Token | com |
Token ID | 785 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
leaflets | +2.020 |
Masquerade | +1.905 |
als | +1.880 |
Rollins | +1.877 |
Dent | +1.867 |
Neg logit contributions | |
uble | -1.759 |
outer | -1.707 |
oro | -1.641 |
olphins | -1.579 |
oster | -1.566 |
Token | / |
Token ID | 14 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
uble | +1.154 |
outer | +1.130 |
oro | +1.074 |
oster | +0.991 |
olphins | +0.951 |
Neg logit contributions | |
leaflets | -2.453 |
senal | -2.411 |
Masquerade | -2.345 |
pse | -2.334 |
Rollins | -2.285 |
Token | iv |
Token ID | 452 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
leaflets | +0.301 |
senal | +0.286 |
Masquerade | +0.284 |
pse | +0.279 |
Rollins | +0.275 |
Neg logit contributions | |
uble | -0.277 |
outer | -0.273 |
oro | -0.263 |
oster | -0.250 |
olphins | -0.245 |
Token | xx |
Token ID | 5324 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
uble | +0.941 |
outer | +0.930 |
oro | +0.895 |
oster | +0.850 |
olphins | +0.830 |
Neg logit contributions | |
leaflets | -1.083 |
senal | -1.033 |
Masquerade | -1.026 |
pse | -1.008 |
Rollins | -0.993 |
Token | brand |
Token ID | 17938 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
uble | +1.602 |
outer | +1.597 |
oro | +1.528 |
oster | +1.451 |
olphins | +1.405 |
Neg logit contributions | |
leaflets | -1.978 |
senal | -1.904 |
Masquerade | -1.867 |
pse | -1.854 |
Rollins | -1.815 |
Token | ? |
Token ID | 30 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
uble | +0.858 |
outer | +0.853 |
oro | +0.821 |
oster | +0.780 |
olphins | +0.752 |
Neg logit contributions | |
leaflets | -1.047 |
senal | -1.005 |
Masquerade | -0.992 |
pse | -0.981 |
Rollins | -0.963 |
Token | f |
Token ID | 69 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
uble | +5.043 |
oro | +4.939 |
outer | +4.884 |
oster | +4.489 |
fashion | +4.393 |
Neg logit contributions | |
leaflets | -7.431 |
senal | -7.234 |
pse | -6.885 |
Dent | -6.866 |
Masquerade | -6.844 |
Token | ref |
Token ID | 5420 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
uble | +2.575 |
outer | +2.525 |
oro | +2.460 |
oster | +2.377 |
fashion | +2.223 |
Neg logit contributions | |
leaflets | -4.135 |
senal | -3.973 |
pse | -3.867 |
Masquerade | -3.805 |
Dent | -3.764 |
Token | = |
Token ID | 28 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
leaflets | +0.491 |
Masquerade | +0.472 |
senal | +0.470 |
pse | +0.462 |
Rollins | +0.458 |
Neg logit contributions | |
uble | -0.233 |
outer | -0.229 |
oro | -0.213 |
oster | -0.198 |
olphins | -0.193 |
Token | ts |
Token ID | 912 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
uble | +1.994 |
outer | +1.988 |
oro | +1.921 |
oster | +1.842 |
fashion | +1.773 |
Neg logit contributions | |
leaflets | -2.219 |
Masquerade | -2.102 |
senal | -2.099 |
pse | -2.073 |
Rollins | -2.019 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
uble | +2.149 |
outer | +2.109 |
oro | +2.050 |
oster | +1.931 |
olphins | +1.867 |
Neg logit contributions | |
leaflets | -2.647 |
senal | -2.542 |
pse | -2.494 |
Masquerade | -2.486 |
Rollins | -2.407 |
Token | Share |
Token ID | 8734 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
leaflets | +2.124 |
Masquerade | +1.986 |
senal | +1.910 |
pse | +1.905 |
Dent | +1.894 |
Neg logit contributions | |
uble | -3.093 |
outer | -3.085 |
oro | -2.959 |
oster | -2.842 |
TEXTURE | -2.834 |
Token | this |
Token ID | 428 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
leaflets | +1.704 |
Masquerade | +1.593 |
senal | +1.579 |
pse | +1.554 |
Rollins | +1.542 |
Neg logit contributions | |
uble | -1.750 |
outer | -1.742 |
oro | -1.670 |
oster | -1.596 |
TEXTURE | -1.570 |
Token | story |
Token ID | 1621 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
leaflets | +0.886 |
Masquerade | +0.768 |
senal | +0.765 |
pse | +0.732 |
Rollins | +0.709 |
Neg logit contributions | |
uble | -2.944 |
outer | -2.917 |
oro | -2.856 |
oster | -2.765 |
olphins | -2.737 |
Token | : |
Token ID | 25 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
leaflets | +1.130 |
Masquerade | +1.054 |
senal | +1.038 |
pse | +1.020 |
Rollins | +1.013 |
Neg logit contributions | |
uble | -1.400 |
outer | -1.388 |
oro | -1.345 |
oster | -1.282 |
olphins | -1.269 |
Token | http |
Token ID | 2638 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
leaflets | +0.229 |
senal | +0.221 |
Masquerade | +0.220 |
pse | +0.217 |
Rollins | +0.215 |
Neg logit contributions | |
uble | -0.084 |
outer | -0.082 |
oro | -0.076 |
oster | -0.069 |
olphins | -0.067 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
uble | +1.143 |
outer | +1.117 |
oro | +0.956 |
oster | +0.829 |
TEXTURE | +0.723 |
Neg logit contributions | |
senal | -6.544 |
leaflets | -6.322 |
pse | -6.201 |
Masquerade | -6.069 |
cffff | -6.002 |
Token | on |
Token ID | 261 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
outer | +4.902 |
uble | +4.813 |
oro | +4.508 |
oster | +4.288 |
usa | +4.168 |
Neg logit contributions | |
senal | -7.501 |
leaflets | -7.420 |
Masquerade | -7.224 |
pse | -7.164 |
Dent | -6.947 |
Token | . |
Token ID | 13 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
uble | +2.011 |
outer | +1.977 |
oro | +1.880 |
oster | +1.777 |
olphins | +1.702 |
Neg logit contributions | |
senal | -3.622 |
leaflets | -3.546 |
pse | -3.444 |
Masquerade | -3.440 |
Dent | -3.306 |
Token | c |
Token ID | 66 |
Feature activation | +4.74e-04 |
Pos logit contributions | |
uble | +1.825 |
outer | +1.798 |
oro | +1.743 |
oster | +1.640 |
obe | +1.602 |
Neg logit contributions | |
leaflets | -2.126 |
senal | -2.069 |
Masquerade | -2.043 |
pse | -2.003 |
Dent | -1.927 |
Token | ps |
Token ID | 862 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
uble | +0.002 |
outer | +0.002 |
oro | +0.001 |
oster | +0.001 |
TEXTURE | +0.001 |
Neg logit contributions | |
leaflets | -0.002 |
Masquerade | -0.002 |
senal | -0.002 |
pse | -0.002 |
Rollins | -0.002 |
Token | j |
Token ID | 73 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
uble | +1.158 |
outer | +1.156 |
oro | +1.105 |
oster | +1.018 |
usa | +1.004 |
Neg logit contributions | |
leaflets | -1.950 |
senal | -1.882 |
Masquerade | -1.874 |
pse | -1.852 |
Dent | -1.809 |
Token | at |
Token ID | 379 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
uble | +0.606 |
outer | +0.599 |
oro | +0.581 |
oster | +0.556 |
olphins | +0.546 |
Neg logit contributions | |
leaflets | -0.480 |
senal | -0.455 |
Masquerade | -0.448 |
pse | -0.441 |
Rollins | -0.432 |
Token | 10 |
Token ID | 838 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
uble | +0.291 |
outer | +0.287 |
oro | +0.280 |
oster | +0.267 |
olphins | +0.261 |
Neg logit contributions | |
leaflets | -0.262 |
senal | -0.257 |
pse | -0.244 |
Masquerade | -0.243 |
cffff | -0.238 |
Token | : |
Token ID | 25 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
uble | +2.456 |
outer | +2.441 |
oro | +2.367 |
oster | +2.222 |
olphins | +2.169 |
Neg logit contributions | |
senal | -2.516 |
leaflets | -2.460 |
pse | -2.356 |
Masquerade | -2.303 |
cffff | -2.235 |
Token | 02 |
Token ID | 2999 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
leaflets | +0.509 |
senal | +0.486 |
Masquerade | +0.474 |
pse | +0.469 |
Rollins | +0.455 |
Neg logit contributions | |
uble | -0.624 |
outer | -0.618 |
oro | -0.597 |
oster | -0.572 |
TEXTURE | -0.562 |
Token | am |
Token ID | 321 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
uble | +0.521 |
outer | +0.515 |
oro | +0.489 |
oster | +0.455 |
olphins | +0.442 |
Neg logit contributions | |
leaflets | -0.927 |
senal | -0.892 |
Masquerade | -0.882 |
pse | -0.873 |
Rollins | -0.861 |
Token | PST |
Token ID | 28220 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
uble | +2.338 |
outer | +2.235 |
oro | +2.172 |
oster | +1.989 |
olphins | +1.963 |
Neg logit contributions | |
leaflets | -4.453 |
senal | -4.418 |
pse | -4.354 |
Masquerade | -4.271 |
Rollins | -4.147 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
uble | +4.258 |
outer | +4.165 |
oro | +4.018 |
oster | +3.701 |
obe | +3.696 |
Neg logit contributions | |
leaflets | -7.407 |
pse | -7.290 |
senal | -7.236 |
Masquerade | -6.970 |
cffff | -6.947 |
Token |
|
Token ID | 198 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
uble | +0.449 |
outer | +0.443 |
oro | +0.424 |
oster | +0.401 |
olphins | +0.393 |
Neg logit contributions | |
leaflets | -0.581 |
senal | -0.551 |
Masquerade | -0.551 |
pse | -0.541 |
Rollins | -0.535 |
Token | Do |
Token ID | 5211 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
uble | +0.095 |
outer | +0.094 |
oro | +0.090 |
oster | +0.085 |
TEXTURE | +0.083 |
Neg logit contributions | |
leaflets | -0.121 |
senal | -0.116 |
Masquerade | -0.114 |
pse | -0.113 |
Rollins | -0.111 |
Token | not |
Token ID | 407 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
leaflets | +0.638 |
senal | +0.606 |
Masquerade | +0.598 |
pse | +0.588 |
Rollins | +0.578 |
Neg logit contributions | |
uble | -0.717 |
outer | -0.708 |
oro | -0.685 |
oster | -0.655 |
olphins | -0.642 |
Token | use |
Token ID | 779 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
uble | +0.948 |
outer | +0.936 |
oro | +0.902 |
oster | +0.865 |
olphins | +0.838 |
Neg logit contributions | |
leaflets | -0.921 |
senal | -0.907 |
Masquerade | -0.870 |
pse | -0.857 |
Rollins | -0.843 |
Token | responds |
Token ID | 20067 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
uble | +0.328 |
outer | +0.325 |
oro | +0.313 |
oster | +0.298 |
olphins | +0.292 |
Neg logit contributions | |
leaflets | -0.327 |
senal | -0.310 |
Masquerade | -0.308 |
pse | -0.302 |
Rollins | -0.298 |
Token | , |
Token ID | 11 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
leaflets | +0.249 |
Masquerade | +0.234 |
senal | +0.232 |
pse | +0.229 |
Rollins | +0.226 |
Neg logit contributions | |
uble | -0.255 |
outer | -0.253 |
oro | -0.243 |
oster | -0.232 |
olphins | -0.228 |
Token | " |
Token ID | 366 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
leaflets | +0.317 |
senal | +0.296 |
Masquerade | +0.294 |
pse | +0.287 |
Rollins | +0.283 |
Neg logit contributions | |
uble | -0.455 |
outer | -0.452 |
oro | -0.438 |
oster | -0.420 |
olphins | -0.413 |
Token | You |
Token ID | 1639 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
leaflets | +0.333 |
senal | +0.319 |
Masquerade | +0.317 |
pse | +0.312 |
Rollins | +0.308 |
Neg logit contributions | |
uble | -0.225 |
outer | -0.222 |
oro | -0.212 |
oster | -0.199 |
olphins | -0.194 |
Token | are |
Token ID | 389 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
uble | +0.587 |
outer | +0.581 |
oro | +0.558 |
oster | +0.529 |
olphins | +0.514 |
Neg logit contributions | |
leaflets | -0.717 |
senal | -0.691 |
Masquerade | -0.678 |
pse | -0.669 |
Rollins | -0.658 |
Token | such |
Token ID | 884 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
uble | +0.698 |
outer | +0.690 |
oro | +0.664 |
oster | +0.632 |
olphins | +0.621 |
Neg logit contributions | |
leaflets | -0.715 |
senal | -0.677 |
Masquerade | -0.673 |
pse | -0.660 |
Rollins | -0.652 |
Token | a |
Token ID | 257 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
outer | +5.630 |
uble | +5.570 |
oro | +5.477 |
oster | +5.293 |
TEXTURE | +5.114 |
Neg logit contributions | |
senal | -6.130 |
leaflets | -6.118 |
pse | -5.772 |
Masquerade | -5.705 |
Dent | -5.606 |
Token | tease |
Token ID | 34691 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
uble | +2.932 |
outer | +2.917 |
oro | +2.801 |
oster | +2.699 |
TEXTURE | +2.623 |
Neg logit contributions | |
leaflets | -2.936 |
senal | -2.837 |
Masquerade | -2.733 |
pse | -2.720 |
Dent | -2.660 |
Token | ." |
Token ID | 526 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
uble | +2.545 |
outer | +2.496 |
oro | +2.410 |
oster | +2.305 |
obe | +2.219 |
Neg logit contributions | |
leaflets | -3.276 |
senal | -3.215 |
pse | -3.081 |
Masquerade | -3.080 |
cffff | -2.986 |
Token |
|
Token ID | 198 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
uble | +0.386 |
outer | +0.381 |
oro | +0.365 |
oster | +0.345 |
olphins | +0.337 |
Neg logit contributions | |
leaflets | -0.505 |
senal | -0.482 |
Masquerade | -0.478 |
pse | -0.472 |
Rollins | -0.464 |
Token |
|
Token ID | 198 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
uble | +0.649 |
outer | +0.642 |
oro | +0.615 |
oster | +0.581 |
TEXTURE | +0.566 |
Neg logit contributions | |
leaflets | -0.869 |
senal | -0.839 |
Masquerade | -0.823 |
pse | -0.816 |
Rollins | -0.799 |
Token | Share |
Token ID | 8734 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
leaflets | +2.338 |
Masquerade | +2.149 |
Rollins | +2.072 |
Dent | +2.069 |
pse | +2.066 |
Neg logit contributions | |
uble | -3.807 |
outer | -3.790 |
oro | -3.640 |
TEXTURE | -3.492 |
olphins | -3.491 |
Token | this |
Token ID | 428 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
leaflets | +1.710 |
Masquerade | +1.592 |
Rollins | +1.543 |
Dent | +1.535 |
pse | +1.528 |
Neg logit contributions | |
outer | -1.885 |
uble | -1.873 |
oro | -1.795 |
oster | -1.720 |
TEXTURE | -1.693 |
Token | story |
Token ID | 1621 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
leaflets | +1.150 |
Masquerade | +0.965 |
Dent | +0.890 |
pse | +0.890 |
senal | +0.887 |
Neg logit contributions | |
uble | -4.294 |
outer | -4.253 |
oro | -4.174 |
oster | -4.047 |
TEXTURE | -4.015 |
Token | : |
Token ID | 25 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
leaflets | +1.556 |
Masquerade | +1.449 |
Dent | +1.392 |
Rollins | +1.388 |
pse | +1.388 |
Neg logit contributions | |
uble | -2.012 |
outer | -2.000 |
oro | -1.939 |
oster | -1.849 |
olphins | -1.834 |
Token | http |
Token ID | 2638 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
leaflets | +0.133 |
senal | +0.128 |
Masquerade | +0.128 |
pse | +0.126 |
Rollins | +0.125 |
Neg logit contributions | |
uble | -0.051 |
outer | -0.050 |
oro | -0.046 |
oster | -0.042 |
olphins | -0.041 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
uble | +1.177 |
outer | +1.152 |
oro | +1.018 |
oster | +0.876 |
TEXTURE | +0.788 |
Neg logit contributions | |
senal | -6.003 |
leaflets | -5.888 |
pse | -5.718 |
Masquerade | -5.662 |
cffff | -5.568 |
Token | usat |
Token ID | 37937 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
outer | +2.612 |
uble | +2.570 |
oro | +2.292 |
oster | +2.106 |
obe | +2.007 |
Neg logit contributions | |
senal | -8.803 |
leaflets | -8.799 |
Masquerade | -8.590 |
pse | -8.524 |
Dent | -8.340 |
Token | . |
Token ID | 13 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
uble | +2.607 |
outer | +2.555 |
oro | +2.442 |
oster | +2.285 |
usa | +2.188 |
Neg logit contributions | |
senal | -5.805 |
leaflets | -5.440 |
pse | -5.410 |
Masquerade | -5.195 |
cffff | -5.132 |
Token | ly |
Token ID | 306 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
uble | +1.517 |
outer | +1.474 |
oro | +1.389 |
oster | +1.276 |
olphins | +1.192 |
Neg logit contributions | |
leaflets | -3.919 |
senal | -3.848 |
Masquerade | -3.765 |
pse | -3.736 |
Rollins | -3.677 |
Token | / |
Token ID | 14 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
uble | +2.651 |
outer | +2.538 |
oro | +2.490 |
oster | +2.262 |
TEXTURE | +2.181 |
Neg logit contributions | |
senal | -7.627 |
leaflets | -7.254 |
pse | -7.099 |
cffff | -6.817 |
Masquerade | -6.813 |
Token | 1 |
Token ID | 16 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
uble | +1.881 |
outer | +1.867 |
oro | +1.778 |
oster | +1.682 |
TEXTURE | +1.651 |
Neg logit contributions | |
leaflets | -2.556 |
senal | -2.500 |
Masquerade | -2.411 |
pse | -2.381 |
Dent | -2.317 |
Token | Share |
Token ID | 8734 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
leaflets | +2.518 |
Masquerade | +2.294 |
Dent | +2.226 |
Rollins | +2.210 |
pse | +2.192 |
Neg logit contributions | |
uble | -4.235 |
outer | -4.216 |
oro | -4.058 |
TEXTURE | -3.910 |
olphins | -3.899 |
Token | this |
Token ID | 428 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
leaflets | +1.956 |
Masquerade | +1.812 |
Rollins | +1.752 |
Dent | +1.747 |
pse | +1.730 |
Neg logit contributions | |
outer | -2.202 |
uble | -2.186 |
oro | -2.101 |
oster | -2.012 |
TEXTURE | -1.986 |
Token | story |
Token ID | 1621 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
leaflets | +1.022 |
Masquerade | +0.859 |
pse | +0.805 |
senal | +0.797 |
Dent | +0.794 |
Neg logit contributions | |
uble | -3.775 |
outer | -3.734 |
oro | -3.663 |
oster | -3.554 |
TEXTURE | -3.523 |
Token | : |
Token ID | 25 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
leaflets | +1.586 |
Masquerade | +1.477 |
Dent | +1.419 |
Rollins | +1.414 |
pse | +1.412 |
Neg logit contributions | |
uble | -2.064 |
outer | -2.049 |
oro | -1.986 |
oster | -1.895 |
olphins | -1.882 |
Token | http |
Token ID | 2638 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
leaflets | +0.534 |
senal | +0.514 |
Masquerade | +0.511 |
pse | +0.505 |
Rollins | +0.500 |
Neg logit contributions | |
uble | -0.219 |
outer | -0.215 |
oro | -0.201 |
oster | -0.185 |
olphins | -0.178 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
uble | +1.102 |
outer | +1.093 |
oro | +0.958 |
oster | +0.824 |
TEXTURE | +0.740 |
Neg logit contributions | |
senal | -5.498 |
leaflets | -5.407 |
pse | -5.245 |
Masquerade | -5.210 |
cffff | -5.108 |
Token | cin |
Token ID | 17879 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
outer | +6.526 |
uble | +6.381 |
oro | +6.129 |
oster | +5.946 |
obe | +5.772 |
Neg logit contributions | |
leaflets | -4.882 |
senal | -4.874 |
Masquerade | -4.727 |
pse | -4.703 |
Rollins | -4.504 |
Token | . |
Token ID | 13 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
uble | +1.257 |
outer | +1.245 |
oro | +1.182 |
oster | +1.135 |
usa | +1.091 |
Neg logit contributions | |
senal | -2.485 |
leaflets | -2.433 |
Masquerade | -2.371 |
pse | -2.363 |
Rollins | -2.273 |
Token | ci |
Token ID | 979 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
uble | +1.216 |
outer | +1.213 |
oro | +1.182 |
oster | +1.126 |
obe | +1.086 |
Neg logit contributions | |
leaflets | -1.346 |
senal | -1.326 |
Masquerade | -1.277 |
pse | -1.259 |
Rollins | -1.234 |
Token | / |
Token ID | 14 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
uble | +1.055 |
outer | +1.038 |
oro | +0.983 |
oster | +0.912 |
olphins | +0.880 |
Neg logit contributions | |
leaflets | -2.145 |
senal | -2.073 |
Masquerade | -2.050 |
pse | -2.027 |
Rollins | -2.001 |
Token | 2 |
Token ID | 17 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
uble | +2.544 |
outer | +2.543 |
oro | +2.400 |
oster | +2.271 |
usa | +2.240 |
Neg logit contributions | |
leaflets | -3.962 |
senal | -3.858 |
Masquerade | -3.738 |
pse | -3.680 |
Dent | -3.603 |
Token | Share |
Token ID | 8734 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
leaflets | +2.453 |
Masquerade | +2.254 |
pse | +2.178 |
Rollins | +2.171 |
senal | +2.171 |
Neg logit contributions | |
uble | -3.880 |
outer | -3.862 |
oro | -3.716 |
oster | -3.563 |
TEXTURE | -3.559 |
Token | this |
Token ID | 428 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
leaflets | +2.176 |
Masquerade | +2.020 |
Rollins | +1.958 |
Dent | +1.948 |
pse | +1.926 |
Neg logit contributions | |
outer | -2.472 |
uble | -2.448 |
oro | -2.352 |
oster | -2.256 |
TEXTURE | -2.232 |
Token | story |
Token ID | 1621 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
leaflets | +1.024 |
Masquerade | +0.874 |
senal | +0.839 |
pse | +0.818 |
Dent | +0.806 |
Neg logit contributions | |
uble | -3.615 |
outer | -3.585 |
oro | -3.513 |
oster | -3.404 |
TEXTURE | -3.368 |
Token | : |
Token ID | 25 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
leaflets | +1.414 |
Masquerade | +1.316 |
senal | +1.276 |
pse | +1.270 |
Dent | +1.265 |
Neg logit contributions | |
uble | -1.783 |
outer | -1.770 |
oro | -1.716 |
oster | -1.636 |
olphins | -1.620 |
Token | http |
Token ID | 2638 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
leaflets | +0.339 |
senal | +0.328 |
Masquerade | +0.326 |
pse | +0.322 |
Rollins | +0.319 |
Neg logit contributions | |
uble | -0.127 |
outer | -0.124 |
oro | -0.115 |
oster | -0.105 |
olphins | -0.101 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
uble | +1.137 |
outer | +1.113 |
oro | +0.979 |
oster | +0.848 |
TEXTURE | +0.765 |
Neg logit contributions | |
senal | -5.688 |
leaflets | -5.590 |
pse | -5.436 |
Masquerade | -5.380 |
cffff | -5.292 |
Token | usat |
Token ID | 37937 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
outer | +2.812 |
uble | +2.807 |
oro | +2.505 |
oster | +2.269 |
usa | +2.229 |
Neg logit contributions | |
leaflets | -8.506 |
senal | -8.469 |
Masquerade | -8.325 |
pse | -8.238 |
Dent | -8.054 |
Token | . |
Token ID | 13 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
uble | +2.531 |
outer | +2.491 |
oro | +2.375 |
oster | +2.225 |
usa | +2.136 |
Neg logit contributions | |
senal | -5.499 |
leaflets | -5.190 |
pse | -5.140 |
Masquerade | -4.949 |
cffff | -4.885 |
Token | ly |
Token ID | 306 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
uble | +1.435 |
outer | +1.394 |
oro | +1.317 |
oster | +1.206 |
olphins | +1.128 |
Neg logit contributions | |
leaflets | -3.708 |
senal | -3.647 |
Masquerade | -3.565 |
pse | -3.536 |
Rollins | -3.482 |
Token | / |
Token ID | 14 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
uble | +2.694 |
outer | +2.573 |
oro | +2.525 |
oster | +2.285 |
TEXTURE | +2.210 |
Neg logit contributions | |
senal | -8.035 |
leaflets | -7.579 |
pse | -7.461 |
anwhile | -7.152 |
cffff | -7.145 |
Token | 1 |
Token ID | 16 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
uble | +1.767 |
outer | +1.750 |
oro | +1.673 |
oster | +1.579 |
TEXTURE | +1.543 |
Neg logit contributions | |
leaflets | -2.321 |
senal | -2.260 |
Masquerade | -2.184 |
pse | -2.157 |
Dent | -2.105 |
Token | $ |
Token ID | 720 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
uble | +1.917 |
outer | +1.882 |
oro | +1.834 |
oster | +1.768 |
olphins | +1.735 |
Neg logit contributions | |
leaflets | -1.668 |
senal | -1.596 |
Masquerade | -1.563 |
pse | -1.535 |
Rollins | -1.484 |
Token | 11 |
Token ID | 1157 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
uble | +1.686 |
outer | +1.672 |
oro | +1.609 |
oster | +1.531 |
TEXTURE | +1.508 |
Neg logit contributions | |
leaflets | -1.847 |
senal | -1.834 |
pse | -1.756 |
Masquerade | -1.729 |
cffff | -1.666 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
leaflets | +0.816 |
senal | +0.775 |
Masquerade | +0.772 |
pse | +0.760 |
Rollins | +0.754 |
Neg logit contributions | |
uble | -0.580 |
outer | -0.575 |
oro | -0.550 |
oster | -0.514 |
TEXTURE | -0.508 |
Token | 25 |
Token ID | 1495 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
leaflets | +0.056 |
senal | +0.053 |
Masquerade | +0.053 |
pse | +0.052 |
Rollins | +0.051 |
Neg logit contributions | |
uble | -0.056 |
outer | -0.055 |
oro | -0.053 |
oster | -0.051 |
olphins | -0.050 |
Token | million |
Token ID | 1510 |
Feature activation | +9.55e-02 |
Pos logit contributions | |
uble | +0.262 |
outer | +0.258 |
oro | +0.248 |
oster | +0.234 |
olphins | +0.229 |
Neg logit contributions | |
leaflets | -0.325 |
senal | -0.310 |
Masquerade | -0.308 |
pse | -0.303 |
Rollins | -0.299 |
Token | contract |
Token ID | 2775 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
uble | +0.387 |
outer | +0.382 |
oro | +0.371 |
oster | +0.356 |
olphins | +0.350 |
Neg logit contributions | |
leaflets | -0.303 |
senal | -0.285 |
Masquerade | -0.282 |
pse | -0.276 |
Rollins | -0.271 |
Token | signed |
Token ID | 4488 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
uble | +4.930 |
outer | +4.750 |
oro | +4.540 |
oster | +4.454 |
olphins | +4.253 |
Neg logit contributions | |
leaflets | -6.201 |
senal | -6.101 |
Masquerade | -5.863 |
pse | -5.741 |
cffff | -5.652 |
Token | in |
Token ID | 287 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
uble | +1.951 |
outer | +1.888 |
oro | +1.840 |
oster | +1.761 |
olphins | +1.732 |
Neg logit contributions | |
leaflets | -1.804 |
senal | -1.753 |
Masquerade | -1.694 |
pse | -1.679 |
Rollins | -1.643 |
Token | March |
Token ID | 2805 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
uble | +1.099 |
outer | +1.077 |
oro | +1.039 |
oster | +0.979 |
olphins | +0.949 |
Neg logit contributions | |
leaflets | -1.577 |
senal | -1.566 |
Masquerade | -1.500 |
pse | -1.493 |
cffff | -1.469 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
uble | +2.849 |
outer | +2.753 |
oro | +2.691 |
oster | +2.552 |
olphins | +2.451 |
Neg logit contributions | |
senal | -4.067 |
leaflets | -4.003 |
pse | -3.838 |
Masquerade | -3.830 |
cffff | -3.780 |
Token |
|
Token ID | 198 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
uble | +0.602 |
outer | +0.592 |
oro | +0.568 |
oster | +0.538 |
olphins | +0.526 |
Neg logit contributions | |
leaflets | -0.791 |
senal | -0.756 |
Masquerade | -0.750 |
pse | -0.739 |
Rollins | -0.728 |
Token | at |
Token ID | 379 |
Feature activation | +2.87e-03 |
Pos logit contributions | |
uble | +0.400 |
outer | +0.396 |
oro | +0.384 |
oster | +0.368 |
olphins | +0.361 |
Neg logit contributions | |
leaflets | -0.311 |
senal | -0.293 |
Masquerade | -0.290 |
pse | -0.284 |
Rollins | -0.279 |
Token | 9 |
Token ID | 860 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
uble | +0.011 |
outer | +0.011 |
oro | +0.011 |
oster | +0.010 |
olphins | +0.010 |
Neg logit contributions | |
leaflets | -0.010 |
senal | -0.009 |
Masquerade | -0.009 |
pse | -0.009 |
cffff | -0.009 |
Token | : |
Token ID | 25 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
uble | +1.807 |
outer | +1.794 |
oro | +1.734 |
oster | +1.649 |
TEXTURE | +1.613 |
Neg logit contributions | |
leaflets | -1.691 |
senal | -1.691 |
pse | -1.600 |
Masquerade | -1.582 |
cffff | -1.521 |
Token | 28 |
Token ID | 2078 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
uble | +0.216 |
outer | +0.214 |
oro | +0.206 |
oster | +0.197 |
TEXTURE | +0.195 |
Neg logit contributions | |
leaflets | -0.183 |
senal | -0.181 |
pse | -0.172 |
Masquerade | -0.170 |
cffff | -0.163 |
Token | am |
Token ID | 321 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
uble | +0.892 |
outer | +0.882 |
oro | +0.834 |
oster | +0.775 |
olphins | +0.749 |
Neg logit contributions | |
leaflets | -1.687 |
senal | -1.626 |
Masquerade | -1.608 |
pse | -1.594 |
Rollins | -1.570 |
Token | PST |
Token ID | 28220 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
uble | +2.247 |
outer | +2.184 |
oro | +2.049 |
oster | +1.941 |
TERN | +1.865 |
Neg logit contributions | |
senal | -4.352 |
leaflets | -4.318 |
pse | -4.201 |
Masquerade | -4.102 |
cffff | -4.083 |
Token |
|
Token ID | 198 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
uble | +4.164 |
outer | +4.092 |
oro | +3.900 |
oster | +3.675 |
fashion | +3.623 |
Neg logit contributions | |
leaflets | -6.690 |
pse | -6.427 |
senal | -6.414 |
Masquerade | -6.273 |
Rollins | -6.196 |
Token |
|
Token ID | 198 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
uble | +0.072 |
outer | +0.071 |
oro | +0.068 |
oster | +0.065 |
olphins | +0.063 |
Neg logit contributions | |
leaflets | -0.089 |
Masquerade | -0.085 |
senal | -0.083 |
Rollins | -0.082 |
pse | -0.082 |
Token | Do |
Token ID | 5211 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
leaflets | +0.084 |
senal | +0.080 |
Masquerade | +0.079 |
pse | +0.078 |
Rollins | +0.077 |
Neg logit contributions | |
uble | -0.064 |
outer | -0.064 |
oro | -0.061 |
oster | -0.058 |
TEXTURE | -0.056 |
Token | use |
Token ID | 779 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
leaflets | +0.636 |
senal | +0.599 |
Masquerade | +0.594 |
pse | +0.582 |
Rollins | +0.572 |
Neg logit contributions | |
uble | -0.787 |
outer | -0.779 |
oro | -0.753 |
oster | -0.721 |
olphins | -0.709 |
Token | social |
Token ID | 1919 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
uble | +1.545 |
outer | +1.523 |
oro | +1.488 |
oster | +1.435 |
TEXTURE | +1.412 |
Neg logit contributions | |
leaflets | -0.813 |
senal | -0.774 |
Masquerade | -0.751 |
pse | -0.730 |
Rollins | -0.710 |
Token | ., |
Token ID | 1539 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
uble | +1.608 |
outer | +1.543 |
oro | +1.485 |
oster | +1.374 |
olphins | +1.336 |
Neg logit contributions | |
leaflets | -3.648 |
senal | -3.515 |
Masquerade | -3.492 |
pse | -3.458 |
Rollins | -3.416 |
Token | where |
Token ID | 810 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
uble | +0.470 |
outer | +0.464 |
oro | +0.451 |
oster | +0.430 |
olphins | +0.425 |
Neg logit contributions | |
leaflets | -0.433 |
senal | -0.416 |
Masquerade | -0.406 |
pse | -0.402 |
Rollins | -0.392 |
Token | killer |
Token ID | 11868 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
uble | +0.870 |
outer | +0.859 |
oro | +0.843 |
oster | +0.802 |
olphins | +0.796 |
Neg logit contributions | |
leaflets | -0.723 |
senal | -0.698 |
Masquerade | -0.678 |
pse | -0.668 |
Rollins | -0.654 |
Token | whale |
Token ID | 22206 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
uble | +2.623 |
outer | +2.585 |
oro | +2.539 |
olphins | +2.469 |
oster | +2.420 |
Neg logit contributions | |
leaflets | -1.962 |
senal | -1.959 |
Masquerade | -1.832 |
pse | -1.817 |
Rollins | -1.789 |
Token | Til |
Token ID | 40422 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
uble | +3.784 |
outer | +3.722 |
oro | +3.708 |
olphins | +3.557 |
oster | +3.534 |
Neg logit contributions | |
senal | -2.819 |
leaflets | -2.779 |
Masquerade | -2.643 |
pse | -2.588 |
cffff | -2.579 |
Token | ik |
Token ID | 1134 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
uble | +2.335 |
outer | +2.309 |
oro | +2.274 |
oster | +2.122 |
olphins | +2.061 |
Neg logit contributions | |
leaflets | -3.555 |
senal | -3.476 |
Masquerade | -3.388 |
pse | -3.347 |
cffff | -3.287 |
Token | um |
Token ID | 388 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
oro | +5.488 |
uble | +5.399 |
outer | +5.319 |
usa | +5.045 |
olphins | +4.962 |
Neg logit contributions | |
leaflets | -5.371 |
senal | -5.280 |
cffff | -5.263 |
Masquerade | -5.142 |
pse | -5.121 |
Token | was |
Token ID | 373 |
Feature activation | -9.75e-02 |
Pos logit contributions | |
uble | +1.391 |
outer | +1.371 |
oro | +1.350 |
oster | +1.273 |
olphins | +1.270 |
Neg logit contributions | |
leaflets | -1.217 |
senal | -1.175 |
Masquerade | -1.147 |
pse | -1.121 |
Rollins | -1.102 |
Token | involved |
Token ID | 2950 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
leaflets | +0.244 |
senal | +0.226 |
Masquerade | +0.223 |
pse | +0.217 |
Rollins | +0.212 |
Neg logit contributions | |
uble | -0.459 |
outer | -0.455 |
oro | -0.443 |
oster | -0.427 |
olphins | -0.421 |
Token | in |
Token ID | 287 |
Feature activation | -1.77e-03 |
Pos logit contributions | |
uble | +0.311 |
outer | +0.306 |
oro | +0.296 |
oster | +0.282 |
olphins | +0.276 |
Neg logit contributions | |
leaflets | -0.325 |
senal | -0.310 |
Masquerade | -0.306 |
pse | -0.301 |
Rollins | -0.296 |
Token | three |
Token ID | 1115 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
leaflets | +0.006 |
senal | +0.005 |
Masquerade | +0.005 |
pse | +0.005 |
Rollins | +0.005 |
Neg logit contributions | |
uble | -0.007 |
outer | -0.007 |
oro | -0.007 |
oster | -0.006 |
olphins | -0.006 |
Token | cin |
Token ID | 17879 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
outer | +6.526 |
uble | +6.381 |
oro | +6.129 |
oster | +5.946 |
obe | +5.772 |
Neg logit contributions | |
leaflets | -4.882 |
senal | -4.874 |
Masquerade | -4.727 |
pse | -4.703 |
Rollins | -4.504 |
Token | . |
Token ID | 13 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
uble | +1.257 |
outer | +1.245 |
oro | +1.182 |
oster | +1.135 |
usa | +1.091 |
Neg logit contributions | |
senal | -2.485 |
leaflets | -2.433 |
Masquerade | -2.371 |
pse | -2.363 |
Rollins | -2.273 |
Token | ci |
Token ID | 979 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
uble | +1.216 |
outer | +1.213 |
oro | +1.182 |
oster | +1.126 |
obe | +1.086 |
Neg logit contributions | |
leaflets | -1.346 |
senal | -1.326 |
Masquerade | -1.277 |
pse | -1.259 |
Rollins | -1.234 |
Token | / |
Token ID | 14 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
uble | +1.055 |
outer | +1.038 |
oro | +0.983 |
oster | +0.912 |
olphins | +0.880 |
Neg logit contributions | |
leaflets | -2.145 |
senal | -2.073 |
Masquerade | -2.050 |
pse | -2.027 |
Rollins | -2.001 |
Token | 2 |
Token ID | 17 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
uble | +2.544 |
outer | +2.543 |
oro | +2.400 |
oster | +2.271 |
usa | +2.240 |
Neg logit contributions | |
leaflets | -3.962 |
senal | -3.858 |
Masquerade | -3.738 |
pse | -3.680 |
Dent | -3.603 |
Token | yp |
Token ID | 4464 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
uble | +2.273 |
outer | +2.249 |
oro | +2.178 |
oster | +2.038 |
obe | +1.968 |
Neg logit contributions | |
leaflets | -3.078 |
senal | -2.973 |
Masquerade | -2.924 |
pse | -2.861 |
Dent | -2.828 |
Token | d |
Token ID | 67 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
uble | +4.592 |
outer | +4.548 |
oro | +4.430 |
oster | +4.178 |
obe | +4.017 |
Neg logit contributions | |
leaflets | -6.001 |
senal | -5.851 |
Masquerade | -5.713 |
pse | -5.549 |
Dent | -5.463 |
Token | G |
Token ID | 38 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
uble | +0.945 |
outer | +0.932 |
oro | +0.896 |
oster | +0.847 |
olphins | +0.822 |
Neg logit contributions | |
leaflets | -1.217 |
senal | -1.167 |
Masquerade | -1.154 |
pse | -1.132 |
Rollins | -1.115 |
Token | uf |
Token ID | 3046 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
uble | +1.662 |
outer | +1.649 |
oro | +1.585 |
oster | +1.490 |
obe | +1.437 |
Neg logit contributions | |
leaflets | -2.221 |
senal | -2.133 |
Masquerade | -2.102 |
pse | -2.069 |
Rollins | -2.032 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
uble | +0.517 |
outer | +0.510 |
oro | +0.487 |
oster | +0.455 |
olphins | +0.440 |
Neg logit contributions | |
leaflets | -0.912 |
senal | -0.882 |
Masquerade | -0.867 |
pse | -0.863 |
Rollins | -0.843 |
Token | A |
Token ID | 32 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
uble | +0.329 |
outer | +0.327 |
oro | +0.312 |
oster | +0.296 |
TEXTURE | +0.291 |
Neg logit contributions | |
leaflets | -0.403 |
senal | -0.386 |
Masquerade | -0.380 |
pse | -0.376 |
Rollins | -0.368 |
Token | at |
Token ID | 379 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
leaflets | +0.381 |
Masquerade | +0.354 |
senal | +0.349 |
pse | +0.344 |
Rollins | +0.341 |
Neg logit contributions | |
uble | -0.505 |
outer | -0.501 |
oro | -0.484 |
oster | -0.464 |
olphins | -0.457 |
Token | 9 |
Token ID | 860 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
leaflets | +0.293 |
senal | +0.282 |
Masquerade | +0.273 |
pse | +0.271 |
Rollins | +0.263 |
Neg logit contributions | |
uble | -0.344 |
outer | -0.340 |
oro | -0.330 |
oster | -0.315 |
olphins | -0.309 |
Token | : |
Token ID | 25 |
Feature activation | -5.01e-03 |
Pos logit contributions | |
uble | +1.719 |
outer | +1.706 |
oro | +1.649 |
oster | +1.570 |
TEXTURE | +1.537 |
Neg logit contributions | |
senal | -1.663 |
leaflets | -1.638 |
pse | -1.561 |
Masquerade | -1.531 |
cffff | -1.483 |
Token | 01 |
Token ID | 486 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
leaflets | +0.017 |
senal | +0.016 |
pse | +0.016 |
Masquerade | +0.015 |
cffff | +0.015 |
Neg logit contributions | |
uble | -0.020 |
outer | -0.019 |
oro | -0.019 |
oster | -0.018 |
TEXTURE | -0.018 |
Token | am |
Token ID | 321 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
uble | +0.964 |
outer | +0.953 |
oro | +0.903 |
oster | +0.837 |
olphins | +0.811 |
Neg logit contributions | |
leaflets | -1.777 |
senal | -1.712 |
Masquerade | -1.692 |
pse | -1.679 |
Rollins | -1.651 |
Token | PDT |
Token ID | 28288 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
uble | +3.014 |
outer | +2.956 |
oro | +2.869 |
oster | +2.711 |
TEXTURE | +2.672 |
Neg logit contributions | |
senal | -3.661 |
leaflets | -3.545 |
pse | -3.436 |
Masquerade | -3.332 |
cffff | -3.309 |
Token |
|
Token ID | 198 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
uble | +4.010 |
outer | +3.958 |
oro | +3.758 |
oster | +3.533 |
olphins | +3.519 |
Neg logit contributions | |
leaflets | -6.355 |
senal | -6.072 |
pse | -6.054 |
Masquerade | -6.016 |
Rollins | -5.883 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
uble | +0.703 |
outer | +0.694 |
oro | +0.665 |
oster | +0.629 |
olphins | +0.614 |
Neg logit contributions | |
leaflets | -0.923 |
senal | -0.882 |
Masquerade | -0.875 |
pse | -0.862 |
Rollins | -0.849 |
Token | Do |
Token ID | 5211 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
uble | +0.469 |
outer | +0.466 |
oro | +0.447 |
oster | +0.422 |
TEXTURE | +0.414 |
Neg logit contributions | |
leaflets | -0.613 |
senal | -0.591 |
Masquerade | -0.577 |
pse | -0.575 |
Rollins | -0.560 |
Token | use |
Token ID | 779 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
leaflets | +0.685 |
senal | +0.643 |
Masquerade | +0.639 |
pse | +0.624 |
Rollins | +0.615 |
Neg logit contributions | |
uble | -0.878 |
outer | -0.871 |
oro | -0.842 |
oster | -0.806 |
olphins | -0.793 |
Token | social |
Token ID | 1919 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
uble | +1.973 |
outer | +1.944 |
oro | +1.901 |
oster | +1.832 |
TEXTURE | +1.805 |
Neg logit contributions | |
leaflets | -1.056 |
senal | -1.016 |
Masquerade | -0.978 |
pse | -0.950 |
Rollins | -0.925 |
Token | import |
Token ID | 1330 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
uble | +0.412 |
outer | +0.405 |
oro | +0.382 |
oster | +0.355 |
olphins | +0.343 |
Neg logit contributions | |
leaflets | -0.781 |
senal | -0.755 |
Masquerade | -0.744 |
pse | -0.733 |
Rollins | -0.731 |
Token | paths |
Token ID | 13532 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
uble | +0.803 |
outer | +0.796 |
oro | +0.769 |
oster | +0.739 |
TEXTURE | +0.719 |
Neg logit contributions | |
leaflets | -0.707 |
senal | -0.680 |
Masquerade | -0.661 |
pse | -0.643 |
Rollins | -0.641 |
Token | import |
Token ID | 1330 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
uble | +3.200 |
outer | +3.195 |
oro | +3.044 |
oster | +2.900 |
obe | +2.818 |
Neg logit contributions | |
leaflets | -3.491 |
senal | -3.348 |
Masquerade | -3.276 |
Rollins | -3.237 |
cffff | -3.199 |
Token | n |
Token ID | 299 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
uble | +1.868 |
outer | +1.852 |
oro | +1.795 |
oster | +1.724 |
TEXTURE | +1.668 |
Neg logit contributions | |
leaflets | -1.608 |
senal | -1.562 |
Masquerade | -1.499 |
cffff | -1.468 |
Rollins | -1.456 |
Token | umpy |
Token ID | 32152 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
uble | +1.883 |
outer | +1.878 |
oro | +1.815 |
oster | +1.726 |
obe | +1.667 |
Neg logit contributions | |
leaflets | -2.266 |
senal | -2.177 |
Masquerade | -2.145 |
Rollins | -2.087 |
pse | -2.081 |
Token | as |
Token ID | 355 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
uble | +0.558 |
outer | +0.551 |
oro | +0.532 |
oster | +0.508 |
TEXTURE | +0.493 |
Neg logit contributions | |
leaflets | -0.564 |
senal | -0.537 |
Masquerade | -0.530 |
pse | -0.520 |
Rollins | -0.516 |
Token | np |
Token ID | 45941 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
uble | +5.715 |
oro | +5.555 |
outer | +5.530 |
oster | +5.365 |
obe | +5.076 |
Neg logit contributions | |
senal | -4.676 |
leaflets | -4.675 |
Masquerade | -4.520 |
Dent | -4.309 |
cffff | -4.292 |
Token | import |
Token ID | 1330 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
uble | +1.928 |
outer | +1.905 |
oro | +1.835 |
oster | +1.731 |
obe | +1.667 |
Neg logit contributions | |
leaflets | -2.581 |
senal | -2.499 |
Masquerade | -2.443 |
cffff | -2.395 |
Rollins | -2.388 |
Token | arg |
Token ID | 1822 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
uble | +2.559 |
outer | +2.508 |
oro | +2.464 |
oster | +2.359 |
TEXTURE | +2.267 |
Neg logit contributions | |
leaflets | -2.058 |
senal | -2.043 |
Masquerade | -1.942 |
cffff | -1.882 |
Rollins | -1.862 |
Token | parse |
Token ID | 29572 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
uble | +1.213 |
outer | +1.208 |
oro | +1.151 |
oster | +1.111 |
obe | +1.066 |
Neg logit contributions | |
leaflets | -1.281 |
senal | -1.213 |
Masquerade | -1.213 |
Rollins | -1.185 |
pse | -1.169 |
Token | import |
Token ID | 1330 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
uble | +1.264 |
outer | +1.249 |
oro | +1.197 |
oster | +1.128 |
TEXTURE | +1.090 |
Neg logit contributions | |
leaflets | -1.644 |
senal | -1.583 |
Masquerade | -1.555 |
Rollins | -1.525 |
pse | -1.519 |
Token | import |
Token ID | 1330 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
uble | +0.710 |
outer | +0.696 |
oro | +0.653 |
oster | +0.597 |
olphins | +0.576 |
Neg logit contributions | |
leaflets | -1.725 |
senal | -1.671 |
Masquerade | -1.654 |
pse | -1.634 |
Rollins | -1.618 |
Token | paths |
Token ID | 13532 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
leaflets | +0.163 |
senal | +0.153 |
Masquerade | +0.150 |
pse | +0.145 |
Rollins | +0.143 |
Neg logit contributions | |
uble | -0.309 |
outer | -0.306 |
oro | -0.298 |
oster | -0.287 |
olphins | -0.283 |
Token | import |
Token ID | 1330 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
outer | +2.044 |
uble | +2.037 |
oro | +1.910 |
oster | +1.704 |
usa | +1.605 |
Neg logit contributions | |
senal | -6.207 |
leaflets | -6.113 |
Masquerade | -5.892 |
pse | -5.856 |
cffff | -5.848 |
Token | n |
Token ID | 299 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
uble | +1.169 |
outer | +1.157 |
oro | +1.117 |
oster | +1.058 |
TEXTURE | +1.036 |
Neg logit contributions | |
leaflets | -1.270 |
senal | -1.232 |
Masquerade | -1.203 |
pse | -1.173 |
Rollins | -1.167 |
Token | umpy |
Token ID | 32152 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
uble | +1.781 |
outer | +1.751 |
oro | +1.718 |
oster | +1.621 |
olphins | +1.579 |
Neg logit contributions | |
senal | -2.263 |
leaflets | -2.239 |
Masquerade | -2.148 |
pse | -2.101 |
Rollins | -2.061 |
Token | as |
Token ID | 355 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
uble | +0.566 |
outer | +0.560 |
oro | +0.541 |
oster | +0.517 |
olphins | +0.508 |
Neg logit contributions | |
leaflets | -0.488 |
senal | -0.459 |
Masquerade | -0.456 |
pse | -0.447 |
Rollins | -0.440 |
Token | np |
Token ID | 45941 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
uble | +5.463 |
oro | +5.432 |
outer | +5.360 |
oster | +5.072 |
olphins | +5.003 |
Neg logit contributions | |
senal | -5.025 |
leaflets | -4.481 |
Masquerade | -4.421 |
cffff | -4.200 |
anwhile | -4.199 |
Token | import |
Token ID | 1330 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
uble | +1.572 |
outer | +1.550 |
oro | +1.453 |
oster | +1.325 |
olphins | +1.224 |
Neg logit contributions | |
senal | -4.532 |
leaflets | -4.519 |
Masquerade | -4.378 |
cffff | -4.313 |
Rollins | -4.306 |
Token | arg |
Token ID | 1822 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
uble | +1.639 |
outer | +1.617 |
oro | +1.555 |
oster | +1.452 |
olphins | +1.365 |
Neg logit contributions | |
senal | -2.787 |
leaflets | -2.784 |
Masquerade | -2.738 |
cffff | -2.639 |
Rollins | -2.624 |
Token | parse |
Token ID | 29572 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
uble | +2.344 |
outer | +2.326 |
oro | +2.236 |
oster | +2.132 |
olphins | +2.070 |
Neg logit contributions | |
senal | -2.461 |
leaflets | -2.452 |
Masquerade | -2.333 |
pse | -2.274 |
Rollins | -2.259 |
Token | import |
Token ID | 1330 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
uble | +1.296 |
outer | +1.285 |
oro | +1.198 |
oster | +1.094 |
olphins | +1.016 |
Neg logit contributions | |
leaflets | -3.566 |
senal | -3.558 |
Masquerade | -3.432 |
pse | -3.391 |
Rollins | -3.387 |
Token | $ |
Token ID | 720 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
uble | +1.503 |
outer | +1.477 |
oro | +1.439 |
oster | +1.385 |
olphins | +1.360 |
Neg logit contributions | |
leaflets | -1.286 |
senal | -1.231 |
Masquerade | -1.205 |
pse | -1.184 |
Rollins | -1.145 |
Token | 16 |
Token ID | 1433 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
uble | +1.619 |
outer | +1.607 |
oro | +1.544 |
oster | +1.470 |
TEXTURE | +1.449 |
Neg logit contributions | |
leaflets | -1.805 |
senal | -1.797 |
pse | -1.719 |
Masquerade | -1.689 |
cffff | -1.630 |
Token | . |
Token ID | 13 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
leaflets | +0.524 |
senal | +0.498 |
Masquerade | +0.496 |
pse | +0.488 |
Rollins | +0.484 |
Neg logit contributions | |
uble | -0.377 |
outer | -0.373 |
oro | -0.357 |
oster | -0.335 |
TEXTURE | -0.330 |
Token | 25 |
Token ID | 1495 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
uble | +0.266 |
outer | +0.262 |
oro | +0.252 |
oster | +0.241 |
TEXTURE | +0.235 |
Neg logit contributions | |
leaflets | -0.288 |
senal | -0.278 |
Masquerade | -0.270 |
pse | -0.269 |
Rollins | -0.261 |
Token | million |
Token ID | 1510 |
Feature activation | +6.66e-03 |
Pos logit contributions | |
uble | +0.149 |
outer | +0.147 |
oro | +0.141 |
oster | +0.134 |
TEXTURE | +0.131 |
Neg logit contributions | |
leaflets | -0.183 |
senal | -0.174 |
Masquerade | -0.173 |
pse | -0.170 |
Rollins | -0.168 |
Token | contract |
Token ID | 2775 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
uble | +0.027 |
outer | +0.026 |
oro | +0.026 |
oster | +0.025 |
olphins | +0.024 |
Neg logit contributions | |
leaflets | -0.021 |
senal | -0.020 |
Masquerade | -0.020 |
pse | -0.019 |
Rollins | -0.019 |
Token | signed |
Token ID | 4488 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
uble | +4.646 |
outer | +4.508 |
oro | +4.308 |
oster | +4.211 |
olphins | +4.046 |
Neg logit contributions | |
leaflets | -5.641 |
senal | -5.549 |
Masquerade | -5.331 |
pse | -5.221 |
cffff | -5.128 |
Token | in |
Token ID | 287 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
uble | +1.740 |
outer | +1.688 |
oro | +1.648 |
oster | +1.574 |
olphins | +1.547 |
Neg logit contributions | |
leaflets | -1.608 |
senal | -1.576 |
Masquerade | -1.511 |
pse | -1.495 |
Rollins | -1.466 |
Token | February |
Token ID | 3945 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
uble | +1.057 |
outer | +1.037 |
oro | +1.001 |
oster | +0.943 |
olphins | +0.918 |
Neg logit contributions | |
leaflets | -1.499 |
senal | -1.486 |
Masquerade | -1.424 |
pse | -1.417 |
cffff | -1.393 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
uble | +2.935 |
outer | +2.820 |
oro | +2.767 |
oster | +2.618 |
olphins | +2.527 |
Neg logit contributions | |
senal | -4.325 |
leaflets | -4.252 |
pse | -4.100 |
Masquerade | -4.069 |
cffff | -4.016 |
Token |
|
Token ID | 198 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
uble | +0.119 |
outer | +0.118 |
oro | +0.113 |
oster | +0.107 |
olphins | +0.104 |
Neg logit contributions | |
leaflets | -0.153 |
senal | -0.146 |
Masquerade | -0.145 |
pse | -0.143 |
Rollins | -0.141 |
Token | year |
Token ID | 1941 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
outer | +0.469 |
uble | +0.467 |
oro | +0.446 |
oster | +0.425 |
olphins | +0.413 |
Neg logit contributions | |
leaflets | -0.629 |
senal | -0.607 |
Masquerade | -0.596 |
pse | -0.594 |
Rollins | -0.575 |
Token | , |
Token ID | 11 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
uble | +1.570 |
outer | +1.531 |
oro | +1.493 |
oster | +1.417 |
olphins | +1.397 |
Neg logit contributions | |
leaflets | -1.651 |
senal | -1.593 |
Masquerade | -1.557 |
pse | -1.538 |
Rollins | -1.490 |
Token | $ |
Token ID | 720 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
uble | +1.015 |
outer | +0.997 |
oro | +0.971 |
oster | +0.937 |
olphins | +0.919 |
Neg logit contributions | |
leaflets | -0.861 |
senal | -0.833 |
Masquerade | -0.809 |
pse | -0.795 |
Dent | -0.767 |
Token | 72 |
Token ID | 4761 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
uble | +3.623 |
outer | +3.608 |
oro | +3.475 |
oster | +3.314 |
TEXTURE | +3.302 |
Neg logit contributions | |
senal | -3.916 |
leaflets | -3.765 |
pse | -3.685 |
Masquerade | -3.485 |
cffff | -3.389 |
Token | million |
Token ID | 1510 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
leaflets | +0.339 |
senal | +0.320 |
Masquerade | +0.319 |
pse | +0.314 |
Rollins | +0.312 |
Neg logit contributions | |
uble | -0.276 |
outer | -0.274 |
oro | -0.263 |
oster | -0.246 |
TEXTURE | -0.243 |
Token | contract |
Token ID | 2775 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
uble | +1.229 |
outer | +1.206 |
oro | +1.173 |
oster | +1.129 |
olphins | +1.113 |
Neg logit contributions | |
leaflets | -1.092 |
senal | -1.045 |
Masquerade | -1.022 |
pse | -1.006 |
Rollins | -0.977 |
Token | with |
Token ID | 351 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
uble | +4.870 |
outer | +4.736 |
oro | +4.538 |
oster | +4.372 |
olphins | +4.262 |
Neg logit contributions | |
senal | -5.365 |
leaflets | -5.216 |
Masquerade | -4.986 |
pse | -4.865 |
cffff | -4.760 |
Token | $ |
Token ID | 720 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
uble | +0.907 |
outer | +0.900 |
oro | +0.872 |
oster | +0.844 |
olphins | +0.828 |
Neg logit contributions | |
leaflets | -0.774 |
senal | -0.759 |
Masquerade | -0.732 |
pse | -0.720 |
cffff | -0.698 |
Token | 37 |
Token ID | 2718 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
uble | +1.589 |
outer | +1.580 |
oro | +1.521 |
oster | +1.449 |
TEXTURE | +1.429 |
Neg logit contributions | |
leaflets | -1.661 |
senal | -1.645 |
pse | -1.570 |
Masquerade | -1.549 |
cffff | -1.485 |
Token | million |
Token ID | 1510 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
leaflets | +0.426 |
senal | +0.405 |
Masquerade | +0.403 |
pse | +0.396 |
Rollins | +0.392 |
Neg logit contributions | |
uble | -0.327 |
outer | -0.323 |
oro | -0.309 |
oster | -0.292 |
olphins | -0.285 |
Token | guaranteed |
Token ID | 11462 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
uble | +0.195 |
outer | +0.192 |
oro | +0.185 |
oster | +0.178 |
olphins | +0.174 |
Neg logit contributions | |
leaflets | -0.202 |
senal | -0.195 |
Masquerade | -0.191 |
pse | -0.187 |
Dent | -0.183 |
Token | : |
Token ID | 25 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
leaflets | +1.414 |
Masquerade | +1.316 |
senal | +1.276 |
pse | +1.270 |
Dent | +1.265 |
Neg logit contributions | |
uble | -1.783 |
outer | -1.770 |
oro | -1.716 |
oster | -1.636 |
olphins | -1.620 |
Token | http |
Token ID | 2638 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
leaflets | +0.339 |
senal | +0.328 |
Masquerade | +0.326 |
pse | +0.322 |
Rollins | +0.319 |
Neg logit contributions | |
uble | -0.127 |
outer | -0.124 |
oro | -0.115 |
oster | -0.105 |
olphins | -0.101 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
uble | +1.137 |
outer | +1.113 |
oro | +0.979 |
oster | +0.848 |
TEXTURE | +0.765 |
Neg logit contributions | |
senal | -5.688 |
leaflets | -5.590 |
pse | -5.436 |
Masquerade | -5.380 |
cffff | -5.292 |
Token | usat |
Token ID | 37937 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
outer | +2.812 |
uble | +2.807 |
oro | +2.505 |
oster | +2.269 |
usa | +2.229 |
Neg logit contributions | |
leaflets | -8.506 |
senal | -8.469 |
Masquerade | -8.325 |
pse | -8.238 |
Dent | -8.054 |
Token | . |
Token ID | 13 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
uble | +2.531 |
outer | +2.491 |
oro | +2.375 |
oster | +2.225 |
usa | +2.136 |
Neg logit contributions | |
senal | -5.499 |
leaflets | -5.190 |
pse | -5.140 |
Masquerade | -4.949 |
cffff | -4.885 |
Token | ly |
Token ID | 306 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
uble | +1.435 |
outer | +1.394 |
oro | +1.317 |
oster | +1.206 |
olphins | +1.128 |
Neg logit contributions | |
leaflets | -3.708 |
senal | -3.647 |
Masquerade | -3.565 |
pse | -3.536 |
Rollins | -3.482 |
Token | / |
Token ID | 14 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
uble | +2.694 |
outer | +2.573 |
oro | +2.525 |
oster | +2.285 |
TEXTURE | +2.210 |
Neg logit contributions | |
senal | -8.035 |
leaflets | -7.579 |
pse | -7.461 |
anwhile | -7.152 |
cffff | -7.145 |
Token | 1 |
Token ID | 16 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
uble | +1.767 |
outer | +1.750 |
oro | +1.673 |
oster | +1.579 |
TEXTURE | +1.543 |
Neg logit contributions | |
leaflets | -2.321 |
senal | -2.260 |
Masquerade | -2.184 |
pse | -2.157 |
Dent | -2.105 |
Token | G |
Token ID | 38 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
uble | +2.583 |
outer | +2.561 |
oro | +2.479 |
oster | +2.321 |
obe | +2.249 |
Neg logit contributions | |
leaflets | -3.446 |
senal | -3.332 |
Masquerade | -3.261 |
pse | -3.201 |
Dent | -3.160 |
Token | q |
Token ID | 80 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
uble | +1.894 |
outer | +1.881 |
oro | +1.813 |
oster | +1.702 |
obe | +1.641 |
Neg logit contributions | |
leaflets | -2.448 |
senal | -2.349 |
Masquerade | -2.318 |
pse | -2.273 |
Rollins | -2.238 |
Token | FP |
Token ID | 5837 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
uble | +1.740 |
outer | +1.724 |
oro | +1.660 |
oster | +1.568 |
TEXTURE | +1.508 |
Neg logit contributions | |
leaflets | -2.269 |
senal | -2.180 |
Masquerade | -2.151 |
pse | -2.101 |
Rollins | -2.072 |
Token | names |
Token ID | 3891 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
leaflets | +0.245 |
senal | +0.234 |
Masquerade | +0.230 |
pse | +0.224 |
Rollins | +0.221 |
Neg logit contributions | |
uble | -0.322 |
outer | -0.319 |
oro | -0.309 |
oster | -0.297 |
olphins | -0.291 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
uble | +1.034 |
outer | +1.014 |
oro | +0.980 |
oster | +0.940 |
olphins | +0.909 |
Neg logit contributions | |
leaflets | -1.022 |
senal | -1.005 |
Masquerade | -0.968 |
pse | -0.951 |
Rollins | -0.932 |
Token | and |
Token ID | 290 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
leaflets | +0.388 |
senal | +0.375 |
Masquerade | +0.367 |
pse | +0.357 |
Rollins | +0.350 |
Neg logit contributions | |
uble | -0.441 |
outer | -0.433 |
oro | -0.419 |
oster | -0.403 |
TEXTURE | -0.393 |
Token | the |
Token ID | 262 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
leaflets | +0.412 |
senal | +0.397 |
Masquerade | +0.389 |
pse | +0.376 |
Rollins | +0.368 |
Neg logit contributions | |
uble | -0.486 |
outer | -0.480 |
oro | -0.464 |
oster | -0.445 |
TEXTURE | -0.434 |
Token | # |
Token ID | 1303 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
leaflets | +1.147 |
senal | +1.099 |
Masquerade | +1.079 |
pse | +1.053 |
Rollins | +1.035 |
Neg logit contributions | |
uble | -1.357 |
outer | -1.342 |
oro | -1.300 |
oster | -1.240 |
olphins | -1.215 |
Token | Never |
Token ID | 12295 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
uble | +0.275 |
outer | +0.272 |
oro | +0.258 |
oster | +0.238 |
TEXTURE | +0.231 |
Neg logit contributions | |
leaflets | -0.537 |
senal | -0.515 |
Masquerade | -0.512 |
pse | -0.503 |
Rollins | -0.498 |
Token | Trump |
Token ID | 6170 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
outer | +3.293 |
uble | +3.118 |
oro | +3.082 |
oster | +2.992 |
JUST | +2.966 |
Neg logit contributions | |
senal | -6.976 |
leaflets | -6.782 |
pse | -6.701 |
Masquerade | -6.570 |
anwhile | -6.512 |
Token | forces |
Token ID | 3386 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
uble | +1.304 |
outer | +1.288 |
oro | +1.255 |
oster | +1.201 |
olphins | +1.159 |
Neg logit contributions | |
leaflets | -1.173 |
senal | -1.136 |
Masquerade | -1.114 |
pse | -1.090 |
Rollins | -1.066 |
Token | have |
Token ID | 423 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
uble | +0.268 |
outer | +0.265 |
oro | +0.255 |
oster | +0.244 |
olphins | +0.236 |
Neg logit contributions | |
leaflets | -0.302 |
senal | -0.294 |
Masquerade | -0.287 |
pse | -0.281 |
Rollins | -0.277 |
Token | invested |
Token ID | 13356 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
uble | +1.626 |
outer | +1.602 |
oro | +1.547 |
oster | +1.502 |
TEXTURE | +1.441 |
Neg logit contributions | |
senal | -1.472 |
leaflets | -1.447 |
Masquerade | -1.392 |
pse | -1.353 |
cffff | -1.339 |
Token | a |
Token ID | 257 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
uble | +0.668 |
outer | +0.659 |
oro | +0.637 |
oster | +0.615 |
olphins | +0.597 |
Neg logit contributions | |
leaflets | -0.595 |
senal | -0.579 |
Masquerade | -0.564 |
pse | -0.550 |
Rollins | -0.542 |
Token | we |
Token ID | 356 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
leaflets | +0.693 |
senal | +0.652 |
Masquerade | +0.649 |
pse | +0.636 |
Rollins | +0.626 |
Neg logit contributions | |
uble | -0.799 |
outer | -0.791 |
oro | -0.764 |
oster | -0.730 |
olphins | -0.718 |
Token | must |
Token ID | 1276 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
uble | +0.054 |
outer | +0.053 |
oro | +0.051 |
oster | +0.049 |
olphins | +0.047 |
Neg logit contributions | |
leaflets | -0.063 |
senal | -0.060 |
Masquerade | -0.059 |
pse | -0.058 |
Rollins | -0.058 |
Token | win |
Token ID | 1592 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
leaflets | +0.666 |
senal | +0.621 |
Masquerade | +0.619 |
pse | +0.607 |
Rollins | +0.596 |
Neg logit contributions | |
uble | -0.885 |
outer | -0.878 |
oro | -0.851 |
oster | -0.814 |
olphins | -0.804 |
Token | . |
Token ID | 13 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
leaflets | +0.782 |
senal | +0.746 |
Masquerade | +0.742 |
pse | +0.730 |
Rollins | +0.721 |
Neg logit contributions | |
uble | -0.586 |
outer | -0.578 |
oro | -0.554 |
oster | -0.523 |
olphins | -0.511 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
uble | +0.261 |
outer | +0.258 |
oro | +0.248 |
oster | +0.236 |
TEXTURE | +0.230 |
Neg logit contributions | |
leaflets | -0.321 |
senal | -0.311 |
pse | -0.301 |
Masquerade | -0.299 |
cffff | -0.293 |
Token | Mr |
Token ID | 5246 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
leaflets | +0.053 |
senal | +0.050 |
Masquerade | +0.050 |
pse | +0.049 |
Rollins | +0.048 |
Neg logit contributions | |
uble | -0.043 |
outer | -0.043 |
oro | -0.041 |
oster | -0.039 |
TEXTURE | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
uble | +5.012 |
outer | +4.814 |
oro | +4.739 |
oster | +4.467 |
olphins | +4.317 |
Neg logit contributions | |
leaflets | -5.127 |
senal | -4.895 |
pse | -4.818 |
Masquerade | -4.768 |
cffff | -4.655 |
Token | Sel |
Token ID | 15300 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
uble | +3.840 |
outer | +3.774 |
oro | +3.676 |
oster | +3.514 |
olphins | +3.424 |
Neg logit contributions | |
leaflets | -2.987 |
senal | -2.893 |
pse | -2.784 |
Masquerade | -2.723 |
cffff | -2.694 |
Token | z |
Token ID | 89 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
uble | +0.585 |
outer | +0.579 |
oro | +0.555 |
oster | +0.527 |
olphins | +0.513 |
Neg logit contributions | |
leaflets | -0.718 |
senal | -0.687 |
Masquerade | -0.679 |
pse | -0.671 |
Rollins | -0.659 |
Token | nick |
Token ID | 17172 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
uble | +2.347 |
outer | +2.291 |
oro | +2.232 |
oster | +2.077 |
obe | +1.974 |
Neg logit contributions | |
leaflets | -4.200 |
senal | -3.999 |
Masquerade | -3.989 |
pse | -3.914 |
cffff | -3.845 |
Token | was |
Token ID | 373 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
uble | +0.345 |
outer | +0.339 |
oro | +0.329 |
oster | +0.311 |
olphins | +0.304 |
Neg logit contributions | |
leaflets | -0.366 |
senal | -0.351 |
Masquerade | -0.345 |
pse | -0.339 |
Rollins | -0.332 |
Token | his |
Token ID | 465 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
leaflets | +1.888 |
Masquerade | +1.747 |
senal | +1.721 |
Rollins | +1.702 |
pse | +1.698 |
Neg logit contributions | |
uble | -2.581 |
outer | -2.560 |
oro | -2.459 |
oster | -2.341 |
TEXTURE | -2.341 |
Token | current |
Token ID | 1459 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
leaflets | +0.119 |
senal | +0.113 |
Masquerade | +0.111 |
pse | +0.109 |
Rollins | +0.107 |
Neg logit contributions | |
uble | -0.145 |
outer | -0.143 |
oro | -0.139 |
oster | -0.133 |
olphins | -0.131 |
Token | three |
Token ID | 1115 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
uble | +2.516 |
outer | +2.501 |
oro | +2.468 |
oster | +2.344 |
olphins | +2.322 |
Neg logit contributions | |
leaflets | -2.438 |
senal | -2.409 |
Masquerade | -2.286 |
pse | -2.258 |
cffff | -2.189 |
Token | - |
Token ID | 12 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
uble | +1.314 |
outer | +1.302 |
oro | +1.253 |
oster | +1.203 |
olphins | +1.178 |
Neg logit contributions | |
leaflets | -1.494 |
senal | -1.443 |
Masquerade | -1.420 |
pse | -1.395 |
Rollins | -1.370 |
Token | year |
Token ID | 1941 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
uble | +0.203 |
outer | +0.201 |
oro | +0.193 |
oster | +0.183 |
olphins | +0.179 |
Neg logit contributions | |
leaflets | -0.248 |
senal | -0.236 |
Masquerade | -0.234 |
pse | -0.231 |
Rollins | -0.227 |
Token | contract |
Token ID | 2775 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
uble | +1.789 |
outer | +1.751 |
oro | +1.713 |
oster | +1.628 |
olphins | +1.604 |
Neg logit contributions | |
leaflets | -1.805 |
senal | -1.744 |
Masquerade | -1.699 |
pse | -1.679 |
Rollins | -1.625 |
Token | . |
Token ID | 13 |
Feature activation | +3.37e-03 |
Pos logit contributions | |
uble | +4.320 |
outer | +4.244 |
oro | +4.029 |
oster | +3.874 |
olphins | +3.783 |
Neg logit contributions | |
leaflets | -5.763 |
senal | -5.680 |
Masquerade | -5.467 |
pse | -5.284 |
Rollins | -5.254 |
Token | Last |
Token ID | 4586 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
uble | +0.012 |
outer | +0.012 |
oro | +0.011 |
oster | +0.011 |
olphins | +0.010 |
Neg logit contributions | |
leaflets | -0.013 |
senal | -0.012 |
Masquerade | -0.012 |
pse | -0.012 |
Rollins | -0.011 |
Token | year |
Token ID | 614 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
leaflets | +1.074 |
senal | +1.011 |
Masquerade | +1.005 |
pse | +0.985 |
Rollins | +0.969 |
Neg logit contributions | |
uble | -1.269 |
outer | -1.256 |
oro | -1.213 |
oster | -1.161 |
olphins | -1.140 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
leaflets | +0.408 |
senal | +0.388 |
Masquerade | +0.383 |
pse | +0.377 |
Rollins | +0.371 |
Neg logit contributions | |
uble | -0.406 |
outer | -0.400 |
oro | -0.388 |
oster | -0.370 |
olphins | -0.363 |
Token | he |
Token ID | 339 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
uble | +0.821 |
outer | +0.810 |
oro | +0.795 |
oster | +0.762 |
olphins | +0.755 |
Neg logit contributions | |
leaflets | -0.648 |
senal | -0.620 |
Masquerade | -0.601 |
pse | -0.596 |
Rollins | -0.578 |
Token | BR |
Token ID | 11473 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
leaflets | +0.043 |
senal | +0.041 |
Masquerade | +0.040 |
pse | +0.040 |
Rollins | +0.039 |
Neg logit contributions | |
uble | -0.035 |
outer | -0.035 |
oro | -0.033 |
oster | -0.032 |
TEXTURE | -0.031 |
Token | USS |
Token ID | 32835 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
leaflets | +0.812 |
senal | +0.769 |
Masquerade | +0.766 |
pse | +0.751 |
Rollins | +0.742 |
Neg logit contributions | |
uble | -0.755 |
outer | -0.746 |
oro | -0.717 |
oster | -0.683 |
olphins | -0.670 |
Token | ELS |
Token ID | 37142 |
Feature activation | -4.53e-03 |
Pos logit contributions | |
leaflets | +0.331 |
senal | +0.297 |
Masquerade | +0.284 |
pse | +0.277 |
Rollins | +0.258 |
Neg logit contributions | |
uble | -1.202 |
outer | -1.192 |
oro | -1.167 |
oster | -1.133 |
TEXTURE | -1.121 |
Token | ( |
Token ID | 357 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
leaflets | +0.016 |
senal | +0.015 |
Masquerade | +0.015 |
pse | +0.015 |
Rollins | +0.015 |
Neg logit contributions | |
uble | -0.017 |
outer | -0.016 |
oro | -0.016 |
oster | -0.015 |
olphins | -0.015 |
Token | Reuters |
Token ID | 12637 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
leaflets | +1.670 |
Masquerade | +1.549 |
senal | +1.516 |
pse | +1.489 |
Rollins | +1.474 |
Neg logit contributions | |
uble | -2.680 |
outer | -2.620 |
oro | -2.563 |
oster | -2.453 |
olphins | -2.440 |
Token | ) |
Token ID | 8 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
leaflets | +1.777 |
Masquerade | +1.674 |
Dent | +1.632 |
Rollins | +1.629 |
Typh | +1.574 |
Neg logit contributions | |
uble | -2.071 |
outer | -2.055 |
oro | -1.963 |
oster | -1.873 |
olphins | -1.862 |
Token | - |
Token ID | 532 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Masquerade | +4.032 |
leaflets | +3.971 |
Dent | +3.959 |
Rollins | +3.876 |
Typh | +3.795 |
Neg logit contributions | |
uble | -9.944 |
outer | -9.875 |
oro | -9.405 |
ibaba | -9.336 |
obe | -9.183 |
Token | The |
Token ID | 383 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
leaflets | +4.091 |
Masquerade | +3.898 |
Dent | +3.798 |
Rollins | +3.761 |
Typh | +3.752 |
Neg logit contributions | |
uble | -5.277 |
outer | -5.237 |
oro | -5.055 |
oster | -4.839 |
TEXTURE | -4.791 |
Token | world |
Token ID | 995 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
leaflets | +0.906 |
senal | +0.873 |
Masquerade | +0.858 |
pse | +0.845 |
Rollins | +0.830 |
Neg logit contributions | |
uble | -0.836 |
outer | -0.824 |
oro | -0.794 |
oster | -0.751 |
olphins | -0.737 |
Token | � |
Token ID | 447 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
uble | +0.492 |
outer | +0.483 |
oro | +0.465 |
oster | +0.441 |
TEXTURE | +0.429 |
Neg logit contributions | |
leaflets | -0.615 |
senal | -0.593 |
Masquerade | -0.585 |
pse | -0.575 |
Rollins | -0.567 |
Token | � |
Token ID | 247 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
uble | +0.387 |
outer | +0.378 |
oro | +0.362 |
oster | +0.336 |
TEXTURE | +0.326 |
Neg logit contributions | |
leaflets | -0.661 |
senal | -0.639 |
Masquerade | -0.631 |
pse | -0.621 |
Rollins | -0.616 |
Token | HA |
Token ID | 7801 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
uble | +0.048 |
outer | +0.048 |
oro | +0.046 |
oster | +0.043 |
TEXTURE | +0.042 |
Neg logit contributions | |
leaflets | -0.059 |
senal | -0.056 |
Masquerade | -0.056 |
pse | -0.055 |
Rollins | -0.054 |
Token | V |
Token ID | 53 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
uble | +0.135 |
outer | +0.133 |
oro | +0.127 |
oster | +0.121 |
TEXTURE | +0.118 |
Neg logit contributions | |
leaflets | -0.173 |
senal | -0.166 |
Masquerade | -0.163 |
pse | -0.162 |
Rollins | -0.159 |
Token | ANA |
Token ID | 31574 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
uble | +0.076 |
outer | +0.076 |
oro | +0.073 |
oster | +0.069 |
olphins | +0.068 |
Neg logit contributions | |
leaflets | -0.079 |
senal | -0.075 |
Masquerade | -0.075 |
pse | -0.073 |
Rollins | -0.072 |
Token | ( |
Token ID | 357 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
uble | +0.228 |
outer | +0.225 |
oro | +0.218 |
oster | +0.206 |
TEXTURE | +0.203 |
Neg logit contributions | |
leaflets | -0.235 |
senal | -0.224 |
Masquerade | -0.221 |
pse | -0.218 |
Rollins | -0.213 |
Token | Reuters |
Token ID | 12637 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
leaflets | +1.955 |
Masquerade | +1.815 |
senal | +1.802 |
pse | +1.744 |
Rollins | +1.738 |
Neg logit contributions | |
uble | -2.927 |
outer | -2.870 |
oro | -2.789 |
oster | -2.678 |
olphins | -2.646 |
Token | ) |
Token ID | 8 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
leaflets | +1.735 |
Masquerade | +1.636 |
Dent | +1.592 |
Rollins | +1.589 |
pse | +1.539 |
Neg logit contributions | |
uble | -2.011 |
outer | -1.994 |
oro | -1.907 |
oster | -1.820 |
olphins | -1.804 |
Token | - |
Token ID | 532 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Masquerade | +3.992 |
Dent | +3.920 |
leaflets | +3.915 |
Rollins | +3.832 |
Typh | +3.748 |
Neg logit contributions | |
uble | -9.723 |
outer | -9.646 |
oro | -9.171 |
ibaba | -9.086 |
obe | -8.966 |
Token | Latin |
Token ID | 9133 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
leaflets | +3.825 |
Masquerade | +3.646 |
Dent | +3.515 |
Rollins | +3.505 |
senal | +3.462 |
Neg logit contributions | |
uble | -5.144 |
outer | -5.107 |
oro | -4.884 |
oster | -4.692 |
TEXTURE | -4.652 |
Token | American |
Token ID | 1605 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
leaflets | +1.080 |
senal | +1.013 |
Masquerade | +1.007 |
pse | +0.987 |
Rollins | +0.977 |
Neg logit contributions | |
uble | -1.204 |
outer | -1.192 |
oro | -1.148 |
oster | -1.096 |
olphins | -1.079 |
Token | and |
Token ID | 290 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
uble | +0.921 |
outer | +0.910 |
oro | +0.890 |
oster | +0.851 |
olphins | +0.835 |
Neg logit contributions | |
leaflets | -0.657 |
senal | -0.635 |
Masquerade | -0.617 |
pse | -0.602 |
cffff | -0.600 |
Token | Caribbean |
Token ID | 18020 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
leaflets | +0.636 |
Masquerade | +0.604 |
senal | +0.604 |
pse | +0.595 |
Rollins | +0.589 |
Neg logit contributions | |
uble | -0.386 |
outer | -0.381 |
oro | -0.362 |
oster | -0.341 |
TEXTURE | -0.332 |
Token | OT |
Token ID | 2394 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
leaflets | +0.063 |
senal | +0.060 |
Masquerade | +0.060 |
pse | +0.059 |
Rollins | +0.058 |
Neg logit contributions | |
uble | -0.052 |
outer | -0.051 |
oro | -0.049 |
oster | -0.047 |
TEXTURE | -0.046 |
Token | TA |
Token ID | 5603 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
uble | +0.510 |
outer | +0.506 |
oro | +0.491 |
oster | +0.458 |
TEXTURE | +0.439 |
Neg logit contributions | |
leaflets | -0.862 |
senal | -0.831 |
Masquerade | -0.822 |
pse | -0.807 |
Rollins | -0.791 |
Token | WA |
Token ID | 15543 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
leaflets | +1.074 |
senal | +1.044 |
pse | +1.020 |
Masquerade | +0.991 |
cffff | +0.987 |
Neg logit contributions | |
uble | -1.143 |
outer | -1.131 |
oro | -1.105 |
oster | -1.056 |
TEXTURE | -1.044 |
Token | ( |
Token ID | 357 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
leaflets | +1.529 |
senal | +1.443 |
Masquerade | +1.442 |
pse | +1.412 |
Rollins | +1.394 |
Neg logit contributions | |
uble | -1.483 |
outer | -1.467 |
oro | -1.413 |
oster | -1.343 |
olphins | -1.319 |
Token | Reuters |
Token ID | 12637 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
leaflets | +2.091 |
Masquerade | +1.956 |
senal | +1.914 |
Dent | +1.884 |
Rollins | +1.876 |
Neg logit contributions | |
uble | -3.089 |
outer | -3.029 |
oro | -2.948 |
oster | -2.816 |
olphins | -2.808 |
Token | ) |
Token ID | 8 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
leaflets | +1.312 |
Masquerade | +1.235 |
Dent | +1.202 |
Rollins | +1.202 |
pse | +1.168 |
Neg logit contributions | |
uble | -1.499 |
outer | -1.487 |
oro | -1.422 |
oster | -1.357 |
olphins | -1.343 |
Token | - |
Token ID | 532 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Masquerade | +3.860 |
Dent | +3.813 |
leaflets | +3.812 |
Rollins | +3.707 |
Typh | +3.638 |
Neg logit contributions | |
uble | -9.407 |
outer | -9.349 |
oro | -8.893 |
ibaba | -8.771 |
obe | -8.671 |
Token | Canada |
Token ID | 3340 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
leaflets | +3.883 |
Masquerade | +3.735 |
Dent | +3.667 |
Rollins | +3.584 |
Typh | +3.522 |
Neg logit contributions | |
uble | -5.660 |
outer | -5.612 |
oro | -5.382 |
oster | -5.183 |
olphins | -5.115 |
Token | � |
Token ID | 447 |
Feature activation | +5.61e-03 |
Pos logit contributions | |
leaflets | +3.015 |
senal | +2.834 |
Masquerade | +2.831 |
pse | +2.792 |
Dent | +2.764 |
Neg logit contributions | |
uble | -2.621 |
outer | -2.604 |
oro | -2.495 |
oster | -2.373 |
olphins | -2.326 |
Token | � |
Token ID | 247 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
uble | +0.016 |
outer | +0.015 |
oro | +0.015 |
oster | +0.014 |
olphins | +0.013 |
Neg logit contributions | |
leaflets | -0.025 |
senal | -0.024 |
Masquerade | -0.024 |
pse | -0.023 |
Rollins | -0.023 |
Token | s |
Token ID | 82 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
uble | +0.894 |
outer | +0.884 |
oro | +0.852 |
oster | +0.807 |
olphins | +0.790 |
Neg logit contributions | |
leaflets | -0.969 |
senal | -0.926 |
Masquerade | -0.919 |
pse | -0.898 |
Rollins | -0.890 |
Token | ITED |
Token ID | 22061 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
uble | +1.962 |
outer | +1.922 |
oro | +1.872 |
oster | +1.759 |
TEXTURE | +1.737 |
Neg logit contributions | |
leaflets | -2.646 |
senal | -2.571 |
Masquerade | -2.517 |
pse | -2.476 |
Rollins | -2.440 |
Token | N |
Token ID | 399 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
leaflets | +0.511 |
senal | +0.478 |
Masquerade | +0.477 |
pse | +0.466 |
Rollins | +0.460 |
Neg logit contributions | |
uble | -0.651 |
outer | -0.645 |
oro | -0.623 |
oster | -0.597 |
olphins | -0.588 |
Token | ATIONS |
Token ID | 18421 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
uble | +0.460 |
outer | +0.454 |
oro | +0.440 |
oster | +0.423 |
olphins | +0.415 |
Neg logit contributions | |
leaflets | -0.367 |
senal | -0.348 |
Masquerade | -0.342 |
pse | -0.338 |
Rollins | -0.331 |
Token | ( |
Token ID | 357 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
leaflets | +1.012 |
senal | +0.950 |
Masquerade | +0.949 |
pse | +0.929 |
Rollins | +0.915 |
Neg logit contributions | |
uble | -1.101 |
outer | -1.089 |
oro | -1.050 |
oster | -1.004 |
olphins | -0.985 |
Token | Reuters |
Token ID | 12637 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
leaflets | +2.005 |
Masquerade | +1.867 |
senal | +1.813 |
Rollins | +1.795 |
Dent | +1.784 |
Neg logit contributions | |
uble | -3.068 |
outer | -3.004 |
oro | -2.917 |
oster | -2.794 |
olphins | -2.773 |
Token | ) |
Token ID | 8 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
leaflets | +1.668 |
Masquerade | +1.566 |
Dent | +1.526 |
Rollins | +1.526 |
pse | +1.488 |
Neg logit contributions | |
uble | -1.918 |
outer | -1.903 |
oro | -1.820 |
oster | -1.733 |
olphins | -1.723 |
Token | - |
Token ID | 532 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Masquerade | +3.836 |
leaflets | +3.752 |
Dent | +3.741 |
Rollins | +3.640 |
Typh | +3.552 |
Neg logit contributions | |
uble | -9.143 |
outer | -9.059 |
oro | -8.649 |
ibaba | -8.620 |
obe | -8.465 |
Token | An |
Token ID | 1052 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
leaflets | +4.020 |
Masquerade | +3.832 |
Dent | +3.735 |
Rollins | +3.718 |
Typh | +3.649 |
Neg logit contributions | |
uble | -5.282 |
outer | -5.226 |
oro | -5.012 |
oster | -4.813 |
TEXTURE | -4.745 |
Token | army |
Token ID | 5428 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
leaflets | +2.167 |
Masquerade | +1.995 |
senal | +1.990 |
pse | +1.961 |
Rollins | +1.929 |
Neg logit contributions | |
uble | -2.634 |
outer | -2.600 |
oro | -2.502 |
oster | -2.419 |
TEXTURE | -2.385 |
Token | battalion |
Token ID | 36328 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
uble | +0.700 |
outer | +0.695 |
oro | +0.673 |
oster | +0.647 |
olphins | +0.630 |
Neg logit contributions | |
leaflets | -0.574 |
senal | -0.554 |
Masquerade | -0.545 |
pse | -0.530 |
cffff | -0.521 |
Token | in |
Token ID | 287 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
leaflets | +1.016 |
senal | +0.947 |
Masquerade | +0.944 |
pse | +0.925 |
Rollins | +0.910 |
Neg logit contributions | |
uble | -1.287 |
outer | -1.274 |
oro | -1.231 |
oster | -1.180 |
olphins | -1.162 |
Token | ONG |
Token ID | 18494 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
leaflets | +0.969 |
senal | +0.905 |
Masquerade | +0.898 |
pse | +0.882 |
Rollins | +0.867 |
Neg logit contributions | |
uble | -1.240 |
outer | -1.220 |
oro | -1.182 |
oster | -1.132 |
olphins | -1.114 |
Token | K |
Token ID | 509 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
leaflets | +2.197 |
Rollins | +2.054 |
Dent | +2.035 |
Masquerade | +2.024 |
senal | +1.996 |
Neg logit contributions | |
uble | -2.715 |
outer | -2.589 |
oro | -2.459 |
oster | -2.431 |
olphins | -2.403 |
Token | ONG |
Token ID | 18494 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
uble | +0.473 |
outer | +0.469 |
oro | +0.456 |
oster | +0.439 |
olphins | +0.431 |
Neg logit contributions | |
leaflets | -0.289 |
senal | -0.273 |
Masquerade | -0.267 |
pse | -0.263 |
Rollins | -0.255 |
Token | ( |
Token ID | 357 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
leaflets | +3.115 |
Masquerade | +2.927 |
senal | +2.855 |
Dent | +2.849 |
Rollins | +2.819 |
Neg logit contributions | |
uble | -3.462 |
outer | -3.439 |
oro | -3.238 |
oster | -3.129 |
olphins | -3.054 |
Token | Reuters |
Token ID | 12637 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
leaflets | +1.080 |
Masquerade | +0.995 |
senal | +0.989 |
pse | +0.963 |
Rollins | +0.953 |
Neg logit contributions | |
uble | -1.657 |
outer | -1.631 |
oro | -1.586 |
oster | -1.521 |
olphins | -1.504 |
Token | ) |
Token ID | 8 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
leaflets | +1.169 |
Masquerade | +1.104 |
Dent | +1.072 |
Rollins | +1.070 |
senal | +1.040 |
Neg logit contributions | |
uble | -1.338 |
outer | -1.321 |
oro | -1.270 |
oster | -1.207 |
olphins | -1.194 |
Token | - |
Token ID | 532 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Masquerade | +3.774 |
Dent | +3.697 |
leaflets | +3.621 |
Rollins | +3.545 |
Typh | +3.469 |
Neg logit contributions | |
uble | -8.963 |
outer | -8.859 |
ibaba | -8.458 |
oro | -8.391 |
obe | -8.186 |
Token | One |
Token ID | 1881 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
leaflets | +3.929 |
Masquerade | +3.717 |
Dent | +3.636 |
Rollins | +3.578 |
senal | +3.554 |
Neg logit contributions | |
uble | -4.868 |
outer | -4.795 |
oro | -4.582 |
oster | -4.404 |
TEXTURE | -4.378 |
Token | needs |
Token ID | 2476 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
uble | +0.426 |
outer | +0.420 |
oro | +0.410 |
oster | +0.391 |
olphins | +0.384 |
Neg logit contributions | |
leaflets | -0.360 |
senal | -0.348 |
Masquerade | -0.340 |
pse | -0.332 |
Rollins | -0.327 |
Token | to |
Token ID | 284 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
uble | +1.214 |
outer | +1.184 |
oro | +1.156 |
oster | +1.104 |
olphins | +1.078 |
Neg logit contributions | |
leaflets | -1.252 |
senal | -1.212 |
Masquerade | -1.197 |
pse | -1.164 |
Rollins | -1.154 |
Token | look |
Token ID | 804 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
leaflets | +1.300 |
Masquerade | +1.213 |
senal | +1.208 |
pse | +1.197 |
Rollins | +1.172 |
Neg logit contributions | |
uble | -1.476 |
outer | -1.461 |
oro | -1.411 |
oster | -1.346 |
TEXTURE | -1.328 |
Token | a |
Token ID | 257 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
uble | +0.732 |
outer | +0.725 |
oro | +0.704 |
oster | +0.671 |
olphins | +0.657 |
Neg logit contributions | |
leaflets | -0.638 |
senal | -0.608 |
Masquerade | -0.598 |
pse | -0.589 |
Dent | -0.574 |
Token | fighter |
Token ID | 10543 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
uble | +0.635 |
outer | +0.633 |
oro | +0.613 |
oster | +0.589 |
olphins | +0.577 |
Neg logit contributions | |
leaflets | -0.424 |
senal | -0.398 |
Masquerade | -0.389 |
pse | -0.377 |
Rollins | -0.373 |
Token | . |
Token ID | 13 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
leaflets | +1.241 |
Masquerade | +1.175 |
senal | +1.175 |
pse | +1.154 |
Rollins | +1.141 |
Neg logit contributions | |
uble | -1.061 |
outer | -1.047 |
oro | -1.006 |
oster | -0.951 |
olphins | -0.938 |
Token | As |
Token ID | 1081 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
uble | +0.748 |
outer | +0.740 |
oro | +0.715 |
oster | +0.678 |
olphins | +0.658 |
Neg logit contributions | |
leaflets | -0.933 |
senal | -0.901 |
pse | -0.877 |
Masquerade | -0.873 |
cffff | -0.850 |
Token | they |
Token ID | 484 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
leaflets | +0.711 |
senal | +0.673 |
Masquerade | +0.668 |
pse | +0.655 |
Rollins | +0.644 |
Neg logit contributions | |
uble | -0.768 |
outer | -0.760 |
oro | -0.734 |
oster | -0.700 |
olphins | -0.687 |
Token | say |
Token ID | 910 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
uble | +0.239 |
outer | +0.237 |
oro | +0.229 |
oster | +0.219 |
TEXTURE | +0.213 |
Neg logit contributions | |
leaflets | -0.219 |
senal | -0.209 |
Masquerade | -0.206 |
pse | -0.202 |
Rollins | -0.199 |
Token | , |
Token ID | 11 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
leaflets | +5.674 |
Masquerade | +5.276 |
pse | +5.137 |
senal | +5.118 |
Dent | +5.078 |
Neg logit contributions | |
outer | -6.878 |
uble | -6.868 |
oro | -6.554 |
TEXTURE | -6.314 |
oster | -6.307 |
Token | nothing |
Token ID | 2147 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
leaflets | +2.440 |
Masquerade | +2.275 |
senal | +2.263 |
pse | +2.238 |
Rollins | +2.195 |
Neg logit contributions | |
uble | -2.803 |
outer | -2.776 |
oro | -2.669 |
oster | -2.552 |
olphins | -2.529 |
Token | is |
Token ID | 318 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
uble | +1.277 |
outer | +1.261 |
oro | +1.216 |
oster | +1.152 |
TEXTURE | +1.117 |
Neg logit contributions | |
leaflets | -1.604 |
senal | -1.560 |
Masquerade | -1.514 |
pse | -1.497 |
Rollins | -1.475 |
Token | more |
Token ID | 517 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
uble | +1.575 |
outer | +1.564 |
oro | +1.506 |
oster | +1.442 |
olphins | +1.392 |
Neg logit contributions | |
leaflets | -1.554 |
senal | -1.491 |
Masquerade | -1.453 |
pse | -1.429 |
Rollins | -1.406 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
uble | +1.321 |
outer | +1.307 |
oro | +1.263 |
oster | +1.194 |
TEXTURE | +1.168 |
Neg logit contributions | |
leaflets | -1.561 |
senal | -1.506 |
Masquerade | -1.467 |
pse | -1.456 |
Rollins | -1.429 |
Token | ote |
Token ID | 1258 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
outer | +1.803 |
uble | +1.789 |
oro | +1.729 |
oster | +1.615 |
obe | +1.516 |
Neg logit contributions | |
leaflets | -3.213 |
senal | -3.192 |
Masquerade | -3.117 |
pse | -3.065 |
Rollins | -3.007 |
Token | ( |
Token ID | 357 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
leaflets | +1.074 |
senal | +1.009 |
Masquerade | +1.008 |
pse | +0.984 |
Rollins | +0.977 |
Neg logit contributions | |
uble | -1.270 |
outer | -1.261 |
oro | -1.215 |
oster | -1.164 |
TEXTURE | -1.151 |
Token | O |
Token ID | 46 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
uble | +0.039 |
outer | +0.039 |
oro | +0.037 |
oster | +0.035 |
TEXTURE | +0.034 |
Neg logit contributions | |
leaflets | -0.048 |
senal | -0.045 |
Masquerade | -0.045 |
pse | -0.044 |
Rollins | -0.044 |
Token | mega |
Token ID | 13731 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
leaflets | +0.843 |
senal | +0.805 |
Masquerade | +0.802 |
pse | +0.787 |
Rollins | +0.777 |
Neg logit contributions | |
uble | -0.642 |
outer | -0.632 |
oro | -0.603 |
oster | -0.572 |
olphins | -0.565 |
Token | Pharma |
Token ID | 41845 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
leaflets | +3.215 |
Masquerade | +3.005 |
Dent | +2.988 |
Rollins | +2.974 |
pse | +2.918 |
Neg logit contributions | |
uble | -3.051 |
outer | -3.041 |
oro | -2.861 |
oster | -2.755 |
TEXTURE | -2.700 |
Token | - |
Token ID | 532 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
leaflets | +3.572 |
Masquerade | +3.376 |
Dent | +3.331 |
Rollins | +3.198 |
Typh | +3.163 |
Neg logit contributions | |
uble | -5.785 |
outer | -5.764 |
oro | -5.396 |
olphins | -5.272 |
oster | -5.227 |
Token | Quick |
Token ID | 12029 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
Masquerade | +3.216 |
leaflets | +3.167 |
Dent | +3.036 |
Rollins | +2.977 |
Typh | +2.816 |
Neg logit contributions | |
uble | -8.795 |
outer | -8.746 |
oro | -8.496 |
olphins | -8.368 |
oster | -8.291 |
Token | step |
Token ID | 9662 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
leaflets | +2.139 |
Masquerade | +1.970 |
pse | +1.936 |
Rollins | +1.927 |
als | +1.898 |
Neg logit contributions | |
uble | -3.044 |
outer | -2.960 |
oro | -2.910 |
olphins | -2.809 |
oster | -2.782 |
Token | ) |
Token ID | 8 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
leaflets | +1.032 |
Masquerade | +0.968 |
Rollins | +0.942 |
Dent | +0.938 |
senal | +0.924 |
Neg logit contributions | |
uble | -1.130 |
outer | -1.119 |
oro | -1.076 |
oster | -1.029 |
olphins | -1.017 |
Token | s |
Token ID | 264 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
leaflets | +0.972 |
senal | +0.917 |
Masquerade | +0.911 |
pse | +0.896 |
Rollins | +0.882 |
Neg logit contributions | |
uble | -1.106 |
outer | -1.096 |
oro | -1.056 |
oster | -1.011 |
olphins | -0.994 |
Token | . |
Token ID | 13 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
leaflets | +1.105 |
Masquerade | +1.044 |
Rollins | +1.030 |
Dent | +1.024 |
als | +1.020 |
Neg logit contributions | |
uble | -0.843 |
outer | -0.829 |
oro | -0.789 |
oster | -0.748 |
olphins | -0.745 |
Token | country |
Token ID | 1499 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
outer | +2.644 |
uble | +2.629 |
oro | +2.547 |
oster | +2.413 |
obe | +2.347 |
Neg logit contributions | |
leaflets | -2.560 |
senal | -2.524 |
Masquerade | -2.413 |
pse | -2.349 |
Rollins | -2.323 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
leaflets | +0.827 |
senal | +0.789 |
Masquerade | +0.785 |
pse | +0.773 |
Rollins | +0.763 |
Neg logit contributions | |
uble | -0.598 |
outer | -0.590 |
oro | -0.564 |
oster | -0.533 |
olphins | -0.520 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
uble | +0.430 |
outer | +0.426 |
oro | +0.410 |
oster | +0.386 |
olphins | +0.378 |
Neg logit contributions | |
leaflets | -0.582 |
senal | -0.559 |
Masquerade | -0.548 |
pse | -0.546 |
Rollins | -0.533 |
Token |
|
Token ID | 198 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
uble | +0.347 |
outer | +0.343 |
oro | +0.328 |
oster | +0.310 |
olphins | +0.303 |
Neg logit contributions | |
leaflets | -0.458 |
senal | -0.439 |
Masquerade | -0.434 |
pse | -0.428 |
Rollins | -0.421 |
Token | Read |
Token ID | 5569 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
uble | +0.264 |
outer | +0.262 |
oro | +0.252 |
oster | +0.238 |
TEXTURE | +0.233 |
Neg logit contributions | |
leaflets | -0.316 |
senal | -0.304 |
Masquerade | -0.298 |
pse | -0.295 |
Rollins | -0.289 |
Token | full |
Token ID | 1336 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
leaflets | +1.336 |
senal | +1.244 |
Masquerade | +1.237 |
pse | +1.215 |
Rollins | +1.205 |
Neg logit contributions | |
uble | -1.578 |
outer | -1.556 |
oro | -1.506 |
oster | -1.446 |
TEXTURE | -1.437 |
Token | story |
Token ID | 1621 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
leaflets | +2.206 |
Story | +1.663 |
Dent | +1.655 |
Rollins | +1.647 |
Masquerade | +1.612 |
Neg logit contributions | |
uble | -9.524 |
outer | -9.470 |
oro | -9.099 |
oster | -9.040 |
TEXTURE | -9.008 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
leaflets | +3.699 |
Masquerade | +3.499 |
senal | +3.466 |
Dent | +3.418 |
pse | +3.410 |
Neg logit contributions | |
uble | -2.586 |
outer | -2.567 |
oro | -2.413 |
oster | -2.267 |
TEXTURE | -2.234 |
Token | Asia |
Token ID | 38555 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
leaflets | +0.152 |
senal | +0.145 |
Masquerade | +0.143 |
pse | +0.141 |
Rollins | +0.139 |
Neg logit contributions | |
uble | -0.124 |
outer | -0.123 |
oro | -0.118 |
oster | -0.112 |
TEXTURE | -0.109 |
Token | Health |
Token ID | 3893 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
leaflets | +0.193 |
senal | +0.184 |
Masquerade | +0.182 |
pse | +0.179 |
Rollins | +0.176 |
Neg logit contributions | |
uble | -0.180 |
outer | -0.178 |
oro | -0.172 |
oster | -0.163 |
olphins | -0.160 |
Token | Correspond |
Token ID | 34428 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
leaflets | +2.374 |
Masquerade | +2.222 |
senal | +2.214 |
pse | +2.176 |
Rollins | +2.157 |
Neg logit contributions | |
uble | -2.573 |
outer | -2.533 |
oro | -2.436 |
oster | -2.327 |
olphins | -2.297 |
Token | . |
Token ID | 13 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
leaflets | +1.958 |
Masquerade | +1.846 |
senal | +1.814 |
pse | +1.805 |
Rollins | +1.785 |
Neg logit contributions | |
uble | -2.208 |
outer | -2.178 |
oro | -2.100 |
oster | -2.004 |
olphins | -1.985 |
Token | ( |
Token ID | 357 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
leaflets | +0.742 |
senal | +0.703 |
Masquerade | +0.693 |
pse | +0.684 |
Rollins | +0.668 |
Neg logit contributions | |
uble | -0.818 |
outer | -0.809 |
oro | -0.782 |
oster | -0.747 |
olphins | -0.733 |
Token | Photo |
Token ID | 6191 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
leaflets | +1.074 |
senal | +1.014 |
Masquerade | +1.005 |
pse | +0.988 |
Rollins | +0.970 |
Neg logit contributions | |
uble | -1.207 |
outer | -1.195 |
oro | -1.154 |
oster | -1.103 |
olphins | -1.082 |
Token | by |
Token ID | 416 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
leaflets | +0.963 |
senal | +0.904 |
Masquerade | +0.899 |
pse | +0.879 |
Rollins | +0.864 |
Neg logit contributions | |
uble | -1.296 |
outer | -1.284 |
oro | -1.242 |
oster | -1.189 |
olphins | -1.172 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
leaflets | +0.565 |
senal | +0.533 |
Masquerade | +0.528 |
pse | +0.518 |
Rollins | +0.509 |
Neg logit contributions | |
uble | -0.679 |
outer | -0.672 |
oro | -0.650 |
oster | -0.622 |
olphins | -0.611 |
Token | / |
Token ID | 14 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
leaflets | +1.806 |
Masquerade | +1.738 |
Rollins | +1.700 |
Dent | +1.696 |
Typh | +1.662 |
Neg logit contributions | |
uble | -1.068 |
outer | -1.050 |
oro | -0.990 |
oster | -0.922 |
olphins | -0.909 |
Token | Car |
Token ID | 9914 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
leaflets | +5.414 |
Masquerade | +5.316 |
Rollins | +5.169 |
Dent | +5.113 |
als | +5.039 |
Neg logit contributions | |
uble | -5.973 |
outer | -5.776 |
oro | -5.556 |
ibaba | -5.526 |
olphins | -5.338 |
Token | lo |
Token ID | 5439 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
leaflets | +1.510 |
senal | +1.432 |
Masquerade | +1.431 |
Rollins | +1.398 |
pse | +1.393 |
Neg logit contributions | |
uble | -1.271 |
outer | -1.249 |
oro | -1.204 |
oster | -1.133 |
TEXTURE | -1.121 |
Token | Alleg |
Token ID | 26326 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
leaflets | +0.859 |
senal | +0.807 |
Masquerade | +0.792 |
pse | +0.780 |
Rollins | +0.754 |
Neg logit contributions | |
uble | -1.334 |
outer | -1.320 |
oro | -1.288 |
oster | -1.240 |
olphins | -1.219 |
Token | ri |
Token ID | 380 |
Feature activation | -2.87e-03 |
Pos logit contributions | |
uble | +0.086 |
outer | +0.085 |
oro | +0.080 |
TEXTURE | +0.077 |
olphins | +0.076 |
Neg logit contributions | |
leaflets | -0.090 |
Masquerade | -0.084 |
senal | -0.083 |
Rollins | -0.082 |
pse | -0.082 |
Token | ) |
Token ID | 8 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
leaflets | +0.011 |
senal | +0.011 |
Masquerade | +0.011 |
pse | +0.011 |
Rollins | +0.010 |
Neg logit contributions | |
uble | -0.009 |
outer | -0.009 |
oro | -0.009 |
oster | -0.008 |
olphins | -0.008 |
Token | k |
Token ID | 74 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
uble | +0.707 |
outer | +0.693 |
oro | +0.674 |
oster | +0.644 |
usa | +0.610 |
Neg logit contributions | |
leaflets | -1.011 |
senal | -0.978 |
Masquerade | -0.968 |
pse | -0.959 |
cffff | -0.929 |
Token | ( |
Token ID | 357 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
uble | +0.192 |
outer | +0.189 |
oro | +0.184 |
oster | +0.175 |
olphins | +0.171 |
Neg logit contributions | |
leaflets | -0.176 |
senal | -0.166 |
Masquerade | -0.165 |
pse | -0.162 |
Rollins | -0.159 |
Token | O |
Token ID | 46 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
outer | +0.820 |
uble | +0.816 |
oro | +0.786 |
oster | +0.740 |
TEXTURE | +0.733 |
Neg logit contributions | |
leaflets | -1.082 |
senal | -1.049 |
pse | -1.026 |
Masquerade | -1.011 |
cffff | -0.998 |
Token | mega |
Token ID | 13731 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
leaflets | +0.102 |
senal | +0.097 |
Masquerade | +0.097 |
pse | +0.095 |
Rollins | +0.094 |
Neg logit contributions | |
uble | -0.087 |
outer | -0.086 |
oro | -0.083 |
oster | -0.079 |
olphins | -0.077 |
Token | Pharma |
Token ID | 41845 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
leaflets | +3.134 |
Masquerade | +2.935 |
Dent | +2.902 |
Rollins | +2.898 |
senal | +2.868 |
Neg logit contributions | |
uble | -2.923 |
outer | -2.917 |
oro | -2.760 |
oster | -2.641 |
TEXTURE | -2.606 |
Token | - |
Token ID | 532 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
leaflets | +3.393 |
Masquerade | +3.169 |
Dent | +3.140 |
Rollins | +3.039 |
senal | +3.036 |
Neg logit contributions | |
uble | -5.440 |
outer | -5.435 |
oro | -5.093 |
olphins | -4.972 |
TEXTURE | -4.936 |
Token | Quick |
Token ID | 12029 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
leaflets | +3.213 |
Masquerade | +3.151 |
Dent | +3.004 |
Rollins | +2.967 |
Typh | +2.818 |
Neg logit contributions | |
uble | -8.198 |
outer | -8.120 |
oro | -7.857 |
olphins | -7.713 |
oster | -7.623 |
Token | step |
Token ID | 9662 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
leaflets | +1.876 |
Masquerade | +1.740 |
pse | +1.707 |
Rollins | +1.696 |
Dent | +1.675 |
Neg logit contributions | |
uble | -2.512 |
outer | -2.459 |
oro | -2.401 |
olphins | -2.299 |
oster | -2.295 |
Token | ) |
Token ID | 8 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
leaflets | +1.029 |
Masquerade | +0.965 |
Rollins | +0.938 |
Dent | +0.934 |
senal | +0.931 |
Neg logit contributions | |
uble | -1.111 |
outer | -1.100 |
oro | -1.058 |
oster | -1.012 |
olphins | -0.999 |
Token | s |
Token ID | 264 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
leaflets | +0.825 |
senal | +0.779 |
Masquerade | +0.773 |
pse | +0.759 |
Rollins | +0.747 |
Neg logit contributions | |
uble | -0.919 |
outer | -0.910 |
oro | -0.878 |
oster | -0.839 |
olphins | -0.824 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
leaflets | +1.102 |
Masquerade | +1.041 |
Rollins | +1.027 |
Dent | +1.022 |
als | +1.017 |
Neg logit contributions | |
uble | -0.838 |
outer | -0.825 |
oro | -0.785 |
oster | -0.744 |
olphins | -0.741 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
leaflets | +0.213 |
senal | +0.204 |
Masquerade | +0.202 |
pse | +0.198 |
Rollins | +0.195 |
Neg logit contributions | |
uble | -0.198 |
outer | -0.196 |
oro | -0.189 |
oster | -0.180 |
olphins | -0.175 |
Token | ( |
Token ID | 357 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
leaflets | +0.415 |
senal | +0.397 |
Masquerade | +0.386 |
pse | +0.385 |
cffff | +0.373 |
Neg logit contributions | |
uble | -0.462 |
outer | -0.456 |
oro | -0.442 |
oster | -0.422 |
olphins | -0.414 |
Token | Photo |
Token ID | 6191 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
leaflets | +1.033 |
senal | +0.973 |
Masquerade | +0.964 |
pse | +0.946 |
Rollins | +0.929 |
Neg logit contributions | |
uble | -1.260 |
outer | -1.247 |
oro | -1.206 |
oster | -1.155 |
olphins | -1.134 |
Token | by |
Token ID | 416 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
leaflets | +0.989 |
senal | +0.927 |
Masquerade | +0.924 |
pse | +0.902 |
Rollins | +0.888 |
Neg logit contributions | |
uble | -1.352 |
outer | -1.341 |
oro | -1.298 |
oster | -1.241 |
olphins | -1.225 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
leaflets | +0.769 |
senal | +0.724 |
Masquerade | +0.719 |
pse | +0.704 |
Rollins | +0.693 |
Neg logit contributions | |
uble | -0.928 |
outer | -0.919 |
oro | -0.888 |
oster | -0.850 |
olphins | -0.836 |
Token | / |
Token ID | 14 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
leaflets | +1.713 |
Masquerade | +1.649 |
Rollins | +1.612 |
Dent | +1.610 |
Typh | +1.577 |
Neg logit contributions | |
uble | -1.016 |
outer | -1.000 |
oro | -0.942 |
oster | -0.880 |
olphins | -0.867 |
Token | Gary |
Token ID | 33820 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
leaflets | +5.080 |
Masquerade | +4.967 |
Rollins | +4.820 |
Dent | +4.805 |
als | +4.692 |
Neg logit contributions | |
uble | -6.116 |
outer | -5.962 |
oro | -5.743 |
ibaba | -5.675 |
olphins | -5.515 |
Token | Cameron |
Token ID | 10821 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
leaflets | +1.541 |
Masquerade | +1.471 |
senal | +1.446 |
Rollins | +1.446 |
Dent | +1.432 |
Neg logit contributions | |
uble | -1.289 |
outer | -1.272 |
oro | -1.223 |
oster | -1.149 |
olphins | -1.128 |
Token | / |
Token ID | 14 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
leaflets | +3.105 |
Masquerade | +2.983 |
senal | +2.924 |
Dent | +2.908 |
Rollins | +2.891 |
Neg logit contributions | |
uble | -2.892 |
outer | -2.859 |
oro | -2.707 |
oster | -2.569 |
TEXTURE | -2.545 |
Token | File |
Token ID | 8979 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
leaflets | +1.458 |
Masquerade | +1.377 |
senal | +1.376 |
pse | +1.340 |
Rollins | +1.333 |
Neg logit contributions | |
uble | -1.502 |
outer | -1.483 |
oro | -1.428 |
oster | -1.359 |
olphins | -1.340 |
Token | photo |
Token ID | 4590 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
uble | +0.840 |
outer | +0.832 |
oro | +0.814 |
oster | +0.784 |
olphins | +0.772 |
Neg logit contributions | |
leaflets | -0.513 |
senal | -0.480 |
Masquerade | -0.469 |
pse | -0.467 |
Rollins | -0.449 |
Token | Ryan |
Token ID | 6047 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
uble | +0.239 |
outer | +0.236 |
oro | +0.229 |
oster | +0.219 |
olphins | +0.214 |
Neg logit contributions | |
leaflets | -0.204 |
senal | -0.194 |
Masquerade | -0.190 |
pse | -0.188 |
Rollins | -0.183 |
Token | , |
Token ID | 11 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
uble | +0.065 |
outer | +0.064 |
oro | +0.062 |
oster | +0.059 |
olphins | +0.058 |
Neg logit contributions | |
leaflets | -0.061 |
senal | -0.058 |
Masquerade | -0.057 |
pse | -0.056 |
Rollins | -0.055 |
Token | who |
Token ID | 508 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
uble | +0.228 |
outer | +0.226 |
oro | +0.218 |
oster | +0.209 |
olphins | +0.205 |
Neg logit contributions | |
leaflets | -0.190 |
senal | -0.180 |
Masquerade | -0.177 |
pse | -0.173 |
Rollins | -0.170 |
Token | was |
Token ID | 373 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
uble | +0.511 |
outer | +0.502 |
oro | +0.485 |
oster | +0.459 |
olphins | +0.449 |
Neg logit contributions | |
leaflets | -0.602 |
senal | -0.579 |
Masquerade | -0.571 |
pse | -0.561 |
Rollins | -0.552 |
Token | em |
Token ID | 795 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
uble | +0.860 |
outer | +0.847 |
oro | +0.822 |
oster | +0.787 |
TEXTURE | +0.771 |
Neg logit contributions | |
leaflets | -0.675 |
senal | -0.640 |
Masquerade | -0.627 |
pse | -0.616 |
Rollins | -0.597 |
Token | ce |
Token ID | 344 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
uble | +2.513 |
outer | +2.503 |
oro | +2.371 |
oster | +2.237 |
obe | +2.210 |
Neg logit contributions | |
leaflets | -2.951 |
senal | -2.796 |
pse | -2.785 |
Masquerade | -2.763 |
Rollins | -2.675 |
Token | e |
Token ID | 68 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
leaflets | +5.275 |
Masquerade | +5.072 |
Rollins | +4.892 |
Dent | +4.814 |
als | +4.804 |
Neg logit contributions | |
uble | -5.847 |
outer | -5.668 |
oro | -5.539 |
olphins | -5.465 |
TEXTURE | -5.409 |
Token | ing |
Token ID | 278 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
uble | +0.458 |
outer | +0.450 |
oro | +0.436 |
oster | +0.416 |
olphins | +0.404 |
Neg logit contributions | |
leaflets | -0.450 |
senal | -0.430 |
Masquerade | -0.422 |
pse | -0.415 |
Rollins | -0.407 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
leaflets | +1.192 |
senal | +1.119 |
Masquerade | +1.116 |
pse | +1.092 |
Rollins | +1.079 |
Neg logit contributions | |
uble | -1.390 |
outer | -1.378 |
oro | -1.330 |
oster | -1.273 |
olphins | -1.250 |
Token | program |
Token ID | 1430 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
uble | +0.011 |
outer | +0.011 |
oro | +0.011 |
oster | +0.010 |
olphins | +0.010 |
Neg logit contributions | |
leaflets | -0.009 |
senal | -0.009 |
Masquerade | -0.009 |
pse | -0.009 |
cffff | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -5.11e-04 |
Pos logit contributions | |
leaflets | +0.155 |
senal | +0.148 |
Masquerade | +0.145 |
pse | +0.143 |
Rollins | +0.140 |
Neg logit contributions | |
uble | -0.161 |
outer | -0.159 |
oro | -0.154 |
oster | -0.147 |
olphins | -0.144 |
Token | " |
Token ID | 1 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
uble | +0.422 |
outer | +0.419 |
oro | +0.403 |
oster | +0.381 |
TEXTURE | +0.375 |
Neg logit contributions | |
leaflets | -0.494 |
senal | -0.476 |
Masquerade | -0.465 |
pse | -0.461 |
Rollins | -0.450 |
Token | As |
Token ID | 1722 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
leaflets | +0.746 |
senal | +0.708 |
Masquerade | +0.708 |
pse | +0.694 |
Rollins | +0.687 |
Neg logit contributions | |
uble | -0.592 |
outer | -0.584 |
oro | -0.560 |
oster | -0.530 |
olphins | -0.519 |
Token | you |
Token ID | 345 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
leaflets | +1.247 |
senal | +1.167 |
Masquerade | +1.164 |
pse | +1.141 |
Rollins | +1.123 |
Neg logit contributions | |
uble | -1.495 |
outer | -1.482 |
oro | -1.427 |
oster | -1.368 |
olphins | -1.347 |
Token | may |
Token ID | 743 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
leaflets | +0.405 |
senal | +0.387 |
Masquerade | +0.382 |
pse | +0.374 |
Rollins | +0.369 |
Neg logit contributions | |
uble | -0.397 |
outer | -0.393 |
oro | -0.379 |
oster | -0.361 |
olphins | -0.354 |
Token | have |
Token ID | 423 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
leaflets | +3.423 |
Masquerade | +3.112 |
pse | +3.101 |
Rollins | +3.025 |
Dent | +3.007 |
Neg logit contributions | |
uble | -3.977 |
outer | -3.935 |
oro | -3.778 |
TEXTURE | -3.647 |
oster | -3.580 |
Token | heard |
Token ID | 2982 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
leaflets | +2.623 |
Masquerade | +2.421 |
pse | +2.416 |
Rollins | +2.378 |
Dent | +2.344 |
Neg logit contributions | |
uble | -2.731 |
outer | -2.706 |
oro | -2.583 |
TEXTURE | -2.469 |
oster | -2.455 |
Token | , |
Token ID | 11 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
leaflets | +4.841 |
Masquerade | +4.432 |
Rollins | +4.329 |
pse | +4.324 |
Dent | +4.301 |
Neg logit contributions | |
outer | -6.322 |
uble | -6.252 |
oro | -5.972 |
olphins | -5.743 |
oster | -5.697 |
Token | Winter |
Token ID | 10633 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
leaflets | +1.255 |
Masquerade | +1.171 |
senal | +1.170 |
pse | +1.145 |
Rollins | +1.128 |
Neg logit contributions | |
uble | -1.527 |
outer | -1.513 |
oro | -1.461 |
oster | -1.400 |
olphins | -1.379 |
Token | ke |
Token ID | 365 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
uble | +0.443 |
outer | +0.438 |
oro | +0.422 |
oster | +0.405 |
olphins | +0.396 |
Neg logit contributions | |
leaflets | -0.382 |
senal | -0.365 |
Masquerade | -0.357 |
pse | -0.353 |
Rollins | -0.346 |
Token | wl |
Token ID | 40989 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
uble | +0.703 |
outer | +0.694 |
oro | +0.662 |
oster | +0.624 |
olphins | +0.609 |
Neg logit contributions | |
leaflets | -1.031 |
senal | -0.993 |
Masquerade | -0.982 |
pse | -0.969 |
Rollins | -0.955 |
Token | Games |
Token ID | 5776 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
uble | +0.073 |
outer | +0.072 |
oro | +0.069 |
oster | +0.065 |
olphins | +0.064 |
Neg logit contributions | |
leaflets | -0.086 |
senal | -0.082 |
Masquerade | -0.082 |
pse | -0.080 |
Rollins | -0.079 |
Token | could |
Token ID | 714 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
leaflets | +0.211 |
senal | +0.205 |
Masquerade | +0.201 |
pse | +0.196 |
Rollins | +0.195 |
Neg logit contributions | |
uble | -0.176 |
outer | -0.172 |
oro | -0.166 |
oster | -0.159 |
olphins | -0.154 |
Token | name |
Token ID | 1438 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
leaflets | +0.560 |
senal | +0.536 |
Masquerade | +0.529 |
pse | +0.518 |
Rollins | +0.511 |
Neg logit contributions | |
uble | -0.545 |
outer | -0.538 |
oro | -0.518 |
oster | -0.495 |
olphins | -0.484 |
Token | . |
Token ID | 13 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
uble | +0.372 |
outer | +0.364 |
oro | +0.353 |
oster | +0.339 |
olphins | +0.328 |
Neg logit contributions | |
leaflets | -0.362 |
senal | -0.350 |
Masquerade | -0.342 |
pse | -0.335 |
Rollins | -0.327 |
Token | The |
Token ID | 383 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
uble | +0.186 |
outer | +0.184 |
oro | +0.179 |
oster | +0.171 |
=~ | +0.166 |
Neg logit contributions | |
leaflets | -0.181 |
senal | -0.175 |
pse | -0.169 |
Masquerade | -0.167 |
cffff | -0.165 |
Token | g |
Token ID | 308 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
leaflets | +0.385 |
senal | +0.370 |
Masquerade | +0.361 |
pse | +0.352 |
Rollins | +0.346 |
Neg logit contributions | |
uble | -0.457 |
outer | -0.452 |
oro | -0.436 |
oster | -0.418 |
TEXTURE | -0.409 |
Token | reg |
Token ID | 2301 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
leaflets | +1.710 |
senal | +1.608 |
Masquerade | +1.601 |
pse | +1.569 |
Rollins | +1.550 |
Neg logit contributions | |
uble | -1.835 |
outer | -1.815 |
oro | -1.751 |
oster | -1.672 |
TEXTURE | -1.644 |
Token | arious |
Token ID | 27129 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
leaflets | +3.675 |
Masquerade | +3.439 |
als | +3.334 |
Dent | +3.205 |
Rollins | +3.179 |
Neg logit contributions | |
outer | -7.231 |
uble | -7.190 |
oro | -6.828 |
olphins | -6.819 |
TEXTURE | -6.735 |
Token | Massachusetts |
Token ID | 10140 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
leaflets | +0.896 |
senal | +0.855 |
Masquerade | +0.840 |
pse | +0.821 |
Rollins | +0.807 |
Neg logit contributions | |
uble | -1.033 |
outer | -1.022 |
oro | -0.986 |
oster | -0.944 |
olphins | -0.924 |
Token | pol |
Token ID | 755 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
leaflets | +0.134 |
senal | +0.128 |
Masquerade | +0.126 |
pse | +0.123 |
Rollins | +0.121 |
Neg logit contributions | |
uble | -0.171 |
outer | -0.169 |
oro | -0.164 |
oster | -0.157 |
olphins | -0.154 |
Token | , |
Token ID | 11 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
uble | +1.182 |
outer | +1.167 |
oro | +1.127 |
oster | +1.078 |
olphins | +1.041 |
Neg logit contributions | |
leaflets | -1.189 |
senal | -1.144 |
Masquerade | -1.118 |
pse | -1.089 |
Rollins | -1.067 |
Token | House |
Token ID | 2097 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
leaflets | +0.086 |
senal | +0.082 |
Masquerade | +0.081 |
pse | +0.079 |
Rollins | +0.077 |
Neg logit contributions | |
uble | -0.109 |
outer | -0.107 |
oro | -0.104 |
oster | -0.099 |
olphins | -0.097 |
Token | request |
Token ID | 2581 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
uble | +0.592 |
outer | +0.584 |
oro | +0.561 |
oster | +0.535 |
olphins | +0.517 |
Neg logit contributions | |
leaflets | -0.714 |
senal | -0.698 |
Masquerade | -0.677 |
pse | -0.668 |
Rollins | -0.659 |
Token | stamp |
Token ID | 17977 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
uble | +1.748 |
outer | +1.727 |
oro | +1.683 |
oster | +1.601 |
TEXTURE | +1.551 |
Neg logit contributions | |
leaflets | -1.660 |
senal | -1.637 |
Masquerade | -1.572 |
pse | -1.545 |
cffff | -1.531 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
outer | +0.964 |
uble | +0.963 |
oro | +0.936 |
oster | +0.899 |
obe | +0.870 |
Neg logit contributions | |
leaflets | -0.865 |
senal | -0.836 |
Masquerade | -0.824 |
pse | -0.799 |
cffff | -0.796 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
leaflets | +0.728 |
senal | +0.692 |
Masquerade | +0.687 |
pse | +0.676 |
Rollins | +0.665 |
Neg logit contributions | |
uble | -0.653 |
outer | -0.646 |
oro | -0.621 |
oster | -0.590 |
olphins | -0.578 |
Token | ED |
Token ID | 1961 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
leaflets | +0.580 |
senal | +0.552 |
Masquerade | +0.549 |
pse | +0.540 |
Rollins | +0.532 |
Neg logit contributions | |
uble | -0.476 |
outer | -0.470 |
oro | -0.451 |
oster | -0.428 |
olphins | -0.418 |
Token | MON |
Token ID | 27857 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
leaflets | +0.235 |
senal | +0.222 |
Masquerade | +0.221 |
pse | +0.217 |
Dent | +0.212 |
Neg logit contributions | |
uble | -0.241 |
outer | -0.238 |
oro | -0.230 |
oster | -0.218 |
TEXTURE | -0.215 |
Token | TON |
Token ID | 11357 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
leaflets | +4.771 |
Dent | +4.624 |
Masquerade | +4.563 |
Rollins | +4.436 |
pse | +4.387 |
Neg logit contributions | |
uble | -6.175 |
outer | -5.756 |
oro | -5.746 |
olphins | -5.549 |
ibaba | -5.502 |
Token | – |
Token ID | 784 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
leaflets | +2.603 |
Masquerade | +2.461 |
senal | +2.433 |
pse | +2.387 |
Dent | +2.382 |
Neg logit contributions | |
uble | -2.452 |
outer | -2.425 |
oro | -2.315 |
oster | -2.205 |
olphins | -2.163 |
Token | Omar |
Token ID | 24980 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
leaflets | +4.222 |
Masquerade | +4.053 |
Dent | +3.982 |
Rollins | +3.947 |
Typh | +3.824 |
Neg logit contributions | |
uble | -5.380 |
outer | -5.327 |
oro | -5.101 |
oster | -4.866 |
TEXTURE | -4.822 |
Token | Kh |
Token ID | 5311 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
leaflets | +1.241 |
Masquerade | +1.154 |
senal | +1.149 |
Rollins | +1.113 |
Dent | +1.110 |
Neg logit contributions | |
uble | -1.815 |
outer | -1.804 |
oro | -1.733 |
oster | -1.672 |
olphins | -1.654 |
Token | adr |
Token ID | 41909 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
leaflets | +1.429 |
Masquerade | +1.362 |
senal | +1.352 |
pse | +1.334 |
Rollins | +1.318 |
Neg logit contributions | |
uble | -0.768 |
outer | -0.763 |
oro | -0.716 |
oster | -0.673 |
TEXTURE | -0.660 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
uble | +1.698 |
outer | +1.674 |
oro | +1.646 |
oster | +1.561 |
olphins | +1.521 |
Neg logit contributions | |
leaflets | -1.914 |
senal | -1.908 |
pse | -1.822 |
cffff | -1.793 |
Masquerade | -1.791 |
Token | Metro |
Token ID | 45141 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
uble | +0.427 |
outer | +0.425 |
oro | +0.406 |
oster | +0.384 |
TEXTURE | +0.378 |
Neg logit contributions | |
leaflets | -0.523 |
senal | -0.502 |
Masquerade | -0.493 |
pse | -0.488 |
Rollins | -0.478 |
Token | Manila |
Token ID | 31721 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
leaflets | +0.459 |
senal | +0.434 |
Masquerade | +0.431 |
pse | +0.423 |
Rollins | +0.416 |
Neg logit contributions | |
uble | -0.497 |
outer | -0.491 |
oro | -0.476 |
oster | -0.453 |
olphins | -0.445 |
Token | ( |
Token ID | 357 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
leaflets | +3.889 |
Masquerade | +3.624 |
senal | +3.582 |
Dent | +3.582 |
pse | +3.502 |
Neg logit contributions | |
uble | -4.708 |
outer | -4.659 |
oro | -4.408 |
oster | -4.286 |
TEXTURE | -4.239 |
Token | CNN |
Token ID | 18474 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
leaflets | +1.042 |
Masquerade | +0.920 |
senal | +0.919 |
pse | +0.878 |
Rollins | +0.857 |
Neg logit contributions | |
uble | -3.066 |
outer | -3.024 |
oro | -2.948 |
oster | -2.869 |
TEXTURE | -2.834 |
Token | Philippines |
Token ID | 13316 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
leaflets | +2.553 |
Masquerade | +2.369 |
senal | +2.331 |
Dent | +2.312 |
Rollins | +2.272 |
Neg logit contributions | |
uble | -3.604 |
outer | -3.565 |
oro | -3.393 |
oster | -3.260 |
olphins | -3.232 |
Token | ) |
Token ID | 8 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
leaflets | +4.618 |
Dent | +4.156 |
senal | +4.147 |
pse | +4.131 |
Masquerade | +4.112 |
Neg logit contributions | |
uble | -6.068 |
outer | -5.990 |
oro | -5.570 |
oster | -5.480 |
TEXTURE | -5.437 |
Token | — |
Token ID | 851 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
leaflets | +3.747 |
Masquerade | +3.608 |
Dent | +3.532 |
Rollins | +3.502 |
senal | +3.489 |
Neg logit contributions | |
uble | -3.908 |
outer | -3.829 |
oro | -3.643 |
oster | -3.484 |
TEXTURE | -3.457 |
Token | A |
Token ID | 317 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
leaflets | +2.320 |
Masquerade | +2.190 |
senal | +2.154 |
Rollins | +2.122 |
Dent | +2.122 |
Neg logit contributions | |
uble | -2.715 |
outer | -2.677 |
oro | -2.572 |
oster | -2.468 |
TEXTURE | -2.433 |
Token | " |
Token ID | 366 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
leaflets | +1.318 |
senal | +1.228 |
Masquerade | +1.226 |
pse | +1.204 |
Rollins | +1.186 |
Neg logit contributions | |
uble | -1.586 |
outer | -1.570 |
oro | -1.515 |
oster | -1.451 |
TEXTURE | -1.430 |
Token | special |
Token ID | 20887 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
outer | +0.548 |
uble | +0.546 |
oro | +0.523 |
oster | +0.492 |
TEXTURE | +0.481 |
Neg logit contributions | |
leaflets | -0.698 |
senal | -0.664 |
Masquerade | -0.659 |
pse | -0.651 |
Rollins | -0.640 |
Token | a |
Token ID | 257 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
leaflets | +0.542 |
senal | +0.514 |
Masquerade | +0.506 |
pse | +0.496 |
Rollins | +0.487 |
Neg logit contributions | |
uble | -0.671 |
outer | -0.665 |
oro | -0.642 |
oster | -0.615 |
olphins | -0.606 |
Token | model |
Token ID | 2746 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
leaflets | +0.174 |
senal | +0.165 |
Masquerade | +0.163 |
pse | +0.159 |
Rollins | +0.157 |
Neg logit contributions | |
uble | -0.194 |
outer | -0.192 |
oro | -0.186 |
oster | -0.178 |
olphins | -0.174 |
Token | ine |
Token ID | 500 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
leaflets | +0.040 |
senal | +0.037 |
Masquerade | +0.036 |
pse | +0.036 |
Rollins | +0.035 |
Neg logit contributions | |
uble | -0.071 |
outer | -0.070 |
oro | -0.068 |
oster | -0.066 |
olphins | -0.065 |
Token | only |
Token ID | 691 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
leaflets | +0.886 |
senal | +0.836 |
Masquerade | +0.831 |
pse | +0.816 |
Rollins | +0.803 |
Neg logit contributions | |
uble | -0.953 |
outer | -0.942 |
oro | -0.910 |
oster | -0.868 |
olphins | -0.853 |
Token | for |
Token ID | 329 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
leaflets | +2.197 |
senal | +2.060 |
Masquerade | +2.054 |
pse | +2.019 |
Rollins | +1.986 |
Neg logit contributions | |
uble | -2.412 |
outer | -2.389 |
oro | -2.308 |
oster | -2.206 |
TEXTURE | -2.163 |
Token | Vim |
Token ID | 36645 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
leaflets | +1.649 |
Masquerade | +1.533 |
senal | +1.531 |
pse | +1.499 |
Rollins | +1.475 |
Neg logit contributions | |
uble | -2.176 |
outer | -2.151 |
oro | -2.082 |
oster | -2.001 |
TEXTURE | -1.963 |
Token | 6 |
Token ID | 718 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
leaflets | +4.471 |
Masquerade | +4.096 |
senal | +4.057 |
pse | +4.007 |
Rollins | +3.983 |
Neg logit contributions | |
uble | -6.104 |
outer | -6.017 |
oro | -5.761 |
oster | -5.634 |
ibaba | -5.578 |
Token | . |
Token ID | 13 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
leaflets | +2.781 |
senal | +2.637 |
Masquerade | +2.633 |
pse | +2.586 |
Rollins | +2.560 |
Neg logit contributions | |
uble | -2.011 |
outer | -1.984 |
oro | -1.907 |
oster | -1.795 |
TEXTURE | -1.774 |
Token | 0 |
Token ID | 15 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
leaflets | +1.847 |
Masquerade | +1.753 |
senal | +1.748 |
pse | +1.713 |
Rollins | +1.695 |
Neg logit contributions | |
uble | -1.534 |
outer | -1.511 |
oro | -1.454 |
oster | -1.382 |
olphins | -1.354 |
Token | and |
Token ID | 290 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
leaflets | +0.914 |
senal | +0.868 |
Masquerade | +0.859 |
pse | +0.843 |
Rollins | +0.830 |
Neg logit contributions | |
uble | -0.955 |
outer | -0.944 |
oro | -0.910 |
oster | -0.868 |
olphins | -0.852 |
Token | later |
Token ID | 1568 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
leaflets | +0.166 |
senal | +0.158 |
Masquerade | +0.155 |
pse | +0.152 |
Rollins | +0.149 |
Neg logit contributions | |
uble | -0.226 |
outer | -0.224 |
oro | -0.217 |
oster | -0.208 |
olphins | -0.205 |
Token | cameras |
Token ID | 9073 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
leaflets | +0.541 |
senal | +0.513 |
Masquerade | +0.505 |
pse | +0.493 |
Rollins | +0.486 |
Neg logit contributions | |
uble | -0.699 |
outer | -0.694 |
oro | -0.671 |
oster | -0.643 |
olphins | -0.631 |
Token | being |
Token ID | 852 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
leaflets | +0.513 |
senal | +0.485 |
Masquerade | +0.482 |
pse | +0.473 |
Rollins | +0.466 |
Neg logit contributions | |
uble | -0.538 |
outer | -0.532 |
oro | -0.513 |
oster | -0.489 |
olphins | -0.481 |
Token | defective |
Token ID | 32129 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
uble | +0.849 |
outer | +0.841 |
oro | +0.813 |
oster | +0.784 |
TEXTURE | +0.767 |
Neg logit contributions | |
leaflets | -0.692 |
senal | -0.662 |
Masquerade | -0.648 |
pse | -0.628 |
Rollins | -0.623 |
Token | ( |
Token ID | 357 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
leaflets | +1.444 |
Masquerade | +1.352 |
senal | +1.348 |
pse | +1.327 |
Rollins | +1.302 |
Neg logit contributions | |
uble | -1.615 |
outer | -1.604 |
oro | -1.545 |
oster | -1.475 |
olphins | -1.457 |
Token | cons |
Token ID | 5936 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
outer | +0.526 |
uble | +0.525 |
oro | +0.500 |
oster | +0.472 |
TEXTURE | +0.460 |
Neg logit contributions | |
leaflets | -0.745 |
senal | -0.715 |
Masquerade | -0.705 |
pse | -0.695 |
Rollins | -0.686 |
Token | ist |
Token ID | 396 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
leaflets | +0.610 |
senal | +0.585 |
Masquerade | +0.581 |
pse | +0.572 |
Rollins | +0.565 |
Neg logit contributions | |
uble | -0.396 |
outer | -0.390 |
oro | -0.372 |
oster | -0.351 |
olphins | -0.340 |
Token | ently |
Token ID | 1473 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
leaflets | +5.027 |
senal | +4.818 |
Masquerade | +4.704 |
Dent | +4.695 |
pse | +4.677 |
Neg logit contributions | |
outer | -5.316 |
uble | -5.274 |
oro | -5.017 |
TEXTURE | -4.939 |
olphins | -4.851 |
Token | front |
Token ID | 2166 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
leaflets | +1.516 |
senal | +1.422 |
Masquerade | +1.419 |
pse | +1.398 |
Rollins | +1.375 |
Neg logit contributions | |
uble | -1.678 |
outer | -1.660 |
oro | -1.604 |
oster | -1.527 |
olphins | -1.511 |
Token | - |
Token ID | 12 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
leaflets | +2.516 |
Masquerade | +2.342 |
senal | +2.337 |
pse | +2.308 |
Rollins | +2.271 |
Neg logit contributions | |
uble | -2.602 |
outer | -2.570 |
oro | -2.489 |
olphins | -2.360 |
oster | -2.354 |
Token | f |
Token ID | 69 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
leaflets | +0.511 |
senal | +0.484 |
Masquerade | +0.483 |
pse | +0.474 |
Rollins | +0.468 |
Neg logit contributions | |
uble | -0.452 |
outer | -0.444 |
oro | -0.428 |
oster | -0.407 |
olphins | -0.400 |
Token | ocusing |
Token ID | 45743 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
leaflets | +1.565 |
Masquerade | +1.477 |
senal | +1.454 |
Rollins | +1.454 |
pse | +1.451 |
Neg logit contributions | |
uble | -1.347 |
outer | -1.327 |
oro | -1.297 |
TEXTURE | -1.214 |
olphins | -1.205 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
leaflets | +0.839 |
senal | +0.799 |
Masquerade | +0.796 |
pse | +0.783 |
Rollins | +0.775 |
Neg logit contributions | |
uble | -0.602 |
outer | -0.595 |
oro | -0.568 |
oster | -0.536 |
olphins | -0.524 |
Token | ( |
Token ID | 357 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
leaflets | +0.419 |
senal | +0.399 |
Masquerade | +0.392 |
pse | +0.387 |
Rollins | +0.377 |
Neg logit contributions | |
uble | -0.450 |
outer | -0.445 |
oro | -0.430 |
oster | -0.411 |
olphins | -0.403 |
Token | Photo |
Token ID | 6191 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
leaflets | +0.835 |
senal | +0.794 |
Masquerade | +0.789 |
pse | +0.775 |
Rollins | +0.765 |
Neg logit contributions | |
uble | -0.735 |
outer | -0.726 |
oro | -0.698 |
oster | -0.662 |
olphins | -0.649 |
Token | by |
Token ID | 416 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
leaflets | +0.880 |
senal | +0.827 |
Masquerade | +0.821 |
pse | +0.804 |
Rollins | +0.790 |
Neg logit contributions | |
uble | -1.129 |
outer | -1.118 |
oro | -1.081 |
oster | -1.036 |
olphins | -1.019 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
uble | +0.045 |
outer | +0.045 |
oro | +0.043 |
oster | +0.042 |
olphins | +0.041 |
Neg logit contributions | |
leaflets | -0.037 |
senal | -0.035 |
Masquerade | -0.035 |
pse | -0.034 |
Rollins | -0.033 |
Token | / |
Token ID | 14 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
leaflets | +0.955 |
Masquerade | +0.911 |
senal | +0.909 |
pse | +0.894 |
Rollins | +0.888 |
Neg logit contributions | |
uble | -0.584 |
outer | -0.573 |
oro | -0.545 |
oster | -0.509 |
olphins | -0.498 |
Token | John |
Token ID | 7554 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
leaflets | +4.801 |
Masquerade | +4.690 |
Rollins | +4.550 |
Dent | +4.480 |
Typh | +4.403 |
Neg logit contributions | |
uble | -5.483 |
outer | -5.376 |
oro | -5.090 |
ibaba | -5.054 |
olphins | -4.918 |
Token | S |
Token ID | 311 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
leaflets | +0.846 |
Masquerade | +0.778 |
Rollins | +0.768 |
Dent | +0.757 |
senal | +0.751 |
Neg logit contributions | |
uble | -1.754 |
outer | -1.749 |
oro | -1.697 |
olphins | -1.630 |
TEXTURE | -1.625 |
Token | omm |
Token ID | 2002 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
leaflets | +2.120 |
Rollins | +1.987 |
Masquerade | +1.977 |
senal | +1.960 |
Dent | +1.936 |
Neg logit contributions | |
uble | -2.241 |
outer | -2.181 |
oro | -2.108 |
TEXTURE | -2.046 |
olphins | -2.021 |
Token | ers |
Token ID | 364 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
uble | +0.075 |
outer | +0.074 |
oro | +0.072 |
oster | +0.069 |
olphins | +0.067 |
Neg logit contributions | |
leaflets | -0.055 |
senal | -0.052 |
Masquerade | -0.051 |
pse | -0.050 |
Rollins | -0.048 |
Token | II |
Token ID | 2873 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
uble | +1.667 |
outer | +1.649 |
oro | +1.619 |
oster | +1.528 |
olphins | +1.461 |
Neg logit contributions | |
leaflets | -2.039 |
senal | -1.967 |
pse | -1.913 |
Masquerade | -1.908 |
cffff | -1.852 |
Token | an |
Token ID | 281 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
uble | +1.159 |
outer | +1.142 |
oro | +1.118 |
oster | +1.066 |
olphins | +1.054 |
Neg logit contributions | |
leaflets | -0.958 |
senal | -0.918 |
Masquerade | -0.891 |
pse | -0.877 |
cffff | -0.860 |
Token | Amber |
Token ID | 21896 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
uble | +1.076 |
outer | +1.071 |
oro | +1.038 |
oster | +0.982 |
olphins | +0.965 |
Neg logit contributions | |
leaflets | -1.018 |
senal | -0.971 |
Masquerade | -0.948 |
pse | -0.933 |
Rollins | -0.919 |
Token | Rose |
Token ID | 8049 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
leaflets | +0.637 |
senal | +0.602 |
Masquerade | +0.598 |
pse | +0.586 |
Rollins | +0.578 |
Neg logit contributions | |
uble | -0.694 |
outer | -0.687 |
oro | -0.663 |
oster | -0.633 |
olphins | -0.622 |
Token | - |
Token ID | 12 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
leaflets | +0.582 |
senal | +0.551 |
Masquerade | +0.547 |
pse | +0.537 |
Rollins | +0.529 |
Neg logit contributions | |
uble | -0.588 |
outer | -0.582 |
oro | -0.561 |
oster | -0.535 |
olphins | -0.524 |
Token | re |
Token ID | 260 |
Feature activation | -8.72e-02 |
Pos logit contributions | |
leaflets | +1.057 |
senal | +1.015 |
Masquerade | +1.010 |
pse | +0.996 |
Rollins | +0.986 |
Neg logit contributions | |
uble | -0.542 |
outer | -0.533 |
oro | -0.505 |
oster | -0.469 |
olphins | -0.455 |
Token | min |
Token ID | 1084 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
leaflets | +0.330 |
senal | +0.315 |
Masquerade | +0.310 |
pse | +0.306 |
Dent | +0.300 |
Neg logit contributions | |
uble | -0.302 |
outer | -0.298 |
oro | -0.286 |
oster | -0.274 |
olphins | -0.265 |
Token | is |
Token ID | 271 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
leaflets | +5.764 |
Masquerade | +5.609 |
als | +5.492 |
Rollins | +5.403 |
Dent | +5.372 |
Neg logit contributions | |
outer | -4.425 |
uble | -4.354 |
oro | -4.209 |
TEXTURE | -4.113 |
oster | -4.011 |
Token | cent |
Token ID | 1087 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
leaflets | +1.259 |
Masquerade | +1.165 |
senal | +1.162 |
pse | +1.144 |
Dent | +1.112 |
Neg logit contributions | |
uble | -2.182 |
outer | -2.179 |
oro | -2.107 |
oster | -2.034 |
olphins | -2.015 |
Token | voice |
Token ID | 3809 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
leaflets | +2.466 |
Masquerade | +2.340 |
senal | +2.322 |
pse | +2.293 |
Dent | +2.259 |
Neg logit contributions | |
uble | -2.740 |
outer | -2.719 |
oro | -2.607 |
oster | -2.497 |
olphins | -2.463 |
Token | actress |
Token ID | 14549 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
uble | +0.309 |
outer | +0.305 |
oro | +0.294 |
oster | +0.280 |
olphins | +0.274 |
Neg logit contributions | |
leaflets | -0.315 |
senal | -0.298 |
Masquerade | -0.296 |
pse | -0.290 |
Rollins | -0.286 |
Token | to |
Token ID | 284 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
leaflets | +0.299 |
senal | +0.284 |
Masquerade | +0.282 |
pse | +0.277 |
Rollins | +0.272 |
Neg logit contributions | |
uble | -0.290 |
outer | -0.286 |
oro | -0.276 |
oster | -0.262 |
olphins | -0.257 |
Token | em |
Token ID | 368 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
uble | +0.120 |
outer | +0.118 |
oro | +0.114 |
oster | +0.110 |
olphins | +0.108 |
Neg logit contributions | |
leaflets | -0.091 |
senal | -0.085 |
Masquerade | -0.085 |
pse | -0.083 |
Rollins | -0.082 |
Token | ruining |
Token ID | 39842 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
uble | +1.798 |
outer | +1.736 |
oro | +1.713 |
oster | +1.613 |
obe | +1.574 |
Neg logit contributions | |
leaflets | -2.247 |
senal | -2.149 |
Masquerade | -2.124 |
pse | -2.096 |
Rollins | -2.068 |
Token | your |
Token ID | 534 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
uble | +0.452 |
outer | +0.446 |
oro | +0.433 |
oster | +0.414 |
olphins | +0.406 |
Neg logit contributions | |
leaflets | -0.376 |
senal | -0.358 |
Masquerade | -0.351 |
pse | -0.346 |
Rollins | -0.339 |
Token | attempt |
Token ID | 2230 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
leaflets | +1.142 |
Masquerade | +1.074 |
senal | +1.068 |
pse | +1.048 |
Rollins | +1.033 |
Neg logit contributions | |
uble | -1.285 |
outer | -1.273 |
oro | -1.226 |
oster | -1.173 |
olphins | -1.155 |
Token | to |
Token ID | 284 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
leaflets | +1.668 |
senal | +1.580 |
Masquerade | +1.579 |
pse | +1.547 |
Rollins | +1.526 |
Neg logit contributions | |
uble | -1.465 |
outer | -1.460 |
oro | -1.392 |
oster | -1.330 |
olphins | -1.308 |
Token | tape |
Token ID | 9154 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
leaflets | +0.707 |
Masquerade | +0.664 |
senal | +0.662 |
pse | +0.652 |
Rollins | +0.642 |
Neg logit contributions | |
uble | -0.736 |
outer | -0.730 |
oro | -0.704 |
oster | -0.672 |
olphins | -0.660 |
Token | record |
Token ID | 1700 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
uble | +3.749 |
outer | +3.707 |
oro | +3.605 |
oster | +3.412 |
fashion | +3.374 |
Neg logit contributions | |
leaflets | -3.538 |
senal | -3.503 |
Masquerade | -3.339 |
pse | -3.330 |
cffff | -3.226 |
Token | the |
Token ID | 262 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
uble | +2.014 |
outer | +1.979 |
oro | +1.928 |
oster | +1.834 |
olphins | +1.794 |
Neg logit contributions | |
leaflets | -1.881 |
senal | -1.833 |
Masquerade | -1.779 |
pse | -1.758 |
Dent | -1.708 |
Token | first |
Token ID | 717 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
uble | +0.304 |
outer | +0.301 |
oro | +0.291 |
oster | +0.278 |
olphins | +0.273 |
Neg logit contributions | |
leaflets | -0.250 |
senal | -0.238 |
Masquerade | -0.233 |
pse | -0.229 |
Rollins | -0.225 |
Token | Western |
Token ID | 4885 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
leaflets | +0.383 |
senal | +0.361 |
Masquerade | +0.359 |
pse | +0.352 |
Rollins | +0.346 |
Neg logit contributions | |
uble | -0.445 |
outer | -0.441 |
oro | -0.426 |
oster | -0.407 |
olphins | -0.400 |
Token | song |
Token ID | 3496 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
uble | +0.413 |
outer | +0.409 |
oro | +0.395 |
oster | +0.377 |
olphins | +0.371 |
Neg logit contributions | |
leaflets | -0.371 |
senal | -0.351 |
Masquerade | -0.347 |
pse | -0.341 |
Rollins | -0.335 |
Token | s |
Token ID | 82 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
leaflets | +1.055 |
senal | +0.998 |
Masquerade | +0.996 |
pse | +0.977 |
Rollins | +0.963 |
Neg logit contributions | |
uble | -0.988 |
outer | -0.980 |
oro | -0.941 |
oster | -0.896 |
olphins | -0.879 |
Token | books |
Token ID | 3835 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
uble | +0.627 |
outer | +0.620 |
oro | +0.601 |
oster | +0.576 |
olphins | +0.565 |
Neg logit contributions | |
leaflets | -0.483 |
senal | -0.460 |
Masquerade | -0.448 |
pse | -0.442 |
Rollins | -0.434 |
Token | take |
Token ID | 1011 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
uble | +1.603 |
outer | +1.573 |
oro | +1.525 |
oster | +1.453 |
olphins | +1.416 |
Neg logit contributions | |
leaflets | -1.713 |
senal | -1.660 |
Masquerade | -1.608 |
pse | -1.590 |
Rollins | -1.574 |
Token | the |
Token ID | 262 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
uble | +0.756 |
outer | +0.747 |
oro | +0.724 |
oster | +0.692 |
olphins | +0.677 |
Neg logit contributions | |
leaflets | -0.666 |
senal | -0.644 |
Masquerade | -0.627 |
pse | -0.616 |
Rollins | -0.606 |
Token | reader |
Token ID | 9173 |
Feature activation | -3.50e-03 |
Pos logit contributions | |
uble | +0.621 |
outer | +0.617 |
oro | +0.596 |
oster | +0.570 |
olphins | +0.557 |
Neg logit contributions | |
leaflets | -0.567 |
senal | -0.547 |
Masquerade | -0.531 |
pse | -0.523 |
Rollins | -0.512 |
Token | beyond |
Token ID | 3675 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
leaflets | +0.012 |
senal | +0.012 |
Masquerade | +0.012 |
pse | +0.012 |
Rollins | +0.011 |
Neg logit contributions | |
uble | -0.013 |
outer | -0.013 |
oro | -0.012 |
oster | -0.012 |
olphins | -0.011 |
Token | falling |
Token ID | 7463 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
uble | +3.410 |
outer | +3.347 |
oro | +3.221 |
oster | +3.072 |
olphins | +3.010 |
Neg logit contributions | |
senal | -3.156 |
leaflets | -3.146 |
Masquerade | -2.952 |
pse | -2.931 |
cffff | -2.882 |
Token | in |
Token ID | 287 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
leaflets | +1.754 |
Masquerade | +1.640 |
senal | +1.640 |
pse | +1.603 |
Rollins | +1.577 |
Neg logit contributions | |
uble | -2.042 |
outer | -2.024 |
oro | -1.955 |
oster | -1.872 |
olphins | -1.840 |
Token | love |
Token ID | 1842 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
uble | +0.201 |
outer | +0.198 |
oro | +0.191 |
oster | +0.182 |
olphins | +0.178 |
Neg logit contributions | |
leaflets | -0.207 |
senal | -0.198 |
Masquerade | -0.194 |
pse | -0.192 |
Rollins | -0.189 |
Token | and |
Token ID | 290 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
uble | +1.060 |
outer | +1.043 |
oro | +1.010 |
oster | +0.960 |
olphins | +0.943 |
Neg logit contributions | |
leaflets | -1.063 |
senal | -1.018 |
Masquerade | -0.999 |
pse | -0.985 |
Rollins | -0.969 |
Token | into |
Token ID | 656 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
uble | +0.502 |
outer | +0.498 |
oro | +0.479 |
oster | +0.456 |
olphins | +0.447 |
Neg logit contributions | |
leaflets | -0.508 |
senal | -0.484 |
Masquerade | -0.478 |
pse | -0.470 |
Rollins | -0.463 |
Token | . |
Token ID | 13 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
uble | +0.591 |
outer | +0.583 |
oro | +0.567 |
oster | +0.539 |
olphins | +0.527 |
Neg logit contributions | |
leaflets | -0.548 |
senal | -0.523 |
Masquerade | -0.516 |
pse | -0.504 |
Rollins | -0.499 |
Token | |
Token ID | 220 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
uble | +0.337 |
outer | +0.333 |
oro | +0.323 |
oster | +0.308 |
olphins | +0.301 |
Neg logit contributions | |
leaflets | -0.315 |
senal | -0.300 |
Masquerade | -0.295 |
pse | -0.291 |
Rollins | -0.284 |
Token | � |
Token ID | 134 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
leaflets | +0.932 |
senal | +0.894 |
Masquerade | +0.892 |
pse | +0.881 |
Rollins | +0.870 |
Neg logit contributions | |
uble | -0.429 |
outer | -0.422 |
oro | -0.394 |
oster | -0.366 |
olphins | -0.354 |
Token | � |
Token ID | 119 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
uble | +2.982 |
outer | +2.827 |
oro | +2.792 |
oster | +2.515 |
=~ | +2.490 |
Neg logit contributions | |
leaflets | -4.939 |
Masquerade | -4.768 |
senal | -4.723 |
Rollins | -4.676 |
cffff | -4.596 |
Token | A |
Token ID | 32 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
uble | +0.937 |
outer | +0.925 |
oro | +0.890 |
oster | +0.834 |
olphins | +0.809 |
Neg logit contributions | |
leaflets | -1.372 |
senal | -1.317 |
Masquerade | -1.305 |
pse | -1.284 |
Rollins | -1.269 |
Token | � |
Token ID | 134 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
uble | +1.491 |
outer | +1.467 |
oro | +1.429 |
oster | +1.349 |
olphins | +1.309 |
Neg logit contributions | |
leaflets | -1.616 |
senal | -1.545 |
Masquerade | -1.526 |
pse | -1.488 |
Rollins | -1.483 |
Token | � |
Token ID | 119 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
uble | +2.424 |
outer | +2.321 |
oro | +2.274 |
oster | +2.075 |
=~ | +2.062 |
Neg logit contributions | |
leaflets | -3.791 |
Masquerade | -3.631 |
senal | -3.620 |
Rollins | -3.578 |
Dent | -3.519 |
Token | ole |
Token ID | 2305 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
uble | +0.720 |
outer | +0.710 |
oro | +0.685 |
oster | +0.646 |
olphins | +0.629 |
Neg logit contributions | |
leaflets | -0.909 |
senal | -0.869 |
Masquerade | -0.862 |
pse | -0.846 |
Rollins | -0.836 |
Token | i |
Token ID | 1312 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
uble | +0.489 |
outer | +0.483 |
oro | +0.464 |
oster | +0.440 |
olphins | +0.431 |
Neg logit contributions | |
leaflets | -0.578 |
senal | -0.549 |
Masquerade | -0.546 |
pse | -0.537 |
Rollins | -0.529 |
Token | |
Token ID | 220 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
uble | +1.458 |
outer | +1.434 |
oro | +1.406 |
oster | +1.335 |
olphins | +1.303 |
Neg logit contributions | |
leaflets | -1.210 |
senal | -1.156 |
Masquerade | -1.131 |
pse | -1.100 |
Rollins | -1.094 |
Token | � |
Token ID | 134 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
leaflets | +0.798 |
senal | +0.769 |
Masquerade | +0.765 |
pse | +0.758 |
Rollins | +0.747 |
Neg logit contributions | |
uble | -0.303 |
outer | -0.298 |
oro | -0.274 |
oster | -0.252 |
TEXTURE | -0.245 |
Token | the |
Token ID | 262 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
leaflets | +0.830 |
senal | +0.779 |
Masquerade | +0.778 |
pse | +0.764 |
Rollins | +0.752 |
Neg logit contributions | |
uble | -0.892 |
outer | -0.883 |
oro | -0.848 |
oster | -0.811 |
olphins | -0.800 |
Token | information |
Token ID | 1321 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
uble | +0.047 |
outer | +0.047 |
oro | +0.046 |
oster | +0.044 |
TEXTURE | +0.043 |
Neg logit contributions | |
leaflets | -0.040 |
senal | -0.039 |
Masquerade | -0.038 |
pse | -0.037 |
Rollins | -0.036 |
Token | containing |
Token ID | 7268 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
leaflets | +0.269 |
senal | +0.257 |
Masquerade | +0.255 |
pse | +0.250 |
Rollins | +0.247 |
Neg logit contributions | |
uble | -0.228 |
outer | -0.226 |
oro | -0.217 |
oster | -0.206 |
olphins | -0.201 |
Token | those |
Token ID | 883 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
leaflets | +1.504 |
Masquerade | +1.397 |
senal | +1.392 |
pse | +1.370 |
Dent | +1.348 |
Neg logit contributions | |
uble | -1.860 |
outer | -1.840 |
oro | -1.771 |
oster | -1.694 |
olphins | -1.674 |
Token | allegations |
Token ID | 7636 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
leaflets | +1.805 |
Masquerade | +1.656 |
senal | +1.648 |
pse | +1.627 |
Dent | +1.594 |
Neg logit contributions | |
uble | -2.468 |
outer | -2.438 |
oro | -2.350 |
oster | -2.257 |
olphins | -2.234 |
Token | ? |
Token ID | 30 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
leaflets | +1.001 |
senal | +0.949 |
Masquerade | +0.948 |
pse | +0.933 |
Rollins | +0.922 |
Neg logit contributions | |
uble | -0.721 |
outer | -0.713 |
oro | -0.680 |
oster | -0.640 |
olphins | -0.628 |
Token | DEF |
Token ID | 23449 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
uble | +3.414 |
outer | +3.368 |
oro | +3.312 |
TEXTURE | +3.202 |
oster | +3.173 |
Neg logit contributions | |
senal | -3.354 |
leaflets | -3.325 |
pse | -3.156 |
Masquerade | -3.060 |
cffff | -3.042 |
Token | END |
Token ID | 10619 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
outer | +1.939 |
uble | +1.908 |
oro | +1.805 |
oster | +1.728 |
TEXTURE | +1.728 |
Neg logit contributions | |
senal | -3.360 |
leaflets | -3.348 |
pse | -3.203 |
Masquerade | -3.166 |
cffff | -3.079 |
Token | AN |
Token ID | 1565 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
leaflets | +0.974 |
Masquerade | +0.919 |
senal | +0.917 |
pse | +0.897 |
Rollins | +0.889 |
Neg logit contributions | |
uble | -0.942 |
outer | -0.931 |
oro | -0.896 |
oster | -0.851 |
olphins | -0.837 |
Token | TS |
Token ID | 4694 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
uble | +0.650 |
outer | +0.641 |
oro | +0.618 |
oster | +0.590 |
TEXTURE | +0.580 |
Neg logit contributions | |
leaflets | -0.704 |
senal | -0.682 |
Masquerade | -0.666 |
pse | -0.659 |
Rollins | -0.642 |
Token | � |
Token ID | 447 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
uble | +0.306 |
outer | +0.302 |
oro | +0.289 |
oster | +0.273 |
olphins | +0.267 |
Neg logit contributions | |
leaflets | -0.409 |
senal | -0.390 |
Masquerade | -0.388 |
pse | -0.382 |
Rollins | -0.377 |
Token | protect |
Token ID | 1805 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
uble | +0.812 |
outer | +0.801 |
oro | +0.769 |
oster | +0.739 |
olphins | +0.720 |
Neg logit contributions | |
leaflets | -0.784 |
senal | -0.768 |
Masquerade | -0.739 |
pse | -0.726 |
Rollins | -0.718 |
Token | them |
Token ID | 606 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
uble | +0.495 |
outer | +0.490 |
oro | +0.472 |
oster | +0.454 |
olphins | +0.442 |
Neg logit contributions | |
leaflets | -0.526 |
senal | -0.517 |
Masquerade | -0.499 |
pse | -0.492 |
Rollins | -0.485 |
Token | from |
Token ID | 422 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
leaflets | +0.275 |
senal | +0.262 |
Masquerade | +0.258 |
pse | +0.253 |
Rollins | +0.249 |
Neg logit contributions | |
uble | -0.326 |
outer | -0.322 |
oro | -0.312 |
oster | -0.299 |
olphins | -0.293 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
leaflets | +1.028 |
Masquerade | +0.945 |
senal | +0.939 |
pse | +0.923 |
Rollins | +0.904 |
Neg logit contributions | |
uble | -1.561 |
outer | -1.544 |
oro | -1.496 |
oster | -1.434 |
TEXTURE | -1.417 |
Token | harsh |
Token ID | 11859 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
uble | +0.567 |
outer | +0.562 |
oro | +0.544 |
oster | +0.519 |
olphins | +0.509 |
Neg logit contributions | |
leaflets | -0.521 |
senal | -0.504 |
Masquerade | -0.491 |
pse | -0.482 |
Rollins | -0.476 |
Token | Antarctic |
Token ID | 33149 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
outer | +1.738 |
uble | +1.734 |
oro | +1.688 |
oster | +1.602 |
olphins | +1.573 |
Neg logit contributions | |
leaflets | -1.526 |
senal | -1.501 |
Masquerade | -1.446 |
pse | -1.419 |
Rollins | -1.407 |
Token | winter |
Token ID | 7374 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
uble | +3.268 |
outer | +3.256 |
oro | +3.202 |
oster | +3.029 |
olphins | +2.971 |
Neg logit contributions | |
leaflets | -2.712 |
senal | -2.695 |
Masquerade | -2.573 |
pse | -2.544 |
cffff | -2.514 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
leaflets | +0.046 |
senal | +0.044 |
Masquerade | +0.043 |
pse | +0.043 |
Rollins | +0.042 |
Neg logit contributions | |
uble | -0.046 |
outer | -0.046 |
oro | -0.044 |
oster | -0.042 |
olphins | -0.041 |
Token | incub |
Token ID | 25543 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
leaflets | +0.408 |
senal | +0.393 |
Masquerade | +0.386 |
pse | +0.378 |
Rollins | +0.373 |
Neg logit contributions | |
uble | -0.398 |
outer | -0.392 |
oro | -0.378 |
oster | -0.362 |
olphins | -0.353 |
Token | ate |
Token ID | 378 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
leaflets | +0.194 |
senal | +0.184 |
Masquerade | +0.184 |
pse | +0.181 |
Rollins | +0.178 |
Neg logit contributions | |
uble | -0.145 |
outer | -0.143 |
oro | -0.137 |
oster | -0.129 |
olphins | -0.126 |
Token | their |
Token ID | 511 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
uble | +0.483 |
outer | +0.477 |
oro | +0.461 |
oster | +0.444 |
olphins | +0.434 |
Neg logit contributions | |
leaflets | -0.409 |
senal | -0.396 |
Masquerade | -0.385 |
pse | -0.378 |
Rollins | -0.371 |
Token | - |
Token ID | 12 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
uble | +0.117 |
outer | +0.116 |
oro | +0.112 |
oster | +0.106 |
olphins | +0.104 |
Neg logit contributions | |
leaflets | -0.127 |
senal | -0.121 |
Masquerade | -0.120 |
pse | -0.118 |
Rollins | -0.116 |
Token | ACC |
Token ID | 26861 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
leaflets | +0.303 |
senal | +0.289 |
Masquerade | +0.284 |
pse | +0.283 |
Rollins | +0.274 |
Neg logit contributions | |
uble | -0.295 |
outer | -0.293 |
oro | -0.282 |
oster | -0.269 |
TEXTURE | -0.264 |
Token | Fresh |
Token ID | 20138 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
outer | +1.888 |
uble | +1.879 |
oro | +1.825 |
oster | +1.761 |
olphins | +1.727 |
Neg logit contributions | |
leaflets | -1.339 |
senal | -1.300 |
Masquerade | -1.237 |
pse | -1.236 |
cffff | -1.202 |
Token | man |
Token ID | 805 |
Feature activation | -5.64e-03 |
Pos logit contributions | |
leaflets | +1.096 |
senal | +1.043 |
Masquerade | +1.034 |
pse | +1.019 |
Rollins | +1.003 |
Neg logit contributions | |
uble | -0.960 |
outer | -0.951 |
oro | -0.913 |
oster | -0.868 |
olphins | -0.850 |
Token | first |
Token ID | 717 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
leaflets | +0.018 |
senal | +0.017 |
Masquerade | +0.017 |
pse | +0.017 |
Rollins | +0.016 |
Neg logit contributions | |
uble | -0.023 |
outer | -0.022 |
oro | -0.022 |
oster | -0.021 |
olphins | -0.020 |
Token | team |
Token ID | 1074 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
leaflets | +0.510 |
senal | +0.477 |
Masquerade | +0.469 |
pse | +0.456 |
Rollins | +0.446 |
Neg logit contributions | |
uble | -0.946 |
outer | -0.939 |
oro | -0.913 |
oster | -0.881 |
olphins | -0.868 |
Token | ( |
Token ID | 357 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
leaflets | +0.309 |
senal | +0.293 |
Masquerade | +0.292 |
pse | +0.287 |
Rollins | +0.283 |
Neg logit contributions | |
uble | -0.275 |
outer | -0.272 |
oro | -0.261 |
oster | -0.248 |
olphins | -0.243 |
Token | along |
Token ID | 24176 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
outer | +1.414 |
uble | +1.392 |
oro | +1.341 |
oster | +1.267 |
TEXTURE | +1.234 |
Neg logit contributions | |
leaflets | -1.831 |
senal | -1.753 |
Masquerade | -1.720 |
pse | -1.706 |
Dent | -1.673 |
Token | with |
Token ID | 351 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
uble | +1.458 |
outer | +1.450 |
oro | +1.398 |
oster | +1.347 |
olphins | +1.297 |
Neg logit contributions | |
leaflets | -1.779 |
senal | -1.692 |
Masquerade | -1.679 |
pse | -1.648 |
Dent | -1.608 |
Token | Jones |
Token ID | 5437 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
leaflets | +0.688 |
senal | +0.644 |
Masquerade | +0.644 |
pse | +0.629 |
Rollins | +0.623 |
Neg logit contributions | |
uble | -0.848 |
outer | -0.839 |
oro | -0.811 |
oster | -0.776 |
olphins | -0.763 |
Token | and |
Token ID | 290 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
leaflets | +0.228 |
senal | +0.215 |
Masquerade | +0.214 |
pse | +0.210 |
Rollins | +0.206 |
Neg logit contributions | |
uble | -0.246 |
outer | -0.243 |
oro | -0.235 |
oster | -0.224 |
olphins | -0.220 |
Token |
|
Token ID | 198 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
leaflets | +1.145 |
senal | +1.086 |
Masquerade | +1.081 |
pse | +1.061 |
Rollins | +1.048 |
Neg logit contributions | |
uble | -1.045 |
outer | -1.033 |
oro | -0.993 |
oster | -0.944 |
olphins | -0.925 |
Token |
|
Token ID | 198 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
leaflets | +2.190 |
Masquerade | +2.067 |
Rollins | +2.032 |
Dent | +2.023 |
als | +2.003 |
Neg logit contributions | |
uble | -2.145 |
outer | -2.108 |
oro | -2.024 |
olphins | -1.928 |
oster | -1.921 |
Token | See |
Token ID | 6214 |
Feature activation | +9.62e-02 |
Pos logit contributions | |
leaflets | +1.315 |
Masquerade | +1.244 |
senal | +1.242 |
pse | +1.215 |
Rollins | +1.204 |
Neg logit contributions | |
uble | -1.270 |
outer | -1.248 |
oro | -1.203 |
oster | -1.146 |
olphins | -1.126 |
Token | also |
Token ID | 635 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
uble | +0.248 |
outer | +0.245 |
oro | +0.234 |
oster | +0.218 |
olphins | +0.212 |
Neg logit contributions | |
leaflets | -0.445 |
senal | -0.430 |
Masquerade | -0.425 |
pse | -0.419 |
Rollins | -0.413 |
Token | [ |
Token ID | 685 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
leaflets | +1.461 |
Masquerade | +1.340 |
senal | +1.328 |
pse | +1.297 |
Dent | +1.287 |
Neg logit contributions | |
uble | -2.387 |
outer | -2.365 |
oro | -2.275 |
oster | -2.199 |
TEXTURE | -2.170 |
Token | edit |
Token ID | 4370 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
leaflets | +0.460 |
Masquerade | +0.424 |
senal | +0.423 |
pse | +0.413 |
Rollins | +0.406 |
Neg logit contributions | |
uble | -0.726 |
outer | -0.719 |
oro | -0.698 |
oster | -0.671 |
olphins | -0.662 |
Token | ] |
Token ID | 2361 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
uble | +0.302 |
outer | +0.299 |
oro | +0.288 |
oster | +0.275 |
olphins | +0.270 |
Neg logit contributions | |
leaflets | -0.295 |
senal | -0.280 |
Masquerade | -0.277 |
pse | -0.273 |
Rollins | -0.268 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
leaflets | +1.786 |
Masquerade | +1.690 |
senal | +1.688 |
Rollins | +1.654 |
pse | +1.646 |
Neg logit contributions | |
uble | -1.341 |
outer | -1.321 |
oro | -1.253 |
oster | -1.179 |
TEXTURE | -1.161 |
Token | I |
Token ID | 40 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
leaflets | +0.085 |
senal | +0.081 |
Masquerade | +0.080 |
pse | +0.079 |
Rollins | +0.077 |
Neg logit contributions | |
uble | -0.070 |
outer | -0.069 |
oro | -0.066 |
oster | -0.063 |
TEXTURE | -0.061 |
Token | ke |
Token ID | 365 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
uble | +1.229 |
outer | +1.198 |
oro | +1.171 |
oster | +1.111 |
olphins | +1.068 |
Neg logit contributions | |
leaflets | -1.492 |
senal | -1.437 |
Masquerade | -1.408 |
pse | -1.376 |
Rollins | -1.355 |
Token | a |
Token ID | 64 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
leaflets | +2.077 |
Masquerade | +1.957 |
senal | +1.949 |
pse | +1.907 |
Rollins | +1.890 |
Neg logit contributions | |
uble | -2.231 |
outer | -2.215 |
oro | -2.121 |
oster | -2.031 |
TEXTURE | -1.995 |
Token | a |
Token ID | 257 |
Feature activation | +2.21e-03 |
Pos logit contributions | |
leaflets | +0.283 |
senal | +0.271 |
Masquerade | +0.264 |
pse | +0.258 |
Rollins | +0.253 |
Neg logit contributions | |
uble | -0.412 |
outer | -0.407 |
oro | -0.395 |
oster | -0.380 |
olphins | -0.372 |
Token | week |
Token ID | 1285 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
uble | +0.010 |
outer | +0.010 |
oro | +0.010 |
oster | +0.010 |
olphins | +0.009 |
Neg logit contributions | |
leaflets | -0.006 |
senal | -0.005 |
Masquerade | -0.005 |
pse | -0.005 |
Rollins | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
leaflets | +0.309 |
senal | +0.293 |
Masquerade | +0.292 |
pse | +0.287 |
Rollins | +0.284 |
Neg logit contributions | |
uble | -0.247 |
outer | -0.244 |
oro | -0.234 |
oster | -0.222 |
olphins | -0.217 |
Token | a |
Token ID | 257 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
uble | +0.888 |
outer | +0.874 |
oro | +0.853 |
oster | +0.819 |
olphins | +0.798 |
Neg logit contributions | |
leaflets | -0.620 |
senal | -0.595 |
Masquerade | -0.578 |
pse | -0.566 |
Rollins | -0.553 |
Token | couple |
Token ID | 3155 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
uble | +1.367 |
outer | +1.347 |
oro | +1.313 |
oster | +1.256 |
olphins | +1.226 |
Neg logit contributions | |
leaflets | -1.047 |
senal | -0.997 |
Masquerade | -0.977 |
pse | -0.955 |
Rollins | -0.935 |
Token | of |
Token ID | 286 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
uble | +0.348 |
outer | +0.345 |
oro | +0.334 |
oster | +0.321 |
olphins | +0.315 |
Neg logit contributions | |
leaflets | -0.258 |
senal | -0.242 |
Masquerade | -0.240 |
pse | -0.235 |
Rollins | -0.231 |
Token | months |
Token ID | 1933 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
leaflets | +0.105 |
senal | +0.097 |
Masquerade | +0.097 |
pse | +0.094 |
Rollins | +0.093 |
Neg logit contributions | |
uble | -0.174 |
outer | -0.173 |
oro | -0.168 |
oster | -0.162 |
olphins | -0.159 |
Token | , |
Token ID | 11 |
Feature activation | -9.98e-02 |
Pos logit contributions | |
leaflets | +0.049 |
senal | +0.046 |
Masquerade | +0.046 |
pse | +0.045 |
Rollins | +0.045 |
Neg logit contributions | |
uble | -0.041 |
outer | -0.041 |
oro | -0.039 |
oster | -0.037 |
olphins | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
leaflets | +0.324 |
senal | +0.309 |
Masquerade | +0.304 |
pse | +0.298 |
Rollins | +0.291 |
Neg logit contributions | |
uble | -0.395 |
outer | -0.391 |
oro | -0.378 |
oster | -0.363 |
olphins | -0.355 |
Token | the |
Token ID | 262 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
leaflets | +0.074 |
senal | +0.070 |
Masquerade | +0.070 |
pse | +0.068 |
Rollins | +0.067 |
Neg logit contributions | |
uble | -0.075 |
outer | -0.074 |
oro | -0.071 |
oster | -0.068 |
olphins | -0.066 |
Token | pressure |
Token ID | 3833 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
leaflets | +0.659 |
senal | +0.620 |
Masquerade | +0.616 |
pse | +0.603 |
Rollins | +0.593 |
Neg logit contributions | |
uble | -0.783 |
outer | -0.775 |
oro | -0.749 |
oster | -0.717 |
olphins | -0.704 |
Token | me |
Token ID | 502 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
uble | +1.256 |
outer | +1.235 |
oro | +1.205 |
oster | +1.140 |
TEXTURE | +1.108 |
Neg logit contributions | |
leaflets | -1.398 |
senal | -1.357 |
Masquerade | -1.317 |
pse | -1.304 |
Rollins | -1.276 |
Token | . |
Token ID | 13 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
uble | +0.191 |
outer | +0.189 |
oro | +0.181 |
oster | +0.171 |
olphins | +0.168 |
Neg logit contributions | |
leaflets | -0.237 |
senal | -0.226 |
Masquerade | -0.225 |
pse | -0.221 |
Rollins | -0.218 |
Token | I |
Token ID | 314 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
uble | +0.922 |
outer | +0.910 |
oro | +0.876 |
oster | +0.826 |
TEXTURE | +0.803 |
Neg logit contributions | |
leaflets | -1.274 |
senal | -1.224 |
Masquerade | -1.201 |
pse | -1.192 |
Rollins | -1.168 |
Token | am |
Token ID | 716 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
uble | +0.649 |
outer | +0.640 |
oro | +0.616 |
oster | +0.585 |
olphins | +0.569 |
Neg logit contributions | |
leaflets | -0.770 |
senal | -0.738 |
Masquerade | -0.726 |
pse | -0.716 |
Rollins | -0.705 |
Token | ready |
Token ID | 3492 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
uble | +1.298 |
outer | +1.282 |
oro | +1.241 |
oster | +1.184 |
TEXTURE | +1.155 |
Neg logit contributions | |
leaflets | -1.262 |
senal | -1.201 |
Masquerade | -1.181 |
pse | -1.169 |
Rollins | -1.140 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
uble | +0.127 |
outer | +0.126 |
oro | +0.121 |
oster | +0.114 |
olphins | +0.111 |
Neg logit contributions | |
leaflets | -0.171 |
senal | -0.163 |
Masquerade | -0.162 |
pse | -0.160 |
Rollins | -0.158 |
Token | � |
Token ID | 564 |
Feature activation | -9.39e-03 |
Pos logit contributions | |
uble | +0.817 |
outer | +0.806 |
oro | +0.778 |
oster | +0.738 |
TEXTURE | +0.720 |
Neg logit contributions | |
leaflets | -0.967 |
senal | -0.927 |
Masquerade | -0.907 |
pse | -0.901 |
Rollins | -0.880 |
Token | � |
Token ID | 251 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
leaflets | +0.037 |
senal | +0.035 |
Masquerade | +0.035 |
pse | +0.034 |
Rollins | +0.034 |
Neg logit contributions | |
uble | -0.031 |
outer | -0.031 |
oro | -0.029 |
oster | -0.028 |
olphins | -0.027 |
Token | Then |
Token ID | 3244 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
uble | +1.087 |
outer | +1.073 |
oro | +1.036 |
oster | +0.979 |
TEXTURE | +0.955 |
Neg logit contributions | |
leaflets | -1.381 |
senal | -1.332 |
Masquerade | -1.294 |
pse | -1.292 |
Rollins | -1.259 |
Token | , |
Token ID | 11 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
uble | +0.768 |
outer | +0.759 |
oro | +0.736 |
oster | +0.698 |
TEXTURE | +0.683 |
Neg logit contributions | |
leaflets | -0.829 |
senal | -0.804 |
Masquerade | -0.783 |
pse | -0.774 |
Rollins | -0.755 |
Token | it |
Token ID | 340 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
uble | +0.835 |
outer | +0.825 |
oro | +0.800 |
oster | +0.762 |
TEXTURE | +0.745 |
Neg logit contributions | |
leaflets | -0.827 |
senal | -0.805 |
Masquerade | -0.781 |
pse | -0.771 |
Rollins | -0.750 |
Token | all |
Token ID | 477 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
uble | +2.020 |
outer | +1.978 |
oro | +1.911 |
oster | +1.830 |
olphins | +1.774 |
Neg logit contributions | |
leaflets | -2.268 |
senal | -2.227 |
Masquerade | -2.156 |
pse | -2.127 |
Rollins | -2.087 |
Token | ? |
Token ID | 30 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
leaflets | +0.402 |
Masquerade | +0.380 |
senal | +0.379 |
pse | +0.374 |
Dent | +0.370 |
Neg logit contributions | |
uble | -0.290 |
outer | -0.287 |
oro | -0.273 |
oster | -0.257 |
TEXTURE | -0.252 |
Token |
|
Token ID | 198 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
uble | +2.379 |
outer | +2.338 |
oro | +2.295 |
oster | +2.154 |
usa | +2.096 |
Neg logit contributions | |
leaflets | -2.908 |
senal | -2.857 |
pse | -2.748 |
cffff | -2.681 |
Masquerade | -2.664 |
Token |
|
Token ID | 198 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
uble | +0.583 |
outer | +0.576 |
oro | +0.552 |
oster | +0.521 |
TEXTURE | +0.509 |
Neg logit contributions | |
leaflets | -0.793 |
senal | -0.770 |
Masquerade | -0.751 |
pse | -0.747 |
Rollins | -0.728 |
Token | The |
Token ID | 464 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
uble | +0.622 |
outer | +0.617 |
oro | +0.594 |
oster | +0.559 |
TEXTURE | +0.556 |
Neg logit contributions | |
leaflets | -0.775 |
senal | -0.751 |
pse | -0.725 |
Masquerade | -0.725 |
Rollins | -0.702 |
Token | first |
Token ID | 717 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
uble | +0.298 |
outer | +0.294 |
oro | +0.287 |
oster | +0.271 |
olphins | +0.266 |
Neg logit contributions | |
leaflets | -0.248 |
senal | -0.242 |
Masquerade | -0.233 |
pse | -0.228 |
cffff | -0.223 |
Token | proposal |
Token ID | 6961 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
uble | +0.855 |
outer | +0.843 |
oro | +0.822 |
oster | +0.782 |
olphins | +0.762 |
Neg logit contributions | |
leaflets | -0.788 |
senal | -0.770 |
Masquerade | -0.743 |
pse | -0.731 |
Rollins | -0.718 |
Token | , |
Token ID | 11 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
uble | +2.620 |
outer | +2.547 |
oro | +2.487 |
oster | +2.363 |
obe | +2.277 |
Neg logit contributions | |
senal | -2.954 |
leaflets | -2.905 |
Masquerade | -2.770 |
pse | -2.731 |
cffff | -2.716 |
Token | Mandatory |
Token ID | 47018 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
uble | +2.720 |
outer | +2.681 |
oro | +2.605 |
oster | +2.489 |
olphins | +2.415 |
Neg logit contributions | |
leaflets | -2.591 |
senal | -2.584 |
Masquerade | -2.456 |
pse | -2.441 |
cffff | -2.406 |
Token | In |
Token ID | 554 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
leaflets | +0.227 |
senal | +0.215 |
Masquerade | +0.211 |
pse | +0.210 |
Rollins | +0.204 |
Neg logit contributions | |
uble | -0.296 |
outer | -0.293 |
oro | -0.285 |
oster | -0.273 |
olphins | -0.268 |
Token | clusion |
Token ID | 4717 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
uble | +0.257 |
outer | +0.253 |
oro | +0.244 |
oster | +0.233 |
olphins | +0.228 |
Neg logit contributions | |
leaflets | -0.255 |
senal | -0.243 |
Masquerade | -0.239 |
pse | -0.237 |
Rollins | -0.232 |
Token | that |
Token ID | 326 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
leaflets | +0.928 |
senal | +0.873 |
Masquerade | +0.867 |
pse | +0.849 |
Rollins | +0.836 |
Neg logit contributions | |
uble | -1.126 |
outer | -1.115 |
oro | -1.078 |
oster | -1.032 |
olphins | -1.014 |
Token | authorities |
Token ID | 4773 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
uble | +0.092 |
outer | +0.091 |
oro | +0.088 |
oster | +0.084 |
olphins | +0.083 |
Neg logit contributions | |
leaflets | -0.075 |
senal | -0.072 |
Masquerade | -0.070 |
pse | -0.069 |
cffff | -0.067 |
Token | are |
Token ID | 389 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
outer | +1.509 |
uble | +1.504 |
oro | +1.464 |
oster | +1.399 |
olphins | +1.336 |
Neg logit contributions | |
senal | -1.679 |
leaflets | -1.661 |
Masquerade | -1.600 |
pse | -1.575 |
cffff | -1.561 |
Token | questioning |
Token ID | 14085 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
leaflets | +2.264 |
Masquerade | +2.089 |
senal | +2.071 |
pse | +2.055 |
Rollins | +2.047 |
Neg logit contributions | |
uble | -2.452 |
outer | -2.423 |
oro | -2.331 |
oster | -2.222 |
TEXTURE | -2.207 |
Token | a |
Token ID | 257 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
leaflets | +0.281 |
senal | +0.271 |
Masquerade | +0.263 |
pse | +0.259 |
cffff | +0.251 |
Neg logit contributions | |
uble | -0.375 |
outer | -0.370 |
oro | -0.360 |
oster | -0.346 |
olphins | -0.340 |
Token | person |
Token ID | 1048 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
leaflets | +0.864 |
senal | +0.815 |
Masquerade | +0.809 |
pse | +0.793 |
Rollins | +0.780 |
Neg logit contributions | |
uble | -1.002 |
outer | -0.992 |
oro | -0.958 |
oster | -0.916 |
olphins | -0.900 |
Token | of |
Token ID | 286 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
leaflets | +0.573 |
senal | +0.543 |
Masquerade | +0.534 |
pse | +0.524 |
Rollins | +0.511 |
Neg logit contributions | |
uble | -0.790 |
outer | -0.780 |
oro | -0.758 |
oster | -0.728 |
olphins | -0.714 |
Token | interest |
Token ID | 1393 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
leaflets | +2.791 |
Masquerade | +2.621 |
pse | +2.592 |
senal | +2.582 |
Dent | +2.563 |
Neg logit contributions | |
uble | -2.425 |
outer | -2.415 |
oro | -2.304 |
oster | -2.191 |
olphins | -2.163 |
Token | at |
Token ID | 379 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
leaflets | +0.190 |
senal | +0.183 |
Masquerade | +0.179 |
pse | +0.176 |
Rollins | +0.171 |
Neg logit contributions | |
uble | -0.216 |
outer | -0.213 |
oro | -0.206 |
oster | -0.197 |
olphins | -0.192 |
Token | Brigham |
Token ID | 37434 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
leaflets | +1.649 |
senal | +1.550 |
Masquerade | +1.542 |
pse | +1.507 |
Rollins | +1.488 |
Neg logit contributions | |
uble | -2.005 |
outer | -1.984 |
oro | -1.918 |
oster | -1.836 |
olphins | -1.804 |
Token | and |
Token ID | 290 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
uble | +1.859 |
outer | +1.845 |
oro | +1.829 |
oster | +1.766 |
TEXTURE | +1.704 |
Neg logit contributions | |
leaflets | -1.233 |
senal | -1.193 |
Masquerade | -1.143 |
pse | -1.143 |
cffff | -1.113 |
Token | the |
Token ID | 262 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
leaflets | +0.911 |
senal | +0.863 |
Masquerade | +0.854 |
pse | +0.839 |
Rollins | +0.823 |
Neg logit contributions | |
uble | -1.007 |
outer | -0.997 |
oro | -0.964 |
oster | -0.920 |
olphins | -0.902 |
Token | rooft |
Token ID | 27291 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
leaflets | +1.139 |
senal | +1.074 |
Masquerade | +1.064 |
pse | +1.044 |
Rollins | +1.026 |
Neg logit contributions | |
uble | -1.357 |
outer | -1.343 |
oro | -1.299 |
oster | -1.242 |
olphins | -1.220 |
Token | ops |
Token ID | 2840 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
leaflets | +0.979 |
Masquerade | +0.875 |
pse | +0.847 |
senal | +0.840 |
Dent | +0.832 |
Neg logit contributions | |
uble | -2.016 |
outer | -1.991 |
oro | -1.938 |
oster | -1.868 |
TEXTURE | -1.866 |
Token | to |
Token ID | 284 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
leaflets | +0.559 |
senal | +0.531 |
Masquerade | +0.526 |
pse | +0.516 |
Rollins | +0.507 |
Neg logit contributions | |
uble | -0.586 |
outer | -0.579 |
oro | -0.560 |
oster | -0.533 |
olphins | -0.523 |
Token | duel |
Token ID | 24662 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
leaflets | +1.621 |
Masquerade | +1.528 |
senal | +1.506 |
pse | +1.494 |
Rollins | +1.473 |
Neg logit contributions | |
uble | -1.588 |
outer | -1.567 |
oro | -1.507 |
oster | -1.440 |
olphins | -1.419 |
Token | to |
Token ID | 284 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
leaflets | +0.748 |
senal | +0.707 |
Masquerade | +0.701 |
pse | +0.688 |
Rollins | +0.676 |
Neg logit contributions | |
uble | -0.845 |
outer | -0.836 |
oro | -0.808 |
oster | -0.772 |
olphins | -0.758 |
Token | the |
Token ID | 262 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
leaflets | +0.713 |
senal | +0.671 |
Masquerade | +0.670 |
pse | +0.657 |
Rollins | +0.647 |
Neg logit contributions | |
uble | -0.769 |
outer | -0.760 |
oro | -0.733 |
oster | -0.700 |
olphins | -0.688 |
Token | death |
Token ID | 1918 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
uble | +1.829 |
outer | +1.821 |
oro | +1.786 |
oster | +1.706 |
olphins | +1.684 |
Neg logit contributions | |
leaflets | -0.782 |
senal | -0.731 |
pse | -0.685 |
Masquerade | -0.681 |
cffff | -0.667 |
Token | in |
Token ID | 287 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
uble | +0.363 |
outer | +0.358 |
oro | +0.344 |
oster | +0.325 |
olphins | +0.317 |
Neg logit contributions | |
leaflets | -0.462 |
senal | -0.441 |
Masquerade | -0.438 |
pse | -0.432 |
Rollins | -0.423 |
Token | the |
Token ID | 262 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
leaflets | +0.984 |
senal | +0.924 |
Masquerade | +0.922 |
pse | +0.903 |
Rollins | +0.890 |
Neg logit contributions | |
uble | -1.122 |
outer | -1.109 |
oro | -1.071 |
oster | -1.025 |
olphins | -1.007 |
Token | name |
Token ID | 1438 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
leaflets | +1.338 |
Masquerade | +1.257 |
senal | +1.252 |
pse | +1.226 |
Rollins | +1.210 |
Neg logit contributions | |
uble | -1.551 |
outer | -1.532 |
oro | -1.477 |
oster | -1.417 |
olphins | -1.393 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
uble | +0.838 |
outer | +0.828 |
oro | +0.806 |
oster | +0.759 |
olphins | +0.734 |
Neg logit contributions | |
leaflets | -1.114 |
senal | -1.080 |
pse | -1.051 |
Masquerade | -1.043 |
cffff | -1.025 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
uble | +0.710 |
outer | +0.702 |
oro | +0.672 |
oster | +0.635 |
TEXTURE | +0.619 |
Neg logit contributions | |
leaflets | -0.955 |
senal | -0.924 |
Masquerade | -0.905 |
pse | -0.898 |
Rollins | -0.878 |
Token | � |
Token ID | 447 |
Feature activation | -8.69e-02 |
Pos logit contributions | |
uble | +0.466 |
outer | +0.460 |
oro | +0.443 |
oster | +0.416 |
TEXTURE | +0.407 |
Neg logit contributions | |
leaflets | -0.675 |
senal | -0.651 |
Masquerade | -0.638 |
pse | -0.633 |
Rollins | -0.619 |
Token | � |
Token ID | 250 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
leaflets | +0.341 |
senal | +0.324 |
Masquerade | +0.322 |
pse | +0.317 |
Rollins | +0.313 |
Neg logit contributions | |
uble | -0.286 |
outer | -0.283 |
oro | -0.271 |
oster | -0.257 |
olphins | -0.252 |
Token | Maybe |
Token ID | 13300 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
leaflets | +0.070 |
senal | +0.067 |
Masquerade | +0.066 |
pse | +0.065 |
Rollins | +0.064 |
Neg logit contributions | |
uble | -0.052 |
outer | -0.052 |
oro | -0.050 |
oster | -0.047 |
TEXTURE | -0.046 |
Token | we |
Token ID | 356 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
uble | +0.295 |
outer | +0.292 |
oro | +0.283 |
oster | +0.270 |
olphins | +0.263 |
Neg logit contributions | |
leaflets | -0.263 |
senal | -0.253 |
Masquerade | -0.249 |
pse | -0.242 |
Rollins | -0.239 |
Token | have |
Token ID | 423 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
leaflets | +0.947 |
senal | +0.904 |
Masquerade | +0.896 |
pse | +0.881 |
Rollins | +0.869 |
Neg logit contributions | |
uble | -0.801 |
outer | -0.791 |
oro | -0.760 |
oster | -0.721 |
olphins | -0.705 |
Token | to |
Token ID | 284 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
leaflets | +0.506 |
senal | +0.480 |
Masquerade | +0.477 |
pse | +0.468 |
Rollins | +0.461 |
Neg logit contributions | |
uble | -0.504 |
outer | -0.498 |
oro | -0.480 |
oster | -0.458 |
olphins | -0.449 |
Token | pray |
Token ID | 12472 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
leaflets | +1.807 |
Masquerade | +1.684 |
pse | +1.664 |
senal | +1.662 |
Rollins | +1.630 |
Neg logit contributions | |
uble | -1.975 |
outer | -1.955 |
oro | -1.884 |
oster | -1.798 |
TEXTURE | -1.780 |
Token | , |
Token ID | 11 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
leaflets | +1.399 |
senal | +1.314 |
Masquerade | +1.310 |
pse | +1.288 |
Rollins | +1.269 |
Neg logit contributions | |
uble | -1.476 |
outer | -1.460 |
oro | -1.409 |
oster | -1.342 |
olphins | -1.321 |
Token | � |
Token ID | 447 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
leaflets | +0.816 |
senal | +0.780 |
Masquerade | +0.774 |
pse | +0.762 |
Rollins | +0.752 |
Neg logit contributions | |
uble | -0.597 |
outer | -0.589 |
oro | -0.564 |
oster | -0.533 |
olphins | -0.519 |
Token | � |
Token ID | 564 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
leaflets | +1.463 |
Masquerade | +1.361 |
senal | +1.361 |
pse | +1.336 |
Dent | +1.322 |
Neg logit contributions | |
uble | -1.958 |
outer | -1.950 |
oro | -1.882 |
oster | -1.805 |
TEXTURE | -1.782 |
Token | � |
Token ID | 250 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
leaflets | +1.877 |
senal | +1.778 |
Masquerade | +1.771 |
pse | +1.754 |
Rollins | +1.727 |
Neg logit contributions | |
outer | -1.760 |
uble | -1.746 |
oro | -1.675 |
oster | -1.598 |
TEXTURE | -1.584 |
Token | parent |
Token ID | 8000 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
leaflets | +0.711 |
senal | +0.674 |
Masquerade | +0.669 |
pse | +0.657 |
Rollins | +0.647 |
Neg logit contributions | |
uble | -0.657 |
outer | -0.650 |
oro | -0.625 |
oster | -0.594 |
olphins | -0.581 |
Token | � |
Token ID | 447 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
leaflets | +2.201 |
senal | +2.091 |
Masquerade | +2.087 |
pse | +2.061 |
Dent | +2.029 |
Neg logit contributions | |
uble | -1.746 |
outer | -1.733 |
oro | -1.654 |
oster | -1.565 |
olphins | -1.545 |
Token | � |
Token ID | 251 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
leaflets | +1.373 |
senal | +1.305 |
Masquerade | +1.302 |
pse | +1.284 |
Rollins | +1.268 |
Neg logit contributions | |
outer | -1.145 |
uble | -1.141 |
oro | -1.086 |
oster | -1.036 |
olphins | -1.021 |
Token | since |
Token ID | 1201 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
leaflets | +1.783 |
senal | +1.680 |
Masquerade | +1.678 |
pse | +1.645 |
Rollins | +1.634 |
Neg logit contributions | |
uble | -1.848 |
outer | -1.837 |
oro | -1.769 |
oster | -1.681 |
TEXTURE | -1.669 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
leaflets | +1.468 |
Masquerade | +1.385 |
pse | +1.360 |
senal | +1.360 |
Rollins | +1.355 |
Neg logit contributions | |
uble | -1.435 |
outer | -1.425 |
oro | -1.363 |
oster | -1.294 |
TEXTURE | -1.290 |
Token | . |
Token ID | 13 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
uble | +0.160 |
outer | +0.157 |
oro | +0.150 |
oster | +0.142 |
olphins | +0.138 |
Neg logit contributions | |
leaflets | -0.228 |
senal | -0.218 |
Masquerade | -0.217 |
pse | -0.214 |
Rollins | -0.211 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
leaflets | +0.247 |
senal | +0.236 |
Masquerade | +0.234 |
pse | +0.231 |
Rollins | +0.227 |
Neg logit contributions | |
uble | -0.198 |
outer | -0.196 |
oro | -0.188 |
oster | -0.178 |
olphins | -0.174 |
Token |
|
Token ID | 198 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
leaflets | +0.537 |
Masquerade | +0.508 |
Rollins | +0.496 |
Dent | +0.494 |
pse | +0.487 |
Neg logit contributions | |
uble | -0.452 |
outer | -0.445 |
oro | -0.427 |
oster | -0.404 |
olphins | -0.399 |
Token | She |
Token ID | 3347 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
leaflets | +0.104 |
senal | +0.099 |
Masquerade | +0.098 |
pse | +0.097 |
Rollins | +0.095 |
Neg logit contributions | |
uble | -0.080 |
outer | -0.079 |
oro | -0.076 |
oster | -0.072 |
olphins | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
uble | +0.027 |
outer | +0.027 |
oro | +0.026 |
oster | +0.024 |
olphins | +0.024 |
Neg logit contributions | |
leaflets | -0.039 |
Masquerade | -0.037 |
Rollins | -0.037 |
Dent | -0.036 |
senal | -0.036 |
Token | A |
Token ID | 317 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
uble | +0.573 |
outer | +0.567 |
oro | +0.549 |
oster | +0.522 |
TEXTURE | +0.511 |
Neg logit contributions | |
leaflets | -0.582 |
senal | -0.559 |
Masquerade | -0.545 |
pse | -0.540 |
cffff | -0.528 |
Token | US |
Token ID | 2937 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
leaflets | +0.171 |
senal | +0.164 |
Masquerade | +0.162 |
pse | +0.160 |
Rollins | +0.157 |
Neg logit contributions | |
uble | -0.126 |
outer | -0.124 |
oro | -0.120 |
oster | -0.113 |
TEXTURE | -0.110 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
outer | +1.554 |
uble | +1.543 |
oro | +1.498 |
oster | +1.427 |
TEXTURE | +1.391 |
Neg logit contributions | |
leaflets | -1.468 |
senal | -1.407 |
Masquerade | -1.390 |
pse | -1.353 |
cffff | -1.330 |
Token | Robbie |
Token ID | 34855 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
leaflets | +0.339 |
senal | +0.319 |
Masquerade | +0.316 |
pse | +0.310 |
Rollins | +0.303 |
Neg logit contributions | |
uble | -0.426 |
outer | -0.422 |
oro | -0.408 |
oster | -0.391 |
olphins | -0.384 |
Token | M |
Token ID | 337 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
uble | +0.282 |
outer | +0.279 |
oro | +0.271 |
oster | +0.261 |
olphins | +0.258 |
Neg logit contributions | |
leaflets | -0.164 |
Masquerade | -0.151 |
senal | -0.149 |
pse | -0.146 |
Rollins | -0.145 |
Token | ce |
Token ID | 344 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
leaflets | +2.172 |
Masquerade | +2.066 |
senal | +2.057 |
Rollins | +2.035 |
Dent | +2.025 |
Neg logit contributions | |
uble | -1.411 |
outer | -1.371 |
oro | -1.312 |
oster | -1.224 |
olphins | -1.222 |
Token | wen |
Token ID | 21006 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
leaflets | +1.215 |
senal | +1.154 |
Masquerade | +1.150 |
pse | +1.130 |
Rollins | +1.120 |
Neg logit contributions | |
uble | -0.965 |
outer | -0.953 |
oro | -0.913 |
oster | -0.863 |
TEXTURE | -0.849 |
Token | ( |
Token ID | 357 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
uble | +1.093 |
outer | +1.079 |
oro | +1.046 |
oster | +1.002 |
olphins | +0.965 |
Neg logit contributions | |
leaflets | -1.115 |
senal | -1.067 |
Masquerade | -1.034 |
pse | -1.012 |
cffff | -1.001 |
Token | Green |
Token ID | 13719 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
uble | +0.318 |
outer | +0.317 |
oro | +0.305 |
oster | +0.286 |
TEXTURE | +0.281 |
Neg logit contributions | |
leaflets | -0.422 |
senal | -0.406 |
Masquerade | -0.398 |
pse | -0.397 |
Rollins | -0.385 |
Token | Edge |
Token ID | 37021 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
leaflets | +0.591 |
senal | +0.569 |
Masquerade | +0.563 |
pse | +0.556 |
Rollins | +0.548 |
Neg logit contributions | |
uble | -0.366 |
outer | -0.361 |
oro | -0.344 |
oster | -0.322 |
olphins | -0.313 |
Token | upsetting |
Token ID | 38423 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
uble | +0.380 |
outer | +0.376 |
oro | +0.363 |
oster | +0.348 |
TEXTURE | +0.338 |
Neg logit contributions | |
leaflets | -0.365 |
senal | -0.351 |
Masquerade | -0.345 |
pse | -0.338 |
Rollins | -0.333 |
Token | . |
Token ID | 764 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
uble | +0.385 |
outer | +0.379 |
oro | +0.367 |
oster | +0.352 |
olphins | +0.340 |
Neg logit contributions | |
leaflets | -0.414 |
senal | -0.399 |
Masquerade | -0.393 |
pse | -0.386 |
Rollins | -0.380 |
Token | . |
Token ID | 764 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
leaflets | +0.179 |
senal | +0.170 |
Masquerade | +0.168 |
pse | +0.166 |
Rollins | +0.163 |
Neg logit contributions | |
uble | -0.173 |
outer | -0.171 |
oro | -0.165 |
oster | -0.157 |
olphins | -0.154 |
Token | . |
Token ID | 764 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
leaflets | +0.629 |
senal | +0.593 |
Masquerade | +0.590 |
pse | +0.581 |
Rollins | +0.571 |
Neg logit contributions | |
uble | -0.660 |
outer | -0.653 |
oro | -0.627 |
oster | -0.599 |
olphins | -0.592 |
Token | the |
Token ID | 262 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
leaflets | +1.197 |
senal | +1.132 |
Masquerade | +1.124 |
pse | +1.103 |
Rollins | +1.086 |
Neg logit contributions | |
uble | -1.268 |
outer | -1.254 |
oro | -1.210 |
oster | -1.155 |
olphins | -1.133 |
Token | bottom |
Token ID | 4220 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
leaflets | +1.270 |
senal | +1.217 |
Masquerade | +1.197 |
pse | +1.173 |
Rollins | +1.153 |
Neg logit contributions | |
uble | -1.414 |
outer | -1.402 |
oro | -1.353 |
oster | -1.295 |
olphins | -1.267 |
Token | line |
Token ID | 1627 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
leaflets | +4.627 |
Masquerade | +4.335 |
pse | +4.276 |
Rollins | +4.276 |
Dent | +4.265 |
Neg logit contributions | |
uble | -3.624 |
outer | -3.598 |
oro | -3.426 |
TEXTURE | -3.260 |
olphins | -3.221 |
Token | is |
Token ID | 318 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
leaflets | +1.252 |
senal | +1.183 |
Masquerade | +1.181 |
pse | +1.162 |
Rollins | +1.152 |
Neg logit contributions | |
uble | -0.973 |
outer | -0.959 |
oro | -0.919 |
oster | -0.867 |
olphins | -0.853 |
Token | the |
Token ID | 262 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
leaflets | +0.132 |
senal | +0.127 |
Masquerade | +0.125 |
pse | +0.122 |
Rollins | +0.120 |
Neg logit contributions | |
uble | -0.149 |
outer | -0.147 |
oro | -0.142 |
oster | -0.136 |
TEXTURE | -0.133 |
Token | comments |
Token ID | 3651 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
uble | +0.669 |
outer | +0.666 |
oro | +0.645 |
oster | +0.619 |
TEXTURE | +0.605 |
Neg logit contributions | |
senal | -0.574 |
leaflets | -0.567 |
Masquerade | -0.542 |
pse | -0.533 |
cffff | -0.532 |
Token | are |
Token ID | 389 |
Feature activation | -8.69e-02 |
Pos logit contributions | |
uble | +0.854 |
outer | +0.843 |
oro | +0.822 |
oster | +0.783 |
TEXTURE | +0.761 |
Neg logit contributions | |
leaflets | -0.902 |
senal | -0.899 |
Masquerade | -0.858 |
pse | -0.844 |
cffff | -0.842 |
Token | minimized |
Token ID | 49491 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
leaflets | +0.362 |
senal | +0.340 |
Masquerade | +0.336 |
pse | +0.328 |
Rollins | +0.322 |
Neg logit contributions | |
uble | -0.511 |
outer | -0.506 |
oro | -0.491 |
oster | -0.471 |
olphins | -0.463 |
Token | . |
Token ID | 13 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
leaflets | +1.287 |
Masquerade | +1.198 |
senal | +1.194 |
pse | +1.178 |
Rollins | +1.166 |
Neg logit contributions | |
uble | -1.321 |
outer | -1.306 |
oro | -1.261 |
oster | -1.199 |
olphins | -1.182 |
Token |
|
Token ID | 198 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
leaflets | +0.812 |
senal | +0.772 |
Masquerade | +0.769 |
pse | +0.755 |
Rollins | +0.746 |
Neg logit contributions | |
uble | -0.671 |
outer | -0.662 |
oro | -0.636 |
oster | -0.602 |
olphins | -0.590 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
leaflets | +0.824 |
Masquerade | +0.779 |
Rollins | +0.760 |
Dent | +0.757 |
als | +0.745 |
Neg logit contributions | |
uble | -0.703 |
outer | -0.692 |
oro | -0.665 |
oster | -0.629 |
olphins | -0.621 |
Token | Twitter |
Token ID | 14254 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
leaflets | +0.509 |
senal | +0.484 |
Masquerade | +0.481 |
pse | +0.473 |
Rollins | +0.467 |
Neg logit contributions | |
uble | -0.434 |
outer | -0.428 |
oro | -0.412 |
oster | -0.391 |
olphins | -0.382 |
Token | : |
Token ID | 25 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
leaflets | +2.386 |
Masquerade | +2.229 |
senal | +2.224 |
pse | +2.179 |
Rollins | +2.151 |
Neg logit contributions | |
uble | -2.871 |
outer | -2.844 |
oro | -2.742 |
oster | -2.628 |
olphins | -2.593 |
Token | @ |
Token ID | 2488 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
leaflets | +4.501 |
Masquerade | +4.144 |
pse | +4.129 |
Dent | +4.110 |
Rollins | +4.083 |
Neg logit contributions | |
uble | -5.156 |
outer | -5.025 |
oro | -4.874 |
TEXTURE | -4.673 |
oster | -4.669 |
Token | brand |
Token ID | 17938 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
leaflets | +0.856 |
senal | +0.817 |
Masquerade | +0.811 |
pse | +0.798 |
Rollins | +0.788 |
Neg logit contributions | |
uble | -0.664 |
outer | -0.657 |
oro | -0.629 |
oster | -0.595 |
olphins | -0.580 |
Token | t |
Token ID | 83 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
leaflets | +0.062 |
senal | +0.059 |
Masquerade | +0.059 |
pse | +0.058 |
Rollins | +0.057 |
Neg logit contributions | |
uble | -0.049 |
outer | -0.048 |
oro | -0.046 |
oster | -0.044 |
olphins | -0.043 |
Token | st |
Token ID | 301 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
leaflets | +1.662 |
senal | +1.573 |
Masquerade | +1.565 |
pse | +1.552 |
Rollins | +1.535 |
Neg logit contributions | |
uble | -1.250 |
outer | -1.229 |
oro | -1.176 |
oster | -1.109 |
TEXTURE | -1.103 |
Token | rib |
Token ID | 822 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
uble | +0.829 |
outer | +0.819 |
oro | +0.790 |
oster | +0.745 |
olphins | +0.727 |
Neg logit contributions | |
leaflets | -1.019 |
senal | -0.976 |
Masquerade | -0.966 |
pse | -0.952 |
Rollins | -0.934 |
Token | G |
Token ID | 402 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
leaflets | +0.761 |
senal | +0.719 |
Masquerade | +0.712 |
pse | +0.698 |
Rollins | +0.686 |
Neg logit contributions | |
uble | -0.898 |
outer | -0.889 |
oro | -0.859 |
oster | -0.823 |
olphins | -0.808 |
Token | Q |
Token ID | 48 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
leaflets | +1.889 |
senal | +1.769 |
Masquerade | +1.767 |
pse | +1.726 |
Rollins | +1.719 |
Neg logit contributions | |
uble | -1.886 |
outer | -1.855 |
oro | -1.777 |
oster | -1.706 |
TEXTURE | -1.682 |
Token | ( |
Token ID | 357 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
leaflets | +2.667 |
Masquerade | +2.502 |
senal | +2.466 |
pse | +2.418 |
Dent | +2.403 |
Neg logit contributions | |
uble | -3.511 |
outer | -3.450 |
oro | -3.342 |
oster | -3.195 |
TEXTURE | -3.189 |
Token | read |
Token ID | 961 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
leaflets | +0.823 |
senal | +0.784 |
Masquerade | +0.781 |
pse | +0.767 |
Rollins | +0.758 |
Neg logit contributions | |
uble | -0.633 |
outer | -0.622 |
oro | -0.597 |
oster | -0.565 |
olphins | -0.554 |
Token | the |
Token ID | 262 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
leaflets | +1.375 |
senal | +1.293 |
Masquerade | +1.287 |
pse | +1.262 |
Rollins | +1.243 |
Neg logit contributions | |
uble | -1.594 |
outer | -1.575 |
oro | -1.524 |
oster | -1.457 |
TEXTURE | -1.432 |
Token | full |
Token ID | 1336 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
leaflets | +2.473 |
Masquerade | +2.298 |
senal | +2.275 |
pse | +2.249 |
Rollins | +2.206 |
Neg logit contributions | |
uble | -3.182 |
outer | -3.120 |
oro | -3.042 |
oster | -2.913 |
olphins | -2.875 |
Token | profile |
Token ID | 7034 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
leaflets | +3.954 |
Masquerade | +3.644 |
pse | +3.545 |
Dent | +3.494 |
senal | +3.473 |
Neg logit contributions | |
uble | -5.548 |
outer | -5.346 |
oro | -5.265 |
oster | -5.057 |
TEXTURE | -5.023 |
Token | here |
Token ID | 994 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
leaflets | +1.198 |
senal | +1.143 |
Masquerade | +1.136 |
pse | +1.118 |
Rollins | +1.104 |
Neg logit contributions | |
uble | -0.903 |
outer | -0.891 |
oro | -0.854 |
oster | -0.807 |
olphins | -0.788 |
Token | ). |
Token ID | 737 |
Feature activation | -8.49e-02 |
Pos logit contributions | |
leaflets | +2.711 |
senal | +2.523 |
Masquerade | +2.519 |
pse | +2.480 |
Rollins | +2.450 |
Neg logit contributions | |
uble | -3.005 |
outer | -2.976 |
oro | -2.869 |
oster | -2.742 |
TEXTURE | -2.706 |
Token | Talking |
Token ID | 33445 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
leaflets | +0.325 |
senal | +0.311 |
Masquerade | +0.305 |
pse | +0.304 |
Rollins | +0.295 |
Neg logit contributions | |
uble | -0.287 |
outer | -0.283 |
oro | -0.273 |
oster | -0.260 |
olphins | -0.254 |
Token | Points |
Token ID | 11045 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
uble | +0.671 |
outer | +0.662 |
oro | +0.641 |
oster | +0.613 |
olphins | +0.603 |
Neg logit contributions | |
leaflets | -0.585 |
senal | -0.552 |
Masquerade | -0.547 |
pse | -0.538 |
Rollins | -0.528 |
Token | ing |
Token ID | 278 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
leaflets | +1.638 |
senal | +1.538 |
Masquerade | +1.532 |
pse | +1.504 |
Rollins | +1.480 |
Neg logit contributions | |
uble | -1.731 |
outer | -1.716 |
oro | -1.649 |
oster | -1.578 |
TEXTURE | -1.551 |
Token | to |
Token ID | 284 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
uble | +0.222 |
outer | +0.219 |
oro | +0.211 |
oster | +0.200 |
olphins | +0.195 |
Neg logit contributions | |
leaflets | -0.265 |
senal | -0.254 |
Masquerade | -0.251 |
pse | -0.247 |
Rollins | -0.244 |
Token | other |
Token ID | 584 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
leaflets | +0.496 |
senal | +0.472 |
Masquerade | +0.464 |
pse | +0.456 |
Rollins | +0.447 |
Neg logit contributions | |
uble | -0.588 |
outer | -0.583 |
oro | -0.563 |
oster | -0.539 |
olphins | -0.529 |
Token | browsers |
Token ID | 22616 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
uble | +0.483 |
outer | +0.477 |
oro | +0.457 |
oster | +0.428 |
olphins | +0.418 |
Neg logit contributions | |
leaflets | -0.728 |
senal | -0.712 |
Masquerade | -0.695 |
pse | -0.685 |
Rollins | -0.678 |
Token | , |
Token ID | 11 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
leaflets | +1.721 |
Masquerade | +1.618 |
senal | +1.598 |
pse | +1.589 |
Rollins | +1.574 |
Neg logit contributions | |
uble | -1.558 |
outer | -1.539 |
oro | -1.478 |
oster | -1.409 |
TEXTURE | -1.392 |
Token | Mozilla |
Token ID | 29258 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
uble | +0.066 |
outer | +0.066 |
oro | +0.064 |
oster | +0.060 |
olphins | +0.059 |
Neg logit contributions | |
leaflets | -0.064 |
senal | -0.062 |
Masquerade | -0.060 |
pse | -0.059 |
Rollins | -0.058 |
Token | has |
Token ID | 468 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
leaflets | +3.724 |
Masquerade | +3.501 |
pse | +3.403 |
senal | +3.358 |
Rollins | +3.346 |
Neg logit contributions | |
uble | -5.087 |
outer | -5.045 |
oro | -4.844 |
oster | -4.644 |
olphins | -4.638 |
Token | said |
Token ID | 531 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
leaflets | +1.532 |
Masquerade | +1.425 |
senal | +1.414 |
pse | +1.393 |
Rollins | +1.374 |
Neg logit contributions | |
uble | -2.047 |
outer | -2.026 |
oro | -1.962 |
oster | -1.876 |
olphins | -1.860 |
Token | . |
Token ID | 13 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
leaflets | +1.515 |
Masquerade | +1.437 |
senal | +1.429 |
pse | +1.412 |
Rollins | +1.397 |
Neg logit contributions | |
uble | -1.091 |
outer | -1.081 |
oro | -1.032 |
oster | -0.971 |
olphins | -0.955 |
Token |
|
Token ID | 198 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
uble | +0.235 |
outer | +0.233 |
oro | +0.224 |
oster | +0.212 |
olphins | +0.208 |
Neg logit contributions | |
leaflets | -0.283 |
senal | -0.272 |
pse | -0.265 |
Masquerade | -0.264 |
cffff | -0.257 |
Token |
|
Token ID | 198 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
uble | +0.161 |
outer | +0.159 |
oro | +0.152 |
oster | +0.144 |
olphins | +0.142 |
Neg logit contributions | |
leaflets | -0.200 |
Masquerade | -0.189 |
senal | -0.185 |
Rollins | -0.184 |
pse | -0.183 |
Token | it |
Token ID | 340 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
leaflets | +0.743 |
senal | +0.699 |
Masquerade | +0.698 |
pse | +0.685 |
Rollins | +0.674 |
Neg logit contributions | |
uble | -0.798 |
outer | -0.789 |
oro | -0.761 |
oster | -0.727 |
olphins | -0.715 |
Token | is |
Token ID | 318 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
uble | +0.169 |
outer | +0.167 |
oro | +0.160 |
oster | +0.151 |
olphins | +0.148 |
Neg logit contributions | |
leaflets | -0.214 |
senal | -0.205 |
Masquerade | -0.203 |
pse | -0.199 |
Rollins | -0.197 |
Token | ). |
Token ID | 737 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
leaflets | +1.515 |
senal | +1.417 |
Masquerade | +1.416 |
pse | +1.394 |
Rollins | +1.368 |
Neg logit contributions | |
uble | -1.695 |
outer | -1.677 |
oro | -1.619 |
oster | -1.550 |
olphins | -1.523 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
uble | +0.821 |
outer | +0.815 |
oro | +0.788 |
oster | +0.741 |
olphins | +0.722 |
Neg logit contributions | |
leaflets | -1.032 |
senal | -1.001 |
Masquerade | -0.968 |
pse | -0.951 |
Rollins | -0.940 |
Token |
|
Token ID | 198 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
leaflets | +0.398 |
Masquerade | +0.377 |
Rollins | +0.367 |
Dent | +0.366 |
pse | +0.364 |
Neg logit contributions | |
uble | -0.329 |
outer | -0.325 |
oro | -0.312 |
oster | -0.295 |
olphins | -0.291 |
Token | sudo |
Token ID | 24032 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
leaflets | +0.602 |
senal | +0.571 |
Masquerade | +0.564 |
pse | +0.553 |
Rollins | +0.545 |
Neg logit contributions | |
uble | -0.632 |
outer | -0.626 |
oro | -0.603 |
oster | -0.575 |
olphins | -0.564 |
Token | system |
Token ID | 1080 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
leaflets | +4.376 |
Masquerade | +4.109 |
pse | +4.078 |
senal | +4.010 |
Dent | +3.939 |
Neg logit contributions | |
uble | -4.838 |
outer | -4.804 |
oro | -4.619 |
oster | -4.433 |
TEXTURE | -4.359 |
Token | ctl |
Token ID | 34168 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
leaflets | +0.082 |
senal | +0.081 |
Masquerade | +0.079 |
pse | +0.078 |
Dent | +0.077 |
Neg logit contributions | |
outer | -0.032 |
uble | -0.032 |
oro | -0.030 |
oster | -0.028 |
=~ | -0.027 |
Token | restart |
Token ID | 15765 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
leaflets | +1.728 |
senal | +1.652 |
Masquerade | +1.622 |
pse | +1.587 |
Rollins | +1.557 |
Neg logit contributions | |
uble | -2.026 |
outer | -2.012 |
oro | -1.939 |
oster | -1.860 |
olphins | -1.819 |
Token | network |
Token ID | 3127 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
leaflets | +2.594 |
Masquerade | +2.434 |
senal | +2.418 |
pse | +2.402 |
Rollins | +2.350 |
Neg logit contributions | |
uble | -2.645 |
outer | -2.617 |
oro | -2.527 |
oster | -2.416 |
TEXTURE | -2.388 |
Token | - |
Token ID | 12 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
uble | +0.596 |
outer | +0.593 |
oro | +0.571 |
oster | +0.545 |
olphins | +0.531 |
Neg logit contributions | |
leaflets | -0.580 |
senal | -0.550 |
Masquerade | -0.544 |
pse | -0.532 |
Dent | -0.526 |