Token | K |
Token ID | 42 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Adidas | +0.465 |
Rust | +0.458 |
aila | +0.458 |
Pak | +0.451 |
bub | +0.451 |
Neg logit contributions | |
enthal | -0.577 |
sted | -0.525 |
carbohyd | -0.515 |
deceive | -0.497 |
cius | -0.494 |
Token | ris |
Token ID | 2442 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Adidas | +0.933 |
aila | +0.925 |
Rust | +0.924 |
Pak | +0.911 |
bub | +0.911 |
Neg logit contributions | |
enthal | -1.078 |
sted | -0.977 |
carbohyd | -0.967 |
deceive | -0.928 |
cius | -0.919 |
Token | Dunn |
Token ID | 30833 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
enthal | +3.106 |
sted | +2.787 |
carbohyd | +2.712 |
deceive | +2.646 |
cius | +2.639 |
Neg logit contributions | |
Adidas | -2.454 |
aila | -2.452 |
Rust | -2.427 |
Pak | -2.396 |
bub | -2.378 |
Token | had |
Token ID | 550 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
enthal | +2.474 |
sted | +2.231 |
carbohyd | +2.148 |
deceive | +2.100 |
ares | +2.084 |
Neg logit contributions | |
Rust | -2.281 |
Adidas | -2.270 |
aila | -2.249 |
Pak | -2.242 |
bub | -2.232 |
Token | a |
Token ID | 257 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
enthal | +0.964 |
sted | +0.875 |
carbohyd | +0.854 |
deceive | +0.834 |
cius | +0.821 |
Neg logit contributions | |
Rust | -0.799 |
Adidas | -0.795 |
aila | -0.793 |
Pak | -0.789 |
bub | -0.784 |
Token | tendon |
Token ID | 42205 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
Adidas | +0.428 |
Rust | +0.422 |
aila | +0.422 |
bub | +0.416 |
Pak | +0.416 |
Neg logit contributions | |
enthal | -0.458 |
sted | -0.414 |
carbohyd | -0.409 |
deceive | -0.390 |
cius | -0.389 |
Token | sticking |
Token ID | 17274 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
Pak | +4.375 |
aila | +4.354 |
Adidas | +4.326 |
Rust | +4.321 |
Wra | +4.262 |
Neg logit contributions | |
enthal | -7.518 |
sted | -6.847 |
carbohyd | -6.802 |
eele | -6.301 |
ares | -6.292 |
Token | out |
Token ID | 503 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Adidas | +1.835 |
Rust | +1.800 |
aila | +1.773 |
Pak | +1.770 |
bub | +1.761 |
Neg logit contributions | |
enthal | -2.883 |
carbohyd | -2.637 |
sted | -2.620 |
cius | -2.515 |
deceive | -2.499 |
Token | of |
Token ID | 286 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Adidas | +0.967 |
Rust | +0.952 |
aila | +0.946 |
bub | +0.939 |
Pak | +0.937 |
Neg logit contributions | |
enthal | -1.027 |
sted | -0.922 |
carbohyd | -0.916 |
deceive | -0.873 |
cius | -0.872 |
Token | his |
Token ID | 465 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Adidas | +0.433 |
Rust | +0.428 |
aila | +0.427 |
Pak | +0.422 |
bub | +0.421 |
Neg logit contributions | |
enthal | -0.486 |
sted | -0.440 |
carbohyd | -0.434 |
deceive | -0.417 |
cius | -0.414 |
Token | open |
Token ID | 1280 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
Adidas | +0.768 |
Rust | +0.751 |
aila | +0.748 |
bub | +0.740 |
Pak | +0.739 |
Neg logit contributions | |
enthal | -1.030 |
sted | -0.937 |
carbohyd | -0.930 |
deceive | -0.890 |
cius | -0.888 |
Token | suffered |
Token ID | 6989 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
Adidas | +0.011 |
Rust | +0.011 |
aila | +0.011 |
Pak | +0.011 |
bub | +0.011 |
Neg logit contributions | |
enthal | -0.012 |
sted | -0.011 |
carbohyd | -0.011 |
deceive | -0.011 |
cius | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
enthal | +1.077 |
sted | +0.980 |
carbohyd | +0.961 |
deceive | +0.930 |
ares | +0.919 |
Neg logit contributions | |
Adidas | -0.898 |
Rust | -0.894 |
aila | -0.891 |
Pak | -0.884 |
bub | -0.878 |
Token | rupt |
Token ID | 31580 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
Adidas | +0.330 |
Rust | +0.326 |
aila | +0.325 |
bub | +0.320 |
Pak | +0.320 |
Neg logit contributions | |
enthal | -0.436 |
sted | -0.398 |
carbohyd | -0.393 |
deceive | -0.378 |
cius | -0.376 |
Token | ured |
Token ID | 1522 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
Adidas | +1.100 |
aila | +1.092 |
Rust | +1.089 |
bub | +1.075 |
Pak | +1.074 |
Neg logit contributions | |
enthal | -1.419 |
sted | -1.292 |
carbohyd | -1.290 |
deceive | -1.234 |
cius | -1.220 |
Token | Achilles |
Token ID | 39561 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Adidas | +2.140 |
Rust | +2.064 |
aila | +2.051 |
bub | +2.041 |
Pak | +2.039 |
Neg logit contributions | |
enthal | -2.605 |
sted | -2.360 |
carbohyd | -2.328 |
cius | -2.215 |
eele | -2.199 |
Token | tendon |
Token ID | 42205 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Adidas | +1.900 |
Rust | +1.857 |
aila | +1.845 |
Pak | +1.828 |
bub | +1.796 |
Neg logit contributions | |
enthal | -5.224 |
sted | -4.855 |
carbohyd | -4.834 |
cius | -4.639 |
deceive | -4.619 |
Token | in |
Token ID | 287 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
Adidas | +4.689 |
aila | +4.606 |
Rust | +4.546 |
Rust | +4.494 |
bub | +4.486 |
Neg logit contributions | |
enthal | -6.883 |
carbohyd | -6.355 |
sted | -6.233 |
cius | -5.988 |
Dise | -5.832 |
Token | Thursday |
Token ID | 3635 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
Adidas | +1.624 |
aila | +1.586 |
Rust | +1.580 |
bub | +1.561 |
Pak | +1.547 |
Neg logit contributions | |
enthal | -1.686 |
carbohyd | -1.521 |
sted | -1.509 |
cius | -1.434 |
deceive | -1.423 |
Token | 's |
Token ID | 338 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
enthal | +1.450 |
sted | +1.298 |
carbohyd | +1.280 |
deceive | +1.235 |
cius | +1.208 |
Neg logit contributions | |
Adidas | -1.527 |
Rust | -1.515 |
aila | -1.509 |
Pak | -1.492 |
bub | -1.490 |
Token | game |
Token ID | 983 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
Adidas | +0.060 |
Rust | +0.060 |
aila | +0.059 |
Pak | +0.059 |
bub | +0.059 |
Neg logit contributions | |
enthal | -0.052 |
sted | -0.046 |
carbohyd | -0.046 |
deceive | -0.044 |
cius | -0.043 |
Token | against |
Token ID | 1028 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
enthal | +1.526 |
sted | +1.395 |
carbohyd | +1.354 |
deceive | +1.326 |
cius | +1.302 |
Neg logit contributions | |
Adidas | -1.269 |
Rust | -1.262 |
aila | -1.251 |
Pak | -1.250 |
bub | -1.247 |
Token | Women |
Token ID | 6926 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Adidas | +0.224 |
Rust | +0.222 |
aila | +0.221 |
Pak | +0.219 |
bub | +0.219 |
Neg logit contributions | |
enthal | -0.228 |
sted | -0.205 |
carbohyd | -0.201 |
deceive | -0.193 |
cius | -0.192 |
Token | captives |
Token ID | 46522 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Adidas | +0.395 |
Rust | +0.391 |
aila | +0.389 |
Pak | +0.385 |
bub | +0.385 |
Neg logit contributions | |
enthal | -0.469 |
sted | -0.426 |
carbohyd | -0.419 |
deceive | -0.404 |
cius | -0.401 |
Token | were |
Token ID | 547 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
enthal | +0.477 |
sted | +0.431 |
carbohyd | +0.420 |
deceive | +0.409 |
cius | +0.403 |
Neg logit contributions | |
Adidas | -0.443 |
Rust | -0.440 |
aila | -0.438 |
bub | -0.434 |
Pak | -0.434 |
Token | sent |
Token ID | 1908 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
enthal | +0.122 |
sted | +0.111 |
carbohyd | +0.108 |
deceive | +0.105 |
cius | +0.104 |
Neg logit contributions | |
Adidas | -0.107 |
Rust | -0.106 |
aila | -0.106 |
bub | -0.105 |
Pak | -0.105 |
Token | to |
Token ID | 284 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
enthal | +0.082 |
sted | +0.075 |
carbohyd | +0.073 |
deceive | +0.071 |
cius | +0.070 |
Neg logit contributions | |
Adidas | -0.064 |
Rust | -0.064 |
aila | -0.064 |
bub | -0.063 |
Pak | -0.063 |
Token | Naj |
Token ID | 37135 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
enthal | +1.027 |
sted | +0.930 |
carbohyd | +0.907 |
deceive | +0.896 |
cius | +0.871 |
Neg logit contributions | |
Adidas | -0.890 |
Rust | -0.886 |
aila | -0.880 |
bub | -0.872 |
Pak | -0.866 |
Token | d |
Token ID | 67 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
aila | +4.279 |
bub | +4.217 |
Adidas | +4.183 |
Pak | +4.137 |
Rust | +4.077 |
Neg logit contributions | |
enthal | -6.417 |
carbohyd | -5.950 |
sted | -5.727 |
deceive | -5.622 |
cius | -5.555 |
Token | to |
Token ID | 284 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
Adidas | +0.235 |
Rust | +0.233 |
aila | +0.231 |
bub | +0.229 |
Pak | +0.229 |
Neg logit contributions | |
enthal | -0.308 |
sted | -0.281 |
carbohyd | -0.277 |
deceive | -0.267 |
cius | -0.265 |
Token | be |
Token ID | 307 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
Adidas | +0.711 |
Rust | +0.704 |
aila | +0.701 |
Pak | +0.693 |
bub | +0.692 |
Neg logit contributions | |
enthal | -0.844 |
sted | -0.766 |
carbohyd | -0.755 |
deceive | -0.727 |
cius | -0.722 |
Token | exchanged |
Token ID | 22112 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
Adidas | +0.101 |
Rust | +0.100 |
aila | +0.100 |
Pak | +0.099 |
bub | +0.099 |
Neg logit contributions | |
enthal | -0.109 |
sted | -0.099 |
carbohyd | -0.097 |
deceive | -0.094 |
cius | -0.092 |
Token | with |
Token ID | 351 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
enthal | +2.231 |
sted | +2.041 |
carbohyd | +1.975 |
deceive | +1.954 |
ares | +1.938 |
Neg logit contributions | |
Adidas | -1.913 |
aila | -1.904 |
bub | -1.904 |
Rust | -1.899 |
Pak | -1.893 |
Token | ended |
Token ID | 4444 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
enthal | +0.267 |
sted | +0.242 |
carbohyd | +0.236 |
deceive | +0.231 |
cius | +0.227 |
Neg logit contributions | |
Adidas | -0.230 |
Rust | -0.229 |
aila | -0.227 |
bub | -0.225 |
Pak | -0.225 |
Token | up |
Token ID | 510 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
enthal | +0.159 |
sted | +0.146 |
carbohyd | +0.143 |
deceive | +0.139 |
cius | +0.138 |
Neg logit contributions | |
Adidas | -0.110 |
Rust | -0.109 |
aila | -0.108 |
Pak | -0.107 |
bub | -0.107 |
Token | in |
Token ID | 287 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
Adidas | +1.606 |
aila | +1.582 |
Rust | +1.579 |
Pak | +1.562 |
bub | +1.554 |
Neg logit contributions | |
enthal | -1.877 |
sted | -1.700 |
carbohyd | -1.699 |
deceive | -1.602 |
cius | -1.601 |
Token | Prime |
Token ID | 5537 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Adidas | +0.790 |
Rust | +0.775 |
aila | +0.773 |
Pak | +0.767 |
bub | +0.763 |
Neg logit contributions | |
enthal | -0.999 |
sted | -0.911 |
carbohyd | -0.903 |
deceive | -0.861 |
cius | -0.858 |
Token | Minister |
Token ID | 4139 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
Adidas | +1.285 |
Rust | +1.269 |
aila | +1.268 |
Pak | +1.264 |
bub | +1.258 |
Neg logit contributions | |
enthal | -0.782 |
carbohyd | -0.683 |
sted | -0.673 |
deceive | -0.629 |
cius | -0.616 |
Token | Naj |
Token ID | 37135 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Adidas | +0.631 |
Rust | +0.627 |
aila | +0.622 |
Pak | +0.611 |
bub | +0.610 |
Neg logit contributions | |
enthal | -1.007 |
sted | -0.926 |
carbohyd | -0.903 |
deceive | -0.885 |
cius | -0.878 |
Token | ib |
Token ID | 571 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
Adidas | +3.001 |
aila | +2.948 |
Rust | +2.935 |
Pak | +2.902 |
bub | +2.890 |
Neg logit contributions | |
enthal | -7.668 |
carbohyd | -7.108 |
sted | -7.093 |
deceive | -6.845 |
cius | -6.829 |
Token | Raz |
Token ID | 38058 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Adidas | +0.947 |
Rust | +0.925 |
aila | +0.921 |
Pak | +0.908 |
bub | +0.904 |
Neg logit contributions | |
enthal | -2.478 |
sted | -2.308 |
carbohyd | -2.292 |
cius | -2.215 |
deceive | -2.214 |
Token | ak |
Token ID | 461 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
aila | +2.677 |
Adidas | +2.589 |
Pak | +2.548 |
Rust | +2.513 |
bub | +2.501 |
Neg logit contributions | |
enthal | -6.714 |
carbohyd | -6.326 |
sted | -6.056 |
cius | -5.912 |
deceive | -5.873 |
Token | 's |
Token ID | 338 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Adidas | +2.123 |
aila | +2.100 |
Pak | +2.089 |
Rust | +2.077 |
bub | +2.050 |
Neg logit contributions | |
enthal | -2.672 |
carbohyd | -2.447 |
sted | -2.445 |
deceive | -2.315 |
cius | -2.300 |
Token | personal |
Token ID | 2614 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
Adidas | +0.657 |
Rust | +0.651 |
aila | +0.649 |
Pak | +0.640 |
bub | +0.639 |
Neg logit contributions | |
enthal | -0.801 |
sted | -0.728 |
carbohyd | -0.718 |
deceive | -0.692 |
cius | -0.687 |
Token | Instead |
Token ID | 13193 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
Adidas | +0.134 |
aila | +0.132 |
Rust | +0.132 |
bub | +0.130 |
Pak | +0.130 |
Neg logit contributions | |
enthal | -0.161 |
sted | -0.146 |
carbohyd | -0.143 |
deceive | -0.138 |
cius | -0.137 |
Token | , |
Token ID | 11 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
Adidas | +0.027 |
Rust | +0.027 |
aila | +0.027 |
Pak | +0.027 |
bub | +0.027 |
Neg logit contributions | |
enthal | -0.035 |
sted | -0.032 |
carbohyd | -0.032 |
deceive | -0.030 |
cius | -0.030 |
Token | Republicans |
Token ID | 4734 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
enthal | +0.198 |
sted | +0.179 |
carbohyd | +0.176 |
deceive | +0.170 |
cius | +0.168 |
Neg logit contributions | |
Adidas | -0.175 |
Rust | -0.173 |
aila | -0.172 |
Pak | -0.170 |
bub | -0.170 |
Token | spent |
Token ID | 3377 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Adidas | +1.054 |
aila | +1.037 |
Rust | +1.033 |
Pak | +1.023 |
bub | +1.020 |
Neg logit contributions | |
enthal | -1.202 |
carbohyd | -1.090 |
sted | -1.088 |
cius | -1.027 |
deceive | -1.024 |
Token | their |
Token ID | 511 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
enthal | +0.582 |
sted | +0.528 |
carbohyd | +0.513 |
deceive | +0.500 |
ares | +0.493 |
Neg logit contributions | |
Adidas | -0.510 |
Rust | -0.509 |
aila | -0.507 |
Pak | -0.502 |
bub | -0.501 |
Token | recess |
Token ID | 28836 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
Adidas | +0.868 |
Rust | +0.858 |
aila | +0.855 |
Pak | +0.844 |
bub | +0.843 |
Neg logit contributions | |
enthal | -1.115 |
sted | -1.015 |
carbohyd | -1.002 |
deceive | -0.965 |
cius | -0.959 |
Token | boasting |
Token ID | 40776 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Adidas | +4.865 |
Rust | +4.781 |
aila | +4.777 |
Pak | +4.743 |
bub | +4.718 |
Neg logit contributions | |
enthal | -5.413 |
carbohyd | -5.001 |
sted | -4.906 |
cius | -4.715 |
eele | -4.663 |
Token | their |
Token ID | 511 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Adidas | +0.975 |
Rust | +0.959 |
aila | +0.959 |
bub | +0.945 |
Pak | +0.944 |
Neg logit contributions | |
enthal | -1.203 |
sted | -1.092 |
carbohyd | -1.085 |
cius | -1.035 |
deceive | -1.034 |
Token | Republican |
Token ID | 3415 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
Adidas | +0.730 |
Rust | +0.721 |
aila | +0.719 |
Pak | +0.711 |
bub | +0.709 |
Neg logit contributions | |
enthal | -0.844 |
sted | -0.764 |
carbohyd | -0.756 |
deceive | -0.725 |
cius | -0.721 |
Token | standard |
Token ID | 3210 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Adidas | +0.188 |
aila | +0.186 |
Rust | +0.186 |
bub | +0.184 |
Pak | +0.183 |
Neg logit contributions | |
enthal | -0.231 |
sted | -0.212 |
carbohyd | -0.205 |
deceive | -0.200 |
cius | -0.198 |
Token | bearer |
Token ID | 49508 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
enthal | +0.519 |
sted | +0.465 |
carbohyd | +0.451 |
deceive | +0.439 |
ares | +0.433 |
Neg logit contributions | |
Adidas | -0.562 |
aila | -0.560 |
Rust | -0.560 |
Pak | -0.552 |
bub | -0.550 |
Token | two |
Token ID | 734 |
Feature activation | +9.26e-04 |
Pos logit contributions | |
Adidas | +0.019 |
Rust | +0.018 |
aila | +0.018 |
Pak | +0.018 |
bub | +0.018 |
Neg logit contributions | |
enthal | -0.022 |
sted | -0.020 |
carbohyd | -0.020 |
deceive | -0.019 |
cius | -0.019 |
Token | 8 |
Token ID | 807 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
Adidas | +0.002 |
Rust | +0.002 |
aila | +0.002 |
Pak | +0.002 |
bub | +0.002 |
Neg logit contributions | |
enthal | -0.002 |
sted | -0.002 |
carbohyd | -0.002 |
deceive | -0.002 |
cius | -0.002 |
Token | cm |
Token ID | 11215 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
Adidas | +0.998 |
Rust | +0.979 |
aila | +0.978 |
Pak | +0.971 |
bub | +0.964 |
Neg logit contributions | |
enthal | -1.450 |
sted | -1.322 |
carbohyd | -1.311 |
deceive | -1.269 |
cius | -1.250 |
Token | P |
Token ID | 350 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
Adidas | +0.977 |
Rust | +0.958 |
aila | +0.954 |
Pak | +0.947 |
bub | +0.944 |
Neg logit contributions | |
enthal | -1.384 |
sted | -1.267 |
carbohyd | -1.256 |
deceive | -1.206 |
cius | -1.199 |
Token | WM |
Token ID | 22117 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
enthal | +1.297 |
sted | +1.166 |
carbohyd | +1.138 |
deceive | +1.099 |
ares | +1.097 |
Neg logit contributions | |
Adidas | -1.177 |
Rust | -1.162 |
aila | -1.156 |
Pak | -1.143 |
bub | -1.138 |
Token | fan |
Token ID | 4336 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Adidas | +0.172 |
Rust | +0.170 |
aila | +0.170 |
Pak | +0.168 |
bub | +0.167 |
Neg logit contributions | |
enthal | -0.212 |
sted | -0.192 |
carbohyd | -0.190 |
deceive | -0.183 |
cius | -0.182 |
Token | setup |
Token ID | 9058 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
Adidas | +4.472 |
bub | +4.422 |
Pak | +4.415 |
Wra | +4.366 |
Rust | +4.330 |
Neg logit contributions | |
enthal | -5.764 |
carbohyd | -5.312 |
sted | -5.229 |
deceive | -5.011 |
cius | -4.995 |
Token | with |
Token ID | 351 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
Adidas | +0.186 |
Rust | +0.184 |
aila | +0.184 |
Pak | +0.181 |
bub | +0.181 |
Neg logit contributions | |
enthal | -0.222 |
sted | -0.201 |
carbohyd | -0.199 |
deceive | -0.191 |
cius | -0.190 |
Token | Pro |
Token ID | 1041 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
enthal | +0.069 |
sted | +0.063 |
carbohyd | +0.062 |
deceive | +0.059 |
cius | +0.059 |
Neg logit contributions | |
Adidas | -0.061 |
Rust | -0.060 |
aila | -0.060 |
Pak | -0.059 |
bub | -0.059 |
Token | pe |
Token ID | 431 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Adidas | +0.996 |
Rust | +0.982 |
aila | +0.979 |
Pak | +0.971 |
bub | +0.969 |
Neg logit contributions | |
enthal | -1.673 |
carbohyd | -1.540 |
sted | -1.536 |
deceive | -1.478 |
cius | -1.462 |
Token | ller |
Token ID | 6051 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Adidas | +0.689 |
Rust | +0.682 |
aila | +0.682 |
Pak | +0.676 |
bub | +0.674 |
Neg logit contributions | |
enthal | -0.641 |
sted | -0.574 |
carbohyd | -0.574 |
deceive | -0.544 |
cius | -0.536 |
Token | 50 |
Token ID | 1120 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Adidas | +0.095 |
Rust | +0.094 |
aila | +0.094 |
Pak | +0.093 |
bub | +0.093 |
Neg logit contributions | |
enthal | -0.131 |
sted | -0.119 |
carbohyd | -0.118 |
deceive | -0.114 |
cius | -0.113 |
Token | polymer |
Token ID | 30528 |
Feature activation | +3.10e-03 |
Pos logit contributions | |
enthal | +0.484 |
sted | +0.443 |
carbohyd | +0.433 |
deceive | +0.421 |
cius | +0.418 |
Neg logit contributions | |
Rust | -0.349 |
Adidas | -0.348 |
aila | -0.347 |
Pak | -0.339 |
bub | -0.338 |
Token | bank |
Token ID | 3331 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
Adidas | +0.006 |
Rust | +0.006 |
aila | +0.006 |
Pak | +0.006 |
bub | +0.006 |
Neg logit contributions | |
enthal | -0.009 |
sted | -0.008 |
carbohyd | -0.008 |
deceive | -0.008 |
cius | -0.008 |
Token | notes |
Token ID | 17815 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
enthal | +0.238 |
sted | +0.220 |
carbohyd | +0.217 |
deceive | +0.211 |
cius | +0.210 |
Neg logit contributions | |
Adidas | -0.120 |
Rust | -0.119 |
aila | -0.118 |
Pak | -0.116 |
bub | -0.115 |
Token | in |
Token ID | 287 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
Adidas | +2.430 |
aila | +2.367 |
Rust | +2.349 |
Pak | +2.334 |
bub | +2.332 |
Neg logit contributions | |
enthal | -2.994 |
carbohyd | -2.745 |
sted | -2.727 |
deceive | -2.589 |
cius | -2.573 |
Token | commem |
Token ID | 19512 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Adidas | +0.740 |
Rust | +0.738 |
aila | +0.735 |
Pak | +0.724 |
bub | +0.722 |
Neg logit contributions | |
enthal | -0.913 |
sted | -0.832 |
carbohyd | -0.818 |
deceive | -0.789 |
cius | -0.784 |
Token | oration |
Token ID | 6944 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
aila | +4.477 |
bub | +4.422 |
Adidas | +4.345 |
Pak | +4.292 |
Rust | +4.265 |
Neg logit contributions | |
carbohyd | -5.655 |
enthal | -5.631 |
deceive | -5.196 |
sted | -5.148 |
Dise | -5.045 |
Token | of |
Token ID | 286 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
Adidas | +3.166 |
aila | +3.101 |
Rust | +3.092 |
bub | +3.067 |
Pak | +3.063 |
Neg logit contributions | |
enthal | -3.546 |
carbohyd | -3.199 |
sted | -3.197 |
cius | -3.042 |
deceive | -3.031 |
Token | the |
Token ID | 262 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
Adidas | +1.461 |
aila | +1.433 |
Rust | +1.429 |
Pak | +1.417 |
bub | +1.417 |
Neg logit contributions | |
enthal | -1.645 |
carbohyd | -1.488 |
sted | -1.483 |
deceive | -1.416 |
cius | -1.401 |
Token | 50 |
Token ID | 2026 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
Adidas | +0.029 |
Rust | +0.029 |
aila | +0.029 |
Pak | +0.028 |
bub | +0.028 |
Neg logit contributions | |
enthal | -0.041 |
sted | -0.038 |
carbohyd | -0.037 |
deceive | -0.036 |
cius | -0.036 |
Token | th |
Token ID | 400 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
Adidas | +0.972 |
Rust | +0.953 |
aila | +0.951 |
Pak | +0.942 |
bub | +0.941 |
Neg logit contributions | |
enthal | -1.225 |
sted | -1.115 |
carbohyd | -1.109 |
deceive | -1.065 |
cius | -1.055 |
Token | at |
Token ID | 379 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
Adidas | +2.058 |
Rust | +2.019 |
bub | +1.988 |
aila | +1.984 |
Pak | +1.965 |
Neg logit contributions | |
enthal | -2.351 |
carbohyd | -2.124 |
sted | -2.119 |
deceive | -2.002 |
cius | -1.988 |
Token | every |
Token ID | 790 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
enthal | +1.016 |
sted | +0.917 |
carbohyd | +0.900 |
deceive | +0.866 |
cius | +0.863 |
Neg logit contributions | |
Adidas | -0.918 |
aila | -0.912 |
Rust | -0.911 |
Pak | -0.900 |
bub | -0.895 |
Token | boot |
Token ID | 6297 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
enthal | +0.819 |
sted | +0.734 |
carbohyd | +0.720 |
deceive | +0.695 |
cius | +0.690 |
Neg logit contributions | |
Adidas | -0.813 |
Rust | -0.805 |
aila | -0.804 |
Pak | -0.795 |
bub | -0.793 |
Token | , |
Token ID | 11 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Adidas | +0.446 |
Rust | +0.439 |
aila | +0.437 |
Pak | +0.433 |
bub | +0.433 |
Neg logit contributions | |
enthal | -0.548 |
sted | -0.499 |
carbohyd | -0.493 |
deceive | -0.474 |
cius | -0.470 |
Token | the |
Token ID | 262 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
enthal | +0.249 |
sted | +0.225 |
carbohyd | +0.221 |
deceive | +0.213 |
cius | +0.211 |
Neg logit contributions | |
Adidas | -0.228 |
Rust | -0.225 |
aila | -0.225 |
Pak | -0.223 |
bub | -0.222 |
Token | fan |
Token ID | 4336 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Adidas | +0.525 |
Rust | +0.519 |
aila | +0.518 |
Pak | +0.512 |
bub | +0.511 |
Neg logit contributions | |
enthal | -0.622 |
sted | -0.564 |
carbohyd | -0.557 |
deceive | -0.535 |
cius | -0.531 |
Token | will |
Token ID | 481 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
Adidas | +4.609 |
Rust | +4.548 |
Pak | +4.534 |
aila | +4.516 |
bub | +4.513 |
Neg logit contributions | |
enthal | -5.482 |
carbohyd | -5.115 |
sted | -5.034 |
eele | -4.673 |
deceive | -4.669 |
Token | reverse |
Token ID | 9575 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Adidas | +1.751 |
Rust | +1.730 |
aila | +1.727 |
Pak | +1.704 |
bub | +1.704 |
Neg logit contributions | |
enthal | -2.232 |
carbohyd | -2.041 |
sted | -2.040 |
ares | -1.906 |
cius | -1.905 |
Token | for |
Token ID | 329 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Adidas | +0.753 |
Rust | +0.745 |
aila | +0.743 |
Pak | +0.733 |
bub | +0.732 |
Neg logit contributions | |
enthal | -0.870 |
sted | -0.789 |
carbohyd | -0.779 |
deceive | -0.747 |
cius | -0.742 |
Token | 30 |
Token ID | 1542 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Adidas | +0.855 |
Rust | +0.845 |
aila | +0.842 |
Pak | +0.832 |
bub | +0.830 |
Neg logit contributions | |
enthal | -1.062 |
sted | -0.966 |
carbohyd | -0.954 |
deceive | -0.918 |
cius | -0.911 |
Token | seconds |
Token ID | 4201 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
Adidas | +0.249 |
Rust | +0.246 |
aila | +0.245 |
Pak | +0.242 |
bub | +0.242 |
Neg logit contributions | |
enthal | -0.285 |
sted | -0.258 |
carbohyd | -0.254 |
deceive | -0.244 |
cius | -0.244 |
Token | coming |
Token ID | 2406 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Adidas | +0.538 |
Rust | +0.531 |
aila | +0.529 |
Pak | +0.522 |
bub | +0.521 |
Neg logit contributions | |
enthal | -0.618 |
sted | -0.558 |
carbohyd | -0.553 |
deceive | -0.529 |
cius | -0.527 |
Token | off |
Token ID | 572 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
enthal | +0.385 |
sted | +0.356 |
carbohyd | +0.351 |
deceive | +0.341 |
ares | +0.337 |
Neg logit contributions | |
Adidas | -0.197 |
aila | -0.196 |
Rust | -0.195 |
Pak | -0.192 |
bub | -0.192 |
Token | a |
Token ID | 257 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
enthal | +0.654 |
sted | +0.594 |
carbohyd | +0.584 |
deceive | +0.564 |
cius | +0.558 |
Neg logit contributions | |
Adidas | -0.545 |
Rust | -0.543 |
aila | -0.541 |
Pak | -0.536 |
bub | -0.533 |
Token | torn |
Token ID | 12445 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
enthal | +0.621 |
sted | +0.564 |
carbohyd | +0.549 |
deceive | +0.537 |
cius | +0.530 |
Neg logit contributions | |
Adidas | -0.545 |
Rust | -0.545 |
aila | -0.544 |
Pak | -0.540 |
bub | -0.534 |
Token | Achilles |
Token ID | 39561 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Adidas | +2.621 |
Rust | +2.526 |
aila | +2.506 |
bub | +2.480 |
Pak | +2.478 |
Neg logit contributions | |
enthal | -3.031 |
sted | -2.721 |
carbohyd | -2.717 |
cius | -2.598 |
eele | -2.568 |
Token | tendon |
Token ID | 42205 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Adidas | +2.589 |
Rust | +2.537 |
aila | +2.526 |
Pak | +2.498 |
bub | +2.468 |
Neg logit contributions | |
enthal | -4.702 |
sted | -4.301 |
carbohyd | -4.272 |
cius | -4.097 |
deceive | -4.087 |
Token | , |
Token ID | 11 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
Adidas | +3.990 |
aila | +3.876 |
Rust | +3.850 |
bub | +3.783 |
Wra | +3.741 |
Neg logit contributions | |
enthal | -6.116 |
sted | -5.533 |
carbohyd | -5.531 |
cius | -5.298 |
deceive | -5.250 |
Token | Wake |
Token ID | 20441 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
enthal | +0.161 |
sted | +0.149 |
carbohyd | +0.147 |
deceive | +0.143 |
cius | +0.142 |
Neg logit contributions | |
Adidas | -0.085 |
Rust | -0.084 |
aila | -0.084 |
Pak | -0.083 |
bub | -0.082 |
Token | collected |
Token ID | 7723 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
enthal | +0.436 |
sted | +0.396 |
carbohyd | +0.386 |
deceive | +0.373 |
ares | +0.369 |
Neg logit contributions | |
Adidas | -0.380 |
Rust | -0.376 |
aila | -0.374 |
bub | -0.371 |
Pak | -0.370 |
Token | 11 |
Token ID | 1367 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Adidas | +1.156 |
aila | +1.128 |
Rust | +1.125 |
bub | +1.108 |
Pak | +1.106 |
Neg logit contributions | |
enthal | -1.548 |
sted | -1.410 |
carbohyd | -1.408 |
cius | -1.340 |
deceive | -1.338 |
Token | . |
Token ID | 13 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
Adidas | +0.821 |
Rust | +0.809 |
aila | +0.808 |
Pak | +0.795 |
bub | +0.794 |
Neg logit contributions | |
enthal | -1.256 |
sted | -1.152 |
carbohyd | -1.140 |
deceive | -1.099 |
cius | -1.093 |
Token | org |
Token ID | 2398 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
Adidas | +1.394 |
Rust | +1.385 |
aila | +1.378 |
bub | +1.365 |
Pak | +1.356 |
Neg logit contributions | |
enthal | -2.017 |
carbohyd | -1.849 |
sted | -1.846 |
deceive | -1.766 |
cius | -1.738 |
Token | / |
Token ID | 14 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
enthal | +0.899 |
sted | +0.807 |
carbohyd | +0.772 |
deceive | +0.755 |
cius | +0.753 |
Neg logit contributions | |
Adidas | -0.991 |
aila | -0.980 |
Rust | -0.979 |
Pak | -0.969 |
bub | -0.966 |
Token | index |
Token ID | 9630 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
Adidas | +1.911 |
Rust | +1.896 |
aila | +1.881 |
Pak | +1.858 |
bub | +1.858 |
Neg logit contributions | |
enthal | -3.254 |
sted | -2.988 |
carbohyd | -2.969 |
deceive | -2.865 |
cius | -2.835 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
enthal | +1.299 |
sted | +1.164 |
carbohyd | +1.102 |
ares | +1.084 |
deceive | +1.081 |
Neg logit contributions | |
Adidas | -1.371 |
Rust | -1.351 |
aila | -1.350 |
Pak | -1.330 |
bub | -1.324 |
Token | php |
Token ID | 10121 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
Adidas | +1.345 |
aila | +1.330 |
Rust | +1.327 |
bub | +1.307 |
Pak | +1.295 |
Neg logit contributions | |
enthal | -4.290 |
carbohyd | -4.027 |
sted | -4.007 |
deceive | -3.894 |
cius | -3.831 |
Token | ? |
Token ID | 30 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
Adidas | +1.572 |
Rust | +1.569 |
aila | +1.549 |
Pak | +1.541 |
bub | +1.541 |
Neg logit contributions | |
enthal | -1.996 |
carbohyd | -1.873 |
sted | -1.823 |
deceive | -1.747 |
cius | -1.710 |
Token | topic |
Token ID | 26652 |
Feature activation | +4.78e-03 |
Pos logit contributions | |
Rust | +6.367 |
bub | +6.297 |
Pak | +6.203 |
Adidas | +6.119 |
aila | +6.078 |
Neg logit contributions | |
enthal | -3.759 |
carbohyd | -3.607 |
sted | -3.280 |
deceive | -3.240 |
underest | -3.153 |
Token | = |
Token ID | 28 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Adidas | +0.010 |
aila | +0.010 |
Rust | +0.010 |
bub | +0.009 |
Pak | +0.009 |
Neg logit contributions | |
enthal | -0.013 |
sted | -0.012 |
cius | -0.011 |
deceive | -0.011 |
carbohyd | -0.011 |
Token | 28 |
Token ID | 2078 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Rust | +2.377 |
Adidas | +2.373 |
bub | +2.344 |
aila | +2.336 |
Pak | +2.332 |
Neg logit contributions | |
enthal | -3.164 |
carbohyd | -2.984 |
sted | -2.871 |
deceive | -2.791 |
cius | -2.735 |
Token | 18 |
Token ID | 1507 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
enthal | +0.313 |
sted | +0.285 |
carbohyd | +0.278 |
deceive | +0.270 |
cius | +0.268 |
Neg logit contributions | |
Adidas | -0.257 |
Rust | -0.254 |
aila | -0.254 |
Pak | -0.251 |
bub | -0.250 |
Token | 48 |
Token ID | 2780 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
enthal | +0.510 |
sted | +0.464 |
carbohyd | +0.453 |
deceive | +0.439 |
cius | +0.437 |
Neg logit contributions | |
Adidas | -0.420 |
Rust | -0.415 |
aila | -0.415 |
Pak | -0.409 |
bub | -0.408 |
Token | stad |
Token ID | 24107 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
enthal | +1.287 |
sted | +1.105 |
carbohyd | +1.006 |
deceive | +0.962 |
cius | +0.955 |
Neg logit contributions | |
Adidas | -2.735 |
Rust | -2.728 |
aila | -2.717 |
bub | -2.694 |
Pak | -2.686 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
enthal | +1.696 |
sted | +1.542 |
carbohyd | +1.465 |
deceive | +1.453 |
ares | +1.432 |
Neg logit contributions | |
Rust | -1.599 |
Adidas | -1.594 |
aila | -1.582 |
Pak | -1.580 |
bub | -1.575 |
Token | Jim |
Token ID | 5395 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
enthal | +0.263 |
sted | +0.237 |
carbohyd | +0.234 |
deceive | +0.223 |
cius | +0.222 |
Neg logit contributions | |
Adidas | -0.265 |
Rust | -0.261 |
aila | -0.260 |
Pak | -0.257 |
bub | -0.257 |
Token | Brennan |
Token ID | 26577 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
Adidas | +2.365 |
aila | +2.344 |
Rust | +2.316 |
bub | +2.307 |
Pak | +2.305 |
Neg logit contributions | |
enthal | -3.794 |
carbohyd | -3.471 |
sted | -3.470 |
deceive | -3.348 |
cius | -3.315 |
Token | and |
Token ID | 290 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Adidas | +0.334 |
aila | +0.329 |
Rust | +0.329 |
Pak | +0.324 |
bub | +0.323 |
Neg logit contributions | |
enthal | -0.447 |
sted | -0.407 |
carbohyd | -0.404 |
deceive | -0.388 |
cius | -0.386 |
Token | Kara |
Token ID | 34856 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Adidas | +0.507 |
Rust | +0.502 |
aila | +0.500 |
Pak | +0.495 |
bub | +0.494 |
Neg logit contributions | |
enthal | -0.532 |
sted | -0.480 |
carbohyd | -0.473 |
deceive | -0.454 |
cius | -0.450 |
Token | Lang |
Token ID | 16332 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
Adidas | +4.876 |
aila | +4.819 |
Rust | +4.791 |
Rust | +4.707 |
Pak | +4.702 |
Neg logit contributions | |
enthal | -5.020 |
carbohyd | -4.692 |
sted | -4.464 |
deceive | -4.322 |
underest | -4.201 |
Token | will |
Token ID | 481 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
enthal | +1.678 |
sted | +1.525 |
carbohyd | +1.460 |
deceive | +1.417 |
cius | +1.414 |
Neg logit contributions | |
Adidas | -1.465 |
Rust | -1.459 |
aila | -1.435 |
Pak | -1.433 |
bub | -1.414 |
Token | officially |
Token ID | 8720 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Adidas | +2.173 |
Rust | +2.117 |
aila | +2.110 |
Pak | +2.080 |
bub | +2.076 |
Neg logit contributions | |
enthal | -2.844 |
carbohyd | -2.580 |
sted | -2.578 |
cius | -2.458 |
ares | -2.423 |
Token | be |
Token ID | 307 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Adidas | +0.556 |
Rust | +0.548 |
aila | +0.547 |
Pak | +0.540 |
bub | +0.539 |
Neg logit contributions | |
enthal | -0.659 |
sted | -0.597 |
carbohyd | -0.591 |
deceive | -0.565 |
cius | -0.563 |
Token | induct |
Token ID | 28948 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
Adidas | +0.301 |
Rust | +0.297 |
aila | +0.296 |
Pak | +0.292 |
bub | +0.291 |
Neg logit contributions | |
enthal | -0.422 |
sted | -0.386 |
carbohyd | -0.381 |
deceive | -0.368 |
cius | -0.365 |
Token | . |
Token ID | 13 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
enthal | +1.211 |
sted | +1.087 |
carbohyd | +1.047 |
deceive | +1.013 |
ares | +1.008 |
Neg logit contributions | |
Rust | -1.197 |
Adidas | -1.187 |
aila | -1.176 |
bub | -1.166 |
Pak | -1.161 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
enthal | +0.613 |
sted | +0.553 |
carbohyd | +0.530 |
deceive | +0.518 |
ares | +0.513 |
Neg logit contributions | |
Adidas | -0.617 |
Rust | -0.615 |
aila | -0.614 |
bub | -0.607 |
Pak | -0.603 |
Token |
|
Token ID | 198 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
enthal | +0.314 |
sted | +0.284 |
carbohyd | +0.276 |
deceive | +0.268 |
cius | +0.266 |
Neg logit contributions | |
Adidas | -0.289 |
Rust | -0.286 |
aila | -0.285 |
Pak | -0.281 |
bub | -0.281 |
Token | � |
Token ID | 447 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
enthal | +0.188 |
sted | +0.171 |
carbohyd | +0.164 |
ares | +0.160 |
deceive | +0.160 |
Neg logit contributions | |
Adidas | -0.158 |
aila | -0.155 |
Rust | -0.154 |
bub | -0.152 |
Pak | -0.151 |
Token | � |
Token ID | 250 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
enthal | +1.054 |
sted | +0.956 |
carbohyd | +0.939 |
deceive | +0.904 |
cius | +0.897 |
Neg logit contributions | |
Adidas | -0.979 |
aila | -0.966 |
Rust | -0.964 |
bub | -0.954 |
Pak | -0.950 |
Token | Tel |
Token ID | 33317 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
enthal | +0.315 |
sted | +0.286 |
carbohyd | +0.279 |
deceive | +0.270 |
cius | +0.269 |
Neg logit contributions | |
Adidas | -0.258 |
aila | -0.254 |
Rust | -0.253 |
bub | -0.250 |
Pak | -0.249 |
Token | stra |
Token ID | 12044 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
bub | +1.983 |
Adidas | +1.965 |
aila | +1.947 |
Rust | +1.935 |
Pak | +1.909 |
Neg logit contributions | |
enthal | -7.815 |
carbohyd | -7.554 |
sted | -7.204 |
deceive | -7.192 |
Dise | -7.147 |
Token | is |
Token ID | 318 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Adidas | +0.982 |
Rust | +0.969 |
aila | +0.967 |
Pak | +0.957 |
bub | +0.954 |
Neg logit contributions | |
enthal | -1.085 |
sted | -0.980 |
carbohyd | -0.972 |
deceive | -0.928 |
cius | -0.922 |
Token | working |
Token ID | 1762 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
Adidas | +0.475 |
Rust | +0.469 |
aila | +0.468 |
Pak | +0.463 |
bub | +0.461 |
Neg logit contributions | |
enthal | -0.583 |
sted | -0.530 |
carbohyd | -0.524 |
deceive | -0.503 |
cius | -0.500 |
Token | with |
Token ID | 351 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
enthal | +1.225 |
sted | +1.113 |
carbohyd | +1.086 |
deceive | +1.061 |
ares | +1.049 |
Neg logit contributions | |
Adidas | -1.026 |
Rust | -1.019 |
aila | -1.018 |
bub | -1.010 |
Pak | -0.996 |
Token | the |
Token ID | 262 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
enthal | +0.069 |
sted | +0.062 |
carbohyd | +0.061 |
deceive | +0.059 |
cius | +0.059 |
Neg logit contributions | |
Adidas | -0.063 |
Rust | -0.063 |
aila | -0.062 |
Pak | -0.062 |
bub | -0.062 |
Token | advanced |
Token ID | 6190 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
enthal | +0.337 |
sted | +0.303 |
carbohyd | +0.299 |
deceive | +0.287 |
cius | +0.285 |
Neg logit contributions | |
Adidas | -0.333 |
Rust | -0.329 |
aila | -0.329 |
Pak | -0.325 |
bub | -0.324 |
Token | metrics |
Token ID | 20731 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
enthal | +1.785 |
sted | +1.611 |
carbohyd | +1.550 |
deceive | +1.504 |
ares | +1.473 |
Neg logit contributions | |
Rust | -2.226 |
aila | -2.224 |
Adidas | -2.206 |
Pak | -2.192 |
bub | -2.182 |
Token | courtesy |
Token ID | 12537 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
enthal | +0.584 |
sted | +0.529 |
carbohyd | +0.522 |
deceive | +0.502 |
cius | +0.498 |
Neg logit contributions | |
Adidas | -0.510 |
Rust | -0.505 |
aila | -0.504 |
Pak | -0.498 |
bub | -0.497 |
Token | of |
Token ID | 286 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
enthal | +0.799 |
sted | +0.717 |
carbohyd | +0.705 |
deceive | +0.676 |
cius | +0.669 |
Neg logit contributions | |
Adidas | -0.846 |
Rust | -0.840 |
aila | -0.837 |
Pak | -0.829 |
bub | -0.827 |
Token | Pro |
Token ID | 1041 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
enthal | +0.271 |
sted | +0.247 |
carbohyd | +0.244 |
deceive | +0.235 |
cius | +0.233 |
Neg logit contributions | |
Adidas | -0.202 |
Rust | -0.200 |
aila | -0.200 |
Pak | -0.197 |
bub | -0.197 |
Token | Football |
Token ID | 9957 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Adidas | +1.690 |
Rust | +1.663 |
aila | +1.649 |
Pak | +1.635 |
bub | +1.629 |
Neg logit contributions | |
enthal | -3.133 |
sted | -2.883 |
carbohyd | -2.870 |
deceive | -2.767 |
cius | -2.754 |
Token | Focus |
Token ID | 17061 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Adidas | +4.804 |
Rust | +4.713 |
aila | +4.705 |
Pak | +4.681 |
bub | +4.624 |
Neg logit contributions | |
enthal | -5.195 |
carbohyd | -4.703 |
sted | -4.697 |
deceive | -4.462 |
cius | -4.415 |
Token | unless |
Token ID | 4556 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
enthal | +0.803 |
sted | +0.725 |
carbohyd | +0.711 |
deceive | +0.686 |
cius | +0.681 |
Neg logit contributions | |
Adidas | -0.738 |
Rust | -0.733 |
aila | -0.731 |
Pak | -0.722 |
bub | -0.721 |
Token | otherwise |
Token ID | 4306 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
Adidas | +1.259 |
Rust | +1.224 |
aila | +1.219 |
bub | +1.197 |
Pak | +1.192 |
Neg logit contributions | |
enthal | -2.169 |
carbohyd | -1.995 |
sted | -1.990 |
deceive | -1.917 |
cius | -1.905 |
Token | indicated |
Token ID | 8203 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Adidas | +0.150 |
Rust | +0.148 |
aila | +0.148 |
Pak | +0.146 |
bub | +0.146 |
Neg logit contributions | |
enthal | -0.152 |
sted | -0.137 |
carbohyd | -0.135 |
deceive | -0.129 |
cius | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | -2.33e-03 |
Pos logit contributions | |
Adidas | +0.459 |
Rust | +0.452 |
aila | +0.451 |
Pak | +0.445 |
bub | +0.444 |
Neg logit contributions | |
enthal | -0.487 |
sted | -0.440 |
carbohyd | -0.436 |
deceive | -0.416 |
cius | -0.413 |
Token | , |
Token ID | 11 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
Adidas | +0.858 |
aila | +0.839 |
Rust | +0.839 |
Pak | +0.832 |
bub | +0.827 |
Neg logit contributions | |
enthal | -1.109 |
sted | -1.008 |
carbohyd | -1.006 |
deceive | -0.961 |
cius | -0.960 |
Token | telecommunications |
Token ID | 27473 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Adidas | +0.071 |
Rust | +0.069 |
aila | +0.069 |
Pak | +0.069 |
bub | +0.068 |
Neg logit contributions | |
enthal | -0.087 |
sted | -0.079 |
carbohyd | -0.079 |
deceive | -0.075 |
cius | -0.075 |
Token | companies |
Token ID | 2706 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
Adidas | +3.000 |
aila | +2.970 |
bub | +2.920 |
Pak | +2.913 |
Rust | +2.905 |
Neg logit contributions | |
enthal | -4.221 |
carbohyd | -3.863 |
sted | -3.815 |
cius | -3.673 |
ares | -3.620 |
Token | were |
Token ID | 547 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Adidas | +1.777 |
aila | +1.743 |
Rust | +1.736 |
Pak | +1.723 |
bub | +1.716 |
Neg logit contributions | |
enthal | -1.924 |
carbohyd | -1.752 |
sted | -1.737 |
cius | -1.636 |
ares | -1.633 |
Token | granted |
Token ID | 7520 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Adidas | +0.297 |
Rust | +0.294 |
aila | +0.293 |
Pak | +0.289 |
bub | +0.289 |
Neg logit contributions | |
enthal | -0.342 |
sted | -0.310 |
carbohyd | -0.305 |
deceive | -0.294 |
cius | -0.291 |
Token | retro |
Token ID | 12175 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Adidas | +0.367 |
Rust | +0.363 |
aila | +0.362 |
Pak | +0.358 |
bub | +0.357 |
Neg logit contributions | |
enthal | -0.359 |
sted | -0.322 |
carbohyd | -0.319 |
deceive | -0.304 |
cius | -0.302 |
Token | active |
Token ID | 5275 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Adidas | +1.525 |
Rust | +1.429 |
Pak | +1.412 |
aila | +1.398 |
bub | +1.349 |
Neg logit contributions | |
enthal | -8.234 |
carbohyd | -7.803 |
sted | -7.721 |
cius | -7.694 |
deceive | -7.605 |
Token | immunity |
Token ID | 16989 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Adidas | +5.320 |
aila | +5.215 |
Pak | +5.183 |
Rust | +5.174 |
Rust | +5.119 |
Neg logit contributions | |
enthal | -3.938 |
carbohyd | -3.450 |
sted | -3.365 |
cius | -3.285 |
ares | -3.156 |
Token | for |
Token ID | 329 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
Adidas | +2.458 |
Rust | +2.401 |
aila | +2.399 |
Pak | +2.381 |
bub | +2.358 |
Neg logit contributions | |
enthal | -3.266 |
carbohyd | -2.994 |
sted | -2.965 |
cius | -2.845 |
deceive | -2.837 |
Token | violating |
Token ID | 18134 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
Adidas | +1.131 |
aila | +1.113 |
Rust | +1.109 |
Pak | +1.101 |
bub | +1.097 |
Neg logit contributions | |
enthal | -1.176 |
sted | -1.058 |
carbohyd | -1.051 |
cius | -0.993 |
deceive | -0.991 |
Token | the |
Token ID | 262 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
enthal | +1.375 |
sted | +1.245 |
carbohyd | +1.201 |
deceive | +1.175 |
cius | +1.160 |
Neg logit contributions | |
Rust | -1.480 |
Adidas | -1.465 |
aila | -1.451 |
bub | -1.444 |
Pak | -1.442 |
Token | . |
Token ID | 13 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
Adidas | +0.583 |
Rust | +0.576 |
aila | +0.575 |
Pak | +0.568 |
bub | +0.567 |
Neg logit contributions | |
enthal | -0.672 |
sted | -0.609 |
carbohyd | -0.602 |
deceive | -0.578 |
cius | -0.574 |
Token | In |
Token ID | 554 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
Adidas | +0.183 |
Rust | +0.181 |
aila | +0.180 |
Pak | +0.179 |
bub | +0.178 |
Neg logit contributions | |
enthal | -0.187 |
sted | -0.168 |
carbohyd | -0.166 |
deceive | -0.159 |
cius | -0.157 |
Token | this |
Token ID | 428 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
enthal | +0.184 |
sted | +0.166 |
carbohyd | +0.163 |
deceive | +0.156 |
cius | +0.155 |
Neg logit contributions | |
Adidas | -0.188 |
Rust | -0.187 |
aila | -0.186 |
Pak | -0.184 |
bub | -0.184 |
Token | post |
Token ID | 1281 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
Adidas | +0.573 |
Rust | +0.566 |
aila | +0.563 |
bub | +0.557 |
Pak | +0.556 |
Neg logit contributions | |
enthal | -0.660 |
sted | -0.597 |
carbohyd | -0.593 |
deceive | -0.566 |
cius | -0.562 |
Token | I |
Token ID | 314 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
enthal | +0.040 |
sted | +0.036 |
carbohyd | +0.035 |
deceive | +0.034 |
cius | +0.034 |
Neg logit contributions | |
Adidas | -0.034 |
Rust | -0.034 |
aila | -0.034 |
Pak | -0.033 |
bub | -0.033 |
Token | 'll |
Token ID | 1183 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Adidas | +0.861 |
aila | +0.848 |
Rust | +0.841 |
bub | +0.839 |
Pak | +0.833 |
Neg logit contributions | |
enthal | -1.051 |
carbohyd | -0.960 |
sted | -0.953 |
cius | -0.901 |
deceive | -0.897 |
Token | round |
Token ID | 2835 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
Adidas | +4.556 |
aila | +4.416 |
bub | +4.403 |
Rust | +4.400 |
Rust | +4.364 |
Neg logit contributions | |
enthal | -5.229 |
carbohyd | -4.969 |
sted | -4.745 |
cius | -4.472 |
ares | -4.448 |
Token | up |
Token ID | 510 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
Adidas | +0.942 |
Rust | +0.934 |
aila | +0.926 |
bub | +0.917 |
Pak | +0.915 |
Neg logit contributions | |
enthal | -1.225 |
sted | -1.112 |
carbohyd | -1.107 |
deceive | -1.059 |
cius | -1.057 |
Token | some |
Token ID | 617 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Adidas | +2.223 |
Rust | +2.195 |
aila | +2.158 |
bub | +2.137 |
Pak | +2.129 |
Neg logit contributions | |
enthal | -2.459 |
sted | -2.240 |
carbohyd | -2.229 |
cius | -2.100 |
deceive | -2.090 |
Token | got |
Token ID | 1392 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Adidas | +0.776 |
Rust | +0.766 |
aila | +0.760 |
Pak | +0.753 |
bub | +0.752 |
Neg logit contributions | |
enthal | -0.778 |
sted | -0.702 |
carbohyd | -0.696 |
deceive | -0.659 |
cius | -0.657 |
Token | cha |
Token ID | 11693 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
Adidas | +2.229 |
Rust | +2.208 |
aila | +2.197 |
bub | +2.169 |
Pak | +2.167 |
Neg logit contributions | |
enthal | -2.949 |
sted | -2.680 |
carbohyd | -2.665 |
deceive | -2.556 |
cius | -2.539 |
Token | , |
Token ID | 11 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Adidas | +0.990 |
Rust | +0.966 |
aila | +0.964 |
Pak | +0.951 |
bub | +0.948 |
Neg logit contributions | |
enthal | -1.292 |
sted | -1.175 |
carbohyd | -1.164 |
deceive | -1.125 |
cius | -1.120 |
Token | he |
Token ID | 339 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Adidas | +0.425 |
Rust | +0.417 |
aila | +0.416 |
Pak | +0.410 |
bub | +0.409 |
Neg logit contributions | |
enthal | -0.575 |
sted | -0.525 |
carbohyd | -0.519 |
deceive | -0.499 |
cius | -0.497 |
Token | finished |
Token ID | 5201 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
Adidas | +0.256 |
Rust | +0.253 |
aila | +0.253 |
Pak | +0.250 |
bub | +0.249 |
Neg logit contributions | |
enthal | -0.271 |
sted | -0.244 |
carbohyd | -0.241 |
deceive | -0.231 |
cius | -0.229 |
Token | as |
Token ID | 355 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
enthal | +0.889 |
sted | +0.809 |
carbohyd | +0.788 |
deceive | +0.765 |
cius | +0.756 |
Neg logit contributions | |
Adidas | -0.813 |
Rust | -0.806 |
aila | -0.806 |
Pak | -0.798 |
bub | -0.795 |
Token | Pro |
Token ID | 1041 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
Adidas | +0.865 |
Rust | +0.849 |
aila | +0.847 |
Pak | +0.836 |
bub | +0.833 |
Neg logit contributions | |
enthal | -0.971 |
sted | -0.873 |
carbohyd | -0.866 |
deceive | -0.824 |
cius | -0.822 |
Token | Football |
Token ID | 9957 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Adidas | +1.386 |
Rust | +1.358 |
aila | +1.348 |
Pak | +1.337 |
bub | +1.327 |
Neg logit contributions | |
enthal | -2.726 |
sted | -2.513 |
carbohyd | -2.497 |
deceive | -2.412 |
cius | -2.396 |
Token | Focus |
Token ID | 17061 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
Adidas | +4.460 |
aila | +4.379 |
Pak | +4.342 |
Rust | +4.313 |
Rust | +4.154 |
Neg logit contributions | |
enthal | -5.289 |
carbohyd | -4.971 |
sted | -4.839 |
deceive | -4.670 |
cius | -4.563 |
Token | � |
Token ID | 447 |
Feature activation | +8.46e-03 |
Pos logit contributions | |
enthal | +0.233 |
sted | +0.213 |
carbohyd | +0.211 |
deceive | +0.203 |
cius | +0.202 |
Neg logit contributions | |
Adidas | -0.161 |
Rust | -0.159 |
aila | -0.158 |
Pak | -0.156 |
bub | -0.156 |
Token | � |
Token ID | 247 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
Adidas | +0.017 |
Rust | +0.017 |
aila | +0.017 |
Pak | +0.017 |
bub | +0.017 |
Neg logit contributions | |
enthal | -0.023 |
sted | -0.021 |
carbohyd | -0.021 |
deceive | -0.020 |
cius | -0.020 |
Token | s |
Token ID | 82 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Adidas | +0.127 |
Rust | +0.125 |
aila | +0.125 |
bub | +0.123 |
Pak | +0.122 |
Neg logit contributions | |
enthal | -0.202 |
sted | -0.187 |
carbohyd | -0.182 |
deceive | -0.177 |
cius | -0.176 |
Token | second |
Token ID | 1218 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
Adidas | +0.520 |
Rust | +0.512 |
aila | +0.510 |
Pak | +0.505 |
bub | +0.504 |
Neg logit contributions | |
enthal | -0.521 |
sted | -0.467 |
carbohyd | -0.464 |
deceive | -0.441 |
cius | -0.438 |
Token | to |
Token ID | 284 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
enthal | +0.867 |
sted | +0.791 |
carbohyd | +0.777 |
deceive | +0.747 |
ares | +0.739 |
Neg logit contributions | |
Adidas | -0.703 |
Rust | -0.698 |
aila | -0.695 |
bub | -0.687 |
Pak | -0.686 |
Token | attend |
Token ID | 5262 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
Adidas | +0.751 |
Rust | +0.742 |
aila | +0.741 |
Pak | +0.732 |
bub | +0.730 |
Neg logit contributions | |
enthal | -0.831 |
sted | -0.751 |
carbohyd | -0.742 |
deceive | -0.710 |
cius | -0.706 |
Token | several |
Token ID | 1811 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Adidas | +1.332 |
Rust | +1.308 |
aila | +1.302 |
bub | +1.286 |
Pak | +1.284 |
Neg logit contributions | |
enthal | -1.557 |
carbohyd | -1.409 |
sted | -1.408 |
deceive | -1.343 |
cius | -1.343 |
Token | meetings |
Token ID | 8292 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
enthal | +0.324 |
sted | +0.293 |
carbohyd | +0.289 |
deceive | +0.278 |
cius | +0.275 |
Neg logit contributions | |
Adidas | -0.287 |
Rust | -0.285 |
aila | -0.284 |
Pak | -0.281 |
bub | -0.280 |
Token | in |
Token ID | 287 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
enthal | +0.494 |
sted | +0.447 |
carbohyd | +0.437 |
deceive | +0.422 |
cius | +0.419 |
Neg logit contributions | |
Adidas | -0.453 |
Rust | -0.449 |
aila | -0.448 |
Pak | -0.443 |
bub | -0.442 |
Token | protest |
Token ID | 5402 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Adidas | +0.867 |
Rust | +0.862 |
aila | +0.860 |
Pak | +0.852 |
bub | +0.848 |
Neg logit contributions | |
enthal | -0.964 |
sted | -0.874 |
carbohyd | -0.857 |
deceive | -0.827 |
cius | -0.820 |
Token | at |
Token ID | 379 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
Adidas | +4.163 |
Rust | +4.050 |
aila | +4.049 |
bub | +4.019 |
Pak | +3.919 |
Neg logit contributions | |
enthal | -5.540 |
carbohyd | -5.134 |
sted | -4.909 |
deceive | -4.856 |
eele | -4.851 |
Token | Spain |
Token ID | 8602 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
Adidas | +1.415 |
aila | +1.389 |
Rust | +1.385 |
bub | +1.368 |
Pak | +1.362 |
Neg logit contributions | |
enthal | -1.651 |
carbohyd | -1.492 |
sted | -1.490 |
deceive | -1.425 |
cius | -1.420 |
Token | � |
Token ID | 447 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
enthal | +0.008 |
sted | +0.008 |
carbohyd | +0.008 |
deceive | +0.007 |
cius | +0.007 |
Neg logit contributions | |
Adidas | -0.007 |
Rust | -0.007 |
aila | -0.007 |
Pak | -0.007 |
bub | -0.007 |
Token | � |
Token ID | 247 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
enthal | +1.068 |
sted | +0.976 |
carbohyd | +0.955 |
deceive | +0.923 |
cius | +0.918 |
Neg logit contributions | |
Adidas | -0.843 |
aila | -0.830 |
Rust | -0.830 |
bub | -0.819 |
Pak | -0.815 |
Token | s |
Token ID | 82 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
enthal | +0.505 |
sted | +0.468 |
carbohyd | +0.458 |
deceive | +0.446 |
cius | +0.443 |
Neg logit contributions | |
Adidas | -0.276 |
Rust | -0.273 |
aila | -0.271 |
Pak | -0.266 |
bub | -0.265 |
Token | " |
Token ID | 366 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Adidas | +0.029 |
Rust | +0.029 |
aila | +0.029 |
bub | +0.028 |
Pak | +0.028 |
Neg logit contributions | |
enthal | -0.032 |
sted | -0.029 |
carbohyd | -0.029 |
deceive | -0.028 |
cius | -0.028 |
Token | I |
Token ID | 40 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
enthal | +0.569 |
sted | +0.517 |
carbohyd | +0.489 |
deceive | +0.484 |
ares | +0.483 |
Neg logit contributions | |
Adidas | -0.531 |
aila | -0.528 |
Rust | -0.518 |
bub | -0.515 |
Pak | -0.510 |
Token | consider |
Token ID | 2074 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
Adidas | +0.234 |
Rust | +0.231 |
aila | +0.231 |
Pak | +0.228 |
bub | +0.228 |
Neg logit contributions | |
enthal | -0.238 |
sted | -0.214 |
carbohyd | -0.212 |
deceive | -0.202 |
cius | -0.201 |
Token | myself |
Token ID | 3589 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
enthal | +1.724 |
sted | +1.531 |
carbohyd | +1.444 |
deceive | +1.432 |
cius | +1.397 |
Neg logit contributions | |
Rust | -2.596 |
aila | -2.588 |
Adidas | -2.576 |
Pak | -2.565 |
bub | -2.555 |
Token | smart |
Token ID | 4451 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
Adidas | +0.137 |
Rust | +0.136 |
aila | +0.136 |
bub | +0.134 |
Pak | +0.134 |
Neg logit contributions | |
enthal | -0.167 |
sted | -0.152 |
carbohyd | -0.149 |
deceive | -0.144 |
cius | -0.143 |
Token | enough |
Token ID | 1576 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Adidas | +0.988 |
Rust | +0.976 |
aila | +0.973 |
Pak | +0.962 |
bub | +0.961 |
Neg logit contributions | |
enthal | -1.195 |
sted | -1.085 |
carbohyd | -1.072 |
deceive | -1.030 |
cius | -1.023 |
Token | to |
Token ID | 284 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Adidas | +3.637 |
aila | +3.558 |
Pak | +3.522 |
Rust | +3.510 |
bub | +3.482 |
Neg logit contributions | |
enthal | -5.923 |
carbohyd | -5.497 |
sted | -5.447 |
Dise | -5.207 |
Admission | -5.172 |
Token | hire |
Token ID | 11078 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
Adidas | +0.394 |
Rust | +0.391 |
aila | +0.390 |
Pak | +0.386 |
bub | +0.386 |
Neg logit contributions | |
enthal | -0.291 |
sted | -0.256 |
carbohyd | -0.252 |
deceive | -0.239 |
cius | -0.237 |
Token | excellent |
Token ID | 6275 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
enthal | +0.099 |
sted | +0.090 |
carbohyd | +0.089 |
deceive | +0.085 |
cius | +0.084 |
Neg logit contributions | |
Adidas | -0.093 |
Rust | -0.092 |
aila | -0.091 |
Pak | -0.090 |
bub | -0.090 |
Token | people |
Token ID | 661 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
enthal | +0.760 |
sted | +0.686 |
carbohyd | +0.668 |
deceive | +0.647 |
cius | +0.643 |
Neg logit contributions | |
Adidas | -0.798 |
Rust | -0.797 |
aila | -0.793 |
bub | -0.784 |
Pak | -0.782 |
Token | who |
Token ID | 508 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
enthal | +1.007 |
sted | +0.910 |
carbohyd | +0.889 |
deceive | +0.864 |
cius | +0.858 |
Neg logit contributions | |
Adidas | -0.900 |
Rust | -0.896 |
aila | -0.891 |
bub | -0.881 |
Pak | -0.879 |
Token | from |
Token ID | 422 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Adidas | +0.478 |
Rust | +0.472 |
aila | +0.469 |
Pak | +0.464 |
bub | +0.463 |
Neg logit contributions | |
enthal | -0.621 |
sted | -0.566 |
carbohyd | -0.560 |
deceive | -0.538 |
cius | -0.535 |
Token | a |
Token ID | 257 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Adidas | +0.647 |
Rust | +0.639 |
aila | +0.637 |
Pak | +0.625 |
bub | +0.624 |
Neg logit contributions | |
enthal | -1.249 |
sted | -1.154 |
carbohyd | -1.139 |
deceive | -1.106 |
cius | -1.099 |
Token | 10 |
Token ID | 838 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
Adidas | +0.203 |
Rust | +0.200 |
aila | +0.200 |
Pak | +0.197 |
bub | +0.196 |
Neg logit contributions | |
enthal | -0.362 |
sted | -0.334 |
carbohyd | -0.328 |
deceive | -0.320 |
cius | -0.317 |
Token | - |
Token ID | 12 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
Adidas | +1.103 |
aila | +1.087 |
Rust | +1.085 |
Pak | +1.080 |
bub | +1.072 |
Neg logit contributions | |
enthal | -1.927 |
carbohyd | -1.772 |
sted | -1.764 |
deceive | -1.697 |
cius | -1.689 |
Token | day |
Token ID | 820 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
enthal | +1.122 |
sted | +1.016 |
carbohyd | +0.981 |
deceive | +0.951 |
cius | +0.948 |
Neg logit contributions | |
Adidas | -1.019 |
aila | -1.007 |
Rust | -1.003 |
Pak | -0.978 |
bub | -0.976 |
Token | recess |
Token ID | 28836 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
enthal | +1.610 |
sted | +1.507 |
carbohyd | +1.457 |
deceive | +1.452 |
cius | +1.441 |
Neg logit contributions | |
aila | -0.492 |
Rust | -0.484 |
Adidas | -0.484 |
bub | -0.467 |
Pak | -0.464 |
Token | . |
Token ID | 13 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
Adidas | +3.922 |
bub | +3.819 |
Rust | +3.816 |
aila | +3.808 |
Pak | +3.783 |
Neg logit contributions | |
enthal | -5.487 |
carbohyd | -5.098 |
sted | -4.976 |
eele | -4.808 |
cius | -4.797 |
Token | But |
Token ID | 887 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
Adidas | +0.092 |
Rust | +0.091 |
aila | +0.090 |
Pak | +0.089 |
bub | +0.089 |
Neg logit contributions | |
enthal | -0.095 |
carbohyd | -0.086 |
sted | -0.085 |
deceive | -0.081 |
cius | -0.080 |
Token | even |
Token ID | 772 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
Adidas | +1.076 |
Rust | +1.056 |
aila | +1.049 |
Pak | +1.039 |
bub | +1.038 |
Neg logit contributions | |
enthal | -1.241 |
carbohyd | -1.132 |
sted | -1.124 |
deceive | -1.058 |
cius | -1.056 |
Token | though |
Token ID | 996 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
enthal | +1.798 |
sted | +1.636 |
carbohyd | +1.578 |
deceive | +1.551 |
cius | +1.528 |
Neg logit contributions | |
Adidas | -1.538 |
aila | -1.535 |
Rust | -1.534 |
Pak | -1.519 |
bub | -1.508 |
Token | Republicans |
Token ID | 4734 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
enthal | +0.644 |
sted | +0.582 |
carbohyd | +0.572 |
deceive | +0.552 |
cius | +0.547 |
Neg logit contributions | |
Adidas | -0.590 |
Rust | -0.585 |
aila | -0.583 |
Pak | -0.577 |
bub | -0.575 |
Token | rather |
Token ID | 2138 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
Adidas | +1.451 |
Rust | +1.425 |
aila | +1.425 |
Pak | +1.409 |
bub | +1.408 |
Neg logit contributions | |
enthal | -1.670 |
carbohyd | -1.509 |
sted | -1.508 |
cius | -1.422 |
deceive | -1.420 |
Token | that |
Token ID | 326 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
enthal | +1.721 |
sted | +1.558 |
carbohyd | +1.508 |
deceive | +1.486 |
cius | +1.458 |
Neg logit contributions | |
Adidas | -1.664 |
Rust | -1.660 |
aila | -1.653 |
Pak | -1.632 |
bub | -1.627 |
Token | they |
Token ID | 484 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
Adidas | +0.120 |
Rust | +0.119 |
aila | +0.118 |
Pak | +0.117 |
bub | +0.117 |
Neg logit contributions | |
enthal | -0.121 |
sted | -0.108 |
carbohyd | -0.108 |
deceive | -0.102 |
cius | -0.102 |
Token | were |
Token ID | 547 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
enthal | +0.093 |
sted | +0.081 |
carbohyd | +0.081 |
deceive | +0.074 |
cius | +0.074 |
Neg logit contributions | |
Adidas | -0.146 |
Rust | -0.144 |
aila | -0.144 |
Pak | -0.143 |
bub | -0.143 |
Token | stupid |
Token ID | 8531 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
enthal | +0.588 |
sted | +0.532 |
carbohyd | +0.522 |
deceive | +0.504 |
cius | +0.499 |
Neg logit contributions | |
Adidas | -0.544 |
Rust | -0.539 |
aila | -0.538 |
Pak | -0.531 |
bub | -0.530 |
Token | enough |
Token ID | 1576 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
enthal | +1.244 |
sted | +1.145 |
carbohyd | +1.115 |
deceive | +1.092 |
cius | +1.081 |
Neg logit contributions | |
Adidas | -0.850 |
Rust | -0.842 |
aila | -0.839 |
Pak | -0.823 |
bub | -0.822 |
Token | to |
Token ID | 284 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Adidas | +3.530 |
aila | +3.446 |
Rust | +3.432 |
Pak | +3.431 |
bub | +3.367 |
Neg logit contributions | |
enthal | -5.829 |
carbohyd | -5.368 |
sted | -5.316 |
Dise | -5.037 |
Admission | -5.014 |
Token | expect |
Token ID | 1607 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Adidas | +0.447 |
aila | +0.440 |
Rust | +0.440 |
Pak | +0.435 |
bub | +0.435 |
Neg logit contributions | |
enthal | -0.441 |
carbohyd | -0.396 |
sted | -0.395 |
cius | -0.371 |
ares | -0.367 |
Token | a |
Token ID | 257 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
enthal | +0.629 |
sted | +0.567 |
carbohyd | +0.553 |
deceive | +0.534 |
cius | +0.527 |
Neg logit contributions | |
Adidas | -0.667 |
Rust | -0.661 |
aila | -0.659 |
Pak | -0.652 |
bub | -0.651 |
Token | piece |
Token ID | 3704 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
enthal | +0.401 |
sted | +0.362 |
carbohyd | +0.355 |
deceive | +0.343 |
cius | +0.339 |
Neg logit contributions | |
Adidas | -0.376 |
Rust | -0.372 |
aila | -0.371 |
Pak | -0.367 |
bub | -0.366 |
Token | from |
Token ID | 422 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
Adidas | +1.496 |
aila | +1.468 |
Rust | +1.466 |
Pak | +1.459 |
bub | +1.455 |
Neg logit contributions | |
enthal | -1.552 |
sted | -1.401 |
carbohyd | -1.401 |
cius | -1.316 |
deceive | -1.315 |
Token | Luke |
Token ID | 11336 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
Adidas | +0.921 |
Rust | +0.908 |
aila | +0.904 |
bub | +0.893 |
Pak | +0.893 |
Neg logit contributions | |
enthal | -1.043 |
sted | -0.941 |
carbohyd | -0.934 |
deceive | -0.890 |
cius | -0.887 |
Token | Skywalker |
Token ID | 29715 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
enthal | +1.864 |
sted | +1.619 |
carbohyd | +1.550 |
deceive | +1.501 |
cius | +1.489 |
Neg logit contributions | |
aila | -2.643 |
Rust | -2.639 |
Adidas | -2.638 |
bub | -2.607 |
Pak | -2.603 |
Token | in |
Token ID | 287 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
enthal | +4.987 |
sted | +4.467 |
carbohyd | +4.178 |
deceive | +4.175 |
Swanson | +4.161 |
Neg logit contributions | |
aila | -5.008 |
Rust | -4.892 |
Adidas | -4.856 |
Pak | -4.813 |
bub | -4.763 |
Token | the |
Token ID | 262 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Adidas | +1.305 |
Rust | +1.277 |
aila | +1.274 |
bub | +1.266 |
Pak | +1.264 |
Neg logit contributions | |
enthal | -1.303 |
carbohyd | -1.171 |
sted | -1.165 |
deceive | -1.107 |
cius | -1.103 |
Token | Star |
Token ID | 2907 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Adidas | +0.522 |
Rust | +0.516 |
aila | +0.514 |
Pak | +0.509 |
bub | +0.508 |
Neg logit contributions | |
enthal | -0.532 |
sted | -0.479 |
carbohyd | -0.473 |
deceive | -0.452 |
cius | -0.449 |
Token | Wars |
Token ID | 6176 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
enthal | +2.073 |
sted | +1.818 |
carbohyd | +1.708 |
deceive | +1.668 |
cius | +1.648 |
Neg logit contributions | |
Adidas | -3.537 |
Rust | -3.519 |
aila | -3.518 |
Pak | -3.460 |
bub | -3.447 |
Token | films |
Token ID | 7328 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
enthal | +5.561 |
sted | +4.974 |
deceive | +4.789 |
ares | +4.738 |
underest | +4.687 |
Neg logit contributions | |
Rust | -7.172 |
aila | -7.095 |
Adidas | -6.985 |
Pak | -6.813 |
bub | -6.715 |
Token | — |
Token ID | 960 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
enthal | +2.565 |
sted | +2.327 |
carbohyd | +2.218 |
ares | +2.199 |
deceive | +2.194 |
Neg logit contributions | |
Adidas | -2.203 |
aila | -2.201 |
Rust | -2.196 |
Pak | -2.176 |
bub | -2.164 |
Token | including |
Token ID | 8201 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
Adidas | +0.415 |
Rust | +0.412 |
aila | +0.410 |
Pak | +0.406 |
bub | +0.405 |
Neg logit contributions | |
enthal | -0.413 |
sted | -0.371 |
carbohyd | -0.367 |
deceive | -0.351 |
cius | -0.348 |
Token | this |
Token ID | 428 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
enthal | +1.265 |
sted | +1.149 |
carbohyd | +1.120 |
deceive | +1.084 |
ares | +1.072 |
Neg logit contributions | |
Adidas | -1.166 |
Rust | -1.162 |
aila | -1.158 |
Pak | -1.143 |
bub | -1.141 |
Token | weekend |
Token ID | 5041 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
enthal | +0.316 |
sted | +0.286 |
carbohyd | +0.282 |
deceive | +0.272 |
cius | +0.269 |
Neg logit contributions | |
Adidas | -0.270 |
Rust | -0.267 |
aila | -0.267 |
Pak | -0.263 |
bub | -0.263 |
Token | day |
Token ID | 1110 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
enthal | +0.512 |
sted | +0.459 |
carbohyd | +0.450 |
deceive | +0.433 |
cius | +0.429 |
Neg logit contributions | |
Adidas | -0.534 |
Rust | -0.531 |
aila | -0.529 |
bub | -0.523 |
Pak | -0.522 |
Token | after |
Token ID | 706 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
enthal | +0.652 |
sted | +0.598 |
carbohyd | +0.593 |
deceive | +0.571 |
cius | +0.568 |
Neg logit contributions | |
Adidas | -0.419 |
Rust | -0.412 |
aila | -0.411 |
Pak | -0.405 |
bub | -0.404 |
Token | the |
Token ID | 262 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
enthal | +0.826 |
sted | +0.744 |
carbohyd | +0.732 |
deceive | +0.703 |
cius | +0.697 |
Neg logit contributions | |
Adidas | -0.806 |
Rust | -0.798 |
aila | -0.796 |
Pak | -0.787 |
bub | -0.786 |
Token | final |
Token ID | 2457 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
enthal | +0.647 |
sted | +0.580 |
carbohyd | +0.566 |
deceive | +0.546 |
cius | +0.539 |
Neg logit contributions | |
Adidas | -0.703 |
Rust | -0.701 |
aila | -0.698 |
Pak | -0.690 |
bub | -0.689 |
Token | Force |
Token ID | 5221 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
enthal | +0.156 |
sted | +0.140 |
carbohyd | +0.139 |
deceive | +0.132 |
cius | +0.132 |
Neg logit contributions | |
Adidas | -0.157 |
Rust | -0.155 |
aila | -0.155 |
Pak | -0.153 |
bub | -0.153 |
Token | Awakens |
Token ID | 39613 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
enthal | +0.864 |
sted | +0.698 |
carbohyd | +0.674 |
deceive | +0.627 |
cius | +0.611 |
Neg logit contributions | |
Adidas | -2.324 |
aila | -2.312 |
Rust | -2.310 |
Pak | -2.282 |
bub | -2.282 |
Token | trailer |
Token ID | 12268 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
enthal | +5.442 |
sted | +4.913 |
deceive | +4.756 |
Admission | +4.654 |
underest | +4.604 |
Neg logit contributions | |
Rust | -6.851 |
aila | -6.672 |
Adidas | -6.627 |
bub | -6.576 |
Pak | -6.573 |
Token | premiered |
Token ID | 44119 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
enthal | +3.370 |
sted | +3.063 |
deceive | +2.917 |
carbohyd | +2.882 |
ares | +2.843 |
Neg logit contributions | |
Rust | -3.439 |
Adidas | -3.430 |
Pak | -3.395 |
aila | -3.394 |
bub | -3.366 |
Token | ( |
Token ID | 357 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
enthal | +2.150 |
sted | +1.948 |
carbohyd | +1.894 |
deceive | +1.845 |
cius | +1.822 |
Neg logit contributions | |
Adidas | -1.939 |
Rust | -1.930 |
aila | -1.922 |
Pak | -1.905 |
bub | -1.900 |
Token | along |
Token ID | 24176 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
enthal | +1.344 |
sted | +1.210 |
carbohyd | +1.181 |
deceive | +1.139 |
cius | +1.131 |
Neg logit contributions | |
Adidas | -1.282 |
aila | -1.268 |
Rust | -1.263 |
Pak | -1.245 |
bub | -1.242 |
Token | with |
Token ID | 351 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
enthal | +0.548 |
sted | +0.497 |
carbohyd | +0.489 |
deceive | +0.470 |
cius | +0.467 |
Neg logit contributions | |
Adidas | -0.482 |
Rust | -0.477 |
aila | -0.476 |
Pak | -0.470 |
bub | -0.470 |
Token | This |
Token ID | 1212 |
Feature activation | +9.41e-02 |
Pos logit contributions | |
enthal | +0.649 |
sted | +0.588 |
carbohyd | +0.564 |
deceive | +0.553 |
cius | +0.549 |
Neg logit contributions | |
Adidas | -0.599 |
aila | -0.593 |
Rust | -0.586 |
bub | -0.582 |
Pak | -0.578 |
Token | is |
Token ID | 318 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
Adidas | +0.210 |
Rust | +0.208 |
aila | +0.207 |
Pak | +0.205 |
bub | +0.205 |
Neg logit contributions | |
enthal | -0.239 |
sted | -0.216 |
carbohyd | -0.213 |
deceive | -0.205 |
cius | -0.203 |
Token | the |
Token ID | 262 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
enthal | +0.013 |
sted | +0.012 |
carbohyd | +0.012 |
deceive | +0.011 |
cius | +0.011 |
Neg logit contributions | |
Adidas | -0.011 |
Rust | -0.011 |
aila | -0.011 |
Pak | -0.011 |
bub | -0.011 |
Token | first |
Token ID | 717 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
enthal | +0.352 |
sted | +0.320 |
carbohyd | +0.313 |
deceive | +0.304 |
cius | +0.302 |
Neg logit contributions | |
Adidas | -0.280 |
Rust | -0.279 |
aila | -0.278 |
Pak | -0.275 |
bub | -0.274 |
Token | Star |
Token ID | 2907 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
enthal | +0.716 |
sted | +0.653 |
carbohyd | +0.642 |
deceive | +0.621 |
cius | +0.616 |
Neg logit contributions | |
Adidas | -0.541 |
Rust | -0.536 |
aila | -0.534 |
Pak | -0.528 |
bub | -0.527 |
Token | Wars |
Token ID | 6176 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
enthal | +1.661 |
sted | +1.475 |
carbohyd | +1.387 |
deceive | +1.349 |
cius | +1.334 |
Neg logit contributions | |
Adidas | -2.695 |
aila | -2.676 |
Rust | -2.673 |
Pak | -2.629 |
bub | -2.625 |
Token | movie |
Token ID | 3807 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
enthal | +5.964 |
sted | +5.284 |
deceive | +5.098 |
Admission | +5.025 |
underest | +5.008 |
Neg logit contributions | |
Rust | -6.397 |
aila | -6.237 |
Adidas | -6.203 |
Pak | -6.143 |
bub | -6.139 |
Token | in |
Token ID | 287 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
enthal | +2.455 |
sted | +2.205 |
carbohyd | +2.118 |
deceive | +2.092 |
ares | +2.055 |
Neg logit contributions | |
Rust | -2.337 |
Adidas | -2.319 |
aila | -2.309 |
bub | -2.289 |
Pak | -2.286 |
Token | the |
Token ID | 262 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Adidas | +0.641 |
Rust | +0.630 |
aila | +0.628 |
Pak | +0.620 |
bub | +0.618 |
Neg logit contributions | |
enthal | -0.877 |
sted | -0.799 |
carbohyd | -0.793 |
deceive | -0.761 |
cius | -0.759 |
Token | age |
Token ID | 2479 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Adidas | +0.876 |
Rust | +0.861 |
aila | +0.860 |
Pak | +0.851 |
bub | +0.849 |
Neg logit contributions | |
enthal | -0.974 |
sted | -0.879 |
carbohyd | -0.874 |
deceive | -0.832 |
cius | -0.830 |
Token | of |
Token ID | 286 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Adidas | +3.076 |
bub | +3.015 |
aila | +3.008 |
Rust | +2.976 |
Pak | +2.973 |
Neg logit contributions | |
enthal | -3.270 |
carbohyd | -2.962 |
sted | -2.950 |
cius | -2.790 |
deceive | -2.773 |
Token | , |
Token ID | 11 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
enthal | +1.037 |
sted | +0.941 |
carbohyd | +0.922 |
deceive | +0.889 |
cius | +0.882 |
Neg logit contributions | |
Adidas | -0.866 |
Rust | -0.859 |
aila | -0.856 |
Pak | -0.843 |
bub | -0.842 |
Token | being |
Token ID | 852 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Adidas | +0.563 |
Rust | +0.550 |
aila | +0.549 |
bub | +0.544 |
Pak | +0.543 |
Neg logit contributions | |
enthal | -0.577 |
carbohyd | -0.520 |
sted | -0.520 |
deceive | -0.490 |
cius | -0.489 |
Token | in |
Token ID | 287 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
enthal | +0.553 |
sted | +0.500 |
carbohyd | +0.493 |
deceive | +0.473 |
cius | +0.469 |
Neg logit contributions | |
Adidas | -0.512 |
Rust | -0.506 |
aila | -0.505 |
Pak | -0.499 |
bub | -0.498 |
Token | a |
Token ID | 257 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
enthal | +0.455 |
sted | +0.410 |
carbohyd | +0.400 |
deceive | +0.388 |
cius | +0.383 |
Neg logit contributions | |
Rust | -0.433 |
Adidas | -0.433 |
aila | -0.432 |
Pak | -0.427 |
bub | -0.422 |
Token | Star |
Token ID | 2907 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
Adidas | +0.129 |
Rust | +0.128 |
aila | +0.127 |
Pak | +0.126 |
bub | +0.126 |
Neg logit contributions | |
enthal | -0.130 |
sted | -0.117 |
carbohyd | -0.115 |
deceive | -0.110 |
cius | -0.109 |
Token | Wars |
Token ID | 6176 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
enthal | +1.441 |
sted | +1.259 |
carbohyd | +1.191 |
deceive | +1.150 |
cius | +1.144 |
Neg logit contributions | |
Adidas | -2.354 |
aila | -2.340 |
Rust | -2.339 |
Pak | -2.309 |
bub | -2.301 |
Token | movie |
Token ID | 3807 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
enthal | +5.039 |
sted | +4.496 |
deceive | +4.352 |
ares | +4.326 |
Admission | +4.209 |
Neg logit contributions | |
Rust | -6.391 |
aila | -6.284 |
Pak | -6.235 |
Adidas | -6.188 |
bub | -6.024 |
Token | is |
Token ID | 318 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
enthal | +1.994 |
sted | +1.807 |
carbohyd | +1.724 |
deceive | +1.719 |
ares | +1.705 |
Neg logit contributions | |
Rust | -1.974 |
Adidas | -1.952 |
aila | -1.946 |
Pak | -1.935 |
bub | -1.928 |
Token | a |
Token ID | 257 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Adidas | +0.439 |
Rust | +0.432 |
aila | +0.432 |
Pak | +0.426 |
bub | +0.426 |
Neg logit contributions | |
enthal | -0.475 |
sted | -0.428 |
carbohyd | -0.424 |
deceive | -0.405 |
cius | -0.402 |
Token | great |
Token ID | 1049 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
enthal | +0.514 |
sted | +0.464 |
carbohyd | +0.453 |
deceive | +0.439 |
cius | +0.435 |
Neg logit contributions | |
Adidas | -0.502 |
Rust | -0.500 |
aila | -0.497 |
Pak | -0.492 |
bub | -0.490 |
Token | career |
Token ID | 3451 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
Adidas | +0.030 |
Rust | +0.030 |
aila | +0.030 |
Pak | +0.030 |
bub | +0.030 |
Neg logit contributions | |
enthal | -0.022 |
sted | -0.019 |
carbohyd | -0.019 |
deceive | -0.018 |
cius | -0.018 |
Token | time |
Token ID | 640 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
Adidas | +1.692 |
Rust | +1.671 |
aila | +1.666 |
Pak | +1.646 |
bub | +1.642 |
Neg logit contributions | |
enthal | -2.067 |
sted | -1.879 |
carbohyd | -1.856 |
deceive | -1.783 |
cius | -1.772 |
Token | since |
Token ID | 1201 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
enthal | +2.090 |
sted | +1.869 |
carbohyd | +1.815 |
deceive | +1.813 |
underest | +1.799 |
Neg logit contributions | |
Rust | -1.761 |
aila | -1.753 |
Adidas | -1.752 |
Pak | -1.726 |
bub | -1.716 |
Token | the |
Token ID | 262 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
enthal | +0.043 |
carbohyd | +0.039 |
sted | +0.039 |
cius | +0.037 |
deceive | +0.037 |
Neg logit contributions | |
Adidas | -0.036 |
Rust | -0.036 |
aila | -0.036 |
bub | -0.035 |
Pak | -0.035 |
Token | last |
Token ID | 938 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
Adidas | +0.137 |
Rust | +0.135 |
aila | +0.134 |
bub | +0.133 |
Pak | +0.133 |
Neg logit contributions | |
enthal | -0.176 |
sted | -0.160 |
carbohyd | -0.159 |
deceive | -0.152 |
cius | -0.152 |
Token | Star |
Token ID | 2907 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
enthal | +0.170 |
sted | +0.153 |
carbohyd | +0.153 |
deceive | +0.145 |
cius | +0.145 |
Neg logit contributions | |
Adidas | -0.154 |
Rust | -0.152 |
aila | -0.152 |
Pak | -0.150 |
bub | -0.150 |
Token | Wars |
Token ID | 6176 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
enthal | +1.410 |
sted | +1.229 |
carbohyd | +1.164 |
deceive | +1.124 |
cius | +1.116 |
Neg logit contributions | |
Adidas | -2.297 |
Rust | -2.281 |
aila | -2.280 |
Pak | -2.252 |
bub | -2.247 |
Token | movie |
Token ID | 3807 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
enthal | +4.431 |
sted | +3.880 |
deceive | +3.731 |
underest | +3.596 |
ares | +3.582 |
Neg logit contributions | |
Rust | -6.884 |
aila | -6.781 |
Adidas | -6.710 |
Pak | -6.671 |
bub | -6.630 |
Token | came |
Token ID | 1625 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
enthal | +1.923 |
sted | +1.740 |
carbohyd | +1.678 |
deceive | +1.646 |
cius | +1.616 |
Neg logit contributions | |
Rust | -1.835 |
Adidas | -1.834 |
aila | -1.820 |
Pak | -1.807 |
bub | -1.798 |
Token | out |
Token ID | 503 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Adidas | +0.150 |
Rust | +0.149 |
aila | +0.148 |
Pak | +0.146 |
bub | +0.146 |
Neg logit contributions | |
enthal | -0.221 |
sted | -0.202 |
carbohyd | -0.200 |
deceive | -0.193 |
cius | -0.192 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
enthal | +0.876 |
sted | +0.791 |
carbohyd | +0.775 |
deceive | +0.750 |
cius | +0.739 |
Neg logit contributions | |
Adidas | -0.799 |
Rust | -0.795 |
aila | -0.791 |
Pak | -0.784 |
bub | -0.782 |
Token | I |
Token ID | 314 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
Adidas | +0.046 |
Rust | +0.045 |
aila | +0.045 |
Pak | +0.045 |
bub | +0.044 |
Neg logit contributions | |
enthal | -0.049 |
carbohyd | -0.045 |
sted | -0.044 |
deceive | -0.042 |
cius | -0.042 |
Token | ( |
Token ID | 357 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
enthal | +1.440 |
sted | +1.326 |
carbohyd | +1.284 |
deceive | +1.249 |
ares | +1.246 |
Neg logit contributions | |
Adidas | -0.998 |
Rust | -0.992 |
aila | -0.986 |
Pak | -0.982 |
bub | -0.974 |
Token | Equ |
Token ID | 23588 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
enthal | +2.538 |
sted | +2.307 |
ares | +2.139 |
deceive | +2.123 |
Admission | +2.108 |
Neg logit contributions | |
aila | -2.322 |
Adidas | -2.297 |
bub | -2.248 |
Rust | -2.230 |
angelo | -2.218 |
Token | ipe |
Token ID | 3757 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
enthal | +2.730 |
sted | +2.468 |
ares | +2.351 |
cius | +2.336 |
carbohyd | +2.319 |
Neg logit contributions | |
Rust | -2.282 |
Adidas | -2.273 |
aila | -2.233 |
bub | -2.224 |
Pak | -2.215 |
Token | Cycl |
Token ID | 28007 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Adidas | +0.220 |
Rust | +0.216 |
aila | +0.216 |
Pak | +0.213 |
bub | +0.213 |
Neg logit contributions | |
enthal | -0.235 |
sted | -0.212 |
carbohyd | -0.210 |
deceive | -0.200 |
cius | -0.199 |
Token | iste |
Token ID | 40833 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
enthal | +0.213 |
sted | +0.190 |
carbohyd | +0.182 |
ares | +0.179 |
cius | +0.176 |
Neg logit contributions | |
Adidas | -0.269 |
Rust | -0.268 |
aila | -0.266 |
Pak | -0.265 |
bub | -0.264 |
Token | FD |
Token ID | 30002 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
enthal | +0.064 |
sted | +0.058 |
carbohyd | +0.057 |
deceive | +0.055 |
cius | +0.055 |
Neg logit contributions | |
Adidas | -0.052 |
Rust | -0.051 |
aila | -0.051 |
Pak | -0.050 |
bub | -0.050 |
Token | J |
Token ID | 41 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
enthal | +6.804 |
ares | +6.369 |
sted | +6.360 |
Admission | +6.201 |
carbohyd | +6.107 |
Neg logit contributions | |
Rust | -4.021 |
Adidas | -4.021 |
aila | -3.987 |
bub | -3.952 |
Pak | -3.875 |
Token | - |
Token ID | 532 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
Adidas | +1.100 |
Rust | +1.077 |
aila | +1.067 |
Pak | +1.056 |
bub | +1.053 |
Neg logit contributions | |
enthal | -0.929 |
sted | -0.817 |
carbohyd | -0.812 |
cius | -0.770 |
deceive | -0.765 |
Token | Big |
Token ID | 4403 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
enthal | +1.035 |
sted | +0.935 |
carbohyd | +0.906 |
deceive | +0.881 |
ares | +0.875 |
Neg logit contributions | |
aila | -0.970 |
Rust | -0.970 |
Adidas | -0.969 |
Pak | -0.961 |
bub | -0.957 |
Token | Mat |
Token ID | 19044 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
enthal | +0.028 |
sted | +0.025 |
carbohyd | +0.024 |
ares | +0.024 |
deceive | +0.024 |
Neg logit contributions | |
Adidas | -0.020 |
Rust | -0.020 |
aila | -0.020 |
bub | -0.020 |
Pak | -0.020 |
Token | ) |
Token ID | 8 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
enthal | +0.267 |
sted | +0.240 |
carbohyd | +0.235 |
deceive | +0.226 |
cius | +0.224 |
Neg logit contributions | |
Adidas | -0.278 |
Rust | -0.276 |
aila | -0.275 |
Pak | -0.272 |
bub | -0.272 |
Token | ( |
Token ID | 357 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
Adidas | +0.148 |
Rust | +0.148 |
aila | +0.147 |
Pak | +0.145 |
bub | +0.144 |
Neg logit contributions | |
enthal | -0.220 |
sted | -0.202 |
carbohyd | -0.197 |
deceive | -0.192 |
cius | -0.191 |
Token | Equ |
Token ID | 23588 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
enthal | +2.100 |
sted | +1.906 |
ares | +1.809 |
carbohyd | +1.796 |
deceive | +1.783 |
Neg logit contributions | |
Adidas | -1.845 |
aila | -1.834 |
Rust | -1.799 |
bub | -1.795 |
Pak | -1.775 |
Token | ipe |
Token ID | 3757 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
enthal | +3.044 |
sted | +2.773 |
ares | +2.665 |
cius | +2.654 |
carbohyd | +2.621 |
Neg logit contributions | |
Rust | -2.105 |
Adidas | -2.093 |
bub | -2.038 |
aila | -2.035 |
Pak | -2.031 |
Token | Cycl |
Token ID | 28007 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
enthal | +0.229 |
sted | +0.200 |
carbohyd | +0.195 |
deceive | +0.185 |
cius | +0.184 |
Neg logit contributions | |
Adidas | -0.345 |
Rust | -0.342 |
aila | -0.342 |
Pak | -0.339 |
bub | -0.338 |
Token | iste |
Token ID | 40833 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
enthal | +0.398 |
sted | +0.348 |
carbohyd | +0.321 |
ares | +0.318 |
cius | +0.317 |
Neg logit contributions | |
Rust | -0.600 |
Adidas | -0.599 |
aila | -0.591 |
bub | -0.590 |
Pak | -0.590 |
Token | FD |
Token ID | 30002 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Adidas | +0.066 |
Rust | +0.066 |
aila | +0.065 |
Pak | +0.065 |
bub | +0.065 |
Neg logit contributions | |
enthal | -0.028 |
sted | -0.024 |
carbohyd | -0.023 |
deceive | -0.021 |
cius | -0.021 |
Token | J |
Token ID | 41 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
enthal | +6.365 |
sted | +5.879 |
ares | +5.627 |
Admission | +5.616 |
eele | +5.436 |
Neg logit contributions | |
aila | -4.294 |
Adidas | -4.186 |
bub | -4.062 |
adic | -4.033 |
Rust | -4.031 |
Token | - |
Token ID | 532 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
Adidas | +0.935 |
Rust | +0.916 |
aila | +0.909 |
Pak | +0.905 |
bub | +0.897 |
Neg logit contributions | |
enthal | -1.023 |
carbohyd | -0.960 |
sted | -0.918 |
deceive | -0.887 |
cius | -0.880 |
Token | Big |
Token ID | 4403 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
enthal | +1.317 |
sted | +1.212 |
carbohyd | +1.191 |
deceive | +1.152 |
cius | +1.145 |
Neg logit contributions | |
Adidas | -0.858 |
aila | -0.856 |
Rust | -0.853 |
Pak | -0.846 |
bub | -0.839 |
Token | Mat |
Token ID | 19044 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
enthal | +0.464 |
sted | +0.432 |
carbohyd | +0.419 |
deceive | +0.411 |
cius | +0.410 |
Neg logit contributions | |
Adidas | -0.217 |
aila | -0.212 |
Rust | -0.211 |
bub | -0.207 |
Pak | -0.206 |
Token | ) |
Token ID | 8 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
enthal | +0.447 |
sted | +0.394 |
carbohyd | +0.380 |
deceive | +0.365 |
cius | +0.362 |
Neg logit contributions | |
Adidas | -0.613 |
Rust | -0.609 |
aila | -0.608 |
bub | -0.601 |
Pak | -0.601 |
Token | a |
Token ID | 257 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
Adidas | +0.080 |
Rust | +0.079 |
aila | +0.079 |
Pak | +0.078 |
bub | +0.078 |
Neg logit contributions | |
enthal | -0.086 |
sted | -0.078 |
carbohyd | -0.077 |
deceive | -0.074 |
cius | -0.073 |
Token | sleeping |
Token ID | 11029 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Adidas | +0.157 |
Rust | +0.156 |
aila | +0.156 |
Pak | +0.154 |
bub | +0.153 |
Neg logit contributions | |
enthal | -0.164 |
sted | -0.148 |
carbohyd | -0.146 |
deceive | -0.140 |
cius | -0.139 |
Token | est |
Token ID | 1556 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
enthal | +0.523 |
sted | +0.475 |
carbohyd | +0.463 |
deceive | +0.446 |
cius | +0.442 |
Neg logit contributions | |
Adidas | -0.517 |
Rust | -0.515 |
aila | -0.512 |
Pak | -0.507 |
bub | -0.505 |
Token | u |
Token ID | 84 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
enthal | +1.127 |
sted | +1.036 |
carbohyd | +1.022 |
deceive | +0.989 |
cius | +0.984 |
Neg logit contributions | |
Adidas | -0.704 |
Rust | -0.696 |
aila | -0.691 |
Pak | -0.682 |
bub | -0.680 |
Token | arine |
Token ID | 34569 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
enthal | +0.980 |
sted | +0.876 |
carbohyd | +0.842 |
deceive | +0.810 |
cius | +0.810 |
Neg logit contributions | |
Adidas | -1.253 |
Rust | -1.243 |
aila | -1.234 |
bub | -1.226 |
Pak | -1.220 |
Token | crocod |
Token ID | 37565 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
enthal | +2.107 |
sted | +1.928 |
carbohyd | +1.861 |
deceive | +1.824 |
ares | +1.792 |
Neg logit contributions | |
Rust | -1.942 |
Adidas | -1.932 |
aila | -1.917 |
Pak | -1.901 |
bub | -1.883 |
Token | ile |
Token ID | 576 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
enthal | +6.247 |
sted | +5.715 |
ares | +5.500 |
cius | +5.409 |
carbohyd | +5.364 |
Neg logit contributions | |
Rust | -4.700 |
Adidas | -4.630 |
Pak | -4.456 |
XY | -4.340 |
Wra | -4.318 |
Token | or |
Token ID | 393 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
enthal | +0.245 |
sted | +0.223 |
carbohyd | +0.220 |
deceive | +0.211 |
cius | +0.210 |
Neg logit contributions | |
Adidas | -0.199 |
Rust | -0.196 |
aila | -0.196 |
Pak | -0.193 |
bub | -0.193 |
Token | fly |
Token ID | 6129 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
enthal | +1.061 |
sted | +0.965 |
carbohyd | +0.948 |
deceive | +0.921 |
cius | +0.908 |
Neg logit contributions | |
Adidas | -0.963 |
Rust | -0.956 |
aila | -0.954 |
Pak | -0.942 |
bub | -0.935 |
Token | over |
Token ID | 625 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
enthal | +0.195 |
sted | +0.178 |
carbohyd | +0.174 |
deceive | +0.168 |
cius | +0.165 |
Neg logit contributions | |
Adidas | -0.179 |
Rust | -0.177 |
aila | -0.177 |
Pak | -0.175 |
bub | -0.174 |
Token | the |
Token ID | 262 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
enthal | +0.760 |
sted | +0.695 |
carbohyd | +0.679 |
deceive | +0.654 |
cius | +0.647 |
Neg logit contributions | |
Adidas | -0.679 |
Rust | -0.673 |
aila | -0.672 |
Pak | -0.664 |
bub | -0.659 |
Token | 19 |
Token ID | 1129 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
enthal | +2.562 |
sted | +2.325 |
carbohyd | +2.215 |
ares | +2.185 |
deceive | +2.161 |
Neg logit contributions | |
Adidas | -2.229 |
aila | -2.199 |
Rust | -2.156 |
Pak | -2.136 |
bub | -2.135 |
Token | - |
Token ID | 12 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Adidas | +0.240 |
Rust | +0.238 |
aila | +0.237 |
Pak | +0.234 |
bub | +0.234 |
Neg logit contributions | |
enthal | -0.280 |
sted | -0.254 |
carbohyd | -0.249 |
deceive | -0.241 |
cius | -0.238 |
Token | year |
Token ID | 1941 |
Feature activation | +7.42e-03 |
Pos logit contributions | |
enthal | +1.571 |
sted | +1.439 |
carbohyd | +1.398 |
deceive | +1.372 |
ares | +1.366 |
Neg logit contributions | |
Adidas | -1.048 |
aila | -1.035 |
Rust | -1.030 |
bub | -1.006 |
Pak | -0.992 |
Token | - |
Token ID | 12 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Adidas | +0.012 |
Rust | +0.012 |
aila | +0.012 |
Pak | +0.012 |
bub | +0.012 |
Neg logit contributions | |
enthal | -0.023 |
sted | -0.021 |
carbohyd | -0.021 |
deceive | -0.020 |
cius | -0.020 |
Token | old |
Token ID | 727 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
enthal | +0.855 |
sted | +0.796 |
ares | +0.756 |
cius | +0.751 |
carbohyd | +0.751 |
Neg logit contributions | |
Adidas | -0.431 |
aila | -0.420 |
Rust | -0.420 |
Pak | -0.408 |
bub | -0.405 |
Token | Hed |
Token ID | 30920 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Adidas | +0.909 |
Rust | +0.897 |
aila | +0.895 |
Pak | +0.886 |
bub | +0.882 |
Neg logit contributions | |
enthal | -0.879 |
sted | -0.786 |
carbohyd | -0.782 |
deceive | -0.742 |
cius | -0.742 |
Token | ges |
Token ID | 3212 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
enthal | +5.629 |
sted | +5.141 |
ares | +4.717 |
Swanson | +4.628 |
carbohyd | +4.627 |
Neg logit contributions | |
Adidas | -5.282 |
Rust | -5.211 |
aila | -5.184 |
XY | -5.044 |
bub | -5.035 |
Token | is |
Token ID | 318 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
enthal | +2.641 |
sted | +2.397 |
carbohyd | +2.272 |
deceive | +2.226 |
ares | +2.219 |
Neg logit contributions | |
Adidas | -2.615 |
aila | -2.599 |
Rust | -2.596 |
bub | -2.564 |
Pak | -2.545 |
Token | sure |
Token ID | 1654 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
enthal | +0.243 |
sted | +0.221 |
carbohyd | +0.219 |
deceive | +0.210 |
cius | +0.209 |
Neg logit contributions | |
Adidas | -0.195 |
Rust | -0.192 |
aila | -0.192 |
Pak | -0.190 |
bub | -0.189 |
Token | to |
Token ID | 284 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Adidas | +1.168 |
Rust | +1.148 |
aila | +1.143 |
Pak | +1.133 |
bub | +1.130 |
Neg logit contributions | |
enthal | -1.533 |
carbohyd | -1.385 |
sted | -1.383 |
cius | -1.337 |
deceive | -1.321 |
Token | be |
Token ID | 307 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
enthal | +0.408 |
sted | +0.367 |
carbohyd | +0.362 |
deceive | +0.346 |
cius | +0.344 |
Neg logit contributions | |
Adidas | -0.404 |
Rust | -0.399 |
aila | -0.398 |
Pak | -0.394 |
bub | -0.393 |
Token | i |
Token ID | 72 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
aila | +1.651 |
Adidas | +1.622 |
bub | +1.587 |
Pak | +1.582 |
Rust | +1.581 |
Neg logit contributions | |
enthal | -3.174 |
carbohyd | -3.003 |
sted | -2.916 |
deceive | -2.852 |
cius | -2.776 |
Token | , |
Token ID | 11 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
Adidas | +0.806 |
Rust | +0.797 |
aila | +0.795 |
Pak | +0.785 |
bub | +0.783 |
Neg logit contributions | |
enthal | -0.894 |
sted | -0.806 |
carbohyd | -0.804 |
deceive | -0.765 |
cius | -0.764 |
Token | hub |
Token ID | 12575 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Adidas | +0.679 |
Rust | +0.669 |
aila | +0.667 |
Pak | +0.659 |
bub | +0.658 |
Neg logit contributions | |
enthal | -0.798 |
sted | -0.724 |
carbohyd | -0.718 |
deceive | -0.685 |
cius | -0.684 |
Token | by |
Token ID | 1525 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
enthal | +0.661 |
sted | +0.617 |
carbohyd | +0.606 |
deceive | +0.590 |
cius | +0.586 |
Neg logit contributions | |
Adidas | -0.286 |
Rust | -0.281 |
aila | -0.277 |
Pak | -0.275 |
bub | -0.267 |
Token | Dean |
Token ID | 11325 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
enthal | +1.261 |
sted | +1.141 |
carbohyd | +1.112 |
deceive | +1.080 |
cius | +1.064 |
Neg logit contributions | |
Adidas | -1.148 |
Rust | -1.139 |
aila | -1.134 |
Pak | -1.126 |
bub | -1.118 |
Token | McD |
Token ID | 23394 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
enthal | +0.871 |
sted | +0.794 |
carbohyd | +0.771 |
deceive | +0.750 |
cius | +0.744 |
Neg logit contributions | |
Adidas | -0.735 |
Rust | -0.727 |
aila | -0.723 |
Pak | -0.717 |
bub | -0.714 |
Token | ermott |
Token ID | 46187 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
enthal | +5.646 |
sted | +4.927 |
ares | +4.907 |
eele | +4.767 |
cius | +4.654 |
Neg logit contributions | |
Adidas | -5.251 |
Rust | -5.186 |
Pak | -5.118 |
bub | -4.938 |
aila | -4.884 |
Token | , |
Token ID | 11 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
enthal | +0.471 |
sted | +0.429 |
carbohyd | +0.423 |
deceive | +0.408 |
cius | +0.405 |
Neg logit contributions | |
Adidas | -0.366 |
Rust | -0.362 |
aila | -0.361 |
Pak | -0.357 |
bub | -0.356 |
Token | their |
Token ID | 511 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
enthal | +0.222 |
sted | +0.202 |
carbohyd | +0.198 |
deceive | +0.191 |
cius | +0.189 |
Neg logit contributions | |
Adidas | -0.190 |
Rust | -0.188 |
aila | -0.188 |
Pak | -0.186 |
bub | -0.185 |
Token | kids |
Token ID | 3988 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
Adidas | +0.451 |
Rust | +0.447 |
aila | +0.445 |
Pak | +0.439 |
bub | +0.438 |
Neg logit contributions | |
enthal | -0.631 |
sted | -0.578 |
carbohyd | -0.569 |
deceive | -0.551 |
cius | -0.546 |
Token | , |
Token ID | 11 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
Adidas | +1.174 |
Rust | +1.157 |
aila | +1.155 |
Pak | +1.138 |
bub | +1.135 |
Neg logit contributions | |
enthal | -1.545 |
sted | -1.409 |
carbohyd | -1.398 |
deceive | -1.338 |
cius | -1.333 |
Token | on |
Token ID | 319 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
enthal | +1.062 |
sted | +0.972 |
carbohyd | +0.945 |
deceive | +0.919 |
ares | +0.912 |
Neg logit contributions | |
Adidas | -0.797 |
Rust | -0.797 |
aila | -0.791 |
Pak | -0.785 |
bub | -0.779 |
Token | marijuana |
Token ID | 5727 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
enthal | +1.163 |
sted | +1.060 |
carbohyd | +1.033 |
deceive | +1.000 |
cius | +0.993 |
Neg logit contributions | |
Rust | -0.993 |
Adidas | -0.991 |
aila | -0.986 |
Pak | -0.979 |
bub | -0.973 |
Token | dispensary |
Token ID | 50136 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
enthal | +0.807 |
sted | +0.705 |
carbohyd | +0.677 |
deceive | +0.652 |
ares | +0.647 |
Neg logit contributions | |
Adidas | -1.193 |
Rust | -1.192 |
aila | -1.185 |
Pak | -1.178 |
bub | -1.173 |
Token | Sky |
Token ID | 5274 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
enthal | +2.619 |
sted | +2.383 |
ares | +2.246 |
carbohyd | +2.239 |
deceive | +2.236 |
Neg logit contributions | |
aila | -2.483 |
Pak | -2.471 |
Rust | -2.468 |
Adidas | -2.459 |
bub | -2.413 |
Token | High |
Token ID | 3334 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
enthal | +1.617 |
sted | +1.487 |
carbohyd | +1.423 |
cius | +1.394 |
deceive | +1.394 |
Neg logit contributions | |
Adidas | -1.369 |
Rust | -1.337 |
aila | -1.334 |
bub | -1.302 |
Pak | -1.302 |
Token | Hol |
Token ID | 6479 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
enthal | +1.208 |
sted | +1.089 |
carbohyd | +1.047 |
deceive | +1.017 |
ares | +1.014 |
Neg logit contributions | |
Adidas | -1.150 |
Rust | -1.144 |
aila | -1.139 |
bub | -1.123 |
Pak | -1.120 |
Token | istic |
Token ID | 2569 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
enthal | +6.293 |
sted | +5.830 |
ares | +5.430 |
cius | +5.377 |
deceive | +5.293 |
Neg logit contributions | |
Adidas | -4.503 |
Rust | -4.486 |
aila | -4.365 |
XY | -4.309 |
bub | -4.236 |
Token | , |
Token ID | 11 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
enthal | +0.207 |
sted | +0.186 |
carbohyd | +0.184 |
deceive | +0.175 |
cius | +0.174 |
Neg logit contributions | |
Adidas | -0.218 |
Rust | -0.215 |
aila | -0.215 |
Pak | -0.213 |
bub | -0.212 |
Token | in |
Token ID | 287 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
enthal | +0.017 |
sted | +0.016 |
carbohyd | +0.016 |
deceive | +0.015 |
cius | +0.015 |
Neg logit contributions | |
Adidas | -0.013 |
Rust | -0.013 |
aila | -0.013 |
Pak | -0.013 |
bub | -0.013 |
Token | May |
Token ID | 1737 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Adidas | +0.217 |
Rust | +0.215 |
aila | +0.214 |
Pak | +0.211 |
bub | +0.211 |
Neg logit contributions | |
enthal | -0.325 |
sted | -0.298 |
carbohyd | -0.294 |
deceive | -0.284 |
cius | -0.282 |
Token | 2015 |
Token ID | 1853 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
Adidas | +0.810 |
Rust | +0.797 |
aila | +0.796 |
bub | +0.786 |
Pak | +0.786 |
Neg logit contributions | |
enthal | -1.035 |
sted | -0.942 |
carbohyd | -0.940 |
deceive | -0.898 |
cius | -0.894 |
Token | 2013 |
Token ID | 2211 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
enthal | +1.071 |
sted | +0.984 |
carbohyd | +0.965 |
deceive | +0.938 |
cius | +0.930 |
Neg logit contributions | |
Adidas | -0.691 |
Rust | -0.686 |
aila | -0.682 |
Pak | -0.672 |
bub | -0.670 |
Token | ), |
Token ID | 828 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
enthal | +0.655 |
sted | +0.574 |
carbohyd | +0.560 |
deceive | +0.533 |
cius | +0.523 |
Neg logit contributions | |
Adidas | -0.967 |
Rust | -0.964 |
aila | -0.960 |
Pak | -0.951 |
bub | -0.949 |
Token | Slovakia |
Token ID | 36839 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
enthal | +0.550 |
sted | +0.498 |
carbohyd | +0.489 |
deceive | +0.471 |
cius | +0.468 |
Neg logit contributions | |
Adidas | -0.494 |
Rust | -0.490 |
aila | -0.489 |
Pak | -0.483 |
bub | -0.483 |
Token | - |
Token ID | 12 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
enthal | +0.808 |
sted | +0.733 |
carbohyd | +0.715 |
deceive | +0.690 |
cius | +0.688 |
Neg logit contributions | |
Adidas | -0.732 |
Rust | -0.722 |
aila | -0.721 |
bub | -0.712 |
Pak | -0.710 |
Token | based |
Token ID | 3106 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
enthal | +0.643 |
sted | +0.578 |
carbohyd | +0.562 |
deceive | +0.541 |
cius | +0.537 |
Neg logit contributions | |
Adidas | -0.693 |
aila | -0.686 |
Rust | -0.682 |
bub | -0.674 |
Pak | -0.671 |
Token | SV |
Token ID | 20546 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
enthal | +3.178 |
sted | +2.911 |
carbohyd | +2.774 |
deceive | +2.728 |
Admission | +2.721 |
Neg logit contributions | |
Rust | -2.843 |
aila | -2.829 |
Adidas | -2.820 |
bub | -2.809 |
Pak | -2.789 |
Token | OP |
Token ID | 3185 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
enthal | +5.541 |
sted | +5.117 |
ares | +4.830 |
Admission | +4.773 |
carbohyd | +4.730 |
Neg logit contributions | |
Adidas | -4.879 |
aila | -4.813 |
bub | -4.807 |
Rust | -4.749 |
Pak | -4.739 |
Token | Ltd |
Token ID | 12052 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
enthal | +0.733 |
sted | +0.666 |
carbohyd | +0.651 |
deceive | +0.627 |
cius | +0.625 |
Neg logit contributions | |
Adidas | -0.608 |
Rust | -0.602 |
aila | -0.599 |
bub | -0.591 |
Pak | -0.591 |
Token | . |
Token ID | 13 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
Adidas | +0.153 |
Rust | +0.151 |
aila | +0.151 |
Pak | +0.150 |
bub | +0.149 |
Neg logit contributions | |
enthal | -0.130 |
sted | -0.116 |
carbohyd | -0.114 |
deceive | -0.109 |
cius | -0.108 |
Token | ( |
Token ID | 357 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
Adidas | +0.156 |
Rust | +0.154 |
aila | +0.154 |
Pak | +0.151 |
bub | +0.151 |
Neg logit contributions | |
enthal | -0.237 |
sted | -0.217 |
carbohyd | -0.215 |
deceive | -0.207 |
cius | -0.206 |
Token | October |
Token ID | 18517 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
enthal | +1.295 |
sted | +1.148 |
carbohyd | +1.078 |
deceive | +1.051 |
ares | +1.051 |
Neg logit contributions | |
Adidas | -1.736 |
aila | -1.716 |
Rust | -1.701 |
bub | -1.683 |
Pak | -1.678 |
Token | Walking |
Token ID | 21276 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
enthal | +0.254 |
sted | +0.230 |
carbohyd | +0.224 |
deceive | +0.216 |
cius | +0.215 |
Neg logit contributions | |
Adidas | -0.239 |
aila | -0.238 |
Rust | -0.237 |
Pak | -0.234 |
bub | -0.234 |
Token | Dead |
Token ID | 5542 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
enthal | +1.111 |
sted | +1.010 |
carbohyd | +0.970 |
ares | +0.960 |
Admission | +0.957 |
Neg logit contributions | |
aila | -0.816 |
Rust | -0.806 |
Adidas | -0.802 |
bub | -0.796 |
Pak | -0.787 |
Token | and |
Token ID | 290 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
enthal | +4.147 |
sted | +3.779 |
ares | +3.575 |
deceive | +3.572 |
carbohyd | +3.564 |
Neg logit contributions | |
aila | -3.500 |
Adidas | -3.489 |
Rust | -3.480 |
bub | -3.414 |
Pak | -3.397 |
Token | An |
Token ID | 1052 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
enthal | +0.784 |
sted | +0.707 |
carbohyd | +0.691 |
deceive | +0.666 |
cius | +0.661 |
Neg logit contributions | |
Adidas | -0.772 |
aila | -0.766 |
Rust | -0.766 |
Pak | -0.756 |
bub | -0.755 |
Token | American |
Token ID | 1605 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Adidas | +1.067 |
Rust | +1.054 |
aila | +1.050 |
Pak | +1.037 |
bub | +1.033 |
Neg logit contributions | |
enthal | -1.451 |
sted | -1.322 |
carbohyd | -1.310 |
deceive | -1.261 |
cius | -1.250 |
Token | Werewolf |
Token ID | 40261 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Rust | +0.342 |
Adidas | +0.342 |
aila | +0.341 |
Pak | +0.337 |
bub | +0.335 |
Neg logit contributions | |
enthal | -0.381 |
sted | -0.346 |
carbohyd | -0.331 |
deceive | -0.324 |
Admission | -0.322 |
Token | in |
Token ID | 287 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
enthal | +4.512 |
carbohyd | +4.039 |
sted | +4.007 |
Admission | +3.883 |
ares | +3.859 |
Neg logit contributions | |
bub | -6.025 |
Rust | -5.976 |
aila | -5.891 |
Adidas | -5.791 |
Pak | -5.773 |
Token | London |
Token ID | 3576 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
enthal | +1.781 |
sted | +1.646 |
deceive | +1.577 |
carbohyd | +1.575 |
Admission | +1.568 |
Neg logit contributions | |
bub | -1.130 |
aila | -1.118 |
Adidas | -1.088 |
Rust | -1.083 |
angelo | -1.069 |
Token | . |
Token ID | 13 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
Adidas | +1.554 |
aila | +1.523 |
Rust | +1.521 |
Pak | +1.511 |
bub | +1.507 |
Neg logit contributions | |
enthal | -1.777 |
carbohyd | -1.623 |
sted | -1.617 |
deceive | -1.533 |
cius | -1.527 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Adidas | +0.166 |
Rust | +0.164 |
aila | +0.163 |
Pak | +0.161 |
bub | +0.161 |
Neg logit contributions | |
enthal | -0.177 |
sted | -0.160 |
carbohyd | -0.160 |
deceive | -0.152 |
cius | -0.151 |
Token |
|
Token ID | 198 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
enthal | +0.324 |
sted | +0.294 |
carbohyd | +0.281 |
deceive | +0.275 |
cius | +0.273 |
Neg logit contributions | |
Adidas | -0.303 |
Rust | -0.300 |
aila | -0.300 |
bub | -0.295 |
Pak | -0.295 |
Token | get |
Token ID | 651 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
Adidas | +2.728 |
aila | +2.694 |
Pak | +2.645 |
Rust | +2.643 |
bub | +2.642 |
Neg logit contributions | |
enthal | -2.956 |
carbohyd | -2.766 |
sted | -2.659 |
ares | -2.490 |
cius | -2.483 |
Token | your |
Token ID | 534 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Adidas | +1.478 |
Rust | +1.454 |
aila | +1.450 |
Pak | +1.434 |
bub | +1.426 |
Neg logit contributions | |
enthal | -1.778 |
sted | -1.605 |
carbohyd | -1.603 |
cius | -1.524 |
deceive | -1.524 |
Token | love |
Token ID | 1842 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Adidas | +1.070 |
Rust | +1.057 |
aila | +1.054 |
Pak | +1.041 |
bub | +1.038 |
Neg logit contributions | |
enthal | -1.339 |
sted | -1.218 |
carbohyd | -1.204 |
deceive | -1.158 |
cius | -1.150 |
Token | for |
Token ID | 329 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
Adidas | +0.412 |
Rust | +0.411 |
aila | +0.406 |
Pak | +0.401 |
bub | +0.400 |
Neg logit contributions | |
enthal | -0.641 |
sted | -0.587 |
carbohyd | -0.575 |
deceive | -0.559 |
cius | -0.556 |
Token | Star |
Token ID | 2907 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
Adidas | +0.906 |
Rust | +0.886 |
aila | +0.881 |
bub | +0.875 |
Pak | +0.872 |
Neg logit contributions | |
enthal | -0.937 |
carbohyd | -0.845 |
sted | -0.836 |
cius | -0.794 |
deceive | -0.791 |
Token | Wars |
Token ID | 6176 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
enthal | +1.357 |
sted | +1.190 |
carbohyd | +1.120 |
deceive | +1.087 |
cius | +1.080 |
Neg logit contributions | |
Adidas | -2.276 |
aila | -2.262 |
Rust | -2.261 |
Pak | -2.232 |
bub | -2.222 |
Token | ? |
Token ID | 30 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
enthal | +5.173 |
sted | +4.673 |
deceive | +4.611 |
underest | +4.443 |
Swanson | +4.422 |
Neg logit contributions | |
Rust | -4.938 |
aila | -4.840 |
Adidas | -4.835 |
bub | -4.771 |
Pak | -4.755 |
Token |
|
Token ID | 198 |
Feature activation | -4.83e-03 |
Pos logit contributions | |
Adidas | +0.804 |
Rust | +0.789 |
aila | +0.784 |
Pak | +0.781 |
bub | +0.776 |
Neg logit contributions | |
enthal | -0.921 |
carbohyd | -0.846 |
sted | -0.833 |
deceive | -0.796 |
cius | -0.788 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
enthal | +0.012 |
sted | +0.011 |
carbohyd | +0.011 |
deceive | +0.010 |
cius | +0.010 |
Neg logit contributions | |
Adidas | -0.011 |
Rust | -0.011 |
aila | -0.011 |
Pak | -0.011 |
bub | -0.011 |
Token | No |
Token ID | 2949 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Adidas | +0.255 |
aila | +0.253 |
Rust | +0.250 |
bub | +0.247 |
Pak | +0.246 |
Neg logit contributions | |
enthal | -0.278 |
sted | -0.252 |
carbohyd | -0.241 |
deceive | -0.235 |
cius | -0.235 |
Token | . |
Token ID | 13 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
enthal | +0.504 |
sted | +0.454 |
carbohyd | +0.447 |
deceive | +0.432 |
cius | +0.426 |
Neg logit contributions | |
Adidas | -0.460 |
Rust | -0.458 |
aila | -0.457 |
Pak | -0.452 |
bub | -0.450 |
Token | but |
Token ID | 475 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Adidas | +0.247 |
Rust | +0.242 |
aila | +0.241 |
bub | +0.238 |
Pak | +0.238 |
Neg logit contributions | |
enthal | -0.349 |
sted | -0.320 |
carbohyd | -0.318 |
deceive | -0.303 |
cius | -0.303 |
Token | were |
Token ID | 547 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
Adidas | +0.275 |
Rust | +0.268 |
aila | +0.267 |
bub | +0.264 |
Pak | +0.264 |
Neg logit contributions | |
enthal | -0.320 |
carbohyd | -0.291 |
sted | -0.291 |
cius | -0.274 |
deceive | -0.274 |
Token | you |
Token ID | 345 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
enthal | +0.150 |
sted | +0.134 |
carbohyd | +0.132 |
deceive | +0.126 |
cius | +0.125 |
Neg logit contributions | |
Adidas | -0.164 |
Rust | -0.162 |
aila | -0.162 |
Pak | -0.160 |
bub | -0.160 |
Token | a |
Token ID | 257 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
enthal | +0.109 |
sted | +0.098 |
carbohyd | +0.096 |
deceive | +0.092 |
cius | +0.091 |
Neg logit contributions | |
Adidas | -0.117 |
Rust | -0.116 |
aila | -0.115 |
Pak | -0.114 |
bub | -0.114 |
Token | Star |
Token ID | 2907 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
enthal | +0.479 |
sted | +0.434 |
carbohyd | +0.426 |
deceive | +0.411 |
cius | +0.408 |
Neg logit contributions | |
Adidas | -0.430 |
Rust | -0.427 |
aila | -0.425 |
Pak | -0.420 |
bub | -0.419 |
Token | Wars |
Token ID | 6176 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
enthal | +1.172 |
sted | +1.024 |
carbohyd | +0.978 |
deceive | +0.939 |
cius | +0.933 |
Neg logit contributions | |
Adidas | -1.883 |
Rust | -1.871 |
aila | -1.867 |
Pak | -1.847 |
bub | -1.841 |
Token | fan |
Token ID | 4336 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
enthal | +5.338 |
sted | +4.839 |
deceive | +4.649 |
contingency | +4.572 |
ares | +4.548 |
Neg logit contributions | |
Rust | -4.859 |
aila | -4.779 |
Adidas | -4.723 |
Pak | -4.651 |
bub | -4.624 |
Token | as |
Token ID | 355 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Adidas | +2.568 |
aila | +2.516 |
Rust | +2.509 |
bub | +2.492 |
Pak | +2.474 |
Neg logit contributions | |
enthal | -3.260 |
carbohyd | -2.969 |
sted | -2.940 |
deceive | -2.808 |
cius | -2.794 |
Token | a |
Token ID | 257 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
enthal | +0.386 |
sted | +0.352 |
carbohyd | +0.346 |
deceive | +0.334 |
cius | +0.331 |
Neg logit contributions | |
Adidas | -0.312 |
Rust | -0.310 |
aila | -0.308 |
Pak | -0.305 |
bub | -0.304 |
Token | kid |
Token ID | 5141 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
enthal | +0.589 |
sted | +0.541 |
carbohyd | +0.528 |
deceive | +0.515 |
cius | +0.509 |
Neg logit contributions | |
Adidas | -0.419 |
Rust | -0.418 |
aila | -0.413 |
Pak | -0.409 |
bub | -0.407 |
Token | ? |
Token ID | 30 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Adidas | +0.770 |
Rust | +0.763 |
aila | +0.761 |
Pak | +0.751 |
bub | +0.749 |
Neg logit contributions | |
enthal | -0.921 |
sted | -0.837 |
carbohyd | -0.823 |
deceive | -0.793 |
cius | -0.787 |
Token | at |
Token ID | 379 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
enthal | +0.239 |
sted | +0.217 |
carbohyd | +0.214 |
deceive | +0.206 |
cius | +0.205 |
Neg logit contributions | |
Adidas | -0.194 |
Rust | -0.192 |
aila | -0.192 |
Pak | -0.189 |
bub | -0.189 |
Token | Rs |
Token ID | 12820 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Adidas | +0.793 |
aila | +0.770 |
Rust | +0.769 |
Pak | +0.766 |
bub | +0.756 |
Neg logit contributions | |
enthal | -1.480 |
sted | -1.367 |
carbohyd | -1.361 |
deceive | -1.305 |
cius | -1.303 |
Token | 31 |
Token ID | 3261 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
enthal | +1.016 |
sted | +0.931 |
carbohyd | +0.907 |
deceive | +0.885 |
cius | +0.878 |
Neg logit contributions | |
Adidas | -0.740 |
Rust | -0.735 |
aila | -0.734 |
bub | -0.723 |
Pak | -0.721 |
Token | . |
Token ID | 13 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
Adidas | +0.945 |
aila | +0.933 |
Rust | +0.927 |
Pak | +0.924 |
bub | +0.921 |
Neg logit contributions | |
enthal | -0.867 |
sted | -0.772 |
carbohyd | -0.770 |
deceive | -0.728 |
cius | -0.725 |
Token | 20 |
Token ID | 1238 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
enthal | +0.240 |
sted | +0.220 |
carbohyd | +0.215 |
deceive | +0.209 |
cius | +0.208 |
Neg logit contributions | |
Adidas | -0.165 |
Rust | -0.163 |
aila | -0.163 |
bub | -0.160 |
Pak | -0.160 |
Token | cro |
Token ID | 6763 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
enthal | +0.592 |
sted | +0.502 |
carbohyd | +0.486 |
deceive | +0.454 |
cius | +0.448 |
Neg logit contributions | |
Adidas | -1.232 |
Rust | -1.225 |
aila | -1.221 |
Pak | -1.210 |
bub | -1.209 |
Token | res |
Token ID | 411 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
enthal | +4.920 |
sted | +4.531 |
ares | +4.336 |
deceive | +4.235 |
cius | +4.226 |
Neg logit contributions | |
Rust | -5.193 |
Adidas | -5.131 |
bub | -5.126 |
aila | -5.098 |
Pak | -5.048 |
Token | as |
Token ID | 355 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
enthal | +0.968 |
sted | +0.879 |
carbohyd | +0.858 |
deceive | +0.831 |
cius | +0.827 |
Neg logit contributions | |
Adidas | -0.797 |
Rust | -0.793 |
aila | -0.787 |
Pak | -0.778 |
bub | -0.777 |
Token | opposed |
Token ID | 6886 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Adidas | +0.972 |
aila | +0.955 |
Rust | +0.949 |
Pak | +0.939 |
bub | +0.939 |
Neg logit contributions | |
enthal | -1.106 |
sted | -0.997 |
carbohyd | -0.992 |
deceive | -0.942 |
cius | -0.939 |
Token | to |
Token ID | 284 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
enthal | +0.579 |
sted | +0.529 |
carbohyd | +0.504 |
deceive | +0.497 |
ares | +0.496 |
Neg logit contributions | |
Adidas | -0.481 |
Rust | -0.479 |
aila | -0.474 |
bub | -0.474 |
Pak | -0.469 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
Adidas | +0.509 |
aila | +0.497 |
Rust | +0.495 |
Pak | +0.487 |
bub | +0.482 |
Neg logit contributions | |
enthal | -1.035 |
sted | -0.956 |
carbohyd | -0.951 |
deceive | -0.917 |
cius | -0.913 |
Token | a |
Token ID | 257 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Adidas | +0.700 |
Rust | +0.694 |
aila | +0.692 |
Pak | +0.683 |
bub | +0.682 |
Neg logit contributions | |
enthal | -0.828 |
sted | -0.751 |
carbohyd | -0.740 |
deceive | -0.712 |
cius | -0.707 |
Token | selfie |
Token ID | 38704 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
Adidas | +0.486 |
Rust | +0.482 |
aila | +0.481 |
Pak | +0.476 |
bub | +0.475 |
Neg logit contributions | |
enthal | -0.488 |
sted | -0.439 |
carbohyd | -0.431 |
deceive | -0.414 |
cius | -0.410 |
Token | with |
Token ID | 351 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Adidas | +1.047 |
Rust | +1.030 |
aila | +1.029 |
Pak | +1.014 |
bub | +1.013 |
Neg logit contributions | |
enthal | -1.296 |
sted | -1.175 |
carbohyd | -1.168 |
deceive | -1.116 |
cius | -1.111 |
Token | Joe |
Token ID | 5689 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
Adidas | +1.020 |
Rust | +1.000 |
aila | +0.997 |
Pak | +0.987 |
bub | +0.983 |
Neg logit contributions | |
enthal | -1.248 |
sted | -1.134 |
carbohyd | -1.128 |
deceive | -1.073 |
cius | -1.069 |
Token | K |
Token ID | 509 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Adidas | +1.646 |
Rust | +1.604 |
aila | +1.603 |
Pak | +1.586 |
bub | +1.573 |
Neg logit contributions | |
enthal | -2.694 |
carbohyd | -2.483 |
sted | -2.478 |
deceive | -2.375 |
cius | -2.366 |
Token | ober |
Token ID | 2023 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Adidas | +0.998 |
Rust | +0.988 |
Pak | +0.971 |
aila | +0.969 |
bub | +0.966 |
Neg logit contributions | |
enthal | -1.187 |
sted | -1.069 |
carbohyd | -1.044 |
ares | -1.019 |
deceive | -1.006 |
Token | na |
Token ID | 2616 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
enthal | +5.498 |
sted | +5.054 |
carbohyd | +4.639 |
ares | +4.633 |
cius | +4.627 |
Neg logit contributions | |
Rust | -4.859 |
Adidas | -4.716 |
aila | -4.697 |
Pak | -4.650 |
XY | -4.581 |
Token | at |
Token ID | 379 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
Adidas | +1.143 |
aila | +1.135 |
Rust | +1.124 |
bub | +1.118 |
Pak | +1.113 |
Neg logit contributions | |
enthal | -1.498 |
carbohyd | -1.381 |
sted | -1.362 |
deceive | -1.316 |
cius | -1.292 |
Token | the |
Token ID | 262 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Adidas | +0.111 |
Rust | +0.110 |
aila | +0.110 |
Pak | +0.108 |
bub | +0.108 |
Neg logit contributions | |
enthal | -0.125 |
sted | -0.113 |
carbohyd | -0.111 |
deceive | -0.107 |
cius | -0.106 |
Token | Johnson |
Token ID | 5030 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
enthal | +0.505 |
sted | +0.459 |
carbohyd | +0.451 |
deceive | +0.436 |
cius | +0.433 |
Neg logit contributions | |
Adidas | -0.412 |
Rust | -0.410 |
aila | -0.408 |
Pak | -0.404 |
bub | -0.403 |
Token | County |
Token ID | 3418 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Adidas | +1.260 |
Rust | +1.242 |
aila | +1.239 |
Pak | +1.228 |
bub | +1.224 |
Neg logit contributions | |
enthal | -1.332 |
sted | -1.201 |
carbohyd | -1.192 |
deceive | -1.138 |
cius | -1.129 |
Token | growing |
Token ID | 3957 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
Adidas | +0.016 |
Rust | +0.016 |
aila | +0.016 |
Pak | +0.015 |
bub | +0.015 |
Neg logit contributions | |
enthal | -0.016 |
sted | -0.015 |
carbohyd | -0.015 |
deceive | -0.014 |
cius | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
enthal | +1.128 |
sted | +1.010 |
carbohyd | +0.983 |
deceive | +0.951 |
cius | +0.948 |
Neg logit contributions | |
Adidas | -1.185 |
Rust | -1.182 |
aila | -1.177 |
Pak | -1.167 |
bub | -1.162 |
Token | important |
Token ID | 1593 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
enthal | +0.556 |
sted | +0.506 |
carbohyd | +0.493 |
deceive | +0.480 |
cius | +0.479 |
Neg logit contributions | |
Adidas | -0.460 |
Rust | -0.458 |
aila | -0.456 |
Pak | -0.449 |
bub | -0.449 |
Token | trend |
Token ID | 5182 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
enthal | +0.007 |
sted | +0.006 |
carbohyd | +0.006 |
deceive | +0.006 |
cius | +0.006 |
Neg logit contributions | |
Adidas | -0.007 |
Rust | -0.007 |
aila | -0.007 |
Pak | -0.006 |
bub | -0.006 |
Token | : |
Token ID | 25 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
enthal | +1.953 |
sted | +1.753 |
carbohyd | +1.696 |
cius | +1.649 |
deceive | +1.640 |
Neg logit contributions | |
Adidas | -1.935 |
Rust | -1.924 |
aila | -1.904 |
Pak | -1.890 |
bub | -1.872 |
Token | blended |
Token ID | 32063 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
enthal | +0.445 |
sted | +0.403 |
carbohyd | +0.397 |
deceive | +0.382 |
cius | +0.379 |
Neg logit contributions | |
Adidas | -0.392 |
Rust | -0.387 |
aila | -0.386 |
Pak | -0.382 |
bub | -0.381 |
Token | roles |
Token ID | 9176 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
enthal | +4.968 |
sted | +4.495 |
deceive | +4.281 |
carbohyd | +4.269 |
ares | +4.216 |
Neg logit contributions | |
Rust | -5.171 |
bub | -5.094 |
Adidas | -5.092 |
Pak | -5.012 |
aila | -5.002 |
Token | that |
Token ID | 326 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
enthal | +0.672 |
sted | +0.609 |
carbohyd | +0.602 |
deceive | +0.578 |
cius | +0.573 |
Neg logit contributions | |
Adidas | -0.573 |
Rust | -0.566 |
aila | -0.565 |
Pak | -0.559 |
bub | -0.558 |
Token | require |
Token ID | 2421 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
enthal | +0.145 |
sted | +0.131 |
carbohyd | +0.130 |
deceive | +0.124 |
cius | +0.124 |
Neg logit contributions | |
Adidas | -0.130 |
Rust | -0.129 |
aila | -0.129 |
Pak | -0.127 |
bub | -0.127 |
Token | compet |
Token ID | 2307 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
enthal | +0.133 |
sted | +0.120 |
carbohyd | +0.118 |
deceive | +0.113 |
cius | +0.113 |
Neg logit contributions | |
Adidas | -0.120 |
Rust | -0.119 |
aila | -0.119 |
Pak | -0.118 |
bub | -0.118 |
Token | ency |
Token ID | 1387 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
enthal | +1.108 |
sted | +1.008 |
carbohyd | +0.985 |
cius | +0.950 |
deceive | +0.948 |
Neg logit contributions | |
Adidas | -0.915 |
Rust | -0.907 |
aila | -0.894 |
Pak | -0.886 |
bub | -0.885 |
Token | in |
Token ID | 287 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
enthal | +1.011 |
sted | +0.919 |
carbohyd | +0.900 |
deceive | +0.870 |
cius | +0.860 |
Neg logit contributions | |
Adidas | -0.903 |
Rust | -0.896 |
aila | -0.895 |
Pak | -0.884 |
bub | -0.882 |
Token | the |
Token ID | 262 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
Adidas | +0.806 |
Rust | +0.790 |
aila | +0.788 |
Pak | +0.779 |
bub | +0.777 |
Neg logit contributions | |
enthal | -0.885 |
sted | -0.797 |
carbohyd | -0.792 |
deceive | -0.755 |
cius | -0.753 |
Token | summer |
Token ID | 3931 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
Adidas | +0.683 |
Rust | +0.673 |
aila | +0.671 |
Pak | +0.663 |
bub | +0.663 |
Neg logit contributions | |
enthal | -0.765 |
sted | -0.691 |
carbohyd | -0.684 |
deceive | -0.655 |
cius | -0.651 |
Token | blockbuster |
Token ID | 32034 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Adidas | +1.478 |
Rust | +1.453 |
aila | +1.451 |
bub | +1.438 |
Pak | +1.436 |
Neg logit contributions | |
enthal | -1.471 |
sted | -1.323 |
carbohyd | -1.312 |
deceive | -1.250 |
cius | -1.248 |
Token | Pacific |
Token ID | 8211 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
enthal | +0.353 |
sted | +0.319 |
carbohyd | +0.314 |
deceive | +0.302 |
cius | +0.299 |
Neg logit contributions | |
Adidas | -0.325 |
Rust | -0.322 |
aila | -0.321 |
Pak | -0.317 |
bub | -0.317 |
Token | Rim |
Token ID | 29542 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
enthal | +2.960 |
sted | +2.720 |
carbohyd | +2.644 |
deceive | +2.616 |
ares | +2.594 |
Neg logit contributions | |
Adidas | -1.575 |
aila | -1.556 |
Rust | -1.542 |
bub | -1.538 |
Pak | -1.502 |
Token | . |
Token ID | 13 |
Feature activation | +9.55e-02 |
Pos logit contributions | |
enthal | +4.948 |
sted | +4.528 |
Admission | +4.241 |
deceive | +4.195 |
eele | +4.168 |
Neg logit contributions | |
aila | -4.970 |
Rust | -4.933 |
Adidas | -4.899 |
Pak | -4.857 |
bub | -4.857 |
Token | He |
Token ID | 679 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
Adidas | +0.233 |
Rust | +0.229 |
aila | +0.228 |
Pak | +0.227 |
bub | +0.225 |
Neg logit contributions | |
enthal | -0.224 |
carbohyd | -0.202 |
sted | -0.201 |
deceive | -0.191 |
cius | -0.189 |
Token | � |
Token ID | 447 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Adidas | +0.182 |
Rust | +0.180 |
aila | +0.179 |
Pak | +0.177 |
bub | +0.177 |
Neg logit contributions | |
enthal | -0.213 |
sted | -0.193 |
carbohyd | -0.189 |
deceive | -0.183 |
cius | -0.181 |
Token | � |
Token ID | 247 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
Adidas | +0.355 |
Rust | +0.352 |
aila | +0.350 |
Pak | +0.346 |
bub | +0.344 |
Neg logit contributions | |
enthal | -0.432 |
sted | -0.391 |
carbohyd | -0.389 |
deceive | -0.372 |
cius | -0.370 |
Token | s |
Token ID | 82 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Adidas | +0.188 |
Rust | +0.186 |
aila | +0.186 |
Pak | +0.183 |
bub | +0.183 |
Neg logit contributions | |
enthal | -0.250 |
sted | -0.228 |
carbohyd | -0.226 |
deceive | -0.217 |
cius | -0.216 |
Token | of |
Token ID | 286 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
Adidas | +0.079 |
aila | +0.078 |
Rust | +0.077 |
Pak | +0.076 |
bub | +0.076 |
Neg logit contributions | |
enthal | -0.083 |
sted | -0.075 |
carbohyd | -0.074 |
deceive | -0.071 |
cius | -0.070 |
Token | the |
Token ID | 262 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
Adidas | +1.686 |
aila | +1.642 |
Rust | +1.624 |
bub | +1.613 |
Pak | +1.594 |
Neg logit contributions | |
enthal | -2.295 |
carbohyd | -2.111 |
sted | -2.090 |
cius | -2.002 |
deceive | -1.994 |
Token | routine |
Token ID | 8027 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
Adidas | +1.610 |
aila | +1.574 |
Rust | +1.570 |
bub | +1.554 |
Pak | +1.548 |
Neg logit contributions | |
enthal | -1.703 |
carbohyd | -1.541 |
sted | -1.536 |
cius | -1.448 |
deceive | -1.444 |
Token | that |
Token ID | 326 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Adidas | +1.392 |
aila | +1.364 |
Rust | +1.357 |
bub | +1.346 |
Pak | +1.343 |
Neg logit contributions | |
enthal | -1.534 |
carbohyd | -1.381 |
sted | -1.377 |
cius | -1.303 |
deceive | -1.296 |
Token | helped |
Token ID | 4193 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Adidas | +0.692 |
Rust | +0.676 |
aila | +0.670 |
bub | +0.666 |
Pak | +0.664 |
Neg logit contributions | |
enthal | -0.798 |
sted | -0.722 |
carbohyd | -0.718 |
deceive | -0.681 |
cius | -0.678 |
Token | LC |
Token ID | 22228 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Adidas | +0.268 |
Rust | +0.264 |
aila | +0.263 |
Pak | +0.260 |
bub | +0.260 |
Neg logit contributions | |
enthal | -0.281 |
sted | -0.253 |
carbohyd | -0.251 |
cius | -0.237 |
deceive | -0.237 |
Token | get |
Token ID | 651 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
enthal | +4.176 |
sted | +3.777 |
deceive | +3.720 |
carbohyd | +3.689 |
eele | +3.570 |
Neg logit contributions | |
Adidas | -5.554 |
aila | -5.529 |
Rust | -5.476 |
bub | -5.436 |
Pak | -5.297 |
Token | some |
Token ID | 617 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Adidas | +1.748 |
Rust | +1.710 |
aila | +1.701 |
bub | +1.684 |
Pak | +1.674 |
Neg logit contributions | |
enthal | -2.176 |
carbohyd | -1.981 |
sted | -1.976 |
cius | -1.884 |
deceive | -1.873 |
Token | of |
Token ID | 286 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
Adidas | +0.454 |
Rust | +0.448 |
aila | +0.447 |
bub | +0.441 |
Pak | +0.441 |
Neg logit contributions | |
enthal | -0.479 |
sted | -0.432 |
carbohyd | -0.427 |
deceive | -0.407 |
cius | -0.406 |
Token | their |
Token ID | 511 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
Adidas | +1.717 |
Rust | +1.662 |
aila | +1.655 |
bub | +1.647 |
Pak | +1.633 |
Neg logit contributions | |
enthal | -2.036 |
carbohyd | -1.851 |
sted | -1.839 |
cius | -1.772 |
deceive | -1.765 |
Token | wins |
Token ID | 7864 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Adidas | +1.991 |
Rust | +1.934 |
aila | +1.922 |
bub | +1.908 |
Pak | +1.893 |
Neg logit contributions | |
enthal | -2.459 |
carbohyd | -2.255 |
sted | -2.242 |
cius | -2.130 |
deceive | -2.122 |
Token | that |
Token ID | 326 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
enthal | +0.598 |
sted | +0.542 |
carbohyd | +0.528 |
deceive | +0.514 |
cius | +0.510 |
Neg logit contributions | |
Adidas | -0.552 |
Rust | -0.550 |
aila | -0.548 |
Pak | -0.545 |
bub | -0.540 |
Token | numbers |
Token ID | 3146 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
enthal | +0.312 |
sted | +0.282 |
carbohyd | +0.275 |
deceive | +0.266 |
cius | +0.265 |
Neg logit contributions | |
Adidas | -0.302 |
Rust | -0.301 |
aila | -0.301 |
Pak | -0.297 |
bub | -0.296 |
Token | follow |
Token ID | 1061 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
enthal | +1.461 |
sted | +1.322 |
carbohyd | +1.275 |
deceive | +1.261 |
cius | +1.246 |
Neg logit contributions | |
Rust | -1.355 |
aila | -1.351 |
Adidas | -1.348 |
Pak | -1.331 |
bub | -1.328 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
enthal | +0.419 |
sted | +0.380 |
carbohyd | +0.371 |
deceive | +0.359 |
cius | +0.357 |
Neg logit contributions | |
Adidas | -0.380 |
aila | -0.379 |
Rust | -0.379 |
Pak | -0.374 |
bub | -0.372 |
Token | 15 |
Token ID | 1314 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
Rust | +2.085 |
Adidas | +2.082 |
Pak | +2.039 |
bub | +2.037 |
aila | +2.034 |
Neg logit contributions | |
enthal | -3.627 |
carbohyd | -3.392 |
sted | -3.320 |
deceive | -3.216 |
cius | -3.179 |
Token | ][ |
Token ID | 7131 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Adidas | +1.072 |
Rust | +1.058 |
Pak | +1.054 |
aila | +1.052 |
bub | +1.047 |
Neg logit contributions | |
enthal | -1.193 |
sted | -1.074 |
carbohyd | -1.071 |
cius | -1.024 |
deceive | -1.020 |
Token | 16 |
Token ID | 1433 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
Rust | +2.536 |
Adidas | +2.505 |
bub | +2.474 |
Pak | +2.467 |
aila | +2.466 |
Neg logit contributions | |
enthal | -3.732 |
carbohyd | -3.523 |
sted | -3.438 |
deceive | -3.285 |
Dise | -3.252 |
Token | ] |
Token ID | 60 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Adidas | +0.996 |
Rust | +0.984 |
aila | +0.979 |
Pak | +0.978 |
bub | +0.971 |
Neg logit contributions | |
enthal | -1.020 |
sted | -0.917 |
carbohyd | -0.913 |
cius | -0.871 |
deceive | -0.868 |
Token |
|
Token ID | 198 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Adidas | +0.345 |
Rust | +0.343 |
aila | +0.343 |
Pak | +0.338 |
bub | +0.338 |
Neg logit contributions | |
enthal | -0.344 |
sted | -0.310 |
carbohyd | -0.301 |
deceive | -0.291 |
cius | -0.289 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Adidas | +0.443 |
Rust | +0.438 |
aila | +0.436 |
Pak | +0.432 |
bub | +0.430 |
Neg logit contributions | |
enthal | -0.503 |
carbohyd | -0.458 |
sted | -0.455 |
deceive | -0.433 |
cius | -0.430 |
Token | Comm |
Token ID | 6935 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
Adidas | +0.321 |
aila | +0.317 |
Rust | +0.314 |
bub | +0.309 |
Pak | +0.309 |
Neg logit contributions | |
enthal | -0.395 |
sted | -0.360 |
carbohyd | -0.347 |
deceive | -0.339 |
cius | -0.338 |
Token | t |
Token ID | 83 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
enthal | +1.230 |
sted | +1.130 |
carbohyd | +1.069 |
cius | +1.060 |
ares | +1.060 |
Neg logit contributions | |
Adidas | -0.856 |
Rust | -0.839 |
aila | -0.832 |
Pak | -0.822 |
bub | -0.810 |
Token | . |
Token ID | 13 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
enthal | +0.350 |
sted | +0.315 |
carbohyd | +0.301 |
deceive | +0.294 |
ares | +0.292 |
Neg logit contributions | |
Adidas | -0.359 |
Rust | -0.356 |
aila | -0.354 |
Pak | -0.351 |
bub | -0.350 |
Token | co |
Token ID | 1073 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Adidas | +0.518 |
Rust | +0.509 |
aila | +0.506 |
Pak | +0.500 |
bub | +0.499 |
Neg logit contributions | |
enthal | -1.537 |
carbohyd | -1.457 |
sted | -1.428 |
deceive | -1.391 |
cius | -1.375 |
Token | / |
Token ID | 14 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
Adidas | +0.621 |
Rust | +0.614 |
aila | +0.611 |
Pak | +0.607 |
bub | +0.603 |
Neg logit contributions | |
enthal | -0.628 |
carbohyd | -0.581 |
sted | -0.562 |
deceive | -0.539 |
cius | -0.533 |
Token | P |
Token ID | 47 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Adidas | +1.757 |
Rust | +1.753 |
aila | +1.742 |
Pak | +1.726 |
bub | +1.724 |
Neg logit contributions | |
enthal | -2.449 |
carbohyd | -2.245 |
sted | -2.236 |
deceive | -2.149 |
cius | -2.112 |
Token | 9 |
Token ID | 24 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
enthal | +0.361 |
sted | +0.331 |
carbohyd | +0.319 |
cius | +0.314 |
ares | +0.313 |
Neg logit contributions | |
Adidas | -0.243 |
Rust | -0.237 |
aila | -0.236 |
Pak | -0.232 |
bub | -0.231 |
Token | gc |
Token ID | 36484 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
Rust | +2.626 |
Adidas | +2.611 |
aila | +2.610 |
Pak | +2.590 |
bub | +2.582 |
Neg logit contributions | |
enthal | -3.545 |
carbohyd | -3.291 |
sted | -3.226 |
deceive | -3.123 |
Dise | -3.057 |
Token | N |
Token ID | 45 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
Adidas | +1.420 |
Rust | +1.411 |
aila | +1.405 |
Pak | +1.390 |
bub | +1.386 |
Neg logit contributions | |
enthal | -1.952 |
sted | -1.781 |
carbohyd | -1.776 |
deceive | -1.704 |
cius | -1.684 |
Token | PA |
Token ID | 4537 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
Adidas | +1.599 |
Rust | +1.583 |
aila | +1.580 |
Pak | +1.559 |
bub | +1.558 |
Neg logit contributions | |
enthal | -2.380 |
sted | -2.177 |
carbohyd | -2.171 |
deceive | -2.087 |
cius | -2.065 |
Token | um |
Token ID | 388 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
Adidas | +1.457 |
Rust | +1.442 |
aila | +1.438 |
Pak | +1.420 |
bub | +1.417 |
Neg logit contributions | |
enthal | -2.166 |
sted | -1.983 |
carbohyd | -1.971 |
deceive | -1.897 |
cius | -1.880 |
Token | H |
Token ID | 39 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Adidas | +1.412 |
Rust | +1.400 |
aila | +1.395 |
Pak | +1.379 |
bub | +1.376 |
Neg logit contributions | |
enthal | -1.948 |
sted | -1.778 |
carbohyd | -1.770 |
deceive | -1.700 |
cius | -1.681 |
Token | players |
Token ID | 1938 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
Adidas | +0.952 |
Rust | +0.939 |
aila | +0.938 |
Pak | +0.925 |
bub | +0.924 |
Neg logit contributions | |
enthal | -1.048 |
sted | -0.946 |
carbohyd | -0.935 |
deceive | -0.895 |
cius | -0.891 |
Token | with |
Token ID | 351 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
Adidas | +1.737 |
aila | +1.706 |
Rust | +1.701 |
Pak | +1.672 |
bub | +1.665 |
Neg logit contributions | |
enthal | -2.051 |
carbohyd | -1.847 |
sted | -1.847 |
deceive | -1.757 |
cius | -1.754 |
Token | 33 |
Token ID | 4747 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
Adidas | +1.366 |
aila | +1.337 |
Rust | +1.333 |
bub | +1.311 |
Pak | +1.309 |
Neg logit contributions | |
enthal | -1.887 |
sted | -1.721 |
carbohyd | -1.711 |
deceive | -1.636 |
cius | -1.626 |
Token | . |
Token ID | 13 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
Adidas | +1.011 |
Rust | +0.998 |
aila | +0.998 |
Pak | +0.985 |
bub | +0.983 |
Neg logit contributions | |
enthal | -1.173 |
sted | -1.065 |
carbohyd | -1.051 |
deceive | -1.009 |
cius | -1.002 |
Token | 5 |
Token ID | 20 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Adidas | +0.693 |
Rust | +0.685 |
aila | +0.683 |
bub | +0.672 |
Pak | +0.671 |
Neg logit contributions | |
enthal | -1.177 |
sted | -1.083 |
carbohyd | -1.061 |
deceive | -1.034 |
cius | -1.025 |
Token | pass |
Token ID | 1208 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
enthal | +0.378 |
sted | +0.344 |
carbohyd | +0.340 |
deceive | +0.329 |
ares | +0.327 |
Neg logit contributions | |
Adidas | -0.268 |
Rust | -0.267 |
aila | -0.264 |
bub | -0.261 |
Pak | -0.260 |
Token | pressures |
Token ID | 18895 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Adidas | +2.659 |
aila | +2.613 |
Pak | +2.594 |
Rust | +2.570 |
bub | +2.566 |
Neg logit contributions | |
enthal | -4.480 |
sted | -4.124 |
carbohyd | -4.075 |
cius | -3.937 |
deceive | -3.909 |
Token | , |
Token ID | 11 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Adidas | +2.431 |
aila | +2.396 |
Rust | +2.376 |
Pak | +2.350 |
bub | +2.347 |
Neg logit contributions | |
enthal | -3.046 |
carbohyd | -2.773 |
sted | -2.769 |
deceive | -2.648 |
cius | -2.636 |
Token | per |
Token ID | 583 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
Adidas | +0.323 |
Rust | +0.320 |
aila | +0.319 |
Pak | +0.315 |
bub | +0.315 |
Neg logit contributions | |
enthal | -0.364 |
sted | -0.330 |
carbohyd | -0.325 |
deceive | -0.312 |
cius | -0.310 |
Token | Football |
Token ID | 9957 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
enthal | +0.843 |
sted | +0.767 |
carbohyd | +0.747 |
deceive | +0.728 |
Admission | +0.719 |
Neg logit contributions | |
Rust | -0.716 |
Adidas | -0.707 |
aila | -0.706 |
bub | -0.705 |
Pak | -0.704 |
Token | Outs |
Token ID | 46580 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Adidas | +2.677 |
Rust | +2.636 |
Pak | +2.632 |
aila | +2.627 |
bub | +2.568 |
Neg logit contributions | |
enthal | -3.975 |
carbohyd | -3.650 |
sted | -3.620 |
deceive | -3.475 |
cius | -3.459 |
Token | it |
Token ID | 340 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Adidas | +0.549 |
Rust | +0.541 |
aila | +0.540 |
Pak | +0.534 |
bub | +0.533 |
Neg logit contributions | |
enthal | -0.630 |
sted | -0.570 |
carbohyd | -0.564 |
deceive | -0.539 |
cius | -0.536 |
Token | would |
Token ID | 561 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
Adidas | +1.111 |
Rust | +1.096 |
aila | +1.095 |
Pak | +1.082 |
bub | +1.079 |
Neg logit contributions | |
enthal | -1.180 |
sted | -1.064 |
carbohyd | -1.055 |
deceive | -1.006 |
cius | -1.001 |
Token | refuse |
Token ID | 11148 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
Adidas | +1.018 |
Rust | +1.005 |
aila | +1.003 |
Pak | +0.990 |
bub | +0.988 |
Neg logit contributions | |
enthal | -1.297 |
sted | -1.181 |
carbohyd | -1.167 |
deceive | -1.121 |
cius | -1.115 |
Token | to |
Token ID | 284 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
enthal | +0.185 |
sted | +0.168 |
carbohyd | +0.165 |
deceive | +0.160 |
cius | +0.158 |
Neg logit contributions | |
Adidas | -0.158 |
Rust | -0.157 |
aila | -0.156 |
bub | -0.155 |
Pak | -0.154 |
Token | take |
Token ID | 1011 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
Adidas | +1.346 |
aila | +1.322 |
Rust | +1.320 |
Pak | +1.305 |
bub | +1.300 |
Neg logit contributions | |
enthal | -1.610 |
sted | -1.461 |
carbohyd | -1.453 |
cius | -1.375 |
deceive | -1.367 |
Token | part |
Token ID | 636 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Adidas | +1.435 |
aila | +1.412 |
Rust | +1.411 |
Pak | +1.393 |
bub | +1.388 |
Neg logit contributions | |
enthal | -1.719 |
sted | -1.562 |
carbohyd | -1.546 |
deceive | -1.480 |
cius | -1.473 |
Token | in |
Token ID | 287 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
Adidas | +3.346 |
Rust | +3.283 |
Pak | +3.246 |
aila | +3.226 |
bub | +3.198 |
Neg logit contributions | |
enthal | -4.372 |
carbohyd | -3.931 |
sted | -3.920 |
eele | -3.756 |
cius | -3.734 |
Token | any |
Token ID | 597 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Adidas | +0.200 |
Rust | +0.198 |
aila | +0.197 |
Pak | +0.195 |
bub | +0.195 |
Neg logit contributions | |
enthal | -0.217 |
sted | -0.196 |
carbohyd | -0.193 |
deceive | -0.185 |
cius | -0.184 |
Token | government |
Token ID | 1230 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Adidas | +0.455 |
Rust | +0.449 |
aila | +0.448 |
Pak | +0.443 |
bub | +0.442 |
Neg logit contributions | |
enthal | -0.581 |
sted | -0.529 |
carbohyd | -0.523 |
deceive | -0.503 |
cius | -0.499 |
Token | unless |
Token ID | 4556 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
enthal | +0.503 |
sted | +0.459 |
carbohyd | +0.450 |
deceive | +0.437 |
cius | +0.433 |
Neg logit contributions | |
Adidas | -0.372 |
Rust | -0.370 |
aila | -0.368 |
Pak | -0.364 |
bub | -0.362 |
Token | Ken |
Token ID | 7148 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
Adidas | +2.016 |
aila | +1.972 |
Pak | +1.944 |
Rust | +1.943 |
bub | +1.936 |
Neg logit contributions | |
enthal | -2.378 |
carbohyd | -2.153 |
sted | -2.142 |
cius | -2.021 |
deceive | -2.020 |
Token | in |
Token ID | 287 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
Adidas | +0.995 |
Rust | +0.983 |
aila | +0.981 |
Pak | +0.969 |
bub | +0.966 |
Neg logit contributions | |
enthal | -1.216 |
sted | -1.105 |
carbohyd | -1.090 |
deceive | -1.049 |
cius | -1.042 |
Token | the |
Token ID | 262 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Adidas | +0.177 |
Rust | +0.175 |
aila | +0.175 |
Pak | +0.173 |
bub | +0.172 |
Neg logit contributions | |
enthal | -0.193 |
sted | -0.174 |
carbohyd | -0.171 |
deceive | -0.165 |
cius | -0.163 |
Token | vent |
Token ID | 7435 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
Adidas | +0.596 |
Rust | +0.590 |
aila | +0.589 |
Pak | +0.583 |
bub | +0.578 |
Neg logit contributions | |
enthal | -0.669 |
sted | -0.606 |
carbohyd | -0.595 |
deceive | -0.575 |
cius | -0.569 |
Token | ral |
Token ID | 1373 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Adidas | +1.950 |
bub | +1.947 |
Rust | +1.939 |
aila | +1.929 |
Pak | +1.921 |
Neg logit contributions | |
enthal | -1.780 |
sted | -1.589 |
carbohyd | -1.579 |
deceive | -1.497 |
cius | -1.475 |
Token | sensory |
Token ID | 23326 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Adidas | +0.896 |
Rust | +0.892 |
aila | +0.890 |
Pak | +0.876 |
bub | +0.866 |
Neg logit contributions | |
enthal | -1.127 |
sted | -1.027 |
carbohyd | -1.010 |
deceive | -0.980 |
ares | -0.969 |
Token | motor |
Token ID | 5584 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Adidas | +2.606 |
Rust | +2.577 |
bub | +2.569 |
aila | +2.561 |
Pak | +2.548 |
Neg logit contributions | |
enthal | -3.386 |
sted | -3.076 |
carbohyd | -3.046 |
cius | -2.917 |
deceive | -2.898 |
Token | cortex |
Token ID | 20223 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Adidas | +2.424 |
Rust | +2.388 |
aila | +2.381 |
bub | +2.375 |
Pak | +2.366 |
Neg logit contributions | |
enthal | -3.506 |
sted | -3.185 |
carbohyd | -3.175 |
deceive | -3.041 |
cius | -3.032 |
Token | ( |
Token ID | 357 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
Adidas | +2.679 |
Rust | +2.637 |
bub | +2.628 |
aila | +2.614 |
Pak | +2.581 |
Neg logit contributions | |
enthal | -3.723 |
carbohyd | -3.441 |
sted | -3.425 |
deceive | -3.255 |
cius | -3.252 |
Token | v |
Token ID | 85 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
enthal | +2.085 |
sted | +1.890 |
carbohyd | +1.805 |
cius | +1.780 |
ares | +1.774 |
Neg logit contributions | |
Adidas | -1.833 |
aila | -1.805 |
Rust | -1.760 |
bub | -1.742 |
Pak | -1.739 |
Token | S |
Token ID | 50 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
enthal | +0.494 |
sted | +0.449 |
carbohyd | +0.437 |
deceive | +0.422 |
cius | +0.422 |
Neg logit contributions | |
Adidas | -0.418 |
aila | -0.411 |
Rust | -0.409 |
bub | -0.405 |
Pak | -0.404 |
Token | MC |
Token ID | 9655 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
Adidas | +0.972 |
Rust | +0.969 |
aila | +0.968 |
Pak | +0.957 |
bub | +0.956 |
Neg logit contributions | |
enthal | -0.839 |
carbohyd | -0.752 |
sted | -0.747 |
deceive | -0.701 |
cius | -0.694 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Adidas | +1.450 |
aila | +1.425 |
Rust | +1.422 |
bub | +1.407 |
Pak | +1.402 |
Neg logit contributions | |
enthal | -1.757 |
sted | -1.593 |
carbohyd | -1.583 |
cius | -1.513 |
deceive | -1.510 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
enthal | +0.246 |
sted | +0.222 |
carbohyd | +0.220 |
deceive | +0.210 |
cius | +0.208 |
Neg logit contributions | |
Adidas | -0.242 |
Rust | -0.239 |
aila | -0.239 |
Pak | -0.236 |
bub | -0.236 |
Token |
|
Token ID | 198 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Adidas | +0.278 |
Rust | +0.275 |
aila | +0.274 |
Pak | +0.272 |
bub | +0.271 |
Neg logit contributions | |
enthal | -0.314 |
sted | -0.284 |
carbohyd | -0.284 |
deceive | -0.270 |
cius | -0.268 |
Token | Running |
Token ID | 28768 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
Adidas | +0.281 |
Rust | +0.277 |
aila | +0.277 |
Pak | +0.273 |
bub | +0.273 |
Neg logit contributions | |
enthal | -0.352 |
sted | -0.321 |
carbohyd | -0.316 |
deceive | -0.304 |
cius | -0.302 |
Token | back |
Token ID | 736 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Adidas | +1.393 |
aila | +1.348 |
Rust | +1.343 |
Pak | +1.325 |
bub | +1.319 |
Neg logit contributions | |
enthal | -2.785 |
sted | -2.569 |
carbohyd | -2.554 |
cius | -2.483 |
deceive | -2.466 |
Token | Bernard |
Token ID | 16197 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
Adidas | +0.807 |
Rust | +0.796 |
aila | +0.794 |
Pak | +0.784 |
bub | +0.783 |
Neg logit contributions | |
enthal | -0.852 |
sted | -0.768 |
carbohyd | -0.761 |
deceive | -0.727 |
cius | -0.723 |
Token | Pierce |
Token ID | 23023 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
Adidas | +0.487 |
Rust | +0.481 |
aila | +0.475 |
bub | +0.466 |
Pak | +0.466 |
Neg logit contributions | |
enthal | -0.744 |
sted | -0.697 |
carbohyd | -0.663 |
cius | -0.654 |
Swanson | -0.650 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
enthal | +0.139 |
sted | +0.126 |
carbohyd | +0.123 |
deceive | +0.119 |
cius | +0.118 |
Neg logit contributions | |
Adidas | -0.127 |
Rust | -0.126 |
aila | -0.125 |
Pak | -0.124 |
bub | -0.124 |
Token | offensive |
Token ID | 5859 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
enthal | +0.233 |
sted | +0.208 |
carbohyd | +0.204 |
deceive | +0.196 |
cius | +0.194 |
Neg logit contributions | |
Adidas | -0.259 |
Rust | -0.257 |
aila | -0.256 |
Pak | -0.253 |
bub | -0.253 |
Token | guard |
Token ID | 4860 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Adidas | +1.107 |
Rust | +1.090 |
aila | +1.088 |
Pak | +1.074 |
bub | +1.069 |
Neg logit contributions | |
enthal | -1.576 |
sted | -1.442 |
carbohyd | -1.428 |
deceive | -1.373 |
cius | -1.368 |
Token | Ron |
Token ID | 6575 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Adidas | +1.040 |
Rust | +1.026 |
aila | +1.022 |
Pak | +1.010 |
bub | +1.009 |
Neg logit contributions | |
enthal | -1.102 |
sted | -0.993 |
carbohyd | -0.989 |
deceive | -0.941 |
cius | -0.934 |
Token | 2 |
Token ID | 362 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
enthal | +0.110 |
sted | +0.100 |
carbohyd | +0.100 |
deceive | +0.096 |
cius | +0.095 |
Neg logit contributions | |
Adidas | -0.079 |
Rust | -0.078 |
aila | -0.077 |
Pak | -0.076 |
bub | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
enthal | +1.995 |
sted | +1.819 |
carbohyd | +1.779 |
deceive | +1.711 |
cius | +1.706 |
Neg logit contributions | |
Adidas | -1.682 |
Rust | -1.665 |
aila | -1.663 |
Pak | -1.642 |
bub | -1.634 |
Token | 18 |
Token ID | 1248 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
enthal | +0.695 |
sted | +0.632 |
carbohyd | +0.616 |
deceive | +0.599 |
cius | +0.595 |
Neg logit contributions | |
Adidas | -0.580 |
Rust | -0.576 |
aila | -0.575 |
Pak | -0.569 |
bub | -0.568 |
Token | 64 |
Token ID | 2414 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
Adidas | +0.646 |
Rust | +0.636 |
aila | +0.636 |
bub | +0.625 |
Pak | +0.625 |
Neg logit contributions | |
enthal | -0.985 |
sted | -0.905 |
carbohyd | -0.881 |
deceive | -0.862 |
cius | -0.855 |
Token | , |
Token ID | 11 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
enthal | +1.925 |
sted | +1.746 |
carbohyd | +1.718 |
deceive | +1.648 |
cius | +1.645 |
Neg logit contributions | |
Adidas | -1.622 |
Rust | -1.604 |
aila | -1.601 |
Pak | -1.587 |
bub | -1.578 |
Token | Poll |
Token ID | 12868 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
enthal | +1.236 |
sted | +1.130 |
carbohyd | +1.108 |
deceive | +1.077 |
cius | +1.073 |
Neg logit contributions | |
Adidas | -0.882 |
Rust | -0.873 |
aila | -0.871 |
Pak | -0.863 |
bub | -0.856 |
Token | ock |
Token ID | 735 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
Adidas | +0.164 |
Rust | +0.163 |
aila | +0.161 |
bub | +0.160 |
Pak | +0.160 |
Neg logit contributions | |
enthal | -0.135 |
sted | -0.120 |
carbohyd | -0.114 |
deceive | -0.111 |
cius | -0.111 |
Token | wrote |
Token ID | 2630 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
Adidas | +0.013 |
Rust | +0.013 |
aila | +0.013 |
Pak | +0.013 |
bub | +0.013 |
Neg logit contributions | |
enthal | -0.014 |
sted | -0.013 |
carbohyd | -0.013 |
deceive | -0.012 |
cius | -0.012 |
Token | urgently |
Token ID | 37788 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Adidas | +0.988 |
Rust | +0.970 |
aila | +0.970 |
Pak | +0.954 |
bub | +0.952 |
Neg logit contributions | |
enthal | -1.318 |
sted | -1.199 |
carbohyd | -1.194 |
deceive | -1.139 |
cius | -1.135 |
Token | to |
Token ID | 284 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
Adidas | +0.923 |
Rust | +0.910 |
aila | +0.908 |
Pak | +0.897 |
bub | +0.894 |
Neg logit contributions | |
enthal | -1.222 |
sted | -1.113 |
carbohyd | -1.105 |
deceive | -1.059 |
cius | -1.053 |
Token | Chase |
Token ID | 16346 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Adidas | +0.033 |
Rust | +0.033 |
aila | +0.033 |
Pak | +0.032 |
bub | +0.032 |
Neg logit contributions | |
enthal | -0.039 |
sted | -0.035 |
carbohyd | -0.035 |
deceive | -0.033 |
cius | -0.033 |
Token | their |
Token ID | 511 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
Adidas | +0.605 |
Rust | +0.605 |
aila | +0.600 |
bub | +0.591 |
Pak | +0.585 |
Neg logit contributions | |
enthal | -0.793 |
sted | -0.723 |
carbohyd | -0.708 |
deceive | -0.688 |
ares | -0.682 |
Token | kids |
Token ID | 3988 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
enthal | +0.145 |
sted | +0.134 |
carbohyd | +0.131 |
deceive | +0.128 |
ares | +0.128 |
Neg logit contributions | |
Adidas | -0.095 |
Rust | -0.095 |
aila | -0.094 |
bub | -0.092 |
Wra | -0.091 |
Token | toys |
Token ID | 14958 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
enthal | +0.283 |
sted | +0.256 |
carbohyd | +0.250 |
deceive | +0.242 |
cius | +0.241 |
Neg logit contributions | |
Adidas | -0.248 |
Rust | -0.247 |
aila | -0.246 |
bub | -0.242 |
Pak | -0.241 |
Token | in |
Token ID | 287 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
enthal | +0.676 |
sted | +0.607 |
carbohyd | +0.592 |
deceive | +0.575 |
cius | +0.571 |
Neg logit contributions | |
Adidas | -0.632 |
Rust | -0.631 |
aila | -0.626 |
bub | -0.618 |
Pak | -0.614 |
Token | Pakistan |
Token ID | 7648 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
Adidas | +0.369 |
Rust | +0.369 |
aila | +0.367 |
bub | +0.360 |
Pak | +0.354 |
Neg logit contributions | |
enthal | -0.555 |
sted | -0.507 |
carbohyd | -0.500 |
deceive | -0.485 |
cius | -0.479 |
Token | from |
Token ID | 422 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
Adidas | +1.495 |
Rust | +1.475 |
aila | +1.471 |
Pak | +1.466 |
bub | +1.457 |
Neg logit contributions | |
enthal | -1.627 |
sted | -1.472 |
carbohyd | -1.463 |
deceive | -1.397 |
cius | -1.385 |
Token | their |
Token ID | 511 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
Adidas | +1.592 |
Pak | +1.561 |
Rust | +1.553 |
aila | +1.552 |
bub | +1.535 |
Neg logit contributions | |
enthal | -1.886 |
sted | -1.711 |
carbohyd | -1.709 |
deceive | -1.621 |
cius | -1.620 |
Token | homes |
Token ID | 5682 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
Rust | +0.114 |
Adidas | +0.114 |
aila | +0.113 |
bub | +0.111 |
Pak | +0.110 |
Neg logit contributions | |
enthal | -0.160 |
sted | -0.147 |
carbohyd | -0.143 |
deceive | -0.140 |
ares | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Adidas | +0.101 |
Rust | +0.100 |
aila | +0.099 |
Pak | +0.098 |
bub | +0.098 |
Neg logit contributions | |
enthal | -0.111 |
sted | -0.100 |
carbohyd | -0.098 |
deceive | -0.095 |
cius | -0.094 |
Token | An |
Token ID | 1052 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
enthal | +0.795 |
sted | +0.715 |
Admission | +0.667 |
carbohyd | +0.665 |
deceive | +0.664 |
Neg logit contributions | |
aila | -0.839 |
Rust | -0.837 |
Adidas | -0.834 |
bub | -0.820 |
Pak | -0.803 |
Token | array |
Token ID | 7177 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Adidas | +1.021 |
Rust | +1.012 |
aila | +1.008 |
Pak | +0.994 |
bub | +0.994 |
Neg logit contributions | |
enthal | -1.172 |
sted | -1.062 |
carbohyd | -1.046 |
deceive | -1.006 |
cius | -0.999 |
Token | 11 |
Token ID | 1367 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
enthal | +0.340 |
sted | +0.308 |
carbohyd | +0.303 |
deceive | +0.292 |
cius | +0.290 |
Neg logit contributions | |
Adidas | -0.285 |
Rust | -0.282 |
aila | -0.281 |
Pak | -0.277 |
bub | -0.277 |
Token | 190 |
Token ID | 19782 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Adidas | +1.492 |
Rust | +1.477 |
aila | +1.466 |
bub | +1.452 |
Pak | +1.449 |
Neg logit contributions | |
enthal | -2.005 |
carbohyd | -1.864 |
sted | -1.809 |
deceive | -1.743 |
cius | -1.742 |
Token | 34 |
Token ID | 2682 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
enthal | +0.546 |
sted | +0.499 |
carbohyd | +0.483 |
deceive | +0.473 |
ares | +0.469 |
Neg logit contributions | |
Adidas | -0.416 |
Rust | -0.412 |
aila | -0.411 |
Pak | -0.405 |
bub | -0.404 |
Token | x |
Token ID | 2124 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
enthal | +0.556 |
sted | +0.510 |
carbohyd | +0.498 |
deceive | +0.486 |
cius | +0.482 |
Neg logit contributions | |
Adidas | -0.366 |
Rust | -0.362 |
aila | -0.362 |
Pak | -0.356 |
bub | -0.356 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Adidas | +0.070 |
Rust | +0.069 |
aila | +0.069 |
Pak | +0.068 |
bub | +0.068 |
Neg logit contributions | |
enthal | -0.072 |
sted | -0.065 |
carbohyd | -0.064 |
deceive | -0.061 |
cius | -0.061 |
Token | x |
Token ID | 87 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
Adidas | +0.190 |
Rust | +0.186 |
aila | +0.185 |
Pak | +0.181 |
bub | +0.181 |
Neg logit contributions | |
enthal | -0.509 |
sted | -0.474 |
carbohyd | -0.468 |
deceive | -0.456 |
cius | -0.454 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
enthal | +0.174 |
carbohyd | +0.157 |
sted | +0.157 |
deceive | +0.149 |
cius | +0.147 |
Neg logit contributions | |
Adidas | -0.169 |
Rust | -0.167 |
aila | -0.167 |
Pak | -0.165 |
bub | -0.165 |
Token | x |
Token ID | 87 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
Adidas | +0.408 |
Rust | +0.403 |
aila | +0.400 |
bub | +0.396 |
Pak | +0.394 |
Neg logit contributions | |
enthal | -1.191 |
carbohyd | -1.129 |
sted | -1.109 |
deceive | -1.083 |
cius | -1.065 |
Token | . |
Token ID | 13 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
Adidas | +0.097 |
Rust | +0.096 |
aila | +0.096 |
Pak | +0.095 |
bub | +0.095 |
Neg logit contributions | |
enthal | -0.103 |
carbohyd | -0.096 |
sted | -0.093 |
deceive | -0.089 |
cius | -0.088 |
Token | 111 |
Token ID | 16243 |
Feature activation | -9.69e-03 |
Pos logit contributions | |
Adidas | +0.981 |
Rust | +0.977 |
aila | +0.971 |
Pak | +0.961 |
bub | +0.958 |
Neg logit contributions | |
enthal | -1.293 |
sted | -1.185 |
carbohyd | -1.183 |
deceive | -1.128 |
eele | -1.114 |
Token | 10 |
Token ID | 838 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
enthal | +0.025 |
sted | +0.023 |
carbohyd | +0.023 |
deceive | +0.022 |
cius | +0.022 |
Neg logit contributions | |
Adidas | -0.021 |
Rust | -0.021 |
aila | -0.021 |
Pak | -0.020 |
bub | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
enthal | +0.374 |
sted | +0.341 |
carbohyd | +0.334 |
deceive | +0.323 |
cius | +0.320 |
Neg logit contributions | |
Adidas | -0.315 |
aila | -0.313 |
Rust | -0.313 |
Pak | -0.309 |
bub | -0.307 |
Token | the |
Token ID | 262 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
Adidas | +0.358 |
Rust | +0.354 |
aila | +0.352 |
Pak | +0.348 |
bub | +0.348 |
Neg logit contributions | |
enthal | -0.380 |
sted | -0.343 |
carbohyd | -0.339 |
deceive | -0.324 |
cius | -0.322 |
Token | fans |
Token ID | 3296 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
enthal | +0.097 |
sted | +0.087 |
carbohyd | +0.086 |
deceive | +0.083 |
cius | +0.082 |
Neg logit contributions | |
Adidas | -0.087 |
Rust | -0.086 |
aila | -0.086 |
Pak | -0.085 |
bub | -0.085 |
Token | won |
Token ID | 1839 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Adidas | +0.850 |
aila | +0.836 |
Rust | +0.836 |
Pak | +0.825 |
bub | +0.824 |
Neg logit contributions | |
enthal | -1.014 |
sted | -0.920 |
carbohyd | -0.913 |
deceive | -0.866 |
cius | -0.865 |
Token | 't |
Token ID | 470 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
enthal | +0.930 |
sted | +0.847 |
carbohyd | +0.803 |
deceive | +0.795 |
ares | +0.791 |
Neg logit contributions | |
Adidas | -0.789 |
aila | -0.779 |
Rust | -0.778 |
bub | -0.769 |
Pak | -0.766 |
Token | be |
Token ID | 307 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Adidas | +0.043 |
Rust | +0.042 |
aila | +0.042 |
Pak | +0.042 |
bub | +0.041 |
Neg logit contributions | |
enthal | -0.052 |
sted | -0.047 |
carbohyd | -0.047 |
deceive | -0.045 |
cius | -0.044 |
Token | able |
Token ID | 1498 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
Adidas | +0.370 |
Rust | +0.365 |
aila | +0.364 |
Pak | +0.360 |
bub | +0.360 |
Neg logit contributions | |
enthal | -0.417 |
sted | -0.377 |
carbohyd | -0.373 |
deceive | -0.357 |
cius | -0.355 |
Token | to |
Token ID | 284 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
Adidas | +0.064 |
Rust | +0.063 |
aila | +0.063 |
Pak | +0.062 |
bub | +0.062 |
Neg logit contributions | |
enthal | -0.082 |
sted | -0.074 |
carbohyd | -0.073 |
deceive | -0.071 |
cius | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
Adidas | +0.090 |
Rust | +0.088 |
aila | +0.088 |
bub | +0.087 |
Pak | +0.087 |
Neg logit contributions | |
enthal | -0.103 |
sted | -0.093 |
carbohyd | -0.092 |
cius | -0.088 |
deceive | -0.088 |
Token | no |
Token ID | 645 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Adidas | +0.380 |
Rust | +0.375 |
aila | +0.374 |
Pak | +0.369 |
bub | +0.369 |
Neg logit contributions | |
enthal | -0.493 |
sted | -0.449 |
carbohyd | -0.443 |
deceive | -0.426 |
cius | -0.424 |
Token | matter |
Token ID | 2300 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
Adidas | +0.572 |
Rust | +0.563 |
aila | +0.562 |
bub | +0.555 |
Pak | +0.554 |
Neg logit contributions | |
enthal | -0.670 |
sted | -0.608 |
carbohyd | -0.601 |
deceive | -0.575 |
cius | -0.573 |
Token | things |
Token ID | 1243 |
Feature activation | -4.41e-03 |
Pos logit contributions | |
enthal | +0.034 |
sted | +0.032 |
carbohyd | +0.030 |
deceive | +0.030 |
ares | +0.029 |
Neg logit contributions | |
Rust | -0.035 |
aila | -0.035 |
Adidas | -0.035 |
Pak | -0.035 |
bub | -0.034 |
Token | lately |
Token ID | 16537 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
enthal | +0.011 |
sted | +0.010 |
carbohyd | +0.010 |
deceive | +0.010 |
cius | +0.010 |
Neg logit contributions | |
Adidas | -0.010 |
Rust | -0.010 |
aila | -0.010 |
Pak | -0.010 |
bub | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
enthal | +0.495 |
sted | +0.447 |
carbohyd | +0.438 |
deceive | +0.423 |
cius | +0.420 |
Neg logit contributions | |
Adidas | -0.465 |
Rust | -0.462 |
aila | -0.461 |
Pak | -0.456 |
bub | -0.454 |
Token | Owner |
Token ID | 23853 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
enthal | +0.179 |
sted | +0.161 |
carbohyd | +0.157 |
deceive | +0.151 |
cius | +0.150 |
Neg logit contributions | |
Adidas | -0.185 |
Rust | -0.184 |
aila | -0.184 |
Pak | -0.181 |
bub | -0.181 |
Token | Sylvia |
Token ID | 45425 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Adidas | +1.542 |
Rust | +1.521 |
aila | +1.510 |
Pak | +1.493 |
bub | +1.492 |
Neg logit contributions | |
enthal | -1.646 |
carbohyd | -1.491 |
sted | -1.481 |
deceive | -1.406 |
cius | -1.398 |
Token | Cas |
Token ID | 11294 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
enthal | +0.568 |
sted | +0.514 |
carbohyd | +0.503 |
deceive | +0.486 |
cius | +0.482 |
Neg logit contributions | |
Adidas | -0.498 |
Rust | -0.493 |
aila | -0.492 |
Pak | -0.486 |
bub | -0.485 |
Token | ares |
Token ID | 3565 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
enthal | +1.310 |
sted | +1.184 |
carbohyd | +1.154 |
cius | +1.113 |
deceive | +1.112 |
Neg logit contributions | |
Adidas | -1.224 |
Rust | -1.212 |
aila | -1.201 |
Pak | -1.193 |
bub | -1.188 |
Token | was |
Token ID | 373 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
enthal | +1.605 |
sted | +1.461 |
carbohyd | +1.375 |
ares | +1.359 |
cius | +1.357 |
Neg logit contributions | |
Adidas | -1.515 |
Rust | -1.505 |
Pak | -1.492 |
aila | -1.491 |
bub | -1.488 |
Token | critically |
Token ID | 19475 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
Adidas | +0.422 |
Rust | +0.418 |
aila | +0.416 |
Pak | +0.411 |
bub | +0.411 |
Neg logit contributions | |
enthal | -0.516 |
sted | -0.470 |
carbohyd | -0.463 |
deceive | -0.446 |
cius | -0.443 |
Token | injured |
Token ID | 6686 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Adidas | +1.364 |
Rust | +1.347 |
aila | +1.344 |
Pak | +1.324 |
bub | +1.323 |
Neg logit contributions | |
enthal | -1.752 |
sted | -1.589 |
carbohyd | -1.573 |
deceive | -1.511 |
cius | -1.503 |
Token | when |
Token ID | 618 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Adidas | +0.543 |
Rust | +0.537 |
aila | +0.535 |
Pak | +0.528 |
bub | +0.528 |
Neg logit contributions | |
enthal | -0.666 |
sted | -0.604 |
carbohyd | -0.597 |
deceive | -0.574 |
cius | -0.570 |
Token | did |
Token ID | 750 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
enthal | +0.565 |
sted | +0.507 |
carbohyd | +0.493 |
deceive | +0.477 |
cius | +0.471 |
Neg logit contributions | |
Adidas | -0.601 |
Rust | -0.597 |
aila | -0.594 |
Pak | -0.589 |
bub | -0.588 |
Token | say |
Token ID | 910 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Adidas | +0.523 |
Rust | +0.516 |
aila | +0.515 |
Pak | +0.509 |
bub | +0.507 |
Neg logit contributions | |
enthal | -0.676 |
sted | -0.617 |
carbohyd | -0.610 |
deceive | -0.584 |
cius | -0.582 |
Token | he |
Token ID | 339 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Adidas | +2.745 |
aila | +2.660 |
Rust | +2.641 |
bub | +2.640 |
Pak | +2.614 |
Neg logit contributions | |
enthal | -3.122 |
carbohyd | -2.839 |
sted | -2.802 |
deceive | -2.676 |
cius | -2.659 |
Token | supports |
Token ID | 6971 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
Adidas | +0.881 |
aila | +0.869 |
Rust | +0.869 |
Pak | +0.859 |
bub | +0.856 |
Neg logit contributions | |
enthal | -0.966 |
sted | -0.871 |
carbohyd | -0.867 |
deceive | -0.824 |
cius | -0.821 |
Token | legalizing |
Token ID | 44553 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
enthal | +1.849 |
sted | +1.678 |
carbohyd | +1.612 |
deceive | +1.580 |
ares | +1.562 |
Neg logit contributions | |
Rust | -1.649 |
Adidas | -1.647 |
aila | -1.634 |
bub | -1.632 |
Pak | -1.623 |
Token | medical |
Token ID | 3315 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
enthal | +1.344 |
sted | +1.215 |
carbohyd | +1.188 |
deceive | +1.149 |
cius | +1.137 |
Neg logit contributions | |
Rust | -1.304 |
Adidas | -1.302 |
aila | -1.298 |
Pak | -1.285 |
bub | -1.283 |
Token | marijuana |
Token ID | 5727 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
enthal | +1.387 |
sted | +1.250 |
carbohyd | +1.216 |
deceive | +1.186 |
ares | +1.164 |
Neg logit contributions | |
Rust | -1.463 |
Adidas | -1.451 |
aila | -1.449 |
Pak | -1.426 |
bub | -1.422 |
Token | — |
Token ID | 851 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
enthal | +0.189 |
sted | +0.171 |
carbohyd | +0.168 |
deceive | +0.162 |
cius | +0.160 |
Neg logit contributions | |
Adidas | -0.160 |
Rust | -0.159 |
aila | -0.159 |
Pak | -0.157 |
bub | -0.156 |
Token | as |
Token ID | 355 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Adidas | +0.477 |
Rust | +0.472 |
aila | +0.471 |
Pak | +0.465 |
bub | +0.464 |
Neg logit contributions | |
enthal | -0.635 |
sted | -0.579 |
carbohyd | -0.571 |
deceive | -0.551 |
cius | -0.547 |
Token | long |
Token ID | 890 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
enthal | +0.528 |
sted | +0.486 |
carbohyd | +0.478 |
deceive | +0.464 |
cius | +0.462 |
Neg logit contributions | |
Adidas | -0.330 |
Rust | -0.327 |
aila | -0.326 |
Pak | -0.321 |
bub | -0.320 |
Token | as |
Token ID | 355 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Adidas | +0.927 |
Rust | +0.913 |
aila | +0.911 |
bub | +0.899 |
Pak | +0.898 |
Neg logit contributions | |
enthal | -1.115 |
sted | -1.011 |
carbohyd | -1.002 |
deceive | -0.962 |
cius | -0.956 |
Token | them |
Token ID | 606 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
enthal | +0.962 |
sted | +0.866 |
carbohyd | +0.846 |
deceive | +0.818 |
cius | +0.809 |
Neg logit contributions | |
Adidas | -0.980 |
Rust | -0.973 |
aila | -0.969 |
Pak | -0.958 |
bub | -0.956 |
Token | : |
Token ID | 25 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
enthal | +0.797 |
sted | +0.721 |
carbohyd | +0.708 |
deceive | +0.684 |
cius | +0.677 |
Neg logit contributions | |
Adidas | -0.716 |
Rust | -0.709 |
aila | -0.708 |
Pak | -0.698 |
bub | -0.697 |
Token | medicinal |
Token ID | 30381 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
enthal | +0.361 |
sted | +0.327 |
carbohyd | +0.323 |
deceive | +0.310 |
cius | +0.308 |
Neg logit contributions | |
Adidas | -0.309 |
Rust | -0.305 |
aila | -0.304 |
Pak | -0.301 |
bub | -0.300 |
Token | herbs |
Token ID | 25411 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
Adidas | +0.422 |
Rust | +0.417 |
aila | +0.416 |
Pak | +0.412 |
bub | +0.410 |
Neg logit contributions | |
enthal | -0.471 |
sted | -0.426 |
carbohyd | -0.420 |
deceive | -0.403 |
cius | -0.401 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
enthal | +1.090 |
sted | +0.989 |
carbohyd | +0.970 |
deceive | +0.940 |
cius | +0.930 |
Neg logit contributions | |
Adidas | -0.922 |
Rust | -0.916 |
aila | -0.912 |
Pak | -0.900 |
bub | -0.899 |
Token | Chinese |
Token ID | 3999 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
Adidas | +0.026 |
Rust | +0.026 |
aila | +0.026 |
Pak | +0.026 |
bub | +0.026 |
Neg logit contributions | |
enthal | -0.029 |
sted | -0.026 |
carbohyd | -0.026 |
deceive | -0.024 |
cius | -0.024 |
Token | herbs |
Token ID | 25411 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
enthal | +0.892 |
sted | +0.795 |
carbohyd | +0.783 |
cius | +0.755 |
deceive | +0.749 |
Neg logit contributions | |
Adidas | -1.009 |
Rust | -1.006 |
aila | -0.998 |
bub | -0.991 |
Pak | -0.990 |
Token | , |
Token ID | 11 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
enthal | +0.757 |
sted | +0.688 |
carbohyd | +0.677 |
deceive | +0.653 |
cius | +0.648 |
Neg logit contributions | |
Adidas | -0.621 |
Rust | -0.615 |
aila | -0.613 |
Pak | -0.605 |
bub | -0.604 |
Token | cut |
Token ID | 2005 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Adidas | +0.178 |
Rust | +0.176 |
aila | +0.175 |
Pak | +0.173 |
bub | +0.173 |
Neg logit contributions | |
enthal | -0.204 |
sted | -0.184 |
carbohyd | -0.182 |
deceive | -0.175 |
cius | -0.174 |
Token | flowers |
Token ID | 12734 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
enthal | +1.095 |
sted | +0.994 |
carbohyd | +0.979 |
deceive | +0.940 |
cius | +0.934 |
Neg logit contributions | |
Adidas | -0.935 |
Rust | -0.924 |
aila | -0.920 |
Pak | -0.910 |
bub | -0.909 |
Token | , |
Token ID | 11 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
enthal | +1.185 |
sted | +1.075 |
carbohyd | +1.057 |
deceive | +1.020 |
cius | +1.011 |
Neg logit contributions | |
Adidas | -0.974 |
Rust | -0.965 |
aila | -0.962 |
bub | -0.949 |
Pak | -0.948 |
Token | who |
Token ID | 508 |
Feature activation | +8.77e-05 |
Pos logit contributions | |
enthal | +0.930 |
sted | +0.839 |
carbohyd | +0.818 |
deceive | +0.792 |
cius | +0.786 |
Neg logit contributions | |
Rust | -0.924 |
Adidas | -0.923 |
aila | -0.919 |
Pak | -0.909 |
bub | -0.905 |
Token | participate |
Token ID | 8277 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Adidas | +0.000 |
Rust | +0.000 |
aila | +0.000 |
Pak | +0.000 |
bub | +0.000 |
Neg logit contributions | |
enthal | -0.000 |
sted | -0.000 |
carbohyd | -0.000 |
deceive | -0.000 |
cius | -0.000 |
Token | do |
Token ID | 466 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Adidas | +0.438 |
Rust | +0.432 |
aila | +0.431 |
Pak | +0.426 |
bub | +0.425 |
Neg logit contributions | |
enthal | -0.501 |
sted | -0.454 |
carbohyd | -0.449 |
deceive | -0.428 |
cius | -0.425 |
Token | so |
Token ID | 523 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
enthal | +0.299 |
sted | +0.266 |
carbohyd | +0.262 |
deceive | +0.250 |
cius | +0.248 |
Neg logit contributions | |
Adidas | -0.344 |
Rust | -0.341 |
aila | -0.340 |
Pak | -0.336 |
bub | -0.336 |
Token | with |
Token ID | 351 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
enthal | +0.722 |
sted | +0.656 |
carbohyd | +0.640 |
deceive | +0.622 |
ares | +0.614 |
Neg logit contributions | |
Adidas | -0.640 |
Rust | -0.640 |
aila | -0.637 |
Pak | -0.629 |
bub | -0.627 |
Token | the |
Token ID | 262 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
enthal | +0.274 |
sted | +0.248 |
carbohyd | +0.241 |
deceive | +0.233 |
cius | +0.231 |
Neg logit contributions | |
Rust | -0.260 |
Adidas | -0.260 |
aila | -0.258 |
Pak | -0.256 |
bub | -0.255 |
Token | aim |
Token ID | 4031 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
enthal | +0.588 |
sted | +0.534 |
carbohyd | +0.522 |
deceive | +0.505 |
cius | +0.502 |
Neg logit contributions | |
Adidas | -0.486 |
Rust | -0.485 |
aila | -0.484 |
bub | -0.476 |
Pak | -0.476 |
Token | of |
Token ID | 286 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
enthal | +0.134 |
sted | +0.120 |
carbohyd | +0.118 |
deceive | +0.113 |
cius | +0.113 |
Neg logit contributions | |
Adidas | -0.140 |
Rust | -0.139 |
aila | -0.138 |
Pak | -0.137 |
bub | -0.137 |
Token | ensuring |
Token ID | 13359 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
Adidas | +0.689 |
Rust | +0.678 |
aila | +0.677 |
Pak | +0.670 |
bub | +0.667 |
Neg logit contributions | |
enthal | -0.807 |
sted | -0.732 |
carbohyd | -0.727 |
deceive | -0.693 |
cius | -0.691 |
Token | that |
Token ID | 326 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Adidas | +1.078 |
aila | +1.050 |
Rust | +1.048 |
bub | +1.040 |
Pak | +1.038 |
Neg logit contributions | |
enthal | -1.239 |
carbohyd | -1.122 |
sted | -1.118 |
deceive | -1.060 |
cius | -1.059 |
Token | it |
Token ID | 340 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
enthal | +0.327 |
sted | +0.295 |
carbohyd | +0.292 |
deceive | +0.279 |
cius | +0.277 |
Neg logit contributions | |
Adidas | -0.297 |
Rust | -0.293 |
aila | -0.292 |
Pak | -0.289 |
bub | -0.289 |
Token | which |
Token ID | 543 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
enthal | +0.443 |
sted | +0.401 |
carbohyd | +0.396 |
deceive | +0.383 |
cius | +0.380 |
Neg logit contributions | |
Adidas | -0.355 |
Rust | -0.351 |
aila | -0.350 |
Pak | -0.346 |
bub | -0.345 |
Token | will |
Token ID | 481 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
enthal | +0.182 |
sted | +0.165 |
carbohyd | +0.162 |
deceive | +0.156 |
cius | +0.155 |
Neg logit contributions | |
Adidas | -0.167 |
Rust | -0.166 |
aila | -0.165 |
Pak | -0.163 |
bub | -0.163 |
Token | become |
Token ID | 1716 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
Adidas | +2.310 |
aila | +2.283 |
Rust | +2.256 |
Pak | +2.228 |
bub | +2.222 |
Neg logit contributions | |
enthal | -2.922 |
carbohyd | -2.668 |
sted | -2.649 |
cius | -2.504 |
ares | -2.482 |
Token | possible |
Token ID | 1744 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
enthal | +0.040 |
sted | +0.036 |
carbohyd | +0.036 |
deceive | +0.034 |
cius | +0.034 |
Neg logit contributions | |
Adidas | -0.036 |
Rust | -0.036 |
aila | -0.036 |
Pak | -0.035 |
bub | -0.035 |
Token | when |
Token ID | 618 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Adidas | +0.411 |
Rust | +0.407 |
aila | +0.405 |
Pak | +0.400 |
bub | +0.400 |
Neg logit contributions | |
enthal | -0.516 |
sted | -0.469 |
carbohyd | -0.464 |
deceive | -0.446 |
cius | -0.443 |
Token | justified |
Token ID | 14460 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
enthal | +0.500 |
sted | +0.452 |
carbohyd | +0.445 |
deceive | +0.428 |
cius | +0.425 |
Neg logit contributions | |
Adidas | -0.455 |
Rust | -0.450 |
aila | -0.449 |
Pak | -0.444 |
bub | -0.443 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
enthal | +2.328 |
sted | +2.086 |
carbohyd | +2.066 |
deceive | +2.000 |
ares | +1.984 |
Neg logit contributions | |
Adidas | -2.017 |
aila | -1.986 |
Rust | -1.970 |
Pak | -1.960 |
bub | -1.956 |
Token | while |
Token ID | 981 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
enthal | +0.283 |
sted | +0.257 |
carbohyd | +0.253 |
deceive | +0.245 |
cius | +0.243 |
Neg logit contributions | |
Adidas | -0.223 |
Rust | -0.220 |
aila | -0.219 |
Pak | -0.217 |
bub | -0.216 |
Token | also |
Token ID | 635 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Adidas | +0.614 |
Rust | +0.606 |
aila | +0.604 |
Pak | +0.597 |
bub | +0.596 |
Neg logit contributions | |
enthal | -0.702 |
sted | -0.636 |
carbohyd | -0.630 |
deceive | -0.601 |
cius | -0.599 |
Token | providing |
Token ID | 4955 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Adidas | +0.517 |
Rust | +0.511 |
aila | +0.510 |
Pak | +0.504 |
bub | +0.503 |
Neg logit contributions | |
enthal | -0.584 |
sted | -0.529 |
carbohyd | -0.523 |
deceive | -0.501 |
cius | -0.498 |
Token | the |
Token ID | 262 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
enthal | +0.525 |
sted | +0.473 |
carbohyd | +0.465 |
deceive | +0.447 |
cius | +0.444 |
Neg logit contributions | |
Adidas | -0.500 |
Rust | -0.495 |
aila | -0.494 |
Pak | -0.489 |
bub | -0.488 |
Token | the |
Token ID | 262 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
enthal | +0.256 |
sted | +0.231 |
carbohyd | +0.228 |
deceive | +0.217 |
cius | +0.216 |
Neg logit contributions | |
Adidas | -0.248 |
Rust | -0.245 |
aila | -0.245 |
Pak | -0.242 |
bub | -0.241 |
Token | D |
Token ID | 360 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
enthal | +0.251 |
sted | +0.228 |
carbohyd | +0.224 |
deceive | +0.217 |
cius | +0.215 |
Neg logit contributions | |
Adidas | -0.209 |
Rust | -0.206 |
aila | -0.206 |
Pak | -0.203 |
bub | -0.203 |
Token | NR |
Token ID | 24723 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
Adidas | +0.065 |
Rust | +0.064 |
aila | +0.064 |
bub | +0.063 |
Pak | +0.063 |
Neg logit contributions | |
enthal | -0.034 |
sted | -0.029 |
carbohyd | -0.029 |
deceive | -0.027 |
cius | -0.026 |
Token | fals |
Token ID | 27807 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
enthal | +1.876 |
sted | +1.695 |
carbohyd | +1.647 |
deceive | +1.601 |
cius | +1.578 |
Neg logit contributions | |
Adidas | -1.869 |
Rust | -1.851 |
aila | -1.848 |
Pak | -1.826 |
bub | -1.819 |
Token | ified |
Token ID | 1431 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
enthal | +2.104 |
sted | +1.947 |
carbohyd | +1.869 |
deceive | +1.825 |
ares | +1.807 |
Neg logit contributions | |
Adidas | -1.456 |
Rust | -1.439 |
aila | -1.411 |
Pak | -1.407 |
bub | -1.400 |
Token | bear |
Token ID | 6842 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
enthal | +1.154 |
sted | +1.043 |
carbohyd | +1.020 |
deceive | +0.985 |
cius | +0.977 |
Neg logit contributions | |
Adidas | -1.118 |
Rust | -1.109 |
aila | -1.105 |
Pak | -1.094 |
bub | -1.092 |
Token | complaints |
Token ID | 9687 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
enthal | +4.170 |
sted | +3.797 |
carbohyd | +3.606 |
deceive | +3.582 |
ares | +3.570 |
Neg logit contributions | |
aila | -4.090 |
Adidas | -4.082 |
Rust | -4.064 |
bub | -4.005 |
Pak | -3.981 |
Token | , |
Token ID | 11 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
Adidas | +0.601 |
Rust | +0.592 |
aila | +0.592 |
Pak | +0.583 |
bub | +0.582 |
Neg logit contributions | |
enthal | -0.780 |
sted | -0.710 |
carbohyd | -0.709 |
deceive | -0.677 |
cius | -0.672 |
Token | David |
Token ID | 3271 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
enthal | +0.227 |
sted | +0.205 |
carbohyd | +0.204 |
deceive | +0.192 |
cius | +0.192 |
Neg logit contributions | |
Adidas | -0.215 |
Rust | -0.212 |
aila | -0.212 |
Pak | -0.209 |
bub | -0.208 |
Token | went |
Token ID | 1816 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
Adidas | +0.302 |
Rust | +0.298 |
aila | +0.298 |
Pak | +0.295 |
bub | +0.293 |
Neg logit contributions | |
enthal | -0.310 |
sted | -0.280 |
carbohyd | -0.279 |
deceive | -0.264 |
cius | -0.263 |
Token | to |
Token ID | 284 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Adidas | +0.782 |
Rust | +0.772 |
aila | +0.769 |
Pak | +0.760 |
bub | +0.758 |
Neg logit contributions | |
enthal | -1.048 |
sted | -0.955 |
carbohyd | -0.945 |
deceive | -0.909 |
cius | -0.904 |
Token | just |
Token ID | 655 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
enthal | +0.211 |
sted | +0.191 |
carbohyd | +0.190 |
deceive | +0.181 |
cius | +0.180 |
Neg logit contributions | |
Adidas | -0.182 |
Rust | -0.179 |
aila | -0.178 |
Pak | -0.176 |
bub | -0.175 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
enthal | +0.905 |
sted | +0.817 |
carbohyd | +0.806 |
deceive | +0.773 |
cius | +0.767 |
Neg logit contributions | |
Adidas | -0.839 |
Rust | -0.830 |
aila | -0.828 |
Pak | -0.819 |
bub | -0.817 |
Token | animals |
Token ID | 4695 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
Adidas | +0.179 |
Rust | +0.177 |
aila | +0.177 |
Pak | +0.175 |
bub | +0.175 |
Neg logit contributions | |
enthal | -0.162 |
sted | -0.144 |
carbohyd | -0.143 |
deceive | -0.136 |
cius | -0.135 |
Token | ," |
Token ID | 553 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
enthal | +2.220 |
sted | +1.989 |
carbohyd | +1.923 |
deceive | +1.884 |
ares | +1.866 |
Neg logit contributions | |
Adidas | -2.307 |
aila | -2.303 |
Rust | -2.301 |
Pak | -2.272 |
bub | -2.271 |
Token | Brad |
Token ID | 8114 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
enthal | +2.633 |
sted | +2.330 |
carbohyd | +2.207 |
deceive | +2.148 |
Swanson | +2.141 |
Neg logit contributions | |
Adidas | -3.447 |
aila | -3.418 |
Rust | -3.408 |
Pak | -3.398 |
Wra | -3.344 |
Token | Schro |
Token ID | 47349 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
enthal | +1.632 |
sted | +1.436 |
carbohyd | +1.370 |
deceive | +1.318 |
ares | +1.305 |
Neg logit contributions | |
Adidas | -2.177 |
Rust | -2.167 |
aila | -2.157 |
Pak | -2.142 |
bub | -2.126 |
Token | eder |
Token ID | 5702 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
enthal | +3.797 |
sted | +3.444 |
ares | +3.172 |
cius | +3.085 |
eele | +3.078 |
Neg logit contributions | |
Rust | -3.736 |
Adidas | -3.718 |
aila | -3.653 |
Pak | -3.643 |
bub | -3.639 |
Token | said |
Token ID | 531 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
enthal | +1.638 |
sted | +1.460 |
carbohyd | +1.427 |
deceive | +1.364 |
cius | +1.353 |
Neg logit contributions | |
Adidas | -1.917 |
Rust | -1.899 |
aila | -1.891 |
Pak | -1.876 |
bub | -1.869 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
enthal | +0.305 |
sted | +0.275 |
carbohyd | +0.271 |
deceive | +0.260 |
cius | +0.258 |
Neg logit contributions | |
Adidas | -0.294 |
Rust | -0.291 |
aila | -0.290 |
Pak | -0.287 |
bub | -0.287 |
Token |
|
Token ID | 198 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
enthal | +0.744 |
sted | +0.678 |
carbohyd | +0.670 |
deceive | +0.646 |
cius | +0.641 |
Neg logit contributions | |
Adidas | -0.565 |
Rust | -0.559 |
aila | -0.557 |
Pak | -0.550 |
bub | -0.549 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
enthal | +0.514 |
sted | +0.466 |
carbohyd | +0.438 |
deceive | +0.433 |
ares | +0.432 |
Neg logit contributions | |
Adidas | -0.491 |
aila | -0.485 |
Rust | -0.485 |
bub | -0.478 |
Pak | -0.477 |
Token | � |
Token ID | 564 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
Adidas | +0.068 |
Rust | +0.067 |
aila | +0.067 |
Pak | +0.066 |
bub | +0.066 |
Neg logit contributions | |
enthal | -0.082 |
sted | -0.075 |
carbohyd | -0.074 |
deceive | -0.071 |
cius | -0.071 |
Token | � |
Token ID | 250 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Adidas | +0.628 |
Rust | +0.623 |
aila | +0.619 |
Pak | +0.614 |
bub | +0.610 |
Neg logit contributions | |
enthal | -0.778 |
carbohyd | -0.706 |
sted | -0.704 |
deceive | -0.673 |
cius | -0.666 |
Token | selling |
Token ID | 16473 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Adidas | +0.668 |
Rust | +0.663 |
aila | +0.661 |
Pak | +0.656 |
bub | +0.656 |
Neg logit contributions | |
enthal | -0.769 |
carbohyd | -0.697 |
sted | -0.695 |
deceive | -0.664 |
cius | -0.655 |
Token | � |
Token ID | 447 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
Adidas | +0.735 |
Rust | +0.727 |
aila | +0.723 |
Pak | +0.718 |
bub | +0.712 |
Neg logit contributions | |
enthal | -0.869 |
sted | -0.789 |
carbohyd | -0.779 |
deceive | -0.749 |
cius | -0.746 |
Token | � |
Token ID | 251 |
Feature activation | +3.91e-03 |
Pos logit contributions | |
Adidas | +0.133 |
Rust | +0.132 |
aila | +0.131 |
Pak | +0.130 |
bub | +0.130 |
Neg logit contributions | |
enthal | -0.107 |
sted | -0.094 |
carbohyd | -0.093 |
deceive | -0.089 |
cius | -0.088 |
Token | fetal |
Token ID | 27652 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Adidas | +0.009 |
Rust | +0.009 |
aila | +0.009 |
Pak | +0.009 |
bub | +0.009 |
Neg logit contributions | |
enthal | -0.010 |
sted | -0.009 |
carbohyd | -0.009 |
deceive | -0.008 |
cius | -0.008 |
Token | tissue |
Token ID | 10712 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
enthal | +4.367 |
sted | +4.008 |
carbohyd | +3.976 |
ares | +3.852 |
deceive | +3.803 |
Neg logit contributions | |
aila | -3.174 |
Adidas | -3.155 |
Rust | -3.132 |
bub | -3.097 |
Pak | -3.057 |
Token | . |
Token ID | 13 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
enthal | +0.727 |
sted | +0.650 |
carbohyd | +0.639 |
deceive | +0.617 |
ares | +0.609 |
Neg logit contributions | |
Adidas | -0.708 |
Rust | -0.701 |
aila | -0.700 |
bub | -0.693 |
Pak | -0.691 |
Token | With |
Token ID | 2080 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Adidas | +0.100 |
Rust | +0.099 |
aila | +0.098 |
Pak | +0.098 |
bub | +0.097 |
Neg logit contributions | |
enthal | -0.098 |
carbohyd | -0.088 |
sted | -0.088 |
deceive | -0.083 |
cius | -0.083 |
Token | Republicans |
Token ID | 4734 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
enthal | +0.254 |
sted | +0.230 |
carbohyd | +0.226 |
deceive | +0.217 |
cius | +0.215 |
Neg logit contributions | |
Adidas | -0.240 |
Rust | -0.238 |
aila | -0.237 |
Pak | -0.234 |
bub | -0.234 |
Token | using |
Token ID | 1262 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
enthal | +0.234 |
sted | +0.212 |
carbohyd | +0.208 |
deceive | +0.200 |
cius | +0.199 |
Neg logit contributions | |
Adidas | -0.209 |
Rust | -0.207 |
aila | -0.206 |
Pak | -0.204 |
bub | -0.204 |
Token | Research |
Token ID | 4992 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
enthal | +2.334 |
sted | +2.091 |
carbohyd | +2.021 |
deceive | +1.954 |
cius | +1.933 |
Neg logit contributions | |
Adidas | -2.665 |
Rust | -2.639 |
aila | -2.638 |
bub | -2.609 |
Pak | -2.602 |
Token | Institute |
Token ID | 5136 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
enthal | +0.140 |
sted | +0.125 |
carbohyd | +0.124 |
deceive | +0.118 |
cius | +0.117 |
Neg logit contributions | |
Adidas | -0.151 |
Rust | -0.150 |
aila | -0.149 |
Pak | -0.148 |
bub | -0.147 |
Token | and |
Token ID | 290 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
enthal | +0.793 |
sted | +0.718 |
carbohyd | +0.710 |
deceive | +0.681 |
cius | +0.676 |
Neg logit contributions | |
Adidas | -0.688 |
Rust | -0.680 |
aila | -0.678 |
Pak | -0.670 |
bub | -0.669 |
Token | North |
Token ID | 2258 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
enthal | +0.985 |
sted | +0.888 |
carbohyd | +0.873 |
deceive | +0.839 |
cius | +0.832 |
Neg logit contributions | |
Adidas | -0.954 |
Rust | -0.945 |
aila | -0.944 |
Pak | -0.933 |
bub | -0.931 |
Token | American |
Token ID | 1605 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
Adidas | +0.503 |
Rust | +0.499 |
aila | +0.495 |
Pak | +0.489 |
bub | +0.488 |
Neg logit contributions | |
enthal | -0.661 |
carbohyd | -0.601 |
sted | -0.600 |
deceive | -0.577 |
cius | -0.570 |
Token | Bear |
Token ID | 14732 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
enthal | +1.001 |
sted | +0.900 |
carbohyd | +0.876 |
deceive | +0.844 |
cius | +0.838 |
Neg logit contributions | |
Adidas | -1.071 |
aila | -1.065 |
Rust | -1.061 |
Pak | -1.050 |
bub | -1.049 |
Token | Center |
Token ID | 3337 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
enthal | +3.252 |
sted | +2.912 |
carbohyd | +2.711 |
ares | +2.708 |
Admission | +2.702 |
Neg logit contributions | |
aila | -4.097 |
Adidas | -4.068 |
Rust | -4.035 |
bub | -3.982 |
Pak | -3.963 |
Token |
|
Token ID | 198 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
enthal | +1.627 |
sted | +1.477 |
carbohyd | +1.439 |
deceive | +1.393 |
cius | +1.382 |
Neg logit contributions | |
Adidas | -1.486 |
aila | -1.470 |
Rust | -1.469 |
Pak | -1.450 |
bub | -1.446 |
Token |
|
Token ID | 198 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
enthal | +1.205 |
sted | +1.094 |
ares | +1.013 |
deceive | +1.011 |
cius | +1.007 |
Neg logit contributions | |
Adidas | -1.183 |
Rust | -1.170 |
aila | -1.170 |
bub | -1.152 |
Pak | -1.149 |
Token | All |
Token ID | 3237 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
enthal | +0.868 |
sted | +0.797 |
carbohyd | +0.762 |
cius | +0.745 |
ares | +0.743 |
Neg logit contributions | |
Adidas | -0.719 |
aila | -0.701 |
Rust | -0.692 |
bub | -0.686 |
Pak | -0.684 |
Token | photos |
Token ID | 5205 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
enthal | +0.526 |
sted | +0.476 |
carbohyd | +0.470 |
deceive | +0.451 |
cius | +0.448 |
Neg logit contributions | |
Adidas | -0.466 |
Rust | -0.461 |
aila | -0.460 |
Pak | -0.454 |
bub | -0.453 |
Token | release |
Token ID | 2650 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
Adidas | +0.199 |
Rust | +0.196 |
aila | +0.195 |
bub | +0.193 |
Pak | +0.193 |
Neg logit contributions | |
enthal | -0.176 |
sted | -0.157 |
carbohyd | -0.155 |
cius | -0.147 |
deceive | -0.147 |
Token | date |
Token ID | 3128 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
enthal | +1.116 |
sted | +0.987 |
carbohyd | +0.960 |
deceive | +0.928 |
cius | +0.913 |
Neg logit contributions | |
Rust | -1.339 |
Adidas | -1.338 |
aila | -1.334 |
Pak | -1.320 |
bub | -1.312 |
Token | for |
Token ID | 329 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
enthal | +0.754 |
sted | +0.683 |
carbohyd | +0.667 |
deceive | +0.648 |
cius | +0.641 |
Neg logit contributions | |
Adidas | -0.645 |
Rust | -0.644 |
aila | -0.642 |
Pak | -0.634 |
bub | -0.631 |
Token | " |
Token ID | 366 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
enthal | +0.429 |
sted | +0.385 |
carbohyd | +0.378 |
deceive | +0.362 |
cius | +0.359 |
Neg logit contributions | |
Adidas | -0.452 |
Rust | -0.449 |
aila | -0.448 |
Pak | -0.443 |
bub | -0.442 |
Token | Final |
Token ID | 19006 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Adidas | +0.329 |
Rust | +0.325 |
aila | +0.324 |
Pak | +0.320 |
bub | +0.319 |
Neg logit contributions | |
enthal | -0.434 |
sted | -0.395 |
carbohyd | -0.391 |
deceive | -0.376 |
cius | -0.374 |
Token | Fantasy |
Token ID | 10982 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Adidas | +0.280 |
Rust | +0.276 |
aila | +0.274 |
Pak | +0.272 |
bub | +0.271 |
Neg logit contributions | |
enthal | -0.306 |
carbohyd | -0.277 |
sted | -0.276 |
deceive | -0.262 |
cius | -0.261 |
Token | V |
Token ID | 569 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
enthal | +2.833 |
sted | +2.491 |
ares | +2.309 |
deceive | +2.299 |
carbohyd | +2.289 |
Neg logit contributions | |
aila | -4.320 |
Rust | -4.280 |
Adidas | -4.256 |
Pak | -4.221 |
bub | -4.210 |
Token | X |
Token ID | 55 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
Adidas | +0.358 |
Rust | +0.354 |
aila | +0.352 |
Pak | +0.348 |
bub | +0.347 |
Neg logit contributions | |
enthal | -0.506 |
sted | -0.462 |
carbohyd | -0.457 |
deceive | -0.441 |
cius | -0.438 |
Token | " |
Token ID | 1 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Adidas | +0.831 |
Rust | +0.822 |
aila | +0.816 |
Pak | +0.807 |
bub | +0.807 |
Neg logit contributions | |
enthal | -1.024 |
sted | -0.931 |
carbohyd | -0.924 |
deceive | -0.885 |
cius | -0.881 |
Token | will |
Token ID | 481 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
enthal | +0.492 |
sted | +0.445 |
carbohyd | +0.437 |
deceive | +0.423 |
cius | +0.419 |
Neg logit contributions | |
Adidas | -0.423 |
Rust | -0.419 |
aila | -0.418 |
Pak | -0.413 |
bub | -0.412 |
Token | be |
Token ID | 307 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
Adidas | +1.914 |
aila | +1.874 |
Rust | +1.872 |
Pak | +1.845 |
bub | +1.843 |
Neg logit contributions | |
enthal | -2.731 |
carbohyd | -2.490 |
sted | -2.489 |
cius | -2.370 |
ares | -2.352 |