Token | : |
Token ID | 25 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
ortunate | +1.353 |
ciating | +1.306 |
udo | +1.305 |
lasses | +1.282 |
abouts | +1.262 |
Neg logit contributions | |
Pand | -1.040 |
LOAD | -1.029 |
democrat | -0.982 |
mat | -0.970 |
Hunt | -0.955 |
Token |
|
Token ID | 198 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ortunate | +0.754 |
ciating | +0.730 |
udo | +0.730 |
lasses | +0.715 |
abouts | +0.704 |
Neg logit contributions | |
Pand | -0.552 |
LOAD | -0.543 |
democrat | -0.515 |
mat | -0.513 |
Hunt | -0.505 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Pand | +0.156 |
LOAD | +0.154 |
mat | +0.146 |
democrat | +0.143 |
Hunt | +0.142 |
Neg logit contributions | |
ortunate | -0.258 |
ciating | -0.255 |
udo | -0.247 |
lasses | -0.245 |
abouts | -0.241 |
Token | 13 |
Token ID | 1485 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Pand | +0.105 |
LOAD | +0.104 |
democrat | +0.100 |
mat | +0.098 |
Hunt | +0.096 |
Neg logit contributions | |
ortunate | -0.148 |
ciating | -0.144 |
udo | -0.143 |
lasses | -0.141 |
abouts | -0.139 |
Token | PH |
Token ID | 9370 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
ortunate | +1.412 |
udo | +1.354 |
ciating | +1.348 |
lasses | +1.319 |
abouts | +1.298 |
Neg logit contributions | |
Pand | -1.386 |
LOAD | -1.372 |
democrat | -1.305 |
mat | -1.304 |
Hunt | -1.291 |
Token | OTOS |
Token ID | 33291 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Pand | +0.028 |
LOAD | +0.028 |
democrat | +0.026 |
mat | +0.026 |
Hunt | +0.025 |
Neg logit contributions | |
ortunate | -0.051 |
ciating | -0.049 |
udo | -0.049 |
lasses | -0.048 |
abouts | -0.048 |
Token | Donald |
Token ID | 3759 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
LOAD | +5.335 |
Pand | +5.200 |
Hel | +5.134 |
hide | +4.910 |
mat | +4.879 |
Neg logit contributions | |
ortunate | -8.553 |
ciating | -8.515 |
lasses | -8.156 |
udo | -7.825 |
abouts | -7.736 |
Token | Trump |
Token ID | 1301 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
ortunate | +3.122 |
udo | +3.019 |
ciating | +3.018 |
lasses | +2.962 |
abouts | +2.921 |
Neg logit contributions | |
Pand | -2.224 |
LOAD | -2.201 |
democrat | -2.093 |
mat | -2.063 |
Hunt | -2.031 |
Token | 's |
Token ID | 338 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ortunate | +1.825 |
udo | +1.780 |
ciating | +1.756 |
lasses | +1.735 |
abouts | +1.731 |
Neg logit contributions | |
Pand | -1.465 |
LOAD | -1.437 |
democrat | -1.354 |
mat | -1.351 |
Hunt | -1.349 |
Token | potential |
Token ID | 2785 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
ortunate | +1.027 |
ciating | +0.993 |
udo | +0.992 |
lasses | +0.976 |
abouts | +0.965 |
Neg logit contributions | |
Pand | -0.743 |
LOAD | -0.736 |
democrat | -0.697 |
mat | -0.693 |
Hunt | -0.683 |
Token | running |
Token ID | 2491 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
ortunate | +0.927 |
ciating | +0.902 |
udo | +0.899 |
lasses | +0.887 |
abouts | +0.875 |
Neg logit contributions | |
Pand | -0.465 |
LOAD | -0.459 |
democrat | -0.432 |
mat | -0.425 |
Hunt | -0.416 |
Token | radically |
Token ID | 25330 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
ortunate | +1.079 |
udo | +1.044 |
ciating | +1.040 |
lasses | +1.021 |
abouts | +1.011 |
Neg logit contributions | |
Pand | -0.866 |
LOAD | -0.858 |
democrat | -0.816 |
mat | -0.806 |
Hunt | -0.795 |
Token | around |
Token ID | 1088 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
Pand | +0.083 |
LOAD | +0.082 |
democrat | +0.079 |
mat | +0.078 |
Hunt | +0.077 |
Neg logit contributions | |
ortunate | -0.094 |
ciating | -0.091 |
udo | -0.090 |
lasses | -0.089 |
abouts | -0.087 |
Token | Mont |
Token ID | 5575 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
Pand | +0.341 |
LOAD | +0.338 |
democrat | +0.325 |
mat | +0.321 |
Hunt | +0.316 |
Neg logit contributions | |
ortunate | -0.365 |
ciating | -0.353 |
udo | -0.351 |
lasses | -0.345 |
abouts | -0.339 |
Token | a |
Token ID | 64 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
Pand | +1.995 |
LOAD | +1.939 |
mat | +1.931 |
democrat | +1.881 |
hide | +1.844 |
Neg logit contributions | |
ciating | -3.687 |
ortunate | -3.642 |
udo | -3.503 |
lasses | -3.451 |
abouts | -3.371 |
Token | as |
Token ID | 355 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Pand | +0.299 |
LOAD | +0.297 |
democrat | +0.283 |
mat | +0.280 |
Hunt | +0.275 |
Neg logit contributions | |
ortunate | -0.328 |
udo | -0.317 |
ciating | -0.316 |
lasses | -0.309 |
abouts | -0.306 |
Token | either |
Token ID | 2035 |
Feature activation | +9.26e+00 |
Pos logit contributions | |
ortunate | +0.199 |
ciating | +0.192 |
udo | +0.191 |
lasses | +0.187 |
abouts | +0.184 |
Neg logit contributions | |
Pand | -0.189 |
LOAD | -0.188 |
democrat | -0.179 |
mat | -0.177 |
Hunt | -0.175 |
Token | the |
Token ID | 262 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
democrat | +5.379 |
Pand | +5.330 |
Hel | +5.242 |
mat | +5.130 |
LOAD | +5.111 |
Neg logit contributions | |
ortunate | -7.290 |
ciating | -7.190 |
lasses | -6.958 |
udo | -6.899 |
abouts | -6.708 |
Token | point |
Token ID | 966 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Pand | +1.550 |
LOAD | +1.525 |
democrat | +1.496 |
mat | +1.466 |
apopt | +1.424 |
Neg logit contributions | |
ortunate | -2.196 |
ciating | -2.137 |
udo | -2.119 |
lasses | -2.091 |
abouts | -2.049 |
Token | guard |
Token ID | 4860 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
ortunate | +1.170 |
ciating | +1.135 |
udo | +1.131 |
lasses | +1.113 |
abouts | +1.099 |
Neg logit contributions | |
Pand | -0.756 |
LOAD | -0.747 |
democrat | -0.709 |
mat | -0.699 |
Hunt | -0.687 |
Token | or |
Token ID | 393 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
Pand | +0.575 |
LOAD | +0.569 |
democrat | +0.548 |
mat | +0.541 |
Hunt | +0.533 |
Neg logit contributions | |
ortunate | -0.632 |
ciating | -0.611 |
udo | -0.607 |
lasses | -0.597 |
abouts | -0.586 |
Token | a |
Token ID | 257 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
Pand | +0.397 |
LOAD | +0.393 |
democrat | +0.380 |
mat | +0.374 |
Hunt | +0.367 |
Neg logit contributions | |
ortunate | -0.482 |
ciating | -0.467 |
udo | -0.463 |
lasses | -0.457 |
abouts | -0.448 |
Token | can |
Token ID | 460 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
ortunate | +0.635 |
udo | +0.610 |
ciating | +0.610 |
lasses | +0.600 |
abouts | +0.594 |
Neg logit contributions | |
Pand | -0.520 |
LOAD | -0.515 |
democrat | -0.490 |
mat | -0.483 |
Hunt | -0.479 |
Token | swing |
Token ID | 9628 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Pand | +1.444 |
LOAD | +1.437 |
democrat | +1.402 |
mat | +1.375 |
Hunt | +1.334 |
Neg logit contributions | |
ortunate | -1.766 |
ciating | -1.740 |
udo | -1.710 |
lasses | -1.681 |
abouts | -1.646 |
Token | five |
Token ID | 1936 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Pand | +1.215 |
LOAD | +1.198 |
democrat | +1.156 |
mat | +1.144 |
Hunt | +1.119 |
Neg logit contributions | |
ortunate | -1.342 |
ciating | -1.310 |
udo | -1.291 |
lasses | -1.262 |
abouts | -1.237 |
Token | days |
Token ID | 1528 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Pand | +0.748 |
LOAD | +0.736 |
democrat | +0.713 |
mat | +0.702 |
Hunt | +0.685 |
Neg logit contributions | |
ortunate | -0.925 |
ciating | -0.895 |
udo | -0.889 |
lasses | -0.876 |
abouts | -0.860 |
Token | in |
Token ID | 287 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
LOAD | +0.982 |
Pand | +0.981 |
democrat | +0.943 |
mat | +0.933 |
Hunt | +0.910 |
Neg logit contributions | |
ortunate | -1.175 |
ciating | -1.146 |
udo | -1.126 |
lasses | -1.111 |
abouts | -1.080 |
Token | either |
Token ID | 2035 |
Feature activation | +8.82e+00 |
Pos logit contributions | |
Pand | +1.874 |
LOAD | +1.858 |
democrat | +1.798 |
mat | +1.769 |
Hunt | +1.748 |
Neg logit contributions | |
ortunate | -2.314 |
ciating | -2.262 |
udo | -2.219 |
lasses | -2.192 |
abouts | -2.147 |
Token | direction |
Token ID | 4571 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Pand | +4.821 |
democrat | +4.816 |
LOAD | +4.663 |
Hunt | +4.542 |
Hel | +4.537 |
Neg logit contributions | |
ortunate | -7.340 |
ciating | -7.292 |
udo | -7.000 |
lasses | -6.888 |
abouts | -6.857 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ortunate | +0.766 |
ciating | +0.737 |
udo | +0.734 |
lasses | +0.723 |
abouts | +0.713 |
Neg logit contributions | |
Pand | -0.757 |
LOAD | -0.750 |
democrat | -0.719 |
mat | -0.711 |
Hunt | -0.703 |
Token | � |
Token ID | 564 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
Pand | +0.647 |
LOAD | +0.635 |
mat | +0.602 |
democrat | +0.602 |
Hunt | +0.592 |
Neg logit contributions | |
ortunate | -0.903 |
ciating | -0.877 |
udo | -0.868 |
lasses | -0.858 |
abouts | -0.842 |
Token | � |
Token ID | 250 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ortunate | +0.383 |
ciating | +0.375 |
udo | +0.367 |
lasses | +0.364 |
abouts | +0.359 |
Neg logit contributions | |
Pand | -0.313 |
LOAD | -0.311 |
democrat | -0.295 |
mat | -0.294 |
Hunt | -0.290 |
Token | If |
Token ID | 1532 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
ortunate | +0.302 |
ciating | +0.293 |
udo | +0.291 |
lasses | +0.286 |
abouts | +0.281 |
Neg logit contributions | |
Pand | -0.243 |
LOAD | -0.240 |
democrat | -0.228 |
mat | -0.227 |
Hunt | -0.224 |
Token | source |
Token ID | 2723 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Pand | +0.128 |
LOAD | +0.127 |
democrat | +0.122 |
mat | +0.120 |
Hunt | +0.118 |
Neg logit contributions | |
ortunate | -0.159 |
ciating | -0.154 |
udo | -0.153 |
lasses | -0.151 |
abouts | -0.148 |
Token | of |
Token ID | 286 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ortunate | +0.954 |
ciating | +0.923 |
udo | +0.923 |
lasses | +0.905 |
abouts | +0.898 |
Neg logit contributions | |
Pand | -0.802 |
LOAD | -0.793 |
democrat | -0.753 |
mat | -0.746 |
Hunt | -0.737 |
Token | the |
Token ID | 262 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
ortunate | +0.816 |
ciating | +0.787 |
udo | +0.782 |
lasses | +0.768 |
abouts | +0.757 |
Neg logit contributions | |
Pand | -0.824 |
LOAD | -0.820 |
democrat | -0.786 |
mat | -0.778 |
Hunt | -0.769 |
Token | data |
Token ID | 1366 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
ortunate | +0.616 |
ciating | +0.596 |
udo | +0.593 |
lasses | +0.583 |
abouts | +0.574 |
Neg logit contributions | |
Pand | -0.526 |
LOAD | -0.522 |
democrat | -0.499 |
mat | -0.494 |
Hunt | -0.487 |
Token | , |
Token ID | 11 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Pand | +0.323 |
LOAD | +0.320 |
democrat | +0.307 |
mat | +0.304 |
Hunt | +0.299 |
Neg logit contributions | |
ortunate | -0.363 |
ciating | -0.351 |
udo | -0.349 |
lasses | -0.343 |
abouts | -0.337 |
Token | either |
Token ID | 2035 |
Feature activation | +8.67e+00 |
Pos logit contributions | |
Pand | +0.222 |
LOAD | +0.220 |
democrat | +0.212 |
mat | +0.209 |
Hunt | +0.206 |
Neg logit contributions | |
ortunate | -0.253 |
ciating | -0.244 |
udo | -0.243 |
lasses | -0.239 |
abouts | -0.235 |
Token | .) |
Token ID | 2014 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
Pand | +5.349 |
LOAD | +5.319 |
democrat | +5.159 |
mat | +5.077 |
Hunt | +4.932 |
Neg logit contributions | |
ortunate | -6.728 |
ciating | -6.509 |
udo | -6.432 |
lasses | -6.403 |
abouts | -6.142 |
Token | : |
Token ID | 1058 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
Pand | +0.021 |
LOAD | +0.021 |
democrat | +0.020 |
mat | +0.019 |
Hunt | +0.019 |
Neg logit contributions | |
ortunate | -0.024 |
ciating | -0.024 |
udo | -0.023 |
lasses | -0.023 |
abouts | -0.023 |
Token | This |
Token ID | 770 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Pand | +0.257 |
LOAD | +0.254 |
democrat | +0.244 |
mat | +0.241 |
Hunt | +0.237 |
Neg logit contributions | |
ortunate | -0.292 |
ciating | -0.283 |
udo | -0.281 |
lasses | -0.276 |
abouts | -0.271 |
Token | can |
Token ID | 460 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
Pand | +0.139 |
LOAD | +0.138 |
democrat | +0.132 |
mat | +0.130 |
Hunt | +0.128 |
Neg logit contributions | |
ortunate | -0.179 |
ciating | -0.174 |
udo | -0.173 |
lasses | -0.170 |
abouts | -0.168 |
Token | also |
Token ID | 635 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
Pand | +1.654 |
LOAD | +1.642 |
democrat | +1.605 |
mat | +1.583 |
Hunt | +1.540 |
Neg logit contributions | |
ortunate | -1.496 |
ciating | -1.459 |
udo | -1.432 |
lasses | -1.406 |
abouts | -1.378 |
Token | was |
Token ID | 373 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
Pand | +0.017 |
LOAD | +0.017 |
democrat | +0.016 |
mat | +0.016 |
Hunt | +0.015 |
Neg logit contributions | |
ortunate | -0.022 |
udo | -0.021 |
ciating | -0.021 |
lasses | -0.021 |
abouts | -0.020 |
Token | not |
Token ID | 407 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ortunate | +0.282 |
ciating | +0.271 |
udo | +0.271 |
lasses | +0.266 |
abouts | +0.262 |
Neg logit contributions | |
Pand | -0.242 |
LOAD | -0.239 |
democrat | -0.229 |
mat | -0.226 |
Hunt | -0.223 |
Token | affiliated |
Token ID | 18552 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Pand | +0.851 |
LOAD | +0.842 |
democrat | +0.810 |
mat | +0.799 |
Hunt | +0.779 |
Neg logit contributions | |
ortunate | -1.105 |
ciating | -1.078 |
udo | -1.064 |
lasses | -1.054 |
abouts | -1.027 |
Token | with |
Token ID | 351 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
ortunate | +2.134 |
ciating | +2.061 |
udo | +2.006 |
lasses | +1.981 |
abouts | +1.978 |
Neg logit contributions | |
LOAD | -2.324 |
Pand | -2.321 |
democrat | -2.177 |
hide | -2.149 |
Hunt | -2.149 |
Token | Sky |
Token ID | 5274 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Pand | +0.653 |
LOAD | +0.645 |
democrat | +0.621 |
mat | +0.615 |
Hunt | +0.605 |
Neg logit contributions | |
ortunate | -0.687 |
ciating | -0.665 |
udo | -0.660 |
lasses | -0.649 |
abouts | -0.636 |
Token | High |
Token ID | 3334 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
Pand | +1.299 |
LOAD | +1.284 |
democrat | +1.211 |
mat | +1.189 |
Hunt | +1.162 |
Neg logit contributions | |
ortunate | -2.537 |
ciating | -2.468 |
udo | -2.459 |
lasses | -2.422 |
abouts | -2.393 |
Token | Hol |
Token ID | 6479 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
LOAD | +3.900 |
Pand | +3.886 |
Hel | +3.680 |
mat | +3.661 |
democrat | +3.657 |
Neg logit contributions | |
ortunate | -7.986 |
ciating | -7.868 |
udo | -7.742 |
lasses | -7.696 |
abouts | -7.475 |
Token | istic |
Token ID | 2569 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
mat | +1.637 |
Pand | +1.604 |
LOAD | +1.594 |
democrat | +1.535 |
hide | +1.531 |
Neg logit contributions | |
ciating | -2.205 |
ortunate | -2.172 |
lasses | -2.093 |
udo | -2.053 |
abouts | -2.023 |
Token | but |
Token ID | 475 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Pand | +0.182 |
LOAD | +0.181 |
democrat | +0.173 |
mat | +0.171 |
Hunt | +0.169 |
Neg logit contributions | |
ortunate | -0.198 |
ciating | -0.191 |
udo | -0.190 |
lasses | -0.187 |
abouts | -0.184 |
Token | lost |
Token ID | 2626 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
Pand | +0.116 |
LOAD | +0.115 |
democrat | +0.110 |
mat | +0.108 |
Hunt | +0.107 |
Neg logit contributions | |
ortunate | -0.151 |
ciating | -0.146 |
udo | -0.145 |
lasses | -0.143 |
abouts | -0.141 |
Token | power |
Token ID | 1176 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
Pand | +0.011 |
LOAD | +0.011 |
democrat | +0.011 |
mat | +0.011 |
Hunt | +0.010 |
Neg logit contributions | |
ortunate | -0.012 |
ciating | -0.011 |
udo | -0.011 |
lasses | -0.011 |
abouts | -0.011 |
Token | image |
Token ID | 2939 |
Feature activation | +7.72e+00 |
Pos logit contributions | |
Pand | +1.117 |
LOAD | +1.068 |
democrat | +1.047 |
mat | +1.007 |
Hel | +0.983 |
Neg logit contributions | |
ortunate | -3.087 |
ciating | -3.057 |
udo | -2.981 |
abouts | -2.965 |
lasses | -2.943 |
Token |
|
Token ID | 198 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
LOAD | +3.226 |
Hel | +3.098 |
Pand | +3.080 |
mat | +2.974 |
hide | +2.940 |
Neg logit contributions | |
ciating | -7.885 |
ortunate | -7.840 |
abouts | -7.560 |
udo | -7.361 |
lasses | -7.323 |
Token |
|
Token ID | 198 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
Pand | +2.197 |
LOAD | +2.133 |
mat | +2.076 |
hide | +1.999 |
Hel | +1.965 |
Neg logit contributions | |
ciating | -4.901 |
ortunate | -4.790 |
lasses | -4.526 |
udo | -4.524 |
abouts | -4.449 |
Token | larg |
Token ID | 15521 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Pand | +3.053 |
LOAD | +2.988 |
mat | +2.846 |
hide | +2.697 |
democrat | +2.650 |
Neg logit contributions | |
ortunate | -5.080 |
ciating | -5.033 |
udo | -4.989 |
lasses | -4.905 |
abouts | -4.716 |
Token | er |
Token ID | 263 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
LOAD | +1.001 |
Pand | +0.990 |
democrat | +0.921 |
mat | +0.918 |
Hel | +0.853 |
Neg logit contributions | |
ortunate | -2.932 |
ciating | -2.915 |
abouts | -2.834 |
udo | -2.797 |
lasses | -2.797 |
Token | image |
Token ID | 2939 |
Feature activation | +8.54e+00 |
Pos logit contributions | |
Pand | +2.033 |
LOAD | +1.943 |
mat | +1.874 |
hide | +1.858 |
democrat | +1.848 |
Neg logit contributions | |
ciating | -7.017 |
ortunate | -6.878 |
udo | -6.687 |
abouts | -6.686 |
lasses | -6.639 |
Token | T |
Token ID | 309 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
LOAD | +3.379 |
mat | +3.227 |
Hel | +3.223 |
hide | +3.193 |
Pand | +3.076 |
Neg logit contributions | |
ortunate | -8.769 |
ciating | -8.762 |
abouts | -8.716 |
lasses | -8.448 |
udo | -8.217 |
Token | IFF |
Token ID | 29267 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
LOAD | +1.582 |
democrat | +1.516 |
Pand | +1.455 |
mat | +1.438 |
exodus | +1.389 |
Neg logit contributions | |
ciating | -4.164 |
ortunate | -4.106 |
abouts | -4.000 |
lasses | -3.947 |
udo | -3.905 |
Token | original |
Token ID | 2656 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
Pand | +2.386 |
LOAD | +2.380 |
democrat | +2.331 |
mat | +2.278 |
Hel | +2.250 |
Neg logit contributions | |
abouts | -4.103 |
ortunate | -4.091 |
lasses | -4.053 |
ciating | -4.049 |
udo | -4.020 |
Token | image |
Token ID | 2939 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
LOAD | +1.391 |
Pand | +1.366 |
democrat | +1.348 |
mat | +1.280 |
hide | +1.253 |
Neg logit contributions | |
ortunate | -4.057 |
ciating | -3.974 |
udo | -3.889 |
abouts | -3.873 |
lasses | -3.863 |
Token | Download |
Token ID | 10472 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
LOAD | +3.201 |
hide | +3.038 |
Hel | +2.971 |
Pand | +2.957 |
mat | +2.940 |
Neg logit contributions | |
ortunate | -4.852 |
ciating | -4.805 |
abouts | -4.760 |
lasses | -4.653 |
udo | -4.579 |
Token | doing |
Token ID | 1804 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
ortunate | +2.013 |
ciating | +1.931 |
udo | +1.930 |
lasses | +1.893 |
abouts | +1.880 |
Neg logit contributions | |
Pand | -1.629 |
LOAD | -1.608 |
democrat | -1.525 |
mat | -1.519 |
Hunt | -1.497 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ortunate | +2.268 |
ciating | +2.176 |
udo | +2.175 |
abouts | +2.154 |
lasses | +2.137 |
Neg logit contributions | |
Pand | -2.077 |
LOAD | -2.053 |
mat | -1.924 |
democrat | -1.910 |
Hunt | -1.908 |
Token | the |
Token ID | 262 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
ortunate | +0.812 |
ciating | +0.782 |
udo | +0.779 |
lasses | +0.766 |
abouts | +0.755 |
Neg logit contributions | |
Pand | -0.727 |
LOAD | -0.721 |
democrat | -0.688 |
mat | -0.682 |
Hunt | -0.672 |
Token | indigenous |
Token ID | 17673 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ortunate | +0.642 |
ciating | +0.620 |
udo | +0.617 |
lasses | +0.608 |
abouts | +0.599 |
Neg logit contributions | |
Pand | -0.517 |
LOAD | -0.511 |
democrat | -0.487 |
mat | -0.482 |
Hunt | -0.476 |
Token | population |
Token ID | 3265 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Pand | +0.733 |
LOAD | +0.726 |
democrat | +0.700 |
mat | +0.687 |
Hunt | +0.673 |
Neg logit contributions | |
ortunate | -0.977 |
ciating | -0.948 |
udo | -0.938 |
lasses | -0.926 |
abouts | -0.905 |
Token | either |
Token ID | 2035 |
Feature activation | +8.47e+00 |
Pos logit contributions | |
Pand | +0.790 |
LOAD | +0.783 |
democrat | +0.754 |
mat | +0.743 |
Hunt | +0.730 |
Neg logit contributions | |
ortunate | -0.946 |
ciating | -0.919 |
udo | -0.911 |
lasses | -0.900 |
abouts | -0.877 |
Token | lack |
Token ID | 3092 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
democrat | +4.872 |
LOAD | +4.765 |
Pand | +4.717 |
donated | +4.646 |
exodus | +4.641 |
Neg logit contributions | |
ortunate | -6.888 |
ciating | -6.837 |
lasses | -6.669 |
udo | -6.614 |
rious | -6.218 |
Token | the |
Token ID | 262 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
Pand | +1.105 |
LOAD | +1.100 |
democrat | +1.062 |
mat | +1.046 |
Hunt | +1.021 |
Neg logit contributions | |
ortunate | -1.255 |
ciating | -1.218 |
udo | -1.214 |
lasses | -1.187 |
abouts | -1.167 |
Token | skills |
Token ID | 4678 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Pand | +0.436 |
LOAD | +0.434 |
democrat | +0.421 |
mat | +0.413 |
Hunt | +0.404 |
Neg logit contributions | |
ortunate | -0.475 |
ciating | -0.460 |
udo | -0.460 |
lasses | -0.449 |
abouts | -0.441 |
Token | to |
Token ID | 284 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ortunate | +0.312 |
ciating | +0.302 |
udo | +0.300 |
lasses | +0.295 |
abouts | +0.290 |
Neg logit contributions | |
Pand | -0.272 |
LOAD | -0.269 |
democrat | -0.258 |
mat | -0.255 |
Hunt | -0.251 |
Token | do |
Token ID | 466 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ortunate | +1.362 |
ciating | +1.316 |
udo | +1.311 |
lasses | +1.289 |
abouts | +1.269 |
Neg logit contributions | |
Pand | -1.135 |
LOAD | -1.124 |
democrat | -1.075 |
mat | -1.063 |
Hunt | -1.046 |
Token | are |
Token ID | 389 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Pand | +0.755 |
LOAD | +0.751 |
democrat | +0.727 |
mat | +0.716 |
Hunt | +0.699 |
Neg logit contributions | |
ortunate | -0.856 |
ciating | -0.829 |
udo | -0.820 |
lasses | -0.807 |
abouts | -0.792 |
Token | there |
Token ID | 612 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ortunate | +1.165 |
ciating | +1.124 |
udo | +1.122 |
lasses | +1.101 |
abouts | +1.086 |
Neg logit contributions | |
Pand | -1.041 |
LOAD | -1.030 |
democrat | -0.983 |
mat | -0.975 |
Hunt | -0.964 |
Token | at |
Token ID | 379 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ortunate | +0.865 |
ciating | +0.836 |
udo | +0.834 |
lasses | +0.819 |
abouts | +0.812 |
Neg logit contributions | |
Pand | -0.744 |
LOAD | -0.735 |
democrat | -0.704 |
mat | -0.696 |
Hunt | -0.688 |
Token | 16 |
Token ID | 1467 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
Pand | +0.148 |
LOAD | +0.146 |
democrat | +0.140 |
mat | +0.138 |
Hunt | +0.136 |
Neg logit contributions | |
ortunate | -0.193 |
ciating | -0.187 |
udo | -0.187 |
lasses | -0.184 |
abouts | -0.181 |
Token | 80 |
Token ID | 1795 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
Pand | +1.604 |
LOAD | +1.593 |
democrat | +1.529 |
mat | +1.517 |
Hunt | +1.479 |
Neg logit contributions | |
ortunate | -1.989 |
ciating | -1.926 |
udo | -1.914 |
lasses | -1.880 |
abouts | -1.847 |
Token | x |
Token ID | 87 |
Feature activation | +8.45e+00 |
Pos logit contributions | |
Pand | +2.496 |
LOAD | +2.465 |
democrat | +2.364 |
mat | +2.361 |
Hunt | +2.292 |
Neg logit contributions | |
ortunate | -2.987 |
ciating | -2.898 |
udo | -2.876 |
lasses | -2.826 |
abouts | -2.780 |
Token | 10 |
Token ID | 940 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
Pand | +4.726 |
LOAD | +4.686 |
mat | +4.525 |
democrat | +4.453 |
Hunt | +4.364 |
Neg logit contributions | |
ortunate | -7.031 |
ciating | -6.889 |
lasses | -6.639 |
udo | -6.614 |
abouts | -6.584 |
Token | 50 |
Token ID | 1120 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Pand | +2.008 |
LOAD | +1.924 |
democrat | +1.883 |
mat | +1.862 |
Hunt | +1.774 |
Neg logit contributions | |
ortunate | -3.896 |
ciating | -3.791 |
udo | -3.762 |
abouts | -3.642 |
lasses | -3.641 |
Token | the |
Token ID | 262 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Pand | +1.069 |
LOAD | +1.058 |
democrat | +1.012 |
mat | +1.001 |
Hunt | +0.981 |
Neg logit contributions | |
ortunate | -1.383 |
ciating | -1.339 |
udo | -1.332 |
lasses | -1.311 |
abouts | -1.289 |
Token | pixels |
Token ID | 17848 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Pand | +0.083 |
LOAD | +0.082 |
democrat | +0.078 |
mat | +0.077 |
Hunt | +0.076 |
Neg logit contributions | |
ortunate | -0.120 |
ciating | -0.116 |
udo | -0.116 |
lasses | -0.114 |
abouts | -0.112 |
Token | are |
Token ID | 389 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Pand | +1.461 |
LOAD | +1.451 |
democrat | +1.398 |
mat | +1.385 |
Hunt | +1.349 |
Neg logit contributions | |
ortunate | -1.768 |
ciating | -1.712 |
udo | -1.699 |
lasses | -1.677 |
abouts | -1.638 |
Token | t |
Token ID | 83 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Pand | +0.980 |
LOAD | +0.969 |
mat | +0.940 |
democrat | +0.931 |
Hunt | +0.908 |
Neg logit contributions | |
ortunate | -0.979 |
ciating | -0.955 |
udo | -0.940 |
lasses | -0.928 |
abouts | -0.907 |
Token | that |
Token ID | 326 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Pand | +0.802 |
LOAD | +0.793 |
democrat | +0.770 |
mat | +0.758 |
Hunt | +0.741 |
Neg logit contributions | |
ortunate | -0.869 |
ciating | -0.844 |
udo | -0.838 |
lasses | -0.825 |
abouts | -0.806 |
Token | critically |
Token ID | 19475 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Pand | +0.304 |
LOAD | +0.301 |
democrat | +0.290 |
mat | +0.286 |
Hunt | +0.280 |
Neg logit contributions | |
ortunate | -0.380 |
ciating | -0.368 |
udo | -0.366 |
lasses | -0.360 |
abouts | -0.354 |
Token | high |
Token ID | 1029 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
Pand | +0.200 |
LOAD | +0.198 |
democrat | +0.191 |
mat | +0.188 |
Hunt | +0.183 |
Neg logit contributions | |
ortunate | -0.259 |
ciating | -0.251 |
udo | -0.250 |
lasses | -0.246 |
abouts | -0.241 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Pand | +2.971 |
LOAD | +2.925 |
democrat | +2.878 |
mat | +2.827 |
apopt | +2.712 |
Neg logit contributions | |
ortunate | -3.681 |
ciating | -3.605 |
udo | -3.555 |
lasses | -3.532 |
abouts | -3.335 |
Token | either |
Token ID | 2035 |
Feature activation | +8.42e+00 |
Pos logit contributions | |
Pand | +1.047 |
LOAD | +1.035 |
democrat | +1.006 |
mat | +0.991 |
Hunt | +0.964 |
Neg logit contributions | |
ortunate | -1.199 |
ciating | -1.163 |
udo | -1.157 |
lasses | -1.139 |
abouts | -1.111 |
Token | . |
Token ID | 13 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Pand | +5.136 |
LOAD | +5.027 |
democrat | +4.959 |
mat | +4.910 |
Hunt | +4.677 |
Neg logit contributions | |
ortunate | -6.544 |
ciating | -6.451 |
udo | -6.298 |
lasses | -6.271 |
abouts | -5.958 |
Token | But |
Token ID | 887 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Pand | +1.646 |
LOAD | +1.619 |
mat | +1.550 |
democrat | +1.533 |
Hel | +1.515 |
Neg logit contributions | |
ortunate | -2.054 |
ciating | -1.999 |
udo | -1.947 |
lasses | -1.936 |
abouts | -1.897 |
Token | the |
Token ID | 262 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
Pand | +0.860 |
LOAD | +0.852 |
democrat | +0.825 |
mat | +0.812 |
Hunt | +0.795 |
Neg logit contributions | |
ortunate | -1.027 |
ciating | -0.998 |
udo | -0.988 |
lasses | -0.971 |
abouts | -0.950 |
Token | main |
Token ID | 1388 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
Pand | +0.246 |
LOAD | +0.244 |
democrat | +0.233 |
mat | +0.230 |
Hunt | +0.226 |
Neg logit contributions | |
ortunate | -0.333 |
ciating | -0.323 |
udo | -0.322 |
lasses | -0.316 |
abouts | -0.312 |
Token | reason |
Token ID | 1738 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Pand | +0.179 |
LOAD | +0.178 |
democrat | +0.171 |
mat | +0.169 |
Hunt | +0.165 |
Neg logit contributions | |
ortunate | -0.216 |
ciating | -0.210 |
udo | -0.208 |
lasses | -0.205 |
abouts | -0.201 |
Token | Pulse |
Token ID | 25062 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
Pand | +2.410 |
LOAD | +2.393 |
democrat | +2.385 |
mat | +2.276 |
apopt | +2.236 |
Neg logit contributions | |
ortunate | -3.302 |
ciating | -3.265 |
udo | -3.146 |
lasses | -3.120 |
abouts | -3.063 |
Token | Wave |
Token ID | 17084 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Pand | +1.620 |
LOAD | +1.596 |
democrat | +1.538 |
mat | +1.517 |
Hunt | +1.512 |
Neg logit contributions | |
ortunate | -1.981 |
ciating | -1.923 |
udo | -1.871 |
lasses | -1.850 |
abouts | -1.837 |
Token | me |
Token ID | 502 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Pand | +0.684 |
LOAD | +0.675 |
democrat | +0.654 |
mat | +0.643 |
Hunt | +0.633 |
Neg logit contributions | |
ortunate | -0.781 |
ciating | -0.757 |
udo | -0.743 |
lasses | -0.730 |
abouts | -0.721 |
Token | , |
Token ID | 11 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Pand | +1.143 |
LOAD | +1.132 |
democrat | +1.091 |
mat | +1.078 |
Hunt | +1.057 |
Neg logit contributions | |
ortunate | -1.303 |
ciating | -1.266 |
udo | -1.247 |
lasses | -1.226 |
abouts | -1.204 |
Token | they |
Token ID | 484 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Pand | +1.390 |
LOAD | +1.367 |
democrat | +1.331 |
mat | +1.300 |
Hunt | +1.287 |
Neg logit contributions | |
ortunate | -1.835 |
ciating | -1.791 |
udo | -1.754 |
lasses | -1.731 |
abouts | -1.727 |
Token | either |
Token ID | 2035 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
Pand | +1.322 |
LOAD | +1.310 |
democrat | +1.267 |
mat | +1.252 |
Hunt | +1.228 |
Neg logit contributions | |
ortunate | -1.324 |
ciating | -1.292 |
udo | -1.275 |
lasses | -1.251 |
abouts | -1.229 |
Token | choose |
Token ID | 3853 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
Pand | +5.111 |
LOAD | +5.107 |
democrat | +5.090 |
mat | +4.871 |
Hel | +4.848 |
Neg logit contributions | |
ciating | -6.558 |
ortunate | -6.521 |
udo | -6.234 |
lasses | -6.115 |
abouts | -6.078 |
Token | to |
Token ID | 284 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
Pand | +3.115 |
LOAD | +3.036 |
democrat | +2.953 |
mat | +2.922 |
Hunt | +2.902 |
Neg logit contributions | |
ortunate | -3.794 |
ciating | -3.701 |
udo | -3.596 |
lasses | -3.518 |
abouts | -3.499 |
Token | not |
Token ID | 407 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Pand | +1.947 |
LOAD | +1.927 |
democrat | +1.870 |
mat | +1.824 |
Hunt | +1.805 |
Neg logit contributions | |
ortunate | -2.593 |
ciating | -2.539 |
udo | -2.471 |
lasses | -2.440 |
abouts | -2.417 |
Token | have |
Token ID | 423 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Pand | +1.319 |
LOAD | +1.306 |
democrat | +1.258 |
mat | +1.237 |
Hunt | +1.213 |
Neg logit contributions | |
ortunate | -1.820 |
ciating | -1.777 |
udo | -1.736 |
lasses | -1.715 |
abouts | -1.698 |
Token | B |
Token ID | 347 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
Pand | +1.336 |
LOAD | +1.313 |
democrat | +1.272 |
mat | +1.262 |
Hunt | +1.234 |
Neg logit contributions | |
ortunate | -1.646 |
ciating | -1.596 |
udo | -1.572 |
lasses | -1.543 |
abouts | -1.525 |
Token | stars |
Token ID | 5788 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ortunate | +0.498 |
ciating | +0.481 |
udo | +0.480 |
lasses | +0.471 |
abouts | +0.464 |
Neg logit contributions | |
Pand | -0.411 |
LOAD | -0.408 |
democrat | -0.389 |
mat | -0.385 |
Hunt | -0.380 |
Token | . |
Token ID | 13 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
ortunate | +1.402 |
udo | +1.349 |
ciating | +1.337 |
lasses | +1.318 |
abouts | +1.310 |
Neg logit contributions | |
Pand | -1.310 |
LOAD | -1.309 |
democrat | -1.238 |
Hunt | -1.219 |
mat | -1.211 |
Token | So |
Token ID | 1406 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
ortunate | +0.620 |
ciating | +0.600 |
udo | +0.593 |
lasses | +0.585 |
abouts | +0.574 |
Neg logit contributions | |
Pand | -0.558 |
LOAD | -0.552 |
democrat | -0.528 |
mat | -0.525 |
Hunt | -0.516 |
Token | you |
Token ID | 345 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
Pand | +0.486 |
LOAD | +0.479 |
democrat | +0.464 |
mat | +0.457 |
Hunt | +0.448 |
Neg logit contributions | |
ortunate | -0.567 |
ciating | -0.551 |
udo | -0.544 |
lasses | -0.538 |
abouts | -0.524 |
Token | can |
Token ID | 460 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
ortunate | +0.291 |
ciating | +0.282 |
udo | +0.279 |
lasses | +0.275 |
abouts | +0.269 |
Neg logit contributions | |
Pand | -0.260 |
LOAD | -0.257 |
democrat | -0.250 |
mat | -0.246 |
Hunt | -0.241 |
Token | either |
Token ID | 2035 |
Feature activation | +8.40e+00 |
Pos logit contributions | |
ortunate | +0.723 |
ciating | +0.699 |
udo | +0.695 |
lasses | +0.683 |
abouts | +0.672 |
Neg logit contributions | |
Pand | -0.615 |
LOAD | -0.609 |
democrat | -0.586 |
mat | -0.578 |
Hunt | -0.568 |
Token | pick |
Token ID | 2298 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
democrat | +5.013 |
Pand | +4.644 |
mat | +4.573 |
Hel | +4.526 |
apopt | +4.506 |
Neg logit contributions | |
ciating | -6.894 |
ortunate | -6.842 |
udo | -6.439 |
lasses | -6.373 |
abouts | -6.176 |
Token | up |
Token ID | 510 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
Pand | +2.282 |
LOAD | +2.213 |
democrat | +2.163 |
mat | +2.158 |
Hunt | +2.079 |
Neg logit contributions | |
ortunate | -2.558 |
ciating | -2.496 |
udo | -2.425 |
lasses | -2.423 |
abouts | -2.333 |
Token | the |
Token ID | 262 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
ortunate | +1.848 |
udo | +1.784 |
ciating | +1.768 |
lasses | +1.733 |
abouts | +1.717 |
Neg logit contributions | |
Pand | -1.825 |
LOAD | -1.816 |
democrat | -1.733 |
mat | -1.710 |
Hunt | -1.709 |
Token | value |
Token ID | 1988 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ortunate | +0.761 |
ciating | +0.735 |
udo | +0.733 |
lasses | +0.720 |
abouts | +0.708 |
Neg logit contributions | |
Pand | -0.653 |
LOAD | -0.647 |
democrat | -0.618 |
mat | -0.612 |
Hunt | -0.604 |
Token | system |
Token ID | 1080 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
ortunate | +0.103 |
udo | +0.100 |
ciating | +0.100 |
lasses | +0.098 |
abouts | +0.097 |
Neg logit contributions | |
Pand | -0.064 |
LOAD | -0.064 |
democrat | -0.060 |
mat | -0.059 |
Hunt | -0.058 |
Token | � |
Token ID | 447 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Pand | +0.500 |
LOAD | +0.495 |
mat | +0.475 |
Hunt | +0.459 |
democrat | +0.455 |
Neg logit contributions | |
ortunate | -0.695 |
ciating | -0.688 |
udo | -0.662 |
lasses | -0.658 |
abouts | -0.642 |
Token | � |
Token ID | 247 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
Pand | +0.050 |
LOAD | +0.050 |
democrat | +0.046 |
mat | +0.046 |
Hunt | +0.044 |
Neg logit contributions | |
ortunate | -0.116 |
ciating | -0.113 |
udo | -0.113 |
lasses | -0.111 |
abouts | -0.110 |
Token | t |
Token ID | 83 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ortunate | +0.436 |
ciating | +0.421 |
udo | +0.419 |
lasses | +0.411 |
abouts | +0.404 |
Neg logit contributions | |
Pand | -0.405 |
LOAD | -0.402 |
democrat | -0.386 |
mat | -0.382 |
Hunt | -0.376 |
Token | ideal |
Token ID | 7306 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
ortunate | +0.261 |
ciating | +0.251 |
udo | +0.250 |
lasses | +0.246 |
abouts | +0.242 |
Neg logit contributions | |
Pand | -0.240 |
LOAD | -0.238 |
democrat | -0.228 |
mat | -0.226 |
Hunt | -0.223 |
Token | , |
Token ID | 11 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Pand | +0.396 |
LOAD | +0.393 |
democrat | +0.377 |
mat | +0.372 |
Hunt | +0.367 |
Neg logit contributions | |
ortunate | -0.435 |
ciating | -0.420 |
udo | -0.418 |
lasses | -0.411 |
abouts | -0.404 |
Token | either |
Token ID | 2035 |
Feature activation | +8.33e+00 |
Pos logit contributions | |
Pand | +1.048 |
LOAD | +1.038 |
democrat | +1.004 |
mat | +0.990 |
Hunt | +0.969 |
Neg logit contributions | |
ortunate | -1.241 |
ciating | -1.197 |
udo | -1.196 |
lasses | -1.173 |
abouts | -1.154 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Pand | +4.947 |
LOAD | +4.916 |
democrat | +4.840 |
mat | +4.781 |
Hunt | +4.591 |
Neg logit contributions | |
ortunate | -6.622 |
ciating | -6.388 |
udo | -6.344 |
lasses | -6.257 |
abouts | -6.096 |
Token | ( |
Token ID | 357 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
Pand | +1.347 |
LOAD | +1.329 |
mat | +1.265 |
democrat | +1.255 |
Hunt | +1.243 |
Neg logit contributions | |
ortunate | -1.595 |
ciating | -1.544 |
udo | -1.511 |
lasses | -1.494 |
abouts | -1.472 |
Token | Both |
Token ID | 10265 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
Pand | +0.641 |
LOAD | +0.632 |
democrat | +0.601 |
mat | +0.600 |
Hunt | +0.590 |
Neg logit contributions | |
ortunate | -0.784 |
ciating | -0.760 |
udo | -0.754 |
lasses | -0.742 |
abouts | -0.729 |
Token | of |
Token ID | 286 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
ortunate | +0.519 |
ciating | +0.502 |
udo | +0.500 |
lasses | +0.492 |
abouts | +0.484 |
Neg logit contributions | |
Pand | -0.423 |
LOAD | -0.420 |
democrat | -0.401 |
mat | -0.396 |
Hunt | -0.390 |
Token | which |
Token ID | 543 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ortunate | +1.524 |
udo | +1.464 |
ciating | +1.458 |
lasses | +1.438 |
abouts | +1.401 |
Neg logit contributions | |
Pand | -1.709 |
LOAD | -1.695 |
democrat | -1.626 |
mat | -1.603 |
Hunt | -1.598 |
Token | MB |
Token ID | 10744 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Pand | +0.619 |
LOAD | +0.614 |
democrat | +0.590 |
mat | +0.585 |
Hunt | +0.575 |
Neg logit contributions | |
ortunate | -0.660 |
ciating | -0.638 |
udo | -0.635 |
lasses | -0.623 |
abouts | -0.613 |
Token | , |
Token ID | 11 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Pand | +1.071 |
LOAD | +1.062 |
democrat | +1.020 |
mat | +1.009 |
Hunt | +0.989 |
Neg logit contributions | |
ortunate | -1.279 |
udo | -1.231 |
ciating | -1.231 |
lasses | -1.210 |
abouts | -1.193 |
Token | resolution |
Token ID | 6323 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
Pand | +0.871 |
LOAD | +0.866 |
democrat | +0.806 |
mat | +0.793 |
Hunt | +0.752 |
Neg logit contributions | |
ortunate | -2.495 |
udo | -2.438 |
ciating | -2.437 |
lasses | -2.400 |
abouts | -2.384 |
Token | : |
Token ID | 25 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Pand | +2.487 |
LOAD | +2.428 |
democrat | +2.319 |
mat | +2.291 |
Hunt | +2.211 |
Neg logit contributions | |
ortunate | -4.455 |
ciating | -4.435 |
udo | -4.302 |
lasses | -4.259 |
abouts | -4.241 |
Token | 1600 |
Token ID | 26143 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Pand | +1.056 |
LOAD | +1.043 |
democrat | +0.981 |
mat | +0.972 |
Hunt | +0.932 |
Neg logit contributions | |
ortunate | -2.223 |
ciating | -2.170 |
udo | -2.151 |
lasses | -2.131 |
abouts | -2.099 |
Token | x |
Token ID | 87 |
Feature activation | +8.31e+00 |
Pos logit contributions | |
Pand | +1.209 |
LOAD | +1.198 |
democrat | +1.147 |
mat | +1.138 |
Hunt | +1.117 |
Neg logit contributions | |
ortunate | -1.365 |
ciating | -1.321 |
udo | -1.312 |
lasses | -1.290 |
abouts | -1.271 |
Token | 900 |
Token ID | 12865 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
Pand | +4.567 |
LOAD | +4.474 |
Hunt | +4.195 |
mat | +4.180 |
hide | +4.096 |
Neg logit contributions | |
ortunate | -7.215 |
ciating | -7.051 |
abouts | -6.715 |
udo | -6.693 |
lasses | -6.655 |
Token | pixels |
Token ID | 17848 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ortunate | +0.151 |
ciating | +0.146 |
udo | +0.146 |
lasses | +0.143 |
abouts | +0.141 |
Neg logit contributions | |
Pand | -0.120 |
LOAD | -0.119 |
democrat | -0.114 |
mat | -0.112 |
Hunt | -0.111 |
Token | ) |
Token ID | 8 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
Pand | +1.656 |
LOAD | +1.633 |
democrat | +1.562 |
mat | +1.561 |
Hunt | +1.519 |
Neg logit contributions | |
ortunate | -2.224 |
ciating | -2.146 |
udo | -2.136 |
lasses | -2.108 |
abouts | -2.077 |
Token |
|
Token ID | 198 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
Pand | +0.574 |
LOAD | +0.567 |
democrat | +0.543 |
mat | +0.536 |
Hunt | +0.527 |
Neg logit contributions | |
ortunate | -0.746 |
ciating | -0.721 |
udo | -0.717 |
lasses | -0.706 |
abouts | -0.696 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Pand | +0.510 |
LOAD | +0.503 |
mat | +0.469 |
Hunt | +0.460 |
hide | +0.449 |
Neg logit contributions | |
ortunate | -0.856 |
ciating | -0.853 |
udo | -0.820 |
lasses | -0.814 |
abouts | -0.803 |
Token | executive |
Token ID | 4640 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
ortunate | +0.931 |
ciating | +0.901 |
udo | +0.900 |
lasses | +0.884 |
abouts | +0.872 |
Neg logit contributions | |
Pand | -0.636 |
LOAD | -0.629 |
democrat | -0.597 |
mat | -0.589 |
Hunt | -0.579 |
Token | vice |
Token ID | 7927 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Pand | +0.118 |
LOAD | +0.117 |
democrat | +0.111 |
mat | +0.109 |
Hunt | +0.107 |
Neg logit contributions | |
ortunate | -0.186 |
ciating | -0.180 |
udo | -0.180 |
lasses | -0.177 |
abouts | -0.174 |
Token | president |
Token ID | 1893 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
ortunate | +1.318 |
udo | +1.295 |
ciating | +1.279 |
lasses | +1.253 |
abouts | +1.237 |
Neg logit contributions | |
Pand | -0.678 |
LOAD | -0.675 |
Hunt | -0.604 |
democrat | -0.602 |
mat | -0.587 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ortunate | +1.635 |
udo | +1.598 |
ciating | +1.550 |
lasses | +1.531 |
abouts | +1.528 |
Neg logit contributions | |
Pand | -1.571 |
LOAD | -1.570 |
democrat | -1.462 |
mat | -1.450 |
Hunt | -1.436 |
Token | C |
Token ID | 327 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Pand | +1.268 |
LOAD | +1.257 |
democrat | +1.204 |
mat | +1.189 |
Hunt | +1.169 |
Neg logit contributions | |
ortunate | -1.478 |
ciating | -1.425 |
udo | -1.421 |
lasses | -1.393 |
abouts | -1.372 |
Token | ough |
Token ID | 619 |
Feature activation | +8.22e+00 |
Pos logit contributions | |
Pand | +1.170 |
LOAD | +1.162 |
democrat | +1.126 |
mat | +1.115 |
Hunt | +1.102 |
Neg logit contributions | |
ortunate | -0.736 |
ciating | -0.700 |
udo | -0.697 |
lasses | -0.679 |
abouts | -0.663 |
Token | lin |
Token ID | 2815 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
mat | +3.144 |
Pand | +3.106 |
LOAD | +3.099 |
democrat | +3.032 |
Hel | +2.877 |
Neg logit contributions | |
ciating | -8.041 |
ortunate | -7.807 |
abouts | -7.722 |
udo | -7.703 |
lasses | -7.647 |
Token | praised |
Token ID | 15342 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Pand | +1.144 |
LOAD | +1.141 |
democrat | +1.114 |
mat | +1.096 |
Hunt | +1.050 |
Neg logit contributions | |
ortunate | -1.745 |
ciating | -1.700 |
udo | -1.676 |
lasses | -1.656 |
abouts | -1.623 |
Token | Ramsey |
Token ID | 30552 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ortunate | +1.728 |
udo | +1.669 |
ciating | +1.666 |
lasses | +1.635 |
abouts | +1.604 |
Neg logit contributions | |
Pand | -1.453 |
LOAD | -1.434 |
democrat | -1.354 |
mat | -1.346 |
Hunt | -1.317 |
Token | this |
Token ID | 428 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
ortunate | +0.188 |
ciating | +0.182 |
udo | +0.182 |
lasses | +0.179 |
abouts | +0.176 |
Neg logit contributions | |
Pand | -0.149 |
LOAD | -0.147 |
democrat | -0.140 |
mat | -0.139 |
Hunt | -0.137 |
Token | week |
Token ID | 1285 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Pand | +0.420 |
LOAD | +0.418 |
democrat | +0.399 |
mat | +0.392 |
Hunt | +0.385 |
Neg logit contributions | |
ortunate | -0.668 |
ciating | -0.649 |
udo | -0.645 |
lasses | -0.636 |
abouts | -0.625 |
Token | i |
Token ID | 72 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
Pand | +1.751 |
LOAD | +1.685 |
mat | +1.684 |
democrat | +1.637 |
hide | +1.633 |
Neg logit contributions | |
ortunate | -1.766 |
ciating | -1.759 |
udo | -1.667 |
lasses | -1.654 |
abouts | -1.652 |
Token | and |
Token ID | 290 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
ortunate | +0.445 |
ciating | +0.429 |
udo | +0.429 |
lasses | +0.422 |
abouts | +0.417 |
Neg logit contributions | |
Pand | -0.304 |
LOAD | -0.302 |
democrat | -0.285 |
mat | -0.281 |
Hunt | -0.279 |
Token | Sh |
Token ID | 911 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
Pand | +0.621 |
LOAD | +0.615 |
democrat | +0.589 |
mat | +0.581 |
Hunt | +0.571 |
Neg logit contributions | |
ortunate | -0.792 |
ciating | -0.767 |
udo | -0.763 |
lasses | -0.751 |
abouts | -0.739 |
Token | us |
Token ID | 385 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Pand | +0.638 |
mat | +0.627 |
democrat | +0.622 |
LOAD | +0.620 |
hide | +0.609 |
Neg logit contributions | |
ciating | -0.621 |
ortunate | -0.607 |
lasses | -0.574 |
udo | -0.569 |
abouts | -0.555 |
Token | aku |
Token ID | 8719 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
Pand | +1.087 |
LOAD | +1.067 |
democrat | +1.046 |
mat | +1.039 |
hide | +1.023 |
Neg logit contributions | |
ciating | -0.879 |
ortunate | -0.875 |
lasses | -0.821 |
abouts | -0.813 |
udo | -0.806 |
Token | U |
Token ID | 471 |
Feature activation | +8.10e+00 |
Pos logit contributions | |
Pand | +2.532 |
LOAD | +2.514 |
democrat | +2.444 |
mat | +2.416 |
Hunt | +2.384 |
Neg logit contributions | |
ortunate | -1.660 |
ciating | -1.587 |
udo | -1.562 |
lasses | -1.541 |
abouts | -1.500 |
Token | ch |
Token ID | 354 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
mat | +3.783 |
hide | +3.349 |
Pand | +3.273 |
democrat | +3.161 |
LOAD | +3.140 |
Neg logit contributions | |
ciating | -7.825 |
ortunate | -7.541 |
udo | -7.245 |
lasses | -7.106 |
abouts | -7.014 |
Token | iy |
Token ID | 7745 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
mat | +3.552 |
Pand | +3.509 |
democrat | +3.477 |
hide | +3.465 |
LOAD | +3.453 |
Neg logit contributions | |
ortunate | -1.883 |
ciating | -1.883 |
lasses | -1.708 |
abouts | -1.637 |
udo | -1.630 |
Token | ama |
Token ID | 1689 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
Pand | +0.529 |
mat | +0.460 |
LOAD | +0.447 |
democrat | +0.438 |
hide | +0.376 |
Neg logit contributions | |
ciating | -4.060 |
ortunate | -4.007 |
lasses | -3.895 |
udo | -3.862 |
abouts | -3.852 |
Token | struck |
Token ID | 7425 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Pand | +1.270 |
LOAD | +1.250 |
democrat | +1.187 |
mat | +1.165 |
Hunt | +1.137 |
Neg logit contributions | |
ortunate | -2.357 |
ciating | -2.298 |
udo | -2.286 |
lasses | -2.257 |
abouts | -2.219 |
Token | gold |
Token ID | 3869 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
ortunate | +2.149 |
udo | +2.074 |
ciating | +2.045 |
lasses | +2.038 |
abouts | +2.006 |
Neg logit contributions | |
Pand | -1.944 |
LOAD | -1.943 |
mat | -1.830 |
democrat | -1.823 |
Hunt | -1.822 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ortunate | +1.059 |
udo | +1.023 |
ciating | +1.020 |
lasses | +1.003 |
abouts | +0.989 |
Neg logit contributions | |
Pand | -0.899 |
LOAD | -0.893 |
democrat | -0.861 |
mat | -0.843 |
Hunt | -0.829 |
Token | Caption |
Token ID | 11260 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
Pand | +0.686 |
LOAD | +0.673 |
mat | +0.642 |
democrat | +0.640 |
Hunt | +0.618 |
Neg logit contributions | |
ortunate | -1.099 |
ciating | -1.074 |
udo | -1.045 |
lasses | -1.040 |
abouts | -1.019 |
Token | 4 |
Token ID | 604 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Pand | +1.622 |
LOAD | +1.594 |
mat | +1.494 |
Hel | +1.484 |
Hunt | +1.476 |
Neg logit contributions | |
ortunate | -2.768 |
ciating | -2.701 |
lasses | -2.625 |
udo | -2.622 |
abouts | -2.548 |
Token | of |
Token ID | 286 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Pand | +1.530 |
LOAD | +1.480 |
mat | +1.422 |
democrat | +1.390 |
Hunt | +1.387 |
Neg logit contributions | |
ciating | -2.519 |
ortunate | -2.474 |
lasses | -2.361 |
udo | -2.340 |
abouts | -2.296 |
Token | 15 |
Token ID | 1315 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
Pand | +1.045 |
LOAD | +1.026 |
mat | +0.960 |
democrat | +0.952 |
Hunt | +0.943 |
Neg logit contributions | |
ortunate | -1.789 |
ciating | -1.754 |
udo | -1.697 |
lasses | -1.687 |
abouts | -1.645 |
Token | Photos |
Token ID | 9434 |
Feature activation | +8.05e+00 |
Pos logit contributions | |
Pand | +1.287 |
LOAD | +1.266 |
democrat | +1.194 |
mat | +1.168 |
Hunt | +1.143 |
Neg logit contributions | |
ortunate | -2.893 |
ciating | -2.819 |
udo | -2.788 |
lasses | -2.761 |
abouts | -2.719 |
Token | : |
Token ID | 25 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
Pand | +3.308 |
LOAD | +3.166 |
mat | +3.143 |
Hel | +3.081 |
hide | +3.000 |
Neg logit contributions | |
ciating | -8.347 |
ortunate | -7.930 |
lasses | -7.622 |
udo | -7.454 |
rious | -7.194 |
Token | Carly |
Token ID | 35982 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
Pand | +2.321 |
LOAD | +2.277 |
mat | +2.168 |
democrat | +2.163 |
Hel | +2.139 |
Neg logit contributions | |
ortunate | -3.335 |
ciating | -3.252 |
udo | -3.184 |
lasses | -3.156 |
abouts | -3.092 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
ortunate | +0.751 |
udo | +0.729 |
ciating | +0.727 |
lasses | +0.720 |
abouts | +0.707 |
Neg logit contributions | |
LOAD | -0.385 |
Pand | -0.384 |
democrat | -0.355 |
mat | -0.350 |
Hunt | -0.344 |
Token | 's |
Token ID | 338 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ortunate | +3.287 |
udo | +3.195 |
lasses | +3.119 |
abouts | +3.100 |
ciating | +3.098 |
Neg logit contributions | |
Pand | -2.693 |
LOAD | -2.686 |
mat | -2.472 |
Hunt | -2.463 |
democrat | -2.456 |
Token | political |
Token ID | 1964 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
Pand | +0.060 |
LOAD | +0.060 |
democrat | +0.057 |
mat | +0.056 |
Hunt | +0.055 |
Neg logit contributions | |
ortunate | -0.090 |
ciating | -0.087 |
udo | -0.087 |
lasses | -0.086 |
abouts | -0.084 |
Token | make |
Token ID | 787 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Pand | +0.404 |
LOAD | +0.400 |
democrat | +0.382 |
mat | +0.378 |
Hunt | +0.372 |
Neg logit contributions | |
ortunate | -0.495 |
ciating | -0.478 |
udo | -0.477 |
lasses | -0.468 |
abouts | -0.462 |
Token | reproductive |
Token ID | 18391 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Pand | +1.240 |
LOAD | +1.229 |
democrat | +1.179 |
mat | +1.158 |
Hunt | +1.134 |
Neg logit contributions | |
ortunate | -1.679 |
ciating | -1.635 |
udo | -1.620 |
lasses | -1.594 |
abouts | -1.570 |
Token | choices |
Token ID | 7747 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
Pand | +0.804 |
LOAD | +0.792 |
democrat | +0.754 |
mat | +0.740 |
Hunt | +0.721 |
Neg logit contributions | |
ortunate | -1.534 |
ciating | -1.495 |
udo | -1.486 |
lasses | -1.466 |
abouts | -1.448 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Pand | +2.511 |
LOAD | +2.496 |
democrat | +2.424 |
mat | +2.384 |
Hunt | +2.310 |
Neg logit contributions | |
ortunate | -3.270 |
ciating | -3.198 |
udo | -3.161 |
lasses | -3.106 |
abouts | -2.999 |
Token | Why |
Token ID | 4162 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Pand | +0.185 |
LOAD | +0.183 |
democrat | +0.174 |
mat | +0.173 |
Hunt | +0.171 |
Neg logit contributions | |
ortunate | -0.206 |
ciating | -0.199 |
udo | -0.197 |
lasses | -0.195 |
abouts | -0.191 |
Token | don |
Token ID | 836 |
Feature activation | +7.92e+00 |
Pos logit contributions | |
ortunate | +1.155 |
udo | +1.112 |
ciating | +1.108 |
abouts | +1.087 |
lasses | +1.085 |
Neg logit contributions | |
Pand | -1.113 |
LOAD | -1.102 |
democrat | -1.046 |
mat | -1.042 |
Hunt | -1.028 |
Token | � |
Token ID | 447 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
Pand | +3.901 |
LOAD | +3.823 |
mat | +3.643 |
Hunt | +3.570 |
hide | +3.436 |
Neg logit contributions | |
ciating | -7.301 |
ortunate | -7.273 |
lasses | -6.909 |
udo | -6.807 |
abouts | -6.575 |
Token | � |
Token ID | 247 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ortunate | +2.319 |
ciating | +2.255 |
udo | +2.249 |
lasses | +2.218 |
abouts | +2.189 |
Neg logit contributions | |
Pand | -1.107 |
LOAD | -1.091 |
democrat | -1.026 |
mat | -1.008 |
Hunt | -0.985 |
Token | t |
Token ID | 83 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
ortunate | +0.857 |
ciating | +0.826 |
udo | +0.821 |
lasses | +0.806 |
abouts | +0.791 |
Neg logit contributions | |
Pand | -0.878 |
LOAD | -0.871 |
democrat | -0.838 |
mat | -0.830 |
Hunt | -0.817 |
Token | you |
Token ID | 345 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
Pand | +1.314 |
LOAD | +1.311 |
democrat | +1.275 |
mat | +1.238 |
Hunt | +1.217 |
Neg logit contributions | |
ortunate | -1.731 |
ciating | -1.682 |
udo | -1.658 |
lasses | -1.649 |
abouts | -1.602 |
Token | trust |
Token ID | 3774 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Pand | +2.102 |
LOAD | +2.089 |
democrat | +2.087 |
mat | +2.011 |
apopt | +1.939 |
Neg logit contributions | |
ortunate | -2.835 |
ciating | -2.739 |
udo | -2.694 |
lasses | -2.690 |
abouts | -2.603 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ortunate | +1.206 |
ciating | +1.165 |
udo | +1.157 |
abouts | +1.137 |
lasses | +1.127 |
Neg logit contributions | |
Pand | -1.220 |
LOAD | -1.210 |
democrat | -1.153 |
mat | -1.138 |
Hunt | -1.137 |
Token | I |
Token ID | 314 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Pand | +0.908 |
LOAD | +0.898 |
mat | +0.855 |
democrat | +0.844 |
Hunt | +0.840 |
Neg logit contributions | |
ortunate | -1.119 |
ciating | -1.080 |
udo | -1.062 |
lasses | -1.054 |
abouts | -1.034 |
Token | was |
Token ID | 373 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Pand | +1.187 |
LOAD | +1.176 |
democrat | +1.156 |
mat | +1.134 |
donated | +1.091 |
Neg logit contributions | |
ortunate | -1.912 |
ciating | -1.857 |
udo | -1.838 |
lasses | -1.809 |
abouts | -1.777 |
Token | so |
Token ID | 523 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ortunate | +0.105 |
ciating | +0.101 |
udo | +0.101 |
lasses | +0.099 |
abouts | +0.098 |
Neg logit contributions | |
Pand | -0.082 |
LOAD | -0.081 |
democrat | -0.078 |
mat | -0.077 |
Hunt | -0.076 |
Token | desp |
Token ID | 11267 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
ortunate | +0.221 |
ciating | +0.214 |
udo | +0.213 |
lasses | +0.210 |
abouts | +0.207 |
Neg logit contributions | |
Pand | -0.159 |
LOAD | -0.157 |
democrat | -0.150 |
mat | -0.148 |
Hunt | -0.145 |
Token | ond |
Token ID | 623 |
Feature activation | +7.91e+00 |
Pos logit contributions | |
ortunate | +0.272 |
ciating | +0.264 |
udo | +0.258 |
abouts | +0.256 |
lasses | +0.253 |
Neg logit contributions | |
Pand | -0.539 |
LOAD | -0.532 |
democrat | -0.523 |
mat | -0.522 |
Hunt | -0.510 |
Token | ent |
Token ID | 298 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
Pand | +3.864 |
mat | +3.778 |
democrat | +3.702 |
LOAD | +3.656 |
Hel | +3.581 |
Neg logit contributions | |
ortunate | -6.708 |
abouts | -6.680 |
ciating | -6.666 |
udo | -6.663 |
lasses | -6.661 |
Token | and |
Token ID | 290 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ortunate | +0.286 |
ciating | +0.276 |
udo | +0.274 |
lasses | +0.268 |
abouts | +0.266 |
Neg logit contributions | |
Pand | -0.281 |
LOAD | -0.278 |
democrat | -0.267 |
mat | -0.264 |
Hunt | -0.261 |
Token | depressed |
Token ID | 19095 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
Pand | +0.272 |
LOAD | +0.270 |
democrat | +0.257 |
mat | +0.254 |
Hunt | +0.249 |
Neg logit contributions | |
ortunate | -0.375 |
ciating | -0.363 |
udo | -0.362 |
lasses | -0.356 |
abouts | -0.351 |
Token | that |
Token ID | 326 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
ortunate | +0.028 |
ciating | +0.027 |
udo | +0.027 |
lasses | +0.027 |
abouts | +0.026 |
Neg logit contributions | |
Pand | -0.026 |
LOAD | -0.026 |
democrat | -0.025 |
mat | -0.025 |
Hunt | -0.024 |
Token | I |
Token ID | 314 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
ortunate | +0.410 |
ciating | +0.398 |
udo | +0.395 |
lasses | +0.389 |
abouts | +0.384 |
Neg logit contributions | |
Pand | -0.319 |
LOAD | -0.316 |
democrat | -0.300 |
mat | -0.297 |
Hunt | -0.292 |
Token | Gh |
Token ID | 11972 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ortunate | +0.919 |
udo | +0.881 |
ciating | +0.880 |
lasses | +0.865 |
abouts | +0.851 |
Neg logit contributions | |
Pand | -0.880 |
LOAD | -0.875 |
democrat | -0.839 |
mat | -0.829 |
Hunt | -0.823 |
Token | ai |
Token ID | 1872 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ortunate | +1.995 |
ciating | +1.946 |
udo | +1.939 |
lasses | +1.915 |
abouts | +1.892 |
Neg logit contributions | |
Pand | -0.766 |
LOAD | -0.754 |
democrat | -0.702 |
mat | -0.687 |
Hunt | -0.669 |
Token | and |
Token ID | 290 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
ortunate | +1.429 |
udo | +1.392 |
ciating | +1.364 |
abouts | +1.337 |
lasses | +1.328 |
Neg logit contributions | |
LOAD | -1.472 |
Pand | -1.465 |
democrat | -1.399 |
mat | -1.380 |
Hunt | -1.376 |
Token | Wh |
Token ID | 854 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Pand | +0.217 |
LOAD | +0.215 |
democrat | +0.206 |
mat | +0.204 |
Hunt | +0.201 |
Neg logit contributions | |
ortunate | -0.231 |
ciating | -0.223 |
udo | -0.222 |
lasses | -0.218 |
abouts | -0.214 |
Token | ist |
Token ID | 396 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
Pand | +1.139 |
LOAD | +1.107 |
mat | +1.081 |
democrat | +1.075 |
Hunt | +1.046 |
Neg logit contributions | |
ortunate | -1.773 |
ciating | -1.745 |
udo | -1.715 |
lasses | -1.706 |
abouts | -1.668 |
Token | ling |
Token ID | 1359 |
Feature activation | +7.91e+00 |
Pos logit contributions | |
Pand | +1.140 |
LOAD | +1.076 |
mat | +1.041 |
Hunt | +0.985 |
democrat | +0.984 |
Neg logit contributions | |
ciating | -2.452 |
ortunate | -2.447 |
udo | -2.371 |
lasses | -2.326 |
abouts | -2.292 |
Token | Woods |
Token ID | 16483 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
Pand | +3.587 |
LOAD | +3.577 |
Hel | +3.482 |
mat | +3.400 |
Hunt | +3.378 |
Neg logit contributions | |
ciating | -7.340 |
ortunate | -7.232 |
udo | -6.812 |
lasses | -6.658 |
abouts | -6.588 |
Token | to |
Token ID | 284 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Pand | +0.542 |
LOAD | +0.536 |
democrat | +0.514 |
mat | +0.509 |
Hunt | +0.500 |
Neg logit contributions | |
ortunate | -0.625 |
ciating | -0.605 |
udo | -0.600 |
lasses | -0.591 |
abouts | -0.580 |
Token | vac |
Token ID | 6658 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
Pand | +1.085 |
LOAD | +1.075 |
democrat | +1.040 |
mat | +1.018 |
apopt | +0.992 |
Neg logit contributions | |
ortunate | -1.547 |
ciating | -1.508 |
udo | -1.482 |
lasses | -1.464 |
abouts | -1.433 |
Token | ate |
Token ID | 378 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
ortunate | +2.775 |
udo | +2.697 |
lasses | +2.627 |
ciating | +2.621 |
abouts | +2.526 |
Neg logit contributions | |
LOAD | -3.626 |
Pand | -3.620 |
democrat | -3.464 |
mat | -3.416 |
Hunt | -3.354 |
Token | 14 |
Token ID | 1478 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
ortunate | +0.685 |
udo | +0.659 |
ciating | +0.659 |
lasses | +0.646 |
abouts | +0.637 |
Neg logit contributions | |
Pand | -0.657 |
LOAD | -0.652 |
democrat | -0.627 |
mat | -0.619 |
Hunt | -0.612 |
Token | to |
Token ID | 284 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
ortunate | +0.030 |
ciating | +0.029 |
udo | +0.029 |
lasses | +0.029 |
abouts | +0.028 |
Neg logit contributions | |
Pand | -0.029 |
LOAD | -0.028 |
democrat | -0.027 |
mat | -0.027 |
Hunt | -0.027 |
Token | great |
Token ID | 1049 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
ortunate | +0.682 |
ciating | +0.660 |
udo | +0.657 |
lasses | +0.646 |
abouts | +0.636 |
Neg logit contributions | |
Pand | -0.543 |
LOAD | -0.538 |
democrat | -0.514 |
mat | -0.508 |
Hunt | -0.500 |
Token | abuse |
Token ID | 5076 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
ortunate | +0.605 |
ciating | +0.585 |
udo | +0.583 |
lasses | +0.572 |
abouts | +0.564 |
Neg logit contributions | |
Pand | -0.491 |
LOAD | -0.485 |
democrat | -0.464 |
mat | -0.459 |
Hunt | -0.452 |
Token | , |
Token ID | 11 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ortunate | +0.426 |
ciating | +0.411 |
udo | +0.409 |
lasses | +0.401 |
abouts | +0.395 |
Neg logit contributions | |
Pand | -0.417 |
LOAD | -0.414 |
democrat | -0.397 |
mat | -0.393 |
Hunt | -0.387 |
Token | it |
Token ID | 340 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Pand | +0.126 |
LOAD | +0.124 |
democrat | +0.119 |
mat | +0.117 |
Hunt | +0.115 |
Neg logit contributions | |
ortunate | -0.158 |
ciating | -0.153 |
udo | -0.153 |
lasses | -0.150 |
abouts | -0.148 |
Token | either |
Token ID | 2035 |
Feature activation | +7.89e+00 |
Pos logit contributions | |
ortunate | +0.225 |
ciating | +0.217 |
udo | +0.216 |
lasses | +0.213 |
abouts | +0.209 |
Neg logit contributions | |
Pand | -0.204 |
LOAD | -0.202 |
democrat | -0.193 |
mat | -0.191 |
Hunt | -0.189 |
Token | spells |
Token ID | 10377 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
democrat | +4.265 |
mat | +4.223 |
Pand | +4.185 |
LOAD | +4.162 |
Hel | +4.057 |
Neg logit contributions | |
ciating | -6.754 |
ortunate | -6.685 |
udo | -6.444 |
lasses | -6.233 |
abouts | -6.184 |
Token | short |
Token ID | 1790 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
ortunate | +1.539 |
udo | +1.482 |
ciating | +1.476 |
lasses | +1.467 |
abouts | +1.441 |
Neg logit contributions | |
Pand | -0.928 |
LOAD | -0.918 |
Hunt | -0.869 |
democrat | -0.864 |
mat | -0.859 |
Token | life |
Token ID | 1204 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
ortunate | +0.417 |
ciating | +0.404 |
udo | +0.403 |
lasses | +0.396 |
abouts | +0.390 |
Neg logit contributions | |
Pand | -0.345 |
LOAD | -0.340 |
democrat | -0.326 |
mat | -0.323 |
Hunt | -0.319 |
Token | or |
Token ID | 393 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ortunate | +1.995 |
udo | +1.925 |
ciating | +1.897 |
lasses | +1.896 |
abouts | +1.867 |
Neg logit contributions | |
Pand | -1.937 |
LOAD | -1.913 |
democrat | -1.828 |
Hunt | -1.800 |
mat | -1.796 |
Token | exotic |
Token ID | 21036 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ortunate | +0.849 |
ciating | +0.817 |
udo | +0.816 |
lasses | +0.807 |
abouts | +0.795 |
Neg logit contributions | |
Pand | -0.679 |
LOAD | -0.673 |
democrat | -0.637 |
mat | -0.632 |
Hunt | -0.628 |
Token | still |
Token ID | 991 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Pand | +0.359 |
LOAD | +0.356 |
democrat | +0.347 |
mat | +0.341 |
Hunt | +0.334 |
Neg logit contributions | |
ortunate | -0.391 |
ciating | -0.378 |
udo | -0.375 |
lasses | -0.370 |
abouts | -0.360 |
Token | a |
Token ID | 257 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ortunate | +1.977 |
ciating | +1.900 |
udo | +1.891 |
lasses | +1.853 |
abouts | +1.829 |
Neg logit contributions | |
Pand | -2.139 |
LOAD | -2.125 |
democrat | -2.027 |
mat | -2.009 |
Hunt | -1.993 |
Token | long |
Token ID | 890 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
ortunate | +1.466 |
ciating | +1.412 |
udo | +1.405 |
lasses | +1.379 |
abouts | +1.358 |
Neg logit contributions | |
Pand | -1.302 |
LOAD | -1.294 |
democrat | -1.229 |
mat | -1.220 |
Hunt | -1.210 |
Token | way |
Token ID | 835 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
ortunate | +3.240 |
ciating | +3.113 |
udo | +3.110 |
lasses | +3.051 |
abouts | +2.992 |
Neg logit contributions | |
Pand | -3.286 |
LOAD | -3.256 |
democrat | -3.073 |
mat | -3.059 |
Hunt | -3.041 |
Token | to |
Token ID | 284 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
ortunate | +3.322 |
udo | +3.208 |
abouts | +3.183 |
lasses | +3.151 |
ciating | +3.141 |
Neg logit contributions | |
Pand | -4.130 |
LOAD | -4.042 |
Hunt | -3.813 |
democrat | -3.783 |
mat | -3.780 |
Token | go |
Token ID | 467 |
Feature activation | -8.92e+00 |
Pos logit contributions | |
lasses | +4.672 |
ortunate | +4.667 |
udo | +4.614 |
abouts | +4.558 |
ciating | +4.412 |
Neg logit contributions | |
Pand | -4.680 |
LOAD | -4.487 |
Hunt | -4.203 |
vetoed | -4.180 |
apopt | -4.120 |
Token | to |
Token ID | 284 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
abouts | +5.046 |
udo | +4.887 |
ortunate | +4.844 |
lasses | +4.682 |
ciating | +4.589 |
Neg logit contributions | |
Pand | -7.036 |
LOAD | -6.778 |
Hunt | -6.480 |
apopt | -6.381 |
srfAttach | -6.380 |
Token | prove |
Token ID | 5879 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
ortunate | +2.860 |
udo | +2.802 |
ciating | +2.775 |
lasses | +2.744 |
abouts | +2.699 |
Neg logit contributions | |
Pand | -2.446 |
LOAD | -2.434 |
Hunt | -2.259 |
mat | -2.239 |
democrat | -2.219 |
Token | whether |
Token ID | 1771 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
ortunate | +2.194 |
udo | +2.136 |
ciating | +2.098 |
lasses | +2.083 |
abouts | +2.031 |
Neg logit contributions | |
Pand | -2.284 |
LOAD | -2.262 |
democrat | -2.162 |
mat | -2.140 |
Hunt | -2.122 |
Token | or |
Token ID | 393 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
ortunate | +0.277 |
ciating | +0.268 |
udo | +0.266 |
lasses | +0.262 |
abouts | +0.258 |
Neg logit contributions | |
Pand | -0.230 |
LOAD | -0.228 |
democrat | -0.218 |
mat | -0.215 |
Hunt | -0.212 |
Token | not |
Token ID | 407 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ortunate | +2.641 |
ciating | +2.537 |
udo | +2.528 |
lasses | +2.480 |
abouts | +2.437 |
Neg logit contributions | |
Pand | -2.865 |
LOAD | -2.843 |
democrat | -2.734 |
mat | -2.705 |
Hunt | -2.671 |
Token | has |
Token ID | 468 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ortunate | +0.465 |
ciating | +0.450 |
udo | +0.448 |
lasses | +0.441 |
abouts | +0.434 |
Neg logit contributions | |
Pand | -0.345 |
LOAD | -0.342 |
democrat | -0.326 |
mat | -0.322 |
Hunt | -0.316 |
Token | a |
Token ID | 257 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ortunate | +1.433 |
ciating | +1.383 |
udo | +1.376 |
lasses | +1.352 |
abouts | +1.330 |
Neg logit contributions | |
Pand | -1.347 |
LOAD | -1.335 |
democrat | -1.278 |
mat | -1.265 |
Hunt | -1.247 |
Token | long |
Token ID | 890 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
ortunate | +1.179 |
ciating | +1.137 |
udo | +1.132 |
lasses | +1.112 |
abouts | +1.094 |
Neg logit contributions | |
Pand | -0.990 |
LOAD | -0.980 |
democrat | -0.934 |
mat | -0.926 |
Hunt | -0.915 |
Token | way |
Token ID | 835 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
ortunate | +2.421 |
ciating | +2.324 |
udo | +2.322 |
lasses | +2.278 |
abouts | +2.233 |
Neg logit contributions | |
Pand | -2.370 |
LOAD | -2.334 |
democrat | -2.228 |
mat | -2.208 |
Hunt | -2.185 |
Token | to |
Token ID | 284 |
Feature activation | -6.28e+00 |
Pos logit contributions | |
ortunate | +2.833 |
udo | +2.707 |
abouts | +2.681 |
ciating | +2.661 |
lasses | +2.649 |
Neg logit contributions | |
Pand | -3.445 |
LOAD | -3.347 |
Hunt | -3.187 |
apopt | -3.182 |
democrat | -3.150 |
Token | go |
Token ID | 467 |
Feature activation | -8.89e+00 |
Pos logit contributions | |
ortunate | +4.669 |
udo | +4.597 |
lasses | +4.540 |
abouts | +4.447 |
ciating | +4.311 |
Neg logit contributions | |
Pand | -4.048 |
LOAD | -3.858 |
Hunt | -3.654 |
mat | -3.589 |
vetoed | -3.560 |
Token | with |
Token ID | 351 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
udo | +5.296 |
abouts | +5.250 |
ortunate | +5.246 |
lasses | +5.094 |
ciating | +4.925 |
Neg logit contributions | |
Pand | -6.618 |
LOAD | -6.458 |
Hunt | -6.119 |
apopt | -6.090 |
hide | -6.027 |
Token | mobile |
Token ID | 5175 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ortunate | +1.410 |
ciating | +1.366 |
udo | +1.363 |
lasses | +1.335 |
abouts | +1.317 |
Neg logit contributions | |
Pand | -1.201 |
LOAD | -1.194 |
democrat | -1.127 |
mat | -1.120 |
Hunt | -1.106 |
Token | users |
Token ID | 2985 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ortunate | +1.775 |
udo | +1.716 |
ciating | +1.707 |
lasses | +1.673 |
abouts | +1.655 |
Neg logit contributions | |
LOAD | -1.659 |
Pand | -1.648 |
democrat | -1.560 |
mat | -1.554 |
Hunt | -1.537 |
Token | , |
Token ID | 11 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
ortunate | +1.340 |
udo | +1.293 |
ciating | +1.287 |
lasses | +1.259 |
abouts | +1.249 |
Neg logit contributions | |
Pand | -1.365 |
LOAD | -1.357 |
democrat | -1.298 |
mat | -1.281 |
Hunt | -1.273 |
Token | though |
Token ID | 996 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
ortunate | +1.733 |
ciating | +1.675 |
udo | +1.675 |
lasses | +1.638 |
abouts | +1.611 |
Neg logit contributions | |
Pand | -1.616 |
LOAD | -1.615 |
democrat | -1.534 |
mat | -1.521 |
Hunt | -1.499 |
Token | revealed |
Token ID | 4602 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
ortunate | +0.851 |
ciating | +0.827 |
udo | +0.826 |
lasses | +0.815 |
abouts | +0.807 |
Neg logit contributions | |
Pand | -0.403 |
LOAD | -0.398 |
democrat | -0.369 |
mat | -0.364 |
Hunt | -0.359 |
Token | . |
Token ID | 13 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
ortunate | +0.068 |
ciating | +0.066 |
udo | +0.066 |
lasses | +0.064 |
abouts | +0.064 |
Neg logit contributions | |
Pand | -0.066 |
LOAD | -0.065 |
democrat | -0.063 |
mat | -0.062 |
Hunt | -0.061 |
Token |
|
Token ID | 198 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
Pand | +0.430 |
LOAD | +0.427 |
democrat | +0.409 |
mat | +0.401 |
Hunt | +0.395 |
Neg logit contributions | |
ortunate | -0.580 |
ciating | -0.561 |
udo | -0.560 |
lasses | -0.551 |
abouts | -0.543 |
Token |
|
Token ID | 198 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
ortunate | +0.684 |
ciating | +0.672 |
udo | +0.656 |
lasses | +0.650 |
abouts | +0.640 |
Neg logit contributions | |
Pand | -0.425 |
LOAD | -0.417 |
mat | -0.396 |
democrat | -0.392 |
Hunt | -0.385 |
Token | Gil |
Token ID | 40747 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
Pand | +0.287 |
LOAD | +0.284 |
democrat | +0.269 |
mat | +0.268 |
Hunt | +0.264 |
Neg logit contributions | |
ortunate | -0.388 |
ciating | -0.376 |
udo | -0.374 |
lasses | -0.368 |
abouts | -0.362 |
Token | ad |
Token ID | 324 |
Feature activation | -8.69e+00 |
Pos logit contributions | |
ortunate | +0.264 |
ciating | +0.256 |
udo | +0.254 |
lasses | +0.250 |
abouts | +0.246 |
Neg logit contributions | |
Pand | -0.207 |
LOAD | -0.205 |
democrat | -0.196 |
mat | -0.195 |
Hunt | -0.191 |
Token | Perry |
Token ID | 14105 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ortunate | +6.497 |
udo | +6.315 |
ciating | +6.210 |
lasses | +6.076 |
abouts | +5.910 |
Neg logit contributions | |
LOAD | -5.598 |
Pand | -5.426 |
democrat | -5.108 |
Hunt | -5.025 |
apopt | -4.960 |
Token | , |
Token ID | 11 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
ortunate | +0.249 |
udo | +0.240 |
ciating | +0.240 |
lasses | +0.235 |
abouts | +0.231 |
Neg logit contributions | |
Pand | -0.242 |
LOAD | -0.241 |
democrat | -0.231 |
mat | -0.227 |
Hunt | -0.225 |
Token | D |
Token ID | 360 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ortunate | +0.401 |
ciating | +0.387 |
udo | +0.387 |
lasses | +0.381 |
abouts | +0.375 |
Neg logit contributions | |
Pand | -0.266 |
LOAD | -0.264 |
democrat | -0.249 |
mat | -0.245 |
Hunt | -0.243 |
Token | ror |
Token ID | 1472 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
Pand | +1.195 |
LOAD | +1.188 |
democrat | +1.140 |
mat | +1.128 |
Hunt | +1.112 |
Neg logit contributions | |
ortunate | -1.188 |
ciating | -1.152 |
udo | -1.140 |
lasses | -1.119 |
abouts | -1.101 |
Token | Israel |
Token ID | 2692 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Pand | +2.174 |
LOAD | +2.154 |
democrat | +2.069 |
mat | +2.047 |
Hunt | +2.001 |
Neg logit contributions | |
ortunate | -2.940 |
ciating | -2.852 |
udo | -2.826 |
lasses | -2.791 |
abouts | -2.752 |
Token | to |
Token ID | 284 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ortunate | +0.248 |
ciating | +0.240 |
udo | +0.240 |
lasses | +0.235 |
abouts | +0.231 |
Neg logit contributions | |
Pand | -0.219 |
LOAD | -0.218 |
democrat | -0.207 |
mat | -0.206 |
Hunt | -0.203 |
Token | st |
Token ID | 336 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Pand | +0.604 |
democrat | +0.593 |
LOAD | +0.592 |
mat | +0.569 |
apopt | +0.556 |
Neg logit contributions | |
ortunate | -0.847 |
ciating | -0.834 |
udo | -0.813 |
lasses | -0.803 |
abouts | -0.790 |
Token | oke |
Token ID | 2088 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
Pand | +1.912 |
LOAD | +1.878 |
democrat | +1.833 |
mat | +1.824 |
Hunt | +1.789 |
Neg logit contributions | |
ortunate | -2.166 |
ciating | -2.112 |
udo | -2.054 |
lasses | -2.037 |
abouts | -2.014 |
Token | through |
Token ID | 832 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
Pand | +2.396 |
LOAD | +2.330 |
democrat | +2.286 |
mat | +2.241 |
Hunt | +2.187 |
Neg logit contributions | |
ortunate | -2.913 |
ciating | -2.837 |
udo | -2.793 |
lasses | -2.749 |
abouts | -2.667 |
Token | Pad |
Token ID | 15744 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Pand | +2.358 |
LOAD | +2.283 |
democrat | +2.264 |
mat | +2.207 |
apopt | +2.180 |
Neg logit contributions | |
ortunate | -2.768 |
ciating | -2.711 |
udo | -2.696 |
lasses | -2.612 |
abouts | -2.584 |
Token | m |
Token ID | 76 |
Feature activation | -8.33e+00 |
Pos logit contributions | |
ortunate | +0.472 |
ciating | +0.460 |
udo | +0.459 |
lasses | +0.453 |
abouts | +0.448 |
Neg logit contributions | |
Pand | -0.164 |
LOAD | -0.161 |
democrat | -0.149 |
mat | -0.146 |
Hunt | -0.141 |
Token | av |
Token ID | 615 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
ortunate | +5.616 |
udo | +5.513 |
ciating | +5.345 |
lasses | +5.183 |
abouts | +5.083 |
Neg logit contributions | |
Pand | -5.970 |
LOAD | -5.963 |
democrat | -5.761 |
Hunt | -5.619 |
mat | -5.578 |
Token | ati |
Token ID | 7246 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
ortunate | +0.498 |
ciating | +0.483 |
udo | +0.478 |
lasses | +0.472 |
abouts | +0.465 |
Neg logit contributions | |
Pand | -0.390 |
LOAD | -0.384 |
democrat | -0.368 |
mat | -0.366 |
Hunt | -0.358 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ortunate | +0.070 |
ciating | +0.068 |
udo | +0.067 |
lasses | +0.066 |
abouts | +0.065 |
Neg logit contributions | |
Pand | -0.059 |
LOAD | -0.058 |
democrat | -0.056 |
mat | -0.055 |
Hunt | -0.054 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ortunate | +0.789 |
ciating | +0.764 |
udo | +0.756 |
lasses | +0.744 |
abouts | +0.731 |
Neg logit contributions | |
Pand | -0.711 |
LOAD | -0.701 |
democrat | -0.669 |
mat | -0.667 |
Hunt | -0.656 |
Token | In |
Token ID | 818 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Pand | +0.978 |
LOAD | +0.965 |
mat | +0.912 |
democrat | +0.909 |
Hunt | +0.900 |
Neg logit contributions | |
ortunate | -1.200 |
ciating | -1.165 |
udo | -1.152 |
lasses | -1.137 |
abouts | -1.115 |
Token | the |
Token ID | 262 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
Pand | +0.625 |
LOAD | +0.617 |
democrat | +0.599 |
mat | +0.583 |
Hunt | +0.566 |
Neg logit contributions | |
ortunate | -0.939 |
ciating | -0.920 |
udo | -0.909 |
lasses | -0.894 |
abouts | -0.879 |
Token | potential |
Token ID | 2785 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Pand | +2.003 |
LOAD | +1.950 |
democrat | +1.931 |
mat | +1.882 |
Hunt | +1.833 |
Neg logit contributions | |
ortunate | -2.497 |
ciating | -2.459 |
udo | -2.433 |
lasses | -2.407 |
abouts | -2.337 |
Token | or |
Token ID | 393 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Pand | +1.517 |
LOAD | +1.516 |
democrat | +1.433 |
mat | +1.426 |
Hunt | +1.415 |
Neg logit contributions | |
ortunate | -1.610 |
ciating | -1.553 |
udo | -1.544 |
lasses | -1.507 |
abouts | -1.488 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ortunate | +0.875 |
ciating | +0.842 |
udo | +0.839 |
lasses | +0.824 |
abouts | +0.812 |
Neg logit contributions | |
Pand | -0.785 |
LOAD | -0.779 |
democrat | -0.745 |
mat | -0.736 |
Hunt | -0.726 |
Token | har |
Token ID | 3971 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Pand | +0.806 |
LOAD | +0.794 |
democrat | +0.764 |
mat | +0.755 |
Hunt | +0.742 |
Neg logit contributions | |
ortunate | -0.940 |
ciating | -0.909 |
udo | -0.906 |
lasses | -0.891 |
abouts | -0.874 |
Token | v |
Token ID | 85 |
Feature activation | -8.29e+00 |
Pos logit contributions | |
Pand | +0.345 |
LOAD | +0.333 |
mat | +0.329 |
democrat | +0.323 |
Hunt | +0.320 |
Neg logit contributions | |
ortunate | -0.247 |
ciating | -0.236 |
udo | -0.233 |
lasses | -0.232 |
abouts | -0.221 |
Token | ests |
Token ID | 3558 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
ortunate | +4.716 |
udo | +4.451 |
ciating | +4.358 |
abouts | +4.318 |
lasses | +4.306 |
Neg logit contributions | |
LOAD | -6.918 |
Pand | -6.747 |
democrat | -6.403 |
apopt | -6.341 |
Hunt | -6.280 |
Token | a |
Token ID | 257 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Pand | +0.460 |
LOAD | +0.456 |
democrat | +0.436 |
mat | +0.430 |
Hunt | +0.421 |
Neg logit contributions | |
ortunate | -0.638 |
ciating | -0.620 |
udo | -0.616 |
lasses | -0.607 |
abouts | -0.596 |
Token | year |
Token ID | 614 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Pand | +0.623 |
LOAD | +0.615 |
democrat | +0.587 |
mat | +0.577 |
Hunt | +0.564 |
Neg logit contributions | |
ortunate | -0.996 |
ciating | -0.969 |
udo | -0.965 |
lasses | -0.953 |
abouts | -0.932 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Pand | +1.161 |
LOAD | +1.148 |
democrat | +1.106 |
mat | +1.094 |
Hunt | +1.066 |
Neg logit contributions | |
ortunate | -1.390 |
ciating | -1.356 |
udo | -1.338 |
lasses | -1.325 |
abouts | -1.286 |
Token | unlike |
Token ID | 5023 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
Pand | +0.893 |
LOAD | +0.877 |
democrat | +0.849 |
mat | +0.835 |
Hunt | +0.822 |
Neg logit contributions | |
ortunate | -1.075 |
ciating | -1.046 |
udo | -1.035 |
lasses | -1.020 |
abouts | -1.000 |
Token | |
Token ID | 3907 |
Feature activation | -7.23e+00 |
Pos logit contributions | |
Pand | +0.381 |
LOAD | +0.378 |
democrat | +0.361 |
mat | +0.356 |
Hunt | +0.350 |
Neg logit contributions | |
ortunate | -0.474 |
ciating | -0.459 |
udo | -0.457 |
lasses | -0.449 |
abouts | -0.442 |
Token | nel |
Token ID | 4954 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
ortunate | +5.633 |
ciating | +5.484 |
udo | +5.469 |
lasses | +5.321 |
abouts | +5.302 |
Neg logit contributions | |
LOAD | -4.420 |
Pand | -4.318 |
democrat | -4.173 |
apopt | -4.131 |
srfAttach | -3.993 |
Token | after |
Token ID | 706 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Pand | +0.056 |
LOAD | +0.056 |
democrat | +0.054 |
mat | +0.053 |
Hunt | +0.052 |
Neg logit contributions | |
ortunate | -0.068 |
ciating | -0.066 |
udo | -0.065 |
lasses | -0.064 |
abouts | -0.063 |
Token | Obama |
Token ID | 2486 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ortunate | +0.200 |
ciating | +0.194 |
udo | +0.193 |
lasses | +0.189 |
abouts | +0.186 |
Neg logit contributions | |
Pand | -0.173 |
LOAD | -0.171 |
democrat | -0.164 |
mat | -0.162 |
Hunt | -0.160 |
Token | nor |
Token ID | 4249 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Pand | +0.920 |
LOAD | +0.910 |
democrat | +0.872 |
mat | +0.860 |
Hunt | +0.842 |
Neg logit contributions | |
ortunate | -1.291 |
ciating | -1.251 |
udo | -1.243 |
lasses | -1.225 |
abouts | -1.206 |
Token | |
Token ID | 3907 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
Pand | +0.768 |
LOAD | +0.760 |
democrat | +0.730 |
mat | +0.722 |
Hunt | +0.706 |
Neg logit contributions | |
ortunate | -0.978 |
ciating | -0.947 |
udo | -0.940 |
lasses | -0.926 |
abouts | -0.910 |
Token | mal |
Token ID | 7617 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
ortunate | +6.160 |
abouts | +5.770 |
udo | +5.767 |
lasses | +5.754 |
ciating | +5.693 |
Neg logit contributions | |
LOAD | -5.382 |
Pand | -5.361 |
apopt | -4.969 |
democrat | -4.945 |
Hunt | -4.884 |
Token | |
Token ID | 3907 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
Pand | +0.033 |
LOAD | +0.033 |
democrat | +0.031 |
mat | +0.031 |
Hunt | +0.030 |
Neg logit contributions | |
ortunate | -0.041 |
ciating | -0.040 |
udo | -0.040 |
lasses | -0.039 |
abouts | -0.038 |
Token | ized |
Token ID | 1143 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ortunate | +2.756 |
udo | +2.639 |
ciating | +2.625 |
lasses | +2.552 |
abouts | +2.505 |
Neg logit contributions | |
LOAD | -3.116 |
Pand | -3.104 |
democrat | -2.946 |
apopt | -2.923 |
Hunt | -2.885 |
Token | re |
Token ID | 302 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
Pand | +0.929 |
LOAD | +0.922 |
democrat | +0.892 |
mat | +0.881 |
Hunt | +0.863 |
Neg logit contributions | |
ortunate | -0.950 |
ciating | -0.917 |
udo | -0.908 |
lasses | -0.892 |
abouts | -0.876 |
Token | |
Token ID | 3907 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
Pand | +2.692 |
LOAD | +2.664 |
democrat | +2.553 |
mat | +2.527 |
Hunt | +2.477 |
Neg logit contributions | |
ortunate | -3.438 |
ciating | -3.327 |
udo | -3.303 |
lasses | -3.253 |
abouts | -3.207 |
Token | , |
Token ID | 11 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
ortunate | +3.565 |
udo | +3.484 |
ciating | +3.391 |
lasses | +3.348 |
abouts | +3.329 |
Neg logit contributions | |
LOAD | -4.548 |
Pand | -4.535 |
democrat | -4.399 |
mat | -4.282 |
Hunt | -4.281 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
ortunate | +2.844 |
udo | +2.719 |
ciating | +2.700 |
lasses | +2.660 |
abouts | +2.614 |
Neg logit contributions | |
Pand | -3.452 |
LOAD | -3.436 |
democrat | -3.317 |
mat | -3.261 |
Hunt | -3.229 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
ortunate | +3.120 |
udo | +3.024 |
ciating | +2.998 |
lasses | +2.958 |
abouts | +2.926 |
Neg logit contributions | |
Pand | -2.183 |
LOAD | -2.157 |
democrat | -2.079 |
mat | -2.012 |
Hunt | -1.989 |
Token | : |
Token ID | 25 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
ortunate | +2.434 |
udo | +2.355 |
ciating | +2.353 |
lasses | +2.314 |
abouts | +2.281 |
Neg logit contributions | |
Pand | -1.733 |
LOAD | -1.716 |
democrat | -1.645 |
mat | -1.614 |
Hunt | -1.587 |
Token | 21 |
Token ID | 2481 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
ortunate | +3.442 |
udo | +3.352 |
lasses | +3.256 |
ciating | +3.236 |
abouts | +3.204 |
Neg logit contributions | |
Pand | -3.609 |
LOAD | -3.606 |
democrat | -3.547 |
apopt | -3.401 |
mat | -3.383 |
Token | : |
Token ID | 25 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
ortunate | +3.624 |
udo | +3.568 |
ciating | +3.456 |
abouts | +3.370 |
lasses | +3.359 |
Neg logit contributions | |
LOAD | -3.222 |
Pand | -3.163 |
democrat | -3.131 |
Hunt | -2.981 |
mat | -2.969 |
Token | 20 |
Token ID | 1238 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
ortunate | +5.033 |
udo | +4.979 |
lasses | +4.776 |
abouts | +4.702 |
ciating | +4.589 |
Neg logit contributions | |
democrat | -5.879 |
LOAD | -5.830 |
conflic | -5.808 |
Pand | -5.784 |
apopt | -5.589 |
Token | IST |
Token ID | 45790 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
ortunate | +4.085 |
udo | +4.002 |
ciating | +3.868 |
lasses | +3.798 |
abouts | +3.775 |
Neg logit contributions | |
LOAD | -3.330 |
Pand | -3.314 |
democrat | -3.250 |
mat | -3.080 |
Hunt | -3.079 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ortunate | +3.997 |
udo | +3.849 |
lasses | +3.772 |
ciating | +3.732 |
abouts | +3.628 |
Neg logit contributions | |
LOAD | -2.683 |
Pand | -2.678 |
democrat | -2.606 |
Hunt | -2.493 |
mat | -2.478 |
Token | It |
Token ID | 1026 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
Pand | +0.679 |
LOAD | +0.671 |
democrat | +0.635 |
mat | +0.634 |
Hunt | +0.625 |
Neg logit contributions | |
ortunate | -0.835 |
ciating | -0.810 |
udo | -0.803 |
lasses | -0.792 |
abouts | -0.778 |
Token | 's |
Token ID | 338 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Pand | +0.258 |
LOAD | +0.256 |
democrat | +0.244 |
mat | +0.241 |
Hunt | +0.237 |
Neg logit contributions | |
ortunate | -0.340 |
ciating | -0.329 |
udo | -0.328 |
lasses | -0.323 |
abouts | -0.318 |
Token | 4 |
Token ID | 19 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ortunate | +0.310 |
ciating | +0.300 |
udo | +0.298 |
lasses | +0.293 |
abouts | +0.289 |
Neg logit contributions | |
Pand | -0.250 |
LOAD | -0.248 |
democrat | -0.236 |
mat | -0.234 |
Hunt | -0.230 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ortunate | +1.095 |
ciating | +1.058 |
udo | +1.051 |
lasses | +1.032 |
abouts | +1.019 |
Neg logit contributions | |
Pand | -0.951 |
LOAD | -0.944 |
democrat | -0.898 |
mat | -0.887 |
Hunt | -0.880 |
Token | He |
Token ID | 679 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
ortunate | +1.264 |
ciating | +1.220 |
udo | +1.217 |
lasses | +1.196 |
abouts | +1.176 |
Neg logit contributions | |
Pand | -1.081 |
LOAD | -1.070 |
democrat | -1.027 |
mat | -1.011 |
Hunt | -0.998 |
Token | Has |
Token ID | 7875 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
ortunate | +0.678 |
udo | +0.655 |
ciating | +0.655 |
lasses | +0.643 |
abouts | +0.634 |
Neg logit contributions | |
Pand | -0.517 |
LOAD | -0.511 |
democrat | -0.486 |
mat | -0.479 |
Hunt | -0.473 |
Token | Posted |
Token ID | 12918 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ortunate | +1.359 |
ciating | +1.315 |
udo | +1.310 |
lasses | +1.288 |
abouts | +1.267 |
Neg logit contributions | |
Pand | -1.209 |
LOAD | -1.198 |
democrat | -1.148 |
mat | -1.131 |
Hunt | -1.119 |
Token | Conspiracy |
Token ID | 38786 |
Feature activation | -7.93e+00 |
Pos logit contributions | |
ortunate | +0.877 |
ciating | +0.847 |
udo | +0.843 |
lasses | +0.829 |
abouts | +0.815 |
Neg logit contributions | |
Pand | -0.755 |
LOAD | -0.748 |
democrat | -0.717 |
mat | -0.709 |
Hunt | -0.698 |
Token | The |
Token ID | 383 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
ortunate | +5.495 |
ciating | +5.400 |
udo | +5.393 |
lasses | +5.220 |
abouts | +5.123 |
Neg logit contributions | |
LOAD | -5.506 |
Pand | -5.367 |
democrat | -5.243 |
apopt | -5.081 |
Hunt | -5.064 |
Token | ories |
Token ID | 1749 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
ortunate | +0.314 |
ciating | +0.302 |
udo | +0.300 |
lasses | +0.294 |
abouts | +0.288 |
Neg logit contributions | |
Pand | -0.377 |
LOAD | -0.374 |
democrat | -0.360 |
mat | -0.357 |
Hunt | -0.352 |
Token | & |
Token ID | 1222 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ortunate | +3.899 |
udo | +3.798 |
ciating | +3.779 |
lasses | +3.696 |
abouts | +3.693 |
Neg logit contributions | |
Pand | -4.142 |
LOAD | -4.083 |
democrat | -3.950 |
mat | -3.880 |
Hunt | -3.852 |
Token | Alt |
Token ID | 12344 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
ortunate | +1.329 |
udo | +1.283 |
ciating | +1.282 |
lasses | +1.258 |
abouts | +1.242 |
Neg logit contributions | |
Pand | -1.202 |
LOAD | -1.194 |
democrat | -1.144 |
mat | -1.127 |
Hunt | -1.113 |
Token | - |
Token ID | 12 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ortunate | +1.306 |
udo | +1.260 |
ciating | +1.246 |
lasses | +1.233 |
abouts | +1.218 |
Neg logit contributions | |
Pand | -1.174 |
LOAD | -1.165 |
democrat | -1.111 |
apopt | -1.086 |
mat | -1.084 |
Token | system |
Token ID | 1080 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
ortunate | +0.641 |
ciating | +0.619 |
udo | +0.618 |
lasses | +0.606 |
abouts | +0.598 |
Neg logit contributions | |
Pand | -0.529 |
LOAD | -0.526 |
democrat | -0.499 |
mat | -0.494 |
Hunt | -0.486 |
Token | used |
Token ID | 973 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Pand | +0.497 |
LOAD | +0.493 |
democrat | +0.478 |
mat | +0.469 |
Hunt | +0.461 |
Neg logit contributions | |
ortunate | -0.582 |
ciating | -0.566 |
udo | -0.560 |
lasses | -0.553 |
abouts | -0.539 |
Token | by |
Token ID | 416 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
Pand | +0.655 |
LOAD | +0.649 |
democrat | +0.621 |
mat | +0.611 |
Hunt | +0.598 |
Neg logit contributions | |
ortunate | -0.969 |
ciating | -0.942 |
udo | -0.935 |
lasses | -0.922 |
abouts | -0.905 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ortunate | +0.396 |
ciating | +0.383 |
udo | +0.381 |
lasses | +0.374 |
abouts | +0.368 |
Neg logit contributions | |
Pand | -0.339 |
LOAD | -0.336 |
democrat | -0.321 |
mat | -0.318 |
Hunt | -0.313 |
Token | Mau |
Token ID | 28931 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
Pand | +0.007 |
LOAD | +0.007 |
democrat | +0.007 |
mat | +0.007 |
Hunt | +0.006 |
Neg logit contributions | |
ortunate | -0.009 |
ciating | -0.009 |
udo | -0.009 |
lasses | -0.009 |
abouts | -0.009 |
Token | Mau |
Token ID | 28931 |
Feature activation | -7.89e+00 |
Pos logit contributions | |
ortunate | +0.402 |
udo | +0.393 |
ciating | +0.392 |
lasses | +0.384 |
abouts | +0.382 |
Neg logit contributions | |
Pand | -0.217 |
LOAD | -0.214 |
democrat | -0.200 |
mat | -0.195 |
Hunt | -0.194 |
Token | , |
Token ID | 11 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
ortunate | +5.235 |
udo | +5.143 |
abouts | +4.976 |
ciating | +4.968 |
lasses | +4.836 |
Neg logit contributions | |
Pand | -5.629 |
LOAD | -5.584 |
mat | -5.243 |
democrat | -5.219 |
apopt | -5.199 |
Token | and |
Token ID | 290 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Pand | +0.391 |
LOAD | +0.386 |
democrat | +0.375 |
mat | +0.368 |
Hunt | +0.361 |
Neg logit contributions | |
ortunate | -0.435 |
ciating | -0.421 |
udo | -0.417 |
lasses | -0.413 |
abouts | -0.405 |
Token | denied |
Token ID | 6699 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ortunate | +0.951 |
ciating | +0.920 |
udo | +0.916 |
lasses | +0.901 |
abouts | +0.887 |
Neg logit contributions | |
Pand | -0.773 |
LOAD | -0.766 |
democrat | -0.732 |
mat | -0.723 |
Hunt | -0.712 |
Token | having |
Token ID | 1719 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
ortunate | +1.244 |
udo | +1.200 |
ciating | +1.199 |
lasses | +1.175 |
abouts | +1.161 |
Neg logit contributions | |
Pand | -1.165 |
LOAD | -1.152 |
democrat | -1.098 |
mat | -1.093 |
Hunt | -1.079 |
Token | ever |
Token ID | 1683 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
Pand | +0.287 |
LOAD | +0.284 |
democrat | +0.270 |
mat | +0.267 |
Hunt | +0.264 |
Neg logit contributions | |
ortunate | -0.376 |
ciating | -0.363 |
udo | -0.363 |
lasses | -0.357 |
abouts | -0.353 |
Token | from |
Token ID | 422 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ortunate | +1.213 |
ciating | +1.174 |
udo | +1.169 |
lasses | +1.149 |
abouts | +1.132 |
Neg logit contributions | |
Pand | -0.964 |
LOAD | -0.955 |
democrat | -0.912 |
mat | -0.900 |
Hunt | -0.887 |
Token | the |
Token ID | 262 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Pand | +0.080 |
LOAD | +0.080 |
democrat | +0.076 |
mat | +0.076 |
Hunt | +0.074 |
Neg logit contributions | |
ortunate | -0.090 |
ciating | -0.087 |
udo | -0.087 |
lasses | -0.085 |
abouts | -0.084 |
Token | back |
Token ID | 736 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
ortunate | +1.396 |
ciating | +1.353 |
udo | +1.346 |
lasses | +1.326 |
abouts | +1.311 |
Neg logit contributions | |
Pand | -0.923 |
LOAD | -0.911 |
democrat | -0.861 |
mat | -0.852 |
Hunt | -0.839 |
Token | to |
Token ID | 284 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
ortunate | +3.932 |
udo | +3.783 |
ciating | +3.734 |
abouts | +3.716 |
lasses | +3.706 |
Neg logit contributions | |
Pand | -3.791 |
LOAD | -3.717 |
democrat | -3.542 |
Hunt | -3.504 |
apopt | -3.442 |
Token | the |
Token ID | 262 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
ortunate | +1.823 |
ciating | +1.765 |
udo | +1.747 |
lasses | +1.708 |
abouts | +1.696 |
Neg logit contributions | |
Pand | -1.974 |
LOAD | -1.955 |
democrat | -1.861 |
mat | -1.850 |
Hunt | -1.829 |
Token | front |
Token ID | 2166 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
ortunate | +2.902 |
ciating | +2.821 |
udo | +2.800 |
lasses | +2.754 |
abouts | +2.735 |
Neg logit contributions | |
Pand | -1.955 |
LOAD | -1.932 |
democrat | -1.807 |
mat | -1.788 |
Hunt | -1.773 |
Token | . |
Token ID | 13 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
ortunate | +5.131 |
udo | +4.994 |
abouts | +4.993 |
ciating | +4.944 |
lasses | +4.892 |
Neg logit contributions | |
Pand | -5.684 |
LOAD | -5.559 |
Hunt | -5.245 |
democrat | -5.237 |
mat | -5.125 |
Token | Kart |
Token ID | 32872 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ortunate | +0.512 |
ciating | +0.494 |
udo | +0.489 |
lasses | +0.482 |
abouts | +0.472 |
Neg logit contributions | |
Pand | -0.497 |
LOAD | -0.493 |
democrat | -0.471 |
mat | -0.469 |
Hunt | -0.462 |
Token | ing |
Token ID | 278 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
ortunate | +1.392 |
ciating | +1.349 |
udo | +1.345 |
lasses | +1.322 |
abouts | +1.313 |
Neg logit contributions | |
Pand | -1.051 |
LOAD | -1.044 |
democrat | -0.989 |
mat | -0.975 |
Hunt | -0.962 |
Token | has |
Token ID | 468 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Pand | +0.145 |
LOAD | +0.144 |
democrat | +0.138 |
mat | +0.136 |
Hunt | +0.134 |
Neg logit contributions | |
ortunate | -0.175 |
ciating | -0.169 |
udo | -0.169 |
lasses | -0.166 |
abouts | -0.163 |
Token | bo |
Token ID | 1489 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Pand | +0.743 |
LOAD | +0.738 |
democrat | +0.714 |
mat | +0.700 |
Hunt | +0.686 |
Neg logit contributions | |
ortunate | -0.867 |
ciating | -0.836 |
udo | -0.833 |
lasses | -0.820 |
abouts | -0.802 |
Token | � |
Token ID | 447 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
ortunate | +0.367 |
udo | +0.352 |
ciating | +0.352 |
lasses | +0.346 |
abouts | +0.342 |
Neg logit contributions | |
Pand | -0.338 |
LOAD | -0.336 |
democrat | -0.318 |
mat | -0.316 |
Hunt | -0.314 |
Token | � |
Token ID | 247 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Pand | +0.253 |
LOAD | +0.250 |
democrat | +0.230 |
mat | +0.222 |
Hunt | +0.219 |
Neg logit contributions | |
ortunate | -0.809 |
ciating | -0.801 |
udo | -0.786 |
lasses | -0.780 |
abouts | -0.772 |
Token | s |
Token ID | 82 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
ortunate | +1.157 |
ciating | +1.133 |
udo | +1.114 |
lasses | +1.098 |
abouts | +1.077 |
Neg logit contributions | |
Pand | -0.933 |
LOAD | -0.920 |
mat | -0.880 |
democrat | -0.880 |
Hunt | -0.859 |
Token | G |
Token ID | 402 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
ortunate | +2.310 |
udo | +2.217 |
ciating | +2.207 |
lasses | +2.190 |
abouts | +2.170 |
Neg logit contributions | |
Pand | -1.745 |
LOAD | -1.728 |
mat | -1.603 |
Hunt | -1.600 |
democrat | -1.597 |
Token | ug |
Token ID | 1018 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
ortunate | +2.361 |
udo | +2.257 |
ciating | +2.219 |
lasses | +2.207 |
abouts | +2.178 |
Neg logit contributions | |
Pand | -1.895 |
LOAD | -1.877 |
democrat | -1.782 |
Hunt | -1.753 |
mat | -1.751 |
Token | gen |
Token ID | 5235 |
Feature activation | -7.76e+00 |
Pos logit contributions | |
ortunate | +2.017 |
ciating | +1.964 |
udo | +1.947 |
lasses | +1.918 |
abouts | +1.894 |
Neg logit contributions | |
Pand | -1.218 |
LOAD | -1.202 |
democrat | -1.144 |
mat | -1.130 |
Hunt | -1.102 |
Token | heim |
Token ID | 9096 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ortunate | +3.406 |
udo | +3.373 |
lasses | +3.219 |
ciating | +3.187 |
abouts | +3.047 |
Neg logit contributions | |
Pand | -7.360 |
LOAD | -7.193 |
democrat | -7.072 |
Hunt | -6.928 |
mat | -6.889 |
Token | Museum |
Token ID | 9594 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
ortunate | +1.129 |
udo | +1.091 |
ciating | +1.078 |
lasses | +1.076 |
abouts | +1.063 |
Neg logit contributions | |
Pand | -0.889 |
LOAD | -0.880 |
democrat | -0.828 |
Hunt | -0.820 |
mat | -0.812 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ortunate | +0.306 |
udo | +0.295 |
ciating | +0.294 |
lasses | +0.288 |
abouts | +0.286 |
Neg logit contributions | |
Pand | -0.254 |
LOAD | -0.252 |
democrat | -0.239 |
mat | -0.236 |
Hunt | -0.234 |
Token | he |
Token ID | 339 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ortunate | +1.516 |
udo | +1.455 |
ciating | +1.453 |
lasses | +1.426 |
abouts | +1.409 |
Neg logit contributions | |
Pand | -1.399 |
LOAD | -1.386 |
democrat | -1.321 |
mat | -1.310 |
Hunt | -1.297 |
Token | � |
Token ID | 447 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ortunate | +1.165 |
udo | +1.124 |
ciating | +1.115 |
lasses | +1.109 |
abouts | +1.103 |
Neg logit contributions | |
Pand | -0.870 |
LOAD | -0.867 |
democrat | -0.804 |
Hunt | -0.796 |
mat | -0.795 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Pand | +0.891 |
LOAD | +0.872 |
mat | +0.852 |
Hunt | +0.831 |
hide | +0.825 |
Neg logit contributions | |
ciating | -1.213 |
ortunate | -1.210 |
lasses | -1.146 |
udo | -1.145 |
abouts | -1.109 |
Token | com |
Token ID | 785 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Pand | +0.077 |
LOAD | +0.076 |
mat | +0.074 |
hide | +0.072 |
Hunt | +0.071 |
Neg logit contributions | |
ortunate | -0.105 |
ciating | -0.105 |
udo | -0.100 |
lasses | -0.099 |
abouts | -0.097 |
Token | / |
Token ID | 14 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
ortunate | +0.967 |
ciating | +0.949 |
udo | +0.926 |
lasses | +0.919 |
abouts | +0.901 |
Neg logit contributions | |
Pand | -0.652 |
LOAD | -0.643 |
mat | -0.608 |
democrat | -0.607 |
Hunt | -0.597 |
Token | Eh |
Token ID | 43894 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
ortunate | +1.759 |
udo | +1.698 |
ciating | +1.690 |
lasses | +1.663 |
abouts | +1.632 |
Neg logit contributions | |
Pand | -1.687 |
LOAD | -1.677 |
democrat | -1.621 |
mat | -1.585 |
Hunt | -1.566 |
Token | U |
Token ID | 52 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
ortunate | +3.153 |
udo | +3.068 |
ciating | +3.001 |
lasses | +2.991 |
abouts | +2.926 |
Neg logit contributions | |
Pand | -2.981 |
LOAD | -2.974 |
democrat | -2.906 |
mat | -2.795 |
apopt | -2.782 |
Token | g |
Token ID | 70 |
Feature activation | -7.71e+00 |
Pos logit contributions | |
ortunate | +3.132 |
udo | +3.049 |
ciating | +2.990 |
lasses | +2.964 |
abouts | +2.891 |
Neg logit contributions | |
Pand | -3.084 |
LOAD | -3.082 |
democrat | -3.006 |
mat | -2.883 |
apopt | -2.882 |
Token | I |
Token ID | 40 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
ortunate | +5.448 |
udo | +5.397 |
lasses | +5.213 |
ciating | +5.124 |
abouts | +5.055 |
Neg logit contributions | |
LOAD | -5.060 |
democrat | -5.048 |
Pand | -5.042 |
apopt | -4.800 |
vetoed | -4.757 |
Token | x |
Token ID | 87 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
ortunate | +2.801 |
udo | +2.725 |
ciating | +2.679 |
lasses | +2.650 |
abouts | +2.590 |
Neg logit contributions | |
Pand | -2.706 |
LOAD | -2.703 |
democrat | -2.619 |
mat | -2.534 |
apopt | -2.518 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
ortunate | +3.016 |
udo | +2.942 |
ciating | +2.871 |
lasses | +2.866 |
abouts | +2.800 |
Neg logit contributions | |
Pand | -2.862 |
LOAD | -2.855 |
democrat | -2.786 |
mat | -2.679 |
apopt | -2.673 |
Token | N |
Token ID | 45 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
ortunate | +3.130 |
udo | +3.053 |
ciating | +2.984 |
lasses | +2.975 |
abouts | +2.905 |
Neg logit contributions | |
Pand | -2.991 |
LOAD | -2.983 |
democrat | -2.918 |
mat | -2.805 |
apopt | -2.800 |
Token | t |
Token ID | 83 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ortunate | +1.930 |
udo | +1.867 |
ciating | +1.853 |
lasses | +1.824 |
abouts | +1.785 |
Neg logit contributions | |
Pand | -1.840 |
LOAD | -1.827 |
democrat | -1.772 |
mat | -1.726 |
Hunt | -1.710 |
Token | ales |
Token ID | 2040 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
Pand | +1.389 |
LOAD | +1.375 |
democrat | +1.322 |
mat | +1.311 |
Hunt | +1.289 |
Neg logit contributions | |
ortunate | -1.511 |
ciating | -1.464 |
udo | -1.448 |
lasses | -1.429 |
abouts | -1.405 |
Token | in |
Token ID | 287 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
Pand | +0.588 |
LOAD | +0.582 |
democrat | +0.556 |
mat | +0.549 |
Hunt | +0.539 |
Neg logit contributions | |
ortunate | -0.786 |
ciating | -0.762 |
udo | -0.757 |
lasses | -0.745 |
abouts | -0.734 |
Token | com |
Token ID | 401 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
Pand | +0.484 |
LOAD | +0.479 |
democrat | +0.459 |
mat | +0.453 |
Hunt | +0.446 |
Neg logit contributions | |
ortunate | -0.589 |
ciating | -0.570 |
udo | -0.567 |
lasses | -0.558 |
abouts | -0.549 |
Token | |
Token ID | 3907 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
ortunate | +0.076 |
udo | +0.073 |
ciating | +0.073 |
lasses | +0.072 |
abouts | +0.071 |
Neg logit contributions | |
Pand | -0.063 |
LOAD | -0.063 |
democrat | -0.060 |
mat | -0.058 |
Hunt | -0.058 |
Token | par |
Token ID | 1845 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
ortunate | +3.375 |
ciating | +3.247 |
lasses | +3.233 |
udo | +3.233 |
abouts | +3.131 |
Neg logit contributions | |
LOAD | -2.432 |
Pand | -2.381 |
democrat | -2.287 |
Hunt | -2.238 |
apopt | -2.208 |
Token | |
Token ID | 3907 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
Pand | +0.415 |
LOAD | +0.408 |
democrat | +0.393 |
mat | +0.391 |
Hunt | +0.381 |
Neg logit contributions | |
ortunate | -0.531 |
ciating | -0.513 |
udo | -0.511 |
lasses | -0.503 |
abouts | -0.497 |
Token | is |
Token ID | 271 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ortunate | +4.827 |
ciating | +4.581 |
udo | +4.558 |
lasses | +4.489 |
rious | +4.280 |
Neg logit contributions | |
LOAD | -6.193 |
Pand | -6.000 |
democrat | -5.709 |
Hunt | -5.685 |
conflic | -5.621 |
Token | |
Token ID | 3907 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
ortunate | +0.818 |
ciating | +0.793 |
udo | +0.789 |
lasses | +0.773 |
abouts | +0.760 |
Neg logit contributions | |
Pand | -0.677 |
LOAD | -0.674 |
democrat | -0.639 |
mat | -0.627 |
Hunt | -0.624 |
Token | on |
Token ID | 261 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
ortunate | +2.358 |
ciating | +2.276 |
udo | +2.262 |
lasses | +2.231 |
abouts | +2.168 |
Neg logit contributions | |
Pand | -2.106 |
LOAD | -2.102 |
democrat | -2.001 |
Hunt | -1.947 |
apopt | -1.934 |
Token | to |
Token ID | 284 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ortunate | +0.362 |
ciating | +0.350 |
udo | +0.349 |
lasses | +0.342 |
abouts | +0.337 |
Neg logit contributions | |
Pand | -0.310 |
LOAD | -0.308 |
democrat | -0.294 |
mat | -0.290 |
Hunt | -0.287 |
Token | this |
Token ID | 428 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ortunate | +0.391 |
ciating | +0.377 |
udo | +0.376 |
lasses | +0.369 |
abouts | +0.364 |
Neg logit contributions | |
Pand | -0.342 |
LOAD | -0.339 |
democrat | -0.324 |
mat | -0.320 |
Hunt | -0.316 |
Token | had |
Token ID | 550 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ortunate | +1.187 |
udo | +1.144 |
ciating | +1.140 |
lasses | +1.122 |
abouts | +1.112 |
Neg logit contributions | |
Pand | -1.062 |
LOAD | -1.052 |
democrat | -0.999 |
mat | -0.990 |
Hunt | -0.983 |
Token | a |
Token ID | 257 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ortunate | +1.061 |
udo | +1.024 |
ciating | +1.022 |
lasses | +1.005 |
abouts | +0.997 |
Neg logit contributions | |
Pand | -0.895 |
LOAD | -0.884 |
democrat | -0.837 |
mat | -0.835 |
Hunt | -0.833 |
Token | long |
Token ID | 890 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Pand | +0.131 |
LOAD | +0.130 |
democrat | +0.124 |
mat | +0.123 |
Hunt | +0.121 |
Neg logit contributions | |
ortunate | -0.163 |
ciating | -0.157 |
udo | -0.157 |
lasses | -0.154 |
abouts | -0.151 |
Token | way |
Token ID | 835 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
ortunate | +1.507 |
ciating | +1.455 |
udo | +1.451 |
lasses | +1.426 |
abouts | +1.402 |
Neg logit contributions | |
Pand | -1.253 |
LOAD | -1.239 |
democrat | -1.184 |
mat | -1.170 |
Hunt | -1.155 |
Token | to |
Token ID | 284 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
ortunate | +1.891 |
udo | +1.816 |
abouts | +1.794 |
lasses | +1.784 |
ciating | +1.780 |
Neg logit contributions | |
Pand | -2.130 |
LOAD | -2.068 |
Hunt | -1.980 |
democrat | -1.976 |
apopt | -1.971 |
Token | go |
Token ID | 467 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
ortunate | +3.765 |
udo | +3.718 |
lasses | +3.691 |
abouts | +3.611 |
ciating | +3.448 |
Neg logit contributions | |
Pand | -3.128 |
LOAD | -2.962 |
Hunt | -2.812 |
mat | -2.791 |
apopt | -2.786 |
Token | to |
Token ID | 284 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
ortunate | +4.629 |
udo | +4.605 |
abouts | +4.595 |
lasses | +4.489 |
ciating | +4.341 |
Neg logit contributions | |
Pand | -5.673 |
LOAD | -5.530 |
apopt | -5.333 |
Hunt | -5.303 |
mat | -5.205 |
Token | prove |
Token ID | 5879 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ortunate | +2.394 |
udo | +2.330 |
ciating | +2.281 |
lasses | +2.277 |
abouts | +2.254 |
Neg logit contributions | |
Pand | -1.917 |
LOAD | -1.891 |
Hunt | -1.779 |
mat | -1.770 |
democrat | -1.739 |
Token | its |
Token ID | 663 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ortunate | +1.421 |
udo | +1.372 |
ciating | +1.352 |
lasses | +1.338 |
abouts | +1.325 |
Neg logit contributions | |
Pand | -1.284 |
LOAD | -1.270 |
democrat | -1.201 |
Hunt | -1.197 |
mat | -1.196 |
Token | intentions |
Token ID | 14953 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Pand | +1.071 |
LOAD | +1.067 |
democrat | +1.039 |
mat | +1.011 |
apopt | +0.978 |
Neg logit contributions | |
ortunate | -1.345 |
ciating | -1.313 |
udo | -1.286 |
lasses | -1.271 |
abouts | -1.257 |
Token | were |
Token ID | 547 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Pand | +0.142 |
LOAD | +0.140 |
democrat | +0.135 |
mat | +0.133 |
Hunt | +0.131 |
Neg logit contributions | |
ortunate | -0.160 |
ciating | -0.155 |
udo | -0.154 |
lasses | -0.151 |
abouts | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
ortunate | +0.971 |
udo | +0.934 |
ciating | +0.933 |
lasses | +0.916 |
abouts | +0.900 |
Neg logit contributions | |
LOAD | -0.797 |
Pand | -0.793 |
democrat | -0.764 |
Hunt | -0.749 |
mat | -0.743 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ortunate | +0.790 |
ciating | +0.776 |
udo | +0.760 |
lasses | +0.751 |
abouts | +0.739 |
Neg logit contributions | |
Pand | -0.501 |
LOAD | -0.493 |
mat | -0.467 |
democrat | -0.465 |
Hunt | -0.455 |
Token | - |
Token ID | 12 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
ortunate | +0.802 |
udo | +0.768 |
ciating | +0.761 |
lasses | +0.746 |
abouts | +0.740 |
Neg logit contributions | |
Pand | -0.783 |
LOAD | -0.778 |
democrat | -0.773 |
apopt | -0.751 |
mat | -0.741 |
Token | Automatic |
Token ID | 30199 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Pand | +0.363 |
LOAD | +0.360 |
democrat | +0.344 |
mat | +0.339 |
Hunt | +0.334 |
Neg logit contributions | |
ortunate | -0.466 |
ciating | -0.451 |
udo | -0.449 |
lasses | -0.442 |
abouts | -0.435 |
Token | plug |
Token ID | 6107 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Pand | +0.803 |
LOAD | +0.794 |
democrat | +0.762 |
mat | +0.752 |
Hunt | +0.738 |
Neg logit contributions | |
ortunate | -0.963 |
ciating | -0.932 |
udo | -0.924 |
lasses | -0.911 |
abouts | -0.895 |
Token | - |
Token ID | 12 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
Pand | +1.018 |
LOAD | +1.011 |
democrat | +0.968 |
mat | +0.964 |
Hunt | +0.940 |
Neg logit contributions | |
ortunate | -1.168 |
ciating | -1.135 |
udo | -1.118 |
lasses | -1.099 |
abouts | -1.082 |
Token | in |
Token ID | 259 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
ortunate | +5.192 |
udo | +5.022 |
lasses | +4.932 |
abouts | +4.897 |
ciating | +4.662 |
Neg logit contributions | |
Pand | -5.222 |
LOAD | -5.181 |
democrat | -5.063 |
apopt | -4.949 |
Hunt | -4.945 |
Token | delay |
Token ID | 5711 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
ortunate | +2.610 |
udo | +2.526 |
ciating | +2.486 |
lasses | +2.480 |
abouts | +2.441 |
Neg logit contributions | |
Pand | -1.968 |
LOAD | -1.958 |
democrat | -1.859 |
Hunt | -1.836 |
mat | -1.836 |
Token | compensation |
Token ID | 9836 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Pand | +0.378 |
LOAD | +0.374 |
democrat | +0.358 |
mat | +0.353 |
Hunt | +0.347 |
Neg logit contributions | |
ortunate | -0.501 |
ciating | -0.487 |
udo | -0.483 |
lasses | -0.476 |
abouts | -0.468 |
Token | to |
Token ID | 284 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
Pand | +0.940 |
LOAD | +0.930 |
democrat | +0.893 |
mat | +0.883 |
Hunt | +0.864 |
Neg logit contributions | |
ortunate | -1.143 |
ciating | -1.116 |
udo | -1.101 |
lasses | -1.084 |
abouts | -1.066 |
Token | support |
Token ID | 1104 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
ortunate | +0.467 |
ciating | +0.451 |
udo | +0.451 |
lasses | +0.444 |
abouts | +0.438 |
Neg logit contributions | |
Pand | -0.335 |
LOAD | -0.333 |
democrat | -0.315 |
mat | -0.313 |
Hunt | -0.308 |
Token | ay |
Token ID | 323 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ortunate | +3.372 |
udo | +3.341 |
lasses | +3.245 |
ciating | +3.218 |
abouts | +3.165 |
Neg logit contributions | |
LOAD | -2.448 |
Pand | -2.440 |
democrat | -2.326 |
Hunt | -2.247 |
apopt | -2.218 |
Token | ong |
Token ID | 506 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
ortunate | +1.130 |
ciating | +1.086 |
udo | +1.086 |
lasses | +1.063 |
abouts | +1.044 |
Neg logit contributions | |
Pand | -1.163 |
LOAD | -1.154 |
democrat | -1.110 |
mat | -1.094 |
Hunt | -1.083 |
Token | bat |
Token ID | 7365 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
ortunate | +2.715 |
udo | +2.624 |
ciating | +2.622 |
lasses | +2.594 |
abouts | +2.516 |
Neg logit contributions | |
Pand | -2.526 |
LOAD | -2.523 |
democrat | -2.384 |
Hunt | -2.351 |
mat | -2.339 |
Token | ik |
Token ID | 1134 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
ortunate | +3.123 |
udo | +3.047 |
ciating | +3.020 |
lasses | +2.972 |
abouts | +2.927 |
Neg logit contributions | |
LOAD | -2.708 |
Pand | -2.694 |
democrat | -2.547 |
Hunt | -2.505 |
mat | -2.470 |
Token | os |
Token ID | 418 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
ortunate | +1.809 |
udo | +1.748 |
ciating | +1.742 |
lasses | +1.712 |
abouts | +1.679 |
Neg logit contributions | |
Pand | -1.675 |
LOAD | -1.670 |
democrat | -1.588 |
mat | -1.562 |
Hunt | -1.558 |
Token | na |
Token ID | 12385 |
Feature activation | -7.62e+00 |
Pos logit contributions | |
ortunate | +2.358 |
udo | +2.285 |
ciating | +2.272 |
lasses | +2.222 |
abouts | +2.192 |
Neg logit contributions | |
Pand | -2.238 |
LOAD | -2.234 |
democrat | -2.121 |
mat | -2.090 |
Hunt | -2.086 |
Token | nar |
Token ID | 30083 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
ortunate | +5.573 |
udo | +5.478 |
ciating | +5.326 |
lasses | +5.232 |
abouts | +5.232 |
Neg logit contributions | |
LOAD | -4.966 |
Pand | -4.909 |
Hunt | -4.603 |
mat | -4.530 |
democrat | -4.506 |
Token | irin |
Token ID | 47388 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
ortunate | +5.267 |
udo | +5.160 |
ciating | +4.976 |
lasses | +4.927 |
abouts | +4.914 |
Neg logit contributions | |
LOAD | -4.551 |
Pand | -4.510 |
Hunt | -4.251 |
democrat | -4.248 |
apopt | -4.130 |
Token | ig |
Token ID | 328 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
ortunate | +3.613 |
udo | +3.519 |
ciating | +3.489 |
lasses | +3.398 |
abouts | +3.387 |
Neg logit contributions | |
LOAD | -3.435 |
Pand | -3.398 |
democrat | -3.217 |
Hunt | -3.184 |
mat | -3.121 |
Token | sa |
Token ID | 473 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
ortunate | +3.150 |
udo | +3.063 |
ciating | +3.021 |
lasses | +2.976 |
abouts | +2.934 |
Neg logit contributions | |
LOAD | -2.893 |
Pand | -2.881 |
democrat | -2.722 |
Hunt | -2.693 |
mat | -2.650 |
Token | at |
Token ID | 379 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
ortunate | +5.604 |
udo | +5.485 |
ciating | +5.344 |
lasses | +5.262 |
abouts | +5.249 |
Neg logit contributions | |
LOAD | -4.748 |
Pand | -4.677 |
Hunt | -4.363 |
democrat | -4.304 |
mat | -4.249 |
Token | Ger |
Token ID | 13573 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Pand | +0.954 |
LOAD | +0.944 |
democrat | +0.906 |
mat | +0.896 |
Hunt | +0.880 |
Neg logit contributions | |
ortunate | -1.199 |
ciating | -1.163 |
udo | -1.154 |
lasses | -1.137 |
abouts | -1.119 |
Token | ads |
Token ID | 5643 |
Feature activation | +6.69e-04 |
Pos logit contributions | |
ortunate | +0.169 |
ciating | +0.164 |
udo | +0.162 |
lasses | +0.159 |
abouts | +0.157 |
Neg logit contributions | |
Pand | -0.169 |
LOAD | -0.168 |
democrat | -0.162 |
mat | -0.160 |
Hunt | -0.157 |
Token | , |
Token ID | 11 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
Pand | +0.000 |
LOAD | +0.000 |
democrat | +0.000 |
mat | +0.000 |
Hunt | +0.000 |
Neg logit contributions | |
ortunate | -0.000 |
ciating | -0.000 |
udo | -0.000 |
lasses | -0.000 |
abouts | -0.000 |
Token | following |
Token ID | 1708 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ortunate | +0.489 |
ciating | +0.473 |
udo | +0.470 |
lasses | +0.463 |
abouts | +0.455 |
Neg logit contributions | |
Pand | -0.431 |
LOAD | -0.427 |
democrat | -0.410 |
mat | -0.405 |
Hunt | -0.399 |
Token | their |
Token ID | 511 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Pand | +0.774 |
LOAD | +0.767 |
democrat | +0.740 |
mat | +0.733 |
Hunt | +0.719 |
Neg logit contributions | |
ortunate | -0.867 |
ciating | -0.844 |
udo | -0.835 |
lasses | -0.821 |
abouts | -0.808 |
Token | critically |
Token ID | 19475 |
Feature activation | -7.58e+00 |
Pos logit contributions | |
Pand | +0.860 |
LOAD | +0.855 |
democrat | +0.830 |
mat | +0.812 |
Hunt | +0.795 |
Neg logit contributions | |
ortunate | -1.103 |
ciating | -1.079 |
udo | -1.069 |
lasses | -1.051 |
abouts | -1.033 |
Token | acclaimed |
Token ID | 27023 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
ortunate | +4.428 |
udo | +4.249 |
ciating | +4.110 |
lasses | +4.086 |
abouts | +4.077 |
Neg logit contributions | |
LOAD | -6.103 |
Pand | -6.073 |
Hunt | -5.711 |
hide | -5.659 |
democrat | -5.641 |
Token | Sheriff |
Token ID | 12874 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
ortunate | +4.169 |
udo | +4.006 |
lasses | +3.913 |
ciating | +3.888 |
abouts | +3.851 |
Neg logit contributions | |
Pand | -3.719 |
LOAD | -3.703 |
mat | -3.438 |
democrat | -3.408 |
Hunt | -3.388 |
Token | of |
Token ID | 286 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
ortunate | +2.652 |
udo | +2.562 |
ciating | +2.561 |
lasses | +2.505 |
abouts | +2.479 |
Neg logit contributions | |
Pand | -2.218 |
LOAD | -2.210 |
democrat | -2.108 |
mat | -2.068 |
apopt | -2.023 |
Token | Babylon |
Token ID | 28028 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ortunate | +1.552 |
ciating | +1.490 |
udo | +1.489 |
lasses | +1.463 |
abouts | +1.440 |
Neg logit contributions | |
Pand | -1.605 |
LOAD | -1.600 |
democrat | -1.532 |
mat | -1.511 |
Hunt | -1.494 |
Token | min |
Token ID | 949 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
Pand | +0.949 |
LOAD | +0.941 |
democrat | +0.909 |
mat | +0.898 |
Hunt | +0.887 |
Neg logit contributions | |
ortunate | -1.060 |
ciating | -1.034 |
udo | -1.015 |
lasses | -1.002 |
abouts | -0.984 |
Token | the |
Token ID | 262 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
ortunate | +0.215 |
ciating | +0.208 |
udo | +0.207 |
lasses | +0.204 |
abouts | +0.201 |
Neg logit contributions | |
Pand | -0.202 |
LOAD | -0.199 |
democrat | -0.191 |
mat | -0.189 |
Hunt | -0.187 |
Token | city |
Token ID | 1748 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
Pand | +0.231 |
LOAD | +0.229 |
democrat | +0.220 |
mat | +0.217 |
Hunt | +0.213 |
Neg logit contributions | |
ortunate | -0.277 |
ciating | -0.268 |
udo | -0.267 |
lasses | -0.262 |
abouts | -0.258 |
Token | 's |
Token ID | 338 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
Pand | +0.491 |
LOAD | +0.486 |
democrat | +0.464 |
mat | +0.458 |
Hunt | +0.453 |
Neg logit contributions | |
ortunate | -0.587 |
ciating | -0.567 |
udo | -0.567 |
lasses | -0.556 |
abouts | -0.550 |
Token | broad |
Token ID | 3154 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Pand | +0.259 |
LOAD | +0.257 |
democrat | +0.247 |
mat | +0.243 |
Hunt | +0.238 |
Neg logit contributions | |
ortunate | -0.324 |
ciating | -0.314 |
udo | -0.313 |
lasses | -0.307 |
abouts | -0.302 |
Token | bou |
Token ID | 35833 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ortunate | +0.751 |
ciating | +0.723 |
udo | +0.722 |
lasses | +0.709 |
abouts | +0.700 |
Neg logit contributions | |
Pand | -0.758 |
LOAD | -0.752 |
democrat | -0.719 |
mat | -0.713 |
Hunt | -0.707 |
Token | lev |
Token ID | 2768 |
Feature activation | -7.56e+00 |
Pos logit contributions | |
ortunate | +0.193 |
ciating | +0.187 |
udo | +0.185 |
lasses | +0.183 |
abouts | +0.179 |
Neg logit contributions | |
Pand | -0.157 |
LOAD | -0.155 |
democrat | -0.150 |
mat | -0.149 |
Hunt | -0.145 |
Token | ards |
Token ID | 1371 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
ortunate | +6.682 |
udo | +6.435 |
lasses | +6.372 |
abouts | +6.232 |
ciating | +6.109 |
Neg logit contributions | |
LOAD | -4.065 |
Pand | -4.029 |
Hunt | -3.686 |
democrat | -3.656 |
apopt | -3.499 |
Token | in |
Token ID | 287 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
ortunate | +0.364 |
ciating | +0.350 |
udo | +0.349 |
lasses | +0.342 |
abouts | +0.339 |
Neg logit contributions | |
Pand | -0.359 |
LOAD | -0.356 |
democrat | -0.341 |
mat | -0.338 |
Hunt | -0.334 |
Token | support |
Token ID | 1104 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ortunate | +0.426 |
ciating | +0.411 |
udo | +0.410 |
lasses | +0.403 |
abouts | +0.397 |
Neg logit contributions | |
Pand | -0.357 |
LOAD | -0.353 |
democrat | -0.338 |
mat | -0.334 |
Hunt | -0.329 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ortunate | +1.486 |
udo | +1.457 |
ciating | +1.440 |
abouts | +1.406 |
lasses | +1.389 |
Neg logit contributions | |
LOAD | -1.481 |
Pand | -1.476 |
Hunt | -1.373 |
democrat | -1.371 |
mat | -1.356 |
Token | many |
Token ID | 867 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ortunate | +0.764 |
ciating | +0.736 |
udo | +0.734 |
lasses | +0.721 |
abouts | +0.710 |
Neg logit contributions | |
Pand | -0.735 |
LOAD | -0.728 |
democrat | -0.697 |
mat | -0.691 |
Hunt | -0.682 |
Token |
|
Token ID | 198 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
ortunate | +0.328 |
udo | +0.318 |
ciating | +0.317 |
lasses | +0.311 |
abouts | +0.304 |
Neg logit contributions | |
Pand | -0.249 |
LOAD | -0.247 |
democrat | -0.237 |
mat | -0.232 |
Hunt | -0.230 |
Token |
|
Token ID | 198 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
ortunate | +2.004 |
udo | +1.938 |
ciating | +1.935 |
lasses | +1.905 |
abouts | +1.878 |
Neg logit contributions | |
Pand | -1.406 |
LOAD | -1.393 |
democrat | -1.331 |
mat | -1.305 |
Hunt | -1.286 |
Token | # |
Token ID | 2 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
ortunate | +1.700 |
udo | +1.645 |
ciating | +1.630 |
lasses | +1.603 |
abouts | +1.567 |
Neg logit contributions | |
Pand | -1.767 |
LOAD | -1.752 |
democrat | -1.709 |
mat | -1.667 |
Hunt | -1.659 |
Token | !/ |
Token ID | 48443 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
ortunate | +1.675 |
udo | +1.618 |
ciating | +1.611 |
lasses | +1.581 |
abouts | +1.553 |
Neg logit contributions | |
Pand | -1.496 |
LOAD | -1.481 |
democrat | -1.421 |
mat | -1.402 |
Hunt | -1.387 |
Token | bin |
Token ID | 8800 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
ortunate | +2.693 |
udo | +2.599 |
ciating | +2.512 |
lasses | +2.479 |
abouts | +2.455 |
Neg logit contributions | |
Pand | -4.085 |
LOAD | -4.053 |
democrat | -3.943 |
Hunt | -3.842 |
mat | -3.835 |
Token | / |
Token ID | 14 |
Feature activation | -7.49e+00 |
Pos logit contributions | |
ortunate | +3.972 |
udo | +3.881 |
lasses | +3.756 |
ciating | +3.743 |
abouts | +3.686 |
Neg logit contributions | |
Pand | -3.271 |
LOAD | -3.250 |
democrat | -3.134 |
mat | -3.035 |
Hunt | -3.026 |
Token | sh |
Token ID | 1477 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
udo | +3.959 |
ortunate | +3.925 |
ciating | +3.706 |
lasses | +3.587 |
abouts | +3.385 |
Neg logit contributions | |
Pand | -6.224 |
LOAD | -6.201 |
democrat | -6.142 |
Hunt | -6.111 |
apopt | -5.928 |
Token | / |
Token ID | 1220 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
ortunate | +1.609 |
udo | +1.557 |
ciating | +1.546 |
lasses | +1.520 |
abouts | +1.490 |
Neg logit contributions | |
Pand | -1.461 |
LOAD | -1.447 |
democrat | -1.385 |
mat | -1.370 |
Hunt | -1.357 |
Token | s |
Token ID | 82 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
ortunate | +2.152 |
udo | +2.078 |
ciating | +2.057 |
lasses | +2.025 |
abouts | +1.994 |
Neg logit contributions | |
Pand | -2.242 |
LOAD | -2.217 |
democrat | -2.138 |
mat | -2.104 |
Hunt | -2.091 |
Token | bin |
Token ID | 8800 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
ortunate | +1.708 |
udo | +1.659 |
ciating | +1.629 |
lasses | +1.602 |
abouts | +1.556 |
Neg logit contributions | |
Pand | -2.305 |
LOAD | -2.285 |
democrat | -2.206 |
mat | -2.183 |
Hunt | -2.165 |
Token | / |
Token ID | 14 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
ortunate | +0.843 |
ciating | +0.822 |
udo | +0.808 |
lasses | +0.799 |
abouts | +0.791 |
Neg logit contributions | |
Pand | -0.583 |
LOAD | -0.579 |
democrat | -0.551 |
mat | -0.548 |
Hunt | -0.534 |
Token | os |
Token ID | 418 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
ortunate | +1.809 |
udo | +1.748 |
ciating | +1.742 |
lasses | +1.712 |
abouts | +1.679 |
Neg logit contributions | |
Pand | -1.675 |
LOAD | -1.670 |
democrat | -1.588 |
mat | -1.562 |
Hunt | -1.558 |
Token | na |
Token ID | 12385 |
Feature activation | -7.62e+00 |
Pos logit contributions | |
ortunate | +2.358 |
udo | +2.285 |
ciating | +2.272 |
lasses | +2.222 |
abouts | +2.192 |
Neg logit contributions | |
Pand | -2.238 |
LOAD | -2.234 |
democrat | -2.121 |
mat | -2.090 |
Hunt | -2.086 |
Token | nar |
Token ID | 30083 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
ortunate | +5.573 |
udo | +5.478 |
ciating | +5.326 |
lasses | +5.232 |
abouts | +5.232 |
Neg logit contributions | |
LOAD | -4.966 |
Pand | -4.909 |
Hunt | -4.603 |
mat | -4.530 |
democrat | -4.506 |
Token | irin |
Token ID | 47388 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
ortunate | +5.267 |
udo | +5.160 |
ciating | +4.976 |
lasses | +4.927 |
abouts | +4.914 |
Neg logit contributions | |
LOAD | -4.551 |
Pand | -4.510 |
Hunt | -4.251 |
democrat | -4.248 |
apopt | -4.130 |
Token | ig |
Token ID | 328 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
ortunate | +3.613 |
udo | +3.519 |
ciating | +3.489 |
lasses | +3.398 |
abouts | +3.387 |
Neg logit contributions | |
LOAD | -3.435 |
Pand | -3.398 |
democrat | -3.217 |
Hunt | -3.184 |
mat | -3.121 |
Token | sa |
Token ID | 473 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
ortunate | +3.150 |
udo | +3.063 |
ciating | +3.021 |
lasses | +2.976 |
abouts | +2.934 |
Neg logit contributions | |
LOAD | -2.893 |
Pand | -2.881 |
democrat | -2.722 |
Hunt | -2.693 |
mat | -2.650 |
Token | at |
Token ID | 379 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
ortunate | +5.604 |
udo | +5.485 |
ciating | +5.344 |
lasses | +5.262 |
abouts | +5.249 |
Neg logit contributions | |
LOAD | -4.748 |
Pand | -4.677 |
Hunt | -4.363 |
democrat | -4.304 |
mat | -4.249 |
Token | ing |
Token ID | 278 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ortunate | +4.598 |
udo | +4.501 |
ciating | +4.438 |
lasses | +4.373 |
abouts | +4.316 |
Neg logit contributions | |
LOAD | -3.759 |
Pand | -3.685 |
democrat | -3.490 |
Hunt | -3.445 |
apopt | -3.380 |
Token | gin |
Token ID | 39733 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
ortunate | +1.610 |
udo | +1.554 |
ciating | +1.552 |
lasses | +1.523 |
abouts | +1.496 |
Neg logit contributions | |
Pand | -1.498 |
LOAD | -1.493 |
democrat | -1.423 |
mat | -1.396 |
Hunt | -1.394 |
Token | ag |
Token ID | 363 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
ortunate | +2.390 |
udo | +2.321 |
ciating | +2.301 |
lasses | +2.264 |
abouts | +2.227 |
Neg logit contributions | |
Pand | -2.083 |
LOAD | -2.080 |
democrat | -1.969 |
Hunt | -1.927 |
mat | -1.919 |
Token | awa |
Token ID | 6909 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
ortunate | +2.578 |
udo | +2.509 |
ciating | +2.490 |
lasses | +2.447 |
abouts | +2.401 |
Neg logit contributions | |
Pand | -2.244 |
LOAD | -2.241 |
democrat | -2.130 |
Hunt | -2.088 |
mat | -2.078 |
Token | features |
Token ID | 3033 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
Pand | +0.265 |
LOAD | +0.263 |
democrat | +0.252 |
mat | +0.248 |
Hunt | +0.243 |
Neg logit contributions | |
ortunate | -0.366 |
ciating | -0.355 |
udo | -0.353 |
lasses | -0.348 |
abouts | -0.342 |
Token | for |
Token ID | 329 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Pand | +0.019 |
LOAD | +0.019 |
democrat | +0.018 |
mat | +0.018 |
Hunt | +0.017 |
Neg logit contributions | |
ortunate | -0.021 |
ciating | -0.020 |
udo | -0.020 |
lasses | -0.020 |
abouts | -0.020 |
Token | Lightning |
Token ID | 12469 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Pand | +0.759 |
LOAD | +0.753 |
democrat | +0.725 |
mat | +0.712 |
Hunt | +0.697 |
Neg logit contributions | |
ortunate | -0.947 |
ciating | -0.917 |
udo | -0.910 |
lasses | -0.896 |
abouts | -0.881 |
Token | , |
Token ID | 11 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
ortunate | +0.202 |
ciating | +0.196 |
udo | +0.194 |
lasses | +0.191 |
abouts | +0.188 |
Neg logit contributions | |
Pand | -0.171 |
LOAD | -0.169 |
democrat | -0.163 |
mat | -0.161 |
Hunt | -0.158 |
Token | a |
Token ID | 257 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Pand | +0.280 |
LOAD | +0.277 |
democrat | +0.268 |
mat | +0.264 |
Hunt | +0.259 |
Neg logit contributions | |
ortunate | -0.314 |
ciating | -0.304 |
udo | -0.301 |
lasses | -0.297 |
abouts | -0.291 |
Token | bid |
Token ID | 8406 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
ortunate | +0.137 |
ciating | +0.132 |
udo | +0.132 |
lasses | +0.130 |
abouts | +0.127 |
Neg logit contributions | |
Pand | -0.108 |
LOAD | -0.107 |
democrat | -0.103 |
mat | -0.101 |
Hunt | -0.099 |
Token | irection |
Token ID | 4154 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
LOAD | +3.436 |
Pand | +3.406 |
democrat | +3.293 |
mat | +3.255 |
hide | +3.139 |
Neg logit contributions | |
ortunate | -4.304 |
ciating | -4.221 |
udo | -4.078 |
lasses | -4.074 |
abouts | -3.967 |
Token | al |
Token ID | 282 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
Pand | +1.882 |
LOAD | +1.868 |
democrat | +1.808 |
mat | +1.791 |
Hunt | +1.768 |
Neg logit contributions | |
ortunate | -1.355 |
ciating | -1.297 |
udo | -1.288 |
lasses | -1.259 |
abouts | -1.233 |
Token | payment |
Token ID | 6074 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
Pand | +2.053 |
LOAD | +2.030 |
democrat | +1.971 |
mat | +1.903 |
apopt | +1.848 |
Neg logit contributions | |
ortunate | -3.828 |
ciating | -3.728 |
udo | -3.660 |
lasses | -3.649 |
abouts | -3.571 |
Token | channel |
Token ID | 6518 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Pand | +2.925 |
LOAD | +2.910 |
democrat | +2.846 |
mat | +2.806 |
apopt | +2.658 |
Neg logit contributions | |
ortunate | -5.113 |
ciating | -5.054 |
udo | -4.913 |
lasses | -4.873 |
abouts | -4.765 |
Token | proposal |
Token ID | 6961 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Pand | +0.068 |
LOAD | +0.068 |
democrat | +0.065 |
mat | +0.064 |
Hunt | +0.063 |
Neg logit contributions | |
ortunate | -0.076 |
ciating | -0.073 |
udo | -0.073 |
lasses | -0.072 |
abouts | -0.070 |
Token | you |
Token ID | 345 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
Pand | +1.151 |
LOAD | +1.140 |
democrat | +1.108 |
mat | +1.086 |
Hunt | +1.068 |
Neg logit contributions | |
ortunate | -1.519 |
ciating | -1.487 |
udo | -1.479 |
lasses | -1.451 |
abouts | -1.419 |
Token | must |
Token ID | 1276 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Pand | +0.442 |
LOAD | +0.438 |
democrat | +0.425 |
mat | +0.420 |
Hunt | +0.410 |
Neg logit contributions | |
ortunate | -0.426 |
ciating | -0.413 |
udo | -0.410 |
lasses | -0.403 |
abouts | -0.393 |
Token | make |
Token ID | 787 |
Feature activation | +5.42e-03 |
Pos logit contributions | |
ortunate | +0.143 |
ciating | +0.138 |
udo | +0.138 |
lasses | +0.136 |
abouts | +0.133 |
Neg logit contributions | |
Pand | -0.106 |
LOAD | -0.105 |
democrat | -0.101 |
mat | -0.099 |
Hunt | -0.098 |
Token | it |
Token ID | 340 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
Pand | +0.004 |
LOAD | +0.004 |
democrat | +0.004 |
mat | +0.003 |
Hunt | +0.003 |
Neg logit contributions | |
ortunate | -0.004 |
ciating | -0.004 |
udo | -0.004 |
lasses | -0.004 |
abouts | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ortunate | +0.405 |
ciating | +0.392 |
udo | +0.389 |
lasses | +0.383 |
abouts | +0.377 |
Neg logit contributions | |
Pand | -0.332 |
LOAD | -0.329 |
democrat | -0.315 |
mat | -0.311 |
Hunt | -0.306 |
Token | Either |
Token ID | 15467 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
Pand | +0.797 |
LOAD | +0.788 |
mat | +0.748 |
democrat | +0.748 |
Hunt | +0.743 |
Neg logit contributions | |
ortunate | -0.885 |
ciating | -0.858 |
udo | -0.844 |
lasses | -0.834 |
abouts | -0.819 |
Token | way |
Token ID | 835 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
Pand | +3.293 |
LOAD | +3.277 |
democrat | +3.247 |
mat | +3.137 |
Hunt | +3.091 |
Neg logit contributions | |
ortunate | -4.246 |
ciating | -4.181 |
udo | -4.091 |
lasses | -4.026 |
abouts | -3.941 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ortunate | +2.928 |
ciating | +2.820 |
udo | +2.812 |
abouts | +2.723 |
lasses | +2.699 |
Neg logit contributions | |
LOAD | -3.928 |
Pand | -3.928 |
mat | -3.724 |
Hunt | -3.690 |
democrat | -3.689 |
Token | my |
Token ID | 616 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
ortunate | +0.817 |
ciating | +0.789 |
udo | +0.786 |
lasses | +0.772 |
abouts | +0.759 |
Neg logit contributions | |
Pand | -0.721 |
LOAD | -0.714 |
democrat | -0.682 |
mat | -0.676 |
Hunt | -0.665 |
Token | first |
Token ID | 717 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
ortunate | +0.326 |
ciating | +0.316 |
udo | +0.314 |
lasses | +0.310 |
abouts | +0.305 |
Neg logit contributions | |
Pand | -0.224 |
LOAD | -0.222 |
democrat | -0.211 |
mat | -0.208 |
Hunt | -0.205 |
Token | three |
Token ID | 1115 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ortunate | +0.681 |
ciating | +0.660 |
udo | +0.659 |
lasses | +0.648 |
abouts | +0.640 |
Neg logit contributions | |
Pand | -0.404 |
LOAD | -0.400 |
democrat | -0.377 |
mat | -0.372 |
Hunt | -0.365 |
Token | going |
Token ID | 1016 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Pand | +1.018 |
LOAD | +1.018 |
democrat | +0.986 |
mat | +0.964 |
Hel | +0.933 |
Neg logit contributions | |
ortunate | -1.276 |
ciating | -1.247 |
udo | -1.227 |
lasses | -1.209 |
abouts | -1.190 |
Token | to |
Token ID | 284 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
ortunate | +1.077 |
udo | +1.041 |
ciating | +1.038 |
lasses | +1.018 |
abouts | +1.005 |
Neg logit contributions | |
Pand | -0.969 |
LOAD | -0.960 |
democrat | -0.914 |
mat | -0.909 |
Hunt | -0.898 |
Token | cave |
Token ID | 11527 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
ortunate | +0.426 |
ciating | +0.412 |
udo | +0.409 |
lasses | +0.403 |
abouts | +0.396 |
Neg logit contributions | |
Pand | -0.342 |
LOAD | -0.339 |
democrat | -0.327 |
mat | -0.321 |
Hunt | -0.315 |
Token | just |
Token ID | 655 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
Pand | +0.366 |
LOAD | +0.363 |
democrat | +0.349 |
mat | +0.346 |
Hunt | +0.338 |
Neg logit contributions | |
ortunate | -0.430 |
ciating | -0.416 |
udo | -0.413 |
lasses | -0.407 |
abouts | -0.399 |
Token | c |
Token ID | 269 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Pand | +0.291 |
LOAD | +0.288 |
democrat | +0.275 |
mat | +0.272 |
Hunt | +0.268 |
Neg logit contributions | |
ortunate | -0.372 |
ciating | -0.360 |
udo | -0.358 |
lasses | -0.352 |
abouts | -0.347 |
Token | uz |
Token ID | 10277 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
Pand | +0.225 |
LOAD | +0.223 |
democrat | +0.214 |
mat | +0.212 |
Hunt | +0.208 |
Neg logit contributions | |
ortunate | -0.246 |
ciating | -0.238 |
udo | -0.236 |
lasses | -0.233 |
abouts | -0.229 |
Token | he |
Token ID | 339 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Pand | +3.169 |
LOAD | +3.132 |
democrat | +3.128 |
mat | +3.011 |
donated | +2.944 |
Neg logit contributions | |
ortunate | -4.275 |
ciating | -4.189 |
lasses | -4.120 |
udo | -4.099 |
abouts | -3.973 |
Token | sends |
Token ID | 12800 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Pand | +0.602 |
LOAD | +0.596 |
democrat | +0.575 |
mat | +0.566 |
Hunt | +0.550 |
Neg logit contributions | |
ortunate | -0.844 |
ciating | -0.822 |
udo | -0.813 |
lasses | -0.802 |
abouts | -0.788 |
Token | me |
Token ID | 502 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Pand | +0.723 |
LOAD | +0.721 |
democrat | +0.699 |
mat | +0.684 |
apopt | +0.667 |
Neg logit contributions | |
ortunate | -0.841 |
ciating | -0.815 |
udo | -0.803 |
lasses | -0.791 |
abouts | -0.784 |
Token | a |
Token ID | 257 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
ortunate | +0.237 |
ciating | +0.230 |
udo | +0.228 |
lasses | +0.224 |
abouts | +0.221 |
Neg logit contributions | |
Pand | -0.201 |
LOAD | -0.200 |
democrat | -0.193 |
mat | -0.190 |
Hunt | -0.185 |
Token | note |
Token ID | 3465 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ortunate | +0.380 |
ciating | +0.366 |
udo | +0.364 |
lasses | +0.357 |
abouts | +0.351 |
Neg logit contributions | |
Pand | -0.428 |
LOAD | -0.425 |
democrat | -0.411 |
mat | -0.406 |
Hunt | -0.398 |
Token | at |
Token ID | 379 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
ortunate | +0.114 |
ciating | +0.110 |
udo | +0.110 |
lasses | +0.108 |
abouts | +0.106 |
Neg logit contributions | |
Pand | -0.096 |
LOAD | -0.095 |
democrat | -0.091 |
mat | -0.090 |
Hunt | -0.088 |
Token | events |
Token ID | 2995 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ortunate | +0.166 |
ciating | +0.160 |
udo | +0.160 |
lasses | +0.157 |
abouts | +0.155 |
Neg logit contributions | |
Pand | -0.147 |
LOAD | -0.145 |
democrat | -0.139 |
mat | -0.138 |
Hunt | -0.136 |
Token |
|
Token ID | 198 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
Pand | +0.672 |
LOAD | +0.666 |
democrat | +0.640 |
mat | +0.632 |
Hunt | +0.621 |
Neg logit contributions | |
ortunate | -0.827 |
ciating | -0.802 |
udo | -0.796 |
lasses | -0.784 |
abouts | -0.768 |
Token |
|
Token ID | 198 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Pand | +0.154 |
LOAD | +0.151 |
mat | +0.144 |
democrat | +0.141 |
Hunt | +0.140 |
Neg logit contributions | |
ortunate | -0.261 |
ciating | -0.259 |
udo | -0.249 |
lasses | -0.248 |
abouts | -0.244 |
Token | W |
Token ID | 54 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Pand | +0.353 |
LOAD | +0.350 |
democrat | +0.334 |
mat | +0.330 |
Hunt | +0.325 |
Neg logit contributions | |
ortunate | -0.459 |
ciating | -0.445 |
udo | -0.442 |
lasses | -0.435 |
abouts | -0.429 |
Token | AB |
Token ID | 6242 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
Pand | +0.357 |
LOAD | +0.353 |
democrat | +0.341 |
mat | +0.337 |
Hunt | +0.333 |
Neg logit contributions | |
ortunate | -0.329 |
ciating | -0.316 |
udo | -0.315 |
lasses | -0.308 |
abouts | -0.302 |
Token | L |
Token ID | 43 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
LOAD | +2.787 |
Pand | +2.645 |
Hunt | +2.429 |
mat | +2.422 |
Hel | +2.327 |
Neg logit contributions | |
ciating | -5.475 |
ortunate | -5.308 |
udo | -5.074 |
lasses | -4.963 |
abouts | -4.942 |
Token | M |
Token ID | 337 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
Pand | +0.579 |
LOAD | +0.573 |
democrat | +0.548 |
mat | +0.540 |
Hunt | +0.530 |
Neg logit contributions | |
ortunate | -0.820 |
ciating | -0.796 |
udo | -0.791 |
lasses | -0.779 |
abouts | -0.768 |
Token | EMBER |
Token ID | 28952 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Pand | +0.492 |
LOAD | +0.490 |
democrat | +0.468 |
mat | +0.465 |
Hunt | +0.456 |
Neg logit contributions | |
ortunate | -0.487 |
ciating | -0.475 |
udo | -0.465 |
lasses | -0.461 |
abouts | -0.457 |
Token | ST |
Token ID | 2257 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Pand | +0.207 |
LOAD | +0.205 |
democrat | +0.197 |
mat | +0.194 |
Hunt | +0.191 |
Neg logit contributions | |
ortunate | -0.260 |
ciating | -0.251 |
udo | -0.250 |
lasses | -0.246 |
abouts | -0.242 |
Token | o |
Token ID | 78 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
LOAD | +1.156 |
Pand | +1.154 |
democrat | +1.094 |
mat | +1.089 |
Hunt | +1.069 |
Neg logit contributions | |
ortunate | -1.218 |
ciating | -1.177 |
udo | -1.162 |
lasses | -1.142 |
abouts | -1.121 |
Token | a |
Token ID | 257 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Pand | +2.412 |
LOAD | +2.369 |
democrat | +2.361 |
mat | +2.282 |
apopt | +2.234 |
Neg logit contributions | |
ortunate | -2.701 |
udo | -2.626 |
ciating | -2.617 |
lasses | -2.596 |
abouts | -2.515 |
Token | book |
Token ID | 1492 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
Pand | +1.255 |
LOAD | +1.241 |
democrat | +1.213 |
mat | +1.177 |
Hunt | +1.147 |
Neg logit contributions | |
ortunate | -1.559 |
ciating | -1.516 |
udo | -1.505 |
lasses | -1.487 |
abouts | -1.460 |
Token | like |
Token ID | 588 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Pand | +2.009 |
LOAD | +2.001 |
democrat | +1.944 |
mat | +1.903 |
Hunt | +1.845 |
Neg logit contributions | |
ortunate | -2.607 |
ciating | -2.546 |
udo | -2.516 |
lasses | -2.487 |
abouts | -2.427 |
Token | X |
Token ID | 1395 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Pand | +1.557 |
LOAD | +1.523 |
democrat | +1.492 |
mat | +1.462 |
Hunt | +1.437 |
Neg logit contributions | |
ortunate | -1.969 |
ciating | -1.914 |
udo | -1.903 |
lasses | -1.882 |
abouts | -1.827 |
Token | - |
Token ID | 12 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
Pand | +1.967 |
LOAD | +1.950 |
democrat | +1.872 |
mat | +1.846 |
Hunt | +1.819 |
Neg logit contributions | |
ortunate | -2.151 |
ciating | -2.077 |
udo | -2.069 |
lasses | -2.029 |
abouts | -1.993 |
Token | O |
Token ID | 46 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
Pand | +2.837 |
LOAD | +2.785 |
mat | +2.668 |
democrat | +2.662 |
Hunt | +2.647 |
Neg logit contributions | |
ortunate | -3.025 |
ciating | -2.945 |
udo | -2.908 |
lasses | -2.863 |
abouts | -2.826 |
Token | and |
Token ID | 290 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
Pand | +3.312 |
LOAD | +3.252 |
democrat | +3.134 |
mat | +3.127 |
Hunt | +3.017 |
Neg logit contributions | |
ortunate | -5.428 |
ciating | -5.248 |
udo | -5.236 |
lasses | -5.181 |
abouts | -5.113 |
Token | we |
Token ID | 356 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
Pand | +1.990 |
democrat | +1.955 |
LOAD | +1.953 |
mat | +1.876 |
Hunt | +1.840 |
Neg logit contributions | |
ortunate | -2.640 |
ciating | -2.582 |
udo | -2.549 |
lasses | -2.525 |
abouts | -2.463 |
Token | say |
Token ID | 910 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
Pand | +0.354 |
LOAD | +0.350 |
democrat | +0.338 |
mat | +0.332 |
Hunt | +0.325 |
Neg logit contributions | |
ortunate | -0.464 |
ciating | -0.450 |
udo | -0.448 |
lasses | -0.440 |
abouts | -0.433 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Pand | +2.006 |
LOAD | +1.984 |
democrat | +1.946 |
mat | +1.899 |
Hunt | +1.861 |
Neg logit contributions | |
ortunate | -2.217 |
ciating | -2.154 |
udo | -2.139 |
lasses | -2.100 |
abouts | -2.057 |
Token | " |
Token ID | 366 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
Pand | +1.230 |
LOAD | +1.216 |
democrat | +1.189 |
mat | +1.166 |
Hunt | +1.142 |
Neg logit contributions | |
ortunate | -1.317 |
ciating | -1.279 |
udo | -1.275 |
lasses | -1.252 |
abouts | -1.231 |
Token | reading |
Token ID | 3555 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Pand | +1.752 |
LOAD | +1.751 |
democrat | +1.707 |
mat | +1.693 |
apopt | +1.651 |
Neg logit contributions | |
ortunate | -1.809 |
ciating | -1.777 |
udo | -1.737 |
lasses | -1.696 |
abouts | -1.643 |
Token | the |
Token ID | 262 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Pand | +1.607 |
LOAD | +1.595 |
mat | +1.544 |
democrat | +1.518 |
Hel | +1.498 |
Neg logit contributions | |
ciating | -2.071 |
ortunate | -2.053 |
udo | -1.980 |
lasses | -1.947 |
abouts | -1.886 |
Token | main |
Token ID | 1388 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
Pand | +1.248 |
LOAD | +1.229 |
democrat | +1.205 |
mat | +1.198 |
apopt | +1.161 |
Neg logit contributions | |
ciating | -1.803 |
ortunate | -1.802 |
udo | -1.747 |
lasses | -1.719 |
abouts | -1.677 |
Token | story |
Token ID | 1621 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
Pand | +1.090 |
LOAD | +1.062 |
democrat | +1.045 |
mat | +1.037 |
hide | +0.972 |
Neg logit contributions | |
ciating | -2.514 |
ortunate | -2.514 |
udo | -2.441 |
lasses | -2.421 |
abouts | -2.374 |
Token |
|
Token ID | 198 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Pand | +1.211 |
LOAD | +1.195 |
mat | +1.117 |
Hunt | +1.096 |
hide | +1.086 |
Neg logit contributions | |
ortunate | -2.230 |
ciating | -2.229 |
lasses | -2.118 |
udo | -2.118 |
abouts | -2.071 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Pand | +0.961 |
LOAD | +0.929 |
mat | +0.902 |
Hunt | +0.862 |
hide | +0.862 |
Neg logit contributions | |
ciating | -1.803 |
ortunate | -1.795 |
udo | -1.720 |
lasses | -1.704 |
abouts | -1.671 |
Token | Although |
Token ID | 7003 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Pand | +0.792 |
LOAD | +0.782 |
mat | +0.738 |
democrat | +0.731 |
Hunt | +0.727 |
Neg logit contributions | |
ortunate | -0.988 |
ciating | -0.960 |
udo | -0.946 |
lasses | -0.935 |
abouts | -0.917 |
Token | the |
Token ID | 262 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Pand | +0.183 |
LOAD | +0.181 |
democrat | +0.175 |
mat | +0.172 |
Hunt | +0.169 |
Neg logit contributions | |
ortunate | -0.218 |
ciating | -0.211 |
udo | -0.209 |
lasses | -0.206 |
abouts | -0.202 |
Token | mar |
Token ID | 1667 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
ortunate | +0.206 |
ciating | +0.200 |
udo | +0.198 |
lasses | +0.195 |
abouts | +0.192 |
Neg logit contributions | |
Pand | -0.158 |
LOAD | -0.157 |
democrat | -0.151 |
mat | -0.149 |
Hunt | -0.146 |
Token | chers |
Token ID | 3533 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
ortunate | +0.427 |
ciating | +0.411 |
udo | +0.409 |
lasses | +0.402 |
abouts | +0.395 |
Neg logit contributions | |
Pand | -0.436 |
LOAD | -0.433 |
democrat | -0.416 |
mat | -0.411 |
Hunt | -0.405 |
Token | celebrating |
Token ID | 17499 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
ortunate | +0.029 |
ciating | +0.028 |
udo | +0.028 |
lasses | +0.028 |
abouts | +0.027 |
Neg logit contributions | |
Pand | -0.022 |
LOAD | -0.022 |
democrat | -0.021 |
mat | -0.021 |
Hunt | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Pand | +0.660 |
LOAD | +0.656 |
democrat | +0.629 |
mat | +0.624 |
Hunt | +0.611 |
Neg logit contributions | |
ortunate | -0.763 |
ciating | -0.737 |
udo | -0.731 |
lasses | -0.722 |
abouts | -0.703 |
Token |
|
Token ID | 198 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
ortunate | +0.146 |
ciating | +0.141 |
udo | +0.141 |
lasses | +0.138 |
abouts | +0.137 |
Neg logit contributions | |
Pand | -0.108 |
LOAD | -0.107 |
democrat | -0.102 |
mat | -0.100 |
Hunt | -0.099 |
Token |
|
Token ID | 198 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
ortunate | +0.704 |
ciating | +0.691 |
udo | +0.677 |
lasses | +0.669 |
abouts | +0.657 |
Neg logit contributions | |
Pand | -0.443 |
LOAD | -0.435 |
mat | -0.413 |
democrat | -0.410 |
Hunt | -0.403 |
Token | T |
Token ID | 51 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ortunate | +0.253 |
ciating | +0.246 |
udo | +0.245 |
lasses | +0.241 |
abouts | +0.238 |
Neg logit contributions | |
Pand | -0.175 |
LOAD | -0.173 |
democrat | -0.168 |
mat | -0.163 |
apopt | -0.161 |
Token | ight |
Token ID | 432 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
Pand | +1.014 |
LOAD | +1.003 |
democrat | +0.952 |
mat | +0.946 |
Hunt | +0.921 |
Neg logit contributions | |
ortunate | -1.617 |
ciating | -1.580 |
udo | -1.560 |
lasses | -1.541 |
abouts | -1.523 |
Token | ening |
Token ID | 3101 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Pand | +3.521 |
LOAD | +3.513 |
democrat | +3.401 |
mat | +3.360 |
Hel | +3.228 |
Neg logit contributions | |
ortunate | -4.451 |
udo | -4.283 |
ciating | -4.271 |
lasses | -4.195 |
abouts | -4.054 |
Token | polls |
Token ID | 9231 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Pand | +1.363 |
LOAD | +1.338 |
democrat | +1.307 |
mat | +1.276 |
Hel | +1.246 |
Neg logit contributions | |
ortunate | -1.820 |
udo | -1.766 |
ciating | -1.760 |
lasses | -1.715 |
abouts | -1.684 |
Token |
|
Token ID | 198 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
ortunate | +1.326 |
udo | +1.288 |
ciating | +1.280 |
lasses | +1.256 |
abouts | +1.247 |
Neg logit contributions | |
Pand | -1.072 |
LOAD | -1.056 |
democrat | -1.003 |
mat | -0.994 |
Hunt | -0.986 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Pand | +0.280 |
LOAD | +0.274 |
mat | +0.260 |
democrat | +0.255 |
Hunt | +0.254 |
Neg logit contributions | |
ortunate | -0.467 |
ciating | -0.462 |
udo | -0.447 |
lasses | -0.444 |
abouts | -0.435 |
Token | A |
Token ID | 32 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
Pand | +0.724 |
LOAD | +0.715 |
democrat | +0.675 |
mat | +0.673 |
Hunt | +0.664 |
Neg logit contributions | |
ortunate | -0.993 |
ciating | -0.963 |
udo | -0.956 |
lasses | -0.944 |
abouts | -0.927 |
Token | G |
Token ID | 402 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
Pand | +0.520 |
LOAD | +0.516 |
democrat | +0.491 |
mat | +0.484 |
Hunt | +0.472 |
Neg logit contributions | |
ortunate | -0.819 |
ciating | -0.796 |
udo | -0.791 |
lasses | -0.782 |
abouts | -0.769 |
Token | off |
Token ID | 572 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ortunate | +1.315 |
ciating | +1.261 |
udo | +1.259 |
lasses | +1.239 |
abouts | +1.221 |
Neg logit contributions | |
Pand | -1.249 |
LOAD | -1.245 |
democrat | -1.191 |
mat | -1.175 |
Hunt | -1.158 |
Token | stump |
Token ID | 42497 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Pand | +1.491 |
LOAD | +1.479 |
democrat | +1.415 |
mat | +1.414 |
Hunt | +1.385 |
Neg logit contributions | |
ortunate | -1.625 |
ciating | -1.586 |
udo | -1.569 |
lasses | -1.529 |
abouts | -1.505 |
Token | and |
Token ID | 290 |
Feature activation | -9.03e-02 |
Pos logit contributions | |
ortunate | +1.016 |
ciating | +0.977 |
udo | +0.975 |
lasses | +0.958 |
abouts | +0.947 |
Neg logit contributions | |
Pand | -0.973 |
LOAD | -0.964 |
democrat | -0.925 |
mat | -0.912 |
Hunt | -0.900 |
Token | edged |
Token ID | 45871 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
ortunate | +0.071 |
ciating | +0.069 |
udo | +0.069 |
lasses | +0.068 |
abouts | +0.067 |
Neg logit contributions | |
Pand | -0.057 |
LOAD | -0.057 |
democrat | -0.054 |
mat | -0.054 |
Hunt | -0.053 |
Token | it |
Token ID | 340 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
Pand | +0.272 |
LOAD | +0.269 |
democrat | +0.259 |
mat | +0.255 |
Hunt | +0.251 |
Neg logit contributions | |
ortunate | -0.314 |
ciating | -0.305 |
udo | -0.302 |
lasses | -0.296 |
abouts | -0.291 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ortunate | +0.497 |
ciating | +0.481 |
udo | +0.478 |
lasses | +0.470 |
abouts | +0.463 |
Neg logit contributions | |
Pand | -0.423 |
LOAD | -0.419 |
democrat | -0.401 |
mat | -0.396 |
Hunt | -0.390 |
Token | Dh |
Token ID | 20529 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
Pand | +0.690 |
LOAD | +0.683 |
democrat | +0.656 |
mat | +0.648 |
Hunt | +0.638 |
Neg logit contributions | |
ortunate | -0.801 |
ciating | -0.778 |
udo | -0.772 |
lasses | -0.758 |
abouts | -0.743 |
Token | oni |
Token ID | 14651 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ortunate | +1.617 |
udo | +1.548 |
ciating | +1.535 |
lasses | +1.508 |
abouts | +1.482 |
Neg logit contributions | |
Pand | -2.078 |
LOAD | -2.071 |
democrat | -2.000 |
mat | -1.967 |
Hunt | -1.949 |
Token | . |
Token ID | 13 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
ortunate | +1.390 |
ciating | +1.343 |
udo | +1.340 |
lasses | +1.317 |
abouts | +1.301 |
Neg logit contributions | |
Pand | -1.120 |
LOAD | -1.112 |
democrat | -1.065 |
mat | -1.047 |
Hunt | -1.032 |
Token | Oh |
Token ID | 3966 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
ortunate | +0.317 |
ciating | +0.306 |
udo | +0.304 |
lasses | +0.299 |
abouts | +0.294 |
Neg logit contributions | |
Pand | -0.291 |
LOAD | -0.288 |
democrat | -0.276 |
mat | -0.273 |
Hunt | -0.269 |
Token | dear |
Token ID | 13674 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Pand | +1.406 |
LOAD | +1.391 |
democrat | +1.336 |
mat | +1.328 |
Hunt | +1.299 |
Neg logit contributions | |
ortunate | -1.472 |
ciating | -1.439 |
udo | -1.421 |
lasses | -1.388 |
abouts | -1.359 |
Token | , |
Token ID | 11 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Pand | +1.166 |
LOAD | +1.161 |
democrat | +1.121 |
mat | +1.103 |
Hunt | +1.081 |
Neg logit contributions | |
ortunate | -1.385 |
ciating | -1.344 |
udo | -1.328 |
lasses | -1.309 |
abouts | -1.289 |
Token | and |
Token ID | 290 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
ortunate | +1.009 |
udo | +0.976 |
ciating | +0.974 |
lasses | +0.958 |
abouts | +0.935 |
Neg logit contributions | |
Pand | -0.857 |
LOAD | -0.852 |
mat | -0.802 |
democrat | -0.801 |
Hunt | -0.793 |
Token | of |
Token ID | 286 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
ortunate | +0.354 |
udo | +0.343 |
ciating | +0.341 |
lasses | +0.335 |
abouts | +0.330 |
Neg logit contributions | |
Pand | -0.319 |
LOAD | -0.317 |
democrat | -0.299 |
mat | -0.299 |
Hunt | -0.295 |
Token | nuclear |
Token ID | 4523 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Pand | +0.144 |
LOAD | +0.142 |
democrat | +0.137 |
mat | +0.135 |
Hunt | +0.134 |
Neg logit contributions | |
ortunate | -0.142 |
ciating | -0.137 |
udo | -0.137 |
lasses | -0.134 |
abouts | -0.132 |
Token | weapons |
Token ID | 3777 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
ortunate | +1.030 |
udo | +1.003 |
ciating | +1.000 |
lasses | +0.988 |
abouts | +0.971 |
Neg logit contributions | |
Pand | -0.513 |
LOAD | -0.506 |
democrat | -0.466 |
mat | -0.464 |
Hunt | -0.458 |
Token | in |
Token ID | 287 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Pand | +1.771 |
LOAD | +1.765 |
democrat | +1.708 |
mat | +1.676 |
Hunt | +1.640 |
Neg logit contributions | |
ortunate | -2.136 |
ciating | -2.067 |
udo | -2.039 |
lasses | -2.016 |
abouts | -1.985 |
Token | particular |
Token ID | 1948 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Pand | +1.588 |
LOAD | +1.566 |
democrat | +1.539 |
mat | +1.502 |
apopt | +1.466 |
Neg logit contributions | |
ortunate | -1.678 |
ciating | -1.619 |
udo | -1.588 |
lasses | -1.572 |
abouts | -1.552 |
Token | … |
Token ID | 1399 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
Pand | +1.459 |
LOAD | +1.444 |
democrat | +1.396 |
mat | +1.372 |
Hunt | +1.342 |
Neg logit contributions | |
ortunate | -1.803 |
ciating | -1.746 |
udo | -1.723 |
lasses | -1.700 |
abouts | -1.674 |
Token | The |
Token ID | 464 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
Pand | +0.543 |
LOAD | +0.536 |
democrat | +0.513 |
mat | +0.508 |
Hunt | +0.499 |
Neg logit contributions | |
ortunate | -0.689 |
ciating | -0.668 |
udo | -0.661 |
lasses | -0.654 |
abouts | -0.642 |
Token | non |
Token ID | 1729 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
Pand | +0.485 |
LOAD | +0.480 |
democrat | +0.461 |
mat | +0.452 |
Hunt | +0.443 |
Neg logit contributions | |
ortunate | -0.661 |
ciating | -0.640 |
udo | -0.636 |
lasses | -0.627 |
abouts | -0.618 |
Token | - |
Token ID | 12 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Pand | +0.568 |
LOAD | +0.564 |
democrat | +0.537 |
mat | +0.531 |
Hunt | +0.529 |
Neg logit contributions | |
ortunate | -0.607 |
udo | -0.584 |
ciating | -0.584 |
lasses | -0.570 |
abouts | -0.563 |
Token | at |
Token ID | 379 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
ortunate | +0.387 |
ciating | +0.374 |
udo | +0.371 |
lasses | +0.365 |
abouts | +0.359 |
Neg logit contributions | |
Pand | -0.367 |
LOAD | -0.364 |
democrat | -0.349 |
mat | -0.346 |
Hunt | -0.340 |
Token | the |
Token ID | 262 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
ortunate | +0.449 |
ciating | +0.434 |
udo | +0.432 |
lasses | +0.425 |
abouts | +0.417 |
Neg logit contributions | |
Pand | -0.399 |
LOAD | -0.396 |
democrat | -0.380 |
mat | -0.375 |
Hunt | -0.370 |
Token | European |
Token ID | 3427 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
Pand | +0.270 |
LOAD | +0.267 |
democrat | +0.256 |
mat | +0.253 |
Hunt | +0.248 |
Neg logit contributions | |
ortunate | -0.363 |
ciating | -0.353 |
udo | -0.351 |
lasses | -0.345 |
abouts | -0.340 |
Token | Beer |
Token ID | 16971 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
Pand | +0.366 |
LOAD | +0.362 |
democrat | +0.349 |
mat | +0.345 |
Hunt | +0.341 |
Neg logit contributions | |
ortunate | -0.385 |
ciating | -0.374 |
udo | -0.368 |
lasses | -0.364 |
abouts | -0.357 |
Token | Blog |
Token ID | 14001 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Pand | +0.245 |
LOAD | +0.241 |
democrat | +0.231 |
mat | +0.231 |
Hunt | +0.226 |
Neg logit contributions | |
ortunate | -0.306 |
ciating | -0.298 |
udo | -0.295 |
lasses | -0.291 |
abouts | -0.285 |
Token | gers |
Token ID | 5355 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
ortunate | +0.881 |
udo | +0.848 |
ciating | +0.847 |
lasses | +0.830 |
abouts | +0.818 |
Neg logit contributions | |
Pand | -0.792 |
LOAD | -0.785 |
democrat | -0.753 |
mat | -0.740 |
Hunt | -0.731 |
Token | Conference |
Token ID | 8785 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
Pand | +0.538 |
LOAD | +0.532 |
democrat | +0.511 |
mat | +0.506 |
Hunt | +0.498 |
Neg logit contributions | |
ortunate | -0.627 |
ciating | -0.609 |
udo | -0.601 |
lasses | -0.595 |
abouts | -0.584 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ortunate | +0.683 |
ciating | +0.660 |
udo | +0.657 |
lasses | +0.646 |
abouts | +0.635 |
Neg logit contributions | |
Pand | -0.590 |
LOAD | -0.585 |
democrat | -0.561 |
mat | -0.554 |
Hunt | -0.546 |
Token | as |
Token ID | 355 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
ortunate | +0.996 |
ciating | +0.964 |
udo | +0.960 |
lasses | +0.944 |
abouts | +0.929 |
Neg logit contributions | |
Pand | -0.798 |
LOAD | -0.791 |
democrat | -0.756 |
mat | -0.747 |
Hunt | -0.735 |
Token | I |
Token ID | 314 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
ortunate | +0.674 |
ciating | +0.649 |
udo | +0.647 |
lasses | +0.636 |
abouts | +0.624 |
Neg logit contributions | |
Pand | -0.622 |
LOAD | -0.618 |
democrat | -0.591 |
mat | -0.585 |
Hunt | -0.577 |
Token | mentioned |
Token ID | 4750 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Pand | +1.466 |
LOAD | +1.454 |
democrat | +1.447 |
mat | +1.424 |
donated | +1.370 |
Neg logit contributions | |
ortunate | -2.106 |
ciating | -2.096 |
udo | -2.031 |
lasses | -2.005 |
abouts | -1.988 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ortunate | +0.019 |
ciating | +0.019 |
udo | +0.019 |
lasses | +0.018 |
abouts | +0.018 |
Neg logit contributions | |
Pand | -0.018 |
LOAD | -0.018 |
democrat | -0.017 |
mat | -0.017 |
Hunt | -0.016 |
Token | pioneering |
Token ID | 36304 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
ortunate | +1.402 |
udo | +1.349 |
ciating | +1.346 |
lasses | +1.334 |
abouts | +1.309 |
Neg logit contributions | |
Pand | -1.011 |
LOAD | -1.005 |
democrat | -0.939 |
mat | -0.938 |
Hunt | -0.926 |
Token | test |
Token ID | 1332 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Pand | +0.309 |
LOAD | +0.306 |
democrat | +0.289 |
mat | +0.286 |
Hunt | +0.282 |
Neg logit contributions | |
ortunate | -0.452 |
ciating | -0.438 |
udo | -0.436 |
lasses | -0.430 |
abouts | -0.424 |
Token | pilot |
Token ID | 8022 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ortunate | +2.155 |
udo | +2.118 |
ciating | +2.083 |
lasses | +2.050 |
abouts | +2.025 |
Neg logit contributions | |
Pand | -1.300 |
LOAD | -1.298 |
democrat | -1.188 |
Hunt | -1.177 |
apopt | -1.167 |
Token | , |
Token ID | 11 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ortunate | +1.043 |
ciating | +0.998 |
udo | +0.997 |
lasses | +0.980 |
abouts | +0.967 |
Neg logit contributions | |
Pand | -1.044 |
LOAD | -1.037 |
democrat | -0.985 |
mat | -0.978 |
Hunt | -0.970 |
Token | but |
Token ID | 475 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ortunate | +0.963 |
ciating | +0.923 |
udo | +0.918 |
lasses | +0.907 |
abouts | +0.890 |
Neg logit contributions | |
Pand | -0.882 |
LOAD | -0.877 |
democrat | -0.833 |
mat | -0.828 |
Hunt | -0.818 |
Token | also |
Token ID | 635 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ortunate | +1.733 |
ciating | +1.653 |
udo | +1.647 |
lasses | +1.635 |
abouts | +1.600 |
Neg logit contributions | |
Pand | -1.742 |
LOAD | -1.733 |
democrat | -1.634 |
mat | -1.628 |
Hunt | -1.622 |
Token | as |
Token ID | 355 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ortunate | +1.654 |
ciating | +1.579 |
udo | +1.575 |
lasses | +1.563 |
abouts | +1.536 |
Neg logit contributions | |
LOAD | -1.455 |
Pand | -1.449 |
democrat | -1.352 |
mat | -1.349 |
Hunt | -1.349 |
Token | a |
Token ID | 257 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ortunate | +0.902 |
ciating | +0.861 |
udo | +0.858 |
lasses | +0.849 |
abouts | +0.829 |
Neg logit contributions | |
Pand | -0.916 |
LOAD | -0.914 |
democrat | -0.863 |
mat | -0.856 |
Hunt | -0.854 |
Token | military |
Token ID | 2422 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
ortunate | +0.854 |
ciating | +0.823 |
udo | +0.822 |
lasses | +0.810 |
abouts | +0.798 |
Neg logit contributions | |
Pand | -0.590 |
LOAD | -0.586 |
democrat | -0.549 |
mat | -0.547 |
Hunt | -0.542 |
Token | av |
Token ID | 1196 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
Pand | +0.275 |
LOAD | +0.272 |
democrat | +0.260 |
mat | +0.255 |
Hunt | +0.249 |
Neg logit contributions | |
ortunate | -0.467 |
ciating | -0.455 |
udo | -0.452 |
lasses | -0.445 |
abouts | -0.440 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ortunate | +0.457 |
ciating | +0.442 |
udo | +0.440 |
lasses | +0.433 |
abouts | +0.426 |
Neg logit contributions | |
Pand | -0.346 |
LOAD | -0.343 |
democrat | -0.327 |
mat | -0.323 |
Hunt | -0.318 |
Token |
|
Token ID | 198 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
ortunate | +0.999 |
ciating | +0.978 |
udo | +0.962 |
lasses | +0.950 |
abouts | +0.935 |
Neg logit contributions | |
Pand | -0.649 |
LOAD | -0.640 |
democrat | -0.605 |
mat | -0.604 |
Hunt | -0.591 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
ortunate | +0.417 |
ciating | +0.403 |
udo | +0.402 |
lasses | +0.395 |
abouts | +0.389 |
Neg logit contributions | |
Pand | -0.327 |
LOAD | -0.324 |
democrat | -0.310 |
mat | -0.306 |
Hunt | -0.301 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Pand | +0.035 |
LOAD | +0.035 |
mat | +0.033 |
democrat | +0.033 |
Hunt | +0.032 |
Neg logit contributions | |
ortunate | -0.042 |
ciating | -0.042 |
udo | -0.041 |
lasses | -0.040 |
abouts | -0.039 |
Token | Keep |
Token ID | 9175 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
ortunate | +1.191 |
udo | +1.147 |
ciating | +1.146 |
lasses | +1.122 |
abouts | +1.101 |
Neg logit contributions | |
Pand | -1.192 |
LOAD | -1.184 |
democrat | -1.141 |
mat | -1.126 |
Hunt | -1.109 |
Token | your |
Token ID | 534 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
Pand | +0.335 |
LOAD | +0.329 |
democrat | +0.317 |
mat | +0.315 |
Hunt | +0.307 |
Neg logit contributions | |
ortunate | -0.374 |
ciating | -0.362 |
udo | -0.360 |
lasses | -0.353 |
abouts | -0.347 |
Token | Kindle |
Token ID | 27114 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ortunate | +0.680 |
ciating | +0.658 |
udo | +0.655 |
lasses | +0.645 |
abouts | +0.634 |
Neg logit contributions | |
Pand | -0.525 |
LOAD | -0.520 |
democrat | -0.498 |
mat | -0.491 |
Hunt | -0.482 |
Token | � |
Token ID | 447 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
ortunate | +1.119 |
ciating | +1.080 |
udo | +1.078 |
lasses | +1.059 |
abouts | +1.042 |
Neg logit contributions | |
Pand | -0.909 |
LOAD | -0.900 |
democrat | -0.861 |
mat | -0.850 |
Hunt | -0.838 |
Token | � |
Token ID | 247 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
ortunate | +0.367 |
ciating | +0.361 |
udo | +0.356 |
lasses | +0.353 |
abouts | +0.350 |
Neg logit contributions | |
Pand | -0.116 |
LOAD | -0.115 |
democrat | -0.104 |
mat | -0.101 |
Hunt | -0.099 |
Token | s |
Token ID | 82 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
ortunate | +0.005 |
ciating | +0.005 |
udo | +0.005 |
lasses | +0.005 |
abouts | +0.005 |
Neg logit contributions | |
Pand | -0.005 |
LOAD | -0.005 |
democrat | -0.004 |
mat | -0.004 |
Hunt | -0.004 |
Token | wireless |
Token ID | 12521 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
Pand | +0.369 |
LOAD | +0.365 |
democrat | +0.350 |
mat | +0.346 |
Hunt | +0.336 |
Neg logit contributions | |
ortunate | -0.503 |
ciating | -0.489 |
udo | -0.484 |
lasses | -0.479 |
abouts | -0.471 |
Token | fist |
Token ID | 18606 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
ortunate | +2.202 |
udo | +2.136 |
ciating | +2.134 |
lasses | +2.098 |
abouts | +2.060 |
Neg logit contributions | |
Pand | -1.615 |
LOAD | -1.602 |
democrat | -1.506 |
mat | -1.492 |
Hunt | -1.485 |
Token | while |
Token ID | 981 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
Pand | +0.424 |
LOAD | +0.422 |
mat | +0.407 |
democrat | +0.405 |
Hunt | +0.391 |
Neg logit contributions | |
ortunate | -0.503 |
ciating | -0.487 |
udo | -0.481 |
lasses | -0.470 |
abouts | -0.468 |
Token | an |
Token ID | 281 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ortunate | +0.036 |
ciating | +0.035 |
udo | +0.035 |
lasses | +0.034 |
abouts | +0.034 |
Neg logit contributions | |
Pand | -0.029 |
LOAD | -0.029 |
democrat | -0.028 |
mat | -0.027 |
Hunt | -0.027 |
Token | ambulance |
Token ID | 22536 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ortunate | +0.163 |
ciating | +0.157 |
udo | +0.156 |
lasses | +0.153 |
abouts | +0.152 |
Neg logit contributions | |
Pand | -0.145 |
LOAD | -0.143 |
democrat | -0.138 |
mat | -0.136 |
Hunt | -0.134 |
Token | s |
Token ID | 264 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ortunate | +1.287 |
ciating | +1.243 |
udo | +1.242 |
lasses | +1.224 |
abouts | +1.207 |
Neg logit contributions | |
Pand | -0.945 |
LOAD | -0.928 |
democrat | -0.876 |
mat | -0.874 |
Hunt | -0.869 |
Token | iren |
Token ID | 24080 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Pand | +0.174 |
LOAD | +0.172 |
democrat | +0.166 |
mat | +0.164 |
Hunt | +0.162 |
Neg logit contributions | |
ortunate | -0.162 |
ciating | -0.156 |
udo | -0.155 |
lasses | -0.152 |
abouts | -0.149 |
Token | w |
Token ID | 266 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
ortunate | +0.139 |
ciating | +0.135 |
udo | +0.134 |
lasses | +0.132 |
abouts | +0.130 |
Neg logit contributions | |
Pand | -0.110 |
LOAD | -0.109 |
democrat | -0.104 |
mat | -0.103 |
Hunt | -0.101 |
Token | ailed |
Token ID | 6255 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Pand | +0.482 |
LOAD | +0.477 |
democrat | +0.453 |
mat | +0.446 |
Hunt | +0.438 |
Neg logit contributions | |
ortunate | -0.740 |
ciating | -0.718 |
udo | -0.716 |
lasses | -0.704 |
abouts | -0.694 |
Token | outside |
Token ID | 2354 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ortunate | +0.202 |
ciating | +0.196 |
udo | +0.195 |
lasses | +0.191 |
abouts | +0.188 |
Neg logit contributions | |
Pand | -0.174 |
LOAD | -0.172 |
democrat | -0.165 |
mat | -0.163 |
Hunt | -0.160 |
Token | her |
Token ID | 607 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
ortunate | +1.250 |
ciating | +1.212 |
udo | +1.206 |
lasses | +1.188 |
abouts | +1.170 |
Neg logit contributions | |
Pand | -1.238 |
LOAD | -1.234 |
democrat | -1.184 |
mat | -1.170 |
Hunt | -1.158 |
Token | window |
Token ID | 4324 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
Pand | +0.244 |
LOAD | +0.242 |
democrat | +0.234 |
mat | +0.231 |
Hunt | +0.227 |
Neg logit contributions | |
ortunate | -0.219 |
ciating | -0.211 |
udo | -0.210 |
lasses | -0.205 |
abouts | -0.202 |
Token | uncontrolled |
Token ID | 47913 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ortunate | +2.482 |
udo | +2.402 |
ciating | +2.381 |
lasses | +2.343 |
abouts | +2.316 |
Neg logit contributions | |
Pand | -1.940 |
LOAD | -1.929 |
mat | -1.818 |
Hunt | -1.807 |
democrat | -1.804 |
Token | prescriptions |
Token ID | 34092 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
ortunate | +0.902 |
udo | +0.873 |
ciating | +0.871 |
lasses | +0.855 |
abouts | +0.845 |
Neg logit contributions | |
Pand | -0.688 |
LOAD | -0.682 |
democrat | -0.648 |
mat | -0.643 |
Hunt | -0.634 |
Token | need |
Token ID | 761 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
ortunate | +0.479 |
udo | +0.461 |
ciating | +0.459 |
lasses | +0.452 |
abouts | +0.447 |
Neg logit contributions | |
Pand | -0.432 |
LOAD | -0.428 |
democrat | -0.405 |
mat | -0.402 |
Hunt | -0.399 |
Token | not |
Token ID | 407 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
ortunate | +2.245 |
udo | +2.156 |
ciating | +2.154 |
lasses | +2.105 |
abouts | +2.090 |
Neg logit contributions | |
Pand | -2.592 |
LOAD | -2.587 |
democrat | -2.481 |
Hunt | -2.427 |
mat | -2.412 |
Token | create |
Token ID | 2251 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
ortunate | +0.696 |
udo | +0.670 |
ciating | +0.664 |
lasses | +0.655 |
abouts | +0.647 |
Neg logit contributions | |
Pand | -0.686 |
LOAD | -0.681 |
democrat | -0.641 |
mat | -0.638 |
Hunt | -0.637 |
Token | a |
Token ID | 257 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
ortunate | +3.265 |
udo | +3.158 |
lasses | +3.110 |
ciating | +3.101 |
abouts | +3.035 |
Neg logit contributions | |
LOAD | -2.775 |
Pand | -2.760 |
mat | -2.612 |
Hunt | -2.604 |
democrat | -2.570 |
Token | whole |
Token ID | 2187 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Pand | +0.215 |
LOAD | +0.213 |
democrat | +0.202 |
mat | +0.200 |
Hunt | +0.197 |
Neg logit contributions | |
ortunate | -0.332 |
ciating | -0.322 |
udo | -0.321 |
lasses | -0.316 |
abouts | -0.311 |
Token | new |
Token ID | 649 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
Pand | +1.007 |
LOAD | +0.993 |
democrat | +0.952 |
mat | +0.933 |
Hunt | +0.913 |
Neg logit contributions | |
ortunate | -1.333 |
ciating | -1.290 |
udo | -1.284 |
lasses | -1.262 |
abouts | -1.243 |
Token | population |
Token ID | 3265 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
Pand | +0.514 |
LOAD | +0.507 |
democrat | +0.485 |
mat | +0.476 |
Hunt | +0.467 |
Neg logit contributions | |
ortunate | -0.736 |
ciating | -0.714 |
udo | -0.709 |
lasses | -0.698 |
abouts | -0.690 |
Token | of |
Token ID | 286 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
ortunate | +0.024 |
udo | +0.023 |
ciating | +0.023 |
lasses | +0.023 |
abouts | +0.023 |
Neg logit contributions | |
Pand | -0.021 |
LOAD | -0.021 |
democrat | -0.020 |
mat | -0.020 |
Hunt | -0.020 |
Token | chronic |
Token ID | 10726 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ortunate | +0.759 |
ciating | +0.735 |
udo | +0.733 |
lasses | +0.721 |
abouts | +0.711 |
Neg logit contributions | |
Pand | -0.533 |
LOAD | -0.527 |
democrat | -0.502 |
mat | -0.496 |
Hunt | -0.488 |
Token | . |
Token ID | 13 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
ortunate | +1.111 |
udo | +1.082 |
ciating | +1.066 |
lasses | +1.055 |
abouts | +1.031 |
Neg logit contributions | |
LOAD | -0.972 |
Pand | -0.965 |
democrat | -0.918 |
mat | -0.895 |
apopt | -0.888 |
Token | Cullen |
Token ID | 47681 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ortunate | +2.012 |
udo | +1.958 |
ciating | +1.935 |
lasses | +1.919 |
abouts | +1.876 |
Neg logit contributions | |
LOAD | -1.473 |
Pand | -1.468 |
democrat | -1.402 |
mat | -1.365 |
apopt | -1.347 |
Token | said |
Token ID | 531 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Pand | +0.188 |
LOAD | +0.186 |
democrat | +0.178 |
mat | +0.175 |
Hunt | +0.172 |
Neg logit contributions | |
ortunate | -0.269 |
ciating | -0.261 |
udo | -0.259 |
lasses | -0.255 |
abouts | -0.251 |
Token | the |
Token ID | 262 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
Pand | +0.753 |
LOAD | +0.746 |
democrat | +0.719 |
mat | +0.708 |
Hunt | +0.698 |
Neg logit contributions | |
ortunate | -0.841 |
ciating | -0.814 |
udo | -0.808 |
lasses | -0.795 |
abouts | -0.780 |
Token | federal |
Token ID | 2717 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
ortunate | +0.045 |
ciating | +0.044 |
udo | +0.044 |
lasses | +0.043 |
abouts | +0.042 |
Neg logit contributions | |
Pand | -0.034 |
LOAD | -0.033 |
democrat | -0.032 |
mat | -0.031 |
Hunt | -0.031 |
Token | Finance |
Token ID | 15007 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
Pand | +1.403 |
LOAD | +1.393 |
democrat | +1.362 |
mat | +1.333 |
Hunt | +1.308 |
Neg logit contributions | |
ortunate | -1.514 |
ciating | -1.469 |
udo | -1.447 |
lasses | -1.428 |
abouts | -1.398 |
Token | Department |
Token ID | 2732 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
Pand | +0.369 |
LOAD | +0.367 |
democrat | +0.353 |
mat | +0.349 |
Hunt | +0.344 |
Neg logit contributions | |
ortunate | -0.374 |
ciating | -0.361 |
udo | -0.359 |
lasses | -0.352 |
abouts | -0.346 |
Token | study |
Token ID | 2050 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
ortunate | +0.563 |
udo | +0.544 |
ciating | +0.542 |
lasses | +0.533 |
abouts | +0.527 |
Neg logit contributions | |
Pand | -0.470 |
LOAD | -0.463 |
democrat | -0.440 |
mat | -0.436 |
Hunt | -0.431 |
Token | needs |
Token ID | 2476 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
ortunate | +2.544 |
udo | +2.465 |
ciating | +2.442 |
lasses | +2.406 |
abouts | +2.392 |
Neg logit contributions | |
Pand | -1.900 |
LOAD | -1.872 |
democrat | -1.746 |
mat | -1.728 |
Hunt | -1.725 |
Token | to |
Token ID | 284 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
ortunate | +2.101 |
udo | +2.051 |
ciating | +2.048 |
lasses | +1.980 |
abouts | +1.966 |
Neg logit contributions | |
Pand | -2.183 |
LOAD | -2.146 |
democrat | -2.045 |
Hunt | -2.045 |
mat | -2.012 |
Token | focus |
Token ID | 2962 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
ortunate | +1.206 |
udo | +1.154 |
ciating | +1.151 |
lasses | +1.128 |
abouts | +1.112 |
Neg logit contributions | |
Pand | -1.507 |
LOAD | -1.499 |
democrat | -1.422 |
mat | -1.411 |
Hunt | -1.410 |
Token | - |
Token ID | 12 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
LOAD | +0.343 |
Pand | +0.343 |
mat | +0.325 |
Hel | +0.320 |
Hunt | +0.319 |
Neg logit contributions | |
ciating | -0.493 |
ortunate | -0.486 |
lasses | -0.466 |
udo | -0.461 |
abouts | -0.454 |
Token | 09 |
Token ID | 2931 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
Pand | +1.381 |
LOAD | +1.352 |
Hunt | +1.295 |
mat | +1.280 |
hide | +1.257 |
Neg logit contributions | |
ciating | -1.865 |
ortunate | -1.834 |
lasses | -1.722 |
udo | -1.718 |
abouts | -1.671 |
Token | - |
Token ID | 12 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
ortunate | +0.481 |
ciating | +0.479 |
udo | +0.459 |
lasses | +0.456 |
abouts | +0.446 |
Neg logit contributions | |
Pand | -0.376 |
LOAD | -0.371 |
mat | -0.355 |
democrat | -0.346 |
Hunt | -0.345 |
Token | 20 |
Token ID | 1238 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
ortunate | +1.131 |
ciating | +1.115 |
udo | +1.071 |
lasses | +1.061 |
abouts | +1.035 |
Neg logit contributions | |
Pand | -1.203 |
LOAD | -1.193 |
mat | -1.137 |
Hunt | -1.128 |
democrat | -1.122 |
Token | 01 |
Token ID | 5534 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ortunate | +3.295 |
udo | +3.184 |
ciating | +3.161 |
lasses | +3.118 |
abouts | +3.089 |
Neg logit contributions | |
Pand | -2.778 |
LOAD | -2.755 |
democrat | -2.664 |
mat | -2.613 |
Hunt | -2.563 |
Token | : |
Token ID | 25 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
ortunate | +0.884 |
ciating | +0.867 |
udo | +0.849 |
lasses | +0.841 |
abouts | +0.825 |
Neg logit contributions | |
Pand | -0.577 |
LOAD | -0.568 |
mat | -0.538 |
democrat | -0.534 |
Hunt | -0.526 |
Token | 44 |
Token ID | 2598 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
ortunate | +3.285 |
udo | +3.199 |
lasses | +3.105 |
ciating | +3.097 |
abouts | +3.055 |
Neg logit contributions | |
Pand | -3.481 |
LOAD | -3.480 |
democrat | -3.418 |
apopt | -3.272 |
mat | -3.272 |
Token | : |
Token ID | 25 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
ortunate | +3.295 |
udo | +3.232 |
ciating | +3.138 |
lasses | +3.136 |
abouts | +3.118 |
Neg logit contributions | |
LOAD | -2.630 |
Pand | -2.618 |
democrat | -2.558 |
mat | -2.430 |
apopt | -2.422 |
Token | 24 |
Token ID | 1731 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
ortunate | +3.176 |
udo | +3.084 |
ciating | +3.005 |
lasses | +3.002 |
abouts | +2.957 |
Neg logit contributions | |
Pand | -3.252 |
LOAD | -3.248 |
democrat | -3.175 |
mat | -3.055 |
apopt | -3.045 |
Token | # |
Token ID | 1303 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
ortunate | +2.162 |
ciating | +2.078 |
udo | +2.066 |
lasses | +2.025 |
abouts | +1.986 |
Neg logit contributions | |
Pand | -2.521 |
LOAD | -2.501 |
democrat | -2.412 |
mat | -2.388 |
Hunt | -2.356 |
Token | 19 |
Token ID | 1129 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
ortunate | +2.539 |
ciating | +2.473 |
udo | +2.425 |
lasses | +2.389 |
abouts | +2.350 |
Neg logit contributions | |
Pand | -2.812 |
LOAD | -2.781 |
democrat | -2.675 |
mat | -2.662 |
Hunt | -2.624 |
Token | G |
Token ID | 38 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ortunate | +1.344 |
udo | +1.297 |
ciating | +1.282 |
lasses | +1.273 |
abouts | +1.258 |
Neg logit contributions | |
Pand | -1.224 |
LOAD | -1.206 |
democrat | -1.169 |
mat | -1.136 |
apopt | -1.133 |
Token | MI |
Token ID | 8895 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ortunate | +1.493 |
udo | +1.442 |
lasses | +1.422 |
ciating | +1.400 |
abouts | +1.388 |
Neg logit contributions | |
Pand | -1.289 |
LOAD | -1.260 |
democrat | -1.232 |
Hunt | -1.192 |
mat | -1.189 |
Token | ). |
Token ID | 737 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
Pand | +0.927 |
LOAD | +0.917 |
democrat | +0.876 |
mat | +0.865 |
Hunt | +0.850 |
Neg logit contributions | |
ortunate | -1.239 |
ciating | -1.200 |
udo | -1.194 |
lasses | -1.175 |
abouts | -1.157 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ortunate | +0.535 |
ciating | +0.518 |
udo | +0.514 |
lasses | +0.506 |
abouts | +0.497 |
Neg logit contributions | |
Pand | -0.443 |
LOAD | -0.439 |
democrat | -0.420 |
mat | -0.416 |
Hunt | -0.408 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ortunate | +1.113 |
ciating | +1.091 |
udo | +1.071 |
lasses | +1.059 |
abouts | +1.041 |
Neg logit contributions | |
Pand | -0.716 |
LOAD | -0.705 |
democrat | -0.667 |
mat | -0.667 |
Hunt | -0.652 |
Token | Block |
Token ID | 12235 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
ortunate | +0.857 |
ciating | +0.828 |
udo | +0.826 |
lasses | +0.812 |
abouts | +0.799 |
Neg logit contributions | |
Pand | -0.678 |
LOAD | -0.673 |
democrat | -0.645 |
mat | -0.635 |
Hunt | -0.624 |
Token | chain |
Token ID | 7983 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
ortunate | +2.440 |
ciating | +2.320 |
udo | +2.308 |
lasses | +2.238 |
abouts | +2.220 |
Neg logit contributions | |
Pand | -3.897 |
LOAD | -3.878 |
democrat | -3.729 |
mat | -3.673 |
Hunt | -3.658 |
Token | cities |
Token ID | 4736 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
ortunate | +1.855 |
ciating | +1.791 |
udo | +1.788 |
lasses | +1.763 |
abouts | +1.735 |
Neg logit contributions | |
Pand | -1.509 |
LOAD | -1.501 |
democrat | -1.407 |
mat | -1.397 |
Hunt | -1.386 |
Token |
|
Token ID | 198 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Pand | +0.439 |
LOAD | +0.434 |
democrat | +0.421 |
mat | +0.414 |
Hunt | +0.406 |
Neg logit contributions | |
ortunate | -0.496 |
ciating | -0.480 |
udo | -0.476 |
lasses | -0.470 |
abouts | -0.458 |
Token |
|
Token ID | 198 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
Pand | +0.202 |
LOAD | +0.198 |
mat | +0.188 |
democrat | +0.185 |
Hunt | +0.183 |
Neg logit contributions | |
ortunate | -0.343 |
ciating | -0.341 |
udo | -0.329 |
lasses | -0.326 |
abouts | -0.320 |
Token | We |
Token ID | 1135 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Pand | +0.625 |
LOAD | +0.613 |
mat | +0.582 |
democrat | +0.574 |
Hunt | +0.572 |
Neg logit contributions | |
ortunate | -0.802 |
ciating | -0.783 |
udo | -0.766 |
lasses | -0.759 |
abouts | -0.745 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
ortunate | +0.268 |
ciating | +0.256 |
udo | +0.255 |
lasses | +0.249 |
abouts | +0.244 |
Neg logit contributions | |
Pand | -0.420 |
LOAD | -0.417 |
democrat | -0.405 |
mat | -0.400 |
Hunt | -0.396 |
Token |
|
Token ID | 198 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Pand | +2.462 |
LOAD | +2.443 |
mat | +2.343 |
democrat | +2.328 |
Hunt | +2.278 |
Neg logit contributions | |
ortunate | -3.271 |
ciating | -3.148 |
udo | -3.105 |
lasses | -3.071 |
abouts | -3.005 |
Token |
|
Token ID | 198 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Pand | +0.141 |
LOAD | +0.139 |
mat | +0.132 |
democrat | +0.129 |
Hunt | +0.128 |
Neg logit contributions | |
ortunate | -0.240 |
ciating | -0.238 |
udo | -0.230 |
lasses | -0.228 |
abouts | -0.224 |
Token | Read |
Token ID | 5569 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Pand | +0.209 |
LOAD | +0.207 |
democrat | +0.197 |
mat | +0.195 |
Hunt | +0.191 |
Neg logit contributions | |
ortunate | -0.299 |
ciating | -0.290 |
udo | -0.288 |
lasses | -0.284 |
abouts | -0.280 |
Token | or |
Token ID | 393 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Pand | +0.945 |
LOAD | +0.941 |
democrat | +0.906 |
mat | +0.899 |
Hunt | +0.873 |
Neg logit contributions | |
ortunate | -1.129 |
ciating | -1.097 |
udo | -1.079 |
lasses | -1.061 |
abouts | -1.046 |
Token | Share |
Token ID | 8734 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
ortunate | +1.719 |
ciating | +1.676 |
udo | +1.666 |
lasses | +1.647 |
abouts | +1.624 |
Neg logit contributions | |
Pand | -0.795 |
LOAD | -0.784 |
democrat | -0.742 |
mat | -0.725 |
Hunt | -0.706 |
Token | this |
Token ID | 428 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ortunate | +3.703 |
udo | +3.585 |
ciating | +3.567 |
lasses | +3.521 |
abouts | +3.468 |
Neg logit contributions | |
Pand | -2.909 |
LOAD | -2.874 |
democrat | -2.745 |
mat | -2.713 |
Hunt | -2.663 |
Token | story |
Token ID | 1621 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
ortunate | +1.741 |
ciating | +1.693 |
udo | +1.684 |
lasses | +1.661 |
abouts | +1.638 |
Neg logit contributions | |
Pand | -0.982 |
LOAD | -0.971 |
democrat | -0.921 |
mat | -0.906 |
Hunt | -0.887 |
Token | : |
Token ID | 25 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
Pand | +1.097 |
LOAD | +1.081 |
mat | +1.043 |
democrat | +1.034 |
Hunt | +0.998 |
Neg logit contributions | |
ortunate | -2.056 |
ciating | -2.040 |
udo | -1.991 |
lasses | -1.961 |
abouts | -1.909 |
Token | http |
Token ID | 2638 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
Pand | +1.083 |
LOAD | +1.072 |
democrat | +1.015 |
mat | +0.998 |
Hunt | +0.972 |
Neg logit contributions | |
ortunate | -2.082 |
ciating | -2.020 |
udo | -2.011 |
lasses | -1.987 |
abouts | -1.960 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
LOAD | +2.004 |
Pand | +1.982 |
mat | +1.947 |
hide | +1.857 |
Hunt | +1.823 |
Neg logit contributions | |
ciating | -4.298 |
ortunate | -4.223 |
lasses | -4.038 |
abouts | -3.968 |
udo | -3.967 |
Token | j |
Token ID | 73 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
ortunate | +0.238 |
udo | +0.221 |
ciating | +0.219 |
lasses | +0.214 |
abouts | +0.206 |
Neg logit contributions | |
Pand | -0.571 |
LOAD | -0.566 |
democrat | -0.549 |
Hunt | -0.539 |
mat | -0.537 |
Token | ' |
Token ID | 6 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
ortunate | +2.791 |
udo | +2.709 |
ciating | +2.669 |
lasses | +2.636 |
abouts | +2.574 |
Neg logit contributions | |
Pand | -2.495 |
LOAD | -2.445 |
democrat | -2.364 |
Hunt | -2.319 |
mat | -2.297 |
Token | OR |
Token ID | 6375 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ortunate | +0.355 |
ciating | +0.342 |
udo | +0.341 |
lasses | +0.335 |
abouts | +0.328 |
Neg logit contributions | |
Pand | -0.341 |
LOAD | -0.337 |
democrat | -0.324 |
mat | -0.320 |
Hunt | -0.316 |
Token | path |
Token ID | 3108 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
ortunate | +0.916 |
ciating | +0.884 |
udo | +0.882 |
lasses | +0.868 |
abouts | +0.856 |
Neg logit contributions | |
Pand | -0.656 |
LOAD | -0.647 |
democrat | -0.615 |
mat | -0.609 |
Hunt | -0.603 |
Token | LIKE |
Token ID | 34178 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ortunate | +2.584 |
udo | +2.538 |
ciating | +2.484 |
lasses | +2.475 |
abouts | +2.393 |
Neg logit contributions | |
Pand | -2.166 |
LOAD | -2.130 |
democrat | -2.073 |
Hunt | -2.018 |
mat | -2.009 |
Token | ' |
Token ID | 705 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
Pand | +1.252 |
LOAD | +1.241 |
democrat | +1.198 |
mat | +1.189 |
Hunt | +1.181 |
Neg logit contributions | |
ortunate | -0.883 |
ciating | -0.847 |
udo | -0.841 |
lasses | -0.819 |
abouts | -0.799 |
Token | % |
Token ID | 4 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ortunate | +4.443 |
udo | +4.337 |
ciating | +4.292 |
lasses | +4.236 |
abouts | +4.204 |
Neg logit contributions | |
Pand | -2.079 |
LOAD | -1.995 |
democrat | -1.936 |
Hunt | -1.853 |
apopt | -1.848 |
Token | build |
Token ID | 11249 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
ortunate | +1.002 |
ciating | +0.957 |
udo | +0.955 |
lasses | +0.935 |
abouts | +0.917 |
Neg logit contributions | |
Pand | -1.264 |
LOAD | -1.249 |
democrat | -1.210 |
mat | -1.191 |
Hunt | -1.183 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ortunate | +1.489 |
udo | +1.448 |
ciating | +1.421 |
lasses | +1.404 |
abouts | +1.389 |
Neg logit contributions | |
Pand | -1.651 |
LOAD | -1.613 |
democrat | -1.568 |
Hunt | -1.523 |
apopt | -1.522 |
Token | boot |
Token ID | 18769 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
ortunate | +0.907 |
udo | +0.856 |
ciating | +0.850 |
lasses | +0.838 |
abouts | +0.793 |
Neg logit contributions | |
Pand | -2.155 |
LOAD | -2.102 |
democrat | -2.064 |
Hunt | -2.034 |
apopt | -2.014 |
Token | ' |
Token ID | 6 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Pand | +0.329 |
LOAD | +0.321 |
democrat | +0.313 |
mat | +0.305 |
Hunt | +0.304 |
Neg logit contributions | |
ortunate | -0.351 |
udo | -0.338 |
ciating | -0.337 |
lasses | -0.331 |
abouts | -0.325 |
Token |
|
Token ID | 198 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
ortunate | +1.048 |
ciating | +1.023 |
udo | +1.010 |
lasses | +0.997 |
abouts | +0.981 |
Neg logit contributions | |
Pand | -0.690 |
LOAD | -0.681 |
democrat | -0.646 |
mat | -0.642 |
Hunt | -0.629 |
Token | And |
Token ID | 1870 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
ortunate | +0.824 |
ciating | +0.799 |
udo | +0.797 |
lasses | +0.785 |
abouts | +0.775 |
Neg logit contributions | |
Pand | -0.506 |
LOAD | -0.501 |
democrat | -0.479 |
mat | -0.468 |
Hunt | -0.459 |
Token | so |
Token ID | 523 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ortunate | +0.659 |
ciating | +0.639 |
udo | +0.637 |
lasses | +0.627 |
abouts | +0.618 |
Neg logit contributions | |
Pand | -0.410 |
LOAD | -0.405 |
democrat | -0.385 |
mat | -0.379 |
Hunt | -0.372 |
Token | to |
Token ID | 284 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
Pand | +1.308 |
LOAD | +1.291 |
democrat | +1.245 |
mat | +1.230 |
Hunt | +1.203 |
Neg logit contributions | |
ortunate | -1.590 |
ciating | -1.547 |
udo | -1.533 |
lasses | -1.491 |
abouts | -1.457 |
Token | the |
Token ID | 262 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Pand | +0.451 |
LOAD | +0.447 |
democrat | +0.431 |
mat | +0.426 |
Hunt | +0.416 |
Neg logit contributions | |
ortunate | -0.519 |
ciating | -0.503 |
udo | -0.499 |
lasses | -0.490 |
abouts | -0.481 |
Token | Members |
Token ID | 12688 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
ortunate | +0.233 |
ciating | +0.226 |
udo | +0.225 |
lasses | +0.221 |
abouts | +0.218 |
Neg logit contributions | |
Pand | -0.183 |
LOAD | -0.181 |
democrat | -0.173 |
mat | -0.170 |
Hunt | -0.168 |
Token | and |
Token ID | 290 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ortunate | +3.263 |
udo | +3.179 |
ciating | +3.163 |
lasses | +3.086 |
abouts | +3.082 |
Neg logit contributions | |
LOAD | -2.880 |
Pand | -2.843 |
democrat | -2.701 |
mat | -2.671 |
apopt | -2.658 |
Token | a |
Token ID | 257 |
Feature activation | -6.34e-02 |
Pos logit contributions | |
ortunate | +2.089 |
udo | +2.016 |
ciating | +2.007 |
lasses | +1.976 |
abouts | +1.957 |
Neg logit contributions | |
Pand | -1.821 |
LOAD | -1.804 |
democrat | -1.715 |
mat | -1.705 |
Hunt | -1.685 |
Token | beer |
Token ID | 6099 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ortunate | +0.048 |
ciating | +0.047 |
udo | +0.046 |
lasses | +0.046 |
abouts | +0.045 |
Neg logit contributions | |
Pand | -0.042 |
LOAD | -0.042 |
democrat | -0.040 |
mat | -0.040 |
Hunt | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ortunate | +0.077 |
ciating | +0.075 |
udo | +0.074 |
lasses | +0.073 |
abouts | +0.072 |
Neg logit contributions | |
Pand | -0.066 |
LOAD | -0.066 |
democrat | -0.063 |
mat | -0.063 |
Hunt | -0.061 |
Token | … |
Token ID | 3926 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
ortunate | +1.880 |
udo | +1.814 |
ciating | +1.809 |
lasses | +1.789 |
abouts | +1.758 |
Neg logit contributions | |
Pand | -1.732 |
LOAD | -1.721 |
democrat | -1.643 |
mat | -1.627 |
Hunt | -1.612 |