Token | . |
Token ID | 13 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Franch | +0.448 |
tti | +0.425 |
Maj | +0.396 |
inker | +0.392 |
uve | +0.388 |
Neg logit contributions | |
20439 | -0.522 |
Sexual | -0.428 |
Clo | -0.400 |
isolation | -0.395 |
sheltered | -0.393 |
Token | Featuring |
Token ID | 39778 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
20439 | +0.132 |
Sexual | +0.106 |
Clo | +0.099 |
isolation | +0.097 |
sheltered | +0.096 |
Neg logit contributions | |
Franch | -0.139 |
tti | -0.133 |
Maj | -0.124 |
inker | -0.124 |
uve | -0.122 |
Token | all |
Token ID | 477 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
20439 | +0.225 |
Sexual | +0.183 |
Clo | +0.172 |
isolation | +0.169 |
sheltered | +0.168 |
Neg logit contributions | |
Franch | -0.218 |
tti | -0.209 |
Maj | -0.193 |
inker | -0.193 |
uve | -0.192 |
Token | of |
Token ID | 286 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Franch | +0.204 |
tti | +0.194 |
Maj | +0.180 |
inker | +0.179 |
uve | +0.177 |
Neg logit contributions | |
20439 | -0.229 |
Sexual | -0.188 |
Clo | -0.176 |
isolation | -0.173 |
sheltered | -0.172 |
Token | Greg |
Token ID | 8547 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Franch | +0.473 |
tti | +0.450 |
Maj | +0.420 |
inker | +0.416 |
uve | +0.412 |
Neg logit contributions | |
20439 | -0.493 |
Sexual | -0.400 |
Clo | -0.371 |
isolation | -0.367 |
sheltered | -0.365 |
Token | Ber |
Token ID | 4312 |
Feature activation | +6.68e+00 |
Pos logit contributions | |
Franch | +0.293 |
tti | +0.281 |
inker | +0.257 |
rieg | +0.255 |
Maj | +0.255 |
Neg logit contributions | |
20439 | -0.375 |
Sexual | -0.312 |
Clo | -0.295 |
isolation | -0.289 |
sheltered | -0.289 |
Token | l |
Token ID | 75 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Franch | +4.645 |
tti | +4.644 |
inker | +4.437 |
Maj | +4.408 |
rieg | +4.321 |
Neg logit contributions | |
20439 | -5.766 |
Sexual | -4.301 |
isolation | -4.275 |
apes | -4.254 |
sheltered | -4.230 |
Token | anti |
Token ID | 17096 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Franch | +1.165 |
tti | +1.121 |
inker | +1.063 |
Maj | +1.062 |
rieg | +1.060 |
Neg logit contributions | |
20439 | -0.601 |
Sexual | -0.441 |
Clo | -0.393 |
isolation | -0.381 |
sheltered | -0.376 |
Token | � |
Token ID | 447 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Franch | +0.359 |
tti | +0.342 |
Maj | +0.317 |
inker | +0.315 |
uve | +0.312 |
Neg logit contributions | |
20439 | -0.404 |
Sexual | -0.331 |
Clo | -0.309 |
isolation | -0.305 |
sheltered | -0.304 |
Token | � |
Token ID | 247 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
Franch | +1.557 |
tti | +1.526 |
Maj | +1.427 |
inker | +1.417 |
rieg | +1.405 |
Neg logit contributions | |
20439 | -1.456 |
Sexual | -1.147 |
Clo | -1.074 |
isolation | -1.056 |
sheltered | -1.049 |
Token | s |
Token ID | 82 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
Franch | +0.781 |
tti | +0.749 |
Maj | +0.705 |
inker | +0.700 |
uve | +0.695 |
Neg logit contributions | |
20439 | -0.610 |
Sexual | -0.474 |
Clo | -0.436 |
isolation | -0.428 |
sheltered | -0.426 |
Token | icle |
Token ID | 1548 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
Franch | +1.444 |
tti | +1.377 |
Maj | +1.281 |
inker | +1.272 |
uve | +1.261 |
Neg logit contributions | |
20439 | -1.551 |
Sexual | -1.259 |
Clo | -1.176 |
isolation | -1.157 |
sheltered | -1.154 |
Token | :: |
Token ID | 3712 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Franch | +0.640 |
tti | +0.609 |
Maj | +0.568 |
inker | +0.563 |
uve | +0.558 |
Neg logit contributions | |
20439 | -0.669 |
Sexual | -0.542 |
Clo | -0.506 |
isolation | -0.498 |
sheltered | -0.496 |
Token | Get |
Token ID | 3855 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
20439 | +0.165 |
Sexual | +0.133 |
Clo | +0.123 |
isolation | +0.121 |
sheltered | +0.120 |
Neg logit contributions | |
Franch | -0.173 |
tti | -0.165 |
Maj | -0.154 |
inker | -0.153 |
uve | -0.152 |
Token | Mass |
Token ID | 20273 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
Franch | +0.662 |
tti | +0.632 |
Maj | +0.591 |
inker | +0.587 |
uve | +0.582 |
Neg logit contributions | |
20439 | -0.621 |
Sexual | -0.498 |
Clo | -0.461 |
isolation | -0.454 |
sheltered | -0.452 |
Token | ( |
Token ID | 7 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
20439 | +0.376 |
Sexual | +0.309 |
Clo | +0.289 |
isolation | +0.285 |
sheltered | +0.283 |
Neg logit contributions | |
Franch | -0.323 |
tti | -0.307 |
Maj | -0.284 |
inker | -0.283 |
rieg | -0.280 |
Token | float |
Token ID | 12178 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
Franch | +1.064 |
tti | +1.014 |
Maj | +0.939 |
inker | +0.933 |
uve | +0.921 |
Neg logit contributions | |
20439 | -1.283 |
Sexual | -1.051 |
Clo | -0.990 |
isolation | -0.973 |
sheltered | -0.968 |
Token | ambient |
Token ID | 25237 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Franch | +4.896 |
tti | +4.708 |
Maj | +4.445 |
inker | +4.311 |
rieg | +4.264 |
Neg logit contributions | |
20439 | -5.046 |
Sexual | -4.116 |
ileaks | -3.762 |
Clo | -3.704 |
apes | -3.676 |
Token | D |
Token ID | 35 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Franch | +1.361 |
tti | +1.299 |
Maj | +1.207 |
inker | +1.196 |
uve | +1.188 |
Neg logit contributions | |
20439 | -1.484 |
Sexual | -1.204 |
Clo | -1.128 |
sheltered | -1.105 |
isolation | -1.105 |
Token | ensity |
Token ID | 6377 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Franch | +0.270 |
tti | +0.256 |
Maj | +0.236 |
inker | +0.234 |
uve | +0.232 |
Neg logit contributions | |
20439 | -0.340 |
Sexual | -0.281 |
Clo | -0.264 |
isolation | -0.261 |
sheltered | -0.260 |
Token | ) |
Token ID | 1267 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
Franch | +1.245 |
tti | +1.186 |
Maj | +1.107 |
inker | +1.098 |
uve | +1.089 |
Neg logit contributions | |
20439 | -1.267 |
Sexual | -1.024 |
Clo | -0.954 |
isolation | -0.939 |
sheltered | -0.935 |
Token | const |
Token ID | 1500 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
Franch | +0.681 |
tti | +0.650 |
Maj | +0.608 |
inker | +0.602 |
uve | +0.596 |
Neg logit contributions | |
20439 | -0.675 |
Sexual | -0.543 |
Clo | -0.504 |
isolation | -0.496 |
sheltered | -0.494 |
Token | one |
Token ID | 530 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Franch | +0.118 |
tti | +0.112 |
Maj | +0.105 |
inker | +0.104 |
uve | +0.103 |
Neg logit contributions | |
20439 | -0.120 |
Sexual | -0.097 |
Clo | -0.090 |
isolation | -0.089 |
sheltered | -0.088 |
Token | barely |
Token ID | 8523 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Franch | +1.963 |
tti | +1.876 |
Maj | +1.770 |
inker | +1.736 |
uve | +1.727 |
Neg logit contributions | |
20439 | -1.955 |
Sexual | -1.565 |
Clo | -1.445 |
ileaks | -1.431 |
isolation | -1.413 |
Token | has |
Token ID | 468 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
Franch | +1.994 |
tti | +1.907 |
Maj | +1.806 |
inker | +1.770 |
uve | +1.768 |
Neg logit contributions | |
20439 | -1.792 |
Sexual | -1.419 |
Clo | -1.289 |
ileaks | -1.282 |
IRC | -1.259 |
Token | to |
Token ID | 284 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Franch | +0.578 |
tti | +0.550 |
Maj | +0.514 |
inker | +0.507 |
uve | +0.504 |
Neg logit contributions | |
20439 | -0.618 |
Sexual | -0.502 |
Clo | -0.466 |
isolation | -0.458 |
ileaks | -0.457 |
Token | squ |
Token ID | 2809 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
20439 | +0.097 |
Sexual | +0.078 |
Clo | +0.073 |
isolation | +0.072 |
sheltered | +0.071 |
Neg logit contributions | |
Franch | -0.103 |
tti | -0.098 |
Maj | -0.091 |
inker | -0.091 |
uve | -0.090 |
Token | int |
Token ID | 600 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
Franch | +0.193 |
tti | +0.186 |
Maj | +0.176 |
inker | +0.175 |
uve | +0.173 |
Neg logit contributions | |
20439 | -0.127 |
Sexual | -0.096 |
Clo | -0.087 |
isolation | -0.086 |
sheltered | -0.085 |
Token | to |
Token ID | 284 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
Franch | +4.545 |
tti | +4.336 |
Maj | +4.068 |
inker | +4.017 |
rieg | +3.984 |
Neg logit contributions | |
20439 | -5.374 |
Sexual | -4.421 |
Clo | -4.056 |
ileaks | -4.054 |
IRC | -4.024 |
Token | be |
Token ID | 307 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Franch | +0.446 |
tti | +0.423 |
Maj | +0.392 |
inker | +0.389 |
rieg | +0.386 |
Neg logit contributions | |
20439 | -0.530 |
Sexual | -0.436 |
Clo | -0.411 |
isolation | -0.405 |
sheltered | -0.403 |
Token | transported |
Token ID | 18665 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
Franch | +0.144 |
tti | +0.137 |
Maj | +0.127 |
inker | +0.127 |
rieg | +0.126 |
Neg logit contributions | |
20439 | -0.145 |
Sexual | -0.117 |
Clo | -0.110 |
sheltered | -0.108 |
isolation | -0.108 |
Token | back |
Token ID | 736 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
Franch | +0.203 |
tti | +0.193 |
Maj | +0.179 |
inker | +0.178 |
rieg | +0.176 |
Neg logit contributions | |
20439 | -0.220 |
Sexual | -0.179 |
Clo | -0.168 |
isolation | -0.166 |
sheltered | -0.165 |
Token | to |
Token ID | 284 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
20439 | +0.258 |
Sexual | +0.210 |
Clo | +0.197 |
isolation | +0.194 |
sheltered | +0.194 |
Neg logit contributions | |
Franch | -0.240 |
tti | -0.228 |
inker | -0.211 |
Maj | -0.211 |
uve | -0.209 |
Token | Try |
Token ID | 9993 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Franch | +1.028 |
tti | +0.978 |
Maj | +0.904 |
inker | +0.894 |
rieg | +0.878 |
Neg logit contributions | |
20439 | -1.208 |
Sexual | -0.995 |
Clo | -0.924 |
isolation | -0.915 |
sheltered | -0.914 |
Token | { |
Token ID | 1391 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
20439 | +0.215 |
Sexual | +0.173 |
Clo | +0.161 |
isolation | +0.159 |
sheltered | +0.158 |
Neg logit contributions | |
Franch | -0.218 |
tti | -0.208 |
Maj | -0.194 |
inker | -0.193 |
uve | -0.192 |
Token | for |
Token ID | 329 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Franch | +1.213 |
tti | +1.146 |
Maj | +1.064 |
inker | +1.047 |
rieg | +1.032 |
Neg logit contributions | |
20439 | -1.517 |
Sexual | -1.252 |
Clo | -1.164 |
sheltered | -1.151 |
ileaks | -1.148 |
Token | ($ |
Token ID | 7198 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Franch | +1.316 |
tti | +1.236 |
Maj | +1.124 |
inker | +1.112 |
uve | +1.097 |
Neg logit contributions | |
20439 | -2.197 |
Sexual | -1.857 |
Clo | -1.758 |
isolation | -1.737 |
sheltered | -1.732 |
Token | i |
Token ID | 72 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Franch | +1.394 |
tti | +1.323 |
Maj | +1.190 |
inker | +1.188 |
rieg | +1.163 |
Neg logit contributions | |
20439 | -2.312 |
Sexual | -1.949 |
Clo | -1.851 |
isolation | -1.829 |
sheltered | -1.822 |
Token | ; |
Token ID | 2162 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
Franch | +1.327 |
tti | +1.265 |
Maj | +1.169 |
inker | +1.160 |
rieg | +1.142 |
Neg logit contributions | |
20439 | -1.661 |
Sexual | -1.371 |
Clo | -1.287 |
isolation | -1.267 |
sheltered | -1.265 |
Token | $ |
Token ID | 720 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
Franch | +3.208 |
tti | +3.048 |
Maj | +2.673 |
inker | +2.664 |
uve | +2.533 |
Neg logit contributions | |
20439 | -6.693 |
Sexual | -5.706 |
sheltered | -5.353 |
Clo | -5.333 |
isolation | -5.311 |
Token | i |
Token ID | 72 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
Franch | +1.417 |
tti | +1.351 |
inker | +1.209 |
Maj | +1.199 |
uve | +1.179 |
Neg logit contributions | |
20439 | -2.551 |
Sexual | -2.158 |
Clo | -2.058 |
isolation | -2.037 |
sheltered | -2.028 |
Token | - |
Token ID | 532 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Franch | +0.022 |
tti | +0.021 |
Maj | +0.019 |
inker | +0.019 |
uve | +0.019 |
Neg logit contributions | |
20439 | -0.018 |
Sexual | -0.014 |
Clo | -0.013 |
isolation | -0.013 |
sheltered | -0.013 |
Token | le |
Token ID | 293 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Franch | +0.012 |
tti | +0.011 |
Maj | +0.011 |
inker | +0.011 |
uve | +0.010 |
Neg logit contributions | |
20439 | -0.012 |
Sexual | -0.010 |
Clo | -0.009 |
isolation | -0.009 |
sheltered | -0.009 |
Token | $ |
Token ID | 720 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Franch | +1.557 |
tti | +1.468 |
Maj | +1.350 |
inker | +1.345 |
rieg | +1.329 |
Neg logit contributions | |
20439 | -2.145 |
Sexual | -1.791 |
Clo | -1.690 |
isolation | -1.669 |
sheltered | -1.659 |
Token | plus |
Token ID | 5556 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
Franch | +1.032 |
tti | +0.983 |
Maj | +0.916 |
inker | +0.906 |
uve | +0.900 |
Neg logit contributions | |
20439 | -1.132 |
Sexual | -0.920 |
Clo | -0.857 |
sheltered | -0.841 |
ileaks | -0.840 |
Token | deviation |
Token ID | 28833 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Franch | +0.527 |
tti | +0.493 |
Maj | +0.447 |
inker | +0.443 |
uve | +0.438 |
Neg logit contributions | |
20439 | -0.915 |
Sexual | -0.776 |
Clo | -0.736 |
isolation | -0.730 |
sheltered | -0.726 |
Token | . |
Token ID | 13 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
Franch | +1.617 |
tti | +1.552 |
Maj | +1.436 |
inker | +1.414 |
rieg | +1.400 |
Neg logit contributions | |
20439 | -2.089 |
Sexual | -1.738 |
Clo | -1.624 |
ileaks | -1.602 |
sheltered | -1.592 |
Token |
|
Token ID | 198 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
Franch | +0.753 |
tti | +0.718 |
Maj | +0.671 |
inker | +0.661 |
uve | +0.654 |
Neg logit contributions | |
20439 | -0.765 |
Sexual | -0.618 |
Clo | -0.570 |
sheltered | -0.566 |
isolation | -0.565 |
Token |
|
Token ID | 198 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Franch | +0.640 |
tti | +0.614 |
Maj | +0.575 |
inker | +0.562 |
rieg | +0.555 |
Neg logit contributions | |
20439 | -0.717 |
Sexual | -0.572 |
ileaks | -0.538 |
isolation | -0.538 |
Clo | -0.537 |
Token | float |
Token ID | 22468 |
Feature activation | +6.13e+00 |
Pos logit contributions | |
Franch | +0.268 |
tti | +0.255 |
Maj | +0.238 |
inker | +0.236 |
uve | +0.234 |
Neg logit contributions | |
20439 | -0.282 |
Sexual | -0.229 |
Clo | -0.214 |
isolation | -0.211 |
sheltered | -0.209 |
Token | Part |
Token ID | 2142 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Franch | +4.596 |
tti | +4.408 |
Maj | +4.170 |
inker | +3.958 |
uve | +3.935 |
Neg logit contributions | |
20439 | -5.084 |
Sexual | -4.173 |
ileaks | -3.851 |
aeus | -3.848 |
IRC | -3.762 |
Token | icle |
Token ID | 1548 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
Franch | +1.444 |
tti | +1.377 |
Maj | +1.281 |
inker | +1.272 |
uve | +1.261 |
Neg logit contributions | |
20439 | -1.551 |
Sexual | -1.259 |
Clo | -1.176 |
isolation | -1.157 |
sheltered | -1.154 |
Token | :: |
Token ID | 3712 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Franch | +0.640 |
tti | +0.609 |
Maj | +0.568 |
inker | +0.563 |
uve | +0.558 |
Neg logit contributions | |
20439 | -0.669 |
Sexual | -0.542 |
Clo | -0.506 |
isolation | -0.498 |
sheltered | -0.496 |
Token | Get |
Token ID | 3855 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
20439 | +0.165 |
Sexual | +0.133 |
Clo | +0.123 |
isolation | +0.121 |
sheltered | +0.120 |
Neg logit contributions | |
Franch | -0.173 |
tti | -0.165 |
Maj | -0.154 |
inker | -0.153 |
uve | -0.152 |
Token | Mass |
Token ID | 20273 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
Franch | +0.662 |
tti | +0.632 |
Maj | +0.591 |
inker | +0.587 |
uve | +0.582 |
Neg logit contributions | |
20439 | -0.621 |
Sexual | -0.498 |
Clo | -0.461 |
isolation | -0.454 |
sheltered | -0.452 |
Token | Mil |
Token ID | 4460 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Franch | +0.753 |
tti | +0.715 |
Maj | +0.670 |
inker | +0.659 |
rieg | +0.653 |
Neg logit contributions | |
20439 | -0.823 |
Sexual | -0.670 |
Clo | -0.623 |
ileaks | -0.611 |
isolation | -0.610 |
Token | it |
Token ID | 270 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
Franch | +0.820 |
tti | +0.791 |
inker | +0.730 |
Maj | +0.729 |
rieg | +0.722 |
Neg logit contributions | |
20439 | -0.850 |
Sexual | -0.684 |
Clo | -0.636 |
isolation | -0.631 |
sheltered | -0.624 |
Token | ants |
Token ID | 1187 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
20439 | +0.709 |
Sexual | +0.571 |
Clo | +0.532 |
isolation | +0.524 |
sheltered | +0.521 |
Neg logit contributions | |
Franch | -0.716 |
tti | -0.683 |
Maj | -0.638 |
inker | -0.632 |
uve | -0.629 |
Token | if |
Token ID | 611 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
20439 | +0.424 |
Sexual | +0.346 |
Clo | +0.324 |
isolation | +0.323 |
sheltered | +0.320 |
Neg logit contributions | |
Franch | -0.395 |
tti | -0.375 |
Maj | -0.348 |
inker | -0.348 |
uve | -0.344 |
Token | one |
Token ID | 530 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
Franch | +1.077 |
tti | +1.027 |
Maj | +0.957 |
inker | +0.950 |
uve | +0.942 |
Neg logit contributions | |
20439 | -1.116 |
Sexual | -0.904 |
Clo | -0.843 |
isolation | -0.831 |
sheltered | -0.827 |
Token | failed |
Token ID | 4054 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
Franch | +2.571 |
tti | +2.470 |
Maj | +2.326 |
uve | +2.260 |
inker | +2.258 |
Neg logit contributions | |
20439 | -2.557 |
Sexual | -2.042 |
Clo | -1.861 |
ileaks | -1.852 |
IRC | -1.828 |
Token | to |
Token ID | 284 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
Franch | +4.011 |
tti | +3.824 |
Maj | +3.526 |
inker | +3.497 |
uve | +3.445 |
Neg logit contributions | |
20439 | -5.287 |
Sexual | -4.400 |
Clo | -4.112 |
ileaks | -4.041 |
IRC | -4.040 |
Token | recognize |
Token ID | 7564 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Franch | +2.516 |
tti | +2.378 |
Maj | +2.195 |
inker | +2.159 |
rieg | +2.131 |
Neg logit contributions | |
20439 | -3.404 |
Sexual | -2.809 |
Clo | -2.603 |
ileaks | -2.581 |
IRC | -2.553 |
Token | that |
Token ID | 326 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Franch | +1.274 |
tti | +1.213 |
Maj | +1.133 |
inker | +1.122 |
uve | +1.112 |
Neg logit contributions | |
20439 | -1.311 |
Sexual | -1.060 |
Clo | -0.986 |
isolation | -0.970 |
sheltered | -0.967 |
Token | their |
Token ID | 511 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Franch | +1.031 |
tti | +0.984 |
Maj | +0.919 |
inker | +0.912 |
uve | +0.904 |
Neg logit contributions | |
20439 | -1.023 |
Sexual | -0.825 |
Clo | -0.767 |
isolation | -0.755 |
sheltered | -0.752 |
Token | ambitions |
Token ID | 22455 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Franch | +0.798 |
tti | +0.759 |
Maj | +0.711 |
inker | +0.701 |
rieg | +0.696 |
Neg logit contributions | |
20439 | -0.831 |
Sexual | -0.672 |
Clo | -0.625 |
ileaks | -0.612 |
isolation | -0.611 |
Token | cent |
Token ID | 1247 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
20439 | +0.033 |
Sexual | +0.025 |
Clo | +0.022 |
isolation | +0.022 |
sheltered | +0.022 |
Neg logit contributions | |
Franch | -0.051 |
tti | -0.049 |
Maj | -0.046 |
inker | -0.046 |
uve | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
20439 | +1.409 |
Sexual | +1.161 |
Clo | +1.092 |
isolation | +1.085 |
sheltered | +1.081 |
Neg logit contributions | |
Franch | -1.175 |
tti | -1.115 |
inker | -1.028 |
Maj | -1.023 |
uve | -1.015 |
Token | those |
Token ID | 883 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
Franch | +2.125 |
tti | +2.012 |
Maj | +1.902 |
uve | +1.849 |
inker | +1.847 |
Neg logit contributions | |
20439 | -2.199 |
Sexual | -1.769 |
Clo | -1.637 |
ileaks | -1.618 |
isolation | -1.608 |
Token | who |
Token ID | 508 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
Franch | +0.408 |
tti | +0.389 |
Maj | +0.362 |
inker | +0.359 |
uve | +0.356 |
Neg logit contributions | |
20439 | -0.443 |
Sexual | -0.360 |
Clo | -0.337 |
isolation | -0.332 |
sheltered | -0.330 |
Token | took |
Token ID | 1718 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
20439 | +0.031 |
Sexual | +0.025 |
Clo | +0.023 |
isolation | +0.023 |
sheltered | +0.023 |
Neg logit contributions | |
Franch | -0.030 |
tti | -0.028 |
Maj | -0.027 |
inker | -0.026 |
uve | -0.026 |
Token | part |
Token ID | 636 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
Franch | +0.599 |
tti | +0.568 |
Maj | +0.526 |
inker | +0.520 |
uve | +0.515 |
Neg logit contributions | |
20439 | -0.766 |
Sexual | -0.632 |
Clo | -0.593 |
isolation | -0.585 |
sheltered | -0.582 |
Token | answered |
Token ID | 9373 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Franch | +4.258 |
tti | +4.087 |
Maj | +3.844 |
inker | +3.700 |
uve | +3.698 |
Neg logit contributions | |
20439 | -5.081 |
Sexual | -4.072 |
Clo | -3.801 |
ileaks | -3.799 |
isolation | -3.762 |
Token | Yes |
Token ID | 3363 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
20439 | +0.962 |
Sexual | +0.792 |
Clo | +0.743 |
isolation | +0.733 |
sheltered | +0.729 |
Neg logit contributions | |
Franch | -0.834 |
tti | -0.791 |
Maj | -0.731 |
inker | -0.728 |
uve | -0.723 |
Token | - |
Token ID | 12 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
20439 | +1.377 |
Sexual | +1.125 |
Clo | +1.055 |
isolation | +1.035 |
sheltered | +1.033 |
Neg logit contributions | |
Franch | -1.243 |
tti | -1.174 |
Maj | -1.087 |
inker | -1.085 |
rieg | -1.077 |
Token | Yes |
Token ID | 5297 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
20439 | +0.341 |
Sexual | +0.277 |
Clo | +0.259 |
isolation | +0.255 |
sheltered | +0.254 |
Neg logit contributions | |
Franch | -0.319 |
tti | -0.304 |
Maj | -0.283 |
inker | -0.280 |
uve | -0.278 |
Token | to |
Token ID | 284 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
20439 | +0.595 |
Sexual | +0.488 |
Clo | +0.457 |
isolation | +0.451 |
sheltered | +0.448 |
Neg logit contributions | |
Franch | -0.515 |
tti | -0.488 |
Maj | -0.452 |
inker | -0.450 |
uve | -0.446 |
Token | , |
Token ID | 11 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
Franch | +1.169 |
tti | +1.113 |
Maj | +1.043 |
inker | +1.026 |
rieg | +1.018 |
Neg logit contributions | |
20439 | -1.269 |
Sexual | -1.029 |
Clo | -0.956 |
ileaks | -0.944 |
isolation | -0.940 |
Token | covering |
Token ID | 9505 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
20439 | +0.501 |
Sexual | +0.394 |
Clo | +0.363 |
isolation | +0.355 |
sheltered | +0.354 |
Neg logit contributions | |
Franch | -0.597 |
tti | -0.572 |
Maj | -0.537 |
inker | -0.533 |
uve | -0.530 |
Token | nose |
Token ID | 9686 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
20439 | +0.623 |
Sexual | +0.494 |
Clo | +0.457 |
isolation | +0.451 |
sheltered | +0.449 |
Neg logit contributions | |
Franch | -0.730 |
tti | -0.698 |
Maj | -0.655 |
inker | -0.651 |
rieg | -0.646 |
Token | when |
Token ID | 618 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Franch | +0.516 |
tti | +0.492 |
Maj | +0.456 |
inker | +0.451 |
uve | +0.445 |
Neg logit contributions | |
20439 | -0.619 |
Sexual | -0.508 |
Clo | -0.475 |
isolation | -0.467 |
sheltered | -0.466 |
Token | sne |
Token ID | 10505 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
20439 | +1.048 |
Sexual | +0.818 |
Clo | +0.752 |
isolation | +0.743 |
sheltered | +0.738 |
Neg logit contributions | |
Franch | -1.357 |
tti | -1.301 |
Maj | -1.223 |
inker | -1.217 |
rieg | -1.207 |
Token | ez |
Token ID | 8471 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
20439 | +0.519 |
Sexual | +0.431 |
Clo | +0.405 |
isolation | +0.400 |
sheltered | +0.399 |
Neg logit contributions | |
Franch | -0.398 |
tti | -0.375 |
Maj | -0.347 |
inker | -0.343 |
uve | -0.340 |
Token | ing |
Token ID | 278 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
Franch | +3.352 |
tti | +3.145 |
inker | +2.882 |
rieg | +2.847 |
Maj | +2.842 |
Neg logit contributions | |
20439 | -5.779 |
Sexual | -4.898 |
Clo | -4.661 |
IRC | -4.587 |
sheltered | -4.516 |
Token | advised |
Token ID | 13030 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Franch | +3.052 |
tti | +2.871 |
Maj | +2.725 |
inker | +2.627 |
uve | +2.611 |
Neg logit contributions | |
20439 | -3.778 |
Sexual | -3.021 |
ileaks | -2.863 |
Clo | -2.822 |
aeus | -2.808 |
Token |
|
Token ID | 198 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
Franch | +0.176 |
tti | +0.168 |
Maj | +0.157 |
inker | +0.155 |
uve | +0.153 |
Neg logit contributions | |
20439 | -0.185 |
Sexual | -0.149 |
Clo | -0.139 |
ileaks | -0.137 |
sheltered | -0.136 |
Token |
|
Token ID | 198 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
20439 | +0.601 |
Sexual | +0.475 |
Clo | +0.454 |
isolation | +0.449 |
sheltered | +0.448 |
Neg logit contributions | |
Franch | -0.568 |
tti | -0.545 |
Maj | -0.511 |
inker | -0.502 |
uve | -0.499 |
Token | Parents |
Token ID | 42969 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
20439 | +0.438 |
Sexual | +0.351 |
Clo | +0.326 |
isolation | +0.321 |
sheltered | +0.319 |
Neg logit contributions | |
Franch | -0.461 |
tti | -0.440 |
Maj | -0.412 |
inker | -0.409 |
uve | -0.406 |
Token | < |
Token ID | 1279 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Franch | +1.855 |
tti | +1.784 |
Maj | +1.703 |
inker | +1.692 |
uve | +1.674 |
Neg logit contributions | |
20439 | -1.006 |
Sexual | -0.733 |
Clo | -0.643 |
ileaks | -0.628 |
sheltered | -0.625 |
Token | li |
Token ID | 4528 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
Franch | +1.603 |
tti | +1.541 |
Maj | +1.430 |
inker | +1.423 |
uve | +1.409 |
Neg logit contributions | |
20439 | -1.644 |
Sexual | -1.331 |
Clo | -1.241 |
isolation | -1.219 |
sheltered | -1.214 |
Token | ng |
Token ID | 23370 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
20439 | +0.360 |
Sexual | +0.271 |
Clo | +0.248 |
isolation | +0.244 |
sheltered | +0.241 |
Neg logit contributions | |
Franch | -0.555 |
tti | -0.533 |
Maj | -0.503 |
inker | -0.500 |
uve | -0.497 |
Token | - |
Token ID | 12 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Franch | +1.475 |
tti | +1.435 |
Maj | +1.308 |
inker | +1.290 |
rieg | +1.282 |
Neg logit contributions | |
20439 | -2.235 |
Sexual | -1.865 |
Clo | -1.761 |
isolation | -1.754 |
sheltered | -1.752 |
Token | repeat |
Token ID | 44754 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Franch | +0.241 |
tti | +0.232 |
Maj | +0.220 |
inker | +0.218 |
uve | +0.217 |
Neg logit contributions | |
20439 | -0.144 |
Sexual | -0.107 |
Clo | -0.096 |
isolation | -0.094 |
sheltered | -0.093 |
Token | =" |
Token ID | 2625 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
Franch | +0.703 |
tti | +0.658 |
Maj | +0.588 |
inker | +0.581 |
rieg | +0.570 |
Neg logit contributions | |
20439 | -1.518 |
Sexual | -1.300 |
Clo | -1.235 |
isolation | -1.228 |
sheltered | -1.225 |
Token | phone |
Token ID | 4862 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Franch | +4.067 |
tti | +3.979 |
inker | +3.627 |
Maj | +3.623 |
rieg | +3.567 |
Neg logit contributions | |
20439 | -4.946 |
Sexual | -4.098 |
Clo | -3.874 |
sheltered | -3.813 |
ileaks | -3.796 |
Token | in |
Token ID | 287 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Franch | +0.830 |
tti | +0.790 |
Maj | +0.735 |
inker | +0.730 |
uve | +0.725 |
Neg logit contributions | |
20439 | -0.875 |
Sexual | -0.710 |
Clo | -0.663 |
isolation | -0.656 |
sheltered | -0.650 |
Token | phones |
Token ID | 9512 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
Franch | +1.049 |
tti | +1.005 |
Maj | +0.944 |
inker | +0.935 |
rieg | +0.927 |
Neg logit contributions | |
20439 | -0.899 |
Sexual | -0.712 |
Clo | -0.656 |
isolation | -0.643 |
sheltered | -0.641 |
Token | "> |
Token ID | 5320 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Franch | +0.705 |
tti | +0.671 |
Maj | +0.624 |
inker | +0.621 |
uve | +0.617 |
Neg logit contributions | |
20439 | -0.729 |
Sexual | -0.588 |
Clo | -0.550 |
isolation | -0.543 |
sheltered | -0.539 |
Token | < |
Token ID | 1279 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
Franch | +2.038 |
tti | +1.961 |
Maj | +1.865 |
inker | +1.853 |
rieg | +1.834 |
Neg logit contributions | |
20439 | -1.208 |
Sexual | -0.899 |
Clo | -0.803 |
isolation | -0.783 |
sheltered | -0.782 |
Token | I |
Token ID | 40 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Franch | +0.842 |
tti | +0.804 |
Maj | +0.748 |
inker | +0.734 |
uve | +0.728 |
Neg logit contributions | |
20439 | -0.984 |
Sexual | -0.807 |
Clo | -0.750 |
isolation | -0.740 |
ileaks | -0.734 |
Token | did |
Token ID | 750 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
20439 | +0.941 |
Sexual | +0.764 |
Clo | +0.712 |
isolation | +0.702 |
sheltered | +0.699 |
Neg logit contributions | |
Franch | -0.902 |
tti | -0.858 |
Maj | -0.800 |
inker | -0.793 |
uve | -0.787 |
Token | receive |
Token ID | 3328 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
20439 | +0.984 |
Sexual | +0.806 |
Clo | +0.760 |
isolation | +0.751 |
sheltered | +0.744 |
Neg logit contributions | |
Franch | -0.918 |
tti | -0.875 |
Maj | -0.809 |
inker | -0.805 |
rieg | -0.804 |
Token | a |
Token ID | 257 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
Franch | +0.192 |
tti | +0.182 |
Maj | +0.170 |
inker | +0.168 |
uve | +0.167 |
Neg logit contributions | |
20439 | -0.206 |
Sexual | -0.168 |
Clo | -0.157 |
isolation | -0.154 |
sheltered | -0.154 |
Token | last |
Token ID | 938 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
Franch | +0.030 |
tti | +0.028 |
Maj | +0.027 |
inker | +0.026 |
uve | +0.026 |
Neg logit contributions | |
20439 | -0.029 |
Sexual | -0.023 |
Clo | -0.021 |
isolation | -0.021 |
sheltered | -0.021 |
Token | name |
Token ID | 1438 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
Franch | +0.585 |
tti | +0.558 |
Maj | +0.522 |
inker | +0.518 |
uve | +0.513 |
Neg logit contributions | |
20439 | -0.572 |
Sexual | -0.460 |
Clo | -0.428 |
isolation | -0.421 |
sheltered | -0.419 |
Token | Sur |
Token ID | 4198 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Franch | +4.439 |
tti | +4.217 |
Maj | +3.995 |
inker | +3.889 |
rieg | +3.759 |
Neg logit contributions | |
20439 | -4.716 |
Sexual | -3.873 |
ileaks | -3.524 |
IRC | -3.521 |
Clo | -3.484 |
Token | ley |
Token ID | 1636 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
20439 | +0.903 |
Sexual | +0.746 |
Clo | +0.697 |
ileaks | +0.690 |
isolation | +0.688 |
Neg logit contributions | |
Franch | -0.757 |
tti | -0.713 |
Maj | -0.663 |
inker | -0.654 |
rieg | -0.651 |
Token | , |
Token ID | 11 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
20439 | +0.945 |
Sexual | +0.771 |
Clo | +0.727 |
isolation | +0.710 |
sheltered | +0.707 |
Neg logit contributions | |
Franch | -0.856 |
tti | -0.812 |
inker | -0.756 |
Maj | -0.752 |
rieg | -0.749 |
Token | a |
Token ID | 257 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Franch | +0.766 |
tti | +0.730 |
Maj | +0.681 |
inker | +0.676 |
uve | +0.670 |
Neg logit contributions | |
20439 | -0.782 |
Sexual | -0.633 |
Clo | -0.590 |
isolation | -0.581 |
sheltered | -0.578 |
Token | date |
Token ID | 3128 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
Franch | +1.391 |
tti | +1.326 |
Maj | +1.243 |
inker | +1.230 |
uve | +1.218 |
Neg logit contributions | |
20439 | -1.353 |
Sexual | -1.086 |
Clo | -1.007 |
isolation | -0.992 |
sheltered | -0.985 |
Token | have |
Token ID | 423 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
Franch | +0.563 |
tti | +0.535 |
Maj | +0.501 |
inker | +0.495 |
uve | +0.490 |
Neg logit contributions | |
20439 | -0.581 |
Sexual | -0.469 |
Clo | -0.434 |
isolation | -0.428 |
sheltered | -0.427 |
Token | the |
Token ID | 262 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
Franch | +0.250 |
tti | +0.238 |
Maj | +0.222 |
inker | +0.220 |
uve | +0.218 |
Neg logit contributions | |
20439 | -0.254 |
Sexual | -0.205 |
Clo | -0.191 |
isolation | -0.188 |
sheltered | -0.187 |
Token | Nexus |
Token ID | 16756 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
Franch | +0.591 |
tti | +0.563 |
Maj | +0.524 |
inker | +0.520 |
uve | +0.516 |
Neg logit contributions | |
20439 | -0.628 |
Sexual | -0.510 |
Clo | -0.476 |
isolation | -0.469 |
sheltered | -0.466 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Franch | +0.673 |
tti | +0.638 |
Maj | +0.594 |
inker | +0.587 |
uve | +0.581 |
Neg logit contributions | |
20439 | -0.803 |
Sexual | -0.659 |
Clo | -0.616 |
isolation | -0.608 |
sheltered | -0.605 |
Token | in |
Token ID | 287 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
Franch | +1.534 |
tti | +1.470 |
Maj | +1.385 |
inker | +1.365 |
uve | +1.351 |
Neg logit contributions | |
20439 | -1.441 |
Sexual | -1.152 |
Clo | -1.060 |
ileaks | -1.046 |
isolation | -1.042 |
Token | Stock |
Token ID | 10500 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
Franch | +0.692 |
tti | +0.657 |
Maj | +0.616 |
inker | +0.608 |
uve | +0.603 |
Neg logit contributions | |
20439 | -0.718 |
Sexual | -0.579 |
Clo | -0.535 |
ileaks | -0.527 |
isolation | -0.526 |
Token | on |
Token ID | 319 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
Franch | +4.345 |
tti | +4.042 |
Maj | +3.908 |
inker | +3.740 |
uve | +3.720 |
Neg logit contributions | |
20439 | -4.789 |
Sexual | -3.853 |
ileaks | -3.543 |
aeus | -3.485 |
sheltered | -3.483 |
Token | Nov |
Token ID | 5267 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
Franch | +0.268 |
tti | +0.254 |
Maj | +0.238 |
inker | +0.234 |
uve | +0.232 |
Neg logit contributions | |
20439 | -0.288 |
Sexual | -0.234 |
Clo | -0.217 |
isolation | -0.214 |
sheltered | -0.213 |
Token | . |
Token ID | 13 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
Franch | +0.576 |
tti | +0.548 |
Maj | +0.510 |
inker | +0.503 |
rieg | +0.497 |
Neg logit contributions | |
20439 | -0.705 |
Sexual | -0.581 |
Clo | -0.540 |
isolation | -0.538 |
sheltered | -0.534 |
Token | 21 |
Token ID | 2310 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Franch | +2.845 |
tti | +2.702 |
Maj | +2.575 |
inker | +2.438 |
Valhalla | +2.402 |
Neg logit contributions | |
20439 | -3.392 |
Sexual | -2.760 |
isolation | -2.611 |
ileaks | -2.598 |
sheltered | -2.574 |
Token | st |
Token ID | 301 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Franch | +0.935 |
tti | +0.894 |
Maj | +0.834 |
inker | +0.824 |
uve | +0.817 |
Neg logit contributions | |
20439 | -0.995 |
Sexual | -0.810 |
Clo | -0.752 |
isolation | -0.741 |
sheltered | -0.740 |
Token | Silver |
Token ID | 7698 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Franch | +1.794 |
tti | +1.713 |
Maj | +1.597 |
inker | +1.576 |
rieg | +1.563 |
Neg logit contributions | |
20439 | -1.754 |
Sexual | -1.412 |
Clo | -1.302 |
sheltered | -1.284 |
ileaks | -1.281 |
Token | Phant |
Token ID | 38699 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
Franch | +0.515 |
tti | +0.474 |
Maj | +0.418 |
inker | +0.412 |
uve | +0.406 |
Neg logit contributions | |
20439 | -1.254 |
Sexual | -1.082 |
Clo | -1.034 |
isolation | -1.023 |
sheltered | -1.020 |
Token | oms |
Token ID | 3150 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Franch | +0.445 |
tti | +0.413 |
Maj | +0.364 |
inker | +0.359 |
rieg | +0.350 |
Neg logit contributions | |
20439 | -1.099 |
Sexual | -0.948 |
Clo | -0.905 |
isolation | -0.897 |
sheltered | -0.894 |
Token | , |
Token ID | 11 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
20439 | +0.953 |
Sexual | +0.767 |
Clo | +0.717 |
isolation | +0.707 |
sheltered | +0.703 |
Neg logit contributions | |
Franch | -0.981 |
tti | -0.934 |
Maj | -0.874 |
inker | -0.870 |
uve | -0.862 |
Token | with |
Token ID | 351 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Franch | +0.682 |
tti | +0.650 |
Maj | +0.607 |
inker | +0.601 |
uve | +0.596 |
Neg logit contributions | |
20439 | -0.685 |
Sexual | -0.553 |
Clo | -0.514 |
isolation | -0.506 |
sheltered | -0.503 |
Token | Dial |
Token ID | 21269 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
Franch | +1.034 |
tti | +0.985 |
Maj | +0.919 |
inker | +0.908 |
uve | +0.898 |
Neg logit contributions | |
20439 | -1.097 |
Sexual | -0.890 |
Clo | -0.823 |
ileaks | -0.809 |
isolation | -0.808 |
Token | og |
Token ID | 519 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Franch | +4.423 |
tti | +4.253 |
inker | +3.960 |
Maj | +3.958 |
uve | +3.872 |
Neg logit contributions | |
20439 | -4.616 |
Sexual | -3.703 |
Clo | -3.401 |
sheltered | -3.388 |
ileaks | -3.369 |
Token | , |
Token ID | 11 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Franch | +0.779 |
tti | +0.743 |
Maj | +0.691 |
inker | +0.685 |
uve | +0.678 |
Neg logit contributions | |
20439 | -0.844 |
Sexual | -0.687 |
Clo | -0.640 |
isolation | -0.630 |
sheltered | -0.629 |
Token | matching |
Token ID | 12336 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
Franch | +0.358 |
tti | +0.341 |
Maj | +0.319 |
inker | +0.316 |
uve | +0.313 |
Neg logit contributions | |
20439 | -0.353 |
Sexual | -0.284 |
Clo | -0.264 |
isolation | -0.260 |
sheltered | -0.259 |
Token | Branch |
Token ID | 20551 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Franch | +2.007 |
tti | +1.924 |
Maj | +1.800 |
inker | +1.773 |
uve | +1.753 |
Neg logit contributions | |
20439 | -1.964 |
Sexual | -1.570 |
Clo | -1.438 |
ileaks | -1.427 |
sheltered | -1.417 |
Token | stands |
Token ID | 6296 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Franch | +0.091 |
tti | +0.086 |
Maj | +0.080 |
inker | +0.080 |
uve | +0.079 |
Neg logit contributions | |
20439 | -0.100 |
Sexual | -0.081 |
Clo | -0.076 |
isolation | -0.075 |
sheltered | -0.075 |
Token | like |
Token ID | 588 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
20439 | +1.266 |
Sexual | +1.036 |
Clo | +0.976 |
isolation | +0.968 |
sheltered | +0.957 |
Neg logit contributions | |
Franch | -1.129 |
tti | -1.067 |
Maj | -0.992 |
inker | -0.987 |
uve | -0.980 |
Token | this |
Token ID | 428 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
Franch | +0.306 |
tti | +0.291 |
Maj | +0.271 |
inker | +0.269 |
uve | +0.267 |
Neg logit contributions | |
20439 | -0.326 |
Sexual | -0.265 |
Clo | -0.247 |
isolation | -0.243 |
sheltered | -0.242 |
Token | : |
Token ID | 25 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
20439 | +0.831 |
Sexual | +0.682 |
Clo | +0.641 |
isolation | +0.633 |
sheltered | +0.629 |
Neg logit contributions | |
Franch | -0.702 |
tti | -0.666 |
Maj | -0.617 |
inker | -0.613 |
uve | -0.609 |
Token |
|
Token ID | 198 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
20439 | +0.740 |
Sexual | +0.594 |
Clo | +0.552 |
isolation | +0.545 |
sheltered | +0.542 |
Neg logit contributions | |
Franch | -0.782 |
tti | -0.748 |
Maj | -0.699 |
inker | -0.695 |
uve | -0.690 |
Token |
|
Token ID | 198 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
20439 | +0.654 |
Sexual | +0.524 |
Clo | +0.488 |
isolation | +0.484 |
sheltered | +0.481 |
Neg logit contributions | |
Franch | -0.643 |
tti | -0.615 |
Maj | -0.576 |
inker | -0.568 |
uve | -0.563 |
Token | void |
Token ID | 19382 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
20439 | +0.795 |
Sexual | +0.645 |
Clo | +0.596 |
isolation | +0.589 |
sheltered | +0.588 |
Neg logit contributions | |
Franch | -0.800 |
tti | -0.760 |
Maj | -0.713 |
inker | -0.704 |
uve | -0.699 |
Token | vert |
Token ID | 9421 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Franch | +4.478 |
tti | +4.238 |
Maj | +4.051 |
inker | +3.884 |
rieg | +3.864 |
Neg logit contributions | |
20439 | -4.455 |
Sexual | -3.621 |
Clo | -3.230 |
aeus | -3.214 |
IRC | -3.212 |
Token | ( |
Token ID | 357 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
20439 | +0.097 |
Sexual | +0.080 |
Clo | +0.075 |
isolation | +0.074 |
sheltered | +0.073 |
Neg logit contributions | |
Franch | -0.081 |
tti | -0.077 |
Maj | -0.071 |
inker | -0.070 |
uve | -0.070 |
Token | in |
Token ID | 259 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
Franch | +1.064 |
tti | +1.019 |
Maj | +0.960 |
inker | +0.947 |
rieg | +0.937 |
Neg logit contributions | |
20439 | -0.960 |
Sexual | -0.763 |
Clo | -0.704 |
ileaks | -0.688 |
isolation | -0.687 |
Token | out |
Token ID | 448 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Franch | +1.622 |
tti | +1.541 |
Maj | +1.435 |
inker | +1.417 |
rieg | +1.408 |
Neg logit contributions | |
20439 | -1.870 |
Sexual | -1.534 |
Clo | -1.421 |
ileaks | -1.394 |
sheltered | -1.393 |
Token | app |
Token ID | 598 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Franch | +0.859 |
tti | +0.820 |
Maj | +0.767 |
inker | +0.760 |
rieg | +0.751 |
Neg logit contributions | |
20439 | -0.890 |
Sexual | -0.724 |
Clo | -0.671 |
isolation | -0.655 |
ileaks | -0.654 |
Token | Jack |
Token ID | 3619 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Franch | +0.361 |
tti | +0.345 |
Maj | +0.321 |
inker | +0.320 |
uve | +0.317 |
Neg logit contributions | |
20439 | -0.357 |
Sexual | -0.288 |
Clo | -0.270 |
isolation | -0.266 |
sheltered | -0.265 |
Token | is |
Token ID | 318 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
20439 | +0.161 |
Sexual | +0.129 |
Clo | +0.120 |
isolation | +0.118 |
sheltered | +0.117 |
Neg logit contributions | |
Franch | -0.177 |
tti | -0.169 |
Maj | -0.158 |
inker | -0.157 |
uve | -0.156 |
Token | clumsy |
Token ID | 39120 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
Franch | +0.447 |
tti | +0.427 |
Maj | +0.399 |
inker | +0.396 |
uve | +0.393 |
Neg logit contributions | |
20439 | -0.416 |
Sexual | -0.332 |
Clo | -0.308 |
isolation | -0.303 |
sheltered | -0.301 |
Token | and |
Token ID | 290 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
Franch | +2.226 |
tti | +2.113 |
Maj | +1.976 |
inker | +1.942 |
uve | +1.920 |
Neg logit contributions | |
20439 | -2.704 |
Sexual | -2.207 |
Clo | -2.055 |
ileaks | -2.027 |
isolation | -2.023 |
Token | gu |
Token ID | 915 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
20439 | +0.032 |
Sexual | +0.025 |
Clo | +0.024 |
isolation | +0.023 |
sheltered | +0.023 |
Neg logit contributions | |
Franch | -0.038 |
tti | -0.036 |
Maj | -0.034 |
inker | -0.034 |
uve | -0.033 |
Token | ile |
Token ID | 576 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
20439 | +0.991 |
Sexual | +0.786 |
Clo | +0.731 |
sheltered | +0.714 |
isolation | +0.711 |
Neg logit contributions | |
Franch | -1.157 |
tti | -1.097 |
Maj | -1.034 |
inker | -1.020 |
rieg | -1.013 |
Token | less |
Token ID | 1203 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
tti | +4.191 |
Franch | +4.132 |
Maj | +3.839 |
uve | +3.752 |
inker | +3.731 |
Neg logit contributions | |
20439 | -4.656 |
Sexual | -3.683 |
Clo | -3.451 |
ileaks | -3.449 |
IRC | -3.422 |
Token | , |
Token ID | 11 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Franch | +0.788 |
tti | +0.748 |
Maj | +0.693 |
inker | +0.687 |
uve | +0.681 |
Neg logit contributions | |
20439 | -0.946 |
Sexual | -0.779 |
Clo | -0.730 |
isolation | -0.720 |
sheltered | -0.717 |
Token | incapable |
Token ID | 23402 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Franch | +0.332 |
tti | +0.317 |
Maj | +0.297 |
inker | +0.294 |
uve | +0.291 |
Neg logit contributions | |
20439 | -0.322 |
Sexual | -0.258 |
Clo | -0.240 |
isolation | -0.236 |
sheltered | -0.235 |
Token | of |
Token ID | 286 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Franch | +1.027 |
tti | +0.965 |
Maj | +0.883 |
inker | +0.875 |
uve | +0.863 |
Neg logit contributions | |
20439 | -1.615 |
Sexual | -1.356 |
Clo | -1.282 |
isolation | -1.264 |
sheltered | -1.260 |
Token | managing |
Token ID | 11149 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
20439 | +1.382 |
Sexual | +1.106 |
Clo | +1.036 |
isolation | +1.031 |
sheltered | +1.019 |
Neg logit contributions | |
Franch | -1.603 |
tti | -1.545 |
inker | -1.435 |
Maj | -1.433 |
rieg | -1.424 |
Token | " |
Token ID | 1 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Franch | +0.722 |
tti | +0.682 |
inker | +0.621 |
Maj | +0.618 |
uve | +0.613 |
Neg logit contributions | |
20439 | -1.137 |
Sexual | -0.958 |
Clo | -0.914 |
isolation | -0.900 |
sheltered | -0.891 |
Token | over |
Token ID | 625 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
Franch | +1.151 |
tti | +1.097 |
Maj | +1.024 |
inker | +1.013 |
uve | +1.006 |
Neg logit contributions | |
20439 | -1.193 |
Sexual | -0.967 |
Clo | -0.898 |
isolation | -0.885 |
sheltered | -0.882 |
Token | printed |
Token ID | 49695 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
Franch | +0.697 |
tti | +0.663 |
Maj | +0.618 |
inker | +0.615 |
uve | +0.609 |
Neg logit contributions | |
20439 | -0.710 |
Sexual | -0.574 |
Clo | -0.536 |
isolation | -0.527 |
sheltered | -0.525 |
Token | on |
Token ID | 319 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
20439 | +0.669 |
Sexual | +0.542 |
Clo | +0.513 |
isolation | +0.508 |
sheltered | +0.502 |
Neg logit contributions | |
Franch | -0.659 |
tti | -0.626 |
inker | -0.588 |
Maj | -0.581 |
uve | -0.580 |
Token | ob |
Token ID | 909 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Franch | +1.172 |
tti | +1.117 |
Maj | +1.046 |
inker | +1.031 |
uve | +1.024 |
Neg logit contributions | |
20439 | -1.198 |
Sexual | -0.970 |
Clo | -0.898 |
isolation | -0.883 |
sheltered | -0.880 |
Token | verse |
Token ID | 4399 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
Franch | +0.623 |
tti | +0.570 |
Maj | +0.489 |
inker | +0.479 |
uve | +0.474 |
Neg logit contributions | |
20439 | -1.801 |
Sexual | -1.565 |
Clo | -1.495 |
isolation | -1.486 |
sheltered | -1.477 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Franch | +3.823 |
tti | +3.662 |
Maj | +3.388 |
inker | +3.276 |
uve | +3.268 |
Neg logit contributions | |
20439 | -5.083 |
Sexual | -4.212 |
Clo | -3.891 |
ileaks | -3.867 |
IRC | -3.836 |
Token | In |
Token ID | 554 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
Franch | +1.207 |
tti | +1.152 |
Maj | +1.075 |
inker | +1.068 |
uve | +1.060 |
Neg logit contributions | |
20439 | -1.192 |
Sexual | -0.960 |
Clo | -0.894 |
isolation | -0.879 |
sheltered | -0.874 |
Token | addition |
Token ID | 3090 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
Franch | +0.321 |
tti | +0.305 |
inker | +0.282 |
Maj | +0.282 |
uve | +0.278 |
Neg logit contributions | |
20439 | -0.371 |
Sexual | -0.304 |
Clo | -0.287 |
isolation | -0.284 |
sheltered | -0.281 |
Token | , |
Token ID | 11 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
20439 | +0.459 |
Sexual | +0.373 |
Clo | +0.355 |
isolation | +0.348 |
sheltered | +0.345 |
Neg logit contributions | |
Franch | -0.391 |
tti | -0.371 |
Maj | -0.344 |
inker | -0.343 |
uve | -0.342 |
Token | the |
Token ID | 262 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Franch | +0.606 |
tti | +0.578 |
Maj | +0.538 |
inker | +0.537 |
uve | +0.533 |
Neg logit contributions | |
20439 | -0.613 |
Sexual | -0.494 |
Clo | -0.464 |
isolation | -0.457 |
sheltered | -0.453 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Franch | +0.021 |
tti | +0.020 |
Maj | +0.018 |
inker | +0.018 |
uve | +0.018 |
Neg logit contributions | |
20439 | -0.022 |
Sexual | -0.017 |
Clo | -0.016 |
isolation | -0.016 |
sheltered | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
20439 | +0.928 |
Sexual | +0.767 |
Clo | +0.721 |
isolation | +0.711 |
sheltered | +0.708 |
Neg logit contributions | |
Franch | -0.736 |
tti | -0.697 |
Maj | -0.645 |
inker | -0.639 |
uve | -0.633 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
20439 | +0.560 |
Sexual | +0.462 |
Clo | +0.436 |
isolation | +0.430 |
sheltered | +0.429 |
Neg logit contributions | |
Franch | -0.451 |
tti | -0.428 |
Maj | -0.394 |
inker | -0.391 |
uve | -0.388 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Franch | +0.190 |
tti | +0.182 |
Maj | +0.171 |
inker | +0.166 |
rieg | +0.165 |
Neg logit contributions | |
20439 | -0.205 |
Sexual | -0.165 |
isolation | -0.154 |
ileaks | -0.153 |
Clo | -0.153 |
Token |
|
Token ID | 198 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
Franch | +1.035 |
tti | +0.991 |
Maj | +0.933 |
inker | +0.902 |
rieg | +0.893 |
Neg logit contributions | |
20439 | -1.202 |
Sexual | -0.958 |
ileaks | -0.905 |
isolation | -0.901 |
Clo | -0.898 |
Token | Subject |
Token ID | 19776 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
Franch | +0.436 |
tti | +0.413 |
Maj | +0.370 |
inker | +0.367 |
uve | +0.356 |
Neg logit contributions | |
20439 | -0.985 |
Sexual | -0.838 |
Clo | -0.819 |
isolation | -0.804 |
padded | -0.803 |
Token | : |
Token ID | 25 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Franch | +3.049 |
tti | +2.973 |
Maj | +2.772 |
inker | +2.601 |
uve | +2.589 |
Neg logit contributions | |
20439 | -5.693 |
Sexual | -4.660 |
isolation | -4.615 |
sheltered | -4.542 |
ileaks | -4.538 |
Token | Que |
Token ID | 4670 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
Franch | +0.859 |
tti | +0.820 |
Maj | +0.769 |
inker | +0.760 |
uve | +0.751 |
Neg logit contributions | |
20439 | -0.834 |
Sexual | -0.666 |
Clo | -0.619 |
isolation | -0.610 |
sheltered | -0.607 |
Token | er |
Token ID | 263 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
20439 | +0.488 |
Sexual | +0.396 |
Clo | +0.370 |
isolation | +0.364 |
sheltered | +0.362 |
Neg logit contributions | |
Franch | -0.468 |
tti | -0.445 |
Maj | -0.415 |
inker | -0.412 |
uve | -0.408 |
Token | magnet |
Token ID | 19972 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
20439 | +0.737 |
Sexual | +0.599 |
Clo | +0.556 |
isolation | +0.549 |
sheltered | +0.545 |
Neg logit contributions | |
Franch | -0.746 |
tti | -0.711 |
Maj | -0.663 |
inker | -0.660 |
rieg | -0.656 |
Token | ? |
Token ID | 30 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
20439 | +0.651 |
Sexual | +0.525 |
Clo | +0.487 |
isolation | +0.480 |
sheltered | +0.477 |
Neg logit contributions | |
Franch | -0.687 |
tti | -0.656 |
Maj | -0.613 |
inker | -0.609 |
uve | -0.606 |
Token | the |
Token ID | 262 |
Feature activation | +6.25e-03 |
Pos logit contributions | |
20439 | +0.277 |
Sexual | +0.224 |
Clo | +0.210 |
isolation | +0.207 |
sheltered | +0.206 |
Neg logit contributions | |
Franch | -0.267 |
tti | -0.255 |
Maj | -0.237 |
inker | -0.236 |
uve | -0.234 |
Token | Google |
Token ID | 3012 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Franch | +0.005 |
tti | +0.005 |
Maj | +0.005 |
inker | +0.005 |
uve | +0.004 |
Neg logit contributions | |
20439 | -0.005 |
Sexual | -0.004 |
Clo | -0.004 |
isolation | -0.004 |
sheltered | -0.004 |
Token | Nexus |
Token ID | 16756 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
Franch | +1.065 |
tti | +1.017 |
Maj | +0.951 |
inker | +0.944 |
uve | +0.934 |
Neg logit contributions | |
20439 | -1.043 |
Sexual | -0.838 |
Clo | -0.777 |
isolation | -0.766 |
sheltered | -0.762 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Franch | +0.397 |
tti | +0.375 |
Maj | +0.346 |
inker | +0.343 |
uve | +0.340 |
Neg logit contributions | |
20439 | -0.527 |
Sexual | -0.438 |
Clo | -0.412 |
isolation | -0.407 |
sheltered | -0.405 |
Token | in |
Token ID | 287 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
Franch | +1.206 |
tti | +1.152 |
Maj | +1.079 |
inker | +1.060 |
uve | +1.053 |
Neg logit contributions | |
20439 | -1.281 |
Sexual | -1.039 |
Clo | -0.962 |
ileaks | -0.952 |
isolation | -0.947 |
Token | stock |
Token ID | 4283 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
Franch | +0.396 |
tti | +0.376 |
Maj | +0.354 |
inker | +0.349 |
uve | +0.346 |
Neg logit contributions | |
20439 | -0.401 |
Sexual | -0.323 |
Clo | -0.298 |
isolation | -0.293 |
sheltered | -0.293 |
Token | on |
Token ID | 319 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
Franch | +4.064 |
tti | +3.799 |
Maj | +3.682 |
uve | +3.540 |
inker | +3.494 |
Neg logit contributions | |
20439 | -4.853 |
Sexual | -3.950 |
ileaks | -3.642 |
Clo | -3.604 |
aeus | -3.572 |
Token | November |
Token ID | 3389 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Franch | +0.439 |
tti | +0.418 |
Maj | +0.392 |
inker | +0.386 |
uve | +0.383 |
Neg logit contributions | |
20439 | -0.450 |
Sexual | -0.364 |
Clo | -0.337 |
isolation | -0.332 |
sheltered | -0.331 |
Token | 21 |
Token ID | 2310 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Franch | +0.742 |
tti | +0.704 |
Maj | +0.652 |
inker | +0.646 |
uve | +0.640 |
Neg logit contributions | |
20439 | -0.906 |
Sexual | -0.747 |
Clo | -0.701 |
isolation | -0.692 |
sheltered | -0.689 |
Token | st |
Token ID | 301 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Franch | +1.154 |
tti | +1.111 |
Maj | +1.036 |
inker | +1.027 |
rieg | +1.021 |
Neg logit contributions | |
20439 | -1.060 |
Sexual | -0.846 |
Clo | -0.781 |
isolation | -0.767 |
sheltered | -0.764 |
Token | . |
Token ID | 13 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
Franch | +1.254 |
tti | +1.198 |
Maj | +1.114 |
inker | +1.095 |
rieg | +1.085 |
Neg logit contributions | |
20439 | -1.547 |
Sexual | -1.281 |
Clo | -1.192 |
isolation | -1.174 |
ileaks | -1.173 |
Token | a |
Token ID | 257 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
20439 | +0.556 |
Sexual | +0.450 |
Clo | +0.421 |
isolation | +0.416 |
sheltered | +0.413 |
Neg logit contributions | |
Franch | -0.543 |
tti | -0.518 |
Maj | -0.483 |
inker | -0.481 |
uve | -0.476 |
Token | grid |
Token ID | 10706 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Franch | +0.028 |
tti | +0.027 |
Maj | +0.025 |
inker | +0.025 |
uve | +0.025 |
Neg logit contributions | |
20439 | -0.031 |
Sexual | -0.025 |
Clo | -0.023 |
isolation | -0.023 |
sheltered | -0.023 |
Token | : |
Token ID | 25 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
Franch | +1.415 |
tti | +1.349 |
Maj | +1.251 |
inker | +1.239 |
rieg | +1.227 |
Neg logit contributions | |
20439 | -1.679 |
Sexual | -1.379 |
Clo | -1.292 |
ileaks | -1.267 |
isolation | -1.265 |
Token |
|
Token ID | 198 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
20439 | +0.062 |
Sexual | +0.050 |
Clo | +0.046 |
isolation | +0.046 |
sheltered | +0.045 |
Neg logit contributions | |
Franch | -0.063 |
tti | -0.060 |
Maj | -0.056 |
inker | -0.055 |
uve | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
20439 | +0.183 |
Sexual | +0.146 |
Clo | +0.136 |
isolation | +0.135 |
ileaks | +0.135 |
Neg logit contributions | |
Franch | -0.175 |
tti | -0.167 |
Maj | -0.156 |
inker | -0.154 |
uve | -0.152 |
Token | void |
Token ID | 19382 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
20439 | +0.590 |
Sexual | +0.483 |
Clo | +0.449 |
isolation | +0.443 |
sheltered | +0.442 |
Neg logit contributions | |
Franch | -0.541 |
tti | -0.513 |
Maj | -0.479 |
inker | -0.473 |
uve | -0.469 |
Token | V |
Token ID | 569 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
Franch | +4.202 |
tti | +3.918 |
Maj | +3.744 |
Valhalla | +3.581 |
inker | +3.549 |
Neg logit contributions | |
20439 | -4.681 |
Sexual | -3.783 |
aeus | -3.498 |
Clo | -3.489 |
ileaks | -3.487 |
Token | ort |
Token ID | 419 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
20439 | +0.546 |
Sexual | +0.425 |
Clo | +0.390 |
isolation | +0.383 |
sheltered | +0.380 |
Neg logit contributions | |
Franch | -0.704 |
tti | -0.676 |
Maj | -0.636 |
inker | -0.632 |
uve | -0.627 |
Token | on |
Token ID | 261 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
20439 | +1.557 |
Sexual | +1.281 |
Clo | +1.178 |
isolation | +1.167 |
sheltered | +1.159 |
Neg logit contributions | |
Franch | -1.451 |
tti | -1.383 |
Maj | -1.298 |
inker | -1.267 |
uve | -1.256 |
Token | Sim |
Token ID | 8890 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
20439 | +0.841 |
Sexual | +0.655 |
Clo | +0.597 |
isolation | +0.586 |
sheltered | +0.582 |
Neg logit contributions | |
Franch | -1.116 |
tti | -1.072 |
Maj | -1.009 |
inker | -1.003 |
uve | -0.996 |
Token | :: |
Token ID | 3712 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
20439 | +1.513 |
Sexual | +1.268 |
Clo | +1.186 |
isolation | +1.168 |
sheltered | +1.159 |
Neg logit contributions | |
Franch | -1.164 |
tti | -1.102 |
Maj | -1.020 |
inker | -1.012 |
rieg | -1.002 |
Token | to |
Token ID | 284 |
Feature activation | +8.48e-02 |
Pos logit contributions | |
Franch | +2.689 |
tti | +2.574 |
Maj | +2.402 |
inker | +2.372 |
uve | +2.355 |
Neg logit contributions | |
20439 | -2.925 |
Sexual | -2.365 |
Clo | -2.192 |
sheltered | -2.158 |
ileaks | -2.148 |
Token | images |
Token ID | 4263 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
Franch | +0.067 |
tti | +0.064 |
inker | +0.059 |
Maj | +0.059 |
rieg | +0.059 |
Neg logit contributions | |
20439 | -0.069 |
Sexual | -0.056 |
Clo | -0.052 |
isolation | -0.052 |
sheltered | -0.052 |
Token | directory |
Token ID | 8619 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
Franch | +0.595 |
tti | +0.564 |
Maj | +0.521 |
inker | +0.517 |
uve | +0.512 |
Neg logit contributions | |
20439 | -0.755 |
Sexual | -0.624 |
Clo | -0.587 |
isolation | -0.579 |
sheltered | -0.576 |
Token | ") |
Token ID | 4943 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
Franch | +0.040 |
tti | +0.038 |
Maj | +0.034 |
inker | +0.034 |
uve | +0.034 |
Neg logit contributions | |
20439 | -0.057 |
Sexual | -0.048 |
Clo | -0.045 |
isolation | -0.045 |
sheltered | -0.044 |
Token | args |
Token ID | 26498 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
20439 | +0.269 |
Sexual | +0.209 |
Clo | +0.190 |
isolation | +0.187 |
sheltered | +0.186 |
Neg logit contributions | |
Franch | -0.355 |
tti | -0.341 |
Maj | -0.321 |
inker | -0.319 |
uve | -0.317 |
Token | = |
Token ID | 796 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
Franch | +1.787 |
tti | +1.708 |
inker | +1.566 |
Maj | +1.561 |
rieg | +1.534 |
Neg logit contributions | |
20439 | -2.451 |
Sexual | -2.043 |
Clo | -1.918 |
isolation | -1.895 |
sheltered | -1.888 |
Token | v |
Token ID | 410 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Franch | +4.099 |
tti | +3.971 |
Maj | +3.763 |
inker | +3.591 |
uve | +3.565 |
Neg logit contributions | |
20439 | -4.727 |
Sexual | -3.818 |
ileaks | -3.434 |
Hague | -3.427 |
IRC | -3.415 |
Token | ars |
Token ID | 945 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
20439 | +1.126 |
Sexual | +0.903 |
Clo | +0.844 |
isolation | +0.830 |
sheltered | +0.826 |
Neg logit contributions | |
Franch | -1.186 |
tti | -1.123 |
Maj | -1.053 |
inker | -1.043 |
uve | -1.037 |
Token | ( |
Token ID | 7 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Franch | +0.928 |
tti | +0.888 |
inker | +0.819 |
Maj | +0.819 |
uve | +0.806 |
Neg logit contributions | |
20439 | -1.218 |
Sexual | -1.017 |
Clo | -0.950 |
isolation | -0.933 |
sheltered | -0.930 |
Token | ap |
Token ID | 499 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Franch | +1.610 |
tti | +1.556 |
Maj | +1.452 |
inker | +1.443 |
uve | +1.431 |
Neg logit contributions | |
20439 | -1.587 |
Sexual | -1.270 |
Clo | -1.180 |
isolation | -1.156 |
sheltered | -1.154 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Franch | +1.283 |
tti | +1.225 |
Maj | +1.131 |
inker | +1.125 |
rieg | +1.110 |
Neg logit contributions | |
20439 | -1.654 |
Sexual | -1.366 |
Clo | -1.279 |
isolation | -1.261 |
sheltered | -1.255 |
Token | ... |
Token ID | 986 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
20439 | +0.757 |
Sexual | +0.603 |
Clo | +0.559 |
isolation | +0.549 |
sheltered | +0.547 |
Neg logit contributions | |
Franch | -0.836 |
tti | -0.799 |
Maj | -0.748 |
inker | -0.743 |
uve | -0.737 |
Token | 1 |
Token ID | 352 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
20439 | +1.708 |
Sexual | +1.379 |
Clo | +1.282 |
isolation | +1.260 |
sheltered | +1.251 |
Neg logit contributions | |
Franch | -1.776 |
tti | -1.695 |
Maj | -1.578 |
inker | -1.567 |
uve | -1.560 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Franch | +0.031 |
tti | +0.029 |
Maj | +0.027 |
inker | +0.027 |
uve | +0.027 |
Neg logit contributions | |
20439 | -0.034 |
Sexual | -0.028 |
Clo | -0.026 |
isolation | -0.025 |
sheltered | -0.025 |
Token | [ |
Token ID | 685 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
20439 | +0.127 |
Sexual | +0.102 |
Clo | +0.094 |
isolation | +0.093 |
sheltered | +0.093 |
Neg logit contributions | |
Franch | -0.134 |
tti | -0.128 |
Maj | -0.120 |
inker | -0.119 |
uve | -0.118 |
Token | color |
Token ID | 8043 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
20439 | +1.146 |
Sexual | +0.925 |
Clo | +0.855 |
isolation | +0.842 |
sheltered | +0.836 |
Neg logit contributions | |
Franch | -1.178 |
tti | -1.121 |
Maj | -1.045 |
inker | -1.038 |
uve | -1.032 |
Token | = |
Token ID | 28 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
Franch | +1.092 |
tti | +1.046 |
Maj | +0.976 |
inker | +0.969 |
uve | +0.959 |
Neg logit contributions | |
20439 | -1.129 |
Sexual | -0.910 |
Clo | -0.848 |
isolation | -0.832 |
sheltered | -0.831 |
Token | red |
Token ID | 445 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Franch | +4.394 |
tti | +4.300 |
inker | +4.022 |
Maj | +4.000 |
uve | +3.960 |
Neg logit contributions | |
20439 | -4.200 |
Sexual | -3.316 |
Clo | -3.160 |
isolation | -3.103 |
sheltered | -3.087 |
Token | ][ |
Token ID | 7131 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
Franch | +0.116 |
tti | +0.111 |
Maj | +0.105 |
inker | +0.104 |
uve | +0.103 |
Neg logit contributions | |
20439 | -0.095 |
Sexual | -0.074 |
Clo | -0.069 |
isolation | -0.067 |
sheltered | -0.067 |
Token | b |
Token ID | 65 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Franch | +0.511 |
tti | +0.486 |
Maj | +0.451 |
inker | +0.448 |
uve | +0.444 |
Neg logit contributions | |
20439 | -0.587 |
Sexual | -0.480 |
Clo | -0.450 |
isolation | -0.444 |
sheltered | -0.442 |
Token | ] |
Token ID | 60 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Franch | +1.089 |
tti | +1.050 |
Maj | +0.986 |
inker | +0.984 |
rieg | +0.973 |
Neg logit contributions | |
20439 | -0.857 |
Sexual | -0.666 |
Clo | -0.613 |
isolation | -0.603 |
sheltered | -0.599 |
Token | B |
Token ID | 33 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
Franch | +0.101 |
tti | +0.096 |
Maj | +0.090 |
inker | +0.089 |
uve | +0.089 |
Neg logit contributions | |
20439 | -0.097 |
Sexual | -0.078 |
Clo | -0.073 |
isolation | -0.072 |
sheltered | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
20439 | +2.271 |
Sexual | +1.857 |
Clo | +1.744 |
isolation | +1.714 |
sheltered | +1.701 |
Neg logit contributions | |
Franch | -2.131 |
tti | -2.039 |
inker | -1.893 |
uve | -1.883 |
rieg | -1.876 |
Token |
|
Token ID | 198 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Franch | +0.437 |
tti | +0.417 |
Maj | +0.392 |
inker | +0.384 |
uve | +0.381 |
Neg logit contributions | |
20439 | -0.455 |
Sexual | -0.364 |
Clo | -0.343 |
isolation | -0.342 |
sheltered | -0.341 |
Token | Santa |
Token ID | 42694 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
Franch | +0.324 |
tti | +0.310 |
Maj | +0.290 |
inker | +0.287 |
uve | +0.285 |
Neg logit contributions | |
20439 | -0.303 |
Sexual | -0.243 |
Clo | -0.225 |
isolation | -0.221 |
sheltered | -0.220 |
Token | Clara |
Token ID | 27443 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
20439 | +0.231 |
Sexual | +0.176 |
Clo | +0.161 |
isolation | +0.158 |
sheltered | +0.157 |
Neg logit contributions | |
Franch | -0.331 |
tti | -0.318 |
Maj | -0.300 |
inker | -0.299 |
uve | -0.296 |
Token | County |
Token ID | 3418 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Franch | +1.286 |
tti | +1.210 |
Maj | +1.128 |
inker | +1.101 |
uve | +1.079 |
Neg logit contributions | |
20439 | -1.651 |
Sexual | -1.355 |
Clo | -1.270 |
ileaks | -1.261 |
sheltered | -1.257 |
Token | v |
Token ID | 410 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
20439 | +1.727 |
Sexual | +1.415 |
Clo | +1.324 |
isolation | +1.304 |
sheltered | +1.295 |
Neg logit contributions | |
Franch | -1.600 |
tti | -1.528 |
inker | -1.415 |
uve | -1.413 |
rieg | -1.411 |
Token | . |
Token ID | 13 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
20439 | +5.633 |
Sexual | +4.629 |
Clo | +4.504 |
Hague | +4.329 |
isolation | +4.242 |
Neg logit contributions | |
Franch | -5.413 |
tti | -5.304 |
uve | -4.947 |
rieg | -4.860 |
inker | -4.847 |
Token | Southern |
Token ID | 8050 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
20439 | +0.268 |
Sexual | +0.218 |
Clo | +0.203 |
isolation | +0.201 |
sheltered | +0.200 |
Neg logit contributions | |
Franch | -0.249 |
tti | -0.237 |
Maj | -0.221 |
inker | -0.219 |
uve | -0.217 |
Token | Pacific |
Token ID | 8211 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
Franch | +0.698 |
tti | +0.661 |
Maj | +0.612 |
inker | +0.607 |
uve | +0.600 |
Neg logit contributions | |
20439 | -0.858 |
Sexual | -0.707 |
Clo | -0.664 |
isolation | -0.655 |
sheltered | -0.653 |
Token | Railroad |
Token ID | 36289 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Franch | +0.537 |
tti | +0.512 |
Maj | +0.479 |
inker | +0.475 |
uve | +0.470 |
Neg logit contributions | |
20439 | -0.527 |
Sexual | -0.424 |
Clo | -0.394 |
isolation | -0.388 |
sheltered | -0.386 |
Token | Company |
Token ID | 5834 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Franch | +0.941 |
tti | +0.891 |
Maj | +0.828 |
inker | +0.819 |
uve | +0.810 |
Neg logit contributions | |
20439 | -1.119 |
Sexual | -0.919 |
Clo | -0.862 |
isolation | -0.850 |
sheltered | -0.847 |
Token | , |
Token ID | 11 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Franch | +0.599 |
tti | +0.568 |
Maj | +0.527 |
inker | +0.521 |
uve | +0.516 |
Neg logit contributions | |
20439 | -0.715 |
Sexual | -0.588 |
Clo | -0.550 |
isolation | -0.542 |
sheltered | -0.539 |
Token | lack |
Token ID | 3092 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
Franch | +0.204 |
tti | +0.194 |
Maj | +0.180 |
inker | +0.179 |
uve | +0.178 |
Neg logit contributions | |
20439 | -0.217 |
Sexual | -0.177 |
Clo | -0.166 |
isolation | -0.164 |
sheltered | -0.163 |
Token | character |
Token ID | 2095 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Franch | +1.715 |
tti | +1.629 |
Maj | +1.537 |
inker | +1.516 |
uve | +1.505 |
Neg logit contributions | |
20439 | -1.581 |
Sexual | -1.254 |
Clo | -1.155 |
ileaks | -1.135 |
isolation | -1.134 |
Token | ? |
Token ID | 30 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
20439 | +0.159 |
Sexual | +0.127 |
Clo | +0.118 |
isolation | +0.116 |
sheltered | +0.115 |
Neg logit contributions | |
Franch | -0.178 |
tti | -0.170 |
Maj | -0.160 |
inker | -0.159 |
uve | -0.157 |
Token | What |
Token ID | 1867 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
Franch | +0.673 |
tti | +0.639 |
Maj | +0.605 |
inker | +0.592 |
rieg | +0.585 |
Neg logit contributions | |
20439 | -0.589 |
Sexual | -0.463 |
isolation | -0.422 |
Clo | -0.422 |
ileaks | -0.421 |
Token | about |
Token ID | 546 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
Franch | +0.374 |
tti | +0.357 |
Maj | +0.334 |
inker | +0.330 |
uve | +0.328 |
Neg logit contributions | |
20439 | -0.374 |
Sexual | -0.301 |
Clo | -0.280 |
isolation | -0.276 |
sheltered | -0.274 |
Token | PK |
Token ID | 29673 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
20439 | +5.397 |
Sexual | +4.464 |
Clo | +4.417 |
isolation | +4.373 |
sheltered | +4.338 |
Neg logit contributions | |
Franch | -5.306 |
tti | -5.303 |
uve | -4.998 |
rieg | -4.977 |
inker | -4.950 |
Token | Sub |
Token ID | 3834 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
Franch | +1.646 |
tti | +1.558 |
Maj | +1.471 |
inker | +1.439 |
rieg | +1.433 |
Neg logit contributions | |
20439 | -1.654 |
Sexual | -1.319 |
Clo | -1.205 |
ileaks | -1.183 |
sheltered | -1.181 |
Token | ban |
Token ID | 3820 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Franch | +0.768 |
tti | +0.735 |
Maj | +0.682 |
inker | +0.679 |
uve | +0.669 |
Neg logit contributions | |
20439 | -0.798 |
Sexual | -0.653 |
Clo | -0.611 |
isolation | -0.602 |
sheltered | -0.601 |
Token | ? |
Token ID | 30 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Franch | +1.581 |
tti | +1.509 |
Maj | +1.414 |
inker | +1.385 |
uve | +1.378 |
Neg logit contributions | |
20439 | -1.664 |
Sexual | -1.347 |
Clo | -1.248 |
isolation | -1.227 |
ileaks | -1.222 |
Token | ( |
Token ID | 357 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Franch | +0.531 |
tti | +0.504 |
Maj | +0.476 |
inker | +0.467 |
uve | +0.463 |
Neg logit contributions | |
20439 | -0.480 |
Sexual | -0.380 |
Clo | -0.349 |
isolation | -0.346 |
ileaks | -0.345 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Franch | +1.218 |
tti | +1.170 |
Maj | +1.094 |
inker | +1.063 |
rieg | +1.051 |
Neg logit contributions | |
20439 | -1.401 |
Sexual | -1.115 |
ileaks | -1.055 |
isolation | -1.053 |
Clo | -1.045 |
Token | � |
Token ID | 447 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Franch | +0.926 |
tti | +0.884 |
Maj | +0.824 |
inker | +0.819 |
uve | +0.811 |
Neg logit contributions | |
20439 | -0.934 |
Sexual | -0.752 |
Clo | -0.703 |
isolation | -0.692 |
sheltered | -0.689 |
Token | � |
Token ID | 250 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
Franch | +1.527 |
tti | +1.474 |
Maj | +1.384 |
inker | +1.371 |
uve | +1.360 |
Neg logit contributions | |
20439 | -1.378 |
Sexual | -1.088 |
Clo | -1.010 |
isolation | -0.993 |
sheltered | -0.983 |
Token | But |
Token ID | 1537 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Franch | +0.745 |
tti | +0.711 |
Maj | +0.663 |
inker | +0.659 |
uve | +0.652 |
Neg logit contributions | |
20439 | -0.757 |
Sexual | -0.611 |
Clo | -0.570 |
isolation | -0.561 |
sheltered | -0.558 |
Token | what |
Token ID | 644 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
20439 | +0.326 |
Sexual | +0.262 |
Clo | +0.244 |
isolation | +0.240 |
sheltered | +0.238 |
Neg logit contributions | |
Franch | -0.342 |
tti | -0.326 |
Maj | -0.305 |
inker | -0.302 |
uve | -0.301 |
Token | about |
Token ID | 546 |
Feature activation | -7.05e+00 |
Pos logit contributions | |
Franch | +0.158 |
tti | +0.150 |
Maj | +0.140 |
inker | +0.139 |
uve | +0.138 |
Neg logit contributions | |
20439 | -0.157 |
Sexual | -0.126 |
Clo | -0.118 |
isolation | -0.116 |
sheltered | -0.115 |
Token | the |
Token ID | 262 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
20439 | +5.283 |
Sexual | +4.201 |
Clo | +4.048 |
isolation | +4.016 |
padded | +3.984 |
Neg logit contributions | |
Franch | -5.587 |
tti | -5.417 |
uve | -5.078 |
rieg | -5.046 |
inker | -5.015 |
Token | books |
Token ID | 3835 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
20439 | +0.608 |
Sexual | +0.491 |
Clo | +0.460 |
isolation | +0.453 |
sheltered | +0.451 |
Neg logit contributions | |
Franch | -0.598 |
tti | -0.570 |
Maj | -0.531 |
inker | -0.528 |
uve | -0.525 |
Token | I |
Token ID | 314 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Franch | +0.645 |
tti | +0.617 |
Maj | +0.579 |
inker | +0.574 |
uve | +0.569 |
Neg logit contributions | |
20439 | -0.578 |
Sexual | -0.460 |
Clo | -0.424 |
isolation | -0.418 |
sheltered | -0.415 |
Token | bought |
Token ID | 5839 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
20439 | +0.090 |
Sexual | +0.073 |
Clo | +0.068 |
isolation | +0.067 |
sheltered | +0.066 |
Neg logit contributions | |
Franch | -0.088 |
tti | -0.084 |
Maj | -0.078 |
inker | -0.077 |
uve | -0.077 |
Token | from |
Token ID | 422 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
20439 | +1.563 |
Sexual | +1.255 |
Clo | +1.176 |
isolation | +1.154 |
sheltered | +1.152 |
Neg logit contributions | |
Franch | -1.608 |
tti | -1.529 |
inker | -1.429 |
Maj | -1.426 |
uve | -1.417 |
Token | Which |
Token ID | 13828 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Franch | +0.283 |
tti | +0.268 |
Maj | +0.251 |
inker | +0.248 |
uve | +0.246 |
Neg logit contributions | |
20439 | -0.278 |
Sexual | -0.226 |
Clo | -0.208 |
isolation | -0.205 |
sheltered | -0.204 |
Token | reminds |
Token ID | 17603 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
20439 | +0.125 |
Sexual | +0.101 |
Clo | +0.094 |
isolation | +0.093 |
sheltered | +0.093 |
Neg logit contributions | |
Franch | -0.140 |
tti | -0.133 |
inker | -0.125 |
Maj | -0.125 |
rieg | -0.124 |
Token | me |
Token ID | 502 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
20439 | +1.493 |
Sexual | +1.165 |
Clo | +1.094 |
isolation | +1.069 |
Hague | +1.060 |
Neg logit contributions | |
Franch | -2.272 |
tti | -2.187 |
uve | -2.063 |
rieg | -2.063 |
inker | -2.051 |
Token | : |
Token ID | 25 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
20439 | +0.820 |
Sexual | +0.681 |
Clo | +0.648 |
isolation | +0.639 |
sheltered | +0.631 |
Neg logit contributions | |
Franch | -0.674 |
tti | -0.636 |
uve | -0.589 |
Maj | -0.585 |
inker | -0.583 |
Token | what |
Token ID | 644 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
20439 | +1.248 |
Sexual | +1.009 |
Clo | +0.952 |
isolation | +0.937 |
sheltered | +0.926 |
Neg logit contributions | |
Franch | -1.359 |
tti | -1.293 |
Maj | -1.205 |
inker | -1.205 |
rieg | -1.201 |
Token | about |
Token ID | 546 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
20439 | +0.153 |
Sexual | +0.123 |
Clo | +0.116 |
isolation | +0.114 |
sheltered | +0.113 |
Neg logit contributions | |
Franch | -0.167 |
tti | -0.159 |
inker | -0.148 |
Maj | -0.148 |
uve | -0.147 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
20439 | +4.989 |
isolation | +4.109 |
Sexual | +4.102 |
Clo | +4.094 |
apes | +4.002 |
Neg logit contributions | |
Franch | -5.504 |
tti | -5.309 |
inker | -4.920 |
rieg | -4.903 |
uve | -4.872 |
Token | boil |
Token ID | 20667 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
20439 | +1.101 |
Sexual | +0.895 |
Clo | +0.849 |
isolation | +0.843 |
sheltered | +0.834 |
Neg logit contributions | |
Franch | -1.120 |
tti | -1.068 |
inker | -0.992 |
Maj | -0.987 |
uve | -0.985 |
Token | ? |
Token ID | 30 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
Franch | +1.497 |
tti | +1.435 |
Maj | +1.341 |
inker | +1.332 |
rieg | +1.320 |
Neg logit contributions | |
20439 | -1.408 |
Sexual | -1.124 |
Clo | -1.040 |
isolation | -1.019 |
sheltered | -1.012 |
Token | Anders |
Token ID | 25519 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Franch | +0.645 |
tti | +0.616 |
Maj | +0.578 |
inker | +0.573 |
uve | +0.568 |
Neg logit contributions | |
20439 | -0.588 |
Sexual | -0.468 |
Clo | -0.432 |
isolation | -0.426 |
sheltered | -0.424 |
Token | boils |
Token ID | 40169 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
Franch | +1.412 |
tti | +1.359 |
Maj | +1.271 |
inker | +1.253 |
uve | +1.245 |
Neg logit contributions | |
20439 | -1.366 |
Sexual | -1.089 |
Clo | -0.998 |
isolation | -0.985 |
ileaks | -0.983 |
Token | man |
Token ID | 805 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
20439 | +0.348 |
Sexual | +0.271 |
Clo | +0.250 |
isolation | +0.246 |
sheltered | +0.245 |
Neg logit contributions | |
Franch | -0.434 |
tti | -0.417 |
Maj | -0.392 |
inker | -0.390 |
uve | -0.386 |
Token | : |
Token ID | 25 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
20439 | +0.614 |
Sexual | +0.506 |
Clo | +0.476 |
isolation | +0.471 |
sheltered | +0.469 |
Neg logit contributions | |
Franch | -0.477 |
tti | -0.453 |
Maj | -0.419 |
inker | -0.413 |
uve | -0.410 |
Token | Really |
Token ID | 16123 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
20439 | +0.768 |
Sexual | +0.615 |
Clo | +0.572 |
isolation | +0.556 |
sheltered | +0.552 |
Neg logit contributions | |
Franch | -0.869 |
tti | -0.834 |
inker | -0.780 |
Maj | -0.775 |
uve | -0.773 |
Token | ? |
Token ID | 30 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
20439 | +0.761 |
Sexual | +0.610 |
Clo | +0.563 |
isolation | +0.557 |
sheltered | +0.553 |
Neg logit contributions | |
Franch | -0.887 |
tti | -0.846 |
inker | -0.793 |
Maj | -0.788 |
rieg | -0.785 |
Token | What |
Token ID | 1867 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
20439 | +1.059 |
Sexual | +0.850 |
Clo | +0.791 |
isolation | +0.771 |
sheltered | +0.767 |
Neg logit contributions | |
Franch | -1.161 |
tti | -1.110 |
inker | -1.037 |
Maj | -1.034 |
uve | -1.028 |
Token | about |
Token ID | 546 |
Feature activation | -6.93e+00 |
Pos logit contributions | |
20439 | +0.343 |
Sexual | +0.275 |
Clo | +0.255 |
isolation | +0.251 |
sheltered | +0.250 |
Neg logit contributions | |
Franch | -0.372 |
tti | -0.355 |
Maj | -0.332 |
inker | -0.331 |
uve | -0.328 |
Token | sou |
Token ID | 24049 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
20439 | +4.938 |
Sexual | +4.021 |
isolation | +3.945 |
Clo | +3.887 |
sheltered | +3.869 |
Neg logit contributions | |
Franch | -5.664 |
tti | -5.425 |
inker | -5.114 |
rieg | -5.087 |
uve | -5.079 |
Token | ff |
Token ID | 487 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
20439 | +0.583 |
Sexual | +0.433 |
Clo | +0.391 |
isolation | +0.380 |
sheltered | +0.379 |
Neg logit contributions | |
Franch | -0.980 |
tti | -0.940 |
Maj | -0.891 |
inker | -0.887 |
uve | -0.879 |
Token | l |
Token ID | 75 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
Franch | +2.718 |
tti | +2.621 |
uve | +2.380 |
inker | +2.370 |
Maj | +2.370 |
Neg logit contributions | |
20439 | -3.103 |
Sexual | -2.510 |
Clo | -2.353 |
isolation | -2.338 |
IRC | -2.299 |
Token | és |
Token ID | 20954 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
Franch | +1.672 |
tti | +1.569 |
uve | +1.384 |
inker | +1.379 |
rieg | +1.379 |
Neg logit contributions | |
20439 | -3.379 |
Sexual | -2.862 |
isolation | -2.706 |
Clo | -2.706 |
sheltered | -2.682 |
Token | or |
Token ID | 393 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
Franch | +0.050 |
tti | +0.047 |
Maj | +0.044 |
inker | +0.044 |
uve | +0.044 |
Neg logit contributions | |
20439 | -0.047 |
Sexual | -0.038 |
Clo | -0.035 |
isolation | -0.034 |
sheltered | -0.034 |
Token | grand |
Token ID | 4490 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
20439 | +0.839 |
Sexual | +0.666 |
Clo | +0.617 |
isolation | +0.606 |
sheltered | +0.604 |
Neg logit contributions | |
Franch | -0.981 |
tti | -0.940 |
Maj | -0.877 |
inker | -0.874 |
rieg | -0.868 |
Token | level |
Token ID | 1241 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
Franch | +0.953 |
tti | +0.907 |
Maj | +0.844 |
inker | +0.837 |
uve | +0.829 |
Neg logit contributions | |
20439 | -1.068 |
Sexual | -0.871 |
Clo | -0.815 |
isolation | -0.802 |
sheltered | -0.799 |
Token | , |
Token ID | 11 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
20439 | +0.505 |
Sexual | +0.413 |
Clo | +0.387 |
isolation | +0.381 |
sheltered | +0.379 |
Neg logit contributions | |
Franch | -0.445 |
tti | -0.422 |
Maj | -0.392 |
inker | -0.389 |
uve | -0.386 |
Token | but |
Token ID | 475 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
Franch | +0.118 |
tti | +0.112 |
Maj | +0.105 |
inker | +0.104 |
uve | +0.103 |
Neg logit contributions | |
20439 | -0.114 |
Sexual | -0.092 |
Clo | -0.085 |
isolation | -0.084 |
sheltered | -0.083 |
Token | what |
Token ID | 644 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
20439 | +0.032 |
Sexual | +0.026 |
Clo | +0.024 |
isolation | +0.024 |
sheltered | +0.024 |
Neg logit contributions | |
Franch | -0.034 |
tti | -0.032 |
Maj | -0.030 |
inker | -0.030 |
uve | -0.030 |
Token | about |
Token ID | 546 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
20439 | +0.122 |
Sexual | +0.098 |
Clo | +0.092 |
isolation | +0.090 |
sheltered | +0.090 |
Neg logit contributions | |
Franch | -0.120 |
tti | -0.115 |
Maj | -0.107 |
inker | -0.106 |
uve | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
20439 | +5.045 |
Sexual | +4.057 |
isolation | +3.923 |
Clo | +3.887 |
sheltered | +3.856 |
Neg logit contributions | |
Franch | -5.423 |
tti | -5.240 |
inker | -4.908 |
rieg | -4.839 |
uve | -4.830 |
Token | passport |
Token ID | 17981 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
20439 | +0.764 |
Sexual | +0.616 |
Clo | +0.575 |
isolation | +0.568 |
sheltered | +0.564 |
Neg logit contributions | |
Franch | -0.766 |
tti | -0.731 |
Maj | -0.681 |
inker | -0.678 |
uve | -0.672 |
Token | ing |
Token ID | 278 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Franch | +1.128 |
tti | +1.077 |
Maj | +1.008 |
inker | +0.999 |
uve | +0.991 |
Neg logit contributions | |
20439 | -1.095 |
Sexual | -0.880 |
Clo | -0.817 |
isolation | -0.803 |
sheltered | -0.800 |
Token | of |
Token ID | 286 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
Franch | +1.378 |
tti | +1.310 |
Maj | +1.223 |
inker | +1.203 |
uve | +1.195 |
Neg logit contributions | |
20439 | -1.620 |
Sexual | -1.329 |
Clo | -1.235 |
ileaks | -1.217 |
isolation | -1.217 |
Token | people |
Token ID | 661 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
Franch | +0.593 |
tti | +0.565 |
Maj | +0.528 |
inker | +0.522 |
uve | +0.518 |
Neg logit contributions | |
20439 | -0.608 |
Sexual | -0.491 |
Clo | -0.456 |
isolation | -0.450 |
sheltered | -0.448 |
Token | igated |
Token ID | 26963 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
Franch | +0.250 |
tti | +0.237 |
Maj | +0.222 |
inker | +0.221 |
uve | +0.220 |
Neg logit contributions | |
20439 | -0.275 |
Sexual | -0.223 |
Clo | -0.210 |
isolation | -0.208 |
sheltered | -0.206 |
Token | disaster |
Token ID | 9336 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
20439 | +1.771 |
Sexual | +1.474 |
isolation | +1.398 |
Clo | +1.384 |
sheltered | +1.379 |
Neg logit contributions | |
Franch | -1.689 |
tti | -1.610 |
uve | -1.473 |
Maj | -1.470 |
rieg | -1.463 |
Token | . |
Token ID | 13 |
Feature activation | +9.46e-02 |
Pos logit contributions | |
20439 | +0.471 |
Sexual | +0.388 |
Clo | +0.364 |
isolation | +0.359 |
sheltered | +0.358 |
Neg logit contributions | |
Franch | -0.391 |
tti | -0.371 |
Maj | -0.344 |
inker | -0.341 |
uve | -0.338 |
Token | But |
Token ID | 887 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Franch | +0.075 |
tti | +0.072 |
Maj | +0.067 |
inker | +0.066 |
uve | +0.066 |
Neg logit contributions | |
20439 | -0.077 |
Sexual | -0.063 |
Clo | -0.058 |
isolation | -0.057 |
sheltered | -0.057 |
Token | what |
Token ID | 644 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
Franch | +0.796 |
tti | +0.758 |
Maj | +0.707 |
inker | +0.701 |
uve | +0.694 |
Neg logit contributions | |
20439 | -0.843 |
Sexual | -0.683 |
Clo | -0.637 |
isolation | -0.627 |
sheltered | -0.624 |
Token | about |
Token ID | 546 |
Feature activation | -6.55e+00 |
Pos logit contributions | |
Franch | +0.268 |
tti | +0.256 |
Maj | +0.240 |
inker | +0.238 |
uve | +0.236 |
Neg logit contributions | |
20439 | -0.247 |
Sexual | -0.197 |
Clo | -0.183 |
isolation | -0.180 |
sheltered | -0.179 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
20439 | +5.045 |
Sexual | +4.104 |
isolation | +4.075 |
Clo | +4.000 |
sheltered | +3.894 |
Neg logit contributions | |
Franch | -4.972 |
tti | -4.885 |
uve | -4.474 |
inker | -4.455 |
rieg | -4.450 |
Token | remainder |
Token ID | 17675 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
20439 | +0.927 |
Sexual | +0.745 |
Clo | +0.703 |
isolation | +0.695 |
sheltered | +0.687 |
Neg logit contributions | |
Franch | -0.957 |
tti | -0.915 |
Maj | -0.850 |
inker | -0.848 |
uve | -0.844 |
Token | of |
Token ID | 286 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
20439 | +1.609 |
Sexual | +1.329 |
Clo | +1.255 |
isolation | +1.240 |
sheltered | +1.237 |
Neg logit contributions | |
Franch | -1.293 |
tti | -1.218 |
Maj | -1.122 |
inker | -1.121 |
uve | -1.110 |
Token | his |
Token ID | 465 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Franch | +0.384 |
tti | +0.362 |
Maj | +0.333 |
inker | +0.330 |
uve | +0.326 |
Neg logit contributions | |
20439 | -0.539 |
Sexual | -0.450 |
Clo | -0.425 |
isolation | -0.420 |
sheltered | -0.417 |
Token | term |
Token ID | 3381 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
20439 | +0.856 |
Sexual | +0.701 |
Clo | +0.663 |
isolation | +0.659 |
sheltered | +0.651 |
Neg logit contributions | |
Franch | -0.762 |
tti | -0.728 |
inker | -0.668 |
Maj | -0.667 |
uve | -0.665 |
Token | … |
Token ID | 1399 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
Franch | +0.960 |
tti | +0.913 |
Maj | +0.852 |
inker | +0.836 |
uve | +0.829 |
Neg logit contributions | |
20439 | -1.083 |
Sexual | -0.886 |
Clo | -0.823 |
isolation | -0.814 |
sheltered | -0.810 |
Token |
|
Token ID | 198 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
20439 | +2.033 |
Sexual | +1.634 |
Clo | +1.523 |
isolation | +1.493 |
sheltered | +1.484 |
Neg logit contributions | |
Franch | -2.135 |
tti | -2.039 |
Maj | -1.902 |
inker | -1.895 |
uve | -1.882 |
Token |
|
Token ID | 198 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
20439 | +0.504 |
Sexual | +0.403 |
Clo | +0.377 |
isolation | +0.376 |
ileaks | +0.373 |
Neg logit contributions | |
Franch | -0.482 |
tti | -0.461 |
Maj | -0.432 |
inker | -0.424 |
rieg | -0.420 |
Token | Game |
Token ID | 8777 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
20439 | +0.742 |
Sexual | +0.600 |
Clo | +0.553 |
isolation | +0.544 |
sheltered | +0.542 |
Neg logit contributions | |
Franch | -0.766 |
tti | -0.729 |
Maj | -0.683 |
inker | -0.676 |
uve | -0.672 |
Token | 75 |
Token ID | 5441 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
Franch | +2.174 |
tti | +2.067 |
Maj | +1.926 |
inker | +1.892 |
uve | +1.881 |
Neg logit contributions | |
20439 | -2.471 |
Sexual | -2.011 |
Clo | -1.865 |
isolation | -1.852 |
sheltered | -1.842 |
Token | v |
Token ID | 410 |
Feature activation | -6.47e+00 |
Pos logit contributions | |
20439 | +0.344 |
Sexual | +0.280 |
Clo | +0.263 |
isolation | +0.259 |
sheltered | +0.257 |
Neg logit contributions | |
Franch | -0.314 |
tti | -0.299 |
Maj | -0.278 |
inker | -0.276 |
uve | -0.273 |
Token | Blue |
Token ID | 4518 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
20439 | +5.066 |
Sexual | +4.102 |
Clo | +3.975 |
Hague | +3.844 |
sheltered | +3.837 |
Neg logit contributions | |
Franch | -4.919 |
tti | -4.750 |
uve | -4.482 |
inker | -4.420 |
Maj | -4.389 |
Token | Jackets |
Token ID | 41324 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
20439 | +0.833 |
Sexual | +0.681 |
Clo | +0.649 |
isolation | +0.633 |
sheltered | +0.629 |
Neg logit contributions | |
Franch | -0.839 |
tti | -0.803 |
inker | -0.744 |
rieg | -0.740 |
Maj | -0.737 |
Token | – |
Token ID | 784 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
20439 | +1.585 |
Sexual | +1.284 |
Clo | +1.203 |
isolation | +1.183 |
sheltered | +1.178 |
Neg logit contributions | |
Franch | -1.576 |
tti | -1.508 |
inker | -1.400 |
Maj | -1.399 |
uve | -1.390 |
Token | Won |
Token ID | 23306 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
20439 | +0.219 |
Sexual | +0.177 |
Clo | +0.163 |
isolation | +0.161 |
sheltered | +0.161 |
Neg logit contributions | |
Franch | -0.214 |
tti | -0.203 |
Maj | -0.190 |
inker | -0.187 |
uve | -0.186 |
Token | 4 |
Token ID | 604 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
20439 | +1.173 |
Sexual | +0.956 |
Clo | +0.900 |
isolation | +0.883 |
sheltered | +0.877 |
Neg logit contributions | |
Franch | -1.125 |
tti | -1.071 |
Maj | -0.993 |
inker | -0.989 |
rieg | -0.983 |
Token | reading |
Token ID | 3555 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
20439 | +1.976 |
Sexual | +1.578 |
Clo | +1.464 |
isolation | +1.441 |
sheltered | +1.435 |
Neg logit contributions | |
Franch | -2.152 |
tti | -2.055 |
Maj | -1.921 |
inker | -1.912 |
rieg | -1.894 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
20439 | +3.325 |
Sexual | +2.693 |
Clo | +2.515 |
isolation | +2.439 |
sheltered | +2.435 |
Neg logit contributions | |
Franch | -3.840 |
tti | -3.684 |
inker | -3.461 |
uve | -3.402 |
rieg | -3.359 |
Token | main |
Token ID | 1388 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
20439 | +1.365 |
Sexual | +1.129 |
Clo | +1.061 |
isolation | +1.047 |
sheltered | +1.043 |
Neg logit contributions | |
Franch | -1.085 |
tti | -1.028 |
Maj | -0.949 |
inker | -0.942 |
uve | -0.933 |
Token | story |
Token ID | 1621 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
20439 | +1.597 |
Sexual | +1.323 |
Clo | +1.247 |
isolation | +1.232 |
sheltered | +1.226 |
Neg logit contributions | |
Franch | -1.145 |
tti | -1.080 |
Maj | -1.001 |
inker | -0.988 |
rieg | -0.978 |
Token | Please |
Token ID | 4222 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
20439 | +2.325 |
Sexual | +1.928 |
Clo | +1.813 |
isolation | +1.783 |
sheltered | +1.776 |
Neg logit contributions | |
Franch | -1.862 |
tti | -1.774 |
inker | -1.633 |
Maj | -1.628 |
uve | -1.611 |
Token | verify |
Token ID | 11767 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
20439 | +2.971 |
Sexual | +2.311 |
Clo | +2.119 |
isolation | +2.083 |
sheltered | +2.075 |
Neg logit contributions | |
Franch | -4.046 |
tti | -3.881 |
Maj | -3.639 |
inker | -3.627 |
uve | -3.617 |
Token | you |
Token ID | 345 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
20439 | +4.227 |
Sexual | +3.290 |
Clo | +3.061 |
isolation | +2.960 |
sheltered | +2.954 |
Neg logit contributions | |
Franch | -5.952 |
tti | -5.685 |
inker | -5.375 |
Maj | -5.315 |
uve | -5.300 |
Token | 're |
Token ID | 821 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
20439 | +1.153 |
Sexual | +0.944 |
Clo | +0.881 |
isolation | +0.871 |
ileaks | +0.866 |
Neg logit contributions | |
Franch | -0.951 |
tti | -0.907 |
Maj | -0.848 |
inker | -0.825 |
rieg | -0.824 |
Token | not |
Token ID | 407 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
20439 | +1.255 |
Sexual | +1.039 |
Clo | +0.973 |
ileaks | +0.962 |
isolation | +0.961 |
Neg logit contributions | |
Franch | -0.962 |
tti | -0.908 |
Maj | -0.848 |
inker | -0.826 |
rieg | -0.821 |
Token | a |
Token ID | 257 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
20439 | +0.711 |
Sexual | +0.585 |
Clo | +0.549 |
isolation | +0.542 |
sheltered | +0.540 |
Neg logit contributions | |
Franch | -0.587 |
tti | -0.557 |
Maj | -0.515 |
inker | -0.511 |
uve | -0.506 |
Token | robot |
Token ID | 9379 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
20439 | +0.819 |
Sexual | +0.616 |
Clo | +0.560 |
isolation | +0.547 |
sheltered | +0.544 |
Neg logit contributions | |
Franch | -1.288 |
tti | -1.240 |
Maj | -1.172 |
inker | -1.166 |
uve | -1.160 |
Token | cake |
Token ID | 12187 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Franch | +1.449 |
tti | +1.385 |
Maj | +1.286 |
inker | +1.282 |
uve | +1.277 |
Neg logit contributions | |
20439 | -1.386 |
Sexual | -1.119 |
Clo | -1.045 |
isolation | -1.030 |
sheltered | -1.026 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Franch | +1.567 |
tti | +1.469 |
Maj | +1.330 |
inker | +1.313 |
rieg | +1.295 |
Neg logit contributions | |
20439 | -2.820 |
Sexual | -2.395 |
Clo | -2.270 |
isolation | -2.243 |
sheltered | -2.236 |
Token |
|
Token ID | 198 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
Franch | +0.940 |
tti | +0.896 |
Maj | +0.840 |
inker | +0.831 |
uve | +0.823 |
Neg logit contributions | |
20439 | -0.890 |
Sexual | -0.710 |
Clo | -0.658 |
isolation | -0.650 |
sheltered | -0.648 |
Token |
|
Token ID | 198 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Franch | +0.426 |
tti | +0.407 |
Maj | +0.380 |
inker | +0.378 |
uve | +0.374 |
Neg logit contributions | |
20439 | -0.411 |
Sexual | -0.330 |
Clo | -0.307 |
isolation | -0.302 |
sheltered | -0.300 |
Token | How |
Token ID | 2437 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Franch | +0.323 |
tti | +0.307 |
Maj | +0.288 |
inker | +0.285 |
uve | +0.283 |
Neg logit contributions | |
20439 | -0.315 |
Sexual | -0.255 |
Clo | -0.236 |
isolation | -0.232 |
sheltered | -0.231 |
Token | about |
Token ID | 546 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
Franch | +1.003 |
tti | +0.957 |
Maj | +0.896 |
inker | +0.890 |
uve | +0.883 |
Neg logit contributions | |
20439 | -0.937 |
Sexual | -0.750 |
Clo | -0.697 |
isolation | -0.685 |
sheltered | -0.682 |
Token | just |
Token ID | 655 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
20439 | +4.747 |
Sexual | +3.907 |
isolation | +3.848 |
Clo | +3.788 |
sheltered | +3.715 |
Neg logit contributions | |
Franch | -4.927 |
tti | -4.764 |
uve | -4.453 |
inker | -4.432 |
rieg | -4.413 |
Token | in |
Token ID | 287 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
20439 | +0.548 |
Sexual | +0.439 |
Clo | +0.411 |
isolation | +0.406 |
sheltered | +0.402 |
Neg logit contributions | |
Franch | -0.594 |
tti | -0.568 |
Maj | -0.529 |
inker | -0.527 |
uve | -0.525 |
Token | the |
Token ID | 262 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
Franch | +0.306 |
tti | +0.292 |
Maj | +0.271 |
inker | +0.270 |
uve | +0.267 |
Neg logit contributions | |
20439 | -0.330 |
Sexual | -0.269 |
Clo | -0.252 |
isolation | -0.249 |
sheltered | -0.247 |
Token | Ruby |
Token ID | 10888 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
20439 | +0.416 |
Sexual | +0.339 |
Clo | +0.318 |
isolation | +0.315 |
sheltered | +0.313 |
Neg logit contributions | |
Franch | -0.395 |
tti | -0.377 |
inker | -0.350 |
Maj | -0.348 |
uve | -0.346 |
Token | community |
Token ID | 2055 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
20439 | +0.157 |
Sexual | +0.130 |
Clo | +0.122 |
isolation | +0.120 |
sheltered | +0.120 |
Neg logit contributions | |
Franch | -0.133 |
tti | -0.126 |
Maj | -0.116 |
inker | -0.116 |
uve | -0.114 |
Token | after |
Token ID | 706 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
20439 | +4.486 |
Sexual | +3.615 |
isolation | +3.572 |
Clo | +3.543 |
padded | +3.439 |
Neg logit contributions | |
Franch | -5.054 |
tti | -4.852 |
inker | -4.558 |
uve | -4.540 |
rieg | -4.528 |
Token | the |
Token ID | 262 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
20439 | +0.287 |
Sexual | +0.231 |
Clo | +0.218 |
isolation | +0.215 |
sheltered | +0.211 |
Neg logit contributions | |
Franch | -0.299 |
tti | -0.285 |
Maj | -0.266 |
inker | -0.265 |
uve | -0.263 |
Token | presentation |
Token ID | 10470 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
20439 | +0.061 |
Sexual | +0.050 |
Clo | +0.048 |
isolation | +0.047 |
sheltered | +0.047 |
Neg logit contributions | |
Franch | -0.051 |
tti | -0.049 |
Maj | -0.045 |
inker | -0.045 |
uve | -0.044 |
Token | ? |
Token ID | 30 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
20439 | +0.528 |
Sexual | +0.425 |
Clo | +0.397 |
isolation | +0.391 |
sheltered | +0.387 |
Neg logit contributions | |
Franch | -0.547 |
tti | -0.521 |
Maj | -0.485 |
inker | -0.484 |
uve | -0.479 |
Token | How |
Token ID | 1374 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Franch | +1.362 |
tti | +1.298 |
Maj | +1.227 |
inker | +1.203 |
uve | +1.195 |
Neg logit contributions | |
20439 | -1.239 |
Sexual | -0.982 |
Clo | -0.898 |
sheltered | -0.891 |
isolation | -0.890 |
Token | about |
Token ID | 546 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
Franch | +0.087 |
tti | +0.082 |
Maj | +0.076 |
inker | +0.076 |
rieg | +0.076 |
Neg logit contributions | |
20439 | -0.091 |
Sexual | -0.074 |
Clo | -0.069 |
isolation | -0.068 |
sheltered | -0.068 |
Token | after |
Token ID | 706 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
20439 | +4.639 |
Sexual | +3.740 |
Clo | +3.670 |
isolation | +3.660 |
padded | +3.546 |
Neg logit contributions | |
Franch | -5.107 |
tti | -4.881 |
inker | -4.573 |
rieg | -4.559 |
uve | -4.556 |
Token | first |
Token ID | 717 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
20439 | +0.131 |
Sexual | +0.105 |
Clo | +0.099 |
isolation | +0.097 |
sheltered | +0.096 |
Neg logit contributions | |
Franch | -0.136 |
tti | -0.130 |
Maj | -0.121 |
inker | -0.121 |
uve | -0.119 |
Token | 10 |
Token ID | 838 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
20439 | +1.587 |
Sexual | +1.263 |
Clo | +1.187 |
isolation | +1.181 |
sheltered | +1.148 |
Neg logit contributions | |
Franch | -1.730 |
tti | -1.647 |
inker | -1.532 |
Maj | -1.522 |
rieg | -1.515 |
Token | uses |
Token ID | 3544 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
Franch | +0.735 |
tti | +0.703 |
Maj | +0.659 |
inker | +0.652 |
uve | +0.647 |
Neg logit contributions | |
20439 | -0.681 |
Sexual | -0.544 |
Clo | -0.504 |
isolation | -0.496 |
sheltered | -0.494 |
Token | ? |
Token ID | 30 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
20439 | +0.788 |
Sexual | +0.639 |
Clo | +0.600 |
isolation | +0.595 |
sheltered | +0.586 |
Neg logit contributions | |
Franch | -0.747 |
tti | -0.708 |
inker | -0.656 |
Maj | -0.656 |
uve | -0.649 |
Token | pharmac |
Token ID | 25702 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
20439 | +0.385 |
Sexual | +0.319 |
Clo | +0.300 |
isolation | +0.298 |
sheltered | +0.295 |
Neg logit contributions | |
Franch | -0.310 |
tti | -0.294 |
Maj | -0.270 |
inker | -0.269 |
uve | -0.266 |
Token | ological |
Token ID | 2770 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
Franch | +0.788 |
tti | +0.739 |
Maj | +0.666 |
inker | +0.662 |
uve | +0.651 |
Neg logit contributions | |
20439 | -1.500 |
Sexual | -1.276 |
Clo | -1.213 |
isolation | -1.197 |
sheltered | -1.197 |
Token | profile |
Token ID | 7034 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
Franch | +0.257 |
tti | +0.244 |
Maj | +0.226 |
inker | +0.224 |
uve | +0.222 |
Neg logit contributions | |
20439 | -0.318 |
Sexual | -0.263 |
Clo | -0.246 |
isolation | -0.243 |
sheltered | -0.242 |
Token | of |
Token ID | 286 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
20439 | +0.539 |
Sexual | +0.450 |
Clo | +0.426 |
isolation | +0.424 |
sheltered | +0.419 |
Neg logit contributions | |
Franch | -0.374 |
tti | -0.351 |
Maj | -0.320 |
inker | -0.318 |
uve | -0.315 |
Token | N |
Token ID | 399 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
20439 | +0.906 |
Sexual | +0.710 |
Clo | +0.654 |
isolation | +0.642 |
sheltered | +0.638 |
Neg logit contributions | |
Franch | -1.123 |
tti | -1.076 |
Maj | -1.012 |
inker | -1.006 |
uve | -0.998 |
Token | - |
Token ID | 12 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
20439 | +1.760 |
Sexual | +1.448 |
Clo | +1.356 |
isolation | +1.340 |
sheltered | +1.328 |
Neg logit contributions | |
Franch | -1.502 |
tti | -1.424 |
Maj | -1.324 |
inker | -1.314 |
uve | -1.295 |
Token | cyclop |
Token ID | 22873 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
20439 | +4.963 |
Sexual | +4.081 |
Clo | +3.721 |
isolation | +3.683 |
IRC | +3.641 |
Neg logit contributions | |
Franch | -5.068 |
tti | -4.794 |
Maj | -4.515 |
inker | -4.470 |
rieg | -4.432 |
Token | rop |
Token ID | 1773 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
20439 | +0.723 |
Sexual | +0.565 |
Clo | +0.522 |
isolation | +0.512 |
sheltered | +0.508 |
Neg logit contributions | |
Franch | -0.896 |
tti | -0.857 |
Maj | -0.804 |
inker | -0.792 |
rieg | -0.791 |
Token | yl |
Token ID | 2645 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
20439 | +1.054 |
Sexual | +0.861 |
Clo | +0.800 |
sheltered | +0.794 |
aeus | +0.792 |
Neg logit contributions | |
Franch | -0.944 |
tti | -0.890 |
Maj | -0.835 |
inker | -0.817 |
uve | -0.811 |
Token | methyl |
Token ID | 43654 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
Franch | +0.929 |
tti | +0.889 |
Maj | +0.830 |
inker | +0.824 |
uve | +0.816 |
Neg logit contributions | |
20439 | -0.923 |
Sexual | -0.743 |
Clo | -0.690 |
isolation | -0.681 |
sheltered | -0.678 |
Token | - |
Token ID | 12 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
20439 | +2.248 |
Sexual | +1.830 |
Clo | +1.728 |
isolation | +1.699 |
ileaks | +1.675 |
Neg logit contributions | |
Franch | -2.177 |
tti | -2.049 |
Maj | -1.907 |
rieg | -1.890 |
inker | -1.888 |
Token | first |
Token ID | 717 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
20439 | +0.131 |
Sexual | +0.105 |
Clo | +0.099 |
isolation | +0.097 |
sheltered | +0.096 |
Neg logit contributions | |
Franch | -0.136 |
tti | -0.130 |
Maj | -0.121 |
inker | -0.121 |
uve | -0.119 |
Token | 10 |
Token ID | 838 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
20439 | +1.587 |
Sexual | +1.263 |
Clo | +1.187 |
isolation | +1.181 |
sheltered | +1.148 |
Neg logit contributions | |
Franch | -1.730 |
tti | -1.647 |
inker | -1.532 |
Maj | -1.522 |
rieg | -1.515 |
Token | uses |
Token ID | 3544 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
Franch | +0.735 |
tti | +0.703 |
Maj | +0.659 |
inker | +0.652 |
uve | +0.647 |
Neg logit contributions | |
20439 | -0.681 |
Sexual | -0.544 |
Clo | -0.504 |
isolation | -0.496 |
sheltered | -0.494 |
Token | ? |
Token ID | 30 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
20439 | +0.788 |
Sexual | +0.639 |
Clo | +0.600 |
isolation | +0.595 |
sheltered | +0.586 |
Neg logit contributions | |
Franch | -0.747 |
tti | -0.708 |
inker | -0.656 |
Maj | -0.656 |
uve | -0.649 |
Token | How |
Token ID | 1374 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Franch | +1.083 |
tti | +1.031 |
Maj | +0.973 |
inker | +0.956 |
uve | +0.949 |
Neg logit contributions | |
20439 | -0.991 |
Sexual | -0.788 |
Clo | -0.724 |
isolation | -0.717 |
sheltered | -0.717 |
Token | about |
Token ID | 546 |
Feature activation | -6.30e+00 |
Pos logit contributions | |
20439 | +0.314 |
Sexual | +0.257 |
Clo | +0.241 |
isolation | +0.238 |
sheltered | +0.237 |
Neg logit contributions | |
Franch | -0.291 |
tti | -0.275 |
inker | -0.255 |
Maj | -0.254 |
rieg | -0.253 |
Token | after |
Token ID | 706 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
20439 | +4.854 |
Sexual | +3.959 |
isolation | +3.878 |
Clo | +3.863 |
padded | +3.748 |
Neg logit contributions | |
Franch | -4.903 |
tti | -4.655 |
inker | -4.344 |
uve | -4.320 |
rieg | -4.305 |
Token | a |
Token ID | 257 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
20439 | +0.114 |
Sexual | +0.093 |
Clo | +0.087 |
isolation | +0.085 |
sheltered | +0.085 |
Neg logit contributions | |
Franch | -0.111 |
tti | -0.106 |
Maj | -0.099 |
inker | -0.098 |
uve | -0.097 |
Token | year |
Token ID | 614 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
20439 | +0.591 |
Sexual | +0.472 |
Clo | +0.440 |
isolation | +0.433 |
sheltered | +0.430 |
Neg logit contributions | |
Franch | -0.669 |
tti | -0.640 |
Maj | -0.596 |
inker | -0.596 |
uve | -0.592 |
Token | ? |
Token ID | 30 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
Franch | +0.585 |
tti | +0.557 |
Maj | +0.520 |
inker | +0.516 |
uve | +0.511 |
Neg logit contributions | |
20439 | -0.600 |
Sexual | -0.485 |
Clo | -0.452 |
isolation | -0.445 |
sheltered | -0.443 |
Token | How |
Token ID | 1374 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
Franch | +0.742 |
tti | +0.708 |
Maj | +0.666 |
inker | +0.657 |
uve | +0.652 |
Neg logit contributions | |
20439 | -0.667 |
Sexual | -0.530 |
Clo | -0.488 |
isolation | -0.482 |
sheltered | -0.481 |
Token | sway |
Token ID | 20009 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
20439 | +1.219 |
Sexual | +1.000 |
Clo | +0.947 |
sheltered | +0.945 |
isolation | +0.943 |
Neg logit contributions | |
Franch | -1.189 |
tti | -1.126 |
Maj | -1.055 |
inker | -1.050 |
uve | -1.049 |
Token | policy |
Token ID | 2450 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
20439 | +0.204 |
Sexual | +0.164 |
Clo | +0.153 |
isolation | +0.151 |
sheltered | +0.150 |
Neg logit contributions | |
Franch | -0.211 |
tti | -0.202 |
Maj | -0.188 |
inker | -0.187 |
uve | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Franch | +0.882 |
tti | +0.838 |
Maj | +0.778 |
inker | +0.768 |
uve | +0.762 |
Neg logit contributions | |
20439 | -1.065 |
Sexual | -0.871 |
Clo | -0.815 |
ileaks | -0.801 |
sheltered | -0.797 |
Token | But |
Token ID | 887 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
20439 | +0.105 |
Sexual | +0.084 |
Clo | +0.078 |
isolation | +0.077 |
sheltered | +0.077 |
Neg logit contributions | |
Franch | -0.109 |
tti | -0.104 |
Maj | -0.097 |
inker | -0.096 |
uve | -0.095 |
Token | how |
Token ID | 703 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
Franch | +0.258 |
tti | +0.247 |
Maj | +0.232 |
inker | +0.230 |
uve | +0.227 |
Neg logit contributions | |
20439 | -0.228 |
Sexual | -0.180 |
Clo | -0.165 |
isolation | -0.162 |
sheltered | -0.162 |
Token | about |
Token ID | 546 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
Franch | +0.030 |
tti | +0.029 |
Maj | +0.027 |
inker | +0.027 |
uve | +0.027 |
Neg logit contributions | |
20439 | -0.028 |
Sexual | -0.022 |
Clo | -0.021 |
isolation | -0.020 |
sheltered | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
20439 | +4.535 |
Sexual | +3.756 |
isolation | +3.627 |
Clo | +3.584 |
sheltered | +3.546 |
Neg logit contributions | |
Franch | -5.103 |
tti | -4.904 |
uve | -4.618 |
rieg | -4.592 |
inker | -4.535 |
Token | nice |
Token ID | 3621 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
20439 | +1.210 |
Sexual | +0.985 |
Clo | +0.921 |
isolation | +0.907 |
sheltered | +0.907 |
Neg logit contributions | |
Franch | -1.213 |
tti | -1.159 |
Maj | -1.076 |
inker | -1.069 |
uve | -1.068 |
Token | bump |
Token ID | 13852 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Franch | +1.151 |
tti | +1.101 |
Maj | +1.032 |
inker | +1.025 |
uve | +1.008 |
Neg logit contributions | |
20439 | -1.134 |
Sexual | -0.903 |
Clo | -0.835 |
isolation | -0.818 |
ileaks | -0.818 |
Token | in |
Token ID | 287 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
20439 | +0.979 |
Sexual | +0.793 |
Clo | +0.739 |
isolation | +0.728 |
sheltered | +0.726 |
Neg logit contributions | |
Franch | -0.954 |
tti | -0.907 |
Maj | -0.847 |
inker | -0.840 |
uve | -0.834 |
Token | standardized |
Token ID | 25713 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Franch | +0.804 |
tti | +0.767 |
Maj | +0.721 |
inker | +0.711 |
uve | +0.705 |
Neg logit contributions | |
20439 | -0.803 |
Sexual | -0.643 |
Clo | -0.597 |
ileaks | -0.583 |
IRC | -0.582 |
Token | reading |
Token ID | 3555 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
20439 | +1.734 |
Sexual | +1.385 |
Clo | +1.285 |
isolation | +1.264 |
sheltered | +1.259 |
Neg logit contributions | |
Franch | -1.897 |
tti | -1.812 |
Maj | -1.694 |
inker | -1.686 |
rieg | -1.671 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
20439 | +3.171 |
Sexual | +2.555 |
Clo | +2.392 |
sheltered | +2.333 |
isolation | +2.330 |
Neg logit contributions | |
Franch | -3.631 |
tti | -3.478 |
inker | -3.262 |
uve | -3.201 |
Maj | -3.168 |
Token | main |
Token ID | 1388 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
20439 | +1.164 |
Sexual | +0.962 |
Clo | +0.904 |
isolation | +0.892 |
sheltered | +0.889 |
Neg logit contributions | |
Franch | -0.941 |
tti | -0.893 |
Maj | -0.822 |
inker | -0.818 |
uve | -0.810 |
Token | story |
Token ID | 1621 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
20439 | +1.707 |
Sexual | +1.417 |
Clo | +1.334 |
isolation | +1.317 |
sheltered | +1.312 |
Neg logit contributions | |
Franch | -1.273 |
tti | -1.204 |
Maj | -1.110 |
inker | -1.100 |
uve | -1.088 |
Token | Please |
Token ID | 4222 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
20439 | +1.801 |
Sexual | +1.492 |
Clo | +1.404 |
isolation | +1.382 |
sheltered | +1.376 |
Neg logit contributions | |
Franch | -1.433 |
tti | -1.363 |
inker | -1.253 |
Maj | -1.253 |
uve | -1.237 |
Token | verify |
Token ID | 11767 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
20439 | +2.811 |
Sexual | +2.191 |
Clo | +2.011 |
isolation | +1.975 |
sheltered | +1.965 |
Neg logit contributions | |
Franch | -3.669 |
tti | -3.519 |
Maj | -3.306 |
inker | -3.287 |
uve | -3.269 |
Token | you |
Token ID | 345 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
20439 | +4.102 |
Sexual | +3.187 |
Clo | +2.965 |
sheltered | +2.864 |
isolation | +2.857 |
Neg logit contributions | |
Franch | -5.822 |
tti | -5.560 |
inker | -5.251 |
Maj | -5.205 |
uve | -5.178 |
Token | 're |
Token ID | 821 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
20439 | +0.756 |
Sexual | +0.621 |
Clo | +0.580 |
isolation | +0.574 |
ileaks | +0.571 |
Neg logit contributions | |
Franch | -0.615 |
tti | -0.587 |
Maj | -0.546 |
rieg | -0.534 |
inker | -0.532 |
Token | not |
Token ID | 407 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
20439 | +0.668 |
Sexual | +0.554 |
Clo | +0.520 |
ileaks | +0.515 |
isolation | +0.513 |
Neg logit contributions | |
Franch | -0.504 |
tti | -0.475 |
Maj | -0.444 |
inker | -0.432 |
rieg | -0.430 |
Token | a |
Token ID | 257 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
20439 | +0.290 |
Sexual | +0.239 |
Clo | +0.224 |
isolation | +0.221 |
sheltered | +0.220 |
Neg logit contributions | |
Franch | -0.237 |
tti | -0.225 |
Maj | -0.208 |
inker | -0.206 |
uve | -0.204 |
Token | robot |
Token ID | 9379 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
20439 | +0.412 |
Sexual | +0.312 |
Clo | +0.282 |
isolation | +0.276 |
sheltered | +0.273 |
Neg logit contributions | |
Franch | -0.619 |
tti | -0.595 |
Maj | -0.563 |
inker | -0.559 |
uve | -0.554 |
Token | IFF |
Token ID | 29267 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
20439 | +1.809 |
Sexual | +1.517 |
Clo | +1.421 |
isolation | +1.415 |
Hague | +1.402 |
Neg logit contributions | |
Franch | -1.176 |
tti | -1.092 |
Maj | -0.985 |
uve | -0.984 |
rieg | -0.974 |
Token | original |
Token ID | 2656 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
20439 | +2.660 |
Sexual | +2.250 |
Clo | +2.161 |
isolation | +2.109 |
padded | +2.098 |
Neg logit contributions | |
Franch | -2.079 |
tti | -2.015 |
inker | -1.830 |
uve | -1.785 |
rieg | -1.773 |
Token | image |
Token ID | 2939 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
20439 | +2.388 |
Sexual | +1.979 |
Clo | +1.871 |
isolation | +1.848 |
padded | +1.825 |
Neg logit contributions | |
Franch | -1.931 |
tti | -1.823 |
inker | -1.664 |
Maj | -1.661 |
rieg | -1.656 |
Token | Download |
Token ID | 10472 |
Feature activation | -5.68e+00 |
Pos logit contributions | |
20439 | +0.822 |
Sexual | +0.586 |
Clo | +0.521 |
isolation | +0.486 |
Hague | +0.475 |
Neg logit contributions | |
Franch | -1.745 |
tti | -1.706 |
uve | -1.612 |
inker | -1.611 |
rieg | -1.598 |
Token | : |
Token ID | 25 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
20439 | +4.362 |
Sexual | +3.476 |
Clo | +3.294 |
padded | +3.157 |
isolation | +3.154 |
Neg logit contributions | |
Franch | -4.768 |
tti | -4.544 |
inker | -4.274 |
uve | -4.230 |
rieg | -4.151 |
Token | Figure |
Token ID | 11291 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
20439 | +1.812 |
Sexual | +1.489 |
Clo | +1.407 |
isolation | +1.373 |
sheltered | +1.364 |
Neg logit contributions | |
Franch | -1.550 |
tti | -1.479 |
uve | -1.367 |
inker | -1.361 |
rieg | -1.350 |
Token | 1 |
Token ID | 352 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
20439 | +4.747 |
Sexual | +3.949 |
isolation | +3.749 |
Clo | +3.713 |
apes | +3.640 |
Neg logit contributions | |
Franch | -4.738 |
tti | -4.631 |
inker | -4.400 |
rieg | -4.334 |
uve | -4.301 |
Token | . |
Token ID | 13 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
20439 | +3.369 |
Sexual | +2.817 |
Clo | +2.675 |
isolation | +2.604 |
apes | +2.559 |
Neg logit contributions | |
Franch | -3.145 |
tti | -3.010 |
inker | -2.805 |
rieg | -2.800 |
uve | -2.786 |
Token | Maze |
Token ID | 33412 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
20439 | +2.183 |
Sexual | +1.787 |
Clo | +1.687 |
isolation | +1.639 |
sheltered | +1.615 |
Neg logit contributions | |
Franch | -2.128 |
tti | -2.043 |
inker | -1.905 |
rieg | -1.889 |
uve | -1.888 |
Token | and |
Token ID | 290 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
20439 | +0.438 |
Sexual | +0.370 |
Clo | +0.351 |
isolation | +0.347 |
sheltered | +0.345 |
Neg logit contributions | |
Franch | -0.270 |
tti | -0.254 |
Maj | -0.231 |
inker | -0.229 |
uve | -0.226 |
Token | task |
Token ID | 4876 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
20439 | +0.665 |
Sexual | +0.535 |
Clo | +0.497 |
isolation | +0.488 |
sheltered | +0.487 |
Neg logit contributions | |
Franch | -0.666 |
tti | -0.636 |
Maj | -0.594 |
inker | -0.588 |
uve | -0.583 |
Token | reading |
Token ID | 3555 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
20439 | +1.580 |
Sexual | +1.261 |
Clo | +1.171 |
isolation | +1.152 |
sheltered | +1.147 |
Neg logit contributions | |
Franch | -1.724 |
tti | -1.647 |
Maj | -1.539 |
inker | -1.532 |
rieg | -1.518 |
Token | the |
Token ID | 262 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
20439 | +3.610 |
Sexual | +2.917 |
Clo | +2.732 |
sheltered | +2.642 |
isolation | +2.642 |
Neg logit contributions | |
Franch | -4.107 |
tti | -3.919 |
inker | -3.691 |
uve | -3.641 |
rieg | -3.599 |
Token | main |
Token ID | 1388 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
20439 | +1.365 |
Sexual | +1.129 |
Clo | +1.061 |
isolation | +1.047 |
sheltered | +1.042 |
Neg logit contributions | |
Franch | -1.073 |
tti | -1.017 |
Maj | -0.940 |
inker | -0.931 |
uve | -0.922 |
Token | story |
Token ID | 1621 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
20439 | +1.704 |
Sexual | +1.412 |
Clo | +1.331 |
isolation | +1.313 |
sheltered | +1.307 |
Neg logit contributions | |
Franch | -1.228 |
tti | -1.161 |
Maj | -1.075 |
inker | -1.061 |
rieg | -1.051 |
Token | Please |
Token ID | 4222 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
20439 | +2.042 |
Sexual | +1.692 |
Clo | +1.593 |
isolation | +1.562 |
sheltered | +1.556 |
Neg logit contributions | |
Franch | -1.662 |
tti | -1.588 |
inker | -1.466 |
Maj | -1.453 |
uve | -1.446 |
Token | verify |
Token ID | 11767 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
20439 | +2.663 |
Sexual | +2.069 |
Clo | +1.898 |
isolation | +1.865 |
sheltered | +1.857 |
Neg logit contributions | |
Franch | -3.624 |
tti | -3.477 |
Maj | -3.258 |
inker | -3.248 |
uve | -3.242 |
Token | you |
Token ID | 345 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
20439 | +4.099 |
Sexual | +3.189 |
Clo | +2.962 |
sheltered | +2.854 |
isolation | +2.853 |
Neg logit contributions | |
Franch | -5.805 |
tti | -5.538 |
inker | -5.226 |
Maj | -5.185 |
uve | -5.165 |
Token | 're |
Token ID | 821 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
20439 | +0.994 |
Sexual | +0.816 |
Clo | +0.761 |
isolation | +0.753 |
ileaks | +0.750 |
Neg logit contributions | |
Franch | -0.838 |
tti | -0.799 |
Maj | -0.744 |
inker | -0.729 |
rieg | -0.727 |
Token | not |
Token ID | 407 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
20439 | +0.797 |
Sexual | +0.661 |
Clo | +0.619 |
ileaks | +0.613 |
isolation | +0.612 |
Neg logit contributions | |
Franch | -0.613 |
tti | -0.579 |
Maj | -0.540 |
inker | -0.528 |
rieg | -0.524 |
Token | a |
Token ID | 257 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
20439 | +0.352 |
Sexual | +0.290 |
Clo | +0.272 |
isolation | +0.268 |
sheltered | +0.267 |
Neg logit contributions | |
Franch | -0.288 |
tti | -0.273 |
Maj | -0.253 |
inker | -0.251 |
uve | -0.249 |
Token | robot |
Token ID | 9379 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
20439 | +0.689 |
Sexual | +0.520 |
Clo | +0.471 |
isolation | +0.461 |
sheltered | +0.457 |
Neg logit contributions | |
Franch | -1.063 |
tti | -1.023 |
Maj | -0.967 |
inker | -0.961 |
uve | -0.955 |
Token | in |
Token ID | 287 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Franch | +0.361 |
tti | +0.343 |
Maj | +0.319 |
inker | +0.317 |
uve | +0.314 |
Neg logit contributions | |
20439 | -0.390 |
Sexual | -0.318 |
Clo | -0.297 |
isolation | -0.293 |
sheltered | -0.291 |
Token | awe |
Token ID | 25030 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Franch | +0.142 |
tti | +0.135 |
Maj | +0.125 |
inker | +0.125 |
uve | +0.124 |
Neg logit contributions | |
20439 | -0.154 |
Sexual | -0.125 |
Clo | -0.117 |
isolation | -0.116 |
sheltered | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Franch | +2.060 |
tti | +1.969 |
Maj | +1.835 |
inker | +1.800 |
uve | +1.789 |
Neg logit contributions | |
20439 | -2.564 |
Sexual | -2.106 |
Clo | -1.971 |
sheltered | -1.947 |
isolation | -1.946 |
Token | But |
Token ID | 887 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
20439 | +0.233 |
Sexual | +0.187 |
Clo | +0.174 |
isolation | +0.171 |
sheltered | +0.170 |
Neg logit contributions | |
Franch | -0.245 |
tti | -0.234 |
Maj | -0.219 |
inker | -0.218 |
uve | -0.216 |
Token | how |
Token ID | 703 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Franch | +0.669 |
tti | +0.638 |
Maj | +0.597 |
inker | +0.592 |
uve | +0.586 |
Neg logit contributions | |
20439 | -0.661 |
Sexual | -0.532 |
Clo | -0.493 |
isolation | -0.486 |
sheltered | -0.484 |
Token | about |
Token ID | 546 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
20439 | +0.101 |
Sexual | +0.081 |
Clo | +0.076 |
isolation | +0.074 |
sheltered | +0.074 |
Neg logit contributions | |
Franch | -0.110 |
tti | -0.104 |
Maj | -0.097 |
inker | -0.097 |
rieg | -0.096 |
Token | after |
Token ID | 706 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
20439 | +4.486 |
Sexual | +3.615 |
isolation | +3.572 |
Clo | +3.543 |
padded | +3.439 |
Neg logit contributions | |
Franch | -5.054 |
tti | -4.852 |
inker | -4.558 |
uve | -4.540 |
rieg | -4.528 |
Token | the |
Token ID | 262 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
20439 | +0.287 |
Sexual | +0.231 |
Clo | +0.218 |
isolation | +0.215 |
sheltered | +0.211 |
Neg logit contributions | |
Franch | -0.299 |
tti | -0.285 |
Maj | -0.266 |
inker | -0.265 |
uve | -0.263 |
Token | presentation |
Token ID | 10470 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
20439 | +0.061 |
Sexual | +0.050 |
Clo | +0.048 |
isolation | +0.047 |
sheltered | +0.047 |
Neg logit contributions | |
Franch | -0.051 |
tti | -0.049 |
Maj | -0.045 |
inker | -0.045 |
uve | -0.044 |
Token | ? |
Token ID | 30 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
20439 | +0.528 |
Sexual | +0.425 |
Clo | +0.397 |
isolation | +0.391 |
sheltered | +0.387 |
Neg logit contributions | |
Franch | -0.547 |
tti | -0.521 |
Maj | -0.485 |
inker | -0.484 |
uve | -0.479 |
Token | How |
Token ID | 1374 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Franch | +1.362 |
tti | +1.298 |
Maj | +1.227 |
inker | +1.203 |
uve | +1.195 |
Neg logit contributions | |
20439 | -1.239 |
Sexual | -0.982 |
Clo | -0.898 |
sheltered | -0.891 |
isolation | -0.890 |
Token | reading |
Token ID | 3555 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
20439 | +1.515 |
Sexual | +1.212 |
Clo | +1.124 |
isolation | +1.106 |
sheltered | +1.100 |
Neg logit contributions | |
Franch | -1.614 |
tti | -1.542 |
Maj | -1.444 |
inker | -1.432 |
uve | -1.421 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
20439 | +3.139 |
Sexual | +2.539 |
Clo | +2.370 |
isolation | +2.308 |
sheltered | +2.303 |
Neg logit contributions | |
Franch | -3.427 |
tti | -3.268 |
inker | -3.067 |
uve | -3.022 |
Maj | -2.999 |
Token | main |
Token ID | 1388 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
20439 | +1.046 |
Sexual | +0.865 |
Clo | +0.812 |
isolation | +0.801 |
ileaks | +0.798 |
Neg logit contributions | |
Franch | -0.793 |
tti | -0.750 |
Maj | -0.698 |
inker | -0.686 |
uve | -0.680 |
Token | story |
Token ID | 1621 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
20439 | +1.818 |
Sexual | +1.506 |
Clo | +1.419 |
isolation | +1.401 |
sheltered | +1.394 |
Neg logit contributions | |
Franch | -1.296 |
tti | -1.225 |
Maj | -1.136 |
inker | -1.119 |
rieg | -1.109 |
Token | Please |
Token ID | 4222 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
20439 | +1.702 |
Sexual | +1.409 |
Clo | +1.325 |
isolation | +1.307 |
sheltered | +1.301 |
Neg logit contributions | |
Franch | -1.332 |
tti | -1.263 |
Maj | -1.165 |
inker | -1.157 |
uve | -1.145 |
Token | verify |
Token ID | 11767 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
20439 | +2.705 |
Sexual | +2.104 |
Clo | +1.933 |
isolation | +1.897 |
sheltered | +1.889 |
Neg logit contributions | |
Franch | -3.608 |
tti | -3.460 |
Maj | -3.247 |
inker | -3.232 |
uve | -3.220 |
Token | you |
Token ID | 345 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
20439 | +4.060 |
Sexual | +3.161 |
Clo | +2.939 |
isolation | +2.844 |
sheltered | +2.840 |
Neg logit contributions | |
Franch | -5.635 |
tti | -5.380 |
inker | -5.076 |
Maj | -5.037 |
uve | -5.013 |
Token | 're |
Token ID | 821 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
20439 | +0.687 |
Sexual | +0.565 |
Clo | +0.525 |
isolation | +0.521 |
ileaks | +0.519 |
Neg logit contributions | |
Franch | -0.554 |
tti | -0.529 |
Maj | -0.494 |
rieg | -0.481 |
inker | -0.480 |
Token | not |
Token ID | 407 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
20439 | +0.677 |
Sexual | +0.561 |
Clo | +0.525 |
ileaks | +0.521 |
isolation | +0.519 |
Neg logit contributions | |
Franch | -0.514 |
tti | -0.485 |
Maj | -0.453 |
inker | -0.441 |
rieg | -0.439 |
Token | a |
Token ID | 257 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
20439 | +0.292 |
Sexual | +0.240 |
Clo | +0.225 |
isolation | +0.222 |
sheltered | +0.221 |
Neg logit contributions | |
Franch | -0.237 |
tti | -0.225 |
Maj | -0.208 |
inker | -0.206 |
uve | -0.204 |
Token | robot |
Token ID | 9379 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
20439 | +0.471 |
Sexual | +0.357 |
Clo | +0.322 |
isolation | +0.316 |
sheltered | +0.313 |
Neg logit contributions | |
Franch | -0.710 |
tti | -0.683 |
Maj | -0.646 |
inker | -0.641 |
uve | -0.636 |
Token | work |
Token ID | 670 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Franch | +0.035 |
tti | +0.033 |
Maj | +0.031 |
inker | +0.031 |
uve | +0.031 |
Neg logit contributions | |
20439 | -0.036 |
Sexual | -0.029 |
Clo | -0.027 |
isolation | -0.027 |
sheltered | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Franch | +0.103 |
tti | +0.098 |
Maj | +0.091 |
inker | +0.090 |
rieg | +0.089 |
Neg logit contributions | |
20439 | -0.126 |
Sexual | -0.104 |
Clo | -0.097 |
isolation | -0.095 |
sheltered | -0.095 |
Token | � |
Token ID | 564 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
20439 | +0.762 |
Sexual | +0.600 |
Clo | +0.556 |
isolation | +0.544 |
sheltered | +0.540 |
Neg logit contributions | |
Franch | -0.907 |
tti | -0.869 |
Maj | -0.815 |
inker | -0.812 |
uve | -0.806 |
Token | � |
Token ID | 250 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
20439 | +0.299 |
Sexual | +0.240 |
Clo | +0.223 |
isolation | +0.220 |
sheltered | +0.219 |
Neg logit contributions | |
Franch | -0.309 |
tti | -0.297 |
Maj | -0.277 |
inker | -0.274 |
rieg | -0.272 |
Token | What |
Token ID | 2061 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
20439 | +0.784 |
Sexual | +0.631 |
Clo | +0.579 |
isolation | +0.567 |
IRC | +0.564 |
Neg logit contributions | |
Franch | -0.875 |
tti | -0.832 |
Maj | -0.780 |
inker | -0.774 |
uve | -0.769 |
Token | kind |
Token ID | 1611 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
20439 | +0.709 |
Sexual | +0.568 |
Clo | +0.529 |
isolation | +0.520 |
sheltered | +0.516 |
Neg logit contributions | |
Franch | -0.784 |
tti | -0.747 |
Maj | -0.699 |
inker | -0.699 |
uve | -0.691 |
Token | of |
Token ID | 286 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
20439 | +5.291 |
Sexual | +4.463 |
Clo | +4.223 |
sheltered | +4.136 |
isolation | +4.132 |
Neg logit contributions | |
Franch | -4.274 |
tti | -3.918 |
inker | -3.614 |
uve | -3.611 |
Maj | -3.582 |
Token | a |
Token ID | 257 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
20439 | +2.205 |
Sexual | +1.814 |
isolation | +1.718 |
Clo | +1.710 |
sheltered | +1.690 |
Neg logit contributions | |
Franch | -2.162 |
tti | -2.054 |
inker | -1.916 |
rieg | -1.901 |
uve | -1.896 |
Token | person |
Token ID | 1048 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
20439 | +2.609 |
Sexual | +2.130 |
Clo | +1.997 |
isolation | +1.996 |
sheltered | +1.989 |
Neg logit contributions | |
Franch | -2.904 |
tti | -2.779 |
uve | -2.573 |
rieg | -2.568 |
Maj | -2.565 |
Token | is |
Token ID | 318 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
20439 | +0.412 |
Sexual | +0.328 |
Clo | +0.302 |
isolation | +0.298 |
sheltered | +0.296 |
Neg logit contributions | |
Franch | -0.447 |
tti | -0.428 |
Maj | -0.402 |
inker | -0.397 |
uve | -0.394 |
Token | Y |
Token ID | 575 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
20439 | +0.508 |
Sexual | +0.402 |
Clo | +0.371 |
isolation | +0.365 |
sheltered | +0.363 |
Neg logit contributions | |
Franch | -0.588 |
tti | -0.562 |
Maj | -0.528 |
inker | -0.524 |
uve | -0.520 |
Token | fourth |
Token ID | 5544 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
20439 | +0.678 |
Sexual | +0.559 |
Clo | +0.527 |
isolation | +0.521 |
sheltered | +0.515 |
Neg logit contributions | |
Franch | -0.611 |
tti | -0.584 |
inker | -0.540 |
Maj | -0.536 |
rieg | -0.535 |
Token | quarter |
Token ID | 3860 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
20439 | +0.821 |
Sexual | +0.668 |
Clo | +0.627 |
isolation | +0.621 |
padded | +0.614 |
Neg logit contributions | |
Franch | -0.849 |
tti | -0.813 |
inker | -0.749 |
Maj | -0.749 |
uve | -0.743 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
20439 | +0.132 |
Sexual | +0.109 |
Clo | +0.102 |
isolation | +0.101 |
sheltered | +0.100 |
Neg logit contributions | |
Franch | -0.107 |
tti | -0.102 |
Maj | -0.094 |
inker | -0.093 |
uve | -0.092 |
Token | But |
Token ID | 887 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
Franch | +0.301 |
tti | +0.288 |
Maj | +0.268 |
inker | +0.267 |
uve | +0.265 |
Neg logit contributions | |
20439 | -0.298 |
Sexual | -0.240 |
Clo | -0.224 |
isolation | -0.219 |
sheltered | -0.218 |
Token | after |
Token ID | 706 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Franch | +0.422 |
tti | +0.403 |
Maj | +0.374 |
inker | +0.373 |
uve | +0.371 |
Neg logit contributions | |
20439 | -0.438 |
Sexual | -0.356 |
Clo | -0.334 |
isolation | -0.328 |
sheltered | -0.327 |
Token | Washington |
Token ID | 2669 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
20439 | +0.799 |
Sexual | +0.647 |
Clo | +0.613 |
isolation | +0.602 |
sheltered | +0.597 |
Neg logit contributions | |
Franch | -0.822 |
tti | -0.791 |
inker | -0.733 |
Maj | -0.732 |
rieg | -0.731 |
Token | kicker |
Token ID | 38297 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Franch | +2.675 |
tti | +2.530 |
Maj | +2.394 |
inker | +2.325 |
uve | +2.324 |
Neg logit contributions | |
20439 | -2.608 |
Sexual | -2.053 |
ileaks | -1.862 |
Clo | -1.862 |
IRC | -1.808 |
Token | Joe |
Token ID | 5689 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
20439 | +0.294 |
Sexual | +0.240 |
Clo | +0.225 |
isolation | +0.222 |
sheltered | +0.220 |
Neg logit contributions | |
Franch | -0.281 |
tti | -0.269 |
Maj | -0.249 |
inker | -0.249 |
uve | -0.247 |
Token | Agu |
Token ID | 33118 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Franch | +0.575 |
tti | +0.548 |
Maj | +0.511 |
inker | +0.508 |
uve | +0.504 |
Neg logit contributions | |
20439 | -0.587 |
Sexual | -0.475 |
Clo | -0.443 |
isolation | -0.436 |
sheltered | -0.434 |
Token | ir |
Token ID | 343 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
Franch | +1.143 |
tti | +1.094 |
Maj | +1.016 |
inker | +1.006 |
uve | +0.993 |
Neg logit contributions | |
20439 | -1.300 |
Sexual | -1.053 |
Clo | -0.982 |
isolation | -0.967 |
sheltered | -0.959 |
Token | re |
Token ID | 260 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
20439 | +0.493 |
Sexual | +0.386 |
isolation | +0.348 |
Clo | +0.346 |
sheltered | +0.342 |
Neg logit contributions | |
Franch | -0.694 |
tti | -0.662 |
inker | -0.628 |
Maj | -0.627 |
uve | -0.617 |
Token | and |
Token ID | 290 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
20439 | +0.125 |
Sexual | +0.103 |
Clo | +0.096 |
ileaks | +0.095 |
isolation | +0.095 |
Neg logit contributions | |
Franch | -0.097 |
tti | -0.092 |
Maj | -0.086 |
inker | -0.083 |
rieg | -0.083 |
Token | parse |
Token ID | 21136 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
20439 | +0.465 |
Sexual | +0.391 |
Clo | +0.370 |
isolation | +0.366 |
sheltered | +0.364 |
Neg logit contributions | |
Franch | -0.299 |
tti | -0.280 |
Maj | -0.256 |
inker | -0.254 |
uve | -0.251 |
Token | the |
Token ID | 262 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
Franch | +0.528 |
tti | +0.504 |
Maj | +0.472 |
rieg | +0.459 |
inker | +0.459 |
Neg logit contributions | |
20439 | -0.641 |
Sexual | -0.521 |
Clo | -0.481 |
ileaks | -0.477 |
aeus | -0.477 |
Token | arguments |
Token ID | 7159 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Franch | +0.009 |
tti | +0.009 |
Maj | +0.008 |
inker | +0.008 |
rieg | +0.008 |
Neg logit contributions | |
20439 | -0.012 |
Sexual | -0.010 |
Clo | -0.010 |
ileaks | -0.009 |
isolation | -0.009 |
Token | ap |
Token ID | 2471 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Franch | +1.062 |
tti | +1.023 |
Maj | +0.975 |
inker | +0.966 |
uve | +0.958 |
Neg logit contributions | |
20439 | -0.627 |
Sexual | -0.466 |
Clo | -0.412 |
sheltered | -0.397 |
isolation | -0.396 |
Token | = |
Token ID | 796 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
Franch | +0.301 |
tti | +0.286 |
Maj | +0.262 |
inker | +0.259 |
rieg | +0.256 |
Neg logit contributions | |
20439 | -0.418 |
Sexual | -0.347 |
Clo | -0.328 |
isolation | -0.325 |
sheltered | -0.324 |
Token | arg |
Token ID | 1822 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
Franch | +1.470 |
tti | +1.433 |
Maj | +1.277 |
inker | +1.158 |
rieg | +1.141 |
Neg logit contributions | |
20439 | -4.455 |
Sexual | -3.853 |
Clo | -3.612 |
ileaks | -3.612 |
IRC | -3.564 |
Token | parse |
Token ID | 29572 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
tti | +1.110 |
Franch | +1.101 |
inker | +0.950 |
uve | +0.901 |
rieg | +0.883 |
Neg logit contributions | |
20439 | -4.173 |
Sexual | -3.642 |
Clo | -3.498 |
Hague | -3.472 |
isolation | -3.467 |
Token | . |
Token ID | 13 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
Franch | +0.167 |
tti | +0.159 |
Maj | +0.148 |
inker | +0.143 |
rieg | +0.143 |
Neg logit contributions | |
20439 | -0.236 |
Sexual | -0.195 |
Clo | -0.183 |
isolation | -0.183 |
sheltered | -0.182 |
Token | Arg |
Token ID | 28100 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
Franch | +0.438 |
tti | +0.423 |
Maj | +0.395 |
inker | +0.389 |
rieg | +0.385 |
Neg logit contributions | |
20439 | -0.450 |
Sexual | -0.357 |
Clo | -0.340 |
sheltered | -0.338 |
isolation | -0.337 |
Token | ument |
Token ID | 1713 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Franch | +0.038 |
tti | +0.035 |
Maj | +0.031 |
inker | +0.031 |
uve | +0.030 |
Neg logit contributions | |
20439 | -0.099 |
Sexual | -0.085 |
Clo | -0.082 |
isolation | -0.081 |
sheltered | -0.081 |
Token | time |
Token ID | 640 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
20439 | +0.392 |
Sexual | +0.311 |
Clo | +0.288 |
isolation | +0.285 |
sheltered | +0.282 |
Neg logit contributions | |
Franch | -0.451 |
tti | -0.432 |
Maj | -0.403 |
inker | -0.402 |
uve | -0.399 |
Token | . |
Token ID | 13 |
Feature activation | -9.78e-03 |
Pos logit contributions | |
20439 | +0.612 |
Sexual | +0.502 |
Clo | +0.471 |
isolation | +0.465 |
sheltered | +0.463 |
Neg logit contributions | |
Franch | -0.526 |
tti | -0.499 |
Maj | -0.463 |
inker | -0.460 |
uve | -0.456 |
Token | When |
Token ID | 1649 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
20439 | +0.007 |
Sexual | +0.006 |
Clo | +0.005 |
isolation | +0.005 |
sheltered | +0.005 |
Neg logit contributions | |
Franch | -0.008 |
tti | -0.008 |
Maj | -0.008 |
inker | -0.008 |
uve | -0.007 |
Token | I |
Token ID | 314 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
20439 | +0.462 |
Sexual | +0.358 |
Clo | +0.334 |
isolation | +0.329 |
sheltered | +0.324 |
Neg logit contributions | |
Franch | -0.615 |
tti | -0.593 |
inker | -0.555 |
uve | -0.553 |
Maj | -0.553 |
Token | was |
Token ID | 373 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Franch | +0.734 |
tti | +0.703 |
Maj | +0.659 |
inker | +0.653 |
uve | +0.648 |
Neg logit contributions | |
20439 | -0.644 |
Sexual | -0.511 |
Clo | -0.471 |
isolation | -0.463 |
sheltered | -0.460 |
Token | applying |
Token ID | 11524 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
Franch | +0.567 |
tti | +0.541 |
Maj | +0.505 |
inker | +0.501 |
uve | +0.497 |
Neg logit contributions | |
20439 | -0.562 |
Sexual | -0.453 |
Clo | -0.421 |
isolation | -0.415 |
sheltered | -0.413 |
Token | , |
Token ID | 11 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Franch | +3.142 |
tti | +2.993 |
Maj | +2.832 |
inker | +2.789 |
rieg | +2.760 |
Neg logit contributions | |
20439 | -2.896 |
Sexual | -2.300 |
Clo | -2.097 |
sheltered | -2.072 |
ileaks | -2.065 |
Token | there |
Token ID | 612 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
20439 | +0.191 |
Sexual | +0.149 |
Clo | +0.139 |
isolation | +0.136 |
sheltered | +0.135 |
Neg logit contributions | |
Franch | -0.237 |
tti | -0.228 |
Maj | -0.213 |
inker | -0.213 |
uve | -0.212 |
Token | were |
Token ID | 547 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
20439 | +0.201 |
Sexual | +0.158 |
Clo | +0.145 |
isolation | +0.143 |
sheltered | +0.142 |
Neg logit contributions | |
Franch | -0.245 |
tti | -0.235 |
Maj | -0.221 |
inker | -0.219 |
uve | -0.218 |
Token | really |
Token ID | 1107 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Franch | +0.279 |
tti | +0.266 |
Maj | +0.248 |
inker | +0.247 |
uve | +0.245 |
Neg logit contributions | |
20439 | -0.276 |
Sexual | -0.222 |
Clo | -0.207 |
isolation | -0.204 |
sheltered | -0.203 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
20439 | +0.219 |
Sexual | +0.176 |
Clo | +0.165 |
isolation | +0.164 |
sheltered | +0.162 |
Neg logit contributions | |
Franch | -0.235 |
tti | -0.224 |
inker | -0.208 |
Maj | -0.208 |
uve | -0.207 |
Token | out |
Token ID | 503 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
20439 | +1.492 |
Sexual | +1.191 |
Clo | +1.122 |
isolation | +1.106 |
sheltered | +1.093 |
Neg logit contributions | |
Franch | -1.665 |
tti | -1.603 |
inker | -1.486 |
Maj | -1.481 |
uve | -1.481 |
Token | Jets |
Token ID | 14728 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Franch | +1.065 |
tti | +1.005 |
Maj | +0.946 |
inker | +0.929 |
uve | +0.918 |
Neg logit contributions | |
20439 | -1.144 |
Sexual | -0.929 |
Clo | -0.857 |
ileaks | -0.846 |
isolation | -0.845 |
Token | work |
Token ID | 670 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
Franch | +0.131 |
tti | +0.125 |
Maj | +0.117 |
inker | +0.116 |
uve | +0.115 |
Neg logit contributions | |
20439 | -0.125 |
Sexual | -0.100 |
Clo | -0.093 |
isolation | -0.092 |
sheltered | -0.091 |
Token | horse |
Token ID | 30527 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
20439 | +0.485 |
Sexual | +0.366 |
Clo | +0.332 |
isolation | +0.325 |
sheltered | +0.322 |
Neg logit contributions | |
Franch | -0.743 |
tti | -0.715 |
Maj | -0.676 |
inker | -0.672 |
uve | -0.667 |
Token | Matt |
Token ID | 4705 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
20439 | +1.297 |
Sexual | +1.064 |
Clo | +1.009 |
isolation | +0.993 |
sheltered | +0.985 |
Neg logit contributions | |
Franch | -1.220 |
tti | -1.176 |
inker | -1.084 |
rieg | -1.080 |
Maj | -1.076 |
Token | Fort |
Token ID | 6401 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
Franch | +0.218 |
tti | +0.207 |
Maj | +0.194 |
inker | +0.191 |
uve | +0.190 |
Neg logit contributions | |
20439 | -0.230 |
Sexual | -0.186 |
Clo | -0.173 |
isolation | -0.171 |
sheltered | -0.170 |
Token | e |
Token ID | 68 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
Franch | +2.821 |
tti | +2.745 |
Maj | +2.485 |
uve | +2.470 |
inker | +2.440 |
Neg logit contributions | |
20439 | -3.482 |
Sexual | -2.843 |
ileaks | -2.663 |
Hague | -2.625 |
Clo | -2.621 |
Token | last |
Token ID | 938 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Franch | +0.372 |
tti | +0.354 |
Maj | +0.329 |
inker | +0.327 |
uve | +0.324 |
Neg logit contributions | |
20439 | -0.407 |
Sexual | -0.332 |
Clo | -0.310 |
isolation | -0.306 |
sheltered | -0.304 |
Token | year |
Token ID | 614 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
20439 | +0.477 |
Sexual | +0.394 |
Clo | +0.371 |
isolation | +0.367 |
sheltered | +0.365 |
Neg logit contributions | |
Franch | -0.391 |
tti | -0.371 |
Maj | -0.342 |
inker | -0.341 |
rieg | -0.337 |
Token | with |
Token ID | 351 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Franch | +0.943 |
tti | +0.899 |
Maj | +0.836 |
inker | +0.824 |
uve | +0.818 |
Neg logit contributions | |
20439 | -1.100 |
Sexual | -0.903 |
Clo | -0.843 |
isolation | -0.831 |
ileaks | -0.826 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
20439 | +0.956 |
Sexual | +0.785 |
Clo | +0.739 |
isolation | +0.733 |
sheltered | +0.730 |
Neg logit contributions | |
Franch | -0.888 |
tti | -0.849 |
inker | -0.786 |
rieg | -0.780 |
Maj | -0.779 |
Token | at |
Token ID | 379 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
Franch | +0.642 |
tti | +0.614 |
Maj | +0.573 |
inker | +0.566 |
uve | +0.561 |
Neg logit contributions | |
20439 | -0.666 |
Sexual | -0.537 |
Clo | -0.501 |
isolation | -0.491 |
sheltered | -0.489 |
Token | a |
Token ID | 257 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Franch | +0.470 |
tti | +0.447 |
Maj | +0.416 |
inker | +0.413 |
uve | +0.410 |
Neg logit contributions | |
20439 | -0.504 |
Sexual | -0.410 |
Clo | -0.384 |
isolation | -0.378 |
sheltered | -0.376 |
Token | Mexican |
Token ID | 10816 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
20439 | +1.219 |
Sexual | +0.984 |
Clo | +0.922 |
isolation | +0.906 |
sheltered | +0.905 |
Neg logit contributions | |
Franch | -1.268 |
tti | -1.218 |
inker | -1.128 |
Maj | -1.125 |
uve | -1.124 |
Token | fast |
Token ID | 3049 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
20439 | +0.415 |
Sexual | +0.337 |
Clo | +0.315 |
isolation | +0.311 |
sheltered | +0.308 |
Neg logit contributions | |
Franch | -0.450 |
tti | -0.430 |
inker | -0.399 |
Maj | -0.399 |
rieg | -0.397 |
Token | - |
Token ID | 12 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
Franch | +1.954 |
tti | +1.880 |
Maj | +1.780 |
inker | +1.769 |
uve | +1.757 |
Neg logit contributions | |
20439 | -1.225 |
Sexual | -0.918 |
Clo | -0.829 |
isolation | -0.811 |
sheltered | -0.805 |
Token | food |
Token ID | 19425 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
Franch | +2.337 |
tti | +2.243 |
Maj | +2.104 |
inker | +2.095 |
uve | +2.072 |
Neg logit contributions | |
20439 | -1.885 |
Sexual | -1.460 |
Clo | -1.349 |
isolation | -1.321 |
sheltered | -1.313 |
Token | restaurant |
Token ID | 7072 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
Franch | +2.759 |
tti | +2.603 |
Maj | +2.437 |
inker | +2.394 |
rieg | +2.364 |
Neg logit contributions | |
20439 | -3.344 |
Sexual | -2.712 |
Clo | -2.525 |
ileaks | -2.493 |
isolation | -2.479 |
Token | .) |
Token ID | 2014 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Franch | +0.376 |
tti | +0.359 |
Maj | +0.334 |
inker | +0.331 |
uve | +0.328 |
Neg logit contributions | |
20439 | -0.399 |
Sexual | -0.324 |
Clo | -0.303 |
isolation | -0.298 |
sheltered | -0.297 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
20439 | +1.072 |
Sexual | +0.864 |
Clo | +0.800 |
isolation | +0.779 |
sheltered | +0.775 |
Neg logit contributions | |
Franch | -1.161 |
tti | -1.115 |
inker | -1.039 |
Maj | -1.034 |
uve | -1.032 |
Token |
|
Token ID | 198 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Franch | +0.159 |
tti | +0.152 |
Maj | +0.143 |
inker | +0.140 |
rieg | +0.139 |
Neg logit contributions | |
20439 | -0.163 |
Sexual | -0.130 |
Clo | -0.123 |
isolation | -0.122 |
sheltered | -0.122 |
Token | Cash |
Token ID | 35361 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
20439 | +0.201 |
Sexual | +0.164 |
Clo | +0.150 |
isolation | +0.147 |
IRC | +0.147 |
Neg logit contributions | |
Franch | -0.207 |
tti | -0.197 |
Maj | -0.184 |
inker | -0.182 |
uve | -0.181 |
Token | to |
Token ID | 284 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
20439 | +0.754 |
Sexual | +0.616 |
Clo | +0.576 |
isolation | +0.572 |
sheltered | +0.566 |
Neg logit contributions | |
Franch | -0.695 |
tti | -0.651 |
Maj | -0.613 |
inker | -0.610 |
uve | -0.606 |
Token | life |
Token ID | 1204 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Franch | +0.319 |
tti | +0.302 |
Maj | +0.279 |
inker | +0.278 |
uve | +0.275 |
Neg logit contributions | |
20439 | -0.384 |
Sexual | -0.317 |
Clo | -0.298 |
isolation | -0.295 |
sheltered | -0.293 |
Token | is |
Token ID | 318 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Franch | +0.984 |
tti | +0.941 |
Maj | +0.880 |
inker | +0.867 |
uve | +0.864 |
Neg logit contributions | |
20439 | -0.967 |
Sexual | -0.776 |
Clo | -0.720 |
isolation | -0.706 |
ileaks | -0.704 |
Token | a |
Token ID | 257 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
20439 | +0.833 |
Sexual | +0.680 |
Clo | +0.635 |
isolation | +0.635 |
sheltered | +0.627 |
Neg logit contributions | |
Franch | -0.823 |
tti | -0.779 |
Maj | -0.726 |
inker | -0.726 |
uve | -0.721 |
Token | concession |
Token ID | 33130 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
20439 | +0.019 |
Sexual | +0.015 |
Clo | +0.014 |
isolation | +0.014 |
sheltered | +0.014 |
Neg logit contributions | |
Franch | -0.019 |
tti | -0.018 |
Maj | -0.017 |
inker | -0.017 |
uve | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
Franch | +0.173 |
tti | +0.164 |
Maj | +0.152 |
inker | +0.151 |
uve | +0.150 |
Neg logit contributions | |
20439 | -0.198 |
Sexual | -0.163 |
Clo | -0.153 |
isolation | -0.151 |
sheltered | -0.150 |
Token | power |
Token ID | 1176 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
Franch | +0.371 |
tti | +0.353 |
Maj | +0.326 |
inker | +0.325 |
uve | +0.322 |
Neg logit contributions | |
20439 | -0.427 |
Sexual | -0.351 |
Clo | -0.329 |
isolation | -0.326 |
sheltered | -0.324 |
Token | lessness |
Token ID | 17587 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Franch | +0.543 |
tti | +0.516 |
Maj | +0.479 |
inker | +0.475 |
uve | +0.470 |
Neg logit contributions | |
20439 | -0.631 |
Sexual | -0.517 |
Clo | -0.484 |
isolation | -0.477 |
sheltered | -0.475 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
20439 | +0.103 |
Sexual | +0.084 |
Clo | +0.079 |
isolation | +0.078 |
sheltered | +0.078 |
Neg logit contributions | |
Franch | -0.088 |
tti | -0.083 |
Maj | -0.077 |
inker | -0.077 |
uve | -0.076 |
Token | It |
Token ID | 632 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
Franch | +0.183 |
tti | +0.175 |
Maj | +0.163 |
inker | +0.163 |
uve | +0.161 |
Neg logit contributions | |
20439 | -0.185 |
Sexual | -0.149 |
Clo | -0.139 |
isolation | -0.137 |
sheltered | -0.136 |
Token | is |
Token ID | 318 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
20439 | +0.544 |
Sexual | +0.432 |
Clo | +0.400 |
isolation | +0.394 |
sheltered | +0.392 |
Neg logit contributions | |
Franch | -0.624 |
tti | -0.596 |
Maj | -0.559 |
inker | -0.556 |
uve | -0.551 |
Token | . |
Token ID | 13 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
20439 | +0.887 |
Sexual | +0.728 |
Clo | +0.684 |
isolation | +0.673 |
sheltered | +0.672 |
Neg logit contributions | |
Franch | -0.758 |
tti | -0.718 |
Maj | -0.666 |
inker | -0.663 |
uve | -0.656 |
Token | It |
Token ID | 632 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
20439 | +0.068 |
Sexual | +0.054 |
Clo | +0.051 |
isolation | +0.050 |
sheltered | +0.049 |
Neg logit contributions | |
Franch | -0.070 |
tti | -0.067 |
Maj | -0.062 |
inker | -0.062 |
uve | -0.061 |
Token | was |
Token ID | 373 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
Franch | +0.090 |
tti | +0.087 |
Maj | +0.082 |
inker | +0.081 |
uve | +0.081 |
Neg logit contributions | |
20439 | -0.072 |
Sexual | -0.056 |
Clo | -0.051 |
isolation | -0.050 |
ileaks | -0.049 |
Token | there |
Token ID | 612 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
20439 | +0.302 |
Sexual | +0.244 |
Clo | +0.228 |
isolation | +0.224 |
sheltered | +0.223 |
Neg logit contributions | |
Franch | -0.302 |
tti | -0.288 |
Maj | -0.268 |
inker | -0.267 |
uve | -0.265 |
Token | , |
Token ID | 11 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
Franch | +0.419 |
tti | +0.399 |
Maj | +0.373 |
inker | +0.370 |
uve | +0.366 |
Neg logit contributions | |
20439 | -0.422 |
Sexual | -0.341 |
Clo | -0.317 |
isolation | -0.312 |
sheltered | -0.311 |
Token | on |
Token ID | 319 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
20439 | +0.044 |
Sexual | +0.036 |
Clo | +0.033 |
isolation | +0.033 |
sheltered | +0.033 |
Neg logit contributions | |
Franch | -0.043 |
tti | -0.041 |
Maj | -0.038 |
inker | -0.038 |
uve | -0.037 |
Token | an |
Token ID | 281 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
Franch | +0.235 |
tti | +0.224 |
Maj | +0.209 |
inker | +0.205 |
uve | +0.203 |
Neg logit contributions | |
20439 | -0.263 |
Sexual | -0.215 |
Clo | -0.198 |
isolation | -0.195 |
sheltered | -0.195 |
Token | un |
Token ID | 555 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
Franch | +0.587 |
tti | +0.563 |
Maj | +0.529 |
inker | +0.522 |
uve | +0.517 |
Neg logit contributions | |
20439 | -0.543 |
Sexual | -0.435 |
Clo | -0.400 |
sheltered | -0.391 |
isolation | -0.390 |
Token | season |
Token ID | 6230 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Franch | +1.702 |
tti | +1.639 |
Maj | +1.534 |
inker | +1.530 |
uve | +1.514 |
Neg logit contributions | |
20439 | -1.609 |
Sexual | -1.283 |
Clo | -1.186 |
isolation | -1.171 |
sheltered | -1.157 |
Token | ably |
Token ID | 1346 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
20439 | +0.866 |
Sexual | +0.655 |
Clo | +0.594 |
isolation | +0.581 |
sheltered | +0.577 |
Neg logit contributions | |
Franch | -1.319 |
tti | -1.269 |
Maj | -1.200 |
inker | -1.192 |
uve | -1.184 |
Token | warm |
Token ID | 5814 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Franch | +0.218 |
tti | +0.210 |
Maj | +0.198 |
inker | +0.197 |
uve | +0.196 |
Neg logit contributions | |
20439 | -0.145 |
Sexual | -0.110 |
Clo | -0.100 |
isolation | -0.098 |
sheltered | -0.097 |
Token | � |
Token ID | 447 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
20439 | +0.508 |
Sexual | +0.412 |
Clo | +0.377 |
isolation | +0.370 |
IRC | +0.368 |
Neg logit contributions | |
Franch | -0.545 |
tti | -0.518 |
Maj | -0.486 |
inker | -0.480 |
uve | -0.478 |
Token | � |
Token ID | 250 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
Franch | +0.878 |
tti | +0.842 |
Maj | +0.787 |
inker | +0.781 |
uve | +0.775 |
Neg logit contributions | |
20439 | -0.827 |
Sexual | -0.661 |
Clo | -0.614 |
isolation | -0.605 |
sheltered | -0.601 |
Token | T |
Token ID | 51 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
20439 | +0.040 |
Sexual | +0.032 |
Clo | +0.030 |
isolation | +0.030 |
sheltered | +0.029 |
Neg logit contributions | |
Franch | -0.041 |
tti | -0.039 |
Maj | -0.037 |
inker | -0.036 |
uve | -0.036 |
Token | read |
Token ID | 961 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Franch | +0.294 |
tti | +0.279 |
Maj | +0.260 |
inker | +0.257 |
uve | +0.255 |
Neg logit contributions | |
20439 | -0.328 |
Sexual | -0.268 |
Clo | -0.251 |
isolation | -0.247 |
sheltered | -0.246 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
20439 | +1.236 |
Sexual | +1.033 |
Clo | +0.970 |
ileaks | +0.956 |
sheltered | +0.956 |
Neg logit contributions | |
Franch | -0.878 |
tti | -0.816 |
Maj | -0.755 |
inker | -0.742 |
uve | -0.739 |
Token | � |
Token ID | 251 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Franch | +1.007 |
tti | +0.969 |
Maj | +0.909 |
inker | +0.903 |
uve | +0.895 |
Neg logit contributions | |
20439 | -0.892 |
Sexual | -0.708 |
Clo | -0.654 |
isolation | -0.644 |
sheltered | -0.639 |
Token | Zone |
Token ID | 13035 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Franch | +0.183 |
tti | +0.175 |
Maj | +0.164 |
inker | +0.162 |
uve | +0.161 |
Neg logit contributions | |
20439 | -0.164 |
Sexual | -0.131 |
Clo | -0.121 |
isolation | -0.119 |
sheltered | -0.118 |
Token | Threat |
Token ID | 25238 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Franch | +0.119 |
tti | +0.114 |
Maj | +0.106 |
inker | +0.106 |
uve | +0.105 |
Neg logit contributions | |
20439 | -0.115 |
Sexual | -0.093 |
Clo | -0.086 |
isolation | -0.085 |
sheltered | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
Franch | +0.282 |
tti | +0.270 |
Maj | +0.253 |
inker | +0.251 |
uve | +0.249 |
Neg logit contributions | |
20439 | -0.260 |
Sexual | -0.208 |
Clo | -0.193 |
isolation | -0.190 |
sheltered | -0.189 |
Token |
|
Token ID | 198 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Franch | +0.434 |
tti | +0.415 |
Maj | +0.389 |
inker | +0.380 |
rieg | +0.377 |
Neg logit contributions | |
20439 | -0.471 |
Sexual | -0.376 |
isolation | -0.353 |
Clo | -0.352 |
ileaks | -0.352 |
Token | Sur |
Token ID | 14214 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Franch | +0.207 |
tti | +0.197 |
Maj | +0.185 |
inker | +0.183 |
uve | +0.182 |
Neg logit contributions | |
20439 | -0.197 |
Sexual | -0.159 |
Clo | -0.147 |
isolation | -0.144 |
sheltered | -0.143 |
Token | is |
Token ID | 318 |
Feature activation | +4.83e-03 |
Pos logit contributions | |
20439 | +0.251 |
Sexual | +0.202 |
Clo | +0.188 |
isolation | +0.185 |
sheltered | +0.184 |
Neg logit contributions | |
Franch | -0.258 |
tti | -0.246 |
Maj | -0.230 |
inker | -0.228 |
uve | -0.226 |
Token | yet |
Token ID | 1865 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Franch | +0.004 |
tti | +0.004 |
Maj | +0.004 |
inker | +0.003 |
uve | +0.003 |
Neg logit contributions | |
20439 | -0.004 |
Sexual | -0.003 |
Clo | -0.003 |
isolation | -0.003 |
sheltered | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Franch | +1.379 |
tti | +1.323 |
Maj | +1.213 |
inker | +1.199 |
uve | +1.183 |
Neg logit contributions | |
20439 | -1.791 |
Sexual | -1.499 |
Clo | -1.400 |
isolation | -1.377 |
sheltered | -1.370 |
Token | emerge |
Token ID | 14740 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
Franch | +1.366 |
tti | +1.313 |
Maj | +1.238 |
inker | +1.226 |
rieg | +1.214 |
Neg logit contributions | |
20439 | -1.009 |
Sexual | -0.783 |
Clo | -0.714 |
isolation | -0.693 |
sheltered | -0.688 |
Token | in |
Token ID | 287 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
20439 | +0.082 |
Sexual | +0.068 |
Clo | +0.063 |
isolation | +0.062 |
sheltered | +0.062 |
Neg logit contributions | |
Franch | -0.070 |
tti | -0.066 |
Maj | -0.061 |
inker | -0.061 |
uve | -0.060 |
Token | terms |
Token ID | 2846 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
20439 | +0.594 |
Sexual | +0.486 |
Clo | +0.457 |
isolation | +0.452 |
sheltered | +0.449 |
Neg logit contributions | |
Franch | -0.514 |
tti | -0.489 |
Maj | -0.452 |
inker | -0.451 |
rieg | -0.446 |
Token | of |
Token ID | 286 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Franch | +1.094 |
tti | +1.033 |
Maj | +0.944 |
inker | +0.916 |
rieg | +0.905 |
Neg logit contributions | |
20439 | -1.913 |
Sexual | -1.617 |
Clo | -1.538 |
isolation | -1.525 |
ileaks | -1.525 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
20439 | +1.101 |
Sexual | +0.893 |
Clo | +0.843 |
isolation | +0.839 |
sheltered | +0.829 |
Neg logit contributions | |
Franch | -1.040 |
tti | -0.997 |
inker | -0.928 |
Maj | -0.920 |
rieg | -0.919 |
Token | car |
Token ID | 1097 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
20439 | +0.667 |
Sexual | +0.547 |
Clo | +0.513 |
isolation | +0.506 |
sheltered | +0.504 |
Neg logit contributions | |
Franch | -0.571 |
tti | -0.542 |
Maj | -0.503 |
inker | -0.499 |
uve | -0.494 |
Token | performance |
Token ID | 2854 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
20439 | +0.642 |
Sexual | +0.527 |
Clo | +0.493 |
isolation | +0.489 |
sheltered | +0.484 |
Neg logit contributions | |
Franch | -0.564 |
tti | -0.535 |
Maj | -0.496 |
inker | -0.493 |
rieg | -0.488 |
Token | . |
Token ID | 13 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Franch | +0.328 |
tti | +0.313 |
Maj | +0.289 |
inker | +0.284 |
uve | +0.282 |
Neg logit contributions | |
20439 | -0.417 |
Sexual | -0.345 |
Clo | -0.323 |
ileaks | -0.318 |
sheltered | -0.317 |
Token | rine |
Token ID | 7640 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
20439 | +0.313 |
Sexual | +0.245 |
Clo | +0.228 |
isolation | +0.219 |
ileaks | +0.219 |
Neg logit contributions | |
Franch | -0.425 |
tti | -0.408 |
Maj | -0.385 |
inker | -0.383 |
uve | -0.379 |
Token | Lat |
Token ID | 5476 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
Franch | +0.706 |
tti | +0.671 |
Maj | +0.628 |
inker | +0.618 |
uve | +0.615 |
Neg logit contributions | |
20439 | -0.738 |
Sexual | -0.597 |
Clo | -0.552 |
isolation | -0.548 |
sheltered | -0.545 |
Token | end |
Token ID | 437 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Franch | +2.373 |
tti | +2.304 |
Maj | +2.130 |
inker | +2.127 |
uve | +2.120 |
Neg logit contributions | |
20439 | -2.607 |
Sexual | -2.115 |
Clo | -1.958 |
isolation | -1.936 |
sheltered | -1.922 |
Token | res |
Token ID | 411 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
Franch | +1.399 |
tti | +1.340 |
Maj | +1.253 |
inker | +1.245 |
uve | +1.240 |
Neg logit contributions | |
20439 | -1.360 |
Sexual | -1.091 |
Clo | -1.006 |
isolation | -0.997 |
sheltered | -0.988 |
Token | se |
Token ID | 325 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Franch | +0.714 |
tti | +0.686 |
Maj | +0.648 |
inker | +0.641 |
uve | +0.641 |
Neg logit contributions | |
20439 | -0.547 |
Sexual | -0.422 |
Clo | -0.383 |
isolation | -0.376 |
ileaks | -0.376 |
Token | , |
Token ID | 11 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
Franch | +0.253 |
tti | +0.240 |
Maj | +0.222 |
inker | +0.220 |
rieg | +0.218 |
Neg logit contributions | |
20439 | -0.317 |
Sexual | -0.262 |
Clo | -0.246 |
isolation | -0.243 |
sheltered | -0.242 |
Token | the |
Token ID | 262 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Franch | +0.411 |
tti | +0.391 |
Maj | +0.364 |
inker | +0.362 |
uve | +0.358 |
Neg logit contributions | |
20439 | -0.438 |
Sexual | -0.356 |
Clo | -0.333 |
isolation | -0.328 |
sheltered | -0.326 |
Token | NDP |
Token ID | 20392 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Franch | +1.515 |
tti | +1.442 |
Maj | +1.361 |
inker | +1.334 |
uve | +1.319 |
Neg logit contributions | |
20439 | -1.539 |
Sexual | -1.226 |
Clo | -1.131 |
ileaks | -1.122 |
isolation | -1.114 |
Token | � |
Token ID | 447 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
20439 | +0.340 |
Sexual | +0.278 |
Clo | +0.259 |
isolation | +0.255 |
sheltered | +0.254 |
Neg logit contributions | |
Franch | -0.319 |
tti | -0.303 |
Maj | -0.281 |
inker | -0.280 |
uve | -0.278 |
Token | � |
Token ID | 247 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
20439 | +0.339 |
Sexual | +0.265 |
Clo | +0.243 |
isolation | +0.238 |
sheltered | +0.237 |
Neg logit contributions | |
Franch | -0.438 |
tti | -0.419 |
Maj | -0.394 |
inker | -0.391 |
uve | -0.388 |
Token | s |
Token ID | 82 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
Franch | +0.661 |
tti | +0.636 |
Maj | +0.603 |
inker | +0.599 |
uve | +0.595 |
Neg logit contributions | |
20439 | -0.396 |
Sexual | -0.294 |
Clo | -0.265 |
isolation | -0.259 |
sheltered | -0.256 |
Token | have |
Token ID | 423 |
Feature activation | -9.65e-03 |
Pos logit contributions | |
20439 | +0.767 |
Sexual | +0.629 |
Clo | +0.593 |
sheltered | +0.590 |
isolation | +0.588 |
Neg logit contributions | |
Franch | -0.723 |
tti | -0.690 |
Maj | -0.642 |
inker | -0.639 |
uve | -0.634 |
Token | re |
Token ID | 302 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
20439 | +0.007 |
Sexual | +0.006 |
Clo | +0.006 |
isolation | +0.005 |
sheltered | +0.005 |
Neg logit contributions | |
Franch | -0.008 |
tti | -0.008 |
Maj | -0.007 |
inker | -0.007 |
uve | -0.007 |
Token | aped |
Token ID | 5813 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
20439 | +0.367 |
Sexual | +0.303 |
Clo | +0.284 |
sheltered | +0.281 |
isolation | +0.280 |
Neg logit contributions | |
Franch | -0.343 |
tti | -0.324 |
Maj | -0.303 |
inker | -0.299 |
rieg | -0.297 |
Token | billions |
Token ID | 13188 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Franch | +2.009 |
tti | +1.899 |
Maj | +1.785 |
inker | +1.755 |
rieg | +1.744 |
Neg logit contributions | |
20439 | -2.241 |
Sexual | -1.815 |
Clo | -1.678 |
ileaks | -1.655 |
isolation | -1.648 |
Token | of |
Token ID | 286 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Franch | +1.844 |
tti | +1.748 |
Maj | +1.623 |
inker | +1.595 |
rieg | +1.591 |
Neg logit contributions | |
20439 | -2.416 |
Sexual | -1.994 |
Clo | -1.858 |
isolation | -1.832 |
IRC | -1.830 |
Token | profits |
Token ID | 10177 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
Franch | +0.662 |
tti | +0.617 |
Maj | +0.559 |
inker | +0.551 |
rieg | +0.543 |
Neg logit contributions | |
20439 | -1.224 |
Sexual | -1.040 |
Clo | -0.986 |
isolation | -0.974 |
sheltered | -0.970 |
Token | since |
Token ID | 1201 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
20439 | +0.564 |
Sexual | +0.457 |
Clo | +0.427 |
isolation | +0.421 |
sheltered | +0.420 |
Neg logit contributions | |
Franch | -0.540 |
tti | -0.515 |
Maj | -0.480 |
inker | -0.476 |
uve | -0.472 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
Franch | +0.632 |
tti | +0.597 |
Maj | +0.565 |
inker | +0.556 |
rieg | +0.551 |
Neg logit contributions | |
20439 | -0.652 |
Sexual | -0.527 |
Clo | -0.481 |
isolation | -0.474 |
IRC | -0.474 |
Token | as |
Token ID | 355 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
20439 | +0.642 |
Sexual | +0.525 |
Clo | +0.492 |
isolation | +0.485 |
sheltered | +0.483 |
Neg logit contributions | |
Franch | -0.568 |
tti | -0.540 |
Maj | -0.502 |
inker | -0.498 |
uve | -0.494 |
Token | the |
Token ID | 262 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
Franch | +0.355 |
tti | +0.338 |
Maj | +0.316 |
inker | +0.313 |
rieg | +0.310 |
Neg logit contributions | |
20439 | -0.377 |
Sexual | -0.306 |
Clo | -0.285 |
isolation | -0.281 |
sheltered | -0.279 |
Token | Fed |
Token ID | 10169 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Franch | +0.333 |
tti | +0.318 |
Maj | +0.296 |
inker | +0.294 |
uve | +0.291 |
Neg logit contributions | |
20439 | -0.343 |
Sexual | -0.277 |
Clo | -0.259 |
isolation | -0.255 |
sheltered | -0.254 |
Token | voting |
Token ID | 6709 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Franch | +2.266 |
tti | +2.156 |
Maj | +2.034 |
inker | +1.984 |
rieg | +1.973 |
Neg logit contributions | |
20439 | -2.355 |
Sexual | -1.867 |
Clo | -1.726 |
ileaks | -1.709 |
sheltered | -1.709 |
Token | ( |
Token ID | 357 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
20439 | +0.202 |
Sexual | +0.168 |
Clo | +0.158 |
isolation | +0.156 |
sheltered | +0.154 |
Neg logit contributions | |
Franch | -0.178 |
tti | -0.169 |
inker | -0.156 |
Maj | -0.155 |
rieg | -0.154 |
Token | 33 |
Token ID | 2091 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
Franch | +0.324 |
tti | +0.309 |
Maj | +0.288 |
inker | +0.286 |
uve | +0.284 |
Neg logit contributions | |
20439 | -0.331 |
Sexual | -0.266 |
Clo | -0.250 |
isolation | -0.245 |
sheltered | -0.245 |
Token | 85 |
Token ID | 5332 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
20439 | +0.403 |
Sexual | +0.330 |
Clo | +0.309 |
isolation | +0.305 |
sheltered | +0.302 |
Neg logit contributions | |
Franch | -0.375 |
tti | -0.355 |
inker | -0.330 |
Maj | -0.330 |
uve | -0.327 |
Token | – |
Token ID | 1906 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
20439 | +1.185 |
Sexual | +0.941 |
Clo | +0.878 |
isolation | +0.864 |
sheltered | +0.849 |
Neg logit contributions | |
Franch | -1.450 |
tti | -1.394 |
inker | -1.313 |
uve | -1.300 |
rieg | -1.300 |
Token | 30 |
Token ID | 1270 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
20439 | +0.765 |
Sexual | +0.597 |
Clo | +0.548 |
isolation | +0.536 |
sheltered | +0.533 |
Neg logit contributions | |
Franch | -0.963 |
tti | -0.922 |
Maj | -0.868 |
inker | -0.863 |
uve | -0.857 |
Token | 60 |
Token ID | 1899 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
20439 | +0.445 |
Sexual | +0.350 |
Clo | +0.323 |
isolation | +0.317 |
sheltered | +0.315 |
Neg logit contributions | |
Franch | -0.537 |
tti | -0.514 |
Maj | -0.482 |
inker | -0.480 |
uve | -0.476 |
Token | ).[ |
Token ID | 42669 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
20439 | +0.916 |
Sexual | +0.746 |
Clo | +0.700 |
isolation | +0.690 |
sheltered | +0.685 |
Neg logit contributions | |
Franch | -0.854 |
tti | -0.814 |
inker | -0.754 |
Maj | -0.753 |
uve | -0.746 |
Token | 126 |
Token ID | 19420 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
20439 | +0.027 |
Sexual | +0.021 |
Clo | +0.019 |
isolation | +0.019 |
sheltered | +0.019 |
Neg logit contributions | |
Franch | -0.031 |
tti | -0.030 |
Maj | -0.028 |
inker | -0.028 |
uve | -0.028 |
Token | ] |
Token ID | 60 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
20439 | +1.355 |
Sexual | +0.997 |
Clo | +0.898 |
isolation | +0.878 |
sheltered | +0.866 |
Neg logit contributions | |
Franch | -2.337 |
tti | -2.243 |
inker | -2.125 |
Maj | -2.120 |
uve | -2.111 |
Token | On |
Token ID | 1550 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
Franch | +0.637 |
tti | +0.606 |
Maj | +0.569 |
inker | +0.562 |
uve | +0.557 |
Neg logit contributions | |
20439 | -0.611 |
Sexual | -0.488 |
Clo | -0.453 |
isolation | -0.448 |
sheltered | -0.447 |
Token | for |
Token ID | 329 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
20439 | +0.693 |
Sexual | +0.557 |
Clo | +0.518 |
isolation | +0.510 |
sheltered | +0.507 |
Neg logit contributions | |
Franch | -0.708 |
tti | -0.676 |
Maj | -0.632 |
inker | -0.627 |
uve | -0.621 |
Token | present |
Token ID | 1944 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
20439 | +0.060 |
Sexual | +0.049 |
Clo | +0.046 |
isolation | +0.045 |
sheltered | +0.045 |
Neg logit contributions | |
Franch | -0.058 |
tti | -0.056 |
Maj | -0.052 |
inker | -0.051 |
uve | -0.051 |
Token | ers |
Token ID | 364 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Franch | +1.828 |
tti | +1.745 |
Maj | +1.630 |
inker | +1.603 |
uve | +1.597 |
Neg logit contributions | |
20439 | -1.881 |
Sexual | -1.528 |
Clo | -1.402 |
isolation | -1.390 |
sheltered | -1.385 |
Token | entering |
Token ID | 8218 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Franch | +0.198 |
tti | +0.188 |
Maj | +0.174 |
inker | +0.172 |
uve | +0.171 |
Neg logit contributions | |
20439 | -0.237 |
Sexual | -0.195 |
Clo | -0.182 |
isolation | -0.180 |
sheltered | -0.179 |
Token | from |
Token ID | 422 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
Franch | +1.102 |
tti | +1.047 |
Maj | +0.978 |
inker | +0.964 |
uve | +0.959 |
Neg logit contributions | |
20439 | -1.205 |
Sexual | -0.980 |
Clo | -0.908 |
isolation | -0.897 |
sheltered | -0.895 |
Token | their |
Token ID | 511 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
Franch | +0.741 |
tti | +0.704 |
Maj | +0.659 |
inker | +0.650 |
uve | +0.646 |
Neg logit contributions | |
20439 | -0.774 |
Sexual | -0.628 |
Clo | -0.581 |
isolation | -0.573 |
sheltered | -0.571 |
Token | side |
Token ID | 1735 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
20439 | +0.423 |
Sexual | +0.340 |
Clo | +0.315 |
isolation | +0.310 |
ileaks | +0.309 |
Neg logit contributions | |
Franch | -0.424 |
tti | -0.403 |
Maj | -0.378 |
inker | -0.372 |
uve | -0.370 |
Token | of |
Token ID | 286 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
20439 | +0.302 |
Sexual | +0.248 |
Clo | +0.233 |
isolation | +0.230 |
sheltered | +0.229 |
Neg logit contributions | |
Franch | -0.257 |
tti | -0.243 |
Maj | -0.226 |
inker | -0.225 |
rieg | -0.222 |
Token | the |
Token ID | 262 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Franch | +0.792 |
tti | +0.754 |
Maj | +0.704 |
inker | +0.697 |
uve | +0.692 |
Neg logit contributions | |
20439 | -0.833 |
Sexual | -0.675 |
Clo | -0.627 |
isolation | -0.619 |
sheltered | -0.616 |
Token | stage |
Token ID | 3800 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
20439 | +0.203 |
Sexual | +0.162 |
Clo | +0.150 |
isolation | +0.148 |
sheltered | +0.147 |
Neg logit contributions | |
Franch | -0.216 |
tti | -0.206 |
Maj | -0.193 |
inker | -0.191 |
uve | -0.190 |
Token | and |
Token ID | 290 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
Franch | +0.230 |
tti | +0.218 |
Maj | +0.203 |
inker | +0.200 |
uve | +0.198 |
Neg logit contributions | |
20439 | -0.281 |
Sexual | -0.232 |
Clo | -0.217 |
isolation | -0.214 |
sheltered | -0.213 |
Token | MP |
Token ID | 4904 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
20439 | +1.510 |
Sexual | +1.239 |
Clo | +1.166 |
isolation | +1.141 |
sheltered | +1.129 |
Neg logit contributions | |
Franch | -1.398 |
tti | -1.339 |
inker | -1.238 |
rieg | -1.231 |
Maj | -1.231 |
Token | I |
Token ID | 40 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
20439 | +1.831 |
Sexual | +1.449 |
Clo | +1.358 |
isolation | +1.318 |
IRC | +1.310 |
Neg logit contributions | |
Franch | -2.215 |
tti | -2.121 |
Maj | -1.978 |
inker | -1.969 |
rieg | -1.964 |
Token | for |
Token ID | 329 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
20439 | +1.162 |
Sexual | +0.968 |
Clo | +0.913 |
isolation | +0.900 |
sheltered | +0.890 |
Neg logit contributions | |
Franch | -0.943 |
tti | -0.895 |
Maj | -0.823 |
inker | -0.822 |
rieg | -0.818 |
Token | Heart |
Token ID | 8894 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
20439 | +0.944 |
Sexual | +0.773 |
Clo | +0.727 |
isolation | +0.715 |
sheltered | +0.706 |
Neg logit contributions | |
Franch | -0.892 |
tti | -0.849 |
inker | -0.789 |
Maj | -0.787 |
rieg | -0.782 |
Token | and |
Token ID | 290 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
20439 | +1.626 |
Sexual | +1.359 |
Clo | +1.285 |
isolation | +1.259 |
IRC | +1.245 |
Neg logit contributions | |
Franch | -1.394 |
tti | -1.300 |
Maj | -1.203 |
inker | -1.198 |
uve | -1.197 |
Token | Lung |
Token ID | 39337 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
Franch | +0.245 |
tti | +0.235 |
Maj | +0.222 |
inker | +0.220 |
uve | +0.219 |
Neg logit contributions | |
20439 | -0.182 |
Sexual | -0.141 |
Clo | -0.129 |
isolation | -0.127 |
sheltered | -0.126 |
Token | Research |
Token ID | 4992 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
20439 | +1.808 |
Sexual | +1.534 |
Clo | +1.475 |
isolation | +1.441 |
Hague | +1.425 |
Neg logit contributions | |
Franch | -1.305 |
tti | -1.232 |
rieg | -1.135 |
inker | -1.131 |
uve | -1.129 |
Token | For |
Token ID | 1114 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
20439 | +0.564 |
Sexual | +0.462 |
Clo | +0.433 |
isolation | +0.426 |
sheltered | +0.423 |
Neg logit contributions | |
Franch | -0.523 |
tti | -0.499 |
Maj | -0.461 |
inker | -0.460 |
rieg | -0.458 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
20439 | +1.791 |
Sexual | +1.460 |
Clo | +1.382 |
isolation | +1.365 |
sheltered | +1.345 |
Neg logit contributions | |
Franch | -1.783 |
tti | -1.685 |
Maj | -1.566 |
inker | -1.565 |
rieg | -1.563 |
Token | kidneys |
Token ID | 41395 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
20439 | +0.805 |
Sexual | +0.632 |
Clo | +0.587 |
isolation | +0.578 |
sheltered | +0.571 |
Neg logit contributions | |
Franch | -1.002 |
tti | -0.958 |
Maj | -0.900 |
inker | -0.897 |
rieg | -0.890 |
Token | to |
Token ID | 284 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Franch | +0.097 |
tti | +0.093 |
Maj | +0.086 |
inker | +0.085 |
uve | +0.085 |
Neg logit contributions | |
20439 | -0.109 |
Sexual | -0.089 |
Clo | -0.084 |
isolation | -0.083 |
sheltered | -0.083 |
Token | has |
Token ID | 468 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Franch | +0.178 |
tti | +0.170 |
Maj | +0.160 |
inker | +0.157 |
uve | +0.156 |
Neg logit contributions | |
20439 | -0.162 |
Sexual | -0.128 |
Clo | -0.118 |
isolation | -0.116 |
ileaks | -0.116 |
Token | had |
Token ID | 550 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
20439 | +0.087 |
Sexual | +0.070 |
Clo | +0.065 |
isolation | +0.064 |
sheltered | +0.064 |
Neg logit contributions | |
Franch | -0.092 |
tti | -0.088 |
Maj | -0.082 |
inker | -0.081 |
uve | -0.081 |
Token | more |
Token ID | 517 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
Franch | +0.844 |
tti | +0.806 |
Maj | +0.755 |
inker | +0.745 |
rieg | +0.735 |
Neg logit contributions | |
20439 | -0.884 |
Sexual | -0.716 |
Clo | -0.660 |
ileaks | -0.652 |
isolation | -0.647 |
Token | than |
Token ID | 621 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Franch | +0.373 |
tti | +0.357 |
Maj | +0.336 |
inker | +0.332 |
rieg | +0.329 |
Neg logit contributions | |
20439 | -0.323 |
Sexual | -0.254 |
Clo | -0.234 |
isolation | -0.228 |
ileaks | -0.228 |
Token | its |
Token ID | 663 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
20439 | +0.373 |
Sexual | +0.307 |
Clo | +0.289 |
isolation | +0.286 |
sheltered | +0.285 |
Neg logit contributions | |
Franch | -0.319 |
tti | -0.303 |
Maj | -0.280 |
inker | -0.279 |
rieg | -0.276 |
Token | share |
Token ID | 2648 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
Franch | +0.211 |
tti | +0.199 |
Maj | +0.183 |
inker | +0.181 |
uve | +0.180 |
Neg logit contributions | |
20439 | -0.294 |
Sexual | -0.246 |
Clo | -0.232 |
isolation | -0.229 |
sheltered | -0.228 |
Token | of |
Token ID | 286 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
20439 | +0.654 |
Sexual | +0.549 |
Clo | +0.519 |
isolation | +0.513 |
sheltered | +0.512 |
Neg logit contributions | |
Franch | -0.429 |
tti | -0.404 |
Maj | -0.370 |
inker | -0.366 |
uve | -0.362 |
Token | crises |
Token ID | 25712 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Franch | +0.782 |
tti | +0.743 |
Maj | +0.703 |
inker | +0.691 |
uve | +0.682 |
Neg logit contributions | |
20439 | -0.756 |
Sexual | -0.602 |
Clo | -0.554 |
ileaks | -0.548 |
IRC | -0.544 |
Token | in |
Token ID | 287 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
20439 | +0.230 |
Sexual | +0.189 |
Clo | +0.177 |
isolation | +0.175 |
sheltered | +0.174 |
Neg logit contributions | |
Franch | -0.193 |
tti | -0.183 |
Maj | -0.170 |
inker | -0.168 |
uve | -0.166 |
Token | recent |
Token ID | 2274 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Franch | +1.011 |
tti | +0.970 |
Maj | +0.923 |
inker | +0.909 |
rieg | +0.900 |
Neg logit contributions | |
20439 | -0.743 |
Sexual | -0.572 |
Clo | -0.516 |
ileaks | -0.509 |
aeus | -0.501 |
Token | decades |
Token ID | 4647 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
20439 | +0.869 |
Sexual | +0.712 |
Clo | +0.669 |
isolation | +0.663 |
sheltered | +0.658 |
Neg logit contributions | |
Franch | -0.760 |
tti | -0.720 |
Maj | -0.665 |
inker | -0.664 |
uve | -0.660 |
Token | . |
Token ID | 13 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
Franch | +0.464 |
tti | +0.441 |
Maj | +0.409 |
inker | +0.404 |
uve | +0.398 |
Neg logit contributions | |
20439 | -0.579 |
Sexual | -0.477 |
Clo | -0.447 |
isolation | -0.442 |
sheltered | -0.439 |
Token |
|
Token ID | 198 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
Franch | +0.573 |
tti | +0.546 |
Maj | +0.509 |
inker | +0.506 |
uve | +0.502 |
Neg logit contributions | |
20439 | -0.600 |
Sexual | -0.487 |
Clo | -0.455 |
isolation | -0.447 |
sheltered | -0.445 |
Token |
|
Token ID | 198 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
Franch | +0.704 |
tti | +0.674 |
Maj | +0.633 |
inker | +0.615 |
rieg | +0.609 |
Neg logit contributions | |
20439 | -0.790 |
Sexual | -0.632 |
isolation | -0.597 |
ileaks | -0.596 |
Clo | -0.594 |
Token | Tom |
Token ID | 13787 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Franch | +0.425 |
tti | +0.404 |
Maj | +0.376 |
inker | +0.372 |
uve | +0.370 |
Neg logit contributions | |
20439 | -0.471 |
Sexual | -0.386 |
Clo | -0.359 |
isolation | -0.353 |
sheltered | -0.351 |
Token | C |
Token ID | 327 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
Franch | +0.340 |
tti | +0.324 |
Maj | +0.302 |
inker | +0.299 |
uve | +0.297 |
Neg logit contributions | |
20439 | -0.352 |
Sexual | -0.285 |
Clo | -0.265 |
isolation | -0.262 |
sheltered | -0.260 |
Token | ray |
Token ID | 2433 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
20439 | +0.394 |
Sexual | +0.324 |
Clo | +0.304 |
isolation | +0.299 |
sheltered | +0.298 |
Neg logit contributions | |
Franch | -0.348 |
tti | -0.330 |
Maj | -0.306 |
inker | -0.303 |
uve | -0.301 |
Token | was |
Token ID | 373 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
20439 | +3.383 |
Sexual | +2.808 |
Clo | +2.607 |
isolation | +2.586 |
padded | +2.577 |
Neg logit contributions | |
Franch | -3.124 |
tti | -2.918 |
inker | -2.773 |
rieg | -2.757 |
uve | -2.755 |
Token | one |
Token ID | 530 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
20439 | +0.268 |
Sexual | +0.218 |
Clo | +0.204 |
isolation | +0.201 |
sheltered | +0.200 |
Neg logit contributions | |
Franch | -0.252 |
tti | -0.240 |
Maj | -0.223 |
inker | -0.222 |
uve | -0.220 |
Token | of |
Token ID | 286 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Franch | +1.785 |
tti | +1.677 |
Maj | +1.541 |
inker | +1.522 |
uve | +1.492 |
Neg logit contributions | |
20439 | -2.876 |
Sexual | -2.432 |
Clo | -2.295 |
sheltered | -2.256 |
isolation | -2.255 |
Token | two |
Token ID | 734 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
Franch | +2.124 |
tti | +2.013 |
Maj | +1.909 |
inker | +1.858 |
rieg | +1.835 |
Neg logit contributions | |
20439 | -2.219 |
Sexual | -1.805 |
Clo | -1.645 |
sheltered | -1.633 |
ileaks | -1.630 |
Token | HB |
Token ID | 25997 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
20439 | +1.635 |
Sexual | +1.327 |
Clo | +1.259 |
isolation | +1.242 |
sheltered | +1.226 |
Neg logit contributions | |
Franch | -1.573 |
tti | -1.506 |
inker | -1.405 |
uve | -1.399 |
rieg | -1.394 |
Token | Alberta |
Token ID | 15555 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
Franch | +1.288 |
tti | +1.217 |
Maj | +1.149 |
inker | +1.130 |
uve | +1.117 |
Neg logit contributions | |
20439 | -1.376 |
Sexual | -1.113 |
Clo | -1.034 |
ileaks | -1.023 |
isolation | -1.010 |
Token | � |
Token ID | 447 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
20439 | +0.572 |
Sexual | +0.468 |
Clo | +0.437 |
isolation | +0.432 |
sheltered | +0.430 |
Neg logit contributions | |
Franch | -0.511 |
tti | -0.485 |
Maj | -0.451 |
inker | -0.447 |
uve | -0.444 |
Token | � |
Token ID | 247 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
Franch | +0.163 |
tti | +0.156 |
Maj | +0.146 |
inker | +0.145 |
uve | +0.144 |
Neg logit contributions | |
20439 | -0.141 |
Sexual | -0.112 |
Clo | -0.103 |
isolation | -0.101 |
sheltered | -0.101 |
Token | s |
Token ID | 82 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
Franch | +0.031 |
tti | +0.029 |
Maj | +0.028 |
inker | +0.028 |
uve | +0.028 |
Neg logit contributions | |
20439 | -0.018 |
Sexual | -0.013 |
Clo | -0.012 |
isolation | -0.012 |
sheltered | -0.012 |
Token | budget |
Token ID | 4466 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
20439 | +0.029 |
Sexual | +0.024 |
Clo | +0.022 |
isolation | +0.022 |
sheltered | +0.022 |
Neg logit contributions | |
Franch | -0.027 |
tti | -0.025 |
Maj | -0.024 |
inker | -0.023 |
uve | -0.023 |
Token | hole |
Token ID | 7604 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
20439 | +0.358 |
Sexual | +0.281 |
Clo | +0.259 |
isolation | +0.254 |
sheltered | +0.253 |
Neg logit contributions | |
Franch | -0.438 |
tti | -0.420 |
Maj | -0.395 |
inker | -0.392 |
uve | -0.389 |
Token | . |
Token ID | 13 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
20439 | +3.816 |
Sexual | +3.138 |
sheltered | +2.928 |
Clo | +2.917 |
isolation | +2.916 |
Neg logit contributions | |
Franch | -3.655 |
tti | -3.399 |
inker | -3.178 |
Maj | -3.173 |
rieg | -3.143 |
Token | � |
Token ID | 564 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
20439 | +0.461 |
Sexual | +0.372 |
Clo | +0.348 |
isolation | +0.339 |
sheltered | +0.338 |
Neg logit contributions | |
Franch | -0.462 |
tti | -0.442 |
inker | -0.411 |
Maj | -0.411 |
uve | -0.407 |
Token | � |
Token ID | 250 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Franch | +0.184 |
tti | +0.175 |
Maj | +0.164 |
inker | +0.163 |
uve | +0.162 |
Neg logit contributions | |
20439 | -0.172 |
Sexual | -0.138 |
Clo | -0.128 |
isolation | -0.126 |
sheltered | -0.125 |
Token | Cont |
Token ID | 4264 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
20439 | +0.147 |
Sexual | +0.118 |
Clo | +0.109 |
isolation | +0.107 |
sheltered | +0.107 |
Neg logit contributions | |
Franch | -0.153 |
tti | -0.146 |
Maj | -0.137 |
inker | -0.136 |
uve | -0.135 |
Token | rary |
Token ID | 11619 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
20439 | +0.231 |
Sexual | +0.189 |
Clo | +0.177 |
isolation | +0.175 |
sheltered | +0.174 |
Neg logit contributions | |
Franch | -0.206 |
tti | -0.195 |
Maj | -0.182 |
inker | -0.180 |
uve | -0.179 |
Token | ile |
Token ID | 576 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
20439 | +0.703 |
Sexual | +0.558 |
Clo | +0.517 |
isolation | +0.512 |
sheltered | +0.507 |
Neg logit contributions | |
Franch | -0.756 |
tti | -0.725 |
Maj | -0.677 |
inker | -0.676 |
uve | -0.671 |
Token | 's |
Token ID | 338 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
20439 | +0.432 |
Sexual | +0.351 |
Clo | +0.328 |
isolation | +0.322 |
sheltered | +0.321 |
Neg logit contributions | |
Franch | -0.425 |
tti | -0.404 |
Maj | -0.377 |
inker | -0.376 |
rieg | -0.371 |
Token | movie |
Token ID | 3807 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
20439 | +0.232 |
Sexual | +0.190 |
Clo | +0.178 |
isolation | +0.175 |
sheltered | +0.174 |
Neg logit contributions | |
Franch | -0.232 |
tti | -0.222 |
inker | -0.205 |
Maj | -0.205 |
rieg | -0.204 |
Token | does |
Token ID | 857 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
20439 | +0.063 |
Sexual | +0.051 |
Clo | +0.047 |
isolation | +0.046 |
sheltered | +0.046 |
Neg logit contributions | |
Franch | -0.072 |
tti | -0.068 |
Maj | -0.064 |
inker | -0.064 |
rieg | -0.063 |
Token | not |
Token ID | 407 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
20439 | +0.145 |
Sexual | +0.119 |
Clo | +0.112 |
isolation | +0.111 |
sheltered | +0.110 |
Neg logit contributions | |
Franch | -0.130 |
tti | -0.123 |
Maj | -0.114 |
inker | -0.113 |
rieg | -0.113 |
Token | excuse |
Token ID | 12226 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
Franch | +0.421 |
tti | +0.400 |
Maj | +0.372 |
inker | +0.370 |
uve | +0.366 |
Neg logit contributions | |
20439 | -0.460 |
Sexual | -0.376 |
Clo | -0.352 |
isolation | -0.348 |
sheltered | -0.346 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
20439 | +3.362 |
Sexual | +2.876 |
isolation | +2.779 |
Clo | +2.771 |
sheltered | +2.704 |
Neg logit contributions | |
Franch | -3.289 |
tti | -3.155 |
inker | -2.906 |
rieg | -2.903 |
uve | -2.863 |
Token | riot |
Token ID | 16352 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
20439 | +0.161 |
Sexual | +0.130 |
Clo | +0.121 |
isolation | +0.119 |
sheltered | +0.118 |
Neg logit contributions | |
Franch | -0.167 |
tti | -0.160 |
Maj | -0.149 |
inker | -0.148 |
uve | -0.147 |
Token | ing |
Token ID | 278 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Franch | +0.381 |
tti | +0.362 |
Maj | +0.336 |
inker | +0.333 |
uve | +0.330 |
Neg logit contributions | |
20439 | -0.441 |
Sexual | -0.361 |
Clo | -0.338 |
isolation | -0.333 |
sheltered | -0.332 |
Token | in |
Token ID | 287 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Franch | +1.117 |
tti | +1.060 |
Maj | +0.991 |
inker | +0.976 |
uve | +0.971 |
Neg logit contributions | |
20439 | -1.253 |
Sexual | -1.017 |
Clo | -0.947 |
isolation | -0.934 |
ileaks | -0.930 |
Token | Libya |
Token ID | 13465 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
Franch | +0.408 |
tti | +0.391 |
Maj | +0.366 |
inker | +0.365 |
uve | +0.362 |
Neg logit contributions | |
20439 | -0.346 |
Sexual | -0.273 |
Clo | -0.253 |
isolation | -0.249 |
sheltered | -0.247 |
Token | rule |
Token ID | 25135 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
20439 | +1.690 |
Sexual | +1.408 |
Clo | +1.324 |
sheltered | +1.304 |
isolation | +1.300 |
Neg logit contributions | |
Franch | -1.526 |
tti | -1.432 |
inker | -1.327 |
Maj | -1.318 |
rieg | -1.318 |
Token | Fi |
Token ID | 23238 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Franch | +1.216 |
tti | +1.161 |
Maj | +1.083 |
inker | +1.063 |
uve | +1.056 |
Neg logit contributions | |
20439 | -1.373 |
Sexual | -1.119 |
Clo | -1.039 |
ileaks | -1.024 |
isolation | -1.023 |
Token | end |
Token ID | 437 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
20439 | +0.212 |
Sexual | +0.169 |
Clo | +0.157 |
isolation | +0.154 |
sheltered | +0.153 |
Neg logit contributions | |
Franch | -0.242 |
tti | -0.232 |
Maj | -0.217 |
inker | -0.216 |
uve | -0.214 |
Token | , |
Token ID | 11 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
20439 | +0.513 |
Sexual | +0.418 |
Clo | +0.391 |
isolation | +0.386 |
sheltered | +0.384 |
Neg logit contributions | |
Franch | -0.465 |
tti | -0.442 |
Maj | -0.411 |
inker | -0.408 |
uve | -0.404 |
Token | O |
Token ID | 440 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
Franch | +0.268 |
tti | +0.256 |
Maj | +0.240 |
inker | +0.237 |
uve | +0.235 |
Neg logit contributions | |
20439 | -0.265 |
Sexual | -0.213 |
Clo | -0.197 |
isolation | -0.194 |
sheltered | -0.194 |
Token | car |
Token ID | 7718 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
20439 | +0.223 |
Sexual | +0.159 |
Clo | +0.141 |
isolation | +0.139 |
sheltered | +0.137 |
Neg logit contributions | |
Franch | -0.415 |
tti | -0.405 |
inker | -0.382 |
Maj | -0.381 |
rieg | -0.378 |
Token | ina |
Token ID | 1437 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
20439 | +2.642 |
Sexual | +2.022 |
Clo | +1.841 |
sheltered | +1.784 |
IRC | +1.778 |
Neg logit contributions | |
Franch | -3.913 |
tti | -3.707 |
Maj | -3.516 |
uve | -3.516 |
inker | -3.492 |
Token | � |
Token ID | 447 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
20439 | +0.839 |
Sexual | +0.697 |
Clo | +0.659 |
isolation | +0.650 |
sheltered | +0.647 |
Neg logit contributions | |
Franch | -0.641 |
tti | -0.607 |
inker | -0.559 |
Maj | -0.557 |
uve | -0.551 |
Token | � |
Token ID | 247 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
Franch | +0.051 |
tti | +0.049 |
Maj | +0.046 |
inker | +0.046 |
rieg | +0.045 |
Neg logit contributions | |
20439 | -0.042 |
Sexual | -0.033 |
Clo | -0.031 |
isolation | -0.030 |
sheltered | -0.030 |
Token | s |
Token ID | 82 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
20439 | +0.224 |
Sexual | +0.166 |
Clo | +0.150 |
isolation | +0.146 |
sheltered | +0.145 |
Neg logit contributions | |
Franch | -0.380 |
tti | -0.366 |
Maj | -0.347 |
inker | -0.346 |
uve | -0.343 |
Token | O |
Token ID | 440 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
20439 | +0.401 |
Sexual | +0.323 |
Clo | +0.302 |
isolation | +0.297 |
sheltered | +0.295 |
Neg logit contributions | |
Franch | -0.422 |
tti | -0.402 |
Maj | -0.374 |
inker | -0.374 |
rieg | -0.371 |
Token | ed |
Token ID | 276 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
20439 | +1.736 |
Sexual | +1.439 |
Clo | +1.345 |
sheltered | +1.337 |
isolation | +1.335 |
Neg logit contributions | |
Franch | -1.420 |
tti | -1.322 |
Maj | -1.224 |
inker | -1.199 |
uve | -1.199 |
Token | by |
Token ID | 416 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Franch | +0.582 |
tti | +0.553 |
Maj | +0.514 |
inker | +0.510 |
uve | +0.506 |
Neg logit contributions | |
20439 | -0.640 |
Sexual | -0.524 |
Clo | -0.490 |
isolation | -0.484 |
sheltered | -0.481 |
Token | a |
Token ID | 257 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
20439 | +0.285 |
Sexual | +0.230 |
Clo | +0.215 |
isolation | +0.213 |
sheltered | +0.211 |
Neg logit contributions | |
Franch | -0.287 |
tti | -0.274 |
Maj | -0.255 |
inker | -0.254 |
uve | -0.253 |
Token | lifetime |
Token ID | 10869 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
20439 | +0.897 |
Sexual | +0.719 |
Clo | +0.666 |
isolation | +0.657 |
sheltered | +0.657 |
Neg logit contributions | |
Franch | -0.981 |
tti | -0.938 |
Maj | -0.876 |
inker | -0.871 |
uve | -0.867 |
Token | of |
Token ID | 286 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
20439 | +1.431 |
Sexual | +1.204 |
isolation | +1.137 |
sheltered | +1.133 |
Clo | +1.132 |
Neg logit contributions | |
Franch | -1.026 |
tti | -0.962 |
Maj | -0.882 |
inker | -0.873 |
uve | -0.872 |
Token | exposure |
Token ID | 7111 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
20439 | +0.713 |
Sexual | +0.580 |
Clo | +0.541 |
isolation | +0.540 |
sheltered | +0.536 |
Neg logit contributions | |
Franch | -0.712 |
tti | -0.679 |
Maj | -0.630 |
inker | -0.628 |
uve | -0.627 |
Token | to |
Token ID | 284 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
20439 | +3.104 |
Sexual | +2.530 |
sheltered | +2.372 |
isolation | +2.368 |
Clo | +2.355 |
Neg logit contributions | |
Franch | -3.036 |
tti | -2.837 |
uve | -2.650 |
Maj | -2.648 |
inker | -2.633 |
Token | a |
Token ID | 257 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
20439 | +0.430 |
Sexual | +0.348 |
Clo | +0.326 |
isolation | +0.324 |
sheltered | +0.321 |
Neg logit contributions | |
Franch | -0.438 |
tti | -0.420 |
Maj | -0.389 |
inker | -0.388 |
uve | -0.388 |
Token | culture |
Token ID | 3968 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
20439 | +0.414 |
Sexual | +0.337 |
Clo | +0.315 |
isolation | +0.311 |
sheltered | +0.311 |
Neg logit contributions | |
Franch | -0.394 |
tti | -0.376 |
Maj | -0.350 |
inker | -0.348 |
uve | -0.346 |
Token | that |
Token ID | 326 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
20439 | +1.886 |
Sexual | +1.534 |
Clo | +1.432 |
sheltered | +1.422 |
isolation | +1.420 |
Neg logit contributions | |
Franch | -1.865 |
tti | -1.775 |
Maj | -1.651 |
inker | -1.647 |
uve | -1.633 |
Token | says |
Token ID | 1139 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
20439 | +0.664 |
Sexual | +0.522 |
Clo | +0.481 |
isolation | +0.471 |
ileaks | +0.469 |
Neg logit contributions | |
Franch | -0.775 |
tti | -0.742 |
Maj | -0.697 |
inker | -0.690 |
uve | -0.684 |