Token | milk |
Token ID | 7545 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
idas | +1.195 |
Smile | +1.178 |
Babel | +1.115 |
tto | +1.106 |
blush | +1.105 |
Neg logit contributions | |
imation | -2.925 |
�� | -2.869 |
uthor | -2.762 |
ablishment | -2.691 |
obin | -2.689 |
Token | , |
Token ID | 11 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
idas | +1.299 |
Smile | +1.289 |
Babel | +1.251 |
tto | +1.245 |
blush | +1.245 |
Neg logit contributions | |
imation | -1.552 |
�� | -1.517 |
uthor | -1.440 |
ablishment | -1.389 |
obin | -1.388 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
idas | +0.124 |
Smile | +0.123 |
Babel | +0.119 |
ラン | +0.118 |
tto | +0.118 |
Neg logit contributions | |
imation | -0.135 |
�� | -0.131 |
uthor | -0.124 |
obin | -0.120 |
ablishment | -0.119 |
Token | teaspoons |
Token ID | 47234 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
imation | +1.933 |
�� | +1.879 |
uthor | +1.796 |
ablishment | +1.733 |
usion | +1.733 |
Neg logit contributions | |
idas | -1.404 |
Smile | -1.387 |
Babel | -1.348 |
ラン | -1.340 |
tto | -1.311 |
Token | of |
Token ID | 286 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
idas | +0.555 |
Smile | +0.549 |
Babel | +0.529 |
ラン | +0.527 |
tto | +0.521 |
Neg logit contributions | |
imation | -0.756 |
�� | -0.731 |
uthor | -0.696 |
obin | -0.675 |
ablishment | -0.673 |
Token | cinnamon |
Token ID | 29181 |
Feature activation | +8.34e+00 |
Pos logit contributions | |
idas | +0.526 |
Smile | +0.517 |
Babel | +0.496 |
ラン | +0.495 |
tto | +0.489 |
Neg logit contributions | |
imation | -0.905 |
�� | -0.879 |
uthor | -0.840 |
obin | -0.820 |
ablishment | -0.815 |
Token | , |
Token ID | 11 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
Smile | +4.974 |
blush | +4.959 |
idas | +4.930 |
Babel | +4.791 |
tto | +4.742 |
Neg logit contributions | |
�� | -7.014 |
imation | -6.940 |
uthor | -6.637 |
ablishment | -6.452 |
obin | -6.385 |
Token | and |
Token ID | 290 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
idas | +0.564 |
Smile | +0.559 |
Babel | +0.544 |
tto | +0.538 |
ラン | +0.536 |
Neg logit contributions | |
imation | -0.623 |
�� | -0.606 |
uthor | -0.574 |
obin | -0.556 |
ablishment | -0.553 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
idas | +0.202 |
Smile | +0.200 |
Babel | +0.195 |
ラン | +0.193 |
tto | +0.193 |
Neg logit contributions | |
imation | -0.201 |
�� | -0.195 |
uthor | -0.184 |
obin | -0.178 |
ablishment | -0.177 |
Token | he |
Token ID | 339 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
imation | +1.413 |
�� | +1.366 |
uthor | +1.297 |
ablishment | +1.251 |
usion | +1.251 |
Neg logit contributions | |
idas | -1.249 |
Smile | -1.235 |
Babel | -1.207 |
ラン | -1.197 |
tto | -1.176 |
Token | aping |
Token ID | 9269 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
idas | +0.836 |
Smile | +0.832 |
Babel | +0.819 |
ラン | +0.815 |
blush | +0.810 |
Neg logit contributions | |
imation | -0.250 |
�� | -0.229 |
uthor | -0.200 |
obin | -0.184 |
ablishment | -0.182 |
Token | most |
Token ID | 749 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
idas | +0.420 |
Smile | +0.415 |
Babel | +0.401 |
ラン | +0.396 |
tto | +0.396 |
Neg logit contributions | |
imation | -0.616 |
�� | -0.600 |
uthor | -0.573 |
obin | -0.557 |
ablishment | -0.554 |
Token | in |
Token ID | 287 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
idas | +1.754 |
Smile | +1.744 |
Babel | +1.688 |
tto | +1.667 |
ラン | +1.661 |
Neg logit contributions | |
imation | -2.181 |
�� | -2.124 |
uthor | -2.016 |
obin | -1.953 |
ablishment | -1.945 |
Token | team |
Token ID | 1074 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
idas | +0.539 |
Smile | +0.534 |
Babel | +0.519 |
ラン | +0.514 |
tto | +0.513 |
Neg logit contributions | |
imation | -0.581 |
�� | -0.563 |
uthor | -0.533 |
obin | -0.516 |
ablishment | -0.513 |
Token | history |
Token ID | 2106 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
imation | +0.359 |
�� | +0.349 |
uthor | +0.333 |
obin | +0.323 |
ablishment | +0.322 |
Neg logit contributions | |
idas | -0.246 |
Smile | -0.244 |
Babel | -0.237 |
ラン | -0.235 |
tto | -0.235 |
Token | ( |
Token ID | 357 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
idas | +0.867 |
Smile | +0.858 |
Babel | +0.831 |
tto | +0.822 |
ラン | +0.821 |
Neg logit contributions | |
imation | -1.060 |
�� | -1.031 |
uthor | -0.980 |
obin | -0.949 |
ablishment | -0.945 |
Token | Patri |
Token ID | 9606 |
Feature activation | +7.74e+00 |
Pos logit contributions | |
idas | +0.809 |
Smile | +0.801 |
Babel | +0.775 |
ラン | +0.765 |
tto | +0.765 |
Neg logit contributions | |
imation | -1.090 |
�� | -1.061 |
uthor | -1.011 |
obin | -0.981 |
ablishment | -0.976 |
Token | k |
Token ID | 74 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
idas | +4.338 |
Smile | +4.074 |
Babel | +4.030 |
tto | +3.992 |
Wend | +3.930 |
Neg logit contributions | |
imation | -7.006 |
�� | -6.754 |
uthor | -6.648 |
� | -6.285 |
obin | -6.282 |
Token | Elias |
Token ID | 41462 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
idas | +0.669 |
Smile | +0.660 |
Babel | +0.619 |
tto | +0.602 |
ラン | +0.601 |
Neg logit contributions | |
imation | -1.912 |
�� | -1.875 |
uthor | -1.813 |
obin | -1.768 |
ablishment | -1.763 |
Token | , |
Token ID | 837 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
idas | +0.548 |
Smile | +0.543 |
Babel | +0.525 |
ラン | +0.520 |
tto | +0.519 |
Neg logit contributions | |
imation | -0.638 |
�� | -0.623 |
uthor | -0.590 |
obin | -0.570 |
ablishment | -0.570 |
Token | Claude |
Token ID | 40559 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
idas | +0.390 |
Smile | +0.385 |
Babel | +0.371 |
ラン | +0.367 |
tto | +0.366 |
Neg logit contributions | |
imation | -0.609 |
�� | -0.594 |
uthor | -0.567 |
obin | -0.552 |
ablishment | -0.549 |
Token | Lem |
Token ID | 20607 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Smile | +1.909 |
idas | +1.907 |
Babel | +1.849 |
tto | +1.793 |
ラン | +1.777 |
Neg logit contributions | |
imation | -3.002 |
�� | -2.927 |
uthor | -2.801 |
obin | -2.703 |
ablishment | -2.702 |
Token | the |
Token ID | 262 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
imation | +0.462 |
�� | +0.448 |
uthor | +0.424 |
obin | +0.409 |
ablishment | +0.407 |
Neg logit contributions | |
idas | -0.459 |
Smile | -0.455 |
Babel | -0.443 |
tto | -0.438 |
ラン | -0.438 |
Token | minimum |
Token ID | 5288 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
imation | +0.271 |
�� | +0.263 |
uthor | +0.250 |
obin | +0.242 |
ablishment | +0.241 |
Neg logit contributions | |
idas | -0.223 |
Smile | -0.220 |
Babel | -0.213 |
ラン | -0.212 |
tto | -0.211 |
Token | required |
Token ID | 2672 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
idas | +0.350 |
Smile | +0.347 |
Babel | +0.334 |
tto | +0.329 |
blush | +0.329 |
Neg logit contributions | |
imation | -0.501 |
�� | -0.488 |
uthor | -0.467 |
obin | -0.454 |
ablishment | -0.450 |
Token | for |
Token ID | 329 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
idas | +1.464 |
Smile | +1.461 |
blush | +1.399 |
Babel | +1.398 |
tto | +1.389 |
Neg logit contributions | |
imation | -1.978 |
�� | -1.926 |
uthor | -1.852 |
obin | -1.794 |
ablishment | -1.774 |
Token | a |
Token ID | 257 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
imation | +0.197 |
�� | +0.191 |
uthor | +0.182 |
obin | +0.176 |
ablishment | +0.175 |
Neg logit contributions | |
idas | -0.158 |
Smile | -0.157 |
Babel | -0.152 |
tto | -0.150 |
ラン | -0.150 |
Token | binding |
Token ID | 12765 |
Feature activation | +7.66e+00 |
Pos logit contributions | |
idas | +0.165 |
Smile | +0.165 |
Babel | +0.159 |
tto | +0.157 |
blush | +0.157 |
Neg logit contributions | |
imation | -0.201 |
�� | -0.195 |
uthor | -0.186 |
obin | -0.180 |
ablishment | -0.180 |
Token | referendum |
Token ID | 11467 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Smile | +5.018 |
idas | +4.921 |
Babel | +4.903 |
blush | +4.784 |
tto | +4.745 |
Neg logit contributions | |
imation | -6.043 |
�� | -5.865 |
uthor | -5.562 |
ablishment | -5.524 |
obin | -5.457 |
Token | . |
Token ID | 13 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
idas | +1.186 |
Smile | +1.173 |
Babel | +1.138 |
tto | +1.129 |
blush | +1.124 |
Neg logit contributions | |
imation | -1.456 |
�� | -1.425 |
uthor | -1.355 |
obin | -1.316 |
ablishment | -1.297 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
imation | +0.350 |
�� | +0.340 |
uthor | +0.322 |
obin | +0.311 |
ablishment | +0.310 |
Neg logit contributions | |
idas | -0.325 |
Smile | -0.322 |
Babel | -0.313 |
ラン | -0.309 |
tto | -0.309 |
Token |
|
Token ID | 198 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
imation | +0.799 |
�� | +0.772 |
uthor | +0.731 |
obin | +0.710 |
ablishment | +0.705 |
Neg logit contributions | |
idas | -0.722 |
Smile | -0.714 |
Babel | -0.694 |
blush | -0.688 |
ラン | -0.686 |
Token | In |
Token ID | 818 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
imation | +0.384 |
�� | +0.371 |
uthor | +0.350 |
obin | +0.338 |
ablishment | +0.336 |
Neg logit contributions | |
idas | -0.410 |
Smile | -0.406 |
Babel | -0.396 |
ラン | -0.392 |
tto | -0.391 |
Token | Santiago |
Token ID | 34802 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
imation | +0.204 |
�� | +0.198 |
uthor | +0.188 |
obin | +0.183 |
ablishment | +0.182 |
Neg logit contributions | |
idas | -0.158 |
Smile | -0.156 |
Babel | -0.151 |
ラン | -0.150 |
tto | -0.149 |
Token | de |
Token ID | 390 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
imation | +2.027 |
�� | +1.967 |
uthor | +1.869 |
obin | +1.820 |
ablishment | +1.810 |
Neg logit contributions | |
idas | -1.585 |
Smile | -1.564 |
ラン | -1.520 |
Babel | -1.514 |
tto | -1.499 |
Token | Cuba |
Token ID | 14159 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
idas | +1.396 |
Smile | +1.387 |
Babel | +1.351 |
tto | +1.325 |
ラン | +1.321 |
Neg logit contributions | |
imation | -1.771 |
�� | -1.733 |
uthor | -1.649 |
ablishment | -1.600 |
obin | -1.588 |
Token | - |
Token ID | 12 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
imation | +2.008 |
�� | +1.942 |
uthor | +1.851 |
obin | +1.800 |
usion | +1.783 |
Neg logit contributions | |
idas | -1.718 |
Smile | -1.696 |
Babel | -1.652 |
ラン | -1.641 |
tto | -1.629 |
Token | based |
Token ID | 3106 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
imation | +0.286 |
�� | +0.278 |
uthor | +0.265 |
obin | +0.256 |
ablishment | +0.255 |
Neg logit contributions | |
idas | -0.224 |
Smile | -0.221 |
Babel | -0.214 |
ラン | -0.212 |
tto | -0.212 |
Token | Patri |
Token ID | 9606 |
Feature activation | +7.55e+00 |
Pos logit contributions | |
imation | +1.699 |
�� | +1.646 |
uthor | +1.566 |
obin | +1.531 |
usion | +1.512 |
Neg logit contributions | |
idas | -1.334 |
Smile | -1.309 |
Babel | -1.280 |
ラン | -1.278 |
tto | -1.263 |
Token | otic |
Token ID | 6210 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
idas | +4.084 |
Smile | +3.843 |
tto | +3.803 |
Babel | +3.643 |
ten | +3.562 |
Neg logit contributions | |
imation | -6.757 |
�� | -6.742 |
uthor | -6.379 |
nikov | -6.115 |
vier | -6.077 |
Token | Union |
Token ID | 4479 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
idas | +1.267 |
Smile | +1.262 |
Babel | +1.218 |
tto | +1.202 |
ラン | +1.198 |
Neg logit contributions | |
imation | -1.496 |
�� | -1.457 |
uthor | -1.392 |
obin | -1.342 |
ablishment | -1.332 |
Token | of |
Token ID | 286 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
idas | +1.839 |
Smile | +1.817 |
Babel | +1.742 |
tto | +1.728 |
blush | +1.707 |
Neg logit contributions | |
imation | -2.254 |
�� | -2.200 |
uthor | -2.094 |
obin | -2.034 |
ablishment | -2.004 |
Token | Cuba |
Token ID | 14159 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
idas | +0.570 |
Smile | +0.564 |
Babel | +0.544 |
tto | +0.536 |
ラン | +0.536 |
Neg logit contributions | |
imation | -0.855 |
�� | -0.833 |
uthor | -0.795 |
obin | -0.773 |
ablishment | -0.769 |
Token | , |
Token ID | 11 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
imation | +1.395 |
�� | +1.356 |
uthor | +1.287 |
obin | +1.242 |
ablishment | +1.237 |
Neg logit contributions | |
idas | -1.268 |
Smile | -1.255 |
Babel | -1.224 |
ラン | -1.212 |
tto | -1.207 |
Token | agent |
Token ID | 5797 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
idas | +1.181 |
Smile | +1.174 |
Babel | +1.142 |
tto | +1.125 |
ラン | +1.124 |
Neg logit contributions | |
imation | -1.319 |
�� | -1.278 |
uthor | -1.214 |
obin | -1.175 |
ablishment | -1.170 |
Token | who |
Token ID | 508 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
idas | +0.496 |
Smile | +0.491 |
Babel | +0.476 |
ラン | +0.471 |
tto | +0.471 |
Neg logit contributions | |
imation | -0.582 |
�� | -0.566 |
uthor | -0.537 |
obin | -0.520 |
ablishment | -0.518 |
Token | happened |
Token ID | 3022 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
idas | +0.733 |
Smile | +0.727 |
Babel | +0.708 |
tto | +0.698 |
blush | +0.696 |
Neg logit contributions | |
imation | -0.804 |
�� | -0.782 |
uthor | -0.738 |
obin | -0.716 |
ablishment | -0.715 |
Token | to |
Token ID | 284 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
idas | +2.405 |
Smile | +2.376 |
Babel | +2.303 |
tto | +2.284 |
ラン | +2.273 |
Neg logit contributions | |
imation | -3.014 |
�� | -2.950 |
uthor | -2.797 |
obin | -2.710 |
ablishment | -2.698 |
Token | represent |
Token ID | 2380 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
idas | +0.457 |
Smile | +0.451 |
Babel | +0.437 |
ラン | +0.434 |
tto | +0.432 |
Neg logit contributions | |
imation | -0.579 |
�� | -0.562 |
uthor | -0.536 |
obin | -0.520 |
ablishment | -0.516 |
Token | Patrick |
Token ID | 9925 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
idas | +0.469 |
Smile | +0.461 |
Babel | +0.446 |
ラン | +0.443 |
tto | +0.441 |
Neg logit contributions | |
imation | -0.678 |
�� | -0.660 |
uthor | -0.631 |
obin | -0.613 |
ablishment | -0.608 |
Token | O |
Token ID | 440 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
idas | +3.787 |
Smile | +3.767 |
Babel | +3.637 |
tto | +3.528 |
blush | +3.523 |
Neg logit contributions | |
imation | -7.149 |
�� | -6.999 |
uthor | -6.679 |
ablishment | -6.465 |
usion | -6.439 |
Token | ' |
Token ID | 6 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
idas | +2.081 |
Smile | +2.053 |
Babel | +1.991 |
tto | +1.988 |
ラン | +1.966 |
Neg logit contributions | |
imation | -2.163 |
�� | -2.118 |
uthor | -1.990 |
ablishment | -1.917 |
obin | -1.913 |
Token | Brian |
Token ID | 24761 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
idas | +0.283 |
Smile | +0.280 |
Babel | +0.273 |
ラン | +0.271 |
blush | +0.270 |
Neg logit contributions | |
imation | -0.255 |
�� | -0.246 |
uthor | -0.233 |
obin | -0.226 |
ablishment | -0.222 |
Token | . |
Token ID | 13 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
idas | +2.163 |
Smile | +2.151 |
Babel | +2.072 |
tto | +2.055 |
blush | +2.041 |
Neg logit contributions | |
imation | -2.863 |
�� | -2.800 |
uthor | -2.646 |
ablishment | -2.578 |
obin | -2.571 |
Token | He |
Token ID | 679 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
idas | +0.448 |
Smile | +0.442 |
Babel | +0.429 |
ラン | +0.426 |
tto | +0.425 |
Neg logit contributions | |
imation | -0.555 |
�� | -0.539 |
uthor | -0.513 |
obin | -0.497 |
ablishment | -0.495 |
Token | Nikol |
Token ID | 48127 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
imation | +0.246 |
�� | +0.239 |
uthor | +0.229 |
obin | +0.223 |
usion | +0.221 |
Neg logit contributions | |
idas | -0.157 |
Smile | -0.153 |
ラン | -0.149 |
Babel | -0.148 |
tto | -0.146 |
Token | aj |
Token ID | 1228 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
imation | +0.787 |
�� | +0.769 |
uthor | +0.717 |
obin | +0.701 |
usion | +0.684 |
Neg logit contributions | |
Smile | -1.047 |
idas | -1.045 |
ラン | -1.019 |
Babel | -1.017 |
tto | -1.013 |
Token | Eh |
Token ID | 31480 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
imation | +0.231 |
�� | +0.230 |
uthor | +0.209 |
obin | +0.204 |
usion | +0.204 |
Neg logit contributions | |
idas | -0.282 |
ラン | -0.281 |
Smile | -0.277 |
tto | -0.276 |
blush | -0.275 |
Token | lers |
Token ID | 8116 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
imation | +0.848 |
�� | +0.824 |
uthor | +0.783 |
obin | +0.781 |
nikov | +0.771 |
Neg logit contributions | |
idas | -0.584 |
Smile | -0.573 |
Babel | -0.564 |
ラン | -0.554 |
blush | -0.551 |
Token | and |
Token ID | 290 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
idas | +0.264 |
Smile | +0.260 |
Babel | +0.254 |
tto | +0.251 |
ラン | +0.251 |
Neg logit contributions | |
imation | -0.317 |
�� | -0.308 |
uthor | -0.292 |
obin | -0.283 |
ablishment | -0.281 |
Token | Patri |
Token ID | 9606 |
Feature activation | +7.46e+00 |
Pos logit contributions | |
idas | +0.218 |
Smile | +0.215 |
Babel | +0.207 |
ラン | +0.207 |
tto | +0.206 |
Neg logit contributions | |
imation | -0.347 |
�� | -0.339 |
uthor | -0.324 |
obin | -0.315 |
usion | -0.312 |
Token | k |
Token ID | 74 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
idas | +4.136 |
Smile | +3.953 |
Babel | +3.894 |
tto | +3.888 |
Wend | +3.807 |
Neg logit contributions | |
imation | -6.785 |
�� | -6.517 |
uthor | -6.400 |
� | -6.105 |
obin | -6.099 |
Token | L |
Token ID | 406 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
idas | +0.960 |
Smile | +0.951 |
Babel | +0.919 |
tto | +0.907 |
ラン | +0.907 |
Neg logit contributions | |
imation | -1.261 |
�� | -1.227 |
uthor | -1.170 |
obin | -1.134 |
ablishment | -1.129 |
Token | aine |
Token ID | 5718 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
idas | +0.196 |
Smile | +0.193 |
tto | +0.187 |
Babel | +0.187 |
ラン | +0.185 |
Neg logit contributions | |
imation | -0.133 |
�� | -0.130 |
uthor | -0.120 |
ablishment | -0.114 |
obin | -0.113 |
Token | carrying |
Token ID | 6872 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
imation | +0.754 |
�� | +0.730 |
uthor | +0.692 |
obin | +0.673 |
usion | +0.669 |
Neg logit contributions | |
idas | -0.641 |
Smile | -0.634 |
Babel | -0.618 |
ラン | -0.612 |
tto | -0.611 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
idas | +1.295 |
Smile | +1.284 |
Babel | +1.247 |
tto | +1.231 |
ラン | +1.229 |
Neg logit contributions | |
imation | -1.425 |
�� | -1.383 |
uthor | -1.313 |
obin | -1.268 |
ablishment | -1.264 |
Token | AV |
Token ID | 10116 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
idas | +0.945 |
Smile | +0.941 |
Babel | +0.915 |
tto | +0.911 |
ラン | +0.911 |
Neg logit contributions | |
imation | -0.745 |
�� | -0.723 |
uthor | -0.684 |
ablishment | -0.649 |
obin | -0.648 |
Token | C |
Token ID | 34 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
imation | +1.161 |
�� | +1.108 |
uthor | +1.030 |
obin | +1.000 |
usion | +0.983 |
Neg logit contributions | |
idas | -1.725 |
Smile | -1.709 |
Babel | -1.673 |
blush | -1.660 |
ラン | -1.656 |
Token | : |
Token ID | 25 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
imation | +0.333 |
�� | +0.315 |
uthor | +0.298 |
obin | +0.292 |
usion | +0.289 |
Neg logit contributions | |
idas | -0.352 |
Smile | -0.347 |
Babel | -0.339 |
ラン | -0.338 |
blush | -0.337 |
Token | You |
Token ID | 921 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
idas | +0.093 |
Smile | +0.091 |
ラン | +0.088 |
Babel | +0.088 |
blush | +0.088 |
Neg logit contributions | |
imation | -0.095 |
�� | -0.092 |
uthor | -0.087 |
obin | -0.085 |
ablishment | -0.084 |
Token | have |
Token ID | 423 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
idas | +1.463 |
Smile | +1.454 |
Babel | +1.405 |
tto | +1.393 |
blush | +1.391 |
Neg logit contributions | |
imation | -1.741 |
�� | -1.703 |
uthor | -1.610 |
ablishment | -1.557 |
obin | -1.556 |
Token | Patrick |
Token ID | 9925 |
Feature activation | +7.42e+00 |
Pos logit contributions | |
imation | +0.754 |
�� | +0.736 |
uthor | +0.701 |
obin | +0.674 |
usion | +0.668 |
Neg logit contributions | |
idas | -0.659 |
Smile | -0.643 |
ラン | -0.629 |
Babel | -0.623 |
tto | -0.623 |
Token | War |
Token ID | 1810 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Smile | +4.485 |
idas | +4.446 |
Babel | +4.329 |
blush | +4.231 |
tto | +4.217 |
Neg logit contributions | |
imation | -6.415 |
�� | -6.257 |
uthor | -5.981 |
ablishment | -5.797 |
obin | -5.757 |
Token | bur |
Token ID | 6236 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
idas | +0.967 |
Smile | +0.956 |
Babel | +0.921 |
tto | +0.912 |
ラン | +0.910 |
Neg logit contributions | |
imation | -1.465 |
�� | -1.428 |
uthor | -1.364 |
obin | -1.323 |
ablishment | -1.320 |
Token | ton |
Token ID | 1122 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
idas | +0.906 |
Smile | +0.889 |
Babel | +0.836 |
ラン | +0.816 |
tto | +0.816 |
Neg logit contributions | |
imation | -2.948 |
�� | -2.888 |
uthor | -2.787 |
obin | -2.729 |
ablishment | -2.717 |
Token | playing |
Token ID | 2712 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
idas | +1.137 |
Smile | +1.128 |
Babel | +1.092 |
tto | +1.079 |
ラン | +1.077 |
Neg logit contributions | |
imation | -1.364 |
�� | -1.330 |
uthor | -1.262 |
obin | -1.220 |
ablishment | -1.218 |
Token | Lem |
Token ID | 20607 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
idas | +1.989 |
Smile | +1.981 |
Babel | +1.915 |
tto | +1.886 |
blush | +1.876 |
Neg logit contributions | |
imation | -2.835 |
�� | -2.753 |
uthor | -2.630 |
ablishment | -2.551 |
obin | -2.543 |
Token | � |
Token ID | 564 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
idas | +2.589 |
Smile | +2.543 |
Babel | +2.460 |
blush | +2.434 |
ラン | +2.430 |
Neg logit contributions | |
imation | -2.971 |
�� | -2.902 |
uthor | -2.727 |
obin | -2.661 |
ablishment | -2.659 |
Token | � |
Token ID | 250 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
idas | +1.017 |
Smile | +1.006 |
Babel | +0.978 |
ラン | +0.974 |
tto | +0.974 |
Neg logit contributions | |
imation | -0.924 |
�� | -0.891 |
uthor | -0.845 |
obin | -0.815 |
ablishment | -0.811 |
Token | the |
Token ID | 1169 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
idas | +0.550 |
Smile | +0.541 |
Babel | +0.524 |
tto | +0.521 |
ラン | +0.521 |
Neg logit contributions | |
imation | -0.660 |
�� | -0.643 |
uthor | -0.607 |
obin | -0.590 |
ablishment | -0.589 |
Token | exploitation |
Token ID | 17238 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
idas | +0.401 |
Smile | +0.397 |
Babel | +0.383 |
ラン | +0.377 |
tto | +0.377 |
Neg logit contributions | |
imation | -0.573 |
�� | -0.560 |
uthor | -0.533 |
obin | -0.518 |
ablishment | -0.516 |
Token | of |
Token ID | 286 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
imation | +0.856 |
�� | +0.827 |
uthor | +0.789 |
obin | +0.762 |
ablishment | +0.761 |
Neg logit contributions | |
idas | -0.732 |
Smile | -0.721 |
Babel | -0.703 |
tto | -0.694 |
ラン | -0.692 |
Token | adjunct |
Token ID | 44737 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
idas | +0.104 |
Smile | +0.103 |
Babel | +0.100 |
ラン | +0.099 |
tto | +0.098 |
Neg logit contributions | |
imation | -0.126 |
�� | -0.122 |
uthor | -0.116 |
obin | -0.112 |
ablishment | -0.112 |
Token | labor |
Token ID | 4827 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
idas | +4.192 |
Smile | +4.114 |
ラン | +3.998 |
Babel | +3.963 |
blush | +3.918 |
Neg logit contributions | |
imation | -6.481 |
�� | -6.345 |
uthor | -6.030 |
obin | -5.982 |
ablishment | -5.891 |
Token | � |
Token ID | 447 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
imation | +0.153 |
�� | +0.148 |
uthor | +0.141 |
obin | +0.136 |
ablishment | +0.135 |
Neg logit contributions | |
idas | -0.132 |
Smile | -0.131 |
Babel | -0.127 |
tto | -0.125 |
ラン | -0.125 |
Token | � |
Token ID | 251 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
imation | +0.147 |
�� | +0.142 |
uthor | +0.133 |
obin | +0.128 |
ablishment | +0.127 |
Neg logit contributions | |
idas | -0.179 |
Smile | -0.178 |
Babel | -0.173 |
ラン | -0.172 |
tto | -0.172 |
Token | and |
Token ID | 290 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
idas | +0.273 |
Smile | +0.270 |
Babel | +0.262 |
ラン | +0.259 |
tto | +0.259 |
Neg logit contributions | |
imation | -0.321 |
�� | -0.312 |
uthor | -0.296 |
obin | -0.286 |
ablishment | -0.285 |
Token | � |
Token ID | 564 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
imation | +0.232 |
�� | +0.226 |
uthor | +0.216 |
obin | +0.209 |
ablishment | +0.209 |
Neg logit contributions | |
idas | -0.162 |
Smile | -0.160 |
Babel | -0.155 |
ラン | -0.153 |
tto | -0.153 |
Token | EPA |
Token ID | 10193 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
idas | +0.477 |
Smile | +0.472 |
Babel | +0.457 |
ラン | +0.451 |
tto | +0.451 |
Neg logit contributions | |
imation | -0.651 |
�� | -0.634 |
uthor | -0.604 |
obin | -0.586 |
ablishment | -0.584 |
Token | funding |
Token ID | 4918 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
idas | +1.346 |
Smile | +1.331 |
Babel | +1.284 |
ラン | +1.268 |
tto | +1.267 |
Neg logit contributions | |
imation | -2.066 |
�� | -2.013 |
uthor | -1.923 |
obin | -1.869 |
ablishment | -1.861 |
Token | to |
Token ID | 284 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
imation | +0.877 |
�� | +0.849 |
uthor | +0.807 |
obin | +0.781 |
usion | +0.778 |
Neg logit contributions | |
idas | -0.779 |
Smile | -0.771 |
Babel | -0.750 |
ラン | -0.744 |
tto | -0.741 |
Token | ensure |
Token ID | 4155 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
imation | +0.021 |
�� | +0.020 |
uthor | +0.020 |
obin | +0.019 |
ablishment | +0.019 |
Neg logit contributions | |
idas | -0.014 |
Smile | -0.014 |
Babel | -0.014 |
ラン | -0.014 |
tto | -0.014 |
Token | their |
Token ID | 511 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
idas | +1.025 |
Smile | +1.018 |
Babel | +0.989 |
tto | +0.975 |
blush | +0.972 |
Neg logit contributions | |
imation | -1.151 |
�� | -1.118 |
uthor | -1.057 |
obin | -1.026 |
ablishment | -1.019 |
Token | compliance |
Token ID | 11846 |
Feature activation | +7.28e+00 |
Pos logit contributions | |
imation | +0.493 |
�� | +0.480 |
uthor | +0.456 |
obin | +0.443 |
ablishment | +0.441 |
Neg logit contributions | |
idas | -0.383 |
Smile | -0.379 |
Babel | -0.368 |
tto | -0.363 |
ラン | -0.362 |
Token | with |
Token ID | 351 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
idas | +3.943 |
Smile | +3.913 |
tto | +3.774 |
Babel | +3.685 |
blush | +3.684 |
Neg logit contributions | |
imation | -6.629 |
�� | -6.493 |
uthor | -6.139 |
obin | -6.036 |
ablishment | -6.007 |
Token | federal |
Token ID | 2717 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
idas | +0.784 |
Smile | +0.783 |
Babel | +0.758 |
blush | +0.742 |
tto | +0.741 |
Neg logit contributions | |
imation | -0.974 |
�� | -0.950 |
uthor | -0.895 |
obin | -0.874 |
ablishment | -0.866 |
Token | civil |
Token ID | 3026 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
idas | +1.577 |
Smile | +1.574 |
Babel | +1.516 |
blush | +1.493 |
ラン | +1.480 |
Neg logit contributions | |
imation | -2.340 |
�� | -2.282 |
uthor | -2.153 |
ablishment | -2.118 |
obin | -2.115 |
Token | - |
Token ID | 12 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
idas | +0.240 |
Smile | +0.238 |
Babel | +0.231 |
ラン | +0.229 |
tto | +0.229 |
Neg logit contributions | |
imation | -0.243 |
�� | -0.235 |
uthor | -0.223 |
obin | -0.215 |
ablishment | -0.214 |
Token | rights |
Token ID | 28046 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
imation | +0.606 |
�� | +0.585 |
uthor | +0.552 |
obin | +0.527 |
usion | +0.526 |
Neg logit contributions | |
idas | -0.808 |
Smile | -0.805 |
Babel | -0.787 |
ラン | -0.777 |
tto | -0.776 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
idas | +0.334 |
Smile | +0.331 |
Babel | +0.322 |
ラン | +0.318 |
tto | +0.317 |
Neg logit contributions | |
imation | -0.387 |
�� | -0.376 |
uthor | -0.358 |
obin | -0.345 |
ablishment | -0.344 |
Token | S |
Token ID | 50 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
idas | +0.798 |
Smile | +0.790 |
Babel | +0.768 |
ラン | +0.759 |
tto | +0.759 |
Neg logit contributions | |
imation | -0.903 |
�� | -0.876 |
uthor | -0.832 |
obin | -0.804 |
ablishment | -0.801 |
Token | . |
Token ID | 13 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
idas | +1.477 |
Smile | +1.464 |
Babel | +1.418 |
tto | +1.402 |
ラン | +1.401 |
Neg logit contributions | |
imation | -1.769 |
�� | -1.722 |
uthor | -1.634 |
obin | -1.584 |
ablishment | -1.576 |
Token | Immigration |
Token ID | 18204 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
idas | +0.627 |
Smile | +0.616 |
Babel | +0.600 |
tto | +0.594 |
ラン | +0.592 |
Neg logit contributions | |
imation | -0.745 |
�� | -0.724 |
uthor | -0.689 |
obin | -0.664 |
ablishment | -0.662 |
Token | and |
Token ID | 290 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
idas | +1.799 |
Smile | +1.792 |
Babel | +1.729 |
ラン | +1.707 |
tto | +1.706 |
Neg logit contributions | |
imation | -2.534 |
�� | -2.470 |
uthor | -2.342 |
obin | -2.290 |
ablishment | -2.274 |
Token | Customs |
Token ID | 23888 |
Feature activation | +7.24e+00 |
Pos logit contributions | |
idas | +0.048 |
Smile | +0.048 |
Babel | +0.045 |
ラン | +0.045 |
tto | +0.044 |
Neg logit contributions | |
imation | -0.140 |
�� | -0.137 |
uthor | -0.132 |
obin | -0.129 |
ablishment | -0.129 |
Token | Enforcement |
Token ID | 19198 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
Smile | +3.175 |
idas | +3.112 |
ラン | +2.987 |
Babel | +2.974 |
tto | +2.961 |
Neg logit contributions | |
imation | -7.330 |
�� | -7.213 |
uthor | -6.841 |
obin | -6.782 |
ablishment | -6.672 |
Token | and |
Token ID | 290 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
idas | +3.274 |
Smile | +3.265 |
tto | +3.138 |
Babel | +3.137 |
blush | +3.115 |
Neg logit contributions | |
imation | -4.368 |
�� | -4.205 |
uthor | -3.965 |
ablishment | -3.906 |
obin | -3.901 |
Token | the |
Token ID | 262 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
idas | +0.161 |
Smile | +0.159 |
Babel | +0.154 |
ラン | +0.153 |
tto | +0.153 |
Neg logit contributions | |
imation | -0.194 |
�� | -0.189 |
uthor | -0.179 |
obin | -0.173 |
ablishment | -0.173 |
Token | U |
Token ID | 471 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
imation | +0.244 |
�� | +0.237 |
uthor | +0.227 |
obin | +0.219 |
ablishment | +0.218 |
Neg logit contributions | |
idas | -0.190 |
Smile | -0.187 |
ラン | -0.181 |
Babel | -0.181 |
tto | -0.179 |
Token | . |
Token ID | 13 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
idas | +0.264 |
Smile | +0.262 |
Babel | +0.255 |
blush | +0.253 |
ラン | +0.253 |
Neg logit contributions | |
imation | -0.295 |
�� | -0.284 |
uthor | -0.272 |
obin | -0.262 |
ablishment | -0.261 |
Token | io |
Token ID | 952 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
imation | +1.894 |
�� | +1.804 |
uthor | +1.690 |
obin | +1.623 |
usion | +1.586 |
Neg logit contributions | |
Smile | -3.211 |
idas | -3.200 |
Babel | -3.145 |
ラン | -3.139 |
blush | -3.108 |
Token | 's |
Token ID | 338 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
idas | +0.744 |
Smile | +0.736 |
Babel | +0.714 |
tto | +0.708 |
blush | +0.705 |
Neg logit contributions | |
imation | -0.824 |
�� | -0.802 |
uthor | -0.757 |
ablishment | -0.734 |
obin | -0.731 |
Token | decision |
Token ID | 2551 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Smile | +1.314 |
idas | +1.299 |
Babel | +1.261 |
blush | +1.248 |
tto | +1.246 |
Neg logit contributions | |
imation | -1.688 |
�� | -1.652 |
uthor | -1.573 |
obin | -1.523 |
ablishment | -1.522 |
Token | effectively |
Token ID | 6840 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
imation | +1.092 |
�� | +1.056 |
uthor | +1.004 |
obin | +0.976 |
usion | +0.970 |
Neg logit contributions | |
idas | -0.937 |
Smile | -0.934 |
Babel | -0.902 |
ラン | -0.899 |
tto | -0.888 |
Token | allows |
Token ID | 3578 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
imation | +0.961 |
�� | +0.928 |
uthor | +0.889 |
obin | +0.865 |
usion | +0.857 |
Neg logit contributions | |
idas | -0.705 |
Smile | -0.703 |
Babel | -0.672 |
ラン | -0.670 |
tto | -0.668 |
Token | Patrick |
Token ID | 9925 |
Feature activation | +7.20e+00 |
Pos logit contributions | |
idas | +0.278 |
Smile | +0.275 |
Babel | +0.267 |
tto | +0.263 |
ラン | +0.263 |
Neg logit contributions | |
imation | -0.360 |
�� | -0.350 |
uthor | -0.333 |
obin | -0.323 |
ablishment | -0.321 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
idas | +4.289 |
Smile | +4.266 |
Babel | +4.135 |
tto | +4.078 |
blush | +4.016 |
Neg logit contributions | |
imation | -6.147 |
�� | -5.996 |
uthor | -5.746 |
obin | -5.538 |
ablishment | -5.531 |
Token | who |
Token ID | 508 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
idas | +0.702 |
Smile | +0.695 |
Babel | +0.674 |
tto | +0.665 |
ラン | +0.664 |
Neg logit contributions | |
imation | -0.868 |
�� | -0.844 |
uthor | -0.802 |
obin | -0.778 |
ablishment | -0.775 |
Token | controls |
Token ID | 6973 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
idas | +1.053 |
Smile | +1.041 |
Babel | +1.010 |
blush | +0.999 |
tto | +0.997 |
Neg logit contributions | |
imation | -1.353 |
�� | -1.321 |
uthor | -1.248 |
ablishment | -1.226 |
obin | -1.220 |
Token | the |
Token ID | 262 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
imation | +0.337 |
�� | +0.328 |
uthor | +0.311 |
obin | +0.301 |
ablishment | +0.300 |
Neg logit contributions | |
idas | -0.281 |
Smile | -0.278 |
Babel | -0.270 |
tto | -0.266 |
ラン | -0.266 |
Token | Senate |
Token ID | 3845 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
idas | +0.437 |
Smile | +0.436 |
Babel | +0.422 |
tto | +0.416 |
blush | +0.416 |
Neg logit contributions | |
imation | -0.560 |
�� | -0.547 |
uthor | -0.519 |
obin | -0.504 |
ablishment | -0.503 |
Token | year |
Token ID | 614 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
imation | +0.332 |
�� | +0.324 |
uthor | +0.309 |
obin | +0.301 |
ablishment | +0.299 |
Neg logit contributions | |
idas | -0.217 |
Smile | -0.214 |
Babel | -0.207 |
ラン | -0.204 |
tto | -0.204 |
Token | , |
Token ID | 11 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
imation | +0.739 |
�� | +0.715 |
uthor | +0.679 |
obin | +0.657 |
ablishment | +0.655 |
Neg logit contributions | |
idas | -0.664 |
Smile | -0.657 |
Babel | -0.639 |
ラン | -0.632 |
tto | -0.630 |
Token | � |
Token ID | 447 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
imation | +0.280 |
�� | +0.271 |
uthor | +0.258 |
obin | +0.249 |
ablishment | +0.248 |
Neg logit contributions | |
idas | -0.236 |
Smile | -0.233 |
Babel | -0.227 |
ラン | -0.224 |
tto | -0.224 |
Token | � |
Token ID | 251 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
imation | +0.242 |
�� | +0.233 |
uthor | +0.220 |
obin | +0.213 |
ablishment | +0.211 |
Neg logit contributions | |
idas | -0.271 |
Smile | -0.269 |
Babel | -0.262 |
ラン | -0.260 |
tto | -0.260 |
Token | said |
Token ID | 531 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
idas | +0.465 |
Smile | +0.461 |
Babel | +0.445 |
tto | +0.443 |
ラン | +0.442 |
Neg logit contributions | |
imation | -0.558 |
�� | -0.544 |
uthor | -0.516 |
obin | -0.500 |
ablishment | -0.499 |
Token | Patrick |
Token ID | 9925 |
Feature activation | +7.18e+00 |
Pos logit contributions | |
idas | +0.555 |
Smile | +0.552 |
Babel | +0.531 |
tto | +0.524 |
ラン | +0.523 |
Neg logit contributions | |
imation | -0.846 |
�� | -0.826 |
uthor | -0.789 |
obin | -0.766 |
ablishment | -0.765 |
Token | Sp |
Token ID | 1338 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Smile | +4.190 |
idas | +4.151 |
Babel | +4.028 |
Wend | +3.957 |
Moe | +3.938 |
Neg logit contributions | |
imation | -6.249 |
�� | -6.124 |
uthor | -5.896 |
ablishment | -5.678 |
obin | -5.604 |
Token | angler |
Token ID | 49910 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
idas | +0.883 |
Smile | +0.861 |
Babel | +0.831 |
tto | +0.831 |
ラン | +0.824 |
Neg logit contributions | |
imation | -0.879 |
�� | -0.868 |
uthor | -0.808 |
ablishment | -0.778 |
obin | -0.771 |
Token | , |
Token ID | 11 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
idas | +1.543 |
Smile | +1.525 |
tto | +1.469 |
Babel | +1.467 |
ラン | +1.454 |
Neg logit contributions | |
imation | -1.857 |
�� | -1.806 |
uthor | -1.717 |
ablishment | -1.668 |
obin | -1.657 |
Token | owner |
Token ID | 4870 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
idas | +0.680 |
Smile | +0.673 |
Babel | +0.648 |
tto | +0.641 |
ラン | +0.638 |
Neg logit contributions | |
imation | -1.000 |
�� | -0.975 |
uthor | -0.930 |
obin | -0.906 |
ablishment | -0.902 |
Token | of |
Token ID | 286 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
idas | +1.758 |
Smile | +1.744 |
Babel | +1.675 |
tto | +1.656 |
ラン | +1.655 |
Neg logit contributions | |
imation | -2.264 |
�� | -2.205 |
uthor | -2.097 |
obin | -2.050 |
ablishment | -2.028 |
Token | includes |
Token ID | 3407 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
imation | +0.392 |
�� | +0.381 |
uthor | +0.361 |
obin | +0.350 |
ablishment | +0.349 |
Neg logit contributions | |
idas | -0.337 |
Smile | -0.334 |
Babel | -0.325 |
tto | -0.320 |
ラン | -0.319 |
Token | additional |
Token ID | 3224 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
idas | +0.073 |
Smile | +0.072 |
Babel | +0.070 |
ラン | +0.069 |
tto | +0.069 |
Neg logit contributions | |
imation | -0.099 |
�� | -0.096 |
uthor | -0.091 |
obin | -0.089 |
ablishment | -0.088 |
Token | instructions |
Token ID | 7729 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
idas | +0.516 |
Smile | +0.511 |
Babel | +0.496 |
tto | +0.488 |
ラン | +0.487 |
Neg logit contributions | |
imation | -0.668 |
�� | -0.651 |
uthor | -0.620 |
obin | -0.600 |
ablishment | -0.599 |
Token | for |
Token ID | 329 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
idas | +0.098 |
Smile | +0.097 |
Babel | +0.094 |
tto | +0.093 |
blush | +0.093 |
Neg logit contributions | |
imation | -0.110 |
�� | -0.108 |
uthor | -0.102 |
obin | -0.098 |
ablishment | -0.098 |
Token | ensuring |
Token ID | 13359 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
imation | +0.639 |
�� | +0.618 |
uthor | +0.588 |
obin | +0.569 |
ablishment | +0.566 |
Neg logit contributions | |
idas | -0.532 |
Smile | -0.525 |
ラン | -0.508 |
Babel | -0.507 |
tto | -0.506 |
Token | compatibility |
Token ID | 17764 |
Feature activation | +7.15e+00 |
Pos logit contributions | |
idas | +0.416 |
Smile | +0.413 |
Babel | +0.401 |
tto | +0.395 |
ラン | +0.394 |
Neg logit contributions | |
imation | -0.481 |
�� | -0.468 |
uthor | -0.444 |
obin | -0.430 |
ablishment | -0.428 |
Token | with |
Token ID | 351 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
idas | +4.011 |
Smile | +3.976 |
Babel | +3.837 |
tto | +3.807 |
blush | +3.724 |
Neg logit contributions | |
�� | -6.237 |
imation | -6.211 |
uthor | -5.907 |
obin | -5.742 |
ablishment | -5.729 |
Token | V |
Token ID | 569 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
idas | +1.024 |
Smile | +1.018 |
Babel | +0.986 |
tto | +0.969 |
blush | +0.965 |
Neg logit contributions | |
imation | -1.334 |
�� | -1.301 |
uthor | -1.240 |
obin | -1.201 |
ablishment | -1.197 |
Token | OD |
Token ID | 3727 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
imation | +0.096 |
�� | +0.093 |
uthor | +0.088 |
obin | +0.085 |
ablishment | +0.084 |
Neg logit contributions | |
idas | -0.099 |
Smile | -0.098 |
Babel | -0.096 |
ラン | -0.095 |
tto | -0.095 |
Token | services |
Token ID | 2594 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
imation | +0.922 |
�� | +0.894 |
uthor | +0.852 |
obin | +0.825 |
ablishment | +0.816 |
Neg logit contributions | |
idas | -0.749 |
Smile | -0.741 |
Babel | -0.718 |
tto | -0.715 |
ラン | -0.715 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
idas | +0.061 |
Smile | +0.060 |
Babel | +0.058 |
tto | +0.058 |
ラン | +0.057 |
Neg logit contributions | |
imation | -0.071 |
�� | -0.069 |
uthor | -0.065 |
obin | -0.063 |
ablishment | -0.063 |
Token | armies |
Token ID | 18837 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
idas | +0.373 |
Smile | +0.369 |
Babel | +0.354 |
tto | +0.349 |
ラン | +0.349 |
Neg logit contributions | |
imation | -0.656 |
�� | -0.639 |
uthor | -0.612 |
obin | -0.596 |
ablishment | -0.594 |
Token | retreat |
Token ID | 13703 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
idas | +0.426 |
Smile | +0.421 |
Babel | +0.408 |
tto | +0.403 |
blush | +0.402 |
Neg logit contributions | |
imation | -0.587 |
�� | -0.572 |
uthor | -0.544 |
obin | -0.529 |
ablishment | -0.526 |
Token | ), |
Token ID | 828 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
imation | +1.086 |
�� | +1.047 |
uthor | +1.000 |
obin | +0.962 |
ablishment | +0.960 |
Neg logit contributions | |
idas | -0.980 |
Smile | -0.971 |
Babel | -0.935 |
ラン | -0.933 |
tto | -0.928 |
Token | or |
Token ID | 393 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
idas | +0.042 |
Smile | +0.041 |
Babel | +0.040 |
ラン | +0.040 |
tto | +0.040 |
Neg logit contributions | |
imation | -0.048 |
�� | -0.046 |
uthor | -0.044 |
obin | -0.043 |
ablishment | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
imation | +0.408 |
�� | +0.396 |
uthor | +0.377 |
obin | +0.365 |
ablishment | +0.364 |
Neg logit contributions | |
idas | -0.340 |
Smile | -0.336 |
Babel | -0.325 |
ラン | -0.322 |
tto | -0.321 |
Token | Baltic |
Token ID | 32882 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
imation | +0.229 |
�� | +0.222 |
uthor | +0.212 |
obin | +0.206 |
ablishment | +0.206 |
Neg logit contributions | |
idas | -0.148 |
Smile | -0.145 |
Babel | -0.140 |
ラン | -0.139 |
tto | -0.138 |
Token | coast |
Token ID | 7051 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
Smile | +4.007 |
idas | +3.992 |
tto | +3.859 |
Babel | +3.838 |
ラン | +3.798 |
Neg logit contributions | |
imation | -6.165 |
�� | -6.155 |
uthor | -5.788 |
obin | -5.688 |
ablishment | -5.599 |
Token | ( |
Token ID | 357 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
imation | +0.353 |
�� | +0.342 |
uthor | +0.325 |
obin | +0.315 |
ablishment | +0.313 |
Neg logit contributions | |
idas | -0.302 |
Smile | -0.299 |
Babel | -0.290 |
ラン | -0.287 |
tto | -0.287 |
Token | should |
Token ID | 21754 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
idas | +0.865 |
Smile | +0.853 |
Babel | +0.827 |
tto | +0.821 |
ラン | +0.820 |
Neg logit contributions | |
imation | -1.091 |
�� | -1.063 |
uthor | -1.011 |
obin | -0.979 |
ablishment | -0.976 |
Token | German |
Token ID | 2679 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
idas | +0.290 |
Smile | +0.287 |
Babel | +0.278 |
ラン | +0.275 |
tto | +0.275 |
Neg logit contributions | |
imation | -0.347 |
�� | -0.338 |
uthor | -0.321 |
obin | -0.310 |
ablishment | -0.309 |
Token | forces |
Token ID | 3386 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
idas | +0.667 |
Smile | +0.656 |
Babel | +0.629 |
ラン | +0.619 |
tto | +0.618 |
Neg logit contributions | |
imation | -1.445 |
�� | -1.414 |
uthor | -1.357 |
obin | -1.324 |
ablishment | -1.318 |
Token | first |
Token ID | 717 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
idas | +0.106 |
Smile | +0.105 |
Babel | +0.101 |
ラン | +0.100 |
tto | +0.100 |
Neg logit contributions | |
imation | -0.168 |
�� | -0.164 |
uthor | -0.157 |
obin | -0.152 |
ablishment | -0.152 |
Token | time |
Token ID | 640 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
imation | +0.715 |
�� | +0.694 |
uthor | +0.660 |
obin | +0.637 |
ablishment | +0.636 |
Neg logit contributions | |
idas | -0.579 |
Smile | -0.575 |
Babel | -0.555 |
ラン | -0.550 |
tto | -0.550 |
Token | to |
Token ID | 284 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
imation | +1.093 |
�� | +1.062 |
uthor | +1.012 |
ablishment | +0.974 |
obin | +0.968 |
Neg logit contributions | |
idas | -0.965 |
Smile | -0.957 |
Babel | -0.934 |
ラン | -0.920 |
tto | -0.916 |
Token | conduct |
Token ID | 3189 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
imation | +0.858 |
�� | +0.832 |
uthor | +0.798 |
ablishment | +0.773 |
obin | +0.772 |
Neg logit contributions | |
idas | -0.600 |
Smile | -0.592 |
Babel | -0.573 |
ラン | -0.568 |
tto | -0.566 |
Token | targeted |
Token ID | 7977 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
idas | +0.182 |
Smile | +0.180 |
Babel | +0.174 |
ラン | +0.172 |
tto | +0.172 |
Neg logit contributions | |
imation | -0.243 |
�� | -0.236 |
uthor | -0.225 |
obin | -0.218 |
ablishment | -0.217 |
Token | compliance |
Token ID | 11846 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
idas | +0.051 |
Smile | +0.050 |
Babel | +0.049 |
ラン | +0.048 |
tto | +0.048 |
Neg logit contributions | |
imation | -0.072 |
�� | -0.070 |
uthor | -0.067 |
obin | -0.065 |
usion | -0.064 |
Token | reviews |
Token ID | 8088 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
idas | +3.812 |
Smile | +3.807 |
tto | +3.657 |
blush | +3.630 |
Babel | +3.626 |
Neg logit contributions | |
imation | -6.339 |
�� | -6.284 |
uthor | -5.937 |
obin | -5.808 |
ablishment | -5.801 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-03 |
Pos logit contributions | |
idas | +0.024 |
Smile | +0.024 |
Babel | +0.023 |
ラン | +0.023 |
tto | +0.023 |
Neg logit contributions | |
imation | -0.028 |
�� | -0.027 |
uthor | -0.026 |
obin | -0.025 |
ablishment | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
idas | +0.002 |
Smile | +0.002 |
Babel | +0.002 |
tto | +0.002 |
ラン | +0.002 |
Neg logit contributions | |
imation | -0.002 |
�� | -0.002 |
uthor | -0.002 |
obin | -0.002 |
ablishment | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
imation | +0.321 |
�� | +0.306 |
uthor | +0.291 |
obin | +0.284 |
usion | +0.282 |
Neg logit contributions | |
idas | -0.297 |
Smile | -0.294 |
Babel | -0.286 |
ラン | -0.285 |
blush | -0.283 |
Token | Beginning |
Token ID | 45198 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
imation | +0.013 |
�� | +0.013 |
uthor | +0.012 |
obin | +0.012 |
ablishment | +0.012 |
Neg logit contributions | |
idas | -0.016 |
Smile | -0.016 |
Babel | -0.015 |
blush | -0.015 |
tto | -0.015 |
Token | office |
Token ID | 2607 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
imation | +0.313 |
�� | +0.302 |
uthor | +0.291 |
obin | +0.281 |
ablishment | +0.280 |
Neg logit contributions | |
idas | -0.224 |
Smile | -0.219 |
Babel | -0.213 |
ラン | -0.211 |
tto | -0.210 |
Token | promises |
Token ID | 10497 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
idas | +1.097 |
Smile | +1.084 |
Babel | +1.048 |
tto | +1.043 |
ラン | +1.042 |
Neg logit contributions | |
imation | -1.313 |
�� | -1.284 |
uthor | -1.211 |
ablishment | -1.179 |
obin | -1.175 |
Token | to |
Token ID | 284 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
idas | +0.139 |
Smile | +0.137 |
Babel | +0.133 |
ラン | +0.132 |
tto | +0.131 |
Neg logit contributions | |
imation | -0.164 |
�� | -0.159 |
uthor | -0.152 |
obin | -0.146 |
ablishment | -0.146 |
Token | complete |
Token ID | 1844 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
idas | +0.390 |
Smile | +0.386 |
Babel | +0.373 |
ラン | +0.368 |
tto | +0.367 |
Neg logit contributions | |
imation | -0.605 |
�� | -0.587 |
uthor | -0.563 |
obin | -0.547 |
ablishment | -0.544 |
Token | six |
Token ID | 2237 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
idas | +0.261 |
Smile | +0.258 |
Babel | +0.250 |
ラン | +0.248 |
tto | +0.248 |
Neg logit contributions | |
imation | -0.324 |
�� | -0.314 |
uthor | -0.301 |
obin | -0.290 |
ablishment | -0.289 |
Token | compliance |
Token ID | 11846 |
Feature activation | +6.95e+00 |
Pos logit contributions | |
idas | +1.089 |
Smile | +1.076 |
Babel | +1.038 |
ラン | +1.025 |
tto | +1.025 |
Neg logit contributions | |
imation | -1.689 |
�� | -1.646 |
uthor | -1.574 |
obin | -1.528 |
ablishment | -1.522 |
Token | reviews |
Token ID | 8088 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
idas | +2.517 |
Smile | +2.506 |
blush | +2.347 |
Babel | +2.323 |
tto | +2.291 |
Neg logit contributions | |
imation | -7.632 |
�� | -7.539 |
uthor | -7.217 |
ablishment | -7.094 |
obin | -7.042 |
Token | of |
Token ID | 286 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
idas | +0.267 |
Smile | +0.265 |
Babel | +0.257 |
ラン | +0.255 |
tto | +0.254 |
Neg logit contributions | |
imation | -0.311 |
�� | -0.302 |
uthor | -0.286 |
obin | -0.277 |
ablishment | -0.276 |
Token | recipient |
Token ID | 17800 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
idas | +0.471 |
Smile | +0.466 |
Babel | +0.452 |
ラン | +0.447 |
tto | +0.447 |
Neg logit contributions | |
imation | -0.565 |
�� | -0.549 |
uthor | -0.522 |
obin | -0.505 |
ablishment | -0.502 |
Token | agencies |
Token ID | 5942 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
idas | +0.999 |
Smile | +0.986 |
Babel | +0.946 |
ラン | +0.932 |
tto | +0.931 |
Neg logit contributions | |
imation | -1.943 |
�� | -1.898 |
uthor | -1.820 |
obin | -1.773 |
ablishment | -1.766 |
Token | per |
Token ID | 583 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
idas | +0.938 |
Smile | +0.928 |
Babel | +0.899 |
tto | +0.889 |
ラン | +0.888 |
Neg logit contributions | |
imation | -1.135 |
�� | -1.105 |
uthor | -1.049 |
obin | -1.017 |
ablishment | -1.012 |
Token | , |
Token ID | 11 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
idas | +1.886 |
Smile | +1.873 |
tto | +1.820 |
Babel | +1.784 |
blush | +1.773 |
Neg logit contributions | |
imation | -2.444 |
�� | -2.399 |
uthor | -2.291 |
ablishment | -2.219 |
obin | -2.214 |
Token | a |
Token ID | 257 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
idas | +0.524 |
Smile | +0.518 |
Babel | +0.500 |
ラン | +0.495 |
tto | +0.494 |
Neg logit contributions | |
imation | -0.717 |
�� | -0.698 |
uthor | -0.668 |
obin | -0.649 |
ablishment | -0.646 |
Token | Fore |
Token ID | 4558 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
idas | +0.053 |
Smile | +0.053 |
Babel | +0.051 |
ラン | +0.050 |
tto | +0.050 |
Neg logit contributions | |
imation | -0.059 |
�� | -0.057 |
uthor | -0.055 |
obin | -0.053 |
ablishment | -0.052 |
Token | word |
Token ID | 4775 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
imation | +0.245 |
�� | +0.238 |
uthor | +0.227 |
obin | +0.221 |
ablishment | +0.220 |
Neg logit contributions | |
idas | -0.181 |
Smile | -0.180 |
Babel | -0.173 |
tto | -0.172 |
ラン | -0.172 |
Token | by |
Token ID | 416 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
imation | +0.812 |
�� | +0.774 |
uthor | +0.729 |
usion | +0.713 |
ablishment | +0.711 |
Neg logit contributions | |
idas | -0.897 |
Smile | -0.888 |
Babel | -0.875 |
blush | -0.861 |
ラン | -0.860 |
Token | Patrick |
Token ID | 9925 |
Feature activation | +6.94e+00 |
Pos logit contributions | |
idas | +0.165 |
Smile | +0.162 |
Babel | +0.154 |
tto | +0.151 |
ラン | +0.151 |
Neg logit contributions | |
imation | -0.451 |
�� | -0.442 |
uthor | -0.426 |
obin | -0.417 |
ablishment | -0.416 |
Token | J |
Token ID | 449 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
idas | +4.526 |
Babel | +4.438 |
Smile | +4.431 |
tto | +4.356 |
Wend | +4.355 |
Neg logit contributions | |
imation | -5.633 |
�� | -5.486 |
uthor | -5.232 |
ablishment | -5.054 |
vier | -4.980 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
idas | +0.465 |
Babel | +0.461 |
Smile | +0.455 |
land | +0.435 |
tto | +0.430 |
Neg logit contributions | |
imation | -0.795 |
�� | -0.754 |
uthor | -0.746 |
ablishment | -0.727 |
� | -0.720 |
Token | Buchanan |
Token ID | 36358 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
idas | +1.158 |
Smile | +1.152 |
Babel | +1.125 |
tto | +1.103 |
Moe | +1.081 |
Neg logit contributions | |
imation | -1.824 |
�� | -1.762 |
uthor | -1.702 |
ablishment | -1.652 |
obin | -1.632 |
Token | , |
Token ID | 11 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
imation | +1.279 |
�� | +1.227 |
uthor | +1.158 |
obin | +1.130 |
usion | +1.117 |
Neg logit contributions | |
idas | -1.350 |
Smile | -1.322 |
Babel | -1.300 |
ラン | -1.284 |
tto | -1.255 |
Token | and |
Token ID | 290 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
Smile | +0.404 |
idas | +0.403 |
Babel | +0.386 |
ラン | +0.385 |
tto | +0.381 |
Neg logit contributions | |
imation | -0.601 |
�� | -0.582 |
uthor | -0.562 |
obin | -0.550 |
ablishment | -0.540 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
idas | +0.940 |
Smile | +0.931 |
Babel | +0.902 |
tto | +0.893 |
ラン | +0.890 |
Neg logit contributions | |
imation | -1.131 |
�� | -1.104 |
uthor | -1.047 |
obin | -1.012 |
ablishment | -1.009 |
Token | + |
Token ID | 10 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
idas | +1.146 |
Smile | +1.137 |
Babel | +1.105 |
ラン | +1.101 |
tto | +1.100 |
Neg logit contributions | |
imation | -0.902 |
�� | -0.874 |
uthor | -0.819 |
obin | -0.785 |
ablishment | -0.785 |
Token | Conf |
Token ID | 7326 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
imation | +0.302 |
�� | +0.294 |
uthor | +0.280 |
obin | +0.271 |
ablishment | +0.270 |
Neg logit contributions | |
idas | -0.242 |
Smile | -0.239 |
Babel | -0.232 |
ラン | -0.230 |
tto | -0.229 |
Token | ident |
Token ID | 738 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
imation | +1.413 |
�� | +1.349 |
uthor | +1.271 |
obin | +1.216 |
usion | +1.208 |
Neg logit contributions | |
idas | -1.965 |
Smile | -1.954 |
Babel | -1.908 |
ラン | -1.894 |
tto | -1.889 |
Token | , |
Token ID | 11 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
imation | +0.230 |
�� | +0.224 |
uthor | +0.212 |
obin | +0.206 |
ablishment | +0.205 |
Neg logit contributions | |
idas | -0.197 |
Smile | -0.197 |
Babel | -0.191 |
tto | -0.188 |
ラン | -0.187 |
Token | Patri |
Token ID | 9606 |
Feature activation | +6.90e+00 |
Pos logit contributions | |
idas | +0.277 |
Smile | +0.277 |
Babel | +0.267 |
tto | +0.263 |
ラン | +0.262 |
Neg logit contributions | |
imation | -0.337 |
�� | -0.328 |
uthor | -0.312 |
obin | -0.302 |
ablishment | -0.301 |
Token | otic |
Token ID | 6210 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
idas | +3.586 |
Smile | +3.439 |
tto | +3.332 |
blush | +3.214 |
Babel | +3.213 |
Neg logit contributions | |
�� | -6.439 |
imation | -6.266 |
uthor | -5.983 |
obin | -5.694 |
vier | -5.690 |
Token | , |
Token ID | 11 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
Smile | +1.588 |
idas | +1.565 |
Babel | +1.509 |
tto | +1.494 |
blush | +1.487 |
Neg logit contributions | |
imation | -1.951 |
�� | -1.907 |
uthor | -1.795 |
obin | -1.744 |
ablishment | -1.735 |
Token | Des |
Token ID | 2935 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
Smile | +0.540 |
idas | +0.538 |
Babel | +0.520 |
tto | +0.511 |
ラン | +0.508 |
Neg logit contributions | |
imation | -0.660 |
�� | -0.643 |
uthor | -0.609 |
obin | -0.591 |
ablishment | -0.588 |
Token | en |
Token ID | 268 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
imation | +0.298 |
�� | +0.290 |
uthor | +0.272 |
obin | +0.262 |
ablishment | +0.261 |
Neg logit contributions | |
idas | -0.318 |
Smile | -0.315 |
Babel | -0.306 |
tto | -0.304 |
ラン | -0.304 |
Token | r |
Token ID | 81 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
imation | +0.534 |
�� | +0.515 |
uthor | +0.489 |
obin | +0.471 |
ablishment | +0.467 |
Neg logit contributions | |
idas | -0.571 |
Smile | -0.568 |
Babel | -0.554 |
ラン | -0.548 |
tto | -0.546 |
Token | no |
Token ID | 645 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
imation | +0.288 |
�� | +0.280 |
uthor | +0.267 |
obin | +0.258 |
ablishment | +0.257 |
Neg logit contributions | |
idas | -0.229 |
Smile | -0.226 |
Babel | -0.219 |
ラン | -0.218 |
tto | -0.217 |
Token | fees |
Token ID | 6642 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
imation | +2.387 |
�� | +2.326 |
uthor | +2.231 |
usion | +2.178 |
obin | +2.152 |
Neg logit contributions | |
idas | -1.618 |
Smile | -1.594 |
ラン | -1.552 |
Babel | -1.518 |
tto | -1.517 |
Token | for |
Token ID | 329 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
imation | +0.640 |
�� | +0.620 |
uthor | +0.587 |
obin | +0.567 |
ablishment | +0.563 |
Neg logit contributions | |
idas | -0.630 |
Smile | -0.625 |
Babel | -0.608 |
ラン | -0.602 |
tto | -0.601 |
Token | included |
Token ID | 3017 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
imation | +0.541 |
�� | +0.527 |
uthor | +0.503 |
obin | +0.487 |
usion | +0.484 |
Neg logit contributions | |
idas | -0.404 |
Smile | -0.393 |
Babel | -0.383 |
ラン | -0.382 |
tto | -0.381 |
Token | PCI |
Token ID | 17976 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
imation | +0.935 |
�� | +0.906 |
uthor | +0.868 |
obin | +0.845 |
usion | +0.839 |
Neg logit contributions | |
idas | -0.600 |
Smile | -0.587 |
ラン | -0.575 |
Babel | -0.568 |
tto | -0.567 |
Token | Compliance |
Token ID | 40536 |
Feature activation | +6.80e+00 |
Pos logit contributions | |
Smile | +3.317 |
idas | +3.295 |
Babel | +3.183 |
blush | +3.103 |
tto | +3.087 |
Neg logit contributions | |
imation | -5.518 |
�� | -5.373 |
uthor | -5.098 |
ablishment | -5.036 |
obin | -4.968 |
Token | protections |
Token ID | 15018 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Smile | +4.057 |
idas | +3.941 |
Babel | +3.829 |
blush | +3.774 |
tto | +3.737 |
Neg logit contributions | |
imation | -5.931 |
�� | -5.796 |
uthor | -5.444 |
ablishment | -5.402 |
obin | -5.329 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
idas | +0.845 |
Smile | +0.840 |
Babel | +0.810 |
tto | +0.805 |
blush | +0.799 |
Neg logit contributions | |
imation | -1.026 |
�� | -1.000 |
uthor | -0.948 |
obin | -0.918 |
ablishment | -0.916 |
Token |
|
Token ID | 198 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
idas | +0.169 |
Smile | +0.167 |
Babel | +0.163 |
ラン | +0.161 |
tto | +0.161 |
Neg logit contributions | |
imation | -0.194 |
�� | -0.188 |
uthor | -0.178 |
obin | -0.173 |
ablishment | -0.172 |
Token |
|
Token ID | 198 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
idas | +0.039 |
Smile | +0.039 |
Babel | +0.038 |
ラン | +0.037 |
blush | +0.037 |
Neg logit contributions | |
imation | -0.044 |
�� | -0.042 |
uthor | -0.040 |
obin | -0.039 |
usion | -0.038 |
Token | Complete |
Token ID | 20988 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
idas | +0.253 |
Smile | +0.251 |
Babel | +0.245 |
blush | +0.242 |
ラン | +0.241 |
Neg logit contributions | |
imation | -0.266 |
�� | -0.258 |
uthor | -0.244 |
obin | -0.236 |
ablishment | -0.234 |
Token | exactly |
Token ID | 3446 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
imation | +0.289 |
�� | +0.280 |
uthor | +0.267 |
obin | +0.258 |
ablishment | +0.257 |
Neg logit contributions | |
idas | -0.232 |
Smile | -0.229 |
Babel | -0.223 |
ラン | -0.221 |
tto | -0.219 |
Token | that |
Token ID | 326 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
idas | +0.882 |
Smile | +0.875 |
Babel | +0.854 |
tto | +0.841 |
blush | +0.839 |
Neg logit contributions | |
imation | -0.973 |
�� | -0.954 |
uthor | -0.903 |
obin | -0.875 |
ablishment | -0.874 |
Token | in |
Token ID | 287 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
idas | +0.469 |
Smile | +0.464 |
Babel | +0.450 |
tto | +0.446 |
ラン | +0.445 |
Neg logit contributions | |
imation | -0.531 |
�� | -0.515 |
uthor | -0.489 |
obin | -0.473 |
ablishment | -0.471 |
Token | the |
Token ID | 262 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
idas | +0.569 |
Smile | +0.564 |
Babel | +0.547 |
tto | +0.540 |
ラン | +0.539 |
Neg logit contributions | |
imation | -0.716 |
�� | -0.697 |
uthor | -0.663 |
obin | -0.642 |
ablishment | -0.640 |
Token | Geneva |
Token ID | 20552 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
imation | +0.238 |
�� | +0.231 |
uthor | +0.221 |
obin | +0.214 |
usion | +0.213 |
Neg logit contributions | |
idas | -0.158 |
Smile | -0.154 |
Babel | -0.149 |
ラン | -0.149 |
tto | -0.147 |
Token | graveyard |
Token ID | 27672 |
Feature activation | +6.76e+00 |
Pos logit contributions | |
imation | +0.075 |
�� | +0.073 |
uthor | +0.070 |
obin | +0.068 |
ablishment | +0.067 |
Neg logit contributions | |
idas | -0.059 |
Smile | -0.059 |
Babel | -0.057 |
tto | -0.056 |
ラン | -0.056 |
Token | where |
Token ID | 810 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
idas | +4.195 |
Smile | +4.148 |
tto | +4.055 |
Babel | +4.020 |
blush | +3.975 |
Neg logit contributions | |
imation | -5.651 |
�� | -5.549 |
uthor | -5.279 |
obin | -5.155 |
ablishment | -5.051 |
Token | Borg |
Token ID | 29004 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
imation | +0.850 |
�� | +0.828 |
uthor | +0.788 |
obin | +0.761 |
ablishment | +0.758 |
Neg logit contributions | |
idas | -0.679 |
Smile | -0.673 |
Babel | -0.649 |
ラン | -0.646 |
tto | -0.643 |
Token | es |
Token ID | 274 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
idas | +1.345 |
Smile | +1.317 |
Babel | +1.265 |
tto | +1.248 |
ラン | +1.240 |
Neg logit contributions | |
imation | -2.208 |
�� | -2.157 |
uthor | -2.064 |
obin | -2.010 |
ablishment | -2.003 |
Token | 's |
Token ID | 338 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
idas | +0.335 |
Smile | +0.332 |
Babel | +0.323 |
tto | +0.319 |
ラン | +0.318 |
Neg logit contributions | |
imation | -0.385 |
�� | -0.373 |
uthor | -0.355 |
obin | -0.343 |
ablishment | -0.342 |
Token | well |
Token ID | 880 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
idas | +1.394 |
Smile | +1.385 |
Babel | +1.340 |
tto | +1.317 |
blush | +1.309 |
Neg logit contributions | |
imation | -2.200 |
�� | -2.141 |
uthor | -2.052 |
obin | -1.996 |
ablishment | -1.994 |
Token | police |
Token ID | 1644 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
imation | +0.353 |
�� | +0.344 |
uthor | +0.327 |
obin | +0.317 |
usion | +0.316 |
Neg logit contributions | |
idas | -0.259 |
Smile | -0.257 |
Babel | -0.248 |
ラン | -0.245 |
tto | -0.244 |
Token | officers |
Token ID | 3790 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
idas | +1.671 |
Smile | +1.633 |
Babel | +1.587 |
tto | +1.558 |
blush | +1.549 |
Neg logit contributions | |
imation | -3.010 |
�� | -2.937 |
uthor | -2.809 |
obin | -2.747 |
ablishment | -2.731 |
Token | affected |
Token ID | 5676 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
idas | +0.308 |
Smile | +0.303 |
Babel | +0.295 |
tto | +0.292 |
blush | +0.291 |
Neg logit contributions | |
imation | -0.396 |
�� | -0.385 |
uthor | -0.366 |
obin | -0.355 |
ablishment | -0.354 |
Token | by |
Token ID | 416 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
imation | +0.406 |
�� | +0.394 |
uthor | +0.374 |
obin | +0.362 |
ablishment | +0.360 |
Neg logit contributions | |
idas | -0.362 |
Smile | -0.359 |
Babel | -0.348 |
ラン | -0.345 |
tto | -0.344 |
Token | smoke |
Token ID | 7523 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
idas | +0.641 |
Smile | +0.639 |
Babel | +0.624 |
tto | +0.617 |
blush | +0.613 |
Neg logit contributions | |
imation | -0.705 |
�� | -0.684 |
uthor | -0.652 |
obin | -0.629 |
ablishment | -0.626 |
Token | inhal |
Token ID | 40982 |
Feature activation | -7.96e+00 |
Pos logit contributions | |
imation | +1.482 |
�� | +1.445 |
uthor | +1.350 |
usion | +1.312 |
obin | +1.311 |
Neg logit contributions | |
idas | -1.459 |
Smile | -1.452 |
Babel | -1.400 |
ラン | -1.386 |
tto | -1.383 |
Token | ation |
Token ID | 341 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
imation | +2.981 |
�� | +2.605 |
usion | +2.456 |
uthor | +2.436 |
ablishment | +2.301 |
Neg logit contributions | |
Smile | -8.562 |
idas | -8.552 |
Babel | -8.389 |
ラン | -8.360 |
tto | -8.256 |
Token | . |
Token ID | 13 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
imation | +1.739 |
�� | +1.685 |
uthor | +1.598 |
obin | +1.547 |
usion | +1.544 |
Neg logit contributions | |
idas | -1.595 |
Smile | -1.582 |
Babel | -1.530 |
ラン | -1.525 |
tto | -1.511 |
Token |
|
Token ID | 198 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
imation | +0.428 |
�� | +0.416 |
uthor | +0.394 |
obin | +0.381 |
ablishment | +0.380 |
Neg logit contributions | |
idas | -0.377 |
Smile | -0.372 |
Babel | -0.361 |
ラン | -0.358 |
tto | -0.357 |
Token |
|
Token ID | 198 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
imation | +0.400 |
�� | +0.381 |
uthor | +0.363 |
obin | +0.354 |
usion | +0.352 |
Neg logit contributions | |
idas | -0.379 |
Smile | -0.375 |
Babel | -0.365 |
ラン | -0.365 |
blush | -0.362 |
Token | France |
Token ID | 28572 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
imation | +0.217 |
�� | +0.211 |
uthor | +0.200 |
obin | +0.193 |
ablishment | +0.192 |
Neg logit contributions | |
idas | -0.210 |
Smile | -0.208 |
Babel | -0.202 |
ラン | -0.200 |
tto | -0.200 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
idas | +0.442 |
Smile | +0.438 |
Babel | +0.425 |
ラン | +0.420 |
tto | +0.420 |
Neg logit contributions | |
imation | -0.504 |
�� | -0.489 |
uthor | -0.464 |
obin | -0.449 |
ablishment | -0.447 |
Token | establish |
Token ID | 4474 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
idas | +0.082 |
Smile | +0.082 |
Babel | +0.079 |
tto | +0.078 |
ラン | +0.078 |
Neg logit contributions | |
imation | -0.124 |
�� | -0.121 |
uthor | -0.115 |
obin | -0.112 |
ablishment | -0.112 |
Token | a |
Token ID | 257 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
idas | +0.167 |
Smile | +0.165 |
Babel | +0.160 |
tto | +0.159 |
ラン | +0.159 |
Neg logit contributions | |
imation | -0.214 |
�� | -0.208 |
uthor | -0.198 |
obin | -0.192 |
ablishment | -0.191 |
Token | new |
Token ID | 649 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
idas | +0.505 |
Smile | +0.498 |
Babel | +0.481 |
ラン | +0.477 |
tto | +0.476 |
Neg logit contributions | |
imation | -0.711 |
�� | -0.692 |
uthor | -0.660 |
obin | -0.641 |
ablishment | -0.638 |
Token | Asia |
Token ID | 7229 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
idas | +0.235 |
Smile | +0.232 |
Babel | +0.225 |
ラン | +0.223 |
tto | +0.223 |
Neg logit contributions | |
imation | -0.319 |
�� | -0.310 |
uthor | -0.295 |
obin | -0.287 |
ablishment | -0.285 |
Token | foc |
Token ID | 2133 |
Feature activation | -7.91e+00 |
Pos logit contributions | |
idas | +0.672 |
Smile | +0.665 |
Babel | +0.642 |
ラン | +0.634 |
tto | +0.634 |
Neg logit contributions | |
imation | -0.960 |
�� | -0.936 |
uthor | -0.893 |
obin | -0.866 |
ablishment | -0.862 |
Token | ussed |
Token ID | 29569 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
imation | +4.639 |
�� | +4.148 |
uthor | +3.984 |
usion | +3.935 |
ablishment | +3.929 |
Neg logit contributions | |
Smile | -6.917 |
idas | -6.815 |
Babel | -6.766 |
blush | -6.735 |
Tokens | -6.664 |
Token | joint |
Token ID | 6466 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
imation | +2.706 |
�� | +2.617 |
uthor | +2.479 |
obin | +2.434 |
usion | +2.415 |
Neg logit contributions | |
idas | -2.081 |
Smile | -2.025 |
Babel | -1.968 |
tto | -1.967 |
ラン | -1.966 |
Token | venture |
Token ID | 13189 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
idas | +1.157 |
Smile | +1.144 |
Babel | +1.103 |
tto | +1.086 |
ラン | +1.086 |
Neg logit contributions | |
imation | -1.811 |
�� | -1.770 |
uthor | -1.690 |
obin | -1.640 |
ablishment | -1.634 |
Token | , |
Token ID | 11 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
imation | +0.372 |
�� | +0.360 |
uthor | +0.342 |
obin | +0.332 |
ablishment | +0.331 |
Neg logit contributions | |
idas | -0.318 |
Smile | -0.314 |
Babel | -0.305 |
ラン | -0.303 |
tto | -0.302 |
Token | S |
Token ID | 311 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
idas | +0.187 |
Smile | +0.185 |
Babel | +0.179 |
ラン | +0.177 |
tto | +0.177 |
Neg logit contributions | |
imation | -0.243 |
�� | -0.237 |
uthor | -0.225 |
obin | -0.218 |
ablishment | -0.218 |
Token | guilty |
Token ID | 6717 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
imation | +0.948 |
�� | +0.919 |
uthor | +0.863 |
obin | +0.846 |
usion | +0.839 |
Neg logit contributions | |
idas | -0.844 |
Smile | -0.835 |
Babel | -0.811 |
ラン | -0.807 |
tto | -0.801 |
Token | of |
Token ID | 286 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
imation | +0.150 |
�� | +0.146 |
uthor | +0.139 |
obin | +0.134 |
ablishment | +0.134 |
Neg logit contributions | |
idas | -0.127 |
Smile | -0.126 |
Babel | -0.122 |
ラン | -0.121 |
tto | -0.121 |
Token | doing |
Token ID | 1804 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
imation | +0.254 |
�� | +0.247 |
uthor | +0.233 |
obin | +0.226 |
ablishment | +0.225 |
Neg logit contributions | |
idas | -0.228 |
Smile | -0.225 |
Babel | -0.219 |
ラン | -0.218 |
tto | -0.218 |
Token | ). |
Token ID | 737 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
imation | +0.996 |
�� | +0.960 |
uthor | +0.908 |
obin | +0.883 |
usion | +0.875 |
Neg logit contributions | |
idas | -0.897 |
Smile | -0.885 |
Babel | -0.863 |
ラン | -0.861 |
tto | -0.852 |
Token | By |
Token ID | 2750 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
idas | +0.146 |
Smile | +0.144 |
Babel | +0.140 |
ラン | +0.139 |
tto | +0.139 |
Neg logit contributions | |
imation | -0.150 |
�� | -0.146 |
uthor | -0.138 |
obin | -0.133 |
ablishment | -0.133 |
Token | foc |
Token ID | 2133 |
Feature activation | -7.89e+00 |
Pos logit contributions | |
idas | +1.175 |
Smile | +1.170 |
Babel | +1.130 |
tto | +1.112 |
blush | +1.111 |
Neg logit contributions | |
imation | -1.547 |
�� | -1.506 |
uthor | -1.437 |
ablishment | -1.391 |
obin | -1.389 |
Token | uss |
Token ID | 1046 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
imation | +5.008 |
�� | +4.414 |
usion | +4.313 |
uthor | +4.251 |
ablishment | +4.097 |
Neg logit contributions | |
Smile | -6.545 |
idas | -6.476 |
blush | -6.412 |
ラン | -6.401 |
Babel | -6.394 |
Token | ing |
Token ID | 278 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
imation | +2.195 |
�� | +2.121 |
uthor | +1.993 |
usion | +1.936 |
obin | +1.934 |
Neg logit contributions | |
idas | -1.991 |
Smile | -1.976 |
Babel | -1.914 |
tto | -1.913 |
ラン | -1.910 |
Token | on |
Token ID | 319 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
imation | +1.285 |
�� | +1.242 |
uthor | +1.177 |
obin | +1.138 |
usion | +1.130 |
Neg logit contributions | |
idas | -1.186 |
Smile | -1.168 |
Babel | -1.137 |
tto | -1.132 |
ラン | -1.131 |
Token | the |
Token ID | 262 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
idas | +0.090 |
Smile | +0.089 |
Babel | +0.086 |
tto | +0.085 |
ラン | +0.085 |
Neg logit contributions | |
imation | -0.111 |
�� | -0.108 |
uthor | -0.102 |
obin | -0.099 |
ablishment | -0.099 |
Token | pure |
Token ID | 5899 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
idas | +0.346 |
Smile | +0.340 |
Babel | +0.329 |
ラン | +0.325 |
tto | +0.325 |
Neg logit contributions | |
imation | -0.542 |
�� | -0.528 |
uthor | -0.504 |
obin | -0.490 |
ablishment | -0.488 |
Token | AND |
Token ID | 6981 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
imation | +0.593 |
�� | +0.574 |
uthor | +0.540 |
obin | +0.519 |
ablishment | +0.517 |
Neg logit contributions | |
idas | -0.685 |
Smile | -0.679 |
Babel | -0.661 |
ラン | -0.655 |
tto | -0.655 |
Token | OF |
Token ID | 3963 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
imation | +0.140 |
�� | +0.135 |
uthor | +0.128 |
obin | +0.123 |
ablishment | +0.123 |
Neg logit contributions | |
idas | -0.141 |
Smile | -0.140 |
Babel | -0.136 |
tto | -0.135 |
ラン | -0.134 |
Token | EXT |
Token ID | 27489 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
imation | +0.556 |
�� | +0.540 |
uthor | +0.512 |
obin | +0.497 |
ablishment | +0.494 |
Neg logit contributions | |
idas | -0.461 |
Smile | -0.455 |
Babel | -0.441 |
ラン | -0.438 |
tto | -0.437 |
Token | REM |
Token ID | 40726 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
imation | +2.039 |
�� | +1.961 |
uthor | +1.837 |
obin | +1.800 |
usion | +1.784 |
Neg logit contributions | |
idas | -1.950 |
Smile | -1.918 |
Babel | -1.861 |
tto | -1.847 |
ラン | -1.843 |
Token | ELY |
Token ID | 30943 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
imation | +4.021 |
�� | +3.875 |
uthor | +3.658 |
usion | +3.581 |
obin | +3.562 |
Neg logit contributions | |
idas | -3.482 |
Smile | -3.468 |
blush | -3.426 |
tto | -3.413 |
Babel | -3.393 |
Token | EXP |
Token ID | 25703 |
Feature activation | -7.83e+00 |
Pos logit contributions | |
imation | +1.363 |
�� | +1.323 |
uthor | +1.252 |
obin | +1.220 |
usion | +1.210 |
Neg logit contributions | |
idas | -1.139 |
Smile | -1.114 |
Babel | -1.083 |
ラン | -1.078 |
tto | -1.077 |
Token | ENS |
Token ID | 16938 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
imation | +4.555 |
�� | +4.311 |
uthor | +3.981 |
usion | +3.921 |
obin | +3.851 |
Neg logit contributions | |
idas | -6.684 |
Smile | -6.660 |
Babel | -6.480 |
tto | -6.464 |
blush | -6.459 |
Token | IVE |
Token ID | 9306 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
imation | +1.213 |
�� | +1.170 |
uthor | +1.091 |
obin | +1.054 |
ablishment | +1.045 |
Neg logit contributions | |
idas | -1.492 |
Smile | -1.479 |
Babel | -1.443 |
tto | -1.432 |
ラン | -1.430 |
Token | BE |
Token ID | 9348 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
imation | +0.128 |
�� | +0.124 |
uthor | +0.118 |
obin | +0.114 |
ablishment | +0.113 |
Neg logit contributions | |
idas | -0.104 |
Smile | -0.102 |
Babel | -0.099 |
ラン | -0.098 |
tto | -0.098 |
Token | ER |
Token ID | 1137 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
imation | +0.071 |
�� | +0.069 |
uthor | +0.066 |
obin | +0.064 |
ablishment | +0.064 |
Neg logit contributions | |
idas | -0.048 |
Smile | -0.047 |
Babel | -0.045 |
tto | -0.045 |
ラン | -0.045 |
Token | WITHOUT |
Token ID | 42881 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
imation | +0.186 |
�� | +0.181 |
uthor | +0.171 |
obin | +0.166 |
ablishment | +0.165 |
Neg logit contributions | |
idas | -0.164 |
Smile | -0.162 |
Babel | -0.157 |
ラン | -0.156 |
tto | -0.155 |
Token | 992 |
Token ID | 41561 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
idas | +0.425 |
Smile | +0.421 |
Babel | +0.407 |
ラン | +0.402 |
tto | +0.401 |
Neg logit contributions | |
imation | -0.557 |
�� | -0.543 |
uthor | -0.516 |
obin | -0.501 |
ablishment | -0.499 |
Token | chronic |
Token ID | 10726 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
imation | +0.749 |
�� | +0.730 |
uthor | +0.698 |
obin | +0.679 |
ablishment | +0.674 |
Neg logit contributions | |
idas | -0.450 |
Smile | -0.442 |
Babel | -0.429 |
ラン | -0.422 |
tto | -0.422 |
Token | � |
Token ID | 564 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
imation | +0.389 |
�� | +0.379 |
uthor | +0.362 |
obin | +0.351 |
ablishment | +0.350 |
Neg logit contributions | |
idas | -0.271 |
Smile | -0.268 |
Babel | -0.259 |
ラン | -0.255 |
tto | -0.255 |
Token | � |
Token ID | 246 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
idas | +0.794 |
Smile | +0.785 |
Babel | +0.768 |
ラン | +0.765 |
tto | +0.763 |
Neg logit contributions | |
imation | -0.487 |
�� | -0.466 |
uthor | -0.434 |
obin | -0.420 |
ablishment | -0.411 |
Token | John |
Token ID | 7554 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
imation | +1.034 |
�� | +1.005 |
uthor | +0.957 |
obin | +0.930 |
ablishment | +0.921 |
Neg logit contributions | |
idas | -0.819 |
Smile | -0.814 |
Babel | -0.788 |
tto | -0.776 |
ラン | -0.776 |
Token | Hancock |
Token ID | 39261 |
Feature activation | -7.70e+00 |
Pos logit contributions | |
imation | +0.743 |
�� | +0.723 |
uthor | +0.691 |
obin | +0.671 |
ablishment | +0.666 |
Neg logit contributions | |
idas | -0.525 |
Smile | -0.518 |
Babel | -0.502 |
tto | -0.499 |
ラン | -0.498 |
Token | � |
Token ID | 447 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
imation | +5.778 |
�� | +5.675 |
uthor | +5.340 |
obin | +5.170 |
usion | +5.127 |
Neg logit contributions | |
idas | -5.122 |
Babel | -5.066 |
Smile | -5.014 |
tto | -4.949 |
ラン | -4.868 |
Token | � |
Token ID | 247 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
imation | +0.241 |
�� | +0.232 |
uthor | +0.217 |
obin | +0.208 |
ablishment | +0.206 |
Neg logit contributions | |
idas | -0.343 |
Smile | -0.340 |
Babel | -0.332 |
ラン | -0.329 |
tto | -0.329 |
Token | s |
Token ID | 82 |
Feature activation | +9.98e-02 |
Pos logit contributions | |
imation | +0.513 |
�� | +0.499 |
uthor | +0.475 |
obin | +0.461 |
ablishment | +0.457 |
Neg logit contributions | |
idas | -0.403 |
Smile | -0.400 |
Babel | -0.389 |
tto | -0.383 |
ラン | -0.383 |
Token | � |
Token ID | 447 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
idas | +0.065 |
Smile | +0.064 |
Babel | +0.062 |
ラン | +0.061 |
tto | +0.061 |
Neg logit contributions | |
imation | -0.083 |
�� | -0.080 |
uthor | -0.077 |
obin | -0.074 |
ablishment | -0.074 |
Token | � |
Token ID | 247 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
imation | +0.203 |
�� | +0.195 |
uthor | +0.181 |
obin | +0.173 |
ablishment | +0.172 |
Neg logit contributions | |
idas | -0.311 |
Smile | -0.309 |
Babel | -0.302 |
ラン | -0.300 |
tto | -0.299 |
Token | able |
Token ID | 540 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
idas | +1.546 |
Smile | +1.540 |
Babel | +1.509 |
ラン | +1.489 |
blush | +1.487 |
Neg logit contributions | |
imation | -0.863 |
�� | -0.815 |
uthor | -0.761 |
obin | -0.732 |
ablishment | -0.718 |
Token | version |
Token ID | 2196 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
idas | +0.444 |
Smile | +0.441 |
Babel | +0.428 |
blush | +0.422 |
ラン | +0.420 |
Neg logit contributions | |
imation | -0.575 |
�� | -0.565 |
uthor | -0.538 |
ablishment | -0.521 |
obin | -0.521 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
idas | +0.818 |
Smile | +0.810 |
Babel | +0.790 |
tto | +0.776 |
blush | +0.776 |
Neg logit contributions | |
imation | -0.748 |
�� | -0.722 |
uthor | -0.678 |
ablishment | -0.655 |
obin | -0.652 |
Token | Rob |
Token ID | 14350 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
imation | +1.230 |
�� | +1.190 |
uthor | +1.124 |
obin | +1.085 |
usion | +1.076 |
Neg logit contributions | |
idas | -1.251 |
Smile | -1.247 |
Babel | -1.219 |
blush | -1.199 |
ラン | -1.197 |
Token | C |
Token ID | 327 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
imation | +1.514 |
�� | +1.471 |
uthor | +1.394 |
obin | +1.365 |
usion | +1.351 |
Neg logit contributions | |
Smile | -1.178 |
idas | -1.177 |
Babel | -1.141 |
ラン | -1.136 |
blush | -1.132 |
Token | estern |
Token ID | 3330 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
imation | +0.426 |
�� | +0.396 |
uthor | +0.353 |
obin | +0.324 |
usion | +0.317 |
Neg logit contributions | |
idas | -1.358 |
Smile | -1.352 |
Babel | -1.327 |
ラン | -1.322 |
tto | -1.317 |
Token | ino |
Token ID | 2879 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
imation | +4.765 |
�� | +4.092 |
usion | +4.083 |
uthor | +4.025 |
obin | +4.019 |
Neg logit contributions | |
Smile | -6.352 |
idas | -6.285 |
Tokens | -6.279 |
ラン | -6.259 |
Babel | -6.246 |
Token | hosts |
Token ID | 11453 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
imation | +1.240 |
�� | +1.189 |
uthor | +1.143 |
obin | +1.107 |
usion | +1.097 |
Neg logit contributions | |
idas | -1.064 |
Smile | -1.053 |
ラン | -1.026 |
Babel | -1.023 |
tto | -1.011 |
Token | a |
Token ID | 257 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
imation | +0.879 |
�� | +0.847 |
uthor | +0.806 |
obin | +0.786 |
usion | +0.779 |
Neg logit contributions | |
idas | -0.730 |
Smile | -0.718 |
ラン | -0.710 |
tto | -0.699 |
Babel | -0.696 |
Token | jam |
Token ID | 16853 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
imation | +0.497 |
�� | +0.480 |
uthor | +0.457 |
obin | +0.448 |
usion | +0.445 |
Neg logit contributions | |
idas | -0.340 |
Smile | -0.328 |
ラン | -0.324 |
tto | -0.318 |
Babel | -0.318 |
Token | packed |
Token ID | 11856 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
idas | +1.446 |
Smile | +1.422 |
Babel | +1.380 |
tto | +1.359 |
ラン | +1.354 |
Neg logit contributions | |
imation | -1.845 |
�� | -1.814 |
uthor | -1.729 |
ablishment | -1.666 |
obin | -1.653 |
Token | happen |
Token ID | 1645 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
imation | +0.225 |
�� | +0.219 |
uthor | +0.209 |
obin | +0.203 |
ablishment | +0.202 |
Neg logit contributions | |
idas | -0.154 |
Smile | -0.152 |
Babel | -0.147 |
ラン | -0.145 |
tto | -0.145 |
Token | with |
Token ID | 351 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
idas | +1.371 |
Smile | +1.357 |
Babel | +1.316 |
tto | +1.307 |
blush | +1.302 |
Neg logit contributions | |
imation | -1.587 |
�� | -1.545 |
uthor | -1.468 |
ablishment | -1.415 |
obin | -1.415 |
Token | solid |
Token ID | 4735 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
idas | +0.396 |
Smile | +0.393 |
Babel | +0.380 |
tto | +0.375 |
ラン | +0.375 |
Neg logit contributions | |
imation | -0.515 |
�� | -0.501 |
uthor | -0.477 |
obin | -0.462 |
ablishment | -0.461 |
Token | - |
Token ID | 12 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
imation | +0.879 |
�� | +0.856 |
uthor | +0.817 |
obin | +0.791 |
ablishment | +0.789 |
Neg logit contributions | |
idas | -0.625 |
Smile | -0.618 |
Babel | -0.597 |
ラン | -0.591 |
tto | -0.590 |
Token | organ |
Token ID | 9971 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
idas | +0.157 |
Smile | +0.155 |
Babel | +0.151 |
tto | +0.150 |
ラン | +0.150 |
Neg logit contributions | |
imation | -0.151 |
�� | -0.146 |
uthor | -0.138 |
obin | -0.133 |
ablishment | -0.132 |
Token | transpl |
Token ID | 37100 |
Feature activation | -7.60e+00 |
Pos logit contributions | |
imation | +1.675 |
�� | +1.624 |
uthor | +1.535 |
obin | +1.499 |
usion | +1.487 |
Neg logit contributions | |
idas | -1.416 |
Smile | -1.396 |
Babel | -1.356 |
tto | -1.347 |
ラン | -1.342 |
Token | ants |
Token ID | 1187 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
imation | +5.492 |
usion | +4.983 |
�� | +4.917 |
uthor | +4.883 |
obin | +4.851 |
Neg logit contributions | |
Smile | -5.758 |
idas | -5.634 |
ラン | -5.615 |
Babel | -5.494 |
tto | -5.421 |
Token | , |
Token ID | 11 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
imation | +0.259 |
�� | +0.252 |
uthor | +0.239 |
obin | +0.231 |
ablishment | +0.230 |
Neg logit contributions | |
idas | -0.232 |
Smile | -0.230 |
Babel | -0.223 |
tto | -0.221 |
ラン | -0.221 |
Token | where |
Token ID | 810 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
imation | +0.303 |
�� | +0.295 |
uthor | +0.280 |
obin | +0.270 |
ablishment | +0.269 |
Neg logit contributions | |
idas | -0.262 |
Smile | -0.257 |
Babel | -0.250 |
ラン | -0.249 |
tto | -0.248 |
Token | a |
Token ID | 257 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
imation | +1.059 |
�� | +1.032 |
uthor | +0.978 |
obin | +0.952 |
usion | +0.943 |
Neg logit contributions | |
idas | -0.878 |
Smile | -0.867 |
Babel | -0.840 |
ラン | -0.835 |
tto | -0.831 |
Token | patient |
Token ID | 5827 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
imation | +0.054 |
�� | +0.052 |
uthor | +0.049 |
obin | +0.047 |
ablishment | +0.046 |
Neg logit contributions | |
idas | -0.063 |
Smile | -0.063 |
Babel | -0.061 |
ラン | -0.061 |
tto | -0.061 |
Token | if |
Token ID | 611 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
imation | +1.722 |
�� | +1.658 |
uthor | +1.573 |
obin | +1.528 |
ablishment | +1.516 |
Neg logit contributions | |
idas | -1.547 |
Smile | -1.530 |
Babel | -1.493 |
ラン | -1.483 |
tto | -1.471 |
Token | carefully |
Token ID | 7773 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
imation | +0.142 |
�� | +0.138 |
uthor | +0.131 |
obin | +0.127 |
ablishment | +0.126 |
Neg logit contributions | |
idas | -0.126 |
Smile | -0.125 |
Babel | -0.121 |
ラン | -0.120 |
tto | -0.120 |
Token | guided |
Token ID | 17455 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
imation | +2.261 |
�� | +2.170 |
uthor | +2.042 |
obin | +1.962 |
usion | +1.953 |
Neg logit contributions | |
idas | -2.721 |
Smile | -2.698 |
Babel | -2.624 |
ラン | -2.616 |
tto | -2.594 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
imation | +2.443 |
�� | +2.356 |
uthor | +2.246 |
obin | +2.160 |
ablishment | +2.149 |
Neg logit contributions | |
idas | -2.212 |
Smile | -2.183 |
Babel | -2.134 |
ラン | -2.123 |
tto | -2.093 |
Token | The |
Token ID | 383 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
imation | +0.220 |
�� | +0.213 |
uthor | +0.202 |
obin | +0.195 |
ablishment | +0.194 |
Neg logit contributions | |
idas | -0.204 |
Smile | -0.202 |
Babel | -0.196 |
ラン | -0.194 |
tto | -0.194 |
Token | rave |
Token ID | 46242 |
Feature activation | -7.42e+00 |
Pos logit contributions | |
imation | +0.335 |
�� | +0.325 |
uthor | +0.310 |
obin | +0.302 |
ablishment | +0.300 |
Neg logit contributions | |
idas | -0.232 |
Smile | -0.228 |
Babel | -0.221 |
ラン | -0.219 |
tto | -0.219 |
Token | community |
Token ID | 2055 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
imation | +6.933 |
�� | +6.624 |
uthor | +6.451 |
usion | +6.305 |
ablishment | +6.279 |
Neg logit contributions | |
idas | -3.791 |
Smile | -3.655 |
Babel | -3.545 |
ラン | -3.514 |
tto | -3.496 |
Token | should |
Token ID | 815 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
imation | +0.621 |
�� | +0.604 |
uthor | +0.575 |
obin | +0.557 |
ablishment | +0.554 |
Neg logit contributions | |
idas | -0.495 |
Smile | -0.490 |
Babel | -0.475 |
tto | -0.469 |
ラン | -0.469 |
Token | act |
Token ID | 719 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
imation | +1.454 |
�� | +1.386 |
uthor | +1.332 |
obin | +1.301 |
usion | +1.287 |
Neg logit contributions | |
idas | -1.130 |
Smile | -1.109 |
ラン | -1.092 |
Babel | -1.083 |
tto | -1.062 |
Token | with |
Token ID | 351 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
imation | +0.666 |
�� | +0.647 |
uthor | +0.614 |
obin | +0.594 |
ablishment | +0.590 |
Neg logit contributions | |
idas | -0.586 |
Smile | -0.581 |
Babel | -0.563 |
ラン | -0.558 |
tto | -0.557 |
Token | caution |
Token ID | 13041 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
imation | +0.196 |
�� | +0.191 |
uthor | +0.182 |
obin | +0.176 |
ablishment | +0.175 |
Neg logit contributions | |
idas | -0.147 |
Smile | -0.145 |
Babel | -0.141 |
tto | -0.139 |
ラン | -0.139 |
Token | and |
Token ID | 290 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
imation | +2.559 |
�� | +2.471 |
uthor | +2.379 |
obin | +2.259 |
ablishment | +2.257 |
Neg logit contributions | |
Smile | -2.444 |
idas | -2.440 |
ラン | -2.376 |
Babel | -2.365 |
blush | -2.330 |
Token | the |
Token ID | 262 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
imation | +0.368 |
�� | +0.358 |
uthor | +0.341 |
obin | +0.329 |
ablishment | +0.329 |
Neg logit contributions | |
idas | -0.296 |
Smile | -0.293 |
Babel | -0.284 |
ラン | -0.282 |
tto | -0.281 |
Token | investigation |
Token ID | 3645 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
imation | +0.622 |
�� | +0.599 |
uthor | +0.577 |
usion | +0.556 |
obin | +0.555 |
Neg logit contributions | |
idas | -0.446 |
Smile | -0.439 |
ラン | -0.423 |
Babel | -0.423 |
tto | -0.421 |
Token | had |
Token ID | 550 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
imation | +0.580 |
�� | +0.563 |
uthor | +0.536 |
obin | +0.518 |
usion | +0.516 |
Neg logit contributions | |
idas | -0.491 |
Smile | -0.486 |
ラン | -0.473 |
Babel | -0.471 |
tto | -0.465 |
Token | been |
Token ID | 587 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
imation | +1.504 |
�� | +1.468 |
uthor | +1.392 |
obin | +1.333 |
usion | +1.331 |
Neg logit contributions | |
idas | -1.515 |
Smile | -1.503 |
Babel | -1.459 |
ラン | -1.452 |
tto | -1.444 |
Token | priorit |
Token ID | 19086 |
Feature activation | -7.29e+00 |
Pos logit contributions | |
imation | +1.415 |
�� | +1.391 |
uthor | +1.323 |
obin | +1.275 |
usion | +1.271 |
Neg logit contributions | |
idas | -1.154 |
Smile | -1.143 |
ラン | -1.106 |
Babel | -1.094 |
tto | -1.093 |
Token | ised |
Token ID | 1417 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
imation | +5.419 |
�� | +5.035 |
uthor | +4.704 |
ablishment | +4.641 |
usion | +4.604 |
Neg logit contributions | |
Smile | -5.268 |
idas | -5.189 |
ラン | -5.104 |
Babel | -5.082 |
tto | -5.036 |
Token | accordingly |
Token ID | 16062 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
imation | +4.482 |
�� | +4.300 |
uthor | +4.159 |
obin | +3.946 |
ablishment | +3.929 |
Neg logit contributions | |
idas | -4.488 |
Smile | -4.454 |
ラン | -4.409 |
Babel | -4.311 |
tto | -4.292 |
Token | , |
Token ID | 11 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
imation | +1.493 |
�� | +1.447 |
uthor | +1.377 |
obin | +1.322 |
ablishment | +1.318 |
Neg logit contributions | |
idas | -1.391 |
Smile | -1.382 |
Babel | -1.342 |
ラン | -1.331 |
tto | -1.328 |
Token | � |
Token ID | 447 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
imation | +0.602 |
�� | +0.584 |
uthor | +0.556 |
obin | +0.536 |
ablishment | +0.535 |
Neg logit contributions | |
idas | -0.512 |
Smile | -0.506 |
Babel | -0.491 |
ラン | -0.487 |
tto | -0.486 |
Token | � |
Token ID | 251 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
imation | +0.527 |
�� | +0.510 |
uthor | +0.475 |
obin | +0.454 |
ablishment | +0.452 |
Neg logit contributions | |
idas | -0.719 |
Smile | -0.713 |
Babel | -0.696 |
tto | -0.690 |
ラン | -0.689 |
Token | bad |
Token ID | 2089 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
imation | +0.464 |
�� | +0.452 |
uthor | +0.430 |
obin | +0.417 |
ablishment | +0.415 |
Neg logit contributions | |
idas | -0.347 |
Smile | -0.343 |
Babel | -0.332 |
ラン | -0.329 |
tto | -0.328 |
Token | debts |
Token ID | 20250 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
imation | +0.622 |
�� | +0.605 |
uthor | +0.577 |
obin | +0.561 |
ablishment | +0.559 |
Neg logit contributions | |
idas | -0.405 |
Smile | -0.399 |
Babel | -0.386 |
ラン | -0.382 |
tto | -0.381 |
Token | . |
Token ID | 13 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
imation | +1.363 |
�� | +1.316 |
uthor | +1.251 |
obin | +1.207 |
ablishment | +1.202 |
Neg logit contributions | |
idas | -1.221 |
Smile | -1.207 |
Babel | -1.177 |
ラン | -1.167 |
tto | -1.160 |
Token | Standing |
Token ID | 22493 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
imation | +0.298 |
�� | +0.289 |
uthor | +0.274 |
obin | +0.265 |
ablishment | +0.264 |
Neg logit contributions | |
idas | -0.269 |
Smile | -0.266 |
Babel | -0.259 |
ラン | -0.256 |
tto | -0.256 |
Token | Lord |
Token ID | 4453 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
idas | +1.005 |
Smile | +0.995 |
Babel | +0.963 |
tto | +0.952 |
ラン | +0.950 |
Neg logit contributions | |
imation | -1.314 |
�� | -1.279 |
uthor | -1.218 |
obin | -1.182 |
ablishment | -1.176 |
Token | Gan |
Token ID | 23207 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
imation | +0.131 |
�� | +0.128 |
uthor | +0.122 |
obin | +0.119 |
ablishment | +0.118 |
Neg logit contributions | |
idas | -0.078 |
Smile | -0.077 |
Babel | -0.074 |
ラン | -0.073 |
tto | -0.073 |
Token | esh |
Token ID | 5069 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
imation | +4.592 |
�� | +4.187 |
uthor | +4.117 |
usion | +4.016 |
obin | +4.010 |
Neg logit contributions | |
Smile | -5.819 |
ラン | -5.761 |
idas | -5.749 |
Babel | -5.726 |
blush | -5.679 |
Token | and |
Token ID | 290 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
idas | +0.277 |
Smile | +0.274 |
Babel | +0.265 |
tto | +0.262 |
ラン | +0.262 |
Neg logit contributions | |
imation | -0.348 |
�� | -0.338 |
uthor | -0.322 |
obin | -0.312 |
ablishment | -0.310 |
Token | Vish |
Token ID | 36900 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
imation | +0.115 |
�� | +0.112 |
uthor | +0.107 |
obin | +0.103 |
ablishment | +0.103 |
Neg logit contributions | |
idas | -0.078 |
Smile | -0.077 |
Babel | -0.075 |
ラン | -0.074 |
tto | -0.074 |
Token | nu |
Token ID | 28803 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
idas | +1.037 |
Smile | +1.012 |
Babel | +0.966 |
tto | +0.957 |
ラン | +0.938 |
Neg logit contributions | |
imation | -2.020 |
�� | -1.980 |
uthor | -1.899 |
obin | -1.849 |
ablishment | -1.843 |
Token | D |
Token ID | 360 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
idas | +0.031 |
Smile | +0.031 |
Babel | +0.030 |
ラン | +0.030 |
tto | +0.030 |
Neg logit contributions | |
imation | -0.041 |
�� | -0.039 |
uthor | -0.038 |
obin | -0.036 |
ablishment | -0.036 |
Token | + |
Token ID | 10 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
idas | +1.332 |
Smile | +1.323 |
Babel | +1.286 |
ラン | +1.282 |
tto | +1.280 |
Neg logit contributions | |
imation | -1.033 |
�� | -1.001 |
uthor | -0.938 |
ablishment | -0.899 |
obin | -0.898 |
Token | Law |
Token ID | 3854 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
imation | +0.195 |
�� | +0.190 |
uthor | +0.181 |
obin | +0.175 |
ablishment | +0.174 |
Neg logit contributions | |
idas | -0.156 |
Smile | -0.154 |
Babel | -0.149 |
ラン | -0.148 |
tto | -0.148 |
Token | - |
Token ID | 12 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
idas | +1.659 |
Smile | +1.635 |
Babel | +1.579 |
tto | +1.560 |
ラン | +1.556 |
Neg logit contributions | |
imation | -2.521 |
�� | -2.462 |
uthor | -2.346 |
obin | -2.280 |
ablishment | -2.275 |
Token | abiding |
Token ID | 43056 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
imation | +0.759 |
�� | +0.734 |
uthor | +0.702 |
obin | +0.679 |
ablishment | +0.675 |
Neg logit contributions | |
idas | -0.637 |
Smile | -0.634 |
Babel | -0.615 |
blush | -0.608 |
ラン | -0.606 |
Token | , |
Token ID | 11 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
idas | +0.127 |
Smile | +0.127 |
Babel | +0.122 |
tto | +0.121 |
ラン | +0.121 |
Neg logit contributions | |
imation | -0.148 |
�� | -0.144 |
uthor | -0.136 |
obin | -0.132 |
ablishment | -0.132 |
Token | Ded |
Token ID | 35023 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
idas | +0.383 |
Smile | +0.382 |
Babel | +0.369 |
tto | +0.363 |
ラン | +0.363 |
Neg logit contributions | |
imation | -0.467 |
�� | -0.453 |
uthor | -0.430 |
obin | -0.417 |
ablishment | -0.416 |
Token | icated |
Token ID | 3474 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
imation | +2.100 |
�� | +1.682 |
uthor | +1.630 |
usion | +1.483 |
obin | +1.462 |
Neg logit contributions | |
idas | -8.308 |
Smile | -8.272 |
Babel | -8.259 |
ラン | -8.178 |
tto | -8.119 |
Token | , |
Token ID | 11 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
imation | +3.122 |
�� | +3.032 |
uthor | +2.916 |
ablishment | +2.787 |
obin | +2.780 |
Neg logit contributions | |
idas | -2.946 |
Smile | -2.842 |
Babel | -2.810 |
ラン | -2.799 |
tto | -2.777 |
Token | Log |
Token ID | 5972 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
Smile | +0.432 |
idas | +0.431 |
Babel | +0.416 |
tto | +0.410 |
ラン | +0.408 |
Neg logit contributions | |
imation | -0.514 |
�� | -0.500 |
uthor | -0.473 |
obin | -0.459 |
ablishment | -0.457 |
Token | ical |
Token ID | 605 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
idas | +3.020 |
Smile | +3.013 |
Babel | +2.917 |
tto | +2.863 |
ラン | +2.842 |
Neg logit contributions | |
imation | -2.800 |
�� | -2.713 |
uthor | -2.546 |
obin | -2.471 |
usion | -2.446 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Smile | +1.319 |
idas | +1.301 |
Babel | +1.258 |
tto | +1.242 |
ラン | +1.239 |
Neg logit contributions | |
imation | -1.669 |
�� | -1.627 |
uthor | -1.524 |
obin | -1.490 |
ablishment | -1.485 |
Token | back |
Token ID | 736 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
idas | +0.226 |
Smile | +0.224 |
Babel | +0.216 |
tto | +0.213 |
ラン | +0.213 |
Neg logit contributions | |
imation | -0.326 |
�� | -0.318 |
uthor | -0.303 |
obin | -0.294 |
ablishment | -0.293 |
Token | ' |
Token ID | 6 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
idas | +1.097 |
Smile | +1.089 |
Babel | +1.061 |
tto | +1.044 |
blush | +1.040 |
Neg logit contributions | |
imation | -1.248 |
�� | -1.216 |
uthor | -1.154 |
obin | -1.112 |
ablishment | -1.111 |
Token | the |
Token ID | 262 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
imation | +0.517 |
�� | +0.501 |
uthor | +0.476 |
obin | +0.461 |
ablishment | +0.458 |
Neg logit contributions | |
idas | -0.448 |
Smile | -0.443 |
Babel | -0.429 |
ラン | -0.427 |
tto | -0.426 |
Token | web |
Token ID | 3992 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
idas | +0.107 |
Smile | +0.105 |
Babel | +0.101 |
ラン | +0.100 |
tto | +0.100 |
Neg logit contributions | |
imation | -0.171 |
�� | -0.166 |
uthor | -0.159 |
obin | -0.155 |
ablishment | -0.154 |
Token | A |
Token ID | 317 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
imation | +0.636 |
�� | +0.617 |
uthor | +0.587 |
obin | +0.572 |
ablishment | +0.569 |
Neg logit contributions | |
idas | -0.472 |
Smile | -0.466 |
Babel | -0.450 |
ラン | -0.448 |
tto | -0.447 |
Token | Downing |
Token ID | 31355 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
idas | +0.286 |
Smile | +0.283 |
Babel | +0.272 |
ラン | +0.271 |
tto | +0.269 |
Neg logit contributions | |
imation | -0.469 |
�� | -0.457 |
uthor | -0.438 |
obin | -0.425 |
ablishment | -0.423 |
Token | Street |
Token ID | 3530 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
imation | +5.922 |
�� | +5.559 |
usion | +5.325 |
uthor | +5.255 |
ablishment | +5.203 |
Neg logit contributions | |
idas | -4.609 |
ラン | -4.472 |
Smile | -4.381 |
tto | -4.228 |
Tokens | -4.200 |
Token | petition |
Token ID | 8853 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
imation | +1.635 |
�� | +1.578 |
uthor | +1.507 |
usion | +1.457 |
obin | +1.450 |
Neg logit contributions | |
idas | -1.403 |
Smile | -1.364 |
ラン | -1.345 |
Babel | -1.322 |
tto | -1.319 |
Token | is |
Token ID | 318 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
idas | +1.871 |
Smile | +1.809 |
Babel | +1.754 |
tto | +1.748 |
blush | +1.738 |
Neg logit contributions | |
imation | -2.644 |
�� | -2.579 |
uthor | -2.446 |
ablishment | -2.394 |
obin | -2.393 |
Token | calling |
Token ID | 4585 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
imation | +0.361 |
�� | +0.352 |
uthor | +0.337 |
obin | +0.328 |
ablishment | +0.326 |
Neg logit contributions | |
idas | -0.214 |
Smile | -0.212 |
Babel | -0.204 |
ラン | -0.202 |
tto | -0.201 |
Token | for |
Token ID | 329 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
imation | +0.097 |
�� | +0.094 |
uthor | +0.089 |
obin | +0.085 |
ablishment | +0.085 |
Neg logit contributions | |
idas | -0.100 |
Smile | -0.099 |
Babel | -0.097 |
ラン | -0.096 |
tto | -0.096 |
Token | � |
Token ID | 250 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
idas | +0.309 |
Smile | +0.307 |
Babel | +0.299 |
tto | +0.296 |
ラン | +0.296 |
Neg logit contributions | |
imation | -0.276 |
�� | -0.266 |
uthor | -0.251 |
obin | -0.242 |
ablishment | -0.241 |
Token | These |
Token ID | 4711 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
idas | +0.266 |
Smile | +0.265 |
Babel | +0.257 |
tto | +0.255 |
ラン | +0.255 |
Neg logit contributions | |
imation | -0.259 |
�� | -0.250 |
uthor | -0.238 |
obin | -0.228 |
ablishment | -0.226 |
Token | seats |
Token ID | 8632 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
imation | +0.409 |
�� | +0.397 |
uthor | +0.378 |
obin | +0.367 |
ablishment | +0.366 |
Neg logit contributions | |
idas | -0.310 |
Smile | -0.307 |
Babel | -0.297 |
ラン | -0.293 |
tto | -0.293 |
Token | are |
Token ID | 389 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
imation | +1.325 |
�� | +1.282 |
uthor | +1.221 |
obin | +1.188 |
ablishment | +1.181 |
Neg logit contributions | |
idas | -1.038 |
Smile | -1.026 |
Babel | -0.993 |
ラン | -0.985 |
tto | -0.979 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
imation | +1.241 |
�� | +1.207 |
uthor | +1.151 |
obin | +1.117 |
usion | +1.113 |
Neg logit contributions | |
idas | -0.846 |
Smile | -0.833 |
Babel | -0.804 |
ラン | -0.796 |
tto | -0.791 |
Token | Everest |
Token ID | 41336 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
imation | +0.914 |
�� | +0.887 |
uthor | +0.843 |
obin | +0.825 |
usion | +0.820 |
Neg logit contributions | |
idas | -0.608 |
Smile | -0.600 |
Babel | -0.578 |
tto | -0.573 |
ラン | -0.573 |
Token | of |
Token ID | 286 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
imation | +5.238 |
�� | +5.010 |
ablishment | +4.604 |
uthor | +4.581 |
usion | +4.541 |
Neg logit contributions | |
idas | -4.922 |
Smile | -4.774 |
ラン | -4.702 |
tto | -4.683 |
Babel | -4.638 |
Token | uphill |
Token ID | 35256 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
imation | +0.302 |
�� | +0.294 |
uthor | +0.280 |
obin | +0.271 |
ablishment | +0.269 |
Neg logit contributions | |
idas | -0.252 |
Smile | -0.250 |
Babel | -0.243 |
tto | -0.240 |
blush | -0.239 |
Token | climbs |
Token ID | 34332 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
imation | +1.711 |
�� | +1.658 |
uthor | +1.577 |
ablishment | +1.529 |
obin | +1.528 |
Neg logit contributions | |
idas | -1.305 |
Smile | -1.293 |
Babel | -1.247 |
ラン | -1.232 |
tto | -1.230 |
Token | — |
Token ID | 851 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
imation | +4.070 |
�� | +3.933 |
uthor | +3.656 |
ablishment | +3.597 |
obin | +3.578 |
Neg logit contributions | |
idas | -3.972 |
Smile | -3.925 |
Babel | -3.802 |
ラン | -3.786 |
tto | -3.759 |
Token | seats |
Token ID | 8632 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
idas | +0.378 |
Smile | +0.376 |
Babel | +0.364 |
tto | +0.360 |
ラン | +0.360 |
Neg logit contributions | |
imation | -0.476 |
�� | -0.464 |
uthor | -0.442 |
obin | -0.428 |
ablishment | -0.425 |
Token | Other |
Token ID | 6395 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
idas | +0.087 |
Smile | +0.086 |
Babel | +0.084 |
ラン | +0.083 |
tto | +0.083 |
Neg logit contributions | |
imation | -0.082 |
�� | -0.079 |
uthor | -0.075 |
obin | -0.072 |
ablishment | -0.072 |
Token | executions |
Token ID | 30632 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
idas | +0.834 |
Smile | +0.827 |
Babel | +0.801 |
tto | +0.789 |
ラン | +0.788 |
Neg logit contributions | |
imation | -1.153 |
�� | -1.123 |
uthor | -1.072 |
obin | -1.040 |
ablishment | -1.037 |
Token | took |
Token ID | 1718 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
idas | +0.574 |
Smile | +0.570 |
Babel | +0.553 |
tto | +0.547 |
blush | +0.545 |
Neg logit contributions | |
imation | -0.653 |
�� | -0.635 |
uthor | -0.602 |
obin | -0.583 |
ablishment | -0.581 |
Token | place |
Token ID | 1295 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
imation | +1.762 |
�� | +1.706 |
uthor | +1.622 |
usion | +1.563 |
ablishment | +1.558 |
Neg logit contributions | |
idas | -1.891 |
Smile | -1.878 |
Babel | -1.810 |
ラン | -1.800 |
tto | -1.792 |
Token | in |
Token ID | 287 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
imation | +0.803 |
�� | +0.780 |
uthor | +0.743 |
obin | +0.716 |
usion | +0.713 |
Neg logit contributions | |
idas | -0.692 |
Smile | -0.683 |
ラン | -0.662 |
Babel | -0.660 |
tto | -0.654 |
Token | Chong |
Token ID | 46892 |
Feature activation | -6.85e+00 |
Pos logit contributions | |
imation | +0.020 |
�� | +0.019 |
uthor | +0.018 |
obin | +0.018 |
ablishment | +0.018 |
Neg logit contributions | |
idas | -0.014 |
Smile | -0.014 |
Babel | -0.013 |
ラン | -0.013 |
tto | -0.013 |
Token | jin |
Token ID | 18594 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
imation | +5.515 |
�� | +5.245 |
obin | +5.076 |
uthor | +5.055 |
usion | +4.927 |
Neg logit contributions | |
idas | -4.455 |
Smile | -4.323 |
blush | -4.248 |
Babel | -4.196 |
ラン | -4.182 |
Token | in |
Token ID | 287 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
imation | +0.967 |
�� | +0.938 |
uthor | +0.893 |
obin | +0.866 |
ablishment | +0.862 |
Neg logit contributions | |
idas | -0.779 |
Smile | -0.769 |
Babel | -0.745 |
ラン | -0.739 |
tto | -0.737 |
Token | North |
Token ID | 2258 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
idas | +0.064 |
Smile | +0.064 |
Babel | +0.062 |
ラン | +0.061 |
tto | +0.061 |
Neg logit contributions | |
imation | -0.091 |
�� | -0.088 |
uthor | -0.084 |
obin | -0.082 |
ablishment | -0.082 |
Token | Ham |
Token ID | 4345 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
idas | +1.038 |
Smile | +1.030 |
Babel | +0.995 |
tto | +0.974 |
ラン | +0.971 |
Neg logit contributions | |
imation | -1.760 |
�� | -1.724 |
uthor | -1.652 |
obin | -1.597 |
ablishment | -1.595 |
Token | gy |
Token ID | 1360 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
idas | +0.113 |
Smile | +0.111 |
Babel | +0.107 |
tto | +0.106 |
ラン | +0.106 |
Neg logit contributions | |
imation | -0.173 |
�� | -0.170 |
uthor | -0.162 |
obin | -0.157 |
ablishment | -0.156 |
Token | for |
Token ID | 329 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
imation | +0.958 |
�� | +0.930 |
uthor | +0.852 |
ablishment | +0.838 |
obin | +0.836 |
Neg logit contributions | |
idas | -1.146 |
Smile | -1.139 |
ラン | -1.124 |
Babel | -1.110 |
tto | -1.104 |
Token | subscribing |
Token ID | 18412 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
imation | +0.394 |
�� | +0.378 |
uthor | +0.355 |
ablishment | +0.343 |
obin | +0.342 |
Neg logit contributions | |
idas | -0.551 |
Smile | -0.551 |
Babel | -0.536 |
ラン | -0.535 |
tto | -0.531 |
Token | ! |
Token ID | 0 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
imation | +1.441 |
�� | +1.396 |
uthor | +1.329 |
obin | +1.296 |
ablishment | +1.286 |
Neg logit contributions | |
idas | -1.147 |
Smile | -1.114 |
ラン | -1.096 |
Babel | -1.095 |
blush | -1.082 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
imation | +0.935 |
�� | +0.861 |
ablishment | +0.820 |
uthor | +0.810 |
usion | +0.803 |
Neg logit contributions | |
idas | -1.379 |
Smile | -1.350 |
ラン | -1.323 |
Babel | -1.318 |
Tokens | -1.315 |
Token | Nick |
Token ID | 23609 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
imation | +1.295 |
�� | +1.252 |
uthor | +1.183 |
obin | +1.143 |
usion | +1.133 |
Neg logit contributions | |
idas | -1.308 |
Smile | -1.303 |
Babel | -1.274 |
blush | -1.254 |
ラン | -1.251 |
Token | Saban |
Token ID | 41618 |
Feature activation | -6.85e+00 |
Pos logit contributions | |
idas | +0.396 |
Smile | +0.392 |
Babel | +0.378 |
ラン | +0.375 |
tto | +0.374 |
Neg logit contributions | |
imation | -0.574 |
�� | -0.558 |
uthor | -0.532 |
obin | -0.518 |
ablishment | -0.515 |
Token | has |
Token ID | 468 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
imation | +5.579 |
�� | +5.301 |
uthor | +5.183 |
obin | +4.988 |
usion | +4.977 |
Neg logit contributions | |
Smile | -4.190 |
idas | -4.151 |
Babel | -4.140 |
ラン | -4.106 |
tto | -4.061 |
Token | not |
Token ID | 407 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
imation | +0.108 |
�� | +0.105 |
uthor | +0.099 |
obin | +0.096 |
ablishment | +0.095 |
Neg logit contributions | |
idas | -0.102 |
Smile | -0.102 |
Babel | -0.099 |
ラン | -0.098 |
tto | -0.098 |
Token | been |
Token ID | 587 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
imation | +0.252 |
�� | +0.245 |
uthor | +0.231 |
obin | +0.224 |
ablishment | +0.223 |
Neg logit contributions | |
idas | -0.247 |
Smile | -0.244 |
Babel | -0.237 |
tto | -0.235 |
ラン | -0.235 |
Token | hesitant |
Token ID | 32848 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
imation | +0.127 |
�� | +0.123 |
uthor | +0.118 |
obin | +0.114 |
ablishment | +0.114 |
Neg logit contributions | |
idas | -0.092 |
Smile | -0.091 |
Babel | -0.088 |
tto | -0.087 |
blush | -0.087 |
Token | to |
Token ID | 284 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
imation | +1.429 |
�� | +1.383 |
uthor | +1.312 |
obin | +1.267 |
ablishment | +1.265 |
Neg logit contributions | |
idas | -1.318 |
Smile | -1.308 |
Babel | -1.269 |
ラン | -1.262 |
tto | -1.254 |
Token |
|
Token ID | 198 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
idas | +0.437 |
Smile | +0.437 |
Babel | +0.420 |
tto | +0.417 |
ラン | +0.415 |
Neg logit contributions | |
imation | -0.535 |
�� | -0.519 |
uthor | -0.494 |
obin | -0.475 |
ablishment | -0.474 |
Token |
|
Token ID | 198 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
imation | +0.586 |
�� | +0.558 |
uthor | +0.532 |
obin | +0.520 |
usion | +0.515 |
Neg logit contributions | |
idas | -0.547 |
Smile | -0.540 |
Babel | -0.526 |
ラン | -0.525 |
blush | -0.522 |
Token | Obviously |
Token ID | 20670 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
imation | +0.440 |
�� | +0.426 |
uthor | +0.402 |
obin | +0.390 |
ablishment | +0.385 |
Neg logit contributions | |
idas | -0.458 |
Smile | -0.454 |
Babel | -0.444 |
ラン | -0.437 |
tto | -0.437 |
Token | an |
Token ID | 281 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
imation | +0.028 |
�� | +0.027 |
uthor | +0.026 |
obin | +0.025 |
ablishment | +0.025 |
Neg logit contributions | |
idas | -0.024 |
Smile | -0.023 |
Babel | -0.023 |
ラン | -0.023 |
tto | -0.023 |
Token | uns |
Token ID | 5576 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
imation | +1.595 |
�� | +1.551 |
uthor | +1.482 |
obin | +1.443 |
ablishment | +1.426 |
Neg logit contributions | |
idas | -1.138 |
Smile | -1.128 |
Babel | -1.089 |
ラン | -1.087 |
tto | -1.073 |
Token | ourced |
Token ID | 30555 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
imation | +0.954 |
�� | +0.917 |
uthor | +0.873 |
obin | +0.836 |
usion | +0.830 |
Neg logit contributions | |
idas | -1.185 |
Smile | -1.181 |
Babel | -1.150 |
ラン | -1.144 |
blush | -1.135 |
Token | internet |
Token ID | 5230 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
imation | +5.126 |
�� | +4.884 |
uthor | +4.760 |
obin | +4.606 |
usion | +4.605 |
Neg logit contributions | |
idas | -4.635 |
ラン | -4.528 |
Smile | -4.315 |
Tokens | -4.293 |
tto | -4.284 |
Token | report |
Token ID | 989 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
imation | +2.404 |
�� | +2.328 |
uthor | +2.217 |
usion | +2.144 |
obin | +2.140 |
Neg logit contributions | |
idas | -2.018 |
Smile | -1.971 |
ラン | -1.923 |
tto | -1.908 |
Babel | -1.907 |
Token | is |
Token ID | 318 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
imation | +0.589 |
�� | +0.572 |
uthor | +0.544 |
obin | +0.526 |
ablishment | +0.523 |
Neg logit contributions | |
idas | -0.502 |
Smile | -0.498 |
Babel | -0.483 |
ラン | -0.478 |
tto | -0.477 |
Token | just |
Token ID | 655 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
imation | +0.993 |
�� | +0.970 |
uthor | +0.925 |
obin | +0.896 |
usion | +0.889 |
Neg logit contributions | |
idas | -0.743 |
Smile | -0.732 |
ラン | -0.710 |
Babel | -0.706 |
tto | -0.702 |
Token | that |
Token ID | 326 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
imation | +0.783 |
�� | +0.761 |
uthor | +0.724 |
obin | +0.702 |
ablishment | +0.697 |
Neg logit contributions | |
idas | -0.624 |
Smile | -0.616 |
Babel | -0.596 |
ラン | -0.592 |
tto | -0.591 |
Token | 22 |
Token ID | 2534 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
idas | +0.118 |
Smile | +0.117 |
Babel | +0.114 |
blush | +0.113 |
tto | +0.112 |
Neg logit contributions | |
imation | -0.113 |
�� | -0.109 |
uthor | -0.103 |
obin | -0.100 |
ablishment | -0.099 |
Token | 23 |
Token ID | 2242 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
imation | +0.086 |
�� | +0.083 |
uthor | +0.079 |
obin | +0.076 |
ablishment | +0.076 |
Neg logit contributions | |
idas | -0.097 |
Smile | -0.097 |
Babel | -0.095 |
blush | -0.093 |
tto | -0.093 |
Token | 24 |
Token ID | 1987 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
imation | +0.191 |
�� | +0.185 |
uthor | +0.174 |
obin | +0.167 |
ablishment | +0.166 |
Neg logit contributions | |
idas | -0.227 |
Smile | -0.225 |
Babel | -0.220 |
blush | -0.217 |
tto | -0.217 |
Token | SELECT |
Token ID | 33493 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
idas | +0.088 |
Smile | +0.086 |
Babel | +0.084 |
blush | +0.083 |
tto | +0.083 |
Neg logit contributions | |
imation | -0.084 |
�� | -0.081 |
uthor | -0.076 |
obin | -0.074 |
ablishment | -0.073 |
Token | REG |
Token ID | 23337 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
imation | +0.777 |
�� | +0.753 |
uthor | +0.718 |
obin | +0.697 |
ablishment | +0.691 |
Neg logit contributions | |
idas | -0.619 |
Smile | -0.614 |
Babel | -0.592 |
ラン | -0.591 |
tto | -0.589 |
Token | EXP |
Token ID | 49864 |
Feature activation | -6.71e+00 |
Pos logit contributions | |
imation | +1.726 |
�� | +1.641 |
uthor | +1.564 |
usion | +1.513 |
obin | +1.508 |
Neg logit contributions | |
Smile | -1.423 |
idas | -1.421 |
ラン | -1.391 |
tto | -1.380 |
Babel | -1.374 |
Token | _ |
Token ID | 62 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
imation | +5.038 |
�� | +4.791 |
uthor | +4.527 |
obin | +4.467 |
usion | +4.432 |
Neg logit contributions | |
Smile | -4.606 |
idas | -4.566 |
Babel | -4.478 |
tto | -4.446 |
ラン | -4.409 |
Token | EX |
Token ID | 6369 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
idas | +0.044 |
Smile | +0.043 |
Babel | +0.042 |
ラン | +0.042 |
tto | +0.042 |
Neg logit contributions | |
imation | -0.043 |
�� | -0.042 |
uthor | -0.040 |
obin | -0.038 |
ablishment | -0.038 |
Token | TR |
Token ID | 5446 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
imation | +1.486 |
�� | +1.424 |
uthor | +1.363 |
obin | +1.319 |
usion | +1.314 |
Neg logit contributions | |
idas | -1.245 |
Smile | -1.235 |
Babel | -1.196 |
ラン | -1.195 |
tto | -1.189 |
Token | ACT |
Token ID | 10659 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
imation | +0.891 |
�� | +0.863 |
uthor | +0.814 |
obin | +0.787 |
usion | +0.782 |
Neg logit contributions | |
idas | -0.924 |
Smile | -0.914 |
Babel | -0.889 |
ラン | -0.883 |
tto | -0.881 |
Token | ( |
Token ID | 357 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
imation | +0.747 |
�� | +0.722 |
uthor | +0.680 |
obin | +0.656 |
ablishment | +0.650 |
Neg logit contributions | |
idas | -0.821 |
Smile | -0.815 |
Babel | -0.794 |
ラン | -0.787 |
tto | -0.787 |
Token | infections |
Token ID | 16079 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
idas | +0.339 |
Smile | +0.336 |
Babel | +0.326 |
tto | +0.323 |
ラン | +0.323 |
Neg logit contributions | |
imation | -0.356 |
�� | -0.346 |
uthor | -0.328 |
obin | -0.316 |
ablishment | -0.315 |
Token | . |
Token ID | 13 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
imation | +0.869 |
�� | +0.840 |
uthor | +0.800 |
obin | +0.775 |
ablishment | +0.768 |
Neg logit contributions | |
idas | -0.775 |
Smile | -0.768 |
Babel | -0.746 |
ラン | -0.740 |
tto | -0.736 |
Token | In |
Token ID | 554 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
idas | +0.193 |
Smile | +0.191 |
Babel | +0.185 |
ラン | +0.183 |
tto | +0.183 |
Neg logit contributions | |
imation | -0.220 |
�� | -0.214 |
uthor | -0.203 |
obin | -0.196 |
ablishment | -0.195 |
Token | Saskatchewan |
Token ID | 31346 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
idas | +0.600 |
Smile | +0.594 |
Babel | +0.577 |
ラン | +0.570 |
tto | +0.570 |
Neg logit contributions | |
imation | -0.701 |
�� | -0.680 |
uthor | -0.646 |
obin | -0.625 |
ablishment | -0.622 |
Token | , |
Token ID | 11 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
imation | +2.851 |
�� | +2.729 |
uthor | +2.607 |
obin | +2.505 |
usion | +2.498 |
Neg logit contributions | |
idas | -2.760 |
Smile | -2.718 |
Babel | -2.659 |
tto | -2.645 |
ラン | -2.637 |
Token | Wong |
Token ID | 27247 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
imation | +0.580 |
�� | +0.562 |
uthor | +0.534 |
obin | +0.516 |
ablishment | +0.513 |
Neg logit contributions | |
idas | -0.506 |
Smile | -0.501 |
Babel | -0.487 |
ラン | -0.483 |
tto | -0.482 |
Token | is |
Token ID | 318 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
imation | +4.917 |
�� | +4.683 |
uthor | +4.470 |
obin | +4.350 |
usion | +4.311 |
Neg logit contributions | |
Smile | -4.704 |
idas | -4.682 |
Babel | -4.594 |
tto | -4.585 |
ラン | -4.543 |
Token | frustrated |
Token ID | 14718 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
idas | +0.218 |
Smile | +0.215 |
Babel | +0.208 |
ラン | +0.206 |
tto | +0.206 |
Neg logit contributions | |
imation | -0.298 |
�� | -0.290 |
uthor | -0.277 |
obin | -0.268 |
ablishment | -0.267 |
Token | by |
Token ID | 416 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
idas | +1.393 |
Smile | +1.383 |
Babel | +1.336 |
tto | +1.322 |
ラン | +1.322 |
Neg logit contributions | |
imation | -1.519 |
�� | -1.478 |
uthor | -1.403 |
obin | -1.356 |
ablishment | -1.349 |
Token | policy |
Token ID | 2450 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
idas | +1.028 |
Smile | +1.020 |
Babel | +0.985 |
ラン | +0.972 |
blush | +0.972 |
Neg logit contributions | |
imation | -1.190 |
�� | -1.157 |
uthor | -1.100 |
obin | -1.064 |
ablishment | -1.060 |
Token | failures |
Token ID | 15536 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
imation | +0.069 |
�� | +0.067 |
uthor | +0.064 |
obin | +0.062 |
ablishment | +0.062 |
Neg logit contributions | |
idas | -0.049 |
Smile | -0.049 |
Babel | -0.047 |
ラン | -0.047 |
tto | -0.047 |
Token | re |
Token ID | 302 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
imation | +0.036 |
�� | +0.035 |
uthor | +0.033 |
obin | +0.032 |
ablishment | +0.032 |
Neg logit contributions | |
idas | -0.029 |
Smile | -0.029 |
Babel | -0.028 |
tto | -0.028 |
ラン | -0.028 |
Token | - |
Token ID | 12 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
idas | +0.880 |
Smile | +0.865 |
Babel | +0.842 |
tto | +0.836 |
ラン | +0.832 |
Neg logit contributions | |
imation | -1.021 |
�� | -0.996 |
uthor | -0.943 |
obin | -0.913 |
ablishment | -0.910 |
Token | stud |
Token ID | 19149 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
imation | +0.468 |
�� | +0.452 |
uthor | +0.432 |
obin | +0.417 |
usion | +0.414 |
Neg logit contributions | |
Smile | -0.407 |
idas | -0.405 |
Babel | -0.393 |
ラン | -0.388 |
blush | -0.387 |
Token | ying |
Token ID | 1112 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
imation | +1.192 |
�� | +1.135 |
uthor | +1.053 |
obin | +1.006 |
ablishment | +0.994 |
Neg logit contributions | |
idas | -1.949 |
Smile | -1.943 |
Babel | -1.902 |
ラン | -1.890 |
tto | -1.883 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
imation | +2.186 |
�� | +2.131 |
uthor | +2.010 |
usion | +1.948 |
obin | +1.937 |
Neg logit contributions | |
idas | -1.763 |
Smile | -1.746 |
ラン | -1.732 |
Babel | -1.691 |
tto | -1.688 |
Token | Deng |
Token ID | 41985 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
imation | +0.185 |
�� | +0.181 |
uthor | +0.172 |
obin | +0.167 |
ablishment | +0.166 |
Neg logit contributions | |
idas | -0.132 |
Smile | -0.130 |
Babel | -0.126 |
ラン | -0.125 |
tto | -0.125 |
Token | intelligence |
Token ID | 4430 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
imation | +5.790 |
�� | +5.592 |
uthor | +5.295 |
obin | +5.198 |
usion | +5.186 |
Neg logit contributions | |
Smile | -3.770 |
idas | -3.749 |
ラン | -3.741 |
tto | -3.684 |
Babel | -3.648 |
Token | report |
Token ID | 989 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
idas | +1.331 |
Smile | +1.312 |
Babel | +1.278 |
tto | +1.259 |
blush | +1.257 |
Neg logit contributions | |
imation | -1.687 |
�� | -1.644 |
uthor | -1.567 |
obin | -1.515 |
ablishment | -1.510 |
Token | – |
Token ID | 784 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
imation | +0.070 |
�� | +0.068 |
uthor | +0.065 |
obin | +0.063 |
ablishment | +0.063 |
Neg logit contributions | |
idas | -0.059 |
Smile | -0.058 |
Babel | -0.057 |
tto | -0.056 |
blush | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
imation | +0.199 |
�� | +0.193 |
uthor | +0.184 |
obin | +0.178 |
ablishment | +0.176 |
Neg logit contributions | |
idas | -0.168 |
Smile | -0.167 |
Babel | -0.162 |
ラン | -0.161 |
tto | -0.160 |
Token | player |
Token ID | 2137 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
imation | +0.580 |
�� | +0.563 |
uthor | +0.538 |
obin | +0.526 |
usion | +0.521 |
Neg logit contributions | |
idas | -0.382 |
Smile | -0.377 |
ラン | -0.363 |
Babel | -0.362 |
tto | -0.359 |
Token | photo |
Token ID | 4590 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
idas | +0.454 |
Smile | +0.447 |
Babel | +0.433 |
ラン | +0.426 |
tto | +0.426 |
Neg logit contributions | |
imation | -0.738 |
�� | -0.718 |
uthor | -0.687 |
obin | -0.668 |
ablishment | -0.664 |
Token | posted |
Token ID | 4481 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
idas | +0.022 |
Smile | +0.022 |
Babel | +0.021 |
ラン | +0.021 |
tto | +0.021 |
Neg logit contributions | |
imation | -0.020 |
�� | -0.019 |
uthor | -0.018 |
obin | -0.018 |
ablishment | -0.017 |
Token | by |
Token ID | 416 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
imation | +1.083 |
�� | +1.027 |
uthor | +0.992 |
obin | +0.940 |
ablishment | +0.937 |
Neg logit contributions | |
idas | -1.173 |
Smile | -1.159 |
ラン | -1.138 |
Babel | -1.135 |
blush | -1.114 |
Token | Krist |
Token ID | 14912 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
idas | +0.340 |
Smile | +0.339 |
Babel | +0.323 |
tto | +0.320 |
blush | +0.317 |
Neg logit contributions | |
imation | -0.637 |
�� | -0.623 |
uthor | -0.596 |
obin | -0.581 |
ablishment | -0.580 |
Token | in |
Token ID | 259 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
imation | +0.051 |
�� | +0.049 |
uthor | +0.047 |
obin | +0.045 |
ablishment | +0.045 |
Neg logit contributions | |
idas | -0.043 |
Smile | -0.043 |
Babel | -0.041 |
ラン | -0.041 |
tto | -0.041 |
Token | Cav |
Token ID | 19931 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
idas | +0.942 |
Smile | +0.932 |
Babel | +0.900 |
tto | +0.886 |
ラン | +0.882 |
Neg logit contributions | |
imation | -1.384 |
�� | -1.349 |
uthor | -1.287 |
ablishment | -1.248 |
obin | -1.247 |
Token | all |
Token ID | 439 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
imation | +5.019 |
�� | +4.706 |
uthor | +4.598 |
obin | +4.541 |
usion | +4.510 |
Neg logit contributions | |
Smile | -4.546 |
Babel | -4.432 |
idas | -4.411 |
blush | -4.385 |
ラン | -4.384 |
Token | ari |
Token ID | 2743 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
imation | +1.116 |
�� | +1.074 |
uthor | +1.025 |
obin | +0.998 |
usion | +0.988 |
Neg logit contributions | |
idas | -0.993 |
Smile | -0.992 |
Babel | -0.965 |
ラン | -0.959 |
blush | -0.949 |
Token | (@ |
Token ID | 4275 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
idas | +0.686 |
Smile | +0.680 |
Babel | +0.661 |
tto | +0.656 |
ラン | +0.654 |
Neg logit contributions | |
imation | -0.645 |
�� | -0.624 |
uthor | -0.588 |
obin | -0.568 |
ablishment | -0.566 |
Token | k |
Token ID | 74 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
idas | +0.460 |
Smile | +0.455 |
Babel | +0.440 |
tto | +0.438 |
ラン | +0.437 |
Neg logit contributions | |
imation | -0.547 |
�� | -0.533 |
uthor | -0.506 |
obin | -0.489 |
ablishment | -0.488 |
Token | rist |
Token ID | 1585 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
idas | +0.234 |
Smile | +0.232 |
Babel | +0.224 |
tto | +0.223 |
ラン | +0.222 |
Neg logit contributions | |
imation | -0.281 |
�� | -0.274 |
uthor | -0.260 |
obin | -0.251 |
ablishment | -0.250 |
Token | et |
Token ID | 316 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
idas | +2.399 |
Smile | +2.367 |
tto | +2.310 |
Babel | +2.303 |
ラン | +2.249 |
Neg logit contributions | |
imation | -2.343 |
�� | -2.310 |
uthor | -2.162 |
ablishment | -2.075 |
obin | -2.070 |
Token | ahs |
Token ID | 39095 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
idas | +1.728 |
Smile | +1.695 |
Babel | +1.655 |
tto | +1.641 |
ラン | +1.635 |
Neg logit contributions | |
imation | -1.434 |
�� | -1.393 |
uthor | -1.310 |
ablishment | -1.242 |
obin | -1.242 |
Token | are |
Token ID | 389 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
imation | +0.608 |
�� | +0.586 |
uthor | +0.562 |
obin | +0.547 |
usion | +0.544 |
Neg logit contributions | |
idas | -0.453 |
Smile | -0.445 |
ラン | -0.434 |
Babel | -0.431 |
tto | -0.426 |
Token | racing |
Token ID | 11717 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
imation | +0.753 |
�� | +0.734 |
uthor | +0.697 |
obin | +0.679 |
usion | +0.675 |
Neg logit contributions | |
idas | -0.540 |
Smile | -0.531 |
ラン | -0.515 |
Babel | -0.512 |
tto | -0.508 |
Token | toward |
Token ID | 3812 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
imation | +0.747 |
�� | +0.727 |
uthor | +0.687 |
obin | +0.668 |
ablishment | +0.661 |
Neg logit contributions | |
idas | -0.622 |
Smile | -0.613 |
ラン | -0.594 |
Babel | -0.591 |
tto | -0.586 |
Token | extinction |
Token ID | 21935 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
idas | +0.952 |
Smile | +0.942 |
Babel | +0.911 |
ラン | +0.899 |
tto | +0.899 |
Neg logit contributions | |
imation | -1.315 |
�� | -1.280 |
uthor | -1.220 |
obin | -1.184 |
ablishment | -1.179 |
Token |
|
Token ID | 198 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
idas | +3.056 |
Smile | +3.049 |
Babel | +2.965 |
tto | +2.911 |
blush | +2.895 |
Neg logit contributions | |
imation | -3.841 |
�� | -3.762 |
uthor | -3.555 |
ablishment | -3.446 |
obin | -3.439 |
Token |
|
Token ID | 198 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
idas | +0.601 |
Smile | +0.595 |
Babel | +0.578 |
ラン | +0.573 |
blush | +0.570 |
Neg logit contributions | |
imation | -0.683 |
�� | -0.660 |
uthor | -0.627 |
obin | -0.608 |
ablishment | -0.604 |
Token | How |
Token ID | 2437 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
idas | +0.607 |
Smile | +0.602 |
Babel | +0.586 |
ラン | +0.579 |
tto | +0.579 |
Neg logit contributions | |
imation | -0.586 |
�� | -0.568 |
uthor | -0.536 |
obin | -0.517 |
ablishment | -0.514 |
Token | Vera |
Token ID | 44413 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
idas | +0.700 |
Smile | +0.693 |
Babel | +0.670 |
tto | +0.661 |
ラン | +0.660 |
Neg logit contributions | |
imation | -0.995 |
�� | -0.969 |
uthor | -0.925 |
obin | -0.898 |
ablishment | -0.894 |
Token | Rubin |
Token ID | 34599 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
imation | +0.320 |
�� | +0.311 |
uthor | +0.299 |
obin | +0.291 |
usion | +0.287 |
Neg logit contributions | |
idas | -0.219 |
Smile | -0.216 |
ラン | -0.209 |
Babel | -0.208 |
tto | -0.208 |
Token | , |
Token ID | 11 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
idas | +1.490 |
Smile | +1.477 |
Babel | +1.419 |
tto | +1.412 |
blush | +1.410 |
Neg logit contributions | |
imation | -1.841 |
�� | -1.815 |
uthor | -1.720 |
obin | -1.663 |
ablishment | -1.661 |
Token | just |
Token ID | 655 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
imation | +0.483 |
�� | +0.467 |
uthor | +0.444 |
obin | +0.430 |
ablishment | +0.426 |
Neg logit contributions | |
idas | -0.417 |
Smile | -0.410 |
Babel | -0.399 |
ラン | -0.397 |
tto | -0.394 |
Token | like |
Token ID | 588 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
imation | +0.524 |
�� | +0.507 |
uthor | +0.482 |
obin | +0.468 |
usion | +0.464 |
Neg logit contributions | |
idas | -0.435 |
Smile | -0.428 |
Babel | -0.415 |
ラン | -0.413 |
tto | -0.412 |
Token | the |
Token ID | 262 |
Feature activation | -7.81e-02 |
Pos logit contributions | |
idas | +0.039 |
Smile | +0.038 |
Babel | +0.037 |
ラン | +0.037 |
tto | +0.037 |
Neg logit contributions | |
imation | -0.044 |
�� | -0.043 |
uthor | -0.040 |
obin | -0.039 |
ablishment | -0.039 |
Token | optical |
Token ID | 18480 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
imation | +0.068 |
�� | +0.066 |
uthor | +0.063 |
obin | +0.061 |
usion | +0.061 |
Neg logit contributions | |
idas | -0.047 |
Smile | -0.047 |
Babel | -0.045 |
ラン | -0.045 |
tto | -0.045 |
Token | bench |
Token ID | 7624 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
idas | +0.940 |
Smile | +0.927 |
Babel | +0.870 |
blush | +0.854 |
tto | +0.848 |
Neg logit contributions | |
imation | -3.129 |
�� | -3.081 |
uthor | -2.976 |
obin | -2.913 |
ablishment | -2.905 |
Token | says |
Token ID | 1139 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
idas | +2.590 |
Smile | +2.557 |
Babel | +2.427 |
tto | +2.423 |
blush | +2.418 |
Neg logit contributions | |
imation | -3.926 |
�� | -3.916 |
uthor | -3.711 |
ablishment | -3.637 |
obin | -3.598 |
Token | you |
Token ID | 345 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
idas | +0.489 |
Smile | +0.484 |
Babel | +0.470 |
ラン | +0.464 |
tto | +0.464 |
Neg logit contributions | |
imation | -0.567 |
�� | -0.551 |
uthor | -0.523 |
obin | -0.506 |
ablishment | -0.504 |
Token | could |
Token ID | 714 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
idas | +1.182 |
Smile | +1.167 |
Babel | +1.123 |
tto | +1.116 |
blush | +1.112 |
Neg logit contributions | |
imation | -1.571 |
�� | -1.538 |
uthor | -1.464 |
obin | -1.417 |
ablishment | -1.417 |
Token | . |
Token ID | 13 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
idas | +0.531 |
Smile | +0.525 |
Babel | +0.507 |
ラン | +0.500 |
tto | +0.500 |
Neg logit contributions | |
imation | -0.844 |
�� | -0.823 |
uthor | -0.787 |
obin | -0.765 |
ablishment | -0.761 |
Token |
|
Token ID | 198 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
idas | +0.488 |
Smile | +0.486 |
Babel | +0.471 |
tto | +0.465 |
ラン | +0.465 |
Neg logit contributions | |
imation | -0.529 |
�� | -0.514 |
uthor | -0.488 |
obin | -0.471 |
ablishment | -0.468 |
Token | despite |
Token ID | 3805 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
imation | +0.391 |
�� | +0.379 |
uthor | +0.360 |
obin | +0.349 |
usion | +0.347 |
Neg logit contributions | |
idas | -0.325 |
Smile | -0.320 |
ラン | -0.312 |
Babel | -0.310 |
tto | -0.310 |
Token | the |
Token ID | 262 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
idas | +0.028 |
Smile | +0.027 |
Babel | +0.026 |
ラン | +0.026 |
tto | +0.026 |
Neg logit contributions | |
imation | -0.033 |
�� | -0.032 |
uthor | -0.030 |
obin | -0.029 |
usion | -0.029 |
Token | consequences |
Token ID | 6948 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
imation | +0.166 |
�� | +0.161 |
uthor | +0.154 |
obin | +0.149 |
usion | +0.148 |
Neg logit contributions | |
idas | -0.119 |
Smile | -0.118 |
Babel | -0.113 |
ラン | -0.113 |
tto | -0.113 |
Token | of |
Token ID | 286 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
idas | +1.454 |
Smile | +1.444 |
Babel | +1.396 |
blush | +1.382 |
tto | +1.369 |
Neg logit contributions | |
imation | -1.778 |
�� | -1.740 |
uthor | -1.652 |
ablishment | -1.609 |
obin | -1.606 |
Token | running |
Token ID | 2491 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
imation | +0.236 |
�� | +0.229 |
uthor | +0.219 |
obin | +0.211 |
usion | +0.210 |
Neg logit contributions | |
idas | -0.191 |
Smile | -0.187 |
ラン | -0.183 |
tto | -0.182 |
Babel | -0.181 |
Token | counter |
Token ID | 3753 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
imation | +0.372 |
�� | +0.361 |
uthor | +0.344 |
obin | +0.331 |
usion | +0.329 |
Neg logit contributions | |
idas | -0.338 |
Smile | -0.333 |
ラン | -0.324 |
Babel | -0.324 |
tto | -0.320 |
Token | to |
Token ID | 284 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
idas | +3.053 |
Smile | +2.977 |
Babel | +2.864 |
tto | +2.851 |
blush | +2.819 |
Neg logit contributions | |
imation | -4.137 |
�� | -4.024 |
uthor | -3.837 |
obin | -3.796 |
usion | -3.732 |
Token | what |
Token ID | 644 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
idas | +0.013 |
Smile | +0.013 |
ラン | +0.012 |
tto | +0.012 |
Babel | +0.012 |
Neg logit contributions | |
imation | -0.018 |
�� | -0.017 |
uthor | -0.016 |
obin | -0.016 |
ablishment | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
idas | +1.175 |
Smile | +1.166 |
Babel | +1.124 |
tto | +1.104 |
blush | +1.103 |
Neg logit contributions | |
imation | -1.847 |
�� | -1.802 |
uthor | -1.722 |
obin | -1.676 |
ablishment | -1.669 |
Token | expected |
Token ID | 2938 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
idas | +0.424 |
Smile | +0.420 |
Babel | +0.407 |
ラン | +0.403 |
tto | +0.403 |
Neg logit contributions | |
imation | -0.485 |
�� | -0.471 |
uthor | -0.447 |
obin | -0.433 |
ablishment | -0.430 |
Token | of |
Token ID | 286 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
idas | +0.574 |
Smile | +0.568 |
Babel | +0.551 |
ラン | +0.546 |
tto | +0.545 |
Neg logit contributions | |
imation | -0.669 |
�� | -0.650 |
uthor | -0.617 |
obin | -0.597 |
ablishment | -0.594 |
Token | you |
Token ID | 345 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
idas | +0.917 |
Smile | +0.914 |
Babel | +0.885 |
tto | +0.876 |
ラン | +0.875 |
Neg logit contributions | |
imation | -1.081 |
�� | -1.055 |
uthor | -1.004 |
ablishment | -0.969 |
obin | -0.967 |
Token | decide |
Token ID | 5409 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
idas | +1.106 |
Smile | +1.092 |
Babel | +1.056 |
ラン | +1.043 |
tto | +1.042 |
Neg logit contributions | |
imation | -1.624 |
�� | -1.579 |
uthor | -1.508 |
obin | -1.466 |
ablishment | -1.458 |
Token | to |
Token ID | 284 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
idas | +0.202 |
Smile | +0.200 |
Babel | +0.194 |
ラン | +0.192 |
tto | +0.192 |
Neg logit contributions | |
imation | -0.238 |
�� | -0.231 |
uthor | -0.219 |
obin | -0.212 |
ablishment | -0.211 |
Token | use |
Token ID | 779 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
idas | +0.052 |
Smile | +0.051 |
Babel | +0.050 |
ラン | +0.050 |
tto | +0.049 |
Neg logit contributions | |
imation | -0.068 |
�� | -0.066 |
uthor | -0.063 |
obin | -0.061 |
usion | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
imation | +1.194 |
�� | +1.158 |
uthor | +1.104 |
obin | +1.071 |
usion | +1.063 |
Neg logit contributions | |
idas | -0.928 |
Smile | -0.911 |
Babel | -0.884 |
tto | -0.881 |
ラン | -0.877 |
Token | card |
Token ID | 2657 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
idas | +0.287 |
Smile | +0.281 |
Babel | +0.270 |
ラン | +0.267 |
tto | +0.267 |
Neg logit contributions | |
imation | -0.529 |
�� | -0.516 |
uthor | -0.495 |
obin | -0.482 |
ablishment | -0.479 |
Token | , |
Token ID | 11 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
Smile | +2.868 |
idas | +2.858 |
Babel | +2.763 |
ラン | +2.735 |
tto | +2.729 |
Neg logit contributions | |
imation | -3.519 |
�� | -3.458 |
uthor | -3.286 |
ablishment | -3.168 |
obin | -3.166 |
Token | it |
Token ID | 340 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
imation | +0.546 |
�� | +0.527 |
uthor | +0.502 |
obin | +0.487 |
usion | +0.482 |
Neg logit contributions | |
idas | -0.455 |
Smile | -0.445 |
Babel | -0.433 |
ラン | -0.430 |
tto | -0.430 |
Token | � |
Token ID | 447 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
imation | +0.733 |
�� | +0.700 |
uthor | +0.670 |
obin | +0.654 |
usion | +0.644 |
Neg logit contributions | |
idas | -0.574 |
Smile | -0.566 |
Babel | -0.554 |
ラン | -0.544 |
tto | -0.544 |
Token | � |
Token ID | 247 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
imation | +0.093 |
�� | +0.090 |
uthor | +0.086 |
obin | +0.083 |
ablishment | +0.082 |
Neg logit contributions | |
idas | -0.089 |
Smile | -0.088 |
Babel | -0.085 |
tto | -0.085 |
ラン | -0.085 |
Token | s |
Token ID | 82 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
imation | +0.448 |
�� | +0.431 |
uthor | +0.418 |
obin | +0.405 |
usion | +0.403 |
Neg logit contributions | |
idas | -0.242 |
Smile | -0.240 |
Babel | -0.234 |
ラン | -0.228 |
blush | -0.228 |
Token | reefs |
Token ID | 43190 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
imation | +3.042 |
�� | +2.950 |
uthor | +2.708 |
usion | +2.664 |
obin | +2.627 |
Neg logit contributions | |
idas | -3.581 |
Smile | -3.573 |
Babel | -3.482 |
ラン | -3.471 |
tto | -3.434 |
Token | , |
Token ID | 11 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
imation | +3.377 |
�� | +3.248 |
uthor | +3.060 |
usion | +3.027 |
obin | +2.960 |
Neg logit contributions | |
idas | -3.231 |
Smile | -3.210 |
ラン | -3.129 |
Babel | -3.098 |
tto | -3.037 |
Token | but |
Token ID | 475 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
imation | +0.288 |
�� | +0.280 |
uthor | +0.267 |
obin | +0.257 |
usion | +0.257 |
Neg logit contributions | |
idas | -0.229 |
Smile | -0.226 |
Babel | -0.218 |
ラン | -0.217 |
tto | -0.216 |
Token | they |
Token ID | 484 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
idas | +0.981 |
Smile | +0.972 |
Babel | +0.943 |
tto | +0.932 |
ラン | +0.932 |
Neg logit contributions | |
imation | -1.180 |
�� | -1.148 |
uthor | -1.090 |
obin | -1.058 |
ablishment | -1.051 |
Token | are |
Token ID | 389 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
idas | +0.393 |
Smile | +0.388 |
Babel | +0.376 |
ラン | +0.373 |
tto | +0.370 |
Neg logit contributions | |
imation | -0.532 |
�� | -0.515 |
uthor | -0.492 |
obin | -0.478 |
ablishment | -0.475 |
Token | paradox |
Token ID | 22226 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
idas | +0.176 |
Smile | +0.174 |
Babel | +0.168 |
ラン | +0.167 |
tto | +0.166 |
Neg logit contributions | |
imation | -0.225 |
�� | -0.219 |
uthor | -0.208 |
obin | -0.201 |
usion | -0.200 |
Token | ically |
Token ID | 1146 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
idas | +4.695 |
Smile | +4.602 |
Babel | +4.501 |
tto | +4.456 |
ラン | +4.455 |
Neg logit contributions | |
imation | -4.235 |
�� | -4.129 |
uthor | -3.951 |
obin | -3.785 |
ablishment | -3.774 |
Token | one |
Token ID | 530 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
idas | +1.217 |
Smile | +1.204 |
Babel | +1.165 |
ラン | +1.151 |
tto | +1.151 |
Neg logit contributions | |
imation | -1.658 |
�� | -1.614 |
uthor | -1.538 |
obin | -1.493 |
ablishment | -1.487 |
Token | of |
Token ID | 286 |
Feature activation | +2.43e-03 |
Pos logit contributions | |
idas | +0.580 |
Smile | +0.573 |
Babel | +0.556 |
tto | +0.548 |
ラン | +0.548 |
Neg logit contributions | |
imation | -0.726 |
�� | -0.707 |
uthor | -0.673 |
obin | -0.652 |
ablishment | -0.648 |
Token | the |
Token ID | 262 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
idas | +0.002 |
Smile | +0.002 |
Babel | +0.002 |
ラン | +0.002 |
tto | +0.002 |
Neg logit contributions | |
imation | -0.002 |
�� | -0.002 |
uthor | -0.002 |
obin | -0.002 |
ablishment | -0.002 |
Token | most |
Token ID | 749 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
imation | +0.052 |
�� | +0.050 |
uthor | +0.048 |
obin | +0.046 |
usion | +0.046 |
Neg logit contributions | |
idas | -0.037 |
Smile | -0.037 |
Babel | -0.035 |
ラン | -0.035 |
tto | -0.035 |
Token | ards |
Token ID | 1371 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
imation | +2.656 |
�� | +2.386 |
uthor | +2.364 |
obin | +2.307 |
usion | +2.306 |
Neg logit contributions | |
Smile | -3.392 |
Babel | -3.313 |
ラン | -3.279 |
blush | -3.270 |
idas | -3.252 |
Token | in |
Token ID | 287 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
idas | +0.775 |
Smile | +0.766 |
Babel | +0.743 |
tto | +0.734 |
blush | +0.732 |
Neg logit contributions | |
imation | -0.974 |
�� | -0.947 |
uthor | -0.901 |
obin | -0.874 |
ablishment | -0.869 |
Token | support |
Token ID | 1104 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
imation | +0.143 |
�� | +0.139 |
uthor | +0.134 |
obin | +0.130 |
ablishment | +0.130 |
Neg logit contributions | |
idas | -0.071 |
Smile | -0.070 |
Babel | -0.067 |
tto | -0.066 |
ラン | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
imation | +0.800 |
�� | +0.777 |
uthor | +0.736 |
obin | +0.710 |
ablishment | +0.709 |
Neg logit contributions | |
idas | -0.725 |
Smile | -0.717 |
Babel | -0.697 |
ラン | -0.691 |
tto | -0.688 |
Token | many |
Token ID | 867 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
idas | +0.016 |
Smile | +0.016 |
Babel | +0.015 |
tto | +0.015 |
ラン | +0.015 |
Neg logit contributions | |
imation | -0.021 |
�� | -0.020 |
uthor | -0.019 |
obin | -0.019 |
ablishment | -0.018 |
Token | of |
Token ID | 286 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
idas | +1.034 |
Smile | +1.024 |
Babel | +0.994 |
ラン | +0.984 |
tto | +0.982 |
Neg logit contributions | |
imation | -1.218 |
�� | -1.182 |
uthor | -1.124 |
obin | -1.087 |
ablishment | -1.082 |
Token | the |
Token ID | 262 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
idas | +0.671 |
Smile | +0.665 |
Babel | +0.647 |
ラン | +0.640 |
tto | +0.640 |
Neg logit contributions | |
imation | -0.668 |
�� | -0.647 |
uthor | -0.612 |
obin | -0.591 |
ablishment | -0.588 |
Token | tract |
Token ID | 14998 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
idas | +0.154 |
Smile | +0.153 |
Babel | +0.149 |
ラン | +0.148 |
tto | +0.147 |
Neg logit contributions | |
imation | -0.164 |
�� | -0.158 |
uthor | -0.150 |
obin | -0.145 |
usion | -0.145 |
Token | ors |
Token ID | 669 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
imation | +1.251 |
�� | +1.159 |
uthor | +1.097 |
obin | +1.053 |
usion | +1.044 |
Neg logit contributions | |
Smile | -2.237 |
idas | -2.210 |
ラン | -2.196 |
Babel | -2.188 |
blush | -2.172 |
Token | carried |
Token ID | 5281 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
imation | +0.615 |
�� | +0.598 |
uthor | +0.571 |
obin | +0.554 |
ablishment | +0.551 |
Neg logit contributions | |
idas | -0.433 |
Smile | -0.429 |
Babel | -0.414 |
tto | -0.409 |
ラン | -0.408 |
Token | the |
Token ID | 262 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
idas | +0.498 |
Smile | +0.493 |
Babel | +0.480 |
tto | +0.474 |
ラン | +0.473 |
Neg logit contributions | |
imation | -0.521 |
�� | -0.506 |
uthor | -0.478 |
obin | -0.464 |
ablishment | -0.461 |
Token | in |
Token ID | 287 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
idas | +2.231 |
Smile | +2.197 |
Babel | +2.136 |
blush | +2.122 |
tto | +2.121 |
Neg logit contributions | |
imation | -2.661 |
�� | -2.569 |
uthor | -2.431 |
obin | -2.375 |
ablishment | -2.364 |
Token | the |
Token ID | 262 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
idas | +0.649 |
Smile | +0.641 |
Babel | +0.620 |
ラン | +0.613 |
tto | +0.613 |
Neg logit contributions | |
imation | -0.835 |
�� | -0.809 |
uthor | -0.773 |
obin | -0.748 |
ablishment | -0.744 |
Token | U |
Token ID | 471 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
imation | +0.048 |
�� | +0.046 |
uthor | +0.044 |
obin | +0.043 |
usion | +0.042 |
Neg logit contributions | |
idas | -0.038 |
Smile | -0.037 |
Babel | -0.036 |
ラン | -0.036 |
tto | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
idas | +0.237 |
Smile | +0.235 |
Babel | +0.228 |
ラン | +0.226 |
tto | +0.225 |
Neg logit contributions | |
imation | -0.275 |
�� | -0.266 |
uthor | -0.254 |
obin | -0.245 |
ablishment | -0.244 |
Token | S |
Token ID | 50 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
idas | +0.793 |
Smile | +0.785 |
Babel | +0.762 |
ラン | +0.754 |
tto | +0.754 |
Neg logit contributions | |
imation | -0.914 |
�� | -0.888 |
uthor | -0.843 |
obin | -0.816 |
ablishment | -0.812 |
Token | . |
Token ID | 13 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
idas | +1.150 |
Smile | +1.135 |
Babel | +1.098 |
ラン | +1.097 |
tto | +1.097 |
Neg logit contributions | |
imation | -1.182 |
�� | -1.161 |
uthor | -1.084 |
obin | -1.056 |
ablishment | -1.042 |
Token | of |
Token ID | 286 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
idas | +0.618 |
Smile | +0.612 |
Babel | +0.593 |
ラン | +0.587 |
tto | +0.586 |
Neg logit contributions | |
imation | -0.760 |
�� | -0.739 |
uthor | -0.701 |
obin | -0.681 |
ablishment | -0.676 |
Token | more |
Token ID | 517 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
idas | +0.460 |
Smile | +0.455 |
Babel | +0.440 |
ラン | +0.435 |
tto | +0.435 |
Neg logit contributions | |
imation | -0.620 |
�� | -0.604 |
uthor | -0.575 |
obin | -0.558 |
ablishment | -0.556 |
Token | than |
Token ID | 621 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
idas | +1.005 |
Smile | +0.992 |
Babel | +0.946 |
tto | +0.931 |
ラン | +0.929 |
Neg logit contributions | |
imation | -2.358 |
�� | -2.308 |
uthor | -2.216 |
obin | -2.166 |
ablishment | -2.162 |
Token | a |
Token ID | 257 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
idas | +0.279 |
Smile | +0.275 |
Babel | +0.268 |
ラン | +0.266 |
tto | +0.265 |
Neg logit contributions | |
imation | -0.293 |
�� | -0.284 |
uthor | -0.270 |
obin | -0.260 |
ablishment | -0.258 |
Token | dozen |
Token ID | 8667 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
idas | +0.124 |
Smile | +0.123 |
Babel | +0.118 |
tto | +0.117 |
ラン | +0.117 |
Neg logit contributions | |
imation | -0.211 |
�� | -0.205 |
uthor | -0.197 |
obin | -0.191 |
ablishment | -0.190 |
Token |
|
Token ID | 198 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
imation | +1.111 |
�� | +1.065 |
uthor | +1.004 |
obin | +0.982 |
usion | +0.974 |
Neg logit contributions | |
idas | -1.049 |
Smile | -1.035 |
Babel | -1.012 |
blush | -1.008 |
tto | -0.999 |
Token | L |
Token ID | 43 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
imation | +0.701 |
�� | +0.682 |
uthor | +0.644 |
obin | +0.624 |
usion | +0.619 |
Neg logit contributions | |
idas | -0.638 |
Smile | -0.635 |
Babel | -0.617 |
tto | -0.610 |
blush | -0.608 |
Token | ings |
Token ID | 654 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
imation | +0.557 |
�� | +0.539 |
uthor | +0.510 |
obin | +0.492 |
ablishment | +0.489 |
Neg logit contributions | |
idas | -0.577 |
Smile | -0.572 |
Babel | -0.557 |
ラン | -0.552 |
tto | -0.551 |
Token | added |
Token ID | 2087 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
imation | +0.911 |
�� | +0.885 |
uthor | +0.839 |
obin | +0.811 |
ablishment | +0.807 |
Neg logit contributions | |
idas | -0.808 |
Smile | -0.801 |
Babel | -0.777 |
ラン | -0.769 |
tto | -0.769 |
Token | the |
Token ID | 262 |
Feature activation | +9.19e-03 |
Pos logit contributions | |
idas | +0.553 |
Smile | +0.548 |
Babel | +0.532 |
ラン | +0.527 |
tto | +0.527 |
Neg logit contributions | |
imation | -0.584 |
�� | -0.567 |
uthor | -0.537 |
obin | -0.519 |
ablishment | -0.516 |
Token | footnote |
Token ID | 38512 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
idas | +0.006 |
Smile | +0.006 |
Babel | +0.006 |
ラン | +0.006 |
tto | +0.006 |
Neg logit contributions | |
imation | -0.007 |
�� | -0.007 |
uthor | -0.007 |
obin | -0.007 |
usion | -0.007 |
Token | 1 |
Token ID | 352 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
idas | +0.285 |
Smile | +0.283 |
Babel | +0.275 |
tto | +0.272 |
ラン | +0.271 |
Neg logit contributions | |
imation | -0.312 |
�� | -0.303 |
uthor | -0.287 |
obin | -0.277 |
ablishment | -0.276 |
Token | at |
Token ID | 379 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
imation | +1.096 |
�� | +1.064 |
uthor | +1.007 |
obin | +0.972 |
ablishment | +0.969 |
Neg logit contributions | |
idas | -1.013 |
Smile | -1.005 |
Babel | -0.976 |
ラン | -0.969 |
tto | -0.965 |
Token | the |
Token ID | 262 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
imation | +1.020 |
�� | +0.985 |
uthor | +0.933 |
obin | +0.906 |
ablishment | +0.897 |
Neg logit contributions | |
idas | -0.923 |
Smile | -0.914 |
ラン | -0.884 |
tto | -0.883 |
Babel | -0.882 |
Token | bottom |
Token ID | 4220 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
imation | +0.426 |
�� | +0.416 |
uthor | +0.399 |
obin | +0.390 |
ablishment | +0.388 |
Neg logit contributions | |
idas | -0.208 |
Smile | -0.204 |
Babel | -0.195 |
ラン | -0.194 |
tto | -0.193 |
Token | of |
Token ID | 286 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
idas | +0.287 |
Smile | +0.284 |
Babel | +0.276 |
tto | +0.273 |
ラン | +0.272 |
Neg logit contributions | |
imation | -0.343 |
�� | -0.333 |
uthor | -0.316 |
obin | -0.306 |
ablishment | -0.305 |
Token | to |
Token ID | 284 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
imation | +0.421 |
�� | +0.409 |
uthor | +0.389 |
obin | +0.375 |
ablishment | +0.375 |
Neg logit contributions | |
idas | -0.359 |
Smile | -0.356 |
Babel | -0.345 |
ラン | -0.341 |
tto | -0.340 |
Token | leave |
Token ID | 2666 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
imation | +0.146 |
�� | +0.142 |
uthor | +0.136 |
obin | +0.132 |
ablishment | +0.131 |
Neg logit contributions | |
idas | -0.087 |
Smile | -0.086 |
Babel | -0.082 |
ラン | -0.082 |
tto | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
idas | +1.267 |
Smile | +1.259 |
Babel | +1.224 |
tto | +1.206 |
blush | +1.202 |
Neg logit contributions | |
imation | -1.377 |
�� | -1.341 |
uthor | -1.261 |
obin | -1.230 |
ablishment | -1.219 |
Token | European |
Token ID | 3427 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
idas | +0.641 |
Smile | +0.635 |
Babel | +0.611 |
tto | +0.602 |
ラン | +0.600 |
Neg logit contributions | |
imation | -1.072 |
�� | -1.046 |
uthor | -1.000 |
obin | -0.974 |
ablishment | -0.970 |
Token | Union |
Token ID | 4479 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
Smile | +2.394 |
idas | +2.380 |
Babel | +2.304 |
tto | +2.265 |
blush | +2.257 |
Neg logit contributions | |
imation | -3.395 |
�� | -3.297 |
uthor | -3.132 |
ablishment | -3.051 |
obin | -3.037 |
Token | , |
Token ID | 11 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
idas | +2.349 |
Smile | +2.331 |
Babel | +2.262 |
tto | +2.240 |
blush | +2.227 |
Neg logit contributions | |
imation | -2.984 |
�� | -2.905 |
uthor | -2.747 |
obin | -2.677 |
ablishment | -2.675 |
Token | particularly |
Token ID | 3573 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
idas | +0.216 |
Smile | +0.214 |
Babel | +0.207 |
ラン | +0.205 |
tto | +0.205 |
Neg logit contributions | |
imation | -0.275 |
�� | -0.267 |
uthor | -0.254 |
obin | -0.246 |
ablishment | -0.245 |
Token | on |
Token ID | 319 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
imation | +0.370 |
�� | +0.358 |
uthor | +0.341 |
obin | +0.328 |
ablishment | +0.327 |
Neg logit contributions | |
idas | -0.332 |
Smile | -0.328 |
Babel | -0.318 |
tto | -0.316 |
ラン | -0.315 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
idas | +0.485 |
Smile | +0.481 |
Babel | +0.465 |
tto | +0.459 |
ラン | +0.459 |
Neg logit contributions | |
imation | -0.707 |
�� | -0.688 |
uthor | -0.656 |
obin | -0.637 |
ablishment | -0.636 |
Token | trade |
Token ID | 3292 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
idas | +0.128 |
Smile | +0.126 |
Babel | +0.122 |
ラン | +0.120 |
tto | +0.120 |
Neg logit contributions | |
imation | -0.202 |
�� | -0.197 |
uthor | -0.187 |
obin | -0.183 |
ablishment | -0.181 |
Token | front |
Token ID | 2166 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
idas | +1.360 |
Smile | +1.346 |
Babel | +1.298 |
tto | +1.286 |
blush | +1.285 |
Neg logit contributions | |
imation | -1.900 |
�� | -1.854 |
uthor | -1.763 |
ablishment | -1.715 |
obin | -1.709 |
Token | 's |
Token ID | 338 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
imation | +0.661 |
�� | +0.642 |
uthor | +0.611 |
obin | +0.592 |
ablishment | +0.587 |
Neg logit contributions | |
idas | -0.549 |
Smile | -0.543 |
Babel | -0.528 |
ラン | -0.521 |
tto | -0.519 |
Token | annual |
Token ID | 5079 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
idas | +0.827 |
Smile | +0.820 |
Babel | +0.790 |
tto | +0.779 |
ラン | +0.778 |
Neg logit contributions | |
imation | -1.313 |
�� | -1.281 |
uthor | -1.225 |
obin | -1.191 |
ablishment | -1.186 |
Token | report |
Token ID | 989 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
idas | +1.628 |
Smile | +1.625 |
Babel | +1.566 |
blush | +1.536 |
tto | +1.535 |
Neg logit contributions | |
imation | -2.629 |
�� | -2.569 |
uthor | -2.458 |
ablishment | -2.386 |
obin | -2.383 |
Token | for |
Token ID | 329 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
idas | +0.537 |
Smile | +0.530 |
Babel | +0.514 |
tto | +0.509 |
blush | +0.507 |
Neg logit contributions | |
imation | -0.590 |
�� | -0.572 |
uthor | -0.542 |
obin | -0.525 |
ablishment | -0.524 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
imation | +0.451 |
�� | +0.436 |
uthor | +0.413 |
obin | +0.400 |
ablishment | +0.397 |
Neg logit contributions | |
idas | -0.429 |
Smile | -0.424 |
Babel | -0.412 |
ラン | -0.410 |
tto | -0.409 |
Token | said |
Token ID | 531 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
imation | +0.085 |
�� | +0.082 |
uthor | +0.078 |
obin | +0.075 |
ablishment | +0.075 |
Neg logit contributions | |
idas | -0.082 |
Smile | -0.081 |
Babel | -0.079 |
ラン | -0.078 |
tto | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
idas | +0.318 |
Smile | +0.315 |
Babel | +0.305 |
tto | +0.302 |
ラン | +0.301 |
Neg logit contributions | |
imation | -0.361 |
�� | -0.351 |
uthor | -0.333 |
obin | -0.322 |
ablishment | -0.320 |
Token | deal |
Token ID | 1730 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
imation | +0.198 |
�� | +0.192 |
uthor | +0.183 |
obin | +0.179 |
usion | +0.177 |
Neg logit contributions | |
idas | -0.133 |
Smile | -0.131 |
Babel | -0.126 |
ラン | -0.126 |
tto | -0.125 |
Token | with |
Token ID | 351 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
imation | +1.097 |
�� | +1.063 |
uthor | +1.005 |
obin | +0.973 |
ablishment | +0.968 |
Neg logit contributions | |
idas | -0.999 |
Smile | -0.987 |
Babel | -0.961 |
ラン | -0.960 |
tto | -0.955 |
Token | Nav |
Token ID | 13244 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
idas | +0.336 |
Smile | +0.333 |
Babel | +0.322 |
tto | +0.317 |
ラン | +0.317 |
Neg logit contributions | |
imation | -0.467 |
�� | -0.455 |
uthor | -0.434 |
obin | -0.421 |
ablishment | -0.419 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
imation | +1.069 |
�� | +0.964 |
uthor | +0.862 |
obin | +0.811 |
usion | +0.790 |
Neg logit contributions | |
idas | -3.501 |
Smile | -3.491 |
Babel | -3.429 |
ラン | -3.426 |
blush | -3.411 |
Token | by |
Token ID | 416 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
imation | +0.465 |
�� | +0.452 |
uthor | +0.429 |
obin | +0.415 |
ablishment | +0.413 |
Neg logit contributions | |
idas | -0.398 |
Smile | -0.393 |
Babel | -0.382 |
ラン | -0.378 |
tto | -0.377 |
Token | others |
Token ID | 1854 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
idas | +0.296 |
Smile | +0.293 |
Babel | +0.283 |
ラン | +0.281 |
tto | +0.280 |
Neg logit contributions | |
imation | -0.367 |
�� | -0.356 |
uthor | -0.339 |
obin | -0.328 |
ablishment | -0.327 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
idas | +0.719 |
Smile | +0.711 |
Babel | +0.690 |
tto | +0.682 |
ラン | +0.681 |
Neg logit contributions | |
imation | -0.872 |
�� | -0.849 |
uthor | -0.806 |
obin | -0.781 |
ablishment | -0.776 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
imation | +0.189 |
�� | +0.184 |
uthor | +0.175 |
obin | +0.169 |
ablishment | +0.168 |
Neg logit contributions | |
idas | -0.162 |
Smile | -0.161 |
Babel | -0.156 |
ラン | -0.154 |
tto | -0.154 |
Token |
|
Token ID | 198 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
imation | +0.088 |
�� | +0.084 |
uthor | +0.080 |
obin | +0.078 |
usion | +0.077 |
Neg logit contributions | |
idas | -0.080 |
Smile | -0.079 |
Babel | -0.077 |
ラン | -0.077 |
blush | -0.076 |
Token | � |
Token ID | 447 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
idas | +0.047 |
Smile | +0.047 |
Babel | +0.046 |
ラン | +0.045 |
tto | +0.045 |
Neg logit contributions | |
imation | -0.046 |
�� | -0.045 |
uthor | -0.042 |
obin | -0.041 |
ablishment | -0.040 |
Token | � |
Token ID | 250 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
imation | +0.544 |
�� | +0.524 |
uthor | +0.494 |
obin | +0.475 |
ablishment | +0.472 |
Neg logit contributions | |
idas | -0.650 |
Smile | -0.645 |
Babel | -0.628 |
ラン | -0.624 |
tto | -0.623 |
Token | Trade |
Token ID | 35965 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
imation | +0.069 |
�� | +0.067 |
uthor | +0.063 |
obin | +0.060 |
ablishment | +0.060 |
Neg logit contributions | |
idas | -0.077 |
Smile | -0.076 |
Babel | -0.074 |
ラン | -0.073 |
tto | -0.073 |
Token | is |
Token ID | 318 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
idas | +0.665 |
Smile | +0.659 |
Babel | +0.639 |
ラン | +0.632 |
tto | +0.632 |
Neg logit contributions | |
imation | -0.794 |
�� | -0.772 |
uthor | -0.733 |
obin | -0.710 |
ablishment | -0.707 |
Token | a |
Token ID | 257 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
idas | +0.055 |
Smile | +0.055 |
Babel | +0.053 |
ラン | +0.052 |
tto | +0.052 |
Neg logit contributions | |
imation | -0.075 |
�� | -0.073 |
uthor | -0.070 |
obin | -0.068 |
ablishment | -0.067 |
Token | winner |
Token ID | 8464 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
imation | +0.544 |
�� | +0.528 |
uthor | +0.505 |
obin | +0.493 |
usion | +0.490 |
Neg logit contributions | |
idas | -0.351 |
Smile | -0.342 |
Babel | -0.330 |
ラン | -0.329 |
tto | -0.328 |
Token | m |
Token ID | 76 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
idas | +0.034 |
Smile | +0.033 |
Babel | +0.032 |
ラン | +0.032 |
blush | +0.031 |
Neg logit contributions | |
imation | -0.058 |
�� | -0.057 |
uthor | -0.055 |
obin | -0.053 |
ablishment | -0.053 |
Token | a |
Token ID | 257 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
idas | +0.460 |
Smile | +0.454 |
Babel | +0.438 |
ラン | +0.433 |
tto | +0.433 |
Neg logit contributions | |
imation | -0.701 |
�� | -0.683 |
uthor | -0.653 |
obin | -0.634 |
ablishment | -0.631 |
Token | better |
Token ID | 1365 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
idas | +0.081 |
Smile | +0.080 |
Babel | +0.076 |
ラン | +0.075 |
tto | +0.075 |
Neg logit contributions | |
imation | -0.179 |
�� | -0.175 |
uthor | -0.168 |
obin | -0.164 |
ablishment | -0.163 |
Token | player |
Token ID | 2137 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
imation | +1.472 |
�� | +1.426 |
uthor | +1.362 |
obin | +1.324 |
ablishment | +1.308 |
Neg logit contributions | |
idas | -1.073 |
Smile | -1.053 |
ラン | -1.027 |
Babel | -1.026 |
tto | -1.007 |
Token | . |
Token ID | 13 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
idas | +0.849 |
Smile | +0.840 |
Babel | +0.809 |
tto | +0.801 |
blush | +0.796 |
Neg logit contributions | |
imation | -1.320 |
�� | -1.289 |
uthor | -1.233 |
obin | -1.196 |
ablishment | -1.194 |
Token | I |
Token ID | 314 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
imation | +0.230 |
�� | +0.223 |
uthor | +0.209 |
obin | +0.202 |
ablishment | +0.201 |
Neg logit contributions | |
idas | -0.252 |
Smile | -0.249 |
Babel | -0.243 |
ラン | -0.241 |
tto | -0.240 |
Token | � |
Token ID | 447 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
imation | +0.842 |
�� | +0.813 |
uthor | +0.775 |
obin | +0.751 |
usion | +0.747 |
Neg logit contributions | |
idas | -0.669 |
Smile | -0.658 |
Babel | -0.644 |
ラン | -0.634 |
tto | -0.630 |
Token | � |
Token ID | 247 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
idas | +0.210 |
Smile | +0.208 |
Babel | +0.202 |
tto | +0.202 |
ラン | +0.201 |
Neg logit contributions | |
imation | -0.204 |
�� | -0.197 |
uthor | -0.187 |
obin | -0.181 |
ablishment | -0.180 |
Token | m |
Token ID | 76 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
imation | +0.185 |
�� | +0.179 |
uthor | +0.172 |
obin | +0.167 |
ablishment | +0.166 |
Neg logit contributions | |
idas | -0.110 |
Smile | -0.108 |
Babel | -0.105 |
ラン | -0.103 |
blush | -0.102 |
Token | not |
Token ID | 407 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
idas | +0.372 |
Smile | +0.368 |
Babel | +0.356 |
tto | +0.351 |
ラン | +0.351 |
Neg logit contributions | |
imation | -0.533 |
�� | -0.519 |
uthor | -0.495 |
obin | -0.481 |
ablishment | -0.479 |
Token | who |
Token ID | 508 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
imation | +0.593 |
�� | +0.577 |
uthor | +0.549 |
obin | +0.532 |
ablishment | +0.530 |
Neg logit contributions | |
idas | -0.453 |
Smile | -0.448 |
Babel | -0.434 |
ラン | -0.429 |
tto | -0.429 |
Token | not |
Token ID | 407 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
idas | +0.540 |
Smile | +0.535 |
Babel | +0.518 |
tto | +0.512 |
ラン | +0.512 |
Neg logit contributions | |
imation | -0.685 |
�� | -0.667 |
uthor | -0.634 |
obin | -0.615 |
ablishment | -0.612 |
Token | enough |
Token ID | 1576 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
imation | +1.003 |
�� | +0.968 |
uthor | +0.921 |
obin | +0.882 |
usion | +0.882 |
Neg logit contributions | |
idas | -0.985 |
Smile | -0.966 |
ラン | -0.945 |
Babel | -0.941 |
tto | -0.938 |
Token | , |
Token ID | 11 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
imation | +0.416 |
�� | +0.402 |
uthor | +0.382 |
obin | +0.370 |
usion | +0.370 |
Neg logit contributions | |
idas | -0.346 |
Smile | -0.340 |
Babel | -0.331 |
ラン | -0.329 |
tto | -0.328 |
Token | Da |
Token ID | 9637 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
imation | +0.501 |
�� | +0.484 |
uthor | +0.462 |
obin | +0.447 |
usion | +0.445 |
Neg logit contributions | |
idas | -0.421 |
Smile | -0.413 |
ラン | -0.405 |
tto | -0.401 |
Babel | -0.400 |
Token | um |
Token ID | 388 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
imation | +1.617 |
�� | +1.547 |
uthor | +1.497 |
obin | +1.434 |
usion | +1.430 |
Neg logit contributions | |
idas | -1.374 |
Smile | -1.357 |
Babel | -1.331 |
tto | -1.324 |
ラン | -1.319 |
Token | Games |
Token ID | 5776 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
idas | +0.558 |
Smile | +0.552 |
Babel | +0.536 |
ラン | +0.530 |
tto | +0.529 |
Neg logit contributions | |
imation | -0.695 |
�� | -0.675 |
uthor | -0.643 |
obin | -0.623 |
ablishment | -0.619 |
Token | have |
Token ID | 423 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
imation | +0.035 |
�� | +0.034 |
uthor | +0.033 |
obin | +0.032 |
ablishment | +0.031 |
Neg logit contributions | |
idas | -0.028 |
Smile | -0.028 |
Babel | -0.027 |
ラン | -0.027 |
tto | -0.027 |
Token | released |
Token ID | 2716 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
imation | +1.690 |
�� | +1.645 |
uthor | +1.578 |
usion | +1.502 |
obin | +1.495 |
Neg logit contributions | |
idas | -1.570 |
Smile | -1.546 |
ラン | -1.510 |
tto | -1.494 |
Babel | -1.493 |
Token | Black |
Token ID | 2619 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
idas | +1.200 |
Smile | +1.186 |
Babel | +1.149 |
ラン | +1.141 |
tto | +1.139 |
Neg logit contributions | |
imation | -1.521 |
�� | -1.478 |
uthor | -1.408 |
obin | -1.363 |
ablishment | -1.354 |
Token | Desert |
Token ID | 18692 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
idas | +1.452 |
Smile | +1.441 |
Babel | +1.371 |
tto | +1.332 |
ラン | +1.326 |
Neg logit contributions | |
imation | -3.414 |
�� | -3.351 |
uthor | -3.226 |
obin | -3.150 |
ablishment | -3.137 |
Token | Online |
Token ID | 7467 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
idas | +0.914 |
Smile | +0.909 |
Babel | +0.884 |
tto | +0.875 |
ラン | +0.873 |
Neg logit contributions | |
imation | -0.805 |
�� | -0.779 |
uthor | -0.734 |
obin | -0.709 |
ablishment | -0.705 |
Token | site |
Token ID | 2524 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
idas | +0.158 |
Smile | +0.156 |
Babel | +0.151 |
ラン | +0.149 |
tto | +0.149 |
Neg logit contributions | |
imation | -0.236 |
�� | -0.229 |
uthor | -0.219 |
obin | -0.212 |
ablishment | -0.211 |
Token | of |
Token ID | 286 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
imation | +1.038 |
�� | +1.008 |
uthor | +0.956 |
ablishment | +0.922 |
obin | +0.921 |
Neg logit contributions | |
idas | -0.895 |
Smile | -0.889 |
Babel | -0.861 |
tto | -0.852 |
ラン | -0.851 |
Token | ancient |
Token ID | 6156 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
idas | +0.218 |
Smile | +0.215 |
Babel | +0.208 |
ラン | +0.207 |
tto | +0.207 |
Neg logit contributions | |
imation | -0.254 |
�� | -0.246 |
uthor | -0.234 |
obin | -0.226 |
ablishment | -0.225 |
Token | Troy |
Token ID | 21439 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
idas | +0.523 |
Smile | +0.517 |
Babel | +0.498 |
ラン | +0.495 |
tto | +0.495 |
Neg logit contributions | |
imation | -0.738 |
�� | -0.718 |
uthor | -0.684 |
obin | -0.664 |
ablishment | -0.661 |
Token | , |
Token ID | 11 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
idas | +1.280 |
Smile | +1.262 |
Babel | +1.226 |
tto | +1.214 |
ラン | +1.209 |
Neg logit contributions | |
imation | -1.519 |
�� | -1.483 |
uthor | -1.408 |
obin | -1.364 |
ablishment | -1.358 |
Token | where |
Token ID | 810 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
idas | +0.192 |
Smile | +0.190 |
Babel | +0.185 |
ラン | +0.183 |
tto | +0.183 |
Neg logit contributions | |
imation | -0.218 |
�� | -0.211 |
uthor | -0.201 |
obin | -0.194 |
ablishment | -0.193 |
Token | Homer |
Token ID | 28440 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
imation | +0.622 |
�� | +0.605 |
uthor | +0.576 |
obin | +0.554 |
usion | +0.554 |
Neg logit contributions | |
idas | -0.513 |
Smile | -0.511 |
ラン | -0.491 |
Babel | -0.490 |
tto | -0.488 |
Token | located |
Token ID | 5140 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
idas | +0.919 |
Smile | +0.903 |
Babel | +0.878 |
ラン | +0.866 |
tto | +0.863 |
Neg logit contributions | |
imation | -1.218 |
�� | -1.187 |
uthor | -1.131 |
obin | -1.096 |
ablishment | -1.096 |
Token | the |
Token ID | 262 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
imation | +0.453 |
�� | +0.441 |
uthor | +0.418 |
obin | +0.404 |
usion | +0.402 |
Neg logit contributions | |
idas | -0.373 |
Smile | -0.372 |
ラン | -0.357 |
tto | -0.356 |
Babel | -0.355 |
Token | legendary |
Token ID | 13273 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
idas | +0.356 |
Smile | +0.352 |
Babel | +0.338 |
ラン | +0.337 |
tto | +0.336 |
Neg logit contributions | |
imation | -0.526 |
�� | -0.512 |
uthor | -0.488 |
obin | -0.474 |
ablishment | -0.472 |
Token | war |
Token ID | 1175 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
idas | +0.597 |
Smile | +0.590 |
Babel | +0.568 |
ラン | +0.564 |
tto | +0.563 |
Neg logit contributions | |
imation | -0.836 |
�� | -0.813 |
uthor | -0.775 |
obin | -0.752 |
ablishment | -0.748 |
Token | will |
Token ID | 481 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
imation | +1.395 |
�� | +1.351 |
uthor | +1.286 |
obin | +1.244 |
usion | +1.238 |
Neg logit contributions | |
idas | -1.189 |
Smile | -1.181 |
Babel | -1.149 |
ラン | -1.138 |
tto | -1.126 |
Token | do |
Token ID | 466 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
imation | +0.793 |
�� | +0.770 |
uthor | +0.737 |
obin | +0.715 |
ablishment | +0.711 |
Neg logit contributions | |
idas | -0.553 |
Smile | -0.547 |
Babel | -0.529 |
ラン | -0.525 |
tto | -0.521 |
Token | roughly |
Token ID | 7323 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
imation | +0.573 |
�� | +0.557 |
uthor | +0.530 |
obin | +0.513 |
ablishment | +0.511 |
Neg logit contributions | |
idas | -0.453 |
Smile | -0.449 |
Babel | -0.435 |
ラン | -0.430 |
tto | -0.430 |
Token | 17 |
Token ID | 1596 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
imation | +0.149 |
�� | +0.144 |
uthor | +0.136 |
obin | +0.132 |
ablishment | +0.131 |
Neg logit contributions | |
idas | -0.145 |
Smile | -0.144 |
Babel | -0.139 |
ラン | -0.138 |
tto | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
imation | +0.365 |
�� | +0.356 |
uthor | +0.340 |
obin | +0.330 |
ablishment | +0.329 |
Neg logit contributions | |
idas | -0.233 |
Smile | -0.230 |
Babel | -0.222 |
ラン | -0.219 |
tto | -0.219 |
Token | 5 |
Token ID | 20 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
idas | +0.782 |
Smile | +0.774 |
Babel | +0.747 |
ラン | +0.738 |
tto | +0.737 |
Neg logit contributions | |
imation | -1.190 |
�� | -1.162 |
uthor | -1.109 |
obin | -1.077 |
ablishment | -1.073 |
Token | laps |
Token ID | 24590 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
imation | +0.291 |
�� | +0.285 |
uthor | +0.275 |
obin | +0.268 |
ablishment | +0.267 |
Neg logit contributions | |
idas | -0.099 |
Smile | -0.098 |
Babel | -0.092 |
ラン | -0.090 |
tto | -0.090 |
Token | of |
Token ID | 286 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
imation | +0.539 |
�� | +0.522 |
uthor | +0.496 |
obin | +0.480 |
ablishment | +0.477 |
Neg logit contributions | |
idas | -0.461 |
Smile | -0.457 |
Babel | -0.445 |
ラン | -0.441 |
tto | -0.438 |
Token | the |
Token ID | 262 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
idas | +0.315 |
Smile | +0.312 |
Babel | +0.303 |
tto | +0.299 |
blush | +0.298 |
Neg logit contributions | |
imation | -0.368 |
�� | -0.358 |
uthor | -0.341 |
obin | -0.331 |
ablishment | -0.329 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
imation | +0.024 |
�� | +0.024 |
uthor | +0.022 |
obin | +0.022 |
ablishment | +0.022 |
Neg logit contributions | |
idas | -0.021 |
Smile | -0.021 |
Babel | -0.020 |
tto | -0.020 |
blush | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
imation | +2.129 |
�� | +2.060 |
uthor | +1.959 |
obin | +1.875 |
ablishment | +1.871 |
Neg logit contributions | |
idas | -2.043 |
Smile | -2.032 |
Babel | -1.985 |
ラン | -1.950 |
blush | -1.948 |
Token | these |
Token ID | 777 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
imation | +0.212 |
�� | +0.206 |
uthor | +0.196 |
obin | +0.190 |
ablishment | +0.189 |
Neg logit contributions | |
idas | -0.173 |
Smile | -0.171 |
Babel | -0.166 |
ラン | -0.164 |
tto | -0.164 |
Token | awards |
Token ID | 13304 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
imation | +0.550 |
�� | +0.535 |
uthor | +0.510 |
obin | +0.494 |
ablishment | +0.492 |
Neg logit contributions | |
idas | -0.426 |
Smile | -0.420 |
Babel | -0.407 |
ラン | -0.404 |
tto | -0.404 |
Token | were |
Token ID | 547 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
imation | +0.416 |
�� | +0.404 |
uthor | +0.384 |
obin | +0.372 |
ablishment | +0.371 |
Neg logit contributions | |
idas | -0.336 |
Smile | -0.332 |
Babel | -0.322 |
ラン | -0.318 |
tto | -0.318 |
Token | always |
Token ID | 1464 |
Feature activation | +9.60e-02 |
Pos logit contributions | |
imation | +0.346 |
�� | +0.336 |
uthor | +0.318 |
obin | +0.307 |
ablishment | +0.306 |
Neg logit contributions | |
idas | -0.334 |
Smile | -0.331 |
Babel | -0.322 |
ラン | -0.319 |
tto | -0.319 |
Token | being |
Token ID | 852 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
idas | +0.072 |
Smile | +0.072 |
Babel | +0.070 |
tto | +0.069 |
ラン | +0.069 |
Neg logit contributions | |
imation | -0.070 |
�� | -0.067 |
uthor | -0.064 |
obin | -0.061 |
ablishment | -0.061 |
Token | rigged |
Token ID | 31043 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
imation | +0.916 |
�� | +0.886 |
uthor | +0.834 |
obin | +0.803 |
ablishment | +0.798 |
Neg logit contributions | |
idas | -1.040 |
Smile | -1.031 |
Babel | -1.004 |
ラン | -0.995 |
tto | -0.994 |
Token | by |
Token ID | 416 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
imation | +3.725 |
�� | +3.582 |
uthor | +3.444 |
obin | +3.330 |
usion | +3.308 |
Neg logit contributions | |
idas | -3.578 |
Smile | -3.547 |
ラン | -3.471 |
Babel | -3.463 |
blush | -3.398 |
Token | cl |
Token ID | 537 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
idas | +0.316 |
Smile | +0.315 |
Babel | +0.305 |
blush | +0.300 |
tto | +0.300 |
Neg logit contributions | |
imation | -0.384 |
�� | -0.374 |
uthor | -0.354 |
obin | -0.343 |
ablishment | -0.342 |
Token | iques |
Token ID | 6368 |
Feature activation | -1.81e-03 |
Pos logit contributions | |
idas | +0.414 |
Smile | +0.407 |
Babel | +0.395 |
tto | +0.392 |
blush | +0.389 |
Neg logit contributions | |
imation | -0.401 |
�� | -0.397 |
uthor | -0.369 |
obin | -0.355 |
ablishment | -0.352 |
Token | of |
Token ID | 286 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
imation | +0.001 |
�� | +0.001 |
uthor | +0.001 |
obin | +0.001 |
ablishment | +0.001 |
Neg logit contributions | |
idas | -0.001 |
Smile | -0.001 |
Babel | -0.001 |
tto | -0.001 |
ラン | -0.001 |
Token | el |
Token ID | 1288 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Smile | +0.050 |
idas | +0.050 |
Babel | +0.048 |
blush | +0.047 |
ラン | +0.047 |
Neg logit contributions | |
imation | -0.065 |
�� | -0.063 |
uthor | -0.060 |
obin | -0.058 |
ablishment | -0.058 |
Token | out |
Token ID | 503 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
imation | +0.832 |
�� | +0.814 |
uthor | +0.781 |
obin | +0.761 |
ablishment | +0.757 |
Neg logit contributions | |
idas | -0.420 |
Smile | -0.412 |
Babel | -0.396 |
ラン | -0.392 |
tto | -0.391 |
Token | on |
Token ID | 319 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
imation | +0.465 |
�� | +0.452 |
uthor | +0.429 |
obin | +0.415 |
ablishment | +0.413 |
Neg logit contributions | |
idas | -0.415 |
Smile | -0.410 |
Babel | -0.398 |
ラン | -0.395 |
tto | -0.394 |
Token | the |
Token ID | 262 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
idas | +0.515 |
Smile | +0.511 |
Babel | +0.494 |
tto | +0.487 |
blush | +0.487 |
Neg logit contributions | |
imation | -0.675 |
�� | -0.657 |
uthor | -0.626 |
obin | -0.606 |
ablishment | -0.604 |
Token | gadgets |
Token ID | 35281 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
idas | +0.251 |
Smile | +0.248 |
Babel | +0.240 |
ラン | +0.237 |
tto | +0.237 |
Neg logit contributions | |
imation | -0.344 |
�� | -0.334 |
uthor | -0.319 |
obin | -0.309 |
ablishment | -0.308 |
Token | of |
Token ID | 286 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
imation | +1.962 |
�� | +1.898 |
uthor | +1.801 |
obin | +1.745 |
ablishment | +1.740 |
Neg logit contributions | |
idas | -1.751 |
Smile | -1.738 |
Babel | -1.685 |
ラン | -1.684 |
tto | -1.676 |
Token | Silicon |
Token ID | 18210 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
imation | +0.188 |
�� | +0.183 |
uthor | +0.174 |
obin | +0.168 |
ablishment | +0.168 |
Neg logit contributions | |
idas | -0.144 |
Smile | -0.143 |
Babel | -0.139 |
tto | -0.137 |
ラン | -0.137 |
Token | Valley |
Token ID | 6916 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
imation | +3.459 |
�� | +3.317 |
uthor | +3.151 |
obin | +3.108 |
usion | +3.106 |
Neg logit contributions | |
idas | -3.652 |
ラン | -3.590 |
Smile | -3.549 |
tto | -3.518 |
blush | -3.499 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
imation | +0.544 |
�� | +0.530 |
uthor | +0.504 |
obin | +0.488 |
ablishment | +0.486 |
Neg logit contributions | |
idas | -0.450 |
Smile | -0.444 |
Babel | -0.431 |
ラン | -0.428 |
tto | -0.426 |
Token | may |
Token ID | 743 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
idas | +0.078 |
Smile | +0.077 |
Babel | +0.075 |
tto | +0.074 |
ラン | +0.074 |
Neg logit contributions | |
imation | -0.102 |
�� | -0.100 |
uthor | -0.095 |
obin | -0.092 |
ablishment | -0.092 |
Token | prefer |
Token ID | 4702 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
imation | +0.726 |
�� | +0.699 |
uthor | +0.670 |
obin | +0.653 |
usion | +0.648 |
Neg logit contributions | |
idas | -0.559 |
Smile | -0.553 |
ラン | -0.538 |
Babel | -0.538 |
tto | -0.527 |
Token | the |
Token ID | 262 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
imation | +1.019 |
�� | +0.994 |
uthor | +0.944 |
obin | +0.915 |
ablishment | +0.912 |
Neg logit contributions | |
idas | -0.795 |
Smile | -0.786 |
Babel | -0.762 |
ラン | -0.756 |
tto | -0.752 |
Token | me |
Token ID | 502 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
idas | +1.526 |
Smile | +1.514 |
Babel | +1.463 |
blush | +1.421 |
ラン | +1.420 |
Neg logit contributions | |
imation | -2.482 |
�� | -2.421 |
uthor | -2.325 |
obin | -2.250 |
ablishment | -2.249 |
Token | later |
Token ID | 1568 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
idas | +0.877 |
Smile | +0.871 |
Babel | +0.840 |
tto | +0.829 |
blush | +0.828 |
Neg logit contributions | |
imation | -1.268 |
�� | -1.242 |
uthor | -1.186 |
ablishment | -1.150 |
obin | -1.149 |
Token | . |
Token ID | 13 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
idas | +0.894 |
Smile | +0.889 |
Babel | +0.859 |
tto | +0.849 |
blush | +0.847 |
Neg logit contributions | |
imation | -1.095 |
�� | -1.075 |
uthor | -1.019 |
ablishment | -0.985 |
obin | -0.985 |
Token |
|
Token ID | 198 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
idas | +0.309 |
Smile | +0.308 |
Babel | +0.298 |
tto | +0.294 |
ラン | +0.294 |
Neg logit contributions | |
imation | -0.328 |
�� | -0.319 |
uthor | -0.303 |
obin | -0.292 |
ablishment | -0.291 |
Token |
|
Token ID | 198 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
imation | +0.506 |
�� | +0.491 |
uthor | +0.466 |
obin | +0.451 |
ablishment | +0.449 |
Neg logit contributions | |
idas | -0.436 |
Smile | -0.432 |
Babel | -0.419 |
ラン | -0.415 |
tto | -0.415 |
Token | Rated |
Token ID | 15322 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
imation | +0.041 |
�� | +0.039 |
uthor | +0.037 |
obin | +0.035 |
ablishment | +0.035 |
Neg logit contributions | |
idas | -0.055 |
Smile | -0.054 |
Babel | -0.053 |
ラン | -0.052 |
tto | -0.052 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
imation | +2.572 |
�� | +2.493 |
uthor | +2.307 |
usion | +2.239 |
obin | +2.197 |
Neg logit contributions | |
idas | -3.391 |
Smile | -3.316 |
ラン | -3.272 |
tto | -3.253 |
Babel | -3.223 |
Token | out |
Token ID | 503 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
imation | +0.155 |
�� | +0.151 |
uthor | +0.144 |
obin | +0.141 |
usion | +0.140 |
Neg logit contributions | |
idas | -0.079 |
Smile | -0.078 |
Babel | -0.075 |
tto | -0.074 |
ラン | -0.074 |
Token | of |
Token ID | 286 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
imation | +0.459 |
�� | +0.437 |
uthor | +0.414 |
obin | +0.405 |
usion | +0.404 |
Neg logit contributions | |
idas | -0.417 |
Smile | -0.414 |
Babel | -0.404 |
ラン | -0.402 |
blush | -0.401 |
Token | 5 |
Token ID | 642 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
idas | +0.213 |
Smile | +0.211 |
Babel | +0.205 |
ラン | +0.204 |
tto | +0.204 |
Neg logit contributions | |
imation | -0.185 |
�� | -0.178 |
uthor | -0.168 |
obin | -0.162 |
usion | -0.160 |
Token | by |
Token ID | 416 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
imation | +0.013 |
�� | +0.013 |
uthor | +0.012 |
obin | +0.012 |
usion | +0.012 |
Neg logit contributions | |
idas | -0.014 |
Smile | -0.013 |
Babel | -0.013 |
ラン | -0.013 |
blush | -0.013 |
Token | shall |
Token ID | 2236 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
imation | +0.896 |
�� | +0.869 |
uthor | +0.825 |
obin | +0.796 |
ablishment | +0.794 |
Neg logit contributions | |
idas | -0.821 |
Smile | -0.813 |
Babel | -0.790 |
ラン | -0.784 |
tto | -0.782 |
Token | be |
Token ID | 307 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
imation | +0.926 |
�� | +0.892 |
uthor | +0.854 |
obin | +0.825 |
ablishment | +0.822 |
Neg logit contributions | |
idas | -0.755 |
Smile | -0.742 |
ラン | -0.729 |
Babel | -0.722 |
tto | -0.716 |
Token | entitled |
Token ID | 9080 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
imation | +1.448 |
�� | +1.412 |
uthor | +1.328 |
obin | +1.276 |
ablishment | +1.266 |
Neg logit contributions | |
idas | -1.596 |
Smile | -1.586 |
Babel | -1.543 |
ラン | -1.536 |
tto | -1.534 |
Token | to |
Token ID | 284 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
imation | +1.601 |
�� | +1.557 |
uthor | +1.483 |
ablishment | +1.426 |
obin | +1.426 |
Neg logit contributions | |
idas | -1.426 |
Smile | -1.410 |
Babel | -1.362 |
ラン | -1.362 |
tto | -1.348 |
Token | all |
Token ID | 477 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
imation | +0.977 |
�� | +0.942 |
uthor | +0.906 |
obin | +0.872 |
ablishment | +0.869 |
Neg logit contributions | |
idas | -0.804 |
Smile | -0.790 |
ラン | -0.771 |
tto | -0.765 |
Babel | -0.764 |
Token | Priv |
Token ID | 9243 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
imation | +2.380 |
�� | +2.307 |
uthor | +2.210 |
usion | +2.124 |
obin | +2.121 |
Neg logit contributions | |
idas | -2.123 |
Smile | -2.085 |
ラン | -2.031 |
tto | -2.017 |
Babel | -2.011 |
Token | ile |
Token ID | 576 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
imation | +3.794 |
�� | +3.521 |
uthor | +3.462 |
obin | +3.370 |
usion | +3.338 |
Neg logit contributions | |
Smile | -3.129 |
idas | -3.101 |
blush | -3.052 |
Babel | -3.035 |
ラン | -3.034 |
Token | ges |
Token ID | 3212 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
imation | +0.302 |
�� | +0.294 |
uthor | +0.281 |
obin | +0.272 |
ablishment | +0.271 |
Neg logit contributions | |
idas | -0.216 |
Smile | -0.214 |
Babel | -0.207 |
tto | -0.204 |
ラン | -0.204 |
Token | and |
Token ID | 290 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
imation | +1.264 |
�� | +1.230 |
uthor | +1.167 |
obin | +1.133 |
ablishment | +1.126 |
Neg logit contributions | |
idas | -1.031 |
Smile | -1.022 |
Babel | -0.991 |
tto | -0.978 |
ラン | -0.978 |
Token | Immun |
Token ID | 25445 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
imation | +0.021 |
�� | +0.020 |
uthor | +0.018 |
obin | +0.017 |
vier | +0.017 |
Neg logit contributions | |
idas | -0.033 |
Smile | -0.033 |
Babel | -0.033 |
tto | -0.032 |
ラン | -0.032 |
Token | ities |
Token ID | 871 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
imation | +1.154 |
�� | +1.115 |
uthor | +1.064 |
obin | +1.031 |
ablishment | +1.023 |
Neg logit contributions | |
idas | -0.983 |
Smile | -0.978 |
Babel | -0.950 |
ラン | -0.939 |
tto | -0.938 |
Token | and |
Token ID | 290 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
idas | +0.080 |
Smile | +0.079 |
Babel | +0.076 |
ラン | +0.076 |
tto | +0.075 |
Neg logit contributions | |
imation | -0.095 |
�� | -0.092 |
uthor | -0.088 |
obin | -0.085 |
ablishment | -0.085 |
Token | he |
Token ID | 339 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
imation | +0.081 |
�� | +0.078 |
uthor | +0.074 |
obin | +0.072 |
ablishment | +0.071 |
Neg logit contributions | |
idas | -0.075 |
Smile | -0.075 |
Babel | -0.073 |
tto | -0.072 |
ラン | -0.072 |
Token | was |
Token ID | 373 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
idas | +0.334 |
Smile | +0.330 |
Babel | +0.321 |
tto | +0.317 |
blush | +0.317 |
Neg logit contributions | |
imation | -0.381 |
�� | -0.371 |
uthor | -0.352 |
obin | -0.340 |
ablishment | -0.340 |
Token | handcuffed |
Token ID | 41529 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
idas | +0.759 |
Smile | +0.747 |
Babel | +0.731 |
tto | +0.722 |
blush | +0.722 |
Neg logit contributions | |
imation | -0.788 |
�� | -0.759 |
uthor | -0.722 |
ablishment | -0.700 |
obin | -0.696 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
imation | +1.019 |
�� | +0.984 |
uthor | +0.932 |
obin | +0.909 |
usion | +0.903 |
Neg logit contributions | |
idas | -0.930 |
Smile | -0.926 |
ラン | -0.903 |
Babel | -0.897 |
tto | -0.878 |
Token | taken |
Token ID | 2077 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
imation | +0.103 |
�� | +0.100 |
uthor | +0.094 |
obin | +0.091 |
usion | +0.090 |
Neg logit contributions | |
idas | -0.113 |
Smile | -0.113 |
Babel | -0.109 |
ラン | -0.109 |
tto | -0.109 |
Token | away |
Token ID | 1497 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
imation | +3.409 |
�� | +3.362 |
uthor | +3.116 |
usion | +3.055 |
obin | +3.052 |
Neg logit contributions | |
Smile | -3.548 |
idas | -3.544 |
ラン | -3.486 |
Babel | -3.388 |
tto | -3.280 |
Token | . |
Token ID | 13 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
imation | +1.854 |
�� | +1.784 |
uthor | +1.687 |
obin | +1.639 |
usion | +1.632 |
Neg logit contributions | |
idas | -1.803 |
Smile | -1.790 |
ラン | -1.754 |
Babel | -1.733 |
tto | -1.703 |
Token | The |
Token ID | 383 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
imation | +0.259 |
�� | +0.252 |
uthor | +0.239 |
obin | +0.231 |
ablishment | +0.231 |
Neg logit contributions | |
idas | -0.234 |
Smile | -0.230 |
Babel | -0.224 |
blush | -0.222 |
ラン | -0.222 |
Token | king |
Token ID | 5822 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
imation | +0.373 |
�� | +0.363 |
uthor | +0.347 |
obin | +0.337 |
ablishment | +0.335 |
Neg logit contributions | |
idas | -0.251 |
Smile | -0.248 |
Babel | -0.239 |
ラン | -0.237 |
tto | -0.236 |
Token | turned |
Token ID | 2900 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
imation | +2.696 |
�� | +2.606 |
uthor | +2.491 |
obin | +2.411 |
usion | +2.394 |
Neg logit contributions | |
idas | -2.331 |
Smile | -2.327 |
ラン | -2.275 |
Babel | -2.251 |
tto | -2.227 |