Token | appearance |
Token ID | 5585 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
holiest | +3.686 |
emi | +3.668 |
athlet | +3.592 |
cean | +3.580 |
Lanka | +3.579 |
Neg logit contributions | |
chrom | -2.484 |
roit | -2.315 |
proof | -2.312 |
rans | -2.219 |
eor | -2.212 |
Token | with |
Token ID | 351 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
holiest | +1.373 |
emi | +1.358 |
athlet | +1.326 |
Lanka | +1.308 |
cean | +1.307 |
Neg logit contributions | |
chrom | -1.735 |
proof | -1.641 |
roit | -1.640 |
bos | -1.610 |
eor | -1.592 |
Token | Treasury |
Token ID | 13419 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
holiest | +2.654 |
emi | +2.631 |
athlet | +2.592 |
cean | +2.559 |
goodbye | +2.551 |
Neg logit contributions | |
chrom | -2.848 |
roit | -2.678 |
proof | -2.662 |
eor | -2.605 |
rans | -2.597 |
Token | Secretary |
Token ID | 4986 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
holiest | +2.140 |
emi | +2.111 |
athlet | +2.057 |
goodbye | +2.001 |
cean | +1.988 |
Neg logit contributions | |
chrom | -5.671 |
roit | -5.445 |
proof | -5.440 |
eor | -5.358 |
rans | -5.323 |
Token | Steven |
Token ID | 8239 |
Feature activation | +6.95e+00 |
Pos logit contributions | |
emi | +2.537 |
holiest | +2.498 |
athlet | +2.438 |
olicy | +2.384 |
cean | +2.382 |
Neg logit contributions | |
chrom | -4.157 |
proof | -3.989 |
roit | -3.988 |
bos | -3.927 |
eor | -3.859 |
Token | Mn |
Token ID | 36030 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
holiest | +4.011 |
emi | +3.981 |
athlet | +3.958 |
goodbye | +3.930 |
olicy | +3.870 |
Neg logit contributions | |
chrom | -6.319 |
roit | -5.991 |
proof | -5.891 |
bos | -5.828 |
rans | -5.816 |
Token | uchin |
Token ID | 43416 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
holiest | +5.013 |
emi | +4.942 |
athlet | +4.760 |
goodbye | +4.727 |
cean | +4.693 |
Neg logit contributions | |
chrom | -10.311 |
proof | -9.800 |
roit | -9.774 |
inant | -9.688 |
bos | -9.653 |
Token | , |
Token ID | 11 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
holiest | +3.867 |
emi | +3.790 |
athlet | +3.743 |
goodbye | +3.727 |
cean | +3.670 |
Neg logit contributions | |
chrom | -5.698 |
roit | -5.355 |
proof | -5.340 |
eor | -5.241 |
obyl | -5.223 |
Token | that |
Token ID | 326 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
holiest | +1.542 |
emi | +1.520 |
athlet | +1.503 |
cean | +1.465 |
goodbye | +1.461 |
Neg logit contributions | |
chrom | -2.240 |
proof | -2.106 |
roit | -2.094 |
rans | -2.048 |
eor | -2.048 |
Token | the |
Token ID | 262 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
chrom | +0.140 |
proof | +0.133 |
roit | +0.131 |
bos | +0.127 |
eor | +0.127 |
Neg logit contributions | |
emi | -0.123 |
holiest | -0.122 |
athlet | -0.120 |
olicy | -0.119 |
cean | -0.117 |
Token | debt |
Token ID | 5057 |
Feature activation | +7.11e+00 |
Pos logit contributions | |
emi | +1.575 |
olicy | +1.562 |
holiest | +1.551 |
cean | +1.539 |
athlet | +1.534 |
Neg logit contributions | |
chrom | -2.321 |
proof | -2.191 |
roit | -2.156 |
rans | -2.118 |
eor | -2.106 |
Token | . |
Token ID | 13 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
holiest | +3.079 |
emi | +2.997 |
athlet | +2.964 |
goodbye | +2.930 |
cean | +2.917 |
Neg logit contributions | |
chrom | -4.162 |
proof | -3.920 |
roit | -3.915 |
eor | -3.838 |
rans | -3.816 |
Token | Blank |
Token ID | 31990 |
Feature activation | +6.52e+00 |
Pos logit contributions | |
athlet | +1.772 |
holiest | +1.744 |
emi | +1.649 |
goodbye | +1.629 |
cean | +1.621 |
Neg logit contributions | |
chrom | -2.452 |
proof | -2.352 |
roit | -2.310 |
eor | -2.287 |
rans | -2.273 |
Token | fe |
Token ID | 5036 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
holiest | +4.803 |
athlet | +4.688 |
emi | +4.618 |
goodbye | +4.604 |
olicy | +4.577 |
Neg logit contributions | |
chrom | -4.979 |
proof | -4.629 |
roit | -4.616 |
rans | -4.555 |
obyl | -4.505 |
Token | in |
Token ID | 259 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
emi | +7.226 |
holiest | +7.151 |
goodbye | +7.015 |
bargaining | +6.943 |
athlet | +6.915 |
Neg logit contributions | |
chrom | -5.396 |
proof | -4.781 |
obyl | -4.780 |
roit | -4.757 |
rans | -4.666 |
Token | , |
Token ID | 11 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
holiest | +3.619 |
athlet | +3.492 |
emi | +3.465 |
goodbye | +3.465 |
olicy | +3.461 |
Neg logit contributions | |
chrom | -3.934 |
proof | -3.677 |
roit | -3.666 |
rans | -3.580 |
eor | -3.579 |
Token | Cohn |
Token ID | 45005 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
holiest | +2.205 |
emi | +2.171 |
cean | +2.147 |
athlet | +2.127 |
Lanka | +2.088 |
Neg logit contributions | |
chrom | -2.320 |
proof | -2.176 |
roit | -2.167 |
bos | -2.134 |
rans | -2.115 |
Token | � |
Token ID | 447 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
holiest | +5.804 |
emi | +5.802 |
goodbye | +5.685 |
athlet | +5.608 |
cean | +5.550 |
Neg logit contributions | |
chrom | -9.373 |
roit | -8.759 |
proof | -8.758 |
obyl | -8.592 |
bos | -8.591 |
Token | � |
Token ID | 247 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
holiest | +2.489 |
athlet | +2.444 |
emi | +2.439 |
cean | +2.373 |
olicy | +2.372 |
Neg logit contributions | |
chrom | -2.266 |
proof | -2.113 |
roit | -2.103 |
rans | -2.033 |
inant | -2.026 |
Token | s |
Token ID | 82 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
holiest | +3.285 |
emi | +3.218 |
athlet | +3.205 |
goodbye | +3.192 |
cean | +3.151 |
Neg logit contributions | |
chrom | -2.408 |
roit | -2.208 |
proof | -2.203 |
eor | -2.145 |
bos | -2.122 |
Token | mentor |
Token ID | 22387 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
holiest | +3.429 |
emi | +3.364 |
athlet | +3.346 |
cean | +3.283 |
olicy | +3.276 |
Neg logit contributions | |
chrom | -4.740 |
roit | -4.544 |
proof | -4.514 |
eor | -4.396 |
bos | -4.374 |
Token | and |
Token ID | 290 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
holiest | +3.506 |
emi | +3.394 |
athlet | +3.355 |
goodbye | +3.316 |
cean | +3.308 |
Neg logit contributions | |
chrom | -4.657 |
proof | -4.394 |
roit | -4.383 |
eor | -4.277 |
rans | -4.255 |
Token | designed |
Token ID | 3562 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
emi | +0.521 |
olicy | +0.507 |
Lanka | +0.505 |
cean | +0.502 |
assi | +0.489 |
Neg logit contributions | |
chrom | -0.577 |
proof | -0.537 |
roit | -0.529 |
bos | -0.522 |
rans | -0.518 |
Token | stone |
Token ID | 7815 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
emi | +0.678 |
cean | +0.673 |
holiest | +0.672 |
olicy | +0.665 |
athlet | +0.655 |
Neg logit contributions | |
chrom | -0.730 |
proof | -0.695 |
roit | -0.665 |
bos | -0.661 |
eor | -0.652 |
Token | mug |
Token ID | 25152 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
emi | +0.899 |
holiest | +0.899 |
cean | +0.882 |
olicy | +0.881 |
goodbye | +0.873 |
Neg logit contributions | |
chrom | -1.011 |
proof | -0.965 |
roit | -0.916 |
bos | -0.912 |
eor | -0.904 |
Token | costs |
Token ID | 3484 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
holiest | +2.505 |
emi | +2.461 |
cean | +2.413 |
olicy | +2.406 |
goodbye | +2.400 |
Neg logit contributions | |
chrom | -2.635 |
proof | -2.463 |
roit | -2.409 |
eor | -2.373 |
bos | -2.364 |
Token | 16 |
Token ID | 1467 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
holiest | +3.915 |
emi | +3.797 |
athlet | +3.763 |
cean | +3.739 |
olicy | +3.725 |
Neg logit contributions | |
chrom | -5.055 |
proof | -4.746 |
roit | -4.716 |
rans | -4.611 |
bos | -4.589 |
Token | euros |
Token ID | 21138 |
Feature activation | +9.53e+00 |
Pos logit contributions | |
holiest | +0.374 |
cean | +0.360 |
emi | +0.359 |
goodbye | +0.358 |
olicy | +0.356 |
Neg logit contributions | |
chrom | -0.484 |
roit | -0.457 |
proof | -0.456 |
rans | -0.451 |
bos | -0.445 |
Token | ($ |
Token ID | 7198 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
holiest | +5.650 |
emi | +5.589 |
athlet | +5.517 |
goodbye | +5.504 |
cean | +5.399 |
Neg logit contributions | |
chrom | -8.290 |
roit | -7.791 |
proof | -7.755 |
eor | -7.657 |
obyl | -7.639 |
Token | 18 |
Token ID | 1507 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
holiest | +3.952 |
emi | +3.890 |
goodbye | +3.836 |
athlet | +3.836 |
cean | +3.783 |
Neg logit contributions | |
chrom | -4.620 |
roit | -4.316 |
proof | -4.295 |
eor | -4.214 |
obyl | -4.201 |
Token | ) |
Token ID | 8 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
holiest | +1.310 |
emi | +1.262 |
athlet | +1.249 |
goodbye | +1.244 |
olicy | +1.223 |
Neg logit contributions | |
chrom | -1.633 |
proof | -1.533 |
roit | -1.532 |
rans | -1.505 |
bos | -1.488 |
Token | from |
Token ID | 422 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
holiest | +0.819 |
Lanka | +0.782 |
emi | +0.781 |
cean | +0.773 |
athlet | +0.772 |
Neg logit contributions | |
chrom | -1.038 |
proof | -0.984 |
roit | -0.970 |
rans | -0.952 |
bos | -0.939 |
Token | the |
Token ID | 262 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
holiest | +0.934 |
cean | +0.920 |
emi | +0.911 |
olicy | +0.903 |
athlet | +0.898 |
Neg logit contributions | |
chrom | -1.199 |
proof | -1.132 |
roit | -1.124 |
bos | -1.103 |
rans | -1.103 |
Token | of |
Token ID | 286 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
holiest | +1.470 |
emi | +1.434 |
athlet | +1.410 |
goodbye | +1.404 |
cean | +1.376 |
Neg logit contributions | |
chrom | -3.151 |
roit | -2.983 |
proof | -2.977 |
eor | -2.932 |
obyl | -2.923 |
Token | law |
Token ID | 1099 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
holiest | +1.683 |
emi | +1.651 |
cean | +1.622 |
olicy | +1.620 |
athlet | +1.620 |
Neg logit contributions | |
chrom | -2.414 |
proof | -2.323 |
roit | -2.309 |
rans | -2.232 |
inant | -2.208 |
Token | , |
Token ID | 11 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
chrom | +0.673 |
roit | +0.641 |
proof | +0.640 |
rans | +0.618 |
bos | +0.602 |
Neg logit contributions | |
holiest | -0.587 |
emi | -0.581 |
athlet | -0.567 |
cean | -0.567 |
olicy | -0.563 |
Token | � |
Token ID | 447 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
holiest | +1.637 |
emi | +1.600 |
athlet | +1.573 |
cean | +1.564 |
goodbye | +1.540 |
Neg logit contributions | |
chrom | -1.914 |
proof | -1.804 |
roit | -1.795 |
rans | -1.762 |
bos | -1.726 |
Token | � |
Token ID | 251 |
Feature activation | +5.10e-03 |
Pos logit contributions | |
holiest | +1.272 |
athlet | +1.269 |
emi | +1.231 |
olicy | +1.221 |
cean | +1.208 |
Neg logit contributions | |
chrom | -1.813 |
roit | -1.734 |
proof | -1.724 |
eor | -1.687 |
rans | -1.684 |
Token | Fe |
Token ID | 5452 |
Feature activation | +9.47e+00 |
Pos logit contributions | |
holiest | +0.003 |
athlet | +0.003 |
emi | +0.003 |
goodbye | +0.003 |
cean | +0.003 |
Neg logit contributions | |
chrom | -0.004 |
proof | -0.004 |
roit | -0.004 |
rans | -0.004 |
eor | -0.004 |
Token | ing |
Token ID | 278 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
emi | +7.829 |
holiest | +7.776 |
cean | +7.624 |
athlet | +7.560 |
goodbye | +7.558 |
Neg logit contributions | |
chrom | -5.936 |
roit | -5.459 |
proof | -5.430 |
obyl | -5.303 |
eor | -5.303 |
Token | old |
Token ID | 727 |
Feature activation | +6.93e-03 |
Pos logit contributions | |
holiest | +2.618 |
athlet | +2.563 |
cean | +2.524 |
goodbye | +2.516 |
bargaining | +2.514 |
Neg logit contributions | |
chrom | -1.798 |
roit | -1.712 |
proof | -1.658 |
rans | -1.652 |
bos | -1.622 |
Token | said |
Token ID | 531 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
holiest | +0.005 |
athlet | +0.005 |
olicy | +0.005 |
cean | +0.005 |
goodbye | +0.005 |
Neg logit contributions | |
chrom | -0.005 |
roit | -0.005 |
proof | -0.005 |
rans | -0.004 |
eor | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
holiest | +1.116 |
emi | +1.080 |
athlet | +1.076 |
cean | +1.061 |
olicy | +1.049 |
Neg logit contributions | |
chrom | -1.436 |
roit | -1.353 |
proof | -1.340 |
bos | -1.315 |
rans | -1.310 |
Token | a |
Token ID | 257 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
holiest | +2.642 |
emi | +2.588 |
athlet | +2.561 |
goodbye | +2.518 |
cean | +2.503 |
Neg logit contributions | |
chrom | -4.028 |
proof | -3.809 |
roit | -3.804 |
rans | -3.705 |
bos | -3.703 |
Token | . |
Token ID | 13 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
holiest | +0.369 |
Lanka | +0.353 |
olicy | +0.351 |
emi | +0.350 |
cean | +0.348 |
Neg logit contributions | |
chrom | -0.455 |
proof | -0.433 |
roit | -0.427 |
eor | -0.418 |
rans | -0.416 |
Token | � |
Token ID | 447 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
holiest | +2.069 |
athlet | +2.027 |
emi | +1.944 |
goodbye | +1.930 |
cean | +1.915 |
Neg logit contributions | |
chrom | -2.796 |
proof | -2.641 |
roit | -2.599 |
eor | -2.574 |
bos | -2.542 |
Token | � |
Token ID | 251 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
holiest | +2.190 |
emi | +2.159 |
athlet | +2.151 |
cean | +2.102 |
goodbye | +2.100 |
Neg logit contributions | |
chrom | -2.486 |
roit | -2.324 |
proof | -2.320 |
eor | -2.269 |
rans | -2.257 |
Token |
|
Token ID | 198 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
holiest | +0.560 |
athlet | +0.557 |
emi | +0.533 |
olicy | +0.531 |
goodbye | +0.530 |
Neg logit contributions | |
chrom | -0.715 |
proof | -0.674 |
roit | -0.668 |
eor | -0.654 |
bos | -0.648 |
Token |
|
Token ID | 198 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
holiest | +1.954 |
athlet | +1.937 |
emi | +1.876 |
olicy | +1.854 |
goodbye | +1.839 |
Neg logit contributions | |
chrom | -2.490 |
proof | -2.336 |
roit | -2.295 |
eor | -2.257 |
bos | -2.247 |
Token | Fe |
Token ID | 14304 |
Feature activation | +9.36e+00 |
Pos logit contributions | |
holiest | +2.067 |
athlet | +2.066 |
goodbye | +1.992 |
emi | +1.970 |
Lanka | +1.970 |
Neg logit contributions | |
chrom | -2.336 |
proof | -2.176 |
roit | -2.129 |
bos | -2.103 |
eor | -2.090 |
Token | eling |
Token ID | 10809 |
Feature activation | +6.90e+00 |
Pos logit contributions | |
holiest | +7.717 |
emi | +7.695 |
athlet | +7.521 |
goodbye | +7.517 |
cean | +7.511 |
Neg logit contributions | |
chrom | -5.952 |
proof | -5.451 |
roit | -5.443 |
eor | -5.300 |
obyl | -5.288 |
Token | Hel |
Token ID | 5053 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
holiest | +4.188 |
emi | +4.115 |
athlet | +4.043 |
cean | +4.031 |
goodbye | +4.010 |
Neg logit contributions | |
chrom | -6.118 |
proof | -5.767 |
roit | -5.746 |
rans | -5.578 |
bos | -5.572 |
Token | pless |
Token ID | 14570 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
holiest | +2.977 |
emi | +2.909 |
athlet | +2.908 |
goodbye | +2.899 |
bargaining | +2.858 |
Neg logit contributions | |
chrom | -2.522 |
proof | -2.333 |
roit | -2.333 |
bos | -2.260 |
obyl | -2.256 |
Token |
|
Token ID | 198 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
holiest | +2.491 |
emi | +2.400 |
athlet | +2.387 |
olicy | +2.372 |
goodbye | +2.372 |
Neg logit contributions | |
chrom | -3.108 |
proof | -2.965 |
roit | -2.934 |
obyl | -2.874 |
bos | -2.868 |
Token |
|
Token ID | 198 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
holiest | +1.762 |
athlet | +1.753 |
emi | +1.685 |
olicy | +1.684 |
bargaining | +1.653 |
Neg logit contributions | |
chrom | -2.125 |
proof | -2.002 |
roit | -1.949 |
eor | -1.917 |
bos | -1.914 |
Token | the |
Token ID | 262 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
holiest | +3.013 |
emi | +2.951 |
athlet | +2.919 |
goodbye | +2.915 |
cean | +2.857 |
Neg logit contributions | |
chrom | -4.056 |
roit | -3.802 |
proof | -3.796 |
eor | -3.704 |
rans | -3.694 |
Token | tens |
Token ID | 11192 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
emi | +1.924 |
olicy | +1.899 |
holiest | +1.899 |
cean | +1.868 |
goodbye | +1.866 |
Neg logit contributions | |
chrom | -2.612 |
proof | -2.450 |
roit | -2.444 |
rans | -2.394 |
eor | -2.377 |
Token | of |
Token ID | 286 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
holiest | +2.295 |
athlet | +2.198 |
emi | +2.193 |
goodbye | +2.137 |
cean | +2.114 |
Neg logit contributions | |
chrom | -3.896 |
proof | -3.681 |
roit | -3.639 |
rans | -3.618 |
eor | -3.578 |
Token | millions |
Token ID | 5242 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
holiest | +1.950 |
emi | +1.935 |
cean | +1.878 |
athlet | +1.874 |
goodbye | +1.863 |
Neg logit contributions | |
chrom | -3.101 |
proof | -2.948 |
rans | -2.909 |
roit | -2.907 |
bos | -2.883 |
Token | of |
Token ID | 286 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
holiest | +3.277 |
emi | +3.204 |
athlet | +3.156 |
goodbye | +3.144 |
cean | +3.089 |
Neg logit contributions | |
chrom | -5.878 |
roit | -5.549 |
proof | -5.535 |
eor | -5.437 |
obyl | -5.418 |
Token | dollars |
Token ID | 5054 |
Feature activation | +9.33e+00 |
Pos logit contributions | |
holiest | +1.550 |
emi | +1.492 |
cean | +1.439 |
goodbye | +1.419 |
athlet | +1.406 |
Neg logit contributions | |
chrom | -3.595 |
proof | -3.442 |
roit | -3.436 |
rans | -3.412 |
bos | -3.357 |
Token | . |
Token ID | 13 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
holiest | +5.375 |
emi | +5.274 |
athlet | +5.228 |
goodbye | +5.191 |
cean | +5.087 |
Neg logit contributions | |
chrom | -8.334 |
roit | -7.843 |
proof | -7.823 |
obyl | -7.714 |
eor | -7.712 |
Token |
|
Token ID | 198 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
holiest | +2.037 |
athlet | +2.017 |
emi | +1.941 |
goodbye | +1.934 |
cean | +1.907 |
Neg logit contributions | |
chrom | -2.456 |
proof | -2.334 |
roit | -2.304 |
eor | -2.260 |
bos | -2.242 |
Token |
|
Token ID | 198 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
holiest | +1.947 |
athlet | +1.935 |
emi | +1.872 |
olicy | +1.858 |
bargaining | +1.828 |
Neg logit contributions | |
chrom | -2.372 |
proof | -2.235 |
roit | -2.183 |
eor | -2.149 |
bos | -2.144 |
Token | Story |
Token ID | 11605 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
holiest | +1.914 |
athlet | +1.891 |
goodbye | +1.844 |
emi | +1.823 |
Lanka | +1.815 |
Neg logit contributions | |
chrom | -2.370 |
proof | -2.235 |
roit | -2.196 |
bos | -2.162 |
eor | -2.156 |
Token | continues |
Token ID | 4477 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
holiest | +2.466 |
emi | +2.367 |
athlet | +2.348 |
goodbye | +2.320 |
olicy | +2.269 |
Neg logit contributions | |
chrom | -3.750 |
proof | -3.537 |
roit | -3.523 |
eor | -3.464 |
rans | -3.458 |
Token | attention |
Token ID | 3241 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
emi | +2.135 |
holiest | +2.130 |
olicy | +2.123 |
cean | +2.094 |
athlet | +2.079 |
Neg logit contributions | |
chrom | -2.381 |
proof | -2.246 |
roit | -2.208 |
bos | -2.180 |
rans | -2.161 |
Token | , |
Token ID | 11 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
holiest | +2.768 |
emi | +2.716 |
olicy | +2.662 |
athlet | +2.656 |
goodbye | +2.636 |
Neg logit contributions | |
chrom | -3.776 |
roit | -3.546 |
proof | -3.532 |
rans | -3.475 |
eor | -3.452 |
Token | and |
Token ID | 290 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
emi | +2.051 |
holiest | +2.046 |
cean | +1.989 |
goodbye | +1.979 |
olicy | +1.979 |
Neg logit contributions | |
chrom | -2.381 |
proof | -2.254 |
roit | -2.220 |
rans | -2.207 |
bos | -2.194 |
Token | millions |
Token ID | 5242 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
holiest | +2.583 |
emi | +2.583 |
cean | +2.478 |
athlet | +2.474 |
olicy | +2.462 |
Neg logit contributions | |
chrom | -3.112 |
proof | -2.953 |
roit | -2.934 |
rans | -2.880 |
bos | -2.877 |
Token | of |
Token ID | 286 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
holiest | +3.579 |
emi | +3.486 |
athlet | +3.431 |
cean | +3.395 |
goodbye | +3.392 |
Neg logit contributions | |
chrom | -5.295 |
roit | -4.998 |
proof | -4.997 |
rans | -4.885 |
bos | -4.867 |
Token | dollars |
Token ID | 5054 |
Feature activation | +9.16e+00 |
Pos logit contributions | |
holiest | +2.416 |
emi | +2.384 |
cean | +2.342 |
olicy | +2.296 |
athlet | +2.283 |
Neg logit contributions | |
chrom | -3.041 |
proof | -2.863 |
roit | -2.863 |
rans | -2.800 |
bos | -2.793 |
Token | of |
Token ID | 286 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
holiest | +5.543 |
emi | +5.447 |
athlet | +5.382 |
goodbye | +5.365 |
cean | +5.273 |
Neg logit contributions | |
chrom | -7.950 |
roit | -7.462 |
proof | -7.442 |
eor | -7.309 |
obyl | -7.279 |
Token | outside |
Token ID | 2354 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
holiest | +2.629 |
emi | +2.625 |
cean | +2.568 |
olicy | +2.546 |
athlet | +2.507 |
Neg logit contributions | |
chrom | -3.079 |
proof | -2.894 |
roit | -2.871 |
bos | -2.834 |
rans | -2.811 |
Token | spending |
Token ID | 4581 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
holiest | +1.765 |
emi | +1.752 |
olicy | +1.695 |
cean | +1.685 |
goodbye | +1.680 |
Neg logit contributions | |
chrom | -2.547 |
proof | -2.413 |
roit | -2.405 |
bos | -2.356 |
rans | -2.349 |
Token | , |
Token ID | 11 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
holiest | +3.529 |
emi | +3.442 |
olicy | +3.394 |
cean | +3.383 |
athlet | +3.376 |
Neg logit contributions | |
chrom | -4.782 |
proof | -4.517 |
roit | -4.510 |
bos | -4.409 |
eor | -4.405 |
Token | to |
Token ID | 284 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
holiest | +2.369 |
emi | +2.346 |
cean | +2.322 |
olicy | +2.297 |
athlet | +2.278 |
Neg logit contributions | |
chrom | -2.580 |
proof | -2.440 |
roit | -2.405 |
rans | -2.386 |
bos | -2.369 |
Token | hat |
Token ID | 6877 |
Feature activation | +6.81e+00 |
Pos logit contributions | |
holiest | +3.167 |
emi | +3.131 |
olicy | +3.084 |
cean | +3.078 |
athlet | +3.040 |
Neg logit contributions | |
chrom | -4.180 |
roit | -3.955 |
proof | -3.951 |
bos | -3.833 |
eor | -3.817 |
Token | - |
Token ID | 12 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
holiest | +4.083 |
emi | +3.959 |
athlet | +3.934 |
goodbye | +3.910 |
Lanka | +3.864 |
Neg logit contributions | |
chrom | -6.028 |
roit | -5.691 |
proof | -5.685 |
eor | -5.564 |
rans | -5.529 |
Token | tr |
Token ID | 2213 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
chrom | +0.343 |
proof | +0.313 |
roit | +0.299 |
bos | +0.289 |
rans | +0.286 |
Neg logit contributions | |
holiest | -0.794 |
Lanka | -0.783 |
cean | -0.771 |
emi | -0.771 |
athlet | -0.768 |
Token | ick |
Token ID | 624 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
holiest | +1.032 |
athlet | +0.999 |
goodbye | +0.985 |
emi | +0.975 |
Lanka | +0.968 |
Neg logit contributions | |
chrom | -1.210 |
roit | -1.136 |
proof | -1.128 |
rans | -1.121 |
eor | -1.108 |
Token | and |
Token ID | 290 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
holiest | +3.411 |
emi | +3.333 |
athlet | +3.280 |
cean | +3.256 |
goodbye | +3.227 |
Neg logit contributions | |
chrom | -4.922 |
proof | -4.677 |
roit | -4.670 |
eor | -4.526 |
bos | -4.525 |
Token | Fra |
Token ID | 39313 |
Feature activation | +9.10e+00 |
Pos logit contributions | |
holiest | +2.119 |
emi | +2.050 |
cean | +2.023 |
olicy | +2.014 |
athlet | +1.987 |
Neg logit contributions | |
chrom | -3.013 |
proof | -2.892 |
roit | -2.876 |
bos | -2.787 |
eor | -2.778 |
Token | izer |
Token ID | 7509 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
emi | +8.493 |
holiest | +8.373 |
athlet | +8.265 |
Lanka | +8.242 |
cean | +8.229 |
Neg logit contributions | |
chrom | -4.791 |
roit | -4.274 |
proof | -4.224 |
obyl | -4.181 |
inant | -4.135 |
Token | Campbell |
Token ID | 14327 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
holiest | +2.467 |
emi | +2.375 |
athlet | +2.362 |
olicy | +2.346 |
cean | +2.334 |
Neg logit contributions | |
chrom | -2.837 |
proof | -2.699 |
roit | -2.668 |
bos | -2.639 |
rans | -2.590 |
Token | 's |
Token ID | 338 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
holiest | +0.696 |
emi | +0.668 |
athlet | +0.667 |
goodbye | +0.663 |
cean | +0.661 |
Neg logit contributions | |
chrom | -0.703 |
proof | -0.659 |
roit | -0.658 |
bos | -0.639 |
eor | -0.638 |
Token | opener |
Token ID | 21996 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
holiest | +2.839 |
emi | +2.792 |
olicy | +2.750 |
cean | +2.750 |
athlet | +2.728 |
Neg logit contributions | |
chrom | -3.719 |
roit | -3.523 |
proof | -3.519 |
bos | -3.411 |
eor | -3.402 |
Token | , |
Token ID | 11 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
holiest | +2.149 |
emi | +2.108 |
cean | +2.061 |
olicy | +2.060 |
athlet | +2.059 |
Neg logit contributions | |
chrom | -2.854 |
proof | -2.740 |
roit | -2.720 |
bos | -2.644 |
rans | -2.627 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
holiest | +1.759 |
athlet | +1.724 |
goodbye | +1.702 |
emi | +1.699 |
bargaining | +1.694 |
Neg logit contributions | |
chrom | -1.999 |
roit | -1.868 |
proof | -1.851 |
bos | -1.848 |
rans | -1.821 |
Token | S |
Token ID | 50 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
holiest | +1.241 |
emi | +1.220 |
athlet | +1.208 |
goodbye | +1.205 |
cean | +1.196 |
Neg logit contributions | |
chrom | -1.213 |
roit | -1.128 |
proof | -1.121 |
eor | -1.098 |
obyl | -1.096 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
holiest | +2.846 |
emi | +2.800 |
athlet | +2.766 |
goodbye | +2.755 |
bargaining | +2.717 |
Neg logit contributions | |
chrom | -5.382 |
proof | -5.092 |
roit | -5.048 |
obyl | -5.024 |
bos | -4.963 |
Token | economist |
Token ID | 17646 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
holiest | +0.834 |
emi | +0.823 |
athlet | +0.804 |
goodbye | +0.790 |
cean | +0.786 |
Neg logit contributions | |
chrom | -1.256 |
proof | -1.201 |
roit | -1.196 |
eor | -1.175 |
bos | -1.169 |
Token | Paul |
Token ID | 3362 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
holiest | +3.262 |
emi | +3.211 |
athlet | +3.118 |
cean | +3.106 |
goodbye | +3.094 |
Neg logit contributions | |
chrom | -4.869 |
roit | -4.629 |
proof | -4.624 |
eor | -4.525 |
bos | -4.508 |
Token | Krugman |
Token ID | 46311 |
Feature activation | +9.02e+00 |
Pos logit contributions | |
holiest | +1.301 |
athlet | +1.274 |
goodbye | +1.264 |
emi | +1.259 |
cean | +1.228 |
Neg logit contributions | |
chrom | -2.137 |
roit | -2.040 |
proof | -2.018 |
bos | -1.988 |
eor | -1.985 |
Token | dubbed |
Token ID | 17494 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
holiest | +6.582 |
emi | +6.482 |
athlet | +6.417 |
goodbye | +6.400 |
cean | +6.311 |
Neg logit contributions | |
chrom | -6.720 |
roit | -6.228 |
proof | -6.211 |
eor | -6.076 |
obyl | -6.059 |
Token | the |
Token ID | 262 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
holiest | +0.046 |
emi | +0.046 |
athlet | +0.045 |
cean | +0.045 |
olicy | +0.044 |
Neg logit contributions | |
chrom | -0.055 |
proof | -0.052 |
roit | -0.052 |
bos | -0.051 |
rans | -0.050 |
Token | revision |
Token ID | 18440 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
emi | +1.037 |
holiest | +1.027 |
cean | +1.017 |
olicy | +1.004 |
athlet | +1.002 |
Neg logit contributions | |
chrom | -1.096 |
proof | -1.033 |
roit | -1.027 |
rans | -0.999 |
bos | -0.997 |
Token | from |
Token ID | 422 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
holiest | +2.102 |
emi | +2.074 |
athlet | +2.024 |
goodbye | +2.001 |
cean | +1.992 |
Neg logit contributions | |
chrom | -2.632 |
proof | -2.488 |
roit | -2.448 |
bos | -2.401 |
rans | -2.397 |
Token | an |
Token ID | 281 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
holiest | +0.838 |
emi | +0.837 |
athlet | +0.811 |
cean | +0.810 |
assi | +0.788 |
Neg logit contributions | |
chrom | -1.113 |
proof | -1.061 |
roit | -1.052 |
bos | -1.040 |
rans | -1.036 |
Token | there |
Token ID | 612 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
emi | +2.012 |
holiest | +1.992 |
athlet | +1.924 |
olicy | +1.920 |
cean | +1.919 |
Neg logit contributions | |
chrom | -2.506 |
proof | -2.366 |
roit | -2.349 |
rans | -2.308 |
bos | -2.296 |
Token | have |
Token ID | 423 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
holiest | +1.482 |
emi | +1.457 |
athlet | +1.427 |
olicy | +1.424 |
goodbye | +1.421 |
Neg logit contributions | |
chrom | -1.436 |
proof | -1.339 |
roit | -1.326 |
rans | -1.308 |
eor | -1.301 |
Token | been |
Token ID | 587 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
holiest | +1.418 |
emi | +1.392 |
olicy | +1.379 |
athlet | +1.367 |
cean | +1.361 |
Neg logit contributions | |
chrom | -1.611 |
proof | -1.525 |
roit | -1.520 |
rans | -1.505 |
bos | -1.491 |
Token | reports |
Token ID | 3136 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
emi | +0.260 |
holiest | +0.259 |
olicy | +0.256 |
cean | +0.255 |
athlet | +0.253 |
Neg logit contributions | |
chrom | -0.207 |
proof | -0.196 |
roit | -0.190 |
rans | -0.187 |
eor | -0.184 |
Token | that |
Token ID | 326 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
holiest | +2.278 |
emi | +2.243 |
olicy | +2.180 |
athlet | +2.179 |
cean | +2.163 |
Neg logit contributions | |
chrom | -3.404 |
proof | -3.211 |
roit | -3.210 |
rans | -3.143 |
eor | -3.106 |
Token | Bannon |
Token ID | 19688 |
Feature activation | +8.98e+00 |
Pos logit contributions | |
chrom | +0.214 |
proof | +0.203 |
roit | +0.200 |
rans | +0.199 |
bos | +0.195 |
Neg logit contributions | |
emi | -0.178 |
holiest | -0.176 |
olicy | -0.171 |
athlet | -0.170 |
cean | -0.168 |
Token | might |
Token ID | 1244 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
holiest | +5.916 |
emi | +5.810 |
athlet | +5.740 |
goodbye | +5.717 |
cean | +5.643 |
Neg logit contributions | |
chrom | -7.379 |
roit | -6.901 |
proof | -6.884 |
eor | -6.740 |
obyl | -6.714 |
Token | be |
Token ID | 307 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
holiest | +2.237 |
emi | +2.179 |
olicy | +2.156 |
Lanka | +2.148 |
athlet | +2.142 |
Neg logit contributions | |
chrom | -1.906 |
roit | -1.775 |
proof | -1.765 |
rans | -1.741 |
eor | -1.724 |
Token | edged |
Token ID | 45871 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
holiest | +0.641 |
emi | +0.640 |
olicy | +0.630 |
cean | +0.627 |
Lanka | +0.619 |
Neg logit contributions | |
chrom | -0.734 |
roit | -0.692 |
proof | -0.690 |
rans | -0.675 |
bos | -0.659 |
Token | out |
Token ID | 503 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
holiest | +3.194 |
emi | +3.158 |
cean | +3.070 |
olicy | +3.039 |
athlet | +3.038 |
Neg logit contributions | |
chrom | -4.826 |
proof | -4.556 |
roit | -4.522 |
rans | -4.443 |
bos | -4.414 |
Token | , |
Token ID | 11 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
holiest | +1.497 |
emi | +1.469 |
olicy | +1.441 |
cean | +1.404 |
Lanka | +1.391 |
Neg logit contributions | |
chrom | -2.185 |
proof | -2.045 |
roit | -2.035 |
rans | -2.015 |
bos | -2.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
holiest | +1.536 |
olicy | +1.510 |
emi | +1.504 |
athlet | +1.475 |
cean | +1.469 |
Neg logit contributions | |
chrom | -1.864 |
roit | -1.744 |
proof | -1.739 |
rans | -1.727 |
eor | -1.718 |
Token |
|
Token ID | 198 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
athlet | +2.156 |
holiest | +2.149 |
emi | +2.078 |
goodbye | +2.074 |
olicy | +2.052 |
Neg logit contributions | |
chrom | -2.875 |
proof | -2.722 |
roit | -2.695 |
eor | -2.653 |
rans | -2.639 |
Token |
|
Token ID | 198 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
holiest | +2.155 |
athlet | +2.147 |
emi | +2.067 |
olicy | +2.051 |
goodbye | +2.027 |
Neg logit contributions | |
chrom | -2.712 |
proof | -2.553 |
roit | -2.500 |
eor | -2.462 |
rans | -2.450 |
Token | President |
Token ID | 10364 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
athlet | +2.204 |
holiest | +2.193 |
goodbye | +2.132 |
emi | +2.111 |
bargaining | +2.108 |
Neg logit contributions | |
chrom | -2.457 |
proof | -2.317 |
roit | -2.266 |
eor | -2.228 |
rans | -2.223 |
Token | Hassan |
Token ID | 24485 |
Feature activation | +8.26e+00 |
Pos logit contributions | |
holiest | +2.985 |
athlet | +2.908 |
goodbye | +2.881 |
emi | +2.869 |
bargaining | +2.829 |
Neg logit contributions | |
chrom | -3.712 |
roit | -3.492 |
proof | -3.481 |
bos | -3.406 |
eor | -3.397 |
Token | Rouhani |
Token ID | 34915 |
Feature activation | +8.97e+00 |
Pos logit contributions | |
holiest | +3.499 |
emi | +3.410 |
athlet | +3.340 |
goodbye | +3.321 |
cean | +3.251 |
Neg logit contributions | |
chrom | -8.700 |
roit | -8.253 |
proof | -8.233 |
eor | -8.109 |
obyl | -8.093 |
Token | has |
Token ID | 468 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
holiest | +6.232 |
emi | +6.128 |
athlet | +6.061 |
goodbye | +6.042 |
cean | +5.960 |
Neg logit contributions | |
chrom | -7.032 |
roit | -6.555 |
proof | -6.534 |
eor | -6.397 |
obyl | -6.373 |
Token | shown |
Token ID | 3402 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
holiest | +2.857 |
emi | +2.806 |
olicy | +2.792 |
goodbye | +2.751 |
cean | +2.747 |
Neg logit contributions | |
chrom | -2.747 |
proof | -2.573 |
roit | -2.552 |
rans | -2.489 |
eor | -2.452 |
Token | he |
Token ID | 339 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
emi | +0.543 |
holiest | +0.543 |
olicy | +0.541 |
cean | +0.531 |
assi | +0.529 |
Neg logit contributions | |
chrom | -0.865 |
proof | -0.832 |
roit | -0.814 |
rans | -0.799 |
eor | -0.778 |
Token | is |
Token ID | 318 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
holiest | +1.429 |
olicy | +1.385 |
emi | +1.384 |
Lanka | +1.373 |
goodbye | +1.370 |
Neg logit contributions | |
chrom | -1.462 |
proof | -1.375 |
roit | -1.352 |
rans | -1.348 |
eor | -1.327 |
Token | listening |
Token ID | 8680 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
holiest | +2.474 |
emi | +2.455 |
assi | +2.412 |
olicy | +2.406 |
cean | +2.394 |
Neg logit contributions | |
chrom | -3.298 |
proof | -3.172 |
roit | -3.145 |
rans | -3.067 |
bos | -3.001 |
Token | of |
Token ID | 286 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
chrom | +1.181 |
proof | +1.113 |
roit | +1.094 |
inant | +1.081 |
rans | +1.078 |
Neg logit contributions | |
holiest | -0.806 |
emi | -0.790 |
cean | -0.779 |
olicy | -0.775 |
athlet | -0.763 |
Token | the |
Token ID | 262 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
holiest | +0.460 |
athlet | +0.453 |
emi | +0.448 |
olicy | +0.442 |
goodbye | +0.436 |
Neg logit contributions | |
chrom | -0.630 |
proof | -0.592 |
roit | -0.586 |
rans | -0.579 |
eor | -0.579 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
holiest | +0.402 |
athlet | +0.398 |
olicy | +0.396 |
emi | +0.396 |
goodbye | +0.387 |
Neg logit contributions | |
chrom | -0.504 |
proof | -0.468 |
roit | -0.465 |
rans | -0.460 |
bos | -0.456 |
Token | film |
Token ID | 2646 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
chrom | +0.074 |
proof | +0.070 |
roit | +0.069 |
rans | +0.067 |
bos | +0.067 |
Neg logit contributions | |
holiest | -0.079 |
emi | -0.078 |
olicy | -0.077 |
athlet | -0.077 |
cean | -0.076 |
Token | Kung |
Token ID | 44753 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
chrom | +0.625 |
proof | +0.594 |
roit | +0.577 |
eor | +0.569 |
rans | +0.567 |
Neg logit contributions | |
holiest | -0.438 |
athlet | -0.431 |
olicy | -0.423 |
emi | -0.421 |
goodbye | -0.417 |
Token | Fu |
Token ID | 13333 |
Feature activation | +8.91e+00 |
Pos logit contributions | |
holiest | +3.416 |
athlet | +3.306 |
emi | +3.300 |
goodbye | +3.271 |
cean | +3.247 |
Neg logit contributions | |
chrom | -4.790 |
roit | -4.518 |
proof | -4.515 |
obyl | -4.398 |
eor | -4.395 |
Token | Panda |
Token ID | 41112 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
holiest | +3.050 |
emi | +2.948 |
athlet | +2.882 |
goodbye | +2.858 |
cean | +2.780 |
Neg logit contributions | |
chrom | -10.109 |
roit | -9.635 |
proof | -9.611 |
eor | -9.479 |
obyl | -9.457 |
Token | , |
Token ID | 11 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
holiest | +2.408 |
athlet | +2.332 |
emi | +2.314 |
goodbye | +2.311 |
cean | +2.295 |
Neg logit contributions | |
chrom | -3.074 |
proof | -2.917 |
roit | -2.885 |
bos | -2.817 |
rans | -2.814 |
Token | is |
Token ID | 318 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
holiest | +0.413 |
olicy | +0.407 |
emi | +0.405 |
cean | +0.395 |
goodbye | +0.390 |
Neg logit contributions | |
chrom | -0.426 |
proof | -0.399 |
rans | -0.387 |
bos | -0.386 |
roit | -0.386 |
Token | an |
Token ID | 281 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
holiest | +1.352 |
olicy | +1.325 |
emi | +1.325 |
goodbye | +1.296 |
cean | +1.291 |
Neg logit contributions | |
chrom | -1.615 |
proof | -1.521 |
rans | -1.484 |
roit | -1.474 |
obyl | -1.441 |
Token | anthrop |
Token ID | 17911 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
holiest | +1.300 |
emi | +1.276 |
olicy | +1.275 |
goodbye | +1.263 |
cean | +1.242 |
Neg logit contributions | |
chrom | -1.605 |
proof | -1.514 |
roit | -1.509 |
rans | -1.492 |
eor | -1.468 |
Token | graft |
Token ID | 38455 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
emi | +0.454 |
holiest | +0.445 |
cean | +0.435 |
olicy | +0.435 |
athlet | +0.433 |
Neg logit contributions | |
chrom | -0.523 |
proof | -0.492 |
roit | -0.488 |
bos | -0.479 |
rans | -0.477 |
Token | last |
Token ID | 938 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
holiest | +0.911 |
emi | +0.902 |
athlet | +0.891 |
cean | +0.888 |
goodbye | +0.880 |
Neg logit contributions | |
chrom | -1.103 |
proof | -1.047 |
roit | -1.026 |
rans | -1.002 |
eor | -0.996 |
Token | year |
Token ID | 614 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
chrom | +0.129 |
proof | +0.122 |
roit | +0.122 |
rans | +0.119 |
bos | +0.118 |
Neg logit contributions | |
olicy | -0.100 |
cean | -0.100 |
emi | -0.099 |
athlet | -0.099 |
holiest | -0.099 |
Token | as |
Token ID | 355 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
holiest | +1.480 |
emi | +1.433 |
athlet | +1.422 |
olicy | +1.408 |
cean | +1.408 |
Neg logit contributions | |
chrom | -1.747 |
proof | -1.629 |
roit | -1.611 |
rans | -1.604 |
bos | -1.599 |
Token | President |
Token ID | 1992 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
emi | +0.727 |
holiest | +0.724 |
cean | +0.716 |
athlet | +0.708 |
olicy | +0.693 |
Neg logit contributions | |
chrom | -0.862 |
proof | -0.825 |
roit | -0.812 |
bos | -0.804 |
rans | -0.795 |
Token | Xi |
Token ID | 21313 |
Feature activation | +8.85e+00 |
Pos logit contributions | |
holiest | +0.859 |
athlet | +0.824 |
emi | +0.788 |
goodbye | +0.779 |
cean | +0.779 |
Neg logit contributions | |
chrom | -2.226 |
proof | -2.153 |
bos | -2.140 |
roit | -2.139 |
eor | -2.113 |
Token | Jinping |
Token ID | 39823 |
Feature activation | +7.47e+00 |
Pos logit contributions | |
holiest | +2.926 |
emi | +2.800 |
athlet | +2.724 |
goodbye | +2.695 |
cean | +2.649 |
Neg logit contributions | |
chrom | -10.247 |
roit | -9.771 |
proof | -9.763 |
eor | -9.606 |
obyl | -9.590 |
Token | continued |
Token ID | 3767 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
holiest | +5.429 |
emi | +5.344 |
athlet | +5.239 |
goodbye | +5.231 |
cean | +5.204 |
Neg logit contributions | |
chrom | -5.699 |
proof | -5.297 |
roit | -5.297 |
eor | -5.161 |
bos | -5.143 |
Token | to |
Token ID | 284 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
emi | +0.633 |
holiest | +0.628 |
assi | +0.610 |
athlet | +0.605 |
cean | +0.605 |
Neg logit contributions | |
chrom | -0.831 |
proof | -0.799 |
roit | -0.785 |
eor | -0.767 |
bos | -0.761 |
Token | wage |
Token ID | 7699 |
Feature activation | +6.12e+00 |
Pos logit contributions | |
chrom | +0.579 |
proof | +0.546 |
roit | +0.540 |
eor | +0.529 |
rans | +0.508 |
Neg logit contributions | |
emi | -0.672 |
holiest | -0.669 |
assi | -0.648 |
olicy | -0.646 |
cean | -0.645 |
Token | a |
Token ID | 257 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
holiest | +3.713 |
emi | +3.685 |
cean | +3.576 |
athlet | +3.563 |
goodbye | +3.539 |
Neg logit contributions | |
chrom | -5.449 |
proof | -5.168 |
roit | -5.108 |
eor | -4.983 |
bos | -4.976 |
Token | White |
Token ID | 2635 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
emi | +0.012 |
holiest | +0.012 |
athlet | +0.012 |
cean | +0.012 |
externalActionCode | +0.012 |
Neg logit contributions | |
chrom | -0.016 |
proof | -0.015 |
roit | -0.015 |
rans | -0.015 |
bos | -0.015 |
Token | House |
Token ID | 2097 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
holiest | +1.059 |
emi | +1.008 |
athlet | +1.005 |
bargaining | +1.003 |
olicy | +0.996 |
Neg logit contributions | |
chrom | -1.051 |
proof | -1.006 |
roit | -0.976 |
eor | -0.976 |
rans | -0.975 |
Token | chief |
Token ID | 4039 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
holiest | +3.003 |
emi | +2.979 |
athlet | +2.898 |
cean | +2.860 |
goodbye | +2.855 |
Neg logit contributions | |
chrom | -3.773 |
roit | -3.555 |
proof | -3.534 |
eor | -3.457 |
rans | -3.454 |
Token | strategist |
Token ID | 25651 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
holiest | +2.052 |
emi | +2.042 |
athlet | +1.927 |
goodbye | +1.921 |
cean | +1.912 |
Neg logit contributions | |
chrom | -4.293 |
roit | -4.131 |
proof | -4.125 |
bos | -4.018 |
rans | -4.017 |
Token | Stephen |
Token ID | 7970 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
holiest | +2.498 |
emi | +2.432 |
athlet | +2.374 |
goodbye | +2.331 |
cean | +2.322 |
Neg logit contributions | |
chrom | -5.848 |
proof | -5.550 |
roit | -5.550 |
eor | -5.448 |
rans | -5.430 |
Token | Bannon |
Token ID | 19688 |
Feature activation | +8.84e+00 |
Pos logit contributions | |
athlet | +3.745 |
holiest | +3.716 |
emi | +3.682 |
goodbye | +3.570 |
bargaining | +3.564 |
Neg logit contributions | |
chrom | -5.021 |
roit | -4.684 |
proof | -4.683 |
rans | -4.570 |
eor | -4.549 |
Token | during |
Token ID | 1141 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
holiest | +5.605 |
emi | +5.488 |
athlet | +5.424 |
goodbye | +5.391 |
cean | +5.323 |
Neg logit contributions | |
chrom | -7.497 |
roit | -7.025 |
proof | -7.006 |
eor | -6.869 |
rans | -6.841 |
Token | the |
Token ID | 262 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
emi | +1.539 |
holiest | +1.538 |
athlet | +1.528 |
cean | +1.505 |
olicy | +1.473 |
Neg logit contributions | |
chrom | -2.031 |
proof | -1.945 |
roit | -1.927 |
rans | -1.913 |
eor | -1.891 |
Token | presidential |
Token ID | 4787 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
emi | +1.495 |
olicy | +1.464 |
cean | +1.463 |
athlet | +1.461 |
holiest | +1.443 |
Neg logit contributions | |
chrom | -2.025 |
proof | -1.945 |
roit | -1.930 |
rans | -1.904 |
bos | -1.885 |
Token | campaign |
Token ID | 1923 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
holiest | +2.649 |
emi | +2.617 |
athlet | +2.601 |
olicy | +2.554 |
cean | +2.539 |
Neg logit contributions | |
chrom | -3.037 |
proof | -2.847 |
roit | -2.841 |
rans | -2.805 |
bos | -2.779 |
Token | ), |
Token ID | 828 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
holiest | +2.060 |
emi | +2.003 |
athlet | +1.989 |
goodbye | +1.960 |
cean | +1.955 |
Neg logit contributions | |
chrom | -2.273 |
proof | -2.109 |
roit | -2.103 |
rans | -2.069 |
bos | -2.057 |
Token | with |
Token ID | 351 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
holiest | +1.955 |
emi | +1.917 |
cean | +1.888 |
goodbye | +1.873 |
athlet | +1.869 |
Neg logit contributions | |
chrom | -2.442 |
proof | -2.320 |
roit | -2.280 |
rans | -2.243 |
bos | -2.232 |
Token | hundreds |
Token ID | 5179 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
holiest | +2.525 |
emi | +2.449 |
athlet | +2.433 |
cean | +2.419 |
goodbye | +2.409 |
Neg logit contributions | |
chrom | -3.497 |
proof | -3.341 |
roit | -3.270 |
rans | -3.211 |
bos | -3.198 |
Token | of |
Token ID | 286 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
holiest | +1.514 |
emi | +1.440 |
goodbye | +1.429 |
athlet | +1.426 |
Lanka | +1.420 |
Neg logit contributions | |
chrom | -2.385 |
proof | -2.252 |
roit | -2.231 |
rans | -2.211 |
eor | -2.194 |
Token | thousands |
Token ID | 4138 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
holiest | +2.019 |
emi | +1.944 |
cean | +1.912 |
athlet | +1.906 |
goodbye | +1.894 |
Neg logit contributions | |
chrom | -2.706 |
proof | -2.583 |
roit | -2.533 |
bos | -2.505 |
rans | -2.504 |
Token | of |
Token ID | 286 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
holiest | +2.670 |
emi | +2.564 |
athlet | +2.527 |
goodbye | +2.523 |
cean | +2.506 |
Neg logit contributions | |
chrom | -4.545 |
proof | -4.295 |
roit | -4.284 |
rans | -4.223 |
eor | -4.187 |
Token | dollars |
Token ID | 5054 |
Feature activation | +8.82e+00 |
Pos logit contributions | |
holiest | +1.484 |
emi | +1.383 |
cean | +1.377 |
athlet | +1.346 |
goodbye | +1.332 |
Neg logit contributions | |
chrom | -3.206 |
proof | -3.082 |
roit | -3.038 |
rans | -3.014 |
bos | -2.980 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
holiest | +5.285 |
emi | +5.167 |
athlet | +5.099 |
goodbye | +5.082 |
cean | +5.009 |
Neg logit contributions | |
chrom | -7.785 |
roit | -7.316 |
proof | -7.302 |
eor | -7.160 |
rans | -7.131 |
Token | � |
Token ID | 447 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
holiest | +1.864 |
athlet | +1.810 |
goodbye | +1.745 |
emi | +1.744 |
cean | +1.727 |
Neg logit contributions | |
chrom | -2.540 |
proof | -2.411 |
roit | -2.359 |
eor | -2.340 |
rans | -2.315 |
Token | � |
Token ID | 251 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
holiest | +2.423 |
emi | +2.405 |
athlet | +2.381 |
cean | +2.339 |
olicy | +2.330 |
Neg logit contributions | |
chrom | -2.294 |
roit | -2.138 |
proof | -2.132 |
rans | -2.087 |
eor | -2.075 |
Token |
|
Token ID | 198 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
holiest | +0.402 |
athlet | +0.384 |
goodbye | +0.382 |
emi | +0.382 |
cean | +0.376 |
Neg logit contributions | |
chrom | -0.550 |
proof | -0.524 |
roit | -0.514 |
eor | -0.510 |
rans | -0.503 |
Token |
|
Token ID | 198 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
athlet | +1.887 |
holiest | +1.880 |
olicy | +1.786 |
emi | +1.773 |
bargaining | +1.754 |
Neg logit contributions | |
chrom | -2.155 |
proof | -2.023 |
roit | -1.960 |
eor | -1.931 |
bos | -1.912 |
Token |
|
Token ID | 198 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
holiest | +1.518 |
emi | +1.463 |
athlet | +1.456 |
goodbye | +1.432 |
cean | +1.428 |
Neg logit contributions | |
chrom | -1.886 |
proof | -1.775 |
roit | -1.750 |
eor | -1.719 |
bos | -1.716 |
Token |
|
Token ID | 198 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
holiest | +1.736 |
athlet | +1.735 |
olicy | +1.661 |
emi | +1.658 |
bargaining | +1.628 |
Neg logit contributions | |
chrom | -2.042 |
proof | -1.923 |
roit | -1.862 |
eor | -1.835 |
bos | -1.829 |
Token | Section |
Token ID | 16375 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
holiest | +1.866 |
athlet | +1.833 |
emi | +1.812 |
goodbye | +1.803 |
bargaining | +1.778 |
Neg logit contributions | |
chrom | -1.938 |
proof | -1.808 |
roit | -1.761 |
bos | -1.736 |
eor | -1.729 |
Token | III |
Token ID | 6711 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
holiest | +0.525 |
athlet | +0.504 |
emi | +0.502 |
cean | +0.502 |
goodbye | +0.494 |
Neg logit contributions | |
chrom | -0.663 |
proof | -0.632 |
roit | -0.625 |
bos | -0.611 |
eor | -0.609 |
Token | : |
Token ID | 25 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
holiest | +3.309 |
emi | +3.236 |
athlet | +3.199 |
goodbye | +3.194 |
cean | +3.158 |
Neg logit contributions | |
chrom | -3.890 |
proof | -3.637 |
roit | -3.627 |
eor | -3.548 |
bos | -3.538 |
Token | Lean |
Token ID | 45661 |
Feature activation | +8.78e+00 |
Pos logit contributions | |
holiest | +1.470 |
athlet | +1.420 |
emi | +1.418 |
cean | +1.392 |
goodbye | +1.387 |
Neg logit contributions | |
chrom | -1.838 |
proof | -1.735 |
roit | -1.692 |
bos | -1.674 |
rans | -1.667 |
Token | Six |
Token ID | 9699 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
holiest | +5.910 |
emi | +5.821 |
goodbye | +5.746 |
athlet | +5.737 |
bargaining | +5.659 |
Neg logit contributions | |
chrom | -6.964 |
roit | -6.504 |
proof | -6.443 |
obyl | -6.358 |
eor | -6.332 |
Token | Sigma |
Token ID | 31669 |
Feature activation | +6.33e+00 |
Pos logit contributions | |
holiest | +1.132 |
emi | +1.098 |
athlet | +1.095 |
goodbye | +1.090 |
cean | +1.064 |
Neg logit contributions | |
chrom | -1.538 |
proof | -1.468 |
roit | -1.427 |
eor | -1.414 |
bos | -1.402 |
Token |
|
Token ID | 198 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
holiest | +4.288 |
emi | +4.198 |
athlet | +4.137 |
goodbye | +4.122 |
cean | +4.080 |
Neg logit contributions | |
chrom | -5.158 |
proof | -4.830 |
roit | -4.795 |
eor | -4.702 |
bos | -4.683 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
athlet | +1.381 |
holiest | +1.379 |
olicy | +1.322 |
emi | +1.318 |
bargaining | +1.291 |
Neg logit contributions | |
chrom | -1.578 |
proof | -1.490 |
roit | -1.437 |
eor | -1.415 |
rans | -1.409 |
Token | What |
Token ID | 2061 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
holiest | +1.495 |
athlet | +1.463 |
emi | +1.458 |
goodbye | +1.441 |
Lanka | +1.425 |
Neg logit contributions | |
chrom | -1.619 |
proof | -1.518 |
roit | -1.470 |
bos | -1.446 |
rans | -1.442 |
Token | by |
Token ID | 416 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
holiest | +2.671 |
athlet | +2.619 |
emi | +2.614 |
goodbye | +2.589 |
cean | +2.567 |
Neg logit contributions | |
chrom | -2.963 |
proof | -2.767 |
roit | -2.754 |
rans | -2.714 |
obyl | -2.706 |
Token | blocking |
Token ID | 12013 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
holiest | +1.422 |
emi | +1.412 |
goodbye | +1.392 |
cean | +1.388 |
athlet | +1.387 |
Neg logit contributions | |
chrom | -1.923 |
proof | -1.794 |
roit | -1.790 |
rans | -1.763 |
eor | -1.744 |
Token | national |
Token ID | 2260 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
emi | +0.770 |
holiest | +0.760 |
athlet | +0.750 |
olicy | +0.742 |
cean | +0.738 |
Neg logit contributions | |
chrom | -1.249 |
proof | -1.187 |
roit | -1.168 |
rans | -1.162 |
bos | -1.146 |
Token | highway |
Token ID | 12763 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
emi | +1.163 |
holiest | +1.161 |
athlet | +1.141 |
olicy | +1.138 |
goodbye | +1.121 |
Neg logit contributions | |
chrom | -1.105 |
proof | -1.024 |
roit | -1.020 |
obyl | -0.996 |
rans | -0.995 |
Token | connecting |
Token ID | 14320 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
holiest | +2.723 |
emi | +2.695 |
athlet | +2.661 |
cean | +2.629 |
olicy | +2.625 |
Neg logit contributions | |
chrom | -3.484 |
roit | -3.289 |
proof | -3.283 |
rans | -3.181 |
bos | -3.181 |
Token | Roh |
Token ID | 32694 |
Feature activation | +8.73e+00 |
Pos logit contributions | |
emi | +0.413 |
holiest | +0.406 |
athlet | +0.400 |
olicy | +0.400 |
cean | +0.397 |
Neg logit contributions | |
chrom | -0.602 |
proof | -0.571 |
roit | -0.564 |
eor | -0.558 |
bos | -0.554 |
Token | t |
Token ID | 83 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
emi | +8.307 |
holiest | +8.300 |
Lanka | +8.151 |
goodbye | +8.114 |
cean | +8.106 |
Neg logit contributions | |
chrom | -4.305 |
roit | -3.865 |
proof | -3.772 |
eor | -3.690 |
obyl | -3.634 |
Token | ak |
Token ID | 461 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
holiest | +0.375 |
athlet | +0.368 |
goodbye | +0.359 |
bargaining | +0.358 |
forgiveness | +0.355 |
Neg logit contributions | |
chrom | -0.393 |
roit | -0.375 |
obyl | -0.373 |
proof | -0.372 |
rans | -0.371 |
Token | to |
Token ID | 284 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
holiest | +2.669 |
emi | +2.605 |
athlet | +2.588 |
goodbye | +2.578 |
cean | +2.540 |
Neg logit contributions | |
chrom | -3.665 |
proof | -3.436 |
roit | -3.436 |
rans | -3.362 |
eor | -3.361 |
Token | Delhi |
Token ID | 12517 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
emi | +0.751 |
holiest | +0.749 |
athlet | +0.740 |
olicy | +0.739 |
cean | +0.730 |
Neg logit contributions | |
chrom | -1.097 |
proof | -1.043 |
roit | -1.039 |
eor | -1.025 |
bos | -1.018 |
Token | . |
Token ID | 13 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
holiest | +3.649 |
emi | +3.575 |
athlet | +3.538 |
goodbye | +3.519 |
cean | +3.470 |
Neg logit contributions | |
chrom | -5.231 |
roit | -4.915 |
proof | -4.901 |
eor | -4.804 |
obyl | -4.788 |
Token | was |
Token ID | 373 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
holiest | +2.200 |
emi | +2.140 |
athlet | +2.125 |
goodbye | +2.123 |
olicy | +2.118 |
Neg logit contributions | |
chrom | -3.210 |
proof | -3.044 |
roit | -3.025 |
rans | -2.966 |
bos | -2.960 |
Token | the |
Token ID | 262 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
holiest | +1.805 |
emi | +1.782 |
cean | +1.781 |
goodbye | +1.761 |
olicy | +1.738 |
Neg logit contributions | |
chrom | -2.146 |
proof | -2.020 |
roit | -1.998 |
rans | -1.941 |
bos | -1.932 |
Token | brig |
Token ID | 24393 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
emi | +2.098 |
holiest | +2.092 |
olicy | +2.080 |
goodbye | +2.073 |
cean | +2.072 |
Neg logit contributions | |
chrom | -2.684 |
roit | -2.531 |
proof | -2.530 |
inant | -2.454 |
bos | -2.447 |
Token | adier |
Token ID | 38868 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
holiest | +2.908 |
emi | +2.855 |
athlet | +2.824 |
goodbye | +2.812 |
bargaining | +2.744 |
Neg logit contributions | |
chrom | -4.175 |
roit | -3.923 |
proof | -3.922 |
rans | -3.856 |
eor | -3.849 |
Token | general |
Token ID | 2276 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
holiest | +1.387 |
emi | +1.347 |
goodbye | +1.334 |
olicy | +1.317 |
athlet | +1.313 |
Neg logit contributions | |
chrom | -2.792 |
proof | -2.674 |
roit | -2.665 |
eor | -2.614 |
rans | -2.612 |
Token | Pier |
Token ID | 13762 |
Feature activation | +8.70e+00 |
Pos logit contributions | |
holiest | +0.758 |
emi | +0.735 |
cean | +0.730 |
olicy | +0.726 |
goodbye | +0.722 |
Neg logit contributions | |
chrom | -0.959 |
proof | -0.911 |
roit | -0.906 |
bos | -0.882 |
eor | -0.880 |
Token | a |
Token ID | 64 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
holiest | +7.178 |
emi | +7.141 |
athlet | +7.016 |
cean | +6.997 |
goodbye | +6.992 |
Neg logit contributions | |
chrom | -5.542 |
roit | -5.064 |
proof | -5.061 |
eor | -4.926 |
obyl | -4.921 |
Token | G |
Token ID | 402 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
holiest | +2.079 |
emi | +2.007 |
goodbye | +2.000 |
athlet | +1.985 |
olicy | +1.968 |
Neg logit contributions | |
chrom | -2.811 |
roit | -2.627 |
proof | -2.625 |
eor | -2.579 |
bos | -2.566 |
Token | att |
Token ID | 1078 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
holiest | +3.661 |
goodbye | +3.570 |
athlet | +3.550 |
bargaining | +3.525 |
emi | +3.515 |
Neg logit contributions | |
chrom | -2.494 |
roit | -2.325 |
proof | -2.292 |
bos | -2.225 |
rans | -2.217 |
Token | es |
Token ID | 274 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
holiest | +3.279 |
goodbye | +3.189 |
athlet | +3.188 |
bargaining | +3.146 |
emi | +3.130 |
Neg logit contributions | |
chrom | -2.489 |
roit | -2.305 |
proof | -2.260 |
rans | -2.224 |
eor | -2.212 |
Token | chi |
Token ID | 11072 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
holiest | +2.036 |
athlet | +1.954 |
goodbye | +1.953 |
emi | +1.934 |
olicy | +1.932 |
Neg logit contributions | |
chrom | -2.227 |
roit | -2.082 |
proof | -2.068 |
bos | -2.044 |
rans | -2.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
holiest | +0.954 |
emi | +0.920 |
athlet | +0.911 |
goodbye | +0.899 |
Lanka | +0.898 |
Neg logit contributions | |
chrom | -1.195 |
roit | -1.129 |
proof | -1.119 |
eor | -1.101 |
rans | -1.093 |
Token |
|
Token ID | 198 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
holiest | +1.769 |
athlet | +1.731 |
emi | +1.710 |
goodbye | +1.686 |
cean | +1.674 |
Neg logit contributions | |
chrom | -2.351 |
proof | -2.212 |
roit | -2.208 |
eor | -2.156 |
rans | -2.144 |
Token |
|
Token ID | 198 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
holiest | +1.853 |
athlet | +1.840 |
emi | +1.776 |
olicy | +1.771 |
bargaining | +1.738 |
Neg logit contributions | |
chrom | -2.267 |
proof | -2.135 |
roit | -2.082 |
eor | -2.053 |
bos | -2.044 |
Token | In |
Token ID | 818 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
holiest | +2.007 |
athlet | +1.997 |
emi | +1.933 |
goodbye | +1.931 |
bargaining | +1.926 |
Neg logit contributions | |
chrom | -2.192 |
proof | -2.054 |
roit | -2.017 |
bos | -1.971 |
rans | -1.968 |
Token | St |
Token ID | 520 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
holiest | +3.537 |
emi | +3.446 |
athlet | +3.426 |
goodbye | +3.386 |
cean | +3.348 |
Neg logit contributions | |
chrom | -5.232 |
proof | -4.949 |
roit | -4.947 |
eor | -4.833 |
bos | -4.816 |
Token | Petersburg |
Token ID | 27051 |
Feature activation | +8.61e+00 |
Pos logit contributions | |
holiest | +2.574 |
goodbye | +2.495 |
athlet | +2.488 |
emi | +2.481 |
bargaining | +2.457 |
Neg logit contributions | |
chrom | -3.321 |
roit | -3.189 |
proof | -3.111 |
eor | -3.081 |
rans | -3.079 |
Token | , |
Token ID | 11 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
holiest | +5.034 |
emi | +4.970 |
goodbye | +4.907 |
athlet | +4.857 |
bargaining | +4.765 |
Neg logit contributions | |
chrom | -7.594 |
roit | -7.097 |
proof | -7.079 |
eor | -6.979 |
obyl | -6.961 |
Token | for |
Token ID | 329 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
holiest | +1.966 |
emi | +1.932 |
athlet | +1.909 |
cean | +1.899 |
olicy | +1.877 |
Neg logit contributions | |
chrom | -2.472 |
proof | -2.342 |
roit | -2.333 |
rans | -2.300 |
bos | -2.268 |
Token | example |
Token ID | 1672 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
holiest | +2.444 |
athlet | +2.409 |
emi | +2.400 |
cean | +2.369 |
olicy | +2.365 |
Neg logit contributions | |
chrom | -2.718 |
roit | -2.545 |
proof | -2.545 |
rans | -2.484 |
eor | -2.470 |
Token | , |
Token ID | 11 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
holiest | +0.519 |
emi | +0.510 |
goodbye | +0.503 |
athlet | +0.501 |
cean | +0.492 |
Neg logit contributions | |
chrom | -0.811 |
roit | -0.764 |
proof | -0.760 |
eor | -0.747 |
obyl | -0.746 |
Token | D |
Token ID | 360 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
holiest | +1.662 |
emi | +1.640 |
athlet | +1.621 |
cean | +1.617 |
olicy | +1.602 |
Neg logit contributions | |
chrom | -2.080 |
proof | -1.966 |
roit | -1.945 |
rans | -1.930 |
bos | -1.902 |
Token | as |
Token ID | 355 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
holiest | +1.643 |
emi | +1.579 |
athlet | +1.557 |
goodbye | +1.544 |
cean | +1.543 |
Neg logit contributions | |
chrom | -2.079 |
roit | -1.958 |
proof | -1.955 |
eor | -1.911 |
rans | -1.901 |
Token | Treasury |
Token ID | 13419 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
holiest | +2.209 |
emi | +2.189 |
athlet | +2.139 |
goodbye | +2.102 |
cean | +2.088 |
Neg logit contributions | |
chrom | -3.128 |
proof | -2.983 |
roit | -2.972 |
bos | -2.903 |
eor | -2.881 |
Token | secretary |
Token ID | 7705 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
holiest | +2.176 |
emi | +2.125 |
athlet | +2.083 |
goodbye | +2.024 |
cean | +2.006 |
Neg logit contributions | |
chrom | -5.732 |
proof | -5.526 |
roit | -5.523 |
eor | -5.409 |
rans | -5.397 |
Token | . |
Token ID | 13 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
holiest | +3.079 |
emi | +2.997 |
athlet | +2.964 |
goodbye | +2.930 |
cean | +2.917 |
Neg logit contributions | |
chrom | -4.162 |
proof | -3.920 |
roit | -3.915 |
eor | -3.838 |
rans | -3.816 |
Token | Blank |
Token ID | 31990 |
Feature activation | +6.52e+00 |
Pos logit contributions | |
athlet | +1.772 |
holiest | +1.744 |
emi | +1.649 |
goodbye | +1.629 |
cean | +1.621 |
Neg logit contributions | |
chrom | -2.452 |
proof | -2.352 |
roit | -2.310 |
eor | -2.287 |
rans | -2.273 |
Token | fe |
Token ID | 5036 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
holiest | +4.803 |
athlet | +4.688 |
emi | +4.618 |
goodbye | +4.604 |
olicy | +4.577 |
Neg logit contributions | |
chrom | -4.979 |
proof | -4.629 |
roit | -4.616 |
rans | -4.555 |
obyl | -4.505 |
Token | in |
Token ID | 259 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
emi | +7.226 |
holiest | +7.151 |
goodbye | +7.015 |
bargaining | +6.943 |
athlet | +6.915 |
Neg logit contributions | |
chrom | -5.396 |
proof | -4.781 |
obyl | -4.780 |
roit | -4.757 |
rans | -4.666 |
Token | , |
Token ID | 11 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
holiest | +3.619 |
athlet | +3.492 |
emi | +3.465 |
goodbye | +3.465 |
olicy | +3.461 |
Neg logit contributions | |
chrom | -3.934 |
proof | -3.677 |
roit | -3.666 |
rans | -3.580 |
eor | -3.579 |
Token | Cohn |
Token ID | 45005 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
holiest | +2.205 |
emi | +2.171 |
cean | +2.147 |
athlet | +2.127 |
Lanka | +2.088 |
Neg logit contributions | |
chrom | -2.320 |
proof | -2.176 |
roit | -2.167 |
bos | -2.134 |
rans | -2.115 |
Token | � |
Token ID | 447 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
holiest | +5.804 |
emi | +5.802 |
goodbye | +5.685 |
athlet | +5.608 |
cean | +5.550 |
Neg logit contributions | |
chrom | -9.373 |
roit | -8.759 |
proof | -8.758 |
obyl | -8.592 |
bos | -8.591 |
Token | � |
Token ID | 247 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
holiest | +2.489 |
athlet | +2.444 |
emi | +2.439 |
cean | +2.373 |
olicy | +2.372 |
Neg logit contributions | |
chrom | -2.266 |
proof | -2.113 |
roit | -2.103 |
rans | -2.033 |
inant | -2.026 |
Token | techniques |
Token ID | 7605 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
chrom | +5.732 |
proof | +5.453 |
roit | +5.306 |
rans | +5.214 |
inant | +5.113 |
Neg logit contributions | |
olicy | -5.132 |
emi | -5.015 |
athlet | -4.998 |
holiest | -4.993 |
QUI | -4.930 |
Token | to |
Token ID | 284 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
chrom | +4.186 |
proof | +3.920 |
roit | +3.891 |
rans | +3.805 |
bos | +3.786 |
Neg logit contributions | |
holiest | -3.985 |
olicy | -3.968 |
cean | -3.908 |
emi | -3.872 |
assi | -3.825 |
Token | write |
Token ID | 3551 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
chrom | +3.918 |
proof | +3.610 |
roit | +3.417 |
rans | +3.345 |
inant | +3.322 |
Neg logit contributions | |
olicy | -5.302 |
holiest | -5.251 |
emi | -5.195 |
QUI | -5.138 |
assi | -5.077 |
Token | to |
Token ID | 284 |
Feature activation | -5.94e+00 |
Pos logit contributions | |
chrom | +3.601 |
proof | +3.394 |
inant | +3.149 |
bos | +3.141 |
roit | +3.140 |
Neg logit contributions | |
emi | -2.958 |
cean | -2.945 |
olicy | -2.914 |
holiest | -2.889 |
QUI | -2.885 |
Token | multiple |
Token ID | 3294 |
Feature activation | -7.57e+00 |
Pos logit contributions | |
chrom | +4.658 |
proof | +4.337 |
bos | +4.290 |
inant | +4.129 |
roit | +4.115 |
Neg logit contributions | |
holiest | -3.879 |
athlet | -3.800 |
emi | -3.750 |
cean | -3.740 |
assi | -3.716 |
Token | dat |
Token ID | 4818 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
chrom | +5.311 |
proof | +4.978 |
bos | +4.848 |
inant | +4.665 |
rans | +4.603 |
Neg logit contributions | |
emi | -5.354 |
athlet | -5.243 |
holiest | -5.201 |
olicy | -5.135 |
assi | -5.130 |
Token | acent |
Token ID | 12643 |
Feature activation | -8.09e+00 |
Pos logit contributions | |
chrom | +4.953 |
rans | +4.656 |
bos | +4.508 |
eor | +4.438 |
proof | +4.416 |
Neg logit contributions | |
holiest | -10.919 |
QUI | -10.393 |
athlet | -10.288 |
forgiveness | -10.110 |
CONCLUS | -10.028 |
Token | ers |
Token ID | 364 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
chrom | +4.406 |
rans | +4.365 |
ards | +4.342 |
roit | +4.302 |
eor | +4.298 |
Neg logit contributions | |
holiest | -7.257 |
athlet | -7.186 |
srfAttach | -6.899 |
Lanka | -6.855 |
forgiveness | -6.813 |
Token | in |
Token ID | 287 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
chrom | +3.491 |
proof | +3.313 |
bos | +3.191 |
inant | +3.128 |
eor | +3.118 |
Neg logit contributions | |
olicy | -3.754 |
holiest | -3.739 |
emi | -3.650 |
QUI | -3.635 |
cean | -3.579 |
Token | different |
Token ID | 1180 |
Feature activation | -6.39e+00 |
Pos logit contributions | |
chrom | +1.656 |
proof | +1.534 |
roit | +1.477 |
bos | +1.469 |
rans | +1.457 |
Neg logit contributions | |
holiest | -1.311 |
emi | -1.262 |
athlet | -1.256 |
cean | -1.245 |
olicy | -1.241 |
Token | cities |
Token ID | 4736 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
chrom | +4.205 |
proof | +3.901 |
izations | +3.748 |
bos | +3.698 |
inant | +3.683 |
Neg logit contributions | |
emi | -5.013 |
olicy | -4.853 |
athlet | -4.838 |
cean | -4.794 |
assi | -4.768 |
Token | with |
Token ID | 351 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
holiest | +1.439 |
goodbye | +1.409 |
emi | +1.408 |
athlet | +1.404 |
bargaining | +1.382 |
Neg logit contributions | |
chrom | -2.184 |
roit | -2.046 |
proof | -2.026 |
obyl | -2.015 |
eor | -2.011 |
Token | multiple |
Token ID | 3294 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
chrom | +3.493 |
proof | +3.318 |
roit | +3.258 |
rans | +3.201 |
bos | +3.196 |
Neg logit contributions | |
olicy | -2.775 |
emi | -2.760 |
cean | -2.719 |
holiest | -2.684 |
QUI | -2.658 |
Token | calls |
Token ID | 3848 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
chrom | +5.900 |
proof | +5.520 |
roit | +5.349 |
bos | +5.319 |
eor | +5.310 |
Neg logit contributions | |
emi | -5.133 |
olicy | -4.925 |
cean | -4.844 |
QUI | -4.787 |
holiest | -4.786 |
Token | over |
Token ID | 625 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
chrom | +3.935 |
roit | +3.746 |
proof | +3.739 |
rans | +3.658 |
bos | +3.623 |
Neg logit contributions | |
holiest | -3.716 |
olicy | -3.620 |
emi | -3.565 |
Lanka | -3.489 |
athlet | -3.459 |
Token | the |
Token ID | 262 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
chrom | +3.702 |
proof | +3.452 |
rans | +3.344 |
bos | +3.317 |
roit | +3.303 |
Neg logit contributions | |
holiest | -3.085 |
athlet | -3.041 |
olicy | -3.029 |
emi | -3.019 |
cean | -2.983 |
Token | satellite |
Token ID | 11210 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
chrom | +4.124 |
proof | +3.847 |
bos | +3.746 |
rans | +3.738 |
roit | +3.716 |
Neg logit contributions | |
olicy | -3.007 |
cean | -2.956 |
emi | -2.944 |
athlet | -2.935 |
QUI | -2.922 |
Token | phone |
Token ID | 3072 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
chrom | +7.062 |
proof | +6.661 |
rans | +6.503 |
isation | +6.280 |
roit | +6.267 |
Neg logit contributions | |
olicy | -7.586 |
holiest | -7.310 |
athlet | -7.285 |
QUI | -7.272 |
emi | -7.256 |
Token | , |
Token ID | 11 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
chrom | +4.029 |
proof | +3.715 |
roit | +3.621 |
rans | +3.607 |
bos | +3.490 |
Neg logit contributions | |
olicy | -4.223 |
holiest | -4.175 |
emi | -4.144 |
athlet | -4.133 |
QUI | -4.085 |
Token | Sullivan |
Token ID | 18501 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
chrom | +3.441 |
proof | +3.264 |
roit | +3.190 |
rans | +3.167 |
bos | +3.132 |
Neg logit contributions | |
emi | -3.018 |
olicy | -2.997 |
holiest | -2.995 |
cean | -2.945 |
QUI | -2.940 |
Token | is |
Token ID | 318 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
chrom | +1.736 |
proof | +1.639 |
roit | +1.598 |
rans | +1.572 |
bos | +1.568 |
Neg logit contributions | |
holiest | -2.184 |
olicy | -2.129 |
athlet | -2.088 |
emi | -2.076 |
Lanka | -2.045 |
Token | finally |
Token ID | 3443 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
chrom | +2.137 |
proof | +2.064 |
roit | +2.030 |
rans | +1.983 |
bos | +1.939 |
Neg logit contributions | |
emi | -1.898 |
holiest | -1.852 |
olicy | -1.845 |
cean | -1.839 |
assi | -1.829 |
Token | � |
Token ID | 250 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
chrom | +4.302 |
eor | +4.030 |
proof | +3.863 |
roit | +3.855 |
rans | +3.808 |
Neg logit contributions | |
holiest | -4.787 |
goodbye | -4.644 |
athlet | -4.635 |
emi | -4.622 |
cean | -4.590 |
Token | Big |
Token ID | 12804 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
chrom | +3.637 |
proof | +3.421 |
eor | +3.343 |
rans | +3.332 |
roit | +3.330 |
Neg logit contributions | |
holiest | -2.761 |
athlet | -2.714 |
emi | -2.684 |
Lanka | -2.650 |
bargaining | -2.639 |
Token | gest |
Token ID | 3495 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
chrom | +3.977 |
proof | +3.873 |
eor | +3.753 |
bos | +3.717 |
roit | +3.651 |
Neg logit contributions | |
holiest | -3.068 |
athlet | -2.999 |
olicy | -2.976 |
emi | -2.949 |
QUI | -2.872 |
Token | at |
Token ID | 379 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
chrom | +3.109 |
proof | +3.004 |
eor | +2.850 |
roit | +2.850 |
rans | +2.834 |
Neg logit contributions | |
emi | -2.511 |
olicy | -2.478 |
holiest | -2.414 |
cean | -2.410 |
athlet | -2.362 |
Token | - |
Token ID | 12 |
Feature activation | -9.18e+00 |
Pos logit contributions | |
chrom | +4.531 |
roit | +4.335 |
eor | +4.258 |
rans | +4.254 |
proof | +4.252 |
Neg logit contributions | |
holiest | -3.369 |
olicy | -3.351 |
athlet | -3.295 |
cean | -3.235 |
Lanka | -3.198 |
Token | bat |
Token ID | 8664 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
chrom | +5.591 |
proof | +5.251 |
rans | +5.151 |
bos | +5.049 |
obyl | +4.955 |
Neg logit contributions | |
holiest | -7.562 |
athlet | -7.290 |
cean | -7.207 |
goodbye | -7.180 |
olicy | -7.158 |
Token | of |
Token ID | 286 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
chrom | +7.425 |
proof | +7.144 |
roit | +7.075 |
eor | +6.951 |
inant | +6.924 |
Neg logit contributions | |
olicy | -6.434 |
holiest | -6.182 |
cean | -6.166 |
jri | -6.049 |
Lanka | -6.045 |
Token | my |
Token ID | 616 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
chrom | +3.093 |
roit | +3.008 |
proof | +2.929 |
eor | +2.907 |
bos | +2.844 |
Neg logit contributions | |
olicy | -2.443 |
holiest | -2.362 |
athlet | -2.339 |
cean | -2.295 |
emi | -2.261 |
Token | life |
Token ID | 1204 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
chrom | +2.612 |
roit | +2.489 |
eor | +2.449 |
proof | +2.416 |
rans | +2.382 |
Neg logit contributions | |
olicy | -1.873 |
holiest | -1.868 |
emi | -1.860 |
athlet | -1.835 |
cean | -1.824 |
Token | , |
Token ID | 11 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
chrom | +2.574 |
roit | +2.417 |
proof | +2.396 |
eor | +2.369 |
bos | +2.357 |
Neg logit contributions | |
holiest | -2.425 |
olicy | -2.392 |
cean | -2.312 |
emi | -2.284 |
Lanka | -2.264 |
Token | � |
Token ID | 447 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
chrom | +2.979 |
roit | +2.799 |
proof | +2.786 |
bos | +2.730 |
rans | +2.722 |
Neg logit contributions | |
olicy | -2.199 |
holiest | -2.171 |
emi | -2.138 |
Lanka | -2.124 |
cean | -2.121 |
Token | media |
Token ID | 2056 |
Feature activation | -7.77e+00 |
Pos logit contributions | |
holiest | +0.898 |
emi | +0.872 |
goodbye | +0.868 |
athlet | +0.866 |
bargaining | +0.854 |
Neg logit contributions | |
chrom | -1.250 |
roit | -1.174 |
proof | -1.166 |
eor | -1.151 |
obyl | -1.149 |
Token | , |
Token ID | 11 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
chrom | +5.594 |
proof | +5.348 |
roit | +5.259 |
rans | +5.093 |
eor | +5.031 |
Neg logit contributions | |
olicy | -5.247 |
cean | -5.212 |
emi | -5.138 |
holiest | -5.135 |
assi | -5.061 |
Token | saying |
Token ID | 2282 |
Feature activation | -6.37e+00 |
Pos logit contributions | |
chrom | +4.210 |
proof | +3.980 |
roit | +3.954 |
rans | +3.933 |
bos | +3.864 |
Neg logit contributions | |
emi | -3.613 |
cean | -3.520 |
holiest | -3.518 |
olicy | -3.494 |
assi | -3.421 |
Token | an |
Token ID | 281 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
chrom | +4.587 |
proof | +4.427 |
roit | +4.352 |
bos | +4.313 |
rans | +4.232 |
Neg logit contributions | |
emi | -4.358 |
olicy | -4.266 |
cean | -4.230 |
holiest | -4.217 |
QUI | -4.092 |
Token | oft |
Token ID | 28639 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
chrom | +3.341 |
roit | +3.268 |
proof | +3.254 |
rans | +3.161 |
eor | +3.063 |
Neg logit contributions | |
emi | -2.784 |
holiest | -2.775 |
olicy | -2.745 |
cean | -2.702 |
Lanka | -2.696 |
Token | - |
Token ID | 12 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
chrom | +2.453 |
rans | +2.277 |
roit | +2.270 |
proof | +2.236 |
bos | +2.220 |
Neg logit contributions | |
holiest | -2.113 |
Lanka | -2.079 |
emi | -2.078 |
olicy | -2.025 |
athlet | -2.016 |
Token | qu |
Token ID | 421 |
Feature activation | -8.75e+00 |
Pos logit contributions | |
chrom | +5.836 |
rans | +5.469 |
proof | +5.264 |
roit | +5.156 |
identified | +5.145 |
Neg logit contributions | |
holiest | -9.071 |
Lanka | -8.647 |
goodbye | -8.487 |
srfAttach | -8.417 |
athlet | -8.407 |
Token | oted |
Token ID | 5191 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
roit | +1.482 |
chrom | +1.426 |
rans | +1.345 |
bos | +1.267 |
inant | +1.188 |
Neg logit contributions | |
bargaining | -11.126 |
holiest | -11.040 |
goodbye | -10.982 |
srfAttach | -10.821 |
forgiveness | -10.708 |
Token | blog |
Token ID | 4130 |
Feature activation | -5.92e+00 |
Pos logit contributions | |
chrom | +4.032 |
proof | +3.929 |
rans | +3.757 |
roit | +3.687 |
bos | +3.630 |
Neg logit contributions | |
olicy | -3.533 |
emi | -3.509 |
cean | -3.437 |
assi | -3.383 |
holiest | -3.362 |
Token | post |
Token ID | 1281 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
chrom | +3.731 |
proof | +3.610 |
roit | +3.496 |
eor | +3.444 |
rans | +3.425 |
Neg logit contributions | |
holiest | -4.766 |
athlet | -4.658 |
emi | -4.643 |
Lanka | -4.526 |
srfAttach | -4.486 |
Token | from |
Token ID | 422 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
chrom | +4.844 |
proof | +4.755 |
roit | +4.567 |
bos | +4.410 |
ards | +4.355 |
Neg logit contributions | |
olicy | -5.120 |
emi | -5.037 |
srfAttach | -4.988 |
holiest | -4.982 |
cean | -4.866 |
Token | skin |
Token ID | 4168 |
Feature activation | -7.29e+00 |
Pos logit contributions | |
holiest | +0.698 |
emi | +0.680 |
goodbye | +0.677 |
athlet | +0.675 |
bargaining | +0.665 |
Neg logit contributions | |
chrom | -0.982 |
roit | -0.924 |
proof | -0.917 |
eor | -0.906 |
obyl | -0.903 |
Token | condition |
Token ID | 4006 |
Feature activation | -8.32e+00 |
Pos logit contributions | |
chrom | +5.664 |
proof | +5.271 |
roit | +5.212 |
rans | +5.025 |
obyl | +4.990 |
Neg logit contributions | |
cean | -4.702 |
holiest | -4.658 |
olicy | -4.647 |
athlet | -4.627 |
Lanka | -4.618 |
Token | , |
Token ID | 11 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
chrom | +5.838 |
proof | +5.521 |
roit | +5.296 |
rans | +5.227 |
bos | +5.210 |
Neg logit contributions | |
cean | -5.757 |
olicy | -5.714 |
assi | -5.585 |
holiest | -5.546 |
Lanka | -5.476 |
Token | an |
Token ID | 281 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
chrom | +4.219 |
proof | +3.955 |
roit | +3.894 |
bos | +3.839 |
rans | +3.815 |
Neg logit contributions | |
cean | -3.611 |
olicy | -3.589 |
emi | -3.537 |
holiest | -3.532 |
assi | -3.511 |
Token | autos |
Token ID | 44619 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
chrom | +3.451 |
roit | +3.323 |
proof | +3.200 |
rans | +3.166 |
eor | +3.126 |
Neg logit contributions | |
holiest | -2.997 |
goodbye | -2.941 |
srfAttach | -2.919 |
Lanka | -2.912 |
bargaining | -2.887 |
Token | omal |
Token ID | 18048 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
chrom | +3.311 |
rans | +2.778 |
roit | +2.727 |
inant | +2.702 |
proof | +2.681 |
Neg logit contributions | |
bargaining | -5.835 |
goodbye | -5.829 |
holiest | -5.807 |
athlet | -5.767 |
Lanka | -5.659 |
Token | dominant |
Token ID | 11410 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
chrom | +7.089 |
inant | +6.303 |
roit | +6.139 |
proof | +6.121 |
isation | +5.824 |
Neg logit contributions | |
olicy | -7.639 |
cean | -7.367 |
emi | -7.306 |
holiest | -7.174 |
assi | -7.169 |
Token | palm |
Token ID | 18057 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
chrom | +4.339 |
roit | +3.778 |
proof | +3.665 |
inant | +3.657 |
rans | +3.641 |
Neg logit contributions | |
olicy | -4.948 |
emi | -4.892 |
cean | -4.876 |
holiest | -4.732 |
assi | -4.675 |
Token | opl |
Token ID | 20106 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
chrom | +2.438 |
roit | +2.258 |
inant | +2.251 |
proof | +2.245 |
rans | +2.203 |
Neg logit contributions | |
holiest | -2.301 |
olicy | -2.222 |
cean | -2.205 |
emi | -2.204 |
Lanka | -2.182 |
Token | ant |
Token ID | 415 |
Feature activation | -8.29e+00 |
Pos logit contributions | |
chrom | +1.545 |
proof | +1.362 |
rans | +1.352 |
roit | +1.343 |
eor | +1.303 |
Neg logit contributions | |
holiest | -3.425 |
bargaining | -3.338 |
goodbye | -3.303 |
athlet | -3.249 |
QUI | -3.237 |
Token | ar |
Token ID | 283 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
chrom | +5.950 |
inant | +5.473 |
rans | +5.403 |
proof | +5.370 |
roit | +5.326 |
Neg logit contributions | |
holiest | -6.164 |
olicy | -5.928 |
cean | -5.794 |
goodbye | -5.785 |
bargaining | -5.732 |
Token | a |
Token ID | 257 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
chrom | +2.362 |
proof | +2.298 |
bos | +2.244 |
rans | +2.187 |
roit | +2.182 |
Neg logit contributions | |
emi | -2.194 |
cean | -2.183 |
olicy | -2.153 |
CONCLUS | -2.120 |
assi | -2.105 |
Token | junior |
Token ID | 13430 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
holiest | +0.698 |
emi | +0.680 |
goodbye | +0.677 |
athlet | +0.675 |
bargaining | +0.665 |
Neg logit contributions | |
chrom | -0.982 |
roit | -0.924 |
proof | -0.917 |
eor | -0.906 |
obyl | -0.903 |
Token | to |
Token ID | 284 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
chrom | +4.831 |
roit | +4.684 |
proof | +4.549 |
rans | +4.481 |
eor | +4.458 |
Neg logit contributions | |
holiest | -4.153 |
olicy | -4.146 |
emi | -4.089 |
QUI | -4.065 |
assi | -3.955 |
Token | earn |
Token ID | 5160 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
chrom | +5.213 |
roit | +5.113 |
proof | +5.001 |
rans | +4.987 |
bos | +4.854 |
Neg logit contributions | |
emi | -4.333 |
holiest | -4.325 |
olicy | -4.306 |
cean | -4.177 |
QUI | -4.152 |
Token | all |
Token ID | 477 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
chrom | +2.510 |
proof | +2.415 |
roit | +2.339 |
bos | +2.293 |
rans | +2.254 |
Neg logit contributions | |
olicy | -1.886 |
holiest | -1.873 |
cean | -1.865 |
QUI | -1.846 |
emi | -1.842 |
Token | - |
Token ID | 12 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
chrom | +5.409 |
proof | +5.182 |
roit | +5.030 |
eor | +4.816 |
rans | +4.814 |
Neg logit contributions | |
holiest | -4.517 |
emi | -4.484 |
srfAttach | -4.473 |
olicy | -4.429 |
QUI | -4.392 |
Token | state |
Token ID | 5219 |
Feature activation | -8.54e+00 |
Pos logit contributions | |
chrom | +5.633 |
proof | +5.366 |
roit | +5.091 |
rans | +5.006 |
bos | +4.827 |
Neg logit contributions | |
holiest | -8.575 |
olicy | -8.205 |
Lanka | -8.171 |
goodbye | -8.167 |
athlet | -8.073 |
Token | honors |
Token ID | 25279 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
chrom | +6.251 |
roit | +6.085 |
proof | +5.998 |
bos | +5.932 |
inant | +5.776 |
Neg logit contributions | |
olicy | -5.472 |
emi | -5.369 |
assi | -5.297 |
holiest | -5.275 |
QUI | -5.159 |
Token | . |
Token ID | 13 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
chrom | +2.733 |
roit | +2.650 |
proof | +2.569 |
bos | +2.506 |
inant | +2.458 |
Neg logit contributions | |
holiest | -2.642 |
emi | -2.618 |
cean | -2.547 |
olicy | -2.546 |
assi | -2.512 |
Token |
|
Token ID | 198 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
chrom | +3.151 |
proof | +2.941 |
roit | +2.911 |
bos | +2.872 |
rans | +2.823 |
Neg logit contributions | |
holiest | -2.610 |
athlet | -2.534 |
olicy | -2.479 |
emi | -2.444 |
cean | -2.440 |
Token |
|
Token ID | 198 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
chrom | +2.558 |
proof | +2.425 |
bos | +2.229 |
roit | +2.227 |
rans | +2.214 |
Neg logit contributions | |
athlet | -2.927 |
holiest | -2.845 |
nomine | -2.774 |
referen | -2.770 |
olicy | -2.769 |
Token | drama |
Token ID | 10512 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
chrom | +0.674 |
roit | +0.633 |
proof | +0.629 |
eor | +0.620 |
obyl | +0.619 |
Neg logit contributions | |
holiest | -0.479 |
emi | -0.469 |
athlet | -0.465 |
goodbye | -0.464 |
bargaining | -0.457 |
Token | parody |
Token ID | 29695 |
Feature activation | -6.89e+00 |
Pos logit contributions | |
chrom | +4.256 |
proof | +4.049 |
roit | +4.014 |
rans | +3.869 |
inant | +3.844 |
Neg logit contributions | |
holiest | -3.909 |
emi | -3.865 |
cean | -3.842 |
olicy | -3.814 |
athlet | -3.773 |
Token | sk |
Token ID | 1341 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
chrom | +4.936 |
proof | +4.636 |
roit | +4.618 |
rans | +4.381 |
inant | +4.379 |
Neg logit contributions | |
emi | -4.764 |
holiest | -4.646 |
cean | -4.613 |
olicy | -4.527 |
QUI | -4.509 |
Token | it |
Token ID | 270 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
chrom | +2.643 |
roit | +2.530 |
bos | +2.520 |
rans | +2.498 |
eor | +2.451 |
Neg logit contributions | |
holiest | -6.853 |
bargaining | -6.825 |
athlet | -6.732 |
QUI | -6.676 |
goodbye | -6.651 |
Token | " |
Token ID | 366 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
chrom | +3.204 |
roit | +3.016 |
proof | +3.006 |
rans | +2.957 |
eor | +2.892 |
Neg logit contributions | |
holiest | -2.934 |
cean | -2.842 |
emi | -2.830 |
athlet | -2.781 |
olicy | -2.768 |
Token | Veter |
Token ID | 45182 |
Feature activation | -9.92e+00 |
Pos logit contributions | |
chrom | +3.467 |
proof | +3.295 |
bos | +3.121 |
roit | +3.118 |
eor | +3.079 |
Neg logit contributions | |
athlet | -3.186 |
holiest | -3.175 |
emi | -3.069 |
olicy | -3.062 |
Lanka | -3.053 |
Token | in |
Token ID | 259 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
chrom | +4.108 |
roit | +3.941 |
inant | +3.804 |
rans | +3.732 |
proof | +3.692 |
Neg logit contributions | |
athlet | -10.074 |
holiest | -9.884 |
goodbye | -9.681 |
Lanka | -9.581 |
olicy | -9.448 |
Token | arian |
Token ID | 3699 |
Feature activation | -6.00e+00 |
Pos logit contributions | |
chrom | +1.920 |
proof | +1.735 |
ards | +1.694 |
obyl | +1.683 |
roit | +1.666 |
Neg logit contributions | |
holiest | -3.149 |
forgiveness | -3.057 |
bargaining | -3.052 |
athlet | -3.049 |
goodbye | -3.013 |
Token | 's |
Token ID | 338 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
chrom | +4.776 |
proof | +4.636 |
roit | +4.463 |
bos | +4.434 |
eor | +4.312 |
Neg logit contributions | |
holiest | -3.739 |
athlet | -3.594 |
olicy | -3.589 |
emi | -3.530 |
externalActionCode | -3.504 |
Token | Hospital |
Token ID | 9256 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
chrom | +2.510 |
proof | +2.455 |
bos | +2.368 |
roit | +2.363 |
rans | +2.278 |
Neg logit contributions | |
emi | -1.649 |
cean | -1.625 |
athlet | -1.607 |
olicy | -1.603 |
holiest | -1.587 |
Token | ", |
Token ID | 1600 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
chrom | +5.015 |
roit | +4.940 |
proof | +4.936 |
bos | +4.812 |
izations | +4.808 |
Neg logit contributions | |
holiest | -4.311 |
athlet | -4.239 |
cean | -4.138 |
olicy | -4.086 |
CONCLUS | -4.067 |
Token | . |
Token ID | 13 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
chrom | +4.587 |
proof | +4.270 |
bos | +4.225 |
eor | +4.200 |
roit | +4.158 |
Neg logit contributions | |
olicy | -4.629 |
holiest | -4.390 |
Lanka | -4.281 |
emi | -4.264 |
QUI | -4.240 |
Token | Typically |
Token ID | 27095 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
chrom | +3.166 |
proof | +2.940 |
eor | +2.924 |
roit | +2.841 |
bos | +2.839 |
Neg logit contributions | |
athlet | -2.508 |
holiest | -2.438 |
olicy | -2.430 |
bargaining | -2.346 |
goodbye | -2.307 |
Token | the |
Token ID | 262 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
chrom | +3.686 |
bos | +3.420 |
proof | +3.392 |
rans | +3.341 |
eor | +3.334 |
Neg logit contributions | |
olicy | -3.547 |
emi | -3.462 |
holiest | -3.364 |
assi | -3.337 |
athlet | -3.334 |
Token | most |
Token ID | 749 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
chrom | +2.811 |
bos | +2.552 |
proof | +2.543 |
eor | +2.540 |
roit | +2.511 |
Neg logit contributions | |
olicy | -2.399 |
emi | -2.325 |
assi | -2.271 |
athlet | -2.256 |
QUI | -2.246 |
Token | eas |
Token ID | 1396 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
chrom | +3.050 |
roit | +2.861 |
proof | +2.813 |
eor | +2.776 |
bos | +2.729 |
Neg logit contributions | |
olicy | -2.123 |
emi | -2.098 |
srfAttach | -1.971 |
assi | -1.933 |
QUI | -1.917 |
Token | ter |
Token ID | 353 |
Feature activation | -9.92e+00 |
Pos logit contributions | |
chrom | +1.039 |
proof | +0.926 |
roit | +0.874 |
bos | +0.858 |
rans | +0.843 |
Neg logit contributions | |
holiest | -2.988 |
goodbye | -2.963 |
bargaining | -2.939 |
emi | -2.934 |
athlet | -2.917 |
Token | ly |
Token ID | 306 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
chrom | +5.508 |
proof | +5.442 |
bos | +5.344 |
roit | +5.107 |
rans | +4.962 |
Neg logit contributions | |
emi | -8.471 |
olicy | -8.352 |
holiest | -8.039 |
goodbye | -8.033 |
forgiveness | -7.860 |
Token | aim |
Token ID | 4031 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
chrom | +2.917 |
bos | +2.675 |
proof | +2.658 |
eor | +2.626 |
roit | +2.549 |
Neg logit contributions | |
olicy | -2.656 |
emi | -2.609 |
assi | -2.498 |
QUI | -2.485 |
athlet | -2.471 |
Token | point |
Token ID | 966 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
chrom | +1.505 |
proof | +1.425 |
roit | +1.386 |
eor | +1.367 |
bos | +1.353 |
Neg logit contributions | |
athlet | -1.303 |
emi | -1.302 |
holiest | -1.294 |
goodbye | -1.271 |
olicy | -1.271 |
Token | was |
Token ID | 373 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
chrom | +2.125 |
proof | +1.974 |
bos | +1.959 |
eor | +1.924 |
roit | +1.911 |
Neg logit contributions | |
olicy | -2.076 |
emi | -2.013 |
Lanka | -1.941 |
holiest | -1.935 |
QUI | -1.929 |
Token | targeted |
Token ID | 7977 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
chrom | +1.964 |
proof | +1.835 |
roit | +1.816 |
bos | +1.803 |
eor | +1.784 |
Neg logit contributions | |
olicy | -1.785 |
emi | -1.749 |
holiest | -1.735 |
QUI | -1.722 |
assi | -1.703 |
Token | are |
Token ID | 389 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
chrom | +3.631 |
proof | +3.305 |
roit | +3.283 |
bos | +3.253 |
rans | +3.248 |
Neg logit contributions | |
holiest | -4.312 |
olicy | -4.205 |
srfAttach | -4.190 |
emi | -4.129 |
cean | -4.104 |
Token | here |
Token ID | 994 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
chrom | +4.051 |
proof | +3.921 |
roit | +3.808 |
rans | +3.801 |
bos | +3.793 |
Neg logit contributions | |
olicy | -3.514 |
emi | -3.451 |
assi | -3.392 |
cean | -3.392 |
holiest | -3.340 |
Token | to |
Token ID | 284 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
chrom | +4.792 |
bos | +4.650 |
proof | +4.636 |
roit | +4.602 |
inant | +4.439 |
Neg logit contributions | |
olicy | -5.050 |
holiest | -4.996 |
emi | -4.890 |
assi | -4.811 |
cean | -4.774 |
Token | protect |
Token ID | 1805 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
chrom | +3.540 |
proof | +3.427 |
roit | +3.304 |
rans | +3.182 |
bos | +3.077 |
Neg logit contributions | |
olicy | -5.429 |
emi | -5.400 |
holiest | -5.388 |
assi | -5.237 |
cean | -5.198 |
Token | the |
Token ID | 262 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
chrom | +5.304 |
roit | +5.082 |
proof | +5.062 |
rans | +4.933 |
bos | +4.906 |
Neg logit contributions | |
olicy | -4.528 |
emi | -4.512 |
cean | -4.401 |
assi | -4.377 |
holiest | -4.254 |
Token | civilians |
Token ID | 10380 |
Feature activation | -9.82e+00 |
Pos logit contributions | |
chrom | +3.707 |
proof | +3.431 |
rans | +3.429 |
roit | +3.426 |
bos | +3.334 |
Neg logit contributions | |
emi | -2.874 |
olicy | -2.842 |
assi | -2.811 |
cean | -2.773 |
versa | -2.686 |
Token | and |
Token ID | 290 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
proof | +6.312 |
chrom | +6.297 |
rans | +6.218 |
roit | +5.949 |
ards | +5.936 |
Neg logit contributions | |
olicy | -6.899 |
srfAttach | -6.763 |
QUI | -6.586 |
CONCLUS | -6.559 |
emi | -6.549 |
Token | to |
Token ID | 284 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
chrom | +2.686 |
proof | +2.598 |
roit | +2.573 |
bos | +2.491 |
rans | +2.474 |
Neg logit contributions | |
emi | -2.654 |
cean | -2.605 |
holiest | -2.575 |
olicy | -2.551 |
athlet | -2.506 |
Token | free |
Token ID | 1479 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
chrom | +2.725 |
proof | +2.617 |
roit | +2.474 |
rans | +2.402 |
bos | +2.361 |
Neg logit contributions | |
olicy | -4.576 |
emi | -4.564 |
holiest | -4.501 |
cean | -4.421 |
assi | -4.414 |
Token | their |
Token ID | 511 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
chrom | +2.356 |
proof | +2.255 |
bos | +2.196 |
rans | +2.172 |
roit | +2.171 |
Neg logit contributions | |
olicy | -1.994 |
emi | -1.983 |
cean | -1.967 |
holiest | -1.932 |
athlet | -1.905 |
Token | city |
Token ID | 1748 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
chrom | +2.801 |
proof | +2.674 |
roit | +2.566 |
rans | +2.551 |
bos | +2.509 |
Neg logit contributions | |
emi | -2.782 |
cean | -2.727 |
olicy | -2.689 |
assi | -2.622 |
srfAttach | -2.619 |
Token | au |
Token ID | 559 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
chrom | +2.514 |
roit | +2.348 |
proof | +2.341 |
eor | +2.293 |
obyl | +2.284 |
Neg logit contributions | |
holiest | -2.109 |
emi | -2.073 |
athlet | -2.049 |
goodbye | -2.043 |
cean | -2.014 |
Token | , |
Token ID | 11 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
chrom | +4.045 |
proof | +3.779 |
roit | +3.772 |
rans | +3.724 |
obyl | +3.708 |
Neg logit contributions | |
holiest | -3.409 |
athlet | -3.306 |
olicy | -3.278 |
goodbye | -3.192 |
emi | -3.155 |
Token | who |
Token ID | 508 |
Feature activation | -7.82e+00 |
Pos logit contributions | |
chrom | +4.021 |
proof | +3.797 |
roit | +3.794 |
rans | +3.693 |
bos | +3.688 |
Neg logit contributions | |
holiest | -2.977 |
emi | -2.927 |
olicy | -2.914 |
cean | -2.885 |
athlet | -2.844 |
Token | is |
Token ID | 318 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
chrom | +5.370 |
proof | +5.034 |
bos | +4.953 |
roit | +4.932 |
rans | +4.819 |
Neg logit contributions | |
olicy | -5.630 |
holiest | -5.418 |
QUI | -5.355 |
CONCLUS | -5.338 |
emi | -5.332 |
Token | partially |
Token ID | 12387 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
chrom | +3.216 |
proof | +3.103 |
roit | +2.988 |
rans | +2.972 |
bos | +2.855 |
Neg logit contributions | |
emi | -2.853 |
olicy | -2.850 |
cean | -2.803 |
Lanka | -2.765 |
versa | -2.756 |
Token | disabled |
Token ID | 10058 |
Feature activation | -9.78e+00 |
Pos logit contributions | |
chrom | +3.954 |
proof | +3.868 |
rans | +3.628 |
roit | +3.522 |
ards | +3.470 |
Neg logit contributions | |
cean | -3.565 |
emi | -3.539 |
olicy | -3.530 |
Lanka | -3.443 |
holiest | -3.357 |
Token | , |
Token ID | 11 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
chrom | +6.500 |
proof | +6.196 |
roit | +6.064 |
rans | +5.887 |
bos | +5.835 |
Neg logit contributions | |
olicy | -6.841 |
emi | -6.807 |
holiest | -6.776 |
assi | -6.673 |
cean | -6.541 |
Token | told |
Token ID | 1297 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
chrom | +3.460 |
proof | +3.250 |
bos | +3.213 |
rans | +3.172 |
roit | +3.162 |
Neg logit contributions | |
olicy | -3.567 |
cean | -3.438 |
holiest | -3.419 |
emi | -3.417 |
QUI | -3.369 |
Token | authorities |
Token ID | 4773 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
chrom | +5.050 |
roit | +4.828 |
proof | +4.746 |
bos | +4.671 |
rans | +4.662 |
Neg logit contributions | |
holiest | -4.313 |
olicy | -4.205 |
emi | -4.195 |
cean | -4.118 |
athlet | -4.053 |
Token | that |
Token ID | 326 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
chrom | +3.667 |
proof | +3.462 |
bos | +3.397 |
roit | +3.358 |
rans | +3.322 |
Neg logit contributions | |
holiest | -3.827 |
olicy | -3.801 |
emi | -3.793 |
cean | -3.698 |
QUI | -3.638 |
Token | he |
Token ID | 339 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
chrom | +4.736 |
proof | +4.525 |
bos | +4.407 |
roit | +4.397 |
rans | +4.295 |
Neg logit contributions | |
olicy | -4.527 |
holiest | -4.509 |
emi | -4.500 |
cean | -4.354 |
QUI | -4.324 |
Token | to |
Token ID | 284 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
chrom | +1.697 |
proof | +1.566 |
bos | +1.545 |
roit | +1.528 |
inant | +1.491 |
Neg logit contributions | |
holiest | -2.150 |
cean | -2.134 |
emi | -2.133 |
olicy | -2.122 |
QUI | -2.113 |
Token | the |
Token ID | 262 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
chrom | +0.123 |
roit | +0.116 |
proof | +0.115 |
eor | +0.113 |
obyl | +0.113 |
Neg logit contributions | |
holiest | -0.091 |
emi | -0.089 |
goodbye | -0.088 |
athlet | -0.088 |
bargaining | -0.086 |
Token | bottom |
Token ID | 4220 |
Feature activation | -7.36e+00 |
Pos logit contributions | |
chrom | +4.691 |
proof | +4.359 |
roit | +4.346 |
bos | +4.312 |
rans | +4.261 |
Neg logit contributions | |
olicy | -3.403 |
emi | -3.387 |
cean | -3.351 |
assi | -3.257 |
QUI | -3.251 |
Token | of |
Token ID | 286 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
chrom | +5.728 |
proof | +5.349 |
roit | +5.323 |
rans | +5.296 |
eor | +5.168 |
Neg logit contributions | |
emi | -4.384 |
QUI | -4.371 |
cean | -4.371 |
athlet | -4.363 |
holiest | -4.340 |
Token | the |
Token ID | 262 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
chrom | +4.199 |
proof | +3.907 |
roit | +3.803 |
eor | +3.776 |
rans | +3.772 |
Neg logit contributions | |
athlet | -3.511 |
olicy | -3.499 |
holiest | -3.485 |
cean | -3.460 |
emi | -3.450 |
Token | container |
Token ID | 9290 |
Feature activation | -9.78e+00 |
Pos logit contributions | |
chrom | +4.108 |
proof | +3.775 |
roit | +3.773 |
bos | +3.720 |
eor | +3.656 |
Neg logit contributions | |
olicy | -3.990 |
cean | -3.860 |
emi | -3.848 |
athlet | -3.804 |
QUI | -3.767 |
Token | . |
Token ID | 13 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
chrom | +6.674 |
proof | +6.468 |
roit | +6.135 |
rans | +6.107 |
obyl | +6.052 |
Neg logit contributions | |
holiest | -6.581 |
olicy | -6.503 |
emi | -6.420 |
QUI | -6.345 |
cean | -6.249 |
Token | When |
Token ID | 2215 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
chrom | +4.247 |
proof | +4.003 |
roit | +3.861 |
eor | +3.837 |
obyl | +3.818 |
Neg logit contributions | |
holiest | -3.391 |
athlet | -3.381 |
emi | -3.270 |
bargaining | -3.253 |
cean | -3.236 |
Token | moisture |
Token ID | 20160 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
chrom | +4.995 |
proof | +4.711 |
roit | +4.587 |
rans | +4.549 |
eor | +4.543 |
Neg logit contributions | |
holiest | -4.631 |
olicy | -4.558 |
emi | -4.514 |
athlet | -4.475 |
cean | -4.357 |
Token | starts |
Token ID | 4940 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
proof | +4.941 |
chrom | +4.824 |
rans | +4.510 |
roit | +4.462 |
ards | +4.304 |
Neg logit contributions | |
olicy | -4.802 |
holiest | -4.698 |
Lanka | -4.691 |
athlet | -4.660 |
emi | -4.657 |
Token | to |
Token ID | 284 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
chrom | +2.584 |
rans | +2.497 |
proof | +2.481 |
roit | +2.476 |
bos | +2.445 |
Neg logit contributions | |
olicy | -2.423 |
emi | -2.362 |
holiest | -2.351 |
Lanka | -2.334 |
cean | -2.294 |
Token | is |
Token ID | 318 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
chrom | +1.225 |
rans | +1.171 |
proof | +1.166 |
roit | +1.160 |
bos | +1.118 |
Neg logit contributions | |
holiest | -1.416 |
cean | -1.367 |
olicy | -1.366 |
srfAttach | -1.363 |
emi | -1.361 |
Token | a |
Token ID | 257 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
holiest | +0.983 |
emi | +0.959 |
goodbye | +0.956 |
athlet | +0.955 |
bargaining | +0.936 |
Neg logit contributions | |
chrom | -1.466 |
roit | -1.378 |
proof | -1.367 |
eor | -1.355 |
obyl | -1.350 |
Token | play |
Token ID | 711 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
chrom | +4.590 |
proof | +4.284 |
roit | +4.158 |
rans | +4.067 |
inant | +4.060 |
Neg logit contributions | |
olicy | -3.059 |
emi | -2.998 |
cean | -2.887 |
athlet | -2.875 |
assi | -2.867 |
Token | - |
Token ID | 12 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
chrom | +4.068 |
proof | +3.990 |
roit | +3.878 |
bos | +3.786 |
inant | +3.712 |
Neg logit contributions | |
holiest | -3.542 |
Lanka | -3.485 |
olicy | -3.377 |
cean | -3.340 |
emi | -3.336 |
Token | by |
Token ID | 1525 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
chrom | +5.359 |
proof | +5.209 |
bos | +4.857 |
rans | +4.801 |
roit | +4.735 |
Neg logit contributions | |
Lanka | -9.213 |
holiest | -9.027 |
bargaining | -8.741 |
srfAttach | -8.627 |
cean | -8.618 |
Token | - |
Token ID | 12 |
Feature activation | -9.76e+00 |
Pos logit contributions | |
chrom | +4.995 |
proof | +4.889 |
roit | +4.739 |
rans | +4.493 |
eor | +4.388 |
Neg logit contributions | |
olicy | -5.395 |
athlet | -5.296 |
holiest | -5.262 |
retty | -5.042 |
Lanka | -4.998 |
Token | play |
Token ID | 1759 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
chrom | +2.714 |
proof | +2.478 |
rans | +2.048 |
bos | +1.902 |
roit | +1.855 |
Neg logit contributions | |
holiest | -12.154 |
athlet | -11.935 |
referen | -11.675 |
olicy | -11.570 |
Lanka | -11.450 |
Token | guy |
Token ID | 3516 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
chrom | +4.150 |
roit | +4.033 |
proof | +3.942 |
inant | +3.830 |
rans | +3.802 |
Neg logit contributions | |
olicy | -3.882 |
emi | -3.859 |
holiest | -3.788 |
cean | -3.723 |
QUI | -3.719 |
Token | who |
Token ID | 508 |
Feature activation | -8.23e+00 |
Pos logit contributions | |
chrom | +4.016 |
proof | +3.849 |
roit | +3.774 |
bos | +3.731 |
rans | +3.716 |
Neg logit contributions | |
olicy | -4.249 |
holiest | -4.217 |
emi | -4.094 |
srfAttach | -4.072 |
Lanka | -4.037 |
Token | is |
Token ID | 318 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
chrom | +5.400 |
proof | +5.147 |
roit | +5.058 |
bos | +4.990 |
rans | +4.929 |
Neg logit contributions | |
olicy | -6.157 |
srfAttach | -5.960 |
holiest | -5.949 |
emi | -5.889 |
QUI | -5.745 |
Token | not |
Token ID | 407 |
Feature activation | -6.00e+00 |
Pos logit contributions | |
chrom | +2.598 |
proof | +2.569 |
roit | +2.525 |
rans | +2.444 |
bos | +2.408 |
Neg logit contributions | |
olicy | -2.217 |
emi | -2.156 |
holiest | -2.116 |
cean | -2.114 |
Lanka | -2.085 |
Token | it |
Token ID | 340 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
chrom | +3.631 |
proof | +3.360 |
roit | +3.333 |
bos | +3.318 |
eor | +3.295 |
Neg logit contributions | |
emi | -3.089 |
olicy | -3.071 |
holiest | -3.042 |
athlet | -3.024 |
cean | -2.953 |
Token | is |
Token ID | 318 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
chrom | +3.858 |
proof | +3.618 |
bos | +3.533 |
roit | +3.488 |
rans | +3.472 |
Neg logit contributions | |
olicy | -4.104 |
emi | -3.911 |
cean | -3.813 |
holiest | -3.778 |
Lanka | -3.766 |
Token | directed |
Token ID | 7924 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
chrom | +3.239 |
proof | +3.054 |
bos | +2.944 |
rans | +2.921 |
roit | +2.914 |
Neg logit contributions | |
emi | -2.443 |
cean | -2.393 |
olicy | -2.369 |
holiest | -2.299 |
assi | -2.266 |
Token | or |
Token ID | 393 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
chrom | +4.325 |
proof | +4.109 |
roit | +4.104 |
bos | +3.976 |
rans | +3.954 |
Neg logit contributions | |
olicy | -3.463 |
emi | -3.425 |
assi | -3.303 |
holiest | -3.299 |
cean | -3.218 |
Token | ab |
Token ID | 450 |
Feature activation | -7.03e+00 |
Pos logit contributions | |
chrom | +3.090 |
proof | +2.936 |
roit | +2.874 |
bos | +2.817 |
rans | +2.770 |
Neg logit contributions | |
olicy | -3.483 |
emi | -3.357 |
Lanka | -3.315 |
holiest | -3.279 |
srfAttach | -3.259 |
Token | et |
Token ID | 316 |
Feature activation | -9.72e+00 |
Pos logit contributions | |
chrom | +4.438 |
roit | +4.263 |
proof | +4.102 |
bos | +4.041 |
eor | +4.015 |
Neg logit contributions | |
holiest | -5.841 |
goodbye | -5.746 |
forgiveness | -5.615 |
athlet | -5.607 |
Lanka | -5.571 |
Token | ted |
Token ID | 1513 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
roit | +1.734 |
chrom | +1.697 |
proof | +1.671 |
rans | +1.352 |
eor | +1.273 |
Neg logit contributions | |
holiest | -12.112 |
goodbye | -11.936 |
emi | -11.833 |
athlet | -11.676 |
Lanka | -11.631 |
Token | by |
Token ID | 416 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
chrom | +5.648 |
roit | +5.387 |
proof | +5.366 |
rans | +5.140 |
bos | +5.088 |
Neg logit contributions | |
olicy | -5.785 |
holiest | -5.777 |
emi | -5.762 |
assi | -5.605 |
cean | -5.594 |
Token | states |
Token ID | 2585 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
chrom | +3.405 |
proof | +3.171 |
roit | +3.164 |
bos | +3.123 |
rans | +3.097 |
Neg logit contributions | |
cean | -2.556 |
olicy | -2.550 |
emi | -2.529 |
holiest | -2.528 |
assi | -2.464 |
Token | who |
Token ID | 508 |
Feature activation | -6.65e+00 |
Pos logit contributions | |
chrom | +3.736 |
rans | +3.581 |
roit | +3.561 |
bos | +3.511 |
proof | +3.494 |
Neg logit contributions | |
holiest | -3.300 |
olicy | -3.281 |
Lanka | -3.256 |
emi | -3.233 |
cean | -3.187 |
Token | are |
Token ID | 389 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
chrom | +4.230 |
roit | +3.957 |
proof | +3.846 |
bos | +3.794 |
rans | +3.785 |
Neg logit contributions | |
srfAttach | -5.149 |
holiest | -5.139 |
olicy | -5.067 |
emi | -5.052 |
QUI | -5.017 |
Token | uk |
Token ID | 2724 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
chrom | +3.571 |
roit | +3.391 |
proof | +3.379 |
eor | +3.356 |
bos | +3.303 |
Neg logit contributions | |
holiest | -3.431 |
goodbye | -3.374 |
olicy | -3.362 |
athlet | -3.329 |
bargaining | -3.297 |
Token | Moor |
Token ID | 31451 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
chrom | +1.994 |
roit | +1.889 |
proof | +1.883 |
rans | +1.870 |
bos | +1.859 |
Neg logit contributions | |
holiest | -1.728 |
athlet | -1.706 |
goodbye | -1.657 |
emi | -1.644 |
olicy | -1.627 |
Token | claw |
Token ID | 43143 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
chrom | +3.693 |
proof | +3.579 |
rans | +3.489 |
bos | +3.484 |
roit | +3.447 |
Neg logit contributions | |
holiest | -3.870 |
athlet | -3.730 |
goodbye | -3.727 |
bargaining | -3.720 |
olicy | -3.640 |
Token | , |
Token ID | 11 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
chrom | +2.605 |
proof | +2.462 |
roit | +2.431 |
bos | +2.403 |
eor | +2.398 |
Neg logit contributions | |
holiest | -2.305 |
goodbye | -2.218 |
athlet | -2.202 |
olicy | -2.184 |
emi | -2.182 |
Token | and |
Token ID | 290 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
chrom | +2.314 |
proof | +2.175 |
roit | +2.163 |
eor | +2.149 |
bos | +2.119 |
Neg logit contributions | |
holiest | -1.657 |
athlet | -1.640 |
olicy | -1.632 |
emi | -1.618 |
cean | -1.618 |
Token | Col |
Token ID | 1623 |
Feature activation | -9.70e+00 |
Pos logit contributions | |
chrom | +1.684 |
proof | +1.609 |
roit | +1.584 |
eor | +1.554 |
bos | +1.549 |
Neg logit contributions | |
olicy | -1.214 |
emi | -1.212 |
cean | -1.208 |
holiest | -1.203 |
athlet | -1.198 |
Token | bie |
Token ID | 12590 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
chrom | +6.615 |
roit | +6.310 |
bos | +6.192 |
eor | +6.086 |
inant | +6.050 |
Neg logit contributions | |
holiest | -6.938 |
goodbye | -6.933 |
athlet | -6.820 |
olicy | -6.759 |
bargaining | -6.720 |
Token | Sterling |
Token ID | 23647 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
chrom | +2.986 |
proof | +2.818 |
roit | +2.783 |
eor | +2.770 |
bos | +2.767 |
Neg logit contributions | |
holiest | -2.061 |
athlet | -2.002 |
olicy | -1.991 |
goodbye | -1.966 |
emi | -1.958 |
Token | — |
Token ID | 960 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
chrom | +2.694 |
bos | +2.524 |
proof | +2.522 |
roit | +2.507 |
rans | +2.472 |
Neg logit contributions | |
holiest | -2.435 |
olicy | -2.350 |
emi | -2.288 |
athlet | -2.275 |
cean | -2.275 |
Token | all |
Token ID | 439 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
chrom | +2.248 |
proof | +2.120 |
rans | +1.949 |
eor | +1.942 |
roit | +1.940 |
Neg logit contributions | |
holiest | -3.228 |
athlet | -3.220 |
Lanka | -3.199 |
olicy | -3.148 |
emi | -3.106 |
Token | of |
Token ID | 286 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
chrom | +4.545 |
proof | +4.318 |
roit | +4.299 |
rans | +4.212 |
inant | +4.207 |
Neg logit contributions | |
holiest | -3.590 |
cean | -3.502 |
olicy | -3.500 |
emi | -3.445 |
Lanka | -3.396 |
Token | of |
Token ID | 286 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
chrom | +3.859 |
proof | +3.616 |
bos | +3.598 |
roit | +3.588 |
inant | +3.552 |
Neg logit contributions | |
holiest | -2.470 |
emi | -2.380 |
olicy | -2.369 |
athlet | -2.366 |
goodbye | -2.354 |
Token | critical |
Token ID | 4688 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
chrom | +3.402 |
proof | +3.138 |
roit | +3.112 |
bos | +3.092 |
rans | +3.028 |
Neg logit contributions | |
olicy | -2.804 |
cean | -2.796 |
emi | -2.750 |
holiest | -2.736 |
assi | -2.650 |
Token | illness |
Token ID | 8526 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
chrom | +3.663 |
roit | +3.412 |
proof | +3.336 |
eor | +3.238 |
rans | +3.235 |
Neg logit contributions | |
holiest | -3.426 |
emi | -3.362 |
olicy | -3.357 |
cean | -3.316 |
athlet | -3.260 |
Token | - |
Token ID | 12 |
Feature activation | -8.86e+00 |
Pos logit contributions | |
chrom | +3.254 |
proof | +3.099 |
roit | +3.011 |
bos | +2.948 |
rans | +2.911 |
Neg logit contributions | |
holiest | -3.252 |
olicy | -3.233 |
cean | -3.216 |
emi | -3.129 |
Lanka | -3.112 |
Token | related |
Token ID | 5363 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
chrom | +4.390 |
proof | +4.110 |
linked | +3.886 |
bos | +3.742 |
rans | +3.678 |
Neg logit contributions | |
holiest | -8.249 |
Lanka | -8.202 |
cean | -8.055 |
athlet | -8.053 |
olicy | -8.051 |
Token | cort |
Token ID | 12794 |
Feature activation | -9.61e+00 |
Pos logit contributions | |
chrom | +3.392 |
proof | +3.114 |
roit | +3.069 |
bos | +2.987 |
izations | +2.974 |
Neg logit contributions | |
cean | -3.766 |
olicy | -3.755 |
emi | -3.712 |
holiest | -3.691 |
assi | -3.625 |
Token | ic |
Token ID | 291 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
chrom | +2.555 |
roit | +2.239 |
proof | +2.105 |
rans | +2.014 |
inant | +1.872 |
Neg logit contributions | |
holiest | -11.299 |
goodbye | -11.211 |
bargaining | -11.208 |
athlet | -11.081 |
QUI | -11.026 |
Token | oster |
Token ID | 6197 |
Feature activation | -6.89e+00 |
Pos logit contributions | |
chrom | +2.323 |
roit | +2.148 |
obyl | +2.038 |
proof | +2.035 |
rans | +2.028 |
Neg logit contributions | |
holiest | -4.208 |
bargaining | -4.141 |
Lanka | -4.137 |
goodbye | -4.092 |
athlet | -4.086 |
Token | oid |
Token ID | 1868 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
chrom | +1.370 |
proof | +1.284 |
roit | +1.160 |
rans | +1.139 |
bos | +1.113 |
Neg logit contributions | |
holiest | -8.526 |
athlet | -8.514 |
Lanka | -8.485 |
emi | -8.407 |
olicy | -8.361 |
Token | ins |
Token ID | 1035 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
chrom | +3.662 |
proof | +3.516 |
roit | +3.469 |
bos | +3.316 |
rans | +3.219 |
Neg logit contributions | |
olicy | -3.774 |
emi | -3.704 |
holiest | -3.658 |
cean | -3.656 |
athlet | -3.560 |
Token | uff |
Token ID | 1648 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
chrom | +0.067 |
proof | +0.060 |
rans | +0.059 |
roit | +0.059 |
bos | +0.059 |
Neg logit contributions | |
holiest | -0.082 |
athlet | -0.082 |
bargaining | -0.080 |
emi | -0.080 |
goodbye | -0.080 |
Token | find |
Token ID | 1064 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
chrom | +4.528 |
proof | +4.167 |
roit | +3.976 |
eor | +3.927 |
rans | +3.911 |
Neg logit contributions | |
holiest | -5.356 |
olicy | -5.307 |
emi | -5.277 |
cean | -5.107 |
QUI | -5.102 |
Token | a |
Token ID | 257 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
chrom | +4.886 |
proof | +4.613 |
bos | +4.408 |
roit | +4.365 |
rans | +4.339 |
Neg logit contributions | |
olicy | -3.864 |
emi | -3.783 |
cean | -3.737 |
assi | -3.606 |
holiest | -3.594 |
Token | specific |
Token ID | 2176 |
Feature activation | -9.23e+00 |
Pos logit contributions | |
chrom | +4.138 |
proof | +3.735 |
roit | +3.624 |
bos | +3.580 |
inant | +3.573 |
Neg logit contributions | |
olicy | -3.141 |
emi | -3.096 |
cean | -3.050 |
athlet | -3.005 |
holiest | -2.981 |
Token | pet |
Token ID | 4273 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
chrom | +6.719 |
proof | +6.210 |
inant | +6.001 |
roit | +5.852 |
bos | +5.832 |
Neg logit contributions | |
olicy | -6.130 |
emi | -6.101 |
cean | -6.026 |
QUI | -5.822 |
assi | -5.811 |
Token | - |
Token ID | 12 |
Feature activation | -8.82e+00 |
Pos logit contributions | |
chrom | +5.695 |
proof | +5.382 |
roit | +5.345 |
rans | +5.256 |
eor | +5.169 |
Neg logit contributions | |
holiest | -4.994 |
cean | -4.920 |
emi | -4.902 |
athlet | -4.845 |
CONCLUS | -4.832 |
Token | colour |
Token ID | 49903 |
Feature activation | -9.51e+00 |
Pos logit contributions | |
chrom | +5.039 |
proof | +4.937 |
bos | +4.345 |
rans | +4.337 |
roit | +4.273 |
Neg logit contributions | |
Lanka | -7.687 |
holiest | -7.567 |
athlet | -7.474 |
emi | -7.327 |
forgiveness | -7.271 |
Token | combination |
Token ID | 6087 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
chrom | +7.097 |
proof | +6.683 |
roit | +6.236 |
inant | +6.160 |
isation | +6.107 |
Neg logit contributions | |
olicy | -6.308 |
cean | -6.167 |
holiest | -6.128 |
CONCLUS | -6.083 |
emi | -6.071 |
Token | , |
Token ID | 11 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
chrom | +4.253 |
proof | +3.971 |
roit | +3.837 |
rans | +3.735 |
inant | +3.725 |
Neg logit contributions | |
olicy | -3.886 |
cean | -3.849 |
emi | -3.834 |
holiest | -3.814 |
CONCLUS | -3.758 |
Token | by |
Token ID | 416 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
chrom | +2.847 |
proof | +2.651 |
roit | +2.602 |
bos | +2.531 |
rans | +2.531 |
Neg logit contributions | |
holiest | -2.556 |
olicy | -2.547 |
emi | -2.538 |
cean | -2.497 |
Lanka | -2.471 |
Token | setting |
Token ID | 4634 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
chrom | +2.232 |
proof | +2.042 |
roit | +2.016 |
bos | +1.970 |
rans | +1.956 |
Neg logit contributions | |
olicy | -2.221 |
holiest | -2.160 |
emi | -2.158 |
cean | -2.137 |
goodbye | -2.109 |
Token | both |
Token ID | 1111 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
chrom | +3.174 |
proof | +2.984 |
roit | +2.883 |
bos | +2.833 |
rans | +2.809 |
Neg logit contributions | |
holiest | -2.506 |
emi | -2.435 |
cean | -2.400 |
olicy | -2.392 |
athlet | -2.381 |
Token | be |
Token ID | 307 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
chrom | +0.935 |
proof | +0.899 |
rans | +0.882 |
roit | +0.862 |
eor | +0.840 |
Neg logit contributions | |
holiest | -0.856 |
emi | -0.855 |
olicy | -0.851 |
cean | -0.836 |
assi | -0.830 |
Token | for |
Token ID | 329 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
chrom | +0.565 |
roit | +0.531 |
proof | +0.528 |
eor | +0.521 |
obyl | +0.519 |
Neg logit contributions | |
holiest | -0.383 |
emi | -0.375 |
athlet | -0.371 |
goodbye | -0.370 |
bargaining | -0.363 |
Token | " |
Token ID | 366 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
chrom | +4.156 |
proof | +3.956 |
roit | +3.922 |
rans | +3.818 |
bos | +3.812 |
Neg logit contributions | |
olicy | -3.043 |
emi | -3.014 |
holiest | -2.990 |
cean | -2.968 |
assi | -2.879 |
Token | active |
Token ID | 5275 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
chrom | +3.780 |
proof | +3.627 |
bos | +3.350 |
rans | +3.343 |
roit | +3.341 |
Neg logit contributions | |
holiest | -4.246 |
athlet | -4.150 |
Lanka | -4.126 |
olicy | -4.108 |
goodbye | -4.093 |
Token | " |
Token ID | 1 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
chrom | +5.181 |
proof | +4.876 |
roit | +4.833 |
bos | +4.730 |
eor | +4.639 |
Neg logit contributions | |
holiest | -3.948 |
emi | -3.813 |
cean | -3.777 |
olicy | -3.755 |
ofi | -3.687 |
Token | registered |
Token ID | 6823 |
Feature activation | -9.45e+00 |
Pos logit contributions | |
chrom | +4.976 |
proof | +4.644 |
roit | +4.561 |
bos | +4.476 |
rans | +4.379 |
Neg logit contributions | |
emi | -4.407 |
olicy | -4.376 |
holiest | -4.344 |
cean | -4.330 |
assi | -4.250 |
Token | voters |
Token ID | 4446 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
chrom | +6.315 |
roit | +5.758 |
proof | +5.680 |
bos | +5.604 |
rans | +5.492 |
Neg logit contributions | |
holiest | -6.932 |
cean | -6.775 |
emi | -6.685 |
assi | -6.672 |
olicy | -6.671 |
Token | , |
Token ID | 11 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
chrom | +4.517 |
proof | +4.346 |
rans | +4.231 |
roit | +4.182 |
bos | +4.149 |
Neg logit contributions | |
holiest | -4.842 |
olicy | -4.788 |
emi | -4.660 |
cean | -4.647 |
Lanka | -4.577 |
Token | i |
Token ID | 1312 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
chrom | +3.596 |
proof | +3.449 |
rans | +3.384 |
roit | +3.365 |
bos | +3.308 |
Neg logit contributions | |
cean | -3.240 |
emi | -3.208 |
holiest | -3.182 |
assi | -3.114 |
olicy | -3.108 |
Token | . |
Token ID | 13 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
chrom | +2.941 |
proof | +2.681 |
roit | +2.635 |
rans | +2.628 |
ards | +2.606 |
Neg logit contributions | |
holiest | -2.806 |
goodbye | -2.752 |
athlet | -2.701 |
Lanka | -2.649 |
bargaining | -2.646 |
Token | e |
Token ID | 68 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
chrom | +1.104 |
proof | +0.917 |
eor | +0.837 |
roit | +0.685 |
rans | +0.652 |
Neg logit contributions | |
holiest | -6.332 |
athlet | -6.272 |
olicy | -6.161 |
Lanka | -6.087 |
bargaining | -6.035 |
Token | natural |
Token ID | 3288 |
Feature activation | -6.26e+00 |
Pos logit contributions | |
chrom | +4.098 |
roit | +3.805 |
proof | +3.802 |
bos | +3.727 |
rans | +3.716 |
Neg logit contributions | |
emi | -3.241 |
olicy | -3.163 |
cean | -3.117 |
assi | -3.109 |
QUI | -3.027 |
Token | habitat |
Token ID | 20018 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
chrom | +4.704 |
proof | +4.308 |
roit | +4.236 |
isation | +4.195 |
izations | +4.153 |
Neg logit contributions | |
emi | -4.425 |
assi | -4.349 |
olicy | -4.295 |
holiest | -4.180 |
Lanka | -4.101 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
chrom | +5.597 |
proof | +5.395 |
rans | +5.275 |
roit | +5.156 |
bos | +5.119 |
Neg logit contributions | |
olicy | -4.984 |
emi | -4.821 |
athlet | -4.821 |
cean | -4.817 |
assi | -4.754 |
Token | The |
Token ID | 383 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
chrom | +3.671 |
proof | +3.475 |
roit | +3.366 |
eor | +3.351 |
bos | +3.316 |
Neg logit contributions | |
athlet | -3.074 |
holiest | -3.000 |
olicy | -2.905 |
bargaining | -2.851 |
emi | -2.809 |
Token | fire |
Token ID | 2046 |
Feature activation | -6.62e+00 |
Pos logit contributions | |
chrom | +2.844 |
proof | +2.674 |
roit | +2.624 |
bos | +2.582 |
rans | +2.577 |
Neg logit contributions | |
emi | -2.186 |
olicy | -2.186 |
athlet | -2.148 |
holiest | -2.135 |
cean | -2.130 |
Token | ant |
Token ID | 1885 |
Feature activation | -9.45e+00 |
Pos logit contributions | |
proof | +5.001 |
chrom | +4.891 |
roit | +4.504 |
eor | +4.435 |
rans | +4.429 |
Neg logit contributions | |
athlet | -4.523 |
holiest | -4.496 |
olicy | -4.459 |
cean | -4.417 |
Lanka | -4.415 |
Token | epidemic |
Token ID | 18195 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
proof | +6.578 |
chrom | +6.567 |
roit | +6.187 |
rans | +6.021 |
eor | +6.001 |
Neg logit contributions | |
holiest | -6.524 |
emi | -6.341 |
QUI | -6.306 |
srfAttach | -6.273 |
athlet | -6.268 |
Token | arose |
Token ID | 21172 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
chrom | +3.062 |
proof | +2.944 |
bos | +2.796 |
roit | +2.789 |
inant | +2.741 |
Neg logit contributions | |
olicy | -3.233 |
holiest | -3.157 |
cean | -3.142 |
emi | -3.128 |
QUI | -3.097 |
Token | when |
Token ID | 618 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
chrom | +2.620 |
proof | +2.439 |
roit | +2.413 |
bos | +2.406 |
rans | +2.364 |
Neg logit contributions | |
emi | -2.451 |
holiest | -2.435 |
olicy | -2.420 |
assi | -2.364 |
cean | -2.346 |
Token | the |
Token ID | 262 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
chrom | +4.591 |
proof | +4.429 |
bos | +4.280 |
eor | +4.252 |
roit | +4.244 |
Neg logit contributions | |
emi | -3.987 |
olicy | -3.984 |
holiest | -3.946 |
QUI | -3.935 |
cean | -3.840 |
Token | killer |
Token ID | 11868 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
chrom | +2.437 |
proof | +2.277 |
roit | +2.241 |
eor | +2.223 |
rans | +2.217 |
Neg logit contributions | |
emi | -1.976 |
olicy | -1.972 |
cean | -1.914 |
holiest | -1.904 |
athlet | -1.884 |
Token | lives |
Token ID | 3160 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
chrom | +4.062 |
proof | +3.795 |
roit | +3.728 |
rans | +3.720 |
bos | +3.699 |
Neg logit contributions | |
emi | -3.125 |
holiest | -3.122 |
cean | -3.102 |
olicy | -3.102 |
athlet | -3.007 |
Token | , |
Token ID | 11 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
chrom | +2.931 |
proof | +2.827 |
rans | +2.776 |
bos | +2.759 |
obyl | +2.723 |
Neg logit contributions | |
olicy | -2.739 |
holiest | -2.622 |
emi | -2.621 |
cean | -2.599 |
assi | -2.592 |
Token | including |
Token ID | 1390 |
Feature activation | -7.48e+00 |
Pos logit contributions | |
chrom | +3.935 |
proof | +3.764 |
rans | +3.696 |
bos | +3.671 |
roit | +3.641 |
Neg logit contributions | |
cean | -3.445 |
olicy | -3.389 |
emi | -3.348 |
holiest | -3.347 |
assi | -3.322 |
Token | hundreds |
Token ID | 5179 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
chrom | +5.324 |
proof | +5.283 |
bos | +5.001 |
roit | +4.921 |
rans | +4.905 |
Neg logit contributions | |
olicy | -4.926 |
cean | -4.840 |
emi | -4.820 |
QUI | -4.701 |
assi | -4.671 |
Token | of |
Token ID | 286 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
chrom | +4.303 |
proof | +4.101 |
rans | +4.044 |
bos | +4.044 |
roit | +3.992 |
Neg logit contributions | |
olicy | -3.264 |
cean | -3.241 |
holiest | -3.229 |
emi | -3.209 |
athlet | -3.162 |
Token | civilians |
Token ID | 10380 |
Feature activation | -9.43e+00 |
Pos logit contributions | |
chrom | +3.498 |
proof | +3.328 |
bos | +3.294 |
roit | +3.241 |
rans | +3.218 |
Neg logit contributions | |
emi | -3.150 |
olicy | -3.109 |
cean | -3.086 |
holiest | -3.043 |
srfAttach | -3.040 |
Token | . |
Token ID | 13 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
chrom | +5.907 |
rans | +5.827 |
proof | +5.791 |
eor | +5.726 |
roit | +5.620 |
Neg logit contributions | |
olicy | -6.912 |
holiest | -6.595 |
cean | -6.567 |
athlet | -6.513 |
emi | -6.464 |
Token |
|
Token ID | 198 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
chrom | +2.683 |
proof | +2.562 |
roit | +2.474 |
eor | +2.470 |
bos | +2.467 |
Neg logit contributions | |
athlet | -2.261 |
holiest | -2.177 |
olicy | -2.111 |
bargaining | -2.082 |
cean | -2.080 |
Token |
|
Token ID | 198 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
chrom | +2.020 |
proof | +1.917 |
roit | +1.768 |
bos | +1.766 |
rans | +1.757 |
Neg logit contributions | |
athlet | -2.285 |
holiest | -2.194 |
olicy | -2.163 |
referen | -2.141 |
nomine | -2.134 |
Token | The |
Token ID | 464 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
chrom | +1.902 |
proof | +1.795 |
bos | +1.720 |
roit | +1.702 |
eor | +1.677 |
Neg logit contributions | |
athlet | -1.857 |
holiest | -1.782 |
olicy | -1.753 |
goodbye | -1.751 |
bargaining | -1.739 |
Token | hypocrisy |
Token ID | 29442 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
chrom | +1.654 |
proof | +1.565 |
roit | +1.533 |
bos | +1.533 |
rans | +1.519 |
Neg logit contributions | |
olicy | -1.361 |
emi | -1.354 |
athlet | -1.334 |
cean | -1.331 |
goodbye | -1.305 |
Token |
|
Token ID | 198 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
chrom | +3.527 |
proof | +3.262 |
roit | +2.994 |
bos | +2.954 |
rans | +2.935 |
Neg logit contributions | |
athlet | -4.203 |
holiest | -4.041 |
olicy | -3.913 |
nomine | -3.834 |
bargaining | -3.821 |
Token | Development |
Token ID | 41206 |
Feature activation | -5.68e+00 |
Pos logit contributions | |
chrom | +3.752 |
proof | +3.497 |
roit | +3.293 |
bos | +3.291 |
rans | +3.255 |
Neg logit contributions | |
holiest | -3.337 |
athlet | -3.310 |
Lanka | -3.234 |
olicy | -3.209 |
goodbye | -3.203 |
Token | of |
Token ID | 286 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
chrom | +4.490 |
proof | +4.161 |
eor | +3.968 |
rans | +3.965 |
roit | +3.965 |
Neg logit contributions | |
holiest | -3.664 |
emi | -3.600 |
athlet | -3.583 |
olicy | -3.562 |
cean | -3.509 |
Token | the |
Token ID | 262 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
chrom | +3.734 |
proof | +3.455 |
roit | +3.374 |
bos | +3.342 |
inant | +3.303 |
Neg logit contributions | |
emi | -2.882 |
cean | -2.878 |
holiest | -2.873 |
olicy | -2.848 |
goodbye | -2.812 |
Token | F |
Token ID | 376 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
chrom | +3.866 |
proof | +3.576 |
roit | +3.528 |
bos | +3.469 |
rans | +3.460 |
Neg logit contributions | |
cean | -3.117 |
olicy | -3.091 |
emi | -3.089 |
holiest | -3.008 |
athlet | -3.001 |
Token | - |
Token ID | 12 |
Feature activation | -9.36e+00 |
Pos logit contributions | |
chrom | +1.880 |
roit | +1.759 |
proof | +1.746 |
bos | +1.714 |
obyl | +1.712 |
Neg logit contributions | |
holiest | -2.071 |
athlet | -2.046 |
goodbye | -2.016 |
bargaining | -1.981 |
cean | -1.980 |
Token | 35 |
Token ID | 2327 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
chrom | +6.391 |
proof | +5.912 |
bos | +5.669 |
roit | +5.361 |
linked | +5.299 |
Neg logit contributions | |
holiest | -6.901 |
athlet | -6.812 |
cean | -6.717 |
goodbye | -6.576 |
emi | -6.568 |
Token | fighter |
Token ID | 10543 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
chrom | +1.992 |
proof | +1.922 |
roit | +1.888 |
bos | +1.858 |
eor | +1.838 |
Neg logit contributions | |
holiest | -1.942 |
emi | -1.893 |
cean | -1.878 |
athlet | -1.876 |
olicy | -1.864 |
Token | jet |
Token ID | 12644 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
chrom | +1.925 |
proof | +1.869 |
roit | +1.814 |
bos | +1.765 |
rans | +1.753 |
Neg logit contributions | |
holiest | -2.144 |
olicy | -2.095 |
emi | -2.089 |
athlet | -2.089 |
Lanka | -2.070 |
Token | will |
Token ID | 481 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
chrom | +3.092 |
proof | +2.955 |
roit | +2.866 |
bos | +2.800 |
inant | +2.771 |
Neg logit contributions | |
holiest | -3.074 |
olicy | -3.009 |
cean | -2.986 |
emi | -2.977 |
QUI | -2.959 |
Token | cost |
Token ID | 1575 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
chrom | +3.153 |
roit | +2.935 |
proof | +2.875 |
bos | +2.856 |
eor | +2.839 |
Neg logit contributions | |
olicy | -4.667 |
holiest | -4.662 |
QUI | -4.630 |
assi | -4.566 |
emi | -4.489 |
Token | well |
Token ID | 880 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
holiest | +1.908 |
emi | +1.883 |
cean | +1.866 |
athlet | +1.834 |
olicy | +1.832 |
Neg logit contributions | |
chrom | -2.348 |
proof | -2.235 |
roit | -2.196 |
rans | -2.168 |
bos | -2.158 |
Token | founded |
Token ID | 9393 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
holiest | +1.912 |
emi | +1.871 |
athlet | +1.848 |
cean | +1.845 |
goodbye | +1.833 |
Neg logit contributions | |
chrom | -2.138 |
proof | -2.038 |
roit | -2.014 |
bos | -1.987 |
rans | -1.942 |
Token | in |
Token ID | 287 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
holiest | +2.230 |
emi | +2.166 |
athlet | +2.131 |
goodbye | +2.111 |
cean | +2.098 |
Neg logit contributions | |
chrom | -2.881 |
proof | -2.718 |
roit | -2.696 |
bos | -2.649 |
rans | -2.639 |
Token | fairness |
Token ID | 22692 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
holiest | +2.602 |
emi | +2.577 |
athlet | +2.534 |
cean | +2.514 |
goodbye | +2.480 |
Neg logit contributions | |
chrom | -3.775 |
proof | -3.586 |
roit | -3.540 |
rans | -3.488 |
eor | -3.466 |
Token | and |
Token ID | 290 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
holiest | +2.704 |
athlet | +2.619 |
emi | +2.617 |
goodbye | +2.585 |
cean | +2.564 |
Neg logit contributions | |
chrom | -3.605 |
proof | -3.413 |
roit | -3.361 |
bos | -3.313 |
eor | -3.301 |
Token | economics |
Token ID | 12446 |
Feature activation | +7.23e+00 |
Pos logit contributions | |
emi | +1.846 |
holiest | +1.823 |
cean | +1.811 |
athlet | +1.757 |
olicy | +1.749 |
Neg logit contributions | |
chrom | -2.506 |
proof | -2.400 |
roit | -2.377 |
bos | -2.279 |
rans | -2.272 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
holiest | +4.536 |
emi | +4.430 |
athlet | +4.388 |
goodbye | +4.351 |
cean | +4.295 |
Neg logit contributions | |
chrom | -6.246 |
proof | -5.873 |
roit | -5.862 |
eor | -5.740 |
rans | -5.711 |
Token | But |
Token ID | 887 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
holiest | +1.383 |
athlet | +1.378 |
emi | +1.331 |
cean | +1.299 |
goodbye | +1.288 |
Neg logit contributions | |
chrom | -1.904 |
proof | -1.824 |
roit | -1.794 |
rans | -1.759 |
eor | -1.743 |
Token | like |
Token ID | 588 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
holiest | +2.126 |
emi | +2.104 |
athlet | +2.047 |
cean | +2.045 |
olicy | +1.996 |
Neg logit contributions | |
chrom | -2.543 |
proof | -2.412 |
roit | -2.389 |
rans | -2.357 |
bos | -2.339 |
Token | most |
Token ID | 749 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
emi | +2.217 |
holiest | +2.183 |
athlet | +2.145 |
cean | +2.141 |
olicy | +2.069 |
Neg logit contributions | |
chrom | -3.059 |
proof | -2.905 |
roit | -2.887 |
bos | -2.821 |
rans | -2.815 |
Token | reforms |
Token ID | 12506 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
emi | +1.800 |
holiest | +1.788 |
cean | +1.758 |
athlet | +1.735 |
olicy | +1.711 |
Neg logit contributions | |
chrom | -2.291 |
proof | -2.180 |
roit | -2.178 |
rans | -2.126 |
bos | -2.111 |
Token | He |
Token ID | 679 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
holiest | +1.213 |
athlet | +1.157 |
cean | +1.137 |
goodbye | +1.134 |
bargaining | +1.133 |
Neg logit contributions | |
chrom | -1.552 |
proof | -1.462 |
roit | -1.460 |
bos | -1.426 |
rans | -1.412 |
Token | has |
Token ID | 468 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
olicy | +1.771 |
holiest | +1.770 |
QUI | +1.710 |
emi | +1.704 |
Lanka | +1.698 |
Neg logit contributions | |
chrom | -1.875 |
proof | -1.745 |
roit | -1.732 |
rans | -1.708 |
bos | -1.701 |
Token | one |
Token ID | 530 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
holiest | +2.294 |
olicy | +2.270 |
emi | +2.251 |
cean | +2.200 |
goodbye | +2.183 |
Neg logit contributions | |
chrom | -2.707 |
proof | -2.555 |
roit | -2.522 |
rans | -2.481 |
bos | -2.463 |
Token | year |
Token ID | 614 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
holiest | +1.782 |
olicy | +1.752 |
emi | +1.733 |
cean | +1.732 |
goodbye | +1.712 |
Neg logit contributions | |
chrom | -1.754 |
proof | -1.653 |
roit | -1.652 |
rans | -1.599 |
inant | -1.589 |
Token | and |
Token ID | 290 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
holiest | +2.225 |
emi | +2.152 |
Lanka | +2.100 |
cean | +2.092 |
olicy | +2.086 |
Neg logit contributions | |
chrom | -3.695 |
roit | -3.487 |
proof | -3.480 |
bos | -3.414 |
rans | -3.398 |
Token | $ |
Token ID | 720 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
holiest | +1.536 |
olicy | +1.522 |
cean | +1.515 |
emi | +1.492 |
Lanka | +1.486 |
Neg logit contributions | |
chrom | -2.444 |
proof | -2.360 |
roit | -2.330 |
bos | -2.255 |
rans | -2.254 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
holiest | +4.032 |
athlet | +3.956 |
emi | +3.908 |
goodbye | +3.852 |
bargaining | +3.834 |
Neg logit contributions | |
chrom | -4.355 |
proof | -4.052 |
roit | -4.018 |
eor | -3.914 |
rans | -3.914 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
holiest | +1.716 |
emi | +1.671 |
athlet | +1.657 |
goodbye | +1.655 |
cean | +1.635 |
Neg logit contributions | |
chrom | -2.423 |
roit | -2.273 |
proof | -2.267 |
bos | -2.221 |
rans | -2.218 |
Token | 35 |
Token ID | 2327 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
athlet | +1.292 |
holiest | +1.286 |
bargaining | +1.227 |
olicy | +1.220 |
emi | +1.211 |
Neg logit contributions | |
chrom | -1.239 |
proof | -1.160 |
roit | -1.121 |
bos | -1.115 |
rans | -1.115 |
Token | million |
Token ID | 1510 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
holiest | +2.268 |
emi | +2.213 |
athlet | +2.193 |
goodbye | +2.183 |
cean | +2.156 |
Neg logit contributions | |
chrom | -3.254 |
proof | -3.051 |
roit | -3.047 |
bos | -2.992 |
rans | -2.980 |
Token | left |
Token ID | 1364 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
holiest | +2.247 |
emi | +2.162 |
cean | +2.085 |
athlet | +2.080 |
goodbye | +2.064 |
Neg logit contributions | |
chrom | -4.419 |
roit | -4.217 |
proof | -4.201 |
bos | -4.135 |
rans | -4.128 |
Token | get |
Token ID | 1136 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
chrom | +0.441 |
roit | +0.397 |
proof | +0.395 |
eor | +0.390 |
bos | +0.387 |
Neg logit contributions | |
holiest | -0.795 |
athlet | -0.771 |
goodbye | -0.763 |
emi | -0.758 |
bargaining | -0.756 |
Token | tes |
Token ID | 4879 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
chrom | +0.452 |
roit | +0.419 |
proof | +0.398 |
rans | +0.390 |
eor | +0.388 |
Neg logit contributions | |
holiest | -1.194 |
goodbye | -1.164 |
Lanka | -1.151 |
athlet | -1.151 |
emi | -1.146 |
Token | , |
Token ID | 11 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
chrom | +0.900 |
roit | +0.842 |
proof | +0.838 |
bos | +0.837 |
eor | +0.824 |
Neg logit contributions | |
holiest | -0.773 |
olicy | -0.756 |
goodbye | -0.739 |
emi | -0.739 |
athlet | -0.737 |
Token | basil |
Token ID | 37792 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
holiest | +0.129 |
emi | +0.128 |
olicy | +0.126 |
athlet | +0.125 |
cean | +0.124 |
Neg logit contributions | |
chrom | -0.172 |
proof | -0.160 |
roit | -0.159 |
bos | -0.158 |
rans | -0.154 |
Token | and |
Token ID | 290 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
chrom | +1.204 |
proof | +1.147 |
roit | +1.137 |
bos | +1.123 |
obyl | +1.113 |
Neg logit contributions | |
holiest | -1.022 |
olicy | -1.005 |
emi | -1.003 |
athlet | -0.987 |
cean | -0.974 |
Token | spinach |
Token ID | 39129 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
emi | +0.871 |
holiest | +0.869 |
olicy | +0.852 |
cean | +0.846 |
athlet | +0.843 |
Neg logit contributions | |
chrom | -1.151 |
proof | -1.072 |
roit | -1.060 |
bos | -1.051 |
obyl | -1.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
holiest | +3.731 |
emi | +3.661 |
athlet | +3.609 |
goodbye | +3.582 |
cean | +3.542 |
Neg logit contributions | |
chrom | -5.293 |
roit | -4.963 |
proof | -4.959 |
eor | -4.846 |
bos | -4.843 |
Token | and |
Token ID | 290 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
holiest | +0.882 |
emi | +0.875 |
olicy | +0.868 |
cean | +0.862 |
athlet | +0.849 |
Neg logit contributions | |
chrom | -1.012 |
proof | -0.945 |
roit | -0.937 |
bos | -0.936 |
rans | -0.908 |
Token | named |
Token ID | 3706 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
holiest | +1.836 |
emi | +1.836 |
olicy | +1.801 |
cean | +1.784 |
Lanka | +1.766 |
Neg logit contributions | |
chrom | -1.576 |
proof | -1.452 |
roit | -1.441 |
bos | -1.422 |
rans | -1.389 |
Token | in |
Token ID | 287 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
chrom | +0.361 |
proof | +0.342 |
roit | +0.334 |
bos | +0.331 |
eor | +0.329 |
Neg logit contributions | |
holiest | -0.342 |
emi | -0.341 |
athlet | -0.335 |
olicy | -0.332 |
cean | -0.332 |
Token | her |
Token ID | 607 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
holiest | +1.571 |
athlet | +1.569 |
olicy | +1.565 |
emi | +1.559 |
cean | +1.499 |
Neg logit contributions | |
chrom | -3.054 |
proof | -2.874 |
roit | -2.860 |
rans | -2.844 |
bos | -2.812 |
Token | it |
Token ID | 340 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
holiest | +1.024 |
emi | +1.014 |
athlet | +1.011 |
cean | +1.010 |
olicy | +0.989 |
Neg logit contributions | |
chrom | -1.077 |
proof | -1.027 |
roit | -1.005 |
eor | -0.984 |
rans | -0.980 |
Token | , |
Token ID | 11 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
holiest | +1.785 |
emi | +1.680 |
cean | +1.675 |
Lanka | +1.663 |
athlet | +1.660 |
Neg logit contributions | |
chrom | -2.354 |
proof | -2.201 |
roit | -2.191 |
eor | -2.143 |
rans | -2.141 |
Token | � |
Token ID | 447 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
holiest | +1.911 |
emi | +1.833 |
cean | +1.822 |
Lanka | +1.806 |
athlet | +1.804 |
Neg logit contributions | |
chrom | -2.346 |
proof | -2.201 |
roit | -2.199 |
rans | -2.159 |
bos | -2.118 |
Token | � |
Token ID | 251 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
holiest | +2.113 |
athlet | +2.100 |
emi | +2.095 |
cean | +2.053 |
olicy | +2.049 |
Neg logit contributions | |
chrom | -2.002 |
roit | -1.889 |
proof | -1.867 |
rans | -1.836 |
eor | -1.800 |
Token | said |
Token ID | 531 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
holiest | +0.536 |
athlet | +0.522 |
emi | +0.519 |
cean | +0.513 |
goodbye | +0.512 |
Neg logit contributions | |
chrom | -0.590 |
proof | -0.550 |
roit | -0.547 |
rans | -0.532 |
eor | -0.527 |
Token | Ryan |
Token ID | 6047 |
Feature activation | +7.09e+00 |
Pos logit contributions | |
holiest | +1.295 |
emi | +1.263 |
athlet | +1.259 |
cean | +1.245 |
olicy | +1.221 |
Neg logit contributions | |
chrom | -1.835 |
roit | -1.742 |
proof | -1.734 |
rans | -1.682 |
bos | -1.678 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
holiest | +4.245 |
emi | +4.145 |
athlet | +4.107 |
goodbye | +4.086 |
cean | +4.018 |
Neg logit contributions | |
chrom | -6.270 |
roit | -5.906 |
proof | -5.885 |
eor | -5.774 |
bos | -5.749 |
Token | attribut |
Token ID | 24548 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
holiest | +2.017 |
emi | +1.983 |
athlet | +1.960 |
cean | +1.939 |
olicy | +1.916 |
Neg logit contributions | |
chrom | -2.114 |
proof | -1.976 |
roit | -1.973 |
rans | -1.928 |
bos | -1.906 |
Token | ing |
Token ID | 278 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
holiest | +2.998 |
athlet | +2.953 |
goodbye | +2.926 |
emi | +2.894 |
olicy | +2.882 |
Neg logit contributions | |
chrom | -1.719 |
roit | -1.598 |
proof | -1.593 |
eor | -1.550 |
inant | -1.520 |
Token | the |
Token ID | 262 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
holiest | +1.714 |
athlet | +1.686 |
emi | +1.663 |
cean | +1.658 |
goodbye | +1.634 |
Neg logit contributions | |
chrom | -2.269 |
proof | -2.155 |
roit | -2.146 |
eor | -2.088 |
rans | -2.077 |
Token | foul |
Token ID | 15626 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
holiest | +2.067 |
emi | +2.054 |
cean | +2.041 |
athlet | +2.023 |
goodbye | +2.022 |
Neg logit contributions | |
chrom | -2.108 |
roit | -1.951 |
proof | -1.940 |
rans | -1.888 |
eor | -1.887 |
Token | , |
Token ID | 11 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
holiest | +2.685 |
emi | +2.572 |
athlet | +2.544 |
Lanka | +2.534 |
cean | +2.526 |
Neg logit contributions | |
chrom | -3.395 |
roit | -3.189 |
proof | -3.178 |
eor | -3.113 |
bos | -3.108 |
Token | you |
Token ID | 345 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
holiest | +2.136 |
emi | +2.109 |
cean | +2.072 |
athlet | +2.052 |
Lanka | +2.050 |
Neg logit contributions | |
chrom | -2.320 |
proof | -2.182 |
roit | -2.149 |
eor | -2.126 |
rans | -2.116 |
Token | will |
Token ID | 481 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
holiest | +1.915 |
olicy | +1.889 |
emi | +1.884 |
Lanka | +1.857 |
cean | +1.854 |
Neg logit contributions | |
chrom | -1.560 |
proof | -1.442 |
roit | -1.400 |
rans | -1.393 |
bos | -1.383 |
Token | get |
Token ID | 651 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
olicy | +1.464 |
holiest | +1.462 |
emi | +1.458 |
cean | +1.432 |
Lanka | +1.428 |
Neg logit contributions | |
chrom | -0.963 |
proof | -0.895 |
rans | -0.872 |
roit | -0.859 |
bos | -0.844 |
Token | a |
Token ID | 257 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
holiest | +1.765 |
emi | +1.762 |
cean | +1.736 |
olicy | +1.717 |
athlet | +1.704 |
Neg logit contributions | |
chrom | -2.634 |
proof | -2.538 |
roit | -2.444 |
bos | -2.434 |
rans | -2.419 |
Token | $ |
Token ID | 720 |
Feature activation | +6.40e+00 |
Pos logit contributions | |
emi | +2.190 |
holiest | +2.186 |
olicy | +2.142 |
athlet | +2.131 |
cean | +2.129 |
Neg logit contributions | |
chrom | -2.814 |
proof | -2.667 |
roit | -2.597 |
rans | -2.554 |
bos | -2.548 |
Token | 1 |
Token ID | 16 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
holiest | +4.443 |
emi | +4.349 |
athlet | +4.331 |
goodbye | +4.274 |
bargaining | +4.220 |
Neg logit contributions | |
chrom | -5.108 |
proof | -4.761 |
roit | -4.735 |
eor | -4.625 |
rans | -4.621 |
Token | , |
Token ID | 11 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
holiest | +2.321 |
emi | +2.286 |
goodbye | +2.246 |
athlet | +2.236 |
bargaining | +2.198 |
Neg logit contributions | |
chrom | -3.669 |
roit | -3.463 |
proof | -3.433 |
eor | -3.399 |
obyl | -3.380 |
Token | 000 |
Token ID | 830 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
holiest | +2.067 |
emi | +2.016 |
athlet | +2.014 |
goodbye | +1.975 |
Lanka | +1.960 |
Neg logit contributions | |
chrom | -2.644 |
proof | -2.466 |
roit | -2.442 |
rans | -2.410 |
eor | -2.398 |
Token | check |
Token ID | 2198 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
holiest | +4.114 |
emi | +4.061 |
athlet | +3.996 |
cean | +3.978 |
Lanka | +3.956 |
Neg logit contributions | |
chrom | -2.762 |
proof | -2.554 |
roit | -2.520 |
eor | -2.435 |
rans | -2.434 |
Token | from |
Token ID | 422 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
holiest | +1.317 |
emi | +1.251 |
olicy | +1.242 |
Lanka | +1.239 |
cean | +1.232 |
Neg logit contributions | |
chrom | -1.733 |
proof | -1.659 |
roit | -1.633 |
eor | -1.589 |
rans | -1.587 |
Token | own |
Token ID | 898 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
holiest | +0.656 |
emi | +0.654 |
cean | +0.641 |
olicy | +0.638 |
athlet | +0.631 |
Neg logit contributions | |
chrom | -0.811 |
roit | -0.766 |
proof | -0.762 |
eor | -0.758 |
rans | -0.744 |
Token | John |
Token ID | 1757 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
emi | +0.829 |
holiest | +0.812 |
cean | +0.794 |
olicy | +0.792 |
Lanka | +0.778 |
Neg logit contributions | |
chrom | -0.988 |
proof | -0.940 |
roit | -0.932 |
eor | -0.916 |
rans | -0.908 |
Token | Mu |
Token ID | 8252 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
chrom | +0.294 |
roit | +0.278 |
proof | +0.278 |
eor | +0.273 |
obyl | +0.272 |
Neg logit contributions | |
holiest | -0.154 |
emi | -0.151 |
athlet | -0.149 |
goodbye | -0.148 |
cean | -0.146 |
Token | ir |
Token ID | 343 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
holiest | +1.854 |
athlet | +1.824 |
emi | +1.795 |
goodbye | +1.793 |
olicy | +1.782 |
Neg logit contributions | |
chrom | -0.801 |
proof | -0.726 |
roit | -0.716 |
eor | -0.697 |
rans | -0.696 |
Token | hike |
Token ID | 18390 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
chrom | +0.444 |
proof | +0.423 |
rans | +0.407 |
eor | +0.405 |
roit | +0.404 |
Neg logit contributions | |
emi | -0.395 |
holiest | -0.393 |
cean | -0.377 |
athlet | -0.376 |
olicy | -0.375 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
holiest | +2.352 |
emi | +2.316 |
athlet | +2.254 |
goodbye | +2.241 |
bargaining | +2.233 |
Neg logit contributions | |
chrom | -3.071 |
proof | -2.913 |
roit | -2.864 |
eor | -2.819 |
rans | -2.807 |
Token | Bob |
Token ID | 5811 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
athlet | +0.745 |
holiest | +0.737 |
emi | +0.715 |
olicy | +0.709 |
goodbye | +0.708 |
Neg logit contributions | |
chrom | -0.931 |
proof | -0.873 |
roit | -0.854 |
eor | -0.844 |
bos | -0.841 |
Token | In |
Token ID | 554 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
chrom | +1.589 |
proof | +1.508 |
roit | +1.491 |
bos | +1.481 |
eor | +1.460 |
Neg logit contributions | |
holiest | -1.122 |
athlet | -1.077 |
goodbye | -1.065 |
bargaining | -1.054 |
emi | -1.053 |
Token | man |
Token ID | 805 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
holiest | +2.841 |
goodbye | +2.797 |
athlet | +2.761 |
emi | +2.715 |
bargaining | +2.709 |
Neg logit contributions | |
chrom | -2.399 |
proof | -2.189 |
roit | -2.161 |
eor | -2.141 |
rans | -2.120 |
Token | had |
Token ID | 550 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
chrom | +0.506 |
proof | +0.481 |
roit | +0.466 |
bos | +0.463 |
rans | +0.462 |
Neg logit contributions | |
holiest | -0.450 |
olicy | -0.435 |
Lanka | -0.433 |
athlet | -0.432 |
goodbye | -0.432 |
Token | written |
Token ID | 3194 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
holiest | +0.112 |
olicy | +0.111 |
emi | +0.109 |
Lanka | +0.107 |
cean | +0.106 |
Neg logit contributions | |
chrom | -0.120 |
proof | -0.113 |
rans | -0.109 |
roit | -0.109 |
bos | -0.108 |
Token | ama |
Token ID | 1689 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
holiest | +2.168 |
athlet | +2.093 |
goodbye | +2.073 |
emi | +2.072 |
bargaining | +2.059 |
Neg logit contributions | |
chrom | -2.600 |
roit | -2.455 |
proof | -2.436 |
eor | -2.411 |
rans | -2.403 |
Token | i |
Token ID | 72 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
holiest | +0.969 |
athlet | +0.928 |
olicy | +0.922 |
bargaining | +0.917 |
goodbye | +0.916 |
Neg logit contributions | |
chrom | -1.060 |
roit | -0.992 |
proof | -0.984 |
eor | -0.981 |
rans | -0.974 |
Token | , |
Token ID | 11 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
holiest | +1.277 |
athlet | +1.224 |
olicy | +1.219 |
emi | +1.207 |
bargaining | +1.207 |
Neg logit contributions | |
chrom | -1.657 |
roit | -1.570 |
proof | -1.544 |
rans | -1.536 |
eor | -1.534 |
Token | k |
Token ID | 479 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
holiest | +0.649 |
emi | +0.624 |
olicy | +0.623 |
athlet | +0.622 |
cean | +0.618 |
Neg logit contributions | |
chrom | -0.835 |
roit | -0.780 |
rans | -0.776 |
eor | -0.773 |
proof | -0.772 |
Token | ū |
Token ID | 20317 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
holiest | +1.272 |
bargaining | +1.230 |
athlet | +1.229 |
goodbye | +1.221 |
forgiveness | +1.202 |
Neg logit contributions | |
chrom | -0.960 |
roit | -0.899 |
eor | -0.883 |
proof | -0.882 |
rans | -0.877 |
Token | pa |
Token ID | 8957 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
holiest | +1.032 |
athlet | +0.992 |
bargaining | +0.983 |
emi | +0.982 |
goodbye | +0.981 |
Neg logit contributions | |
chrom | -0.990 |
roit | -0.920 |
proof | -0.912 |
eor | -0.909 |
rans | -0.905 |
Token | � |
Token ID | 134 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
holiest | +2.350 |
athlet | +2.258 |
emi | +2.242 |
goodbye | +2.235 |
bargaining | +2.227 |
Neg logit contributions | |
chrom | -2.697 |
roit | -2.519 |
proof | -2.504 |
eor | -2.477 |
rans | -2.464 |
Token | � |
Token ID | 119 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
holiest | +3.888 |
athlet | +3.826 |
emi | +3.805 |
goodbye | +3.776 |
cean | +3.745 |
Neg logit contributions | |
chrom | -2.800 |
proof | -2.534 |
roit | -2.526 |
eor | -2.483 |
obyl | -2.461 |
Token | a |
Token ID | 64 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
chrom | +1.308 |
eor | +1.221 |
rans | +1.195 |
roit | +1.194 |
proof | +1.185 |
Neg logit contributions | |
holiest | -2.288 |
bargaining | -2.194 |
athlet | -2.192 |
goodbye | -2.175 |
CONCLUS | -2.145 |
Token | , |
Token ID | 11 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
holiest | +0.548 |
olicy | +0.522 |
athlet | +0.521 |
bargaining | +0.516 |
goodbye | +0.516 |
Neg logit contributions | |
chrom | -0.676 |
roit | -0.637 |
eor | -0.626 |
proof | -0.626 |
rans | -0.624 |
Token | al |
Token ID | 435 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
holiest | +0.586 |
emi | +0.560 |
olicy | +0.560 |
athlet | +0.559 |
cean | +0.557 |
Neg logit contributions | |
chrom | -0.746 |
roit | -0.699 |
rans | -0.691 |
proof | -0.690 |
eor | -0.690 |
Token | > |
Token ID | 29 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
chrom | +2.964 |
proof | +2.777 |
roit | +2.710 |
bos | +2.678 |
rans | +2.624 |
Neg logit contributions | |
holiest | -3.681 |
goodbye | -3.488 |
bargaining | -3.477 |
Lanka | -3.441 |
athlet | -3.426 |
Token | lol |
Token ID | 19462 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
emi | +0.197 |
holiest | +0.195 |
olicy | +0.194 |
cean | +0.192 |
QUI | +0.189 |
Neg logit contributions | |
chrom | -0.243 |
proof | -0.224 |
roit | -0.224 |
bos | -0.222 |
eor | -0.219 |
Token | m |
Token ID | 285 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
holiest | +0.945 |
emi | +0.931 |
athlet | +0.912 |
bargaining | +0.910 |
olicy | +0.910 |
Neg logit contributions | |
chrom | -1.030 |
proof | -0.949 |
roit | -0.948 |
bos | -0.929 |
eor | -0.927 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
holiest | +0.059 |
emi | +0.058 |
athlet | +0.057 |
goodbye | +0.057 |
cean | +0.056 |
Neg logit contributions | |
chrom | -0.082 |
roit | -0.077 |
proof | -0.077 |
eor | -0.075 |
obyl | -0.075 |
Token | k |
Token ID | 74 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
chrom | +1.344 |
proof | +1.249 |
roit | +1.194 |
eor | +1.192 |
bos | +1.189 |
Neg logit contributions | |
holiest | -1.738 |
athlet | -1.714 |
olicy | -1.669 |
emi | -1.655 |
bargaining | -1.622 |
Token | [ |
Token ID | 685 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
chrom | +0.239 |
proof | +0.223 |
roit | +0.223 |
eor | +0.218 |
bos | +0.218 |
Neg logit contributions | |
holiest | -0.177 |
emi | -0.175 |
athlet | -0.172 |
cean | -0.170 |
olicy | -0.169 |
Token | 10 |
Token ID | 940 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
athlet | +0.339 |
holiest | +0.338 |
olicy | +0.326 |
bargaining | +0.322 |
emi | +0.321 |
Neg logit contributions | |
chrom | -0.294 |
proof | -0.273 |
bos | -0.261 |
roit | -0.259 |
eor | -0.259 |
Token | : |
Token ID | 25 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
athlet | +0.702 |
holiest | +0.700 |
olicy | +0.680 |
emi | +0.673 |
bargaining | +0.662 |
Neg logit contributions | |
chrom | -0.674 |
proof | -0.637 |
roit | -0.608 |
eor | -0.603 |
bos | -0.601 |
Token | 47 |
Token ID | 2857 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
athlet | +0.474 |
holiest | +0.470 |
olicy | +0.457 |
emi | +0.451 |
bargaining | +0.449 |
Neg logit contributions | |
chrom | -0.400 |
proof | -0.364 |
eor | -0.355 |
rans | -0.348 |
roit | -0.346 |
Token | ] |
Token ID | 60 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
chrom | +2.908 |
proof | +2.718 |
rans | +2.539 |
eor | +2.514 |
roit | +2.490 |
Neg logit contributions | |
athlet | -3.793 |
holiest | -3.702 |
referen | -3.670 |
nomine | -3.649 |
olicy | -3.619 |
Token | < |
Token ID | 1279 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
chrom | +0.127 |
proof | +0.119 |
roit | +0.119 |
eor | +0.117 |
obyl | +0.116 |
Neg logit contributions | |
holiest | -0.086 |
emi | -0.084 |
goodbye | -0.083 |
athlet | -0.083 |
bargaining | -0.081 |
Token | of |
Token ID | 286 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
holiest | +1.707 |
emi | +1.678 |
cean | +1.672 |
olicy | +1.633 |
Lanka | +1.630 |
Neg logit contributions | |
chrom | -2.683 |
proof | -2.593 |
roit | -2.560 |
rans | -2.504 |
bos | -2.494 |
Token | the |
Token ID | 262 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
holiest | +1.860 |
emi | +1.850 |
cean | +1.818 |
athlet | +1.773 |
Lanka | +1.761 |
Neg logit contributions | |
chrom | -2.332 |
proof | -2.277 |
roit | -2.174 |
bos | -2.140 |
rans | -2.131 |
Token | business |
Token ID | 1597 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
holiest | +1.747 |
emi | +1.728 |
cean | +1.725 |
olicy | +1.689 |
Lanka | +1.658 |
Neg logit contributions | |
chrom | -1.908 |
proof | -1.861 |
roit | -1.781 |
bos | -1.742 |
rans | -1.731 |
Token | ; |
Token ID | 26 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
holiest | +1.652 |
cean | +1.600 |
emi | +1.597 |
Lanka | +1.581 |
olicy | +1.564 |
Neg logit contributions | |
chrom | -1.979 |
proof | -1.918 |
roit | -1.847 |
rans | -1.817 |
eor | -1.803 |
Token | having |
Token ID | 1719 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
holiest | +1.916 |
emi | +1.915 |
Lanka | +1.832 |
olicy | +1.827 |
cean | +1.824 |
Neg logit contributions | |
chrom | -2.235 |
proof | -2.149 |
roit | -2.103 |
rans | -2.065 |
bos | -2.047 |
Token | [ |
Token ID | 685 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
holiest | +1.365 |
emi | +1.351 |
cean | +1.322 |
olicy | +1.316 |
athlet | +1.298 |
Neg logit contributions | |
chrom | -1.707 |
proof | -1.644 |
bos | -1.569 |
roit | -1.558 |
rans | -1.542 |
Token | a |
Token ID | 64 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
holiest | +2.858 |
athlet | +2.778 |
emi | +2.760 |
goodbye | +2.751 |
Lanka | +2.735 |
Neg logit contributions | |
chrom | -1.917 |
proof | -1.778 |
roit | -1.702 |
rans | -1.689 |
bos | -1.678 |
Token | big |
Token ID | 1263 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
holiest | +1.798 |
emi | +1.789 |
cean | +1.737 |
olicy | +1.714 |
athlet | +1.714 |
Neg logit contributions | |
chrom | -2.476 |
proof | -2.336 |
roit | -2.315 |
rans | -2.264 |
bos | -2.242 |
Token | ] |
Token ID | 60 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
holiest | +2.268 |
emi | +2.226 |
athlet | +2.156 |
cean | +2.156 |
Lanka | +2.121 |
Neg logit contributions | |
chrom | -2.563 |
proof | -2.432 |
roit | -2.393 |
rans | -2.340 |
eor | -2.327 |
Token | enough |
Token ID | 1576 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
emi | +1.221 |
holiest | +1.214 |
cean | +1.185 |
assi | +1.166 |
olicy | +1.163 |
Neg logit contributions | |
chrom | -1.402 |
proof | -1.350 |
roit | -1.303 |
bos | -1.287 |
rans | -1.274 |
Token | premium |
Token ID | 8683 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
holiest | +3.180 |
emi | +3.178 |
cean | +3.066 |
olicy | +3.020 |
athlet | +3.010 |
Neg logit contributions | |
chrom | -3.586 |
proof | -3.418 |
roit | -3.316 |
bos | -3.262 |
rans | -3.250 |
Token | y |
Token ID | 88 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
holiest | +0.200 |
olicy | +0.196 |
emi | +0.195 |
athlet | +0.193 |
cean | +0.193 |
Neg logit contributions | |
chrom | -0.100 |
proof | -0.095 |
roit | -0.090 |
eor | -0.087 |
rans | -0.087 |
Token | would |
Token ID | 561 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
emi | +1.232 |
holiest | +1.213 |
athlet | +1.169 |
cean | +1.162 |
Lanka | +1.162 |
Neg logit contributions | |
chrom | -1.299 |
proof | -1.244 |
roit | -1.204 |
bos | -1.189 |
rans | -1.161 |
Token | pay |
Token ID | 1414 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
chrom | +0.096 |
proof | +0.089 |
roit | +0.088 |
rans | +0.087 |
eor | +0.085 |
Neg logit contributions | |
holiest | -0.130 |
olicy | -0.126 |
emi | -0.125 |
assi | -0.123 |
cean | -0.123 |
Token | off |
Token ID | 572 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
holiest | +1.525 |
cean | +1.472 |
emi | +1.445 |
olicy | +1.442 |
athlet | +1.426 |
Neg logit contributions | |
chrom | -3.280 |
proof | -3.177 |
roit | -3.147 |
bos | -3.079 |
rans | -3.064 |
Token | , |
Token ID | 11 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
holiest | +0.492 |
emi | +0.472 |
olicy | +0.469 |
Lanka | +0.468 |
assi | +0.461 |
Neg logit contributions | |
chrom | -0.548 |
proof | -0.517 |
roit | -0.504 |
rans | -0.500 |
bos | -0.499 |
Token | and |
Token ID | 290 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
holiest | +0.547 |
emi | +0.533 |
olicy | +0.524 |
Lanka | +0.517 |
cean | +0.513 |
Neg logit contributions | |
chrom | -0.653 |
proof | -0.621 |
roit | -0.603 |
rans | -0.603 |
bos | -0.593 |
Token | that |
Token ID | 326 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
holiest | +1.223 |
emi | +1.218 |
olicy | +1.184 |
athlet | +1.172 |
cean | +1.166 |
Neg logit contributions | |
chrom | -1.417 |
proof | -1.346 |
roit | -1.324 |
rans | -1.303 |
eor | -1.294 |
Token | it |
Token ID | 340 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
chrom | +1.141 |
proof | +1.082 |
roit | +1.042 |
rans | +1.013 |
bos | +1.006 |
Neg logit contributions | |
emi | -1.113 |
holiest | -1.109 |
olicy | -1.076 |
athlet | -1.076 |
Lanka | -1.064 |
Token | would |
Token ID | 561 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
holiest | +0.666 |
olicy | +0.641 |
emi | +0.640 |
Lanka | +0.637 |
athlet | +0.631 |
Neg logit contributions | |
chrom | -0.736 |
proof | -0.687 |
roit | -0.685 |
obyl | -0.670 |
eor | -0.668 |
Token | come |
Token ID | 1282 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
chrom | +0.252 |
proof | +0.235 |
roit | +0.233 |
rans | +0.227 |
eor | +0.227 |
Neg logit contributions | |
holiest | -0.340 |
olicy | -0.331 |
emi | -0.329 |
QUI | -0.323 |
assi | -0.322 |
Token | to |
Token ID | 284 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
emi | +1.171 |
holiest | +1.154 |
cean | +1.145 |
olicy | +1.112 |
assi | +1.098 |
Neg logit contributions | |
chrom | -1.352 |
proof | -1.286 |
bos | -1.265 |
roit | -1.242 |
rans | -1.221 |
Token | L |
Token ID | 406 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
holiest | +2.048 |
emi | +2.030 |
cean | +1.981 |
olicy | +1.977 |
Lanka | +1.969 |
Neg logit contributions | |
chrom | -2.280 |
roit | -2.176 |
proof | -2.148 |
rans | -2.113 |
eor | -2.073 |
Token | sound |
Token ID | 2128 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
holiest | +2.213 |
emi | +2.156 |
athlet | +2.123 |
goodbye | +2.109 |
cean | +2.108 |
Neg logit contributions | |
chrom | -2.610 |
roit | -2.453 |
proof | -2.436 |
rans | -2.379 |
bos | -2.367 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
holiest | +1.324 |
emi | +1.278 |
Lanka | +1.278 |
athlet | +1.255 |
cean | +1.254 |
Neg logit contributions | |
chrom | -1.705 |
proof | -1.618 |
roit | -1.587 |
rans | -1.558 |
inant | -1.548 |
Token | something |
Token ID | 1223 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
holiest | +0.836 |
emi | +0.818 |
olicy | +0.809 |
Lanka | +0.789 |
cean | +0.787 |
Neg logit contributions | |
chrom | -1.036 |
proof | -0.975 |
roit | -0.970 |
rans | -0.952 |
eor | -0.944 |
Token | that |
Token ID | 326 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
holiest | +2.271 |
emi | +2.253 |
olicy | +2.244 |
cean | +2.212 |
bargaining | +2.164 |
Neg logit contributions | |
chrom | -2.857 |
proof | -2.693 |
roit | -2.665 |
bos | -2.596 |
rans | -2.592 |
Token | Phil |
Token ID | 4543 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
chrom | +1.128 |
proof | +1.050 |
roit | +1.050 |
rans | +1.019 |
bos | +1.015 |
Neg logit contributions | |
olicy | -1.037 |
emi | -1.023 |
holiest | -1.021 |
cean | -0.984 |
goodbye | -0.963 |
Token | adel |
Token ID | 6959 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
chrom | +0.870 |
proof | +0.805 |
bos | +0.796 |
roit | +0.788 |
inant | +0.768 |
Neg logit contributions | |
holiest | -0.743 |
emi | -0.716 |
goodbye | -0.709 |
olicy | -0.707 |
bargaining | -0.698 |
Token | ph |
Token ID | 746 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
chrom | +0.532 |
proof | +0.483 |
bos | +0.481 |
roit | +0.480 |
rans | +0.450 |
Neg logit contributions | |
holiest | -1.302 |
goodbye | -1.260 |
Lanka | -1.248 |
bargaining | -1.242 |
athlet | -1.238 |
Token | ians |
Token ID | 1547 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
holiest | +0.322 |
goodbye | +0.312 |
cean | +0.311 |
emi | +0.311 |
athlet | +0.309 |
Neg logit contributions | |
chrom | -0.155 |
roit | -0.150 |
proof | -0.146 |
eor | -0.142 |
rans | -0.142 |
Token | do |
Token ID | 466 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
holiest | +1.420 |
emi | +1.386 |
olicy | +1.377 |
cean | +1.363 |
Lanka | +1.358 |
Neg logit contributions | |
chrom | -1.377 |
proof | -1.276 |
roit | -1.271 |
rans | -1.254 |
eor | -1.236 |
Token | more |
Token ID | 517 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
holiest | +0.692 |
emi | +0.671 |
Lanka | +0.670 |
cean | +0.662 |
olicy | +0.661 |
Neg logit contributions | |
chrom | -0.935 |
proof | -0.874 |
roit | -0.872 |
eor | -0.864 |
rans | -0.863 |
Token | using |
Token ID | 1262 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
olicy | +0.007 |
holiest | +0.007 |
emi | +0.007 |
cean | +0.007 |
Lanka | +0.007 |
Neg logit contributions | |
chrom | -0.009 |
proof | -0.008 |
roit | -0.008 |
rans | -0.008 |
bos | -0.008 |
Token | your |
Token ID | 534 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
chrom | +0.581 |
proof | +0.554 |
roit | +0.545 |
bos | +0.532 |
eor | +0.519 |
Neg logit contributions | |
olicy | -0.447 |
holiest | -0.446 |
cean | -0.438 |
goodbye | -0.433 |
emi | -0.431 |
Token | new |
Token ID | 649 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
holiest | +0.355 |
cean | +0.355 |
emi | +0.354 |
olicy | +0.352 |
goodbye | +0.351 |
Neg logit contributions | |
chrom | -0.467 |
roit | -0.444 |
proof | -0.441 |
bos | -0.432 |
inant | -0.421 |
Token | found |
Token ID | 1043 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
chrom | +0.678 |
proof | +0.645 |
roit | +0.636 |
bos | +0.621 |
inant | +0.606 |
Neg logit contributions | |
holiest | -0.600 |
cean | -0.591 |
emi | -0.589 |
olicy | -0.584 |
goodbye | -0.579 |
Token | Deep |
Token ID | 10766 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
chrom | +1.018 |
roit | +0.982 |
proof | +0.977 |
bos | +0.945 |
inant | +0.926 |
Neg logit contributions | |
holiest | -0.737 |
emi | -0.735 |
cean | -0.735 |
goodbye | -0.727 |
olicy | -0.726 |
Token | Conf |
Token ID | 7326 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
holiest | +0.492 |
goodbye | +0.483 |
athlet | +0.469 |
olicy | +0.469 |
emi | +0.464 |
Neg logit contributions | |
chrom | -0.595 |
proof | -0.566 |
roit | -0.563 |
bos | -0.553 |
rans | -0.542 |
Token | idence |
Token ID | 1704 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
chrom | +0.791 |
proof | +0.718 |
roit | +0.711 |
inant | +0.690 |
rans | +0.687 |
Neg logit contributions | |
goodbye | -1.416 |
holiest | -1.414 |
athlet | -1.385 |
Lanka | -1.364 |
bargaining | -1.337 |
Token | . |
Token ID | 13 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
chrom | +0.191 |
proof | +0.184 |
roit | +0.182 |
bos | +0.176 |
inant | +0.175 |
Neg logit contributions | |
holiest | -0.170 |
olicy | -0.163 |
goodbye | -0.163 |
emi | -0.163 |
Lanka | -0.158 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
holiest | +0.425 |
athlet | +0.418 |
olicy | +0.414 |
emi | +0.403 |
goodbye | +0.399 |
Neg logit contributions | |
chrom | -0.480 |
proof | -0.455 |
roit | -0.446 |
eor | -0.432 |
bos | -0.430 |
Token |
|
Token ID | 198 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
athlet | +0.751 |
holiest | +0.749 |
olicy | +0.723 |
emi | +0.713 |
bargaining | +0.702 |
Neg logit contributions | |
chrom | -0.848 |
proof | -0.802 |
roit | -0.771 |
eor | -0.758 |
bos | -0.758 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
holiest | +0.714 |
athlet | +0.709 |
olicy | +0.694 |
Lanka | +0.689 |
goodbye | +0.682 |
Neg logit contributions | |
chrom | -0.779 |
proof | -0.733 |
roit | -0.703 |
bos | -0.696 |
eor | -0.687 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
chrom | +0.784 |
proof | +0.745 |
roit | +0.702 |
rans | +0.695 |
eor | +0.693 |
Neg logit contributions | |
athlet | -0.776 |
holiest | -0.764 |
olicy | -0.745 |
emi | -0.724 |
bargaining | -0.717 |
Token | About |
Token ID | 8585 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
chrom | +0.831 |
proof | +0.790 |
roit | +0.749 |
rans | +0.746 |
bos | +0.738 |
Neg logit contributions | |
athlet | -0.809 |
holiest | -0.792 |
olicy | -0.783 |
Lanka | -0.779 |
bargaining | -0.778 |
Token | former |
Token ID | 1966 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
chrom | +0.340 |
proof | +0.328 |
rans | +0.320 |
roit | +0.319 |
eor | +0.310 |
Neg logit contributions | |
emi | -0.267 |
cean | -0.265 |
holiest | -0.263 |
olicy | -0.262 |
athlet | -0.261 |
Token | meth |
Token ID | 11248 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
chrom | +1.962 |
proof | +1.881 |
roit | +1.823 |
rans | +1.812 |
bos | +1.790 |
Neg logit contributions | |
emi | -1.536 |
olicy | -1.518 |
cean | -1.490 |
athlet | -1.485 |
ofi | -1.469 |
Token | dealer |
Token ID | 16456 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
chrom | +0.834 |
proof | +0.799 |
roit | +0.770 |
inant | +0.766 |
rans | +0.765 |
Neg logit contributions | |
emi | -0.650 |
holiest | -0.650 |
athlet | -0.629 |
cean | -0.625 |
olicy | -0.622 |
Token | and |
Token ID | 290 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
chrom | +0.976 |
proof | +0.939 |
roit | +0.919 |
rans | +0.904 |
eor | +0.894 |
Neg logit contributions | |
emi | -0.741 |
holiest | -0.735 |
cean | -0.726 |
olicy | -0.721 |
athlet | -0.716 |
Token | escort |
Token ID | 27675 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
chrom | +0.933 |
proof | +0.903 |
roit | +0.897 |
rans | +0.873 |
bos | +0.860 |
Neg logit contributions | |
emi | -0.758 |
olicy | -0.750 |
cean | -0.742 |
QUI | -0.718 |
holiest | -0.716 |
Token | Mike |
Token ID | 4995 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
chrom | +1.170 |
proof | +1.121 |
roit | +1.097 |
eor | +1.071 |
rans | +1.062 |
Neg logit contributions | |
emi | -0.871 |
holiest | -0.861 |
cean | -0.835 |
externalActionCode | -0.826 |
athlet | -0.826 |
Token | Jones |
Token ID | 5437 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
chrom | +0.711 |
proof | +0.672 |
roit | +0.663 |
bos | +0.658 |
eor | +0.653 |
Neg logit contributions | |
holiest | -0.514 |
athlet | -0.506 |
emi | -0.498 |
goodbye | -0.492 |
bargaining | -0.488 |
Token | , |
Token ID | 11 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
chrom | +1.286 |
proof | +1.216 |
roit | +1.196 |
obyl | +1.170 |
rans | +1.167 |
Neg logit contributions | |
holiest | -1.179 |
athlet | -1.157 |
olicy | -1.136 |
emi | -1.132 |
cean | -1.125 |
Token | H |
Token ID | 367 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
chrom | +1.087 |
proof | +1.024 |
roit | +1.015 |
rans | +1.002 |
bos | +0.974 |
Neg logit contributions | |
emi | -0.957 |
athlet | -0.956 |
cean | -0.956 |
holiest | -0.954 |
olicy | -0.948 |
Token | also |
Token ID | 635 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
chrom | +2.219 |
proof | +2.056 |
rans | +2.030 |
roit | +2.021 |
eor | +1.992 |
Neg logit contributions | |
holiest | -2.539 |
olicy | -2.424 |
QUI | -2.422 |
emi | -2.401 |
athlet | -2.391 |
Token | need |
Token ID | 761 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
chrom | +2.669 |
proof | +2.459 |
rans | +2.429 |
roit | +2.396 |
eor | +2.358 |
Neg logit contributions | |
holiest | -3.668 |
QUI | -3.556 |
olicy | -3.552 |
srfAttach | -3.508 |
emi | -3.478 |
Token | to |
Token ID | 284 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
chrom | +0.986 |
proof | +0.943 |
roit | +0.909 |
bos | +0.897 |
rans | +0.894 |
Neg logit contributions | |
holiest | -0.717 |
emi | -0.690 |
athlet | -0.688 |
goodbye | -0.683 |
cean | -0.679 |
Token | authorize |
Token ID | 29145 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
chrom | +2.521 |
proof | +2.334 |
rans | +2.258 |
roit | +2.221 |
bos | +2.186 |
Neg logit contributions | |
holiest | -3.435 |
olicy | -3.322 |
emi | -3.322 |
cean | -3.272 |
QUI | -3.266 |
Token | each |
Token ID | 1123 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
chrom | +2.355 |
proof | +2.287 |
roit | +2.190 |
bos | +2.163 |
rans | +2.138 |
Neg logit contributions | |
holiest | -2.028 |
emi | -1.982 |
olicy | -1.913 |
athlet | -1.909 |
cean | -1.896 |
Token | other |
Token ID | 584 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
chrom | +2.772 |
proof | +2.599 |
roit | +2.533 |
eor | +2.507 |
inant | +2.500 |
Neg logit contributions | |
holiest | -2.393 |
emi | -2.291 |
assi | -2.266 |
athlet | -2.223 |
goodbye | -2.198 |
Token | to |
Token ID | 284 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
chrom | +3.749 |
proof | +3.547 |
roit | +3.412 |
rans | +3.385 |
obyl | +3.380 |
Neg logit contributions | |
holiest | -3.481 |
emi | -3.287 |
Lanka | -3.239 |
cean | -3.203 |
athlet | -3.170 |
Token | use |
Token ID | 779 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
chrom | +2.515 |
proof | +2.349 |
rans | +2.262 |
roit | +2.228 |
inant | +2.179 |
Neg logit contributions | |
holiest | -3.680 |
olicy | -3.668 |
emi | -3.633 |
QUI | -3.557 |
cean | -3.525 |
Token | the |
Token ID | 262 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
chrom | +2.488 |
proof | +2.377 |
roit | +2.234 |
rans | +2.232 |
bos | +2.227 |
Neg logit contributions | |
holiest | -2.100 |
emi | -2.098 |
olicy | -2.069 |
cean | -2.062 |
assi | -2.055 |
Token | credit |
Token ID | 3884 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
chrom | +1.773 |
proof | +1.670 |
roit | +1.600 |
bos | +1.594 |
eor | +1.577 |
Neg logit contributions | |
emi | -1.714 |
holiest | -1.712 |
olicy | -1.699 |
athlet | -1.675 |
cean | -1.672 |
Token | and |
Token ID | 290 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
chrom | +0.602 |
proof | +0.560 |
roit | +0.548 |
bos | +0.544 |
eor | +0.525 |
Neg logit contributions | |
holiest | -0.675 |
emi | -0.667 |
athlet | -0.659 |
olicy | -0.652 |
goodbye | -0.651 |
Token | of |
Token ID | 286 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
chrom | +1.684 |
proof | +1.567 |
rans | +1.540 |
roit | +1.519 |
eor | +1.511 |
Neg logit contributions | |
holiest | -1.255 |
olicy | -1.242 |
emi | -1.215 |
Lanka | -1.207 |
cean | -1.206 |
Token | the |
Token ID | 262 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
holiest | +0.567 |
emi | +0.556 |
cean | +0.555 |
athlet | +0.551 |
olicy | +0.549 |
Neg logit contributions | |
chrom | -0.729 |
proof | -0.688 |
roit | -0.664 |
rans | -0.662 |
eor | -0.659 |
Token | new |
Token ID | 649 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
cean | +0.188 |
olicy | +0.188 |
emi | +0.186 |
holiest | +0.185 |
athlet | +0.179 |
Neg logit contributions | |
chrom | -0.223 |
proof | -0.209 |
roit | -0.202 |
rans | -0.201 |
bos | -0.200 |
Token | polymer |
Token ID | 30528 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
chrom | +0.337 |
proof | +0.321 |
roit | +0.305 |
rans | +0.305 |
bos | +0.304 |
Neg logit contributions | |
holiest | -0.269 |
cean | -0.269 |
emi | -0.267 |
olicy | -0.264 |
athlet | -0.263 |
Token | notes |
Token ID | 4710 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
chrom | +1.624 |
proof | +1.500 |
bos | +1.392 |
rans | +1.383 |
roit | +1.376 |
Neg logit contributions | |
holiest | -1.902 |
emi | -1.879 |
olicy | -1.859 |
cean | -1.848 |
athlet | -1.831 |
Token | are |
Token ID | 389 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
holiest | +1.242 |
emi | +1.218 |
olicy | +1.202 |
cean | +1.201 |
athlet | +1.190 |
Neg logit contributions | |
chrom | -1.444 |
proof | -1.343 |
roit | -1.315 |
rans | -1.298 |
eor | -1.292 |
Token | not |
Token ID | 407 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
chrom | +0.230 |
proof | +0.213 |
rans | +0.209 |
roit | +0.207 |
eor | +0.201 |
Neg logit contributions | |
olicy | -0.229 |
emi | -0.227 |
holiest | -0.226 |
cean | -0.222 |
athlet | -0.220 |
Token | raised |
Token ID | 4376 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
chrom | +1.109 |
proof | +1.034 |
rans | +1.022 |
roit | +0.987 |
ards | +0.971 |
Neg logit contributions | |
holiest | -0.961 |
olicy | -0.958 |
cean | -0.949 |
emi | -0.944 |
athlet | -0.942 |
Token | . |
Token ID | 13 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
holiest | +0.363 |
emi | +0.360 |
olicy | +0.359 |
cean | +0.354 |
Lanka | +0.349 |
Neg logit contributions | |
chrom | -0.418 |
proof | -0.396 |
roit | -0.382 |
rans | -0.380 |
bos | -0.371 |
Token | The |
Token ID | 383 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
athlet | +0.039 |
holiest | +0.039 |
bargaining | +0.037 |
emi | +0.037 |
olicy | +0.037 |
Neg logit contributions | |
chrom | -0.053 |
proof | -0.050 |
roit | -0.048 |
eor | -0.048 |
rans | -0.048 |
Token | Bra |
Token ID | 9718 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
emi | +0.810 |
olicy | +0.804 |
cean | +0.797 |
holiest | +0.797 |
athlet | +0.775 |
Neg logit contributions | |
chrom | -1.008 |
proof | -0.936 |
roit | -0.922 |
bos | -0.909 |
rans | -0.905 |
Token | ite |
Token ID | 578 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
chrom | +0.913 |
proof | +0.793 |
roit | +0.764 |
rans | +0.743 |
eor | +0.721 |
Neg logit contributions | |
goodbye | -3.125 |
holiest | -3.085 |
athlet | -3.071 |
srfAttach | -3.060 |
olicy | -3.041 |
Token | cleric |
Token ID | 33824 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
chrom | +1.516 |
proof | +1.473 |
roit | +1.449 |
rans | +1.409 |
eor | +1.403 |
Neg logit contributions | |
olicy | -1.178 |
cean | -1.143 |
goodbye | -1.133 |
emi | -1.126 |
srfAttach | -1.123 |
Token | in |
Token ID | 287 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
chrom | +2.293 |
proof | +2.174 |
rans | +2.143 |
roit | +2.119 |
linked | +2.095 |
Neg logit contributions | |
olicy | -2.680 |
emi | -2.617 |
cean | -2.592 |
goodbye | -2.586 |
srfAttach | -2.583 |
Token | Iraq |
Token ID | 3908 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
chrom | +0.901 |
proof | +0.876 |
roit | +0.855 |
eor | +0.847 |
rans | +0.838 |
Neg logit contributions | |
olicy | -0.591 |
emi | -0.581 |
athlet | -0.580 |
cean | -0.575 |
goodbye | -0.567 |
Token | , |
Token ID | 11 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
chrom | +1.143 |
proof | +1.082 |
roit | +1.067 |
rans | +1.056 |
eor | +1.029 |
Neg logit contributions | |
cean | -1.191 |
emi | -1.182 |
olicy | -1.180 |
athlet | -1.180 |
holiest | -1.165 |
Token | who |
Token ID | 508 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
chrom | +1.935 |
proof | +1.830 |
rans | +1.820 |
roit | +1.779 |
bos | +1.777 |
Neg logit contributions | |
olicy | -2.124 |
cean | -2.091 |
athlet | -2.072 |
emi | -2.067 |
holiest | -2.033 |
Token | has |
Token ID | 468 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
chrom | +3.906 |
proof | +3.739 |
bos | +3.678 |
rans | +3.605 |
roit | +3.584 |
Neg logit contributions | |
olicy | -4.560 |
emi | -4.396 |
srfAttach | -4.299 |
cean | -4.291 |
goodbye | -4.253 |
Token | been |
Token ID | 587 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
chrom | +1.830 |
proof | +1.762 |
rans | +1.713 |
roit | +1.712 |
bos | +1.679 |
Neg logit contributions | |
olicy | -1.954 |
emi | -1.925 |
cean | -1.886 |
holiest | -1.864 |
goodbye | -1.862 |
Token | outspoken |
Token ID | 27687 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
chrom | +3.793 |
proof | +3.651 |
linked | +3.563 |
roit | +3.533 |
rans | +3.485 |
Neg logit contributions | |
emi | -4.141 |
olicy | -4.104 |
srfAttach | -4.078 |
cean | -4.050 |
holiest | -4.002 |
Token | against |
Token ID | 1028 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
chrom | +2.303 |
proof | +2.232 |
roit | +2.194 |
rans | +2.121 |
bos | +2.114 |
Neg logit contributions | |
olicy | -2.112 |
emi | -2.102 |
holiest | -2.094 |
cean | -2.039 |
QUI | -2.000 |
Token | the |
Token ID | 262 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
chrom | +2.811 |
proof | +2.692 |
roit | +2.631 |
bos | +2.610 |
rans | +2.554 |
Neg logit contributions | |
emi | -2.385 |
olicy | -2.317 |
athlet | -2.272 |
srfAttach | -2.258 |
cean | -2.230 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
chrom | +4.508 |
proof | +4.213 |
roit | +4.207 |
rans | +4.131 |
bos | +4.121 |
Neg logit contributions | |
olicy | -2.548 |
holiest | -2.484 |
athlet | -2.483 |
cean | -2.481 |
emi | -2.453 |
Token | . |
Token ID | 13 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
chrom | +4.565 |
roit | +4.409 |
proof | +4.278 |
eor | +4.254 |
rans | +4.198 |
Neg logit contributions | |
holiest | -4.468 |
athlet | -4.333 |
olicy | -4.296 |
bargaining | -4.279 |
emi | -4.218 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
chrom | +2.960 |
proof | +2.759 |
roit | +2.689 |
bos | +2.644 |
eor | +2.634 |
Neg logit contributions | |
athlet | -3.392 |
holiest | -3.324 |
bargaining | -3.277 |
olicy | -3.271 |
goodbye | -3.265 |
Token | / |
Token ID | 14 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
chrom | +1.966 |
proof | +1.846 |
roit | +1.768 |
rans | +1.755 |
eor | +1.740 |
Neg logit contributions | |
athlet | -2.382 |
holiest | -2.304 |
olicy | -2.280 |
emi | -2.228 |
bargaining | -2.200 |
Token | Cl |
Token ID | 2601 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
chrom | +3.291 |
proof | +3.183 |
eor | +3.035 |
bos | +2.993 |
roit | +2.984 |
Neg logit contributions | |
athlet | -3.273 |
holiest | -3.165 |
bargaining | -3.141 |
emi | -3.054 |
olicy | -3.015 |
Token | od |
Token ID | 375 |
Feature activation | -8.11e+00 |
Pos logit contributions | |
roit | +3.317 |
chrom | +3.316 |
obyl | +3.292 |
rans | +3.285 |
bos | +3.246 |
Neg logit contributions | |
holiest | -6.457 |
goodbye | -6.406 |
bargaining | -6.368 |
athlet | -6.334 |
QUI | -6.326 |
Token | agh |
Token ID | 10471 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
chrom | +4.407 |
rans | +4.161 |
proof | +4.111 |
obyl | +4.085 |
bos | +4.079 |
Neg logit contributions | |
goodbye | -7.367 |
athlet | -7.300 |
holiest | -7.189 |
versa | -7.153 |
forgiveness | -7.088 |
Token | Kil |
Token ID | 19902 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
chrom | +1.327 |
proof | +1.294 |
bos | +1.278 |
roit | +1.268 |
rans | +1.261 |
Neg logit contributions | |
athlet | -0.831 |
holiest | -0.831 |
versa | -0.819 |
goodbye | -0.819 |
emi | -0.804 |
Token | c |
Token ID | 66 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
chrom | +1.600 |
roit | +1.502 |
proof | +1.479 |
bos | +1.470 |
rans | +1.445 |
Neg logit contributions | |
goodbye | -2.262 |
athlet | -2.225 |
olicy | -2.204 |
holiest | -2.203 |
emi | -2.169 |
Token | oy |
Token ID | 726 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
proof | +1.782 |
obyl | +1.730 |
chrom | +1.580 |
ards | +1.579 |
oad | +1.563 |
Neg logit contributions | |
externalActionCode | -6.849 |
versa | -6.781 |
holiest | -6.737 |
athlet | -6.727 |
bargaining | -6.681 |
Token | ne |
Token ID | 710 |
Feature activation | -5.64e+00 |
Pos logit contributions | |
chrom | +2.540 |
roit | +2.301 |
eor | +2.259 |
proof | +2.177 |
rans | +2.074 |
Neg logit contributions | |
holiest | -5.687 |
bargaining | -5.551 |
athlet | -5.537 |
QUI | -5.537 |
olicy | -5.498 |
Token | act |
Token ID | 719 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
holiest | +1.438 |
goodbye | +1.406 |
athlet | +1.402 |
emi | +1.402 |
bargaining | +1.383 |
Neg logit contributions | |
chrom | -2.144 |
roit | -2.013 |
proof | -1.988 |
obyl | -1.982 |
eor | -1.977 |
Token | worth |
Token ID | 2861 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
chrom | +3.743 |
roit | +3.580 |
proof | +3.559 |
bos | +3.476 |
rans | +3.447 |
Neg logit contributions | |
holiest | -3.151 |
emi | -3.078 |
cean | -3.075 |
olicy | -3.046 |
Lanka | -3.015 |
Token | $ |
Token ID | 720 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
chrom | +1.362 |
proof | +1.353 |
bos | +1.287 |
roit | +1.282 |
rans | +1.279 |
Neg logit contributions | |
emi | -1.017 |
holiest | -1.016 |
olicy | -1.002 |
cean | -0.994 |
assi | -0.991 |
Token | 20 |
Token ID | 1238 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
chrom | +1.098 |
proof | +1.019 |
roit | +0.970 |
rans | +0.970 |
bos | +0.962 |
Neg logit contributions | |
holiest | -1.197 |
athlet | -1.194 |
olicy | -1.135 |
bargaining | -1.134 |
emi | -1.129 |
Token | million |
Token ID | 1510 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
chrom | +4.906 |
proof | +4.600 |
bos | +4.599 |
rans | +4.482 |
roit | +4.476 |
Neg logit contributions | |
holiest | -4.140 |
Lanka | -4.055 |
emi | -4.046 |
goodbye | -4.030 |
cean | -4.026 |
Token | that |
Token ID | 326 |
Feature activation | -7.12e+00 |
Pos logit contributions | |
chrom | +2.077 |
proof | +1.982 |
roit | +1.980 |
bos | +1.934 |
rans | +1.923 |
Neg logit contributions | |
holiest | -1.880 |
emi | -1.837 |
olicy | -1.833 |
cean | -1.827 |
Lanka | -1.783 |
Token | was |
Token ID | 373 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
chrom | +5.073 |
proof | +4.718 |
roit | +4.703 |
bos | +4.637 |
rans | +4.518 |
Neg logit contributions | |
emi | -4.948 |
olicy | -4.873 |
holiest | -4.755 |
assi | -4.755 |
cean | -4.734 |
Token | passed |
Token ID | 3804 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
chrom | +3.524 |
rans | +3.260 |
roit | +3.230 |
proof | +3.208 |
bos | +3.113 |
Neg logit contributions | |
emi | -3.640 |
holiest | -3.614 |
cean | -3.571 |
srfAttach | -3.523 |
olicy | -3.519 |
Token | to |
Token ID | 284 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
chrom | +3.575 |
proof | +3.413 |
roit | +3.353 |
bos | +3.304 |
rans | +3.245 |
Neg logit contributions | |
holiest | -3.477 |
emi | -3.452 |
cean | -3.390 |
assi | -3.383 |
Lanka | -3.356 |
Token | help |
Token ID | 1037 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
chrom | +4.036 |
roit | +3.868 |
proof | +3.842 |
rans | +3.711 |
bos | +3.684 |
Neg logit contributions | |
holiest | -4.051 |
cean | -3.957 |
emi | -3.951 |
assi | -3.869 |
olicy | -3.858 |
Token | repair |
Token ID | 9185 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
chrom | +2.250 |
proof | +2.161 |
roit | +2.129 |
bos | +2.087 |
rans | +2.076 |
Neg logit contributions | |
emi | -2.048 |
holiest | -2.028 |
cean | -1.971 |
assi | -1.953 |
olicy | -1.937 |
Token | or |
Token ID | 393 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
chrom | +2.389 |
roit | +2.181 |
proof | +2.171 |
rans | +2.122 |
isation | +2.114 |
Neg logit contributions | |
holiest | -2.462 |
emi | -2.366 |
olicy | -2.307 |
QUI | -2.293 |
goodbye | -2.287 |
Token | wage |
Token ID | 7699 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
chrom | +2.084 |
proof | +1.924 |
roit | +1.908 |
rans | +1.898 |
eor | +1.858 |
Neg logit contributions | |
holiest | -1.631 |
emi | -1.585 |
Lanka | -1.549 |
olicy | -1.548 |
goodbye | -1.538 |
Token | employment |
Token ID | 7184 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
holiest | +1.378 |
emi | +1.349 |
goodbye | +1.317 |
athlet | +1.317 |
olicy | +1.312 |
Neg logit contributions | |
chrom | -1.727 |
proof | -1.629 |
roit | -1.583 |
rans | -1.554 |
eor | -1.551 |
Token | , |
Token ID | 11 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
chrom | +2.678 |
proof | +2.542 |
roit | +2.469 |
bos | +2.436 |
rans | +2.424 |
Neg logit contributions | |
holiest | -2.642 |
cean | -2.559 |
olicy | -2.543 |
emi | -2.539 |
CONCLUS | -2.504 |
Token | whether |
Token ID | 1771 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
chrom | +2.391 |
proof | +2.221 |
roit | +2.181 |
rans | +2.176 |
bos | +2.105 |
Neg logit contributions | |
holiest | -2.195 |
olicy | -2.178 |
emi | -2.134 |
cean | -2.123 |
QUI | -2.121 |
Token | regular |
Token ID | 3218 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
chrom | +3.590 |
roit | +3.309 |
proof | +3.157 |
rans | +3.156 |
bos | +3.155 |
Neg logit contributions | |
olicy | -3.510 |
holiest | -3.460 |
emi | -3.447 |
Lanka | -3.394 |
srfAttach | -3.344 |
Token | or |
Token ID | 393 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
chrom | +4.537 |
roit | +4.357 |
isation | +4.344 |
proof | +4.285 |
bos | +4.199 |
Neg logit contributions | |
holiest | -5.006 |
emi | -4.784 |
olicy | -4.780 |
srfAttach | -4.671 |
CONCLUS | -4.662 |
Token | casual |
Token ID | 9341 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
chrom | +2.437 |
roit | +2.298 |
proof | +2.220 |
bos | +2.214 |
eor | +2.183 |
Neg logit contributions | |
holiest | -1.989 |
olicy | -1.983 |
Lanka | -1.936 |
emi | -1.930 |
goodbye | -1.911 |
Token | , |
Token ID | 11 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
chrom | +3.661 |
roit | +3.427 |
proof | +3.422 |
isation | +3.373 |
rans | +3.336 |
Neg logit contributions | |
holiest | -3.949 |
olicy | -3.783 |
emi | -3.765 |
Lanka | -3.646 |
srfAttach | -3.633 |
Token | less |
Token ID | 1342 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
chrom | +2.868 |
proof | +2.637 |
roit | +2.625 |
rans | +2.622 |
bos | +2.555 |
Neg logit contributions | |
holiest | -2.582 |
olicy | -2.543 |
emi | -2.488 |
cean | -2.457 |
Lanka | -2.454 |
Token | than |
Token ID | 621 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
chrom | +2.101 |
roit | +1.939 |
proof | +1.913 |
rans | +1.853 |
ards | +1.819 |
Neg logit contributions | |
olicy | -2.526 |
emi | -2.521 |
holiest | -2.521 |
goodbye | -2.463 |
Lanka | -2.459 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
chrom | +0.520 |
proof | +0.488 |
roit | +0.487 |
bos | +0.478 |
eor | +0.476 |
Neg logit contributions | |
holiest | -0.353 |
emi | -0.346 |
athlet | -0.340 |
goodbye | -0.337 |
olicy | -0.335 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
chrom | +1.660 |
proof | +1.547 |
roit | +1.522 |
eor | +1.502 |
rans | +1.499 |
Neg logit contributions | |
holiest | -1.632 |
emi | -1.561 |
athlet | -1.547 |
goodbye | -1.535 |
bargaining | -1.530 |
Token | D |
Token ID | 35 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
chrom | +1.419 |
proof | +1.328 |
roit | +1.286 |
rans | +1.281 |
bos | +1.268 |
Neg logit contributions | |
holiest | -1.191 |
athlet | -1.166 |
bargaining | -1.116 |
olicy | -1.107 |
emi | -1.104 |
Token | ensity |
Token ID | 6377 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
chrom | +1.004 |
roit | +0.931 |
inant | +0.887 |
proof | +0.876 |
rans | +0.854 |
Neg logit contributions | |
holiest | -3.017 |
athlet | -2.993 |
emi | -2.923 |
goodbye | -2.922 |
bargaining | -2.915 |
Token | as |
Token ID | 355 |
Feature activation | -7.56e-03 |
Pos logit contributions | |
chrom | +0.298 |
proof | +0.278 |
roit | +0.272 |
rans | +0.270 |
obyl | +0.268 |
Neg logit contributions | |
holiest | -0.257 |
athlet | -0.249 |
emi | -0.247 |
olicy | -0.245 |
goodbye | -0.241 |
Token | ambient |
Token ID | 25237 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
chrom | +0.006 |
proof | +0.006 |
roit | +0.006 |
bos | +0.006 |
rans | +0.006 |
Neg logit contributions | |
holiest | -0.005 |
emi | -0.005 |
athlet | -0.005 |
olicy | -0.005 |
cean | -0.005 |
Token | plus |
Token ID | 5556 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
chrom | +4.094 |
proof | +3.899 |
roit | +3.787 |
rans | +3.706 |
bos | +3.679 |
Neg logit contributions | |
holiest | -4.146 |
emi | -3.963 |
athlet | -3.913 |
olicy | -3.904 |
Lanka | -3.809 |
Token | deviation |
Token ID | 28833 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
holiest | +0.102 |
emi | +0.100 |
athlet | +0.099 |
goodbye | +0.097 |
olicy | +0.097 |
Neg logit contributions | |
chrom | -0.084 |
proof | -0.077 |
roit | -0.076 |
eor | -0.074 |
obyl | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
chrom | +0.708 |
proof | +0.675 |
roit | +0.660 |
rans | +0.650 |
obyl | +0.647 |
Neg logit contributions | |
holiest | -0.642 |
emi | -0.605 |
athlet | -0.604 |
olicy | -0.592 |
goodbye | -0.583 |
Token | Fl |
Token ID | 1610 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
chrom | +0.763 |
proof | +0.720 |
roit | +0.706 |
rans | +0.696 |
obyl | +0.692 |
Neg logit contributions | |
holiest | -0.653 |
athlet | -0.635 |
emi | -0.617 |
bargaining | -0.614 |
goodbye | -0.614 |
Token | uid |
Token ID | 27112 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
holiest | +1.490 |
goodbye | +1.463 |
athlet | +1.455 |
bargaining | +1.446 |
cean | +1.437 |
Neg logit contributions | |
chrom | -0.840 |
roit | -0.766 |
proof | -0.761 |
obyl | -0.739 |
bos | -0.732 |