Token | forum |
Token ID | 27302 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
abeth | +0.481 |
mallow | +0.447 |
bda | +0.447 |
hof | +0.416 |
assic | +0.371 |
Neg logit contributions | |
Whites | -0.517 |
udo | -0.485 |
="# | -0.471 |
YP | -0.467 |
Sel | -0.460 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
abeth | +1.151 |
bda | +1.066 |
mallow | +1.065 |
hof | +0.988 |
assic | +0.860 |
Neg logit contributions | |
Whites | -1.510 |
udo | -1.409 |
="# | -1.382 |
YP | -1.376 |
Sel | -1.352 |
Token | com |
Token ID | 785 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
abeth | +1.124 |
bda | +1.029 |
mallow | +1.016 |
hof | +0.935 |
assic | +0.785 |
Neg logit contributions | |
Whites | -1.995 |
udo | -1.881 |
="# | -1.856 |
YP | -1.843 |
Sel | -1.811 |
Token | / |
Token ID | 14 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
abeth | +2.064 |
bda | +1.918 |
mallow | +1.901 |
hof | +1.770 |
assic | +1.535 |
Neg logit contributions | |
Whites | -2.690 |
udo | -2.528 |
="# | -2.479 |
YP | -2.470 |
Sel | -2.426 |
Token | forums |
Token ID | 37141 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
abeth | +2.422 |
bda | +2.278 |
mallow | +2.252 |
hof | +2.106 |
assic | +1.834 |
Neg logit contributions | |
Whites | -3.160 |
udo | -2.958 |
="# | -2.910 |
YP | -2.877 |
Sel | -2.817 |
Token | ... |
Token ID | 986 |
Feature activation | +7.42e+00 |
Pos logit contributions | |
Whites | +1.462 |
udo | +1.387 |
="# | +1.345 |
YP | +1.327 |
Sel | +1.311 |
Neg logit contributions | |
abeth | -1.391 |
mallow | -1.292 |
bda | -1.289 |
hof | -1.194 |
assic | -1.090 |
Token | with |
Token ID | 4480 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
Whites | +5.384 |
udo | +5.231 |
YP | +5.002 |
="# | +4.977 |
Sel | +4.917 |
Neg logit contributions | |
abeth | -5.464 |
mallow | -4.992 |
bda | -4.878 |
hof | -4.566 |
assic | -4.245 |
Token | - |
Token ID | 12 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Whites | +0.461 |
udo | +0.435 |
="# | +0.423 |
YP | +0.418 |
Sel | +0.413 |
Neg logit contributions | |
abeth | -0.411 |
mallow | -0.381 |
bda | -0.379 |
hof | -0.353 |
assic | -0.314 |
Token | p |
Token ID | 79 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
Whites | +0.124 |
udo | +0.116 |
="# | +0.113 |
YP | +0.112 |
Sel | +0.110 |
Neg logit contributions | |
abeth | -0.129 |
mallow | -0.120 |
bda | -0.120 |
hof | -0.112 |
assic | -0.101 |
Token | ics |
Token ID | 873 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
abeth | +0.470 |
mallow | +0.440 |
bda | +0.438 |
hof | +0.411 |
assic | +0.370 |
Neg logit contributions | |
Whites | -0.444 |
udo | -0.419 |
="# | -0.404 |
YP | -0.400 |
Sel | -0.393 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
abeth | +0.375 |
mallow | +0.348 |
bda | +0.348 |
hof | +0.324 |
assic | +0.287 |
Neg logit contributions | |
Whites | -0.432 |
udo | -0.405 |
="# | -0.395 |
YP | -0.392 |
Sel | -0.385 |
Token | youtube |
Token ID | 11604 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
abeth | +1.214 |
mallow | +1.141 |
bda | +1.133 |
hof | +1.064 |
assic | +0.950 |
Neg logit contributions | |
Whites | -1.260 |
udo | -1.172 |
="# | -1.141 |
YP | -1.132 |
Sel | -1.110 |
Token | . |
Token ID | 13 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
Whites | +1.390 |
udo | +1.306 |
="# | +1.279 |
YP | +1.261 |
Sel | +1.246 |
Neg logit contributions | |
abeth | -1.189 |
mallow | -1.098 |
bda | -1.096 |
hof | -1.017 |
assic | -0.909 |
Token | com |
Token ID | 785 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Whites | +0.926 |
udo | +0.879 |
="# | +0.860 |
YP | +0.852 |
Sel | +0.844 |
Neg logit contributions | |
abeth | -0.576 |
mallow | -0.522 |
bda | -0.521 |
hof | -0.473 |
assic | -0.411 |
Token | / |
Token ID | 14 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
abeth | +1.457 |
mallow | +1.356 |
bda | +1.355 |
hof | +1.253 |
assic | +1.089 |
Neg logit contributions | |
Whites | -1.857 |
udo | -1.747 |
YP | -1.694 |
="# | -1.687 |
Sel | -1.662 |
Token | watch |
Token ID | 8340 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
abeth | +2.319 |
mallow | +2.207 |
bda | +2.201 |
hof | +2.072 |
assic | +1.876 |
Neg logit contributions | |
Whites | -2.047 |
udo | -1.872 |
="# | -1.823 |
YP | -1.807 |
Sel | -1.760 |
Token | ? |
Token ID | 30 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
abeth | +0.757 |
mallow | +0.700 |
bda | +0.698 |
hof | +0.643 |
assic | +0.551 |
Neg logit contributions | |
Whites | -1.112 |
udo | -1.049 |
="# | -1.020 |
YP | -1.016 |
Sel | -0.999 |
Token | v |
Token ID | 85 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Whites | +4.614 |
udo | +4.249 |
="# | +4.194 |
YP | +4.062 |
Sel | +4.026 |
Neg logit contributions | |
abeth | -5.902 |
mallow | -5.358 |
bda | -5.287 |
hof | -5.070 |
assic | -4.586 |
Token | = |
Token ID | 28 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Whites | +0.605 |
udo | +0.547 |
="# | +0.526 |
YP | +0.517 |
Sel | +0.503 |
Neg logit contributions | |
abeth | -1.182 |
mallow | -1.121 |
bda | -1.118 |
hof | -1.065 |
assic | -0.985 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
abeth | +0.936 |
bda | +0.880 |
mallow | +0.877 |
hof | +0.827 |
assic | +0.745 |
Neg logit contributions | |
Whites | -0.819 |
udo | -0.755 |
="# | -0.734 |
YP | -0.720 |
Sel | -0.710 |
Token | g |
Token ID | 70 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Whites | +1.385 |
udo | +1.307 |
YP | +1.270 |
="# | +1.261 |
Sel | +1.238 |
Neg logit contributions | |
abeth | -1.529 |
mallow | -1.433 |
bda | -1.420 |
hof | -1.332 |
assic | -1.208 |
Token | 7 |
Token ID | 22 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Whites | +1.361 |
udo | +1.280 |
YP | +1.245 |
="# | +1.236 |
Sel | +1.210 |
Neg logit contributions | |
abeth | -1.625 |
mallow | -1.531 |
bda | -1.518 |
hof | -1.426 |
assic | -1.297 |
Token | . |
Token ID | 13 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
Whites | +0.357 |
udo | +0.335 |
="# | +0.327 |
YP | +0.323 |
Sel | +0.318 |
Neg logit contributions | |
abeth | -0.307 |
mallow | -0.285 |
bda | -0.285 |
hof | -0.264 |
assic | -0.235 |
Token | � |
Token ID | 447 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
Whites | +0.225 |
udo | +0.209 |
="# | +0.204 |
YP | +0.202 |
Sel | +0.198 |
Neg logit contributions | |
abeth | -0.225 |
mallow | -0.210 |
bda | -0.210 |
hof | -0.196 |
assic | -0.177 |
Token | � |
Token ID | 251 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
abeth | +0.227 |
mallow | +0.213 |
bda | +0.213 |
hof | +0.202 |
assic | +0.184 |
Neg logit contributions | |
Whites | -0.162 |
udo | -0.149 |
="# | -0.143 |
YP | -0.142 |
Sel | -0.139 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
abeth | +0.848 |
mallow | +0.795 |
bda | +0.794 |
hof | +0.747 |
assic | +0.669 |
Neg logit contributions | |
Whites | -0.752 |
udo | -0.705 |
="# | -0.682 |
YP | -0.676 |
Sel | -0.662 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
abeth | +0.153 |
mallow | +0.144 |
bda | +0.144 |
hof | +0.135 |
assic | +0.123 |
Neg logit contributions | |
Whites | -0.126 |
udo | -0.116 |
="# | -0.113 |
YP | -0.111 |
Sel | -0.109 |
Token | again |
Token ID | 757 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
Whites | +2.111 |
udo | +1.939 |
="# | +1.855 |
YP | +1.850 |
Sel | +1.819 |
Neg logit contributions | |
abeth | -2.364 |
bda | -2.230 |
mallow | -2.218 |
hof | -2.078 |
assic | -1.895 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Whites | +5.242 |
udo | +4.764 |
="# | +4.651 |
YP | +4.617 |
Scouting | +4.559 |
Neg logit contributions | |
abeth | -5.282 |
bda | -4.957 |
mallow | -4.906 |
hof | -4.545 |
assic | -4.127 |
Token | we |
Token ID | 356 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Whites | +0.986 |
udo | +0.916 |
="# | +0.890 |
YP | +0.882 |
Sel | +0.865 |
Neg logit contributions | |
abeth | -1.023 |
mallow | -0.956 |
bda | -0.955 |
hof | -0.893 |
assic | -0.803 |
Token | 're |
Token ID | 821 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Whites | +0.986 |
udo | +0.910 |
="# | +0.880 |
YP | +0.870 |
Sel | +0.852 |
Neg logit contributions | |
abeth | -1.214 |
bda | -1.141 |
mallow | -1.140 |
hof | -1.073 |
assic | -0.976 |
Token | hitting |
Token ID | 9008 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Whites | +1.185 |
udo | +1.098 |
="# | +1.070 |
YP | +1.058 |
Sel | +1.040 |
Neg logit contributions | |
abeth | -1.160 |
bda | -1.083 |
mallow | -1.077 |
hof | -1.004 |
assic | -0.907 |
Token | the |
Token ID | 262 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
Whites | +1.708 |
udo | +1.585 |
="# | +1.533 |
YP | +1.518 |
Sel | +1.488 |
Neg logit contributions | |
abeth | -1.797 |
bda | -1.688 |
mallow | -1.677 |
hof | -1.576 |
assic | -1.418 |
Token | Birmingham |
Token ID | 18899 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Whites | +0.158 |
udo | +0.146 |
="# | +0.143 |
YP | +0.141 |
Sel | +0.140 |
Neg logit contributions | |
abeth | -0.146 |
mallow | -0.136 |
bda | -0.136 |
hof | -0.126 |
assic | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
abeth | +0.773 |
mallow | +0.715 |
bda | +0.712 |
hof | +0.664 |
assic | +0.584 |
Neg logit contributions | |
Whites | -0.929 |
udo | -0.879 |
="# | -0.856 |
YP | -0.848 |
Sel | -0.831 |
Token |
|
Token ID | 198 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Whites | +0.894 |
udo | +0.814 |
="# | +0.789 |
YP | +0.782 |
Sel | +0.773 |
Neg logit contributions | |
abeth | -1.048 |
bda | -0.986 |
mallow | -0.984 |
hof | -0.924 |
assic | -0.848 |
Token |
|
Token ID | 198 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
Whites | +0.295 |
udo | +0.273 |
="# | +0.266 |
YP | +0.263 |
Sel | +0.258 |
Neg logit contributions | |
abeth | -0.343 |
mallow | -0.322 |
bda | -0.321 |
hof | -0.302 |
assic | -0.274 |
Token | Out |
Token ID | 7975 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Whites | +0.427 |
udo | +0.396 |
="# | +0.385 |
YP | +0.384 |
Sel | +0.379 |
Neg logit contributions | |
abeth | -0.537 |
mallow | -0.506 |
bda | -0.504 |
hof | -0.476 |
assic | -0.434 |
Token | of |
Token ID | 286 |
Feature activation | +6.84e+00 |
Pos logit contributions | |
Whites | +0.739 |
udo | +0.686 |
="# | +0.664 |
YP | +0.659 |
Sel | +0.648 |
Neg logit contributions | |
abeth | -0.786 |
mallow | -0.737 |
bda | -0.736 |
hof | -0.689 |
assic | -0.626 |
Token | those |
Token ID | 883 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Whites | +4.820 |
udo | +4.220 |
="# | +4.122 |
YP | +4.057 |
Sel | +4.012 |
Neg logit contributions | |
abeth | -5.439 |
mallow | -5.297 |
bda | -5.217 |
hof | -4.981 |
assic | -4.599 |
Token | already |
Token ID | 1541 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Whites | +1.893 |
udo | +1.710 |
="# | +1.656 |
YP | +1.647 |
Sel | +1.610 |
Neg logit contributions | |
abeth | -2.381 |
bda | -2.244 |
mallow | -2.243 |
hof | -2.123 |
assic | -1.929 |
Token | working |
Token ID | 1762 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
abeth | +0.308 |
mallow | +0.290 |
bda | +0.290 |
hof | +0.273 |
assic | +0.247 |
Neg logit contributions | |
Whites | -0.249 |
udo | -0.231 |
="# | -0.223 |
YP | -0.221 |
Sel | -0.217 |
Token | from |
Token ID | 422 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
abeth | +1.407 |
mallow | +1.300 |
bda | +1.298 |
hof | +1.207 |
assic | +1.065 |
Neg logit contributions | |
Whites | -1.647 |
udo | -1.558 |
="# | -1.516 |
YP | -1.499 |
Sel | -1.476 |
Token | home |
Token ID | 1363 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
abeth | +0.977 |
mallow | +0.918 |
bda | +0.917 |
hof | +0.861 |
assic | +0.771 |
Neg logit contributions | |
Whites | -0.862 |
udo | -0.811 |
="# | -0.781 |
YP | -0.775 |
Sel | -0.762 |
Token | cs |
Token ID | 6359 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
abeth | +0.952 |
mallow | +0.882 |
bda | +0.881 |
hof | +0.820 |
assic | +0.723 |
Neg logit contributions | |
Whites | -1.143 |
udo | -1.074 |
="# | -1.046 |
YP | -1.038 |
Sel | -1.021 |
Token | will |
Token ID | 481 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
abeth | +0.948 |
mallow | +0.886 |
bda | +0.885 |
hof | +0.832 |
assic | +0.748 |
Neg logit contributions | |
Whites | -0.875 |
udo | -0.813 |
="# | -0.791 |
YP | -0.784 |
Sel | -0.770 |
Token | go |
Token ID | 467 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
abeth | +1.167 |
bda | +1.094 |
mallow | +1.093 |
hof | +1.026 |
assic | +0.923 |
Neg logit contributions | |
Whites | -1.053 |
udo | -0.979 |
="# | -0.951 |
YP | -0.943 |
Sel | -0.925 |
Token | here |
Token ID | 994 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
abeth | +2.196 |
bda | +2.051 |
mallow | +2.050 |
hof | +1.922 |
assic | +1.698 |
Neg logit contributions | |
Whites | -2.289 |
udo | -2.150 |
="# | -2.082 |
YP | -2.063 |
Sel | -2.046 |
Token | + |
Token ID | 1343 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
abeth | +0.266 |
mallow | +0.249 |
bda | +0.249 |
hof | +0.234 |
assic | +0.211 |
Neg logit contributions | |
Whites | -0.244 |
udo | -0.227 |
="# | -0.221 |
YP | -0.218 |
Sel | -0.214 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
abeth | +0.582 |
bda | +0.543 |
mallow | +0.543 |
hof | +0.510 |
assic | +0.457 |
Neg logit contributions | |
Whites | -0.553 |
udo | -0.516 |
="# | -0.503 |
YP | -0.497 |
Sel | -0.488 |
Token | --+ |
Token ID | 44785 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
Whites | +1.342 |
udo | +1.044 |
="# | +0.828 |
YP | +0.786 |
Sel | +0.715 |
Neg logit contributions | |
abeth | -8.856 |
mallow | -8.573 |
bda | -8.505 |
hof | -8.199 |
assic | -7.769 |
Token | + |
Token ID | 1343 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Whites | +3.826 |
udo | +3.529 |
="# | +3.312 |
YP | +3.288 |
Sel | +3.258 |
Neg logit contributions | |
abeth | -5.228 |
mallow | -4.942 |
bda | -4.879 |
hof | -4.602 |
assic | -4.253 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
Whites | +2.122 |
udo | +1.978 |
="# | +1.900 |
YP | +1.889 |
Sel | +1.859 |
Neg logit contributions | |
abeth | -2.361 |
mallow | -2.214 |
bda | -2.199 |
hof | -2.062 |
assic | -1.869 |
Token | --+ |
Token ID | 44785 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
Whites | +0.963 |
udo | +0.720 |
="# | +0.580 |
YP | +0.533 |
Sel | +0.480 |
Neg logit contributions | |
abeth | -7.101 |
mallow | -6.855 |
bda | -6.816 |
hof | -6.578 |
assic | -6.231 |
Token | < |
Token ID | 1279 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
Whites | +3.620 |
udo | +3.338 |
="# | +3.158 |
YP | +3.127 |
Sel | +3.103 |
Neg logit contributions | |
abeth | -4.633 |
mallow | -4.353 |
bda | -4.303 |
hof | -4.056 |
assic | -3.724 |
Token | 4 |
Token ID | 19 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
abeth | +0.284 |
mallow | +0.268 |
bda | +0.268 |
hof | +0.252 |
assic | +0.228 |
Neg logit contributions | |
Whites | -0.223 |
udo | -0.207 |
="# | -0.201 |
YP | -0.197 |
Sel | -0.194 |
Token | m |
Token ID | 76 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
abeth | +0.332 |
mallow | +0.305 |
bda | +0.304 |
hof | +0.279 |
assic | +0.242 |
Neg logit contributions | |
Whites | -0.491 |
udo | -0.464 |
="# | -0.454 |
YP | -0.450 |
Sel | -0.443 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
abeth | +0.982 |
mallow | +0.911 |
bda | +0.909 |
hof | +0.845 |
assic | +0.741 |
Neg logit contributions | |
Whites | -1.205 |
udo | -1.139 |
="# | -1.115 |
YP | -1.102 |
Sel | -1.086 |
Token | As |
Token ID | 1081 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
abeth | +0.112 |
mallow | +0.105 |
bda | +0.105 |
hof | +0.099 |
assic | +0.090 |
Neg logit contributions | |
Whites | -0.089 |
udo | -0.082 |
="# | -0.080 |
YP | -0.079 |
Sel | -0.077 |
Token | a |
Token ID | 257 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
abeth | +0.094 |
mallow | +0.088 |
bda | +0.088 |
hof | +0.082 |
assic | +0.074 |
Neg logit contributions | |
Whites | -0.091 |
udo | -0.086 |
="# | -0.083 |
YP | -0.082 |
Sel | -0.081 |
Token | share |
Token ID | 2648 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
Whites | +1.266 |
udo | +1.152 |
="# | +1.126 |
YP | +1.108 |
Sel | +1.080 |
Neg logit contributions | |
abeth | -1.641 |
mallow | -1.550 |
bda | -1.545 |
hof | -1.455 |
assic | -1.330 |
Token | of |
Token ID | 286 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Whites | +4.424 |
udo | +4.075 |
="# | +3.964 |
YP | +3.906 |
Sel | +3.816 |
Neg logit contributions | |
abeth | -5.364 |
bda | -5.113 |
mallow | -5.061 |
hof | -4.776 |
assic | -4.295 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Whites | +0.946 |
udo | +0.872 |
="# | +0.847 |
YP | +0.839 |
Sel | +0.824 |
Neg logit contributions | |
abeth | -1.022 |
bda | -0.958 |
mallow | -0.958 |
hof | -0.898 |
assic | -0.812 |
Token | population |
Token ID | 3265 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
Whites | +0.877 |
udo | +0.802 |
="# | +0.772 |
YP | +0.764 |
Sel | +0.748 |
Neg logit contributions | |
abeth | -1.254 |
mallow | -1.183 |
bda | -1.182 |
hof | -1.118 |
assic | -1.024 |
Token | , |
Token ID | 11 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
Whites | +0.611 |
udo | +0.569 |
="# | +0.553 |
YP | +0.548 |
Sel | +0.540 |
Neg logit contributions | |
abeth | -0.568 |
bda | -0.530 |
mallow | -0.529 |
hof | -0.493 |
assic | -0.440 |
Token | it |
Token ID | 340 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
Whites | +0.517 |
udo | +0.481 |
="# | +0.467 |
YP | +0.462 |
Sel | +0.454 |
Neg logit contributions | |
abeth | -0.581 |
mallow | -0.544 |
bda | -0.543 |
hof | -0.510 |
assic | -0.460 |
Token | make |
Token ID | 787 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
Whites | +0.074 |
udo | +0.068 |
="# | +0.066 |
YP | +0.065 |
Sel | +0.064 |
Neg logit contributions | |
abeth | -0.085 |
mallow | -0.079 |
bda | -0.079 |
hof | -0.074 |
assic | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Whites | +0.261 |
udo | +0.242 |
="# | +0.235 |
YP | +0.231 |
Sel | +0.229 |
Neg logit contributions | |
abeth | -0.264 |
bda | -0.247 |
mallow | -0.246 |
hof | -0.230 |
assic | -0.205 |
Token | ocean |
Token ID | 9151 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
abeth | +0.210 |
mallow | +0.193 |
bda | +0.193 |
hof | +0.177 |
assic | +0.154 |
Neg logit contributions | |
Whites | -0.298 |
udo | -0.279 |
="# | -0.273 |
YP | -0.271 |
Sel | -0.267 |
Token | our |
Token ID | 674 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
abeth | +0.428 |
bda | +0.400 |
mallow | +0.399 |
hof | +0.373 |
assic | +0.334 |
Neg logit contributions | |
Whites | -0.425 |
udo | -0.397 |
="# | -0.387 |
YP | -0.382 |
Sel | -0.376 |
Token | umb |
Token ID | 20810 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
Whites | +0.110 |
udo | +0.102 |
="# | +0.100 |
YP | +0.098 |
Sel | +0.097 |
Neg logit contributions | |
abeth | -0.113 |
mallow | -0.106 |
bda | -0.106 |
hof | -0.099 |
assic | -0.088 |
Token | il |
Token ID | 346 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
abeth | +0.461 |
mallow | +0.431 |
bda | +0.429 |
hof | +0.401 |
assic | +0.359 |
Neg logit contributions | |
Whites | -0.474 |
udo | -0.443 |
="# | -0.431 |
YP | -0.427 |
Sel | -0.419 |
Token | ical |
Token ID | 605 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
Whites | +4.783 |
udo | +4.553 |
YP | +4.426 |
="# | +4.416 |
idas | +4.336 |
Neg logit contributions | |
abeth | -4.817 |
bda | -4.472 |
mallow | -4.452 |
hof | -4.198 |
assic | -3.652 |
Token | cord |
Token ID | 15050 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
Whites | +0.270 |
udo | +0.250 |
="# | +0.245 |
YP | +0.241 |
Sel | +0.238 |
Neg logit contributions | |
abeth | -0.269 |
bda | -0.251 |
mallow | -0.250 |
hof | -0.235 |
assic | -0.210 |
Token | to |
Token ID | 284 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
abeth | +0.616 |
mallow | +0.573 |
bda | +0.570 |
hof | +0.532 |
assic | +0.471 |
Neg logit contributions | |
Whites | -0.707 |
udo | -0.664 |
="# | -0.646 |
YP | -0.641 |
Sel | -0.630 |
Token | life |
Token ID | 1204 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
abeth | +1.484 |
mallow | +1.381 |
bda | +1.379 |
hof | +1.287 |
assic | +1.148 |
Neg logit contributions | |
Whites | -1.596 |
udo | -1.499 |
="# | -1.456 |
YP | -1.444 |
Sel | -1.418 |
Token | . |
Token ID | 13 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
Whites | +0.527 |
udo | +0.493 |
="# | +0.479 |
YP | +0.476 |
Sel | +0.469 |
Neg logit contributions | |
abeth | -0.470 |
mallow | -0.437 |
bda | -0.436 |
hof | -0.406 |
assic | -0.361 |
Token | � |
Token ID | 247 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Whites | +0.435 |
udo | +0.385 |
="# | +0.365 |
YP | +0.358 |
Sel | +0.347 |
Neg logit contributions | |
abeth | -1.105 |
bda | -1.054 |
mallow | -1.054 |
hof | -1.005 |
assic | -0.938 |
Token | s |
Token ID | 82 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
Whites | +1.537 |
udo | +1.446 |
="# | +1.409 |
YP | +1.395 |
Sel | +1.387 |
Neg logit contributions | |
abeth | -1.095 |
mallow | -1.004 |
bda | -1.003 |
hof | -0.919 |
assic | -0.807 |
Token | more |
Token ID | 517 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Whites | +1.890 |
udo | +1.736 |
="# | +1.703 |
YP | +1.669 |
uda | +1.645 |
Neg logit contributions | |
abeth | -1.879 |
bda | -1.760 |
mallow | -1.757 |
hof | -1.628 |
assic | -1.460 |
Token | important |
Token ID | 1593 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
Whites | +0.266 |
udo | +0.249 |
="# | +0.242 |
YP | +0.240 |
Sel | +0.236 |
Neg logit contributions | |
abeth | -0.242 |
mallow | -0.225 |
bda | -0.225 |
hof | -0.210 |
assic | -0.187 |
Token | than |
Token ID | 621 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
abeth | +0.606 |
mallow | +0.561 |
bda | +0.560 |
hof | +0.520 |
assic | +0.458 |
Neg logit contributions | |
Whites | -0.734 |
udo | -0.697 |
="# | -0.676 |
YP | -0.670 |
Sel | -0.659 |
Token | ever |
Token ID | 1683 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
Whites | +0.341 |
udo | +0.317 |
="# | +0.308 |
YP | +0.305 |
Sel | +0.300 |
Neg logit contributions | |
abeth | -0.358 |
mallow | -0.334 |
bda | -0.334 |
hof | -0.313 |
assic | -0.281 |
Token | to |
Token ID | 284 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
Whites | +4.289 |
udo | +3.852 |
="# | +3.788 |
YP | +3.768 |
Sel | +3.696 |
Neg logit contributions | |
abeth | -5.288 |
mallow | -4.961 |
bda | -4.946 |
hof | -4.642 |
assic | -4.295 |
Token | spread |
Token ID | 4104 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Whites | +0.692 |
udo | +0.636 |
="# | +0.625 |
YP | +0.610 |
Sel | +0.600 |
Neg logit contributions | |
abeth | -0.769 |
mallow | -0.720 |
bda | -0.718 |
hof | -0.677 |
assic | -0.612 |
Token | complete |
Token ID | 1844 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Whites | +1.408 |
udo | +1.315 |
="# | +1.276 |
YP | +1.265 |
Sel | +1.242 |
Neg logit contributions | |
abeth | -1.460 |
mallow | -1.363 |
bda | -1.361 |
hof | -1.275 |
assic | -1.144 |
Token | and |
Token ID | 290 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Whites | +0.138 |
udo | +0.130 |
="# | +0.125 |
YP | +0.125 |
Sel | +0.122 |
Neg logit contributions | |
abeth | -0.153 |
mallow | -0.142 |
bda | -0.142 |
hof | -0.134 |
assic | -0.121 |
Token | accurate |
Token ID | 7187 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
Whites | +1.502 |
udo | +1.393 |
="# | +1.356 |
YP | +1.335 |
Sel | +1.313 |
Neg logit contributions | |
abeth | -1.570 |
bda | -1.473 |
mallow | -1.473 |
hof | -1.380 |
assic | -1.239 |
Token | com |
Token ID | 785 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Whites | +0.362 |
udo | +0.343 |
="# | +0.336 |
YP | +0.333 |
Sel | +0.329 |
Neg logit contributions | |
abeth | -0.219 |
mallow | -0.199 |
bda | -0.199 |
hof | -0.180 |
assic | -0.156 |
Token | / |
Token ID | 14 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
abeth | +0.207 |
mallow | +0.192 |
bda | +0.192 |
hof | +0.178 |
assic | +0.158 |
Neg logit contributions | |
Whites | -0.242 |
udo | -0.228 |
="# | -0.222 |
YP | -0.220 |
Sel | -0.216 |
Token | iv |
Token ID | 452 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
abeth | +0.518 |
mallow | +0.487 |
bda | +0.487 |
hof | +0.460 |
assic | +0.417 |
Neg logit contributions | |
Whites | -0.404 |
udo | -0.373 |
="# | -0.361 |
YP | -0.354 |
Sel | -0.348 |
Token | xx |
Token ID | 5324 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
abeth | +1.779 |
mallow | +1.680 |
bda | +1.677 |
hof | +1.592 |
assic | +1.453 |
Neg logit contributions | |
Whites | -1.219 |
udo | -1.109 |
="# | -1.075 |
YP | -1.059 |
Sel | -1.038 |
Token | brand |
Token ID | 17938 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
abeth | +1.067 |
mallow | +0.994 |
bda | +0.994 |
hof | +0.930 |
assic | +0.830 |
Neg logit contributions | |
Whites | -1.093 |
udo | -1.021 |
="# | -0.994 |
YP | -0.982 |
Sel | -0.966 |
Token | ? |
Token ID | 30 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
abeth | +1.999 |
mallow | +1.879 |
bda | +1.868 |
hof | +1.757 |
assic | +1.550 |
Neg logit contributions | |
Whites | -2.091 |
udo | -1.959 |
="# | -1.907 |
YP | -1.872 |
Sel | -1.851 |
Token | f |
Token ID | 69 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Whites | +5.098 |
udo | +4.756 |
="# | +4.701 |
YP | +4.634 |
Sel | +4.573 |
Neg logit contributions | |
abeth | -4.310 |
mallow | -3.990 |
bda | -3.894 |
hof | -3.756 |
assic | -3.357 |
Token | ref |
Token ID | 5420 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
Whites | +2.276 |
udo | +2.146 |
="# | +2.120 |
YP | +2.099 |
Sel | +2.075 |
Neg logit contributions | |
abeth | -1.638 |
mallow | -1.516 |
bda | -1.508 |
hof | -1.395 |
assic | -1.236 |
Token | = |
Token ID | 28 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
abeth | +0.102 |
bda | +0.097 |
mallow | +0.097 |
hof | +0.092 |
assic | +0.084 |
Neg logit contributions | |
Whites | -0.057 |
udo | -0.052 |
="# | -0.049 |
YP | -0.049 |
Sel | -0.047 |
Token | ts |
Token ID | 912 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
abeth | +1.470 |
mallow | +1.379 |
bda | +1.379 |
hof | +1.299 |
assic | +1.173 |
Neg logit contributions | |
Whites | -1.251 |
udo | -1.154 |
="# | -1.115 |
YP | -1.095 |
Sel | -1.076 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
abeth | +0.434 |
mallow | +0.405 |
bda | +0.405 |
hof | +0.379 |
assic | +0.339 |
Neg logit contributions | |
Whites | -0.419 |
udo | -0.391 |
="# | -0.380 |
YP | -0.376 |
Sel | -0.370 |
Token | ) |
Token ID | 8 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Whites | +1.337 |
udo | +1.265 |
="# | +1.238 |
YP | +1.217 |
Sel | +1.208 |
Neg logit contributions | |
abeth | -1.088 |
bda | -0.996 |
mallow | -0.994 |
hof | -0.914 |
assic | -0.829 |
Token | Mem |
Token ID | 4942 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Whites | +0.945 |
udo | +0.885 |
="# | +0.862 |
YP | +0.855 |
Sel | +0.841 |
Neg logit contributions | |
abeth | -0.813 |
bda | -0.753 |
mallow | -0.753 |
hof | -0.700 |
assic | -0.621 |
Token | c |
Token ID | 66 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
Whites | +0.714 |
udo | +0.666 |
="# | +0.647 |
YP | +0.633 |
Sel | +0.626 |
Neg logit contributions | |
abeth | -0.914 |
mallow | -0.852 |
bda | -0.852 |
hof | -0.805 |
assic | -0.731 |
Token | py |
Token ID | 9078 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Whites | +0.252 |
udo | +0.224 |
="# | +0.213 |
YP | +0.210 |
Sel | +0.203 |
Neg logit contributions | |
abeth | -0.596 |
mallow | -0.568 |
bda | -0.567 |
hof | -0.542 |
assic | -0.504 |
Token | In |
Token ID | 818 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
Whites | +0.833 |
udo | +0.773 |
="# | +0.751 |
YP | +0.744 |
Sel | +0.731 |
Neg logit contributions | |
abeth | -1.020 |
mallow | -0.958 |
bda | -0.954 |
hof | -0.900 |
assic | -0.816 |
Token | Memory |
Token ID | 30871 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
abeth | +0.464 |
mallow | +0.431 |
bda | +0.431 |
hof | +0.401 |
assic | +0.355 |
Neg logit contributions | |
Whites | -0.530 |
udo | -0.496 |
="# | -0.483 |
YP | -0.478 |
Sel | -0.470 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Whites | +4.069 |
udo | +3.682 |
="# | +3.627 |
YP | +3.588 |
uda | +3.457 |
Neg logit contributions | |
abeth | -5.293 |
mallow | -4.965 |
bda | -4.923 |
hof | -4.674 |
assic | -4.334 |
Token | 66 |
Token ID | 2791 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Whites | +0.947 |
udo | +0.868 |
="# | +0.836 |
YP | +0.825 |
Sel | +0.807 |
Neg logit contributions | |
abeth | -1.465 |
mallow | -1.381 |
bda | -1.380 |
hof | -1.309 |
assic | -1.202 |
Token | 284 |
Token ID | 30336 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
Whites | +0.082 |
udo | +0.076 |
="# | +0.074 |
YP | +0.073 |
Sel | +0.072 |
Neg logit contributions | |
abeth | -0.098 |
bda | -0.092 |
mallow | -0.092 |
hof | -0.087 |
assic | -0.078 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Whites | +2.594 |
udo | +2.362 |
="# | +2.301 |
YP | +2.271 |
Scouting | +2.204 |
Neg logit contributions | |
abeth | -3.404 |
mallow | -3.176 |
bda | -3.159 |
hof | -3.004 |
assic | -2.782 |
Token | 64 |
Token ID | 2414 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
Whites | +0.066 |
udo | +0.059 |
="# | +0.056 |
YP | +0.055 |
Sel | +0.053 |
Neg logit contributions | |
abeth | -0.167 |
mallow | -0.159 |
bda | -0.159 |
hof | -0.151 |
assic | -0.141 |
Token | EX |
Token ID | 7788 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
Whites | +0.069 |
udo | +0.063 |
="# | +0.062 |
YP | +0.061 |
Sel | +0.059 |
Neg logit contributions | |
abeth | -0.092 |
bda | -0.087 |
mallow | -0.087 |
hof | -0.082 |
assic | -0.075 |
Token | AM |
Token ID | 2390 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Whites | +0.538 |
udo | +0.497 |
="# | +0.480 |
YP | +0.476 |
Sel | +0.464 |
Neg logit contributions | |
abeth | -0.943 |
bda | -0.898 |
mallow | -0.895 |
hof | -0.851 |
assic | -0.786 |
Token | came |
Token ID | 1625 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
Whites | +1.250 |
udo | +1.165 |
="# | +1.133 |
YP | +1.126 |
Sel | +1.098 |
Neg logit contributions | |
abeth | -1.274 |
bda | -1.192 |
mallow | -1.189 |
hof | -1.118 |
assic | -1.004 |
Token | out |
Token ID | 503 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Whites | +0.298 |
udo | +0.275 |
="# | +0.267 |
YP | +0.264 |
Sel | +0.258 |
Neg logit contributions | |
abeth | -0.390 |
mallow | -0.367 |
bda | -0.366 |
hof | -0.346 |
assic | -0.315 |
Token | a |
Token ID | 257 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Whites | +1.271 |
udo | +1.173 |
="# | +1.133 |
YP | +1.122 |
Sel | +1.112 |
Neg logit contributions | |
abeth | -1.309 |
bda | -1.222 |
mallow | -1.219 |
hof | -1.138 |
assic | -1.029 |
Token | little |
Token ID | 1310 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
Whites | +1.752 |
udo | +1.623 |
="# | +1.568 |
YP | +1.561 |
Sel | +1.536 |
Neg logit contributions | |
abeth | -1.893 |
mallow | -1.764 |
bda | -1.751 |
hof | -1.655 |
assic | -1.485 |
Token | more |
Token ID | 517 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
Whites | +4.295 |
udo | +3.924 |
Scouting | +3.762 |
YP | +3.752 |
="# | +3.737 |
Neg logit contributions | |
abeth | -5.042 |
mallow | -4.642 |
bda | -4.610 |
hof | -4.354 |
thia | -3.972 |
Token | polished |
Token ID | 23895 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Whites | +2.037 |
udo | +1.880 |
="# | +1.835 |
YP | +1.819 |
Sel | +1.786 |
Neg logit contributions | |
abeth | -1.987 |
bda | -1.874 |
mallow | -1.860 |
hof | -1.740 |
assic | -1.538 |
Token | . |
Token ID | 13 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
Whites | +1.663 |
udo | +1.546 |
YP | +1.496 |
="# | +1.496 |
Sel | +1.463 |
Neg logit contributions | |
abeth | -1.507 |
bda | -1.397 |
mallow | -1.394 |
hof | -1.304 |
assic | -1.156 |
Token | The |
Token ID | 383 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Whites | +0.567 |
udo | +0.520 |
="# | +0.500 |
YP | +0.498 |
Sel | +0.487 |
Neg logit contributions | |
abeth | -0.707 |
mallow | -0.663 |
bda | -0.662 |
hof | -0.624 |
assic | -0.574 |
Token | team |
Token ID | 1074 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
abeth | +0.106 |
mallow | +0.099 |
bda | +0.099 |
hof | +0.092 |
assic | +0.082 |
Neg logit contributions | |
Whites | -0.118 |
udo | -0.111 |
="# | -0.107 |
YP | -0.107 |
Sel | -0.104 |
Token | could |
Token ID | 714 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Whites | +0.421 |
udo | +0.390 |
="# | +0.379 |
YP | +0.376 |
Sel | +0.369 |
Neg logit contributions | |
abeth | -0.439 |
bda | -0.409 |
mallow | -0.409 |
hof | -0.383 |
assic | -0.344 |
Token |
|
Token ID | 198 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Whites | +0.750 |
udo | +0.694 |
="# | +0.675 |
YP | +0.665 |
Sel | +0.651 |
Neg logit contributions | |
abeth | -0.857 |
mallow | -0.800 |
bda | -0.799 |
hof | -0.751 |
assic | -0.682 |
Token |
|
Token ID | 198 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Whites | +0.325 |
udo | +0.302 |
="# | +0.293 |
YP | +0.290 |
Sel | +0.284 |
Neg logit contributions | |
abeth | -0.369 |
mallow | -0.346 |
bda | -0.346 |
hof | -0.325 |
assic | -0.293 |
Token | 3 |
Token ID | 18 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
abeth | +0.245 |
mallow | +0.230 |
bda | +0.230 |
hof | +0.217 |
assic | +0.196 |
Neg logit contributions | |
Whites | -0.199 |
udo | -0.183 |
="# | -0.178 |
YP | -0.174 |
Sel | -0.171 |
Token | D |
Token ID | 35 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Whites | +1.489 |
udo | +1.391 |
="# | +1.352 |
YP | +1.341 |
Sel | +1.317 |
Neg logit contributions | |
abeth | -1.449 |
mallow | -1.349 |
bda | -1.348 |
hof | -1.259 |
assic | -1.127 |
Token | MAX |
Token ID | 22921 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
Whites | +0.834 |
udo | +0.778 |
="# | +0.756 |
YP | +0.749 |
Sel | +0.736 |
Neg logit contributions | |
abeth | -0.843 |
mallow | -0.787 |
bda | -0.786 |
hof | -0.735 |
assic | -0.660 |
Token |
|
Token ID | 198 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
Whites | +4.243 |
udo | +3.857 |
YP | +3.807 |
="# | +3.719 |
Sel | +3.653 |
Neg logit contributions | |
abeth | -5.099 |
bda | -4.766 |
mallow | -4.735 |
hof | -4.448 |
assic | -4.100 |
Token |
|
Token ID | 198 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
Whites | +1.829 |
udo | +1.685 |
="# | +1.648 |
YP | +1.618 |
Sel | +1.597 |
Neg logit contributions | |
abeth | -2.359 |
mallow | -2.202 |
bda | -2.191 |
hof | -2.051 |
assic | -1.906 |
Token | 3 |
Token ID | 18 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
Whites | +0.439 |
udo | +0.406 |
="# | +0.393 |
YP | +0.390 |
Sel | +0.382 |
Neg logit contributions | |
abeth | -0.556 |
mallow | -0.522 |
bda | -0.521 |
hof | -0.491 |
assic | -0.446 |
Token | D |
Token ID | 35 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
abeth | +0.036 |
bda | +0.034 |
mallow | +0.034 |
hof | +0.031 |
assic | +0.028 |
Neg logit contributions | |
Whites | -0.041 |
udo | -0.038 |
="# | -0.037 |
YP | -0.037 |
Sel | -0.036 |
Token | MAX |
Token ID | 22921 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
Whites | +0.300 |
udo | +0.280 |
="# | +0.271 |
YP | +0.269 |
Sel | +0.264 |
Neg logit contributions | |
abeth | -0.323 |
mallow | -0.301 |
bda | -0.301 |
hof | -0.282 |
assic | -0.254 |
Token | ) |
Token ID | 8 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
Whites | +1.093 |
udo | +1.034 |
="# | +1.012 |
YP | +0.995 |
Sel | +0.988 |
Neg logit contributions | |
abeth | -0.878 |
bda | -0.804 |
mallow | -0.802 |
hof | -0.738 |
assic | -0.667 |
Token | Mem |
Token ID | 4942 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Whites | +0.644 |
udo | +0.603 |
="# | +0.587 |
YP | +0.582 |
Sel | +0.573 |
Neg logit contributions | |
abeth | -0.561 |
bda | -0.520 |
mallow | -0.520 |
hof | -0.483 |
assic | -0.429 |
Token | c |
Token ID | 66 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Whites | +0.671 |
udo | +0.626 |
="# | +0.608 |
YP | +0.594 |
Sel | +0.588 |
Neg logit contributions | |
abeth | -0.859 |
bda | -0.801 |
mallow | -0.800 |
hof | -0.756 |
assic | -0.687 |
Token | py |
Token ID | 9078 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Whites | +0.172 |
udo | +0.153 |
="# | +0.146 |
YP | +0.143 |
Sel | +0.139 |
Neg logit contributions | |
abeth | -0.402 |
mallow | -0.383 |
bda | -0.383 |
hof | -0.365 |
assic | -0.339 |
Token | In |
Token ID | 818 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
Whites | +0.750 |
udo | +0.696 |
="# | +0.677 |
YP | +0.670 |
Sel | +0.658 |
Neg logit contributions | |
abeth | -0.900 |
mallow | -0.844 |
bda | -0.842 |
hof | -0.794 |
assic | -0.720 |
Token | Memory |
Token ID | 30871 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
abeth | +0.630 |
mallow | +0.587 |
bda | +0.585 |
hof | +0.544 |
assic | +0.480 |
Neg logit contributions | |
Whites | -0.729 |
udo | -0.683 |
="# | -0.665 |
YP | -0.658 |
Sel | -0.646 |
Token | 4 |
Token ID | 604 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
Whites | +3.999 |
udo | +3.633 |
="# | +3.560 |
YP | +3.525 |
uda | +3.416 |
Neg logit contributions | |
abeth | -5.284 |
mallow | -4.946 |
bda | -4.919 |
hof | -4.674 |
assic | -4.301 |
Token | 66 |
Token ID | 2791 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
Whites | +0.562 |
udo | +0.515 |
="# | +0.497 |
YP | +0.490 |
Sel | +0.479 |
Neg logit contributions | |
abeth | -0.862 |
mallow | -0.813 |
bda | -0.813 |
hof | -0.770 |
assic | -0.707 |
Token | 284 |
Token ID | 30336 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
abeth | +0.022 |
bda | +0.021 |
mallow | +0.021 |
hof | +0.020 |
assic | +0.018 |
Neg logit contributions | |
Whites | -0.019 |
udo | -0.017 |
="# | -0.017 |
YP | -0.017 |
Sel | -0.016 |
Token | 4 |
Token ID | 604 |
Feature activation | -4.96e-03 |
Pos logit contributions | |
Whites | +2.726 |
udo | +2.488 |
="# | +2.424 |
YP | +2.384 |
Scouting | +2.313 |
Neg logit contributions | |
abeth | -3.614 |
mallow | -3.367 |
bda | -3.345 |
hof | -3.181 |
assic | -2.952 |
Token | 64 |
Token ID | 2414 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
abeth | +0.005 |
mallow | +0.005 |
bda | +0.005 |
hof | +0.005 |
assic | +0.005 |
Neg logit contributions | |
Whites | -0.002 |
udo | -0.002 |
="# | -0.002 |
YP | -0.002 |
Sel | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
abeth | +0.074 |
bda | +0.069 |
mallow | +0.069 |
hof | +0.064 |
assic | +0.057 |
Neg logit contributions | |
Whites | -0.080 |
udo | -0.075 |
="# | -0.073 |
YP | -0.072 |
Sel | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
abeth | +1.288 |
mallow | +1.199 |
bda | +1.198 |
hof | +1.119 |
assic | +0.996 |
Neg logit contributions | |
Whites | -1.373 |
udo | -1.285 |
="# | -1.251 |
YP | -1.239 |
Sel | -1.219 |
Token |
|
Token ID | 198 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Whites | +0.500 |
udo | +0.465 |
="# | +0.451 |
YP | +0.446 |
Sel | +0.438 |
Neg logit contributions | |
abeth | -0.555 |
mallow | -0.519 |
bda | -0.518 |
hof | -0.487 |
assic | -0.441 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Whites | +1.146 |
udo | +1.059 |
="# | +1.032 |
YP | +1.015 |
Sel | +1.003 |
Neg logit contributions | |
abeth | -1.431 |
mallow | -1.337 |
bda | -1.333 |
hof | -1.251 |
assic | -1.154 |
Token | In |
Token ID | 818 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Whites | +0.971 |
udo | +0.913 |
="# | +0.885 |
YP | +0.883 |
Sel | +0.872 |
Neg logit contributions | |
abeth | -1.169 |
mallow | -1.095 |
bda | -1.087 |
hof | -1.022 |
assic | -0.935 |
Token | total |
Token ID | 2472 |
Feature activation | +6.06e+00 |
Pos logit contributions | |
Whites | +1.383 |
udo | +1.278 |
="# | +1.235 |
YP | +1.234 |
uda | +1.214 |
Neg logit contributions | |
abeth | -1.413 |
mallow | -1.323 |
bda | -1.316 |
hof | -1.199 |
assic | -1.117 |
Token | , |
Token ID | 11 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Whites | +4.467 |
udo | +4.179 |
="# | +4.022 |
YP | +3.990 |
uda | +3.913 |
Neg logit contributions | |
abeth | -4.600 |
bda | -4.334 |
mallow | -4.311 |
hof | -4.011 |
assic | -3.635 |
Token | there |
Token ID | 612 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
Whites | +1.438 |
udo | +1.341 |
="# | +1.302 |
YP | +1.289 |
Sel | +1.265 |
Neg logit contributions | |
abeth | -1.394 |
mallow | -1.301 |
bda | -1.301 |
hof | -1.212 |
assic | -1.091 |
Token | were |
Token ID | 547 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Whites | +1.624 |
udo | +1.523 |
="# | +1.481 |
YP | +1.458 |
Sel | +1.435 |
Neg logit contributions | |
abeth | -1.727 |
mallow | -1.615 |
bda | -1.607 |
hof | -1.511 |
assic | -1.364 |
Token | around |
Token ID | 1088 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Whites | +0.721 |
udo | +0.667 |
="# | +0.647 |
YP | +0.640 |
Sel | +0.628 |
Neg logit contributions | |
abeth | -0.823 |
mallow | -0.771 |
bda | -0.768 |
hof | -0.721 |
assic | -0.653 |
Token | 25 |
Token ID | 1679 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
abeth | +0.335 |
mallow | +0.314 |
bda | +0.314 |
hof | +0.294 |
assic | +0.265 |
Neg logit contributions | |
Whites | -0.305 |
udo | -0.284 |
="# | -0.276 |
YP | -0.273 |
Sel | -0.268 |
Token | Tony |
Token ID | 8832 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
abeth | +0.201 |
mallow | +0.187 |
bda | +0.187 |
hof | +0.175 |
assic | +0.155 |
Neg logit contributions | |
Whites | -0.219 |
udo | -0.206 |
="# | -0.200 |
YP | -0.199 |
Sel | -0.195 |
Token | Ferguson |
Token ID | 15031 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
abeth | +0.060 |
mallow | +0.056 |
bda | +0.056 |
hof | +0.053 |
assic | +0.048 |
Neg logit contributions | |
Whites | -0.046 |
udo | -0.043 |
="# | -0.041 |
YP | -0.041 |
Sel | -0.040 |
Token | versus |
Token ID | 9051 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
Whites | +1.245 |
udo | +1.166 |
="# | +1.134 |
YP | +1.123 |
Sel | +1.106 |
Neg logit contributions | |
abeth | -1.114 |
bda | -1.031 |
mallow | -1.029 |
hof | -0.957 |
assic | -0.853 |
Token | Kh |
Token ID | 5311 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
abeth | +0.069 |
mallow | +0.064 |
bda | +0.064 |
hof | +0.059 |
assic | +0.053 |
Neg logit contributions | |
Whites | -0.077 |
udo | -0.072 |
="# | -0.070 |
YP | -0.069 |
Sel | -0.068 |
Token | ab |
Token ID | 397 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
abeth | +0.316 |
mallow | +0.293 |
bda | +0.292 |
hof | +0.275 |
assic | +0.239 |
Neg logit contributions | |
Whites | -0.362 |
udo | -0.347 |
="# | -0.330 |
YP | -0.329 |
uda | -0.325 |
Token | ib |
Token ID | 571 |
Feature activation | +6.04e+00 |
Pos logit contributions | |
Whites | +4.284 |
udo | +4.095 |
uda | +3.843 |
="# | +3.833 |
YP | +3.813 |
Neg logit contributions | |
abeth | -3.790 |
mallow | -3.568 |
bda | -3.501 |
hof | -3.271 |
thia | -2.872 |
Token | Nur |
Token ID | 49281 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Whites | +4.240 |
udo | +3.659 |
Sel | +3.505 |
="# | +3.463 |
uda | +3.452 |
Neg logit contributions | |
abeth | -5.185 |
mallow | -4.899 |
bda | -4.824 |
hof | -4.601 |
assic | -4.276 |
Token | mag |
Token ID | 19726 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
abeth | +1.415 |
mallow | +1.337 |
bda | +1.326 |
hof | +1.276 |
oop | +1.144 |
Neg logit contributions | |
Whites | -1.053 |
udo | -0.971 |
="# | -0.941 |
YP | -0.936 |
Scouting | -0.909 |
Token | omed |
Token ID | 12657 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
abeth | +1.180 |
mallow | +1.114 |
bda | +1.113 |
hof | +1.054 |
assic | +0.965 |
Neg logit contributions | |
Whites | -0.784 |
udo | -0.719 |
="# | -0.693 |
YP | -0.685 |
Sel | -0.669 |
Token | ov |
Token ID | 709 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
Whites | +1.914 |
udo | +1.675 |
="# | +1.648 |
YP | +1.542 |
idas | +1.522 |
Neg logit contributions | |
abeth | -4.757 |
mallow | -4.531 |
bda | -4.510 |
hof | -4.245 |
assic | -4.041 |
Token | – |
Token ID | 784 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
Whites | +0.426 |
udo | +0.399 |
="# | +0.389 |
YP | +0.386 |
Sel | +0.380 |
Neg logit contributions | |
abeth | -0.369 |
mallow | -0.342 |
bda | -0.341 |
hof | -0.317 |
assic | -0.282 |
Token | 's |
Token ID | 338 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
abeth | +0.783 |
mallow | +0.726 |
bda | +0.726 |
hof | +0.675 |
assic | +0.600 |
Neg logit contributions | |
Whites | -0.890 |
udo | -0.835 |
="# | -0.813 |
YP | -0.805 |
Sel | -0.792 |
Token | speed |
Token ID | 2866 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Whites | +0.949 |
udo | +0.898 |
="# | +0.880 |
YP | +0.868 |
Sel | +0.860 |
Neg logit contributions | |
abeth | -0.526 |
bda | -0.476 |
mallow | -0.474 |
hof | -0.429 |
assic | -0.363 |
Token | is |
Token ID | 318 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
abeth | +0.134 |
mallow | +0.125 |
bda | +0.125 |
hof | +0.117 |
assic | +0.105 |
Neg logit contributions | |
Whites | -0.128 |
udo | -0.120 |
="# | -0.116 |
YP | -0.115 |
Sel | -0.113 |
Token | calculated |
Token ID | 10488 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Whites | +1.494 |
udo | +1.377 |
="# | +1.331 |
YP | +1.311 |
Sel | +1.294 |
Neg logit contributions | |
abeth | -1.666 |
bda | -1.567 |
mallow | -1.557 |
hof | -1.453 |
assic | -1.332 |
Token | by |
Token ID | 416 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Whites | +1.016 |
udo | +0.937 |
="# | +0.911 |
YP | +0.894 |
Sel | +0.882 |
Neg logit contributions | |
abeth | -1.176 |
bda | -1.106 |
mallow | -1.097 |
hof | -1.024 |
assic | -0.946 |
Token | dividing |
Token ID | 27241 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
Whites | +0.704 |
udo | +0.646 |
="# | +0.627 |
YP | +0.614 |
Sel | +0.607 |
Neg logit contributions | |
abeth | -0.871 |
bda | -0.817 |
mallow | -0.816 |
hof | -0.764 |
assic | -0.704 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Whites | +4.415 |
udo | +4.059 |
="# | +3.976 |
YP | +3.838 |
Sel | +3.834 |
Neg logit contributions | |
abeth | -4.599 |
bda | -4.383 |
mallow | -4.287 |
hof | -4.049 |
assic | -3.755 |
Token | 84 |
Token ID | 5705 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Whites | +1.094 |
udo | +0.996 |
="# | +0.957 |
YP | +0.944 |
Sel | +0.921 |
Neg logit contributions | |
abeth | -1.866 |
mallow | -1.767 |
bda | -1.766 |
hof | -1.677 |
assic | -1.543 |
Token | million |
Token ID | 1510 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
abeth | +0.139 |
mallow | +0.128 |
bda | +0.127 |
hof | +0.116 |
assic | +0.099 |
Neg logit contributions | |
Whites | -0.221 |
udo | -0.209 |
="# | -0.205 |
YP | -0.203 |
Sel | -0.201 |
Token | miles |
Token ID | 4608 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
abeth | +0.208 |
mallow | +0.196 |
bda | +0.195 |
hof | +0.184 |
assic | +0.167 |
Neg logit contributions | |
Whites | -0.170 |
udo | -0.158 |
="# | -0.152 |
YP | -0.151 |
Sel | -0.148 |
Token | ( |
Token ID | 357 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
abeth | +1.463 |
mallow | +1.362 |
bda | +1.351 |
hof | +1.262 |
assic | +1.110 |
Neg logit contributions | |
Whites | -1.708 |
udo | -1.604 |
="# | -1.558 |
YP | -1.550 |
Sel | -1.525 |
Token | will |
Token ID | 481 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
abeth | +0.948 |
mallow | +0.886 |
bda | +0.885 |
hof | +0.832 |
assic | +0.748 |
Neg logit contributions | |
Whites | -0.875 |
udo | -0.813 |
="# | -0.791 |
YP | -0.784 |
Sel | -0.770 |
Token | go |
Token ID | 467 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
abeth | +1.167 |
bda | +1.094 |
mallow | +1.093 |
hof | +1.026 |
assic | +0.923 |
Neg logit contributions | |
Whites | -1.053 |
udo | -0.979 |
="# | -0.951 |
YP | -0.943 |
Sel | -0.925 |
Token | here |
Token ID | 994 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
abeth | +2.196 |
bda | +2.051 |
mallow | +2.050 |
hof | +1.922 |
assic | +1.698 |
Neg logit contributions | |
Whites | -2.289 |
udo | -2.150 |
="# | -2.082 |
YP | -2.063 |
Sel | -2.046 |
Token | + |
Token ID | 1343 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
abeth | +0.266 |
mallow | +0.249 |
bda | +0.249 |
hof | +0.234 |
assic | +0.211 |
Neg logit contributions | |
Whites | -0.244 |
udo | -0.227 |
="# | -0.221 |
YP | -0.218 |
Sel | -0.214 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
abeth | +0.582 |
bda | +0.543 |
mallow | +0.543 |
hof | +0.510 |
assic | +0.457 |
Neg logit contributions | |
Whites | -0.553 |
udo | -0.516 |
="# | -0.503 |
YP | -0.497 |
Sel | -0.488 |
Token | --+ |
Token ID | 44785 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
Whites | +1.342 |
udo | +1.044 |
="# | +0.828 |
YP | +0.786 |
Sel | +0.715 |
Neg logit contributions | |
abeth | -8.856 |
mallow | -8.573 |
bda | -8.505 |
hof | -8.199 |
assic | -7.769 |
Token | + |
Token ID | 1343 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Whites | +3.826 |
udo | +3.529 |
="# | +3.312 |
YP | +3.288 |
Sel | +3.258 |
Neg logit contributions | |
abeth | -5.228 |
mallow | -4.942 |
bda | -4.879 |
hof | -4.602 |
assic | -4.253 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
Whites | +2.122 |
udo | +1.978 |
="# | +1.900 |
YP | +1.889 |
Sel | +1.859 |
Neg logit contributions | |
abeth | -2.361 |
mallow | -2.214 |
bda | -2.199 |
hof | -2.062 |
assic | -1.869 |
Token | --+ |
Token ID | 44785 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
Whites | +0.963 |
udo | +0.720 |
="# | +0.580 |
YP | +0.533 |
Sel | +0.480 |
Neg logit contributions | |
abeth | -7.101 |
mallow | -6.855 |
bda | -6.816 |
hof | -6.578 |
assic | -6.231 |
Token | < |
Token ID | 1279 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
Whites | +3.620 |
udo | +3.338 |
="# | +3.158 |
YP | +3.127 |
Sel | +3.103 |
Neg logit contributions | |
abeth | -4.633 |
mallow | -4.353 |
bda | -4.303 |
hof | -4.056 |
assic | -3.724 |
Token | -- |
Token ID | 438 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
abeth | +0.403 |
mallow | +0.376 |
bda | +0.376 |
hof | +0.352 |
assic | +0.315 |
Neg logit contributions | |
Whites | -0.401 |
udo | -0.374 |
="# | -0.364 |
YP | -0.361 |
Sel | -0.354 |
Token | , |
Token ID | 11 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
abeth | +0.166 |
mallow | +0.154 |
bda | +0.154 |
hof | +0.143 |
assic | +0.127 |
Neg logit contributions | |
Whites | -0.192 |
udo | -0.180 |
="# | -0.175 |
YP | -0.174 |
Sel | -0.171 |
Token | old |
Token ID | 1468 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
abeth | +0.205 |
mallow | +0.191 |
bda | +0.191 |
hof | +0.179 |
assic | +0.160 |
Neg logit contributions | |
Whites | -0.203 |
udo | -0.189 |
="# | -0.184 |
YP | -0.182 |
Sel | -0.179 |
Token | photos |
Token ID | 5205 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
Whites | +0.679 |
udo | +0.628 |
="# | +0.614 |
YP | +0.610 |
Sel | +0.599 |
Neg logit contributions | |
abeth | -0.652 |
mallow | -0.606 |
bda | -0.605 |
hof | -0.562 |
assic | -0.505 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
abeth | +0.645 |
mallow | +0.597 |
bda | +0.595 |
hof | +0.555 |
assic | +0.490 |
Neg logit contributions | |
Whites | -0.762 |
udo | -0.717 |
="# | -0.698 |
YP | -0.692 |
Sel | -0.681 |
Token | etc |
Token ID | 3503 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
abeth | +0.106 |
mallow | +0.099 |
bda | +0.099 |
hof | +0.092 |
assic | +0.083 |
Neg logit contributions | |
Whites | -0.106 |
udo | -0.099 |
="# | -0.096 |
YP | -0.096 |
Sel | -0.094 |
Token | .? |
Token ID | 40791 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
Whites | +0.805 |
udo | +0.751 |
="# | +0.731 |
YP | +0.724 |
Sel | +0.712 |
Neg logit contributions | |
abeth | -0.767 |
bda | -0.716 |
mallow | -0.715 |
hof | -0.668 |
assic | -0.597 |
Token | Want |
Token ID | 16168 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
Whites | +4.032 |
udo | +3.586 |
="# | +3.553 |
YP | +3.488 |
Scouting | +3.465 |
Neg logit contributions | |
abeth | -4.931 |
mallow | -4.678 |
bda | -4.651 |
hof | -4.367 |
assic | -4.027 |
Token | to |
Token ID | 284 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
Whites | +2.576 |
udo | +2.330 |
="# | +2.309 |
YP | +2.270 |
Sel | +2.224 |
Neg logit contributions | |
abeth | -3.276 |
mallow | -3.056 |
bda | -3.041 |
hof | -2.839 |
assic | -2.610 |
Token | write |
Token ID | 3551 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Whites | +2.160 |
="# | +1.943 |
udo | +1.943 |
YP | +1.886 |
uda | +1.849 |
Neg logit contributions | |
abeth | -2.506 |
mallow | -2.355 |
bda | -2.340 |
hof | -2.197 |
assic | -2.037 |
Token | a |
Token ID | 257 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Whites | +1.842 |
udo | +1.681 |
="# | +1.642 |
YP | +1.625 |
Sel | +1.595 |
Neg logit contributions | |
abeth | -2.124 |
mallow | -1.985 |
bda | -1.984 |
hof | -1.862 |
assic | -1.691 |
Token | guest |
Token ID | 8319 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Whites | +0.885 |
udo | +0.818 |
="# | +0.805 |
YP | +0.798 |
Sel | +0.782 |
Neg logit contributions | |
abeth | -0.765 |
bda | -0.706 |
mallow | -0.703 |
hof | -0.658 |
assic | -0.589 |
Token | R |
Token ID | 371 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
abeth | +1.101 |
mallow | +1.022 |
bda | +1.021 |
hof | +0.954 |
assic | +0.849 |
Neg logit contributions | |
Whites | -1.179 |
udo | -1.112 |
="# | -1.081 |
YP | -1.072 |
Sel | -1.052 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Whites | +0.136 |
udo | +0.128 |
="# | +0.123 |
YP | +0.122 |
Sel | +0.120 |
Neg logit contributions | |
abeth | -0.138 |
bda | -0.130 |
mallow | -0.129 |
hof | -0.121 |
assic | -0.108 |
Token | E |
Token ID | 36 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
abeth | +0.789 |
mallow | +0.736 |
bda | +0.735 |
hof | +0.687 |
assic | +0.615 |
Neg logit contributions | |
Whites | -0.804 |
udo | -0.752 |
="# | -0.731 |
YP | -0.724 |
Sel | -0.711 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Whites | +1.647 |
udo | +1.546 |
="# | +1.493 |
YP | +1.484 |
Sel | +1.458 |
Neg logit contributions | |
abeth | -1.399 |
mallow | -1.306 |
bda | -1.301 |
hof | -1.212 |
assic | -1.068 |
Token | M |
Token ID | 44 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
abeth | +1.062 |
mallow | +0.989 |
bda | +0.986 |
hof | +0.923 |
assic | +0.825 |
Neg logit contributions | |
Whites | -1.078 |
udo | -1.012 |
="# | -0.984 |
YP | -0.972 |
Sel | -0.954 |
Token | .' |
Token ID | 2637 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
Whites | +0.990 |
udo | +0.924 |
="# | +0.898 |
YP | +0.891 |
Sel | +0.874 |
Neg logit contributions | |
abeth | -0.980 |
mallow | -0.917 |
bda | -0.916 |
hof | -0.855 |
assic | -0.766 |
Token | s |
Token ID | 82 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
Whites | +4.787 |
udo | +4.513 |
="# | +4.512 |
Sel | +4.430 |
YP | +4.427 |
Neg logit contributions | |
abeth | -4.069 |
bda | -3.751 |
mallow | -3.729 |
hof | -3.480 |
assic | -3.162 |
Token | lead |
Token ID | 1085 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Whites | +2.408 |
udo | +2.202 |
="# | +2.152 |
YP | +2.125 |
Sel | +2.103 |
Neg logit contributions | |
abeth | -2.280 |
mallow | -2.152 |
bda | -2.145 |
hof | -1.991 |
assic | -1.785 |
Token | singer |
Token ID | 14015 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Whites | +0.977 |
udo | +0.901 |
="# | +0.881 |
YP | +0.876 |
Sel | +0.857 |
Neg logit contributions | |
abeth | -0.978 |
mallow | -0.907 |
bda | -0.900 |
hof | -0.840 |
assic | -0.758 |
Token | Michael |
Token ID | 3899 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
Whites | +1.431 |
udo | +1.316 |
="# | +1.281 |
YP | +1.273 |
Sel | +1.261 |
Neg logit contributions | |
abeth | -1.284 |
bda | -1.204 |
mallow | -1.202 |
hof | -1.114 |
assic | -1.006 |
Token | St |
Token ID | 520 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Whites | +0.548 |
udo | +0.509 |
="# | +0.494 |
YP | +0.490 |
Sel | +0.481 |
Neg logit contributions | |
abeth | -0.553 |
bda | -0.517 |
mallow | -0.517 |
hof | -0.483 |
assic | -0.434 |
Token | hardship |
Token ID | 30699 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Whites | +0.702 |
udo | +0.654 |
="# | +0.637 |
YP | +0.629 |
Sel | +0.618 |
Neg logit contributions | |
abeth | -0.694 |
mallow | -0.647 |
bda | -0.646 |
hof | -0.604 |
assic | -0.539 |
Token | you |
Token ID | 345 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
Whites | +1.093 |
udo | +1.013 |
="# | +0.993 |
YP | +0.979 |
Sel | +0.965 |
Neg logit contributions | |
abeth | -1.040 |
mallow | -0.968 |
bda | -0.967 |
hof | -0.901 |
assic | -0.807 |
Token | can |
Token ID | 460 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Whites | +1.606 |
udo | +1.473 |
="# | +1.431 |
YP | +1.414 |
Sel | +1.390 |
Neg logit contributions | |
abeth | -1.838 |
bda | -1.735 |
mallow | -1.732 |
hof | -1.614 |
assic | -1.469 |
Token | contact |
Token ID | 2800 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Whites | +1.013 |
udo | +0.933 |
="# | +0.925 |
YP | +0.882 |
Sel | +0.878 |
Neg logit contributions | |
abeth | -1.158 |
mallow | -1.092 |
bda | -1.082 |
hof | -1.012 |
assic | -0.932 |
Token | Wh |
Token ID | 854 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Whites | +1.130 |
udo | +1.034 |
="# | +1.016 |
YP | +1.001 |
Sel | +0.984 |
Neg logit contributions | |
abeth | -1.242 |
bda | -1.163 |
mallow | -1.161 |
hof | -1.083 |
assic | -0.983 |
Token | itt |
Token ID | 715 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
Whites | +1.718 |
udo | +1.609 |
="# | +1.580 |
YP | +1.550 |
Sel | +1.530 |
Neg logit contributions | |
abeth | -1.694 |
bda | -1.600 |
mallow | -1.577 |
hof | -1.480 |
assic | -1.322 |
Token | les |
Token ID | 829 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
Whites | +1.676 |
udo | +1.342 |
="# | +1.332 |
YP | +1.298 |
Sel | +1.243 |
Neg logit contributions | |
abeth | -7.103 |
bda | -6.754 |
mallow | -6.697 |
hof | -6.455 |
assic | -6.173 |
Token | ea |
Token ID | 18213 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
Whites | +1.838 |
udo | +1.761 |
="# | +1.699 |
YP | +1.663 |
uda | +1.652 |
Neg logit contributions | |
abeth | -1.878 |
mallow | -1.760 |
bda | -1.758 |
hof | -1.658 |
assic | -1.488 |
Token | Community |
Token ID | 8108 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
abeth | +0.070 |
mallow | +0.065 |
bda | +0.065 |
hof | +0.061 |
assic | +0.055 |
Neg logit contributions | |
Whites | -0.064 |
udo | -0.060 |
="# | -0.058 |
YP | -0.057 |
Sel | -0.056 |
Token | Connect |
Token ID | 8113 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
Whites | +0.359 |
udo | +0.337 |
="# | +0.329 |
YP | +0.326 |
Sel | +0.321 |
Neg logit contributions | |
abeth | -0.291 |
mallow | -0.270 |
bda | -0.269 |
hof | -0.249 |
assic | -0.220 |
Token | ions |
Token ID | 507 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
abeth | +0.441 |
mallow | +0.399 |
bda | +0.398 |
hof | +0.358 |
assic | +0.304 |
Neg logit contributions | |
Whites | -0.815 |
udo | -0.774 |
="# | -0.759 |
YP | -0.752 |
Sel | -0.742 |
Token | Democratic |
Token ID | 33939 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
abeth | +0.458 |
mallow | +0.430 |
bda | +0.430 |
hof | +0.405 |
assic | +0.367 |
Neg logit contributions | |
Whites | -0.376 |
udo | -0.347 |
="# | -0.336 |
YP | -0.332 |
Sel | -0.325 |
Token | presidential |
Token ID | 4787 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
Whites | +0.440 |
udo | +0.401 |
="# | +0.387 |
YP | +0.382 |
Sel | +0.372 |
Neg logit contributions | |
abeth | -0.721 |
mallow | -0.682 |
bda | -0.681 |
hof | -0.646 |
assic | -0.594 |
Token | nominee |
Token ID | 10429 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
Whites | +0.290 |
udo | +0.264 |
="# | +0.254 |
YP | +0.251 |
Sel | +0.245 |
Neg logit contributions | |
abeth | -0.477 |
mallow | -0.451 |
bda | -0.451 |
hof | -0.428 |
assic | -0.393 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Whites | +0.643 |
udo | +0.592 |
="# | +0.574 |
YP | +0.566 |
Sel | +0.555 |
Neg logit contributions | |
abeth | -0.840 |
mallow | -0.792 |
bda | -0.791 |
hof | -0.746 |
assic | -0.679 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
abeth | +1.101 |
mallow | +1.038 |
bda | +1.035 |
hof | +0.980 |
assic | +0.894 |
Neg logit contributions | |
Whites | -0.768 |
udo | -0.718 |
="# | -0.686 |
YP | -0.681 |
Sel | -0.666 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -7.83e+00 |
Pos logit contributions | |
abeth | +0.496 |
mallow | +0.462 |
bda | +0.462 |
hof | +0.432 |
assic | +0.387 |
Neg logit contributions | |
Whites | -0.493 |
udo | -0.460 |
="# | -0.448 |
YP | -0.443 |
Sel | -0.436 |
Token | Diane |
Token ID | 26542 |
Feature activation | -7.13e+00 |
Pos logit contributions | |
abeth | +3.994 |
mallow | +3.564 |
bda | +3.522 |
hof | +3.117 |
Kathleen | +2.693 |
Neg logit contributions | |
Whites | -7.691 |
udo | -7.424 |
="# | -7.195 |
uda | -7.127 |
YP | -7.121 |
Token | Rodham |
Token ID | 41848 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
abeth | +5.481 |
bda | +5.138 |
mallow | +5.058 |
hof | +4.858 |
assic | +4.371 |
Neg logit contributions | |
Whites | -5.164 |
udo | -4.944 |
YP | -4.736 |
="# | -4.712 |
uda | -4.621 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -7.32e+00 |
Pos logit contributions | |
abeth | +5.142 |
mallow | +4.865 |
bda | +4.851 |
hof | +4.570 |
assic | +4.126 |
Neg logit contributions | |
Whites | -3.691 |
udo | -3.504 |
="# | -3.351 |
YP | -3.315 |
Sel | -3.268 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
abeth | +5.688 |
mallow | +5.263 |
bda | +5.245 |
hof | +4.944 |
assic | +4.442 |
Neg logit contributions | |
Whites | -5.319 |
udo | -4.910 |
="# | -4.902 |
uda | -4.695 |
YP | -4.686 |
Token | : |
Token ID | 25 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
abeth | +3.954 |
mallow | +3.615 |
bda | +3.588 |
hof | +3.351 |
assic | +2.899 |
Neg logit contributions | |
Whites | -5.618 |
udo | -5.392 |
="# | -5.235 |
YP | -5.151 |
uda | -5.098 |
Token | President |
Token ID | 1992 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
Whites | +1.318 |
udo | +1.203 |
="# | +1.161 |
YP | +1.144 |
Sel | +1.124 |
Neg logit contributions | |
abeth | -1.666 |
mallow | -1.570 |
bda | -1.567 |
hof | -1.470 |
assic | -1.343 |
Token | Trump |
Token ID | 1301 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
Whites | +0.327 |
udo | +0.300 |
="# | +0.290 |
YP | +0.286 |
Sel | +0.280 |
Neg logit contributions | |
abeth | -0.480 |
mallow | -0.453 |
bda | -0.453 |
hof | -0.429 |
assic | -0.392 |
Token | Donald |
Token ID | 3759 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
Whites | +0.818 |
udo | +0.765 |
="# | +0.741 |
YP | +0.734 |
Sel | +0.724 |
Neg logit contributions | |
abeth | -0.693 |
mallow | -0.640 |
bda | -0.638 |
hof | -0.590 |
assic | -0.524 |
Token | John |
Token ID | 1757 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
abeth | +2.449 |
bda | +2.235 |
mallow | +2.206 |
hof | +2.099 |
ield | +1.838 |
Neg logit contributions | |
Whites | -2.964 |
udo | -2.883 |
YP | -2.757 |
uda | -2.753 |
="# | -2.740 |
Token | Trump |
Token ID | 1301 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
abeth | +4.950 |
mallow | +4.695 |
bda | +4.647 |
hof | +4.489 |
assic | +3.971 |
Neg logit contributions | |
Whites | -4.707 |
udo | -4.637 |
YP | -4.404 |
="# | -4.399 |
uda | -4.346 |
Token | House |
Token ID | 18102 |
Feature activation | -7.70e+00 |
Pos logit contributions | |
abeth | +4.855 |
bda | +4.571 |
mallow | +4.526 |
hof | +4.364 |
assic | +3.899 |
Neg logit contributions | |
Whites | -4.274 |
udo | -3.924 |
="# | -3.851 |
YP | -3.745 |
uda | -3.728 |
Token | committee |
Token ID | 5583 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
abeth | +5.761 |
mallow | +5.414 |
bda | +5.369 |
hof | +5.193 |
assic | +4.789 |
Neg logit contributions | |
Whites | -5.624 |
="# | -5.525 |
udo | -5.382 |
Sel | -5.200 |
YP | -5.172 |
Token | believes |
Token ID | 5804 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
abeth | +0.730 |
mallow | +0.687 |
bda | +0.683 |
hof | +0.645 |
thia | +0.585 |
Neg logit contributions | |
Whites | -0.535 |
udo | -0.490 |
="# | -0.472 |
YP | -0.465 |
Sel | -0.458 |
Token | it |
Token ID | 340 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
abeth | +0.428 |
bda | +0.403 |
mallow | +0.402 |
hof | +0.380 |
assic | +0.340 |
Neg logit contributions | |
Whites | -0.384 |
udo | -0.361 |
="# | -0.350 |
YP | -0.344 |
Sel | -0.340 |
Token | has |
Token ID | 468 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
abeth | +1.599 |
mallow | +1.491 |
bda | +1.483 |
hof | +1.408 |
assic | +1.268 |
Neg logit contributions | |
Whites | -1.222 |
udo | -1.107 |
="# | -1.069 |
YP | -1.060 |
Sel | -1.039 |
Token | evidence |
Token ID | 2370 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
abeth | +0.431 |
mallow | +0.405 |
bda | +0.404 |
hof | +0.382 |
thia | +0.351 |
Neg logit contributions | |
Whites | -0.289 |
udo | -0.255 |
Fired | -0.248 |
YP | -0.247 |
Scouting | -0.237 |
Token | 're |
Token ID | 821 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
abeth | +2.073 |
bda | +1.955 |
mallow | +1.946 |
hof | +1.829 |
assic | +1.621 |
Neg logit contributions | |
Whites | -2.006 |
udo | -1.872 |
="# | -1.842 |
YP | -1.812 |
Sel | -1.779 |
Token | not |
Token ID | 407 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
abeth | +1.445 |
mallow | +1.364 |
bda | +1.355 |
hof | +1.282 |
assic | +1.158 |
Neg logit contributions | |
Whites | -1.184 |
udo | -1.111 |
="# | -1.068 |
YP | -1.062 |
Sel | -1.033 |
Token | a |
Token ID | 257 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
abeth | +1.660 |
mallow | +1.555 |
bda | +1.546 |
hof | +1.455 |
assic | +1.286 |
Neg logit contributions | |
Whites | -1.747 |
udo | -1.641 |
="# | -1.595 |
YP | -1.594 |
Sel | -1.556 |
Token | robot |
Token ID | 9379 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
abeth | +0.168 |
mallow | +0.154 |
bda | +0.154 |
hof | +0.141 |
assic | +0.122 |
Neg logit contributions | |
Whites | -0.253 |
udo | -0.239 |
="# | -0.233 |
YP | -0.231 |
Sel | -0.228 |
Token | by |
Token ID | 416 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
abeth | +2.065 |
mallow | +1.943 |
bda | +1.929 |
hof | +1.807 |
assic | +1.610 |
Neg logit contributions | |
Whites | -2.078 |
udo | -1.943 |
="# | -1.884 |
YP | -1.873 |
Sel | -1.843 |
Token | clicking |
Token ID | 12264 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
abeth | +0.524 |
mallow | +0.476 |
bda | +0.476 |
hof | +0.435 |
assic | +0.375 |
Neg logit contributions | |
Whites | -0.830 |
udo | -0.785 |
="# | -0.768 |
YP | -0.762 |
Sel | -0.751 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
abeth | +4.674 |
mallow | +4.408 |
bda | +4.312 |
hof | +3.903 |
circulation | +3.441 |
Neg logit contributions | |
Whites | -6.553 |
udo | -6.424 |
="# | -6.155 |
YP | -6.135 |
Sel | -6.034 |
Token | box |
Token ID | 3091 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
abeth | +1.203 |
mallow | +1.140 |
bda | +1.128 |
hof | +1.059 |
assic | +0.949 |
Neg logit contributions | |
Whites | -1.166 |
udo | -1.094 |
="# | -1.059 |
YP | -1.054 |
Sel | -1.035 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
abeth | +0.364 |
mallow | +0.337 |
bda | +0.336 |
hof | +0.311 |
assic | +0.274 |
Neg logit contributions | |
Whites | -0.458 |
udo | -0.431 |
="# | -0.420 |
YP | -0.417 |
Sel | -0.410 |
Token | Invalid |
Token ID | 17665 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
abeth | +0.573 |
mallow | +0.515 |
bda | +0.515 |
hof | +0.458 |
assic | +0.364 |
Neg logit contributions | |
Whites | -1.324 |
udo | -1.264 |
="# | -1.238 |
YP | -1.230 |
Sel | -1.217 |
Token | email |
Token ID | 3053 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
abeth | +2.080 |
mallow | +1.941 |
bda | +1.922 |
hof | +1.763 |
assic | +1.546 |
Neg logit contributions | |
Whites | -2.970 |
udo | -2.812 |
="# | -2.744 |
YP | -2.732 |
Sel | -2.687 |
Token | , |
Token ID | 11 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Whites | +0.371 |
udo | +0.346 |
="# | +0.336 |
YP | +0.333 |
Sel | +0.327 |
Neg logit contributions | |
abeth | -0.369 |
bda | -0.345 |
mallow | -0.345 |
hof | -0.321 |
assic | -0.291 |
Token | Baltimore |
Token ID | 10346 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
abeth | +0.275 |
mallow | +0.258 |
bda | +0.258 |
hof | +0.242 |
assic | +0.218 |
Neg logit contributions | |
Whites | -0.246 |
udo | -0.229 |
="# | -0.222 |
YP | -0.220 |
Sel | -0.215 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
abeth | +0.343 |
mallow | +0.320 |
bda | +0.319 |
hof | +0.299 |
assic | +0.268 |
Neg logit contributions | |
Whites | -0.339 |
udo | -0.317 |
="# | -0.308 |
YP | -0.305 |
Sel | -0.300 |
Token | The |
Token ID | 464 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
abeth | +0.714 |
bda | +0.671 |
mallow | +0.670 |
hof | +0.631 |
assic | +0.572 |
Neg logit contributions | |
Whites | -0.587 |
udo | -0.542 |
="# | -0.524 |
YP | -0.518 |
Sel | -0.506 |
Token | opinions |
Token ID | 9317 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Whites | +1.220 |
udo | +1.127 |
="# | +1.093 |
YP | +1.087 |
Sel | +1.064 |
Neg logit contributions | |
abeth | -1.274 |
mallow | -1.190 |
bda | -1.189 |
hof | -1.114 |
assic | -1.001 |
Token | expressed |
Token ID | 6241 |
Feature activation | -7.54e+00 |
Pos logit contributions | |
Whites | +0.830 |
udo | +0.750 |
="# | +0.718 |
YP | +0.709 |
Sel | +0.692 |
Neg logit contributions | |
abeth | -1.374 |
mallow | -1.303 |
bda | -1.302 |
hof | -1.236 |
assic | -1.138 |
Token | by |
Token ID | 416 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
abeth | +4.681 |
bda | +4.325 |
mallow | +4.132 |
hof | +3.975 |
circulation | +3.582 |
Neg logit contributions | |
Whites | -6.226 |
udo | -6.075 |
YP | -5.937 |
Sel | -5.896 |
Scouting | -5.892 |
Token | column |
Token ID | 5721 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
abeth | +2.889 |
bda | +2.718 |
mallow | +2.606 |
hof | +2.472 |
circulation | +2.197 |
Neg logit contributions | |
Whites | -3.854 |
YP | -3.827 |
udo | -3.768 |
idas | -3.700 |
="# | -3.671 |
Token | ists |
Token ID | 1023 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
abeth | +0.077 |
bda | +0.071 |
mallow | +0.069 |
hof | +0.064 |
assic | +0.052 |
Neg logit contributions | |
Whites | -0.149 |
udo | -0.141 |
YP | -0.138 |
="# | -0.138 |
Sel | -0.137 |
Token | are |
Token ID | 389 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Whites | +0.472 |
udo | +0.441 |
="# | +0.428 |
YP | +0.428 |
Sel | +0.419 |
Neg logit contributions | |
abeth | -0.532 |
bda | -0.498 |
mallow | -0.495 |
hof | -0.467 |
assic | -0.420 |
Token | their |
Token ID | 511 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
abeth | +1.402 |
bda | +1.310 |
mallow | +1.292 |
hof | +1.213 |
assic | +1.094 |
Neg logit contributions | |
Whites | -1.153 |
udo | -1.087 |
YP | -1.050 |
="# | -1.041 |
Sel | -1.029 |
Token | Donald |
Token ID | 3759 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Whites | +0.228 |
udo | +0.207 |
="# | +0.201 |
YP | +0.196 |
Sel | +0.193 |
Neg logit contributions | |
abeth | -0.341 |
mallow | -0.323 |
bda | -0.322 |
hof | -0.303 |
assic | -0.279 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Whites | +1.149 |
udo | +1.036 |
="# | +1.008 |
YP | +0.988 |
Sel | +0.978 |
Neg logit contributions | |
abeth | -1.560 |
bda | -1.469 |
mallow | -1.468 |
hof | -1.368 |
assic | -1.268 |
Token | Donald |
Token ID | 3759 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
Whites | +0.837 |
udo | +0.763 |
="# | +0.734 |
YP | +0.721 |
Sel | +0.711 |
Neg logit contributions | |
abeth | -1.287 |
mallow | -1.219 |
bda | -1.214 |
hof | -1.142 |
assic | -1.054 |
Token | John |
Token ID | 1757 |
Feature activation | -6.82e+00 |
Pos logit contributions | |
abeth | +2.744 |
bda | +2.516 |
mallow | +2.491 |
hof | +2.358 |
assic | +2.084 |
Neg logit contributions | |
Whites | -3.229 |
udo | -3.089 |
YP | -2.956 |
="# | -2.954 |
uda | -2.943 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
abeth | +5.183 |
mallow | +4.900 |
bda | +4.842 |
hof | +4.666 |
assic | +4.171 |
Neg logit contributions | |
Whites | -4.857 |
udo | -4.746 |
="# | -4.518 |
YP | -4.475 |
Sel | -4.444 |
Token | House |
Token ID | 18102 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
abeth | +4.581 |
bda | +4.298 |
mallow | +4.279 |
hof | +4.115 |
assic | +3.696 |
Neg logit contributions | |
Whites | -3.771 |
udo | -3.476 |
="# | -3.395 |
YP | -3.303 |
uda | -3.270 |
Token | committee |
Token ID | 5583 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
abeth | +5.708 |
mallow | +5.368 |
bda | +5.301 |
hof | +5.169 |
assic | +4.734 |
Neg logit contributions | |
Whites | -5.508 |
="# | -5.313 |
udo | -5.244 |
Sel | -5.009 |
YP | -4.989 |
Token | believes |
Token ID | 5804 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
abeth | +0.623 |
mallow | +0.586 |
bda | +0.584 |
hof | +0.550 |
thia | +0.501 |
Neg logit contributions | |
Whites | -0.450 |
udo | -0.412 |
="# | -0.397 |
YP | -0.392 |
Sel | -0.384 |
Token | it |
Token ID | 340 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
abeth | +0.782 |
mallow | +0.738 |
bda | +0.737 |
hof | +0.700 |
assic | +0.630 |
Neg logit contributions | |
Whites | -0.628 |
udo | -0.588 |
="# | -0.572 |
YP | -0.558 |
Sel | -0.553 |
Token | has |
Token ID | 468 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
abeth | +1.763 |
mallow | +1.647 |
bda | +1.637 |
hof | +1.552 |
assic | +1.396 |
Neg logit contributions | |
Whites | -1.337 |
udo | -1.212 |
="# | -1.167 |
YP | -1.159 |
Sel | -1.137 |
Token | evidence |
Token ID | 2370 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
abeth | +0.536 |
bda | +0.506 |
mallow | +0.504 |
hof | +0.477 |
assic | +0.437 |
Neg logit contributions | |
Whites | -0.370 |
udo | -0.331 |
YP | -0.323 |
Fired | -0.316 |
Scouting | -0.311 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Whites | +0.643 |
udo | +0.592 |
="# | +0.574 |
YP | +0.566 |
Sel | +0.555 |
Neg logit contributions | |
abeth | -0.840 |
mallow | -0.792 |
bda | -0.791 |
hof | -0.746 |
assic | -0.679 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
abeth | +1.101 |
mallow | +1.038 |
bda | +1.035 |
hof | +0.980 |
assic | +0.894 |
Neg logit contributions | |
Whites | -0.768 |
udo | -0.718 |
="# | -0.686 |
YP | -0.681 |
Sel | -0.666 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -7.83e+00 |
Pos logit contributions | |
abeth | +0.496 |
mallow | +0.462 |
bda | +0.462 |
hof | +0.432 |
assic | +0.387 |
Neg logit contributions | |
Whites | -0.493 |
udo | -0.460 |
="# | -0.448 |
YP | -0.443 |
Sel | -0.436 |
Token | Diane |
Token ID | 26542 |
Feature activation | -7.13e+00 |
Pos logit contributions | |
abeth | +3.994 |
mallow | +3.564 |
bda | +3.522 |
hof | +3.117 |
Kathleen | +2.693 |
Neg logit contributions | |
Whites | -7.691 |
udo | -7.424 |
="# | -7.195 |
uda | -7.127 |
YP | -7.121 |
Token | Rodham |
Token ID | 41848 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
abeth | +5.481 |
bda | +5.138 |
mallow | +5.058 |
hof | +4.858 |
assic | +4.371 |
Neg logit contributions | |
Whites | -5.164 |
udo | -4.944 |
YP | -4.736 |
="# | -4.712 |
uda | -4.621 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -7.32e+00 |
Pos logit contributions | |
abeth | +5.142 |
mallow | +4.865 |
bda | +4.851 |
hof | +4.570 |
assic | +4.126 |
Neg logit contributions | |
Whites | -3.691 |
udo | -3.504 |
="# | -3.351 |
YP | -3.315 |
Sel | -3.268 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
abeth | +5.688 |
mallow | +5.263 |
bda | +5.245 |
hof | +4.944 |
assic | +4.442 |
Neg logit contributions | |
Whites | -5.319 |
udo | -4.910 |
="# | -4.902 |
uda | -4.695 |
YP | -4.686 |
Token | : |
Token ID | 25 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
abeth | +3.954 |
mallow | +3.615 |
bda | +3.588 |
hof | +3.351 |
assic | +2.899 |
Neg logit contributions | |
Whites | -5.618 |
udo | -5.392 |
="# | -5.235 |
YP | -5.151 |
uda | -5.098 |
Token | ' |
Token ID | 705 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
abeth | +3.852 |
mallow | +3.649 |
bda | +3.525 |
hof | +3.374 |
assic | +2.966 |
Neg logit contributions | |
Whites | -4.309 |
udo | -4.062 |
="# | -4.023 |
YP | -3.969 |
Sel | -3.869 |
Token | I |
Token ID | 40 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
abeth | +1.509 |
mallow | +1.408 |
bda | +1.406 |
hof | +1.316 |
assic | +1.179 |
Neg logit contributions | |
Whites | -1.502 |
udo | -1.402 |
="# | -1.363 |
YP | -1.350 |
Sel | -1.325 |
Token | fully |
Token ID | 3938 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
abeth | +0.518 |
bda | +0.490 |
mallow | +0.480 |
hof | +0.458 |
assic | +0.421 |
Neg logit contributions | |
Whites | -0.404 |
udo | -0.380 |
YP | -0.365 |
="# | -0.361 |
Fired | -0.353 |
Token | 're |
Token ID | 821 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
abeth | +2.026 |
bda | +1.905 |
mallow | +1.900 |
hof | +1.788 |
assic | +1.588 |
Neg logit contributions | |
Whites | -1.925 |
udo | -1.794 |
="# | -1.767 |
YP | -1.736 |
Sel | -1.700 |
Token | not |
Token ID | 407 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
abeth | +1.015 |
mallow | +0.957 |
bda | +0.952 |
hof | +0.901 |
assic | +0.815 |
Neg logit contributions | |
Whites | -0.820 |
udo | -0.767 |
="# | -0.739 |
YP | -0.735 |
Sel | -0.714 |
Token | a |
Token ID | 257 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
abeth | +1.385 |
mallow | +1.295 |
bda | +1.290 |
hof | +1.212 |
assic | +1.079 |
Neg logit contributions | |
Whites | -1.408 |
udo | -1.318 |
="# | -1.283 |
YP | -1.277 |
Sel | -1.249 |
Token | robot |
Token ID | 9379 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
abeth | +0.120 |
mallow | +0.110 |
bda | +0.110 |
hof | +0.101 |
assic | +0.087 |
Neg logit contributions | |
Whites | -0.183 |
udo | -0.173 |
="# | -0.169 |
YP | -0.168 |
Sel | -0.166 |
Token | by |
Token ID | 416 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
abeth | +1.746 |
mallow | +1.641 |
bda | +1.630 |
hof | +1.528 |
assic | +1.362 |
Neg logit contributions | |
Whites | -1.746 |
udo | -1.632 |
="# | -1.583 |
YP | -1.573 |
Sel | -1.547 |
Token | clicking |
Token ID | 12264 |
Feature activation | -7.28e+00 |
Pos logit contributions | |
abeth | +0.184 |
mallow | +0.167 |
bda | +0.167 |
hof | +0.153 |
assic | +0.132 |
Neg logit contributions | |
Whites | -0.288 |
udo | -0.272 |
="# | -0.266 |
YP | -0.264 |
Sel | -0.260 |
Token | the |
Token ID | 262 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
abeth | +4.436 |
mallow | +4.195 |
bda | +4.104 |
hof | +3.724 |
circulation | +3.299 |
Neg logit contributions | |
Whites | -6.246 |
udo | -6.107 |
="# | -5.862 |
YP | -5.837 |
Sel | -5.732 |
Token | box |
Token ID | 3091 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
abeth | +0.772 |
mallow | +0.729 |
bda | +0.723 |
hof | +0.679 |
assic | +0.610 |
Neg logit contributions | |
Whites | -0.730 |
udo | -0.682 |
="# | -0.662 |
YP | -0.658 |
Sel | -0.645 |
Token | . |
Token ID | 13 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
Whites | +0.174 |
udo | +0.163 |
="# | +0.159 |
YP | +0.157 |
Sel | +0.155 |
Neg logit contributions | |
abeth | -0.143 |
mallow | -0.132 |
bda | -0.132 |
hof | -0.122 |
assic | -0.108 |
Token | Invalid |
Token ID | 17665 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
abeth | +0.252 |
mallow | +0.226 |
bda | +0.225 |
hof | +0.201 |
assic | +0.165 |
Neg logit contributions | |
Whites | -0.548 |
udo | -0.522 |
="# | -0.511 |
YP | -0.508 |
Sel | -0.501 |
Token | email |
Token ID | 3053 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
abeth | +1.488 |
mallow | +1.384 |
bda | +1.375 |
hof | +1.264 |
assic | +1.108 |
Neg logit contributions | |
Whites | -2.067 |
udo | -1.953 |
="# | -1.907 |
YP | -1.895 |
Sel | -1.865 |
Token | 're |
Token ID | 821 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
abeth | +2.280 |
bda | +2.142 |
mallow | +2.138 |
hof | +2.014 |
assic | +1.775 |
Neg logit contributions | |
Whites | -2.230 |
udo | -2.077 |
="# | -2.050 |
YP | -2.019 |
Sel | -1.973 |
Token | not |
Token ID | 407 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
abeth | +1.345 |
mallow | +1.269 |
bda | +1.259 |
hof | +1.192 |
assic | +1.075 |
Neg logit contributions | |
Whites | -1.111 |
udo | -1.043 |
="# | -1.003 |
YP | -1.001 |
Sel | -0.971 |
Token | a |
Token ID | 257 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
abeth | +1.467 |
mallow | +1.374 |
bda | +1.366 |
hof | +1.284 |
assic | +1.139 |
Neg logit contributions | |
Whites | -1.515 |
udo | -1.419 |
="# | -1.383 |
YP | -1.379 |
Sel | -1.346 |
Token | robot |
Token ID | 9379 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
abeth | +0.176 |
mallow | +0.161 |
bda | +0.161 |
hof | +0.148 |
assic | +0.128 |
Neg logit contributions | |
Whites | -0.268 |
udo | -0.253 |
="# | -0.247 |
YP | -0.245 |
Sel | -0.242 |
Token | by |
Token ID | 416 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
abeth | +1.835 |
mallow | +1.729 |
bda | +1.713 |
hof | +1.606 |
assic | +1.428 |
Neg logit contributions | |
Whites | -1.865 |
udo | -1.745 |
="# | -1.691 |
YP | -1.684 |
Sel | -1.656 |
Token | clicking |
Token ID | 12264 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
abeth | +0.230 |
mallow | +0.209 |
bda | +0.208 |
hof | +0.191 |
assic | +0.165 |
Neg logit contributions | |
Whites | -0.363 |
udo | -0.344 |
="# | -0.336 |
YP | -0.334 |
Sel | -0.329 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
abeth | +4.444 |
mallow | +4.209 |
bda | +4.095 |
hof | +3.721 |
circulation | +3.294 |
Neg logit contributions | |
Whites | -6.216 |
udo | -6.071 |
="# | -5.826 |
YP | -5.805 |
Sel | -5.704 |
Token | box |
Token ID | 3091 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
abeth | +0.906 |
mallow | +0.859 |
bda | +0.849 |
hof | +0.796 |
assic | +0.714 |
Neg logit contributions | |
Whites | -0.876 |
udo | -0.820 |
="# | -0.794 |
YP | -0.791 |
Sel | -0.776 |
Token | . |
Token ID | 13 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
Whites | +0.129 |
udo | +0.121 |
="# | +0.118 |
YP | +0.117 |
Sel | +0.115 |
Neg logit contributions | |
abeth | -0.105 |
mallow | -0.097 |
bda | -0.097 |
hof | -0.090 |
assic | -0.080 |
Token | Invalid |
Token ID | 17665 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
abeth | +0.270 |
mallow | +0.241 |
bda | +0.241 |
hof | +0.215 |
assic | +0.174 |
Neg logit contributions | |
Whites | -0.600 |
udo | -0.571 |
="# | -0.560 |
YP | -0.556 |
Sel | -0.549 |
Token | email |
Token ID | 3053 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
abeth | +1.797 |
mallow | +1.673 |
bda | +1.659 |
hof | +1.527 |
assic | +1.337 |
Neg logit contributions | |
Whites | -2.511 |
udo | -2.370 |
="# | -2.315 |
YP | -2.301 |
Sel | -2.265 |
Token | 're |
Token ID | 821 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
abeth | +1.838 |
mallow | +1.724 |
bda | +1.721 |
hof | +1.618 |
assic | +1.443 |
Neg logit contributions | |
Whites | -1.718 |
udo | -1.603 |
="# | -1.569 |
YP | -1.547 |
Sel | -1.514 |
Token | not |
Token ID | 407 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
abeth | +0.968 |
mallow | +0.913 |
bda | +0.908 |
hof | +0.858 |
assic | +0.778 |
Neg logit contributions | |
Whites | -0.779 |
udo | -0.731 |
="# | -0.702 |
YP | -0.698 |
Sel | -0.679 |
Token | a |
Token ID | 257 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
abeth | +1.238 |
mallow | +1.159 |
bda | +1.155 |
hof | +1.084 |
assic | +0.966 |
Neg logit contributions | |
Whites | -1.252 |
udo | -1.172 |
="# | -1.140 |
YP | -1.135 |
Sel | -1.110 |
Token | robot |
Token ID | 9379 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Whites | +0.016 |
udo | +0.015 |
="# | +0.015 |
YP | +0.015 |
Sel | +0.015 |
Neg logit contributions | |
abeth | -0.011 |
mallow | -0.010 |
bda | -0.010 |
hof | -0.009 |
assic | -0.008 |
Token | by |
Token ID | 416 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
abeth | +1.777 |
mallow | +1.670 |
bda | +1.659 |
hof | +1.554 |
assic | +1.387 |
Neg logit contributions | |
Whites | -1.771 |
udo | -1.656 |
="# | -1.606 |
YP | -1.595 |
Sel | -1.567 |
Token | clicking |
Token ID | 12264 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
abeth | +0.306 |
mallow | +0.278 |
bda | +0.278 |
hof | +0.255 |
assic | +0.220 |
Neg logit contributions | |
Whites | -0.484 |
udo | -0.457 |
="# | -0.448 |
YP | -0.444 |
Sel | -0.437 |
Token | the |
Token ID | 262 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
abeth | +4.437 |
mallow | +4.206 |
bda | +4.091 |
hof | +3.715 |
circulation | +3.292 |
Neg logit contributions | |
Whites | -6.194 |
udo | -6.064 |
="# | -5.824 |
YP | -5.782 |
Sel | -5.687 |
Token | box |
Token ID | 3091 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
abeth | +0.592 |
mallow | +0.558 |
bda | +0.554 |
hof | +0.520 |
assic | +0.468 |
Neg logit contributions | |
Whites | -0.550 |
udo | -0.513 |
="# | -0.498 |
YP | -0.494 |
Sel | -0.485 |
Token | . |
Token ID | 13 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
Whites | +0.221 |
udo | +0.207 |
="# | +0.202 |
YP | +0.200 |
Sel | +0.197 |
Neg logit contributions | |
abeth | -0.181 |
mallow | -0.167 |
bda | -0.167 |
hof | -0.155 |
assic | -0.137 |
Token | Invalid |
Token ID | 17665 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
abeth | +0.236 |
mallow | +0.211 |
bda | +0.211 |
hof | +0.188 |
assic | +0.155 |
Neg logit contributions | |
Whites | -0.508 |
udo | -0.483 |
="# | -0.474 |
YP | -0.471 |
Sel | -0.465 |
Token | email |
Token ID | 3053 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
abeth | +1.501 |
mallow | +1.393 |
bda | +1.385 |
hof | +1.275 |
assic | +1.119 |
Neg logit contributions | |
Whites | -2.050 |
udo | -1.935 |
="# | -1.887 |
YP | -1.875 |
Sel | -1.846 |
Token | Donald |
Token ID | 3759 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Whites | +0.032 |
udo | +0.029 |
="# | +0.028 |
YP | +0.028 |
Sel | +0.028 |
Neg logit contributions | |
abeth | -0.041 |
mallow | -0.038 |
bda | -0.038 |
hof | -0.036 |
assic | -0.033 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Whites | +0.885 |
udo | +0.810 |
="# | +0.786 |
YP | +0.776 |
Sel | +0.760 |
Neg logit contributions | |
abeth | -1.129 |
bda | -1.061 |
mallow | -1.058 |
hof | -0.995 |
assic | -0.904 |
Token | Donald |
Token ID | 3759 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
Whites | +0.105 |
udo | +0.098 |
="# | +0.096 |
YP | +0.095 |
Sel | +0.093 |
Neg logit contributions | |
abeth | -0.093 |
mallow | -0.087 |
bda | -0.086 |
hof | -0.080 |
assic | -0.071 |
Token | John |
Token ID | 1757 |
Feature activation | -7.04e+00 |
Pos logit contributions | |
abeth | +2.947 |
bda | +2.722 |
mallow | +2.671 |
hof | +2.523 |
assic | +2.236 |
Neg logit contributions | |
Whites | -3.620 |
udo | -3.521 |
uda | -3.360 |
YP | -3.331 |
="# | -3.320 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
abeth | +5.294 |
mallow | +5.031 |
bda | +4.967 |
hof | +4.810 |
assic | +4.278 |
Neg logit contributions | |
Whites | -4.996 |
udo | -4.942 |
="# | -4.662 |
YP | -4.631 |
Sel | -4.605 |
Token | House |
Token ID | 18102 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
abeth | +4.204 |
bda | +3.952 |
mallow | +3.940 |
hof | +3.767 |
assic | +3.396 |
Neg logit contributions | |
Whites | -3.492 |
udo | -3.234 |
="# | -3.157 |
YP | -3.087 |
uda | -3.030 |
Token | committee |
Token ID | 5583 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
abeth | +5.481 |
mallow | +5.166 |
bda | +5.130 |
hof | +4.960 |
assic | +4.545 |
Neg logit contributions | |
Whites | -5.157 |
="# | -4.971 |
udo | -4.896 |
Sel | -4.683 |
YP | -4.672 |
Token | believes |
Token ID | 5804 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
abeth | +0.714 |
mallow | +0.671 |
bda | +0.666 |
hof | +0.629 |
thia | +0.577 |
Neg logit contributions | |
Whites | -0.508 |
udo | -0.463 |
="# | -0.448 |
YP | -0.439 |
Sel | -0.433 |
Token | it |
Token ID | 340 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
abeth | +0.688 |
mallow | +0.650 |
bda | +0.649 |
hof | +0.615 |
assic | +0.553 |
Neg logit contributions | |
Whites | -0.595 |
udo | -0.562 |
="# | -0.545 |
YP | -0.531 |
Sel | -0.529 |
Token | has |
Token ID | 468 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
abeth | +1.699 |
mallow | +1.580 |
bda | +1.568 |
hof | +1.486 |
assic | +1.324 |
Neg logit contributions | |
Whites | -1.442 |
udo | -1.311 |
="# | -1.265 |
YP | -1.258 |
Sel | -1.237 |
Token | evidence |
Token ID | 2370 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
abeth | +0.459 |
bda | +0.434 |
mallow | +0.429 |
hof | +0.412 |
thia | +0.372 |
Neg logit contributions | |
Whites | -0.312 |
udo | -0.279 |
Fired | -0.269 |
YP | -0.269 |
Scouting | -0.260 |
Token | presidential |
Token ID | 4787 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
Whites | +0.440 |
udo | +0.401 |
="# | +0.387 |
YP | +0.382 |
Sel | +0.372 |
Neg logit contributions | |
abeth | -0.721 |
mallow | -0.682 |
bda | -0.681 |
hof | -0.646 |
assic | -0.594 |
Token | nominee |
Token ID | 10429 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
Whites | +0.290 |
udo | +0.264 |
="# | +0.254 |
YP | +0.251 |
Sel | +0.245 |
Neg logit contributions | |
abeth | -0.477 |
mallow | -0.451 |
bda | -0.451 |
hof | -0.428 |
assic | -0.393 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Whites | +0.643 |
udo | +0.592 |
="# | +0.574 |
YP | +0.566 |
Sel | +0.555 |
Neg logit contributions | |
abeth | -0.840 |
mallow | -0.792 |
bda | -0.791 |
hof | -0.746 |
assic | -0.679 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
abeth | +1.101 |
mallow | +1.038 |
bda | +1.035 |
hof | +0.980 |
assic | +0.894 |
Neg logit contributions | |
Whites | -0.768 |
udo | -0.718 |
="# | -0.686 |
YP | -0.681 |
Sel | -0.666 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -7.83e+00 |
Pos logit contributions | |
abeth | +0.496 |
mallow | +0.462 |
bda | +0.462 |
hof | +0.432 |
assic | +0.387 |
Neg logit contributions | |
Whites | -0.493 |
udo | -0.460 |
="# | -0.448 |
YP | -0.443 |
Sel | -0.436 |
Token | Diane |
Token ID | 26542 |
Feature activation | -7.13e+00 |
Pos logit contributions | |
abeth | +3.994 |
mallow | +3.564 |
bda | +3.522 |
hof | +3.117 |
Kathleen | +2.693 |
Neg logit contributions | |
Whites | -7.691 |
udo | -7.424 |
="# | -7.195 |
uda | -7.127 |
YP | -7.121 |
Token | Rodham |
Token ID | 41848 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
abeth | +5.481 |
bda | +5.138 |
mallow | +5.058 |
hof | +4.858 |
assic | +4.371 |
Neg logit contributions | |
Whites | -5.164 |
udo | -4.944 |
YP | -4.736 |
="# | -4.712 |
uda | -4.621 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -7.32e+00 |
Pos logit contributions | |
abeth | +5.142 |
mallow | +4.865 |
bda | +4.851 |
hof | +4.570 |
assic | +4.126 |
Neg logit contributions | |
Whites | -3.691 |
udo | -3.504 |
="# | -3.351 |
YP | -3.315 |
Sel | -3.268 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
abeth | +5.688 |
mallow | +5.263 |
bda | +5.245 |
hof | +4.944 |
assic | +4.442 |
Neg logit contributions | |
Whites | -5.319 |
udo | -4.910 |
="# | -4.902 |
uda | -4.695 |
YP | -4.686 |
Token | : |
Token ID | 25 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
abeth | +3.954 |
mallow | +3.615 |
bda | +3.588 |
hof | +3.351 |
assic | +2.899 |
Neg logit contributions | |
Whites | -5.618 |
udo | -5.392 |
="# | -5.235 |
YP | -5.151 |
uda | -5.098 |
Token | ' |
Token ID | 705 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
abeth | +3.852 |
mallow | +3.649 |
bda | +3.525 |
hof | +3.374 |
assic | +2.966 |
Neg logit contributions | |
Whites | -4.309 |
udo | -4.062 |
="# | -4.023 |
YP | -3.969 |
Sel | -3.869 |
Token | drops |
Token ID | 49253 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
abeth | +0.985 |
mallow | +0.919 |
bda | +0.918 |
hof | +0.865 |
assic | +0.769 |
Neg logit contributions | |
Whites | -0.972 |
udo | -0.903 |
="# | -0.877 |
YP | -0.874 |
Sel | -0.850 |
Token | - |
Token ID | 12 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
abeth | +0.901 |
mallow | +0.828 |
bda | +0.828 |
hof | +0.769 |
assic | +0.675 |
Neg logit contributions | |
Whites | -1.116 |
udo | -1.048 |
="# | -1.018 |
YP | -1.017 |
Sel | -0.993 |
Token | re |
Token ID | 260 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
abeth | +1.550 |
mallow | +1.433 |
bda | +1.427 |
hof | +1.352 |
assic | +1.195 |
Neg logit contributions | |
Whites | -1.562 |
udo | -1.444 |
="# | -1.404 |
YP | -1.397 |
Scouting | -1.360 |
Token | za |
Token ID | 4496 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
abeth | +3.342 |
bda | +3.155 |
mallow | +3.095 |
hof | +2.968 |
assic | +2.649 |
Neg logit contributions | |
Whites | -2.729 |
udo | -2.429 |
YP | -2.422 |
="# | -2.403 |
Scouting | -2.358 |
Token | - |
Token ID | 12 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
abeth | +1.675 |
mallow | +1.538 |
bda | +1.537 |
hof | +1.438 |
assic | +1.249 |
Neg logit contributions | |
Whites | -2.259 |
udo | -2.147 |
YP | -2.098 |
="# | -2.076 |
Sel | -2.047 |
Token | as |
Token ID | 292 |
Feature activation | -7.13e+00 |
Pos logit contributions | |
abeth | +1.286 |
mallow | +1.210 |
bda | +1.208 |
hof | +1.152 |
assic | +1.034 |
Neg logit contributions | |
Whites | -1.029 |
udo | -0.942 |
YP | -0.914 |
="# | -0.909 |
Sel | -0.890 |
Token | lan |
Token ID | 9620 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
abeth | +4.145 |
bda | +3.911 |
mallow | +3.896 |
hof | +3.616 |
ield | +3.055 |
Neg logit contributions | |
Whites | -6.666 |
YP | -6.171 |
udo | -6.091 |
Scouting | -6.070 |
�� | -5.988 |
Token | - |
Token ID | 12 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
abeth | +3.085 |
mallow | +2.828 |
bda | +2.825 |
hof | +2.651 |
assic | +2.276 |
Neg logit contributions | |
Whites | -4.197 |
udo | -4.004 |
YP | -3.875 |
="# | -3.862 |
Sel | -3.811 |
Token | after |
Token ID | 8499 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
abeth | +2.486 |
mallow | +2.312 |
bda | +2.311 |
hof | +2.185 |
assic | +1.938 |
Neg logit contributions | |
Whites | -2.461 |
udo | -2.283 |
="# | -2.209 |
YP | -2.202 |
Scouting | -2.145 |
Token | - |
Token ID | 12 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
abeth | +2.371 |
bda | +2.207 |
mallow | +2.197 |
hof | +2.058 |
assic | +1.768 |
Neg logit contributions | |
Whites | -3.200 |
udo | -3.023 |
="# | -2.956 |
YP | -2.952 |
Sel | -2.894 |
Token | prof |
Token ID | 5577 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
abeth | +1.116 |
mallow | +1.044 |
bda | +1.043 |
hof | +0.983 |
assic | +0.875 |
Neg logit contributions | |
Whites | -1.097 |
udo | -1.021 |
="# | -0.991 |
YP | -0.983 |
Sel | -0.961 |
Token | pl |
Token ID | 489 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
abeth | +1.412 |
mallow | +1.319 |
bda | +1.318 |
hof | +1.234 |
assic | +1.105 |
Neg logit contributions | |
Whites | -1.394 |
udo | -1.295 |
="# | -1.263 |
YP | -1.250 |
Sel | -1.229 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
abeth | +1.172 |
mallow | +1.092 |
bda | +1.091 |
hof | +1.019 |
assic | +0.911 |
Neg logit contributions | |
Whites | -1.218 |
udo | -1.137 |
="# | -1.107 |
YP | -1.096 |
Sel | -1.078 |
Token | us |
Token ID | 385 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
abeth | +0.999 |
bda | +0.927 |
mallow | +0.925 |
hof | +0.860 |
assic | +0.753 |
Neg logit contributions | |
Whites | -1.241 |
udo | -1.159 |
="# | -1.138 |
YP | -1.125 |
Sel | -1.107 |
Token | / |
Token ID | 14 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
abeth | +1.652 |
bda | +1.534 |
mallow | +1.528 |
hof | +1.425 |
assic | +1.255 |
Neg logit contributions | |
Whites | -1.858 |
udo | -1.730 |
="# | -1.693 |
YP | -1.677 |
Sel | -1.657 |
Token | wiki |
Token ID | 15466 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
abeth | +4.025 |
bda | +3.807 |
mallow | +3.772 |
hof | +3.584 |
ield | +3.111 |
Neg logit contributions | |
Whites | -3.917 |
udo | -3.648 |
="# | -3.562 |
YP | -3.488 |
Sel | -3.406 |
Token | / |
Token ID | 14 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
abeth | +0.281 |
mallow | +0.260 |
bda | +0.260 |
hof | +0.241 |
assic | +0.214 |
Neg logit contributions | |
Whites | -0.331 |
udo | -0.311 |
="# | -0.303 |
YP | -0.301 |
Sel | -0.296 |
Token | trans |
Token ID | 7645 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
abeth | +5.710 |
bda | +5.399 |
mallow | +5.345 |
hof | +5.083 |
ield | +4.554 |
Neg logit contributions | |
Whites | -4.822 |
udo | -4.360 |
="# | -4.293 |
YP | -4.106 |
idas | -4.102 |
Token | cript |
Token ID | 6519 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
abeth | +1.566 |
mallow | +1.434 |
bda | +1.430 |
hof | +1.310 |
assic | +1.109 |
Neg logit contributions | |
Whites | -2.485 |
udo | -2.332 |
="# | -2.283 |
YP | -2.265 |
Sel | -2.233 |
Token | s |
Token ID | 82 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
abeth | +1.390 |
bda | +1.287 |
mallow | +1.283 |
hof | +1.182 |
assic | +1.028 |
Neg logit contributions | |
Whites | -1.839 |
udo | -1.728 |
="# | -1.683 |
YP | -1.675 |
Sel | -1.645 |
Token | / |
Token ID | 14 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
Whites | +0.506 |
udo | +0.477 |
="# | +0.464 |
YP | +0.460 |
Sel | +0.453 |
Neg logit contributions | |
abeth | -0.418 |
mallow | -0.387 |
bda | -0.386 |
hof | -0.359 |
assic | -0.319 |
Token | sc |
Token ID | 1416 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
abeth | +3.985 |
bda | +3.761 |
mallow | +3.733 |
hof | +3.540 |
ield | +3.127 |
Neg logit contributions | |
Whites | -3.496 |
udo | -3.204 |
="# | -3.127 |
YP | -3.046 |
Fired | -2.985 |
Token | pl |
Token ID | 489 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
abeth | +2.447 |
mallow | +2.333 |
bda | +2.325 |
hof | +2.184 |
assic | +1.980 |
Neg logit contributions | |
Whites | -1.943 |
udo | -1.768 |
="# | -1.720 |
YP | -1.709 |
Sel | -1.657 |
Token | . |
Token ID | 13 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
abeth | +1.498 |
mallow | +1.390 |
bda | +1.390 |
hof | +1.290 |
assic | +1.101 |
Neg logit contributions | |
Whites | -2.078 |
udo | -1.941 |
="# | -1.898 |
YP | -1.892 |
Sel | -1.856 |
Token | us |
Token ID | 385 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
abeth | +0.674 |
mallow | +0.637 |
bda | +0.637 |
hof | +0.608 |
assic | +0.552 |
Neg logit contributions | |
Whites | -0.459 |
udo | -0.414 |
="# | -0.404 |
YP | -0.400 |
Sel | -0.388 |
Token | / |
Token ID | 14 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
abeth | +1.331 |
bda | +1.234 |
mallow | +1.231 |
hof | +1.144 |
assic | +1.003 |
Neg logit contributions | |
Whites | -1.622 |
udo | -1.525 |
="# | -1.485 |
YP | -1.475 |
Sel | -1.451 |
Token | wiki |
Token ID | 15466 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
abeth | +3.798 |
bda | +3.594 |
mallow | +3.545 |
hof | +3.393 |
assic | +3.017 |
Neg logit contributions | |
Whites | -3.248 |
udo | -2.993 |
="# | -2.948 |
YP | -2.889 |
Fired | -2.817 |
Token | / |
Token ID | 14 |
Feature activation | -7.04e+00 |
Pos logit contributions | |
abeth | +0.135 |
mallow | +0.125 |
bda | +0.125 |
hof | +0.116 |
assic | +0.104 |
Neg logit contributions | |
Whites | -0.151 |
udo | -0.142 |
="# | -0.139 |
YP | -0.137 |
Sel | -0.135 |
Token | trans |
Token ID | 7645 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
abeth | +5.454 |
bda | +5.172 |
mallow | +5.118 |
hof | +4.896 |
ield | +4.304 |
Neg logit contributions | |
Whites | -5.095 |
udo | -4.640 |
="# | -4.553 |
YP | -4.384 |
Fired | -4.353 |
Token | cript |
Token ID | 6519 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
abeth | +1.888 |
mallow | +1.749 |
bda | +1.745 |
hof | +1.640 |
assic | +1.448 |
Neg logit contributions | |
Whites | -2.052 |
udo | -1.899 |
="# | -1.843 |
YP | -1.843 |
Sel | -1.805 |
Token | s |
Token ID | 82 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
abeth | +1.530 |
bda | +1.402 |
mallow | +1.398 |
hof | +1.282 |
assic | +1.089 |
Neg logit contributions | |
Whites | -2.476 |
udo | -2.336 |
="# | -2.278 |
YP | -2.274 |
Sel | -2.229 |
Token | / |
Token ID | 14 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
Whites | +0.696 |
udo | +0.653 |
="# | +0.637 |
YP | +0.630 |
Sel | +0.620 |
Neg logit contributions | |
abeth | -0.620 |
mallow | -0.576 |
bda | -0.575 |
hof | -0.535 |
assic | -0.478 |
Token | sc |
Token ID | 1416 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
abeth | +3.135 |
bda | +2.952 |
mallow | +2.939 |
hof | +2.768 |
assic | +2.408 |
Neg logit contributions | |
Whites | -3.285 |
udo | -3.034 |
="# | -2.964 |
YP | -2.906 |
Sel | -2.839 |
Token | matchup |
Token ID | 18406 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Whites | +0.206 |
udo | +0.190 |
="# | +0.184 |
YP | +0.182 |
Sel | +0.178 |
Neg logit contributions | |
abeth | -0.253 |
bda | -0.236 |
mallow | -0.236 |
hof | -0.222 |
assic | -0.201 |
Token | between |
Token ID | 1022 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
Whites | +1.271 |
udo | +1.180 |
="# | +1.153 |
YP | +1.141 |
Sel | +1.126 |
Neg logit contributions | |
abeth | -1.102 |
bda | -1.021 |
mallow | -1.019 |
hof | -0.939 |
assic | -0.842 |
Token | Donald |
Token ID | 3759 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Whites | +0.032 |
udo | +0.029 |
="# | +0.028 |
YP | +0.028 |
Sel | +0.028 |
Neg logit contributions | |
abeth | -0.041 |
mallow | -0.038 |
bda | -0.038 |
hof | -0.036 |
assic | -0.033 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Whites | +0.885 |
udo | +0.810 |
="# | +0.786 |
YP | +0.776 |
Sel | +0.760 |
Neg logit contributions | |
abeth | -1.129 |
bda | -1.061 |
mallow | -1.058 |
hof | -0.995 |
assic | -0.904 |
Token | Donald |
Token ID | 3759 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
Whites | +0.105 |
udo | +0.098 |
="# | +0.096 |
YP | +0.095 |
Sel | +0.093 |
Neg logit contributions | |
abeth | -0.093 |
mallow | -0.087 |
bda | -0.086 |
hof | -0.080 |
assic | -0.071 |
Token | John |
Token ID | 1757 |
Feature activation | -7.04e+00 |
Pos logit contributions | |
abeth | +2.947 |
bda | +2.722 |
mallow | +2.671 |
hof | +2.523 |
assic | +2.236 |
Neg logit contributions | |
Whites | -3.620 |
udo | -3.521 |
uda | -3.360 |
YP | -3.331 |
="# | -3.320 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
abeth | +5.294 |
mallow | +5.031 |
bda | +4.967 |
hof | +4.810 |
assic | +4.278 |
Neg logit contributions | |
Whites | -4.996 |
udo | -4.942 |
="# | -4.662 |
YP | -4.631 |
Sel | -4.605 |
Token | House |
Token ID | 18102 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
abeth | +4.204 |
bda | +3.952 |
mallow | +3.940 |
hof | +3.767 |
assic | +3.396 |
Neg logit contributions | |
Whites | -3.492 |
udo | -3.234 |
="# | -3.157 |
YP | -3.087 |
uda | -3.030 |
Token | committee |
Token ID | 5583 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
abeth | +5.481 |
mallow | +5.166 |
bda | +5.130 |
hof | +4.960 |
assic | +4.545 |
Neg logit contributions | |
Whites | -5.157 |
="# | -4.971 |
udo | -4.896 |
Sel | -4.683 |
YP | -4.672 |
Token | believes |
Token ID | 5804 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
abeth | +0.714 |
mallow | +0.671 |
bda | +0.666 |
hof | +0.629 |
thia | +0.577 |
Neg logit contributions | |
Whites | -0.508 |
udo | -0.463 |
="# | -0.448 |
YP | -0.439 |
Sel | -0.433 |
Token | it |
Token ID | 340 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
abeth | +0.688 |
mallow | +0.650 |
bda | +0.649 |
hof | +0.615 |
assic | +0.553 |
Neg logit contributions | |
Whites | -0.595 |
udo | -0.562 |
="# | -0.545 |
YP | -0.531 |
Sel | -0.529 |
Token | Are |
Token ID | 4231 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
abeth | +0.674 |
mallow | +0.635 |
bda | +0.634 |
hof | +0.599 |
assic | +0.545 |
Neg logit contributions | |
Whites | -0.487 |
udo | -0.452 |
="# | -0.436 |
YP | -0.431 |
Sel | -0.422 |
Token | you |
Token ID | 345 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
abeth | +1.707 |
mallow | +1.569 |
bda | +1.560 |
hof | +1.442 |
assic | +1.252 |
Neg logit contributions | |
Whites | -2.285 |
udo | -2.181 |
="# | -2.122 |
YP | -2.102 |
Sel | -2.078 |
Token | able |
Token ID | 1498 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
abeth | +0.885 |
mallow | +0.825 |
bda | +0.825 |
hof | +0.771 |
assic | +0.691 |
Neg logit contributions | |
Whites | -0.888 |
udo | -0.828 |
="# | -0.805 |
YP | -0.798 |
Sel | -0.784 |
Token | to |
Token ID | 284 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
abeth | +0.558 |
mallow | +0.525 |
bda | +0.523 |
hof | +0.493 |
assic | +0.445 |
Neg logit contributions | |
Whites | -0.465 |
udo | -0.432 |
="# | -0.417 |
YP | -0.414 |
Sel | -0.406 |
Token | sit |
Token ID | 1650 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
abeth | +0.299 |
bda | +0.280 |
mallow | +0.280 |
hof | +0.263 |
assic | +0.238 |
Neg logit contributions | |
Whites | -0.263 |
udo | -0.243 |
="# | -0.237 |
YP | -0.233 |
Sel | -0.229 |
Token | back |
Token ID | 736 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
abeth | +0.743 |
mallow | +0.693 |
bda | +0.692 |
hof | +0.645 |
assic | +0.576 |
Neg logit contributions | |
Whites | -0.793 |
udo | -0.740 |
="# | -0.721 |
YP | -0.714 |
Sel | -0.702 |
Token | and |
Token ID | 290 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
abeth | +4.378 |
mallow | +3.994 |
bda | +3.936 |
hof | +3.702 |
assic | +3.131 |
Neg logit contributions | |
Whites | -6.023 |
udo | -5.762 |
="# | -5.662 |
YP | -5.634 |
Sel | -5.544 |
Token | appreciate |
Token ID | 9144 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
abeth | +1.264 |
mallow | +1.183 |
bda | +1.182 |
hof | +1.108 |
assic | +0.998 |
Neg logit contributions | |
Whites | -1.142 |
udo | -1.066 |
="# | -1.033 |
YP | -1.025 |
Sel | -1.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Whites | +0.912 |
udo | +0.841 |
="# | +0.818 |
YP | +0.815 |
Sel | +0.797 |
Neg logit contributions | |
abeth | -0.942 |
bda | -0.878 |
mallow | -0.877 |
hof | -0.824 |
assic | -0.744 |
Token | ride |
Token ID | 6594 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Whites | +0.167 |
udo | +0.155 |
="# | +0.151 |
YP | +0.150 |
Sel | +0.147 |
Neg logit contributions | |
abeth | -0.154 |
bda | -0.142 |
mallow | -0.142 |
hof | -0.132 |
assic | -0.118 |
Token | you |
Token ID | 345 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Whites | +0.822 |
udo | +0.765 |
="# | +0.745 |
YP | +0.738 |
Sel | +0.726 |
Neg logit contributions | |
abeth | -0.731 |
bda | -0.677 |
mallow | -0.675 |
hof | -0.627 |
assic | -0.562 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
abeth | +2.196 |
mallow | +2.054 |
bda | +2.049 |
hof | +1.950 |
assic | +1.758 |
Neg logit contributions | |
Whites | -1.862 |
udo | -1.742 |
="# | -1.695 |
YP | -1.678 |
Sel | -1.632 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
abeth | +2.267 |
mallow | +2.132 |
bda | +2.120 |
hof | +2.020 |
assic | +1.828 |
Neg logit contributions | |
Whites | -1.655 |
udo | -1.567 |
="# | -1.498 |
YP | -1.486 |
Sel | -1.450 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
abeth | +1.790 |
bda | +1.676 |
mallow | +1.675 |
hof | +1.572 |
assic | +1.420 |
Neg logit contributions | |
Whites | -1.531 |
udo | -1.430 |
="# | -1.384 |
YP | -1.371 |
Sel | -1.339 |
Token | Diane |
Token ID | 26542 |
Feature activation | -6.47e+00 |
Pos logit contributions | |
abeth | +3.473 |
mallow | +3.133 |
bda | +3.077 |
hof | +2.746 |
Kathleen | +2.354 |
Neg logit contributions | |
Whites | -6.407 |
udo | -6.175 |
="# | -5.995 |
YP | -5.948 |
uda | -5.922 |
Token | Rodham |
Token ID | 41848 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
abeth | +4.968 |
bda | +4.667 |
mallow | +4.622 |
hof | +4.418 |
assic | +3.950 |
Neg logit contributions | |
Whites | -4.698 |
udo | -4.477 |
YP | -4.291 |
="# | -4.285 |
uda | -4.196 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
abeth | +4.452 |
mallow | +4.209 |
bda | +4.205 |
hof | +3.974 |
assic | +3.624 |
Neg logit contributions | |
Whites | -3.027 |
udo | -2.808 |
="# | -2.703 |
YP | -2.670 |
Sel | -2.616 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
abeth | +5.427 |
mallow | +5.042 |
bda | +5.025 |
hof | +4.704 |
assic | +4.267 |
Neg logit contributions | |
Whites | -5.103 |
udo | -4.685 |
="# | -4.673 |
YP | -4.507 |
uda | -4.455 |
Token | : |
Token ID | 25 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
abeth | +3.484 |
mallow | +3.181 |
bda | +3.172 |
hof | +2.921 |
assic | +2.515 |
Neg logit contributions | |
Whites | -5.355 |
udo | -5.105 |
="# | -4.976 |
YP | -4.916 |
Sel | -4.849 |
Token | ' |
Token ID | 705 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
abeth | +4.107 |
mallow | +3.924 |
bda | +3.663 |
hof | +3.570 |
Rath | +3.121 |
Neg logit contributions | |
Whites | -4.901 |
="# | -4.738 |
udo | -4.699 |
YP | -4.652 |
Sel | -4.508 |
Token | I |
Token ID | 40 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
abeth | +1.309 |
mallow | +1.222 |
bda | +1.218 |
hof | +1.141 |
assic | +1.020 |
Neg logit contributions | |
Whites | -1.314 |
udo | -1.226 |
="# | -1.193 |
YP | -1.179 |
Sel | -1.157 |
Token | fully |
Token ID | 3938 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
abeth | +0.386 |
bda | +0.367 |
mallow | +0.358 |
hof | +0.345 |
assic | +0.316 |
Neg logit contributions | |
Whites | -0.296 |
udo | -0.280 |
YP | -0.268 |
="# | -0.262 |
Fired | -0.261 |
Token | Republican |
Token ID | 3415 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Whites | +0.118 |
udo | +0.109 |
="# | +0.105 |
YP | +0.104 |
Sel | +0.102 |
Neg logit contributions | |
abeth | -0.159 |
mallow | -0.150 |
bda | -0.150 |
hof | -0.141 |
assic | -0.129 |
Token | nominee |
Token ID | 10429 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
abeth | +1.273 |
bda | +1.199 |
mallow | +1.197 |
hof | +1.142 |
assic | +1.039 |
Neg logit contributions | |
Whites | -0.881 |
udo | -0.813 |
="# | -0.786 |
YP | -0.785 |
Sel | -0.760 |
Token | Donald |
Token ID | 3759 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Whites | +0.228 |
udo | +0.207 |
="# | +0.201 |
YP | +0.196 |
Sel | +0.193 |
Neg logit contributions | |
abeth | -0.341 |
mallow | -0.323 |
bda | -0.322 |
hof | -0.303 |
assic | -0.279 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Whites | +1.149 |
udo | +1.036 |
="# | +1.008 |
YP | +0.988 |
Sel | +0.978 |
Neg logit contributions | |
abeth | -1.560 |
bda | -1.469 |
mallow | -1.468 |
hof | -1.368 |
assic | -1.268 |
Token | Donald |
Token ID | 3759 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
Whites | +0.837 |
udo | +0.763 |
="# | +0.734 |
YP | +0.721 |
Sel | +0.711 |
Neg logit contributions | |
abeth | -1.287 |
mallow | -1.219 |
bda | -1.214 |
hof | -1.142 |
assic | -1.054 |
Token | John |
Token ID | 1757 |
Feature activation | -6.82e+00 |
Pos logit contributions | |
abeth | +2.744 |
bda | +2.516 |
mallow | +2.491 |
hof | +2.358 |
assic | +2.084 |
Neg logit contributions | |
Whites | -3.229 |
udo | -3.089 |
YP | -2.956 |
="# | -2.954 |
uda | -2.943 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
abeth | +5.183 |
mallow | +4.900 |
bda | +4.842 |
hof | +4.666 |
assic | +4.171 |
Neg logit contributions | |
Whites | -4.857 |
udo | -4.746 |
="# | -4.518 |
YP | -4.475 |
Sel | -4.444 |
Token | House |
Token ID | 18102 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
abeth | +4.581 |
bda | +4.298 |
mallow | +4.279 |
hof | +4.115 |
assic | +3.696 |
Neg logit contributions | |
Whites | -3.771 |
udo | -3.476 |
="# | -3.395 |
YP | -3.303 |
uda | -3.270 |
Token | committee |
Token ID | 5583 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
abeth | +5.708 |
mallow | +5.368 |
bda | +5.301 |
hof | +5.169 |
assic | +4.734 |
Neg logit contributions | |
Whites | -5.508 |
="# | -5.313 |
udo | -5.244 |
Sel | -5.009 |
YP | -4.989 |
Token | believes |
Token ID | 5804 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
abeth | +0.623 |
mallow | +0.586 |
bda | +0.584 |
hof | +0.550 |
thia | +0.501 |
Neg logit contributions | |
Whites | -0.450 |
udo | -0.412 |
="# | -0.397 |
YP | -0.392 |
Sel | -0.384 |
Token | it |
Token ID | 340 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
abeth | +0.782 |
mallow | +0.738 |
bda | +0.737 |
hof | +0.700 |
assic | +0.630 |
Neg logit contributions | |
Whites | -0.628 |
udo | -0.588 |
="# | -0.572 |
YP | -0.558 |
Sel | -0.553 |
Token | . |
Token ID | 13 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
abeth | +0.023 |
mallow | +0.022 |
bda | +0.022 |
hof | +0.020 |
assic | +0.018 |
Neg logit contributions | |
Whites | -0.025 |
udo | -0.024 |
="# | -0.023 |
YP | -0.023 |
Sel | -0.023 |
Token | � |
Token ID | 447 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Whites | +0.259 |
udo | +0.240 |
="# | +0.233 |
YP | +0.231 |
Sel | +0.226 |
Neg logit contributions | |
abeth | -0.292 |
bda | -0.273 |
mallow | -0.273 |
hof | -0.257 |
assic | -0.232 |
Token | � |
Token ID | 251 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
Whites | +0.206 |
udo | +0.191 |
="# | +0.186 |
YP | +0.184 |
Sel | +0.180 |
Neg logit contributions | |
abeth | -0.229 |
mallow | -0.215 |
bda | -0.214 |
hof | -0.201 |
assic | -0.182 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
abeth | +0.360 |
mallow | +0.338 |
bda | +0.337 |
hof | +0.317 |
assic | +0.286 |
Neg logit contributions | |
Whites | -0.308 |
udo | -0.287 |
="# | -0.278 |
YP | -0.275 |
Sel | -0.270 |
Token | Image |
Token ID | 5159 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
abeth | +0.214 |
mallow | +0.201 |
bda | +0.201 |
hof | +0.189 |
assic | +0.172 |
Neg logit contributions | |
Whites | -0.176 |
udo | -0.163 |
="# | -0.158 |
YP | -0.156 |
Sel | -0.153 |
Token | copyright |
Token ID | 6634 |
Feature activation | -6.79e+00 |
Pos logit contributions | |
Whites | +1.479 |
udo | +1.384 |
="# | +1.350 |
YP | +1.330 |
Sel | +1.313 |
Neg logit contributions | |
abeth | -1.364 |
mallow | -1.268 |
bda | -1.265 |
hof | -1.181 |
assic | -1.051 |
Token | Deadline |
Token ID | 35954 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
abeth | +5.101 |
bda | +4.783 |
mallow | +4.769 |
hof | +4.529 |
Rath | +4.075 |
Neg logit contributions | |
Whites | -4.763 |
udo | -4.549 |
="# | -4.410 |
YP | -4.402 |
idas | -4.321 |
Token |
|
Token ID | 198 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Whites | +0.665 |
udo | +0.612 |
="# | +0.585 |
YP | +0.585 |
Sel | +0.571 |
Neg logit contributions | |
abeth | -0.959 |
mallow | -0.903 |
bda | -0.901 |
hof | -0.849 |
assic | -0.782 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Whites | +1.326 |
udo | +1.220 |
="# | +1.194 |
YP | +1.174 |
Sel | +1.160 |
Neg logit contributions | |
abeth | -1.627 |
mallow | -1.525 |
bda | -1.520 |
hof | -1.426 |
assic | -1.313 |
Token | Police |
Token ID | 9039 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Whites | +0.853 |
udo | +0.795 |
="# | +0.775 |
YP | +0.771 |
Sel | +0.761 |
Neg logit contributions | |
abeth | -0.987 |
mallow | -0.928 |
bda | -0.923 |
hof | -0.868 |
assic | -0.786 |
Token | have |
Token ID | 423 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
abeth | +0.263 |
mallow | +0.246 |
bda | +0.246 |
hof | +0.230 |
assic | +0.207 |
Neg logit contributions | |
Whites | -0.248 |
udo | -0.231 |
="# | -0.224 |
YP | -0.222 |
Sel | -0.218 |
Token | million |
Token ID | 1510 |
Feature activation | +9.26e-02 |
Pos logit contributions | |
Whites | +0.651 |
udo | +0.609 |
="# | +0.591 |
YP | +0.590 |
Sel | +0.579 |
Neg logit contributions | |
abeth | -0.607 |
mallow | -0.562 |
bda | -0.562 |
hof | -0.525 |
assic | -0.463 |
Token | years |
Token ID | 812 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Whites | +0.094 |
udo | +0.089 |
="# | +0.087 |
YP | +0.087 |
Sel | +0.085 |
Neg logit contributions | |
abeth | -0.048 |
mallow | -0.043 |
bda | -0.043 |
hof | -0.038 |
assic | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
abeth | +0.733 |
mallow | +0.679 |
bda | +0.678 |
hof | +0.630 |
assic | +0.558 |
Neg logit contributions | |
Whites | -0.870 |
udo | -0.817 |
="# | -0.798 |
YP | -0.790 |
Sel | -0.777 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
Whites | +0.293 |
udo | +0.271 |
="# | +0.262 |
YP | +0.260 |
Sel | +0.255 |
Neg logit contributions | |
abeth | -0.340 |
mallow | -0.319 |
bda | -0.318 |
hof | -0.299 |
assic | -0.271 |
Token | Image |
Token ID | 5159 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
abeth | +0.334 |
mallow | +0.314 |
bda | +0.314 |
hof | +0.295 |
assic | +0.268 |
Neg logit contributions | |
Whites | -0.275 |
udo | -0.254 |
="# | -0.246 |
YP | -0.244 |
Sel | -0.239 |
Token | copyright |
Token ID | 6634 |
Feature activation | -6.71e+00 |
Pos logit contributions | |
Whites | +1.486 |
udo | +1.391 |
="# | +1.355 |
YP | +1.336 |
Sel | +1.319 |
Neg logit contributions | |
abeth | -1.371 |
mallow | -1.275 |
bda | -1.272 |
hof | -1.186 |
assic | -1.056 |
Token | AFP |
Token ID | 8916 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
abeth | +5.028 |
bda | +4.719 |
mallow | +4.696 |
hof | +4.464 |
Rath | +4.010 |
Neg logit contributions | |
Whites | -4.729 |
udo | -4.521 |
="# | -4.389 |
YP | -4.379 |
idas | -4.302 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
abeth | +1.309 |
mallow | +1.243 |
bda | +1.241 |
hof | +1.180 |
assic | +1.083 |
Neg logit contributions | |
Whites | -0.775 |
udo | -0.704 |
="# | -0.685 |
YP | -0.670 |
Sel | -0.658 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Whites | +1.120 |
udo | +1.033 |
="# | +1.009 |
YP | +0.993 |
Sel | +0.980 |
Neg logit contributions | |
abeth | -1.361 |
mallow | -1.275 |
bda | -1.271 |
hof | -1.192 |
assic | -1.096 |
Token | The |
Token ID | 464 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Whites | +1.041 |
udo | +0.968 |
="# | +0.941 |
YP | +0.937 |
Sel | +0.923 |
Neg logit contributions | |
abeth | -1.313 |
mallow | -1.236 |
bda | -1.230 |
hof | -1.158 |
assic | -1.055 |
Token | Bank |
Token ID | 5018 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
Whites | +0.981 |
udo | +0.900 |
="# | +0.872 |
YP | +0.867 |
Sel | +0.848 |
Neg logit contributions | |
abeth | -1.118 |
mallow | -1.049 |
bda | -1.045 |
hof | -0.981 |
assic | -0.888 |
Token | the |
Token ID | 262 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
Whites | +1.046 |
udo | +0.971 |
="# | +0.948 |
YP | +0.935 |
Sel | +0.922 |
Neg logit contributions | |
abeth | -1.001 |
bda | -0.930 |
mallow | -0.929 |
hof | -0.867 |
assic | -0.775 |
Token | reason |
Token ID | 1738 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Whites | +0.303 |
udo | +0.281 |
="# | +0.272 |
YP | +0.270 |
Sel | +0.266 |
Neg logit contributions | |
abeth | -0.320 |
bda | -0.298 |
mallow | -0.297 |
hof | -0.278 |
assic | -0.250 |
Token | we |
Token ID | 356 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
Whites | +1.112 |
udo | +1.028 |
="# | +1.000 |
YP | +0.989 |
Sel | +0.975 |
Neg logit contributions | |
abeth | -1.145 |
bda | -1.068 |
mallow | -1.064 |
hof | -0.991 |
assic | -0.894 |
Token | lost |
Token ID | 2626 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Whites | +0.374 |
udo | +0.347 |
="# | +0.337 |
YP | +0.333 |
Sel | +0.328 |
Neg logit contributions | |
abeth | -0.411 |
mallow | -0.384 |
bda | -0.384 |
hof | -0.361 |
assic | -0.325 |
Token | the |
Token ID | 262 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Whites | +1.197 |
udo | +1.100 |
="# | +1.077 |
YP | +1.055 |
Sel | +1.050 |
Neg logit contributions | |
abeth | -1.255 |
bda | -1.182 |
mallow | -1.173 |
hof | -1.096 |
assic | -0.991 |
Token | Presidential |
Token ID | 17471 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
abeth | +0.138 |
mallow | +0.129 |
bda | +0.129 |
hof | +0.121 |
assic | +0.108 |
Neg logit contributions | |
Whites | -0.134 |
udo | -0.125 |
="# | -0.122 |
YP | -0.121 |
Sel | -0.118 |
Token | election |
Token ID | 3071 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Whites | +2.727 |
udo | +2.502 |
="# | +2.439 |
YP | +2.355 |
Sel | +2.343 |
Neg logit contributions | |
abeth | -3.073 |
bda | -2.890 |
mallow | -2.851 |
hof | -2.707 |
assic | -2.434 |
Token | was |
Token ID | 373 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Whites | +1.344 |
udo | +1.235 |
="# | +1.218 |
YP | +1.190 |
Sel | +1.178 |
Neg logit contributions | |
abeth | -1.404 |
bda | -1.309 |
mallow | -1.304 |
hof | -1.223 |
assic | -1.099 |
Token | that |
Token ID | 326 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
abeth | +0.930 |
mallow | +0.867 |
bda | +0.867 |
hof | +0.805 |
assic | +0.713 |
Neg logit contributions | |
Whites | -1.112 |
udo | -1.051 |
="# | -1.024 |
YP | -1.017 |
Sel | -0.999 |
Token | the |
Token ID | 262 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Whites | +0.236 |
udo | +0.220 |
="# | +0.213 |
YP | +0.211 |
Sel | +0.207 |
Neg logit contributions | |
abeth | -0.261 |
mallow | -0.244 |
bda | -0.244 |
hof | -0.229 |
assic | -0.206 |
Token | Democratic |
Token ID | 4390 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
Whites | +0.155 |
udo | +0.143 |
="# | +0.139 |
YP | +0.138 |
Sel | +0.135 |
Neg logit contributions | |
abeth | -0.174 |
bda | -0.162 |
mallow | -0.162 |
hof | -0.152 |
assic | -0.137 |
Token |
|
Token ID | 198 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
abeth | +0.975 |
mallow | +0.914 |
bda | +0.913 |
hof | +0.859 |
assic | +0.774 |
Neg logit contributions | |
Whites | -0.852 |
udo | -0.793 |
="# | -0.772 |
YP | -0.762 |
Sel | -0.747 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Whites | +0.618 |
udo | +0.574 |
="# | +0.557 |
YP | +0.551 |
Sel | +0.541 |
Neg logit contributions | |
abeth | -0.725 |
mallow | -0.679 |
bda | -0.677 |
hof | -0.636 |
assic | -0.578 |
Token | Rated |
Token ID | 15322 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
Whites | +1.224 |
udo | +1.160 |
="# | +1.135 |
YP | +1.124 |
Sel | +1.114 |
Neg logit contributions | |
abeth | -1.016 |
mallow | -0.935 |
bda | -0.931 |
hof | -0.865 |
assic | -0.769 |
Token | 5 |
Token ID | 642 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Whites | +0.375 |
udo | +0.350 |
="# | +0.340 |
YP | +0.337 |
Sel | +0.331 |
Neg logit contributions | |
abeth | -0.385 |
mallow | -0.359 |
bda | -0.359 |
hof | -0.336 |
assic | -0.302 |
Token | out |
Token ID | 503 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
abeth | +0.496 |
mallow | +0.473 |
bda | +0.471 |
hof | +0.450 |
assic | +0.413 |
Neg logit contributions | |
Whites | -0.260 |
udo | -0.235 |
="# | -0.225 |
YP | -0.223 |
Sel | -0.216 |
Token | of |
Token ID | 286 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
Whites | +2.307 |
udo | +2.155 |
="# | +2.108 |
YP | +2.046 |
Sel | +2.037 |
Neg logit contributions | |
abeth | -2.808 |
bda | -2.611 |
mallow | -2.586 |
hof | -2.413 |
assic | -2.261 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Whites | +2.734 |
udo | +2.516 |
="# | +2.443 |
YP | +2.402 |
Sel | +2.392 |
Neg logit contributions | |
abeth | -3.196 |
mallow | -2.948 |
bda | -2.941 |
hof | -2.775 |
assic | -2.566 |
Token | by |
Token ID | 416 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Whites | +1.178 |
udo | +1.095 |
="# | +1.063 |
YP | +1.051 |
Sel | +1.033 |
Neg logit contributions | |
abeth | -1.296 |
bda | -1.210 |
mallow | -1.207 |
hof | -1.131 |
assic | -1.028 |
Token | Quake |
Token ID | 42901 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
abeth | +1.418 |
mallow | +1.322 |
bda | +1.321 |
hof | +1.238 |
assic | +1.101 |
Neg logit contributions | |
Whites | -1.430 |
udo | -1.342 |
="# | -1.310 |
YP | -1.296 |
Sel | -1.271 |
Token | D |
Token ID | 35 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Whites | +0.044 |
udo | +0.041 |
="# | +0.040 |
YP | +0.039 |
Sel | +0.039 |
Neg logit contributions | |
abeth | -0.045 |
mallow | -0.042 |
bda | -0.042 |
hof | -0.039 |
assic | -0.035 |
Token | ude |
Token ID | 2507 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
Whites | +1.684 |
udo | +1.592 |
YP | +1.523 |
="# | +1.510 |
uda | +1.487 |
Neg logit contributions | |
abeth | -1.762 |
bda | -1.653 |
mallow | -1.646 |
hof | -1.533 |
assic | -1.383 |
Token | and |
Token ID | 290 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
Whites | +0.897 |
udo | +0.837 |
="# | +0.812 |
YP | +0.803 |
Sel | +0.791 |
Neg logit contributions | |
abeth | -0.830 |
bda | -0.774 |
mallow | -0.768 |
hof | -0.717 |
assic | -0.643 |
Token | wearing |
Token ID | 5762 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
abeth | +0.050 |
bda | +0.047 |
mallow | +0.047 |
hof | +0.044 |
assic | +0.039 |
Neg logit contributions | |
Whites | -0.052 |
udo | -0.048 |
="# | -0.047 |
YP | -0.047 |
Sel | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
abeth | +0.595 |
mallow | +0.556 |
bda | +0.555 |
hof | +0.520 |
assic | +0.467 |
Neg logit contributions | |
Whites | -0.568 |
udo | -0.530 |
="# | -0.514 |
YP | -0.509 |
Sel | -0.500 |
Token | face |
Token ID | 1986 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Whites | +1.241 |
udo | +1.149 |
="# | +1.113 |
YP | +1.089 |
Scouting | +1.079 |
Neg logit contributions | |
abeth | -1.261 |
bda | -1.187 |
mallow | -1.182 |
hof | -1.105 |
assic | -0.986 |
Token | of |
Token ID | 286 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
Whites | +1.228 |
udo | +1.151 |
="# | +1.104 |
YP | +1.089 |
Sel | +1.069 |
Neg logit contributions | |
abeth | -1.336 |
bda | -1.256 |
mallow | -1.243 |
hof | -1.171 |
assic | -1.057 |
Token | scandal |
Token ID | 10731 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
Whites | +2.341 |
udo | +2.163 |
="# | +2.094 |
YP | +2.064 |
Sel | +2.050 |
Neg logit contributions | |
abeth | -2.338 |
bda | -2.207 |
mallow | -2.182 |
hof | -2.040 |
assic | -1.842 |
Token | - |
Token ID | 12 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
Whites | +2.892 |
udo | +2.720 |
="# | +2.660 |
YP | +2.595 |
Sel | +2.590 |
Neg logit contributions | |
abeth | -2.706 |
bda | -2.526 |
mallow | -2.524 |
hof | -2.354 |
assic | -2.098 |
Token | hit |
Token ID | 17945 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
Whites | +0.571 |
udo | +0.530 |
="# | +0.513 |
YP | +0.508 |
Sel | +0.497 |
Neg logit contributions | |
abeth | -0.686 |
mallow | -0.644 |
bda | -0.643 |
hof | -0.605 |
assic | -0.548 |
Token | former |
Token ID | 1966 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Whites | +0.408 |
udo | +0.379 |
="# | +0.368 |
YP | +0.364 |
Sel | +0.359 |
Neg logit contributions | |
abeth | -0.419 |
bda | -0.393 |
mallow | -0.392 |
hof | -0.366 |
assic | -0.329 |
Token | International |
Token ID | 4037 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Whites | +1.282 |
udo | +1.178 |
="# | +1.148 |
YP | +1.128 |
Sel | +1.109 |
Neg logit contributions | |
abeth | -1.571 |
mallow | -1.477 |
bda | -1.475 |
hof | -1.385 |
assic | -1.257 |
Token | Monetary |
Token ID | 34112 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Whites | +0.816 |
udo | +0.750 |
="# | +0.733 |
YP | +0.721 |
Scouting | +0.712 |
Neg logit contributions | |
abeth | -0.890 |
bda | -0.838 |
mallow | -0.831 |
hof | -0.778 |
assic | -0.702 |
Token | here |
Token ID | 994 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
abeth | +2.196 |
bda | +2.051 |
mallow | +2.050 |
hof | +1.922 |
assic | +1.698 |
Neg logit contributions | |
Whites | -2.289 |
udo | -2.150 |
="# | -2.082 |
YP | -2.063 |
Sel | -2.046 |
Token | + |
Token ID | 1343 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
abeth | +0.266 |
mallow | +0.249 |
bda | +0.249 |
hof | +0.234 |
assic | +0.211 |
Neg logit contributions | |
Whites | -0.244 |
udo | -0.227 |
="# | -0.221 |
YP | -0.218 |
Sel | -0.214 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
abeth | +0.582 |
bda | +0.543 |
mallow | +0.543 |
hof | +0.510 |
assic | +0.457 |
Neg logit contributions | |
Whites | -0.553 |
udo | -0.516 |
="# | -0.503 |
YP | -0.497 |
Sel | -0.488 |
Token | --+ |
Token ID | 44785 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
Whites | +1.342 |
udo | +1.044 |
="# | +0.828 |
YP | +0.786 |
Sel | +0.715 |
Neg logit contributions | |
abeth | -8.856 |
mallow | -8.573 |
bda | -8.505 |
hof | -8.199 |
assic | -7.769 |
Token | + |
Token ID | 1343 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Whites | +3.826 |
udo | +3.529 |
="# | +3.312 |
YP | +3.288 |
Sel | +3.258 |
Neg logit contributions | |
abeth | -5.228 |
mallow | -4.942 |
bda | -4.879 |
hof | -4.602 |
assic | -4.253 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
Whites | +2.122 |
udo | +1.978 |
="# | +1.900 |
YP | +1.889 |
Sel | +1.859 |
Neg logit contributions | |
abeth | -2.361 |
mallow | -2.214 |
bda | -2.199 |
hof | -2.062 |
assic | -1.869 |
Token | --+ |
Token ID | 44785 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
Whites | +0.963 |
udo | +0.720 |
="# | +0.580 |
YP | +0.533 |
Sel | +0.480 |
Neg logit contributions | |
abeth | -7.101 |
mallow | -6.855 |
bda | -6.816 |
hof | -6.578 |
assic | -6.231 |
Token | < |
Token ID | 1279 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
Whites | +3.620 |
udo | +3.338 |
="# | +3.158 |
YP | +3.127 |
Sel | +3.103 |
Neg logit contributions | |
abeth | -4.633 |
mallow | -4.353 |
bda | -4.303 |
hof | -4.056 |
assic | -3.724 |
Token | -- |
Token ID | 438 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
abeth | +0.403 |
mallow | +0.376 |
bda | +0.376 |
hof | +0.352 |
assic | +0.315 |
Neg logit contributions | |
Whites | -0.401 |
udo | -0.374 |
="# | -0.364 |
YP | -0.361 |
Sel | -0.354 |
Token | Start |
Token ID | 7253 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
Whites | +1.169 |
udo | +1.084 |
="# | +1.045 |
YP | +1.040 |
Sel | +1.024 |
Neg logit contributions | |
abeth | -1.213 |
mallow | -1.131 |
bda | -1.125 |
hof | -1.054 |
assic | -0.951 |
Token | of |
Token ID | 286 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
Whites | +0.697 |
udo | +0.651 |
="# | +0.631 |
YP | +0.626 |
Sel | +0.617 |
Neg logit contributions | |
abeth | -0.670 |
mallow | -0.624 |
bda | -0.622 |
hof | -0.580 |
assic | -0.521 |
Token | make |
Token ID | 787 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Whites | +0.955 |
udo | +0.880 |
="# | +0.866 |
YP | +0.846 |
uda | +0.831 |
Neg logit contributions | |
abeth | -1.041 |
mallow | -0.970 |
bda | -0.969 |
hof | -0.909 |
assic | -0.823 |
Token | franchise |
Token ID | 8663 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Whites | +0.962 |
udo | +0.895 |
="# | +0.872 |
YP | +0.864 |
Sel | +0.847 |
Neg logit contributions | |
abeth | -0.905 |
bda | -0.844 |
mallow | -0.841 |
hof | -0.784 |
assic | -0.701 |
Token | - |
Token ID | 12 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Whites | +0.745 |
udo | +0.688 |
="# | +0.669 |
YP | +0.663 |
Sel | +0.653 |
Neg logit contributions | |
abeth | -0.799 |
mallow | -0.745 |
bda | -0.744 |
hof | -0.696 |
assic | -0.632 |
Token | sh |
Token ID | 1477 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Whites | +0.299 |
udo | +0.278 |
="# | +0.269 |
YP | +0.267 |
Sel | +0.263 |
Neg logit contributions | |
abeth | -0.344 |
mallow | -0.322 |
bda | -0.321 |
hof | -0.301 |
assic | -0.274 |
Token | ifting |
Token ID | 13309 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
Whites | +1.178 |
udo | +1.116 |
="# | +1.070 |
YP | +1.063 |
Sel | +1.041 |
Neg logit contributions | |
abeth | -1.121 |
bda | -1.041 |
mallow | -1.035 |
hof | -0.964 |
assic | -0.864 |
Token | personal |
Token ID | 2614 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
abeth | +0.614 |
mallow | +0.574 |
bda | +0.573 |
hof | +0.537 |
assic | +0.482 |
Neg logit contributions | |
Whites | -0.601 |
udo | -0.562 |
="# | -0.546 |
YP | -0.541 |
Sel | -0.531 |
Token | announcements |
Token ID | 24009 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Whites | +3.437 |
udo | +3.127 |
="# | +3.099 |
YP | +3.030 |
Scouting | +2.996 |
Neg logit contributions | |
abeth | -3.576 |
mallow | -3.301 |
bda | -3.282 |
hof | -3.083 |
assic | -2.821 |
Token | . |
Token ID | 13 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
abeth | +0.197 |
mallow | +0.184 |
bda | +0.184 |
hof | +0.172 |
assic | +0.154 |
Neg logit contributions | |
Whites | -0.203 |
udo | -0.190 |
="# | -0.184 |
YP | -0.183 |
Sel | -0.180 |
Token |
|
Token ID | 198 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Whites | +0.415 |
udo | +0.383 |
="# | +0.371 |
YP | +0.367 |
Sel | +0.360 |
Neg logit contributions | |
abeth | -0.501 |
bda | -0.471 |
mallow | -0.471 |
hof | -0.442 |
assic | -0.403 |
Token |
|
Token ID | 198 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Whites | +0.203 |
udo | +0.189 |
="# | +0.183 |
YP | +0.181 |
Sel | +0.178 |
Neg logit contributions | |
abeth | -0.232 |
mallow | -0.217 |
bda | -0.217 |
hof | -0.204 |
assic | -0.184 |
Token | Do |
Token ID | 5211 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
abeth | +0.486 |
mallow | +0.458 |
bda | +0.458 |
hof | +0.433 |
assic | +0.395 |
Neg logit contributions | |
Whites | -0.346 |
udo | -0.318 |
="# | -0.307 |
YP | -0.304 |
Sel | -0.297 |
Token | country |
Token ID | 1499 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
abeth | +0.172 |
bda | +0.161 |
mallow | +0.161 |
hof | +0.152 |
assic | +0.138 |
Neg logit contributions | |
Whites | -0.135 |
udo | -0.126 |
="# | -0.122 |
YP | -0.121 |
Sel | -0.118 |
Token | 's |
Token ID | 338 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Whites | +0.529 |
udo | +0.499 |
="# | +0.487 |
YP | +0.483 |
Sel | +0.476 |
Neg logit contributions | |
abeth | -0.372 |
mallow | -0.342 |
bda | -0.341 |
hof | -0.314 |
assic | -0.273 |
Token | exports |
Token ID | 15319 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Whites | +1.103 |
udo | +1.003 |
="# | +0.965 |
YP | +0.957 |
Sel | +0.942 |
Neg logit contributions | |
abeth | -1.415 |
mallow | -1.333 |
bda | -1.327 |
hof | -1.254 |
assic | -1.140 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Whites | +0.980 |
udo | +0.915 |
="# | +0.890 |
YP | +0.882 |
Sel | +0.866 |
Neg logit contributions | |
abeth | -0.903 |
mallow | -0.840 |
bda | -0.837 |
hof | -0.779 |
assic | -0.697 |
Token | were |
Token ID | 547 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Whites | +0.110 |
udo | +0.102 |
="# | +0.098 |
YP | +0.098 |
Sel | +0.096 |
Neg logit contributions | |
abeth | -0.117 |
mallow | -0.110 |
bda | -0.110 |
hof | -0.103 |
assic | -0.093 |
Token | a |
Token ID | 257 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
abeth | +0.963 |
mallow | +0.901 |
bda | +0.899 |
hof | +0.843 |
assic | +0.758 |
Neg logit contributions | |
Whites | -0.908 |
udo | -0.845 |
="# | -0.820 |
YP | -0.812 |
Sel | -0.798 |
Token | vital |
Token ID | 9204 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
Whites | +0.878 |
udo | +0.813 |
="# | +0.790 |
YP | +0.781 |
Sel | +0.767 |
Neg logit contributions | |
abeth | -0.970 |
mallow | -0.908 |
bda | -0.903 |
hof | -0.851 |
assic | -0.768 |
Token | part |
Token ID | 636 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
abeth | +0.437 |
mallow | +0.409 |
bda | +0.409 |
hof | +0.385 |
assic | +0.349 |
Neg logit contributions | |
Whites | -0.365 |
udo | -0.338 |
="# | -0.328 |
YP | -0.325 |
Sel | -0.318 |
Token | of |
Token ID | 286 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
Whites | +0.423 |
udo | +0.394 |
="# | +0.383 |
YP | +0.379 |
Sel | +0.373 |
Neg logit contributions | |
abeth | -0.442 |
mallow | -0.413 |
bda | -0.412 |
hof | -0.386 |
assic | -0.347 |
Token | its |
Token ID | 663 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
abeth | +0.618 |
bda | +0.579 |
mallow | +0.578 |
hof | +0.543 |
assic | +0.488 |
Neg logit contributions | |
Whites | -0.545 |
udo | -0.515 |
="# | -0.499 |
YP | -0.491 |
Sel | -0.481 |
Token | economy |
Token ID | 3773 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Whites | +0.226 |
udo | +0.209 |
="# | +0.202 |
YP | +0.201 |
Sel | +0.197 |
Neg logit contributions | |
abeth | -0.248 |
mallow | -0.232 |
bda | -0.232 |
hof | -0.218 |
assic | -0.196 |
Token | often |
Token ID | 1690 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
abeth | +1.400 |
mallow | +1.304 |
bda | +1.301 |
hof | +1.205 |
assic | +1.063 |
Neg logit contributions | |
Whites | -1.631 |
udo | -1.530 |
="# | -1.486 |
YP | -1.473 |
Sel | -1.451 |
Token | grim |
Token ID | 18288 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
abeth | +2.209 |
mallow | +2.060 |
bda | +2.051 |
hof | +1.909 |
assic | +1.714 |
Neg logit contributions | |
Whites | -2.489 |
udo | -2.344 |
="# | -2.280 |
YP | -2.262 |
Sel | -2.230 |
Token | world |
Token ID | 995 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
abeth | +0.910 |
mallow | +0.848 |
bda | +0.847 |
hof | +0.790 |
assic | +0.706 |
Neg logit contributions | |
Whites | -0.965 |
udo | -0.902 |
="# | -0.879 |
YP | -0.870 |
Sel | -0.856 |
Token | , |
Token ID | 11 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
abeth | +0.465 |
mallow | +0.433 |
bda | +0.432 |
hof | +0.404 |
assic | +0.360 |
Neg logit contributions | |
Whites | -0.497 |
udo | -0.465 |
="# | -0.453 |
YP | -0.449 |
Sel | -0.441 |
Token | the |
Token ID | 262 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
abeth | +0.467 |
bda | +0.434 |
mallow | +0.434 |
hof | +0.406 |
assic | +0.363 |
Neg logit contributions | |
Whites | -0.474 |
udo | -0.442 |
="# | -0.430 |
YP | -0.426 |
Sel | -0.418 |
Token | GL |
Token ID | 10188 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
abeth | +0.621 |
bda | +0.577 |
mallow | +0.577 |
hof | +0.538 |
assic | +0.481 |
Neg logit contributions | |
Whites | -0.648 |
udo | -0.604 |
="# | -0.587 |
YP | -0.582 |
Sel | -0.571 |
Token | OO |
Token ID | 6684 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Whites | +0.101 |
udo | +0.077 |
="# | +0.068 |
YP | +0.065 |
Sel | +0.058 |
Neg logit contributions | |
abeth | -0.647 |
mallow | -0.621 |
bda | -0.621 |
hof | -0.597 |
assic | -0.564 |
Token | cannon |
Token ID | 21202 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
Whites | +0.917 |
udo | +0.849 |
="# | +0.823 |
YP | +0.817 |
Sel | +0.798 |
Neg logit contributions | |
abeth | -1.034 |
bda | -0.962 |
mallow | -0.953 |
hof | -0.903 |
assic | -0.812 |
Token | is |
Token ID | 318 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
abeth | +0.037 |
bda | +0.034 |
mallow | +0.034 |
hof | +0.032 |
assic | +0.028 |
Neg logit contributions | |
Whites | -0.037 |
udo | -0.035 |
="# | -0.034 |
YP | -0.034 |
Sel | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Whites | +0.125 |
udo | +0.117 |
="# | +0.113 |
YP | +0.112 |
Sel | +0.110 |
Neg logit contributions | |
abeth | -0.125 |
bda | -0.117 |
mallow | -0.117 |
hof | -0.109 |
assic | -0.098 |
Token | piece |
Token ID | 3704 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
abeth | +0.126 |
mallow | +0.118 |
bda | +0.118 |
hof | +0.110 |
assic | +0.099 |
Neg logit contributions | |
Whites | -0.125 |
udo | -0.117 |
="# | -0.113 |
YP | -0.112 |
Sel | -0.110 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
abeth | +0.749 |
mallow | +0.699 |
bda | +0.693 |
hof | +0.657 |
assic | +0.589 |
Neg logit contributions | |
Whites | -0.669 |
udo | -0.625 |
="# | -0.607 |
YP | -0.602 |
Sel | -0.588 |
Token | oshenko |
Token ID | 43934 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
Whites | +1.310 |
udo | +1.209 |
="# | +1.139 |
YP | +1.126 |
uda | +1.120 |
Neg logit contributions | |
abeth | -2.016 |
bda | -1.933 |
mallow | -1.912 |
hof | -1.810 |
assic | -1.655 |
Token | and |
Token ID | 290 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
Whites | +2.355 |
udo | +2.155 |
="# | +2.055 |
YP | +2.043 |
uda | +2.036 |
Neg logit contributions | |
abeth | -2.462 |
bda | -2.329 |
mallow | -2.317 |
hof | -2.143 |
assic | -1.992 |
Token | Zh |
Token ID | 10511 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
abeth | +0.500 |
bda | +0.467 |
mallow | +0.467 |
hof | +0.439 |
assic | +0.394 |
Neg logit contributions | |
Whites | -0.464 |
udo | -0.434 |
="# | -0.422 |
YP | -0.417 |
Sel | -0.409 |
Token | uk |
Token ID | 2724 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
Whites | +0.090 |
udo | +0.081 |
="# | +0.078 |
YP | +0.077 |
Sel | +0.075 |
Neg logit contributions | |
abeth | -0.161 |
mallow | -0.153 |
bda | -0.152 |
hof | -0.145 |
assic | -0.133 |
Token | ov |
Token ID | 709 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Whites | +1.713 |
udo | +1.594 |
="# | +1.464 |
uda | +1.461 |
YP | +1.423 |
Neg logit contributions | |
abeth | -4.220 |
mallow | -4.014 |
bda | -4.012 |
hof | -3.775 |
assic | -3.535 |
Token | suggested |
Token ID | 5220 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Whites | +0.835 |
udo | +0.778 |
YP | +0.741 |
="# | +0.740 |
Sel | +0.729 |
Neg logit contributions | |
abeth | -0.871 |
mallow | -0.821 |
bda | -0.820 |
hof | -0.763 |
assic | -0.696 |
Token | to |
Token ID | 284 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
abeth | +1.255 |
bda | +1.171 |
mallow | +1.170 |
hof | +1.097 |
assic | +0.982 |
Neg logit contributions | |
Whites | -1.224 |
udo | -1.145 |
="# | -1.113 |
YP | -1.101 |
Sel | -1.081 |
Token | Joseph |
Token ID | 7212 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
abeth | +2.045 |
mallow | +1.901 |
bda | +1.893 |
hof | +1.798 |
assic | +1.584 |
Neg logit contributions | |
Whites | -1.992 |
udo | -1.883 |
="# | -1.844 |
YP | -1.811 |
Sel | -1.778 |
Token | Stalin |
Token ID | 17482 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
Whites | +1.207 |
udo | +1.105 |
="# | +1.058 |
YP | +1.051 |
Sel | +1.029 |
Neg logit contributions | |
abeth | -1.675 |
bda | -1.582 |
mallow | -1.580 |
hof | -1.487 |
assic | -1.369 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
abeth | +0.251 |
mallow | +0.234 |
bda | +0.234 |
hof | +0.219 |
assic | +0.196 |
Neg logit contributions | |
Whites | -0.252 |
udo | -0.235 |
="# | -0.229 |
YP | -0.227 |
Sel | -0.223 |
Token | grids |
Token ID | 50000 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
Whites | +0.151 |
udo | +0.141 |
="# | +0.138 |
YP | +0.136 |
Sel | +0.134 |
Neg logit contributions | |
abeth | -0.136 |
bda | -0.126 |
mallow | -0.126 |
hof | -0.117 |
assic | -0.105 |
Token | are |
Token ID | 389 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
Whites | +1.893 |
udo | +1.747 |
="# | +1.703 |
YP | +1.667 |
Sel | +1.640 |
Neg logit contributions | |
abeth | -2.084 |
bda | -1.969 |
mallow | -1.942 |
hof | -1.839 |
assic | -1.652 |
Token | removed |
Token ID | 4615 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
Whites | +0.385 |
udo | +0.355 |
="# | +0.347 |
YP | +0.341 |
Sel | +0.334 |
Neg logit contributions | |
abeth | -0.458 |
bda | -0.433 |
mallow | -0.430 |
hof | -0.407 |
assic | -0.367 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Whites | +0.514 |
udo | +0.479 |
="# | +0.466 |
YP | +0.462 |
Sel | +0.455 |
Neg logit contributions | |
abeth | -0.473 |
bda | -0.441 |
mallow | -0.438 |
hof | -0.409 |
assic | -0.368 |
Token | But |
Token ID | 887 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
Whites | +0.130 |
udo | +0.118 |
="# | +0.115 |
YP | +0.114 |
Sel | +0.112 |
Neg logit contributions | |
abeth | -0.160 |
bda | -0.149 |
mallow | -0.149 |
hof | -0.140 |
assic | -0.130 |
Token | while |
Token ID | 981 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
Whites | +0.329 |
udo | +0.304 |
="# | +0.298 |
YP | +0.294 |
Sel | +0.290 |
Neg logit contributions | |
abeth | -0.316 |
mallow | -0.293 |
bda | -0.293 |
hof | -0.273 |
assic | -0.246 |
Token | Chang |
Token ID | 22597 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
Whites | +0.134 |
udo | +0.123 |
="# | +0.120 |
YP | +0.119 |
Sel | +0.118 |
Neg logit contributions | |
abeth | -0.135 |
bda | -0.126 |
mallow | -0.126 |
hof | -0.117 |
assic | -0.106 |
Token | � |
Token ID | 447 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
abeth | +0.554 |
bda | +0.514 |
mallow | +0.513 |
hof | +0.478 |
assic | +0.425 |
Neg logit contributions | |
Whites | -0.623 |
udo | -0.584 |
="# | -0.569 |
YP | -0.562 |
Sel | -0.555 |
Token | � |
Token ID | 247 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Whites | +0.190 |
udo | +0.167 |
="# | +0.158 |
YP | +0.155 |
Sel | +0.150 |
Neg logit contributions | |
abeth | -0.503 |
mallow | -0.479 |
bda | -0.479 |
hof | -0.458 |
assic | -0.427 |
Token | s |
Token ID | 82 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
abeth | +0.175 |
bda | +0.160 |
mallow | +0.160 |
hof | +0.147 |
assic | +0.128 |
Neg logit contributions | |
Whites | -0.251 |
udo | -0.237 |
="# | -0.231 |
YP | -0.229 |
Sel | -0.227 |
Token | patients |
Token ID | 3871 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
Whites | +0.055 |
udo | +0.052 |
="# | +0.051 |
YP | +0.050 |
Sel | +0.049 |
Neg logit contributions | |
abeth | -0.052 |
mallow | -0.048 |
bda | -0.048 |
hof | -0.045 |
assic | -0.040 |
Token | � |
Token ID | 251 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Whites | +0.315 |
udo | +0.287 |
="# | +0.275 |
YP | +0.272 |
Sel | +0.265 |
Neg logit contributions | |
abeth | -0.552 |
mallow | -0.524 |
bda | -0.524 |
hof | -0.496 |
assic | -0.458 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
abeth | +0.341 |
bda | +0.319 |
mallow | +0.319 |
hof | +0.300 |
assic | +0.272 |
Neg logit contributions | |
Whites | -0.302 |
udo | -0.279 |
="# | -0.272 |
YP | -0.269 |
Sel | -0.265 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
abeth | +0.015 |
mallow | +0.014 |
bda | +0.014 |
hof | +0.013 |
assic | +0.012 |
Neg logit contributions | |
Whites | -0.013 |
udo | -0.012 |
="# | -0.012 |
YP | -0.012 |
Sel | -0.012 |
Token | Offset |
Token ID | 34519 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Whites | +0.106 |
udo | +0.098 |
="# | +0.096 |
YP | +0.095 |
Sel | +0.093 |
Neg logit contributions | |
abeth | -0.125 |
mallow | -0.117 |
bda | -0.117 |
hof | -0.110 |
assic | -0.100 |
Token | � |
Token ID | 447 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Whites | +1.053 |
udo | +0.977 |
="# | +0.953 |
YP | +0.947 |
Sel | +0.931 |
Neg logit contributions | |
abeth | -0.991 |
mallow | -0.923 |
bda | -0.922 |
hof | -0.861 |
assic | -0.775 |
Token | � |
Token ID | 247 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
Whites | +0.613 |
udo | +0.540 |
="# | +0.510 |
YP | +0.500 |
Sel | +0.483 |
Neg logit contributions | |
abeth | -1.652 |
bda | -1.577 |
mallow | -1.577 |
hof | -1.507 |
assic | -1.407 |
Token | s |
Token ID | 82 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Whites | +0.043 |
udo | +0.041 |
="# | +0.040 |
YP | +0.039 |
Sel | +0.039 |
Neg logit contributions | |
abeth | -0.032 |
mallow | -0.029 |
bda | -0.029 |
hof | -0.027 |
assic | -0.024 |
Token | mother |
Token ID | 2802 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
Whites | +2.020 |
udo | +1.816 |
="# | +1.795 |
YP | +1.785 |
Scouting | +1.737 |
Neg logit contributions | |
abeth | -2.252 |
bda | -2.106 |
mallow | -2.102 |
hof | -1.968 |
assic | -1.790 |
Token | , |
Token ID | 11 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
abeth | +1.438 |
mallow | +1.333 |
bda | +1.327 |
hof | +1.235 |
assic | +1.095 |
Neg logit contributions | |
Whites | -1.597 |
udo | -1.507 |
="# | -1.465 |
YP | -1.450 |
Sel | -1.421 |
Token | Lat |
Token ID | 5476 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
abeth | +1.604 |
mallow | +1.483 |
bda | +1.474 |
hof | +1.369 |
assic | +1.212 |
Neg logit contributions | |
Whites | -1.804 |
udo | -1.716 |
="# | -1.664 |
YP | -1.645 |
Sel | -1.609 |
Token | ab |
Token ID | 397 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
abeth | +0.643 |
mallow | +0.601 |
bda | +0.599 |
hof | +0.564 |
assic | +0.507 |
Neg logit contributions | |
Whites | -0.581 |
udo | -0.540 |
="# | -0.528 |
YP | -0.520 |
Sel | -0.511 |
Token | Super |
Token ID | 3115 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
Whites | +0.056 |
udo | +0.053 |
="# | +0.051 |
YP | +0.051 |
Sel | +0.050 |
Neg logit contributions | |
abeth | -0.057 |
mallow | -0.053 |
bda | -0.053 |
hof | -0.050 |
assic | -0.045 |
Token | Metroid |
Token ID | 45430 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
abeth | +0.447 |
bda | +0.415 |
mallow | +0.415 |
hof | +0.386 |
assic | +0.344 |
Neg logit contributions | |
Whites | -0.495 |
udo | -0.464 |
="# | -0.451 |
YP | -0.447 |
Sel | -0.440 |
Token | speed |
Token ID | 2866 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
abeth | +1.428 |
mallow | +1.334 |
bda | +1.331 |
hof | +1.244 |
assic | +1.112 |
Neg logit contributions | |
Whites | -1.486 |
udo | -1.387 |
="# | -1.353 |
YP | -1.340 |
Sel | -1.317 |
Token | run |
Token ID | 5143 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
abeth | +1.844 |
mallow | +1.735 |
bda | +1.734 |
hof | +1.625 |
assic | +1.462 |
Neg logit contributions | |
Whites | -1.695 |
udo | -1.572 |
="# | -1.527 |
YP | -1.515 |
Sel | -1.489 |
Token | race |
Token ID | 3234 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
abeth | +0.257 |
mallow | +0.239 |
bda | +0.239 |
hof | +0.223 |
assic | +0.199 |
Neg logit contributions | |
Whites | -0.267 |
udo | -0.249 |
="# | -0.242 |
YP | -0.240 |
Sel | -0.236 |
Token | , |
Token ID | 11 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
abeth | +0.285 |
mallow | +0.265 |
bda | +0.265 |
hof | +0.247 |
assic | +0.220 |
Neg logit contributions | |
Whites | -0.312 |
udo | -0.292 |
="# | -0.284 |
YP | -0.282 |
Sel | -0.277 |
Token | from |
Token ID | 422 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
abeth | +1.012 |
mallow | +0.945 |
bda | +0.942 |
hof | +0.882 |
assic | +0.790 |
Neg logit contributions | |
Whites | -1.020 |
udo | -0.953 |
="# | -0.929 |
YP | -0.920 |
Sel | -0.904 |
Token | Awesome |
Token ID | 25020 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
abeth | +0.124 |
bda | +0.115 |
mallow | +0.115 |
hof | +0.107 |
assic | +0.096 |
Neg logit contributions | |
Whites | -0.126 |
udo | -0.117 |
="# | -0.114 |
YP | -0.112 |
Sel | -0.111 |
Token | Games |
Token ID | 5776 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
abeth | +0.059 |
mallow | +0.055 |
bda | +0.055 |
hof | +0.051 |
assic | +0.046 |
Neg logit contributions | |
Whites | -0.057 |
udo | -0.053 |
="# | -0.052 |
YP | -0.051 |
Sel | -0.050 |
Token | Done |
Token ID | 24429 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Whites | +2.090 |
udo | +1.964 |
="# | +1.886 |
YP | +1.884 |
Sel | +1.841 |
Neg logit contributions | |
abeth | -1.986 |
bda | -1.846 |
mallow | -1.841 |
hof | -1.702 |
assic | -1.544 |
Token | Quick |
Token ID | 12029 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
abeth | +1.108 |
mallow | +1.038 |
bda | +1.036 |
hof | +0.980 |
assic | +0.872 |
Neg logit contributions | |
Whites | -1.014 |
udo | -0.949 |
="# | -0.924 |
YP | -0.913 |
Sel | -0.895 |
Token | Emirates |
Token ID | 24880 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
abeth | +0.017 |
mallow | +0.016 |
bda | +0.016 |
hof | +0.015 |
assic | +0.013 |
Neg logit contributions | |
Whites | -0.016 |
udo | -0.014 |
="# | -0.014 |
YP | -0.014 |
Sel | -0.014 |
Token | ID |
Token ID | 4522 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
Whites | +0.932 |
udo | +0.857 |
="# | +0.840 |
YP | +0.827 |
Sel | +0.817 |
Neg logit contributions | |
abeth | -0.942 |
mallow | -0.879 |
bda | -0.879 |
hof | -0.821 |
assic | -0.740 |
Token | or |
Token ID | 393 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
abeth | +1.352 |
mallow | +1.250 |
bda | +1.249 |
hof | +1.155 |
assic | +1.018 |
Neg logit contributions | |
Whites | -1.693 |
udo | -1.595 |
="# | -1.554 |
YP | -1.541 |
Sel | -1.517 |
Token | visa |
Token ID | 14552 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
abeth | +0.100 |
mallow | +0.094 |
bda | +0.093 |
hof | +0.087 |
assic | +0.078 |
Neg logit contributions | |
Whites | -0.099 |
udo | -0.092 |
="# | -0.090 |
YP | -0.089 |
Sel | -0.087 |
Token | to |
Token ID | 284 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
abeth | +0.424 |
mallow | +0.396 |
bda | +0.393 |
hof | +0.369 |
assic | +0.328 |
Neg logit contributions | |
Whites | -0.451 |
udo | -0.420 |
="# | -0.408 |
YP | -0.404 |
Sel | -0.398 |
Token | avoid |
Token ID | 3368 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
abeth | +0.307 |
mallow | +0.288 |
bda | +0.287 |
hof | +0.269 |
assic | +0.244 |
Neg logit contributions | |
Whites | -0.277 |
udo | -0.256 |
="# | -0.248 |
YP | -0.245 |
Sel | -0.242 |
Token | facing |
Token ID | 6476 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
abeth | +2.141 |
bda | +2.002 |
mallow | +2.002 |
hof | +1.876 |
assic | +1.677 |
Neg logit contributions | |
Whites | -2.121 |
udo | -1.995 |
="# | -1.940 |
YP | -1.921 |
Sel | -1.889 |
Token | immediate |
Token ID | 7103 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
Whites | +0.948 |
udo | +0.869 |
="# | +0.843 |
YP | +0.834 |
Sel | +0.817 |
Neg logit contributions | |
abeth | -1.030 |
bda | -0.961 |
mallow | -0.956 |
hof | -0.895 |
assic | -0.813 |
Token | suspension |
Token ID | 11461 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Whites | +0.467 |
udo | +0.430 |
="# | +0.419 |
YP | +0.412 |
Sel | +0.404 |
Neg logit contributions | |
abeth | -0.519 |
mallow | -0.484 |
bda | -0.484 |
hof | -0.454 |
assic | -0.410 |
Token | of |
Token ID | 286 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
abeth | +1.339 |
mallow | +1.239 |
bda | +1.234 |
hof | +1.154 |
assic | +1.021 |
Neg logit contributions | |
Whites | -1.562 |
udo | -1.467 |
="# | -1.431 |
YP | -1.420 |
Sel | -1.400 |
Token | service |
Token ID | 2139 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Whites | +0.446 |
udo | +0.406 |
="# | +0.395 |
YP | +0.390 |
Sel | +0.383 |
Neg logit contributions | |
abeth | -0.582 |
mallow | -0.549 |
bda | -0.547 |
hof | -0.516 |
assic | -0.470 |
Token | After |
Token ID | 2293 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Whites | +0.186 |
udo | +0.172 |
="# | +0.166 |
YP | +0.164 |
Sel | +0.162 |
Neg logit contributions | |
abeth | -0.225 |
bda | -0.211 |
mallow | -0.211 |
hof | -0.198 |
assic | -0.180 |
Token | adding |
Token ID | 4375 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
abeth | +1.034 |
mallow | +0.965 |
bda | +0.964 |
hof | +0.902 |
assic | +0.808 |
Neg logit contributions | |
Whites | -1.008 |
udo | -0.944 |
="# | -0.919 |
YP | -0.909 |
Sel | -0.891 |
Token | the |
Token ID | 262 |
Feature activation | +9.55e-02 |
Pos logit contributions | |
abeth | +0.882 |
mallow | +0.823 |
bda | +0.818 |
hof | +0.769 |
assic | +0.688 |
Neg logit contributions | |
Whites | -0.867 |
udo | -0.820 |
="# | -0.799 |
YP | -0.788 |
Sel | -0.773 |
Token | roster |
Token ID | 9354 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
Whites | +0.070 |
udo | +0.064 |
="# | +0.062 |
YP | +0.062 |
Sel | +0.061 |
Neg logit contributions | |
abeth | -0.076 |
bda | -0.072 |
mallow | -0.072 |
hof | -0.067 |
assic | -0.060 |
Token | charges |
Token ID | 4530 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
abeth | +0.017 |
mallow | +0.016 |
bda | +0.015 |
hof | +0.015 |
assic | +0.013 |
Neg logit contributions | |
Whites | -0.014 |
udo | -0.013 |
="# | -0.013 |
YP | -0.013 |
Sel | -0.012 |
Token | for |
Token ID | 329 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
abeth | +1.260 |
mallow | +1.170 |
bda | +1.160 |
hof | +1.094 |
assic | +0.973 |
Neg logit contributions | |
Whites | -1.333 |
udo | -1.257 |
="# | -1.232 |
YP | -1.218 |
Sel | -1.196 |
Token | unf |
Token ID | 3684 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
abeth | +0.289 |
bda | +0.270 |
mallow | +0.270 |
hof | +0.253 |
assic | +0.227 |
Neg logit contributions | |
Whites | -0.279 |
udo | -0.259 |
="# | -0.252 |
YP | -0.249 |
Sel | -0.245 |
Token | illed |
Token ID | 2967 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Whites | +1.089 |
udo | +1.025 |
="# | +0.987 |
YP | +0.976 |
Sel | +0.959 |
Neg logit contributions | |
abeth | -1.153 |
mallow | -1.078 |
bda | -1.076 |
hof | -1.013 |
assic | -0.903 |
Token | roster |
Token ID | 9354 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
Whites | +1.026 |
udo | +0.928 |
="# | +0.894 |
YP | +0.888 |
Sel | +0.871 |
Neg logit contributions | |
abeth | -1.273 |
bda | -1.196 |
mallow | -1.194 |
hof | -1.120 |
assic | -1.017 |
Token | spots |
Token ID | 10222 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
abeth | +0.697 |
mallow | +0.658 |
bda | +0.657 |
hof | +0.624 |
assic | +0.572 |
Neg logit contributions | |
Whites | -0.454 |
udo | -0.418 |
="# | -0.403 |
YP | -0.397 |
Sel | -0.389 |
Token | , |
Token ID | 11 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Whites | +0.148 |
udo | +0.139 |
="# | +0.135 |
YP | +0.134 |
Sel | +0.131 |
Neg logit contributions | |
abeth | -0.134 |
mallow | -0.125 |
bda | -0.125 |
hof | -0.116 |
assic | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
abeth | +1.246 |
mallow | +1.151 |
bda | +1.149 |
hof | +1.071 |
assic | +0.941 |
Neg logit contributions | |
Whites | -1.445 |
udo | -1.366 |
="# | -1.326 |
YP | -1.315 |
Sel | -1.290 |
Token |
|
Token ID | 198 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
abeth | +1.599 |
mallow | +1.500 |
bda | +1.499 |
hof | +1.410 |
assic | +1.268 |
Neg logit contributions | |
Whites | -1.384 |
udo | -1.292 |
="# | -1.254 |
YP | -1.238 |
Sel | -1.214 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
abeth | +1.388 |
bda | +1.308 |
mallow | +1.304 |
hof | +1.234 |
assic | +1.080 |
Neg logit contributions | |
Whites | -1.353 |
udo | -1.266 |
="# | -1.219 |
YP | -1.216 |
Sel | -1.186 |
Token | There |
Token ID | 1858 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
abeth | +1.140 |
mallow | +1.069 |
bda | +1.069 |
hof | +1.006 |
assic | +0.910 |
Neg logit contributions | |
Whites | -0.956 |
udo | -0.885 |
="# | -0.858 |
YP | -0.846 |
Sel | -0.828 |
Token | are |
Token ID | 389 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Whites | +0.831 |
udo | +0.770 |
="# | +0.747 |
YP | +0.738 |
Sel | +0.726 |
Neg logit contributions | |
abeth | -0.942 |
mallow | -0.884 |
bda | -0.881 |
hof | -0.829 |
assic | -0.749 |
Token | hundreds |
Token ID | 5179 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Whites | +0.183 |
udo | +0.170 |
="# | +0.166 |
YP | +0.164 |
Sel | +0.161 |
Neg logit contributions | |
abeth | -0.170 |
mallow | -0.158 |
bda | -0.157 |
hof | -0.147 |
assic | -0.131 |
Token | of |
Token ID | 286 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
abeth | +0.338 |
mallow | +0.317 |
bda | +0.315 |
hof | +0.295 |
assic | +0.265 |
Neg logit contributions | |
Whites | -0.339 |
udo | -0.317 |
="# | -0.308 |
YP | -0.305 |
Sel | -0.300 |
Token | great |
Token ID | 1049 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
abeth | +0.332 |
mallow | +0.308 |
bda | +0.308 |
hof | +0.287 |
assic | +0.256 |
Neg logit contributions | |
Whites | -0.358 |
udo | -0.335 |
="# | -0.326 |
YP | -0.323 |
Sel | -0.318 |
Token | horror |
Token ID | 9961 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
abeth | +0.466 |
mallow | +0.435 |
bda | +0.435 |
hof | +0.407 |
assic | +0.364 |
Neg logit contributions | |
Whites | -0.462 |
udo | -0.431 |
="# | -0.419 |
YP | -0.415 |
Sel | -0.408 |
Token | settings |
Token ID | 6460 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
abeth | +0.260 |
mallow | +0.243 |
bda | +0.242 |
hof | +0.227 |
assic | +0.205 |
Neg logit contributions | |
Whites | -0.241 |
udo | -0.225 |
="# | -0.218 |
YP | -0.216 |
Sel | -0.212 |
Token | , |
Token ID | 11 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
abeth | +0.300 |
mallow | +0.282 |
bda | +0.282 |
hof | +0.265 |
assic | +0.240 |
Neg logit contributions | |
Whites | -0.254 |
udo | -0.236 |
="# | -0.229 |
YP | -0.226 |
Sel | -0.222 |
Token | in |
Token ID | 287 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Whites | +0.647 |
udo | +0.601 |
="# | +0.586 |
YP | +0.577 |
Sel | +0.569 |
Neg logit contributions | |
abeth | -0.650 |
mallow | -0.603 |
bda | -0.603 |
hof | -0.566 |
assic | -0.507 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
Whites | +0.105 |
udo | +0.097 |
="# | +0.094 |
YP | +0.094 |
Sel | +0.092 |
Neg logit contributions | |
abeth | -0.112 |
mallow | -0.105 |
bda | -0.105 |
hof | -0.098 |
assic | -0.088 |
Token | sets |
Token ID | 5621 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Whites | +0.450 |
udo | +0.420 |
="# | +0.408 |
YP | +0.404 |
Sel | +0.397 |
Neg logit contributions | |
abeth | -0.444 |
mallow | -0.413 |
bda | -0.413 |
hof | -0.385 |
assic | -0.346 |
Token | the |
Token ID | 262 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
abeth | +0.759 |
bda | +0.709 |
mallow | +0.707 |
hof | +0.657 |
assic | +0.589 |
Neg logit contributions | |
Whites | -0.804 |
udo | -0.749 |
="# | -0.728 |
YP | -0.722 |
Sel | -0.710 |
Token | stage |
Token ID | 3800 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
abeth | +1.018 |
mallow | +0.931 |
bda | +0.929 |
hof | +0.851 |
assic | +0.734 |
Neg logit contributions | |
Whites | -1.566 |
udo | -1.481 |
="# | -1.447 |
YP | -1.436 |
Sel | -1.416 |
Token | for |
Token ID | 329 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
abeth | +0.446 |
mallow | +0.411 |
bda | +0.411 |
hof | +0.380 |
assic | +0.333 |
Neg logit contributions | |
Whites | -0.588 |
udo | -0.554 |
="# | -0.540 |
YP | -0.536 |
Sel | -0.527 |
Token | more |
Token ID | 517 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
abeth | +0.312 |
mallow | +0.291 |
bda | +0.291 |
hof | +0.271 |
assic | +0.243 |
Neg logit contributions | |
Whites | -0.320 |
udo | -0.299 |
="# | -0.291 |
YP | -0.288 |
Sel | -0.283 |
Token | potential |
Token ID | 2785 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
Whites | +0.314 |
udo | +0.292 |
="# | +0.283 |
YP | +0.280 |
Sel | +0.275 |
Neg logit contributions | |
abeth | -0.344 |
mallow | -0.322 |
bda | -0.322 |
hof | -0.302 |
assic | -0.272 |
Token | post |
Token ID | 1281 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
abeth | +0.403 |
mallow | +0.382 |
bda | +0.382 |
hof | +0.362 |
assic | +0.334 |
Neg logit contributions | |
Whites | -0.227 |
udo | -0.206 |
="# | -0.198 |
YP | -0.195 |
Sel | -0.190 |
Token | - |
Token ID | 12 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
Whites | +0.448 |
udo | +0.421 |
="# | +0.409 |
YP | +0.405 |
Sel | +0.400 |
Neg logit contributions | |
abeth | -0.392 |
bda | -0.364 |
mallow | -0.363 |
hof | -0.337 |
assic | -0.299 |
Token | election |
Token ID | 14300 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
abeth | +0.413 |
mallow | +0.388 |
bda | +0.388 |
hof | +0.365 |
assic | +0.331 |
Neg logit contributions | |
Whites | -0.330 |
udo | -0.306 |
="# | -0.296 |
YP | -0.293 |
Sel | -0.288 |
Token | with |
Token ID | 351 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
abeth | +0.261 |
mallow | +0.243 |
bda | +0.243 |
hof | +0.226 |
assic | +0.201 |
Neg logit contributions | |
Whites | -0.291 |
udo | -0.272 |
="# | -0.265 |
YP | -0.263 |
Sel | -0.258 |
Token | Batman |
Token ID | 9827 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
abeth | +0.353 |
bda | +0.330 |
mallow | +0.330 |
hof | +0.309 |
assic | +0.277 |
Neg logit contributions | |
Whites | -0.330 |
udo | -0.307 |
="# | -0.298 |
YP | -0.295 |
Sel | -0.290 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
abeth | +1.328 |
mallow | +1.237 |
bda | +1.234 |
hof | +1.143 |
assic | +1.019 |
Neg logit contributions | |
Whites | -1.535 |
udo | -1.449 |
="# | -1.407 |
YP | -1.395 |
Sel | -1.373 |
Token | On |
Token ID | 1550 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
abeth | +0.938 |
mallow | +0.885 |
bda | +0.885 |
hof | +0.837 |
assic | +0.768 |
Neg logit contributions | |
Whites | -0.622 |
udo | -0.569 |
="# | -0.547 |
YP | -0.540 |
Sel | -0.529 |
Token | the |
Token ID | 262 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
abeth | +1.051 |
bda | +0.979 |
mallow | +0.978 |
hof | +0.911 |
assic | +0.816 |
Neg logit contributions | |
Whites | -1.111 |
udo | -1.037 |
="# | -1.010 |
YP | -0.999 |
Sel | -0.984 |
Token | other |
Token ID | 584 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
abeth | +0.642 |
mallow | +0.593 |
bda | +0.592 |
hof | +0.545 |
assic | +0.479 |
Neg logit contributions | |
Whites | -0.847 |
udo | -0.797 |
="# | -0.778 |
YP | -0.770 |
Sel | -0.759 |
Token | hand |
Token ID | 1021 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
abeth | +2.598 |
mallow | +2.371 |
bda | +2.328 |
hof | +2.159 |
assic | +1.834 |
Neg logit contributions | |
Whites | -4.407 |
udo | -4.170 |
="# | -4.119 |
YP | -4.096 |
Sel | -4.035 |
Token | , |
Token ID | 11 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
abeth | +2.824 |
mallow | +2.595 |
bda | +2.584 |
hof | +2.402 |
assic | +2.140 |
Neg logit contributions | |
Whites | -3.677 |
udo | -3.469 |
="# | -3.409 |
YP | -3.384 |
Sel | -3.307 |
Token | it |
Token ID | 340 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
abeth | +1.014 |
mallow | +0.942 |
bda | +0.941 |
hof | +0.877 |
assic | +0.780 |
Neg logit contributions | |
Whites | -1.133 |
udo | -1.063 |
="# | -1.036 |
YP | -1.026 |
Sel | -1.009 |
Token | still |
Token ID | 991 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
abeth | +0.686 |
mallow | +0.639 |
bda | +0.639 |
hof | +0.596 |
assic | +0.533 |
Neg logit contributions | |
Whites | -0.716 |
udo | -0.669 |
="# | -0.651 |
YP | -0.645 |
Sel | -0.634 |
Token | might |
Token ID | 1244 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
abeth | +1.856 |
mallow | +1.736 |
bda | +1.729 |
hof | +1.620 |
assic | +1.450 |
Neg logit contributions | |
Whites | -1.848 |
udo | -1.734 |
="# | -1.682 |
YP | -1.669 |
Sel | -1.639 |
Token | matter |
Token ID | 2300 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
abeth | +0.903 |
mallow | +0.838 |
bda | +0.837 |
hof | +0.790 |
assic | +0.703 |
Neg logit contributions | |
Whites | -0.909 |
udo | -0.851 |
="# | -0.825 |
YP | -0.820 |
Sel | -0.804 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
abeth | +1.530 |
mallow | +1.415 |
bda | +1.408 |
hof | +1.312 |
assic | +1.114 |
Neg logit contributions | |
Whites | -2.103 |
udo | -1.988 |
YP | -1.930 |
="# | -1.929 |
Sel | -1.885 |
Token |
|
Token ID | 198 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
abeth | +0.841 |
bda | +0.789 |
mallow | +0.789 |
hof | +0.741 |
assic | +0.656 |
Neg logit contributions | |
Whites | -0.793 |
udo | -0.744 |
="# | -0.721 |
YP | -0.714 |
Sel | -0.699 |
Token |
|
Token ID | 198 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
abeth | +0.281 |
bda | +0.264 |
mallow | +0.264 |
hof | +0.248 |
assic | +0.221 |
Neg logit contributions | |
Whites | -0.258 |
udo | -0.241 |
="# | -0.233 |
YP | -0.231 |
Sel | -0.226 |
Token | Fight |
Token ID | 27365 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
abeth | +0.636 |
mallow | +0.597 |
bda | +0.596 |
hof | +0.562 |
assic | +0.513 |
Neg logit contributions | |
Whites | -0.514 |
udo | -0.476 |
="# | -0.463 |
YP | -0.457 |
Sel | -0.454 |
Token | Back |
Token ID | 5157 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
abeth | +0.480 |
bda | +0.447 |
mallow | +0.446 |
hof | +0.418 |
assic | +0.385 |
Neg logit contributions | |
Whites | -0.385 |
udo | -0.344 |
YP | -0.336 |
="# | -0.336 |
Scouting | -0.324 |
Token | ! |
Token ID | 0 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
abeth | +2.714 |
bda | +2.626 |
mallow | +2.497 |
hof | +2.370 |
thia | +1.961 |
Neg logit contributions | |
Whites | -4.657 |
udo | -4.584 |
YP | -4.428 |
="# | -4.354 |
Sel | -4.339 |
Token | Sign |
Token ID | 5865 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
abeth | +3.325 |
mallow | +3.190 |
bda | +3.161 |
hof | +3.027 |
assic | +2.772 |
Neg logit contributions | |
Whites | -1.559 |
udo | -1.409 |
="# | -1.363 |
YP | -1.347 |
Sel | -1.306 |
Token | up |
Token ID | 510 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
abeth | +0.170 |
bda | +0.157 |
mallow | +0.157 |
hof | +0.145 |
assic | +0.128 |
Neg logit contributions | |
Whites | -0.207 |
udo | -0.194 |
="# | -0.190 |
YP | -0.188 |
Sel | -0.185 |
Token | for |
Token ID | 329 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
abeth | +0.463 |
mallow | +0.428 |
bda | +0.426 |
hof | +0.395 |
assic | +0.350 |
Neg logit contributions | |
Whites | -0.586 |
udo | -0.548 |
="# | -0.535 |
YP | -0.530 |
Sel | -0.522 |
Token | Take |
Token ID | 7214 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Whites | +0.309 |
udo | +0.285 |
="# | +0.274 |
YP | +0.270 |
Sel | +0.261 |
Neg logit contributions | |
abeth | -0.612 |
bda | -0.585 |
mallow | -0.583 |
hof | -0.559 |
assic | -0.510 |
Token | our |
Token ID | 454 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Whites | +0.483 |
udo | +0.437 |
="# | +0.409 |
YP | +0.405 |
Sel | +0.392 |
Neg logit contributions | |
abeth | -1.172 |
bda | -1.115 |
mallow | -1.111 |
hof | -1.062 |
assic | -0.987 |
Token | into |
Token ID | 656 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
abeth | +0.163 |
mallow | +0.152 |
bda | +0.152 |
hof | +0.142 |
assic | +0.127 |
Neg logit contributions | |
Whites | -0.164 |
udo | -0.153 |
="# | -0.149 |
YP | -0.147 |
Sel | -0.145 |
Token | the |
Token ID | 262 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Whites | +0.403 |
udo | +0.373 |
="# | +0.361 |
YP | +0.358 |
Sel | +0.353 |
Neg logit contributions | |
abeth | -0.418 |
bda | -0.391 |
mallow | -0.390 |
hof | -0.364 |
assic | -0.330 |
Token | brewery |
Token ID | 22120 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
Whites | +0.816 |
udo | +0.758 |
="# | +0.731 |
YP | +0.723 |
Sel | +0.716 |
Neg logit contributions | |
abeth | -0.737 |
bda | -0.684 |
mallow | -0.682 |
hof | -0.631 |
assic | -0.569 |
Token | to |
Token ID | 284 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
Whites | +0.754 |
udo | +0.706 |
="# | +0.680 |
YP | +0.677 |
Sel | +0.668 |
Neg logit contributions | |
abeth | -0.676 |
bda | -0.626 |
mallow | -0.626 |
hof | -0.574 |
assic | -0.523 |
Token | show |
Token ID | 905 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
abeth | +1.975 |
mallow | +1.856 |
bda | +1.852 |
hof | +1.757 |
assic | +1.573 |
Neg logit contributions | |
Whites | -1.669 |
udo | -1.559 |
="# | -1.509 |
YP | -1.506 |
Sel | -1.471 |
Token | me |
Token ID | 502 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
abeth | +2.692 |
mallow | +2.440 |
bda | +2.426 |
hof | +2.298 |
assic | +1.924 |
Neg logit contributions | |
Whites | -3.842 |
udo | -3.647 |
="# | -3.614 |
YP | -3.588 |
Sel | -3.511 |
Token | something |
Token ID | 1223 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
abeth | +0.140 |
mallow | +0.130 |
bda | +0.130 |
hof | +0.122 |
assic | +0.110 |
Neg logit contributions | |
Whites | -0.137 |
udo | -0.127 |
="# | -0.123 |
YP | -0.122 |
Sel | -0.120 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
abeth | +0.742 |
mallow | +0.691 |
bda | +0.691 |
hof | +0.640 |
assic | +0.573 |
Neg logit contributions | |
Whites | -0.814 |
udo | -0.759 |
="# | -0.737 |
YP | -0.731 |
Sel | -0.720 |
Token | He |
Token ID | 679 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
abeth | +0.012 |
mallow | +0.012 |
bda | +0.012 |
hof | +0.011 |
assic | +0.010 |
Neg logit contributions | |
Whites | -0.010 |
udo | -0.010 |
="# | -0.009 |
YP | -0.009 |
Sel | -0.009 |
Token | holds |
Token ID | 6622 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
abeth | +0.161 |
mallow | +0.150 |
bda | +0.150 |
hof | +0.140 |
assic | +0.125 |
Neg logit contributions | |
Whites | -0.166 |
udo | -0.155 |
="# | -0.150 |
YP | -0.148 |
Sel | -0.146 |
Token | smartphone |
Token ID | 11745 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
abeth | +0.155 |
bda | +0.144 |
mallow | +0.144 |
hof | +0.135 |
assic | +0.121 |
Neg logit contributions | |
Whites | -0.160 |
udo | -0.148 |
="# | -0.144 |
YP | -0.143 |
Sel | -0.140 |
Token | . |
Token ID | 13 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Whites | +0.719 |
udo | +0.666 |
="# | +0.651 |
YP | +0.645 |
Sel | +0.630 |
Neg logit contributions | |
abeth | -0.693 |
bda | -0.645 |
mallow | -0.640 |
hof | -0.600 |
assic | -0.542 |
Token | It |
Token ID | 632 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
abeth | +0.222 |
mallow | +0.208 |
bda | +0.208 |
hof | +0.195 |
assic | +0.177 |
Neg logit contributions | |
Whites | -0.190 |
udo | -0.176 |
="# | -0.170 |
YP | -0.169 |
Sel | -0.166 |
Token | then |
Token ID | 788 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
abeth | +1.084 |
mallow | +1.011 |
bda | +1.009 |
hof | +0.941 |
assic | +0.839 |
Neg logit contributions | |
Whites | -1.145 |
udo | -1.071 |
="# | -1.042 |
YP | -1.033 |
Sel | -1.016 |
Token | took |
Token ID | 1718 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
abeth | +0.646 |
bda | +0.604 |
mallow | +0.602 |
hof | +0.565 |
assic | +0.510 |
Neg logit contributions | |
Whites | -0.602 |
udo | -0.560 |
="# | -0.544 |
YP | -0.537 |
Sel | -0.526 |
Token | to |
Token ID | 284 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
abeth | +0.712 |
mallow | +0.665 |
bda | +0.664 |
hof | +0.622 |
assic | +0.559 |
Neg logit contributions | |
Whites | -0.688 |
udo | -0.642 |
="# | -0.625 |
YP | -0.618 |
Sel | -0.608 |
Token | social |
Token ID | 1919 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
abeth | +2.861 |
mallow | +2.713 |
bda | +2.688 |
hof | +2.502 |
assic | +2.211 |
Neg logit contributions | |
Whites | -3.367 |
udo | -3.187 |
="# | -3.099 |
YP | -3.044 |
Sel | -3.019 |
Token | media |
Token ID | 2056 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
abeth | +1.433 |
mallow | +1.354 |
bda | +1.343 |
hof | +1.242 |
assic | +1.106 |
Neg logit contributions | |
Whites | -1.557 |
udo | -1.451 |
="# | -1.412 |
YP | -1.403 |
Sel | -1.375 |
Token | to |
Token ID | 284 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
abeth | +0.649 |
mallow | +0.611 |
bda | +0.610 |
hof | +0.574 |
assic | +0.518 |
Neg logit contributions | |
Whites | -0.564 |
udo | -0.524 |
="# | -0.508 |
YP | -0.503 |
Sel | -0.494 |
Token | promote |
Token ID | 7719 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
abeth | +1.248 |
mallow | +1.171 |
bda | +1.168 |
hof | +1.095 |
assic | +0.985 |
Neg logit contributions | |
Whites | -1.172 |
udo | -1.096 |
="# | -1.059 |
YP | -1.053 |
Sel | -1.037 |
Token | the |
Token ID | 262 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
Whites | +1.027 |
udo | +0.957 |
="# | +0.933 |
YP | +0.920 |
Sel | +0.900 |
Neg logit contributions | |
abeth | -1.049 |
bda | -0.980 |
mallow | -0.976 |
hof | -0.916 |
assic | -0.827 |
Token | shall |
Token ID | 2236 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
abeth | +0.121 |
mallow | +0.114 |
bda | +0.114 |
hof | +0.108 |
assic | +0.098 |
Neg logit contributions | |
Whites | -0.093 |
udo | -0.086 |
="# | -0.083 |
YP | -0.082 |
Sel | -0.081 |
Token | be |
Token ID | 307 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Whites | +0.320 |
udo | +0.298 |
="# | +0.289 |
YP | +0.285 |
Sel | +0.280 |
Neg logit contributions | |
abeth | -0.367 |
mallow | -0.344 |
bda | -0.343 |
hof | -0.323 |
assic | -0.292 |
Token | required |
Token ID | 2672 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
Whites | +0.222 |
udo | +0.206 |
="# | +0.199 |
YP | +0.195 |
Sel | +0.192 |
Neg logit contributions | |
abeth | -0.288 |
mallow | -0.271 |
bda | -0.271 |
hof | -0.256 |
assic | -0.234 |
Token | to |
Token ID | 284 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
Whites | +0.214 |
udo | +0.199 |
="# | +0.194 |
YP | +0.192 |
Sel | +0.188 |
Neg logit contributions | |
abeth | -0.237 |
bda | -0.222 |
mallow | -0.222 |
hof | -0.208 |
assic | -0.188 |
Token | give |
Token ID | 1577 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Whites | +1.682 |
udo | +1.533 |
="# | +1.462 |
uda | +1.427 |
YP | +1.420 |
Neg logit contributions | |
abeth | -3.102 |
mallow | -2.950 |
bda | -2.924 |
hof | -2.796 |
assic | -2.600 |
Token | effect |
Token ID | 1245 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
Whites | +0.189 |
udo | +0.175 |
="# | +0.170 |
YP | +0.168 |
Sel | +0.165 |
Neg logit contributions | |
abeth | -0.217 |
mallow | -0.205 |
bda | -0.204 |
hof | -0.191 |
assic | -0.173 |
Token | to |
Token ID | 284 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
abeth | +3.199 |
bda | +3.003 |
mallow | +2.960 |
hof | +2.811 |
assic | +2.511 |
Neg logit contributions | |
Whites | -3.064 |
udo | -2.804 |
="# | -2.748 |
YP | -2.724 |
Sel | -2.671 |
Token | any |
Token ID | 597 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
abeth | +1.784 |
bda | +1.663 |
mallow | +1.649 |
hof | +1.538 |
circulation | +1.342 |
Neg logit contributions | |
Whites | -2.087 |
udo | -1.959 |
="# | -1.904 |
YP | -1.897 |
Sel | -1.873 |
Token | public |
Token ID | 1171 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
abeth | +1.060 |
mallow | +0.988 |
bda | +0.988 |
hof | +0.924 |
assic | +0.825 |
Neg logit contributions | |
Whites | -1.079 |
udo | -1.008 |
="# | -0.981 |
YP | -0.974 |
Sel | -0.956 |
Token | act |
Token ID | 719 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
abeth | +0.474 |
bda | +0.442 |
mallow | +0.441 |
hof | +0.412 |
assic | +0.369 |
Neg logit contributions | |
Whites | -0.484 |
udo | -0.451 |
="# | -0.439 |
YP | -0.434 |
Sel | -0.427 |
Token | , |
Token ID | 11 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
abeth | +0.732 |
mallow | +0.682 |
bda | +0.681 |
hof | +0.636 |
assic | +0.569 |
Neg logit contributions | |
Whites | -0.753 |
udo | -0.703 |
="# | -0.684 |
YP | -0.677 |
Sel | -0.665 |