Token | The |
Token ID | 383 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
wipes | +0.870 |
ignores | +0.796 |
ath | +0.758 |
misses | +0.728 |
crossings | +0.714 |
Neg logit contributions | |
xual | -0.965 |
rolet | -0.896 |
�� | -0.895 |
uana | -0.832 |
orescence | -0.825 |
Token | article |
Token ID | 2708 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
wipes | +0.187 |
ignores | +0.174 |
ath | +0.165 |
misses | +0.159 |
crossings | +0.157 |
Neg logit contributions | |
xual | -0.179 |
�� | -0.164 |
rolet | -0.164 |
uana | -0.152 |
orescence | -0.151 |
Token | was |
Token ID | 373 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
xual | +0.307 |
�� | +0.280 |
rolet | +0.280 |
uana | +0.262 |
orescence | +0.262 |
Neg logit contributions | |
wipes | -0.261 |
ignores | -0.236 |
ath | -0.228 |
Typhoon | -0.216 |
misses | -0.215 |
Token | published |
Token ID | 3199 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
wipes | +0.265 |
ignores | +0.243 |
ath | +0.233 |
misses | +0.225 |
Typhoon | +0.222 |
Neg logit contributions | |
xual | -0.246 |
rolet | -0.225 |
�� | -0.224 |
uana | -0.208 |
orescence | -0.207 |
Token | by |
Token ID | 416 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
wipes | +0.060 |
ignores | +0.055 |
ath | +0.053 |
misses | +0.051 |
Typhoon | +0.050 |
Neg logit contributions | |
xual | -0.060 |
rolet | -0.056 |
�� | -0.055 |
uana | -0.051 |
orescence | -0.051 |
Token | and |
Token ID | 392 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
wipes | +0.755 |
ignores | +0.694 |
ath | +0.661 |
misses | +0.640 |
crossings | +0.630 |
Neg logit contributions | |
xual | -0.719 |
rolet | -0.663 |
�� | -0.662 |
uana | -0.614 |
orescence | -0.610 |
Token | translated |
Token ID | 14251 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
wipes | +3.652 |
ignores | +3.392 |
ath | +3.228 |
misses | +3.118 |
Typhoon | +3.042 |
Neg logit contributions | |
xual | -3.934 |
�� | -3.688 |
rolet | -3.636 |
orescence | -3.386 |
uana | -3.366 |
Token | to |
Token ID | 284 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
wipes | +0.764 |
ignores | +0.701 |
ath | +0.668 |
misses | +0.644 |
Typhoon | +0.633 |
Neg logit contributions | |
xual | -0.781 |
�� | -0.722 |
rolet | -0.719 |
uana | -0.666 |
orescence | -0.662 |
Token | English |
Token ID | 3594 |
Feature activation | +2.22e-03 |
Pos logit contributions | |
wipes | +0.008 |
ignores | +0.008 |
ath | +0.007 |
misses | +0.007 |
crossings | +0.007 |
Neg logit contributions | |
xual | -0.007 |
rolet | -0.006 |
�� | -0.006 |
uana | -0.006 |
ukong | -0.005 |
Token | by |
Token ID | 416 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
wipes | +0.007 |
ignores | +0.006 |
ath | +0.006 |
misses | +0.006 |
Typhoon | +0.006 |
Neg logit contributions | |
xual | -0.007 |
�� | -0.006 |
rolet | -0.006 |
uana | -0.006 |
orescence | -0.006 |
Token | After |
Token ID | 3260 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
wipes | +0.679 |
ignores | +0.624 |
ath | +0.594 |
misses | +0.574 |
crossings | +0.563 |
Neg logit contributions | |
xual | -0.683 |
rolet | -0.629 |
�� | -0.628 |
uana | -0.584 |
orescence | -0.581 |
Token | ; |
Token ID | 26 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
wipes | +0.265 |
ignores | +0.245 |
ath | +0.235 |
Typhoon | +0.226 |
misses | +0.226 |
Neg logit contributions | |
xual | -0.217 |
rolet | -0.197 |
�� | -0.197 |
orescence | -0.181 |
uana | -0.180 |
Token | as |
Token ID | 355 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
xual | +0.083 |
rolet | +0.076 |
�� | +0.075 |
uana | +0.070 |
orescence | +0.069 |
Neg logit contributions | |
wipes | -0.101 |
ignores | -0.092 |
ath | -0.090 |
Typhoon | -0.086 |
crossings | -0.086 |
Token | Slav |
Token ID | 34314 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
wipes | +0.329 |
ignores | +0.303 |
ath | +0.291 |
misses | +0.281 |
crossings | +0.276 |
Neg logit contributions | |
xual | -0.292 |
�� | -0.270 |
rolet | -0.268 |
uana | -0.247 |
orescence | -0.246 |
Token | oj |
Token ID | 13210 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
wipes | +0.675 |
ignores | +0.595 |
ath | +0.565 |
misses | +0.515 |
Typhoon | +0.509 |
Neg logit contributions | |
xual | -1.463 |
rolet | -1.394 |
�� | -1.392 |
uana | -1.319 |
orescence | -1.312 |
Token | � |
Token ID | 25370 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
xual | +0.095 |
rolet | +0.091 |
�� | +0.088 |
uana | +0.085 |
ancer | +0.084 |
Neg logit contributions | |
wipes | -0.091 |
ignores | -0.082 |
ath | -0.080 |
weak | -0.074 |
successes | -0.074 |
Token | � |
Token ID | 121 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
wipes | +1.164 |
ignores | +1.095 |
ath | +1.026 |
misses | +1.016 |
Typhoon | +0.993 |
Neg logit contributions | |
xual | -1.169 |
rolet | -1.062 |
�� | -1.021 |
orescence | -0.999 |
ukong | -0.998 |
Token | i |
Token ID | 72 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
wipes | +2.925 |
ignores | +2.615 |
ath | +2.464 |
misses | +2.393 |
Typhoon | +2.279 |
Neg logit contributions | |
xual | -4.236 |
�� | -3.985 |
rolet | -3.948 |
orescence | -3.687 |
uana | -3.673 |
Token | � |
Token ID | 129 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
wipes | +0.587 |
ignores | +0.538 |
ath | +0.516 |
misses | +0.492 |
Typhoon | +0.485 |
Neg logit contributions | |
xual | -0.647 |
rolet | -0.605 |
�� | -0.604 |
uana | -0.560 |
orescence | -0.558 |
Token | � |
Token ID | 122 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
wipes | +0.199 |
ignores | +0.185 |
ath | +0.179 |
misses | +0.173 |
Typhoon | +0.173 |
Neg logit contributions | |
xual | -0.138 |
�� | -0.128 |
rolet | -0.124 |
uana | -0.115 |
orescence | -0.111 |
Token | ek |
Token ID | 988 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
wipes | +1.589 |
ignores | +1.466 |
ath | +1.407 |
misses | +1.351 |
Typhoon | +1.334 |
Neg logit contributions | |
xual | -1.506 |
�� | -1.386 |
rolet | -1.378 |
uana | -1.279 |
orescence | -1.271 |
Token | has |
Token ID | 468 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
xual | +0.197 |
�� | +0.184 |
rolet | +0.183 |
uana | +0.170 |
orescence | +0.170 |
Neg logit contributions | |
wipes | -0.157 |
ignores | -0.143 |
ath | -0.138 |
misses | -0.130 |
Typhoon | -0.129 |
Token | the |
Token ID | 262 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
wipes | +0.271 |
ignores | +0.252 |
ath | +0.241 |
misses | +0.232 |
Typhoon | +0.229 |
Neg logit contributions | |
xual | -0.236 |
rolet | -0.215 |
�� | -0.214 |
uana | -0.197 |
orescence | -0.197 |
Token | show |
Token ID | 905 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
xual | +0.250 |
rolet | +0.228 |
�� | +0.227 |
uana | +0.210 |
orescence | +0.209 |
Neg logit contributions | |
wipes | -0.275 |
ignores | -0.257 |
ath | -0.244 |
misses | -0.234 |
Typhoon | -0.232 |
Token | and |
Token ID | 290 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
wipes | +0.594 |
ignores | +0.549 |
ath | +0.526 |
misses | +0.506 |
Typhoon | +0.500 |
Neg logit contributions | |
xual | -0.557 |
rolet | -0.510 |
�� | -0.510 |
uana | -0.470 |
orescence | -0.468 |
Token | give |
Token ID | 1577 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
wipes | +0.219 |
ignores | +0.202 |
ath | +0.193 |
misses | +0.185 |
Typhoon | +0.184 |
Neg logit contributions | |
xual | -0.223 |
rolet | -0.205 |
�� | -0.203 |
uana | -0.189 |
orescence | -0.188 |
Token | a |
Token ID | 257 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
wipes | +0.709 |
ignores | +0.657 |
ath | +0.628 |
misses | +0.605 |
Typhoon | +0.598 |
Neg logit contributions | |
xual | -0.647 |
rolet | -0.591 |
�� | -0.590 |
uana | -0.546 |
orescence | -0.545 |
Token | taste |
Token ID | 6938 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
wipes | +0.536 |
ignores | +0.493 |
ath | +0.469 |
misses | +0.450 |
crossings | +0.446 |
Neg logit contributions | |
xual | -0.533 |
rolet | -0.489 |
�� | -0.487 |
uana | -0.450 |
orescence | -0.449 |
Token | of |
Token ID | 286 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
wipes | +3.095 |
ignores | +2.845 |
ath | +2.727 |
misses | +2.623 |
successes | +2.548 |
Neg logit contributions | |
xual | -3.426 |
�� | -3.224 |
rolet | -3.189 |
uana | -2.971 |
ukong | -2.950 |
Token | who |
Token ID | 508 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
wipes | +0.296 |
ignores | +0.275 |
ath | +0.264 |
misses | +0.254 |
Typhoon | +0.251 |
Neg logit contributions | |
xual | -0.248 |
rolet | -0.225 |
�� | -0.224 |
uana | -0.207 |
orescence | -0.206 |
Token | Sl |
Token ID | 3454 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
wipes | +0.010 |
ignores | +0.009 |
ath | +0.009 |
Typhoon | +0.008 |
misses | +0.008 |
Neg logit contributions | |
xual | -0.009 |
rolet | -0.008 |
�� | -0.008 |
orescence | -0.007 |
uana | -0.007 |
Token | ade |
Token ID | 671 |
Feature activation | +7.03e-03 |
Pos logit contributions | |
wipes | +0.021 |
ignores | +0.019 |
ath | +0.018 |
misses | +0.017 |
Typhoon | +0.017 |
Neg logit contributions | |
xual | -0.026 |
�� | -0.024 |
rolet | -0.024 |
uana | -0.022 |
orescence | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
wipes | +0.020 |
ignores | +0.019 |
ath | +0.018 |
misses | +0.017 |
Typhoon | +0.017 |
Neg logit contributions | |
xual | -0.022 |
�� | -0.021 |
rolet | -0.021 |
uana | -0.019 |
orescence | -0.019 |
Token | ; |
Token ID | 2162 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
wipes | +0.442 |
ignores | +0.397 |
ath | +0.383 |
misses | +0.365 |
Typhoon | +0.363 |
Neg logit contributions | |
xual | -0.512 |
rolet | -0.478 |
�� | -0.471 |
uana | -0.444 |
orescence | -0.441 |
Token | return |
Token ID | 1441 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
wipes | +0.644 |
ignores | +0.586 |
ath | +0.564 |
misses | +0.543 |
Typhoon | +0.529 |
Neg logit contributions | |
xual | -0.715 |
rolet | -0.667 |
�� | -0.656 |
uana | -0.621 |
orescence | -0.616 |
Token | normal |
Token ID | 3487 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
wipes | +1.762 |
ignores | +1.608 |
ath | +1.540 |
misses | +1.478 |
Typhoon | +1.456 |
Neg logit contributions | |
xual | -1.883 |
rolet | -1.738 |
�� | -1.733 |
uana | -1.625 |
orescence | -1.616 |
Token | ; |
Token ID | 2162 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
xual | +0.100 |
rolet | +0.093 |
�� | +0.091 |
uana | +0.088 |
orescence | +0.087 |
Neg logit contributions | |
wipes | -0.085 |
ignores | -0.076 |
ath | -0.073 |
misses | -0.070 |
Typhoon | -0.069 |
Token | # |
Token ID | 1303 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
wipes | +0.276 |
ignores | +0.250 |
ath | +0.241 |
misses | +0.232 |
Typhoon | +0.228 |
Neg logit contributions | |
xual | -0.287 |
rolet | -0.265 |
�� | -0.263 |
uana | -0.247 |
orescence | -0.245 |
Token | endif |
Token ID | 32088 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
wipes | +1.315 |
ignores | +1.173 |
ath | +1.116 |
misses | +1.057 |
Typhoon | +1.041 |
Neg logit contributions | |
xual | -2.084 |
rolet | -1.960 |
�� | -1.957 |
uana | -1.846 |
orescence | -1.836 |
Token | } |
Token ID | 1782 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
wipes | +3.123 |
ignores | +2.872 |
ath | +2.746 |
misses | +2.635 |
Typhoon | +2.585 |
Neg logit contributions | |
xual | -3.361 |
�� | -3.119 |
rolet | -3.104 |
uana | -2.876 |
orescence | -2.870 |
Token | If |
Token ID | 1002 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
wipes | +1.005 |
ignores | +0.921 |
ath | +0.885 |
misses | +0.855 |
Typhoon | +0.833 |
Neg logit contributions | |
xual | -1.049 |
rolet | -0.975 |
�� | -0.968 |
uana | -0.908 |
orescence | -0.895 |
Token | you |
Token ID | 345 |
Feature activation | -4.78e-03 |
Pos logit contributions | |
wipes | +0.501 |
ignores | +0.460 |
ath | +0.439 |
misses | +0.422 |
crossings | +0.417 |
Neg logit contributions | |
xual | -0.506 |
�� | -0.471 |
rolet | -0.469 |
uana | -0.442 |
orescence | -0.432 |
Token | are |
Token ID | 389 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
xual | +0.014 |
rolet | +0.013 |
�� | +0.013 |
uana | +0.012 |
ukong | +0.012 |
Neg logit contributions | |
wipes | -0.014 |
ignores | -0.013 |
ath | -0.013 |
misses | -0.012 |
Typhoon | -0.012 |
Token | curious |
Token ID | 11040 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
xual | +0.178 |
�� | +0.164 |
rolet | +0.161 |
uana | +0.153 |
ancer | +0.150 |
Neg logit contributions | |
wipes | -0.184 |
ignores | -0.168 |
ath | -0.160 |
misses | -0.154 |
Typhoon | -0.152 |
Token | to |
Token ID | 284 |
Feature activation | +8.99e-04 |
Pos logit contributions | |
wipes | +0.690 |
ignores | +0.641 |
ath | +0.617 |
misses | +0.594 |
Typhoon | +0.579 |
Neg logit contributions | |
xual | -0.763 |
�� | -0.724 |
rolet | -0.701 |
orescence | -0.657 |
uana | -0.651 |
Token | Reuters |
Token ID | 8428 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
wipes | +0.003 |
ignores | +0.003 |
ath | +0.003 |
misses | +0.002 |
crossings | +0.002 |
Neg logit contributions | |
xual | -0.003 |
rolet | -0.002 |
�� | -0.002 |
uana | -0.002 |
orescence | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
wipes | +0.482 |
ignores | +0.448 |
ath | +0.428 |
misses | +0.412 |
Typhoon | +0.404 |
Neg logit contributions | |
xual | -0.460 |
�� | -0.421 |
rolet | -0.420 |
uana | -0.388 |
orescence | -0.388 |
Token |
|
Token ID | 198 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
wipes | +0.616 |
ignores | +0.563 |
ath | +0.533 |
misses | +0.513 |
crossings | +0.507 |
Neg logit contributions | |
xual | -0.732 |
rolet | -0.682 |
�� | -0.677 |
uana | -0.630 |
orescence | -0.630 |
Token |
|
Token ID | 198 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
wipes | +0.713 |
ignores | +0.649 |
ath | +0.617 |
misses | +0.590 |
Typhoon | +0.570 |
Neg logit contributions | |
xual | -1.165 |
�� | -1.112 |
rolet | -1.075 |
orescence | -1.021 |
uana | -1.013 |
Token | ADVERTISEMENT |
Token ID | 19053 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
wipes | +0.583 |
ignores | +0.527 |
ath | +0.498 |
misses | +0.476 |
crossings | +0.466 |
Neg logit contributions | |
xual | -0.806 |
rolet | -0.756 |
�� | -0.754 |
uana | -0.709 |
orescence | -0.704 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
wipes | +2.527 |
ignores | +2.291 |
ath | +2.176 |
misses | +2.076 |
Typhoon | +2.030 |
Neg logit contributions | |
xual | -3.432 |
�� | -3.212 |
rolet | -3.204 |
uana | -2.993 |
orescence | -2.982 |
Token |
|
Token ID | 198 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
xual | +0.563 |
�� | +0.527 |
rolet | +0.525 |
uana | +0.491 |
orescence | +0.490 |
Neg logit contributions | |
wipes | -0.405 |
ignores | -0.367 |
ath | -0.348 |
misses | -0.332 |
Typhoon | -0.325 |
Token | Twenty |
Token ID | 34096 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
xual | +0.633 |
rolet | +0.598 |
�� | +0.592 |
uana | +0.562 |
ukong | +0.556 |
Neg logit contributions | |
wipes | -0.502 |
ignores | -0.454 |
ath | -0.426 |
misses | -0.411 |
crossings | -0.408 |
Token | - |
Token ID | 12 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
wipes | +0.161 |
ignores | +0.150 |
ath | +0.143 |
misses | +0.138 |
Typhoon | +0.135 |
Neg logit contributions | |
xual | -0.144 |
rolet | -0.132 |
�� | -0.132 |
orescence | -0.121 |
ancer | -0.120 |
Token | three |
Token ID | 15542 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
wipes | +0.419 |
ignores | +0.381 |
ath | +0.363 |
misses | +0.345 |
Typhoon | +0.338 |
Neg logit contributions | |
xual | -0.546 |
rolet | -0.510 |
�� | -0.506 |
uana | -0.478 |
orescence | -0.473 |
Token | terrible |
Token ID | 7818 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
wipes | +0.208 |
ignores | +0.196 |
ath | +0.187 |
misses | +0.179 |
crossings | +0.177 |
Neg logit contributions | |
xual | -0.181 |
�� | -0.165 |
rolet | -0.164 |
uana | -0.153 |
ukong | -0.151 |
Token | w |
Token ID | 266 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
xual | +0.660 |
rolet | +0.606 |
�� | +0.604 |
uana | +0.574 |
ukong | +0.568 |
Neg logit contributions | |
wipes | -0.735 |
ignores | -0.684 |
ath | -0.647 |
misses | -0.618 |
eworks | -0.616 |
Token | icket |
Token ID | 9715 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
xual | +0.232 |
rolet | +0.215 |
�� | +0.215 |
uana | +0.205 |
enture | +0.204 |
Neg logit contributions | |
wipes | -0.187 |
ignores | -0.169 |
ath | -0.159 |
misses | -0.154 |
crossings | -0.152 |
Token | and |
Token ID | 290 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
xual | +0.620 |
rolet | +0.566 |
�� | +0.565 |
uana | +0.528 |
orescence | +0.523 |
Neg logit contributions | |
wipes | -0.648 |
ignores | -0.601 |
ath | -0.573 |
misses | -0.552 |
Typhoon | -0.548 |
Token | as |
Token ID | 355 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
xual | +0.404 |
rolet | +0.372 |
�� | +0.366 |
uana | +0.351 |
ancer | +0.342 |
Neg logit contributions | |
wipes | -0.449 |
ignores | -0.416 |
ath | -0.400 |
Typhoon | -0.379 |
weak | -0.377 |
Token | soon |
Token ID | 2582 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
wipes | +0.535 |
ignores | +0.498 |
ath | +0.479 |
misses | +0.461 |
Typhoon | +0.453 |
Neg logit contributions | |
xual | -0.426 |
�� | -0.390 |
rolet | -0.388 |
uana | -0.359 |
orescence | -0.354 |
Token | as |
Token ID | 355 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
wipes | +3.008 |
ignores | +2.785 |
ath | +2.650 |
misses | +2.607 |
crossings | +2.509 |
Neg logit contributions | |
xual | -2.998 |
�� | -2.869 |
rolet | -2.777 |
orescence | -2.515 |
uana | -2.500 |
Token | you |
Token ID | 345 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
xual | +0.066 |
rolet | +0.060 |
�� | +0.060 |
uana | +0.057 |
orescence | +0.056 |
Neg logit contributions | |
wipes | -0.080 |
ignores | -0.075 |
ath | -0.072 |
misses | -0.068 |
Typhoon | -0.068 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
wipes | +0.764 |
ignores | +0.701 |
ath | +0.669 |
misses | +0.638 |
Typhoon | +0.634 |
Neg logit contributions | |
xual | -0.870 |
rolet | -0.813 |
�� | -0.804 |
uana | -0.759 |
orescence | -0.751 |
Token | at |
Token ID | 379 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
wipes | +0.326 |
ignores | +0.303 |
ath | +0.287 |
misses | +0.276 |
Typhoon | +0.274 |
Neg logit contributions | |
xual | -0.304 |
�� | -0.280 |
rolet | -0.279 |
uana | -0.260 |
orescence | -0.257 |
Token | the |
Token ID | 262 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
wipes | +0.242 |
ignores | +0.227 |
ath | +0.218 |
misses | +0.207 |
Typhoon | +0.207 |
Neg logit contributions | |
xual | -0.183 |
rolet | -0.166 |
�� | -0.165 |
uana | -0.155 |
orescence | -0.153 |
Token | . |
Token ID | 13 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
wipes | +0.274 |
ignores | +0.252 |
ath | +0.242 |
misses | +0.233 |
Typhoon | +0.230 |
Neg logit contributions | |
xual | -0.262 |
�� | -0.241 |
rolet | -0.241 |
uana | -0.222 |
orescence | -0.222 |
Token | When |
Token ID | 1649 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
wipes | +0.256 |
ignores | +0.232 |
ath | +0.222 |
misses | +0.213 |
crossings | +0.212 |
Neg logit contributions | |
xual | -0.266 |
rolet | -0.247 |
�� | -0.245 |
uana | -0.228 |
orescence | -0.226 |
Token | Trump |
Token ID | 1301 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
wipes | +0.657 |
ignores | +0.605 |
ath | +0.584 |
misses | +0.560 |
weak | +0.547 |
Neg logit contributions | |
xual | -0.595 |
�� | -0.546 |
rolet | -0.538 |
uana | -0.509 |
orescence | -0.501 |
Token | named |
Token ID | 3706 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
xual | +0.012 |
rolet | +0.011 |
�� | +0.011 |
uana | +0.011 |
orescence | +0.010 |
Neg logit contributions | |
wipes | -0.011 |
ignores | -0.010 |
ath | -0.010 |
misses | -0.009 |
Typhoon | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
xual | +0.181 |
�� | +0.168 |
rolet | +0.166 |
uana | +0.154 |
ancer | +0.154 |
Neg logit contributions | |
wipes | -0.196 |
ignores | -0.181 |
ath | -0.172 |
misses | -0.165 |
weak | -0.161 |
Token | vice |
Token ID | 7927 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
wipes | +0.949 |
ignores | +0.875 |
ath | +0.829 |
misses | +0.798 |
weak | +0.784 |
Neg logit contributions | |
xual | -0.936 |
�� | -0.866 |
rolet | -0.865 |
uana | -0.803 |
ancer | -0.799 |
Token | presidential |
Token ID | 4787 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
wipes | +2.679 |
ignores | +2.448 |
ath | +2.332 |
misses | +2.236 |
Typhoon | +2.190 |
Neg logit contributions | |
xual | -3.170 |
�� | -2.964 |
rolet | -2.946 |
uana | -2.740 |
orescence | -2.733 |
Token | pick |
Token ID | 2298 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
wipes | +0.404 |
ignores | +0.370 |
ath | +0.352 |
misses | +0.335 |
weak | +0.333 |
Neg logit contributions | |
xual | -0.470 |
�� | -0.435 |
rolet | -0.433 |
ancer | -0.409 |
uana | -0.407 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
wipes | +0.307 |
ignores | +0.282 |
ath | +0.271 |
misses | +0.261 |
Typhoon | +0.256 |
Neg logit contributions | |
xual | -0.287 |
�� | -0.265 |
rolet | -0.263 |
uana | -0.243 |
orescence | -0.241 |
Token | Gov |
Token ID | 10964 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
wipes | +0.397 |
ignores | +0.363 |
ath | +0.349 |
misses | +0.335 |
successes | +0.328 |
Neg logit contributions | |
xual | -0.384 |
�� | -0.357 |
rolet | -0.352 |
uana | -0.328 |
orescence | -0.326 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
xual | +0.374 |
�� | +0.345 |
rolet | +0.343 |
uana | +0.317 |
orescence | +0.316 |
Neg logit contributions | |
wipes | -0.358 |
ignores | -0.330 |
ath | -0.317 |
misses | -0.304 |
Typhoon | -0.298 |
Token | published |
Token ID | 3199 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
xual | +0.316 |
rolet | +0.286 |
�� | +0.284 |
uana | +0.266 |
orescence | +0.264 |
Neg logit contributions | |
wipes | -0.337 |
ignores | -0.312 |
ath | -0.298 |
misses | -0.288 |
Typhoon | -0.284 |
Token | by |
Token ID | 416 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
xual | +0.671 |
rolet | +0.603 |
�� | +0.596 |
enture | +0.555 |
orescence | +0.555 |
Neg logit contributions | |
wipes | -0.697 |
ignores | -0.644 |
ath | -0.612 |
misses | -0.596 |
Typhoon | -0.588 |
Token | Danish |
Token ID | 20849 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
wipes | +0.861 |
ignores | +0.801 |
ath | +0.762 |
misses | +0.739 |
crossings | +0.723 |
Neg logit contributions | |
xual | -0.756 |
�� | -0.692 |
rolet | -0.689 |
orescence | -0.637 |
uana | -0.634 |
Token | newspaper |
Token ID | 7533 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
wipes | +1.162 |
ignores | +1.071 |
ath | +1.022 |
misses | +0.985 |
successes | +0.959 |
Neg logit contributions | |
xual | -1.214 |
�� | -1.136 |
rolet | -1.114 |
orescence | -1.039 |
uana | -1.039 |
Token | J |
Token ID | 449 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
wipes | +0.190 |
ignores | +0.176 |
ath | +0.167 |
misses | +0.163 |
crossings | +0.160 |
Neg logit contributions | |
xual | -0.168 |
�� | -0.154 |
rolet | -0.150 |
orescence | -0.141 |
uana | -0.139 |
Token | yll |
Token ID | 25727 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
wipes | +0.498 |
ignores | +0.448 |
ath | +0.425 |
misses | +0.405 |
Typhoon | +0.405 |
Neg logit contributions | |
xual | -0.674 |
rolet | -0.631 |
�� | -0.627 |
uana | -0.599 |
orescence | -0.590 |
Token | ands |
Token ID | 1746 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
wipes | +2.995 |
ignores | +2.769 |
ath | +2.658 |
misses | +2.561 |
Typhoon | +2.516 |
Neg logit contributions | |
xual | -2.775 |
�� | -2.558 |
rolet | -2.548 |
uana | -2.346 |
orescence | -2.339 |
Token | - |
Token ID | 12 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
xual | +0.087 |
�� | +0.080 |
rolet | +0.079 |
uana | +0.073 |
enture | +0.073 |
Neg logit contributions | |
wipes | -0.102 |
ignores | -0.094 |
ath | -0.091 |
misses | -0.087 |
crossings | -0.086 |
Token | Post |
Token ID | 6307 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
wipes | +0.314 |
ignores | +0.291 |
ath | +0.285 |
Typhoon | +0.265 |
misses | +0.264 |
Neg logit contributions | |
xual | -0.286 |
rolet | -0.273 |
�� | -0.271 |
uana | -0.254 |
enture | -0.253 |
Token | en |
Token ID | 268 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
wipes | +1.002 |
ignores | +0.941 |
ath | +0.911 |
misses | +0.880 |
crossings | +0.868 |
Neg logit contributions | |
xual | -0.614 |
�� | -0.552 |
rolet | -0.551 |
uana | -0.494 |
orescence | -0.487 |
Token | in |
Token ID | 259 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
wipes | +0.510 |
ignores | +0.471 |
ath | +0.451 |
misses | +0.434 |
Typhoon | +0.426 |
Neg logit contributions | |
xual | -0.503 |
�� | -0.463 |
rolet | -0.461 |
uana | -0.426 |
orescence | -0.425 |
Token | r |
Token ID | 81 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
wipes | +0.619 |
ignores | +0.571 |
ath | +0.550 |
misses | +0.529 |
Typhoon | +0.523 |
Neg logit contributions | |
xual | -0.562 |
rolet | -0.522 |
�� | -0.510 |
uana | -0.482 |
orescence | -0.475 |
Token | mann |
Token ID | 9038 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
xual | +0.958 |
rolet | +0.885 |
�� | +0.872 |
uana | +0.814 |
ault | +0.814 |
Neg logit contributions | |
wipes | -1.310 |
ignores | -1.219 |
ath | -1.186 |
Typhoon | -1.138 |
Nato | -1.128 |
Token | 's |
Token ID | 338 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
xual | +1.321 |
rolet | +1.217 |
�� | +1.211 |
ancer | +1.123 |
orescence | +1.122 |
Neg logit contributions | |
wipes | -1.321 |
ignores | -1.214 |
ath | -1.186 |
Typhoon | -1.130 |
crossings | -1.116 |
Token | score |
Token ID | 4776 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
wipes | +0.321 |
ignores | +0.295 |
ath | +0.283 |
misses | +0.271 |
crossings | +0.266 |
Neg logit contributions | |
xual | -0.311 |
rolet | -0.289 |
�� | -0.288 |
uana | -0.268 |
orescence | -0.266 |
Token | for |
Token ID | 329 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
wipes | +0.391 |
ignores | +0.358 |
ath | +0.345 |
misses | +0.328 |
Typhoon | +0.328 |
Neg logit contributions | |
xual | -0.426 |
rolet | -0.393 |
�� | -0.390 |
orescence | -0.365 |
uana | -0.364 |
Token | Psych |
Token ID | 31923 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
wipes | +0.155 |
ignores | +0.143 |
ath | +0.137 |
misses | +0.132 |
Typhoon | +0.129 |
Neg logit contributions | |
xual | -0.142 |
�� | -0.131 |
rolet | -0.131 |
uana | -0.120 |
orescence | -0.120 |
Token | o |
Token ID | 78 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
wipes | +2.725 |
ignores | +2.539 |
ath | +2.417 |
misses | +2.315 |
successes | +2.273 |
Neg logit contributions | |
xual | -3.040 |
�� | -2.844 |
rolet | -2.696 |
orescence | -2.511 |
uana | -2.506 |
Token | is |
Token ID | 318 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
xual | +0.077 |
rolet | +0.072 |
�� | +0.071 |
orescence | +0.066 |
uana | +0.066 |
Neg logit contributions | |
wipes | -0.070 |
ignores | -0.063 |
ath | -0.062 |
Typhoon | -0.058 |
misses | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
xual | +0.536 |
rolet | +0.497 |
�� | +0.493 |
uana | +0.458 |
orescence | +0.455 |
Neg logit contributions | |
wipes | -0.582 |
ignores | -0.534 |
ath | -0.510 |
misses | -0.493 |
crossings | -0.488 |
Token | fore |
Token ID | 1674 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
xual | +0.186 |
rolet | +0.171 |
�� | +0.169 |
orescence | +0.157 |
uana | +0.157 |
Neg logit contributions | |
wipes | -0.184 |
ignores | -0.169 |
ath | -0.161 |
misses | -0.153 |
crossings | -0.153 |
Token | b |
Token ID | 65 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
wipes | +0.432 |
ignores | +0.401 |
ath | +0.379 |
crossings | +0.368 |
misses | +0.366 |
Neg logit contributions | |
xual | -0.389 |
rolet | -0.359 |
�� | -0.352 |
ancer | -0.329 |
uana | -0.327 |
Token | group |
Token ID | 1448 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
xual | +0.610 |
rolet | +0.565 |
�� | +0.561 |
orescence | +0.523 |
uana | +0.523 |
Neg logit contributions | |
wipes | -0.700 |
ignores | -0.650 |
ath | -0.613 |
misses | -0.599 |
Typhoon | -0.585 |
Token | Raqqa |
Token ID | 30391 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
xual | +0.608 |
rolet | +0.559 |
�� | +0.557 |
uana | +0.521 |
orescence | +0.520 |
Neg logit contributions | |
wipes | -0.634 |
ignores | -0.583 |
ath | -0.552 |
misses | -0.536 |
weak | -0.526 |
Token | is |
Token ID | 318 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
wipes | +0.608 |
ignores | +0.561 |
ath | +0.538 |
misses | +0.518 |
Typhoon | +0.509 |
Neg logit contributions | |
xual | -0.573 |
�� | -0.528 |
rolet | -0.528 |
uana | -0.488 |
orescence | -0.484 |
Token | Being |
Token ID | 11204 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
wipes | +0.448 |
ignores | +0.418 |
ath | +0.403 |
misses | +0.391 |
Typhoon | +0.387 |
Neg logit contributions | |
xual | -0.280 |
�� | -0.254 |
rolet | -0.253 |
uana | -0.228 |
orescence | -0.225 |
Token | Sl |
Token ID | 3454 |
Feature activation | +3.41e-03 |
Pos logit contributions | |
wipes | +0.057 |
ignores | +0.052 |
ath | +0.050 |
misses | +0.048 |
Typhoon | +0.047 |
Neg logit contributions | |
xual | -0.063 |
�� | -0.059 |
rolet | -0.058 |
uana | -0.054 |
orescence | -0.054 |
Token | aughtered |
Token ID | 32734 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
wipes | +0.010 |
ignores | +0.010 |
ath | +0.009 |
misses | +0.009 |
crossings | +0.009 |
Neg logit contributions | |
xual | -0.010 |
rolet | -0.009 |
�� | -0.009 |
uana | -0.009 |
orescence | -0.009 |
Token | Sil |
Token ID | 4243 |
Feature activation | -9.55e-03 |
Pos logit contributions | |
wipes | +1.825 |
ignores | +1.618 |
ath | +1.503 |
Typhoon | +1.396 |
misses | +1.395 |
Neg logit contributions | |
xual | -3.794 |
�� | -3.571 |
rolet | -3.558 |
uana | -3.384 |
orescence | -3.383 |
Token | ently |
Token ID | 1473 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
xual | +0.027 |
�� | +0.025 |
rolet | +0.025 |
orescence | +0.023 |
uana | +0.023 |
Neg logit contributions | |
wipes | -0.031 |
ignores | -0.029 |
ath | -0.028 |
misses | -0.027 |
Typhoon | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
wipes | +0.385 |
ignores | +0.355 |
ath | +0.339 |
misses | +0.328 |
Typhoon | +0.321 |
Neg logit contributions | |
xual | -0.358 |
�� | -0.330 |
rolet | -0.328 |
uana | -0.302 |
orescence | -0.302 |
Token |
|
Token ID | 198 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
wipes | +0.161 |
ignores | +0.147 |
ath | +0.140 |
misses | +0.135 |
successes | +0.133 |
Neg logit contributions | |
xual | -0.180 |
rolet | -0.168 |
�� | -0.168 |
uana | -0.155 |
ancer | -0.155 |
Token |
|
Token ID | 198 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
wipes | +0.738 |
ignores | +0.672 |
ath | +0.639 |
misses | +0.610 |
Typhoon | +0.591 |
Neg logit contributions | |
xual | -1.190 |
�� | -1.136 |
rolet | -1.101 |
orescence | -1.044 |
uana | -1.036 |
Token | Hayes |
Token ID | 25109 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
xual | +0.272 |
rolet | +0.248 |
�� | +0.248 |
uana | +0.234 |
ukong | +0.233 |
Neg logit contributions | |
wipes | -0.247 |
ignores | -0.225 |
ath | -0.219 |
Typhoon | -0.208 |
eworks | -0.206 |
Token | at |
Token ID | 379 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
xual | +0.098 |
rolet | +0.089 |
�� | +0.089 |
uana | +0.084 |
orescence | +0.084 |
Neg logit contributions | |
wipes | -0.079 |
ignores | -0.072 |
ath | -0.069 |
Typhoon | -0.066 |
Nato | -0.065 |
Token | nickel |
Token ID | 30666 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
xual | +0.163 |
rolet | +0.149 |
�� | +0.148 |
ukong | +0.138 |
uana | +0.138 |
Neg logit contributions | |
wipes | -0.183 |
ignores | -0.170 |
ath | -0.159 |
misses | -0.154 |
crossings | -0.152 |
Token | ( |
Token ID | 357 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
wipes | +0.424 |
ignores | +0.390 |
ath | +0.375 |
misses | +0.359 |
Typhoon | +0.354 |
Neg logit contributions | |
xual | -0.409 |
rolet | -0.377 |
�� | -0.377 |
orescence | -0.346 |
uana | -0.346 |
Token | or |
Token ID | 273 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
xual | +0.018 |
rolet | +0.017 |
�� | +0.017 |
uana | +0.016 |
ukong | +0.016 |
Neg logit contributions | |
wipes | -0.016 |
ignores | -0.014 |
ath | -0.014 |
misses | -0.013 |
Typhoon | -0.013 |
Token | vice |
Token ID | 7927 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
wipes | +0.150 |
ignores | +0.137 |
ath | +0.131 |
misses | +0.126 |
successes | +0.125 |
Neg logit contributions | |
xual | -0.145 |
rolet | -0.133 |
�� | -0.132 |
uana | -0.123 |
ukong | -0.123 |
Token | versa |
Token ID | 25470 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
wipes | +3.013 |
ignores | +2.795 |
ath | +2.686 |
misses | +2.599 |
Typhoon | +2.558 |
Neg logit contributions | |
xual | -2.470 |
�� | -2.266 |
rolet | -2.259 |
orescence | -2.063 |
uana | -2.062 |
Token | ), |
Token ID | 828 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
wipes | +0.206 |
ignores | +0.189 |
ath | +0.182 |
misses | +0.175 |
Typhoon | +0.175 |
Neg logit contributions | |
xual | -0.174 |
rolet | -0.159 |
�� | -0.158 |
uana | -0.145 |
orescence | -0.145 |
Token | then |
Token ID | 788 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
wipes | +0.124 |
ignores | +0.114 |
ath | +0.110 |
Typhoon | +0.105 |
misses | +0.105 |
Neg logit contributions | |
xual | -0.110 |
rolet | -0.100 |
�� | -0.099 |
uana | -0.093 |
ukong | -0.092 |
Token | the |
Token ID | 262 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
xual | +0.142 |
rolet | +0.128 |
�� | +0.128 |
uana | +0.119 |
ukong | +0.119 |
Neg logit contributions | |
wipes | -0.161 |
ignores | -0.148 |
ath | -0.144 |
Typhoon | -0.136 |
misses | -0.136 |
Token | following |
Token ID | 1708 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
xual | +0.634 |
rolet | +0.581 |
�� | +0.580 |
uana | +0.546 |
ukong | +0.545 |
Neg logit contributions | |
wipes | -0.625 |
ignores | -0.576 |
ath | -0.545 |
misses | -0.515 |
eworks | -0.513 |
Token | on |
Token ID | 319 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
wipes | +0.003 |
ignores | +0.003 |
ath | +0.002 |
misses | +0.002 |
crossings | +0.002 |
Neg logit contributions | |
xual | -0.003 |
�� | -0.003 |
rolet | -0.003 |
orescence | -0.002 |
uana | -0.002 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
wipes | +0.605 |
ignores | +0.560 |
ath | +0.535 |
misses | +0.518 |
Typhoon | +0.508 |
Neg logit contributions | |
xual | -0.588 |
rolet | -0.547 |
�� | -0.544 |
orescence | -0.503 |
uana | -0.503 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
wipes | +0.123 |
ignores | +0.113 |
ath | +0.108 |
misses | +0.105 |
successes | +0.103 |
Neg logit contributions | |
xual | -0.116 |
�� | -0.108 |
rolet | -0.108 |
uana | -0.099 |
ancer | -0.099 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
xual | +0.054 |
rolet | +0.050 |
�� | +0.049 |
uana | +0.045 |
orescence | +0.044 |
Neg logit contributions | |
wipes | -0.076 |
ignores | -0.070 |
ath | -0.067 |
misses | -0.065 |
crossings | -0.065 |
Token | Media |
Token ID | 13152 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
wipes | +0.650 |
ignores | +0.587 |
ath | +0.556 |
misses | +0.534 |
crossings | +0.526 |
Neg logit contributions | |
xual | -0.822 |
rolet | -0.771 |
�� | -0.769 |
uana | -0.725 |
ukong | -0.718 |
Token | playback |
Token ID | 16388 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
xual | +0.628 |
�� | +0.581 |
rolet | +0.573 |
uana | +0.511 |
enture | +0.510 |
Neg logit contributions | |
wipes | -1.213 |
ignores | -1.132 |
ath | -1.108 |
misses | -1.062 |
Nato | -1.058 |
Token | is |
Token ID | 318 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
wipes | +2.056 |
ignores | +1.884 |
ath | +1.740 |
misses | +1.711 |
Nato | +1.619 |
Neg logit contributions | |
xual | -3.321 |
�� | -3.204 |
rolet | -3.137 |
uana | -2.927 |
enture | -2.922 |
Token | unsupported |
Token ID | 24222 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
xual | +0.687 |
�� | +0.644 |
rolet | +0.642 |
uana | +0.606 |
orescence | +0.602 |
Neg logit contributions | |
wipes | -0.479 |
ignores | -0.426 |
ath | -0.402 |
misses | -0.380 |
crossings | -0.378 |
Token | on |
Token ID | 319 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
wipes | +1.205 |
ignores | +1.106 |
ath | +1.060 |
misses | +1.011 |
Typhoon | +0.989 |
Neg logit contributions | |
xual | -1.456 |
�� | -1.375 |
rolet | -1.349 |
uana | -1.255 |
orescence | -1.255 |
Token | your |
Token ID | 534 |
Feature activation | -1.15e-04 |
Pos logit contributions | |
wipes | +0.438 |
ignores | +0.401 |
ath | +0.381 |
misses | +0.365 |
crossings | +0.358 |
Neg logit contributions | |
xual | -0.514 |
rolet | -0.475 |
�� | -0.474 |
uana | -0.445 |
orescence | -0.442 |
Token | device |
Token ID | 3335 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
xual | +0.000 |
�� | +0.000 |
rolet | +0.000 |
uana | +0.000 |
orescence | +0.000 |
Neg logit contributions | |
wipes | -0.000 |
ignores | -0.000 |
ath | -0.000 |
misses | -0.000 |
Typhoon | -0.000 |
Token | performances |
Token ID | 13289 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
wipes | +0.364 |
ignores | +0.337 |
ath | +0.323 |
misses | +0.309 |
Typhoon | +0.307 |
Neg logit contributions | |
xual | -0.342 |
rolet | -0.315 |
�� | -0.314 |
orescence | -0.291 |
uana | -0.291 |
Token | as |
Token ID | 355 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
xual | +0.067 |
rolet | +0.061 |
�� | +0.061 |
uana | +0.056 |
orescence | +0.056 |
Neg logit contributions | |
wipes | -0.072 |
ignores | -0.067 |
ath | -0.064 |
misses | -0.061 |
Typhoon | -0.061 |
Token | two |
Token ID | 734 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
xual | +0.493 |
�� | +0.454 |
rolet | +0.452 |
uana | +0.422 |
orescence | +0.419 |
Neg logit contributions | |
wipes | -0.531 |
ignores | -0.491 |
ath | -0.469 |
misses | -0.452 |
Typhoon | -0.448 |
Token | women |
Token ID | 1466 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
xual | +0.168 |
�� | +0.154 |
rolet | +0.153 |
uana | +0.143 |
orescence | +0.142 |
Neg logit contributions | |
wipes | -0.175 |
ignores | -0.162 |
ath | -0.154 |
misses | -0.148 |
Typhoon | -0.148 |
Token | at |
Token ID | 379 |
Feature activation | +7.36e-05 |
Pos logit contributions | |
wipes | +1.691 |
ignores | +1.569 |
ath | +1.509 |
misses | +1.456 |
Typhoon | +1.433 |
Neg logit contributions | |
xual | -1.423 |
�� | -1.307 |
rolet | -1.301 |
uana | -1.193 |
orescence | -1.188 |
Token | opposite |
Token ID | 6697 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
wipes | +0.000 |
ignores | +0.000 |
ath | +0.000 |
misses | +0.000 |
Typhoon | +0.000 |
Neg logit contributions | |
xual | -0.000 |
rolet | -0.000 |
�� | -0.000 |
uana | -0.000 |
orescence | -0.000 |
Token | ends |
Token ID | 5645 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
wipes | +1.752 |
ignores | +1.543 |
ath | +1.439 |
misses | +1.350 |
Typhoon | +1.304 |
Neg logit contributions | |
xual | -3.603 |
�� | -3.404 |
rolet | -3.395 |
uana | -3.205 |
orescence | -3.198 |
Token | of |
Token ID | 286 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
wipes | +0.966 |
ignores | +0.889 |
ath | +0.851 |
misses | +0.818 |
Typhoon | +0.801 |
Neg logit contributions | |
xual | -1.010 |
�� | -0.936 |
rolet | -0.933 |
uana | -0.864 |
orescence | -0.861 |
Token | the |
Token ID | 262 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
wipes | +0.402 |
ignores | +0.376 |
ath | +0.361 |
misses | +0.351 |
Typhoon | +0.347 |
Neg logit contributions | |
xual | -0.278 |
rolet | -0.251 |
�� | -0.250 |
orescence | -0.228 |
uana | -0.227 |
Token | gratification |
Token ID | 47459 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
wipes | +0.374 |
ignores | +0.347 |
ath | +0.331 |
misses | +0.320 |
Typhoon | +0.315 |
Neg logit contributions | |
xual | -0.347 |
�� | -0.318 |
rolet | -0.317 |
uana | -0.293 |
orescence | -0.293 |
Token | spectrum |
Token ID | 10958 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
xual | +0.045 |
�� | +0.041 |
rolet | +0.041 |
orescence | +0.038 |
uana | +0.038 |
Neg logit contributions | |
wipes | -0.043 |
ignores | -0.040 |
ath | -0.038 |
misses | -0.037 |
Typhoon | -0.036 |
Token | be |
Token ID | 307 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
wipes | +0.142 |
ignores | +0.130 |
ath | +0.125 |
misses | +0.120 |
Typhoon | +0.119 |
Neg logit contributions | |
xual | -0.147 |
rolet | -0.136 |
�� | -0.133 |
uana | -0.126 |
orescence | -0.125 |
Token | chosen |
Token ID | 7147 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
wipes | +0.037 |
ignores | +0.034 |
ath | +0.032 |
misses | +0.031 |
Typhoon | +0.031 |
Neg logit contributions | |
xual | -0.035 |
�� | -0.033 |
rolet | -0.032 |
uana | -0.030 |
orescence | -0.030 |
Token | as |
Token ID | 355 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
xual | +0.367 |
rolet | +0.337 |
�� | +0.336 |
uana | +0.305 |
orescence | +0.304 |
Neg logit contributions | |
wipes | -0.454 |
ignores | -0.419 |
ath | -0.401 |
misses | -0.391 |
Typhoon | -0.386 |
Token | Romney |
Token ID | 8431 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
xual | +0.180 |
�� | +0.170 |
rolet | +0.166 |
ancer | +0.152 |
orescence | +0.151 |
Neg logit contributions | |
wipes | -0.254 |
ignores | -0.237 |
ath | -0.226 |
misses | -0.219 |
crossings | -0.218 |
Token | 's |
Token ID | 338 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
wipes | +0.365 |
ignores | +0.336 |
ath | +0.329 |
Typhoon | +0.314 |
misses | +0.313 |
Neg logit contributions | |
xual | -0.294 |
�� | -0.275 |
rolet | -0.267 |
ancer | -0.251 |
uana | -0.248 |
Token | vice |
Token ID | 7927 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
wipes | +0.555 |
ignores | +0.513 |
ath | +0.492 |
misses | +0.471 |
Typhoon | +0.468 |
Neg logit contributions | |
xual | -0.444 |
�� | -0.408 |
rolet | -0.407 |
ancer | -0.375 |
uana | -0.375 |
Token | presidential |
Token ID | 4787 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
wipes | +2.403 |
ignores | +2.192 |
ath | +2.083 |
misses | +2.000 |
Typhoon | +1.960 |
Neg logit contributions | |
xual | -2.897 |
�� | -2.717 |
rolet | -2.699 |
uana | -2.513 |
orescence | -2.505 |
Token | candidate |
Token ID | 4540 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
wipes | +0.046 |
ignores | +0.042 |
ath | +0.041 |
misses | +0.039 |
Typhoon | +0.039 |
Neg logit contributions | |
xual | -0.041 |
�� | -0.037 |
rolet | -0.037 |
ancer | -0.035 |
uana | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +7.37e-03 |
Pos logit contributions | |
wipes | +0.194 |
ignores | +0.179 |
ath | +0.171 |
misses | +0.166 |
Typhoon | +0.164 |
Neg logit contributions | |
xual | -0.182 |
rolet | -0.166 |
�� | -0.166 |
uana | -0.154 |
orescence | -0.152 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
wipes | +0.021 |
ignores | +0.019 |
ath | +0.018 |
crossings | +0.018 |
misses | +0.017 |
Neg logit contributions | |
xual | -0.023 |
rolet | -0.022 |
�� | -0.022 |
Stay | -0.020 |
ukong | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
wipes | +0.277 |
ignores | +0.251 |
ath | +0.238 |
misses | +0.228 |
Typhoon | +0.221 |
Neg logit contributions | |
xual | -0.419 |
�� | -0.397 |
rolet | -0.389 |
orescence | -0.366 |
uana | -0.365 |
Token | : |
Token ID | 1058 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
xual | +0.045 |
�� | +0.042 |
rolet | +0.041 |
uana | +0.039 |
orescence | +0.038 |
Neg logit contributions | |
wipes | -0.042 |
ignores | -0.038 |
ath | -0.036 |
misses | -0.035 |
Typhoon | -0.035 |
Token | " |
Token ID | 366 |
Feature activation | +5.15e-03 |
Pos logit contributions | |
xual | +0.165 |
rolet | +0.153 |
�� | +0.152 |
uana | +0.143 |
orescence | +0.141 |
Neg logit contributions | |
wipes | -0.145 |
ignores | -0.131 |
ath | -0.126 |
misses | -0.121 |
crossings | -0.119 |
Token | the |
Token ID | 1169 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
wipes | +0.013 |
ignores | +0.012 |
ath | +0.011 |
misses | +0.011 |
crossings | +0.011 |
Neg logit contributions | |
xual | -0.018 |
rolet | -0.017 |
�� | -0.017 |
uana | -0.016 |
orescence | -0.016 |
Token | First |
Token ID | 3274 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
wipes | +0.570 |
ignores | +0.528 |
ath | +0.503 |
misses | +0.487 |
Typhoon | +0.477 |
Neg logit contributions | |
xual | -0.516 |
�� | -0.473 |
rolet | -0.470 |
uana | -0.434 |
orescence | -0.432 |
Token | s |
Token ID | 82 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
wipes | +0.759 |
ignores | +0.700 |
ath | +0.677 |
misses | +0.650 |
crossings | +0.638 |
Neg logit contributions | |
xual | -0.665 |
�� | -0.612 |
rolet | -0.603 |
uana | -0.564 |
orescence | -0.558 |
Token | Cors |
Token ID | 26978 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
wipes | +0.464 |
ignores | +0.423 |
ath | +0.405 |
misses | +0.390 |
Typhoon | +0.383 |
Neg logit contributions | |
xual | -0.528 |
�� | -0.489 |
rolet | -0.487 |
uana | -0.455 |
orescence | -0.452 |
Token | airs |
Token ID | 3468 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
wipes | +3.768 |
ignores | +3.565 |
ath | +3.462 |
misses | +3.372 |
Typhoon | +3.329 |
Neg logit contributions | |
xual | -1.514 |
�� | -1.319 |
rolet | -1.301 |
uana | -1.111 |
orescence | -1.108 |
Token | are |
Token ID | 389 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
wipes | +0.783 |
ignores | +0.714 |
ath | +0.683 |
misses | +0.656 |
Typhoon | +0.646 |
Neg logit contributions | |
xual | -0.893 |
�� | -0.824 |
rolet | -0.823 |
uana | -0.772 |
orescence | -0.765 |
Token | the |
Token ID | 262 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
wipes | +0.631 |
ignores | +0.582 |
ath | +0.556 |
misses | +0.538 |
Typhoon | +0.530 |
Neg logit contributions | |
xual | -0.571 |
rolet | -0.521 |
�� | -0.521 |
uana | -0.485 |
orescence | -0.479 |
Token | guardians |
Token ID | 32769 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
wipes | +0.459 |
ignores | +0.425 |
ath | +0.403 |
misses | +0.389 |
Typhoon | +0.385 |
Neg logit contributions | |
xual | -0.439 |
rolet | -0.402 |
�� | -0.401 |
uana | -0.377 |
orescence | -0.371 |
Token | of |
Token ID | 286 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
wipes | +0.080 |
ignores | +0.074 |
ath | +0.070 |
misses | +0.068 |
Typhoon | +0.067 |
Neg logit contributions | |
xual | -0.074 |
rolet | -0.068 |
�� | -0.068 |
orescence | -0.063 |
uana | -0.063 |
Token | world |
Token ID | 995 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
xual | +0.444 |
rolet | +0.395 |
�� | +0.393 |
orescence | +0.369 |
uana | +0.368 |
Neg logit contributions | |
wipes | -0.484 |
ignores | -0.449 |
ath | -0.427 |
Typhoon | -0.415 |
misses | -0.415 |
Token | . |
Token ID | 13 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
wipes | +0.387 |
ignores | +0.359 |
ath | +0.344 |
misses | +0.333 |
Typhoon | +0.329 |
Neg logit contributions | |
xual | -0.360 |
rolet | -0.324 |
�� | -0.322 |
orescence | -0.300 |
uana | -0.300 |
Token | � |
Token ID | 564 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
wipes | +0.086 |
ignores | +0.078 |
ath | +0.075 |
misses | +0.072 |
crossings | +0.071 |
Neg logit contributions | |
xual | -0.096 |
rolet | -0.089 |
�� | -0.089 |
orescence | -0.082 |
uana | -0.082 |
Token | � |
Token ID | 250 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
wipes | +0.408 |
ignores | +0.382 |
ath | +0.369 |
misses | +0.358 |
Typhoon | +0.352 |
Neg logit contributions | |
xual | -0.260 |
�� | -0.235 |
rolet | -0.234 |
uana | -0.211 |
orescence | -0.210 |
Token | As |
Token ID | 1722 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
xual | +0.418 |
rolet | +0.391 |
�� | +0.390 |
uana | +0.370 |
orescence | +0.366 |
Neg logit contributions | |
wipes | -0.291 |
ignores | -0.259 |
ath | -0.244 |
misses | -0.234 |
crossings | -0.232 |
Token | soon |
Token ID | 2582 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
wipes | +0.294 |
ignores | +0.273 |
ath | +0.260 |
misses | +0.252 |
Typhoon | +0.248 |
Neg logit contributions | |
xual | -0.255 |
�� | -0.233 |
rolet | -0.231 |
uana | -0.216 |
orescence | -0.214 |
Token | as |
Token ID | 355 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
wipes | +2.636 |
ignores | +2.434 |
ath | +2.341 |
misses | +2.258 |
successes | +2.204 |
Neg logit contributions | |
xual | -2.602 |
�� | -2.502 |
rolet | -2.456 |
orescence | -2.204 |
uana | -2.194 |
Token | I |
Token ID | 314 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
wipes | +0.142 |
ignores | +0.133 |
ath | +0.127 |
misses | +0.122 |
Typhoon | +0.121 |
Neg logit contributions | |
xual | -0.116 |
�� | -0.104 |
rolet | -0.103 |
uana | -0.097 |
orescence | -0.097 |
Token | implant |
Token ID | 29016 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
wipes | +0.552 |
ignores | +0.507 |
ath | +0.484 |
misses | +0.464 |
Typhoon | +0.455 |
Neg logit contributions | |
xual | -0.621 |
�� | -0.577 |
rolet | -0.576 |
uana | -0.535 |
orescence | -0.533 |
Token | it |
Token ID | 340 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
xual | +0.158 |
�� | +0.142 |
rolet | +0.141 |
orescence | +0.131 |
uana | +0.131 |
Neg logit contributions | |
wipes | -0.213 |
ignores | -0.200 |
ath | -0.192 |
misses | -0.186 |
Typhoon | -0.184 |
Token | and |
Token ID | 290 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
wipes | +0.776 |
ignores | +0.714 |
ath | +0.680 |
misses | +0.656 |
Typhoon | +0.644 |
Neg logit contributions | |
xual | -0.835 |
�� | -0.773 |
rolet | -0.771 |
uana | -0.716 |
orescence | -0.715 |
Token | Two |
Token ID | 4930 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
xual | +0.765 |
�� | +0.708 |
rolet | +0.700 |
uana | +0.650 |
orescence | +0.642 |
Neg logit contributions | |
wipes | -0.835 |
ignores | -0.769 |
ath | -0.741 |
misses | -0.709 |
crossings | -0.699 |
Token | Mind |
Token ID | 10175 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
xual | +0.198 |
�� | +0.186 |
rolet | +0.185 |
uana | +0.177 |
orescence | +0.175 |
Neg logit contributions | |
wipes | -0.092 |
ignores | -0.079 |
ath | -0.075 |
misses | -0.068 |
Typhoon | -0.067 |
Token | s |
Token ID | 82 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
wipes | +1.460 |
ignores | +1.352 |
ath | +1.304 |
misses | +1.251 |
Typhoon | +1.234 |
Neg logit contributions | |
xual | -1.273 |
�� | -1.166 |
rolet | -1.160 |
uana | -1.063 |
orescence | -1.062 |
Token | blog |
Token ID | 4130 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
wipes | +0.936 |
ignores | +0.863 |
ath | +0.829 |
misses | +0.796 |
crossings | +0.782 |
Neg logit contributions | |
xual | -0.938 |
�� | -0.869 |
rolet | -0.863 |
uana | -0.797 |
orescence | -0.792 |
Token | - |
Token ID | 12 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
wipes | +0.937 |
ignores | +0.862 |
ath | +0.827 |
misses | +0.795 |
Typhoon | +0.780 |
Neg logit contributions | |
xual | -0.941 |
�� | -0.874 |
rolet | -0.869 |
uana | -0.803 |
orescence | -0.799 |
Token | Kind |
Token ID | 35854 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
xual | +0.322 |
rolet | +0.299 |
�� | +0.298 |
uana | +0.276 |
enture | +0.273 |
Neg logit contributions | |
wipes | -0.311 |
ignores | -0.285 |
ath | -0.273 |
misses | -0.263 |
crossings | -0.258 |
Token | le |
Token ID | 293 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
wipes | +2.255 |
ignores | +2.053 |
ath | +1.955 |
misses | +1.864 |
Typhoon | +1.826 |
Neg logit contributions | |
xual | -2.936 |
�� | -2.737 |
rolet | -2.736 |
uana | -2.561 |
orescence | -2.545 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
wipes | +0.536 |
ignores | +0.493 |
ath | +0.474 |
misses | +0.454 |
crossings | +0.450 |
Neg logit contributions | |
xual | -0.517 |
�� | -0.480 |
rolet | -0.477 |
uana | -0.440 |
orescence | -0.434 |
Token | A |
Token ID | 32 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
xual | +0.339 |
rolet | +0.320 |
�� | +0.318 |
uana | +0.301 |
ukong | +0.299 |
Neg logit contributions | |
wipes | -0.271 |
ignores | -0.244 |
ath | -0.230 |
misses | -0.222 |
crossings | -0.220 |
Token | Review |
Token ID | 6602 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
xual | +0.848 |
rolet | +0.781 |
�� | +0.776 |
uana | +0.717 |
orescence | +0.714 |
Neg logit contributions | |
wipes | -0.855 |
ignores | -0.791 |
ath | -0.756 |
misses | -0.722 |
crossings | -0.719 |
Token | of |
Token ID | 286 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
xual | +0.611 |
rolet | +0.556 |
�� | +0.555 |
ancer | +0.511 |
uana | +0.509 |
Neg logit contributions | |
wipes | -0.647 |
ignores | -0.591 |
ath | -0.566 |
crossings | -0.547 |
misses | -0.545 |
Token | thinks |
Token ID | 6834 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
wipes | +0.116 |
ignores | +0.105 |
ath | +0.103 |
Typhoon | +0.100 |
successes | +0.096 |
Neg logit contributions | |
xual | -0.160 |
rolet | -0.147 |
�� | -0.144 |
orescence | -0.139 |
enture | -0.138 |
Token | of |
Token ID | 286 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
xual | +0.086 |
rolet | +0.078 |
�� | +0.078 |
uana | +0.073 |
orescence | +0.073 |
Neg logit contributions | |
wipes | -0.088 |
ignores | -0.081 |
ath | -0.079 |
misses | -0.074 |
crossings | -0.074 |
Token | when |
Token ID | 618 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
xual | +0.609 |
rolet | +0.554 |
�� | +0.546 |
orescence | +0.508 |
uana | +0.503 |
Neg logit contributions | |
wipes | -0.772 |
ignores | -0.711 |
ath | -0.688 |
misses | -0.660 |
crossings | -0.653 |
Token | you |
Token ID | 345 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
wipes | +0.299 |
ignores | +0.276 |
ath | +0.265 |
misses | +0.255 |
Typhoon | +0.250 |
Neg logit contributions | |
xual | -0.288 |
rolet | -0.262 |
�� | -0.262 |
uana | -0.245 |
orescence | -0.244 |
Token | mention |
Token ID | 3068 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
xual | +0.532 |
rolet | +0.502 |
�� | +0.486 |
uana | +0.463 |
ancer | +0.458 |
Neg logit contributions | |
wipes | -0.556 |
ignores | -0.512 |
ath | -0.495 |
misses | -0.474 |
Typhoon | -0.470 |
Token | Psych |
Token ID | 31923 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
xual | +1.398 |
rolet | +1.271 |
�� | +1.257 |
uana | +1.182 |
ancer | +1.171 |
Neg logit contributions | |
wipes | -1.612 |
ignores | -1.487 |
ath | -1.436 |
misses | -1.375 |
crossings | -1.357 |
Token | o |
Token ID | 78 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
wipes | +2.419 |
ignores | +2.248 |
ath | +2.152 |
misses | +2.051 |
successes | +2.018 |
Neg logit contributions | |
xual | -2.746 |
�� | -2.588 |
rolet | -2.438 |
exting | -2.291 |
orescence | -2.278 |
Token | , |
Token ID | 11 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
xual | +0.330 |
rolet | +0.304 |
�� | +0.300 |
orescence | +0.278 |
uana | +0.277 |
Neg logit contributions | |
wipes | -0.351 |
ignores | -0.322 |
ath | -0.314 |
Typhoon | -0.298 |
misses | -0.297 |
Token | and |
Token ID | 290 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
xual | +0.267 |
rolet | +0.245 |
�� | +0.242 |
uana | +0.227 |
orescence | +0.226 |
Neg logit contributions | |
wipes | -0.263 |
ignores | -0.240 |
ath | -0.232 |
misses | -0.222 |
crossings | -0.219 |
Token | with |
Token ID | 351 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
xual | +0.230 |
rolet | +0.208 |
�� | +0.206 |
uana | +0.192 |
orescence | +0.191 |
Neg logit contributions | |
wipes | -0.255 |
ignores | -0.233 |
ath | -0.227 |
misses | -0.216 |
crossings | -0.215 |
Token | good |
Token ID | 922 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
xual | +0.243 |
rolet | +0.219 |
�� | +0.219 |
uana | +0.205 |
orescence | +0.202 |
Neg logit contributions | |
wipes | -0.277 |
ignores | -0.256 |
ath | -0.247 |
misses | -0.237 |
Typhoon | -0.234 |
Token | bronze |
Token ID | 22101 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
wipes | +0.433 |
ignores | +0.402 |
ath | +0.385 |
misses | +0.372 |
Typhoon | +0.364 |
Neg logit contributions | |
xual | -0.383 |
�� | -0.351 |
rolet | -0.349 |
uana | -0.323 |
orescence | -0.322 |
Token | , |
Token ID | 11 |
Feature activation | -6.86e-03 |
Pos logit contributions | |
wipes | +0.619 |
ignores | +0.574 |
ath | +0.550 |
misses | +0.532 |
Typhoon | +0.525 |
Neg logit contributions | |
xual | -0.539 |
�� | -0.491 |
rolet | -0.488 |
uana | -0.452 |
orescence | -0.451 |
Token | balance |
Token ID | 5236 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
xual | +0.022 |
rolet | +0.020 |
�� | +0.020 |
uana | +0.019 |
orescence | +0.019 |
Neg logit contributions | |
wipes | -0.019 |
ignores | -0.018 |
ath | -0.017 |
misses | -0.016 |
Typhoon | -0.016 |
Token | perfectly |
Token ID | 7138 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
wipes | +1.520 |
ignores | +1.409 |
ath | +1.351 |
misses | +1.307 |
Typhoon | +1.287 |
Neg logit contributions | |
xual | -1.303 |
�� | -1.188 |
rolet | -1.185 |
uana | -1.092 |
orescence | -1.090 |
Token | on |
Token ID | 319 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
wipes | +0.163 |
ignores | +0.150 |
ath | +0.143 |
misses | +0.138 |
Typhoon | +0.137 |
Neg logit contributions | |
xual | -0.163 |
rolet | -0.149 |
�� | -0.149 |
uana | -0.139 |
orescence | -0.138 |
Token | opposite |
Token ID | 6697 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
wipes | +0.156 |
ignores | +0.146 |
ath | +0.141 |
misses | +0.136 |
Typhoon | +0.134 |
Neg logit contributions | |
xual | -0.115 |
�� | -0.104 |
rolet | -0.104 |
orescence | -0.096 |
uana | -0.095 |
Token | ends |
Token ID | 5645 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
wipes | +2.696 |
ignores | +2.499 |
ath | +2.395 |
misses | +2.309 |
Typhoon | +2.274 |
Neg logit contributions | |
xual | -2.447 |
�� | -2.254 |
rolet | -2.241 |
uana | -2.066 |
orescence | -2.065 |
Token | of |
Token ID | 286 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
wipes | +0.928 |
ignores | +0.856 |
ath | +0.820 |
misses | +0.791 |
Typhoon | +0.782 |
Neg logit contributions | |
xual | -0.897 |
rolet | -0.823 |
�� | -0.821 |
orescence | -0.764 |
uana | -0.760 |
Token | a |
Token ID | 257 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
wipes | +0.437 |
ignores | +0.409 |
ath | +0.394 |
misses | +0.380 |
Typhoon | +0.374 |
Neg logit contributions | |
xual | -0.313 |
�� | -0.284 |
rolet | -0.283 |
orescence | -0.258 |
uana | -0.257 |
Token | scale |
Token ID | 5046 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
wipes | +0.478 |
ignores | +0.444 |
ath | +0.423 |
misses | +0.408 |
successes | +0.400 |
Neg logit contributions | |
xual | -0.450 |
�� | -0.414 |
rolet | -0.412 |
orescence | -0.380 |
uana | -0.379 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
wipes | +0.610 |
ignores | +0.563 |
ath | +0.538 |
misses | +0.520 |
Typhoon | +0.510 |
Neg logit contributions | |
xual | -0.581 |
�� | -0.530 |
rolet | -0.530 |
uana | -0.492 |
orescence | -0.490 |
Token | with |
Token ID | 351 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
wipes | +0.027 |
ignores | +0.025 |
ath | +0.023 |
misses | +0.022 |
Typhoon | +0.022 |
Neg logit contributions | |
xual | -0.032 |
�� | -0.030 |
rolet | -0.030 |
uana | -0.028 |
ukong | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
wipes | +0.123 |
ignores | +0.116 |
ath | +0.111 |
misses | +0.107 |
Typhoon | +0.106 |
Neg logit contributions | |
xual | -0.090 |
�� | -0.081 |
rolet | -0.080 |
uana | -0.075 |
orescence | -0.073 |
Token | rest |
Token ID | 1334 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
xual | +0.069 |
�� | +0.063 |
rolet | +0.063 |
uana | +0.059 |
ukong | +0.058 |
Neg logit contributions | |
wipes | -0.074 |
ignores | -0.069 |
ath | -0.066 |
misses | -0.064 |
Typhoon | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
wipes | +0.507 |
ignores | +0.471 |
ath | +0.450 |
misses | +0.433 |
Typhoon | +0.427 |
Neg logit contributions | |
xual | -0.496 |
�� | -0.455 |
rolet | -0.455 |
uana | -0.423 |
orescence | -0.419 |
Token | As |
Token ID | 1081 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
xual | +0.191 |
rolet | +0.177 |
�� | +0.175 |
uana | +0.163 |
orescence | +0.162 |
Neg logit contributions | |
wipes | -0.191 |
ignores | -0.176 |
ath | -0.169 |
misses | -0.161 |
crossings | -0.160 |
Token | soon |
Token ID | 2582 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
wipes | +0.439 |
ignores | +0.408 |
ath | +0.392 |
misses | +0.379 |
Typhoon | +0.373 |
Neg logit contributions | |
xual | -0.350 |
�� | -0.321 |
rolet | -0.319 |
uana | -0.292 |
orescence | -0.291 |
Token | as |
Token ID | 355 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
wipes | +2.768 |
ignores | +2.561 |
ath | +2.457 |
misses | +2.388 |
Typhoon | +2.337 |
Neg logit contributions | |
xual | -2.398 |
�� | -2.205 |
rolet | -2.197 |
orescence | -1.983 |
uana | -1.981 |
Token | we |
Token ID | 356 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
wipes | +0.165 |
ignores | +0.154 |
ath | +0.148 |
misses | +0.143 |
Typhoon | +0.141 |
Neg logit contributions | |
xual | -0.121 |
�� | -0.110 |
rolet | -0.109 |
uana | -0.101 |
orescence | -0.100 |
Token | have |
Token ID | 423 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
wipes | +1.129 |
ignores | +1.030 |
ath | +0.978 |
misses | +0.932 |
Typhoon | +0.917 |
Neg logit contributions | |
xual | -1.464 |
rolet | -1.366 |
�� | -1.364 |
uana | -1.279 |
orescence | -1.271 |
Token | reached |
Token ID | 4251 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
wipes | +1.100 |
ignores | +1.026 |
ath | +0.982 |
misses | +0.947 |
Typhoon | +0.938 |
Neg logit contributions | |
xual | -0.917 |
�� | -0.840 |
rolet | -0.836 |
uana | -0.773 |
orescence | -0.767 |
Token | a |
Token ID | 257 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
wipes | +1.750 |
ignores | +1.623 |
ath | +1.563 |
misses | +1.507 |
Typhoon | +1.482 |
Neg logit contributions | |
xual | -1.482 |
�� | -1.360 |
rolet | -1.354 |
uana | -1.240 |
orescence | -1.237 |
Token | hen |
Token ID | 831 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
xual | +0.113 |
rolet | +0.106 |
�� | +0.106 |
uana | +0.100 |
orescence | +0.099 |
Neg logit contributions | |
wipes | -0.087 |
ignores | -0.079 |
ath | -0.075 |
misses | -0.071 |
Typhoon | -0.070 |
Token | ry |
Token ID | 563 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
xual | +0.390 |
rolet | +0.357 |
�� | +0.352 |
uana | +0.329 |
orescence | +0.326 |
Neg logit contributions | |
wipes | -0.472 |
ignores | -0.435 |
ath | -0.413 |
Typhoon | -0.404 |
misses | -0.403 |
Token | . |
Token ID | 13 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
xual | +0.590 |
rolet | +0.536 |
�� | +0.533 |
uana | +0.498 |
orescence | +0.492 |
Neg logit contributions | |
wipes | -0.621 |
ignores | -0.576 |
ath | -0.547 |
misses | -0.532 |
Typhoon | -0.527 |
Token | c |
Token ID | 66 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
xual | +0.062 |
rolet | +0.057 |
�� | +0.056 |
uana | +0.053 |
orescence | +0.052 |
Neg logit contributions | |
wipes | -0.062 |
ignores | -0.057 |
ath | -0.054 |
misses | -0.053 |
Typhoon | -0.052 |
Token | ordes |
Token ID | 35770 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
xual | +0.281 |
rolet | +0.261 |
�� | +0.253 |
uana | +0.242 |
orescence | +0.239 |
Neg logit contributions | |
wipes | -0.340 |
ignores | -0.316 |
ath | -0.300 |
misses | -0.294 |
Typhoon | -0.293 |
Token | @ |
Token ID | 31 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
xual | +0.802 |
rolet | +0.749 |
�� | +0.710 |
ault | +0.688 |
uana | +0.680 |
Neg logit contributions | |
wipes | -0.865 |
ignores | -0.806 |
ath | -0.777 |
misses | -0.743 |
Nato | -0.736 |
Token | ow |
Token ID | 322 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
xual | +2.501 |
rolet | +2.342 |
�� | +2.270 |
uana | +2.135 |
orescence | +2.105 |
Neg logit contributions | |
wipes | -2.913 |
ignores | -2.755 |
ath | -2.622 |
misses | -2.544 |
Typhoon | -2.520 |
Token | h |
Token ID | 71 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
xual | +0.203 |
rolet | +0.189 |
�� | +0.186 |
uana | +0.175 |
orescence | +0.175 |
Neg logit contributions | |
wipes | -0.172 |
ignores | -0.159 |
ath | -0.150 |
misses | -0.145 |
Typhoon | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | +4.11e-03 |
Pos logit contributions | |
xual | +0.699 |
rolet | +0.656 |
�� | +0.635 |
uana | +0.618 |
ancer | +0.605 |
Neg logit contributions | |
wipes | -0.814 |
ignores | -0.750 |
ath | -0.715 |
misses | -0.702 |
Typhoon | -0.694 |
Token | com |
Token ID | 785 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
wipes | +0.013 |
ignores | +0.012 |
ath | +0.012 |
misses | +0.011 |
Typhoon | +0.011 |
Neg logit contributions | |
xual | -0.012 |
rolet | -0.011 |
�� | -0.011 |
uana | -0.010 |
orescence | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
wipes | +0.035 |
ignores | +0.032 |
ath | +0.031 |
misses | +0.030 |
Typhoon | +0.029 |
Neg logit contributions | |
xual | -0.036 |
rolet | -0.034 |
�� | -0.033 |
uana | -0.031 |
orescence | -0.031 |
Token | j |
Token ID | 474 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
wipes | +0.511 |
ignores | +0.470 |
ath | +0.444 |
Typhoon | +0.434 |
misses | +0.432 |
Neg logit contributions | |
xual | -0.429 |
rolet | -0.410 |
�� | -0.389 |
orescence | -0.362 |
ukong | -0.361 |
Token | on |
Token ID | 261 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
xual | +1.479 |
rolet | +1.386 |
ancer | +1.287 |
ault | +1.284 |
uana | +1.281 |
Neg logit contributions | |
wipes | -0.936 |
ignores | -0.844 |
Typhoon | -0.784 |
ath | -0.763 |
misses | -0.755 |
Token | . |
Token ID | 13 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
xual | +0.155 |
rolet | +0.144 |
�� | +0.140 |
uana | +0.131 |
orescence | +0.129 |
Neg logit contributions | |
wipes | -0.174 |
ignores | -0.161 |
ath | -0.151 |
misses | -0.149 |
Typhoon | -0.148 |
Token | chest |
Token ID | 46713 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
xual | +0.559 |
rolet | +0.502 |
�� | +0.494 |
uana | +0.450 |
orescence | +0.446 |
Neg logit contributions | |
wipes | -0.865 |
ignores | -0.809 |
ath | -0.778 |
misses | -0.759 |
Typhoon | -0.750 |
Token | o |
Token ID | 78 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
xual | +0.454 |
rolet | +0.417 |
�� | +0.415 |
uana | +0.384 |
orescence | +0.382 |
Neg logit contributions | |
wipes | -0.506 |
ignores | -0.468 |
ath | -0.449 |
misses | -0.433 |
Typhoon | -0.427 |
Token | @ |
Token ID | 31 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
xual | +0.931 |
rolet | +0.874 |
�� | +0.844 |
ancer | +0.765 |
ault | +0.764 |
Neg logit contributions | |
wipes | -1.338 |
ignores | -1.247 |
ath | -1.187 |
misses | -1.154 |
crossings | -1.146 |
Token | gl |
Token ID | 4743 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
xual | +2.789 |
rolet | +2.769 |
�� | +2.541 |
orescence | +2.519 |
uana | +2.512 |
Neg logit contributions | |
wipes | -2.381 |
ignores | -2.288 |
ath | -2.147 |
misses | -2.097 |
Typhoon | -2.040 |
Token | obe |
Token ID | 5910 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
xual | +0.238 |
rolet | +0.218 |
�� | +0.216 |
uana | +0.198 |
orescence | +0.198 |
Neg logit contributions | |
wipes | -0.313 |
ignores | -0.293 |
ath | -0.281 |
misses | -0.272 |
Typhoon | -0.269 |
Token | . |
Token ID | 13 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
wipes | +0.879 |
ignores | +0.807 |
ath | +0.776 |
misses | +0.742 |
Typhoon | +0.727 |
Neg logit contributions | |
xual | -0.932 |
�� | -0.877 |
rolet | -0.861 |
uana | -0.798 |
orescence | -0.794 |
Token | com |
Token ID | 785 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
xual | +0.119 |
�� | +0.112 |
rolet | +0.108 |
orescence | +0.100 |
uana | +0.100 |
Neg logit contributions | |
wipes | -0.119 |
ignores | -0.110 |
ath | -0.106 |
misses | -0.102 |
Typhoon | -0.100 |
Token | . |
Token ID | 764 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
xual | +0.097 |
rolet | +0.092 |
�� | +0.090 |
uana | +0.085 |
orescence | +0.085 |
Neg logit contributions | |
wipes | -0.086 |
ignores | -0.079 |
ath | -0.075 |
misses | -0.072 |
successes | -0.071 |
Token | the |
Token ID | 262 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
xual | +0.089 |
rolet | +0.080 |
�� | +0.080 |
uana | +0.074 |
orescence | +0.074 |
Neg logit contributions | |
wipes | -0.116 |
ignores | -0.109 |
ath | -0.105 |
misses | -0.101 |
Typhoon | -0.100 |
Token | Lif |
Token ID | 21073 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
xual | +0.296 |
rolet | +0.273 |
�� | +0.270 |
uana | +0.254 |
orescence | +0.253 |
Neg logit contributions | |
wipes | -0.274 |
ignores | -0.253 |
ath | -0.240 |
misses | -0.230 |
Typhoon | -0.227 |
Token | eline |
Token ID | 4470 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
wipes | +0.243 |
ignores | +0.226 |
ath | +0.219 |
misses | +0.211 |
Typhoon | +0.207 |
Neg logit contributions | |
xual | -0.194 |
�� | -0.180 |
rolet | -0.177 |
uana | -0.161 |
orescence | -0.160 |
Token | program |
Token ID | 1430 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
wipes | +0.086 |
ignores | +0.080 |
ath | +0.078 |
misses | +0.074 |
Typhoon | +0.074 |
Neg logit contributions | |
xual | -0.069 |
�� | -0.062 |
rolet | -0.062 |
uana | -0.057 |
orescence | -0.057 |
Token | diver |
Token ID | 12312 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
xual | +0.279 |
rolet | +0.253 |
�� | +0.251 |
uana | +0.240 |
orescence | +0.240 |
Neg logit contributions | |
wipes | -0.224 |
ignores | -0.202 |
ath | -0.198 |
Typhoon | -0.189 |
weak | -0.187 |
Token | ts |
Token ID | 912 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
xual | +1.009 |
rolet | +0.899 |
�� | +0.880 |
uana | +0.818 |
ukong | +0.805 |
Neg logit contributions | |
wipes | -1.581 |
ignores | -1.485 |
ath | -1.452 |
misses | -1.385 |
Typhoon | -1.383 |
Token | scarce |
Token ID | 18549 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
xual | +2.455 |
rolet | +2.204 |
uana | +2.166 |
�� | +2.165 |
ancer | +2.095 |
Neg logit contributions | |
wipes | -2.593 |
ignores | -2.410 |
ath | -2.302 |
eworks | -2.224 |
weak | -2.214 |
Token | funds |
Token ID | 5153 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
xual | +0.139 |
rolet | +0.130 |
�� | +0.129 |
uana | +0.124 |
orescence | +0.121 |
Neg logit contributions | |
wipes | -0.114 |
ignores | -0.106 |
ath | -0.100 |
misses | -0.095 |
weak | -0.094 |
Token | from |
Token ID | 422 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
xual | +1.061 |
rolet | +0.962 |
�� | +0.946 |
uana | +0.903 |
orescence | +0.899 |
Neg logit contributions | |
wipes | -1.077 |
ignores | -0.993 |
ath | -0.954 |
misses | -0.911 |
Typhoon | -0.907 |
Token | the |
Token ID | 262 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
wipes | +0.215 |
ignores | +0.201 |
ath | +0.193 |
misses | +0.185 |
Typhoon | +0.182 |
Neg logit contributions | |
xual | -0.173 |
rolet | -0.158 |
�� | -0.156 |
uana | -0.146 |
orescence | -0.143 |
Token | consumers |
Token ID | 7008 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
wipes | +0.113 |
ignores | +0.105 |
ath | +0.101 |
misses | +0.096 |
Typhoon | +0.095 |
Neg logit contributions | |
xual | -0.104 |
rolet | -0.095 |
�� | -0.094 |
uana | -0.088 |
orescence | -0.087 |
Token | of |
Token ID | 286 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
wipes | +0.046 |
ignores | +0.042 |
ath | +0.040 |
misses | +0.039 |
Typhoon | +0.038 |
Neg logit contributions | |
xual | -0.045 |
rolet | -0.042 |
�� | -0.041 |
uana | -0.038 |
orescence | -0.038 |
Token | Mad |
Token ID | 4627 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
wipes | +0.249 |
ignores | +0.230 |
ath | +0.220 |
misses | +0.212 |
Typhoon | +0.208 |
Neg logit contributions | |
xual | -0.247 |
�� | -0.229 |
rolet | -0.228 |
uana | -0.210 |
orescence | -0.210 |
Token | Max |
Token ID | 5436 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
wipes | +0.055 |
ignores | +0.051 |
ath | +0.049 |
misses | +0.047 |
crossings | +0.046 |
Neg logit contributions | |
xual | -0.048 |
rolet | -0.044 |
�� | -0.044 |
uana | -0.041 |
orescence | -0.041 |
Token | : |
Token ID | 25 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
xual | +0.845 |
rolet | +0.771 |
�� | +0.763 |
uana | +0.706 |
enture | +0.699 |
Neg logit contributions | |
wipes | -1.074 |
ignores | -0.989 |
ath | -0.964 |
misses | -0.922 |
Typhoon | -0.920 |
Token | Fury |
Token ID | 18427 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
xual | +0.796 |
�� | +0.743 |
rolet | +0.722 |
uana | +0.681 |
ancer | +0.675 |
Neg logit contributions | |
wipes | -1.123 |
ignores | -1.034 |
ath | -1.012 |
misses | -0.966 |
crossings | -0.959 |
Token | Road |
Token ID | 5567 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
xual | +2.014 |
�� | +1.825 |
rolet | +1.825 |
uana | +1.604 |
ault | +1.586 |
Neg logit contributions | |
wipes | -4.792 |
ignores | -4.459 |
ath | -4.378 |
misses | -4.233 |
Typhoon | -4.179 |
Token | on |
Token ID | 319 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
xual | +2.337 |
rolet | +2.159 |
�� | +2.137 |
uana | +1.993 |
ancer | +1.951 |
Neg logit contributions | |
wipes | -2.661 |
ignores | -2.476 |
ath | -2.393 |
Typhoon | -2.288 |
weak | -2.268 |
Token | Blu |
Token ID | 12391 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
xual | +1.118 |
rolet | +1.027 |
�� | +1.023 |
ancer | +0.942 |
uana | +0.939 |
Neg logit contributions | |
wipes | -1.432 |
ignores | -1.337 |
ath | -1.273 |
misses | -1.232 |
crossings | -1.217 |
Token | - |
Token ID | 12 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
xual | +0.113 |
�� | +0.105 |
rolet | +0.105 |
orescence | +0.097 |
uana | +0.097 |
Neg logit contributions | |
wipes | -0.123 |
ignores | -0.114 |
ath | -0.109 |
misses | -0.105 |
crossings | -0.104 |
Token | ray |
Token ID | 2433 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
xual | +0.152 |
rolet | +0.139 |
�� | +0.138 |
uana | +0.126 |
orescence | +0.125 |
Neg logit contributions | |
wipes | -0.215 |
ignores | -0.199 |
ath | -0.195 |
misses | -0.187 |
successes | -0.184 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
wipes | +0.067 |
ignores | +0.061 |
ath | +0.059 |
misses | +0.057 |
Typhoon | +0.056 |
Neg logit contributions | |
xual | -0.067 |
�� | -0.063 |
rolet | -0.062 |
uana | -0.058 |
orescence | -0.057 |
Token | states |
Token ID | 2585 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
xual | +0.310 |
�� | +0.289 |
rolet | +0.289 |
uana | +0.265 |
ancer | +0.262 |
Neg logit contributions | |
wipes | -0.352 |
ignores | -0.328 |
ath | -0.316 |
misses | -0.303 |
Typhoon | -0.297 |
Token | man |
Token ID | 805 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
wipes | +0.099 |
ignores | +0.092 |
ath | +0.089 |
misses | +0.086 |
crossings | +0.085 |
Neg logit contributions | |
xual | -0.072 |
rolet | -0.067 |
�� | -0.066 |
uana | -0.061 |
enture | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
wipes | +0.204 |
ignores | +0.188 |
ath | +0.181 |
misses | +0.174 |
Typhoon | +0.172 |
Neg logit contributions | |
xual | -0.195 |
�� | -0.180 |
rolet | -0.179 |
uana | -0.166 |
orescence | -0.164 |
Token |
|
Token ID | 198 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
xual | +0.397 |
rolet | +0.375 |
�� | +0.371 |
uana | +0.343 |
Stay | +0.342 |
Neg logit contributions | |
wipes | -0.383 |
ignores | -0.345 |
ath | -0.332 |
crossings | -0.318 |
misses | -0.317 |
Token |
|
Token ID | 198 |
Feature activation | +2.75e-03 |
Pos logit contributions | |
xual | +0.254 |
�� | +0.239 |
rolet | +0.237 |
uana | +0.222 |
orescence | +0.222 |
Neg logit contributions | |
wipes | -0.176 |
ignores | -0.160 |
ath | -0.152 |
misses | -0.145 |
Typhoon | -0.141 |
Token | Enter |
Token ID | 17469 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
wipes | +0.007 |
ignores | +0.006 |
ath | +0.006 |
misses | +0.005 |
crossings | +0.005 |
Neg logit contributions | |
xual | -0.010 |
rolet | -0.009 |
�� | -0.009 |
uana | -0.009 |
orescence | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
xual | +2.473 |
�� | +2.333 |
rolet | +2.327 |
orescence | +2.132 |
uana | +2.117 |
Neg logit contributions | |
wipes | -2.599 |
ignores | -2.361 |
ath | -2.277 |
misses | -2.190 |
crossings | -2.136 |
Token | heroic |
Token ID | 23523 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
xual | +0.617 |
�� | +0.574 |
rolet | +0.572 |
uana | +0.527 |
orescence | +0.526 |
Neg logit contributions | |
wipes | -0.626 |
ignores | -0.580 |
ath | -0.551 |
misses | -0.529 |
crossings | -0.515 |
Token | Poles |
Token ID | 45631 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
xual | +0.655 |
�� | +0.609 |
rolet | +0.606 |
uana | +0.559 |
orescence | +0.559 |
Neg logit contributions | |
wipes | -0.653 |
ignores | -0.602 |
ath | -0.575 |
misses | -0.550 |
crossings | -0.537 |
Token | , |
Token ID | 11 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
xual | +0.373 |
�� | +0.344 |
rolet | +0.343 |
uana | +0.315 |
orescence | +0.315 |
Neg logit contributions | |
wipes | -0.436 |
ignores | -0.403 |
ath | -0.386 |
misses | -0.374 |
Typhoon | -0.369 |
Token | who |
Token ID | 508 |
Feature activation | +2.34e-03 |
Pos logit contributions | |
xual | +0.580 |
rolet | +0.526 |
�� | +0.524 |
uana | +0.477 |
orescence | +0.476 |
Neg logit contributions | |
wipes | -0.856 |
ignores | -0.795 |
ath | -0.767 |
misses | -0.746 |
crossings | -0.733 |
Token | then |
Token ID | 788 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
xual | +0.372 |
�� | +0.338 |
rolet | +0.336 |
uana | +0.318 |
orescence | +0.316 |
Neg logit contributions | |
wipes | -0.313 |
ignores | -0.284 |
ath | -0.281 |
misses | -0.263 |
Typhoon | -0.261 |
Token | you |
Token ID | 345 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
xual | +0.230 |
rolet | +0.210 |
�� | +0.209 |
uana | +0.198 |
orescence | +0.198 |
Neg logit contributions | |
wipes | -0.174 |
ignores | -0.157 |
ath | -0.155 |
misses | -0.144 |
Typhoon | -0.143 |
Token | Special |
Token ID | 6093 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
wipes | +0.072 |
ignores | +0.067 |
ath | +0.064 |
misses | +0.062 |
crossings | +0.061 |
Neg logit contributions | |
xual | -0.076 |
rolet | -0.071 |
�� | -0.070 |
uana | -0.066 |
ukong | -0.065 |
Token | Summon |
Token ID | 19515 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
xual | +0.454 |
�� | +0.404 |
rolet | +0.403 |
uana | +0.372 |
ukong | +0.370 |
Neg logit contributions | |
wipes | -0.639 |
ignores | -0.592 |
ath | -0.581 |
misses | -0.551 |
crossings | -0.548 |
Token | an |
Token ID | 281 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
xual | +0.901 |
rolet | +0.814 |
�� | +0.809 |
uana | +0.751 |
ukong | +0.751 |
Neg logit contributions | |
wipes | -1.101 |
ignores | -1.021 |
ath | -0.989 |
misses | -0.955 |
crossings | -0.934 |
Token | ATK |
Token ID | 24526 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
xual | +0.600 |
�� | +0.550 |
rolet | +0.549 |
uana | +0.517 |
orescence | +0.507 |
Neg logit contributions | |
wipes | -0.732 |
ignores | -0.668 |
ath | -0.645 |
misses | -0.625 |
crossings | -0.612 |
Token | 0 |
Token ID | 657 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
xual | +2.482 |
rolet | +2.229 |
�� | +2.216 |
ukong | +2.091 |
uana | +2.088 |
Neg logit contributions | |
wipes | -2.608 |
ignores | -2.398 |
ath | -2.318 |
misses | -2.236 |
crossings | -2.208 |
Token | / |
Token ID | 14 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
xual | +0.729 |
�� | +0.666 |
rolet | +0.665 |
uana | +0.615 |
orescence | +0.612 |
Neg logit contributions | |
wipes | -0.792 |
ignores | -0.729 |
ath | -0.702 |
misses | -0.676 |
crossings | -0.663 |
Token | DEF |
Token ID | 32988 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
xual | +1.615 |
rolet | +1.486 |
�� | +1.473 |
� | +1.386 |
orescence | +1.380 |
Neg logit contributions | |
wipes | -1.415 |
ignores | -1.258 |
ath | -1.225 |
crossings | -1.155 |
misses | -1.155 |
Token | 0 |
Token ID | 657 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
xual | +0.663 |
rolet | +0.611 |
�� | +0.611 |
uana | +0.569 |
orescence | +0.567 |
Neg logit contributions | |
wipes | -0.597 |
ignores | -0.546 |
ath | -0.524 |
misses | -0.501 |
crossings | -0.491 |
Token | Zombie |
Token ID | 14609 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
xual | +1.002 |
�� | +0.912 |
rolet | +0.910 |
uana | +0.845 |
orescence | +0.840 |
Neg logit contributions | |
wipes | -1.128 |
ignores | -1.044 |
ath | -1.006 |
misses | -0.971 |
crossings | -0.953 |
Token | s |
Token ID | 82 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
xual | +0.614 |
�� | +0.575 |
rolet | +0.569 |
orescence | +0.523 |
uana | +0.521 |
Neg logit contributions | |
wipes | -0.633 |
ignores | -0.588 |
ath | -0.561 |
misses | -0.543 |
successes | -0.528 |
Token | Creed |
Token ID | 24299 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
wipes | +0.329 |
ignores | +0.299 |
ath | +0.283 |
misses | +0.270 |
successes | +0.261 |
Neg logit contributions | |
xual | -0.466 |
rolet | -0.440 |
�� | -0.436 |
ukong | -0.407 |
uana | -0.406 |
Token | ® |
Token ID | 7461 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
xual | +0.515 |
�� | +0.476 |
rolet | +0.470 |
uana | +0.434 |
orescence | +0.434 |
Neg logit contributions | |
wipes | -0.547 |
ignores | -0.504 |
ath | -0.488 |
misses | -0.466 |
crossings | -0.461 |
Token | Liberation |
Token ID | 29235 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
xual | +0.510 |
�� | +0.455 |
rolet | +0.449 |
uana | +0.399 |
orescence | +0.398 |
Neg logit contributions | |
wipes | -0.960 |
ignores | -0.900 |
ath | -0.878 |
misses | -0.849 |
crossings | -0.840 |
Token | HD |
Token ID | 5572 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
wipes | +1.039 |
ignores | +0.968 |
ath | +0.936 |
misses | +0.903 |
Typhoon | +0.891 |
Neg logit contributions | |
xual | -0.758 |
�� | -0.689 |
rolet | -0.685 |
uana | -0.623 |
orescence | -0.622 |
Token | introduces |
Token ID | 20718 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
xual | +0.459 |
�� | +0.430 |
rolet | +0.426 |
orescence | +0.401 |
uana | +0.400 |
Neg logit contributions | |
wipes | -0.330 |
ignores | -0.299 |
ath | -0.286 |
misses | -0.270 |
Typhoon | -0.268 |
Token | graphical |
Token ID | 27831 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
xual | +2.303 |
�� | +2.081 |
rolet | +2.057 |
uana | +1.915 |
ancer | +1.913 |
Neg logit contributions | |
wipes | -2.723 |
ignores | -2.555 |
ath | -2.416 |
misses | -2.359 |
weak | -2.326 |
Token | improvements |
Token ID | 8561 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
xual | +0.215 |
rolet | +0.198 |
�� | +0.198 |
uana | +0.188 |
orescence | +0.186 |
Neg logit contributions | |
wipes | -0.157 |
ignores | -0.145 |
ath | -0.135 |
Typhoon | -0.128 |
misses | -0.127 |
Token | and |
Token ID | 290 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
xual | +0.913 |
rolet | +0.826 |
�� | +0.816 |
orescence | +0.756 |
uana | +0.756 |
Neg logit contributions | |
wipes | -1.018 |
ignores | -0.944 |
ath | -0.898 |
misses | -0.871 |
Typhoon | -0.862 |
Token | new |
Token ID | 649 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
xual | +0.098 |
�� | +0.090 |
rolet | +0.089 |
uana | +0.083 |
orescence | +0.082 |
Neg logit contributions | |
wipes | -0.098 |
ignores | -0.091 |
ath | -0.087 |
Typhoon | -0.083 |
misses | -0.083 |
Token | missions |
Token ID | 10566 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
xual | +0.853 |
�� | +0.788 |
rolet | +0.786 |
uana | +0.730 |
ancer | +0.724 |
Neg logit contributions | |
wipes | -0.939 |
ignores | -0.884 |
ath | -0.840 |
misses | -0.803 |
Typhoon | -0.796 |
Token | used |
Token ID | 973 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
xual | +0.464 |
rolet | +0.427 |
�� | +0.423 |
ancer | +0.393 |
enture | +0.387 |
Neg logit contributions | |
wipes | -0.523 |
ignores | -0.481 |
ath | -0.464 |
Typhoon | -0.447 |
misses | -0.445 |
Token | courtesy |
Token ID | 12537 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
wipes | +0.200 |
ignores | +0.182 |
ath | +0.175 |
misses | +0.169 |
Typhoon | +0.167 |
Neg logit contributions | |
xual | -0.208 |
rolet | -0.192 |
�� | -0.190 |
orescence | -0.177 |
uana | -0.175 |
Token | of |
Token ID | 286 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
wipes | +0.191 |
ignores | +0.176 |
ath | +0.168 |
misses | +0.162 |
Typhoon | +0.160 |
Neg logit contributions | |
xual | -0.187 |
�� | -0.173 |
rolet | -0.173 |
uana | -0.159 |
orescence | -0.158 |
Token | Basketball |
Token ID | 25911 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
wipes | +0.515 |
ignores | +0.480 |
ath | +0.459 |
misses | +0.445 |
Typhoon | +0.442 |
Neg logit contributions | |
xual | -0.388 |
rolet | -0.356 |
�� | -0.351 |
uana | -0.320 |
ancer | -0.318 |
Token | - |
Token ID | 12 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
wipes | +0.730 |
ignores | +0.673 |
ath | +0.643 |
misses | +0.619 |
crossings | +0.617 |
Neg logit contributions | |
xual | -0.660 |
rolet | -0.610 |
�� | -0.607 |
uana | -0.558 |
orescence | -0.557 |
Token | Reference |
Token ID | 26687 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
xual | +0.436 |
rolet | +0.401 |
�� | +0.381 |
uana | +0.370 |
orescence | +0.361 |
Neg logit contributions | |
wipes | -0.660 |
ignores | -0.613 |
ath | -0.589 |
Typhoon | -0.572 |
misses | -0.566 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
xual | +2.285 |
�� | +2.080 |
rolet | +2.074 |
ancer | +1.894 |
uana | +1.890 |
Neg logit contributions | |
wipes | -2.700 |
ignores | -2.500 |
ath | -2.416 |
misses | -2.313 |
crossings | -2.303 |
Token | com |
Token ID | 785 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
wipes | +0.389 |
ignores | +0.360 |
ath | +0.346 |
misses | +0.333 |
crossings | +0.330 |
Neg logit contributions | |
xual | -0.331 |
rolet | -0.305 |
�� | -0.301 |
uana | -0.279 |
orescence | -0.277 |
Token | and |
Token ID | 290 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
wipes | +0.461 |
ignores | +0.424 |
ath | +0.408 |
misses | +0.392 |
Typhoon | +0.386 |
Neg logit contributions | |
xual | -0.445 |
�� | -0.411 |
rolet | -0.408 |
uana | -0.378 |
orescence | -0.375 |
Token | NBA |
Token ID | 7403 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
wipes | +0.502 |
ignores | +0.464 |
ath | +0.448 |
misses | +0.432 |
Typhoon | +0.430 |
Neg logit contributions | |
xual | -0.390 |
rolet | -0.354 |
�� | -0.352 |
uana | -0.321 |
ukong | -0.321 |
Token | . |
Token ID | 13 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
wipes | +0.102 |
ignores | +0.094 |
ath | +0.090 |
misses | +0.087 |
Typhoon | +0.086 |
Neg logit contributions | |
xual | -0.095 |
rolet | -0.087 |
�� | -0.087 |
uana | -0.081 |
orescence | -0.080 |
Token | ," |
Token ID | 553 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
xual | +0.624 |
rolet | +0.561 |
�� | +0.552 |
orescence | +0.522 |
uana | +0.513 |
Neg logit contributions | |
wipes | -0.697 |
ignores | -0.646 |
ath | -0.619 |
misses | -0.597 |
Typhoon | -0.594 |
Token | Ger |
Token ID | 13573 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
xual | +0.491 |
�� | +0.449 |
rolet | +0.448 |
orescence | +0.412 |
uana | +0.412 |
Neg logit contributions | |
wipes | -0.575 |
ignores | -0.532 |
ath | -0.516 |
misses | -0.493 |
Typhoon | -0.489 |
Token | ads |
Token ID | 5643 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
xual | +0.363 |
rolet | +0.337 |
�� | +0.337 |
uana | +0.314 |
orescence | +0.314 |
Neg logit contributions | |
wipes | -0.297 |
ignores | -0.272 |
ath | -0.259 |
misses | -0.248 |
Typhoon | -0.244 |
Token | tells |
Token ID | 4952 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
wipes | +0.486 |
ignores | +0.443 |
ath | +0.423 |
misses | +0.400 |
Typhoon | +0.399 |
Neg logit contributions | |
xual | -0.693 |
rolet | -0.648 |
�� | -0.644 |
orescence | -0.606 |
uana | -0.603 |
Token | Heat |
Token ID | 12308 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
xual | +0.705 |
�� | +0.648 |
rolet | +0.646 |
orescence | +0.605 |
uana | +0.604 |
Neg logit contributions | |
wipes | -0.702 |
ignores | -0.653 |
ath | -0.611 |
misses | -0.599 |
crossings | -0.582 |
Token | Vision |
Token ID | 19009 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
wipes | +1.235 |
ignores | +1.165 |
ath | +1.132 |
misses | +1.102 |
Typhoon | +1.086 |
Neg logit contributions | |
xual | -0.547 |
�� | -0.474 |
rolet | -0.473 |
uana | -0.412 |
orescence | -0.410 |
Token | via |
Token ID | 2884 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
xual | +2.328 |
�� | +2.081 |
rolet | +2.078 |
ancer | +1.924 |
enture | +1.922 |
Neg logit contributions | |
wipes | -2.637 |
ignores | -2.489 |
ath | -2.341 |
misses | -2.289 |
weak | -2.241 |
Token | phone |
Token ID | 3072 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
xual | +0.931 |
rolet | +0.872 |
�� | +0.861 |
enture | +0.824 |
orescence | +0.820 |
Neg logit contributions | |
wipes | -0.684 |
ignores | -0.621 |
ath | -0.579 |
misses | -0.562 |
weak | -0.550 |
Token | . |
Token ID | 13 |
Feature activation | +8.26e-03 |
Pos logit contributions | |
xual | +0.150 |
rolet | +0.138 |
�� | +0.137 |
orescence | +0.128 |
uana | +0.127 |
Neg logit contributions | |
wipes | -0.146 |
ignores | -0.135 |
ath | -0.129 |
misses | -0.124 |
Typhoon | -0.123 |
Token | " |
Token ID | 366 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
wipes | +0.023 |
ignores | +0.021 |
ath | +0.020 |
misses | +0.019 |
crossings | +0.019 |
Neg logit contributions | |
xual | -0.027 |
rolet | -0.026 |
�� | -0.026 |
uana | -0.024 |
orescence | -0.024 |
Token | My |
Token ID | 3666 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
xual | +0.589 |
rolet | +0.560 |
�� | +0.553 |
ukong | +0.524 |
uana | +0.523 |
Neg logit contributions | |
wipes | -0.415 |
ignores | -0.369 |
ath | -0.347 |
crossings | -0.333 |
misses | -0.328 |
Token | sits |
Token ID | 10718 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
wipes | +0.333 |
ignores | +0.305 |
ath | +0.295 |
misses | +0.280 |
crossings | +0.278 |
Neg logit contributions | |
xual | -0.331 |
�� | -0.307 |
rolet | -0.306 |
uana | -0.283 |
orescence | -0.283 |
Token | , |
Token ID | 11 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
xual | +0.204 |
rolet | +0.190 |
�� | +0.189 |
orescence | +0.177 |
uana | +0.177 |
Neg logit contributions | |
wipes | -0.208 |
ignores | -0.192 |
ath | -0.180 |
misses | -0.176 |
Typhoon | -0.175 |
Token | un |
Token ID | 555 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
xual | +0.063 |
rolet | +0.058 |
�� | +0.058 |
uana | +0.054 |
orescence | +0.054 |
Neg logit contributions | |
wipes | -0.058 |
ignores | -0.053 |
ath | -0.051 |
misses | -0.049 |
Typhoon | -0.048 |
Token | cl |
Token ID | 565 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
xual | +0.050 |
rolet | +0.047 |
�� | +0.046 |
uana | +0.043 |
orescence | +0.043 |
Neg logit contributions | |
wipes | -0.053 |
ignores | -0.049 |
ath | -0.047 |
misses | -0.045 |
Typhoon | -0.045 |
Token | ot |
Token ID | 313 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
wipes | +0.226 |
ignores | +0.210 |
ath | +0.202 |
misses | +0.193 |
Typhoon | +0.192 |
Neg logit contributions | |
xual | -0.218 |
rolet | -0.201 |
�� | -0.199 |
uana | -0.186 |
orescence | -0.185 |
Token | hed |
Token ID | 704 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
xual | +0.630 |
rolet | +0.580 |
�� | +0.578 |
orescence | +0.527 |
ukong | +0.526 |
Neg logit contributions | |
wipes | -0.718 |
ignores | -0.661 |
ath | -0.647 |
Typhoon | -0.617 |
misses | -0.610 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
xual | +2.209 |
�� | +2.024 |
rolet | +1.989 |
uana | +1.877 |
orescence | +1.859 |
Neg logit contributions | |
wipes | -2.602 |
ignores | -2.412 |
ath | -2.298 |
misses | -2.239 |
Typhoon | -2.233 |
Token | in |
Token ID | 287 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
wipes | +0.353 |
ignores | +0.324 |
ath | +0.309 |
misses | +0.298 |
Typhoon | +0.295 |
Neg logit contributions | |
xual | -0.366 |
�� | -0.338 |
rolet | -0.337 |
uana | -0.314 |
orescence | -0.313 |
Token | a |
Token ID | 257 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
wipes | +0.899 |
ignores | +0.838 |
ath | +0.804 |
misses | +0.777 |
Typhoon | +0.765 |
Neg logit contributions | |
xual | -0.717 |
�� | -0.657 |
rolet | -0.655 |
uana | -0.600 |
orescence | -0.597 |
Token | glass |
Token ID | 5405 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
xual | +0.172 |
rolet | +0.160 |
�� | +0.159 |
uana | +0.147 |
orescence | +0.146 |
Neg logit contributions | |
wipes | -0.188 |
ignores | -0.176 |
ath | -0.166 |
misses | -0.162 |
successes | -0.158 |
Token | display |
Token ID | 3359 |
Feature activation | -6.52e-03 |
Pos logit contributions | |
xual | +1.288 |
rolet | +1.198 |
�� | +1.195 |
orescence | +1.110 |
uana | +1.105 |
Neg logit contributions | |
wipes | -1.495 |
ignores | -1.382 |
ath | -1.311 |
misses | -1.281 |
crossings | -1.253 |
Token | a |
Token ID | 257 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
wipes | +1.001 |
ignores | +0.929 |
ath | +0.892 |
misses | +0.855 |
Typhoon | +0.844 |
Neg logit contributions | |
xual | -0.923 |
�� | -0.854 |
rolet | -0.853 |
orescence | -0.783 |
uana | -0.778 |
Token | rat |
Token ID | 4227 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
xual | +0.498 |
rolet | +0.459 |
�� | +0.457 |
uana | +0.419 |
ukong | +0.418 |
Neg logit contributions | |
wipes | -0.522 |
ignores | -0.486 |
ath | -0.463 |
crossings | -0.446 |
misses | -0.445 |
Token | and |
Token ID | 290 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
xual | +0.620 |
rolet | +0.573 |
�� | +0.566 |
uana | +0.530 |
ancer | +0.522 |
Neg logit contributions | |
wipes | -0.673 |
ignores | -0.624 |
ath | -0.600 |
misses | -0.579 |
successes | -0.573 |
Token | get |
Token ID | 651 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
wipes | +0.329 |
ignores | +0.303 |
ath | +0.289 |
misses | +0.278 |
Typhoon | +0.277 |
Neg logit contributions | |
xual | -0.361 |
rolet | -0.334 |
�� | -0.331 |
uana | -0.311 |
orescence | -0.307 |
Token | the |
Token ID | 262 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
xual | +0.010 |
�� | +0.009 |
rolet | +0.009 |
uana | +0.008 |
orescence | +0.008 |
Neg logit contributions | |
wipes | -0.010 |
ignores | -0.009 |
ath | -0.009 |
misses | -0.008 |
Typhoon | -0.008 |
Token | heck |
Token ID | 22574 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
wipes | +0.075 |
ignores | +0.070 |
ath | +0.067 |
misses | +0.064 |
Typhoon | +0.063 |
Neg logit contributions | |
xual | -0.072 |
rolet | -0.066 |
�� | -0.066 |
uana | -0.061 |
orescence | -0.061 |
Token | off |
Token ID | 572 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
xual | +2.078 |
rolet | +1.867 |
�� | +1.834 |
uana | +1.705 |
orescence | +1.696 |
Neg logit contributions | |
wipes | -2.785 |
ignores | -2.622 |
ath | -2.507 |
Typhoon | -2.441 |
misses | -2.434 |
Token | this |
Token ID | 428 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
wipes | +0.240 |
ignores | +0.223 |
ath | +0.213 |
misses | +0.207 |
crossings | +0.203 |
Neg logit contributions | |
xual | -0.209 |
rolet | -0.194 |
�� | -0.192 |
orescence | -0.177 |
uana | -0.177 |
Token | sinking |
Token ID | 27141 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
xual | +0.191 |
rolet | +0.176 |
�� | +0.176 |
uana | +0.163 |
orescence | +0.162 |
Neg logit contributions | |
wipes | -0.191 |
ignores | -0.176 |
ath | -0.168 |
misses | -0.162 |
Typhoon | -0.160 |
Token | ship |
Token ID | 4074 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
xual | +0.531 |
rolet | +0.506 |
�� | +0.499 |
ukong | +0.469 |
ancer | +0.463 |
Neg logit contributions | |
wipes | -0.455 |
ignores | -0.420 |
ath | -0.393 |
misses | -0.379 |
crossings | -0.377 |
Token | of |
Token ID | 286 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
wipes | +0.177 |
ignores | +0.164 |
ath | +0.157 |
misses | +0.152 |
successes | +0.149 |
Neg logit contributions | |
xual | -0.164 |
rolet | -0.151 |
�� | -0.150 |
uana | -0.138 |
orescence | -0.138 |
Token | fully |
Token ID | 3938 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
wipes | +0.092 |
ignores | +0.085 |
ath | +0.080 |
misses | +0.077 |
Typhoon | +0.077 |
Neg logit contributions | |
xual | -0.098 |
�� | -0.090 |
rolet | -0.090 |
uana | -0.085 |
orescence | -0.084 |
Token | conscious |
Token ID | 6921 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
wipes | +0.604 |
ignores | +0.557 |
ath | +0.533 |
misses | +0.514 |
Typhoon | +0.510 |
Neg logit contributions | |
xual | -0.565 |
�� | -0.521 |
rolet | -0.517 |
uana | -0.482 |
orescence | -0.479 |
Token | . |
Token ID | 13 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
xual | +0.326 |
�� | +0.298 |
rolet | +0.298 |
uana | +0.276 |
orescence | +0.276 |
Neg logit contributions | |
wipes | -0.362 |
ignores | -0.334 |
ath | -0.321 |
misses | -0.311 |
Typhoon | -0.309 |
Token | When |
Token ID | 1649 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
xual | +0.022 |
rolet | +0.020 |
�� | +0.020 |
uana | +0.019 |
orescence | +0.018 |
Neg logit contributions | |
wipes | -0.020 |
ignores | -0.018 |
ath | -0.017 |
misses | -0.017 |
crossings | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
wipes | +0.813 |
ignores | +0.752 |
ath | +0.720 |
misses | +0.695 |
Typhoon | +0.683 |
Neg logit contributions | |
xual | -0.761 |
�� | -0.692 |
rolet | -0.692 |
uana | -0.647 |
orescence | -0.643 |
Token | advent |
Token ID | 19980 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
wipes | +0.085 |
ignores | +0.079 |
ath | +0.075 |
misses | +0.072 |
Typhoon | +0.071 |
Neg logit contributions | |
xual | -0.077 |
�� | -0.071 |
rolet | -0.070 |
uana | -0.066 |
orescence | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
xual | +2.358 |
rolet | +2.135 |
�� | +2.123 |
uana | +1.994 |
orescence | +1.985 |
Neg logit contributions | |
wipes | -2.547 |
ignores | -2.368 |
ath | -2.256 |
misses | -2.183 |
Typhoon | -2.173 |
Token | anesthesia |
Token ID | 49592 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
xual | +0.051 |
rolet | +0.046 |
�� | +0.046 |
uana | +0.043 |
orescence | +0.043 |
Neg logit contributions | |
wipes | -0.055 |
ignores | -0.052 |
ath | -0.049 |
misses | -0.048 |
Typhoon | -0.047 |
Token | made |
Token ID | 925 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
wipes | +0.202 |
ignores | +0.187 |
ath | +0.179 |
misses | +0.173 |
Typhoon | +0.171 |
Neg logit contributions | |
xual | -0.199 |
�� | -0.182 |
rolet | -0.182 |
uana | -0.170 |
orescence | -0.170 |
Token | medical |
Token ID | 3315 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
xual | +0.508 |
�� | +0.456 |
rolet | +0.455 |
uana | +0.428 |
orescence | +0.425 |
Neg logit contributions | |
wipes | -0.604 |
ignores | -0.565 |
ath | -0.536 |
misses | -0.521 |
Typhoon | -0.519 |
Token | practices |
Token ID | 6593 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
xual | +0.259 |
rolet | +0.238 |
�� | +0.238 |
uana | +0.226 |
orescence | +0.225 |
Neg logit contributions | |
wipes | -0.259 |
ignores | -0.238 |
ath | -0.226 |
Typhoon | -0.220 |
misses | -0.218 |
Token | i |
Token ID | 1312 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
wipes | +0.743 |
ignores | +0.677 |
ath | +0.646 |
misses | +0.615 |
crossings | +0.607 |
Neg logit contributions | |
xual | -0.926 |
�� | -0.870 |
rolet | -0.859 |
uana | -0.811 |
orescence | -0.802 |
Token | Player |
Token ID | 14140 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
wipes | +0.535 |
ignores | +0.486 |
ath | +0.460 |
Typhoon | +0.450 |
misses | +0.442 |
Neg logit contributions | |
xual | -0.596 |
rolet | -0.566 |
�� | -0.558 |
uana | -0.533 |
orescence | -0.516 |
Token | afterwards |
Token ID | 12979 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
xual | +0.325 |
�� | +0.302 |
rolet | +0.297 |
uana | +0.279 |
ancer | +0.274 |
Neg logit contributions | |
wipes | -0.356 |
ignores | -0.329 |
ath | -0.314 |
misses | -0.303 |
crossings | -0.300 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
wipes | +0.693 |
ignores | +0.639 |
ath | +0.613 |
misses | +0.589 |
Typhoon | +0.579 |
Neg logit contributions | |
xual | -0.686 |
�� | -0.633 |
rolet | -0.633 |
uana | -0.585 |
orescence | -0.582 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
wipes | +0.041 |
ignores | +0.037 |
ath | +0.036 |
misses | +0.035 |
crossings | +0.034 |
Neg logit contributions | |
xual | -0.036 |
�� | -0.033 |
rolet | -0.033 |
uana | -0.031 |
orescence | -0.030 |
Token | Develop |
Token ID | 19246 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
xual | +0.364 |
rolet | +0.342 |
�� | +0.340 |
uana | +0.323 |
ukong | +0.320 |
Neg logit contributions | |
wipes | -0.290 |
ignores | -0.261 |
ath | -0.247 |
misses | -0.238 |
crossings | -0.236 |
Token | ers |
Token ID | 364 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
xual | +2.188 |
rolet | +1.970 |
�� | +1.947 |
ancer | +1.811 |
enture | +1.803 |
Neg logit contributions | |
wipes | -2.661 |
ignores | -2.490 |
ath | -2.374 |
misses | -2.315 |
crossings | -2.278 |
Token | claim |
Token ID | 1624 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
xual | +0.065 |
rolet | +0.061 |
�� | +0.060 |
uana | +0.056 |
orescence | +0.056 |
Neg logit contributions | |
wipes | -0.064 |
ignores | -0.059 |
ath | -0.056 |
misses | -0.054 |
crossings | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
wipes | +0.180 |
ignores | +0.167 |
ath | +0.161 |
misses | +0.154 |
crossings | +0.151 |
Neg logit contributions | |
xual | -0.160 |
rolet | -0.147 |
�� | -0.145 |
uana | -0.136 |
orescence | -0.135 |
Token | browser |
Token ID | 6444 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
xual | +0.409 |
rolet | +0.380 |
�� | +0.373 |
orescence | +0.351 |
uana | +0.351 |
Neg logit contributions | |
wipes | -0.426 |
ignores | -0.402 |
ath | -0.378 |
misses | -0.361 |
weak | -0.355 |
Token | is |
Token ID | 318 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
wipes | +0.050 |
ignores | +0.045 |
ath | +0.045 |
crossings | +0.042 |
weak | +0.042 |
Neg logit contributions | |
xual | -0.056 |
�� | -0.052 |
rolet | -0.051 |
ancer | -0.049 |
ukong | -0.049 |
Token | uk |
Token ID | 2724 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
xual | +0.426 |
�� | +0.415 |
rolet | +0.395 |
orescence | +0.369 |
exting | +0.368 |
Neg logit contributions | |
wipes | -0.350 |
ignores | -0.324 |
ath | -0.307 |
misses | -0.298 |
Typhoon | -0.292 |
Token | / |
Token ID | 14 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
wipes | +1.529 |
ignores | +1.407 |
ath | +1.369 |
misses | +1.306 |
Typhoon | +1.283 |
Neg logit contributions | |
xual | -1.840 |
�� | -1.761 |
rolet | -1.676 |
exting | -1.631 |
orescence | -1.590 |
Token | in |
Token ID | 259 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
wipes | +0.301 |
ignores | +0.275 |
ath | +0.264 |
misses | +0.252 |
Typhoon | +0.249 |
Neg logit contributions | |
xual | -0.316 |
rolet | -0.293 |
�� | -0.286 |
uana | -0.270 |
orescence | -0.269 |
Token | coming |
Token ID | 4976 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
xual | +0.783 |
rolet | +0.743 |
�� | +0.707 |
ancer | +0.696 |
enture | +0.688 |
Neg logit contributions | |
wipes | -0.513 |
ignores | -0.458 |
ath | -0.423 |
misses | -0.407 |
Typhoon | -0.407 |
Token | / |
Token ID | 14 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
xual | +0.085 |
rolet | +0.079 |
�� | +0.078 |
orescence | +0.072 |
uana | +0.072 |
Neg logit contributions | |
wipes | -0.094 |
ignores | -0.087 |
ath | -0.083 |
misses | -0.080 |
Typhoon | -0.080 |
Token | article |
Token ID | 20205 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
xual | +0.696 |
rolet | +0.627 |
�� | +0.598 |
uana | +0.548 |
orescence | +0.544 |
Neg logit contributions | |
wipes | -1.294 |
ignores | -1.205 |
ath | -1.170 |
Typhoon | -1.132 |
misses | -1.129 |
Token | 35 |
Token ID | 2327 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
xual | +2.584 |
rolet | +2.356 |
�� | +2.329 |
ancer | +2.194 |
ukong | +2.184 |
Neg logit contributions | |
wipes | -2.312 |
ignores | -2.101 |
ath | -1.985 |
Typhoon | -1.939 |
crossings | -1.921 |
Token | 79 |
Token ID | 3720 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
xual | +0.757 |
rolet | +0.700 |
�� | +0.688 |
uana | +0.647 |
ukong | +0.643 |
Neg logit contributions | |
wipes | -0.639 |
ignores | -0.582 |
ath | -0.552 |
misses | -0.532 |
crossings | -0.526 |
Token | 23 |
Token ID | 1954 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
xual | +1.313 |
rolet | +1.217 |
�� | +1.183 |
uana | +1.131 |
ancer | +1.129 |
Neg logit contributions | |
wipes | -1.051 |
ignores | -0.956 |
ath | -0.905 |
misses | -0.868 |
crossings | -0.862 |
Token | 12 |
Token ID | 1065 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
xual | +0.333 |
rolet | +0.309 |
�� | +0.304 |
uana | +0.289 |
ancer | +0.288 |
Neg logit contributions | |
wipes | -0.242 |
ignores | -0.218 |
ath | -0.207 |
misses | -0.197 |
crossings | -0.195 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
xual | +0.499 |
�� | +0.466 |
rolet | +0.461 |
uana | +0.426 |
orescence | +0.426 |
Neg logit contributions | |
wipes | -0.475 |
ignores | -0.437 |
ath | -0.419 |
misses | -0.404 |
Typhoon | -0.396 |
Token |
|
Token ID | 198 |
Feature activation | -3.50e-03 |
Pos logit contributions | |
wipes | +0.214 |
ignores | +0.195 |
ath | +0.187 |
misses | +0.178 |
crossings | +0.177 |
Neg logit contributions | |
xual | -0.243 |
rolet | -0.227 |
�� | -0.225 |
uana | -0.209 |
orescence | -0.208 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
xual | +0.013 |
�� | +0.012 |
rolet | +0.012 |
orescence | +0.011 |
uana | +0.011 |
Neg logit contributions | |
wipes | -0.009 |
ignores | -0.008 |
ath | -0.007 |
misses | -0.007 |
Typhoon | -0.007 |
Token | How |
Token ID | 2437 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
wipes | +0.035 |
ignores | +0.031 |
ath | +0.030 |
misses | +0.028 |
crossings | +0.028 |
Neg logit contributions | |
xual | -0.048 |
rolet | -0.045 |
�� | -0.045 |
uana | -0.042 |
ukong | -0.042 |
Token | in |
Token ID | 287 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
xual | +0.094 |
�� | +0.087 |
rolet | +0.087 |
uana | +0.081 |
orescence | +0.080 |
Neg logit contributions | |
wipes | -0.089 |
ignores | -0.081 |
ath | -0.078 |
misses | -0.075 |
Typhoon | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
xual | +0.760 |
�� | +0.682 |
rolet | +0.681 |
orescence | +0.613 |
uana | +0.612 |
Neg logit contributions | |
wipes | -1.253 |
ignores | -1.178 |
ath | -1.128 |
misses | -1.098 |
crossings | -1.093 |
Token | hell |
Token ID | 5968 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
xual | +0.477 |
�� | +0.434 |
rolet | +0.434 |
uana | +0.393 |
orescence | +0.391 |
Neg logit contributions | |
wipes | -0.629 |
ignores | -0.592 |
ath | -0.562 |
misses | -0.548 |
Typhoon | -0.542 |
Token | could |
Token ID | 714 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
xual | +2.501 |
rolet | +2.314 |
�� | +2.298 |
uana | +2.148 |
ukong | +2.142 |
Neg logit contributions | |
wipes | -2.202 |
ignores | -2.008 |
ath | -1.926 |
Typhoon | -1.888 |
weak | -1.850 |
Token | a |
Token ID | 257 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
xual | +0.765 |
rolet | +0.695 |
�� | +0.691 |
uana | +0.640 |
orescence | +0.639 |
Neg logit contributions | |
wipes | -0.898 |
ignores | -0.833 |
ath | -0.801 |
misses | -0.769 |
Typhoon | -0.759 |
Token | man |
Token ID | 582 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
xual | +0.553 |
rolet | +0.507 |
�� | +0.505 |
uana | +0.468 |
orescence | +0.463 |
Neg logit contributions | |
wipes | -0.620 |
ignores | -0.573 |
ath | -0.551 |
crossings | -0.527 |
misses | -0.526 |
Token | enjoy |
Token ID | 2883 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
xual | +0.530 |
rolet | +0.483 |
�� | +0.478 |
uana | +0.445 |
orescence | +0.444 |
Neg logit contributions | |
wipes | -0.587 |
ignores | -0.540 |
ath | -0.518 |
misses | -0.500 |
Typhoon | -0.499 |
Token | being |
Token ID | 852 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
xual | +0.457 |
rolet | +0.414 |
�� | +0.410 |
uana | +0.380 |
orescence | +0.379 |
Neg logit contributions | |
wipes | -0.542 |
ignores | -0.503 |
ath | -0.484 |
misses | -0.464 |
Typhoon | -0.462 |
Token | Read |
Token ID | 5569 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
wipes | +0.183 |
ignores | +0.164 |
ath | +0.156 |
misses | +0.148 |
crossings | +0.147 |
Neg logit contributions | |
xual | -0.245 |
rolet | -0.233 |
�� | -0.231 |
uana | -0.218 |
ukong | -0.216 |
Token | More |
Token ID | 3125 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
xual | +0.079 |
rolet | +0.073 |
�� | +0.073 |
uana | +0.067 |
ancer | +0.067 |
Neg logit contributions | |
wipes | -0.084 |
ignores | -0.077 |
ath | -0.074 |
misses | -0.071 |
Typhoon | -0.070 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
xual | +0.797 |
rolet | +0.736 |
�� | +0.732 |
uana | +0.673 |
ancer | +0.669 |
Neg logit contributions | |
wipes | -1.166 |
ignores | -1.071 |
ath | -1.027 |
crossings | -1.002 |
misses | -0.990 |
Token | H |
Token ID | 39 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
xual | +0.205 |
rolet | +0.193 |
�� | +0.192 |
uana | +0.182 |
ukong | +0.180 |
Neg logit contributions | |
wipes | -0.162 |
ignores | -0.146 |
ath | -0.138 |
misses | -0.133 |
crossings | -0.132 |
Token | ats |
Token ID | 1381 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
xual | +0.850 |
rolet | +0.797 |
�� | +0.777 |
uana | +0.748 |
orescence | +0.738 |
Neg logit contributions | |
wipes | -0.944 |
ignores | -0.871 |
ath | -0.828 |
misses | -0.797 |
crossings | -0.790 |
Token | une |
Token ID | 1726 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
xual | +1.072 |
rolet | +0.972 |
�� | +0.966 |
uana | +0.923 |
ault | +0.895 |
Neg logit contributions | |
wipes | -1.278 |
ignores | -1.188 |
ath | -1.143 |
crossings | -1.101 |
misses | -1.099 |
Token | Mik |
Token ID | 17722 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
xual | +1.998 |
rolet | +1.755 |
�� | +1.734 |
uana | +1.610 |
enture | +1.593 |
Neg logit contributions | |
wipes | -2.827 |
ignores | -2.637 |
ath | -2.553 |
misses | -2.455 |
successes | -2.423 |
Token | u |
Token ID | 84 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
wipes | +0.182 |
ignores | +0.168 |
ath | +0.161 |
misses | +0.154 |
Typhoon | +0.151 |
Neg logit contributions | |
xual | -0.186 |
rolet | -0.173 |
�� | -0.170 |
uana | -0.162 |
orescence | -0.159 |
Token | : |
Token ID | 25 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
xual | +0.190 |
rolet | +0.174 |
�� | +0.174 |
uana | +0.162 |
orescence | +0.160 |
Neg logit contributions | |
wipes | -0.189 |
ignores | -0.173 |
ath | -0.168 |
misses | -0.159 |
crossings | -0.158 |
Token | Project |
Token ID | 4935 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
xual | +0.992 |
�� | +0.912 |
rolet | +0.904 |
uana | +0.832 |
ukong | +0.831 |
Neg logit contributions | |
wipes | -1.117 |
ignores | -1.029 |
ath | -0.988 |
misses | -0.949 |
crossings | -0.939 |
Token | Div |
Token ID | 4777 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
xual | +1.019 |
rolet | +0.938 |
�� | +0.934 |
ukong | +0.861 |
orescence | +0.860 |
Neg logit contributions | |
wipes | -1.092 |
ignores | -1.009 |
ath | -0.963 |
misses | -0.929 |
crossings | -0.919 |
Token | . |
Token ID | 13 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
xual | +0.591 |
rolet | +0.548 |
�� | +0.544 |
uana | +0.500 |
orescence | +0.500 |
Neg logit contributions | |
wipes | -0.660 |
ignores | -0.613 |
ath | -0.584 |
misses | -0.566 |
Typhoon | -0.559 |
Token | The |
Token ID | 383 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
xual | +0.221 |
rolet | +0.211 |
�� | +0.206 |
Stay | +0.192 |
uana | +0.191 |
Neg logit contributions | |
wipes | -0.219 |
ignores | -0.198 |
ath | -0.190 |
misses | -0.182 |
crossings | -0.181 |
Token | poll |
Token ID | 3278 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
wipes | +0.276 |
ignores | +0.257 |
ath | +0.245 |
misses | +0.233 |
Typhoon | +0.232 |
Neg logit contributions | |
xual | -0.273 |
rolet | -0.255 |
�� | -0.253 |
orescence | -0.235 |
uana | -0.235 |
Token | below |
Token ID | 2174 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
wipes | +1.290 |
ignores | +1.178 |
ath | +1.134 |
misses | +1.080 |
Typhoon | +1.078 |
Neg logit contributions | |
xual | -1.417 |
�� | -1.317 |
rolet | -1.312 |
orescence | -1.218 |
uana | -1.215 |
Token | , |
Token ID | 11 |
Feature activation | +3.24e-03 |
Pos logit contributions | |
xual | +0.263 |
rolet | +0.245 |
�� | +0.244 |
orescence | +0.229 |
ancer | +0.226 |
Neg logit contributions | |
wipes | -0.208 |
ignores | -0.187 |
ath | -0.183 |
Typhoon | -0.174 |
Nato | -0.171 |
Token | commissioned |
Token ID | 20462 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
wipes | +0.010 |
ignores | +0.009 |
ath | +0.009 |
misses | +0.009 |
Typhoon | +0.009 |
Neg logit contributions | |
xual | -0.009 |
rolet | -0.009 |
�� | -0.008 |
orescence | -0.008 |
uana | -0.008 |
Token | by |
Token ID | 416 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
xual | +2.139 |
rolet | +1.997 |
�� | +1.971 |
orescence | +1.833 |
enture | +1.814 |
Neg logit contributions | |
wipes | -2.599 |
ignores | -2.383 |
ath | -2.278 |
misses | -2.246 |
Typhoon | -2.218 |
Token | Bloomberg |
Token ID | 15689 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
wipes | +0.246 |
ignores | +0.230 |
ath | +0.220 |
misses | +0.212 |
Typhoon | +0.209 |
Neg logit contributions | |
xual | -0.198 |
rolet | -0.182 |
�� | -0.182 |
uana | -0.168 |
orescence | -0.167 |
Token | Politics |
Token ID | 17554 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
wipes | +0.204 |
ignores | +0.188 |
ath | +0.180 |
misses | +0.174 |
Typhoon | +0.172 |
Neg logit contributions | |
xual | -0.189 |
�� | -0.175 |
rolet | -0.174 |
uana | -0.161 |
orescence | -0.161 |
Token | and |
Token ID | 290 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
xual | +0.295 |
�� | +0.273 |
rolet | +0.271 |
orescence | +0.249 |
uana | +0.248 |
Neg logit contributions | |
wipes | -0.340 |
ignores | -0.314 |
ath | -0.302 |
misses | -0.292 |
Typhoon | -0.290 |
Token | Saint |
Token ID | 9281 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
wipes | +0.221 |
ignores | +0.203 |
ath | +0.195 |
misses | +0.188 |
Typhoon | +0.185 |
Neg logit contributions | |
xual | -0.201 |
�� | -0.186 |
rolet | -0.185 |
uana | -0.171 |
orescence | -0.170 |
Token | - |
Token ID | 12 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
xual | +0.396 |
�� | +0.369 |
rolet | +0.358 |
uana | +0.336 |
enture | +0.333 |
Neg logit contributions | |
wipes | -0.453 |
ignores | -0.415 |
ath | -0.397 |
misses | -0.380 |
crossings | -0.376 |
Token | 1 |
Token ID | 16 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
xual | +0.753 |
�� | +0.687 |
rolet | +0.686 |
uana | +0.652 |
ukong | +0.629 |
Neg logit contributions | |
wipes | -0.935 |
ignores | -0.868 |
ath | -0.828 |
misses | -0.807 |
crossings | -0.793 |
Token | / |
Token ID | 14 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
xual | +1.088 |
�� | +1.006 |
rolet | +0.976 |
uana | +0.927 |
enture | +0.905 |
Neg logit contributions | |
wipes | -1.287 |
ignores | -1.188 |
ath | -1.137 |
misses | -1.099 |
crossings | -1.086 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
xual | +1.507 |
rolet | +1.349 |
�� | +1.338 |
uana | +1.234 |
ukong | +1.202 |
Neg logit contributions | |
wipes | -2.342 |
ignores | -2.165 |
ath | -2.113 |
misses | -2.025 |
Typhoon | -2.011 |
Token | "] |
Token ID | 8973 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
xual | +0.512 |
�� | +0.470 |
rolet | +0.461 |
uana | +0.434 |
enture | +0.427 |
Neg logit contributions | |
wipes | -0.606 |
ignores | -0.555 |
ath | -0.533 |
crossings | -0.510 |
misses | -0.509 |
Token | [ |
Token ID | 685 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
xual | +0.324 |
�� | +0.299 |
rolet | +0.298 |
orescence | +0.275 |
uana | +0.274 |
Neg logit contributions | |
wipes | -0.323 |
ignores | -0.298 |
ath | -0.288 |
misses | -0.276 |
Typhoon | -0.270 |
Token | EC |
Token ID | 2943 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
xual | +2.501 |
rolet | +2.408 |
�� | +2.358 |
uana | +2.324 |
enture | +2.219 |
Neg logit contributions | |
wipes | -2.166 |
ignores | -1.990 |
ath | -1.873 |
misses | -1.794 |
successes | -1.766 |
Token | O |
Token ID | 46 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
wipes | +0.178 |
ignores | +0.164 |
ath | +0.157 |
misses | +0.151 |
successes | +0.148 |
Neg logit contributions | |
xual | -0.202 |
�� | -0.187 |
rolet | -0.186 |
orescence | -0.173 |
uana | -0.170 |
Token | " |
Token ID | 366 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
xual | +0.489 |
�� | +0.457 |
rolet | +0.456 |
orescence | +0.425 |
uana | +0.424 |
Neg logit contributions | |
wipes | -0.342 |
ignores | -0.311 |
ath | -0.295 |
misses | -0.280 |
Typhoon | -0.274 |
Token | A |
Token ID | 32 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
xual | +1.105 |
�� | +1.043 |
rolet | +1.043 |
uana | +1.002 |
enture | +0.967 |
Neg logit contributions | |
wipes | -0.809 |
ignores | -0.724 |
ath | -0.675 |
misses | -0.655 |
Typhoon | -0.653 |
Token | 46 |
Token ID | 3510 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
xual | +1.261 |
rolet | +1.179 |
�� | +1.159 |
uana | +1.101 |
orescence | +1.091 |
Neg logit contributions | |
wipes | -1.010 |
ignores | -0.912 |
ath | -0.862 |
misses | -0.832 |
Typhoon | -0.824 |
Token | ov |
Token ID | 709 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
xual | +0.792 |
�� | +0.745 |
rolet | +0.743 |
uana | +0.699 |
orescence | +0.697 |
Neg logit contributions | |
wipes | -0.472 |
ignores | -0.422 |
ath | -0.398 |
misses | -0.376 |
Typhoon | -0.367 |
Token | , |
Token ID | 11 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
xual | +0.339 |
rolet | +0.313 |
�� | +0.310 |
orescence | +0.288 |
uana | +0.287 |
Neg logit contributions | |
wipes | -0.346 |
ignores | -0.318 |
ath | -0.309 |
misses | -0.293 |
Typhoon | -0.292 |
Token | owner |
Token ID | 4870 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
xual | +0.540 |
rolet | +0.496 |
�� | +0.494 |
orescence | +0.454 |
uana | +0.452 |
Neg logit contributions | |
wipes | -0.695 |
ignores | -0.642 |
ath | -0.618 |
misses | -0.595 |
successes | -0.585 |
Token | of |
Token ID | 286 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
wipes | +0.142 |
ignores | +0.131 |
ath | +0.125 |
misses | +0.120 |
Typhoon | +0.118 |
Neg logit contributions | |
xual | -0.138 |
�� | -0.128 |
rolet | -0.127 |
uana | -0.117 |
orescence | -0.117 |
Token | Olymp |
Token ID | 7001 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
xual | +0.136 |
rolet | +0.126 |
�� | +0.124 |
uana | +0.116 |
orescence | +0.116 |
Neg logit contributions | |
wipes | -0.150 |
ignores | -0.139 |
ath | -0.132 |
misses | -0.128 |
successes | -0.125 |
Token | Oil |
Token ID | 11474 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
xual | +0.678 |
rolet | +0.630 |
�� | +0.616 |
uana | +0.590 |
orescence | +0.583 |
Neg logit contributions | |
wipes | -0.670 |
ignores | -0.619 |
ath | -0.592 |
misses | -0.571 |
Typhoon | -0.556 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
xual | +2.177 |
�� | +1.968 |
rolet | +1.945 |
uana | +1.880 |
ancer | +1.821 |
Neg logit contributions | |
wipes | -2.548 |
ignores | -2.344 |
ath | -2.301 |
misses | -2.159 |
successes | -2.148 |
Token | which |
Token ID | 543 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
xual | +0.528 |
rolet | +0.488 |
�� | +0.482 |
uana | +0.454 |
ancer | +0.452 |
Neg logit contributions | |
wipes | -0.570 |
ignores | -0.522 |
ath | -0.509 |
weak | -0.479 |
misses | -0.478 |
Token | received |
Token ID | 2722 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
xual | +0.221 |
�� | +0.206 |
rolet | +0.205 |
uana | +0.192 |
ancer | +0.192 |
Neg logit contributions | |
wipes | -0.189 |
ignores | -0.171 |
ath | -0.165 |
misses | -0.155 |
Typhoon | -0.154 |
Token | 7 |
Token ID | 767 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
xual | +0.431 |
rolet | +0.396 |
�� | +0.390 |
enture | +0.365 |
uana | +0.365 |
Neg logit contributions | |
wipes | -0.479 |
ignores | -0.445 |
ath | -0.424 |
misses | -0.408 |
weak | -0.397 |
Token | 15 |
Token ID | 1314 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
wipes | +0.266 |
ignores | +0.244 |
ath | +0.233 |
misses | +0.223 |
Typhoon | +0.218 |
Neg logit contributions | |
xual | -0.290 |
�� | -0.270 |
rolet | -0.269 |
uana | -0.248 |
orescence | -0.248 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
xual | +0.097 |
rolet | +0.090 |
�� | +0.089 |
uana | +0.083 |
orescence | +0.083 |
Neg logit contributions | |
wipes | -0.092 |
ignores | -0.084 |
ath | -0.080 |
misses | -0.077 |
crossings | -0.076 |
Token |
|
Token ID | 198 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
xual | +0.385 |
�� | +0.363 |
rolet | +0.358 |
uana | +0.336 |
orescence | +0.336 |
Neg logit contributions | |
wipes | -0.268 |
ignores | -0.243 |
ath | -0.231 |
misses | -0.220 |
Typhoon | -0.214 |
Token | In |
Token ID | 818 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
xual | +0.318 |
rolet | +0.297 |
�� | +0.295 |
uana | +0.278 |
orescence | +0.276 |
Neg logit contributions | |
wipes | -0.262 |
ignores | -0.237 |
ath | -0.225 |
misses | -0.215 |
crossings | -0.214 |
Token | a |
Token ID | 257 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
xual | +0.172 |
�� | +0.156 |
rolet | +0.156 |
uana | +0.143 |
orescence | +0.143 |
Neg logit contributions | |
wipes | -0.216 |
ignores | -0.200 |
ath | -0.192 |
misses | -0.185 |
Typhoon | -0.183 |
Token | recent |
Token ID | 2274 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
xual | +0.807 |
rolet | +0.735 |
�� | +0.733 |
enture | +0.678 |
orescence | +0.678 |
Neg logit contributions | |
wipes | -0.833 |
ignores | -0.765 |
ath | -0.729 |
misses | -0.700 |
crossings | -0.697 |
Token | article |
Token ID | 2708 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
xual | +1.479 |
rolet | +1.361 |
�� | +1.344 |
orescence | +1.259 |
enture | +1.254 |
Neg logit contributions | |
wipes | -1.635 |
ignores | -1.501 |
ath | -1.421 |
misses | -1.373 |
crossings | -1.368 |
Token | for |
Token ID | 329 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
xual | +2.265 |
rolet | +2.040 |
�� | +2.036 |
orescence | +1.886 |
uana | +1.860 |
Neg logit contributions | |
wipes | -2.511 |
ignores | -2.288 |
ath | -2.174 |
misses | -2.123 |
crossings | -2.117 |
Token | World |
Token ID | 2159 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
xual | +1.107 |
�� | +1.021 |
rolet | +1.016 |
uana | +0.944 |
orescence | +0.943 |
Neg logit contributions | |
wipes | -1.143 |
ignores | -1.050 |
ath | -0.990 |
misses | -0.964 |
crossings | -0.946 |
Token | Net |
Token ID | 7934 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
xual | +0.008 |
�� | +0.007 |
rolet | +0.007 |
orescence | +0.006 |
uana | +0.006 |
Neg logit contributions | |
wipes | -0.008 |
ignores | -0.007 |
ath | -0.007 |
misses | -0.007 |
crossings | -0.006 |
Token | Daily |
Token ID | 28545 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
xual | +1.152 |
�� | +1.073 |
rolet | +1.070 |
ault | +0.978 |
uana | +0.969 |
Neg logit contributions | |
wipes | -1.369 |
ignores | -1.262 |
ath | -1.233 |
misses | -1.172 |
crossings | -1.162 |
Token | , |
Token ID | 11 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
xual | +0.654 |
�� | +0.598 |
rolet | +0.592 |
uana | +0.543 |
orescence | +0.543 |
Neg logit contributions | |
wipes | -0.783 |
ignores | -0.724 |
ath | -0.697 |
misses | -0.674 |
Typhoon | -0.665 |
Token | generated |
Token ID | 7560 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
wipes | +0.962 |
ignores | +0.887 |
ath | +0.847 |
misses | +0.815 |
successes | +0.800 |
Neg logit contributions | |
xual | -0.951 |
rolet | -0.872 |
�� | -0.863 |
uana | -0.806 |
orescence | -0.802 |
Token | by |
Token ID | 416 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
xual | +0.048 |
rolet | +0.043 |
�� | +0.043 |
orescence | +0.040 |
uana | +0.040 |
Neg logit contributions | |
wipes | -0.052 |
ignores | -0.048 |
ath | -0.046 |
misses | -0.044 |
successes | -0.043 |
Token | Hurricane |
Token ID | 16004 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
wipes | +0.455 |
ignores | +0.425 |
ath | +0.403 |
misses | +0.388 |
successes | +0.381 |
Neg logit contributions | |
xual | -0.407 |
rolet | -0.379 |
�� | -0.372 |
uana | -0.345 |
orescence | -0.344 |
Token | Matthew |
Token ID | 9308 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
wipes | +0.677 |
ignores | +0.620 |
ath | +0.575 |
misses | +0.550 |
successes | +0.543 |
Neg logit contributions | |
xual | -0.976 |
rolet | -0.925 |
�� | -0.913 |
uana | -0.863 |
orescence | -0.862 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
wipes | +1.501 |
ignores | +1.385 |
ath | +1.328 |
misses | +1.274 |
successes | +1.247 |
Neg logit contributions | |
xual | -1.530 |
rolet | -1.409 |
�� | -1.407 |
uana | -1.304 |
orescence | -1.300 |
Token | Credit |
Token ID | 10504 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
wipes | +0.416 |
ignores | +0.386 |
ath | +0.371 |
misses | +0.357 |
crossings | +0.354 |
Neg logit contributions | |
xual | -0.339 |
rolet | -0.316 |
�� | -0.307 |
uana | -0.286 |
orescence | -0.283 |
Token | : |
Token ID | 25 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
wipes | +2.272 |
ignores | +2.117 |
ath | +2.037 |
misses | +1.964 |
Typhoon | +1.944 |
Neg logit contributions | |
xual | -2.026 |
�� | -1.888 |
rolet | -1.838 |
orescence | -1.708 |
uana | -1.685 |
Token | NO |
Token ID | 15285 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
wipes | +0.029 |
ignores | +0.027 |
ath | +0.026 |
misses | +0.025 |
crossings | +0.024 |
Neg logit contributions | |
xual | -0.034 |
rolet | -0.032 |
�� | -0.031 |
uana | -0.030 |
orescence | -0.029 |
Token | AA |
Token ID | 3838 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
wipes | +0.264 |
ignores | +0.236 |
ath | +0.226 |
misses | +0.211 |
successes | +0.207 |
Neg logit contributions | |
xual | -0.400 |
�� | -0.376 |
rolet | -0.373 |
uana | -0.352 |
orescence | -0.349 |
Token | Around |
Token ID | 16824 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
wipes | +1.531 |
ignores | +1.414 |
ath | +1.351 |
misses | +1.299 |
crossings | +1.272 |
Neg logit contributions | |
xual | -1.544 |
rolet | -1.433 |
�� | -1.424 |
uana | -1.322 |
orescence | -1.314 |
Token | the |
Token ID | 262 |
Feature activation | -4.48e-03 |
Pos logit contributions | |
wipes | +0.471 |
ignores | +0.437 |
ath | +0.418 |
misses | +0.399 |
successes | +0.392 |
Neg logit contributions | |
xual | -0.427 |
rolet | -0.399 |
�� | -0.393 |
uana | -0.367 |
orescence | -0.365 |
Token | - |
Token ID | 532 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
wipes | +0.389 |
ignores | +0.356 |
ath | +0.342 |
misses | +0.328 |
crossings | +0.324 |
Neg logit contributions | |
xual | -0.396 |
�� | -0.362 |
rolet | -0.361 |
uana | -0.336 |
orescence | -0.333 |
Token | December |
Token ID | 3426 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
wipes | +0.245 |
ignores | +0.227 |
ath | +0.216 |
misses | +0.208 |
Typhoon | +0.205 |
Neg logit contributions | |
xual | -0.264 |
�� | -0.244 |
rolet | -0.243 |
orescence | -0.224 |
uana | -0.224 |
Token | 5 |
Token ID | 642 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
xual | +0.415 |
�� | +0.396 |
rolet | +0.384 |
orescence | +0.360 |
uana | +0.359 |
Neg logit contributions | |
wipes | -0.346 |
ignores | -0.318 |
ath | -0.303 |
misses | -0.293 |
Typhoon | -0.285 |
Token | , |
Token ID | 11 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
xual | +0.076 |
�� | +0.071 |
rolet | +0.070 |
orescence | +0.065 |
uana | +0.064 |
Neg logit contributions | |
wipes | -0.076 |
ignores | -0.071 |
ath | -0.068 |
misses | -0.066 |
Typhoon | -0.065 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
xual | +0.022 |
�� | +0.021 |
rolet | +0.020 |
orescence | +0.019 |
uana | +0.019 |
Neg logit contributions | |
wipes | -0.017 |
ignores | -0.016 |
ath | -0.015 |
misses | -0.015 |
Typhoon | -0.014 |
Token | Que |
Token ID | 15681 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
xual | +0.150 |
rolet | +0.140 |
�� | +0.139 |
uana | +0.131 |
ukong | +0.130 |
Neg logit contributions | |
wipes | -0.113 |
ignores | -0.102 |
ath | -0.097 |
misses | -0.092 |
Typhoon | -0.090 |
Token | ers |
Token ID | 364 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
wipes | +2.237 |
ignores | +2.051 |
ath | +1.947 |
misses | +1.880 |
successes | +1.844 |
Neg logit contributions | |
�� | -2.586 |
xual | -2.577 |
rolet | -2.465 |
exting | -2.364 |
uana | -2.289 |
Token | are |
Token ID | 389 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
wipes | +0.704 |
ignores | +0.627 |
ath | +0.590 |
misses | +0.556 |
Typhoon | +0.541 |
Neg logit contributions | |
xual | -1.276 |
�� | -1.205 |
rolet | -1.198 |
uana | -1.129 |
orescence | -1.127 |
Token | Here |
Token ID | 3423 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
wipes | +0.568 |
ignores | +0.522 |
ath | +0.498 |
misses | +0.478 |
Typhoon | +0.470 |
Neg logit contributions | |
xual | -0.583 |
rolet | -0.538 |
�� | -0.535 |
uana | -0.495 |
orescence | -0.491 |
Token | .... |
Token ID | 1106 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
wipes | +0.844 |
ignores | +0.771 |
ath | +0.747 |
misses | +0.711 |
crossings | +0.707 |
Neg logit contributions | |
xual | -0.804 |
rolet | -0.763 |
�� | -0.741 |
uana | -0.699 |
orescence | -0.693 |
Token |
|
Token ID | 198 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
wipes | +0.976 |
ignores | +0.893 |
ath | +0.855 |
misses | +0.816 |
successes | +0.802 |
Neg logit contributions | |
xual | -1.100 |
rolet | -1.018 |
�� | -1.017 |
uana | -0.944 |
orescence | -0.942 |
Token | attempt |
Token ID | 2230 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
wipes | +0.157 |
ignores | +0.144 |
ath | +0.133 |
misses | +0.127 |
Typhoon | +0.127 |
Neg logit contributions | |
xual | -0.229 |
rolet | -0.215 |
�� | -0.214 |
uana | -0.202 |
orescence | -0.202 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
xual | +0.489 |
�� | +0.449 |
rolet | +0.447 |
orescence | +0.408 |
uana | +0.405 |
Neg logit contributions | |
wipes | -0.583 |
ignores | -0.539 |
ath | -0.519 |
misses | -0.502 |
Typhoon | -0.499 |
Token | go |
Token ID | 467 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
xual | +0.314 |
rolet | +0.292 |
�� | +0.291 |
orescence | +0.271 |
uana | +0.271 |
Neg logit contributions | |
wipes | -0.291 |
ignores | -0.267 |
ath | -0.257 |
misses | -0.247 |
Typhoon | -0.244 |
Token | get |
Token ID | 651 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
xual | +0.036 |
�� | +0.033 |
rolet | +0.033 |
uana | +0.031 |
orescence | +0.031 |
Neg logit contributions | |
wipes | -0.034 |
ignores | -0.031 |
ath | -0.030 |
misses | -0.029 |
Typhoon | -0.029 |
Token | Ber |
Token ID | 4312 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
xual | +0.230 |
�� | +0.213 |
rolet | +0.212 |
orescence | +0.198 |
uana | +0.198 |
Neg logit contributions | |
wipes | -0.246 |
ignores | -0.229 |
ath | -0.218 |
misses | -0.209 |
Typhoon | -0.207 |
Token | gd |
Token ID | 21287 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
wipes | +0.433 |
ignores | +0.383 |
ath | +0.362 |
misses | +0.340 |
Typhoon | +0.329 |
Neg logit contributions | |
xual | -0.795 |
�� | -0.750 |
rolet | -0.743 |
orescence | -0.699 |
uana | -0.698 |
Token | ahl |
Token ID | 15668 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
wipes | +2.176 |
ignores | +2.001 |
ath | +1.894 |
misses | +1.843 |
wi | +1.768 |
Neg logit contributions | |
xual | -2.792 |
�� | -2.657 |
rolet | -2.538 |
orescence | -2.375 |
exting | -2.365 |
Token | in |
Token ID | 287 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
wipes | +1.173 |
ignores | +1.089 |
ath | +1.048 |
misses | +1.011 |
Typhoon | +0.995 |
Neg logit contributions | |
xual | -0.976 |
�� | -0.895 |
rolet | -0.891 |
uana | -0.816 |
orescence | -0.813 |
Token | the |
Token ID | 262 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
wipes | +0.425 |
ignores | +0.393 |
ath | +0.377 |
misses | +0.363 |
Typhoon | +0.362 |
Neg logit contributions | |
xual | -0.356 |
�� | -0.330 |
rolet | -0.325 |
uana | -0.303 |
orescence | -0.301 |
Token | way |
Token ID | 835 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
wipes | +0.168 |
ignores | +0.157 |
ath | +0.148 |
misses | +0.142 |
Typhoon | +0.142 |
Neg logit contributions | |
xual | -0.151 |
�� | -0.141 |
rolet | -0.141 |
orescence | -0.130 |
uana | -0.130 |
Token | that |
Token ID | 326 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
xual | +0.487 |
�� | +0.449 |
rolet | +0.445 |
uana | +0.409 |
orescence | +0.409 |
Neg logit contributions | |
wipes | -0.592 |
ignores | -0.547 |
ath | -0.527 |
misses | -0.510 |
Typhoon | -0.504 |
Token | this |
Token ID | 428 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
wipes | +0.254 |
ignores | +0.235 |
ath | +0.228 |
misses | +0.217 |
Typhoon | +0.216 |
Neg logit contributions | |
xual | -0.201 |
rolet | -0.183 |
�� | -0.183 |
ukong | -0.169 |
uana | -0.168 |
Token | , |
Token ID | 11 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
xual | +0.072 |
�� | +0.065 |
rolet | +0.065 |
ukong | +0.060 |
orescence | +0.060 |
Neg logit contributions | |
wipes | -0.078 |
ignores | -0.071 |
ath | -0.069 |
misses | -0.066 |
Typhoon | -0.065 |
Token | as |
Token ID | 355 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
xual | +0.278 |
rolet | +0.255 |
�� | +0.251 |
ukong | +0.234 |
orescence | +0.233 |
Neg logit contributions | |
wipes | -0.292 |
ignores | -0.266 |
ath | -0.257 |
misses | -0.245 |
Typhoon | -0.244 |
Token | Jaguars |
Token ID | 28392 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
xual | +0.379 |
�� | +0.349 |
rolet | +0.347 |
uana | +0.321 |
ukong | +0.320 |
Neg logit contributions | |
wipes | -0.404 |
ignores | -0.370 |
ath | -0.356 |
misses | -0.340 |
Typhoon | -0.336 |
Token | executive |
Token ID | 4640 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
xual | +0.180 |
rolet | +0.168 |
�� | +0.168 |
ukong | +0.156 |
uana | +0.155 |
Neg logit contributions | |
wipes | -0.177 |
ignores | -0.162 |
ath | -0.154 |
misses | -0.147 |
crossings | -0.145 |
Token | vice |
Token ID | 7927 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
xual | +0.149 |
�� | +0.138 |
rolet | +0.138 |
uana | +0.129 |
ukong | +0.129 |
Neg logit contributions | |
wipes | -0.144 |
ignores | -0.132 |
ath | -0.126 |
misses | -0.120 |
weak | -0.119 |
Token | president |
Token ID | 1893 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
wipes | +2.385 |
ignores | +2.179 |
ath | +2.080 |
misses | +2.001 |
Typhoon | +1.965 |
Neg logit contributions | |
xual | -2.637 |
rolet | -2.474 |
�� | -2.468 |
orescence | -2.281 |
uana | -2.273 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
wipes | +1.287 |
ignores | +1.184 |
ath | +1.135 |
misses | +1.085 |
Typhoon | +1.070 |
Neg logit contributions | |
xual | -1.266 |
�� | -1.174 |
rolet | -1.167 |
orescence | -1.081 |
uana | -1.080 |
Token | C |
Token ID | 327 |
Feature activation | -7.69e-03 |
Pos logit contributions | |
wipes | +0.488 |
ignores | +0.448 |
ath | +0.430 |
misses | +0.407 |
successes | +0.404 |
Neg logit contributions | |
xual | -0.516 |
rolet | -0.481 |
�� | -0.473 |
uana | -0.446 |
orescence | -0.441 |
Token | ough |
Token ID | 619 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
xual | +0.020 |
rolet | +0.018 |
�� | +0.018 |
uana | +0.017 |
ukong | +0.017 |
Neg logit contributions | |
wipes | -0.027 |
ignores | -0.025 |
ath | -0.024 |
misses | -0.023 |
Typhoon | -0.023 |
Token | lin |
Token ID | 2815 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
xual | +0.740 |
rolet | +0.683 |
�� | +0.651 |
uana | +0.643 |
ancer | +0.634 |
Neg logit contributions | |
wipes | -0.750 |
ignores | -0.687 |
ath | -0.677 |
Typhoon | -0.646 |
Nato | -0.634 |
Token | a |
Token ID | 257 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
wipes | +0.770 |
ignores | +0.710 |
ath | +0.674 |
misses | +0.658 |
Typhoon | +0.643 |
Neg logit contributions | |
xual | -0.729 |
rolet | -0.671 |
�� | -0.669 |
uana | -0.618 |
orescence | -0.614 |
Token | cumulative |
Token ID | 23818 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
wipes | +0.458 |
ignores | +0.424 |
ath | +0.400 |
misses | +0.389 |
crossings | +0.380 |
Neg logit contributions | |
xual | -0.460 |
rolet | -0.422 |
�� | -0.422 |
uana | -0.389 |
orescence | -0.387 |
Token | disp |
Token ID | 4596 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
xual | +0.206 |
rolet | +0.188 |
�� | +0.186 |
orescence | +0.174 |
uana | +0.174 |
Neg logit contributions | |
wipes | -0.194 |
ignores | -0.180 |
ath | -0.166 |
misses | -0.165 |
crossings | -0.161 |
Token | ersion |
Token ID | 6900 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
xual | +0.170 |
rolet | +0.154 |
�� | +0.136 |
orescence | +0.133 |
uana | +0.128 |
Neg logit contributions | |
wipes | -0.419 |
ignores | -0.395 |
ath | -0.382 |
misses | -0.374 |
Typhoon | -0.371 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
wipes | +0.137 |
ignores | +0.127 |
ath | +0.120 |
misses | +0.118 |
Typhoon | +0.116 |
Neg logit contributions | |
xual | -0.130 |
rolet | -0.118 |
�� | -0.118 |
orescence | -0.110 |
uana | -0.109 |
Token | in |
Token ID | 259 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
wipes | +0.413 |
ignores | +0.379 |
ath | +0.359 |
misses | +0.351 |
Typhoon | +0.343 |
Neg logit contributions | |
xual | -0.441 |
rolet | -0.406 |
�� | -0.402 |
uana | -0.377 |
orescence | -0.376 |
Token | which |
Token ID | 543 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
wipes | +2.238 |
ignores | +2.081 |
ath | +2.003 |
misses | +1.935 |
Typhoon | +1.904 |
Neg logit contributions | |
xual | -1.796 |
�� | -1.645 |
rolet | -1.638 |
uana | -1.497 |
orescence | -1.492 |
Token | on |
Token ID | 319 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
wipes | +0.059 |
ignores | +0.055 |
ath | +0.052 |
misses | +0.051 |
Typhoon | +0.050 |
Neg logit contributions | |
xual | -0.052 |
rolet | -0.047 |
�� | -0.047 |
uana | -0.043 |
orescence | -0.043 |
Token | top |
Token ID | 1353 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
wipes | +0.322 |
ignores | +0.301 |
ath | +0.287 |
misses | +0.279 |
Typhoon | +0.276 |
Neg logit contributions | |
xual | -0.252 |
rolet | -0.228 |
�� | -0.227 |
uana | -0.210 |
orescence | -0.209 |
Token | of |
Token ID | 286 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
wipes | +0.151 |
ignores | +0.139 |
ath | +0.132 |
misses | +0.129 |
Typhoon | +0.127 |
Neg logit contributions | |
xual | -0.144 |
�� | -0.133 |
rolet | -0.132 |
uana | -0.123 |
orescence | -0.123 |
Token | everything |
Token ID | 2279 |
Feature activation | +6.15e-03 |
Pos logit contributions | |
wipes | +0.496 |
ignores | +0.461 |
ath | +0.441 |
misses | +0.429 |
Typhoon | +0.423 |
Neg logit contributions | |
xual | -0.394 |
rolet | -0.359 |
�� | -0.356 |
uana | -0.330 |
orescence | -0.327 |
Token | with |
Token ID | 351 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
xual | +0.886 |
�� | +0.808 |
rolet | +0.806 |
uana | +0.755 |
orescence | +0.751 |
Neg logit contributions | |
wipes | -0.914 |
ignores | -0.845 |
ath | -0.805 |
Typhoon | -0.779 |
misses | -0.779 |
Token | fellow |
Token ID | 5891 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
xual | +0.125 |
rolet | +0.113 |
�� | +0.113 |
uana | +0.104 |
orescence | +0.104 |
Neg logit contributions | |
wipes | -0.151 |
ignores | -0.142 |
ath | -0.134 |
misses | -0.130 |
crossings | -0.128 |
Token | parliament |
Token ID | 8540 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
xual | +0.159 |
rolet | +0.147 |
�� | +0.146 |
orescence | +0.136 |
uana | +0.135 |
Neg logit contributions | |
wipes | -0.169 |
ignores | -0.157 |
ath | -0.149 |
misses | -0.144 |
Typhoon | -0.140 |
Token | arians |
Token ID | 13517 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
wipes | +0.402 |
ignores | +0.379 |
ath | +0.368 |
misses | +0.358 |
Typhoon | +0.355 |
Neg logit contributions | |
xual | -0.190 |
�� | -0.169 |
rolet | -0.169 |
orescence | -0.147 |
uana | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
xual | +0.181 |
rolet | +0.167 |
�� | +0.167 |
uana | +0.154 |
orescence | +0.154 |
Neg logit contributions | |
wipes | -0.193 |
ignores | -0.178 |
ath | -0.170 |
misses | -0.164 |
Typhoon | -0.161 |
Token |
|
Token ID | 198 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
wipes | +0.659 |
ignores | +0.598 |
ath | +0.571 |
misses | +0.547 |
crossings | +0.541 |
Neg logit contributions | |
xual | -0.733 |
rolet | -0.689 |
�� | -0.685 |
uana | -0.633 |
orescence | -0.631 |
Token |
|
Token ID | 198 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
wipes | +0.771 |
ignores | +0.701 |
ath | +0.669 |
misses | +0.637 |
Typhoon | +0.618 |
Neg logit contributions | |
xual | -1.279 |
�� | -1.220 |
rolet | -1.178 |
orescence | -1.123 |
uana | -1.113 |
Token | With |
Token ID | 3152 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
wipes | +0.564 |
ignores | +0.508 |
ath | +0.481 |
misses | +0.458 |
Typhoon | +0.447 |
Neg logit contributions | |
xual | -0.802 |
rolet | -0.754 |
�� | -0.753 |
uana | -0.706 |
orescence | -0.703 |
Token | the |
Token ID | 262 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
xual | +0.082 |
rolet | +0.075 |
�� | +0.075 |
uana | +0.069 |
orescence | +0.069 |
Neg logit contributions | |
wipes | -0.098 |
ignores | -0.091 |
ath | -0.087 |
misses | -0.084 |
Typhoon | -0.083 |
Token | Parliament |
Token ID | 8411 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
wipes | +0.273 |
ignores | +0.256 |
ath | +0.242 |
misses | +0.233 |
Typhoon | +0.228 |
Neg logit contributions | |
xual | -0.262 |
rolet | -0.242 |
�� | -0.242 |
orescence | -0.224 |
uana | -0.224 |
Token | being |
Token ID | 852 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
xual | +0.333 |
�� | +0.308 |
rolet | +0.306 |
orescence | +0.284 |
uana | +0.282 |
Neg logit contributions | |
wipes | -0.351 |
ignores | -0.325 |
ath | -0.311 |
misses | -0.300 |
Typhoon | -0.295 |
Token | c |
Token ID | 269 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
wipes | +0.200 |
ignores | +0.185 |
ath | +0.177 |
misses | +0.171 |
Typhoon | +0.169 |
Neg logit contributions | |
xual | -0.173 |
rolet | -0.162 |
�� | -0.161 |
uana | -0.151 |
orescence | -0.148 |
Token | ot |
Token ID | 313 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
wipes | +0.382 |
ignores | +0.354 |
ath | +0.341 |
misses | +0.330 |
Typhoon | +0.325 |
Neg logit contributions | |
xual | -0.313 |
rolet | -0.286 |
�� | -0.286 |
uana | -0.264 |
orescence | -0.262 |
Token | erie |
Token ID | 18287 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
wipes | +0.332 |
ignores | +0.310 |
ath | +0.300 |
misses | +0.291 |
successes | +0.288 |
Neg logit contributions | |
xual | -0.232 |
rolet | -0.209 |
�� | -0.208 |
uana | -0.190 |
orescence | -0.186 |
Token | of |
Token ID | 286 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
xual | +0.632 |
�� | +0.571 |
rolet | +0.568 |
uana | +0.531 |
orescence | +0.525 |
Neg logit contributions | |
wipes | -0.699 |
ignores | -0.645 |
ath | -0.616 |
misses | -0.599 |
Typhoon | -0.594 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
wipes | +0.169 |
ignores | +0.157 |
ath | +0.149 |
misses | +0.143 |
Typhoon | +0.142 |
Neg logit contributions | |
xual | -0.163 |
�� | -0.151 |
rolet | -0.150 |
uana | -0.139 |
orescence | -0.138 |
Token | super |
Token ID | 2208 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
wipes | +0.355 |
ignores | +0.329 |
ath | +0.312 |
misses | +0.301 |
Typhoon | +0.297 |
Neg logit contributions | |
xual | -0.350 |
�� | -0.323 |
rolet | -0.322 |
uana | -0.299 |
orescence | -0.296 |
Token | - |
Token ID | 12 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
wipes | +0.769 |
ignores | +0.711 |
ath | +0.681 |
misses | +0.655 |
Typhoon | +0.645 |
Neg logit contributions | |
xual | -0.746 |
�� | -0.688 |
rolet | -0.686 |
uana | -0.636 |
orescence | -0.630 |
Token | rich |
Token ID | 7527 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
xual | +0.493 |
rolet | +0.443 |
�� | +0.440 |
uana | +0.405 |
enture | +0.394 |
Neg logit contributions | |
wipes | -0.845 |
ignores | -0.792 |
ath | -0.763 |
misses | -0.745 |
Typhoon | -0.734 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
xual | +0.925 |
�� | +0.838 |
rolet | +0.830 |
uana | +0.778 |
orescence | +0.766 |
Neg logit contributions | |
wipes | -1.039 |
ignores | -0.967 |
ath | -0.926 |
misses | -0.897 |
Typhoon | -0.888 |
Token | And |
Token ID | 843 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
xual | +0.666 |
rolet | +0.625 |
�� | +0.609 |
Stay | +0.572 |
uana | +0.572 |
Neg logit contributions | |
wipes | -0.668 |
ignores | -0.607 |
ath | -0.580 |
crossings | -0.561 |
misses | -0.558 |
Token | then |
Token ID | 788 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
xual | +0.436 |
rolet | +0.400 |
�� | +0.395 |
uana | +0.370 |
orescence | +0.365 |
Neg logit contributions | |
wipes | -0.497 |
ignores | -0.460 |
ath | -0.442 |
misses | -0.427 |
Typhoon | -0.421 |
Token | brick |
Token ID | 17214 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
xual | +0.966 |
rolet | +0.896 |
�� | +0.882 |
uana | +0.823 |
orescence | +0.817 |
Neg logit contributions | |
wipes | -1.164 |
ignores | -1.095 |
ath | -1.030 |
misses | -1.009 |
crossings | -0.985 |
Token | building |
Token ID | 2615 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
xual | +0.199 |
rolet | +0.181 |
�� | +0.180 |
uana | +0.167 |
enture | +0.164 |
Neg logit contributions | |
wipes | -0.264 |
ignores | -0.246 |
ath | -0.234 |
misses | -0.230 |
successes | -0.225 |
Token | in |
Token ID | 287 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
wipes | +0.702 |
ignores | +0.649 |
ath | +0.619 |
misses | +0.599 |
Typhoon | +0.591 |
Neg logit contributions | |
xual | -0.687 |
�� | -0.626 |
rolet | -0.626 |
uana | -0.589 |
orescence | -0.589 |
Token | D |
Token ID | 360 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
wipes | +0.145 |
ignores | +0.135 |
ath | +0.128 |
misses | +0.124 |
crossings | +0.122 |
Neg logit contributions | |
xual | -0.121 |
rolet | -0.111 |
�� | -0.110 |
orescence | -0.103 |
ukong | -0.103 |
Token | ae |
Token ID | 3609 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
wipes | +0.173 |
ignores | +0.160 |
ath | +0.154 |
misses | +0.149 |
Typhoon | +0.146 |
Neg logit contributions | |
xual | -0.148 |
rolet | -0.137 |
�� | -0.136 |
uana | -0.126 |
orescence | -0.125 |
Token | je |
Token ID | 18015 |
Feature activation | +8.88e-02 |
Pos logit contributions | |
wipes | +0.726 |
ignores | +0.664 |
ath | +0.635 |
misses | +0.603 |
successes | +0.590 |
Neg logit contributions | |
xual | -0.915 |
rolet | -0.856 |
�� | -0.847 |
ukong | -0.794 |
uana | -0.794 |
Token | on |
Token ID | 261 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
wipes | +0.202 |
ignores | +0.176 |
ath | +0.174 |
misses | +0.156 |
crossings | +0.153 |
Neg logit contributions | |
xual | -0.332 |
rolet | -0.313 |
�� | -0.308 |
uana | -0.298 |
ancer | -0.298 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
wipes | +0.713 |
ignores | +0.660 |
ath | +0.639 |
misses | +0.610 |
crossings | +0.601 |
Neg logit contributions | |
xual | -0.645 |
rolet | -0.593 |
�� | -0.592 |
uana | -0.546 |
orescence | -0.544 |
Token | South |
Token ID | 2520 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
xual | +0.030 |
rolet | +0.028 |
�� | +0.027 |
orescence | +0.026 |
ukong | +0.026 |
Neg logit contributions | |
wipes | -0.031 |
ignores | -0.029 |
ath | -0.028 |
misses | -0.027 |
crossings | -0.027 |
Token | Korea |
Token ID | 4969 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
xual | +0.532 |
rolet | +0.510 |
�� | +0.484 |
ukong | +0.473 |
orescence | +0.470 |
Neg logit contributions | |
wipes | -0.489 |
ignores | -0.445 |
ath | -0.430 |
successes | -0.412 |
crossings | -0.410 |
Token | , |
Token ID | 11 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
xual | +0.574 |
rolet | +0.530 |
�� | +0.527 |
orescence | +0.497 |
uana | +0.496 |
Neg logit contributions | |
wipes | -0.694 |
ignores | -0.644 |
ath | -0.628 |
misses | -0.598 |
weak | -0.594 |
Token | negative |
Token ID | 4633 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
wipes | +0.273 |
ignores | +0.251 |
ath | +0.236 |
Typhoon | +0.226 |
misses | +0.226 |
Neg logit contributions | |
xual | -0.323 |
�� | -0.298 |
rolet | -0.297 |
uana | -0.276 |
orescence | -0.276 |
Token | cultural |
Token ID | 6467 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
wipes | +1.330 |
ignores | +1.217 |
ath | +1.158 |
misses | +1.102 |
Typhoon | +1.093 |
Neg logit contributions | |
xual | -1.588 |
�� | -1.472 |
rolet | -1.469 |
orescence | -1.370 |
uana | -1.370 |
Token | influences |
Token ID | 16717 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
wipes | +0.152 |
ignores | +0.139 |
ath | +0.133 |
Typhoon | +0.125 |
eworks | +0.124 |
Neg logit contributions | |
xual | -0.181 |
rolet | -0.168 |
�� | -0.167 |
orescence | -0.158 |
uana | -0.156 |
Token | , |
Token ID | 11 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
wipes | +0.366 |
ignores | +0.339 |
ath | +0.323 |
misses | +0.313 |
Typhoon | +0.308 |
Neg logit contributions | |
xual | -0.335 |
rolet | -0.306 |
�� | -0.301 |
uana | -0.281 |
orescence | -0.281 |
Token | brand |
Token ID | 4508 |
Feature activation | +9.75e-02 |
Pos logit contributions | |
wipes | +0.434 |
ignores | +0.398 |
ath | +0.382 |
misses | +0.366 |
Typhoon | +0.364 |
Neg logit contributions | |
xual | -0.457 |
�� | -0.418 |
rolet | -0.417 |
uana | -0.387 |
orescence | -0.386 |
Token | names |
Token ID | 3891 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
wipes | +0.246 |
ignores | +0.223 |
ath | +0.211 |
Typhoon | +0.204 |
misses | +0.199 |
Neg logit contributions | |
xual | -0.341 |
�� | -0.319 |
rolet | -0.315 |
ukong | -0.298 |
uana | -0.297 |
Token | , |
Token ID | 11 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
wipes | +0.668 |
ignores | +0.614 |
ath | +0.588 |
misses | +0.565 |
Typhoon | +0.562 |
Neg logit contributions | |
xual | -0.651 |
�� | -0.599 |
rolet | -0.596 |
uana | -0.552 |
orescence | -0.552 |
Token | products |
Token ID | 3186 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
wipes | +0.669 |
ignores | +0.614 |
ath | +0.586 |
misses | +0.559 |
Typhoon | +0.557 |
Neg logit contributions | |
xual | -0.728 |
�� | -0.675 |
rolet | -0.670 |
uana | -0.623 |
orescence | -0.618 |
Token | and |
Token ID | 290 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
wipes | +0.806 |
ignores | +0.742 |
ath | +0.710 |
misses | +0.681 |
Typhoon | +0.677 |
Neg logit contributions | |
xual | -0.802 |
�� | -0.741 |
rolet | -0.733 |
uana | -0.684 |
orescence | -0.684 |
Token | television |
Token ID | 5581 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
xual | +0.136 |
�� | +0.126 |
rolet | +0.125 |
uana | +0.116 |
enture | +0.114 |
Neg logit contributions | |
wipes | -0.127 |
ignores | -0.117 |
ath | -0.111 |
Typhoon | -0.107 |
misses | -0.106 |
Token | shows |
Token ID | 2523 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
wipes | +0.615 |
ignores | +0.561 |
ath | +0.540 |
misses | +0.513 |
Typhoon | +0.511 |
Neg logit contributions | |
xual | -0.677 |
�� | -0.627 |
rolet | -0.627 |
orescence | -0.585 |
uana | -0.584 |
Token | absor |
Token ID | 46303 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
xual | +0.116 |
rolet | +0.100 |
�� | +0.100 |
orescence | +0.087 |
uana | +0.087 |
Neg logit contributions | |
wipes | -0.284 |
ignores | -0.268 |
ath | -0.260 |
misses | -0.253 |
Typhoon | -0.251 |
Token | ptive |
Token ID | 21665 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
wipes | +0.050 |
ignores | +0.047 |
ath | +0.045 |
misses | +0.043 |
Typhoon | +0.043 |
Neg logit contributions | |
xual | -0.042 |
�� | -0.039 |
rolet | -0.039 |
uana | -0.035 |
orescence | -0.035 |
Token | state |
Token ID | 1181 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
xual | +0.589 |
�� | +0.541 |
rolet | +0.540 |
orescence | +0.501 |
uana | +0.501 |
Neg logit contributions | |
wipes | -0.687 |
ignores | -0.639 |
ath | -0.611 |
misses | -0.590 |
Typhoon | -0.590 |
Token | lasts |
Token ID | 20374 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
xual | +0.167 |
rolet | +0.153 |
�� | +0.152 |
orescence | +0.145 |
uana | +0.144 |
Neg logit contributions | |
wipes | -0.133 |
ignores | -0.121 |
ath | -0.117 |
Typhoon | -0.113 |
Nato | -0.111 |
Token | until |
Token ID | 1566 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
xual | +0.733 |
�� | +0.660 |
rolet | +0.658 |
uana | +0.613 |
orescence | +0.610 |
Neg logit contributions | |
wipes | -0.797 |
ignores | -0.735 |
ath | -0.695 |
misses | -0.684 |
Typhoon | -0.666 |
Token | 8 |
Token ID | 807 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
xual | +0.308 |
�� | +0.281 |
rolet | +0.278 |
uana | +0.260 |
orescence | +0.259 |
Neg logit contributions | |
wipes | -0.361 |
ignores | -0.336 |
ath | -0.320 |
misses | -0.309 |
Typhoon | -0.304 |
Token | to |
Token ID | 284 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
wipes | +0.966 |
ignores | +0.900 |
ath | +0.866 |
misses | +0.837 |
Typhoon | +0.824 |
Neg logit contributions | |
xual | -0.743 |
�� | -0.679 |
rolet | -0.674 |
uana | -0.616 |
orescence | -0.613 |
Token | 12 |
Token ID | 1105 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
wipes | +0.549 |
ignores | +0.507 |
ath | +0.486 |
misses | +0.467 |
Typhoon | +0.459 |
Neg logit contributions | |
xual | -0.527 |
�� | -0.486 |
rolet | -0.485 |
uana | -0.447 |
orescence | -0.446 |
Token | hours |
Token ID | 2250 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
wipes | +0.636 |
ignores | +0.597 |
ath | +0.578 |
misses | +0.559 |
Typhoon | +0.555 |
Neg logit contributions | |
xual | -0.353 |
�� | -0.316 |
rolet | -0.307 |
uana | -0.280 |
orescence | -0.278 |
Token | after |
Token ID | 706 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
wipes | +0.256 |
ignores | +0.236 |
ath | +0.226 |
misses | +0.217 |
Typhoon | +0.214 |
Neg logit contributions | |
xual | -0.257 |
�� | -0.237 |
rolet | -0.236 |
uana | -0.221 |
orescence | -0.219 |
Token | your |
Token ID | 534 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
xual | +0.367 |
rolet | +0.333 |
�� | +0.333 |
uana | +0.310 |
orescence | +0.308 |
Neg logit contributions | |
wipes | -0.416 |
ignores | -0.386 |
ath | -0.369 |
misses | -0.355 |
Typhoon | -0.350 |
Token | the |
Token ID | 262 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
wipes | +1.012 |
ignores | +0.944 |
ath | +0.900 |
misses | +0.872 |
crossings | +0.853 |
Neg logit contributions | |
xual | -0.891 |
�� | -0.818 |
rolet | -0.813 |
uana | -0.756 |
orescence | -0.749 |
Token | wooden |
Token ID | 13510 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
wipes | +0.821 |
ignores | +0.765 |
ath | +0.723 |
misses | +0.699 |
Typhoon | +0.687 |
Neg logit contributions | |
xual | -0.800 |
�� | -0.740 |
rolet | -0.736 |
uana | -0.683 |
orescence | -0.683 |
Token | legs |
Token ID | 7405 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
wipes | +0.457 |
ignores | +0.428 |
ath | +0.402 |
misses | +0.389 |
weak | +0.381 |
Neg logit contributions | |
xual | -0.472 |
�� | -0.437 |
rolet | -0.433 |
uana | -0.409 |
enture | -0.404 |
Token | of |
Token ID | 286 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
wipes | +0.371 |
ignores | +0.343 |
ath | +0.329 |
misses | +0.317 |
Typhoon | +0.314 |
Neg logit contributions | |
xual | -0.346 |
�� | -0.319 |
rolet | -0.317 |
orescence | -0.297 |
uana | -0.295 |
Token | High |
Token ID | 3334 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
wipes | +0.431 |
ignores | +0.404 |
ath | +0.385 |
misses | +0.374 |
crossings | +0.365 |
Neg logit contributions | |
xual | -0.336 |
�� | -0.308 |
rolet | -0.307 |
uana | -0.282 |
orescence | -0.279 |
Token | landers |
Token ID | 32358 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
wipes | +0.551 |
ignores | +0.510 |
ath | +0.491 |
misses | +0.473 |
successes | +0.465 |
Neg logit contributions | |
xual | -0.443 |
rolet | -0.407 |
�� | -0.406 |
orescence | -0.369 |
uana | -0.367 |
Token | enslaved |
Token ID | 39216 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
xual | +0.053 |
�� | +0.049 |
rolet | +0.048 |
uana | +0.045 |
orescence | +0.044 |
Neg logit contributions | |
wipes | -0.058 |
ignores | -0.054 |
ath | -0.051 |
misses | -0.050 |
weak | -0.049 |
Token | after |
Token ID | 706 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
wipes | +0.124 |
ignores | +0.116 |
ath | +0.111 |
misses | +0.107 |
weak | +0.105 |
Neg logit contributions | |
xual | -0.115 |
rolet | -0.104 |
�� | -0.103 |
uana | -0.097 |
enture | -0.096 |
Token | the |
Token ID | 262 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
xual | +0.313 |
�� | +0.283 |
rolet | +0.282 |
uana | +0.261 |
orescence | +0.256 |
Neg logit contributions | |
wipes | -0.407 |
ignores | -0.381 |
ath | -0.369 |
misses | -0.353 |
weak | -0.345 |
Token | Battle |
Token ID | 5838 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
xual | +0.195 |
�� | +0.180 |
rolet | +0.178 |
uana | +0.166 |
enture | +0.165 |
Neg logit contributions | |
wipes | -0.225 |
ignores | -0.213 |
ath | -0.203 |
misses | -0.194 |
weak | -0.190 |
Token | of |
Token ID | 286 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
wipes | +0.673 |
ignores | +0.622 |
ath | +0.595 |
misses | +0.573 |
Typhoon | +0.562 |
Neg logit contributions | |
xual | -0.637 |
�� | -0.588 |
rolet | -0.585 |
orescence | -0.539 |
uana | -0.537 |
Token | legislature |
Token ID | 15928 |
Feature activation | -6.03e-03 |
Pos logit contributions | |
xual | +0.003 |
�� | +0.003 |
rolet | +0.003 |
uana | +0.002 |
orescence | +0.002 |
Neg logit contributions | |
wipes | -0.003 |
ignores | -0.003 |
ath | -0.003 |
misses | -0.003 |
Typhoon | -0.002 |
Token | restored |
Token ID | 15032 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
xual | +0.019 |
rolet | +0.018 |
�� | +0.018 |
uana | +0.016 |
orescence | +0.016 |
Neg logit contributions | |
wipes | -0.017 |
ignores | -0.016 |
ath | -0.015 |
misses | -0.014 |
Typhoon | -0.014 |
Token | some |
Token ID | 617 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
xual | +0.048 |
�� | +0.044 |
rolet | +0.044 |
uana | +0.040 |
orescence | +0.040 |
Neg logit contributions | |
wipes | -0.064 |
ignores | -0.059 |
ath | -0.057 |
misses | -0.055 |
Typhoon | -0.054 |
Token | of |
Token ID | 286 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
xual | +0.305 |
�� | +0.278 |
rolet | +0.276 |
uana | +0.259 |
orescence | +0.258 |
Neg logit contributions | |
wipes | -0.325 |
ignores | -0.300 |
ath | -0.290 |
misses | -0.276 |
Typhoon | -0.274 |
Token | the |
Token ID | 262 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
xual | +0.386 |
rolet | +0.352 |
�� | +0.348 |
uana | +0.318 |
orescence | +0.317 |
Neg logit contributions | |
wipes | -0.566 |
ignores | -0.529 |
ath | -0.511 |
misses | -0.491 |
Typhoon | -0.485 |
Token | scholarship |
Token ID | 18652 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
xual | +0.198 |
rolet | +0.180 |
�� | +0.180 |
orescence | +0.167 |
uana | +0.167 |
Neg logit contributions | |
wipes | -0.227 |
ignores | -0.212 |
ath | -0.202 |
misses | -0.194 |
Typhoon | -0.192 |
Token | funding |
Token ID | 4918 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
xual | +0.560 |
rolet | +0.512 |
�� | +0.510 |
uana | +0.477 |
orescence | +0.476 |
Neg logit contributions | |
wipes | -0.575 |
ignores | -0.532 |
ath | -0.515 |
misses | -0.489 |
Typhoon | -0.487 |
Token | affected |
Token ID | 5676 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
xual | +0.306 |
rolet | +0.280 |
�� | +0.279 |
uana | +0.259 |
orescence | +0.258 |
Neg logit contributions | |
wipes | -0.340 |
ignores | -0.315 |
ath | -0.305 |
misses | -0.291 |
Typhoon | -0.288 |
Token | by |
Token ID | 416 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
xual | +0.588 |
rolet | +0.547 |
�� | +0.537 |
ukong | +0.491 |
uana | +0.490 |
Neg logit contributions | |
wipes | -0.644 |
ignores | -0.598 |
ath | -0.575 |
misses | -0.549 |
Typhoon | -0.547 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
xual | +0.132 |
rolet | +0.120 |
�� | +0.120 |
uana | +0.108 |
orescence | +0.107 |
Neg logit contributions | |
wipes | -0.203 |
ignores | -0.190 |
ath | -0.185 |
misses | -0.177 |
Typhoon | -0.175 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -9.70e-02 |
Pos logit contributions | |
xual | +0.331 |
rolet | +0.307 |
�� | +0.307 |
uana | +0.281 |
orescence | +0.280 |
Neg logit contributions | |
wipes | -0.348 |
ignores | -0.326 |
ath | -0.310 |
misses | -0.296 |
Nato | -0.293 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
xual | +0.528 |
�� | +0.471 |
rolet | +0.466 |
uana | +0.431 |
orescence | +0.429 |
Neg logit contributions | |
wipes | -0.818 |
ignores | -0.764 |
ath | -0.736 |
misses | -0.711 |
crossings | -0.697 |
Token | commentary |
Token ID | 14604 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
xual | +0.613 |
�� | +0.551 |
rolet | +0.546 |
uana | +0.515 |
enture | +0.513 |
Neg logit contributions | |
wipes | -0.671 |
ignores | -0.624 |
ath | -0.586 |
misses | -0.565 |
weak | -0.562 |
Token | rev |
Token ID | 2710 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
xual | +0.130 |
rolet | +0.117 |
�� | +0.116 |
orescence | +0.110 |
uana | +0.109 |
Neg logit contributions | |
wipes | -0.130 |
ignores | -0.117 |
ath | -0.115 |
Typhoon | -0.110 |
weak | -0.109 |
Token | olved |
Token ID | 5634 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
xual | +1.441 |
rolet | +1.320 |
�� | +1.285 |
enture | +1.243 |
orescence | +1.239 |
Neg logit contributions | |
wipes | -1.532 |
ignores | -1.403 |
ath | -1.355 |
Typhoon | -1.329 |
misses | -1.292 |
Token | around |
Token ID | 1088 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
xual | +0.917 |
rolet | +0.852 |
�� | +0.843 |
orescence | +0.793 |
enture | +0.787 |
Neg logit contributions | |
wipes | -0.760 |
ignores | -0.682 |
ath | -0.647 |
misses | -0.626 |
Typhoon | -0.621 |
Token | the |
Token ID | 262 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
xual | +0.159 |
�� | +0.144 |
rolet | +0.143 |
uana | +0.132 |
orescence | +0.129 |
Neg logit contributions | |
wipes | -0.223 |
ignores | -0.208 |
ath | -0.200 |
misses | -0.193 |
Typhoon | -0.190 |
Token | aesthetics |
Token ID | 35431 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
xual | +0.224 |
�� | +0.205 |
rolet | +0.204 |
ukong | +0.190 |
uana | +0.189 |
Neg logit contributions | |
wipes | -0.235 |
ignores | -0.218 |
ath | -0.206 |
misses | -0.198 |
Typhoon | -0.195 |
Token | and |
Token ID | 290 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
wipes | +1.020 |
ignores | +0.937 |
ath | +0.899 |
misses | +0.860 |
Typhoon | +0.849 |
Neg logit contributions | |
xual | -0.970 |
�� | -0.887 |
rolet | -0.879 |
uana | -0.819 |
orescence | -0.818 |
Token | design |
Token ID | 1486 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
wipes | +0.545 |
ignores | +0.501 |
ath | +0.481 |
misses | +0.462 |
Typhoon | +0.460 |
Neg logit contributions | |
xual | -0.509 |
�� | -0.466 |
rolet | -0.465 |
uana | -0.431 |
orescence | -0.427 |
Token | of |
Token ID | 286 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
wipes | +0.359 |
ignores | +0.328 |
ath | +0.315 |
Typhoon | +0.302 |
misses | +0.298 |
Neg logit contributions | |
xual | -0.362 |
�� | -0.328 |
rolet | -0.327 |
orescence | -0.308 |
enture | -0.306 |
Token | the |
Token ID | 262 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
xual | +0.210 |
�� | +0.189 |
rolet | +0.186 |
uana | +0.171 |
ukong | +0.168 |
Neg logit contributions | |
wipes | -0.338 |
ignores | -0.317 |
ath | -0.305 |
misses | -0.296 |
weak | -0.289 |
Token | . |
Token ID | 13 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
xual | +0.863 |
rolet | +0.788 |
�� | +0.777 |
uana | +0.722 |
orescence | +0.720 |
Neg logit contributions | |
wipes | -0.995 |
ignores | -0.913 |
ath | -0.877 |
misses | -0.847 |
Typhoon | -0.840 |
Token |
|
Token ID | 198 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
wipes | +0.234 |
ignores | +0.212 |
ath | +0.204 |
misses | +0.194 |
successes | +0.192 |
Neg logit contributions | |
xual | -0.251 |
rolet | -0.236 |
�� | -0.230 |
uana | -0.215 |
ancer | -0.214 |
Token |
|
Token ID | 198 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
xual | +0.882 |
�� | +0.825 |
rolet | +0.823 |
uana | +0.770 |
orescence | +0.767 |
Neg logit contributions | |
wipes | -0.639 |
ignores | -0.580 |
ath | -0.550 |
misses | -0.524 |
Typhoon | -0.513 |
Token | " |
Token ID | 1 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
xual | +0.620 |
rolet | +0.588 |
�� | +0.576 |
uana | +0.547 |
ukong | +0.539 |
Neg logit contributions | |
wipes | -0.623 |
ignores | -0.564 |
ath | -0.544 |
misses | -0.520 |
crossings | -0.513 |
Token | In |
Token ID | 818 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
xual | +0.421 |
rolet | +0.400 |
�� | +0.393 |
uana | +0.374 |
ukong | +0.371 |
Neg logit contributions | |
wipes | -0.287 |
ignores | -0.253 |
ath | -0.241 |
misses | -0.227 |
crossings | -0.226 |
Token | this |
Token ID | 428 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
xual | +0.070 |
rolet | +0.064 |
�� | +0.064 |
uana | +0.059 |
orescence | +0.059 |
Neg logit contributions | |
wipes | -0.076 |
ignores | -0.071 |
ath | -0.068 |
misses | -0.065 |
Typhoon | -0.064 |
Token | case |
Token ID | 1339 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
xual | +0.366 |
rolet | +0.337 |
�� | +0.335 |
uana | +0.309 |
enture | +0.309 |
Neg logit contributions | |
wipes | -0.427 |
ignores | -0.396 |
ath | -0.381 |
misses | -0.367 |
Typhoon | -0.361 |
Token | ... |
Token ID | 2644 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
wipes | +1.011 |
ignores | +0.935 |
ath | +0.902 |
misses | +0.866 |
Typhoon | +0.853 |
Neg logit contributions | |
xual | -0.881 |
�� | -0.807 |
rolet | -0.805 |
uana | -0.740 |
orescence | -0.736 |
Token | when |
Token ID | 618 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
wipes | +0.696 |
ignores | +0.642 |
ath | +0.620 |
misses | +0.595 |
Typhoon | +0.587 |
Neg logit contributions | |
xual | -0.607 |
rolet | -0.554 |
�� | -0.552 |
uana | -0.511 |
orescence | -0.506 |
Token | you |
Token ID | 345 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
wipes | +0.107 |
ignores | +0.098 |
ath | +0.096 |
misses | +0.091 |
Typhoon | +0.090 |
Neg logit contributions | |
xual | -0.092 |
�� | -0.083 |
rolet | -0.083 |
uana | -0.077 |
orescence | -0.076 |
Token | include |
Token ID | 2291 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
xual | +0.193 |
rolet | +0.181 |
�� | +0.178 |
uana | +0.168 |
orescence | +0.166 |
Neg logit contributions | |
wipes | -0.179 |
ignores | -0.164 |
ath | -0.158 |
misses | -0.151 |
Typhoon | -0.150 |
Token | to |
Token ID | 284 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
wipes | +0.276 |
ignores | +0.254 |
ath | +0.246 |
misses | +0.235 |
Typhoon | +0.233 |
Neg logit contributions | |
xual | -0.241 |
rolet | -0.219 |
�� | -0.218 |
orescence | -0.202 |
uana | -0.200 |
Token | put |
Token ID | 1234 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
wipes | +0.416 |
ignores | +0.381 |
ath | +0.365 |
misses | +0.349 |
Typhoon | +0.346 |
Neg logit contributions | |
xual | -0.439 |
rolet | -0.404 |
�� | -0.402 |
uana | -0.374 |
orescence | -0.373 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
wipes | +0.613 |
ignores | +0.565 |
ath | +0.541 |
misses | +0.516 |
Typhoon | +0.509 |
Neg logit contributions | |
xual | -0.684 |
�� | -0.634 |
rolet | -0.623 |
uana | -0.586 |
orescence | -0.584 |
Token | unpleasant |
Token ID | 22029 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
xual | +0.467 |
�� | +0.422 |
rolet | +0.420 |
orescence | +0.393 |
uana | +0.392 |
Neg logit contributions | |
wipes | -0.449 |
ignores | -0.419 |
ath | -0.399 |
misses | -0.378 |
Typhoon | -0.377 |
Token | ness |
Token ID | 1108 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
wipes | +0.120 |
ignores | +0.112 |
ath | +0.108 |
misses | +0.103 |
Typhoon | +0.103 |
Neg logit contributions | |
xual | -0.102 |
�� | -0.093 |
rolet | -0.092 |
orescence | -0.086 |
uana | -0.085 |
Token | of |
Token ID | 286 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
xual | +0.427 |
�� | +0.391 |
rolet | +0.384 |
orescence | +0.363 |
uana | +0.359 |
Neg logit contributions | |
wipes | -0.413 |
ignores | -0.382 |
ath | -0.367 |
Typhoon | -0.349 |
misses | -0.348 |
Token | this |
Token ID | 428 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
xual | +0.256 |
rolet | +0.225 |
�� | +0.224 |
uana | +0.208 |
orescence | +0.207 |
Neg logit contributions | |
wipes | -0.330 |
ignores | -0.309 |
ath | -0.297 |
misses | -0.286 |
Typhoon | -0.281 |
Token | film |
Token ID | 2646 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
xual | +0.618 |
rolet | +0.545 |
�� | +0.543 |
uana | +0.514 |
orescence | +0.513 |
Neg logit contributions | |
wipes | -0.694 |
ignores | -0.637 |
ath | -0.608 |
misses | -0.587 |
Typhoon | -0.585 |
Token | into |
Token ID | 656 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
wipes | +0.069 |
ignores | +0.063 |
ath | +0.060 |
Typhoon | +0.058 |
misses | +0.058 |
Neg logit contributions | |
xual | -0.076 |
�� | -0.070 |
rolet | -0.070 |
uana | -0.065 |
orescence | -0.065 |
Token | words |
Token ID | 2456 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
xual | +0.050 |
�� | +0.047 |
rolet | +0.046 |
uana | +0.043 |
orescence | +0.043 |
Neg logit contributions | |
wipes | -0.045 |
ignores | -0.041 |
ath | -0.039 |
misses | -0.037 |
Typhoon | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
wipes | +0.124 |
ignores | +0.115 |
ath | +0.111 |
misses | +0.106 |
Typhoon | +0.106 |
Neg logit contributions | |
xual | -0.110 |
rolet | -0.100 |
�� | -0.100 |
orescence | -0.092 |
uana | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +9.65e-02 |
Pos logit contributions | |
wipes | +0.609 |
ignores | +0.561 |
ath | +0.539 |
misses | +0.518 |
Typhoon | +0.515 |
Neg logit contributions | |
xual | -0.583 |
rolet | -0.534 |
�� | -0.534 |
uana | -0.491 |
orescence | -0.489 |
Token | Republican |
Token ID | 3415 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
wipes | +0.289 |
ignores | +0.261 |
ath | +0.252 |
crossings | +0.241 |
misses | +0.240 |
Neg logit contributions | |
xual | -0.292 |
rolet | -0.275 |
�� | -0.268 |
uana | -0.250 |
ancer | -0.249 |
Token | standard |
Token ID | 3210 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
wipes | +0.338 |
ignores | +0.309 |
ath | +0.298 |
misses | +0.284 |
crossings | +0.279 |
Neg logit contributions | |
xual | -0.377 |
�� | -0.354 |
rolet | -0.349 |
uana | -0.326 |
orescence | -0.324 |
Token | - |
Token ID | 12 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
xual | +0.248 |
�� | +0.231 |
rolet | +0.227 |
ancer | +0.213 |
uana | +0.213 |
Neg logit contributions | |
wipes | -0.211 |
ignores | -0.191 |
ath | -0.185 |
Typhoon | -0.177 |
misses | -0.176 |
Token | be |
Token ID | 1350 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
wipes | +0.033 |
ignores | +0.030 |
ath | +0.029 |
misses | +0.028 |
Typhoon | +0.028 |
Neg logit contributions | |
xual | -0.031 |
rolet | -0.028 |
�� | -0.028 |
uana | -0.027 |
enture | -0.026 |
Token | arer |
Token ID | 11258 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
xual | +0.522 |
�� | +0.498 |
rolet | +0.479 |
ancer | +0.460 |
ukong | +0.449 |
Neg logit contributions | |
wipes | -0.439 |
ignores | -0.396 |
ath | -0.379 |
misses | -0.369 |
Typhoon | -0.359 |
Token | Mitt |
Token ID | 16627 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
xual | +1.668 |
�� | +1.551 |
rolet | +1.538 |
ancer | +1.447 |
orescence | +1.436 |
Neg logit contributions | |
wipes | -1.606 |
ignores | -1.426 |
ath | -1.408 |
Cooldown | -1.337 |
misses | -1.331 |
Token | Romney |
Token ID | 8431 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
xual | +0.009 |
rolet | +0.009 |
�� | +0.009 |
ancer | +0.008 |
uana | +0.008 |
Neg logit contributions | |
wipes | -0.006 |
ignores | -0.006 |
ath | -0.006 |
Typhoon | -0.005 |
crossings | -0.005 |
Token | just |
Token ID | 655 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
wipes | +0.684 |
ignores | +0.621 |
ath | +0.604 |
Typhoon | +0.572 |
misses | +0.569 |
Neg logit contributions | |
xual | -0.801 |
rolet | -0.739 |
�� | -0.736 |
uana | -0.687 |
orescence | -0.687 |
Token | last |
Token ID | 938 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
wipes | +0.144 |
ignores | +0.131 |
ath | +0.127 |
Typhoon | +0.121 |
misses | +0.120 |
Neg logit contributions | |
xual | -0.159 |
rolet | -0.147 |
�� | -0.146 |
uana | -0.136 |
orescence | -0.136 |
Token | year |
Token ID | 614 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
wipes | +0.302 |
ignores | +0.279 |
ath | +0.270 |
misses | +0.259 |
Typhoon | +0.258 |
Neg logit contributions | |
xual | -0.243 |
�� | -0.225 |
rolet | -0.223 |
uana | -0.207 |
orescence | -0.204 |
Token | paused |
Token ID | 24487 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
xual | +0.119 |
rolet | +0.110 |
�� | +0.110 |
uana | +0.102 |
orescence | +0.102 |
Neg logit contributions | |
wipes | -0.133 |
ignores | -0.123 |
ath | -0.116 |
misses | -0.113 |
Typhoon | -0.112 |
Token | for |
Token ID | 329 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
xual | +0.326 |
�� | +0.299 |
rolet | +0.299 |
orescence | +0.277 |
uana | +0.276 |
Neg logit contributions | |
wipes | -0.381 |
ignores | -0.351 |
ath | -0.334 |
misses | -0.325 |
Typhoon | -0.321 |
Token | breath |
Token ID | 8033 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
wipes | +0.189 |
ignores | +0.177 |
ath | +0.169 |
misses | +0.162 |
Typhoon | +0.159 |
Neg logit contributions | |
xual | -0.155 |
�� | -0.144 |
rolet | -0.142 |
uana | -0.131 |
orescence | -0.130 |
Token | ( |
Token ID | 357 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
xual | +0.388 |
rolet | +0.353 |
�� | +0.352 |
orescence | +0.330 |
uana | +0.325 |
Neg logit contributions | |
wipes | -0.445 |
ignores | -0.413 |
ath | -0.398 |
misses | -0.382 |
Typhoon | -0.380 |
Token | after |
Token ID | 8499 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
xual | +0.049 |
rolet | +0.046 |
�� | +0.045 |
uana | +0.043 |
orescence | +0.042 |
Neg logit contributions | |
wipes | -0.045 |
ignores | -0.041 |
ath | -0.039 |
misses | -0.037 |
Typhoon | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
xual | +0.743 |
rolet | +0.692 |
�� | +0.688 |
uana | +0.636 |
orescence | +0.627 |
Neg logit contributions | |
wipes | -0.892 |
ignores | -0.835 |
ath | -0.801 |
misses | -0.764 |
crossings | -0.752 |
Token | steep |
Token ID | 14559 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
xual | +1.623 |
rolet | +1.529 |
�� | +1.511 |
uana | +1.409 |
enture | +1.406 |
Neg logit contributions | |
wipes | -1.638 |
ignores | -1.529 |
ath | -1.457 |
tools | -1.387 |
crossings | -1.367 |
Token | climb |
Token ID | 12080 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
xual | +0.118 |
rolet | +0.112 |
�� | +0.110 |
uana | +0.104 |
orescence | +0.102 |
Neg logit contributions | |
wipes | -0.101 |
ignores | -0.093 |
ath | -0.088 |
misses | -0.083 |
Typhoon | -0.082 |
Token | out |
Token ID | 503 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
xual | +0.212 |
rolet | +0.193 |
�� | +0.192 |
uana | +0.179 |
orescence | +0.179 |
Neg logit contributions | |
wipes | -0.214 |
ignores | -0.197 |
ath | -0.189 |
misses | -0.181 |
Typhoon | -0.179 |
Token | of |
Token ID | 286 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
wipes | +0.004 |
ignores | +0.004 |
ath | +0.003 |
misses | +0.003 |
Typhoon | +0.003 |
Neg logit contributions | |
xual | -0.004 |
�� | -0.003 |
rolet | -0.003 |
uana | -0.003 |
orescence | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
wipes | +0.524 |
ignores | +0.491 |
ath | +0.472 |
misses | +0.453 |
crossings | +0.448 |
Neg logit contributions | |
xual | -0.365 |
rolet | -0.338 |
�� | -0.332 |
uana | -0.307 |
orescence | -0.306 |
Token | dain |
Token ID | 27162 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
wipes | +0.448 |
ignores | +0.417 |
ath | +0.402 |
misses | +0.388 |
Typhoon | +0.383 |
Neg logit contributions | |
xual | -0.338 |
rolet | -0.309 |
�� | -0.305 |
uana | -0.280 |
orescence | -0.277 |
Token | in |
Token ID | 287 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
wipes | +0.099 |
ignores | +0.092 |
ath | +0.089 |
misses | +0.086 |
Typhoon | +0.085 |
Neg logit contributions | |
xual | -0.070 |
�� | -0.063 |
rolet | -0.063 |
uana | -0.057 |
orescence | -0.057 |
Token | public |
Token ID | 1171 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
wipes | +0.485 |
ignores | +0.449 |
ath | +0.432 |
misses | +0.416 |
Typhoon | +0.411 |
Neg logit contributions | |
xual | -0.399 |
�� | -0.366 |
rolet | -0.361 |
uana | -0.334 |
orescence | -0.332 |
Token | — |
Token ID | 960 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
wipes | +0.740 |
ignores | +0.682 |
ath | +0.656 |
misses | +0.630 |
Typhoon | +0.623 |
Neg logit contributions | |
xual | -0.695 |
�� | -0.638 |
rolet | -0.636 |
orescence | -0.585 |
uana | -0.585 |
Token | p |
Token ID | 79 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
wipes | +0.641 |
ignores | +0.582 |
ath | +0.556 |
misses | +0.533 |
Typhoon | +0.525 |
Neg logit contributions | |
xual | -0.758 |
rolet | -0.705 |
�� | -0.702 |
uana | -0.658 |
orescence | -0.654 |
Token | iss |
Token ID | 747 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
wipes | +0.402 |
ignores | +0.372 |
ath | +0.357 |
misses | +0.346 |
Typhoon | +0.342 |
Neg logit contributions | |
xual | -0.352 |
rolet | -0.324 |
�� | -0.320 |
uana | -0.299 |
orescence | -0.298 |
Token | ing |
Token ID | 278 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
xual | +1.593 |
�� | +1.472 |
rolet | +1.467 |
uana | +1.361 |
orescence | +1.360 |
Neg logit contributions | |
wipes | -1.707 |
ignores | -1.584 |
ath | -1.527 |
Typhoon | -1.478 |
crossings | -1.463 |
Token | off |
Token ID | 572 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
xual | +0.315 |
�� | +0.291 |
rolet | +0.287 |
uana | +0.268 |
orescence | +0.264 |
Neg logit contributions | |
wipes | -0.323 |
ignores | -0.296 |
ath | -0.286 |
misses | -0.273 |
crossings | -0.272 |
Token | one |
Token ID | 530 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
wipes | +0.507 |
ignores | +0.467 |
ath | +0.448 |
misses | +0.431 |
Typhoon | +0.427 |
Neg logit contributions | |
xual | -0.456 |
�� | -0.416 |
rolet | -0.413 |
orescence | -0.381 |
uana | -0.381 |
Token | of |
Token ID | 286 |
Feature activation | +8.29e-02 |
Pos logit contributions | |
wipes | +0.579 |
ignores | +0.531 |
ath | +0.513 |
misses | +0.491 |
crossings | +0.487 |
Neg logit contributions | |
xual | -0.530 |
�� | -0.486 |
rolet | -0.482 |
uana | -0.446 |
orescence | -0.444 |
Token | the |
Token ID | 262 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
wipes | +0.282 |
ignores | +0.262 |
ath | +0.252 |
misses | +0.242 |
Typhoon | +0.240 |
Neg logit contributions | |
xual | -0.221 |
�� | -0.202 |
rolet | -0.202 |
orescence | -0.184 |
uana | -0.183 |
Token | sm |
Token ID | 895 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
wipes | +0.405 |
ignores | +0.373 |
ath | +0.357 |
misses | +0.344 |
Typhoon | +0.336 |
Neg logit contributions | |
xual | -0.427 |
�� | -0.396 |
rolet | -0.394 |
uana | -0.364 |
orescence | -0.363 |
Token | earing |
Token ID | 6648 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
wipes | +2.220 |
ignores | +2.070 |
ath | +1.994 |
misses | +1.929 |
Typhoon | +1.899 |
Neg logit contributions | |
xual | -1.647 |
�� | -1.505 |
rolet | -1.495 |
uana | -1.359 |
orescence | -1.354 |
Token | of |
Token ID | 286 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
wipes | +1.390 |
ignores | +1.278 |
ath | +1.233 |
misses | +1.175 |
crossings | +1.172 |
Neg logit contributions | |
xual | -1.326 |
�� | -1.200 |
rolet | -1.194 |
uana | -1.123 |
orescence | -1.117 |
Token | a |
Token ID | 257 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
xual | +0.493 |
rolet | +0.447 |
�� | +0.446 |
orescence | +0.419 |
uana | +0.418 |
Neg logit contributions | |
wipes | -0.511 |
ignores | -0.476 |
ath | -0.447 |
misses | -0.432 |
eworks | -0.426 |
Token | wholly |
Token ID | 18174 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
xual | +0.107 |
�� | +0.098 |
rolet | +0.098 |
uana | +0.090 |
orescence | +0.089 |
Neg logit contributions | |
wipes | -0.113 |
ignores | -0.105 |
ath | -0.100 |
crossings | -0.096 |
misses | -0.096 |
Token | benevolent |
Token ID | 45599 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
wipes | +0.222 |
ignores | +0.203 |
ath | +0.195 |
misses | +0.187 |
Typhoon | +0.187 |
Neg logit contributions | |
xual | -0.212 |
�� | -0.196 |
rolet | -0.195 |
uana | -0.181 |
orescence | -0.180 |
Token | foundation |
Token ID | 8489 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
xual | +1.582 |
rolet | +1.445 |
�� | +1.430 |
uana | +1.349 |
ancer | +1.338 |
Neg logit contributions | |
wipes | -1.825 |
ignores | -1.695 |
ath | -1.614 |
misses | -1.556 |
crossings | -1.552 |
Token | , |
Token ID | 11 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
wipes | +0.505 |
ignores | +0.463 |
ath | +0.447 |
misses | +0.430 |
Typhoon | +0.429 |
Neg logit contributions | |
xual | -0.481 |
rolet | -0.437 |
�� | -0.434 |
uana | -0.406 |
orescence | -0.404 |
Token | due |
Token ID | 2233 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
wipes | +0.458 |
ignores | +0.418 |
ath | +0.406 |
misses | +0.390 |
Typhoon | +0.388 |
Neg logit contributions | |
xual | -0.425 |
rolet | -0.386 |
�� | -0.386 |
uana | -0.361 |
orescence | -0.360 |
Token | only |
Token ID | 691 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
xual | +0.059 |
rolet | +0.054 |
�� | +0.054 |
uana | +0.050 |
orescence | +0.050 |
Neg logit contributions | |
wipes | -0.068 |
ignores | -0.062 |
ath | -0.060 |
misses | -0.058 |
Typhoon | -0.058 |
Token | to |
Token ID | 284 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
xual | +0.272 |
rolet | +0.250 |
�� | +0.249 |
orescence | +0.229 |
uana | +0.226 |
Neg logit contributions | |
wipes | -0.336 |
ignores | -0.311 |
ath | -0.299 |
Typhoon | -0.290 |
misses | -0.289 |
Token | of |
Token ID | 286 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
xual | +0.505 |
rolet | +0.457 |
�� | +0.451 |
orescence | +0.418 |
uana | +0.414 |
Neg logit contributions | |
wipes | -0.600 |
ignores | -0.554 |
ath | -0.530 |
misses | -0.513 |
Typhoon | -0.508 |
Token | misinformation |
Token ID | 32805 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
wipes | +0.164 |
ignores | +0.150 |
ath | +0.143 |
misses | +0.137 |
Typhoon | +0.137 |
Neg logit contributions | |
xual | -0.162 |
rolet | -0.147 |
�� | -0.147 |
uana | -0.137 |
orescence | -0.137 |
Token | around |
Token ID | 1088 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
xual | +0.083 |
rolet | +0.076 |
�� | +0.076 |
orescence | +0.070 |
uana | +0.070 |
Neg logit contributions | |
wipes | -0.089 |
ignores | -0.082 |
ath | -0.079 |
misses | -0.076 |
Typhoon | -0.075 |
Token | trans |
Token ID | 1007 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
wipes | +0.033 |
ignores | +0.030 |
ath | +0.028 |
misses | +0.027 |
Typhoon | +0.027 |
Neg logit contributions | |
xual | -0.035 |
rolet | -0.032 |
�� | -0.032 |
uana | -0.030 |
orescence | -0.030 |
Token | identity |
Token ID | 5369 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
xual | +0.470 |
�� | +0.428 |
rolet | +0.424 |
uana | +0.396 |
orescence | +0.394 |
Neg logit contributions | |
wipes | -0.493 |
ignores | -0.456 |
ath | -0.437 |
misses | -0.419 |
Typhoon | -0.418 |
Token | .) |
Token ID | 2014 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
wipes | +0.058 |
ignores | +0.054 |
ath | +0.052 |
misses | +0.050 |
Typhoon | +0.049 |
Neg logit contributions | |
xual | -0.046 |
�� | -0.042 |
rolet | -0.041 |
uana | -0.038 |
orescence | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
xual | +1.810 |
rolet | +1.714 |
�� | +1.654 |
Stay | +1.573 |
ault | +1.560 |
Neg logit contributions | |
wipes | -1.697 |
ignores | -1.500 |
ath | -1.449 |
crossings | -1.420 |
successes | -1.388 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
xual | +0.719 |
�� | +0.673 |
rolet | +0.671 |
uana | +0.628 |
orescence | +0.626 |
Neg logit contributions | |
wipes | -0.523 |
ignores | -0.474 |
ath | -0.450 |
misses | -0.429 |
Typhoon | -0.419 |
Token | So |
Token ID | 2396 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
xual | +0.425 |
rolet | +0.404 |
�� | +0.398 |
uana | +0.378 |
orescence | +0.376 |
Neg logit contributions | |
wipes | -0.298 |
ignores | -0.262 |
ath | -0.248 |
crossings | -0.238 |
misses | -0.236 |
Token | long |
Token ID | 890 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
xual | +0.637 |
rolet | +0.585 |
�� | +0.582 |
orescence | +0.537 |
uana | +0.535 |
Neg logit contributions | |
wipes | -0.672 |
ignores | -0.614 |
ath | -0.590 |
misses | -0.567 |
Typhoon | -0.566 |
Token | as |
Token ID | 355 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
wipes | +0.952 |
ignores | +0.884 |
ath | +0.850 |
misses | +0.821 |
Typhoon | +0.807 |
Neg logit contributions | |
xual | -0.786 |
�� | -0.721 |
rolet | -0.717 |
uana | -0.657 |
orescence | -0.655 |