Token | U |
Token ID | 52 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
イト | +0.474 |
ー� | +0.459 |
ゴン | +0.452 |
checks | +0.449 |
roup | +0.449 |
Neg logit contributions | |
Palest | -0.522 |
anon | -0.457 |
Bey | -0.449 |
ILLE | -0.427 |
audi | -0.412 |
Token | ng |
Token ID | 782 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
イト | +2.292 |
roup | +2.227 |
ー� | +2.226 |
checks | +2.193 |
ゴン | +2.191 |
Neg logit contributions | |
Palest | -2.278 |
anon | -1.966 |
Bey | -1.930 |
ILLE | -1.832 |
oire | -1.759 |
Token | roup |
Token ID | 3233 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
roup | +4.903 |
zilla | +4.486 |
warts | +4.469 |
イト | +4.460 |
checks | +4.434 |
Neg logit contributions | |
Palest | -5.960 |
Bey | -5.180 |
anon | -4.920 |
ILLE | -4.911 |
oire | -4.605 |
Token | ed |
Token ID | 276 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
イト | +1.138 |
ー� | +1.105 |
roup | +1.099 |
checks | +1.086 |
ゴン | +1.084 |
Neg logit contributions | |
Palest | -1.282 |
anon | -1.115 |
Bey | -1.114 |
ILLE | -1.060 |
audi | -1.022 |
Token | [ |
Token ID | 685 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Palest | +1.788 |
anon | +1.573 |
Bey | +1.535 |
ILLE | +1.452 |
audi | +1.402 |
Neg logit contributions | |
イト | -1.693 |
ー� | -1.630 |
ゴン | -1.610 |
checks | -1.593 |
roup | -1.580 |
Token | edit |
Token ID | 4370 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
イト | +0.756 |
ー� | +0.735 |
checks | +0.728 |
roup | +0.722 |
safety | +0.715 |
Neg logit contributions | |
Palest | -0.804 |
anon | -0.687 |
Bey | -0.682 |
ILLE | -0.648 |
audi | -0.624 |
Token | ] |
Token ID | 2361 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
ー� | +3.777 |
roup | +3.620 |
zilla | +3.618 |
safety | +3.611 |
イト | +3.543 |
Neg logit contributions | |
Palest | -13.298 |
Bey | -11.387 |
ILLE | -11.294 |
anon | -10.956 |
audi | -10.878 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ー� | +2.637 |
イト | +2.636 |
roup | +2.629 |
checks | +2.585 |
zilla | +2.579 |
Neg logit contributions | |
Palest | -3.535 |
Bey | -2.950 |
anon | -2.928 |
ILLE | -2.878 |
audi | -2.762 |
Token |
|
Token ID | 198 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
イト | +1.150 |
ー� | +1.144 |
checks | +1.130 |
roup | +1.115 |
safety | +1.108 |
Neg logit contributions | |
Palest | -1.441 |
anon | -1.200 |
Bey | -1.189 |
ILLE | -1.156 |
audi | -1.116 |
Token | Gen |
Token ID | 13746 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
イト | +1.127 |
ー� | +1.096 |
roup | +1.080 |
ゴン | +1.079 |
checks | +1.078 |
Neg logit contributions | |
Palest | -1.129 |
anon | -0.971 |
Bey | -0.952 |
ILLE | -0.908 |
audi | -0.874 |
Token | etics |
Token ID | 14596 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
イト | +2.109 |
roup | +2.080 |
ー� | +2.050 |
checks | +2.016 |
zilla | +1.992 |
Neg logit contributions | |
Palest | -2.749 |
anon | -2.404 |
Bey | -2.391 |
ILLE | -2.288 |
audi | -2.180 |
Token | community |
Token ID | 2055 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
イト | +1.940 |
ー� | +1.890 |
safety | +1.867 |
checks | +1.857 |
roup | +1.842 |
Neg logit contributions | |
Palest | -2.173 |
anon | -1.950 |
Bey | -1.891 |
ILLE | -1.800 |
oire | -1.739 |
Token | boards |
Token ID | 11490 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
イト | +1.285 |
ー� | +1.237 |
ゴン | +1.208 |
checks | +1.207 |
roup | +1.201 |
Neg logit contributions | |
Palest | -1.913 |
anon | -1.716 |
Bey | -1.688 |
ILLE | -1.616 |
audi | -1.569 |
Token | across |
Token ID | 1973 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
イト | +1.904 |
ー� | +1.849 |
safety | +1.830 |
roup | +1.822 |
checks | +1.820 |
Neg logit contributions | |
Palest | -2.410 |
anon | -2.119 |
Bey | -2.096 |
ILLE | -1.991 |
audi | -1.921 |
Token | the |
Token ID | 262 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Palest | +0.286 |
anon | +0.254 |
Bey | +0.250 |
ILLE | +0.239 |
audi | +0.232 |
Neg logit contributions | |
イト | -0.208 |
ー� | -0.200 |
ゴン | -0.197 |
checks | -0.195 |
roup | -0.195 |
Token | city |
Token ID | 1748 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Palest | +0.109 |
anon | +0.096 |
Bey | +0.094 |
ILLE | +0.090 |
audi | +0.086 |
Neg logit contributions | |
イト | -0.103 |
ー� | -0.100 |
roup | -0.098 |
checks | -0.098 |
ゴン | -0.098 |
Token | weigh |
Token ID | 10164 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
Palest | +0.219 |
anon | +0.195 |
Bey | +0.191 |
ILLE | +0.183 |
audi | +0.177 |
Neg logit contributions | |
イト | -0.169 |
ー� | -0.162 |
ゴン | -0.160 |
checks | -0.158 |
roup | -0.158 |
Token | in |
Token ID | 287 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
safety | +6.522 |
イト | +6.424 |
checks | +6.228 |
roles | +6.097 |
rev | +6.052 |
Neg logit contributions | |
Palest | -10.134 |
anon | -9.104 |
Bey | -8.841 |
oire | -8.437 |
audi | -8.418 |
Token | on |
Token ID | 319 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
イト | +0.068 |
ー� | +0.065 |
ゴン | +0.064 |
checks | +0.064 |
roup | +0.064 |
Neg logit contributions | |
Palest | -0.083 |
anon | -0.073 |
Bey | -0.072 |
ILLE | -0.069 |
audi | -0.066 |
Token | proposed |
Token ID | 5150 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
イト | +1.184 |
ー� | +1.142 |
checks | +1.116 |
ゴン | +1.112 |
safety | +1.112 |
Neg logit contributions | |
Palest | -1.687 |
anon | -1.509 |
Bey | -1.480 |
ILLE | -1.416 |
audi | -1.374 |
Token | housing |
Token ID | 5627 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
イト | +0.405 |
ー� | +0.387 |
ゴン | +0.380 |
checks | +0.377 |
roup | +0.376 |
Neg logit contributions | |
Palest | -0.703 |
anon | -0.633 |
Bey | -0.624 |
ILLE | -0.598 |
audi | -0.582 |
Token | policies |
Token ID | 4788 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
イト | +0.321 |
ー� | +0.306 |
ゴン | +0.300 |
checks | +0.298 |
roup | +0.297 |
Neg logit contributions | |
Palest | -0.590 |
anon | -0.532 |
Bey | -0.525 |
ILLE | -0.504 |
audi | -0.490 |
Token |
|
Token ID | 198 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
イト | +0.054 |
ー� | +0.052 |
ゴン | +0.051 |
roup | +0.051 |
checks | +0.051 |
Neg logit contributions | |
Palest | -0.058 |
anon | -0.051 |
Bey | -0.050 |
ILLE | -0.047 |
audi | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Palest | +0.359 |
anon | +0.305 |
Bey | +0.301 |
ILLE | +0.288 |
audi | +0.279 |
Neg logit contributions | |
イト | -0.331 |
ー� | -0.324 |
checks | -0.319 |
roup | -0.315 |
safety | -0.313 |
Token | Middle |
Token ID | 34621 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Palest | +0.332 |
anon | +0.290 |
Bey | +0.284 |
ILLE | +0.269 |
audi | +0.260 |
Neg logit contributions | |
イト | -0.327 |
ー� | -0.317 |
ゴン | -0.312 |
checks | -0.310 |
roup | -0.310 |
Token | Ages |
Token ID | 21449 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
Palest | +1.620 |
anon | +1.418 |
Bey | +1.396 |
ILLE | +1.313 |
audi | +1.278 |
Neg logit contributions | |
イト | -1.450 |
ー� | -1.391 |
ゴン | -1.382 |
checks | -1.364 |
roup | -1.351 |
Token | [ |
Token ID | 685 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Palest | +2.743 |
anon | +2.402 |
Bey | +2.323 |
ILLE | +2.201 |
audi | +2.126 |
Neg logit contributions | |
イト | -2.767 |
ー� | -2.652 |
ゴン | -2.640 |
checks | -2.597 |
plet | -2.573 |
Token | edit |
Token ID | 4370 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
イト | +0.112 |
ー� | +0.109 |
checks | +0.108 |
roup | +0.107 |
ゴン | +0.107 |
Neg logit contributions | |
Palest | -0.118 |
anon | -0.102 |
Bey | -0.101 |
ILLE | -0.096 |
audi | -0.092 |
Token | ] |
Token ID | 2361 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
ー� | +3.708 |
roup | +3.569 |
safety | +3.503 |
zilla | +3.462 |
checks | +3.437 |
Neg logit contributions | |
Palest | -13.349 |
Bey | -11.349 |
ILLE | -11.272 |
anon | -10.897 |
audi | -10.825 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
イト | +1.933 |
ー� | +1.922 |
roup | +1.897 |
checks | +1.881 |
safety | +1.866 |
Neg logit contributions | |
Palest | -2.468 |
Bey | -2.058 |
anon | -2.051 |
ILLE | -2.001 |
audi | -1.918 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
イト | +0.811 |
ー� | +0.804 |
checks | +0.791 |
roup | +0.783 |
safety | +0.777 |
Neg logit contributions | |
Palest | -0.991 |
anon | -0.826 |
Bey | -0.818 |
ILLE | -0.793 |
audi | -0.765 |
Token | The |
Token ID | 464 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
イト | +0.829 |
ー� | +0.806 |
ゴン | +0.791 |
roup | +0.789 |
checks | +0.788 |
Neg logit contributions | |
Palest | -0.892 |
anon | -0.771 |
Bey | -0.752 |
ILLE | -0.722 |
audi | -0.697 |
Token | most |
Token ID | 749 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
イト | +0.653 |
ー� | +0.636 |
ゴン | +0.623 |
roup | +0.623 |
checks | +0.622 |
Neg logit contributions | |
Palest | -0.596 |
anon | -0.521 |
Bey | -0.509 |
ILLE | -0.483 |
audi | -0.464 |
Token | uck |
Token ID | 1347 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
Palest | +0.691 |
anon | +0.611 |
Bey | +0.599 |
ILLE | +0.568 |
audi | +0.550 |
Neg logit contributions | |
イト | -0.617 |
ー� | -0.596 |
ゴン | -0.588 |
checks | -0.581 |
roup | -0.578 |
Token | ley |
Token ID | 1636 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Palest | +0.629 |
anon | +0.541 |
Bey | +0.530 |
ILLE | +0.501 |
audi | +0.480 |
Neg logit contributions | |
イト | -0.728 |
ー� | -0.706 |
ゴン | -0.697 |
checks | -0.694 |
roup | -0.693 |
Token | NBA |
Token ID | 32470 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Palest | +0.508 |
anon | +0.442 |
Bey | +0.434 |
ILLE | +0.410 |
audi | +0.394 |
Neg logit contributions | |
イト | -0.538 |
ー� | -0.522 |
ゴン | -0.515 |
checks | -0.510 |
roup | -0.510 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
Palest | +0.078 |
anon | +0.069 |
Bey | +0.067 |
ILLE | +0.064 |
audi | +0.062 |
Neg logit contributions | |
イト | -0.070 |
ー� | -0.067 |
ゴン | -0.067 |
checks | -0.066 |
roup | -0.066 |
Token | Ted |
Token ID | 38972 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
イト | +0.583 |
ー� | +0.567 |
checks | +0.559 |
ゴン | +0.556 |
roup | +0.554 |
Neg logit contributions | |
Palest | -0.579 |
anon | -0.493 |
Bey | -0.483 |
ILLE | -0.459 |
audi | -0.443 |
Token | Nug |
Token ID | 45777 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
イト | +1.570 |
ー� | +1.516 |
roup | +1.472 |
checks | +1.469 |
safety | +1.468 |
Neg logit contributions | |
Palest | -2.231 |
anon | -1.985 |
Bey | -1.950 |
ILLE | -1.876 |
audi | -1.822 |
Token | ent |
Token ID | 298 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
zilla | +5.897 |
checks | +5.852 |
ー� | +5.789 |
roup | +5.779 |
safety | +5.487 |
Neg logit contributions | |
Palest | -11.076 |
Bey | -9.523 |
ILLE | -9.378 |
anon | -8.952 |
oire | -8.845 |
Token | promised |
Token ID | 8072 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
イト | +1.989 |
ー� | +1.942 |
ゴン | +1.901 |
checks | +1.897 |
safety | +1.877 |
Neg logit contributions | |
Palest | -2.337 |
anon | -2.046 |
Bey | -2.026 |
ILLE | -1.921 |
audi | -1.877 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
Palest | +0.146 |
anon | +0.129 |
Bey | +0.126 |
ILLE | +0.120 |
audi | +0.116 |
Neg logit contributions | |
イト | -0.124 |
ー� | -0.120 |
ゴン | -0.118 |
checks | -0.117 |
roup | -0.117 |
Token | that |
Token ID | 326 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
イト | +4.042 |
safety | +4.008 |
checks | +3.905 |
ー� | +3.864 |
zilla | +3.801 |
Neg logit contributions | |
Palest | -6.216 |
anon | -5.650 |
Bey | -5.502 |
ILLE | -5.317 |
audi | -5.179 |
Token | he |
Token ID | 339 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
イト | +0.292 |
ー� | +0.282 |
ゴン | +0.277 |
checks | +0.276 |
roup | +0.275 |
Neg logit contributions | |
Palest | -0.366 |
anon | -0.325 |
Bey | -0.319 |
ILLE | -0.304 |
audi | -0.295 |
Token | for |
Token ID | 329 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
Palest | +1.935 |
anon | +1.681 |
Bey | +1.653 |
ILLE | +1.556 |
audi | +1.502 |
Neg logit contributions | |
イト | -1.994 |
ー� | -1.912 |
ゴン | -1.892 |
checks | -1.868 |
roup | -1.859 |
Token | war |
Token ID | 1175 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
Palest | +3.395 |
anon | +2.954 |
Bey | +2.909 |
ILLE | +2.774 |
oire | +2.642 |
Neg logit contributions | |
イト | -2.938 |
ゴン | -2.772 |
ー� | -2.760 |
checks | -2.684 |
roup | -2.673 |
Token | with |
Token ID | 351 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Palest | +3.004 |
anon | +2.595 |
Bey | +2.539 |
ILLE | +2.410 |
oire | +2.335 |
Neg logit contributions | |
イト | -3.131 |
ー� | -3.017 |
ゴン | -2.978 |
checks | -2.931 |
roup | -2.930 |
Token | Germany |
Token ID | 4486 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
Palest | +1.488 |
anon | +1.277 |
Bey | +1.247 |
ILLE | +1.177 |
audi | +1.132 |
Neg logit contributions | |
イト | -1.637 |
ー� | -1.570 |
ゴン | -1.567 |
checks | -1.538 |
roup | -1.532 |
Token | [ |
Token ID | 685 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
イト | +0.549 |
ー� | +0.531 |
ゴン | +0.523 |
checks | +0.521 |
roup | +0.521 |
Neg logit contributions | |
Palest | -0.607 |
anon | -0.533 |
Bey | -0.527 |
ILLE | -0.500 |
audi | -0.480 |
Token | edit |
Token ID | 4370 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
イト | +0.312 |
ー� | +0.305 |
checks | +0.301 |
roup | +0.299 |
safety | +0.296 |
Neg logit contributions | |
Palest | -0.341 |
anon | -0.292 |
Bey | -0.289 |
ILLE | -0.275 |
audi | -0.264 |
Token | ] |
Token ID | 2361 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
ー� | +3.897 |
roup | +3.765 |
safety | +3.763 |
zilla | +3.680 |
checks | +3.673 |
Neg logit contributions | |
Palest | -12.244 |
Bey | -10.593 |
ILLE | -10.357 |
anon | -10.192 |
audi | -10.017 |
Token |
|
Token ID | 198 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
イト | +2.095 |
ー� | +2.089 |
roup | +2.045 |
checks | +2.038 |
safety | +2.018 |
Neg logit contributions | |
Palest | -2.699 |
Bey | -2.254 |
anon | -2.251 |
ILLE | -2.196 |
audi | -2.120 |
Token |
|
Token ID | 198 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
イト | +0.575 |
ー� | +0.567 |
checks | +0.557 |
roup | +0.552 |
safety | +0.548 |
Neg logit contributions | |
Palest | -0.670 |
anon | -0.564 |
Bey | -0.558 |
ILLE | -0.538 |
audi | -0.519 |
Token | From |
Token ID | 4863 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
イト | +0.343 |
ー� | +0.333 |
ゴン | +0.328 |
checks | +0.327 |
roup | +0.326 |
Neg logit contributions | |
Palest | -0.346 |
anon | -0.299 |
Bey | -0.293 |
ILLE | -0.279 |
audi | -0.269 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
イト | +0.289 |
ー� | +0.278 |
ゴン | +0.274 |
checks | +0.271 |
roup | +0.271 |
Neg logit contributions | |
Palest | -0.371 |
anon | -0.329 |
Bey | -0.324 |
ILLE | -0.309 |
audi | -0.299 |
Token | : |
Token ID | 25 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Palest | +5.791 |
anon | +4.910 |
Bey | +4.829 |
ILLE | +4.581 |
heid | +4.410 |
Neg logit contributions | |
イト | -6.169 |
ー� | -5.969 |
plet | -5.925 |
ゴン | -5.856 |
warts | -5.760 |
Token | 1961 |
Token ID | 20510 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
Palest | +0.207 |
anon | +0.182 |
Bey | +0.179 |
ILLE | +0.170 |
audi | +0.164 |
Neg logit contributions | |
イト | -0.193 |
ー� | -0.186 |
ゴン | -0.184 |
checks | -0.183 |
roup | -0.183 |
Token | – |
Token ID | 1906 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Palest | +0.304 |
anon | +0.267 |
Bey | +0.263 |
ILLE | +0.249 |
audi | +0.241 |
Neg logit contributions | |
イト | -0.295 |
ー� | -0.286 |
ゴン | -0.283 |
roup | -0.282 |
checks | -0.281 |
Token | 1963 |
Token ID | 45192 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
Palest | +1.633 |
anon | +1.432 |
Bey | +1.407 |
ILLE | +1.318 |
audi | +1.263 |
Neg logit contributions | |
イト | -1.742 |
ー� | -1.679 |
ゴン | -1.674 |
checks | -1.650 |
roup | -1.650 |
Token | [ |
Token ID | 685 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
イト | +0.359 |
ー� | +0.347 |
roup | +0.344 |
ゴン | +0.343 |
checks | +0.341 |
Neg logit contributions | |
Palest | -0.375 |
anon | -0.331 |
Bey | -0.326 |
ILLE | -0.308 |
audi | -0.300 |
Token | edit |
Token ID | 4370 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
Palest | +0.373 |
anon | +0.323 |
Bey | +0.318 |
ILLE | +0.301 |
audi | +0.291 |
Neg logit contributions | |
イト | -0.369 |
ー� | -0.359 |
checks | -0.353 |
ゴン | -0.353 |
roup | -0.351 |
Token | ] |
Token ID | 2361 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
ー� | +3.696 |
roup | +3.516 |
safety | +3.496 |
イト | +3.471 |
zilla | +3.425 |
Neg logit contributions | |
Palest | -12.271 |
Bey | -10.581 |
ILLE | -10.402 |
anon | -10.256 |
interrupted | -10.007 |
Token |
|
Token ID | 198 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
イト | +1.749 |
ー� | +1.740 |
roup | +1.703 |
checks | +1.691 |
safety | +1.676 |
Neg logit contributions | |
Palest | -2.168 |
anon | -1.836 |
Bey | -1.819 |
ILLE | -1.759 |
audi | -1.712 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
イト | +0.146 |
ー� | +0.143 |
checks | +0.141 |
roup | +0.140 |
safety | +0.139 |
Neg logit contributions | |
Palest | -0.164 |
anon | -0.139 |
Bey | -0.137 |
ILLE | -0.131 |
audi | -0.127 |
Token | Ren |
Token ID | 26764 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
イト | +0.078 |
ー� | +0.075 |
ゴン | +0.074 |
roup | +0.074 |
checks | +0.074 |
Neg logit contributions | |
Palest | -0.072 |
anon | -0.062 |
Bey | -0.061 |
ILLE | -0.058 |
audi | -0.056 |
Token | ison |
Token ID | 1653 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
イト | +0.771 |
ー� | +0.750 |
roup | +0.741 |
ゴン | +0.736 |
checks | +0.734 |
Neg logit contributions | |
Palest | -0.821 |
anon | -0.719 |
Bey | -0.706 |
ILLE | -0.674 |
audi | -0.641 |
Token |
|
Token ID | 198 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
イト | +0.821 |
ー� | +0.800 |
checks | +0.787 |
ゴン | +0.783 |
roup | +0.782 |
Neg logit contributions | |
Palest | -0.895 |
anon | -0.787 |
Bey | -0.777 |
ILLE | -0.734 |
audi | -0.713 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
イト | +0.280 |
ー� | +0.276 |
checks | +0.272 |
roup | +0.269 |
safety | +0.268 |
Neg logit contributions | |
Palest | -0.326 |
anon | -0.274 |
Bey | -0.271 |
ILLE | -0.261 |
audi | -0.252 |
Token | F |
Token ID | 37 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
Palest | +0.080 |
anon | +0.069 |
Bey | +0.068 |
ILLE | +0.064 |
audi | +0.062 |
Neg logit contributions | |
イト | -0.084 |
ー� | -0.082 |
ゴン | -0.081 |
checks | -0.080 |
roup | -0.080 |
Token | acts |
Token ID | 8656 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Palest | +0.068 |
anon | +0.060 |
Bey | +0.059 |
ILLE | +0.056 |
audi | +0.055 |
Neg logit contributions | |
イト | -0.055 |
ー� | -0.053 |
ゴン | -0.052 |
checks | -0.052 |
roup | -0.052 |
Token | [ |
Token ID | 685 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
Palest | +1.399 |
anon | +1.229 |
Bey | +1.201 |
ILLE | +1.140 |
audi | +1.097 |
Neg logit contributions | |
イト | -1.363 |
ー� | -1.310 |
ゴン | -1.296 |
checks | -1.282 |
roup | -1.279 |
Token | edit |
Token ID | 4370 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
Palest | +2.040 |
anon | +1.788 |
Bey | +1.750 |
ILLE | +1.655 |
audi | +1.591 |
Neg logit contributions | |
イト | -2.151 |
ー� | -2.071 |
ゴン | -2.050 |
roup | -2.029 |
checks | -2.026 |
Token | ] |
Token ID | 2361 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
ー� | +3.696 |
イト | +3.583 |
roup | +3.570 |
safety | +3.567 |
checks | +3.502 |
Neg logit contributions | |
Palest | -12.128 |
Bey | -10.628 |
ILLE | -10.368 |
anon | -10.327 |
audi | -10.006 |
Token |
|
Token ID | 198 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
イト | +1.945 |
ー� | +1.923 |
roup | +1.888 |
checks | +1.883 |
safety | +1.861 |
Neg logit contributions | |
Palest | -2.441 |
Bey | -2.069 |
anon | -2.068 |
ILLE | -1.997 |
audi | -1.925 |
Token |
|
Token ID | 198 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
イト | +0.040 |
ー� | +0.039 |
checks | +0.039 |
roup | +0.038 |
safety | +0.038 |
Neg logit contributions | |
Palest | -0.045 |
anon | -0.038 |
Bey | -0.038 |
ILLE | -0.036 |
audi | -0.035 |
Token | At |
Token ID | 2953 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
Palest | +0.233 |
anon | +0.204 |
Bey | +0.201 |
ILLE | +0.190 |
audi | +0.183 |
Neg logit contributions | |
イト | -0.223 |
ー� | -0.215 |
ゴン | -0.212 |
checks | -0.211 |
roup | -0.211 |
Token | the |
Token ID | 262 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
イト | +1.437 |
ー� | +1.392 |
safety | +1.364 |
checks | +1.357 |
roup | +1.351 |
Neg logit contributions | |
Palest | -2.281 |
anon | -2.033 |
Bey | -2.022 |
ILLE | -1.939 |
audi | -1.884 |
Token | ma |
Token ID | 2611 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
イト | +3.169 |
ー� | +3.097 |
roup | +3.045 |
ゴン | +3.013 |
checks | +3.011 |
Neg logit contributions | |
Palest | -3.341 |
Bey | -2.869 |
anon | -2.865 |
ILLE | -2.726 |
audi | -2.615 |
Token | in |
Token ID | 287 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Palest | +1.073 |
anon | +0.953 |
Bey | +0.932 |
ILLE | +0.888 |
audi | +0.858 |
Neg logit contributions | |
イト | -0.903 |
ー� | -0.866 |
ゴン | -0.855 |
checks | -0.853 |
roup | -0.847 |
Token | Finnish |
Token ID | 26838 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Palest | +0.076 |
anon | +0.064 |
Bey | +0.063 |
ILLE | +0.058 |
audi | +0.055 |
Neg logit contributions | |
イト | -0.111 |
ー� | -0.108 |
ゴン | -0.107 |
checks | -0.106 |
roup | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
イト | +1.228 |
ー� | +1.178 |
ゴン | +1.157 |
checks | +1.144 |
roup | +1.142 |
Neg logit contributions | |
Palest | -1.907 |
anon | -1.709 |
Bey | -1.684 |
ILLE | -1.613 |
audi | -1.567 |
Token | M |
Token ID | 337 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
イト | +1.497 |
ー� | +1.453 |
ゴン | +1.426 |
checks | +1.408 |
safety | +1.407 |
Neg logit contributions | |
Palest | -1.636 |
anon | -1.450 |
Bey | -1.423 |
ILLE | -1.357 |
audi | -1.311 |
Token | umin |
Token ID | 7230 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
イト | +1.014 |
ー� | +0.976 |
ゴン | +0.962 |
roup | +0.958 |
checks | +0.956 |
Neg logit contributions | |
Palest | -1.271 |
anon | -1.122 |
Bey | -1.105 |
ILLE | -1.051 |
audi | -1.015 |
Token | v |
Token ID | 85 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
イト | +7.789 |
ー� | +7.574 |
roup | +7.518 |
zilla | +7.464 |
ゴン | +7.442 |
Neg logit contributions | |
Palest | -7.646 |
Bey | -6.558 |
anon | -6.291 |
ILLE | -5.984 |
audi | -5.650 |
Token | ä |
Token ID | 11033 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Palest | +0.076 |
anon | +0.066 |
Bey | +0.065 |
ILLE | +0.062 |
audi | +0.060 |
Neg logit contributions | |
イト | -0.072 |
ー� | -0.069 |
ゴン | -0.068 |
checks | -0.068 |
roup | -0.068 |
Token | r |
Token ID | 81 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
イト | +2.035 |
ー� | +1.978 |
roup | +1.933 |
ゴン | +1.931 |
checks | +1.925 |
Neg logit contributions | |
Palest | -2.219 |
anon | -1.930 |
Bey | -1.912 |
ILLE | -1.806 |
audi | -1.742 |
Token | ld |
Token ID | 335 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
イト | +1.180 |
ー� | +1.143 |
ゴン | +1.122 |
checks | +1.116 |
roup | +1.116 |
Neg logit contributions | |
Palest | -1.354 |
anon | -1.185 |
Bey | -1.171 |
ILLE | -1.108 |
audi | -1.070 |
Token | en |
Token ID | 268 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
Palest | +0.631 |
anon | +0.555 |
Bey | +0.543 |
ILLE | +0.514 |
audi | +0.497 |
Neg logit contributions | |
イト | -0.616 |
ー� | -0.595 |
ゴン | -0.588 |
checks | -0.583 |
roup | -0.580 |
Token | at |
Token ID | 379 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Palest | +0.272 |
anon | +0.241 |
Bey | +0.236 |
ILLE | +0.225 |
audi | +0.217 |
Neg logit contributions | |
イト | -0.232 |
ー� | -0.224 |
ゴン | -0.220 |
checks | -0.219 |
roup | -0.219 |
Token | home |
Token ID | 1363 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
イト | +0.976 |
ー� | +0.933 |
ゴン | +0.914 |
checks | +0.907 |
roup | +0.906 |
Neg logit contributions | |
Palest | -1.674 |
anon | -1.507 |
Bey | -1.486 |
ILLE | -1.425 |
audi | -1.386 |
Token | than |
Token ID | 621 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Palest | +1.167 |
anon | +1.026 |
Bey | +1.008 |
ILLE | +0.961 |
audi | +0.925 |
Neg logit contributions | |
イト | -0.999 |
ー� | -0.965 |
ゴン | -0.961 |
roup | -0.941 |
checks | -0.940 |
Token | most |
Token ID | 749 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
イト | +1.073 |
ー� | +1.031 |
safety | +1.027 |
roup | +1.015 |
checks | +1.011 |
Neg logit contributions | |
Palest | -1.661 |
anon | -1.486 |
Bey | -1.476 |
ILLE | -1.414 |
audi | -1.377 |
Token | other |
Token ID | 584 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Palest | +0.404 |
anon | +0.359 |
Bey | +0.353 |
ILLE | +0.337 |
audi | +0.326 |
Neg logit contributions | |
イト | -0.309 |
ー� | -0.297 |
ゴン | -0.293 |
checks | -0.290 |
roup | -0.290 |
Token | nut |
Token ID | 6701 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
イト | +1.899 |
safety | +1.870 |
ー� | +1.826 |
checks | +1.803 |
roup | +1.795 |
Neg logit contributions | |
Palest | -3.054 |
anon | -2.750 |
Bey | -2.685 |
ILLE | -2.610 |
audi | -2.554 |
Token | fl |
Token ID | 781 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
safety | +6.644 |
ritional | +6.606 |
イト | +6.595 |
warts | +6.502 |
ties | +6.449 |
Neg logit contributions | |
Palest | -8.708 |
anon | -7.484 |
ILLE | -7.447 |
Bey | -7.430 |
audi | -7.272 |
Token | ours |
Token ID | 4662 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
イト | +0.607 |
checks | +0.582 |
roup | +0.582 |
warts | +0.574 |
ー� | +0.573 |
Neg logit contributions | |
Palest | -1.199 |
Bey | -1.046 |
anon | -1.031 |
ILLE | -1.023 |
audi | -0.966 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
Palest | +0.266 |
anon | +0.236 |
Bey | +0.232 |
ILLE | +0.220 |
audi | +0.213 |
Neg logit contributions | |
イト | -0.217 |
ー� | -0.209 |
ゴン | -0.207 |
checks | -0.204 |
roup | -0.204 |
Token |
|
Token ID | 198 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
イト | +0.001 |
ー� | +0.001 |
ゴン | +0.001 |
checks | +0.001 |
roup | +0.001 |
Neg logit contributions | |
Palest | -0.001 |
anon | -0.001 |
Bey | -0.001 |
ILLE | -0.001 |
audi | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Palest | +0.066 |
anon | +0.056 |
Bey | +0.056 |
ILLE | +0.053 |
audi | +0.052 |
Neg logit contributions | |
イト | -0.060 |
ー� | -0.059 |
checks | -0.058 |
roup | -0.057 |
safety | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Palest | +0.196 |
anon | +0.167 |
Bey | +0.164 |
ILLE | +0.156 |
audi | +0.152 |
Neg logit contributions | |
イト | -0.185 |
ー� | -0.181 |
checks | -0.177 |
roup | -0.175 |
ゴン | -0.174 |
Token | 2011 |
Token ID | 9804 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Palest | +0.097 |
anon | +0.084 |
Bey | +0.083 |
ILLE | +0.078 |
audi | +0.076 |
Neg logit contributions | |
イト | -0.094 |
ー� | -0.091 |
ゴン | -0.090 |
checks | -0.090 |
roup | -0.089 |
Token | polymer |
Token ID | 30528 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Palest | +0.321 |
anon | +0.282 |
Bey | +0.277 |
ILLE | +0.263 |
audi | +0.254 |
Neg logit contributions | |
イト | -0.286 |
ー� | -0.276 |
ゴン | -0.272 |
checks | -0.270 |
roup | -0.269 |
Token | series |
Token ID | 2168 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Palest | +0.981 |
anon | +0.878 |
Bey | +0.863 |
ILLE | +0.825 |
audi | +0.801 |
Neg logit contributions | |
イト | -0.673 |
ー� | -0.645 |
ゴン | -0.635 |
checks | -0.629 |
roup | -0.628 |
Token | [ |
Token ID | 685 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
イト | +0.152 |
ー� | +0.147 |
ゴン | +0.144 |
checks | +0.144 |
roup | +0.143 |
Neg logit contributions | |
Palest | -0.178 |
anon | -0.157 |
Bey | -0.155 |
ILLE | -0.147 |
audi | -0.142 |
Token | edit |
Token ID | 4370 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
Palest | +0.543 |
anon | +0.469 |
Bey | +0.462 |
ILLE | +0.438 |
audi | +0.420 |
Neg logit contributions | |
イト | -0.536 |
ー� | -0.520 |
checks | -0.512 |
ゴン | -0.509 |
roup | -0.509 |
Token | ] |
Token ID | 2361 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
ー� | +3.849 |
safety | +3.643 |
roup | +3.643 |
イト | +3.642 |
zilla | +3.603 |
Neg logit contributions | |
Palest | -12.214 |
Bey | -10.462 |
ILLE | -10.347 |
anon | -10.136 |
audi | -9.793 |
Token |
|
Token ID | 198 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
イト | +2.217 |
ー� | +2.202 |
roup | +2.152 |
checks | +2.131 |
safety | +2.121 |
Neg logit contributions | |
Palest | -2.789 |
Bey | -2.330 |
anon | -2.322 |
ILLE | -2.268 |
audi | -2.156 |
Token |
|
Token ID | 198 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
イト | +0.601 |
ー� | +0.594 |
checks | +0.585 |
roup | +0.578 |
safety | +0.575 |
Neg logit contributions | |
Palest | -0.721 |
anon | -0.602 |
Bey | -0.596 |
ILLE | -0.577 |
audi | -0.555 |
Token | $ |
Token ID | 3 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
イト | +0.509 |
ー� | +0.495 |
ゴン | +0.486 |
checks | +0.485 |
roup | +0.484 |
Neg logit contributions | |
Palest | -0.531 |
anon | -0.458 |
Bey | -0.449 |
ILLE | -0.428 |
audi | -0.411 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Palest | +2.633 |
anon | +2.321 |
Bey | +2.245 |
ILLE | +2.117 |
audi | +2.046 |
Neg logit contributions | |
イト | -2.798 |
ゴン | -2.693 |
ー� | -2.692 |
roup | -2.642 |
checks | -2.639 |
Token | road |
Token ID | 2975 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
イト | +0.152 |
ー� | +0.146 |
ゴン | +0.143 |
checks | +0.143 |
roup | +0.142 |
Neg logit contributions | |
Palest | -0.224 |
anon | -0.201 |
Bey | -0.198 |
ILLE | -0.189 |
audi | -0.183 |
Token | to |
Token ID | 284 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
Palest | +0.948 |
anon | +0.831 |
Bey | +0.814 |
ILLE | +0.771 |
audi | +0.747 |
Neg logit contributions | |
イト | -0.894 |
ゴン | -0.864 |
ー� | -0.858 |
roup | -0.843 |
checks | -0.839 |
Token | the |
Token ID | 262 |
Feature activation | +4.76e-03 |
Pos logit contributions | |
イト | +0.056 |
ー� | +0.054 |
ゴン | +0.053 |
checks | +0.053 |
roup | +0.053 |
Neg logit contributions | |
Palest | -0.078 |
anon | -0.070 |
Bey | -0.069 |
ILLE | -0.066 |
audi | -0.064 |
Token | North |
Token ID | 2258 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
イト | +0.003 |
ー� | +0.003 |
ゴン | +0.003 |
checks | +0.003 |
roup | +0.003 |
Neg logit contributions | |
Palest | -0.004 |
anon | -0.004 |
Bey | -0.003 |
ILLE | -0.003 |
audi | -0.003 |
Token | American |
Token ID | 1605 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
イト | +2.256 |
checks | +2.198 |
ー� | +2.194 |
safety | +2.173 |
roup | +2.153 |
Neg logit contributions | |
Palest | -2.235 |
anon | -1.970 |
Bey | -1.964 |
ILLE | -1.857 |
audi | -1.765 |
Token | Bear |
Token ID | 14732 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
イト | +0.544 |
ー� | +0.530 |
safety | +0.521 |
checks | +0.516 |
roup | +0.514 |
Neg logit contributions | |
Palest | -0.761 |
anon | -0.681 |
Bey | -0.675 |
ILLE | -0.642 |
audi | -0.624 |
Token | Center |
Token ID | 3337 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
safety | +6.835 |
zilla | +6.792 |
イト | +6.737 |
ー� | +6.682 |
checks | +6.509 |
Neg logit contributions | |
Palest | -8.456 |
anon | -7.699 |
Bey | -7.606 |
ILLE | -7.199 |
audi | -7.151 |
Token | and |
Token ID | 290 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
Palest | +0.419 |
anon | +0.370 |
Bey | +0.363 |
ILLE | +0.345 |
audi | +0.333 |
Neg logit contributions | |
イト | -0.359 |
ー� | -0.345 |
ゴン | -0.341 |
checks | -0.338 |
roup | -0.338 |
Token | the |
Token ID | 262 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
Palest | +0.690 |
anon | +0.611 |
Bey | +0.599 |
ILLE | +0.571 |
audi | +0.552 |
Neg logit contributions | |
イト | -0.566 |
ー� | -0.545 |
ゴン | -0.539 |
checks | -0.531 |
roup | -0.530 |
Token | North |
Token ID | 2258 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Palest | +0.794 |
anon | +0.704 |
Bey | +0.692 |
ILLE | +0.660 |
audi | +0.638 |
Neg logit contributions | |
イト | -0.624 |
ー� | -0.600 |
ゴン | -0.592 |
checks | -0.585 |
roup | -0.585 |
Token | woods |
Token ID | 39493 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
イト | +2.367 |
checks | +2.322 |
ー� | +2.315 |
roup | +2.292 |
safety | +2.291 |
Neg logit contributions | |
Palest | -1.830 |
anon | -1.573 |
Bey | -1.563 |
ILLE | -1.455 |
audi | -1.378 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Palest | +0.831 |
anon | +0.715 |
Bey | +0.703 |
ILLE | +0.668 |
audi | +0.644 |
Neg logit contributions | |
イト | -0.817 |
ー� | -0.795 |
checks | -0.781 |
roup | -0.776 |
ゴン | -0.773 |
Token | Leg |
Token ID | 11484 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
Palest | +0.822 |
anon | +0.727 |
Bey | +0.714 |
ILLE | +0.677 |
audi | +0.651 |
Neg logit contributions | |
イト | -0.769 |
ー� | -0.742 |
ゴン | -0.734 |
roup | -0.726 |
checks | -0.725 |
Token | isl |
Token ID | 3044 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Palest | +3.914 |
anon | +3.482 |
Bey | +3.291 |
oire | +3.061 |
ILLE | +3.058 |
Neg logit contributions | |
イト | -4.638 |
ゴン | -4.466 |
ー� | -4.466 |
checks | -4.341 |
plet | -4.336 |
Token | ation |
Token ID | 341 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
イト | +0.309 |
ー� | +0.299 |
ゴン | +0.295 |
roup | +0.293 |
checks | +0.292 |
Neg logit contributions | |
Palest | -0.330 |
anon | -0.288 |
Bey | -0.285 |
ILLE | -0.270 |
audi | -0.260 |
Token | [ |
Token ID | 685 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Palest | +1.271 |
anon | +1.115 |
Bey | +1.088 |
ILLE | +1.032 |
audi | +0.992 |
Neg logit contributions | |
イト | -1.232 |
ー� | -1.189 |
ゴン | -1.171 |
roup | -1.159 |
checks | -1.158 |
Token | edit |
Token ID | 4370 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
Palest | +1.674 |
anon | +1.458 |
Bey | +1.430 |
ILLE | +1.350 |
audi | +1.299 |
Neg logit contributions | |
イト | -1.757 |
ー� | -1.700 |
ゴン | -1.679 |
checks | -1.666 |
roup | -1.664 |
Token | ] |
Token ID | 2361 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ー� | +3.455 |
roup | +3.383 |
safety | +3.370 |
zilla | +3.304 |
checks | +3.271 |
Neg logit contributions | |
Palest | -12.244 |
Bey | -10.586 |
ILLE | -10.485 |
anon | -10.195 |
audi | -10.055 |
Token |
|
Token ID | 198 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
イト | +1.674 |
ー� | +1.656 |
roup | +1.623 |
checks | +1.616 |
safety | +1.600 |
Neg logit contributions | |
Palest | -1.965 |
anon | -1.666 |
Bey | -1.659 |
ILLE | -1.599 |
audi | -1.542 |
Token |
|
Token ID | 198 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Palest | +0.571 |
anon | +0.490 |
Bey | +0.483 |
ILLE | +0.460 |
audi | +0.443 |
Neg logit contributions | |
イト | -0.551 |
ー� | -0.538 |
checks | -0.528 |
roup | -0.526 |
ゴン | -0.520 |
Token | On |
Token ID | 2202 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
Palest | +0.500 |
anon | +0.441 |
Bey | +0.434 |
ILLE | +0.410 |
audi | +0.394 |
Neg logit contributions | |
イト | -0.484 |
ー� | -0.467 |
ゴン | -0.461 |
roup | -0.456 |
checks | -0.456 |
Token | March |
Token ID | 2805 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
イト | +0.548 |
ー� | +0.527 |
ゴン | +0.518 |
checks | +0.514 |
roup | +0.513 |
Neg logit contributions | |
Palest | -0.779 |
anon | -0.695 |
Bey | -0.685 |
ILLE | -0.654 |
audi | -0.635 |
Token | – |
Token ID | 784 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Palest | +0.312 |
anon | +0.277 |
Bey | +0.273 |
ILLE | +0.260 |
audi | +0.252 |
Neg logit contributions | |
イト | -0.227 |
ー� | -0.218 |
ゴン | -0.216 |
roup | -0.212 |
checks | -0.212 |
Token | Jewish |
Token ID | 5582 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Palest | +1.418 |
anon | +1.255 |
Bey | +1.237 |
ILLE | +1.172 |
audi | +1.138 |
Neg logit contributions | |
イト | -1.099 |
ー� | -1.051 |
ゴン | -1.046 |
roup | -1.027 |
checks | -1.027 |
Token | , |
Token ID | 11 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
イト | +0.899 |
ー� | +0.870 |
checks | +0.852 |
roup | +0.850 |
safety | +0.849 |
Neg logit contributions | |
Palest | -1.013 |
anon | -0.898 |
Bey | -0.881 |
ILLE | -0.842 |
audi | -0.812 |
Token | Arab |
Token ID | 4498 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
イト | +0.023 |
ー� | +0.022 |
checks | +0.022 |
ゴン | +0.022 |
roup | +0.022 |
Neg logit contributions | |
Palest | -0.014 |
anon | -0.012 |
Bey | -0.012 |
ILLE | -0.011 |
audi | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Palest | +1.328 |
anon | +1.166 |
Bey | +1.145 |
ILLE | +1.084 |
audi | +1.046 |
Neg logit contributions | |
イト | -1.220 |
ー� | -1.177 |
ゴン | -1.165 |
checks | -1.153 |
roup | -1.149 |
Token | Dru |
Token ID | 21295 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
イト | +0.101 |
ー� | +0.098 |
safety | +0.096 |
checks | +0.096 |
roup | +0.096 |
Neg logit contributions | |
Palest | -0.089 |
anon | -0.077 |
Bey | -0.076 |
ILLE | -0.071 |
audi | -0.069 |
Token | ze |
Token ID | 2736 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
ー� | +4.806 |
plet | +4.553 |
zilla | +4.461 |
イト | +4.339 |
checks | +4.256 |
Neg logit contributions | |
Palest | -10.467 |
Bey | -9.433 |
ILLE | -9.265 |
anon | -9.007 |
Explan | -8.632 |
Token | – |
Token ID | 784 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
Palest | +0.645 |
anon | +0.564 |
Bey | +0.553 |
ILLE | +0.524 |
audi | +0.505 |
Neg logit contributions | |
イト | -0.623 |
ー� | -0.601 |
ゴン | -0.595 |
checks | -0.589 |
roup | -0.588 |
Token | who |
Token ID | 508 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
Palest | +2.649 |
anon | +2.340 |
Bey | +2.303 |
ILLE | +2.191 |
audi | +2.131 |
Neg logit contributions | |
イト | -1.838 |
ゴン | -1.761 |
ー� | -1.734 |
roup | -1.688 |
checks | -1.670 |
Token | came |
Token ID | 1625 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
イト | +0.268 |
ー� | +0.259 |
ゴン | +0.253 |
checks | +0.253 |
roup | +0.253 |
Neg logit contributions | |
Palest | -0.342 |
anon | -0.303 |
Bey | -0.299 |
ILLE | -0.285 |
audi | -0.275 |
Token | together |
Token ID | 1978 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Palest | +0.970 |
anon | +0.844 |
Bey | +0.827 |
ILLE | +0.781 |
audi | +0.756 |
Neg logit contributions | |
イト | -0.968 |
ー� | -0.934 |
ゴン | -0.927 |
checks | -0.915 |
roup | -0.914 |
Token | making |
Token ID | 1642 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
イト | +0.254 |
ー� | +0.244 |
ゴン | +0.241 |
checks | +0.238 |
roup | +0.238 |
Neg logit contributions | |
Palest | -0.348 |
anon | -0.310 |
Bey | -0.305 |
ILLE | -0.291 |
audi | -0.281 |
Token | plans |
Token ID | 3352 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
イト | +1.800 |
ー� | +1.722 |
checks | +1.713 |
safety | +1.695 |
roup | +1.687 |
Neg logit contributions | |
Palest | -2.685 |
anon | -2.391 |
Bey | -2.342 |
ILLE | -2.256 |
oire | -2.191 |
Token | for |
Token ID | 329 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
イト | +0.519 |
ー� | +0.502 |
ゴン | +0.494 |
checks | +0.492 |
roup | +0.490 |
Neg logit contributions | |
Palest | -0.564 |
anon | -0.496 |
Bey | -0.486 |
ILLE | -0.462 |
audi | -0.446 |
Token | their |
Token ID | 511 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Palest | +0.880 |
anon | +0.779 |
Bey | +0.771 |
ILLE | +0.732 |
audi | +0.702 |
Neg logit contributions | |
イト | -0.716 |
ー� | -0.686 |
ゴン | -0.684 |
roup | -0.672 |
checks | -0.665 |
Token | upcoming |
Token ID | 7865 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
イト | +1.442 |
ー� | +1.390 |
checks | +1.361 |
ゴン | +1.360 |
roup | +1.354 |
Neg logit contributions | |
Palest | -2.000 |
anon | -1.781 |
Bey | -1.746 |
ILLE | -1.669 |
audi | -1.622 |
Token | nu |
Token ID | 14364 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
イト | +2.513 |
ー� | +2.447 |
checks | +2.415 |
safety | +2.409 |
roup | +2.398 |
Neg logit contributions | |
Palest | -3.501 |
anon | -3.117 |
Bey | -3.030 |
ILLE | -2.911 |
audi | -2.831 |
Token | pt |
Token ID | 457 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
plet | +4.209 |
ー� | +4.176 |
checks | +4.083 |
イト | +4.031 |
ties | +3.830 |
Neg logit contributions | |
Palest | -11.226 |
anon | -10.009 |
Bey | -9.972 |
ILLE | -9.918 |
audi | -9.477 |
Token | ials |
Token ID | 8231 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
イト | +2.424 |
ー� | +2.360 |
checks | +2.325 |
roup | +2.321 |
ties | +2.280 |
Neg logit contributions | |
Palest | -3.562 |
anon | -3.157 |
Bey | -3.143 |
ILLE | -3.003 |
audi | -2.913 |
Token | , |
Token ID | 11 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
イト | +2.252 |
ー� | +2.163 |
checks | +2.152 |
ゴン | +2.130 |
safety | +2.117 |
Neg logit contributions | |
Palest | -3.084 |
anon | -2.740 |
Bey | -2.678 |
ILLE | -2.567 |
audi | -2.522 |
Token | but |
Token ID | 475 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
イト | +1.177 |
ー� | +1.136 |
checks | +1.121 |
safety | +1.112 |
ゴン | +1.110 |
Neg logit contributions | |
Palest | -1.404 |
anon | -1.241 |
Bey | -1.211 |
ILLE | -1.166 |
audi | -1.128 |
Token | there |
Token ID | 612 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
イト | +3.486 |
ー� | +3.364 |
safety | +3.354 |
checks | +3.345 |
zilla | +3.265 |
Neg logit contributions | |
Palest | -4.652 |
anon | -4.147 |
Bey | -4.036 |
ILLE | -3.906 |
audi | -3.795 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Palest | +0.596 |
anon | +0.509 |
Bey | +0.501 |
ILLE | +0.479 |
audi | +0.462 |
Neg logit contributions | |
イト | -0.563 |
ー� | -0.550 |
checks | -0.541 |
roup | -0.536 |
safety | -0.533 |
Token | The |
Token ID | 464 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Palest | +0.753 |
anon | +0.659 |
Bey | +0.647 |
ILLE | +0.612 |
audi | +0.589 |
Neg logit contributions | |
イト | -0.751 |
ー� | -0.726 |
ゴン | -0.717 |
checks | -0.712 |
roup | -0.711 |
Token | Two |
Token ID | 4930 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Palest | +0.320 |
anon | +0.282 |
Bey | +0.277 |
ILLE | +0.263 |
audi | +0.254 |
Neg logit contributions | |
イト | -0.282 |
ー� | -0.272 |
ゴン | -0.268 |
checks | -0.266 |
roup | -0.266 |
Token | Towers |
Token ID | 29031 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
Palest | +1.345 |
anon | +1.169 |
Bey | +1.145 |
ILLE | +1.080 |
audi | +1.038 |
Neg logit contributions | |
イト | -1.411 |
ー� | -1.364 |
ゴン | -1.348 |
checks | -1.338 |
roup | -1.333 |
Token | [ |
Token ID | 685 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Palest | +2.253 |
anon | +1.956 |
Bey | +1.908 |
ILLE | +1.804 |
audi | +1.735 |
Neg logit contributions | |
イト | -2.289 |
ー� | -2.211 |
ゴン | -2.183 |
checks | -2.166 |
roup | -2.145 |
Token | edit |
Token ID | 4370 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
Palest | +1.466 |
anon | +1.277 |
Bey | +1.252 |
ILLE | +1.182 |
audi | +1.137 |
Neg logit contributions | |
イト | -1.549 |
ー� | -1.498 |
ゴン | -1.481 |
checks | -1.468 |
roup | -1.466 |
Token | ] |
Token ID | 2361 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
ー� | +3.996 |
イト | +3.828 |
roup | +3.799 |
safety | +3.766 |
zilla | +3.752 |
Neg logit contributions | |
Palest | -11.803 |
Bey | -10.047 |
ILLE | -9.912 |
anon | -9.774 |
audi | -9.551 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
イト | +2.061 |
ー� | +2.051 |
roup | +2.008 |
checks | +1.991 |
safety | +1.979 |
Neg logit contributions | |
Palest | -2.662 |
anon | -2.217 |
Bey | -2.216 |
ILLE | -2.152 |
audi | -2.083 |
Token |
|
Token ID | 198 |
Feature activation | -8.52e-02 |
Pos logit contributions | |
イト | +0.095 |
ー� | +0.093 |
checks | +0.091 |
roup | +0.091 |
safety | +0.090 |
Neg logit contributions | |
Palest | -0.105 |
anon | -0.089 |
Bey | -0.088 |
ILLE | -0.084 |
audi | -0.081 |
Token | Or |
Token ID | 5574 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Palest | +0.065 |
anon | +0.056 |
Bey | +0.055 |
ILLE | +0.053 |
audi | +0.051 |
Neg logit contributions | |
イト | -0.061 |
ー� | -0.059 |
ゴン | -0.059 |
checks | -0.058 |
roup | -0.058 |
Token | cs |
Token ID | 6359 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Palest | +1.198 |
anon | +1.051 |
Bey | +1.026 |
ILLE | +0.966 |
audi | +0.938 |
Neg logit contributions | |
イト | -1.196 |
ー� | -1.150 |
ゴン | -1.140 |
roup | -1.125 |
checks | -1.124 |
Token | already |
Token ID | 1541 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Palest | +0.439 |
anon | +0.389 |
Bey | +0.383 |
ILLE | +0.364 |
audi | +0.352 |
Neg logit contributions | |
イト | -0.351 |
ー� | -0.339 |
ゴン | -0.332 |
checks | -0.331 |
roup | -0.331 |
Token | designed |
Token ID | 3562 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Palest | +1.111 |
anon | +0.984 |
Bey | +0.967 |
ILLE | +0.921 |
audi | +0.891 |
Neg logit contributions | |
イト | -0.900 |
ー� | -0.867 |
ゴン | -0.855 |
checks | -0.847 |
roup | -0.846 |
Token | and |
Token ID | 290 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
イト | +1.316 |
ー� | +1.278 |
checks | +1.255 |
ゴン | +1.252 |
roup | +1.250 |
Neg logit contributions | |
Palest | -1.350 |
anon | -1.183 |
Bey | -1.165 |
ILLE | -1.099 |
audi | -1.064 |
Token | create |
Token ID | 2251 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
イト | +0.141 |
ー� | +0.136 |
checks | +0.134 |
roup | +0.134 |
safety | +0.133 |
Neg logit contributions | |
Palest | -0.163 |
anon | -0.145 |
Bey | -0.143 |
ILLE | -0.135 |
audi | -0.131 |
Token | your |
Token ID | 534 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
イト | +1.451 |
ー� | +1.414 |
checks | +1.383 |
roup | +1.375 |
safety | +1.374 |
Neg logit contributions | |
Palest | -1.697 |
anon | -1.486 |
Bey | -1.483 |
ILLE | -1.398 |
audi | -1.350 |
Token | monster |
Token ID | 9234 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
Palest | +1.262 |
anon | +1.124 |
Bey | +1.097 |
ILLE | +1.054 |
audi | +1.017 |
Neg logit contributions | |
イト | -0.996 |
ー� | -0.953 |
ゴン | -0.950 |
roup | -0.930 |
checks | -0.930 |
Token | specifically |
Token ID | 5734 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
safety | +6.607 |
ー� | +6.525 |
zilla | +6.494 |
checks | +6.447 |
イト | +6.443 |
Neg logit contributions | |
Palest | -8.695 |
anon | -7.488 |
Bey | -7.414 |
ILLE | -7.158 |
audi | -7.008 |
Token | , |
Token ID | 11 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
イト | +3.377 |
ー� | +3.332 |
safety | +3.277 |
checks | +3.241 |
ties | +3.202 |
Neg logit contributions | |
Palest | -4.434 |
anon | -3.994 |
Bey | -3.910 |
ILLE | -3.685 |
audi | -3.588 |
Token | or |
Token ID | 393 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
イト | +1.801 |
ー� | +1.748 |
safety | +1.728 |
roup | +1.726 |
checks | +1.722 |
Neg logit contributions | |
Palest | -1.456 |
anon | -1.253 |
Bey | -1.230 |
ILLE | -1.149 |
audi | -1.097 |
Token | choose |
Token ID | 3853 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
イト | +1.054 |
ー� | +1.015 |
checks | +0.995 |
safety | +0.993 |
roup | +0.992 |
Neg logit contributions | |
Palest | -1.444 |
anon | -1.289 |
Bey | -1.275 |
ILLE | -1.212 |
audi | -1.173 |
Token | an |
Token ID | 281 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
イト | +2.261 |
ー� | +2.190 |
safety | +2.172 |
checks | +2.138 |
roup | +2.126 |
Neg logit contributions | |
Palest | -2.929 |
anon | -2.612 |
Bey | -2.610 |
ILLE | -2.453 |
audi | -2.369 |
Token | currently |
Token ID | 3058 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
Palest | +0.158 |
anon | +0.140 |
Bey | +0.137 |
ILLE | +0.130 |
audi | +0.126 |
Neg logit contributions | |
イト | -0.132 |
ー� | -0.127 |
ゴン | -0.125 |
roup | -0.123 |
checks | -0.123 |
Token | the |
Token ID | 262 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
イト | +1.514 |
ー� | +1.467 |
checks | +1.437 |
ゴン | +1.434 |
roup | +1.432 |
Neg logit contributions | |
Palest | -2.048 |
anon | -1.822 |
Bey | -1.797 |
ILLE | -1.712 |
audi | -1.662 |
Token | Stars |
Token ID | 10271 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
イト | +1.047 |
ー� | +1.015 |
checks | +0.993 |
safety | +0.987 |
roup | +0.987 |
Neg logit contributions | |
Palest | -1.639 |
anon | -1.471 |
Bey | -1.459 |
ILLE | -1.391 |
audi | -1.353 |
Token | � |
Token ID | 447 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
イト | +3.002 |
ー� | +2.952 |
safety | +2.923 |
checks | +2.919 |
roup | +2.907 |
Neg logit contributions | |
Palest | -2.059 |
anon | -1.721 |
Bey | -1.717 |
ILLE | -1.569 |
audi | -1.515 |
Token | � |
Token ID | 247 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
イト | +1.008 |
ー� | +0.984 |
ゴン | +0.953 |
roup | +0.953 |
safety | +0.942 |
Neg logit contributions | |
Palest | -2.008 |
anon | -1.789 |
Bey | -1.779 |
ILLE | -1.690 |
audi | -1.647 |
Token | general |
Token ID | 2276 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
イト | +1.219 |
ー� | +1.183 |
checks | +1.161 |
roup | +1.159 |
ゴン | +1.156 |
Neg logit contributions | |
Palest | -1.570 |
anon | -1.374 |
Bey | -1.369 |
ILLE | -1.297 |
audi | -1.253 |
Token | manager |
Token ID | 4706 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
safety | +2.285 |
rev | +1.848 |
ties | +1.621 |
roup | +1.584 |
roles | +1.578 |
Neg logit contributions | |
Palest | -13.696 |
ILLE | -12.236 |
Bey | -12.178 |
anon | -12.106 |
ł | -11.628 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
イト | +1.810 |
ー� | +1.746 |
checks | +1.715 |
ゴン | +1.715 |
roup | +1.711 |
Neg logit contributions | |
Palest | -2.285 |
anon | -2.013 |
Bey | -1.990 |
ILLE | -1.900 |
audi | -1.829 |
Token | The |
Token ID | 383 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
イト | +0.969 |
ー� | +0.939 |
ゴン | +0.926 |
checks | +0.918 |
roup | +0.917 |
Neg logit contributions | |
Palest | -1.005 |
anon | -0.878 |
Bey | -0.860 |
ILLE | -0.817 |
audi | -0.787 |
Token | Devils |
Token ID | 26199 |
Feature activation | +6.85e+00 |
Pos logit contributions | |
イト | +0.824 |
ー� | +0.793 |
ゴン | +0.777 |
checks | +0.773 |
roup | +0.771 |
Neg logit contributions | |
Palest | -1.253 |
anon | -1.121 |
Bey | -1.105 |
ILLE | -1.057 |
audi | -1.027 |
Token | re |
Token ID | 302 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
safety | +4.204 |
ー� | +4.176 |
イト | +4.162 |
roup | +4.102 |
checks | +4.074 |
Neg logit contributions | |
Palest | -5.589 |
Bey | -4.939 |
anon | -4.909 |
ILLE | -4.590 |
audi | -4.543 |
Token | believe |
Token ID | 1975 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
Palest | +1.395 |
anon | +1.240 |
Bey | +1.220 |
ILLE | +1.163 |
audi | +1.126 |
Neg logit contributions | |
イト | -1.062 |
ー� | -1.022 |
ゴン | -1.006 |
checks | -0.998 |
roup | -0.997 |
Token | the |
Token ID | 262 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
Palest | +1.995 |
anon | +1.749 |
Bey | +1.720 |
ILLE | +1.643 |
audi | +1.586 |
Neg logit contributions | |
イト | -1.712 |
ー� | -1.657 |
ゴン | -1.653 |
roup | -1.607 |
checks | -1.601 |
Token | unnamed |
Token ID | 23226 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
イト | +0.487 |
ー� | +0.471 |
checks | +0.462 |
safety | +0.460 |
roup | +0.460 |
Neg logit contributions | |
Palest | -0.597 |
anon | -0.529 |
Bey | -0.523 |
ILLE | -0.495 |
audi | -0.479 |
Token | sources |
Token ID | 4237 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
イト | +1.579 |
ー� | +1.528 |
safety | +1.516 |
checks | +1.510 |
roup | +1.496 |
Neg logit contributions | |
Palest | -2.162 |
anon | -1.927 |
Bey | -1.918 |
ILLE | -1.820 |
audi | -1.770 |
Token | from |
Token ID | 422 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
イト | +0.835 |
ー� | +0.808 |
checks | +0.795 |
safety | +0.791 |
roup | +0.787 |
Neg logit contributions | |
Palest | -1.089 |
anon | -0.968 |
Bey | -0.953 |
ILLE | -0.910 |
audi | -0.879 |
Token | Mur |
Token ID | 5921 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
Palest | +0.431 |
anon | +0.382 |
Bey | +0.376 |
ILLE | +0.358 |
audi | +0.346 |
Neg logit contributions | |
イト | -0.341 |
ー� | -0.328 |
ゴン | -0.323 |
checks | -0.320 |
roup | -0.320 |
Token | phys |
Token ID | 34411 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
roup | +7.223 |
イト | +7.223 |
zilla | +7.184 |
ー� | +7.168 |
checks | +7.143 |
Neg logit contributions | |
Palest | -7.732 |
Bey | -6.528 |
anon | -6.483 |
ILLE | -6.118 |
oire | -5.950 |
Token | Law |
Token ID | 3854 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
イト | +1.512 |
ー� | +1.461 |
checks | +1.449 |
roup | +1.441 |
safety | +1.437 |
Neg logit contributions | |
Palest | -1.784 |
anon | -1.578 |
Bey | -1.573 |
ILLE | -1.469 |
audi | -1.443 |
Token | blog |
Token ID | 4130 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Palest | +0.294 |
anon | +0.261 |
Bey | +0.256 |
ILLE | +0.244 |
audi | +0.236 |
Neg logit contributions | |
イト | -0.243 |
ー� | -0.234 |
ゴン | -0.230 |
checks | -0.229 |
roup | -0.229 |
Token | from |
Token ID | 422 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
イト | +0.930 |
ー� | +0.897 |
checks | +0.879 |
ゴン | +0.877 |
roup | +0.877 |
Neg logit contributions | |
Palest | -1.144 |
anon | -1.013 |
Bey | -1.000 |
ILLE | -0.948 |
audi | -0.920 |
Token | Boston |
Token ID | 6182 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Palest | +0.841 |
anon | +0.744 |
Bey | +0.731 |
ILLE | +0.697 |
audi | +0.673 |
Neg logit contributions | |
イト | -0.679 |
ー� | -0.654 |
ゴン | -0.646 |
checks | -0.638 |
roup | -0.638 |
Token |
|
Token ID | 198 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
イト | +0.136 |
ー� | +0.132 |
ゴン | +0.128 |
roup | +0.128 |
checks | +0.128 |
Neg logit contributions | |
Palest | -0.144 |
anon | -0.126 |
Bey | -0.124 |
ILLE | -0.118 |
audi | -0.114 |
Token |
|
Token ID | 198 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
イト | +0.064 |
ー� | +0.063 |
checks | +0.062 |
roup | +0.061 |
safety | +0.061 |
Neg logit contributions | |
Palest | -0.071 |
anon | -0.060 |
Bey | -0.059 |
ILLE | -0.057 |
audi | -0.055 |
Token | Part |
Token ID | 7841 |
Feature activation | -7.76e+00 |
Pos logit contributions | |
Palest | +0.045 |
anon | +0.039 |
Bey | +0.038 |
ILLE | +0.036 |
audi | +0.035 |
Neg logit contributions | |
イト | -0.045 |
ー� | -0.044 |
ゴン | -0.043 |
checks | -0.043 |
roup | -0.043 |
Token | 6 |
Token ID | 718 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
Palest | +5.321 |
anon | +4.831 |
Bey | +4.481 |
oire | +4.240 |
ILLE | +4.220 |
Neg logit contributions | |
イト | -5.836 |
ゴン | -5.658 |
ー� | -5.582 |
checks | -5.469 |
roup | -5.441 |
Token | [ |
Token ID | 685 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
イト | +0.486 |
ー� | +0.468 |
ゴン | +0.462 |
checks | +0.458 |
roup | +0.458 |
Neg logit contributions | |
Palest | -0.575 |
anon | -0.507 |
Bey | -0.500 |
ILLE | -0.475 |
audi | -0.460 |
Token | edit |
Token ID | 4370 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
Palest | +1.837 |
anon | +1.608 |
Bey | +1.566 |
ILLE | +1.478 |
audi | +1.413 |
Neg logit contributions | |
イト | -2.048 |
ー� | -1.972 |
ゴン | -1.960 |
checks | -1.940 |
roup | -1.934 |
Token | ] |
Token ID | 2361 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ー� | +4.295 |
イト | +4.263 |
roup | +4.254 |
safety | +4.161 |
checks | +4.095 |
Neg logit contributions | |
Palest | -11.069 |
Bey | -9.650 |
ILLE | -9.371 |
anon | -9.360 |
audi | -8.916 |
Token |
|
Token ID | 198 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
イト | +0.908 |
ー� | +0.890 |
roup | +0.873 |
checks | +0.866 |
safety | +0.861 |
Neg logit contributions | |
Palest | -1.013 |
anon | -0.859 |
Bey | -0.857 |
ILLE | -0.819 |
audi | -0.788 |
Token |
|
Token ID | 198 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
Palest | +0.406 |
anon | +0.345 |
Bey | +0.341 |
ILLE | +0.325 |
audi | +0.313 |
Neg logit contributions | |
イト | -0.382 |
ー� | -0.373 |
checks | -0.366 |
roup | -0.364 |
safety | -0.361 |
Token | It |
Token ID | 1026 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
Palest | +0.422 |
anon | +0.370 |
Bey | +0.363 |
ILLE | +0.343 |
audi | +0.330 |
Neg logit contributions | |
イト | -0.421 |
ー� | -0.407 |
ゴン | -0.402 |
checks | -0.399 |
roup | -0.398 |
Token | was |
Token ID | 373 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
イト | +0.270 |
ー� | +0.261 |
ゴン | +0.258 |
checks | +0.256 |
roup | +0.255 |
Neg logit contributions | |
Palest | -0.262 |
anon | -0.229 |
Bey | -0.224 |
ILLE | -0.212 |
audi | -0.204 |
Token | RS |
Token ID | 6998 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
Palest | +0.168 |
anon | +0.146 |
Bey | +0.143 |
ILLE | +0.135 |
audi | +0.131 |
Neg logit contributions | |
イト | -0.166 |
ー� | -0.161 |
ゴン | -0.158 |
checks | -0.158 |
roup | -0.158 |
Token | I |
Token ID | 40 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
Palest | +2.174 |
anon | +1.881 |
Bey | +1.839 |
ILLE | +1.730 |
audi | +1.661 |
Neg logit contributions | |
イト | -2.485 |
ー� | -2.402 |
ゴン | -2.370 |
checks | -2.354 |
roup | -2.346 |
Token | military |
Token ID | 2422 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Palest | +4.031 |
anon | +3.556 |
Bey | +3.466 |
ILLE | +3.332 |
audi | +3.180 |
Neg logit contributions | |
イト | -3.371 |
ー� | -3.199 |
ゴン | -3.187 |
checks | -3.122 |
plet | -3.109 |
Token | formations |
Token ID | 30648 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Palest | +1.647 |
anon | +1.469 |
Bey | +1.441 |
ILLE | +1.377 |
audi | +1.335 |
Neg logit contributions | |
イト | -1.212 |
ー� | -1.163 |
ゴン | -1.151 |
checks | -1.134 |
roup | -1.128 |
Token | [ |
Token ID | 685 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
Palest | +1.426 |
anon | +1.250 |
Bey | +1.222 |
ILLE | +1.159 |
audi | +1.118 |
Neg logit contributions | |
イト | -1.337 |
ー� | -1.287 |
ゴン | -1.281 |
checks | -1.260 |
roup | -1.251 |
Token | edit |
Token ID | 4370 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
Palest | +0.672 |
anon | +0.583 |
Bey | +0.574 |
ILLE | +0.544 |
audi | +0.524 |
Neg logit contributions | |
イト | -0.667 |
ー� | -0.648 |
checks | -0.636 |
roup | -0.635 |
ゴン | -0.635 |
Token | ] |
Token ID | 2361 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
ー� | +3.769 |
safety | +3.640 |
イト | +3.601 |
roup | +3.596 |
zilla | +3.541 |
Neg logit contributions | |
Palest | -11.582 |
Bey | -10.022 |
ILLE | -9.803 |
anon | -9.656 |
audi | -9.436 |
Token |
|
Token ID | 198 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
イト | +1.693 |
ー� | +1.684 |
roup | +1.655 |
checks | +1.635 |
zilla | +1.621 |
Neg logit contributions | |
Palest | -2.093 |
anon | -1.759 |
Bey | -1.758 |
ILLE | -1.691 |
audi | -1.640 |
Token |
|
Token ID | 198 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
イト | +0.053 |
ー� | +0.052 |
checks | +0.051 |
roup | +0.051 |
safety | +0.050 |
Neg logit contributions | |
Palest | -0.059 |
anon | -0.050 |
Bey | -0.050 |
ILLE | -0.048 |
audi | -0.046 |
Token | Women |
Token ID | 18495 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Palest | +0.052 |
anon | +0.045 |
Bey | +0.044 |
ILLE | +0.042 |
audi | +0.040 |
Neg logit contributions | |
イト | -0.050 |
ー� | -0.049 |
ゴン | -0.048 |
roup | -0.048 |
checks | -0.048 |
Token | volunteers |
Token ID | 11661 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
Palest | +1.183 |
anon | +1.048 |
Bey | +1.027 |
ILLE | +0.978 |
audi | +0.944 |
Neg logit contributions | |
イト | -0.991 |
ー� | -0.951 |
ゴン | -0.948 |
checks | -0.933 |
roup | -0.925 |
Token |
|
Token ID | 198 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
Palest | +0.376 |
anon | +0.319 |
Bey | +0.315 |
ILLE | +0.301 |
audi | +0.291 |
Neg logit contributions | |
イト | -0.342 |
ー� | -0.335 |
checks | -0.330 |
roup | -0.327 |
safety | -0.325 |
Token | H |
Token ID | 39 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Palest | +0.666 |
anon | +0.581 |
Bey | +0.569 |
ILLE | +0.538 |
audi | +0.518 |
Neg logit contributions | |
イト | -0.688 |
ー� | -0.666 |
ゴン | -0.657 |
checks | -0.652 |
roup | -0.652 |
Token | ousing |
Token ID | 12752 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
Palest | +0.183 |
anon | +0.154 |
Bey | +0.150 |
ILLE | +0.140 |
audi | +0.133 |
Neg logit contributions | |
イト | -0.272 |
ー� | -0.265 |
ゴン | -0.262 |
checks | -0.260 |
roup | -0.260 |
Token | and |
Token ID | 290 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
Palest | +2.264 |
anon | +1.993 |
Bey | +1.949 |
ILLE | +1.847 |
audi | +1.790 |
Neg logit contributions | |
イト | -1.987 |
ー� | -1.905 |
ゴン | -1.899 |
roup | -1.869 |
checks | -1.853 |
Token | the |
Token ID | 262 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
Palest | +2.121 |
anon | +1.869 |
Bey | +1.820 |
ILLE | +1.733 |
audi | +1.674 |
Neg logit contributions | |
イト | -1.825 |
ゴン | -1.742 |
ー� | -1.739 |
checks | -1.703 |
roup | -1.692 |
Token | Paradox |
Token ID | 37983 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
Palest | +1.958 |
anon | +1.720 |
Bey | +1.686 |
ILLE | +1.604 |
audi | +1.546 |
Neg logit contributions | |
イト | -1.762 |
ー� | -1.697 |
ゴン | -1.682 |
checks | -1.659 |
roup | -1.658 |
Token | of |
Token ID | 286 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Palest | +7.320 |
anon | +6.278 |
Bey | +5.965 |
Interpret | +5.769 |
audio | +5.634 |
Neg logit contributions | |
イト | -8.603 |
ゴン | -8.464 |
checks | -8.288 |
roup | -8.240 |
ー� | -8.208 |
Token | Credit |
Token ID | 10504 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Palest | +1.305 |
anon | +1.149 |
Bey | +1.127 |
ILLE | +1.070 |
audi | +1.033 |
Neg logit contributions | |
イト | -1.164 |
ー� | -1.122 |
ゴン | -1.109 |
checks | -1.098 |
roup | -1.096 |
Token | Bub |
Token ID | 19645 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
Palest | +0.909 |
anon | +0.797 |
Bey | +0.782 |
ILLE | +0.741 |
audi | +0.715 |
Neg logit contributions | |
イト | -0.864 |
ー� | -0.835 |
ゴン | -0.824 |
checks | -0.817 |
roup | -0.816 |
Token | bles |
Token ID | 7689 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
イト | +0.472 |
ー� | +0.460 |
checks | +0.455 |
roup | +0.451 |
ゴン | +0.449 |
Neg logit contributions | |
Palest | -0.414 |
anon | -0.354 |
Bey | -0.350 |
ILLE | -0.329 |
audi | -0.314 |
Token | , |
Token ID | 11 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Palest | +1.721 |
anon | +1.510 |
Bey | +1.465 |
ILLE | +1.391 |
audi | +1.338 |
Neg logit contributions | |
イト | -1.691 |
ー� | -1.632 |
ゴン | -1.617 |
roup | -1.595 |
checks | -1.593 |
Token | director |
Token ID | 3437 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Palest | +1.238 |
anon | +1.123 |
Bey | +1.108 |
ILLE | +1.066 |
audi | +1.040 |
Neg logit contributions | |
イト | -0.575 |
ー� | -0.545 |
ゴン | -0.534 |
checks | -0.528 |
roup | -0.526 |
Token | at |
Token ID | 379 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Palest | +1.222 |
anon | +1.069 |
Bey | +1.047 |
ILLE | +0.989 |
audi | +0.961 |
Neg logit contributions | |
イト | -1.175 |
ー� | -1.135 |
ゴン | -1.122 |
checks | -1.110 |
roup | -1.110 |
Token | Buck |
Token ID | 13452 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
Palest | +0.846 |
anon | +0.742 |
Bey | +0.729 |
ILLE | +0.691 |
audi | +0.666 |
Neg logit contributions | |
イト | -0.801 |
ー� | -0.774 |
ゴン | -0.763 |
checks | -0.758 |
roup | -0.757 |
Token | more |
Token ID | 3549 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
Palest | +2.036 |
anon | +1.807 |
Bey | +1.768 |
ILLE | +1.656 |
audi | +1.617 |
Neg logit contributions | |
イト | -1.893 |
ー� | -1.835 |
ゴン | -1.819 |
checks | -1.783 |
roup | -1.776 |
Token | Park |
Token ID | 3250 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Palest | +2.080 |
anon | +1.819 |
Bey | +1.780 |
ILLE | +1.693 |
audi | +1.635 |
Neg logit contributions | |
イト | -1.950 |
ー� | -1.893 |
ゴン | -1.878 |
checks | -1.847 |
roup | -1.839 |
Token | Kart |
Token ID | 32872 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
Palest | +1.491 |
anon | +1.311 |
Bey | +1.285 |
ILLE | +1.222 |
audi | +1.182 |
Neg logit contributions | |
イト | -1.343 |
ー� | -1.301 |
ゴン | -1.286 |
checks | -1.272 |
roup | -1.267 |
Token | Circuit |
Token ID | 13588 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
Palest | +6.551 |
anon | +5.640 |
Bey | +5.270 |
ILLE | +5.071 |
Interpret | +4.954 |
Neg logit contributions | |
ゴン | -8.798 |
イト | -8.708 |
ー� | -8.591 |
checks | -8.453 |
peror | -8.398 |
Token | , |
Token ID | 11 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
Palest | +3.463 |
anon | +3.050 |
Bey | +2.966 |
ILLE | +2.840 |
audi | +2.751 |
Neg logit contributions | |
イト | -3.127 |
ー� | -3.035 |
ゴン | -3.016 |
checks | -2.951 |
roup | -2.928 |
Token | where |
Token ID | 810 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
Palest | +2.173 |
anon | +1.918 |
Bey | +1.884 |
ILLE | +1.791 |
audi | +1.731 |
Neg logit contributions | |
イト | -1.866 |
ー� | -1.799 |
ゴン | -1.774 |
checks | -1.760 |
roup | -1.757 |
Token | Hamilton |
Token ID | 11582 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
Palest | +1.868 |
anon | +1.632 |
Bey | +1.611 |
ILLE | +1.530 |
audi | +1.474 |
Neg logit contributions | |
イト | -1.730 |
ー� | -1.663 |
ゴン | -1.655 |
checks | -1.623 |
roup | -1.621 |
Token | caught |
Token ID | 4978 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Palest | +0.561 |
anon | +0.497 |
Bey | +0.486 |
ILLE | +0.462 |
audi | +0.448 |
Neg logit contributions | |
イト | -0.484 |
ー� | -0.465 |
ゴン | -0.461 |
roup | -0.454 |
checks | -0.454 |
Token | common |
Token ID | 2219 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Palest | +0.511 |
anon | +0.452 |
Bey | +0.444 |
ILLE | +0.423 |
audi | +0.409 |
Neg logit contributions | |
イト | -0.424 |
ー� | -0.409 |
ゴン | -0.403 |
checks | -0.400 |
roup | -0.399 |
Token | response |
Token ID | 2882 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
イト | +0.687 |
ー� | +0.665 |
ゴン | +0.651 |
checks | +0.645 |
safety | +0.645 |
Neg logit contributions | |
Palest | -0.821 |
anon | -0.729 |
Bey | -0.720 |
ILLE | -0.684 |
audi | -0.662 |
Token | to |
Token ID | 284 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
ー� | +3.421 |
イト | +3.408 |
safety | +3.329 |
checks | +3.292 |
roup | +3.277 |
Neg logit contributions | |
Palest | -3.807 |
anon | -3.484 |
Bey | -3.394 |
ILLE | -3.263 |
audi | -3.092 |
Token | charges |
Token ID | 4530 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
イト | +0.678 |
ー� | +0.658 |
ゴン | +0.644 |
checks | +0.642 |
safety | +0.640 |
Neg logit contributions | |
Palest | -0.735 |
anon | -0.653 |
Bey | -0.641 |
ILLE | -0.609 |
audi | -0.588 |
Token | of |
Token ID | 286 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
Palest | +0.873 |
anon | +0.769 |
Bey | +0.755 |
ILLE | +0.717 |
audi | +0.693 |
Neg logit contributions | |
イト | -0.763 |
ー� | -0.736 |
ゴン | -0.726 |
checks | -0.720 |
roup | -0.719 |
Token | apartheid |
Token ID | 38264 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
Palest | +0.678 |
anon | +0.595 |
Bey | +0.585 |
ILLE | +0.555 |
audi | +0.535 |
Neg logit contributions | |
イト | -0.614 |
ー� | -0.592 |
ゴン | -0.585 |
checks | -0.580 |
roup | -0.579 |
Token | these |
Token ID | 777 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Palest | +7.943 |
anon | +6.542 |
Bey | +6.453 |
ł | +5.956 |
ILLE | +5.934 |
Neg logit contributions | |
イト | -7.866 |
ゴン | -7.636 |
peror | -7.449 |
ー� | -7.441 |
checks | -7.440 |
Token | days |
Token ID | 1528 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
イト | +0.475 |
ー� | +0.452 |
ゴン | +0.441 |
checks | +0.434 |
roup | +0.433 |
Neg logit contributions | |
Palest | -1.051 |
anon | -0.963 |
Bey | -0.948 |
ILLE | -0.915 |
audi | -0.890 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
イト | +1.877 |
ー� | +1.839 |
checks | +1.786 |
safety | +1.777 |
roup | +1.776 |
Neg logit contributions | |
Palest | -2.453 |
anon | -2.202 |
Bey | -2.177 |
ILLE | -2.079 |
audi | -2.000 |
Token | It |
Token ID | 632 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
イト | +1.245 |
ー� | +1.219 |
checks | +1.164 |
roup | +1.163 |
ゴン | +1.161 |
Neg logit contributions | |
Palest | -1.247 |
anon | -1.124 |
Bey | -1.095 |
ILLE | -1.050 |
audi | -1.022 |
Token | is |
Token ID | 318 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
イト | +1.441 |
ー� | +1.399 |
checks | +1.360 |
ゴン | +1.355 |
roup | +1.349 |
Neg logit contributions | |
Palest | -1.902 |
anon | -1.686 |
Bey | -1.663 |
ILLE | -1.596 |
audi | -1.533 |
Token | eties |
Token ID | 31638 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
イト | +0.817 |
ー� | +0.770 |
ゴン | +0.743 |
checks | +0.737 |
roup | +0.734 |
Neg logit contributions | |
Palest | -2.393 |
anon | -2.190 |
Bey | -2.163 |
ILLE | -2.093 |
audi | -2.040 |
Token | anime |
Token ID | 11984 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Palest | +0.263 |
anon | +0.230 |
Bey | +0.227 |
ILLE | +0.214 |
audi | +0.207 |
Neg logit contributions | |
イト | -0.246 |
ー� | -0.237 |
ゴン | -0.235 |
checks | -0.232 |
roup | -0.232 |
Token | , |
Token ID | 11 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
イト | +1.957 |
ー� | +1.898 |
ゴン | +1.852 |
checks | +1.850 |
roup | +1.843 |
Neg logit contributions | |
Palest | -2.199 |
anon | -1.940 |
Bey | -1.896 |
ILLE | -1.811 |
audi | -1.756 |
Token | by |
Token ID | 416 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
イト | +0.434 |
ー� | +0.419 |
ゴン | +0.412 |
checks | +0.409 |
roup | +0.408 |
Neg logit contributions | |
Palest | -0.516 |
anon | -0.457 |
Bey | -0.448 |
ILLE | -0.427 |
audi | -0.413 |
Token | Pierre |
Token ID | 21204 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
イト | +0.239 |
ー� | +0.231 |
ゴン | +0.228 |
checks | +0.226 |
roup | +0.226 |
Neg logit contributions | |
Palest | -0.263 |
anon | -0.232 |
Bey | -0.227 |
ILLE | -0.216 |
audi | -0.208 |
Token | Kart |
Token ID | 32872 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
Palest | +2.936 |
anon | +2.519 |
Bey | +2.469 |
ILLE | +2.323 |
audi | +2.259 |
Neg logit contributions | |
イト | -2.962 |
ゴン | -2.872 |
ー� | -2.833 |
checks | -2.795 |
roup | -2.781 |
Token | ner |
Token ID | 1008 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Palest | +7.721 |
anon | +7.139 |
Bey | +6.662 |
audi | +6.433 |
oire | +6.426 |
Neg logit contributions | |
イト | -6.658 |
ゴン | -6.412 |
ー� | -6.329 |
checks | -6.093 |
safety | -6.037 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
イト | +1.077 |
ー� | +1.041 |
ゴン | +1.023 |
roup | +1.021 |
checks | +1.020 |
Neg logit contributions | |
Palest | -1.210 |
anon | -1.068 |
Bey | -1.047 |
ILLE | -0.996 |
audi | -0.960 |
Token | with |
Token ID | 351 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Palest | +1.045 |
anon | +0.910 |
Bey | +0.895 |
ILLE | +0.845 |
audi | +0.816 |
Neg logit contributions | |
イト | -1.016 |
ー� | -0.980 |
ゴン | -0.971 |
checks | -0.960 |
roup | -0.960 |
Token | translated |
Token ID | 14251 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
イト | +0.176 |
ー� | +0.170 |
ゴン | +0.167 |
checks | +0.166 |
roup | +0.165 |
Neg logit contributions | |
Palest | -0.221 |
anon | -0.196 |
Bey | -0.193 |
ILLE | -0.184 |
audi | -0.178 |
Token | versions |
Token ID | 6300 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
Palest | +5.910 |
anon | +5.150 |
Bey | +5.105 |
ILLE | +4.731 |
audio | +4.728 |
Neg logit contributions | |
イト | -4.720 |
ゴン | -4.539 |
roup | -4.408 |
plet | -4.375 |
ー� | -4.372 |
Token | � |
Token ID | 247 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
イト | +0.304 |
ー� | +0.293 |
ゴン | +0.285 |
checks | +0.282 |
roup | +0.281 |
Neg logit contributions | |
Palest | -0.569 |
anon | -0.511 |
Bey | -0.505 |
ILLE | -0.483 |
audi | -0.470 |
Token | s |
Token ID | 82 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
イト | +1.070 |
ー� | +1.033 |
ゴン | +1.012 |
checks | +1.010 |
roup | +1.009 |
Neg logit contributions | |
Palest | -1.311 |
anon | -1.159 |
Bey | -1.139 |
ILLE | -1.086 |
audi | -1.048 |
Token | stage |
Token ID | 3800 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
イト | +0.539 |
ー� | +0.518 |
safety | +0.510 |
roup | +0.508 |
checks | +0.507 |
Neg logit contributions | |
Palest | -0.758 |
anon | -0.679 |
Bey | -0.670 |
ILLE | -0.641 |
audi | -0.621 |
Token | covers |
Token ID | 8698 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Palest | +1.036 |
anon | +0.920 |
Bey | +0.903 |
ILLE | +0.859 |
audi | +0.835 |
Neg logit contributions | |
イト | -0.801 |
ー� | -0.770 |
ゴン | -0.766 |
checks | -0.750 |
roup | -0.749 |
Token | 130 |
Token ID | 11323 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
Palest | +0.235 |
anon | +0.208 |
Bey | +0.205 |
ILLE | +0.195 |
audi | +0.189 |
Neg logit contributions | |
イト | -0.187 |
ー� | -0.181 |
ゴン | -0.178 |
checks | -0.176 |
roup | -0.176 |
Token | kilometres |
Token ID | 23990 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
Palest | +1.197 |
anon | +1.022 |
Bey | +0.999 |
ILLE | +0.933 |
audi | +0.894 |
Neg logit contributions | |
イト | -1.524 |
ー� | -1.479 |
ゴン | -1.467 |
checks | -1.458 |
roup | -1.454 |
Token | to |
Token ID | 284 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
Palest | +6.897 |
anon | +5.867 |
Bey | +5.483 |
oire | +5.309 |
ł | +5.305 |
Neg logit contributions | |
ゴン | -7.560 |
イト | -7.515 |
checks | -7.147 |
ー� | -7.142 |
warts | -7.091 |
Token | Tan |
Token ID | 11818 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Palest | +2.297 |
anon | +2.011 |
Bey | +1.985 |
ILLE | +1.869 |
audi | +1.813 |
Neg logit contributions | |
イト | -1.937 |
ゴン | -1.855 |
ー� | -1.847 |
checks | -1.831 |
roup | -1.801 |
Token | unda |
Token ID | 46535 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
イト | +1.406 |
ー� | +1.365 |
checks | +1.340 |
roup | +1.339 |
ゴン | +1.334 |
Neg logit contributions | |
Palest | -1.504 |
anon | -1.314 |
Bey | -1.296 |
ILLE | -1.242 |
audi | -1.180 |
Token | and |
Token ID | 290 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Palest | +2.080 |
anon | +1.829 |
Bey | +1.789 |
ILLE | +1.692 |
audi | +1.634 |
Neg logit contributions | |
イト | -1.875 |
ー� | -1.803 |
ゴン | -1.802 |
checks | -1.782 |
roup | -1.753 |
Token | may |
Token ID | 743 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Palest | +0.263 |
anon | +0.233 |
Bey | +0.229 |
ILLE | +0.218 |
audi | +0.211 |
Neg logit contributions | |
イト | -0.214 |
ー� | -0.207 |
ゴン | -0.204 |
checks | -0.202 |
roup | -0.202 |
Token | sure |
Token ID | 1654 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Palest | +3.766 |
anon | +3.293 |
Bey | +3.222 |
ILLE | +3.007 |
audio | +2.901 |
Neg logit contributions | |
イト | -3.989 |
ゴン | -3.863 |
ー� | -3.806 |
checks | -3.770 |
roup | -3.767 |
Token | as |
Token ID | 355 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Palest | +0.183 |
anon | +0.162 |
Bey | +0.159 |
ILLE | +0.151 |
audi | +0.146 |
Neg logit contributions | |
イト | -0.159 |
ー� | -0.154 |
ゴン | -0.152 |
checks | -0.150 |
roup | -0.150 |
Token | to |
Token ID | 284 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
イト | +0.803 |
ー� | +0.776 |
ゴン | +0.765 |
checks | +0.760 |
roup | +0.758 |
Neg logit contributions | |
Palest | -0.840 |
anon | -0.738 |
Bey | -0.723 |
ILLE | -0.686 |
audi | -0.661 |
Token | how |
Token ID | 703 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
イト | +0.459 |
ー� | +0.443 |
ゴン | +0.434 |
checks | +0.433 |
roup | +0.431 |
Neg logit contributions | |
Palest | -0.579 |
anon | -0.514 |
Bey | -0.505 |
ILLE | -0.481 |
audi | -0.466 |
Token | on |
Token ID | 319 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
Palest | +3.758 |
anon | +3.253 |
Bey | +3.237 |
ILLE | +3.099 |
audio | +2.982 |
Neg logit contributions | |
イト | -3.230 |
ー� | -3.120 |
ゴン | -3.094 |
checks | -3.034 |
roup | -2.994 |
Token | par |
Token ID | 1582 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
Palest | +0.595 |
anon | +0.524 |
Bey | +0.515 |
ILLE | +0.488 |
audi | +0.473 |
Neg logit contributions | |
イト | -0.518 |
ー� | -0.500 |
ゴン | -0.496 |
checks | -0.490 |
roup | -0.488 |
Token | the |
Token ID | 262 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
Palest | +7.069 |
anon | +5.967 |
Bey | +5.895 |
ILLE | +5.566 |
audio | +5.466 |
Neg logit contributions | |
イト | -7.094 |
ー� | -6.973 |
ゴン | -6.894 |
checks | -6.678 |
roup | -6.610 |
Token | Xbox |
Token ID | 9445 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
イト | +0.297 |
ー� | +0.286 |
ゴン | +0.281 |
roup | +0.280 |
checks | +0.279 |
Neg logit contributions | |
Palest | -0.375 |
anon | -0.333 |
Bey | -0.327 |
ILLE | -0.312 |
audi | -0.302 |
Token | version |
Token ID | 2196 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Palest | +1.017 |
anon | +0.883 |
Bey | +0.855 |
ILLE | +0.813 |
audi | +0.774 |
Neg logit contributions | |
イト | -1.256 |
ー� | -1.214 |
ゴン | -1.204 |
checks | -1.189 |
roup | -1.182 |
Token | will |
Token ID | 481 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Palest | +0.868 |
anon | +0.764 |
Bey | +0.747 |
ILLE | +0.709 |
audi | +0.690 |
Neg logit contributions | |
イト | -0.795 |
ー� | -0.766 |
ゴン | -0.763 |
roup | -0.751 |
checks | -0.740 |
Token | be |
Token ID | 307 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Palest | +1.277 |
anon | +1.148 |
Bey | +1.135 |
ILLE | +1.075 |
audi | +1.055 |
Neg logit contributions | |
イト | -0.914 |
ー� | -0.868 |
ゴン | -0.866 |
checks | -0.846 |
roup | -0.845 |
Token | back |
Token ID | 736 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
イト | +0.121 |
ー� | +0.117 |
roup | +0.114 |
checks | +0.114 |
ゴン | +0.114 |
Neg logit contributions | |
Palest | -0.170 |
anon | -0.152 |
Bey | -0.149 |
ILLE | -0.142 |
audi | -0.138 |
Token | to |
Token ID | 284 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Palest | +1.475 |
anon | +1.291 |
Bey | +1.262 |
ILLE | +1.194 |
audi | +1.151 |
Neg logit contributions | |
イト | -1.476 |
ゴン | -1.421 |
ー� | -1.418 |
roup | -1.385 |
checks | -1.384 |
Token | the |
Token ID | 262 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
イト | +0.973 |
ー� | +0.938 |
roup | +0.913 |
ゴン | +0.912 |
safety | +0.911 |
Neg logit contributions | |
Palest | -1.491 |
anon | -1.335 |
Bey | -1.316 |
ILLE | -1.256 |
audi | -1.224 |
Token | front |
Token ID | 2166 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
イト | +0.552 |
ー� | +0.532 |
safety | +0.526 |
roup | +0.522 |
checks | +0.520 |
Neg logit contributions | |
Palest | -0.794 |
anon | -0.711 |
Bey | -0.702 |
ILLE | -0.672 |
audi | -0.649 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Palest | +2.460 |
anon | +2.165 |
Bey | +2.117 |
ILLE | +2.006 |
audi | +1.924 |
Neg logit contributions | |
イト | -2.320 |
ゴン | -2.246 |
ー� | -2.215 |
roup | -2.157 |
checks | -2.147 |
Token | Kart |
Token ID | 32872 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
イト | +1.244 |
ー� | +1.213 |
roup | +1.177 |
safety | +1.167 |
checks | +1.166 |
Neg logit contributions | |
Palest | -1.517 |
anon | -1.349 |
Bey | -1.325 |
ILLE | -1.262 |
audi | -1.234 |
Token | ing |
Token ID | 278 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Palest | +6.785 |
anon | +6.028 |
Bey | +5.670 |
ILLE | +5.449 |
heid | +5.249 |
Neg logit contributions | |
イト | -7.324 |
ゴン | -7.319 |
ー� | -7.193 |
checks | -6.996 |
phrine | -6.950 |
Token | has |
Token ID | 468 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
Palest | +1.642 |
anon | +1.460 |
Bey | +1.435 |
ILLE | +1.368 |
audi | +1.325 |
Neg logit contributions | |
イト | -1.255 |
ー� | -1.208 |
ゴン | -1.191 |
checks | -1.178 |
roup | -1.176 |
Token | bo |
Token ID | 1489 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Palest | +0.549 |
anon | +0.488 |
Bey | +0.481 |
ILLE | +0.459 |
audi | +0.444 |
Neg logit contributions | |
イト | -0.406 |
ー� | -0.391 |
ゴン | -0.384 |
checks | -0.382 |
roup | -0.381 |
Token | omed |
Token ID | 12657 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
Palest | +1.053 |
anon | +0.918 |
Bey | +0.903 |
ILLE | +0.855 |
audi | +0.821 |
Neg logit contributions | |
イト | -1.049 |
ー� | -1.016 |
ゴン | -1.000 |
roup | -0.997 |
checks | -0.996 |
Token | since |
Token ID | 1201 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Palest | +0.408 |
anon | +0.360 |
Bey | +0.354 |
ILLE | +0.336 |
audi | +0.325 |
Neg logit contributions | |
イト | -0.358 |
ー� | -0.346 |
ゴン | -0.341 |
checks | -0.338 |
roup | -0.338 |
Token | stand |
Token ID | 1302 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Palest | +1.349 |
anon | +1.205 |
Bey | +1.184 |
ILLE | +1.127 |
audi | +1.093 |
Neg logit contributions | |
イト | -1.017 |
ゴン | -0.973 |
ー� | -0.972 |
checks | -0.950 |
roup | -0.944 |
Token | with |
Token ID | 351 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
Palest | +0.941 |
anon | +0.828 |
Bey | +0.813 |
ILLE | +0.772 |
audi | +0.745 |
Neg logit contributions | |
イト | -0.852 |
ー� | -0.823 |
ゴン | -0.811 |
checks | -0.805 |
roup | -0.804 |
Token | or |
Token ID | 393 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
Palest | +3.003 |
anon | +2.627 |
Bey | +2.598 |
ILLE | +2.465 |
audi | +2.372 |
Neg logit contributions | |
イト | -2.448 |
ゴン | -2.357 |
ー� | -2.340 |
roup | -2.284 |
checks | -2.277 |
Token | for |
Token ID | 329 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
Palest | +1.782 |
anon | +1.554 |
Bey | +1.524 |
ILLE | +1.432 |
audi | +1.388 |
Neg logit contributions | |
イト | -1.989 |
ゴン | -1.919 |
ー� | -1.918 |
checks | -1.884 |
roup | -1.860 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Palest | +2.535 |
anon | +2.251 |
Bey | +2.226 |
ILLE | +2.120 |
audi | +2.052 |
Neg logit contributions | |
イト | -1.719 |
ゴン | -1.646 |
ー� | -1.641 |
roup | -1.601 |
checks | -1.592 |
Token | oppressed |
Token ID | 25765 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
Palest | +1.181 |
anon | +1.042 |
Bey | +1.024 |
ILLE | +0.973 |
audi | +0.941 |
Neg logit contributions | |
イト | -1.014 |
ー� | -0.978 |
ゴン | -0.966 |
checks | -0.956 |
roup | -0.955 |
Token | . |
Token ID | 13 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
Palest | +7.558 |
anon | +6.375 |
Bey | +6.286 |
ILLE | +5.892 |
ł | +5.855 |
Neg logit contributions | |
イト | -6.954 |
ゴン | -6.905 |
ー� | -6.615 |
peror | -6.486 |
phrine | -6.440 |
Token | � |
Token ID | 447 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Palest | +0.545 |
anon | +0.479 |
Bey | +0.470 |
ILLE | +0.446 |
audi | +0.431 |
Neg logit contributions | |
イト | -0.512 |
ー� | -0.495 |
ゴン | -0.485 |
checks | -0.483 |
roup | -0.483 |
Token | � |
Token ID | 251 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Palest | +2.458 |
anon | +2.231 |
Bey | +2.207 |
ILLE | +2.125 |
audi | +2.071 |
Neg logit contributions | |
イト | -0.970 |
ー� | -0.916 |
roup | -0.897 |
checks | -0.895 |
ゴン | -0.890 |
Token |
|
Token ID | 198 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Palest | +1.795 |
anon | +1.559 |
Bey | +1.535 |
ILLE | +1.443 |
audi | +1.386 |
Neg logit contributions | |
イト | -1.785 |
ゴン | -1.727 |
ー� | -1.723 |
checks | -1.695 |
roup | -1.692 |
Token |
|
Token ID | 198 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Palest | +1.313 |
anon | +1.138 |
Bey | +1.117 |
ILLE | +1.058 |
audi | +1.019 |
Neg logit contributions | |
イト | -1.348 |
ー� | -1.307 |
ゴン | -1.283 |
checks | -1.282 |
roup | -1.278 |
Token | year |
Token ID | 1941 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
Palest | +1.423 |
anon | +1.252 |
Bey | +1.230 |
ILLE | +1.160 |
audi | +1.120 |
Neg logit contributions | |
イト | -1.385 |
ー� | -1.337 |
ゴン | -1.322 |
checks | -1.306 |
roup | -1.305 |
Token | - |
Token ID | 12 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Palest | +3.205 |
anon | +2.759 |
Bey | +2.666 |
ILLE | +2.521 |
audi | +2.440 |
Neg logit contributions | |
イト | -4.047 |
ー� | -3.878 |
ゴン | -3.862 |
checks | -3.818 |
roup | -3.779 |
Token | old |
Token ID | 727 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
イト | +0.232 |
ー� | +0.228 |
roup | +0.226 |
checks | +0.226 |
zilla | +0.221 |
Neg logit contributions | |
Palest | -0.360 |
anon | -0.307 |
Bey | -0.306 |
ILLE | -0.296 |
audi | -0.282 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Palest | +2.491 |
anon | +2.190 |
Bey | +2.169 |
ILLE | +2.051 |
audi | +1.983 |
Neg logit contributions | |
イト | -1.996 |
ゴン | -1.918 |
ー� | -1.914 |
checks | -1.867 |
roup | -1.865 |
Token | was |
Token ID | 373 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
イト | +0.203 |
ー� | +0.197 |
checks | +0.193 |
ゴン | +0.193 |
roup | +0.192 |
Neg logit contributions | |
Palest | -0.215 |
anon | -0.189 |
Bey | -0.185 |
ILLE | -0.177 |
audi | -0.170 |
Token | kidnapped |
Token ID | 23384 |
Feature activation | -9.96e+00 |
Pos logit contributions | |
Palest | +0.550 |
anon | +0.480 |
Bey | +0.471 |
ILLE | +0.445 |
audi | +0.429 |
Neg logit contributions | |
イト | -0.561 |
ー� | -0.543 |
ゴン | -0.535 |
checks | -0.532 |
roup | -0.531 |
Token | after |
Token ID | 706 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
Palest | +6.245 |
anon | +5.166 |
Bey | +5.144 |
ł | +4.571 |
ILLE | +4.568 |
Neg logit contributions | |
イト | -8.046 |
ゴン | -7.978 |
roup | -7.647 |
ー� | -7.646 |
checks | -7.605 |
Token | attending |
Token ID | 11969 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
イト | +1.311 |
ー� | +1.264 |
checks | +1.242 |
ゴン | +1.234 |
safety | +1.232 |
Neg logit contributions | |
Palest | -1.877 |
anon | -1.685 |
Bey | -1.645 |
ILLE | -1.579 |
audi | -1.536 |
Token | a |
Token ID | 257 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
イト | +0.720 |
ー� | +0.693 |
ゴン | +0.681 |
checks | +0.678 |
roup | +0.676 |
Neg logit contributions | |
Palest | -0.931 |
anon | -0.829 |
Bey | -0.813 |
ILLE | -0.777 |
audi | -0.752 |
Token | punk |
Token ID | 22782 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
イト | +0.742 |
ー� | +0.714 |
ゴン | +0.700 |
checks | +0.696 |
roup | +0.696 |
Neg logit contributions | |
Palest | -1.051 |
anon | -0.940 |
Bey | -0.924 |
ILLE | -0.883 |
audi | -0.857 |
Token | rock |
Token ID | 3881 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
Palest | +2.835 |
anon | +2.479 |
Bey | +2.449 |
ILLE | +2.312 |
audio | +2.248 |
Neg logit contributions | |
イト | -2.308 |
ゴン | -2.227 |
ー� | -2.216 |
checks | -2.165 |
plet | -2.115 |
Token | , |
Token ID | 11 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
イト | +0.020 |
ー� | +0.019 |
ゴン | +0.019 |
checks | +0.019 |
roup | +0.018 |
Neg logit contributions | |
Palest | -0.022 |
anon | -0.019 |
Bey | -0.019 |
ILLE | -0.018 |
audi | -0.017 |
Token | some |
Token ID | 617 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
イト | +0.407 |
ー� | +0.395 |
checks | +0.386 |
ゴン | +0.386 |
roup | +0.385 |
Neg logit contributions | |
Palest | -0.466 |
anon | -0.411 |
Bey | -0.404 |
ILLE | -0.385 |
audi | -0.372 |
Token | less |
Token ID | 1342 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
イト | +1.055 |
ー� | +1.030 |
safety | +1.010 |
checks | +1.008 |
roup | +1.006 |
Neg logit contributions | |
Palest | -1.223 |
anon | -1.082 |
Bey | -1.062 |
ILLE | -1.012 |
audi | -0.980 |
Token | than |
Token ID | 621 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Palest | +3.164 |
anon | +2.751 |
Bey | +2.718 |
ILLE | +2.546 |
audi | +2.446 |
Neg logit contributions | |
イト | -3.181 |
ゴン | -3.075 |
ー� | -3.031 |
checks | -2.958 |
warts | -2.915 |
Token | 50 |
Token ID | 2026 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Palest | +1.190 |
anon | +1.036 |
Bey | +1.017 |
ILLE | +0.961 |
audi | +0.925 |
Neg logit contributions | |
イト | -1.220 |
ー� | -1.179 |
ゴン | -1.166 |
checks | -1.154 |
roup | -1.153 |
Token | miles |
Token ID | 4608 |
Feature activation | -9.89e+00 |
Pos logit contributions | |
イト | +0.114 |
ー� | +0.111 |
ゴン | +0.109 |
checks | +0.108 |
roup | +0.108 |
Neg logit contributions | |
Palest | -0.126 |
anon | -0.110 |
Bey | -0.108 |
ILLE | -0.103 |
audi | -0.100 |
Token | from |
Token ID | 422 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
Palest | +6.035 |
anon | +5.143 |
Bey | +4.894 |
oire | +4.600 |
ILLE | +4.521 |
Neg logit contributions | |
イト | -8.136 |
ゴン | -8.123 |
ー� | -7.674 |
warts | -7.572 |
roup | -7.541 |
Token | the |
Token ID | 262 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
Palest | +2.955 |
anon | +2.558 |
Bey | +2.494 |
ILLE | +2.363 |
audi | +2.268 |
Neg logit contributions | |
イト | -3.021 |
ゴン | -2.990 |
ー� | -2.856 |
roup | -2.801 |
checks | -2.794 |
Token | ISIS |
Token ID | 7768 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
Palest | +1.547 |
anon | +1.355 |
Bey | +1.325 |
ILLE | +1.262 |
audi | +1.218 |
Neg logit contributions | |
イト | -1.436 |
ゴン | -1.396 |
ー� | -1.370 |
checks | -1.341 |
roup | -1.341 |
Token | - |
Token ID | 12 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Palest | +2.200 |
anon | +1.929 |
Bey | +1.881 |
ILLE | +1.810 |
audi | +1.732 |
Neg logit contributions | |
イト | -1.991 |
ゴン | -1.930 |
ー� | -1.912 |
roup | -1.878 |
checks | -1.875 |
Token | controlled |
Token ID | 14401 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
イト | +0.548 |
ー� | +0.535 |
checks | +0.527 |
ゴン | +0.526 |
roup | +0.524 |
Neg logit contributions | |
Palest | -0.380 |
anon | -0.319 |
Bey | -0.312 |
ILLE | -0.291 |
audi | -0.276 |
Token | of |
Token ID | 286 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
イト | +0.993 |
ー� | +0.964 |
roup | +0.943 |
safety | +0.943 |
checks | +0.942 |
Neg logit contributions | |
Palest | -1.045 |
anon | -0.923 |
Bey | -0.903 |
ILLE | -0.858 |
audi | -0.828 |
Token | about |
Token ID | 546 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
Palest | +1.115 |
anon | +0.980 |
Bey | +0.962 |
ILLE | +0.912 |
audi | +0.880 |
Neg logit contributions | |
イト | -1.024 |
ー� | -0.988 |
ゴン | -0.976 |
checks | -0.967 |
roup | -0.966 |
Token | 1 |
Token ID | 352 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
Palest | +2.224 |
anon | +1.954 |
Bey | +1.916 |
ILLE | +1.811 |
audi | +1.751 |
Neg logit contributions | |
イト | -1.997 |
ー� | -1.916 |
ゴン | -1.903 |
checks | -1.876 |
roup | -1.873 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
イト | +0.054 |
ー� | +0.052 |
ゴン | +0.051 |
checks | +0.051 |
roup | +0.050 |
Neg logit contributions | |
Palest | -0.068 |
anon | -0.060 |
Bey | -0.059 |
ILLE | -0.057 |
audi | -0.055 |
Token | 900 |
Token ID | 12865 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Palest | +1.033 |
anon | +0.904 |
Bey | +0.884 |
ILLE | +0.833 |
audi | +0.801 |
Neg logit contributions | |
イト | -1.124 |
ー� | -1.089 |
ゴン | -1.080 |
checks | -1.069 |
roup | -1.068 |
Token | kilometers |
Token ID | 18212 |
Feature activation | -9.86e+00 |
Pos logit contributions | |
Palest | +0.957 |
anon | +0.831 |
Bey | +0.814 |
ILLE | +0.768 |
audi | +0.738 |
Neg logit contributions | |
イト | -1.045 |
ー� | -1.013 |
ゴン | -1.000 |
checks | -0.993 |
roup | -0.992 |
Token | ( |
Token ID | 357 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
Palest | +6.880 |
anon | +5.984 |
Bey | +5.703 |
ILLE | +5.432 |
oire | +5.310 |
Neg logit contributions | |
イト | -7.315 |
ゴン | -7.188 |
ー� | -6.955 |
roup | -6.770 |
checks | -6.768 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
Palest | +2.407 |
anon | +2.102 |
Bey | +2.043 |
ILLE | +1.904 |
audi | +1.833 |
Neg logit contributions | |
イト | -3.149 |
ー� | -3.049 |
ゴン | -3.017 |
roup | -2.985 |
checks | -2.968 |
Token | , |
Token ID | 11 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
イト | +1.514 |
ゴン | +1.459 |
ー� | +1.450 |
checks | +1.420 |
roup | +1.419 |
Neg logit contributions | |
Palest | -2.152 |
anon | -1.920 |
Bey | -1.885 |
ILLE | -1.815 |
audi | -1.755 |
Token | 200 |
Token ID | 2167 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
Palest | +0.208 |
anon | +0.179 |
Bey | +0.176 |
ILLE | +0.165 |
audi | +0.159 |
Neg logit contributions | |
イト | -0.240 |
ー� | -0.233 |
ゴン | -0.230 |
checks | -0.228 |
roup | -0.228 |
Token | miles |
Token ID | 4608 |
Feature activation | -7.13e+00 |
Pos logit contributions | |
Palest | +0.649 |
anon | +0.565 |
Bey | +0.553 |
ILLE | +0.523 |
audi | +0.503 |
Neg logit contributions | |
イト | -0.702 |
ー� | -0.680 |
ゴン | -0.673 |
checks | -0.668 |
roup | -0.666 |
Token | a |
Token ID | 257 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
Palest | +2.126 |
anon | +1.873 |
Bey | +1.842 |
ILLE | +1.754 |
audi | +1.694 |
Neg logit contributions | |
イト | -1.690 |
ー� | -1.611 |
ゴン | -1.611 |
roup | -1.576 |
checks | -1.573 |
Token | form |
Token ID | 1296 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Palest | +0.630 |
anon | +0.558 |
Bey | +0.549 |
ILLE | +0.522 |
audi | +0.506 |
Neg logit contributions | |
イト | -0.514 |
ー� | -0.496 |
ゴン | -0.487 |
checks | -0.485 |
roup | -0.484 |
Token | of |
Token ID | 286 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Palest | +0.757 |
anon | +0.660 |
Bey | +0.647 |
ILLE | +0.611 |
audi | +0.589 |
Neg logit contributions | |
イト | -0.782 |
ー� | -0.756 |
ゴン | -0.747 |
checks | -0.741 |
roup | -0.740 |
Token | racism |
Token ID | 10713 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
Palest | +0.751 |
anon | +0.658 |
Bey | +0.647 |
ILLE | +0.611 |
audi | +0.591 |
Neg logit contributions | |
イト | -0.770 |
ー� | -0.750 |
checks | -0.735 |
ゴン | -0.734 |
roup | -0.733 |
Token | and |
Token ID | 290 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Palest | +3.034 |
anon | +2.646 |
Bey | +2.565 |
ILLE | +2.436 |
audi | +2.340 |
Neg logit contributions | |
イト | -2.848 |
ゴン | -2.743 |
ー� | -2.712 |
checks | -2.665 |
roup | -2.652 |
Token | colonialism |
Token ID | 48359 |
Feature activation | -9.76e+00 |
Pos logit contributions | |
Palest | +1.108 |
anon | +0.975 |
Bey | +0.957 |
ILLE | +0.908 |
audi | +0.876 |
Neg logit contributions | |
イト | -0.992 |
ー� | -0.956 |
ゴン | -0.945 |
checks | -0.934 |
roup | -0.934 |
Token | … |
Token ID | 1399 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Palest | +6.891 |
anon | +5.923 |
Bey | +5.462 |
ILLE | +5.296 |
Orwell | +5.193 |
Neg logit contributions | |
イト | -7.224 |
ゴン | -7.159 |
plet | -6.769 |
ー� | -6.744 |
checks | -6.697 |
Token | The |
Token ID | 464 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Palest | +1.881 |
anon | +1.647 |
Bey | +1.616 |
ILLE | +1.518 |
audi | +1.469 |
Neg logit contributions | |
イト | -1.860 |
ー� | -1.788 |
ゴン | -1.783 |
roup | -1.753 |
checks | -1.748 |
Token | just |
Token ID | 655 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
Palest | +0.269 |
anon | +0.237 |
Bey | +0.234 |
ILLE | +0.221 |
audi | +0.213 |
Neg logit contributions | |
イト | -0.260 |
ー� | -0.252 |
checks | -0.246 |
ゴン | -0.246 |
roup | -0.246 |
Token | cause |
Token ID | 2728 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Palest | +5.294 |
anon | +4.622 |
Bey | +4.530 |
ILLE | +4.307 |
oire | +4.240 |
Neg logit contributions | |
イト | -4.358 |
ゴン | -4.216 |
ー� | -4.160 |
plet | -4.064 |
checks | -4.054 |
Token | of |
Token ID | 286 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Palest | +1.133 |
anon | +0.986 |
Bey | +0.967 |
ILLE | +0.913 |
audi | +0.880 |
Neg logit contributions | |
イト | -1.156 |
ー� | -1.116 |
ゴン | -1.104 |
roup | -1.093 |
checks | -1.092 |
Token | Nations |
Token ID | 7973 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
Palest | +1.563 |
anon | +1.356 |
Bey | +1.329 |
ILLE | +1.253 |
audi | +1.204 |
Neg logit contributions | |
イト | -1.726 |
ー� | -1.672 |
ゴン | -1.651 |
checks | -1.640 |
roup | -1.639 |
Token | said |
Token ID | 531 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
Palest | +2.726 |
anon | +2.405 |
Bey | +2.344 |
ILLE | +2.230 |
audi | +2.152 |
Neg logit contributions | |
イト | -2.371 |
ー� | -2.272 |
ゴン | -2.259 |
roup | -2.212 |
checks | -2.206 |
Token | 126 |
Token ID | 19710 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Palest | +0.602 |
anon | +0.534 |
Bey | +0.526 |
ILLE | +0.501 |
audi | +0.485 |
Neg logit contributions | |
イト | -0.477 |
ー� | -0.460 |
ゴン | -0.453 |
checks | -0.449 |
roup | -0.448 |
Token | women |
Token ID | 1466 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
イト | +0.105 |
ー� | +0.103 |
safety | +0.101 |
checks | +0.101 |
roup | +0.100 |
Neg logit contributions | |
Palest | -0.110 |
anon | -0.097 |
Bey | -0.095 |
ILLE | -0.090 |
audi | -0.087 |
Token | were |
Token ID | 547 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Palest | +2.476 |
anon | +2.182 |
Bey | +2.134 |
ILLE | +2.028 |
audi | +1.953 |
Neg logit contributions | |
イト | -2.318 |
ー� | -2.229 |
ゴン | -2.223 |
checks | -2.181 |
roup | -2.177 |
Token | raped |
Token ID | 16110 |
Feature activation | -9.74e+00 |
Pos logit contributions | |
Palest | +0.758 |
anon | +0.658 |
Bey | +0.644 |
ILLE | +0.606 |
audi | +0.584 |
Neg logit contributions | |
イト | -0.851 |
ー� | -0.828 |
checks | -0.814 |
ゴン | -0.812 |
roup | -0.811 |
Token | in |
Token ID | 287 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Palest | +6.265 |
anon | +5.307 |
Bey | +5.151 |
ILLE | +4.755 |
ł | +4.606 |
Neg logit contributions | |
イト | -7.920 |
ゴン | -7.754 |
ー� | -7.495 |
roup | -7.341 |
plet | -7.279 |
Token | Min |
Token ID | 1855 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Palest | +1.914 |
anon | +1.677 |
Bey | +1.646 |
ILLE | +1.560 |
audi | +1.506 |
Neg logit contributions | |
イト | -1.701 |
ー� | -1.632 |
ゴン | -1.627 |
checks | -1.594 |
roup | -1.594 |
Token | ova |
Token ID | 10071 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Palest | +0.783 |
anon | +0.692 |
Bey | +0.664 |
audi | +0.610 |
ILLE | +0.610 |
Neg logit contributions | |
イト | -0.897 |
ゴン | -0.867 |
ー� | -0.862 |
checks | -0.836 |
roup | -0.834 |
Token | in |
Token ID | 287 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Palest | +1.733 |
anon | +1.525 |
Bey | +1.497 |
ILLE | +1.422 |
audi | +1.373 |
Neg logit contributions | |
イト | -1.561 |
ー� | -1.507 |
ゴン | -1.487 |
checks | -1.475 |
roup | -1.471 |
Token | Congo |
Token ID | 25935 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
Palest | +0.956 |
anon | +0.844 |
Bey | +0.830 |
ILLE | +0.790 |
audi | +0.763 |
Neg logit contributions | |
イト | -0.842 |
ー� | -0.816 |
ゴン | -0.799 |
checks | -0.798 |
roup | -0.797 |
Token | � |
Token ID | 447 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
イト | +1.560 |
ー� | +1.516 |
checks | +1.471 |
ゴン | +1.465 |
roup | +1.462 |
Neg logit contributions | |
Palest | -1.517 |
anon | -1.329 |
Bey | -1.296 |
ILLE | -1.239 |
audi | -1.199 |
Token | � |
Token ID | 251 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Palest | +1.131 |
anon | +1.032 |
Bey | +1.021 |
ILLE | +0.984 |
audi | +0.962 |
Neg logit contributions | |
イト | -0.404 |
ー� | -0.380 |
ゴン | -0.369 |
roup | -0.367 |
checks | -0.366 |
Token |
|
Token ID | 198 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
Palest | +0.997 |
anon | +0.869 |
Bey | +0.856 |
ILLE | +0.805 |
audi | +0.776 |
Neg logit contributions | |
イト | -1.026 |
ー� | -0.993 |
ゴン | -0.986 |
roup | -0.974 |
checks | -0.973 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Palest | +0.456 |
anon | +0.387 |
Bey | +0.382 |
ILLE | +0.366 |
audi | +0.352 |
Neg logit contributions | |
イト | -0.420 |
ー� | -0.410 |
checks | -0.403 |
roup | -0.400 |
safety | -0.397 |
Token | Three |
Token ID | 12510 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
Palest | +0.747 |
anon | +0.648 |
Bey | +0.636 |
ILLE | +0.598 |
audi | +0.574 |
Neg logit contributions | |
イト | -0.843 |
ー� | -0.817 |
ゴン | -0.807 |
checks | -0.801 |
roup | -0.801 |
Token | decades |
Token ID | 4647 |
Feature activation | -9.73e+00 |
Pos logit contributions | |
イト | +0.470 |
ー� | +0.447 |
ゴン | +0.436 |
checks | +0.435 |
roup | +0.429 |
Neg logit contributions | |
Palest | -0.924 |
anon | -0.836 |
Bey | -0.824 |
ILLE | -0.790 |
audi | -0.771 |
Token | on |
Token ID | 319 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Palest | +6.402 |
anon | +5.545 |
Bey | +5.253 |
ILLE | +5.053 |
audi | +4.904 |
Neg logit contributions | |
ゴン | -7.511 |
イト | -7.488 |
ー� | -7.198 |
roup | -6.946 |
plet | -6.939 |
Token | , |
Token ID | 11 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
Palest | +1.529 |
anon | +1.344 |
Bey | +1.324 |
ILLE | +1.256 |
audi | +1.217 |
Neg logit contributions | |
イト | -1.326 |
ー� | -1.282 |
ゴン | -1.269 |
roup | -1.251 |
checks | -1.250 |
Token | Bl |
Token ID | 1086 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Palest | +0.673 |
anon | +0.592 |
Bey | +0.582 |
ILLE | +0.551 |
audi | +0.533 |
Neg logit contributions | |
イト | -0.609 |
ー� | -0.588 |
ゴン | -0.582 |
roup | -0.576 |
checks | -0.575 |
Token | ume |
Token ID | 2454 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
イト | +0.074 |
ー� | +0.069 |
ゴン | +0.067 |
checks | +0.067 |
roup | +0.067 |
Neg logit contributions | |
Palest | -0.193 |
anon | -0.175 |
Bey | -0.173 |
ILLE | -0.167 |
audi | -0.163 |
Token | still |
Token ID | 991 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
イト | +1.653 |
ー� | +1.595 |
checks | +1.564 |
roup | +1.542 |
ゴン | +1.538 |
Neg logit contributions | |
Palest | -2.432 |
anon | -2.166 |
Bey | -2.134 |
ILLE | -2.048 |
audi | -1.978 |
Token | end |
Token ID | 886 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Palest | +1.978 |
anon | +1.718 |
Bey | +1.683 |
ILLE | +1.581 |
audi | +1.516 |
Neg logit contributions | |
イト | -2.187 |
ー� | -2.110 |
ゴン | -2.096 |
checks | -2.071 |
roup | -2.061 |
Token | to |
Token ID | 284 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
Palest | +1.187 |
anon | +1.030 |
Bey | +1.012 |
ILLE | +0.951 |
audi | +0.915 |
Neg logit contributions | |
イト | -1.252 |
ー� | -1.203 |
ゴン | -1.198 |
checks | -1.189 |
roup | -1.183 |
Token | the |
Token ID | 262 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
Palest | +0.715 |
anon | +0.636 |
Bey | +0.625 |
ILLE | +0.596 |
audi | +0.577 |
Neg logit contributions | |
イト | -0.560 |
ー� | -0.539 |
ゴン | -0.530 |
checks | -0.527 |
roup | -0.526 |
Token | policy |
Token ID | 2450 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Palest | +0.649 |
anon | +0.570 |
Bey | +0.560 |
ILLE | +0.530 |
audi | +0.510 |
Neg logit contributions | |
イト | -0.634 |
ー� | -0.615 |
ゴン | -0.604 |
checks | -0.602 |
roup | -0.600 |
Token | of |
Token ID | 286 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
イト | +0.455 |
ー� | +0.442 |
ゴン | +0.433 |
checks | +0.433 |
roup | +0.432 |
Neg logit contributions | |
Palest | -0.470 |
anon | -0.413 |
Bey | -0.406 |
ILLE | -0.386 |
audi | -0.372 |
Token | apartheid |
Token ID | 38264 |
Feature activation | -9.71e+00 |
Pos logit contributions | |
Palest | +1.379 |
anon | +1.204 |
Bey | +1.181 |
ILLE | +1.118 |
audi | +1.077 |
Neg logit contributions | |
イト | -1.354 |
ー� | -1.307 |
ゴン | -1.292 |
checks | -1.280 |
roup | -1.279 |
Token | in |
Token ID | 287 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Palest | +6.874 |
anon | +5.838 |
Bey | +5.562 |
ILLE | +5.228 |
heid | +5.124 |
Neg logit contributions | |
イト | -7.257 |
ゴン | -7.011 |
ー� | -6.899 |
plet | -6.826 |
checks | -6.754 |
Token | South |
Token ID | 2520 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
Palest | +1.030 |
anon | +0.905 |
Bey | +0.888 |
ILLE | +0.844 |
audi | +0.816 |
Neg logit contributions | |
イト | -0.901 |
ー� | -0.867 |
ゴン | -0.858 |
checks | -0.848 |
roup | -0.848 |
Token | Africa |
Token ID | 5478 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Palest | +1.835 |
anon | +1.267 |
Bey | +1.194 |
ILLE | +0.986 |
audi | +0.886 |
Neg logit contributions | |
イト | -6.168 |
ゴン | -6.034 |
ー� | -6.005 |
checks | -5.927 |
roup | -5.899 |
Token | it |
Token ID | 340 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Palest | +0.171 |
anon | +0.152 |
Bey | +0.149 |
ILLE | +0.142 |
audi | +0.137 |
Neg logit contributions | |
イト | -0.145 |
ー� | -0.140 |
ゴン | -0.138 |
checks | -0.137 |
roup | -0.136 |
Token | would |
Token ID | 561 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
イト | +1.085 |
ー� | +1.049 |
checks | +1.022 |
ゴン | +1.019 |
roup | +1.015 |
Neg logit contributions | |
Palest | -1.444 |
anon | -1.281 |
Bey | -1.264 |
ILLE | -1.208 |
audi | -1.166 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
イト | +0.034 |
ー� | +0.033 |
ゴン | +0.033 |
checks | +0.032 |
roup | +0.032 |
Neg logit contributions | |
Palest | -0.045 |
anon | -0.040 |
Bey | -0.039 |
ILLE | -0.037 |
audi | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
イト | +2.317 |
roup | +2.255 |
ー� | +2.255 |
safety | +2.242 |
checks | +2.228 |
Neg logit contributions | |
Palest | -3.415 |
anon | -3.076 |
Bey | -3.076 |
ILLE | -2.941 |
audi | -2.812 |
Token |
|
Token ID | 198 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
イト | +0.117 |
ー� | +0.113 |
ゴン | +0.111 |
roup | +0.111 |
checks | +0.111 |
Neg logit contributions | |
Palest | -0.116 |
anon | -0.101 |
Bey | -0.099 |
ILLE | -0.094 |
audi | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
Palest | +0.290 |
anon | +0.246 |
Bey | +0.242 |
ILLE | +0.233 |
audi | +0.224 |
Neg logit contributions | |
イト | -0.259 |
ー� | -0.254 |
checks | -0.250 |
roup | -0.248 |
safety | -0.246 |
Token | A |
Token ID | 32 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
Palest | +0.565 |
anon | +0.488 |
Bey | +0.477 |
ILLE | +0.452 |
audi | +0.436 |
Neg logit contributions | |
イト | -0.584 |
ー� | -0.568 |
ゴン | -0.557 |
checks | -0.557 |
roup | -0.556 |
Token | BBC |
Token ID | 7823 |
Feature activation | -9.70e+00 |
Pos logit contributions | |
イト | +0.168 |
ー� | +0.162 |
ゴン | +0.159 |
roup | +0.159 |
checks | +0.159 |
Neg logit contributions | |
Palest | -0.194 |
anon | -0.171 |
Bey | -0.169 |
ILLE | -0.160 |
audi | -0.155 |
Token | correspondent |
Token ID | 21076 |
Feature activation | -8.45e+00 |
Pos logit contributions | |
Palest | +7.038 |
anon | +6.183 |
Bey | +5.852 |
ILLE | +5.749 |
audi | +5.637 |
Neg logit contributions | |
イト | -7.048 |
ゴン | -6.832 |
ー� | -6.555 |
checks | -6.528 |
peror | -6.509 |
Token | in |
Token ID | 287 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
Palest | +5.711 |
anon | +5.015 |
Bey | +4.746 |
audi | +4.463 |
ILLE | +4.433 |
Neg logit contributions | |
ゴン | -6.530 |
イト | -6.515 |
ー� | -6.241 |
warts | -6.043 |
roup | -6.039 |
Token | Somalia |
Token ID | 23918 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Palest | +2.933 |
anon | +2.469 |
Bey | +2.392 |
ILLE | +2.202 |
audi | +2.133 |
Neg logit contributions | |
イト | -3.981 |
ゴン | -3.858 |
ー� | -3.811 |
roup | -3.747 |
checks | -3.739 |
Token | says |
Token ID | 1139 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
Palest | +1.513 |
anon | +1.327 |
Bey | +1.298 |
ILLE | +1.228 |
audi | +1.185 |
Neg logit contributions | |
イト | -1.483 |
ー� | -1.431 |
ゴン | -1.417 |
roup | -1.398 |
checks | -1.398 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Palest | +3.694 |
anon | +3.202 |
Bey | +3.176 |
ILLE | +2.990 |
audi | +2.906 |
Neg logit contributions | |
イト | -3.049 |
ゴン | -2.948 |
ー� | -2.868 |
roup | -2.797 |
warts | -2.778 |
Token | the |
Token ID | 262 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
Palest | +0.623 |
anon | +0.554 |
Bey | +0.545 |
ILLE | +0.521 |
audi | +0.505 |
Neg logit contributions | |
イト | -0.456 |
ー� | -0.438 |
ゴン | -0.433 |
checks | -0.427 |
roup | -0.427 |
Token | Mag |
Token ID | 2944 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
Palest | +0.779 |
anon | +0.690 |
Bey | +0.679 |
ILLE | +0.649 |
audi | +0.629 |
Neg logit contributions | |
イト | -0.586 |
ー� | -0.562 |
ゴン | -0.557 |
roup | -0.549 |
checks | -0.549 |
Token | i |
Token ID | 72 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Palest | +0.301 |
anon | +0.247 |
Bey | +0.240 |
ILLE | +0.220 |
audi | +0.208 |
Neg logit contributions | |
イト | -0.561 |
ー� | -0.546 |
ゴン | -0.543 |
checks | -0.538 |
roup | -0.537 |
Token | is |
Token ID | 318 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Palest | +2.000 |
anon | +1.753 |
Bey | +1.719 |
ILLE | +1.649 |
audi | +1.591 |
Neg logit contributions | |
イト | -1.677 |
ー� | -1.612 |
ゴン | -1.612 |
roup | -1.571 |
checks | -1.566 |
Token | CAS |
Token ID | 35106 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
Palest | +2.016 |
anon | +1.766 |
Bey | +1.739 |
ILLE | +1.670 |
audi | +1.605 |
Neg logit contributions | |
イト | -1.630 |
ゴン | -1.566 |
ー� | -1.564 |
checks | -1.533 |
roup | -1.531 |
Token | PAR |
Token ID | 27082 |
Feature activation | -9.68e+00 |
Pos logit contributions | |
Palest | +4.835 |
anon | +4.169 |
Bey | +4.037 |
ILLE | +4.002 |
audi | +3.718 |
Neg logit contributions | |
イト | -4.784 |
ー� | -4.620 |
ゴン | -4.619 |
roup | -4.497 |
checks | -4.481 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Palest | +7.019 |
anon | +6.075 |
ILLE | +5.929 |
Bey | +5.884 |
IAN | +5.530 |
Neg logit contributions | |
イト | -6.924 |
ゴン | -6.817 |
ー� | -6.648 |
checks | -6.432 |
roup | -6.418 |
Token | and |
Token ID | 290 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Palest | +1.089 |
anon | +0.959 |
Bey | +0.942 |
ILLE | +0.898 |
audi | +0.867 |
Neg logit contributions | |
イト | -0.910 |
ー� | -0.876 |
ゴン | -0.869 |
roup | -0.857 |
checks | -0.856 |
Token | � |
Token ID | 564 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
イト | +0.086 |
ー� | +0.082 |
ゴン | +0.081 |
checks | +0.080 |
roup | +0.080 |
Neg logit contributions | |
Palest | -0.109 |
anon | -0.097 |
Bey | -0.095 |
ILLE | -0.091 |
audi | -0.088 |
Token | � |
Token ID | 246 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Palest | +1.309 |
anon | +1.187 |
Bey | +1.167 |
ILLE | +1.128 |
audi | +1.098 |
Neg logit contributions | |
イト | -0.630 |
ー� | -0.598 |
ゴン | -0.590 |
checks | -0.585 |
roup | -0.581 |
Token | box |
Token ID | 3524 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Palest | +0.183 |
anon | +0.160 |
Bey | +0.157 |
ILLE | +0.148 |
audi | +0.143 |
Neg logit contributions | |
イト | -0.189 |
ー� | -0.182 |
ゴン | -0.180 |
checks | -0.179 |
roup | -0.179 |
Token | the |
Token ID | 262 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
イト | +0.335 |
ー� | +0.322 |
ゴン | +0.316 |
checks | +0.315 |
roup | +0.314 |
Neg logit contributions | |
Palest | -0.448 |
anon | -0.399 |
Bey | -0.393 |
ILLE | -0.375 |
audi | -0.363 |
Token | Liberal |
Token ID | 12266 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Palest | +0.306 |
anon | +0.269 |
Bey | +0.264 |
ILLE | +0.250 |
audi | +0.242 |
Neg logit contributions | |
イト | -0.275 |
ー� | -0.266 |
ゴン | -0.262 |
checks | -0.260 |
roup | -0.260 |
Token | party |
Token ID | 2151 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
Palest | +0.994 |
anon | +0.891 |
Bey | +0.878 |
ILLE | +0.839 |
audi | +0.817 |
Neg logit contributions | |
イト | -0.618 |
ー� | -0.593 |
ゴン | -0.586 |
checks | -0.579 |
roup | -0.575 |
Token | . |
Token ID | 13 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
Palest | +0.405 |
anon | +0.358 |
Bey | +0.352 |
ILLE | +0.335 |
audi | +0.324 |
Neg logit contributions | |
イト | -0.339 |
ー� | -0.327 |
ゴン | -0.323 |
checks | -0.320 |
roup | -0.319 |
Token | How |
Token ID | 1374 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
イト | +0.574 |
ー� | +0.556 |
roup | +0.539 |
checks | +0.538 |
ゴン | +0.534 |
Neg logit contributions | |
Palest | -0.622 |
anon | -0.548 |
Bey | -0.536 |
ILLE | -0.515 |
audi | -0.499 |
Token | can |
Token ID | 460 |
Feature activation | -9.68e+00 |
Pos logit contributions | |
Palest | +2.928 |
anon | +2.570 |
Bey | +2.507 |
ILLE | +2.384 |
audi | +2.310 |
Neg logit contributions | |
イト | -2.637 |
ー� | -2.564 |
ゴン | -2.560 |
checks | -2.491 |
roup | -2.477 |
Token | I |
Token ID | 314 |
Feature activation | -8.33e+00 |
Pos logit contributions | |
Palest | +7.070 |
anon | +6.133 |
Bey | +6.031 |
Orwell | +5.559 |
audi | +5.515 |
Neg logit contributions | |
ゴン | -6.717 |
イト | -6.605 |
ー� | -6.442 |
checks | -6.314 |
plet | -6.227 |
Token | be |
Token ID | 307 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
Palest | +6.095 |
anon | +5.602 |
Bey | +5.447 |
audi | +4.919 |
Interpret | +4.918 |
Neg logit contributions | |
イト | -5.789 |
ゴン | -5.738 |
ー� | -5.437 |
checks | -5.432 |
peror | -5.337 |
Token | so |
Token ID | 523 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
Palest | +3.057 |
anon | +2.628 |
Bey | +2.605 |
ILLE | +2.445 |
audi | +2.353 |
Neg logit contributions | |
イト | -3.245 |
ー� | -3.139 |
ゴン | -3.131 |
checks | -3.096 |
roup | -3.095 |
Token | sure |
Token ID | 1654 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
Palest | +4.732 |
anon | +4.015 |
Bey | +3.976 |
ILLE | +3.760 |
audi | +3.557 |
Neg logit contributions | |
イト | -5.635 |
ゴン | -5.522 |
ー� | -5.458 |
roup | -5.372 |
checks | -5.369 |
Token | ? |
Token ID | 30 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
Palest | +2.902 |
anon | +2.517 |
Bey | +2.478 |
ILLE | +2.327 |
audi | +2.251 |
Neg logit contributions | |
イト | -2.949 |
ゴン | -2.867 |
ー� | -2.864 |
roup | -2.817 |
checks | -2.805 |
Token | . |
Token ID | 13 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
イト | +0.144 |
ー� | +0.139 |
ゴン | +0.136 |
checks | +0.136 |
roup | +0.135 |
Neg logit contributions | |
Palest | -0.176 |
anon | -0.156 |
Bey | -0.154 |
ILLE | -0.146 |
audi | -0.141 |
Token |
|
Token ID | 198 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Palest | +0.291 |
anon | +0.258 |
Bey | +0.253 |
ILLE | +0.242 |
audi | +0.232 |
Neg logit contributions | |
イト | -0.266 |
ー� | -0.259 |
ゴン | -0.252 |
checks | -0.251 |
roup | -0.251 |
Token |
|
Token ID | 198 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
Palest | +0.195 |
anon | +0.165 |
Bey | +0.163 |
ILLE | +0.157 |
audi | +0.151 |
Neg logit contributions | |
イト | -0.174 |
ー� | -0.170 |
checks | -0.168 |
roup | -0.166 |
safety | -0.165 |
Token | Just |
Token ID | 5703 |
Feature activation | -7.09e+00 |
Pos logit contributions | |
Palest | +0.329 |
anon | +0.285 |
Bey | +0.279 |
ILLE | +0.266 |
audi | +0.256 |
Neg logit contributions | |
イト | -0.324 |
ー� | -0.314 |
ゴン | -0.308 |
checks | -0.307 |
roup | -0.306 |
Token | five |
Token ID | 1936 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Palest | +5.295 |
anon | +4.626 |
Bey | +4.599 |
ILLE | +4.339 |
audi | +4.226 |
Neg logit contributions | |
イト | -4.903 |
ゴン | -4.802 |
ー� | -4.687 |
roup | -4.622 |
checks | -4.620 |
Token | years |
Token ID | 812 |
Feature activation | -9.67e+00 |
Pos logit contributions | |
Palest | +1.412 |
anon | +1.276 |
Bey | +1.257 |
ILLE | +1.208 |
audi | +1.175 |
Neg logit contributions | |
イト | -0.754 |
ー� | -0.720 |
ゴン | -0.705 |
checks | -0.698 |
roup | -0.696 |
Token | later |
Token ID | 1568 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
Palest | +6.213 |
anon | +5.350 |
Bey | +5.102 |
ILLE | +4.873 |
audi | +4.753 |
Neg logit contributions | |
イト | -7.715 |
ゴン | -7.574 |
ー� | -7.365 |
plet | -7.252 |
checks | -7.139 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Palest | +2.788 |
anon | +2.419 |
Bey | +2.370 |
ILLE | +2.253 |
audi | +2.210 |
Neg logit contributions | |
イト | -2.412 |
ー� | -2.311 |
ゴン | -2.298 |
checks | -2.260 |
roup | -2.252 |
Token | in |
Token ID | 287 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
イト | +0.986 |
ー� | +0.956 |
safety | +0.938 |
checks | +0.934 |
roup | +0.933 |
Neg logit contributions | |
Palest | -1.181 |
anon | -1.056 |
Bey | -1.038 |
ILLE | -0.994 |
audi | -0.948 |
Token | 1976 |
Token ID | 15408 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
イト | +0.746 |
ー� | +0.728 |
safety | +0.713 |
checks | +0.711 |
roup | +0.706 |
Neg logit contributions | |
Palest | -0.849 |
anon | -0.752 |
Bey | -0.742 |
ILLE | -0.713 |
audi | -0.678 |
Token | , |
Token ID | 11 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Palest | +3.410 |
anon | +2.961 |
Bey | +2.903 |
ILLE | +2.745 |
audi | +2.687 |
Neg logit contributions | |
イト | -3.004 |
ー� | -2.847 |
ゴン | -2.847 |
checks | -2.813 |
roup | -2.802 |
Token | - |
Token ID | 12 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
イト | +1.801 |
ー� | +1.748 |
ゴン | +1.719 |
checks | +1.706 |
roup | +1.705 |
Neg logit contributions | |
Palest | -1.759 |
anon | -1.531 |
Bey | -1.506 |
ILLE | -1.420 |
audi | -1.367 |
Token | x |
Token ID | 87 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Palest | +0.220 |
anon | +0.191 |
Bey | +0.186 |
ILLE | +0.174 |
audi | +0.167 |
Neg logit contributions | |
イト | -0.275 |
ー� | -0.267 |
ゴン | -0.265 |
roup | -0.262 |
checks | -0.261 |
Token | ), |
Token ID | 828 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
イト | +0.281 |
ー� | +0.270 |
ゴン | +0.266 |
checks | +0.264 |
roup | +0.263 |
Neg logit contributions | |
Palest | -0.369 |
anon | -0.329 |
Bey | -0.323 |
ILLE | -0.307 |
audi | -0.298 |
Token | and |
Token ID | 290 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
Palest | +0.934 |
anon | +0.824 |
Bey | +0.808 |
ILLE | +0.766 |
audi | +0.742 |
Neg logit contributions | |
イト | -0.826 |
ー� | -0.796 |
ゴン | -0.790 |
checks | -0.776 |
roup | -0.776 |
Token | using |
Token ID | 1262 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Palest | +0.506 |
anon | +0.448 |
Bey | +0.439 |
ILLE | +0.418 |
audi | +0.404 |
Neg logit contributions | |
イト | -0.416 |
ー� | -0.400 |
ゴン | -0.397 |
roup | -0.389 |
checks | -0.388 |
Token | par |
Token ID | 1582 |
Feature activation | -9.67e+00 |
Pos logit contributions | |
イト | +0.127 |
ー� | +0.122 |
ゴン | +0.121 |
checks | +0.120 |
roup | +0.119 |
Neg logit contributions | |
Palest | -0.160 |
anon | -0.142 |
Bey | -0.140 |
ILLE | -0.133 |
audi | -0.129 |
Token | av |
Token ID | 615 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Palest | +7.184 |
anon | +6.554 |
Bey | +6.065 |
audio | +6.046 |
ILLE | +5.923 |
Neg logit contributions | |
イト | -6.484 |
ゴン | -6.276 |
ー� | -6.223 |
warts | -5.976 |
roup | -5.953 |
Token | irt |
Token ID | 2265 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
Palest | +1.344 |
anon | +1.205 |
Bey | +1.163 |
ILLE | +1.128 |
audio | +1.084 |
Neg logit contributions | |
イト | -1.043 |
ー� | -0.995 |
ゴン | -0.990 |
checks | -0.968 |
roup | -0.957 |
Token | drivers |
Token ID | 6643 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
Palest | +0.380 |
anon | +0.336 |
Bey | +0.331 |
ILLE | +0.314 |
audi | +0.304 |
Neg logit contributions | |
イト | -0.317 |
ー� | -0.306 |
ゴン | -0.301 |
checks | -0.299 |
roup | -0.298 |
Token | for |
Token ID | 329 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
Palest | +2.242 |
anon | +1.970 |
Bey | +1.919 |
ILLE | +1.821 |
audi | +1.765 |
Neg logit contributions | |
イト | -2.124 |
ー� | -2.033 |
ゴン | -2.022 |
roup | -1.982 |
checks | -1.977 |
Token | network |
Token ID | 3127 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Palest | +3.249 |
anon | +2.883 |
Bey | +2.801 |
ILLE | +2.714 |
audi | +2.616 |
Neg logit contributions | |
イト | -2.548 |
ゴン | -2.440 |
ー� | -2.420 |
roup | -2.375 |
checks | -2.334 |
Token | exercise |
Token ID | 5517 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Palest | +1.034 |
anon | +0.882 |
Bey | +0.862 |
ILLE | +0.806 |
audi | +0.771 |
Neg logit contributions | |
イト | -1.379 |
ー� | -1.340 |
ゴン | -1.324 |
checks | -1.316 |
roup | -1.315 |
Token | to |
Token ID | 284 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
イト | +0.270 |
ー� | +0.261 |
checks | +0.256 |
roup | +0.256 |
ゴン | +0.255 |
Neg logit contributions | |
Palest | -0.326 |
anon | -0.288 |
Bey | -0.284 |
ILLE | -0.271 |
audi | -0.262 |
Token | prepare |
Token ID | 8335 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Palest | +0.800 |
anon | +0.713 |
Bey | +0.700 |
ILLE | +0.668 |
audi | +0.646 |
Neg logit contributions | |
イト | -0.593 |
ゴン | -0.566 |
ー� | -0.566 |
checks | -0.553 |
roup | -0.550 |
Token | our |
Token ID | 674 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
Palest | +0.923 |
anon | +0.812 |
Bey | +0.797 |
ILLE | +0.756 |
audi | +0.729 |
Neg logit contributions | |
イト | -0.819 |
ー� | -0.785 |
ゴン | -0.785 |
checks | -0.765 |
roup | -0.765 |
Token | military |
Token ID | 2422 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
Palest | +2.142 |
anon | +1.894 |
Bey | +1.854 |
ILLE | +1.762 |
audi | +1.683 |
Neg logit contributions | |
イト | -1.876 |
ゴン | -1.816 |
ー� | -1.787 |
roup | -1.749 |
checks | -1.737 |
Token | personnel |
Token ID | 8213 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
イト | +0.530 |
ー� | +0.513 |
checks | +0.504 |
roup | +0.502 |
ゴン | +0.500 |
Neg logit contributions | |
Palest | -0.650 |
anon | -0.574 |
Bey | -0.566 |
ILLE | -0.538 |
audi | -0.522 |
Token | for |
Token ID | 329 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
イト | +3.825 |
checks | +3.769 |
safety | +3.767 |
ー� | +3.759 |
roup | +3.679 |
Neg logit contributions | |
Palest | -5.418 |
anon | -4.821 |
Bey | -4.794 |
ILLE | -4.614 |
audi | -4.497 |
Token | foreign |
Token ID | 3215 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Palest | +0.215 |
anon | +0.191 |
Bey | +0.188 |
ILLE | +0.179 |
audi | +0.173 |
Neg logit contributions | |
イト | -0.161 |
ー� | -0.155 |
ゴン | -0.153 |
checks | -0.151 |
roup | -0.151 |
Token | engagements |
Token ID | 40588 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
Palest | +1.320 |
anon | +1.166 |
Bey | +1.147 |
ILLE | +1.088 |
audi | +1.052 |
Neg logit contributions | |
イト | -1.113 |
ゴン | -1.071 |
ー� | -1.064 |
roup | -1.041 |
checks | -1.036 |
Token | as |
Token ID | 355 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
イト | +2.034 |
ー� | +1.968 |
checks | +1.945 |
safety | +1.932 |
roup | +1.919 |
Neg logit contributions | |
Palest | -2.676 |
anon | -2.395 |
Bey | -2.369 |
ILLE | -2.263 |
audi | -2.201 |
Token | has |
Token ID | 468 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
イト | +0.790 |
ー� | +0.765 |
checks | +0.752 |
roup | +0.750 |
safety | +0.749 |
Neg logit contributions | |
Palest | -1.067 |
anon | -0.952 |
Bey | -0.934 |
ILLE | -0.893 |
audi | -0.866 |
Token | or |
Token ID | 393 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
イト | +1.801 |
ー� | +1.748 |
safety | +1.728 |
roup | +1.726 |
checks | +1.722 |
Neg logit contributions | |
Palest | -1.456 |
anon | -1.253 |
Bey | -1.230 |
ILLE | -1.149 |
audi | -1.097 |
Token | choose |
Token ID | 3853 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
イト | +1.054 |
ー� | +1.015 |
checks | +0.995 |
safety | +0.993 |
roup | +0.992 |
Neg logit contributions | |
Palest | -1.444 |
anon | -1.289 |
Bey | -1.275 |
ILLE | -1.212 |
audi | -1.173 |
Token | an |
Token ID | 281 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
イト | +2.261 |
ー� | +2.190 |
safety | +2.172 |
checks | +2.138 |
roup | +2.126 |
Neg logit contributions | |
Palest | -2.929 |
anon | -2.612 |
Bey | -2.610 |
ILLE | -2.453 |
audi | -2.369 |
Token | existing |
Token ID | 4683 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
イト | +0.434 |
ー� | +0.418 |
roup | +0.410 |
ゴン | +0.410 |
safety | +0.409 |
Neg logit contributions | |
Palest | -0.533 |
anon | -0.471 |
Bey | -0.468 |
ILLE | -0.440 |
audi | -0.426 |
Token | creepy |
Token ID | 23387 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
イト | +0.355 |
ー� | +0.342 |
roup | +0.334 |
ゴン | +0.334 |
checks | +0.333 |
Neg logit contributions | |
Palest | -0.518 |
anon | -0.462 |
Bey | -0.459 |
ILLE | -0.435 |
audi | -0.423 |
Token | monster |
Token ID | 9234 |
Feature activation | +9.64e+00 |
Pos logit contributions | |
イト | +1.795 |
ー� | +1.749 |
safety | +1.737 |
roup | +1.712 |
ゴン | +1.690 |
Neg logit contributions | |
Palest | -2.420 |
Bey | -2.148 |
anon | -2.141 |
ILLE | -2.012 |
audi | -1.970 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
safety | +5.571 |
イト | +5.459 |
ー� | +5.449 |
zilla | +5.430 |
roup | +5.345 |
Neg logit contributions | |
Palest | -8.049 |
anon | -7.083 |
Bey | -7.038 |
ILLE | -6.685 |
audi | -6.563 |
Token | focus |
Token ID | 2962 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
Palest | +0.108 |
anon | +0.096 |
Bey | +0.095 |
ILLE | +0.091 |
audi | +0.088 |
Neg logit contributions | |
イト | -0.075 |
ー� | -0.072 |
ゴン | -0.070 |
checks | -0.070 |
roup | -0.070 |
Token | heavily |
Token ID | 7272 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
イト | +2.656 |
ー� | +2.558 |
safety | +2.527 |
checks | +2.510 |
roup | +2.488 |
Neg logit contributions | |
Palest | -3.762 |
anon | -3.408 |
Bey | -3.356 |
ILLE | -3.181 |
audi | -3.087 |
Token | on |
Token ID | 319 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
イト | +0.248 |
ー� | +0.239 |
ゴン | +0.235 |
checks | +0.233 |
roup | +0.233 |
Neg logit contributions | |
Palest | -0.324 |
anon | -0.288 |
Bey | -0.283 |
ILLE | -0.270 |
audi | -0.261 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
イト | +0.974 |
ー� | +0.935 |
checks | +0.911 |
safety | +0.911 |
ゴン | +0.908 |
Neg logit contributions | |
Palest | -1.442 |
anon | -1.291 |
Bey | -1.278 |
ILLE | -1.214 |
audi | -1.182 |
Token | Ra |
Token ID | 7567 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
イト | +0.195 |
ー� | +0.189 |
ゴン | +0.186 |
checks | +0.185 |
roup | +0.185 |
Neg logit contributions | |
Palest | -0.198 |
anon | -0.174 |
Bey | -0.170 |
ILLE | -0.161 |
audi | -0.156 |
Token | ich |
Token ID | 488 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
イト | +1.469 |
ー� | +1.442 |
roup | +1.416 |
checks | +1.410 |
ゴン | +1.406 |
Neg logit contributions | |
Palest | -1.551 |
anon | -1.335 |
Bey | -1.320 |
ILLE | -1.262 |
audi | -1.200 |
Token | , |
Token ID | 11 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
イト | +3.304 |
ー� | +3.268 |
checks | +3.246 |
zilla | +3.194 |
safety | +3.190 |
Neg logit contributions | |
Palest | -3.661 |
Bey | -3.238 |
anon | -3.173 |
ILLE | -3.005 |
audi | -2.880 |
Token | a |
Token ID | 257 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
Palest | +0.348 |
anon | +0.308 |
Bey | +0.303 |
ILLE | +0.288 |
audi | +0.279 |
Neg logit contributions | |
イト | -0.283 |
ー� | -0.272 |
ゴン | -0.269 |
checks | -0.266 |
roup | -0.266 |
Token | leading |
Token ID | 3756 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
イト | +0.370 |
ー� | +0.356 |
ゴン | +0.351 |
checks | +0.348 |
roup | +0.348 |
Neg logit contributions | |
Palest | -0.446 |
anon | -0.395 |
Bey | -0.388 |
ILLE | -0.369 |
audi | -0.357 |
Token | marijuana |
Token ID | 5727 |
Feature activation | +6.94e+00 |
Pos logit contributions | |
Palest | +2.471 |
anon | +2.194 |
Bey | +2.143 |
ILLE | +2.032 |
audi | +1.980 |
Neg logit contributions | |
イト | -1.927 |
ゴン | -1.833 |
ー� | -1.831 |
checks | -1.814 |
roup | -1.799 |
Token | attorney |
Token ID | 6136 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
safety | +4.480 |
ー� | +4.397 |
イト | +4.385 |
ties | +4.190 |
roup | +4.168 |
Neg logit contributions | |
Palest | -5.586 |
Bey | -4.849 |
anon | -4.818 |
ILLE | -4.673 |
audi | -4.465 |
Token | most |
Token ID | 749 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
Palest | +1.690 |
anon | +1.494 |
Bey | +1.467 |
ILLE | +1.388 |
audi | +1.357 |
Neg logit contributions | |
イト | -1.374 |
ー� | -1.319 |
ゴン | -1.306 |
checks | -1.287 |
roup | -1.285 |
Token | remarkable |
Token ID | 11004 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Palest | +2.738 |
anon | +2.433 |
Bey | +2.404 |
ILLE | +2.263 |
audi | +2.220 |
Neg logit contributions | |
イト | -2.125 |
ー� | -2.029 |
ゴン | -2.023 |
roup | -1.987 |
checks | -1.955 |
Token | for |
Token ID | 329 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Palest | +1.243 |
anon | +1.087 |
Bey | +1.072 |
ILLE | +1.016 |
audi | +0.983 |
Neg logit contributions | |
イト | -1.152 |
ー� | -1.107 |
ゴン | -1.103 |
roup | -1.084 |
checks | -1.079 |
Token | his |
Token ID | 465 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
Palest | +0.103 |
anon | +0.092 |
Bey | +0.091 |
ILLE | +0.087 |
audi | +0.084 |
Neg logit contributions | |
イト | -0.064 |
ー� | -0.061 |
ゴン | -0.060 |
checks | -0.059 |
roup | -0.059 |
Token | of |
Token ID | 286 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
Palest | +0.310 |
anon | +0.273 |
Bey | +0.267 |
ILLE | +0.253 |
audi | +0.244 |
Neg logit contributions | |
イト | -0.294 |
ー� | -0.283 |
ゴン | -0.282 |
roup | -0.277 |
checks | -0.276 |
Token | the |
Token ID | 262 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
イト | +0.457 |
ー� | +0.442 |
ゴン | +0.434 |
checks | +0.432 |
roup | +0.432 |
Neg logit contributions | |
Palest | -0.582 |
anon | -0.517 |
Bey | -0.508 |
ILLE | -0.483 |
audi | -0.469 |
Token | utility |
Token ID | 10361 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
Palest | +0.231 |
anon | +0.206 |
Bey | +0.202 |
ILLE | +0.193 |
audi | +0.187 |
Neg logit contributions | |
イト | -0.173 |
ー� | -0.166 |
ゴン | -0.164 |
checks | -0.162 |
roup | -0.162 |
Token | will |
Token ID | 481 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
イト | +2.392 |
ー� | +2.342 |
safety | +2.340 |
checks | +2.340 |
roup | +2.267 |
Neg logit contributions | |
Palest | -3.382 |
anon | -3.003 |
Bey | -2.977 |
ILLE | -2.838 |
audi | -2.753 |
Token | mean |
Token ID | 1612 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
イト | +0.108 |
ー� | +0.103 |
ゴン | +0.102 |
roup | +0.100 |
checks | +0.100 |
Neg logit contributions | |
Palest | -0.153 |
anon | -0.138 |
Bey | -0.135 |
ILLE | -0.129 |
audi | -0.125 |
Token | cuts |
Token ID | 6630 |
Feature activation | +6.94e+00 |
Pos logit contributions | |
イト | +1.739 |
ー� | +1.684 |
checks | +1.653 |
safety | +1.647 |
roup | +1.639 |
Neg logit contributions | |
Palest | -2.612 |
anon | -2.346 |
Bey | -2.312 |
ILLE | -2.194 |
audi | -2.148 |
Token | . |
Token ID | 13 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
イト | +4.333 |
safety | +4.301 |
checks | +4.267 |
ー� | +4.244 |
roup | +4.184 |
Neg logit contributions | |
Palest | -5.618 |
anon | -5.030 |
Bey | -4.984 |
ILLE | -4.739 |
audi | -4.519 |
Token |
|
Token ID | 198 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
イト | +0.279 |
ー� | +0.271 |
ゴン | +0.265 |
roup | +0.265 |
checks | +0.264 |
Neg logit contributions | |
Palest | -0.283 |
anon | -0.248 |
Bey | -0.243 |
ILLE | -0.230 |
audi | -0.222 |
Token |
|
Token ID | 198 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
イト | +0.581 |
ー� | +0.575 |
checks | +0.568 |
roup | +0.562 |
safety | +0.560 |
Neg logit contributions | |
Palest | -0.697 |
anon | -0.582 |
Bey | -0.576 |
ILLE | -0.557 |
audi | -0.536 |
Token | K |
Token ID | 42 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
イト | +0.202 |
ー� | +0.196 |
checks | +0.192 |
ゴン | +0.192 |
roup | +0.192 |
Neg logit contributions | |
Palest | -0.212 |
anon | -0.183 |
Bey | -0.179 |
ILLE | -0.170 |
audi | -0.164 |
Token | el |
Token ID | 417 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Palest | +3.120 |
anon | +2.845 |
Bey | +2.736 |
ILLE | +2.667 |
audi | +2.528 |
Neg logit contributions | |
イト | -3.066 |
ゴン | -2.970 |
ー� | -2.936 |
checks | -2.862 |
roup | -2.821 |
Token | will |
Token ID | 481 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
イト | +3.118 |
ー� | +3.063 |
safety | +3.061 |
checks | +2.984 |
roup | +2.973 |
Neg logit contributions | |
Palest | -4.153 |
anon | -3.696 |
Bey | -3.658 |
ILLE | -3.475 |
audi | -3.393 |
Token | be |
Token ID | 307 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
イト | +1.311 |
ー� | +1.269 |
roup | +1.230 |
checks | +1.229 |
safety | +1.221 |
Neg logit contributions | |
Palest | -2.151 |
anon | -1.925 |
Bey | -1.901 |
ILLE | -1.824 |
audi | -1.765 |
Token | in |
Token ID | 287 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
イト | +2.067 |
ー� | +2.005 |
checks | +1.970 |
safety | +1.961 |
roup | +1.952 |
Neg logit contributions | |
Palest | -2.781 |
anon | -2.491 |
Bey | -2.443 |
ILLE | -2.340 |
audi | -2.269 |
Token | pretty |
Token ID | 2495 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
イト | +1.382 |
ー� | +1.341 |
checks | +1.307 |
ゴン | +1.305 |
safety | +1.300 |
Neg logit contributions | |
Palest | -1.982 |
anon | -1.768 |
Bey | -1.741 |
ILLE | -1.669 |
audi | -1.615 |
Token | good |
Token ID | 922 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Palest | +0.260 |
anon | +0.233 |
Bey | +0.228 |
ILLE | +0.219 |
audi | +0.212 |
Neg logit contributions | |
イト | -0.180 |
ー� | -0.171 |
ゴン | -0.170 |
checks | -0.167 |
roup | -0.167 |
Token | shape |
Token ID | 5485 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
イト | +0.928 |
ー� | +0.884 |
ゴン | +0.862 |
checks | +0.857 |
roup | +0.855 |
Neg logit contributions | |
Palest | -1.903 |
anon | -1.725 |
Bey | -1.701 |
ILLE | -1.637 |
audi | -1.595 |
Token | next |
Token ID | 1306 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
イト | +3.787 |
ー� | +3.714 |
checks | +3.695 |
safety | +3.669 |
roup | +3.574 |
Neg logit contributions | |
Palest | -5.310 |
anon | -4.756 |
Bey | -4.659 |
ILLE | -4.471 |
audi | -4.360 |
Token | offseason |
Token ID | 16349 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
イト | +2.878 |
ー� | +2.813 |
safety | +2.787 |
checks | +2.752 |
roup | +2.743 |
Neg logit contributions | |
Palest | -6.045 |
anon | -5.494 |
Bey | -5.418 |
ILLE | -5.222 |
oire | -5.043 |
Token | . |
Token ID | 13 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
イト | +3.348 |
ー� | +3.266 |
checks | +3.211 |
safety | +3.174 |
roup | +3.146 |
Neg logit contributions | |
Palest | -4.791 |
Bey | -4.264 |
anon | -4.259 |
ILLE | -4.056 |
audi | -3.919 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
イト | +1.692 |
ー� | +1.644 |
checks | +1.600 |
ゴン | +1.590 |
roup | +1.589 |
Neg logit contributions | |
Palest | -1.838 |
anon | -1.614 |
Bey | -1.581 |
ILLE | -1.512 |
audi | -1.463 |
Token |
|
Token ID | 198 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
イト | +0.716 |
ー� | +0.708 |
checks | +0.699 |
roup | +0.687 |
safety | +0.686 |
Neg logit contributions | |
Palest | -0.858 |
anon | -0.715 |
Bey | -0.709 |
ILLE | -0.683 |
audi | -0.660 |
Token | them |
Token ID | 606 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
Palest | +3.560 |
anon | +3.055 |
Bey | +2.940 |
ILLE | +2.776 |
oire | +2.634 |
Neg logit contributions | |
イト | -4.615 |
ゴン | -4.530 |
ー� | -4.435 |
checks | -4.328 |
roup | -4.316 |
Token | how |
Token ID | 703 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
イト | +0.365 |
ー� | +0.353 |
checks | +0.347 |
safety | +0.346 |
roup | +0.345 |
Neg logit contributions | |
Palest | -0.399 |
anon | -0.351 |
Bey | -0.346 |
ILLE | -0.327 |
audi | -0.318 |
Token | to |
Token ID | 284 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Palest | +3.417 |
anon | +2.990 |
Bey | +2.902 |
ILLE | +2.766 |
ł | +2.603 |
Neg logit contributions | |
イト | -3.853 |
ゴン | -3.731 |
ー� | -3.722 |
roup | -3.654 |
checks | -3.639 |
Token | thread |
Token ID | 4704 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Palest | +1.845 |
anon | +1.655 |
Bey | +1.612 |
ILLE | +1.538 |
audi | +1.485 |
Neg logit contributions | |
イト | -1.532 |
ゴン | -1.464 |
ー� | -1.462 |
checks | -1.429 |
roup | -1.419 |
Token | a |
Token ID | 257 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Palest | +1.788 |
anon | +1.588 |
Bey | +1.555 |
ILLE | +1.487 |
audi | +1.430 |
Neg logit contributions | |
イト | -1.479 |
ー� | -1.422 |
ゴン | -1.414 |
roup | -1.387 |
checks | -1.386 |
Token | needle |
Token ID | 17598 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Palest | +1.149 |
anon | +1.024 |
Bey | +1.007 |
ILLE | +0.962 |
audi | +0.930 |
Neg logit contributions | |
イト | -0.837 |
ー� | -0.802 |
ゴン | -0.793 |
checks | -0.783 |
roup | -0.781 |
Token | : |
Token ID | 25 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
イト | +0.294 |
ー� | +0.286 |
safety | +0.281 |
checks | +0.281 |
roup | +0.281 |
Neg logit contributions | |
Palest | -0.286 |
anon | -0.247 |
Bey | -0.244 |
ILLE | -0.231 |
audi | -0.224 |
Token | Using |
Token ID | 8554 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
Palest | +0.704 |
anon | +0.618 |
Bey | +0.606 |
ILLE | +0.575 |
audi | +0.554 |
Neg logit contributions | |
イト | -0.664 |
ー� | -0.641 |
ゴン | -0.633 |
checks | -0.628 |
roup | -0.627 |
Token | a |
Token ID | 257 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
イト | +0.193 |
ー� | +0.187 |
checks | +0.182 |
ゴン | +0.182 |
roup | +0.182 |
Neg logit contributions | |
Palest | -0.248 |
anon | -0.220 |
Bey | -0.217 |
ILLE | -0.206 |
audi | -0.200 |
Token | needle |
Token ID | 17598 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
Palest | +0.678 |
anon | +0.598 |
Bey | +0.587 |
ILLE | +0.558 |
audi | +0.539 |
Neg logit contributions | |
イト | -0.580 |
ー� | -0.558 |
ゴン | -0.553 |
checks | -0.546 |
roup | -0.544 |
Token | thread |
Token ID | 4704 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
イト | +0.258 |
ー� | +0.249 |
ゴン | +0.244 |
checks | +0.244 |
roup | +0.243 |
Neg logit contributions | |
Palest | -0.311 |
anon | -0.274 |
Bey | -0.270 |
ILLE | -0.257 |
audi | -0.249 |
Token | : |
Token ID | 25 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
イト | +0.535 |
ー� | +0.517 |
ゴン | +0.508 |
checks | +0.506 |
roup | +0.503 |
Neg logit contributions | |
Palest | -0.636 |
anon | -0.562 |
Bey | -0.551 |
ILLE | -0.526 |
audi | -0.507 |
Token | possession |
Token ID | 7797 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
イト | +1.102 |
ー� | +1.063 |
safety | +1.038 |
checks | +1.037 |
ゴン | +1.036 |
Neg logit contributions | |
Palest | -1.401 |
anon | -1.248 |
Bey | -1.220 |
ILLE | -1.171 |
audi | -1.127 |
Token | of |
Token ID | 286 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Palest | +1.131 |
anon | +0.984 |
Bey | +0.968 |
ILLE | +0.910 |
audi | +0.878 |
Neg logit contributions | |
イト | -1.155 |
ー� | -1.116 |
ゴン | -1.107 |
roup | -1.095 |
checks | -1.092 |
Token | the |
Token ID | 262 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
Palest | +0.208 |
anon | +0.185 |
Bey | +0.182 |
ILLE | +0.173 |
audi | +0.168 |
Neg logit contributions | |
イト | -0.159 |
ー� | -0.153 |
ゴン | -0.150 |
checks | -0.149 |
roup | -0.149 |
Token | Energy |
Token ID | 6682 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
Palest | +0.585 |
anon | +0.517 |
Bey | +0.508 |
ILLE | +0.484 |
audi | +0.468 |
Neg logit contributions | |
イト | -0.487 |
ー� | -0.470 |
ゴン | -0.462 |
checks | -0.459 |
roup | -0.458 |
Token | Committee |
Token ID | 4606 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
イト | +0.235 |
ー� | +0.228 |
checks | +0.221 |
safety | +0.219 |
roup | +0.218 |
Neg logit contributions | |
Palest | -0.310 |
anon | -0.279 |
Bey | -0.275 |
ILLE | -0.264 |
audi | -0.255 |
Token | ga |
Token ID | 31986 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
イト | +0.903 |
ー� | +0.874 |
checks | +0.852 |
ゴン | +0.851 |
roup | +0.847 |
Neg logit contributions | |
Palest | -1.150 |
anon | -1.024 |
Bey | -1.004 |
ILLE | -0.962 |
audi | -0.927 |
Token | vel |
Token ID | 626 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Palest | +0.096 |
anon | +0.078 |
Bey | +0.075 |
ILLE | +0.068 |
audi | +0.063 |
Neg logit contributions | |
イト | -0.197 |
ー� | -0.192 |
ゴン | -0.191 |
checks | -0.189 |
roup | -0.189 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Palest | +0.535 |
anon | +0.473 |
Bey | +0.465 |
ILLE | +0.442 |
audi | +0.428 |
Neg logit contributions | |
イト | -0.450 |
ー� | -0.433 |
ゴン | -0.427 |
checks | -0.424 |
roup | -0.423 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Palest | +0.952 |
anon | +0.830 |
Bey | +0.816 |
ILLE | +0.770 |
audi | +0.741 |
Neg logit contributions | |
イト | -0.968 |
ー� | -0.934 |
ゴン | -0.926 |
checks | -0.918 |
roup | -0.916 |
Token |
|
Token ID | 198 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
Palest | +0.183 |
anon | +0.155 |
Bey | +0.153 |
ILLE | +0.146 |
audi | +0.141 |
Neg logit contributions | |
イト | -0.170 |
ー� | -0.166 |
checks | -0.163 |
roup | -0.162 |
safety | -0.161 |
Token | have |
Token ID | 423 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Palest | +0.277 |
anon | +0.244 |
Bey | +0.240 |
ILLE | +0.228 |
audi | +0.220 |
Neg logit contributions | |
イト | -0.238 |
ー� | -0.230 |
ゴン | -0.226 |
checks | -0.225 |
roup | -0.224 |
Token | used |
Token ID | 973 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
イト | +0.081 |
ー� | +0.078 |
ゴン | +0.077 |
checks | +0.076 |
roup | +0.076 |
Neg logit contributions | |
Palest | -0.122 |
anon | -0.109 |
Bey | -0.107 |
ILLE | -0.103 |
audi | -0.100 |
Token | it |
Token ID | 340 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
イト | +1.059 |
ー� | +1.021 |
ゴン | +0.999 |
checks | +0.997 |
safety | +0.992 |
Neg logit contributions | |
Palest | -1.387 |
anon | -1.236 |
Bey | -1.221 |
ILLE | -1.166 |
audi | -1.123 |
Token | , |
Token ID | 11 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
イト | +0.444 |
ー� | +0.429 |
ゴン | +0.421 |
checks | +0.420 |
roup | +0.418 |
Neg logit contributions | |
Palest | -0.520 |
anon | -0.460 |
Bey | -0.453 |
ILLE | -0.431 |
audi | -0.415 |
Token | like |
Token ID | 588 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
イト | +0.446 |
ー� | +0.430 |
checks | +0.421 |
ゴン | +0.418 |
roup | +0.417 |
Neg logit contributions | |
Palest | -0.593 |
anon | -0.530 |
Bey | -0.521 |
ILLE | -0.499 |
audi | -0.481 |
Token | the |
Token ID | 262 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
イト | +1.949 |
ー� | +1.885 |
ゴン | +1.845 |
checks | +1.841 |
safety | +1.836 |
Neg logit contributions | |
Palest | -2.376 |
anon | -2.123 |
Bey | -2.090 |
ILLE | -1.994 |
oire | -1.919 |
Token | Dis |
Token ID | 3167 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
イト | +0.404 |
ー� | +0.391 |
ゴン | +0.384 |
checks | +0.382 |
roup | +0.381 |
Neg logit contributions | |
Palest | -0.443 |
anon | -0.391 |
Bey | -0.384 |
ILLE | -0.365 |
audi | -0.351 |
Token | orient |
Token ID | 13989 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
イト | +0.940 |
ー� | +0.916 |
checks | +0.899 |
ゴン | +0.898 |
roup | +0.890 |
Neg logit contributions | |
Palest | -1.004 |
anon | -0.878 |
Bey | -0.864 |
ILLE | -0.825 |
audi | -0.793 |
Token | Pyramid |
Token ID | 41450 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
Palest | +1.989 |
anon | +1.760 |
Bey | +1.714 |
ILLE | +1.626 |
audi | +1.576 |
Neg logit contributions | |
イト | -1.846 |
ー� | -1.785 |
ゴン | -1.774 |
checks | -1.761 |
roup | -1.746 |
Token | . |
Token ID | 13 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
Palest | +2.077 |
anon | +1.829 |
Bey | +1.797 |
ILLE | +1.707 |
audi | +1.651 |
Neg logit contributions | |
イト | -1.833 |
ー� | -1.765 |
ゴン | -1.756 |
checks | -1.736 |
roup | -1.732 |
Token | Recently |
Token ID | 23413 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Palest | +0.454 |
anon | +0.398 |
Bey | +0.390 |
ILLE | +0.370 |
audi | +0.357 |
Neg logit contributions | |
イト | -0.440 |
ー� | -0.426 |
ゴン | -0.419 |
checks | -0.417 |
roup | -0.416 |
Token | has |
Token ID | 468 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
イト | +0.688 |
ー� | +0.665 |
ゴン | +0.652 |
checks | +0.652 |
roup | +0.650 |
Neg logit contributions | |
Palest | -0.904 |
anon | -0.802 |
Bey | -0.791 |
ILLE | -0.757 |
audi | -0.731 |
Token | not |
Token ID | 407 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
Palest | +0.788 |
anon | +0.699 |
Bey | +0.689 |
ILLE | +0.656 |
audi | +0.636 |
Neg logit contributions | |
イト | -0.563 |
ー� | -0.538 |
ゴン | -0.534 |
checks | -0.522 |
roup | -0.522 |
Token | spread |
Token ID | 4104 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Palest | +3.116 |
anon | +2.750 |
Bey | +2.702 |
ILLE | +2.538 |
audi | +2.482 |
Neg logit contributions | |
イト | -2.628 |
ゴン | -2.484 |
ー� | -2.469 |
checks | -2.417 |
warts | -2.401 |
Token | beyond |
Token ID | 3675 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
Palest | +1.797 |
anon | +1.574 |
Bey | +1.543 |
ILLE | +1.457 |
audi | +1.406 |
Neg logit contributions | |
イト | -1.708 |
ー� | -1.646 |
ゴン | -1.633 |
roup | -1.609 |
checks | -1.608 |
Token | Brazil |
Token ID | 7595 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Palest | +0.358 |
anon | +0.313 |
Bey | +0.307 |
ILLE | +0.290 |
audi | +0.279 |
Neg logit contributions | |
イト | -0.368 |
ー� | -0.356 |
ゴン | -0.351 |
checks | -0.349 |
roup | -0.349 |
Token | � |
Token ID | 447 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Palest | +1.513 |
anon | +1.334 |
Bey | +1.303 |
ILLE | +1.239 |
audi | +1.198 |
Neg logit contributions | |
イト | -1.301 |
ー� | -1.249 |
ゴン | -1.240 |
roup | -1.221 |
checks | -1.219 |
Token | � |
Token ID | 247 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
イト | +1.239 |
ー� | +1.203 |
ゴン | +1.156 |
� | +1.155 |
checks | +1.138 |
Neg logit contributions | |
Palest | -2.929 |
anon | -2.620 |
Bey | -2.602 |
ILLE | -2.506 |
audi | -2.435 |
Token | s |
Token ID | 82 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
イト | +0.929 |
ー� | +0.902 |
checks | +0.884 |
ゴン | +0.881 |
roup | +0.879 |
Neg logit contributions | |
Palest | -1.057 |
anon | -0.933 |
Bey | -0.918 |
ILLE | -0.876 |
audi | -0.841 |
Token | borders |
Token ID | 11637 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
イト | +0.280 |
ー� | +0.272 |
ゴン | +0.266 |
checks | +0.266 |
roup | +0.265 |
Neg logit contributions | |
Palest | -0.304 |
anon | -0.268 |
Bey | -0.264 |
ILLE | -0.251 |
audi | -0.240 |
Token | , |
Token ID | 11 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Palest | +2.651 |
anon | +2.327 |
Bey | +2.268 |
ILLE | +2.145 |
audi | +2.077 |
Neg logit contributions | |
イト | -2.364 |
ゴン | -2.262 |
ー� | -2.258 |
roup | -2.226 |
checks | -2.209 |
Token | it |
Token ID | 340 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
イト | +0.141 |
ー� | +0.135 |
ゴン | +0.132 |
checks | +0.132 |
roup | +0.132 |
Neg logit contributions | |
Palest | -0.201 |
anon | -0.180 |
Bey | -0.177 |
ILLE | -0.169 |
audi | -0.164 |
Token | the |
Token ID | 262 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
イト | +0.853 |
ー� | +0.831 |
checks | +0.804 |
ゴン | +0.804 |
safety | +0.799 |
Neg logit contributions | |
Palest | -1.137 |
anon | -1.009 |
Bey | -0.989 |
ILLE | -0.946 |
audi | -0.912 |
Token | New |
Token ID | 968 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
イト | +0.984 |
ー� | +0.964 |
safety | +0.936 |
checks | +0.928 |
ゴン | +0.922 |
Neg logit contributions | |
Palest | -1.321 |
anon | -1.179 |
Bey | -1.156 |
ILLE | -1.103 |
oire | -1.060 |
Token | A |
Token ID | 317 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
イト | +3.774 |
ー� | +3.751 |
ties | +3.626 |
checks | +3.540 |
safety | +3.534 |
Neg logit contributions | |
Palest | -4.623 |
anon | -4.072 |
Bey | -3.978 |
ILLE | -3.881 |
audi | -3.705 |
Token | ger |
Token ID | 1362 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
イト | +3.218 |
ー� | +3.189 |
roup | +3.153 |
plet | +3.093 |
checks | +3.088 |
Neg logit contributions | |
Palest | -3.087 |
anon | -2.681 |
Bey | -2.595 |
ILLE | -2.429 |
oire | -2.370 |
Token | � |
Token ID | 447 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
イト | +1.094 |
ー� | +1.060 |
ゴン | +1.037 |
roup | +1.033 |
checks | +1.031 |
Neg logit contributions | |
Palest | -1.168 |
anon | -1.022 |
Bey | -1.007 |
ILLE | -0.955 |
audi | -0.917 |
Token | � |
Token ID | 247 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Palest | +0.135 |
anon | +0.121 |
Bey | +0.119 |
ILLE | +0.114 |
audi | +0.111 |
Neg logit contributions | |
イト | -0.079 |
ー� | -0.075 |
ゴン | -0.074 |
checks | -0.073 |
roup | -0.073 |
Token | s |
Token ID | 82 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
イト | +1.024 |
ー� | +0.990 |
ゴン | +0.968 |
checks | +0.965 |
roup | +0.964 |
Neg logit contributions | |
Palest | -1.301 |
anon | -1.148 |
Bey | -1.133 |
ILLE | -1.079 |
audi | -1.041 |
Token | console |
Token ID | 8624 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Palest | +0.052 |
anon | +0.046 |
Bey | +0.046 |
ILLE | +0.044 |
audi | +0.042 |
Neg logit contributions | |
イト | -0.039 |
ー� | -0.037 |
ゴン | -0.037 |
checks | -0.037 |
roup | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Palest | +1.488 |
anon | +1.320 |
Bey | +1.302 |
ILLE | +1.239 |
audi | +1.202 |
Neg logit contributions | |
イト | -1.188 |
ー� | -1.133 |
ゴン | -1.127 |
roup | -1.116 |
checks | -1.111 |
Token | choice |
Token ID | 3572 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
Palest | +1.178 |
anon | +1.054 |
Bey | +1.037 |
ILLE | +0.991 |
audi | +0.963 |
Neg logit contributions | |
イト | -0.801 |
ー� | -0.764 |
ゴン | -0.758 |
roup | -0.750 |
checks | -0.746 |
Token | with |
Token ID | 351 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
イト | +3.328 |
ー� | +3.250 |
checks | +3.225 |
safety | +3.197 |
roup | +3.102 |
Neg logit contributions | |
Palest | -5.125 |
anon | -4.632 |
Bey | -4.546 |
ILLE | -4.368 |
audi | -4.170 |
Token | future |
Token ID | 2003 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
イト | +1.188 |
ー� | +1.151 |
safety | +1.135 |
checks | +1.132 |
roup | +1.117 |
Neg logit contributions | |
Palest | -1.474 |
anon | -1.306 |
Bey | -1.281 |
ILLE | -1.222 |
audi | -1.191 |
Token | of |
Token ID | 286 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Palest | +0.833 |
anon | +0.739 |
Bey | +0.728 |
ILLE | +0.692 |
audi | +0.667 |
Neg logit contributions | |
イト | -0.642 |
ー� | -0.617 |
ゴン | -0.616 |
roup | -0.601 |
checks | -0.594 |
Token | R |
Token ID | 371 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
イト | +1.142 |
ー� | +1.106 |
checks | +1.086 |
ゴン | +1.081 |
roup | +1.081 |
Neg logit contributions | |
Palest | -1.294 |
anon | -1.142 |
Bey | -1.122 |
ILLE | -1.063 |
audi | -1.032 |
Token | country |
Token ID | 1499 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Palest | +2.213 |
anon | +1.989 |
Bey | +1.948 |
ILLE | +1.872 |
audi | +1.796 |
Neg logit contributions | |
イト | -1.983 |
ー� | -1.892 |
ゴン | -1.890 |
checks | -1.831 |
roup | -1.817 |
Token | just |
Token ID | 655 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Palest | +2.061 |
anon | +1.831 |
Bey | +1.796 |
ILLE | +1.707 |
audi | +1.639 |
Neg logit contributions | |
イト | -1.731 |
ゴン | -1.678 |
ー� | -1.667 |
roup | -1.627 |
checks | -1.607 |
Token | got |
Token ID | 1392 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Palest | +2.064 |
anon | +1.848 |
Bey | +1.818 |
ILLE | +1.747 |
audi | +1.682 |
Neg logit contributions | |
イト | -1.435 |
ー� | -1.371 |
ゴン | -1.370 |
roup | -1.337 |
checks | -1.317 |
Token | way |
Token ID | 835 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
Palest | +1.273 |
anon | +1.138 |
Bey | +1.121 |
ILLE | +1.070 |
audi | +1.038 |
Neg logit contributions | |
イト | -0.867 |
ー� | -0.835 |
ゴン | -0.828 |
roup | -0.812 |
checks | -0.811 |
Token | brighter |
Token ID | 26083 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Palest | +2.259 |
anon | +2.032 |
Bey | +2.008 |
ILLE | +1.913 |
audi | +1.855 |
Neg logit contributions | |
イト | -1.420 |
ー� | -1.362 |
ゴン | -1.353 |
roup | -1.323 |
checks | -1.318 |
Token | !!! |
Token ID | 10185 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
イト | +1.692 |
ー� | +1.631 |
checks | +1.604 |
roup | +1.594 |
ゴン | +1.592 |
Neg logit contributions | |
Palest | -1.883 |
anon | -1.658 |
Bey | -1.632 |
ILLE | -1.549 |
audi | -1.501 |
Token | Cong |
Token ID | 2908 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
イト | +1.076 |
ー� | +1.043 |
checks | +1.025 |
ゴン | +1.018 |
roup | +1.016 |
Neg logit contributions | |
Palest | -1.163 |
anon | -1.018 |
Bey | -0.998 |
ILLE | -0.948 |
audi | -0.923 |
Token | rats |
Token ID | 46714 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
roup | +1.963 |
イト | +1.913 |
ー� | +1.908 |
checks | +1.886 |
warts | +1.857 |
Neg logit contributions | |
Palest | -5.963 |
Bey | -5.420 |
anon | -5.393 |
ILLE | -5.256 |
audi | -5.117 |
Token | - |
Token ID | 12 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
Palest | +0.877 |
anon | +0.763 |
Bey | +0.746 |
ILLE | +0.704 |
audi | +0.679 |
Neg logit contributions | |
イト | -0.942 |
ー� | -0.911 |
ゴン | -0.899 |
checks | -0.894 |
roup | -0.890 |
Token | store |
Token ID | 8095 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
イト | +0.356 |
ー� | +0.346 |
ゴン | +0.340 |
checks | +0.339 |
roup | +0.339 |
Neg logit contributions | |
Palest | -0.374 |
anon | -0.326 |
Bey | -0.322 |
ILLE | -0.306 |
audi | -0.292 |
Token | y |
Token ID | 88 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
イト | +0.131 |
ー� | +0.126 |
ゴン | +0.124 |
checks | +0.123 |
roup | +0.122 |
Neg logit contributions | |
Palest | -0.202 |
anon | -0.181 |
Bey | -0.179 |
ILLE | -0.171 |
audi | -0.166 |
Token | residential |
Token ID | 12420 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
Palest | +2.852 |
anon | +2.531 |
Bey | +2.470 |
ILLE | +2.339 |
audi | +2.297 |
Neg logit contributions | |
イト | -2.322 |
ゴン | -2.244 |
ー� | -2.230 |
checks | -2.194 |
roup | -2.180 |
Token | and |
Token ID | 290 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
Palest | +3.248 |
anon | +2.879 |
Bey | +2.800 |
ILLE | +2.666 |
audi | +2.604 |
Neg logit contributions | |
イト | -2.585 |
ゴン | -2.535 |
ー� | -2.501 |
checks | -2.448 |
roup | -2.431 |
Token | commercial |
Token ID | 5068 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Palest | +0.001 |
anon | +0.001 |
Bey | +0.001 |
ILLE | +0.001 |
audi | +0.001 |
Neg logit contributions | |
イト | -0.001 |
ー� | -0.001 |
ゴン | -0.001 |
checks | -0.001 |
roup | -0.001 |
Token | buildings |
Token ID | 6832 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Palest | +1.680 |
anon | +1.495 |
Bey | +1.464 |
ILLE | +1.397 |
audi | +1.356 |
Neg logit contributions | |
イト | -1.253 |
ー� | -1.206 |
ゴン | -1.202 |
checks | -1.180 |
roup | -1.177 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Palest | +0.245 |
anon | +0.217 |
Bey | +0.213 |
ILLE | +0.203 |
audi | +0.196 |
Neg logit contributions | |
イト | -0.206 |
ー� | -0.199 |
ゴン | -0.196 |
checks | -0.194 |
roup | -0.194 |
Token |
|
Token ID | 198 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
Palest | +1.032 |
anon | +0.902 |
Bey | +0.885 |
ILLE | +0.836 |
audi | +0.805 |
Neg logit contributions | |
イト | -1.028 |
ー� | -0.991 |
ゴン | -0.983 |
checks | -0.975 |
roup | -0.973 |
Token |
|
Token ID | 198 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
Palest | +0.562 |
anon | +0.479 |
Bey | +0.472 |
ILLE | +0.451 |
audi | +0.435 |
Neg logit contributions | |
イト | -0.528 |
ー� | -0.516 |
checks | -0.508 |
roup | -0.504 |
safety | -0.500 |
Token | The |
Token ID | 464 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
Palest | +0.480 |
anon | +0.419 |
Bey | +0.411 |
ILLE | +0.389 |
audi | +0.374 |
Neg logit contributions | |
イト | -0.482 |
ー� | -0.467 |
ゴン | -0.460 |
checks | -0.457 |
roup | -0.457 |
Token | s |
Token ID | 82 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
イト | +0.859 |
ー� | +0.838 |
checks | +0.822 |
roup | +0.819 |
safety | +0.810 |
Neg logit contributions | |
Palest | -0.921 |
anon | -0.804 |
Bey | -0.787 |
ILLE | -0.748 |
audi | -0.718 |
Token | port |
Token ID | 634 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
roup | +1.324 |
ー� | +1.292 |
checks | +1.281 |
イト | +1.281 |
safety | +1.273 |
Neg logit contributions | |
Palest | -1.818 |
anon | -1.605 |
Bey | -1.597 |
ILLE | -1.548 |
oire | -1.445 |
Token |
|
Token ID | 198 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
Palest | +4.040 |
anon | +3.606 |
Bey | +3.531 |
ILLE | +3.323 |
audio | +3.317 |
Neg logit contributions | |
イト | -3.710 |
ゴン | -3.573 |
ー� | -3.538 |
plet | -3.410 |
peror | -3.400 |
Token |
|
Token ID | 198 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
イト | +0.486 |
ー� | +0.480 |
checks | +0.473 |
roup | +0.469 |
safety | +0.466 |
Neg logit contributions | |
Palest | -0.584 |
anon | -0.490 |
Bey | -0.484 |
ILLE | -0.465 |
audi | -0.449 |
Token | Back |
Token ID | 7282 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
イト | +0.298 |
ー� | +0.289 |
ゴン | +0.284 |
checks | +0.284 |
roup | +0.283 |
Neg logit contributions | |
Palest | -0.301 |
anon | -0.261 |
Bey | -0.255 |
ILLE | -0.242 |
audi | -0.232 |
Token | then |
Token ID | 788 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
Palest | +1.635 |
anon | +1.432 |
Bey | +1.407 |
ILLE | +1.331 |
audi | +1.296 |
Neg logit contributions | |
イト | -1.550 |
ー� | -1.502 |
ゴン | -1.484 |
roup | -1.465 |
checks | -1.465 |
Token | we |
Token ID | 356 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
イト | +0.014 |
ー� | +0.014 |
ゴン | +0.014 |
checks | +0.014 |
roup | +0.014 |
Neg logit contributions | |
Palest | -0.017 |
anon | -0.015 |
Bey | -0.015 |
ILLE | -0.014 |
audi | -0.014 |
Token | trained |
Token ID | 8776 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
イト | +0.600 |
ー� | +0.584 |
roup | +0.572 |
checks | +0.570 |
ゴン | +0.568 |
Neg logit contributions | |
Palest | -0.633 |
anon | -0.556 |
Bey | -0.547 |
ILLE | -0.519 |
audi | -0.499 |
Token | in |
Token ID | 287 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Palest | +0.358 |
anon | +0.317 |
Bey | +0.311 |
ILLE | +0.296 |
audi | +0.286 |
Neg logit contributions | |
イト | -0.310 |
ー� | -0.299 |
ゴン | -0.294 |
checks | -0.292 |
roup | -0.292 |
Token | a |
Token ID | 257 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Palest | +0.830 |
anon | +0.734 |
Bey | +0.720 |
ILLE | +0.686 |
audi | +0.665 |
Neg logit contributions | |
イト | -0.672 |
ー� | -0.647 |
ゴン | -0.639 |
checks | -0.632 |
roup | -0.631 |
Token | gym |
Token ID | 11550 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
イト | +0.723 |
ー� | +0.697 |
safety | +0.686 |
roup | +0.683 |
ゴン | +0.679 |
Neg logit contributions | |
Palest | -0.980 |
anon | -0.882 |
Bey | -0.872 |
ILLE | -0.829 |
audi | -0.800 |
Token | to |
Token ID | 284 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
イト | +3.045 |
ー� | +2.950 |
checks | +2.912 |
ゴン | +2.890 |
safety | +2.878 |
Neg logit contributions | |
Palest | -3.787 |
anon | -3.359 |
Bey | -3.299 |
ILLE | -3.133 |
audi | -3.035 |
Token | the |
Token ID | 262 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
イト | +0.574 |
ー� | +0.552 |
ゴン | +0.545 |
roup | +0.537 |
checks | +0.537 |
Neg logit contributions | |
Palest | -0.774 |
anon | -0.690 |
Bey | -0.678 |
ILLE | -0.648 |
audi | -0.627 |
Token | goals |
Token ID | 4661 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
イト | +0.203 |
ー� | +0.195 |
ゴン | +0.192 |
checks | +0.190 |
roup | +0.190 |
Neg logit contributions | |
Palest | -0.288 |
anon | -0.257 |
Bey | -0.253 |
ILLE | -0.242 |
audi | -0.234 |
Token | from |
Token ID | 422 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Palest | +0.542 |
anon | +0.478 |
Bey | +0.470 |
ILLE | +0.447 |
audi | +0.432 |
Neg logit contributions | |
イト | -0.464 |
ー� | -0.447 |
ゴン | -0.442 |
checks | -0.436 |
roup | -0.436 |
Token | Wilson |
Token ID | 8127 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Palest | +1.072 |
anon | +0.944 |
Bey | +0.924 |
ILLE | +0.880 |
audi | +0.846 |
Neg logit contributions | |
イト | -0.987 |
ゴン | -0.946 |
ー� | -0.946 |
roup | -0.922 |
checks | -0.920 |
Token | ( |
Token ID | 357 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
Palest | +1.925 |
anon | +1.680 |
Bey | +1.639 |
ILLE | +1.573 |
audi | +1.498 |
Neg logit contributions | |
イト | -1.916 |
ゴン | -1.863 |
ー� | -1.851 |
roup | -1.816 |
checks | -1.800 |
Token | 3 |
Token ID | 18 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
Palest | +0.062 |
anon | +0.054 |
Bey | +0.053 |
ILLE | +0.050 |
audi | +0.048 |
Neg logit contributions | |
イト | -0.064 |
ー� | -0.062 |
ゴン | -0.061 |
checks | -0.061 |
roup | -0.061 |
Token | : |
Token ID | 25 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
イト | +3.245 |
checks | +3.188 |
ー� | +3.174 |
safety | +3.145 |
ties | +3.066 |
Neg logit contributions | |
Palest | -5.003 |
Bey | -4.467 |
anon | -4.371 |
ILLE | -4.169 |
audi | -4.046 |
Token | 46 |
Token ID | 3510 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
Palest | +0.200 |
anon | +0.176 |
Bey | +0.173 |
ILLE | +0.166 |
audi | +0.160 |
Neg logit contributions | |
イト | -0.151 |
ー� | -0.146 |
checks | -0.143 |
ゴン | -0.143 |
roup | -0.142 |
Token | ), |
Token ID | 828 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
Palest | +0.605 |
anon | +0.538 |
Bey | +0.530 |
ILLE | +0.503 |
audi | +0.489 |
Neg logit contributions | |
イト | -0.459 |
ー� | -0.442 |
ゴン | -0.433 |
checks | -0.433 |
roup | -0.431 |
Token | Osh |
Token ID | 46614 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
Palest | +0.367 |
anon | +0.325 |
Bey | +0.319 |
ILLE | +0.303 |
audi | +0.293 |
Neg logit contributions | |
イト | -0.313 |
ー� | -0.300 |
ゴン | -0.299 |
roup | -0.293 |
checks | -0.293 |
Token | congressman |
Token ID | 29545 |
Feature activation | +2.96e-03 |
Pos logit contributions | |
イト | +0.381 |
ー� | +0.367 |
ゴン | +0.361 |
checks | +0.359 |
roup | +0.358 |
Neg logit contributions | |
Palest | -0.456 |
anon | -0.403 |
Bey | -0.396 |
ILLE | -0.377 |
audi | -0.365 |
Token | was |
Token ID | 373 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
イト | +0.002 |
ー� | +0.002 |
ゴン | +0.002 |
checks | +0.002 |
roup | +0.002 |
Neg logit contributions | |
Palest | -0.002 |
anon | -0.002 |
Bey | -0.002 |
ILLE | -0.002 |
audi | -0.002 |
Token | caught |
Token ID | 4978 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
イト | +0.222 |
ー� | +0.214 |
ゴン | +0.210 |
checks | +0.209 |
roup | +0.208 |
Neg logit contributions | |
Palest | -0.287 |
anon | -0.255 |
Bey | -0.251 |
ILLE | -0.239 |
audi | -0.232 |
Token | kissing |
Token ID | 25847 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
Palest | +3.170 |
anon | +2.775 |
Bey | +2.745 |
ILLE | +2.599 |
audi | +2.509 |
Neg logit contributions | |
イト | -2.828 |
ゴン | -2.763 |
ー� | -2.732 |
roup | -2.695 |
checks | -2.673 |
Token | one |
Token ID | 530 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Palest | +2.241 |
anon | +1.960 |
Bey | +1.952 |
ILLE | +1.836 |
audi | +1.772 |
Neg logit contributions | |
イト | -1.909 |
ゴン | -1.839 |
ー� | -1.817 |
roup | -1.786 |
checks | -1.777 |
Token | of |
Token ID | 286 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
Palest | +2.278 |
anon | +1.972 |
Bey | +1.952 |
ILLE | +1.823 |
audi | +1.746 |
Neg logit contributions | |
イト | -2.443 |
ゴン | -2.347 |
ー� | -2.323 |
roup | -2.296 |
checks | -2.290 |
Token | his |
Token ID | 465 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Palest | +0.320 |
anon | +0.285 |
Bey | +0.282 |
ILLE | +0.269 |
audi | +0.261 |
Neg logit contributions | |
イト | -0.222 |
ー� | -0.212 |
ゴン | -0.211 |
checks | -0.207 |
roup | -0.207 |
Token | staffers |
Token ID | 23033 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
Palest | +1.584 |
anon | +1.405 |
Bey | +1.384 |
ILLE | +1.315 |
audi | +1.274 |
Neg logit contributions | |
イト | -1.254 |
ー� | -1.204 |
ゴン | -1.192 |
roup | -1.176 |
checks | -1.174 |
Token | , |
Token ID | 11 |
Feature activation | -6.59e-03 |
Pos logit contributions | |
イト | +1.722 |
ー� | +1.691 |
checks | +1.681 |
safety | +1.664 |
roup | +1.630 |
Neg logit contributions | |
Palest | -2.306 |
anon | -2.068 |
Bey | -2.017 |
ILLE | -1.943 |
audi | -1.882 |
Token | and |
Token ID | 290 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
Palest | +0.005 |
anon | +0.005 |
Bey | +0.005 |
ILLE | +0.004 |
audi | +0.004 |
Neg logit contributions | |
イト | -0.004 |
ー� | -0.004 |
ゴン | -0.004 |
checks | -0.004 |
roup | -0.004 |
Token | has |
Token ID | 468 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
イト | +0.336 |
ー� | +0.324 |
ゴン | +0.319 |
checks | +0.317 |
roup | +0.316 |
Neg logit contributions | |
Palest | -0.400 |
anon | -0.354 |
Bey | -0.348 |
ILLE | -0.331 |
audi | -0.320 |
Token | 500 |
Token ID | 4059 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Palest | +2.531 |
anon | +2.231 |
Bey | +2.172 |
ILLE | +2.015 |
audi | +1.932 |
Neg logit contributions | |
イト | -3.175 |
ゴン | -3.091 |
ー� | -3.073 |
roup | -3.028 |
checks | -3.008 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Palest | +1.223 |
anon | +1.078 |
Bey | +1.061 |
ILLE | +1.009 |
audi | +0.977 |
Neg logit contributions | |
イト | -1.022 |
ー� | -0.984 |
ゴン | -0.973 |
roup | -0.962 |
checks | -0.960 |
Token | 000 |
Token ID | 830 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
Palest | +1.577 |
anon | +1.374 |
Bey | +1.363 |
ILLE | +1.284 |
audi | +1.248 |
Neg logit contributions | |
イト | -1.435 |
ー� | -1.385 |
ゴン | -1.379 |
roup | -1.362 |
checks | -1.359 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Palest | +2.075 |
anon | +1.815 |
Bey | +1.790 |
ILLE | +1.702 |
audi | +1.652 |
Neg logit contributions | |
イト | -1.771 |
ー� | -1.702 |
ゴン | -1.698 |
roup | -1.669 |
checks | -1.659 |
Token | I |
Token ID | 314 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
Palest | +0.935 |
anon | +0.807 |
Bey | +0.792 |
ILLE | +0.745 |
audi | +0.715 |
Neg logit contributions | |
イト | -1.069 |
ー� | -1.035 |
ゴン | -1.025 |
checks | -1.016 |
roup | -1.016 |
Token | can |
Token ID | 460 |
Feature activation | -6.28e+00 |
Pos logit contributions | |
Palest | +3.166 |
anon | +2.808 |
Bey | +2.734 |
ILLE | +2.587 |
audi | +2.523 |
Neg logit contributions | |
イト | -2.998 |
ゴン | -2.888 |
ー� | -2.858 |
roup | -2.803 |
checks | -2.803 |
Token | � |
Token ID | 447 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Palest | +4.689 |
anon | +4.187 |
Bey | +4.093 |
audi | +3.826 |
ILLE | +3.820 |
Neg logit contributions | |
イト | -4.406 |
ゴン | -4.314 |
ー� | -4.181 |
roup | -4.120 |
checks | -4.114 |
Token | � |
Token ID | 247 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Palest | +2.178 |
anon | +1.966 |
Bey | +1.936 |
ILLE | +1.860 |
audi | +1.805 |
Neg logit contributions | |
イト | -1.332 |
ー� | -1.267 |
ゴン | -1.253 |
checks | -1.239 |
roup | -1.235 |
Token | t |
Token ID | 83 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
Palest | +1.428 |
anon | +1.291 |
Bey | +1.263 |
ILLE | +1.193 |
audi | +1.169 |
Neg logit contributions | |
イト | -1.152 |
ゴン | -1.106 |
ー� | -1.094 |
roup | -1.074 |
checks | -1.074 |
Token | afford |
Token ID | 5368 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
Palest | +2.460 |
anon | +2.186 |
Bey | +2.142 |
ILLE | +2.023 |
audi | +1.980 |
Neg logit contributions | |
イト | -2.103 |
ー� | -2.014 |
ゴン | -2.012 |
checks | -1.974 |
roup | -1.967 |
Token | that |
Token ID | 326 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Palest | +4.586 |
anon | +4.000 |
Bey | +3.916 |
audi | +3.701 |
ILLE | +3.672 |
Neg logit contributions | |
イト | -3.982 |
ゴン | -3.968 |
roup | -3.849 |
ー� | -3.821 |
peror | -3.778 |
Token | There |
Token ID | 1858 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
イト | +0.916 |
ー� | +0.889 |
checks | +0.874 |
ゴン | +0.874 |
roup | +0.871 |
Neg logit contributions | |
Palest | -0.832 |
anon | -0.709 |
Bey | -0.694 |
ILLE | -0.660 |
audi | -0.630 |
Token | is |
Token ID | 318 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
イト | +0.816 |
ー� | +0.786 |
ゴン | +0.773 |
checks | +0.769 |
roup | +0.767 |
Neg logit contributions | |
Palest | -0.951 |
anon | -0.837 |
Bey | -0.825 |
ILLE | -0.785 |
audi | -0.758 |
Token | so |
Token ID | 523 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
Palest | +1.599 |
anon | +1.428 |
Bey | +1.402 |
ILLE | +1.335 |
audi | +1.298 |
Neg logit contributions | |
イト | -1.161 |
ー� | -1.113 |
ゴン | -1.107 |
checks | -1.090 |
roup | -1.089 |
Token | much |
Token ID | 881 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Palest | +4.464 |
anon | +3.959 |
Bey | +3.875 |
ILLE | +3.707 |
oire | +3.582 |
Neg logit contributions | |
イト | -4.020 |
ゴン | -3.824 |
ー� | -3.816 |
checks | -3.798 |
roup | -3.728 |
Token | I |
Token ID | 314 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
Palest | +1.721 |
anon | +1.525 |
Bey | +1.499 |
ILLE | +1.427 |
audi | +1.380 |
Neg logit contributions | |
イト | -1.379 |
ー� | -1.327 |
ゴン | -1.311 |
checks | -1.297 |
roup | -1.295 |
Token | cannot |
Token ID | 2314 |
Feature activation | -7.10e+00 |
Pos logit contributions | |
Palest | +3.318 |
anon | +2.998 |
Bey | +2.904 |
ILLE | +2.794 |
audi | +2.688 |
Neg logit contributions | |
イト | -2.613 |
ゴン | -2.535 |
ー� | -2.471 |
checks | -2.459 |
roup | -2.421 |
Token | control |
Token ID | 1630 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
Palest | +5.376 |
anon | +4.959 |
Bey | +4.774 |
ILLE | +4.433 |
audi | +4.351 |
Neg logit contributions | |
イト | -4.856 |
ゴン | -4.757 |
checks | -4.538 |
ー� | -4.515 |
peror | -4.426 |
Token | , |
Token ID | 11 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
Palest | +2.554 |
anon | +2.246 |
Bey | +2.202 |
ILLE | +2.078 |
oire | +1.993 |
Neg logit contributions | |
イト | -2.374 |
ー� | -2.288 |
ゴン | -2.274 |
roup | -2.237 |
checks | -2.236 |
Token | that |
Token ID | 326 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
Palest | +0.669 |
anon | +0.588 |
Bey | +0.578 |
ILLE | +0.547 |
audi | +0.528 |
Neg logit contributions | |
イト | -0.600 |
ー� | -0.580 |
ゴン | -0.574 |
roup | -0.567 |
checks | -0.567 |
Token | I |
Token ID | 314 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Palest | +0.040 |
anon | +0.035 |
Bey | +0.035 |
ILLE | +0.033 |
audi | +0.032 |
Neg logit contributions | |
イト | -0.039 |
ー� | -0.038 |
ゴン | -0.037 |
checks | -0.037 |
roup | -0.037 |
Token | either |
Token ID | 2035 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Palest | +1.677 |
anon | +1.504 |
Bey | +1.461 |
ILLE | +1.393 |
audi | +1.348 |
Neg logit contributions | |
イト | -1.430 |
ゴン | -1.379 |
ー� | -1.366 |
checks | -1.343 |
roup | -1.338 |
Token | be |
Token ID | 307 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
Palest | +4.981 |
anon | +4.580 |
Bey | +4.433 |
ILLE | +4.105 |
audi | +4.087 |
Neg logit contributions | |
イト | -4.511 |
ゴン | -4.341 |
ー� | -4.255 |
checks | -4.144 |
roup | -4.099 |
Token | directly |
Token ID | 3264 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
Palest | +3.219 |
anon | +2.799 |
Bey | +2.774 |
ILLE | +2.609 |
audi | +2.515 |
Neg logit contributions | |
イト | -2.994 |
ー� | -2.877 |
ゴン | -2.868 |
roup | -2.801 |
checks | -2.790 |
Token | measured |
Token ID | 8630 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
Palest | +2.809 |
anon | +2.460 |
Bey | +2.432 |
ILLE | +2.287 |
audi | +2.216 |
Neg logit contributions | |
イト | -2.561 |
ー� | -2.458 |
ゴン | -2.444 |
roup | -2.395 |
checks | -2.388 |
Token | ; |
Token ID | 26 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Palest | +0.774 |
anon | +0.683 |
Bey | +0.672 |
ILLE | +0.639 |
audi | +0.616 |
Neg logit contributions | |
イト | -0.677 |
ー� | -0.654 |
ゴン | -0.644 |
checks | -0.641 |
roup | -0.638 |
Token | nor |
Token ID | 4249 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Palest | +0.093 |
anon | +0.082 |
Bey | +0.081 |
ILLE | +0.077 |
audi | +0.075 |
Neg logit contributions | |
イト | -0.072 |
ー� | -0.069 |
ゴン | -0.068 |
checks | -0.067 |
roup | -0.067 |
Token | can |
Token ID | 460 |
Feature activation | -8.10e+00 |
Pos logit contributions | |
Palest | +1.456 |
anon | +1.278 |
Bey | +1.248 |
ILLE | +1.183 |
audi | +1.142 |
Neg logit contributions | |
イト | -1.400 |
ー� | -1.353 |
ゴン | -1.339 |
checks | -1.318 |
roup | -1.317 |
Token | feedback |
Token ID | 7538 |
Feature activation | +9.43e-02 |
Pos logit contributions | |
Palest | +6.299 |
anon | +5.450 |
Bey | +5.431 |
ILLE | +5.173 |
audio | +4.954 |
Neg logit contributions | |
イト | -5.389 |
ゴン | -5.184 |
ー� | -5.096 |
roup | -4.975 |
warts | -4.967 |
Token | s |
Token ID | 82 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
イト | +0.060 |
ー� | +0.057 |
ゴン | +0.057 |
checks | +0.056 |
roup | +0.056 |
Neg logit contributions | |
Palest | -0.080 |
anon | -0.071 |
Bey | -0.070 |
ILLE | -0.066 |
audi | -0.064 |
Token | be |
Token ID | 307 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
Palest | +2.567 |
anon | +2.260 |
Bey | +2.222 |
ILLE | +2.087 |
audi | +2.018 |
Neg logit contributions | |
イト | -2.473 |
ー� | -2.375 |
ゴン | -2.360 |
checks | -2.323 |
roup | -2.304 |
Token | readily |
Token ID | 14704 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
Palest | +3.315 |
anon | +2.869 |
Bey | +2.849 |
ILLE | +2.659 |
audi | +2.567 |
Neg logit contributions | |
イト | -3.396 |
ー� | -3.245 |
ゴン | -3.237 |
roup | -3.159 |
checks | -3.152 |
Token | distinguished |
Token ID | 18876 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Palest | +3.376 |
anon | +2.938 |
Bey | +2.909 |
ILLE | +2.713 |
audi | +2.626 |
Neg logit contributions | |
イト | -3.367 |
ゴン | -3.208 |
ー� | -3.206 |
checks | -3.132 |
roup | -3.118 |
Token | to |
Token ID | 284 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
Palest | +1.687 |
anon | +1.494 |
Bey | +1.463 |
ILLE | +1.386 |
audi | +1.351 |
Neg logit contributions | |
イト | -1.336 |
ー� | -1.291 |
ゴン | -1.280 |
checks | -1.263 |
roup | -1.244 |
Token | speed |
Token ID | 2866 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
イト | +0.415 |
ー� | +0.398 |
roup | +0.389 |
ゴン | +0.388 |
checks | +0.387 |
Neg logit contributions | |
Palest | -0.636 |
anon | -0.569 |
Bey | -0.562 |
ILLE | -0.539 |
audi | -0.520 |
Token | the |
Token ID | 262 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
Palest | +1.991 |
anon | +1.747 |
Bey | +1.713 |
ILLE | +1.618 |
audi | +1.568 |
Neg logit contributions | |
イト | -1.788 |
ー� | -1.715 |
ゴン | -1.696 |
checks | -1.675 |
roup | -1.663 |
Token | process |
Token ID | 1429 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Palest | +0.542 |
anon | +0.483 |
Bey | +0.475 |
ILLE | +0.453 |
audi | +0.440 |
Neg logit contributions | |
イト | -0.409 |
ー� | -0.394 |
ゴン | -0.388 |
roup | -0.385 |
checks | -0.385 |
Token | of |
Token ID | 286 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Palest | +1.585 |
anon | +1.376 |
Bey | +1.346 |
ILLE | +1.261 |
audi | +1.218 |
Neg logit contributions | |
イト | -1.678 |
ー� | -1.617 |
ゴン | -1.596 |
checks | -1.585 |
roup | -1.581 |
Token | independence |
Token ID | 10404 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
Palest | +0.459 |
anon | +0.410 |
Bey | +0.403 |
ILLE | +0.385 |
audi | +0.374 |
Neg logit contributions | |
イト | -0.332 |
ー� | -0.320 |
ゴン | -0.315 |
checks | -0.313 |
roup | -0.312 |
Token | . |
Token ID | 13 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
Palest | +5.238 |
anon | +4.471 |
Bey | +4.467 |
ILLE | +4.078 |
oire | +3.999 |
Neg logit contributions | |
イト | -5.350 |
ー� | -5.120 |
ゴン | -5.085 |
plet | -4.999 |
roup | -4.992 |
Token |
|
Token ID | 198 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
イト | +0.583 |
ー� | +0.566 |
roup | +0.550 |
checks | +0.548 |
ゴン | +0.548 |
Neg logit contributions | |
Palest | -0.695 |
anon | -0.613 |
Bey | -0.603 |
ILLE | -0.579 |
audi | -0.564 |
Token |
|
Token ID | 198 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Palest | +0.024 |
anon | +0.020 |
Bey | +0.020 |
ILLE | +0.019 |
audi | +0.018 |
Neg logit contributions | |
イト | -0.022 |
ー� | -0.021 |
checks | -0.021 |
roup | -0.021 |
safety | -0.020 |
Token | Ken |
Token ID | 27827 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
Palest | +0.167 |
anon | +0.143 |
Bey | +0.140 |
ILLE | +0.132 |
audi | +0.128 |
Neg logit contributions | |
イト | -0.185 |
ー� | -0.180 |
ゴン | -0.177 |
checks | -0.176 |
roup | -0.176 |
Token | y |
Token ID | 88 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Palest | +2.216 |
anon | +1.998 |
Bey | +1.954 |
ILLE | +1.853 |
audi | +1.800 |
Neg logit contributions | |
イト | -1.631 |
ー� | -1.563 |
ゴン | -1.552 |
checks | -1.520 |
roup | -1.511 |
Token | with |
Token ID | 351 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
Palest | +0.691 |
anon | +0.604 |
Bey | +0.593 |
ILLE | +0.561 |
audi | +0.541 |
Neg logit contributions | |
イト | -0.669 |
ー� | -0.646 |
ゴン | -0.638 |
checks | -0.632 |
roup | -0.631 |
Token | local |
Token ID | 1957 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Palest | +0.462 |
anon | +0.408 |
Bey | +0.402 |
ILLE | +0.384 |
audi | +0.371 |
Neg logit contributions | |
イト | -0.362 |
ー� | -0.348 |
ゴン | -0.344 |
checks | -0.339 |
roup | -0.339 |
Token | forces |
Token ID | 3386 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Palest | +0.348 |
anon | +0.308 |
Bey | +0.302 |
ILLE | +0.287 |
audi | +0.276 |
Neg logit contributions | |
イト | -0.292 |
ー� | -0.280 |
ゴン | -0.279 |
checks | -0.273 |
roup | -0.273 |
Token | within |
Token ID | 1626 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Palest | +0.964 |
anon | +0.846 |
Bey | +0.830 |
ILLE | +0.788 |
audi | +0.761 |
Neg logit contributions | |
イト | -0.860 |
ー� | -0.826 |
ゴン | -0.823 |
checks | -0.807 |
roup | -0.807 |
Token | 20 |
Token ID | 1160 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
イト | +0.944 |
ー� | +0.910 |
checks | +0.893 |
roup | +0.889 |
safety | +0.886 |
Neg logit contributions | |
Palest | -1.516 |
anon | -1.364 |
Bey | -1.342 |
ILLE | -1.290 |
audi | -1.250 |
Token | miles |
Token ID | 4608 |
Feature activation | -8.12e+00 |
Pos logit contributions | |
Palest | +0.711 |
anon | +0.621 |
Bey | +0.609 |
ILLE | +0.576 |
audi | +0.555 |
Neg logit contributions | |
イト | -0.711 |
ー� | -0.688 |
ゴン | -0.679 |
checks | -0.674 |
roup | -0.673 |
Token | of |
Token ID | 286 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Palest | +5.522 |
anon | +4.753 |
Bey | +4.580 |
ILLE | +4.280 |
oire | +4.249 |
Neg logit contributions | |
イト | -6.231 |
ゴン | -6.073 |
ー� | -5.905 |
roup | -5.815 |
checks | -5.739 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Palest | +1.057 |
anon | +0.924 |
Bey | +0.906 |
ILLE | +0.858 |
audi | +0.827 |
Neg logit contributions | |
イト | -0.999 |
ゴン | -0.967 |
ー� | -0.958 |
checks | -0.936 |
roup | -0.936 |
Token | ISIS |
Token ID | 7768 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
Palest | +0.988 |
anon | +0.858 |
Bey | +0.842 |
ILLE | +0.795 |
audi | +0.765 |
Neg logit contributions | |
イト | -1.050 |
ゴン | -1.016 |
ー� | -1.012 |
checks | -0.990 |
roup | -0.989 |
Token | capital |
Token ID | 3139 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Palest | +1.873 |
anon | +1.639 |
Bey | +1.597 |
ILLE | +1.528 |
audi | +1.461 |
Neg logit contributions | |
イト | -1.854 |
ゴン | -1.791 |
ー� | -1.782 |
roup | -1.749 |
checks | -1.749 |
Token | city |
Token ID | 1748 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Palest | +1.697 |
anon | +1.487 |
Bey | +1.456 |
ILLE | +1.383 |
audi | +1.338 |
Neg logit contributions | |
イト | -1.499 |
ー� | -1.441 |
ゴン | -1.434 |
roup | -1.412 |
checks | -1.410 |