Token |
|
Token ID | 198 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
mond | +0.857 |
olate | +0.818 |
strip | +0.795 |
sole | +0.780 |
wo | +0.771 |
Neg logit contributions | |
Cipher | -0.874 |
rez | -0.861 |
iewicz | -0.845 |
signatures | -0.791 |
NX | -0.779 |
Token | AB |
Token ID | 6242 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
mond | +0.275 |
olate | +0.261 |
ccording | +0.259 |
strip | +0.253 |
sole | +0.247 |
Neg logit contributions | |
Cipher | -0.396 |
rez | -0.391 |
iewicz | -0.388 |
signatures | -0.365 |
vier | -0.360 |
Token | : |
Token ID | 25 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
Cipher | +0.529 |
rez | +0.524 |
iewicz | +0.512 |
signatures | +0.459 |
NX | +0.452 |
Neg logit contributions | |
mond | -0.985 |
olate | -0.953 |
strip | -0.934 |
ccording | -0.934 |
sole | -0.921 |
Token | [ |
Token ID | 685 |
Feature activation | +9.12e-02 |
Pos logit contributions | |
Cipher | +0.178 |
rez | +0.177 |
iewicz | +0.175 |
signatures | +0.162 |
vier | +0.161 |
Neg logit contributions | |
mond | -0.181 |
olate | -0.175 |
ccording | -0.174 |
strip | -0.170 |
sole | -0.166 |
Token | As |
Token ID | 1722 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
mond | +0.377 |
olate | +0.361 |
ccording | +0.360 |
strip | +0.351 |
sole | +0.344 |
Neg logit contributions | |
Cipher | -0.461 |
rez | -0.456 |
iewicz | -0.453 |
signatures | -0.422 |
NX | -0.418 |
Token | if |
Token ID | 611 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
mond | +1.796 |
olate | +1.719 |
ccording | +1.694 |
strip | +1.655 |
sole | +1.628 |
Neg logit contributions | |
Cipher | -1.541 |
rez | -1.540 |
iewicz | -1.514 |
vier | -1.389 |
pps | -1.374 |
Token | counting |
Token ID | 14143 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
mond | +6.859 |
olate | +6.713 |
strip | +6.391 |
wo | +6.319 |
ccording | +6.301 |
Neg logit contributions | |
rez | -6.627 |
iewicz | -6.578 |
Cipher | -6.461 |
vier | -5.952 |
pps | -5.871 |
Token | before |
Token ID | 878 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
mond | +2.010 |
olate | +1.936 |
ccording | +1.916 |
strip | +1.897 |
sole | +1.852 |
Neg logit contributions | |
Cipher | -1.693 |
rez | -1.687 |
iewicz | -1.661 |
vier | -1.512 |
pps | -1.506 |
Token | a |
Token ID | 257 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
mond | +1.014 |
olate | +0.977 |
ccording | +0.970 |
strip | +0.951 |
sole | +0.932 |
Neg logit contributions | |
Cipher | -0.964 |
rez | -0.955 |
iewicz | -0.945 |
signatures | -0.867 |
vier | -0.865 |
Token | song |
Token ID | 3496 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
mond | +0.961 |
olate | +0.924 |
ccording | +0.922 |
strip | +0.898 |
sole | +0.882 |
Neg logit contributions | |
Cipher | -1.062 |
rez | -1.055 |
iewicz | -1.042 |
signatures | -0.968 |
vier | -0.963 |
Token | ] |
Token ID | 60 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
mond | +2.156 |
olate | +2.053 |
ccording | +2.026 |
strip | +2.016 |
sole | +1.968 |
Neg logit contributions | |
Cipher | -2.223 |
rez | -2.214 |
iewicz | -2.189 |
vier | -2.035 |
NX | -2.012 |
Token | my |
Token ID | 616 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
mond | +1.450 |
olate | +1.393 |
ccording | +1.372 |
strip | +1.353 |
sole | +1.331 |
Neg logit contributions | |
Cipher | -1.338 |
rez | -1.319 |
iewicz | -1.308 |
signatures | -1.193 |
vier | -1.188 |
Token | 70 |
Token ID | 4317 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
mond | +1.091 |
olate | +1.047 |
ccording | +1.016 |
strip | +0.998 |
sole | +0.991 |
Neg logit contributions | |
Cipher | -1.522 |
rez | -1.504 |
iewicz | -1.488 |
vier | -1.388 |
pps | -1.371 |
Token | s |
Token ID | 82 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
mond | +0.065 |
olate | +0.062 |
ccording | +0.062 |
strip | +0.060 |
sole | +0.059 |
Neg logit contributions | |
Cipher | -0.084 |
rez | -0.083 |
iewicz | -0.082 |
signatures | -0.077 |
vier | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
Cipher | +1.025 |
rez | +1.016 |
iewicz | +1.002 |
signatures | +0.917 |
NX | +0.902 |
Neg logit contributions | |
mond | -1.390 |
ccording | -1.350 |
olate | -1.349 |
strip | -1.315 |
sole | -1.294 |
Token | God |
Token ID | 1793 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
mond | +0.061 |
olate | +0.059 |
ccording | +0.059 |
strip | +0.057 |
sole | +0.056 |
Neg logit contributions | |
Cipher | -0.064 |
rez | -0.063 |
iewicz | -0.063 |
signatures | -0.058 |
vier | -0.057 |
Token | willing |
Token ID | 4684 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
mond | +2.517 |
olate | +2.423 |
ccording | +2.386 |
strip | +2.324 |
sole | +2.289 |
Neg logit contributions | |
Cipher | -2.487 |
iewicz | -2.462 |
rez | -2.447 |
vier | -2.247 |
signatures | -2.246 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
mond | +6.613 |
olate | +6.314 |
ccording | +6.140 |
strip | +6.073 |
wo | +5.982 |
Neg logit contributions | |
Cipher | -6.262 |
rez | -6.049 |
iewicz | -6.044 |
vier | -5.597 |
signatures | -5.460 |
Token | I |
Token ID | 314 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Cipher | +0.535 |
rez | +0.530 |
iewicz | +0.524 |
signatures | +0.485 |
NX | +0.480 |
Neg logit contributions | |
mond | -0.535 |
ccording | -0.517 |
olate | -0.516 |
strip | -0.502 |
sole | -0.493 |
Token | � |
Token ID | 447 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
mond | +0.624 |
olate | +0.602 |
ccording | +0.596 |
strip | +0.586 |
sole | +0.576 |
Neg logit contributions | |
Cipher | -0.626 |
rez | -0.614 |
iewicz | -0.608 |
signatures | -0.566 |
NX | -0.560 |
Token | � |
Token ID | 247 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
Cipher | +0.884 |
rez | +0.879 |
iewicz | +0.871 |
signatures | +0.825 |
vier | +0.818 |
Neg logit contributions | |
mond | -0.387 |
ccording | -0.365 |
olate | -0.364 |
strip | -0.347 |
sole | -0.336 |
Token | d |
Token ID | 67 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
Cipher | +0.442 |
rez | +0.439 |
iewicz | +0.433 |
signatures | +0.402 |
vier | +0.398 |
Neg logit contributions | |
mond | -0.430 |
ccording | -0.416 |
olate | -0.415 |
strip | -0.403 |
sole | -0.395 |
Token | can |
Token ID | 460 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
mond | +1.218 |
olate | +1.175 |
ccording | +1.165 |
strip | +1.149 |
sole | +1.129 |
Neg logit contributions | |
Cipher | -1.200 |
rez | -1.170 |
iewicz | -1.168 |
signatures | -1.087 |
NX | -1.074 |
Token | � |
Token ID | 447 |
Feature activation | -5.97e-03 |
Pos logit contributions | |
mond | +0.855 |
olate | +0.824 |
ccording | +0.815 |
strip | +0.803 |
sole | +0.786 |
Neg logit contributions | |
Cipher | -0.911 |
rez | -0.899 |
iewicz | -0.889 |
signatures | -0.825 |
vier | -0.820 |
Token | � |
Token ID | 247 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Cipher | +0.038 |
rez | +0.038 |
iewicz | +0.038 |
signatures | +0.036 |
NX | +0.035 |
Neg logit contributions | |
mond | -0.017 |
olate | -0.016 |
ccording | -0.015 |
strip | -0.015 |
sole | -0.014 |
Token | t |
Token ID | 83 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
mond | +1.052 |
olate | +1.003 |
strip | +0.977 |
sole | +0.967 |
ccording | +0.959 |
Neg logit contributions | |
Cipher | -1.180 |
iewicz | -1.156 |
rez | -1.140 |
signatures | -1.079 |
NX | -1.076 |
Token | help |
Token ID | 1037 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
mond | +1.174 |
olate | +1.127 |
strip | +1.096 |
ccording | +1.089 |
sole | +1.074 |
Neg logit contributions | |
Cipher | -1.468 |
rez | -1.440 |
iewicz | -1.437 |
vier | -1.333 |
NX | -1.332 |
Token | but |
Token ID | 475 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
mond | +2.258 |
olate | +2.157 |
ccording | +2.143 |
strip | +2.106 |
sole | +2.043 |
Neg logit contributions | |
Cipher | -3.109 |
rez | -3.092 |
iewicz | -3.049 |
signatures | -2.846 |
vier | -2.832 |
Token | wonder |
Token ID | 4240 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
mond | +4.904 |
olate | +4.690 |
strip | +4.649 |
sole | +4.451 |
wo | +4.411 |
Neg logit contributions | |
Cipher | -7.225 |
rez | -7.087 |
iewicz | -7.057 |
vier | -6.609 |
NX | -6.472 |
Token | if |
Token ID | 611 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
mond | +1.493 |
olate | +1.431 |
strip | +1.388 |
ccording | +1.374 |
sole | +1.366 |
Neg logit contributions | |
Cipher | -1.357 |
rez | -1.356 |
iewicz | -1.323 |
signatures | -1.219 |
pps | -1.210 |
Token | a |
Token ID | 257 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
mond | +1.057 |
olate | +1.018 |
ccording | +1.008 |
strip | +0.990 |
sole | +0.967 |
Neg logit contributions | |
Cipher | -0.990 |
rez | -0.984 |
iewicz | -0.969 |
signatures | -0.891 |
vier | -0.891 |
Token | better |
Token ID | 1365 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Cipher | +0.118 |
rez | +0.117 |
iewicz | +0.115 |
signatures | +0.107 |
NX | +0.106 |
Neg logit contributions | |
mond | -0.108 |
ccording | -0.104 |
olate | -0.104 |
strip | -0.100 |
sole | -0.099 |
Token | choice |
Token ID | 3572 |
Feature activation | +6.08e-03 |
Pos logit contributions | |
Cipher | +0.691 |
rez | +0.685 |
iewicz | +0.678 |
signatures | +0.630 |
vier | +0.622 |
Neg logit contributions | |
mond | -0.642 |
ccording | -0.619 |
olate | -0.619 |
strip | -0.600 |
sole | -0.589 |
Token | E |
Token ID | 36 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
mond | +1.710 |
olate | +1.587 |
strip | +1.544 |
sole | +1.508 |
wo | +1.502 |
Neg logit contributions | |
Cipher | -2.265 |
rez | -2.256 |
iewicz | -2.234 |
signatures | -2.102 |
vier | -2.081 |
Token | , |
Token ID | 11 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
mond | +0.550 |
ccording | +0.533 |
olate | +0.533 |
strip | +0.520 |
sole | +0.511 |
Neg logit contributions | |
Cipher | -0.398 |
rez | -0.392 |
iewicz | -0.390 |
signatures | -0.354 |
vier | -0.351 |
Token | DP |
Token ID | 6322 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
mond | +0.146 |
ccording | +0.139 |
olate | +0.138 |
strip | +0.134 |
sole | +0.131 |
Neg logit contributions | |
Cipher | -0.228 |
rez | -0.225 |
iewicz | -0.224 |
signatures | -0.211 |
vier | -0.208 |
Token | 02 |
Token ID | 2999 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
mond | +1.176 |
olate | +1.139 |
ccording | +1.134 |
strip | +1.104 |
sole | +1.085 |
Neg logit contributions | |
Cipher | -0.986 |
rez | -0.973 |
iewicz | -0.967 |
signatures | -0.888 |
vier | -0.871 |
Token | _ |
Token ID | 62 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
mond | +2.961 |
olate | +2.680 |
strip | +2.633 |
sole | +2.542 |
wo | +2.532 |
Neg logit contributions | |
Cipher | -4.709 |
rez | -4.541 |
iewicz | -4.510 |
ModLoader | -4.414 |
signatures | -4.344 |
Token | 00 |
Token ID | 405 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
mond | +0.868 |
olate | +0.837 |
ccording | +0.830 |
strip | +0.814 |
sole | +0.799 |
Neg logit contributions | |
Cipher | -0.753 |
rez | -0.742 |
iewicz | -0.740 |
signatures | -0.682 |
NX | -0.667 |
Token | 64 |
Token ID | 2414 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
mond | +4.710 |
olate | +4.368 |
sole | +4.236 |
strip | +4.223 |
ccording | +4.158 |
Neg logit contributions | |
Cipher | -6.353 |
iewicz | -6.341 |
rez | -6.316 |
vier | -5.859 |
signatures | -5.799 |
Token | E |
Token ID | 36 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
mond | +2.002 |
olate | +1.828 |
strip | +1.795 |
sole | +1.753 |
wo | +1.747 |
Neg logit contributions | |
Cipher | -2.756 |
rez | -2.740 |
iewicz | -2.706 |
signatures | -2.576 |
vier | -2.528 |
Token | , |
Token ID | 11 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
Cipher | +0.130 |
rez | +0.128 |
iewicz | +0.126 |
signatures | +0.115 |
pps | +0.113 |
Neg logit contributions | |
mond | -0.187 |
olate | -0.182 |
ccording | -0.182 |
strip | -0.177 |
sole | -0.175 |
Token | DP |
Token ID | 6322 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Cipher | +0.403 |
rez | +0.400 |
iewicz | +0.396 |
signatures | +0.373 |
vier | +0.369 |
Neg logit contributions | |
mond | -0.260 |
olate | -0.248 |
ccording | -0.248 |
strip | -0.239 |
sole | -0.233 |
Token | 02 |
Token ID | 2999 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
mond | +0.684 |
olate | +0.660 |
strip | +0.638 |
ccording | +0.629 |
sole | +0.627 |
Neg logit contributions | |
Cipher | -0.613 |
rez | -0.605 |
iewicz | -0.604 |
signatures | -0.558 |
vier | -0.545 |
Token | field |
Token ID | 2214 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
mond | +0.037 |
olate | +0.035 |
ccording | +0.035 |
strip | +0.035 |
sole | +0.034 |
Neg logit contributions | |
Cipher | -0.037 |
rez | -0.037 |
iewicz | -0.037 |
vier | -0.034 |
signatures | -0.033 |
Token | on |
Token ID | 319 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
Cipher | +0.301 |
rez | +0.297 |
iewicz | +0.294 |
signatures | +0.269 |
vier | +0.266 |
Neg logit contributions | |
mond | -0.378 |
olate | -0.365 |
ccording | -0.364 |
strip | -0.357 |
sole | -0.351 |
Token | military |
Token ID | 2422 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Cipher | +0.178 |
rez | +0.176 |
iewicz | +0.175 |
vier | +0.161 |
pps | +0.160 |
Neg logit contributions | |
mond | -0.179 |
olate | -0.173 |
ccording | -0.171 |
strip | -0.168 |
sole | -0.164 |
Token | operations |
Token ID | 4560 |
Feature activation | -5.37e-03 |
Pos logit contributions | |
Cipher | +0.488 |
rez | +0.482 |
iewicz | +0.475 |
signatures | +0.431 |
vier | +0.429 |
Neg logit contributions | |
mond | -0.688 |
olate | -0.668 |
ccording | -0.666 |
strip | -0.652 |
sole | -0.641 |
Token | ad |
Token ID | 512 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Cipher | +0.022 |
rez | +0.022 |
iewicz | +0.021 |
signatures | +0.020 |
NX | +0.019 |
Neg logit contributions | |
mond | -0.027 |
olate | -0.026 |
ccording | -0.026 |
strip | -0.026 |
sole | -0.025 |
Token | inf |
Token ID | 1167 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
mond | +0.841 |
olate | +0.811 |
ccording | +0.811 |
strip | +0.789 |
sole | +0.775 |
Neg logit contributions | |
Cipher | -0.828 |
rez | -0.819 |
iewicz | -0.811 |
signatures | -0.749 |
NX | -0.742 |
Token | init |
Token ID | 15003 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
mond | +5.447 |
olate | +5.198 |
sole | +4.891 |
airs | +4.859 |
wo | +4.822 |
Neg logit contributions | |
Cipher | -5.545 |
iewicz | -5.447 |
rez | -5.117 |
Reloaded | -5.101 |
NX | -5.075 |
Token | um |
Token ID | 388 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Cipher | +0.694 |
rez | +0.683 |
iewicz | +0.661 |
signatures | +0.618 |
pps | +0.608 |
Neg logit contributions | |
mond | -0.976 |
ccording | -0.968 |
olate | -0.949 |
strip | -0.932 |
sole | -0.908 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
mond | +1.282 |
olate | +1.238 |
ccording | +1.229 |
strip | +1.208 |
sole | +1.187 |
Neg logit contributions | |
Cipher | -1.003 |
rez | -0.987 |
iewicz | -0.978 |
signatures | -0.893 |
NX | -0.889 |
Token | � |
Token ID | 447 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Cipher | +0.922 |
rez | +0.913 |
iewicz | +0.902 |
signatures | +0.829 |
vier | +0.818 |
Neg logit contributions | |
mond | -1.064 |
ccording | -1.031 |
olate | -1.030 |
strip | -1.003 |
sole | -0.987 |
Token | � |
Token ID | 251 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Cipher | +1.555 |
rez | +1.551 |
iewicz | +1.523 |
signatures | +1.455 |
pps | +1.454 |
Neg logit contributions | |
mond | -0.561 |
olate | -0.521 |
ccording | -0.511 |
strip | -0.499 |
sole | -0.481 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
mond | +0.016 |
olate | +0.015 |
ccording | +0.015 |
strip | +0.015 |
sole | +0.014 |
Neg logit contributions | |
Cipher | -0.017 |
rez | -0.017 |
iewicz | -0.017 |
signatures | -0.015 |
NX | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e-03 |
Pos logit contributions | |
Cipher | +0.891 |
rez | +0.881 |
iewicz | +0.869 |
signatures | +0.803 |
NX | +0.793 |
Neg logit contributions | |
mond | -0.992 |
olate | -0.953 |
strip | -0.930 |
ccording | -0.924 |
sole | -0.912 |
Token |
|
Token ID | 198 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
Cipher | +0.005 |
rez | +0.005 |
iewicz | +0.005 |
signatures | +0.005 |
NX | +0.005 |
Neg logit contributions | |
mond | -0.005 |
olate | -0.005 |
strip | -0.005 |
sole | -0.005 |
ccording | -0.005 |
Token | # |
Token ID | 2 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
Cipher | +0.190 |
rez | +0.188 |
iewicz | +0.186 |
signatures | +0.174 |
NX | +0.172 |
Neg logit contributions | |
mond | -0.167 |
olate | -0.161 |
ccording | -0.159 |
strip | -0.156 |
sole | -0.153 |
Token | ad |
Token ID | 324 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
mond | +3.221 |
olate | +3.107 |
strip | +3.069 |
ccording | +3.039 |
sole | +2.929 |
Neg logit contributions | |
Cipher | -3.342 |
rez | -3.316 |
iewicz | -3.302 |
signatures | -3.093 |
NX | -3.088 |
Token | # |
Token ID | 2 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
mond | +1.907 |
ccording | +1.843 |
olate | +1.842 |
strip | +1.799 |
sole | +1.729 |
Neg logit contributions | |
Cipher | -2.410 |
rez | -2.404 |
iewicz | -2.393 |
NX | -2.214 |
pps | -2.198 |
Token | They |
Token ID | 2990 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
mond | +4.471 |
strip | +4.222 |
olate | +4.162 |
wo | +4.088 |
ccording | +3.999 |
Neg logit contributions | |
Cipher | -6.162 |
iewicz | -6.111 |
rez | -6.037 |
signatures | -5.828 |
NX | -5.747 |
Token | d |
Token ID | 288 |
Feature activation | -2.19e-03 |
Pos logit contributions | |
mond | +0.643 |
olate | +0.623 |
ccording | +0.614 |
strip | +0.606 |
sole | +0.592 |
Neg logit contributions | |
Cipher | -0.600 |
rez | -0.587 |
iewicz | -0.584 |
signatures | -0.541 |
NX | -0.537 |
Token | usted |
Token ID | 8459 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
Cipher | +0.010 |
rez | +0.010 |
iewicz | +0.010 |
signatures | +0.010 |
NX | +0.009 |
Neg logit contributions | |
mond | -0.010 |
olate | -0.009 |
ccording | -0.009 |
strip | -0.009 |
sole | -0.009 |
Token | off |
Token ID | 572 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
Cipher | +0.064 |
rez | +0.064 |
iewicz | +0.063 |
pps | +0.055 |
vier | +0.054 |
Neg logit contributions | |
mond | -0.137 |
olate | -0.132 |
ccording | -0.131 |
strip | -0.130 |
sole | -0.128 |
Token | the |
Token ID | 262 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Cipher | +0.327 |
rez | +0.325 |
iewicz | +0.322 |
signatures | +0.295 |
vier | +0.294 |
Neg logit contributions | |
mond | -0.339 |
olate | -0.327 |
ccording | -0.324 |
strip | -0.319 |
sole | -0.311 |
Token | Belfast |
Token ID | 29713 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
mond | +2.183 |
olate | +2.076 |
ccording | +2.055 |
strip | +2.033 |
sole | +1.973 |
Neg logit contributions | |
iewicz | -2.071 |
Cipher | -2.070 |
rez | -2.060 |
signatures | -1.885 |
vier | -1.884 |
Token | Te |
Token ID | 6767 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
Cipher | +0.691 |
rez | +0.686 |
iewicz | +0.677 |
signatures | +0.635 |
vier | +0.625 |
Neg logit contributions | |
mond | -0.565 |
ccording | -0.545 |
olate | -0.542 |
strip | -0.524 |
sole | -0.515 |
Token | legraph |
Token ID | 16606 |
Feature activation | -9.75e-02 |
Pos logit contributions | |
Cipher | +0.341 |
rez | +0.338 |
iewicz | +0.336 |
signatures | +0.310 |
NX | +0.306 |
Neg logit contributions | |
mond | -0.324 |
olate | -0.311 |
ccording | -0.310 |
strip | -0.303 |
sole | -0.297 |
Token | . |
Token ID | 13 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
Cipher | +0.372 |
rez | +0.368 |
iewicz | +0.363 |
signatures | +0.330 |
vier | +0.326 |
Neg logit contributions | |
mond | -0.522 |
olate | -0.506 |
ccording | -0.504 |
strip | -0.494 |
sole | -0.485 |
Token | co |
Token ID | 1073 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
mond | +1.891 |
olate | +1.749 |
strip | +1.720 |
wo | +1.680 |
sole | +1.658 |
Neg logit contributions | |
Cipher | -2.688 |
iewicz | -2.638 |
rez | -2.622 |
signatures | -2.455 |
iffe | -2.423 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
mond | +1.354 |
olate | +1.300 |
strip | +1.268 |
sole | +1.239 |
wo | +1.222 |
Neg logit contributions | |
Cipher | -1.075 |
rez | -1.044 |
iewicz | -1.032 |
signatures | -0.962 |
NX | -0.945 |
Token | uk |
Token ID | 2724 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
mond | +6.441 |
strip | +6.154 |
olate | +6.120 |
wo | +6.016 |
sole | +5.942 |
Neg logit contributions | |
Cipher | -4.428 |
iewicz | -4.121 |
rez | -4.073 |
signatures | -3.952 |
NX | -3.886 |
Token | Dis |
Token ID | 3167 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
Cipher | +0.925 |
rez | +0.914 |
iewicz | +0.904 |
signatures | +0.832 |
NX | +0.823 |
Neg logit contributions | |
mond | -1.049 |
ccording | -1.018 |
olate | -1.016 |
strip | -0.989 |
sole | -0.973 |
Token | ruption |
Token ID | 6417 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
mond | +0.215 |
olate | +0.206 |
ccording | +0.206 |
strip | +0.200 |
sole | +0.196 |
Neg logit contributions | |
Cipher | -0.255 |
rez | -0.253 |
iewicz | -0.250 |
signatures | -0.233 |
NX | -0.231 |
Token | is |
Token ID | 318 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
Cipher | +0.507 |
rez | +0.502 |
iewicz | +0.496 |
signatures | +0.456 |
vier | +0.451 |
Neg logit contributions | |
mond | -0.588 |
olate | -0.568 |
ccording | -0.567 |
strip | -0.554 |
sole | -0.544 |
Token | perhaps |
Token ID | 3737 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
mond | +0.215 |
olate | +0.207 |
ccording | +0.207 |
strip | +0.201 |
sole | +0.197 |
Neg logit contributions | |
Cipher | -0.211 |
rez | -0.209 |
iewicz | -0.207 |
signatures | -0.191 |
vier | -0.190 |
Token | py |
Token ID | 9078 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
mond | +2.328 |
strip | +2.186 |
olate | +2.181 |
sole | +2.120 |
wo | +2.098 |
Neg logit contributions | |
Cipher | -2.473 |
iewicz | -2.360 |
rez | -2.325 |
signatures | -2.250 |
NX | -2.239 |
Token | _ |
Token ID | 62 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
mond | +0.992 |
olate | +0.957 |
ccording | +0.957 |
strip | +0.933 |
sole | +0.912 |
Neg logit contributions | |
Cipher | -1.018 |
rez | -1.007 |
iewicz | -1.001 |
signatures | -0.923 |
vier | -0.916 |
Token | speed |
Token ID | 12287 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
mond | +1.038 |
olate | +0.995 |
ccording | +0.987 |
strip | +0.982 |
sole | +0.954 |
Neg logit contributions | |
Cipher | -1.224 |
iewicz | -1.202 |
rez | -1.190 |
NX | -1.115 |
signatures | -1.113 |
Token | _ |
Token ID | 62 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
mond | +1.707 |
olate | +1.647 |
ccording | +1.628 |
strip | +1.620 |
sole | +1.573 |
Neg logit contributions | |
Cipher | -1.649 |
rez | -1.636 |
iewicz | -1.620 |
signatures | -1.493 |
NX | -1.479 |
Token | com |
Token ID | 785 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
mond | +0.970 |
olate | +0.928 |
strip | +0.919 |
ccording | +0.916 |
sole | +0.885 |
Neg logit contributions | |
Cipher | -1.116 |
iewicz | -1.092 |
rez | -1.090 |
signatures | -1.015 |
NX | -1.014 |
Token | par |
Token ID | 1845 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Cipher | +1.287 |
rez | +1.280 |
iewicz | +1.264 |
signatures | +1.188 |
pps | +1.177 |
Neg logit contributions | |
mond | -0.877 |
ccording | -0.847 |
olate | -0.845 |
strip | -0.814 |
sole | -0.796 |
Token | ison |
Token ID | 1653 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
mond | +5.132 |
olate | +4.875 |
strip | +4.790 |
sole | +4.602 |
airs | +4.550 |
Neg logit contributions | |
Cipher | -5.402 |
iewicz | -5.326 |
rez | -5.323 |
NX | -4.975 |
secrets | -4.945 |
Token | , |
Token ID | 11 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
Cipher | +0.281 |
rez | +0.278 |
iewicz | +0.275 |
signatures | +0.255 |
vier | +0.252 |
Neg logit contributions | |
mond | -0.284 |
olate | -0.274 |
ccording | -0.274 |
strip | -0.267 |
sole | -0.262 |
Token | 0 |
Token ID | 657 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
mond | +0.198 |
olate | +0.191 |
ccording | +0.190 |
strip | +0.187 |
sole | +0.182 |
Neg logit contributions | |
Cipher | -0.185 |
rez | -0.184 |
iewicz | -0.184 |
vier | -0.168 |
signatures | -0.167 |
Token | ) |
Token ID | 8 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
mond | +0.077 |
olate | +0.075 |
ccording | +0.074 |
strip | +0.073 |
sole | +0.071 |
Neg logit contributions | |
Cipher | -0.068 |
rez | -0.067 |
iewicz | -0.066 |
signatures | -0.061 |
vier | -0.060 |
Token | RE |
Token ID | 4526 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Cipher | +0.597 |
rez | +0.592 |
iewicz | +0.586 |
signatures | +0.538 |
vier | +0.535 |
Neg logit contributions | |
mond | -0.655 |
olate | -0.633 |
ccording | -0.632 |
strip | -0.616 |
sole | -0.604 |
Token | ina |
Token ID | 1437 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
mond | +2.545 |
olate | +2.440 |
ccording | +2.382 |
strip | +2.353 |
sole | +2.342 |
Neg logit contributions | |
Cipher | -2.436 |
rez | -2.348 |
iewicz | -2.342 |
signatures | -2.173 |
NX | -2.153 |
Token | a |
Token ID | 257 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
mond | +0.545 |
olate | +0.525 |
ccording | +0.522 |
strip | +0.510 |
sole | +0.503 |
Neg logit contributions | |
Cipher | -0.486 |
rez | -0.480 |
iewicz | -0.474 |
signatures | -0.436 |
vier | -0.432 |
Token | |
Token ID | 220 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
Cipher | +0.615 |
rez | +0.610 |
iewicz | +0.602 |
signatures | +0.558 |
pps | +0.551 |
Neg logit contributions | |
mond | -0.638 |
ccording | -0.616 |
olate | -0.616 |
strip | -0.599 |
sole | -0.587 |
Token | � |
Token ID | 134 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
mond | +0.256 |
olate | +0.244 |
ccording | +0.239 |
strip | +0.232 |
sole | +0.230 |
Neg logit contributions | |
Cipher | -0.405 |
rez | -0.399 |
iewicz | -0.394 |
signatures | -0.372 |
NX | -0.369 |
Token | � |
Token ID | 119 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
mond | +0.217 |
olate | +0.200 |
ccording | +0.196 |
strip | +0.188 |
sole | +0.181 |
Neg logit contributions | |
Cipher | -0.665 |
rez | -0.660 |
iewicz | -0.654 |
signatures | -0.624 |
NX | -0.619 |
Token | ike |
Token ID | 522 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
mond | +0.864 |
olate | +0.833 |
ccording | +0.819 |
strip | +0.803 |
sole | +0.795 |
Neg logit contributions | |
Cipher | -0.852 |
rez | -0.832 |
iewicz | -0.821 |
signatures | -0.771 |
NX | -0.761 |
Token | p |
Token ID | 279 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
mond | +5.290 |
olate | +5.021 |
ccording | +4.837 |
sole | +4.816 |
wo | +4.777 |
Neg logit contributions | |
Cipher | -5.286 |
iewicz | -5.126 |
rez | -5.075 |
signatures | -4.653 |
vier | -4.644 |
Token | ū |
Token ID | 20317 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Cipher | +0.454 |
rez | +0.452 |
iewicz | +0.447 |
signatures | +0.415 |
pps | +0.412 |
Neg logit contributions | |
mond | -0.402 |
ccording | -0.389 |
olate | -0.386 |
strip | -0.376 |
sole | -0.368 |
Token | i |
Token ID | 1312 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Cipher | +0.513 |
rez | +0.508 |
iewicz | +0.501 |
signatures | +0.461 |
vier | +0.454 |
Neg logit contributions | |
mond | -0.621 |
ccording | -0.601 |
olate | -0.601 |
strip | -0.586 |
sole | -0.576 |
Token | ke |
Token ID | 885 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
mond | +1.091 |
olate | +1.049 |
ccording | +1.041 |
strip | +1.013 |
sole | +1.003 |
Neg logit contributions | |
Cipher | -1.175 |
rez | -1.161 |
iewicz | -1.147 |
signatures | -1.065 |
vier | -1.056 |
Token | au |
Token ID | 35851 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
mond | +0.745 |
olate | +0.718 |
ccording | +0.714 |
strip | +0.695 |
sole | +0.689 |
Neg logit contributions | |
Cipher | -0.678 |
rez | -0.669 |
iewicz | -0.662 |
signatures | -0.607 |
vier | -0.603 |
Token | prost |
Token ID | 11825 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
mond | +0.706 |
olate | +0.682 |
ccording | +0.681 |
strip | +0.663 |
sole | +0.651 |
Neg logit contributions | |
Cipher | -0.702 |
rez | -0.696 |
iewicz | -0.687 |
signatures | -0.637 |
vier | -0.630 |
Token | hetic |
Token ID | 6587 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
mond | +0.046 |
ccording | +0.044 |
olate | +0.044 |
strip | +0.043 |
sole | +0.042 |
Neg logit contributions | |
Cipher | -0.055 |
rez | -0.055 |
iewicz | -0.054 |
signatures | -0.050 |
vier | -0.050 |
Token | penis |
Token ID | 16360 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
mond | +0.525 |
olate | +0.505 |
ccording | +0.503 |
strip | +0.491 |
sole | +0.482 |
Neg logit contributions | |
Cipher | -0.599 |
rez | -0.594 |
iewicz | -0.588 |
signatures | -0.546 |
vier | -0.543 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
mond | +0.136 |
olate | +0.131 |
ccording | +0.130 |
strip | +0.128 |
sole | +0.126 |
Neg logit contributions | |
Cipher | -0.125 |
rez | -0.123 |
iewicz | -0.122 |
signatures | -0.112 |
vier | -0.111 |
Token | God |
Token ID | 1793 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Cipher | +0.485 |
rez | +0.481 |
iewicz | +0.475 |
signatures | +0.438 |
vier | +0.433 |
Neg logit contributions | |
mond | -0.515 |
olate | -0.497 |
ccording | -0.495 |
strip | -0.484 |
sole | -0.475 |
Token | help |
Token ID | 1037 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
mond | +0.803 |
olate | +0.772 |
ccording | +0.758 |
strip | +0.739 |
sole | +0.730 |
Neg logit contributions | |
Cipher | -0.835 |
rez | -0.826 |
iewicz | -0.822 |
vier | -0.755 |
signatures | -0.755 |
Token | me |
Token ID | 502 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
mond | +4.994 |
olate | +4.675 |
strip | +4.651 |
ccording | +4.477 |
sole | +4.458 |
Neg logit contributions | |
Cipher | -5.326 |
iewicz | -5.264 |
rez | -5.254 |
signatures | -4.897 |
vier | -4.895 |
Token | then |
Token ID | 788 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
mond | +2.224 |
olate | +2.146 |
strip | +2.115 |
ccording | +2.106 |
sole | +2.051 |
Neg logit contributions | |
Cipher | -1.811 |
rez | -1.748 |
iewicz | -1.745 |
signatures | -1.612 |
NX | -1.579 |
Token | , |
Token ID | 11 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
mond | +1.180 |
olate | +1.144 |
ccording | +1.124 |
strip | +1.113 |
sole | +1.091 |
Neg logit contributions | |
Cipher | -1.020 |
rez | -1.004 |
iewicz | -0.993 |
signatures | -0.909 |
vier | -0.903 |
Token | � |
Token ID | 447 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
mond | +1.356 |
olate | +1.311 |
ccording | +1.300 |
strip | +1.278 |
sole | +1.253 |
Neg logit contributions | |
Cipher | -1.190 |
rez | -1.176 |
iewicz | -1.161 |
signatures | -1.067 |
vier | -1.061 |
Token | � |
Token ID | 251 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
mond | +0.590 |
olate | +0.538 |
ccording | +0.500 |
strip | +0.484 |
sole | +0.473 |
Neg logit contributions | |
Cipher | -2.411 |
iewicz | -2.388 |
rez | -2.386 |
signatures | -2.272 |
vier | -2.263 |
Token | E |
Token ID | 36 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
mond | +2.002 |
olate | +1.828 |
strip | +1.795 |
sole | +1.753 |
wo | +1.747 |
Neg logit contributions | |
Cipher | -2.756 |
rez | -2.740 |
iewicz | -2.706 |
signatures | -2.576 |
vier | -2.528 |
Token | , |
Token ID | 11 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
Cipher | +0.130 |
rez | +0.128 |
iewicz | +0.126 |
signatures | +0.115 |
pps | +0.113 |
Neg logit contributions | |
mond | -0.187 |
olate | -0.182 |
ccording | -0.182 |
strip | -0.177 |
sole | -0.175 |
Token | DP |
Token ID | 6322 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Cipher | +0.403 |
rez | +0.400 |
iewicz | +0.396 |
signatures | +0.373 |
vier | +0.369 |
Neg logit contributions | |
mond | -0.260 |
olate | -0.248 |
ccording | -0.248 |
strip | -0.239 |
sole | -0.233 |
Token | 02 |
Token ID | 2999 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
mond | +0.684 |
olate | +0.660 |
strip | +0.638 |
ccording | +0.629 |
sole | +0.627 |
Neg logit contributions | |
Cipher | -0.613 |
rez | -0.605 |
iewicz | -0.604 |
signatures | -0.558 |
vier | -0.545 |
Token | _ |
Token ID | 62 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
mond | +2.661 |
olate | +2.425 |
strip | +2.379 |
sole | +2.297 |
wo | +2.283 |
Neg logit contributions | |
Cipher | -4.132 |
rez | -3.994 |
iewicz | -3.962 |
ModLoader | -3.826 |
signatures | -3.815 |
Token | 00 |
Token ID | 405 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
mond | +0.535 |
olate | +0.517 |
ccording | +0.513 |
strip | +0.502 |
sole | +0.493 |
Neg logit contributions | |
Cipher | -0.457 |
rez | -0.451 |
iewicz | -0.448 |
signatures | -0.413 |
NX | -0.404 |
Token | 65 |
Token ID | 2996 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
mond | +3.397 |
olate | +3.157 |
ccording | +2.983 |
sole | +2.939 |
strip | +2.900 |
Neg logit contributions | |
Cipher | -7.012 |
iewicz | -7.010 |
rez | -6.941 |
signatures | -6.560 |
NX | -6.492 |
Token | E |
Token ID | 36 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
mond | +1.874 |
olate | +1.744 |
strip | +1.691 |
sole | +1.656 |
wo | +1.649 |
Neg logit contributions | |
Cipher | -2.509 |
rez | -2.500 |
iewicz | -2.459 |
signatures | -2.338 |
vier | -2.309 |
Token | & |
Token ID | 5 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Cipher | +0.400 |
rez | +0.397 |
iewicz | +0.389 |
signatures | +0.354 |
pps | +0.349 |
Neg logit contributions | |
mond | -0.595 |
olate | -0.577 |
ccording | -0.576 |
strip | -0.564 |
sole | -0.556 |
Token | for |
Token ID | 1640 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Cipher | +0.891 |
rez | +0.880 |
iewicz | +0.874 |
signatures | +0.813 |
NX | +0.804 |
Neg logit contributions | |
mond | -0.799 |
olate | -0.768 |
ccording | -0.767 |
strip | -0.748 |
sole | -0.732 |
Token | = |
Token ID | 28 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
mond | +0.594 |
olate | +0.574 |
ccording | +0.571 |
strip | +0.558 |
sole | +0.549 |
Neg logit contributions | |
Cipher | -0.557 |
rez | -0.549 |
iewicz | -0.549 |
signatures | -0.503 |
NX | -0.498 |
Token | per |
Token ID | 583 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Cipher | +0.072 |
rez | +0.071 |
iewicz | +0.070 |
signatures | +0.065 |
vier | +0.064 |
Neg logit contributions | |
mond | -0.077 |
ccording | -0.074 |
olate | -0.074 |
strip | -0.072 |
sole | -0.071 |
Token | company |
Token ID | 1664 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
mond | +2.391 |
olate | +2.311 |
ccording | +2.310 |
strip | +2.262 |
sole | +2.223 |
Neg logit contributions | |
Cipher | -2.179 |
rez | -2.174 |
iewicz | -2.151 |
vier | -1.968 |
signatures | -1.962 |
Token | procedure |
Token ID | 8771 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
mond | +0.592 |
ccording | +0.574 |
olate | +0.573 |
strip | +0.561 |
sole | +0.552 |
Neg logit contributions | |
rez | -0.427 |
Cipher | -0.427 |
iewicz | -0.419 |
vier | -0.380 |
signatures | -0.377 |
Token | , |
Token ID | 11 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
mond | +1.070 |
olate | +1.037 |
ccording | +1.037 |
strip | +1.016 |
sole | +0.996 |
Neg logit contributions | |
Cipher | -0.789 |
rez | -0.777 |
iewicz | -0.767 |
signatures | -0.696 |
vier | -0.690 |
Token | realized |
Token ID | 6939 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
mond | +1.896 |
olate | +1.826 |
ccording | +1.804 |
strip | +1.791 |
sole | +1.749 |
Neg logit contributions | |
Cipher | -1.755 |
rez | -1.723 |
iewicz | -1.710 |
vier | -1.572 |
signatures | -1.559 |
Token | instantly |
Token ID | 11101 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
mond | +0.626 |
olate | +0.606 |
ccording | +0.602 |
strip | +0.588 |
sole | +0.576 |
Neg logit contributions | |
Cipher | -0.595 |
rez | -0.593 |
iewicz | -0.586 |
signatures | -0.538 |
vier | -0.535 |
Token | that |
Token ID | 326 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
mond | +4.813 |
olate | +4.690 |
ccording | +4.626 |
wo | +4.505 |
strip | +4.432 |
Neg logit contributions | |
rez | -5.006 |
Cipher | -5.003 |
iewicz | -4.943 |
signatures | -4.556 |
iffe | -4.539 |
Token | an |
Token ID | 281 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
mond | +2.375 |
olate | +2.289 |
ccording | +2.275 |
strip | +2.214 |
sole | +2.172 |
Neg logit contributions | |
rez | -2.357 |
Cipher | -2.351 |
iewicz | -2.345 |
signatures | -2.136 |
vier | -2.136 |
Token | error |
Token ID | 4049 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
mond | +0.445 |
ccording | +0.432 |
olate | +0.427 |
strip | +0.417 |
sole | +0.401 |
Neg logit contributions | |
Cipher | -0.654 |
rez | -0.646 |
iewicz | -0.646 |
vier | -0.599 |
pps | -0.598 |
Token | had |
Token ID | 550 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
mond | +1.382 |
olate | +1.317 |
ccording | +1.302 |
strip | +1.285 |
sole | +1.277 |
Neg logit contributions | |
Cipher | -1.470 |
iewicz | -1.444 |
rez | -1.439 |
signatures | -1.321 |
vier | -1.320 |
Token | been |
Token ID | 587 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
mond | +1.020 |
olate | +0.973 |
ccording | +0.961 |
strip | +0.945 |
sole | +0.929 |
Neg logit contributions | |
Cipher | -1.362 |
rez | -1.345 |
iewicz | -1.327 |
vier | -1.238 |
signatures | -1.235 |
Token | � |
Token ID | 447 |
Feature activation | +6.84e-03 |
Pos logit contributions | |
Cipher | +0.425 |
rez | +0.422 |
iewicz | +0.417 |
signatures | +0.386 |
vier | +0.381 |
Neg logit contributions | |
mond | -0.439 |
olate | -0.423 |
ccording | -0.422 |
strip | -0.412 |
sole | -0.404 |
Token | � |
Token ID | 251 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
mond | +0.019 |
olate | +0.017 |
ccording | +0.017 |
strip | +0.017 |
sole | +0.016 |
Neg logit contributions | |
Cipher | -0.044 |
rez | -0.044 |
iewicz | -0.043 |
signatures | -0.041 |
pps | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
mond | +0.487 |
ccording | +0.472 |
olate | +0.472 |
strip | +0.460 |
sole | +0.452 |
Neg logit contributions | |
Cipher | -0.410 |
rez | -0.406 |
iewicz | -0.400 |
signatures | -0.368 |
vier | -0.363 |
Token |
|
Token ID | 198 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
mond | +0.154 |
olate | +0.148 |
strip | +0.144 |
sole | +0.141 |
wo | +0.139 |
Neg logit contributions | |
Cipher | -0.146 |
rez | -0.143 |
iewicz | -0.141 |
signatures | -0.131 |
NX | -0.130 |
Token | EM |
Token ID | 3620 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
Cipher | +0.205 |
rez | +0.202 |
iewicz | +0.201 |
signatures | +0.187 |
NX | +0.184 |
Neg logit contributions | |
mond | -0.191 |
olate | -0.183 |
ccording | -0.183 |
strip | -0.179 |
sole | -0.175 |
Token | M |
Token ID | 44 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Cipher | +0.035 |
rez | +0.035 |
iewicz | +0.034 |
signatures | +0.032 |
vier | +0.031 |
Neg logit contributions | |
mond | -0.034 |
olate | -0.033 |
ccording | -0.033 |
strip | -0.032 |
sole | -0.031 |
Token | ITT |
Token ID | 22470 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
mond | +5.169 |
olate | +4.930 |
strip | +4.771 |
ccording | +4.732 |
� | +4.637 |
Neg logit contributions | |
rez | -4.767 |
Cipher | -4.739 |
iewicz | -4.572 |
pps | -4.374 |
iffe | -4.356 |
Token | SM |
Token ID | 9447 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
mond | +2.849 |
olate | +2.729 |
strip | +2.633 |
ccording | +2.615 |
wo | +2.587 |
Neg logit contributions | |
rez | -2.347 |
Cipher | -2.319 |
iewicz | -2.273 |
pps | -2.126 |
signatures | -2.104 |
Token | ITH |
Token ID | 10554 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
mond | +2.699 |
olate | +2.590 |
strip | +2.434 |
wo | +2.402 |
ccording | +2.399 |
Neg logit contributions | |
Cipher | -3.345 |
rez | -3.331 |
iewicz | -3.230 |
signatures | -3.079 |
pps | -3.024 |
Token | , |
Token ID | 11 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
mond | +2.345 |
olate | +2.255 |
ccording | +2.233 |
strip | +2.199 |
sole | +2.154 |
Neg logit contributions | |
Cipher | -1.814 |
rez | -1.784 |
iewicz | -1.748 |
signatures | -1.603 |
vier | -1.584 |
Token | FL |
Token ID | 9977 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
mond | +3.323 |
olate | +3.182 |
strip | +3.148 |
ccording | +3.052 |
sole | +2.996 |
Neg logit contributions | |
rez | -2.585 |
Cipher | -2.538 |
iewicz | -2.519 |
pps | -2.319 |
iffe | -2.311 |
Token | Final |
Token ID | 8125 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Cipher | +0.053 |
rez | +0.053 |
iewicz | +0.052 |
signatures | +0.048 |
vier | +0.047 |
Neg logit contributions | |
mond | -0.064 |
ccording | -0.062 |
olate | -0.062 |
strip | -0.061 |
sole | -0.060 |
Token | extr |
Token ID | 22820 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
mond | +1.086 |
olate | +1.056 |
ccording | +1.044 |
strip | +1.019 |
sole | +0.998 |
Neg logit contributions | |
Cipher | -1.039 |
rez | -1.034 |
iewicz | -1.023 |
signatures | -0.935 |
vier | -0.933 |
Token | usion |
Token ID | 4241 |
Feature activation | +7.16e-03 |
Pos logit contributions | |
mond | +1.688 |
olate | +1.597 |
strip | +1.521 |
ccording | +1.504 |
sole | +1.422 |
Neg logit contributions | |
Cipher | -4.495 |
rez | -4.424 |
iewicz | -4.422 |
pps | -4.205 |
signatures | -4.203 |
Token | v |
Token ID | 410 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
mond | +0.033 |
olate | +0.032 |
ccording | +0.032 |
strip | +0.031 |
sole | +0.030 |
Neg logit contributions | |
Cipher | -0.032 |
rez | -0.032 |
iewicz | -0.032 |
signatures | -0.029 |
vier | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
mond | +0.433 |
olate | +0.419 |
ccording | +0.419 |
strip | +0.409 |
sole | +0.402 |
Neg logit contributions | |
Cipher | -0.337 |
rez | -0.333 |
iewicz | -0.329 |
signatures | -0.301 |
vier | -0.297 |
Token | ver |
Token ID | 332 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
mond | +2.559 |
olate | +2.462 |
strip | +2.409 |
ccording | +2.387 |
sole | +2.337 |
Neg logit contributions | |
Cipher | -3.127 |
iewicz | -3.085 |
rez | -3.049 |
signatures | -2.876 |
NX | -2.859 |
Token | tex |
Token ID | 16886 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
mond | +2.938 |
olate | +2.715 |
strip | +2.545 |
sole | +2.481 |
wo | +2.391 |
Neg logit contributions | |
Cipher | -7.379 |
iewicz | -7.188 |
rez | -7.110 |
NX | -6.958 |
signatures | -6.956 |
Token | . |
Token ID | 13 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
mond | +1.171 |
ccording | +1.135 |
olate | +1.131 |
strip | +1.106 |
sole | +1.091 |
Neg logit contributions | |
Cipher | -0.864 |
rez | -0.856 |
iewicz | -0.842 |
signatures | -0.770 |
pps | -0.758 |
Token | xy |
Token ID | 5431 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
mond | +3.455 |
olate | +3.339 |
strip | +3.283 |
ccording | +3.248 |
sole | +3.150 |
Neg logit contributions | |
Cipher | -3.380 |
iewicz | -3.279 |
rez | -3.261 |
signatures | -3.082 |
NX | -3.058 |
Token | z |
Token ID | 89 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
mond | +3.904 |
olate | +3.744 |
strip | +3.709 |
ccording | +3.695 |
sole | +3.549 |
Neg logit contributions | |
Cipher | -3.540 |
iewicz | -3.363 |
rez | -3.358 |
signatures | -3.144 |
NX | -3.120 |
Token | += |
Token ID | 15853 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
mond | +1.093 |
olate | +1.047 |
ccording | +1.039 |
strip | +1.013 |
sole | +0.983 |
Neg logit contributions | |
Cipher | -1.482 |
rez | -1.467 |
iewicz | -1.453 |
signatures | -1.364 |
NX | -1.352 |
Token | bone |
Token ID | 9970 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
mond | +1.038 |
olate | +0.999 |
ccording | +0.991 |
strip | +0.978 |
sole | +0.952 |
Neg logit contributions | |
Cipher | -1.206 |
rez | -1.199 |
iewicz | -1.196 |
pps | -1.098 |
vier | -1.097 |
Token | . |
Token ID | 13 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Cipher | +0.666 |
rez | +0.659 |
iewicz | +0.650 |
signatures | +0.594 |
vier | +0.586 |
Neg logit contributions | |
mond | -0.886 |
olate | -0.859 |
ccording | -0.858 |
strip | -0.838 |
sole | -0.824 |
Token | And |
Token ID | 843 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Cipher | +1.099 |
rez | +1.084 |
iewicz | +1.071 |
signatures | +0.993 |
NX | +0.983 |
Neg logit contributions | |
mond | -1.091 |
ccording | -1.060 |
olate | -1.053 |
strip | -1.025 |
sole | -1.005 |
Token | , |
Token ID | 11 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
Cipher | +0.576 |
rez | +0.573 |
iewicz | +0.571 |
signatures | +0.521 |
vier | +0.520 |
Neg logit contributions | |
mond | -0.619 |
olate | -0.598 |
ccording | -0.593 |
strip | -0.580 |
sole | -0.570 |
Token | as |
Token ID | 355 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
Cipher | +0.364 |
rez | +0.360 |
iewicz | +0.355 |
signatures | +0.328 |
NX | +0.323 |
Neg logit contributions | |
mond | -0.424 |
ccording | -0.410 |
olate | -0.410 |
strip | -0.399 |
sole | -0.392 |
Token | if |
Token ID | 611 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Cipher | +0.270 |
rez | +0.269 |
iewicz | +0.267 |
signatures | +0.245 |
vier | +0.244 |
Neg logit contributions | |
mond | -0.284 |
olate | -0.273 |
ccording | -0.272 |
strip | -0.265 |
sole | -0.261 |
Token | that |
Token ID | 326 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
mond | +4.833 |
olate | +4.713 |
strip | +4.512 |
ccording | +4.481 |
sole | +4.461 |
Neg logit contributions | |
iewicz | -5.123 |
rez | -5.030 |
Cipher | -4.907 |
vier | -4.634 |
pps | -4.556 |
Token | wasn |
Token ID | 2492 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Cipher | +0.340 |
rez | +0.337 |
iewicz | +0.332 |
signatures | +0.305 |
vier | +0.301 |
Neg logit contributions | |
mond | -0.410 |
olate | -0.396 |
ccording | -0.396 |
strip | -0.386 |
sole | -0.380 |
Token | 't |
Token ID | 470 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
Cipher | +0.677 |
rez | +0.667 |
iewicz | +0.659 |
signatures | +0.610 |
NX | +0.603 |
Neg logit contributions | |
mond | -0.749 |
olate | -0.722 |
ccording | -0.707 |
strip | -0.703 |
sole | -0.692 |
Token | enough |
Token ID | 1576 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Cipher | +0.138 |
rez | +0.137 |
iewicz | +0.136 |
signatures | +0.126 |
vier | +0.124 |
Neg logit contributions | |
mond | -0.131 |
olate | -0.126 |
ccording | -0.126 |
strip | -0.122 |
sole | -0.120 |
Token | to |
Token ID | 284 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
mond | +2.570 |
ccording | +2.485 |
olate | +2.478 |
strip | +2.425 |
sole | +2.378 |
Neg logit contributions | |
Cipher | -1.927 |
rez | -1.900 |
iewicz | -1.894 |
vier | -1.710 |
NX | -1.691 |
Token | save |
Token ID | 3613 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
mond | +0.868 |
olate | +0.848 |
strip | +0.827 |
sole | +0.816 |
ccording | +0.810 |
Neg logit contributions | |
Cipher | -0.576 |
rez | -0.576 |
iewicz | -0.566 |
vier | -0.510 |
NX | -0.507 |
Token | , |
Token ID | 11 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
mond | +0.366 |
olate | +0.352 |
strip | +0.344 |
sole | +0.339 |
wo | +0.333 |
Neg logit contributions | |
Cipher | -0.272 |
rez | -0.270 |
iewicz | -0.264 |
signatures | -0.242 |
vier | -0.240 |
Token | your |
Token ID | 534 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
mond | +0.949 |
olate | +0.903 |
strip | +0.869 |
sole | +0.854 |
wo | +0.837 |
Neg logit contributions | |
rez | -1.330 |
Cipher | -1.327 |
iewicz | -1.311 |
vier | -1.224 |
pps | -1.218 |
Token | character |
Token ID | 2095 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
Cipher | +0.405 |
rez | +0.404 |
iewicz | +0.399 |
vier | +0.362 |
pps | +0.360 |
Neg logit contributions | |
mond | -0.528 |
olate | -0.510 |
strip | -0.498 |
ccording | -0.495 |
sole | -0.490 |
Token | now |
Token ID | 783 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Cipher | +0.062 |
rez | +0.061 |
iewicz | +0.060 |
vier | +0.055 |
NX | +0.055 |
Neg logit contributions | |
mond | -0.063 |
olate | -0.060 |
strip | -0.058 |
sole | -0.057 |
ccording | -0.057 |
Token | receives |
Token ID | 11583 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
mond | +0.718 |
olate | +0.688 |
sole | +0.679 |
strip | +0.674 |
wo | +0.655 |
Neg logit contributions | |
iewicz | -0.579 |
rez | -0.576 |
Cipher | -0.571 |
vier | -0.521 |
NX | -0.514 |
Token | secret |
Token ID | 3200 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
mond | +5.804 |
strip | +5.598 |
sole | +5.434 |
olate | +5.416 |
wo | +5.403 |
Neg logit contributions | |
iewicz | -3.950 |
rez | -3.943 |
vier | -3.723 |
Cipher | -3.666 |
ModLoader | -3.514 |
Token | voices |
Token ID | 10839 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
mond | +2.133 |
olate | +2.028 |
strip | +1.993 |
wo | +1.993 |
sole | +1.976 |
Neg logit contributions | |
Cipher | -1.651 |
rez | -1.637 |
iewicz | -1.628 |
vier | -1.498 |
iffe | -1.454 |
Token | in |
Token ID | 287 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
mond | +2.542 |
olate | +2.421 |
strip | +2.344 |
sole | +2.297 |
wo | +2.280 |
Neg logit contributions | |
Cipher | -2.971 |
rez | -2.965 |
iewicz | -2.910 |
pps | -2.720 |
vier | -2.719 |
Token | his |
Token ID | 465 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
mond | +0.959 |
olate | +0.912 |
strip | +0.884 |
ccording | +0.870 |
sole | +0.869 |
Neg logit contributions | |
Cipher | -1.292 |
rez | -1.280 |
iewicz | -1.268 |
vier | -1.185 |
NX | -1.182 |
Token | or |
Token ID | 393 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
mond | +0.624 |
olate | +0.602 |
strip | +0.584 |
sole | +0.577 |
ccording | +0.567 |
Neg logit contributions | |
Cipher | -0.501 |
rez | -0.500 |
iewicz | -0.489 |
vier | -0.452 |
pps | -0.444 |
Token | enter |
Token ID | 3802 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
mond | +0.730 |
olate | +0.701 |
strip | +0.687 |
ccording | +0.684 |
sole | +0.671 |
Neg logit contributions | |
Cipher | -0.799 |
rez | -0.789 |
iewicz | -0.780 |
vier | -0.719 |
NX | -0.718 |
Token | the |
Token ID | 262 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
mond | +0.271 |
olate | +0.262 |
ccording | +0.260 |
strip | +0.255 |
sole | +0.251 |
Neg logit contributions | |
Cipher | -0.259 |
rez | -0.257 |
iewicz | -0.255 |
signatures | -0.233 |
pps | -0.232 |
Token | bathroom |
Token ID | 12436 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
mond | +1.262 |
olate | +1.203 |
ccording | +1.187 |
strip | +1.175 |
sole | +1.151 |
Neg logit contributions | |
Cipher | -1.600 |
rez | -1.595 |
iewicz | -1.579 |
vier | -1.460 |
pps | -1.458 |
Token | of |
Token ID | 286 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
mond | +1.232 |
olate | +1.180 |
strip | +1.171 |
ccording | +1.171 |
sole | +1.155 |
Neg logit contributions | |
Cipher | -1.036 |
rez | -1.029 |
iewicz | -1.026 |
vier | -0.931 |
pps | -0.928 |
Token | the |
Token ID | 262 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
mond | +0.795 |
olate | +0.759 |
ccording | +0.747 |
strip | +0.736 |
sole | +0.727 |
Neg logit contributions | |
Cipher | -0.927 |
rez | -0.922 |
iewicz | -0.914 |
pps | -0.844 |
signatures | -0.840 |
Token | opposite |
Token ID | 6697 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
mond | +1.594 |
olate | +1.510 |
ccording | +1.496 |
strip | +1.483 |
sole | +1.460 |
Neg logit contributions | |
Cipher | -1.926 |
rez | -1.911 |
iewicz | -1.893 |
pps | -1.748 |
vier | -1.741 |
Token | sex |
Token ID | 1714 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
mond | +3.542 |
olate | +3.267 |
ccording | +3.265 |
strip | +3.238 |
sole | +3.152 |
Neg logit contributions | |
Cipher | -6.446 |
rez | -6.345 |
iewicz | -6.310 |
vier | -5.882 |
signatures | -5.882 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
mond | +1.296 |
olate | +1.248 |
ccording | +1.230 |
strip | +1.228 |
sole | +1.217 |
Neg logit contributions | |
Cipher | -1.129 |
rez | -1.119 |
iewicz | -1.105 |
pps | -1.008 |
signatures | -1.000 |
Token | If |
Token ID | 1002 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
mond | +0.790 |
olate | +0.756 |
ccording | +0.739 |
strip | +0.733 |
sole | +0.718 |
Neg logit contributions | |
rez | -0.893 |
Cipher | -0.891 |
iewicz | -0.879 |
signatures | -0.817 |
vier | -0.811 |
Token | that |
Token ID | 326 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
mond | +0.344 |
olate | +0.332 |
ccording | +0.328 |
strip | +0.322 |
sole | +0.315 |
Neg logit contributions | |
Cipher | -0.353 |
rez | -0.351 |
iewicz | -0.348 |
vier | -0.318 |
pps | -0.317 |
Token | is |
Token ID | 318 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
mond | +2.147 |
olate | +2.071 |
ccording | +2.055 |
strip | +2.029 |
sole | +1.995 |
Neg logit contributions | |
Cipher | -1.876 |
rez | -1.863 |
iewicz | -1.840 |
vier | -1.678 |
pps | -1.664 |
Token | at |
Token ID | 379 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
mond | +0.031 |
olate | +0.030 |
ccording | +0.030 |
strip | +0.029 |
sole | +0.029 |
Neg logit contributions | |
Cipher | -0.025 |
rez | -0.025 |
iewicz | -0.025 |
signatures | -0.022 |
vier | -0.022 |
Token | its |
Token ID | 663 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
Cipher | +0.065 |
rez | +0.064 |
iewicz | +0.064 |
signatures | +0.059 |
vier | +0.059 |
Neg logit contributions | |
mond | -0.059 |
ccording | -0.057 |
olate | -0.057 |
strip | -0.055 |
sole | -0.054 |
Token | best |
Token ID | 1266 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
Cipher | +0.415 |
rez | +0.412 |
iewicz | +0.408 |
signatures | +0.378 |
vier | +0.376 |
Neg logit contributions | |
mond | -0.373 |
olate | -0.358 |
ccording | -0.358 |
strip | -0.347 |
sole | -0.342 |
Token | [ |
Token ID | 685 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Cipher | +0.351 |
rez | +0.347 |
iewicz | +0.341 |
signatures | +0.311 |
vier | +0.308 |
Neg logit contributions | |
mond | -0.476 |
olate | -0.460 |
ccording | -0.460 |
strip | -0.449 |
sole | -0.443 |
Token | em |
Token ID | 368 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
mond | +0.786 |
ccording | +0.751 |
olate | +0.750 |
strip | +0.739 |
sole | +0.727 |
Neg logit contributions | |
Cipher | -0.866 |
rez | -0.853 |
iewicz | -0.849 |
signatures | -0.790 |
NX | -0.783 |
Token | ph |
Token ID | 746 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Cipher | +0.272 |
rez | +0.270 |
iewicz | +0.267 |
signatures | +0.251 |
vier | +0.248 |
Neg logit contributions | |
mond | -0.199 |
olate | -0.191 |
ccording | -0.190 |
strip | -0.184 |
sole | -0.180 |
Token | ases |
Token ID | 1386 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
mond | +3.619 |
olate | +3.528 |
ccording | +3.367 |
strip | +3.319 |
sole | +3.180 |
Neg logit contributions | |
Cipher | -6.349 |
iewicz | -6.228 |
rez | -6.174 |
signatures | -5.920 |
NX | -5.851 |
Token | added |
Token ID | 2087 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
mond | +2.740 |
olate | +2.629 |
ccording | +2.619 |
strip | +2.566 |
sole | +2.490 |
Neg logit contributions | |
Cipher | -2.719 |
rez | -2.715 |
iewicz | -2.665 |
vier | -2.478 |
signatures | -2.471 |
Token | ]," |
Token ID | 17241 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
mond | +2.060 |
olate | +1.942 |
ccording | +1.939 |
strip | +1.900 |
sole | +1.875 |
Neg logit contributions | |
Cipher | -2.814 |
rez | -2.789 |
iewicz | -2.748 |
NX | -2.577 |
signatures | -2.564 |
Token | r |
Token ID | 374 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
mond | +1.100 |
ccording | +1.060 |
olate | +1.055 |
strip | +1.029 |
sole | +1.010 |
Neg logit contributions | |
Cipher | -1.033 |
rez | -1.026 |
iewicz | -1.019 |
vier | -0.935 |
signatures | -0.934 |
Token | aves |
Token ID | 3080 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Cipher | +0.551 |
rez | +0.542 |
iewicz | +0.539 |
signatures | +0.498 |
NX | +0.495 |
Neg logit contributions | |
mond | -0.579 |
olate | -0.556 |
ccording | -0.555 |
strip | -0.544 |
sole | -0.530 |
Token | ous |
Token ID | 516 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
Cipher | +0.916 |
rez | +0.907 |
iewicz | +0.897 |
signatures | +0.828 |
NX | +0.817 |
Neg logit contributions | |
mond | -0.988 |
ccording | -0.956 |
olate | -0.954 |
strip | -0.927 |
sole | -0.911 |
Token | rex |
Token ID | 21510 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
mond | +2.186 |
olate | +2.095 |
ccording | +2.086 |
strip | +2.054 |
sole | +2.002 |
Neg logit contributions | |
rez | -1.947 |
Cipher | -1.939 |
iewicz | -1.923 |
signatures | -1.767 |
vier | -1.766 |
Token | s |
Token ID | 82 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
mond | +0.548 |
olate | +0.528 |
ccording | +0.527 |
strip | +0.515 |
sole | +0.506 |
Neg logit contributions | |
Cipher | -0.485 |
rez | -0.480 |
iewicz | -0.474 |
signatures | -0.438 |
vier | -0.433 |
Token | path |
Token ID | 3108 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
mond | +0.298 |
olate | +0.288 |
ccording | +0.287 |
strip | +0.280 |
sole | +0.275 |
Neg logit contributions | |
Cipher | -0.280 |
rez | -0.277 |
iewicz | -0.274 |
signatures | -0.253 |
vier | -0.251 |
Token | . |
Token ID | 13 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Cipher | +0.896 |
rez | +0.887 |
iewicz | +0.874 |
signatures | +0.801 |
vier | +0.788 |
Neg logit contributions | |
mond | -1.186 |
ccording | -1.153 |
olate | -1.149 |
strip | -1.119 |
sole | -1.100 |
Token | Seriously |
Token ID | 27777 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
mond | +1.144 |
olate | +1.098 |
ccording | +1.086 |
strip | +1.068 |
sole | +1.050 |
Neg logit contributions | |
Cipher | -1.048 |
rez | -1.043 |
iewicz | -1.031 |
signatures | -0.954 |
vier | -0.943 |
Token | , |
Token ID | 11 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
mond | +5.237 |
olate | +4.971 |
strip | +4.848 |
ccording | +4.822 |
wo | +4.809 |
Neg logit contributions | |
iewicz | -4.533 |
Cipher | -4.519 |
rez | -4.504 |
signatures | -4.109 |
iffe | -4.036 |
Token | the |
Token ID | 262 |
Feature activation | -8.89e-03 |
Pos logit contributions | |
mond | +1.428 |
olate | +1.371 |
ccording | +1.360 |
strip | +1.338 |
sole | +1.313 |
Neg logit contributions | |
Cipher | -1.211 |
rez | -1.204 |
iewicz | -1.196 |
signatures | -1.091 |
vier | -1.080 |
Token | greatest |
Token ID | 6000 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
Cipher | +0.040 |
rez | +0.040 |
iewicz | +0.039 |
signatures | +0.036 |
vier | +0.036 |
Neg logit contributions | |
mond | -0.042 |
ccording | -0.040 |
olate | -0.040 |
strip | -0.039 |
sole | -0.038 |
Token | addition |
Token ID | 3090 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
mond | +1.562 |
ccording | +1.473 |
olate | +1.471 |
strip | +1.448 |
wo | +1.422 |
Neg logit contributions | |
Cipher | -1.664 |
rez | -1.662 |
iewicz | -1.643 |
vier | -1.509 |
signatures | -1.500 |
Token | I |
Token ID | 314 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
mond | +0.525 |
olate | +0.502 |
ccording | +0.498 |
strip | +0.485 |
sole | +0.479 |
Neg logit contributions | |
Cipher | -0.607 |
rez | -0.601 |
iewicz | -0.594 |
signatures | -0.552 |
vier | -0.548 |
Token | ruling |
Token ID | 6922 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
mond | +0.353 |
olate | +0.335 |
ccording | +0.335 |
strip | +0.324 |
sole | +0.316 |
Neg logit contributions | |
Cipher | -0.545 |
rez | -0.540 |
iewicz | -0.536 |
signatures | -0.501 |
vier | -0.500 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
mond | +2.003 |
olate | +1.921 |
ccording | +1.918 |
strip | +1.883 |
sole | +1.860 |
Neg logit contributions | |
Cipher | -1.647 |
rez | -1.616 |
iewicz | -1.603 |
NX | -1.456 |
signatures | -1.451 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
mond | +1.020 |
olate | +0.969 |
ccording | +0.960 |
strip | +0.939 |
sole | +0.921 |
Neg logit contributions | |
Cipher | -0.962 |
rez | -0.960 |
iewicz | -0.948 |
signatures | -0.875 |
vier | -0.868 |
Token |
|
Token ID | 198 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
mond | +0.690 |
olate | +0.659 |
strip | +0.643 |
sole | +0.631 |
wo | +0.621 |
Neg logit contributions | |
Cipher | -0.666 |
rez | -0.657 |
iewicz | -0.647 |
signatures | -0.602 |
NX | -0.594 |
Token | More |
Token ID | 5167 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
mond | +0.794 |
ccording | +0.747 |
olate | +0.746 |
strip | +0.728 |
sole | +0.717 |
Neg logit contributions | |
Cipher | -0.928 |
iewicz | -0.905 |
rez | -0.899 |
signatures | -0.845 |
NX | -0.841 |
Token | than |
Token ID | 621 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
mond | +1.508 |
ccording | +1.447 |
olate | +1.430 |
strip | +1.395 |
sole | +1.375 |
Neg logit contributions | |
Cipher | -1.445 |
rez | -1.424 |
iewicz | -1.412 |
vier | -1.298 |
pps | -1.286 |
Token | 1 |
Token ID | 352 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
mond | +3.955 |
olate | +3.743 |
ccording | +3.616 |
wo | +3.589 |
strip | +3.566 |
Neg logit contributions | |
rez | -5.624 |
iewicz | -5.605 |
Cipher | -5.601 |
vier | -5.203 |
iffe | -5.174 |
Token | , |
Token ID | 11 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
mond | +1.724 |
ccording | +1.673 |
olate | +1.647 |
strip | +1.616 |
sole | +1.585 |
Neg logit contributions | |
Cipher | -1.324 |
rez | -1.309 |
iewicz | -1.294 |
signatures | -1.166 |
NX | -1.161 |
Token | 000 |
Token ID | 830 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
mond | +1.766 |
olate | +1.689 |
ccording | +1.656 |
strip | +1.634 |
sole | +1.593 |
Neg logit contributions | |
Cipher | -2.230 |
rez | -2.217 |
iewicz | -2.185 |
signatures | -2.053 |
NX | -2.025 |
Token | flag |
Token ID | 6056 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
mond | +3.051 |
ccording | +2.895 |
olate | +2.862 |
strip | +2.825 |
sole | +2.753 |
Neg logit contributions | |
rez | -2.076 |
Cipher | -2.065 |
iewicz | -2.037 |
vier | -1.846 |
NX | -1.795 |
Token | - |
Token ID | 12 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
mond | +1.712 |
olate | +1.642 |
ccording | +1.637 |
strip | +1.623 |
sole | +1.583 |
Neg logit contributions | |
Cipher | -1.198 |
rez | -1.176 |
iewicz | -1.171 |
vier | -1.048 |
signatures | -1.040 |
Token | 16 |
Token ID | 1467 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
mond | +0.587 |
olate | +0.557 |
strip | +0.541 |
sole | +0.532 |
ccording | +0.529 |
Neg logit contributions | |
rez | -0.672 |
Cipher | -0.671 |
iewicz | -0.659 |
signatures | -0.615 |
pps | -0.609 |
Token | , |
Token ID | 11 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
mond | +0.773 |
olate | +0.743 |
ccording | +0.740 |
strip | +0.726 |
sole | +0.715 |
Neg logit contributions | |
Cipher | -0.560 |
rez | -0.552 |
iewicz | -0.544 |
signatures | -0.497 |
NX | -0.488 |
Token | 1981 |
Token ID | 14745 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Cipher | +0.255 |
rez | +0.254 |
iewicz | +0.249 |
signatures | +0.229 |
vier | +0.227 |
Neg logit contributions | |
mond | -0.310 |
olate | -0.299 |
ccording | -0.296 |
strip | -0.292 |
sole | -0.287 |
Token |
|
Token ID | 198 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
Cipher | +1.443 |
rez | +1.436 |
iewicz | +1.416 |
signatures | +1.298 |
AK | +1.285 |
Neg logit contributions | |
mond | -1.871 |
ccording | -1.833 |
olate | -1.820 |
strip | -1.778 |
sole | -1.752 |
Token |
|
Token ID | 198 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
Cipher | +2.638 |
rez | +2.612 |
iewicz | +2.593 |
signatures | +2.357 |
AK | +2.342 |
Neg logit contributions | |
ccording | -3.590 |
mond | -3.452 |
olate | -3.366 |
strip | -3.278 |
sole | -3.235 |
Token | Birth |
Token ID | 38480 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
rez | +3.964 |
Cipher | +3.895 |
iewicz | +3.835 |
pps | +3.590 |
vier | +3.551 |
Neg logit contributions | |
ccording | -3.662 |
mond | -3.657 |
olate | -3.553 |
strip | -3.419 |
sole | -3.377 |
Token | place |
Token ID | 5372 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
Cipher | +5.645 |
rez | +5.325 |
iewicz | +5.209 |
AK | +5.165 |
signatures | +5.053 |
Neg logit contributions | |
ccording | -8.283 |
olate | -7.835 |
mond | -7.772 |
strip | -7.508 |
sole | -7.423 |
Token | : |
Token ID | 25 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
Cipher | +1.155 |
rez | +1.151 |
iewicz | +1.124 |
signatures | +1.011 |
vier | +0.990 |
Neg logit contributions | |
mond | -2.170 |
olate | -2.100 |
ccording | -2.062 |
strip | -2.058 |
sole | -2.030 |
Token | Long |
Token ID | 5882 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Cipher | +2.420 |
rez | +2.361 |
iewicz | +2.346 |
NX | +2.169 |
AK | +2.159 |
Neg logit contributions | |
mond | -2.439 |
ccording | -2.428 |
olate | -2.379 |
strip | -2.315 |
sole | -2.271 |
Token | Beach |
Token ID | 8511 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
mond | +0.512 |
olate | +0.489 |
ccording | +0.486 |
strip | +0.478 |
sole | +0.469 |
Neg logit contributions | |
Cipher | -0.481 |
rez | -0.476 |
iewicz | -0.471 |
signatures | -0.438 |
NX | -0.430 |
Token | , |
Token ID | 11 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Cipher | +1.717 |
rez | +1.700 |
iewicz | +1.674 |
signatures | +1.519 |
pps | +1.503 |
Neg logit contributions | |
mond | -2.607 |
ccording | -2.542 |
olate | -2.538 |
strip | -2.479 |
sole | -2.444 |
Token | Sound |
Token ID | 9506 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Cipher | +2.182 |
rez | +2.128 |
iewicz | +2.106 |
signatures | +1.978 |
NX | +1.967 |
Neg logit contributions | |
mond | -1.737 |
ccording | -1.676 |
olate | -1.668 |
strip | -1.609 |
sole | -1.578 |
Token | Barrier |
Token ID | 32804 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Cipher | +1.192 |
rez | +1.175 |
iewicz | +1.158 |
signatures | +1.065 |
NX | +1.050 |
Neg logit contributions | |
mond | -1.472 |
ccording | -1.428 |
olate | -1.425 |
strip | -1.386 |
sole | -1.365 |
Token | . |
Token ID | 13 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Cipher | +0.953 |
rez | +0.942 |
iewicz | +0.930 |
signatures | +0.852 |
pps | +0.840 |
Neg logit contributions | |
mond | -1.220 |
ccording | -1.181 |
olate | -1.181 |
strip | -1.151 |
sole | -1.133 |
Token | New |
Token ID | 968 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
mond | +0.766 |
olate | +0.733 |
ccording | +0.718 |
strip | +0.717 |
sole | +0.700 |
Neg logit contributions | |
rez | -0.664 |
Cipher | -0.658 |
iewicz | -0.653 |
signatures | -0.604 |
vier | -0.594 |
Token | York |
Token ID | 1971 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
mond | +0.891 |
ccording | +0.861 |
olate | +0.860 |
strip | +0.832 |
sole | +0.818 |
Neg logit contributions | |
Cipher | -1.024 |
rez | -1.015 |
iewicz | -1.005 |
signatures | -0.933 |
pps | -0.925 |
Token | : |
Token ID | 25 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Cipher | +1.704 |
iewicz | +1.648 |
rez | +1.639 |
signatures | +1.459 |
AK | +1.456 |
Neg logit contributions | |
mond | -3.528 |
olate | -3.496 |
ccording | -3.495 |
strip | -3.366 |
sole | -3.363 |
Token | Penguin |
Token ID | 34424 |
Feature activation | -6.72e-02 |
Pos logit contributions | |
Cipher | +5.954 |
iewicz | +5.585 |
rez | +5.497 |
AK | +5.448 |
NX | +5.250 |
Neg logit contributions | |
ccording | -7.431 |
mond | -6.962 |
olate | -6.903 |
strip | -6.769 |
sole | -6.712 |
Token | Studio |
Token ID | 11733 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Cipher | +0.269 |
rez | +0.266 |
iewicz | +0.263 |
signatures | +0.241 |
pps | +0.236 |
Neg logit contributions | |
mond | -0.348 |
olate | -0.336 |
ccording | -0.334 |
strip | -0.328 |
sole | -0.322 |
Token | , |
Token ID | 11 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
Cipher | +0.732 |
rez | +0.725 |
iewicz | +0.714 |
signatures | +0.649 |
vier | +0.638 |
Neg logit contributions | |
mond | -1.089 |
olate | -1.056 |
ccording | -1.055 |
strip | -1.032 |
sole | -1.016 |
Token | 1997 |
Token ID | 8309 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
rez | +0.087 |
Cipher | +0.087 |
iewicz | +0.085 |
signatures | +0.078 |
vier | +0.077 |
Neg logit contributions | |
mond | -0.110 |
olate | -0.105 |
ccording | -0.105 |
strip | -0.103 |
sole | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
Cipher | +0.622 |
rez | +0.618 |
iewicz | +0.606 |
signatures | +0.551 |
pps | +0.546 |
Neg logit contributions | |
mond | -0.928 |
ccording | -0.906 |
olate | -0.903 |
strip | -0.880 |
sole | -0.868 |
Token | , |
Token ID | 11 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
mond | +0.072 |
olate | +0.070 |
ccording | +0.069 |
strip | +0.068 |
sole | +0.067 |
Neg logit contributions | |
Cipher | -0.053 |
rez | -0.053 |
iewicz | -0.052 |
signatures | -0.048 |
vier | -0.047 |
Token | USAF |
Token ID | 45353 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
mond | +1.088 |
ccording | +1.045 |
olate | +1.045 |
strip | +1.027 |
sole | +1.003 |
Neg logit contributions | |
rez | -0.941 |
Cipher | -0.935 |
iewicz | -0.926 |
signatures | -0.853 |
vier | -0.845 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
rez | +0.510 |
Cipher | +0.508 |
iewicz | +0.500 |
signatures | +0.460 |
vier | +0.455 |
Neg logit contributions | |
mond | -0.657 |
olate | -0.636 |
ccording | -0.633 |
strip | -0.623 |
sole | -0.609 |
Token | New |
Token ID | 968 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
mond | +0.775 |
olate | +0.744 |
ccording | +0.730 |
strip | +0.724 |
sole | +0.709 |
Neg logit contributions | |
rez | -0.706 |
Cipher | -0.702 |
iewicz | -0.694 |
signatures | -0.644 |
vier | -0.631 |
Token | York |
Token ID | 1971 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
mond | +1.396 |
olate | +1.332 |
ccording | +1.327 |
strip | +1.297 |
sole | +1.266 |
Neg logit contributions | |
Cipher | -1.661 |
rez | -1.647 |
iewicz | -1.627 |
signatures | -1.523 |
vier | -1.501 |
Token | : |
Token ID | 25 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Cipher | +1.284 |
rez | +1.246 |
iewicz | +1.241 |
signatures | +1.101 |
AK | +1.094 |
Neg logit contributions | |
mond | -2.691 |
ccording | -2.659 |
olate | -2.659 |
strip | -2.573 |
sole | -2.563 |
Token | William |
Token ID | 3977 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
Cipher | +5.767 |
iewicz | +5.364 |
AK | +5.332 |
rez | +5.267 |
NX | +5.135 |
Neg logit contributions | |
ccording | -7.235 |
mond | -6.789 |
olate | -6.732 |
strip | -6.579 |
sole | -6.530 |
Token | Morrow |
Token ID | 34693 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Cipher | +1.656 |
rez | +1.633 |
iewicz | +1.617 |
signatures | +1.505 |
vier | +1.498 |
Neg logit contributions | |
mond | -1.408 |
ccording | -1.398 |
olate | -1.369 |
strip | -1.336 |
sole | -1.298 |
Token | and |
Token ID | 290 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
Cipher | +1.116 |
rez | +1.099 |
iewicz | +1.082 |
signatures | +0.976 |
vier | +0.972 |
Neg logit contributions | |
mond | -1.680 |
ccording | -1.653 |
olate | -1.638 |
strip | -1.598 |
sole | -1.575 |
Token | Company |
Token ID | 5834 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
mond | +0.484 |
olate | +0.465 |
ccording | +0.456 |
strip | +0.454 |
sole | +0.447 |
Neg logit contributions | |
rez | -0.331 |
iewicz | -0.328 |
Cipher | -0.327 |
signatures | -0.296 |
pps | -0.290 |
Token | , |
Token ID | 11 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Cipher | +1.355 |
rez | +1.312 |
iewicz | +1.303 |
pps | +1.182 |
vier | +1.179 |
Neg logit contributions | |
mond | -2.196 |
ccording | -2.174 |
olate | -2.161 |
strip | -2.092 |
sole | -2.067 |
Token | boys |
Token ID | 6510 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
Cipher | +0.004 |
rez | +0.004 |
iewicz | +0.004 |
signatures | +0.004 |
vier | +0.004 |
Neg logit contributions | |
mond | -0.006 |
ccording | -0.005 |
olate | -0.005 |
strip | -0.005 |
sole | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
Cipher | +0.277 |
rez | +0.275 |
iewicz | +0.269 |
signatures | +0.244 |
vier | +0.242 |
Neg logit contributions | |
mond | -0.401 |
olate | -0.388 |
ccording | -0.387 |
strip | -0.380 |
sole | -0.372 |
Token | Washington |
Token ID | 2669 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
mond | +0.070 |
olate | +0.067 |
ccording | +0.066 |
strip | +0.066 |
sole | +0.064 |
Neg logit contributions | |
rez | -0.061 |
Cipher | -0.061 |
iewicz | -0.060 |
signatures | -0.056 |
vier | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
Cipher | +1.037 |
rez | +1.017 |
iewicz | +1.006 |
signatures | +0.910 |
vier | +0.901 |
Neg logit contributions | |
mond | -1.615 |
ccording | -1.586 |
olate | -1.575 |
strip | -1.539 |
sole | -1.524 |
Token | DC |
Token ID | 6257 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Cipher | +1.761 |
rez | +1.692 |
iewicz | +1.690 |
signatures | +1.514 |
AK | +1.510 |
Neg logit contributions | |
mond | -3.825 |
ccording | -3.803 |
olate | -3.763 |
strip | -3.685 |
sole | -3.659 |
Token | : |
Token ID | 1058 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Cipher | +0.772 |
rez | +0.748 |
iewicz | +0.739 |
signatures | +0.665 |
vier | +0.653 |
Neg logit contributions | |
mond | -1.568 |
ccording | -1.539 |
olate | -1.535 |
strip | -1.495 |
sole | -1.487 |
Token | Hemisphere |
Token ID | 42811 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Cipher | +5.751 |
iewicz | +5.334 |
AK | +5.277 |
rez | +5.148 |
NX | +5.045 |
Neg logit contributions | |
ccording | -7.081 |
mond | -6.746 |
olate | -6.712 |
strip | -6.649 |
sole | -6.507 |
Token | Publishing |
Token ID | 23499 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
rez | +0.507 |
Cipher | +0.507 |
iewicz | +0.501 |
signatures | +0.453 |
NX | +0.443 |
Neg logit contributions | |
mond | -0.777 |
olate | -0.751 |
ccording | -0.740 |
strip | -0.732 |
sole | -0.720 |
Token | . |
Token ID | 764 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
mond | +0.385 |
olate | +0.367 |
ccording | +0.361 |
strip | +0.361 |
sole | +0.354 |
Neg logit contributions | |
rez | -0.262 |
Cipher | -0.261 |
iewicz | -0.257 |
signatures | -0.232 |
pps | -0.229 |
Token |
|
Token ID | 198 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
Cipher | +1.283 |
rez | +1.261 |
iewicz | +1.238 |
vier | +1.138 |
AK | +1.138 |
Neg logit contributions | |
mond | -1.674 |
ccording | -1.658 |
olate | -1.639 |
strip | -1.600 |
sole | -1.577 |
Token |
|
Token ID | 198 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
mond | +0.191 |
olate | +0.182 |
strip | +0.177 |
sole | +0.174 |
wo | +0.171 |
Neg logit contributions | |
Cipher | -0.184 |
rez | -0.182 |
iewicz | -0.179 |
signatures | -0.167 |
NX | -0.164 |
Token | obi |
Token ID | 13411 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
mond | +0.769 |
olate | +0.744 |
ccording | +0.738 |
strip | +0.724 |
sole | +0.709 |
Neg logit contributions | |
Cipher | -0.729 |
rez | -0.722 |
iewicz | -0.712 |
signatures | -0.662 |
NX | -0.653 |
Token | ography |
Token ID | 4867 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Cipher | +0.808 |
rez | +0.798 |
iewicz | +0.786 |
signatures | +0.693 |
pps | +0.687 |
Neg logit contributions | |
mond | -1.540 |
ccording | -1.512 |
olate | -1.492 |
strip | -1.460 |
sole | -1.447 |
Token | . |
Token ID | 13 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
mond | +1.951 |
olate | +1.870 |
ccording | +1.856 |
strip | +1.836 |
sole | +1.790 |
Neg logit contributions | |
Cipher | -1.509 |
rez | -1.508 |
iewicz | -1.485 |
signatures | -1.372 |
vier | -1.355 |
Token | New |
Token ID | 968 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
mond | +1.770 |
olate | +1.684 |
strip | +1.643 |
ccording | +1.640 |
sole | +1.603 |
Neg logit contributions | |
rez | -1.598 |
Cipher | -1.576 |
iewicz | -1.566 |
signatures | -1.454 |
iffe | -1.428 |
Token | York |
Token ID | 1971 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
mond | +1.728 |
olate | +1.638 |
ccording | +1.619 |
strip | +1.596 |
sole | +1.554 |
Neg logit contributions | |
Cipher | -2.093 |
rez | -2.077 |
iewicz | -2.046 |
signatures | -1.929 |
vier | -1.891 |
Token | : |
Token ID | 25 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Cipher | +0.846 |
rez | +0.830 |
iewicz | +0.821 |
signatures | +0.732 |
vier | +0.720 |
Neg logit contributions | |
mond | -1.635 |
ccording | -1.603 |
olate | -1.600 |
strip | -1.560 |
sole | -1.544 |
Token | B |
Token ID | 347 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Cipher | +5.554 |
iewicz | +5.244 |
rez | +5.160 |
AK | +5.136 |
NX | +4.953 |
Neg logit contributions | |
ccording | -7.224 |
mond | -6.799 |
olate | -6.742 |
strip | -6.622 |
sole | -6.531 |
Token | antam |
Token ID | 49653 |
Feature activation | -5.47e-03 |
Pos logit contributions | |
Cipher | +0.584 |
rez | +0.571 |
iewicz | +0.556 |
signatures | +0.460 |
NX | +0.446 |
Neg logit contributions | |
mond | -2.083 |
olate | -2.036 |
ccording | -2.032 |
strip | -1.997 |
sole | -1.977 |
Token | Books |
Token ID | 13661 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
Cipher | +0.022 |
rez | +0.022 |
iewicz | +0.022 |
signatures | +0.020 |
NX | +0.020 |
Neg logit contributions | |
mond | -0.028 |
olate | -0.027 |
ccording | -0.027 |
strip | -0.026 |
sole | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
Cipher | +0.216 |
rez | +0.213 |
iewicz | +0.210 |
signatures | +0.190 |
vier | +0.189 |
Neg logit contributions | |
mond | -0.331 |
ccording | -0.323 |
olate | -0.323 |
strip | -0.314 |
sole | -0.310 |
Token | 1985 |
Token ID | 12863 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Cipher | +0.085 |
rez | +0.084 |
iewicz | +0.083 |
signatures | +0.076 |
vier | +0.075 |
Neg logit contributions | |
mond | -0.108 |
olate | -0.104 |
ccording | -0.103 |
strip | -0.102 |
sole | -0.100 |
Token | Weight |
Token ID | 25844 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
rez | +3.075 |
Cipher | +3.041 |
iewicz | +3.006 |
signatures | +2.797 |
pps | +2.787 |
Neg logit contributions | |
mond | -2.604 |
ccording | -2.529 |
olate | -2.483 |
sole | -2.393 |
strip | -2.393 |
Token | : |
Token ID | 25 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
Cipher | +1.597 |
rez | +1.565 |
iewicz | +1.544 |
signatures | +1.370 |
vier | +1.335 |
Neg logit contributions | |
ccording | -3.412 |
mond | -3.407 |
olate | -3.325 |
strip | -3.250 |
sole | -3.232 |
Token | 190 |
Token ID | 19884 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Cipher | +2.978 |
rez | +2.933 |
iewicz | +2.914 |
AK | +2.694 |
NX | +2.691 |
Neg logit contributions | |
mond | -2.911 |
ccording | -2.848 |
olate | -2.803 |
strip | -2.720 |
sole | -2.688 |
Token |
|
Token ID | 198 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
Cipher | +1.736 |
rez | +1.735 |
iewicz | +1.692 |
signatures | +1.555 |
pps | +1.537 |
Neg logit contributions | |
mond | -2.317 |
ccording | -2.254 |
olate | -2.252 |
strip | -2.187 |
sole | -2.166 |
Token |
|
Token ID | 198 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
Cipher | +2.381 |
rez | +2.361 |
iewicz | +2.338 |
signatures | +2.135 |
pps | +2.110 |
Neg logit contributions | |
ccording | -3.064 |
mond | -3.012 |
olate | -2.929 |
strip | -2.849 |
sole | -2.813 |
Token | Birth |
Token ID | 38480 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
rez | +4.071 |
Cipher | +3.983 |
iewicz | +3.926 |
pps | +3.684 |
signatures | +3.653 |
Neg logit contributions | |
mond | -3.377 |
ccording | -3.276 |
olate | -3.215 |
sole | -3.097 |
strip | -3.077 |
Token | Date |
Token ID | 7536 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
Cipher | +4.979 |
rez | +4.801 |
iewicz | +4.592 |
signatures | +4.499 |
AK | +4.476 |
Neg logit contributions | |
ccording | -6.752 |
olate | -6.744 |
mond | -6.634 |
strip | -6.304 |
wo | -6.223 |
Token | : |
Token ID | 25 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
Cipher | +1.839 |
rez | +1.792 |
iewicz | +1.781 |
signatures | +1.562 |
AK | +1.543 |
Neg logit contributions | |
ccording | -3.969 |
mond | -3.929 |
olate | -3.871 |
strip | -3.785 |
sole | -3.734 |
Token | October |
Token ID | 3267 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Cipher | +2.580 |
rez | +2.502 |
iewicz | +2.480 |
NX | +2.272 |
AK | +2.265 |
Neg logit contributions | |
ccording | -3.683 |
mond | -3.674 |
olate | -3.621 |
strip | -3.514 |
sole | -3.468 |
Token | 16 |
Token ID | 1467 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
mond | +0.587 |
olate | +0.557 |
strip | +0.541 |
sole | +0.532 |
ccording | +0.529 |
Neg logit contributions | |
rez | -0.672 |
Cipher | -0.671 |
iewicz | -0.659 |
signatures | -0.615 |
pps | -0.609 |
Token | , |
Token ID | 11 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
mond | +0.773 |
olate | +0.743 |
ccording | +0.740 |
strip | +0.726 |
sole | +0.715 |
Neg logit contributions | |
Cipher | -0.560 |
rez | -0.552 |
iewicz | -0.544 |
signatures | -0.497 |
NX | -0.488 |
Token | A |
Token ID | 317 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
Cipher | +1.797 |
rez | +1.774 |
iewicz | +1.744 |
signatures | +1.617 |
NX | +1.604 |
Neg logit contributions | |
mond | -1.870 |
olate | -1.814 |
ccording | -1.812 |
strip | -1.763 |
sole | -1.736 |
Token | Novel |
Token ID | 24467 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
mond | +0.073 |
olate | +0.070 |
ccording | +0.070 |
strip | +0.068 |
sole | +0.067 |
Neg logit contributions | |
Cipher | -0.075 |
rez | -0.075 |
iewicz | -0.074 |
signatures | -0.069 |
vier | -0.068 |
Token | ( |
Token ID | 357 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
Cipher | +0.630 |
rez | +0.625 |
iewicz | +0.616 |
signatures | +0.565 |
vier | +0.557 |
Neg logit contributions | |
mond | -0.827 |
olate | -0.801 |
ccording | -0.799 |
strip | -0.782 |
sole | -0.768 |
Token | New |
Token ID | 3791 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
mond | +0.080 |
olate | +0.076 |
ccording | +0.076 |
strip | +0.075 |
sole | +0.073 |
Neg logit contributions | |
Cipher | -0.096 |
rez | -0.095 |
iewicz | -0.094 |
signatures | -0.088 |
NX | -0.087 |
Token | York |
Token ID | 1971 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
mond | +0.438 |
olate | +0.422 |
ccording | +0.421 |
strip | +0.409 |
sole | +0.401 |
Neg logit contributions | |
Cipher | -0.509 |
rez | -0.505 |
iewicz | -0.499 |
signatures | -0.465 |
vier | -0.460 |
Token | : |
Token ID | 25 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Cipher | +0.788 |
rez | +0.770 |
iewicz | +0.761 |
signatures | +0.678 |
vier | +0.664 |
Neg logit contributions | |
mond | -1.589 |
ccording | -1.560 |
olate | -1.556 |
strip | -1.516 |
sole | -1.504 |
Token | St |
Token ID | 520 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Cipher | +5.213 |
iewicz | +4.923 |
rez | +4.908 |
AK | +4.793 |
NX | +4.618 |
Neg logit contributions | |
ccording | -6.674 |
mond | -6.347 |
olate | -6.270 |
strip | -6.129 |
sole | -6.092 |
Token | . |
Token ID | 13 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Cipher | +0.716 |
rez | +0.708 |
iewicz | +0.699 |
signatures | +0.640 |
vier | +0.629 |
Neg logit contributions | |
mond | -0.969 |
olate | -0.937 |
ccording | -0.934 |
strip | -0.915 |
sole | -0.899 |
Token | Martin |
Token ID | 5780 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Cipher | +1.233 |
rez | +1.220 |
iewicz | +1.205 |
signatures | +1.121 |
NX | +1.113 |
Neg logit contributions | |
mond | -1.146 |
ccording | -1.118 |
olate | -1.111 |
strip | -1.079 |
sole | -1.063 |
Token | � |
Token ID | 447 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
mond | +1.056 |
olate | +1.015 |
ccording | +1.004 |
strip | +0.994 |
sole | +0.969 |
Neg logit contributions | |
Cipher | -0.853 |
rez | -0.848 |
iewicz | -0.846 |
signatures | -0.769 |
pps | -0.763 |
Token | � |
Token ID | 247 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
Cipher | +1.822 |
rez | +1.813 |
iewicz | +1.793 |
signatures | +1.701 |
pps | +1.693 |
Neg logit contributions | |
mond | -0.700 |
ccording | -0.659 |
olate | -0.654 |
strip | -0.627 |
sole | -0.601 |
Token | null |
Token ID | 9242 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Cipher | +0.854 |
rez | +0.843 |
iewicz | +0.831 |
signatures | +0.773 |
NX | +0.763 |
Neg logit contributions | |
mond | -0.957 |
ccording | -0.925 |
olate | -0.924 |
strip | -0.900 |
sole | -0.884 |
Token | atomic |
Token ID | 17226 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Cipher | +0.660 |
rez | +0.652 |
iewicz | +0.644 |
signatures | +0.601 |
NX | +0.593 |
Neg logit contributions | |
mond | -0.629 |
ccording | -0.608 |
olate | -0.604 |
strip | -0.590 |
sole | -0.577 |
Token | pointer |
Token ID | 17562 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
Cipher | +0.868 |
rez | +0.858 |
iewicz | +0.847 |
signatures | +0.787 |
NX | +0.774 |
Neg logit contributions | |
mond | -0.945 |
ccording | -0.913 |
olate | -0.911 |
strip | -0.888 |
sole | -0.873 |
Token | . |
Token ID | 13 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Cipher | +1.906 |
rez | +1.866 |
iewicz | +1.825 |
signatures | +1.713 |
AK | +1.665 |
Neg logit contributions | |
mond | -2.502 |
ccording | -2.450 |
olate | -2.418 |
strip | -2.371 |
sole | -2.337 |
Token | pub |
Token ID | 2240 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
Cipher | +0.899 |
rez | +0.888 |
iewicz | +0.875 |
signatures | +0.810 |
NX | +0.795 |
Neg logit contributions | |
mond | -1.071 |
ccording | -1.037 |
olate | -1.036 |
strip | -1.010 |
sole | -0.994 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Cipher | +2.509 |
rez | +2.459 |
iewicz | +2.396 |
signatures | +2.257 |
NX | +2.202 |
Neg logit contributions | |
mond | -3.109 |
ccording | -3.019 |
olate | -3.010 |
strip | -2.943 |
sole | -2.905 |
Token | null |
Token ID | 9242 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Cipher | +5.134 |
rez | +4.773 |
signatures | +4.751 |
iewicz | +4.671 |
AK | +4.530 |
Neg logit contributions | |
mond | -6.122 |
ccording | -6.110 |
olate | -5.773 |
strip | -5.733 |
sole | -5.720 |
Token | () |
Token ID | 7499 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Cipher | +0.656 |
rez | +0.648 |
iewicz | +0.639 |
signatures | +0.579 |
vier | +0.570 |
Neg logit contributions | |
mond | -0.991 |
olate | -0.963 |
ccording | -0.961 |
strip | -0.939 |
sole | -0.925 |
Token | -> |
Token ID | 4613 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
Cipher | +4.420 |
rez | +4.270 |
iewicz | +4.073 |
signatures | +3.978 |
AK | +3.939 |
Neg logit contributions | |
mond | -6.004 |
ccording | -5.962 |
olate | -5.804 |
strip | -5.757 |
sole | -5.710 |
Token | Atomic |
Token ID | 28976 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Cipher | +3.161 |
rez | +2.989 |
iewicz | +2.927 |
signatures | +2.815 |
NX | +2.755 |
Neg logit contributions | |
mond | -4.459 |
ccording | -4.417 |
olate | -4.281 |
strip | -4.266 |
sole | -4.204 |
Token | < |
Token ID | 1279 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
mond | +0.789 |
olate | +0.770 |
ccording | +0.763 |
strip | +0.742 |
sole | +0.732 |
Neg logit contributions | |
rez | -0.585 |
Cipher | -0.584 |
iewicz | -0.575 |
signatures | -0.518 |
vier | -0.518 |
Token | ). |
Token ID | 737 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
Cipher | +0.745 |
rez | +0.738 |
iewicz | +0.728 |
signatures | +0.670 |
vier | +0.659 |
Neg logit contributions | |
mond | -0.900 |
olate | -0.867 |
ccording | -0.865 |
strip | -0.847 |
sole | -0.832 |
Token | New |
Token ID | 968 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
rez | +0.051 |
Cipher | +0.050 |
iewicz | +0.050 |
signatures | +0.046 |
vier | +0.045 |
Neg logit contributions | |
mond | -0.058 |
olate | -0.055 |
ccording | -0.054 |
strip | -0.054 |
sole | -0.053 |
Token | York |
Token ID | 1971 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
mond | +1.188 |
olate | +1.131 |
ccording | +1.124 |
strip | +1.102 |
sole | +1.073 |
Neg logit contributions | |
Cipher | -1.476 |
rez | -1.467 |
iewicz | -1.447 |
signatures | -1.353 |
NX | -1.336 |
Token | , |
Token ID | 11 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
Cipher | +1.016 |
rez | +1.008 |
iewicz | +0.990 |
signatures | +0.890 |
NX | +0.874 |
Neg logit contributions | |
mond | -1.730 |
olate | -1.678 |
ccording | -1.672 |
strip | -1.641 |
sole | -1.615 |
Token | NY |
Token ID | 6645 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Cipher | +2.419 |
rez | +2.381 |
iewicz | +2.354 |
signatures | +2.178 |
NX | +2.153 |
Neg logit contributions | |
mond | -2.718 |
ccording | -2.650 |
olate | -2.642 |
strip | -2.570 |
sole | -2.532 |
Token | : |
Token ID | 1058 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Cipher | +1.130 |
rez | +1.120 |
iewicz | +1.100 |
signatures | +0.983 |
NX | +0.965 |
Neg logit contributions | |
mond | -2.046 |
olate | -1.985 |
ccording | -1.982 |
strip | -1.944 |
sole | -1.915 |
Token | Worth |
Token ID | 22301 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
Cipher | +4.667 |
iewicz | +4.400 |
rez | +4.331 |
AK | +4.206 |
NX | +4.080 |
Neg logit contributions | |
ccording | -6.651 |
mond | -6.457 |
olate | -6.345 |
strip | -6.237 |
sole | -6.166 |
Token | Publishers |
Token ID | 43403 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
rez | +0.133 |
Cipher | +0.132 |
iewicz | +0.126 |
signatures | +0.113 |
NX | +0.110 |
Neg logit contributions | |
mond | -0.284 |
olate | -0.275 |
strip | -0.269 |
ccording | -0.269 |
sole | -0.267 |
Token | . |
Token ID | 764 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Cipher | +0.583 |
rez | +0.578 |
iewicz | +0.569 |
signatures | +0.512 |
NX | +0.500 |
Neg logit contributions | |
mond | -1.026 |
olate | -0.993 |
ccording | -0.987 |
strip | -0.971 |
sole | -0.957 |
Token |
|
Token ID | 198 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
Cipher | +0.659 |
rez | +0.651 |
iewicz | +0.639 |
vier | +0.586 |
signatures | +0.586 |
Neg logit contributions | |
mond | -0.818 |
ccording | -0.799 |
olate | -0.798 |
strip | -0.777 |
sole | -0.765 |
Token |
|
Token ID | 198 |
Feature activation | +9.26e-02 |
Pos logit contributions | |
mond | +0.121 |
olate | +0.115 |
strip | +0.112 |
sole | +0.110 |
wo | +0.108 |
Neg logit contributions | |
Cipher | -0.116 |
rez | -0.115 |
iewicz | -0.113 |
signatures | -0.105 |
vier | -0.103 |
Token | Cha |
Token ID | 20703 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Cipher | +0.936 |
rez | +0.925 |
iewicz | +0.914 |
signatures | +0.838 |
NX | +0.827 |
Neg logit contributions | |
mond | -1.143 |
ccording | -1.110 |
olate | -1.107 |
strip | -1.080 |
sole | -1.062 |
Token | vel |
Token ID | 626 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Cipher | +0.665 |
rez | +0.658 |
iewicz | +0.646 |
signatures | +0.586 |
NX | +0.577 |
Neg logit contributions | |
mond | -1.106 |
olate | -1.073 |
ccording | -1.062 |
strip | -1.044 |
sole | -1.034 |
Token | ( |
Token ID | 357 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
mond | +1.163 |
olate | +1.114 |
ccording | +1.100 |
strip | +1.085 |
sole | +1.076 |
Neg logit contributions | |
Cipher | -0.871 |
rez | -0.860 |
iewicz | -0.845 |
signatures | -0.787 |
NX | -0.777 |
Token | New |
Token ID | 3791 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
mond | +1.109 |
olate | +1.041 |
ccording | +1.031 |
strip | +1.031 |
sole | +1.006 |
Neg logit contributions | |
Cipher | -1.360 |
iewicz | -1.337 |
rez | -1.335 |
signatures | -1.258 |
NX | -1.242 |
Token | York |
Token ID | 1971 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
mond | +1.412 |
olate | +1.340 |
ccording | +1.332 |
strip | +1.304 |
sole | +1.273 |
Neg logit contributions | |
Cipher | -1.700 |
rez | -1.684 |
iewicz | -1.664 |
signatures | -1.560 |
NX | -1.536 |
Token | : |
Token ID | 25 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Cipher | +0.723 |
rez | +0.706 |
iewicz | +0.698 |
signatures | +0.617 |
AK | +0.608 |
Neg logit contributions | |
mond | -1.539 |
olate | -1.517 |
ccording | -1.517 |
strip | -1.472 |
sole | -1.465 |
Token | Sh |
Token ID | 911 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Cipher | +5.146 |
rez | +4.856 |
iewicz | +4.837 |
AK | +4.710 |
NX | +4.571 |
Neg logit contributions | |
ccording | -6.132 |
mond | -5.812 |
olate | -5.796 |
strip | -5.597 |
sole | -5.587 |
Token | ilo |
Token ID | 18526 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
Cipher | +1.445 |
rez | +1.435 |
iewicz | +1.416 |
signatures | +1.312 |
vier | +1.304 |
Neg logit contributions | |
mond | -1.359 |
ccording | -1.320 |
olate | -1.308 |
strip | -1.274 |
sole | -1.250 |
Token | Publishing |
Token ID | 23499 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
mond | +0.248 |
olate | +0.240 |
ccording | +0.238 |
strip | +0.235 |
sole | +0.229 |
Neg logit contributions | |
Cipher | -0.180 |
rez | -0.179 |
iewicz | -0.177 |
signatures | -0.162 |
NX | -0.158 |
Token | House |
Token ID | 2097 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
mond | +0.462 |
olate | +0.446 |
ccording | +0.444 |
strip | +0.436 |
sole | +0.428 |
Neg logit contributions | |
Cipher | -0.370 |
rez | -0.367 |
iewicz | -0.362 |
signatures | -0.332 |
vier | -0.327 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
mond | +1.342 |
olate | +1.297 |
ccording | +1.295 |
strip | +1.270 |
sole | +1.250 |
Neg logit contributions | |
Cipher | -0.926 |
rez | -0.917 |
iewicz | -0.903 |
signatures | -0.823 |
NX | -0.808 |
Token | Guard |
Token ID | 4932 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Cipher | +4.014 |
rez | +3.845 |
iewicz | +3.772 |
signatures | +3.583 |
NX | +3.563 |
Neg logit contributions | |
mond | -4.304 |
ccording | -4.212 |
olate | -4.135 |
strip | -4.105 |
sole | -4.033 |
Token | { |
Token ID | 1391 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
Cipher | +0.576 |
rez | +0.574 |
iewicz | +0.568 |
signatures | +0.518 |
vier | +0.512 |
Neg logit contributions | |
mond | -0.711 |
olate | -0.689 |
ccording | -0.688 |
strip | -0.669 |
sole | -0.657 |
Token | ... |
Token ID | 2644 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Cipher | +2.393 |
rez | +2.334 |
iewicz | +2.303 |
signatures | +2.175 |
NX | +2.120 |
Neg logit contributions | |
mond | -2.482 |
ccording | -2.419 |
olate | -2.402 |
strip | -2.336 |
sole | -2.298 |
Token | } |
Token ID | 1782 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
Cipher | +1.396 |
rez | +1.380 |
iewicz | +1.361 |
signatures | +1.275 |
NX | +1.254 |
Neg logit contributions | |
mond | -1.272 |
ccording | -1.229 |
olate | -1.226 |
strip | -1.190 |
sole | -1.167 |
Token | pub |
Token ID | 2240 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
Cipher | +2.586 |
rez | +2.535 |
iewicz | +2.486 |
signatures | +2.338 |
NX | +2.287 |
Neg logit contributions | |
mond | -3.182 |
ccording | -3.087 |
olate | -3.078 |
strip | -3.007 |
sole | -2.970 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Cipher | +3.352 |
rez | +3.277 |
iewicz | +3.177 |
signatures | +3.026 |
NX | +2.971 |
Neg logit contributions | |
mond | -3.948 |
ccording | -3.824 |
olate | -3.818 |
strip | -3.716 |
sole | -3.678 |
Token | pin |
Token ID | 6757 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Cipher | +5.355 |
rez | +5.049 |
iewicz | +5.002 |
signatures | +4.889 |
secrets | +4.744 |
Neg logit contributions | |
mond | -5.572 |
ccording | -5.486 |
olate | -5.291 |
strip | -5.244 |
sole | -5.237 |
Token | () |
Token ID | 7499 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Cipher | +0.956 |
rez | +0.944 |
iewicz | +0.932 |
signatures | +0.851 |
NX | +0.840 |
Neg logit contributions | |
mond | -1.292 |
olate | -1.253 |
ccording | -1.245 |
strip | -1.225 |
sole | -1.201 |
Token | -> |
Token ID | 4613 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
Cipher | +4.373 |
rez | +4.213 |
iewicz | +4.060 |
signatures | +3.923 |
AK | +3.857 |
Neg logit contributions | |
mond | -5.795 |
ccording | -5.760 |
olate | -5.658 |
strip | -5.562 |
sole | -5.560 |
Token | Guard |
Token ID | 4932 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Cipher | +4.263 |
rez | +4.057 |
iewicz | +3.988 |
signatures | +3.812 |
AK | +3.773 |
Neg logit contributions | |
mond | -4.412 |
ccording | -4.407 |
olate | -4.257 |
strip | -4.201 |
sole | -4.170 |
Token | ; |
Token ID | 2162 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
mond | +0.606 |
olate | +0.590 |
ccording | +0.582 |
strip | +0.568 |
sole | +0.556 |
Neg logit contributions | |
rez | -0.511 |
Cipher | -0.507 |
iewicz | -0.503 |
signatures | -0.457 |
vier | -0.456 |
Token | , |
Token ID | 11 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Cipher | +1.717 |
rez | +1.700 |
iewicz | +1.674 |
signatures | +1.519 |
pps | +1.503 |
Neg logit contributions | |
mond | -2.607 |
ccording | -2.542 |
olate | -2.538 |
strip | -2.479 |
sole | -2.444 |
Token | CA |
Token ID | 7257 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Cipher | +1.298 |
rez | +1.277 |
iewicz | +1.264 |
signatures | +1.166 |
NX | +1.153 |
Neg logit contributions | |
mond | -1.484 |
ccording | -1.443 |
olate | -1.437 |
strip | -1.401 |
sole | -1.377 |
Token |
|
Token ID | 198 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Cipher | +0.638 |
rez | +0.631 |
iewicz | +0.623 |
signatures | +0.572 |
vier | +0.564 |
Neg logit contributions | |
mond | -0.787 |
olate | -0.762 |
ccording | -0.762 |
strip | -0.742 |
sole | -0.730 |
Token |
|
Token ID | 198 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
Cipher | +1.474 |
rez | +1.459 |
iewicz | +1.439 |
signatures | +1.327 |
vier | +1.310 |
Neg logit contributions | |
mond | -1.690 |
olate | -1.631 |
ccording | -1.607 |
strip | -1.589 |
sole | -1.560 |
Token | H |
Token ID | 39 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
Cipher | +2.914 |
rez | +2.910 |
iewicz | +2.861 |
signatures | +2.656 |
pps | +2.653 |
Neg logit contributions | |
mond | -2.489 |
ccording | -2.427 |
olate | -2.398 |
strip | -2.319 |
sole | -2.276 |
Token | ometown |
Token ID | 19191 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
rez | +1.778 |
Cipher | +1.693 |
iewicz | +1.573 |
signatures | +1.365 |
pps | +1.357 |
Neg logit contributions | |
mond | -5.831 |
ccording | -5.776 |
olate | -5.697 |
strip | -5.579 |
sole | -5.558 |
Token | : |
Token ID | 25 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
Cipher | +3.178 |
rez | +3.097 |
iewicz | +3.005 |
signatures | +2.692 |
AK | +2.672 |
Neg logit contributions | |
ccording | -7.809 |
mond | -7.706 |
olate | -7.582 |
strip | -7.343 |
sole | -7.337 |
Token | Long |
Token ID | 5882 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Cipher | +3.782 |
rez | +3.660 |
iewicz | +3.614 |
AK | +3.392 |
NX | +3.390 |
Neg logit contributions | |
ccording | -3.856 |
mond | -3.803 |
olate | -3.736 |
strip | -3.627 |
sole | -3.586 |
Token | Beach |
Token ID | 8511 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Cipher | +0.998 |
rez | +0.984 |
iewicz | +0.971 |
signatures | +0.882 |
vier | +0.874 |
Neg logit contributions | |
mond | -1.386 |
ccording | -1.353 |
olate | -1.352 |
strip | -1.315 |
sole | -1.296 |
Token | , |
Token ID | 11 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
Cipher | +2.027 |
rez | +2.009 |
iewicz | +1.982 |
signatures | +1.790 |
pps | +1.780 |
Neg logit contributions | |
mond | -3.146 |
olate | -3.078 |
ccording | -3.077 |
strip | -3.001 |
sole | -2.963 |
Token | CA |
Token ID | 7257 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
Cipher | +1.815 |
iewicz | +1.723 |
rez | +1.720 |
AK | +1.560 |
signatures | +1.521 |
Neg logit contributions | |
mond | -4.291 |
olate | -4.220 |
ccording | -4.197 |
strip | -4.135 |
sole | -4.102 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
Cipher | +0.339 |
rez | +0.336 |
iewicz | +0.333 |
signatures | +0.313 |
NX | +0.310 |
Neg logit contributions | |
mond | -0.222 |
ccording | -0.214 |
olate | -0.212 |
strip | -0.205 |
sole | -0.200 |
Token | / |
Token ID | 14 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
Cipher | +0.080 |
rez | +0.080 |
iewicz | +0.079 |
signatures | +0.071 |
vier | +0.071 |
Neg logit contributions | |
mond | -0.106 |
olate | -0.103 |
ccording | -0.103 |
strip | -0.101 |
sole | -0.099 |
Token | 6 |
Token ID | 21 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
Cipher | +0.167 |
rez | +0.166 |
iewicz | +0.164 |
signatures | +0.155 |
NX | +0.153 |
Neg logit contributions | |
mond | -0.103 |
olate | -0.097 |
ccording | -0.095 |
strip | -0.094 |
sole | -0.092 |
Token | / |
Token ID | 14 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Cipher | +1.247 |
rez | +1.230 |
iewicz | +1.208 |
signatures | +1.076 |
vier | +1.055 |
Neg logit contributions | |
mond | -2.449 |
ccording | -2.385 |
olate | -2.383 |
strip | -2.334 |
sole | -2.302 |
Token | 08 |
Token ID | 2919 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
Cipher | +0.526 |
rez | +0.521 |
iewicz | +0.515 |
signatures | +0.480 |
pps | +0.474 |
Neg logit contributions | |
mond | -0.461 |
olate | -0.443 |
ccording | -0.441 |
strip | -0.430 |
sole | -0.421 |
Token | Rating |
Token ID | 12028 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
mond | +0.210 |
olate | +0.201 |
ccording | +0.200 |
strip | +0.194 |
sole | +0.189 |
Neg logit contributions | |
Cipher | -0.307 |
rez | -0.305 |
iewicz | -0.302 |
signatures | -0.283 |
vier | -0.281 |
Token | : |
Token ID | 25 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
Cipher | +3.040 |
iewicz | +2.893 |
rez | +2.883 |
AK | +2.560 |
signatures | +2.544 |
Neg logit contributions | |
ccording | -8.211 |
mond | -7.669 |
olate | -7.575 |
ntil | -7.408 |
strip | -7.382 |
Token | 5 |
Token ID | 642 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
Cipher | +3.508 |
rez | +3.437 |
iewicz | +3.383 |
NX | +3.199 |
AK | +3.173 |
Neg logit contributions | |
mond | -3.569 |
ccording | -3.554 |
olate | -3.439 |
strip | -3.348 |
sole | -3.326 |
Token |
|
Token ID | 198 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
Cipher | +1.867 |
rez | +1.839 |
iewicz | +1.802 |
signatures | +1.674 |
AK | +1.653 |
Neg logit contributions | |
mond | -2.470 |
ccording | -2.385 |
olate | -2.379 |
strip | -2.324 |
sole | -2.310 |
Token |
|
Token ID | 198 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
Cipher | +1.679 |
rez | +1.662 |
iewicz | +1.641 |
signatures | +1.508 |
NX | +1.486 |
Neg logit contributions | |
mond | -2.011 |
ccording | -1.969 |
olate | -1.946 |
strip | -1.896 |
sole | -1.865 |
Token | Crit |
Token ID | 18559 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
rez | +2.257 |
Cipher | +2.238 |
iewicz | +2.217 |
signatures | +2.061 |
pps | +2.045 |
Neg logit contributions | |
mond | -1.973 |
ccording | -1.914 |
olate | -1.903 |
strip | -1.822 |
sole | -1.793 |
Token | here |
Token ID | 994 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Cipher | +1.034 |
rez | +1.020 |
iewicz | +1.005 |
signatures | +0.902 |
vier | +0.888 |
Neg logit contributions | |
mond | -1.795 |
olate | -1.744 |
ccording | -1.740 |
strip | -1.706 |
sole | -1.682 |
Token | . |
Token ID | 13 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
Cipher | +0.661 |
rez | +0.653 |
iewicz | +0.643 |
signatures | +0.587 |
NX | +0.580 |
Neg logit contributions | |
mond | -0.902 |
olate | -0.871 |
ccording | -0.852 |
strip | -0.850 |
sole | -0.838 |
Token | Sign |
Token ID | 5865 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Cipher | +0.065 |
rez | +0.063 |
iewicz | +0.063 |
signatures | +0.052 |
NX | +0.052 |
Neg logit contributions | |
mond | -0.200 |
olate | -0.195 |
strip | -0.192 |
ccording | -0.191 |
sole | -0.189 |
Token | up |
Token ID | 510 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
Cipher | +1.175 |
rez | +1.170 |
iewicz | +1.147 |
signatures | +1.051 |
pps | +1.029 |
Neg logit contributions | |
mond | -1.733 |
ccording | -1.705 |
olate | -1.682 |
strip | -1.641 |
sole | -1.614 |
Token | for |
Token ID | 329 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Cipher | +1.831 |
rez | +1.824 |
iewicz | +1.789 |
signatures | +1.654 |
vier | +1.621 |
Neg logit contributions | |
ccording | -2.489 |
mond | -2.471 |
olate | -2.413 |
strip | -2.339 |
sole | -2.301 |
Token | Take |
Token ID | 7214 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Cipher | +0.783 |
rez | +0.776 |
iewicz | +0.770 |
signatures | +0.716 |
vier | +0.712 |
Neg logit contributions | |
mond | -0.636 |
olate | -0.611 |
ccording | -0.605 |
strip | -0.592 |
sole | -0.578 |
Token | Action |
Token ID | 7561 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
rez | +1.520 |
Cipher | +1.480 |
iewicz | +1.397 |
AK | +1.128 |
NX | +1.081 |
Neg logit contributions | |
ccording | -9.688 |
mond | -9.067 |
strip | -8.913 |
olate | -8.852 |
ntil | -8.792 |
Token | Now |
Token ID | 2735 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
Cipher | +5.869 |
rez | +5.663 |
iewicz | +5.580 |
AK | +5.417 |
NX | +5.332 |
Neg logit contributions | |
ccording | -5.323 |
olate | -4.615 |
mond | -4.506 |
ntil | -4.456 |
strip | -4.408 |
Token | and |
Token ID | 290 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
Cipher | +2.316 |
rez | +2.311 |
iewicz | +2.283 |
signatures | +2.109 |
vier | +2.053 |
Neg logit contributions | |
ccording | -3.244 |
mond | -3.188 |
olate | -3.097 |
strip | -3.030 |
sole | -2.957 |
Token | we |
Token ID | 356 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
rez | +1.951 |
Cipher | +1.946 |
iewicz | +1.900 |
signatures | +1.724 |
pps | +1.681 |
Neg logit contributions | |
mond | -3.497 |
ccording | -3.483 |
olate | -3.403 |
strip | -3.312 |
sole | -3.277 |
Token | � |
Token ID | 447 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
rez | +2.527 |
Cipher | +2.515 |
iewicz | +2.464 |
signatures | +2.270 |
pps | +2.252 |
Neg logit contributions | |
mond | -3.253 |
ccording | -3.191 |
olate | -3.147 |
strip | -3.068 |
sole | -3.017 |
Token | Back |
Token ID | 5157 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
mond | +1.440 |
ccording | +1.400 |
olate | +1.400 |
strip | +1.343 |
sole | +1.330 |
Neg logit contributions | |
Cipher | -1.403 |
rez | -1.374 |
iewicz | -1.367 |
signatures | -1.275 |
NX | -1.245 |
Token | ! |
Token ID | 0 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
mond | +1.660 |
olate | +1.609 |
ccording | +1.596 |
strip | +1.569 |
sole | +1.553 |
Neg logit contributions | |
rez | -0.994 |
Cipher | -0.989 |
iewicz | -0.970 |
signatures | -0.870 |
vier | -0.860 |
Token | Sign |
Token ID | 5865 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
mond | +0.169 |
olate | +0.162 |
strip | +0.162 |
ccording | +0.162 |
sole | +0.159 |
Neg logit contributions | |
rez | -0.063 |
Cipher | -0.063 |
iewicz | -0.061 |
vier | -0.053 |
NX | -0.053 |
Token | up |
Token ID | 510 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Cipher | +0.850 |
rez | +0.841 |
iewicz | +0.829 |
signatures | +0.755 |
vier | +0.744 |
Neg logit contributions | |
mond | -1.205 |
olate | -1.168 |
ccording | -1.168 |
strip | -1.140 |
sole | -1.122 |
Token | for |
Token ID | 329 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
Cipher | +1.480 |
rez | +1.465 |
iewicz | +1.447 |
signatures | +1.325 |
NX | +1.309 |
Neg logit contributions | |
mond | -1.829 |
olate | -1.767 |
ccording | -1.762 |
strip | -1.724 |
sole | -1.696 |
Token | Take |
Token ID | 7214 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
mond | +0.209 |
ccording | +0.202 |
olate | +0.200 |
strip | +0.194 |
sole | +0.189 |
Neg logit contributions | |
rez | -0.283 |
Cipher | -0.282 |
iewicz | -0.282 |
vier | -0.262 |
NX | -0.259 |
Token | Action |
Token ID | 7561 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
rez | +1.310 |
Cipher | +1.257 |
iewicz | +1.174 |
NX | +0.930 |
AK | +0.884 |
Neg logit contributions | |
ccording | -9.751 |
mond | -9.107 |
strip | -9.000 |
olate | -8.911 |
ntil | -8.908 |
Token | Now |
Token ID | 2735 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Cipher | +5.816 |
rez | +5.778 |
iewicz | +5.492 |
signatures | +5.415 |
AK | +5.295 |
Neg logit contributions | |
ccording | -4.829 |
olate | -4.601 |
mond | -4.515 |
sole | -4.363 |
strip | -4.340 |
Token | and |
Token ID | 290 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
Cipher | +1.478 |
rez | +1.461 |
iewicz | +1.439 |
signatures | +1.335 |
pps | +1.303 |
Neg logit contributions | |
mond | -1.915 |
ccording | -1.873 |
olate | -1.855 |
strip | -1.814 |
sole | -1.771 |
Token | we |
Token ID | 356 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
Cipher | +1.829 |
rez | +1.813 |
iewicz | +1.761 |
signatures | +1.623 |
pps | +1.565 |
Neg logit contributions | |
mond | -3.126 |
ccording | -3.059 |
olate | -3.040 |
strip | -2.960 |
sole | -2.933 |
Token | � |
Token ID | 447 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Cipher | +1.968 |
rez | +1.947 |
iewicz | +1.865 |
signatures | +1.727 |
pps | +1.682 |
Neg logit contributions | |
mond | -3.741 |
ccording | -3.692 |
olate | -3.646 |
strip | -3.586 |
sole | -3.529 |
Token | pointer |
Token ID | 17562 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
Cipher | +0.868 |
rez | +0.858 |
iewicz | +0.847 |
signatures | +0.787 |
NX | +0.774 |
Neg logit contributions | |
mond | -0.945 |
ccording | -0.913 |
olate | -0.911 |
strip | -0.888 |
sole | -0.873 |
Token | . |
Token ID | 13 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Cipher | +1.906 |
rez | +1.866 |
iewicz | +1.825 |
signatures | +1.713 |
AK | +1.665 |
Neg logit contributions | |
mond | -2.502 |
ccording | -2.450 |
olate | -2.418 |
strip | -2.371 |
sole | -2.337 |
Token | pub |
Token ID | 2240 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
Cipher | +0.899 |
rez | +0.888 |
iewicz | +0.875 |
signatures | +0.810 |
NX | +0.795 |
Neg logit contributions | |
mond | -1.071 |
ccording | -1.037 |
olate | -1.036 |
strip | -1.010 |
sole | -0.994 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Cipher | +2.509 |
rez | +2.459 |
iewicz | +2.396 |
signatures | +2.257 |
NX | +2.202 |
Neg logit contributions | |
mond | -3.109 |
ccording | -3.019 |
olate | -3.010 |
strip | -2.943 |
sole | -2.905 |
Token | null |
Token ID | 9242 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Cipher | +5.134 |
rez | +4.773 |
signatures | +4.751 |
iewicz | +4.671 |
AK | +4.530 |
Neg logit contributions | |
mond | -6.122 |
ccording | -6.110 |
olate | -5.773 |
strip | -5.733 |
sole | -5.720 |
Token | () |
Token ID | 7499 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Cipher | +0.656 |
rez | +0.648 |
iewicz | +0.639 |
signatures | +0.579 |
vier | +0.570 |
Neg logit contributions | |
mond | -0.991 |
olate | -0.963 |
ccording | -0.961 |
strip | -0.939 |
sole | -0.925 |
Token | -> |
Token ID | 4613 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
Cipher | +4.420 |
rez | +4.270 |
iewicz | +4.073 |
signatures | +3.978 |
AK | +3.939 |
Neg logit contributions | |
mond | -6.004 |
ccording | -5.962 |
olate | -5.804 |
strip | -5.757 |
sole | -5.710 |
Token | Atomic |
Token ID | 28976 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Cipher | +3.161 |
rez | +2.989 |
iewicz | +2.927 |
signatures | +2.815 |
NX | +2.755 |
Neg logit contributions | |
mond | -4.459 |
ccording | -4.417 |
olate | -4.281 |
strip | -4.266 |
sole | -4.204 |
Token | < |
Token ID | 1279 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
mond | +0.789 |
olate | +0.770 |
ccording | +0.763 |
strip | +0.742 |
sole | +0.732 |
Neg logit contributions | |
rez | -0.585 |
Cipher | -0.584 |
iewicz | -0.575 |
signatures | -0.518 |
vier | -0.518 |
Token | T |
Token ID | 309 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
Cipher | +1.412 |
rez | +1.390 |
iewicz | +1.372 |
signatures | +1.257 |
NX | +1.237 |
Neg logit contributions | |
mond | -1.920 |
ccording | -1.863 |
olate | -1.858 |
strip | -1.815 |
sole | -1.786 |
Token | > |
Token ID | 1875 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
Cipher | +0.201 |
rez | +0.199 |
iewicz | +0.197 |
signatures | +0.182 |
vier | +0.180 |
Neg logit contributions | |
mond | -0.216 |
olate | -0.209 |
ccording | -0.209 |
strip | -0.203 |
sole | -0.200 |
Token | . |
Token ID | 13 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
Cipher | +0.661 |
rez | +0.653 |
iewicz | +0.643 |
signatures | +0.587 |
NX | +0.580 |
Neg logit contributions | |
mond | -0.902 |
olate | -0.871 |
ccording | -0.852 |
strip | -0.850 |
sole | -0.838 |
Token | Sign |
Token ID | 5865 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Cipher | +0.065 |
rez | +0.063 |
iewicz | +0.063 |
signatures | +0.052 |
NX | +0.052 |
Neg logit contributions | |
mond | -0.200 |
olate | -0.195 |
strip | -0.192 |
ccording | -0.191 |
sole | -0.189 |
Token | up |
Token ID | 510 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
Cipher | +1.175 |
rez | +1.170 |
iewicz | +1.147 |
signatures | +1.051 |
pps | +1.029 |
Neg logit contributions | |
mond | -1.733 |
ccording | -1.705 |
olate | -1.682 |
strip | -1.641 |
sole | -1.614 |
Token | for |
Token ID | 329 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Cipher | +1.831 |
rez | +1.824 |
iewicz | +1.789 |
signatures | +1.654 |
vier | +1.621 |
Neg logit contributions | |
ccording | -2.489 |
mond | -2.471 |
olate | -2.413 |
strip | -2.339 |
sole | -2.301 |
Token | Take |
Token ID | 7214 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Cipher | +0.783 |
rez | +0.776 |
iewicz | +0.770 |
signatures | +0.716 |
vier | +0.712 |
Neg logit contributions | |
mond | -0.636 |
olate | -0.611 |
ccording | -0.605 |
strip | -0.592 |
sole | -0.578 |
Token | Action |
Token ID | 7561 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
rez | +1.520 |
Cipher | +1.480 |
iewicz | +1.397 |
AK | +1.128 |
NX | +1.081 |
Neg logit contributions | |
ccording | -9.688 |
mond | -9.067 |
strip | -8.913 |
olate | -8.852 |
ntil | -8.792 |
Token | Now |
Token ID | 2735 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
Cipher | +5.869 |
rez | +5.663 |
iewicz | +5.580 |
AK | +5.417 |
NX | +5.332 |
Neg logit contributions | |
ccording | -5.323 |
olate | -4.615 |
mond | -4.506 |
ntil | -4.456 |
strip | -4.408 |
Token | and |
Token ID | 290 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
Cipher | +2.316 |
rez | +2.311 |
iewicz | +2.283 |
signatures | +2.109 |
vier | +2.053 |
Neg logit contributions | |
ccording | -3.244 |
mond | -3.188 |
olate | -3.097 |
strip | -3.030 |
sole | -2.957 |
Token | we |
Token ID | 356 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
rez | +1.951 |
Cipher | +1.946 |
iewicz | +1.900 |
signatures | +1.724 |
pps | +1.681 |
Neg logit contributions | |
mond | -3.497 |
ccording | -3.483 |
olate | -3.403 |
strip | -3.312 |
sole | -3.277 |
Token | � |
Token ID | 447 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
rez | +2.527 |
Cipher | +2.515 |
iewicz | +2.464 |
signatures | +2.270 |
pps | +2.252 |
Neg logit contributions | |
mond | -3.253 |
ccording | -3.191 |
olate | -3.147 |
strip | -3.068 |
sole | -3.017 |
Token | � |
Token ID | 247 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
Cipher | +2.073 |
rez | +2.068 |
iewicz | +2.046 |
signatures | +1.936 |
pps | +1.921 |
Neg logit contributions | |
mond | -0.957 |
ccording | -0.918 |
olate | -0.900 |
strip | -0.868 |
sole | -0.836 |
Token | ! |
Token ID | 0 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
mond | +1.660 |
olate | +1.609 |
ccording | +1.596 |
strip | +1.569 |
sole | +1.553 |
Neg logit contributions | |
rez | -0.994 |
Cipher | -0.989 |
iewicz | -0.970 |
signatures | -0.870 |
vier | -0.860 |
Token | Sign |
Token ID | 5865 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
mond | +0.169 |
olate | +0.162 |
strip | +0.162 |
ccording | +0.162 |
sole | +0.159 |
Neg logit contributions | |
rez | -0.063 |
Cipher | -0.063 |
iewicz | -0.061 |
vier | -0.053 |
NX | -0.053 |
Token | up |
Token ID | 510 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Cipher | +0.850 |
rez | +0.841 |
iewicz | +0.829 |
signatures | +0.755 |
vier | +0.744 |
Neg logit contributions | |
mond | -1.205 |
olate | -1.168 |
ccording | -1.168 |
strip | -1.140 |
sole | -1.122 |
Token | for |
Token ID | 329 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
Cipher | +1.480 |
rez | +1.465 |
iewicz | +1.447 |
signatures | +1.325 |
NX | +1.309 |
Neg logit contributions | |
mond | -1.829 |
olate | -1.767 |
ccording | -1.762 |
strip | -1.724 |
sole | -1.696 |
Token | Take |
Token ID | 7214 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
mond | +0.209 |
ccording | +0.202 |
olate | +0.200 |
strip | +0.194 |
sole | +0.189 |
Neg logit contributions | |
rez | -0.283 |
Cipher | -0.282 |
iewicz | -0.282 |
vier | -0.262 |
NX | -0.259 |
Token | Action |
Token ID | 7561 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
rez | +1.310 |
Cipher | +1.257 |
iewicz | +1.174 |
NX | +0.930 |
AK | +0.884 |
Neg logit contributions | |
ccording | -9.751 |
mond | -9.107 |
strip | -9.000 |
olate | -8.911 |
ntil | -8.908 |
Token | Now |
Token ID | 2735 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Cipher | +5.816 |
rez | +5.778 |
iewicz | +5.492 |
signatures | +5.415 |
AK | +5.295 |
Neg logit contributions | |
ccording | -4.829 |
olate | -4.601 |
mond | -4.515 |
sole | -4.363 |
strip | -4.340 |
Token | and |
Token ID | 290 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
Cipher | +1.478 |
rez | +1.461 |
iewicz | +1.439 |
signatures | +1.335 |
pps | +1.303 |
Neg logit contributions | |
mond | -1.915 |
ccording | -1.873 |
olate | -1.855 |
strip | -1.814 |
sole | -1.771 |
Token | we |
Token ID | 356 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
Cipher | +1.829 |
rez | +1.813 |
iewicz | +1.761 |
signatures | +1.623 |
pps | +1.565 |
Neg logit contributions | |
mond | -3.126 |
ccording | -3.059 |
olate | -3.040 |
strip | -2.960 |
sole | -2.933 |
Token | � |
Token ID | 447 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Cipher | +1.968 |
rez | +1.947 |
iewicz | +1.865 |
signatures | +1.727 |
pps | +1.682 |
Neg logit contributions | |
mond | -3.741 |
ccording | -3.692 |
olate | -3.646 |
strip | -3.586 |
sole | -3.529 |
Token | � |
Token ID | 247 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
Cipher | +1.247 |
rez | +1.247 |
iewicz | +1.231 |
signatures | +1.168 |
pps | +1.159 |
Neg logit contributions | |
mond | -0.558 |
ccording | -0.535 |
olate | -0.523 |
strip | -0.503 |
sole | -0.485 |
Token | but |
Token ID | 475 |
Feature activation | +9.94e-02 |
Pos logit contributions | |
mond | +0.416 |
olate | +0.402 |
ccording | +0.401 |
strip | +0.391 |
sole | +0.384 |
Neg logit contributions | |
Cipher | -0.397 |
rez | -0.397 |
iewicz | -0.391 |
vier | -0.358 |
signatures | -0.358 |
Token | numbers |
Token ID | 3146 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
mond | +0.466 |
olate | +0.451 |
ccording | +0.449 |
strip | +0.435 |
sole | +0.428 |
Neg logit contributions | |
Cipher | -0.443 |
rez | -0.442 |
iewicz | -0.436 |
vier | -0.399 |
signatures | -0.398 |
Token | are |
Token ID | 389 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
Cipher | +0.093 |
rez | +0.092 |
iewicz | +0.091 |
signatures | +0.085 |
vier | +0.084 |
Neg logit contributions | |
mond | -0.085 |
olate | -0.082 |
ccording | -0.081 |
strip | -0.080 |
sole | -0.078 |
Token | growing |
Token ID | 3957 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
Cipher | +0.365 |
rez | +0.361 |
iewicz | +0.358 |
signatures | +0.330 |
vier | +0.328 |
Neg logit contributions | |
mond | -0.370 |
olate | -0.358 |
ccording | -0.357 |
strip | -0.348 |
sole | -0.341 |
Token | through |
Token ID | 832 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Cipher | +2.066 |
rez | +2.041 |
iewicz | +2.015 |
signatures | +1.885 |
NX | +1.840 |
Neg logit contributions | |
mond | -2.468 |
ccording | -2.419 |
olate | -2.395 |
strip | -2.333 |
sole | -2.302 |
Token | word |
Token ID | 1573 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Cipher | +1.299 |
rez | +1.283 |
iewicz | +1.267 |
signatures | +1.165 |
NX | +1.147 |
Neg logit contributions | |
mond | -1.637 |
ccording | -1.585 |
olate | -1.583 |
strip | -1.545 |
sole | -1.518 |
Token | of |
Token ID | 286 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Cipher | +3.570 |
rez | +3.460 |
iewicz | +3.422 |
signatures | +3.257 |
AK | +3.033 |
Neg logit contributions | |
ccording | -6.884 |
mond | -6.809 |
olate | -6.630 |
sole | -6.489 |
strip | -6.453 |
Token | mouth |
Token ID | 5422 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Cipher | +0.863 |
rez | +0.856 |
iewicz | +0.846 |
signatures | +0.790 |
vier | +0.782 |
Neg logit contributions | |
mond | -0.707 |
olate | -0.679 |
ccording | -0.678 |
strip | -0.657 |
sole | -0.644 |
Token | and |
Token ID | 290 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Cipher | +0.714 |
rez | +0.708 |
iewicz | +0.696 |
signatures | +0.634 |
vier | +0.629 |
Neg logit contributions | |
mond | -0.944 |
olate | -0.914 |
ccording | -0.911 |
strip | -0.891 |
sole | -0.876 |
Token | social |
Token ID | 1919 |
Feature activation | +1.55e-03 |
Pos logit contributions | |
Cipher | +0.613 |
rez | +0.612 |
iewicz | +0.602 |
signatures | +0.551 |
vier | +0.549 |
Neg logit contributions | |
mond | -0.685 |
olate | -0.663 |
ccording | -0.661 |
strip | -0.645 |
sole | -0.632 |
Token | media |
Token ID | 2056 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
mond | +0.008 |
olate | +0.008 |
ccording | +0.008 |
strip | +0.007 |
sole | +0.007 |
Neg logit contributions | |
rez | -0.006 |
Cipher | -0.006 |
iewicz | -0.006 |
pps | -0.006 |
vier | -0.006 |
Token | depth |
Token ID | 6795 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Cipher | +0.886 |
rez | +0.878 |
iewicz | +0.867 |
signatures | +0.803 |
vier | +0.793 |
Neg logit contributions | |
mond | -0.919 |
olate | -0.887 |
ccording | -0.887 |
strip | -0.863 |
sole | -0.847 |
Token | : |
Token ID | 1058 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
Cipher | +0.579 |
rez | +0.573 |
iewicz | +0.565 |
signatures | +0.511 |
NX | +0.505 |
Neg logit contributions | |
mond | -0.849 |
olate | -0.823 |
ccording | -0.821 |
strip | -0.804 |
sole | -0.790 |
Token | u |
Token ID | 334 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
Cipher | +2.181 |
rez | +2.117 |
iewicz | +2.091 |
signatures | +1.974 |
NX | +1.949 |
Neg logit contributions | |
mond | -2.078 |
ccording | -2.027 |
olate | -2.003 |
strip | -1.940 |
sole | -1.925 |
Token | 16 |
Token ID | 1433 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
mond | +0.282 |
olate | +0.270 |
ccording | +0.267 |
strip | +0.259 |
sole | +0.253 |
Neg logit contributions | |
Cipher | -0.432 |
rez | -0.430 |
iewicz | -0.426 |
signatures | -0.400 |
vier | -0.397 |
Token | , |
Token ID | 837 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Cipher | +1.198 |
rez | +1.180 |
iewicz | +1.152 |
signatures | +1.033 |
pps | +1.024 |
Neg logit contributions | |
mond | -2.330 |
ccording | -2.289 |
olate | -2.270 |
strip | -2.225 |
sole | -2.204 |
Token | // |
Token ID | 3373 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Cipher | +3.729 |
rez | +3.641 |
iewicz | +3.580 |
signatures | +3.453 |
AK | +3.387 |
Neg logit contributions | |
mond | -2.731 |
ccording | -2.651 |
olate | -2.615 |
strip | -2.504 |
sole | -2.482 |
Token | Current |
Token ID | 9236 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Cipher | +4.833 |
rez | +4.635 |
iewicz | +4.527 |
signatures | +4.334 |
AK | +4.275 |
Neg logit contributions | |
mond | -5.437 |
ccording | -5.355 |
olate | -5.218 |
sole | -5.133 |
strip | -5.104 |
Token | depth |
Token ID | 6795 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
mond | +0.954 |
olate | +0.921 |
ccording | +0.911 |
strip | +0.891 |
sole | +0.869 |
Neg logit contributions | |
rez | -1.070 |
Cipher | -1.068 |
iewicz | -1.060 |
vier | -0.973 |
signatures | -0.972 |
Token | since |
Token ID | 1201 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
mond | +1.685 |
olate | +1.635 |
ccording | +1.607 |
strip | +1.586 |
sole | +1.539 |
Neg logit contributions | |
rez | -1.378 |
Cipher | -1.372 |
iewicz | -1.367 |
vier | -1.227 |
NX | -1.223 |
Token | we |
Token ID | 356 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
mond | +0.472 |
olate | +0.454 |
ccording | +0.449 |
strip | +0.438 |
sole | +0.430 |
Neg logit contributions | |
rez | -0.459 |
Cipher | -0.457 |
iewicz | -0.457 |
vier | -0.413 |
pps | -0.413 |
Token | started |
Token ID | 2067 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Cipher | +1.559 |
rez | +1.548 |
iewicz | +1.519 |
signatures | +1.412 |
pps | +1.389 |
Neg logit contributions | |
mond | -1.726 |
ccording | -1.679 |
olate | -1.665 |
strip | -1.620 |
sole | -1.596 |
Token | FI |
Token ID | 11674 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
mond | +0.902 |
olate | +0.862 |
strip | +0.836 |
sole | +0.815 |
ccording | +0.808 |
Neg logit contributions | |
Cipher | -1.271 |
rez | -1.257 |
iewicz | -1.230 |
signatures | -1.168 |
NX | -1.161 |
Token | then |
Token ID | 788 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
mond | +1.951 |
olate | +1.904 |
ccording | +1.875 |
strip | +1.850 |
sole | +1.809 |
Neg logit contributions | |
Cipher | -1.492 |
rez | -1.477 |
iewicz | -1.461 |
vier | -1.322 |
signatures | -1.313 |
Token | you |
Token ID | 345 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
mond | +1.011 |
olate | +0.978 |
ccording | +0.963 |
strip | +0.949 |
sole | +0.923 |
Neg logit contributions | |
Cipher | -1.075 |
rez | -1.067 |
iewicz | -1.059 |
signatures | -0.977 |
vier | -0.971 |
Token | 're |
Token ID | 821 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
mond | +1.285 |
olate | +1.240 |
ccording | +1.210 |
strip | +1.206 |
sole | +1.179 |
Neg logit contributions | |
Cipher | -1.157 |
rez | -1.140 |
iewicz | -1.125 |
signatures | -1.037 |
vier | -1.033 |
Token | in |
Token ID | 287 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
mond | +1.622 |
olate | +1.566 |
ccording | +1.524 |
strip | +1.506 |
sole | +1.483 |
Neg logit contributions | |
rez | -1.535 |
Cipher | -1.520 |
iewicz | -1.504 |
vier | -1.388 |
pps | -1.375 |
Token | luck |
Token ID | 8458 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
mond | +0.738 |
olate | +0.708 |
ccording | +0.705 |
strip | +0.685 |
sole | +0.670 |
Neg logit contributions | |
Cipher | -0.916 |
rez | -0.909 |
iewicz | -0.899 |
signatures | -0.838 |
vier | -0.830 |
Token | . |
Token ID | 13 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
mond | +4.327 |
olate | +4.173 |
strip | +4.044 |
ccording | +4.033 |
sole | +3.939 |
Neg logit contributions | |
Cipher | -3.680 |
rez | -3.670 |
iewicz | -3.632 |
signatures | -3.294 |
vier | -3.255 |
Token | Turn |
Token ID | 6756 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
mond | +1.686 |
olate | +1.627 |
strip | +1.579 |
ccording | +1.574 |
sole | +1.529 |
Neg logit contributions | |
rez | -1.755 |
Cipher | -1.745 |
iewicz | -1.734 |
signatures | -1.613 |
vier | -1.600 |
Token | on |
Token ID | 319 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
mond | +0.190 |
olate | +0.184 |
ccording | +0.184 |
strip | +0.180 |
sole | +0.177 |
Neg logit contributions | |
Cipher | -0.120 |
rez | -0.119 |
iewicz | -0.117 |
signatures | -0.106 |
vier | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
mond | +0.188 |
ccording | +0.181 |
olate | +0.181 |
strip | +0.175 |
sole | +0.172 |
Neg logit contributions | |
Cipher | -0.201 |
rez | -0.199 |
iewicz | -0.197 |
signatures | -0.183 |
NX | -0.181 |
Token | monitor |
Token ID | 5671 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
mond | +1.197 |
olate | +1.139 |
ccording | +1.135 |
strip | +1.118 |
sole | +1.075 |
Neg logit contributions | |
Cipher | -1.503 |
rez | -1.499 |
iewicz | -1.487 |
signatures | -1.378 |
vier | -1.378 |
Token | ? |
Token ID | 30 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
mond | +0.418 |
olate | +0.404 |
ccording | +0.399 |
strip | +0.392 |
sole | +0.387 |
Neg logit contributions | |
Cipher | -0.388 |
rez | -0.382 |
iewicz | -0.376 |
signatures | -0.347 |
vier | -0.345 |
Token |
|
Token ID | 198 |
Feature activation | -2.53e-03 |
Pos logit contributions | |
Cipher | +1.391 |
rez | +1.373 |
iewicz | +1.359 |
signatures | +1.253 |
NX | +1.238 |
Neg logit contributions | |
mond | -1.559 |
ccording | -1.521 |
olate | -1.511 |
strip | -1.475 |
sole | -1.447 |
Token |
|
Token ID | 198 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
Cipher | +0.011 |
rez | +0.011 |
iewicz | +0.011 |
signatures | +0.010 |
NX | +0.010 |
Neg logit contributions | |
mond | -0.012 |
olate | -0.012 |
strip | -0.011 |
sole | -0.011 |
wo | -0.011 |
Token | William |
Token ID | 17121 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Cipher | +0.323 |
rez | +0.319 |
iewicz | +0.316 |
signatures | +0.294 |
NX | +0.291 |
Neg logit contributions | |
mond | -0.280 |
olate | -0.269 |
ccording | -0.268 |
strip | -0.261 |
sole | -0.256 |
Token | Carpenter |
Token ID | 32659 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
mond | +0.827 |
olate | +0.793 |
ccording | +0.778 |
strip | +0.766 |
sole | +0.761 |
Neg logit contributions | |
Cipher | -0.646 |
rez | -0.643 |
iewicz | -0.631 |
signatures | -0.582 |
pps | -0.577 |
Token | , |
Token ID | 11 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
mond | +0.788 |
olate | +0.758 |
ccording | +0.756 |
strip | +0.739 |
sole | +0.732 |
Neg logit contributions | |
Cipher | -0.606 |
rez | -0.598 |
iewicz | -0.588 |
signatures | -0.536 |
NX | -0.533 |
Token | Mont |
Token ID | 5575 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
mond | +4.217 |
olate | +3.964 |
ccording | +3.924 |
strip | +3.863 |
sole | +3.827 |
Neg logit contributions | |
rez | -3.403 |
Cipher | -3.374 |
iewicz | -3.370 |
vier | -3.058 |
signatures | -3.032 |
Token | pel |
Token ID | 30242 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
mond | +1.628 |
olate | +1.533 |
ccording | +1.478 |
strip | +1.462 |
sole | +1.437 |
Neg logit contributions | |
Cipher | -2.885 |
iewicz | -2.821 |
rez | -2.811 |
signatures | -2.695 |
NX | -2.668 |
Token | ier |
Token ID | 959 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
mond | +2.517 |
olate | +2.403 |
strip | +2.359 |
sole | +2.342 |
wo | +2.305 |
Neg logit contributions | |
Cipher | -1.539 |
rez | -1.438 |
iewicz | -1.417 |
signatures | -1.330 |
NX | -1.310 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
mond | +2.660 |
olate | +2.492 |
ccording | +2.490 |
strip | +2.422 |
sole | +2.403 |
Neg logit contributions | |
Cipher | -2.412 |
rez | -2.402 |
iewicz | -2.349 |
vier | -2.150 |
signatures | -2.141 |
Token |
|
Token ID | 198 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
mond | +0.492 |
olate | +0.470 |
strip | +0.457 |
sole | +0.449 |
wo | +0.443 |
Neg logit contributions | |
Cipher | -0.482 |
rez | -0.476 |
iewicz | -0.467 |
signatures | -0.435 |
NX | -0.430 |
Token | R |
Token ID | 49 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
mond | +1.209 |
olate | +1.151 |
ccording | +1.138 |
strip | +1.121 |
sole | +1.098 |
Neg logit contributions | |
Cipher | -1.447 |
rez | -1.418 |
iewicz | -1.410 |
signatures | -1.327 |
NX | -1.310 |
Token | end |
Token ID | 437 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
mond | +0.370 |
olate | +0.355 |
ccording | +0.351 |
strip | +0.347 |
sole | +0.339 |
Neg logit contributions | |
Cipher | -0.350 |
rez | -0.345 |
iewicz | -0.339 |
signatures | -0.314 |
NX | -0.312 |
Token | ering |
Token ID | 1586 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
mond | +0.866 |
olate | +0.839 |
ccording | +0.830 |
strip | +0.818 |
sole | +0.805 |
Neg logit contributions | |
Cipher | -0.585 |
rez | -0.571 |
iewicz | -0.569 |
signatures | -0.514 |
pps | -0.512 |
Token | of |
Token ID | 286 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
mond | +1.761 |
olate | +1.685 |
ccording | +1.680 |
strip | +1.658 |
sole | +1.617 |
Neg logit contributions | |
rez | -1.349 |
Cipher | -1.348 |
iewicz | -1.319 |
vier | -1.226 |
pps | -1.206 |
Token | 1 |
Token ID | 352 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
mond | +2.209 |
olate | +2.106 |
ccording | +2.071 |
strip | +2.038 |
sole | +1.984 |
Neg logit contributions | |
rez | -2.358 |
Cipher | -2.349 |
iewicz | -2.323 |
vier | -2.140 |
pps | -2.134 |
Token | E |
Token ID | 412 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
mond | +1.482 |
olate | +1.417 |
ccording | +1.406 |
strip | +1.383 |
sole | +1.357 |
Neg logit contributions | |
rez | -1.313 |
Cipher | -1.312 |
iewicz | -1.289 |
signatures | -1.186 |
vier | -1.182 |
Token | gl |
Token ID | 4743 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
mond | +2.213 |
olate | +1.900 |
strip | +1.878 |
sole | +1.857 |
wo | +1.699 |
Neg logit contributions | |
Cipher | -6.467 |
iewicz | -6.412 |
rez | -6.386 |
signatures | -6.140 |
NX | -6.026 |
Token | inton |
Token ID | 2371 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
mond | +0.579 |
olate | +0.553 |
strip | +0.540 |
sole | +0.531 |
ccording | +0.526 |
Neg logit contributions | |
Cipher | -0.551 |
rez | -0.545 |
iewicz | -0.530 |
signatures | -0.504 |
NX | -0.497 |
Token | East |
Token ID | 3687 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
mond | +1.486 |
olate | +1.429 |
ccording | +1.401 |
strip | +1.381 |
sole | +1.350 |
Neg logit contributions | |
rez | -1.587 |
Cipher | -1.579 |
iewicz | -1.551 |
vier | -1.443 |
signatures | -1.438 |
Token | , |
Token ID | 11 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
mond | +1.067 |
olate | +1.028 |
ccording | +1.016 |
strip | +1.003 |
sole | +0.982 |
Neg logit contributions | |
Cipher | -0.855 |
rez | -0.854 |
iewicz | -0.834 |
vier | -0.770 |
signatures | -0.759 |
Token | image |
Token ID | 2939 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
mond | +0.083 |
ccording | +0.080 |
olate | +0.080 |
strip | +0.077 |
sole | +0.076 |
Neg logit contributions | |
Cipher | -0.106 |
rez | -0.105 |
iewicz | -0.104 |
signatures | -0.097 |
NX | -0.096 |
Token | will |
Token ID | 481 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
Cipher | +1.516 |
rez | +1.502 |
iewicz | +1.488 |
signatures | +1.379 |
NX | +1.355 |
Neg logit contributions | |
mond | -1.721 |
ccording | -1.680 |
olate | -1.657 |
strip | -1.613 |
sole | -1.597 |
Token | be |
Token ID | 307 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
Cipher | +0.051 |
rez | +0.050 |
iewicz | +0.050 |
signatures | +0.046 |
vier | +0.045 |
Neg logit contributions | |
mond | -0.051 |
olate | -0.049 |
ccording | -0.049 |
strip | -0.048 |
sole | -0.047 |
Token | set |
Token ID | 900 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
Cipher | +0.411 |
rez | +0.407 |
iewicz | +0.402 |
signatures | +0.372 |
vier | +0.368 |
Neg logit contributions | |
mond | -0.407 |
olate | -0.392 |
ccording | -0.391 |
strip | -0.381 |
sole | -0.374 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
mond | +0.011 |
olate | +0.010 |
ccording | +0.010 |
strip | +0.010 |
sole | +0.010 |
Neg logit contributions | |
Cipher | -0.010 |
rez | -0.010 |
iewicz | -0.010 |
signatures | -0.009 |
vier | -0.009 |
Token | * |
Token ID | 1635 |
Feature activation | +7.16e-03 |
Pos logit contributions | |
mond | +0.589 |
olate | +0.567 |
ccording | +0.565 |
strip | +0.552 |
sole | +0.540 |
Neg logit contributions | |
Cipher | -0.601 |
rez | -0.598 |
iewicz | -0.590 |
signatures | -0.546 |
vier | -0.542 |
Token | mod |
Token ID | 4666 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
mond | +0.035 |
olate | +0.034 |
ccording | +0.034 |
strip | +0.033 |
sole | +0.032 |
Neg logit contributions | |
Cipher | -0.031 |
rez | -0.030 |
iewicz | -0.030 |
signatures | -0.028 |
NX | -0.027 |
Token | eline |
Token ID | 4470 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
mond | +4.439 |
olate | +4.307 |
strip | +4.216 |
ccording | +4.154 |
sole | +4.121 |
Neg logit contributions | |
Cipher | -3.711 |
rez | -3.553 |
iewicz | -3.529 |
signatures | -3.346 |
AK | -3.304 |
Token | - |
Token ID | 12 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
mond | +4.079 |
olate | +3.922 |
strip | +3.905 |
ccording | +3.878 |
sole | +3.797 |
Neg logit contributions | |
Cipher | -2.910 |
iewicz | -2.857 |
rez | -2.848 |
signatures | -2.549 |
vier | -2.535 |
Token | version |
Token ID | 9641 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
mond | +3.372 |
strip | +3.235 |
olate | +3.164 |
sole | +3.109 |
ccording | +3.056 |
Neg logit contributions | |
Cipher | -3.996 |
iewicz | -3.899 |
rez | -3.825 |
signatures | -3.646 |
NX | -3.621 |
Token | * |
Token ID | 9 |
Feature activation | -7.36e-02 |
Pos logit contributions | |
mond | +0.421 |
olate | +0.406 |
ccording | +0.405 |
strip | +0.395 |
sole | +0.386 |
Neg logit contributions | |
Cipher | -0.445 |
rez | -0.442 |
iewicz | -0.437 |
signatures | -0.404 |
vier | -0.400 |
Token | If |
Token ID | 1002 |
Feature activation | +1.51e-03 |
Pos logit contributions | |
Cipher | +0.313 |
rez | +0.311 |
iewicz | +0.307 |
signatures | +0.282 |
vier | +0.279 |
Neg logit contributions | |
mond | -0.361 |
olate | -0.349 |
ccording | -0.349 |
strip | -0.340 |
sole | -0.333 |
Token | at |
Token ID | 379 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
mond | +0.031 |
olate | +0.030 |
ccording | +0.030 |
strip | +0.029 |
sole | +0.029 |
Neg logit contributions | |
Cipher | -0.025 |
rez | -0.025 |
iewicz | -0.025 |
signatures | -0.022 |
vier | -0.022 |
Token | its |
Token ID | 663 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
Cipher | +0.065 |
rez | +0.064 |
iewicz | +0.064 |
signatures | +0.059 |
vier | +0.059 |
Neg logit contributions | |
mond | -0.059 |
ccording | -0.057 |
olate | -0.057 |
strip | -0.055 |
sole | -0.054 |
Token | best |
Token ID | 1266 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
Cipher | +0.415 |
rez | +0.412 |
iewicz | +0.408 |
signatures | +0.378 |
vier | +0.376 |
Neg logit contributions | |
mond | -0.373 |
olate | -0.358 |
ccording | -0.358 |
strip | -0.347 |
sole | -0.342 |
Token | [ |
Token ID | 685 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Cipher | +0.351 |
rez | +0.347 |
iewicz | +0.341 |
signatures | +0.311 |
vier | +0.308 |
Neg logit contributions | |
mond | -0.476 |
olate | -0.460 |
ccording | -0.460 |
strip | -0.449 |
sole | -0.443 |
Token | em |
Token ID | 368 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
mond | +0.786 |
ccording | +0.751 |
olate | +0.750 |
strip | +0.739 |
sole | +0.727 |
Neg logit contributions | |
Cipher | -0.866 |
rez | -0.853 |
iewicz | -0.849 |
signatures | -0.790 |
NX | -0.783 |
Token | ph |
Token ID | 746 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Cipher | +0.272 |
rez | +0.270 |
iewicz | +0.267 |
signatures | +0.251 |
vier | +0.248 |
Neg logit contributions | |
mond | -0.199 |
olate | -0.191 |
ccording | -0.190 |
strip | -0.184 |
sole | -0.180 |
Token | ases |
Token ID | 1386 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
mond | +3.619 |
olate | +3.528 |
ccording | +3.367 |
strip | +3.319 |
sole | +3.180 |
Neg logit contributions | |
Cipher | -6.349 |
iewicz | -6.228 |
rez | -6.174 |
signatures | -5.920 |
NX | -5.851 |
Token | added |
Token ID | 2087 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
mond | +2.740 |
olate | +2.629 |
ccording | +2.619 |
strip | +2.566 |
sole | +2.490 |
Neg logit contributions | |
Cipher | -2.719 |
rez | -2.715 |
iewicz | -2.665 |
vier | -2.478 |
signatures | -2.471 |
Token | ]," |
Token ID | 17241 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
mond | +2.060 |
olate | +1.942 |
ccording | +1.939 |
strip | +1.900 |
sole | +1.875 |
Neg logit contributions | |
Cipher | -2.814 |
rez | -2.789 |
iewicz | -2.748 |
NX | -2.577 |
signatures | -2.564 |
Token | r |
Token ID | 374 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
mond | +1.100 |
ccording | +1.060 |
olate | +1.055 |
strip | +1.029 |
sole | +1.010 |
Neg logit contributions | |
Cipher | -1.033 |
rez | -1.026 |
iewicz | -1.019 |
vier | -0.935 |
signatures | -0.934 |
Token | aves |
Token ID | 3080 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Cipher | +0.551 |
rez | +0.542 |
iewicz | +0.539 |
signatures | +0.498 |
NX | +0.495 |
Neg logit contributions | |
mond | -0.579 |
olate | -0.556 |
ccording | -0.555 |
strip | -0.544 |
sole | -0.530 |
Token | under |
Token ID | 739 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Cipher | +0.831 |
rez | +0.822 |
iewicz | +0.811 |
signatures | +0.742 |
vier | +0.732 |
Neg logit contributions | |
mond | -1.070 |
olate | -1.036 |
ccording | -1.035 |
strip | -1.010 |
sole | -0.994 |
Token | these |
Token ID | 777 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
mond | +0.704 |
olate | +0.677 |
ccording | +0.677 |
strip | +0.659 |
sole | +0.647 |
Neg logit contributions | |
Cipher | -0.725 |
rez | -0.719 |
iewicz | -0.711 |
signatures | -0.658 |
NX | -0.651 |
Token | � |
Token ID | 564 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Cipher | +0.890 |
rez | +0.881 |
iewicz | +0.865 |
signatures | +0.797 |
vier | +0.780 |
Neg logit contributions | |
mond | -1.268 |
ccording | -1.232 |
olate | -1.230 |
strip | -1.200 |
sole | -1.182 |
Token | � |
Token ID | 250 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
rez | +1.466 |
Cipher | +1.465 |
iewicz | +1.445 |
signatures | +1.380 |
pps | +1.380 |
Neg logit contributions | |
mond | -0.433 |
ccording | -0.413 |
olate | -0.393 |
strip | -0.375 |
sole | -0.351 |
Token | self |
Token ID | 944 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
mond | +0.745 |
olate | +0.711 |
ccording | +0.708 |
strip | +0.698 |
sole | +0.687 |
Neg logit contributions | |
Cipher | -0.876 |
rez | -0.857 |
iewicz | -0.856 |
signatures | -0.797 |
NX | -0.793 |
Token | - |
Token ID | 12 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
mond | +1.346 |
ccording | +1.309 |
olate | +1.308 |
strip | +1.282 |
sole | +1.263 |
Neg logit contributions | |
Cipher | -0.900 |
rez | -0.877 |
iewicz | -0.871 |
signatures | -0.788 |
NX | -0.780 |
Token | imposed |
Token ID | 36457 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
mond | +1.114 |
ccording | +1.069 |
olate | +1.066 |
strip | +1.045 |
sole | +1.023 |
Neg logit contributions | |
Cipher | -1.287 |
rez | -1.266 |
iewicz | -1.258 |
signatures | -1.169 |
NX | -1.160 |
Token | , |
Token ID | 11 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
mond | +1.067 |
olate | +1.038 |
ccording | +1.037 |
strip | +1.015 |
sole | +1.001 |
Neg logit contributions | |
Cipher | -0.594 |
rez | -0.584 |
iewicz | -0.577 |
signatures | -0.514 |
NX | -0.508 |
Token | inf |
Token ID | 1167 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
mond | +0.152 |
olate | +0.147 |
ccording | +0.147 |
strip | +0.143 |
sole | +0.140 |
Neg logit contributions | |
Cipher | -0.135 |
rez | -0.134 |
iewicz | -0.132 |
signatures | -0.122 |
pps | -0.120 |
Token | lex |
Token ID | 2588 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
mond | +0.701 |
olate | +0.665 |
ccording | +0.623 |
strip | +0.603 |
sole | +0.592 |
Neg logit contributions | |
Cipher | -2.167 |
iewicz | -2.126 |
rez | -2.122 |
signatures | -2.026 |
NX | -2.019 |
Token | ible |
Token ID | 856 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Cipher | +0.908 |
rez | +0.900 |
iewicz | +0.885 |
signatures | +0.816 |
pps | +0.805 |
Neg logit contributions | |
mond | -1.161 |
ccording | -1.126 |
olate | -1.120 |
strip | -1.102 |
sole | -1.078 |
Token | to |
Token ID | 284 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
mond | +1.202 |
olate | +1.138 |
ccording | +1.122 |
strip | +1.109 |
sole | +1.098 |
Neg logit contributions | |
Cipher | -1.328 |
rez | -1.322 |
iewicz | -1.311 |
vier | -1.205 |
signatures | -1.195 |
Token | i |
Token ID | 1312 |
Feature activation | -8.73e-03 |
Pos logit contributions | |
Cipher | +2.327 |
rez | +2.308 |
iewicz | +2.275 |
signatures | +2.137 |
pps | +2.106 |
Neg logit contributions | |
mond | -2.085 |
ccording | -2.056 |
olate | -2.009 |
strip | -1.941 |
sole | -1.913 |
Token | ) |
Token ID | 8 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Cipher | +0.038 |
rez | +0.037 |
iewicz | +0.037 |
signatures | +0.034 |
vier | +0.034 |
Neg logit contributions | |
mond | -0.042 |
olate | -0.041 |
ccording | -0.041 |
strip | -0.040 |
sole | -0.039 |
Token | prohibit |
Token ID | 20767 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
mond | +1.232 |
olate | +1.200 |
strip | +1.162 |
ccording | +1.159 |
sole | +1.127 |
Neg logit contributions | |
Cipher | -1.398 |
iewicz | -1.381 |
rez | -1.381 |
vier | -1.280 |
signatures | -1.274 |
Token | the |
Token ID | 262 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
Cipher | +0.838 |
rez | +0.827 |
iewicz | +0.819 |
signatures | +0.763 |
vier | +0.750 |
Neg logit contributions | |
mond | -0.850 |
olate | -0.822 |
ccording | -0.821 |
strip | -0.797 |
sole | -0.782 |
Token | use |
Token ID | 779 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
Cipher | +0.184 |
rez | +0.183 |
iewicz | +0.180 |
signatures | +0.164 |
vier | +0.162 |
Neg logit contributions | |
mond | -0.250 |
ccording | -0.241 |
olate | -0.241 |
strip | -0.236 |
sole | -0.232 |
Token | of |
Token ID | 286 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
mond | +0.392 |
olate | +0.381 |
ccording | +0.380 |
strip | +0.371 |
sole | +0.366 |
Neg logit contributions | |
Cipher | -0.259 |
rez | -0.256 |
iewicz | -0.252 |
signatures | -0.229 |
pps | -0.226 |
Token | drones |
Token ID | 15382 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
mond | +1.438 |
olate | +1.386 |
ccording | +1.376 |
strip | +1.354 |
sole | +1.328 |
Neg logit contributions | |
rez | -1.251 |
Cipher | -1.250 |
iewicz | -1.235 |
vier | -1.127 |
signatures | -1.119 |
Token | by |
Token ID | 416 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
mond | +0.656 |
olate | +0.630 |
ccording | +0.624 |
strip | +0.614 |
sole | +0.606 |
Neg logit contributions | |
Cipher | -0.649 |
rez | -0.643 |
iewicz | -0.634 |
signatures | -0.583 |
vier | -0.582 |
Token | law |
Token ID | 1099 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
Cipher | +0.973 |
rez | +0.960 |
iewicz | +0.951 |
signatures | +0.879 |
NX | +0.866 |
Neg logit contributions | |
mond | -1.066 |
ccording | -1.034 |
olate | -1.033 |
strip | -1.004 |
sole | -0.985 |
Token | enforcement |
Token ID | 5394 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
Cipher | +1.607 |
rez | +1.588 |
iewicz | +1.552 |
signatures | +1.437 |
pps | +1.420 |
Neg logit contributions | |
mond | -2.279 |
olate | -2.242 |
ccording | -2.229 |
strip | -2.158 |
sole | -2.132 |
Token |
|
Token ID | 198 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
mond | +0.160 |
olate | +0.154 |
strip | +0.150 |
sole | +0.147 |
ccording | +0.145 |
Neg logit contributions | |
Cipher | -0.150 |
rez | -0.148 |
iewicz | -0.146 |
signatures | -0.135 |
NX | -0.133 |
Token | In |
Token ID | 818 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
mond | +0.012 |
olate | +0.012 |
ccording | +0.012 |
strip | +0.012 |
sole | +0.011 |
Neg logit contributions | |
Cipher | -0.014 |
rez | -0.014 |
iewicz | -0.013 |
signatures | -0.013 |
NX | -0.012 |
Token | Hum |
Token ID | 11054 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
mond | +0.628 |
olate | +0.605 |
ccording | +0.600 |
strip | +0.587 |
sole | +0.578 |
Neg logit contributions | |
Cipher | -0.595 |
rez | -0.592 |
iewicz | -0.582 |
signatures | -0.539 |
vier | -0.535 |
Token | bers |
Token ID | 1213 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
mond | +1.240 |
olate | +1.153 |
strip | +1.109 |
ccording | +1.100 |
sole | +1.075 |
Neg logit contributions | |
Cipher | -1.948 |
rez | -1.920 |
iewicz | -1.908 |
signatures | -1.811 |
NX | -1.781 |
Token | ide |
Token ID | 485 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
mond | +2.936 |
olate | +2.844 |
strip | +2.755 |
ccording | +2.748 |
sole | +2.736 |
Neg logit contributions | |
Cipher | -1.345 |
rez | -1.326 |
iewicz | -1.300 |
NX | -1.146 |
signatures | -1.139 |
Token | a |
Token ID | 257 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
mond | +2.291 |
olate | +2.201 |
ccording | +2.172 |
strip | +2.126 |
sole | +2.092 |
Neg logit contributions | |
Cipher | -1.954 |
rez | -1.938 |
iewicz | -1.909 |
vier | -1.743 |
pps | -1.738 |
Token | mosque |
Token ID | 18575 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
mond | +0.916 |
olate | +0.879 |
ccording | +0.879 |
strip | +0.854 |
sole | +0.837 |
Neg logit contributions | |
Cipher | -1.028 |
rez | -1.021 |
iewicz | -1.008 |
signatures | -0.937 |
vier | -0.930 |
Token | chairman |
Token ID | 8900 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
mond | +0.518 |
olate | +0.500 |
ccording | +0.499 |
strip | +0.487 |
sole | +0.479 |
Neg logit contributions | |
Cipher | -0.433 |
rez | -0.428 |
iewicz | -0.423 |
signatures | -0.387 |
vier | -0.385 |
Token | described |
Token ID | 3417 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
mond | +0.966 |
olate | +0.929 |
ccording | +0.916 |
strip | +0.897 |
sole | +0.890 |
Neg logit contributions | |
Cipher | -0.848 |
rez | -0.839 |
iewicz | -0.823 |
pps | -0.759 |
vier | -0.755 |
Token | how |
Token ID | 703 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
mond | +1.218 |
olate | +1.175 |
ccording | +1.164 |
strip | +1.135 |
sole | +1.113 |
Neg logit contributions | |
Cipher | -1.309 |
rez | -1.301 |
iewicz | -1.283 |
signatures | -1.189 |
vier | -1.187 |
Token | he |
Token ID | 339 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
mond | +0.841 |
olate | +0.811 |
ccording | +0.807 |
strip | +0.785 |
sole | +0.771 |
Neg logit contributions | |
Cipher | -0.801 |
rez | -0.796 |
iewicz | -0.788 |
vier | -0.725 |
pps | -0.723 |
Token | a |
Token ID | 257 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
Cipher | +0.508 |
rez | +0.505 |
iewicz | +0.499 |
signatures | +0.461 |
vier | +0.459 |
Neg logit contributions | |
mond | -0.517 |
olate | -0.499 |
ccording | -0.495 |
strip | -0.483 |
sole | -0.475 |
Token | brilliant |
Token ID | 10457 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Cipher | +0.363 |
rez | +0.359 |
iewicz | +0.355 |
signatures | +0.330 |
vier | +0.326 |
Neg logit contributions | |
mond | -0.348 |
olate | -0.335 |
ccording | -0.335 |
strip | -0.325 |
sole | -0.319 |
Token | idea |
Token ID | 2126 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
Cipher | +0.785 |
rez | +0.779 |
iewicz | +0.768 |
signatures | +0.705 |
vier | +0.699 |
Neg logit contributions | |
mond | -0.941 |
olate | -0.910 |
ccording | -0.908 |
strip | -0.887 |
sole | -0.872 |
Token | . |
Token ID | 13 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
Cipher | +0.040 |
rez | +0.040 |
iewicz | +0.039 |
vier | +0.036 |
signatures | +0.036 |
Neg logit contributions | |
mond | -0.045 |
olate | -0.044 |
ccording | -0.043 |
strip | -0.042 |
sole | -0.042 |
Token | For |
Token ID | 1114 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
rez | +0.369 |
Cipher | +0.368 |
iewicz | +0.362 |
signatures | +0.337 |
vier | +0.334 |
Neg logit contributions | |
mond | -0.391 |
olate | -0.374 |
ccording | -0.368 |
strip | -0.363 |
sole | -0.357 |
Token | me |
Token ID | 502 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
mond | +0.438 |
olate | +0.419 |
ccording | +0.415 |
strip | +0.407 |
sole | +0.402 |
Neg logit contributions | |
rez | -0.385 |
Cipher | -0.385 |
iewicz | -0.384 |
vier | -0.350 |
signatures | -0.348 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
mond | +0.589 |
olate | +0.569 |
ccording | +0.563 |
strip | +0.552 |
sole | +0.543 |
Neg logit contributions | |
Cipher | -0.451 |
rez | -0.448 |
iewicz | -0.440 |
vier | -0.403 |
signatures | -0.402 |
Token | it |
Token ID | 340 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
Cipher | +0.552 |
rez | +0.549 |
iewicz | +0.541 |
signatures | +0.492 |
vier | +0.490 |
Neg logit contributions | |
mond | -0.759 |
olate | -0.733 |
ccording | -0.729 |
strip | -0.714 |
sole | -0.703 |
Token | seems |
Token ID | 2331 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Cipher | +0.418 |
rez | +0.410 |
iewicz | +0.406 |
signatures | +0.372 |
vier | +0.372 |
Neg logit contributions | |
mond | -0.488 |
olate | -0.471 |
ccording | -0.466 |
strip | -0.456 |
sole | -0.452 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
mond | +0.520 |
olate | +0.501 |
ccording | +0.494 |
strip | +0.483 |
sole | +0.478 |
Neg logit contributions | |
Cipher | -0.516 |
rez | -0.511 |
iewicz | -0.507 |
signatures | -0.467 |
vier | -0.465 |
Token | make |
Token ID | 787 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
mond | +0.609 |
olate | +0.585 |
ccording | +0.580 |
strip | +0.568 |
sole | +0.556 |
Neg logit contributions | |
Cipher | -0.673 |
rez | -0.664 |
iewicz | -0.658 |
signatures | -0.612 |
vier | -0.609 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
mond | +0.009 |
olate | +0.009 |
ccording | +0.009 |
strip | +0.009 |
sole | +0.008 |
Neg logit contributions | |
Cipher | -0.007 |
rez | -0.007 |
iewicz | -0.007 |
signatures | -0.007 |
pps | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
Cipher | +0.069 |
rez | +0.068 |
iewicz | +0.067 |
signatures | +0.062 |
NX | +0.061 |
Neg logit contributions | |
mond | -0.081 |
ccording | -0.078 |
olate | -0.078 |
strip | -0.076 |
sole | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
mond | +0.210 |
olate | +0.201 |
strip | +0.196 |
sole | +0.193 |
ccording | +0.190 |
Neg logit contributions | |
Cipher | -0.195 |
rez | -0.193 |
iewicz | -0.190 |
signatures | -0.177 |
vier | -0.174 |
Token | The |
Token ID | 464 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Cipher | +0.247 |
rez | +0.245 |
iewicz | +0.242 |
signatures | +0.226 |
NX | +0.224 |
Neg logit contributions | |
mond | -0.207 |
olate | -0.198 |
ccording | -0.198 |
strip | -0.192 |
sole | -0.188 |
Token | shocking |
Token ID | 14702 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
mond | +0.536 |
olate | +0.514 |
ccording | +0.512 |
strip | +0.500 |
sole | +0.489 |
Neg logit contributions | |
Cipher | -0.639 |
rez | -0.636 |
iewicz | -0.628 |
vier | -0.583 |
signatures | -0.583 |
Token | incidents |
Token ID | 10207 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
mond | +1.644 |
olate | +1.585 |
ccording | +1.564 |
strip | +1.551 |
sole | +1.501 |
Neg logit contributions | |
rez | -1.894 |
Cipher | -1.885 |
iewicz | -1.841 |
vier | -1.743 |
pps | -1.709 |
Token | occurred |
Token ID | 5091 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
mond | +1.351 |
olate | +1.304 |
strip | +1.270 |
ccording | +1.269 |
sole | +1.232 |
Neg logit contributions | |
Cipher | -1.456 |
rez | -1.427 |
iewicz | -1.408 |
vier | -1.308 |
NX | -1.306 |
Token | in |
Token ID | 287 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
mond | +1.807 |
olate | +1.738 |
ccording | +1.703 |
strip | +1.691 |
sole | +1.673 |
Neg logit contributions | |
Cipher | -1.412 |
rez | -1.403 |
iewicz | -1.381 |
vier | -1.253 |
pps | -1.243 |
Token | Mar |
Token ID | 1526 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
mond | +1.181 |
olate | +1.142 |
ccording | +1.131 |
strip | +1.106 |
sole | +1.090 |
Neg logit contributions | |
Cipher | -1.160 |
rez | -1.159 |
iewicz | -1.149 |
signatures | -1.050 |
vier | -1.049 |
Token | an |
Token ID | 272 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
mond | +0.151 |
olate | +0.146 |
ccording | +0.145 |
strip | +0.142 |
sole | +0.139 |
Neg logit contributions | |
Cipher | -0.142 |
rez | -0.140 |
iewicz | -0.139 |
signatures | -0.129 |
NX | -0.127 |
Token | hao |
Token ID | 23778 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Cipher | +1.378 |
rez | +1.367 |
iewicz | +1.356 |
vier | +1.268 |
signatures | +1.267 |
Neg logit contributions | |
mond | -1.112 |
ccording | -1.101 |
olate | -1.074 |
strip | -1.042 |
sole | -1.022 |
Token | + |
Token ID | 1343 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Cipher | +1.593 |
rez | +1.560 |
iewicz | +1.538 |
signatures | +1.445 |
NX | +1.426 |
Neg logit contributions | |
mond | -1.651 |
ccording | -1.599 |
olate | -1.592 |
strip | -1.558 |
sole | -1.533 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Cipher | +0.695 |
rez | +0.685 |
iewicz | +0.679 |
signatures | +0.634 |
vier | +0.625 |
Neg logit contributions | |
mond | -0.601 |
olate | -0.575 |
ccording | -0.562 |
strip | -0.559 |
sole | -0.546 |
Token | --+ |
Token ID | 44785 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
Cipher | +1.215 |
rez | +1.204 |
iewicz | +1.192 |
signatures | +1.119 |
NX | +1.108 |
Neg logit contributions | |
mond | -0.869 |
olate | -0.829 |
ccording | -0.804 |
strip | -0.801 |
sole | -0.782 |
Token | + |
Token ID | 1343 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Cipher | +0.147 |
rez | +0.146 |
iewicz | +0.144 |
signatures | +0.134 |
vier | +0.133 |
Neg logit contributions | |
mond | -0.131 |
olate | -0.125 |
ccording | -0.123 |
strip | -0.122 |
sole | -0.119 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Cipher | +1.018 |
rez | +1.007 |
iewicz | +0.996 |
signatures | +0.928 |
vier | +0.917 |
Neg logit contributions | |
mond | -0.905 |
olate | -0.869 |
ccording | -0.862 |
strip | -0.844 |
sole | -0.827 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Cipher | +1.928 |
rez | +1.912 |
iewicz | +1.893 |
signatures | +1.774 |
NX | +1.755 |
Neg logit contributions | |
mond | -1.427 |
olate | -1.366 |
ccording | -1.349 |
strip | -1.321 |
sole | -1.291 |
Token | < |
Token ID | 1279 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
Cipher | +0.657 |
rez | +0.643 |
iewicz | +0.633 |
signatures | +0.581 |
NX | +0.571 |
Neg logit contributions | |
mond | -1.020 |
ccording | -0.990 |
olate | -0.987 |
strip | -0.970 |
sole | -0.956 |
Token | -- |
Token ID | 438 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Cipher | +1.405 |
rez | +1.391 |
iewicz | +1.362 |
signatures | +1.205 |
pps | +1.188 |
Neg logit contributions | |
mond | -2.956 |
ccording | -2.913 |
olate | -2.882 |
strip | -2.820 |
sole | -2.782 |
Token | Start |
Token ID | 7253 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
Cipher | +1.604 |
rez | +1.555 |
iewicz | +1.529 |
NX | +1.430 |
signatures | +1.428 |
Neg logit contributions | |
mond | -1.643 |
ccording | -1.586 |
olate | -1.574 |
strip | -1.530 |
sole | -1.524 |
Token | of |
Token ID | 286 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Cipher | +0.090 |
rez | +0.088 |
iewicz | +0.087 |
signatures | +0.079 |
pps | +0.079 |
Neg logit contributions | |
mond | -0.120 |
olate | -0.116 |
strip | -0.113 |
sole | -0.112 |
ccording | -0.110 |
Token | read |
Token ID | 1100 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
mond | +1.473 |
olate | +1.409 |
ccording | +1.399 |
strip | +1.362 |
sole | +1.329 |
Neg logit contributions | |
Cipher | -1.963 |
rez | -1.962 |
iewicz | -1.950 |
vier | -1.798 |
signatures | -1.789 |
Token | This |
Token ID | 1212 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Cipher | +0.668 |
rez | +0.663 |
iewicz | +0.657 |
signatures | +0.612 |
vier | +0.603 |
Neg logit contributions | |
mond | -0.575 |
olate | -0.552 |
ccording | -0.551 |
strip | -0.536 |
sole | -0.524 |
Token | Week |
Token ID | 6119 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
Cipher | +1.121 |
rez | +1.107 |
iewicz | +1.074 |
signatures | +1.001 |
pps | +0.990 |
Neg logit contributions | |
mond | -1.532 |
ccording | -1.497 |
olate | -1.481 |
strip | -1.454 |
sole | -1.426 |
Token | ." |
Token ID | 526 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
Cipher | +0.354 |
rez | +0.350 |
iewicz | +0.344 |
signatures | +0.315 |
NX | +0.311 |
Neg logit contributions | |
mond | -0.473 |
ccording | -0.461 |
olate | -0.460 |
strip | -0.448 |
sole | -0.441 |
Token | " |
Token ID | 366 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
mond | +0.390 |
olate | +0.377 |
ccording | +0.377 |
strip | +0.368 |
sole | +0.361 |
Neg logit contributions | |
Cipher | -0.330 |
rez | -0.327 |
iewicz | -0.323 |
signatures | -0.297 |
vier | -0.293 |
Token | That |
Token ID | 2504 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Cipher | +0.702 |
rez | +0.697 |
iewicz | +0.690 |
signatures | +0.643 |
vier | +0.636 |
Neg logit contributions | |
mond | -0.598 |
olate | -0.573 |
ccording | -0.568 |
strip | -0.557 |
sole | -0.546 |
Token | didn |
Token ID | 1422 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
mond | +0.731 |
olate | +0.707 |
ccording | +0.700 |
strip | +0.687 |
sole | +0.677 |
Neg logit contributions | |
Cipher | -0.615 |
rez | -0.612 |
iewicz | -0.605 |
vier | -0.553 |
pps | -0.547 |
Token | 't |
Token ID | 470 |
Feature activation | -1.74e-04 |
Pos logit contributions | |
Cipher | +0.358 |
rez | +0.353 |
iewicz | +0.348 |
signatures | +0.323 |
NX | +0.320 |
Neg logit contributions | |
mond | -0.380 |
olate | -0.366 |
strip | -0.356 |
sole | -0.350 |
ccording | -0.345 |
Token | work |
Token ID | 670 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Cipher | +0.001 |
rez | +0.001 |
iewicz | +0.001 |
signatures | +0.001 |
vier | +0.001 |
Neg logit contributions | |
mond | -0.001 |
ccording | -0.001 |
olate | -0.001 |
strip | -0.001 |
sole | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Cipher | +0.585 |
rez | +0.582 |
iewicz | +0.570 |
vier | +0.515 |
signatures | +0.514 |
Neg logit contributions | |
mond | -0.811 |
olate | -0.783 |
ccording | -0.774 |
strip | -0.766 |
sole | -0.754 |
Token | the |
Token ID | 262 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Cipher | +0.869 |
rez | +0.865 |
iewicz | +0.854 |
signatures | +0.785 |
vier | +0.781 |
Neg logit contributions | |
mond | -0.907 |
olate | -0.875 |
ccording | -0.869 |
strip | -0.852 |
sole | -0.839 |
Token | 1930 |
Token ID | 15533 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
Cipher | +1.189 |
rez | +1.177 |
iewicz | +1.163 |
signatures | +1.076 |
NX | +1.061 |
Neg logit contributions | |
mond | -1.328 |
ccording | -1.288 |
olate | -1.282 |
strip | -1.249 |
sole | -1.226 |
Token | through |
Token ID | 832 |
Feature activation | +3.25e-03 |
Pos logit contributions | |
mond | +2.227 |
olate | +2.169 |
ccording | +2.111 |
strip | +2.092 |
sole | +2.066 |
Neg logit contributions | |
Cipher | -1.866 |
rez | -1.847 |
iewicz | -1.829 |
signatures | -1.664 |
pps | -1.660 |
Token | an |
Token ID | 281 |
Feature activation | -8.93e-02 |
Pos logit contributions | |
mond | +0.015 |
olate | +0.014 |
ccording | +0.014 |
strip | +0.014 |
sole | +0.014 |
Neg logit contributions | |
Cipher | -0.015 |
rez | -0.015 |
iewicz | -0.015 |
signatures | -0.014 |
vier | -0.014 |
Token | episode |
Token ID | 4471 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Cipher | +0.391 |
rez | +0.384 |
iewicz | +0.383 |
vier | +0.352 |
signatures | +0.352 |
Neg logit contributions | |
mond | -0.424 |
olate | -0.418 |
ccording | -0.411 |
strip | -0.402 |
sole | -0.394 |
Token | , |
Token ID | 11 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
mond | +0.814 |
olate | +0.790 |
ccording | +0.781 |
strip | +0.771 |
sole | +0.757 |
Neg logit contributions | |
Cipher | -0.632 |
rez | -0.623 |
iewicz | -0.617 |
vier | -0.566 |
signatures | -0.562 |
Token | or |
Token ID | 393 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
mond | +1.556 |
olate | +1.511 |
ccording | +1.490 |
strip | +1.465 |
sole | +1.444 |
Neg logit contributions | |
Cipher | -1.544 |
rez | -1.536 |
iewicz | -1.515 |
vier | -1.397 |
pps | -1.393 |
Token | it |
Token ID | 340 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
mond | +1.173 |
olate | +1.139 |
ccording | +1.119 |
strip | +1.102 |
sole | +1.083 |
Neg logit contributions | |
Cipher | -1.163 |
rez | -1.150 |
iewicz | -1.136 |
signatures | -1.046 |
vier | -1.046 |
Token | can |
Token ID | 460 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Cipher | +0.460 |
rez | +0.454 |
iewicz | +0.448 |
signatures | +0.412 |
vier | +0.407 |
Neg logit contributions | |
mond | -0.548 |
olate | -0.529 |
ccording | -0.526 |
strip | -0.514 |
sole | -0.507 |
Token | be |
Token ID | 307 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
Cipher | +0.557 |
rez | +0.553 |
iewicz | +0.546 |
signatures | +0.508 |
vier | +0.501 |
Neg logit contributions | |
mond | -0.519 |
ccording | -0.500 |
olate | -0.499 |
strip | -0.485 |
sole | -0.476 |
Token | one |
Token ID | 530 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
mond | +0.397 |
olate | +0.384 |
ccording | +0.380 |
strip | +0.371 |
sole | +0.366 |
Neg logit contributions | |
Cipher | -0.407 |
rez | -0.402 |
iewicz | -0.399 |
signatures | -0.367 |
vier | -0.366 |
Token | of |
Token ID | 286 |
Feature activation | -8.07e-03 |
Pos logit contributions | |
Cipher | +0.393 |
rez | +0.388 |
iewicz | +0.381 |
signatures | +0.347 |
NX | +0.341 |
Neg logit contributions | |
mond | -0.596 |
ccording | -0.580 |
olate | -0.579 |
strip | -0.566 |
sole | -0.557 |
Token | the |
Token ID | 262 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
Cipher | +0.038 |
rez | +0.038 |
iewicz | +0.037 |
signatures | +0.035 |
NX | +0.034 |
Neg logit contributions | |
mond | -0.036 |
ccording | -0.035 |
olate | -0.035 |
strip | -0.034 |
sole | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
mond | +0.447 |
olate | +0.431 |
ccording | +0.428 |
strip | +0.418 |
sole | +0.409 |
Neg logit contributions | |
Cipher | -0.467 |
rez | -0.462 |
iewicz | -0.458 |
signatures | -0.422 |
vier | -0.420 |
Token | sheet |
Token ID | 9629 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Cipher | +0.605 |
rez | +0.600 |
iewicz | +0.593 |
signatures | +0.550 |
vier | +0.542 |
Neg logit contributions | |
mond | -0.605 |
olate | -0.583 |
ccording | -0.583 |
strip | -0.567 |
sole | -0.556 |
Token | of |
Token ID | 286 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
mond | +1.335 |
olate | +1.291 |
ccording | +1.264 |
strip | +1.256 |
sole | +1.233 |
Neg logit contributions | |
Cipher | -1.171 |
rez | -1.154 |
iewicz | -1.138 |
vier | -1.040 |
NX | -1.037 |
Token | ice |
Token ID | 4771 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
Cipher | +1.834 |
rez | +1.821 |
iewicz | +1.792 |
signatures | +1.675 |
AK | +1.628 |
Neg logit contributions | |
mond | -2.465 |
ccording | -2.406 |
olate | -2.381 |
strip | -2.326 |
sole | -2.284 |
Token | backwards |
Token ID | 16196 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
Cipher | +0.069 |
rez | +0.068 |
iewicz | +0.067 |
signatures | +0.061 |
vier | +0.061 |
Neg logit contributions | |
mond | -0.084 |
olate | -0.081 |
ccording | -0.080 |
strip | -0.079 |
sole | -0.078 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Cipher | +1.276 |
rez | +1.262 |
iewicz | +1.244 |
signatures | +1.138 |
vier | +1.123 |
Neg logit contributions | |
mond | -1.672 |
olate | -1.619 |
ccording | -1.617 |
strip | -1.579 |
sole | -1.554 |
Token | inland |
Token ID | 37874 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
Cipher | +0.756 |
rez | +0.748 |
iewicz | +0.739 |
signatures | +0.682 |
vier | +0.678 |
Neg logit contributions | |
mond | -0.751 |
olate | -0.724 |
ccording | -0.721 |
strip | -0.703 |
sole | -0.688 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Cipher | +0.994 |
rez | +0.983 |
iewicz | +0.969 |
signatures | +0.885 |
vier | +0.872 |
Neg logit contributions | |
mond | -1.343 |
olate | -1.301 |
ccording | -1.300 |
strip | -1.270 |
sole | -1.249 |
Token | � |
Token ID | 564 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
mond | +0.830 |
olate | +0.798 |
ccording | +0.783 |
strip | +0.773 |
sole | +0.756 |
Neg logit contributions | |
rez | -0.823 |
Cipher | -0.821 |
iewicz | -0.811 |
signatures | -0.753 |
vier | -0.747 |
Token | � |
Token ID | 250 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
mond | +0.309 |
olate | +0.288 |
ccording | +0.288 |
strip | +0.270 |
sole | +0.260 |
Neg logit contributions | |
Cipher | -0.906 |
rez | -0.898 |
iewicz | -0.893 |
signatures | -0.849 |
vier | -0.843 |
Token | During |
Token ID | 7191 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
mond | +0.982 |
ccording | +0.947 |
olate | +0.940 |
strip | +0.916 |
sole | +0.895 |
Neg logit contributions | |
Cipher | -1.130 |
rez | -1.116 |
iewicz | -1.108 |
signatures | -1.031 |
NX | -1.025 |
Token | is |
Token ID | 318 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Cipher | +0.880 |
rez | +0.869 |
iewicz | +0.857 |
signatures | +0.789 |
NX | +0.779 |
Neg logit contributions | |
mond | -1.051 |
olate | -1.014 |
ccording | -1.014 |
strip | -0.989 |
sole | -0.972 |
Token | fiercely |
Token ID | 33285 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
Cipher | +0.962 |
rez | +0.949 |
iewicz | +0.938 |
signatures | +0.865 |
NX | +0.857 |
Neg logit contributions | |
mond | -1.070 |
ccording | -1.036 |
olate | -1.034 |
strip | -1.006 |
sole | -0.990 |
Token | loyal |
Token ID | 9112 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Cipher | +0.161 |
rez | +0.160 |
iewicz | +0.158 |
signatures | +0.147 |
pps | +0.146 |
Neg logit contributions | |
mond | -0.142 |
olate | -0.137 |
ccording | -0.136 |
strip | -0.132 |
sole | -0.130 |
Token | to |
Token ID | 284 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
Cipher | +1.473 |
rez | +1.457 |
iewicz | +1.450 |
signatures | +1.348 |
pps | +1.333 |
Neg logit contributions | |
mond | -1.360 |
ccording | -1.319 |
olate | -1.316 |
strip | -1.279 |
sole | -1.250 |
Token | them |
Token ID | 606 |
Feature activation | +4.98e-03 |
Pos logit contributions | |
Cipher | +0.149 |
rez | +0.148 |
iewicz | +0.146 |
signatures | +0.135 |
vier | +0.134 |
Neg logit contributions | |
mond | -0.161 |
olate | -0.155 |
ccording | -0.155 |
strip | -0.151 |
sole | -0.148 |
Token | and |
Token ID | 290 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
mond | +0.026 |
olate | +0.025 |
ccording | +0.025 |
strip | +0.025 |
sole | +0.025 |
Neg logit contributions | |
Cipher | -0.019 |
rez | -0.019 |
iewicz | -0.019 |
signatures | -0.017 |
NX | -0.017 |
Token | completely |
Token ID | 3190 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
Cipher | +0.266 |
rez | +0.264 |
iewicz | +0.261 |
signatures | +0.239 |
vier | +0.237 |
Neg logit contributions | |
mond | -0.309 |
olate | -0.299 |
ccording | -0.298 |
strip | -0.290 |
sole | -0.286 |
Token | at |
Token ID | 379 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
mond | +1.425 |
olate | +1.378 |
ccording | +1.369 |
strip | +1.341 |
sole | +1.317 |
Neg logit contributions | |
Cipher | -1.289 |
rez | -1.283 |
iewicz | -1.272 |
signatures | -1.157 |
pps | -1.156 |
Token | ease |
Token ID | 10152 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
mond | +0.638 |
ccording | +0.611 |
olate | +0.610 |
strip | +0.593 |
sole | +0.580 |
Neg logit contributions | |
Cipher | -0.797 |
rez | -0.789 |
iewicz | -0.784 |
signatures | -0.731 |
vier | -0.724 |
Token | in |
Token ID | 287 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
mond | +0.147 |
olate | +0.142 |
ccording | +0.141 |
strip | +0.138 |
sole | +0.136 |
Neg logit contributions | |
Cipher | -0.132 |
rez | -0.131 |
iewicz | -0.129 |
signatures | -0.119 |
NX | -0.118 |
Token | their |
Token ID | 511 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
mond | +0.317 |
olate | +0.306 |
ccording | +0.305 |
strip | +0.298 |
sole | +0.293 |
Neg logit contributions | |
Cipher | -0.304 |
rez | -0.302 |
iewicz | -0.298 |
signatures | -0.275 |
vier | -0.275 |
Token | a |
Token ID | 257 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
mond | +0.203 |
olate | +0.195 |
ccording | +0.195 |
strip | +0.190 |
sole | +0.186 |
Neg logit contributions | |
Cipher | -0.201 |
rez | -0.199 |
iewicz | -0.196 |
signatures | -0.180 |
pps | -0.180 |
Token | more |
Token ID | 517 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
mond | +0.727 |
olate | +0.703 |
ccording | +0.698 |
strip | +0.677 |
sole | +0.669 |
Neg logit contributions | |
Cipher | -0.756 |
rez | -0.746 |
iewicz | -0.739 |
signatures | -0.684 |
pps | -0.681 |
Token | gentle |
Token ID | 10296 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
Cipher | +1.720 |
rez | +1.716 |
iewicz | +1.690 |
signatures | +1.582 |
NX | +1.560 |
Neg logit contributions | |
mond | -1.546 |
ccording | -1.498 |
olate | -1.491 |
strip | -1.452 |
sole | -1.417 |
Token | , |
Token ID | 11 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
Cipher | +1.990 |
rez | +1.984 |
iewicz | +1.953 |
signatures | +1.804 |
vier | +1.779 |
Neg logit contributions | |
mond | -2.224 |
ccording | -2.158 |
olate | -2.147 |
strip | -2.095 |
sole | -2.056 |
Token | though |
Token ID | 996 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Cipher | +0.181 |
rez | +0.180 |
iewicz | +0.177 |
signatures | +0.165 |
pps | +0.163 |
Neg logit contributions | |
mond | -0.165 |
olate | -0.159 |
ccording | -0.159 |
strip | -0.155 |
sole | -0.152 |
Token | often |
Token ID | 1690 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
Cipher | +0.583 |
rez | +0.578 |
iewicz | +0.571 |
signatures | +0.528 |
pps | +0.523 |
Neg logit contributions | |
mond | -0.579 |
olate | -0.558 |
ccording | -0.556 |
strip | -0.542 |
sole | -0.532 |
Token | ineffective |
Token ID | 23693 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Cipher | +3.443 |
rez | +3.436 |
iewicz | +3.395 |
signatures | +3.191 |
AK | +3.128 |
Neg logit contributions | |
mond | -3.514 |
ccording | -3.441 |
olate | -3.379 |
strip | -3.299 |
sole | -3.238 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Cipher | +1.375 |
rez | +1.365 |
iewicz | +1.346 |
signatures | +1.230 |
NX | +1.211 |
Neg logit contributions | |
mond | -1.843 |
ccording | -1.788 |
olate | -1.783 |
strip | -1.740 |
sole | -1.714 |
Token | approach |
Token ID | 3164 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
Cipher | +0.557 |
rez | +0.551 |
iewicz | +0.545 |
signatures | +0.505 |
pps | +0.500 |
Neg logit contributions | |
mond | -0.557 |
olate | -0.539 |
ccording | -0.536 |
strip | -0.522 |
sole | -0.513 |
Token | to |
Token ID | 284 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
Cipher | +0.252 |
rez | +0.249 |
iewicz | +0.246 |
signatures | +0.227 |
vier | +0.224 |
Neg logit contributions | |
mond | -0.283 |
olate | -0.274 |
ccording | -0.273 |
strip | -0.266 |
sole | -0.262 |
Token | healing |
Token ID | 11516 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Cipher | +0.263 |
rez | +0.260 |
iewicz | +0.257 |
signatures | +0.237 |
pps | +0.234 |
Neg logit contributions | |
mond | -0.287 |
olate | -0.277 |
ccording | -0.276 |
strip | -0.270 |
sole | -0.265 |
Token | public |
Token ID | 1171 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
mond | +1.518 |
olate | +1.465 |
ccording | +1.460 |
strip | +1.422 |
sole | +1.402 |
Neg logit contributions | |
Cipher | -1.499 |
rez | -1.490 |
iewicz | -1.472 |
signatures | -1.344 |
pps | -1.341 |
Token | monitoring |
Token ID | 9904 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
mond | +0.287 |
olate | +0.277 |
ccording | +0.277 |
strip | +0.270 |
sole | +0.265 |
Neg logit contributions | |
Cipher | -0.263 |
rez | -0.260 |
iewicz | -0.257 |
signatures | -0.236 |
pps | -0.234 |
Token | and |
Token ID | 290 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
mond | +1.140 |
olate | +1.097 |
ccording | +1.094 |
strip | +1.079 |
sole | +1.062 |
Neg logit contributions | |
Cipher | -0.873 |
rez | -0.871 |
iewicz | -0.855 |
vier | -0.776 |
signatures | -0.768 |
Token | accountability |
Token ID | 18241 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
mond | +0.226 |
ccording | +0.219 |
olate | +0.219 |
strip | +0.213 |
sole | +0.209 |
Neg logit contributions | |
Cipher | -0.196 |
rez | -0.194 |
iewicz | -0.192 |
signatures | -0.177 |
vier | -0.174 |
Token | ; |
Token ID | 26 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Cipher | +0.422 |
rez | +0.418 |
iewicz | +0.413 |
signatures | +0.377 |
vier | +0.372 |
Neg logit contributions | |
mond | -0.549 |
olate | -0.531 |
ccording | -0.531 |
strip | -0.518 |
sole | -0.510 |
Token | and |
Token ID | 290 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
Cipher | +0.925 |
rez | +0.907 |
iewicz | +0.897 |
signatures | +0.820 |
NX | +0.810 |
Neg logit contributions | |
mond | -1.353 |
ccording | -1.315 |
olate | -1.308 |
strip | -1.273 |
sole | -1.264 |
Token | iv |
Token ID | 21628 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
Cipher | +2.452 |
rez | +2.326 |
iewicz | +2.263 |
signatures | +2.089 |
NX | +2.051 |
Neg logit contributions | |
mond | -5.069 |
ccording | -5.003 |
olate | -4.900 |
strip | -4.786 |
sole | -4.786 |
Token | ) |
Token ID | 8 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
Cipher | +2.065 |
rez | +2.056 |
iewicz | +2.024 |
signatures | +1.858 |
vier | +1.838 |
Neg logit contributions | |
ccording | -2.562 |
mond | -2.540 |
olate | -2.459 |
strip | -2.407 |
sole | -2.360 |
Token | mandate |
Token ID | 14598 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Cipher | +1.773 |
rez | +1.759 |
iewicz | +1.725 |
signatures | +1.627 |
pps | +1.594 |
Neg logit contributions | |
mond | -1.888 |
ccording | -1.863 |
olate | -1.817 |
strip | -1.769 |
sole | -1.740 |
Token | that |
Token ID | 326 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Cipher | +1.234 |
rez | +1.203 |
iewicz | +1.193 |
signatures | +1.130 |
pps | +1.094 |
Neg logit contributions | |
mond | -1.440 |
ccording | -1.401 |
olate | -1.391 |
strip | -1.358 |
sole | -1.328 |
Token | pictures |
Token ID | 5986 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
Cipher | +0.669 |
rez | +0.660 |
iewicz | +0.652 |
signatures | +0.607 |
NX | +0.596 |
Neg logit contributions | |
mond | -0.725 |
ccording | -0.701 |
olate | -0.701 |
strip | -0.682 |
sole | -0.669 |
Token |
|
Token ID | 198 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
mond | +0.236 |
olate | +0.227 |
ccording | +0.224 |
strip | +0.220 |
sole | +0.216 |
Neg logit contributions | |
rez | -0.240 |
Cipher | -0.239 |
iewicz | -0.236 |
signatures | -0.218 |
vier | -0.217 |
Token |
|
Token ID | 198 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
mond | +0.453 |
olate | +0.436 |
strip | +0.424 |
sole | +0.417 |
ccording | +0.413 |
Neg logit contributions | |
Cipher | -0.428 |
rez | -0.423 |
iewicz | -0.417 |
signatures | -0.388 |
NX | -0.383 |
Token | While |
Token ID | 3633 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Cipher | +0.178 |
rez | +0.176 |
iewicz | +0.175 |
signatures | +0.164 |
NX | +0.162 |
Neg logit contributions | |
mond | -0.141 |
olate | -0.135 |
ccording | -0.134 |
strip | -0.131 |
sole | -0.129 |
Token | the |
Token ID | 262 |
Feature activation | -6.72e-03 |
Pos logit contributions | |
Cipher | +0.672 |
rez | +0.671 |
iewicz | +0.662 |
vier | +0.604 |
signatures | +0.603 |
Neg logit contributions | |
mond | -0.723 |
olate | -0.699 |
ccording | -0.697 |
strip | -0.678 |
sole | -0.666 |
Token | Oregon |
Token ID | 8819 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
rez | +0.029 |
Cipher | +0.028 |
iewicz | +0.028 |
vier | +0.026 |
pps | +0.025 |
Neg logit contributions | |
mond | -0.033 |
olate | -0.032 |
ccording | -0.032 |
strip | -0.031 |
sole | -0.030 |
Token | Cannabis |
Token ID | 28838 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
Cipher | +0.288 |
rez | +0.287 |
iewicz | +0.284 |
vier | +0.260 |
pps | +0.259 |
Neg logit contributions | |
mond | -0.310 |
olate | -0.300 |
ccording | -0.299 |
strip | -0.292 |
sole | -0.287 |
Token | Tax |
Token ID | 9241 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
Cipher | +3.018 |
rez | +2.945 |
iewicz | +2.899 |
signatures | +2.711 |
NX | +2.635 |
Neg logit contributions | |
mond | -4.176 |
ccording | -4.087 |
olate | -4.052 |
strip | -3.950 |
sole | -3.909 |
Token | Act |
Token ID | 2191 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Cipher | +0.185 |
rez | +0.184 |
iewicz | +0.182 |
vier | +0.165 |
NX | +0.163 |
Neg logit contributions | |
mond | -0.254 |
olate | -0.247 |
ccording | -0.245 |
strip | -0.240 |
sole | -0.235 |
Token | was |
Token ID | 373 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Cipher | +0.691 |
rez | +0.686 |
iewicz | +0.676 |
signatures | +0.614 |
vier | +0.611 |
Neg logit contributions | |
mond | -0.913 |
ccording | -0.881 |
olate | -0.881 |
strip | -0.861 |
sole | -0.846 |
Token | able |
Token ID | 1498 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
mond | +1.091 |
olate | +1.054 |
ccording | +1.040 |
strip | +1.025 |
sole | +1.009 |
Neg logit contributions | |
Cipher | -0.982 |
rez | -0.981 |
iewicz | -0.974 |
vier | -0.883 |
pps | -0.877 |
Token | to |
Token ID | 284 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Cipher | +0.740 |
rez | +0.732 |
iewicz | +0.731 |
signatures | +0.688 |
pps | +0.680 |
Neg logit contributions | |
mond | -0.584 |
ccording | -0.567 |
olate | -0.562 |
strip | -0.543 |
sole | -0.533 |
Token | Kickstarter |
Token ID | 14437 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Cipher | +0.057 |
rez | +0.057 |
iewicz | +0.056 |
signatures | +0.052 |
vier | +0.052 |
Neg logit contributions | |
mond | -0.057 |
olate | -0.055 |
ccording | -0.055 |
strip | -0.053 |
sole | -0.053 |
Token | - |
Token ID | 12 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Cipher | +0.621 |
rez | +0.615 |
iewicz | +0.609 |
signatures | +0.555 |
vier | +0.549 |
Neg logit contributions | |
mond | -0.794 |
olate | -0.766 |
ccording | -0.766 |
strip | -0.750 |
sole | -0.736 |
Token | funded |
Token ID | 18246 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
mond | +0.543 |
olate | +0.519 |
ccording | +0.519 |
strip | +0.512 |
sole | +0.503 |
Neg logit contributions | |
Cipher | -0.549 |
iewicz | -0.542 |
rez | -0.539 |
signatures | -0.498 |
vier | -0.491 |
Token | sandbox |
Token ID | 35204 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
Cipher | +0.075 |
rez | +0.075 |
iewicz | +0.074 |
signatures | +0.068 |
vier | +0.068 |
Neg logit contributions | |
mond | -0.082 |
olate | -0.079 |
ccording | -0.079 |
strip | -0.077 |
sole | -0.076 |
Token | game |
Token ID | 983 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Cipher | +1.737 |
rez | +1.721 |
iewicz | +1.698 |
signatures | +1.570 |
NX | +1.553 |
Neg logit contributions | |
mond | -1.885 |
ccording | -1.822 |
olate | -1.821 |
strip | -1.769 |
sole | -1.741 |
Token | Yog |
Token ID | 31604 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
Cipher | +0.574 |
rez | +0.569 |
iewicz | +0.563 |
signatures | +0.518 |
vier | +0.514 |
Neg logit contributions | |
mond | -0.635 |
olate | -0.613 |
ccording | -0.611 |
strip | -0.597 |
sole | -0.586 |
Token | ventures |
Token ID | 10065 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
rez | +3.599 |
Cipher | +3.578 |
iewicz | +3.510 |
pps | +3.229 |
vier | +3.226 |
Neg logit contributions | |
mond | -4.484 |
ccording | -4.422 |
olate | -4.362 |
strip | -4.185 |
sole | -4.155 |
Token | have |
Token ID | 423 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Cipher | +0.913 |
rez | +0.907 |
iewicz | +0.896 |
signatures | +0.820 |
vier | +0.812 |
Neg logit contributions | |
mond | -1.123 |
olate | -1.086 |
ccording | -1.082 |
strip | -1.060 |
sole | -1.041 |
Token | reacted |
Token ID | 22798 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Cipher | +0.667 |
rez | +0.660 |
iewicz | +0.654 |
signatures | +0.600 |
vier | +0.594 |
Neg logit contributions | |
mond | -0.742 |
olate | -0.717 |
ccording | -0.716 |
strip | -0.698 |
sole | -0.686 |
Token | in |
Token ID | 287 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
mond | +0.497 |
olate | +0.477 |
ccording | +0.474 |
strip | +0.463 |
sole | +0.454 |
Neg logit contributions | |
Cipher | -0.545 |
rez | -0.541 |
iewicz | -0.534 |
signatures | -0.494 |
pps | -0.491 |
Token | dismay |
Token ID | 29793 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
mond | +1.152 |
olate | +1.104 |
ccording | +1.100 |
strip | +1.073 |
sole | +1.054 |
Neg logit contributions | |
Cipher | -1.310 |
rez | -1.303 |
iewicz | -1.288 |
signatures | -1.188 |
vier | -1.183 |
Token | means |
Token ID | 1724 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
mond | +0.937 |
olate | +0.903 |
ccording | +0.891 |
strip | +0.874 |
sole | +0.865 |
Neg logit contributions | |
Cipher | -0.796 |
rez | -0.796 |
iewicz | -0.775 |
signatures | -0.714 |
vier | -0.714 |
Token | that |
Token ID | 326 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
mond | +1.992 |
olate | +1.929 |
ccording | +1.868 |
strip | +1.848 |
sole | +1.814 |
Neg logit contributions | |
rez | -2.035 |
Cipher | -2.014 |
iewicz | -1.968 |
vier | -1.826 |
signatures | -1.822 |
Token | anyone |
Token ID | 2687 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Cipher | +0.421 |
rez | +0.419 |
iewicz | +0.412 |
signatures | +0.380 |
vier | +0.377 |
Neg logit contributions | |
mond | -0.450 |
olate | -0.434 |
ccording | -0.431 |
strip | -0.421 |
sole | -0.414 |
Token | who |
Token ID | 508 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
Cipher | +1.157 |
rez | +1.143 |
iewicz | +1.128 |
signatures | +1.028 |
vier | +1.012 |
Neg logit contributions | |
mond | -1.635 |
ccording | -1.587 |
olate | -1.586 |
strip | -1.548 |
sole | -1.524 |
Token | steps |
Token ID | 4831 |
Feature activation | -8.63e-03 |
Pos logit contributions | |
Cipher | +0.183 |
rez | +0.181 |
iewicz | +0.177 |
signatures | +0.163 |
NX | +0.162 |
Neg logit contributions | |
mond | -0.223 |
olate | -0.215 |
ccording | -0.213 |
strip | -0.210 |
sole | -0.207 |
Token | into |
Token ID | 656 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
Cipher | +0.033 |
rez | +0.033 |
iewicz | +0.032 |
signatures | +0.029 |
pps | +0.029 |
Neg logit contributions | |
mond | -0.046 |
olate | -0.045 |
ccording | -0.044 |
strip | -0.043 |
sole | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
Cipher | +3.381 |
rez | +3.326 |
iewicz | +3.318 |
signatures | +3.049 |
AK | +3.035 |
Neg logit contributions | |
mond | -3.650 |
ccording | -3.575 |
olate | -3.492 |
strip | -3.433 |
sole | -3.351 |
Token | ring |
Token ID | 5858 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Cipher | +0.398 |
rez | +0.394 |
iewicz | +0.390 |
signatures | +0.363 |
NX | +0.358 |
Neg logit contributions | |
mond | -0.352 |
ccording | -0.339 |
olate | -0.339 |
strip | -0.329 |
sole | -0.322 |
Token | , |
Token ID | 11 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Cipher | +1.201 |
rez | +1.190 |
iewicz | +1.174 |
signatures | +1.081 |
NX | +1.065 |
Neg logit contributions | |
mond | -1.434 |
ccording | -1.389 |
olate | -1.388 |
strip | -1.350 |
sole | -1.328 |
Token | risking |
Token ID | 37234 |
Feature activation | -3.69e-03 |
Pos logit contributions | |
Cipher | +0.956 |
rez | +0.946 |
iewicz | +0.934 |
signatures | +0.861 |
NX | +0.848 |
Neg logit contributions | |
mond | -1.135 |
ccording | -1.101 |
olate | -1.097 |
strip | -1.069 |
sole | -1.052 |
Token | their |
Token ID | 511 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Cipher | +0.017 |
rez | +0.017 |
iewicz | +0.017 |
signatures | +0.015 |
pps | +0.015 |
Neg logit contributions | |
mond | -0.017 |
olate | -0.016 |
ccording | -0.016 |
strip | -0.016 |
sole | -0.015 |