Token | updates |
Token ID | 5992 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
️ | +3.630 |
ande | +3.163 |
Scrib | +2.996 |
FIELD | +2.987 |
prism | +2.982 |
Neg logit contributions | |
shown | -4.690 |
Hait | -4.534 |
Whale | -4.524 |
hur | -4.366 |
Athena | -4.327 |
Token | ? |
Token ID | 30 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
️ | +4.096 |
ande | +3.570 |
FIELD | +3.492 |
� | +3.427 |
Scrib | +3.407 |
Neg logit contributions | |
shown | -5.411 |
Hait | -5.356 |
Whale | -5.179 |
hur | -5.036 |
Athena | -5.010 |
Token | No |
Token ID | 1400 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
️ | +5.647 |
Scrib | +5.004 |
� | +4.726 |
ande | +4.719 |
prism | +4.683 |
Neg logit contributions | |
shown | -5.508 |
Hait | -5.366 |
itime | -5.199 |
hur | -5.172 |
Whale | -4.967 |
Token | more |
Token ID | 517 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
️ | +1.395 |
ande | +1.290 |
FIELD | +1.235 |
Scrib | +1.212 |
prism | +1.207 |
Neg logit contributions | |
shown | -1.265 |
Hait | -1.236 |
Whale | -1.211 |
Athena | -1.159 |
Shin | -1.147 |
Token | bad |
Token ID | 2089 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
shown | +0.830 |
Hait | +0.807 |
Whale | +0.792 |
Athena | +0.762 |
Shin | +0.756 |
Neg logit contributions | |
️ | -1.004 |
ande | -0.932 |
FIELD | -0.902 |
conflic | -0.892 |
Scrib | -0.882 |
Token | news |
Token ID | 1705 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
shown | +2.065 |
Hait | +1.980 |
Whale | +1.943 |
Shin | +1.851 |
Athena | +1.838 |
Neg logit contributions | |
️ | -4.649 |
ande | -4.453 |
conflic | -4.386 |
FIELD | -4.380 |
�� | -4.298 |
Token | pl |
Token ID | 458 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
️ | +6.314 |
prism | +6.042 |
ande | +5.101 |
Scrib | +4.984 |
LC | +4.742 |
Neg logit contributions | |
shown | -17.455 |
Hait | -17.196 |
hur | -16.850 |
itime | -16.702 |
Nicarag | -16.636 |
Token | s |
Token ID | 82 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
️ | +4.085 |
ande | +3.806 |
ards | +3.677 |
FIELD | +3.622 |
LC | +3.546 |
Neg logit contributions | |
Hait | -4.112 |
Whale | -4.070 |
shown | -4.051 |
Athena | -3.813 |
Howell | -3.768 |
Token | . |
Token ID | 13 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
️ | +4.541 |
ande | +4.061 |
FIELD | +4.028 |
LC | +3.896 |
ards | +3.866 |
Neg logit contributions | |
shown | -5.313 |
Hait | -5.277 |
Whale | -5.133 |
hur | -4.953 |
itime | -4.912 |
Token | Writer |
Token ID | 26606 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
️ | +6.046 |
ande | +5.581 |
Scrib | +5.515 |
prism | +5.506 |
FIELD | +5.368 |
Neg logit contributions | |
shown | -4.949 |
Hait | -4.645 |
Whale | -4.414 |
hur | -4.370 |
Athena | -4.228 |
Token | " |
Token ID | 366 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
️ | +2.842 |
ande | +2.651 |
FIELD | +2.536 |
Scrib | +2.507 |
prism | +2.492 |
Neg logit contributions | |
shown | -2.298 |
Hait | -2.201 |
Whale | -2.121 |
hur | -2.061 |
Athena | -2.030 |
Token | - |
Token ID | 532 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
️ | +4.638 |
ande | +4.298 |
FIELD | +4.150 |
Scrib | +4.052 |
conflic | +4.025 |
Neg logit contributions | |
shown | -5.008 |
Hait | -4.993 |
Whale | -4.885 |
hur | -4.707 |
Athena | -4.633 |
Token | data |
Token ID | 1366 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
️ | +3.336 |
ande | +3.082 |
FIELD | +2.981 |
conflic | +2.965 |
Scrib | +2.936 |
Neg logit contributions | |
shown | -2.936 |
Hait | -2.907 |
Whale | -2.836 |
hur | -2.745 |
Athena | -2.707 |
Token | : |
Token ID | 1058 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
️ | +6.728 |
ande | +5.981 |
FIELD | +5.959 |
Scrib | +5.731 |
conflic | +5.625 |
Neg logit contributions | |
Hait | -9.572 |
Whale | -9.450 |
shown | -9.404 |
hur | -9.151 |
Shin | -8.808 |
Token | github |
Token ID | 33084 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
️ | +3.773 |
ande | +3.348 |
conflic | +3.207 |
prism | +3.163 |
Scrib | +3.159 |
Neg logit contributions | |
shown | -5.008 |
Hait | -4.925 |
Whale | -4.896 |
hur | -4.710 |
Shin | -4.634 |
Token | _ |
Token ID | 62 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
️ | +5.797 |
ande | +5.507 |
FIELD | +5.315 |
Scrib | +5.127 |
ards | +5.073 |
Neg logit contributions | |
Hait | -5.150 |
Whale | -5.128 |
shown | -5.123 |
Shin | -4.807 |
Howell | -4.796 |
Token | re |
Token ID | 260 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
️ | +6.077 |
ande | +5.738 |
FIELD | +5.275 |
ards | +5.105 |
Scrib | +5.073 |
Neg logit contributions | |
Whale | -6.407 |
Hait | -6.386 |
shown | -6.163 |
Athena | -6.072 |
Shin | -6.031 |
Token | pos |
Token ID | 1930 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
️ | +7.583 |
ande | +7.454 |
lez | +6.629 |
ards | +6.556 |
ques | +6.221 |
Neg logit contributions | |
Whale | -16.751 |
Hait | -16.544 |
Howell | -16.385 |
Athena | -16.308 |
Nicarag | -15.972 |
Token | . |
Token ID | 764 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
️ | +7.457 |
ande | +7.007 |
FIELD | +6.785 |
Scrib | +6.757 |
conflic | +6.687 |
Neg logit contributions | |
shown | -4.236 |
Hait | -4.214 |
Whale | -4.131 |
hur | -3.856 |
Shin | -3.808 |
Token | contents |
Token ID | 10154 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
️ | +2.132 |
ande | +1.966 |
FIELD | +1.905 |
conflic | +1.895 |
Scrib | +1.878 |
Neg logit contributions | |
shown | -1.911 |
Hait | -1.873 |
Whale | -1.846 |
Athena | -1.773 |
hur | -1.767 |
Token | ] |
Token ID | 2361 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
️ | +3.956 |
ande | +3.707 |
FIELD | +3.623 |
conflic | +3.533 |
Scrib | +3.522 |
Neg logit contributions | |
shown | -2.793 |
Hait | -2.739 |
Whale | -2.727 |
Athena | -2.574 |
hur | -2.570 |
Token | WHERE |
Token ID | 33411 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
shown | +0.809 |
Hait | +0.790 |
Whale | +0.777 |
Athena | +0.754 |
Shin | +0.750 |
Neg logit contributions | |
️ | -0.705 |
ande | -0.648 |
FIELD | -0.622 |
conflic | -0.615 |
Scrib | -0.605 |
Token | - |
Token ID | 532 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
shown | +1.604 |
Hait | +1.566 |
Whale | +1.539 |
Athena | +1.494 |
Shin | +1.489 |
Neg logit contributions | |
️ | -1.436 |
ande | -1.329 |
FIELD | -1.280 |
conflic | -1.278 |
Scrib | -1.234 |
Token | Kirk |
Token ID | 13855 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
️ | +2.774 |
ande | +2.564 |
FIELD | +2.456 |
Scrib | +2.441 |
conflic | +2.420 |
Neg logit contributions | |
shown | -1.957 |
Hait | -1.893 |
Whale | -1.833 |
Athena | -1.752 |
hur | -1.749 |
Token | Cousins |
Token ID | 32644 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
️ | +4.708 |
ande | +4.355 |
FIELD | +4.234 |
Scrib | +4.156 |
�� | +4.108 |
Neg logit contributions | |
shown | -3.300 |
Hait | -3.137 |
Whale | -3.116 |
Athena | -2.947 |
Shin | -2.894 |
Token | (@ |
Token ID | 4275 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
shown | +0.240 |
Hait | +0.235 |
Whale | +0.232 |
Athena | +0.226 |
Shin | +0.225 |
Neg logit contributions | |
️ | -0.163 |
ande | -0.148 |
FIELD | -0.142 |
conflic | -0.140 |
Scrib | -0.137 |
Token | K |
Token ID | 42 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
️ | +3.899 |
ande | +3.602 |
FIELD | +3.385 |
ards | +3.326 |
LC | +3.290 |
Neg logit contributions | |
Hait | -6.671 |
Whale | -6.554 |
shown | -6.405 |
Athena | -6.317 |
Nicarag | -6.210 |
Token | irk |
Token ID | 14232 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
️ | +2.494 |
ande | +2.300 |
ards | +2.120 |
FIELD | +2.044 |
LC | +2.004 |
Neg logit contributions | |
Whale | -7.461 |
Hait | -7.400 |
shown | -7.268 |
Athena | -7.126 |
Shin | -7.010 |
Token | C |
Token ID | 34 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
️ | +7.191 |
LC | +6.985 |
ande | +6.685 |
ards | +6.427 |
Cro | +6.416 |
Neg logit contributions | |
Whale | -15.694 |
Hait | -15.339 |
Athena | -14.807 |
shown | -14.663 |
Howell | -14.497 |
Token | ous |
Token ID | 516 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
ards | +6.962 |
️ | +6.591 |
ande | +6.396 |
LC | +5.800 |
raf | +5.625 |
Neg logit contributions | |
Whale | -12.741 |
Hait | -12.708 |
Nicarag | -12.145 |
Athena | -12.130 |
shown | -12.032 |
Token | ins |
Token ID | 1040 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
️ | +3.774 |
ande | +3.642 |
ards | +3.544 |
FIELD | +3.455 |
LC | +3.267 |
Neg logit contributions | |
Whale | -5.520 |
shown | -5.394 |
Hait | -5.362 |
Athena | -5.264 |
Shin | -5.096 |
Token | 8 |
Token ID | 23 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
️ | +3.305 |
ande | +3.046 |
FIELD | +2.950 |
Scrib | +2.854 |
conflic | +2.849 |
Neg logit contributions | |
shown | -2.842 |
Hait | -2.790 |
Whale | -2.733 |
Athena | -2.635 |
Shin | -2.592 |
Token | ) |
Token ID | 8 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
️ | +3.054 |
ande | +2.802 |
FIELD | +2.703 |
conflic | +2.657 |
Scrib | +2.650 |
Neg logit contributions | |
shown | -2.382 |
Hait | -2.324 |
Whale | -2.262 |
Athena | -2.182 |
Shin | -2.150 |
Token | Scholar |
Token ID | 11713 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
shown | +0.635 |
Hait | +0.617 |
Whale | +0.606 |
Athena | +0.584 |
Shin | +0.580 |
Neg logit contributions | |
️ | -0.767 |
ande | -0.714 |
FIELD | -0.691 |
conflic | -0.685 |
Scrib | -0.674 |
Token | Crossref |
Token ID | 23613 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
️ | +0.722 |
ande | +0.675 |
FIELD | +0.654 |
conflic | +0.650 |
Scrib | +0.643 |
Neg logit contributions | |
shown | -0.493 |
Hait | -0.479 |
Whale | -0.467 |
Athena | -0.447 |
Shin | -0.444 |
Token | | |
Token ID | 930 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
️ | +3.467 |
ande | +3.226 |
FIELD | +3.118 |
conflic | +3.110 |
Scrib | +3.050 |
Neg logit contributions | |
shown | -2.734 |
Hait | -2.654 |
Whale | -2.603 |
Athena | -2.483 |
Shin | -2.458 |
Token | ISI |
Token ID | 22048 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
️ | +2.376 |
FIELD | +2.007 |
Scrib | +2.004 |
ande | +1.956 |
prism | +1.889 |
Neg logit contributions | |
shown | -4.417 |
Hait | -4.285 |
Whale | -4.171 |
hur | -4.165 |
Shin | -4.040 |
Token |
|
Token ID | 198 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
️ | +4.613 |
FIELD | +4.054 |
ande | +4.023 |
Scrib | +3.976 |
LC | +3.894 |
Neg logit contributions | |
shown | -5.022 |
Hait | -4.931 |
Whale | -4.799 |
hur | -4.661 |
itime | -4.588 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
️ | +5.614 |
FIELD | +4.921 |
ande | +4.819 |
Scrib | +4.793 |
LC | +4.707 |
Neg logit contributions | |
shown | -7.337 |
Whale | -7.296 |
Hait | -7.264 |
itime | -7.095 |
hur | -6.951 |
Token | P |
Token ID | 47 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
️ | +9.617 |
FIELD | +8.607 |
Rail | +8.480 |
LC | +8.150 |
ande | +8.095 |
Neg logit contributions | |
Whale | -12.620 |
Hait | -12.458 |
Athena | -11.887 |
shown | -11.833 |
Hai | -11.501 |
Token | el |
Token ID | 417 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
️ | +4.072 |
ande | +4.012 |
FIELD | +3.714 |
ards | +3.665 |
LC | +3.590 |
Neg logit contributions | |
shown | -4.417 |
Hait | -4.362 |
Whale | -4.342 |
Athena | -4.194 |
Shin | -4.102 |
Token | leg |
Token ID | 1455 |
Feature activation | +7.29e-03 |
Pos logit contributions | |
️ | +2.363 |
ande | +2.256 |
FIELD | +2.110 |
Scrib | +2.059 |
ards | +2.056 |
Neg logit contributions | |
shown | -2.525 |
Hait | -2.464 |
Whale | -2.430 |
Athena | -2.372 |
Shin | -2.321 |
Token | r |
Token ID | 81 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
️ | +0.064 |
ande | +0.060 |
FIELD | +0.057 |
Scrib | +0.056 |
conflic | +0.055 |
Neg logit contributions | |
shown | -0.061 |
Hait | -0.060 |
Whale | -0.059 |
Athena | -0.057 |
Shin | -0.056 |
Token | ini |
Token ID | 5362 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
️ | +2.227 |
ande | +2.122 |
FIELD | +2.024 |
Scrib | +1.945 |
ards | +1.945 |
Neg logit contributions | |
shown | -2.241 |
Hait | -2.236 |
Whale | -2.203 |
Athena | -2.108 |
Shin | -2.075 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
️ | +3.344 |
ande | +3.015 |
FIELD | +2.980 |
Scrib | +2.879 |
ards | +2.863 |
Neg logit contributions | |
shown | -3.631 |
Hait | -3.603 |
Whale | -3.587 |
Athena | -3.382 |
hur | -3.377 |
Token | Google |
Token ID | 11708 |
Feature activation | -8.46e-03 |
Pos logit contributions | |
️ | +1.875 |
ande | +1.708 |
FIELD | +1.677 |
Scrib | +1.603 |
ards | +1.567 |
Neg logit contributions | |
shown | -2.180 |
Hait | -2.179 |
Whale | -2.138 |
Athena | -2.058 |
Shin | -2.042 |
Token | Scholar |
Token ID | 11713 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
shown | +0.067 |
Hait | +0.065 |
Whale | +0.064 |
Athena | +0.061 |
Shin | +0.061 |
Neg logit contributions | |
️ | -0.078 |
ande | -0.072 |
FIELD | -0.070 |
Scrib | -0.069 |
conflic | -0.068 |
Token | Crossref |
Token ID | 23613 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
️ | +1.817 |
ande | +1.689 |
FIELD | +1.636 |
conflic | +1.620 |
Scrib | +1.609 |
Neg logit contributions | |
shown | -1.383 |
Hait | -1.352 |
Whale | -1.323 |
Athena | -1.262 |
hur | -1.258 |
Token |
|
Token ID | 198 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
️ | +3.514 |
ande | +3.254 |
FIELD | +3.141 |
conflic | +3.134 |
Scrib | +3.076 |
Neg logit contributions | |
shown | -2.864 |
Hait | -2.793 |
Whale | -2.736 |
Athena | -2.616 |
Shin | -2.589 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
️ | +5.217 |
FIELD | +4.567 |
ande | +4.517 |
LC | +4.399 |
Scrib | +4.398 |
Neg logit contributions | |
shown | -6.607 |
Hait | -6.569 |
Whale | -6.563 |
itime | -6.332 |
hur | -6.223 |
Token | Pe |
Token ID | 6435 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
️ | +9.421 |
FIELD | +8.179 |
Rail | +7.914 |
LC | +7.872 |
� | +7.708 |
Neg logit contributions | |
Whale | -12.901 |
Hait | -12.800 |
Athena | -12.210 |
shown | -11.989 |
Hai | -11.912 |
Token | eters |
Token ID | 7307 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
shown | +0.895 |
Hait | +0.873 |
Whale | +0.858 |
Athena | +0.829 |
Shin | +0.825 |
Neg logit contributions | |
️ | -0.877 |
ande | -0.808 |
FIELD | -0.781 |
conflic | -0.774 |
Scrib | -0.760 |
Token | , |
Token ID | 11 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
shown | +1.989 |
Hait | +1.944 |
Whale | +1.911 |
Athena | +1.842 |
Shin | +1.833 |
Neg logit contributions | |
️ | -2.931 |
ande | -2.704 |
conflic | -2.655 |
FIELD | -2.652 |
Scrib | -2.594 |
Token | M |
Token ID | 337 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
️ | +0.298 |
ande | +0.275 |
FIELD | +0.269 |
Scrib | +0.268 |
prism | +0.259 |
Neg logit contributions | |
shown | -0.230 |
Hait | -0.219 |
Whale | -0.216 |
hur | -0.210 |
Athena | -0.206 |
Token | ., |
Token ID | 1539 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
️ | +0.365 |
ande | +0.339 |
FIELD | +0.328 |
conflic | +0.324 |
Scrib | +0.320 |
Neg logit contributions | |
shown | -0.309 |
Hait | -0.301 |
Whale | -0.295 |
Athena | -0.284 |
Shin | -0.282 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
️ | +1.665 |
ande | +1.552 |
FIELD | +1.509 |
Scrib | +1.471 |
prism | +1.465 |
Neg logit contributions | |
shown | -1.425 |
Hait | -1.384 |
Whale | -1.355 |
Athena | -1.298 |
hur | -1.293 |
Token | one |
Token ID | 530 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
️ | +1.920 |
ande | +1.787 |
FIELD | +1.738 |
prism | +1.703 |
Scrib | +1.703 |
Neg logit contributions | |
shown | -1.672 |
Hait | -1.616 |
Whale | -1.584 |
hur | -1.516 |
Athena | -1.515 |
Token | might |
Token ID | 1244 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
️ | +2.596 |
ande | +2.414 |
FIELD | +2.340 |
prism | +2.318 |
Scrib | +2.266 |
Neg logit contributions | |
shown | -2.651 |
Hait | -2.544 |
Whale | -2.499 |
Athena | -2.416 |
hur | -2.414 |
Token | ask |
Token ID | 1265 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
️ | +1.051 |
ande | +0.973 |
FIELD | +0.942 |
prism | +0.913 |
Scrib | +0.913 |
Neg logit contributions | |
shown | -1.050 |
Hait | -1.017 |
Whale | -1.010 |
Athena | -0.965 |
hur | -0.960 |
Token | , |
Token ID | 11 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
️ | +2.063 |
ande | +1.927 |
FIELD | +1.859 |
Scrib | +1.823 |
prism | +1.810 |
Neg logit contributions | |
shown | -1.791 |
Hait | -1.717 |
Whale | -1.684 |
Athena | -1.620 |
hur | -1.619 |
Token | why |
Token ID | 1521 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
️ | +4.074 |
ande | +3.722 |
prism | +3.627 |
Scrib | +3.605 |
FIELD | +3.597 |
Neg logit contributions | |
shown | -4.134 |
Hait | -3.971 |
Whale | -3.846 |
hur | -3.789 |
Athena | -3.728 |
Token | go |
Token ID | 467 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
️ | +9.791 |
prism | +9.339 |
ande | +9.189 |
Scrib | +8.674 |
FIELD | +8.659 |
Neg logit contributions | |
shown | -11.308 |
Hait | -11.056 |
hur | -10.574 |
Whale | -10.568 |
Shin | -10.270 |
Token | that |
Token ID | 326 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
️ | +3.516 |
ande | +3.304 |
FIELD | +3.220 |
Scrib | +3.145 |
prism | +3.135 |
Neg logit contributions | |
shown | -3.416 |
Hait | -3.291 |
Whale | -3.214 |
hur | -3.088 |
Shin | -3.069 |
Token | one |
Token ID | 530 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
️ | +1.372 |
ande | +1.269 |
FIELD | +1.227 |
Scrib | +1.205 |
prism | +1.196 |
Neg logit contributions | |
shown | -1.457 |
Hait | -1.419 |
Whale | -1.388 |
hur | -1.336 |
Athena | -1.333 |
Token | small |
Token ID | 1402 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
️ | +1.154 |
ande | +1.074 |
FIELD | +1.035 |
conflic | +1.016 |
Scrib | +1.014 |
Neg logit contributions | |
shown | -0.993 |
Hait | -0.963 |
Whale | -0.943 |
Athena | -0.903 |
Shin | -0.902 |
Token |
|
Token ID | 198 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
️ | +5.067 |
ande | +4.805 |
prism | +4.646 |
FIELD | +4.572 |
Scrib | +4.492 |
Neg logit contributions | |
shown | -4.649 |
Hait | -4.504 |
Whale | -4.350 |
hur | -4.234 |
Athena | -4.228 |
Token |
|
Token ID | 198 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
️ | +0.449 |
ande | +0.418 |
FIELD | +0.404 |
conflic | +0.399 |
Scrib | +0.396 |
Neg logit contributions | |
shown | -0.375 |
Hait | -0.365 |
Whale | -0.358 |
Athena | -0.344 |
Shin | -0.342 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
️ | +2.891 |
ande | +2.627 |
FIELD | +2.587 |
Scrib | +2.502 |
ards | +2.479 |
Neg logit contributions | |
shown | -3.030 |
Hait | -2.987 |
Whale | -2.976 |
Athena | -2.816 |
hur | -2.805 |
Token | Google |
Token ID | 11708 |
Feature activation | -1.42e-03 |
Pos logit contributions | |
️ | +0.121 |
ande | +0.111 |
FIELD | +0.108 |
conflic | +0.105 |
Scrib | +0.104 |
Neg logit contributions | |
shown | -0.128 |
Hait | -0.126 |
Whale | -0.124 |
Athena | -0.119 |
Shin | -0.119 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
shown | +0.011 |
Hait | +0.011 |
Whale | +0.011 |
Athena | +0.010 |
Shin | +0.010 |
Neg logit contributions | |
️ | -0.013 |
ande | -0.012 |
FIELD | -0.012 |
Scrib | -0.012 |
conflic | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
shown | +0.404 |
Hait | +0.392 |
Whale | +0.385 |
Athena | +0.370 |
Shin | +0.368 |
Neg logit contributions | |
️ | -0.521 |
ande | -0.487 |
FIELD | -0.471 |
conflic | -0.466 |
Scrib | -0.460 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
️ | +6.176 |
FIELD | +5.319 |
LC | +5.163 |
ande | +5.163 |
Scrib | +5.131 |
Neg logit contributions | |
shown | -8.501 |
Whale | -8.449 |
Hait | -8.439 |
itime | -8.259 |
hur | -8.100 |
Token | Ol |
Token ID | 30098 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
️ | +9.598 |
FIELD | +8.428 |
� | +8.184 |
Rail | +8.040 |
ande | +7.979 |
Neg logit contributions | |
Whale | -12.340 |
Hait | -12.146 |
Athena | -11.659 |
shown | -11.363 |
Hai | -11.326 |
Token | we |
Token ID | 732 |
Feature activation | +9.54e-03 |
Pos logit contributions | |
️ | +4.268 |
ande | +4.104 |
ards | +3.696 |
FIELD | +3.648 |
Scrib | +3.626 |
Neg logit contributions | |
shown | -4.497 |
Hait | -4.412 |
Athena | -4.359 |
Whale | -4.306 |
Shin | -4.216 |
Token | us |
Token ID | 385 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
️ | +0.083 |
ande | +0.078 |
FIELD | +0.074 |
Scrib | +0.072 |
conflic | +0.072 |
Neg logit contributions | |
shown | -0.080 |
Hait | -0.078 |
Whale | -0.077 |
Athena | -0.074 |
Shin | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
shown | +0.299 |
Hait | +0.291 |
Whale | +0.285 |
Athena | +0.274 |
Shin | +0.271 |
Neg logit contributions | |
️ | -0.388 |
ande | -0.363 |
FIELD | -0.351 |
Scrib | -0.343 |
conflic | -0.343 |
Token | D |
Token ID | 360 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
️ | +1.219 |
ande | +1.146 |
FIELD | +1.117 |
Scrib | +1.112 |
ards | +1.089 |
Neg logit contributions | |
shown | -0.898 |
Hait | -0.856 |
Whale | -0.844 |
hur | -0.817 |
Athena | -0.800 |
Token |
|
Token ID | 198 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
shown | +0.164 |
Hait | +0.159 |
Whale | +0.156 |
Athena | +0.150 |
Shin | +0.149 |
Neg logit contributions | |
️ | -0.201 |
ande | -0.188 |
FIELD | -0.182 |
conflic | -0.180 |
Scrib | -0.177 |
Token |
|
Token ID | 198 |
Feature activation | -9.28e-03 |
Pos logit contributions | |
️ | +2.283 |
ande | +2.084 |
FIELD | +2.045 |
Scrib | +1.980 |
ards | +1.959 |
Neg logit contributions | |
shown | -2.287 |
Hait | -2.251 |
Whale | -2.236 |
Athena | -2.122 |
hur | -2.111 |
Token | Google |
Token ID | 11708 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
shown | +0.082 |
Hait | +0.080 |
Whale | +0.079 |
Athena | +0.076 |
Shin | +0.076 |
Neg logit contributions | |
️ | -0.077 |
ande | -0.071 |
FIELD | -0.069 |
conflic | -0.067 |
Scrib | -0.067 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
shown | +0.127 |
Hait | +0.124 |
Whale | +0.121 |
Athena | +0.116 |
Shin | +0.116 |
Neg logit contributions | |
️ | -0.148 |
ande | -0.138 |
FIELD | -0.133 |
Scrib | -0.131 |
conflic | -0.130 |
Token |
|
Token ID | 198 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
shown | +0.211 |
Hait | +0.205 |
Whale | +0.202 |
Athena | +0.194 |
Shin | +0.193 |
Neg logit contributions | |
️ | -0.266 |
ande | -0.248 |
FIELD | -0.240 |
conflic | -0.238 |
Scrib | -0.235 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
️ | +5.350 |
FIELD | +4.662 |
ande | +4.600 |
Scrib | +4.497 |
LC | +4.497 |
Neg logit contributions | |
shown | -6.864 |
Hait | -6.802 |
Whale | -6.799 |
itime | -6.563 |
hur | -6.484 |
Token | Park |
Token ID | 25478 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
️ | +9.578 |
FIELD | +8.457 |
� | +8.208 |
ande | +8.067 |
Rail | +8.051 |
Neg logit contributions | |
Whale | -12.134 |
Hait | -11.962 |
Athena | -11.484 |
shown | -11.244 |
Hai | -11.125 |
Token | er |
Token ID | 263 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
️ | +2.945 |
ande | +2.822 |
FIELD | +2.695 |
Scrib | +2.626 |
ards | +2.626 |
Neg logit contributions | |
shown | -2.659 |
Hait | -2.582 |
Whale | -2.541 |
Athena | -2.453 |
Shin | -2.374 |
Token | , |
Token ID | 11 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
️ | +0.192 |
ande | +0.179 |
FIELD | +0.173 |
conflic | +0.171 |
Scrib | +0.169 |
Neg logit contributions | |
shown | -0.145 |
Hait | -0.141 |
Whale | -0.138 |
Athena | -0.132 |
Shin | -0.131 |
Token | A |
Token ID | 317 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
️ | +0.466 |
ande | +0.429 |
FIELD | +0.422 |
Scrib | +0.419 |
prism | +0.406 |
Neg logit contributions | |
shown | -0.362 |
Hait | -0.345 |
Whale | -0.340 |
hur | -0.331 |
Athena | -0.324 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
️ | +2.245 |
ande | +2.089 |
FIELD | +2.005 |
conflic | +1.972 |
�� | +1.961 |
Neg logit contributions | |
shown | -2.077 |
Hait | -2.016 |
Whale | -1.976 |
Athena | -1.912 |
Shin | -1.886 |
Token | good |
Token ID | 922 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
shown | +0.683 |
Hait | +0.664 |
Whale | +0.653 |
Athena | +0.629 |
Shin | +0.625 |
Neg logit contributions | |
️ | -0.745 |
ande | -0.690 |
FIELD | -0.666 |
conflic | -0.658 |
Scrib | -0.649 |
Token | ? |
Token ID | 30 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
️ | +2.241 |
ande | +2.058 |
FIELD | +2.008 |
ards | +1.929 |
Scrib | +1.914 |
Neg logit contributions | |
shown | -2.632 |
Hait | -2.601 |
Whale | -2.559 |
Athena | -2.447 |
hur | -2.430 |
Token | We |
Token ID | 775 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
️ | +6.256 |
Scrib | +5.354 |
ande | +5.216 |
FIELD | +5.161 |
� | +5.077 |
Neg logit contributions | |
shown | -7.035 |
hur | -6.650 |
Hait | -6.588 |
Whale | -6.420 |
itime | -6.417 |
Token | need |
Token ID | 761 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
️ | +1.368 |
ande | +1.243 |
FIELD | +1.189 |
Scrib | +1.162 |
prism | +1.158 |
Neg logit contributions | |
shown | -1.617 |
Hait | -1.581 |
Whale | -1.566 |
Athena | -1.499 |
Shin | -1.489 |
Token | something |
Token ID | 1223 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
shown | +1.920 |
Hait | +1.870 |
Whale | +1.837 |
Athena | +1.777 |
Shin | +1.766 |
Neg logit contributions | |
️ | -2.066 |
ande | -1.914 |
FIELD | -1.850 |
conflic | -1.834 |
Scrib | -1.804 |
Token | to |
Token ID | 284 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
️ | +4.106 |
ande | +3.760 |
FIELD | +3.655 |
prism | +3.528 |
ards | +3.524 |
Neg logit contributions | |
shown | -3.640 |
Hait | -3.591 |
Whale | -3.518 |
hur | -3.296 |
Athena | -3.283 |
Token | raise |
Token ID | 5298 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
️ | +5.910 |
ande | +5.123 |
prism | +4.922 |
ards | +4.579 |
LC | +4.541 |
Neg logit contributions | |
shown | -16.048 |
Hait | -15.652 |
Whale | -15.571 |
hur | -14.666 |
Howell | -14.595 |
Token | our |
Token ID | 674 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
️ | +3.519 |
ande | +3.286 |
FIELD | +3.098 |
prism | +3.023 |
Scrib | +2.985 |
Neg logit contributions | |
shown | -3.278 |
Hait | -3.162 |
Whale | -3.142 |
Athena | -2.985 |
hur | -2.960 |
Token | pitch |
Token ID | 7078 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
️ | +4.807 |
ande | +4.189 |
prism | +4.013 |
FIELD | +3.924 |
Scrib | +3.653 |
Neg logit contributions | |
shown | -8.084 |
Hait | -7.955 |
Whale | -7.766 |
Athena | -7.486 |
Howell | -7.382 |
Token | for |
Token ID | 1640 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
️ | +1.599 |
ande | +1.513 |
FIELD | +1.437 |
ards | +1.377 |
Scrib | +1.362 |
Neg logit contributions | |
shown | -1.547 |
Hait | -1.539 |
Whale | -1.517 |
Athena | -1.469 |
Shin | -1.453 |
Token | ks |
Token ID | 591 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
️ | +2.533 |
ards | +2.358 |
ande | +2.298 |
LC | +1.880 |
FIELD | +1.841 |
Neg logit contributions | |
Hait | -10.051 |
shown | -10.032 |
Whale | -9.976 |
Athena | -9.713 |
Nicarag | -9.660 |
Token | | |
Token ID | 930 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
️ | +3.204 |
ande | +2.988 |
FIELD | +2.889 |
conflic | +2.879 |
Scrib | +2.826 |
Neg logit contributions | |
shown | -2.456 |
Hait | -2.384 |
Whale | -2.340 |
Athena | -2.226 |
Shin | -2.206 |
Token | Medline |
Token ID | 34582 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
️ | +1.729 |
FIELD | +1.456 |
ande | +1.441 |
Scrib | +1.430 |
prism | +1.359 |
Neg logit contributions | |
shown | -3.297 |
Hait | -3.215 |
Whale | -3.146 |
hur | -3.111 |
Shin | -3.035 |
Token | | |
Token ID | 930 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
️ | +2.531 |
ande | +2.370 |
FIELD | +2.299 |
conflic | +2.287 |
Scrib | +2.258 |
Neg logit contributions | |
shown | -1.705 |
Hait | -1.657 |
Whale | -1.615 |
Athena | -1.538 |
Shin | -1.523 |
Token | ISI |
Token ID | 22048 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
️ | +2.352 |
ande | +1.918 |
FIELD | +1.915 |
Scrib | +1.836 |
prism | +1.714 |
Neg logit contributions | |
shown | -6.182 |
Hait | -6.155 |
Whale | -6.055 |
hur | -5.942 |
Shin | -5.823 |
Token |
|
Token ID | 198 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
️ | +5.917 |
FIELD | +5.222 |
ande | +5.105 |
Scrib | +5.104 |
LC | +4.942 |
Neg logit contributions | |
shown | -6.928 |
Hait | -6.888 |
Whale | -6.737 |
hur | -6.541 |
itime | -6.473 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
️ | +5.885 |
FIELD | +5.176 |
Scrib | +5.093 |
ande | +5.036 |
LC | +4.955 |
Neg logit contributions | |
Whale | -7.990 |
shown | -7.987 |
Hait | -7.957 |
itime | -7.768 |
hur | -7.592 |
Token | R |
Token ID | 49 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
️ | +8.366 |
FIELD | +7.639 |
Rail | +7.368 |
ande | +7.120 |
Scrib | +7.092 |
Neg logit contributions | |
Whale | -12.864 |
Hait | -12.768 |
Athena | -12.066 |
shown | -12.061 |
Hai | -11.598 |
Token | ig |
Token ID | 328 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
️ | +1.021 |
ande | +0.963 |
FIELD | +0.910 |
ards | +0.891 |
Scrib | +0.885 |
Neg logit contributions | |
shown | -1.059 |
Hait | -1.036 |
Whale | -1.020 |
Athena | -0.991 |
Shin | -0.974 |
Token | by |
Token ID | 1525 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
shown | +1.718 |
Hait | +1.670 |
Whale | +1.644 |
Athena | +1.587 |
Shin | +1.581 |
Neg logit contributions | |
️ | -1.733 |
ande | -1.585 |
FIELD | -1.543 |
conflic | -1.542 |
Scrib | -1.503 |
Token | , |
Token ID | 11 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
shown | +1.722 |
Hait | +1.676 |
Whale | +1.652 |
Shin | +1.588 |
Athena | +1.579 |
Neg logit contributions | |
️ | -2.485 |
ande | -2.303 |
FIELD | -2.251 |
conflic | -2.249 |
Scrib | -2.207 |
Token | K |
Token ID | 509 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
shown | +0.426 |
Hait | +0.409 |
Whale | +0.402 |
hur | +0.387 |
Athena | +0.385 |
Neg logit contributions | |
️ | -0.564 |
ande | -0.523 |
FIELD | -0.511 |
Scrib | -0.504 |
prism | -0.492 |
Token | ata |
Token ID | 1045 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
shown | +2.491 |
Hait | +2.281 |
Whale | +2.205 |
Athena | +2.139 |
hur | +2.093 |
Neg logit contributions | |
️ | -5.939 |
conflic | -5.627 |
PDATE | -5.486 |
ande | -5.485 |
FIELD | -5.461 |
Token | pal |
Token ID | 6340 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
️ | +3.229 |
prism | +2.823 |
ande | +2.823 |
Scrib | +2.678 |
FIELD | +2.594 |
Neg logit contributions | |
shown | -7.449 |
Hait | -7.268 |
Whale | -7.230 |
Athena | -6.936 |
hur | -6.871 |
Token | mar |
Token ID | 3876 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
shown | +1.616 |
Hait | +1.549 |
Whale | +1.509 |
Athena | +1.435 |
hur | +1.429 |
Neg logit contributions | |
️ | -3.024 |
ande | -2.842 |
conflic | -2.785 |
FIELD | -2.772 |
Scrib | -2.718 |
Token | is |
Token ID | 271 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
shown | +0.429 |
Hait | +0.421 |
Whale | +0.415 |
Athena | +0.400 |
Shin | +0.398 |
Neg logit contributions | |
️ | -0.357 |
ande | -0.330 |
FIELD | -0.315 |
Scrib | -0.306 |
prism | -0.301 |
Token | et |
Token ID | 2123 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
️ | +0.720 |
ande | +0.680 |
FIELD | +0.648 |
Scrib | +0.638 |
prism | +0.632 |
Neg logit contributions | |
shown | -0.627 |
Hait | -0.607 |
Whale | -0.604 |
Shin | -0.571 |
Athena | -0.571 |
Token | plant |
Token ID | 4618 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
shown | +0.023 |
Hait | +0.022 |
Whale | +0.022 |
Athena | +0.021 |
Shin | +0.021 |
Neg logit contributions | |
️ | -0.026 |
ande | -0.025 |
FIELD | -0.024 |
conflic | -0.023 |
prism | -0.023 |
Token | aris |
Token ID | 20066 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ande | +7.589 |
ards | +7.027 |
️ | +6.911 |
FIELD | +6.105 |
raf | +5.892 |
Neg logit contributions | |
Whale | -13.622 |
Hait | -13.406 |
shown | -13.000 |
は | -12.427 |
Howell | -12.370 |
Token | ," |
Token ID | 553 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
shown | +1.595 |
Hait | +1.548 |
Whale | +1.514 |
Athena | +1.454 |
Shin | +1.445 |
Neg logit contributions | |
️ | -2.340 |
ande | -2.183 |
conflic | -2.129 |
FIELD | -2.120 |
Scrib | -2.072 |
Token | " |
Token ID | 366 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
️ | +3.778 |
ande | +3.405 |
FIELD | +3.334 |
Scrib | +3.316 |
prism | +3.213 |
Neg logit contributions | |
shown | -4.904 |
Hait | -4.846 |
Whale | -4.756 |
hur | -4.631 |
itime | -4.547 |
Token | P |
Token ID | 47 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
️ | +1.400 |
ande | +1.256 |
FIELD | +1.240 |
Scrib | +1.168 |
� | +1.145 |
Neg logit contributions | |
shown | -1.981 |
Hait | -1.971 |
Whale | -1.949 |
Athena | -1.882 |
Shin | -1.862 |
Token | unct |
Token ID | 16260 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
️ | +2.509 |
ande | +2.328 |
FIELD | +1.881 |
ards | +1.859 |
Scrib | +1.832 |
Neg logit contributions | |
Hait | -9.045 |
Whale | -9.005 |
shown | -8.932 |
Athena | -8.736 |
Shin | -8.679 |
Token | doesn |
Token ID | 1595 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
shown | +0.956 |
Hait | +0.929 |
Whale | +0.913 |
Athena | +0.879 |
Shin | +0.873 |
Neg logit contributions | |
️ | -1.094 |
ande | -1.015 |
FIELD | -0.979 |
conflic | -0.967 |
Scrib | -0.957 |
Token | 't |
Token ID | 470 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
shown | +1.168 |
Hait | +1.131 |
Whale | +1.110 |
Athena | +1.072 |
Shin | +1.067 |
Neg logit contributions | |
️ | -1.383 |
ande | -1.289 |
conflic | -1.263 |
FIELD | -1.245 |
Scrib | -1.219 |
Token | , |
Token ID | 11 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
️ | +1.477 |
ande | +1.353 |
FIELD | +1.287 |
Scrib | +1.262 |
conflic | +1.255 |
Neg logit contributions | |
shown | -1.549 |
Hait | -1.490 |
Whale | -1.473 |
Athena | -1.422 |
Shin | -1.401 |
Token | we |
Token ID | 356 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
️ | +4.290 |
ande | +3.933 |
FIELD | +3.733 |
Scrib | +3.733 |
prism | +3.725 |
Neg logit contributions | |
shown | -4.334 |
Hait | -4.108 |
Whale | -4.067 |
hur | -3.847 |
Athena | -3.845 |
Token | 'll |
Token ID | 1183 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
️ | +3.377 |
ande | +3.062 |
FIELD | +2.929 |
Scrib | +2.849 |
ards | +2.828 |
Neg logit contributions | |
shown | -3.931 |
Hait | -3.792 |
Whale | -3.754 |
Athena | -3.634 |
hur | -3.566 |
Token | play |
Token ID | 711 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
️ | +2.162 |
ande | +1.953 |
FIELD | +1.911 |
conflic | +1.856 |
Scrib | +1.842 |
Neg logit contributions | |
shown | -2.441 |
Hait | -2.366 |
Whale | -2.331 |
hur | -2.234 |
Athena | -2.230 |
Token | ball |
Token ID | 2613 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
️ | +7.808 |
FIELD | +6.811 |
prism | +6.791 |
ande | +6.576 |
Scrib | +6.375 |
Neg logit contributions | |
shown | -12.767 |
Hait | -12.622 |
Whale | -11.939 |
hur | -11.904 |
Athena | -11.680 |
Token | ." |
Token ID | 526 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
️ | +2.227 |
ande | +2.051 |
FIELD | +1.995 |
Scrib | +1.952 |
conflic | +1.933 |
Neg logit contributions | |
shown | -1.791 |
Hait | -1.711 |
Whale | -1.677 |
Athena | -1.613 |
Shin | -1.590 |
Token |
|
Token ID | 198 |
Feature activation | -2.46e-03 |
Pos logit contributions | |
shown | +0.950 |
Hait | +0.921 |
Whale | +0.909 |
Athena | +0.874 |
Shin | +0.868 |
Neg logit contributions | |
️ | -1.183 |
ande | -1.107 |
FIELD | -1.072 |
conflic | -1.064 |
Scrib | -1.045 |
Token |
|
Token ID | 198 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
shown | +0.020 |
Hait | +0.019 |
Whale | +0.019 |
Athena | +0.018 |
Shin | +0.018 |
Neg logit contributions | |
️ | -0.022 |
ande | -0.021 |
FIELD | -0.020 |
Scrib | -0.020 |
prism | -0.019 |
Token | Also |
Token ID | 7583 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
️ | +0.625 |
ande | +0.568 |
FIELD | +0.558 |
Scrib | +0.532 |
�� | +0.523 |
Neg logit contributions | |
shown | -0.729 |
Hait | -0.723 |
Whale | -0.713 |
Athena | -0.689 |
Shin | -0.684 |
Token | � |
Token ID | 247 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
shown | +0.363 |
Hait | +0.356 |
Whale | +0.352 |
Athena | +0.344 |
Shin | +0.342 |
Neg logit contributions | |
️ | -0.159 |
ande | -0.140 |
FIELD | -0.132 |
conflic | -0.129 |
Scrib | -0.126 |
Token | on |
Token ID | 319 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
shown | +0.534 |
Hait | +0.519 |
Whale | +0.509 |
Athena | +0.490 |
Shin | +0.487 |
Neg logit contributions | |
️ | -0.650 |
ande | -0.605 |
FIELD | -0.586 |
conflic | -0.579 |
Scrib | -0.572 |
Token | Him |
Token ID | 10978 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
️ | +0.684 |
ande | +0.634 |
Scrib | +0.616 |
FIELD | +0.612 |
conflic | +0.600 |
Neg logit contributions | |
shown | -0.519 |
Hait | -0.496 |
Whale | -0.481 |
hur | -0.468 |
Athena | -0.467 |
Token |
|
Token ID | 198 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
shown | +1.467 |
Hait | +1.428 |
Whale | +1.410 |
Athena | +1.353 |
Shin | +1.345 |
Neg logit contributions | |
️ | -1.791 |
ande | -1.676 |
FIELD | -1.627 |
conflic | -1.622 |
�� | -1.581 |
Token |
|
Token ID | 198 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
️ | +0.719 |
ande | +0.661 |
FIELD | +0.646 |
Scrib | +0.627 |
ards | +0.617 |
Neg logit contributions | |
shown | -0.649 |
Hait | -0.636 |
Whale | -0.626 |
Athena | -0.600 |
hur | -0.593 |
Token | C |
Token ID | 34 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
️ | +1.062 |
ande | +0.968 |
FIELD | +0.940 |
Scrib | +0.905 |
� | +0.887 |
Neg logit contributions | |
shown | -1.199 |
Hait | -1.186 |
Whale | -1.169 |
Athena | -1.135 |
Shin | -1.126 |
Token | ull |
Token ID | 724 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
ande | +6.755 |
ards | +6.057 |
️ | +5.622 |
LC | +5.417 |
lez | +5.338 |
Neg logit contributions | |
Hait | -14.406 |
Athena | -14.294 |
Nicarag | -14.170 |
Shinra | -13.814 |
Shin | -13.641 |
Token | in |
Token ID | 259 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
️ | +2.845 |
ande | +2.734 |
FIELD | +2.533 |
ards | +2.490 |
Scrib | +2.459 |
Neg logit contributions | |
shown | -3.149 |
Hait | -3.107 |
Whale | -3.087 |
Athena | -2.991 |
Shin | -2.905 |
Token | an |
Token ID | 272 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
️ | +2.171 |
ande | +2.073 |
FIELD | +1.931 |
ards | +1.879 |
Scrib | +1.839 |
Neg logit contributions | |
shown | -2.548 |
Hait | -2.523 |
Whale | -2.497 |
Athena | -2.403 |
Shin | -2.363 |
Token | was |
Token ID | 373 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
️ | +0.684 |
ande | +0.635 |
FIELD | +0.613 |
conflic | +0.603 |
Scrib | +0.598 |
Neg logit contributions | |
shown | -0.587 |
Hait | -0.570 |
Whale | -0.559 |
Athena | -0.538 |
Shin | -0.533 |
Token | positioned |
Token ID | 19378 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
shown | +0.950 |
Hait | +0.925 |
Whale | +0.908 |
Athena | +0.875 |
Shin | +0.869 |
Neg logit contributions | |
️ | -1.067 |
ande | -0.990 |
FIELD | -0.956 |
conflic | -0.942 |
Scrib | -0.932 |
Token | : |
Token ID | 25 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
shown | +1.270 |
Hait | +1.234 |
Whale | +1.210 |
Athena | +1.165 |
Shin | +1.157 |
Neg logit contributions | |
️ | -1.580 |
ande | -1.471 |
FIELD | -1.425 |
conflic | -1.408 |
Scrib | -1.392 |
Token | In |
Token ID | 554 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
shown | +1.094 |
Hait | +1.063 |
Whale | +1.043 |
Athena | +1.007 |
Shin | +1.000 |
Neg logit contributions | |
️ | -1.236 |
ande | -1.147 |
FIELD | -1.108 |
conflic | -1.093 |
Scrib | -1.084 |
Token | the |
Token ID | 262 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
️ | +1.081 |
ande | +1.012 |
FIELD | +0.975 |
Scrib | +0.958 |
conflic | +0.951 |
Neg logit contributions | |
shown | -0.865 |
Hait | -0.840 |
Whale | -0.816 |
Athena | -0.786 |
Shin | -0.776 |
Token | Atlanta |
Token ID | 9371 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
️ | +2.515 |
ande | +2.341 |
Scrib | +2.269 |
prism | +2.260 |
FIELD | +2.243 |
Neg logit contributions | |
shown | -2.468 |
Hait | -2.353 |
Whale | -2.287 |
hur | -2.234 |
Athena | -2.207 |
Token | Journal |
Token ID | 4913 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
️ | +0.178 |
ande | +0.165 |
FIELD | +0.159 |
conflic | +0.158 |
Scrib | +0.156 |
Neg logit contributions | |
shown | -0.150 |
Hait | -0.146 |
Whale | -0.143 |
Athena | -0.138 |
Shin | -0.136 |
Token | - |
Token ID | 12 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
️ | +5.280 |
ande | +5.135 |
Scrib | +4.873 |
FIELD | +4.858 |
prism | +4.771 |
Neg logit contributions | |
shown | -4.503 |
Hait | -4.278 |
Nicarag | -3.955 |
Whale | -3.951 |
hur | -3.946 |
Token | Const |
Token ID | 34184 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ande | +6.248 |
prism | +6.003 |
️ | +5.851 |
LC | +5.371 |
FIELD | +5.342 |
Neg logit contributions | |
shown | -14.431 |
Hait | -14.296 |
Nicarag | -14.265 |
Whale | -13.498 |
Hai | -13.409 |
Token | itution |
Token ID | 2738 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
️ | +0.712 |
ande | +0.654 |
FIELD | +0.589 |
Scrib | +0.578 |
conflic | +0.562 |
Neg logit contributions | |
shown | -1.744 |
Hait | -1.696 |
Whale | -1.677 |
Athena | -1.628 |
Shin | -1.628 |
Token | 's |
Token ID | 338 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
️ | +4.665 |
ande | +4.345 |
Scrib | +4.161 |
FIELD | +4.146 |
prism | +4.094 |
Neg logit contributions | |
shown | -4.287 |
Hait | -4.099 |
Whale | -3.909 |
Athena | -3.814 |
hur | -3.776 |
Token | published |
Token ID | 3199 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
️ | +0.593 |
ande | +0.548 |
FIELD | +0.527 |
Scrib | +0.523 |
conflic | +0.521 |
Neg logit contributions | |
shown | -0.564 |
Hait | -0.546 |
Whale | -0.533 |
Athena | -0.515 |
hur | -0.511 |
Token | scouting |
Token ID | 27088 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
shown | +2.831 |
Hait | +2.785 |
Whale | +2.754 |
Athena | +2.656 |
Shin | +2.655 |
Neg logit contributions | |
️ | -2.935 |
ande | -2.717 |
FIELD | -2.637 |
conflic | -2.608 |
�� | -2.532 |
Token | AM |
Token ID | 2390 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
shown | +1.008 |
Hait | +0.964 |
Whale | +0.941 |
Athena | +0.893 |
Shin | +0.886 |
Neg logit contributions | |
️ | -2.030 |
ande | -1.916 |
conflic | -1.872 |
FIELD | -1.858 |
Scrib | -1.828 |
Token | OUNT |
Token ID | 28270 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
️ | +3.307 |
FIELD | +3.029 |
ande | +2.879 |
LC | +2.707 |
Scrib | +2.699 |
Neg logit contributions | |
Hait | -7.382 |
shown | -7.345 |
Whale | -7.340 |
Athena | -7.171 |
Shin | -7.085 |
Token | P |
Token ID | 350 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
️ | +6.231 |
FIELD | +5.719 |
Scrib | +5.656 |
prism | +5.397 |
ande | +5.390 |
Neg logit contributions | |
shown | -6.164 |
Hait | -6.047 |
hur | -5.946 |
Whale | -5.881 |
Athena | -5.683 |
Token | ICT |
Token ID | 18379 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
️ | +3.598 |
FIELD | +3.320 |
ande | +3.185 |
LC | +3.140 |
Scrib | +3.027 |
Neg logit contributions | |
shown | -5.080 |
Hait | -5.076 |
Whale | -5.054 |
hur | -4.853 |
Athena | -4.782 |
Token | URES |
Token ID | 29514 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
️ | +0.241 |
ande | +0.195 |
FIELD | +0.188 |
Scrib | +0.173 |
ards | +0.165 |
Neg logit contributions | |
shown | -0.816 |
Hait | -0.803 |
Whale | -0.795 |
Athena | -0.777 |
hur | -0.775 |
Token | RE |
Token ID | 4526 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
️ | +8.270 |
FIELD | +7.735 |
Scrib | +7.376 |
ande | +7.090 |
� | +7.017 |
Neg logit contributions | |
shown | -8.073 |
Hait | -7.925 |
hur | -7.804 |
Whale | -7.703 |
itime | -7.445 |
Token | QUEST |
Token ID | 35780 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
️ | +1.749 |
FIELD | +1.612 |
LC | +1.061 |
QUEST | +0.884 |
FR | +0.435 |
Neg logit contributions | |
Hait | -18.838 |
Whale | -18.715 |
Athena | -18.475 |
hur | -18.354 |
Shin | -18.300 |
Token |
|
Token ID | 198 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
️ | +0.529 |
ande | +0.491 |
FIELD | +0.477 |
conflic | +0.468 |
Scrib | +0.465 |
Neg logit contributions | |
shown | -0.444 |
Hait | -0.432 |
Whale | -0.424 |
Athena | -0.409 |
Shin | -0.405 |
Token |
|
Token ID | 198 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
️ | +0.685 |
ande | +0.629 |
FIELD | +0.615 |
Scrib | +0.597 |
ards | +0.588 |
Neg logit contributions | |
shown | -0.623 |
Hait | -0.611 |
Whale | -0.603 |
Athena | -0.576 |
hur | -0.570 |
Token | Another |
Token ID | 6610 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
shown | +0.301 |
Hait | +0.294 |
Whale | +0.290 |
Athena | +0.280 |
Shin | +0.278 |
Neg logit contributions | |
️ | -0.292 |
ande | -0.269 |
FIELD | -0.261 |
conflic | -0.254 |
Scrib | -0.253 |
Token | photo |
Token ID | 4590 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
️ | +1.460 |
ande | +1.341 |
FIELD | +1.309 |
conflic | +1.285 |
Scrib | +1.281 |
Neg logit contributions | |
shown | -1.307 |
Hait | -1.284 |
Whale | -1.256 |
Athena | -1.211 |
hur | -1.204 |
Token | one |
Token ID | 530 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
shown | +1.834 |
Hait | +1.782 |
Whale | +1.743 |
Athena | +1.677 |
Shin | +1.667 |
Neg logit contributions | |
️ | -2.578 |
ande | -2.413 |
FIELD | -2.340 |
conflic | -2.320 |
Scrib | -2.287 |
Token | touchdown |
Token ID | 10242 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
️ | +5.546 |
ande | +4.991 |
FIELD | +4.942 |
prism | +4.840 |
Scrib | +4.798 |
Neg logit contributions | |
shown | -4.633 |
Hait | -4.431 |
Whale | -4.392 |
hur | -4.190 |
Shin | -4.025 |
Token | .) |
Token ID | 2014 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
️ | +1.493 |
ande | +1.371 |
FIELD | +1.337 |
Scrib | +1.307 |
conflic | +1.295 |
Neg logit contributions | |
shown | -1.218 |
Hait | -1.170 |
Whale | -1.149 |
Athena | -1.095 |
hur | -1.091 |
Token |
|
Token ID | 198 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
️ | +0.418 |
ande | +0.387 |
FIELD | +0.376 |
Scrib | +0.369 |
conflic | +0.366 |
Neg logit contributions | |
shown | -0.330 |
Hait | -0.320 |
Whale | -0.314 |
Athena | -0.302 |
Shin | -0.299 |
Token |
|
Token ID | 198 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
️ | +0.182 |
ande | +0.167 |
FIELD | +0.164 |
Scrib | +0.159 |
prism | +0.156 |
Neg logit contributions | |
shown | -0.156 |
Hait | -0.153 |
Whale | -0.150 |
Athena | -0.145 |
Shin | -0.143 |
Token | Mc |
Token ID | 9742 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
️ | +3.279 |
ande | +2.964 |
FIELD | +2.959 |
LC | +2.784 |
� | +2.767 |
Neg logit contributions | |
Hait | -3.346 |
Whale | -3.344 |
shown | -3.303 |
Athena | -3.210 |
Shin | -3.178 |
Token | F |
Token ID | 37 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
️ | +5.219 |
FIELD | +5.202 |
ande | +4.176 |
ards | +4.155 |
raf | +4.022 |
Neg logit contributions | |
Hait | -15.161 |
Athena | -15.045 |
Whale | -14.885 |
Shin | -14.744 |
shown | -14.521 |
Token | adden |
Token ID | 38014 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
️ | +2.614 |
ande | +2.465 |
FIELD | +2.343 |
ards | +2.249 |
LC | +2.179 |
Neg logit contributions | |
shown | -3.741 |
Hait | -3.717 |
Whale | -3.710 |
Athena | -3.581 |
Shin | -3.481 |
Token | � |
Token ID | 447 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
shown | +2.202 |
Hait | +2.144 |
Whale | +2.097 |
Athena | +2.029 |
Shin | +2.027 |
Neg logit contributions | |
️ | -2.560 |
ande | -2.393 |
conflic | -2.313 |
FIELD | -2.312 |
Scrib | -2.260 |
Token | � |
Token ID | 247 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
️ | +0.603 |
ande | +0.492 |
FIELD | +0.449 |
�� | +0.424 |
conflic | +0.414 |
Neg logit contributions | |
shown | -2.197 |
Hait | -2.168 |
Whale | -2.143 |
Athena | -2.096 |
Shin | -2.089 |
Token | s |
Token ID | 82 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
shown | +0.720 |
Hait | +0.700 |
Whale | +0.687 |
Athena | +0.663 |
Shin | +0.659 |
Neg logit contributions | |
️ | -0.825 |
ande | -0.767 |
FIELD | -0.742 |
conflic | -0.734 |
Scrib | -0.724 |
Token | ashing |
Token ID | 2140 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
️ | +2.310 |
ande | +2.190 |
FIELD | +2.043 |
Scrib | +2.038 |
ards | +2.036 |
Neg logit contributions | |
shown | -2.100 |
Hait | -2.068 |
Whale | -2.032 |
Athena | -1.970 |
Shin | -1.946 |
Token | � |
Token ID | 447 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
️ | +1.147 |
ande | +1.055 |
FIELD | +1.016 |
conflic | +1.002 |
Scrib | +0.992 |
Neg logit contributions | |
shown | -1.113 |
Hait | -1.074 |
Whale | -1.051 |
Athena | -1.021 |
Shin | -1.015 |
Token | � |
Token ID | 251 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
️ | +1.156 |
ande | +0.955 |
FIELD | +0.870 |
�� | +0.861 |
conflic | +0.845 |
Neg logit contributions | |
shown | -3.638 |
Hait | -3.580 |
Whale | -3.535 |
Athena | -3.463 |
Shin | -3.462 |
Token | rhetoric |
Token ID | 13214 |
Feature activation | -9.63e-02 |
Pos logit contributions | |
️ | +0.321 |
ande | +0.298 |
FIELD | +0.288 |
conflic | +0.284 |
Scrib | +0.281 |
Neg logit contributions | |
shown | -0.272 |
Hait | -0.265 |
Whale | -0.260 |
Athena | -0.251 |
Shin | -0.249 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
shown | +0.723 |
Hait | +0.704 |
Whale | +0.690 |
Athena | +0.664 |
Shin | +0.659 |
Neg logit contributions | |
️ | -0.926 |
ande | -0.864 |
FIELD | -0.838 |
conflic | -0.831 |
Scrib | -0.819 |
Token | Why |
Token ID | 4162 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
️ | +3.770 |
ande | +3.372 |
Scrib | +3.353 |
FIELD | +3.292 |
� | +3.268 |
Neg logit contributions | |
shown | -3.474 |
Hait | -3.304 |
Whale | -3.235 |
hur | -3.191 |
Athena | -3.156 |
Token | , |
Token ID | 11 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
️ | +9.316 |
ande | +8.293 |
prism | +8.242 |
Scrib | +7.981 |
� | +7.956 |
Neg logit contributions | |
shown | -11.125 |
Hait | -10.124 |
itime | -9.964 |
Whale | -9.935 |
hur | -9.887 |
Token | just |
Token ID | 655 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
️ | +3.265 |
ande | +3.032 |
Scrib | +2.939 |
prism | +2.911 |
FIELD | +2.884 |
Neg logit contributions | |
shown | -3.146 |
Hait | -2.973 |
Whale | -2.942 |
hur | -2.858 |
Athena | -2.830 |
Token | the |
Token ID | 262 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
️ | +0.554 |
ande | +0.514 |
FIELD | +0.491 |
Scrib | +0.487 |
conflic | +0.484 |
Neg logit contributions | |
shown | -0.499 |
Hait | -0.486 |
Whale | -0.475 |
Athena | -0.458 |
Shin | -0.456 |
Token | other |
Token ID | 584 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
shown | +2.523 |
Hait | +2.476 |
Whale | +2.439 |
Athena | +2.338 |
Shin | +2.333 |
Neg logit contributions | |
️ | -3.045 |
ande | -2.830 |
FIELD | -2.763 |
conflic | -2.729 |
�� | -2.659 |
Token | day |
Token ID | 1110 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
️ | +1.269 |
ande | +1.182 |
FIELD | +1.136 |
Scrib | +1.120 |
prism | +1.115 |
Neg logit contributions | |
shown | -0.978 |
Hait | -0.936 |
Whale | -0.921 |
Athena | -0.885 |
hur | -0.875 |
Token | | |
Token ID | 930 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
️ | +3.296 |
ande | +3.063 |
FIELD | +2.954 |
conflic | +2.948 |
Scrib | +2.890 |
Neg logit contributions | |
shown | -2.689 |
Hait | -2.616 |
Whale | -2.565 |
Athena | -2.453 |
Shin | -2.429 |
Token | Medline |
Token ID | 34582 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
️ | +3.051 |
Scrib | +2.502 |
FIELD | +2.479 |
ande | +2.456 |
prism | +2.350 |
Neg logit contributions | |
shown | -6.262 |
Hait | -6.083 |
Whale | -5.910 |
hur | -5.899 |
Shin | -5.702 |
Token | | |
Token ID | 930 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
️ | +3.110 |
ande | +2.906 |
FIELD | +2.814 |
conflic | +2.804 |
Scrib | +2.768 |
Neg logit contributions | |
shown | -2.146 |
Hait | -2.093 |
Whale | -2.036 |
Athena | -1.941 |
Shin | -1.921 |
Token | ISI |
Token ID | 22048 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
️ | +2.056 |
ande | +1.707 |
FIELD | +1.685 |
Scrib | +1.629 |
prism | +1.523 |
Neg logit contributions | |
shown | -5.035 |
Hait | -4.983 |
Whale | -4.899 |
hur | -4.814 |
Shin | -4.727 |
Token |
|
Token ID | 198 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
️ | +4.540 |
ande | +4.046 |
FIELD | +3.966 |
Scrib | +3.908 |
� | +3.849 |
Neg logit contributions | |
shown | -4.495 |
Hait | -4.439 |
Whale | -4.301 |
Athena | -4.133 |
hur | -4.117 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
️ | +5.615 |
FIELD | +4.906 |
ande | +4.804 |
Scrib | +4.775 |
LC | +4.710 |
Neg logit contributions | |
shown | -7.263 |
Whale | -7.219 |
Hait | -7.196 |
itime | -7.017 |
hur | -6.895 |
Token | P |
Token ID | 47 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
️ | +8.946 |
FIELD | +8.003 |
Rail | +7.676 |
LC | +7.573 |
ande | +7.512 |
Neg logit contributions | |
Whale | -11.648 |
Hait | -11.507 |
Athena | -10.999 |
shown | -10.876 |
Hai | -10.635 |
Token | el |
Token ID | 417 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
️ | +1.591 |
ande | +1.516 |
FIELD | +1.425 |
ards | +1.385 |
Scrib | +1.379 |
Neg logit contributions | |
shown | -1.777 |
Hait | -1.748 |
Whale | -1.726 |
Athena | -1.670 |
Shin | -1.650 |
Token | leg |
Token ID | 1455 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
️ | +0.863 |
ande | +0.806 |
FIELD | +0.764 |
conflic | +0.744 |
Scrib | +0.742 |
Neg logit contributions | |
shown | -0.967 |
Hait | -0.944 |
Whale | -0.930 |
Athena | -0.904 |
Shin | -0.894 |
Token | r |
Token ID | 81 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
shown | +1.826 |
Hait | +1.778 |
Whale | +1.746 |
Athena | +1.685 |
Shin | +1.675 |
Neg logit contributions | |
️ | -1.979 |
ande | -1.834 |
FIELD | -1.774 |
conflic | -1.756 |
Scrib | -1.728 |
Token | ini |
Token ID | 5362 |
Feature activation | -6.09e-03 |
Pos logit contributions | |
shown | +0.847 |
Hait | +0.832 |
Whale | +0.811 |
Athena | +0.784 |
Shin | +0.775 |
Neg logit contributions | |
️ | -1.012 |
ande | -0.949 |
FIELD | -0.910 |
conflic | -0.893 |
Scrib | -0.887 |
Token | Enter |
Token ID | 17469 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
️ | +1.153 |
ande | +1.048 |
FIELD | +1.026 |
Scrib | +0.985 |
LC | +0.959 |
Neg logit contributions | |
shown | -1.342 |
Hait | -1.331 |
Whale | -1.314 |
Athena | -1.264 |
Shin | -1.257 |
Token | 4 |
Token ID | 604 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
️ | +5.000 |
ande | +4.738 |
Scrib | +4.536 |
prism | +4.532 |
FIELD | +4.499 |
Neg logit contributions | |
shown | -4.217 |
Hait | -4.182 |
hur | -3.892 |
Whale | -3.880 |
Athena | -3.785 |
Token | different |
Token ID | 1180 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
️ | +0.364 |
ande | +0.337 |
FIELD | +0.326 |
conflic | +0.323 |
Scrib | +0.319 |
Neg logit contributions | |
shown | -0.333 |
Hait | -0.324 |
Whale | -0.316 |
Athena | -0.306 |
hur | -0.304 |
Token | portals |
Token ID | 42604 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
️ | +3.601 |
ande | +3.382 |
prism | +3.291 |
Scrib | +3.267 |
FIELD | +3.237 |
Neg logit contributions | |
shown | -3.275 |
Hait | -3.142 |
Whale | -3.025 |
hur | -3.018 |
Athena | -2.887 |
Token | without |
Token ID | 1231 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
️ | +1.878 |
ande | +1.741 |
FIELD | +1.680 |
prism | +1.659 |
Scrib | +1.657 |
Neg logit contributions | |
shown | -1.639 |
Hait | -1.603 |
Whale | -1.555 |
hur | -1.505 |
Athena | -1.491 |
Token | touching |
Token ID | 15241 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
️ | +3.039 |
ande | +2.861 |
Scrib | +2.776 |
FIELD | +2.754 |
prism | +2.743 |
Neg logit contributions | |
shown | -2.476 |
Hait | -2.356 |
Whale | -2.337 |
hur | -2.238 |
Athena | -2.194 |
Token | the |
Token ID | 262 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
️ | +9.282 |
ande | +8.558 |
prism | +8.536 |
Scrib | +8.431 |
FIELD | +8.344 |
Neg logit contributions | |
shown | -10.453 |
Hait | -9.916 |
Whale | -9.867 |
hur | -9.768 |
は | -9.757 |
Token | ground |
Token ID | 2323 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
️ | +3.456 |
ande | +3.174 |
prism | +3.138 |
Scrib | +3.070 |
FIELD | +3.057 |
Neg logit contributions | |
shown | -3.863 |
Hait | -3.725 |
Whale | -3.633 |
hur | -3.583 |
は | -3.497 |
Token | in |
Token ID | 287 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
️ | +1.848 |
ande | +1.706 |
FIELD | +1.654 |
Scrib | +1.624 |
prism | +1.614 |
Neg logit contributions | |
shown | -1.566 |
Hait | -1.532 |
Whale | -1.499 |
Athena | -1.435 |
hur | -1.426 |
Token | co |
Token ID | 763 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
️ | +6.176 |
ande | +5.824 |
prism | +5.683 |
Scrib | +5.608 |
conflic | +5.441 |
Neg logit contributions | |
shown | -7.308 |
Hait | -7.146 |
hur | -6.945 |
Whale | -6.779 |
Athena | -6.559 |
Token | - |
Token ID | 12 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
️ | +4.733 |
ande | +4.483 |
FIELD | +4.353 |
ards | +4.215 |
Scrib | +4.201 |
Neg logit contributions | |
Hait | -3.745 |
shown | -3.684 |
Whale | -3.663 |
Athena | -3.415 |
Howell | -3.403 |
Token | Scholar |
Token ID | 11713 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
shown | +0.747 |
Hait | +0.725 |
Whale | +0.713 |
Athena | +0.687 |
Shin | +0.682 |
Neg logit contributions | |
️ | -0.907 |
ande | -0.845 |
FIELD | -0.817 |
conflic | -0.812 |
Scrib | -0.796 |
Token | Crossref |
Token ID | 23613 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
shown | +0.118 |
Hait | +0.114 |
Whale | +0.111 |
Athena | +0.107 |
Shin | +0.106 |
Neg logit contributions | |
️ | -0.181 |
ande | -0.169 |
FIELD | -0.165 |
conflic | -0.163 |
Scrib | -0.161 |
Token | | |
Token ID | 930 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
️ | +3.156 |
ande | +2.944 |
FIELD | +2.846 |
conflic | +2.837 |
Scrib | +2.784 |
Neg logit contributions | |
shown | -2.391 |
Hait | -2.319 |
Whale | -2.276 |
Athena | -2.164 |
Shin | -2.146 |
Token | ISI |
Token ID | 22048 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
️ | +2.328 |
FIELD | +1.941 |
Scrib | +1.929 |
ande | +1.894 |
prism | +1.824 |
Neg logit contributions | |
shown | -4.588 |
Hait | -4.469 |
Whale | -4.358 |
hur | -4.342 |
Shin | -4.208 |
Token |
|
Token ID | 198 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
️ | +4.792 |
FIELD | +4.195 |
ande | +4.179 |
Scrib | +4.107 |
LC | +4.040 |
Neg logit contributions | |
shown | -5.344 |
Hait | -5.278 |
Whale | -5.161 |
hur | -4.977 |
itime | -4.938 |
Token |
|
Token ID | 198 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
️ | +4.933 |
FIELD | +4.348 |
ande | +4.308 |
Scrib | +4.225 |
LC | +4.154 |
Neg logit contributions | |
shown | -6.096 |
Whale | -6.047 |
Hait | -6.037 |
itime | -5.804 |
hur | -5.737 |
Token | P |
Token ID | 47 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
️ | +8.425 |
FIELD | +7.544 |
Rail | +7.275 |
ande | +7.167 |
LC | +7.125 |
Neg logit contributions | |
Whale | -11.618 |
Hait | -11.479 |
shown | -11.020 |
Athena | -10.963 |
Hai | -10.631 |
Token | iers |
Token ID | 3183 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
️ | +3.587 |
ande | +3.514 |
FIELD | +3.268 |
ards | +3.210 |
LC | +3.153 |
Neg logit contributions | |
shown | -3.984 |
Hait | -3.932 |
Whale | -3.915 |
Athena | -3.774 |
Shin | -3.698 |
Token | , |
Token ID | 11 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
shown | +1.227 |
Hait | +1.195 |
Whale | +1.173 |
Athena | +1.130 |
Shin | +1.123 |
Neg logit contributions | |
️ | -1.471 |
ande | -1.363 |
FIELD | -1.323 |
conflic | -1.315 |
Scrib | -1.290 |
Token | E |
Token ID | 412 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
️ | +0.357 |
ande | +0.329 |
FIELD | +0.323 |
Scrib | +0.321 |
prism | +0.311 |
Neg logit contributions | |
shown | -0.278 |
Hait | -0.265 |
Whale | -0.261 |
hur | -0.254 |
Athena | -0.249 |
Token | . |
Token ID | 13 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
️ | +0.293 |
ande | +0.273 |
FIELD | +0.264 |
conflic | +0.261 |
Scrib | +0.257 |
Neg logit contributions | |
shown | -0.252 |
Hait | -0.245 |
Whale | -0.241 |
Athena | -0.232 |
Shin | -0.231 |
Token | did |
Token ID | 750 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
shown | +1.621 |
Hait | +1.578 |
Whale | +1.549 |
Athena | +1.492 |
Shin | +1.483 |
Neg logit contributions | |
️ | -1.904 |
ande | -1.771 |
FIELD | -1.713 |
conflic | -1.694 |
Scrib | -1.671 |
Token | the |
Token ID | 262 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
shown | +2.837 |
Hait | +2.775 |
Whale | +2.713 |
Shin | +2.620 |
Athena | +2.609 |
Neg logit contributions | |
️ | -4.117 |
ande | -3.809 |
FIELD | -3.690 |
conflic | -3.658 |
Scrib | -3.648 |
Token | same |
Token ID | 976 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
shown | +1.953 |
Hait | +1.907 |
Whale | +1.875 |
Athena | +1.814 |
Shin | +1.805 |
Neg logit contributions | |
️ | -1.873 |
ande | -1.728 |
FIELD | -1.666 |
conflic | -1.644 |
Scrib | -1.620 |
Token | nearby |
Token ID | 6716 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
shown | +1.514 |
Hait | +1.474 |
Whale | +1.446 |
Athena | +1.389 |
Shin | +1.384 |
Neg logit contributions | |
️ | -1.952 |
ande | -1.822 |
FIELD | -1.766 |
conflic | -1.749 |
Scrib | -1.726 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
️ | +0.431 |
ande | +0.402 |
FIELD | +0.388 |
conflic | +0.382 |
Scrib | +0.379 |
Neg logit contributions | |
shown | -0.362 |
Hait | -0.352 |
Whale | -0.344 |
Athena | -0.332 |
hur | -0.328 |
Token | Ky |
Token ID | 11118 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
shown | +1.099 |
Hait | +1.065 |
Whale | +1.046 |
Athena | +1.006 |
Shin | +0.996 |
Neg logit contributions | |
️ | -1.356 |
ande | -1.267 |
FIELD | -1.225 |
conflic | -1.210 |
Scrib | -1.197 |
Token | odo |
Token ID | 24313 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
shown | +11.400 |
Hait | +11.100 |
hur | +10.901 |
Shin | +10.759 |
Whale | +10.738 |
Neg logit contributions | |
️ | -11.894 |
conflic | -11.661 |
PDATE | -11.045 |
FIELD | -10.693 |
� | -10.451 |
Token | News |
Token ID | 3000 |
Feature activation | -2.47e-04 |
Pos logit contributions | |
shown | +2.141 |
Hait | +2.081 |
Whale | +2.041 |
Shin | +1.959 |
Athena | +1.958 |
Neg logit contributions | |
️ | -3.017 |
ande | -2.816 |
FIELD | -2.734 |
conflic | -2.713 |
Scrib | -2.670 |
Token | Service |
Token ID | 4809 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
shown | +0.002 |
Hait | +0.002 |
Whale | +0.002 |
Athena | +0.002 |
Shin | +0.002 |
Neg logit contributions | |
️ | -0.002 |
ande | -0.002 |
FIELD | -0.002 |
conflic | -0.002 |
Scrib | -0.002 |
Token | reported |
Token ID | 2098 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
shown | +2.591 |
Hait | +2.534 |
Whale | +2.490 |
Athena | +2.419 |
Shin | +2.418 |
Neg logit contributions | |
️ | -2.158 |
ande | -1.971 |
FIELD | -1.897 |
conflic | -1.884 |
Scrib | -1.835 |
Token | . |
Token ID | 13 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
shown | +2.686 |
Hait | +2.624 |
Whale | +2.573 |
Shin | +2.472 |
Athena | +2.469 |
Neg logit contributions | |
️ | -3.670 |
ande | -3.427 |
FIELD | -3.349 |
conflic | -3.303 |
Scrib | -3.249 |
Token | : |
Token ID | 25 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
shown | +0.163 |
Hait | +0.159 |
Whale | +0.156 |
Athena | +0.149 |
Shin | +0.148 |
Neg logit contributions | |
️ | -0.200 |
ande | -0.186 |
FIELD | -0.181 |
conflic | -0.177 |
Scrib | -0.176 |
Token |
|
Token ID | 198 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
️ | +1.910 |
ande | +1.772 |
FIELD | +1.725 |
Scrib | +1.689 |
conflic | +1.668 |
Neg logit contributions | |
shown | -1.596 |
Hait | -1.564 |
Whale | -1.520 |
hur | -1.469 |
Athena | -1.446 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
️ | +0.517 |
ande | +0.477 |
FIELD | +0.465 |
Scrib | +0.451 |
ards | +0.445 |
Neg logit contributions | |
shown | -0.466 |
Hait | -0.457 |
Whale | -0.450 |
Athena | -0.430 |
hur | -0.427 |
Token | AS |
Token ID | 1921 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
️ | +1.099 |
ande | +1.016 |
FIELD | +0.992 |
ards | +0.933 |
Scrib | +0.932 |
Neg logit contributions | |
Hait | -1.223 |
shown | -1.221 |
Whale | -1.210 |
Athena | -1.154 |
Shin | -1.152 |
Token | Q |
Token ID | 48 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
shown | +0.742 |
Hait | +0.724 |
Whale | +0.712 |
Athena | +0.688 |
Shin | +0.684 |
Neg logit contributions | |
️ | -0.720 |
ande | -0.664 |
FIELD | -0.642 |
conflic | -0.631 |
Scrib | -0.624 |
Token | ( |
Token ID | 357 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
shown | +0.517 |
Hait | +0.503 |
Whale | +0.494 |
Athena | +0.477 |
Shin | +0.474 |
Neg logit contributions | |
️ | -0.590 |
ande | -0.549 |
FIELD | -0.530 |
conflic | -0.525 |
Scrib | -0.518 |
Token | The |
Token ID | 464 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
shown | +12.570 |
Athena | +11.398 |
Hait | +10.899 |
hur | +10.853 |
Whale | +10.689 |
Neg logit contributions | |
️ | -11.368 |
conflic | -10.229 |
�� | -10.119 |
ande | -10.013 |
PDATE | -9.931 |
Token | American |
Token ID | 1605 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
shown | +4.787 |
Hait | +4.629 |
Whale | +4.597 |
Athena | +4.575 |
Shin | +4.457 |
Neg logit contributions | |
️ | -5.795 |
ande | -5.380 |
conflic | -5.237 |
FIELD | -5.230 |
�� | -5.080 |
Token | Society |
Token ID | 7023 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
️ | +0.781 |
ande | +0.712 |
FIELD | +0.687 |
Scrib | +0.676 |
conflic | +0.664 |
Neg logit contributions | |
shown | -0.954 |
Hait | -0.934 |
Whale | -0.910 |
hur | -0.885 |
Athena | -0.872 |
Token | for |
Token ID | 329 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
️ | +1.654 |
ande | +1.534 |
FIELD | +1.479 |
conflic | +1.464 |
Scrib | +1.450 |
Neg logit contributions | |
shown | -1.481 |
Hait | -1.453 |
Whale | -1.417 |
Athena | -1.359 |
hur | -1.354 |
Token | Quality |
Token ID | 14156 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
️ | +0.635 |
ande | +0.593 |
FIELD | +0.573 |
Scrib | +0.565 |
conflic | +0.564 |
Neg logit contributions | |
shown | -0.546 |
Hait | -0.531 |
Whale | -0.519 |
hur | -0.500 |
Athena | -0.495 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
shown | +1.950 |
Hait | +1.878 |
Whale | +1.857 |
Athena | +1.784 |
Shin | +1.769 |
Neg logit contributions | |
️ | -2.654 |
ande | -2.483 |
FIELD | -2.413 |
conflic | -2.392 |
Scrib | -2.346 |
Token | output |
Token ID | 5072 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
️ | +0.942 |
ande | +0.868 |
FIELD | +0.832 |
Scrib | +0.829 |
conflic | +0.827 |
Neg logit contributions | |
shown | -0.919 |
Hait | -0.899 |
Whale | -0.877 |
hur | -0.853 |
Athena | -0.848 |
Token | of |
Token ID | 286 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
️ | +0.241 |
ande | +0.223 |
FIELD | +0.216 |
conflic | +0.212 |
Scrib | +0.212 |
Neg logit contributions | |
shown | -0.204 |
Hait | -0.200 |
Whale | -0.195 |
Athena | -0.188 |
hur | -0.188 |
Token | applying |
Token ID | 11524 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
shown | +2.184 |
Hait | +2.110 |
Whale | +2.079 |
Athena | +2.002 |
Shin | +1.986 |
Neg logit contributions | |
️ | -2.903 |
ande | -2.704 |
FIELD | -2.631 |
conflic | -2.599 |
Scrib | -2.557 |
Token | the |
Token ID | 262 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
shown | +1.313 |
Hait | +1.275 |
Whale | +1.250 |
Athena | +1.202 |
Shin | +1.193 |
Neg logit contributions | |
️ | -1.711 |
ande | -1.597 |
FIELD | -1.548 |
conflic | -1.531 |
Scrib | -1.512 |
Token | black |
Token ID | 2042 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
shown | +0.339 |
Hait | +0.330 |
Whale | +0.323 |
Athena | +0.312 |
hur | +0.311 |
Neg logit contributions | |
️ | -0.377 |
ande | -0.351 |
FIELD | -0.337 |
conflic | -0.335 |
Scrib | -0.332 |
Token | hat |
Token ID | 5183 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
shown | +7.098 |
Hait | +6.742 |
hur | +6.639 |
Whale | +6.435 |
Athena | +6.051 |
Neg logit contributions | |
️ | -15.566 |
PDATE | -14.437 |
conflic | -14.368 |
FIELD | -14.102 |
�� | -14.085 |
Token | operator |
Token ID | 10088 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
️ | +1.050 |
ande | +0.964 |
FIELD | +0.927 |
Scrib | +0.915 |
conflic | +0.915 |
Neg logit contributions | |
shown | -1.042 |
Hait | -1.022 |
Whale | -0.996 |
hur | -0.976 |
Athena | -0.968 |
Token | : |
Token ID | 25 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
shown | +1.413 |
Hait | +1.369 |
Whale | +1.345 |
Athena | +1.291 |
Shin | +1.282 |
Neg logit contributions | |
️ | -1.924 |
ande | -1.800 |
FIELD | -1.745 |
conflic | -1.731 |
Scrib | -1.705 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
shown | +1.591 |
Hait | +1.527 |
Whale | +1.510 |
Athena | +1.451 |
Shin | +1.440 |
Neg logit contributions | |
️ | -2.056 |
ande | -1.921 |
FIELD | -1.861 |
conflic | -1.835 |
Scrib | -1.810 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
shown | +1.076 |
Hait | +1.045 |
Whale | +1.025 |
Athena | +0.988 |
Shin | +0.982 |
Neg logit contributions | |
️ | -1.319 |
ande | -1.229 |
FIELD | -1.189 |
conflic | -1.182 |
Scrib | -1.161 |
Token | sides |
Token ID | 5389 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
️ | +2.630 |
ande | +2.444 |
FIELD | +2.359 |
conflic | +2.328 |
Scrib | +2.310 |
Neg logit contributions | |
shown | -2.320 |
Hait | -2.240 |
Whale | -2.189 |
hur | -2.128 |
Athena | -2.110 |
Token | of |
Token ID | 286 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
️ | +3.962 |
ande | +3.622 |
FIELD | +3.486 |
conflic | +3.422 |
prism | +3.390 |
Neg logit contributions | |
shown | -3.928 |
Hait | -3.837 |
Whale | -3.736 |
Athena | -3.636 |
hur | -3.620 |
Token | the |
Token ID | 262 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
️ | +6.132 |
ande | +5.765 |
FIELD | +5.475 |
conflic | +5.469 |
prism | +5.441 |
Neg logit contributions | |
shown | -5.787 |
Hait | -5.606 |
Whale | -5.395 |
hur | -5.301 |
Athena | -5.237 |
Token | map |
Token ID | 3975 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
️ | +4.438 |
ande | +3.984 |
conflic | +3.890 |
prism | +3.880 |
FIELD | +3.842 |
Neg logit contributions | |
shown | -6.027 |
Hait | -5.831 |
Whale | -5.717 |
Athena | -5.574 |
hur | -5.573 |
Token | ? |
Token ID | 30 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
️ | +3.547 |
ande | +3.268 |
FIELD | +3.152 |
conflic | +3.071 |
prism | +3.067 |
Neg logit contributions | |
shown | -3.611 |
Hait | -3.552 |
Whale | -3.463 |
Athena | -3.364 |
hur | -3.342 |
Token | Y |
Token ID | 575 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
shown | +0.215 |
Hait | +0.209 |
Whale | +0.205 |
Athena | +0.197 |
Shin | +0.196 |
Neg logit contributions | |
️ | -0.266 |
ande | -0.247 |
FIELD | -0.239 |
conflic | -0.236 |
Scrib | -0.234 |
Token | up |
Token ID | 929 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
shown | +11.038 |
hur | +10.770 |
Whale | +10.726 |
Athena | +10.583 |
Hait | +10.483 |
Neg logit contributions | |
️ | -10.631 |
conflic | -9.937 |
�� | -9.551 |
Scrib | -9.298 |
FIELD | -9.289 |
Token | , |
Token ID | 11 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
️ | +1.183 |
ande | +1.101 |
FIELD | +1.064 |
conflic | +1.053 |
Scrib | +1.039 |
Neg logit contributions | |
shown | -0.936 |
Hait | -0.908 |
Whale | -0.888 |
Athena | -0.853 |
Shin | -0.848 |
Token | it |
Token ID | 340 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
️ | +0.262 |
ande | +0.242 |
FIELD | +0.235 |
conflic | +0.233 |
Scrib | +0.230 |
Neg logit contributions | |
shown | -0.224 |
Hait | -0.217 |
Whale | -0.213 |
Athena | -0.205 |
Shin | -0.204 |
Token | � |
Token ID | 447 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
shown | +2.189 |
Hait | +2.127 |
Whale | +2.088 |
Athena | +2.015 |
hur | +2.005 |
Neg logit contributions | |
️ | -2.643 |
ande | -2.482 |
FIELD | -2.421 |
conflic | -2.369 |
�� | -2.346 |
Token | � |
Token ID | 247 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
shown | +1.428 |
Hait | +1.403 |
Whale | +1.387 |
Athena | +1.359 |
Shin | +1.352 |
Neg logit contributions | |
️ | -0.445 |
ande | -0.378 |
FIELD | -0.347 |
conflic | -0.342 |
Scrib | -0.326 |
Token | of |
Token ID | 286 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
️ | +0.851 |
ande | +0.785 |
FIELD | +0.763 |
Scrib | +0.741 |
prism | +0.735 |
Neg logit contributions | |
shown | -0.769 |
Hait | -0.756 |
Whale | -0.742 |
Athena | -0.713 |
Shin | -0.708 |
Token | this |
Token ID | 428 |
Feature activation | +5.31e-03 |
Pos logit contributions | |
shown | +0.090 |
Hait | +0.087 |
Whale | +0.086 |
Athena | +0.082 |
Shin | +0.082 |
Neg logit contributions | |
️ | -0.103 |
ande | -0.096 |
FIELD | -0.093 |
conflic | -0.092 |
Scrib | -0.091 |
Token | dataset |
Token ID | 27039 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
️ | +0.048 |
ande | +0.044 |
FIELD | +0.043 |
conflic | +0.042 |
Scrib | +0.042 |
Neg logit contributions | |
shown | -0.043 |
Hait | -0.042 |
Whale | -0.041 |
Athena | -0.040 |
Shin | -0.039 |
Token | ), |
Token ID | 828 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
shown | +0.604 |
Hait | +0.585 |
Whale | +0.573 |
Athena | +0.548 |
Shin | +0.544 |
Neg logit contributions | |
️ | -0.917 |
ande | -0.860 |
FIELD | -0.835 |
conflic | -0.826 |
Scrib | -0.817 |
Token | a |
Token ID | 257 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
shown | +1.583 |
Hait | +1.538 |
Whale | +1.511 |
Athena | +1.455 |
Shin | +1.445 |
Neg logit contributions | |
️ | -1.986 |
ande | -1.851 |
FIELD | -1.794 |
conflic | -1.773 |
Scrib | -1.745 |
Token | black |
Token ID | 2042 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
shown | +0.902 |
Hait | +0.879 |
Whale | +0.863 |
Athena | +0.833 |
Shin | +0.826 |
Neg logit contributions | |
️ | -1.003 |
ande | -0.932 |
FIELD | -0.900 |
conflic | -0.890 |
Scrib | -0.879 |
Token | hat |
Token ID | 5183 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
shown | +5.570 |
Hait | +5.265 |
Whale | +5.095 |
hur | +5.095 |
Shin | +4.652 |
Neg logit contributions | |
️ | -17.018 |
Scrib | -15.459 |
FIELD | -15.441 |
ande | -15.402 |
�� | -15.254 |
Token | operation |
Token ID | 4905 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
️ | +0.809 |
ande | +0.750 |
FIELD | +0.723 |
conflic | +0.716 |
Scrib | +0.712 |
Neg logit contributions | |
shown | -0.690 |
Hait | -0.677 |
Whale | -0.657 |
hur | -0.639 |
Athena | -0.637 |
Token | is |
Token ID | 318 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
shown | +3.320 |
Hait | +3.195 |
Whale | +3.177 |
Athena | +3.043 |
Shin | +3.040 |
Neg logit contributions | |
️ | -4.002 |
ande | -3.727 |
FIELD | -3.640 |
conflic | -3.639 |
�� | -3.541 |
Token | appropriate |
Token ID | 5035 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
shown | +2.514 |
Hait | +2.451 |
Whale | +2.417 |
Athena | +2.347 |
Shin | +2.334 |
Neg logit contributions | |
️ | -2.016 |
ande | -1.845 |
FIELD | -1.774 |
conflic | -1.756 |
Scrib | -1.719 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
shown | +1.432 |
Hait | +1.388 |
Whale | +1.362 |
Athena | +1.312 |
Shin | +1.302 |
Neg logit contributions | |
️ | -1.866 |
ande | -1.743 |
FIELD | -1.689 |
conflic | -1.678 |
Scrib | -1.649 |
Token | 17 |
Token ID | 1596 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
️ | +1.992 |
ande | +1.838 |
FIELD | +1.778 |
Scrib | +1.758 |
conflic | +1.758 |
Neg logit contributions | |
shown | -1.849 |
Hait | -1.811 |
Whale | -1.766 |
Athena | -1.698 |
hur | -1.696 |
Token | - |
Token ID | 12 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
shown | +1.534 |
Hait | +1.482 |
Whale | +1.456 |
Athena | +1.389 |
Shin | +1.384 |
Neg logit contributions | |
️ | -2.858 |
ande | -2.693 |
FIELD | -2.625 |
conflic | -2.609 |
Scrib | -2.574 |
Token | 40 |
Token ID | 1821 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
shown | +5.138 |
Hait | +4.693 |
Whale | +4.584 |
Shin | +4.516 |
hur | +4.440 |
Neg logit contributions | |
️ | -7.669 |
conflic | -7.472 |
PDATE | -7.192 |
ande | -7.079 |
�� | -6.953 |
Token | or |
Token ID | 393 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
️ | +2.649 |
ande | +2.440 |
FIELD | +2.362 |
prism | +2.337 |
conflic | +2.336 |
Neg logit contributions | |
shown | -2.139 |
Hait | -2.079 |
Whale | -2.040 |
Athena | -1.936 |
hur | -1.917 |
Token | 16 |
Token ID | 1467 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
shown | +1.024 |
Hait | +0.991 |
Whale | +0.976 |
Athena | +0.940 |
Shin | +0.937 |
Neg logit contributions | |
️ | -1.220 |
ande | -1.137 |
FIELD | -1.100 |
conflic | -1.084 |
Scrib | -1.073 |
Token | - |
Token ID | 12 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
shown | +1.391 |
Hait | +1.339 |
Whale | +1.313 |
Athena | +1.257 |
Shin | +1.253 |
Neg logit contributions | |
️ | -2.574 |
ande | -2.430 |
conflic | -2.409 |
FIELD | -2.355 |
�� | -2.330 |
Token | 35 |
Token ID | 2327 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
shown | +7.424 |
hur | +6.793 |
Hait | +6.606 |
Brady | +6.555 |
mph | +6.348 |
Neg logit contributions | |
conflic | -15.956 |
PDATE | -15.725 |
️ | -14.962 |
�� | -14.332 |
veter | -14.119 |
Token | f |
Token ID | 277 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
️ | +4.973 |
prism | +4.473 |
ande | +4.469 |
FIELD | +4.400 |
conflic | +4.299 |
Neg logit contributions | |
shown | -4.636 |
Hait | -4.511 |
Whale | -4.422 |
hur | -4.198 |
Athena | -4.186 |
Token | / |
Token ID | 14 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
shown | +0.925 |
Hait | +0.863 |
Whale | +0.838 |
Athena | +0.784 |
Shin | +0.782 |
Neg logit contributions | |
️ | -2.725 |
ande | -2.599 |
conflic | -2.589 |
FIELD | -2.531 |
�� | -2.506 |
Token | 2 |
Token ID | 17 |
Feature activation | +9.84e-03 |
Pos logit contributions | |
shown | +4.271 |
Hait | +3.955 |
Whale | +3.862 |
Shin | +3.790 |
hur | +3.770 |
Neg logit contributions | |
️ | -5.723 |
conflic | -5.673 |
ande | -5.463 |
PDATE | -5.451 |
�� | -5.304 |
Token | . |
Token ID | 13 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
️ | +0.093 |
ande | +0.086 |
FIELD | +0.083 |
conflic | +0.082 |
Scrib | +0.081 |
Neg logit contributions | |
shown | -0.076 |
Hait | -0.074 |
Whale | -0.073 |
Athena | -0.070 |
Shin | -0.070 |
Token | it |
Token ID | 340 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
️ | +2.064 |
ande | +1.907 |
FIELD | +1.841 |
Scrib | +1.837 |
conflic | +1.813 |
Neg logit contributions | |
shown | -1.602 |
Hait | -1.573 |
Whale | -1.506 |
hur | -1.450 |
Athena | -1.439 |
Token | as |
Token ID | 355 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
️ | +0.713 |
ande | +0.662 |
FIELD | +0.639 |
conflic | +0.629 |
Scrib | +0.626 |
Neg logit contributions | |
shown | -0.530 |
Hait | -0.519 |
Whale | -0.504 |
Athena | -0.484 |
Shin | -0.479 |
Token | a |
Token ID | 257 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
️ | +1.191 |
ande | +1.109 |
FIELD | +1.074 |
conflic | +1.060 |
Scrib | +1.054 |
Neg logit contributions | |
shown | -0.927 |
Hait | -0.909 |
Whale | -0.883 |
Athena | -0.844 |
Shin | -0.841 |
Token | clock |
Token ID | 8801 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
️ | +1.718 |
ande | +1.582 |
FIELD | +1.532 |
conflic | +1.516 |
Scrib | +1.514 |
Neg logit contributions | |
shown | -1.486 |
Hait | -1.453 |
Whale | -1.405 |
Athena | -1.360 |
hur | -1.347 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
️ | +3.443 |
ande | +3.176 |
FIELD | +3.059 |
prism | +3.012 |
Scrib | +2.993 |
Neg logit contributions | |
Hait | -2.953 |
shown | -2.934 |
Whale | -2.807 |
Athena | -2.703 |
Shin | -2.681 |
Token | Y |
Token ID | 575 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
️ | +0.293 |
ande | +0.270 |
FIELD | +0.263 |
Scrib | +0.259 |
conflic | +0.255 |
Neg logit contributions | |
shown | -0.225 |
Hait | -0.219 |
Whale | -0.213 |
Athena | -0.205 |
hur | -0.204 |
Token | up |
Token ID | 929 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
shown | +10.619 |
Whale | +10.281 |
hur | +10.183 |
Hait | +10.051 |
Athena | +10.017 |
Neg logit contributions | |
️ | -10.428 |
conflic | -9.936 |
�� | -9.574 |
FIELD | -9.323 |
ande | -9.075 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
️ | +0.965 |
ande | +0.894 |
FIELD | +0.865 |
conflic | +0.851 |
Scrib | +0.847 |
Neg logit contributions | |
shown | -0.778 |
Hait | -0.755 |
Whale | -0.737 |
Athena | -0.708 |
Shin | -0.703 |
Token | the |
Token ID | 262 |
Feature activation | +9.40e-02 |
Pos logit contributions | |
shown | +1.071 |
Hait | +1.041 |
Whale | +1.020 |
Athena | +0.982 |
Shin | +0.976 |
Neg logit contributions | |
️ | -1.314 |
ande | -1.222 |
FIELD | -1.183 |
conflic | -1.169 |
Scrib | -1.157 |
Token | Rebel |
Token ID | 24551 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
️ | +0.862 |
ande | +0.791 |
FIELD | +0.762 |
Scrib | +0.760 |
conflic | +0.755 |
Neg logit contributions | |
shown | -0.759 |
Hait | -0.736 |
Whale | -0.713 |
hur | -0.690 |
Athena | -0.685 |
Token | Alliance |
Token ID | 10302 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
️ | +2.082 |
ande | +1.912 |
FIELD | +1.857 |
Scrib | +1.843 |
conflic | +1.831 |
Neg logit contributions | |
shown | -1.862 |
Hait | -1.814 |
Whale | -1.741 |
hur | -1.695 |
Athena | -1.669 |
Token | kids |
Token ID | 3988 |
Feature activation | +3.69e-03 |
Pos logit contributions | |
shown | +1.330 |
Hait | +1.299 |
Whale | +1.273 |
Athena | +1.228 |
Shin | +1.220 |
Neg logit contributions | |
️ | -1.727 |
ande | -1.613 |
FIELD | -1.564 |
conflic | -1.552 |
Scrib | -1.525 |
Token | , |
Token ID | 11 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
️ | +0.035 |
ande | +0.032 |
FIELD | +0.031 |
conflic | +0.031 |
Scrib | +0.031 |
Neg logit contributions | |
shown | -0.029 |
Hait | -0.028 |
Whale | -0.027 |
Athena | -0.026 |
Shin | -0.026 |
Token | � |
Token ID | 447 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
️ | +0.404 |
ande | +0.374 |
FIELD | +0.360 |
conflic | +0.355 |
Scrib | +0.353 |
Neg logit contributions | |
shown | -0.332 |
Hait | -0.321 |
Whale | -0.316 |
Athena | -0.303 |
Shin | -0.300 |
Token | � |
Token ID | 251 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
️ | +0.078 |
ande | +0.067 |
FIELD | +0.063 |
conflic | +0.061 |
Scrib | +0.060 |
Neg logit contributions | |
shown | -0.195 |
Hait | -0.192 |
Whale | -0.190 |
Athena | -0.185 |
Shin | -0.184 |
Token | U |
Token ID | 471 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
shown | +2.841 |
Hait | +2.772 |
Whale | +2.709 |
Athena | +2.612 |
Shin | +2.611 |
Neg logit contributions | |
️ | -3.786 |
ande | -3.566 |
FIELD | -3.486 |
conflic | -3.481 |
Scrib | -3.392 |
Token | em |
Token ID | 368 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
shown | +6.133 |
Hait | +5.735 |
hur | +5.636 |
Shin | +5.473 |
Whale | +5.446 |
Neg logit contributions | |
conflic | -7.746 |
️ | -7.686 |
PDATE | -7.419 |
ande | -7.063 |
�� | -7.034 |
Token | atsu |
Token ID | 19231 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
shown | +7.323 |
hur | +6.830 |
Shin | +6.419 |
Whale | +6.324 |
Hait | +6.308 |
Neg logit contributions | |
PDATE | -14.964 |
conflic | -14.798 |
️ | -13.999 |
Scrib | -13.402 |
�� | -13.379 |
Token | said |
Token ID | 531 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
shown | +2.251 |
Hait | +2.200 |
Whale | +2.147 |
Shin | +2.073 |
Athena | +2.056 |
Neg logit contributions | |
️ | -3.113 |
ande | -2.933 |
conflic | -2.881 |
FIELD | -2.855 |
Scrib | -2.801 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
shown | +1.888 |
Hait | +1.853 |
Whale | +1.814 |
Shin | +1.748 |
Athena | +1.745 |
Neg logit contributions | |
️ | -2.528 |
ande | -2.371 |
FIELD | -2.306 |
conflic | -2.302 |
Scrib | -2.245 |
Token | � |
Token ID | 564 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
shown | +1.128 |
Hait | +1.099 |
Whale | +1.080 |
Athena | +1.043 |
Shin | +1.037 |
Neg logit contributions | |
️ | -1.249 |
ande | -1.163 |
FIELD | -1.123 |
conflic | -1.116 |
Scrib | -1.092 |
Token | � |
Token ID | 250 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
shown | +2.973 |
Hait | +2.903 |
Whale | +2.878 |
Athena | +2.806 |
Shin | +2.796 |
Neg logit contributions | |
️ | -1.376 |
ande | -1.260 |
FIELD | -1.192 |
conflic | -1.173 |
Scrib | -1.144 |
Token | edge |
Token ID | 5743 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
shown | +2.474 |
Hait | +2.369 |
Whale | +2.366 |
Athena | +2.259 |
Shin | +2.257 |
Neg logit contributions | |
️ | -4.829 |
conflic | -4.528 |
ande | -4.502 |
FIELD | -4.425 |
Scrib | -4.374 |
Token | of |
Token ID | 286 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
️ | +2.232 |
ande | +2.019 |
FIELD | +1.979 |
Scrib | +1.915 |
prism | +1.900 |
Neg logit contributions | |
shown | -2.150 |
Hait | -2.127 |
Whale | -2.068 |
hur | -1.994 |
Athena | -1.982 |
Token | the |
Token ID | 262 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
️ | +3.122 |
ande | +2.827 |
FIELD | +2.748 |
Scrib | +2.727 |
prism | +2.685 |
Neg logit contributions | |
shown | -2.874 |
Hait | -2.811 |
Whale | -2.693 |
hur | -2.663 |
Athena | -2.591 |
Token | Universe |
Token ID | 11950 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
️ | +1.960 |
ande | +1.718 |
FIELD | +1.634 |
Scrib | +1.593 |
prism | +1.574 |
Neg logit contributions | |
shown | -3.338 |
Hait | -3.298 |
Whale | -3.152 |
Athena | -3.117 |
hur | -3.111 |
Token | ? |
Token ID | 30 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
️ | +2.366 |
ande | +2.160 |
FIELD | +2.104 |
Scrib | +2.032 |
ards | +2.018 |
Neg logit contributions | |
shown | -2.870 |
Hait | -2.803 |
Whale | -2.737 |
Athena | -2.632 |
Shin | -2.623 |
Token | Y |
Token ID | 575 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
shown | +1.279 |
Hait | +1.245 |
Whale | +1.221 |
Athena | +1.175 |
Shin | +1.167 |
Neg logit contributions | |
️ | -1.701 |
ande | -1.591 |
FIELD | -1.543 |
conflic | -1.527 |
Scrib | -1.503 |
Token | una |
Token ID | 9613 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
shown | +10.992 |
hur | +10.809 |
Hait | +10.710 |
Whale | +10.624 |
Athena | +10.523 |
Neg logit contributions | |
️ | -9.200 |
conflic | -8.709 |
�� | -8.287 |
FIELD | -8.273 |
PDATE | -8.055 |
Token | : |
Token ID | 25 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
shown | +1.513 |
Hait | +1.479 |
Whale | +1.448 |
Athena | +1.395 |
Shin | +1.389 |
Neg logit contributions | |
️ | -2.106 |
ande | -1.963 |
FIELD | -1.914 |
conflic | -1.901 |
Scrib | -1.867 |
Token | I |
Token ID | 314 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
️ | +1.211 |
ande | +1.119 |
FIELD | +1.080 |
Scrib | +1.074 |
conflic | +1.060 |
Neg logit contributions | |
shown | -0.940 |
Hait | -0.895 |
Whale | -0.881 |
Athena | -0.840 |
hur | -0.838 |
Token | know |
Token ID | 760 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
️ | +0.381 |
ande | +0.350 |
FIELD | +0.337 |
conflic | +0.331 |
Scrib | +0.329 |
Neg logit contributions | |
shown | -0.355 |
Hait | -0.345 |
Whale | -0.339 |
Athena | -0.327 |
Shin | -0.325 |
Token | , |
Token ID | 11 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
shown | +0.704 |
Hait | +0.681 |
Whale | +0.669 |
Athena | +0.642 |
Shin | +0.638 |
Neg logit contributions | |
️ | -0.870 |
ande | -0.808 |
FIELD | -0.783 |
conflic | -0.772 |
Scrib | -0.767 |
Token | More |
Token ID | 3125 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
shown | +1.633 |
Hait | +1.596 |
Whale | +1.575 |
Athena | +1.493 |
Shin | +1.492 |
Neg logit contributions | |
️ | -3.151 |
ande | -2.998 |
conflic | -2.992 |
FIELD | -2.912 |
�� | -2.870 |
Token | About |
Token ID | 7994 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
shown | +1.390 |
Hait | +1.356 |
Whale | +1.331 |
Athena | +1.280 |
Shin | +1.273 |
Neg logit contributions | |
️ | -1.838 |
ande | -1.721 |
FIELD | -1.671 |
conflic | -1.664 |
Scrib | -1.622 |
Token | Sw |
Token ID | 2451 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
️ | +2.281 |
ande | +2.094 |
Scrib | +2.016 |
FIELD | +1.943 |
prism | +1.906 |
Neg logit contributions | |
shown | -2.895 |
Hait | -2.710 |
hur | -2.689 |
Whale | -2.682 |
Athena | -2.604 |
Token | amin |
Token ID | 5669 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
shown | +1.411 |
Hait | +1.340 |
Whale | +1.276 |
Athena | +1.193 |
Shin | +1.192 |
Neg logit contributions | |
️ | -4.365 |
conflic | -4.118 |
ande | -4.102 |
FIELD | -4.055 |
�� | -3.991 |
Token | ar |
Token ID | 283 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
️ | +1.945 |
ande | +1.863 |
FIELD | +1.782 |
ards | +1.773 |
Scrib | +1.757 |
Neg logit contributions | |
shown | -1.182 |
Hait | -1.154 |
Whale | -1.141 |
Athena | -1.069 |
Shin | -1.038 |
Token | ayan |
Token ID | 22931 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
shown | +2.186 |
Hait | +2.145 |
Whale | +2.118 |
Athena | +2.065 |
Shin | +2.056 |
Neg logit contributions | |
️ | -1.129 |
ande | -1.003 |
FIELD | -0.949 |
conflic | -0.931 |
Scrib | -0.910 |
Token | A |
Token ID | 317 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Hait | +5.635 |
Shin | +5.627 |
Athena | +5.536 |
Whale | +5.509 |
Hai | +5.330 |
Neg logit contributions | |
conflic | -15.285 |
PDATE | -15.014 |
️ | -14.859 |
ande | -14.008 |
FIELD | -13.992 |
Token | ks |
Token ID | 591 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
️ | +0.831 |
ande | +0.730 |
FIELD | +0.683 |
ards | +0.657 |
Scrib | +0.650 |
Neg logit contributions | |
shown | -1.988 |
Hait | -1.967 |
Whale | -1.943 |
Athena | -1.882 |
hur | -1.868 |
Token | hard |
Token ID | 10424 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
shown | +2.383 |
Hait | +2.233 |
hur | +2.179 |
Whale | +2.131 |
Shin | +2.086 |
Neg logit contributions | |
️ | -5.312 |
conflic | -5.120 |
PDATE | -4.915 |
ande | -4.885 |
FIELD | -4.858 |
Token | ham |
Token ID | 2763 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
shown | +2.328 |
Hait | +2.276 |
Whale | +2.243 |
Athena | +2.195 |
hur | +2.193 |
Neg logit contributions | |
️ | -1.096 |
ande | -0.961 |
conflic | -0.928 |
FIELD | -0.912 |
Scrib | -0.874 |
Token | Temple |
Token ID | 10857 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
shown | +3.820 |
Hait | +3.762 |
Whale | +3.684 |
Shin | +3.627 |
Athena | +3.619 |
Neg logit contributions | |
️ | -5.637 |
conflic | -5.462 |
ande | -5.364 |
PDATE | -5.238 |
FIELD | -5.205 |
Token | at |
Token ID | 379 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Hait | +4.719 |
shown | +4.702 |
Whale | +4.598 |
Shin | +4.488 |
Athena | +4.427 |
Neg logit contributions | |
️ | -6.088 |
ande | -5.662 |
conflic | -5.597 |
�� | -5.509 |
FIELD | -5.458 |
Token | Tokyo |
Token ID | 11790 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
shown | +4.062 |
Hait | +3.968 |
Whale | +3.954 |
Shin | +3.844 |
Athena | +3.759 |
Neg logit contributions | |
️ | -5.635 |
ande | -5.218 |
FIELD | -5.100 |
conflic | -5.064 |
�� | -4.945 |
Token | 's |
Token ID | 338 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
shown | +3.640 |
Whale | +3.606 |
Hait | +3.604 |
Shin | +3.467 |
Athena | +3.455 |
Neg logit contributions | |
️ | -5.373 |
ande | -5.019 |
FIELD | -4.873 |
conflic | -4.837 |
�� | -4.732 |
Token | Shin |
Token ID | 11466 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Shin | +7.668 |
Whale | +7.499 |
Hait | +7.364 |
shown | +7.204 |
Athena | +7.190 |
Neg logit contributions | |
️ | -10.193 |
ande | -9.452 |
FIELD | -9.310 |
conflic | -9.198 |
PDATE | -8.961 |
Token | ag |
Token ID | 363 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
shown | +8.993 |
Shin | +8.973 |
Hait | +8.969 |
Whale | +8.711 |
Athena | +8.477 |
Neg logit contributions | |
️ | -10.412 |
conflic | -9.656 |
PDATE | -9.260 |
FIELD | -9.255 |
ande | -9.047 |
Token | awa |
Token ID | 6909 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
shown | +1.162 |
Hait | +1.125 |
Whale | +1.104 |
Athena | +1.057 |
Shin | +1.047 |
Neg logit contributions | |
️ | -1.683 |
ande | -1.582 |
FIELD | -1.527 |
conflic | -1.511 |
Scrib | -1.494 |
Token | station |
Token ID | 4429 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Shin | +9.094 |
Whale | +8.845 |
shown | +8.695 |
Hait | +8.624 |
Athena | +8.397 |
Neg logit contributions | |
️ | -11.606 |
conflic | -10.809 |
FIELD | -10.706 |
ande | -10.689 |
PDATE | -10.489 |
Token | on |
Token ID | 319 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
shown | +2.614 |
Hait | +2.536 |
Whale | +2.505 |
Shin | +2.404 |
Athena | +2.402 |
Neg logit contributions | |
️ | -3.425 |
ande | -3.198 |
FIELD | -3.105 |
conflic | -3.093 |
Scrib | -3.023 |
Token | April |
Token ID | 3035 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
shown | +3.820 |
Hait | +3.805 |
Whale | +3.753 |
Shin | +3.640 |
Athena | +3.604 |
Neg logit contributions | |
️ | -6.104 |
ande | -5.680 |
conflic | -5.580 |
FIELD | -5.539 |
�� | -5.406 |
Token | 9 |
Token ID | 860 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
shown | +0.929 |
Hait | +0.901 |
Whale | +0.884 |
Athena | +0.848 |
Shin | +0.840 |
Neg logit contributions | |
️ | -1.206 |
ande | -1.124 |
FIELD | -1.091 |
Scrib | -1.068 |
conflic | -1.067 |
Token | , |
Token ID | 11 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
shown | +2.370 |
Hait | +2.287 |
Whale | +2.281 |
Shin | +2.177 |
Athena | +2.172 |
Neg logit contributions | |
️ | -3.337 |
ande | -3.144 |
FIELD | -3.073 |
conflic | -3.047 |
Scrib | -2.982 |
Token | mm |
Token ID | 3020 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
shown | +1.524 |
Hait | +1.461 |
Whale | +1.427 |
Athena | +1.369 |
Shin | +1.357 |
Neg logit contributions | |
️ | -2.839 |
ande | -2.681 |
FIELD | -2.603 |
conflic | -2.595 |
Scrib | -2.550 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
shown | +0.535 |
Hait | +0.519 |
Whale | +0.510 |
Athena | +0.490 |
Shin | +0.487 |
Neg logit contributions | |
️ | -0.691 |
ande | -0.646 |
FIELD | -0.625 |
conflic | -0.619 |
Scrib | -0.610 |
Token | With |
Token ID | 2080 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
️ | +0.486 |
ande | +0.448 |
FIELD | +0.436 |
Scrib | +0.429 |
conflic | +0.424 |
Neg logit contributions | |
shown | -0.395 |
Hait | -0.384 |
Whale | -0.376 |
Athena | -0.362 |
hur | -0.361 |
Token | the |
Token ID | 262 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
️ | +0.385 |
ande | +0.359 |
FIELD | +0.347 |
conflic | +0.342 |
Scrib | +0.339 |
Neg logit contributions | |
shown | -0.320 |
Hait | -0.312 |
Whale | -0.306 |
Athena | -0.294 |
Shin | -0.291 |
Token | 16 |
Token ID | 1467 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
shown | +1.422 |
Hait | +1.383 |
Whale | +1.358 |
Athena | +1.309 |
Shin | +1.302 |
Neg logit contributions | |
️ | -1.723 |
ande | -1.604 |
FIELD | -1.552 |
conflic | -1.537 |
Scrib | -1.513 |
Token | - |
Token ID | 12 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
shown | +2.159 |
Hait | +2.080 |
Whale | +2.050 |
Shin | +1.974 |
Athena | +1.966 |
Neg logit contributions | |
️ | -4.176 |
ande | -3.932 |
FIELD | -3.825 |
conflic | -3.818 |
Scrib | -3.765 |
Token | 35 |
Token ID | 2327 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
shown | +7.709 |
hur | +7.017 |
Hait | +6.975 |
Shin | +6.783 |
Brady | +6.667 |
Neg logit contributions | |
️ | -13.433 |
conflic | -13.385 |
PDATE | -13.179 |
�� | -12.375 |
Scrib | -12.306 |
Token | f |
Token ID | 277 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
️ | +0.717 |
ande | +0.667 |
FIELD | +0.647 |
conflic | +0.639 |
Scrib | +0.632 |
Neg logit contributions | |
shown | -0.564 |
Hait | -0.548 |
Whale | -0.538 |
Athena | -0.514 |
Shin | -0.508 |
Token | / |
Token ID | 14 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
shown | +1.656 |
Hait | +1.495 |
Whale | +1.460 |
Shin | +1.380 |
Athena | +1.363 |
Neg logit contributions | |
️ | -5.434 |
conflic | -5.344 |
ande | -5.199 |
PDATE | -5.115 |
�� | -5.069 |
Token | 4 |
Token ID | 19 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
shown | +4.687 |
Hait | +4.369 |
Whale | +4.274 |
Shin | +4.212 |
hur | +4.168 |
Neg logit contributions | |
️ | -6.466 |
ande | -6.124 |
conflic | -5.895 |
Scrib | -5.838 |
FIELD | -5.833 |
Token | even |
Token ID | 772 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
shown | +2.570 |
Hait | +2.503 |
Whale | +2.465 |
Shin | +2.406 |
Athena | +2.401 |
Neg logit contributions | |
️ | -2.944 |
ande | -2.757 |
FIELD | -2.636 |
conflic | -2.633 |
Scrib | -2.581 |
Token | 27 |
Token ID | 2681 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
shown | +0.160 |
Hait | +0.155 |
Whale | +0.152 |
hur | +0.146 |
Athena | +0.146 |
Neg logit contributions | |
️ | -0.192 |
ande | -0.178 |
FIELD | -0.173 |
Scrib | -0.170 |
prism | -0.167 |
Token | . |
Token ID | 13 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
️ | +0.238 |
ande | +0.221 |
FIELD | +0.214 |
conflic | +0.210 |
Scrib | +0.209 |
Neg logit contributions | |
shown | -0.190 |
Hait | -0.186 |
Whale | -0.181 |
Athena | -0.174 |
hur | -0.173 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
shown | +0.538 |
Hait | +0.523 |
Whale | +0.512 |
Athena | +0.492 |
hur | +0.489 |
Neg logit contributions | |
️ | -0.689 |
ande | -0.640 |
FIELD | -0.621 |
conflic | -0.610 |
Scrib | -0.610 |
Token |
|
Token ID | 198 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
️ | +0.922 |
ande | +0.846 |
FIELD | +0.828 |
Scrib | +0.801 |
ards | +0.792 |
Neg logit contributions | |
shown | -0.854 |
Hait | -0.841 |
Whale | -0.830 |
Athena | -0.791 |
hur | -0.784 |
Token | A |
Token ID | 32 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
️ | +1.985 |
ande | +1.825 |
FIELD | +1.788 |
LC | +1.684 |
�� | +1.682 |
Neg logit contributions | |
Hait | -2.174 |
Whale | -2.156 |
shown | -2.148 |
Athena | -2.066 |
Shin | -2.065 |
Token | black |
Token ID | 2042 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
️ | +4.142 |
ande | +3.830 |
FIELD | +3.712 |
Scrib | +3.680 |
prism | +3.668 |
Neg logit contributions | |
shown | -3.712 |
Hait | -3.680 |
Whale | -3.514 |
Athena | -3.455 |
hur | -3.403 |
Token | hat |
Token ID | 5183 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
shown | +5.995 |
Hait | +5.708 |
Whale | +5.689 |
hur | +5.551 |
Shin | +5.282 |
Neg logit contributions | |
️ | -14.513 |
ande | -13.388 |
FIELD | -13.214 |
Scrib | -13.129 |
�� | -13.068 |
Token | operator |
Token ID | 10088 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
️ | +0.992 |
ande | +0.914 |
FIELD | +0.882 |
conflic | +0.872 |
Scrib | +0.867 |
Neg logit contributions | |
shown | -0.976 |
Hait | -0.957 |
Whale | -0.930 |
hur | -0.905 |
Athena | -0.903 |
Token | is |
Token ID | 318 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
shown | +1.678 |
Hait | +1.629 |
Whale | +1.602 |
Athena | +1.541 |
Shin | +1.532 |
Neg logit contributions | |
️ | -2.043 |
ande | -1.904 |
FIELD | -1.844 |
conflic | -1.826 |
Scrib | -1.798 |
Token | used |
Token ID | 973 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
shown | +0.806 |
Hait | +0.793 |
Whale | +0.780 |
Athena | +0.758 |
Shin | +0.754 |
Neg logit contributions | |
️ | -0.526 |
ande | -0.475 |
FIELD | -0.453 |
conflic | -0.443 |
Scrib | -0.437 |
Token | to |
Token ID | 284 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
shown | +0.534 |
Hait | +0.522 |
Whale | +0.508 |
Athena | +0.487 |
Shin | +0.483 |
Neg logit contributions | |
️ | -0.734 |
ande | -0.685 |
FIELD | -0.664 |
conflic | -0.653 |
Scrib | -0.650 |
Token | 17 |
Token ID | 1596 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
shown | +1.376 |
Hait | +1.339 |
Whale | +1.314 |
Athena | +1.267 |
Shin | +1.262 |
Neg logit contributions | |
️ | -1.640 |
ande | -1.527 |
FIELD | -1.477 |
conflic | -1.462 |
Scrib | -1.440 |
Token | - |
Token ID | 12 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
shown | +2.108 |
Hait | +2.037 |
Whale | +1.996 |
Shin | +1.914 |
Athena | +1.904 |
Neg logit contributions | |
️ | -4.066 |
ande | -3.828 |
FIELD | -3.728 |
conflic | -3.722 |
Scrib | -3.664 |
Token | 40 |
Token ID | 1821 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
shown | +4.579 |
Hait | +4.257 |
Whale | +4.202 |
Shin | +4.113 |
Athena | +4.002 |
Neg logit contributions | |
️ | -6.457 |
ande | -5.969 |
conflic | -5.796 |
Scrib | -5.791 |
FIELD | -5.701 |
Token | and |
Token ID | 290 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
️ | +0.326 |
ande | +0.304 |
FIELD | +0.294 |
conflic | +0.291 |
Scrib | +0.288 |
Neg logit contributions | |
shown | -0.253 |
Hait | -0.246 |
Whale | -0.242 |
Athena | -0.231 |
Shin | -0.229 |
Token | 16 |
Token ID | 1467 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
shown | +1.653 |
Hait | +1.603 |
Whale | +1.576 |
Athena | +1.519 |
Shin | +1.517 |
Neg logit contributions | |
️ | -2.014 |
ande | -1.874 |
FIELD | -1.811 |
conflic | -1.792 |
Scrib | -1.769 |
Token | - |
Token ID | 12 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
shown | +1.951 |
Hait | +1.862 |
Whale | +1.827 |
Shin | +1.755 |
Athena | +1.751 |
Neg logit contributions | |
️ | -3.764 |
conflic | -3.583 |
ande | -3.563 |
FIELD | -3.437 |
�� | -3.434 |
Token | 35 |
Token ID | 2327 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
shown | +7.241 |
Hait | +6.498 |
hur | +6.483 |
Shin | +6.308 |
Brady | +6.291 |
Neg logit contributions | |
conflic | -14.017 |
PDATE | -13.590 |
️ | -13.495 |
�� | -12.711 |
veter | -12.497 |
Token | f |
Token ID | 277 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
️ | +3.062 |
ande | +2.818 |
FIELD | +2.752 |
prism | +2.729 |
conflic | +2.706 |
Neg logit contributions | |
shown | -2.599 |
Hait | -2.532 |
Whale | -2.501 |
Athena | -2.371 |
hur | -2.360 |
Token | / |
Token ID | 14 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
shown | +0.833 |
Hait | +0.779 |
Whale | +0.752 |
Athena | +0.707 |
Shin | +0.706 |
Neg logit contributions | |
️ | -2.436 |
ande | -2.320 |
conflic | -2.305 |
FIELD | -2.260 |
�� | -2.233 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
shown | +3.754 |
Hait | +3.544 |
Whale | +3.458 |
Shin | +3.403 |
Athena | +3.367 |
Neg logit contributions | |
️ | -4.888 |
ande | -4.624 |
conflic | -4.414 |
FIELD | -4.395 |
Scrib | -4.391 |
Token | . |
Token ID | 13 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
️ | +0.378 |
ande | +0.352 |
FIELD | +0.340 |
conflic | +0.337 |
Scrib | +0.332 |
Neg logit contributions | |
shown | -0.308 |
Hait | -0.299 |
Whale | -0.294 |
Athena | -0.283 |
Shin | -0.280 |
Token | from |
Token ID | 422 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
shown | +0.426 |
Hait | +0.413 |
Whale | +0.406 |
Athena | +0.389 |
Shin | +0.385 |
Neg logit contributions | |
️ | -0.574 |
ande | -0.536 |
FIELD | -0.518 |
conflic | -0.512 |
Scrib | -0.508 |
Token | the |
Token ID | 262 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
shown | +2.560 |
Hait | +2.502 |
Whale | +2.455 |
Shin | +2.385 |
Athena | +2.376 |
Neg logit contributions | |
️ | -3.777 |
ande | -3.530 |
FIELD | -3.439 |
conflic | -3.386 |
�� | -3.340 |
Token | National |
Token ID | 2351 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
shown | +4.253 |
Hait | +4.222 |
Whale | +4.191 |
Shin | +4.182 |
Athena | +4.081 |
Neg logit contributions | |
️ | -5.458 |
ande | -5.051 |
FIELD | -4.938 |
conflic | -4.826 |
�� | -4.790 |
Token | Police |
Token ID | 4287 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
shown | +2.431 |
Hait | +2.386 |
Whale | +2.354 |
Shin | +2.282 |
Athena | +2.274 |
Neg logit contributions | |
️ | -2.651 |
ande | -2.448 |
FIELD | -2.376 |
conflic | -2.351 |
�� | -2.300 |
Token | Agency |
Token ID | 7732 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
Shin | +5.011 |
Hait | +4.905 |
Whale | +4.903 |
shown | +4.894 |
Athena | +4.787 |
Neg logit contributions | |
️ | -9.080 |
FIELD | -8.349 |
ande | -8.335 |
conflic | -8.277 |
�� | -8.216 |
Token | 's |
Token ID | 338 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
shown | +3.359 |
Hait | +3.263 |
Whale | +3.226 |
Shin | +3.164 |
Athena | +3.119 |
Neg logit contributions | |
️ | -4.812 |
ande | -4.499 |
FIELD | -4.408 |
conflic | -4.315 |
�� | -4.312 |
Token | � |
Token ID | 564 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Shin | +9.495 |
Whale | +9.136 |
Hait | +8.970 |
Athena | +8.861 |
Brady | +8.828 |
Neg logit contributions | |
️ | -11.110 |
ande | -10.205 |
FIELD | -10.024 |
�� | -10.008 |
conflic | -9.660 |
Token | � |
Token ID | 250 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
shown | +3.987 |
Hait | +3.904 |
Whale | +3.890 |
Athena | +3.790 |
Shin | +3.779 |
Neg logit contributions | |
️ | -1.722 |
ande | -1.580 |
FIELD | -1.495 |
conflic | -1.484 |
Scrib | -1.420 |
Token | Crime |
Token ID | 45580 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
shown | +3.796 |
Hait | +3.655 |
Whale | +3.631 |
Shin | +3.575 |
Athena | +3.528 |
Neg logit contributions | |
️ | -3.331 |
ande | -3.118 |
conflic | -2.989 |
FIELD | -2.986 |
Scrib | -2.947 |
Token | in |
Token ID | 287 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
shown | +2.239 |
Hait | +2.186 |
Whale | +2.162 |
Shin | +2.081 |
Athena | +2.074 |
Neg logit contributions | |
️ | -2.897 |
ande | -2.713 |
FIELD | -2.636 |
conflic | -2.609 |
�� | -2.560 |
Token | Japan |
Token ID | 2869 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
shown | +2.866 |
Hait | +2.801 |
Whale | +2.777 |
Shin | +2.722 |
Athena | +2.665 |
Neg logit contributions | |
️ | -5.639 |
ande | -5.324 |
FIELD | -5.191 |
conflic | -5.150 |
�� | -5.050 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
️ | +1.280 |
ande | +1.181 |
FIELD | +1.145 |
Scrib | +1.142 |
conflic | +1.106 |
Neg logit contributions | |
shown | -1.083 |
Hait | -1.048 |
Whale | -1.021 |
hur | -0.991 |
Athena | -0.981 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
shown | +1.139 |
Hait | +1.105 |
Whale | +1.083 |
Athena | +1.045 |
Shin | +1.039 |
Neg logit contributions | |
️ | -1.425 |
ande | -1.330 |
conflic | -1.294 |
FIELD | -1.285 |
Scrib | -1.256 |
Token | Now |
Token ID | 3844 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
shown | +1.054 |
Hait | +1.025 |
Whale | +1.007 |
Athena | +0.976 |
Shin | +0.969 |
Neg logit contributions | |
️ | -1.014 |
ande | -0.936 |
FIELD | -0.900 |
conflic | -0.898 |
Scrib | -0.878 |
Token | playing |
Token ID | 2712 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
️ | +1.323 |
ande | +1.243 |
FIELD | +1.197 |
Scrib | +1.178 |
conflic | +1.171 |
Neg logit contributions | |
shown | -1.115 |
Hait | -1.079 |
Whale | -1.054 |
Shin | -1.011 |
Athena | -1.011 |
Token | : |
Token ID | 25 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
shown | +3.573 |
Whale | +3.505 |
Hait | +3.414 |
Athena | +3.300 |
Shin | +3.190 |
Neg logit contributions | |
️ | -6.412 |
ande | -6.009 |
conflic | -6.003 |
�� | -5.889 |
FIELD | -5.784 |
Token | Watch |
Token ID | 6305 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
️ | +1.943 |
ande | +1.831 |
FIELD | +1.776 |
Scrib | +1.761 |
conflic | +1.758 |
Neg logit contributions | |
shown | -0.964 |
Hait | -0.931 |
Whale | -0.903 |
Athena | -0.856 |
hur | -0.841 |
Token | this |
Token ID | 428 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
Shin | +5.832 |
Whale | +5.806 |
Athena | +5.697 |
Hait | +5.600 |
Inside | +5.494 |
Neg logit contributions | |
conflic | -14.260 |
️ | -13.819 |
FIELD | -13.365 |
ande | -13.153 |
PDATE | -13.016 |
Token | : |
Token ID | 25 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Hait | +3.981 |
Whale | +3.938 |
shown | +3.910 |
Athena | +3.760 |
Shin | +3.748 |
Neg logit contributions | |
️ | -7.760 |
conflic | -7.449 |
ande | -7.338 |
FIELD | -7.231 |
�� | -7.137 |
Token | Top |
Token ID | 5849 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
shown | +1.194 |
Hait | +1.160 |
Whale | +1.138 |
Athena | +1.094 |
Shin | +1.086 |
Neg logit contributions | |
️ | -1.585 |
ande | -1.482 |
FIELD | -1.436 |
conflic | -1.422 |
Scrib | -1.401 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
shown | +1.557 |
Hait | +1.515 |
Whale | +1.485 |
Athena | +1.426 |
Shin | +1.416 |
Neg logit contributions | |
️ | -2.107 |
ande | -1.967 |
FIELD | -1.911 |
conflic | -1.893 |
Scrib | -1.863 |
Token | best |
Token ID | 1266 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
shown | +1.290 |
Hait | +1.256 |
Whale | +1.234 |
Athena | +1.190 |
Shin | +1.182 |
Neg logit contributions | |
️ | -1.470 |
ande | -1.366 |
FIELD | -1.322 |
conflic | -1.306 |
Scrib | -1.287 |
Token | . |
Token ID | 13 |
Feature activation | -9.25e-03 |
Pos logit contributions | |
️ | +1.765 |
ande | +1.632 |
FIELD | +1.595 |
Scrib | +1.558 |
conflic | +1.555 |
Neg logit contributions | |
shown | -1.490 |
Hait | -1.455 |
Whale | -1.427 |
Athena | -1.367 |
hur | -1.359 |
Token | We |
Token ID | 775 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
shown | +0.070 |
Hait | +0.068 |
Whale | +0.066 |
Athena | +0.064 |
hur | +0.064 |
Neg logit contributions | |
️ | -0.089 |
ande | -0.082 |
FIELD | -0.080 |
Scrib | -0.079 |
conflic | -0.078 |
Token | then |
Token ID | 788 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
shown | +0.231 |
Hait | +0.225 |
Whale | +0.222 |
Athena | +0.214 |
Shin | +0.213 |
Neg logit contributions | |
️ | -0.233 |
ande | -0.215 |
FIELD | -0.207 |
conflic | -0.204 |
Scrib | -0.202 |
Token | apply |
Token ID | 4174 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
️ | +0.707 |
ande | +0.643 |
FIELD | +0.613 |
Scrib | +0.603 |
conflic | +0.599 |
Neg logit contributions | |
shown | -0.855 |
Hait | -0.833 |
Whale | -0.823 |
hur | -0.795 |
Athena | -0.795 |
Token | a |
Token ID | 257 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
️ | +1.621 |
ande | +1.512 |
FIELD | +1.459 |
conflic | +1.450 |
Scrib | +1.450 |
Neg logit contributions | |
shown | -1.389 |
Hait | -1.357 |
Whale | -1.318 |
hur | -1.282 |
Athena | -1.275 |
Token | black |
Token ID | 2042 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
️ | +2.276 |
ande | +2.117 |
prism | +2.059 |
Scrib | +2.053 |
FIELD | +2.045 |
Neg logit contributions | |
shown | -2.052 |
Hait | -1.988 |
Whale | -1.929 |
hur | -1.895 |
Athena | -1.891 |
Token | hat |
Token ID | 5183 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
shown | +7.554 |
Hait | +7.306 |
Whale | +7.229 |
hur | +6.994 |
Shin | +6.834 |
Neg logit contributions | |
️ | -12.620 |
ande | -11.438 |
FIELD | -11.294 |
�� | -11.169 |
ards | -11.060 |
Token | morph |
Token ID | 17488 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
️ | +1.091 |
ande | +1.013 |
FIELD | +0.972 |
conflic | +0.963 |
Scrib | +0.959 |
Neg logit contributions | |
shown | -0.944 |
Hait | -0.923 |
Whale | -0.896 |
Athena | -0.871 |
hur | -0.870 |
Token | ological |
Token ID | 2770 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
️ | +0.130 |
ande | +0.119 |
FIELD | +0.113 |
conflic | +0.112 |
Scrib | +0.110 |
Neg logit contributions | |
shown | -0.161 |
Hait | -0.158 |
Whale | -0.156 |
Athena | -0.151 |
Shin | -0.150 |
Token | operation |
Token ID | 4905 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
️ | +4.934 |
ande | +4.569 |
prism | +4.454 |
FIELD | +4.379 |
conflic | +4.351 |
Neg logit contributions | |
shown | -4.063 |
Hait | -4.046 |
hur | -3.932 |
Whale | -3.854 |
Athena | -3.781 |
Token | to |
Token ID | 284 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
shown | +0.899 |
Hait | +0.874 |
Whale | +0.856 |
Athena | +0.823 |
Shin | +0.816 |
Neg logit contributions | |
️ | -1.204 |
ande | -1.124 |
FIELD | -1.089 |
conflic | -1.076 |
Scrib | -1.065 |
Token | health |
Token ID | 1535 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
shown | +1.149 |
Hait | +1.122 |
Whale | +1.095 |
Athena | +1.059 |
Shin | +1.057 |
Neg logit contributions | |
️ | -1.372 |
ande | -1.275 |
FIELD | -1.235 |
conflic | -1.221 |
Scrib | -1.200 |
Token | are |
Token ID | 389 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
shown | +1.495 |
Hait | +1.455 |
Whale | +1.425 |
Athena | +1.377 |
Shin | +1.369 |
Neg logit contributions | |
️ | -1.875 |
ande | -1.745 |
FIELD | -1.695 |
conflic | -1.678 |
�� | -1.655 |
Token | much |
Token ID | 881 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
shown | +1.766 |
Hait | +1.718 |
Whale | +1.685 |
Athena | +1.627 |
Shin | +1.617 |
Neg logit contributions | |
️ | -2.110 |
ande | -1.967 |
FIELD | -1.896 |
conflic | -1.880 |
Scrib | -1.852 |
Token | larger |
Token ID | 4025 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
shown | +0.151 |
Hait | +0.146 |
Whale | +0.143 |
Athena | +0.138 |
Shin | +0.137 |
Neg logit contributions | |
️ | -0.185 |
ande | -0.172 |
FIELD | -0.167 |
conflic | -0.165 |
Scrib | -0.164 |
Token | than |
Token ID | 621 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
shown | +1.368 |
Hait | +1.330 |
Whale | +1.303 |
Athena | +1.254 |
Shin | +1.241 |
Neg logit contributions | |
️ | -1.946 |
ande | -1.819 |
FIELD | -1.761 |
conflic | -1.751 |
Scrib | -1.722 |
Token | previously |
Token ID | 4271 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
shown | +4.425 |
Hait | +4.332 |
Whale | +4.276 |
Athena | +4.123 |
Shin | +4.088 |
Neg logit contributions | |
️ | -6.026 |
ande | -5.615 |
conflic | -5.523 |
FIELD | -5.422 |
�� | -5.291 |
Token | realized |
Token ID | 6939 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
shown | +7.361 |
Hait | +7.231 |
Shin | +6.751 |
Athena | +6.698 |
Whale | +6.646 |
Neg logit contributions | |
️ | -12.626 |
conflic | -12.450 |
PDATE | -12.039 |
ande | -11.786 |
�� | -11.714 |
Token | ," |
Token ID | 553 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
shown | +0.583 |
Hait | +0.565 |
Whale | +0.554 |
Athena | +0.532 |
Shin | +0.528 |
Neg logit contributions | |
️ | -0.823 |
ande | -0.770 |
FIELD | -0.747 |
conflic | -0.740 |
Scrib | -0.729 |
Token | said |
Token ID | 531 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
️ | +2.686 |
ande | +2.506 |
FIELD | +2.415 |
Scrib | +2.381 |
conflic | +2.343 |
Neg logit contributions | |
shown | -2.051 |
Hait | -1.969 |
Whale | -1.918 |
hur | -1.855 |
Athena | -1.844 |
Token | Drew |
Token ID | 18624 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
️ | +2.766 |
ande | +2.589 |
FIELD | +2.476 |
Scrib | +2.468 |
prism | +2.409 |
Neg logit contributions | |
shown | -2.294 |
Hait | -2.167 |
Whale | -2.123 |
hur | -2.076 |
Athena | -2.030 |
Token | T |
Token ID | 309 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
shown | +0.727 |
Hait | +0.705 |
Whale | +0.691 |
Athena | +0.664 |
Shin | +0.659 |
Neg logit contributions | |
️ | -0.960 |
ande | -0.897 |
FIELD | -0.868 |
conflic | -0.858 |
Scrib | -0.850 |
Token |
|
Token ID | 198 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
️ | +0.342 |
ande | +0.316 |
FIELD | +0.308 |
Scrib | +0.299 |
prism | +0.295 |
Neg logit contributions | |
shown | -0.302 |
Hait | -0.295 |
Whale | -0.290 |
Athena | -0.278 |
Shin | -0.275 |
Token | Some |
Token ID | 4366 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
shown | +0.576 |
Hait | +0.563 |
Whale | +0.554 |
Athena | +0.535 |
Shin | +0.533 |
Neg logit contributions | |
️ | -0.551 |
ande | -0.508 |
FIELD | -0.490 |
conflic | -0.481 |
Scrib | -0.476 |
Token | 30 |
Token ID | 1542 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
shown | +2.084 |
Hait | +2.042 |
Whale | +1.997 |
Athena | +1.925 |
Shin | +1.907 |
Neg logit contributions | |
️ | -2.672 |
ande | -2.499 |
FIELD | -2.425 |
conflic | -2.397 |
Scrib | -2.348 |
Token | km |
Token ID | 13276 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
shown | +3.434 |
Hait | +3.348 |
Whale | +3.271 |
Athena | +3.190 |
Shin | +3.102 |
Neg logit contributions | |
️ | -5.447 |
ande | -5.144 |
FIELD | -5.055 |
conflic | -4.962 |
Scrib | -4.871 |
Token | to |
Token ID | 284 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
shown | +0.980 |
Hait | +0.950 |
Whale | +0.931 |
Athena | +0.893 |
Shin | +0.886 |
Neg logit contributions | |
️ | -1.386 |
ande | -1.297 |
FIELD | -1.258 |
conflic | -1.245 |
Scrib | -1.230 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
shown | +3.848 |
Hait | +3.767 |
Whale | +3.716 |
Athena | +3.602 |
Shin | +3.569 |
Neg logit contributions | |
️ | -5.650 |
ande | -5.363 |
FIELD | -5.209 |
conflic | -5.179 |
Scrib | -5.054 |
Token | south |
Token ID | 5366 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
Whale | +6.731 |
Hait | +6.601 |
shown | +6.454 |
Shin | +6.323 |
Athena | +6.164 |
Neg logit contributions | |
️ | -12.850 |
ande | -12.393 |
FIELD | -12.010 |
conflic | -11.921 |
�� | -11.729 |
Token | of |
Token ID | 286 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
shown | +3.614 |
Hait | +3.503 |
Whale | +3.482 |
Athena | +3.361 |
Shin | +3.321 |
Neg logit contributions | |
️ | -5.020 |
ande | -4.737 |
FIELD | -4.596 |
conflic | -4.586 |
Scrib | -4.526 |
Token | modern |
Token ID | 3660 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
shown | +1.673 |
Hait | +1.627 |
Whale | +1.596 |
Athena | +1.538 |
Shin | +1.524 |
Neg logit contributions | |
️ | -2.246 |
ande | -2.101 |
FIELD | -2.038 |
conflic | -2.017 |
Scrib | -1.983 |
Token | � |
Token ID | 6184 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
shown | +3.209 |
Hait | +3.189 |
Whale | +3.120 |
Athena | +3.038 |
Shin | +2.965 |
Neg logit contributions | |
️ | -4.986 |
ande | -4.706 |
FIELD | -4.589 |
conflic | -4.556 |
�� | -4.449 |
Token | � |
Token ID | 229 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
shown | +4.943 |
Hait | +4.846 |
Whale | +4.796 |
Athena | +4.685 |
hur | +4.668 |
Neg logit contributions | |
️ | -2.186 |
ande | -2.046 |
FIELD | -1.920 |
conflic | -1.877 |
Scrib | -1.825 |
Token | gradient |
Token ID | 31312 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
️ | +0.740 |
ande | +0.686 |
FIELD | +0.668 |
conflic | +0.659 |
Scrib | +0.658 |
Neg logit contributions | |
shown | -0.625 |
Hait | -0.607 |
Whale | -0.592 |
hur | -0.572 |
Athena | -0.570 |
Token | magnitude |
Token ID | 14735 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
shown | +0.452 |
Hait | +0.441 |
Whale | +0.433 |
Athena | +0.417 |
Shin | +0.413 |
Neg logit contributions | |
️ | -0.528 |
ande | -0.491 |
FIELD | -0.475 |
conflic | -0.468 |
Scrib | -0.464 |
Token | representation |
Token ID | 10552 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
️ | +2.030 |
ande | +1.856 |
FIELD | +1.806 |
prism | +1.762 |
Scrib | +1.760 |
Neg logit contributions | |
shown | -1.792 |
Hait | -1.765 |
Whale | -1.725 |
hur | -1.678 |
Athena | -1.662 |
Token | of |
Token ID | 286 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
shown | +2.278 |
Hait | +2.201 |
Whale | +2.170 |
Athena | +2.084 |
Shin | +2.072 |
Neg logit contributions | |
️ | -2.924 |
ande | -2.738 |
FIELD | -2.646 |
conflic | -2.638 |
Scrib | -2.591 |
Token | the |
Token ID | 262 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
️ | +1.564 |
ande | +1.454 |
FIELD | +1.416 |
conflic | +1.395 |
Scrib | +1.387 |
Neg logit contributions | |
shown | -1.349 |
Hait | -1.321 |
Whale | -1.289 |
hur | -1.244 |
Athena | -1.233 |
Token | black |
Token ID | 2042 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
️ | +2.388 |
ande | +2.203 |
FIELD | +2.146 |
prism | +2.143 |
Scrib | +2.121 |
Neg logit contributions | |
shown | -2.241 |
Hait | -2.165 |
Whale | -2.137 |
hur | -2.075 |
Athena | -2.045 |
Token | hat |
Token ID | 5183 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
shown | +7.461 |
Hait | +7.194 |
Whale | +7.059 |
hur | +6.859 |
Athena | +6.641 |
Neg logit contributions | |
️ | -12.314 |
ande | -11.295 |
Scrib | -11.081 |
FIELD | -10.951 |
�� | -10.877 |
Token | image |
Token ID | 2939 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
️ | +0.469 |
ande | +0.435 |
FIELD | +0.422 |
conflic | +0.414 |
Scrib | +0.412 |
Neg logit contributions | |
shown | -0.398 |
Hait | -0.390 |
Whale | -0.380 |
hur | -0.369 |
Athena | -0.366 |
Token | using |
Token ID | 1262 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
️ | +0.844 |
ande | +0.780 |
FIELD | +0.763 |
Scrib | +0.743 |
prism | +0.742 |
Neg logit contributions | |
shown | -0.705 |
Hait | -0.696 |
Whale | -0.676 |
hur | -0.654 |
Athena | -0.651 |
Token | the |
Token ID | 262 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
️ | +2.516 |
ande | +2.346 |
FIELD | +2.284 |
prism | +2.264 |
Scrib | +2.262 |
Neg logit contributions | |
shown | -2.164 |
Hait | -2.126 |
Whale | -2.043 |
hur | -2.025 |
Athena | -1.955 |
Token | Sch |
Token ID | 3059 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
️ | +2.049 |
ande | +1.904 |
FIELD | +1.839 |
Scrib | +1.835 |
prism | +1.831 |
Neg logit contributions | |
shown | -1.863 |
Hait | -1.812 |
Whale | -1.766 |
hur | -1.736 |
Athena | -1.697 |
Token | in |
Token ID | 287 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
️ | +2.486 |
ande | +2.270 |
FIELD | +2.199 |
prism | +2.180 |
Scrib | +2.158 |
Neg logit contributions | |
shown | -2.405 |
Hait | -2.327 |
Whale | -2.317 |
Athena | -2.211 |
hur | -2.180 |
Token | the |
Token ID | 262 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
shown | +2.822 |
Hait | +2.738 |
Whale | +2.704 |
Shin | +2.595 |
Athena | +2.595 |
Neg logit contributions | |
️ | -4.277 |
ande | -4.013 |
FIELD | -3.904 |
conflic | -3.878 |
Scrib | -3.794 |
Token | water |
Token ID | 1660 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
shown | +3.594 |
Hait | +3.505 |
Whale | +3.473 |
Athena | +3.340 |
Shin | +3.337 |
Neg logit contributions | |
️ | -4.366 |
ande | -4.071 |
FIELD | -3.944 |
conflic | -3.911 |
�� | -3.830 |
Token | , |
Token ID | 11 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
shown | +0.431 |
Hait | +0.419 |
Whale | +0.411 |
Athena | +0.395 |
Shin | +0.392 |
Neg logit contributions | |
️ | -0.552 |
ande | -0.514 |
FIELD | -0.499 |
conflic | -0.492 |
Scrib | -0.487 |
Token | then |
Token ID | 788 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
shown | +0.449 |
Hait | +0.436 |
Whale | +0.428 |
Athena | +0.412 |
Shin | +0.409 |
Neg logit contributions | |
️ | -0.494 |
ande | -0.459 |
FIELD | -0.442 |
conflic | -0.434 |
Scrib | -0.433 |
Token | boil |
Token ID | 20667 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
shown | +1.101 |
Hait | +1.072 |
Whale | +1.053 |
Athena | +1.017 |
Shin | +1.011 |
Neg logit contributions | |
️ | -1.139 |
ande | -1.054 |
FIELD | -1.017 |
conflic | -1.003 |
Scrib | -0.992 |
Token | them |
Token ID | 606 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
️ | +6.465 |
ande | +5.800 |
ards | +5.615 |
FIELD | +5.584 |
prism | +5.574 |
Neg logit contributions | |
shown | -7.209 |
Hait | -6.857 |
Whale | -6.658 |
hur | -6.591 |
Athena | -6.530 |
Token | . |
Token ID | 13 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
️ | +4.656 |
ande | +4.207 |
FIELD | +4.056 |
Scrib | +3.993 |
prism | +3.977 |
Neg logit contributions | |
shown | -4.998 |
Hait | -4.844 |
Whale | -4.713 |
Athena | -4.516 |
hur | -4.489 |
Token | Pour |
Token ID | 39128 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
️ | +2.956 |
Scrib | +2.658 |
ande | +2.640 |
FIELD | +2.601 |
ards | +2.532 |
Neg logit contributions | |
shown | -2.504 |
Hait | -2.382 |
hur | -2.312 |
Whale | -2.297 |
Athena | -2.220 |
Token | about |
Token ID | 546 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
️ | +1.636 |
ande | +1.499 |
FIELD | +1.447 |
prism | +1.420 |
Scrib | +1.416 |
Neg logit contributions | |
shown | -1.419 |
Hait | -1.374 |
Whale | -1.347 |
Athena | -1.297 |
hur | -1.291 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
️ | +2.312 |
ande | +2.169 |
FIELD | +2.092 |
prism | +2.083 |
Scrib | +2.081 |
Neg logit contributions | |
shown | -1.766 |
Hait | -1.690 |
Whale | -1.641 |
Athena | -1.586 |
hur | -1.581 |
Token | and |
Token ID | 290 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
️ | +3.350 |
ande | +3.110 |
FIELD | +2.959 |
Scrib | +2.946 |
prism | +2.937 |
Neg logit contributions | |
shown | -2.954 |
Whale | -2.791 |
Hait | -2.784 |
hur | -2.637 |
Athena | -2.629 |
Token | health |
Token ID | 1535 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
️ | +1.844 |
ande | +1.704 |
FIELD | +1.631 |
Scrib | +1.613 |
conflic | +1.603 |
Neg logit contributions | |
shown | -1.772 |
Hait | -1.684 |
Whale | -1.677 |
hur | -1.608 |
Athena | -1.602 |
Token | care |
Token ID | 1337 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
shown | +0.548 |
Hait | +0.532 |
Whale | +0.524 |
Athena | +0.504 |
Shin | +0.501 |
Neg logit contributions | |
️ | -0.630 |
ande | -0.585 |
FIELD | -0.566 |
conflic | -0.559 |
Scrib | -0.552 |
Token | costs |
Token ID | 3484 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
️ | +0.237 |
ande | +0.221 |
FIELD | +0.214 |
conflic | +0.211 |
Scrib | +0.208 |
Neg logit contributions | |
shown | -0.204 |
Hait | -0.198 |
Whale | -0.195 |
Athena | -0.187 |
Shin | -0.186 |
Token | will |
Token ID | 481 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
️ | +2.064 |
ande | +1.899 |
FIELD | +1.816 |
Scrib | +1.803 |
conflic | +1.795 |
Neg logit contributions | |
shown | -2.026 |
Hait | -1.949 |
Whale | -1.920 |
Athena | -1.857 |
hur | -1.833 |
Token | go |
Token ID | 467 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
️ | +3.957 |
ande | +3.523 |
FIELD | +3.358 |
prism | +3.350 |
Scrib | +3.269 |
Neg logit contributions | |
shown | -5.357 |
Whale | -5.171 |
Hait | -5.167 |
Nicarag | -4.907 |
Athena | -4.880 |
Token | down |
Token ID | 866 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
️ | +5.288 |
ande | +4.437 |
FIELD | +4.335 |
prism | +4.167 |
ards | +4.103 |
Neg logit contributions | |
shown | -10.017 |
Whale | -9.677 |
Hait | -9.573 |
Nicarag | -9.223 |
Athena | -9.198 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
️ | +1.394 |
ande | +1.286 |
FIELD | +1.246 |
Scrib | +1.224 |
conflic | +1.219 |
Neg logit contributions | |
shown | -1.183 |
Hait | -1.148 |
Whale | -1.130 |
Athena | -1.083 |
Shin | -1.076 |
Token | Conservatives |
Token ID | 17897 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
️ | +2.414 |
ande | +2.194 |
Scrib | +2.147 |
FIELD | +2.146 |
� | +2.088 |
Neg logit contributions | |
shown | -2.054 |
Hait | -1.951 |
Whale | -1.914 |
hur | -1.885 |
Athena | -1.845 |
Token | worry |
Token ID | 5490 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
shown | +0.296 |
Hait | +0.288 |
Whale | +0.283 |
Athena | +0.273 |
Shin | +0.271 |
Neg logit contributions | |
️ | -0.328 |
ande | -0.304 |
FIELD | -0.294 |
conflic | -0.290 |
Scrib | -0.286 |
Token | that |
Token ID | 326 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
shown | +2.549 |
Hait | +2.503 |
Whale | +2.458 |
Athena | +2.376 |
Shin | +2.365 |
Neg logit contributions | |
️ | -3.284 |
ande | -3.051 |
FIELD | -2.970 |
conflic | -2.945 |
�� | -2.876 |
Token | to |
Token ID | 284 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
shown | +1.493 |
Hait | +1.447 |
Whale | +1.417 |
Athena | +1.366 |
Shin | +1.354 |
Neg logit contributions | |
️ | -2.133 |
ande | -1.995 |
FIELD | -1.936 |
conflic | -1.916 |
Scrib | -1.891 |
Token | reduce |
Token ID | 4646 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
shown | +2.773 |
Hait | +2.719 |
Whale | +2.649 |
Athena | +2.599 |
Shin | +2.581 |
Neg logit contributions | |
️ | -3.061 |
ande | -2.842 |
FIELD | -2.764 |
conflic | -2.752 |
Scrib | -2.677 |
Token | salary |
Token ID | 9588 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
shown | +2.762 |
Hait | +2.694 |
Whale | +2.627 |
Athena | +2.571 |
Shin | +2.550 |
Neg logit contributions | |
️ | -3.603 |
ande | -3.368 |
FIELD | -3.248 |
conflic | -3.223 |
�� | -3.174 |
Token | without |
Token ID | 1231 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
shown | +2.381 |
Hait | +2.318 |
Whale | +2.263 |
Athena | +2.196 |
Shin | +2.192 |
Neg logit contributions | |
️ | -3.272 |
ande | -3.073 |
FIELD | -2.967 |
conflic | -2.942 |
�� | -2.913 |
Token | running |
Token ID | 2491 |
Feature activation | -9.62e-02 |
Pos logit contributions | |
shown | +1.809 |
Hait | +1.766 |
Whale | +1.731 |
Athena | +1.676 |
Shin | +1.666 |
Neg logit contributions | |
️ | -1.988 |
ande | -1.844 |
FIELD | -1.781 |
conflic | -1.760 |
Scrib | -1.733 |
Token | af |
Token ID | 6580 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
shown | +0.714 |
Hait | +0.692 |
Whale | +0.678 |
Athena | +0.650 |
Shin | +0.646 |
Neg logit contributions | |
️ | -0.937 |
ande | -0.874 |
FIELD | -0.848 |
conflic | -0.840 |
Scrib | -0.830 |
Token | oul |
Token ID | 2852 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
ande | +3.896 |
️ | +3.491 |
FIELD | +3.182 |
ards | +3.099 |
prism | +3.083 |
Neg logit contributions | |
shown | -10.504 |
Hait | -10.364 |
Whale | -10.182 |
Athena | -9.993 |
Howell | -9.915 |
Token | of |
Token ID | 286 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
️ | +0.781 |
ande | +0.724 |
FIELD | +0.702 |
Scrib | +0.681 |
ards | +0.676 |
Neg logit contributions | |
shown | -0.712 |
Hait | -0.694 |
Whale | -0.683 |
Athena | -0.655 |
hur | -0.654 |
Token | age |
Token ID | 2479 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
shown | +1.221 |
Hait | +1.186 |
Whale | +1.164 |
Athena | +1.119 |
Shin | +1.112 |
Neg logit contributions | |
️ | -1.536 |
ande | -1.432 |
FIELD | -1.387 |
conflic | -1.372 |
Scrib | -1.355 |
Token | discrimination |
Token ID | 8839 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
shown | +2.111 |
Hait | +2.061 |
Whale | +2.015 |
Athena | +1.947 |
Shin | +1.935 |
Neg logit contributions | |
️ | -2.709 |
ande | -2.522 |
FIELD | -2.447 |
conflic | -2.420 |
Scrib | -2.387 |
Token | laws |
Token ID | 3657 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
shown | +1.077 |
Hait | +1.049 |
Whale | +1.028 |
Athena | +0.990 |
Shin | +0.983 |
Neg logit contributions | |
️ | -1.390 |
ande | -1.297 |
FIELD | -1.256 |
conflic | -1.243 |
Scrib | -1.227 |
Token | unprecedented |
Token ID | 13029 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
shown | +0.919 |
Hait | +0.894 |
Whale | +0.879 |
Athena | +0.847 |
Shin | +0.841 |
Neg logit contributions | |
️ | -1.039 |
ande | -0.965 |
FIELD | -0.933 |
conflic | -0.922 |
Scrib | -0.909 |
Token | in |
Token ID | 287 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
shown | +2.398 |
Hait | +2.333 |
Whale | +2.288 |
Athena | +2.207 |
Shin | +2.185 |
Neg logit contributions | |
️ | -3.188 |
ande | -3.016 |
FIELD | -2.921 |
conflic | -2.915 |
Scrib | -2.837 |
Token | a |
Token ID | 257 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
️ | +2.302 |
ande | +2.153 |
FIELD | +2.046 |
conflic | +2.035 |
Scrib | +2.026 |
Neg logit contributions | |
shown | -2.061 |
Hait | -1.993 |
Whale | -1.959 |
Athena | -1.892 |
hur | -1.887 |
Token | major |
Token ID | 1688 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
️ | +3.788 |
ande | +3.525 |
FIELD | +3.338 |
prism | +3.326 |
conflic | +3.284 |
Neg logit contributions | |
shown | -4.028 |
Hait | -3.904 |
Whale | -3.809 |
Athena | -3.745 |
hur | -3.681 |
Token | - |
Token ID | 12 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
️ | +4.015 |
ande | +3.764 |
FIELD | +3.533 |
prism | +3.526 |
conflic | +3.475 |
Neg logit contributions | |
shown | -4.468 |
Hait | -4.340 |
Whale | -4.250 |
Athena | -4.146 |
Shin | -4.054 |
Token | party |
Token ID | 10608 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
️ | +4.719 |
ande | +4.701 |
FIELD | +4.292 |
ards | +4.056 |
bledon | +3.978 |
Neg logit contributions | |
Hait | -8.289 |
Whale | -8.112 |
shown | -8.097 |
Shin | -7.923 |
Athena | -7.867 |
Token | presidential |
Token ID | 4787 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
️ | +5.982 |
ande | +5.562 |
prism | +5.377 |
FIELD | +5.186 |
Scrib | +5.075 |
Neg logit contributions | |
shown | -8.393 |
Hait | -8.037 |
Whale | -7.770 |
hur | -7.701 |
Athena | -7.646 |
Token | candidate |
Token ID | 4540 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
️ | +4.292 |
ande | +4.013 |
prism | +3.805 |
FIELD | +3.758 |
conflic | +3.709 |
Neg logit contributions | |
shown | -5.522 |
Hait | -5.363 |
Whale | -5.202 |
Athena | -5.129 |
hur | -5.047 |
Token | . |
Token ID | 13 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
️ | +2.639 |
ande | +2.451 |
FIELD | +2.348 |
conflic | +2.314 |
prism | +2.286 |
Neg logit contributions | |
shown | -2.318 |
Hait | -2.262 |
Whale | -2.205 |
Athena | -2.134 |
Shin | -2.123 |
Token | So |
Token ID | 1406 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
️ | +0.326 |
ande | +0.301 |
FIELD | +0.292 |
Scrib | +0.289 |
conflic | +0.284 |
Neg logit contributions | |
shown | -0.265 |
Hait | -0.256 |
Whale | -0.251 |
Athena | -0.242 |
hur | -0.241 |
Token | I |
Token ID | 314 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
shown | +1.414 |
Hait | +1.380 |
Whale | +1.350 |
Athena | +1.296 |
Shin | +1.293 |
Neg logit contributions | |
️ | -1.912 |
ande | -1.786 |
FIELD | -1.736 |
conflic | -1.725 |
Scrib | -1.690 |
Token | ext |
Token ID | 2302 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
️ | +4.282 |
ande | +4.002 |
FIELD | +3.898 |
ards | +3.796 |
Scrib | +3.790 |
Neg logit contributions | |
shown | -3.551 |
Hait | -3.514 |
Whale | -3.453 |
Athena | -3.341 |
Shin | -3.278 |
Token | = |
Token ID | 796 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
️ | +2.008 |
ande | +1.882 |
FIELD | +1.821 |
Scrib | +1.779 |
conflic | +1.767 |
Neg logit contributions | |
shown | -1.504 |
Hait | -1.473 |
Whale | -1.449 |
Athena | -1.392 |
Shin | -1.373 |
Token | ($ |
Token ID | 7198 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
️ | +0.434 |
ande | +0.402 |
FIELD | +0.387 |
conflic | +0.382 |
Scrib | +0.379 |
Neg logit contributions | |
shown | -0.434 |
Hait | -0.424 |
Whale | -0.413 |
Athena | -0.398 |
hur | -0.398 |
Token | text |
Token ID | 5239 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
shown | +5.371 |
Hait | +5.051 |
Whale | +5.017 |
hur | +4.898 |
Athena | +4.884 |
Neg logit contributions | |
️ | -4.711 |
ande | -4.302 |
conflic | -4.286 |
Scrib | -4.151 |
�� | -4.056 |
Token | - |
Token ID | 532 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
️ | +1.727 |
ande | +1.606 |
FIELD | +1.563 |
conflic | +1.520 |
Scrib | +1.517 |
Neg logit contributions | |
shown | -1.410 |
Hait | -1.379 |
Whale | -1.345 |
Athena | -1.295 |
Shin | -1.289 |
Token | split |
Token ID | 35312 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
shown | +2.162 |
Hait | +2.080 |
Whale | +2.064 |
Athena | +1.981 |
Shin | +1.973 |
Neg logit contributions | |
️ | -2.485 |
ande | -2.288 |
conflic | -2.217 |
FIELD | -2.211 |
Scrib | -2.179 |
Token | "\ |
Token ID | 37082 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
️ | +7.861 |
FIELD | +7.505 |
ande | +7.369 |
Scrib | +7.212 |
LC | +7.038 |
Neg logit contributions | |
shown | -5.788 |
Hait | -5.721 |
Whale | -5.451 |
hur | -5.379 |
Athena | -5.200 |
Token | r |
Token ID | 81 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
️ | +3.785 |
ande | +3.481 |
FIELD | +3.407 |
Scrib | +3.276 |
LC | +3.248 |
Neg logit contributions | |
Hait | -3.131 |
shown | -3.107 |
Whale | -3.029 |
Athena | -2.941 |
Shin | -2.898 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
️ | +1.387 |
ande | +1.282 |
FIELD | +1.254 |
Scrib | +1.208 |
ards | +1.198 |
Neg logit contributions | |
shown | -1.173 |
Hait | -1.161 |
Whale | -1.129 |
Athena | -1.087 |
hur | -1.078 |
Token |
|
Token ID | 198 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
️ | +1.547 |
ande | +1.426 |
FIELD | +1.394 |
Scrib | +1.336 |
ards | +1.333 |
Neg logit contributions | |
Hait | -1.461 |
shown | -1.459 |
Whale | -1.434 |
Athena | -1.371 |
Shin | -1.350 |
Token | ") |
Token ID | 4943 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
️ | +3.222 |
ande | +3.026 |
FIELD | +2.971 |
ards | +2.849 |
� | +2.845 |
Neg logit contributions | |
Hait | -2.026 |
shown | -1.995 |
Whale | -1.945 |
Athena | -1.856 |
Shin | -1.838 |
Token | Here |
Token ID | 4342 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
shown | +3.901 |
Hait | +3.693 |
Whale | +3.576 |
hur | +3.528 |
Athena | +3.496 |
Neg logit contributions | |
️ | -3.974 |
conflic | -3.761 |
ande | -3.696 |
Scrib | -3.520 |
FIELD | -3.499 |
Token | on |
Token ID | 319 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
️ | +3.884 |
ande | +3.684 |
FIELD | +3.487 |
ards | +3.452 |
Scrib | +3.423 |
Neg logit contributions | |
shown | -3.642 |
Hait | -3.507 |
Whale | -3.421 |
hur | -3.319 |
Athena | -3.300 |
Token | a |
Token ID | 257 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
️ | +1.781 |
ande | +1.644 |
FIELD | +1.581 |
Scrib | +1.579 |
conflic | +1.564 |
Neg logit contributions | |
shown | -1.640 |
Hait | -1.593 |
Whale | -1.552 |
hur | -1.507 |
Athena | -1.491 |
Token | few |
Token ID | 1178 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
️ | +1.415 |
ande | +1.312 |
FIELD | +1.260 |
Scrib | +1.250 |
conflic | +1.249 |
Neg logit contributions | |
shown | -1.322 |
Hait | -1.288 |
Whale | -1.252 |
Athena | -1.214 |
Shin | -1.200 |
Token | of |
Token ID | 286 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
️ | +0.449 |
ande | +0.417 |
FIELD | +0.403 |
conflic | +0.399 |
Scrib | +0.397 |
Neg logit contributions | |
shown | -0.381 |
Hait | -0.370 |
Whale | -0.363 |
Athena | -0.349 |
Shin | -0.347 |
Token | the |
Token ID | 262 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
shown | +1.426 |
Hait | +1.384 |
Whale | +1.359 |
Athena | +1.313 |
Shin | +1.302 |
Neg logit contributions | |
️ | -1.947 |
ande | -1.823 |
FIELD | -1.771 |
conflic | -1.754 |
�� | -1.718 |
Token | lessons |
Token ID | 11658 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
️ | +1.951 |
ande | +1.802 |
FIELD | +1.727 |
Scrib | +1.723 |
conflic | +1.708 |
Neg logit contributions | |
shown | -1.748 |
Hait | -1.699 |
Whale | -1.657 |
hur | -1.604 |
Athena | -1.595 |
Token | I |
Token ID | 314 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
shown | +0.290 |
Hait | +0.281 |
Whale | +0.276 |
Athena | +0.264 |
Shin | +0.262 |
Neg logit contributions | |
️ | -0.390 |
ande | -0.364 |
FIELD | -0.352 |
conflic | -0.347 |
Scrib | -0.346 |
Token | learned |
Token ID | 4499 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
️ | +3.709 |
ande | +3.408 |
FIELD | +3.211 |
Scrib | +3.191 |
ards | +3.162 |
Neg logit contributions | |
shown | -3.398 |
Hait | -3.335 |
Whale | -3.330 |
hur | -3.189 |
Athena | -3.135 |
Token | through |
Token ID | 832 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
️ | +1.456 |
ande | +1.343 |
FIELD | +1.291 |
Scrib | +1.283 |
conflic | +1.266 |
Neg logit contributions | |
shown | -1.149 |
Hait | -1.117 |
Whale | -1.104 |
hur | -1.049 |
Athena | -1.047 |
Token | the |
Token ID | 262 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
️ | +4.113 |
ande | +3.795 |
Scrib | +3.664 |
prism | +3.601 |
FIELD | +3.594 |
Neg logit contributions | |
shown | -3.687 |
Hait | -3.568 |
Whale | -3.455 |
hur | -3.389 |
Athena | -3.321 |
Token | that |
Token ID | 326 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
️ | +3.312 |
ande | +3.009 |
FIELD | +2.902 |
Scrib | +2.882 |
conflic | +2.839 |
Neg logit contributions | |
shown | -3.074 |
Hait | -2.998 |
Whale | -2.933 |
hur | -2.834 |
Athena | -2.831 |
Token | a |
Token ID | 257 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
️ | +2.371 |
ande | +2.187 |
FIELD | +2.118 |
Scrib | +2.110 |
conflic | +2.070 |
Neg logit contributions | |
shown | -2.161 |
Hait | -2.102 |
Whale | -2.042 |
hur | -1.988 |
Athena | -1.964 |
Token | panel |
Token ID | 6103 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
shown | +0.849 |
Hait | +0.826 |
Whale | +0.812 |
Athena | +0.784 |
Shin | +0.779 |
Neg logit contributions | |
️ | -0.948 |
ande | -0.880 |
FIELD | -0.850 |
conflic | -0.841 |
Scrib | -0.829 |
Token | you |
Token ID | 345 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
️ | +1.934 |
ande | +1.805 |
FIELD | +1.735 |
conflic | +1.711 |
Scrib | +1.692 |
Neg logit contributions | |
shown | -1.693 |
Hait | -1.662 |
Whale | -1.634 |
Athena | -1.556 |
hur | -1.542 |
Token | wanted |
Token ID | 2227 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
shown | +0.616 |
Hait | +0.600 |
Whale | +0.590 |
Athena | +0.569 |
Shin | +0.565 |
Neg logit contributions | |
️ | -0.671 |
ande | -0.620 |
FIELD | -0.599 |
conflic | -0.591 |
Scrib | -0.584 |
Token | to |
Token ID | 284 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
shown | +0.417 |
Hait | +0.405 |
Whale | +0.397 |
Athena | +0.380 |
Shin | +0.377 |
Neg logit contributions | |
️ | -0.584 |
ande | -0.546 |
FIELD | -0.529 |
conflic | -0.522 |
Scrib | -0.518 |
Token | see |
Token ID | 766 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
️ | +0.762 |
ande | +0.701 |
FIELD | +0.676 |
Scrib | +0.662 |
conflic | +0.659 |
Neg logit contributions | |
shown | -0.756 |
Hait | -0.732 |
Whale | -0.722 |
hur | -0.697 |
Athena | -0.693 |
Token | upstairs |
Token ID | 26148 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
️ | +2.811 |
ande | +2.564 |
FIELD | +2.490 |
Scrib | +2.456 |
prism | +2.405 |
Neg logit contributions | |
shown | -2.632 |
Hait | -2.547 |
Whale | -2.511 |
hur | -2.397 |
Athena | -2.384 |
Token | is |
Token ID | 318 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
️ | +3.012 |
ande | +2.751 |
FIELD | +2.663 |
Scrib | +2.613 |
conflic | +2.593 |
Neg logit contributions | |
shown | -2.777 |
Hait | -2.738 |
Whale | -2.663 |
Athena | -2.561 |
hur | -2.550 |
Token | starting |
Token ID | 3599 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
️ | +1.691 |
ande | +1.557 |
FIELD | +1.509 |
Scrib | +1.488 |
conflic | +1.473 |
Neg logit contributions | |
shown | -1.487 |
Hait | -1.450 |
Whale | -1.430 |
Athena | -1.364 |
hur | -1.353 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
️ | +1.551 |
ande | +1.445 |
FIELD | +1.401 |
conflic | +1.380 |
Scrib | +1.364 |
Neg logit contributions | |
shown | -1.408 |
Hait | -1.366 |
Whale | -1.348 |
Athena | -1.296 |
Shin | -1.282 |
Token | � |
Token ID | 247 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
️ | +0.033 |
ande | +0.028 |
FIELD | +0.026 |
conflic | +0.025 |
Scrib | +0.024 |
Neg logit contributions | |
shown | -0.107 |
Hait | -0.105 |
Whale | -0.104 |
Athena | -0.102 |
Shin | -0.101 |
Token | ve |
Token ID | 303 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
shown | +0.868 |
Hait | +0.843 |
Whale | +0.829 |
Athena | +0.800 |
Shin | +0.795 |
Neg logit contributions | |
️ | -0.966 |
ande | -0.898 |
FIELD | -0.869 |
conflic | -0.860 |
Scrib | -0.847 |
Token | begun |
Token ID | 9258 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
shown | +1.126 |
Hait | +1.094 |
Whale | +1.075 |
Athena | +1.039 |
Shin | +1.032 |
Neg logit contributions | |
️ | -1.234 |
ande | -1.146 |
FIELD | -1.109 |
conflic | -1.099 |
Scrib | -1.077 |
Token | to |
Token ID | 284 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
️ | +1.358 |
ande | +1.257 |
FIELD | +1.206 |
conflic | +1.193 |
Scrib | +1.191 |
Neg logit contributions | |
shown | -1.128 |
Hait | -1.092 |
Whale | -1.071 |
Athena | -1.031 |
Shin | -1.021 |
Token | write |
Token ID | 3551 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
️ | +2.894 |
ande | +2.623 |
FIELD | +2.490 |
Scrib | +2.458 |
prism | +2.437 |
Neg logit contributions | |
shown | -3.380 |
Hait | -3.245 |
Whale | -3.236 |
hur | -3.127 |
Athena | -3.102 |
Token | about |
Token ID | 546 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
️ | +1.809 |
ande | +1.672 |
FIELD | +1.598 |
Scrib | +1.581 |
conflic | +1.579 |
Neg logit contributions | |
shown | -1.599 |
Hait | -1.538 |
Whale | -1.508 |
Athena | -1.455 |
hur | -1.440 |
Token | working |
Token ID | 1762 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
️ | +0.605 |
ande | +0.566 |
FIELD | +0.547 |
conflic | +0.541 |
Scrib | +0.535 |
Neg logit contributions | |
shown | -0.508 |
Hait | -0.490 |
Whale | -0.481 |
Athena | -0.462 |
Shin | -0.459 |
Token | conditions |
Token ID | 3403 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
shown | +2.681 |
Hait | +2.643 |
Whale | +2.596 |
Athena | +2.502 |
Shin | +2.490 |
Neg logit contributions | |
️ | -3.070 |
ande | -2.861 |
FIELD | -2.738 |
conflic | -2.714 |
�� | -2.692 |
Token | for |
Token ID | 329 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
shown | +2.163 |
Hait | +2.121 |
Whale | +2.065 |
Athena | +1.984 |
Shin | +1.974 |
Neg logit contributions | |
️ | -2.904 |
ande | -2.722 |
FIELD | -2.637 |
conflic | -2.609 |
Scrib | -2.578 |
Token | doctors |
Token ID | 7519 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
shown | +1.297 |
Hait | +1.264 |
Whale | +1.238 |
Athena | +1.193 |
Shin | +1.185 |
Neg logit contributions | |
️ | -1.604 |
ande | -1.495 |
FIELD | -1.448 |
conflic | -1.433 |
Scrib | -1.414 |
Token | in |
Token ID | 287 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
shown | +1.316 |
Hait | +1.284 |
Whale | +1.254 |
Athena | +1.207 |
Shin | +1.198 |
Neg logit contributions | |
️ | -1.786 |
ande | -1.672 |
FIELD | -1.624 |
conflic | -1.608 |
Scrib | -1.588 |
Token | guidelines |
Token ID | 9949 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
️ | +0.065 |
ande | +0.060 |
FIELD | +0.058 |
conflic | +0.057 |
Scrib | +0.057 |
Neg logit contributions | |
shown | -0.060 |
Hait | -0.058 |
Whale | -0.057 |
Athena | -0.055 |
Shin | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
️ | +2.145 |
ande | +1.964 |
FIELD | +1.882 |
Scrib | +1.862 |
prism | +1.840 |
Neg logit contributions | |
shown | -1.867 |
Hait | -1.812 |
Whale | -1.783 |
Athena | -1.721 |
Shin | -1.703 |
Token | � |
Token ID | 447 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
shown | +0.675 |
Hait | +0.657 |
Whale | +0.646 |
Athena | +0.624 |
Shin | +0.621 |
Neg logit contributions | |
️ | -0.699 |
ande | -0.648 |
FIELD | -0.625 |
conflic | -0.619 |
Scrib | -0.608 |
Token | � |
Token ID | 251 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
shown | +1.130 |
Hait | +1.110 |
Whale | +1.098 |
Athena | +1.072 |
Shin | +1.068 |
Neg logit contributions | |
️ | -0.461 |
ande | -0.409 |
FIELD | -0.382 |
conflic | -0.372 |
Scrib | -0.361 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
shown | +0.305 |
Hait | +0.297 |
Whale | +0.291 |
Athena | +0.280 |
Shin | +0.278 |
Neg logit contributions | |
️ | -0.375 |
ande | -0.349 |
FIELD | -0.338 |
conflic | -0.333 |
Scrib | -0.330 |
Token |
|
Token ID | 198 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
️ | +1.149 |
ande | +1.053 |
FIELD | +1.030 |
Scrib | +0.999 |
ards | +0.984 |
Neg logit contributions | |
shown | -1.061 |
Hait | -1.040 |
Whale | -1.024 |
Athena | -0.980 |
hur | -0.970 |
Token | ( |
Token ID | 7 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
️ | +1.621 |
ande | +1.478 |
FIELD | +1.439 |
Scrib | +1.375 |
� | +1.363 |
Neg logit contributions | |
shown | -1.670 |
Hait | -1.667 |
Whale | -1.649 |
Athena | -1.591 |
Shin | -1.574 |
Token | © |
Token ID | 16224 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
shown | +0.710 |
Hait | +0.691 |
Whale | +0.680 |
Athena | +0.657 |
Shin | +0.654 |
Neg logit contributions | |
️ | -0.686 |
ande | -0.634 |
FIELD | -0.611 |
conflic | -0.605 |
Scrib | -0.594 |
Token | Copyright |
Token ID | 15069 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
️ | +5.495 |
FIELD | +4.879 |
ande | +4.874 |
Scrib | +4.804 |
ards | +4.656 |
Neg logit contributions | |
shown | -5.517 |
Hait | -5.357 |
Whale | -5.116 |
Athena | -4.997 |
hur | -4.975 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
️ | +4.573 |
ande | +4.187 |
FIELD | +4.075 |
Scrib | +4.049 |
prism | +3.899 |
Neg logit contributions | |
shown | -4.778 |
Hait | -4.636 |
Whale | -4.479 |
hur | -4.422 |
Athena | -4.304 |
Token | The |
Token ID | 383 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
shown | +0.751 |
Hait | +0.730 |
Whale | +0.716 |
Athena | +0.689 |
Shin | +0.684 |
Neg logit contributions | |
️ | -0.977 |
ande | -0.912 |
FIELD | -0.884 |
conflic | -0.875 |
Scrib | -0.863 |
Token | had |
Token ID | 550 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
️ | +0.206 |
ande | +0.191 |
FIELD | +0.183 |
conflic | +0.180 |
Scrib | +0.179 |
Neg logit contributions | |
shown | -0.214 |
Hait | -0.208 |
Whale | -0.205 |
Athena | -0.197 |
Shin | -0.196 |
Token | to |
Token ID | 284 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
shown | +1.104 |
Hait | +1.069 |
Whale | +1.048 |
Athena | +1.006 |
Shin | +0.997 |
Neg logit contributions | |
️ | -1.495 |
ande | -1.400 |
FIELD | -1.356 |
conflic | -1.342 |
Scrib | -1.327 |
Token | a |
Token ID | 257 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
shown | +0.852 |
Hait | +0.827 |
Whale | +0.813 |
Athena | +0.784 |
Shin | +0.778 |
Neg logit contributions | |
️ | -0.907 |
ande | -0.841 |
FIELD | -0.812 |
conflic | -0.801 |
Scrib | -0.792 |
Token | venge |
Token ID | 18674 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
shown | +1.734 |
Hait | +1.659 |
Whale | +1.645 |
Shin | +1.550 |
Athena | +1.512 |
Neg logit contributions | |
️ | -4.526 |
ande | -4.254 |
FIELD | -4.165 |
conflic | -4.131 |
Scrib | -4.095 |
Token | the |
Token ID | 262 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
shown | +1.999 |
Hait | +1.943 |
Whale | +1.906 |
Athena | +1.827 |
Shin | +1.818 |
Neg logit contributions | |
️ | -2.978 |
ande | -2.788 |
FIELD | -2.706 |
conflic | -2.684 |
Scrib | -2.639 |
Token | death |
Token ID | 1918 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
️ | +0.169 |
ande | +0.157 |
FIELD | +0.151 |
conflic | +0.150 |
Scrib | +0.150 |
Neg logit contributions | |
shown | -0.167 |
Hait | -0.161 |
Whale | -0.157 |
Athena | -0.153 |
hur | -0.152 |
Token | of |
Token ID | 286 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
️ | +1.704 |
ande | +1.588 |
FIELD | +1.536 |
conflic | +1.514 |
Scrib | +1.502 |
Neg logit contributions | |
shown | -1.518 |
Hait | -1.475 |
Whale | -1.439 |
Athena | -1.392 |
hur | -1.372 |
Token | Spl |
Token ID | 13341 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
shown | +1.445 |
Hait | +1.398 |
Whale | +1.367 |
Athena | +1.310 |
Shin | +1.298 |
Neg logit contributions | |
️ | -2.116 |
ande | -1.983 |
FIELD | -1.922 |
conflic | -1.902 |
Scrib | -1.886 |
Token | inter |
Token ID | 3849 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
️ | +0.698 |
ande | +0.656 |
FIELD | +0.619 |
Scrib | +0.604 |
ards | +0.596 |
Neg logit contributions | |
shown | -0.831 |
Hait | -0.816 |
Whale | -0.806 |
Athena | -0.784 |
Shin | -0.767 |
Token | 's |
Token ID | 338 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
shown | +1.591 |
Hait | +1.544 |
Whale | +1.513 |
Athena | +1.454 |
Shin | +1.442 |
Neg logit contributions | |
️ | -2.145 |
ande | -2.004 |
FIELD | -1.943 |
conflic | -1.922 |
Scrib | -1.899 |
Token | Master |
Token ID | 5599 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
shown | +1.671 |
Hait | +1.624 |
Whale | +1.593 |
Athena | +1.535 |
Shin | +1.523 |
Neg logit contributions | |
️ | -1.975 |
ande | -1.837 |
FIELD | -1.776 |
conflic | -1.757 |
Scrib | -1.736 |
Token | other |
Token ID | 584 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
shown | +0.661 |
Hait | +0.640 |
Whale | +0.626 |
Athena | +0.603 |
hur | +0.598 |
Neg logit contributions | |
️ | -0.772 |
ande | -0.717 |
FIELD | -0.694 |
conflic | -0.685 |
Scrib | -0.684 |
Token | states |
Token ID | 2585 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
️ | +2.517 |
ande | +2.325 |
Scrib | +2.262 |
FIELD | +2.235 |
prism | +2.211 |
Neg logit contributions | |
shown | -2.483 |
Hait | -2.379 |
Whale | -2.338 |
hur | -2.261 |
Athena | -2.249 |
Token | should |
Token ID | 815 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
️ | +0.247 |
ande | +0.228 |
FIELD | +0.219 |
Scrib | +0.215 |
conflic | +0.215 |
Neg logit contributions | |
shown | -0.249 |
Hait | -0.241 |
Whale | -0.238 |
Athena | -0.230 |
Shin | -0.228 |
Token | push |
Token ID | 4574 |
Feature activation | -7.28e-02 |
Pos logit contributions | |
️ | +0.789 |
ande | +0.732 |
FIELD | +0.702 |
Scrib | +0.686 |
prism | +0.681 |
Neg logit contributions | |
shown | -0.818 |
Hait | -0.793 |
Whale | -0.786 |
hur | -0.752 |
Athena | -0.751 |
Token | ahead |
Token ID | 4058 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
shown | +0.572 |
Hait | +0.555 |
Whale | +0.545 |
Athena | +0.523 |
Shin | +0.520 |
Neg logit contributions | |
️ | -0.677 |
ande | -0.630 |
FIELD | -0.611 |
conflic | -0.600 |
Scrib | -0.598 |
Token | with |
Token ID | 351 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
shown | +0.461 |
Hait | +0.448 |
Whale | +0.440 |
Athena | +0.423 |
Shin | +0.420 |
Neg logit contributions | |
️ | -0.534 |
ande | -0.497 |
FIELD | -0.481 |
conflic | -0.472 |
Scrib | -0.470 |
Token | a |
Token ID | 257 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
shown | +1.848 |
Hait | +1.795 |
Whale | +1.763 |
Athena | +1.698 |
Shin | +1.686 |
Neg logit contributions | |
️ | -2.457 |
ande | -2.291 |
FIELD | -2.218 |
conflic | -2.202 |
Scrib | -2.159 |
Token | regional |
Token ID | 7915 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
️ | +0.033 |
ande | +0.031 |
FIELD | +0.030 |
conflic | +0.029 |
Scrib | +0.029 |
Neg logit contributions | |
shown | -0.030 |
Hait | -0.030 |
Whale | -0.029 |
Athena | -0.028 |
hur | -0.028 |
Token | plan |
Token ID | 1410 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
️ | +0.565 |
ande | +0.527 |
FIELD | +0.510 |
Scrib | +0.504 |
prism | +0.502 |
Neg logit contributions | |
shown | -0.496 |
Hait | -0.478 |
Whale | -0.466 |
hur | -0.450 |
Athena | -0.447 |
Token | that |
Token ID | 326 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
️ | +1.094 |
ande | +1.023 |
FIELD | +0.991 |
Scrib | +0.973 |
conflic | +0.960 |
Neg logit contributions | |
shown | -0.966 |
Hait | -0.929 |
Whale | -0.914 |
Athena | -0.878 |
hur | -0.872 |
Token | can |
Token ID | 460 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
️ | +1.768 |
ande | +1.627 |
FIELD | +1.568 |
Scrib | +1.542 |
ards | +1.532 |
Neg logit contributions | |
shown | -1.939 |
Hait | -1.848 |
Whale | -1.828 |
Athena | -1.758 |
hur | -1.754 |
Token | , |
Token ID | 11 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
shown | +0.529 |
Hait | +0.515 |
Whale | +0.505 |
Athena | +0.486 |
Shin | +0.482 |
Neg logit contributions | |
️ | -0.669 |
ande | -0.624 |
FIELD | -0.604 |
conflic | -0.598 |
Scrib | -0.590 |
Token | I |
Token ID | 314 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
shown | +1.240 |
Hait | +1.210 |
Whale | +1.186 |
Athena | +1.143 |
Shin | +1.136 |
Neg logit contributions | |
️ | -1.444 |
ande | -1.342 |
FIELD | -1.298 |
conflic | -1.285 |
Scrib | -1.265 |
Token | think |
Token ID | 892 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
shown | +0.696 |
Hait | +0.679 |
Whale | +0.664 |
Athena | +0.642 |
Shin | +0.637 |
Neg logit contributions | |
️ | -0.812 |
ande | -0.757 |
FIELD | -0.734 |
conflic | -0.731 |
Scrib | -0.717 |
Token | these |
Token ID | 777 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Hait | +3.273 |
shown | +3.268 |
Whale | +3.180 |
Athena | +3.065 |
Shin | +3.052 |
Neg logit contributions | |
️ | -4.238 |
ande | -3.952 |
conflic | -3.822 |
FIELD | -3.812 |
�� | -3.704 |
Token | salaries |
Token ID | 17058 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
shown | +1.972 |
Hait | +1.940 |
Whale | +1.891 |
Athena | +1.822 |
Shin | +1.813 |
Neg logit contributions | |
️ | -2.424 |
ande | -2.262 |
FIELD | -2.186 |
conflic | -2.157 |
Scrib | -2.132 |
Token | are |
Token ID | 389 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
shown | +2.196 |
Hait | +2.143 |
Whale | +2.098 |
Athena | +2.026 |
Shin | +2.018 |
Neg logit contributions | |
️ | -2.618 |
ande | -2.438 |
FIELD | -2.364 |
conflic | -2.343 |
Scrib | -2.300 |
Token | right |
Token ID | 826 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
shown | +0.986 |
Hait | +0.956 |
Whale | +0.940 |
Athena | +0.902 |
Shin | +0.894 |
Neg logit contributions | |
️ | -1.206 |
ande | -1.122 |
FIELD | -1.090 |
conflic | -1.074 |
Scrib | -1.064 |
Token | in |
Token ID | 287 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
shown | +4.216 |
Hait | +4.130 |
Whale | +4.066 |
Athena | +3.970 |
Shin | +3.962 |
Neg logit contributions | |
️ | -5.789 |
ande | -5.466 |
conflic | -5.349 |
FIELD | -5.233 |
�� | -5.144 |
Token | line |
Token ID | 1627 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
shown | +1.758 |
Hait | +1.713 |
Whale | +1.672 |
Athena | +1.601 |
Shin | +1.595 |
Neg logit contributions | |
️ | -2.930 |
ande | -2.750 |
FIELD | -2.662 |
conflic | -2.653 |
Scrib | -2.608 |
Token | or |
Token ID | 393 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
️ | +0.547 |
ande | +0.507 |
FIELD | +0.490 |
conflic | +0.482 |
Scrib | +0.478 |
Neg logit contributions | |
shown | -0.511 |
Hait | -0.495 |
Whale | -0.487 |
Athena | -0.469 |
hur | -0.465 |
Token | even |
Token ID | 772 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
️ | +0.669 |
ande | +0.614 |
FIELD | +0.596 |
conflic | +0.587 |
Scrib | +0.586 |
Neg logit contributions | |
shown | -0.630 |
Hait | -0.604 |
Whale | -0.599 |
Athena | -0.576 |
hur | -0.573 |
Token | my |
Token ID | 616 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
shown | +0.281 |
Hait | +0.271 |
Whale | +0.266 |
Athena | +0.254 |
Shin | +0.252 |
Neg logit contributions | |
️ | -0.389 |
ande | -0.364 |
FIELD | -0.352 |
conflic | -0.348 |
Scrib | -0.347 |
Token | life |
Token ID | 1204 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
shown | +0.292 |
Hait | +0.284 |
Whale | +0.279 |
Athena | +0.270 |
Shin | +0.268 |
Neg logit contributions | |
️ | -0.248 |
ande | -0.227 |
FIELD | -0.217 |
conflic | -0.215 |
Scrib | -0.213 |
Token | but |
Token ID | 475 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
️ | +0.616 |
ande | +0.572 |
FIELD | +0.553 |
conflic | +0.543 |
Scrib | +0.543 |
Neg logit contributions | |
shown | -0.518 |
Hait | -0.502 |
Whale | -0.493 |
Athena | -0.471 |
hur | -0.468 |
Token | I |
Token ID | 314 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
shown | +0.462 |
Hait | +0.447 |
Whale | +0.440 |
Athena | +0.421 |
Shin | +0.418 |
Neg logit contributions | |
️ | -0.575 |
ande | -0.536 |
FIELD | -0.518 |
conflic | -0.511 |
Scrib | -0.510 |
Token | intend |
Token ID | 14765 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
shown | +0.502 |
Hait | +0.488 |
Whale | +0.481 |
Athena | +0.463 |
Shin | +0.460 |
Neg logit contributions | |
️ | -0.506 |
ande | -0.468 |
FIELD | -0.449 |
conflic | -0.442 |
Scrib | -0.439 |
Token | to |
Token ID | 284 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
shown | +1.188 |
Hait | +1.152 |
Whale | +1.128 |
Athena | +1.083 |
Shin | +1.075 |
Neg logit contributions | |
️ | -1.710 |
ande | -1.600 |
FIELD | -1.553 |
conflic | -1.538 |
Scrib | -1.519 |
Token | get |
Token ID | 651 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
shown | +1.098 |
Hait | +1.072 |
Whale | +1.054 |
Athena | +1.021 |
Shin | +1.015 |
Neg logit contributions | |
️ | -1.048 |
ande | -0.967 |
FIELD | -0.932 |
conflic | -0.921 |
Scrib | -0.906 |
Token | better |
Token ID | 1365 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
shown | +2.615 |
Hait | +2.559 |
Whale | +2.494 |
Athena | +2.421 |
Shin | +2.406 |
Neg logit contributions | |
️ | -3.359 |
ande | -3.143 |
FIELD | -3.045 |
conflic | -3.021 |
Scrib | -2.965 |
Token | ." |
Token ID | 526 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
shown | +0.185 |
Hait | +0.179 |
Whale | +0.177 |
Athena | +0.169 |
Shin | +0.168 |
Neg logit contributions | |
️ | -0.220 |
ande | -0.205 |
FIELD | -0.198 |
conflic | -0.194 |
Scrib | -0.194 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
shown | +1.964 |
Hait | +1.921 |
Whale | +1.886 |
Athena | +1.813 |
Shin | +1.798 |
Neg logit contributions | |
️ | -2.629 |
ande | -2.465 |
conflic | -2.384 |
FIELD | -2.381 |
�� | -2.320 |
Token |
|
Token ID | 198 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
shown | +0.147 |
Hait | +0.143 |
Whale | +0.141 |
Athena | +0.135 |
Shin | +0.134 |
Neg logit contributions | |
️ | -0.172 |
ande | -0.159 |
FIELD | -0.155 |
Scrib | -0.151 |
conflic | -0.149 |
Token | have |
Token ID | 423 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
shown | +0.378 |
Hait | +0.368 |
Whale | +0.362 |
Athena | +0.350 |
Shin | +0.347 |
Neg logit contributions | |
️ | -0.373 |
ande | -0.345 |
FIELD | -0.332 |
conflic | -0.328 |
Scrib | -0.324 |
Token | ? |
Token ID | 30 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
shown | +1.567 |
Hait | +1.531 |
Whale | +1.505 |
Athena | +1.454 |
Shin | +1.444 |
Neg logit contributions | |
️ | -1.823 |
ande | -1.695 |
FIELD | -1.654 |
conflic | -1.635 |
Scrib | -1.598 |
Token | That |
Token ID | 1320 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
shown | +0.514 |
Hait | +0.500 |
Whale | +0.490 |
Athena | +0.472 |
Shin | +0.469 |
Neg logit contributions | |
️ | -0.617 |
ande | -0.574 |
FIELD | -0.556 |
conflic | -0.548 |
Scrib | -0.543 |
Token | � |
Token ID | 447 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
shown | +5.080 |
Hait | +4.920 |
Whale | +4.880 |
hur | +4.752 |
Athena | +4.694 |
Neg logit contributions | |
️ | -5.837 |
ande | -5.509 |
FIELD | -5.458 |
conflic | -5.310 |
�� | -5.246 |
Token | � |
Token ID | 247 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
shown | +0.085 |
Hait | +0.084 |
Whale | +0.083 |
Athena | +0.081 |
Shin | +0.081 |
Neg logit contributions | |
️ | -0.026 |
ande | -0.022 |
FIELD | -0.020 |
conflic | -0.020 |
Scrib | -0.019 |
Token | s |
Token ID | 82 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
shown | +3.203 |
Hait | +3.015 |
Whale | +2.964 |
hur | +2.884 |
Athena | +2.860 |
Neg logit contributions | |
️ | -4.614 |
ande | -4.388 |
FIELD | -4.319 |
conflic | -4.305 |
�� | -4.191 |
Token | a |
Token ID | 257 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
shown | +2.692 |
Hait | +2.605 |
Whale | +2.568 |
Athena | +2.482 |
Shin | +2.453 |
Neg logit contributions | |
️ | -3.657 |
ande | -3.444 |
FIELD | -3.340 |
conflic | -3.318 |
Scrib | -3.242 |
Token | possibility |
Token ID | 5885 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
shown | +4.883 |
Whale | +4.725 |
Hait | +4.707 |
Shin | +4.544 |
Athena | +4.528 |
Neg logit contributions | |
️ | -5.568 |
ande | -5.300 |
FIELD | -5.204 |
conflic | -5.069 |
�� | -5.017 |
Token | . |
Token ID | 13 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
shown | +0.527 |
Hait | +0.512 |
Whale | +0.502 |
Athena | +0.483 |
Shin | +0.480 |
Neg logit contributions | |
️ | -0.655 |
ande | -0.610 |
FIELD | -0.591 |
conflic | -0.584 |
Scrib | -0.577 |
Token |
|
Token ID | 198 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
shown | +0.732 |
Hait | +0.711 |
Whale | +0.697 |
Athena | +0.671 |
Shin | +0.666 |
Neg logit contributions | |
️ | -0.947 |
ande | -0.884 |
FIELD | -0.856 |
conflic | -0.849 |
Scrib | -0.836 |
Token |
|
Token ID | 198 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
️ | +0.720 |
ande | +0.662 |
FIELD | +0.645 |
Scrib | +0.627 |
ards | +0.618 |
Neg logit contributions | |
shown | -0.652 |
Hait | -0.641 |
Whale | -0.632 |
Athena | -0.605 |
Shin | -0.597 |
Token | from |
Token ID | 422 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
️ | +2.673 |
ande | +2.461 |
Scrib | +2.362 |
FIELD | +2.354 |
conflic | +2.319 |
Neg logit contributions | |
shown | -2.275 |
Hait | -2.225 |
Whale | -2.154 |
Athena | -2.088 |
Shin | -2.071 |
Token | Boston |
Token ID | 6182 |
Feature activation | +9.64e-02 |
Pos logit contributions | |
️ | +1.569 |
ande | +1.444 |
Scrib | +1.405 |
FIELD | +1.391 |
prism | +1.361 |
Neg logit contributions | |
shown | -1.390 |
Hait | -1.342 |
Whale | -1.294 |
hur | -1.266 |
Athena | -1.258 |
Token | area |
Token ID | 1989 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
️ | +0.859 |
ande | +0.797 |
FIELD | +0.771 |
conflic | +0.757 |
Scrib | +0.756 |
Neg logit contributions | |
shown | -0.791 |
Hait | -0.769 |
Whale | -0.751 |
Athena | -0.731 |
Shin | -0.726 |
Token | writer |
Token ID | 6260 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
shown | +0.228 |
Hait | +0.221 |
Whale | +0.216 |
Athena | +0.209 |
Shin | +0.208 |
Neg logit contributions | |
️ | -0.280 |
ande | -0.260 |
FIELD | -0.251 |
conflic | -0.248 |
Scrib | -0.248 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
️ | +0.665 |
ande | +0.620 |
FIELD | +0.602 |
Scrib | +0.595 |
conflic | +0.589 |
Neg logit contributions | |
shown | -0.431 |
Hait | -0.410 |
Whale | -0.400 |
Athena | -0.382 |
hur | -0.381 |
Token | Murphy |
Token ID | 14424 |
Feature activation | +3.45e-03 |
Pos logit contributions | |
shown | +1.144 |
Hait | +1.119 |
Whale | +1.101 |
Athena | +1.057 |
Shin | +1.052 |
Neg logit contributions | |
️ | -1.456 |
ande | -1.354 |
FIELD | -1.314 |
conflic | -1.312 |
�� | -1.275 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
️ | +0.033 |
ande | +0.031 |
FIELD | +0.030 |
conflic | +0.029 |
Scrib | +0.029 |
Neg logit contributions | |
shown | -0.026 |
Hait | -0.025 |
Whale | -0.025 |
Athena | -0.024 |
Shin | -0.024 |
Token | he |
Token ID | 339 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
shown | +0.894 |
Hait | +0.870 |
Whale | +0.853 |
Athena | +0.823 |
Shin | +0.817 |
Neg logit contributions | |
️ | -1.049 |
ande | -0.975 |
FIELD | -0.944 |
conflic | -0.932 |
Scrib | -0.922 |
Token | just |
Token ID | 655 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
️ | +1.201 |
ande | +1.105 |
FIELD | +1.059 |
Scrib | +1.033 |
ards | +1.028 |
Neg logit contributions | |
shown | -1.252 |
Hait | -1.217 |
Whale | -1.204 |
Athena | -1.161 |
Shin | -1.146 |
Token | may |
Token ID | 743 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
️ | +1.247 |
ande | +1.150 |
FIELD | +1.101 |
Scrib | +1.082 |
prism | +1.070 |
Neg logit contributions | |
shown | -1.295 |
Hait | -1.257 |
Whale | -1.240 |
Athena | -1.195 |
Shin | -1.179 |
Token | have |
Token ID | 423 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
shown | +0.376 |
Hait | +0.366 |
Whale | +0.360 |
Athena | +0.347 |
Shin | +0.345 |
Neg logit contributions | |
️ | -0.421 |
ande | -0.391 |
FIELD | -0.378 |
conflic | -0.374 |
Scrib | -0.369 |
Token | , |
Token ID | 11 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
shown | +1.791 |
Hait | +1.733 |
Whale | +1.703 |
Athena | +1.638 |
Shin | +1.627 |
Neg logit contributions | |
️ | -2.311 |
ande | -2.159 |
FIELD | -2.091 |
conflic | -2.072 |
Scrib | -2.040 |
Token | apply |
Token ID | 4174 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
shown | +2.400 |
Hait | +2.333 |
Whale | +2.306 |
Athena | +2.211 |
Shin | +2.201 |
Neg logit contributions | |
️ | -3.050 |
ande | -2.865 |
FIELD | -2.771 |
conflic | -2.736 |
�� | -2.701 |
Token | _ |
Token ID | 62 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
shown | +3.929 |
Hait | +3.788 |
Whale | +3.737 |
Shin | +3.553 |
Athena | +3.534 |
Neg logit contributions | |
️ | -5.635 |
ande | -5.311 |
FIELD | -5.169 |
conflic | -5.092 |
Scrib | -5.029 |
Token | move |
Token ID | 21084 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
shown | +3.393 |
Hait | +3.178 |
Whale | +3.112 |
hur | +3.038 |
Athena | +2.976 |
Neg logit contributions | |
️ | -4.499 |
ande | -4.158 |
conflic | -4.093 |
FIELD | -4.070 |
Scrib | -4.011 |
Token | and |
Token ID | 290 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
shown | +3.466 |
Hait | +3.276 |
Whale | +3.227 |
Athena | +3.086 |
hur | +3.047 |
Neg logit contributions | |
️ | -5.816 |
ande | -5.501 |
FIELD | -5.380 |
conflic | -5.361 |
�� | -5.318 |
Token | undo |
Token ID | 23981 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
shown | +5.084 |
Whale | +5.015 |
Hait | +5.000 |
Athena | +4.814 |
Shin | +4.813 |
Neg logit contributions | |
️ | -4.797 |
ande | -4.466 |
FIELD | -4.360 |
conflic | -4.272 |
�� | -4.195 |
Token | _ |
Token ID | 62 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
shown | +4.809 |
Whale | +4.527 |
Hait | +4.474 |
Athena | +4.268 |
Shin | +4.202 |
Neg logit contributions | |
️ | -9.162 |
ande | -8.698 |
FIELD | -8.607 |
Scrib | -8.412 |
conflic | -8.384 |
Token | move |
Token ID | 21084 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
shown | +5.274 |
hur | +4.633 |
Hait | +4.504 |
Whale | +4.415 |
Shin | +4.214 |
Neg logit contributions | |
conflic | -8.560 |
️ | -8.470 |
PDATE | -8.328 |
�� | -7.887 |
Scrib | -7.862 |
Token | function |
Token ID | 2163 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
shown | +2.882 |
Hait | +2.757 |
Whale | +2.720 |
Athena | +2.617 |
Shin | +2.588 |
Neg logit contributions | |
️ | -3.983 |
ande | -3.751 |
FIELD | -3.649 |
conflic | -3.610 |
�� | -3.596 |
Token | , |
Token ID | 11 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
shown | +1.724 |
Hait | +1.669 |
Whale | +1.642 |
Athena | +1.578 |
Shin | +1.569 |
Neg logit contributions | |
️ | -2.307 |
ande | -2.164 |
FIELD | -2.096 |
conflic | -2.084 |
�� | -2.053 |
Token | we |
Token ID | 356 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
shown | +1.636 |
Hait | +1.587 |
Whale | +1.565 |
Athena | +1.505 |
Shin | +1.497 |
Neg logit contributions | |
️ | -2.062 |
ande | -1.927 |
FIELD | -1.868 |
conflic | -1.843 |
�� | -1.813 |
Token | Y |
Token ID | 575 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
️ | +0.982 |
ande | +0.911 |
FIELD | +0.884 |
Scrib | +0.870 |
�� | +0.860 |
Neg logit contributions | |
shown | -0.816 |
Hait | -0.789 |
Whale | -0.764 |
Athena | -0.743 |
hur | -0.736 |
Token | onge |
Token ID | 14220 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
shown | +1.740 |
Hait | +1.699 |
Whale | +1.675 |
Athena | +1.619 |
Shin | +1.616 |
Neg logit contributions | |
️ | -1.561 |
ande | -1.432 |
FIELD | -1.382 |
conflic | -1.377 |
Scrib | -1.340 |
Token | Cond |
Token ID | 9724 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
️ | +1.551 |
ande | +1.444 |
FIELD | +1.405 |
Scrib | +1.371 |
conflic | +1.361 |
Neg logit contributions | |
shown | -1.329 |
Hait | -1.288 |
Whale | -1.258 |
Athena | -1.213 |
hur | -1.197 |
Token | os |
Token ID | 418 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
️ | +1.569 |
ande | +1.448 |
FIELD | +1.368 |
ards | +1.326 |
Scrib | +1.316 |
Neg logit contributions | |
shown | -2.020 |
Hait | -1.986 |
Whale | -1.956 |
Athena | -1.899 |
Shin | -1.861 |
Token | to |
Token ID | 284 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
️ | +1.017 |
ande | +0.949 |
FIELD | +0.922 |
conflic | +0.909 |
Scrib | +0.899 |
Neg logit contributions | |
shown | -0.749 |
Hait | -0.728 |
Whale | -0.706 |
Athena | -0.682 |
hur | -0.673 |
Token | the |
Token ID | 262 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
shown | +1.616 |
Hait | +1.569 |
Whale | +1.542 |
Athena | +1.480 |
Shin | +1.472 |
Neg logit contributions | |
️ | -2.158 |
ande | -2.014 |
FIELD | -1.953 |
conflic | -1.933 |
Scrib | -1.906 |
Token | south |
Token ID | 5366 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
shown | +4.434 |
Whale | +4.378 |
Hait | +4.301 |
Shin | +4.139 |
Athena | +4.117 |
Neg logit contributions | |
️ | -8.172 |
ande | -7.799 |
FIELD | -7.495 |
conflic | -7.459 |
Scrib | -7.323 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
️ | +0.467 |
ande | +0.435 |
FIELD | +0.421 |
conflic | +0.413 |
Scrib | +0.409 |
Neg logit contributions | |
shown | -0.388 |
Hait | -0.378 |
Whale | -0.369 |
Athena | -0.355 |
hur | -0.353 |
Token | However |
Token ID | 2102 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
shown | +1.208 |
Hait | +1.173 |
Whale | +1.151 |
Athena | +1.107 |
Shin | +1.099 |
Neg logit contributions | |
️ | -1.569 |
ande | -1.465 |
FIELD | -1.418 |
conflic | -1.405 |
Scrib | -1.385 |
Token | , |
Token ID | 11 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
shown | +1.131 |
Hait | +1.098 |
Whale | +1.080 |
Athena | +1.036 |
Shin | +1.030 |
Neg logit contributions | |
️ | -1.586 |
ande | -1.482 |
FIELD | -1.435 |
conflic | -1.420 |
Scrib | -1.402 |
Token | the |
Token ID | 262 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
shown | +0.513 |
Hait | +0.499 |
Whale | +0.487 |
Athena | +0.470 |
Shin | +0.467 |
Neg logit contributions | |
️ | -0.620 |
ande | -0.577 |
FIELD | -0.559 |
conflic | -0.552 |
Scrib | -0.548 |
Token | ", |
Token ID | 1600 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
shown | +3.339 |
Hait | +3.074 |
Whale | +3.001 |
Shin | +2.954 |
hur | +2.931 |
Neg logit contributions | |
conflic | -6.268 |
️ | -6.257 |
PDATE | -5.966 |
ande | -5.939 |
�� | -5.848 |
Token | " |
Token ID | 366 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
shown | +1.238 |
Hait | +1.201 |
Whale | +1.183 |
Athena | +1.146 |
Shin | +1.137 |
Neg logit contributions | |
️ | -1.295 |
ande | -1.201 |
conflic | -1.158 |
FIELD | -1.154 |
Scrib | -1.126 |
Token | -- |
Token ID | 438 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
shown | +3.701 |
Hait | +3.407 |
Whale | +3.282 |
hur | +3.263 |
Athena | +3.157 |
Neg logit contributions | |
️ | -6.547 |
conflic | -6.374 |
ande | -6.139 |
PDATE | -6.108 |
�� | -6.080 |
Token | images |
Token ID | 17566 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
shown | +3.592 |
Hait | +3.092 |
hur | +3.062 |
Whale | +3.005 |
Athena | +2.874 |
Neg logit contributions | |
️ | -6.983 |
conflic | -6.754 |
PDATE | -6.538 |
ande | -6.440 |
Scrib | -6.408 |
Token | ", |
Token ID | 1600 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
shown | +2.627 |
Hait | +2.453 |
Whale | +2.405 |
Shin | +2.341 |
Athena | +2.338 |
Neg logit contributions | |
️ | -4.611 |
conflic | -4.458 |
ande | -4.363 |
�� | -4.236 |
PDATE | -4.234 |
Token | required |
Token ID | 2672 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
shown | +5.686 |
Whale | +5.062 |
Athena | +5.047 |
Hait | +4.996 |
Shin | +4.870 |
Neg logit contributions | |
️ | -9.198 |
ande | -8.753 |
conflic | -8.441 |
FIELD | -8.364 |
�� | -8.320 |
Token | = |
Token ID | 28 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
shown | +3.742 |
Hait | +3.299 |
Whale | +3.190 |
Athena | +3.102 |
は | +3.097 |
Neg logit contributions | |
conflic | -9.705 |
PDATE | -9.272 |
️ | -9.020 |
veter | -8.939 |
�� | -8.937 |
Token | True |
Token ID | 17821 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
shown | +2.820 |
Hait | +2.708 |
Whale | +2.689 |
Athena | +2.615 |
hur | +2.599 |
Neg logit contributions | |
️ | -2.119 |
conflic | -2.003 |
ande | -1.983 |
�� | -1.868 |
Scrib | -1.854 |
Token | , |
Token ID | 11 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
shown | +4.334 |
Hait | +3.940 |
Whale | +3.933 |
Athena | +3.894 |
Shin | +3.892 |
Neg logit contributions | |
conflic | -8.743 |
PDATE | -8.266 |
️ | -8.186 |
veter | -8.004 |
ande | -7.936 |
Token | help |
Token ID | 1037 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
shown | +3.273 |
Hait | +3.177 |
Athena | +2.986 |
Shin | +2.984 |
Whale | +2.978 |
Neg logit contributions | |
️ | -7.904 |
conflic | -7.643 |
ande | -7.570 |
�� | -7.449 |
FIELD | -7.375 |
Token | =" |
Token ID | 2625 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
shown | +1.143 |
Hait | +1.086 |
Whale | +1.051 |
Athena | +1.002 |
Shin | +0.991 |
Neg logit contributions | |
️ | -2.483 |
ande | -2.355 |
conflic | -2.316 |
FIELD | -2.282 |
Scrib | -2.247 |
Token | send |
Token ID | 3758 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
shown | +4.746 |
Hait | +4.635 |
Whale | +4.625 |
Athena | +4.477 |
Shin | +4.392 |
Neg logit contributions | |
️ | -4.865 |
ande | -4.645 |
conflic | -4.425 |
FIELD | -4.385 |
�� | -4.301 |
Token | a |
Token ID | 257 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
shown | +2.354 |
Whale | +2.258 |
Hait | +2.244 |
Athena | +2.151 |
Shin | +2.131 |
Neg logit contributions | |
️ | -3.776 |
ande | -3.567 |
conflic | -3.464 |
FIELD | -3.460 |
�� | -3.419 |
Token | link |
Token ID | 2792 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
shown | +2.991 |
Whale | +2.907 |
Shin | +2.735 |
Athena | +2.631 |
Hait | +2.576 |
Neg logit contributions | |
️ | -8.929 |
ande | -8.549 |
conflic | -8.482 |
FIELD | -8.475 |
�� | -8.414 |
Token | using |
Token ID | 1262 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
shown | +1.774 |
Hait | +1.725 |
Whale | +1.686 |
Athena | +1.616 |
Shin | +1.601 |
Neg logit contributions | |
️ | -2.549 |
ande | -2.387 |
FIELD | -2.321 |
conflic | -2.285 |
Scrib | -2.272 |
Token | your |
Token ID | 534 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
shown | +4.243 |
Whale | +3.982 |
Hait | +3.966 |
Athena | +3.855 |
Shin | +3.808 |
Neg logit contributions | |
️ | -5.172 |
ande | -4.844 |
conflic | -4.724 |
FIELD | -4.644 |
�� | -4.601 |
Token | email |
Token ID | 3053 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
shown | +1.951 |
Hait | +1.845 |
Whale | +1.805 |
Athena | +1.753 |
Shin | +1.720 |
Neg logit contributions | |
️ | -3.662 |
ande | -3.454 |
FIELD | -3.373 |
conflic | -3.355 |
�� | -3.305 |
Token | application |
Token ID | 3586 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
shown | +6.855 |
Athena | +6.683 |
Hait | +6.597 |
Shin | +6.589 |
Whale | +6.441 |
Neg logit contributions | |
️ | -7.340 |
ande | -6.768 |
�� | -6.706 |
FIELD | -6.645 |
conflic | -6.476 |
Token |
|
Token ID | 198 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
shown | +3.211 |
Whale | +3.033 |
Hait | +3.018 |
Shin | +2.930 |
Athena | +2.927 |
Neg logit contributions | |
️ | -4.556 |
ande | -4.256 |
conflic | -4.238 |
�� | -4.086 |
FIELD | -4.018 |
Token |
|
Token ID | 198 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
shown | +2.094 |
Hait | +2.001 |
Whale | +1.965 |
Shin | +1.903 |
Athena | +1.901 |
Neg logit contributions | |
️ | -2.810 |
conflic | -2.696 |
ande | -2.649 |
�� | -2.541 |
PDATE | -2.525 |
Token | Ass |
Token ID | 8021 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
️ | +0.187 |
ande | +0.172 |
FIELD | +0.167 |
Scrib | +0.160 |
conflic | +0.160 |
Neg logit contributions | |
shown | -0.203 |
Hait | -0.200 |
Whale | -0.197 |
Athena | -0.191 |
Shin | -0.189 |
Token | assin |
Token ID | 44961 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
️ | +1.792 |
ande | +1.687 |
FIELD | +1.578 |
Scrib | +1.555 |
ards | +1.545 |
Neg logit contributions | |
shown | -2.089 |
Hait | -2.033 |
Whale | -1.983 |
Athena | -1.947 |
Shin | -1.930 |
Token | WASHINGTON |
Token ID | 21793 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
️ | +3.493 |
FIELD | +3.231 |
ande | +3.197 |
LC | +3.010 |
Scrib | +2.966 |
Neg logit contributions | |
Whale | -3.662 |
Hait | -3.659 |
shown | -3.618 |
Athena | -3.485 |
Shin | -3.459 |
Token | — |
Token ID | 851 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
️ | +0.619 |
ande | +0.569 |
FIELD | +0.558 |
Scrib | +0.542 |
conflic | +0.537 |
Neg logit contributions | |
shown | -0.582 |
Hait | -0.562 |
Whale | -0.553 |
Athena | -0.533 |
hur | -0.530 |
Token | A |
Token ID | 317 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
️ | +1.631 |
ande | +1.506 |
Scrib | +1.473 |
FIELD | +1.466 |
prism | +1.412 |
Neg logit contributions | |
shown | -1.250 |
Hait | -1.174 |
Whale | -1.158 |
hur | -1.130 |
Athena | -1.121 |
Token | Cy |
Token ID | 5934 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
️ | +1.970 |
ande | +1.838 |
FIELD | +1.766 |
Scrib | +1.753 |
conflic | +1.733 |
Neg logit contributions | |
shown | -1.837 |
Hait | -1.762 |
Whale | -1.729 |
Athena | -1.689 |
hur | -1.660 |
Token | gn |
Token ID | 4593 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
shown | +3.123 |
Hait | +3.055 |
Whale | +3.007 |
Athena | +2.916 |
Shin | +2.915 |
Neg logit contributions | |
️ | -2.782 |
ande | -2.547 |
FIELD | -2.479 |
conflic | -2.450 |
Scrib | -2.382 |
Token | us |
Token ID | 385 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
shown | +1.721 |
Hait | +1.675 |
Whale | +1.647 |
Athena | +1.588 |
Shin | +1.578 |
Neg logit contributions | |
️ | -1.853 |
ande | -1.724 |
FIELD | -1.662 |
conflic | -1.637 |
Scrib | -1.620 |
Token | cargo |
Token ID | 15892 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
Whale | +6.101 |
shown | +6.071 |
Hait | +6.059 |
Shin | +5.852 |
Athena | +5.844 |
Neg logit contributions | |
️ | -7.165 |
ande | -6.465 |
conflic | -6.302 |
FIELD | -6.302 |
�� | -6.273 |
Token | mission |
Token ID | 4365 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
shown | +2.186 |
Hait | +2.103 |
Whale | +2.075 |
Athena | +1.978 |
Shin | +1.953 |
Neg logit contributions | |
️ | -4.128 |
ande | -3.881 |
FIELD | -3.775 |
conflic | -3.753 |
Scrib | -3.700 |
Token | to |
Token ID | 284 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
shown | +2.194 |
Hait | +2.142 |
Whale | +2.106 |
Athena | +2.024 |
Shin | +2.011 |
Neg logit contributions | |
️ | -2.838 |
ande | -2.638 |
FIELD | -2.558 |
conflic | -2.557 |
�� | -2.508 |
Token | the |
Token ID | 262 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
shown | +1.634 |
Hait | +1.591 |
Whale | +1.561 |
Athena | +1.503 |
Shin | +1.493 |
Neg logit contributions | |
️ | -2.044 |
ande | -1.905 |
FIELD | -1.845 |
conflic | -1.826 |
Scrib | -1.801 |
Token | International |
Token ID | 4037 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
Hait | +4.770 |
shown | +4.751 |
Whale | +4.696 |
Shin | +4.561 |
Athena | +4.539 |
Neg logit contributions | |
️ | -5.901 |
ande | -5.443 |
FIELD | -5.248 |
conflic | -5.217 |
�� | -5.131 |