Token | , |
Token ID | 11 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
kson | +0.136 |
Wolf | +0.130 |
Wiz | +0.130 |
ATK | +0.125 |
pent | +0.117 |
Neg logit contributions | |
erg | -0.120 |
NL | -0.116 |
recomp | -0.112 |
ropolitan | -0.112 |
cape | -0.111 |
Token | though |
Token ID | 996 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
kson | +0.316 |
Wolf | +0.303 |
Wiz | +0.302 |
ATK | +0.291 |
pent | +0.271 |
Neg logit contributions | |
erg | -0.262 |
NL | -0.254 |
recomp | -0.245 |
ropolitan | -0.245 |
cape | -0.243 |
Token | it |
Token ID | 340 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
kson | +2.062 |
Wolf | +2.008 |
Wiz | +1.964 |
ATK | +1.901 |
pent | +1.733 |
Neg logit contributions | |
erg | -2.046 |
NL | -1.986 |
ropolitan | -1.942 |
cape | -1.910 |
recomp | -1.904 |
Token | faces |
Token ID | 6698 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
kson | +0.454 |
Wolf | +0.434 |
Wiz | +0.431 |
ATK | +0.416 |
pent | +0.385 |
Neg logit contributions | |
erg | -0.430 |
NL | -0.419 |
ropolitan | -0.404 |
cape | -0.400 |
recomp | -0.400 |
Token | an |
Token ID | 281 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
kson | +0.510 |
Wolf | +0.490 |
Wiz | +0.486 |
ATK | +0.468 |
pent | +0.433 |
Neg logit contributions | |
erg | -0.507 |
NL | -0.492 |
ropolitan | -0.475 |
cape | -0.474 |
recomp | -0.473 |
Token | uphill |
Token ID | 35256 |
Feature activation | +1.74e+01 |
Pos logit contributions | |
erg | +1.607 |
NL | +1.564 |
recomp | +1.507 |
cape | +1.484 |
ropolitan | +1.483 |
Neg logit contributions | |
kson | -1.976 |
Wiz | -1.882 |
Wolf | -1.871 |
ATK | -1.801 |
pent | -1.712 |
Token | battle |
Token ID | 3344 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Wolf | +8.769 |
Wiz | +8.435 |
kson | +8.415 |
ATK | +8.181 |
restriction | +7.724 |
Neg logit contributions | |
llular | -12.371 |
ropolitan | -12.351 |
zig | -12.299 |
NL | -12.136 |
FORE | -12.078 |
Token | in |
Token ID | 287 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
kson | +1.390 |
Wolf | +1.338 |
Wiz | +1.325 |
ATK | +1.280 |
pent | +1.180 |
Neg logit contributions | |
erg | -1.353 |
NL | -1.317 |
ropolitan | -1.273 |
recomp | -1.262 |
cape | -1.255 |
Token | the |
Token ID | 262 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
erg | +1.132 |
NL | +1.100 |
recomp | +1.071 |
ropolitan | +1.056 |
cape | +1.055 |
Neg logit contributions | |
kson | -1.106 |
Wiz | -1.045 |
Wolf | -1.037 |
ATK | -1.005 |
pent | -0.932 |
Token | House |
Token ID | 2097 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
kson | +0.835 |
Wolf | +0.802 |
Wiz | +0.797 |
ATK | +0.758 |
pent | +0.699 |
Neg logit contributions | |
erg | -1.003 |
NL | -0.975 |
ropolitan | -0.950 |
cape | -0.945 |
recomp | -0.945 |
Token | and |
Token ID | 290 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
erg | +1.525 |
NL | +1.485 |
recomp | +1.426 |
cape | +1.421 |
ropolitan | +1.410 |
Neg logit contributions | |
kson | -1.820 |
Wiz | -1.731 |
Wolf | -1.718 |
ATK | -1.672 |
pent | -1.551 |
Token | suicide |
Token ID | 7341 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
kson | +2.828 |
Wolf | +2.734 |
Wiz | +2.576 |
ATK | +2.526 |
restriction | +2.251 |
Neg logit contributions | |
NL | -4.726 |
erg | -4.716 |
recomp | -4.543 |
cape | -4.534 |
ropolitan | -4.492 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
erg | +0.430 |
NL | +0.415 |
recomp | +0.401 |
ropolitan | +0.398 |
cape | +0.398 |
Neg logit contributions | |
kson | -0.526 |
Wiz | -0.503 |
Wolf | -0.502 |
ATK | -0.485 |
pent | -0.453 |
Token | But |
Token ID | 887 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
kson | +0.837 |
Wolf | +0.805 |
Wiz | +0.799 |
ATK | +0.769 |
pent | +0.713 |
Neg logit contributions | |
erg | -0.774 |
NL | -0.750 |
recomp | -0.729 |
cape | -0.725 |
ropolitan | -0.724 |
Token | in |
Token ID | 287 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
kson | +2.275 |
Wolf | +2.220 |
Wiz | +2.167 |
ATK | +2.074 |
pent | +1.909 |
Neg logit contributions | |
erg | -2.375 |
NL | -2.310 |
cape | -2.242 |
ropolitan | -2.231 |
recomp | -2.216 |
Token | the |
Token ID | 262 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
kson | +2.559 |
Wolf | +2.489 |
Wiz | +2.431 |
ATK | +2.330 |
pent | +2.141 |
Neg logit contributions | |
erg | -2.567 |
NL | -2.493 |
cape | -2.406 |
ropolitan | -2.387 |
recomp | -2.361 |
Token | hardest |
Token ID | 17612 |
Feature activation | +1.68e+01 |
Pos logit contributions | |
kson | +4.057 |
Wolf | +4.003 |
Wiz | +3.875 |
ATK | +3.722 |
restriction | +3.433 |
Neg logit contributions | |
erg | -3.822 |
NL | -3.661 |
cape | -3.565 |
ropolitan | -3.530 |
recomp | -3.506 |
Token | - |
Token ID | 12 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
kson | +8.572 |
Wolf | +8.506 |
Wiz | +8.218 |
ATK | +7.835 |
restriction | +7.510 |
Neg logit contributions | |
NL | -11.435 |
cape | -11.140 |
llular | -11.109 |
FORE | -11.060 |
erg | -11.045 |
Token | hit |
Token ID | 17945 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
kson | +4.398 |
Wolf | +4.291 |
Wiz | +4.060 |
ATK | +4.020 |
pent | +3.719 |
Neg logit contributions | |
recomp | -11.068 |
NL | -10.852 |
llular | -10.762 |
Clarkson | -10.756 |
erg | -10.629 |
Token | counties |
Token ID | 14683 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
kson | +4.846 |
Wolf | +4.753 |
Wiz | +4.621 |
ATK | +4.342 |
restriction | +3.995 |
Neg logit contributions | |
erg | -5.879 |
NL | -5.818 |
llular | -5.678 |
cape | -5.601 |
ropolitan | -5.590 |
Token | in |
Token ID | 287 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
kson | +2.407 |
Wolf | +2.349 |
Wiz | +2.317 |
ATK | +2.202 |
pent | +2.025 |
Neg logit contributions | |
erg | -2.429 |
NL | -2.363 |
ropolitan | -2.301 |
recomp | -2.299 |
cape | -2.273 |
Token | that |
Token ID | 326 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
kson | +1.327 |
Wolf | +1.280 |
Wiz | +1.261 |
ATK | +1.215 |
pent | +1.121 |
Neg logit contributions | |
erg | -1.308 |
NL | -1.271 |
cape | -1.230 |
recomp | -1.222 |
ropolitan | -1.219 |
Token | lovely |
Token ID | 14081 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
erg | +1.479 |
NL | +1.424 |
recomp | +1.397 |
cape | +1.376 |
ropolitan | +1.374 |
Neg logit contributions | |
kson | -1.412 |
Wiz | -1.338 |
Wolf | -1.328 |
ATK | -1.286 |
pent | -1.199 |
Token | ball |
Token ID | 2613 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
erg | +3.094 |
NL | +2.965 |
recomp | +2.958 |
Clarkson | +2.901 |
cape | +2.894 |
Neg logit contributions | |
kson | -2.908 |
Wiz | -2.767 |
Wolf | -2.731 |
ATK | -2.641 |
pent | -2.508 |
Token | to |
Token ID | 284 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
erg | +2.190 |
NL | +2.090 |
recomp | +2.070 |
cape | +2.041 |
Clarkson | +2.013 |
Neg logit contributions | |
kson | -2.541 |
Wiz | -2.427 |
Wolf | -2.412 |
ATK | -2.341 |
pent | -2.191 |
Token | Bent |
Token ID | 20421 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
erg | +1.776 |
NL | +1.723 |
recomp | +1.671 |
cape | +1.663 |
ropolitan | +1.651 |
Neg logit contributions | |
kson | -1.854 |
Wiz | -1.763 |
Wolf | -1.745 |
ATK | -1.697 |
pent | -1.582 |
Token | . |
Token ID | 13 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
erg | +1.268 |
NL | +1.219 |
recomp | +1.179 |
cape | +1.172 |
ropolitan | +1.168 |
Neg logit contributions | |
kson | -1.461 |
Wiz | -1.403 |
Wolf | -1.395 |
ATK | -1.350 |
pent | -1.261 |
Token | Sur |
Token ID | 4198 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
erg | +2.860 |
NL | +2.786 |
Clarkson | +2.701 |
cape | +2.675 |
zig | +2.634 |
Neg logit contributions | |
kson | -3.440 |
Wiz | -3.276 |
Wolf | -3.200 |
ATK | -3.156 |
pent | -2.984 |
Token | ging |
Token ID | 2667 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
kson | +8.122 |
Wolf | +7.930 |
Wiz | +7.887 |
ATK | +7.558 |
pent | +7.440 |
Neg logit contributions | |
NL | -11.085 |
erg | -11.049 |
DOT | -10.569 |
Clarkson | -10.555 |
nexus | -10.453 |
Token | forward |
Token ID | 2651 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
erg | +0.513 |
NL | +0.499 |
recomp | +0.482 |
ropolitan | +0.480 |
cape | +0.479 |
Neg logit contributions | |
kson | -0.548 |
Wolf | -0.523 |
Wiz | -0.522 |
ATK | -0.502 |
pent | -0.467 |
Token | , |
Token ID | 11 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
erg | +1.534 |
NL | +1.485 |
recomp | +1.441 |
cape | +1.433 |
Clarkson | +1.420 |
Neg logit contributions | |
kson | -1.717 |
Wiz | -1.634 |
Wolf | -1.619 |
ATK | -1.577 |
pent | -1.475 |
Token | he |
Token ID | 339 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
erg | +1.139 |
NL | +1.105 |
recomp | +1.069 |
cape | +1.063 |
ropolitan | +1.058 |
Neg logit contributions | |
kson | -1.231 |
Wiz | -1.173 |
Wolf | -1.167 |
ATK | -1.128 |
pent | -1.051 |
Token | held |
Token ID | 2714 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
erg | +1.900 |
NL | +1.833 |
recomp | +1.816 |
cape | +1.784 |
Clarkson | +1.767 |
Neg logit contributions | |
kson | -1.939 |
Wiz | -1.846 |
Wolf | -1.837 |
ATK | -1.776 |
pent | -1.652 |
Token | O |
Token ID | 440 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
erg | +0.804 |
NL | +0.782 |
recomp | +0.745 |
Clarkson | +0.741 |
cape | +0.740 |
Neg logit contributions | |
kson | -1.147 |
Wiz | -1.088 |
Wolf | -1.081 |
ATK | -1.049 |
pent | -0.998 |
Token | & |
Token ID | 5 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
kson | +2.959 |
Wolf | +2.874 |
Wiz | +2.830 |
ATK | +2.726 |
pent | +2.521 |
Neg logit contributions | |
erg | -3.361 |
recomp | -3.348 |
ropolitan | -3.275 |
NL | -3.272 |
cape | -3.230 |
Token | A |
Token ID | 32 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
erg | +0.270 |
NL | +0.263 |
recomp | +0.252 |
cape | +0.251 |
ropolitan | +0.251 |
Neg logit contributions | |
kson | -0.303 |
Wiz | -0.289 |
Wolf | -0.289 |
ATK | -0.278 |
pent | -0.259 |
Token | - |
Token ID | 12 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
kson | +2.164 |
Wolf | +2.100 |
Wiz | +2.083 |
ATK | +2.007 |
pent | +1.850 |
Neg logit contributions | |
erg | -2.071 |
recomp | -1.997 |
NL | -1.992 |
ropolitan | -1.977 |
cape | -1.934 |
Token | M |
Token ID | 44 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
kson | +2.089 |
Wolf | +2.019 |
Wiz | +2.012 |
ATK | +1.916 |
pent | +1.798 |
Neg logit contributions | |
erg | -2.065 |
recomp | -1.993 |
NL | -1.974 |
ropolitan | -1.967 |
cape | -1.933 |
Token | anc |
Token ID | 1192 |
Feature activation | +1.64e+01 |
Pos logit contributions | |
kson | +1.227 |
Wolf | +1.175 |
Wiz | +1.169 |
ATK | +1.129 |
pent | +1.055 |
Neg logit contributions | |
erg | -1.012 |
NL | -0.987 |
recomp | -0.972 |
cape | -0.956 |
ropolitan | -0.948 |
Token | rus |
Token ID | 14932 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
Wolf | +11.467 |
kson | +11.249 |
Wiz | +10.772 |
ATK | +10.287 |
pent | +9.879 |
Neg logit contributions | |
NL | -8.125 |
recomp | -7.949 |
cape | -7.813 |
erg | -7.720 |
Clarkson | -7.681 |
Token | hes |
Token ID | 956 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
kson | +1.821 |
Wolf | +1.729 |
Wiz | +1.728 |
ATK | +1.645 |
pent | +1.514 |
Neg logit contributions | |
erg | -2.226 |
NL | -2.188 |
recomp | -2.127 |
ropolitan | -2.085 |
cape | -2.069 |
Token | - |
Token ID | 12 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
kson | +3.105 |
Wolf | +3.032 |
Wiz | +3.019 |
ATK | +2.866 |
pent | +2.664 |
Neg logit contributions | |
erg | -3.014 |
NL | -2.956 |
recomp | -2.909 |
ropolitan | -2.839 |
cape | -2.806 |
Token | Ro |
Token ID | 15450 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
kson | +3.076 |
Wolf | +2.991 |
Wiz | +2.980 |
ATK | +2.826 |
pent | +2.680 |
Neg logit contributions | |
erg | -2.958 |
recomp | -2.906 |
ropolitan | -2.847 |
NL | -2.800 |
cape | -2.770 |
Token | asting |
Token ID | 9222 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
erg | +0.353 |
NL | +0.340 |
recomp | +0.326 |
ropolitan | +0.325 |
cape | +0.323 |
Neg logit contributions | |
kson | -0.486 |
Wiz | -0.465 |
Wolf | -0.465 |
ATK | -0.451 |
pent | -0.422 |
Token | Resident |
Token ID | 22373 |
Feature activation | +7.76e+00 |
Pos logit contributions | |
erg | +0.709 |
NL | +0.691 |
recomp | +0.668 |
cape | +0.665 |
ropolitan | +0.665 |
Neg logit contributions | |
kson | -0.649 |
Wiz | -0.612 |
Wolf | -0.611 |
ATK | -0.587 |
pent | -0.544 |
Token | Evil |
Token ID | 10461 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
Wolf | +3.042 |
Wiz | +2.846 |
kson | +2.844 |
ATK | +2.577 |
pent | +2.211 |
Neg logit contributions | |
erg | -7.386 |
NL | -7.231 |
cape | -7.093 |
recomp | -7.003 |
ropolitan | -6.980 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
kson | +0.627 |
Wolf | +0.604 |
Wiz | +0.601 |
ATK | +0.577 |
pent | +0.534 |
Neg logit contributions | |
erg | -0.606 |
NL | -0.589 |
recomp | -0.569 |
ropolitan | -0.569 |
cape | -0.565 |
Token |
|
Token ID | 198 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
erg | +0.738 |
NL | +0.717 |
recomp | +0.691 |
cape | +0.687 |
ropolitan | +0.686 |
Neg logit contributions | |
kson | -0.864 |
Wiz | -0.821 |
Wolf | -0.818 |
ATK | -0.792 |
pent | -0.739 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
erg | +0.234 |
NL | +0.227 |
recomp | +0.219 |
ropolitan | +0.218 |
cape | +0.217 |
Neg logit contributions | |
kson | -0.273 |
Wolf | -0.261 |
Wiz | -0.261 |
ATK | -0.251 |
pent | -0.234 |
Token | Mis |
Token ID | 31281 |
Feature activation | +1.62e+01 |
Pos logit contributions | |
kson | +0.105 |
Wolf | +0.100 |
Wiz | +0.100 |
ATK | +0.096 |
pent | +0.090 |
Neg logit contributions | |
erg | -0.098 |
NL | -0.095 |
recomp | -0.093 |
ropolitan | -0.093 |
cape | -0.092 |
Token | ao |
Token ID | 5488 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
kson | +10.620 |
Wolf | +10.179 |
ATK | +9.700 |
Wiz | +9.545 |
pent | +9.361 |
Neg logit contributions | |
recomp | -8.801 |
Clarkson | -8.753 |
NL | -8.440 |
erg | -8.169 |
cape | -8.103 |
Token | Sen |
Token ID | 2311 |
Feature activation | +7.19e+00 |
Pos logit contributions | |
kson | +1.856 |
Wolf | +1.795 |
Wiz | +1.781 |
ATK | +1.698 |
pent | +1.558 |
Neg logit contributions | |
erg | -1.966 |
NL | -1.925 |
ropolitan | -1.860 |
recomp | -1.855 |
cape | -1.844 |
Token | b |
Token ID | 65 |
Feature activation | +6.70e+00 |
Pos logit contributions | |
kson | +4.826 |
Wolf | +4.669 |
Wiz | +4.617 |
ATK | +4.424 |
pent | +4.204 |
Neg logit contributions | |
NL | -4.629 |
erg | -4.596 |
recomp | -4.435 |
ropolitan | -4.413 |
Clarkson | -4.313 |
Token | ong |
Token ID | 506 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
kson | +4.651 |
Wolf | +4.447 |
ATK | +4.322 |
Wiz | +4.311 |
pent | +4.067 |
Neg logit contributions | |
NL | -4.072 |
erg | -4.013 |
cape | -3.990 |
recomp | -3.975 |
ropolitan | -3.916 |
Token | i |
Token ID | 72 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
kson | +4.326 |
Wolf | +4.235 |
Wiz | +4.171 |
ATK | +3.939 |
pent | +3.669 |
Neg logit contributions | |
erg | -4.275 |
NL | -4.243 |
recomp | -4.153 |
ropolitan | -4.147 |
cape | -4.094 |
Token | % |
Token ID | 4 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
kson | +1.010 |
Wolf | +0.970 |
Wiz | +0.968 |
ATK | +0.934 |
pent | +0.866 |
Neg logit contributions | |
erg | -0.910 |
NL | -0.880 |
recomp | -0.855 |
ropolitan | -0.851 |
cape | -0.851 |
Token | of |
Token ID | 286 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
kson | +0.028 |
Wolf | +0.027 |
Wiz | +0.027 |
ATK | +0.026 |
pent | +0.024 |
Neg logit contributions | |
erg | -0.029 |
NL | -0.028 |
recomp | -0.027 |
ropolitan | -0.027 |
cape | -0.027 |
Token | all |
Token ID | 477 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
kson | +1.616 |
Wolf | +1.572 |
Wiz | +1.571 |
ATK | +1.511 |
pent | +1.381 |
Neg logit contributions | |
erg | -1.732 |
NL | -1.679 |
cape | -1.632 |
ropolitan | -1.632 |
recomp | -1.619 |
Token | of |
Token ID | 286 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
kson | +1.966 |
Wolf | +1.925 |
Wiz | +1.924 |
ATK | +1.848 |
pent | +1.664 |
Neg logit contributions | |
erg | -2.310 |
NL | -2.240 |
cape | -2.193 |
ropolitan | -2.193 |
recomp | -2.162 |
Token | the |
Token ID | 262 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
kson | +0.303 |
Wolf | +0.291 |
Wiz | +0.291 |
ATK | +0.280 |
pent | +0.259 |
Neg logit contributions | |
erg | -0.292 |
NL | -0.283 |
ropolitan | -0.274 |
recomp | -0.274 |
cape | -0.273 |
Token | hard |
Token ID | 1327 |
Feature activation | +1.61e+01 |
Pos logit contributions | |
kson | +1.334 |
Wolf | +1.289 |
Wiz | +1.288 |
ATK | +1.236 |
pent | +1.132 |
Neg logit contributions | |
erg | -1.415 |
NL | -1.374 |
ropolitan | -1.336 |
cape | -1.333 |
recomp | -1.325 |
Token | fought |
Token ID | 8350 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
Wolf | +8.920 |
kson | +8.895 |
Wiz | +8.681 |
ATK | +8.672 |
stat | +8.208 |
Neg logit contributions | |
NL | -10.078 |
erg | -10.000 |
ropolitan | -9.861 |
Clarkson | -9.818 |
FORE | -9.739 |
Token | for |
Token ID | 329 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
kson | +3.040 |
Wolf | +3.035 |
Wiz | +3.014 |
ATK | +2.881 |
restriction | +2.619 |
Neg logit contributions | |
erg | -3.500 |
NL | -3.410 |
ropolitan | -3.355 |
zig | -3.292 |
cape | -3.289 |
Token | signatures |
Token ID | 17239 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
kson | +1.594 |
Wolf | +1.529 |
Wiz | +1.523 |
ATK | +1.460 |
pent | +1.345 |
Neg logit contributions | |
erg | -1.763 |
NL | -1.719 |
ropolitan | -1.670 |
recomp | -1.661 |
cape | -1.659 |
Token | will |
Token ID | 481 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
erg | +1.775 |
NL | +1.720 |
recomp | +1.670 |
cape | +1.662 |
ropolitan | +1.636 |
Neg logit contributions | |
kson | -1.938 |
Wiz | -1.830 |
Wolf | -1.810 |
ATK | -1.750 |
pent | -1.635 |
Token | be |
Token ID | 307 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
erg | +1.510 |
NL | +1.454 |
recomp | +1.416 |
cape | +1.396 |
ropolitan | +1.395 |
Neg logit contributions | |
kson | -1.841 |
Wiz | -1.754 |
Wolf | -1.748 |
ATK | -1.682 |
pent | -1.574 |
Token | Y |
Token ID | 56 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
erg | +3.227 |
NL | +3.195 |
recomp | +2.966 |
cape | +2.963 |
ropolitan | +2.932 |
Neg logit contributions | |
kson | -3.525 |
Wiz | -3.229 |
Wolf | -3.229 |
ATK | -3.116 |
pent | -2.925 |
Token | BE |
Token ID | 9348 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
NL | +3.504 |
erg | +3.501 |
cape | +3.256 |
ropolitan | +3.236 |
recomp | +3.234 |
Neg logit contributions | |
kson | -4.202 |
Wiz | -3.943 |
Wolf | -3.873 |
ATK | -3.750 |
pent | -3.551 |
Token | AR |
Token ID | 1503 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
kson | +0.369 |
Wolf | +0.352 |
Wiz | +0.352 |
ATK | +0.339 |
pent | +0.315 |
Neg logit contributions | |
erg | -0.342 |
NL | -0.333 |
recomp | -0.321 |
ropolitan | -0.320 |
cape | -0.319 |
Token | and |
Token ID | 290 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
erg | +1.727 |
NL | +1.689 |
recomp | +1.602 |
cape | +1.596 |
ropolitan | +1.593 |
Neg logit contributions | |
kson | -1.979 |
Wiz | -1.867 |
Wolf | -1.855 |
ATK | -1.792 |
pent | -1.682 |
Token | F |
Token ID | 376 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
kson | +0.021 |
Wolf | +0.020 |
Wiz | +0.020 |
ATK | +0.019 |
pent | +0.018 |
Neg logit contributions | |
erg | -0.019 |
NL | -0.019 |
recomp | -0.018 |
ropolitan | -0.018 |
cape | -0.018 |
Token | ANC |
Token ID | 20940 |
Feature activation | +1.61e+01 |
Pos logit contributions | |
kson | +1.531 |
Wolf | +1.463 |
Wiz | +1.462 |
ATK | +1.413 |
pent | +1.312 |
Neg logit contributions | |
erg | -1.333 |
NL | -1.292 |
recomp | -1.281 |
ropolitan | -1.275 |
cape | -1.274 |
Token | Y |
Token ID | 56 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
kson | +7.686 |
Wolf | +7.625 |
Wiz | +7.560 |
ATK | +7.267 |
pent | +6.122 |
Neg logit contributions | |
erg | -11.765 |
ropolitan | -11.739 |
llular | -11.497 |
recomp | -11.398 |
atures | -11.320 |
Token | BE |
Token ID | 9348 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
erg | +1.689 |
NL | +1.653 |
recomp | +1.587 |
cape | +1.578 |
ropolitan | +1.566 |
Neg logit contributions | |
kson | -1.674 |
Wiz | -1.573 |
Wolf | -1.555 |
ATK | -1.491 |
pent | -1.403 |
Token | AR |
Token ID | 1503 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
erg | +1.174 |
NL | +1.122 |
recomp | +1.030 |
cape | +1.019 |
ropolitan | +1.010 |
Neg logit contributions | |
kson | -2.789 |
Wiz | -2.686 |
Wolf | -2.676 |
ATK | -2.585 |
pent | -2.494 |
Token | for |
Token ID | 329 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
erg | +1.476 |
NL | +1.440 |
recomp | +1.371 |
cape | +1.360 |
ropolitan | +1.358 |
Neg logit contributions | |
kson | -1.821 |
Wiz | -1.731 |
Wolf | -1.722 |
ATK | -1.663 |
pent | -1.559 |
Token | the |
Token ID | 262 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
erg | +0.276 |
NL | +0.268 |
recomp | +0.260 |
ropolitan | +0.258 |
cape | +0.257 |
Neg logit contributions | |
kson | -0.288 |
Wiz | -0.273 |
Wolf | -0.273 |
ATK | -0.263 |
pent | -0.244 |
Token |
|
Token ID | 198 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
erg | +1.285 |
NL | +1.238 |
ropolitan | +1.189 |
recomp | +1.189 |
Clarkson | +1.181 |
Neg logit contributions | |
kson | -1.551 |
Wiz | -1.471 |
Wolf | -1.465 |
ATK | -1.420 |
pent | -1.336 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
erg | +0.396 |
NL | +0.384 |
recomp | +0.371 |
ropolitan | +0.369 |
cape | +0.368 |
Neg logit contributions | |
kson | -0.466 |
Wolf | -0.445 |
Wiz | -0.445 |
ATK | -0.429 |
pent | -0.400 |
Token | Jackson |
Token ID | 31270 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
erg | +1.184 |
NL | +1.156 |
cape | +1.099 |
recomp | +1.093 |
ropolitan | +1.091 |
Neg logit contributions | |
kson | -1.342 |
Wolf | -1.277 |
Wiz | -1.276 |
ATK | -1.234 |
pent | -1.139 |
Token | denied |
Token ID | 6699 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
kson | +0.597 |
Wolf | +0.570 |
Wiz | +0.567 |
ATK | +0.544 |
pent | +0.503 |
Neg logit contributions | |
erg | -0.597 |
NL | -0.582 |
ropolitan | -0.561 |
cape | -0.559 |
recomp | -0.558 |
Token | her |
Token ID | 607 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
kson | +2.263 |
Wolf | +2.210 |
Wiz | +2.180 |
ATK | +2.077 |
pent | +1.913 |
Neg logit contributions | |
erg | -2.414 |
NL | -2.383 |
ropolitan | -2.306 |
cape | -2.265 |
recomp | -2.240 |
Token | husband |
Token ID | 5229 |
Feature activation | +1.59e+01 |
Pos logit contributions | |
kson | +3.117 |
Wolf | +3.024 |
Wiz | +2.976 |
ATK | +2.902 |
pent | +2.690 |
Neg logit contributions | |
erg | -2.344 |
NL | -2.314 |
ropolitan | -2.210 |
cape | -2.183 |
recomp | -2.147 |
Token | 's |
Token ID | 338 |
Feature activation | +7.09e+00 |
Pos logit contributions | |
Wolf | +8.169 |
kson | +8.034 |
Wiz | +7.369 |
ATK | +6.981 |
pent | +6.660 |
Neg logit contributions | |
NL | -11.661 |
erg | -11.549 |
ropolitan | -11.417 |
cape | -11.051 |
llular | -10.989 |
Token | allegations |
Token ID | 7636 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
kson | +4.533 |
Wolf | +4.452 |
Wiz | +4.290 |
ATK | +4.178 |
pent | +3.789 |
Neg logit contributions | |
NL | -4.944 |
erg | -4.937 |
ropolitan | -4.746 |
cape | -4.663 |
llular | -4.587 |
Token | but |
Token ID | 475 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
kson | +0.496 |
Wolf | +0.475 |
Wiz | +0.474 |
ATK | +0.455 |
pent | +0.423 |
Neg logit contributions | |
erg | -0.460 |
NL | -0.447 |
ropolitan | -0.431 |
recomp | -0.431 |
cape | -0.428 |
Token | said |
Token ID | 531 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
erg | +0.758 |
NL | +0.736 |
recomp | +0.716 |
ropolitan | +0.710 |
cape | +0.709 |
Neg logit contributions | |
kson | -0.705 |
Wiz | -0.667 |
Wolf | -0.666 |
ATK | -0.642 |
pent | -0.594 |
Token | she |
Token ID | 673 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
erg | +0.525 |
NL | +0.508 |
recomp | +0.492 |
ropolitan | +0.487 |
cape | +0.487 |
Neg logit contributions | |
kson | -0.583 |
Wiz | -0.555 |
Wolf | -0.553 |
ATK | -0.534 |
pent | -0.498 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
kson | +0.957 |
Wolf | +0.921 |
Wiz | +0.915 |
ATK | +0.882 |
pent | +0.804 |
Neg logit contributions | |
erg | -1.059 |
NL | -1.023 |
ropolitan | -0.998 |
recomp | -0.994 |
cape | -0.987 |
Token | 76 |
Token ID | 4304 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
kson | +0.130 |
Wolf | +0.124 |
Wiz | +0.123 |
ATK | +0.119 |
pent | +0.109 |
Neg logit contributions | |
erg | -0.140 |
NL | -0.136 |
recomp | -0.132 |
ropolitan | -0.132 |
cape | -0.131 |
Token | 14 |
Token ID | 1478 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
kson | +2.665 |
Wolf | +2.575 |
Wiz | +2.535 |
ATK | +2.468 |
pent | +2.230 |
Neg logit contributions | |
erg | -3.037 |
NL | -2.910 |
ropolitan | -2.881 |
recomp | -2.864 |
cape | -2.842 |
Token | 05 |
Token ID | 2713 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
kson | +3.699 |
Wolf | +3.619 |
Wiz | +3.559 |
ATK | +3.468 |
pent | +3.083 |
Neg logit contributions | |
erg | -4.620 |
ropolitan | -4.493 |
recomp | -4.441 |
NL | -4.352 |
llular | -4.331 |
Token | ; |
Token ID | 26 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
kson | +3.113 |
Wolf | +3.021 |
Wiz | +2.978 |
ATK | +2.862 |
pent | +2.656 |
Neg logit contributions | |
erg | -3.477 |
NL | -3.409 |
ropolitan | -3.318 |
recomp | -3.296 |
cape | -3.282 |
Token | trek |
Token ID | 30784 |
Feature activation | +1.58e+01 |
Pos logit contributions | |
erg | +1.539 |
NL | +1.498 |
recomp | +1.464 |
ropolitan | +1.457 |
cape | +1.457 |
Neg logit contributions | |
kson | -1.013 |
Wolf | -0.949 |
Wiz | -0.946 |
ATK | -0.898 |
pent | -0.809 |
Token | amer |
Token ID | 2382 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
kson | +7.122 |
ATK | +6.214 |
Wolf | +5.886 |
pent | +5.877 |
Wiz | +5.812 |
Neg logit contributions | |
NL | -11.888 |
recomp | -11.842 |
Clarkson | -11.810 |
largeDownload | -11.471 |
llular | -11.425 |
Token | ica |
Token ID | 3970 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
kson | +2.619 |
Wiz | +2.508 |
Wolf | +2.496 |
ATK | +2.456 |
pent | +2.319 |
Neg logit contributions | |
erg | -1.281 |
NL | -1.259 |
recomp | -1.216 |
ropolitan | -1.173 |
cape | -1.172 |
Token | . |
Token ID | 13 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
erg | +0.216 |
NL | +0.209 |
recomp | +0.200 |
ropolitan | +0.200 |
cape | +0.199 |
Neg logit contributions | |
kson | -0.282 |
Wiz | -0.270 |
Wolf | -0.270 |
ATK | -0.260 |
pent | -0.243 |
Token | co |
Token ID | 1073 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
erg | +3.286 |
NL | +3.168 |
cape | +3.055 |
blogspot | +3.053 |
ropolitan | +3.000 |
Neg logit contributions | |
kson | -4.050 |
Wiz | -3.866 |
Wolf | -3.862 |
ATK | -3.719 |
pent | -3.405 |
Token | . |
Token ID | 13 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
erg | +0.580 |
NL | +0.560 |
recomp | +0.535 |
ropolitan | +0.534 |
cape | +0.533 |
Neg logit contributions | |
kson | -0.786 |
Wiz | -0.754 |
Wolf | -0.751 |
ATK | -0.725 |
pent | -0.679 |
Token | Cup |
Token ID | 5454 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
erg | +5.935 |
NL | +5.754 |
recomp | +5.576 |
Clarkson | +5.536 |
cape | +5.325 |
Neg logit contributions | |
kson | -9.294 |
Wiz | -8.704 |
ATK | -8.663 |
�� | -8.448 |
Wolf | -8.401 |
Token | and |
Token ID | 290 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
erg | +3.462 |
NL | +3.386 |
recomp | +3.220 |
cape | +3.210 |
Clarkson | +3.202 |
Neg logit contributions | |
kson | -4.430 |
Wiz | -4.202 |
Wolf | -4.103 |
ATK | -4.010 |
pent | -3.799 |
Token | obviously |
Token ID | 6189 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
erg | +0.063 |
NL | +0.062 |
recomp | +0.060 |
ropolitan | +0.059 |
cape | +0.059 |
Neg logit contributions | |
kson | -0.065 |
Wolf | -0.062 |
Wiz | -0.062 |
ATK | -0.059 |
pent | -0.055 |
Token | enjoying |
Token ID | 13226 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
kson | +0.485 |
Wolf | +0.469 |
Wiz | +0.468 |
ATK | +0.448 |
pent | +0.413 |
Neg logit contributions | |
erg | -0.475 |
NL | -0.461 |
ropolitan | -0.447 |
recomp | -0.444 |
cape | -0.442 |
Token | the |
Token ID | 262 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
kson | +0.046 |
Wolf | +0.044 |
Wiz | +0.044 |
ATK | +0.042 |
pent | +0.039 |
Neg logit contributions | |
erg | -0.043 |
NL | -0.041 |
recomp | -0.040 |
ropolitan | -0.040 |
cape | -0.040 |
Token | hard |
Token ID | 1327 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
kson | +2.230 |
Wiz | +2.187 |
Wolf | +2.182 |
ATK | +2.065 |
pent | +1.884 |
Neg logit contributions | |
erg | -2.168 |
NL | -2.103 |
ropolitan | -2.049 |
cape | -2.031 |
zig | -2.008 |
Token | work |
Token ID | 670 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
Wiz | +8.648 |
kson | +8.618 |
Wolf | +8.547 |
ATK | +7.732 |
stat | +7.345 |
Neg logit contributions | |
NL | -10.072 |
erg | -10.052 |
FORE | -9.906 |
llular | -9.856 |
ropolitan | -9.846 |
Token | and |
Token ID | 290 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
erg | +0.284 |
NL | +0.276 |
recomp | +0.267 |
ropolitan | +0.266 |
cape | +0.265 |
Neg logit contributions | |
kson | -0.289 |
Wolf | -0.275 |
Wiz | -0.275 |
ATK | -0.264 |
pent | -0.245 |
Token | success |
Token ID | 1943 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
kson | +1.488 |
Wolf | +1.445 |
Wiz | +1.439 |
ATK | +1.381 |
pent | +1.268 |
Neg logit contributions | |
erg | -1.469 |
NL | -1.435 |
ropolitan | -1.391 |
cape | -1.372 |
recomp | -1.363 |
Token | of |
Token ID | 286 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
erg | +0.645 |
NL | +0.628 |
recomp | +0.607 |
cape | +0.604 |
ropolitan | +0.602 |
Neg logit contributions | |
kson | -0.666 |
Wolf | -0.631 |
Wiz | -0.631 |
ATK | -0.608 |
pent | -0.565 |
Token | Marc |
Token ID | 13067 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
erg | +2.546 |
NL | +2.469 |
recomp | +2.392 |
Clarkson | +2.378 |
cape | +2.363 |
Neg logit contributions | |
kson | -2.803 |
Wolf | -2.600 |
Wiz | -2.599 |
ATK | -2.544 |
pent | -2.382 |
Token | here |
Token ID | 994 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
kson | +0.035 |
Wolf | +0.033 |
Wiz | +0.033 |
ATK | +0.032 |
pent | +0.030 |
Neg logit contributions | |
erg | -0.032 |
NL | -0.031 |
recomp | -0.030 |
ropolitan | -0.030 |
cape | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
kson | +2.513 |
Wolf | +2.446 |
Wiz | +2.393 |
ATK | +2.332 |
pent | +2.131 |
Neg logit contributions | |
erg | -2.265 |
NL | -2.216 |
recomp | -2.194 |
ropolitan | -2.168 |
cape | -2.148 |
Token | Sign |
Token ID | 5865 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
kson | +2.238 |
Wolf | +2.151 |
Wiz | +2.133 |
ATK | +2.053 |
pent | +1.811 |
Neg logit contributions | |
erg | -2.978 |
NL | -2.933 |
ropolitan | -2.893 |
recomp | -2.877 |
cape | -2.854 |
Token | up |
Token ID | 510 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
kson | +2.741 |
Wolf | +2.679 |
Wiz | +2.608 |
ATK | +2.532 |
pent | +2.303 |
Neg logit contributions | |
erg | -3.465 |
NL | -3.435 |
ropolitan | -3.383 |
cape | -3.324 |
recomp | -3.306 |
Token | for |
Token ID | 329 |
Feature activation | +9.25e+00 |
Pos logit contributions | |
kson | +0.093 |
Wolf | +0.089 |
Wiz | +0.089 |
ATK | +0.086 |
pent | +0.079 |
Neg logit contributions | |
erg | -0.087 |
NL | -0.085 |
recomp | -0.082 |
ropolitan | -0.081 |
cape | -0.081 |
Token | Take |
Token ID | 7214 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
Wolf | +4.721 |
kson | +4.671 |
Wiz | +4.638 |
ATK | +4.402 |
Expedition | +3.943 |
Neg logit contributions | |
erg | -7.240 |
NL | -7.229 |
ropolitan | -6.960 |
recomp | -6.960 |
cape | -6.885 |
Token | Action |
Token ID | 7561 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
Wolf | +3.197 |
Wiz | +3.070 |
ATK | +2.751 |
kson | +2.416 |
Expedition | +2.284 |
Neg logit contributions | |
etheless | -16.384 |
recomp | -16.292 |
cape | -15.857 |
ropolitan | -15.766 |
nexus | -15.709 |
Token | Now |
Token ID | 2735 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
kson | +2.472 |
Wolf | +2.421 |
Wiz | +2.380 |
ATK | +2.289 |
Expedition | +2.048 |
Neg logit contributions | |
erg | -2.495 |
recomp | -2.414 |
NL | -2.413 |
ropolitan | -2.387 |
cape | -2.359 |
Token | and |
Token ID | 290 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
kson | +0.485 |
Wolf | +0.464 |
Wiz | +0.461 |
ATK | +0.444 |
pent | +0.411 |
Neg logit contributions | |
erg | -0.487 |
NL | -0.473 |
recomp | -0.458 |
ropolitan | -0.457 |
cape | -0.455 |
Token | we |
Token ID | 356 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
kson | +2.509 |
Wolf | +2.463 |
Wiz | +2.442 |
ATK | +2.331 |
pent | +2.138 |
Neg logit contributions | |
erg | -2.526 |
NL | -2.477 |
ropolitan | -2.392 |
recomp | -2.370 |
cape | -2.365 |
Token | � |
Token ID | 447 |
Feature activation | +6.16e+00 |
Pos logit contributions | |
kson | +3.854 |
Wolf | +3.822 |
Wiz | +3.808 |
ATK | +3.555 |
pent | +3.199 |
Neg logit contributions | |
erg | -6.344 |
recomp | -6.238 |
NL | -6.205 |
ropolitan | -6.166 |
Clarkson | -6.153 |
Token | The |
Token ID | 464 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
erg | +0.254 |
NL | +0.247 |
recomp | +0.239 |
ropolitan | +0.238 |
cape | +0.238 |
Neg logit contributions | |
kson | -0.252 |
Wolf | -0.239 |
Wiz | -0.239 |
ATK | -0.230 |
pent | -0.213 |
Token | bill |
Token ID | 2855 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
erg | +0.327 |
NL | +0.318 |
recomp | +0.308 |
ropolitan | +0.306 |
cape | +0.306 |
Neg logit contributions | |
kson | -0.330 |
Wolf | -0.314 |
Wiz | -0.314 |
ATK | -0.302 |
pent | -0.280 |
Token | will |
Token ID | 481 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
erg | +1.121 |
NL | +1.095 |
recomp | +1.061 |
cape | +1.048 |
ropolitan | +1.046 |
Neg logit contributions | |
kson | -1.212 |
Wiz | -1.155 |
Wolf | -1.147 |
ATK | -1.108 |
pent | -1.036 |
Token | face |
Token ID | 1986 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
erg | +3.507 |
recomp | +3.421 |
NL | +3.418 |
cape | +3.275 |
ropolitan | +3.270 |
Neg logit contributions | |
kson | -4.576 |
Wiz | -4.265 |
Wolf | -4.217 |
ATK | -4.088 |
pent | -3.880 |
Token | an |
Token ID | 281 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
erg | +2.548 |
NL | +2.498 |
recomp | +2.429 |
Clarkson | +2.358 |
ropolitan | +2.358 |
Neg logit contributions | |
kson | -3.036 |
Wiz | -2.841 |
Wolf | -2.800 |
ATK | -2.753 |
pent | -2.578 |
Token | uphill |
Token ID | 35256 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
erg | +3.032 |
NL | +2.978 |
recomp | +2.830 |
ropolitan | +2.791 |
cape | +2.756 |
Neg logit contributions | |
kson | -4.284 |
Wiz | -4.022 |
Wolf | -4.000 |
ATK | -3.865 |
pent | -3.741 |
Token | battle |
Token ID | 3344 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
Wolf | +7.666 |
Wiz | +7.490 |
kson | +7.298 |
ATK | +7.121 |
restriction | +6.534 |
Neg logit contributions | |
ropolitan | -11.263 |
zig | -11.214 |
llular | -11.130 |
NL | -11.064 |
FORE | -10.852 |
Token | in |
Token ID | 287 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
erg | +0.417 |
NL | +0.405 |
recomp | +0.392 |
ropolitan | +0.390 |
cape | +0.389 |
Neg logit contributions | |
kson | -0.436 |
Wiz | -0.415 |
Wolf | -0.415 |
ATK | -0.399 |
pent | -0.370 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
erg | +3.039 |
NL | +2.953 |
recomp | +2.884 |
Clarkson | +2.808 |
ropolitan | +2.782 |
Neg logit contributions | |
kson | -3.648 |
Wiz | -3.425 |
Wolf | -3.371 |
ATK | -3.324 |
pent | -3.110 |
Token | Senate |
Token ID | 3845 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
kson | +0.698 |
Wolf | +0.668 |
Wiz | +0.667 |
ATK | +0.631 |
pent | +0.580 |
Neg logit contributions | |
erg | -0.894 |
NL | -0.870 |
ropolitan | -0.846 |
recomp | -0.844 |
cape | -0.843 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
erg | +0.226 |
NL | +0.219 |
recomp | +0.212 |
ropolitan | +0.211 |
cape | +0.210 |
Neg logit contributions | |
kson | -0.258 |
Wiz | -0.246 |
Wolf | -0.246 |
ATK | -0.237 |
pent | -0.221 |
Token | conclude |
Token ID | 13796 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
kson | +1.868 |
Wolf | +1.804 |
Wiz | +1.775 |
ATK | +1.722 |
pent | +1.578 |
Neg logit contributions | |
erg | -1.790 |
NL | -1.748 |
ropolitan | -1.655 |
cape | -1.651 |
zig | -1.637 |
Token | that |
Token ID | 326 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
erg | +0.611 |
NL | +0.594 |
recomp | +0.575 |
cape | +0.570 |
ropolitan | +0.570 |
Neg logit contributions | |
kson | -0.636 |
Wiz | -0.604 |
Wolf | -0.602 |
ATK | -0.581 |
pent | -0.541 |
Token | McDonnell |
Token ID | 39441 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
kson | +0.507 |
Wolf | +0.486 |
Wiz | +0.485 |
ATK | +0.466 |
pent | +0.435 |
Neg logit contributions | |
erg | -0.426 |
NL | -0.413 |
recomp | -0.397 |
ropolitan | -0.397 |
cape | -0.396 |
Token | faces |
Token ID | 6698 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
kson | +0.240 |
Wolf | +0.230 |
Wiz | +0.229 |
ATK | +0.219 |
pent | +0.204 |
Neg logit contributions | |
erg | -0.240 |
NL | -0.234 |
recomp | -0.225 |
ropolitan | -0.225 |
cape | -0.225 |
Token | an |
Token ID | 281 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
erg | +1.708 |
NL | +1.655 |
recomp | +1.624 |
ropolitan | +1.589 |
cape | +1.584 |
Neg logit contributions | |
kson | -1.999 |
Wiz | -1.892 |
Wolf | -1.878 |
ATK | -1.830 |
pent | -1.702 |
Token | uphill |
Token ID | 35256 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
erg | +2.428 |
NL | +2.356 |
recomp | +2.302 |
cape | +2.241 |
ropolitan | +2.236 |
Neg logit contributions | |
kson | -2.774 |
Wiz | -2.619 |
Wolf | -2.603 |
ATK | -2.517 |
pent | -2.397 |
Token | battle |
Token ID | 3344 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Wolf | +7.797 |
Wiz | +7.493 |
kson | +7.384 |
ATK | +7.055 |
restriction | +6.776 |
Neg logit contributions | |
ropolitan | -11.150 |
zig | -11.110 |
NL | -11.077 |
llular | -10.776 |
FORE | -10.766 |
Token | . |
Token ID | 13 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
kson | +1.568 |
Wolf | +1.517 |
Wiz | +1.498 |
ATK | +1.443 |
pent | +1.329 |
Neg logit contributions | |
erg | -1.634 |
NL | -1.592 |
ropolitan | -1.537 |
recomp | -1.514 |
cape | -1.513 |
Token | The |
Token ID | 383 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
erg | +0.547 |
NL | +0.531 |
recomp | +0.510 |
ropolitan | +0.508 |
cape | +0.508 |
Neg logit contributions | |
kson | -0.646 |
Wiz | -0.614 |
Wolf | -0.613 |
ATK | -0.592 |
pent | -0.556 |
Token | judges |
Token ID | 10266 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
erg | +0.327 |
NL | +0.317 |
recomp | +0.306 |
ropolitan | +0.304 |
cape | +0.303 |
Neg logit contributions | |
kson | -0.394 |
Wolf | -0.376 |
Wiz | -0.376 |
ATK | -0.363 |
pent | -0.339 |
Token | in |
Token ID | 287 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
kson | +0.033 |
Wolf | +0.031 |
Wiz | +0.031 |
ATK | +0.030 |
pent | +0.028 |
Neg logit contributions | |
erg | -0.032 |
NL | -0.031 |
recomp | -0.030 |
ropolitan | -0.030 |
cape | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
kson | +0.798 |
Wolf | +0.768 |
Wiz | +0.764 |
ATK | +0.735 |
pent | +0.681 |
Neg logit contributions | |
erg | -0.718 |
NL | -0.695 |
recomp | -0.678 |
ropolitan | -0.672 |
cape | -0.669 |
Token |
|
Token ID | 198 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
kson | +0.345 |
Wolf | +0.331 |
Wiz | +0.329 |
ATK | +0.318 |
pent | +0.295 |
Neg logit contributions | |
erg | -0.310 |
NL | -0.300 |
recomp | -0.293 |
ropolitan | -0.292 |
cape | -0.289 |
Token | According |
Token ID | 4821 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
erg | +0.484 |
NL | +0.470 |
recomp | +0.452 |
ropolitan | +0.451 |
cape | +0.450 |
Neg logit contributions | |
kson | -0.556 |
Wolf | -0.530 |
Wiz | -0.530 |
ATK | -0.510 |
pent | -0.475 |
Token | to |
Token ID | 284 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
erg | +0.900 |
NL | +0.875 |
recomp | +0.843 |
ropolitan | +0.838 |
cape | +0.837 |
Neg logit contributions | |
kson | -0.964 |
Wiz | -0.915 |
Wolf | -0.909 |
ATK | -0.877 |
pent | -0.822 |
Token | Nick |
Token ID | 8047 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
erg | +2.601 |
NL | +2.527 |
recomp | +2.456 |
Clarkson | +2.434 |
cape | +2.421 |
Neg logit contributions | |
kson | -3.127 |
Wiz | -2.950 |
Wolf | -2.904 |
ATK | -2.855 |
pent | -2.670 |
Token | Sur |
Token ID | 4198 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
erg | +1.690 |
NL | +1.623 |
ropolitan | +1.574 |
cape | +1.573 |
recomp | +1.568 |
Neg logit contributions | |
kson | -1.647 |
Wiz | -1.547 |
Wolf | -1.542 |
ATK | -1.511 |
pent | -1.404 |
Token | gey |
Token ID | 39608 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
kson | +10.020 |
Wolf | +9.519 |
Wiz | +9.321 |
ATK | +9.192 |
pent | +8.933 |
Neg logit contributions | |
recomp | -8.459 |
NL | -8.417 |
erg | -8.362 |
Clarkson | -8.218 |
largeDownload | -8.040 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
kson | +0.117 |
Wolf | +0.111 |
Wiz | +0.111 |
ATK | +0.107 |
pent | +0.099 |
Neg logit contributions | |
erg | -0.105 |
NL | -0.102 |
recomp | -0.098 |
ropolitan | -0.098 |
cape | -0.098 |
Token | C |
Token ID | 327 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
erg | +1.022 |
NL | +0.994 |
recomp | +0.958 |
cape | +0.954 |
ropolitan | +0.948 |
Neg logit contributions | |
kson | -1.117 |
Wiz | -1.060 |
Wolf | -1.054 |
ATK | -1.020 |
pent | -0.950 |
Token | MD |
Token ID | 12740 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
kson | +2.513 |
Wolf | +2.419 |
Wiz | +2.398 |
ATK | +2.335 |
pent | +2.209 |
Neg logit contributions | |
erg | -1.530 |
recomp | -1.489 |
NL | -1.454 |
Clarkson | -1.450 |
cape | -1.438 |
Token | � |
Token ID | 447 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
erg | +0.784 |
NL | +0.764 |
recomp | +0.735 |
ropolitan | +0.732 |
cape | +0.731 |
Neg logit contributions | |
kson | -0.866 |
Wiz | -0.821 |
Wolf | -0.817 |
ATK | -0.790 |
pent | -0.735 |
Token | engine |
Token ID | 3113 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
kson | +2.960 |
Wolf | +2.894 |
Wiz | +2.848 |
ATK | +2.761 |
restriction | +2.503 |
Neg logit contributions | |
erg | -2.971 |
NL | -2.901 |
ropolitan | -2.887 |
llular | -2.780 |
cape | -2.780 |
Token | about |
Token ID | 546 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
kson | +2.266 |
Wolf | +2.182 |
Wiz | +2.161 |
ATK | +2.100 |
pent | +1.936 |
Neg logit contributions | |
erg | -2.072 |
NL | -2.005 |
ropolitan | -1.978 |
cape | -1.933 |
zig | -1.905 |
Token | 16 |
Token ID | 1467 |
Feature activation | -3.35e-03 |
Pos logit contributions | |
kson | +1.856 |
Wolf | +1.797 |
Wiz | +1.781 |
ATK | +1.719 |
pent | +1.568 |
Neg logit contributions | |
erg | -1.963 |
NL | -1.912 |
ropolitan | -1.876 |
cape | -1.828 |
recomp | -1.818 |
Token | hours |
Token ID | 2250 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
erg | +0.002 |
NL | +0.002 |
recomp | +0.002 |
ropolitan | +0.002 |
cape | +0.002 |
Neg logit contributions | |
kson | -0.002 |
Wiz | -0.002 |
Wolf | -0.002 |
ATK | -0.002 |
pent | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
erg | +1.797 |
NL | +1.758 |
recomp | +1.707 |
cape | +1.693 |
Clarkson | +1.659 |
Neg logit contributions | |
kson | -2.225 |
Wiz | -2.128 |
Wolf | -2.103 |
ATK | -2.017 |
pent | -1.910 |
Token | 41 |
Token ID | 6073 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
erg | +0.328 |
NL | +0.318 |
recomp | +0.308 |
ropolitan | +0.306 |
cape | +0.306 |
Neg logit contributions | |
kson | -0.342 |
Wolf | -0.325 |
Wiz | -0.325 |
ATK | -0.313 |
pent | -0.290 |
Token | minutes |
Token ID | 2431 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
Wolf | +5.181 |
kson | +5.146 |
Wiz | +4.859 |
ATK | +4.703 |
Expedition | +4.022 |
Neg logit contributions | |
erg | -13.474 |
ropolitan | -13.055 |
zig | -13.001 |
cape | -12.742 |
NL | -12.717 |
Token | after |
Token ID | 706 |
Feature activation | +9.39e+00 |
Pos logit contributions | |
kson | +2.394 |
Wolf | +2.303 |
Wiz | +2.273 |
ATK | +2.222 |
pent | +2.022 |
Neg logit contributions | |
erg | -2.588 |
NL | -2.485 |
ropolitan | -2.452 |
zig | -2.386 |
recomp | -2.384 |
Token | launch |
Token ID | 4219 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
kson | +5.593 |
Wolf | +5.522 |
Wiz | +5.411 |
ATK | +5.301 |
Expedition | +4.761 |
Neg logit contributions | |
erg | -6.703 |
ropolitan | -6.639 |
NL | -6.491 |
blogspot | -6.296 |
llular | -6.277 |
Token | . |
Token ID | 13 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
kson | +2.965 |
Wolf | +2.864 |
Wiz | +2.815 |
ATK | +2.741 |
pent | +2.540 |
Neg logit contributions | |
erg | -2.689 |
NL | -2.606 |
ropolitan | -2.569 |
cape | -2.490 |
recomp | -2.473 |
Token | This |
Token ID | 770 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
kson | +1.455 |
Wolf | +1.395 |
Wiz | +1.384 |
ATK | +1.342 |
pent | +1.226 |
Neg logit contributions | |
erg | -1.414 |
NL | -1.369 |
ropolitan | -1.335 |
recomp | -1.331 |
cape | -1.317 |
Token | path |
Token ID | 3108 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
kson | +4.552 |
Wolf | +4.545 |
Wiz | +4.294 |
ATK | +4.280 |
restriction | +3.877 |
Neg logit contributions | |
erg | -5.723 |
NL | -5.541 |
ropolitan | -5.490 |
cape | -5.401 |
llular | -5.323 |
Token | , |
Token ID | 837 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
kson | +1.510 |
Wolf | +1.449 |
Wiz | +1.440 |
ATK | +1.401 |
pent | +1.313 |
Neg logit contributions | |
erg | -1.124 |
NL | -1.083 |
recomp | -1.045 |
ropolitan | -1.043 |
cape | -1.038 |
Token | 5 |
Token ID | 642 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
kson | +2.487 |
Wolf | +2.431 |
Wiz | +2.369 |
ATK | +2.312 |
pent | +2.106 |
Neg logit contributions | |
erg | -2.870 |
NL | -2.781 |
ropolitan | -2.734 |
cape | -2.719 |
recomp | -2.666 |
Token | ) |
Token ID | 1267 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
erg | +1.084 |
NL | +1.055 |
recomp | +0.994 |
ropolitan | +0.985 |
cape | +0.984 |
Neg logit contributions | |
kson | -1.998 |
Wiz | -1.929 |
Wolf | -1.914 |
ATK | -1.848 |
pent | -1.752 |
Token | = |
Token ID | 796 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
erg | +1.158 |
NL | +1.127 |
recomp | +1.080 |
cape | +1.062 |
ropolitan | +1.057 |
Neg logit contributions | |
kson | -1.677 |
Wiz | -1.606 |
Wolf | -1.594 |
ATK | -1.535 |
pent | -1.450 |
Token | '. |
Token ID | 45302 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
kson | +3.713 |
Wolf | +3.633 |
Wiz | +3.596 |
ATK | +3.516 |
pent | +3.343 |
Neg logit contributions | |
erg | -1.343 |
NL | -1.264 |
ropolitan | -1.183 |
cape | -1.168 |
recomp | -1.148 |
Token | cl |
Token ID | 565 |
Feature activation | +9.47e+00 |
Pos logit contributions | |
kson | +8.033 |
Wolf | +7.323 |
Wiz | +7.047 |
pent | +6.996 |
ATK | +6.909 |
Neg logit contributions | |
NL | -10.165 |
erg | -9.881 |
ropolitan | -9.820 |
Clarkson | -9.655 |
recomp | -9.482 |
Token | jc |
Token ID | 48055 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
kson | +6.427 |
Wolf | +5.974 |
Wiz | +5.935 |
ATK | +5.726 |
pent | +5.599 |
Neg logit contributions | |
NL | -5.923 |
erg | -5.642 |
ropolitan | -5.619 |
Clarkson | -5.425 |
cape | -5.372 |
Token | ' |
Token ID | 6 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
kson | +0.671 |
Wolf | +0.638 |
Wiz | +0.636 |
ATK | +0.611 |
pent | +0.567 |
Neg logit contributions | |
erg | -0.701 |
NL | -0.682 |
recomp | -0.660 |
ropolitan | -0.659 |
cape | -0.657 |
Token | OR |
Token ID | 6375 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Wolf | +4.561 |
kson | +4.551 |
ATK | +4.414 |
Wiz | +4.348 |
stat | +3.863 |
Neg logit contributions | |
erg | -5.021 |
NL | -4.854 |
cape | -4.775 |
ropolitan | -4.775 |
zig | -4.756 |
Token | RIGHT |
Token ID | 33621 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
kson | +0.306 |
Wolf | +0.292 |
Wiz | +0.289 |
ATK | +0.278 |
pent | +0.253 |
Neg logit contributions | |
erg | -0.381 |
NL | -0.370 |
ropolitan | -0.360 |
cape | -0.359 |
recomp | -0.358 |
Token | . |
Token ID | 13 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
erg | +0.011 |
NL | +0.011 |
recomp | +0.010 |
cape | +0.010 |
ropolitan | +0.010 |
Neg logit contributions | |
kson | -0.013 |
Wiz | -0.012 |
Wolf | -0.012 |
ATK | -0.012 |
pent | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
kson | +3.027 |
Wolf | +2.960 |
Wiz | +2.932 |
ATK | +2.830 |
pent | +2.586 |
Neg logit contributions | |
erg | -2.998 |
NL | -2.902 |
recomp | -2.880 |
ropolitan | -2.848 |
cape | -2.813 |
Token |
|
Token ID | 198 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
kson | +1.174 |
Wolf | +1.131 |
Wiz | +1.118 |
ATK | +1.084 |
pent | +0.998 |
Neg logit contributions | |
erg | -1.141 |
NL | -1.102 |
recomp | -1.089 |
ropolitan | -1.086 |
cape | -1.068 |
Token | For |
Token ID | 1890 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
kson | +2.342 |
Wolf | +2.251 |
Wiz | +2.236 |
ATK | +2.160 |
pent | +2.061 |
Neg logit contributions | |
erg | -2.231 |
recomp | -2.161 |
ropolitan | -2.155 |
NL | -2.124 |
cape | -2.082 |
Token | ged |
Token ID | 2004 |
Feature activation | +7.24e+00 |
Pos logit contributions | |
kson | +1.522 |
Wolf | +1.459 |
Wiz | +1.449 |
ATK | +1.396 |
pent | +1.298 |
Neg logit contributions | |
erg | -1.502 |
NL | -1.468 |
ropolitan | -1.418 |
cape | -1.411 |
recomp | -1.407 |
Token | from |
Token ID | 422 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
kson | +4.409 |
Wolf | +4.381 |
Wiz | +4.239 |
ATK | +4.113 |
pent | +3.779 |
Neg logit contributions | |
erg | -5.049 |
NL | -4.993 |
ropolitan | -4.880 |
blogspot | -4.842 |
recomp | -4.814 |
Token | high |
Token ID | 1029 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
Wolf | +9.143 |
ATK | +8.701 |
kson | +8.691 |
Wiz | +8.535 |
Expedition | +7.755 |
Neg logit contributions | |
NL | -9.565 |
erg | -9.429 |
ropolitan | -9.316 |
blogspot | -9.205 |
cape | -9.091 |
Token | - |
Token ID | 12 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
kson | +0.702 |
Wolf | +0.673 |
Wiz | +0.668 |
ATK | +0.647 |
pent | +0.602 |
Neg logit contributions | |
erg | -0.628 |
NL | -0.610 |
recomp | -0.587 |
ropolitan | -0.585 |
cape | -0.584 |
Token | strength |
Token ID | 41402 |
Feature activation | +8.69e+00 |
Pos logit contributions | |
kson | +0.713 |
Wolf | +0.685 |
Wiz | +0.676 |
ATK | +0.658 |
pent | +0.616 |
Neg logit contributions | |
erg | -0.734 |
NL | -0.714 |
recomp | -0.699 |
ropolitan | -0.692 |
cape | -0.687 |
Token | , |
Token ID | 11 |
Feature activation | +9.64e+00 |
Pos logit contributions | |
Wolf | +5.613 |
kson | +5.536 |
Wiz | +5.388 |
ATK | +5.208 |
Expedition | +4.761 |
Neg logit contributions | |
erg | -5.788 |
NL | -5.740 |
ropolitan | -5.650 |
blogspot | -5.552 |
cape | -5.529 |
Token | military |
Token ID | 2422 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
Wolf | +6.129 |
kson | +6.083 |
Wiz | +5.911 |
ATK | +5.806 |
pent | +5.262 |
Neg logit contributions | |
erg | -6.280 |
NL | -6.240 |
ropolitan | -6.193 |
cape | -6.116 |
blogspot | -6.037 |
Token | ler |
Token ID | 1754 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
kson | +0.071 |
Wolf | +0.068 |
Wiz | +0.068 |
ATK | +0.066 |
pent | +0.062 |
Neg logit contributions | |
erg | -0.053 |
NL | -0.052 |
recomp | -0.050 |
ropolitan | -0.049 |
cape | -0.049 |
Token | named |
Token ID | 3706 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
kson | +1.718 |
Wolf | +1.662 |
Wiz | +1.643 |
ATK | +1.575 |
pent | +1.447 |
Neg logit contributions | |
erg | -1.761 |
NL | -1.726 |
ropolitan | -1.673 |
cape | -1.648 |
recomp | -1.633 |
Token | H |
Token ID | 367 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
kson | +0.869 |
Wolf | +0.837 |
Wiz | +0.835 |
ATK | +0.795 |
pent | +0.733 |
Neg logit contributions | |
erg | -0.830 |
NL | -0.808 |
recomp | -0.781 |
ropolitan | -0.779 |
cape | -0.777 |
Token | id |
Token ID | 312 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
kson | +1.433 |
Wolf | +1.370 |
Wiz | +1.358 |
ATK | +1.307 |
pent | +1.227 |
Neg logit contributions | |
erg | -1.240 |
NL | -1.217 |
recomp | -1.187 |
ropolitan | -1.184 |
cape | -1.178 |
Token | ir |
Token ID | 343 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
kson | +3.341 |
Wolf | +3.202 |
Wiz | +3.175 |
ATK | +3.062 |
pent | +2.832 |
Neg logit contributions | |
erg | -2.874 |
NL | -2.860 |
recomp | -2.780 |
ropolitan | -2.714 |
cape | -2.710 |
Token | Fil |
Token ID | 7066 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
kson | +1.870 |
Wolf | +1.802 |
Wiz | +1.796 |
ATK | +1.700 |
pent | +1.577 |
Neg logit contributions | |
erg | -1.802 |
NL | -1.761 |
recomp | -1.703 |
ropolitan | -1.699 |
cape | -1.690 |
Token | iz |
Token ID | 528 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
kson | +10.422 |
Wolf | +9.702 |
Wiz | +9.523 |
pent | +9.228 |
ATK | +9.146 |
Neg logit contributions | |
NL | -7.894 |
recomp | -7.799 |
Clarkson | -7.632 |
largeDownload | -7.568 |
ropolitan | -7.530 |
Token | told |
Token ID | 1297 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
kson | +2.704 |
Wiz | +2.613 |
Wolf | +2.594 |
ATK | +2.447 |
pent | +2.313 |
Neg logit contributions | |
erg | -2.509 |
NL | -2.495 |
recomp | -2.399 |
ropolitan | -2.397 |
Clarkson | -2.373 |
Token | the |
Token ID | 262 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
kson | +1.380 |
Wolf | +1.343 |
Wiz | +1.339 |
ATK | +1.274 |
pent | +1.170 |
Neg logit contributions | |
erg | -1.339 |
NL | -1.296 |
recomp | -1.257 |
cape | -1.252 |
ropolitan | -1.250 |
Token | Political |
Token ID | 14611 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
kson | +2.251 |
Wolf | +2.219 |
Wiz | +2.218 |
ATK | +2.091 |
pent | +1.923 |
Neg logit contributions | |
erg | -2.268 |
NL | -2.184 |
ropolitan | -2.102 |
cape | -2.095 |
recomp | -2.090 |
Token | Police |
Token ID | 4287 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
Wiz | +4.124 |
Wolf | +4.122 |
kson | +4.046 |
ATK | +3.828 |
pent | +3.566 |
Neg logit contributions | |
erg | -4.219 |
NL | -4.078 |
ropolitan | -4.002 |
recomp | -3.939 |
zig | -3.891 |
Token | RAM |
Token ID | 24115 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
kson | +2.465 |
Wolf | +2.394 |
Wiz | +2.383 |
ATK | +2.270 |
pent | +2.146 |
Neg logit contributions | |
erg | -2.265 |
recomp | -2.202 |
ropolitan | -2.166 |
NL | -2.154 |
cape | -2.118 |
Token | ONE |
Token ID | 11651 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
kson | +0.027 |
Wolf | +0.026 |
Wiz | +0.026 |
ATK | +0.025 |
pent | +0.024 |
Neg logit contributions | |
erg | -0.018 |
NL | -0.018 |
recomp | -0.017 |
ropolitan | -0.017 |
cape | -0.017 |
Token | - |
Token ID | 12 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
kson | +2.246 |
Wolf | +2.166 |
Wiz | +2.152 |
ATK | +2.061 |
pent | +1.898 |
Neg logit contributions | |
erg | -2.355 |
NL | -2.297 |
recomp | -2.237 |
ropolitan | -2.223 |
cape | -2.217 |
Token | Th |
Token ID | 817 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
kson | +3.340 |
Wolf | +3.244 |
Wiz | +3.230 |
ATK | +3.060 |
pent | +2.921 |
Neg logit contributions | |
erg | -3.086 |
recomp | -3.037 |
ropolitan | -2.974 |
NL | -2.924 |
cape | -2.903 |
Token | an |
Token ID | 272 |
Feature activation | +8.19e+00 |
Pos logit contributions | |
kson | +3.572 |
Wolf | +3.370 |
Wiz | +3.356 |
ATK | +3.201 |
pent | +3.080 |
Neg logit contributions | |
erg | -2.868 |
recomp | -2.849 |
NL | -2.839 |
cape | -2.804 |
ropolitan | -2.734 |
Token | E |
Token ID | 412 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
kson | +5.345 |
Wolf | +5.242 |
Wiz | +5.082 |
ATK | +4.898 |
pent | +4.499 |
Neg logit contributions | |
NL | -5.354 |
recomp | -5.353 |
erg | -5.331 |
cape | -5.166 |
ropolitan | -5.102 |
Token | rock |
Token ID | 10823 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
kson | +10.430 |
Wolf | +10.167 |
Wiz | +9.711 |
pent | +9.354 |
ATK | +9.163 |
Neg logit contributions | |
recomp | -7.968 |
NL | -7.854 |
erg | -7.820 |
ropolitan | -7.802 |
cape | -7.586 |
Token | & |
Token ID | 1222 |
Feature activation | +6.94e+00 |
Pos logit contributions | |
kson | +2.658 |
Wolf | +2.547 |
Wiz | +2.532 |
ATK | +2.404 |
pent | +2.238 |
Neg logit contributions | |
erg | -2.653 |
NL | -2.618 |
recomp | -2.548 |
ropolitan | -2.522 |
cape | -2.493 |
Token | Danny |
Token ID | 15105 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Wolf | +4.494 |
kson | +4.490 |
Wiz | +4.434 |
ATK | +4.168 |
Expedition | +3.751 |
Neg logit contributions | |
erg | -4.653 |
recomp | -4.594 |
NL | -4.565 |
cape | -4.518 |
ropolitan | -4.488 |
Token | Fight |
Token ID | 10480 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
kson | +0.290 |
Wolf | +0.276 |
Wiz | +0.276 |
ATK | +0.265 |
pent | +0.246 |
Neg logit contributions | |
erg | -0.286 |
NL | -0.278 |
recomp | -0.268 |
ropolitan | -0.267 |
cape | -0.267 |
Token | With |
Token ID | 2080 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
kson | +3.573 |
Wolf | +3.469 |
Wiz | +3.435 |
ATK | +3.226 |
pent | +3.028 |
Neg logit contributions | |
NL | -3.706 |
erg | -3.688 |
recomp | -3.607 |
ropolitan | -3.537 |
cape | -3.510 |
Token | for |
Token ID | 329 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
kson | +0.009 |
Wolf | +0.008 |
Wiz | +0.008 |
ATK | +0.008 |
pent | +0.008 |
Neg logit contributions | |
erg | -0.008 |
NL | -0.008 |
recomp | -0.007 |
ropolitan | -0.007 |
cape | -0.007 |
Token | Harmon |
Token ID | 39712 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
erg | +2.131 |
NL | +2.078 |
recomp | +2.032 |
Clarkson | +1.999 |
cape | +1.979 |
Neg logit contributions | |
kson | -2.474 |
Wiz | -2.334 |
Wolf | -2.309 |
ATK | -2.245 |
pent | -2.119 |
Token | � |
Token ID | 447 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
kson | +1.798 |
Wolf | +1.725 |
Wiz | +1.692 |
ATK | +1.635 |
pent | +1.520 |
Neg logit contributions | |
erg | -1.663 |
NL | -1.618 |
ropolitan | -1.566 |
recomp | -1.565 |
cape | -1.561 |
Token | � |
Token ID | 247 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
kson | +1.766 |
Wiz | +1.682 |
Wolf | +1.675 |
ATK | +1.598 |
pent | +1.480 |
Neg logit contributions | |
erg | -1.602 |
NL | -1.570 |
cape | -1.537 |
recomp | -1.532 |
ropolitan | -1.520 |
Token | s |
Token ID | 82 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
kson | +0.720 |
Wolf | +0.687 |
Wiz | +0.683 |
ATK | +0.658 |
pent | +0.612 |
Neg logit contributions | |
erg | -0.666 |
NL | -0.647 |
recomp | -0.627 |
ropolitan | -0.624 |
cape | -0.622 |
Token | Re |
Token ID | 797 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
erg | +2.949 |
NL | +2.883 |
recomp | +2.825 |
Clarkson | +2.774 |
ropolitan | +2.743 |
Neg logit contributions | |
kson | -2.975 |
Wiz | -2.804 |
Wolf | -2.736 |
ATK | -2.695 |
pent | -2.539 |
Token | ception |
Token ID | 4516 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
kson | +9.253 |
Wolf | +8.693 |
Wiz | +8.221 |
ATK | +7.871 |
pent | +7.746 |
Neg logit contributions | |
Clarkson | -8.885 |
recomp | -8.780 |
ropolitan | -8.723 |
erg | -8.640 |
llular | -8.547 |
Token | Perception |
Token ID | 35802 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
erg | +1.428 |
NL | +1.389 |
recomp | +1.343 |
ropolitan | +1.333 |
cape | +1.330 |
Neg logit contributions | |
kson | -1.428 |
Wiz | -1.349 |
Wolf | -1.345 |
ATK | -1.294 |
pent | -1.206 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
erg | +4.108 |
NL | +3.982 |
recomp | +3.860 |
Clarkson | +3.850 |
ropolitan | +3.828 |
Neg logit contributions | |
kson | -4.336 |
Wiz | -4.019 |
Wolf | -3.937 |
ATK | -3.848 |
pent | -3.697 |
Token |
|
Token ID | 198 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
erg | +0.726 |
NL | +0.706 |
recomp | +0.678 |
cape | +0.675 |
ropolitan | +0.674 |
Neg logit contributions | |
kson | -0.858 |
Wiz | -0.813 |
Wolf | -0.812 |
ATK | -0.785 |
pent | -0.739 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
kson | +1.665 |
Wolf | +1.605 |
Wiz | +1.582 |
ATK | +1.536 |
pent | +1.411 |
Neg logit contributions | |
erg | -1.673 |
NL | -1.616 |
recomp | -1.603 |
ropolitan | -1.599 |
cape | -1.568 |
Token | � |
Token ID | 447 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
kson | +0.246 |
Wolf | +0.235 |
Wiz | +0.234 |
ATK | +0.225 |
pent | +0.209 |
Neg logit contributions | |
erg | -0.236 |
NL | -0.230 |
ropolitan | -0.221 |
recomp | -0.221 |
cape | -0.220 |
Token | � |
Token ID | 247 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
erg | +0.588 |
NL | +0.569 |
recomp | +0.550 |
ropolitan | +0.547 |
cape | +0.545 |
Neg logit contributions | |
kson | -0.624 |
Wolf | -0.594 |
Wiz | -0.593 |
ATK | -0.572 |
pent | -0.532 |
Token | s |
Token ID | 82 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
kson | +0.567 |
Wolf | +0.539 |
Wiz | +0.538 |
ATK | +0.519 |
pent | +0.484 |
Neg logit contributions | |
erg | -0.529 |
NL | -0.516 |
recomp | -0.499 |
ropolitan | -0.496 |
cape | -0.494 |
Token | curb |
Token ID | 20799 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
erg | +1.751 |
NL | +1.687 |
recomp | +1.648 |
cape | +1.638 |
ropolitan | +1.633 |
Neg logit contributions | |
kson | -1.848 |
Wiz | -1.762 |
Wolf | -1.756 |
ATK | -1.687 |
pent | -1.569 |
Token | , |
Token ID | 11 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
kson | +2.736 |
Wolf | +2.653 |
Wiz | +2.634 |
ATK | +2.541 |
pent | +2.364 |
Neg logit contributions | |
erg | -2.750 |
NL | -2.744 |
ropolitan | -2.648 |
recomp | -2.615 |
llular | -2.582 |
Token | g |
Token ID | 308 |
Feature activation | -1.84e+01 |
Pos logit contributions | |
erg | +2.994 |
NL | +2.878 |
cape | +2.816 |
recomp | +2.814 |
Clarkson | +2.765 |
Neg logit contributions | |
kson | -3.064 |
Wolf | -2.895 |
Wiz | -2.894 |
ATK | -2.801 |
pent | -2.590 |
Token | utter |
Token ID | 10381 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
erg | +9.933 |
ropolitan | +8.095 |
atorial | +8.095 |
cape | +7.877 |
mir | +7.853 |
Neg logit contributions | |
�� | -12.968 |
kson | -12.758 |
ATK | -12.649 |
Medals | -12.611 |
Wolf | -12.503 |
Token | , |
Token ID | 11 |
Feature activation | -7.91e+00 |
Pos logit contributions | |
kson | +0.381 |
Wolf | +0.365 |
Wiz | +0.364 |
ATK | +0.350 |
pent | +0.326 |
Neg logit contributions | |
erg | -0.353 |
NL | -0.343 |
recomp | -0.331 |
ropolitan | -0.330 |
cape | -0.327 |
Token | and |
Token ID | 290 |
Feature activation | -8.37e+00 |
Pos logit contributions | |
erg | +4.760 |
cape | +4.549 |
NL | +4.546 |
recomp | +4.509 |
Clarkson | +4.438 |
Neg logit contributions | |
kson | -5.603 |
Wiz | -5.321 |
Wolf | -5.285 |
ATK | -5.226 |
�� | -4.890 |
Token | sidewalk |
Token ID | 24058 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
erg | +5.284 |
cape | +5.064 |
recomp | +5.033 |
NL | +5.031 |
Clarkson | +4.938 |
Neg logit contributions | |
kson | -5.658 |
Wiz | -5.336 |
Wolf | -5.288 |
ATK | -5.222 |
�� | -4.899 |
Token | are |
Token ID | 389 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
erg | +2.370 |
NL | +2.280 |
cape | +2.242 |
recomp | +2.226 |
ropolitan | +2.185 |
Neg logit contributions | |
kson | -2.597 |
Wiz | -2.457 |
Wolf | -2.440 |
ATK | -2.344 |
pent | -2.196 |
Token | . |
Token ID | 13 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
erg | +1.282 |
NL | +1.235 |
recomp | +1.195 |
cape | +1.188 |
ropolitan | +1.179 |
Neg logit contributions | |
kson | -1.603 |
Wiz | -1.528 |
Wolf | -1.520 |
ATK | -1.471 |
pent | -1.376 |
Token | � |
Token ID | 447 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
erg | +0.457 |
NL | +0.444 |
recomp | +0.425 |
ropolitan | +0.424 |
cape | +0.423 |
Neg logit contributions | |
kson | -0.551 |
Wiz | -0.525 |
Wolf | -0.524 |
ATK | -0.506 |
pent | -0.475 |
Token | � |
Token ID | 251 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
kson | +0.339 |
Wiz | +0.318 |
Wolf | +0.318 |
ATK | +0.301 |
pent | +0.271 |
Neg logit contributions | |
erg | -0.524 |
NL | -0.513 |
recomp | -0.500 |
ropolitan | -0.499 |
cape | -0.498 |
Token |
|
Token ID | 198 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
erg | +1.395 |
NL | +1.353 |
recomp | +1.288 |
ropolitan | +1.284 |
cape | +1.283 |
Neg logit contributions | |
kson | -1.688 |
Wiz | -1.605 |
Wolf | -1.595 |
ATK | -1.546 |
pent | -1.453 |
Token |
|
Token ID | 198 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
kson | +0.669 |
Wolf | +0.642 |
Wiz | +0.638 |
ATK | +0.617 |
pent | +0.572 |
Neg logit contributions | |
erg | -0.611 |
NL | -0.590 |
recomp | -0.580 |
ropolitan | -0.577 |
cape | -0.571 |
Token | N |
Token ID | 45 |
Feature activation | -1.81e+01 |
Pos logit contributions | |
erg | +1.496 |
NL | +1.476 |
cape | +1.382 |
ropolitan | +1.365 |
recomp | +1.363 |
Neg logit contributions | |
kson | -1.751 |
Wiz | -1.667 |
Wolf | -1.666 |
ATK | -1.615 |
pent | -1.491 |
Token | ug |
Token ID | 1018 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
erg | +6.219 |
NL | +4.899 |
zig | +4.465 |
jug | +4.347 |
atures | +4.019 |
Neg logit contributions | |
�� | -17.732 |
kson | -17.083 |
Wiz | -16.905 |
Expedition | -16.424 |
Cind | -16.147 |
Token | ent |
Token ID | 298 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
erg | +0.849 |
NL | +0.821 |
recomp | +0.790 |
ropolitan | +0.790 |
cape | +0.786 |
Neg logit contributions | |
kson | -0.840 |
Wiz | -0.802 |
Wolf | -0.798 |
ATK | -0.766 |
pent | -0.708 |
Token | , |
Token ID | 11 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
erg | +2.665 |
NL | +2.583 |
recomp | +2.536 |
cape | +2.485 |
Clarkson | +2.474 |
Neg logit contributions | |
kson | -2.954 |
Wiz | -2.804 |
Wolf | -2.773 |
ATK | -2.719 |
pent | -2.555 |
Token | who |
Token ID | 508 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
kson | +0.173 |
Wolf | +0.165 |
Wiz | +0.165 |
ATK | +0.159 |
pent | +0.148 |
Neg logit contributions | |
erg | -0.152 |
NL | -0.148 |
recomp | -0.143 |
ropolitan | -0.142 |
cape | -0.142 |
Token | has |
Token ID | 468 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
erg | +3.301 |
NL | +3.181 |
recomp | +3.144 |
Clarkson | +3.093 |
cape | +3.034 |
Neg logit contributions | |
kson | -3.709 |
Wiz | -3.479 |
Wolf | -3.444 |
ATK | -3.400 |
pent | -3.242 |
Token | anyone |
Token ID | 2687 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
kson | +1.902 |
Wolf | +1.850 |
Wiz | +1.841 |
ATK | +1.747 |
pent | +1.609 |
Neg logit contributions | |
erg | -1.892 |
NL | -1.814 |
ropolitan | -1.780 |
recomp | -1.763 |
cape | -1.761 |
Token | in |
Token ID | 287 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
kson | +2.314 |
Wolf | +2.240 |
Wiz | +2.218 |
ATK | +2.115 |
pent | +1.966 |
Neg logit contributions | |
erg | -2.240 |
NL | -2.157 |
ropolitan | -2.114 |
recomp | -2.083 |
cape | -2.079 |
Token | that |
Token ID | 326 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
erg | +1.141 |
NL | +1.113 |
recomp | +1.071 |
cape | +1.064 |
ropolitan | +1.060 |
Neg logit contributions | |
kson | -1.265 |
Wolf | -1.196 |
Wiz | -1.196 |
ATK | -1.158 |
pent | -1.079 |
Token | room |
Token ID | 2119 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
erg | +0.011 |
NL | +0.010 |
recomp | +0.010 |
ropolitan | +0.010 |
cape | +0.010 |
Neg logit contributions | |
kson | -0.012 |
Wolf | -0.011 |
Wiz | -0.011 |
ATK | -0.011 |
pent | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
kson | +0.814 |
Wolf | +0.779 |
Wiz | +0.777 |
ATK | +0.746 |
pent | +0.697 |
Neg logit contributions | |
erg | -0.707 |
NL | -0.686 |
ropolitan | -0.664 |
recomp | -0.661 |
cape | -0.654 |
Token | Zach |
Token ID | 18825 |
Feature activation | -1.72e+01 |
Pos logit contributions | |
erg | +2.548 |
NL | +2.506 |
Clarkson | +2.386 |
cape | +2.352 |
ropolitan | +2.336 |
Neg logit contributions | |
kson | -2.980 |
Wiz | -2.775 |
Wolf | -2.773 |
ATK | -2.721 |
pent | -2.579 |
Token | Walters |
Token ID | 43287 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
erg | +11.607 |
NL | +11.310 |
Clarkson | +10.768 |
zig | +10.570 |
ropolitan | +10.313 |
Neg logit contributions | |
kson | -9.504 |
ATK | -8.430 |
pent | -8.160 |
Wiz | -8.006 |
restriction | -7.844 |
Token | , |
Token ID | 11 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
erg | +3.071 |
NL | +2.971 |
cape | +2.848 |
recomp | +2.845 |
Clarkson | +2.800 |
Neg logit contributions | |
kson | -3.326 |
Wiz | -3.188 |
Wolf | -3.154 |
ATK | -3.114 |
pent | -2.869 |
Token | an |
Token ID | 281 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
erg | +1.363 |
NL | +1.331 |
recomp | +1.273 |
cape | +1.264 |
ropolitan | +1.256 |
Neg logit contributions | |
kson | -1.540 |
Wolf | -1.452 |
Wiz | -1.450 |
ATK | -1.410 |
pent | -1.317 |
Token | infield |
Token ID | 43262 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
erg | +0.838 |
NL | +0.816 |
recomp | +0.781 |
cape | +0.777 |
ropolitan | +0.776 |
Neg logit contributions | |
kson | -0.956 |
Wolf | -0.909 |
Wiz | -0.908 |
ATK | -0.875 |
pent | -0.823 |
Token | er |
Token ID | 263 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
erg | +1.318 |
NL | +1.254 |
recomp | +1.193 |
cape | +1.175 |
ropolitan | +1.169 |
Neg logit contributions | |
kson | -2.195 |
Wolf | -2.088 |
Wiz | -2.087 |
ATK | -2.033 |
pent | -1.903 |
Token | with |
Token ID | 351 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
erg | +1.244 |
NL | +1.207 |
recomp | +1.170 |
cape | +1.162 |
ropolitan | +1.155 |
Neg logit contributions | |
kson | -1.395 |
Wiz | -1.325 |
Wolf | -1.321 |
ATK | -1.282 |
pent | -1.193 |
Token | sanctioned |
Token ID | 30572 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
erg | +0.569 |
NL | +0.554 |
recomp | +0.535 |
ropolitan | +0.533 |
cape | +0.532 |
Neg logit contributions | |
kson | -0.573 |
Wolf | -0.544 |
Wiz | -0.544 |
ATK | -0.523 |
pent | -0.485 |
Token | individuals |
Token ID | 3925 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
kson | +1.112 |
Wolf | +1.075 |
Wiz | +1.070 |
ATK | +1.017 |
pent | +0.940 |
Neg logit contributions | |
erg | -1.184 |
NL | -1.155 |
ropolitan | -1.116 |
recomp | -1.108 |
cape | -1.107 |
Token | , |
Token ID | 11 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
erg | +1.198 |
NL | +1.158 |
recomp | +1.125 |
cape | +1.120 |
ropolitan | +1.112 |
Neg logit contributions | |
kson | -1.398 |
Wiz | -1.328 |
Wolf | -1.325 |
ATK | -1.287 |
pent | -1.198 |
Token | direct |
Token ID | 1277 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
kson | +2.464 |
Wolf | +2.398 |
Wiz | +2.390 |
ATK | +2.265 |
pent | +2.085 |
Neg logit contributions | |
erg | -2.425 |
NL | -2.344 |
ropolitan | -2.298 |
cape | -2.257 |
recomp | -2.251 |
Token | or |
Token ID | 393 |
Feature activation | -1.69e+01 |
Pos logit contributions | |
kson | +0.401 |
Wolf | +0.383 |
Wiz | +0.382 |
ATK | +0.366 |
pent | +0.341 |
Neg logit contributions | |
erg | -0.383 |
NL | -0.372 |
recomp | -0.359 |
ropolitan | -0.358 |
cape | -0.357 |
Token | indirect |
Token ID | 12913 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
recomp | +5.725 |
cape | +5.672 |
backdoor | +5.428 |
erg | +5.348 |
ropolitan | +5.306 |
Neg logit contributions | |
kson | -14.768 |
ATK | -14.076 |
�� | -13.990 |
Wolf | -13.965 |
Wiz | -13.660 |
Token | , |
Token ID | 11 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
kson | +1.761 |
Wolf | +1.706 |
Wiz | +1.692 |
ATK | +1.621 |
pent | +1.519 |
Neg logit contributions | |
erg | -1.623 |
NL | -1.570 |
ropolitan | -1.537 |
recomp | -1.510 |
cape | -1.505 |
Token | � |
Token ID | 447 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
kson | +2.681 |
Wolf | +2.617 |
Wiz | +2.602 |
ATK | +2.454 |
pent | +2.258 |
Neg logit contributions | |
erg | -2.632 |
NL | -2.545 |
ropolitan | -2.494 |
cape | -2.445 |
recomp | -2.445 |
Token | � |
Token ID | 251 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
erg | +0.344 |
NL | +0.335 |
recomp | +0.326 |
ropolitan | +0.325 |
cape | +0.324 |
Neg logit contributions | |
kson | -0.256 |
Wolf | -0.241 |
Wiz | -0.241 |
ATK | -0.230 |
pent | -0.210 |
Token | he |
Token ID | 339 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
kson | +2.393 |
Wolf | +2.300 |
Wiz | +2.287 |
ATK | +2.179 |
pent | +2.031 |
Neg logit contributions | |
erg | -2.287 |
NL | -2.209 |
ropolitan | -2.165 |
recomp | -2.153 |
cape | -2.137 |
Token | . |
Token ID | 13 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
erg | +3.488 |
NL | +3.395 |
ropolitan | +3.158 |
Clarkson | +3.149 |
recomp | +3.142 |
Neg logit contributions | |
kson | -3.820 |
Wiz | -3.612 |
Wolf | -3.536 |
ATK | -3.437 |
pent | -3.263 |
Token | Madison |
Token ID | 14909 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
erg | +2.199 |
NL | +2.161 |
Clarkson | +2.073 |
cape | +2.059 |
ropolitan | +2.058 |
Neg logit contributions | |
kson | -2.242 |
Wiz | -2.090 |
Wolf | -2.078 |
ATK | -2.021 |
pent | -1.903 |
Token | St |
Token ID | 520 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
erg | +1.404 |
NL | +1.366 |
recomp | +1.316 |
ropolitan | +1.312 |
cape | +1.310 |
Neg logit contributions | |
kson | -1.579 |
Wiz | -1.503 |
Wolf | -1.500 |
ATK | -1.449 |
pent | -1.358 |
Token | . |
Token ID | 13 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
erg | +1.201 |
NL | +1.170 |
cape | +1.105 |
ropolitan | +1.104 |
recomp | +1.095 |
Neg logit contributions | |
kson | -1.894 |
Wiz | -1.812 |
Wolf | -1.806 |
ATK | -1.762 |
pent | -1.651 |
Token | Baltimore |
Token ID | 10346 |
Feature activation | -6.93e+00 |
Pos logit contributions | |
erg | +0.551 |
NL | +0.537 |
ropolitan | +0.514 |
cape | +0.514 |
recomp | +0.513 |
Neg logit contributions | |
kson | -0.636 |
Wiz | -0.602 |
Wolf | -0.602 |
ATK | -0.582 |
pent | -0.544 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
NL | +3.724 |
erg | +3.683 |
ropolitan | +3.479 |
cape | +3.397 |
recomp | +3.320 |
Neg logit contributions | |
kson | -5.613 |
Wiz | -5.147 |
Wolf | -5.130 |
ATK | -5.044 |
pent | -4.884 |
Token | MD |
Token ID | 10670 |
Feature activation | -7.25e+00 |
Pos logit contributions | |
NL | +4.855 |
erg | +4.252 |
Ga | +4.137 |
ropolitan | +3.956 |
♦ | +3.777 |
Neg logit contributions | |
kson | -15.259 |
�� | -13.833 |
Wolf | -13.674 |
pent | -13.650 |
ATK | -13.633 |
Token | , |
Token ID | 11 |
Feature activation | -6.44e+00 |
Pos logit contributions | |
NL | +5.130 |
erg | +5.123 |
cape | +5.029 |
recomp | +4.913 |
ropolitan | +4.866 |
Neg logit contributions | |
kson | -4.464 |
Wolf | -4.030 |
Wiz | -4.009 |
ATK | -4.007 |
pent | -3.628 |
Token | 212 |
Token ID | 23679 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
erg | +4.068 |
NL | +4.033 |
cape | +3.869 |
recomp | +3.841 |
ropolitan | +3.791 |
Neg logit contributions | |
kson | -4.460 |
Wolf | -4.121 |
Wiz | -4.092 |
ATK | -4.006 |
pent | -3.764 |
Token | 01 |
Token ID | 486 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
NL | +2.620 |
erg | +2.615 |
cape | +2.456 |
Clarkson | +2.423 |
ropolitan | +2.421 |
Neg logit contributions | |
kson | -2.748 |
Wiz | -2.567 |
Wolf | -2.555 |
ATK | -2.460 |
�� | -2.356 |
Token | . |
Token ID | 13 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
erg | +1.423 |
NL | +1.372 |
cape | +1.317 |
ropolitan | +1.317 |
recomp | +1.312 |
Neg logit contributions | |
kson | -1.739 |
Wiz | -1.646 |
Wolf | -1.638 |
ATK | -1.585 |
pent | -1.497 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
erg | +2.216 |
NL | +2.158 |
cape | +2.041 |
recomp | +2.012 |
Clarkson | +2.009 |
Neg logit contributions | |
kson | -3.142 |
Wiz | -3.008 |
Wolf | -2.970 |
ATK | -2.878 |
�� | -2.778 |
Token | 1998 |
Token ID | 21113 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
NL | +4.379 |
erg | +4.026 |
♦ | +3.816 |
FORE | +3.815 |
zig | +3.714 |
Neg logit contributions | |
kson | -9.884 |
Wiz | -9.507 |
Wolf | -9.504 |
ATK | -9.320 |
�� | -9.298 |
Token | Garry |
Token ID | 45354 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
kson | +0.971 |
Wolf | +0.935 |
Wiz | +0.931 |
ATK | +0.897 |
pent | +0.836 |
Neg logit contributions | |
erg | -0.720 |
NL | -0.699 |
recomp | -0.677 |
cape | -0.672 |
ropolitan | -0.672 |
Token | Sh |
Token ID | 911 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
erg | +1.640 |
NL | +1.598 |
Clarkson | +1.544 |
recomp | +1.536 |
cape | +1.534 |
Neg logit contributions | |
kson | -1.725 |
Wiz | -1.631 |
Wolf | -1.618 |
ATK | -1.561 |
pent | -1.485 |
Token | and |
Token ID | 392 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
erg | +3.169 |
NL | +2.937 |
cape | +2.808 |
zig | +2.787 |
ropolitan | +2.718 |
Neg logit contributions | |
kson | -5.884 |
Wiz | -5.760 |
Wolf | -5.701 |
ATK | -5.537 |
�� | -5.447 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
erg | +1.922 |
NL | +1.813 |
cape | +1.670 |
zig | +1.661 |
ropolitan | +1.628 |
Neg logit contributions | |
kson | -4.980 |
Wiz | -4.898 |
Wolf | -4.825 |
ATK | -4.768 |
�� | -4.440 |
Token | 1999 |
Token ID | 7358 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
erg | +6.839 |
NL | +6.645 |
Clarkson | +6.432 |
recomp | +6.301 |
zig | +6.168 |
Neg logit contributions | |
kson | -12.457 |
Wiz | -11.464 |
Wolf | -11.241 |
ATK | -11.228 |
pent | -11.074 |
Token | John |
Token ID | 1757 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
erg | +0.687 |
NL | +0.665 |
recomp | +0.639 |
ropolitan | +0.637 |
cape | +0.636 |
Neg logit contributions | |
kson | -0.754 |
Wiz | -0.717 |
Wolf | -0.715 |
ATK | -0.691 |
pent | -0.645 |
Token | Lith |
Token ID | 19730 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
erg | +2.247 |
NL | +2.194 |
Clarkson | +2.132 |
cape | +2.131 |
recomp | +2.128 |
Neg logit contributions | |
kson | -1.155 |
Wiz | -1.060 |
Wolf | -1.053 |
ATK | -1.005 |
pent | -0.898 |
Token | gow |
Token ID | 21175 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
erg | +1.156 |
NL | +1.126 |
recomp | +1.092 |
ropolitan | +1.091 |
cape | +1.089 |
Neg logit contributions | |
kson | -0.804 |
Wiz | -0.758 |
Wolf | -0.756 |
ATK | -0.721 |
pent | -0.655 |
Token |
|
Token ID | 198 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
erg | +1.021 |
NL | +0.990 |
cape | +0.946 |
recomp | +0.945 |
ropolitan | +0.938 |
Neg logit contributions | |
kson | -1.276 |
Wiz | -1.222 |
Wolf | -1.217 |
ATK | -1.172 |
pent | -1.102 |
Token | Z |
Token ID | 57 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
erg | +6.289 |
NL | +5.990 |
zig | +5.686 |
ropolitan | +5.570 |
Clarkson | +5.458 |
Neg logit contributions | |
kson | -6.763 |
Wiz | -6.581 |
ATK | -6.416 |
Wolf | -6.415 |
�� | -6.125 |
Token | P |
Token ID | 350 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
erg | +6.875 |
NL | +6.423 |
Clarkson | +5.963 |
recomp | +5.890 |
cape | +5.848 |
Neg logit contributions | |
kson | -7.465 |
Wolf | -6.617 |
Wiz | -6.615 |
ATK | -6.372 |
�� | -6.253 |
Token | ops |
Token ID | 2840 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
erg | +2.401 |
NL | +2.359 |
ropolitan | +2.189 |
zig | +2.139 |
Clarkson | +2.130 |
Neg logit contributions | |
kson | -3.172 |
Wolf | -3.033 |
Wiz | -3.032 |
ATK | -2.970 |
pent | -2.779 |
Token | line |
Token ID | 1627 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
erg | +4.136 |
NL | +3.980 |
cape | +3.816 |
ropolitan | +3.814 |
Clarkson | +3.748 |
Neg logit contributions | |
kson | -4.465 |
Wiz | -4.103 |
Wolf | -4.063 |
ATK | -4.044 |
pent | -3.782 |
Token | with |
Token ID | 351 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
erg | +3.324 |
NL | +3.202 |
Clarkson | +3.044 |
ropolitan | +3.025 |
cape | +3.021 |
Neg logit contributions | |
kson | -3.999 |
Wiz | -3.737 |
Wolf | -3.716 |
ATK | -3.671 |
pent | -3.392 |
Token | Zach |
Token ID | 18825 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
erg | +3.285 |
NL | +3.207 |
Clarkson | +3.143 |
ropolitan | +3.042 |
recomp | +3.040 |
Neg logit contributions | |
kson | -3.405 |
Wiz | -3.148 |
Wolf | -3.112 |
ATK | -3.089 |
pent | -2.885 |
Token | Par |
Token ID | 2547 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
zig | +9.188 |
erg | +9.132 |
Clarkson | +9.081 |
NL | +8.924 |
ropolitan | +8.389 |
Neg logit contributions | |
kson | -9.854 |
byss | -9.076 |
ATK | -8.857 |
PDATE | -8.816 |
Wiz | -8.736 |
Token | ise |
Token ID | 786 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
erg | +2.036 |
NL | +1.870 |
ropolitan | +1.816 |
zig | +1.798 |
cape | +1.797 |
Neg logit contributions | |
kson | -5.487 |
Wiz | -5.362 |
Wolf | -5.303 |
ATK | -5.154 |
�� | -4.905 |
Token | and |
Token ID | 290 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
erg | +3.314 |
NL | +3.241 |
cape | +3.066 |
recomp | +3.051 |
Clarkson | +3.041 |
Neg logit contributions | |
kson | -4.231 |
Wiz | -4.019 |
Wolf | -3.971 |
ATK | -3.892 |
pent | -3.651 |
Token | Travis |
Token ID | 19804 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
erg | +1.140 |
NL | +1.106 |
recomp | +1.070 |
ropolitan | +1.064 |
cape | +1.063 |
Neg logit contributions | |
kson | -1.127 |
Wiz | -1.068 |
Wolf | -1.067 |
ATK | -1.030 |
pent | -0.954 |
Token | Z |
Token ID | 1168 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
NL | +5.447 |
Clarkson | +5.380 |
erg | +5.242 |
zig | +5.184 |
Skywalker | +4.911 |
Neg logit contributions | |
kson | -8.082 |
�� | -7.645 |
ATK | -7.631 |
Wiz | -7.328 |
byss | -7.270 |
Token | this |
Token ID | 428 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
erg | +2.677 |
NL | +2.611 |
recomp | +2.511 |
ropolitan | +2.495 |
cape | +2.495 |
Neg logit contributions | |
kson | -3.192 |
Wolf | -2.980 |
Wiz | -2.974 |
ATK | -2.902 |
pent | -2.768 |
Token | webpage |
Token ID | 35699 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
erg | +3.651 |
NL | +3.524 |
recomp | +3.375 |
cape | +3.366 |
Clarkson | +3.316 |
Neg logit contributions | |
kson | -4.851 |
Wiz | -4.524 |
Wolf | -4.519 |
ATK | -4.469 |
pent | -4.300 |
Token | , |
Token ID | 11 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
erg | +0.638 |
NL | +0.619 |
recomp | +0.599 |
cape | +0.597 |
ropolitan | +0.595 |
Neg logit contributions | |
kson | -0.689 |
Wiz | -0.652 |
Wolf | -0.652 |
ATK | -0.628 |
pent | -0.587 |
Token | in |
Token ID | 287 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
erg | +2.737 |
NL | +2.676 |
cape | +2.600 |
recomp | +2.593 |
Clarkson | +2.535 |
Neg logit contributions | |
kson | -3.294 |
Wiz | -3.066 |
Wolf | -3.059 |
ATK | -2.977 |
pent | -2.857 |
Token | whole |
Token ID | 2187 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
erg | +1.811 |
NL | +1.757 |
recomp | +1.731 |
ropolitan | +1.699 |
cape | +1.699 |
Neg logit contributions | |
kson | -1.593 |
Wiz | -1.498 |
Wolf | -1.490 |
ATK | -1.439 |
pent | -1.355 |
Token | or |
Token ID | 393 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
erg | +3.650 |
NL | +3.503 |
recomp | +3.447 |
ropolitan | +3.410 |
cape | +3.372 |
Neg logit contributions | |
kson | -5.089 |
Wiz | -4.940 |
Wolf | -4.833 |
ATK | -4.745 |
pent | -4.566 |
Token | in |
Token ID | 287 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
recomp | +7.041 |
cape | +7.037 |
erg | +7.021 |
NL | +6.575 |
ropolitan | +6.555 |
Neg logit contributions | |
kson | -12.254 |
Wolf | -11.586 |
Wiz | -11.557 |
ATK | -11.284 |
�� | -11.181 |
Token | part |
Token ID | 636 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
erg | +2.759 |
NL | +2.653 |
recomp | +2.645 |
cape | +2.595 |
ropolitan | +2.549 |
Neg logit contributions | |
kson | -3.104 |
Wolf | -2.929 |
Wiz | -2.920 |
ATK | -2.846 |
pent | -2.663 |
Token | , |
Token ID | 11 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
erg | +1.175 |
NL | +1.138 |
recomp | +1.111 |
cape | +1.104 |
ropolitan | +1.092 |
Neg logit contributions | |
kson | -1.440 |
Wiz | -1.369 |
Wolf | -1.361 |
ATK | -1.323 |
pent | -1.240 |
Token | is |
Token ID | 318 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
erg | +0.438 |
NL | +0.426 |
recomp | +0.412 |
cape | +0.410 |
ropolitan | +0.409 |
Neg logit contributions | |
kson | -0.452 |
Wiz | -0.429 |
Wolf | -0.428 |
ATK | -0.412 |
pent | -0.384 |
Token | strictly |
Token ID | 14084 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
erg | +4.287 |
recomp | +4.218 |
NL | +4.195 |
cape | +4.064 |
Clarkson | +4.022 |
Neg logit contributions | |
kson | -5.502 |
Wiz | -5.010 |
Wolf | -4.956 |
ATK | -4.816 |
pent | -4.634 |
Token | ab |
Token ID | 397 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
kson | +4.231 |
Wolf | +4.157 |
Wiz | +4.087 |
ATK | +3.949 |
pent | +3.752 |
Neg logit contributions | |
NL | -3.493 |
erg | -3.491 |
recomp | -3.433 |
cape | -3.288 |
Clarkson | -3.257 |
Token | ar |
Token ID | 283 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
erg | +1.116 |
NL | +1.076 |
ropolitan | +1.035 |
recomp | +1.034 |
cape | +1.031 |
Neg logit contributions | |
kson | -1.204 |
Wiz | -1.143 |
Wolf | -1.142 |
ATK | -1.098 |
pent | -1.025 |
Token | , |
Token ID | 11 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
erg | +3.627 |
NL | +3.550 |
ropolitan | +3.432 |
cape | +3.394 |
Clarkson | +3.351 |
Neg logit contributions | |
kson | -4.225 |
Wiz | -4.017 |
Wolf | -3.963 |
ATK | -3.905 |
pent | -3.649 |
Token | FL |
Token ID | 9977 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
erg | +3.384 |
NL | +3.319 |
Clarkson | +3.110 |
cape | +3.067 |
recomp | +3.065 |
Neg logit contributions | |
kson | -4.663 |
Wiz | -4.370 |
Wolf | -4.336 |
ATK | -4.211 |
pent | -4.131 |
Token | : |
Token ID | 1058 |
Feature activation | -8.12e+00 |
Pos logit contributions | |
erg | +1.471 |
NL | +1.440 |
recomp | +1.355 |
ropolitan | +1.354 |
cape | +1.344 |
Neg logit contributions | |
kson | -2.044 |
Wiz | -1.936 |
Wolf | -1.935 |
ATK | -1.864 |
pent | -1.772 |
Token | K |
Token ID | 509 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
NL | +5.355 |
erg | +5.263 |
Clarkson | +5.248 |
cape | +5.014 |
ropolitan | +5.007 |
Neg logit contributions | |
kson | -5.241 |
Wiz | -4.752 |
Wolf | -4.650 |
ATK | -4.528 |
pent | -4.481 |
Token | rie |
Token ID | 5034 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
erg | +10.524 |
NL | +9.838 |
Ga | +9.206 |
ropolitan | +9.066 |
cape | +8.982 |
Neg logit contributions | |
kson | -9.265 |
Wiz | -8.685 |
ATK | -8.289 |
Wolf | -8.229 |
�� | -7.943 |
Token | ger |
Token ID | 1362 |
Feature activation | -8.70e+00 |
Pos logit contributions | |
kson | +0.154 |
Wiz | +0.147 |
Wolf | +0.147 |
ATK | +0.141 |
pent | +0.131 |
Neg logit contributions | |
erg | -0.152 |
NL | -0.148 |
recomp | -0.143 |
cape | -0.142 |
ropolitan | -0.142 |
Token | Publishing |
Token ID | 23499 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
erg | +5.985 |
NL | +5.915 |
Clarkson | +5.664 |
cape | +5.625 |
ropolitan | +5.619 |
Neg logit contributions | |
kson | -5.235 |
Wiz | -4.983 |
Wolf | -4.772 |
ATK | -4.757 |
pent | -4.499 |
Token | . |
Token ID | 764 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
erg | +3.018 |
NL | +2.965 |
cape | +2.766 |
Clarkson | +2.755 |
recomp | +2.746 |
Neg logit contributions | |
kson | -4.135 |
Wiz | -3.896 |
Wolf | -3.848 |
ATK | -3.794 |
pent | -3.617 |
Token |
|
Token ID | 198 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
erg | +2.699 |
NL | +2.644 |
Clarkson | +2.489 |
zig | +2.449 |
cape | +2.434 |
Neg logit contributions | |
kson | -3.899 |
Wiz | -3.718 |
Wolf | -3.645 |
ATK | -3.534 |
pent | -3.468 |
Token |
|
Token ID | 198 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
erg | +1.810 |
NL | +1.764 |
recomp | +1.674 |
cape | +1.672 |
ropolitan | +1.670 |
Neg logit contributions | |
kson | -2.067 |
Wiz | -1.953 |
Wolf | -1.935 |
ATK | -1.879 |
pent | -1.774 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
erg | +0.743 |
NL | +0.721 |
recomp | +0.690 |
cape | +0.688 |
ropolitan | +0.687 |
Neg logit contributions | |
kson | -0.906 |
Wiz | -0.865 |
Wolf | -0.863 |
ATK | -0.832 |
pent | -0.779 |
Token | ADVERTISEMENT |
Token ID | 19053 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
erg | +1.437 |
NL | +1.417 |
cape | +1.325 |
ropolitan | +1.320 |
recomp | +1.317 |
Neg logit contributions | |
kson | -1.746 |
Wiz | -1.664 |
Wolf | -1.660 |
ATK | -1.609 |
pent | -1.495 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
kson | +1.046 |
Wolf | +1.002 |
Wiz | +0.999 |
ATK | +0.966 |
pent | +0.891 |
Neg logit contributions | |
erg | -0.930 |
NL | -0.897 |
recomp | -0.878 |
ropolitan | -0.868 |
cape | -0.864 |
Token |
|
Token ID | 198 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
kson | +1.507 |
Wolf | +1.450 |
Wiz | +1.431 |
ATK | +1.390 |
pent | +1.277 |
Neg logit contributions | |
erg | -1.486 |
NL | -1.439 |
recomp | -1.428 |
ropolitan | -1.423 |
cape | -1.395 |
Token | N |
Token ID | 45 |
Feature activation | -1.53e+01 |
Pos logit contributions | |
kson | +0.160 |
Wolf | +0.153 |
Wiz | +0.153 |
ATK | +0.147 |
pent | +0.137 |
Neg logit contributions | |
erg | -0.145 |
NL | -0.139 |
recomp | -0.136 |
ropolitan | -0.135 |
cape | -0.135 |
Token | ug |
Token ID | 1018 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
erg | +5.004 |
NL | +3.990 |
zig | +3.721 |
ropolitan | +3.349 |
jug | +3.338 |
Neg logit contributions | |
kson | -14.922 |
�� | -14.727 |
Wiz | -14.680 |
Wolf | -14.283 |
ATK | -14.040 |
Token | ent |
Token ID | 298 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
erg | +0.606 |
NL | +0.587 |
recomp | +0.566 |
ropolitan | +0.565 |
cape | +0.563 |
Neg logit contributions | |
kson | -0.595 |
Wiz | -0.569 |
Wolf | -0.567 |
ATK | -0.544 |
pent | -0.502 |
Token | � |
Token ID | 447 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
erg | +2.740 |
NL | +2.649 |
recomp | +2.611 |
cape | +2.553 |
Clarkson | +2.543 |
Neg logit contributions | |
kson | -3.067 |
Wiz | -2.922 |
Wolf | -2.880 |
ATK | -2.828 |
pent | -2.662 |
Token | � |
Token ID | 247 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
erg | +0.120 |
NL | +0.117 |
recomp | +0.113 |
ropolitan | +0.113 |
cape | +0.113 |
Neg logit contributions | |
kson | -0.101 |
Wiz | -0.095 |
Wolf | -0.095 |
ATK | -0.091 |
pent | -0.084 |
Token | s |
Token ID | 82 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
erg | +2.311 |
NL | +2.231 |
recomp | +2.172 |
cape | +2.145 |
ropolitan | +2.142 |
Neg logit contributions | |
kson | -2.351 |
Wiz | -2.242 |
Wolf | -2.217 |
ATK | -2.169 |
pent | -2.010 |
Token | have |
Token ID | 423 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
erg | +0.501 |
NL | +0.487 |
recomp | +0.472 |
ropolitan | +0.469 |
cape | +0.468 |
Neg logit contributions | |
kson | -0.499 |
Wiz | -0.474 |
Wolf | -0.473 |
ATK | -0.455 |
pent | -0.422 |
Token | her |
Token ID | 607 |
Feature activation | -9.41e+00 |
Pos logit contributions | |
erg | +3.563 |
NL | +3.447 |
recomp | +3.394 |
Clarkson | +3.313 |
ropolitan | +3.268 |
Neg logit contributions | |
kson | -4.514 |
Wiz | -4.278 |
Wolf | -4.236 |
ATK | -4.142 |
pent | -3.906 |
Token | fired |
Token ID | 6294 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
erg | +6.113 |
recomp | +6.109 |
NL | +5.858 |
Clarkson | +5.849 |
cape | +5.691 |
Neg logit contributions | |
kson | -6.231 |
Wiz | -5.747 |
Wolf | -5.608 |
ATK | -5.427 |
�� | -5.345 |
Token | . |
Token ID | 13 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
erg | +3.253 |
NL | +3.098 |
recomp | +3.071 |
cape | +3.023 |
Clarkson | +2.975 |
Neg logit contributions | |
kson | -4.655 |
Wiz | -4.440 |
Wolf | -4.347 |
ATK | -4.266 |
pent | -3.992 |
Token |
|
Token ID | 198 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
erg | +2.518 |
NL | +2.442 |
Clarkson | +2.339 |
ropolitan | +2.312 |
recomp | +2.305 |
Neg logit contributions | |
kson | -3.089 |
Wiz | -2.924 |
Wolf | -2.889 |
ATK | -2.807 |
pent | -2.658 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
erg | +1.926 |
NL | +1.874 |
cape | +1.773 |
recomp | +1.756 |
ropolitan | +1.745 |
Neg logit contributions | |
kson | -2.616 |
Wiz | -2.502 |
Wolf | -2.476 |
ATK | -2.398 |
�� | -2.271 |
Token | 1999 |
Token ID | 18946 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
NL | +5.950 |
erg | +5.623 |
FORE | +5.246 |
♦ | +5.244 |
cape | +5.080 |
Neg logit contributions | |
kson | -13.757 |
Wolf | -13.020 |
Wiz | -12.951 |
ATK | -12.673 |
�� | -12.359 |
Token | Jessie |
Token ID | 43425 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
erg | +2.001 |
NL | +1.943 |
Clarkson | +1.867 |
recomp | +1.861 |
cape | +1.857 |
Neg logit contributions | |
kson | -2.000 |
Wiz | -1.870 |
Wolf | -1.857 |
ATK | -1.798 |
pent | -1.690 |
Token | G |
Token ID | 402 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
erg | +1.277 |
NL | +1.241 |
recomp | +1.200 |
cape | +1.194 |
ropolitan | +1.189 |
Neg logit contributions | |
kson | -1.247 |
Wiz | -1.184 |
Wolf | -1.177 |
ATK | -1.136 |
pent | -1.057 |
Token | els |
Token ID | 1424 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
erg | +0.480 |
NL | +0.465 |
recomp | +0.448 |
ropolitan | +0.447 |
cape | +0.446 |
Neg logit contributions | |
kson | -0.504 |
Wiz | -0.481 |
Wolf | -0.480 |
ATK | -0.462 |
pent | -0.429 |
Token | inger |
Token ID | 3889 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
erg | +0.041 |
NL | +0.040 |
recomp | +0.039 |
ropolitan | +0.039 |
cape | +0.038 |
Neg logit contributions | |
kson | -0.042 |
Wolf | -0.040 |
Wiz | -0.040 |
ATK | -0.039 |
pent | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
erg | +2.525 |
NL | +2.429 |
recomp | +2.366 |
cape | +2.341 |
ropolitan | +2.331 |
Neg logit contributions | |
kson | -2.576 |
Wiz | -2.444 |
Wolf | -2.417 |
ATK | -2.350 |
pent | -2.173 |
Token | Saudi |
Token ID | 7420 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
kson | +0.286 |
Wiz | +0.274 |
Wolf | +0.274 |
ATK | +0.264 |
pent | +0.246 |
Neg logit contributions | |
erg | -0.237 |
NL | -0.230 |
recomp | -0.221 |
ropolitan | -0.221 |
cape | -0.221 |
Token | Arabia |
Token ID | 9671 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
erg | +0.749 |
NL | +0.726 |
recomp | +0.701 |
ropolitan | +0.698 |
cape | +0.696 |
Neg logit contributions | |
kson | -0.855 |
Wolf | -0.815 |
Wiz | -0.815 |
ATK | -0.785 |
pent | -0.732 |
Token | also |
Token ID | 635 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
kson | +1.300 |
Wolf | +1.250 |
Wiz | +1.244 |
ATK | +1.197 |
pent | +1.106 |
Neg logit contributions | |
erg | -1.290 |
NL | -1.252 |
ropolitan | -1.209 |
cape | -1.198 |
recomp | -1.198 |
Token | follows |
Token ID | 5679 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
erg | +0.374 |
NL | +0.363 |
recomp | +0.352 |
ropolitan | +0.350 |
cape | +0.350 |
Neg logit contributions | |
kson | -0.371 |
Wiz | -0.352 |
Wolf | -0.352 |
ATK | -0.338 |
pent | -0.314 |
Token | Islamic |
Token ID | 5533 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
kson | +0.414 |
Wolf | +0.396 |
Wiz | +0.395 |
ATK | +0.379 |
pent | +0.352 |
Neg logit contributions | |
erg | -0.390 |
NL | -0.379 |
recomp | -0.365 |
ropolitan | -0.365 |
cape | -0.364 |
Token | teachings |
Token ID | 19564 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
erg | +7.870 |
recomp | +7.589 |
Clarkson | +7.541 |
ropolitan | +7.539 |
NL | +7.448 |
Neg logit contributions | |
kson | -10.258 |
ATK | -9.885 |
Wiz | -9.658 |
Wolf | -9.485 |
pent | -9.261 |
Token | too |
Token ID | 1165 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
erg | +3.538 |
NL | +3.399 |
recomp | +3.354 |
cape | +3.347 |
ropolitan | +3.258 |
Neg logit contributions | |
kson | -4.712 |
Wiz | -4.435 |
Wolf | -4.377 |
ATK | -4.297 |
pent | -4.005 |
Token | seriously |
Token ID | 6411 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
kson | +0.464 |
Wolf | +0.446 |
Wiz | +0.444 |
ATK | +0.427 |
pent | +0.399 |
Neg logit contributions | |
erg | -0.398 |
NL | -0.387 |
ropolitan | -0.373 |
recomp | -0.373 |
cape | -0.371 |
Token | and |
Token ID | 290 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
erg | +2.161 |
NL | +2.079 |
recomp | +2.041 |
cape | +2.024 |
ropolitan | +2.006 |
Neg logit contributions | |
kson | -2.809 |
Wiz | -2.672 |
Wolf | -2.649 |
ATK | -2.583 |
pent | -2.406 |
Token | condemns |
Token ID | 49758 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
erg | +0.659 |
NL | +0.639 |
recomp | +0.621 |
cape | +0.615 |
ropolitan | +0.615 |
Neg logit contributions | |
kson | -0.700 |
Wiz | -0.665 |
Wolf | -0.664 |
ATK | -0.640 |
pent | -0.596 |
Token | the |
Token ID | 262 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
erg | +1.409 |
NL | +1.369 |
recomp | +1.312 |
cape | +1.306 |
ropolitan | +1.296 |
Neg logit contributions | |
kson | -1.709 |
Wiz | -1.630 |
Wolf | -1.617 |
ATK | -1.561 |
pent | -1.473 |
Token | sp |
Token ID | 599 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
kson | +0.489 |
Wolf | +0.464 |
Wiz | +0.460 |
ATK | +0.438 |
pent | +0.396 |
Neg logit contributions | |
erg | -0.745 |
NL | -0.732 |
ropolitan | -0.714 |
recomp | -0.709 |
cape | -0.706 |
Token | ines |
Token ID | 1127 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
erg | +0.912 |
NL | +0.881 |
recomp | +0.843 |
ropolitan | +0.841 |
cape | +0.839 |
Neg logit contributions | |
kson | -1.185 |
Wiz | -1.135 |
Wolf | -1.134 |
ATK | -1.094 |
pent | -1.024 |
Token | on |
Token ID | 319 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
erg | +3.196 |
NL | +3.062 |
cape | +2.902 |
recomp | +2.821 |
Clarkson | +2.811 |
Neg logit contributions | |
kson | -5.168 |
Wiz | -5.014 |
Wolf | -4.917 |
�� | -4.864 |
ATK | -4.777 |
Token | a |
Token ID | 257 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
erg | +2.574 |
NL | +2.459 |
cape | +2.389 |
recomp | +2.366 |
Clarkson | +2.327 |
Neg logit contributions | |
kson | -3.646 |
Wiz | -3.447 |
Wolf | -3.418 |
ATK | -3.300 |
�� | -3.224 |
Token | music |
Token ID | 2647 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
erg | +1.786 |
NL | +1.700 |
recomp | +1.657 |
cape | +1.619 |
Clarkson | +1.589 |
Neg logit contributions | |
kson | -2.902 |
Wiz | -2.766 |
Wolf | -2.746 |
ATK | -2.685 |
pent | -2.548 |
Token | box |
Token ID | 3091 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
recomp | +3.494 |
erg | +3.412 |
cape | +3.375 |
NL | +3.104 |
backdoor | +2.796 |
Neg logit contributions | |
kson | -14.874 |
�� | -14.604 |
PDATE | -14.442 |
Wiz | -14.075 |
ATK | -13.989 |
Token | , |
Token ID | 11 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
erg | +1.329 |
NL | +1.288 |
cape | +1.228 |
recomp | +1.220 |
ropolitan | +1.215 |
Neg logit contributions | |
kson | -1.680 |
Wiz | -1.605 |
Wolf | -1.601 |
ATK | -1.545 |
pent | -1.452 |
Token | involving |
Token ID | 7411 |
Feature activation | -8.02e+00 |
Pos logit contributions | |
erg | +1.537 |
NL | +1.486 |
cape | +1.397 |
recomp | +1.396 |
ropolitan | +1.383 |
Neg logit contributions | |
kson | -3.345 |
Wolf | -3.188 |
Wiz | -3.185 |
ATK | -3.089 |
pent | -2.954 |
Token | the |
Token ID | 262 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
erg | +4.019 |
NL | +3.908 |
Clarkson | +3.637 |
recomp | +3.615 |
cape | +3.611 |
Neg logit contributions | |
kson | -6.526 |
Wiz | -6.247 |
�� | -6.207 |
Wolf | -6.100 |
ATK | -5.923 |
Token | entire |
Token ID | 2104 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
erg | +3.296 |
NL | +3.216 |
recomp | +3.087 |
ropolitan | +3.052 |
cape | +3.051 |
Neg logit contributions | |
kson | -3.724 |
Wiz | -3.596 |
Wolf | -3.492 |
ATK | -3.404 |
�� | -3.269 |
Token | gas |
Token ID | 3623 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
kson | +0.205 |
Wolf | +0.197 |
Wiz | +0.196 |
ATK | +0.188 |
pent | +0.175 |
Neg logit contributions | |
erg | -0.189 |
NL | -0.183 |
ropolitan | -0.177 |
recomp | -0.177 |
cape | -0.176 |
Token | station |
Token ID | 4429 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
kson | +1.455 |
Wolf | +1.395 |
Wiz | +1.380 |
ATK | +1.331 |
pent | +1.249 |
Neg logit contributions | |
erg | -1.493 |
NL | -1.461 |
ropolitan | -1.402 |
recomp | -1.402 |
cape | -1.396 |
Token | manager |
Token ID | 4706 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
kson | +2.421 |
Wolf | +2.341 |
Wiz | +2.321 |
ATK | +2.223 |
pent | +2.073 |
Neg logit contributions | |
erg | -2.386 |
NL | -2.334 |
ropolitan | -2.253 |
cape | -2.240 |
recomp | -2.228 |
Token | with |
Token ID | 351 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
kson | +2.463 |
Wolf | +2.396 |
Wiz | +2.352 |
ATK | +2.257 |
pent | +2.104 |
Neg logit contributions | |
erg | -2.480 |
NL | -2.411 |
ropolitan | -2.345 |
cape | -2.324 |
recomp | -2.315 |
Token | a |
Token ID | 257 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
erg | +2.508 |
NL | +2.441 |
recomp | +2.391 |
cape | +2.341 |
Clarkson | +2.340 |
Neg logit contributions | |
kson | -2.694 |
Wiz | -2.530 |
Wolf | -2.501 |
ATK | -2.430 |
pent | -2.282 |
Token | monthly |
Token ID | 9651 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
erg | +4.129 |
NL | +4.013 |
recomp | +3.962 |
Clarkson | +3.860 |
cape | +3.824 |
Neg logit contributions | |
kson | -4.740 |
Wiz | -4.440 |
Wolf | -4.358 |
ATK | -4.314 |
pent | -3.971 |
Token | salary |
Token ID | 9588 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
recomp | +7.843 |
erg | +7.331 |
NL | +7.297 |
cape | +7.018 |
DOT | +6.894 |
Neg logit contributions | |
kson | -10.837 |
Wiz | -9.979 |
�� | -9.829 |
ATK | -9.613 |
Wolf | -9.533 |
Token | expectation |
Token ID | 17507 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
erg | +2.592 |
NL | +2.512 |
recomp | +2.482 |
cape | +2.452 |
Clarkson | +2.382 |
Neg logit contributions | |
kson | -3.033 |
Wiz | -2.869 |
Wolf | -2.821 |
ATK | -2.741 |
pent | -2.556 |
Token | of |
Token ID | 286 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
erg | +3.002 |
NL | +2.900 |
recomp | +2.853 |
cape | +2.813 |
Clarkson | +2.751 |
Neg logit contributions | |
kson | -3.613 |
Wiz | -3.392 |
Wolf | -3.333 |
ATK | -3.241 |
pent | -3.072 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
erg | +3.452 |
NL | +3.333 |
recomp | +3.325 |
Clarkson | +3.200 |
cape | +3.173 |
Neg logit contributions | |
kson | -4.201 |
Wiz | -3.956 |
Wolf | -3.906 |
ATK | -3.799 |
pent | -3.597 |
Token | , |
Token ID | 11 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
erg | +1.095 |
NL | +1.067 |
recomp | +1.025 |
cape | +1.016 |
ropolitan | +1.015 |
Neg logit contributions | |
kson | -1.273 |
Wiz | -1.209 |
Wolf | -1.205 |
ATK | -1.164 |
pent | -1.083 |
Token | this |
Token ID | 428 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
erg | +3.550 |
NL | +3.427 |
recomp | +3.327 |
ropolitan | +3.285 |
Clarkson | +3.256 |
Neg logit contributions | |
kson | -4.340 |
Wiz | -4.062 |
Wolf | -4.032 |
ATK | -3.962 |
pent | -3.711 |
Token | information |
Token ID | 1321 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
kson | +2.198 |
Wolf | +2.140 |
Wiz | +2.104 |
ATK | +2.011 |
pent | +1.871 |
Neg logit contributions | |
erg | -2.043 |
NL | -2.004 |
cape | -1.953 |
ropolitan | -1.939 |
recomp | -1.914 |
Token | . |
Token ID | 13 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
kson | +2.471 |
Wolf | +2.399 |
Wiz | +2.364 |
ATK | +2.249 |
pent | +2.098 |
Neg logit contributions | |
erg | -2.262 |
NL | -2.221 |
recomp | -2.133 |
cape | -2.133 |
ropolitan | -2.122 |
Token |
|
Token ID | 198 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
erg | +0.334 |
NL | +0.324 |
recomp | +0.313 |
ropolitan | +0.311 |
cape | +0.311 |
Neg logit contributions | |
kson | -0.390 |
Wolf | -0.372 |
Wiz | -0.372 |
ATK | -0.358 |
pent | -0.334 |
Token |
|
Token ID | 198 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
erg | +0.294 |
NL | +0.285 |
recomp | +0.276 |
ropolitan | +0.274 |
cape | +0.273 |
Neg logit contributions | |
kson | -0.340 |
Wolf | -0.325 |
Wiz | -0.325 |
ATK | -0.313 |
pent | -0.292 |
Token | K |
Token ID | 42 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
erg | +0.032 |
NL | +0.031 |
recomp | +0.031 |
ropolitan | +0.030 |
cape | +0.030 |
Neg logit contributions | |
kson | -0.038 |
Wolf | -0.036 |
Wiz | -0.036 |
ATK | -0.034 |
pent | -0.032 |
Token | ol |
Token ID | 349 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
erg | +8.257 |
NL | +7.598 |
ropolitan | +7.454 |
abre | +7.243 |
zig | +7.225 |
Neg logit contributions | |
kson | -10.461 |
Wiz | -10.378 |
ATK | -10.165 |
Wolf | -10.040 |
�� | -9.808 |
Token | omo |
Token ID | 17902 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
erg | +3.113 |
NL | +2.920 |
ropolitan | +2.827 |
cape | +2.780 |
recomp | +2.775 |
Neg logit contributions | |
kson | -4.848 |
Wiz | -4.634 |
Wolf | -4.561 |
ATK | -4.512 |
pent | -4.183 |
Token | isky |
Token ID | 34041 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
kson | +0.196 |
Wolf | +0.187 |
Wiz | +0.187 |
ATK | +0.181 |
pent | +0.170 |
Neg logit contributions | |
erg | -0.134 |
NL | -0.130 |
recomp | -0.125 |
ropolitan | -0.125 |
cape | -0.124 |
Token | did |
Token ID | 750 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
erg | +2.075 |
NL | +2.023 |
recomp | +1.961 |
cape | +1.928 |
ropolitan | +1.927 |
Neg logit contributions | |
kson | -2.301 |
Wiz | -2.163 |
Wolf | -2.152 |
ATK | -2.097 |
pent | -1.947 |
Token | not |
Token ID | 407 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
erg | +0.022 |
NL | +0.021 |
recomp | +0.020 |
ropolitan | +0.020 |
cape | +0.020 |
Neg logit contributions | |
kson | -0.026 |
Wiz | -0.025 |
Wolf | -0.025 |
ATK | -0.024 |
pent | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
erg | +3.971 |
NL | +3.769 |
recomp | +3.707 |
cape | +3.684 |
Clarkson | +3.680 |
Neg logit contributions | |
kson | -5.626 |
Wiz | -5.285 |
ATK | -5.177 |
Wolf | -5.086 |
pent | -4.857 |
Token | love |
Token ID | 1842 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
erg | +0.346 |
NL | +0.336 |
recomp | +0.325 |
ropolitan | +0.324 |
cape | +0.323 |
Neg logit contributions | |
kson | -0.345 |
Wiz | -0.327 |
Wolf | -0.327 |
ATK | -0.315 |
pent | -0.292 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
erg | +2.126 |
NL | +2.047 |
recomp | +1.981 |
cape | +1.975 |
ropolitan | +1.954 |
Neg logit contributions | |
kson | -2.809 |
Wiz | -2.713 |
Wolf | -2.643 |
ATK | -2.592 |
pent | -2.399 |
Token |
|
Token ID | 198 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
kson | +1.235 |
Wolf | +1.201 |
Wiz | +1.187 |
ATK | +1.141 |
pent | +1.049 |
Neg logit contributions | |
erg | -1.171 |
NL | -1.135 |
recomp | -1.105 |
cape | -1.091 |
ropolitan | -1.088 |
Token |
|
Token ID | 198 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
erg | +0.562 |
NL | +0.545 |
recomp | +0.525 |
ropolitan | +0.523 |
cape | +0.522 |
Neg logit contributions | |
kson | -0.663 |
Wolf | -0.633 |
Wiz | -0.633 |
ATK | -0.610 |
pent | -0.569 |
Token | Ly |
Token ID | 31633 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
erg | +0.438 |
NL | +0.426 |
recomp | +0.411 |
ropolitan | +0.409 |
cape | +0.408 |
Neg logit contributions | |
kson | -0.488 |
Wolf | -0.465 |
Wiz | -0.465 |
ATK | -0.447 |
pent | -0.416 |
Token | uba |
Token ID | 22013 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
erg | +2.974 |
cape | +2.818 |
NL | +2.714 |
zig | +2.606 |
ropolitan | +2.462 |
Neg logit contributions | |
Wiz | -15.078 |
kson | -14.804 |
ATK | -14.696 |
Wolf | -14.689 |
�� | -14.099 |
Token | lived |
Token ID | 5615 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
erg | +1.832 |
NL | +1.777 |
recomp | +1.727 |
cape | +1.702 |
ropolitan | +1.699 |
Neg logit contributions | |
kson | -2.026 |
Wiz | -1.930 |
Wolf | -1.898 |
ATK | -1.857 |
pent | -1.739 |
Token | 42 |
Token ID | 5433 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
kson | +0.623 |
Wolf | +0.596 |
Wiz | +0.592 |
ATK | +0.568 |
pent | +0.526 |
Neg logit contributions | |
erg | -0.630 |
NL | -0.614 |
ropolitan | -0.592 |
recomp | -0.590 |
cape | -0.590 |
Token | , |
Token ID | 11 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
erg | +1.956 |
NL | +1.884 |
recomp | +1.807 |
ropolitan | +1.795 |
cape | +1.792 |
Neg logit contributions | |
kson | -2.120 |
Wiz | -2.019 |
Wolf | -2.000 |
ATK | -1.923 |
pent | -1.808 |
Token | 000 |
Token ID | 830 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
erg | +0.168 |
NL | +0.163 |
recomp | +0.157 |
ropolitan | +0.156 |
cape | +0.156 |
Neg logit contributions | |
kson | -0.219 |
Wiz | -0.209 |
Wolf | -0.209 |
ATK | -0.202 |
pent | -0.189 |
Token | to |
Token ID | 284 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
erg | +2.802 |
NL | +2.737 |
recomp | +2.654 |
cape | +2.610 |
Clarkson | +2.605 |
Neg logit contributions | |
kson | -3.170 |
Wiz | -2.977 |
Wolf | -2.958 |
ATK | -2.879 |
pent | -2.716 |
Token | Triple |
Token ID | 19817 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
kson | +0.160 |
Wolf | +0.152 |
Wiz | +0.152 |
ATK | +0.146 |
pent | +0.136 |
Neg logit contributions | |
erg | -0.153 |
NL | -0.149 |
recomp | -0.144 |
ropolitan | -0.143 |
cape | -0.143 |
Token | - |
Token ID | 12 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
erg | +5.140 |
NL | +5.034 |
ropolitan | +4.599 |
Clarkson | +4.507 |
recomp | +4.418 |
Neg logit contributions | |
kson | -9.105 |
Wiz | -8.471 |
�� | -8.470 |
Wolf | -8.228 |
ATK | -8.157 |
Token | A |
Token ID | 32 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
erg | +2.655 |
NL | +2.647 |
ropolitan | +2.418 |
cape | +2.410 |
recomp | +2.395 |
Neg logit contributions | |
kson | -3.714 |
Wiz | -3.476 |
Wolf | -3.459 |
ATK | -3.317 |
�� | -3.194 |
Token | to |
Token ID | 284 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
kson | +0.430 |
Wolf | +0.418 |
Wiz | +0.416 |
ATK | +0.400 |
pent | +0.368 |
Neg logit contributions | |
erg | -0.407 |
NL | -0.393 |
recomp | -0.383 |
ropolitan | -0.382 |
cape | -0.382 |
Token | tw |
Token ID | 665 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
erg | +1.037 |
NL | +1.010 |
recomp | +0.980 |
cape | +0.968 |
ropolitan | +0.968 |
Neg logit contributions | |
kson | -1.025 |
Wiz | -0.970 |
Wolf | -0.969 |
ATK | -0.932 |
pent | -0.865 |
Token | iddle |
Token ID | 2509 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
erg | +8.297 |
NL | +7.321 |
recomp | +6.790 |
erker | +6.786 |
cape | +6.754 |
Neg logit contributions | |
kson | -11.199 |
Wiz | -10.227 |
Wolf | -9.773 |
ATK | -9.646 |
restriction | -9.316 |
Token | their |
Token ID | 511 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
erg | +1.120 |
NL | +1.084 |
recomp | +1.049 |
cape | +1.044 |
ropolitan | +1.039 |
Neg logit contributions | |
kson | -1.189 |
Wiz | -1.125 |
Wolf | -1.118 |
ATK | -1.080 |
pent | -1.003 |
Token | thumbs |
Token ID | 32766 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
kson | +0.029 |
Wolf | +0.028 |
Wiz | +0.028 |
ATK | +0.027 |
pent | +0.025 |
Neg logit contributions | |
erg | -0.036 |
NL | -0.035 |
recomp | -0.034 |
ropolitan | -0.034 |
cape | -0.034 |
Token | until |
Token ID | 1566 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
kson | +0.802 |
Wolf | +0.770 |
Wiz | +0.768 |
ATK | +0.740 |
pent | +0.686 |
Neg logit contributions | |
erg | -0.720 |
NL | -0.700 |
ropolitan | -0.675 |
recomp | -0.673 |
cape | -0.667 |
Token | there |
Token ID | 612 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
kson | +1.369 |
Wolf | +1.327 |
Wiz | +1.324 |
ATK | +1.263 |
pent | +1.156 |
Neg logit contributions | |
erg | -1.382 |
NL | -1.330 |
ropolitan | -1.308 |
cape | -1.296 |
recomp | -1.286 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
erg | +0.809 |
NL | +0.786 |
recomp | +0.759 |
cape | +0.753 |
ropolitan | +0.751 |
Neg logit contributions | |
kson | -0.919 |
Wiz | -0.874 |
Wolf | -0.871 |
ATK | -0.842 |
pent | -0.786 |
Token | this |
Token ID | 428 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
erg | +0.883 |
NL | +0.856 |
recomp | +0.829 |
cape | +0.820 |
ropolitan | +0.817 |
Neg logit contributions | |
kson | -0.999 |
Wiz | -0.949 |
Wolf | -0.948 |
ATK | -0.916 |
pent | -0.858 |
Token | dé |
Token ID | 39073 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
kson | +0.178 |
Wolf | +0.170 |
Wiz | +0.170 |
ATK | +0.163 |
pent | +0.151 |
Neg logit contributions | |
erg | -0.171 |
NL | -0.166 |
recomp | -0.161 |
ropolitan | -0.160 |
cape | -0.160 |
Token | j |
Token ID | 73 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
erg | +1.274 |
NL | +1.228 |
cape | +1.185 |
recomp | +1.184 |
ropolitan | +1.177 |
Neg logit contributions | |
kson | -1.641 |
Wiz | -1.572 |
Wolf | -1.569 |
ATK | -1.524 |
pent | -1.406 |
Token | à |
Token ID | 24247 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
erg | +3.843 |
NL | +3.647 |
cape | +3.551 |
ropolitan | +3.461 |
recomp | +3.451 |
Neg logit contributions | |
kson | -5.481 |
Wiz | -5.198 |
Wolf | -5.178 |
ATK | -5.066 |
pent | -4.672 |
Token | v |
Token ID | 410 |
Feature activation | -1.44e+01 |
Pos logit contributions | |
erg | +0.073 |
NL | +0.071 |
recomp | +0.068 |
ropolitan | +0.068 |
cape | +0.068 |
Neg logit contributions | |
kson | -0.095 |
Wolf | -0.091 |
Wiz | -0.091 |
ATK | -0.088 |
pent | -0.083 |
Token | u |
Token ID | 84 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
erg | +3.850 |
NL | +2.948 |
zig | +2.840 |
abre | +2.690 |
cape | +2.679 |
Neg logit contributions | |
kson | -15.223 |
Wiz | -14.704 |
Wolf | -14.379 |
ATK | -14.181 |
�� | -14.068 |
Token | isn |
Token ID | 2125 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
kson | +2.637 |
Wolf | +2.545 |
Wiz | +2.500 |
ATK | +2.388 |
restriction | +2.197 |
Neg logit contributions | |
erg | -2.692 |
NL | -2.655 |
ropolitan | -2.578 |
cape | -2.543 |
recomp | -2.523 |
Token | � |
Token ID | 447 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
erg | +1.632 |
NL | +1.588 |
cape | +1.515 |
ropolitan | +1.499 |
recomp | +1.495 |
Neg logit contributions | |
kson | -1.794 |
Wiz | -1.712 |
Wolf | -1.704 |
ATK | -1.642 |
pent | -1.527 |
Token | � |
Token ID | 247 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
erg | +0.341 |
NL | +0.332 |
recomp | +0.322 |
ropolitan | +0.320 |
cape | +0.320 |
Neg logit contributions | |
kson | -0.290 |
Wolf | -0.274 |
Wiz | -0.274 |
ATK | -0.262 |
pent | -0.241 |
Token | t |
Token ID | 83 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
erg | +0.415 |
NL | +0.400 |
recomp | +0.384 |
cape | +0.382 |
ropolitan | +0.382 |
Neg logit contributions | |
kson | -0.580 |
Wiz | -0.556 |
Wolf | -0.556 |
ATK | -0.537 |
pent | -0.503 |
Token | t |
Token ID | 256 |
Feature activation | -8.06e+00 |
Pos logit contributions | |
kson | +0.937 |
Wolf | +0.903 |
Wiz | +0.900 |
ATK | +0.859 |
pent | +0.795 |
Neg logit contributions | |
erg | -0.979 |
NL | -0.964 |
ropolitan | -0.929 |
cape | -0.919 |
recomp | -0.917 |
Token | inct |
Token ID | 4612 |
Feature activation | -6.00e+00 |
Pos logit contributions | |
erg | +6.153 |
NL | +5.550 |
ropolitan | +5.544 |
cape | +5.539 |
zig | +5.429 |
Neg logit contributions | |
kson | -4.834 |
Wolf | -4.647 |
Wiz | -4.612 |
ATK | -4.502 |
�� | -4.145 |
Token | ure |
Token ID | 495 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
erg | +4.764 |
NL | +4.470 |
recomp | +4.453 |
cape | +4.450 |
ropolitan | +4.428 |
Neg logit contributions | |
kson | -3.398 |
Wiz | -3.203 |
Wolf | -3.152 |
ATK | -3.061 |
pent | -2.708 |
Token | in |
Token ID | 287 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
erg | +0.257 |
NL | +0.250 |
recomp | +0.241 |
ropolitan | +0.240 |
cape | +0.240 |
Neg logit contributions | |
kson | -0.282 |
Wolf | -0.269 |
Wiz | -0.268 |
ATK | -0.258 |
pent | -0.240 |
Token | some |
Token ID | 617 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
erg | +0.943 |
NL | +0.910 |
recomp | +0.882 |
cape | +0.875 |
ropolitan | +0.873 |
Neg logit contributions | |
kson | -1.081 |
Wiz | -1.028 |
Wolf | -1.026 |
ATK | -0.994 |
pent | -0.925 |
Token | dec |
Token ID | 875 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
kson | +0.347 |
Wolf | +0.332 |
Wiz | +0.331 |
ATK | +0.316 |
pent | +0.294 |
Neg logit contributions | |
erg | -0.338 |
NL | -0.332 |
ropolitan | -0.319 |
recomp | -0.318 |
cape | -0.318 |
Token | af |
Token ID | 1878 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
erg | +7.820 |
atures | +7.160 |
NL | +7.121 |
ropolitan | +7.029 |
atorial | +6.908 |
Neg logit contributions | |
kson | -10.376 |
Wiz | -10.166 |
ATK | -9.825 |
Wolf | -9.705 |
�� | -9.482 |
Token | tea |
Token ID | 8887 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
kson | +0.586 |
Wolf | +0.560 |
Wiz | +0.559 |
ATK | +0.534 |
pent | +0.498 |
Neg logit contributions | |
erg | -0.544 |
NL | -0.533 |
recomp | -0.512 |
ropolitan | -0.511 |
cape | -0.509 |
Token | at |
Token ID | 379 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
kson | +0.752 |
Wolf | +0.719 |
Wiz | +0.716 |
ATK | +0.689 |
pent | +0.640 |
Neg logit contributions | |
erg | -0.679 |
NL | -0.662 |
ropolitan | -0.639 |
recomp | -0.636 |
cape | -0.631 |
Token | night |
Token ID | 1755 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
erg | +0.754 |
NL | +0.730 |
recomp | +0.705 |
ropolitan | +0.700 |
cape | +0.699 |
Neg logit contributions | |
kson | -0.872 |
Wiz | -0.828 |
Wolf | -0.827 |
ATK | -0.799 |
pent | -0.746 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
erg | +3.032 |
NL | +2.906 |
cape | +2.832 |
recomp | +2.808 |
Clarkson | +2.741 |
Neg logit contributions | |
kson | -4.046 |
Wiz | -3.847 |
Wolf | -3.789 |
ATK | -3.775 |
pent | -3.481 |
Token | , |
Token ID | 11 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
erg | +1.617 |
NL | +1.559 |
cape | +1.526 |
recomp | +1.507 |
ropolitan | +1.495 |
Neg logit contributions | |
kson | -1.969 |
Wiz | -1.884 |
Wolf | -1.880 |
ATK | -1.827 |
pent | -1.702 |
Token | would |
Token ID | 561 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
erg | +0.062 |
NL | +0.061 |
recomp | +0.059 |
ropolitan | +0.058 |
cape | +0.058 |
Neg logit contributions | |
kson | -0.065 |
Wolf | -0.062 |
Wiz | -0.062 |
ATK | -0.060 |
pent | -0.055 |
Token | not |
Token ID | 407 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
kson | +0.162 |
Wolf | +0.155 |
Wiz | +0.154 |
ATK | +0.149 |
pent | +0.138 |
Neg logit contributions | |
erg | -0.154 |
NL | -0.150 |
ropolitan | -0.144 |
cape | -0.143 |
recomp | -0.143 |
Token | work |
Token ID | 670 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
kson | +1.270 |
Wolf | +1.226 |
Wiz | +1.217 |
ATK | +1.182 |
pent | +1.086 |
Neg logit contributions | |
erg | -1.215 |
NL | -1.188 |
ropolitan | -1.139 |
cape | -1.120 |
zig | -1.119 |
Token | " |
Token ID | 366 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
kson | +1.872 |
Wolf | +1.824 |
Wiz | +1.796 |
ATK | +1.721 |
pent | +1.594 |
Neg logit contributions | |
erg | -1.826 |
NL | -1.787 |
ropolitan | -1.738 |
zig | -1.687 |
recomp | -1.685 |
Token | pro |
Token ID | 1676 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
erg | +1.513 |
NL | +1.461 |
cape | +1.417 |
recomp | +1.409 |
ropolitan | +1.396 |
Neg logit contributions | |
kson | -1.419 |
Wiz | -1.345 |
Wolf | -1.341 |
ATK | -1.292 |
pent | -1.175 |
Token | per |
Token ID | 525 |
Feature activation | -6.78e+00 |
Pos logit contributions | |
erg | +6.886 |
vision | +6.467 |
cape | +6.426 |
NL | +6.358 |
recomp | +6.267 |
Neg logit contributions | |
kson | -11.597 |
�� | -10.785 |
Wolf | -10.774 |
Wiz | -10.739 |
ATK | -10.234 |
Token | ly |
Token ID | 306 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
erg | +3.939 |
recomp | +3.769 |
NL | +3.747 |
cape | +3.698 |
ropolitan | +3.554 |
Neg logit contributions | |
kson | -5.157 |
Wiz | -4.868 |
Wolf | -4.755 |
ATK | -4.664 |
�� | -4.367 |
Token | " |
Token ID | 1 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
erg | +2.480 |
NL | +2.332 |
recomp | +2.331 |
cape | +2.311 |
ropolitan | +2.243 |
Neg logit contributions | |
kson | -3.881 |
Wiz | -3.738 |
Wolf | -3.686 |
ATK | -3.601 |
pent | -3.377 |
Token | with |
Token ID | 351 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
kson | +0.637 |
Wolf | +0.610 |
Wiz | +0.607 |
ATK | +0.583 |
pent | +0.542 |
Neg logit contributions | |
erg | -0.617 |
NL | -0.601 |
ropolitan | -0.580 |
recomp | -0.575 |
cape | -0.574 |
Token | the |
Token ID | 262 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
erg | +0.310 |
NL | +0.301 |
recomp | +0.290 |
ropolitan | +0.289 |
cape | +0.288 |
Neg logit contributions | |
kson | -0.364 |
Wolf | -0.347 |
Wiz | -0.347 |
ATK | -0.335 |
pent | -0.312 |
Token | , |
Token ID | 11 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
erg | +1.931 |
NL | +1.865 |
recomp | +1.804 |
cape | +1.788 |
ropolitan | +1.767 |
Neg logit contributions | |
kson | -2.567 |
Wiz | -2.448 |
Wolf | -2.424 |
ATK | -2.374 |
pent | -2.224 |
Token | two |
Token ID | 734 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
erg | +0.619 |
NL | +0.601 |
recomp | +0.580 |
cape | +0.575 |
ropolitan | +0.574 |
Neg logit contributions | |
kson | -0.722 |
Wiz | -0.688 |
Wolf | -0.686 |
ATK | -0.663 |
pent | -0.620 |
Token | constituencies |
Token ID | 43742 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
kson | +1.897 |
Wolf | +1.839 |
Wiz | +1.811 |
ATK | +1.735 |
pent | +1.592 |
Neg logit contributions | |
erg | -2.093 |
NL | -2.041 |
ropolitan | -2.002 |
cape | -1.990 |
recomp | -1.981 |
Token | that |
Token ID | 326 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
kson | +0.173 |
Wolf | +0.165 |
Wiz | +0.164 |
ATK | +0.158 |
pent | +0.146 |
Neg logit contributions | |
erg | -0.181 |
NL | -0.175 |
recomp | -0.170 |
ropolitan | -0.170 |
cape | -0.169 |
Token | Democrats |
Token ID | 4956 |
Feature activation | +6.67e+00 |
Pos logit contributions | |
kson | +2.897 |
Wolf | +2.856 |
Wiz | +2.779 |
ATK | +2.667 |
pent | +2.367 |
Neg logit contributions | |
erg | -3.271 |
NL | -3.172 |
ropolitan | -3.150 |
recomp | -3.104 |
llular | -3.075 |
Token | are |
Token ID | 389 |
Feature activation | +8.96e+00 |
Pos logit contributions | |
kson | +4.033 |
Wolf | +3.992 |
ATK | +3.837 |
Wiz | +3.832 |
restriction | +3.498 |
Neg logit contributions | |
NL | -4.644 |
erg | -4.622 |
ropolitan | -4.502 |
zig | -4.432 |
llular | -4.415 |
Token | desperately |
Token ID | 16459 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
kson | +5.375 |
Wolf | +5.322 |
Wiz | +5.117 |
ATK | +5.083 |
stat | +4.713 |
Neg logit contributions | |
ropolitan | -6.194 |
NL | -6.150 |
erg | -6.086 |
llular | -6.002 |
zig | -5.781 |
Token | trying |
Token ID | 2111 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
Wolf | +5.677 |
kson | +5.523 |
ATK | +5.359 |
Wiz | +5.140 |
restriction | +4.910 |
Neg logit contributions | |
NL | -9.578 |
ropolitan | -9.430 |
llular | -9.205 |
erg | -9.074 |
abre | -8.912 |
Token | to |
Token ID | 284 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
kson | +3.212 |
Wolf | +3.132 |
Wiz | +3.005 |
ATK | +2.972 |
pent | +2.693 |
Neg logit contributions | |
erg | -4.158 |
NL | -4.087 |
ropolitan | -3.944 |
cape | -3.897 |
recomp | -3.870 |
Token | reach |
Token ID | 3151 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
kson | +4.023 |
Wolf | +3.996 |
Wiz | +3.821 |
ATK | +3.811 |
restriction | +3.408 |
Neg logit contributions | |
erg | -4.653 |
NL | -4.614 |
ropolitan | -4.436 |
zig | -4.353 |
llular | -4.336 |
Token | in |
Token ID | 287 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
kson | +4.047 |
Wolf | +3.984 |
Wiz | +3.860 |
ATK | +3.732 |
pent | +3.474 |
Neg logit contributions | |
erg | -4.575 |
NL | -4.503 |
ropolitan | -4.314 |
cape | -4.303 |
recomp | -4.297 |
Token | 1928 |
Token ID | 35768 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
erg | +0.807 |
NL | +0.784 |
recomp | +0.758 |
cape | +0.753 |
ropolitan | +0.750 |
Neg logit contributions | |
kson | -0.994 |
Wiz | -0.940 |
Wolf | -0.937 |
ATK | -0.910 |
pent | -0.853 |
Token | to |
Token ID | 284 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
erg | +1.574 |
NL | +1.539 |
recomp | +1.494 |
cape | +1.485 |
ropolitan | +1.475 |
Neg logit contributions | |
kson | -1.763 |
Wiz | -1.669 |
Wolf | -1.655 |
ATK | -1.603 |
pent | -1.481 |
Token | a |
Token ID | 257 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
kson | +2.228 |
Wolf | +2.158 |
Wiz | +2.135 |
ATK | +2.055 |
pent | +1.885 |
Neg logit contributions | |
erg | -2.226 |
NL | -2.171 |
ropolitan | -2.119 |
cape | -2.066 |
recomp | -2.056 |
Token | membership |
Token ID | 9931 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
erg | +1.458 |
NL | +1.416 |
recomp | +1.383 |
cape | +1.368 |
ropolitan | +1.359 |
Neg logit contributions | |
kson | -1.384 |
Wiz | -1.304 |
Wolf | -1.298 |
ATK | -1.257 |
pent | -1.160 |
Token | of |
Token ID | 286 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
erg | +1.227 |
NL | +1.182 |
recomp | +1.152 |
cape | +1.147 |
ropolitan | +1.132 |
Neg logit contributions | |
kson | -1.352 |
Wiz | -1.281 |
Wolf | -1.275 |
ATK | -1.228 |
pent | -1.144 |
Token | almost |
Token ID | 2048 |
Feature activation | +9.23e+00 |
Pos logit contributions | |
kson | +2.389 |
Wolf | +2.310 |
Wiz | +2.284 |
ATK | +2.196 |
pent | +2.012 |
Neg logit contributions | |
erg | -2.434 |
NL | -2.389 |
ropolitan | -2.325 |
cape | -2.281 |
recomp | -2.258 |
Token | 17 |
Token ID | 1596 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Wolf | +5.318 |
kson | +5.141 |
Wiz | +5.107 |
ATK | +4.904 |
stat | +4.416 |
Neg logit contributions | |
erg | -6.767 |
ropolitan | -6.647 |
NL | -6.577 |
llular | -6.291 |
abre | -6.273 |
Token | , |
Token ID | 11 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
kson | +1.060 |
Wolf | +1.015 |
Wiz | +1.010 |
ATK | +0.975 |
pent | +0.910 |
Neg logit contributions | |
erg | -0.978 |
NL | -0.947 |
recomp | -0.924 |
cape | -0.914 |
ropolitan | -0.914 |
Token | 000 |
Token ID | 830 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
erg | +1.494 |
NL | +1.444 |
recomp | +1.387 |
cape | +1.386 |
ropolitan | +1.372 |
Neg logit contributions | |
kson | -2.155 |
Wiz | -2.076 |
Wolf | -2.063 |
ATK | -1.997 |
pent | -1.863 |
Token | by |
Token ID | 416 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
erg | +0.856 |
NL | +0.828 |
recomp | +0.801 |
cape | +0.799 |
ropolitan | +0.795 |
Neg logit contributions | |
kson | -0.953 |
Wiz | -0.907 |
Wolf | -0.902 |
ATK | -0.873 |
pent | -0.805 |
Token | 1932 |
Token ID | 32471 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
erg | +2.465 |
NL | +2.401 |
recomp | +2.342 |
Clarkson | +2.325 |
cape | +2.321 |
Neg logit contributions | |
kson | -3.283 |
Wiz | -3.031 |
Wolf | -2.993 |
ATK | -2.938 |
pent | -2.814 |
Token | s |
Token ID | 82 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
kson | +2.143 |
Wolf | +2.033 |
Wiz | +2.029 |
ATK | +1.950 |
pent | +1.837 |
Neg logit contributions | |
erg | -2.092 |
NL | -2.048 |
recomp | -1.990 |
ropolitan | -1.982 |
cape | -1.960 |
Token | story |
Token ID | 1621 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
erg | +2.554 |
NL | +2.473 |
recomp | +2.426 |
cape | +2.400 |
Clarkson | +2.365 |
Neg logit contributions | |
kson | -2.813 |
Wiz | -2.653 |
Wolf | -2.617 |
ATK | -2.543 |
pent | -2.379 |
Token | of |
Token ID | 286 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
kson | +1.016 |
Wolf | +0.977 |
Wiz | +0.972 |
ATK | +0.930 |
pent | +0.864 |
Neg logit contributions | |
erg | -1.000 |
NL | -0.971 |
ropolitan | -0.937 |
recomp | -0.931 |
cape | -0.925 |
Token | how |
Token ID | 703 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
kson | +0.315 |
Wolf | +0.300 |
Wiz | +0.299 |
ATK | +0.286 |
pent | +0.263 |
Neg logit contributions | |
erg | -0.368 |
NL | -0.358 |
ropolitan | -0.346 |
recomp | -0.346 |
cape | -0.345 |
Token | he |
Token ID | 339 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
kson | +1.658 |
Wolf | +1.603 |
Wiz | +1.595 |
ATK | +1.525 |
pent | +1.416 |
Neg logit contributions | |
erg | -1.614 |
NL | -1.564 |
ropolitan | -1.513 |
recomp | -1.505 |
cape | -1.499 |
Token | became |
Token ID | 2627 |
Feature activation | +8.59e+00 |
Pos logit contributions | |
kson | +0.770 |
Wolf | +0.733 |
Wiz | +0.732 |
ATK | +0.701 |
pent | +0.652 |
Neg logit contributions | |
erg | -0.812 |
NL | -0.789 |
ropolitan | -0.763 |
recomp | -0.761 |
cape | -0.758 |
Token | a |
Token ID | 257 |
Feature activation | +7.15e+00 |
Pos logit contributions | |
kson | +5.227 |
Wolf | +5.200 |
Wiz | +5.155 |
ATK | +4.942 |
pent | +4.472 |
Neg logit contributions | |
erg | -6.055 |
NL | -5.720 |
ropolitan | -5.685 |
recomp | -5.568 |
cape | -5.524 |
Token | Kindle |
Token ID | 27114 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
Wolf | +4.504 |
kson | +4.468 |
Wiz | +4.413 |
ATK | +4.178 |
pent | +3.874 |
Neg logit contributions | |
erg | -4.962 |
NL | -4.766 |
ropolitan | -4.610 |
recomp | -4.570 |
cape | -4.564 |
Token | Gold |
Token ID | 3561 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
kson | +2.214 |
Wolf | +2.202 |
Wiz | +2.146 |
ATK | +2.058 |
Expedition | +1.860 |
Neg logit contributions | |
erg | -2.559 |
NL | -2.481 |
recomp | -2.427 |
ropolitan | -2.425 |
cape | -2.408 |
Token | Rus |
Token ID | 9223 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
erg | +1.973 |
NL | +1.899 |
recomp | +1.818 |
ropolitan | +1.814 |
cape | +1.799 |
Neg logit contributions | |
kson | -3.027 |
Wiz | -2.855 |
Wolf | -2.812 |
ATK | -2.759 |
pent | -2.655 |
Token | her |
Token ID | 372 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
erg | +2.921 |
NL | +2.812 |
cape | +2.744 |
ropolitan | +2.737 |
recomp | +2.697 |
Neg logit contributions | |
kson | -1.707 |
Wiz | -1.623 |
Wolf | -1.590 |
ATK | -1.514 |
pent | -1.350 |
Token | le |
Token ID | 293 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
erg | +1.102 |
NL | +1.044 |
ropolitan | +0.993 |
cape | +0.973 |
recomp | +0.972 |
Neg logit contributions | |
kson | -2.092 |
Wiz | -2.000 |
Wolf | -1.982 |
ATK | -1.942 |
pent | -1.830 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
erg | +3.333 |
NL | +3.237 |
recomp | +3.171 |
Clarkson | +3.163 |
cape | +3.148 |
Neg logit contributions | |
kson | -4.161 |
Wiz | -3.922 |
Wolf | -3.848 |
ATK | -3.802 |
pent | -3.630 |
Token |
|
Token ID | 198 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
kson | +0.197 |
Wolf | +0.188 |
Wiz | +0.188 |
ATK | +0.181 |
pent | +0.168 |
Neg logit contributions | |
erg | -0.174 |
NL | -0.169 |
recomp | -0.164 |
ropolitan | -0.163 |
cape | -0.162 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
kson | +0.112 |
Wolf | +0.107 |
Wiz | +0.107 |
ATK | +0.103 |
pent | +0.096 |
Neg logit contributions | |
erg | -0.099 |
NL | -0.096 |
recomp | -0.093 |
ropolitan | -0.093 |
cape | -0.092 |
Token | Sen |
Token ID | 10445 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
kson | +0.797 |
Wolf | +0.763 |
Wiz | +0.760 |
ATK | +0.729 |
pent | +0.683 |
Neg logit contributions | |
erg | -0.735 |
NL | -0.705 |
recomp | -0.698 |
ropolitan | -0.696 |
cape | -0.685 |
Token | . |
Token ID | 13 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
kson | +4.365 |
Wolf | +4.306 |
Wiz | +4.191 |
ATK | +4.020 |
pent | +3.822 |
Neg logit contributions | |
erg | -3.997 |
NL | -3.801 |
recomp | -3.801 |
ropolitan | -3.735 |
cape | -3.720 |
Token | Cruz |
Token ID | 8742 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Wolf | +4.256 |
kson | +4.204 |
Wiz | +4.053 |
ATK | +3.885 |
pent | +3.330 |
Neg logit contributions | |
erg | -7.087 |
ropolitan | -6.776 |
recomp | -6.759 |
cape | -6.643 |
zig | -6.618 |
Token | , |
Token ID | 11 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
kson | +1.320 |
Wolf | +1.272 |
Wiz | +1.262 |
ATK | +1.204 |
pent | +1.111 |
Neg logit contributions | |
erg | -1.389 |
NL | -1.346 |
ropolitan | -1.314 |
cape | -1.302 |
recomp | -1.300 |
Token | in |
Token ID | 287 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
erg | +0.542 |
NL | +0.527 |
recomp | +0.509 |
cape | +0.505 |
ropolitan | +0.505 |
Neg logit contributions | |
kson | -0.597 |
Wiz | -0.567 |
Wolf | -0.566 |
ATK | -0.546 |
pent | -0.510 |
Token | his |
Token ID | 465 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
kson | +0.629 |
Wolf | +0.603 |
Wiz | +0.601 |
ATK | +0.577 |
pent | +0.533 |
Neg logit contributions | |
erg | -0.610 |
NL | -0.594 |
ropolitan | -0.573 |
cape | -0.572 |
recomp | -0.570 |
Token | infinite |
Token ID | 15541 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
erg | +1.907 |
NL | +1.849 |
recomp | +1.808 |
cape | +1.775 |
ropolitan | +1.770 |
Neg logit contributions | |
kson | -1.980 |
Wiz | -1.879 |
Wolf | -1.857 |
ATK | -1.800 |
pent | -1.695 |
Token | break |
Token ID | 2270 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Wolf | +2.973 |
kson | +2.959 |
Wiz | +2.885 |
ATK | +2.721 |
restriction | +2.473 |
Neg logit contributions | |
erg | -4.025 |
NL | -3.933 |
ropolitan | -3.889 |
zig | -3.776 |
cape | -3.773 |
Token | } |
Token ID | 1782 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
erg | +0.561 |
NL | +0.539 |
recomp | +0.517 |
cape | +0.510 |
ropolitan | +0.510 |
Neg logit contributions | |
kson | -0.982 |
Wiz | -0.944 |
Wolf | -0.943 |
ATK | -0.915 |
pent | -0.866 |
Token | } |
Token ID | 1782 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
kson | +2.226 |
Wolf | +2.153 |
Wiz | +2.146 |
ATK | +2.064 |
pent | +1.937 |
Neg logit contributions | |
erg | -1.476 |
NL | -1.418 |
ropolitan | -1.362 |
cape | -1.353 |
recomp | -1.349 |
Token | End |
Token ID | 5268 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
kson | +3.950 |
Wolf | +3.877 |
Wiz | +3.845 |
ATK | +3.663 |
Expedition | +3.347 |
Neg logit contributions | |
erg | -3.663 |
NL | -3.535 |
ropolitan | -3.491 |
zig | -3.397 |
cape | -3.388 |
Token | { |
Token ID | 1391 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
kson | +2.032 |
Wolf | +1.960 |
Wiz | +1.945 |
ATK | +1.855 |
pent | +1.715 |
Neg logit contributions | |
erg | -2.087 |
NL | -2.024 |
ropolitan | -1.967 |
recomp | -1.962 |
cape | -1.955 |
Token | Try |
Token ID | 9993 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
kson | +2.938 |
Wolf | +2.848 |
Wiz | +2.828 |
ATK | +2.702 |
pent | +2.486 |
Neg logit contributions | |
erg | -2.815 |
NL | -2.729 |
ropolitan | -2.661 |
cape | -2.616 |
zig | -2.614 |
Token | { |
Token ID | 1391 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
Wolf | +5.073 |
Wiz | +4.920 |
kson | +4.905 |
ATK | +4.576 |
pent | +4.074 |
Neg logit contributions | |
erg | -8.345 |
ropolitan | -8.033 |
zig | -8.001 |
NL | -7.933 |
cape | -7.908 |
Token | # |
Token ID | 1303 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
kson | +3.817 |
Wolf | +3.750 |
Wiz | +3.705 |
ATK | +3.539 |
pent | +3.229 |
Neg logit contributions | |
erg | -4.027 |
NL | -3.911 |
ropolitan | -3.829 |
zig | -3.774 |
cape | -3.762 |
Token | Close |
Token ID | 13872 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
kson | +0.122 |
Wolf | +0.117 |
Wiz | +0.116 |
ATK | +0.112 |
pent | +0.104 |
Neg logit contributions | |
erg | -0.120 |
NL | -0.116 |
recomp | -0.112 |
ropolitan | -0.112 |
cape | -0.112 |
Token | Graphics |
Token ID | 19840 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
kson | +2.150 |
Wolf | +2.100 |
Wiz | +2.085 |
ATK | +1.981 |
pent | +1.826 |
Neg logit contributions | |
erg | -2.209 |
NL | -2.168 |
ropolitan | -2.093 |
recomp | -2.059 |
Clarkson | -2.051 |
Token | $ |
Token ID | 720 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
kson | +1.528 |
Wolf | +1.469 |
Wiz | +1.467 |
ATK | +1.397 |
pent | +1.291 |
Neg logit contributions | |
erg | -1.530 |
NL | -1.494 |
ropolitan | -1.444 |
recomp | -1.436 |
zig | -1.418 |
Token | , |
Token ID | 837 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
erg | +1.982 |
NL | +1.920 |
recomp | +1.801 |
cape | +1.797 |
ropolitan | +1.768 |
Neg logit contributions | |
kson | -3.312 |
Wiz | -3.168 |
Wolf | -3.137 |
ATK | -3.027 |
pent | -2.929 |
Token | T |
Token ID | 309 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
kson | +1.183 |
Wolf | +1.145 |
Wiz | +1.137 |
ATK | +1.085 |
pent | +0.946 |
Neg logit contributions | |
erg | -1.969 |
NL | -1.912 |
ropolitan | -1.881 |
cape | -1.868 |
recomp | -1.867 |
Token | > |
Token ID | 1875 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
erg | +2.318 |
NL | +2.252 |
recomp | +2.081 |
Clarkson | +2.046 |
cape | +2.042 |
Neg logit contributions | |
kson | -5.580 |
Wiz | -5.393 |
Wolf | -5.360 |
ATK | -5.202 |
pent | -4.982 |
Token | { |
Token ID | 1391 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
kson | +1.070 |
Wolf | +1.024 |
Wiz | +1.015 |
ATK | +0.979 |
pent | +0.878 |
Neg logit contributions | |
erg | -1.379 |
NL | -1.343 |
ropolitan | -1.317 |
recomp | -1.310 |
cape | -1.296 |
Token | ... |
Token ID | 2644 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
erg | +0.500 |
NL | +0.480 |
recomp | +0.462 |
cape | +0.456 |
ropolitan | +0.455 |
Neg logit contributions | |
kson | -0.790 |
Wiz | -0.757 |
Wolf | -0.754 |
ATK | -0.732 |
pent | -0.691 |
Token | } |
Token ID | 1782 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
erg | +0.949 |
NL | +0.907 |
recomp | +0.870 |
cape | +0.856 |
ropolitan | +0.850 |
Neg logit contributions | |
kson | -1.718 |
Wiz | -1.654 |
Wolf | -1.643 |
ATK | -1.600 |
pent | -1.512 |
Token | impl |
Token ID | 4114 |
Feature activation | -8.18e+00 |
Pos logit contributions | |
kson | +2.544 |
Wolf | +2.520 |
Wiz | +2.465 |
ATK | +2.367 |
pent | +2.187 |
Neg logit contributions | |
erg | -2.550 |
NL | -2.501 |
ropolitan | -2.432 |
cape | -2.405 |
recomp | -2.394 |
Token | < |
Token ID | 1279 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
erg | +2.853 |
NL | +2.740 |
cape | +2.479 |
recomp | +2.431 |
DOT | +2.426 |
Neg logit contributions | |
kson | -8.078 |
Wiz | -7.509 |
Wolf | -7.425 |
ATK | -7.299 |
�� | -7.163 |
Token | ' |
Token ID | 705 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
kson | +3.103 |
Wolf | +3.040 |
Wiz | +2.986 |
ATK | +2.872 |
pent | +2.636 |
Neg logit contributions | |
erg | -3.547 |
NL | -3.402 |
cape | -3.334 |
recomp | -3.328 |
ropolitan | -3.319 |
Token | a |
Token ID | 64 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
kson | +1.333 |
Wolf | +1.271 |
Wiz | +1.268 |
ATK | +1.220 |
pent | +1.131 |
Neg logit contributions | |
erg | -1.494 |
NL | -1.462 |
recomp | -1.434 |
ropolitan | -1.430 |
Clarkson | -1.410 |
Token | , |
Token ID | 837 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
erg | +1.894 |
NL | +1.833 |
recomp | +1.735 |
cape | +1.724 |
ropolitan | +1.693 |
Neg logit contributions | |
kson | -3.120 |
Wiz | -2.974 |
Wolf | -2.935 |
ATK | -2.838 |
pent | -2.738 |
Token | in |
Token ID | 287 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
kson | +0.605 |
Wolf | +0.580 |
Wiz | +0.578 |
ATK | +0.553 |
pent | +0.510 |
Neg logit contributions | |
erg | -0.624 |
NL | -0.606 |
recomp | -0.587 |
ropolitan | -0.587 |
cape | -0.583 |
Token | which |
Token ID | 543 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
erg | +1.497 |
NL | +1.440 |
recomp | +1.391 |
ropolitan | +1.374 |
cape | +1.373 |
Neg logit contributions | |
kson | -2.076 |
Wiz | -1.970 |
Wolf | -1.959 |
ATK | -1.916 |
pent | -1.801 |
Token | his |
Token ID | 465 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
erg | +1.373 |
NL | +1.332 |
recomp | +1.286 |
cape | +1.276 |
ropolitan | +1.276 |
Neg logit contributions | |
kson | -1.577 |
Wiz | -1.491 |
Wolf | -1.488 |
ATK | -1.448 |
pent | -1.357 |
Token | administration |
Token ID | 3662 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
erg | +2.744 |
NL | +2.635 |
recomp | +2.593 |
cape | +2.556 |
ropolitan | +2.533 |
Neg logit contributions | |
kson | -2.815 |
Wiz | -2.644 |
Wolf | -2.621 |
ATK | -2.574 |
pent | -2.403 |
Token | has |
Token ID | 468 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
kson | +0.988 |
Wolf | +0.948 |
Wiz | +0.944 |
ATK | +0.905 |
pent | +0.841 |
Neg logit contributions | |
erg | -0.974 |
NL | -0.952 |
ropolitan | -0.918 |
recomp | -0.911 |
cape | -0.906 |
Token | plainly |
Token ID | 30723 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
erg | +0.273 |
NL | +0.265 |
recomp | +0.256 |
ropolitan | +0.255 |
cape | +0.254 |
Neg logit contributions | |
kson | -0.290 |
Wolf | -0.276 |
Wiz | -0.276 |
ATK | -0.265 |
pent | -0.247 |
Token | , |
Token ID | 11 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
erg | +0.121 |
NL | +0.118 |
recomp | +0.113 |
ropolitan | +0.113 |
cape | +0.113 |
Neg logit contributions | |
kson | -0.139 |
Wolf | -0.133 |
Wiz | -0.133 |
ATK | -0.128 |
pent | -0.119 |
Token | if |
Token ID | 611 |
Feature activation | -7.28e+00 |
Pos logit contributions | |
erg | +1.585 |
NL | +1.520 |
recomp | +1.485 |
cape | +1.471 |
ropolitan | +1.454 |
Neg logit contributions | |
kson | -1.890 |
Wiz | -1.790 |
Wolf | -1.778 |
ATK | -1.732 |
pent | -1.607 |
Token | quietly |
Token ID | 12703 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
erg | +4.205 |
recomp | +3.962 |
NL | +3.958 |
Clarkson | +3.829 |
cape | +3.799 |
Neg logit contributions | |
kson | -5.535 |
Wiz | -5.182 |
ATK | -5.130 |
Wolf | -5.117 |
pent | -4.753 |
Token | , |
Token ID | 11 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
erg | +1.580 |
NL | +1.522 |
recomp | +1.478 |
cape | +1.460 |
ropolitan | +1.453 |
Neg logit contributions | |
kson | -1.943 |
Wiz | -1.852 |
Wolf | -1.846 |
ATK | -1.796 |
pent | -1.671 |
Token | failed |
Token ID | 4054 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
kson | +0.436 |
Wolf | +0.418 |
Wiz | +0.416 |
ATK | +0.399 |
pent | +0.371 |
Neg logit contributions | |
erg | -0.417 |
NL | -0.406 |
ropolitan | -0.393 |
recomp | -0.389 |
cape | -0.387 |
Token | The |
Token ID | 383 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
erg | +0.072 |
NL | +0.070 |
recomp | +0.068 |
ropolitan | +0.067 |
cape | +0.067 |
Neg logit contributions | |
kson | -0.082 |
Wiz | -0.078 |
Wolf | -0.078 |
ATK | -0.076 |
pent | -0.070 |
Token | j |
Token ID | 474 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
kson | +0.278 |
Wolf | +0.266 |
Wiz | +0.265 |
ATK | +0.255 |
pent | +0.236 |
Neg logit contributions | |
erg | -0.267 |
NL | -0.259 |
ropolitan | -0.251 |
recomp | -0.250 |
cape | -0.250 |
Token | pe |
Token ID | 431 |
Feature activation | -6.50e+00 |
Pos logit contributions | |
erg | +1.817 |
NL | +1.751 |
recomp | +1.674 |
cape | +1.673 |
ropolitan | +1.664 |
Neg logit contributions | |
kson | -2.000 |
Wiz | -1.923 |
Wolf | -1.911 |
ATK | -1.841 |
pent | -1.710 |
Token | gs |
Token ID | 14542 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
erg | +3.089 |
NL | +2.857 |
recomp | +2.847 |
cape | +2.703 |
Clarkson | +2.616 |
Neg logit contributions | |
kson | -5.599 |
Wiz | -5.492 |
Wolf | -5.383 |
ATK | -5.242 |
pent | -4.930 |
Token | look |
Token ID | 804 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
erg | +0.737 |
NL | +0.714 |
recomp | +0.694 |
cape | +0.690 |
ropolitan | +0.686 |
Neg logit contributions | |
kson | -0.778 |
Wiz | -0.740 |
Wolf | -0.737 |
ATK | -0.708 |
pent | -0.658 |
Token | pretty |
Token ID | 2495 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
kson | +3.473 |
Wolf | +3.405 |
Wiz | +3.341 |
ATK | +3.189 |
restriction | +2.898 |
Neg logit contributions | |
erg | -3.365 |
NL | -3.286 |
ropolitan | -3.275 |
cape | -3.143 |
llular | -3.095 |
Token | good |
Token ID | 922 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
kson | +1.845 |
Wolf | +1.791 |
Wiz | +1.773 |
ATK | +1.702 |
pent | +1.571 |
Neg logit contributions | |
erg | -1.606 |
NL | -1.568 |
ropolitan | -1.539 |
cape | -1.503 |
recomp | -1.482 |
Token | , |
Token ID | 11 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
kson | +0.473 |
Wolf | +0.454 |
Wiz | +0.452 |
ATK | +0.435 |
pent | +0.404 |
Neg logit contributions | |
erg | -0.436 |
NL | -0.424 |
ropolitan | -0.409 |
recomp | -0.407 |
cape | -0.406 |
Token | but |
Token ID | 475 |
Feature activation | +8.72e-03 |
Pos logit contributions | |
kson | +1.417 |
Wolf | +1.370 |
Wiz | +1.359 |
ATK | +1.308 |
pent | +1.209 |
Neg logit contributions | |
erg | -1.320 |
NL | -1.285 |
ropolitan | -1.247 |
cape | -1.231 |
recomp | -1.226 |
Token | the |
Token ID | 262 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
kson | +0.006 |
Wolf | +0.006 |
Wiz | +0.006 |
ATK | +0.006 |
pent | +0.005 |
Neg logit contributions | |
erg | -0.006 |
NL | -0.006 |
recomp | -0.005 |
ropolitan | -0.005 |
cape | -0.005 |
Token | raw |
Token ID | 8246 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
erg | +1.391 |
NL | +1.345 |
recomp | +1.313 |
cape | +1.292 |
ropolitan | +1.282 |
Neg logit contributions | |
kson | -1.436 |
Wiz | -1.355 |
Wolf | -1.350 |
ATK | -1.301 |
pent | -1.214 |
Token | The |
Token ID | 464 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
kson | +0.519 |
Wolf | +0.495 |
Wiz | +0.494 |
ATK | +0.475 |
pent | +0.446 |
Neg logit contributions | |
erg | -0.475 |
NL | -0.458 |
recomp | -0.450 |
ropolitan | -0.446 |
cape | -0.443 |
Token | buildings |
Token ID | 6832 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
kson | +1.432 |
Wolf | +1.374 |
Wiz | +1.362 |
ATK | +1.313 |
pent | +1.215 |
Neg logit contributions | |
erg | -1.457 |
NL | -1.416 |
cape | -1.377 |
ropolitan | -1.364 |
recomp | -1.361 |
Token | range |
Token ID | 2837 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
kson | +2.730 |
Wolf | +2.658 |
Wiz | +2.610 |
ATK | +2.546 |
pent | +2.319 |
Neg logit contributions | |
erg | -3.115 |
NL | -3.037 |
ropolitan | -2.917 |
recomp | -2.909 |
zig | -2.908 |
Token | from |
Token ID | 422 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
kson | +1.389 |
Wolf | +1.321 |
Wiz | +1.311 |
ATK | +1.262 |
pent | +1.170 |
Neg logit contributions | |
erg | -1.513 |
NL | -1.478 |
recomp | -1.428 |
cape | -1.424 |
ropolitan | -1.416 |
Token | refurb |
Token ID | 37969 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
erg | +0.073 |
NL | +0.071 |
recomp | +0.069 |
ropolitan | +0.068 |
cape | +0.068 |
Neg logit contributions | |
kson | -0.077 |
Wolf | -0.073 |
Wiz | -0.073 |
ATK | -0.070 |
pent | -0.065 |
Token | ished |
Token ID | 1348 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
erg | +0.194 |
NL | +0.188 |
recomp | +0.183 |
ropolitan | +0.182 |
cape | +0.182 |
Neg logit contributions | |
kson | -0.173 |
Wiz | -0.164 |
Wolf | -0.164 |
ATK | -0.157 |
pent | -0.145 |
Token | 1960 |
Token ID | 9507 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
kson | +0.593 |
Wolf | +0.566 |
Wiz | +0.565 |
ATK | +0.542 |
pent | +0.501 |
Neg logit contributions | |
erg | -0.596 |
NL | -0.581 |
recomp | -0.559 |
ropolitan | -0.558 |
cape | -0.558 |
Token | s |
Token ID | 82 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
kson | +0.759 |
Wolf | +0.724 |
Wiz | +0.721 |
ATK | +0.693 |
pent | +0.646 |
Neg logit contributions | |
erg | -0.720 |
NL | -0.698 |
recomp | -0.676 |
cape | -0.674 |
ropolitan | -0.671 |
Token | tower |
Token ID | 10580 |
Feature activation | +9.78e+00 |
Pos logit contributions | |
erg | +0.476 |
NL | +0.462 |
recomp | +0.448 |
ropolitan | +0.446 |
cape | +0.445 |
Neg logit contributions | |
kson | -0.488 |
Wiz | -0.463 |
Wolf | -0.463 |
ATK | -0.445 |
pent | -0.414 |
Token | blocks |
Token ID | 7021 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
kson | +4.143 |
Wolf | +3.912 |
Wiz | +3.796 |
ATK | +3.629 |
restriction | +3.196 |
Neg logit contributions | |
erg | -8.650 |
NL | -8.523 |
recomp | -8.352 |
zig | -8.305 |
ropolitan | -8.261 |
Token | to |
Token ID | 284 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
kson | +0.783 |
Wolf | +0.748 |
Wiz | +0.747 |
ATK | +0.716 |
pent | +0.664 |
Neg logit contributions | |
erg | -0.776 |
NL | -0.754 |
recomp | -0.728 |
ropolitan | -0.727 |
cape | -0.722 |
Token | below |
Token ID | 2174 |
Feature activation | -7.34e+00 |
Pos logit contributions | |
erg | +0.106 |
NL | +0.103 |
ropolitan | +0.100 |
recomp | +0.099 |
cape | +0.099 |
Neg logit contributions | |
kson | -0.111 |
Wolf | -0.106 |
Wiz | -0.106 |
ATK | -0.102 |
pent | -0.094 |
Token | what |
Token ID | 644 |
Feature activation | -6.65e+00 |
Pos logit contributions | |
erg | +4.633 |
recomp | +4.528 |
NL | +4.495 |
Clarkson | +4.406 |
cape | +4.375 |
Neg logit contributions | |
kson | -5.206 |
Wiz | -4.862 |
Wolf | -4.667 |
ATK | -4.659 |
�� | -4.289 |
Token | some |
Token ID | 617 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
erg | +3.947 |
NL | +3.806 |
recomp | +3.787 |
Clarkson | +3.706 |
cape | +3.641 |
Neg logit contributions | |
kson | -4.975 |
Wiz | -4.687 |
Wolf | -4.575 |
ATK | -4.544 |
pent | -4.185 |
Token | of |
Token ID | 286 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
erg | +2.155 |
NL | +2.093 |
recomp | +2.027 |
cape | +2.000 |
ropolitan | +1.986 |
Neg logit contributions | |
kson | -2.337 |
Wiz | -2.220 |
Wolf | -2.191 |
ATK | -2.131 |
pent | -1.978 |
Token | the |
Token ID | 262 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
kson | +0.154 |
Wolf | +0.148 |
Wiz | +0.147 |
ATK | +0.142 |
pent | +0.132 |
Neg logit contributions | |
erg | -0.148 |
NL | -0.144 |
ropolitan | -0.139 |
recomp | -0.138 |
cape | -0.138 |
Token | other |
Token ID | 584 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
kson | +0.651 |
Wolf | +0.629 |
Wiz | +0.623 |
ATK | +0.599 |
pent | +0.556 |
Neg logit contributions | |
erg | -0.643 |
NL | -0.623 |
ropolitan | -0.605 |
cape | -0.600 |
recomp | -0.599 |
Token | provinces |
Token ID | 17812 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
kson | +1.612 |
Wolf | +1.576 |
Wiz | +1.540 |
ATK | +1.484 |
pent | +1.374 |
Neg logit contributions | |
erg | -1.803 |
NL | -1.741 |
ropolitan | -1.713 |
cape | -1.693 |
recomp | -1.671 |
Token | and |
Token ID | 290 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
erg | +0.896 |
NL | +0.871 |
recomp | +0.844 |
cape | +0.840 |
ropolitan | +0.837 |
Neg logit contributions | |
kson | -0.930 |
Wiz | -0.884 |
Wolf | -0.882 |
ATK | -0.848 |
pent | -0.786 |
Token | utilities |
Token ID | 20081 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
kson | +1.270 |
Wolf | +1.224 |
Wiz | +1.213 |
ATK | +1.169 |
pent | +1.080 |
Neg logit contributions | |
erg | -1.219 |
NL | -1.177 |
ropolitan | -1.139 |
cape | -1.138 |
recomp | -1.134 |
Token | are |
Token ID | 389 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
erg | +2.472 |
NL | +2.403 |
cape | +2.350 |
recomp | +2.335 |
ropolitan | +2.283 |
Neg logit contributions | |
kson | -2.877 |
Wiz | -2.722 |
Wolf | -2.685 |
ATK | -2.593 |
pent | -2.389 |
Token | paying |
Token ID | 5989 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
erg | +3.860 |
recomp | +3.788 |
NL | +3.730 |
cape | +3.700 |
Clarkson | +3.590 |
Neg logit contributions | |
kson | -4.320 |
Wiz | -4.058 |
Wolf | -3.997 |
ATK | -3.921 |
pent | -3.550 |
Token | rock |
Token ID | 3881 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
kson | +0.279 |
Wolf | +0.266 |
Wiz | +0.265 |
ATK | +0.253 |
pent | +0.232 |
Neg logit contributions | |
erg | -0.333 |
NL | -0.325 |
recomp | -0.315 |
ropolitan | -0.314 |
cape | -0.313 |
Token | - |
Token ID | 12 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
erg | +1.557 |
NL | +1.483 |
cape | +1.436 |
ropolitan | +1.426 |
recomp | +1.426 |
Neg logit contributions | |
kson | -1.950 |
Wiz | -1.852 |
Wolf | -1.844 |
ATK | -1.805 |
pent | -1.669 |
Token | wall |
Token ID | 11930 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
kson | +0.608 |
Wolf | +0.578 |
Wiz | +0.577 |
ATK | +0.551 |
pent | +0.520 |
Neg logit contributions | |
erg | -0.594 |
NL | -0.583 |
recomp | -0.568 |
ropolitan | -0.560 |
cape | -0.555 |
Token | aby |
Token ID | 3930 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
erg | +3.842 |
NL | +3.581 |
ropolitan | +3.569 |
cape | +3.558 |
zig | +3.512 |
Neg logit contributions | |
kson | -3.154 |
Wiz | -3.000 |
Wolf | -2.966 |
ATK | -2.866 |
pent | -2.598 |
Token | populations |
Token ID | 9684 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
erg | +0.902 |
NL | +0.878 |
recomp | +0.851 |
cape | +0.848 |
ropolitan | +0.847 |
Neg logit contributions | |
kson | -0.736 |
Wiz | -0.691 |
Wolf | -0.687 |
ATK | -0.662 |
pent | -0.607 |
Token | are |
Token ID | 389 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
erg | +2.680 |
NL | +2.573 |
recomp | +2.516 |
cape | +2.514 |
ropolitan | +2.455 |
Neg logit contributions | |
kson | -2.991 |
Wiz | -2.812 |
Wolf | -2.771 |
ATK | -2.700 |
pent | -2.528 |
Token | genetically |
Token ID | 20807 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
erg | +2.338 |
NL | +2.243 |
recomp | +2.183 |
cape | +2.142 |
Clarkson | +2.120 |
Neg logit contributions | |
kson | -3.437 |
Wiz | -3.242 |
Wolf | -3.204 |
ATK | -3.157 |
pent | -2.981 |
Token | and |
Token ID | 290 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
erg | +3.053 |
NL | +2.948 |
recomp | +2.887 |
cape | +2.856 |
Clarkson | +2.847 |
Neg logit contributions | |
kson | -5.034 |
Wiz | -4.779 |
Wolf | -4.709 |
ATK | -4.656 |
�� | -4.437 |
Token | morph |
Token ID | 17488 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
kson | +4.200 |
Wolf | +4.118 |
Wiz | +4.051 |
ATK | +3.871 |
stat | +3.647 |
Neg logit contributions | |
erg | -4.832 |
NL | -4.814 |
ropolitan | -4.648 |
zig | -4.622 |
recomp | -4.620 |
Token | ologically |
Token ID | 13437 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
kson | +1.832 |
Wolf | +1.768 |
Wiz | +1.757 |
ATK | +1.700 |
pent | +1.611 |
Neg logit contributions | |
erg | -1.113 |
NL | -1.082 |
recomp | -1.034 |
ropolitan | -1.030 |
cape | -1.025 |
Token | distinct |
Token ID | 7310 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
erg | +1.939 |
NL | +1.873 |
recomp | +1.828 |
cape | +1.807 |
Clarkson | +1.785 |
Neg logit contributions | |
kson | -2.886 |
Wiz | -2.752 |
Wolf | -2.712 |
ATK | -2.661 |
pent | -2.511 |
Token | that |
Token ID | 326 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
erg | +1.262 |
NL | +1.215 |
recomp | +1.182 |
cape | +1.171 |
ropolitan | +1.165 |
Neg logit contributions | |
kson | -1.368 |
Wiz | -1.299 |
Wolf | -1.290 |
ATK | -1.240 |
pent | -1.168 |
Token | I |
Token ID | 314 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
erg | +1.396 |
NL | +1.346 |
recomp | +1.299 |
cape | +1.277 |
Clarkson | +1.273 |
Neg logit contributions | |
kson | -2.120 |
Wiz | -2.022 |
Wolf | -2.014 |
ATK | -1.950 |
pent | -1.858 |
Token | think |
Token ID | 892 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
erg | +2.983 |
NL | +2.824 |
recomp | +2.730 |
ropolitan | +2.719 |
zig | +2.706 |
Neg logit contributions | |
kson | -4.403 |
Wiz | -4.283 |
Wolf | -4.200 |
ATK | -4.081 |
�� | -3.879 |
Token | reduces |
Token ID | 12850 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
erg | +1.498 |
NL | +1.451 |
recomp | +1.411 |
ropolitan | +1.391 |
cape | +1.390 |
Neg logit contributions | |
kson | -1.584 |
Wiz | -1.513 |
Wolf | -1.505 |
ATK | -1.441 |
pent | -1.341 |
Token | immersion |
Token ID | 36375 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
erg | +1.943 |
NL | +1.872 |
cape | +1.805 |
recomp | +1.799 |
ropolitan | +1.758 |
Neg logit contributions | |
kson | -2.688 |
Wiz | -2.578 |
Wolf | -2.547 |
ATK | -2.463 |
pent | -2.359 |
Token | more |
Token ID | 517 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
erg | +0.406 |
NL | +0.393 |
recomp | +0.380 |
cape | +0.377 |
ropolitan | +0.377 |
Neg logit contributions | |
kson | -0.439 |
Wiz | -0.417 |
Wolf | -0.416 |
ATK | -0.401 |
pent | -0.373 |
Token | on |
Token ID | 319 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
erg | +1.209 |
NL | +1.164 |
recomp | +1.120 |
cape | +1.113 |
ropolitan | +1.101 |
Neg logit contributions | |
kson | -1.620 |
Wiz | -1.558 |
Wolf | -1.546 |
ATK | -1.495 |
pent | -1.403 |
Token | H |
Token ID | 367 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
erg | +3.699 |
NL | +3.571 |
recomp | +3.468 |
cape | +3.426 |
Clarkson | +3.404 |
Neg logit contributions | |
kson | -5.698 |
Wiz | -5.357 |
Wolf | -5.294 |
�� | -5.293 |
ATK | -5.152 |
Token | MD |
Token ID | 12740 |
Feature activation | -6.71e+00 |
Pos logit contributions | |
erg | +3.443 |
NL | +3.352 |
cape | +2.634 |
Ga | +2.613 |
nexus | +2.610 |
Neg logit contributions | |
�� | -10.116 |
kson | -10.067 |
Wiz | -9.837 |
Wolf | -9.830 |
ATK | -9.756 |
Token | s |
Token ID | 82 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
erg | +3.604 |
NL | +3.463 |
recomp | +3.238 |
cape | +3.228 |
zig | +3.173 |
Neg logit contributions | |
kson | -5.265 |
Wiz | -5.125 |
Wolf | -5.082 |
�� | -5.009 |
ATK | -4.886 |
Token | but |
Token ID | 475 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
erg | +2.596 |
NL | +2.433 |
recomp | +2.431 |
cape | +2.381 |
Clarkson | +2.332 |
Neg logit contributions | |
kson | -4.077 |
Wiz | -3.908 |
Wolf | -3.858 |
ATK | -3.734 |
�� | -3.574 |
Token | , |
Token ID | 11 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
erg | +1.588 |
NL | +1.536 |
recomp | +1.491 |
cape | +1.476 |
ropolitan | +1.473 |
Neg logit contributions | |
kson | -1.851 |
Wiz | -1.763 |
Wolf | -1.760 |
ATK | -1.704 |
pent | -1.593 |
Token | i |
Token ID | 1312 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
erg | +0.379 |
NL | +0.368 |
recomp | +0.355 |
ropolitan | +0.354 |
cape | +0.353 |
Neg logit contributions | |
kson | -0.423 |
Wolf | -0.404 |
Wiz | -0.404 |
ATK | -0.389 |
pent | -0.362 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
erg | +2.032 |
NL | +1.987 |
cape | +1.858 |
ropolitan | +1.839 |
recomp | +1.817 |
Neg logit contributions | |
kson | -3.046 |
Wiz | -2.979 |
Wolf | -2.957 |
ATK | -2.859 |
�� | -2.729 |
Token | e |
Token ID | 68 |
Feature activation | -8.74e+00 |
Pos logit contributions | |
erg | +5.363 |
NL | +5.043 |
cape | +4.908 |
blogspot | +4.672 |
zig | +4.650 |
Neg logit contributions | |
kson | -8.584 |
Wiz | -8.497 |
�� | -8.384 |
Wolf | -8.357 |
PDATE | -8.189 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
erg | +4.161 |
NL | +4.016 |
ropolitan | +3.878 |
Clarkson | +3.750 |
recomp | +3.708 |
Neg logit contributions | |
kson | -7.330 |
Wiz | -7.098 |
Wolf | -7.044 |
ATK | -6.796 |
pent | -6.423 |
Token | around |
Token ID | 1088 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
erg | +1.836 |
NL | +1.779 |
recomp | +1.726 |
cape | +1.714 |
ropolitan | +1.708 |
Neg logit contributions | |
kson | -2.066 |
Wolf | -1.966 |
Wiz | -1.962 |
ATK | -1.896 |
pent | -1.773 |
Token | 90 |
Token ID | 4101 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
erg | +1.278 |
NL | +1.240 |
recomp | +1.202 |
cape | +1.187 |
ropolitan | +1.185 |
Neg logit contributions | |
kson | -1.470 |
Wiz | -1.398 |
Wolf | -1.398 |
ATK | -1.348 |
pent | -1.261 |
Token | % |
Token ID | 4 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
erg | +1.217 |
NL | +1.182 |
recomp | +1.132 |
ropolitan | +1.132 |
cape | +1.122 |
Neg logit contributions | |
kson | -1.674 |
Wolf | -1.600 |
Wiz | -1.599 |
ATK | -1.548 |
pent | -1.446 |
Token | of |
Token ID | 286 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
kson | +0.141 |
Wolf | +0.134 |
Wiz | +0.134 |
ATK | +0.128 |
pent | +0.119 |
Neg logit contributions | |
erg | -0.138 |
NL | -0.134 |
recomp | -0.129 |
cape | -0.128 |
ropolitan | -0.128 |
Token | times |
Token ID | 1661 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
erg | +1.535 |
NL | +1.495 |
recomp | +1.448 |
ropolitan | +1.441 |
cape | +1.426 |
Neg logit contributions | |
kson | -1.715 |
Wolf | -1.635 |
Wiz | -1.629 |
ATK | -1.573 |
pent | -1.468 |
Token | , |
Token ID | 11 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
erg | +3.251 |
NL | +3.136 |
cape | +3.059 |
Clarkson | +3.022 |
recomp | +3.010 |
Neg logit contributions | |
kson | -4.425 |
Wiz | -4.222 |
Wolf | -4.211 |
ATK | -4.100 |
pent | -3.782 |
Token | The |
Token ID | 464 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
kson | +2.912 |
Wolf | +2.836 |
Wiz | +2.780 |
ATK | +2.661 |
pent | +2.553 |
Neg logit contributions | |
erg | -2.940 |
recomp | -2.850 |
NL | -2.812 |
ropolitan | -2.795 |
cape | -2.737 |
Token | Tr |
Token ID | 833 |
Feature activation | +6.79e+00 |
Pos logit contributions | |
kson | +1.622 |
Wolf | +1.568 |
Wiz | +1.552 |
ATK | +1.464 |
pent | +1.316 |
Neg logit contributions | |
erg | -2.551 |
NL | -2.506 |
recomp | -2.442 |
cape | -2.419 |
ropolitan | -2.414 |
Token | unk |
Token ID | 2954 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
kson | +3.315 |
Wolf | +2.925 |
Wiz | +2.859 |
ATK | +2.723 |
pent | +2.638 |
Neg logit contributions | |
erg | -5.694 |
recomp | -5.686 |
NL | -5.635 |
cape | -5.500 |
Clarkson | -5.499 |
Token | " |
Token ID | 1 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
kson | +2.752 |
Wolf | +2.684 |
Wiz | +2.650 |
ATK | +2.507 |
pent | +2.364 |
Neg logit contributions | |
erg | -2.462 |
NL | -2.398 |
recomp | -2.351 |
ropolitan | -2.318 |
cape | -2.295 |
Token | re |
Token ID | 302 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
erg | +1.252 |
NL | +1.218 |
recomp | +1.181 |
cape | +1.173 |
ropolitan | +1.165 |
Neg logit contributions | |
kson | -1.300 |
Wiz | -1.232 |
Wolf | -1.230 |
ATK | -1.188 |
pent | -1.105 |
Token | opens |
Token ID | 44813 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
erg | +0.121 |
NL | +0.117 |
recomp | +0.113 |
ropolitan | +0.112 |
cape | +0.112 |
Neg logit contributions | |
kson | -0.168 |
Wolf | -0.161 |
Wiz | -0.161 |
ATK | -0.156 |
pent | -0.146 |
Token | in |
Token ID | 287 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
erg | +0.765 |
NL | +0.742 |
recomp | +0.714 |
cape | +0.713 |
ropolitan | +0.711 |
Neg logit contributions | |
kson | -0.856 |
Wiz | -0.814 |
Wolf | -0.810 |
ATK | -0.783 |
pent | -0.732 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
erg | +0.990 |
NL | +0.961 |
recomp | +0.929 |
ropolitan | +0.921 |
cape | +0.920 |
Neg logit contributions | |
kson | -1.104 |
Wiz | -1.049 |
Wolf | -1.041 |
ATK | -1.009 |
pent | -0.943 |
Token | , |
Token ID | 11 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
kson | +0.796 |
Wolf | +0.763 |
Wiz | +0.757 |
ATK | +0.729 |
pent | +0.679 |
Neg logit contributions | |
erg | -0.718 |
NL | -0.694 |
recomp | -0.674 |
ropolitan | -0.670 |
cape | -0.667 |
Token | Franklin |
Token ID | 14021 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
kson | +2.210 |
Wolf | +2.129 |
Wiz | +2.087 |
ATK | +2.009 |
pent | +1.854 |
Neg logit contributions | |
erg | -2.212 |
NL | -2.123 |
recomp | -2.092 |
ropolitan | -2.080 |
cape | -2.068 |
Token | plans |
Token ID | 3352 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
kson | +1.156 |
Wolf | +1.104 |
Wiz | +1.092 |
ATK | +1.052 |
pent | +0.964 |
Neg logit contributions | |
erg | -1.289 |
NL | -1.254 |
ropolitan | -1.221 |
recomp | -1.211 |
cape | -1.209 |
Token | � |
Token ID | 247 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
erg | +0.738 |
NL | +0.720 |
recomp | +0.700 |
ropolitan | +0.698 |
cape | +0.697 |
Neg logit contributions | |
kson | -0.516 |
Wolf | -0.486 |
Wiz | -0.485 |
ATK | -0.462 |
pent | -0.420 |
Token | t |
Token ID | 83 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
erg | +1.100 |
NL | +1.058 |
recomp | +1.016 |
cape | +1.013 |
ropolitan | +1.012 |
Neg logit contributions | |
kson | -1.481 |
Wiz | -1.421 |
Wolf | -1.418 |
ATK | -1.372 |
pent | -1.279 |
Token | do |
Token ID | 466 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
kson | +2.205 |
Wolf | +2.118 |
Wiz | +2.103 |
ATK | +2.013 |
pent | +1.893 |
Neg logit contributions | |
erg | -1.951 |
NL | -1.900 |
ropolitan | -1.843 |
recomp | -1.826 |
cape | -1.814 |
Token | it |
Token ID | 340 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
kson | +2.289 |
Wolf | +2.205 |
Wiz | +2.198 |
ATK | +2.090 |
pent | +1.949 |
Neg logit contributions | |
erg | -2.252 |
NL | -2.195 |
ropolitan | -2.160 |
recomp | -2.122 |
cape | -2.101 |
Token | . |
Token ID | 13 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
kson | +2.227 |
Wolf | +2.146 |
Wiz | +2.139 |
ATK | +2.034 |
pent | +1.910 |
Neg logit contributions | |
erg | -2.046 |
NL | -1.992 |
ropolitan | -1.928 |
recomp | -1.916 |
cape | -1.898 |
Token | This |
Token ID | 770 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
kson | +2.173 |
Wolf | +2.094 |
Wiz | +2.086 |
ATK | +1.996 |
pent | +1.847 |
Neg logit contributions | |
erg | -1.943 |
NL | -1.880 |
recomp | -1.851 |
ropolitan | -1.833 |
cape | -1.824 |
Token | is |
Token ID | 318 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
erg | +2.758 |
NL | +2.660 |
recomp | +2.533 |
zig | +2.492 |
cape | +2.486 |
Neg logit contributions | |
kson | -3.159 |
Wiz | -2.972 |
Wolf | -2.961 |
ATK | -2.916 |
pent | -2.684 |
Token | only |
Token ID | 691 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
erg | +1.941 |
NL | +1.878 |
recomp | +1.805 |
cape | +1.793 |
ropolitan | +1.771 |
Neg logit contributions | |
kson | -2.230 |
Wiz | -2.089 |
Wolf | -2.079 |
ATK | -2.023 |
pent | -1.881 |
Token | the |
Token ID | 262 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
kson | +0.459 |
Wolf | +0.439 |
Wiz | +0.438 |
ATK | +0.422 |
pent | +0.392 |
Neg logit contributions | |
erg | -0.426 |
NL | -0.414 |
ropolitan | -0.400 |
recomp | -0.400 |
cape | -0.398 |
Token | beginning |
Token ID | 3726 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
kson | +2.013 |
Wolf | +1.972 |
Wiz | +1.960 |
ATK | +1.848 |
pent | +1.642 |
Neg logit contributions | |
erg | -3.256 |
NL | -3.194 |
ropolitan | -3.159 |
cape | -3.089 |
recomp | -3.067 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
kson | +0.237 |
Wolf | +0.227 |
Wiz | +0.227 |
ATK | +0.218 |
pent | +0.204 |
Neg logit contributions | |
erg | -0.206 |
NL | -0.199 |
recomp | -0.193 |
ropolitan | -0.192 |
cape | -0.191 |
Token | � |
Token ID | 250 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
erg | +2.365 |
NL | +2.296 |
recomp | +2.220 |
cape | +2.178 |
ropolitan | +2.177 |
Neg logit contributions | |
kson | -2.244 |
Wolf | -2.134 |
Wiz | -2.111 |
ATK | -2.071 |
pent | -1.894 |
Token | really |
Token ID | 27485 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
erg | +0.334 |
NL | +0.324 |
recomp | +0.314 |
ropolitan | +0.312 |
cape | +0.312 |
Neg logit contributions | |
kson | -0.369 |
Wiz | -0.352 |
Wolf | -0.352 |
ATK | -0.338 |
pent | -0.315 |
Token | helped |
Token ID | 4193 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
kson | +4.097 |
Wolf | +3.990 |
Wiz | +3.978 |
ATK | +3.705 |
pent | +3.491 |
Neg logit contributions | |
erg | -4.642 |
NL | -4.511 |
ropolitan | -4.462 |
recomp | -4.363 |
cape | -4.325 |
Token | put |
Token ID | 1234 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
kson | +1.608 |
Wolf | +1.567 |
Wiz | +1.555 |
ATK | +1.495 |
pent | +1.383 |
Neg logit contributions | |
erg | -1.622 |
NL | -1.570 |
ropolitan | -1.520 |
cape | -1.498 |
recomp | -1.496 |
Token | [ |
Token ID | 685 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
kson | +0.098 |
Wolf | +0.093 |
Wiz | +0.093 |
ATK | +0.090 |
pent | +0.083 |
Neg logit contributions | |
erg | -0.089 |
NL | -0.087 |
recomp | -0.084 |
ropolitan | -0.083 |
cape | -0.083 |
Token | V |
Token ID | 53 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
erg | +0.734 |
NL | +0.713 |
cape | +0.684 |
recomp | +0.683 |
ropolitan | +0.682 |
Neg logit contributions | |
kson | -0.830 |
Wiz | -0.791 |
Wolf | -0.790 |
ATK | -0.763 |
pent | -0.706 |
Token | iet |
Token ID | 1155 |
Feature activation | -6.63e+00 |
Pos logit contributions | |
erg | +5.044 |
NL | +4.755 |
ropolitan | +4.101 |
cape | +3.957 |
zig | +3.925 |
Neg logit contributions | |
kson | -9.319 |
Wiz | -9.136 |
Wolf | -8.906 |
ATK | -8.764 |
�� | -8.464 |
Token | - |
Token ID | 12 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
erg | +3.814 |
NL | +3.740 |
ropolitan | +3.569 |
recomp | +3.506 |
cape | +3.482 |
Neg logit contributions | |
kson | -5.141 |
Wiz | -4.839 |
Wolf | -4.777 |
ATK | -4.658 |
pent | -4.395 |
Token | C |
Token ID | 34 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
erg | +1.974 |
NL | +1.920 |
cape | +1.806 |
ropolitan | +1.798 |
recomp | +1.768 |
Neg logit contributions | |
kson | -3.397 |
Wiz | -3.256 |
Wolf | -3.236 |
ATK | -3.172 |
pent | -2.937 |
Token | aj |
Token ID | 1228 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
kson | +1.631 |
Wolf | +1.528 |
Wiz | +1.521 |
ATK | +1.446 |
pent | +1.311 |
Neg logit contributions | |
erg | -2.525 |
NL | -2.492 |
recomp | -2.453 |
cape | -2.426 |
ropolitan | -2.410 |
Token | un |
Token ID | 403 |
Feature activation | -7.57e+00 |
Pos logit contributions | |
erg | +1.165 |
NL | +1.132 |
recomp | +1.093 |
ropolitan | +1.092 |
cape | +1.090 |
Neg logit contributions | |
kson | -1.022 |
Wiz | -0.971 |
Wolf | -0.969 |
ATK | -0.929 |
pent | -0.852 |
Token | is |
Token ID | 318 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
kson | +0.980 |
Wolf | +0.942 |
Wiz | +0.937 |
ATK | +0.900 |
pent | +0.836 |
Neg logit contributions | |
erg | -0.963 |
NL | -0.933 |
cape | -0.902 |
recomp | -0.899 |
ropolitan | -0.897 |
Token | the |
Token ID | 262 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
erg | +1.769 |
NL | +1.719 |
recomp | +1.667 |
ropolitan | +1.649 |
cape | +1.640 |
Neg logit contributions | |
kson | -2.047 |
Wiz | -1.927 |
Wolf | -1.921 |
ATK | -1.864 |
pent | -1.744 |
Token | Governor |
Token ID | 10807 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
erg | +2.689 |
NL | +2.625 |
recomp | +2.549 |
ropolitan | +2.523 |
Clarkson | +2.512 |
Neg logit contributions | |
kson | -3.179 |
Wiz | -2.961 |
Wolf | -2.955 |
ATK | -2.884 |
pent | -2.738 |
Token | - |
Token ID | 12 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
kson | +2.826 |
Wolf | +2.786 |
Wiz | +2.763 |
ATK | +2.619 |
pent | +2.447 |
Neg logit contributions | |
erg | -2.669 |
NL | -2.618 |
cape | -2.558 |
recomp | -2.528 |
ropolitan | -2.511 |
Token | General |
Token ID | 12218 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
erg | +3.004 |
NL | +2.916 |
ropolitan | +2.835 |
cape | +2.810 |
recomp | +2.794 |
Neg logit contributions | |
kson | -1.970 |
Wiz | -1.800 |
Wolf | -1.794 |
ATK | -1.766 |
pent | -1.553 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
kson | +1.771 |
Wolf | +1.716 |
Wiz | +1.708 |
ATK | +1.631 |
pent | +1.517 |
Neg logit contributions | |
erg | -1.747 |
NL | -1.696 |
cape | -1.640 |
recomp | -1.639 |
ropolitan | -1.636 |
Token | 200 |
Token ID | 2167 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
erg | +5.064 |
NL | +4.933 |
cape | +4.562 |
zig | +4.389 |
♦ | +4.306 |
Neg logit contributions | |
kson | -10.514 |
Wiz | -10.380 |
Wolf | -10.275 |
ATK | -9.845 |
�� | -9.336 |
Token | ] |
Token ID | 60 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
kson | +1.266 |
Wolf | +1.216 |
Wiz | +1.214 |
ATK | +1.171 |
pent | +1.096 |
Neg logit contributions | |
erg | -0.985 |
NL | -0.951 |
recomp | -0.920 |
cape | -0.918 |
ropolitan | -0.911 |
Token |
|
Token ID | 198 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
erg | +1.100 |
NL | +1.068 |
ropolitan | +1.024 |
recomp | +1.018 |
cape | +1.017 |
Neg logit contributions | |
kson | -1.296 |
Wiz | -1.230 |
Wolf | -1.224 |
ATK | -1.184 |
pent | -1.114 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
erg | +0.037 |
NL | +0.036 |
recomp | +0.035 |
ropolitan | +0.035 |
cape | +0.035 |
Neg logit contributions | |
kson | -0.042 |
Wolf | -0.040 |
Wiz | -0.040 |
ATK | -0.039 |
pent | -0.036 |
Token | The |
Token ID | 464 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
erg | +1.406 |
NL | +1.376 |
cape | +1.306 |
ropolitan | +1.295 |
recomp | +1.287 |
Neg logit contributions | |
kson | -1.544 |
Wiz | -1.472 |
Wolf | -1.469 |
ATK | -1.417 |
pent | -1.300 |
Token | of |
Token ID | 286 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
kson | +0.848 |
Wolf | +0.816 |
Wiz | +0.812 |
ATK | +0.778 |
pent | +0.726 |
Neg logit contributions | |
erg | -0.780 |
NL | -0.758 |
ropolitan | -0.730 |
recomp | -0.729 |
cape | -0.723 |
Token | human |
Token ID | 1692 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
kson | +0.335 |
Wolf | +0.320 |
Wiz | +0.320 |
ATK | +0.307 |
pent | +0.285 |
Neg logit contributions | |
erg | -0.322 |
NL | -0.313 |
recomp | -0.302 |
ropolitan | -0.302 |
cape | -0.301 |
Token | relationships |
Token ID | 6958 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
erg | +1.112 |
NL | +1.077 |
recomp | +1.054 |
cape | +1.045 |
ropolitan | +1.039 |
Neg logit contributions | |
kson | -1.043 |
Wiz | -0.985 |
Wolf | -0.979 |
ATK | -0.943 |
pent | -0.869 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
erg | +0.751 |
NL | +0.728 |
recomp | +0.705 |
cape | +0.702 |
ropolitan | +0.697 |
Neg logit contributions | |
kson | -0.876 |
Wiz | -0.834 |
Wolf | -0.832 |
ATK | -0.804 |
pent | -0.748 |
Token | the |
Token ID | 262 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
erg | +0.953 |
NL | +0.926 |
recomp | +0.901 |
cape | +0.892 |
ropolitan | +0.890 |
Neg logit contributions | |
kson | -0.950 |
Wiz | -0.897 |
Wolf | -0.894 |
ATK | -0.861 |
pent | -0.799 |
Token | sexual |
Token ID | 3206 |
Feature activation | -9.60e+00 |
Pos logit contributions | |
erg | +4.516 |
recomp | +4.398 |
NL | +4.384 |
cape | +4.219 |
Clarkson | +4.185 |
Neg logit contributions | |
kson | -4.743 |
Wiz | -4.337 |
Wolf | -4.227 |
ATK | -4.172 |
pent | -3.926 |
Token | dynamics |
Token ID | 17262 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
erg | +6.100 |
recomp | +6.026 |
cape | +5.951 |
NL | +5.873 |
Clarkson | +5.648 |
Neg logit contributions | |
kson | -6.585 |
Wiz | -6.079 |
Wolf | -5.733 |
ATK | -5.672 |
�� | -5.643 |
Token | between |
Token ID | 1022 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
erg | +3.689 |
NL | +3.549 |
cape | +3.529 |
recomp | +3.435 |
♦ | +3.341 |
Neg logit contributions | |
kson | -4.636 |
Wiz | -4.272 |
Wolf | -4.198 |
ATK | -4.164 |
pent | -3.859 |
Token | a |
Token ID | 257 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
erg | +1.609 |
NL | +1.555 |
recomp | +1.510 |
cape | +1.491 |
ropolitan | +1.487 |
Neg logit contributions | |
kson | -2.043 |
Wiz | -1.935 |
Wolf | -1.909 |
ATK | -1.862 |
pent | -1.748 |
Token | man |
Token ID | 582 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
kson | +1.164 |
Wolf | +1.123 |
Wiz | +1.113 |
ATK | +1.067 |
pent | +0.994 |
Neg logit contributions | |
erg | -1.108 |
NL | -1.076 |
ropolitan | -1.038 |
recomp | -1.037 |
cape | -1.033 |
Token | and |
Token ID | 290 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
erg | +1.118 |
NL | +1.084 |
recomp | +1.046 |
cape | +1.044 |
ropolitan | +1.040 |
Neg logit contributions | |
kson | -1.248 |
Wiz | -1.185 |
Wolf | -1.178 |
ATK | -1.143 |
pent | -1.058 |
Token | four |
Token ID | 1440 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
kson | +0.470 |
Wolf | +0.448 |
Wiz | +0.447 |
ATK | +0.429 |
pent | +0.398 |
Neg logit contributions | |
erg | -0.460 |
NL | -0.448 |
ropolitan | -0.432 |
recomp | -0.432 |
cape | -0.430 |
Token | other |
Token ID | 584 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
erg | +0.969 |
NL | +0.937 |
recomp | +0.904 |
cape | +0.898 |
ropolitan | +0.893 |
Neg logit contributions | |
kson | -1.064 |
Wiz | -1.014 |
Wolf | -1.007 |
ATK | -0.974 |
pent | -0.906 |
Token | customers |
Token ID | 4297 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
kson | +1.780 |
Wolf | +1.725 |
Wiz | +1.703 |
ATK | +1.641 |
pent | +1.526 |
Neg logit contributions | |
erg | -1.631 |
NL | -1.598 |
ropolitan | -1.555 |
cape | -1.538 |
recomp | -1.534 |
Token | behind |
Token ID | 2157 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
erg | +0.293 |
NL | +0.285 |
recomp | +0.275 |
ropolitan | +0.275 |
cape | +0.274 |
Neg logit contributions | |
kson | -0.292 |
Wolf | -0.279 |
Wiz | -0.278 |
ATK | -0.267 |
pent | -0.247 |
Token | me |
Token ID | 502 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
kson | +1.531 |
Wolf | +1.478 |
Wiz | +1.464 |
ATK | +1.407 |
pent | +1.303 |
Neg logit contributions | |
erg | -1.453 |
NL | -1.409 |
ropolitan | -1.362 |
recomp | -1.359 |
cape | -1.354 |
Token | cl |
Token ID | 537 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
erg | +1.965 |
NL | +1.898 |
recomp | +1.865 |
cape | +1.843 |
ropolitan | +1.829 |
Neg logit contributions | |
kson | -2.041 |
Wiz | -1.943 |
Wolf | -1.924 |
ATK | -1.856 |
pent | -1.735 |
Token | apped |
Token ID | 6320 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
erg | +5.954 |
NL | +5.234 |
ropolitan | +5.104 |
zig | +5.085 |
cape | +4.968 |
Neg logit contributions | |
Wiz | -9.578 |
kson | -9.544 |
Wolf | -9.342 |
ATK | -9.123 |
�� | -8.792 |
Token | , |
Token ID | 11 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
erg | +1.191 |
NL | +1.149 |
recomp | +1.122 |
cape | +1.107 |
ropolitan | +1.102 |
Neg logit contributions | |
kson | -1.407 |
Wiz | -1.335 |
Wolf | -1.328 |
ATK | -1.289 |
pent | -1.205 |
Token | while |
Token ID | 981 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
erg | +2.805 |
NL | +2.714 |
recomp | +2.658 |
cape | +2.598 |
Clarkson | +2.592 |
Neg logit contributions | |
kson | -3.099 |
Wiz | -2.905 |
Wolf | -2.879 |
ATK | -2.817 |
pent | -2.655 |
Token | the |
Token ID | 262 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
erg | +1.100 |
NL | +1.063 |
recomp | +1.031 |
ropolitan | +1.021 |
cape | +1.019 |
Neg logit contributions | |
kson | -1.239 |
Wiz | -1.177 |
Wolf | -1.172 |
ATK | -1.136 |
pent | -1.063 |
Token | customer |
Token ID | 6491 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
kson | +0.298 |
Wolf | +0.284 |
Wiz | +0.284 |
ATK | +0.273 |
pent | +0.253 |
Neg logit contributions | |
erg | -0.296 |
NL | -0.288 |
recomp | -0.278 |
ropolitan | -0.277 |
cape | -0.277 |
Token | ] |
Token ID | 60 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
erg | +0.445 |
NL | +0.436 |
recomp | +0.412 |
cape | +0.410 |
ropolitan | +0.409 |
Neg logit contributions | |
kson | -0.671 |
Wiz | -0.639 |
Wolf | -0.636 |
ATK | -0.612 |
pent | -0.584 |
Token | [ |
Token ID | 685 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
erg | +3.165 |
NL | +3.159 |
Clarkson | +2.996 |
recomp | +2.968 |
cape | +2.918 |
Neg logit contributions | |
kson | -3.720 |
Wiz | -3.501 |
Wolf | -3.429 |
ATK | -3.318 |
pent | -3.161 |
Token | Event |
Token ID | 9237 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
erg | +0.612 |
NL | +0.601 |
recomp | +0.582 |
cape | +0.580 |
ropolitan | +0.580 |
Neg logit contributions | |
kson | -0.358 |
Wiz | -0.333 |
Wolf | -0.332 |
ATK | -0.315 |
pent | -0.283 |
Token | Country |
Token ID | 33921 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
erg | +0.487 |
NL | +0.469 |
recomp | +0.453 |
ropolitan | +0.452 |
cape | +0.451 |
Neg logit contributions | |
kson | -0.615 |
Wolf | -0.591 |
Wiz | -0.590 |
ATK | -0.570 |
pent | -0.533 |
Token | " |
Token ID | 366 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
kson | +0.569 |
Wolf | +0.546 |
Wiz | +0.543 |
ATK | +0.520 |
pent | +0.480 |
Neg logit contributions | |
erg | -0.618 |
NL | -0.599 |
ropolitan | -0.587 |
cape | -0.584 |
recomp | -0.580 |
Token | N |
Token ID | 45 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
kson | +4.586 |
Wiz | +4.485 |
Wolf | +4.446 |
ATK | +4.285 |
pent | +4.016 |
Neg logit contributions | |
erg | -3.639 |
recomp | -3.621 |
ropolitan | -3.594 |
llular | -3.452 |
Clarkson | -3.414 |
Token | ED |
Token ID | 1961 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
erg | +6.310 |
NL | +6.038 |
zig | +5.699 |
atures | +5.313 |
recomp | +5.276 |
Neg logit contributions | |
kson | -8.257 |
Wolf | -7.590 |
Wiz | -7.536 |
ATK | -7.190 |
�� | -7.117 |
Token | "] |
Token ID | 8973 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
NL | +3.340 |
erg | +3.336 |
recomp | +2.959 |
cape | +2.943 |
Clarkson | +2.911 |
Neg logit contributions | |
kson | -6.258 |
Wiz | -6.028 |
Wolf | -5.972 |
ATK | -5.802 |
pent | -5.510 |
Token | [ |
Token ID | 685 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
erg | +1.159 |
NL | +1.131 |
recomp | +1.087 |
ropolitan | +1.077 |
cape | +1.075 |
Neg logit contributions | |
kson | -1.232 |
Wiz | -1.170 |
Wolf | -1.166 |
ATK | -1.118 |
pent | -1.046 |
Token | Time |
Token ID | 7575 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
kson | +0.188 |
Wolf | +0.180 |
Wiz | +0.180 |
ATK | +0.173 |
pent | +0.161 |
Neg logit contributions | |
erg | -0.163 |
NL | -0.156 |
recomp | -0.153 |
ropolitan | -0.152 |
cape | -0.151 |
Token | Control |
Token ID | 15988 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
erg | +2.093 |
NL | +2.066 |
recomp | +1.966 |
ropolitan | +1.932 |
cape | +1.929 |
Neg logit contributions | |
kson | -2.106 |
Wiz | -1.958 |
Wolf | -1.948 |
ATK | -1.871 |
pent | -1.745 |