Token | commander |
Token ID | 11561 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
ONES | +0.323 |
Naz | +0.316 |
OSP | +0.304 |
areth | +0.300 |
HTTP | +0.280 |
Neg logit contributions | |
isine | -0.424 |
opian | -0.390 |
chen | -0.383 |
ulic | -0.369 |
chefs | -0.363 |
Token | , |
Token ID | 11 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
ONES | +1.818 |
Naz | +1.805 |
OSP | +1.713 |
areth | +1.692 |
Sing | +1.583 |
Neg logit contributions | |
isine | -2.361 |
opian | -2.175 |
chen | -2.124 |
ulic | -2.063 |
chefs | -1.999 |
Token | Gen |
Token ID | 5215 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
isine | +0.428 |
opian | +0.395 |
chen | +0.388 |
ulic | +0.375 |
chefs | +0.368 |
Neg logit contributions | |
ONES | -0.287 |
Naz | -0.282 |
OSP | -0.269 |
areth | -0.265 |
HTTP | -0.246 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
ONES | +0.334 |
Naz | +0.328 |
OSP | +0.314 |
areth | +0.311 |
HTTP | +0.290 |
Neg logit contributions | |
isine | -0.419 |
opian | -0.384 |
chen | -0.376 |
ulic | -0.363 |
chefs | -0.356 |
Token | Douglas |
Token ID | 15796 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
ONES | +0.382 |
Naz | +0.375 |
OSP | +0.360 |
areth | +0.356 |
HTTP | +0.333 |
Neg logit contributions | |
isine | -0.455 |
opian | -0.417 |
chen | -0.408 |
ulic | -0.394 |
chefs | -0.385 |
Token | MacArthur |
Token ID | 46626 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
ONES | +1.573 |
Naz | +1.493 |
areth | +1.356 |
OSP | +1.356 |
Sing | +1.187 |
Neg logit contributions | |
isine | -5.112 |
opian | -4.807 |
chen | -4.697 |
ulic | -4.621 |
chefs | -4.515 |
Token | , |
Token ID | 11 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Naz | +6.485 |
ONES | +6.345 |
OSP | +5.985 |
areth | +5.798 |
Sing | +5.628 |
Neg logit contributions | |
isine | -10.548 |
opian | -10.101 |
chen | -9.544 |
ulic | -9.347 |
chefs | -8.992 |
Token | defied |
Token ID | 47437 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
isine | +0.148 |
opian | +0.136 |
chen | +0.134 |
ulic | +0.129 |
chefs | +0.127 |
Neg logit contributions | |
ONES | -0.118 |
Naz | -0.115 |
OSP | -0.111 |
areth | -0.110 |
ospels | -0.103 |
Token | him |
Token ID | 683 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
ONES | +0.704 |
Naz | +0.689 |
OSP | +0.665 |
areth | +0.657 |
HTTP | +0.616 |
Neg logit contributions | |
isine | -0.826 |
opian | -0.756 |
chen | -0.743 |
ulic | -0.714 |
chefs | -0.700 |
Token | , |
Token ID | 11 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
isine | +1.580 |
opian | +1.452 |
chen | +1.430 |
ulic | +1.376 |
chefs | +1.346 |
Neg logit contributions | |
ONES | -1.186 |
Naz | -1.151 |
OSP | -1.116 |
areth | -1.103 |
ospels | -1.032 |
Token | � |
Token ID | 447 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
isine | +0.150 |
opian | +0.138 |
chen | +0.136 |
ulic | +0.131 |
chefs | +0.129 |
Neg logit contributions | |
ONES | -0.103 |
Naz | -0.100 |
OSP | -0.097 |
areth | -0.096 |
ospels | -0.089 |
Token | worked |
Token ID | 3111 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
ONES | +0.220 |
Naz | +0.216 |
OSP | +0.206 |
areth | +0.203 |
HTTP | +0.189 |
Neg logit contributions | |
isine | -0.318 |
opian | -0.293 |
chen | -0.288 |
ulic | -0.278 |
chefs | -0.272 |
Token | out |
Token ID | 503 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
isine | +0.158 |
opian | +0.143 |
chen | +0.140 |
ulic | +0.133 |
chefs | +0.130 |
Neg logit contributions | |
ONES | -0.190 |
Naz | -0.188 |
areth | -0.181 |
OSP | -0.181 |
ospels | -0.171 |
Token | great |
Token ID | 1049 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ONES | +1.775 |
Naz | +1.740 |
OSP | +1.673 |
areth | +1.639 |
HTTP | +1.538 |
Neg logit contributions | |
isine | -2.255 |
opian | -2.066 |
chen | -2.026 |
ulic | -1.953 |
chefs | -1.909 |
Token | . |
Token ID | 13 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
ONES | +1.071 |
Naz | +1.052 |
OSP | +1.009 |
areth | +0.998 |
HTTP | +0.933 |
Neg logit contributions | |
isine | -1.330 |
opian | -1.219 |
chen | -1.197 |
ulic | -1.154 |
chefs | -1.129 |
Token | Competitive |
Token ID | 47665 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ONES | +0.643 |
Naz | +0.632 |
OSP | +0.607 |
areth | +0.600 |
HTTP | +0.562 |
Neg logit contributions | |
isine | -0.763 |
opian | -0.698 |
chen | -0.686 |
ulic | -0.660 |
chefs | -0.646 |
Token | Trib |
Token ID | 10841 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
ONES | +0.827 |
Naz | +0.813 |
OSP | +0.780 |
areth | +0.772 |
HTTP | +0.723 |
Neg logit contributions | |
isine | -1.004 |
opian | -0.920 |
chen | -0.904 |
ulic | -0.869 |
chefs | -0.852 |
Token | es |
Token ID | 274 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
ONES | +6.028 |
Naz | +5.678 |
areth | +5.292 |
OSP | +5.222 |
Sing | +4.977 |
Neg logit contributions | |
isine | -10.826 |
opian | -9.959 |
chen | -9.861 |
chefs | -9.670 |
ulic | -9.623 |
Token | Ascend |
Token ID | 45387 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ONES | +2.095 |
Naz | +2.060 |
OSP | +1.966 |
areth | +1.945 |
HTTP | +1.813 |
Neg logit contributions | |
isine | -2.677 |
opian | -2.456 |
chen | -2.409 |
ulic | -2.331 |
chefs | -2.275 |
Token | player |
Token ID | 2137 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
ONES | +0.837 |
Naz | +0.823 |
OSP | +0.789 |
areth | +0.780 |
HTTP | +0.730 |
Neg logit contributions | |
isine | -1.002 |
opian | -0.917 |
chen | -0.899 |
ulic | -0.866 |
chefs | -0.846 |
Token | . |
Token ID | 13 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
ONES | +0.458 |
Naz | +0.450 |
OSP | +0.432 |
areth | +0.427 |
HTTP | +0.399 |
Neg logit contributions | |
isine | -0.561 |
opian | -0.514 |
chen | -0.505 |
ulic | -0.486 |
chefs | -0.476 |
Token | Sym |
Token ID | 15845 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
ONES | +0.515 |
Naz | +0.506 |
OSP | +0.486 |
areth | +0.481 |
HTTP | +0.450 |
Neg logit contributions | |
isine | -0.615 |
opian | -0.563 |
chen | -0.553 |
ulic | -0.532 |
chefs | -0.521 |
Token | did |
Token ID | 750 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ONES | +0.551 |
Naz | +0.540 |
OSP | +0.514 |
areth | +0.505 |
HTTP | +0.468 |
Neg logit contributions | |
isine | -0.919 |
opian | -0.853 |
chen | -0.841 |
ulic | -0.813 |
chefs | -0.799 |
Token | not |
Token ID | 407 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
ONES | +1.955 |
Naz | +1.926 |
OSP | +1.853 |
areth | +1.837 |
HTTP | +1.733 |
Neg logit contributions | |
isine | -1.912 |
opian | -1.730 |
chen | -1.695 |
ulic | -1.624 |
chefs | -1.585 |
Token | issue |
Token ID | 2071 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
ONES | +0.615 |
Naz | +0.605 |
OSP | +0.577 |
areth | +0.574 |
HTTP | +0.536 |
Neg logit contributions | |
isine | -0.741 |
opian | -0.676 |
chen | -0.665 |
ulic | -0.639 |
chefs | -0.624 |
Token | the |
Token ID | 262 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
isine | +2.133 |
opian | +1.936 |
chen | +1.911 |
ulic | +1.836 |
chefs | +1.810 |
Neg logit contributions | |
ONES | -2.205 |
Naz | -2.194 |
OSP | -2.123 |
areth | -2.066 |
ospels | -1.973 |
Token | total |
Token ID | 2472 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
ONES | +0.534 |
Naz | +0.523 |
OSP | +0.501 |
areth | +0.497 |
HTTP | +0.464 |
Neg logit contributions | |
isine | -0.667 |
opian | -0.610 |
chen | -0.599 |
ulic | -0.577 |
chefs | -0.564 |
Token | Loving |
Token ID | 39202 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
ONES | +0.064 |
Naz | +0.063 |
OSP | +0.061 |
areth | +0.060 |
HTTP | +0.056 |
Neg logit contributions | |
isine | -0.078 |
opian | -0.071 |
chen | -0.070 |
ulic | -0.068 |
chefs | -0.066 |
Token | v |
Token ID | 410 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
ONES | +6.329 |
Naz | +6.034 |
areth | +5.802 |
OSP | +5.693 |
prophets | +5.436 |
Neg logit contributions | |
isine | -10.366 |
opian | -9.453 |
ulic | -9.126 |
chen | -9.080 |
chefs | -8.631 |
Token | . |
Token ID | 13 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
ONES | +2.879 |
Naz | +2.836 |
areth | +2.755 |
OSP | +2.637 |
CTV | +2.491 |
Neg logit contributions | |
isine | -5.095 |
opian | -4.732 |
ulic | -4.479 |
chen | -4.434 |
untled | -4.317 |
Token | Virginia |
Token ID | 6025 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
ONES | +0.588 |
Naz | +0.580 |
OSP | +0.561 |
areth | +0.556 |
HTTP | +0.528 |
Neg logit contributions | |
isine | -0.469 |
opian | -0.420 |
chen | -0.410 |
ulic | -0.392 |
chefs | -0.380 |
Token | victory |
Token ID | 5373 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
ONES | +0.321 |
Naz | +0.318 |
OSP | +0.303 |
areth | +0.298 |
HTTP | +0.277 |
Neg logit contributions | |
isine | -0.466 |
opian | -0.431 |
chen | -0.425 |
ulic | -0.409 |
chefs | -0.403 |
Token | that |
Token ID | 326 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
ONES | +2.453 |
Naz | +2.404 |
OSP | +2.306 |
areth | +2.283 |
HTTP | +2.141 |
Neg logit contributions | |
isine | -3.015 |
opian | -2.761 |
chen | -2.701 |
ulic | -2.610 |
chefs | -2.536 |
Token | , |
Token ID | 11 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ONES | +2.621 |
Naz | +2.590 |
OSP | +2.458 |
areth | +2.453 |
HTTP | +2.268 |
Neg logit contributions | |
isine | -3.480 |
opian | -3.203 |
chen | -3.127 |
ulic | -3.026 |
chefs | -2.944 |
Token | the |
Token ID | 262 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
ONES | +0.224 |
Naz | +0.220 |
OSP | +0.212 |
areth | +0.210 |
HTTP | +0.197 |
Neg logit contributions | |
isine | -0.249 |
opian | -0.227 |
chen | -0.223 |
ulic | -0.214 |
chefs | -0.210 |
Token | Fire |
Token ID | 3764 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
isine | +0.056 |
opian | +0.051 |
chen | +0.050 |
ulic | +0.048 |
chefs | +0.047 |
Neg logit contributions | |
ONES | -0.051 |
Naz | -0.050 |
OSP | -0.048 |
areth | -0.048 |
HTTP | -0.045 |
Token | house |
Token ID | 4803 |
Feature activation | -9.76e-02 |
Pos logit contributions | |
isine | +1.552 |
chen | +1.422 |
opian | +1.416 |
ulic | +1.347 |
chefs | +1.312 |
Neg logit contributions | |
ONES | -1.472 |
Naz | -1.453 |
OSP | -1.395 |
areth | -1.376 |
HTTP | -1.294 |
Token | in |
Token ID | 287 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
isine | +0.085 |
opian | +0.078 |
chen | +0.077 |
ulic | +0.074 |
chefs | +0.072 |
Neg logit contributions | |
ONES | -0.074 |
Naz | -0.073 |
OSP | -0.070 |
areth | -0.069 |
HTTP | -0.065 |
Token | Trib |
Token ID | 10841 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
isine | +0.989 |
opian | +0.905 |
chen | +0.892 |
ulic | +0.850 |
chefs | +0.836 |
Neg logit contributions | |
ONES | -0.947 |
Naz | -0.928 |
OSP | -0.901 |
areth | -0.889 |
HTTP | -0.840 |
Token | eca |
Token ID | 31047 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ONES | +9.667 |
Naz | +9.383 |
areth | +9.206 |
OSP | +9.040 |
ospels | +8.675 |
Neg logit contributions | |
isine | -6.621 |
opian | -5.613 |
chefs | -5.437 |
chen | -5.432 |
ulic | -5.345 |
Token | neighborhood |
Token ID | 6232 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ONES | +1.407 |
Naz | +1.382 |
OSP | +1.323 |
areth | +1.309 |
HTTP | +1.220 |
Neg logit contributions | |
isine | -1.833 |
opian | -1.685 |
chen | -1.654 |
ulic | -1.596 |
chefs | -1.561 |
Token | in |
Token ID | 287 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
ONES | +1.201 |
Naz | +1.181 |
OSP | +1.133 |
areth | +1.120 |
HTTP | +1.048 |
Neg logit contributions | |
isine | -1.472 |
opian | -1.349 |
chen | -1.324 |
ulic | -1.276 |
chefs | -1.248 |
Token | New |
Token ID | 968 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
isine | +0.436 |
opian | +0.400 |
chen | +0.393 |
ulic | +0.376 |
chefs | +0.369 |
Neg logit contributions | |
ONES | -0.401 |
Naz | -0.395 |
OSP | -0.381 |
areth | -0.376 |
HTTP | -0.355 |
Token | York |
Token ID | 1971 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
ONES | +1.178 |
Naz | +1.155 |
OSP | +1.117 |
areth | +1.099 |
HTTP | +1.039 |
Neg logit contributions | |
isine | -1.201 |
opian | -1.094 |
chen | -1.076 |
ulic | -1.030 |
chefs | -1.006 |
Token | especially |
Token ID | 2592 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ONES | +0.097 |
Naz | +0.096 |
OSP | +0.091 |
areth | +0.090 |
HTTP | +0.084 |
Neg logit contributions | |
isine | -0.131 |
opian | -0.121 |
chen | -0.119 |
ulic | -0.115 |
chefs | -0.112 |
Token | since |
Token ID | 1201 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
isine | +1.263 |
opian | +1.147 |
chen | +1.132 |
ulic | +1.082 |
chefs | +1.064 |
Neg logit contributions | |
ONES | -1.253 |
Naz | -1.237 |
OSP | -1.189 |
areth | -1.181 |
ospels | -1.113 |
Token | Rep |
Token ID | 1432 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
isine | +2.025 |
opian | +1.840 |
chen | +1.819 |
ulic | +1.738 |
chefs | +1.725 |
Neg logit contributions | |
ONES | -2.022 |
Naz | -1.996 |
OSP | -1.910 |
areth | -1.902 |
HTTP | -1.793 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ONES | +0.554 |
Naz | +0.548 |
OSP | +0.525 |
areth | +0.520 |
HTTP | +0.492 |
Neg logit contributions | |
isine | -0.644 |
opian | -0.589 |
chen | -0.582 |
ulic | -0.562 |
chefs | -0.545 |
Token | Tom |
Token ID | 4186 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
isine | +1.109 |
opian | +1.015 |
chen | +1.005 |
ulic | +0.964 |
chefs | +0.945 |
Neg logit contributions | |
ONES | -0.934 |
Naz | -0.921 |
OSP | -0.884 |
areth | -0.876 |
HTTP | -0.823 |
Token | MacArthur |
Token ID | 46626 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
isine | +0.653 |
opian | +0.598 |
chen | +0.592 |
ulic | +0.572 |
chefs | +0.558 |
Neg logit contributions | |
ONES | -0.514 |
Naz | -0.508 |
OSP | -0.482 |
areth | -0.478 |
HTTP | -0.448 |
Token | of |
Token ID | 286 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
ONES | +6.124 |
Naz | +5.980 |
OSP | +5.783 |
areth | +5.533 |
Sing | +5.316 |
Neg logit contributions | |
isine | -10.074 |
opian | -9.283 |
chen | -8.803 |
ulic | -8.797 |
untled | -8.429 |
Token | New |
Token ID | 968 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
isine | +0.512 |
opian | +0.464 |
chen | +0.456 |
ulic | +0.436 |
chefs | +0.427 |
Neg logit contributions | |
ONES | -0.537 |
Naz | -0.529 |
OSP | -0.511 |
areth | -0.506 |
ospels | -0.479 |
Token | Jersey |
Token ID | 8221 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
ONES | +0.909 |
Naz | +0.893 |
OSP | +0.867 |
areth | +0.855 |
HTTP | +0.812 |
Neg logit contributions | |
isine | -0.785 |
opian | -0.707 |
chen | -0.696 |
ulic | -0.663 |
chefs | -0.647 |
Token | authored |
Token ID | 33941 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
isine | +0.921 |
opian | +0.848 |
chen | +0.839 |
ulic | +0.804 |
chefs | +0.796 |
Neg logit contributions | |
ONES | -0.669 |
Naz | -0.660 |
OSP | -0.628 |
areth | -0.621 |
ospels | -0.581 |
Token | an |
Token ID | 281 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
ONES | +0.284 |
Naz | +0.280 |
OSP | +0.268 |
areth | +0.266 |
HTTP | +0.250 |
Neg logit contributions | |
isine | -0.308 |
opian | -0.281 |
chen | -0.276 |
ulic | -0.264 |
chefs | -0.259 |
Token | will |
Token ID | 481 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ONES | +0.873 |
Naz | +0.856 |
OSP | +0.816 |
areth | +0.806 |
HTTP | +0.746 |
Neg logit contributions | |
isine | -1.332 |
opian | -1.230 |
chen | -1.208 |
ulic | -1.170 |
chefs | -1.144 |
Token | be |
Token ID | 307 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
isine | +0.973 |
opian | +0.892 |
chen | +0.878 |
ulic | +0.842 |
chefs | +0.826 |
Neg logit contributions | |
ONES | -0.898 |
Naz | -0.885 |
OSP | -0.852 |
areth | -0.840 |
ospels | -0.792 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ONES | +0.551 |
Naz | +0.540 |
OSP | +0.518 |
areth | +0.514 |
HTTP | +0.481 |
Neg logit contributions | |
isine | -0.665 |
opian | -0.609 |
chen | -0.596 |
ulic | -0.575 |
chefs | -0.562 |
Token | equivalent |
Token ID | 7548 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
isine | +0.969 |
opian | +0.879 |
chen | +0.857 |
ulic | +0.820 |
chefs | +0.801 |
Neg logit contributions | |
ONES | -1.129 |
Naz | -1.119 |
OSP | -1.080 |
areth | -1.070 |
ospels | -1.014 |
Token | of |
Token ID | 286 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
ONES | +0.945 |
Naz | +0.936 |
OSP | +0.896 |
areth | +0.888 |
HTTP | +0.837 |
Neg logit contributions | |
isine | -0.969 |
opian | -0.894 |
chen | -0.871 |
ulic | -0.837 |
chefs | -0.818 |
Token | Loving |
Token ID | 39202 |
Feature activation | +9.99e+00 |
Pos logit contributions | |
isine | +0.817 |
opian | +0.745 |
chen | +0.731 |
ulic | +0.701 |
chefs | +0.690 |
Neg logit contributions | |
ONES | -0.786 |
Naz | -0.778 |
OSP | -0.748 |
areth | -0.740 |
ospels | -0.698 |
Token | v |
Token ID | 410 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
ONES | +5.332 |
Naz | +5.183 |
OSP | +4.761 |
areth | +4.724 |
HTTP | +4.453 |
Neg logit contributions | |
isine | -10.577 |
opian | -9.678 |
chen | -9.316 |
ulic | -9.286 |
chefs | -8.948 |
Token | . |
Token ID | 13 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
Naz | +2.795 |
ONES | +2.795 |
areth | +2.600 |
OSP | +2.577 |
Sing | +2.445 |
Neg logit contributions | |
isine | -4.813 |
opian | -4.419 |
ulic | -4.196 |
chen | -4.158 |
untled | -4.058 |
Token | Virginia |
Token ID | 6025 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
ONES | +0.733 |
Naz | +0.724 |
OSP | +0.699 |
areth | +0.694 |
HTTP | +0.658 |
Neg logit contributions | |
isine | -0.587 |
opian | -0.525 |
chen | -0.513 |
ulic | -0.490 |
chefs | -0.476 |
Token | , |
Token ID | 11 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
ONES | +0.572 |
Naz | +0.563 |
OSP | +0.539 |
areth | +0.533 |
HTTP | +0.498 |
Neg logit contributions | |
isine | -0.726 |
opian | -0.666 |
chen | -0.655 |
ulic | -0.631 |
chefs | -0.618 |
Token | which |
Token ID | 543 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ONES | +0.180 |
Naz | +0.177 |
OSP | +0.170 |
areth | +0.168 |
HTTP | +0.158 |
Neg logit contributions | |
isine | -0.217 |
opian | -0.198 |
chen | -0.195 |
ulic | -0.188 |
chefs | -0.183 |
Token | HUN |
Token ID | 41041 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
isine | +1.304 |
opian | +1.193 |
chen | +1.176 |
ulic | +1.123 |
chefs | +1.107 |
Neg logit contributions | |
ONES | -1.146 |
Naz | -1.137 |
OSP | -1.086 |
areth | -1.079 |
ospels | -1.013 |
Token | TER |
Token ID | 5781 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ONES | +0.352 |
Naz | +0.345 |
OSP | +0.329 |
areth | +0.325 |
ospels | +0.300 |
Neg logit contributions | |
isine | -0.550 |
opian | -0.509 |
chen | -0.501 |
ulic | -0.484 |
chefs | -0.475 |
Token |
|
Token ID | 198 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
ONES | +0.796 |
Naz | +0.782 |
OSP | +0.750 |
areth | +0.741 |
HTTP | +0.694 |
Neg logit contributions | |
isine | -0.981 |
opian | -0.899 |
chen | -0.882 |
ulic | -0.850 |
chefs | -0.832 |
Token |
|
Token ID | 198 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
isine | +0.855 |
opian | +0.789 |
chen | +0.769 |
ulic | +0.751 |
chefs | +0.738 |
Neg logit contributions | |
ONES | -0.551 |
Naz | -0.544 |
OSP | -0.514 |
areth | -0.506 |
HTTP | -0.472 |
Token | + |
Token ID | 10 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
isine | +0.794 |
opian | +0.735 |
chen | +0.731 |
ulic | +0.702 |
chefs | +0.685 |
Neg logit contributions | |
ONES | -0.477 |
Naz | -0.466 |
areth | -0.446 |
OSP | -0.444 |
ospels | -0.413 |
Token | Advent |
Token ID | 33732 |
Feature activation | +9.77e+00 |
Pos logit contributions | |
isine | +0.322 |
opian | +0.295 |
chen | +0.290 |
ulic | +0.280 |
chefs | +0.274 |
Neg logit contributions | |
ONES | -0.251 |
Naz | -0.248 |
OSP | -0.237 |
areth | -0.235 |
HTTP | -0.219 |
Token | urous |
Token ID | 29277 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
ONES | +7.139 |
Naz | +7.031 |
areth | +6.739 |
OSP | +6.704 |
wip | +6.278 |
Neg logit contributions | |
isine | -8.289 |
opian | -7.416 |
chen | -7.313 |
ulic | -7.138 |
chefs | -6.880 |
Token | , |
Token ID | 11 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
ONES | +2.657 |
Naz | +2.613 |
OSP | +2.518 |
areth | +2.492 |
HTTP | +2.342 |
Neg logit contributions | |
isine | -2.812 |
opian | -2.560 |
chen | -2.496 |
ulic | -2.417 |
chefs | -2.319 |
Token | Cult |
Token ID | 22449 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
ONES | +0.731 |
Naz | +0.720 |
OSP | +0.692 |
areth | +0.685 |
HTTP | +0.644 |
Neg logit contributions | |
isine | -0.784 |
opian | -0.715 |
chen | -0.701 |
ulic | -0.673 |
chefs | -0.658 |
Token | ured |
Token ID | 1522 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
ONES | +0.931 |
Naz | +0.920 |
OSP | +0.891 |
areth | +0.883 |
HTTP | +0.838 |
Neg logit contributions | |
isine | -0.685 |
opian | -0.609 |
chen | -0.595 |
ulic | -0.567 |
chefs | -0.549 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ONES | +0.475 |
Naz | +0.467 |
OSP | +0.448 |
areth | +0.443 |
HTTP | +0.415 |
Neg logit contributions | |
isine | -0.567 |
opian | -0.519 |
chen | -0.510 |
ulic | -0.490 |
chefs | -0.481 |
Token | bird |
Token ID | 6512 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
isine | +0.649 |
opian | +0.593 |
chen | +0.581 |
ulic | +0.556 |
chefs | +0.547 |
Neg logit contributions | |
ONES | -0.619 |
Naz | -0.610 |
OSP | -0.587 |
areth | -0.583 |
HTTP | -0.548 |
Token | sey |
Token ID | 4397 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
isine | +0.200 |
opian | +0.184 |
chen | +0.181 |
ulic | +0.173 |
chefs | +0.171 |
Neg logit contributions | |
ONES | -0.161 |
Naz | -0.157 |
OSP | -0.151 |
areth | -0.150 |
HTTP | -0.140 |
Token | e |
Token ID | 68 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
ONES | +0.143 |
Naz | +0.138 |
OSP | +0.131 |
areth | +0.127 |
HTTP | +0.116 |
Neg logit contributions | |
isine | -0.351 |
opian | -0.329 |
chen | -0.324 |
ulic | -0.315 |
chefs | -0.310 |
Token | map |
Token ID | 3975 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
isine | +0.586 |
opian | +0.538 |
chen | +0.530 |
ulic | +0.508 |
chefs | +0.500 |
Neg logit contributions | |
ONES | -0.479 |
Naz | -0.471 |
OSP | -0.453 |
areth | -0.447 |
HTTP | -0.419 |
Token | of |
Token ID | 286 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
isine | +1.481 |
opian | +1.364 |
chen | +1.347 |
ulic | +1.291 |
chefs | +1.264 |
Neg logit contributions | |
ONES | -1.186 |
Naz | -1.170 |
OSP | -1.119 |
areth | -1.108 |
HTTP | -1.033 |
Token | Brigham |
Token ID | 37434 |
Feature activation | +9.62e+00 |
Pos logit contributions | |
ONES | +0.715 |
Naz | +0.704 |
OSP | +0.679 |
areth | +0.672 |
HTTP | +0.633 |
Neg logit contributions | |
isine | -0.735 |
opian | -0.669 |
chen | -0.656 |
ulic | -0.629 |
chefs | -0.618 |
Token | City |
Token ID | 2254 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
ONES | +6.966 |
Naz | +6.677 |
OSP | +6.533 |
areth | +6.505 |
prophets | +6.117 |
Neg logit contributions | |
isine | -8.422 |
opian | -7.622 |
chen | -7.437 |
ulic | -7.201 |
chefs | -7.030 |
Token | , |
Token ID | 11 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
ONES | +0.637 |
Naz | +0.627 |
OSP | +0.599 |
areth | +0.591 |
HTTP | +0.552 |
Neg logit contributions | |
isine | -0.848 |
opian | -0.781 |
chen | -0.767 |
ulic | -0.738 |
chefs | -0.727 |
Token | Utah |
Token ID | 10202 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ONES | +0.378 |
Naz | +0.371 |
OSP | +0.355 |
areth | +0.351 |
HTTP | +0.327 |
Neg logit contributions | |
isine | -0.519 |
opian | -0.478 |
chen | -0.470 |
ulic | -0.454 |
chefs | -0.445 |
Token | in |
Token ID | 287 |
Feature activation | +3.89e-03 |
Pos logit contributions | |
ONES | +0.713 |
Naz | +0.700 |
OSP | +0.670 |
areth | +0.662 |
HTTP | +0.617 |
Neg logit contributions | |
isine | -0.966 |
opian | -0.889 |
chen | -0.873 |
ulic | -0.843 |
chefs | -0.825 |
Token | 18 |
Token ID | 1248 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ONES | +0.003 |
Naz | +0.003 |
OSP | +0.003 |
areth | +0.003 |
HTTP | +0.003 |
Neg logit contributions | |
isine | -0.003 |
opian | -0.003 |
chen | -0.003 |
ulic | -0.002 |
chefs | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ONES | +0.290 |
Naz | +0.285 |
OSP | +0.274 |
areth | +0.270 |
HTTP | +0.255 |
Neg logit contributions | |
isine | -0.367 |
opian | -0.337 |
chen | -0.334 |
ulic | -0.320 |
chefs | -0.314 |
Token |
|
Token ID | 198 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
isine | +0.239 |
opian | +0.220 |
chen | +0.214 |
ulic | +0.209 |
chefs | +0.206 |
Neg logit contributions | |
ONES | -0.152 |
Naz | -0.151 |
OSP | -0.142 |
areth | -0.140 |
HTTP | -0.130 |
Token | 16 |
Token ID | 1433 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
isine | +0.260 |
opian | +0.241 |
chen | +0.241 |
ulic | +0.230 |
chefs | +0.225 |
Neg logit contributions | |
ONES | -0.160 |
Naz | -0.155 |
OSP | -0.149 |
areth | -0.148 |
wip | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
isine | +1.354 |
chen | +1.243 |
opian | +1.223 |
ulic | +1.161 |
chefs | +1.142 |
Neg logit contributions | |
ONES | -1.272 |
Naz | -1.239 |
OSP | -1.211 |
areth | -1.185 |
HTTP | -1.136 |
Token | Pat |
Token ID | 3208 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
ONES | +0.672 |
Naz | +0.661 |
OSP | +0.635 |
areth | +0.625 |
HTTP | +0.589 |
Neg logit contributions | |
isine | -0.877 |
opian | -0.805 |
chen | -0.798 |
ulic | -0.764 |
chefs | -0.749 |
Token | MacArthur |
Token ID | 46626 |
Feature activation | +9.58e+00 |
Pos logit contributions | |
ONES | +0.451 |
Naz | +0.444 |
OSP | +0.426 |
areth | +0.420 |
HTTP | +0.397 |
Neg logit contributions | |
isine | -0.504 |
opian | -0.461 |
chen | -0.454 |
ulic | -0.434 |
chefs | -0.424 |
Token | ( |
Token ID | 357 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
ONES | +5.923 |
Naz | +5.765 |
OSP | +5.541 |
areth | +5.422 |
Sing | +5.066 |
Neg logit contributions | |
isine | -9.274 |
opian | -8.633 |
chen | -8.184 |
ulic | -7.967 |
chefs | -7.935 |
Token | 147 |
Token ID | 20198 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
ONES | +0.054 |
Naz | +0.053 |
OSP | +0.050 |
areth | +0.050 |
ospels | +0.046 |
Neg logit contributions | |
isine | -0.082 |
opian | -0.076 |
chen | -0.075 |
ulic | -0.073 |
chefs | -0.071 |
Token | ) |
Token ID | 8 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
isine | +1.917 |
opian | +1.762 |
chen | +1.744 |
ulic | +1.675 |
chefs | +1.638 |
Neg logit contributions | |
ONES | -1.449 |
Naz | -1.420 |
OSP | -1.362 |
areth | -1.346 |
HTTP | -1.259 |
Token | ( |
Token ID | 357 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
ONES | +0.408 |
Naz | +0.401 |
OSP | +0.384 |
areth | +0.384 |
ospels | +0.359 |
Neg logit contributions | |
isine | -0.500 |
opian | -0.457 |
chen | -0.453 |
ulic | -0.434 |
chefs | -0.424 |
Token | 35 |
Token ID | 2327 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
ONES | +0.494 |
Naz | +0.486 |
OSP | +0.462 |
areth | +0.455 |
HTTP | +0.424 |
Neg logit contributions | |
isine | -0.760 |
opian | -0.701 |
chen | -0.685 |
ulic | -0.666 |
chefs | -0.655 |
Token | support |
Token ID | 1104 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
isine | +0.485 |
opian | +0.450 |
chen | +0.446 |
ulic | +0.429 |
chefs | +0.427 |
Neg logit contributions | |
ONES | -0.251 |
Naz | -0.244 |
OSP | -0.231 |
areth | -0.226 |
ospels | -0.207 |
Token | the |
Token ID | 262 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
ONES | +2.158 |
Naz | +2.129 |
OSP | +2.044 |
areth | +2.015 |
HTTP | +1.892 |
Neg logit contributions | |
isine | -2.542 |
opian | -2.337 |
chen | -2.276 |
ulic | -2.218 |
chefs | -2.142 |
Token | mission |
Token ID | 4365 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
isine | +0.624 |
opian | +0.577 |
chen | +0.562 |
ulic | +0.544 |
chefs | +0.530 |
Neg logit contributions | |
ONES | -0.465 |
Naz | -0.460 |
OSP | -0.437 |
areth | -0.431 |
HTTP | -0.402 |
Token | of |
Token ID | 286 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
isine | +0.225 |
opian | +0.206 |
chen | +0.201 |
ulic | +0.194 |
chefs | +0.190 |
Neg logit contributions | |
ONES | -0.200 |
Naz | -0.197 |
OSP | -0.190 |
areth | -0.188 |
HTTP | -0.176 |
Token | New |
Token ID | 968 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
isine | +0.216 |
opian | +0.198 |
chen | +0.195 |
ulic | +0.188 |
chefs | +0.184 |
Neg logit contributions | |
ONES | -0.176 |
Naz | -0.173 |
OSP | -0.166 |
areth | -0.164 |
HTTP | -0.153 |
Token | Advent |
Token ID | 33732 |
Feature activation | +9.32e+00 |
Pos logit contributions | |
ONES | +0.265 |
Naz | +0.239 |
OSP | +0.207 |
areth | +0.193 |
ospels | +0.133 |
Neg logit contributions | |
isine | -1.953 |
opian | -1.859 |
chen | -1.836 |
ulic | -1.797 |
chefs | -1.775 |
Token | and |
Token ID | 290 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
ONES | +4.061 |
Naz | +4.000 |
areth | +3.879 |
OSP | +3.476 |
Sing | +3.466 |
Neg logit contributions | |
isine | -10.769 |
opian | -9.914 |
ulic | -9.798 |
chen | -9.660 |
untled | -9.546 |
Token | get |
Token ID | 651 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ONES | +0.672 |
Naz | +0.652 |
OSP | +0.628 |
areth | +0.615 |
ospels | +0.576 |
Neg logit contributions | |
isine | -0.881 |
opian | -0.818 |
chen | -0.808 |
ulic | -0.775 |
chefs | -0.762 |
Token | the |
Token ID | 262 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ONES | +0.092 |
Naz | +0.089 |
areth | +0.086 |
OSP | +0.086 |
ospels | +0.081 |
Neg logit contributions | |
isine | -0.090 |
opian | -0.082 |
chen | -0.081 |
ulic | -0.077 |
chefs | -0.077 |
Token | full |
Token ID | 1336 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
isine | +1.178 |
chen | +1.060 |
opian | +1.044 |
chefs | +0.991 |
ulic | +0.961 |
Neg logit contributions | |
ONES | -1.770 |
Naz | -1.669 |
OSP | -1.666 |
areth | -1.633 |
HTTP | -1.614 |
Token | contents |
Token ID | 10154 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
isine | +1.246 |
opian | +1.120 |
chen | +1.103 |
ulic | +1.049 |
chefs | +1.030 |
Neg logit contributions | |
ONES | -1.351 |
Naz | -1.322 |
OSP | -1.281 |
areth | -1.267 |
HTTP | -1.198 |
Token | a |
Token ID | 257 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
ONES | +1.877 |
Naz | +1.838 |
OSP | +1.769 |
areth | +1.745 |
ospels | +1.642 |
Neg logit contributions | |
isine | -2.055 |
opian | -1.878 |
chen | -1.824 |
ulic | -1.762 |
chefs | -1.693 |
Token | person |
Token ID | 1048 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
ONES | +0.656 |
Naz | +0.648 |
OSP | +0.624 |
areth | +0.613 |
HTTP | +0.581 |
Neg logit contributions | |
isine | -0.667 |
opian | -0.607 |
chen | -0.589 |
ulic | -0.567 |
chefs | -0.551 |
Token | of |
Token ID | 286 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
isine | +1.982 |
chen | +1.772 |
opian | +1.771 |
ulic | +1.672 |
chefs | +1.655 |
Neg logit contributions | |
ONES | -2.040 |
Naz | -2.002 |
OSP | -1.932 |
areth | -1.929 |
ospels | -1.819 |
Token | interest |
Token ID | 1393 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
isine | +1.233 |
opian | +1.139 |
chen | +1.128 |
ulic | +1.078 |
chefs | +1.070 |
Neg logit contributions | |
ONES | -0.812 |
Naz | -0.795 |
OSP | -0.757 |
areth | -0.753 |
HTTP | -0.694 |
Token | at |
Token ID | 379 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
isine | +1.030 |
opian | +0.928 |
chen | +0.913 |
ulic | +0.869 |
chefs | +0.850 |
Neg logit contributions | |
ONES | -1.156 |
Naz | -1.139 |
OSP | -1.100 |
areth | -1.090 |
ospels | -1.031 |
Token | Brigham |
Token ID | 37434 |
Feature activation | +9.26e+00 |
Pos logit contributions | |
isine | +0.481 |
opian | +0.439 |
chen | +0.433 |
ulic | +0.413 |
chefs | +0.405 |
Neg logit contributions | |
ONES | -0.457 |
Naz | -0.450 |
OSP | -0.432 |
areth | -0.429 |
HTTP | -0.405 |
Token | and |
Token ID | 290 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
ONES | +6.483 |
OSP | +6.155 |
Naz | +6.149 |
areth | +5.962 |
prophets | +5.580 |
Neg logit contributions | |
isine | -8.341 |
opian | -7.624 |
chen | -7.362 |
ulic | -7.083 |
chefs | -6.945 |
Token | Women |
Token ID | 6926 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
isine | +0.920 |
opian | +0.856 |
chen | +0.845 |
ulic | +0.816 |
chefs | +0.802 |
Neg logit contributions | |
ONES | -0.499 |
Naz | -0.489 |
OSP | -0.459 |
areth | -0.454 |
HTTP | -0.418 |
Token | 's |
Token ID | 338 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
isine | +2.368 |
opian | +2.182 |
chen | +2.134 |
ulic | +2.075 |
chefs | +2.027 |
Neg logit contributions | |
ONES | -1.594 |
Naz | -1.578 |
OSP | -1.508 |
areth | -1.486 |
HTTP | -1.372 |
Token | Hospital |
Token ID | 9256 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
isine | +0.752 |
opian | +0.697 |
chen | +0.694 |
ulic | +0.664 |
chefs | +0.655 |
Neg logit contributions | |
ONES | -0.469 |
Naz | -0.457 |
OSP | -0.429 |
areth | -0.429 |
HTTP | -0.397 |
Token | , |
Token ID | 11 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
ONES | +0.723 |
Naz | +0.711 |
OSP | +0.684 |
areth | +0.676 |
HTTP | +0.634 |
Neg logit contributions | |
isine | -0.829 |
opian | -0.759 |
chen | -0.743 |
ulic | -0.716 |
chefs | -0.699 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
isine | +0.329 |
opian | +0.303 |
chen | +0.299 |
ulic | +0.285 |
chefs | +0.284 |
Neg logit contributions | |
ONES | -0.254 |
Naz | -0.249 |
OSP | -0.239 |
areth | -0.235 |
HTTP | -0.222 |
Token | multi |
Token ID | 5021 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ONES | +1.276 |
Naz | +1.262 |
OSP | +1.209 |
areth | +1.197 |
HTTP | +1.125 |
Neg logit contributions | |
isine | -1.410 |
opian | -1.279 |
chen | -1.251 |
ulic | -1.209 |
chefs | -1.175 |
Token | - |
Token ID | 12 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
ONES | +1.007 |
Naz | +0.977 |
OSP | +0.928 |
areth | +0.915 |
HTTP | +0.840 |
Neg logit contributions | |
isine | -1.701 |
opian | -1.567 |
chen | -1.549 |
ulic | -1.502 |
chefs | -1.466 |
Token | ethnic |
Token ID | 38546 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
ONES | +0.469 |
Naz | +0.459 |
OSP | +0.445 |
areth | +0.441 |
HTTP | +0.415 |
Neg logit contributions | |
isine | -0.457 |
opian | -0.413 |
chen | -0.407 |
ulic | -0.389 |
chefs | -0.377 |
Token | society |
Token ID | 3592 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ONES | +2.411 |
Naz | +2.367 |
OSP | +2.255 |
areth | +2.238 |
HTTP | +2.061 |
Neg logit contributions | |
isine | -3.580 |
opian | -3.305 |
chen | -3.240 |
ulic | -3.150 |
chefs | -3.072 |
Token | hosp |
Token ID | 10496 |
Feature activation | +8.87e+00 |
Pos logit contributions | |
ONES | +1.531 |
Naz | +1.506 |
OSP | +1.449 |
areth | +1.431 |
HTTP | +1.345 |
Neg logit contributions | |
isine | -1.600 |
opian | -1.451 |
chen | -1.422 |
ulic | -1.370 |
chefs | -1.329 |
Token | itable |
Token ID | 4674 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
ONES | +5.275 |
Naz | +5.218 |
areth | +5.130 |
OSP | +5.012 |
Sing | +4.678 |
Neg logit contributions | |
isine | -8.281 |
opian | -7.696 |
chefs | -7.331 |
chen | -7.328 |
ulic | -7.291 |
Token | to |
Token ID | 284 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ONES | +2.558 |
Naz | +2.517 |
OSP | +2.409 |
areth | +2.381 |
HTTP | +2.220 |
Neg logit contributions | |
isine | -3.311 |
opian | -3.039 |
chen | -2.986 |
ulic | -2.884 |
chefs | -2.822 |
Token | all |
Token ID | 477 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
ONES | +0.122 |
Naz | +0.120 |
OSP | +0.116 |
areth | +0.115 |
HTTP | +0.109 |
Neg logit contributions | |
isine | -0.121 |
opian | -0.110 |
chen | -0.108 |
ulic | -0.103 |
chefs | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
ONES | +0.052 |
Naz | +0.051 |
OSP | +0.049 |
areth | +0.048 |
HTTP | +0.046 |
Neg logit contributions | |
isine | -0.062 |
opian | -0.057 |
chen | -0.056 |
ulic | -0.053 |
chefs | -0.053 |
Token | Israeli |
Token ID | 6085 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
isine | +0.088 |
opian | +0.081 |
chen | +0.080 |
ulic | +0.077 |
chefs | +0.075 |
Neg logit contributions | |
ONES | -0.066 |
Naz | -0.065 |
OSP | -0.062 |
areth | -0.061 |
HTTP | -0.057 |
Token | ) |
Token ID | 8 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ONES | +0.325 |
Naz | +0.316 |
OSP | +0.306 |
areth | +0.305 |
wip | +0.283 |
Neg logit contributions | |
isine | -0.394 |
chen | -0.360 |
opian | -0.359 |
ulic | -0.345 |
chefs | -0.335 |
Token | who |
Token ID | 508 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
ONES | +0.795 |
Naz | +0.780 |
OSP | +0.747 |
areth | +0.738 |
HTTP | +0.689 |
Neg logit contributions | |
isine | -1.046 |
opian | -0.962 |
chen | -0.945 |
ulic | -0.911 |
chefs | -0.893 |
Token | were |
Token ID | 547 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ONES | +2.348 |
Naz | +2.331 |
OSP | +2.206 |
areth | +2.194 |
HTTP | +2.027 |
Neg logit contributions | |
isine | -3.249 |
opian | -2.980 |
chen | -2.907 |
ulic | -2.829 |
chefs | -2.749 |
Token | marching |
Token ID | 26409 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ONES | +1.432 |
Naz | +1.422 |
OSP | +1.358 |
areth | +1.348 |
HTTP | +1.265 |
Neg logit contributions | |
isine | -1.508 |
opian | -1.377 |
chen | -1.337 |
ulic | -1.289 |
chefs | -1.247 |
Token | on |
Token ID | 319 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
ONES | +1.187 |
Naz | +1.174 |
OSP | +1.124 |
areth | +1.117 |
HTTP | +1.049 |
Neg logit contributions | |
isine | -1.235 |
opian | -1.122 |
chen | -1.099 |
ulic | -1.056 |
chefs | -1.029 |
Token | Downing |
Token ID | 31355 |
Feature activation | +8.61e+00 |
Pos logit contributions | |
ONES | +0.630 |
Naz | +0.617 |
OSP | +0.597 |
areth | +0.589 |
HTTP | +0.554 |
Neg logit contributions | |
isine | -0.706 |
opian | -0.646 |
chen | -0.633 |
ulic | -0.608 |
chefs | -0.598 |
Token | Street |
Token ID | 3530 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
ONES | +5.246 |
Naz | +5.103 |
areth | +4.943 |
OSP | +4.870 |
ships | +4.487 |
Neg logit contributions | |
isine | -8.540 |
opian | -7.897 |
chen | -7.479 |
ulic | -7.370 |
chefs | -7.205 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ONES | +2.937 |
Naz | +2.902 |
OSP | +2.760 |
areth | +2.756 |
HTTP | +2.552 |
Neg logit contributions | |
isine | -3.726 |
opian | -3.423 |
chen | -3.325 |
ulic | -3.228 |
chefs | -3.140 |
Token | clashed |
Token ID | 37003 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
ONES | +0.743 |
Naz | +0.730 |
OSP | +0.701 |
areth | +0.692 |
HTTP | +0.648 |
Neg logit contributions | |
isine | -0.918 |
opian | -0.842 |
chen | -0.828 |
ulic | -0.797 |
chefs | -0.780 |
Token | with |
Token ID | 351 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
isine | +1.503 |
opian | +1.366 |
chen | +1.347 |
ulic | +1.284 |
chefs | +1.278 |
Neg logit contributions | |
ONES | -1.526 |
Naz | -1.504 |
OSP | -1.472 |
areth | -1.446 |
ospels | -1.377 |
Token | anti |
Token ID | 3098 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
ONES | +1.103 |
Naz | +1.086 |
OSP | +1.042 |
areth | +1.032 |
HTTP | +0.970 |
Neg logit contributions | |
isine | -1.189 |
opian | -1.084 |
chen | -1.062 |
ulic | -1.020 |
chefs | -0.994 |
Token | - |
Token ID | 12 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
isine | +0.036 |
opian | +0.034 |
chen | +0.033 |
ulic | +0.032 |
chefs | +0.032 |
Neg logit contributions | |
ONES | -0.019 |
Naz | -0.019 |
OSP | -0.018 |
areth | -0.018 |
HTTP | -0.016 |
Token | bad |
Token ID | 14774 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
isine | +0.155 |
opian | +0.142 |
chen | +0.141 |
ulic | +0.132 |
chefs | +0.129 |
Neg logit contributions | |
ONES | -0.140 |
Naz | -0.136 |
OSP | -0.133 |
areth | -0.131 |
ospels | -0.123 |
Token | - |
Token ID | 12 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
isine | +0.321 |
opian | +0.294 |
chen | +0.292 |
ulic | +0.279 |
chefs | +0.276 |
Neg logit contributions | |
ONES | -0.212 |
Naz | -0.206 |
OSP | -0.197 |
areth | -0.195 |
ospels | -0.182 |
Token | guy |
Token ID | 22932 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
isine | +0.348 |
opian | +0.310 |
chen | +0.308 |
ulic | +0.286 |
chefs | +0.278 |
Neg logit contributions | |
ONES | -0.431 |
Naz | -0.424 |
OSP | -0.413 |
areth | -0.405 |
ospels | -0.387 |
Token | , |
Token ID | 11 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
ONES | +1.336 |
Naz | +1.316 |
OSP | +1.264 |
areth | +1.253 |
HTTP | +1.177 |
Neg logit contributions | |
isine | -1.471 |
opian | -1.343 |
chen | -1.315 |
ulic | -1.266 |
chefs | -1.235 |
Token | unconditional |
Token ID | 42423 |
Feature activation | +8.55e+00 |
Pos logit contributions | |
ONES | +0.386 |
Naz | +0.378 |
OSP | +0.365 |
areth | +0.359 |
ospels | +0.336 |
Neg logit contributions | |
isine | -0.486 |
opian | -0.446 |
chen | -0.438 |
ulic | -0.421 |
chefs | -0.414 |
Token | - |
Token ID | 12 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
Naz | +5.811 |
ONES | +5.685 |
OSP | +5.341 |
areth | +5.314 |
wip | +5.132 |
Neg logit contributions | |
isine | -7.725 |
opian | -6.985 |
chen | -6.887 |
ulic | -6.797 |
untled | -6.498 |
Token | l |
Token ID | 75 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
isine | +0.019 |
opian | +0.018 |
chen | +0.018 |
ulic | +0.017 |
chefs | +0.016 |
Neg logit contributions | |
ONES | -0.017 |
Naz | -0.017 |
OSP | -0.016 |
areth | -0.016 |
ospels | -0.015 |
Token | oyal |
Token ID | 4815 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
isine | +0.019 |
opian | +0.018 |
chen | +0.017 |
ulic | +0.017 |
chefs | +0.016 |
Neg logit contributions | |
ONES | -0.017 |
Naz | -0.017 |
OSP | -0.016 |
areth | -0.016 |
HTTP | -0.015 |
Token | ty |
Token ID | 774 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ONES | +2.738 |
Naz | +2.705 |
OSP | +2.600 |
areth | +2.578 |
HTTP | +2.423 |
Neg logit contributions | |
isine | -2.877 |
opian | -2.617 |
chen | -2.565 |
ulic | -2.472 |
chefs | -2.405 |
Token | - |
Token ID | 12 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ONES | +1.554 |
Naz | +1.527 |
OSP | +1.461 |
areth | +1.444 |
HTTP | +1.346 |
Neg logit contributions | |
isine | -2.080 |
opian | -1.913 |
chen | -1.879 |
ulic | -1.813 |
chefs | -1.776 |
Token | a |
Token ID | 257 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ONES | +0.537 |
Naz | +0.528 |
OSP | +0.508 |
areth | +0.502 |
HTTP | +0.471 |
Neg logit contributions | |
isine | -0.602 |
opian | -0.549 |
chen | -0.539 |
ulic | -0.519 |
chefs | -0.505 |
Token | patient |
Token ID | 5827 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
ONES | +0.008 |
Naz | +0.007 |
OSP | +0.007 |
areth | +0.007 |
HTTP | +0.007 |
Neg logit contributions | |
isine | -0.009 |
opian | -0.009 |
chen | -0.008 |
ulic | -0.008 |
chefs | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
isine | +2.812 |
opian | +2.623 |
chen | +2.568 |
ulic | +2.469 |
chefs | +2.454 |
Neg logit contributions | |
ONES | -2.029 |
Naz | -1.987 |
OSP | -1.897 |
areth | -1.854 |
HTTP | -1.744 |
Token | � |
Token ID | 247 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
isine | +0.607 |
opian | +0.557 |
chen | +0.548 |
ulic | +0.529 |
chefs | +0.518 |
Neg logit contributions | |
ONES | -0.439 |
Naz | -0.432 |
OSP | -0.413 |
areth | -0.410 |
HTTP | -0.380 |
Token | s |
Token ID | 82 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
isine | +0.556 |
opian | +0.514 |
chen | +0.505 |
ulic | +0.487 |
chefs | +0.474 |
Neg logit contributions | |
ONES | -0.430 |
Naz | -0.421 |
OSP | -0.404 |
areth | -0.396 |
HTTP | -0.372 |
Token | immune |
Token ID | 10900 |
Feature activation | +8.38e+00 |
Pos logit contributions | |
isine | +0.977 |
opian | +0.903 |
chen | +0.881 |
ulic | +0.841 |
chefs | +0.828 |
Neg logit contributions | |
ONES | -0.864 |
Naz | -0.849 |
OSP | -0.812 |
areth | -0.807 |
HTTP | -0.757 |
Token | system |
Token ID | 1080 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ONES | +4.466 |
Naz | +4.429 |
OSP | +4.365 |
areth | +4.200 |
HTTP | +3.883 |
Neg logit contributions | |
isine | -8.717 |
opian | -7.996 |
chen | -7.947 |
ulic | -7.685 |
chefs | -7.512 |
Token | attacks |
Token ID | 3434 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ONES | +0.714 |
Naz | +0.701 |
OSP | +0.669 |
areth | +0.660 |
HTTP | +0.613 |
Neg logit contributions | |
isine | -1.045 |
opian | -0.964 |
chen | -0.948 |
ulic | -0.916 |
chefs | -0.898 |
Token | the |
Token ID | 262 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
ONES | +0.226 |
Naz | +0.222 |
OSP | +0.214 |
areth | +0.211 |
ospels | +0.199 |
Neg logit contributions | |
isine | -0.243 |
opian | -0.222 |
chen | -0.217 |
ulic | -0.209 |
chefs | -0.205 |
Token | new |
Token ID | 649 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
isine | +0.348 |
opian | +0.319 |
chen | +0.312 |
ulic | +0.300 |
chefs | +0.294 |
Neg logit contributions | |
ONES | -0.305 |
Naz | -0.299 |
OSP | -0.287 |
areth | -0.285 |
HTTP | -0.267 |
Token | organ |
Token ID | 1618 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
isine | +1.159 |
opian | +1.069 |
chen | +1.045 |
ulic | +1.000 |
chefs | +0.983 |
Neg logit contributions | |
ONES | -0.974 |
Naz | -0.953 |
OSP | -0.915 |
areth | -0.906 |
ospels | -0.850 |
Token | Bird |
Token ID | 42562 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ONES | +0.062 |
Naz | +0.061 |
OSP | +0.058 |
areth | +0.058 |
ospels | +0.053 |
Neg logit contributions | |
isine | -0.106 |
opian | -0.098 |
chen | -0.097 |
ulic | -0.093 |
chefs | -0.091 |
Token | sey |
Token ID | 4397 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ONES | +0.145 |
Naz | +0.143 |
OSP | +0.138 |
areth | +0.137 |
HTTP | +0.129 |
Neg logit contributions | |
isine | -0.143 |
opian | -0.130 |
chen | -0.128 |
ulic | -0.121 |
chefs | -0.119 |
Token | e |
Token ID | 68 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
isine | +0.244 |
opian | +0.230 |
chen | +0.225 |
ulic | +0.220 |
chefs | +0.215 |
Neg logit contributions | |
ONES | -0.109 |
Naz | -0.105 |
OSP | -0.101 |
areth | -0.097 |
HTTP | -0.089 |
Token | view |
Token ID | 1570 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
isine | +0.981 |
opian | +0.903 |
chen | +0.889 |
ulic | +0.857 |
chefs | +0.847 |
Neg logit contributions | |
ONES | -0.729 |
Naz | -0.719 |
OSP | -0.692 |
areth | -0.679 |
HTTP | -0.638 |
Token | of |
Token ID | 286 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
isine | +1.915 |
opian | +1.759 |
chen | +1.724 |
ulic | +1.641 |
chefs | +1.614 |
Neg logit contributions | |
ONES | -1.776 |
Naz | -1.750 |
OSP | -1.672 |
areth | -1.665 |
HTTP | -1.571 |
Token | Brigham |
Token ID | 37434 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
ONES | +0.360 |
Naz | +0.352 |
OSP | +0.333 |
areth | +0.329 |
HTTP | +0.302 |
Neg logit contributions | |
isine | -0.670 |
opian | -0.624 |
chen | -0.614 |
ulic | -0.595 |
chefs | -0.587 |
Token | City |
Token ID | 2254 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
ONES | +5.977 |
Naz | +5.710 |
areth | +5.686 |
OSP | +5.680 |
prophets | +5.319 |
Neg logit contributions | |
isine | -6.998 |
opian | -6.260 |
chen | -6.101 |
ulic | -5.906 |
untled | -5.806 |
Token | , |
Token ID | 11 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ONES | +0.615 |
Naz | +0.604 |
OSP | +0.576 |
areth | +0.570 |
HTTP | +0.531 |
Neg logit contributions | |
isine | -0.837 |
opian | -0.772 |
chen | -0.758 |
ulic | -0.730 |
chefs | -0.717 |
Token | Utah |
Token ID | 10202 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
ONES | +0.222 |
Naz | +0.218 |
OSP | +0.208 |
areth | +0.206 |
HTTP | +0.191 |
Neg logit contributions | |
isine | -0.319 |
opian | -0.294 |
chen | -0.290 |
ulic | -0.280 |
chefs | -0.275 |
Token | Date |
Token ID | 7536 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ONES | +0.433 |
Naz | +0.425 |
OSP | +0.408 |
areth | +0.404 |
HTTP | +0.378 |
Neg logit contributions | |
isine | -0.518 |
opian | -0.474 |
chen | -0.465 |
ulic | -0.448 |
chefs | -0.438 |
Token | : |
Token ID | 25 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
isine | +1.200 |
opian | +1.091 |
chen | +1.074 |
ulic | +1.030 |
chefs | +1.006 |
Neg logit contributions | |
ONES | -1.090 |
Naz | -1.072 |
OSP | -1.031 |
areth | -1.018 |
HTTP | -0.959 |
Token |
|
Token ID | 198 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
ONES | +0.439 |
Naz | +0.424 |
OSP | +0.409 |
areth | +0.407 |
ospels | +0.378 |
Neg logit contributions | |
isine | -0.678 |
opian | -0.623 |
chen | -0.623 |
ulic | -0.598 |
chefs | -0.585 |
Token |
|
Token ID | 198 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ONES | +0.225 |
Naz | +0.223 |
OSP | +0.211 |
areth | +0.206 |
HTTP | +0.194 |
Neg logit contributions | |
isine | -0.347 |
opian | -0.321 |
chen | -0.312 |
ulic | -0.305 |
chefs | -0.300 |
Token | A |
Token ID | 32 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ONES | +0.128 |
Naz | +0.122 |
areth | +0.118 |
OSP | +0.118 |
wip | +0.110 |
Neg logit contributions | |
isine | -0.211 |
chen | -0.195 |
opian | -0.194 |
ulic | -0.187 |
chefs | -0.182 |
Token | bench |
Token ID | 7624 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
ONES | +0.991 |
Naz | +0.969 |
OSP | +0.926 |
areth | +0.917 |
ospels | +0.856 |
Neg logit contributions | |
isine | -1.356 |
opian | -1.246 |
chen | -1.232 |
ulic | -1.187 |
chefs | -1.161 |
Token | of |
Token ID | 286 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ONES | +1.825 |
Naz | +1.798 |
OSP | +1.719 |
areth | +1.702 |
HTTP | +1.586 |
Neg logit contributions | |
isine | -2.351 |
opian | -2.165 |
chen | -2.116 |
ulic | -2.049 |
chefs | -1.999 |
Token | justices |
Token ID | 27818 |
Feature activation | +8.12e+00 |
Pos logit contributions | |
ONES | +0.224 |
Naz | +0.218 |
OSP | +0.211 |
areth | +0.207 |
ospels | +0.195 |
Neg logit contributions | |
isine | -0.278 |
chen | -0.251 |
opian | -0.251 |
ulic | -0.241 |
chefs | -0.238 |
Token | H |
Token ID | 367 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Naz | +6.032 |
ONES | +5.976 |
areth | +5.663 |
OSP | +5.601 |
Sing | +5.390 |
Neg logit contributions | |
isine | -6.886 |
opian | -6.484 |
chen | -6.101 |
ulic | -6.009 |
chefs | -5.701 |
Token | L |
Token ID | 406 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ONES | +0.847 |
Naz | +0.833 |
OSP | +0.801 |
areth | +0.792 |
HTTP | +0.748 |
Neg logit contributions | |
isine | -0.882 |
opian | -0.801 |
chen | -0.787 |
ulic | -0.756 |
chefs | -0.736 |
Token | D |
Token ID | 360 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
ONES | +0.256 |
Naz | +0.251 |
OSP | +0.242 |
areth | +0.238 |
HTTP | +0.226 |
Neg logit contributions | |
isine | -0.282 |
opian | -0.257 |
chen | -0.252 |
ulic | -0.243 |
chefs | -0.236 |
Token | att |
Token ID | 1078 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
ONES | +0.021 |
Naz | +0.021 |
OSP | +0.020 |
areth | +0.020 |
HTTP | +0.019 |
Neg logit contributions | |
isine | -0.025 |
opian | -0.023 |
chen | -0.022 |
ulic | -0.022 |
chefs | -0.021 |
Token | u |
Token ID | 84 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
isine | +0.295 |
opian | +0.268 |
chen | +0.262 |
ulic | +0.251 |
chefs | +0.245 |
Neg logit contributions | |
ONES | -0.312 |
Naz | -0.308 |
OSP | -0.297 |
areth | -0.294 |
HTTP | -0.278 |
Token | on |
Token ID | 319 |
Feature activation | -2.27e-03 |
Pos logit contributions | |
ONES | +1.707 |
Naz | +1.685 |
OSP | +1.627 |
areth | +1.596 |
Sing | +1.505 |
Neg logit contributions | |
isine | -1.872 |
opian | -1.713 |
chen | -1.665 |
ulic | -1.610 |
chefs | -1.560 |
Token | Nov |
Token ID | 5267 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
isine | +0.002 |
opian | +0.002 |
chen | +0.002 |
ulic | +0.002 |
chefs | +0.002 |
Neg logit contributions | |
ONES | -0.002 |
Naz | -0.002 |
OSP | -0.002 |
areth | -0.002 |
HTTP | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
ONES | +0.410 |
Naz | +0.401 |
OSP | +0.384 |
areth | +0.377 |
CTV | +0.354 |
Neg logit contributions | |
isine | -0.625 |
opian | -0.572 |
chen | -0.550 |
ulic | -0.543 |
chefs | -0.536 |
Token | 8 |
Token ID | 807 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
ONES | +0.410 |
Naz | +0.407 |
OSP | +0.388 |
areth | +0.380 |
Sing | +0.364 |
Neg logit contributions | |
isine | -0.456 |
opian | -0.412 |
chen | -0.395 |
ulic | -0.388 |
chefs | -0.377 |
Token | in |
Token ID | 287 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
isine | +0.821 |
opian | +0.749 |
chen | +0.741 |
ulic | +0.708 |
chefs | +0.692 |
Neg logit contributions | |
ONES | -0.708 |
Naz | -0.692 |
OSP | -0.666 |
areth | -0.658 |
HTTP | -0.621 |
Token | Vaughan |
Token ID | 47451 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
ONES | +0.550 |
Naz | +0.541 |
OSP | +0.521 |
areth | +0.515 |
HTTP | +0.485 |
Neg logit contributions | |
isine | -0.586 |
opian | -0.534 |
chen | -0.523 |
ulic | -0.503 |
chefs | -0.491 |
Token | , |
Token ID | 11 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Naz | +4.645 |
ONES | +4.612 |
OSP | +4.382 |
areth | +4.240 |
Sing | +4.025 |
Neg logit contributions | |
isine | -7.998 |
opian | -7.538 |
chen | -7.294 |
ulic | -7.142 |
untled | -6.996 |
Token | Ont |
Token ID | 9463 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
ONES | +0.253 |
Naz | +0.249 |
OSP | +0.240 |
areth | +0.237 |
HTTP | +0.223 |
Neg logit contributions | |
isine | -0.259 |
opian | -0.236 |
chen | -0.231 |
ulic | -0.222 |
chefs | -0.217 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
ONES | +0.143 |
Naz | +0.142 |
OSP | +0.136 |
areth | +0.134 |
HTTP | +0.127 |
Neg logit contributions | |
isine | -0.155 |
opian | -0.140 |
chen | -0.138 |
ulic | -0.132 |
chefs | -0.128 |
Token | The |
Token ID | 383 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
isine | +0.183 |
opian | +0.168 |
chen | +0.165 |
ulic | +0.159 |
chefs | +0.156 |
Neg logit contributions | |
ONES | -0.142 |
Naz | -0.140 |
OSP | -0.134 |
areth | -0.133 |
HTTP | -0.124 |
Token | three |
Token ID | 1115 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
isine | +0.114 |
opian | +0.104 |
chen | +0.102 |
ulic | +0.098 |
chefs | +0.096 |
Neg logit contributions | |
ONES | -0.107 |
Naz | -0.105 |
OSP | -0.101 |
areth | -0.100 |
HTTP | -0.094 |
Token | For |
Token ID | 1890 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
isine | +0.784 |
opian | +0.730 |
chen | +0.725 |
ulic | +0.698 |
chefs | +0.676 |
Neg logit contributions | |
ONES | -0.469 |
Naz | -0.448 |
areth | -0.437 |
OSP | -0.434 |
wip | -0.407 |
Token | some |
Token ID | 617 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
isine | +1.050 |
opian | +0.959 |
chen | +0.945 |
ulic | +0.902 |
chefs | +0.891 |
Neg logit contributions | |
ONES | -1.021 |
Naz | -1.010 |
OSP | -0.973 |
areth | -0.964 |
HTTP | -0.910 |
Token | actors |
Token ID | 10544 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
isine | +3.655 |
chen | +3.347 |
opian | +3.331 |
chefs | +3.216 |
ulic | +3.129 |
Neg logit contributions | |
Naz | -3.489 |
ONES | -3.458 |
OSP | -3.299 |
areth | -3.256 |
HTTP | -3.126 |
Token | , |
Token ID | 11 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ONES | +0.338 |
Naz | +0.333 |
OSP | +0.318 |
areth | +0.315 |
HTTP | +0.295 |
Neg logit contributions | |
isine | -0.441 |
opian | -0.406 |
chen | -0.399 |
ulic | -0.384 |
chefs | -0.378 |
Token | like |
Token ID | 588 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
isine | +1.488 |
opian | +1.362 |
chen | +1.339 |
ulic | +1.275 |
chefs | +1.274 |
Neg logit contributions | |
ONES | -1.449 |
Naz | -1.433 |
OSP | -1.380 |
areth | -1.366 |
HTTP | -1.296 |
Token | Ford |
Token ID | 8092 |
Feature activation | +8.07e+00 |
Pos logit contributions | |
ONES | +0.186 |
Naz | +0.183 |
OSP | +0.176 |
areth | +0.174 |
HTTP | +0.162 |
Neg logit contributions | |
isine | -0.235 |
opian | -0.216 |
chen | -0.213 |
ulic | -0.205 |
chefs | -0.201 |
Token | and |
Token ID | 290 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
ONES | +5.088 |
Naz | +4.945 |
OSP | +4.738 |
areth | +4.669 |
Sing | +4.347 |
Neg logit contributions | |
isine | -7.767 |
opian | -7.258 |
chen | -6.967 |
ulic | -6.889 |
chefs | -6.607 |
Token | Fisher |
Token ID | 14388 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
isine | +0.655 |
opian | +0.601 |
chen | +0.597 |
ulic | +0.571 |
chefs | +0.566 |
Neg logit contributions | |
ONES | -0.502 |
Naz | -0.495 |
OSP | -0.477 |
areth | -0.471 |
HTTP | -0.444 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ONES | +2.611 |
Naz | +2.564 |
OSP | +2.450 |
areth | +2.420 |
HTTP | +2.251 |
Neg logit contributions | |
isine | -3.677 |
opian | -3.388 |
chen | -3.330 |
ulic | -3.216 |
chefs | -3.151 |
Token | being |
Token ID | 852 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
isine | +0.870 |
opian | +0.796 |
chen | +0.783 |
ulic | +0.745 |
chefs | +0.744 |
Neg logit contributions | |
ONES | -0.821 |
Naz | -0.811 |
OSP | -0.779 |
areth | -0.771 |
HTTP | -0.731 |
Token | in |
Token ID | 287 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ONES | +1.688 |
Naz | +1.656 |
OSP | +1.589 |
areth | +1.578 |
HTTP | +1.466 |
Neg logit contributions | |
isine | -2.123 |
opian | -1.948 |
chen | -1.900 |
ulic | -1.842 |
chefs | -1.778 |
Token | more |
Token ID | 517 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
isine | +1.195 |
opian | +1.088 |
chen | +1.069 |
ulic | +1.021 |
chefs | +1.010 |
Neg logit contributions | |
ONES | -1.195 |
Naz | -1.173 |
OSP | -1.136 |
areth | -1.123 |
ospels | -1.062 |
Token | children |
Token ID | 1751 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
isine | +0.796 |
opian | +0.727 |
chen | +0.716 |
ulic | +0.684 |
chefs | +0.678 |
Neg logit contributions | |
ONES | -0.741 |
Naz | -0.728 |
OSP | -0.706 |
areth | -0.698 |
HTTP | -0.657 |
Token | than |
Token ID | 621 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
isine | +1.377 |
opian | +1.255 |
chen | +1.240 |
ulic | +1.181 |
chefs | +1.161 |
Neg logit contributions | |
ONES | -1.301 |
Naz | -1.277 |
OSP | -1.235 |
areth | -1.222 |
ospels | -1.155 |
Token | died |
Token ID | 3724 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
isine | +3.895 |
opian | +3.558 |
chen | +3.526 |
chefs | +3.403 |
ulic | +3.342 |
Neg logit contributions | |
ONES | -3.714 |
Naz | -3.606 |
OSP | -3.570 |
areth | -3.480 |
HTTP | -3.322 |
Token | in |
Token ID | 287 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
isine | +0.411 |
opian | +0.370 |
chen | +0.363 |
ulic | +0.346 |
chefs | +0.339 |
Neg logit contributions | |
ONES | -0.470 |
Naz | -0.462 |
OSP | -0.448 |
areth | -0.444 |
ospels | -0.420 |
Token | Hiroshima |
Token ID | 42922 |
Feature activation | +8.06e+00 |
Pos logit contributions | |
isine | +0.183 |
opian | +0.167 |
chen | +0.164 |
ulic | +0.158 |
chefs | +0.155 |
Neg logit contributions | |
ONES | -0.163 |
Naz | -0.160 |
OSP | -0.155 |
areth | -0.153 |
HTTP | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ONES | +5.116 |
Naz | +5.087 |
OSP | +4.734 |
areth | +4.686 |
Sing | +4.342 |
Neg logit contributions | |
isine | -7.746 |
opian | -7.166 |
chen | -6.944 |
ulic | -6.693 |
chefs | -6.609 |
Token | And |
Token ID | 843 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
isine | +0.170 |
opian | +0.155 |
chen | +0.152 |
ulic | +0.146 |
chefs | +0.143 |
Neg logit contributions | |
ONES | -0.152 |
Naz | -0.149 |
OSP | -0.144 |
areth | -0.142 |
HTTP | -0.133 |
Token | , |
Token ID | 11 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ONES | +1.215 |
Naz | +1.197 |
OSP | +1.147 |
areth | +1.141 |
HTTP | +1.066 |
Neg logit contributions | |
isine | -1.319 |
opian | -1.202 |
chen | -1.175 |
ulic | -1.131 |
chefs | -1.095 |
Token | you |
Token ID | 345 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
isine | +0.181 |
opian | +0.166 |
chen | +0.163 |
ulic | +0.156 |
chefs | +0.153 |
Neg logit contributions | |
ONES | -0.158 |
Naz | -0.156 |
OSP | -0.150 |
areth | -0.148 |
HTTP | -0.139 |
Token | know |
Token ID | 760 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ONES | +1.345 |
Naz | +1.323 |
OSP | +1.262 |
areth | +1.257 |
HTTP | +1.168 |
Neg logit contributions | |
isine | -1.722 |
opian | -1.575 |
chen | -1.540 |
ulic | -1.493 |
chefs | -1.447 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
isine | +0.877 |
opian | +0.813 |
chen | +0.797 |
ulic | +0.763 |
chefs | +0.754 |
Neg logit contributions | |
ONES | -0.725 |
Naz | -0.709 |
OSP | -0.679 |
areth | -0.670 |
ospels | -0.634 |
Token | equivalent |
Token ID | 7548 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
isine | +1.262 |
opian | +1.149 |
chen | +1.126 |
ulic | +1.073 |
chefs | +1.057 |
Neg logit contributions | |
ONES | -1.314 |
Naz | -1.297 |
OSP | -1.250 |
areth | -1.239 |
ospels | -1.170 |
Token | of |
Token ID | 286 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
ONES | +1.039 |
Naz | +1.022 |
OSP | +0.982 |
areth | +0.973 |
HTTP | +0.913 |
Neg logit contributions | |
isine | -1.151 |
opian | -1.052 |
chen | -1.031 |
ulic | -0.990 |
chefs | -0.969 |
Token | an |
Token ID | 281 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
isine | +0.624 |
opian | +0.568 |
chen | +0.557 |
ulic | +0.532 |
chefs | +0.526 |
Neg logit contributions | |
ONES | -0.617 |
Naz | -0.607 |
OSP | -0.586 |
areth | -0.581 |
ospels | -0.546 |
Token | Olympic |
Token ID | 11514 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
isine | +0.022 |
opian | +0.020 |
chen | +0.019 |
ulic | +0.018 |
chefs | +0.018 |
Neg logit contributions | |
ONES | -0.022 |
Naz | -0.022 |
OSP | -0.021 |
areth | -0.021 |
ospels | -0.019 |
Token | gymn |
Token ID | 38581 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
isine | +3.252 |
opian | +2.949 |
chen | +2.923 |
ulic | +2.774 |
chefs | +2.765 |
Neg logit contributions | |
ONES | -3.078 |
Naz | -3.026 |
OSP | -2.931 |
areth | -2.897 |
ospels | -2.756 |
Token | astics |
Token ID | 24232 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
isine | +7.171 |
chen | +6.531 |
opian | +6.466 |
ulic | +5.924 |
rast | +5.715 |
Neg logit contributions | |
ONES | -9.559 |
Naz | -9.387 |
OSP | -9.163 |
areth | -8.844 |
HTTP | -8.759 |
Token | routine |
Token ID | 8027 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
isine | +4.458 |
opian | +4.072 |
chen | +4.068 |
chefs | +3.825 |
ulic | +3.824 |
Neg logit contributions | |
ONES | -4.332 |
Naz | -4.271 |
OSP | -4.128 |
areth | -4.079 |
ospels | -3.919 |
Token | for |
Token ID | 329 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
isine | +1.737 |
opian | +1.590 |
chen | +1.568 |
ulic | +1.495 |
chefs | +1.475 |
Neg logit contributions | |
ONES | -1.483 |
Naz | -1.462 |
OSP | -1.400 |
areth | -1.391 |
ospels | -1.305 |
Token | the |
Token ID | 262 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
isine | +0.116 |
opian | +0.105 |
chen | +0.103 |
ulic | +0.099 |
chefs | +0.097 |
Neg logit contributions | |
ONES | -0.113 |
Naz | -0.111 |
OSP | -0.107 |
areth | -0.106 |
HTTP | -0.100 |
Token | speaker |
Token ID | 10834 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
isine | +1.166 |
opian | +1.061 |
chen | +1.038 |
ulic | +0.993 |
chefs | +0.974 |
Neg logit contributions | |
ONES | -1.193 |
Naz | -1.176 |
OSP | -1.132 |
areth | -1.124 |
ospels | -1.058 |
Token | x |
Token ID | 87 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
ONES | +1.249 |
Naz | +1.228 |
OSP | +1.178 |
areth | +1.157 |
HTTP | +1.085 |
Neg logit contributions | |
isine | -1.603 |
opian | -1.472 |
chen | -1.455 |
ulic | -1.395 |
chefs | -1.367 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ONES | +0.593 |
Naz | +0.583 |
OSP | +0.559 |
areth | +0.553 |
HTTP | +0.516 |
Neg logit contributions | |
isine | -0.742 |
opian | -0.680 |
chen | -0.668 |
ulic | -0.644 |
chefs | -0.631 |
Token | Just |
Token ID | 2329 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
isine | +0.167 |
opian | +0.154 |
chen | +0.151 |
ulic | +0.145 |
chefs | +0.142 |
Neg logit contributions | |
ONES | -0.132 |
Naz | -0.130 |
OSP | -0.124 |
areth | -0.123 |
HTTP | -0.115 |
Token | as |
Token ID | 355 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ONES | +0.628 |
Naz | +0.617 |
OSP | +0.594 |
areth | +0.588 |
HTTP | +0.552 |
Neg logit contributions | |
isine | -0.711 |
opian | -0.649 |
chen | -0.636 |
ulic | -0.612 |
chefs | -0.597 |
Token | a |
Token ID | 257 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
isine | +1.064 |
opian | +0.966 |
chen | +0.952 |
ulic | +0.908 |
chefs | +0.902 |
Neg logit contributions | |
ONES | -1.000 |
Naz | -0.987 |
OSP | -0.952 |
areth | -0.945 |
ospels | -0.886 |
Token | gymn |
Token ID | 38581 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
isine | +0.806 |
opian | +0.734 |
chen | +0.723 |
ulic | +0.692 |
chefs | +0.680 |
Neg logit contributions | |
ONES | -0.734 |
Naz | -0.723 |
OSP | -0.694 |
areth | -0.690 |
ospels | -0.647 |
Token | ast |
Token ID | 459 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
isine | +7.226 |
chen | +6.528 |
opian | +6.510 |
ulic | +6.061 |
chefs | +5.779 |
Neg logit contributions | |
ONES | -9.104 |
Naz | -9.018 |
OSP | -8.668 |
areth | -8.449 |
HTTP | -8.236 |
Token | � |
Token ID | 447 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
isine | +2.698 |
opian | +2.504 |
chen | +2.467 |
ulic | +2.370 |
chefs | +2.352 |
Neg logit contributions | |
ONES | -1.880 |
Naz | -1.853 |
OSP | -1.769 |
areth | -1.726 |
HTTP | -1.620 |
Token | � |
Token ID | 247 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
isine | +0.617 |
opian | +0.567 |
chen | +0.557 |
ulic | +0.537 |
chefs | +0.526 |
Neg logit contributions | |
ONES | -0.469 |
Naz | -0.461 |
OSP | -0.441 |
areth | -0.435 |
HTTP | -0.406 |
Token | s |
Token ID | 82 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
isine | +0.424 |
opian | +0.391 |
chen | +0.386 |
ulic | +0.371 |
chefs | +0.362 |
Neg logit contributions | |
ONES | -0.327 |
Naz | -0.319 |
OSP | -0.307 |
areth | -0.300 |
HTTP | -0.282 |
Token | twists |
Token ID | 30953 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
isine | +1.067 |
opian | +0.977 |
chen | +0.959 |
ulic | +0.918 |
chefs | +0.906 |
Neg logit contributions | |
ONES | -0.932 |
Naz | -0.918 |
OSP | -0.880 |
areth | -0.873 |
HTTP | -0.818 |
Token | ren |
Token ID | 918 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
isine | +0.553 |
opian | +0.503 |
chen | +0.496 |
ulic | +0.473 |
chefs | +0.463 |
Neg logit contributions | |
ONES | -0.537 |
Naz | -0.526 |
OSP | -0.507 |
areth | -0.502 |
HTTP | -0.472 |
Token | owned |
Token ID | 11990 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
ONES | +0.840 |
Naz | +0.822 |
OSP | +0.784 |
areth | +0.775 |
ospels | +0.717 |
Neg logit contributions | |
isine | -1.290 |
opian | -1.195 |
chen | -1.171 |
ulic | -1.137 |
chefs | -1.112 |
Token | perf |
Token ID | 23035 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ONES | +1.650 |
Naz | +1.620 |
OSP | +1.558 |
areth | +1.545 |
wip | +1.461 |
Neg logit contributions | |
isine | -1.664 |
opian | -1.515 |
chen | -1.474 |
ulic | -1.426 |
chefs | -1.342 |
Token | umer |
Token ID | 6975 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
isine | +1.620 |
opian | +1.414 |
chen | +1.372 |
ulic | +1.291 |
chefs | +1.244 |
Neg logit contributions | |
ONES | -2.863 |
Naz | -2.828 |
OSP | -2.747 |
areth | -2.728 |
HTTP | -2.605 |
Token | Fr |
Token ID | 1305 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
isine | +0.079 |
opian | +0.072 |
chen | +0.070 |
ulic | +0.068 |
chefs | +0.066 |
Neg logit contributions | |
ONES | -0.070 |
Naz | -0.069 |
OSP | -0.066 |
areth | -0.065 |
HTTP | -0.061 |
Token | é |
Token ID | 2634 |
Feature activation | -9.29e+00 |
Pos logit contributions | |
isine | +3.012 |
opian | +2.700 |
chen | +2.648 |
ulic | +2.550 |
chefs | +2.444 |
Neg logit contributions | |
ONES | -3.595 |
Naz | -3.560 |
OSP | -3.439 |
areth | -3.361 |
HTTP | -3.245 |
Token | d |
Token ID | 67 |
Feature activation | -5.53e+00 |
Pos logit contributions | |
isine | +7.096 |
chen | +6.798 |
opian | +6.407 |
ulic | +6.356 |
chefs | +6.044 |
Neg logit contributions | |
ONES | -7.619 |
OSP | -7.401 |
Naz | -7.322 |
areth | -6.923 |
ospels | -6.649 |
Token | é |
Token ID | 2634 |
Feature activation | -7.17e+00 |
Pos logit contributions | |
isine | +3.002 |
chen | +2.614 |
opian | +2.602 |
ulic | +2.418 |
chefs | +2.231 |
Neg logit contributions | |
ONES | -5.984 |
Naz | -5.872 |
OSP | -5.783 |
areth | -5.617 |
wip | -5.467 |
Token | ric |
Token ID | 1173 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
isine | +3.549 |
chen | +3.131 |
opian | +3.025 |
ulic | +2.760 |
chefs | +2.697 |
Neg logit contributions | |
ONES | -7.914 |
Naz | -7.844 |
OSP | -7.740 |
areth | -7.567 |
HTTP | -7.356 |
Token | Mal |
Token ID | 4434 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
isine | +2.603 |
chen | +2.368 |
opian | +2.341 |
ulic | +2.237 |
chefs | +2.206 |
Neg logit contributions | |
ONES | -2.497 |
Naz | -2.441 |
OSP | -2.385 |
areth | -2.338 |
HTTP | -2.232 |
Token | le |
Token ID | 293 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
isine | +0.534 |
opian | +0.487 |
chen | +0.475 |
ulic | +0.458 |
chefs | +0.448 |
Neg logit contributions | |
ONES | -0.492 |
Naz | -0.484 |
OSP | -0.464 |
areth | -0.462 |
HTTP | -0.433 |
Token | 't |
Token ID | 470 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ONES | +0.307 |
Naz | +0.304 |
OSP | +0.280 |
areth | +0.273 |
HTTP | +0.248 |
Neg logit contributions | |
isine | -0.779 |
opian | -0.724 |
chen | -0.702 |
ulic | -0.692 |
chefs | -0.680 |
Token | somehow |
Token ID | 7599 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
isine | +1.048 |
opian | +0.962 |
chen | +0.942 |
ulic | +0.907 |
chefs | +0.889 |
Neg logit contributions | |
ONES | -0.938 |
Naz | -0.919 |
OSP | -0.892 |
areth | -0.875 |
HTTP | -0.827 |
Token | destabil |
Token ID | 27397 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
isine | +4.000 |
opian | +3.727 |
chen | +3.597 |
ulic | +3.492 |
chefs | +3.451 |
Neg logit contributions | |
ONES | -3.841 |
Naz | -3.696 |
OSP | -3.665 |
areth | -3.515 |
HTTP | -3.375 |
Token | ize |
Token ID | 1096 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
isine | +2.244 |
opian | +2.028 |
chen | +1.973 |
ulic | +1.875 |
chefs | +1.808 |
Neg logit contributions | |
ONES | -3.102 |
Naz | -3.072 |
OSP | -2.962 |
areth | -2.931 |
ospels | -2.798 |
Token | the |
Token ID | 262 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
isine | +1.313 |
opian | +1.200 |
chen | +1.182 |
ulic | +1.138 |
chefs | +1.114 |
Neg logit contributions | |
ONES | -1.260 |
Naz | -1.239 |
OSP | -1.195 |
areth | -1.179 |
ospels | -1.115 |
Token | grid |
Token ID | 10706 |
Feature activation | -8.81e+00 |
Pos logit contributions | |
isine | +0.797 |
opian | +0.731 |
chen | +0.717 |
ulic | +0.689 |
chefs | +0.675 |
Neg logit contributions | |
ONES | -0.727 |
Naz | -0.716 |
OSP | -0.689 |
areth | -0.681 |
ospels | -0.641 |
Token | could |
Token ID | 714 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
isine | +7.130 |
opian | +6.865 |
chen | +6.761 |
chefs | +6.273 |
ulic | +6.272 |
Neg logit contributions | |
ONES | -6.510 |
Naz | -6.421 |
OSP | -6.297 |
areth | -5.983 |
ospels | -5.691 |
Token | help |
Token ID | 1037 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ONES | +0.278 |
Naz | +0.273 |
OSP | +0.262 |
areth | +0.259 |
HTTP | +0.242 |
Neg logit contributions | |
isine | -0.348 |
opian | -0.320 |
chen | -0.314 |
ulic | -0.303 |
chefs | -0.296 |
Token | that |
Token ID | 326 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
isine | +1.053 |
opian | +0.966 |
chen | +0.947 |
ulic | +0.914 |
chefs | +0.897 |
Neg logit contributions | |
ONES | -0.945 |
Naz | -0.932 |
OSP | -0.895 |
areth | -0.884 |
ospels | -0.832 |
Token | jump |
Token ID | 4391 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
isine | +2.190 |
opian | +2.018 |
chen | +1.986 |
ulic | +1.911 |
chefs | +1.889 |
Neg logit contributions | |
ONES | -1.898 |
Naz | -1.873 |
OSP | -1.801 |
areth | -1.788 |
ospels | -1.679 |
Token | happen |
Token ID | 1645 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
isine | +3.592 |
opian | +3.335 |
chen | +3.241 |
ulic | +3.133 |
chefs | +3.033 |
Neg logit contributions | |
ONES | -3.348 |
Naz | -3.312 |
OSP | -3.185 |
areth | -3.144 |
ospels | -2.964 |
Token | of |
Token ID | 286 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
isine | +3.594 |
opian | +3.239 |
chen | +3.217 |
chefs | +3.028 |
ulic | +3.019 |
Neg logit contributions | |
ONES | -3.888 |
Naz | -3.784 |
OSP | -3.655 |
areth | -3.643 |
ospels | -3.487 |
Token | a |
Token ID | 257 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
isine | +0.322 |
opian | +0.292 |
chen | +0.286 |
ulic | +0.273 |
chefs | +0.267 |
Neg logit contributions | |
ONES | -0.347 |
Naz | -0.342 |
OSP | -0.330 |
areth | -0.327 |
HTTP | -0.309 |
Token | person |
Token ID | 1048 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ONES | +0.289 |
Naz | +0.286 |
OSP | +0.276 |
areth | +0.272 |
HTTP | +0.259 |
Neg logit contributions | |
isine | -0.247 |
opian | -0.223 |
chen | -0.217 |
ulic | -0.207 |
chefs | -0.202 |
Token | who |
Token ID | 508 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
isine | +1.827 |
opian | +1.666 |
chen | +1.635 |
ulic | +1.571 |
chefs | +1.537 |
Neg logit contributions | |
ONES | -1.664 |
Naz | -1.637 |
OSP | -1.573 |
areth | -1.557 |
ospels | -1.464 |
Token | is |
Token ID | 318 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ONES | +0.753 |
Naz | +0.739 |
OSP | +0.704 |
areth | +0.697 |
HTTP | +0.642 |
Neg logit contributions | |
isine | -1.223 |
opian | -1.132 |
chen | -1.111 |
ulic | -1.079 |
chefs | -1.054 |
Token | nude |
Token ID | 26349 |
Feature activation | -8.71e+00 |
Pos logit contributions | |
isine | +1.004 |
opian | +0.904 |
chen | +0.884 |
ulic | +0.844 |
chefs | +0.821 |
Neg logit contributions | |
ONES | -1.185 |
Naz | -1.168 |
OSP | -1.128 |
areth | -1.118 |
HTTP | -1.059 |
Token | or |
Token ID | 393 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
isine | +7.027 |
opian | +6.279 |
chen | +6.248 |
ulic | +5.914 |
chefs | +5.847 |
Neg logit contributions | |
ONES | -6.986 |
Naz | -6.772 |
areth | -6.509 |
OSP | -6.448 |
ospels | -6.269 |
Token | engaged |
Token ID | 7953 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
isine | +2.510 |
opian | +2.289 |
chen | +2.247 |
ulic | +2.156 |
chefs | +2.112 |
Neg logit contributions | |
ONES | -2.389 |
Naz | -2.350 |
OSP | -2.253 |
areth | -2.235 |
ospels | -2.108 |
Token | in |
Token ID | 287 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
isine | +1.765 |
opian | +1.598 |
chen | +1.553 |
ulic | +1.477 |
chefs | +1.446 |
Neg logit contributions | |
ONES | -2.340 |
Naz | -2.308 |
OSP | -2.225 |
areth | -2.207 |
ospels | -2.107 |
Token | a |
Token ID | 257 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ONES | +0.162 |
Naz | +0.160 |
OSP | +0.154 |
areth | +0.152 |
HTTP | +0.143 |
Neg logit contributions | |
isine | -0.171 |
opian | -0.156 |
chen | -0.153 |
ulic | -0.147 |
chefs | -0.143 |
Token | sexual |
Token ID | 3206 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
ONES | +0.188 |
Naz | +0.186 |
OSP | +0.180 |
areth | +0.177 |
HTTP | +0.167 |
Neg logit contributions | |
isine | -0.199 |
opian | -0.182 |
chen | -0.178 |
ulic | -0.171 |
chefs | -0.167 |
Token | effects |
Token ID | 3048 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
isine | +2.048 |
opian | +1.889 |
chen | +1.887 |
ulic | +1.796 |
chefs | +1.787 |
Neg logit contributions | |
ONES | -1.973 |
Naz | -1.956 |
OSP | -1.873 |
areth | -1.859 |
ospels | -1.750 |
Token | here |
Token ID | 994 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
ONES | +1.175 |
Naz | +1.155 |
OSP | +1.109 |
areth | +1.096 |
HTTP | +1.026 |
Neg logit contributions | |
isine | -1.412 |
opian | -1.291 |
chen | -1.263 |
ulic | -1.220 |
chefs | -1.193 |
Token | . |
Token ID | 13 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
ONES | +0.516 |
Naz | +0.507 |
OSP | +0.486 |
areth | +0.480 |
HTTP | +0.448 |
Neg logit contributions | |
isine | -0.676 |
opian | -0.621 |
chen | -0.610 |
ulic | -0.589 |
chefs | -0.576 |
Token | Access |
Token ID | 8798 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
isine | +0.402 |
opian | +0.369 |
chen | +0.362 |
ulic | +0.349 |
chefs | +0.341 |
Neg logit contributions | |
ONES | -0.333 |
Naz | -0.328 |
OSP | -0.315 |
areth | -0.311 |
HTTP | -0.291 |
Token | to |
Token ID | 284 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
isine | +2.590 |
opian | +2.410 |
chen | +2.384 |
ulic | +2.295 |
chefs | +2.244 |
Neg logit contributions | |
ONES | -2.366 |
Naz | -2.323 |
OSP | -2.234 |
areth | -2.189 |
ospels | -2.069 |
Token | freshwater |
Token ID | 40941 |
Feature activation | -8.71e+00 |
Pos logit contributions | |
isine | +1.482 |
opian | +1.344 |
chen | +1.321 |
ulic | +1.268 |
chefs | +1.244 |
Neg logit contributions | |
ONES | -1.551 |
Naz | -1.531 |
OSP | -1.476 |
areth | -1.467 |
ospels | -1.385 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
isine | +7.367 |
opian | +6.835 |
chen | +6.824 |
chefs | +6.751 |
ulic | +6.669 |
Neg logit contributions | |
ONES | -6.220 |
Naz | -6.074 |
OSP | -5.980 |
areth | -5.729 |
ospels | -5.552 |
Token | already |
Token ID | 1541 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
isine | +0.953 |
opian | +0.867 |
chen | +0.852 |
ulic | +0.820 |
chefs | +0.806 |
Neg logit contributions | |
ONES | -0.909 |
Naz | -0.897 |
OSP | -0.866 |
areth | -0.858 |
ospels | -0.808 |
Token | in |
Token ID | 287 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
isine | +1.831 |
opian | +1.673 |
chen | +1.647 |
ulic | +1.579 |
chefs | +1.554 |
Neg logit contributions | |
ONES | -1.667 |
Naz | -1.644 |
OSP | -1.579 |
areth | -1.558 |
ospels | -1.472 |
Token | limited |
Token ID | 3614 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
isine | +0.914 |
opian | +0.844 |
chen | +0.823 |
ulic | +0.794 |
chefs | +0.778 |
Neg logit contributions | |
ONES | -0.802 |
Naz | -0.791 |
OSP | -0.756 |
areth | -0.751 |
ospels | -0.705 |
Token | supply |
Token ID | 5127 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ONES | +1.016 |
Naz | +0.999 |
OSP | +0.958 |
areth | +0.945 |
HTTP | +0.885 |
Neg logit contributions | |
isine | -1.309 |
opian | -1.199 |
chen | -1.178 |
ulic | -1.135 |
chefs | -1.107 |
Token | pdf |
Token ID | 12315 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
ONES | +0.536 |
Naz | +0.526 |
OSP | +0.503 |
areth | +0.497 |
HTTP | +0.463 |
Neg logit contributions | |
isine | -0.738 |
opian | -0.680 |
chen | -0.668 |
ulic | -0.645 |
chefs | -0.631 |
Token |
|
Token ID | 198 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
ONES | +0.521 |
Naz | +0.512 |
OSP | +0.491 |
areth | +0.485 |
HTTP | +0.453 |
Neg logit contributions | |
isine | -0.661 |
opian | -0.607 |
chen | -0.596 |
ulic | -0.575 |
chefs | -0.562 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ONES | +0.406 |
Naz | +0.404 |
OSP | +0.378 |
areth | +0.371 |
Sing | +0.348 |
Neg logit contributions | |
isine | -0.680 |
opian | -0.626 |
chen | -0.607 |
ulic | -0.596 |
chefs | -0.589 |
Token | © |
Token ID | 16224 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
ONES | +0.094 |
Naz | +0.092 |
OSP | +0.088 |
areth | +0.087 |
ospels | +0.081 |
Neg logit contributions | |
isine | -0.148 |
opian | -0.137 |
chen | -0.135 |
ulic | -0.131 |
chefs | -0.128 |
Token | Copyright |
Token ID | 15069 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
isine | +3.808 |
chen | +3.468 |
opian | +3.451 |
ulic | +3.282 |
chefs | +3.240 |
Neg logit contributions | |
ONES | -3.714 |
Naz | -3.632 |
OSP | -3.550 |
areth | -3.497 |
ospels | -3.318 |
Token | 2018 |
Token ID | 2864 |
Feature activation | -8.63e+00 |
Pos logit contributions | |
isine | +2.578 |
opian | +2.336 |
chen | +2.329 |
ulic | +2.206 |
chefs | +2.165 |
Neg logit contributions | |
ONES | -2.725 |
Naz | -2.676 |
OSP | -2.598 |
areth | -2.566 |
ospels | -2.436 |
Token | Red |
Token ID | 2297 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
isine | +6.470 |
chen | +6.038 |
opian | +5.846 |
chefs | +5.634 |
ulic | +5.528 |
Neg logit contributions | |
ONES | -6.919 |
Naz | -6.875 |
OSP | -6.746 |
areth | -6.503 |
ospels | -6.304 |
Token | � |
Token ID | 447 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
isine | +2.803 |
opian | +2.565 |
chen | +2.550 |
ulic | +2.433 |
chefs | +2.375 |
Neg logit contributions | |
ONES | -2.459 |
Naz | -2.431 |
OSP | -2.346 |
areth | -2.324 |
ospels | -2.185 |
Token | � |
Token ID | 247 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
isine | +0.791 |
opian | +0.726 |
chen | +0.712 |
ulic | +0.685 |
chefs | +0.667 |
Neg logit contributions | |
ONES | -0.687 |
Naz | -0.672 |
OSP | -0.644 |
areth | -0.635 |
ospels | -0.599 |
Token | s |
Token ID | 82 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
ONES | +0.025 |
Naz | +0.024 |
OSP | +0.023 |
areth | +0.023 |
HTTP | +0.021 |
Neg logit contributions | |
isine | -0.039 |
opian | -0.036 |
chen | -0.036 |
ulic | -0.034 |
chefs | -0.034 |
Token | Land |
Token ID | 6379 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
isine | +0.812 |
opian | +0.741 |
chen | +0.729 |
ulic | +0.699 |
chefs | +0.682 |
Neg logit contributions | |
ONES | -0.737 |
Naz | -0.727 |
OSP | -0.700 |
areth | -0.691 |
HTTP | -0.651 |
Token | � |
Token ID | 251 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
ONES | +0.173 |
Naz | +0.170 |
OSP | +0.164 |
areth | +0.162 |
ospels | +0.154 |
Neg logit contributions | |
isine | -0.165 |
opian | -0.150 |
chen | -0.147 |
ulic | -0.140 |
chefs | -0.137 |
Token |
|
Token ID | 198 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
isine | +0.509 |
opian | +0.467 |
chen | +0.463 |
ulic | +0.444 |
chefs | +0.434 |
Neg logit contributions | |
ONES | -0.395 |
Naz | -0.388 |
OSP | -0.373 |
areth | -0.372 |
ospels | -0.345 |
Token |
|
Token ID | 198 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
ONES | +0.145 |
Naz | +0.144 |
OSP | +0.135 |
areth | +0.133 |
Sing | +0.124 |
Neg logit contributions | |
isine | -0.240 |
opian | -0.221 |
chen | -0.214 |
ulic | -0.211 |
chefs | -0.208 |
Token | Copyright |
Token ID | 15269 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ONES | +0.012 |
Naz | +0.012 |
OSP | +0.011 |
areth | +0.011 |
ospels | +0.010 |
Neg logit contributions | |
isine | -0.019 |
opian | -0.017 |
chen | -0.017 |
ulic | -0.016 |
chefs | -0.016 |
Token | © |
Token ID | 10673 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
isine | +1.413 |
opian | +1.275 |
chen | +1.253 |
ulic | +1.184 |
chefs | +1.158 |
Neg logit contributions | |
ONES | -1.749 |
Naz | -1.718 |
OSP | -1.671 |
areth | -1.652 |
ospels | -1.565 |
Token | 2019 |
Token ID | 13130 |
Feature activation | -8.51e+00 |
Pos logit contributions | |
isine | +3.076 |
opian | +2.789 |
chen | +2.773 |
ulic | +2.568 |
chefs | +2.497 |
Neg logit contributions | |
ONES | -4.455 |
Naz | -4.374 |
OSP | -4.269 |
areth | -4.239 |
ospels | -4.017 |
Token | The |
Token ID | 383 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
isine | +6.206 |
chen | +5.739 |
opian | +5.635 |
chefs | +5.202 |
ulic | +5.183 |
Neg logit contributions | |
ONES | -7.160 |
Naz | -7.082 |
areth | -6.841 |
OSP | -6.779 |
ospels | -6.420 |
Token | Washington |
Token ID | 2669 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
isine | +1.664 |
opian | +1.513 |
chen | +1.497 |
ulic | +1.415 |
chefs | +1.382 |
Neg logit contributions | |
ONES | -1.949 |
Naz | -1.924 |
OSP | -1.860 |
areth | -1.852 |
HTTP | -1.743 |
Token | Times |
Token ID | 3782 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
ONES | +0.242 |
OSP | +0.233 |
Naz | +0.233 |
areth | +0.228 |
Sing | +0.208 |
Neg logit contributions | |
isine | -0.455 |
opian | -0.414 |
chen | -0.407 |
ulic | -0.401 |
chefs | -0.390 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ONES | +1.557 |
Naz | +1.472 |
OSP | +1.472 |
areth | +1.429 |
ospels | +1.308 |
Neg logit contributions | |
isine | -2.826 |
opian | -2.601 |
chen | -2.561 |
ulic | -2.500 |
chefs | -2.458 |
Token | LLC |
Token ID | 11419 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
isine | +1.382 |
opian | +1.258 |
chen | +1.225 |
ulic | +1.178 |
chefs | +1.146 |
Neg logit contributions | |
ONES | -1.435 |
Naz | -1.412 |
OSP | -1.362 |
areth | -1.351 |
HTTP | -1.273 |
Token | as |
Token ID | 292 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
isine | +1.611 |
opian | +1.456 |
chen | +1.452 |
ulic | +1.388 |
chefs | +1.360 |
Neg logit contributions | |
ONES | -1.438 |
Naz | -1.414 |
OSP | -1.359 |
areth | -1.356 |
ospels | -1.272 |
Token | Le |
Token ID | 1004 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
ONES | +0.176 |
Naz | +0.174 |
OSP | +0.167 |
areth | +0.165 |
ospels | +0.155 |
Neg logit contributions | |
isine | -0.189 |
opian | -0.172 |
chen | -0.169 |
ulic | -0.162 |
chefs | -0.159 |
Token | Fort |
Token ID | 6401 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
isine | +3.127 |
opian | +2.836 |
chen | +2.820 |
ulic | +2.699 |
chefs | +2.669 |
Neg logit contributions | |
ONES | -2.656 |
Naz | -2.615 |
OSP | -2.521 |
areth | -2.484 |
ospels | -2.333 |
Token | de |
Token ID | 390 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
ONES | +2.354 |
Naz | +2.325 |
OSP | +2.250 |
areth | +2.230 |
HTTP | +2.121 |
Neg logit contributions | |
isine | -1.719 |
opian | -1.533 |
chen | -1.494 |
ulic | -1.420 |
chefs | -1.378 |
Token | Br |
Token ID | 1709 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
isine | +2.743 |
chen | +2.477 |
opian | +2.438 |
ulic | +2.356 |
chefs | +2.312 |
Neg logit contributions | |
ONES | -2.663 |
Naz | -2.536 |
OSP | -2.493 |
areth | -2.477 |
ospels | -2.352 |
Token | é |
Token ID | 2634 |
Feature activation | -8.39e+00 |
Pos logit contributions | |
isine | +1.076 |
opian | +0.966 |
chen | +0.948 |
ulic | +0.906 |
chefs | +0.879 |
Neg logit contributions | |
ONES | -1.259 |
Naz | -1.242 |
OSP | -1.201 |
areth | -1.186 |
HTTP | -1.125 |
Token | gan |
Token ID | 1030 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
isine | +7.294 |
chen | +6.739 |
opian | +6.584 |
ulic | +6.352 |
chefs | +6.089 |
Neg logit contributions | |
ONES | -6.240 |
OSP | -5.929 |
Naz | -5.925 |
areth | -5.489 |
HTTP | -5.378 |
Token | ç |
Token ID | 16175 |
Feature activation | -6.44e+00 |
Pos logit contributions | |
isine | +0.855 |
chen | +0.767 |
opian | +0.762 |
ulic | +0.717 |
chefs | +0.698 |
Neg logit contributions | |
ONES | -0.944 |
Naz | -0.924 |
OSP | -0.892 |
areth | -0.881 |
ospels | -0.838 |
Token | on |
Token ID | 261 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
isine | +5.067 |
chen | +4.621 |
opian | +4.534 |
ulic | +4.370 |
chefs | +4.229 |
Neg logit contributions | |
ONES | -5.088 |
Naz | -5.076 |
OSP | -4.901 |
areth | -4.796 |
HTTP | -4.593 |
Token | ser |
Token ID | 1055 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
isine | +2.278 |
opian | +2.054 |
chen | +2.052 |
ulic | +1.953 |
chefs | +1.926 |
Neg logit contributions | |
ONES | -2.090 |
Naz | -2.052 |
OSP | -1.970 |
areth | -1.959 |
ospels | -1.850 |
Token | a |
Token ID | 64 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
isine | +1.146 |
opian | +1.047 |
chen | +1.032 |
ulic | +0.988 |
chefs | +0.972 |
Neg logit contributions | |
ONES | -0.966 |
Naz | -0.949 |
OSP | -0.911 |
areth | -0.900 |
ospels | -0.845 |
Token | has |
Token ID | 468 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
isine | +1.264 |
opian | +1.174 |
chen | +1.155 |
ulic | +1.106 |
chefs | +1.098 |
Neg logit contributions | |
ONES | -0.935 |
Naz | -0.915 |
OSP | -0.875 |
areth | -0.855 |
HTTP | -0.806 |
Token | opened |
Token ID | 4721 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
isine | +1.583 |
opian | +1.454 |
chen | +1.434 |
ulic | +1.370 |
chefs | +1.360 |
Neg logit contributions | |
ONES | -1.420 |
Naz | -1.393 |
OSP | -1.344 |
areth | -1.321 |
ospels | -1.255 |
Token | the |
Token ID | 262 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
isine | +1.001 |
opian | +0.910 |
chen | +0.898 |
ulic | +0.851 |
chefs | +0.849 |
Neg logit contributions | |
ONES | -1.085 |
Naz | -1.073 |
OSP | -1.031 |
areth | -1.027 |
ospels | -0.967 |
Token | door |
Token ID | 3420 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
isine | +0.218 |
opian | +0.200 |
chen | +0.197 |
ulic | +0.189 |
chefs | +0.186 |
Neg logit contributions | |
ONES | -0.190 |
Naz | -0.187 |
OSP | -0.179 |
areth | -0.177 |
ospels | -0.166 |
Token | for |
Token ID | 329 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
ONES | +1.272 |
Naz | +1.248 |
OSP | +1.197 |
areth | +1.192 |
HTTP | +1.118 |
Neg logit contributions | |
isine | -1.267 |
opian | -1.167 |
chen | -1.144 |
ulic | -1.093 |
chefs | -1.069 |
Token | nude |
Token ID | 26349 |
Feature activation | -8.27e+00 |
Pos logit contributions | |
ONES | +0.212 |
Naz | +0.209 |
OSP | +0.201 |
areth | +0.199 |
HTTP | +0.188 |
Neg logit contributions | |
isine | -0.218 |
opian | -0.198 |
chen | -0.194 |
ulic | -0.186 |
chefs | -0.181 |
Token | and |
Token ID | 290 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
isine | +6.622 |
opian | +6.210 |
chen | +6.049 |
chefs | +5.988 |
chef | +5.697 |
Neg logit contributions | |
ONES | -6.436 |
Naz | -6.191 |
areth | -6.092 |
OSP | -5.947 |
ospels | -5.638 |
Token | sexually |
Token ID | 11363 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
isine | +0.256 |
opian | +0.232 |
chen | +0.227 |
ulic | +0.218 |
chefs | +0.212 |
Neg logit contributions | |
ONES | -0.262 |
Naz | -0.259 |
OSP | -0.249 |
areth | -0.247 |
HTTP | -0.233 |
Token | explicit |
Token ID | 7952 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
isine | +3.737 |
opian | +3.329 |
chen | +3.282 |
chefs | +3.106 |
ulic | +3.058 |
Neg logit contributions | |
ONES | -5.191 |
Naz | -4.967 |
areth | -4.883 |
OSP | -4.844 |
ospels | -4.694 |
Token | photos |
Token ID | 5205 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
isine | +4.908 |
opian | +4.515 |
chen | +4.437 |
chefs | +4.303 |
ulic | +4.151 |
Neg logit contributions | |
ONES | -4.519 |
Naz | -4.400 |
OSP | -4.273 |
areth | -4.260 |
ospels | -4.011 |
Token | and |
Token ID | 290 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
isine | +3.723 |
opian | +3.428 |
chen | +3.396 |
ulic | +3.224 |
chefs | +3.189 |
Neg logit contributions | |
ONES | -3.142 |
Naz | -3.078 |
OSP | -2.951 |
areth | -2.928 |
ospels | -2.754 |
Token | is |
Token ID | 318 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
ONES | +0.260 |
Naz | +0.254 |
OSP | +0.244 |
areth | +0.239 |
ospels | +0.224 |
Neg logit contributions | |
isine | -0.368 |
opian | -0.340 |
chen | -0.334 |
ulic | -0.323 |
chefs | -0.316 |
Token | currently |
Token ID | 3058 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
isine | +0.611 |
opian | +0.555 |
chen | +0.544 |
ulic | +0.522 |
chefs | +0.509 |
Neg logit contributions | |
ONES | -0.588 |
Naz | -0.580 |
OSP | -0.558 |
areth | -0.552 |
HTTP | -0.520 |
Token | over |
Token ID | 625 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
isine | +3.849 |
opian | +3.524 |
chen | +3.461 |
ulic | +3.320 |
chefs | +3.252 |
Neg logit contributions | |
ONES | -4.175 |
Naz | -4.097 |
OSP | -3.953 |
areth | -3.945 |
ospels | -3.778 |
Token | a |
Token ID | 257 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
isine | +1.105 |
opian | +1.017 |
chen | +1.001 |
ulic | +0.962 |
chefs | +0.940 |
Neg logit contributions | |
ONES | -0.887 |
Naz | -0.871 |
OSP | -0.837 |
areth | -0.826 |
ospels | -0.775 |
Token | deep |
Token ID | 2769 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
ONES | +0.063 |
Naz | +0.062 |
OSP | +0.060 |
areth | +0.059 |
HTTP | +0.056 |
Neg logit contributions | |
isine | -0.062 |
opian | -0.056 |
chen | -0.055 |
ulic | -0.053 |
chefs | -0.052 |
Token | gou |
Token ID | 50162 |
Feature activation | -8.26e+00 |
Pos logit contributions | |
isine | +2.613 |
opian | +2.396 |
chen | +2.372 |
ulic | +2.268 |
chefs | +2.204 |
Neg logit contributions | |
ONES | -2.318 |
Naz | -2.256 |
OSP | -2.177 |
areth | -2.156 |
ospels | -2.032 |
Token | ge |
Token ID | 469 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
isine | +4.019 |
chen | +3.612 |
opian | +3.535 |
ulic | +3.203 |
chefs | +2.819 |
Neg logit contributions | |
ONES | -9.375 |
Naz | -9.172 |
OSP | -9.048 |
areth | -8.723 |
CTV | -8.546 |
Token | in |
Token ID | 287 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
isine | +3.179 |
opian | +2.915 |
chen | +2.869 |
ulic | +2.721 |
chefs | +2.662 |
Neg logit contributions | |
ONES | -3.381 |
Naz | -3.331 |
OSP | -3.214 |
areth | -3.187 |
ospels | -3.033 |
Token | which |
Token ID | 543 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
isine | +0.178 |
opian | +0.162 |
chen | +0.160 |
ulic | +0.154 |
chefs | +0.149 |
Neg logit contributions | |
ONES | -0.167 |
Naz | -0.164 |
OSP | -0.158 |
areth | -0.156 |
ospels | -0.148 |
Token | the |
Token ID | 262 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
ONES | +1.188 |
Naz | +1.169 |
OSP | +1.124 |
areth | +1.112 |
HTTP | +1.047 |
Neg logit contributions | |
isine | -1.278 |
opian | -1.165 |
chen | -1.141 |
ulic | -1.095 |
chefs | -1.069 |
Token | bedrock |
Token ID | 47856 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
ONES | +0.170 |
Naz | +0.168 |
OSP | +0.162 |
areth | +0.160 |
HTTP | +0.151 |
Neg logit contributions | |
isine | -0.158 |
opian | -0.143 |
chen | -0.140 |
ulic | -0.134 |
chefs | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
isine | +0.306 |
opian | +0.279 |
chen | +0.274 |
ulic | +0.263 |
chefs | +0.257 |
Neg logit contributions | |
ONES | -0.275 |
Naz | -0.270 |
OSP | -0.260 |
areth | -0.259 |
ospels | -0.243 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ONES | +0.186 |
Naz | +0.183 |
OSP | +0.175 |
areth | +0.173 |
HTTP | +0.162 |
Neg logit contributions | |
isine | -0.242 |
opian | -0.222 |
chen | -0.218 |
ulic | -0.210 |
chefs | -0.206 |
Token |
|
Token ID | 198 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
isine | +0.148 |
opian | +0.137 |
chen | +0.133 |
ulic | +0.130 |
chefs | +0.129 |
Neg logit contributions | |
ONES | -0.091 |
Naz | -0.091 |
OSP | -0.085 |
areth | -0.084 |
Sing | -0.078 |
Token | Copyright |
Token ID | 15269 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
isine | +0.367 |
opian | +0.339 |
chen | +0.336 |
ulic | +0.323 |
chefs | +0.314 |
Neg logit contributions | |
ONES | -0.232 |
Naz | -0.226 |
areth | -0.217 |
OSP | -0.216 |
ospels | -0.200 |
Token | © |
Token ID | 10673 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
isine | +1.490 |
opian | +1.345 |
chen | +1.321 |
ulic | +1.246 |
chefs | +1.217 |
Neg logit contributions | |
ONES | -1.892 |
Naz | -1.852 |
OSP | -1.801 |
areth | -1.783 |
ospels | -1.691 |
Token | 2019 |
Token ID | 13130 |
Feature activation | -8.15e+00 |
Pos logit contributions | |
isine | +3.215 |
opian | +2.945 |
chen | +2.936 |
ulic | +2.717 |
chefs | +2.626 |
Neg logit contributions | |
ONES | -4.435 |
Naz | -4.324 |
OSP | -4.196 |
areth | -4.173 |
ospels | -3.967 |
Token | The |
Token ID | 383 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
isine | +6.024 |
chen | +5.587 |
opian | +5.566 |
ulic | +5.035 |
chefs | +5.016 |
Neg logit contributions | |
ONES | -6.894 |
Naz | -6.747 |
areth | -6.501 |
OSP | -6.408 |
ospels | -6.089 |
Token | Washington |
Token ID | 2669 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
isine | +1.716 |
opian | +1.570 |
chen | +1.547 |
ulic | +1.464 |
chefs | +1.423 |
Neg logit contributions | |
ONES | -2.023 |
Naz | -1.991 |
OSP | -1.918 |
areth | -1.913 |
HTTP | -1.802 |
Token | Times |
Token ID | 3782 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
ONES | +0.197 |
OSP | +0.192 |
Naz | +0.191 |
areth | +0.186 |
Sing | +0.170 |
Neg logit contributions | |
isine | -0.381 |
opian | -0.345 |
chen | -0.340 |
ulic | -0.336 |
chefs | -0.328 |
Token | , |
Token ID | 11 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
ONES | +1.628 |
Naz | +1.554 |
OSP | +1.546 |
areth | +1.502 |
ospels | +1.389 |
Neg logit contributions | |
isine | -2.958 |
opian | -2.717 |
chen | -2.680 |
ulic | -2.606 |
chefs | -2.569 |
Token | LLC |
Token ID | 11419 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
isine | +1.498 |
opian | +1.357 |
chen | +1.327 |
ulic | +1.272 |
chefs | +1.239 |
Neg logit contributions | |
ONES | -1.595 |
Naz | -1.572 |
OSP | -1.516 |
areth | -1.502 |
HTTP | -1.418 |
Token | concentrations |
Token ID | 14587 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
ONES | +3.543 |
Naz | +3.440 |
OSP | +3.320 |
areth | +3.282 |
HTTP | +3.075 |
Neg logit contributions | |
isine | -4.498 |
opian | -4.155 |
chen | -4.035 |
ulic | -3.924 |
chefs | -3.749 |
Token | of |
Token ID | 286 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ONES | +0.303 |
Naz | +0.298 |
OSP | +0.288 |
areth | +0.282 |
HTTP | +0.267 |
Neg logit contributions | |
isine | -0.333 |
opian | -0.304 |
chen | -0.300 |
ulic | -0.287 |
chefs | -0.281 |
Token | collagen |
Token ID | 45452 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
ONES | +0.286 |
Naz | +0.281 |
OSP | +0.271 |
areth | +0.269 |
HTTP | +0.254 |
Neg logit contributions | |
isine | -0.270 |
opian | -0.245 |
chen | -0.239 |
ulic | -0.229 |
chefs | -0.223 |
Token | can |
Token ID | 460 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ONES | +1.999 |
Naz | +1.948 |
areth | +1.868 |
OSP | +1.855 |
HTTP | +1.716 |
Neg logit contributions | |
isine | -2.836 |
opian | -2.616 |
chen | -2.576 |
ulic | -2.489 |
chefs | -2.432 |
Token | attract |
Token ID | 4729 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
ONES | +2.086 |
Naz | +2.053 |
areth | +1.977 |
OSP | +1.956 |
ospels | +1.826 |
Neg logit contributions | |
isine | -2.529 |
opian | -2.306 |
chen | -2.265 |
ulic | -2.175 |
chefs | -2.127 |
Token | contamination |
Token ID | 22733 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
ONES | +0.370 |
Naz | +0.364 |
OSP | +0.350 |
areth | +0.346 |
HTTP | +0.325 |
Neg logit contributions | |
isine | -0.409 |
opian | -0.373 |
chen | -0.366 |
ulic | -0.352 |
chefs | -0.343 |
Token | , |
Token ID | 11 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
isine | +6.690 |
opian | +6.240 |
chen | +6.086 |
chefs | +5.882 |
ulic | +5.687 |
Neg logit contributions | |
ONES | -6.011 |
Naz | -5.957 |
OSP | -5.847 |
areth | -5.646 |
ospels | -5.426 |
Token | they |
Token ID | 484 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
isine | +0.457 |
opian | +0.415 |
chen | +0.409 |
ulic | +0.392 |
chefs | +0.387 |
Neg logit contributions | |
ONES | -0.425 |
Naz | -0.419 |
OSP | -0.403 |
areth | -0.399 |
ospels | -0.376 |
Token | compared |
Token ID | 3688 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
isine | +0.296 |
opian | +0.272 |
chen | +0.267 |
ulic | +0.257 |
chefs | +0.253 |
Neg logit contributions | |
ONES | -0.242 |
Naz | -0.238 |
OSP | -0.229 |
areth | -0.225 |
HTTP | -0.211 |
Token | precision |
Token ID | 15440 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ONES | +1.349 |
Naz | +1.326 |
OSP | +1.275 |
areth | +1.262 |
HTTP | +1.187 |
Neg logit contributions | |
isine | -1.471 |
opian | -1.342 |
chen | -1.315 |
ulic | -1.265 |
chefs | -1.234 |
Token | Acceler |
Token ID | 29805 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
isine | +1.577 |
opian | +1.433 |
chen | +1.413 |
ulic | +1.356 |
chefs | +1.344 |
Neg logit contributions | |
ONES | -1.329 |
Naz | -1.317 |
OSP | -1.263 |
areth | -1.247 |
HTTP | -1.168 |
Token | at |
Token ID | 379 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
ONES | +1.747 |
Naz | +1.724 |
OSP | +1.661 |
areth | +1.640 |
HTTP | +1.547 |
Neg logit contributions | |
isine | -1.800 |
opian | -1.632 |
chen | -1.600 |
ulic | -1.542 |
chefs | -1.499 |
Token | the |
Token ID | 262 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
ONES | +0.769 |
Naz | +0.757 |
OSP | +0.727 |
areth | +0.720 |
HTTP | +0.676 |
Neg logit contributions | |
isine | -0.849 |
opian | -0.775 |
chen | -0.760 |
ulic | -0.731 |
chefs | -0.714 |
Token | sites |
Token ID | 5043 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
ONES | +0.199 |
Naz | +0.196 |
OSP | +0.188 |
areth | +0.186 |
HTTP | +0.174 |
Neg logit contributions | |
isine | -0.243 |
opian | -0.222 |
chen | -0.218 |
ulic | -0.210 |
chefs | -0.206 |
Token | that |
Token ID | 326 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
isine | +0.648 |
opian | +0.593 |
chen | +0.582 |
ulic | +0.559 |
chefs | +0.548 |
Neg logit contributions | |
ONES | -0.577 |
Naz | -0.568 |
OSP | -0.545 |
areth | -0.540 |
ospels | -0.507 |
Token | permitted |
Token ID | 10431 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
isine | +0.348 |
opian | +0.319 |
chen | +0.313 |
ulic | +0.301 |
chefs | +0.295 |
Neg logit contributions | |
ONES | -0.300 |
Naz | -0.295 |
OSP | -0.283 |
areth | -0.280 |
ospels | -0.263 |
Token | nude |
Token ID | 26349 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
ONES | +1.306 |
Naz | +1.287 |
OSP | +1.244 |
areth | +1.224 |
HTTP | +1.166 |
Neg logit contributions | |
isine | -1.283 |
opian | -1.163 |
chen | -1.135 |
ulic | -1.092 |
chefs | -1.049 |
Token | photos |
Token ID | 5205 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
isine | +5.963 |
opian | +5.410 |
chen | +5.321 |
chefs | +5.220 |
chef | +4.968 |
Neg logit contributions | |
ONES | -6.973 |
Naz | -6.727 |
areth | -6.628 |
OSP | -6.438 |
ospels | -6.201 |
Token | to |
Token ID | 284 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
isine | +3.267 |
opian | +2.998 |
chen | +2.972 |
ulic | +2.829 |
chefs | +2.783 |
Neg logit contributions | |
ONES | -2.707 |
Naz | -2.662 |
OSP | -2.535 |
areth | -2.523 |
ospels | -2.371 |
Token | be |
Token ID | 307 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
isine | +0.177 |
opian | +0.162 |
chen | +0.159 |
ulic | +0.153 |
chefs | +0.150 |
Neg logit contributions | |
ONES | -0.151 |
Naz | -0.149 |
OSP | -0.143 |
areth | -0.141 |
HTTP | -0.132 |
Token | posted |
Token ID | 4481 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
ONES | +1.190 |
Naz | +1.179 |
OSP | +1.124 |
areth | +1.117 |
HTTP | +1.051 |
Neg logit contributions | |
isine | -1.408 |
opian | -1.286 |
chen | -1.250 |
ulic | -1.214 |
chefs | -1.176 |
Token | of |
Token ID | 286 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
isine | +2.123 |
opian | +1.947 |
chen | +1.911 |
ulic | +1.825 |
chefs | +1.796 |
Neg logit contributions | |
ONES | -1.913 |
Naz | -1.886 |
OSP | -1.810 |
areth | -1.791 |
ospels | -1.693 |
Token | applied |
Token ID | 5625 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ONES | +0.168 |
Naz | +0.166 |
OSP | +0.159 |
areth | +0.157 |
HTTP | +0.147 |
Neg logit contributions | |
isine | -0.214 |
opian | -0.197 |
chen | -0.193 |
ulic | -0.187 |
chefs | -0.183 |
Token | it |
Token ID | 340 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
isine | +1.425 |
opian | +1.295 |
chen | +1.274 |
ulic | +1.232 |
chefs | +1.207 |
Neg logit contributions | |
ONES | -1.364 |
Naz | -1.350 |
OSP | -1.297 |
areth | -1.288 |
ospels | -1.214 |
Token | to |
Token ID | 284 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
isine | +1.126 |
opian | +1.028 |
chen | +1.008 |
ulic | +0.973 |
chefs | +0.951 |
Neg logit contributions | |
ONES | -1.017 |
Naz | -1.005 |
OSP | -0.966 |
areth | -0.956 |
ospels | -0.900 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ONES | +0.359 |
Naz | +0.353 |
OSP | +0.340 |
areth | +0.336 |
HTTP | +0.316 |
Neg logit contributions | |
isine | -0.380 |
opian | -0.345 |
chen | -0.339 |
ulic | -0.324 |
chefs | -0.317 |
Token | Barnett |
Token ID | 38174 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
isine | +0.086 |
opian | +0.078 |
chen | +0.076 |
ulic | +0.073 |
chefs | +0.071 |
Neg logit contributions | |
ONES | -0.082 |
Naz | -0.081 |
OSP | -0.078 |
areth | -0.077 |
HTTP | -0.072 |
Token | shale |
Token ID | 30498 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
isine | +2.863 |
opian | +2.663 |
chen | +2.613 |
ulic | +2.560 |
chefs | +2.451 |
Neg logit contributions | |
ONES | -2.427 |
Naz | -2.405 |
OSP | -2.314 |
areth | -2.263 |
HTTP | -2.144 |
Token | , |
Token ID | 11 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
isine | +6.668 |
opian | +6.316 |
ulic | +6.142 |
chen | +6.138 |
chefs | +5.815 |
Neg logit contributions | |
ONES | -5.942 |
Naz | -5.889 |
OSP | -5.616 |
areth | -5.591 |
ospels | -5.285 |
Token | a |
Token ID | 257 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
isine | +0.546 |
opian | +0.501 |
chen | +0.492 |
ulic | +0.475 |
chefs | +0.464 |
Neg logit contributions | |
ONES | -0.450 |
Naz | -0.443 |
OSP | -0.425 |
areth | -0.421 |
HTTP | -0.394 |
Token | mile |
Token ID | 10591 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
isine | +0.349 |
opian | +0.319 |
chen | +0.313 |
ulic | +0.301 |
chefs | +0.294 |
Neg logit contributions | |
ONES | -0.308 |
Naz | -0.303 |
OSP | -0.291 |
areth | -0.288 |
HTTP | -0.270 |
Token | - |
Token ID | 12 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
isine | +1.157 |
opian | +1.070 |
chen | +1.048 |
ulic | +1.003 |
chefs | +0.985 |
Neg logit contributions | |
ONES | -0.937 |
Naz | -0.918 |
OSP | -0.880 |
areth | -0.867 |
ospels | -0.821 |
Token | and |
Token ID | 392 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
isine | +1.828 |
opian | +1.657 |
chen | +1.630 |
ulic | +1.523 |
chefs | +1.462 |
Neg logit contributions | |
ONES | -2.218 |
Naz | -2.156 |
OSP | -2.104 |
areth | -2.052 |
ospels | -1.989 |
Token | even |
Token ID | 772 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
ONES | +0.161 |
Naz | +0.159 |
OSP | +0.152 |
areth | +0.150 |
HTTP | +0.141 |
Neg logit contributions | |
isine | -0.191 |
opian | -0.175 |
chen | -0.172 |
ulic | -0.165 |
chefs | -0.162 |
Token | our |
Token ID | 674 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ONES | +0.178 |
Naz | +0.176 |
OSP | +0.169 |
areth | +0.167 |
HTTP | +0.158 |
Neg logit contributions | |
isine | -0.183 |
opian | -0.166 |
chen | -0.162 |
ulic | -0.156 |
chefs | -0.152 |
Token | well |
Token ID | 880 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
ONES | +0.173 |
Naz | +0.170 |
OSP | +0.164 |
areth | +0.163 |
HTTP | +0.153 |
Neg logit contributions | |
isine | -0.173 |
opian | -0.157 |
chen | -0.154 |
ulic | -0.148 |
chefs | -0.145 |
Token | water |
Token ID | 1660 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
ONES | +1.960 |
Naz | +1.929 |
OSP | +1.847 |
areth | +1.813 |
HTTP | +1.702 |
Neg logit contributions | |
isine | -2.722 |
opian | -2.509 |
chen | -2.453 |
ulic | -2.383 |
chefs | -2.317 |
Token | is |
Token ID | 318 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
isine | +1.843 |
opian | +1.686 |
chen | +1.677 |
ulic | +1.602 |
chefs | +1.581 |
Neg logit contributions | |
ONES | -1.454 |
Naz | -1.428 |
OSP | -1.369 |
areth | -1.364 |
ospels | -1.269 |
Token | contaminated |
Token ID | 23543 |
Feature activation | -8.10e+00 |
Pos logit contributions | |
isine | +0.220 |
opian | +0.199 |
chen | +0.193 |
ulic | +0.186 |
chefs | +0.180 |
Neg logit contributions | |
ONES | -0.241 |
Naz | -0.237 |
OSP | -0.229 |
areth | -0.226 |
HTTP | -0.215 |
Token | , |
Token ID | 11 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
isine | +6.362 |
opian | +5.755 |
chen | +5.659 |
ulic | +5.388 |
chefs | +5.311 |
Neg logit contributions | |
ONES | -6.518 |
Naz | -6.361 |
OSP | -6.290 |
areth | -6.252 |
ospels | -5.901 |
Token | � |
Token ID | 447 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
isine | +0.290 |
opian | +0.266 |
chen | +0.261 |
ulic | +0.252 |
chefs | +0.247 |
Neg logit contributions | |
ONES | -0.231 |
Naz | -0.227 |
OSP | -0.218 |
areth | -0.216 |
ospels | -0.201 |
Token | � |
Token ID | 251 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
ONES | +0.061 |
Naz | +0.060 |
OSP | +0.058 |
areth | +0.057 |
ospels | +0.054 |
Neg logit contributions | |
isine | -0.057 |
opian | -0.052 |
chen | -0.051 |
ulic | -0.049 |
chefs | -0.047 |
Token | Yun |
Token ID | 20757 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
isine | +0.473 |
opian | +0.431 |
chen | +0.425 |
ulic | +0.406 |
chefs | +0.399 |
Neg logit contributions | |
ONES | -0.435 |
Naz | -0.427 |
OSP | -0.413 |
areth | -0.409 |
ospels | -0.384 |
Token | told |
Token ID | 1297 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ONES | +3.809 |
Naz | +3.785 |
areth | +3.528 |
OSP | +3.525 |
HTTP | +3.302 |
Neg logit contributions | |
isine | -4.946 |
opian | -4.543 |
chen | -4.377 |
ulic | -4.312 |
chefs | -4.171 |
Token | . |
Token ID | 13 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
isine | +0.114 |
opian | +0.104 |
chen | +0.102 |
ulic | +0.099 |
chefs | +0.096 |
Neg logit contributions | |
ONES | -0.095 |
Naz | -0.094 |
OSP | -0.090 |
areth | -0.089 |
HTTP | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
ONES | +0.284 |
Naz | +0.279 |
OSP | +0.268 |
areth | +0.266 |
ospels | +0.250 |
Neg logit contributions | |
isine | -0.310 |
opian | -0.283 |
chen | -0.278 |
ulic | -0.267 |
chefs | -0.260 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ONES | +0.292 |
Naz | +0.291 |
OSP | +0.273 |
areth | +0.266 |
Sing | +0.252 |
Neg logit contributions | |
isine | -0.487 |
opian | -0.449 |
chen | -0.434 |
ulic | -0.426 |
chefs | -0.422 |
Token | Copyright |
Token ID | 15269 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
ONES | +0.094 |
Naz | +0.091 |
areth | +0.087 |
OSP | +0.086 |
ospels | +0.080 |
Neg logit contributions | |
isine | -0.157 |
opian | -0.145 |
chen | -0.144 |
ulic | -0.140 |
chefs | -0.135 |
Token | © |
Token ID | 10673 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
isine | +0.288 |
opian | +0.259 |
chen | +0.256 |
ulic | +0.242 |
chefs | +0.237 |
Neg logit contributions | |
ONES | -0.343 |
Naz | -0.337 |
OSP | -0.326 |
areth | -0.324 |
ospels | -0.308 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -8.07e+00 |
Pos logit contributions | |
isine | +2.791 |
opian | +2.495 |
chen | +2.490 |
ulic | +2.328 |
chefs | +2.284 |
Neg logit contributions | |
ONES | -3.719 |
Naz | -3.647 |
OSP | -3.543 |
areth | -3.528 |
ospels | -3.376 |
Token | Else |
Token ID | 25974 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
isine | +6.359 |
chen | +5.925 |
opian | +5.774 |
chefs | +5.402 |
ulic | +5.282 |
Neg logit contributions | |
ONES | -6.404 |
Naz | -6.176 |
OSP | -6.058 |
areth | -5.825 |
ospels | -5.697 |
Token | vier |
Token ID | 49663 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
isine | +2.509 |
opian | +2.297 |
chen | +2.229 |
ulic | +2.111 |
chefs | +2.082 |
Neg logit contributions | |
ONES | -2.730 |
Naz | -2.686 |
areth | -2.547 |
OSP | -2.538 |
CTV | -2.436 |
Token | B |
Token ID | 347 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
ONES | +0.644 |
Naz | +0.633 |
OSP | +0.606 |
areth | +0.599 |
HTTP | +0.560 |
Neg logit contributions | |
isine | -0.830 |
opian | -0.763 |
chen | -0.747 |
ulic | -0.720 |
chefs | -0.707 |
Token | . |
Token ID | 13 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
isine | +0.387 |
opian | +0.354 |
chen | +0.352 |
ulic | +0.340 |
chefs | +0.328 |
Neg logit contributions | |
ONES | -0.331 |
Naz | -0.326 |
OSP | -0.311 |
areth | -0.309 |
HTTP | -0.289 |
Token | V |
Token ID | 53 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
isine | +1.064 |
opian | +0.996 |
chen | +0.986 |
ulic | +0.959 |
chefs | +0.944 |
Neg logit contributions | |
ONES | -0.405 |
Naz | -0.392 |
OSP | -0.366 |
areth | -0.362 |
ospels | -0.320 |
Token | criminals |
Token ID | 12954 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
isine | +1.305 |
opian | +1.194 |
chen | +1.179 |
ulic | +1.126 |
chefs | +1.121 |
Neg logit contributions | |
ONES | -1.167 |
Naz | -1.145 |
OSP | -1.105 |
areth | -1.094 |
HTTP | -1.027 |
Token | who |
Token ID | 508 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
isine | +2.914 |
opian | +2.638 |
chen | +2.617 |
ulic | +2.478 |
chefs | +2.443 |
Neg logit contributions | |
ONES | -3.028 |
Naz | -2.965 |
OSP | -2.873 |
areth | -2.852 |
ospels | -2.696 |
Token | need |
Token ID | 761 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
ONES | +1.185 |
Naz | +1.166 |
OSP | +1.108 |
areth | +1.104 |
HTTP | +1.022 |
Neg logit contributions | |
isine | -1.661 |
opian | -1.522 |
chen | -1.492 |
ulic | -1.451 |
chefs | -1.409 |
Token | to |
Token ID | 284 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
ONES | +1.876 |
Naz | +1.847 |
OSP | +1.771 |
areth | +1.747 |
HTTP | +1.637 |
Neg logit contributions | |
isine | -2.329 |
opian | -2.132 |
chen | -2.093 |
ulic | -2.017 |
chefs | -1.971 |
Token | be |
Token ID | 307 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
isine | +0.784 |
opian | +0.718 |
chen | +0.706 |
ulic | +0.680 |
chefs | +0.664 |
Neg logit contributions | |
ONES | -0.694 |
Naz | -0.681 |
OSP | -0.657 |
areth | -0.649 |
HTTP | -0.610 |
Token | locked |
Token ID | 8970 |
Feature activation | -8.07e+00 |
Pos logit contributions | |
ONES | +1.076 |
Naz | +1.063 |
OSP | +1.019 |
areth | +1.012 |
HTTP | +0.950 |
Neg logit contributions | |
isine | -1.157 |
opian | -1.053 |
chen | -1.024 |
ulic | -0.990 |
chefs | -0.960 |
Token | up |
Token ID | 510 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
isine | +5.056 |
opian | +4.577 |
chen | +4.550 |
chefs | +4.181 |
ulic | +4.149 |
Neg logit contributions | |
ONES | -7.711 |
Naz | -7.510 |
OSP | -7.385 |
areth | -7.382 |
ospels | -7.011 |
Token | ? |
Token ID | 30 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ONES | +0.208 |
Naz | +0.205 |
OSP | +0.196 |
areth | +0.194 |
HTTP | +0.182 |
Neg logit contributions | |
isine | -0.246 |
opian | -0.225 |
chen | -0.220 |
ulic | -0.212 |
chefs | -0.208 |
Token | It |
Token ID | 632 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
isine | +1.082 |
opian | +0.994 |
chen | +0.984 |
ulic | +0.943 |
chefs | +0.923 |
Neg logit contributions | |
ONES | -0.864 |
Naz | -0.847 |
OSP | -0.814 |
areth | -0.805 |
ospels | -0.752 |
Token | depends |
Token ID | 8338 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
isine | +0.997 |
opian | +0.925 |
chen | +0.914 |
ulic | +0.873 |
chefs | +0.866 |
Neg logit contributions | |
ONES | -0.695 |
Naz | -0.685 |
OSP | -0.655 |
areth | -0.639 |
HTTP | -0.602 |
Token | on |
Token ID | 319 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ONES | +0.131 |
Naz | +0.129 |
OSP | +0.124 |
areth | +0.123 |
ospels | +0.115 |
Neg logit contributions | |
isine | -0.149 |
opian | -0.136 |
chen | -0.134 |
ulic | -0.128 |
chefs | -0.125 |
Token | in |
Token ID | 287 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
isine | +3.839 |
opian | +3.415 |
chen | +3.394 |
ulic | +3.239 |
chefs | +3.216 |
Neg logit contributions | |
ONES | -4.118 |
Naz | -4.014 |
OSP | -3.853 |
areth | -3.813 |
HTTP | -3.663 |
Token | 2013 |
Token ID | 2211 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
isine | +1.117 |
opian | +1.011 |
chen | +0.990 |
ulic | +0.946 |
chefs | +0.924 |
Neg logit contributions | |
ONES | -1.254 |
Naz | -1.234 |
OSP | -1.193 |
areth | -1.182 |
HTTP | -1.118 |
Token | to |
Token ID | 284 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
isine | +2.671 |
opian | +2.441 |
chen | +2.418 |
ulic | +2.303 |
chefs | +2.268 |
Neg logit contributions | |
ONES | -2.519 |
Naz | -2.456 |
OSP | -2.377 |
areth | -2.322 |
HTTP | -2.215 |
Token | create |
Token ID | 2251 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ONES | +0.054 |
Naz | +0.053 |
OSP | +0.051 |
areth | +0.051 |
HTTP | +0.047 |
Neg logit contributions | |
isine | -0.058 |
opian | -0.053 |
chen | -0.052 |
ulic | -0.050 |
chefs | -0.049 |
Token | a |
Token ID | 257 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
isine | +1.457 |
opian | +1.324 |
chen | +1.299 |
ulic | +1.247 |
chefs | +1.226 |
Neg logit contributions | |
ONES | -1.401 |
Naz | -1.390 |
OSP | -1.322 |
areth | -1.318 |
HTTP | -1.248 |
Token | mural |
Token ID | 36192 |
Feature activation | -8.01e+00 |
Pos logit contributions | |
ONES | +0.191 |
Naz | +0.188 |
OSP | +0.181 |
areth | +0.179 |
HTTP | +0.168 |
Neg logit contributions | |
isine | -0.195 |
opian | -0.177 |
chen | -0.173 |
ulic | -0.166 |
chefs | -0.162 |
Token | capturing |
Token ID | 21430 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
isine | +5.838 |
opian | +5.271 |
chen | +5.238 |
chefs | +4.915 |
ulic | +4.888 |
Neg logit contributions | |
ONES | -6.791 |
Naz | -6.753 |
areth | -6.463 |
OSP | -6.409 |
ospels | -6.175 |
Token | the |
Token ID | 262 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
isine | +0.694 |
opian | +0.631 |
chen | +0.619 |
ulic | +0.594 |
chefs | +0.590 |
Neg logit contributions | |
ONES | -0.664 |
Naz | -0.657 |
OSP | -0.632 |
areth | -0.625 |
HTTP | -0.591 |
Token | spirit |
Token ID | 4437 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
isine | +0.850 |
opian | +0.778 |
chen | +0.762 |
ulic | +0.732 |
chefs | +0.722 |
Neg logit contributions | |
ONES | -0.751 |
Naz | -0.739 |
OSP | -0.710 |
areth | -0.704 |
ospels | -0.661 |
Token | of |
Token ID | 286 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
ONES | +0.425 |
Naz | +0.418 |
OSP | +0.401 |
areth | +0.398 |
HTTP | +0.375 |
Neg logit contributions | |
isine | -0.442 |
opian | -0.403 |
chen | -0.394 |
ulic | -0.378 |
chefs | -0.373 |
Token | Toronto |
Token ID | 6586 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
isine | +0.813 |
opian | +0.740 |
chen | +0.725 |
ulic | +0.697 |
chefs | +0.690 |
Neg logit contributions | |
ONES | -0.766 |
Naz | -0.756 |
OSP | -0.727 |
areth | -0.718 |
HTTP | -0.680 |
Token | is |
Token ID | 318 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
isine | +0.303 |
opian | +0.282 |
chen | +0.278 |
ulic | +0.267 |
chefs | +0.265 |
Neg logit contributions | |
ONES | -0.214 |
Naz | -0.210 |
OSP | -0.201 |
areth | -0.197 |
ospels | -0.184 |
Token | going |
Token ID | 1016 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
isine | +1.105 |
opian | +1.004 |
chen | +0.985 |
ulic | +0.944 |
chefs | +0.923 |
Neg logit contributions | |
ONES | -1.107 |
Naz | -1.090 |
OSP | -1.050 |
areth | -1.039 |
ospels | -0.980 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
isine | +0.539 |
opian | +0.491 |
chen | +0.482 |
ulic | +0.461 |
chefs | +0.452 |
Neg logit contributions | |
ONES | -0.515 |
Naz | -0.507 |
OSP | -0.488 |
areth | -0.482 |
ospels | -0.454 |
Token | ban |
Token ID | 3958 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
isine | +1.076 |
opian | +0.986 |
chen | +0.968 |
ulic | +0.930 |
chefs | +0.910 |
Neg logit contributions | |
ONES | -0.993 |
Naz | -0.974 |
OSP | -0.939 |
areth | -0.928 |
ospels | -0.872 |
Token | most |
Token ID | 749 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
isine | +2.163 |
opian | +1.969 |
chen | +1.932 |
ulic | +1.848 |
chefs | +1.822 |
Neg logit contributions | |
ONES | -2.151 |
Naz | -2.114 |
OSP | -2.027 |
areth | -2.014 |
ospels | -1.901 |
Token | nude |
Token ID | 26349 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
isine | +1.727 |
opian | +1.573 |
chen | +1.547 |
ulic | +1.475 |
chefs | +1.465 |
Neg logit contributions | |
ONES | -1.698 |
Naz | -1.673 |
OSP | -1.605 |
areth | -1.601 |
ospels | -1.510 |
Token | photos |
Token ID | 5205 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
isine | +6.250 |
opian | +5.780 |
chen | +5.637 |
chefs | +5.508 |
chef | +5.274 |
Neg logit contributions | |
ONES | -6.474 |
Naz | -6.212 |
areth | -6.109 |
OSP | -5.931 |
ospels | -5.702 |
Token | and |
Token ID | 290 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
isine | +3.134 |
opian | +2.882 |
chen | +2.857 |
ulic | +2.723 |
chefs | +2.683 |
Neg logit contributions | |
ONES | -2.570 |
Naz | -2.511 |
OSP | -2.396 |
areth | -2.382 |
ospels | -2.243 |
Token | video |
Token ID | 2008 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
isine | +0.297 |
opian | +0.273 |
chen | +0.268 |
ulic | +0.259 |
chefs | +0.254 |
Neg logit contributions | |
ONES | -0.240 |
Naz | -0.236 |
OSP | -0.226 |
areth | -0.223 |
ospels | -0.209 |
Token | from |
Token ID | 422 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
ONES | +0.424 |
Naz | +0.417 |
OSP | +0.400 |
areth | +0.395 |
HTTP | +0.371 |
Neg logit contributions | |
isine | -0.517 |
opian | -0.474 |
chen | -0.465 |
ulic | -0.449 |
chefs | -0.437 |
Token | publicly |
Token ID | 7271 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
ONES | +0.032 |
Naz | +0.031 |
OSP | +0.030 |
areth | +0.030 |
ospels | +0.028 |
Neg logit contributions | |
isine | -0.033 |
opian | -0.030 |
chen | -0.030 |
ulic | -0.028 |
chefs | -0.028 |
Token | 46 |
Token ID | 3510 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
isine | +0.000 |
opian | +0.000 |
chen | +0.000 |
ulic | +0.000 |
chefs | +0.000 |
Neg logit contributions | |
ONES | -0.000 |
Naz | -0.000 |
OSP | -0.000 |
areth | -0.000 |
HTTP | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ONES | +0.571 |
Naz | +0.561 |
OSP | +0.538 |
areth | +0.531 |
HTTP | +0.496 |
Neg logit contributions | |
isine | -0.740 |
opian | -0.680 |
chen | -0.667 |
ulic | -0.644 |
chefs | -0.630 |
Token | 35 |
Token ID | 2327 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
ONES | +0.007 |
Naz | +0.007 |
OSP | +0.006 |
areth | +0.006 |
HTTP | +0.006 |
Neg logit contributions | |
isine | -0.015 |
opian | -0.014 |
chen | -0.014 |
ulic | -0.014 |
chefs | -0.013 |
Token | million |
Token ID | 1510 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
isine | +0.767 |
opian | +0.710 |
chen | +0.699 |
ulic | +0.674 |
chefs | +0.662 |
Neg logit contributions | |
ONES | -0.504 |
Naz | -0.493 |
OSP | -0.470 |
areth | -0.465 |
HTTP | -0.430 |
Token | that |
Token ID | 326 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
ONES | +0.065 |
Naz | +0.064 |
OSP | +0.061 |
areth | +0.061 |
HTTP | +0.057 |
Neg logit contributions | |
isine | -0.064 |
opian | -0.059 |
chen | -0.057 |
ulic | -0.055 |
chefs | -0.053 |
Token | Melvin |
Token ID | 48834 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
isine | +0.258 |
opian | +0.236 |
chen | +0.233 |
ulic | +0.223 |
chefs | +0.219 |
Neg logit contributions | |
ONES | -0.221 |
Naz | -0.216 |
OSP | -0.208 |
areth | -0.206 |
HTTP | -0.193 |
Token | Upton |
Token ID | 47755 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ONES | +5.036 |
Naz | +4.953 |
OSP | +4.645 |
areth | +4.569 |
CTV | +4.370 |
Neg logit contributions | |
isine | -6.167 |
opian | -5.869 |
chen | -5.514 |
ulic | -5.219 |
untled | -5.194 |
Token | Jr |
Token ID | 7504 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ONES | +1.395 |
Naz | +1.377 |
OSP | +1.315 |
areth | +1.293 |
HTTP | +1.205 |
Neg logit contributions | |
isine | -2.011 |
opian | -1.858 |
chen | -1.809 |
ulic | -1.752 |
chefs | -1.720 |
Token | . |
Token ID | 13 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
ONES | +0.920 |
Naz | +0.904 |
OSP | +0.867 |
areth | +0.862 |
ospels | +0.812 |
Neg logit contributions | |
isine | -1.052 |
opian | -0.960 |
chen | -0.955 |
ulic | -0.915 |
chefs | -0.887 |
Token | is |
Token ID | 318 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
isine | +0.825 |
opian | +0.758 |
chen | +0.756 |
ulic | +0.724 |
chefs | +0.711 |
Neg logit contributions | |
ONES | -0.607 |
Naz | -0.591 |
OSP | -0.568 |
areth | -0.562 |
ospels | -0.526 |
Token | due |
Token ID | 2233 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
isine | +0.625 |
opian | +0.565 |
chen | +0.551 |
ulic | +0.528 |
chefs | +0.514 |
Neg logit contributions | |
ONES | -0.702 |
Naz | -0.692 |
OSP | -0.668 |
areth | -0.661 |
HTTP | -0.626 |
Token | such |
Token ID | 884 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ONES | +2.362 |
Naz | +2.321 |
OSP | +2.227 |
areth | +2.198 |
HTTP | +2.070 |
Neg logit contributions | |
isine | -2.620 |
opian | -2.398 |
chen | -2.333 |
ulic | -2.267 |
chefs | -2.180 |
Token | as |
Token ID | 355 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ONES | +1.672 |
Naz | +1.656 |
OSP | +1.562 |
areth | +1.541 |
HTTP | +1.438 |
Neg logit contributions | |
isine | -2.808 |
opian | -2.573 |
chen | -2.503 |
ulic | -2.439 |
chefs | -2.391 |
Token | The |
Token ID | 383 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
isine | +0.094 |
opian | +0.085 |
chen | +0.084 |
ulic | +0.080 |
chefs | +0.079 |
Neg logit contributions | |
ONES | -0.087 |
Naz | -0.086 |
OSP | -0.083 |
areth | -0.082 |
HTTP | -0.077 |
Token | New |
Token ID | 968 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
isine | +0.460 |
opian | +0.420 |
chen | +0.414 |
ulic | +0.396 |
chefs | +0.387 |
Neg logit contributions | |
ONES | -0.423 |
Naz | -0.417 |
OSP | -0.401 |
areth | -0.397 |
HTTP | -0.373 |
Token | York |
Token ID | 1971 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ONES | +0.465 |
Naz | +0.457 |
OSP | +0.440 |
areth | +0.436 |
HTTP | +0.410 |
Neg logit contributions | |
isine | -0.475 |
opian | -0.432 |
chen | -0.424 |
ulic | -0.407 |
chefs | -0.396 |
Token | Times |
Token ID | 3782 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
ONES | +0.886 |
Naz | +0.874 |
OSP | +0.829 |
areth | +0.820 |
HTTP | +0.764 |
Neg logit contributions | |
isine | -1.240 |
opian | -1.148 |
chen | -1.127 |
ulic | -1.085 |
chefs | -1.069 |
Token | calling |
Token ID | 4585 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ONES | +4.169 |
Naz | +4.076 |
OSP | +3.925 |
areth | +3.840 |
Sing | +3.653 |
Neg logit contributions | |
isine | -5.047 |
opian | -4.666 |
chen | -4.504 |
ulic | -4.411 |
chefs | -4.241 |
Token | on |
Token ID | 319 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ONES | +1.112 |
Naz | +1.096 |
OSP | +1.053 |
areth | +1.040 |
HTTP | +0.983 |
Neg logit contributions | |
isine | -1.168 |
opian | -1.063 |
chen | -1.039 |
ulic | -1.000 |
chefs | -0.973 |
Token | them |
Token ID | 606 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ONES | +1.423 |
Naz | +1.395 |
OSP | +1.343 |
areth | +1.327 |
HTTP | +1.252 |
Neg logit contributions | |
isine | -1.513 |
opian | -1.381 |
chen | -1.345 |
ulic | -1.294 |
chefs | -1.252 |
Token | to |
Token ID | 284 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
isine | +1.130 |
opian | +1.028 |
chen | +1.014 |
ulic | +0.971 |
chefs | +0.959 |
Neg logit contributions | |
ONES | -1.083 |
Naz | -1.056 |
OSP | -1.019 |
areth | -1.012 |
HTTP | -0.956 |
Token | ban |
Token ID | 3958 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
ONES | +0.440 |
Naz | +0.433 |
OSP | +0.413 |
areth | +0.409 |
HTTP | +0.384 |
Neg logit contributions | |
isine | -0.527 |
opian | -0.483 |
chen | -0.474 |
ulic | -0.456 |
chefs | -0.444 |
Token | passenger |
Token ID | 11849 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
isine | +1.324 |
opian | +1.211 |
chen | +1.188 |
ulic | +1.144 |
chefs | +1.131 |
Neg logit contributions | |
ONES | -1.209 |
Naz | -1.195 |
OSP | -1.149 |
areth | -1.135 |
HTTP | -1.066 |
Token | vehicles |
Token ID | 5672 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
isine | +0.832 |
opian | +0.770 |
chen | +0.762 |
ulic | +0.737 |
chefs | +0.732 |
Neg logit contributions | |
ONES | -0.442 |
Naz | -0.435 |
OSP | -0.410 |
areth | -0.407 |
ospels | -0.374 |
Token | . |
Token ID | 13 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
ONES | +0.220 |
Naz | +0.216 |
OSP | +0.207 |
areth | +0.205 |
HTTP | +0.192 |
Neg logit contributions | |
isine | -0.262 |
opian | -0.240 |
chen | -0.236 |
ulic | -0.227 |
chefs | -0.222 |
Token | Unlike |
Token ID | 12101 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
isine | +0.748 |
opian | +0.685 |
chen | +0.675 |
ulic | +0.649 |
chefs | +0.635 |
Neg logit contributions | |
ONES | -0.626 |
Naz | -0.616 |
OSP | -0.591 |
areth | -0.585 |
ospels | -0.548 |
Token | in |
Token ID | 287 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
isine | +1.165 |
opian | +1.067 |
chen | +1.047 |
ulic | +1.005 |
chefs | +0.988 |
Neg logit contributions | |
ONES | -1.071 |
Naz | -1.055 |
OSP | -1.014 |
areth | -1.003 |
ospels | -0.942 |
Token | Uber |
Token ID | 12024 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
isine | +1.121 |
opian | +1.027 |
chen | +1.005 |
ulic | +0.967 |
chefs | +0.948 |
Neg logit contributions | |
ONES | -1.072 |
Naz | -1.054 |
OSP | -1.014 |
areth | -1.003 |
ospels | -0.942 |
Token | � |
Token ID | 447 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ONES | +3.665 |
Naz | +3.607 |
OSP | +3.432 |
areth | +3.386 |
Sing | +3.166 |
Neg logit contributions | |
isine | -5.515 |
opian | -5.060 |
chen | -4.965 |
ulic | -4.802 |
chefs | -4.711 |
Token | � |
Token ID | 247 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
isine | +0.236 |
opian | +0.217 |
chen | +0.213 |
ulic | +0.206 |
chefs | +0.202 |
Neg logit contributions | |
ONES | -0.179 |
Naz | -0.176 |
OSP | -0.169 |
areth | -0.167 |
HTTP | -0.156 |
Token | s |
Token ID | 82 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
isine | +0.099 |
opian | +0.091 |
chen | +0.090 |
ulic | +0.087 |
chefs | +0.085 |
Neg logit contributions | |
ONES | -0.078 |
Naz | -0.076 |
OSP | -0.073 |
areth | -0.072 |
ospels | -0.067 |
Token | model |
Token ID | 2746 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
isine | +0.606 |
opian | +0.558 |
chen | +0.548 |
ulic | +0.527 |
chefs | +0.517 |
Neg logit contributions | |
ONES | -0.552 |
Naz | -0.541 |
OSP | -0.519 |
areth | -0.513 |
HTTP | -0.483 |
Token | , |
Token ID | 11 |
Feature activation | +4.88e-03 |
Pos logit contributions | |
ONES | +0.030 |
Naz | +0.029 |
areth | +0.028 |
OSP | +0.028 |
ospels | +0.026 |
Neg logit contributions | |
isine | -0.038 |
opian | -0.035 |
chen | -0.034 |
ulic | -0.033 |
chefs | -0.032 |
Token | which |
Token ID | 543 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ONES | +0.270 |
Naz | +0.266 |
OSP | +0.255 |
areth | +0.252 |
HTTP | +0.237 |
Neg logit contributions | |
isine | -0.308 |
opian | -0.281 |
chen | -0.276 |
ulic | -0.266 |
chefs | -0.259 |
Token | was |
Token ID | 373 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ONES | +1.070 |
Naz | +1.052 |
OSP | +1.006 |
areth | +0.996 |
HTTP | +0.928 |
Neg logit contributions | |
isine | -1.423 |
opian | -1.308 |
chen | -1.281 |
ulic | -1.239 |
chefs | -1.207 |
Token | later |
Token ID | 1568 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ONES | +1.464 |
Naz | +1.445 |
OSP | +1.400 |
areth | +1.381 |
HTTP | +1.299 |
Neg logit contributions | |
isine | -1.598 |
opian | -1.445 |
chen | -1.415 |
ulic | -1.363 |
chefs | -1.326 |
Token | dubbed |
Token ID | 17494 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
ONES | +0.847 |
Naz | +0.836 |
OSP | +0.805 |
areth | +0.797 |
HTTP | +0.749 |
Neg logit contributions | |
isine | -0.925 |
opian | -0.842 |
chen | -0.823 |
ulic | -0.795 |
chefs | -0.772 |
Token | , |
Token ID | 11 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
isine | +0.361 |
opian | +0.329 |
chen | +0.324 |
ulic | +0.311 |
chefs | +0.303 |
Neg logit contributions | |
ONES | -0.340 |
Naz | -0.334 |
OSP | -0.320 |
areth | -0.317 |
ospels | -0.300 |
Token | Zuckerberg |
Token ID | 32584 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
ONES | +0.405 |
Naz | +0.399 |
OSP | +0.384 |
areth | +0.381 |
HTTP | +0.358 |
Neg logit contributions | |
isine | -0.415 |
opian | -0.377 |
chen | -0.370 |
ulic | -0.355 |
chefs | -0.346 |
Token | � |
Token ID | 447 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
ONES | +4.331 |
Naz | +4.219 |
OSP | +4.061 |
areth | +3.983 |
HTTP | +3.791 |
Neg logit contributions | |
isine | -5.292 |
opian | -4.884 |
chen | -4.710 |
ulic | -4.590 |
chefs | -4.500 |
Token | � |
Token ID | 247 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
ONES | +0.320 |
Naz | +0.316 |
OSP | +0.302 |
areth | +0.300 |
HTTP | +0.279 |
Neg logit contributions | |
isine | -0.448 |
opian | -0.412 |
chen | -0.404 |
ulic | -0.391 |
chefs | -0.383 |
Token | s |
Token ID | 82 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
ONES | +0.034 |
Naz | +0.033 |
OSP | +0.031 |
areth | +0.031 |
ospels | +0.029 |
Neg logit contributions | |
isine | -0.044 |
opian | -0.040 |
chen | -0.040 |
ulic | -0.038 |
chefs | -0.038 |
Token | Law |
Token ID | 3854 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
isine | +0.407 |
opian | +0.371 |
chen | +0.364 |
ulic | +0.349 |
chefs | +0.341 |
Neg logit contributions | |
ONES | -0.390 |
Naz | -0.384 |
OSP | -0.369 |
areth | -0.366 |
ospels | -0.345 |
Token | of |
Token ID | 286 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ONES | +1.645 |
Naz | +1.612 |
OSP | +1.559 |
areth | +1.531 |
HTTP | +1.443 |
Neg logit contributions | |
isine | -1.939 |
opian | -1.776 |
chen | -1.733 |
ulic | -1.680 |
chefs | -1.644 |
Token | . |
Token ID | 13 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
ONES | +0.144 |
Naz | +0.141 |
OSP | +0.136 |
areth | +0.134 |
HTTP | +0.125 |
Neg logit contributions | |
isine | -0.181 |
opian | -0.166 |
chen | -0.163 |
ulic | -0.157 |
chefs | -0.154 |
Token | It |
Token ID | 632 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
ONES | +0.360 |
Naz | +0.355 |
OSP | +0.337 |
areth | +0.333 |
HTTP | +0.310 |
Neg logit contributions | |
isine | -0.503 |
opian | -0.464 |
chen | -0.451 |
ulic | -0.441 |
chefs | -0.429 |
Token | � |
Token ID | 447 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
isine | +0.168 |
opian | +0.155 |
chen | +0.152 |
ulic | +0.147 |
chefs | +0.144 |
Neg logit contributions | |
ONES | -0.120 |
Naz | -0.118 |
OSP | -0.113 |
areth | -0.111 |
HTTP | -0.103 |
Token | � |
Token ID | 247 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ONES | +0.889 |
Naz | +0.875 |
areth | +0.847 |
OSP | +0.829 |
HTTP | +0.766 |
Neg logit contributions | |
isine | -1.420 |
opian | -1.318 |
chen | -1.278 |
ulic | -1.237 |
chefs | -1.225 |
Token | s |
Token ID | 82 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ONES | +1.113 |
Naz | +1.092 |
OSP | +1.046 |
areth | +1.030 |
HTTP | +0.961 |
Neg logit contributions | |
isine | -1.510 |
opian | -1.390 |
chen | -1.368 |
ulic | -1.319 |
chefs | -1.291 |
Token | kind |
Token ID | 1611 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
ONES | +0.085 |
Naz | +0.083 |
OSP | +0.080 |
areth | +0.079 |
HTTP | +0.074 |
Neg logit contributions | |
isine | -0.092 |
opian | -0.083 |
chen | -0.082 |
ulic | -0.079 |
chefs | -0.076 |
Token | of |
Token ID | 286 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
Naz | +3.968 |
ONES | +3.812 |
OSP | +3.632 |
areth | +3.557 |
ships | +3.475 |
Neg logit contributions | |
isine | -6.516 |
opian | -5.878 |
ulic | -5.682 |
chefs | -5.598 |
chen | -5.579 |
Token | a |
Token ID | 257 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ONES | +0.420 |
Naz | +0.414 |
OSP | +0.397 |
areth | +0.394 |
HTTP | +0.369 |
Neg logit contributions | |
isine | -0.448 |
opian | -0.407 |
chen | -0.398 |
ulic | -0.385 |
chefs | -0.373 |
Token | comedy |
Token ID | 10997 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
ONES | +0.858 |
Naz | +0.845 |
OSP | +0.812 |
areth | +0.799 |
wip | +0.752 |
Neg logit contributions | |
isine | -0.983 |
opian | -0.894 |
chen | -0.872 |
ulic | -0.851 |
chefs | -0.821 |
Token | runner |
Token ID | 17490 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
isine | +1.895 |
opian | +1.732 |
chen | +1.699 |
ulic | +1.628 |
chefs | +1.602 |
Neg logit contributions | |
ONES | -1.681 |
Naz | -1.658 |
OSP | -1.592 |
areth | -1.576 |
HTTP | -1.483 |
Token | , |
Token ID | 11 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
ONES | +1.310 |
Naz | +1.279 |
OSP | +1.228 |
areth | +1.212 |
Sing | +1.139 |
Neg logit contributions | |
isine | -1.682 |
opian | -1.536 |
chen | -1.507 |
ulic | -1.476 |
chefs | -1.426 |
Token | or |
Token ID | 273 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
isine | +1.933 |
opian | +1.742 |
chen | +1.698 |
ulic | +1.633 |
chefs | +1.585 |
Neg logit contributions | |
ONES | -2.221 |
Naz | -2.188 |
OSP | -2.113 |
areth | -2.098 |
HTTP | -1.983 |
Token | highlighted |
Token ID | 14537 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ONES | +0.037 |
Naz | +0.037 |
OSP | +0.035 |
areth | +0.035 |
HTTP | +0.032 |
Neg logit contributions | |
isine | -0.051 |
opian | -0.046 |
chen | -0.046 |
ulic | -0.044 |
chefs | -0.043 |
Token | how |
Token ID | 703 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
isine | +1.620 |
opian | +1.462 |
chen | +1.444 |
ulic | +1.372 |
chefs | +1.360 |
Neg logit contributions | |
ONES | -1.601 |
Naz | -1.591 |
OSP | -1.529 |
areth | -1.518 |
ospels | -1.431 |
Token | important |
Token ID | 1593 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ONES | +2.153 |
Naz | +2.110 |
OSP | +2.025 |
areth | +1.998 |
HTTP | +1.877 |
Neg logit contributions | |
isine | -2.449 |
opian | -2.254 |
chen | -2.196 |
ulic | -2.120 |
chefs | -2.049 |
Token | it |
Token ID | 340 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
ONES | +0.486 |
Naz | +0.479 |
OSP | +0.460 |
areth | +0.456 |
HTTP | +0.429 |
Neg logit contributions | |
isine | -0.538 |
opian | -0.489 |
chen | -0.481 |
ulic | -0.462 |
chefs | -0.454 |
Token | was |
Token ID | 373 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
isine | +0.553 |
chen | +0.503 |
opian | +0.501 |
ulic | +0.476 |
chefs | +0.475 |
Neg logit contributions | |
ONES | -0.435 |
Naz | -0.426 |
OSP | -0.411 |
areth | -0.404 |
ospels | -0.381 |
Token | for |
Token ID | 329 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
ONES | +1.151 |
Naz | +1.134 |
OSP | +1.089 |
areth | +1.077 |
HTTP | +1.012 |
Neg logit contributions | |
isine | -1.252 |
opian | -1.145 |
chen | -1.119 |
ulic | -1.076 |
chefs | -1.051 |
Token | him |
Token ID | 683 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
ONES | +0.373 |
Naz | +0.366 |
OSP | +0.352 |
areth | +0.348 |
HTTP | +0.325 |
Neg logit contributions | |
isine | -0.448 |
opian | -0.411 |
chen | -0.402 |
ulic | -0.388 |
chefs | -0.378 |
Token | to |
Token ID | 284 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
isine | +2.042 |
opian | +1.847 |
chen | +1.835 |
ulic | +1.753 |
chefs | +1.714 |
Neg logit contributions | |
ONES | -1.865 |
Naz | -1.815 |
OSP | -1.752 |
areth | -1.736 |
HTTP | -1.648 |
Token | defend |
Token ID | 4404 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
isine | +0.206 |
opian | +0.188 |
chen | +0.184 |
ulic | +0.177 |
chefs | +0.173 |
Neg logit contributions | |
ONES | -0.178 |
Naz | -0.175 |
OSP | -0.168 |
areth | -0.166 |
HTTP | -0.156 |
Token | his |
Token ID | 465 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
isine | +1.709 |
opian | +1.537 |
chen | +1.521 |
ulic | +1.447 |
chefs | +1.425 |
Neg logit contributions | |
ONES | -1.809 |
Naz | -1.784 |
OSP | -1.717 |
areth | -1.706 |
HTTP | -1.613 |
Token | , |
Token ID | 11 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
isine | +3.516 |
chen | +3.235 |
opian | +3.217 |
ulic | +3.086 |
chefs | +3.060 |
Neg logit contributions | |
ONES | -2.791 |
Naz | -2.738 |
areth | -2.622 |
OSP | -2.616 |
ospels | -2.445 |
Token | further |
Token ID | 2252 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
isine | +0.065 |
opian | +0.059 |
chen | +0.058 |
ulic | +0.056 |
chefs | +0.054 |
Neg logit contributions | |
ONES | -0.058 |
Naz | -0.057 |
OSP | -0.055 |
areth | -0.054 |
HTTP | -0.051 |
Token | Russian |
Token ID | 3394 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
ONES | +0.393 |
Naz | +0.386 |
OSP | +0.371 |
areth | +0.367 |
HTTP | +0.344 |
Neg logit contributions | |
isine | -0.449 |
opian | -0.411 |
chen | -0.403 |
ulic | -0.388 |
chefs | -0.379 |
Token | inc |
Token ID | 753 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
ONES | +0.360 |
Naz | +0.351 |
OSP | +0.339 |
areth | +0.335 |
ospels | +0.313 |
Neg logit contributions | |
isine | -0.472 |
opian | -0.435 |
chen | -0.430 |
ulic | -0.413 |
chefs | -0.407 |
Token | ursions |
Token ID | 42394 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ONES | +3.459 |
Naz | +3.437 |
OSP | +3.327 |
areth | +3.299 |
ospels | +3.139 |
Neg logit contributions | |
isine | -2.505 |
opian | -2.209 |
chen | -2.156 |
ulic | -2.033 |
chefs | -2.030 |
Token | , |
Token ID | 11 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
ONES | +1.566 |
Naz | +1.549 |
OSP | +1.483 |
areth | +1.475 |
HTTP | +1.381 |
Neg logit contributions | |
isine | -1.661 |
opian | -1.508 |
chen | -1.477 |
ulic | -1.430 |
chefs | -1.391 |
Token | would |
Token ID | 561 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ONES | +0.332 |
Naz | +0.325 |
OSP | +0.311 |
areth | +0.306 |
HTTP | +0.284 |
Neg logit contributions | |
isine | -0.500 |
opian | -0.462 |
chen | -0.455 |
ulic | -0.439 |
chefs | -0.432 |
Token | bring |
Token ID | 2222 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
isine | +1.516 |
opian | +1.393 |
chen | +1.364 |
ulic | +1.310 |
chefs | +1.285 |
Neg logit contributions | |
ONES | -1.354 |
Naz | -1.321 |
OSP | -1.277 |
areth | -1.261 |
HTTP | -1.187 |
Token | the |
Token ID | 262 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
isine | +1.804 |
opian | +1.647 |
chen | +1.627 |
ulic | +1.556 |
chefs | +1.536 |
Neg logit contributions | |
ONES | -1.617 |
Naz | -1.576 |
OSP | -1.545 |
areth | -1.523 |
ospels | -1.433 |
Token | crisis |
Token ID | 4902 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
isine | +0.674 |
opian | +0.618 |
chen | +0.607 |
ulic | +0.584 |
chefs | +0.572 |
Neg logit contributions | |
ONES | -0.557 |
Naz | -0.548 |
OSP | -0.527 |
areth | -0.521 |
ospels | -0.487 |
Token | to |
Token ID | 284 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
isine | +3.654 |
opian | +3.360 |
chen | +3.279 |
ulic | +3.117 |
chefs | +3.094 |
Neg logit contributions | |
ONES | -3.644 |
Naz | -3.556 |
OSP | -3.488 |
areth | -3.399 |
ospels | -3.269 |
Token | � |
Token ID | 447 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
ONES | +1.370 |
Naz | +1.350 |
OSP | +1.286 |
areth | +1.274 |
HTTP | +1.191 |
Neg logit contributions | |
isine | -1.780 |
opian | -1.640 |
chen | -1.599 |
ulic | -1.541 |
chefs | -1.509 |
Token | � |
Token ID | 247 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
ONES | +0.613 |
Naz | +0.604 |
OSP | +0.579 |
areth | +0.575 |
HTTP | +0.529 |
Neg logit contributions | |
isine | -0.942 |
opian | -0.872 |
chen | -0.850 |
ulic | -0.824 |
chefs | -0.808 |
Token | s |
Token ID | 82 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
ONES | +0.536 |
Naz | +0.526 |
OSP | +0.504 |
areth | +0.497 |
HTTP | +0.464 |
Neg logit contributions | |
isine | -0.723 |
opian | -0.664 |
chen | -0.655 |
ulic | -0.631 |
chefs | -0.618 |
Token | bliss |
Token ID | 30533 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ONES | +0.159 |
Naz | +0.157 |
OSP | +0.151 |
areth | +0.149 |
HTTP | +0.140 |
Neg logit contributions | |
isine | -0.162 |
opian | -0.147 |
chen | -0.144 |
ulic | -0.139 |
chefs | -0.135 |
Token | ful |
Token ID | 913 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ONES | +2.395 |
Naz | +2.366 |
OSP | +2.288 |
areth | +2.272 |
HTTP | +2.154 |
Neg logit contributions | |
isine | -1.845 |
opian | -1.642 |
chen | -1.604 |
ulic | -1.538 |
chefs | -1.484 |
Token | , |
Token ID | 11 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
ONES | +1.270 |
Naz | +1.252 |
OSP | +1.203 |
areth | +1.191 |
HTTP | +1.116 |
Neg logit contributions | |
isine | -1.410 |
opian | -1.285 |
chen | -1.259 |
ulic | -1.213 |
chefs | -1.181 |
Token | se |
Token ID | 384 |
Feature activation | -9.03e-02 |
Pos logit contributions | |
ONES | +0.231 |
Naz | +0.228 |
OSP | +0.219 |
areth | +0.217 |
HTTP | +0.204 |
Neg logit contributions | |
isine | -0.254 |
opian | -0.232 |
chen | -0.228 |
ulic | -0.219 |
chefs | -0.214 |
Token | rene |
Token ID | 25924 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
isine | +0.073 |
opian | +0.066 |
chen | +0.065 |
ulic | +0.062 |
chefs | +0.061 |
Neg logit contributions | |
ONES | -0.074 |
Naz | -0.073 |
OSP | -0.070 |
areth | -0.070 |
HTTP | -0.066 |
Token | save |
Token ID | 3613 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
ONES | +0.036 |
Naz | +0.036 |
OSP | +0.034 |
areth | +0.034 |
HTTP | +0.032 |
Neg logit contributions | |
isine | -0.042 |
opian | -0.038 |
chen | -0.037 |
ulic | -0.036 |
chefs | -0.035 |
Token | game |
Token ID | 983 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
ONES | +2.834 |
Naz | +2.785 |
OSP | +2.675 |
areth | +2.648 |
ospels | +2.473 |
Neg logit contributions | |
isine | -3.438 |
opian | -3.151 |
chen | -3.092 |
ulic | -2.985 |
chefs | -2.911 |
Token | music |
Token ID | 2647 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
ONES | +0.580 |
Naz | +0.570 |
OSP | +0.546 |
areth | +0.540 |
HTTP | +0.504 |
Neg logit contributions | |
isine | -0.751 |
opian | -0.690 |
chen | -0.677 |
ulic | -0.653 |
chefs | -0.639 |
Token | the |
Token ID | 262 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
ONES | +1.163 |
Naz | +1.144 |
OSP | +1.099 |
areth | +1.090 |
HTTP | +1.024 |
Neg logit contributions | |
isine | -1.251 |
opian | -1.142 |
chen | -1.119 |
ulic | -1.074 |
chefs | -1.050 |
Token | longest |
Token ID | 14069 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
isine | +0.270 |
opian | +0.242 |
chen | +0.236 |
ulic | +0.224 |
chefs | +0.219 |
Neg logit contributions | |
ONES | -0.349 |
Naz | -0.344 |
OSP | -0.332 |
areth | -0.330 |
HTTP | -0.313 |
Token | and |
Token ID | 290 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
isine | +1.014 |
opian | +0.933 |
chen | +0.911 |
ulic | +0.867 |
chefs | +0.861 |
Neg logit contributions | |
ONES | -0.862 |
Naz | -0.846 |
OSP | -0.810 |
areth | -0.809 |
ospels | -0.752 |
Token | most |
Token ID | 749 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
ONES | +0.054 |
Naz | +0.053 |
OSP | +0.052 |
areth | +0.051 |
HTTP | +0.049 |
Neg logit contributions | |
isine | -0.028 |
opian | -0.024 |
chen | -0.023 |
ulic | -0.022 |
chefs | -0.021 |
Token | laud |
Token ID | 28907 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
isine | +1.529 |
opian | +1.410 |
chen | +1.377 |
ulic | +1.306 |
chefs | +1.303 |
Neg logit contributions | |
ONES | -1.446 |
Naz | -1.415 |
OSP | -1.363 |
areth | -1.360 |
ospels | -1.277 |
Token | atory |
Token ID | 2870 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
Naz | +1.634 |
ONES | +1.624 |
OSP | +1.547 |
areth | +1.533 |
ospels | +1.436 |
Neg logit contributions | |
isine | -2.373 |
opian | -2.148 |
chen | -2.103 |
ulic | -2.050 |
chefs | -2.020 |
Token | article |
Token ID | 2708 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
ONES | +1.910 |
Naz | +1.881 |
OSP | +1.812 |
areth | +1.788 |
HTTP | +1.685 |
Neg logit contributions | |
isine | -2.011 |
opian | -1.828 |
chen | -1.792 |
ulic | -1.728 |
chefs | -1.677 |
Token | about |
Token ID | 546 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
isine | +0.326 |
opian | +0.297 |
chen | +0.292 |
ulic | +0.278 |
chefs | +0.273 |
Neg logit contributions | |
ONES | -0.314 |
Naz | -0.309 |
OSP | -0.297 |
areth | -0.295 |
HTTP | -0.278 |
Token | � |
Token ID | 564 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
ONES | +2.418 |
Naz | +2.390 |
OSP | +2.286 |
areth | +2.246 |
HTTP | +2.104 |
Neg logit contributions | |
isine | -2.874 |
opian | -2.633 |
chen | -2.572 |
ulic | -2.486 |
chefs | -2.409 |
Token | � |
Token ID | 250 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
isine | +0.737 |
opian | +0.668 |
chen | +0.657 |
ulic | +0.627 |
chefs | +0.613 |
Neg logit contributions | |
ONES | -0.757 |
Naz | -0.740 |
OSP | -0.716 |
areth | -0.707 |
ospels | -0.667 |
Token | The |
Token ID | 464 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
isine | +0.377 |
opian | +0.344 |
chen | +0.339 |
ulic | +0.326 |
chefs | +0.318 |
Neg logit contributions | |
ONES | -0.314 |
Naz | -0.305 |
OSP | -0.296 |
areth | -0.293 |
ospels | -0.274 |
Token |
|
Token ID | 198 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
isine | +0.489 |
opian | +0.448 |
chen | +0.443 |
ulic | +0.426 |
chefs | +0.415 |
Neg logit contributions | |
ONES | -0.399 |
Naz | -0.392 |
OSP | -0.377 |
areth | -0.373 |
ospels | -0.349 |
Token |
|
Token ID | 198 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
isine | +0.320 |
opian | +0.295 |
chen | +0.287 |
ulic | +0.281 |
chefs | +0.276 |
Neg logit contributions | |
ONES | -0.202 |
Naz | -0.200 |
OSP | -0.188 |
areth | -0.185 |
HTTP | -0.173 |
Token | Council |
Token ID | 40940 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
isine | +0.522 |
opian | +0.485 |
chen | +0.481 |
ulic | +0.465 |
chefs | +0.451 |
Neg logit contributions | |
ONES | -0.321 |
Naz | -0.312 |
areth | -0.299 |
OSP | -0.299 |
wip | -0.276 |
Token | member |
Token ID | 2888 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ONES | +0.267 |
Naz | +0.262 |
OSP | +0.252 |
areth | +0.249 |
HTTP | +0.234 |
Neg logit contributions | |
isine | -0.301 |
opian | -0.275 |
chen | -0.270 |
ulic | -0.260 |
chefs | -0.254 |
Token | John |
Token ID | 1757 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
ONES | +2.107 |
Naz | +2.077 |
OSP | +1.986 |
areth | +1.973 |
ospels | +1.839 |
Neg logit contributions | |
isine | -2.410 |
opian | -2.203 |
chen | -2.143 |
ulic | -2.071 |
chefs | -2.001 |
Token | Elder |
Token ID | 15624 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
isine | +0.738 |
opian | +0.674 |
chen | +0.664 |
ulic | +0.637 |
chefs | +0.621 |
Neg logit contributions | |
ONES | -0.668 |
Naz | -0.658 |
OSP | -0.634 |
areth | -0.624 |
HTTP | -0.590 |
Token | , |
Token ID | 11 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ONES | +3.784 |
Naz | +3.686 |
OSP | +3.583 |
areth | +3.529 |
Sing | +3.312 |
Neg logit contributions | |
isine | -4.938 |
opian | -4.473 |
chen | -4.335 |
ulic | -4.225 |
chefs | -4.186 |
Token | who |
Token ID | 508 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
isine | +0.877 |
opian | +0.801 |
chen | +0.786 |
ulic | +0.756 |
chefs | +0.739 |
Neg logit contributions | |
ONES | -0.778 |
Naz | -0.765 |
OSP | -0.735 |
areth | -0.727 |
HTTP | -0.683 |
Token | is |
Token ID | 318 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ONES | +1.345 |
Naz | +1.321 |
OSP | +1.262 |
areth | +1.248 |
HTTP | +1.160 |
Neg logit contributions | |
isine | -1.894 |
opian | -1.743 |
chen | -1.712 |
ulic | -1.655 |
chefs | -1.619 |
Token | also |
Token ID | 635 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
isine | +1.015 |
opian | +0.921 |
chen | +0.901 |
ulic | +0.865 |
chefs | +0.843 |
Neg logit contributions | |
ONES | -1.028 |
Naz | -1.013 |
OSP | -0.976 |
areth | -0.966 |
HTTP | -0.912 |
Token | a |
Token ID | 257 |
Feature activation | +5.61e-03 |
Pos logit contributions | |
ONES | +0.946 |
Naz | +0.932 |
OSP | +0.895 |
areth | +0.888 |
HTTP | +0.834 |
Neg logit contributions | |
isine | -1.042 |
opian | -0.946 |
chen | -0.915 |
ulic | -0.886 |
chefs | -0.859 |
Token | potentially |
Token ID | 6196 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
ONES | +1.260 |
Naz | +1.241 |
OSP | +1.192 |
areth | +1.183 |
HTTP | +1.109 |
Neg logit contributions | |
isine | -1.427 |
opian | -1.297 |
chen | -1.267 |
ulic | -1.223 |
chefs | -1.192 |
Token | dangerous |
Token ID | 4923 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
isine | +0.680 |
opian | +0.621 |
chen | +0.610 |
ulic | +0.585 |
chefs | +0.572 |
Neg logit contributions | |
ONES | -0.658 |
Naz | -0.648 |
OSP | -0.623 |
areth | -0.617 |
ospels | -0.582 |
Token | Trap |
Token ID | 21914 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
isine | +0.720 |
opian | +0.660 |
chen | +0.650 |
ulic | +0.626 |
chefs | +0.613 |
Neg logit contributions | |
ONES | -0.591 |
Naz | -0.580 |
OSP | -0.557 |
areth | -0.551 |
ospels | -0.517 |
Token | Card |
Token ID | 5172 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
isine | +0.384 |
opian | +0.352 |
chen | +0.346 |
ulic | +0.333 |
chefs | +0.326 |
Neg logit contributions | |
ONES | -0.317 |
Naz | -0.312 |
OSP | -0.299 |
areth | -0.296 |
HTTP | -0.277 |
Token | . |
Token ID | 13 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
ONES | +1.646 |
Naz | +1.621 |
OSP | +1.555 |
areth | +1.529 |
HTTP | +1.447 |
Neg logit contributions | |
isine | -2.058 |
opian | -1.888 |
chen | -1.835 |
ulic | -1.782 |
chefs | -1.738 |
Token | If |
Token ID | 1002 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ONES | +0.301 |
Naz | +0.296 |
OSP | +0.283 |
areth | +0.280 |
HTTP | +0.262 |
Neg logit contributions | |
isine | -0.382 |
opian | -0.350 |
chen | -0.341 |
ulic | -0.331 |
chefs | -0.323 |
Token | you |
Token ID | 345 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
isine | +2.212 |
opian | +2.013 |
chen | +1.994 |
ulic | +1.891 |
chefs | +1.876 |
Neg logit contributions | |
ONES | -2.246 |
Naz | -2.219 |
OSP | -2.142 |
areth | -2.105 |
ospels | -2.018 |
Token | learn |
Token ID | 2193 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
isine | +0.791 |
opian | +0.726 |
chen | +0.717 |
ulic | +0.689 |
chefs | +0.675 |
Neg logit contributions | |
ONES | -0.613 |
Naz | -0.602 |
OSP | -0.580 |
areth | -0.571 |
ospels | -0.535 |
Token | how |
Token ID | 703 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
isine | +1.998 |
opian | +1.832 |
chen | +1.816 |
ulic | +1.731 |
chefs | +1.716 |
Neg logit contributions | |
ONES | -1.867 |
Naz | -1.837 |
OSP | -1.749 |
areth | -1.743 |
HTTP | -1.639 |
Token | best |
Token ID | 1266 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
ONES | +1.482 |
Naz | +1.457 |
OSP | +1.395 |
areth | +1.384 |
ospels | +1.296 |
Neg logit contributions | |
isine | -1.778 |
opian | -1.628 |
chen | -1.602 |
ulic | -1.545 |
chefs | -1.516 |
Token | to |
Token ID | 284 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
isine | +0.583 |
opian | +0.534 |
chen | +0.525 |
ulic | +0.507 |
chefs | +0.496 |
Neg logit contributions | |
ONES | -0.560 |
Naz | -0.541 |
OSP | -0.523 |
areth | -0.521 |
ospels | -0.489 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
isine | +0.624 |
opian | +0.568 |
chen | +0.556 |
ulic | +0.534 |
chefs | +0.522 |
Neg logit contributions | |
ONES | -0.595 |
Naz | -0.586 |
OSP | -0.564 |
areth | -0.558 |
HTTP | -0.525 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
isine | +2.001 |
opian | +1.827 |
chen | +1.790 |
ulic | +1.723 |
chefs | +1.680 |
Neg logit contributions | |
ONES | -1.758 |
Naz | -1.719 |
OSP | -1.656 |
areth | -1.638 |
ospels | -1.540 |
Token | to |
Token ID | 284 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
isine | +0.848 |
opian | +0.776 |
chen | +0.761 |
ulic | +0.734 |
chefs | +0.718 |
Neg logit contributions | |
ONES | -0.701 |
Naz | -0.685 |
OSP | -0.659 |
areth | -0.652 |
ospels | -0.610 |
Token | Bernie |
Token ID | 10477 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
isine | +0.439 |
opian | +0.401 |
chen | +0.393 |
ulic | +0.379 |
chefs | +0.370 |
Neg logit contributions | |
ONES | -0.379 |
Naz | -0.373 |
OSP | -0.358 |
areth | -0.354 |
HTTP | -0.332 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
isine | +1.747 |
opian | +1.589 |
chen | +1.571 |
ulic | +1.500 |
chefs | +1.463 |
Neg logit contributions | |
ONES | -1.700 |
Naz | -1.671 |
OSP | -1.617 |
areth | -1.601 |
ospels | -1.512 |
Token | in |
Token ID | 287 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
ONES | +0.738 |
Naz | +0.730 |
OSP | +0.697 |
areth | +0.689 |
HTTP | +0.647 |
Neg logit contributions | |
isine | -0.896 |
opian | -0.820 |
chen | -0.804 |
ulic | -0.775 |
chefs | -0.759 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
isine | +0.382 |
opian | +0.347 |
chen | +0.341 |
ulic | +0.327 |
chefs | +0.319 |
Neg logit contributions | |
ONES | -0.365 |
Naz | -0.359 |
OSP | -0.346 |
areth | -0.342 |
HTTP | -0.322 |
Token | primary |
Token ID | 4165 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
ONES | +1.056 |
Naz | +1.040 |
OSP | +1.006 |
areth | +0.992 |
HTTP | +0.941 |
Neg logit contributions | |
isine | -1.056 |
opian | -0.943 |
chen | -0.931 |
ulic | -0.891 |
chefs | -0.868 |
Token | last |
Token ID | 938 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
isine | +1.990 |
opian | +1.857 |
chen | +1.814 |
ulic | +1.746 |
chefs | +1.718 |
Neg logit contributions | |
ONES | -1.704 |
Naz | -1.683 |
OSP | -1.611 |
areth | -1.603 |
HTTP | -1.489 |
Token | year |
Token ID | 614 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ONES | +0.832 |
Naz | +0.821 |
OSP | +0.794 |
areth | +0.787 |
HTTP | +0.747 |
Neg logit contributions | |
isine | -0.666 |
opian | -0.597 |
chen | -0.582 |
ulic | -0.556 |
chefs | -0.540 |
Token | . |
Token ID | 13 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
isine | +1.257 |
opian | +1.159 |
chen | +1.140 |
ulic | +1.097 |
chefs | +1.070 |
Neg logit contributions | |
ONES | -0.990 |
Naz | -0.965 |
OSP | -0.929 |
areth | -0.919 |
ospels | -0.858 |
Token | go |
Token ID | 467 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
ONES | +0.309 |
Naz | +0.303 |
OSP | +0.290 |
areth | +0.287 |
HTTP | +0.268 |
Neg logit contributions | |
isine | -0.400 |
opian | -0.367 |
chen | -0.361 |
ulic | -0.348 |
chefs | -0.341 |
Token | hand |
Token ID | 1021 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
isine | +0.218 |
opian | +0.198 |
chen | +0.194 |
ulic | +0.186 |
chefs | +0.182 |
Neg logit contributions | |
ONES | -0.226 |
Naz | -0.223 |
OSP | -0.214 |
areth | -0.212 |
ospels | -0.200 |
Token | in |
Token ID | 287 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
isine | +0.520 |
opian | +0.472 |
chen | +0.456 |
ulic | +0.429 |
chefs | +0.424 |
Neg logit contributions | |
ONES | -0.684 |
Naz | -0.673 |
OSP | -0.650 |
areth | -0.639 |
ospels | -0.614 |
Token | hand |
Token ID | 1021 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ONES | +0.264 |
Naz | +0.260 |
OSP | +0.250 |
areth | +0.248 |
HTTP | +0.233 |
Neg logit contributions | |
isine | -0.278 |
opian | -0.253 |
chen | -0.245 |
ulic | -0.238 |
chefs | -0.231 |
Token | to |
Token ID | 284 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
ONES | +1.481 |
Naz | +1.462 |
OSP | +1.408 |
areth | +1.392 |
HTTP | +1.309 |
Neg logit contributions | |
isine | -1.546 |
opian | -1.397 |
chen | -1.369 |
ulic | -1.324 |
chefs | -1.288 |
Token | realize |
Token ID | 6537 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
ONES | +0.655 |
Naz | +0.645 |
OSP | +0.620 |
areth | +0.613 |
HTTP | +0.576 |
Neg logit contributions | |
isine | -0.726 |
opian | -0.661 |
chen | -0.649 |
ulic | -0.624 |
chefs | -0.609 |
Token | the |
Token ID | 262 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
isine | +0.848 |
opian | +0.775 |
chen | +0.761 |
ulic | +0.732 |
chefs | +0.716 |
Neg logit contributions | |
ONES | -0.747 |
Naz | -0.735 |
OSP | -0.705 |
areth | -0.699 |
ospels | -0.655 |
Token | full |
Token ID | 1336 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
isine | +0.218 |
opian | +0.198 |
chen | +0.194 |
ulic | +0.187 |
chefs | +0.182 |
Neg logit contributions | |
ONES | -0.207 |
Naz | -0.203 |
OSP | -0.196 |
areth | -0.193 |
HTTP | -0.182 |
Token | potential |
Token ID | 2785 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
isine | +0.384 |
opian | +0.350 |
chen | +0.343 |
ulic | +0.329 |
chefs | +0.322 |
Neg logit contributions | |
ONES | -0.365 |
Naz | -0.359 |
OSP | -0.346 |
areth | -0.343 |
HTTP | -0.322 |
Token | of |
Token ID | 286 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
ONES | +0.821 |
Naz | +0.808 |
OSP | +0.780 |
areth | +0.761 |
HTTP | +0.720 |
Neg logit contributions | |
isine | -0.970 |
opian | -0.885 |
chen | -0.866 |
ulic | -0.834 |
chefs | -0.816 |
Token | process |
Token ID | 1429 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
isine | +0.391 |
opian | +0.357 |
chen | +0.351 |
ulic | +0.337 |
chefs | +0.330 |
Neg logit contributions | |
ONES | -0.356 |
Naz | -0.350 |
OSP | -0.337 |
areth | -0.334 |
HTTP | -0.313 |
Token | Jay |
Token ID | 30568 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ONES | +0.097 |
Naz | +0.095 |
OSP | +0.093 |
areth | +0.092 |
wip | +0.087 |
Neg logit contributions | |
isine | -0.106 |
opian | -0.096 |
chen | -0.096 |
ulic | -0.092 |
chefs | -0.088 |
Token | C |
Token ID | 327 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
ONES | +1.050 |
Naz | +1.038 |
OSP | +1.005 |
areth | +0.996 |
Sing | +0.953 |
Neg logit contributions | |
isine | -0.998 |
opian | -0.896 |
ulic | -0.836 |
chen | -0.830 |
chefs | -0.804 |
Token | z |
Token ID | 89 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
ONES | +0.493 |
Naz | +0.488 |
areth | +0.464 |
OSP | +0.460 |
Sing | +0.427 |
Neg logit contributions | |
isine | -0.742 |
opian | -0.679 |
chen | -0.659 |
chefs | -0.647 |
ulic | -0.647 |
Token | ark |
Token ID | 668 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
ONES | +0.630 |
Naz | +0.619 |
areth | +0.608 |
OSP | +0.587 |
Sing | +0.559 |
Neg logit contributions | |
isine | -0.754 |
opian | -0.682 |
ulic | -0.659 |
chen | -0.657 |
chefs | -0.654 |
Token | owski |
Token ID | 12079 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
isine | +0.418 |
opian | +0.337 |
chen | +0.323 |
ulic | +0.300 |
chefs | +0.294 |
Neg logit contributions | |
ONES | -1.135 |
Naz | -1.122 |
OSP | -1.091 |
areth | -1.085 |
HTTP | -1.043 |
Token | : |
Token ID | 25 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
ONES | +0.428 |
Naz | +0.423 |
OSP | +0.399 |
areth | +0.397 |
Sing | +0.377 |
Neg logit contributions | |
isine | -0.555 |
opian | -0.510 |
chen | -0.487 |
ulic | -0.481 |
chefs | -0.472 |
Token | And |
Token ID | 843 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
isine | +0.618 |
opian | +0.569 |
chen | +0.558 |
ulic | +0.539 |
chefs | +0.528 |
Neg logit contributions | |
ONES | -0.456 |
Naz | -0.448 |
OSP | -0.429 |
areth | -0.424 |
HTTP | -0.395 |
Token | you |
Token ID | 345 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ONES | +1.314 |
Naz | +1.293 |
OSP | +1.241 |
areth | +1.227 |
HTTP | +1.150 |
Neg logit contributions | |
isine | -1.534 |
opian | -1.401 |
chen | -1.373 |
ulic | -1.322 |
chefs | -1.279 |
Token | � |
Token ID | 447 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ONES | +0.645 |
Naz | +0.634 |
OSP | +0.599 |
areth | +0.596 |
HTTP | +0.549 |
Neg logit contributions | |
isine | -1.020 |
opian | -0.942 |
chen | -0.922 |
ulic | -0.895 |
chefs | -0.874 |
Token | � |
Token ID | 247 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
Naz | +0.781 |
ONES | +0.780 |
areth | +0.750 |
OSP | +0.731 |
HTTP | +0.682 |
Neg logit contributions | |
isine | -1.324 |
opian | -1.233 |
chen | -1.189 |
chefs | -1.149 |
ulic | -1.149 |
Token | ll |
Token ID | 297 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
ONES | +0.716 |
Naz | +0.707 |
OSP | +0.678 |
areth | +0.674 |
HTTP | +0.632 |
Neg logit contributions | |
isine | -0.787 |
opian | -0.717 |
chen | -0.701 |
ulic | -0.675 |
chefs | -0.660 |
Token | to |
Token ID | 284 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
isine | +0.025 |
opian | +0.023 |
chen | +0.022 |
ulic | +0.022 |
chefs | +0.021 |
Neg logit contributions | |
ONES | -0.022 |
Naz | -0.021 |
OSP | -0.021 |
areth | -0.020 |
ospels | -0.019 |
Token | Recap |
Token ID | 46585 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ONES | +0.535 |
Naz | +0.528 |
OSP | +0.506 |
areth | +0.500 |
ospels | +0.471 |
Neg logit contributions | |
isine | -0.617 |
opian | -0.565 |
chen | -0.555 |
ulic | -0.533 |
chefs | -0.524 |
Token | San |
Token ID | 2986 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
isine | +1.458 |
opian | +1.330 |
chen | +1.312 |
ulic | +1.250 |
chefs | +1.232 |
Neg logit contributions | |
ONES | -1.269 |
Naz | -1.254 |
OSP | -1.194 |
areth | -1.185 |
ospels | -1.117 |
Token | Juan |
Token ID | 16852 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
ONES | +1.974 |
Naz | +1.944 |
OSP | +1.865 |
areth | +1.846 |
HTTP | +1.732 |
Neg logit contributions | |
isine | -2.271 |
opian | -2.078 |
chen | -2.034 |
ulic | -1.958 |
chefs | -1.913 |
Token | Del |
Token ID | 4216 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
isine | +0.597 |
opian | +0.534 |
chen | +0.526 |
ulic | +0.502 |
chefs | +0.491 |
Neg logit contributions | |
ONES | -0.789 |
Naz | -0.778 |
OSP | -0.750 |
areth | -0.745 |
ospels | -0.711 |
Token | Sur |
Token ID | 4198 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
isine | +2.217 |
opian | +2.004 |
chen | +1.963 |
ulic | +1.880 |
chefs | +1.833 |
Neg logit contributions | |
ONES | -2.386 |
Naz | -2.350 |
OSP | -2.267 |
areth | -2.246 |
HTTP | -2.122 |
Token | Episode |
Token ID | 7922 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
isine | +1.644 |
opian | +1.498 |
chen | +1.484 |
ulic | +1.418 |
chefs | +1.401 |
Neg logit contributions | |
ONES | -1.460 |
Naz | -1.442 |
OSP | -1.377 |
areth | -1.371 |
ospels | -1.295 |
Token | 5 |
Token ID | 642 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
isine | +0.585 |
opian | +0.533 |
chen | +0.522 |
ulic | +0.502 |
chefs | +0.490 |
Neg logit contributions | |
ONES | -0.540 |
Naz | -0.531 |
OSP | -0.511 |
areth | -0.506 |
HTTP | -0.475 |
Token |
|
Token ID | 198 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
isine | +0.823 |
opian | +0.751 |
chen | +0.744 |
ulic | +0.711 |
chefs | +0.700 |
Neg logit contributions | |
ONES | -0.702 |
Naz | -0.693 |
OSP | -0.661 |
areth | -0.655 |
HTTP | -0.618 |
Token |
|
Token ID | 198 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
ONES | +0.413 |
Naz | +0.411 |
OSP | +0.384 |
areth | +0.376 |
Sing | +0.354 |
Neg logit contributions | |
isine | -0.699 |
opian | -0.645 |
chen | -0.623 |
ulic | -0.614 |
chefs | -0.606 |
Token | Coach |
Token ID | 40677 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
ONES | +0.269 |
Naz | +0.260 |
OSP | +0.248 |
areth | +0.247 |
ospels | +0.229 |
Neg logit contributions | |
isine | -0.461 |
opian | -0.427 |
chen | -0.424 |
ulic | -0.408 |
chefs | -0.400 |
Token | rise |
Token ID | 4485 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
isine | +1.641 |
opian | +1.498 |
chen | +1.473 |
ulic | +1.418 |
chefs | +1.383 |
Neg logit contributions | |
ONES | -1.618 |
Naz | -1.576 |
OSP | -1.525 |
areth | -1.508 |
HTTP | -1.424 |
Token | to |
Token ID | 284 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
isine | +2.322 |
opian | +2.129 |
chen | +2.076 |
ulic | +2.012 |
chefs | +1.972 |
Neg logit contributions | |
ONES | -2.149 |
Naz | -2.095 |
OSP | -2.006 |
areth | -1.992 |
ospels | -1.891 |
Token | 11 |
Token ID | 1367 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
isine | +0.455 |
opian | +0.413 |
chen | +0.405 |
ulic | +0.389 |
chefs | +0.379 |
Neg logit contributions | |
ONES | -0.442 |
Naz | -0.436 |
OSP | -0.419 |
areth | -0.415 |
HTTP | -0.391 |
Token | reviews |
Token ID | 8088 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
isine | +1.588 |
opian | +1.440 |
chen | +1.416 |
ulic | +1.357 |
chefs | +1.335 |
Neg logit contributions | |
ONES | -1.517 |
Naz | -1.488 |
OSP | -1.427 |
areth | -1.420 |
ospels | -1.333 |
Token | by |
Token ID | 416 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ONES | +0.304 |
Naz | +0.299 |
OSP | +0.286 |
areth | +0.283 |
HTTP | +0.265 |
Neg logit contributions | |
isine | -0.373 |
opian | -0.342 |
chen | -0.336 |
ulic | -0.324 |
chefs | -0.316 |
Token | 2021 |
Token ID | 33448 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
ONES | +0.182 |
Naz | +0.180 |
OSP | +0.173 |
areth | +0.171 |
ospels | +0.160 |
Neg logit contributions | |
isine | -0.205 |
opian | -0.186 |
chen | -0.183 |
ulic | -0.175 |
chefs | -0.171 |
Token | , |
Token ID | 11 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
isine | +4.574 |
opian | +4.146 |
chen | +4.122 |
ulic | +3.903 |
chefs | +3.851 |
Neg logit contributions | |
ONES | -4.276 |
Naz | -4.148 |
areth | -4.024 |
OSP | -3.975 |
ospels | -3.751 |
Token | and |
Token ID | 290 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
isine | +0.153 |
opian | +0.140 |
chen | +0.137 |
ulic | +0.132 |
chefs | +0.129 |
Neg logit contributions | |
ONES | -0.133 |
Naz | -0.131 |
OSP | -0.126 |
areth | -0.124 |
HTTP | -0.117 |
Token | 22 |
Token ID | 2534 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
ONES | +0.043 |
Naz | +0.042 |
OSP | +0.041 |
areth | +0.040 |
HTTP | +0.038 |
Neg logit contributions | |
isine | -0.047 |
opian | -0.043 |
chen | -0.042 |
ulic | -0.040 |
chefs | -0.039 |
Token | by |
Token ID | 416 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
isine | +1.517 |
opian | +1.378 |
chen | +1.353 |
ulic | +1.295 |
chefs | +1.274 |
Neg logit contributions | |
ONES | -1.504 |
Naz | -1.477 |
OSP | -1.415 |
areth | -1.405 |
HTTP | -1.324 |
Token | 2024 |
Token ID | 48609 |
Feature activation | -6.30e+00 |
Pos logit contributions | |
isine | +0.116 |
opian | +0.104 |
chen | +0.102 |
ulic | +0.097 |
chefs | +0.095 |
Neg logit contributions | |
ONES | -0.136 |
Naz | -0.134 |
OSP | -0.130 |
areth | -0.129 |
HTTP | -0.122 |
Token | applied |
Token ID | 5625 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ONES | +0.168 |
Naz | +0.166 |
OSP | +0.159 |
areth | +0.157 |
HTTP | +0.147 |
Neg logit contributions | |
isine | -0.214 |
opian | -0.197 |
chen | -0.193 |
ulic | -0.187 |
chefs | -0.183 |
Token | it |
Token ID | 340 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
isine | +1.425 |
opian | +1.295 |
chen | +1.274 |
ulic | +1.232 |
chefs | +1.207 |
Neg logit contributions | |
ONES | -1.364 |
Naz | -1.350 |
OSP | -1.297 |
areth | -1.288 |
ospels | -1.214 |
Token | to |
Token ID | 284 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
isine | +1.126 |
opian | +1.028 |
chen | +1.008 |
ulic | +0.973 |
chefs | +0.951 |
Neg logit contributions | |
ONES | -1.017 |
Naz | -1.005 |
OSP | -0.966 |
areth | -0.956 |
ospels | -0.900 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ONES | +0.359 |
Naz | +0.353 |
OSP | +0.340 |
areth | +0.336 |
HTTP | +0.316 |
Neg logit contributions | |
isine | -0.380 |
opian | -0.345 |
chen | -0.339 |
ulic | -0.324 |
chefs | -0.317 |
Token | Barnett |
Token ID | 38174 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
isine | +0.086 |
opian | +0.078 |
chen | +0.076 |
ulic | +0.073 |
chefs | +0.071 |
Neg logit contributions | |
ONES | -0.082 |
Naz | -0.081 |
OSP | -0.078 |
areth | -0.077 |
HTTP | -0.072 |
Token | shale |
Token ID | 30498 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
isine | +2.863 |
opian | +2.663 |
chen | +2.613 |
ulic | +2.560 |
chefs | +2.451 |
Neg logit contributions | |
ONES | -2.427 |
Naz | -2.405 |
OSP | -2.314 |
areth | -2.263 |
HTTP | -2.144 |
Token | , |
Token ID | 11 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
isine | +6.668 |
opian | +6.316 |
ulic | +6.142 |
chen | +6.138 |
chefs | +5.815 |
Neg logit contributions | |
ONES | -5.942 |
Naz | -5.889 |
OSP | -5.616 |
areth | -5.591 |
ospels | -5.285 |
Token | a |
Token ID | 257 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
isine | +0.546 |
opian | +0.501 |
chen | +0.492 |
ulic | +0.475 |
chefs | +0.464 |
Neg logit contributions | |
ONES | -0.450 |
Naz | -0.443 |
OSP | -0.425 |
areth | -0.421 |
HTTP | -0.394 |
Token | mile |
Token ID | 10591 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
isine | +0.349 |
opian | +0.319 |
chen | +0.313 |
ulic | +0.301 |
chefs | +0.294 |
Neg logit contributions | |
ONES | -0.308 |
Naz | -0.303 |
OSP | -0.291 |
areth | -0.288 |
HTTP | -0.270 |
Token | - |
Token ID | 12 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
isine | +1.157 |
opian | +1.070 |
chen | +1.048 |
ulic | +1.003 |
chefs | +0.985 |
Neg logit contributions | |
ONES | -0.937 |
Naz | -0.918 |
OSP | -0.880 |
areth | -0.867 |
ospels | -0.821 |
Token | and |
Token ID | 392 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
isine | +1.828 |
opian | +1.657 |
chen | +1.630 |
ulic | +1.523 |
chefs | +1.462 |
Neg logit contributions | |
ONES | -2.218 |
Naz | -2.156 |
OSP | -2.104 |
areth | -2.052 |
ospels | -1.989 |
Token | The |
Token ID | 383 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
ONES | +0.211 |
Naz | +0.208 |
OSP | +0.199 |
areth | +0.197 |
ospels | +0.185 |
Neg logit contributions | |
isine | -0.261 |
opian | -0.239 |
chen | -0.237 |
ulic | -0.227 |
chefs | -0.222 |
Token | move |
Token ID | 1445 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
isine | +0.455 |
opian | +0.418 |
chen | +0.411 |
ulic | +0.394 |
chefs | +0.388 |
Neg logit contributions | |
ONES | -0.398 |
Naz | -0.391 |
OSP | -0.376 |
areth | -0.372 |
ospels | -0.350 |
Token | would |
Token ID | 561 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
isine | +0.262 |
opian | +0.244 |
chen | +0.240 |
ulic | +0.231 |
chefs | +0.229 |
Neg logit contributions | |
ONES | -0.170 |
Naz | -0.166 |
OSP | -0.159 |
areth | -0.155 |
HTTP | -0.145 |
Token | be |
Token ID | 307 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
isine | +1.774 |
opian | +1.641 |
chen | +1.599 |
ulic | +1.540 |
chefs | +1.511 |
Neg logit contributions | |
ONES | -1.600 |
Naz | -1.559 |
OSP | -1.513 |
areth | -1.490 |
ospels | -1.406 |
Token | cheaper |
Token ID | 11721 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ONES | +0.159 |
Naz | +0.156 |
OSP | +0.150 |
areth | +0.148 |
ospels | +0.141 |
Neg logit contributions | |
isine | -0.168 |
opian | -0.154 |
chen | -0.151 |
ulic | -0.145 |
chefs | -0.142 |
Token | than |
Token ID | 621 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
ONES | +1.068 |
Naz | +1.051 |
OSP | +1.009 |
areth | +0.998 |
HTTP | +0.936 |
Neg logit contributions | |
isine | -1.236 |
opian | -1.130 |
chen | -1.109 |
ulic | -1.067 |
chefs | -1.044 |
Token | raising |
Token ID | 8620 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
isine | +4.024 |
chen | +3.661 |
opian | +3.638 |
ulic | +3.484 |
chefs | +3.439 |
Neg logit contributions | |
ONES | -4.333 |
Naz | -4.263 |
OSP | -4.143 |
areth | -4.124 |
ospels | -3.946 |
Token | its |
Token ID | 663 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
ONES | +0.608 |
Naz | +0.599 |
OSP | +0.577 |
areth | +0.571 |
ospels | +0.537 |
Neg logit contributions | |
isine | -0.647 |
opian | -0.589 |
chen | -0.581 |
ulic | -0.557 |
chefs | -0.544 |
Token | $ |
Token ID | 720 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
isine | +0.177 |
opian | +0.162 |
chen | +0.161 |
ulic | +0.154 |
chefs | +0.151 |
Neg logit contributions | |
ONES | -0.153 |
Naz | -0.150 |
OSP | -0.144 |
areth | -0.143 |
ospels | -0.134 |
Token | 31 |
Token ID | 3132 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
ONES | +0.344 |
Naz | +0.337 |
OSP | +0.321 |
areth | +0.317 |
HTTP | +0.294 |
Neg logit contributions | |
isine | -0.536 |
opian | -0.496 |
chen | -0.487 |
ulic | -0.471 |
chefs | -0.462 |
Token | - |
Token ID | 12 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
isine | +0.542 |
chen | +0.491 |
opian | +0.491 |
ulic | +0.464 |
chefs | +0.454 |
Neg logit contributions | |
ONES | -0.510 |
Naz | -0.500 |
OSP | -0.481 |
areth | -0.473 |
HTTP | -0.448 |
Token | on |
Token ID | 319 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
isine | +1.529 |
opian | +1.402 |
chen | +1.375 |
ulic | +1.314 |
chefs | +1.294 |
Neg logit contributions | |
ONES | -1.558 |
Naz | -1.536 |
OSP | -1.477 |
areth | -1.470 |
ospels | -1.387 |
Token | those |
Token ID | 883 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
ONES | +0.191 |
Naz | +0.189 |
OSP | +0.181 |
areth | +0.180 |
ospels | +0.169 |
Neg logit contributions | |
isine | -0.202 |
opian | -0.184 |
chen | -0.181 |
ulic | -0.174 |
chefs | -0.170 |
Token | who |
Token ID | 508 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
isine | +0.623 |
opian | +0.570 |
chen | +0.560 |
ulic | +0.539 |
chefs | +0.530 |
Neg logit contributions | |
ONES | -0.557 |
Naz | -0.552 |
OSP | -0.528 |
areth | -0.524 |
HTTP | -0.492 |
Token | have |
Token ID | 423 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ONES | +1.411 |
Naz | +1.380 |
OSP | +1.323 |
areth | +1.316 |
HTTP | +1.220 |
Neg logit contributions | |
isine | -1.849 |
opian | -1.694 |
chen | -1.661 |
ulic | -1.607 |
chefs | -1.565 |
Token | a |
Token ID | 257 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
isine | +1.159 |
opian | +1.061 |
chen | +1.047 |
ulic | +0.997 |
chefs | +0.986 |
Neg logit contributions | |
ONES | -1.131 |
Naz | -1.122 |
OSP | -1.074 |
areth | -1.062 |
ospels | -1.006 |
Token | Lock |
Token ID | 13656 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
isine | +0.311 |
opian | +0.285 |
chen | +0.281 |
ulic | +0.270 |
chefs | +0.264 |
Neg logit contributions | |
ONES | -0.262 |
Naz | -0.258 |
OSP | -0.247 |
areth | -0.245 |
ospels | -0.229 |
Token | out |
Token ID | 503 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
isine | +4.860 |
opian | +4.559 |
chen | +4.508 |
ulic | +4.296 |
chefs | +4.233 |
Neg logit contributions | |
ONES | -3.436 |
Naz | -3.432 |
OSP | -3.229 |
areth | -3.214 |
HTTP | -2.975 |
Token | sol |
Token ID | 1540 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
ONES | +0.750 |
Naz | +0.736 |
OSP | +0.707 |
areth | +0.699 |
HTTP | +0.653 |
Neg logit contributions | |
isine | -0.925 |
opian | -0.846 |
chen | -0.831 |
ulic | -0.801 |
chefs | -0.784 |
Token | en |
Token ID | 268 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
isine | +2.418 |
opian | +2.278 |
chen | +2.229 |
ulic | +2.140 |
chefs | +2.077 |
Neg logit contributions | |
ONES | -1.550 |
Naz | -1.512 |
OSP | -1.433 |
areth | -1.403 |
HTTP | -1.305 |
Token | oid |
Token ID | 1868 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
isine | +0.120 |
opian | +0.111 |
chen | +0.110 |
ulic | +0.106 |
chefs | +0.103 |
Neg logit contributions | |
ONES | -0.080 |
Naz | -0.079 |
OSP | -0.075 |
areth | -0.073 |
HTTP | -0.069 |
Token | which |
Token ID | 543 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ONES | +2.240 |
Naz | +2.174 |
OSP | +2.124 |
areth | +2.079 |
wip | +1.960 |
Neg logit contributions | |
isine | -2.873 |
opian | -2.605 |
chen | -2.550 |
ulic | -2.453 |
chefs | -2.413 |
Token | took |
Token ID | 1718 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
ONES | +0.380 |
Naz | +0.373 |
OSP | +0.357 |
areth | +0.353 |
HTTP | +0.329 |
Neg logit contributions | |
isine | -0.514 |
opian | -0.473 |
chen | -0.464 |
ulic | -0.449 |
chefs | -0.439 |
Token | special |
Token ID | 2041 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
ONES | +0.463 |
Naz | +0.455 |
OSP | +0.437 |
areth | +0.433 |
HTTP | +0.407 |
Neg logit contributions | |
isine | -0.519 |
opian | -0.475 |
chen | -0.465 |
ulic | -0.448 |
chefs | -0.436 |
Token | care |
Token ID | 1337 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ONES | +0.490 |
Naz | +0.481 |
OSP | +0.459 |
areth | +0.453 |
HTTP | +0.421 |
Neg logit contributions | |
isine | -0.734 |
opian | -0.679 |
chen | -0.667 |
ulic | -0.645 |
chefs | -0.631 |
Token | to |
Token ID | 284 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
ONES | +1.489 |
Naz | +1.468 |
OSP | +1.409 |
areth | +1.395 |
HTTP | +1.310 |
Neg logit contributions | |
isine | -1.623 |
opian | -1.476 |
chen | -1.448 |
ulic | -1.393 |
chefs | -1.359 |
Token | avoid |
Token ID | 3368 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
ONES | +0.053 |
Naz | +0.052 |
OSP | +0.050 |
areth | +0.049 |
HTTP | +0.047 |
Neg logit contributions | |
isine | -0.056 |
opian | -0.051 |
chen | -0.050 |
ulic | -0.048 |
chefs | -0.047 |
Token | contamination |
Token ID | 22733 |
Feature activation | -7.22e+00 |
Pos logit contributions | |
isine | +0.570 |
opian | +0.516 |
chen | +0.506 |
ulic | +0.484 |
chefs | +0.473 |
Neg logit contributions | |
ONES | -0.605 |
Naz | -0.597 |
OSP | -0.576 |
areth | -0.570 |
ospels | -0.538 |
Token | . |
Token ID | 13 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
isine | +5.494 |
opian | +5.062 |
chen | +4.946 |
ulic | +4.655 |
chefs | +4.641 |
Neg logit contributions | |
Naz | -5.860 |
ONES | -5.849 |
OSP | -5.668 |
areth | -5.621 |
ospels | -5.338 |
Token | That |
Token ID | 1320 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
isine | +0.218 |
opian | +0.200 |
chen | +0.195 |
ulic | +0.188 |
chefs | +0.184 |
Neg logit contributions | |
ONES | -0.178 |
Naz | -0.175 |
OSP | -0.168 |
areth | -0.166 |
HTTP | -0.155 |
Token | included |
Token ID | 3017 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
isine | +0.574 |
opian | +0.527 |
chen | +0.520 |
ulic | +0.500 |
chefs | +0.494 |
Neg logit contributions | |
ONES | -0.434 |
Naz | -0.426 |
OSP | -0.408 |
areth | -0.404 |
ospels | -0.377 |
Token | protecting |
Token ID | 10192 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
ONES | +2.107 |
Naz | +2.067 |
OSP | +1.982 |
areth | +1.967 |
HTTP | +1.867 |
Neg logit contributions | |
isine | -2.040 |
opian | -1.844 |
chen | -1.799 |
ulic | -1.730 |
chefs | -1.648 |
Token | the |
Token ID | 262 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
isine | +0.273 |
opian | +0.249 |
chen | +0.244 |
ulic | +0.235 |
chefs | +0.229 |
Neg logit contributions | |
ONES | -0.253 |
Naz | -0.250 |
OSP | -0.240 |
areth | -0.237 |
HTTP | -0.223 |