Token | 55 |
Token ID | 2816 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
illac | +0.880 |
Leaks | +0.848 |
ILY | +0.837 |
Nib | +0.829 |
CLASS | +0.823 |
Neg logit contributions | |
angered | -0.901 |
genre | -0.820 |
adem | -0.728 |
bnb | -0.719 |
arios | -0.708 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
angered | +1.090 |
genre | +0.995 |
adem | +0.893 |
bnb | +0.886 |
arios | +0.872 |
Neg logit contributions | |
illac | -0.900 |
Leaks | -0.870 |
ILY | -0.855 |
Nib | -0.841 |
CLASS | -0.833 |
Token |
|
Token ID | 198 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
angered | +2.152 |
genre | +1.945 |
adem | +1.716 |
bnb | +1.697 |
arios | +1.675 |
Neg logit contributions | |
illac | -2.078 |
Leaks | -1.980 |
ILY | -1.959 |
Nib | -1.930 |
ャ | -1.924 |
Token |
|
Token ID | 198 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
illac | +0.237 |
Leaks | +0.229 |
ILY | +0.226 |
Nib | +0.223 |
CLASS | +0.222 |
Neg logit contributions | |
angered | -0.282 |
genre | -0.259 |
adem | -0.233 |
bnb | -0.230 |
arios | -0.227 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
illac | +0.508 |
Leaks | +0.493 |
ILY | +0.484 |
CLASS | +0.476 |
Nib | +0.471 |
Neg logit contributions | |
angered | -0.727 |
genre | -0.668 |
adem | -0.610 |
bnb | -0.603 |
arios | -0.599 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
angered | +1.747 |
genre | +1.529 |
adem | +1.281 |
bnb | +1.279 |
arios | +1.239 |
Neg logit contributions | |
illac | -2.848 |
Leaks | -2.784 |
ILY | -2.741 |
Nib | -2.716 |
ャ | -2.712 |
Token | this |
Token ID | 428 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
angered | +4.383 |
genre | +3.894 |
adem | +3.432 |
bnb | +3.373 |
arios | +3.328 |
Neg logit contributions | |
illac | -4.866 |
Leaks | -4.777 |
ILY | -4.695 |
ャ | -4.595 |
Nib | -4.568 |
Token | comment |
Token ID | 2912 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
illac | +0.186 |
Leaks | +0.180 |
ILY | +0.179 |
CLASS | +0.178 |
Nib | +0.178 |
Neg logit contributions | |
angered | -0.210 |
genre | -0.191 |
adem | -0.173 |
bnb | -0.170 |
arios | -0.168 |
Token | on |
Token ID | 319 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
angered | +0.396 |
genre | +0.366 |
adem | +0.335 |
bnb | +0.331 |
arios | +0.328 |
Neg logit contributions | |
illac | -0.224 |
Leaks | -0.212 |
ILY | -0.209 |
Nib | -0.205 |
CLASS | -0.202 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
angered | +0.051 |
genre | +0.045 |
adem | +0.040 |
bnb | +0.039 |
arios | +0.039 |
Neg logit contributions | |
illac | -0.058 |
Leaks | -0.056 |
ILY | -0.056 |
Nib | -0.055 |
CLASS | -0.055 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
angered | +0.908 |
genre | +0.803 |
adem | +0.687 |
bnb | +0.675 |
arios | +0.659 |
Neg logit contributions | |
illac | -1.370 |
Leaks | -1.331 |
ILY | -1.317 |
Nib | -1.304 |
CLASS | -1.296 |
Token | 19 |
Token ID | 1129 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
illac | +0.819 |
Leaks | +0.789 |
ILY | +0.778 |
Nib | +0.770 |
CLASS | +0.764 |
Neg logit contributions | |
angered | -0.931 |
genre | -0.851 |
adem | -0.762 |
bnb | -0.752 |
arios | -0.741 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
angered | +1.065 |
genre | +0.972 |
adem | +0.872 |
bnb | +0.864 |
arios | +0.849 |
Neg logit contributions | |
illac | -0.886 |
Leaks | -0.856 |
ILY | -0.840 |
Nib | -0.827 |
ャ | -0.820 |
Token |
|
Token ID | 198 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
angered | +2.371 |
genre | +2.140 |
adem | +1.885 |
bnb | +1.863 |
arios | +1.837 |
Neg logit contributions | |
illac | -2.336 |
Leaks | -2.221 |
ILY | -2.198 |
ャ | -2.164 |
Nib | -2.164 |
Token |
|
Token ID | 198 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
illac | +0.069 |
Leaks | +0.066 |
ILY | +0.065 |
Nib | +0.065 |
CLASS | +0.064 |
Neg logit contributions | |
angered | -0.080 |
genre | -0.074 |
adem | -0.066 |
bnb | -0.065 |
arios | -0.064 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
illac | +0.448 |
Leaks | +0.433 |
ILY | +0.425 |
CLASS | +0.417 |
Nib | +0.416 |
Neg logit contributions | |
angered | -0.632 |
genre | -0.581 |
adem | -0.530 |
bnb | -0.524 |
arios | -0.520 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
angered | +1.738 |
genre | +1.523 |
adem | +1.282 |
bnb | +1.277 |
arios | +1.237 |
Neg logit contributions | |
illac | -2.777 |
Leaks | -2.706 |
ILY | -2.675 |
Nib | -2.648 |
ャ | -2.635 |
Token | this |
Token ID | 428 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
angered | +4.287 |
genre | +3.801 |
adem | +3.331 |
bnb | +3.271 |
argo | +3.225 |
Neg logit contributions | |
illac | -4.921 |
Leaks | -4.776 |
ILY | -4.686 |
ャ | -4.608 |
Nib | -4.582 |
Token | comment |
Token ID | 2912 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
illac | +0.138 |
Leaks | +0.134 |
ILY | +0.133 |
Nib | +0.132 |
CLASS | +0.132 |
Neg logit contributions | |
angered | -0.155 |
genre | -0.141 |
adem | -0.127 |
bnb | -0.125 |
arios | -0.124 |
Token | on |
Token ID | 319 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
angered | +0.599 |
genre | +0.555 |
adem | +0.507 |
bnb | +0.502 |
arios | +0.496 |
Neg logit contributions | |
illac | -0.340 |
Leaks | -0.321 |
ILY | -0.316 |
Nib | -0.310 |
CLASS | -0.307 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
angered | +0.136 |
genre | +0.122 |
adem | +0.107 |
bnb | +0.106 |
arios | +0.104 |
Neg logit contributions | |
illac | -0.157 |
Leaks | -0.152 |
ILY | -0.150 |
Nib | -0.148 |
CLASS | -0.147 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
angered | +1.022 |
genre | +0.901 |
adem | +0.770 |
bnb | +0.757 |
arios | +0.738 |
Neg logit contributions | |
illac | -1.557 |
Leaks | -1.512 |
ILY | -1.497 |
Nib | -1.480 |
CLASS | -1.471 |
Token | 14 |
Token ID | 1415 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
illac | +0.502 |
Leaks | +0.477 |
ILY | +0.472 |
Nib | +0.470 |
CLASS | +0.462 |
Neg logit contributions | |
angered | -0.570 |
genre | -0.523 |
adem | -0.464 |
bnb | -0.458 |
arios | -0.451 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
angered | +1.136 |
genre | +1.034 |
adem | +0.923 |
bnb | +0.918 |
arios | +0.896 |
Neg logit contributions | |
illac | -1.009 |
Leaks | -0.977 |
ILY | -0.955 |
Nib | -0.933 |
ャ | -0.931 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
angered | +2.508 |
genre | +2.257 |
adem | +1.996 |
bnb | +1.977 |
arios | +1.951 |
Neg logit contributions | |
illac | -2.430 |
Leaks | -2.322 |
ILY | -2.299 |
Nib | -2.260 |
ャ | -2.256 |
Token |
|
Token ID | 198 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
illac | +0.326 |
Leaks | +0.317 |
ILY | +0.312 |
Nib | +0.308 |
CLASS | +0.306 |
Neg logit contributions | |
angered | -0.397 |
genre | -0.364 |
adem | -0.329 |
bnb | -0.325 |
arios | -0.320 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
illac | +0.599 |
Leaks | +0.581 |
ILY | +0.572 |
CLASS | +0.564 |
ャ | +0.553 |
Neg logit contributions | |
angered | -0.893 |
genre | -0.820 |
adem | -0.751 |
bnb | -0.746 |
arios | -0.741 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
angered | +1.867 |
genre | +1.640 |
adem | +1.381 |
bnb | +1.366 |
arios | +1.330 |
Neg logit contributions | |
illac | -3.019 |
Leaks | -2.960 |
ILY | -2.905 |
Nib | -2.881 |
ャ | -2.875 |
Token | this |
Token ID | 428 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
angered | +4.252 |
genre | +3.745 |
adem | +3.387 |
bnb | +3.331 |
arios | +3.257 |
Neg logit contributions | |
Leaks | -4.729 |
illac | -4.720 |
ILY | -4.639 |
Nib | -4.524 |
ャ | -4.518 |
Token | comment |
Token ID | 2912 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
illac | +0.329 |
ILY | +0.317 |
Leaks | +0.315 |
CLASS | +0.314 |
Nib | +0.311 |
Neg logit contributions | |
angered | -0.371 |
genre | -0.341 |
adem | -0.307 |
bnb | -0.297 |
arios | -0.296 |
Token | on |
Token ID | 319 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
angered | +0.145 |
genre | +0.134 |
adem | +0.123 |
bnb | +0.121 |
arios | +0.120 |
Neg logit contributions | |
illac | -0.084 |
Leaks | -0.080 |
ILY | -0.079 |
Nib | -0.077 |
ャ | -0.076 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
illac | +0.148 |
Leaks | +0.143 |
ILY | +0.142 |
Nib | +0.140 |
CLASS | +0.139 |
Neg logit contributions | |
angered | -0.130 |
genre | -0.117 |
adem | -0.103 |
bnb | -0.102 |
arios | -0.100 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
angered | +0.682 |
genre | +0.579 |
bnb | +0.490 |
adem | +0.487 |
arios | +0.470 |
Neg logit contributions | |
illac | -1.200 |
Leaks | -1.179 |
Nib | -1.146 |
ャ | -1.144 |
ILY | -1.144 |
Token | PT |
Token ID | 11571 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
illac | +0.025 |
Leaks | +0.024 |
ILY | +0.024 |
Nib | +0.024 |
CLASS | +0.023 |
Neg logit contributions | |
angered | -0.027 |
genre | -0.025 |
adem | -0.022 |
bnb | -0.022 |
arios | -0.022 |
Token | PowerPoint |
Token ID | 43563 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
angered | +0.712 |
genre | +0.659 |
adem | +0.584 |
bnb | +0.566 |
arios | +0.563 |
Neg logit contributions | |
illac | -0.641 |
ILY | -0.610 |
Leaks | -0.602 |
ャ | -0.594 |
Nib | -0.583 |
Token | slide |
Token ID | 10649 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
angered | +1.995 |
genre | +1.809 |
adem | +1.562 |
bnb | +1.513 |
arios | +1.494 |
Neg logit contributions | |
illac | -2.431 |
ILY | -2.357 |
Leaks | -2.318 |
ャ | -2.309 |
CLASS | -2.269 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
angered | +1.398 |
genre | +1.269 |
adem | +1.131 |
bnb | +1.118 |
arios | +1.098 |
Neg logit contributions | |
illac | -1.293 |
Leaks | -1.234 |
ILY | -1.227 |
Nib | -1.206 |
ャ | -1.202 |
Token |
|
Token ID | 198 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
illac | +0.344 |
Leaks | +0.334 |
ILY | +0.328 |
Nib | +0.324 |
CLASS | +0.322 |
Neg logit contributions | |
angered | -0.415 |
genre | -0.381 |
adem | -0.343 |
bnb | -0.340 |
arios | -0.335 |
Token | Power |
Token ID | 13434 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
illac | +0.242 |
Leaks | +0.225 |
ILY | +0.220 |
Nib | +0.215 |
CLASS | +0.212 |
Neg logit contributions | |
angered | -0.715 |
genre | -0.671 |
adem | -0.622 |
bnb | -0.617 |
arios | -0.612 |
Token | Point |
Token ID | 12727 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
angered | +4.871 |
genre | +4.497 |
adem | +4.036 |
bnb | +3.991 |
arios | +3.945 |
Neg logit contributions | |
illac | -4.083 |
Leaks | -3.903 |
ILY | -3.859 |
Nib | -3.785 |
CLASS | -3.757 |
Token | slide |
Token ID | 10649 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
angered | +1.032 |
genre | +0.933 |
adem | +0.833 |
bnb | +0.831 |
arios | +0.808 |
Neg logit contributions | |
illac | -0.986 |
Leaks | -0.964 |
CLASS | -0.943 |
Nib | -0.940 |
ILY | -0.937 |
Token | PNG |
Token ID | 36182 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
angered | +1.405 |
genre | +1.267 |
adem | +1.094 |
bnb | +1.060 |
arios | +1.037 |
Neg logit contributions | |
illac | -1.848 |
ャ | -1.772 |
Leaks | -1.766 |
ILY | -1.764 |
Nib | -1.734 |
Token | larger |
Token ID | 4025 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
angered | +1.392 |
genre | +1.258 |
adem | +1.110 |
bnb | +1.099 |
arios | +1.076 |
Neg logit contributions | |
illac | -1.520 |
Leaks | -1.477 |
ILY | -1.457 |
Nib | -1.442 |
CLASS | -1.437 |
Token | image |
Token ID | 2939 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
angered | +0.703 |
genre | +0.617 |
adem | +0.519 |
bnb | +0.517 |
arios | +0.497 |
Neg logit contributions | |
illac | -1.164 |
Leaks | -1.143 |
Nib | -1.124 |
ILY | -1.124 |
CLASS | -1.112 |
Token | 27 |
Token ID | 1983 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
illac | +0.934 |
Leaks | +0.902 |
ILY | +0.889 |
Nib | +0.878 |
CLASS | +0.873 |
Neg logit contributions | |
angered | -1.054 |
genre | -0.963 |
adem | -0.863 |
bnb | -0.852 |
arios | -0.840 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
angered | +1.348 |
genre | +1.228 |
adem | +1.100 |
bnb | +1.091 |
arios | +1.070 |
Neg logit contributions | |
illac | -1.141 |
Leaks | -1.099 |
ILY | -1.080 |
Nib | -1.062 |
ャ | -1.053 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
angered | +1.939 |
genre | +1.755 |
adem | +1.553 |
bnb | +1.536 |
arios | +1.515 |
Neg logit contributions | |
illac | -1.854 |
Leaks | -1.768 |
ILY | -1.748 |
Nib | -1.723 |
ャ | -1.717 |
Token |
|
Token ID | 198 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
illac | +0.326 |
Leaks | +0.316 |
ILY | +0.311 |
Nib | +0.307 |
CLASS | +0.305 |
Neg logit contributions | |
angered | -0.391 |
genre | -0.359 |
adem | -0.323 |
bnb | -0.320 |
arios | -0.315 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
illac | +0.632 |
Leaks | +0.612 |
ILY | +0.602 |
CLASS | +0.589 |
Nib | +0.586 |
Neg logit contributions | |
angered | -0.901 |
genre | -0.829 |
adem | -0.756 |
bnb | -0.747 |
arios | -0.742 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
angered | +1.622 |
genre | +1.425 |
adem | +1.202 |
bnb | +1.196 |
arios | +1.159 |
Neg logit contributions | |
illac | -2.572 |
Leaks | -2.507 |
ILY | -2.478 |
Nib | -2.454 |
ャ | -2.441 |
Token | this |
Token ID | 428 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
angered | +4.170 |
genre | +3.709 |
adem | +3.249 |
bnb | +3.193 |
argo | +3.147 |
Neg logit contributions | |
illac | -4.737 |
Leaks | -4.598 |
ILY | -4.508 |
ャ | -4.438 |
Nib | -4.410 |
Token | comment |
Token ID | 2912 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
illac | +0.230 |
Leaks | +0.225 |
ILY | +0.222 |
Nib | +0.221 |
CLASS | +0.220 |
Neg logit contributions | |
angered | -0.259 |
genre | -0.236 |
adem | -0.212 |
bnb | -0.210 |
arios | -0.207 |
Token | on |
Token ID | 319 |
Feature activation | +4.56e-03 |
Pos logit contributions | |
angered | +0.221 |
genre | +0.205 |
adem | +0.188 |
bnb | +0.186 |
arios | +0.184 |
Neg logit contributions | |
illac | -0.121 |
Leaks | -0.115 |
ILY | -0.113 |
Nib | -0.111 |
CLASS | -0.110 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
angered | +0.012 |
genre | +0.011 |
adem | +0.009 |
bnb | +0.009 |
arios | +0.009 |
Neg logit contributions | |
illac | -0.014 |
Leaks | -0.013 |
ILY | -0.013 |
Nib | -0.013 |
CLASS | -0.013 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
angered | +0.798 |
genre | +0.706 |
adem | +0.605 |
bnb | +0.595 |
arios | +0.582 |
Neg logit contributions | |
illac | -1.192 |
Leaks | -1.159 |
ILY | -1.147 |
Nib | -1.135 |
CLASS | -1.130 |
Token | , |
Token ID | 11 |
Feature activation | +6.51e-03 |
Pos logit contributions | |
angered | +0.251 |
genre | +0.228 |
adem | +0.203 |
bnb | +0.200 |
arios | +0.197 |
Neg logit contributions | |
illac | -0.245 |
Leaks | -0.237 |
ILY | -0.234 |
Nib | -0.232 |
CLASS | -0.230 |
Token | Mikhail |
Token ID | 42040 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
angered | +0.020 |
genre | +0.018 |
adem | +0.016 |
bnb | +0.016 |
arios | +0.016 |
Neg logit contributions | |
illac | -0.017 |
Leaks | -0.016 |
ILY | -0.016 |
CLASS | -0.016 |
Nib | -0.016 |
Token | Al |
Token ID | 978 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
angered | +0.660 |
genre | +0.564 |
adem | +0.468 |
bnb | +0.443 |
arios | +0.434 |
Neg logit contributions | |
illac | -1.471 |
Leaks | -1.444 |
ILY | -1.422 |
CLASS | -1.408 |
Nib | -1.406 |
Token | "] |
Token ID | 8973 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
illac | +0.029 |
Leaks | +0.028 |
ILY | +0.028 |
Nib | +0.028 |
CLASS | +0.027 |
Neg logit contributions | |
angered | -0.032 |
genre | -0.030 |
adem | -0.027 |
bnb | -0.026 |
arios | -0.026 |
Token | [ |
Token ID | 685 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
illac | +0.256 |
Leaks | +0.248 |
ILY | +0.245 |
Nib | +0.243 |
CLASS | +0.241 |
Neg logit contributions | |
angered | -0.215 |
genre | -0.194 |
adem | -0.170 |
bnb | -0.167 |
arios | -0.164 |
Token | Result |
Token ID | 23004 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
angered | +1.316 |
genre | +1.207 |
adem | +1.079 |
bnb | +1.059 |
arios | +1.053 |
Neg logit contributions | |
illac | -1.116 |
Leaks | -1.067 |
ILY | -1.050 |
ャ | -1.042 |
Nib | -1.036 |
Token | " |
Token ID | 366 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
angered | +3.104 |
genre | +2.673 |
adem | +2.197 |
bnb | +2.186 |
argo | +2.090 |
Neg logit contributions | |
illac | -5.534 |
Leaks | -5.335 |
ILY | -5.289 |
ャ | -5.250 |
CLASS | -5.213 |
Token | 1 |
Token ID | 16 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
illac | +0.394 |
Leaks | +0.378 |
ILY | +0.373 |
Nib | +0.369 |
CLASS | +0.366 |
Neg logit contributions | |
angered | -0.495 |
genre | -0.455 |
adem | -0.410 |
bnb | -0.405 |
arios | -0.399 |
Token | / |
Token ID | 14 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
illac | +0.226 |
Leaks | +0.218 |
ILY | +0.215 |
Nib | +0.212 |
CLASS | +0.211 |
Neg logit contributions | |
angered | -0.275 |
genre | -0.252 |
adem | -0.227 |
bnb | -0.224 |
arios | -0.221 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
angered | +0.088 |
genre | +0.081 |
adem | +0.073 |
bnb | +0.072 |
arios | +0.071 |
Neg logit contributions | |
illac | -0.065 |
Leaks | -0.062 |
ILY | -0.061 |
Nib | -0.061 |
CLASS | -0.060 |
Token | - |
Token ID | 12 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
illac | +0.416 |
Leaks | +0.400 |
ILY | +0.394 |
Nib | +0.389 |
CLASS | +0.386 |
Neg logit contributions | |
angered | -0.533 |
genre | -0.490 |
adem | -0.442 |
bnb | -0.437 |
arios | -0.431 |
Token | ( |
Token ID | 357 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
illac | +0.322 |
Leaks | +0.312 |
ILY | +0.307 |
Nib | +0.305 |
CLASS | +0.303 |
Neg logit contributions | |
angered | -0.346 |
genre | -0.315 |
adem | -0.281 |
bnb | -0.277 |
arios | -0.274 |
Token | old |
Token ID | 727 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
illac | +0.070 |
Leaks | +0.068 |
ILY | +0.067 |
Nib | +0.066 |
CLASS | +0.066 |
Neg logit contributions | |
angered | -0.076 |
genre | -0.069 |
adem | -0.062 |
bnb | -0.061 |
arios | -0.060 |
Token | ) |
Token ID | 8 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
illac | +0.671 |
Leaks | +0.645 |
ILY | +0.634 |
Nib | +0.626 |
CLASS | +0.622 |
Neg logit contributions | |
angered | -0.868 |
genre | -0.796 |
adem | -0.721 |
bnb | -0.713 |
arios | -0.700 |
Token | website |
Token ID | 3052 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
angered | +0.987 |
genre | +0.894 |
adem | +0.797 |
bnb | +0.788 |
arios | +0.772 |
Neg logit contributions | |
illac | -0.989 |
Leaks | -0.952 |
ILY | -0.941 |
Nib | -0.924 |
CLASS | -0.923 |
Token | . |
Token ID | 13 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
angered | +0.187 |
genre | +0.170 |
adem | +0.152 |
bnb | +0.150 |
arios | +0.148 |
Neg logit contributions | |
illac | -0.174 |
Leaks | -0.168 |
ILY | -0.165 |
Nib | -0.163 |
CLASS | -0.162 |
Token | Nevertheless |
Token ID | 15933 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
illac | +0.148 |
Leaks | +0.142 |
ILY | +0.140 |
Nib | +0.139 |
CLASS | +0.138 |
Neg logit contributions | |
angered | -0.182 |
genre | -0.166 |
adem | -0.150 |
bnb | -0.148 |
arios | -0.146 |
Token | we |
Token ID | 356 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
angered | +3.749 |
genre | +3.383 |
bnb | +3.017 |
adem | +2.992 |
argo | +2.827 |
Neg logit contributions | |
illac | -4.634 |
Leaks | -4.528 |
ILY | -4.413 |
Nib | -4.397 |
CLASS | -4.338 |
Token | worked |
Token ID | 3111 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
angered | +0.939 |
genre | +0.861 |
adem | +0.783 |
bnb | +0.781 |
arios | +0.767 |
Neg logit contributions | |
illac | -0.645 |
Leaks | -0.618 |
ILY | -0.604 |
Nib | -0.598 |
CLASS | -0.591 |
Token | hard |
Token ID | 1327 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
illac | +0.142 |
Leaks | +0.135 |
ILY | +0.132 |
Nib | +0.131 |
CLASS | +0.130 |
Neg logit contributions | |
angered | -0.218 |
genre | -0.201 |
adem | -0.183 |
bnb | -0.182 |
arios | -0.180 |
Token | to |
Token ID | 284 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
angered | +0.241 |
genre | +0.223 |
adem | +0.203 |
bnb | +0.202 |
arios | +0.200 |
Neg logit contributions | |
illac | -0.154 |
Leaks | -0.147 |
ILY | -0.143 |
Nib | -0.142 |
CLASS | -0.141 |
Token | cover |
Token ID | 3002 |
Feature activation | -6.12e-03 |
Pos logit contributions | |
illac | +0.140 |
Leaks | +0.134 |
ILY | +0.132 |
Nib | +0.131 |
CLASS | +0.130 |
Neg logit contributions | |
angered | -0.166 |
genre | -0.152 |
adem | -0.137 |
bnb | -0.135 |
arios | -0.133 |
Token | = |
Token ID | 796 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
angered | +0.760 |
genre | +0.704 |
adem | +0.638 |
bnb | +0.627 |
arios | +0.614 |
Neg logit contributions | |
illac | -0.608 |
Leaks | -0.581 |
ILY | -0.574 |
CLASS | -0.569 |
Nib | -0.569 |
Token | $ |
Token ID | 720 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
illac | +2.035 |
Leaks | +1.964 |
ILY | +1.940 |
Nib | +1.932 |
CLASS | +1.927 |
Neg logit contributions | |
angered | -2.167 |
genre | -1.974 |
adem | -1.751 |
bnb | -1.739 |
arios | -1.710 |
Token | b |
Token ID | 65 |
Feature activation | +9.94e-02 |
Pos logit contributions | |
angered | +1.401 |
genre | +1.302 |
adem | +1.177 |
bnb | +1.148 |
arios | +1.126 |
Neg logit contributions | |
illac | -1.083 |
Leaks | -1.038 |
ILY | -1.026 |
Nib | -1.019 |
CLASS | -1.011 |
Token | mp |
Token ID | 3149 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
angered | +0.286 |
genre | +0.261 |
adem | +0.232 |
bnb | +0.229 |
arios | +0.225 |
Neg logit contributions | |
illac | -0.274 |
Leaks | -0.264 |
ILY | -0.261 |
Nib | -0.259 |
CLASS | -0.257 |
Token | | |
Token ID | 930 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
angered | +0.214 |
genre | +0.195 |
adem | +0.174 |
bnb | +0.172 |
arios | +0.169 |
Neg logit contributions | |
illac | -0.200 |
Leaks | -0.192 |
ILY | -0.189 |
Nib | -0.187 |
CLASS | -0.185 |
Token | Select |
Token ID | 9683 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
illac | +0.116 |
Leaks | +0.112 |
ILY | +0.111 |
Nib | +0.109 |
CLASS | +0.108 |
Neg logit contributions | |
angered | -0.129 |
genre | -0.117 |
adem | -0.105 |
bnb | -0.104 |
arios | -0.102 |
Token | Width |
Token ID | 38807 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
angered | +4.251 |
genre | +3.887 |
adem | +3.482 |
arios | +3.343 |
bnb | +3.305 |
Neg logit contributions | |
illac | -4.036 |
ILY | -3.815 |
Leaks | -3.802 |
ャ | -3.712 |
CLASS | -3.653 |
Token | , |
Token ID | 11 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
angered | +0.378 |
genre | +0.346 |
adem | +0.309 |
bnb | +0.303 |
arios | +0.299 |
Neg logit contributions | |
illac | -0.350 |
Leaks | -0.336 |
ILY | -0.330 |
Nib | -0.326 |
CLASS | -0.324 |
Token | Height |
Token ID | 23106 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
illac | +0.160 |
Leaks | +0.151 |
ILY | +0.150 |
Nib | +0.147 |
CLASS | +0.146 |
Neg logit contributions | |
angered | -0.242 |
genre | -0.224 |
adem | -0.203 |
bnb | -0.201 |
arios | -0.198 |
Token | } |
Token ID | 1782 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
illac | +0.300 |
Leaks | +0.289 |
ILY | +0.285 |
Nib | +0.282 |
CLASS | +0.280 |
Neg logit contributions | |
angered | -0.318 |
genre | -0.290 |
adem | -0.258 |
bnb | -0.255 |
arios | -0.251 |
Token | else |
Token ID | 2073 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
illac | +1.170 |
Leaks | +1.130 |
ILY | +1.115 |
Nib | +1.102 |
CLASS | +1.095 |
Neg logit contributions | |
angered | -1.268 |
genre | -1.156 |
adem | -1.032 |
bnb | -1.019 |
arios | -1.004 |
Token | pling |
Token ID | 11347 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
angered | +0.212 |
genre | +0.180 |
adem | +0.143 |
bnb | +0.138 |
arios | +0.135 |
Neg logit contributions | |
illac | -0.514 |
Leaks | -0.500 |
ILY | -0.498 |
Nib | -0.492 |
CLASS | -0.491 |
Token | subway |
Token ID | 19612 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
angered | +0.491 |
genre | +0.451 |
adem | +0.406 |
bnb | +0.405 |
arios | +0.400 |
Neg logit contributions | |
illac | -0.376 |
Leaks | -0.363 |
ILY | -0.361 |
ャ | -0.355 |
Nib | -0.352 |
Token | station |
Token ID | 4429 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
angered | +0.882 |
genre | +0.794 |
adem | +0.705 |
bnb | +0.694 |
arios | +0.691 |
Neg logit contributions | |
illac | -0.984 |
Leaks | -0.951 |
ILY | -0.947 |
ャ | -0.927 |
CLASS | -0.926 |
Token | in |
Token ID | 287 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
angered | +0.503 |
genre | +0.455 |
adem | +0.410 |
bnb | +0.407 |
arios | +0.400 |
Neg logit contributions | |
illac | -0.466 |
Leaks | -0.452 |
ILY | -0.448 |
ャ | -0.437 |
Nib | -0.437 |
Token | Et |
Token ID | 17906 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
angered | +0.145 |
genre | +0.131 |
adem | +0.116 |
bnb | +0.114 |
arios | +0.113 |
Neg logit contributions | |
illac | -0.152 |
Leaks | -0.147 |
ILY | -0.146 |
ャ | -0.143 |
CLASS | -0.143 |
Token | obic |
Token ID | 20803 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
angered | +1.569 |
genre | +1.450 |
adem | +1.325 |
bnb | +1.305 |
arios | +1.290 |
Neg logit contributions | |
illac | -0.981 |
Leaks | -0.949 |
ILY | -0.934 |
Nib | -0.914 |
CLASS | -0.911 |
Token | oke |
Token ID | 2088 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
angered | +3.133 |
genre | +2.804 |
bnb | +2.373 |
adem | +2.344 |
arios | +2.281 |
Neg logit contributions | |
illac | -5.054 |
ILY | -4.877 |
ャ | -4.781 |
Leaks | -4.756 |
CLASS | -4.747 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
angered | +1.148 |
genre | +1.038 |
bnb | +0.924 |
adem | +0.918 |
arios | +0.912 |
Neg logit contributions | |
illac | -1.126 |
Leaks | -1.096 |
ILY | -1.084 |
ャ | -1.073 |
Nib | -1.064 |
Token |
|
Token ID | 198 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
illac | +0.427 |
Leaks | +0.411 |
ILY | +0.406 |
Nib | +0.398 |
CLASS | +0.397 |
Neg logit contributions | |
angered | -0.479 |
genre | -0.433 |
adem | -0.388 |
bnb | -0.385 |
arios | -0.378 |
Token |
|
Token ID | 198 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
illac | +0.638 |
Leaks | +0.620 |
ILY | +0.610 |
Nib | +0.602 |
CLASS | +0.597 |
Neg logit contributions | |
angered | -0.779 |
genre | -0.716 |
adem | -0.646 |
bnb | -0.638 |
arios | -0.628 |
Token | Police |
Token ID | 9039 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
illac | +0.655 |
Leaks | +0.622 |
ILY | +0.614 |
Nib | +0.612 |
CLASS | +0.608 |
Neg logit contributions | |
angered | -0.910 |
genre | -0.839 |
adem | -0.758 |
bnb | -0.749 |
arios | -0.739 |
Token | . |
Token ID | 13 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
angered | +0.076 |
genre | +0.069 |
adem | +0.061 |
bnb | +0.061 |
arios | +0.060 |
Neg logit contributions | |
illac | -0.074 |
Leaks | -0.071 |
ILY | -0.071 |
Nib | -0.069 |
CLASS | -0.069 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
illac | +0.422 |
Leaks | +0.407 |
ILY | +0.400 |
Nib | +0.396 |
CLASS | +0.394 |
Neg logit contributions | |
angered | -0.517 |
genre | -0.474 |
adem | -0.427 |
bnb | -0.422 |
arios | -0.416 |
Token | For |
Token ID | 1890 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
angered | +0.431 |
genre | +0.399 |
adem | +0.358 |
bnb | +0.351 |
arios | +0.347 |
Neg logit contributions | |
illac | -0.330 |
Nib | -0.310 |
Leaks | -0.309 |
ILY | -0.307 |
CLASS | -0.306 |
Token | rapper |
Token ID | 25670 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
illac | +0.235 |
Leaks | +0.226 |
ILY | +0.223 |
Nib | +0.220 |
CLASS | +0.219 |
Neg logit contributions | |
angered | -0.292 |
genre | -0.267 |
adem | -0.241 |
bnb | -0.238 |
arios | -0.235 |
Token | Off |
Token ID | 3242 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
illac | +0.707 |
Leaks | +0.684 |
ILY | +0.675 |
Nib | +0.667 |
CLASS | +0.663 |
Neg logit contributions | |
angered | -0.708 |
genre | -0.644 |
adem | -0.572 |
bnb | -0.564 |
arios | -0.556 |
Token | set |
Token ID | 2617 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
angered | +0.116 |
genre | +0.107 |
adem | +0.096 |
bnb | +0.095 |
arios | +0.094 |
Neg logit contributions | |
illac | -0.091 |
Leaks | -0.087 |
ILY | -0.087 |
Nib | -0.085 |
CLASS | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
angered | +4.108 |
genre | +3.795 |
adem | +3.330 |
arios | +3.289 |
bnb | +3.288 |
Neg logit contributions | |
illac | -3.900 |
ILY | -3.782 |
ャ | -3.694 |
Leaks | -3.688 |
Nib | -3.644 |
Token | of |
Token ID | 286 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
illac | +0.445 |
Leaks | +0.429 |
ILY | +0.423 |
Nib | +0.419 |
CLASS | +0.417 |
Neg logit contributions | |
angered | -0.497 |
genre | -0.454 |
adem | -0.407 |
bnb | -0.402 |
arios | -0.396 |
Token | the |
Token ID | 262 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
illac | +0.736 |
Leaks | +0.710 |
ILY | +0.699 |
Nib | +0.690 |
CLASS | +0.685 |
Neg logit contributions | |
angered | -0.910 |
genre | -0.836 |
adem | -0.751 |
bnb | -0.742 |
arios | -0.732 |
Token | hip |
Token ID | 10359 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
illac | +0.588 |
Leaks | +0.568 |
ILY | +0.560 |
Nib | +0.554 |
CLASS | +0.550 |
Neg logit contributions | |
angered | -0.639 |
genre | -0.583 |
adem | -0.520 |
bnb | -0.514 |
arios | -0.506 |
Token | - |
Token ID | 12 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
illac | +0.568 |
Leaks | +0.547 |
ILY | +0.539 |
Nib | +0.532 |
CLASS | +0.530 |
Neg logit contributions | |
angered | -0.710 |
genre | -0.651 |
adem | -0.586 |
bnb | -0.580 |
arios | -0.572 |
Token | and |
Token ID | 392 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
angered | +1.255 |
genre | +1.144 |
adem | +1.027 |
bnb | +1.004 |
arios | +0.993 |
Neg logit contributions | |
illac | -1.163 |
Leaks | -1.120 |
ILY | -1.112 |
Nib | -1.093 |
CLASS | -1.091 |
Token | Property |
Token ID | 21746 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
illac | +0.804 |
Leaks | +0.765 |
ILY | +0.755 |
Nib | +0.742 |
CLASS | +0.737 |
Neg logit contributions | |
angered | -1.320 |
genre | -1.222 |
adem | -1.115 |
bnb | -1.102 |
arios | -1.091 |
Token | B |
Token ID | 347 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
angered | +0.678 |
genre | +0.622 |
adem | +0.561 |
bnb | +0.551 |
arios | +0.544 |
Neg logit contributions | |
illac | -0.555 |
Leaks | -0.533 |
ILY | -0.525 |
Nib | -0.514 |
ャ | -0.511 |
Token | ounds |
Token ID | 3733 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
angered | +0.258 |
genre | +0.237 |
adem | +0.212 |
bnb | +0.207 |
arios | +0.204 |
Neg logit contributions | |
illac | -0.239 |
Leaks | -0.230 |
ILY | -0.227 |
Nib | -0.226 |
CLASS | -0.223 |
Token | | |
Token ID | 930 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
illac | +0.572 |
Leaks | +0.550 |
ILY | +0.543 |
Nib | +0.535 |
CLASS | +0.531 |
Neg logit contributions | |
angered | -0.658 |
genre | -0.603 |
adem | -0.542 |
bnb | -0.535 |
arios | -0.526 |
Token | Select |
Token ID | 9683 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
angered | +0.401 |
genre | +0.369 |
adem | +0.333 |
bnb | +0.329 |
arios | +0.324 |
Neg logit contributions | |
illac | -0.301 |
Leaks | -0.289 |
ILY | -0.286 |
Nib | -0.278 |
CLASS | -0.276 |
Token | Width |
Token ID | 38807 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
angered | +4.107 |
genre | +3.741 |
adem | +3.396 |
bnb | +3.262 |
arios | +3.235 |
Neg logit contributions | |
illac | -3.739 |
ILY | -3.566 |
Leaks | -3.484 |
ャ | -3.435 |
theless | -3.347 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
angered | +0.145 |
genre | +0.132 |
adem | +0.117 |
bnb | +0.115 |
arios | +0.113 |
Neg logit contributions | |
illac | -0.153 |
Leaks | -0.147 |
ILY | -0.145 |
Nib | -0.142 |
ャ | -0.142 |
Token | Height |
Token ID | 23106 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
angered | +0.055 |
genre | +0.052 |
adem | +0.048 |
bnb | +0.047 |
arios | +0.046 |
Neg logit contributions | |
illac | -0.024 |
Leaks | -0.022 |
ILY | -0.022 |
CLASS | -0.021 |
Nib | -0.021 |
Token | Write |
Token ID | 19430 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
illac | +0.270 |
Leaks | +0.261 |
ILY | +0.258 |
Nib | +0.253 |
CLASS | +0.252 |
Neg logit contributions | |
angered | -0.257 |
genre | -0.234 |
adem | -0.207 |
bnb | -0.204 |
arios | -0.200 |
Token | - |
Token ID | 12 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
angered | +0.580 |
genre | +0.534 |
adem | +0.479 |
bnb | +0.472 |
arios | +0.466 |
Neg logit contributions | |
illac | -0.496 |
Leaks | -0.473 |
ILY | -0.469 |
CLASS | -0.460 |
Nib | -0.459 |
Token | Mill |
Token ID | 9212 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
angered | +0.723 |
genre | +0.658 |
adem | +0.587 |
bnb | +0.578 |
arios | +0.572 |
Neg logit contributions | |
illac | -0.656 |
Leaks | -0.633 |
ILY | -0.626 |
ャ | -0.618 |
CLASS | -0.607 |
Token | Rd |
Token ID | 20769 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
angered | +1.124 |
genre | +1.017 |
adem | +0.926 |
bnb | +0.913 |
arios | +0.910 |
Neg logit contributions | |
illac | -0.961 |
Leaks | -0.935 |
ILY | -0.934 |
ャ | -0.913 |
Nib | -0.910 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
angered | +1.651 |
genre | +1.491 |
adem | +1.316 |
bnb | +1.289 |
arios | +1.272 |
Neg logit contributions | |
illac | -1.704 |
Leaks | -1.679 |
ILY | -1.641 |
ャ | -1.617 |
CLASS | -1.609 |
Token | in |
Token ID | 287 |
Feature activation | +5.38e-03 |
Pos logit contributions | |
illac | +0.279 |
Leaks | +0.269 |
ILY | +0.265 |
Nib | +0.260 |
CLASS | +0.259 |
Neg logit contributions | |
angered | -0.318 |
genre | -0.290 |
adem | -0.259 |
bnb | -0.256 |
arios | -0.252 |
Token | Et |
Token ID | 17906 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
angered | +0.015 |
genre | +0.014 |
adem | +0.012 |
bnb | +0.012 |
arios | +0.012 |
Neg logit contributions | |
illac | -0.015 |
Leaks | -0.015 |
ILY | -0.014 |
Nib | -0.014 |
CLASS | -0.014 |
Token | obic |
Token ID | 20803 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
angered | +1.451 |
genre | +1.337 |
adem | +1.226 |
bnb | +1.202 |
arios | +1.187 |
Neg logit contributions | |
illac | -0.920 |
Leaks | -0.900 |
ILY | -0.886 |
Nib | -0.869 |
CLASS | -0.868 |
Token | oke |
Token ID | 2088 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
angered | +3.122 |
genre | +2.803 |
adem | +2.388 |
bnb | +2.370 |
arios | +2.293 |
Neg logit contributions | |
illac | -4.669 |
ILY | -4.504 |
Leaks | -4.455 |
ャ | -4.426 |
Nib | -4.421 |
Token | � |
Token ID | 447 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
angered | +1.302 |
genre | +1.186 |
adem | +1.052 |
bnb | +1.041 |
arios | +1.030 |
Neg logit contributions | |
illac | -1.203 |
Leaks | -1.155 |
ILY | -1.146 |
ャ | -1.124 |
Nib | -1.123 |
Token | � |
Token ID | 247 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
illac | +0.274 |
Leaks | +0.265 |
ILY | +0.262 |
Nib | +0.260 |
CLASS | +0.259 |
Neg logit contributions | |
angered | -0.215 |
genre | -0.192 |
adem | -0.168 |
bnb | -0.165 |
arios | -0.162 |
Token | s |
Token ID | 82 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
angered | +0.131 |
genre | +0.120 |
adem | +0.107 |
bnb | +0.106 |
arios | +0.104 |
Neg logit contributions | |
illac | -0.116 |
Leaks | -0.112 |
ILY | -0.110 |
Nib | -0.109 |
CLASS | -0.108 |
Token | Mark |
Token ID | 2940 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
illac | +0.197 |
Leaks | +0.190 |
ILY | +0.188 |
Nib | +0.185 |
CLASS | +0.184 |
Neg logit contributions | |
angered | -0.196 |
genre | -0.178 |
adem | -0.158 |
bnb | -0.155 |
arios | -0.153 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
angered | +1.867 |
genre | +1.640 |
adem | +1.381 |
bnb | +1.366 |
arios | +1.330 |
Neg logit contributions | |
illac | -3.019 |
Leaks | -2.960 |
ILY | -2.905 |
Nib | -2.881 |
ャ | -2.875 |
Token | this |
Token ID | 428 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
angered | +4.252 |
genre | +3.745 |
adem | +3.387 |
bnb | +3.331 |
arios | +3.257 |
Neg logit contributions | |
Leaks | -4.729 |
illac | -4.720 |
ILY | -4.639 |
Nib | -4.524 |
ャ | -4.518 |
Token | comment |
Token ID | 2912 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
illac | +0.329 |
ILY | +0.317 |
Leaks | +0.315 |
CLASS | +0.314 |
Nib | +0.311 |
Neg logit contributions | |
angered | -0.371 |
genre | -0.341 |
adem | -0.307 |
bnb | -0.297 |
arios | -0.296 |
Token | on |
Token ID | 319 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
angered | +0.145 |
genre | +0.134 |
adem | +0.123 |
bnb | +0.121 |
arios | +0.120 |
Neg logit contributions | |
illac | -0.084 |
Leaks | -0.080 |
ILY | -0.079 |
Nib | -0.077 |
ャ | -0.076 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
illac | +0.148 |
Leaks | +0.143 |
ILY | +0.142 |
Nib | +0.140 |
CLASS | +0.139 |
Neg logit contributions | |
angered | -0.130 |
genre | -0.117 |
adem | -0.103 |
bnb | -0.102 |
arios | -0.100 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
angered | +0.682 |
genre | +0.579 |
bnb | +0.490 |
adem | +0.487 |
arios | +0.470 |
Neg logit contributions | |
illac | -1.200 |
Leaks | -1.179 |
Nib | -1.146 |
ャ | -1.144 |
ILY | -1.144 |
Token | this |
Token ID | 428 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
angered | +3.884 |
genre | +3.455 |
adem | +3.092 |
bnb | +3.057 |
arios | +3.005 |
Neg logit contributions | |
illac | -3.879 |
Leaks | -3.833 |
ILY | -3.773 |
Nib | -3.679 |
ャ | -3.649 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
illac | +0.475 |
Leaks | +0.459 |
ILY | +0.455 |
CLASS | +0.453 |
Nib | +0.451 |
Neg logit contributions | |
angered | -0.523 |
genre | -0.478 |
adem | -0.430 |
bnb | -0.423 |
arios | -0.418 |
Token | on |
Token ID | 319 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
illac | +0.316 |
Leaks | +0.302 |
ILY | +0.295 |
Nib | +0.291 |
CLASS | +0.289 |
Neg logit contributions | |
angered | -0.612 |
genre | -0.571 |
adem | -0.523 |
bnb | -0.519 |
arios | -0.513 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
illac | +0.397 |
Leaks | +0.383 |
ILY | +0.378 |
Nib | +0.373 |
CLASS | +0.371 |
Neg logit contributions | |
angered | -0.434 |
genre | -0.396 |
adem | -0.353 |
bnb | -0.350 |
arios | -0.344 |
Token |
|
Token ID | 198 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
illac | +1.048 |
Leaks | +1.011 |
ILY | +0.997 |
Nib | +0.985 |
CLASS | +0.979 |
Neg logit contributions | |
angered | -1.208 |
genre | -1.105 |
adem | -0.990 |
bnb | -0.978 |
arios | -0.964 |
Token | been |
Token ID | 587 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
angered | +0.973 |
genre | +0.884 |
adem | +0.787 |
bnb | +0.771 |
arios | +0.763 |
Neg logit contributions | |
illac | -0.906 |
Leaks | -0.873 |
ILY | -0.854 |
Nib | -0.843 |
CLASS | -0.839 |
Token | made |
Token ID | 925 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
angered | +0.244 |
genre | +0.224 |
adem | +0.200 |
bnb | +0.197 |
arios | +0.195 |
Neg logit contributions | |
illac | -0.209 |
Leaks | -0.202 |
ILY | -0.198 |
Nib | -0.195 |
CLASS | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
angered | +1.134 |
genre | +1.041 |
adem | +0.923 |
bnb | +0.915 |
arios | +0.902 |
Neg logit contributions | |
illac | -1.041 |
Leaks | -1.009 |
ILY | -0.986 |
Nib | -0.969 |
ャ | -0.956 |
Token | On |
Token ID | 1550 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
angered | +0.087 |
genre | +0.079 |
adem | +0.071 |
bnb | +0.070 |
arios | +0.069 |
Neg logit contributions | |
illac | -0.076 |
Leaks | -0.073 |
ILY | -0.072 |
Nib | -0.071 |
CLASS | -0.071 |
Token | one |
Token ID | 530 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
angered | +0.755 |
genre | +0.696 |
adem | +0.627 |
bnb | +0.616 |
arios | +0.606 |
Neg logit contributions | |
illac | -0.609 |
Leaks | -0.572 |
ILY | -0.570 |
Nib | -0.554 |
ャ | -0.553 |
Token | hand |
Token ID | 1021 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
angered | +1.614 |
genre | +1.446 |
adem | +1.246 |
bnb | +1.223 |
arios | +1.206 |
Neg logit contributions | |
illac | -2.207 |
Leaks | -2.137 |
ILY | -2.108 |
Nib | -2.081 |
CLASS | -2.075 |
Token | , |
Token ID | 11 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
angered | +3.575 |
genre | +3.256 |
adem | +2.852 |
bnb | +2.771 |
arios | +2.759 |
Neg logit contributions | |
illac | -4.140 |
Leaks | -4.016 |
ILY | -3.885 |
Nib | -3.818 |
ャ | -3.817 |
Token | the |
Token ID | 262 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
angered | +0.130 |
genre | +0.118 |
adem | +0.106 |
bnb | +0.104 |
arios | +0.103 |
Neg logit contributions | |
illac | -0.122 |
Leaks | -0.117 |
ILY | -0.116 |
Nib | -0.114 |
CLASS | -0.113 |
Token | film |
Token ID | 2646 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
illac | +0.207 |
Leaks | +0.200 |
ILY | +0.197 |
Nib | +0.194 |
CLASS | +0.193 |
Neg logit contributions | |
angered | -0.221 |
genre | -0.202 |
adem | -0.179 |
bnb | -0.177 |
arios | -0.175 |
Token | was |
Token ID | 373 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
angered | +0.581 |
genre | +0.532 |
adem | +0.478 |
bnb | +0.471 |
arios | +0.465 |
Neg logit contributions | |
illac | -0.487 |
Leaks | -0.469 |
ILY | -0.462 |
Nib | -0.457 |
CLASS | -0.453 |
Token | turning |
Token ID | 6225 |
Feature activation | -9.26e-03 |
Pos logit contributions | |
illac | +0.027 |
Leaks | +0.026 |
ILY | +0.025 |
Nib | +0.025 |
CLASS | +0.025 |
Neg logit contributions | |
angered | -0.031 |
genre | -0.029 |
adem | -0.026 |
bnb | -0.025 |
arios | -0.025 |
Token | reens |
Token ID | 5681 |
Feature activation | -2.76e-03 |
Pos logit contributions | |
angered | +0.100 |
genre | +0.091 |
adem | +0.081 |
bnb | +0.080 |
arios | +0.079 |
Neg logit contributions | |
illac | -0.089 |
Leaks | -0.086 |
ILY | -0.085 |
Nib | -0.083 |
CLASS | -0.083 |
Token | | |
Token ID | 930 |
Feature activation | -9.19e-03 |
Pos logit contributions | |
illac | +0.007 |
Leaks | +0.007 |
ILY | +0.007 |
Nib | +0.007 |
CLASS | +0.007 |
Neg logit contributions | |
angered | -0.008 |
genre | -0.008 |
adem | -0.007 |
bnb | -0.007 |
arios | -0.007 |
Token | Where |
Token ID | 6350 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
illac | +0.024 |
Leaks | +0.023 |
ILY | +0.023 |
Nib | +0.023 |
CLASS | +0.023 |
Neg logit contributions | |
angered | -0.027 |
genre | -0.025 |
adem | -0.022 |
bnb | -0.022 |
arios | -0.022 |
Token | Primary |
Token ID | 21087 |
Feature activation | -9.98e-02 |
Pos logit contributions | |
angered | +2.609 |
genre | +2.374 |
adem | +2.148 |
arios | +2.071 |
bnb | +2.029 |
Neg logit contributions | |
illac | -2.311 |
ILY | -2.225 |
Leaks | -2.210 |
ャ | -2.155 |
Nib | -2.135 |
Token | | |
Token ID | 930 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
illac | +0.246 |
Leaks | +0.235 |
ILY | +0.232 |
Nib | +0.229 |
CLASS | +0.227 |
Neg logit contributions | |
angered | -0.315 |
genre | -0.290 |
adem | -0.264 |
bnb | -0.258 |
arios | -0.254 |
Token | Select |
Token ID | 9683 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
illac | +0.526 |
Leaks | +0.506 |
ILY | +0.500 |
Nib | +0.491 |
CLASS | +0.487 |
Neg logit contributions | |
angered | -0.671 |
genre | -0.616 |
adem | -0.556 |
bnb | -0.549 |
arios | -0.541 |
Token | - |
Token ID | 532 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
angered | +4.245 |
genre | +3.860 |
adem | +3.532 |
arios | +3.368 |
bnb | +3.363 |
Neg logit contributions | |
illac | -3.419 |
ILY | -3.268 |
Leaks | -3.243 |
ャ | -3.156 |
Chem | -3.050 |
Token | Exp |
Token ID | 16870 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
angered | +1.176 |
genre | +1.084 |
adem | +0.966 |
bnb | +0.943 |
arios | +0.934 |
Neg logit contributions | |
illac | -1.023 |
Leaks | -0.976 |
ILY | -0.968 |
Nib | -0.955 |
ャ | -0.952 |
Token | and |
Token ID | 392 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
angered | +1.255 |
genre | +1.144 |
adem | +1.027 |
bnb | +1.004 |
arios | +0.993 |
Neg logit contributions | |
illac | -1.163 |
Leaks | -1.120 |
ILY | -1.112 |
Nib | -1.093 |
CLASS | -1.091 |
Token | Property |
Token ID | 21746 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
illac | +0.804 |
Leaks | +0.765 |
ILY | +0.755 |
Nib | +0.742 |
CLASS | +0.737 |
Neg logit contributions | |
angered | -1.320 |
genre | -1.222 |
adem | -1.115 |
bnb | -1.102 |
arios | -1.091 |
Token | B |
Token ID | 347 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
angered | +0.678 |
genre | +0.622 |
adem | +0.561 |
bnb | +0.551 |
arios | +0.544 |
Neg logit contributions | |
illac | -0.555 |
Leaks | -0.533 |
ILY | -0.525 |
Nib | -0.514 |
ャ | -0.511 |
Token | at |
Token ID | 265 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
illac | +0.261 |
Leaks | +0.250 |
ILY | +0.248 |
Nib | +0.245 |
CLASS | +0.244 |
Neg logit contributions | |
angered | -0.291 |
genre | -0.267 |
adem | -0.238 |
bnb | -0.236 |
arios | -0.231 |
Token | 5 |
Token ID | 642 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
angered | +1.251 |
genre | +1.138 |
adem | +1.027 |
bnb | +1.002 |
arios | +0.997 |
Neg logit contributions | |
illac | -1.166 |
Leaks | -1.136 |
ILY | -1.116 |
Nib | -1.096 |
ャ | -1.092 |
Token | . |
Token ID | 13 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
illac | +0.196 |
Leaks | +0.188 |
ILY | +0.186 |
Nib | +0.184 |
CLASS | +0.182 |
Neg logit contributions | |
angered | -0.226 |
genre | -0.206 |
adem | -0.185 |
bnb | -0.183 |
arios | -0.180 |
Token | 5 |
Token ID | 20 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
angered | +0.752 |
genre | +0.689 |
adem | +0.619 |
bnb | +0.611 |
arios | +0.602 |
Neg logit contributions | |
illac | -0.621 |
Leaks | -0.594 |
ILY | -0.586 |
Nib | -0.580 |
CLASS | -0.575 |
Token | yards |
Token ID | 5695 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
illac | +0.894 |
Leaks | +0.866 |
ILY | +0.856 |
Nib | +0.848 |
CLASS | +0.845 |
Neg logit contributions | |
angered | -0.785 |
genre | -0.708 |
adem | -0.620 |
bnb | -0.614 |
arios | -0.604 |
Token | per |
Token ID | 583 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
angered | +1.662 |
genre | +1.508 |
adem | +1.347 |
bnb | +1.334 |
arios | +1.302 |
Neg logit contributions | |
illac | -1.673 |
Leaks | -1.615 |
ILY | -1.587 |
Nib | -1.565 |
ャ | -1.552 |
Token | carry |
Token ID | 3283 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
angered | +2.981 |
genre | +2.669 |
adem | +2.302 |
bnb | +2.223 |
arios | +2.185 |
Neg logit contributions | |
illac | -4.667 |
Leaks | -4.503 |
ILY | -4.456 |
ャ | -4.368 |
Nib | -4.352 |
Token | ) |
Token ID | 8 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
angered | +1.020 |
genre | +0.928 |
adem | +0.834 |
bnb | +0.826 |
arios | +0.809 |
Neg logit contributions | |
illac | -0.929 |
Leaks | -0.901 |
ILY | -0.878 |
Nib | -0.868 |
CLASS | -0.861 |
Token | and |
Token ID | 290 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
angered | +0.102 |
genre | +0.093 |
adem | +0.084 |
bnb | +0.083 |
arios | +0.082 |
Neg logit contributions | |
illac | -0.092 |
Leaks | -0.089 |
ILY | -0.087 |
Nib | -0.086 |
CLASS | -0.085 |
Token | another |
Token ID | 1194 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
angered | +0.268 |
genre | +0.246 |
adem | +0.223 |
bnb | +0.220 |
arios | +0.218 |
Neg logit contributions | |
illac | -0.195 |
Leaks | -0.187 |
ILY | -0.184 |
Nib | -0.181 |
CLASS | -0.180 |
Token | 388 |
Token ID | 43550 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
illac | +0.253 |
Leaks | +0.242 |
ILY | +0.239 |
Nib | +0.236 |
CLASS | +0.234 |
Neg logit contributions | |
angered | -0.387 |
genre | -0.358 |
adem | -0.325 |
bnb | -0.322 |
arios | -0.318 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
angered | +1.747 |
genre | +1.529 |
adem | +1.281 |
bnb | +1.279 |
arios | +1.239 |
Neg logit contributions | |
illac | -2.848 |
Leaks | -2.784 |
ILY | -2.741 |
Nib | -2.716 |
ャ | -2.712 |
Token | this |
Token ID | 428 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
angered | +4.383 |
genre | +3.894 |
adem | +3.432 |
bnb | +3.373 |
arios | +3.328 |
Neg logit contributions | |
illac | -4.866 |
Leaks | -4.777 |
ILY | -4.695 |
ャ | -4.595 |
Nib | -4.568 |
Token | comment |
Token ID | 2912 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
illac | +0.186 |
Leaks | +0.180 |
ILY | +0.179 |
CLASS | +0.178 |
Nib | +0.178 |
Neg logit contributions | |
angered | -0.210 |
genre | -0.191 |
adem | -0.173 |
bnb | -0.170 |
arios | -0.168 |
Token | on |
Token ID | 319 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
angered | +0.396 |
genre | +0.366 |
adem | +0.335 |
bnb | +0.331 |
arios | +0.328 |
Neg logit contributions | |
illac | -0.224 |
Leaks | -0.212 |
ILY | -0.209 |
Nib | -0.205 |
CLASS | -0.202 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
angered | +0.051 |
genre | +0.045 |
adem | +0.040 |
bnb | +0.039 |
arios | +0.039 |
Neg logit contributions | |
illac | -0.058 |
Leaks | -0.056 |
ILY | -0.056 |
Nib | -0.055 |
CLASS | -0.055 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
angered | +0.908 |
genre | +0.803 |
adem | +0.687 |
bnb | +0.675 |
arios | +0.659 |
Neg logit contributions | |
illac | -1.370 |
Leaks | -1.331 |
ILY | -1.317 |
Nib | -1.304 |
CLASS | -1.296 |
Token | this |
Token ID | 428 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
angered | +3.754 |
genre | +3.356 |
adem | +2.954 |
bnb | +2.924 |
arios | +2.867 |
Neg logit contributions | |
illac | -3.936 |
Leaks | -3.812 |
ILY | -3.748 |
Nib | -3.685 |
ャ | -3.677 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
illac | +0.396 |
Leaks | +0.384 |
ILY | +0.380 |
Nib | +0.379 |
CLASS | +0.378 |
Neg logit contributions | |
angered | -0.450 |
genre | -0.410 |
adem | -0.371 |
bnb | -0.366 |
arios | -0.362 |
Token | on |
Token ID | 319 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
illac | +0.216 |
Leaks | +0.206 |
ILY | +0.202 |
Nib | +0.199 |
CLASS | +0.197 |
Neg logit contributions | |
angered | -0.419 |
genre | -0.390 |
adem | -0.358 |
bnb | -0.355 |
arios | -0.351 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
illac | +0.251 |
Leaks | +0.243 |
ILY | +0.239 |
Nib | +0.237 |
CLASS | +0.236 |
Neg logit contributions | |
angered | -0.282 |
genre | -0.258 |
adem | -0.231 |
bnb | -0.228 |
arios | -0.225 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
illac | +0.732 |
Leaks | +0.705 |
ILY | +0.695 |
Nib | +0.686 |
CLASS | +0.682 |
Neg logit contributions | |
angered | -0.833 |
genre | -0.760 |
adem | -0.681 |
bnb | -0.673 |
arios | -0.664 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
angered | +1.738 |
genre | +1.523 |
adem | +1.282 |
bnb | +1.277 |
arios | +1.237 |
Neg logit contributions | |
illac | -2.777 |
Leaks | -2.706 |
ILY | -2.675 |
Nib | -2.648 |
ャ | -2.635 |
Token | this |
Token ID | 428 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
angered | +4.287 |
genre | +3.801 |
adem | +3.331 |
bnb | +3.271 |
argo | +3.225 |
Neg logit contributions | |
illac | -4.921 |
Leaks | -4.776 |
ILY | -4.686 |
ャ | -4.608 |
Nib | -4.582 |
Token | comment |
Token ID | 2912 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
illac | +0.138 |
Leaks | +0.134 |
ILY | +0.133 |
Nib | +0.132 |
CLASS | +0.132 |
Neg logit contributions | |
angered | -0.155 |
genre | -0.141 |
adem | -0.127 |
bnb | -0.125 |
arios | -0.124 |
Token | on |
Token ID | 319 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
angered | +0.599 |
genre | +0.555 |
adem | +0.507 |
bnb | +0.502 |
arios | +0.496 |
Neg logit contributions | |
illac | -0.340 |
Leaks | -0.321 |
ILY | -0.316 |
Nib | -0.310 |
CLASS | -0.307 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
angered | +0.136 |
genre | +0.122 |
adem | +0.107 |
bnb | +0.106 |
arios | +0.104 |
Neg logit contributions | |
illac | -0.157 |
Leaks | -0.152 |
ILY | -0.150 |
Nib | -0.148 |
CLASS | -0.147 |
Token | Share |
Token ID | 8734 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
angered | +1.022 |
genre | +0.901 |
adem | +0.770 |
bnb | +0.757 |
arios | +0.738 |
Neg logit contributions | |
illac | -1.557 |
Leaks | -1.512 |
ILY | -1.497 |
Nib | -1.480 |
CLASS | -1.471 |
Token | this |
Token ID | 428 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
angered | +3.729 |
genre | +3.333 |
adem | +2.927 |
bnb | +2.896 |
arios | +2.835 |
Neg logit contributions | |
illac | -3.962 |
Leaks | -3.824 |
ILY | -3.762 |
Nib | -3.697 |
ャ | -3.693 |
Token | comment |
Token ID | 2912 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
illac | +0.415 |
Leaks | +0.403 |
ILY | +0.399 |
Nib | +0.397 |
CLASS | +0.396 |
Neg logit contributions | |
angered | -0.469 |
genre | -0.428 |
adem | -0.386 |
bnb | -0.382 |
arios | -0.378 |
Token | on |
Token ID | 319 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
illac | +0.163 |
Leaks | +0.156 |
ILY | +0.153 |
Nib | +0.151 |
CLASS | +0.149 |
Neg logit contributions | |
angered | -0.315 |
genre | -0.293 |
adem | -0.269 |
bnb | -0.267 |
arios | -0.264 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
illac | +0.145 |
Leaks | +0.140 |
ILY | +0.138 |
Nib | +0.136 |
CLASS | +0.135 |
Neg logit contributions | |
angered | -0.161 |
genre | -0.147 |
adem | -0.132 |
bnb | -0.130 |
arios | -0.128 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
illac | +0.410 |
Leaks | +0.395 |
ILY | +0.389 |
Nib | +0.383 |
CLASS | +0.381 |
Neg logit contributions | |
angered | -0.458 |
genre | -0.417 |
adem | -0.374 |
bnb | -0.369 |
arios | -0.365 |
Token | . |
Token ID | 764 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
angered | +0.294 |
genre | +0.268 |
adem | +0.241 |
bnb | +0.236 |
arios | +0.233 |
Neg logit contributions | |
illac | -0.259 |
Leaks | -0.251 |
ILY | -0.246 |
Nib | -0.241 |
ャ | -0.241 |
Token |
|
Token ID | 198 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
illac | +0.197 |
Leaks | +0.191 |
ILY | +0.188 |
Nib | +0.185 |
CLASS | +0.184 |
Neg logit contributions | |
angered | -0.201 |
genre | -0.183 |
adem | -0.163 |
bnb | -0.161 |
arios | -0.158 |
Token |
|
Token ID | 198 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
angered | +0.932 |
genre | +0.846 |
adem | +0.751 |
bnb | +0.738 |
arios | +0.730 |
Neg logit contributions | |
illac | -0.873 |
Leaks | -0.829 |
ILY | -0.818 |
Nib | -0.814 |
CLASS | -0.810 |
Token | Google |
Token ID | 11708 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
angered | +0.468 |
genre | +0.431 |
adem | +0.385 |
bnb | +0.375 |
arios | +0.374 |
Neg logit contributions | |
illac | -0.397 |
Leaks | -0.378 |
Nib | -0.374 |
CLASS | -0.372 |
ILY | -0.372 |
Token | Scholar |
Token ID | 11713 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
angered | +1.683 |
genre | +1.541 |
adem | +1.385 |
bnb | +1.359 |
arios | +1.331 |
Neg logit contributions | |
illac | -1.568 |
Leaks | -1.510 |
ILY | -1.484 |
Nib | -1.463 |
ャ | -1.456 |
Token | Crossref |
Token ID | 23613 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
angered | +1.421 |
genre | +1.289 |
adem | +1.146 |
bnb | +1.136 |
arios | +1.106 |
Neg logit contributions | |
illac | -1.406 |
Leaks | -1.361 |
ILY | -1.327 |
ャ | -1.313 |
Nib | -1.313 |
Token |
|
Token ID | 198 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
angered | +3.460 |
genre | +3.109 |
adem | +2.720 |
bnb | +2.655 |
arios | +2.607 |
Neg logit contributions | |
illac | -3.988 |
Leaks | -3.953 |
ILY | -3.805 |
Nib | -3.792 |
CLASS | -3.749 |
Token |
|
Token ID | 198 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
angered | +2.078 |
genre | +1.868 |
adem | +1.643 |
bnb | +1.615 |
arios | +1.605 |
Neg logit contributions | |
illac | -2.102 |
Leaks | -1.993 |
ILY | -1.975 |
CLASS | -1.954 |
Nib | -1.949 |
Token | M |
Token ID | 44 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
angered | +1.840 |
genre | +1.704 |
adem | +1.532 |
arios | +1.482 |
bnb | +1.480 |
Neg logit contributions | |
illac | -1.367 |
CLASS | -1.281 |
Nib | -1.272 |
Leaks | -1.261 |
ャ | -1.246 |
Token | asure |
Token ID | 5015 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
angered | +1.000 |
genre | +0.909 |
adem | +0.816 |
bnb | +0.800 |
arios | +0.797 |
Neg logit contributions | |
illac | -0.947 |
Leaks | -0.920 |
ILY | -0.905 |
Nib | -0.902 |
CLASS | -0.895 |
Token | , |
Token ID | 11 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
angered | +1.199 |
genre | +1.096 |
adem | +0.988 |
bnb | +0.975 |
arios | +0.957 |
Neg logit contributions | |
illac | -1.095 |
Leaks | -1.069 |
ILY | -1.058 |
Nib | -1.037 |
ャ | -1.031 |
Token | at |
Token ID | 379 |
Feature activation | -2.95e-03 |
Pos logit contributions | |
angered | +1.592 |
genre | +1.453 |
adem | +1.296 |
bnb | +1.287 |
arios | +1.265 |
Neg logit contributions | |
illac | -1.481 |
Leaks | -1.448 |
ILY | -1.409 |
Nib | -1.384 |
ャ | -1.370 |
Token | 5 |
Token ID | 642 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
illac | +0.009 |
Leaks | +0.009 |
ILY | +0.009 |
Nib | +0.009 |
CLASS | +0.009 |
Neg logit contributions | |
angered | -0.007 |
genre | -0.007 |
adem | -0.006 |
bnb | -0.006 |
arios | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
angered | +0.154 |
genre | +0.141 |
adem | +0.126 |
bnb | +0.124 |
arios | +0.122 |
Neg logit contributions | |
illac | -0.141 |
Leaks | -0.136 |
ILY | -0.135 |
Nib | -0.133 |
CLASS | -0.131 |
Token | 4 |
Token ID | 19 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
angered | +0.641 |
genre | +0.587 |
adem | +0.527 |
bnb | +0.520 |
arios | +0.513 |
Neg logit contributions | |
illac | -0.533 |
Leaks | -0.510 |
ILY | -0.503 |
Nib | -0.498 |
CLASS | -0.494 |
Token | yards |
Token ID | 5695 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
angered | +0.376 |
genre | +0.337 |
adem | +0.294 |
bnb | +0.289 |
arios | +0.283 |
Neg logit contributions | |
illac | -0.477 |
Leaks | -0.464 |
ILY | -0.458 |
Nib | -0.453 |
CLASS | -0.450 |
Token | per |
Token ID | 583 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
angered | +1.735 |
genre | +1.578 |
adem | +1.408 |
bnb | +1.391 |
arios | +1.365 |
Neg logit contributions | |
illac | -1.695 |
Leaks | -1.644 |
ILY | -1.616 |
Nib | -1.593 |
CLASS | -1.579 |
Token | carry |
Token ID | 3283 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
angered | +2.874 |
genre | +2.575 |
adem | +2.195 |
bnb | +2.119 |
arios | +2.083 |
Neg logit contributions | |
illac | -4.604 |
Leaks | -4.499 |
ILY | -4.426 |
Nib | -4.364 |
ャ | -4.352 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
angered | +0.622 |
genre | +0.565 |
adem | +0.505 |
bnb | +0.499 |
arios | +0.491 |
Neg logit contributions | |
illac | -0.598 |
Leaks | -0.582 |
ILY | -0.569 |
Nib | -0.563 |
CLASS | -0.557 |
Token | His |
Token ID | 2399 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
illac | +0.048 |
Leaks | +0.046 |
ILY | +0.045 |
Nib | +0.045 |
CLASS | +0.044 |
Neg logit contributions | |
angered | -0.057 |
genre | -0.052 |
adem | -0.046 |
bnb | -0.046 |
arios | -0.045 |
Token | follow |
Token ID | 1061 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
illac | +0.010 |
Leaks | +0.010 |
ILY | +0.010 |
Nib | +0.010 |
ャ | +0.010 |
Neg logit contributions | |
angered | -0.013 |
genre | -0.011 |
adem | -0.010 |
bnb | -0.010 |
arios | -0.010 |
Token | - |
Token ID | 12 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
illac | +1.212 |
Leaks | +1.168 |
ILY | +1.151 |
Nib | +1.137 |
CLASS | +1.130 |
Neg logit contributions | |
angered | -1.458 |
genre | -1.335 |
adem | -1.200 |
bnb | -1.187 |
arios | -1.169 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
angered | +0.108 |
genre | +0.099 |
adem | +0.089 |
bnb | +0.088 |
arios | +0.086 |
Neg logit contributions | |
illac | -0.091 |
Leaks | -0.088 |
ILY | -0.087 |
Nib | -0.086 |
CLASS | -0.085 |
Token | � |
Token ID | 447 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
angered | +0.030 |
genre | +0.028 |
adem | +0.025 |
bnb | +0.025 |
arios | +0.024 |
Neg logit contributions | |
illac | -0.027 |
Leaks | -0.026 |
ILY | -0.026 |
Nib | -0.025 |
CLASS | -0.025 |
Token | � |
Token ID | 251 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
illac | +0.258 |
Leaks | +0.252 |
ILY | +0.249 |
Nib | +0.247 |
CLASS | +0.246 |
Neg logit contributions | |
angered | -0.155 |
genre | -0.136 |
adem | -0.115 |
bnb | -0.112 |
arios | -0.111 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
illac | +0.034 |
Leaks | +0.032 |
ILY | +0.032 |
Nib | +0.032 |
CLASS | +0.031 |
Neg logit contributions | |
angered | -0.038 |
genre | -0.035 |
adem | -0.031 |
bnb | -0.031 |
arios | -0.030 |
Token | V |
Token ID | 53 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
angered | +0.649 |
genre | +0.601 |
adem | +0.539 |
bnb | +0.528 |
arios | +0.523 |
Neg logit contributions | |
illac | -0.497 |
Nib | -0.466 |
Leaks | -0.465 |
ILY | -0.461 |
CLASS | -0.461 |
Token | ern |
Token ID | 1142 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
illac | +0.375 |
Leaks | +0.362 |
ILY | +0.357 |
Nib | +0.355 |
CLASS | +0.352 |
Neg logit contributions | |
angered | -0.428 |
genre | -0.390 |
adem | -0.352 |
bnb | -0.345 |
arios | -0.343 |
Token | acular |
Token ID | 12754 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
illac | +3.471 |
Leaks | +3.403 |
Nib | +3.252 |
ILY | +3.230 |
CLASS | +3.156 |
Neg logit contributions | |
angered | -5.924 |
genre | -5.543 |
bnb | -4.990 |
adem | -4.964 |
arios | -4.852 |
Token | architecture |
Token ID | 10959 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
illac | +0.398 |
Leaks | +0.383 |
ILY | +0.379 |
Nib | +0.372 |
CLASS | +0.370 |
Neg logit contributions | |
angered | -0.463 |
genre | -0.423 |
adem | -0.380 |
bnb | -0.376 |
arios | -0.369 |
Token | is |
Token ID | 318 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
angered | +0.075 |
genre | +0.068 |
adem | +0.061 |
bnb | +0.061 |
arios | +0.060 |
Neg logit contributions | |
illac | -0.063 |
Leaks | -0.061 |
ILY | -0.060 |
Nib | -0.059 |
CLASS | -0.059 |
Token | a |
Token ID | 257 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
illac | +0.410 |
Leaks | +0.395 |
ILY | +0.389 |
Nib | +0.385 |
CLASS | +0.382 |
Neg logit contributions | |
angered | -0.503 |
genre | -0.461 |
adem | -0.415 |
bnb | -0.410 |
arios | -0.404 |
Token | style |
Token ID | 3918 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
illac | +1.120 |
Leaks | +1.082 |
ILY | +1.072 |
Nib | +1.068 |
CLASS | +1.067 |
Neg logit contributions | |
angered | -1.133 |
genre | -1.023 |
adem | -0.917 |
bnb | -0.904 |
arios | -0.888 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
illac | +0.012 |
Leaks | +0.012 |
ILY | +0.012 |
Nib | +0.011 |
CLASS | +0.011 |
Neg logit contributions | |
angered | -0.014 |
genre | -0.013 |
adem | -0.012 |
bnb | -0.011 |
arios | -0.011 |
Token | Club |
Token ID | 42350 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
illac | +0.282 |
Leaks | +0.269 |
ILY | +0.266 |
Nib | +0.265 |
CLASS | +0.263 |
Neg logit contributions | |
angered | -0.332 |
genre | -0.305 |
adem | -0.274 |
bnb | -0.268 |
arios | -0.265 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
angered | +1.042 |
genre | +0.950 |
adem | +0.852 |
bnb | +0.836 |
arios | +0.822 |
Neg logit contributions | |
illac | -0.992 |
Leaks | -0.945 |
ILY | -0.941 |
Nib | -0.922 |
ャ | -0.914 |
Token |
|
Token ID | 198 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
angered | +0.044 |
genre | +0.040 |
adem | +0.036 |
bnb | +0.035 |
arios | +0.035 |
Neg logit contributions | |
illac | -0.038 |
Leaks | -0.036 |
ILY | -0.036 |
Nib | -0.035 |
CLASS | -0.035 |
Token | Bay |
Token ID | 15262 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
angered | +0.091 |
genre | +0.084 |
adem | +0.075 |
bnb | +0.074 |
arios | +0.073 |
Neg logit contributions | |
illac | -0.075 |
Leaks | -0.071 |
ILY | -0.071 |
Nib | -0.071 |
CLASS | -0.070 |
Token | ern |
Token ID | 1142 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
illac | +0.248 |
Leaks | +0.236 |
ILY | +0.235 |
Nib | +0.230 |
CLASS | +0.230 |
Neg logit contributions | |
angered | -0.358 |
genre | -0.329 |
adem | -0.301 |
bnb | -0.296 |
arios | -0.293 |
Token | Munich |
Token ID | 22418 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
illac | +4.170 |
Leaks | +4.059 |
Nib | +3.984 |
ILY | +3.971 |
CLASS | +3.968 |
Neg logit contributions | |
angered | -4.210 |
genre | -3.849 |
bnb | -3.367 |
adem | -3.335 |
arios | -3.284 |
Token | Jun |
Token ID | 7653 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
illac | +1.932 |
Leaks | +1.869 |
ILY | +1.838 |
Nib | +1.834 |
CLASS | +1.821 |
Neg logit contributions | |
angered | -2.258 |
genre | -2.070 |
adem | -1.841 |
bnb | -1.836 |
arios | -1.804 |
Token | iors |
Token ID | 12706 |
Feature activation | +5.71e-03 |
Pos logit contributions | |
angered | +1.235 |
genre | +1.142 |
adem | +1.045 |
bnb | +1.028 |
arios | +1.018 |
Neg logit contributions | |
illac | -0.780 |
Leaks | -0.750 |
ILY | -0.743 |
Nib | -0.730 |
CLASS | -0.727 |
Token | [ |
Token ID | 58 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
angered | +0.017 |
genre | +0.015 |
adem | +0.014 |
bnb | +0.014 |
arios | +0.013 |
Neg logit contributions | |
illac | -0.015 |
Leaks | -0.015 |
ILY | -0.015 |
Nib | -0.014 |
ャ | -0.014 |
Token | 92 |
Token ID | 5892 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
illac | +0.032 |
Leaks | +0.031 |
ILY | +0.031 |
Nib | +0.030 |
CLASS | +0.030 |
Neg logit contributions | |
angered | -0.032 |
genre | -0.029 |
adem | -0.026 |
bnb | -0.026 |
arios | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
illac | +0.383 |
Leaks | +0.371 |
ILY | +0.364 |
Nib | +0.360 |
CLASS | +0.357 |
Neg logit contributions | |
angered | -0.403 |
genre | -0.368 |
adem | -0.327 |
bnb | -0.323 |
arios | -0.318 |
Token |
|
Token ID | 198 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
illac | +0.201 |
Leaks | +0.194 |
ILY | +0.191 |
Nib | +0.188 |
CLASS | +0.186 |
Neg logit contributions | |
angered | -0.226 |
genre | -0.207 |
adem | -0.185 |
bnb | -0.182 |
arios | -0.180 |
Token |
|
Token ID | 198 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
illac | +0.246 |
Leaks | +0.238 |
ILY | +0.235 |
Nib | +0.232 |
CLASS | +0.230 |
Neg logit contributions | |
angered | -0.294 |
genre | -0.269 |
adem | -0.243 |
bnb | -0.240 |
arios | -0.236 |
Token | UN |
Token ID | 4944 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
illac | +0.707 |
Leaks | +0.675 |
ILY | +0.662 |
Nib | +0.658 |
CLASS | +0.650 |
Neg logit contributions | |
angered | -1.003 |
genre | -0.927 |
adem | -0.837 |
bnb | -0.827 |
arios | -0.817 |
Token | DE |
Token ID | 7206 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
illac | +0.200 |
Leaks | +0.191 |
ILY | +0.188 |
Nib | +0.186 |
CLASS | +0.184 |
Neg logit contributions | |
angered | -0.238 |
genre | -0.218 |
adem | -0.195 |
bnb | -0.193 |
arios | -0.190 |
Token | AD |
Token ID | 2885 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
illac | +1.396 |
Leaks | +1.347 |
ILY | +1.335 |
Nib | +1.309 |
CLASS | +1.307 |
Neg logit contributions | |
angered | -1.882 |
genre | -1.733 |
adem | -1.568 |
bnb | -1.554 |
arios | -1.533 |
Token | * |
Token ID | 9 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
illac | +3.577 |
ILY | +3.523 |
CLASS | +3.506 |
Leaks | +3.432 |
Nib | +3.407 |
Neg logit contributions | |
angered | -4.473 |
genre | -4.126 |
adem | -3.750 |
bnb | -3.667 |
arios | -3.660 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
illac | +1.541 |
Leaks | +1.486 |
ILY | +1.467 |
Nib | +1.448 |
CLASS | +1.442 |
Neg logit contributions | |
angered | -1.803 |
genre | -1.649 |
adem | -1.481 |
bnb | -1.463 |
arios | -1.442 |
Token |
|
Token ID | 198 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
illac | +0.315 |
Leaks | +0.306 |
ILY | +0.302 |
Nib | +0.297 |
CLASS | +0.296 |
Neg logit contributions | |
angered | -0.381 |
genre | -0.350 |
adem | -0.315 |
bnb | -0.312 |
arios | -0.307 |
Token | + |
Token ID | 10 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
illac | +0.756 |
Leaks | +0.728 |
ILY | +0.718 |
Nib | +0.715 |
CLASS | +0.707 |
Neg logit contributions | |
angered | -0.680 |
genre | -0.616 |
adem | -0.541 |
bnb | -0.533 |
arios | -0.524 |
Token | Soul |
Token ID | 8653 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
angered | +0.232 |
genre | +0.209 |
adem | +0.189 |
bnb | +0.185 |
arios | +0.184 |
Neg logit contributions | |
illac | -0.192 |
Leaks | -0.183 |
ILY | -0.182 |
ャ | -0.177 |
CLASS | -0.175 |
Token | book |
Token ID | 1492 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
angered | +0.327 |
genre | +0.296 |
adem | +0.262 |
bnb | +0.258 |
arios | +0.254 |
Neg logit contributions | |
illac | -0.352 |
Leaks | -0.340 |
ILY | -0.336 |
Nib | -0.332 |
CLASS | -0.330 |
Token | , |
Token ID | 11 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
illac | +1.021 |
Leaks | +0.988 |
ILY | +0.974 |
Nib | +0.963 |
CLASS | +0.958 |
Neg logit contributions | |
angered | -1.068 |
genre | -0.972 |
adem | -0.866 |
bnb | -0.856 |
arios | -0.843 |
Token | � |
Token ID | 564 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
illac | +0.884 |
Leaks | +0.854 |
ILY | +0.843 |
Nib | +0.834 |
CLASS | +0.829 |
Neg logit contributions | |
angered | -0.871 |
genre | -0.790 |
adem | -0.701 |
bnb | -0.692 |
arios | -0.681 |
Token | � |
Token ID | 250 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
illac | +1.208 |
Leaks | +1.173 |
ILY | +1.158 |
Nib | +1.145 |
CLASS | +1.140 |
Neg logit contributions | |
angered | -1.050 |
genre | -0.946 |
adem | -0.832 |
bnb | -0.820 |
arios | -0.807 |
Token | C |
Token ID | 34 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
illac | +0.663 |
Leaks | +0.636 |
ILY | +0.628 |
Nib | +0.620 |
CLASS | +0.615 |
Neg logit contributions | |
angered | -0.876 |
genre | -0.806 |
adem | -0.727 |
bnb | -0.719 |
arios | -0.709 |
Token | arn |
Token ID | 1501 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
angered | +0.174 |
genre | +0.156 |
adem | +0.138 |
bnb | +0.136 |
arios | +0.134 |
Neg logit contributions | |
illac | -0.198 |
Leaks | -0.191 |
ILY | -0.188 |
Nib | -0.188 |
CLASS | -0.186 |
Token | al |
Token ID | 282 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
illac | +3.904 |
Leaks | +3.773 |
ILY | +3.689 |
Nib | +3.669 |
CLASS | +3.629 |
Neg logit contributions | |
angered | -4.072 |
genre | -3.722 |
adem | -3.289 |
bnb | -3.281 |
arios | -3.202 |
Token | Abuse |
Token ID | 24221 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
illac | +0.961 |
Leaks | +0.923 |
ILY | +0.913 |
Nib | +0.900 |
CLASS | +0.897 |
Neg logit contributions | |
angered | -1.169 |
genre | -1.071 |
adem | -0.963 |
bnb | -0.952 |
arios | -0.939 |
Token | by |
Token ID | 416 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
illac | +0.670 |
Leaks | +0.647 |
ILY | +0.638 |
Nib | +0.631 |
CLASS | +0.626 |
Neg logit contributions | |
angered | -0.722 |
genre | -0.658 |
adem | -0.587 |
bnb | -0.580 |
arios | -0.571 |
Token | De |
Token ID | 1024 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
illac | +0.920 |
Leaks | +0.886 |
ILY | +0.873 |
Nib | +0.862 |
CLASS | +0.857 |
Neg logit contributions | |
angered | -1.149 |
genre | -1.054 |
adem | -0.949 |
bnb | -0.938 |
arios | -0.925 |
Token | ce |
Token ID | 344 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
illac | +1.542 |
Leaks | +1.499 |
ILY | +1.483 |
Nib | +1.469 |
CLASS | +1.462 |
Neg logit contributions | |
angered | -1.060 |
genre | -0.941 |
adem | -0.809 |
bnb | -0.796 |
arios | -0.779 |
Token |
|
Token ID | 198 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
angered | +0.110 |
genre | +0.101 |
adem | +0.090 |
bnb | +0.089 |
arios | +0.088 |
Neg logit contributions | |
illac | -0.092 |
Leaks | -0.089 |
ILY | -0.087 |
Nib | -0.086 |
CLASS | -0.086 |
Token |
|
Token ID | 198 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
angered | +1.338 |
genre | +1.217 |
adem | +1.074 |
bnb | +1.062 |
arios | +1.044 |
Neg logit contributions | |
illac | -1.266 |
Leaks | -1.198 |
ILY | -1.186 |
Nib | -1.184 |
CLASS | -1.179 |
Token | 47 |
Token ID | 2857 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
angered | +0.977 |
genre | +0.907 |
adem | +0.811 |
bnb | +0.793 |
arios | +0.785 |
Neg logit contributions | |
illac | -0.759 |
Leaks | -0.716 |
Nib | -0.714 |
ILY | -0.710 |
CLASS | -0.708 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
angered | +1.229 |
genre | +1.122 |
adem | +1.012 |
bnb | +0.997 |
arios | +0.983 |
Neg logit contributions | |
illac | -1.035 |
Leaks | -1.003 |
ILY | -0.986 |
Nib | -0.961 |
ャ | -0.959 |
Token | Rec |
Token ID | 3311 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
angered | +0.341 |
genre | +0.311 |
adem | +0.278 |
bnb | +0.275 |
arios | +0.271 |
Neg logit contributions | |
illac | -0.298 |
Leaks | -0.288 |
ILY | -0.283 |
Nib | -0.278 |
CLASS | -0.276 |
Token | y |
Token ID | 88 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
angered | +1.052 |
genre | +0.961 |
adem | +0.869 |
bnb | +0.848 |
arios | +0.836 |
Neg logit contributions | |
illac | -0.989 |
Leaks | -0.960 |
ILY | -0.955 |
Nib | -0.937 |
CLASS | -0.931 |
Token | cling |
Token ID | 8493 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
illac | +3.305 |
Leaks | +3.126 |
ILY | +3.056 |
Nib | +3.050 |
ャ | +3.050 |
Neg logit contributions | |
angered | -4.403 |
genre | -4.074 |
bnb | -3.639 |
adem | -3.631 |
arios | -3.583 |
Token | scheme |
Token ID | 7791 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
illac | +0.502 |
Leaks | +0.485 |
ILY | +0.478 |
Nib | +0.473 |
CLASS | +0.470 |
Neg logit contributions | |
angered | -0.581 |
genre | -0.532 |
adem | -0.477 |
bnb | -0.471 |
arios | -0.464 |
Token | [ |
Token ID | 685 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
angered | +0.382 |
genre | +0.349 |
adem | +0.313 |
bnb | +0.309 |
arios | +0.305 |
Neg logit contributions | |
illac | -0.340 |
Leaks | -0.328 |
ILY | -0.323 |
Nib | -0.319 |
CLASS | -0.317 |
Token | via |
Token ID | 8869 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
illac | +0.385 |
Leaks | +0.366 |
ILY | +0.358 |
Nib | +0.354 |
CLASS | +0.350 |
Neg logit contributions | |
angered | -0.633 |
genre | -0.588 |
adem | -0.534 |
bnb | -0.530 |
arios | -0.522 |
Token | ] |
Token ID | 60 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
angered | +0.265 |
genre | +0.242 |
adem | +0.217 |
bnb | +0.215 |
arios | +0.211 |
Neg logit contributions | |
illac | -0.234 |
Leaks | -0.225 |
ILY | -0.222 |
Nib | -0.218 |
CLASS | -0.217 |
Token | with |
Token ID | 351 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
angered | +0.340 |
genre | +0.312 |
adem | +0.283 |
bnb | +0.279 |
arios | +0.275 |
Neg logit contributions | |
illac | -0.262 |
Leaks | -0.251 |
ILY | -0.248 |
Nib | -0.243 |
CLASS | -0.240 |
Token | 25 |
Token ID | 1679 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
angered | +0.221 |
genre | +0.203 |
adem | +0.184 |
bnb | +0.181 |
arios | +0.179 |
Neg logit contributions | |
illac | -0.167 |
Leaks | -0.162 |
ILY | -0.159 |
Nib | -0.156 |
ャ | -0.154 |
Token | 60 |
Token ID | 1899 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
illac | +0.090 |
Leaks | +0.087 |
ILY | +0.085 |
Nib | +0.084 |
CLASS | +0.084 |
Neg logit contributions | |
angered | -0.108 |
genre | -0.099 |
adem | -0.089 |
bnb | -0.088 |
arios | -0.086 |
Token | CU |
Token ID | 29369 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
illac | +0.762 |
Leaks | +0.734 |
ILY | +0.723 |
Nib | +0.717 |
CLASS | +0.715 |
Neg logit contributions | |
angered | -1.013 |
genre | -0.931 |
adem | -0.843 |
bnb | -0.830 |
arios | -0.819 |
Token | DA |
Token ID | 5631 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
illac | +2.208 |
Leaks | +2.185 |
ILY | +2.149 |
Nib | +2.127 |
CLASS | +2.125 |
Neg logit contributions | |
angered | -2.483 |
genre | -2.256 |
adem | -2.027 |
bnb | -1.996 |
arios | -1.943 |
Token | cores |
Token ID | 21758 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
illac | +2.893 |
Leaks | +2.808 |
ILY | +2.776 |
Nib | +2.739 |
CLASS | +2.736 |
Neg logit contributions | |
angered | -3.360 |
genre | -3.069 |
adem | -2.731 |
bnb | -2.710 |
arios | -2.656 |
Token | and |
Token ID | 290 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
illac | +3.330 |
Leaks | +3.184 |
ILY | +3.183 |
CLASS | +3.151 |
Nib | +3.142 |
Neg logit contributions | |
angered | -4.147 |
genre | -3.782 |
adem | -3.377 |
bnb | -3.345 |
arios | -3.258 |
Token | 20 |
Token ID | 1160 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
illac | +0.388 |
Leaks | +0.371 |
ILY | +0.365 |
Nib | +0.360 |
CLASS | +0.357 |
Neg logit contributions | |
angered | -0.601 |
genre | -0.556 |
adem | -0.506 |
bnb | -0.500 |
arios | -0.495 |
Token | SM |
Token ID | 9447 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
angered | +0.058 |
genre | +0.053 |
adem | +0.048 |
bnb | +0.047 |
arios | +0.047 |
Neg logit contributions | |
illac | -0.047 |
Leaks | -0.045 |
ILY | -0.045 |
Nib | -0.044 |
CLASS | -0.043 |
Token | units |
Token ID | 4991 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
illac | +0.170 |
Leaks | +0.163 |
ILY | +0.160 |
Nib | +0.159 |
CLASS | +0.157 |
Neg logit contributions | |
angered | -0.222 |
genre | -0.204 |
adem | -0.184 |
bnb | -0.182 |
arios | -0.180 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
illac | +1.052 |
Leaks | +1.013 |
ILY | +1.002 |
Nib | +0.990 |
CLASS | +0.986 |
Neg logit contributions | |
angered | -1.190 |
genre | -1.086 |
adem | -0.972 |
bnb | -0.960 |
arios | -0.944 |
Token | will |
Token ID | 481 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
illac | +0.050 |
Leaks | +0.048 |
ILY | +0.047 |
Nib | +0.047 |
CLASS | +0.046 |
Neg logit contributions | |
angered | -0.069 |
genre | -0.064 |
adem | -0.058 |
bnb | -0.057 |
arios | -0.056 |
Token | know |
Token ID | 760 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
illac | +0.264 |
Leaks | +0.253 |
ILY | +0.250 |
Nib | +0.246 |
CLASS | +0.245 |
Neg logit contributions | |
angered | -0.358 |
genre | -0.330 |
adem | -0.299 |
bnb | -0.295 |
arios | -0.291 |
Token | in |
Token ID | 287 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
angered | +0.262 |
genre | +0.240 |
adem | +0.215 |
bnb | +0.213 |
arios | +0.210 |
Neg logit contributions | |
illac | -0.223 |
Leaks | -0.214 |
ILY | -0.211 |
Nib | -0.209 |
CLASS | -0.207 |
Token | only |
Token ID | 691 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
illac | +0.294 |
Leaks | +0.282 |
ILY | +0.279 |
Nib | +0.274 |
CLASS | +0.272 |
Neg logit contributions | |
angered | -0.388 |
genre | -0.357 |
adem | -0.323 |
bnb | -0.319 |
arios | -0.314 |
Token | a |
Token ID | 257 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
illac | +0.432 |
Leaks | +0.415 |
ILY | +0.409 |
Nib | +0.404 |
CLASS | +0.402 |
Neg logit contributions | |
angered | -0.599 |
genre | -0.552 |
adem | -0.499 |
bnb | -0.494 |
arios | -0.488 |
Token | matter |
Token ID | 2300 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
illac | +1.263 |
Leaks | +1.235 |
ILY | +1.216 |
Nib | +1.205 |
CLASS | +1.200 |
Neg logit contributions | |
angered | -1.026 |
genre | -0.918 |
adem | -0.805 |
bnb | -0.791 |
arios | -0.777 |
Token | of |
Token ID | 286 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
illac | +3.265 |
ILY | +3.222 |
Leaks | +3.214 |
Nib | +3.163 |
CLASS | +3.121 |
Neg logit contributions | |
angered | -3.953 |
genre | -3.660 |
adem | -3.335 |
arios | -3.238 |
bnb | -3.234 |
Token | days |
Token ID | 1528 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
illac | +1.491 |
Leaks | +1.439 |
Nib | +1.405 |
ILY | +1.404 |
CLASS | +1.388 |
Neg logit contributions | |
angered | -2.747 |
genre | -2.540 |
adem | -2.338 |
bnb | -2.321 |
arios | -2.285 |
Token | , |
Token ID | 11 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
illac | +1.368 |
Leaks | +1.320 |
ILY | +1.305 |
Nib | +1.291 |
CLASS | +1.283 |
Neg logit contributions | |
angered | -1.595 |
genre | -1.454 |
adem | -1.305 |
bnb | -1.284 |
arios | -1.265 |
Token | but |
Token ID | 475 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
angered | +0.667 |
genre | +0.603 |
adem | +0.531 |
bnb | +0.524 |
arios | +0.515 |
Neg logit contributions | |
illac | -0.747 |
Leaks | -0.724 |
ILY | -0.715 |
Nib | -0.707 |
CLASS | -0.703 |
Token | if |
Token ID | 611 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
angered | +0.724 |
genre | +0.662 |
adem | +0.592 |
bnb | +0.585 |
arios | +0.578 |
Neg logit contributions | |
illac | -0.639 |
Leaks | -0.616 |
ILY | -0.608 |
Nib | -0.599 |
CLASS | -0.596 |
Token | a |
Token ID | 257 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
angered | +1.268 |
genre | +1.156 |
adem | +1.036 |
bnb | +1.025 |
arios | +1.008 |
Neg logit contributions | |
illac | -1.123 |
Leaks | -1.085 |
ILY | -1.065 |
Nib | -1.048 |
CLASS | -1.047 |
Token | friend |
Token ID | 1545 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
angered | +0.583 |
genre | +0.530 |
adem | +0.473 |
bnb | +0.467 |
arios | +0.460 |
Neg logit contributions | |
illac | -0.547 |
Leaks | -0.529 |
ILY | -0.520 |
Nib | -0.513 |
CLASS | -0.510 |
Token | clarified |
Token ID | 28464 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
angered | +0.795 |
genre | +0.725 |
adem | +0.647 |
bnb | +0.639 |
arios | +0.630 |
Neg logit contributions | |
illac | -0.736 |
Leaks | -0.711 |
ILY | -0.701 |
Nib | -0.693 |
CLASS | -0.689 |
Token | — |
Token ID | 960 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
illac | +0.038 |
Leaks | +0.037 |
ILY | +0.036 |
Nib | +0.036 |
CLASS | +0.036 |
Neg logit contributions | |
angered | -0.046 |
genre | -0.042 |
adem | -0.038 |
bnb | -0.037 |
arios | -0.037 |
Token | pr |
Token ID | 1050 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
illac | +0.085 |
Leaks | +0.082 |
ILY | +0.081 |
Nib | +0.080 |
CLASS | +0.079 |
Neg logit contributions | |
angered | -0.097 |
genre | -0.089 |
adem | -0.080 |
bnb | -0.079 |
arios | -0.077 |
Token | ide |
Token ID | 485 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
illac | +0.264 |
Leaks | +0.257 |
ILY | +0.253 |
Nib | +0.251 |
CLASS | +0.249 |
Neg logit contributions | |
angered | -0.263 |
genre | -0.239 |
adem | -0.213 |
bnb | -0.209 |
arios | -0.205 |
Token | fully |
Token ID | 2759 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
illac | +3.353 |
ILY | +3.231 |
Leaks | +3.200 |
Nib | +3.175 |
CLASS | +3.123 |
Neg logit contributions | |
angered | -4.021 |
genre | -3.689 |
adem | -3.283 |
arios | -3.247 |
bnb | -3.231 |
Token | and |
Token ID | 290 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
illac | +1.131 |
Leaks | +1.092 |
ILY | +1.079 |
Nib | +1.067 |
CLASS | +1.061 |
Neg logit contributions | |
angered | -1.229 |
genre | -1.121 |
adem | -0.999 |
bnb | -0.986 |
arios | -0.975 |
Token | unp |
Token ID | 8593 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
illac | +0.015 |
Leaks | +0.014 |
ILY | +0.014 |
Nib | +0.014 |
CLASS | +0.014 |
Neg logit contributions | |
angered | -0.021 |
genre | -0.019 |
adem | -0.018 |
bnb | -0.017 |
arios | -0.017 |
Token | rompt |
Token ID | 45700 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
illac | +0.472 |
Leaks | +0.446 |
ILY | +0.435 |
Nib | +0.422 |
CLASS | +0.421 |
Neg logit contributions | |
angered | -1.068 |
genre | -1.002 |
bnb | -0.916 |
adem | -0.913 |
arios | -0.906 |
Token | ed |
Token ID | 276 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
illac | +1.343 |
Leaks | +1.288 |
ILY | +1.266 |
Nib | +1.247 |
CLASS | +1.237 |
Neg logit contributions | |
angered | -1.977 |
genre | -1.832 |
adem | -1.650 |
bnb | -1.648 |
arios | -1.613 |
Token | Joshua |
Token ID | 47740 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
angered | +0.031 |
genre | +0.029 |
adem | +0.026 |
bnb | +0.026 |
arios | +0.026 |
Neg logit contributions | |
illac | -0.023 |
Leaks | -0.022 |
ILY | -0.021 |
Nib | -0.021 |
CLASS | -0.021 |
Token | Roberts |
Token ID | 10918 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
angered | +0.972 |
genre | +0.870 |
adem | +0.776 |
arios | +0.755 |
bnb | +0.748 |
Neg logit contributions | |
illac | -1.155 |
Leaks | -1.124 |
ILY | -1.113 |
CLASS | -1.102 |
ャ | -1.097 |
Token |
|
Token ID | 198 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
angered | +0.026 |
genre | +0.023 |
adem | +0.021 |
bnb | +0.021 |
arios | +0.020 |
Neg logit contributions | |
illac | -0.023 |
Leaks | -0.022 |
ILY | -0.022 |
Nib | -0.022 |
CLASS | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
angered | +0.897 |
genre | +0.815 |
adem | +0.724 |
bnb | +0.715 |
arios | +0.706 |
Neg logit contributions | |
illac | -0.833 |
Leaks | -0.792 |
ILY | -0.784 |
Nib | -0.777 |
CLASS | -0.773 |
Token | DE |
Token ID | 7206 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
angered | +0.428 |
genre | +0.394 |
adem | +0.352 |
bnb | +0.345 |
arios | +0.342 |
Neg logit contributions | |
illac | -0.339 |
Nib | -0.318 |
Leaks | -0.317 |
CLASS | -0.314 |
ILY | -0.314 |
Token | AD |
Token ID | 2885 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
illac | +0.339 |
Leaks | +0.325 |
ILY | +0.319 |
Nib | +0.315 |
CLASS | +0.313 |
Neg logit contributions | |
angered | -0.482 |
genre | -0.445 |
adem | -0.403 |
bnb | -0.399 |
arios | -0.394 |
Token | LIN |
Token ID | 34509 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
illac | +3.527 |
ILY | +3.475 |
CLASS | +3.443 |
Leaks | +3.425 |
Nib | +3.342 |
Neg logit contributions | |
angered | -3.708 |
genre | -3.423 |
adem | -3.062 |
bnb | -3.016 |
arios | -2.964 |
Token | ES |
Token ID | 1546 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
angered | +0.793 |
genre | +0.730 |
adem | +0.651 |
bnb | +0.647 |
arios | +0.643 |
Neg logit contributions | |
illac | -0.645 |
Leaks | -0.614 |
ILY | -0.600 |
Nib | -0.596 |
ャ | -0.590 |
Token | LO |
Token ID | 17579 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
angered | +1.159 |
genre | +1.053 |
adem | +0.937 |
bnb | +0.929 |
arios | +0.921 |
Neg logit contributions | |
illac | -1.040 |
Leaks | -0.993 |
ILY | -0.960 |
Nib | -0.959 |
ャ | -0.956 |
Token | OM |
Token ID | 2662 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
angered | +0.098 |
genre | +0.089 |
adem | +0.079 |
bnb | +0.079 |
arios | +0.078 |
Neg logit contributions | |
illac | -0.087 |
Leaks | -0.083 |
Nib | -0.081 |
ILY | -0.080 |
ャ | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
angered | +2.262 |
genre | +2.036 |
bnb | +1.798 |
RELE | +1.796 |
adem | +1.791 |
Neg logit contributions | |
illac | -2.055 |
Leaks | -1.948 |
Nib | -1.891 |
ャ | -1.867 |
ILY | -1.832 |
Token | year |
Token ID | 614 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
angered | +0.611 |
genre | +0.556 |
adem | +0.498 |
bnb | +0.490 |
arios | +0.485 |
Neg logit contributions | |
illac | -0.572 |
Leaks | -0.551 |
ILY | -0.544 |
Nib | -0.536 |
CLASS | -0.534 |
Token | has |
Token ID | 468 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
angered | +1.737 |
genre | +1.573 |
adem | +1.422 |
bnb | +1.392 |
arios | +1.386 |
Neg logit contributions | |
illac | -1.574 |
Leaks | -1.513 |
ILY | -1.493 |
Nib | -1.468 |
CLASS | -1.467 |
Token | been |
Token ID | 587 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
angered | +0.907 |
genre | +0.829 |
adem | +0.744 |
bnb | +0.734 |
arios | +0.726 |
Neg logit contributions | |
illac | -0.777 |
Leaks | -0.747 |
ILY | -0.736 |
Nib | -0.726 |
CLASS | -0.723 |
Token | an |
Token ID | 281 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
angered | +0.030 |
genre | +0.028 |
adem | +0.025 |
bnb | +0.024 |
arios | +0.024 |
Neg logit contributions | |
illac | -0.025 |
Leaks | -0.024 |
ILY | -0.024 |
Nib | -0.023 |
CLASS | -0.023 |
Token | un |
Token ID | 555 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
angered | +0.623 |
genre | +0.567 |
adem | +0.508 |
bnb | +0.500 |
arios | +0.495 |
Neg logit contributions | |
illac | -0.531 |
Leaks | -0.511 |
ILY | -0.503 |
Nib | -0.498 |
CLASS | -0.493 |
Token | mit |
Token ID | 2781 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
illac | +1.259 |
Leaks | +1.217 |
ILY | +1.202 |
Nib | +1.187 |
CLASS | +1.182 |
Neg logit contributions | |
angered | -1.278 |
genre | -1.162 |
adem | -1.032 |
bnb | -1.022 |
arios | -1.007 |
Token | igated |
Token ID | 26963 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
illac | +1.560 |
Leaks | +1.414 |
Nib | +1.394 |
CLASS | +1.367 |
Men | +1.358 |
Neg logit contributions | |
angered | -5.415 |
genre | -5.140 |
bnb | -4.821 |
adem | -4.757 |
arios | -4.704 |
Token | disaster |
Token ID | 9336 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
illac | +0.209 |
Leaks | +0.203 |
ILY | +0.200 |
Nib | +0.198 |
CLASS | +0.197 |
Neg logit contributions | |
angered | -0.184 |
genre | -0.166 |
adem | -0.146 |
bnb | -0.144 |
arios | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -5.96e-03 |
Pos logit contributions | |
angered | +0.785 |
genre | +0.718 |
adem | +0.633 |
bnb | +0.625 |
arios | +0.614 |
Neg logit contributions | |
illac | -0.800 |
Leaks | -0.776 |
ILY | -0.759 |
Nib | -0.751 |
CLASS | -0.748 |
Token | But |
Token ID | 887 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
illac | +0.015 |
Leaks | +0.015 |
ILY | +0.015 |
Nib | +0.014 |
CLASS | +0.014 |
Neg logit contributions | |
angered | -0.018 |
genre | -0.017 |
adem | -0.015 |
bnb | -0.015 |
arios | -0.015 |
Token | what |
Token ID | 644 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
illac | +0.163 |
Leaks | +0.157 |
ILY | +0.155 |
Nib | +0.153 |
CLASS | +0.152 |
Neg logit contributions | |
angered | -0.183 |
genre | -0.168 |
adem | -0.150 |
bnb | -0.148 |
arios | -0.146 |
Token | all |
Token ID | 477 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
angered | +1.341 |
genre | +1.220 |
adem | +1.106 |
bnb | +1.085 |
arios | +1.077 |
Neg logit contributions | |
illac | -1.129 |
Leaks | -1.085 |
ILY | -1.073 |
ャ | -1.045 |
Nib | -1.040 |
Token | came |
Token ID | 1625 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
illac | +0.105 |
Leaks | +0.101 |
ILY | +0.100 |
Nib | +0.099 |
CLASS | +0.098 |
Neg logit contributions | |
angered | -0.124 |
genre | -0.114 |
adem | -0.102 |
bnb | -0.101 |
arios | -0.100 |
Token | together |
Token ID | 1978 |
Feature activation | +8.48e-02 |
Pos logit contributions | |
illac | +0.518 |
Leaks | +0.498 |
ILY | +0.490 |
Nib | +0.485 |
CLASS | +0.482 |
Neg logit contributions | |
angered | -0.584 |
genre | -0.534 |
adem | -0.479 |
bnb | -0.472 |
arios | -0.467 |
Token | in |
Token ID | 287 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
angered | +0.254 |
genre | +0.232 |
adem | +0.208 |
bnb | +0.206 |
arios | +0.203 |
Neg logit contributions | |
illac | -0.223 |
Leaks | -0.215 |
ILY | -0.212 |
Nib | -0.208 |
CLASS | -0.208 |
Token | a |
Token ID | 257 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
illac | +0.435 |
Leaks | +0.417 |
ILY | +0.412 |
Nib | +0.404 |
CLASS | +0.402 |
Neg logit contributions | |
angered | -0.565 |
genre | -0.519 |
adem | -0.469 |
bnb | -0.464 |
arios | -0.458 |
Token | matter |
Token ID | 2300 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
illac | +1.108 |
Leaks | +1.074 |
ILY | +1.060 |
Nib | +1.051 |
CLASS | +1.045 |
Neg logit contributions | |
angered | -1.005 |
genre | -0.907 |
adem | -0.800 |
bnb | -0.789 |
arios | -0.776 |
Token | of |
Token ID | 286 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
illac | +3.142 |
Leaks | +3.084 |
Nib | +3.047 |
ILY | +3.041 |
CLASS | +3.023 |
Neg logit contributions | |
angered | -3.631 |
genre | -3.319 |
adem | -3.026 |
bnb | -2.939 |
arios | -2.932 |
Token | weeks |
Token ID | 2745 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
illac | +1.557 |
Leaks | +1.503 |
Nib | +1.469 |
ILY | +1.467 |
CLASS | +1.455 |
Neg logit contributions | |
angered | -2.793 |
genre | -2.594 |
adem | -2.365 |
bnb | -2.358 |
arios | -2.316 |
Token | ," |
Token ID | 553 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
illac | +2.203 |
Leaks | +2.125 |
ILY | +2.109 |
Nib | +2.092 |
CLASS | +2.080 |
Neg logit contributions | |
angered | -2.235 |
genre | -2.028 |
adem | -1.808 |
bnb | -1.760 |
arios | -1.745 |
Token | said |
Token ID | 531 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
illac | +0.191 |
Leaks | +0.183 |
ILY | +0.181 |
CLASS | +0.177 |
Nib | +0.177 |
Neg logit contributions | |
angered | -0.234 |
genre | -0.215 |
adem | -0.192 |
bnb | -0.191 |
arios | -0.189 |
Token | Mel |
Token ID | 5616 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
illac | +0.930 |
Leaks | +0.898 |
ILY | +0.886 |
Nib | +0.874 |
CLASS | +0.870 |
Neg logit contributions | |
angered | -0.996 |
genre | -0.907 |
adem | -0.810 |
bnb | -0.799 |
arios | -0.788 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
illac | +0.142 |
Leaks | +0.138 |
ILY | +0.135 |
Nib | +0.134 |
CLASS | +0.133 |
Neg logit contributions | |
angered | -0.167 |
genre | -0.153 |
adem | -0.138 |
bnb | -0.136 |
arios | -0.134 |
Token | The |
Token ID | 464 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
illac | +0.463 |
Leaks | +0.440 |
ILY | +0.434 |
Nib | +0.431 |
CLASS | +0.428 |
Neg logit contributions | |
angered | -0.586 |
genre | -0.539 |
adem | -0.484 |
bnb | -0.476 |
arios | -0.472 |
Token | rest |
Token ID | 1334 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
illac | +0.367 |
Leaks | +0.352 |
ILY | +0.347 |
Nib | +0.340 |
CLASS | +0.338 |
Neg logit contributions | |
angered | -0.438 |
genre | -0.401 |
adem | -0.361 |
bnb | -0.356 |
arios | -0.352 |
Token | of |
Token ID | 286 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
angered | +0.736 |
genre | +0.654 |
adem | +0.575 |
bnb | +0.567 |
arios | +0.558 |
Neg logit contributions | |
illac | -0.857 |
Leaks | -0.837 |
ILY | -0.820 |
Nib | -0.807 |
ャ | -0.804 |
Token | the |
Token ID | 262 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
illac | +0.551 |
Leaks | +0.528 |
ILY | +0.518 |
ャ | +0.507 |
Nib | +0.506 |
Neg logit contributions | |
angered | -0.723 |
genre | -0.666 |
adem | -0.601 |
bnb | -0.593 |
arios | -0.586 |
Token | class |
Token ID | 1398 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
illac | +0.321 |
Leaks | +0.307 |
ILY | +0.300 |
ャ | +0.293 |
Nib | +0.292 |
Neg logit contributions | |
angered | -0.440 |
genre | -0.406 |
adem | -0.368 |
bnb | -0.362 |
arios | -0.358 |
Token | are |
Token ID | 389 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
illac | +2.891 |
Leaks | +2.756 |
Nib | +2.749 |
ILY | +2.739 |
CLASS | +2.732 |
Neg logit contributions | |
angered | -3.930 |
genre | -3.642 |
adem | -3.261 |
bnb | -3.247 |
arios | -3.194 |
Token | the |
Token ID | 262 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
illac | +0.097 |
Leaks | +0.094 |
ILY | +0.092 |
Nib | +0.091 |
CLASS | +0.090 |
Neg logit contributions | |
angered | -0.107 |
genre | -0.097 |
adem | -0.087 |
bnb | -0.086 |
arios | -0.085 |
Token | 99 |
Token ID | 7388 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
illac | +0.848 |
Leaks | +0.819 |
ILY | +0.808 |
Nib | +0.799 |
CLASS | +0.794 |
Neg logit contributions | |
angered | -0.907 |
genre | -0.827 |
adem | -0.738 |
bnb | -0.729 |
arios | -0.718 |
Token | %; |
Token ID | 26525 |
Feature activation | -8.54e-03 |
Pos logit contributions | |
illac | +0.692 |
Leaks | +0.667 |
ILY | +0.660 |
Nib | +0.651 |
CLASS | +0.646 |
Neg logit contributions | |
angered | -0.704 |
genre | -0.639 |
adem | -0.569 |
bnb | -0.561 |
arios | -0.553 |
Token | Cart |
Token ID | 13690 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
illac | +0.022 |
Leaks | +0.021 |
ILY | +0.021 |
Nib | +0.021 |
CLASS | +0.021 |
Neg logit contributions | |
angered | -0.026 |
genre | -0.024 |
adem | -0.021 |
bnb | -0.021 |
arios | -0.021 |
Token | .) |
Token ID | 2014 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
angered | +1.717 |
genre | +1.562 |
adem | +1.414 |
bnb | +1.395 |
arios | +1.363 |
Neg logit contributions | |
illac | -1.689 |
Leaks | -1.646 |
ILY | -1.609 |
ャ | -1.568 |
CLASS | -1.567 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
illac | +0.553 |
Leaks | +0.531 |
ILY | +0.524 |
Nib | +0.512 |
CLASS | +0.512 |
Neg logit contributions | |
angered | -0.626 |
genre | -0.571 |
adem | -0.507 |
bnb | -0.503 |
arios | -0.495 |
Token |
|
Token ID | 198 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
angered | +0.529 |
genre | +0.482 |
adem | +0.431 |
bnb | +0.426 |
arios | +0.420 |
Neg logit contributions | |
illac | -0.468 |
Leaks | -0.450 |
ILY | -0.444 |
Nib | -0.439 |
CLASS | -0.436 |
Token | War |
Token ID | 13195 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
angered | +0.234 |
genre | +0.215 |
adem | +0.192 |
bnb | +0.188 |
arios | +0.186 |
Neg logit contributions | |
illac | -0.179 |
Leaks | -0.168 |
Nib | -0.167 |
CLASS | -0.166 |
ILY | -0.166 |
Token | ner |
Token ID | 1008 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
illac | +1.098 |
Leaks | +1.066 |
ILY | +1.050 |
Nib | +1.039 |
CLASS | +1.034 |
Neg logit contributions | |
angered | -0.970 |
genre | -0.874 |
adem | -0.768 |
bnb | -0.760 |
arios | -0.745 |
Token | Bros |
Token ID | 14266 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
illac | +1.320 |
Leaks | +1.257 |
ILY | +1.230 |
Nib | +1.210 |
CLASS | +1.198 |
Neg logit contributions | |
angered | -2.630 |
genre | -2.449 |
adem | -2.250 |
bnb | -2.227 |
arios | -2.204 |
Token | / |
Token ID | 1220 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
illac | +3.106 |
Leaks | +2.986 |
ILY | +2.941 |
Nib | +2.912 |
CLASS | +2.885 |
Neg logit contributions | |
angered | -3.696 |
genre | -3.402 |
adem | -3.057 |
bnb | -3.012 |
arios | -2.985 |
Token | Courtesy |
Token ID | 22984 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
angered | +0.554 |
genre | +0.501 |
adem | +0.444 |
bnb | +0.439 |
arios | +0.430 |
Neg logit contributions | |
illac | -0.580 |
Leaks | -0.559 |
ILY | -0.549 |
Nib | -0.540 |
ャ | -0.539 |
Token | Everett |
Token ID | 36815 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
illac | +0.046 |
Leaks | +0.045 |
ILY | +0.044 |
CLASS | +0.043 |
Nib | +0.043 |
Neg logit contributions | |
angered | -0.046 |
genre | -0.042 |
adem | -0.037 |
bnb | -0.037 |
arios | -0.036 |
Token | Collection |
Token ID | 12251 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
illac | +0.634 |
Leaks | +0.600 |
ILY | +0.591 |
Nib | +0.580 |
CLASS | +0.576 |
Neg logit contributions | |
angered | -1.057 |
genre | -0.979 |
adem | -0.896 |
bnb | -0.887 |
arios | -0.874 |
Token | Amy |
Token ID | 14235 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
illac | +1.284 |
Leaks | +1.238 |
ILY | +1.220 |
Nib | +1.205 |
CLASS | +1.197 |
Neg logit contributions | |
angered | -1.518 |
genre | -1.390 |
adem | -1.247 |
bnb | -1.233 |
arios | -1.215 |
Token | component |
Token ID | 7515 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
angered | +0.705 |
genre | +0.643 |
adem | +0.576 |
bnb | +0.569 |
arios | +0.560 |
Neg logit contributions | |
illac | -0.630 |
Leaks | -0.606 |
ILY | -0.596 |
Nib | -0.589 |
CLASS | -0.586 |
Token | const |
Token ID | 1500 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
angered | +1.071 |
genre | +0.975 |
adem | +0.871 |
bnb | +0.857 |
arios | +0.847 |
Neg logit contributions | |
illac | -0.986 |
Leaks | -0.950 |
ILY | -0.927 |
Nib | -0.921 |
CLASS | -0.911 |
Token | float |
Token ID | 12178 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
illac | +2.025 |
Leaks | +1.951 |
ILY | +1.940 |
Nib | +1.910 |
CLASS | +1.909 |
Neg logit contributions | |
angered | -2.152 |
genre | -1.962 |
adem | -1.751 |
bnb | -1.733 |
arios | -1.706 |
Token | TA |
Token ID | 21664 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
illac | +0.574 |
Leaks | +0.554 |
ILY | +0.545 |
Nib | +0.539 |
CLASS | +0.536 |
Neg logit contributions | |
angered | -0.649 |
genre | -0.593 |
adem | -0.531 |
bnb | -0.524 |
arios | -0.517 |
Token | U |
Token ID | 52 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
angered | +0.389 |
genre | +0.360 |
adem | +0.325 |
bnb | +0.323 |
arios | +0.316 |
Neg logit contributions | |
illac | -0.290 |
Leaks | -0.280 |
Nib | -0.272 |
CLASS | -0.268 |
ILY | -0.267 |
Token | = |
Token ID | 796 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
angered | +0.500 |
genre | +0.461 |
adem | +0.415 |
bnb | +0.411 |
arios | +0.402 |
Neg logit contributions | |
illac | -0.397 |
Leaks | -0.380 |
Nib | -0.372 |
ILY | -0.369 |
CLASS | -0.365 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
illac | +2.837 |
CLASS | +2.710 |
ILY | +2.704 |
Leaks | +2.692 |
Nib | +2.682 |
Neg logit contributions | |
angered | -3.961 |
genre | -3.656 |
bnb | -3.290 |
adem | -3.272 |
arios | -3.221 |
Token | . |
Token ID | 13 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
angered | +0.082 |
genre | +0.074 |
adem | +0.066 |
bnb | +0.065 |
arios | +0.064 |
Neg logit contributions | |
illac | -0.076 |
Leaks | -0.074 |
ILY | -0.072 |
Nib | -0.072 |
CLASS | -0.071 |
Token | 283 |
Token ID | 30290 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
angered | +0.794 |
genre | +0.718 |
adem | +0.638 |
bnb | +0.624 |
arios | +0.616 |
Neg logit contributions | |
illac | -0.859 |
Leaks | -0.829 |
ILY | -0.814 |
Nib | -0.810 |
CLASS | -0.802 |
Token | 185 |
Token ID | 21652 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
angered | +0.295 |
genre | +0.268 |
adem | +0.239 |
bnb | +0.236 |
arios | +0.232 |
Neg logit contributions | |
illac | -0.282 |
Leaks | -0.272 |
ILY | -0.267 |
Nib | -0.265 |
CLASS | -0.263 |
Token | 307 |
Token ID | 22996 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
illac | +0.476 |
Leaks | +0.459 |
ILY | +0.454 |
Nib | +0.448 |
CLASS | +0.445 |
Neg logit contributions | |
angered | -0.538 |
genre | -0.491 |
adem | -0.439 |
bnb | -0.435 |
arios | -0.428 |
Token | more |
Token ID | 517 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
angered | +0.645 |
genre | +0.595 |
adem | +0.542 |
bnb | +0.534 |
arios | +0.528 |
Neg logit contributions | |
illac | -0.462 |
Leaks | -0.443 |
ILY | -0.433 |
Nib | -0.426 |
CLASS | -0.423 |
Token | than |
Token ID | 621 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
illac | +0.518 |
Leaks | +0.497 |
ILY | +0.489 |
Nib | +0.482 |
CLASS | +0.479 |
Neg logit contributions | |
angered | -0.748 |
genre | -0.690 |
adem | -0.626 |
bnb | -0.619 |
arios | -0.611 |
Token | 60 |
Token ID | 3126 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
illac | +0.724 |
Leaks | +0.691 |
ILY | +0.682 |
Nib | +0.675 |
CLASS | +0.670 |
Neg logit contributions | |
angered | -1.283 |
genre | -1.190 |
adem | -1.085 |
bnb | -1.080 |
arios | -1.065 |
Token | % |
Token ID | 4 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
illac | +1.302 |
Leaks | +1.262 |
ILY | +1.248 |
Nib | +1.235 |
CLASS | +1.230 |
Neg logit contributions | |
angered | -1.106 |
genre | -0.996 |
adem | -0.873 |
bnb | -0.860 |
arios | -0.846 |
Token | of |
Token ID | 286 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
illac | +0.500 |
Leaks | +0.485 |
ILY | +0.478 |
Nib | +0.473 |
CLASS | +0.470 |
Neg logit contributions | |
angered | -0.468 |
genre | -0.423 |
adem | -0.375 |
bnb | -0.369 |
arios | -0.364 |
Token | respondents |
Token ID | 14502 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
illac | +0.953 |
Leaks | +0.921 |
ILY | +0.910 |
Nib | +0.900 |
CLASS | +0.895 |
Neg logit contributions | |
angered | -1.005 |
genre | -0.915 |
adem | -0.814 |
bnb | -0.804 |
arios | -0.793 |
Token | who |
Token ID | 508 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
illac | +3.147 |
Leaks | +3.002 |
ILY | +2.999 |
Nib | +2.947 |
CLASS | +2.946 |
Neg logit contributions | |
angered | -3.639 |
genre | -3.315 |
adem | -2.949 |
bnb | -2.941 |
arios | -2.889 |
Token | identified |
Token ID | 5174 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
illac | +0.632 |
Leaks | +0.607 |
ILY | +0.598 |
Nib | +0.591 |
CLASS | +0.587 |
Neg logit contributions | |
angered | -0.836 |
genre | -0.768 |
adem | -0.692 |
bnb | -0.686 |
arios | -0.677 |
Token | themselves |
Token ID | 2405 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
illac | +1.181 |
Leaks | +1.125 |
ILY | +1.110 |
Nib | +1.092 |
CLASS | +1.084 |
Neg logit contributions | |
angered | -2.016 |
genre | -1.870 |
adem | -1.706 |
bnb | -1.690 |
arios | -1.671 |
Token | as |
Token ID | 355 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
angered | +1.056 |
genre | +0.966 |
adem | +0.875 |
bnb | +0.862 |
arios | +0.850 |
Neg logit contributions | |
illac | -0.843 |
Leaks | -0.827 |
ILY | -0.794 |
Nib | -0.790 |
CLASS | -0.778 |
Token | middle |
Token ID | 3504 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
illac | +0.085 |
Leaks | +0.082 |
ILY | +0.081 |
Nib | +0.080 |
CLASS | +0.079 |
Neg logit contributions | |
angered | -0.107 |
genre | -0.098 |
adem | -0.089 |
bnb | -0.087 |
arios | -0.086 |
Token | stomach |
Token ID | 11384 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
illac | +0.029 |
Leaks | +0.028 |
ILY | +0.028 |
Nib | +0.027 |
CLASS | +0.027 |
Neg logit contributions | |
angered | -0.033 |
genre | -0.030 |
adem | -0.027 |
bnb | -0.027 |
arios | -0.026 |
Token | contents |
Token ID | 10154 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
illac | +1.351 |
Leaks | +1.308 |
ILY | +1.286 |
Nib | +1.275 |
CLASS | +1.265 |
Neg logit contributions | |
angered | -1.525 |
genre | -1.396 |
adem | -1.246 |
bnb | -1.236 |
arios | -1.218 |
Token | found |
Token ID | 1043 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
angered | +0.343 |
genre | +0.312 |
adem | +0.280 |
bnb | +0.276 |
arios | +0.272 |
Neg logit contributions | |
illac | -0.308 |
Leaks | -0.297 |
ILY | -0.293 |
Nib | -0.289 |
CLASS | -0.288 |
Token | a |
Token ID | 257 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
angered | +0.191 |
genre | +0.173 |
adem | +0.155 |
bnb | +0.152 |
arios | +0.151 |
Neg logit contributions | |
illac | -0.173 |
Leaks | -0.166 |
ILY | -0.164 |
CLASS | -0.161 |
Nib | -0.161 |
Token | con |
Token ID | 369 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
illac | +0.161 |
Leaks | +0.156 |
ILY | +0.154 |
Nib | +0.152 |
CLASS | +0.151 |
Neg logit contributions | |
angered | -0.168 |
genre | -0.153 |
adem | -0.136 |
bnb | -0.134 |
arios | -0.132 |
Token | ge |
Token ID | 469 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
illac | +0.120 |
Leaks | +0.117 |
ILY | +0.115 |
Nib | +0.114 |
CLASS | +0.113 |
Neg logit contributions | |
angered | -0.136 |
genre | -0.124 |
adem | -0.111 |
bnb | -0.109 |
arios | -0.108 |
Token | aled |
Token ID | 3021 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
illac | +3.445 |
Leaks | +3.285 |
Nib | +3.245 |
ILY | +3.220 |
ャ | +3.182 |
Neg logit contributions | |
angered | -3.297 |
genre | -2.962 |
bnb | -2.639 |
adem | -2.593 |
arios | -2.576 |
Token | , |
Token ID | 11 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
angered | +0.187 |
genre | +0.170 |
adem | +0.152 |
bnb | +0.150 |
arios | +0.148 |
Neg logit contributions | |
illac | -0.173 |
Leaks | -0.167 |
ILY | -0.165 |
Nib | -0.162 |
CLASS | -0.162 |
Token | brown |
Token ID | 7586 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
illac | +0.197 |
Leaks | +0.189 |
ILY | +0.187 |
Nib | +0.184 |
CLASS | +0.183 |
Neg logit contributions | |
angered | -0.229 |
genre | -0.209 |
adem | -0.188 |
bnb | -0.186 |
arios | -0.183 |
Token | ish |
Token ID | 680 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
angered | +0.203 |
genre | +0.185 |
adem | +0.165 |
bnb | +0.163 |
arios | +0.160 |
Neg logit contributions | |
illac | -0.187 |
Leaks | -0.180 |
ILY | -0.179 |
Nib | -0.175 |
CLASS | -0.175 |
Token | - |
Token ID | 12 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
illac | +0.643 |
Leaks | +0.621 |
ILY | +0.611 |
Nib | +0.607 |
CLASS | +0.601 |
Neg logit contributions | |
angered | -0.744 |
genre | -0.681 |
adem | -0.610 |
bnb | -0.605 |
arios | -0.595 |
Token | 93 |
Token ID | 6052 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
angered | +0.890 |
genre | +0.808 |
adem | +0.698 |
bnb | +0.680 |
arios | +0.670 |
Neg logit contributions | |
illac | -1.149 |
Leaks | -1.110 |
ILY | -1.101 |
CLASS | -1.091 |
Nib | -1.090 |
Token | ] |
Token ID | 60 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
angered | +0.037 |
genre | +0.034 |
adem | +0.031 |
bnb | +0.030 |
arios | +0.030 |
Neg logit contributions | |
illac | -0.030 |
Leaks | -0.029 |
ILY | -0.028 |
Nib | -0.028 |
CLASS | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
angered | +0.503 |
genre | +0.459 |
adem | +0.413 |
bnb | +0.404 |
arios | +0.398 |
Neg logit contributions | |
illac | -0.456 |
Leaks | -0.440 |
ILY | -0.434 |
Nib | -0.425 |
ャ | -0.423 |
Token |
|
Token ID | 198 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
angered | +1.305 |
genre | +1.182 |
adem | +1.049 |
bnb | +1.030 |
arios | +1.019 |
Neg logit contributions | |
illac | -1.245 |
Leaks | -1.184 |
ILY | -1.172 |
Nib | -1.160 |
CLASS | -1.156 |
Token | Bay |
Token ID | 15262 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
angered | +0.625 |
genre | +0.577 |
adem | +0.519 |
bnb | +0.504 |
arios | +0.497 |
Neg logit contributions | |
illac | -0.516 |
Nib | -0.484 |
Leaks | -0.484 |
ILY | -0.481 |
CLASS | -0.481 |
Token | ern |
Token ID | 1142 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
illac | +0.324 |
Leaks | +0.310 |
ILY | +0.305 |
Nib | +0.301 |
CLASS | +0.299 |
Neg logit contributions | |
angered | -0.496 |
genre | -0.459 |
adem | -0.417 |
bnb | -0.413 |
arios | -0.408 |
Token | Munich |
Token ID | 22418 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
illac | +3.389 |
Leaks | +3.291 |
Nib | +3.237 |
ILY | +3.230 |
CLASS | +3.210 |
Neg logit contributions | |
angered | -3.328 |
genre | -3.030 |
bnb | -2.657 |
adem | -2.646 |
arios | -2.594 |
Token | II |
Token ID | 2873 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
illac | +1.675 |
Leaks | +1.620 |
ILY | +1.596 |
Nib | +1.585 |
CLASS | +1.575 |
Neg logit contributions | |
angered | -1.701 |
genre | -1.548 |
adem | -1.371 |
bnb | -1.360 |
arios | -1.337 |
Token |
|
Token ID | 198 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
illac | +0.188 |
Leaks | +0.182 |
ILY | +0.179 |
Nib | +0.177 |
CLASS | +0.175 |
Neg logit contributions | |
angered | -0.191 |
genre | -0.173 |
adem | -0.156 |
bnb | -0.152 |
arios | -0.151 |
Token |
|
Token ID | 198 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
angered | +0.234 |
genre | +0.214 |
adem | +0.191 |
bnb | +0.189 |
arios | +0.186 |
Neg logit contributions | |
illac | -0.208 |
Leaks | -0.200 |
ILY | -0.197 |
Nib | -0.195 |
CLASS | -0.194 |
Token | Bay |
Token ID | 15262 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
illac | +0.033 |
Leaks | +0.031 |
ILY | +0.031 |
Nib | +0.031 |
CLASS | +0.030 |
Neg logit contributions | |
angered | -0.048 |
genre | -0.045 |
adem | -0.041 |
bnb | -0.040 |
arios | -0.039 |
Token | car |
Token ID | 1097 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
angered | +0.418 |
genre | +0.379 |
adem | +0.340 |
bnb | +0.335 |
arios | +0.330 |
Neg logit contributions | |
illac | -0.382 |
Leaks | -0.370 |
ILY | -0.365 |
Nib | -0.359 |
CLASS | -0.357 |
Token | . |
Token ID | 13 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
angered | +0.566 |
genre | +0.515 |
adem | +0.464 |
bnb | +0.457 |
arios | +0.447 |
Neg logit contributions | |
illac | -0.498 |
Leaks | -0.486 |
ILY | -0.479 |
Nib | -0.471 |
CLASS | -0.469 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
angered | +0.583 |
genre | +0.524 |
adem | +0.468 |
bnb | +0.464 |
arios | +0.456 |
Neg logit contributions | |
illac | -0.523 |
Leaks | -0.499 |
ILY | -0.492 |
CLASS | -0.482 |
Nib | -0.482 |
Token |
|
Token ID | 198 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
angered | +0.557 |
genre | +0.507 |
adem | +0.453 |
bnb | +0.448 |
arios | +0.441 |
Neg logit contributions | |
illac | -0.496 |
Leaks | -0.476 |
ILY | -0.470 |
Nib | -0.465 |
CLASS | -0.462 |
Token | B |
Token ID | 33 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
angered | +0.191 |
genre | +0.175 |
adem | +0.158 |
bnb | +0.154 |
arios | +0.153 |
Neg logit contributions | |
illac | -0.140 |
Nib | -0.130 |
Leaks | -0.130 |
CLASS | -0.130 |
ILY | -0.129 |
Token | art |
Token ID | 433 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
angered | +0.499 |
genre | +0.450 |
adem | +0.404 |
bnb | +0.394 |
arios | +0.392 |
Neg logit contributions | |
illac | -0.495 |
Leaks | -0.479 |
ILY | -0.474 |
Nib | -0.472 |
CLASS | -0.469 |
Token | was |
Token ID | 373 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
illac | +3.410 |
Leaks | +3.295 |
Nib | +3.233 |
ILY | +3.228 |
CLASS | +3.175 |
Neg logit contributions | |
angered | -3.332 |
genre | -3.039 |
adem | -2.683 |
bnb | -2.654 |
arios | -2.602 |
Token | discovered |
Token ID | 5071 |
Feature activation | +8.29e-02 |
Pos logit contributions | |
angered | +0.711 |
genre | +0.644 |
adem | +0.575 |
bnb | +0.563 |
arios | +0.557 |
Neg logit contributions | |
illac | -0.691 |
Leaks | -0.672 |
ILY | -0.659 |
Nib | -0.648 |
CLASS | -0.643 |
Token | by |
Token ID | 416 |
Feature activation | +9.24e-03 |
Pos logit contributions | |
angered | +0.238 |
genre | +0.215 |
adem | +0.192 |
bnb | +0.189 |
arios | +0.186 |
Neg logit contributions | |
illac | -0.230 |
Leaks | -0.222 |
ILY | -0.220 |
Nib | -0.215 |
CLASS | -0.215 |
Token | its |
Token ID | 663 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
angered | +0.028 |
genre | +0.025 |
adem | +0.023 |
bnb | +0.022 |
arios | +0.022 |
Neg logit contributions | |
illac | -0.024 |
Leaks | -0.023 |
ILY | -0.023 |
ャ | -0.023 |
Nib | -0.023 |
Token | owner |
Token ID | 4870 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
angered | +0.211 |
genre | +0.189 |
adem | +0.166 |
bnb | +0.163 |
arios | +0.160 |
Neg logit contributions | |
illac | -0.261 |
Leaks | -0.253 |
ILY | -0.250 |
Nib | -0.247 |
CLASS | -0.246 |
Token | under |
Token ID | 739 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
angered | +0.480 |
genre | +0.438 |
adem | +0.391 |
bnb | +0.385 |
arios | +0.379 |
Neg logit contributions | |
illac | -0.455 |
Leaks | -0.438 |
ILY | -0.431 |
Nib | -0.428 |
CLASS | -0.426 |
Token | here |
Token ID | 994 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
angered | +2.304 |
genre | +2.112 |
adem | +1.880 |
bnb | +1.850 |
arios | +1.837 |
Neg logit contributions | |
illac | -2.061 |
Leaks | -1.932 |
ILY | -1.930 |
Nib | -1.905 |
CLASS | -1.896 |
Token | . |
Token ID | 13 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
angered | +0.509 |
genre | +0.461 |
adem | +0.411 |
bnb | +0.407 |
arios | +0.400 |
Neg logit contributions | |
illac | -0.495 |
Leaks | -0.479 |
ILY | -0.470 |
Nib | -0.467 |
CLASS | -0.465 |
Token |
|
Token ID | 198 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
illac | +0.170 |
Leaks | +0.163 |
ILY | +0.161 |
Nib | +0.159 |
CLASS | +0.158 |
Neg logit contributions | |
angered | -0.199 |
genre | -0.182 |
adem | -0.163 |
bnb | -0.161 |
arios | -0.159 |
Token |
|
Token ID | 198 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
illac | +0.240 |
Leaks | +0.232 |
ILY | +0.229 |
Nib | +0.226 |
CLASS | +0.224 |
Neg logit contributions | |
angered | -0.284 |
genre | -0.261 |
adem | -0.234 |
bnb | -0.232 |
arios | -0.228 |
Token | Thank |
Token ID | 10449 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
illac | +0.448 |
Leaks | +0.425 |
ILY | +0.420 |
Nib | +0.419 |
CLASS | +0.416 |
Neg logit contributions | |
angered | -0.596 |
genre | -0.549 |
adem | -0.496 |
bnb | -0.488 |
arios | -0.482 |
Token | you |
Token ID | 345 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
illac | +2.785 |
Leaks | +2.691 |
ILY | +2.664 |
Nib | +2.608 |
CLASS | +2.585 |
Neg logit contributions | |
angered | -3.909 |
genre | -3.599 |
adem | -3.255 |
bnb | -3.219 |
arios | -3.191 |
Token |
|
Token ID | 198 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
illac | +1.554 |
Leaks | +1.498 |
ILY | +1.483 |
Nib | +1.462 |
CLASS | +1.452 |
Neg logit contributions | |
angered | -1.847 |
genre | -1.691 |
adem | -1.517 |
bnb | -1.499 |
arios | -1.479 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
illac | +0.091 |
Leaks | +0.088 |
ILY | +0.087 |
Nib | +0.086 |
CLASS | +0.085 |
Neg logit contributions | |
angered | -0.108 |
genre | -0.099 |
adem | -0.088 |
bnb | -0.087 |
arios | -0.086 |
Token | Find |
Token ID | 16742 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
illac | +0.298 |
Leaks | +0.283 |
ILY | +0.279 |
Nib | +0.278 |
CLASS | +0.276 |
Neg logit contributions | |
angered | -0.402 |
genre | -0.370 |
adem | -0.335 |
bnb | -0.330 |
arios | -0.326 |
Token | out |
Token ID | 503 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
angered | +0.727 |
genre | +0.663 |
adem | +0.603 |
bnb | +0.596 |
arios | +0.584 |
Neg logit contributions | |
illac | -0.570 |
Leaks | -0.540 |
ILY | -0.530 |
Nib | -0.525 |
CLASS | -0.523 |
Token | like |
Token ID | 588 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
angered | +0.158 |
genre | +0.143 |
adem | +0.128 |
bnb | +0.126 |
arios | +0.124 |
Neg logit contributions | |
illac | -0.153 |
Leaks | -0.148 |
ILY | -0.146 |
Nib | -0.144 |
CLASS | -0.143 |
Token | Mormons |
Token ID | 33003 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
illac | +0.448 |
Leaks | +0.433 |
ILY | +0.426 |
Nib | +0.420 |
CLASS | +0.418 |
Neg logit contributions | |
angered | -0.521 |
genre | -0.476 |
adem | -0.427 |
bnb | -0.422 |
arios | -0.416 |
Token | love |
Token ID | 1842 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
illac | +0.162 |
Leaks | +0.157 |
ILY | +0.154 |
Nib | +0.152 |
CLASS | +0.151 |
Neg logit contributions | |
angered | -0.208 |
genre | -0.191 |
adem | -0.172 |
bnb | -0.171 |
arios | -0.168 |
Token | a |
Token ID | 257 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
illac | +0.713 |
Leaks | +0.685 |
ILY | +0.674 |
Nib | +0.663 |
CLASS | +0.660 |
Neg logit contributions | |
angered | -0.979 |
genre | -0.901 |
adem | -0.816 |
bnb | -0.806 |
arios | -0.797 |
Token | tab |
Token ID | 7400 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
angered | +1.328 |
genre | +1.207 |
adem | +1.083 |
bnb | +1.065 |
arios | +1.054 |
Neg logit contributions | |
illac | -1.174 |
Leaks | -1.131 |
ILY | -1.115 |
Nib | -1.098 |
CLASS | -1.092 |
Token | ern |
Token ID | 1142 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
angered | +0.033 |
genre | +0.030 |
adem | +0.027 |
bnb | +0.027 |
arios | +0.026 |
Neg logit contributions | |
illac | -0.028 |
Leaks | -0.027 |
ILY | -0.027 |
Nib | -0.027 |
CLASS | -0.027 |
Token | acle |
Token ID | 6008 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
illac | +2.121 |
Leaks | +2.019 |
ILY | +1.956 |
Nib | +1.955 |
CLASS | +1.915 |
Neg logit contributions | |
angered | -4.474 |
genre | -4.205 |
bnb | -3.875 |
adem | -3.854 |
arios | -3.769 |
Token | choir |
Token ID | 42644 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
angered | +0.549 |
genre | +0.499 |
adem | +0.447 |
bnb | +0.440 |
arios | +0.433 |
Neg logit contributions | |
illac | -0.526 |
Leaks | -0.509 |
ILY | -0.503 |
CLASS | -0.493 |
Nib | -0.492 |
Token | . |
Token ID | 13 |
Feature activation | +4.06e-03 |
Pos logit contributions | |
angered | +0.311 |
genre | +0.284 |
adem | +0.252 |
bnb | +0.249 |
arios | +0.245 |
Neg logit contributions | |
illac | -0.298 |
Leaks | -0.291 |
ILY | -0.286 |
Nib | -0.282 |
CLASS | -0.280 |
Token | We |
Token ID | 775 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
angered | +0.012 |
genre | +0.011 |
adem | +0.010 |
bnb | +0.010 |
arios | +0.010 |
Neg logit contributions | |
illac | -0.010 |
Leaks | -0.010 |
ILY | -0.010 |
Nib | -0.010 |
CLASS | -0.010 |
Token | pass |
Token ID | 1208 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
angered | +1.090 |
genre | +1.000 |
adem | +0.906 |
bnb | +0.896 |
arios | +0.888 |
Neg logit contributions | |
illac | -0.791 |
Leaks | -0.764 |
ILY | -0.749 |
Nib | -0.741 |
CLASS | -0.734 |
Token | list |
Token ID | 4868 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
angered | +0.558 |
genre | +0.500 |
adem | +0.439 |
bnb | +0.433 |
arios | +0.426 |
Neg logit contributions | |
illac | -0.678 |
Leaks | -0.657 |
ILY | -0.649 |
Nib | -0.642 |
CLASS | -0.639 |
Token | _ |
Token ID | 62 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
angered | +0.170 |
genre | +0.156 |
adem | +0.141 |
bnb | +0.139 |
arios | +0.137 |
Neg logit contributions | |
illac | -0.129 |
Leaks | -0.124 |
ILY | -0.122 |
Nib | -0.121 |
CLASS | -0.120 |
Token | images |
Token ID | 17566 |
Feature activation | -6.60e-03 |
Pos logit contributions | |
illac | +0.200 |
Leaks | +0.194 |
ILY | +0.190 |
Nib | +0.186 |
CLASS | +0.184 |
Neg logit contributions | |
angered | -0.289 |
genre | -0.267 |
adem | -0.242 |
bnb | -0.241 |
arios | -0.236 |
Token | ( |
Token ID | 7 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
illac | +0.017 |
Leaks | +0.017 |
ILY | +0.016 |
Nib | +0.016 |
CLASS | +0.016 |
Neg logit contributions | |
angered | -0.020 |
genre | -0.018 |
adem | -0.016 |
bnb | -0.016 |
arios | -0.016 |
Token | args |
Token ID | 22046 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
angered | +0.141 |
genre | +0.127 |
adem | +0.110 |
bnb | +0.108 |
arios | +0.107 |
Neg logit contributions | |
illac | -0.177 |
Leaks | -0.172 |
ILY | -0.170 |
Nib | -0.169 |
CLASS | -0.168 |
Token | [" |
Token ID | 14692 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
angered | +0.565 |
genre | +0.491 |
adem | +0.401 |
bnb | +0.401 |
arios | +0.386 |
Neg logit contributions | |
illac | -0.958 |
Leaks | -0.935 |
Nib | -0.923 |
ILY | -0.917 |
CLASS | -0.917 |
Token | images |
Token ID | 17566 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
angered | +2.606 |
genre | +2.388 |
adem | +2.144 |
bnb | +2.089 |
arios | +2.071 |
Neg logit contributions | |
illac | -2.147 |
Nib | -2.044 |
Leaks | -2.033 |
CLASS | -2.029 |
ILY | -2.026 |
Token | "] |
Token ID | 8973 |
Feature activation | +9.40e-02 |
Pos logit contributions | |
angered | +0.246 |
genre | +0.210 |
adem | +0.169 |
bnb | +0.165 |
arios | +0.161 |
Neg logit contributions | |
illac | -0.537 |
Leaks | -0.523 |
ILY | -0.518 |
Nib | -0.515 |
CLASS | -0.513 |
Token | ): |
Token ID | 2599 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
angered | +0.224 |
genre | +0.200 |
adem | +0.173 |
bnb | +0.170 |
arios | +0.167 |
Neg logit contributions | |
illac | -0.306 |
Leaks | -0.297 |
ILY | -0.293 |
Nib | -0.290 |
CLASS | -0.289 |
Token | # |
Token ID | 1303 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
angered | +0.844 |
genre | +0.754 |
adem | +0.652 |
bnb | +0.637 |
arios | +0.627 |
Neg logit contributions | |
illac | -1.130 |
Leaks | -1.097 |
ILY | -1.080 |
Nib | -1.063 |
ャ | -1.060 |
Token | load |
Token ID | 3440 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
angered | +1.905 |
genre | +1.693 |
adem | +1.482 |
argo | +1.433 |
bnb | +1.431 |
Neg logit contributions | |
illac | -2.702 |
Leaks | -2.608 |
ILY | -2.582 |
Nib | -2.550 |
ャ | -2.544 |
Token | costs |
Token ID | 3484 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
angered | +1.188 |
genre | +1.066 |
adem | +0.952 |
bnb | +0.933 |
arios | +0.931 |
Neg logit contributions | |
illac | -1.204 |
Leaks | -1.155 |
ILY | -1.150 |
Nib | -1.135 |
CLASS | -1.125 |
Token | . |
Token ID | 13 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
illac | +0.475 |
Leaks | +0.459 |
ILY | +0.453 |
Nib | +0.449 |
CLASS | +0.446 |
Neg logit contributions | |
angered | -0.457 |
genre | -0.415 |
adem | -0.367 |
bnb | -0.362 |
arios | -0.356 |
Token |
|
Token ID | 198 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
illac | +0.183 |
Leaks | +0.177 |
ILY | +0.174 |
Nib | +0.172 |
CLASS | +0.171 |
Neg logit contributions | |
angered | -0.217 |
genre | -0.199 |
adem | -0.178 |
bnb | -0.176 |
arios | -0.174 |
Token |
|
Token ID | 198 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
angered | +0.063 |
genre | +0.057 |
adem | +0.051 |
bnb | +0.051 |
arios | +0.050 |
Neg logit contributions | |
illac | -0.054 |
Leaks | -0.052 |
ILY | -0.051 |
Nib | -0.051 |
CLASS | -0.050 |
Token | L |
Token ID | 43 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
illac | +0.101 |
Leaks | +0.096 |
ILY | +0.095 |
Nib | +0.095 |
CLASS | +0.094 |
Neg logit contributions | |
angered | -0.130 |
genre | -0.120 |
adem | -0.108 |
bnb | -0.106 |
arios | -0.105 |
Token | NG |
Token ID | 10503 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
illac | +0.043 |
Leaks | +0.041 |
Nib | +0.041 |
ャ | +0.040 |
ILY | +0.040 |
Neg logit contributions | |
angered | -0.052 |
genre | -0.047 |
adem | -0.042 |
arios | -0.042 |
bnb | -0.041 |
Token | has |
Token ID | 468 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
angered | +2.943 |
genre | +2.672 |
adem | +2.405 |
bnb | +2.388 |
arios | +2.368 |
Neg logit contributions | |
illac | -2.494 |
ILY | -2.378 |
Leaks | -2.352 |
Nib | -2.326 |
ャ | -2.316 |
Token | a |
Token ID | 257 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
angered | +0.659 |
genre | +0.602 |
adem | +0.540 |
bnb | +0.534 |
arios | +0.527 |
Neg logit contributions | |
illac | -0.562 |
Leaks | -0.541 |
ILY | -0.533 |
Nib | -0.526 |
CLASS | -0.523 |
Token | number |
Token ID | 1271 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
angered | +0.205 |
genre | +0.187 |
adem | +0.166 |
bnb | +0.164 |
arios | +0.161 |
Neg logit contributions | |
illac | -0.201 |
Leaks | -0.194 |
ILY | -0.192 |
Nib | -0.190 |
CLASS | -0.188 |
Token | of |
Token ID | 286 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
illac | +1.045 |
Leaks | +1.012 |
ILY | +1.000 |
Nib | +0.989 |
CLASS | +0.987 |
Neg logit contributions | |
angered | -1.045 |
genre | -0.958 |
adem | -0.851 |
bnb | -0.835 |
arios | -0.822 |
Token | prominent |
Token ID | 9208 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
angered | +0.463 |
genre | +0.418 |
adem | +0.368 |
bnb | +0.363 |
arios | +0.357 |
Neg logit contributions | |
illac | -0.521 |
Leaks | -0.505 |
ILY | -0.499 |
Nib | -0.493 |
CLASS | -0.491 |
Token | . |
Token ID | 13 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
illac | +1.610 |
Leaks | +1.555 |
ILY | +1.553 |
Nib | +1.531 |
CLASS | +1.520 |
Neg logit contributions | |
angered | -2.002 |
genre | -1.845 |
adem | -1.662 |
bnb | -1.637 |
arios | -1.614 |
Token |
|
Token ID | 198 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
illac | +0.201 |
Leaks | +0.192 |
ILY | +0.190 |
Nib | +0.187 |
CLASS | +0.186 |
Neg logit contributions | |
angered | -0.223 |
genre | -0.202 |
adem | -0.181 |
bnb | -0.179 |
arios | -0.176 |
Token |
|
Token ID | 198 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
angered | +0.279 |
genre | +0.255 |
adem | +0.228 |
bnb | +0.225 |
arios | +0.222 |
Neg logit contributions | |
illac | -0.249 |
Leaks | -0.239 |
ILY | -0.236 |
Nib | -0.233 |
CLASS | -0.232 |
Token | Article |
Token ID | 14906 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
illac | +0.095 |
Leaks | +0.090 |
Nib | +0.090 |
CLASS | +0.089 |
ILY | +0.089 |
Neg logit contributions | |
angered | -0.112 |
genre | -0.102 |
adem | -0.091 |
bnb | -0.090 |
arios | -0.089 |
Token | Continued |
Token ID | 22168 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
illac | +0.598 |
Leaks | +0.573 |
ILY | +0.561 |
Nib | +0.552 |
CLASS | +0.547 |
Neg logit contributions | |
angered | -1.109 |
genre | -1.033 |
adem | -0.944 |
bnb | -0.936 |
arios | -0.925 |
Token | Below |
Token ID | 10383 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
angered | +0.952 |
genre | +0.854 |
adem | +0.749 |
bnb | +0.739 |
arios | +0.726 |
Neg logit contributions | |
illac | -1.128 |
Leaks | -1.088 |
ILY | -1.077 |
Nib | -1.065 |
CLASS | -1.059 |
Token |
|
Token ID | 198 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
angered | +3.080 |
genre | +2.751 |
adem | +2.392 |
bnb | +2.349 |
arios | +2.330 |
Neg logit contributions | |
illac | -3.366 |
Leaks | -3.138 |
ャ | -3.129 |
ILY | -3.128 |
Nib | -3.114 |
Token |
|
Token ID | 198 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
illac | +0.531 |
Leaks | +0.517 |
ILY | +0.508 |
Nib | +0.502 |
CLASS | +0.497 |
Neg logit contributions | |
angered | -0.649 |
genre | -0.597 |
adem | -0.539 |
bnb | -0.533 |
arios | -0.524 |
Token | T |
Token ID | 51 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
illac | +0.827 |
Leaks | +0.790 |
ILY | +0.779 |
Nib | +0.773 |
CLASS | +0.768 |
Neg logit contributions | |
angered | -1.065 |
genre | -0.977 |
adem | -0.881 |
bnb | -0.869 |
arios | -0.859 |
Token | od |
Token ID | 375 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
illac | +0.316 |
Leaks | +0.305 |
ILY | +0.301 |
Nib | +0.298 |
CLASS | +0.295 |
Neg logit contributions | |
angered | -0.386 |
genre | -0.353 |
adem | -0.321 |
bnb | -0.313 |
arios | -0.312 |
Token | as |
Token ID | 292 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
angered | +0.846 |
genre | +0.772 |
adem | +0.695 |
bnb | +0.679 |
arios | +0.675 |
Neg logit contributions | |
illac | -0.751 |
Leaks | -0.725 |
ILY | -0.720 |
Nib | -0.712 |
CLASS | -0.710 |
Token | 92 |
Token ID | 5892 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
illac | +0.110 |
Leaks | +0.105 |
ILY | +0.103 |
Nib | +0.103 |
CLASS | +0.102 |
Neg logit contributions | |
angered | -0.135 |
genre | -0.125 |
adem | -0.112 |
bnb | -0.111 |
arios | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
angered | +0.895 |
genre | +0.822 |
adem | +0.741 |
bnb | +0.731 |
arios | +0.719 |
Neg logit contributions | |
illac | -0.771 |
Leaks | -0.740 |
ILY | -0.731 |
Nib | -0.719 |
CLASS | -0.713 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
illac | +0.117 |
Leaks | +0.112 |
ILY | +0.110 |
Nib | +0.109 |
CLASS | +0.108 |
Neg logit contributions | |
angered | -0.149 |
genre | -0.137 |
adem | -0.123 |
bnb | -0.122 |
arios | -0.120 |
Token | - |
Token ID | 12 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
illac | +0.726 |
Leaks | +0.698 |
ILY | +0.687 |
Nib | +0.678 |
CLASS | +0.673 |
Neg logit contributions | |
angered | -0.934 |
genre | -0.859 |
adem | -0.775 |
bnb | -0.766 |
arios | -0.755 |
Token | mile |
Token ID | 18085 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
illac | +0.068 |
Leaks | +0.066 |
ILY | +0.064 |
Nib | +0.064 |
CLASS | +0.063 |
Neg logit contributions | |
angered | -0.081 |
genre | -0.075 |
adem | -0.067 |
bnb | -0.066 |
arios | -0.065 |
Token | per |
Token ID | 583 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
illac | +0.228 |
Leaks | +0.220 |
ILY | +0.217 |
CLASS | +0.212 |
Nib | +0.212 |
Neg logit contributions | |
angered | -0.239 |
genre | -0.218 |
adem | -0.196 |
bnb | -0.192 |
arios | -0.189 |
Token | hour |
Token ID | 1711 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
angered | +2.994 |
genre | +2.778 |
adem | +2.583 |
bnb | +2.497 |
arios | +2.478 |
Neg logit contributions | |
illac | -1.706 |
Leaks | -1.624 |
ILY | -1.576 |
ャ | -1.532 |
CLASS | -1.509 |
Token | ) |
Token ID | 8 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
angered | +0.764 |
genre | +0.702 |
adem | +0.642 |
bnb | +0.624 |
arios | +0.615 |
Neg logit contributions | |
illac | -0.625 |
Leaks | -0.601 |
ILY | -0.588 |
Nib | -0.574 |
CLASS | -0.574 |
Token | change |
Token ID | 1487 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
angered | +0.117 |
genre | +0.107 |
adem | +0.096 |
bnb | +0.094 |
arios | +0.093 |
Neg logit contributions | |
illac | -0.110 |
Leaks | -0.106 |
ILY | -0.105 |
Nib | -0.103 |
CLASS | -0.103 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
illac | +0.994 |
Leaks | +0.960 |
ILY | +0.948 |
Nib | +0.937 |
CLASS | +0.930 |
Neg logit contributions | |
angered | -1.088 |
genre | -0.994 |
adem | -0.887 |
bnb | -0.878 |
arios | -0.863 |
Token | velocity |
Token ID | 15432 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
angered | +0.307 |
genre | +0.280 |
adem | +0.250 |
bnb | +0.246 |
arios | +0.243 |
Neg logit contributions | |
illac | -0.291 |
Leaks | -0.281 |
ILY | -0.277 |
Nib | -0.273 |
CLASS | -0.272 |
Token | can |
Token ID | 460 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
angered | +0.285 |
genre | +0.261 |
adem | +0.235 |
bnb | +0.232 |
arios | +0.228 |
Neg logit contributions | |
illac | -0.240 |
Leaks | -0.231 |
ILY | -0.227 |
Nib | -0.224 |
CLASS | -0.223 |
Token | be |
Token ID | 307 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
illac | +0.212 |
Leaks | +0.205 |
ILY | +0.202 |
Nib | +0.200 |
CLASS | +0.198 |
Neg logit contributions | |
angered | -0.258 |
genre | -0.237 |
adem | -0.213 |
bnb | -0.210 |
arios | -0.207 |
Token | of |
Token ID | 286 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
illac | +0.203 |
Leaks | +0.196 |
ILY | +0.193 |
Nib | +0.191 |
CLASS | +0.190 |
Neg logit contributions | |
angered | -0.239 |
genre | -0.220 |
adem | -0.197 |
bnb | -0.195 |
arios | -0.191 |
Token | great |
Token ID | 1049 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
angered | +0.040 |
genre | +0.037 |
adem | +0.033 |
bnb | +0.033 |
arios | +0.032 |
Neg logit contributions | |
illac | -0.037 |
Leaks | -0.036 |
ILY | -0.035 |
Nib | -0.035 |
CLASS | -0.034 |
Token | mutual |
Token ID | 13584 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
illac | +0.101 |
Leaks | +0.098 |
ILY | +0.097 |
Nib | +0.096 |
CLASS | +0.095 |
Neg logit contributions | |
angered | -0.083 |
genre | -0.075 |
adem | -0.065 |
bnb | -0.065 |
arios | -0.063 |
Token | benefit |
Token ID | 4414 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
angered | +0.254 |
genre | +0.228 |
adem | +0.198 |
bnb | +0.195 |
arios | +0.191 |
Neg logit contributions | |
illac | -0.331 |
Leaks | -0.322 |
ILY | -0.319 |
Nib | -0.316 |
CLASS | -0.314 |
Token | to |
Token ID | 284 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
angered | +2.839 |
genre | +2.601 |
bnb | +2.299 |
adem | +2.291 |
arios | +2.269 |
Neg logit contributions | |
illac | -2.775 |
Leaks | -2.694 |
ILY | -2.590 |
ャ | -2.587 |
CLASS | -2.585 |
Token | fans |
Token ID | 3296 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
illac | +0.322 |
Leaks | +0.310 |
ILY | +0.307 |
Nib | +0.303 |
CLASS | +0.300 |
Neg logit contributions | |
angered | -0.425 |
genre | -0.390 |
adem | -0.352 |
bnb | -0.349 |
arios | -0.344 |
Token | and |
Token ID | 290 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
angered | +0.425 |
genre | +0.386 |
adem | +0.344 |
bnb | +0.340 |
arios | +0.335 |
Neg logit contributions | |
illac | -0.408 |
Leaks | -0.394 |
ILY | -0.389 |
Nib | -0.385 |
CLASS | -0.383 |
Token | club |
Token ID | 3430 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
angered | +0.434 |
genre | +0.396 |
adem | +0.352 |
bnb | +0.348 |
arios | +0.343 |
Neg logit contributions | |
illac | -0.418 |
Leaks | -0.403 |
ILY | -0.397 |
Nib | -0.392 |
CLASS | -0.390 |
Token | alike |
Token ID | 12936 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
illac | +0.132 |
Leaks | +0.128 |
ILY | +0.127 |
Nib | +0.125 |
CLASS | +0.124 |
Neg logit contributions | |
angered | -0.142 |
genre | -0.129 |
adem | -0.116 |
bnb | -0.114 |
arios | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
illac | +0.063 |
Leaks | +0.061 |
ILY | +0.060 |
Nib | +0.060 |
CLASS | +0.059 |
Neg logit contributions | |
angered | -0.064 |
genre | -0.058 |
adem | -0.052 |
bnb | -0.051 |
arios | -0.050 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
angered | +0.456 |
genre | +0.422 |
adem | +0.388 |
bnb | +0.385 |
arios | +0.380 |
Neg logit contributions | |
illac | -0.237 |
Leaks | -0.224 |
ILY | -0.219 |
Nib | -0.214 |
CLASS | -0.213 |
Token | } |
Token ID | 92 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
illac | +0.052 |
Leaks | +0.050 |
ILY | +0.049 |
Nib | +0.049 |
CLASS | +0.049 |
Neg logit contributions | |
angered | -0.057 |
genre | -0.052 |
adem | -0.047 |
bnb | -0.046 |
arios | -0.045 |
Token | -> |
Token ID | 4613 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
illac | +0.897 |
Leaks | +0.853 |
ILY | +0.835 |
Nib | +0.820 |
CLASS | +0.812 |
Neg logit contributions | |
angered | -1.731 |
genre | -1.611 |
adem | -1.476 |
bnb | -1.463 |
arios | -1.446 |
Token | " |
Token ID | 366 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
angered | +0.686 |
genre | +0.608 |
adem | +0.520 |
bnb | +0.513 |
arios | +0.502 |
Neg logit contributions | |
illac | -1.029 |
Leaks | -1.002 |
ILY | -0.989 |
Nib | -0.973 |
CLASS | -0.972 |
Token | S |
Token ID | 50 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
angered | +0.179 |
genre | +0.166 |
adem | +0.150 |
bnb | +0.149 |
arios | +0.147 |
Neg logit contributions | |
illac | -0.111 |
Leaks | -0.105 |
ILY | -0.103 |
Nib | -0.102 |
CLASS | -0.102 |
Token | ", |
Token ID | 1600 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
angered | +0.514 |
genre | +0.457 |
adem | +0.394 |
bnb | +0.389 |
arios | +0.381 |
Neg logit contributions | |
illac | -0.711 |
Leaks | -0.692 |
ILY | -0.681 |
Nib | -0.676 |
CLASS | -0.672 |
Token | { |
Token ID | 1391 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
angered | +0.069 |
genre | +0.062 |
adem | +0.054 |
bnb | +0.053 |
arios | +0.052 |
Neg logit contributions | |
illac | -0.093 |
Leaks | -0.091 |
ILY | -0.090 |
Nib | -0.088 |
CLASS | -0.088 |
Token | 9 |
Token ID | 24 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
angered | +1.398 |
genre | +1.273 |
adem | +1.126 |
bnb | +1.118 |
arios | +1.094 |
Neg logit contributions | |
illac | -1.298 |
Leaks | -1.232 |
ILY | -1.216 |
Nib | -1.214 |
CLASS | -1.207 |
Token | , |
Token ID | 11 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
angered | +0.345 |
genre | +0.314 |
adem | +0.279 |
bnb | +0.276 |
arios | +0.272 |
Neg logit contributions | |
illac | -0.334 |
Leaks | -0.323 |
ILY | -0.319 |
Nib | -0.315 |
CLASS | -0.313 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
angered | +0.772 |
genre | +0.707 |
adem | +0.640 |
bnb | +0.635 |
arios | +0.627 |
Neg logit contributions | |
illac | -0.545 |
Leaks | -0.520 |
ILY | -0.511 |
Nib | -0.499 |
ャ | -0.497 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
angered | +0.496 |
genre | +0.451 |
adem | +0.402 |
bnb | +0.397 |
arios | +0.391 |
Neg logit contributions | |
illac | -0.451 |
Leaks | -0.431 |
ILY | -0.425 |
Nib | -0.422 |
CLASS | -0.420 |
Token | Jud |
Token ID | 26141 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
angered | +0.490 |
genre | +0.450 |
adem | +0.407 |
bnb | +0.396 |
arios | +0.391 |
Neg logit contributions | |
illac | -0.358 |
Nib | -0.338 |
CLASS | -0.331 |
Leaks | -0.328 |
ILY | -0.328 |
Token | icial |
Token ID | 6652 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
angered | +1.357 |
genre | +1.261 |
adem | +1.167 |
bnb | +1.142 |
argo | +1.122 |
Neg logit contributions | |
illac | -0.688 |
Leaks | -0.644 |
ILY | -0.642 |
Nib | -0.639 |
ャ | -0.634 |
Token | Watch |
Token ID | 6305 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
angered | +0.963 |
genre | +0.875 |
adem | +0.787 |
bnb | +0.776 |
arios | +0.759 |
Neg logit contributions | |
illac | -0.906 |
ILY | -0.866 |
Leaks | -0.861 |
Nib | -0.852 |
ャ | -0.844 |
Token | , |
Token ID | 11 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
angered | +1.645 |
genre | +1.474 |
adem | +1.339 |
bnb | +1.322 |
arios | +1.307 |
Neg logit contributions | |
illac | -1.446 |
ILY | -1.362 |
Leaks | -1.358 |
Nib | -1.345 |
ャ | -1.322 |
Token | which |
Token ID | 543 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
angered | +0.231 |
genre | +0.211 |
adem | +0.192 |
bnb | +0.189 |
arios | +0.186 |
Neg logit contributions | |
illac | -0.171 |
Leaks | -0.163 |
ILY | -0.160 |
Nib | -0.159 |
CLASS | -0.157 |
Token | sued |
Token ID | 16334 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
angered | +0.168 |
genre | +0.153 |
adem | +0.138 |
bnb | +0.136 |
arios | +0.135 |
Neg logit contributions | |
illac | -0.141 |
Leaks | -0.134 |
ILY | -0.133 |
Nib | -0.131 |
CLASS | -0.130 |
Token | to |
Token ID | 284 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
angered | +0.547 |
genre | +0.497 |
adem | +0.453 |
bnb | +0.447 |
arios | +0.436 |
Neg logit contributions | |
illac | -0.446 |
Leaks | -0.426 |
ャ | -0.419 |
ILY | -0.418 |
Nib | -0.417 |
Token | force |
Token ID | 2700 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
angered | +0.343 |
genre | +0.313 |
adem | +0.284 |
bnb | +0.277 |
arios | +0.273 |
Neg logit contributions | |
illac | -0.304 |
Leaks | -0.289 |
ILY | -0.286 |
Nib | -0.283 |
ャ | -0.281 |
Token | the |
Token ID | 262 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
angered | +0.913 |
genre | +0.828 |
adem | +0.759 |
bnb | +0.748 |
arios | +0.727 |
Neg logit contributions | |
illac | -0.763 |
Leaks | -0.728 |
ILY | -0.719 |
Nib | -0.711 |
ャ | -0.710 |
Token | production |
Token ID | 3227 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
angered | +0.056 |
genre | +0.051 |
adem | +0.047 |
bnb | +0.046 |
arios | +0.046 |
Neg logit contributions | |
illac | -0.039 |
Leaks | -0.038 |
ILY | -0.037 |
Nib | -0.037 |
CLASS | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
angered | +0.022 |
genre | +0.020 |
adem | +0.018 |
bnb | +0.018 |
arios | +0.017 |
Neg logit contributions | |
illac | -0.018 |
Leaks | -0.018 |
ILY | -0.017 |
Nib | -0.017 |
CLASS | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
angered | +1.105 |
genre | +1.003 |
adem | +0.892 |
bnb | +0.879 |
arios | +0.868 |
Neg logit contributions | |
illac | -1.026 |
Leaks | -0.979 |
ILY | -0.968 |
Nib | -0.958 |
CLASS | -0.956 |
Token | Quest |
Token ID | 12166 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
angered | +0.859 |
genre | +0.790 |
adem | +0.710 |
bnb | +0.695 |
arios | +0.689 |
Neg logit contributions | |
illac | -0.654 |
Nib | -0.614 |
Leaks | -0.611 |
CLASS | -0.610 |
ILY | -0.606 |
Token | Diagn |
Token ID | 31549 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
angered | +0.753 |
genre | +0.675 |
adem | +0.603 |
arios | +0.592 |
bnb | +0.591 |
Neg logit contributions | |
illac | -0.763 |
ILY | -0.736 |
Leaks | -0.730 |
Nib | -0.725 |
ャ | -0.724 |
Token | ostics |
Token ID | 34558 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
illac | +0.943 |
Leaks | +0.895 |
ILY | +0.876 |
Nib | +0.862 |
CLASS | +0.855 |
Neg logit contributions | |
angered | -1.900 |
genre | -1.771 |
adem | -1.625 |
bnb | -1.612 |
arios | -1.593 |
Token | , |
Token ID | 11 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
illac | +0.481 |
Leaks | +0.464 |
ILY | +0.458 |
Nib | +0.451 |
CLASS | +0.448 |
Neg logit contributions | |
angered | -0.555 |
genre | -0.507 |
adem | -0.455 |
bnb | -0.449 |
arios | -0.443 |
Token | based |
Token ID | 1912 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
angered | +0.144 |
genre | +0.132 |
adem | +0.120 |
bnb | +0.118 |
arios | +0.117 |
Neg logit contributions | |
illac | -0.108 |
Leaks | -0.104 |
ILY | -0.102 |
Nib | -0.100 |
CLASS | -0.100 |
Token | in |
Token ID | 287 |
Feature activation | +9.94e-02 |
Pos logit contributions | |
angered | +0.179 |
genre | +0.162 |
adem | +0.145 |
bnb | +0.142 |
arios | +0.141 |
Neg logit contributions | |
illac | -0.179 |
Leaks | -0.176 |
ILY | -0.174 |
Nib | -0.170 |
CLASS | -0.170 |
Token | New |
Token ID | 968 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
angered | +0.267 |
genre | +0.241 |
adem | +0.213 |
bnb | +0.210 |
arios | +0.207 |
Neg logit contributions | |
illac | -0.292 |
Leaks | -0.283 |
ILY | -0.280 |
Nib | -0.275 |
CLASS | -0.275 |
Token | Jersey |
Token ID | 8221 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
angered | +0.095 |
genre | +0.086 |
adem | +0.075 |
bnb | +0.074 |
arios | +0.072 |
Neg logit contributions | |
illac | -0.117 |
Leaks | -0.114 |
ILY | -0.113 |
Nib | -0.111 |
CLASS | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
angered | +0.365 |
genre | +0.331 |
adem | +0.293 |
bnb | +0.289 |
arios | +0.286 |
Neg logit contributions | |
illac | -0.380 |
Leaks | -0.370 |
ILY | -0.367 |
Nib | -0.363 |
CLASS | -0.360 |
Token | , |
Token ID | 11 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
angered | +1.638 |
genre | +1.487 |
adem | +1.313 |
bnb | +1.298 |
arios | +1.282 |
Neg logit contributions | |
illac | -1.754 |
Leaks | -1.705 |
ILY | -1.668 |
Nib | -1.657 |
CLASS | -1.654 |
Token | was |
Token ID | 373 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
illac | +0.197 |
Leaks | +0.189 |
ILY | +0.187 |
Nib | +0.184 |
CLASS | +0.183 |
Neg logit contributions | |
angered | -0.235 |
genre | -0.215 |
adem | -0.193 |
bnb | -0.190 |
arios | -0.188 |
Token | trained |
Token ID | 8776 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
angered | +1.419 |
genre | +1.289 |
adem | +1.152 |
bnb | +1.131 |
arios | +1.119 |
Neg logit contributions | |
illac | -1.369 |
Leaks | -1.322 |
ILY | -1.304 |
Nib | -1.288 |
CLASS | -1.278 |
Token | by |
Token ID | 416 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
angered | +1.129 |
genre | +1.029 |
adem | +0.929 |
bnb | +0.917 |
arios | +0.915 |
Neg logit contributions | |
illac | -0.935 |
Leaks | -0.907 |
ILY | -0.892 |
Nib | -0.879 |
CLASS | -0.872 |
Token | the |
Token ID | 262 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
angered | +0.481 |
genre | +0.439 |
adem | +0.395 |
bnb | +0.387 |
arios | +0.386 |
Neg logit contributions | |
illac | -0.418 |
Leaks | -0.399 |
ILY | -0.394 |
ャ | -0.390 |
CLASS | -0.389 |
Token | United |
Token ID | 1578 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
illac | +0.530 |
Leaks | +0.512 |
ILY | +0.505 |
Nib | +0.500 |
CLASS | +0.496 |
Neg logit contributions | |
angered | -0.583 |
genre | -0.533 |
adem | -0.475 |
bnb | -0.471 |
arios | -0.463 |
Token | States |
Token ID | 1829 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
angered | +0.710 |
genre | +0.649 |
adem | +0.592 |
arios | +0.577 |
bnb | +0.573 |
Neg logit contributions | |
illac | -0.534 |
Leaks | -0.500 |
ILY | -0.496 |
ャ | -0.496 |
CLASS | -0.487 |
Token | , |
Token ID | 11 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
illac | +0.117 |
Leaks | +0.112 |
ILY | +0.111 |
Nib | +0.109 |
ャ | +0.109 |
Neg logit contributions | |
angered | -0.153 |
genre | -0.140 |
adem | -0.127 |
bnb | -0.125 |
arios | -0.124 |
Token | a |
Token ID | 257 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
illac | +0.181 |
Leaks | +0.173 |
ILY | +0.172 |
Nib | +0.169 |
CLASS | +0.168 |
Neg logit contributions | |
angered | -0.214 |
genre | -0.196 |
adem | -0.176 |
bnb | -0.173 |
arios | -0.171 |
Token | senior |
Token ID | 4664 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
angered | +0.355 |
genre | +0.325 |
adem | +0.293 |
bnb | +0.288 |
arios | +0.285 |
Neg logit contributions | |
illac | -0.291 |
Leaks | -0.277 |
ILY | -0.274 |
Nib | -0.270 |
CLASS | -0.269 |
Token | U |
Token ID | 471 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
illac | +0.536 |
Leaks | +0.518 |
ILY | +0.509 |
Nib | +0.505 |
CLASS | +0.501 |
Neg logit contributions | |
angered | -0.651 |
genre | -0.596 |
adem | -0.535 |
bnb | -0.531 |
arios | -0.522 |
Token | the |
Token ID | 262 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
illac | +0.409 |
Leaks | +0.392 |
ILY | +0.386 |
Nib | +0.380 |
CLASS | +0.377 |
Neg logit contributions | |
angered | -0.537 |
genre | -0.495 |
adem | -0.447 |
bnb | -0.441 |
arios | -0.437 |
Token | year |
Token ID | 614 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
angered | +0.443 |
genre | +0.404 |
adem | +0.363 |
arios | +0.355 |
bnb | +0.352 |
Neg logit contributions | |
illac | -0.402 |
Leaks | -0.389 |
ILY | -0.382 |
Nib | -0.376 |
ャ | -0.375 |
Token | . |
Token ID | 13 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
angered | +1.219 |
genre | +1.105 |
adem | +0.988 |
bnb | +0.972 |
arios | +0.964 |
Neg logit contributions | |
illac | -1.231 |
Leaks | -1.208 |
ILY | -1.167 |
Nib | -1.161 |
ャ | -1.148 |
Token |
|
Token ID | 198 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
illac | +0.183 |
Leaks | +0.176 |
ILY | +0.174 |
Nib | +0.171 |
CLASS | +0.170 |
Neg logit contributions | |
angered | -0.203 |
genre | -0.185 |
adem | -0.165 |
bnb | -0.163 |
arios | -0.161 |
Token |
|
Token ID | 198 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
angered | +0.610 |
genre | +0.555 |
adem | +0.496 |
bnb | +0.489 |
arios | +0.483 |
Neg logit contributions | |
illac | -0.552 |
Leaks | -0.529 |
ILY | -0.522 |
Nib | -0.517 |
CLASS | -0.514 |
Token | This |
Token ID | 1212 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
angered | +0.184 |
genre | +0.169 |
adem | +0.152 |
bnb | +0.149 |
arios | +0.148 |
Neg logit contributions | |
illac | -0.141 |
Leaks | -0.133 |
Nib | -0.132 |
ILY | -0.132 |
CLASS | -0.131 |
Token | 3 |
Token ID | 513 |
Feature activation | -8.72e-02 |
Pos logit contributions | |
illac | +0.037 |
Leaks | +0.035 |
ILY | +0.035 |
Nib | +0.034 |
CLASS | +0.034 |
Neg logit contributions | |
angered | -0.044 |
genre | -0.040 |
adem | -0.036 |
bnb | -0.036 |
arios | -0.035 |
Token | - |
Token ID | 12 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
illac | +0.223 |
Leaks | +0.215 |
ILY | +0.211 |
Nib | +0.209 |
CLASS | +0.206 |
Neg logit contributions | |
angered | -0.269 |
genre | -0.247 |
adem | -0.222 |
bnb | -0.219 |
arios | -0.216 |
Token | 3 |
Token ID | 18 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
angered | +0.896 |
genre | +0.829 |
adem | +0.742 |
bnb | +0.729 |
arios | +0.718 |
Neg logit contributions | |
illac | -0.765 |
Leaks | -0.732 |
ILY | -0.725 |
Nib | -0.721 |
ャ | -0.713 |
Token | - |
Token ID | 12 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
angered | +0.837 |
genre | +0.758 |
adem | +0.675 |
bnb | +0.665 |
arios | +0.658 |
Neg logit contributions | |
illac | -0.859 |
Leaks | -0.827 |
ILY | -0.818 |
Nib | -0.808 |
CLASS | -0.800 |
Token | 5 |
Token ID | 20 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
angered | +1.138 |
genre | +1.056 |
adem | +0.945 |
bnb | +0.934 |
arios | +0.922 |
Neg logit contributions | |
illac | -0.938 |
Leaks | -0.889 |
Nib | -0.886 |
ILY | -0.882 |
ャ | -0.876 |
Token | omm |
Token ID | 2002 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
angered | +1.014 |
genre | +0.919 |
adem | +0.834 |
arios | +0.815 |
bnb | +0.815 |
Neg logit contributions | |
illac | -0.818 |
Leaks | -0.797 |
ILY | -0.773 |
Nib | -0.768 |
ャ | -0.764 |
Token | ers |
Token ID | 364 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
angered | +0.329 |
genre | +0.298 |
adem | +0.264 |
arios | +0.258 |
bnb | +0.252 |
Neg logit contributions | |
illac | -0.398 |
Leaks | -0.382 |
ILY | -0.379 |
Nib | -0.373 |
ャ | -0.373 |
Token | II |
Token ID | 2873 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
illac | +0.384 |
Leaks | +0.369 |
ILY | +0.363 |
Nib | +0.359 |
CLASS | +0.356 |
Neg logit contributions | |
angered | -0.511 |
genre | -0.470 |
adem | -0.425 |
bnb | -0.421 |
arios | -0.415 |
Token | ) |
Token ID | 8 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
illac | +0.121 |
Leaks | +0.117 |
ILY | +0.115 |
Nib | +0.114 |
CLASS | +0.113 |
Neg logit contributions | |
angered | -0.150 |
genre | -0.137 |
adem | -0.124 |
bnb | -0.122 |
arios | -0.120 |
Token | Ivanka |
Token ID | 31002 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
illac | +0.900 |
Leaks | +0.870 |
ILY | +0.859 |
Nib | +0.849 |
CLASS | +0.845 |
Neg logit contributions | |
angered | -0.858 |
genre | -0.777 |
adem | -0.688 |
bnb | -0.679 |
arios | -0.668 |
Token | Trump |
Token ID | 1301 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
angered | +0.771 |
genre | +0.688 |
adem | +0.609 |
bnb | +0.600 |
arios | +0.591 |
Neg logit contributions | |
illac | -0.855 |
Leaks | -0.812 |
ILY | -0.803 |
ャ | -0.797 |
Nib | -0.795 |
Token | A |
Token ID | 317 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
illac | +0.744 |
Leaks | +0.714 |
ILY | +0.705 |
Nib | +0.694 |
CLASS | +0.689 |
Neg logit contributions | |
angered | -0.904 |
genre | -0.827 |
adem | -0.745 |
bnb | -0.736 |
arios | -0.723 |
Token | wild |
Token ID | 4295 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
angered | +0.749 |
genre | +0.678 |
adem | +0.606 |
bnb | +0.597 |
arios | +0.588 |
Neg logit contributions | |
illac | -0.708 |
Leaks | -0.682 |
Nib | -0.667 |
ILY | -0.666 |
CLASS | -0.657 |
Token | card |
Token ID | 9517 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
illac | +0.447 |
Leaks | +0.432 |
ILY | +0.426 |
Nib | +0.422 |
CLASS | +0.419 |
Neg logit contributions | |
angered | -0.453 |
genre | -0.411 |
adem | -0.366 |
bnb | -0.361 |
arios | -0.355 |
Token | choice |
Token ID | 3572 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
angered | +3.012 |
genre | +2.727 |
adem | +2.431 |
bnb | +2.412 |
arios | +2.363 |
Neg logit contributions | |
illac | -2.863 |
Leaks | -2.747 |
ILY | -2.691 |
ャ | -2.663 |
Nib | -2.656 |
Token | for |
Token ID | 329 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
illac | +0.235 |
Leaks | +0.227 |
ILY | +0.223 |
Nib | +0.221 |
CLASS | +0.220 |
Neg logit contributions | |
angered | -0.280 |
genre | -0.257 |
adem | -0.230 |
bnb | -0.228 |
arios | -0.224 |
Token | but |
Token ID | 475 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
angered | +0.625 |
genre | +0.567 |
adem | +0.502 |
bnb | +0.496 |
arios | +0.488 |
Neg logit contributions | |
illac | -0.636 |
Leaks | -0.615 |
ILY | -0.606 |
Nib | -0.600 |
CLASS | -0.596 |
Token | they |
Token ID | 484 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
angered | +0.589 |
genre | +0.534 |
adem | +0.475 |
bnb | +0.469 |
arios | +0.461 |
Neg logit contributions | |
illac | -0.583 |
Leaks | -0.564 |
ILY | -0.555 |
Nib | -0.549 |
CLASS | -0.546 |
Token | were |
Token ID | 547 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
angered | +0.372 |
genre | +0.337 |
adem | +0.303 |
bnb | +0.301 |
arios | +0.295 |
Neg logit contributions | |
illac | -0.305 |
Leaks | -0.296 |
ILY | -0.289 |
Nib | -0.287 |
CLASS | -0.284 |
Token | usually |
Token ID | 3221 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
illac | +0.236 |
Leaks | +0.228 |
ILY | +0.225 |
Nib | +0.222 |
CLASS | +0.221 |
Neg logit contributions | |
angered | -0.290 |
genre | -0.266 |
adem | -0.240 |
bnb | -0.237 |
arios | -0.234 |
Token | too |
Token ID | 1165 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
angered | +0.069 |
genre | +0.063 |
adem | +0.057 |
bnb | +0.056 |
arios | +0.055 |
Neg logit contributions | |
illac | -0.064 |
Leaks | -0.061 |
ILY | -0.061 |
Nib | -0.060 |
CLASS | -0.060 |
Token | stunned |
Token ID | 19987 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
angered | +0.515 |
genre | +0.466 |
adem | +0.415 |
bnb | +0.410 |
arios | +0.404 |
Neg logit contributions | |
illac | -0.504 |
Leaks | -0.487 |
ILY | -0.480 |
Nib | -0.473 |
CLASS | -0.470 |
Token | to |
Token ID | 284 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
illac | +0.057 |
Leaks | +0.055 |
ILY | +0.054 |
Nib | +0.053 |
CLASS | +0.053 |
Neg logit contributions | |
angered | -0.077 |
genre | -0.071 |
adem | -0.064 |
bnb | -0.064 |
arios | -0.063 |
Token | realize |
Token ID | 6537 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
angered | +0.708 |
genre | +0.649 |
adem | +0.588 |
bnb | +0.581 |
arios | +0.574 |
Neg logit contributions | |
illac | -0.526 |
Leaks | -0.507 |
ILY | -0.497 |
Nib | -0.490 |
CLASS | -0.486 |
Token | what |
Token ID | 644 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
angered | +0.792 |
genre | +0.716 |
adem | +0.637 |
bnb | +0.629 |
arios | +0.619 |
Neg logit contributions | |
illac | -0.785 |
Leaks | -0.758 |
ILY | -0.744 |
Nib | -0.735 |
CLASS | -0.732 |
Token | had |
Token ID | 550 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
illac | +0.756 |
Leaks | +0.732 |
ILY | +0.724 |
Nib | +0.716 |
CLASS | +0.711 |
Neg logit contributions | |
angered | -0.732 |
genre | -0.665 |
adem | -0.590 |
bnb | -0.582 |
arios | -0.574 |
Token | happened |
Token ID | 3022 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
illac | +0.574 |
Leaks | +0.552 |
ILY | +0.542 |
Nib | +0.532 |
CLASS | +0.531 |
Neg logit contributions | |
angered | -0.718 |
genre | -0.656 |
adem | -0.590 |
bnb | -0.585 |
arios | -0.578 |
Token | . |
Token ID | 13 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
illac | +0.246 |
Leaks | +0.238 |
ILY | +0.232 |
Nib | +0.230 |
CLASS | +0.229 |
Neg logit contributions | |
angered | -0.285 |
genre | -0.260 |
adem | -0.234 |
bnb | -0.232 |
arios | -0.228 |
Token | In |
Token ID | 554 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
illac | +0.211 |
Leaks | +0.204 |
ILY | +0.201 |
Nib | +0.199 |
CLASS | +0.198 |
Neg logit contributions | |
angered | -0.256 |
genre | -0.235 |
adem | -0.211 |
bnb | -0.209 |
arios | -0.205 |
Token | addition |
Token ID | 3090 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
angered | +0.413 |
genre | +0.377 |
adem | +0.337 |
bnb | +0.333 |
arios | +0.328 |
Neg logit contributions | |
illac | -0.370 |
Leaks | -0.357 |
ILY | -0.352 |
Nib | -0.349 |
CLASS | -0.346 |
Token | , |
Token ID | 11 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
illac | +1.797 |
Leaks | +1.726 |
ILY | +1.710 |
Nib | +1.688 |
CLASS | +1.678 |
Neg logit contributions | |
angered | -1.986 |
genre | -1.813 |
adem | -1.620 |
bnb | -1.603 |
arios | -1.572 |
Token | they |
Token ID | 484 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
angered | +0.213 |
genre | +0.195 |
adem | +0.176 |
bnb | +0.174 |
arios | +0.171 |
Neg logit contributions | |
illac | -0.171 |
Leaks | -0.165 |
ILY | -0.162 |
Nib | -0.161 |
CLASS | -0.159 |
Token | would |
Token ID | 561 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
illac | +0.905 |
Leaks | +0.874 |
ILY | +0.865 |
Nib | +0.857 |
CLASS | +0.851 |
Neg logit contributions | |
angered | -0.867 |
genre | -0.788 |
adem | -0.696 |
bnb | -0.688 |
arios | -0.676 |
Token | be |
Token ID | 307 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
illac | +0.868 |
Leaks | +0.837 |
ILY | +0.826 |
Nib | +0.817 |
CLASS | +0.810 |
Neg logit contributions | |
angered | -1.096 |
genre | -1.009 |
adem | -0.907 |
bnb | -0.899 |
arios | -0.881 |
Token | required |
Token ID | 2672 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
illac | +0.433 |
Leaks | +0.422 |
ILY | +0.417 |
Nib | +0.414 |
CLASS | +0.413 |
Neg logit contributions | |
angered | -0.313 |
genre | -0.280 |
adem | -0.240 |
bnb | -0.238 |
arios | -0.231 |
Token | to |
Token ID | 284 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
illac | +0.643 |
Leaks | +0.615 |
ILY | +0.601 |
Nib | +0.593 |
CLASS | +0.588 |
Neg logit contributions | |
angered | -1.111 |
genre | -1.031 |
adem | -0.942 |
bnb | -0.933 |
arios | -0.922 |
Token | undergo |
Token ID | 17777 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
illac | +0.571 |
Leaks | +0.550 |
ILY | +0.542 |
Nib | +0.536 |
CLASS | +0.532 |
Neg logit contributions | |
angered | -0.721 |
genre | -0.662 |
adem | -0.595 |
bnb | -0.589 |
arios | -0.580 |
Token | five |
Token ID | 1936 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
illac | +1.077 |
Leaks | +1.036 |
ILY | +1.023 |
Nib | +1.010 |
CLASS | +1.005 |
Neg logit contributions | |
angered | -1.338 |
genre | -1.228 |
adem | -1.103 |
bnb | -1.092 |
arios | -1.076 |
Token | is |
Token ID | 318 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
angered | +0.101 |
genre | +0.093 |
adem | +0.083 |
bnb | +0.083 |
arios | +0.082 |
Neg logit contributions | |
illac | -0.081 |
Leaks | -0.078 |
ILY | -0.077 |
Nib | -0.075 |
ャ | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
illac | +0.641 |
Leaks | +0.617 |
ILY | +0.608 |
Nib | +0.601 |
CLASS | +0.596 |
Neg logit contributions | |
angered | -0.785 |
genre | -0.719 |
adem | -0.647 |
bnb | -0.639 |
arios | -0.631 |
Token | construct |
Token ID | 5678 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
illac | +1.020 |
Leaks | +0.987 |
ILY | +0.976 |
Nib | +0.967 |
CLASS | +0.967 |
Neg logit contributions | |
angered | -1.053 |
genre | -0.958 |
adem | -0.852 |
bnb | -0.840 |
arios | -0.826 |
Token | that |
Token ID | 326 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
illac | +1.252 |
Leaks | +1.208 |
ILY | +1.196 |
Nib | +1.181 |
CLASS | +1.179 |
Neg logit contributions | |
angered | -1.501 |
genre | -1.375 |
adem | -1.237 |
bnb | -1.217 |
arios | -1.203 |
Token | we |
Token ID | 356 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
angered | +0.284 |
genre | +0.261 |
adem | +0.235 |
bnb | +0.233 |
arios | +0.230 |
Neg logit contributions | |
illac | -0.224 |
Leaks | -0.215 |
ILY | -0.213 |
Nib | -0.209 |
ャ | -0.207 |
Token | use |
Token ID | 779 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
angered | +0.118 |
genre | +0.108 |
adem | +0.099 |
bnb | +0.097 |
arios | +0.096 |
Neg logit contributions | |
illac | -0.082 |
Leaks | -0.078 |
ILY | -0.077 |
Nib | -0.076 |
CLASS | -0.075 |
Token | to |
Token ID | 284 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
illac | +0.474 |
Leaks | +0.457 |
ILY | +0.446 |
Nib | +0.442 |
CLASS | +0.437 |
Neg logit contributions | |
angered | -0.678 |
genre | -0.626 |
adem | -0.567 |
bnb | -0.564 |
arios | -0.556 |
Token | remove |
Token ID | 4781 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
illac | +0.518 |
Leaks | +0.498 |
ILY | +0.491 |
Nib | +0.483 |
CLASS | +0.480 |
Neg logit contributions | |
angered | -0.637 |
genre | -0.585 |
adem | -0.526 |
bnb | -0.520 |
arios | -0.516 |
Token | the |
Token ID | 262 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
illac | +0.721 |
Leaks | +0.693 |
ILY | +0.685 |
Nib | +0.675 |
CLASS | +0.669 |
Neg logit contributions | |
angered | -0.854 |
genre | -0.781 |
adem | -0.702 |
bnb | -0.693 |
arios | -0.684 |
Token | stuff |
Token ID | 3404 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
angered | +0.193 |
genre | +0.175 |
adem | +0.157 |
bnb | +0.155 |
arios | +0.153 |
Neg logit contributions | |
illac | -0.178 |
Leaks | -0.171 |
ILY | -0.169 |
Nib | -0.166 |
ャ | -0.165 |
Token | we |
Token ID | 356 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
illac | +0.075 |
Leaks | +0.072 |
ILY | +0.072 |
Nib | +0.070 |
CLASS | +0.070 |
Neg logit contributions | |
angered | -0.080 |
genre | -0.073 |
adem | -0.065 |
bnb | -0.064 |
arios | -0.063 |
Token | SS |
Token ID | 6723 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
illac | +1.127 |
Leaks | +1.078 |
ILY | +1.069 |
Nib | +1.066 |
CLASS | +1.061 |
Neg logit contributions | |
angered | -1.748 |
genre | -1.622 |
adem | -1.464 |
bnb | -1.456 |
arios | -1.430 |
Token | N |
Token ID | 45 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
illac | +0.094 |
Leaks | +0.090 |
ILY | +0.088 |
ャ | +0.086 |
Nib | +0.086 |
Neg logit contributions | |
angered | -0.118 |
genre | -0.109 |
adem | -0.099 |
bnb | -0.098 |
arios | -0.096 |
Token | coming |
Token ID | 2406 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
angered | +0.275 |
genre | +0.252 |
adem | +0.228 |
bnb | +0.224 |
arios | +0.222 |
Neg logit contributions | |
illac | -0.220 |
Leaks | -0.212 |
ILY | -0.208 |
Nib | -0.205 |
CLASS | -0.203 |
Token | on |
Token ID | 319 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
illac | +0.436 |
Leaks | +0.421 |
ILY | +0.415 |
Nib | +0.410 |
CLASS | +0.407 |
Neg logit contributions | |
angered | -0.477 |
genre | -0.435 |
adem | -0.389 |
bnb | -0.384 |
arios | -0.378 |
Token | line |
Token ID | 1627 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
illac | +0.570 |
Leaks | +0.552 |
ILY | +0.545 |
Nib | +0.539 |
CLASS | +0.536 |
Neg logit contributions | |
angered | -0.542 |
genre | -0.491 |
adem | -0.435 |
bnb | -0.429 |
arios | -0.421 |
Token | from |
Token ID | 422 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
angered | +0.655 |
genre | +0.597 |
adem | +0.534 |
bnb | +0.527 |
arios | +0.521 |
Neg logit contributions | |
illac | -0.603 |
Leaks | -0.583 |
ILY | -0.574 |
Nib | -0.566 |
CLASS | -0.563 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
illac | +0.575 |
Leaks | +0.555 |
ILY | +0.547 |
Nib | +0.543 |
CLASS | +0.540 |
Neg logit contributions | |
angered | -0.602 |
genre | -0.548 |
adem | -0.488 |
bnb | -0.483 |
arios | -0.474 |
Token | . |
Token ID | 13 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
illac | +0.261 |
Leaks | +0.252 |
ILY | +0.248 |
Nib | +0.245 |
CLASS | +0.243 |
Neg logit contributions | |
angered | -0.295 |
genre | -0.269 |
adem | -0.241 |
bnb | -0.239 |
arios | -0.235 |
Token | The |
Token ID | 383 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
illac | +0.605 |
Leaks | +0.583 |
ILY | +0.574 |
Nib | +0.569 |
CLASS | +0.565 |
Neg logit contributions | |
angered | -0.719 |
genre | -0.660 |
adem | -0.592 |
bnb | -0.586 |
arios | -0.578 |
Token | UK |
Token ID | 3482 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
illac | +0.297 |
Leaks | +0.287 |
ILY | +0.283 |
Nib | +0.280 |
CLASS | +0.279 |
Neg logit contributions | |
angered | -0.335 |
genre | -0.306 |
adem | -0.274 |
bnb | -0.271 |
arios | -0.267 |
Token | has |
Token ID | 468 |
Feature activation | +9.06e-02 |
Pos logit contributions | |
illac | +0.094 |
Leaks | +0.090 |
ILY | +0.089 |
Nib | +0.088 |
CLASS | +0.087 |
Neg logit contributions | |
angered | -0.124 |
genre | -0.114 |
adem | -0.103 |
bnb | -0.102 |
arios | -0.100 |
Token | reduces |
Token ID | 12850 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
illac | +0.819 |
Leaks | +0.787 |
ILY | +0.775 |
Nib | +0.765 |
CLASS | +0.759 |
Neg logit contributions | |
angered | -1.118 |
genre | -1.029 |
adem | -0.931 |
bnb | -0.921 |
arios | -0.909 |
Token | power |
Token ID | 1176 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
illac | +0.665 |
Leaks | +0.639 |
ILY | +0.629 |
Nib | +0.621 |
CLASS | +0.616 |
Neg logit contributions | |
angered | -0.878 |
genre | -0.806 |
adem | -0.729 |
bnb | -0.721 |
arios | -0.712 |
Token | supply |
Token ID | 5127 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
illac | +0.629 |
Leaks | +0.613 |
ILY | +0.607 |
Nib | +0.602 |
CLASS | +0.599 |
Neg logit contributions | |
angered | -0.358 |
genre | -0.313 |
adem | -0.263 |
bnb | -0.257 |
arios | -0.250 |
Token | noise |
Token ID | 7838 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
illac | +0.892 |
Leaks | +0.863 |
ILY | +0.853 |
Nib | +0.842 |
CLASS | +0.837 |
Neg logit contributions | |
angered | -1.003 |
genre | -0.916 |
adem | -0.820 |
bnb | -0.810 |
arios | -0.795 |
Token | as |
Token ID | 355 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
illac | +1.062 |
Leaks | +1.027 |
ILY | +1.015 |
Nib | +1.001 |
CLASS | +0.995 |
Neg logit contributions | |
angered | -1.188 |
genre | -1.085 |
adem | -0.971 |
bnb | -0.959 |
arios | -0.942 |
Token | well |
Token ID | 880 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
illac | +1.156 |
Leaks | +1.114 |
ILY | +1.097 |
Nib | +1.084 |
CLASS | +1.074 |
Neg logit contributions | |
angered | -1.363 |
genre | -1.245 |
adem | -1.118 |
bnb | -1.105 |
arios | -1.092 |
Token | as |
Token ID | 355 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
illac | +2.351 |
Leaks | +2.254 |
ILY | +2.229 |
Nib | +2.190 |
CLASS | +2.186 |
Neg logit contributions | |
angered | -3.436 |
genre | -3.165 |
adem | -2.875 |
bnb | -2.842 |
arios | -2.807 |
Token | increases |
Token ID | 5732 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
illac | +1.079 |
Leaks | +1.039 |
ILY | +1.025 |
Nib | +1.012 |
CLASS | +1.006 |
Neg logit contributions | |
angered | -1.281 |
genre | -1.173 |
adem | -1.054 |
bnb | -1.041 |
arios | -1.027 |
Token | overcl |
Token ID | 40397 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
angered | +0.384 |
genre | +0.351 |
adem | +0.314 |
bnb | +0.311 |
arios | +0.307 |
Neg logit contributions | |
illac | -0.343 |
Leaks | -0.329 |
ILY | -0.324 |
Nib | -0.321 |
CLASS | -0.318 |
Token | ocking |
Token ID | 8629 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
angered | +0.163 |
genre | +0.142 |
adem | +0.118 |
bnb | +0.114 |
arios | +0.112 |
Neg logit contributions | |
illac | -0.312 |
Leaks | -0.303 |
ILY | -0.301 |
Nib | -0.299 |
CLASS | -0.298 |
Token | stability |
Token ID | 10159 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
angered | +0.071 |
genre | +0.064 |
adem | +0.056 |
bnb | +0.056 |
arios | +0.055 |
Neg logit contributions | |
illac | -0.082 |
Leaks | -0.080 |
ILY | -0.079 |
Nib | -0.078 |
CLASS | -0.077 |
Token | Hide |
Token ID | 10415 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
illac | +0.489 |
Leaks | +0.464 |
ILY | +0.457 |
Nib | +0.443 |
ャ | +0.443 |
Neg logit contributions | |
angered | -0.856 |
genre | -0.791 |
adem | -0.723 |
bnb | -0.715 |
arios | -0.709 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
angered | +0.873 |
genre | +0.788 |
adem | +0.694 |
bnb | +0.685 |
arios | +0.673 |
Neg logit contributions | |
illac | -0.980 |
Leaks | -0.949 |
ILY | -0.938 |
Nib | -0.928 |
CLASS | -0.923 |
Token | 13 |
Token ID | 1511 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
illac | +0.813 |
Leaks | +0.806 |
Nib | +0.791 |
ILY | +0.783 |
CLASS | +0.768 |
Neg logit contributions | |
angered | -1.230 |
genre | -1.152 |
adem | -1.051 |
bnb | -1.045 |
arios | -1.005 |
Token | of |
Token ID | 286 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
angered | +0.232 |
genre | +0.211 |
adem | +0.187 |
bnb | +0.185 |
arios | +0.182 |
Neg logit contributions | |
illac | -0.245 |
Leaks | -0.238 |
ILY | -0.236 |
Nib | -0.233 |
CLASS | -0.231 |
Token | 15 |
Token ID | 1315 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
illac | +1.073 |
Leaks | +1.043 |
ILY | +1.028 |
CLASS | +1.026 |
Nib | +1.017 |
Neg logit contributions | |
angered | -1.803 |
genre | -1.689 |
adem | -1.545 |
bnb | -1.528 |
arios | -1.503 |
Token | Photos |
Token ID | 9434 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
illac | +0.847 |
Leaks | +0.816 |
ILY | +0.798 |
Nib | +0.794 |
CLASS | +0.787 |
Neg logit contributions | |
angered | -1.501 |
genre | -1.403 |
adem | -1.286 |
bnb | -1.269 |
arios | -1.251 |
Token | : |
Token ID | 25 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
Leaks | +2.096 |
illac | +2.092 |
ILY | +2.061 |
Nib | +2.019 |
Men | +2.004 |
Neg logit contributions | |
angered | -3.058 |
genre | -2.854 |
adem | -2.622 |
bnb | -2.606 |
arios | -2.540 |
Token | Carly |
Token ID | 35982 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
angered | +0.951 |
genre | +0.880 |
adem | +0.815 |
bnb | +0.806 |
arios | +0.800 |
Neg logit contributions | |
illac | -0.427 |
Leaks | -0.397 |
ILY | -0.387 |
ャ | -0.375 |
CLASS | -0.374 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
illac | +0.900 |
Leaks | +0.871 |
ILY | +0.857 |
Nib | +0.849 |
CLASS | +0.838 |
Neg logit contributions | |
angered | -1.172 |
genre | -1.078 |
adem | -0.972 |
bnb | -0.963 |
arios | -0.948 |
Token | 's |
Token ID | 338 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
illac | +0.103 |
Leaks | +0.099 |
ILY | +0.097 |
Nib | +0.096 |
CLASS | +0.095 |
Neg logit contributions | |
angered | -0.152 |
genre | -0.140 |
adem | -0.127 |
bnb | -0.125 |
arios | -0.124 |
Token | political |
Token ID | 1964 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
illac | +1.526 |
Leaks | +1.483 |
ILY | +1.470 |
Nib | +1.445 |
CLASS | +1.440 |
Neg logit contributions | |
angered | -1.939 |
genre | -1.769 |
bnb | -1.595 |
adem | -1.590 |
arios | -1.563 |
Token | tied |
Token ID | 8165 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
angered | +0.881 |
genre | +0.809 |
adem | +0.724 |
bnb | +0.717 |
arios | +0.711 |
Neg logit contributions | |
illac | -0.747 |
Leaks | -0.718 |
ILY | -0.705 |
Nib | -0.692 |
CLASS | -0.687 |
Token | to |
Token ID | 284 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
illac | +1.042 |
Leaks | +0.996 |
ILY | +0.974 |
Nib | +0.962 |
CLASS | +0.955 |
Neg logit contributions | |
angered | -1.783 |
genre | -1.654 |
adem | -1.512 |
bnb | -1.495 |
arios | -1.480 |
Token | the |
Token ID | 262 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
angered | +0.656 |
genre | +0.596 |
adem | +0.531 |
bnb | +0.523 |
arios | +0.517 |
Neg logit contributions | |
illac | -0.640 |
Leaks | -0.614 |
ILY | -0.604 |
Nib | -0.595 |
CLASS | -0.593 |
Token | " |
Token ID | 366 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
angered | +0.189 |
genre | +0.172 |
adem | +0.153 |
bnb | +0.151 |
arios | +0.149 |
Neg logit contributions | |
illac | -0.181 |
Leaks | -0.175 |
ILY | -0.173 |
Nib | -0.171 |
CLASS | -0.170 |
Token | United |
Token ID | 17013 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
illac | +0.447 |
Leaks | +0.429 |
ILY | +0.424 |
Nib | +0.420 |
CLASS | +0.417 |
Neg logit contributions | |
angered | -0.498 |
genre | -0.455 |
adem | -0.406 |
bnb | -0.401 |
arios | -0.395 |
Token | Nations |
Token ID | 7973 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
angered | +0.438 |
genre | +0.400 |
adem | +0.364 |
bnb | +0.359 |
arios | +0.358 |
Neg logit contributions | |
illac | -0.313 |
Leaks | -0.293 |
ILY | -0.292 |
ャ | -0.284 |
Nib | -0.282 |
Token | Millennium |
Token ID | 26139 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
illac | +2.501 |
Leaks | +2.447 |
Nib | +2.396 |
ILY | +2.392 |
CLASS | +2.378 |
Neg logit contributions | |
angered | -2.614 |
genre | -2.395 |
adem | -2.140 |
bnb | -2.111 |
arios | -2.061 |
Token | Development |
Token ID | 7712 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
illac | +0.305 |
Leaks | +0.295 |
ILY | +0.289 |
Nib | +0.286 |
CLASS | +0.284 |
Neg logit contributions | |
angered | -0.442 |
genre | -0.409 |
adem | -0.370 |
bnb | -0.367 |
arios | -0.362 |
Token | Goals |
Token ID | 28510 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
illac | +0.651 |
Leaks | +0.627 |
ILY | +0.611 |
Nib | +0.606 |
CLASS | +0.600 |
Neg logit contributions | |
angered | -1.202 |
genre | -1.122 |
adem | -1.024 |
bnb | -1.016 |
arios | -1.004 |
Token | ." |
Token ID | 526 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
illac | +0.856 |
Leaks | +0.828 |
ILY | +0.818 |
Nib | +0.809 |
CLASS | +0.805 |
Neg logit contributions | |
angered | -0.843 |
genre | -0.766 |
adem | -0.679 |
bnb | -0.671 |
arios | -0.660 |
Token | Students |
Token ID | 14882 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
illac | +0.322 |
Leaks | +0.309 |
ILY | +0.305 |
Nib | +0.299 |
CLASS | +0.297 |
Neg logit contributions | |
angered | -0.405 |
genre | -0.371 |
adem | -0.334 |
bnb | -0.330 |
arios | -0.326 |
Token | understand |
Token ID | 1833 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
angered | +0.661 |
genre | +0.607 |
adem | +0.550 |
bnb | +0.543 |
arios | +0.535 |
Neg logit contributions | |
illac | -0.516 |
Leaks | -0.497 |
ILY | -0.484 |
Nib | -0.476 |
CLASS | -0.475 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
angered | +1.023 |
genre | +0.934 |
adem | +0.835 |
bnb | +0.823 |
arios | +0.813 |
Neg logit contributions | |
illac | -0.954 |
Leaks | -0.917 |
ILY | -0.899 |
Nib | -0.885 |
CLASS | -0.882 |
Token | execute |
Token ID | 12260 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
angered | +0.399 |
genre | +0.365 |
adem | +0.329 |
bnb | +0.323 |
arios | +0.319 |
Neg logit contributions | |
illac | -0.336 |
Leaks | -0.323 |
ILY | -0.318 |
Nib | -0.312 |
CLASS | -0.311 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-03 |
Pos logit contributions | |
angered | +0.392 |
genre | +0.358 |
adem | +0.320 |
bnb | +0.316 |
arios | +0.311 |
Neg logit contributions | |
illac | -0.360 |
Leaks | -0.347 |
ILY | -0.340 |
Nib | -0.336 |
CLASS | -0.334 |
Token | Mu |
Token ID | 8252 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
angered | +0.003 |
genre | +0.003 |
adem | +0.003 |
bnb | +0.003 |
arios | +0.003 |
Neg logit contributions | |
illac | -0.003 |
Leaks | -0.003 |
ILY | -0.003 |
Nib | -0.003 |
CLASS | -0.003 |
Token | ay |
Token ID | 323 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
illac | +1.213 |
Leaks | +1.171 |
ILY | +1.154 |
Nib | +1.143 |
CLASS | +1.135 |
Neg logit contributions | |
angered | -1.350 |
genre | -1.232 |
adem | -1.100 |
bnb | -1.088 |
arios | -1.072 |
Token | Thai |
Token ID | 18933 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
illac | +3.663 |
Leaks | +3.570 |
Nib | +3.547 |
CLASS | +3.530 |
ILY | +3.526 |
Neg logit contributions | |
angered | -1.898 |
genre | -1.623 |
adem | -1.330 |
bnb | -1.309 |
arios | -1.280 |
Token | I |
Token ID | 314 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
illac | +1.214 |
Leaks | +1.180 |
ILY | +1.163 |
Nib | +1.153 |
CLASS | +1.149 |
Neg logit contributions | |
angered | -1.204 |
genre | -1.088 |
adem | -0.965 |
bnb | -0.956 |
arios | -0.938 |
Token | have |
Token ID | 423 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
illac | +0.069 |
Leaks | +0.067 |
ILY | +0.066 |
Nib | +0.065 |
CLASS | +0.064 |
Neg logit contributions | |
angered | -0.091 |
genre | -0.084 |
adem | -0.076 |
bnb | -0.075 |
arios | -0.074 |
Token | been |
Token ID | 587 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
angered | +0.086 |
genre | +0.079 |
adem | +0.072 |
bnb | +0.071 |
arios | +0.071 |
Neg logit contributions | |
illac | -0.060 |
Leaks | -0.058 |
ILY | -0.056 |
Nib | -0.055 |
CLASS | -0.055 |
Token | training |
Token ID | 3047 |
Feature activation | +8.54e-02 |
Pos logit contributions | |
angered | +0.228 |
genre | +0.208 |
adem | +0.187 |
bnb | +0.184 |
arios | +0.181 |
Neg logit contributions | |
illac | -0.200 |
Leaks | -0.193 |
ILY | -0.189 |
Nib | -0.187 |
CLASS | -0.186 |
Token | H |
Token ID | 39 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
illac | +0.602 |
Leaks | +0.569 |
ILY | +0.565 |
Nib | +0.564 |
ャ | +0.556 |
Neg logit contributions | |
angered | -0.769 |
genre | -0.706 |
adem | -0.638 |
bnb | -0.633 |
arios | -0.627 |
Token | VM |
Token ID | 15996 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
illac | +0.232 |
Leaks | +0.218 |
Nib | +0.215 |
ILY | +0.214 |
ャ | +0.211 |
Neg logit contributions | |
angered | -0.371 |
genre | -0.344 |
adem | -0.316 |
bnb | -0.313 |
arios | -0.311 |
Token | ", |
Token ID | 1600 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
illac | +0.709 |
Leaks | +0.673 |
ILY | +0.669 |
Nib | +0.660 |
ャ | +0.654 |
Neg logit contributions | |
angered | -0.881 |
genre | -0.804 |
adem | -0.728 |
bnb | -0.721 |
arios | -0.713 |
Token | after |
Token ID | 706 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
angered | +0.461 |
genre | +0.417 |
adem | +0.370 |
bnb | +0.367 |
arios | +0.362 |
Neg logit contributions | |
illac | -0.466 |
Leaks | -0.451 |
ILY | -0.444 |
Nib | -0.436 |
ャ | -0.433 |
Token | the |
Token ID | 262 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
angered | +0.614 |
genre | +0.563 |
adem | +0.506 |
bnb | +0.503 |
arios | +0.496 |
Neg logit contributions | |
illac | -0.497 |
Leaks | -0.480 |
ILY | -0.472 |
Nib | -0.463 |
ャ | -0.461 |
Token | drivers |
Token ID | 6643 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
illac | +0.207 |
Leaks | +0.200 |
ILY | +0.197 |
Nib | +0.194 |
CLASS | +0.193 |
Neg logit contributions | |
angered | -0.234 |
genre | -0.213 |
adem | -0.191 |
bnb | -0.189 |
arios | -0.186 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e-03 |
Pos logit contributions | |
illac | +2.239 |
Leaks | +2.134 |
ILY | +2.121 |
CLASS | +2.115 |
Nib | +2.114 |
Neg logit contributions | |
angered | -2.622 |
genre | -2.388 |
adem | -2.148 |
bnb | -2.119 |
arios | -2.094 |
Token | This |
Token ID | 770 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
angered | +0.006 |
genre | +0.005 |
adem | +0.005 |
bnb | +0.005 |
arios | +0.005 |
Neg logit contributions | |
illac | -0.005 |
Leaks | -0.005 |
ILY | -0.005 |
Nib | -0.005 |
CLASS | -0.005 |
Token | improves |
Token ID | 19575 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
illac | +0.326 |
Leaks | +0.313 |
ILY | +0.308 |
Nib | +0.303 |
ャ | +0.300 |
Neg logit contributions | |
angered | -0.414 |
genre | -0.381 |
adem | -0.342 |
bnb | -0.340 |
arios | -0.335 |
Token | some |
Token ID | 617 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
angered | +0.856 |
genre | +0.782 |
bnb | +0.706 |
adem | +0.700 |
arios | +0.696 |
Neg logit contributions | |
illac | -0.733 |
Leaks | -0.700 |
ILY | -0.687 |
ャ | -0.678 |
Nib | -0.677 |
Token | kinds |
Token ID | 6982 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
illac | +0.149 |
Leaks | +0.144 |
ILY | +0.142 |
Nib | +0.140 |
CLASS | +0.139 |
Neg logit contributions | |
angered | -0.152 |
genre | -0.138 |
adem | -0.123 |
bnb | -0.121 |
arios | -0.119 |