU | +0.918 |
Neg logit contributions | |
anmar | -1.319 |
eters | -1.153 |
ativity | -1.113 |
andum | -1.065 |
warts | -1.065 |
Token | m |
Token ID | 285 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
subtitles | +1.979 |
Blu | +1.972 |
behavi | +1.960 |
ophy | +1.929 |
AU | +1.870 |
Neg logit contributions | |
anmar | -3.011 |
eters | -2.632 |
ativity | -2.538 |
andum | -2.430 |
warts | -2.426 |
Token | 2 |
Token ID | 17 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
subtitles | +1.358 |
Blu | +1.357 |
behavi | +1.340 |
ophy | +1.337 |
AU | +1.315 |
Neg logit contributions | |
anmar | -2.446 |
eters | -2.156 |
ativity | -2.094 |
warts | -2.020 |
andum | -2.012 |
Token | space |
Token ID | 2272 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
anmar | +1.065 |
eters | +0.907 |
ativity | +0.860 |
andum | +0.818 |
warts | +0.817 |
Neg logit contributions | |
behavi | -1.174 |
subtitles | -1.162 |
Blu | -1.151 |
ophy | -1.139 |
AU | -1.122 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
anmar | +4.661 |
eters | +4.073 |
ativity | +3.902 |
andum | +3.734 |
warts | +3.713 |
Neg logit contributions | |
behavi | -3.750 |
subtitles | -3.629 |
Blu | -3.569 |
ophy | -3.565 |
AU | -3.518 |
Token |
|
Token ID | 198 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
anmar | +1.621 |
eters | +1.435 |
ativity | +1.376 |
warts | +1.325 |
andum | +1.322 |
Neg logit contributions | |
behavi | -1.084 |
subtitles | -1.060 |
Blu | -1.043 |
ophy | -1.031 |
AU | -1.006 |
Token |
|
Token ID | 198 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
anmar | +1.680 |
eters | +1.536 |
ativity | +1.435 |
felt | +1.402 |
warts | +1.396 |
Neg logit contributions | |
behavi | -1.595 |
subtitles | -1.421 |
ophy | -1.390 |
puzz | -1.377 |
Blu | -1.369 |
Token | OR |
Token ID | 1581 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
anmar | +1.315 |
eters | +1.174 |
ativity | +1.127 |
warts | +1.095 |
andum | +1.086 |
Neg logit contributions | |
behavi | -0.801 |
subtitles | -0.774 |
Blu | -0.761 |
ophy | -0.746 |
puzz | -0.721 |
Token | IG |
Token ID | 3528 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
anmar | +1.004 |
eters | +0.884 |
ativity | +0.850 |
andum | +0.819 |
warts | +0.818 |
Neg logit contributions | |
behavi | -0.684 |
subtitles | -0.675 |
Blu | -0.668 |
ophy | -0.656 |
AU | -0.641 |
Token | INAL |
Token ID | 17961 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
Blu | +3.809 |
subtitles | +3.746 |
AU | +3.703 |
ophy | +3.480 |
OVA | +3.345 |
Neg logit contributions | |
anmar | -9.830 |
eters | -8.820 |
�� | -8.672 |
ativity | -8.454 |
andum | -8.399 |
Token | STORY |
Token ID | 46427 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
behavi | +0.166 |
subtitles | +0.164 |
Blu | +0.162 |
ophy | +0.159 |
AU | +0.155 |
Neg logit contributions | |
anmar | -0.270 |
eters | -0.240 |
ativity | -0.231 |
andum | -0.222 |
warts | -0.222 |
Token | : |
Token ID | 25 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Blu | +1.444 |
subtitles | +1.444 |
behavi | +1.405 |
AU | +1.381 |
ophy | +1.373 |
Neg logit contributions | |
anmar | -2.357 |
eters | -2.064 |
ativity | -1.988 |
andum | -1.924 |
warts | -1.920 |
Token | Back |
Token ID | 5157 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
anmar | +1.496 |
eters | +1.317 |
ativity | +1.263 |
warts | +1.214 |
andum | +1.214 |
Neg logit contributions | |
behavi | -1.079 |
subtitles | -1.050 |
Blu | -1.034 |
ophy | -1.029 |
AU | -1.000 |
Token | ers |
Token ID | 364 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
Blu | +1.347 |
subtitles | +1.331 |
behavi | +1.314 |
ophy | +1.276 |
AU | +1.267 |
Neg logit contributions | |
anmar | -2.423 |
eters | -2.145 |
ativity | -2.086 |
andum | -2.042 |
warts | -2.027 |
Token | blowing |
Token ID | 19280 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
behavi | +0.811 |
subtitles | +0.806 |
Blu | +0.800 |
ophy | +0.781 |
AU | +0.769 |
Neg logit contributions | |
anmar | -1.094 |
eters | -0.958 |
ativity | -0.919 |
warts | -0.884 |
andum | -0.884 |
Token | up |
Token ID | 510 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
anmar | +0.218 |
eters | +0.191 |
ativity | +0.182 |
warts | +0.175 |
andum | +0.174 |
Neg logit contributions | |
behavi | -0.182 |
subtitles | -0.180 |
Blu | -0.179 |
ophy | -0.175 |
AU | -0.173 |
Token | — |
Token ID | 960 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
anmar | +0.860 |
eters | +0.755 |
ativity | +0.724 |
warts | +0.696 |
andum | +0.689 |
Neg logit contributions | |
behavi | -0.662 |
subtitles | -0.654 |
Blu | -0.647 |
ophy | -0.640 |
AU | -0.630 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
behavi | +0.129 |
subtitles | +0.128 |
Blu | +0.128 |
ophy | +0.125 |
AU | +0.123 |
Neg logit contributions | |
anmar | -0.163 |
eters | -0.142 |
ativity | -0.136 |
andum | -0.131 |
warts | -0.131 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Blu | +3.315 |
subtitles | +3.203 |
AU | +3.137 |
ophy | +3.008 |
OVA | +2.852 |
Neg logit contributions | |
anmar | -7.140 |
�� | -6.142 |
eters | -6.067 |
ativity | -6.015 |
�醒 | -5.832 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
AU | +3.703 |
Blu | +3.559 |
subtitles | +3.492 |
ophy | +3.460 |
OVA | +3.381 |
Neg logit contributions | |
anmar | -5.860 |
eters | -4.931 |
ativity | -4.906 |
�� | -4.837 |
andum | -4.688 |
Token |
|
Token ID | 198 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Blu | +4.358 |
subtitles | +4.122 |
AU | +3.999 |
OVA | +3.843 |
ophy | +3.778 |
Neg logit contributions | |
anmar | -9.745 |
eters | -8.629 |
ativity | -8.198 |
warts | -8.179 |
andum | -8.007 |
Token |
|
Token ID | 198 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
subtitles | +1.286 |
behavi | +1.280 |
Blu | +1.279 |
ophy | +1.243 |
AU | +1.227 |
Neg logit contributions | |
anmar | -2.036 |
eters | -1.793 |
ativity | -1.727 |
warts | -1.664 |
andum | -1.664 |
Token | N |
Token ID | 45 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
Blu | +1.538 |
subtitles | +1.538 |
AU | +1.519 |
behavi | +1.506 |
ophy | +1.503 |
Neg logit contributions | |
anmar | -2.434 |
eters | -2.115 |
ativity | -2.053 |
andum | -1.974 |
warts | -1.972 |
Token | PH |
Token ID | 11909 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
behavi | +0.088 |
subtitles | +0.088 |
Blu | +0.087 |
ophy | +0.085 |
AU | +0.084 |
Neg logit contributions | |
anmar | -0.161 |
eters | -0.143 |
ativity | -0.138 |
warts | -0.134 |
andum | -0.134 |
Token | : |
Token ID | 25 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
subtitles | +2.238 |
Blu | +2.238 |
ophy | +2.154 |
AU | +2.135 |
behavi | +2.118 |
Neg logit contributions | |
anmar | -3.826 |
eters | -3.360 |
ativity | -3.234 |
andum | -3.163 |
warts | -3.128 |
Token | - |
Token ID | 12 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
behavi | +0.654 |
Blu | +0.652 |
subtitles | +0.649 |
ophy | +0.640 |
AU | +0.619 |
Neg logit contributions | |
anmar | -1.182 |
eters | -1.052 |
ativity | -1.015 |
warts | -0.991 |
andum | -0.978 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
anmar | +1.485 |
eters | +1.322 |
ativity | +1.277 |
andum | +1.233 |
warts | +1.232 |
Neg logit contributions | |
behavi | -0.793 |
subtitles | -0.789 |
Blu | -0.783 |
ophy | -0.763 |
AU | -0.748 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
behavi | +0.524 |
Blu | +0.520 |
subtitles | +0.519 |
ophy | +0.508 |
AU | +0.495 |
Neg logit contributions | |
anmar | -0.892 |
eters | -0.791 |
ativity | -0.762 |
warts | -0.741 |
andum | -0.736 |
Token | with |
Token ID | 351 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
behavi | +0.477 |
subtitles | +0.477 |
Blu | +0.474 |
ophy | +0.462 |
AU | +0.453 |
Neg logit contributions | |
anmar | -0.616 |
eters | -0.537 |
ativity | -0.517 |
warts | -0.496 |
andum | -0.495 |
Token | two |
Token ID | 734 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
Blu | +1.725 |
subtitles | +1.720 |
behavi | +1.686 |
ophy | +1.644 |
AU | +1.609 |
Neg logit contributions | |
anmar | -2.497 |
eters | -2.197 |
ativity | -2.124 |
warts | -2.042 |
andum | -2.040 |
Token | natural |
Token ID | 3288 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Blu | +1.626 |
subtitles | +1.619 |
behavi | +1.599 |
ophy | +1.559 |
AU | +1.521 |
Neg logit contributions | |
anmar | -2.148 |
eters | -1.868 |
ativity | -1.812 |
andum | -1.737 |
warts | -1.734 |
Token | wing |
Token ID | 8539 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
Blu | +5.762 |
subtitles | +5.674 |
puzz | +5.481 |
ophy | +5.468 |
openings | +5.360 |
Neg logit contributions | |
anmar | -7.776 |
eters | -6.678 |
ativity | -6.656 |
initialized | -6.280 |
�� | -6.241 |
Token | ers |
Token ID | 364 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
behavi | +0.183 |
subtitles | +0.182 |
Blu | +0.181 |
ophy | +0.176 |
AU | +0.172 |
Neg logit contributions | |
anmar | -0.348 |
eters | -0.308 |
ativity | -0.299 |
andum | -0.291 |
warts | -0.287 |
Token | , |
Token ID | 11 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Blu | +1.991 |
subtitles | +1.978 |
behavi | +1.938 |
ophy | +1.910 |
AU | +1.865 |
Neg logit contributions | |
anmar | -2.583 |
eters | -2.228 |
ativity | -2.163 |
warts | -2.089 |
andum | -2.074 |
Token | and |
Token ID | 290 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Blu | +0.868 |
subtitles | +0.866 |
behavi | +0.860 |
ophy | +0.836 |
AU | +0.819 |
Neg logit contributions | |
anmar | -1.206 |
eters | -1.057 |
ativity | -1.018 |
warts | -0.980 |
andum | -0.977 |
Token | Holland |
Token ID | 16070 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
Blu | +1.094 |
subtitles | +1.092 |
behavi | +1.078 |
ophy | +1.049 |
AU | +1.031 |
Neg logit contributions | |
anmar | -1.492 |
eters | -1.300 |
ativity | -1.254 |
warts | -1.212 |
andum | -1.202 |
Token | and |
Token ID | 290 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
anmar | +0.040 |
eters | +0.035 |
ativity | +0.033 |
warts | +0.032 |
andum | +0.032 |
Neg logit contributions | |
behavi | -0.027 |
subtitles | -0.027 |
Blu | -0.027 |
ophy | -0.026 |
AU | -0.025 |
Token | bends |
Token ID | 44370 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
anmar | +2.865 |
eters | +2.578 |
ativity | +2.427 |
warts | +2.373 |
andum | +2.332 |
Neg logit contributions | |
behavi | -2.305 |
Blu | -2.228 |
subtitles | -2.222 |
AU | -2.198 |
ophy | -2.196 |
Token | the |
Token ID | 262 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
behavi | +0.089 |
subtitles | +0.089 |
Blu | +0.089 |
ophy | +0.087 |
AU | +0.085 |
Neg logit contributions | |
anmar | -0.115 |
eters | -0.100 |
ativity | -0.096 |
andum | -0.092 |
warts | -0.092 |
Token | rules |
Token ID | 3173 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
Blu | +0.627 |
behavi | +0.627 |
subtitles | +0.626 |
ophy | +0.611 |
AU | +0.594 |
Neg logit contributions | |
anmar | -0.840 |
eters | -0.730 |
ativity | -0.705 |
warts | -0.676 |
andum | -0.676 |
Token | set |
Token ID | 900 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
anmar | +0.228 |
eters | +0.199 |
ativity | +0.192 |
warts | +0.186 |
andum | +0.186 |
Neg logit contributions | |
behavi | -0.142 |
subtitles | -0.142 |
Blu | -0.142 |
ophy | -0.138 |
AU | -0.136 |
Token | out |
Token ID | 503 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Blu | +2.669 |
subtitles | +2.649 |
behavi | +2.630 |
ophy | +2.593 |
AU | +2.506 |
Neg logit contributions | |
anmar | -4.555 |
eters | -3.930 |
ativity | -3.800 |
warts | -3.715 |
andum | -3.682 |
Token | in |
Token ID | 287 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
Blu | +4.655 |
subtitles | +4.627 |
behavi | +4.561 |
ophy | +4.473 |
AU | +4.344 |
Neg logit contributions | |
anmar | -8.838 |
eters | -7.761 |
ativity | -7.494 |
warts | -7.390 |
andum | -7.275 |
Token | the |
Token ID | 262 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
Blu | +2.586 |
subtitles | +2.566 |
behavi | +2.530 |
ophy | +2.461 |
AU | +2.385 |
Neg logit contributions | |
anmar | -4.000 |
eters | -3.502 |
ativity | -3.369 |
warts | -3.279 |
andum | -3.230 |
Token | Tall |
Token ID | 22676 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
Blu | +2.270 |
subtitles | +2.246 |
behavi | +2.211 |
ophy | +2.184 |
AU | +2.124 |
Neg logit contributions | |
anmar | -2.764 |
eters | -2.395 |
ativity | -2.282 |
warts | -2.213 |
andum | -2.184 |
Token | Building |
Token ID | 11819 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Blu | +0.004 |
behavi | +0.004 |
subtitles | +0.004 |
ophy | +0.004 |
AU | +0.004 |
Neg logit contributions | |
anmar | -0.005 |
eters | -0.004 |
ativity | -0.004 |
warts | -0.004 |
andum | -0.004 |
Token | Design |
Token ID | 8495 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Blu | +1.274 |
subtitles | +1.259 |
behavi | +1.254 |
ophy | +1.232 |
AU | +1.203 |
Neg logit contributions | |
anmar | -1.540 |
eters | -1.318 |
ativity | -1.262 |
warts | -1.233 |
andum | -1.209 |
Token | bad |
Token ID | 2089 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
Blu | +2.019 |
subtitles | +2.000 |
behavi | +1.990 |
ophy | +1.959 |
puzz | +1.934 |
Neg logit contributions | |
anmar | -2.344 |
eters | -2.039 |
ativity | -1.948 |
andum | -1.888 |
warts | -1.878 |
Token | idea |
Token ID | 2126 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
Blu | +2.620 |
behavi | +2.608 |
subtitles | +2.606 |
ophy | +2.554 |
puzz | +2.482 |
Neg logit contributions | |
anmar | -2.634 |
eters | -2.277 |
ativity | -2.143 |
�� | -2.082 |
warts | -2.078 |
Token | . |
Token ID | 13 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
anmar | +2.283 |
eters | +2.014 |
ativity | +1.922 |
andum | +1.841 |
warts | +1.840 |
Neg logit contributions | |
behavi | -1.707 |
subtitles | -1.684 |
Blu | -1.653 |
ophy | -1.644 |
AU | -1.604 |
Token | Why |
Token ID | 4162 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
anmar | +0.368 |
eters | +0.323 |
ativity | +0.309 |
andum | +0.296 |
warts | +0.296 |
Neg logit contributions | |
behavi | -0.283 |
subtitles | -0.280 |
Blu | -0.277 |
ophy | -0.273 |
AU | -0.267 |
Token | on |
Token ID | 319 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
subtitles | +3.085 |
Blu | +3.082 |
behavi | +3.004 |
ophy | +2.936 |
AU | +2.889 |
Neg logit contributions | |
anmar | -4.027 |
eters | -3.437 |
ativity | -3.330 |
andum | -3.251 |
�� | -3.232 |
Token | Earth |
Token ID | 3668 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Blu | +1.451 |
behavi | +1.436 |
subtitles | +1.413 |
ophy | +1.396 |
AU | +1.379 |
Neg logit contributions | |
anmar | -2.361 |
eters | -2.065 |
ativity | -1.982 |
warts | -1.926 |
andum | -1.902 |
Token | would |
Token ID | 561 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
Blu | +5.058 |
subtitles | +4.997 |
behavi | +4.741 |
AU | +4.700 |
ophy | +4.694 |
Neg logit contributions | |
anmar | -8.628 |
eters | -7.419 |
ativity | -7.248 |
�� | -7.241 |
andum | -7.115 |
Token | archive |
Token ID | 15424 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
subtitles | +2.813 |
Blu | +2.803 |
behavi | +2.728 |
ophy | +2.670 |
AU | +2.619 |
Neg logit contributions | |
anmar | -3.530 |
eters | -3.045 |
ativity | -2.920 |
andum | -2.831 |
warts | -2.818 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
subtitles | +0.735 |
behavi | +0.732 |
Blu | +0.728 |
ophy | +0.707 |
AU | +0.697 |
Neg logit contributions | |
anmar | -1.062 |
eters | -0.931 |
ativity | -0.895 |
andum | -0.865 |
warts | -0.864 |
Token | org |
Token ID | 2398 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
anmar | +1.208 |
eters | +1.067 |
ativity | +1.027 |
andum | +0.990 |
warts | +0.989 |
Neg logit contributions | |
behavi | -0.769 |
subtitles | -0.764 |
Blu | -0.759 |
ophy | -0.740 |
AU | -0.728 |
Token | allow |
Token ID | 1249 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
anmar | +1.021 |
eters | +0.897 |
ativity | +0.853 |
warts | +0.821 |
andum | +0.817 |
Neg logit contributions | |
behavi | -0.845 |
subtitles | -0.827 |
Blu | -0.819 |
ophy | -0.808 |
AU | -0.796 |
Token | important |
Token ID | 1593 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
behavi | +0.523 |
subtitles | +0.522 |
Blu | +0.519 |
ophy | +0.506 |
AU | +0.499 |
Neg logit contributions | |
anmar | -0.579 |
eters | -0.499 |
ativity | -0.477 |
andum | -0.457 |
warts | -0.457 |
Token | ingredient |
Token ID | 18734 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
anmar | +3.317 |
eters | +2.904 |
ativity | +2.814 |
andum | +2.720 |
warts | +2.682 |
Neg logit contributions | |
behavi | -2.650 |
subtitles | -2.586 |
Blu | -2.562 |
ophy | -2.560 |
AU | -2.517 |
Token | in |
Token ID | 287 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
anmar | +1.141 |
eters | +1.000 |
ativity | +0.958 |
warts | +0.921 |
andum | +0.921 |
Neg logit contributions | |
behavi | -0.851 |
subtitles | -0.846 |
Blu | -0.840 |
ophy | -0.821 |
AU | -0.808 |
Token | a |
Token ID | 257 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
behavi | +0.272 |
subtitles | +0.270 |
Blu | +0.269 |
ophy | +0.262 |
AU | +0.258 |
Neg logit contributions | |
anmar | -0.363 |
eters | -0.318 |
ativity | -0.304 |
andum | -0.292 |
warts | -0.292 |
Token | poly |
Token ID | 7514 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
behavi | +0.904 |
Blu | +0.900 |
subtitles | +0.897 |
ophy | +0.867 |
AU | +0.856 |
Neg logit contributions | |
anmar | -1.177 |
eters | -1.027 |
ativity | -0.984 |
andum | -0.947 |
warts | -0.946 |
Token | gl |
Token ID | 4743 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
subtitles | +0.503 |
behavi | +0.502 |
Blu | +0.498 |
ophy | +0.492 |
AU | +0.480 |
Neg logit contributions | |
anmar | -0.927 |
eters | -0.830 |
ativity | -0.789 |
andum | -0.773 |
�� | -0.766 |
Token | ot |
Token ID | 313 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ophy | +3.461 |
subtitles | +3.284 |
Blu | +3.042 |
puzz | +2.729 |
ci | +2.687 |
Neg logit contributions | |
anmar | -10.341 |
eters | -9.193 |
�� | -8.820 |
warts | -8.663 |
ativity | -8.593 |
Token | stew |
Token ID | 20798 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
behavi | +0.543 |
subtitles | +0.539 |
Blu | +0.538 |
ophy | +0.524 |
AU | +0.515 |
Neg logit contributions | |
anmar | -0.803 |
eters | -0.708 |
ativity | -0.677 |
warts | -0.653 |
andum | -0.652 |
Token | that |
Token ID | 326 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
anmar | +1.097 |
eters | +0.969 |
ativity | +0.930 |
andum | +0.896 |
warts | +0.896 |
Neg logit contributions | |
behavi | -0.732 |
subtitles | -0.727 |
Blu | -0.722 |
ophy | -0.705 |
AU | -0.693 |
Token | goes |
Token ID | 2925 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
subtitles | +1.186 |
behavi | +1.183 |
Blu | +1.179 |
ophy | +1.144 |
AU | +1.124 |
Neg logit contributions | |
anmar | -1.421 |
eters | -1.226 |
ativity | -1.174 |
andum | -1.129 |
warts | -1.117 |
Token | way |
Token ID | 835 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
anmar | +2.222 |
eters | +1.933 |
ativity | +1.830 |
warts | +1.775 |
andum | +1.762 |
Neg logit contributions | |
behavi | -1.842 |
subtitles | -1.828 |
Blu | -1.805 |
ophy | -1.768 |
AU | -1.760 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
anmar | +0.484 |
eters | +0.431 |
ativity | +0.415 |
andum | +0.401 |
warts | +0.401 |
Neg logit contributions | |
behavi | -0.276 |
subtitles | -0.273 |
Blu | -0.271 |
ophy | -0.264 |
AU | -0.259 |
Token |
|
Token ID | 198 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
anmar | +0.509 |
eters | +0.449 |
ativity | +0.432 |
warts | +0.417 |
andum | +0.416 |
Neg logit contributions | |
behavi | -0.321 |
subtitles | -0.321 |
Blu | -0.320 |
ophy | -0.310 |
AU | -0.306 |
Token |
|
Token ID | 198 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
anmar | +1.791 |
eters | +1.643 |
ativity | +1.526 |
felt | +1.493 |
warts | +1.487 |
Neg logit contributions | |
behavi | -1.736 |
subtitles | -1.547 |
ophy | -1.507 |
puzz | -1.493 |
Blu | -1.490 |
Token | CH |
Token ID | 3398 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
anmar | +1.772 |
eters | +1.588 |
ativity | +1.522 |
warts | +1.477 |
andum | +1.474 |
Neg logit contributions | |
behavi | -1.152 |
subtitles | -1.111 |
Blu | -1.088 |
ophy | -1.065 |
puzz | -1.035 |
Token | IC |
Token ID | 2149 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
subtitles | +0.778 |
Blu | +0.769 |
behavi | +0.757 |
AU | +0.748 |
ophy | +0.740 |
Neg logit contributions | |
anmar | -1.742 |
eters | -1.550 |
ativity | -1.502 |
warts | -1.462 |
andum | -1.451 |
Token | AG |
Token ID | 4760 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
behavi | +0.291 |
subtitles | +0.285 |
Blu | +0.283 |
ophy | +0.273 |
AU | +0.266 |
Neg logit contributions | |
anmar | -0.643 |
eters | -0.579 |
ativity | -0.560 |
andum | -0.543 |
warts | -0.542 |
Token | O |
Token ID | 46 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
AU | +2.814 |
subtitles | +2.784 |
Blu | +2.774 |
ophy | +2.631 |
OVA | +2.521 |
Neg logit contributions | |
anmar | -10.891 |
eters | -9.715 |
�� | -9.641 |
ativity | -9.529 |
andum | -9.280 |
Token | -- |
Token ID | 1377 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Blu | +1.249 |
subtitles | +1.238 |
behavi | +1.212 |
ophy | +1.198 |
AU | +1.192 |
Neg logit contributions | |
anmar | -2.453 |
eters | -2.172 |
ativity | -2.105 |
andum | -2.043 |
warts | -2.038 |
Token | It |
Token ID | 632 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
anmar | +1.230 |
eters | +1.087 |
ativity | +1.043 |
andum | +1.004 |
warts | +1.001 |
Neg logit contributions | |
behavi | -0.894 |
subtitles | -0.872 |
Blu | -0.858 |
ophy | -0.849 |
AU | -0.830 |
Token | 's |
Token ID | 338 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
anmar | +2.377 |
eters | +2.065 |
ativity | +1.966 |
warts | +1.876 |
andum | +1.872 |
Neg logit contributions | |
behavi | -2.236 |
subtitles | -2.191 |
Blu | -2.177 |
ophy | -2.144 |
AU | -2.113 |
Token | going |
Token ID | 1016 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
anmar | +0.157 |
eters | +0.136 |
ativity | +0.130 |
warts | +0.124 |
andum | +0.124 |
Neg logit contributions | |
behavi | -0.135 |
subtitles | -0.133 |
Blu | -0.132 |
ophy | -0.130 |
AU | -0.128 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Blu | +0.897 |
subtitles | +0.890 |
behavi | +0.889 |
ophy | +0.870 |
AU | +0.852 |
Neg logit contributions | |
anmar | -1.473 |
eters | -1.298 |
ativity | -1.258 |
andum | -1.216 |
�� | -1.205 |
Token |
|
Token ID | 198 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
behavi | +0.385 |
subtitles | +0.368 |
Blu | +0.361 |
ophy | +0.358 |
AU | +0.348 |
Neg logit contributions | |
anmar | -0.517 |
eters | -0.462 |
ativity | -0.439 |
warts | -0.425 |
andum | -0.424 |
Token | When |
Token ID | 2215 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
behavi | +0.697 |
subtitles | +0.694 |
Blu | +0.692 |
ophy | +0.677 |
AU | +0.667 |
Neg logit contributions | |
anmar | -1.081 |
eters | -0.953 |
ativity | -0.920 |
andum | -0.885 |
warts | -0.881 |
Token | those |
Token ID | 883 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
anmar | +0.312 |
eters | +0.272 |
ativity | +0.261 |
warts | +0.251 |
andum | +0.250 |
Neg logit contributions | |
behavi | -0.246 |
subtitles | -0.244 |
Blu | -0.242 |
ophy | -0.237 |
AU | -0.234 |
Token | for |
Token ID | 329 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
anmar | +0.138 |
eters | +0.120 |
ativity | +0.115 |
andum | +0.110 |
warts | +0.110 |
Neg logit contributions | |
behavi | -0.118 |
subtitles | -0.117 |
Blu | -0.117 |
ophy | -0.114 |
AU | -0.113 |
Token | whom |
Token ID | 4150 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
behavi | +0.110 |
subtitles | +0.110 |
Blu | +0.109 |
ophy | +0.107 |
AU | +0.106 |
Neg logit contributions | |
anmar | -0.112 |
eters | -0.096 |
ativity | -0.091 |
andum | -0.088 |
warts | -0.087 |
Token | we |
Token ID | 356 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Blu | +5.474 |
subtitles | +5.391 |
behavi | +5.315 |
ophy | +5.290 |
puzz | +5.127 |
Neg logit contributions | |
anmar | -7.686 |
eters | -6.838 |
�� | -6.551 |
ativity | -6.432 |
andum | -6.307 |
Token | want |
Token ID | 765 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
subtitles | +0.914 |
behavi | +0.911 |
Blu | +0.907 |
ophy | +0.890 |
AU | +0.875 |
Neg logit contributions | |
anmar | -1.219 |
eters | -1.065 |
ativity | -1.024 |
warts | -0.985 |
andum | -0.983 |
Token | a |
Token ID | 257 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
anmar | +0.663 |
eters | +0.579 |
ativity | +0.554 |
warts | +0.533 |
andum | +0.531 |
Neg logit contributions | |
behavi | -0.533 |
subtitles | -0.528 |
Blu | -0.523 |
ophy | -0.513 |
AU | -0.505 |
Token | kingdom |
Token ID | 13239 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Blu | +1.215 |
behavi | +1.208 |
subtitles | +1.205 |
ophy | +1.176 |
AU | +1.151 |
Neg logit contributions | |
anmar | -1.785 |
eters | -1.577 |
ativity | -1.511 |
andum | -1.461 |
warts | -1.459 |
Token | , |
Token ID | 11 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
behavi | +0.963 |
subtitles | +0.960 |
Blu | +0.955 |
ophy | +0.932 |
AU | +0.917 |
Neg logit contributions | |
anmar | -1.338 |
eters | -1.174 |
ativity | -1.127 |
andum | -1.084 |
warts | -1.083 |
Token | the |
Token ID | 262 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
anmar | +0.155 |
eters | +0.137 |
ativity | +0.131 |
warts | +0.126 |
andum | +0.126 |
Neg logit contributions | |
behavi | -0.108 |
subtitles | -0.107 |
Blu | -0.106 |
ophy | -0.104 |
AU | -0.102 |
Token | CF |
Token ID | 18551 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
behavi | +0.306 |
subtitles | +0.303 |
Blu | +0.301 |
ophy | +0.295 |
AU | +0.291 |
Neg logit contributions | |
anmar | -0.380 |
eters | -0.331 |
ativity | -0.317 |
andum | -0.304 |
warts | -0.304 |
Token | IB |
Token ID | 9865 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
behavi | +0.011 |
subtitles | +0.010 |
Blu | +0.010 |
ophy | +0.010 |
AU | +0.010 |
Neg logit contributions | |
anmar | -0.016 |
eters | -0.014 |
ativity | -0.014 |
warts | -0.013 |
andum | -0.013 |
Token | 's |
Token ID | 338 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
behavi | +0.165 |
subtitles | +0.164 |
Blu | +0.164 |
ophy | +0.160 |
AU | +0.157 |
Neg logit contributions | |
anmar | -0.216 |
eters | -0.189 |
ativity | -0.181 |
warts | -0.174 |
andum | -0.174 |
Token | Jonathan |
Token ID | 11232 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
Blu | +0.819 |
subtitles | +0.814 |
behavi | +0.808 |
ophy | +0.780 |
AU | +0.754 |
Neg logit contributions | |
anmar | -1.590 |
eters | -1.432 |
ativity | -1.376 |
warts | -1.333 |
andum | -1.328 |
Token | Al |
Token ID | 978 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Blu | +2.375 |
subtitles | +2.323 |
ophy | +2.214 |
AU | +2.193 |
behavi | +2.168 |
Neg logit contributions | |
anmar | -4.471 |
eters | -3.929 |
ativity | -3.811 |
�� | -3.729 |
warts | -3.691 |
Token | ward |
Token ID | 904 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
ophy | +2.801 |
Blu | +2.724 |
subtitles | +2.582 |
AU | +2.538 |
esian | +2.420 |
Neg logit contributions | |
anmar | -10.437 |
�� | -9.404 |
eters | -9.265 |
�醒 | -8.942 |
ativity | -8.913 |
Token | . |
Token ID | 13 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
behavi | +1.515 |
subtitles | +1.488 |
Blu | +1.484 |
ophy | +1.421 |
AU | +1.406 |
Neg logit contributions | |
anmar | -2.816 |
eters | -2.513 |
ativity | -2.445 |
warts | -2.349 |
�� | -2.326 |
Token |
|
Token ID | 198 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
anmar | +1.143 |
eters | +1.013 |
ativity | +0.974 |
andum | +0.939 |
warts | +0.939 |
Neg logit contributions | |
behavi | -0.719 |
subtitles | -0.713 |
Blu | -0.706 |
ophy | -0.689 |
AU | -0.677 |
Token |
|
Token ID | 198 |
Feature activation | -9.06e-03 |
Pos logit contributions | |
anmar | +0.796 |
eters | +0.716 |
ativity | +0.677 |
warts | +0.656 |
andum | +0.654 |
Neg logit contributions | |
behavi | -0.656 |
subtitles | -0.608 |
Blu | -0.592 |
ophy | -0.591 |
puzz | -0.582 |
Token | " |
Token ID | 1 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
behavi | +0.028 |
subtitles | +0.028 |
Blu | +0.027 |
ophy | +0.027 |
AU | +0.026 |
Neg logit contributions | |
anmar | -0.047 |
eters | -0.042 |
ativity | -0.040 |
warts | -0.039 |
andum | -0.039 |
Token | moving |
Token ID | 3867 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
behavi | +0.371 |
subtitles | +0.365 |
Blu | +0.363 |
ophy | +0.357 |
AU | +0.353 |
Neg logit contributions | |
anmar | -0.413 |
eters | -0.357 |
ativity | -0.341 |
andum | -0.326 |
warts | -0.326 |
Token | along |
Token ID | 1863 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
anmar | +0.466 |
eters | +0.407 |
ativity | +0.387 |
andum | +0.372 |
warts | +0.371 |
Neg logit contributions | |
behavi | -0.396 |
subtitles | -0.391 |
Blu | -0.387 |
ophy | -0.382 |
AU | -0.376 |
Token | . |
Token ID | 13 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
behavi | +0.967 |
subtitles | +0.962 |
Blu | +0.957 |
ophy | +0.934 |
AU | +0.921 |
Neg logit contributions | |
anmar | -1.146 |
eters | -0.995 |
ativity | -0.952 |
andum | -0.914 |
warts | -0.913 |
Token | Good |
Token ID | 4599 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
Blu | +1.000 |
subtitles | +0.999 |
behavi | +0.997 |
ophy | +0.969 |
AU | +0.958 |
Neg logit contributions | |
anmar | -1.365 |
eters | -1.199 |
ativity | -1.151 |
andum | -1.107 |
warts | -1.106 |
Token | ? |
Token ID | 30 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
subtitles | +2.468 |
Blu | +2.441 |
behavi | +2.399 |
ophy | +2.312 |
puzz | +2.231 |
Neg logit contributions | |
anmar | -4.184 |
eters | -3.679 |
andum | -3.480 |
�� | -3.476 |
ativity | -3.454 |
Token | Why |
Token ID | 4162 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Blu | +1.844 |
subtitles | +1.837 |
behavi | +1.810 |
ophy | +1.755 |
AU | +1.736 |
Neg logit contributions | |
anmar | -3.128 |
eters | -2.773 |
ativity | -2.624 |
�� | -2.561 |
andum | -2.553 |
Token | good |
Token ID | 922 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
Blu | +3.777 |
subtitles | +3.563 |
ophy | +3.301 |
AU | +3.105 |
puzz | +3.078 |
Neg logit contributions | |
anmar | -9.978 |
eters | -8.902 |
�� | -8.781 |
ativity | -8.561 |
�醒 | -8.462 |
Token | ? |
Token ID | 30 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
Blu | +2.387 |
subtitles | +2.373 |
ophy | +2.272 |
AU | +2.207 |
behavi | +2.196 |
Neg logit contributions | |
anmar | -5.042 |
eters | -4.400 |
ativity | -4.284 |
�� | -4.242 |
andum | -4.165 |
Token | We |
Token ID | 775 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
subtitles | +2.367 |
Blu | +2.362 |
behavi | +2.359 |
ophy | +2.288 |
AU | +2.262 |
Neg logit contributions | |
anmar | -3.235 |
eters | -2.817 |
ativity | -2.713 |
andum | -2.608 |
warts | -2.602 |
Token | need |
Token ID | 761 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
behavi | +1.049 |
subtitles | +1.009 |
Blu | +0.999 |
ophy | +0.971 |
AU | +0.950 |
Neg logit contributions | |
anmar | -2.425 |
eters | -2.196 |
ativity | -2.110 |
warts | -2.058 |
andum | -2.048 |
Token | something |
Token ID | 1223 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
behavi | +0.149 |
subtitles | +0.146 |
Blu | +0.144 |
ophy | +0.144 |
AU | +0.143 |
Neg logit contributions | |
anmar | -0.116 |
eters | -0.098 |
ativity | -0.093 |
warts | -0.089 |
andum | -0.087 |
Token | sequel |
Token ID | 16304 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
anmar | +0.147 |
eters | +0.131 |
ativity | +0.126 |
warts | +0.122 |
andum | +0.122 |
Neg logit contributions | |
behavi | -0.080 |
subtitles | -0.079 |
Blu | -0.078 |
ophy | -0.077 |
AU | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
anmar | +1.625 |
eters | +1.442 |
ativity | +1.386 |
warts | +1.337 |
andum | +1.327 |
Neg logit contributions | |
behavi | -1.021 |
subtitles | -0.987 |
ophy | -0.968 |
Blu | -0.967 |
AU | -0.944 |
Token |
|
Token ID | 198 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
Blu | +1.121 |
subtitles | +1.118 |
behavi | +1.105 |
ophy | +1.079 |
AU | +1.073 |
Neg logit contributions | |
anmar | -1.647 |
eters | -1.441 |
ativity | -1.387 |
andum | -1.336 |
warts | -1.333 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
anmar | +0.389 |
eters | +0.349 |
ativity | +0.332 |
warts | +0.321 |
andum | +0.320 |
Neg logit contributions | |
behavi | -0.311 |
subtitles | -0.291 |
Blu | -0.284 |
ophy | -0.284 |
puzz | -0.278 |
Token | VID |
Token ID | 11008 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
behavi | +0.042 |
subtitles | +0.041 |
Blu | +0.041 |
ophy | +0.040 |
AU | +0.039 |
Neg logit contributions | |
anmar | -0.071 |
eters | -0.063 |
ativity | -0.061 |
warts | -0.059 |
andum | -0.059 |
Token | E |
Token ID | 36 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
behavi | +0.917 |
subtitles | +0.910 |
Blu | +0.904 |
ophy | +0.888 |
AU | +0.874 |
Neg logit contributions | |
anmar | -0.951 |
eters | -0.820 |
ativity | -0.782 |
andum | -0.746 |
warts | -0.746 |
Token | OS |
Token ID | 2640 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
subtitles | +6.184 |
AU | +6.123 |
ophy | +6.026 |
Blu | +5.884 |
URA | +5.771 |
Neg logit contributions | |
anmar | -7.436 |
eters | -6.390 |
�� | -6.028 |
ativity | -5.982 |
warts | -5.975 |
Token | HAVE |
Token ID | 21515 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
subtitles | +1.897 |
Blu | +1.890 |
behavi | +1.851 |
ophy | +1.828 |
AU | +1.795 |
Neg logit contributions | |
anmar | -3.901 |
eters | -3.488 |
ativity | -3.376 |
warts | -3.270 |
andum | -3.255 |
Token | BE |
Token ID | 9348 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
subtitles | +2.514 |
Blu | +2.480 |
behavi | +2.405 |
AU | +2.395 |
ophy | +2.368 |
Neg logit contributions | |
anmar | -3.761 |
eters | -3.273 |
ativity | -3.193 |
warts | -3.079 |
andum | -3.073 |
Token | EN |
Token ID | 1677 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
subtitles | +1.488 |
Blu | +1.488 |
AU | +1.462 |
behavi | +1.454 |
ophy | +1.409 |
Neg logit contributions | |
anmar | -2.205 |
eters | -1.905 |
ativity | -1.857 |
andum | -1.788 |
warts | -1.784 |
Token | T |
Token ID | 309 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
behavi | +0.294 |
subtitles | +0.290 |
Blu | +0.287 |
ophy | +0.282 |
AU | +0.275 |
Neg logit contributions | |
anmar | -0.470 |
eters | -0.417 |
ativity | -0.400 |
andum | -0.386 |
warts | -0.386 |
Token | billion |
Token ID | 2997 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Blu | +1.761 |
subtitles | +1.730 |
behavi | +1.702 |
AU | +1.697 |
ophy | +1.682 |
Neg logit contributions | |
anmar | -3.749 |
eters | -3.347 |
ativity | -3.250 |
warts | -3.170 |
�� | -3.154 |
Token | this |
Token ID | 428 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
behavi | +0.598 |
subtitles | +0.594 |
Blu | +0.591 |
ophy | +0.576 |
AU | +0.568 |
Neg logit contributions | |
anmar | -0.866 |
eters | -0.763 |
ativity | -0.733 |
warts | -0.706 |
andum | -0.704 |
Token | year |
Token ID | 614 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
subtitles | +0.689 |
behavi | +0.689 |
Blu | +0.687 |
ophy | +0.663 |
AU | +0.654 |
Neg logit contributions | |
anmar | -1.079 |
eters | -0.955 |
ativity | -0.917 |
warts | -0.889 |
andum | -0.883 |
Token | and |
Token ID | 290 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
subtitles | +0.937 |
Blu | +0.937 |
behavi | +0.932 |
ophy | +0.901 |
AU | +0.897 |
Neg logit contributions | |
anmar | -1.488 |
eters | -1.319 |
ativity | -1.274 |
warts | -1.224 |
�� | -1.217 |
Token | $ |
Token ID | 720 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
subtitles | +2.198 |
Blu | +2.195 |
behavi | +2.166 |
ophy | +2.112 |
AU | +2.100 |
Neg logit contributions | |
anmar | -2.823 |
eters | -2.464 |
ativity | -2.364 |
�� | -2.278 |
warts | -2.273 |
Token | 395 |
Token ID | 31010 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
subtitles | +1.614 |
Blu | +1.605 |
behavi | +1.587 |
ophy | +1.551 |
AU | +1.536 |
Neg logit contributions | |
anmar | -3.271 |
eters | -2.912 |
ativity | -2.817 |
andum | -2.727 |
warts | -2.723 |
Token | . |
Token ID | 13 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
Blu | +3.417 |
subtitles | +3.304 |
ophy | +3.130 |
AU | +3.108 |
behavi | +3.053 |
Neg logit contributions | |
anmar | -9.594 |
eters | -8.555 |
ativity | -8.479 |
warts | -8.323 |
�� | -8.215 |
Token | 7 |
Token ID | 22 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
Blu | +1.565 |
subtitles | +1.544 |
ophy | +1.473 |
AU | +1.464 |
behavi | +1.451 |
Neg logit contributions | |
anmar | -4.205 |
eters | -3.730 |
ativity | -3.674 |
warts | -3.557 |
�� | -3.539 |
Token | billion |
Token ID | 2997 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
Blu | +1.301 |
subtitles | +1.276 |
behavi | +1.248 |
ophy | +1.237 |
AU | +1.234 |
Neg logit contributions | |
anmar | -3.012 |
eters | -2.696 |
ativity | -2.632 |
warts | -2.559 |
�� | -2.532 |
Token | over |
Token ID | 625 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
subtitles | +1.234 |
behavi | +1.230 |
Blu | +1.226 |
ophy | +1.195 |
AU | +1.175 |
Neg logit contributions | |
anmar | -1.693 |
eters | -1.484 |
ativity | -1.426 |
warts | -1.374 |
andum | -1.364 |
Token | all |
Token ID | 477 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
behavi | +0.247 |
subtitles | +0.244 |
Blu | +0.242 |
ophy | +0.237 |
AU | +0.234 |
Neg logit contributions | |
anmar | -0.341 |
eters | -0.299 |
ativity | -0.287 |
andum | -0.277 |
warts | -0.276 |
Token | campaign |
Token ID | 1923 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
Blu | +3.261 |
ophy | +3.157 |
behavi | +3.130 |
puzz | +3.111 |
subtitles | +3.101 |
Neg logit contributions | |
anmar | -6.445 |
eters | -5.933 |
ativity | -5.730 |
�� | -5.628 |
warts | -5.608 |
Token | manager |
Token ID | 4706 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
behavi | +2.032 |
Blu | +2.009 |
subtitles | +1.997 |
ophy | +1.960 |
puzz | +1.934 |
Neg logit contributions | |
anmar | -2.584 |
eters | -2.269 |
ativity | -2.187 |
warts | -2.136 |
�� | -2.111 |
Token | Rob |
Token ID | 3851 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
Blu | +3.882 |
subtitles | +3.821 |
puzz | +3.713 |
ophy | +3.691 |
behavi | +3.668 |
Neg logit contributions | |
anmar | -6.557 |
eters | -5.662 |
ativity | -5.442 |
warts | -5.429 |
andum | -5.294 |
Token | by |
Token ID | 1525 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Blu | +1.533 |
subtitles | +1.527 |
behavi | +1.509 |
ophy | +1.493 |
AU | +1.444 |
Neg logit contributions | |
anmar | -2.841 |
eters | -2.517 |
ativity | -2.427 |
warts | -2.347 |
andum | -2.345 |
Token | M |
Token ID | 337 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
subtitles | +1.092 |
Blu | +1.090 |
behavi | +1.079 |
ophy | +1.062 |
AU | +1.046 |
Neg logit contributions | |
anmar | -1.233 |
eters | -1.060 |
ativity | -1.020 |
warts | -0.977 |
andum | -0.971 |
Token | ook |
Token ID | 566 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ophy | +4.478 |
Blu | +4.256 |
AU | +4.219 |
subtitles | +4.133 |
puzz | +4.047 |
Neg logit contributions | |
anmar | -7.154 |
eters | -6.366 |
�� | -6.288 |
ativity | -6.246 |
�醒 | -6.139 |
Token | said |
Token ID | 531 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
subtitles | +5.108 |
Blu | +5.020 |
puzz | +4.956 |
AU | +4.802 |
ophy | +4.801 |
Neg logit contributions | |
anmar | -7.716 |
�� | -6.560 |
ativity | -6.537 |
eters | -6.516 |
andum | -6.320 |
Token | the |
Token ID | 262 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
subtitles | +2.256 |
Blu | +2.215 |
behavi | +2.194 |
ophy | +2.118 |
puzz | +2.088 |
Neg logit contributions | |
anmar | -3.809 |
eters | -3.353 |
ativity | -3.255 |
warts | -3.180 |
�� | -3.150 |
Token | campaign |
Token ID | 1923 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
subtitles | +1.918 |
Blu | +1.904 |
behavi | +1.892 |
ophy | +1.850 |
puzz | +1.812 |
Neg logit contributions | |
anmar | -2.766 |
eters | -2.433 |
ativity | -2.349 |
warts | -2.272 |
andum | -2.264 |
Token | has |
Token ID | 468 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
anmar | +2.139 |
eters | +1.867 |
ativity | +1.767 |
warts | +1.698 |
andum | +1.696 |
Neg logit contributions | |
behavi | -1.864 |
subtitles | -1.849 |
Blu | -1.835 |
ophy | -1.797 |
AU | -1.778 |
Token | been |
Token ID | 587 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
subtitles | +0.746 |
behavi | +0.742 |
Blu | +0.739 |
ophy | +0.722 |
AU | +0.708 |
Neg logit contributions | |
anmar | -0.795 |
eters | -0.680 |
ativity | -0.653 |
warts | -0.625 |
andum | -0.622 |
Token | ) |
Token ID | 8 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
anmar | +1.069 |
eters | +0.933 |
ativity | +0.897 |
andum | +0.861 |
warts | +0.860 |
Neg logit contributions | |
behavi | -0.803 |
subtitles | -0.802 |
Blu | -0.796 |
ophy | -0.778 |
AU | -0.766 |
Token |
|
Token ID | 198 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
Blu | +1.788 |
subtitles | +1.784 |
behavi | +1.740 |
ophy | +1.725 |
AU | +1.716 |
Neg logit contributions | |
anmar | -2.557 |
eters | -2.229 |
ativity | -2.147 |
andum | -2.059 |
warts | -2.056 |
Token |
|
Token ID | 198 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
subtitles | +0.139 |
Blu | +0.139 |
behavi | +0.137 |
AU | +0.134 |
ophy | +0.134 |
Neg logit contributions | |
anmar | -0.230 |
eters | -0.203 |
ativity | -0.195 |
andum | -0.188 |
warts | -0.188 |
Token | � |
Token ID | 447 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
anmar | +0.018 |
eters | +0.016 |
ativity | +0.015 |
warts | +0.015 |
andum | +0.015 |
Neg logit contributions | |
behavi | -0.011 |
subtitles | -0.011 |
Blu | -0.011 |
ophy | -0.011 |
AU | -0.011 |
Token | � |
Token ID | 250 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
subtitles | +1.330 |
Blu | +1.314 |
behavi | +1.307 |
ophy | +1.288 |
AU | +1.283 |
Neg logit contributions | |
anmar | -1.721 |
eters | -1.507 |
ativity | -1.442 |
warts | -1.367 |
andum | -1.354 |
Token | Why |
Token ID | 5195 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
anmar | +0.664 |
eters | +0.592 |
ativity | +0.569 |
warts | +0.550 |
andum | +0.550 |
Neg logit contributions | |
behavi | -0.398 |
subtitles | -0.392 |
Blu | -0.388 |
ophy | -0.378 |
AU | -0.369 |
Token | !? |
Token ID | 22857 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
subtitles | +5.310 |
Blu | +5.215 |
ophy | +5.033 |
behavi | +5.009 |
AU | +4.970 |
Neg logit contributions | |
anmar | -7.672 |
eters | -6.606 |
ativity | -6.365 |
�� | -6.258 |
andum | -6.250 |
Token | � |
Token ID | 447 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
Blu | +2.894 |
subtitles | +2.866 |
AU | +2.783 |
behavi | +2.754 |
ophy | +2.753 |
Neg logit contributions | |
anmar | -4.387 |
eters | -3.808 |
ativity | -3.692 |
andum | -3.560 |
warts | -3.535 |
Token | � |
Token ID | 251 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
subtitles | +1.696 |
Blu | +1.683 |
behavi | +1.670 |
ophy | +1.656 |
AU | +1.638 |
Neg logit contributions | |
anmar | -1.928 |
eters | -1.673 |
ativity | -1.589 |
andum | -1.510 |
warts | -1.499 |
Token | ( |
Token ID | 357 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
subtitles | +0.881 |
Blu | +0.880 |
behavi | +0.865 |
ophy | +0.849 |
AU | +0.842 |
Neg logit contributions | |
anmar | -1.434 |
eters | -1.258 |
ativity | -1.212 |
andum | -1.172 |
warts | -1.167 |
Token | Na |
Token ID | 26705 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
subtitles | +0.894 |
Blu | +0.891 |
behavi | +0.877 |
AU | +0.873 |
ophy | +0.869 |
Neg logit contributions | |
anmar | -1.573 |
eters | -1.389 |
ativity | -1.344 |
andum | -1.294 |
�� | -1.290 |
Token | thumbs |
Token ID | 32766 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
subtitles | +0.289 |
Blu | +0.288 |
behavi | +0.288 |
ophy | +0.280 |
puzz | +0.278 |
Neg logit contributions | |
anmar | -0.328 |
eters | -0.283 |
ativity | -0.272 |
andum | -0.261 |
warts | -0.259 |
Token | up |
Token ID | 510 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
subtitles | +0.591 |
behavi | +0.590 |
Blu | +0.585 |
ophy | +0.573 |
AU | +0.560 |
Neg logit contributions | |
anmar | -1.023 |
eters | -0.898 |
ativity | -0.874 |
andum | -0.848 |
warts | -0.839 |
Token | . |
Token ID | 13 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
behavi | +0.628 |
subtitles | +0.628 |
Blu | +0.621 |
ophy | +0.601 |
AU | +0.591 |
Neg logit contributions | |
anmar | -1.137 |
eters | -1.012 |
ativity | -0.979 |
andum | -0.945 |
warts | -0.941 |
Token | � |
Token ID | 564 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
behavi | +0.301 |
subtitles | +0.300 |
Blu | +0.298 |
ophy | +0.290 |
AU | +0.286 |
Neg logit contributions | |
anmar | -0.452 |
eters | -0.399 |
ativity | -0.383 |
andum | -0.369 |
warts | -0.369 |
Token | � |
Token ID | 250 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
anmar | +0.843 |
eters | +0.692 |
ativity | +0.650 |
warts | +0.626 |
andum | +0.621 |
Neg logit contributions | |
behavi | -1.284 |
subtitles | -1.252 |
Blu | -1.240 |
ophy | -1.223 |
puzz | -1.209 |
Token | Eh |
Token ID | 43894 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
behavi | +0.896 |
subtitles | +0.888 |
Blu | +0.880 |
ophy | +0.857 |
AU | +0.841 |
Neg logit contributions | |
anmar | -1.595 |
eters | -1.419 |
ativity | -1.367 |
warts | -1.321 |
andum | -1.321 |
Token | ? |
Token ID | 30 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
subtitles | +4.140 |
Blu | +4.120 |
behavi | +3.976 |
ophy | +3.949 |
AU | +3.925 |
Neg logit contributions | |
anmar | -8.492 |
eters | -7.664 |
�� | -7.386 |
ativity | -7.355 |
andum | -7.160 |
Token | Is |
Token ID | 1148 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
subtitles | +1.750 |
Blu | +1.749 |
behavi | +1.737 |
ophy | +1.689 |
AU | +1.675 |
Neg logit contributions | |
anmar | -2.556 |
eters | -2.253 |
ativity | -2.168 |
andum | -2.090 |
warts | -2.079 |
Token | that |
Token ID | 326 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
subtitles | +3.118 |
Blu | +3.117 |
behavi | +3.073 |
ophy | +2.986 |
AU | +2.934 |
Neg logit contributions | |
anmar | -4.447 |
eters | -4.001 |
ativity | -3.841 |
andum | -3.692 |
�� | -3.689 |
Token | a |
Token ID | 257 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
subtitles | +2.144 |
Blu | +2.137 |
behavi | +2.113 |
ophy | +2.056 |
AU | +2.044 |
Neg logit contributions | |
anmar | -2.619 |
eters | -2.299 |
ativity | -2.195 |
andum | -2.106 |
warts | -2.085 |
Token | habit |
Token ID | 7947 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Blu | +2.087 |
subtitles | +2.078 |
behavi | +2.049 |
ophy | +2.003 |
puzz | +1.982 |
Neg logit contributions | |
anmar | -2.631 |
eters | -2.331 |
ativity | -2.231 |
andum | -2.129 |
warts | -2.118 |
Token | 2 |
Token ID | 17 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
anmar | +2.643 |
eters | +2.416 |
ativity | +2.236 |
andum | +2.198 |
felt | +2.176 |
Neg logit contributions | |
behavi | -2.309 |
subtitles | -2.030 |
puzz | -1.990 |
Blu | -1.974 |
ophy | -1.962 |
Token | . |
Token ID | 13 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
anmar | +3.031 |
eters | +2.842 |
ativity | +2.602 |
felt | +2.593 |
initialized | +2.583 |
Neg logit contributions | |
behavi | -2.804 |
puzz | -2.379 |
subtitles | -2.374 |
warr | -2.328 |
ophy | -2.324 |
Token | M |
Token ID | 44 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
anmar | +2.623 |
eters | +2.384 |
ativity | +2.197 |
initialized | +2.156 |
andum | +2.153 |
Neg logit contributions | |
behavi | -2.711 |
subtitles | -2.464 |
Blu | -2.429 |
puzz | -2.412 |
ophy | -2.391 |
Token | OR |
Token ID | 1581 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
anmar | +5.604 |
eters | +5.248 |
ativity | +4.986 |
andum | +4.838 |
initialized | +4.806 |
Neg logit contributions | |
behavi | -3.289 |
subtitles | -2.690 |
puzz | -2.631 |
Blu | -2.564 |
ophy | -2.508 |
Token | PH |
Token ID | 11909 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
anmar | +3.205 |
eters | +2.922 |
ativity | +2.680 |
warts | +2.648 |
felt | +2.644 |
Neg logit contributions | |
behavi | -3.376 |
subtitles | -3.055 |
puzz | -2.999 |
Blu | -2.957 |
ophy | -2.869 |
Token | _ |
Token ID | 62 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
anmar | +2.461 |
eters | +2.259 |
ativity | +2.113 |
felt | +2.075 |
initialized | +2.060 |
Neg logit contributions | |
behavi | -1.907 |
subtitles | -1.654 |
puzz | -1.644 |
ophy | -1.618 |
Blu | -1.618 |
Token | RECT |
Token ID | 23988 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
anmar | +4.275 |
eters | +3.899 |
initialized | +3.678 |
felt | +3.478 |
warts | +3.476 |
Neg logit contributions | |
behavi | -5.622 |
subtitles | -4.902 |
puzz | -4.876 |
warr | -4.857 |
Blu | -4.813 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
anmar | +2.800 |
eters | +2.572 |
ativity | +2.369 |
felt | +2.337 |
initialized | +2.306 |
Neg logit contributions | |
behavi | -3.153 |
subtitles | -2.742 |
puzz | -2.717 |
ophy | -2.701 |
warr | -2.656 |
Token | ( |
Token ID | 357 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
anmar | +4.584 |
eters | +4.197 |
ativity | +3.917 |
felt | +3.833 |
andum | +3.803 |
Neg logit contributions | |
behavi | -4.787 |
puzz | -4.086 |
subtitles | -4.046 |
ophy | -4.030 |
warr | -3.994 |
Token | 21 |
Token ID | 2481 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
anmar | +1.009 |
eters | +0.892 |
ativity | +0.858 |
andum | +0.829 |
warts | +0.827 |
Neg logit contributions | |
subtitles | -0.619 |
Blu | -0.618 |
behavi | -0.612 |
ophy | -0.605 |
AU | -0.600 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
anmar | +4.002 |
eters | +3.761 |
felt | +3.400 |
ativity | +3.382 |
initialized | +3.350 |
Neg logit contributions | |
behavi | -5.019 |
warr | -4.249 |
subtitles | -4.228 |
puzz | -4.222 |
ophy | -4.145 |
Token | scripted |
Token ID | 37341 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
anmar | +1.376 |
eters | +1.212 |
ativity | +1.161 |
andum | +1.117 |
warts | +1.115 |
Neg logit contributions | |
behavi | -0.984 |
subtitles | -0.972 |
Blu | -0.962 |
ophy | -0.942 |
AU | -0.932 |
Token | sequence |
Token ID | 8379 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
behavi | +0.143 |
subtitles | +0.141 |
Blu | +0.140 |
ophy | +0.137 |
AU | +0.135 |
Neg logit contributions | |
anmar | -0.226 |
eters | -0.200 |
ativity | -0.192 |
andum | -0.185 |
warts | -0.185 |
Token | of |
Token ID | 286 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
behavi | +0.551 |
subtitles | +0.549 |
Blu | +0.545 |
ophy | +0.531 |
AU | +0.521 |
Neg logit contributions | |
anmar | -0.854 |
eters | -0.754 |
ativity | -0.725 |
warts | -0.699 |
andum | -0.698 |
Token | events |
Token ID | 2995 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
subtitles | +2.386 |
Blu | +2.352 |
behavi | +2.325 |
puzz | +2.249 |
ophy | +2.241 |
Neg logit contributions | |
anmar | -4.391 |
eters | -3.908 |
ativity | -3.768 |
�� | -3.664 |
andum | -3.652 |
Token | , |
Token ID | 11 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
behavi | +0.235 |
subtitles | +0.233 |
Blu | +0.232 |
ophy | +0.226 |
AU | +0.222 |
Neg logit contributions | |
anmar | -0.354 |
eters | -0.312 |
ativity | -0.300 |
warts | -0.289 |
andum | -0.289 |
Token | but |
Token ID | 475 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
anmar | +0.647 |
eters | +0.560 |
ativity | +0.531 |
warts | +0.509 |
andum | +0.508 |
Neg logit contributions | |
behavi | -0.631 |
subtitles | -0.618 |
Blu | -0.615 |
ophy | -0.605 |
AU | -0.602 |
Token | causing |
Token ID | 6666 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
anmar | +4.581 |
eters | +3.998 |
ativity | +3.768 |
andum | +3.706 |
warts | +3.614 |
Neg logit contributions | |
behavi | -4.490 |
subtitles | -4.325 |
Blu | -4.320 |
ophy | -4.303 |
AU | -4.292 |
Token | the |
Token ID | 262 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
anmar | +0.908 |
eters | +0.796 |
ativity | +0.762 |
andum | +0.732 |
warts | +0.729 |
Neg logit contributions | |
behavi | -0.715 |
subtitles | -0.705 |
Blu | -0.702 |
ophy | -0.690 |
AU | -0.681 |
Token | events |
Token ID | 2995 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
anmar | +0.810 |
eters | +0.715 |
ativity | +0.683 |
andum | +0.657 |
warts | +0.655 |
Neg logit contributions | |
behavi | -0.571 |
subtitles | -0.557 |
Blu | -0.557 |
ophy | -0.545 |
AU | -0.539 |
Token | ( |
Token ID | 357 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
anmar | +0.438 |
eters | +0.379 |
ativity | +0.362 |
andum | +0.347 |
warts | +0.346 |
Neg logit contributions | |
behavi | -0.392 |
subtitles | -0.389 |
Blu | -0.386 |
ophy | -0.379 |
AU | -0.374 |
Token | in |
Token ID | 259 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
subtitles | +1.156 |
behavi | +1.148 |
Blu | +1.146 |
ophy | +1.129 |
AU | +1.119 |
Neg logit contributions | |
anmar | -1.541 |
eters | -1.344 |
ativity | -1.296 |
andum | -1.247 |
�� | -1.245 |
Token | - |
Token ID | 12 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
anmar | +0.731 |
eters | +0.641 |
ativity | +0.616 |
andum | +0.591 |
warts | +0.590 |
Neg logit contributions | |
behavi | -0.545 |
subtitles | -0.540 |
Blu | -0.535 |
ophy | -0.523 |
AU | -0.517 |
Token | minded |
Token ID | 14543 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
anmar | +0.168 |
eters | +0.148 |
ativity | +0.142 |
andum | +0.137 |
warts | +0.136 |
Neg logit contributions | |
behavi | -0.121 |
subtitles | -0.121 |
Blu | -0.120 |
ophy | -0.117 |
AU | -0.116 |
Token | ( |
Token ID | 357 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
anmar | +0.459 |
eters | +0.400 |
ativity | +0.383 |
andum | +0.367 |
warts | +0.367 |
Neg logit contributions | |
behavi | -0.376 |
subtitles | -0.374 |
Blu | -0.371 |
ophy | -0.363 |
AU | -0.359 |
Token | not |
Token ID | 1662 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
anmar | +2.141 |
eters | +1.859 |
ativity | +1.774 |
warts | +1.708 |
andum | +1.698 |
Neg logit contributions | |
behavi | -1.890 |
subtitles | -1.866 |
Blu | -1.853 |
ophy | -1.809 |
AU | -1.779 |
Token | to |
Token ID | 284 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
anmar | +3.754 |
eters | +3.290 |
ativity | +3.165 |
andum | +3.013 |
warts | +2.951 |
Neg logit contributions | |
behavi | -3.450 |
subtitles | -3.355 |
Blu | -3.324 |
AU | -3.273 |
ophy | -3.273 |
Token | mention |
Token ID | 3068 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
anmar | +1.381 |
eters | +1.187 |
ativity | +1.130 |
warts | +1.077 |
andum | +1.077 |
Neg logit contributions | |
behavi | -1.385 |
subtitles | -1.374 |
Blu | -1.365 |
ophy | -1.342 |
AU | -1.324 |
Token | least |
Token ID | 1551 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
anmar | +5.177 |
eters | +4.594 |
ativity | +4.361 |
andum | +4.204 |
warts | +4.120 |
Neg logit contributions | |
behavi | -4.629 |
subtitles | -4.522 |
Blu | -4.460 |
ophy | -4.438 |
AU | -4.418 |
Token | imaginative |
Token ID | 41138 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
anmar | +2.883 |
eters | +2.545 |
ativity | +2.418 |
andum | +2.303 |
warts | +2.288 |
Neg logit contributions | |
behavi | -2.643 |
subtitles | -2.593 |
Blu | -2.566 |
ophy | -2.519 |
AU | -2.507 |
Token | ) |
Token ID | 8 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
anmar | +2.637 |
eters | +2.294 |
ativity | +2.194 |
andum | +2.100 |
warts | +2.099 |
Neg logit contributions | |
behavi | -2.249 |
subtitles | -2.234 |
Blu | -2.219 |
ophy | -2.174 |
AU | -2.143 |
Token | way |
Token ID | 835 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
anmar | +0.554 |
eters | +0.484 |
ativity | +0.464 |
andum | +0.445 |
warts | +0.445 |
Neg logit contributions | |
behavi | -0.441 |
subtitles | -0.438 |
Blu | -0.435 |
ophy | -0.425 |
AU | -0.419 |
Token | of |
Token ID | 286 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
behavi | +0.081 |
subtitles | +0.080 |
Blu | +0.080 |
ophy | +0.078 |
AU | +0.077 |
Neg logit contributions | |
anmar | -0.107 |
eters | -0.094 |
ativity | -0.089 |
warts | -0.087 |
andum | -0.086 |
Token | called |
Token ID | 1444 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
anmar | +0.729 |
eters | +0.634 |
ativity | +0.605 |
warts | +0.579 |
andum | +0.578 |
Neg logit contributions | |
behavi | -0.647 |
subtitles | -0.636 |
Blu | -0.632 |
ophy | -0.624 |
AU | -0.615 |
Token | the |
Token ID | 262 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
anmar | +0.533 |
eters | +0.467 |
ativity | +0.448 |
warts | +0.431 |
andum | +0.430 |
Neg logit contributions | |
behavi | -0.399 |
subtitles | -0.397 |
Blu | -0.394 |
ophy | -0.384 |
AU | -0.378 |
Token | � |
Token ID | 564 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
anmar | +1.112 |
eters | +0.970 |
ativity | +0.928 |
warts | +0.891 |
andum | +0.890 |
Neg logit contributions | |
behavi | -0.899 |
subtitles | -0.893 |
Blu | -0.887 |
ophy | -0.868 |
AU | -0.855 |
Token | � |
Token ID | 250 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
anmar | +1.162 |
eters | +0.991 |
ativity | +0.941 |
warts | +0.900 |
andum | +0.899 |
Neg logit contributions | |
behavi | -1.256 |
subtitles | -1.247 |
Blu | -1.240 |
ophy | -1.213 |
AU | -1.200 |
Token | w |
Token ID | 86 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
anmar | +0.961 |
eters | +0.842 |
ativity | +0.807 |
warts | +0.775 |
andum | +0.775 |
Neg logit contributions | |
behavi | -0.729 |
subtitles | -0.724 |
Blu | -0.719 |
ophy | -0.703 |
AU | -0.693 |
Token | hip |
Token ID | 1056 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
anmar | +1.400 |
eters | +1.217 |
ativity | +1.163 |
warts | +1.115 |
andum | +1.115 |
Neg logit contributions | |
behavi | -1.191 |
subtitles | -1.184 |
Blu | -1.176 |
ophy | -1.152 |
AU | -1.135 |
Token | � |
Token ID | 447 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
anmar | +4.983 |
eters | +4.386 |
ativity | +4.192 |
warts | +4.082 |
andum | +4.066 |
Neg logit contributions | |
behavi | -3.825 |
subtitles | -3.755 |
Blu | -3.729 |
ophy | -3.688 |
AU | -3.596 |
Token | � |
Token ID | 251 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
subtitles | +0.331 |
behavi | +0.331 |
Blu | +0.330 |
ophy | +0.325 |
AU | +0.319 |
Neg logit contributions | |
anmar | -0.365 |
eters | -0.314 |
ativity | -0.301 |
warts | -0.284 |
andum | -0.284 |
Token | stitch |
Token ID | 24695 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
anmar | +2.398 |
eters | +2.117 |
ativity | +2.026 |
warts | +1.961 |
andum | +1.954 |
Neg logit contributions | |
behavi | -1.759 |
subtitles | -1.731 |
Blu | -1.721 |
ophy | -1.687 |
AU | -1.652 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
anmar | +2.806 |
eters | +2.479 |
ativity | +2.390 |
warts | +2.313 |
andum | +2.301 |
Neg logit contributions | |
behavi | -1.877 |
subtitles | -1.847 |
Blu | -1.833 |
ophy | -1.801 |
AU | -1.761 |
Token | Next |
Token ID | 7406 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
anmar | +1.533 |
eters | +1.359 |
ativity | +1.288 |
warts | +1.244 |
andum | +1.239 |
Neg logit contributions | |
behavi | -1.252 |
subtitles | -1.207 |
ophy | -1.187 |
Blu | -1.184 |
AU | -1.158 |
Token | _ |
Token ID | 62 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
behavi | +0.173 |
subtitles | +0.161 |
Blu | +0.158 |
ophy | +0.155 |
puzz | +0.153 |
Neg logit contributions | |
anmar | -0.287 |
eters | -0.259 |
ativity | -0.247 |
andum | -0.239 |
warts | -0.239 |
Token | OR |
Token ID | 1581 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
anmar | +3.669 |
eters | +3.436 |
ativity | +3.258 |
warts | +3.228 |
felt | +3.207 |
Neg logit contributions | |
behavi | -2.077 |
subtitles | -1.742 |
puzz | -1.688 |
Blu | -1.654 |
ophy | -1.617 |
Token | ) |
Token ID | 8 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
subtitles | +1.734 |
behavi | +1.733 |
Blu | +1.726 |
ophy | +1.687 |
AU | +1.665 |
Neg logit contributions | |
anmar | -2.064 |
eters | -1.790 |
ativity | -1.713 |
warts | -1.642 |
andum | -1.641 |
Token | May |
Token ID | 1737 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
behavi | +1.245 |
subtitles | +1.239 |
Blu | +1.231 |
ophy | +1.201 |
AU | +1.182 |
Neg logit contributions | |
anmar | -1.776 |
eters | -1.561 |
ativity | -1.499 |
warts | -1.443 |
andum | -1.443 |
Token | 29 |
Token ID | 2808 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
anmar | +0.590 |
eters | +0.514 |
ativity | +0.495 |
warts | +0.482 |
andum | +0.480 |
Neg logit contributions | |
Blu | -0.414 |
subtitles | -0.414 |
behavi | -0.411 |
ophy | -0.398 |
AU | -0.395 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
anmar | +0.409 |
eters | +0.367 |
ativity | +0.347 |
andum | +0.334 |
warts | +0.334 |
Neg logit contributions | |
behavi | -0.337 |
subtitles | -0.315 |
Blu | -0.308 |
ophy | -0.307 |
puzz | -0.301 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +5.71e-03 |
Pos logit contributions | |
anmar | +3.051 |
eters | +2.819 |
ativity | +2.455 |
felt | +2.401 |
warts | +2.299 |
Neg logit contributions | |
behavi | -6.170 |
subtitles | -5.451 |
puzz | -5.429 |
ophy | -5.386 |
warr | -5.362 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
anmar | +0.029 |
eters | +0.026 |
ativity | +0.025 |
warts | +0.024 |
andum | +0.024 |
Neg logit contributions | |
behavi | -0.018 |
subtitles | -0.018 |
Blu | -0.018 |
ophy | -0.018 |
AU | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
anmar | +0.655 |
eters | +0.592 |
ativity | +0.559 |
warts | +0.542 |
andum | +0.539 |
Neg logit contributions | |
behavi | -0.552 |
subtitles | -0.508 |
ophy | -0.495 |
Blu | -0.495 |
puzz | -0.487 |
Token | Truth |
Token ID | 38782 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
anmar | +1.011 |
eters | +0.911 |
ativity | +0.869 |
warts | +0.850 |
andum | +0.844 |
Neg logit contributions | |
behavi | -0.593 |
subtitles | -0.575 |
Blu | -0.566 |
ophy | -0.550 |
puzz | -0.535 |
Token | . |
Token ID | 13 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
subtitles | +1.379 |
Blu | +1.368 |
behavi | +1.357 |
ophy | +1.322 |
AU | +1.318 |
Neg logit contributions | |
anmar | -1.469 |
eters | -1.239 |
ativity | -1.187 |
andum | -1.133 |
warts | -1.128 |
Token | worth |
Token ID | 2861 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
subtitles | +2.042 |
Blu | +2.040 |
behavi | +1.999 |
ophy | +1.966 |
AU | +1.940 |
Neg logit contributions | |
anmar | -2.862 |
eters | -2.516 |
ativity | -2.426 |
warts | -2.346 |
�� | -2.325 |
Token | of |
Token ID | 286 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
subtitles | +1.078 |
Blu | +1.077 |
behavi | +1.070 |
ophy | +1.034 |
AU | +1.024 |
Neg logit contributions | |
anmar | -1.892 |
eters | -1.680 |
ativity | -1.614 |
warts | -1.566 |
andum | -1.549 |
Token | upgrades |
Token ID | 16608 |
Feature activation | -7.46e-04 |
Pos logit contributions | |
behavi | +0.730 |
subtitles | +0.722 |
Blu | +0.716 |
ophy | +0.702 |
AU | +0.691 |
Neg logit contributions | |
anmar | -0.945 |
eters | -0.827 |
ativity | -0.792 |
andum | -0.761 |
warts | -0.761 |
Token | to |
Token ID | 284 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
behavi | +0.003 |
subtitles | +0.003 |
Blu | +0.003 |
ophy | +0.002 |
AU | +0.002 |
Neg logit contributions | |
anmar | -0.004 |
eters | -0.003 |
ativity | -0.003 |
andum | -0.003 |
warts | -0.003 |
Token | Bahrain |
Token ID | 29066 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
anmar | +0.680 |
eters | +0.593 |
ativity | +0.567 |
andum | +0.549 |
warts | +0.547 |
Neg logit contributions | |
behavi | -0.521 |
subtitles | -0.509 |
ophy | -0.503 |
Blu | -0.502 |
AU | -0.489 |
Token | 's |
Token ID | 338 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
behavi | +0.200 |
subtitles | +0.199 |
Blu | +0.198 |
ophy | +0.193 |
AU | +0.191 |
Neg logit contributions | |
anmar | -0.219 |
eters | -0.189 |
ativity | -0.181 |
warts | -0.173 |
andum | -0.173 |
Token | existing |
Token ID | 4683 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
anmar | +1.688 |
eters | +1.459 |
ativity | +1.401 |
andum | +1.352 |
warts | +1.349 |
Neg logit contributions | |
behavi | -1.376 |
subtitles | -1.339 |
ophy | -1.323 |
Blu | -1.319 |
AU | -1.300 |
Token | fleet |
Token ID | 11026 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
Blu | +1.908 |
subtitles | +1.905 |
behavi | +1.873 |
ophy | +1.823 |
AU | +1.804 |
Neg logit contributions | |
anmar | -2.637 |
eters | -2.325 |
ativity | -2.232 |
warts | -2.139 |
�� | -2.139 |
Token | of |
Token ID | 286 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
anmar | +0.136 |
eters | +0.120 |
ativity | +0.116 |
warts | +0.112 |
andum | +0.112 |
Neg logit contributions | |
behavi | -0.081 |
subtitles | -0.081 |
Blu | -0.080 |
ophy | -0.078 |
AU | -0.077 |
Token | F |
Token ID | 376 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
subtitles | +1.944 |
Blu | +1.944 |
behavi | +1.918 |
ophy | +1.875 |
AU | +1.852 |
Neg logit contributions | |
anmar | -2.531 |
eters | -2.216 |
ativity | -2.122 |
andum | -2.037 |
warts | -2.032 |
Token | - |
Token ID | 12 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
anmar | +0.243 |
eters | +0.214 |
ativity | +0.206 |
warts | +0.199 |
andum | +0.199 |
Neg logit contributions | |
behavi | -0.159 |
subtitles | -0.157 |
Blu | -0.156 |
ophy | -0.152 |
AU | -0.150 |
Token | Mac |
Token ID | 4100 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
anmar | +2.580 |
eters | +2.244 |
ativity | +2.126 |
warts | +2.043 |
andum | +2.023 |
Neg logit contributions | |
behavi | -2.356 |
subtitles | -2.304 |
Blu | -2.300 |
ophy | -2.277 |
AU | -2.239 |
Token | ri |
Token ID | 380 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
anmar | +0.175 |
eters | +0.150 |
ativity | +0.141 |
warts | +0.136 |
andum | +0.135 |
Neg logit contributions | |
behavi | -0.205 |
subtitles | -0.201 |
Blu | -0.198 |
ophy | -0.193 |
AU | -0.192 |
Token | � |
Token ID | 447 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
anmar | +0.648 |
eters | +0.561 |
ativity | +0.537 |
andum | +0.515 |
warts | +0.514 |
Neg logit contributions | |
behavi | -0.564 |
subtitles | -0.561 |
Blu | -0.557 |
ophy | -0.546 |
AU | -0.538 |
Token | � |
Token ID | 247 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
anmar | +0.295 |
eters | +0.258 |
ativity | +0.247 |
andum | +0.239 |
warts | +0.239 |
Neg logit contributions | |
behavi | -0.225 |
subtitles | -0.219 |
Blu | -0.217 |
ophy | -0.212 |
AU | -0.208 |
Token | s |
Token ID | 82 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
subtitles | +1.087 |
behavi | +1.068 |
Blu | +1.057 |
ophy | +1.052 |
AU | +1.015 |
Neg logit contributions | |
anmar | -1.592 |
eters | -1.384 |
ativity | -1.345 |
�� | -1.314 |
andum | -1.301 |
Token | Panama |
Token ID | 23519 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
behavi | +0.867 |
subtitles | +0.864 |
Blu | +0.858 |
ophy | +0.840 |
AU | +0.821 |
Neg logit contributions | |
anmar | -1.108 |
eters | -0.971 |
ativity | -0.934 |
andum | -0.897 |
warts | -0.894 |
Token | Papers |
Token ID | 27420 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
anmar | +0.583 |
eters | +0.509 |
ativity | +0.488 |
warts | +0.469 |
andum | +0.468 |
Neg logit contributions | |
behavi | -0.456 |
subtitles | -0.454 |
Blu | -0.451 |
ophy | -0.442 |
AU | -0.434 |
Token | revelations |
Token ID | 19111 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
anmar | +0.313 |
eters | +0.273 |
ativity | +0.262 |
warts | +0.251 |
andum | +0.251 |
Neg logit contributions | |
behavi | -0.252 |
subtitles | -0.250 |
Blu | -0.248 |
ophy | -0.243 |
AU | -0.239 |
Token | cast |
Token ID | 3350 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
anmar | +3.985 |
eters | +3.533 |
ativity | +3.333 |
warts | +3.278 |
andum | +3.235 |
Neg logit contributions | |
behavi | -3.219 |
subtitles | -3.108 |
Blu | -3.083 |
ophy | -3.040 |
AU | -3.002 |
Token | him |
Token ID | 683 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
behavi | +0.386 |
subtitles | +0.386 |
Blu | +0.384 |
ophy | +0.372 |
AU | +0.365 |
Neg logit contributions | |
anmar | -0.593 |
eters | -0.522 |
ativity | -0.503 |
andum | -0.486 |
warts | -0.484 |
Token | as |
Token ID | 355 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
behavi | +1.385 |
subtitles | +1.382 |
Blu | +1.375 |
ophy | +1.349 |
puzz | +1.320 |
Neg logit contributions | |
anmar | -1.729 |
eters | -1.499 |
ativity | -1.450 |
�� | -1.397 |
andum | -1.396 |
Token | , |
Token ID | 11 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
anmar | +0.348 |
eters | +0.306 |
ativity | +0.294 |
warts | +0.283 |
andum | +0.283 |
Neg logit contributions | |
behavi | -0.244 |
subtitles | -0.242 |
Blu | -0.240 |
ophy | -0.235 |
AU | -0.231 |
Token | I |
Token ID | 314 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
anmar | +1.383 |
eters | +1.211 |
ativity | +1.152 |
warts | +1.118 |
andum | +1.118 |
Neg logit contributions | |
behavi | -1.060 |
subtitles | -1.038 |
Blu | -1.024 |
ophy | -1.016 |
AU | -1.003 |
Token | got |
Token ID | 1392 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
behavi | +0.173 |
subtitles | +0.171 |
Blu | +0.170 |
ophy | +0.166 |
AU | +0.163 |
Neg logit contributions | |
anmar | -0.225 |
eters | -0.197 |
ativity | -0.188 |
andum | -0.181 |
warts | -0.181 |
Token | to |
Token ID | 284 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
anmar | +2.353 |
eters | +2.065 |
ativity | +1.961 |
andum | +1.888 |
warts | +1.869 |
Neg logit contributions | |
behavi | -1.969 |
subtitles | -1.900 |
Blu | -1.899 |
ophy | -1.895 |
AU | -1.871 |
Token | keep |
Token ID | 1394 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
anmar | +2.729 |
eters | +2.374 |
ativity | +2.257 |
warts | +2.183 |
andum | +2.182 |
Neg logit contributions | |
behavi | -2.177 |
subtitles | -2.115 |
ophy | -2.083 |
Blu | -2.081 |
AU | -2.054 |
Token | all |
Token ID | 477 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
anmar | +0.454 |
eters | +0.397 |
ativity | +0.379 |
warts | +0.363 |
andum | +0.363 |
Neg logit contributions | |
behavi | -0.367 |
subtitles | -0.363 |
Blu | -0.361 |
ophy | -0.354 |
AU | -0.350 |
Token | these |
Token ID | 777 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
anmar | +2.901 |
eters | +2.554 |
ativity | +2.452 |
warts | +2.342 |
felt | +2.319 |
Neg logit contributions | |
behavi | -2.343 |
subtitles | -2.301 |
Blu | -2.279 |
ophy | -2.259 |
AU | -2.253 |
Token | apartments |
Token ID | 19592 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
anmar | +4.330 |
eters | +3.834 |
ativity | +3.660 |
warts | +3.488 |
andum | +3.453 |
Neg logit contributions | |
behavi | -3.242 |
ophy | -3.159 |
AU | -3.135 |
Blu | -3.118 |
subtitles | -3.114 |
Token | under |
Token ID | 739 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
anmar | +1.370 |
eters | +1.207 |
ativity | +1.155 |
warts | +1.105 |
andum | +1.102 |
Neg logit contributions | |
behavi | -0.999 |
subtitles | -0.976 |
Blu | -0.969 |
ophy | -0.956 |
AU | -0.946 |
Token | surveillance |
Token ID | 8452 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
subtitles | +1.053 |
behavi | +1.044 |
Blu | +1.043 |
ophy | +1.007 |
AU | +0.992 |
Neg logit contributions | |
anmar | -1.469 |
eters | -1.294 |
ativity | -1.235 |
warts | -1.190 |
andum | -1.190 |
Token | . |
Token ID | 13 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
behavi | +0.042 |
subtitles | +0.041 |
Blu | +0.041 |
ophy | +0.040 |
AU | +0.039 |
Neg logit contributions | |
anmar | -0.061 |
eters | -0.054 |
ativity | -0.052 |
warts | -0.050 |
andum | -0.050 |
Token | your |
Token ID | 534 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
anmar | +1.086 |
eters | +0.946 |
ativity | +0.906 |
warts | +0.869 |
andum | +0.869 |
Neg logit contributions | |
behavi | -0.882 |
subtitles | -0.877 |
Blu | -0.872 |
ophy | -0.852 |
AU | -0.840 |
Token | Kindle |
Token ID | 27114 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
anmar | +2.411 |
eters | +2.115 |
ativity | +2.023 |
warts | +1.953 |
andum | +1.936 |
Neg logit contributions | |
behavi | -1.754 |
subtitles | -1.706 |
Blu | -1.684 |
ophy | -1.681 |
AU | -1.659 |
Token | � |
Token ID | 447 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
subtitles | +0.720 |
Blu | +0.718 |
behavi | +0.708 |
ophy | +0.690 |
AU | +0.683 |
Neg logit contributions | |
anmar | -0.942 |
eters | -0.821 |
ativity | -0.789 |
andum | -0.763 |
warts | -0.759 |
Token | � |
Token ID | 247 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
anmar | +0.572 |
eters | +0.501 |
ativity | +0.480 |
andum | +0.464 |
warts | +0.463 |
Neg logit contributions | |
behavi | -0.436 |
subtitles | -0.426 |
Blu | -0.423 |
ophy | -0.412 |
AU | -0.405 |
Token | s |
Token ID | 82 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
subtitles | +0.067 |
Blu | +0.066 |
behavi | +0.066 |
ophy | +0.065 |
AU | +0.064 |
Neg logit contributions | |
anmar | -0.089 |
eters | -0.078 |
ativity | -0.075 |
andum | -0.072 |
warts | -0.072 |
Token | wireless |
Token ID | 12521 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
subtitles | +0.181 |
behavi | +0.181 |
Blu | +0.180 |
ophy | +0.175 |
AU | +0.172 |
Neg logit contributions | |
anmar | -0.222 |
eters | -0.193 |
ativity | -0.185 |
andum | -0.178 |
warts | -0.177 |
Token | connection |
Token ID | 4637 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
anmar | +3.189 |
eters | +2.819 |
ativity | +2.662 |
warts | +2.552 |
andum | +2.536 |
Neg logit contributions | |
behavi | -2.899 |
ophy | -2.809 |
subtitles | -2.802 |
AU | -2.753 |
Blu | -2.749 |
Token | turned |
Token ID | 2900 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
anmar | +2.780 |
eters | +2.458 |
ativity | +2.328 |
andum | +2.243 |
warts | +2.216 |
Neg logit contributions | |
behavi | -2.327 |
subtitles | -2.249 |
ophy | -2.228 |
Blu | -2.214 |
AU | -2.203 |
Token | off |
Token ID | 572 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
Blu | +0.805 |
subtitles | +0.799 |
behavi | +0.795 |
ophy | +0.770 |
AU | +0.758 |
Neg logit contributions | |
anmar | -1.283 |
eters | -1.132 |
ativity | -1.099 |
andum | -1.063 |
warts | -1.062 |
Token | unless |
Token ID | 4556 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
subtitles | +1.744 |
Blu | +1.737 |
behavi | +1.731 |
ophy | +1.673 |
AU | +1.653 |
Neg logit contributions | |
anmar | -2.841 |
eters | -2.497 |
ativity | -2.419 |
warts | -2.332 |
andum | -2.328 |
Token | you |
Token ID | 345 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
subtitles | +1.467 |
Blu | +1.464 |
behavi | +1.442 |
ophy | +1.408 |
AU | +1.388 |
Neg logit contributions | |
anmar | -1.590 |
eters | -1.366 |
ativity | -1.297 |
warts | -1.244 |
�� | -1.231 |
Token | recently |
Token ID | 2904 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
anmar | +1.025 |
eters | +0.899 |
ativity | +0.860 |
warts | +0.827 |
andum | +0.827 |
Neg logit contributions | |
behavi | -0.779 |
subtitles | -0.771 |
Blu | -0.765 |
ophy | -0.749 |
AU | -0.738 |
Token | under |
Token ID | 739 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
anmar | +0.636 |
eters | +0.547 |
ativity | +0.523 |
warts | +0.500 |
andum | +0.499 |
Neg logit contributions | |
behavi | -0.608 |
subtitles | -0.607 |
Blu | -0.605 |
ophy | -0.591 |
AU | -0.583 |
Token | whelming |
Token ID | 36433 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
anmar | +0.969 |
eters | +0.849 |
ativity | +0.816 |
andum | +0.786 |
warts | +0.786 |
Neg logit contributions | |
behavi | -0.704 |
subtitles | -0.702 |
Blu | -0.699 |
ophy | -0.680 |
AU | -0.671 |
Token | Can |
Token ID | 1680 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
anmar | +2.296 |
eters | +2.009 |
ativity | +1.904 |
warts | +1.836 |
andum | +1.829 |
Neg logit contributions | |
behavi | -1.926 |
subtitles | -1.887 |
Blu | -1.855 |
ophy | -1.831 |
AU | -1.821 |
Token | a |
Token ID | 64 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
anmar | +1.448 |
eters | +1.284 |
ativity | +1.240 |
andum | +1.201 |
warts | +1.191 |
Neg logit contributions | |
behavi | -0.843 |
subtitles | -0.821 |
Blu | -0.806 |
ophy | -0.784 |
puzz | -0.770 |
Token | , |
Token ID | 11 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
anmar | +1.837 |
eters | +1.594 |
ativity | +1.522 |
andum | +1.457 |
warts | +1.455 |
Neg logit contributions | |
behavi | -1.622 |
subtitles | -1.610 |
Blu | -1.597 |
ophy | -1.566 |
AU | -1.546 |
Token | Campbell |
Token ID | 14327 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
anmar | +2.003 |
eters | +1.709 |
ativity | +1.608 |
warts | +1.538 |
andum | +1.530 |
Neg logit contributions | |
behavi | -2.259 |
subtitles | -2.228 |
Blu | -2.210 |
ophy | -2.187 |
AU | -2.161 |
Token | and |
Token ID | 290 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
anmar | +1.991 |
eters | +1.733 |
ativity | +1.650 |
warts | +1.582 |
andum | +1.581 |
Neg logit contributions | |
behavi | -1.729 |
subtitles | -1.710 |
Blu | -1.699 |
ophy | -1.669 |
AU | -1.646 |
Token | St |
Token ID | 520 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
anmar | +0.766 |
eters | +0.671 |
ativity | +0.643 |
warts | +0.618 |
andum | +0.618 |
Neg logit contributions | |
behavi | -0.579 |
subtitles | -0.576 |
Blu | -0.572 |
ophy | -0.559 |
AU | -0.550 |
Token | eed |
Token ID | 2308 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
anmar | +2.329 |
eters | +2.060 |
ativity | +1.956 |
warts | +1.887 |
andum | +1.879 |
Neg logit contributions | |
behavi | -1.868 |
subtitles | -1.827 |
Blu | -1.781 |
ophy | -1.731 |
AU | -1.722 |
Token | Mal |
Token ID | 4434 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
anmar | +4.629 |
eters | +4.145 |
ativity | +3.918 |
warts | +3.881 |
felt | +3.795 |
Neg logit contributions | |
behavi | -3.483 |
subtitles | -3.379 |
ophy | -3.288 |
Blu | -3.234 |
AU | -3.183 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
behavi | +0.207 |
subtitles | +0.206 |
Blu | +0.205 |
ophy | +0.200 |
AU | +0.197 |
Neg logit contributions | |
anmar | -0.255 |
eters | -0.222 |
ativity | -0.213 |
andum | -0.204 |
warts | -0.204 |
Token | first |
Token ID | 717 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
subtitles | +0.961 |
behavi | +0.958 |
Blu | +0.957 |
ophy | +0.932 |
AU | +0.912 |
Neg logit contributions | |
anmar | -1.232 |
eters | -1.078 |
ativity | -1.040 |
andum | -0.993 |
warts | -0.992 |
Token | w |
Token ID | 266 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
anmar | +2.901 |
eters | +2.547 |
ativity | +2.397 |
andum | +2.336 |
warts | +2.335 |
Neg logit contributions | |
behavi | -2.377 |
subtitles | -2.336 |
Blu | -2.295 |
ophy | -2.264 |
AU | -2.246 |
Token | icket |
Token ID | 9715 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
anmar | +3.684 |
eters | +3.217 |
ativity | +2.986 |
warts | +2.905 |
andum | +2.899 |
Neg logit contributions | |
behavi | -3.763 |
subtitles | -3.694 |
Blu | -3.650 |
ophy | -3.537 |
AU | -3.504 |
Token | to |
Token ID | 284 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
anmar | +4.154 |
eters | +3.724 |
ativity | +3.509 |
warts | +3.420 |
felt | +3.410 |
Neg logit contributions | |
behavi | -3.038 |
subtitles | -2.991 |
Blu | -2.910 |
ophy | -2.908 |
AU | -2.818 |
Token | fall |
Token ID | 2121 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
anmar | +1.336 |
eters | +1.163 |
ativity | +1.108 |
warts | +1.064 |
andum | +1.064 |
Neg logit contributions | |
behavi | -1.161 |
subtitles | -1.150 |
Blu | -1.142 |
ophy | -1.121 |
AU | -1.104 |
Token | . |
Token ID | 13 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
behavi | +0.570 |
subtitles | +0.567 |
Blu | +0.565 |
ophy | +0.551 |
AU | +0.541 |
Neg logit contributions | |
anmar | -0.804 |
eters | -0.705 |
ativity | -0.680 |
warts | -0.653 |
andum | -0.652 |
Token | Attempt |
Token ID | 25770 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
anmar | +0.400 |
eters | +0.353 |
ativity | +0.337 |
warts | +0.324 |
andum | +0.324 |
Neg logit contributions | |
behavi | -0.302 |
subtitles | -0.297 |
Blu | -0.293 |
ophy | -0.289 |
AU | -0.283 |
Token | ing |
Token ID | 278 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
anmar | +2.017 |
eters | +1.765 |
ativity | +1.689 |
andum | +1.622 |
warts | +1.620 |
Neg logit contributions | |
behavi | -1.600 |
subtitles | -1.588 |
Blu | -1.577 |
ophy | -1.545 |
AU | -1.522 |
Token | to |
Token ID | 284 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
behavi | +0.071 |
subtitles | +0.071 |
Blu | +0.071 |
ophy | +0.068 |
AU | +0.067 |
Neg logit contributions | |
anmar | -0.097 |
eters | -0.084 |
ativity | -0.081 |
warts | -0.078 |
andum | -0.078 |
Token | crash |
Token ID | 7014 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
subtitles | +2.949 |
Blu | +2.905 |
behavi | +2.783 |
ophy | +2.781 |
puzz | +2.774 |
Neg logit contributions | |
anmar | -3.738 |
eters | -3.171 |
ativity | -3.128 |
�� | -3.029 |
andum | -2.958 |
Token | he |
Token ID | 339 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
anmar | +0.592 |
eters | +0.518 |
ativity | +0.495 |
warts | +0.476 |
andum | +0.475 |
Neg logit contributions | |
behavi | -0.473 |
subtitles | -0.469 |
Blu | -0.466 |
ophy | -0.456 |
AU | -0.449 |
Token | can |
Token ID | 460 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
behavi | +0.267 |
subtitles | +0.265 |
Blu | +0.264 |
ophy | +0.258 |
AU | +0.254 |
Neg logit contributions | |
anmar | -0.319 |
eters | -0.278 |
ativity | -0.266 |
warts | -0.255 |
andum | -0.255 |
Token | make |
Token ID | 787 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
behavi | +0.099 |
subtitles | +0.099 |
Blu | +0.098 |
ophy | +0.096 |
AU | +0.095 |
Neg logit contributions | |
anmar | -0.106 |
eters | -0.092 |
ativity | -0.087 |
warts | -0.084 |
andum | -0.083 |
Token | peace |
Token ID | 4167 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
anmar | +1.588 |
eters | +1.386 |
ativity | +1.325 |
warts | +1.273 |
andum | +1.268 |
Neg logit contributions | |
behavi | -1.288 |
subtitles | -1.266 |
Blu | -1.255 |
ophy | -1.241 |
AU | -1.221 |
Token | , |
Token ID | 11 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
subtitles | +1.695 |
behavi | +1.689 |
Blu | +1.683 |
AU | +1.620 |
ophy | +1.615 |
Neg logit contributions | |
anmar | -2.691 |
eters | -2.379 |
ativity | -2.282 |
andum | -2.222 |
�� | -2.212 |
Token | then |
Token ID | 788 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
subtitles | +1.841 |
behavi | +1.840 |
Blu | +1.832 |
ophy | +1.782 |
AU | +1.748 |
Neg logit contributions | |
anmar | -2.591 |
eters | -2.271 |
ativity | -2.172 |
andum | -2.099 |
�� | -2.084 |
Token | all |
Token ID | 477 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
behavi | +0.364 |
subtitles | +0.361 |
Blu | +0.358 |
ophy | +0.351 |
AU | +0.346 |
Neg logit contributions | |
anmar | -0.467 |
eters | -0.409 |
ativity | -0.392 |
warts | -0.376 |
andum | -0.376 |
Token | the |
Token ID | 262 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
behavi | +0.291 |
subtitles | +0.289 |
Blu | +0.287 |
ophy | +0.281 |
AU | +0.276 |
Neg logit contributions | |
anmar | -0.393 |
eters | -0.345 |
ativity | -0.331 |
warts | -0.319 |
andum | -0.318 |
Token | respect |
Token ID | 2461 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
anmar | +0.704 |
eters | +0.617 |
ativity | +0.587 |
warts | +0.566 |
andum | +0.563 |
Neg logit contributions | |
behavi | -0.544 |
subtitles | -0.536 |
Blu | -0.530 |
ophy | -0.525 |
AU | -0.516 |
Token | to |
Token ID | 284 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
anmar | +0.862 |
eters | +0.756 |
ativity | +0.725 |
warts | +0.696 |
andum | +0.695 |
Neg logit contributions | |
behavi | -0.684 |
subtitles | -0.677 |
Blu | -0.672 |
ophy | -0.660 |
AU | -0.648 |
Token | him |
Token ID | 683 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
anmar | +2.221 |
eters | +1.943 |
ativity | +1.857 |
warts | +1.796 |
andum | +1.790 |
Neg logit contributions | |
behavi | -1.809 |
subtitles | -1.778 |
Blu | -1.762 |
ophy | -1.753 |
AU | -1.708 |
Token | training |
Token ID | 3047 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
anmar | +0.996 |
eters | +0.884 |
ativity | +0.854 |
andum | +0.820 |
warts | +0.817 |
Neg logit contributions | |
behavi | -0.614 |
subtitles | -0.611 |
Blu | -0.608 |
ophy | -0.595 |
AU | -0.582 |
Token | � |
Token ID | 447 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
behavi | +0.627 |
subtitles | +0.621 |
Blu | +0.615 |
ophy | +0.599 |
AU | +0.590 |
Neg logit contributions | |
anmar | -1.068 |
eters | -0.947 |
ativity | -0.911 |
warts | -0.881 |
andum | -0.878 |
Token | � |
Token ID | 251 |
Feature activation | -8.69e-02 |
Pos logit contributions | |
subtitles | +0.146 |
behavi | +0.146 |
Blu | +0.145 |
ophy | +0.142 |
AU | +0.139 |
Neg logit contributions | |
anmar | -0.192 |
eters | -0.168 |
ativity | -0.161 |
andum | -0.154 |
warts | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
behavi | +0.266 |
subtitles | +0.264 |
Blu | +0.262 |
ophy | +0.255 |
AU | +0.251 |
Neg logit contributions | |
anmar | -0.454 |
eters | -0.403 |
ativity | -0.388 |
warts | -0.374 |
andum | -0.374 |
Token | She |
Token ID | 1375 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
behavi | +0.087 |
subtitles | +0.087 |
Blu | +0.087 |
ophy | +0.084 |
AU | +0.083 |
Neg logit contributions | |
anmar | -0.139 |
eters | -0.123 |
ativity | -0.118 |
andum | -0.114 |
warts | -0.114 |
Token | has |
Token ID | 468 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
subtitles | +0.645 |
Blu | +0.634 |
behavi | +0.632 |
ophy | +0.628 |
AU | +0.614 |
Neg logit contributions | |
anmar | -0.789 |
eters | -0.669 |
ativity | -0.650 |
�� | -0.630 |
warts | -0.625 |
Token | also |
Token ID | 635 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
subtitles | +0.813 |
behavi | +0.804 |
Blu | +0.803 |
ophy | +0.783 |
AU | +0.772 |
Neg logit contributions | |
anmar | -0.853 |
eters | -0.723 |
ativity | -0.697 |
warts | -0.672 |
andum | -0.666 |
Token | been |
Token ID | 587 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
anmar | +0.441 |
eters | +0.383 |
ativity | +0.367 |
warts | +0.354 |
andum | +0.352 |
Neg logit contributions | |
subtitles | -0.355 |
behavi | -0.354 |
Blu | -0.352 |
ophy | -0.344 |
AU | -0.339 |
Token | told |
Token ID | 1297 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
behavi | +0.163 |
subtitles | +0.163 |
Blu | +0.162 |
ophy | +0.158 |
AU | +0.156 |
Neg logit contributions | |
anmar | -0.169 |
eters | -0.144 |
ativity | -0.138 |
warts | -0.133 |
andum | -0.132 |
Token | to |
Token ID | 284 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
anmar | +0.582 |
eters | +0.506 |
ativity | +0.485 |
warts | +0.467 |
andum | +0.466 |
Neg logit contributions | |
behavi | -0.453 |
subtitles | -0.451 |
Blu | -0.448 |
ophy | -0.438 |
AU | -0.431 |
Token | move |
Token ID | 1445 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
anmar | +0.953 |
eters | +0.831 |
ativity | +0.793 |
andum | +0.760 |
warts | +0.760 |
Neg logit contributions | |
behavi | -0.817 |
subtitles | -0.808 |
Blu | -0.804 |
ophy | -0.787 |
AU | -0.777 |
Token | then |
Token ID | 788 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
subtitles | +0.747 |
Blu | +0.742 |
behavi | +0.739 |
ophy | +0.716 |
AU | +0.707 |
Neg logit contributions | |
anmar | -1.319 |
eters | -1.167 |
ativity | -1.131 |
warts | -1.085 |
andum | -1.085 |
Token | -- |
Token ID | 1377 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
anmar | +0.704 |
eters | +0.617 |
ativity | +0.589 |
warts | +0.568 |
andum | +0.568 |
Neg logit contributions | |
behavi | -0.559 |
subtitles | -0.546 |
Blu | -0.543 |
ophy | -0.536 |
AU | -0.526 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
subtitles | +0.604 |
Blu | +0.600 |
behavi | +0.599 |
ophy | +0.583 |
AU | +0.576 |
Neg logit contributions | |
anmar | -0.852 |
eters | -0.747 |
ativity | -0.719 |
andum | -0.689 |
warts | -0.689 |
Token | The |
Token ID | 464 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
anmar | +0.211 |
eters | +0.187 |
ativity | +0.181 |
andum | +0.174 |
warts | +0.174 |
Neg logit contributions | |
behavi | -0.121 |
subtitles | -0.121 |
Blu | -0.120 |
ophy | -0.117 |
AU | -0.115 |
Token | nearest |
Token ID | 16936 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
anmar | +0.788 |
eters | +0.691 |
ativity | +0.662 |
warts | +0.637 |
andum | +0.636 |
Neg logit contributions | |
behavi | -0.596 |
subtitles | -0.593 |
Blu | -0.589 |
ophy | -0.575 |
AU | -0.566 |
Token | Is |
Token ID | 1148 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
anmar | +2.118 |
eters | +1.851 |
ativity | +1.762 |
warts | +1.692 |
andum | +1.692 |
Neg logit contributions | |
behavi | -1.716 |
subtitles | -1.684 |
Blu | -1.664 |
ophy | -1.648 |
AU | -1.621 |
Token | il |
Token ID | 346 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
Blu | +0.715 |
subtitles | +0.712 |
behavi | +0.711 |
ophy | +0.699 |
AU | +0.686 |
Neg logit contributions | |
anmar | -0.949 |
eters | -0.836 |
ativity | -0.801 |
warts | -0.773 |
�� | -0.772 |
Token | installation |
Token ID | 9988 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
Blu | +1.021 |
subtitles | +1.020 |
behavi | +1.016 |
ophy | +0.984 |
AU | +0.974 |
Neg logit contributions | |
anmar | -1.336 |
eters | -1.173 |
ativity | -1.131 |
andum | -1.082 |
warts | -1.078 |
Token | to |
Token ID | 284 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
anmar | +2.084 |
eters | +1.815 |
ativity | +1.720 |
andum | +1.653 |
warts | +1.652 |
Neg logit contributions | |
behavi | -1.786 |
subtitles | -1.749 |
Blu | -1.724 |
ophy | -1.716 |
AU | -1.679 |
Token | the |
Token ID | 262 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
anmar | +1.439 |
eters | +1.262 |
ativity | +1.211 |
warts | +1.166 |
andum | +1.165 |
Neg logit contributions | |
behavi | -1.042 |
subtitles | -1.032 |
Blu | -1.022 |
ophy | -1.003 |
AU | -0.987 |
Token | site |
Token ID | 2524 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
anmar | +1.438 |
eters | +1.254 |
ativity | +1.200 |
warts | +1.154 |
andum | +1.153 |
Neg logit contributions | |
behavi | -1.113 |
subtitles | -1.099 |
Blu | -1.089 |
ophy | -1.072 |
AU | -1.056 |
Token | m |
Token ID | 76 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
behavi | +0.434 |
subtitles | +0.426 |
Blu | +0.422 |
ophy | +0.412 |
AU | +0.404 |
Neg logit contributions | |
anmar | -0.634 |
eters | -0.562 |
ativity | -0.538 |
warts | -0.519 |
andum | -0.519 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
anmar | +3.894 |
eters | +3.465 |
ativity | +3.329 |
andum | +3.212 |
warts | +3.210 |
Neg logit contributions | |
behavi | -2.301 |
subtitles | -2.284 |
Blu | -2.258 |
ophy | -2.206 |
AU | -2.162 |
Token | ET |
Token ID | 12152 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
anmar | +0.628 |
eters | +0.554 |
ativity | +0.535 |
warts | +0.519 |
andum | +0.517 |
Neg logit contributions | |
Blu | -0.390 |
subtitles | -0.389 |
behavi | -0.388 |
ophy | -0.375 |
AU | -0.371 |
Token | ), |
Token ID | 828 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
subtitles | +1.236 |
Blu | +1.235 |
behavi | +1.209 |
AU | +1.184 |
ophy | +1.183 |
Neg logit contributions | |
anmar | -1.724 |
eters | -1.508 |
ativity | -1.459 |
warts | -1.420 |
andum | -1.417 |
Token | Carlson |
Token ID | 33059 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
behavi | +0.498 |
subtitles | +0.496 |
Blu | +0.494 |
ophy | +0.479 |
AU | +0.471 |
Neg logit contributions | |
anmar | -0.795 |
eters | -0.702 |
ativity | -0.678 |
warts | -0.653 |
andum | -0.652 |
Token | said |
Token ID | 531 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
subtitles | +0.232 |
behavi | +0.231 |
Blu | +0.229 |
ophy | +0.223 |
AU | +0.217 |
Neg logit contributions | |
anmar | -0.520 |
eters | -0.464 |
ativity | -0.449 |
warts | -0.439 |
andum | -0.435 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
subtitles | +0.812 |
behavi | +0.812 |
Blu | +0.811 |
ophy | +0.775 |
AU | +0.761 |
Neg logit contributions | |
anmar | -1.723 |
eters | -1.531 |
ativity | -1.482 |
warts | -1.444 |
andum | -1.430 |
Token | " |
Token ID | 366 |
Feature activation | +8.85e-03 |
Pos logit contributions | |
Blu | +0.673 |
subtitles | +0.672 |
behavi | +0.664 |
ophy | +0.650 |
AU | +0.643 |
Neg logit contributions | |
anmar | -1.043 |
eters | -0.910 |
ativity | -0.882 |
warts | -0.851 |
andum | -0.847 |
Token | At |
Token ID | 2953 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
anmar | +0.047 |
eters | +0.043 |
ativity | +0.041 |
warts | +0.040 |
andum | +0.040 |
Neg logit contributions | |
behavi | -0.026 |
subtitles | -0.026 |
Blu | -0.025 |
ophy | -0.025 |
puzz | -0.024 |
Token | that |
Token ID | 326 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
behavi | +0.856 |
subtitles | +0.854 |
Blu | +0.850 |
ophy | +0.831 |
AU | +0.817 |
Neg logit contributions | |
anmar | -1.091 |
eters | -0.949 |
ativity | -0.909 |
warts | -0.872 |
andum | -0.871 |
Token | point |
Token ID | 966 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
anmar | +1.672 |
eters | +1.505 |
ativity | +1.452 |
andum | +1.405 |
warts | +1.401 |
Neg logit contributions | |
behavi | -0.777 |
subtitles | -0.766 |
Blu | -0.757 |
ophy | -0.737 |
AU | -0.722 |
Token | can |
Token ID | 460 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
anmar | +0.523 |
eters | +0.455 |
ativity | +0.435 |
warts | +0.417 |
andum | +0.417 |
Neg logit contributions | |
behavi | -0.435 |
subtitles | -0.434 |
Blu | -0.431 |
ophy | -0.422 |
AU | -0.416 |
Token | accommodate |
Token ID | 15550 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
anmar | +1.813 |
eters | +1.569 |
ativity | +1.491 |
andum | +1.433 |
warts | +1.427 |
Neg logit contributions | |
behavi | -1.773 |
subtitles | -1.744 |
Blu | -1.733 |
ophy | -1.695 |
AU | -1.678 |
Token | a |
Token ID | 257 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
anmar | +1.827 |
eters | +1.606 |
ativity | +1.541 |
andum | +1.479 |
warts | +1.468 |
Neg logit contributions | |
behavi | -1.366 |
subtitles | -1.338 |
Blu | -1.322 |
ophy | -1.300 |
AU | -1.281 |
Token | brief |
Token ID | 4506 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
anmar | +0.660 |
eters | +0.576 |
ativity | +0.551 |
andum | +0.529 |
warts | +0.527 |
Neg logit contributions | |
behavi | -0.537 |
subtitles | -0.532 |
Blu | -0.527 |
ophy | -0.517 |
AU | -0.510 |
Token | work |
Token ID | 670 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
anmar | +2.060 |
eters | +1.802 |
ativity | +1.722 |
andum | +1.667 |
warts | +1.639 |
Neg logit contributions | |
behavi | -1.638 |
subtitles | -1.617 |
Blu | -1.590 |
ophy | -1.559 |
AU | -1.542 |
Token | stopp |
Token ID | 43804 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
anmar | +0.070 |
eters | +0.062 |
ativity | +0.059 |
warts | +0.057 |
andum | +0.057 |
Neg logit contributions | |
behavi | -0.044 |
subtitles | -0.044 |
Blu | -0.043 |
ophy | -0.042 |
AU | -0.041 |
Token | age |
Token ID | 496 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
Blu | +2.499 |
ophy | +2.497 |
subtitles | +2.428 |
AU | +2.381 |
puzz | +2.270 |
Neg logit contributions | |
anmar | -5.786 |
eters | -5.178 |
�� | -4.955 |
ativity | -4.947 |
warts | -4.862 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
Blu | +2.369 |
subtitles | +2.354 |
behavi | +2.346 |
ophy | +2.278 |
AU | +2.254 |
Neg logit contributions | |
anmar | -3.526 |
eters | -3.088 |
ativity | -2.972 |
warts | -2.875 |
�� | -2.874 |
Token | But |
Token ID | 887 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
behavi | +0.077 |
subtitles | +0.077 |
Blu | +0.076 |
ophy | +0.074 |
AU | +0.073 |
Neg logit contributions | |
anmar | -0.104 |
eters | -0.091 |
ativity | -0.087 |
warts | -0.084 |
andum | -0.084 |
Token | if |
Token ID | 611 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
behavi | +0.901 |
subtitles | +0.899 |
Blu | +0.897 |
ophy | +0.873 |
AU | +0.858 |
Neg logit contributions | |
anmar | -1.271 |
eters | -1.112 |
ativity | -1.068 |
warts | -1.028 |
andum | -1.026 |
Token | MA |
Token ID | 8779 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
anmar | +0.738 |
eters | +0.649 |
ativity | +0.623 |
warts | +0.600 |
andum | +0.600 |
Neg logit contributions | |
behavi | -0.517 |
subtitles | -0.513 |
Blu | -0.509 |
ophy | -0.497 |
AU | -0.489 |
Token | is |
Token ID | 318 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
anmar | +3.624 |
eters | +3.174 |
ativity | +3.022 |
warts | +2.865 |
andum | +2.864 |
Neg logit contributions | |
behavi | -3.250 |
subtitles | -3.210 |
Blu | -3.162 |
ophy | -3.090 |
AU | -3.061 |
Token | currently |
Token ID | 3058 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
anmar | +1.146 |
eters | +0.996 |
ativity | +0.944 |
warts | +0.905 |
andum | +0.898 |
Neg logit contributions | |
behavi | -1.053 |
subtitles | -1.032 |
Blu | -1.016 |
ophy | -1.009 |
AU | -0.992 |
Token | over |
Token ID | 625 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
behavi | +0.067 |
subtitles | +0.066 |
Blu | +0.065 |
ophy | +0.064 |
AU | +0.063 |
Neg logit contributions | |
anmar | -0.079 |
eters | -0.069 |
ativity | -0.066 |
warts | -0.063 |
andum | -0.063 |
Token | a |
Token ID | 257 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
anmar | +2.570 |
eters | +2.270 |
ativity | +2.169 |
warts | +2.093 |
felt | +2.072 |
Neg logit contributions | |
behavi | -1.816 |
subtitles | -1.791 |
Blu | -1.763 |
ophy | -1.724 |
AU | -1.693 |
Token | deep |
Token ID | 2769 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
anmar | +2.372 |
eters | +2.110 |
ativity | +1.997 |
andum | +1.931 |
warts | +1.916 |
Neg logit contributions | |
behavi | -1.686 |
subtitles | -1.656 |
Blu | -1.615 |
ophy | -1.603 |
AU | -1.588 |
Token | gou |
Token ID | 50162 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
anmar | +3.632 |
eters | +3.171 |
ativity | +3.045 |
andum | +2.936 |
warts | +2.921 |
Neg logit contributions | |
behavi | -2.899 |
subtitles | -2.811 |
Blu | -2.755 |
ophy | -2.728 |
AU | -2.709 |
Token | ge |
Token ID | 469 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
ophy | +5.391 |
Blu | +5.300 |
subtitles | +5.289 |
AU | +5.158 |
esian | +5.113 |
Neg logit contributions | |
anmar | -2.665 |
eters | -1.945 |
ativity | -1.821 |
�� | -1.768 |
andum | -1.686 |
Token | in |
Token ID | 287 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Blu | +1.963 |
subtitles | +1.961 |
behavi | +1.955 |
ophy | +1.909 |
AU | +1.882 |
Neg logit contributions | |
anmar | -2.763 |
eters | -2.423 |
ativity | -2.324 |
andum | -2.243 |
warts | -2.241 |
Token | which |
Token ID | 543 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
subtitles | +0.483 |
behavi | +0.483 |
Blu | +0.482 |
ophy | +0.468 |
AU | +0.458 |
Neg logit contributions | |
anmar | -0.757 |
eters | -0.670 |
ativity | -0.643 |
andum | -0.621 |
warts | -0.621 |
Token | the |
Token ID | 262 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
behavi | +0.151 |
subtitles | +0.149 |
Blu | +0.148 |
ophy | +0.144 |
AU | +0.142 |
Neg logit contributions | |
anmar | -0.219 |
eters | -0.193 |
ativity | -0.185 |
andum | -0.178 |
warts | -0.178 |
Token | bedrock |
Token ID | 47856 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
anmar | +0.332 |
eters | +0.290 |
ativity | +0.278 |
warts | +0.267 |
andum | +0.267 |
Neg logit contributions | |
behavi | -0.259 |
subtitles | -0.257 |
Blu | -0.255 |
ophy | -0.250 |
AU | -0.246 |
Token | er |
Token ID | 263 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
Blu | +0.254 |
behavi | +0.253 |
subtitles | +0.253 |
ophy | +0.246 |
AU | +0.241 |
Neg logit contributions | |
anmar | -0.366 |
eters | -0.320 |
ativity | -0.308 |
andum | -0.298 |
warts | -0.296 |
Token |
|
Token ID | 198 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
anmar | +2.594 |
eters | +2.293 |
ativity | +2.206 |
warts | +2.125 |
andum | +2.123 |
Neg logit contributions | |
behavi | -1.713 |
subtitles | -1.698 |
Blu | -1.681 |
ophy | -1.642 |
AU | -1.615 |
Token |
|
Token ID | 198 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
behavi | +0.183 |
subtitles | +0.174 |
Blu | +0.171 |
ophy | +0.169 |
puzz | +0.165 |
Neg logit contributions | |
anmar | -0.244 |
eters | -0.218 |
ativity | -0.208 |
warts | -0.201 |
andum | -0.200 |
Token | Ph |
Token ID | 2725 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
behavi | +0.064 |
subtitles | +0.063 |
Blu | +0.063 |
ophy | +0.062 |
AU | +0.061 |
Neg logit contributions | |
anmar | -0.104 |
eters | -0.092 |
ativity | -0.089 |
andum | -0.086 |
warts | -0.086 |
Token | y |
Token ID | 88 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ophy | +0.546 |
Blu | +0.545 |
subtitles | +0.542 |
behavi | +0.532 |
AU | +0.527 |
Neg logit contributions | |
anmar | -0.601 |
eters | -0.519 |
ativity | -0.496 |
�� | -0.474 |
andum | -0.471 |
Token | rex |
Token ID | 21510 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
subtitles | +0.855 |
Blu | +0.853 |
ophy | +0.850 |
behavi | +0.848 |
AU | +0.821 |
Neg logit contributions | |
anmar | -0.824 |
eters | -0.706 |
ativity | -0.664 |
andum | -0.636 |
warts | -0.634 |
Token | ian |
Token ID | 666 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
ophy | +3.860 |
Blu | +3.713 |
subtitles | +3.491 |
AU | +3.368 |
esian | +3.349 |
Neg logit contributions | |
anmar | -8.281 |
eters | -7.278 |
ativity | -7.144 |
�� | -7.124 |
warts | -7.020 |
Token | Tower |
Token ID | 8765 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
subtitles | +0.276 |
Blu | +0.275 |
behavi | +0.274 |
ophy | +0.268 |
AU | +0.262 |
Neg logit contributions | |
anmar | -0.373 |
eters | -0.326 |
ativity | -0.312 |
warts | -0.301 |
andum | -0.299 |
Token | vs |
Token ID | 3691 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Blu | +0.191 |
behavi | +0.190 |
subtitles | +0.190 |
ophy | +0.186 |
AU | +0.181 |
Neg logit contributions | |
anmar | -0.304 |
eters | -0.268 |
ativity | -0.257 |
andum | -0.248 |
warts | -0.248 |
Token | Sands |
Token ID | 35359 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
anmar | +1.054 |
eters | +0.926 |
ativity | +0.888 |
warts | +0.854 |
andum | +0.854 |
Neg logit contributions | |
behavi | -0.770 |
subtitles | -0.763 |
Blu | -0.755 |
ophy | -0.740 |
AU | -0.729 |
Token | of |
Token ID | 286 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
anmar | +0.073 |
eters | +0.064 |
ativity | +0.062 |
andum | +0.059 |
warts | +0.059 |
Neg logit contributions | |
behavi | -0.048 |
subtitles | -0.048 |
Blu | -0.048 |
ophy | -0.047 |
AU | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
Blu | +1.398 |
behavi | +1.395 |
subtitles | +1.394 |
ophy | +1.356 |
AU | +1.324 |
Neg logit contributions | |
anmar | -2.115 |
eters | -1.837 |
ativity | -1.769 |
warts | -1.723 |
andum | -1.702 |
Token | show |
Token ID | 905 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
subtitles | +1.595 |
Blu | +1.594 |
ophy | +1.537 |
behavi | +1.535 |
AU | +1.494 |
Neg logit contributions | |
anmar | -2.071 |
eters | -1.761 |
ativity | -1.714 |
�� | -1.664 |
warts | -1.641 |
Token | your |
Token ID | 534 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
anmar | +0.392 |
eters | +0.342 |
ativity | +0.327 |
warts | +0.313 |
andum | +0.313 |
Neg logit contributions | |
behavi | -0.330 |
subtitles | -0.327 |
Blu | -0.325 |
ophy | -0.318 |
AU | -0.314 |
Token | skills |
Token ID | 4678 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
anmar | +1.998 |
eters | +1.755 |
ativity | +1.668 |
warts | +1.622 |
andum | +1.606 |
Neg logit contributions | |
behavi | -1.549 |
subtitles | -1.535 |
Blu | -1.518 |
AU | -1.487 |
ophy | -1.486 |
Token | ? |
Token ID | 30 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
anmar | +0.026 |
eters | +0.023 |
ativity | +0.022 |
andum | +0.021 |
warts | +0.021 |
Neg logit contributions | |
behavi | -0.018 |
subtitles | -0.018 |
Blu | -0.018 |
ophy | -0.018 |
AU | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
Blu | +1.938 |
subtitles | +1.906 |
behavi | +1.866 |
AU | +1.856 |
ophy | +1.836 |
Neg logit contributions | |
anmar | -3.170 |
eters | -2.749 |
ativity | -2.673 |
warts | -2.576 |
�� | -2.568 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Blu | +2.723 |
subtitles | +2.676 |
AU | +2.627 |
ophy | +2.568 |
behavi | +2.453 |
Neg logit contributions | |
anmar | -4.977 |
eters | -4.300 |
ativity | -4.216 |
�� | -4.141 |
warts | -4.045 |
Token | CC |
Token ID | 4093 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
AU | +3.327 |
Blu | +3.216 |
subtitles | +3.159 |
ophy | +3.126 |
OVA | +3.045 |
Neg logit contributions | |
anmar | -5.321 |
eters | -4.532 |
ativity | -4.485 |
�� | -4.402 |
andum | -4.253 |
Token | : |
Token ID | 25 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
Blu | +2.904 |
subtitles | +2.844 |
AU | +2.841 |
ophy | +2.750 |
behavi | +2.683 |
Neg logit contributions | |
anmar | -5.133 |
eters | -4.455 |
ativity | -4.340 |
�� | -4.260 |
warts | -4.206 |
Token | It |
Token ID | 632 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Blu | +2.431 |
subtitles | +2.391 |
behavi | +2.312 |
ophy | +2.304 |
AU | +2.300 |
Neg logit contributions | |
anmar | -3.300 |
eters | -2.844 |
ativity | -2.756 |
warts | -2.658 |
�� | -2.657 |
Token | � |
Token ID | 447 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
subtitles | +1.170 |
Blu | +1.162 |
behavi | +1.142 |
ophy | +1.128 |
AU | +1.114 |
Neg logit contributions | |
anmar | -1.369 |
eters | -1.160 |
ativity | -1.116 |
�� | -1.091 |
andum | -1.079 |
Token | of |
Token ID | 286 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
subtitles | +0.547 |
behavi | +0.547 |
Blu | +0.544 |
ophy | +0.526 |
AU | +0.516 |
Neg logit contributions | |
anmar | -0.987 |
eters | -0.872 |
ativity | -0.833 |
warts | -0.811 |
andum | -0.805 |
Token | system |
Token ID | 1080 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
anmar | +1.205 |
eters | +1.056 |
ativity | +1.012 |
warts | +0.973 |
andum | +0.973 |
Neg logit contributions | |
behavi | -0.903 |
subtitles | -0.897 |
Blu | -0.890 |
ophy | -0.871 |
AU | -0.857 |
Token | () |
Token ID | 3419 |
Feature activation | -7.20e-04 |
Pos logit contributions | |
anmar | +0.302 |
eters | +0.265 |
ativity | +0.253 |
warts | +0.247 |
andum | +0.246 |
Neg logit contributions | |
behavi | -0.197 |
subtitles | -0.195 |
Blu | -0.193 |
ophy | -0.188 |
AU | -0.187 |
Token | ' |
Token ID | 6 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
behavi | +0.002 |
subtitles | +0.002 |
Blu | +0.002 |
ophy | +0.002 |
AU | +0.002 |
Neg logit contributions | |
anmar | -0.004 |
eters | -0.003 |
ativity | -0.003 |
andum | -0.003 |
warts | -0.003 |
Token | s |
Token ID | 82 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
subtitles | +1.321 |
Blu | +1.313 |
behavi | +1.292 |
ophy | +1.281 |
AU | +1.262 |
Neg logit contributions | |
anmar | -1.843 |
eters | -1.607 |
ativity | -1.548 |
�� | -1.490 |
andum | -1.489 |
Token | stack |
Token ID | 8931 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
subtitles | +1.663 |
behavi | +1.657 |
Blu | +1.642 |
ophy | +1.600 |
puzz | +1.577 |
Neg logit contributions | |
anmar | -1.798 |
eters | -1.560 |
ativity | -1.481 |
warts | -1.405 |
andum | -1.403 |
Token | frame |
Token ID | 5739 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
Blu | +1.316 |
behavi | +1.293 |
subtitles | +1.273 |
ophy | +1.178 |
puzz | +1.145 |
Neg logit contributions | |
anmar | -6.454 |
eters | -5.904 |
ativity | -5.623 |
warts | -5.578 |
andum | -5.531 |
Token | | |
Token ID | 930 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
Blu | +2.159 |
subtitles | +2.115 |
behavi | +2.073 |
AU | +2.002 |
puzz | +1.977 |
Neg logit contributions | |
anmar | -4.919 |
eters | -4.314 |
ativity | -4.200 |
andum | -4.082 |
�� | -4.053 |
Token | void |
Token ID | 7951 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
anmar | +0.092 |
eters | +0.080 |
ativity | +0.077 |
warts | +0.073 |
andum | +0.073 |
Neg logit contributions | |
behavi | -0.075 |
subtitles | -0.074 |
Blu | -0.074 |
ophy | -0.072 |
AU | -0.071 |
Token | * |
Token ID | 1635 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
behavi | +1.207 |
subtitles | +1.198 |
Blu | +1.198 |
ophy | +1.149 |
AU | +1.138 |
Neg logit contributions | |
anmar | -1.611 |
eters | -1.403 |
ativity | -1.338 |
warts | -1.314 |
�� | -1.277 |
Token | arg |
Token ID | 853 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
behavi | +0.293 |
subtitles | +0.293 |
Blu | +0.291 |
ophy | +0.289 |
AU | +0.284 |
Neg logit contributions | |
anmar | -0.270 |
eters | -0.225 |
ativity | -0.216 |
�� | -0.206 |
warts | -0.205 |